diff options
1018 files changed, 38442 insertions, 23177 deletions
diff --git a/.gitignore b/.gitignore index b93fb7eff942..946c7ec5c922 100644 --- a/.gitignore +++ b/.gitignore @@ -25,6 +25,7 @@ *.elf *.bin *.gz +*.bz2 *.lzma *.patch *.gcno diff --git a/Documentation/DocBook/tracepoint.tmpl b/Documentation/DocBook/tracepoint.tmpl index b0756d0fd579..8bca1d5cec09 100644 --- a/Documentation/DocBook/tracepoint.tmpl +++ b/Documentation/DocBook/tracepoint.tmpl @@ -86,4 +86,9 @@ !Iinclude/trace/events/irq.h </chapter> + <chapter id="signal"> + <title>SIGNAL</title> +!Iinclude/trace/events/signal.h + </chapter> + </book> diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt index 187bbf10c923..8608fd85e921 100644 --- a/Documentation/RCU/trace.txt +++ b/Documentation/RCU/trace.txt @@ -1,185 +1,10 @@ CONFIG_RCU_TRACE debugfs Files and Formats -The rcupreempt and rcutree implementations of RCU provide debugfs trace -output that summarizes counters and state. This information is useful for -debugging RCU itself, and can sometimes also help to debug abuses of RCU. -Note that the rcuclassic implementation of RCU does not provide debugfs -trace output. - -The following sections describe the debugfs files and formats for -preemptable RCU (rcupreempt) and hierarchical RCU (rcutree). - - -Preemptable RCU debugfs Files and Formats - -This implementation of RCU provides three debugfs files under the -top-level directory RCU: rcu/rcuctrs (which displays the per-CPU -counters used by preemptable RCU) rcu/rcugp (which displays grace-period -counters), and rcu/rcustats (which internal counters for debugging RCU). - -The output of "cat rcu/rcuctrs" looks as follows: - -CPU last cur F M - 0 5 -5 0 0 - 1 -1 0 0 0 - 2 0 1 0 0 - 3 0 1 0 0 - 4 0 1 0 0 - 5 0 1 0 0 - 6 0 2 0 0 - 7 0 -1 0 0 - 8 0 1 0 0 -ggp = 26226, state = waitzero - -The per-CPU fields are as follows: - -o "CPU" gives the CPU number. Offline CPUs are not displayed. - -o "last" gives the value of the counter that is being decremented - for the current grace period phase. In the example above, - the counters sum to 4, indicating that there are still four - RCU read-side critical sections still running that started - before the last counter flip. - -o "cur" gives the value of the counter that is currently being - both incremented (by rcu_read_lock()) and decremented (by - rcu_read_unlock()). In the example above, the counters sum to - 1, indicating that there is only one RCU read-side critical section - still running that started after the last counter flip. - -o "F" indicates whether RCU is waiting for this CPU to acknowledge - a counter flip. In the above example, RCU is not waiting on any, - which is consistent with the state being "waitzero" rather than - "waitack". - -o "M" indicates whether RCU is waiting for this CPU to execute a - memory barrier. In the above example, RCU is not waiting on any, - which is consistent with the state being "waitzero" rather than - "waitmb". - -o "ggp" is the global grace-period counter. - -o "state" is the RCU state, which can be one of the following: - - o "idle": there is no grace period in progress. - - o "waitack": RCU just incremented the global grace-period - counter, which has the effect of reversing the roles of - the "last" and "cur" counters above, and is waiting for - all the CPUs to acknowledge the flip. Once the flip has - been acknowledged, CPUs will no longer be incrementing - what are now the "last" counters, so that their sum will - decrease monotonically down to zero. - - o "waitzero": RCU is waiting for the sum of the "last" counters - to decrease to zero. - - o "waitmb": RCU is waiting for each CPU to execute a memory - barrier, which ensures that instructions from a given CPU's - last RCU read-side critical section cannot be reordered - with instructions following the memory-barrier instruction. - -The output of "cat rcu/rcugp" looks as follows: - -oldggp=48870 newggp=48873 - -Note that reading from this file provokes a synchronize_rcu(). The -"oldggp" value is that of "ggp" from rcu/rcuctrs above, taken before -executing the synchronize_rcu(), and the "newggp" value is also the -"ggp" value, but taken after the synchronize_rcu() command returns. - - -The output of "cat rcu/rcugp" looks as follows: - -na=1337955 nl=40 wa=1337915 wl=44 da=1337871 dl=0 dr=1337871 di=1337871 -1=50989 e1=6138 i1=49722 ie1=82 g1=49640 a1=315203 ae1=265563 a2=49640 -z1=1401244 ze1=1351605 z2=49639 m1=5661253 me1=5611614 m2=49639 - -These are counters tracking internal preemptable-RCU events, however, -some of them may be useful for debugging algorithms using RCU. In -particular, the "nl", "wl", and "dl" values track the number of RCU -callbacks in various states. The fields are as follows: - -o "na" is the total number of RCU callbacks that have been enqueued - since boot. - -o "nl" is the number of RCU callbacks waiting for the previous - grace period to end so that they can start waiting on the next - grace period. - -o "wa" is the total number of RCU callbacks that have started waiting - for a grace period since boot. "na" should be roughly equal to - "nl" plus "wa". - -o "wl" is the number of RCU callbacks currently waiting for their - grace period to end. - -o "da" is the total number of RCU callbacks whose grace periods - have completed since boot. "wa" should be roughly equal to - "wl" plus "da". - -o "dr" is the total number of RCU callbacks that have been removed - from the list of callbacks ready to invoke. "dr" should be roughly - equal to "da". - -o "di" is the total number of RCU callbacks that have been invoked - since boot. "di" should be roughly equal to "da", though some - early versions of preemptable RCU had a bug so that only the - last CPU's count of invocations was displayed, rather than the - sum of all CPU's counts. - -o "1" is the number of calls to rcu_try_flip(). This should be - roughly equal to the sum of "e1", "i1", "a1", "z1", and "m1" - described below. In other words, the number of times that - the state machine is visited should be equal to the sum of the - number of times that each state is visited plus the number of - times that the state-machine lock acquisition failed. - -o "e1" is the number of times that rcu_try_flip() was unable to - acquire the fliplock. - -o "i1" is the number of calls to rcu_try_flip_idle(). - -o "ie1" is the number of times rcu_try_flip_idle() exited early - due to the calling CPU having no work for RCU. - -o "g1" is the number of times that rcu_try_flip_idle() decided - to start a new grace period. "i1" should be roughly equal to - "ie1" plus "g1". - -o "a1" is the number of calls to rcu_try_flip_waitack(). - -o "ae1" is the number of times that rcu_try_flip_waitack() found - that at least one CPU had not yet acknowledge the new grace period - (AKA "counter flip"). - -o "a2" is the number of time rcu_try_flip_waitack() found that - all CPUs had acknowledged. "a1" should be roughly equal to - "ae1" plus "a2". (This particular output was collected on - a 128-CPU machine, hence the smaller-than-usual fraction of - calls to rcu_try_flip_waitack() finding all CPUs having already - acknowledged.) - -o "z1" is the number of calls to rcu_try_flip_waitzero(). - -o "ze1" is the number of times that rcu_try_flip_waitzero() found - that not all of the old RCU read-side critical sections had - completed. - -o "z2" is the number of times that rcu_try_flip_waitzero() finds - the sum of the counters equal to zero, in other words, that - all of the old RCU read-side critical sections had completed. - The value of "z1" should be roughly equal to "ze1" plus - "z2". - -o "m1" is the number of calls to rcu_try_flip_waitmb(). - -o "me1" is the number of times that rcu_try_flip_waitmb() finds - that at least one CPU has not yet executed a memory barrier. - -o "m2" is the number of times that rcu_try_flip_waitmb() finds that - all CPUs have executed a memory barrier. +The rcutree implementation of RCU provides debugfs trace output that +summarizes counters and state. This information is useful for debugging +RCU itself, and can sometimes also help to debug abuses of RCU. +The following sections describe the debugfs files and formats. Hierarchical RCU debugfs Files and Formats @@ -210,9 +35,10 @@ rcu_bh: 6 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=859/1 dn=0 df=15 of=0 ri=0 ql=0 b=10 7 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=3761/1 dn=0 df=15 of=0 ri=0 ql=0 b=10 -The first section lists the rcu_data structures for rcu, the second for -rcu_bh. Each section has one line per CPU, or eight for this 8-CPU system. -The fields are as follows: +The first section lists the rcu_data structures for rcu_sched, the second +for rcu_bh. Note that CONFIG_TREE_PREEMPT_RCU kernels will have an +additional section for rcu_preempt. Each section has one line per CPU, +or eight for this 8-CPU system. The fields are as follows: o The number at the beginning of each line is the CPU number. CPUs numbers followed by an exclamation mark are offline, @@ -223,9 +49,9 @@ o The number at the beginning of each line is the CPU number. o "c" is the count of grace periods that this CPU believes have completed. CPUs in dynticks idle mode may lag quite a ways - behind, for example, CPU 4 under "rcu" above, which has slept - through the past 25 RCU grace periods. It is not unusual to - see CPUs lagging by thousands of grace periods. + behind, for example, CPU 4 under "rcu_sched" above, which has + slept through the past 25 RCU grace periods. It is not unusual + to see CPUs lagging by thousands of grace periods. o "g" is the count of grace periods that this CPU believes have started. Again, CPUs in dynticks idle mode may lag behind. @@ -308,8 +134,10 @@ The output of "cat rcu/rcugp" looks as follows: rcu_sched: completed=33062 gpnum=33063 rcu_bh: completed=464 gpnum=464 -Again, this output is for both "rcu" and "rcu_bh". The fields are -taken from the rcu_state structure, and are as follows: +Again, this output is for both "rcu_sched" and "rcu_bh". Note that +kernels built with CONFIG_TREE_PREEMPT_RCU will have an additional +"rcu_preempt" line. The fields are taken from the rcu_state structure, +and are as follows: o "completed" is the number of grace periods that have completed. It is comparable to the "c" field from rcu/rcudata in that a @@ -324,23 +152,24 @@ o "gpnum" is the number of grace periods that have started. It is If these two fields are equal (as they are for "rcu_bh" above), then there is no grace period in progress, in other words, RCU is idle. On the other hand, if the two fields differ (as they - do for "rcu" above), then an RCU grace period is in progress. + do for "rcu_sched" above), then an RCU grace period is in progress. The output of "cat rcu/rcuhier" looks as follows, with very long lines: -c=6902 g=6903 s=2 jfq=3 j=72c7 nfqs=13142/nfqsng=0(13142) fqlh=6 -1/1 0:127 ^0 -3/3 0:35 ^0 0/0 36:71 ^1 0/0 72:107 ^2 0/0 108:127 ^3 -3/3f 0:5 ^0 2/3 6:11 ^1 0/0 12:17 ^2 0/0 18:23 ^3 0/0 24:29 ^4 0/0 30:35 ^5 0/0 36:41 ^0 0/0 42:47 ^1 0/0 48:53 ^2 0/0 54:59 ^3 0/0 60:65 ^4 0/0 66:71 ^5 0/0 72:77 ^0 0/0 78:83 ^1 0/0 84:89 ^2 0/0 90:95 ^3 0/0 96:101 ^4 0/0 102:107 ^5 0/0 108:113 ^0 0/0 114:119 ^1 0/0 120:125 ^2 0/0 126:127 ^3 +c=6902 g=6903 s=2 jfq=3 j=72c7 nfqs=13142/nfqsng=0(13142) fqlh=6 oqlen=0 +1/1 .>. 0:127 ^0 +3/3 .>. 0:35 ^0 0/0 .>. 36:71 ^1 0/0 .>. 72:107 ^2 0/0 .>. 108:127 ^3 +3/3f .>. 0:5 ^0 2/3 .>. 6:11 ^1 0/0 .>. 12:17 ^2 0/0 .>. 18:23 ^3 0/0 .>. 24:29 ^4 0/0 .>. 30:35 ^5 0/0 .>. 36:41 ^0 0/0 .>. 42:47 ^1 0/0 .>. 48:53 ^2 0/0 .>. 54:59 ^3 0/0 .>. 60:65 ^4 0/0 .>. 66:71 ^5 0/0 .>. 72:77 ^0 0/0 .>. 78:83 ^1 0/0 .>. 84:89 ^2 0/0 .>. 90:95 ^3 0/0 .>. 96:101 ^4 0/0 .>. 102:107 ^5 0/0 .>. 108:113 ^0 0/0 .>. 114:119 ^1 0/0 .>. 120:125 ^2 0/0 .>. 126:127 ^3 rcu_bh: -c=-226 g=-226 s=1 jfq=-5701 j=72c7 nfqs=88/nfqsng=0(88) fqlh=0 -0/1 0:127 ^0 -0/3 0:35 ^0 0/0 36:71 ^1 0/0 72:107 ^2 0/0 108:127 ^3 -0/3f 0:5 ^0 0/3 6:11 ^1 0/0 12:17 ^2 0/0 18:23 ^3 0/0 24:29 ^4 0/0 30:35 ^5 0/0 36:41 ^0 0/0 42:47 ^1 0/0 48:53 ^2 0/0 54:59 ^3 0/0 60:65 ^4 0/0 66:71 ^5 0/0 72:77 ^0 0/0 78:83 ^1 0/0 84:89 ^2 0/0 90:95 ^3 0/0 96:101 ^4 0/0 102:107 ^5 0/0 108:113 ^0 0/0 114:119 ^1 0/0 120:125 ^2 0/0 126:127 ^3 +c=-226 g=-226 s=1 jfq=-5701 j=72c7 nfqs=88/nfqsng=0(88) fqlh=0 oqlen=0 +0/1 .>. 0:127 ^0 +0/3 .>. 0:35 ^0 0/0 .>. 36:71 ^1 0/0 .>. 72:107 ^2 0/0 .>. 108:127 ^3 +0/3f .>. 0:5 ^0 0/3 .>. 6:11 ^1 0/0 .>. 12:17 ^2 0/0 .>. 18:23 ^3 0/0 .>. 24:29 ^4 0/0 .>. 30:35 ^5 0/0 .>. 36:41 ^0 0/0 .>. 42:47 ^1 0/0 .>. 48:53 ^2 0/0 .>. 54:59 ^3 0/0 .>. 60:65 ^4 0/0 .>. 66:71 ^5 0/0 .>. 72:77 ^0 0/0 .>. 78:83 ^1 0/0 .>. 84:89 ^2 0/0 .>. 90:95 ^3 0/0 .>. 96:101 ^4 0/0 .>. 102:107 ^5 0/0 .>. 108:113 ^0 0/0 .>. 114:119 ^1 0/0 .>. 120:125 ^2 0/0 .>. 126:127 ^3 -This is once again split into "rcu" and "rcu_bh" portions. The fields are -as follows: +This is once again split into "rcu_sched" and "rcu_bh" portions, +and CONFIG_TREE_PREEMPT_RCU kernels will again have an additional +"rcu_preempt" section. The fields are as follows: o "c" is exactly the same as "completed" under rcu/rcugp. @@ -372,6 +201,11 @@ o "fqlh" is the number of calls to force_quiescent_state() that exited immediately (without even being counted in nfqs above) due to contention on ->fqslock. +o "oqlen" is the number of callbacks on the "orphan" callback + list. RCU callbacks are placed on this list by CPUs going + offline, and are "adopted" either by the CPU helping the outgoing + CPU or by the next rcu_barrier*() call, whichever comes first. + o Each element of the form "1/1 0:127 ^0" represents one struct rcu_node. Each line represents one level of the hierarchy, from root to leaves. It is best to think of the rcu_data structures @@ -379,7 +213,7 @@ o Each element of the form "1/1 0:127 ^0" represents one struct might be either one, two, or three levels of rcu_node structures, depending on the relationship between CONFIG_RCU_FANOUT and CONFIG_NR_CPUS. - + o The numbers separated by the "/" are the qsmask followed by the qsmaskinit. The qsmask will have one bit set for each entity in the next lower level that @@ -389,10 +223,19 @@ o Each element of the form "1/1 0:127 ^0" represents one struct The value of qsmaskinit is assigned to that of qsmask at the beginning of each grace period. - For example, for "rcu", the qsmask of the first entry - of the lowest level is 0x14, meaning that we are still - waiting for CPUs 2 and 4 to check in for the current - grace period. + For example, for "rcu_sched", the qsmask of the first + entry of the lowest level is 0x14, meaning that we + are still waiting for CPUs 2 and 4 to check in for the + current grace period. + + o The characters separated by the ">" indicate the state + of the blocked-tasks lists. A "T" preceding the ">" + indicates that at least one task blocked in an RCU + read-side critical section blocks the current grace + period, while a "." preceding the ">" indicates otherwise. + The character following the ">" indicates similarly for + the next grace period. A "T" should appear in this + field only for rcu-preempt. o The numbers separated by the ":" are the range of CPUs served by this struct rcu_node. This can be helpful @@ -431,8 +274,9 @@ rcu_bh: 6 np=120834 qsp=9902 cbr=0 cng=0 gpc=6 gps=3 nf=2 nn=110921 7 np=144888 qsp=26336 cbr=0 cng=0 gpc=8 gps=2 nf=0 nn=118542 -As always, this is once again split into "rcu" and "rcu_bh" portions. -The fields are as follows: +As always, this is once again split into "rcu_sched" and "rcu_bh" +portions, with CONFIG_TREE_PREEMPT_RCU kernels having an additional +"rcu_preempt" section. The fields are as follows: o "np" is the number of times that __rcu_pending() has been invoked for the corresponding flavor of RCU. diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt index e41a7fecf0d3..d542ca243b80 100644 --- a/Documentation/RCU/whatisRCU.txt +++ b/Documentation/RCU/whatisRCU.txt @@ -830,7 +830,7 @@ sched: Critical sections Grace period Barrier SRCU: Critical sections Grace period Barrier srcu_read_lock synchronize_srcu N/A - srcu_read_unlock + srcu_read_unlock synchronize_srcu_expedited SRCU: Initialization/cleanup init_srcu_struct diff --git a/Documentation/dontdiff b/Documentation/dontdiff index e1efc400bed6..e151b2a36267 100644 --- a/Documentation/dontdiff +++ b/Documentation/dontdiff @@ -65,6 +65,7 @@ aicdb.h* asm-offsets.h asm_offsets.h autoconf.h* +av_permissions.h bbootsect bin2c binkernel.spec @@ -95,12 +96,14 @@ docproc elf2ecoff elfconfig.h* fixdep +flask.h fore200e_mkfirm fore200e_pca_fw.c* gconf gen-devlist gen_crc32table gen_init_cpio +genheaders genksyms *_gray256.c ihex2fw diff --git a/Documentation/fb/framebuffer.txt b/Documentation/fb/framebuffer.txt index b3e3a0356839..fe79e3c8847d 100644 --- a/Documentation/fb/framebuffer.txt +++ b/Documentation/fb/framebuffer.txt @@ -312,10 +312,8 @@ and to the following documentation: 8. Mailing list --------------- -There are several frame buffer device related mailing lists at SourceForge: - - linux-fbdev-announce@lists.sourceforge.net, for announcements, - - linux-fbdev-user@lists.sourceforge.net, for generic user support, - - linux-fbdev-devel@lists.sourceforge.net, for project developers. +There is a frame buffer device related mailing list at kernel.org: +linux-fbdev@vger.kernel.org. Point your web browser to http://sourceforge.net/projects/linux-fbdev/ for subscription information and archive browsing. diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index bc693fffabe0..f613df8ec7bf 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -6,6 +6,21 @@ be removed from this file. --------------------------- +What: USER_SCHED +When: 2.6.34 + +Why: USER_SCHED was implemented as a proof of concept for group scheduling. + The effect of USER_SCHED can already be achieved from userspace with + the help of libcgroup. The removal of USER_SCHED will also simplify + the scheduler code with the removal of one major ifdef. There are also + issues USER_SCHED has with USER_NS. A decision was taken not to fix + those and instead remove USER_SCHED. Also new group scheduling + features will not be implemented for USER_SCHED. + +Who: Dhaval Giani <dhaval@linux.vnet.ibm.com> + +--------------------------- + What: PRISM54 When: 2.6.34 diff --git a/Documentation/filesystems/caching/fscache.txt b/Documentation/filesystems/caching/fscache.txt index 9e94b9491d89..a91e2e2095b0 100644 --- a/Documentation/filesystems/caching/fscache.txt +++ b/Documentation/filesystems/caching/fscache.txt @@ -235,6 +235,7 @@ proc files. neg=N Number of negative lookups made pos=N Number of positive lookups made crt=N Number of objects created by lookup + tmo=N Number of lookups timed out and requeued Updates n=N Number of update cookie requests seen nul=N Number of upd reqs given a NULL parent run=N Number of upd reqs granted CPU time @@ -250,8 +251,10 @@ proc files. ok=N Number of successful alloc reqs wt=N Number of alloc reqs that waited on lookup completion nbf=N Number of alloc reqs rejected -ENOBUFS + int=N Number of alloc reqs aborted -ERESTARTSYS ops=N Number of alloc reqs submitted owt=N Number of alloc reqs waited for CPU time + abt=N Number of alloc reqs aborted due to object death Retrvls n=N Number of retrieval (read) requests seen ok=N Number of successful retr reqs wt=N Number of retr reqs that waited on lookup completion @@ -261,6 +264,7 @@ proc files. oom=N Number of retr reqs failed -ENOMEM ops=N Number of retr reqs submitted owt=N Number of retr reqs waited for CPU time + abt=N Number of retr reqs aborted due to object death Stores n=N Number of storage (write) requests seen ok=N Number of successful store reqs agn=N Number of store reqs on a page already pending storage @@ -268,12 +272,37 @@ proc files. oom=N Number of store reqs failed -ENOMEM ops=N Number of store reqs submitted run=N Number of store reqs granted CPU time + pgs=N Number of pages given store req processing time + rxd=N Number of store reqs deleted from tracking tree + olm=N Number of store reqs over store limit + VmScan nos=N Number of release reqs against pages with no pending store + gon=N Number of release reqs against pages stored by time lock granted + bsy=N Number of release reqs ignored due to in-progress store + can=N Number of page stores cancelled due to release req Ops pend=N Number of times async ops added to pending queues run=N Number of times async ops given CPU time enq=N Number of times async ops queued for processing + can=N Number of async ops cancelled + rej=N Number of async ops rejected due to object lookup/create failure dfr=N Number of async ops queued for deferred release rel=N Number of async ops released gc=N Number of deferred-release async ops garbage collected + CacheOp alo=N Number of in-progress alloc_object() cache ops + luo=N Number of in-progress lookup_object() cache ops + luc=N Number of in-progress lookup_complete() cache ops + gro=N Number of in-progress grab_object() cache ops + upo=N Number of in-progress update_object() cache ops + dro=N Number of in-progress drop_object() cache ops + pto=N Number of in-progress put_object() cache ops + syn=N Number of in-progress sync_cache() cache ops + atc=N Number of in-progress attr_changed() cache ops + rap=N Number of in-progress read_or_alloc_page() cache ops + ras=N Number of in-progress read_or_alloc_pages() cache ops + alp=N Number of in-progress allocate_page() cache ops + als=N Number of in-progress allocate_pages() cache ops + wrp=N Number of in-progress write_page() cache ops + ucp=N Number of in-progress uncache_page() cache ops + dsp=N Number of in-progress dissociate_pages() cache ops (*) /proc/fs/fscache/histogram @@ -299,6 +328,87 @@ proc files. jiffy range covered, and the SECS field the equivalent number of seconds. +=========== +OBJECT LIST +=========== + +If CONFIG_FSCACHE_OBJECT_LIST is enabled, the FS-Cache facility will maintain a +list of all the objects currently allocated and allow them to be viewed +through: + + /proc/fs/fscache/objects + +This will look something like: + + [root@andromeda ~]# head /proc/fs/fscache/objects + OBJECT PARENT STAT CHLDN OPS OOP IPR EX READS EM EV F S | NETFS_COOKIE_DEF TY FL NETFS_DATA OBJECT_KEY, AUX_DATA + ======== ======== ==== ===== === === === == ===== == == = = | ================ == == ================ ================ + 17e4b 2 ACTV 0 0 0 0 0 0 7b 4 0 8 | NFS.fh DT 0 ffff88001dd82820 010006017edcf8bbc93b43298fdfbe71e50b57b13a172c0117f38472, e567634700000000000000000000000063f2404a000000000000000000000000c9030000000000000000000063f2404a + 1693a 2 ACTV 0 0 0 0 0 0 7b 4 0 8 | NFS.fh DT 0 ffff88002db23380 010006017edcf8bbc93b43298fdfbe71e50b57b1e0162c01a2df0ea6, 420ebc4a000000000000000000000000420ebc4a0000000000000000000000000e1801000000000000000000420ebc4a + +where the first set of columns before the '|' describe the object: + + COLUMN DESCRIPTION + ======= =============================================================== + OBJECT Object debugging ID (appears as OBJ%x in some debug messages) + PARENT Debugging ID of parent object + STAT Object state + CHLDN Number of child objects of this object + OPS Number of outstanding operations on this object + OOP Number of outstanding child object management operations + IPR + EX Number of outstanding exclusive operations + READS Number of outstanding read operations + EM Object's event mask + EV Events raised on this object + F Object flags + S Object slow-work work item flags + +and the second set of columns describe the object's cookie, if present: + + COLUMN DESCRIPTION + =============== ======================================================= + NETFS_COOKIE_DEF Name of netfs cookie definition + TY Cookie type (IX - index, DT - data, hex - special) + FL Cookie flags + NETFS_DATA Netfs private data stored in the cookie + OBJECT_KEY Object key } 1 column, with separating comma + AUX_DATA Object aux data } presence may be configured + +The data shown may be filtered by attaching the a key to an appropriate keyring +before viewing the file. Something like: + + keyctl add user fscache:objlist <restrictions> @s + +where <restrictions> are a selection of the following letters: + + K Show hexdump of object key (don't show if not given) + A Show hexdump of object aux data (don't show if not given) + +and the following paired letters: + + C Show objects that have a cookie + c Show objects that don't have a cookie + B Show objects that are busy + b Show objects that aren't busy + W Show objects that have pending writes + w Show objects that don't have pending writes + R Show objects that have outstanding reads + r Show objects that don't have outstanding reads + S Show objects that have slow work queued + s Show objects that don't have slow work queued + +If neither side of a letter pair is given, then both are implied. For example: + + keyctl add user fscache:objlist KB @s + +shows objects that are busy, and lists their object keys, but does not dump +their auxiliary data. It also implies "CcWwRrSs", but as 'B' is given, 'b' is +not implied. + +By default all objects and all fields will be shown. + + ========= DEBUGGING ========= diff --git a/Documentation/filesystems/caching/netfs-api.txt b/Documentation/filesystems/caching/netfs-api.txt index 2666b1ed5e9e..1902c57b72ef 100644 --- a/Documentation/filesystems/caching/netfs-api.txt +++ b/Documentation/filesystems/caching/netfs-api.txt @@ -641,7 +641,7 @@ data file must be retired (see the relinquish cookie function below). Furthermore, note that this does not cancel the asynchronous read or write operation started by the read/alloc and write functions, so the page -invalidation and release functions must use: +invalidation functions must use: bool fscache_check_page_write(struct fscache_cookie *cookie, struct page *page); @@ -654,6 +654,25 @@ to see if a page is being written to the cache, and: to wait for it to finish if it is. +When releasepage() is being implemented, a special FS-Cache function exists to +manage the heuristics of coping with vmscan trying to eject pages, which may +conflict with the cache trying to write pages to the cache (which may itself +need to allocate memory): + + bool fscache_maybe_release_page(struct fscache_cookie *cookie, + struct page *page, + gfp_t gfp); + +This takes the netfs cookie, and the page and gfp arguments as supplied to +releasepage(). It will return false if the page cannot be released yet for +some reason and if it returns true, the page has been uncached and can now be +released. + +To make a page available for release, this function may wait for an outstanding +storage request to complete, or it may attempt to cancel the storage request - +in which case the page will not be stored in the cache this time. + + ========================== INDEX AND DATA FILE UPDATE ========================== diff --git a/Documentation/filesystems/ocfs2.txt b/Documentation/filesystems/ocfs2.txt index c2a0871280a0..c58b9f5ba002 100644 --- a/Documentation/filesystems/ocfs2.txt +++ b/Documentation/filesystems/ocfs2.txt @@ -20,15 +20,16 @@ Lots of code taken from ext3 and other projects. Authors in alphabetical order: Joel Becker <joel.becker@oracle.com> Zach Brown <zach.brown@oracle.com> -Mark Fasheh <mark.fasheh@oracle.com> +Mark Fasheh <mfasheh@suse.com> Kurt Hackel <kurt.hackel@oracle.com> +Tao Ma <tao.ma@oracle.com> Sunil Mushran <sunil.mushran@oracle.com> Manish Singh <manish.singh@oracle.com> +Tiger Yang <tiger.yang@oracle.com> Caveats ======= Features which OCFS2 does not support yet: - - quotas - Directory change notification (F_NOTIFY) - Distributed Caching (F_SETLEASE/F_GETLEASE/break_lease) @@ -70,7 +71,6 @@ commit=nrsec (*) Ocfs2 can be told to sync all its data and metadata performance. localalloc=8(*) Allows custom localalloc size in MB. If the value is too large, the fs will silently revert it to the default. - Localalloc is not enabled for local mounts. localflocks This disables cluster aware flock. inode64 Indicates that Ocfs2 is allowed to create inodes at any location in the filesystem, including those which diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index 2c48f945546b..4af0018533f2 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -1072,7 +1072,8 @@ second). The meanings of the columns are as follows, from left to right: - irq: servicing interrupts - softirq: servicing softirqs - steal: involuntary wait -- guest: running a guest +- guest: running a normal guest +- guest_nice: running a niced guest The "intr" line gives counts of interrupts serviced since boot time, for each of the possible system interrupts. The first column is the total of all diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 9107b387e91f..fce5b5e516cc 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -85,7 +85,6 @@ parameter is applicable: PPT Parallel port support is enabled. PS2 Appropriate PS/2 support is enabled. RAM RAM disk support is enabled. - ROOTPLUG The example Root Plug LSM is enabled. S390 S390 architecture is enabled. SCSI Appropriate SCSI support is enabled. A lot of drivers has their options described inside of @@ -345,6 +344,15 @@ and is between 256 and 4096 characters. It is defined in the file Change the amount of debugging information output when initialising the APIC and IO-APIC components. + show_lapic= [APIC,X86] Advanced Programmable Interrupt Controller + Limit apic dumping. The parameter defines the maximal + number of local apics being dumped. Also it is possible + to set it to "all" by meaning -- no limit here. + Format: { 1 (default) | 2 | ... | all }. + The parameter valid if only apic=debug or + apic=verbose is specified. + Example: apic=debug show_lapic=all + apm= [APM] Advanced Power Management See header of arch/x86/kernel/apm_32.c. @@ -779,6 +787,13 @@ and is between 256 and 4096 characters. It is defined in the file by the set_ftrace_notrace file in the debugfs tracing directory. + ftrace_graph_filter=[function-list] + [FTRACE] Limit the top level callers functions traced + by the function graph tracer at boot up. + function-list is a comma separated list of functions + that can be changed at run time by the + set_graph_function file in the debugfs tracing directory. + gamecon.map[2|3]= [HW,JOY] Multisystem joystick and NES/SNES/PSX pad support via parallel port (up to 5 devices per port) @@ -2032,8 +2047,15 @@ and is between 256 and 4096 characters. It is defined in the file print-fatal-signals= [KNL] debug: print fatal signals - print-fatal-signals=1: print segfault info to - the kernel console. + + If enabled, warn about various signal handling + related application anomalies: too many signals, + too many POSIX.1 timers, fatal signals causing a + coredump - etc. + + If you hit the warning due to signal overflow, + you might want to try "ulimit -i unlimited". + default: off. printk.time= Show timing data prefixed to each printk message line @@ -2164,15 +2186,6 @@ and is between 256 and 4096 characters. It is defined in the file Useful for devices that are detected asynchronously (e.g. USB and MMC devices). - root_plug.vendor_id= - [ROOTPLUG] Override the default vendor ID - - root_plug.product_id= - [ROOTPLUG] Override the default product ID - - root_plug.debug= - [ROOTPLUG] Enable debugging output - rw [KNL] Mount root device read-write on boot S [KNL] Run init in single mode @@ -2182,6 +2195,8 @@ and is between 256 and 4096 characters. It is defined in the file sbni= [NET] Granch SBNI12 leased line adapter + sched_debug [KNL] Enables verbose scheduler debug messages. + sc1200wdt= [HW,WDT] SC1200 WDT (watchdog) driver Format: <io>[,<timeout>[,<isapnp>]] diff --git a/Documentation/pcmcia/driver-changes.txt b/Documentation/pcmcia/driver-changes.txt index 059934363caf..446f43b309df 100644 --- a/Documentation/pcmcia/driver-changes.txt +++ b/Documentation/pcmcia/driver-changes.txt @@ -1,5 +1,17 @@ This file details changes in 2.6 which affect PCMCIA card driver authors: +* no cs_error / CS_CHECK / CONFIG_PCMCIA_DEBUG (as of 2.6.33) + Instead of the cs_error() callback or the CS_CHECK() macro, please use + Linux-style checking of return values, and -- if necessary -- debug + messages using "dev_dbg()" or "pr_debug()". + +* New CIS tuple access (as of 2.6.33) + Instead of pcmcia_get_{first,next}_tuple(), pcmcia_get_tuple_data() and + pcmcia_parse_tuple(), a driver shall use "pcmcia_get_tuple()" if it is + only interested in one (raw) tuple, or "pcmcia_loop_tuple()" if it is + interested in all tuples of one type. To decode the MAC from CISTPL_FUNCE, + a new helper "pcmcia_get_mac_from_cis()" was added. + * New configuration loop helper (as of 2.6.28) By calling pcmcia_loop_config(), a driver can iterate over all available configuration options. During a driver's probe() phase, one doesn't need diff --git a/Documentation/slow-work.txt b/Documentation/slow-work.txt index ebc50f808ea4..9dbf4470c7e1 100644 --- a/Documentation/slow-work.txt +++ b/Documentation/slow-work.txt @@ -41,6 +41,13 @@ expand files, provided the time taken to do so isn't too long. Operations of both types may sleep during execution, thus tying up the thread loaned to it. +A further class of work item is available, based on the slow work item class: + + (*) Delayed slow work items. + +These are slow work items that have a timer to defer queueing of the item for +a while. + THREAD-TO-CLASS ALLOCATION -------------------------- @@ -64,9 +71,11 @@ USING SLOW WORK ITEMS Firstly, a module or subsystem wanting to make use of slow work items must register its interest: - int ret = slow_work_register_user(); + int ret = slow_work_register_user(struct module *module); -This will return 0 if successful, or a -ve error upon failure. +This will return 0 if successful, or a -ve error upon failure. The module +pointer should be the module interested in using this facility (almost +certainly THIS_MODULE). Slow work items may then be set up by: @@ -93,6 +102,10 @@ Slow work items may then be set up by: or: + delayed_slow_work_init(&myitem, &myitem_ops); + + or: + vslow_work_init(&myitem, &myitem_ops); depending on its class. @@ -102,15 +115,92 @@ A suitably set up work item can then be enqueued for processing: int ret = slow_work_enqueue(&myitem); This will return a -ve error if the thread pool is unable to gain a reference -on the item, 0 otherwise. +on the item, 0 otherwise, or (for delayed work): + + int ret = delayed_slow_work_enqueue(&myitem, my_jiffy_delay); The items are reference counted, so there ought to be no need for a flush -operation. When all a module's slow work items have been processed, and the +operation. But as the reference counting is optional, means to cancel +existing work items are also included: + + cancel_slow_work(&myitem); + cancel_delayed_slow_work(&myitem); + +can be used to cancel pending work. The above cancel function waits for +existing work to have been executed (or prevent execution of them, depending +on timing). + + +When all a module's slow work items have been processed, and the module has no further interest in the facility, it should unregister its interest: - slow_work_unregister_user(); + slow_work_unregister_user(struct module *module); + +The module pointer is used to wait for all outstanding work items for that +module before completing the unregistration. This prevents the put_ref() code +from being taken away before it completes. module should almost certainly be +THIS_MODULE. + + +================ +HELPER FUNCTIONS +================ + +The slow-work facility provides a function by which it can be determined +whether or not an item is queued for later execution: + + bool queued = slow_work_is_queued(struct slow_work *work); + +If it returns false, then the item is not on the queue (it may be executing +with a requeue pending). This can be used to work out whether an item on which +another depends is on the queue, thus allowing a dependent item to be queued +after it. + +If the above shows an item on which another depends not to be queued, then the +owner of the dependent item might need to wait. However, to avoid locking up +the threads unnecessarily be sleeping in them, it can make sense under some +circumstances to return the work item to the queue, thus deferring it until +some other items have had a chance to make use of the yielded thread. + +To yield a thread and defer an item, the work function should simply enqueue +the work item again and return. However, this doesn't work if there's nothing +actually on the queue, as the thread just vacated will jump straight back into +the item's work function, thus busy waiting on a CPU. + +Instead, the item should use the thread to wait for the dependency to go away, +but rather than using schedule() or schedule_timeout() to sleep, it should use +the following function: + + bool requeue = slow_work_sleep_till_thread_needed( + struct slow_work *work, + signed long *_timeout); + +This will add a second wait and then sleep, such that it will be woken up if +either something appears on the queue that could usefully make use of the +thread - and behind which this item can be queued, or if the event the caller +set up to wait for happens. True will be returned if something else appeared +on the queue and this work function should perhaps return, of false if +something else woke it up. The timeout is as for schedule_timeout(). + +For example: + + wq = bit_waitqueue(&my_flags, MY_BIT); + init_wait(&wait); + requeue = false; + do { + prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE); + if (!test_bit(MY_BIT, &my_flags)) + break; + requeue = slow_work_sleep_till_thread_needed(&my_work, + &timeout); + } while (timeout > 0 && !requeue); + finish_wait(wq, &wait); + if (!test_bit(MY_BIT, &my_flags) + goto do_my_thing; + if (requeue) + return; // to slow_work =============== @@ -118,7 +208,8 @@ ITEM OPERATIONS =============== Each work item requires a table of operations of type struct slow_work_ops. -All members are required: +Only ->execute() is required; the getting and putting of a reference and the +describing of an item are all optional. (*) Get a reference on an item: @@ -148,6 +239,16 @@ All members are required: This should perform the work required of the item. It may sleep, it may perform disk I/O and it may wait for locks. + (*) View an item through /proc: + + void (*desc)(struct slow_work *work, struct seq_file *m); + + If supplied, this should print to 'm' a small string describing the work + the item is to do. This should be no more than about 40 characters, and + shouldn't include a newline character. + + See the 'Viewing executing and queued items' section below. + ================== POOL CONFIGURATION @@ -172,3 +273,50 @@ The slow-work thread pool has a number of configurables: is bounded to between 1 and one fewer than the number of active threads. This ensures there is always at least one thread that can process very slow work items, and always at least one thread that won't. + + +================================== +VIEWING EXECUTING AND QUEUED ITEMS +================================== + +If CONFIG_SLOW_WORK_DEBUG is enabled, a debugfs file is made available: + + /sys/kernel/debug/slow_work/runqueue + +through which the list of work items being executed and the queues of items to +be executed may be viewed. The owner of a work item is given the chance to +add some information of its own. + +The contents look something like the following: + + THR PID ITEM ADDR FL MARK DESC + === ===== ================ == ===== ========== + 0 3005 ffff880023f52348 a 952ms FSC: OBJ17d3: LOOK + 1 3006 ffff880024e33668 2 160ms FSC: OBJ17e5 OP60d3b: Write1/Store fl=2 + 2 3165 ffff8800296dd180 a 424ms FSC: OBJ17e4: LOOK + 3 4089 ffff8800262c8d78 a 212ms FSC: OBJ17ea: CRTN + 4 4090 ffff88002792bed8 2 388ms FSC: OBJ17e8 OP60d36: Write1/Store fl=2 + 5 4092 ffff88002a0ef308 2 388ms FSC: OBJ17e7 OP60d2e: Write1/Store fl=2 + 6 4094 ffff88002abaf4b8 2 132ms FSC: OBJ17e2 OP60d4e: Write1/Store fl=2 + 7 4095 ffff88002bb188e0 a 388ms FSC: OBJ17e9: CRTN + vsq - ffff880023d99668 1 308ms FSC: OBJ17e0 OP60f91: Write1/EnQ fl=2 + vsq - ffff8800295d1740 1 212ms FSC: OBJ16be OP4d4b6: Write1/EnQ fl=2 + vsq - ffff880025ba3308 1 160ms FSC: OBJ179a OP58dec: Write1/EnQ fl=2 + vsq - ffff880024ec83e0 1 160ms FSC: OBJ17ae OP599f2: Write1/EnQ fl=2 + vsq - ffff880026618e00 1 160ms FSC: OBJ17e6 OP60d33: Write1/EnQ fl=2 + vsq - ffff880025a2a4b8 1 132ms FSC: OBJ16a2 OP4d583: Write1/EnQ fl=2 + vsq - ffff880023cbe6d8 9 212ms FSC: OBJ17eb: LOOK + vsq - ffff880024d37590 9 212ms FSC: OBJ17ec: LOOK + vsq - ffff880027746cb0 9 212ms FSC: OBJ17ed: LOOK + vsq - ffff880024d37ae8 9 212ms FSC: OBJ17ee: LOOK + vsq - ffff880024d37cb0 9 212ms FSC: OBJ17ef: LOOK + vsq - ffff880025036550 9 212ms FSC: OBJ17f0: LOOK + vsq - ffff8800250368e0 9 212ms FSC: OBJ17f1: LOOK + vsq - ffff880025036aa8 9 212ms FSC: OBJ17f2: LOOK + +In the 'THR' column, executing items show the thread they're occupying and +queued threads indicate which queue they're on. 'PID' shows the process ID of +a slow-work thread that's executing something. 'FL' shows the work item flags. +'MARK' indicates how long since an item was queued or began executing. Lastly, +the 'DESC' column permits the owner of an item to give some information. + diff --git a/Documentation/sysctl/ctl_unnumbered.txt b/Documentation/sysctl/ctl_unnumbered.txt deleted file mode 100644 index 23003a8ea3e7..000000000000 --- a/Documentation/sysctl/ctl_unnumbered.txt +++ /dev/null @@ -1,22 +0,0 @@ - -Except for a few extremely rare exceptions user space applications do not use -the binary sysctl interface. Instead everyone uses /proc/sys/... with -readable ascii names. - -Recently the kernel has started supporting setting the binary sysctl value to -CTL_UNNUMBERED so we no longer need to assign a binary sysctl path to allow -sysctls to show up in /proc/sys. - -Assigning binary sysctl numbers is an endless source of conflicts in sysctl.h, -breaking of the user space ABI (because of those conflicts), and maintenance -problems. A complete pass through all of the sysctl users revealed multiple -instances where the sysctl binary interface was broken and had gone undetected -for years. - -So please do not add new binary sysctl numbers. They are unneeded and -problematic. - -If you really need a new binary sysctl number please first merge your sysctl -into the kernel and then as a separate patch allocate a binary sysctl number. - -(ebiederm@xmission.com, June 2007) diff --git a/Documentation/trace/ftrace-design.txt b/Documentation/trace/ftrace-design.txt index 7003e10f10f5..641a1ef2a7ff 100644 --- a/Documentation/trace/ftrace-design.txt +++ b/Documentation/trace/ftrace-design.txt @@ -213,10 +213,19 @@ If you can't trace NMI functions, then skip this option. <details to be filled> -HAVE_FTRACE_SYSCALLS +HAVE_SYSCALL_TRACEPOINTS --------------------- -<details to be filled> +You need very few things to get the syscalls tracing in an arch. + +- Have a NR_syscalls variable in <asm/unistd.h> that provides the number + of syscalls supported by the arch. +- Implement arch_syscall_addr() that resolves a syscall address from a + syscall number. +- Support the TIF_SYSCALL_TRACEPOINT thread flags +- Put the trace_sys_enter() and trace_sys_exit() tracepoints calls from ptrace + in the ptrace syscalls tracing path. +- Tag this arch as HAVE_SYSCALL_TRACEPOINTS. HAVE_FTRACE_MCOUNT_RECORD diff --git a/Documentation/trace/kprobetrace.txt b/Documentation/trace/kprobetrace.txt new file mode 100644 index 000000000000..47aabeebbdf6 --- /dev/null +++ b/Documentation/trace/kprobetrace.txt @@ -0,0 +1,149 @@ + Kprobe-based Event Tracing + ========================== + + Documentation is written by Masami Hiramatsu + + +Overview +-------- +These events are similar to tracepoint based events. Instead of Tracepoint, +this is based on kprobes (kprobe and kretprobe). So it can probe wherever +kprobes can probe (this means, all functions body except for __kprobes +functions). Unlike the Tracepoint based event, this can be added and removed +dynamically, on the fly. + +To enable this feature, build your kernel with CONFIG_KPROBE_TRACING=y. + +Similar to the events tracer, this doesn't need to be activated via +current_tracer. Instead of that, add probe points via +/sys/kernel/debug/tracing/kprobe_events, and enable it via +/sys/kernel/debug/tracing/events/kprobes/<EVENT>/enabled. + + +Synopsis of kprobe_events +------------------------- + p[:[GRP/]EVENT] SYMBOL[+offs]|MEMADDR [FETCHARGS] : Set a probe + r[:[GRP/]EVENT] SYMBOL[+0] [FETCHARGS] : Set a return probe + + GRP : Group name. If omitted, use "kprobes" for it. + EVENT : Event name. If omitted, the event name is generated + based on SYMBOL+offs or MEMADDR. + SYMBOL[+offs] : Symbol+offset where the probe is inserted. + MEMADDR : Address where the probe is inserted. + + FETCHARGS : Arguments. Each probe can have up to 128 args. + %REG : Fetch register REG + @ADDR : Fetch memory at ADDR (ADDR should be in kernel) + @SYM[+|-offs] : Fetch memory at SYM +|- offs (SYM should be a data symbol) + $stackN : Fetch Nth entry of stack (N >= 0) + $stack : Fetch stack address. + $argN : Fetch function argument. (N >= 0)(*) + $retval : Fetch return value.(**) + +|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(***) + NAME=FETCHARG: Set NAME as the argument name of FETCHARG. + + (*) aN may not correct on asmlinkaged functions and at the middle of + function body. + (**) only for return probe. + (***) this is useful for fetching a field of data structures. + + +Per-Probe Event Filtering +------------------------- + Per-probe event filtering feature allows you to set different filter on each +probe and gives you what arguments will be shown in trace buffer. If an event +name is specified right after 'p:' or 'r:' in kprobe_events, it adds an event +under tracing/events/kprobes/<EVENT>, at the directory you can see 'id', +'enabled', 'format' and 'filter'. + +enabled: + You can enable/disable the probe by writing 1 or 0 on it. + +format: + This shows the format of this probe event. + +filter: + You can write filtering rules of this event. + +id: + This shows the id of this probe event. + + +Event Profiling +--------------- + You can check the total number of probe hits and probe miss-hits via +/sys/kernel/debug/tracing/kprobe_profile. + The first column is event name, the second is the number of probe hits, +the third is the number of probe miss-hits. + + +Usage examples +-------------- +To add a probe as a new event, write a new definition to kprobe_events +as below. + + echo p:myprobe do_sys_open dfd=$arg0 filename=$arg1 flags=$arg2 mode=$arg3 > /sys/kernel/debug/tracing/kprobe_events + + This sets a kprobe on the top of do_sys_open() function with recording +1st to 4th arguments as "myprobe" event. As this example shows, users can +choose more familiar names for each arguments. + + echo r:myretprobe do_sys_open $retval >> /sys/kernel/debug/tracing/kprobe_events + + This sets a kretprobe on the return point of do_sys_open() function with +recording return value as "myretprobe" event. + You can see the format of these events via +/sys/kernel/debug/tracing/events/kprobes/<EVENT>/format. + + cat /sys/kernel/debug/tracing/events/kprobes/myprobe/format +name: myprobe +ID: 75 +format: + field:unsigned short common_type; offset:0; size:2; + field:unsigned char common_flags; offset:2; size:1; + field:unsigned char common_preempt_count; offset:3; size:1; + field:int common_pid; offset:4; size:4; + field:int common_tgid; offset:8; size:4; + + field: unsigned long ip; offset:16;tsize:8; + field: int nargs; offset:24;tsize:4; + field: unsigned long dfd; offset:32;tsize:8; + field: unsigned long filename; offset:40;tsize:8; + field: unsigned long flags; offset:48;tsize:8; + field: unsigned long mode; offset:56;tsize:8; + +print fmt: "(%lx) dfd=%lx filename=%lx flags=%lx mode=%lx", REC->ip, REC->dfd, REC->filename, REC->flags, REC->mode + + + You can see that the event has 4 arguments as in the expressions you specified. + + echo > /sys/kernel/debug/tracing/kprobe_events + + This clears all probe points. + + Right after definition, each event is disabled by default. For tracing these +events, you need to enable it. + + echo 1 > /sys/kernel/debug/tracing/events/kprobes/myprobe/enable + echo 1 > /sys/kernel/debug/tracing/events/kprobes/myretprobe/enable + + And you can see the traced information via /sys/kernel/debug/tracing/trace. + + cat /sys/kernel/debug/tracing/trace +# tracer: nop +# +# TASK-PID CPU# TIMESTAMP FUNCTION +# | | | | | + <...>-1447 [001] 1038282.286875: myprobe: (do_sys_open+0x0/0xd6) dfd=3 filename=7fffd1ec4440 flags=8000 mode=0 + <...>-1447 [001] 1038282.286878: myretprobe: (sys_openat+0xc/0xe <- do_sys_open) $retval=fffffffffffffffe + <...>-1447 [001] 1038282.286885: myprobe: (do_sys_open+0x0/0xd6) dfd=ffffff9c filename=40413c flags=8000 mode=1b6 + <...>-1447 [001] 1038282.286915: myretprobe: (sys_open+0x1b/0x1d <- do_sys_open) $retval=3 + <...>-1447 [001] 1038282.286969: myprobe: (do_sys_open+0x0/0xd6) dfd=ffffff9c filename=4041c6 flags=98800 mode=10 + <...>-1447 [001] 1038282.286976: myretprobe: (sys_open+0x1b/0x1d <- do_sys_open) $retval=3 + + + Each line shows when the kernel hits an event, and <- SYMBOL means kernel +returns from SYMBOL(e.g. "sys_open+0x1b/0x1d <- do_sys_open" means kernel +returns from do_sys_open to sys_open+0x1b). + + diff --git a/MAINTAINERS b/MAINTAINERS index c824b4d62754..4f96ac81089c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -512,10 +512,32 @@ W: http://www.arm.linux.org.uk/ S: Maintained F: arch/arm/ +ARM PRIMECELL AACI PL041 DRIVER +M: Russell King <linux@arm.linux.org.uk> +S: Maintained +F: sound/arm/aaci.* + +ARM PRIMECELL CLCD PL110 DRIVER +M: Russell King <linux@arm.linux.org.uk> +S: Maintained +F: drivers/video/amba-clcd.* + +ARM PRIMECELL KMI PL050 DRIVER +M: Russell King <linux@arm.linux.org.uk> +S: Maintained +F: drivers/input/serio/ambakmi.* +F: include/linux/amba/kmi.h + ARM PRIMECELL MMCI PL180/1 DRIVER S: Orphan F: drivers/mmc/host/mmci.* +ARM PRIMECELL BUS SUPPORT +M: Russell King <linux@arm.linux.org.uk> +S: Maintained +F: drivers/amba/ +F: include/linux/amba/bus.h + ARM/ADI ROADRUNNER MACHINE SUPPORT M: Lennert Buytenhek <kernel@wantstofly.org> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@ -1027,7 +1049,7 @@ F: drivers/serial/atmel_serial.c ATMEL LCDFB DRIVER M: Nicolas Ferre <nicolas.ferre@atmel.com> -L: linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers) +L: linux-fbdev@vger.kernel.org S: Maintained F: drivers/video/atmel_lcdfb.c F: include/video/atmel_lcdc.h @@ -2113,7 +2135,7 @@ F: drivers/net/wan/dlci.c F: drivers/net/wan/sdla.c FRAMEBUFFER LAYER -L: linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers) +L: linux-fbdev@vger.kernel.org W: http://linux-fbdev.sourceforge.net/ S: Orphan F: Documentation/fb/ @@ -2136,7 +2158,7 @@ F: drivers/i2c/busses/i2c-cpm.c FREESCALE IMX / MXC FRAMEBUFFER DRIVER M: Sascha Hauer <kernel@pengutronix.de> -L: linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers) +L: linux-fbdev@vger.kernel.org L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm/plat-mxc/include/mach/imxfb.h @@ -2312,6 +2334,13 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-2.6.git S: Maintained F: drivers/media/video/gspca/finepix.c +GSPCA GL860 SUBDRIVER +M: Olivier Lorin <o.lorin@laposte.net> +L: linux-media@vger.kernel.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-2.6.git +S: Maintained +F: drivers/media/video/gspca/gl860/ + GSPCA M5602 SUBDRIVER M: Erik Andren <erik.andren@gmail.com> L: linux-media@vger.kernel.org @@ -2533,8 +2562,7 @@ S: Maintained F: Documentation/i2c/ F: drivers/i2c/ F: include/linux/i2c.h -F: include/linux/i2c-dev.h -F: include/linux/i2c-id.h +F: include/linux/i2c-*.h I2C-TINY-USB DRIVER M: Till Harbaum <till@harbaum.org> @@ -2635,7 +2663,7 @@ S: Supported F: security/integrity/ima/ IMS TWINTURBO FRAMEBUFFER DRIVER -L: linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers) +L: linux-fbdev@vger.kernel.org S: Orphan F: drivers/video/imsttfb.c @@ -2670,14 +2698,14 @@ F: drivers/input/ INTEL FRAMEBUFFER DRIVER (excluding 810 and 815) M: Sylvain Meyer <sylvain.meyer@worldonline.fr> -L: linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers) +L: linux-fbdev@vger.kernel.org S: Maintained F: Documentation/fb/intelfb.txt F: drivers/video/intelfb/ INTEL 810/815 FRAMEBUFFER DRIVER M: Antonino Daplas <adaplas@gmail.com> -L: linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers) +L: linux-fbdev@vger.kernel.org S: Maintained F: drivers/video/i810/ @@ -2987,11 +3015,8 @@ S: Maintained F: fs/autofs4/ KERNEL BUILD -M: Sam Ravnborg <sam@ravnborg.org> -T: git git://git.kernel.org/pub/scm/linux/kernel/git/sam/kbuild-next.git -T: git git://git.kernel.org/pub/scm/linux/kernel/git/sam/kbuild-fixes.git L: linux-kbuild@vger.kernel.org -S: Maintained +S: Orphan F: Documentation/kbuild/ F: Makefile F: scripts/Makefile.* @@ -3391,7 +3416,7 @@ S: Supported MATROX FRAMEBUFFER DRIVER M: Petr Vandrovec <vandrove@vc.cvut.cz> -L: linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers) +L: linux-fbdev@vger.kernel.org S: Maintained F: drivers/video/matrox/matroxfb_* F: include/linux/matroxfb.h @@ -3778,7 +3803,7 @@ F: fs/ntfs/ NVIDIA (rivafb and nvidiafb) FRAMEBUFFER DRIVER M: Antonino Daplas <adaplas@gmail.com> -L: linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers) +L: linux-fbdev@vger.kernel.org S: Maintained F: drivers/video/riva/ F: drivers/video/nvidia/ @@ -3813,7 +3838,7 @@ F: sound/soc/omap/ OMAP FRAMEBUFFER SUPPORT M: Imre Deak <imre.deak@nokia.com> -L: linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers) +L: linux-fbdev@vger.kernel.org L: linux-omap@vger.kernel.org S: Maintained F: drivers/video/omap/ @@ -4319,14 +4344,14 @@ F: include/linux/qnxtypes.h RADEON FRAMEBUFFER DISPLAY DRIVER M: Benjamin Herrenschmidt <benh@kernel.crashing.org> -L: linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers) +L: linux-fbdev@vger.kernel.org S: Maintained F: drivers/video/aty/radeon* F: include/linux/radeonfb.h RAGE128 FRAMEBUFFER DISPLAY DRIVER M: Paul Mackerras <paulus@samba.org> -L: linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers) +L: linux-fbdev@vger.kernel.org S: Maintained F: drivers/video/aty/aty128fb.c @@ -4465,7 +4490,7 @@ F: drivers/net/wireless/rtl818x/rtl8187* S3 SAVAGE FRAMEBUFFER DRIVER M: Antonino Daplas <adaplas@gmail.com> -L: linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers) +L: linux-fbdev@vger.kernel.org S: Maintained F: drivers/video/savage/ @@ -5628,7 +5653,7 @@ S: Maintained UVESAFB DRIVER M: Michal Januszewski <spock@gentoo.org> -L: linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers) +L: linux-fbdev@vger.kernel.org W: http://dev.gentoo.org/~spock/projects/uvesafb/ S: Maintained F: Documentation/fb/uvesafb.txt @@ -5661,7 +5686,7 @@ F: drivers/mmc/host/via-sdmmc.c VIA UNICHROME(PRO)/CHROME9 FRAMEBUFFER DRIVER M: Joseph Chan <JosephChan@via.com.tw> M: Scott Fang <ScottFang@viatech.com.cn> -L: linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers) +L: linux-fbdev@vger.kernel.org S: Maintained F: drivers/video/via/ @@ -1,7 +1,7 @@ VERSION = 2 PATCHLEVEL = 6 SUBLEVEL = 32 -EXTRAVERSION = -rc8 +EXTRAVERSION = NAME = Man-Eating Seals of Antiquity # *DOCUMENTATION* @@ -379,6 +379,7 @@ export RCS_TAR_IGNORE := --exclude SCCS --exclude BitKeeper --exclude .svn --exc PHONY += scripts_basic scripts_basic: $(Q)$(MAKE) $(build)=scripts/basic + $(Q)rm -f .tmp_quiet_recordmcount # To avoid any implicit rule to kick in, define an empty command. scripts/basic/%: scripts_basic ; diff --git a/arch/Kconfig b/arch/Kconfig index 7f418bbc261a..eef3bbb97075 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -126,4 +126,11 @@ config HAVE_DMA_API_DEBUG config HAVE_DEFAULT_NO_SPIN_MUTEXES bool +config HAVE_HW_BREAKPOINT + bool + depends on HAVE_PERF_EVENTS + select ANON_INODES + select PERF_EVENTS + + source "kernel/gcov/Kconfig" diff --git a/arch/alpha/include/asm/thread_info.h b/arch/alpha/include/asm/thread_info.h index 815680b585ed..b3e888638bb7 100644 --- a/arch/alpha/include/asm/thread_info.h +++ b/arch/alpha/include/asm/thread_info.h @@ -61,21 +61,24 @@ register struct thread_info *__current_thread_info __asm__("$8"); /* * Thread information flags: * - these are process state flags and used from assembly - * - pending work-to-be-done flags come first to fit in and immediate operand. + * - pending work-to-be-done flags come first and must be assigned to be + * within bits 0 to 7 to fit in and immediate operand. + * - ALPHA_UAC_SHIFT below must be kept consistent with the unaligned + * control flags. * * TIF_SYSCALL_TRACE is known to be 0 via blbs. */ #define TIF_SYSCALL_TRACE 0 /* syscall trace active */ -#define TIF_SIGPENDING 1 /* signal pending */ -#define TIF_NEED_RESCHED 2 /* rescheduling necessary */ -#define TIF_POLLING_NRFLAG 3 /* poll_idle is polling NEED_RESCHED */ -#define TIF_DIE_IF_KERNEL 4 /* dik recursion lock */ -#define TIF_UAC_NOPRINT 5 /* see sysinfo.h */ -#define TIF_UAC_NOFIX 6 -#define TIF_UAC_SIGBUS 7 -#define TIF_MEMDIE 8 -#define TIF_RESTORE_SIGMASK 9 /* restore signal mask in do_signal */ -#define TIF_NOTIFY_RESUME 10 /* callback before returning to user */ +#define TIF_NOTIFY_RESUME 1 /* callback before returning to user */ +#define TIF_SIGPENDING 2 /* signal pending */ +#define TIF_NEED_RESCHED 3 /* rescheduling necessary */ +#define TIF_POLLING_NRFLAG 8 /* poll_idle is polling NEED_RESCHED */ +#define TIF_DIE_IF_KERNEL 9 /* dik recursion lock */ +#define TIF_UAC_NOPRINT 10 /* see sysinfo.h */ +#define TIF_UAC_NOFIX 11 +#define TIF_UAC_SIGBUS 12 +#define TIF_MEMDIE 13 +#define TIF_RESTORE_SIGMASK 14 /* restore signal mask in do_signal */ #define TIF_FREEZE 16 /* is freezing for suspend */ #define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE) @@ -94,7 +97,7 @@ register struct thread_info *__current_thread_info __asm__("$8"); #define _TIF_ALLWORK_MASK (_TIF_WORK_MASK \ | _TIF_SYSCALL_TRACE) -#define ALPHA_UAC_SHIFT 6 +#define ALPHA_UAC_SHIFT 10 #define ALPHA_UAC_MASK (1 << TIF_UAC_NOPRINT | 1 << TIF_UAC_NOFIX | \ 1 << TIF_UAC_SIGBUS) diff --git a/arch/alpha/kernel/core_marvel.c b/arch/alpha/kernel/core_marvel.c index 8e059e58b0ac..53dd2f1a53aa 100644 --- a/arch/alpha/kernel/core_marvel.c +++ b/arch/alpha/kernel/core_marvel.c @@ -1103,6 +1103,8 @@ marvel_agp_info(void) * Allocate the info structure. */ agp = kmalloc(sizeof(*agp), GFP_KERNEL); + if (!agp) + return NULL; /* * Fill it in. diff --git a/arch/alpha/kernel/core_titan.c b/arch/alpha/kernel/core_titan.c index 76686497b1e2..219bf271c0ba 100644 --- a/arch/alpha/kernel/core_titan.c +++ b/arch/alpha/kernel/core_titan.c @@ -757,6 +757,8 @@ titan_agp_info(void) * Allocate the info structure. */ agp = kmalloc(sizeof(*agp), GFP_KERNEL); + if (!agp) + return NULL; /* * Fill it in. diff --git a/arch/alpha/kernel/irq.c b/arch/alpha/kernel/irq.c index cc7834661427..c0de072b8305 100644 --- a/arch/alpha/kernel/irq.c +++ b/arch/alpha/kernel/irq.c @@ -92,7 +92,7 @@ show_interrupts(struct seq_file *p, void *v) for_each_online_cpu(j) seq_printf(p, "%10u ", kstat_irqs_cpu(irq, j)); #endif - seq_printf(p, " %14s", irq_desc[irq].chip->typename); + seq_printf(p, " %14s", irq_desc[irq].chip->name); seq_printf(p, " %c%s", (action->flags & IRQF_DISABLED)?'+':' ', action->name); diff --git a/arch/alpha/kernel/irq_alpha.c b/arch/alpha/kernel/irq_alpha.c index 38c805dfc544..cfde865b78e0 100644 --- a/arch/alpha/kernel/irq_alpha.c +++ b/arch/alpha/kernel/irq_alpha.c @@ -228,7 +228,7 @@ struct irqaction timer_irqaction = { }; static struct irq_chip rtc_irq_type = { - .typename = "RTC", + .name = "RTC", .startup = rtc_startup, .shutdown = rtc_enable_disable, .enable = rtc_enable_disable, diff --git a/arch/alpha/kernel/irq_i8259.c b/arch/alpha/kernel/irq_i8259.c index 50bfec9b588f..83a9ac280890 100644 --- a/arch/alpha/kernel/irq_i8259.c +++ b/arch/alpha/kernel/irq_i8259.c @@ -84,7 +84,7 @@ i8259a_end_irq(unsigned int irq) } struct irq_chip i8259a_irq_type = { - .typename = "XT-PIC", + .name = "XT-PIC", .startup = i8259a_startup_irq, .shutdown = i8259a_disable_irq, .enable = i8259a_enable_irq, diff --git a/arch/alpha/kernel/irq_pyxis.c b/arch/alpha/kernel/irq_pyxis.c index 69199a76ec4a..989ce46a0cf3 100644 --- a/arch/alpha/kernel/irq_pyxis.c +++ b/arch/alpha/kernel/irq_pyxis.c @@ -71,7 +71,7 @@ pyxis_mask_and_ack_irq(unsigned int irq) } static struct irq_chip pyxis_irq_type = { - .typename = "PYXIS", + .name = "PYXIS", .startup = pyxis_startup_irq, .shutdown = pyxis_disable_irq, .enable = pyxis_enable_irq, diff --git a/arch/alpha/kernel/irq_srm.c b/arch/alpha/kernel/irq_srm.c index 85229369a1f8..d63e93e1e8bf 100644 --- a/arch/alpha/kernel/irq_srm.c +++ b/arch/alpha/kernel/irq_srm.c @@ -49,7 +49,7 @@ srm_end_irq(unsigned int irq) /* Handle interrupts from the SRM, assuming no additional weirdness. */ static struct irq_chip srm_irq_type = { - .typename = "SRM", + .name = "SRM", .startup = srm_startup_irq, .shutdown = srm_disable_irq, .enable = srm_enable_irq, diff --git a/arch/alpha/kernel/sys_alcor.c b/arch/alpha/kernel/sys_alcor.c index 382035ef7394..20a30b8b9655 100644 --- a/arch/alpha/kernel/sys_alcor.c +++ b/arch/alpha/kernel/sys_alcor.c @@ -90,7 +90,7 @@ alcor_end_irq(unsigned int irq) } static struct irq_chip alcor_irq_type = { - .typename = "ALCOR", + .name = "ALCOR", .startup = alcor_startup_irq, .shutdown = alcor_disable_irq, .enable = alcor_enable_irq, diff --git a/arch/alpha/kernel/sys_cabriolet.c b/arch/alpha/kernel/sys_cabriolet.c index ed349436732b..affd0f3f25df 100644 --- a/arch/alpha/kernel/sys_cabriolet.c +++ b/arch/alpha/kernel/sys_cabriolet.c @@ -72,7 +72,7 @@ cabriolet_end_irq(unsigned int irq) } static struct irq_chip cabriolet_irq_type = { - .typename = "CABRIOLET", + .name = "CABRIOLET", .startup = cabriolet_startup_irq, .shutdown = cabriolet_disable_irq, .enable = cabriolet_enable_irq, diff --git a/arch/alpha/kernel/sys_dp264.c b/arch/alpha/kernel/sys_dp264.c index 46e70ece5176..d64e1e497e76 100644 --- a/arch/alpha/kernel/sys_dp264.c +++ b/arch/alpha/kernel/sys_dp264.c @@ -199,7 +199,7 @@ clipper_set_affinity(unsigned int irq, const struct cpumask *affinity) } static struct irq_chip dp264_irq_type = { - .typename = "DP264", + .name = "DP264", .startup = dp264_startup_irq, .shutdown = dp264_disable_irq, .enable = dp264_enable_irq, @@ -210,7 +210,7 @@ static struct irq_chip dp264_irq_type = { }; static struct irq_chip clipper_irq_type = { - .typename = "CLIPPER", + .name = "CLIPPER", .startup = clipper_startup_irq, .shutdown = clipper_disable_irq, .enable = clipper_enable_irq, diff --git a/arch/alpha/kernel/sys_eb64p.c b/arch/alpha/kernel/sys_eb64p.c index 660c23ef661f..df2090ce5e7f 100644 --- a/arch/alpha/kernel/sys_eb64p.c +++ b/arch/alpha/kernel/sys_eb64p.c @@ -70,7 +70,7 @@ eb64p_end_irq(unsigned int irq) } static struct irq_chip eb64p_irq_type = { - .typename = "EB64P", + .name = "EB64P", .startup = eb64p_startup_irq, .shutdown = eb64p_disable_irq, .enable = eb64p_enable_irq, diff --git a/arch/alpha/kernel/sys_eiger.c b/arch/alpha/kernel/sys_eiger.c index b99ea488d844..3ca1dbcf4044 100644 --- a/arch/alpha/kernel/sys_eiger.c +++ b/arch/alpha/kernel/sys_eiger.c @@ -81,7 +81,7 @@ eiger_end_irq(unsigned int irq) } static struct irq_chip eiger_irq_type = { - .typename = "EIGER", + .name = "EIGER", .startup = eiger_startup_irq, .shutdown = eiger_disable_irq, .enable = eiger_enable_irq, diff --git a/arch/alpha/kernel/sys_jensen.c b/arch/alpha/kernel/sys_jensen.c index ef0b83a070ac..7a7ae36fff91 100644 --- a/arch/alpha/kernel/sys_jensen.c +++ b/arch/alpha/kernel/sys_jensen.c @@ -119,7 +119,7 @@ jensen_local_end(unsigned int irq) } static struct irq_chip jensen_local_irq_type = { - .typename = "LOCAL", + .name = "LOCAL", .startup = jensen_local_startup, .shutdown = jensen_local_shutdown, .enable = jensen_local_enable, diff --git a/arch/alpha/kernel/sys_marvel.c b/arch/alpha/kernel/sys_marvel.c index bbfc4f20ca72..0bb3b5c4f693 100644 --- a/arch/alpha/kernel/sys_marvel.c +++ b/arch/alpha/kernel/sys_marvel.c @@ -170,7 +170,7 @@ marvel_irq_noop_return(unsigned int irq) } static struct irq_chip marvel_legacy_irq_type = { - .typename = "LEGACY", + .name = "LEGACY", .startup = marvel_irq_noop_return, .shutdown = marvel_irq_noop, .enable = marvel_irq_noop, @@ -180,7 +180,7 @@ static struct irq_chip marvel_legacy_irq_type = { }; static struct irq_chip io7_lsi_irq_type = { - .typename = "LSI", + .name = "LSI", .startup = io7_startup_irq, .shutdown = io7_disable_irq, .enable = io7_enable_irq, @@ -190,7 +190,7 @@ static struct irq_chip io7_lsi_irq_type = { }; static struct irq_chip io7_msi_irq_type = { - .typename = "MSI", + .name = "MSI", .startup = io7_startup_irq, .shutdown = io7_disable_irq, .enable = io7_enable_irq, diff --git a/arch/alpha/kernel/sys_mikasa.c b/arch/alpha/kernel/sys_mikasa.c index 4e366641a08e..ee8865169811 100644 --- a/arch/alpha/kernel/sys_mikasa.c +++ b/arch/alpha/kernel/sys_mikasa.c @@ -69,7 +69,7 @@ mikasa_end_irq(unsigned int irq) } static struct irq_chip mikasa_irq_type = { - .typename = "MIKASA", + .name = "MIKASA", .startup = mikasa_startup_irq, .shutdown = mikasa_disable_irq, .enable = mikasa_enable_irq, diff --git a/arch/alpha/kernel/sys_noritake.c b/arch/alpha/kernel/sys_noritake.c index 35753a173bac..86503fe73a88 100644 --- a/arch/alpha/kernel/sys_noritake.c +++ b/arch/alpha/kernel/sys_noritake.c @@ -74,7 +74,7 @@ noritake_end_irq(unsigned int irq) } static struct irq_chip noritake_irq_type = { - .typename = "NORITAKE", + .name = "NORITAKE", .startup = noritake_startup_irq, .shutdown = noritake_disable_irq, .enable = noritake_enable_irq, diff --git a/arch/alpha/kernel/sys_rawhide.c b/arch/alpha/kernel/sys_rawhide.c index f3aec7e085c8..26c322bf89ee 100644 --- a/arch/alpha/kernel/sys_rawhide.c +++ b/arch/alpha/kernel/sys_rawhide.c @@ -136,7 +136,7 @@ rawhide_end_irq(unsigned int irq) } static struct irq_chip rawhide_irq_type = { - .typename = "RAWHIDE", + .name = "RAWHIDE", .startup = rawhide_startup_irq, .shutdown = rawhide_disable_irq, .enable = rawhide_enable_irq, diff --git a/arch/alpha/kernel/sys_ruffian.c b/arch/alpha/kernel/sys_ruffian.c index d9f9cfeb9931..8de1046fe91e 100644 --- a/arch/alpha/kernel/sys_ruffian.c +++ b/arch/alpha/kernel/sys_ruffian.c @@ -66,7 +66,7 @@ ruffian_init_irq(void) common_init_isa_dma(); } -#define RUFFIAN_LATCH ((PIT_TICK_RATE + HZ / 2) / HZ) +#define RUFFIAN_LATCH DIV_ROUND_CLOSEST(PIT_TICK_RATE, HZ) static void __init ruffian_init_rtc(void) diff --git a/arch/alpha/kernel/sys_rx164.c b/arch/alpha/kernel/sys_rx164.c index fc9246373452..be161129eab9 100644 --- a/arch/alpha/kernel/sys_rx164.c +++ b/arch/alpha/kernel/sys_rx164.c @@ -73,7 +73,7 @@ rx164_end_irq(unsigned int irq) } static struct irq_chip rx164_irq_type = { - .typename = "RX164", + .name = "RX164", .startup = rx164_startup_irq, .shutdown = rx164_disable_irq, .enable = rx164_enable_irq, diff --git a/arch/alpha/kernel/sys_sable.c b/arch/alpha/kernel/sys_sable.c index 426eb6906d01..b2abe27a23cf 100644 --- a/arch/alpha/kernel/sys_sable.c +++ b/arch/alpha/kernel/sys_sable.c @@ -502,7 +502,7 @@ sable_lynx_mask_and_ack_irq(unsigned int irq) } static struct irq_chip sable_lynx_irq_type = { - .typename = "SABLE/LYNX", + .name = "SABLE/LYNX", .startup = sable_lynx_startup_irq, .shutdown = sable_lynx_disable_irq, .enable = sable_lynx_enable_irq, diff --git a/arch/alpha/kernel/sys_takara.c b/arch/alpha/kernel/sys_takara.c index 830318c21661..230464885b5c 100644 --- a/arch/alpha/kernel/sys_takara.c +++ b/arch/alpha/kernel/sys_takara.c @@ -75,7 +75,7 @@ takara_end_irq(unsigned int irq) } static struct irq_chip takara_irq_type = { - .typename = "TAKARA", + .name = "TAKARA", .startup = takara_startup_irq, .shutdown = takara_disable_irq, .enable = takara_enable_irq, diff --git a/arch/alpha/kernel/sys_titan.c b/arch/alpha/kernel/sys_titan.c index 88978fc60f83..288053342c83 100644 --- a/arch/alpha/kernel/sys_titan.c +++ b/arch/alpha/kernel/sys_titan.c @@ -195,7 +195,7 @@ init_titan_irqs(struct irq_chip * ops, int imin, int imax) } static struct irq_chip titan_irq_type = { - .typename = "TITAN", + .name = "TITAN", .startup = titan_startup_irq, .shutdown = titan_disable_irq, .enable = titan_enable_irq, diff --git a/arch/alpha/kernel/sys_wildfire.c b/arch/alpha/kernel/sys_wildfire.c index e91b4c3838a8..62fd972e18ef 100644 --- a/arch/alpha/kernel/sys_wildfire.c +++ b/arch/alpha/kernel/sys_wildfire.c @@ -158,7 +158,7 @@ wildfire_end_irq(unsigned int irq) } static struct irq_chip wildfire_irq_type = { - .typename = "WILDFIRE", + .name = "WILDFIRE", .startup = wildfire_startup_irq, .shutdown = wildfire_disable_irq, .enable = wildfire_enable_irq, diff --git a/arch/arm/include/asm/kmap_types.h b/arch/arm/include/asm/kmap_types.h index d16ec97ec9a9..c019949a5189 100644 --- a/arch/arm/include/asm/kmap_types.h +++ b/arch/arm/include/asm/kmap_types.h @@ -22,4 +22,10 @@ enum km_type { KM_TYPE_NR }; +#ifdef CONFIG_DEBUG_HIGHMEM +#define KM_NMI (-1) +#define KM_NMI_PTE (-1) +#define KM_IRQ_PTE (-1) +#endif + #endif diff --git a/arch/arm/kernel/isa.c b/arch/arm/kernel/isa.c index 8ac9b8424007..346485910732 100644 --- a/arch/arm/kernel/isa.c +++ b/arch/arm/kernel/isa.c @@ -22,47 +22,42 @@ static unsigned int isa_membase, isa_portbase, isa_portshift; static ctl_table ctl_isa_vars[4] = { { - .ctl_name = BUS_ISA_MEM_BASE, .procname = "membase", .data = &isa_membase, .maxlen = sizeof(isa_membase), .mode = 0444, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = BUS_ISA_PORT_BASE, .procname = "portbase", .data = &isa_portbase, .maxlen = sizeof(isa_portbase), .mode = 0444, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = BUS_ISA_PORT_SHIFT, .procname = "portshift", .data = &isa_portshift, .maxlen = sizeof(isa_portshift), .mode = 0444, - .proc_handler = &proc_dointvec, - }, {0} + .proc_handler = proc_dointvec, + }, {} }; static struct ctl_table_header *isa_sysctl_header; static ctl_table ctl_isa[2] = { { - .ctl_name = CTL_BUS_ISA, .procname = "isa", .mode = 0555, .child = ctl_isa_vars, - }, {0} + }, {} }; static ctl_table ctl_bus[2] = { { - .ctl_name = CTL_BUS, .procname = "bus", .mode = 0555, .child = ctl_isa, - }, {0} + }, {} }; void __init diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index 2a573d4fea24..e7714f367eb8 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -662,8 +662,12 @@ static void do_signal(struct pt_regs *regs, int syscall) regs->ARM_sp -= 4; usp = (u32 __user *)regs->ARM_sp; - put_user(regs->ARM_pc, usp); - regs->ARM_pc = KERN_RESTART_CODE; + if (put_user(regs->ARM_pc, usp) == 0) { + regs->ARM_pc = KERN_RESTART_CODE; + } else { + regs->ARM_sp += 4; + force_sigsegv(0, current); + } #endif } } diff --git a/arch/arm/mach-bcmring/arch.c b/arch/arm/mach-bcmring/arch.c index 0da693b0f7e1..fbe6fa02c882 100644 --- a/arch/arm/mach-bcmring/arch.c +++ b/arch/arm/mach-bcmring/arch.c @@ -47,10 +47,6 @@ HW_DECLARE_SPINLOCK(gpio) EXPORT_SYMBOL(bcmring_gpio_reg_lock); #endif -/* FIXME: temporary solution */ -#define BCM_SYSCTL_REBOOT_WARM 1 -#define CTL_BCM_REBOOT 112 - /* sysctl */ int bcmring_arch_warm_reboot; /* do a warm reboot on hard reset */ @@ -58,18 +54,16 @@ static struct ctl_table_header *bcmring_sysctl_header; static struct ctl_table bcmring_sysctl_warm_reboot[] = { { - .ctl_name = BCM_SYSCTL_REBOOT_WARM, .procname = "warm", .data = &bcmring_arch_warm_reboot, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec}, + .proc_handler = proc_dointvec}, {} }; static struct ctl_table bcmring_sysctl_reboot[] = { { - .ctl_name = CTL_BCM_REBOOT, .procname = "reboot", .mode = 0555, .child = bcmring_sysctl_warm_reboot}, diff --git a/arch/arm/mach-pxa/cpufreq-pxa2xx.c b/arch/arm/mach-pxa/cpufreq-pxa2xx.c index 983cc8c20081..9e4d9816726a 100644 --- a/arch/arm/mach-pxa/cpufreq-pxa2xx.c +++ b/arch/arm/mach-pxa/cpufreq-pxa2xx.c @@ -447,6 +447,7 @@ static __init int pxa_cpufreq_init(struct cpufreq_policy *policy) pxa27x_freq_table[i].frequency = freq; pxa27x_freq_table[i].index = i; } + pxa27x_freq_table[i].index = i; pxa27x_freq_table[i].frequency = CPUFREQ_TABLE_END; /* diff --git a/arch/arm/mach-pxa/cpufreq-pxa3xx.c b/arch/arm/mach-pxa/cpufreq-pxa3xx.c index 67f34a8d8e60..149cdd9aee4d 100644 --- a/arch/arm/mach-pxa/cpufreq-pxa3xx.c +++ b/arch/arm/mach-pxa/cpufreq-pxa3xx.c @@ -102,7 +102,7 @@ static int setup_freqs_table(struct cpufreq_policy *policy, table[i].index = i; table[i].frequency = freqs[i].cpufreq_mhz * 1000; } - table[num].frequency = i; + table[num].index = i; table[num].frequency = CPUFREQ_TABLE_END; pxa3xx_freqs = freqs; diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c index 3da45d051743..d98023f55503 100644 --- a/arch/arm/mach-pxa/spitz.c +++ b/arch/arm/mach-pxa/spitz.c @@ -802,10 +802,12 @@ static void __init spitz_init(void) { spitz_ficp_platform_data.gpio_pwdown = SPITZ_GPIO_IR_ON; +#ifdef CONFIG_MACH_BORZOI if (machine_is_borzoi()) { sharpsl_nand_platform_data.badblock_pattern = &sharpsl_akita_bbt; sharpsl_nand_platform_data.ecc_layout = &akita_oobinfo; } +#endif platform_scoop_config = &spitz_pcmcia_config; diff --git a/arch/arm/tools/mach-types b/arch/arm/tools/mach-types index 94be7bb6cb9a..07b976da6174 100644 --- a/arch/arm/tools/mach-types +++ b/arch/arm/tools/mach-types @@ -12,7 +12,7 @@ # # http://www.arm.linux.org.uk/developer/machines/?action=new # -# Last update: Fri Sep 18 21:42:00 2009 +# Last update: Wed Nov 25 22:14:58 2009 # # machine_is_xxx CONFIG_xxxx MACH_TYPE_xxx number # @@ -928,7 +928,7 @@ palmt5 MACH_PALMT5 PALMT5 917 palmtc MACH_PALMTC PALMTC 918 omap_apollon MACH_OMAP_APOLLON OMAP_APOLLON 919 mxc30030evb MACH_MXC30030EVB MXC30030EVB 920 -rea_2d MACH_REA_2D REA_2D 921 +rea_cpu2 MACH_REA_2D REA_2D 921 eti3e524 MACH_TI3E524 TI3E524 922 ateb9200 MACH_ATEB9200 ATEB9200 923 auckland MACH_AUCKLAND AUCKLAND 924 @@ -2421,3 +2421,118 @@ liberty MACH_LIBERTY LIBERTY 2434 mh355 MACH_MH355 MH355 2435 pc7802 MACH_PC7802 PC7802 2436 gnet_sgc MACH_GNET_SGC GNET_SGC 2437 +einstein15 MACH_EINSTEIN15 EINSTEIN15 2438 +cmpd MACH_CMPD CMPD 2439 +davinci_hase1 MACH_DAVINCI_HASE1 DAVINCI_HASE1 2440 +lgeincitephone MACH_LGEINCITEPHONE LGEINCITEPHONE 2441 +ea313x MACH_EA313X EA313X 2442 +fwbd_39064 MACH_FWBD_39064 FWBD_39064 2443 +fwbd_390128 MACH_FWBD_390128 FWBD_390128 2444 +pelco_moe MACH_PELCO_MOE PELCO_MOE 2445 +minimix27 MACH_MINIMIX27 MINIMIX27 2446 +omap3_thunder MACH_OMAP3_THUNDER OMAP3_THUNDER 2447 +passionc MACH_PASSIONC PASSIONC 2448 +mx27amata MACH_MX27AMATA MX27AMATA 2449 +bgat1 MACH_BGAT1 BGAT1 2450 +buzz MACH_BUZZ BUZZ 2451 +mb9g20 MACH_MB9G20 MB9G20 2452 +yushan MACH_YUSHAN YUSHAN 2453 +lizard MACH_LIZARD LIZARD 2454 +omap3polycom MACH_OMAP3POLYCOM OMAP3POLYCOM 2455 +smdkv210 MACH_SMDKV210 SMDKV210 2456 +bravo MACH_BRAVO BRAVO 2457 +siogentoo1 MACH_SIOGENTOO1 SIOGENTOO1 2458 +siogentoo2 MACH_SIOGENTOO2 SIOGENTOO2 2459 +sm3k MACH_SM3K SM3K 2460 +acer_tempo_f900 MACH_ACER_TEMPO_F900 ACER_TEMPO_F900 2461 +sst61vc010_dev MACH_SST61VC010_DEV SST61VC010_DEV 2462 +glittertind MACH_GLITTERTIND GLITTERTIND 2463 +omap_zoom3 MACH_OMAP_ZOOM3 OMAP_ZOOM3 2464 +omap_3630sdp MACH_OMAP_3630SDP OMAP_3630SDP 2465 +cybook2440 MACH_CYBOOK2440 CYBOOK2440 2466 +torino_s MACH_TORINO_S TORINO_S 2467 +havana MACH_HAVANA HAVANA 2468 +beaumont_11 MACH_BEAUMONT_11 BEAUMONT_11 2469 +vanguard MACH_VANGUARD VANGUARD 2470 +s5pc110_draco MACH_S5PC110_DRACO S5PC110_DRACO 2471 +cartesio_two MACH_CARTESIO_TWO CARTESIO_TWO 2472 +aster MACH_ASTER ASTER 2473 +voguesv210 MACH_VOGUESV210 VOGUESV210 2474 +acm500x MACH_ACM500X ACM500X 2475 +km9260 MACH_KM9260 KM9260 2476 +nideflexg1 MACH_NIDEFLEXG1 NIDEFLEXG1 2477 +ctera_plug_io MACH_CTERA_PLUG_IO CTERA_PLUG_IO 2478 +smartq7 MACH_SMARTQ7 SMARTQ7 2479 +at91sam9g10ek2 MACH_AT91SAM9G10EK2 AT91SAM9G10EK2 2480 +asusp527 MACH_ASUSP527 ASUSP527 2481 +at91sam9g20mpm2 MACH_AT91SAM9G20MPM2 AT91SAM9G20MPM2 2482 +topasa900 MACH_TOPASA900 TOPASA900 2483 +electrum_100 MACH_ELECTRUM_100 ELECTRUM_100 2484 +mx51grb MACH_MX51GRB MX51GRB 2485 +xea300 MACH_XEA300 XEA300 2486 +htcstartrek MACH_HTCSTARTREK HTCSTARTREK 2487 +lima MACH_LIMA LIMA 2488 +csb740 MACH_CSB740 CSB740 2489 +usb_s8815 MACH_USB_S8815 USB_S8815 2490 +watson_efm_plugin MACH_WATSON_EFM_PLUGIN WATSON_EFM_PLUGIN 2491 +milkyway MACH_MILKYWAY MILKYWAY 2492 +g4evm MACH_G4EVM G4EVM 2493 +picomod6 MACH_PICOMOD6 PICOMOD6 2494 +omapl138_hawkboard MACH_OMAPL138_HAWKBOARD OMAPL138_HAWKBOARD 2495 +ip6000 MACH_IP6000 IP6000 2496 +ip6010 MACH_IP6010 IP6010 2497 +utm400 MACH_UTM400 UTM400 2498 +omap3_zybex MACH_OMAP3_ZYBEX OMAP3_ZYBEX 2499 +wireless_space MACH_WIRELESS_SPACE WIRELESS_SPACE 2500 +sx560 MACH_SX560 SX560 2501 +ts41x MACH_TS41X TS41X 2502 +elphel10373 MACH_ELPHEL10373 ELPHEL10373 2503 +rhobot MACH_RHOBOT RHOBOT 2504 +mx51_refresh MACH_MX51_REFRESH MX51_REFRESH 2505 +ls9260 MACH_LS9260 LS9260 2506 +shank MACH_SHANK SHANK 2507 +qsd8x50_st1 MACH_QSD8X50_ST1 QSD8X50_ST1 2508 +at91sam9m10ekes MACH_AT91SAM9M10EKES AT91SAM9M10EKES 2509 +hiram MACH_HIRAM HIRAM 2510 +phy3250 MACH_PHY3250 PHY3250 2511 +ea3250 MACH_EA3250 EA3250 2512 +fdi3250 MACH_FDI3250 FDI3250 2513 +whitestone MACH_WHITESTONE WHITESTONE 2514 +at91sam9263nit MACH_AT91SAM9263NIT AT91SAM9263NIT 2515 +ccmx51 MACH_CCMX51 CCMX51 2516 +ccmx51js MACH_CCMX51JS CCMX51JS 2517 +ccwmx51 MACH_CCWMX51 CCWMX51 2518 +ccwmx51js MACH_CCWMX51JS CCWMX51JS 2519 +mini6410 MACH_MINI6410 MINI6410 2520 +tiny6410 MACH_TINY6410 TINY6410 2521 +nano6410 MACH_NANO6410 NANO6410 2522 +at572d940hfnldb MACH_AT572D940HFNLDB AT572D940HFNLDB 2523 +htcleo MACH_HTCLEO HTCLEO 2524 +avp13 MACH_AVP13 AVP13 2525 +xxsvideod MACH_XXSVIDEOD XXSVIDEOD 2526 +vpnext MACH_VPNEXT VPNEXT 2527 +swarco_itc3 MACH_SWARCO_ITC3 SWARCO_ITC3 2528 +tx51 MACH_TX51 TX51 2529 +dolby_cat1021 MACH_DOLBY_CAT1021 DOLBY_CAT1021 2530 +mx28evk MACH_MX28EVK MX28EVK 2531 +phoenix260 MACH_PHOENIX260 PHOENIX260 2532 +uvaca_stork MACH_UVACA_STORK UVACA_STORK 2533 +smartq5 MACH_SMARTQ5 SMARTQ5 2534 +all3078 MACH_ALL3078 ALL3078 2535 +ctera_2bay_ds MACH_CTERA_2BAY_DS CTERA_2BAY_DS 2536 +siogentoo3 MACH_SIOGENTOO3 SIOGENTOO3 2537 +epb5000 MACH_EPB5000 EPB5000 2538 +hy9263 MACH_HY9263 HY9263 2539 +acer_tempo_m900 MACH_ACER_TEMPO_M900 ACER_TEMPO_M900 2540 +acer_tempo_dx650 MACH_ACER_TEMPO_DX900 ACER_TEMPO_DX900 2541 +acer_tempo_x960 MACH_ACER_TEMPO_X960 ACER_TEMPO_X960 2542 +acer_eten_v900 MACH_ACER_ETEN_V900 ACER_ETEN_V900 2543 +acer_eten_x900 MACH_ACER_ETEN_X900 ACER_ETEN_X900 2544 +bonnell MACH_BONNELL BONNELL 2545 +oht_mx27 MACH_OHT_MX27 OHT_MX27 2546 +htcquartz MACH_HTCQUARTZ HTCQUARTZ 2547 +davinci_dm6467tevm MACH_DAVINCI_DM6467TEVM DAVINCI_DM6467TEVM 2548 +c3ax03 MACH_C3AX03 C3AX03 2549 +mxt_td60 MACH_MXT_TD60 MXT_TD60 2550 +esyx MACH_ESYX ESYX 2551 +bulldog MACH_BULLDOG BULLDOG 2553 diff --git a/arch/avr32/include/asm/bug.h b/arch/avr32/include/asm/bug.h index 331d45bab18f..2aa373cc61b5 100644 --- a/arch/avr32/include/asm/bug.h +++ b/arch/avr32/include/asm/bug.h @@ -52,7 +52,7 @@ #define BUG() \ do { \ _BUG_OR_WARN(0); \ - for (;;); \ + unreachable(); \ } while (0) #define WARN_ON(condition) \ diff --git a/arch/blackfin/kernel/bfin_dma_5xx.c b/arch/blackfin/kernel/bfin_dma_5xx.c index 1f170216d2f9..3946aff4f414 100644 --- a/arch/blackfin/kernel/bfin_dma_5xx.c +++ b/arch/blackfin/kernel/bfin_dma_5xx.c @@ -225,8 +225,13 @@ int blackfin_dma_suspend(void) void blackfin_dma_resume(void) { int i; - for (i = 0; i < MAX_DMA_SUSPEND_CHANNELS; ++i) - dma_ch[i].regs->peripheral_map = dma_ch[i].saved_peripheral_map; + + for (i = 0; i < MAX_DMA_CHANNELS; ++i) { + dma_ch[i].regs->cfg = 0; + + if (i < MAX_DMA_SUSPEND_CHANNELS) + dma_ch[i].regs->peripheral_map = dma_ch[i].saved_peripheral_map; + } } #endif diff --git a/arch/blackfin/kernel/cplb-mpu/cplbinit.c b/arch/blackfin/kernel/cplb-mpu/cplbinit.c index f7b9cdce8239..b52c1f8c4bc0 100644 --- a/arch/blackfin/kernel/cplb-mpu/cplbinit.c +++ b/arch/blackfin/kernel/cplb-mpu/cplbinit.c @@ -38,7 +38,7 @@ void __init generate_cplb_tables_cpu(unsigned int cpu) #ifdef CONFIG_BFIN_EXTMEM_DCACHEABLE d_cache = CPLB_L1_CHBL; -#ifdef CONFIG_BFIN_EXTMEM_WRITETROUGH +#ifdef CONFIG_BFIN_EXTMEM_WRITETHROUGH d_cache |= CPLB_L1_AOW | CPLB_WT; #endif #endif diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c index 430ae39456e8..5cc7e2e9e415 100644 --- a/arch/blackfin/kernel/process.c +++ b/arch/blackfin/kernel/process.c @@ -151,7 +151,7 @@ void start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_ regs->pc = new_ip; if (current->mm) regs->p5 = current->mm->start_data; -#ifdef CONFIG_SMP +#ifndef CONFIG_SMP task_thread_info(current)->l1_task_info.stack_start = (void *)current->mm->context.stack_start; task_thread_info(current)->l1_task_info.lowest_sp = (void *)new_sp; diff --git a/arch/blackfin/kernel/ptrace.c b/arch/blackfin/kernel/ptrace.c index 0982b5d5af10..56b0ba12175f 100644 --- a/arch/blackfin/kernel/ptrace.c +++ b/arch/blackfin/kernel/ptrace.c @@ -315,7 +315,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) case BFIN_MEM_ACCESS_CORE: case BFIN_MEM_ACCESS_CORE_ONLY: copied = access_process_vm(child, addr, &data, - to_copy, 0); + to_copy, 1); if (copied) break; diff --git a/arch/blackfin/mach-bf518/include/mach/anomaly.h b/arch/blackfin/mach-bf518/include/mach/anomaly.h index e9c65390edd1..2829dd0400f1 100644 --- a/arch/blackfin/mach-bf518/include/mach/anomaly.h +++ b/arch/blackfin/mach-bf518/include/mach/anomaly.h @@ -1,9 +1,13 @@ /* - * File: include/asm-blackfin/mach-bf518/anomaly.h - * Bugs: Enter bugs at http://blackfin.uclinux.org/ + * DO NOT EDIT THIS FILE + * This file is under version control at + * svn://sources.blackfin.uclinux.org/toolchain/trunk/proc-defs/header-frags/ + * and can be replaced with that version at any time + * DO NOT EDIT THIS FILE * - * Copyright (C) 2004-2009 Analog Devices Inc. - * Licensed under the GPL-2 or later. + * Copyright 2004-2009 Analog Devices Inc. + * Licensed under the ADI BSD license. + * https://docs.blackfin.uclinux.org/doku.php?id=adi_bsd */ /* This file should be up to date with: @@ -70,6 +74,10 @@ #define ANOMALY_05000461 (1) /* Synchronization Problem at Startup May Cause SPORT Transmit Channels to Misalign */ #define ANOMALY_05000462 (1) +/* Interrupted 32-Bit SPORT Data Register Access Results In Underflow */ +#define ANOMALY_05000473 (1) +/* TESTSET Instruction Cannot Be Interrupted */ +#define ANOMALY_05000477 (1) /* Anomalies that don't exist on this proc */ #define ANOMALY_05000099 (0) @@ -133,5 +141,7 @@ #define ANOMALY_05000450 (0) #define ANOMALY_05000465 (0) #define ANOMALY_05000467 (0) +#define ANOMALY_05000474 (0) +#define ANOMALY_05000475 (0) #endif diff --git a/arch/blackfin/mach-bf527/include/mach/anomaly.h b/arch/blackfin/mach-bf527/include/mach/anomaly.h index 3f9052687fa8..02040df8ec80 100644 --- a/arch/blackfin/mach-bf527/include/mach/anomaly.h +++ b/arch/blackfin/mach-bf527/include/mach/anomaly.h @@ -1,14 +1,18 @@ /* - * File: include/asm-blackfin/mach-bf527/anomaly.h - * Bugs: Enter bugs at http://blackfin.uclinux.org/ + * DO NOT EDIT THIS FILE + * This file is under version control at + * svn://sources.blackfin.uclinux.org/toolchain/trunk/proc-defs/header-frags/ + * and can be replaced with that version at any time + * DO NOT EDIT THIS FILE * - * Copyright (C) 2004-2009 Analog Devices Inc. - * Licensed under the GPL-2 or later. + * Copyright 2004-2009 Analog Devices Inc. + * Licensed under the ADI BSD license. + * https://docs.blackfin.uclinux.org/doku.php?id=adi_bsd */ /* This file should be up to date with: * - Revision D, 08/14/2009; ADSP-BF526 Blackfin Processor Anomaly List - * - Revision F, 03/03/2009; ADSP-BF527 Blackfin Processor Anomaly List + * - Revision G, 08/25/2009; ADSP-BF527 Blackfin Processor Anomaly List */ #ifndef _MACH_ANOMALY_H_ @@ -200,6 +204,10 @@ #define ANOMALY_05000467 (1) /* PLL Latches Incorrect Settings During Reset */ #define ANOMALY_05000469 (1) +/* Interrupted 32-Bit SPORT Data Register Access Results In Underflow */ +#define ANOMALY_05000473 (1) +/* TESTSET Instruction Cannot Be Interrupted */ +#define ANOMALY_05000477 (1) /* Anomalies that don't exist on this proc */ #define ANOMALY_05000099 (0) @@ -250,5 +258,7 @@ #define ANOMALY_05000412 (0) #define ANOMALY_05000447 (0) #define ANOMALY_05000448 (0) +#define ANOMALY_05000474 (0) +#define ANOMALY_05000475 (0) #endif diff --git a/arch/blackfin/mach-bf533/include/mach/anomaly.h b/arch/blackfin/mach-bf533/include/mach/anomaly.h index cd83db2fb1a1..9b3f7a27714d 100644 --- a/arch/blackfin/mach-bf533/include/mach/anomaly.h +++ b/arch/blackfin/mach-bf533/include/mach/anomaly.h @@ -1,9 +1,13 @@ /* - * File: include/asm-blackfin/mach-bf533/anomaly.h - * Bugs: Enter bugs at http://blackfin.uclinux.org/ + * DO NOT EDIT THIS FILE + * This file is under version control at + * svn://sources.blackfin.uclinux.org/toolchain/trunk/proc-defs/header-frags/ + * and can be replaced with that version at any time + * DO NOT EDIT THIS FILE * - * Copyright (C) 2004-2009 Analog Devices Inc. - * Licensed under the GPL-2 or later. + * Copyright 2004-2009 Analog Devices Inc. + * Licensed under the ADI BSD license. + * https://docs.blackfin.uclinux.org/doku.php?id=adi_bsd */ /* This file should be up to date with: @@ -202,6 +206,10 @@ #define ANOMALY_05000443 (1) /* False Hardware Error when RETI Points to Invalid Memory */ #define ANOMALY_05000461 (1) +/* Interrupted 32-Bit SPORT Data Register Access Results In Underflow */ +#define ANOMALY_05000473 (1) +/* TESTSET Instruction Cannot Be Interrupted */ +#define ANOMALY_05000477 (1) /* These anomalies have been "phased" out of analog.com anomaly sheets and are * here to show running on older silicon just isn't feasible. @@ -349,5 +357,7 @@ #define ANOMALY_05000450 (0) #define ANOMALY_05000465 (0) #define ANOMALY_05000467 (0) +#define ANOMALY_05000474 (0) +#define ANOMALY_05000475 (0) #endif diff --git a/arch/blackfin/mach-bf537/include/mach/anomaly.h b/arch/blackfin/mach-bf537/include/mach/anomaly.h index f091ad2d8ea8..d2c427bc6656 100644 --- a/arch/blackfin/mach-bf537/include/mach/anomaly.h +++ b/arch/blackfin/mach-bf537/include/mach/anomaly.h @@ -1,9 +1,13 @@ /* - * File: include/asm-blackfin/mach-bf537/anomaly.h - * Bugs: Enter bugs at http://blackfin.uclinux.org/ + * DO NOT EDIT THIS FILE + * This file is under version control at + * svn://sources.blackfin.uclinux.org/toolchain/trunk/proc-defs/header-frags/ + * and can be replaced with that version at any time + * DO NOT EDIT THIS FILE * - * Copyright (C) 2004-2009 Analog Devices Inc. - * Licensed under the GPL-2 or later. + * Copyright 2004-2009 Analog Devices Inc. + * Licensed under the ADI BSD license. + * https://docs.blackfin.uclinux.org/doku.php?id=adi_bsd */ /* This file should be up to date with: @@ -156,6 +160,10 @@ #define ANOMALY_05000443 (1) /* False Hardware Error when RETI Points to Invalid Memory */ #define ANOMALY_05000461 (1) +/* Interrupted 32-Bit SPORT Data Register Access Results In Underflow */ +#define ANOMALY_05000473 (1) +/* TESTSET Instruction Cannot Be Interrupted */ +#define ANOMALY_05000477 (1) /* Anomalies that don't exist on this proc */ #define ANOMALY_05000099 (0) @@ -202,5 +210,7 @@ #define ANOMALY_05000450 (0) #define ANOMALY_05000465 (0) #define ANOMALY_05000467 (0) +#define ANOMALY_05000474 (0) +#define ANOMALY_05000475 (0) #endif diff --git a/arch/blackfin/mach-bf538/include/mach/anomaly.h b/arch/blackfin/mach-bf538/include/mach/anomaly.h index 26b76083e14c..d882b7e6f59b 100644 --- a/arch/blackfin/mach-bf538/include/mach/anomaly.h +++ b/arch/blackfin/mach-bf538/include/mach/anomaly.h @@ -1,9 +1,13 @@ /* - * File: include/asm-blackfin/mach-bf538/anomaly.h - * Bugs: Enter bugs at http://blackfin.uclinux.org/ + * DO NOT EDIT THIS FILE + * This file is under version control at + * svn://sources.blackfin.uclinux.org/toolchain/trunk/proc-defs/header-frags/ + * and can be replaced with that version at any time + * DO NOT EDIT THIS FILE * - * Copyright (C) 2004-2009 Analog Devices Inc. - * Licensed under the GPL-2 or later. + * Copyright 2004-2009 Analog Devices Inc. + * Licensed under the ADI BSD license. + * https://docs.blackfin.uclinux.org/doku.php?id=adi_bsd */ /* This file should be up to date with: @@ -128,6 +132,10 @@ #define ANOMALY_05000443 (1) /* False Hardware Error when RETI Points to Invalid Memory */ #define ANOMALY_05000461 (1) +/* Interrupted 32-Bit SPORT Data Register Access Results In Underflow */ +#define ANOMALY_05000473 (1) +/* TESTSET Instruction Cannot Be Interrupted */ +#define ANOMALY_05000477 (1) /* Anomalies that don't exist on this proc */ #define ANOMALY_05000099 (0) @@ -176,5 +184,7 @@ #define ANOMALY_05000450 (0) #define ANOMALY_05000465 (0) #define ANOMALY_05000467 (0) +#define ANOMALY_05000474 (0) +#define ANOMALY_05000475 (0) #endif diff --git a/arch/blackfin/mach-bf548/include/mach/anomaly.h b/arch/blackfin/mach-bf548/include/mach/anomaly.h index 52b116ae522a..7d08c7524498 100644 --- a/arch/blackfin/mach-bf548/include/mach/anomaly.h +++ b/arch/blackfin/mach-bf548/include/mach/anomaly.h @@ -1,9 +1,13 @@ /* - * File: include/asm-blackfin/mach-bf548/anomaly.h - * Bugs: Enter bugs at http://blackfin.uclinux.org/ + * DO NOT EDIT THIS FILE + * This file is under version control at + * svn://sources.blackfin.uclinux.org/toolchain/trunk/proc-defs/header-frags/ + * and can be replaced with that version at any time + * DO NOT EDIT THIS FILE * - * Copyright (C) 2004-2009 Analog Devices Inc. - * Licensed under the GPL-2 or later. + * Copyright 2004-2009 Analog Devices Inc. + * Licensed under the ADI BSD license. + * https://docs.blackfin.uclinux.org/doku.php?id=adi_bsd */ /* This file should be up to date with: @@ -24,6 +28,8 @@ #define ANOMALY_05000119 (1) /* Rx.H Cannot Be Used to Access 16-bit System MMR Registers */ #define ANOMALY_05000122 (1) +/* Data Corruption with Cached External Memory and Non-Cached On-Chip L2 Memory */ +#define ANOMALY_05000220 (1) /* False Hardware Error from an Access in the Shadow of a Conditional Branch */ #define ANOMALY_05000245 (1) /* Sensitivity To Noise with Slow Input Edge Rates on External SPORT TX and RX Clocks */ @@ -200,6 +206,14 @@ #define ANOMALY_05000466 (1) /* Possible RX data corruption when control & data EP FIFOs are accessed via the core */ #define ANOMALY_05000467 (1) +/* Interrupted 32-Bit SPORT Data Register Access Results In Underflow */ +#define ANOMALY_05000473 (1) +/* Access to DDR-SDRAM causes system hang under certain PLL/VR settings */ +#define ANOMALY_05000474 (1) +/* Core Hang With L2/L3 Configured in Writeback Cache Mode */ +#define ANOMALY_05000475 (1) +/* TESTSET Instruction Cannot Be Interrupted */ +#define ANOMALY_05000477 (1) /* Anomalies that don't exist on this proc */ #define ANOMALY_05000099 (0) @@ -215,7 +229,6 @@ #define ANOMALY_05000198 (0) #define ANOMALY_05000202 (0) #define ANOMALY_05000215 (0) -#define ANOMALY_05000220 (0) #define ANOMALY_05000227 (0) #define ANOMALY_05000230 (0) #define ANOMALY_05000231 (0) diff --git a/arch/blackfin/mach-bf561/atomic.S b/arch/blackfin/mach-bf561/atomic.S index 0261a5e751b3..f99f174b129f 100644 --- a/arch/blackfin/mach-bf561/atomic.S +++ b/arch/blackfin/mach-bf561/atomic.S @@ -19,6 +19,16 @@ \reg\().h = _corelock; .endm +.macro safe_testset addr:req, scratch:req +#if ANOMALY_05000477 + cli \scratch; + testset (\addr); + sti \scratch; +#else + testset (\addr); +#endif +.endm + /* * r0 = address of atomic data to flush and invalidate (32bit). * @@ -33,7 +43,7 @@ ENTRY(_get_core_lock) cli r0; coreslot_loadaddr p0; .Lretry_corelock: - testset (p0); + safe_testset p0, r2; if cc jump .Ldone_corelock; SSYNC(r2); jump .Lretry_corelock @@ -56,7 +66,7 @@ ENTRY(_get_core_lock_noflush) cli r0; coreslot_loadaddr p0; .Lretry_corelock_noflush: - testset (p0); + safe_testset p0, r2; if cc jump .Ldone_corelock_noflush; SSYNC(r2); jump .Lretry_corelock_noflush diff --git a/arch/blackfin/mach-bf561/include/mach/anomaly.h b/arch/blackfin/mach-bf561/include/mach/anomaly.h index 70da495c9665..5ddc981e9937 100644 --- a/arch/blackfin/mach-bf561/include/mach/anomaly.h +++ b/arch/blackfin/mach-bf561/include/mach/anomaly.h @@ -1,9 +1,13 @@ /* - * File: include/asm-blackfin/mach-bf561/anomaly.h - * Bugs: Enter bugs at http://blackfin.uclinux.org/ + * DO NOT EDIT THIS FILE + * This file is under version control at + * svn://sources.blackfin.uclinux.org/toolchain/trunk/proc-defs/header-frags/ + * and can be replaced with that version at any time + * DO NOT EDIT THIS FILE * - * Copyright (C) 2004-2009 Analog Devices Inc. - * Licensed under the GPL-2 or later. + * Copyright 2004-2009 Analog Devices Inc. + * Licensed under the ADI BSD license. + * https://docs.blackfin.uclinux.org/doku.php?id=adi_bsd */ /* This file should be up to date with: @@ -213,7 +217,11 @@ /* Disabling Peripherals with DMA Running May Cause DMA System Instability */ #define ANOMALY_05000278 (__SILICON_REVISION__ < 5) /* False Hardware Error Exception when ISR Context Is Not Restored */ -#define ANOMALY_05000281 (__SILICON_REVISION__ < 5) +/* Temporarily walk around for bug 5423 till this issue is confirmed by + * official anomaly document. It looks 05000281 still exists on bf561 + * v0.5. + */ +#define ANOMALY_05000281 (__SILICON_REVISION__ <= 5) /* System MMR Write Is Stalled Indefinitely when Killed in a Particular Stage */ #define ANOMALY_05000283 (1) /* Reads Will Receive Incorrect Data under Certain Conditions */ @@ -280,6 +288,12 @@ #define ANOMALY_05000443 (1) /* False Hardware Error when RETI Points to Invalid Memory */ #define ANOMALY_05000461 (1) +/* Interrupted 32-Bit SPORT Data Register Access Results In Underflow */ +#define ANOMALY_05000473 (1) +/* Core Hang With L2/L3 Configured in Writeback Cache Mode */ +#define ANOMALY_05000475 (__SILICON_REVISION__ < 4) +/* TESTSET Instruction Cannot Be Interrupted */ +#define ANOMALY_05000477 (1) /* Anomalies that don't exist on this proc */ #define ANOMALY_05000119 (0) @@ -304,5 +318,6 @@ #define ANOMALY_05000450 (0) #define ANOMALY_05000465 (0) #define ANOMALY_05000467 (0) +#define ANOMALY_05000474 (0) #endif diff --git a/arch/blackfin/mach-common/arch_checks.c b/arch/blackfin/mach-common/arch_checks.c index 9dbafcdcf479..f2ca211a76a0 100644 --- a/arch/blackfin/mach-common/arch_checks.c +++ b/arch/blackfin/mach-common/arch_checks.c @@ -57,3 +57,8 @@ (!defined(CONFIG_BFIN_EXTMEM_DCACHEABLE) && defined(CONFIG_BFIN_L2_WRITEBACK))) # error You are exposing Anomaly 220 in this config, either config L2 as Write Through, or make External Memory WB. #endif + +#if ANOMALY_05000475 && \ + (defined(CONFIG_BFIN_EXTMEM_WRITEBACK) || defined(CONFIG_BFIN_L2_WRITEBACK)) +# error "Anomaly 475 does not allow you to use Write Back cache with L2 or External Memory" +#endif diff --git a/arch/blackfin/mach-common/smp.c b/arch/blackfin/mach-common/smp.c index d98585f3237d..d92b168c8328 100644 --- a/arch/blackfin/mach-common/smp.c +++ b/arch/blackfin/mach-common/smp.c @@ -276,10 +276,9 @@ void smp_send_reschedule(int cpu) if (cpu_is_offline(cpu)) return; - msg = kmalloc(sizeof(*msg), GFP_ATOMIC); + msg = kzalloc(sizeof(*msg), GFP_ATOMIC); if (!msg) return; - memset(msg, 0, sizeof(msg)); INIT_LIST_HEAD(&msg->list); msg->type = BFIN_IPI_RESCHEDULE; @@ -305,10 +304,9 @@ void smp_send_stop(void) if (cpus_empty(callmap)) return; - msg = kmalloc(sizeof(*msg), GFP_ATOMIC); + msg = kzalloc(sizeof(*msg), GFP_ATOMIC); if (!msg) return; - memset(msg, 0, sizeof(msg)); INIT_LIST_HEAD(&msg->list); msg->type = BFIN_IPI_CPU_STOP; diff --git a/arch/frv/kernel/pm.c b/arch/frv/kernel/pm.c index 0d4d3e3a4cfc..5fa3889d858b 100644 --- a/arch/frv/kernel/pm.c +++ b/arch/frv/kernel/pm.c @@ -211,37 +211,6 @@ static int cmode_procctl(ctl_table *ctl, int write, return try_set_cmode(new_cmode)?:*lenp; } -static int cmode_sysctl(ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - if (oldval && oldlenp) { - size_t oldlen; - - if (get_user(oldlen, oldlenp)) - return -EFAULT; - - if (oldlen != sizeof(int)) - return -EINVAL; - - if (put_user(clock_cmode_current, (unsigned __user *)oldval) || - put_user(sizeof(int), oldlenp)) - return -EFAULT; - } - if (newval && newlen) { - int new_cmode; - - if (newlen != sizeof(int)) - return -EINVAL; - - if (get_user(new_cmode, (int __user *)newval)) - return -EFAULT; - - return try_set_cmode(new_cmode)?:1; - } - return 1; -} - static int try_set_p0(int new_p0) { unsigned long flags, clkc; @@ -314,37 +283,6 @@ static int p0_procctl(ctl_table *ctl, int write, return try_set_p0(new_p0)?:*lenp; } -static int p0_sysctl(ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - if (oldval && oldlenp) { - size_t oldlen; - - if (get_user(oldlen, oldlenp)) - return -EFAULT; - - if (oldlen != sizeof(int)) - return -EINVAL; - - if (put_user(clock_p0_current, (unsigned __user *)oldval) || - put_user(sizeof(int), oldlenp)) - return -EFAULT; - } - if (newval && newlen) { - int new_p0; - - if (newlen != sizeof(int)) - return -EINVAL; - - if (get_user(new_p0, (int __user *)newval)) - return -EFAULT; - - return try_set_p0(new_p0)?:1; - } - return 1; -} - static int cm_procctl(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *fpos) { @@ -358,87 +296,47 @@ static int cm_procctl(ctl_table *ctl, int write, return try_set_cm(new_cm)?:*lenp; } -static int cm_sysctl(ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - if (oldval && oldlenp) { - size_t oldlen; - - if (get_user(oldlen, oldlenp)) - return -EFAULT; - - if (oldlen != sizeof(int)) - return -EINVAL; - - if (put_user(clock_cm_current, (unsigned __user *)oldval) || - put_user(sizeof(int), oldlenp)) - return -EFAULT; - } - if (newval && newlen) { - int new_cm; - - if (newlen != sizeof(int)) - return -EINVAL; - - if (get_user(new_cm, (int __user *)newval)) - return -EFAULT; - - return try_set_cm(new_cm)?:1; - } - return 1; -} - - static struct ctl_table pm_table[] = { { - .ctl_name = CTL_PM_SUSPEND, .procname = "suspend", .data = NULL, .maxlen = 0, .mode = 0200, - .proc_handler = &sysctl_pm_do_suspend, + .proc_handler = sysctl_pm_do_suspend, }, { - .ctl_name = CTL_PM_CMODE, .procname = "cmode", .data = &clock_cmode_current, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &cmode_procctl, - .strategy = &cmode_sysctl, + .proc_handler = cmode_procctl, }, { - .ctl_name = CTL_PM_P0, .procname = "p0", .data = &clock_p0_current, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &p0_procctl, - .strategy = &p0_sysctl, + .proc_handler = p0_procctl, }, { - .ctl_name = CTL_PM_CM, .procname = "cm", .data = &clock_cm_current, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &cm_procctl, - .strategy = &cm_sysctl, + .proc_handler = cm_procctl, }, - { .ctl_name = 0} + { } }; static struct ctl_table pm_dir_table[] = { { - .ctl_name = CTL_PM, .procname = "pm", .mode = 0555, .child = pm_table, }, - { .ctl_name = 0} + { } }; /* diff --git a/arch/frv/kernel/sysctl.c b/arch/frv/kernel/sysctl.c index 3e9d7e03fb95..035516cb7a97 100644 --- a/arch/frv/kernel/sysctl.c +++ b/arch/frv/kernel/sysctl.c @@ -176,21 +176,19 @@ static int procctl_frv_pin_cxnr(ctl_table *table, int write, struct file *filp, static struct ctl_table frv_table[] = { { - .ctl_name = 1, .procname = "cache-mode", .data = NULL, .maxlen = 0, .mode = 0644, - .proc_handler = &procctl_frv_cachemode, + .proc_handler = procctl_frv_cachemode, }, #ifdef CONFIG_MMU { - .ctl_name = 2, .procname = "pin-cxnr", .data = NULL, .maxlen = 0, .mode = 0644, - .proc_handler = &procctl_frv_pin_cxnr + .proc_handler = procctl_frv_pin_cxnr }, #endif {} @@ -203,7 +201,6 @@ static struct ctl_table frv_table[] = static struct ctl_table frv_dir_table[] = { { - .ctl_name = CTL_FRV, .procname = "frv", .mode = 0555, .child = frv_table diff --git a/arch/ia64/ia32/ia32_entry.S b/arch/ia64/ia32/ia32_entry.S index af9405cd70e5..10c37510f4b4 100644 --- a/arch/ia64/ia32/ia32_entry.S +++ b/arch/ia64/ia32/ia32_entry.S @@ -327,7 +327,7 @@ ia32_syscall_table: data8 compat_sys_writev data8 sys_getsid data8 sys_fdatasync - data8 sys32_sysctl + data8 compat_sys_sysctl data8 sys_mlock /* 150 */ data8 sys_munlock data8 sys_mlockall diff --git a/arch/ia64/ia32/sys_ia32.c b/arch/ia64/ia32/sys_ia32.c index 625ed8f76fce..429ec968c9ee 100644 --- a/arch/ia64/ia32/sys_ia32.c +++ b/arch/ia64/ia32/sys_ia32.c @@ -1628,61 +1628,6 @@ sys32_msync (unsigned int start, unsigned int len, int flags) return sys_msync(addr, len + (start - addr), flags); } -struct sysctl32 { - unsigned int name; - int nlen; - unsigned int oldval; - unsigned int oldlenp; - unsigned int newval; - unsigned int newlen; - unsigned int __unused[4]; -}; - -#ifdef CONFIG_SYSCTL_SYSCALL -asmlinkage long -sys32_sysctl (struct sysctl32 __user *args) -{ - struct sysctl32 a32; - mm_segment_t old_fs = get_fs (); - void __user *oldvalp, *newvalp; - size_t oldlen; - int __user *namep; - long ret; - - if (copy_from_user(&a32, args, sizeof(a32))) - return -EFAULT; - - /* - * We need to pre-validate these because we have to disable address checking - * before calling do_sysctl() because of OLDLEN but we can't run the risk of the - * user specifying bad addresses here. Well, since we're dealing with 32 bit - * addresses, we KNOW that access_ok() will always succeed, so this is an - * expensive NOP, but so what... - */ - namep = (int __user *) compat_ptr(a32.name); - oldvalp = compat_ptr(a32.oldval); - newvalp = compat_ptr(a32.newval); - - if ((oldvalp && get_user(oldlen, (int __user *) compat_ptr(a32.oldlenp))) - || !access_ok(VERIFY_WRITE, namep, 0) - || !access_ok(VERIFY_WRITE, oldvalp, 0) - || !access_ok(VERIFY_WRITE, newvalp, 0)) - return -EFAULT; - - set_fs(KERNEL_DS); - lock_kernel(); - ret = do_sysctl(namep, a32.nlen, oldvalp, (size_t __user *) &oldlen, - newvalp, (size_t) a32.newlen); - unlock_kernel(); - set_fs(old_fs); - - if (oldvalp && put_user (oldlen, (int __user *) compat_ptr(a32.oldlenp))) - return -EFAULT; - - return ret; -} -#endif - asmlinkage long sys32_newuname (struct new_utsname __user *name) { diff --git a/arch/ia64/include/asm/swiotlb.h b/arch/ia64/include/asm/swiotlb.h index dcbaea7ce128..f0acde68aaea 100644 --- a/arch/ia64/include/asm/swiotlb.h +++ b/arch/ia64/include/asm/swiotlb.h @@ -4,8 +4,6 @@ #include <linux/dma-mapping.h> #include <linux/swiotlb.h> -extern int swiotlb_force; - #ifdef CONFIG_SWIOTLB extern int swiotlb; extern void pci_swiotlb_init(void); diff --git a/arch/ia64/kernel/crash.c b/arch/ia64/kernel/crash.c index 6631a9dfafdc..b942f4032d7a 100644 --- a/arch/ia64/kernel/crash.c +++ b/arch/ia64/kernel/crash.c @@ -239,32 +239,29 @@ kdump_init_notifier(struct notifier_block *self, unsigned long val, void *data) #ifdef CONFIG_SYSCTL static ctl_table kdump_ctl_table[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "kdump_on_init", .data = &kdump_on_init, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "kdump_on_fatal_mca", .data = &kdump_on_fatal_mca, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, - { .ctl_name = 0 } + { } }; static ctl_table sys_table[] = { { - .ctl_name = CTL_KERN, .procname = "kernel", .mode = 0555, .child = kdump_ctl_table, }, - { .ctl_name = 0 } + { } }; #endif diff --git a/arch/ia64/kernel/pci-swiotlb.c b/arch/ia64/kernel/pci-swiotlb.c index 285aae8431c6..53292abf846c 100644 --- a/arch/ia64/kernel/pci-swiotlb.c +++ b/arch/ia64/kernel/pci-swiotlb.c @@ -41,7 +41,7 @@ struct dma_map_ops swiotlb_dma_ops = { void __init swiotlb_dma_init(void) { dma_ops = &swiotlb_dma_ops; - swiotlb_init(); + swiotlb_init(1); } void __init pci_swiotlb_init(void) @@ -51,7 +51,7 @@ void __init pci_swiotlb_init(void) swiotlb = 1; printk(KERN_INFO "PCI-DMA: Re-initialize machine vector.\n"); machvec_init("dig"); - swiotlb_init(); + swiotlb_init(1); dma_ops = &swiotlb_dma_ops; #else panic("Unable to find Intel IOMMU"); diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index f1782705b1f7..402698b6689f 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -522,42 +522,37 @@ EXPORT_SYMBOL(pfm_sysctl); static ctl_table pfm_ctl_table[]={ { - .ctl_name = CTL_UNNUMBERED, .procname = "debug", .data = &pfm_sysctl.debug, .maxlen = sizeof(int), .mode = 0666, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "debug_ovfl", .data = &pfm_sysctl.debug_ovfl, .maxlen = sizeof(int), .mode = 0666, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "fastctxsw", .data = &pfm_sysctl.fastctxsw, .maxlen = sizeof(int), .mode = 0600, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "expert_mode", .data = &pfm_sysctl.expert_mode, .maxlen = sizeof(int), .mode = 0600, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, {} }; static ctl_table pfm_sysctl_dir[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "perfmon", .mode = 0555, .child = pfm_ctl_table, @@ -566,7 +561,6 @@ static ctl_table pfm_sysctl_dir[] = { }; static ctl_table pfm_sysctl_root[] = { { - .ctl_name = CTL_KERN, .procname = "kernel", .mode = 0555, .child = pfm_sysctl_dir, diff --git a/arch/microblaze/include/asm/prom.h b/arch/microblaze/include/asm/prom.h index 37e6f305a68e..ef3ec1d6ceb3 100644 --- a/arch/microblaze/include/asm/prom.h +++ b/arch/microblaze/include/asm/prom.h @@ -12,23 +12,15 @@ * 2 of the License, or (at your option) any later version. */ +#include <linux/of.h> /* linux/of.h gets to determine #include ordering */ + #ifndef _ASM_MICROBLAZE_PROM_H #define _ASM_MICROBLAZE_PROM_H #ifdef __KERNEL__ - -/* Definitions used by the flattened device tree */ -#define OF_DT_HEADER 0xd00dfeed /* marker */ -#define OF_DT_BEGIN_NODE 0x1 /* Start of node, full name */ -#define OF_DT_END_NODE 0x2 /* End node */ -#define OF_DT_PROP 0x3 /* Property: name off, size, content */ -#define OF_DT_NOP 0x4 /* nop */ -#define OF_DT_END 0x9 - -#define OF_DT_VERSION 0x10 - #ifndef __ASSEMBLY__ #include <linux/types.h> +#include <linux/of_fdt.h> #include <linux/proc_fs.h> #include <linux/platform_device.h> #include <asm/irq.h> @@ -41,122 +33,19 @@ #define of_prop_cmp(s1, s2) strcmp((s1), (s2)) #define of_node_cmp(s1, s2) strcasecmp((s1), (s2)) -/* - * This is what gets passed to the kernel by prom_init or kexec - * - * The dt struct contains the device tree structure, full pathes and - * property contents. The dt strings contain a separate block with just - * the strings for the property names, and is fully page aligned and - * self contained in a page, so that it can be kept around by the kernel, - * each property name appears only once in this page (cheap compression) - * - * the mem_rsvmap contains a map of reserved ranges of physical memory, - * passing it here instead of in the device-tree itself greatly simplifies - * the job of everybody. It's just a list of u64 pairs (base/size) that - * ends when size is 0 - */ -struct boot_param_header { - u32 magic; /* magic word OF_DT_HEADER */ - u32 totalsize; /* total size of DT block */ - u32 off_dt_struct; /* offset to structure */ - u32 off_dt_strings; /* offset to strings */ - u32 off_mem_rsvmap; /* offset to memory reserve map */ - u32 version; /* format version */ - u32 last_comp_version; /* last compatible version */ - /* version 2 fields below */ - u32 boot_cpuid_phys; /* Physical CPU id we're booting on */ - /* version 3 fields below */ - u32 dt_strings_size; /* size of the DT strings block */ - /* version 17 fields below */ - u32 dt_struct_size; /* size of the DT structure block */ -}; - -typedef u32 phandle; -typedef u32 ihandle; - -struct property { - char *name; - int length; - void *value; - struct property *next; -}; - -struct device_node { - const char *name; - const char *type; - phandle node; - phandle linux_phandle; - char *full_name; - - struct property *properties; - struct property *deadprops; /* removed properties */ - struct device_node *parent; - struct device_node *child; - struct device_node *sibling; - struct device_node *next; /* next device of same type */ - struct device_node *allnext; /* next in list of all nodes */ - struct proc_dir_entry *pde; /* this node's proc directory */ - struct kref kref; - unsigned long _flags; - void *data; -}; - extern struct device_node *of_chosen; -static inline int of_node_check_flag(struct device_node *n, unsigned long flag) -{ - return test_bit(flag, &n->_flags); -} - -static inline void of_node_set_flag(struct device_node *n, unsigned long flag) -{ - set_bit(flag, &n->_flags); -} - #define HAVE_ARCH_DEVTREE_FIXUPS -static inline void set_node_proc_entry(struct device_node *dn, - struct proc_dir_entry *de) -{ - dn->pde = de; -} - extern struct device_node *allnodes; /* temporary while merging */ extern rwlock_t devtree_lock; /* temporary while merging */ -extern struct device_node *of_find_all_nodes(struct device_node *prev); -extern struct device_node *of_node_get(struct device_node *node); -extern void of_node_put(struct device_node *node); - -/* For scanning the flat device-tree at boot time */ -extern int __init of_scan_flat_dt(int (*it)(unsigned long node, - const char *uname, int depth, - void *data), - void *data); -extern void *__init of_get_flat_dt_prop(unsigned long node, const char *name, - unsigned long *size); -extern int __init - of_flat_dt_is_compatible(unsigned long node, const char *name); -extern unsigned long __init of_get_flat_dt_root(void); - /* For updating the device tree at runtime */ extern void of_attach_node(struct device_node *); extern void of_detach_node(struct device_node *); /* Other Prototypes */ -extern void finish_device_tree(void); -extern void unflatten_device_tree(void); extern int early_uartlite_console(void); -extern void early_init_devtree(void *); -extern int machine_is_compatible(const char *compat); -extern void print_properties(struct device_node *node); -extern int prom_n_intr_cells(struct device_node *np); -extern void prom_get_irq_senses(unsigned char *senses, int off, int max); -extern int prom_add_property(struct device_node *np, struct property *prop); -extern int prom_remove_property(struct device_node *np, struct property *prop); -extern int prom_update_property(struct device_node *np, - struct property *newprop, - struct property *oldprop); extern struct resource *request_OF_resource(struct device_node *node, int index, const char *name_postfix); @@ -166,18 +55,6 @@ extern int release_OF_resource(struct device_node *node, int index); * OF address retreival & translation */ -/* Helper to read a big number; size is in cells (not bytes) */ -static inline u64 of_read_number(const u32 *cell, int size) -{ - u64 r = 0; - while (size--) - r = (r << 32) | *(cell++); - return r; -} - -/* Like of_read_number, but we want an unsigned long result */ -#define of_read_ulong(cell, size) of_read_number(cell, size) - /* Translate an OF address block into a CPU physical address */ extern u64 of_translate_address(struct device_node *np, const u32 *addr); @@ -305,12 +182,6 @@ extern int of_irq_to_resource(struct device_node *dev, int index, */ extern void __iomem *of_iomap(struct device_node *device, int index); -/* - * NB: This is here while we transition from using asm/prom.h - * to linux/of.h - */ -#include <linux/of.h> - #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ #endif /* _ASM_MICROBLAZE_PROM_H */ diff --git a/arch/microblaze/kernel/head.S b/arch/microblaze/kernel/head.S index 697ce3007f30..30916193fcc7 100644 --- a/arch/microblaze/kernel/head.S +++ b/arch/microblaze/kernel/head.S @@ -31,7 +31,7 @@ #include <linux/linkage.h> #include <asm/thread_info.h> #include <asm/page.h> -#include <asm/prom.h> /* for OF_DT_HEADER */ +#include <linux/of_fdt.h> /* for OF_DT_HEADER */ #ifdef CONFIG_MMU #include <asm/setup.h> /* COMMAND_LINE_SIZE */ diff --git a/arch/microblaze/kernel/prom.c b/arch/microblaze/kernel/prom.c index c005cc6f1aaf..b817df172aa9 100644 --- a/arch/microblaze/kernel/prom.c +++ b/arch/microblaze/kernel/prom.c @@ -860,29 +860,6 @@ struct device_node *of_find_node_by_phandle(phandle handle) EXPORT_SYMBOL(of_find_node_by_phandle); /** - * of_find_all_nodes - Get next node in global list - * @prev: Previous node or NULL to start iteration - * of_node_put() will be called on it - * - * Returns a node pointer with refcount incremented, use - * of_node_put() on it when done. - */ -struct device_node *of_find_all_nodes(struct device_node *prev) -{ - struct device_node *np; - - read_lock(&devtree_lock); - np = prev ? prev->allnext : allnodes; - for (; np != NULL; np = np->allnext) - if (of_node_get(np)) - break; - of_node_put(prev); - read_unlock(&devtree_lock); - return np; -} -EXPORT_SYMBOL(of_find_all_nodes); - -/** * of_node_get - Increment refcount of a node * @node: Node to inc refcount, NULL is supported to * simplify writing of callers diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 1aad0d9f5074..fd7620f025fa 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -358,7 +358,14 @@ config SGI_IP22 select SWAP_IO_SPACE select SYS_HAS_CPU_R4X00 select SYS_HAS_CPU_R5000 - select SYS_HAS_EARLY_PRINTK + # + # Disable EARLY_PRINTK for now since it leads to overwritten prom + # memory during early boot on some machines. + # + # See http://www.linux-mips.org/cgi-bin/mesg.cgi?a=linux-mips&i=20091119164009.GA15038%40deprecation.cyrius.com + # for a more details discussion + # + # select SYS_HAS_EARLY_PRINTK select SYS_SUPPORTS_32BIT_KERNEL select SYS_SUPPORTS_64BIT_KERNEL select SYS_SUPPORTS_BIG_ENDIAN @@ -410,7 +417,14 @@ config SGI_IP28 select SGI_HAS_ZILOG select SWAP_IO_SPACE select SYS_HAS_CPU_R10000 - select SYS_HAS_EARLY_PRINTK + # + # Disable EARLY_PRINTK for now since it leads to overwritten prom + # memory during early boot on some machines. + # + # See http://www.linux-mips.org/cgi-bin/mesg.cgi?a=linux-mips&i=20091119164009.GA15038%40deprecation.cyrius.com + # for a more details discussion + # + # select SYS_HAS_EARLY_PRINTK select SYS_SUPPORTS_64BIT_KERNEL select SYS_SUPPORTS_BIG_ENDIAN help @@ -1439,6 +1453,7 @@ choice config PAGE_SIZE_4KB bool "4kB" + depends on !CPU_LOONGSON2 help This option select the standard 4kB Linux page size. On some R3000-family processors this is the only available page size. Using @@ -1763,7 +1778,7 @@ config SYS_SUPPORTS_SMARTMIPS config ARCH_FLATMEM_ENABLE def_bool y - depends on !NUMA + depends on !NUMA && !CPU_LOONGSON2 config ARCH_DISCONTIGMEM_ENABLE bool diff --git a/arch/mips/include/asm/bug.h b/arch/mips/include/asm/bug.h index 6cf29c26e873..540c98a810d1 100644 --- a/arch/mips/include/asm/bug.h +++ b/arch/mips/include/asm/bug.h @@ -11,9 +11,7 @@ static inline void __noreturn BUG(void) { __asm__ __volatile__("break %0" : : "i" (BRK_BUG)); - /* Fool GCC into thinking the function doesn't return. */ - while (1) - ; + unreachable(); } #define HAVE_ARCH_BUG diff --git a/arch/mips/include/asm/mman.h b/arch/mips/include/asm/mman.h index a2250f390a29..c892bfb3e2c1 100644 --- a/arch/mips/include/asm/mman.h +++ b/arch/mips/include/asm/mman.h @@ -75,6 +75,7 @@ #define MADV_MERGEABLE 12 /* KSM may merge identical pages */ #define MADV_UNMERGEABLE 13 /* KSM may not merge identical pages */ +#define MADV_HWPOISON 100 /* poison a page for testing */ /* compatibility flags */ #define MAP_FILE 0 diff --git a/arch/mips/include/asm/system.h b/arch/mips/include/asm/system.h index fcf5f98d90cc..83b5509e09e8 100644 --- a/arch/mips/include/asm/system.h +++ b/arch/mips/include/asm/system.h @@ -12,6 +12,7 @@ #ifndef _ASM_SYSTEM_H #define _ASM_SYSTEM_H +#include <linux/kernel.h> #include <linux/types.h> #include <linux/irqflags.h> @@ -193,10 +194,6 @@ extern __u64 __xchg_u64_unsupported_on_32bit_kernels(volatile __u64 * m, __u64 v #define __xchg_u64 __xchg_u64_unsupported_on_32bit_kernels #endif -/* This function doesn't exist, so you'll get a linker error - if something tries to do an invalid xchg(). */ -extern void __xchg_called_with_bad_pointer(void); - static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size) { switch (size) { @@ -205,11 +202,17 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz case 8: return __xchg_u64(ptr, x); } - __xchg_called_with_bad_pointer(); + return x; } -#define xchg(ptr, x) ((__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr), sizeof(*(ptr)))) +#define xchg(ptr, x) \ +({ \ + BUILD_BUG_ON(sizeof(*(ptr)) & ~0xc); \ + \ + ((__typeof__(*(ptr))) \ + __xchg((unsigned long)(x), (ptr), sizeof(*(ptr)))); \ +}) extern void set_handler(unsigned long offset, void *addr, unsigned long len); extern void set_uncached_handler(unsigned long offset, void *addr, unsigned long len); diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c index b77fefaff9da..1a2793efdc4e 100644 --- a/arch/mips/kernel/linux32.c +++ b/arch/mips/kernel/linux32.c @@ -265,67 +265,6 @@ SYSCALL_DEFINE5(n32_msgrcv, int, msqid, u32, msgp, size_t, msgsz, } #endif -struct sysctl_args32 -{ - compat_caddr_t name; - int nlen; - compat_caddr_t oldval; - compat_caddr_t oldlenp; - compat_caddr_t newval; - compat_size_t newlen; - unsigned int __unused[4]; -}; - -#ifdef CONFIG_SYSCTL_SYSCALL - -SYSCALL_DEFINE1(32_sysctl, struct sysctl_args32 __user *, args) -{ - struct sysctl_args32 tmp; - int error; - size_t oldlen; - size_t __user *oldlenp = NULL; - unsigned long addr = (((unsigned long)&args->__unused[0]) + 7) & ~7; - - if (copy_from_user(&tmp, args, sizeof(tmp))) - return -EFAULT; - - if (tmp.oldval && tmp.oldlenp) { - /* Duh, this is ugly and might not work if sysctl_args - is in read-only memory, but do_sysctl does indirectly - a lot of uaccess in both directions and we'd have to - basically copy the whole sysctl.c here, and - glibc's __sysctl uses rw memory for the structure - anyway. */ - if (get_user(oldlen, (u32 __user *)A(tmp.oldlenp)) || - put_user(oldlen, (size_t __user *)addr)) - return -EFAULT; - oldlenp = (size_t __user *)addr; - } - - lock_kernel(); - error = do_sysctl((int __user *)A(tmp.name), tmp.nlen, (void __user *)A(tmp.oldval), - oldlenp, (void __user *)A(tmp.newval), tmp.newlen); - unlock_kernel(); - if (oldlenp) { - if (!error) { - if (get_user(oldlen, (size_t __user *)addr) || - put_user(oldlen, (u32 __user *)A(tmp.oldlenp))) - error = -EFAULT; - } - copy_to_user(args->__unused, tmp.__unused, sizeof(tmp.__unused)); - } - return error; -} - -#else - -SYSCALL_DEFINE1(32_sysctl, struct sysctl_args32 __user *, args) -{ - return -ENOSYS; -} - -#endif /* CONFIG_SYSCTL_SYSCALL */ - SYSCALL_DEFINE1(32_newuname, struct new_utsname __user *, name) { int ret = 0; diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index 6ebc07976694..8a0be0bdebad 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -272,7 +272,7 @@ EXPORT(sysn32_call_table) PTR sys_munlockall PTR sys_vhangup /* 6150 */ PTR sys_pivot_root - PTR sys_32_sysctl + PTR compat_sys_sysctl PTR sys_prctl PTR compat_sys_adjtimex PTR compat_sys_setrlimit /* 6155 */ diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index 14dde4ca932e..41dbdb7d67e5 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -356,7 +356,7 @@ sys_call_table: PTR sys_ni_syscall /* 4150 */ PTR sys_getsid PTR sys_fdatasync - PTR sys_32_sysctl + PTR compat_sys_sysctl PTR sys_mlock PTR sys_munlock /* 4155 */ PTR sys_mlockall diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c index 3fe1fcfa2e73..fe0d79805603 100644 --- a/arch/mips/kernel/syscall.c +++ b/arch/mips/kernel/syscall.c @@ -306,6 +306,7 @@ static inline int mips_atomic_set(struct pt_regs *regs, if (cpu_has_llsc && R10000_LLSC_WAR) { __asm__ __volatile__ ( + " .set mips3 \n" " li %[err], 0 \n" "1: ll %[old], (%[addr]) \n" " move %[tmp], %[new] \n" @@ -320,6 +321,7 @@ static inline int mips_atomic_set(struct pt_regs *regs, " "STR(PTR)" 1b, 4b \n" " "STR(PTR)" 2b, 4b \n" " .previous \n" + " .set mips0 \n" : [old] "=&r" (old), [err] "=&r" (err), [tmp] "=&r" (tmp) @@ -329,6 +331,7 @@ static inline int mips_atomic_set(struct pt_regs *regs, : "memory"); } else if (cpu_has_llsc) { __asm__ __volatile__ ( + " .set mips3 \n" " li %[err], 0 \n" "1: ll %[old], (%[addr]) \n" " move %[tmp], %[new] \n" @@ -347,6 +350,7 @@ static inline int mips_atomic_set(struct pt_regs *regs, " "STR(PTR)" 1b, 5b \n" " "STR(PTR)" 2b, 5b \n" " .previous \n" + " .set mips0 \n" : [old] "=&r" (old), [err] "=&r" (err), [tmp] "=&r" (tmp) diff --git a/arch/mips/lasat/sysctl.c b/arch/mips/lasat/sysctl.c index b3deed8db619..14b9a28a4aec 100644 --- a/arch/mips/lasat/sysctl.c +++ b/arch/mips/lasat/sysctl.c @@ -37,23 +37,6 @@ #include "ds1603.h" #endif -/* Strategy function to write EEPROM after changing string entry */ -int sysctl_lasatstring(ctl_table *table, - void *oldval, size_t *oldlenp, - void *newval, size_t newlen) -{ - int r; - - r = sysctl_string(table, oldval, oldlenp, newval, newlen); - if (r < 0) - return r; - - if (newval && newlen) - lasat_write_eeprom_info(); - - return 0; -} - /* And the same for proc */ int proc_dolasatstring(ctl_table *table, int write, @@ -113,46 +96,6 @@ int proc_dolasatrtc(ctl_table *table, int write, } #endif -/* Sysctl for setting the IP addresses */ -int sysctl_lasat_intvec(ctl_table *table, - void *oldval, size_t *oldlenp, - void *newval, size_t newlen) -{ - int r; - - r = sysctl_intvec(table, oldval, oldlenp, newval, newlen); - if (r < 0) - return r; - - if (newval && newlen) - lasat_write_eeprom_info(); - - return 0; -} - -#ifdef CONFIG_DS1603 -/* Same for RTC */ -int sysctl_lasat_rtc(ctl_table *table, - void *oldval, size_t *oldlenp, - void *newval, size_t newlen) -{ - struct timespec ts; - int r; - - read_persistent_clock(&ts); - rtctmp = ts.tv_sec; - if (rtctmp < 0) - rtctmp = 0; - r = sysctl_intvec(table, oldval, oldlenp, newval, newlen); - if (r < 0) - return r; - if (newval && newlen) - rtc_mips_set_mmss(rtctmp); - - return r; -} -#endif - #ifdef CONFIG_INET int proc_lasat_ip(ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) @@ -214,23 +157,6 @@ int proc_lasat_ip(ctl_table *table, int write, } #endif -static int sysctl_lasat_prid(ctl_table *table, - void *oldval, size_t *oldlenp, - void *newval, size_t newlen) -{ - int r; - - r = sysctl_intvec(table, oldval, oldlenp, newval, newlen); - if (r < 0) - return r; - if (newval && newlen) { - lasat_board_info.li_eeprom_info.prid = *(int *)newval; - lasat_write_eeprom_info(); - lasat_init_board_info(); - } - return 0; -} - int proc_lasat_prid(ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -252,115 +178,92 @@ extern int lasat_boot_to_service; static ctl_table lasat_table[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "cpu-hz", .data = &lasat_board_info.li_cpu_hz, .maxlen = sizeof(int), .mode = 0444, - .proc_handler = &proc_dointvec, - .strategy = &sysctl_intvec + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "bus-hz", .data = &lasat_board_info.li_bus_hz, .maxlen = sizeof(int), .mode = 0444, - .proc_handler = &proc_dointvec, - .strategy = &sysctl_intvec + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "bmid", .data = &lasat_board_info.li_bmid, .maxlen = sizeof(int), .mode = 0444, - .proc_handler = &proc_dointvec, - .strategy = &sysctl_intvec + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "prid", .data = &lasat_board_info.li_prid, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_lasat_prid, - .strategy = &sysctl_lasat_prid - }, + .proc_handler = proc_lasat_prid, +. }, #ifdef CONFIG_INET { - .ctl_name = CTL_UNNUMBERED, .procname = "ipaddr", .data = &lasat_board_info.li_eeprom_info.ipaddr, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_lasat_ip, - .strategy = &sysctl_lasat_intvec + .proc_handler = proc_lasat_ip, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "netmask", .data = &lasat_board_info.li_eeprom_info.netmask, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_lasat_ip, - .strategy = &sysctl_lasat_intvec + .proc_handler = proc_lasat_ip, }, #endif { - .ctl_name = CTL_UNNUMBERED, .procname = "passwd_hash", .data = &lasat_board_info.li_eeprom_info.passwd_hash, .maxlen = sizeof(lasat_board_info.li_eeprom_info.passwd_hash), .mode = 0600, - .proc_handler = &proc_dolasatstring, - .strategy = &sysctl_lasatstring + .proc_handler = proc_dolasatstring, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "boot-service", .data = &lasat_boot_to_service, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, - .strategy = &sysctl_intvec + .proc_handler = proc_dointvec, }, #ifdef CONFIG_DS1603 { - .ctl_name = CTL_UNNUMBERED, .procname = "rtc", .data = &rtctmp, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dolasatrtc, - .strategy = &sysctl_lasat_rtc + .proc_handler = proc_dolasatrtc, }, #endif { - .ctl_name = CTL_UNNUMBERED, .procname = "namestr", .data = &lasat_board_info.li_namestr, .maxlen = sizeof(lasat_board_info.li_namestr), .mode = 0444, - .proc_handler = &proc_dostring, - .strategy = &sysctl_string + .proc_handler = proc_dostring, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "typestr", .data = &lasat_board_info.li_typestr, .maxlen = sizeof(lasat_board_info.li_typestr), .mode = 0444, - .proc_handler = &proc_dostring, - .strategy = &sysctl_string + .proc_handler = proc_dostring, }, {} }; static ctl_table lasat_root_table[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "lasat", .mode = 0555, .child = lasat_table diff --git a/arch/mips/rb532/devices.c b/arch/mips/rb532/devices.c index 9f40e1ff9b4f..041fc1afc3f4 100644 --- a/arch/mips/rb532/devices.c +++ b/arch/mips/rb532/devices.c @@ -110,7 +110,6 @@ static struct korina_device korina_dev0_data = { static struct platform_device korina_dev0 = { .id = -1, .name = "korina", - .dev.driver_data = &korina_dev0_data, .resource = korina_dev0_res, .num_resources = ARRAY_SIZE(korina_dev0_res), }; @@ -332,6 +331,8 @@ static int __init plat_setup_devices(void) /* set the uart clock to the current cpu frequency */ rb532_uart_res[0].uartclk = idt_cpu_freq; + dev_set_drvdata(&korina_dev0.dev, &korina_dev0_data); + return platform_add_devices(rb532_devs, ARRAY_SIZE(rb532_devs)); } diff --git a/arch/parisc/kernel/sys_parisc32.c b/arch/parisc/kernel/sys_parisc32.c index 561388b17c91..76d23ec8dfaa 100644 --- a/arch/parisc/kernel/sys_parisc32.c +++ b/arch/parisc/kernel/sys_parisc32.c @@ -90,77 +90,6 @@ asmlinkage long sys32_unimplemented(int r26, int r25, int r24, int r23, return -ENOSYS; } -#ifdef CONFIG_SYSCTL - -struct __sysctl_args32 { - u32 name; - int nlen; - u32 oldval; - u32 oldlenp; - u32 newval; - u32 newlen; - u32 __unused[4]; -}; - -asmlinkage long sys32_sysctl(struct __sysctl_args32 __user *args) -{ -#ifndef CONFIG_SYSCTL_SYSCALL - return -ENOSYS; -#else - struct __sysctl_args32 tmp; - int error; - unsigned int oldlen32; - size_t oldlen, __user *oldlenp = NULL; - unsigned long addr = (((long __force)&args->__unused[0]) + 7) & ~7; - - DBG(("sysctl32(%p)\n", args)); - - if (copy_from_user(&tmp, args, sizeof(tmp))) - return -EFAULT; - - if (tmp.oldval && tmp.oldlenp) { - /* Duh, this is ugly and might not work if sysctl_args - is in read-only memory, but do_sysctl does indirectly - a lot of uaccess in both directions and we'd have to - basically copy the whole sysctl.c here, and - glibc's __sysctl uses rw memory for the structure - anyway. */ - /* a possibly better hack than this, which will avoid the - * problem if the struct is read only, is to push the - * 'oldlen' value out to the user's stack instead. -PB - */ - if (get_user(oldlen32, (u32 *)(u64)tmp.oldlenp)) - return -EFAULT; - oldlen = oldlen32; - if (put_user(oldlen, (size_t *)addr)) - return -EFAULT; - oldlenp = (size_t *)addr; - } - - lock_kernel(); - error = do_sysctl((int __user *)(u64)tmp.name, tmp.nlen, - (void __user *)(u64)tmp.oldval, oldlenp, - (void __user *)(u64)tmp.newval, tmp.newlen); - unlock_kernel(); - if (oldlenp) { - if (!error) { - if (get_user(oldlen, (size_t *)addr)) { - error = -EFAULT; - } else { - oldlen32 = oldlen; - if (put_user(oldlen32, (u32 *)(u64)tmp.oldlenp)) - error = -EFAULT; - } - } - if (copy_to_user(args->__unused, tmp.__unused, sizeof(tmp.__unused))) - error = -EFAULT; - } - return error; -#endif -} - -#endif /* CONFIG_SYSCTL */ - asmlinkage long sys32_sched_rr_get_interval(pid_t pid, struct compat_timespec __user *interval) { diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S index 843f423dec67..01c4fcf8f481 100644 --- a/arch/parisc/kernel/syscall_table.S +++ b/arch/parisc/kernel/syscall_table.S @@ -234,7 +234,7 @@ ENTRY_SAME(getsid) ENTRY_SAME(fdatasync) /* struct __sysctl_args is a mess */ - ENTRY_DIFF(sysctl) + ENTRY_COMP(sysctl) ENTRY_SAME(mlock) /* 150 */ ENTRY_SAME(munlock) ENTRY_SAME(mlockall) diff --git a/arch/parisc/kernel/unwind.c b/arch/parisc/kernel/unwind.c index 69dad5a850a8..a36799e85693 100644 --- a/arch/parisc/kernel/unwind.c +++ b/arch/parisc/kernel/unwind.c @@ -28,7 +28,7 @@ #define dbg(x...) #endif -#define KERNEL_START (KERNEL_BINARY_TEXT_START - 0x1000) +#define KERNEL_START (KERNEL_BINARY_TEXT_START) extern struct unwind_table_entry __start___unwind[]; extern struct unwind_table_entry __stop___unwind[]; diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S index fda4baa059b5..9dab4a4e09f7 100644 --- a/arch/parisc/kernel/vmlinux.lds.S +++ b/arch/parisc/kernel/vmlinux.lds.S @@ -78,9 +78,6 @@ SECTIONS */ . = ALIGN(PAGE_SIZE); data_start = .; - EXCEPTION_TABLE(16) - - NOTES /* unwind info */ .PARISC.unwind : { @@ -89,6 +86,9 @@ SECTIONS __stop___unwind = .; } + EXCEPTION_TABLE(16) + NOTES + /* Data */ RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE) diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug index 3b1005185390..bf3382f1904d 100644 --- a/arch/powerpc/Kconfig.debug +++ b/arch/powerpc/Kconfig.debug @@ -46,7 +46,7 @@ config DEBUG_STACK_USAGE config HCALL_STATS bool "Hypervisor call instrumentation" - depends on PPC_PSERIES && DEBUG_FS + depends on PPC_PSERIES && DEBUG_FS && TRACEPOINTS help Adds code to keep track of the number of hypervisor calls made and the amount of time spent in hypervisor calls. Wall time spent in diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig index f1889abb89b1..c568329723b8 100644 --- a/arch/powerpc/configs/pseries_defconfig +++ b/arch/powerpc/configs/pseries_defconfig @@ -1683,7 +1683,7 @@ CONFIG_HAVE_ARCH_KGDB=y CONFIG_DEBUG_STACKOVERFLOW=y # CONFIG_DEBUG_STACK_USAGE is not set # CONFIG_DEBUG_PAGEALLOC is not set -CONFIG_HCALL_STATS=y +# CONFIG_HCALL_STATS is not set # CONFIG_CODE_PATCHING_SELFTEST is not set # CONFIG_FTR_FIXUP_SELFTEST is not set # CONFIG_MSI_BITMAP_SELFTEST is not set diff --git a/arch/powerpc/include/asm/emulated_ops.h b/arch/powerpc/include/asm/emulated_ops.h index 9154e8526732..f0fb4fc1f6e6 100644 --- a/arch/powerpc/include/asm/emulated_ops.h +++ b/arch/powerpc/include/asm/emulated_ops.h @@ -19,6 +19,7 @@ #define _ASM_POWERPC_EMULATED_OPS_H #include <asm/atomic.h> +#include <linux/perf_event.h> #ifdef CONFIG_PPC_EMULATED_STATS @@ -57,7 +58,7 @@ extern u32 ppc_warn_emulated; extern void ppc_warn_emulated_print(const char *type); -#define PPC_WARN_EMULATED(type) \ +#define __PPC_WARN_EMULATED(type) \ do { \ atomic_inc(&ppc_emulated.type.val); \ if (ppc_warn_emulated) \ @@ -66,8 +67,22 @@ extern void ppc_warn_emulated_print(const char *type); #else /* !CONFIG_PPC_EMULATED_STATS */ -#define PPC_WARN_EMULATED(type) do { } while (0) +#define __PPC_WARN_EMULATED(type) do { } while (0) #endif /* !CONFIG_PPC_EMULATED_STATS */ +#define PPC_WARN_EMULATED(type, regs) \ + do { \ + perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, \ + 1, 0, regs, 0); \ + __PPC_WARN_EMULATED(type); \ + } while (0) + +#define PPC_WARN_ALIGNMENT(type, regs) \ + do { \ + perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, \ + 1, 0, regs, regs->dar); \ + __PPC_WARN_EMULATED(type); \ + } while (0) + #endif /* _ASM_POWERPC_EMULATED_OPS_H */ diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 6251a4b10be7..c27caac47ad1 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -274,6 +274,8 @@ struct hcall_stats { unsigned long num_calls; /* number of calls (on this CPU) */ unsigned long tb_total; /* total wall time (mftb) of calls. */ unsigned long purr_total; /* total cpu time (PURR) of calls. */ + unsigned long tb_start; + unsigned long purr_start; }; #define HCALL_STAT_ARRAY_SIZE ((MAX_HCALL_OPCODE >> 2) + 1) diff --git a/arch/powerpc/include/asm/kmap_types.h b/arch/powerpc/include/asm/kmap_types.h index b6bac6f61c16..916369575c97 100644 --- a/arch/powerpc/include/asm/kmap_types.h +++ b/arch/powerpc/include/asm/kmap_types.h @@ -29,5 +29,16 @@ enum km_type { KM_TYPE_NR }; +/* + * This is a temporary build fix that (so they say on lkml....) should no longer + * be required after 2.6.33, because of changes planned to the kmap code. + * Let's try to remove this cruft then. + */ +#ifdef CONFIG_DEBUG_HIGHMEM +#define KM_NMI (-1) +#define KM_NMI_PTE (-1) +#define KM_IRQ_PTE (-1) +#endif + #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_KMAP_TYPES_H */ diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index 6ff04185d2aa..2ab9cbd98826 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -1,3 +1,4 @@ +#include <linux/of.h> /* linux/of.h gets to determine #include ordering */ #ifndef _POWERPC_PROM_H #define _POWERPC_PROM_H #ifdef __KERNEL__ @@ -16,6 +17,7 @@ * 2 of the License, or (at your option) any later version. */ #include <linux/types.h> +#include <linux/of_fdt.h> #include <linux/proc_fs.h> #include <linux/platform_device.h> #include <asm/irq.h> @@ -28,133 +30,14 @@ #define of_prop_cmp(s1, s2) strcmp((s1), (s2)) #define of_node_cmp(s1, s2) strcasecmp((s1), (s2)) -/* Definitions used by the flattened device tree */ -#define OF_DT_HEADER 0xd00dfeed /* marker */ -#define OF_DT_BEGIN_NODE 0x1 /* Start of node, full name */ -#define OF_DT_END_NODE 0x2 /* End node */ -#define OF_DT_PROP 0x3 /* Property: name off, size, - * content */ -#define OF_DT_NOP 0x4 /* nop */ -#define OF_DT_END 0x9 - -#define OF_DT_VERSION 0x10 - -/* - * This is what gets passed to the kernel by prom_init or kexec - * - * The dt struct contains the device tree structure, full pathes and - * property contents. The dt strings contain a separate block with just - * the strings for the property names, and is fully page aligned and - * self contained in a page, so that it can be kept around by the kernel, - * each property name appears only once in this page (cheap compression) - * - * the mem_rsvmap contains a map of reserved ranges of physical memory, - * passing it here instead of in the device-tree itself greatly simplifies - * the job of everybody. It's just a list of u64 pairs (base/size) that - * ends when size is 0 - */ -struct boot_param_header -{ - u32 magic; /* magic word OF_DT_HEADER */ - u32 totalsize; /* total size of DT block */ - u32 off_dt_struct; /* offset to structure */ - u32 off_dt_strings; /* offset to strings */ - u32 off_mem_rsvmap; /* offset to memory reserve map */ - u32 version; /* format version */ - u32 last_comp_version; /* last compatible version */ - /* version 2 fields below */ - u32 boot_cpuid_phys; /* Physical CPU id we're booting on */ - /* version 3 fields below */ - u32 dt_strings_size; /* size of the DT strings block */ - /* version 17 fields below */ - u32 dt_struct_size; /* size of the DT structure block */ -}; - - - -typedef u32 phandle; -typedef u32 ihandle; - -struct property { - char *name; - int length; - void *value; - struct property *next; -}; - -struct device_node { - const char *name; - const char *type; - phandle node; - phandle linux_phandle; - char *full_name; - - struct property *properties; - struct property *deadprops; /* removed properties */ - struct device_node *parent; - struct device_node *child; - struct device_node *sibling; - struct device_node *next; /* next device of same type */ - struct device_node *allnext; /* next in list of all nodes */ - struct proc_dir_entry *pde; /* this node's proc directory */ - struct kref kref; - unsigned long _flags; - void *data; -}; - extern struct device_node *of_chosen; -static inline int of_node_check_flag(struct device_node *n, unsigned long flag) -{ - return test_bit(flag, &n->_flags); -} - -static inline void of_node_set_flag(struct device_node *n, unsigned long flag) -{ - set_bit(flag, &n->_flags); -} - - #define HAVE_ARCH_DEVTREE_FIXUPS -static inline void set_node_proc_entry(struct device_node *dn, struct proc_dir_entry *de) -{ - dn->pde = de; -} - - -extern struct device_node *of_find_all_nodes(struct device_node *prev); -extern struct device_node *of_node_get(struct device_node *node); -extern void of_node_put(struct device_node *node); - -/* For scanning the flat device-tree at boot time */ -extern int __init of_scan_flat_dt(int (*it)(unsigned long node, - const char *uname, int depth, - void *data), - void *data); -extern void* __init of_get_flat_dt_prop(unsigned long node, const char *name, - unsigned long *size); -extern int __init of_flat_dt_is_compatible(unsigned long node, const char *name); -extern unsigned long __init of_get_flat_dt_root(void); - /* For updating the device tree at runtime */ extern void of_attach_node(struct device_node *); extern void of_detach_node(struct device_node *); -/* Other Prototypes */ -extern void finish_device_tree(void); -extern void unflatten_device_tree(void); -extern void early_init_devtree(void *); -extern int machine_is_compatible(const char *compat); -extern void print_properties(struct device_node *node); -extern int prom_n_intr_cells(struct device_node* np); -extern void prom_get_irq_senses(unsigned char *senses, int off, int max); -extern int prom_add_property(struct device_node* np, struct property* prop); -extern int prom_remove_property(struct device_node *np, struct property *prop); -extern int prom_update_property(struct device_node *np, - struct property *newprop, - struct property *oldprop); - #ifdef CONFIG_PPC32 /* * PCI <-> OF matching functions @@ -178,26 +61,6 @@ extern int release_OF_resource(struct device_node* node, int index); * OF address retreival & translation */ - -/* Helper to read a big number; size is in cells (not bytes) */ -static inline u64 of_read_number(const u32 *cell, int size) -{ - u64 r = 0; - while (size--) - r = (r << 32) | *(cell++); - return r; -} - -/* Like of_read_number, but we want an unsigned long result */ -#ifdef CONFIG_PPC32 -static inline unsigned long of_read_ulong(const u32 *cell, int size) -{ - return cell[size-1]; -} -#else -#define of_read_ulong(cell, size) of_read_number(cell, size) -#endif - /* Translate an OF address block into a CPU physical address */ extern u64 of_translate_address(struct device_node *np, const u32 *addr); @@ -349,11 +212,5 @@ extern int of_irq_to_resource(struct device_node *dev, int index, */ extern void __iomem *of_iomap(struct device_node *device, int index); -/* - * NB: This is here while we transition from using asm/prom.h - * to linux/of.h - */ -#include <linux/of.h> - #endif /* __KERNEL__ */ #endif /* _POWERPC_PROM_H */ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 6315edc205d8..bc8dd53f718a 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -489,6 +489,8 @@ #define SPRN_MMCR1 798 #define SPRN_MMCRA 0x312 #define MMCRA_SDSYNC 0x80000000UL /* SDAR synced with SIAR */ +#define MMCRA_SDAR_DCACHE_MISS 0x40000000UL +#define MMCRA_SDAR_ERAT_MISS 0x20000000UL #define MMCRA_SIHV 0x10000000UL /* state of MSR HV when SIAR set */ #define MMCRA_SIPR 0x08000000UL /* state of MSR PR when SIAR set */ #define MMCRA_SLOT 0x07000000UL /* SLOT bits (37-39) */ diff --git a/arch/powerpc/include/asm/trace.h b/arch/powerpc/include/asm/trace.h new file mode 100644 index 000000000000..cbe2297d68b6 --- /dev/null +++ b/arch/powerpc/include/asm/trace.h @@ -0,0 +1,133 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM powerpc + +#if !defined(_TRACE_POWERPC_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_POWERPC_H + +#include <linux/tracepoint.h> + +struct pt_regs; + +TRACE_EVENT(irq_entry, + + TP_PROTO(struct pt_regs *regs), + + TP_ARGS(regs), + + TP_STRUCT__entry( + __field(struct pt_regs *, regs) + ), + + TP_fast_assign( + __entry->regs = regs; + ), + + TP_printk("pt_regs=%p", __entry->regs) +); + +TRACE_EVENT(irq_exit, + + TP_PROTO(struct pt_regs *regs), + + TP_ARGS(regs), + + TP_STRUCT__entry( + __field(struct pt_regs *, regs) + ), + + TP_fast_assign( + __entry->regs = regs; + ), + + TP_printk("pt_regs=%p", __entry->regs) +); + +TRACE_EVENT(timer_interrupt_entry, + + TP_PROTO(struct pt_regs *regs), + + TP_ARGS(regs), + + TP_STRUCT__entry( + __field(struct pt_regs *, regs) + ), + + TP_fast_assign( + __entry->regs = regs; + ), + + TP_printk("pt_regs=%p", __entry->regs) +); + +TRACE_EVENT(timer_interrupt_exit, + + TP_PROTO(struct pt_regs *regs), + + TP_ARGS(regs), + + TP_STRUCT__entry( + __field(struct pt_regs *, regs) + ), + + TP_fast_assign( + __entry->regs = regs; + ), + + TP_printk("pt_regs=%p", __entry->regs) +); + +#ifdef CONFIG_PPC_PSERIES +extern void hcall_tracepoint_regfunc(void); +extern void hcall_tracepoint_unregfunc(void); + +TRACE_EVENT_FN(hcall_entry, + + TP_PROTO(unsigned long opcode, unsigned long *args), + + TP_ARGS(opcode, args), + + TP_STRUCT__entry( + __field(unsigned long, opcode) + ), + + TP_fast_assign( + __entry->opcode = opcode; + ), + + TP_printk("opcode=%lu", __entry->opcode), + + hcall_tracepoint_regfunc, hcall_tracepoint_unregfunc +); + +TRACE_EVENT_FN(hcall_exit, + + TP_PROTO(unsigned long opcode, unsigned long retval, + unsigned long *retbuf), + + TP_ARGS(opcode, retval, retbuf), + + TP_STRUCT__entry( + __field(unsigned long, opcode) + __field(unsigned long, retval) + ), + + TP_fast_assign( + __entry->opcode = opcode; + __entry->retval = retval; + ), + + TP_printk("opcode=%lu retval=%lu", __entry->opcode, __entry->retval), + + hcall_tracepoint_regfunc, hcall_tracepoint_unregfunc +); +#endif + +#endif /* _TRACE_POWERPC_H */ + +#undef TRACE_INCLUDE_PATH +#undef TRACE_INCLUDE_FILE + +#define TRACE_INCLUDE_PATH asm +#define TRACE_INCLUDE_FILE trace + +#include <trace/define_trace.h> diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index a5b632e52fae..3839839f83c7 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -732,7 +732,7 @@ int fix_alignment(struct pt_regs *regs) #ifdef CONFIG_SPE if ((instr >> 26) == 0x4) { - PPC_WARN_EMULATED(spe); + PPC_WARN_ALIGNMENT(spe, regs); return emulate_spe(regs, reg, instr); } #endif @@ -786,7 +786,7 @@ int fix_alignment(struct pt_regs *regs) flags |= SPLT; nb = 8; } - PPC_WARN_EMULATED(vsx); + PPC_WARN_ALIGNMENT(vsx, regs); return emulate_vsx(addr, reg, areg, regs, flags, nb); } #endif @@ -794,7 +794,7 @@ int fix_alignment(struct pt_regs *regs) * the exception of DCBZ which is handled as a special case here */ if (instr == DCBZ) { - PPC_WARN_EMULATED(dcbz); + PPC_WARN_ALIGNMENT(dcbz, regs); return emulate_dcbz(regs, addr); } if (unlikely(nb == 0)) @@ -804,7 +804,7 @@ int fix_alignment(struct pt_regs *regs) * function */ if (flags & M) { - PPC_WARN_EMULATED(multiple); + PPC_WARN_ALIGNMENT(multiple, regs); return emulate_multiple(regs, addr, reg, nb, flags, instr, swiz); } @@ -825,11 +825,11 @@ int fix_alignment(struct pt_regs *regs) /* Special case for 16-byte FP loads and stores */ if (nb == 16) { - PPC_WARN_EMULATED(fp_pair); + PPC_WARN_ALIGNMENT(fp_pair, regs); return emulate_fp_pair(addr, reg, flags); } - PPC_WARN_EMULATED(unaligned); + PPC_WARN_ALIGNMENT(unaligned, regs); /* If we are loading, get the data from user space, else * get it from register values diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 9763267e38b4..bdcb557d470a 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -551,7 +551,7 @@ restore: BEGIN_FW_FTR_SECTION ld r5,SOFTE(r1) FW_FTR_SECTION_ELSE - b iseries_check_pending_irqs + b .Liseries_check_pending_irqs ALT_FW_FTR_SECTION_END_IFCLR(FW_FEATURE_ISERIES) 2: TRACE_AND_RESTORE_IRQ(r5); @@ -623,7 +623,7 @@ ALT_FW_FTR_SECTION_END_IFCLR(FW_FEATURE_ISERIES) #endif /* CONFIG_PPC_BOOK3E */ -iseries_check_pending_irqs: +.Liseries_check_pending_irqs: #ifdef CONFIG_PPC_ISERIES ld r5,SOFTE(r1) cmpdi 0,r5,0 diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 1808876edcc9..c7eb4e0eb86c 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -185,12 +185,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) * prolog code of the PerformanceMonitor one. A little * trickery is thus necessary */ +performance_monitor_pSeries_1: . = 0xf00 b performance_monitor_pSeries +altivec_unavailable_pSeries_1: . = 0xf20 b altivec_unavailable_pSeries +vsx_unavailable_pSeries_1: . = 0xf40 b vsx_unavailable_pSeries diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index 88d9c1d5e5fb..049dda60e475 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -110,18 +110,16 @@ int powersave_nap; */ static ctl_table powersave_nap_ctl_table[]={ { - .ctl_name = KERN_PPC_POWERSAVE_NAP, .procname = "powersave-nap", .data = &powersave_nap, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, {} }; static ctl_table powersave_nap_sysctl_root[] = { { - .ctl_name = CTL_KERN, .procname = "kernel", .mode = 0555, .child = powersave_nap_ctl_table, diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index e5d121177984..02a334662cc0 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -70,6 +70,8 @@ #include <asm/firmware.h> #include <asm/lv1call.h> #endif +#define CREATE_TRACE_POINTS +#include <asm/trace.h> int __irq_offset_value; static int ppc_spurious_interrupts; @@ -325,6 +327,8 @@ void do_IRQ(struct pt_regs *regs) struct pt_regs *old_regs = set_irq_regs(regs); unsigned int irq; + trace_irq_entry(regs); + irq_enter(); check_stack_overflow(); @@ -348,6 +352,8 @@ void do_IRQ(struct pt_regs *regs) timer_interrupt(regs); } #endif + + trace_irq_exit(regs); } void __init init_IRQ(void) diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c index 87f1663584b0..1eb85fbf53a5 100644 --- a/arch/powerpc/kernel/perf_event.c +++ b/arch/powerpc/kernel/perf_event.c @@ -1165,7 +1165,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val, */ if (record) { struct perf_sample_data data = { - .addr = 0, + .addr = ~0ULL, .period = event->hw.last_period, }; diff --git a/arch/powerpc/kernel/power5+-pmu.c b/arch/powerpc/kernel/power5+-pmu.c index 0f4c1c73a6ad..199de527d411 100644 --- a/arch/powerpc/kernel/power5+-pmu.c +++ b/arch/powerpc/kernel/power5+-pmu.c @@ -73,10 +73,6 @@ #define MMCR1_PMCSEL_MSK 0x7f /* - * Bits in MMCRA - */ - -/* * Layout of constraint bits: * 6666555555555544444444443333333333222222222211111111110000000000 * 3210987654321098765432109876543210987654321098765432109876543210 diff --git a/arch/powerpc/kernel/power5-pmu.c b/arch/powerpc/kernel/power5-pmu.c index c351b3a57fbb..98b6a729a9dd 100644 --- a/arch/powerpc/kernel/power5-pmu.c +++ b/arch/powerpc/kernel/power5-pmu.c @@ -73,10 +73,6 @@ #define MMCR1_PMCSEL_MSK 0x7f /* - * Bits in MMCRA - */ - -/* * Layout of constraint bits: * 6666555555555544444444443333333333222222222211111111110000000000 * 3210987654321098765432109876543210987654321098765432109876543210 @@ -390,7 +386,7 @@ static int power5_compute_mmcr(u64 event[], int n_ev, unsigned int hwc[], unsigned long mmcr[]) { unsigned long mmcr1 = 0; - unsigned long mmcra = 0; + unsigned long mmcra = MMCRA_SDAR_DCACHE_MISS | MMCRA_SDAR_ERAT_MISS; unsigned int pmc, unit, byte, psel; unsigned int ttm, grp; int i, isbus, bit, grsel; diff --git a/arch/powerpc/kernel/power6-pmu.c b/arch/powerpc/kernel/power6-pmu.c index ca399ba5034c..84a607bda8fb 100644 --- a/arch/powerpc/kernel/power6-pmu.c +++ b/arch/powerpc/kernel/power6-pmu.c @@ -178,7 +178,7 @@ static int p6_compute_mmcr(u64 event[], int n_ev, unsigned int hwc[], unsigned long mmcr[]) { unsigned long mmcr1 = 0; - unsigned long mmcra = 0; + unsigned long mmcra = MMCRA_SDAR_DCACHE_MISS | MMCRA_SDAR_ERAT_MISS; int i; unsigned int pmc, ev, b, u, s, psel; unsigned int ttmset = 0; diff --git a/arch/powerpc/kernel/power7-pmu.c b/arch/powerpc/kernel/power7-pmu.c index 28a4daacdc02..852f7b7f6b40 100644 --- a/arch/powerpc/kernel/power7-pmu.c +++ b/arch/powerpc/kernel/power7-pmu.c @@ -51,10 +51,6 @@ #define MMCR1_PMCSEL_MSK 0xff /* - * Bits in MMCRA - */ - -/* * Layout of constraint bits: * 6666555555555544444444443333333333222222222211111111110000000000 * 3210987654321098765432109876543210987654321098765432109876543210 @@ -230,7 +226,7 @@ static int power7_compute_mmcr(u64 event[], int n_ev, unsigned int hwc[], unsigned long mmcr[]) { unsigned long mmcr1 = 0; - unsigned long mmcra = 0; + unsigned long mmcra = MMCRA_SDAR_DCACHE_MISS | MMCRA_SDAR_ERAT_MISS; unsigned int pmc, unit, combine, l2sel, psel; unsigned int pmc_inuse = 0; int i; diff --git a/arch/powerpc/kernel/ppc970-pmu.c b/arch/powerpc/kernel/ppc970-pmu.c index 479574413a93..8eff48e20dba 100644 --- a/arch/powerpc/kernel/ppc970-pmu.c +++ b/arch/powerpc/kernel/ppc970-pmu.c @@ -84,10 +84,6 @@ static short mmcr1_adder_bits[8] = { }; /* - * Bits in MMCRA - */ - -/* * Layout of constraint bits: * 6666555555555544444444443333333333222222222211111111110000000000 * 3210987654321098765432109876543210987654321098765432109876543210 diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index d4405b95bfaa..4ec300862466 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -1317,29 +1317,6 @@ struct device_node *of_find_next_cache_node(struct device_node *np) } /** - * of_find_all_nodes - Get next node in global list - * @prev: Previous node or NULL to start iteration - * of_node_put() will be called on it - * - * Returns a node pointer with refcount incremented, use - * of_node_put() on it when done. - */ -struct device_node *of_find_all_nodes(struct device_node *prev) -{ - struct device_node *np; - - read_lock(&devtree_lock); - np = prev ? prev->allnext : allnodes; - for (; np != 0; np = np->allnext) - if (of_node_get(np)) - break; - of_node_put(prev); - read_unlock(&devtree_lock); - return np; -} -EXPORT_SYMBOL(of_find_all_nodes); - -/** * of_node_get - Increment refcount of a node * @node: Node to inc refcount, NULL is supported to * simplify writing of callers diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 4271f7a655a3..845c72ab7357 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -660,6 +660,7 @@ late_initcall(check_cache_coherency); #ifdef CONFIG_DEBUG_FS struct dentry *powerpc_debugfs_root; +EXPORT_SYMBOL(powerpc_debugfs_root); static int powerpc_debugfs_init(void) { diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 53bcf3d792db..b152de3e64d4 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -345,7 +345,7 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_SWIOTLB if (ppc_swiotlb_enable) - swiotlb_init(); + swiotlb_init(1); #endif paging_init(); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 04f638d82fb3..df2c9e932b37 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -550,7 +550,7 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_SWIOTLB if (ppc_swiotlb_enable) - swiotlb_init(); + swiotlb_init(1); #endif paging_init(); diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index b97c2d67f4ac..c5a4732bcc48 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -520,58 +520,6 @@ asmlinkage long compat_sys_umask(u32 mask) return sys_umask((int)mask); } -#ifdef CONFIG_SYSCTL_SYSCALL -struct __sysctl_args32 { - u32 name; - int nlen; - u32 oldval; - u32 oldlenp; - u32 newval; - u32 newlen; - u32 __unused[4]; -}; - -asmlinkage long compat_sys_sysctl(struct __sysctl_args32 __user *args) -{ - struct __sysctl_args32 tmp; - int error; - size_t oldlen; - size_t __user *oldlenp = NULL; - unsigned long addr = (((unsigned long)&args->__unused[0]) + 7) & ~7; - - if (copy_from_user(&tmp, args, sizeof(tmp))) - return -EFAULT; - - if (tmp.oldval && tmp.oldlenp) { - /* Duh, this is ugly and might not work if sysctl_args - is in read-only memory, but do_sysctl does indirectly - a lot of uaccess in both directions and we'd have to - basically copy the whole sysctl.c here, and - glibc's __sysctl uses rw memory for the structure - anyway. */ - oldlenp = (size_t __user *)addr; - if (get_user(oldlen, (compat_size_t __user *)compat_ptr(tmp.oldlenp)) || - put_user(oldlen, oldlenp)) - return -EFAULT; - } - - lock_kernel(); - error = do_sysctl(compat_ptr(tmp.name), tmp.nlen, - compat_ptr(tmp.oldval), oldlenp, - compat_ptr(tmp.newval), tmp.newlen); - unlock_kernel(); - if (oldlenp) { - if (!error) { - if (get_user(oldlen, oldlenp) || - put_user(oldlen, (compat_size_t __user *)compat_ptr(tmp.oldlenp))) - error = -EFAULT; - } - copy_to_user(args->__unused, tmp.__unused, sizeof(tmp.__unused)); - } - return error; -} -#endif - unsigned long compat_sys_mmap2(unsigned long addr, size_t len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long pgoff) diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index a136a11c490d..36707dec94d7 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -54,6 +54,7 @@ #include <linux/irq.h> #include <linux/delay.h> #include <linux/perf_event.h> +#include <asm/trace.h> #include <asm/io.h> #include <asm/processor.h> @@ -571,6 +572,8 @@ void timer_interrupt(struct pt_regs * regs) struct clock_event_device *evt = &decrementer->event; u64 now; + trace_timer_interrupt_entry(regs); + /* Ensure a positive value is written to the decrementer, or else * some CPUs will continuue to take decrementer exceptions */ set_dec(DECREMENTER_MAX); @@ -590,6 +593,7 @@ void timer_interrupt(struct pt_regs * regs) now = decrementer->next_tb - now; if (now <= DECREMENTER_MAX) set_dec((int)now); + trace_timer_interrupt_exit(regs); return; } old_regs = set_irq_regs(regs); @@ -620,6 +624,8 @@ void timer_interrupt(struct pt_regs * regs) irq_exit(); set_irq_regs(old_regs); + + trace_timer_interrupt_exit(regs); } void wakeup_decrementer(void) diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 6f0ae1a9bfae..9d1f9354d6ca 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -759,7 +759,7 @@ static int emulate_instruction(struct pt_regs *regs) /* Emulate the mfspr rD, PVR. */ if ((instword & PPC_INST_MFSPR_PVR_MASK) == PPC_INST_MFSPR_PVR) { - PPC_WARN_EMULATED(mfpvr); + PPC_WARN_EMULATED(mfpvr, regs); rd = (instword >> 21) & 0x1f; regs->gpr[rd] = mfspr(SPRN_PVR); return 0; @@ -767,7 +767,7 @@ static int emulate_instruction(struct pt_regs *regs) /* Emulating the dcba insn is just a no-op. */ if ((instword & PPC_INST_DCBA_MASK) == PPC_INST_DCBA) { - PPC_WARN_EMULATED(dcba); + PPC_WARN_EMULATED(dcba, regs); return 0; } @@ -776,7 +776,7 @@ static int emulate_instruction(struct pt_regs *regs) int shift = (instword >> 21) & 0x1c; unsigned long msk = 0xf0000000UL >> shift; - PPC_WARN_EMULATED(mcrxr); + PPC_WARN_EMULATED(mcrxr, regs); regs->ccr = (regs->ccr & ~msk) | ((regs->xer >> shift) & msk); regs->xer &= ~0xf0000000UL; return 0; @@ -784,19 +784,19 @@ static int emulate_instruction(struct pt_regs *regs) /* Emulate load/store string insn. */ if ((instword & PPC_INST_STRING_GEN_MASK) == PPC_INST_STRING) { - PPC_WARN_EMULATED(string); + PPC_WARN_EMULATED(string, regs); return emulate_string_inst(regs, instword); } /* Emulate the popcntb (Population Count Bytes) instruction. */ if ((instword & PPC_INST_POPCNTB_MASK) == PPC_INST_POPCNTB) { - PPC_WARN_EMULATED(popcntb); + PPC_WARN_EMULATED(popcntb, regs); return emulate_popcntb_inst(regs, instword); } /* Emulate isel (Integer Select) instruction */ if ((instword & PPC_INST_ISEL_MASK) == PPC_INST_ISEL) { - PPC_WARN_EMULATED(isel); + PPC_WARN_EMULATED(isel, regs); return emulate_isel(regs, instword); } @@ -995,7 +995,7 @@ void SoftwareEmulation(struct pt_regs *regs) #ifdef CONFIG_MATH_EMULATION errcode = do_mathemu(regs); if (errcode >= 0) - PPC_WARN_EMULATED(math); + PPC_WARN_EMULATED(math, regs); switch (errcode) { case 0: @@ -1018,7 +1018,7 @@ void SoftwareEmulation(struct pt_regs *regs) #elif defined(CONFIG_8XX_MINIMAL_FPEMU) errcode = Soft_emulate_8xx(regs); if (errcode >= 0) - PPC_WARN_EMULATED(8xx); + PPC_WARN_EMULATED(8xx, regs); switch (errcode) { case 0: @@ -1129,7 +1129,7 @@ void altivec_assist_exception(struct pt_regs *regs) flush_altivec_to_thread(current); - PPC_WARN_EMULATED(altivec); + PPC_WARN_EMULATED(altivec, regs); err = emulate_altivec(regs); if (err == 0) { regs->nip += 4; /* skip emulated instruction */ diff --git a/arch/powerpc/lib/copypage_64.S b/arch/powerpc/lib/copypage_64.S index 75f3267fdc30..e68beac0a171 100644 --- a/arch/powerpc/lib/copypage_64.S +++ b/arch/powerpc/lib/copypage_64.S @@ -26,11 +26,11 @@ BEGIN_FTR_SECTION srd r8,r5,r11 mtctr r8 -setup: +.Lsetup: dcbt r9,r4 dcbz r9,r3 add r9,r9,r12 - bdnz setup + bdnz .Lsetup END_FTR_SECTION_IFSET(CPU_FTR_CP_USE_DCBTZ) addi r3,r3,-8 srdi r8,r5,7 /* page is copied in 128 byte strides */ diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S index c1427b3634ec..383a5d0e9818 100644 --- a/arch/powerpc/platforms/pseries/hvCall.S +++ b/arch/powerpc/platforms/pseries/hvCall.S @@ -14,68 +14,94 @@ #define STK_PARM(i) (48 + ((i)-3)*8) -#ifdef CONFIG_HCALL_STATS +#ifdef CONFIG_TRACEPOINTS + + .section ".toc","aw" + + .globl hcall_tracepoint_refcount +hcall_tracepoint_refcount: + .llong 0 + + .section ".text" + /* * precall must preserve all registers. use unused STK_PARM() - * areas to save snapshots and opcode. + * areas to save snapshots and opcode. We branch around this + * in early init (eg when populating the MMU hashtable) by using an + * unconditional cpu feature. */ -#define HCALL_INST_PRECALL \ - std r3,STK_PARM(r3)(r1); /* save opcode */ \ - mftb r0; /* get timebase and */ \ - std r0,STK_PARM(r5)(r1); /* save for later */ \ +#define HCALL_INST_PRECALL(FIRST_REG) \ BEGIN_FTR_SECTION; \ - mfspr r0,SPRN_PURR; /* get PURR and */ \ - std r0,STK_PARM(r6)(r1); /* save for later */ \ -END_FTR_SECTION_IFSET(CPU_FTR_PURR); - + b 1f; \ +END_FTR_SECTION(0, 1); \ + ld r12,hcall_tracepoint_refcount@toc(r2); \ + cmpdi r12,0; \ + beq+ 1f; \ + mflr r0; \ + std r3,STK_PARM(r3)(r1); \ + std r4,STK_PARM(r4)(r1); \ + std r5,STK_PARM(r5)(r1); \ + std r6,STK_PARM(r6)(r1); \ + std r7,STK_PARM(r7)(r1); \ + std r8,STK_PARM(r8)(r1); \ + std r9,STK_PARM(r9)(r1); \ + std r10,STK_PARM(r10)(r1); \ + std r0,16(r1); \ + addi r4,r1,STK_PARM(FIRST_REG); \ + stdu r1,-STACK_FRAME_OVERHEAD(r1); \ + bl .__trace_hcall_entry; \ + addi r1,r1,STACK_FRAME_OVERHEAD; \ + ld r0,16(r1); \ + ld r3,STK_PARM(r3)(r1); \ + ld r4,STK_PARM(r4)(r1); \ + ld r5,STK_PARM(r5)(r1); \ + ld r6,STK_PARM(r6)(r1); \ + ld r7,STK_PARM(r7)(r1); \ + ld r8,STK_PARM(r8)(r1); \ + ld r9,STK_PARM(r9)(r1); \ + ld r10,STK_PARM(r10)(r1); \ + mtlr r0; \ +1: + /* * postcall is performed immediately before function return which * allows liberal use of volatile registers. We branch around this * in early init (eg when populating the MMU hashtable) by using an * unconditional cpu feature. */ -#define HCALL_INST_POSTCALL \ +#define __HCALL_INST_POSTCALL \ BEGIN_FTR_SECTION; \ b 1f; \ END_FTR_SECTION(0, 1); \ - ld r4,STK_PARM(r3)(r1); /* validate opcode */ \ - cmpldi cr7,r4,MAX_HCALL_OPCODE; \ - bgt- cr7,1f; \ - \ - /* get time and PURR snapshots after hcall */ \ - mftb r7; /* timebase after */ \ -BEGIN_FTR_SECTION; \ - mfspr r8,SPRN_PURR; /* PURR after */ \ - ld r6,STK_PARM(r6)(r1); /* PURR before */ \ - subf r6,r6,r8; /* delta */ \ -END_FTR_SECTION_IFSET(CPU_FTR_PURR); \ - ld r5,STK_PARM(r5)(r1); /* timebase before */ \ - subf r5,r5,r7; /* time delta */ \ - \ - /* calculate address of stat structure r4 = opcode */ \ - srdi r4,r4,2; /* index into array */ \ - mulli r4,r4,HCALL_STAT_SIZE; \ - LOAD_REG_ADDR(r7, per_cpu__hcall_stats); \ - add r4,r4,r7; \ - ld r7,PACA_DATA_OFFSET(r13); /* per cpu offset */ \ - add r4,r4,r7; \ - \ - /* update stats */ \ - ld r7,HCALL_STAT_CALLS(r4); /* count */ \ - addi r7,r7,1; \ - std r7,HCALL_STAT_CALLS(r4); \ - ld r7,HCALL_STAT_TB(r4); /* timebase */ \ - add r7,r7,r5; \ - std r7,HCALL_STAT_TB(r4); \ -BEGIN_FTR_SECTION; \ - ld r7,HCALL_STAT_PURR(r4); /* PURR */ \ - add r7,r7,r6; \ - std r7,HCALL_STAT_PURR(r4); \ -END_FTR_SECTION_IFSET(CPU_FTR_PURR); \ + ld r12,hcall_tracepoint_refcount@toc(r2); \ + cmpdi r12,0; \ + beq+ 1f; \ + mflr r0; \ + ld r6,STK_PARM(r3)(r1); \ + std r3,STK_PARM(r3)(r1); \ + mr r4,r3; \ + mr r3,r6; \ + std r0,16(r1); \ + stdu r1,-STACK_FRAME_OVERHEAD(r1); \ + bl .__trace_hcall_exit; \ + addi r1,r1,STACK_FRAME_OVERHEAD; \ + ld r0,16(r1); \ + ld r3,STK_PARM(r3)(r1); \ + mtlr r0; \ 1: + +#define HCALL_INST_POSTCALL_NORETS \ + li r5,0; \ + __HCALL_INST_POSTCALL + +#define HCALL_INST_POSTCALL(BUFREG) \ + mr r5,BUFREG; \ + __HCALL_INST_POSTCALL + #else -#define HCALL_INST_PRECALL -#define HCALL_INST_POSTCALL +#define HCALL_INST_PRECALL(FIRST_ARG) +#define HCALL_INST_POSTCALL_NORETS +#define HCALL_INST_POSTCALL(BUFREG) #endif .text @@ -86,11 +112,11 @@ _GLOBAL(plpar_hcall_norets) mfcr r0 stw r0,8(r1) - HCALL_INST_PRECALL + HCALL_INST_PRECALL(r4) HVSC /* invoke the hypervisor */ - HCALL_INST_POSTCALL + HCALL_INST_POSTCALL_NORETS lwz r0,8(r1) mtcrf 0xff,r0 @@ -102,7 +128,7 @@ _GLOBAL(plpar_hcall) mfcr r0 stw r0,8(r1) - HCALL_INST_PRECALL + HCALL_INST_PRECALL(r5) std r4,STK_PARM(r4)(r1) /* Save ret buffer */ @@ -121,7 +147,7 @@ _GLOBAL(plpar_hcall) std r6, 16(r12) std r7, 24(r12) - HCALL_INST_POSTCALL + HCALL_INST_POSTCALL(r12) lwz r0,8(r1) mtcrf 0xff,r0 @@ -168,7 +194,7 @@ _GLOBAL(plpar_hcall9) mfcr r0 stw r0,8(r1) - HCALL_INST_PRECALL + HCALL_INST_PRECALL(r5) std r4,STK_PARM(r4)(r1) /* Save ret buffer */ @@ -196,7 +222,7 @@ _GLOBAL(plpar_hcall9) std r11,56(r12) std r0, 64(r12) - HCALL_INST_POSTCALL + HCALL_INST_POSTCALL(r12) lwz r0,8(r1) mtcrf 0xff,r0 diff --git a/arch/powerpc/platforms/pseries/hvCall_inst.c b/arch/powerpc/platforms/pseries/hvCall_inst.c index 3631a4f277eb..2f58c71b7259 100644 --- a/arch/powerpc/platforms/pseries/hvCall_inst.c +++ b/arch/powerpc/platforms/pseries/hvCall_inst.c @@ -26,6 +26,7 @@ #include <asm/hvcall.h> #include <asm/firmware.h> #include <asm/cputable.h> +#include <asm/trace.h> DEFINE_PER_CPU(struct hcall_stats[HCALL_STAT_ARRAY_SIZE], hcall_stats); @@ -100,6 +101,35 @@ static const struct file_operations hcall_inst_seq_fops = { #define HCALL_ROOT_DIR "hcall_inst" #define CPU_NAME_BUF_SIZE 32 + +static void probe_hcall_entry(unsigned long opcode, unsigned long *args) +{ + struct hcall_stats *h; + + if (opcode > MAX_HCALL_OPCODE) + return; + + h = &get_cpu_var(hcall_stats)[opcode / 4]; + h->tb_start = mftb(); + h->purr_start = mfspr(SPRN_PURR); +} + +static void probe_hcall_exit(unsigned long opcode, unsigned long retval, + unsigned long *retbuf) +{ + struct hcall_stats *h; + + if (opcode > MAX_HCALL_OPCODE) + return; + + h = &__get_cpu_var(hcall_stats)[opcode / 4]; + h->num_calls++; + h->tb_total = mftb() - h->tb_start; + h->purr_total = mfspr(SPRN_PURR) - h->purr_start; + + put_cpu_var(hcall_stats); +} + static int __init hcall_inst_init(void) { struct dentry *hcall_root; @@ -110,6 +140,14 @@ static int __init hcall_inst_init(void) if (!firmware_has_feature(FW_FEATURE_LPAR)) return 0; + if (register_trace_hcall_entry(probe_hcall_entry)) + return -EINVAL; + + if (register_trace_hcall_exit(probe_hcall_exit)) { + unregister_trace_hcall_entry(probe_hcall_entry); + return -EINVAL; + } + hcall_root = debugfs_create_dir(HCALL_ROOT_DIR, NULL); if (!hcall_root) return -ENOMEM; diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 903eb9eec687..0707653612ba 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -39,6 +39,7 @@ #include <asm/cputable.h> #include <asm/udbg.h> #include <asm/smp.h> +#include <asm/trace.h> #include "plpar_wrappers.h" #include "pseries.h" @@ -661,3 +662,35 @@ void arch_free_page(struct page *page, int order) EXPORT_SYMBOL(arch_free_page); #endif + +#ifdef CONFIG_TRACEPOINTS +/* + * We optimise our hcall path by placing hcall_tracepoint_refcount + * directly in the TOC so we can check if the hcall tracepoints are + * enabled via a single load. + */ + +/* NB: reg/unreg are called while guarded with the tracepoints_mutex */ +extern long hcall_tracepoint_refcount; + +void hcall_tracepoint_regfunc(void) +{ + hcall_tracepoint_refcount++; +} + +void hcall_tracepoint_unregfunc(void) +{ + hcall_tracepoint_refcount--; +} + +void __trace_hcall_entry(unsigned long opcode, unsigned long *args) +{ + trace_hcall_entry(opcode, args); +} + +void __trace_hcall_exit(long opcode, unsigned long retval, + unsigned long *retbuf) +{ + trace_hcall_exit(opcode, retval, retbuf); +} +#endif diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 43c0acad7160..16c673096a22 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -95,6 +95,34 @@ config S390 select HAVE_ARCH_TRACEHOOK select INIT_ALL_POSSIBLE select HAVE_PERF_EVENTS + select ARCH_INLINE_SPIN_TRYLOCK + select ARCH_INLINE_SPIN_TRYLOCK_BH + select ARCH_INLINE_SPIN_LOCK + select ARCH_INLINE_SPIN_LOCK_BH + select ARCH_INLINE_SPIN_LOCK_IRQ + select ARCH_INLINE_SPIN_LOCK_IRQSAVE + select ARCH_INLINE_SPIN_UNLOCK + select ARCH_INLINE_SPIN_UNLOCK_BH + select ARCH_INLINE_SPIN_UNLOCK_IRQ + select ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE + select ARCH_INLINE_READ_TRYLOCK + select ARCH_INLINE_READ_LOCK + select ARCH_INLINE_READ_LOCK_BH + select ARCH_INLINE_READ_LOCK_IRQ + select ARCH_INLINE_READ_LOCK_IRQSAVE + select ARCH_INLINE_READ_UNLOCK + select ARCH_INLINE_READ_UNLOCK_BH + select ARCH_INLINE_READ_UNLOCK_IRQ + select ARCH_INLINE_READ_UNLOCK_IRQRESTORE + select ARCH_INLINE_WRITE_TRYLOCK + select ARCH_INLINE_WRITE_LOCK + select ARCH_INLINE_WRITE_LOCK_BH + select ARCH_INLINE_WRITE_LOCK_IRQ + select ARCH_INLINE_WRITE_LOCK_IRQSAVE + select ARCH_INLINE_WRITE_UNLOCK + select ARCH_INLINE_WRITE_UNLOCK_BH + select ARCH_INLINE_WRITE_UNLOCK_IRQ + select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE config SCHED_OMIT_FRAME_POINTER bool diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c index b55fd7ed1c31..495589950dc7 100644 --- a/arch/s390/appldata/appldata_base.c +++ b/arch/s390/appldata/appldata_base.c @@ -61,12 +61,12 @@ static struct ctl_table appldata_table[] = { { .procname = "timer", .mode = S_IRUGO | S_IWUSR, - .proc_handler = &appldata_timer_handler, + .proc_handler = appldata_timer_handler, }, { .procname = "interval", .mode = S_IRUGO | S_IWUSR, - .proc_handler = &appldata_interval_handler, + .proc_handler = appldata_interval_handler, }, { }, }; diff --git a/arch/s390/include/asm/bug.h b/arch/s390/include/asm/bug.h index 7efd0abe8887..efb74fd5156e 100644 --- a/arch/s390/include/asm/bug.h +++ b/arch/s390/include/asm/bug.h @@ -49,7 +49,7 @@ #define BUG() do { \ __EMIT_BUG(0); \ - for (;;); \ + unreachable(); \ } while (0) #define WARN_ON(x) ({ \ diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h index 41ce6861174e..c9af0d19c7ab 100644 --- a/arch/s390/include/asm/spinlock.h +++ b/arch/s390/include/asm/spinlock.h @@ -191,33 +191,4 @@ static inline int __raw_write_trylock(raw_rwlock_t *rw) #define _raw_read_relax(lock) cpu_relax() #define _raw_write_relax(lock) cpu_relax() -#define __always_inline__spin_lock -#define __always_inline__read_lock -#define __always_inline__write_lock -#define __always_inline__spin_lock_bh -#define __always_inline__read_lock_bh -#define __always_inline__write_lock_bh -#define __always_inline__spin_lock_irq -#define __always_inline__read_lock_irq -#define __always_inline__write_lock_irq -#define __always_inline__spin_lock_irqsave -#define __always_inline__read_lock_irqsave -#define __always_inline__write_lock_irqsave -#define __always_inline__spin_trylock -#define __always_inline__read_trylock -#define __always_inline__write_trylock -#define __always_inline__spin_trylock_bh -#define __always_inline__spin_unlock -#define __always_inline__read_unlock -#define __always_inline__write_unlock -#define __always_inline__spin_unlock_bh -#define __always_inline__read_unlock_bh -#define __always_inline__write_unlock_bh -#define __always_inline__spin_unlock_irq -#define __always_inline__read_unlock_irq -#define __always_inline__write_unlock_irq -#define __always_inline__spin_unlock_irqrestore -#define __always_inline__read_unlock_irqrestore -#define __always_inline__write_unlock_irqrestore - #endif /* __ASM_SPINLOCK_H */ diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 0debcec23a39..fda1a8123f9b 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -527,59 +527,6 @@ asmlinkage long sys32_sendfile64(int out_fd, int in_fd, return ret; } -#ifdef CONFIG_SYSCTL_SYSCALL -struct __sysctl_args32 { - u32 name; - int nlen; - u32 oldval; - u32 oldlenp; - u32 newval; - u32 newlen; - u32 __unused[4]; -}; - -asmlinkage long sys32_sysctl(struct __sysctl_args32 __user *args) -{ - struct __sysctl_args32 tmp; - int error; - size_t oldlen; - size_t __user *oldlenp = NULL; - unsigned long addr = (((unsigned long)&args->__unused[0]) + 7) & ~7; - - if (copy_from_user(&tmp, args, sizeof(tmp))) - return -EFAULT; - - if (tmp.oldval && tmp.oldlenp) { - /* Duh, this is ugly and might not work if sysctl_args - is in read-only memory, but do_sysctl does indirectly - a lot of uaccess in both directions and we'd have to - basically copy the whole sysctl.c here, and - glibc's __sysctl uses rw memory for the structure - anyway. */ - if (get_user(oldlen, (u32 __user *)compat_ptr(tmp.oldlenp)) || - put_user(oldlen, (size_t __user *)addr)) - return -EFAULT; - oldlenp = (size_t __user *)addr; - } - - lock_kernel(); - error = do_sysctl(compat_ptr(tmp.name), tmp.nlen, compat_ptr(tmp.oldval), - oldlenp, compat_ptr(tmp.newval), tmp.newlen); - unlock_kernel(); - if (oldlenp) { - if (!error) { - if (get_user(oldlen, (size_t __user *)addr) || - put_user(oldlen, (u32 __user *)compat_ptr(tmp.oldlenp))) - error = -EFAULT; - } - if (copy_to_user(args->__unused, tmp.__unused, - sizeof(tmp.__unused))) - error = -EFAULT; - } - return error; -} -#endif - struct stat64_emu31 { unsigned long long st_dev; unsigned int __pad1; diff --git a/arch/s390/kernel/compat_linux.h b/arch/s390/kernel/compat_linux.h index c07f9ca05ade..45e9092b3aad 100644 --- a/arch/s390/kernel/compat_linux.h +++ b/arch/s390/kernel/compat_linux.h @@ -162,7 +162,6 @@ struct ucontext32 { compat_sigset_t uc_sigmask; /* mask last for extensibility */ }; -struct __sysctl_args32; struct stat64_emu31; struct mmap_arg_struct_emu31; struct fadvise64_64_args; @@ -212,7 +211,6 @@ long sys32_sendfile(int out_fd, int in_fd, compat_off_t __user *offset, size_t count); long sys32_sendfile64(int out_fd, int in_fd, compat_loff_t __user *offset, s32 count); -long sys32_sysctl(struct __sysctl_args32 __user *args); long sys32_stat64(char __user * filename, struct stat64_emu31 __user * statbuf); long sys32_lstat64(char __user * filename, struct stat64_emu31 __user * statbuf); diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S index cbd9901dc0f8..30de2d0e52bb 100644 --- a/arch/s390/kernel/compat_wrapper.S +++ b/arch/s390/kernel/compat_wrapper.S @@ -689,8 +689,6 @@ sys32_fdatasync_wrapper: llgfr %r2,%r2 # unsigned int jg sys_fdatasync # branch to system call -#sys32_sysctl_wrapper # tbd - .globl sys32_mlock_wrapper sys32_mlock_wrapper: llgfr %r2,%r2 # unsigned long @@ -1087,8 +1085,8 @@ sys32_stime_wrapper: .globl sys32_sysctl_wrapper sys32_sysctl_wrapper: - llgtr %r2,%r2 # struct __sysctl_args32 * - jg sys32_sysctl + llgtr %r2,%r2 # struct compat_sysctl_args * + jg compat_sys_sysctl .globl sys32_fstat64_wrapper sys32_fstat64_wrapper: diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index 20f282c911c2..071c81f179ef 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -893,35 +893,30 @@ s390dbf_procactive(ctl_table *table, int write, static struct ctl_table s390dbf_table[] = { { - .ctl_name = CTL_S390DBF_STOPPABLE, .procname = "debug_stoppable", .data = &debug_stoppable, .maxlen = sizeof(int), .mode = S_IRUGO | S_IWUSR, - .proc_handler = &proc_dointvec, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_S390DBF_ACTIVE, .procname = "debug_active", .data = &debug_active, .maxlen = sizeof(int), .mode = S_IRUGO | S_IWUSR, - .proc_handler = &s390dbf_procactive, - .strategy = &sysctl_intvec, + .proc_handler = s390dbf_procactive, }, - { .ctl_name = 0 } + { } }; static struct ctl_table s390dbf_dir_table[] = { { - .ctl_name = CTL_S390DBF, .procname = "s390dbf", .maxlen = 0, .mode = S_IRUGO | S_IXUGO, .child = s390dbf_table, }, - { .ctl_name = 0 } + { } }; static struct ctl_table_header *s390dbf_sysctl_header; diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index f5fe34dd821b..5a82bc68193e 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -203,73 +203,10 @@ out: #ifdef CONFIG_FTRACE_SYSCALLS -extern unsigned long __start_syscalls_metadata[]; -extern unsigned long __stop_syscalls_metadata[]; extern unsigned int sys_call_table[]; -static struct syscall_metadata **syscalls_metadata; - -struct syscall_metadata *syscall_nr_to_meta(int nr) -{ - if (!syscalls_metadata || nr >= NR_syscalls || nr < 0) - return NULL; - - return syscalls_metadata[nr]; -} - -int syscall_name_to_nr(char *name) -{ - int i; - - if (!syscalls_metadata) - return -1; - for (i = 0; i < NR_syscalls; i++) - if (syscalls_metadata[i]) - if (!strcmp(syscalls_metadata[i]->name, name)) - return i; - return -1; -} - -void set_syscall_enter_id(int num, int id) -{ - syscalls_metadata[num]->enter_id = id; -} - -void set_syscall_exit_id(int num, int id) +unsigned long __init arch_syscall_addr(int nr) { - syscalls_metadata[num]->exit_id = id; -} - -static struct syscall_metadata *find_syscall_meta(unsigned long syscall) -{ - struct syscall_metadata *start; - struct syscall_metadata *stop; - char str[KSYM_SYMBOL_LEN]; - - start = (struct syscall_metadata *)__start_syscalls_metadata; - stop = (struct syscall_metadata *)__stop_syscalls_metadata; - kallsyms_lookup(syscall, NULL, NULL, NULL, str); - - for ( ; start < stop; start++) { - if (start->name && !strcmp(start->name + 3, str + 3)) - return start; - } - return NULL; -} - -static int __init arch_init_ftrace_syscalls(void) -{ - struct syscall_metadata *meta; - int i; - syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) * NR_syscalls, - GFP_KERNEL); - if (!syscalls_metadata) - return -ENOMEM; - for (i = 0; i < NR_syscalls; i++) { - meta = find_syscall_meta((unsigned long)sys_call_table[i]); - syscalls_metadata[i] = meta; - } - return 0; + return (unsigned long)sys_call_table[nr]; } -arch_initcall(arch_init_ftrace_syscalls); #endif diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c index b201135cc18c..ff58779bf7e9 100644 --- a/arch/s390/mm/cmm.c +++ b/arch/s390/mm/cmm.c @@ -343,30 +343,29 @@ static struct ctl_table cmm_table[] = { { .procname = "cmm_pages", .mode = 0644, - .proc_handler = &cmm_pages_handler, + .proc_handler = cmm_pages_handler, }, { .procname = "cmm_timed_pages", .mode = 0644, - .proc_handler = &cmm_pages_handler, + .proc_handler = cmm_pages_handler, }, { .procname = "cmm_timeout", .mode = 0644, - .proc_handler = &cmm_timeout_handler, + .proc_handler = cmm_timeout_handler, }, - { .ctl_name = 0 } + { } }; static struct ctl_table cmm_dir_table[] = { { - .ctl_name = CTL_VM, .procname = "vm", .maxlen = 0, .mode = 0555, .child = cmm_table, }, - { .ctl_name = 0 } + { } }; #endif diff --git a/arch/sh/kernel/traps_64.c b/arch/sh/kernel/traps_64.c index 267e5ebbb475..75c0cbe2eda0 100644 --- a/arch/sh/kernel/traps_64.c +++ b/arch/sh/kernel/traps_64.c @@ -877,44 +877,39 @@ static int misaligned_fixup(struct pt_regs *regs) static ctl_table unaligned_table[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "kernel_reports", .data = &kernel_mode_unaligned_fixup_count, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { - .ctl_name = CTL_UNNUMBERED, .procname = "user_reports", .data = &user_mode_unaligned_fixup_count, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { - .ctl_name = CTL_UNNUMBERED, .procname = "user_enable", .data = &user_mode_unaligned_fixup_enable, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec}, + .proc_handler = proc_dointvec}, {} }; static ctl_table unaligned_root[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "unaligned_fixup", .mode = 0555, - unaligned_table + .child = unaligned_table }, {} }; static ctl_table sh64_root[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "sh64", .mode = 0555, .child = unaligned_root diff --git a/arch/sparc/include/asm/prom.h b/arch/sparc/include/asm/prom.h index 82a190d7efc1..f845828ca4c6 100644 --- a/arch/sparc/include/asm/prom.h +++ b/arch/sparc/include/asm/prom.h @@ -1,3 +1,4 @@ +#include <linux/of.h> /* linux/of.h gets to determine #include ordering */ #ifndef _SPARC_PROM_H #define _SPARC_PROM_H #ifdef __KERNEL__ @@ -28,50 +29,11 @@ #define of_prop_cmp(s1, s2) strcasecmp((s1), (s2)) #define of_node_cmp(s1, s2) strcmp((s1), (s2)) -typedef u32 phandle; -typedef u32 ihandle; - -struct property { - char *name; - int length; - void *value; - struct property *next; - unsigned long _flags; - unsigned int unique_id; -}; - -struct of_irq_controller; -struct device_node { - const char *name; - const char *type; - phandle node; - char *path_component_name; - char *full_name; - - struct property *properties; - struct property *deadprops; /* removed properties */ - struct device_node *parent; - struct device_node *child; - struct device_node *sibling; - struct device_node *next; /* next device of same type */ - struct device_node *allnext; /* next in list of all nodes */ - struct proc_dir_entry *pde; /* this node's proc directory */ - struct kref kref; - unsigned long _flags; - void *data; - unsigned int unique_id; - - struct of_irq_controller *irq_trans; -}; - struct of_irq_controller { unsigned int (*irq_build)(struct device_node *, unsigned int, void *); void *data; }; -#define OF_IS_DYNAMIC(x) test_bit(OF_DYNAMIC, &x->_flags) -#define OF_MARK_DYNAMIC(x) set_bit(OF_DYNAMIC, &x->_flags) - extern struct device_node *of_find_node_by_cpuid(int cpuid); extern int of_set_property(struct device_node *node, const char *name, void *val, int len); extern struct mutex of_set_property_mutex; @@ -89,15 +51,6 @@ extern void prom_build_devicetree(void); extern void of_populate_present_mask(void); extern void of_fill_in_cpu_data(void); -/* Dummy ref counting routines - to be implemented later */ -static inline struct device_node *of_node_get(struct device_node *node) -{ - return node; -} -static inline void of_node_put(struct device_node *node) -{ -} - /* These routines are here to provide compatibility with how powerpc * handles IRQ mapping for OF device nodes. We precompute and permanently * register them in the of_device objects, whereas powerpc computes them @@ -108,12 +61,6 @@ static inline void irq_dispose_mapping(unsigned int virq) { } -/* - * NB: This is here while we transition from using asm/prom.h - * to linux/of.h - */ -#include <linux/of.h> - extern struct device_node *of_console_device; extern char *of_console_path; extern char *of_console_options; diff --git a/arch/sparc/kernel/sys_sparc32.c b/arch/sparc/kernel/sys_sparc32.c index 04e28b2671c8..f862372074bc 100644 --- a/arch/sparc/kernel/sys_sparc32.c +++ b/arch/sparc/kernel/sys_sparc32.c @@ -591,63 +591,6 @@ out: return ret; } -struct __sysctl_args32 { - u32 name; - int nlen; - u32 oldval; - u32 oldlenp; - u32 newval; - u32 newlen; - u32 __unused[4]; -}; - -asmlinkage long sys32_sysctl(struct __sysctl_args32 __user *args) -{ -#ifndef CONFIG_SYSCTL_SYSCALL - return -ENOSYS; -#else - struct __sysctl_args32 tmp; - int error; - size_t oldlen, __user *oldlenp = NULL; - unsigned long addr = (((unsigned long)&args->__unused[0]) + 7UL) & ~7UL; - - if (copy_from_user(&tmp, args, sizeof(tmp))) - return -EFAULT; - - if (tmp.oldval && tmp.oldlenp) { - /* Duh, this is ugly and might not work if sysctl_args - is in read-only memory, but do_sysctl does indirectly - a lot of uaccess in both directions and we'd have to - basically copy the whole sysctl.c here, and - glibc's __sysctl uses rw memory for the structure - anyway. */ - if (get_user(oldlen, (u32 __user *)(unsigned long)tmp.oldlenp) || - put_user(oldlen, (size_t __user *)addr)) - return -EFAULT; - oldlenp = (size_t __user *)addr; - } - - lock_kernel(); - error = do_sysctl((int __user *)(unsigned long) tmp.name, - tmp.nlen, - (void __user *)(unsigned long) tmp.oldval, - oldlenp, - (void __user *)(unsigned long) tmp.newval, - tmp.newlen); - unlock_kernel(); - if (oldlenp) { - if (!error) { - if (get_user(oldlen, (size_t __user *)addr) || - put_user(oldlen, (u32 __user *)(unsigned long) tmp.oldlenp)) - error = -EFAULT; - } - if (copy_to_user(args->__unused, tmp.__unused, sizeof(tmp.__unused))) - error = -EFAULT; - } - return error; -#endif -} - long sys32_lookup_dcookie(unsigned long cookie_high, unsigned long cookie_low, char __user *buf, size_t len) diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S index 009825f6e73c..034b10e0d4b0 100644 --- a/arch/sparc/kernel/systbls_64.S +++ b/arch/sparc/kernel/systbls_64.S @@ -68,7 +68,7 @@ sys_call_table32: .word compat_sys_fstatfs64, sys_llseek, sys_mlock, sys_munlock, sys32_mlockall /*240*/ .word sys_munlockall, sys32_sched_setparam, sys32_sched_getparam, sys32_sched_setscheduler, sys32_sched_getscheduler .word sys_sched_yield, sys32_sched_get_priority_max, sys32_sched_get_priority_min, sys32_sched_rr_get_interval, compat_sys_nanosleep -/*250*/ .word sys32_mremap, sys32_sysctl, sys32_getsid, sys_fdatasync, sys32_nfsservctl +/*250*/ .word sys32_mremap, compat_sys_sysctl, sys32_getsid, sys_fdatasync, sys32_nfsservctl .word sys32_sync_file_range, compat_sys_clock_settime, compat_sys_clock_gettime, compat_sys_clock_getres, sys32_clock_nanosleep /*260*/ .word compat_sys_sched_getaffinity, compat_sys_sched_setaffinity, sys32_timer_settime, compat_sys_timer_gettime, sys_timer_getoverrun .word sys_timer_delete, compat_sys_timer_create, sys_ni_syscall, compat_sys_io_setup, sys_io_destroy diff --git a/arch/sparc/mm/init_64.h b/arch/sparc/mm/init_64.h index c2f772dbd556..77d1b313e344 100644 --- a/arch/sparc/mm/init_64.h +++ b/arch/sparc/mm/init_64.h @@ -45,7 +45,7 @@ extern void free_initmem(void); #define VMEMMAP_ALIGN(x) (((x)+VMEMMAP_CHUNK-1UL)&VMEMMAP_CHUNK_MASK) #define VMEMMAP_SIZE ((((1UL << MAX_PHYSADDR_BITS) >> PAGE_SHIFT) * \ - sizeof(struct page *)) >> VMEMMAP_CHUNK_SHIFT) + sizeof(struct page)) >> VMEMMAP_CHUNK_SHIFT) extern unsigned long vmemmap_table[VMEMMAP_SIZE]; #endif diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 72ace9515a07..178084b4377c 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -49,6 +49,7 @@ config X86 select HAVE_KERNEL_GZIP select HAVE_KERNEL_BZIP2 select HAVE_KERNEL_LZMA + select HAVE_HW_BREAKPOINT select HAVE_ARCH_KMEMCHECK config OUTPUT_FORMAT diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 2649840d888f..5e99762eb5c2 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -406,7 +406,7 @@ config X86_CMPXCHG64 # generates cmov. config X86_CMOV def_bool y - depends on (MK8 || MK7 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64 || MATOM) + depends on (MK8 || MK7 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64 || MATOM || MGEODE_LX) config X86_MINIMUM_CPU_FAMILY int diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index d105f29bb6bb..731318e5ac1d 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -186,6 +186,15 @@ config X86_DS_SELFTEST config HAVE_MMIOTRACE_SUPPORT def_bool y +config X86_DECODER_SELFTEST + bool "x86 instruction decoder selftest" + depends on DEBUG_KERNEL + ---help--- + Perform x86 instruction decoder selftests at build time. + This option is useful for checking the sanity of x86 instruction + decoder code. + If unsure, say "N". + # # IO delay types: # @@ -287,4 +296,18 @@ config OPTIMIZE_INLINING If unsure, say N. +config DEBUG_STRICT_USER_COPY_CHECKS + bool "Strict copy size checks" + depends on DEBUG_KERNEL && !TRACE_BRANCH_PROFILING + ---help--- + Enabling this option turns a certain set of sanity checks for user + copy operations into compile time failures. + + The copy_from_user() etc checks are there to help test if there + are sufficient security checks on the length argument of + the copy operation, by having gcc prove that the argument is + within bounds. + + If unsure, or if you run an older (pre 4.4) gcc, say N. + endmenu diff --git a/arch/x86/Makefile b/arch/x86/Makefile index d2d24c9ee64d..78b32be55e9e 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -155,6 +155,9 @@ all: bzImage KBUILD_IMAGE := $(boot)/bzImage bzImage: vmlinux +ifeq ($(CONFIG_X86_DECODER_SELFTEST),y) + $(Q)$(MAKE) $(build)=arch/x86/tools posttest +endif $(Q)$(MAKE) $(build)=$(boot) $(KBUILD_IMAGE) $(Q)mkdir -p $(objtree)/arch/$(UTS_MACHINE)/boot $(Q)ln -fsn ../../x86/boot/bzImage $(objtree)/arch/$(UTS_MACHINE)/boot/$@ diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu index 30e9a264f69d..cbf0776dbec1 100644 --- a/arch/x86/Makefile_32.cpu +++ b/arch/x86/Makefile_32.cpu @@ -41,7 +41,7 @@ cflags-$(CONFIG_X86_ELAN) += -march=i486 # Geode GX1 support cflags-$(CONFIG_MGEODEGX1) += -march=pentium-mmx - +cflags-$(CONFIG_MGEODE_LX) += $(call cc-option,-march=geode,-march=pentium-mmx) # add at the end to overwrite eventual tuning options from earlier # cpu entries cflags-$(CONFIG_X86_GENERIC) += $(call tune,generic,$(call tune,i686)) diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 581b0568fe19..5d2584839be4 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -653,7 +653,7 @@ ia32_sys_call_table: .quad compat_sys_writev .quad sys_getsid .quad sys_fdatasync - .quad sys32_sysctl /* sysctl */ + .quad compat_sys_sysctl /* sysctl */ .quad sys_mlock /* 150 */ .quad sys_munlock .quad sys_mlockall diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index 9f5527198825..df82c0e48ded 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -434,62 +434,6 @@ asmlinkage long sys32_rt_sigqueueinfo(int pid, int sig, return ret; } -#ifdef CONFIG_SYSCTL_SYSCALL -struct sysctl_ia32 { - unsigned int name; - int nlen; - unsigned int oldval; - unsigned int oldlenp; - unsigned int newval; - unsigned int newlen; - unsigned int __unused[4]; -}; - - -asmlinkage long sys32_sysctl(struct sysctl_ia32 __user *args32) -{ - struct sysctl_ia32 a32; - mm_segment_t old_fs = get_fs(); - void __user *oldvalp, *newvalp; - size_t oldlen; - int __user *namep; - long ret; - - if (copy_from_user(&a32, args32, sizeof(a32))) - return -EFAULT; - - /* - * We need to pre-validate these because we have to disable - * address checking before calling do_sysctl() because of - * OLDLEN but we can't run the risk of the user specifying bad - * addresses here. Well, since we're dealing with 32 bit - * addresses, we KNOW that access_ok() will always succeed, so - * this is an expensive NOP, but so what... - */ - namep = compat_ptr(a32.name); - oldvalp = compat_ptr(a32.oldval); - newvalp = compat_ptr(a32.newval); - - if ((oldvalp && get_user(oldlen, (int __user *)compat_ptr(a32.oldlenp))) - || !access_ok(VERIFY_WRITE, namep, 0) - || !access_ok(VERIFY_WRITE, oldvalp, 0) - || !access_ok(VERIFY_WRITE, newvalp, 0)) - return -EFAULT; - - set_fs(KERNEL_DS); - lock_kernel(); - ret = do_sysctl(namep, a32.nlen, oldvalp, (size_t __user *)&oldlen, - newvalp, (size_t) a32.newlen); - unlock_kernel(); - set_fs(old_fs); - - if (oldvalp && put_user(oldlen, (int __user *)compat_ptr(a32.oldlenp))) - return -EFAULT; - - return ret; -} -#endif - /* warning: next two assume little endian */ asmlinkage long sys32_pread(unsigned int fd, char __user *ubuf, u32 count, u32 poslo, u32 poshi) diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild index 4a8e80cdcfa5..9f828f87ca35 100644 --- a/arch/x86/include/asm/Kbuild +++ b/arch/x86/include/asm/Kbuild @@ -10,6 +10,7 @@ header-y += ptrace-abi.h header-y += sigcontext32.h header-y += ucontext.h header-y += processor-flags.h +header-y += hw_breakpoint.h unifdef-y += e820.h unifdef-y += ist.h diff --git a/arch/x86/include/asm/a.out-core.h b/arch/x86/include/asm/a.out-core.h index bb70e397aa84..7a15588e45d4 100644 --- a/arch/x86/include/asm/a.out-core.h +++ b/arch/x86/include/asm/a.out-core.h @@ -17,6 +17,7 @@ #include <linux/user.h> #include <linux/elfcore.h> +#include <asm/debugreg.h> /* * fill in the user structure for an a.out core dump @@ -32,14 +33,7 @@ static inline void aout_dump_thread(struct pt_regs *regs, struct user *dump) >> PAGE_SHIFT; dump->u_dsize -= dump->u_tsize; dump->u_ssize = 0; - dump->u_debugreg[0] = current->thread.debugreg0; - dump->u_debugreg[1] = current->thread.debugreg1; - dump->u_debugreg[2] = current->thread.debugreg2; - dump->u_debugreg[3] = current->thread.debugreg3; - dump->u_debugreg[4] = 0; - dump->u_debugreg[5] = 0; - dump->u_debugreg[6] = current->thread.debugreg6; - dump->u_debugreg[7] = current->thread.debugreg7; + aout_dump_debugregs(dump); if (dump->start_stack < TASK_SIZE) dump->u_ssize = ((unsigned long)(TASK_SIZE - dump->start_stack)) diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h index e2077d343c33..b97f786a48d5 100644 --- a/arch/x86/include/asm/alternative-asm.h +++ b/arch/x86/include/asm/alternative-asm.h @@ -1,17 +1,13 @@ #ifdef __ASSEMBLY__ -#ifdef CONFIG_X86_32 -# define X86_ALIGN .long -#else -# define X86_ALIGN .quad -#endif +#include <asm/asm.h> #ifdef CONFIG_SMP .macro LOCK_PREFIX 1: lock .section .smp_locks,"a" - .align 4 - X86_ALIGN 1b + _ASM_ALIGN + _ASM_PTR 1b .previous .endm #else diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index c240efc74e00..69b74a7b877f 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -84,6 +84,7 @@ static inline void alternatives_smp_switch(int smp) {} " .byte " __stringify(feature) "\n" /* feature bit */ \ " .byte 662b-661b\n" /* sourcelen */ \ " .byte 664f-663f\n" /* replacementlen */ \ + " .byte 0xff + (664f-663f) - (662b-661b)\n" /* rlen <= slen */ \ ".previous\n" \ ".section .altinstr_replacement, \"ax\"\n" \ "663:\n\t" newinstr "\n664:\n" /* replacement */ \ diff --git a/arch/x86/include/asm/amd_iommu.h b/arch/x86/include/asm/amd_iommu.h index 4b180897e6b5..5af2982133b5 100644 --- a/arch/x86/include/asm/amd_iommu.h +++ b/arch/x86/include/asm/amd_iommu.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2008 Advanced Micro Devices, Inc. + * Copyright (C) 2007-2009 Advanced Micro Devices, Inc. * Author: Joerg Roedel <joerg.roedel@amd.com> * Leo Duran <leo.duran@amd.com> * @@ -23,19 +23,13 @@ #include <linux/irqreturn.h> #ifdef CONFIG_AMD_IOMMU -extern int amd_iommu_init(void); -extern int amd_iommu_init_dma_ops(void); -extern int amd_iommu_init_passthrough(void); + extern void amd_iommu_detect(void); -extern irqreturn_t amd_iommu_int_handler(int irq, void *data); -extern void amd_iommu_flush_all_domains(void); -extern void amd_iommu_flush_all_devices(void); -extern void amd_iommu_shutdown(void); -extern void amd_iommu_apply_erratum_63(u16 devid); + #else -static inline int amd_iommu_init(void) { return -ENODEV; } + static inline void amd_iommu_detect(void) { } -static inline void amd_iommu_shutdown(void) { } + #endif #endif /* _ASM_X86_AMD_IOMMU_H */ diff --git a/arch/x86/include/asm/amd_iommu_proto.h b/arch/x86/include/asm/amd_iommu_proto.h new file mode 100644 index 000000000000..84786fb9a23b --- /dev/null +++ b/arch/x86/include/asm/amd_iommu_proto.h @@ -0,0 +1,38 @@ +/* + * Copyright (C) 2009 Advanced Micro Devices, Inc. + * Author: Joerg Roedel <joerg.roedel@amd.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#ifndef _ASM_X86_AMD_IOMMU_PROTO_H +#define _ASM_X86_AMD_IOMMU_PROTO_H + +struct amd_iommu; + +extern int amd_iommu_init_dma_ops(void); +extern int amd_iommu_init_passthrough(void); +extern irqreturn_t amd_iommu_int_handler(int irq, void *data); +extern void amd_iommu_flush_all_domains(void); +extern void amd_iommu_flush_all_devices(void); +extern void amd_iommu_apply_erratum_63(u16 devid); +extern void amd_iommu_reset_cmd_buffer(struct amd_iommu *iommu); + +#ifndef CONFIG_AMD_IOMMU_STATS + +static inline void amd_iommu_stats_init(void) { } + +#endif /* !CONFIG_AMD_IOMMU_STATS */ + +#endif /* _ASM_X86_AMD_IOMMU_PROTO_H */ diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h index 2a2cc7a78a81..ba19ad4c47d0 100644 --- a/arch/x86/include/asm/amd_iommu_types.h +++ b/arch/x86/include/asm/amd_iommu_types.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2008 Advanced Micro Devices, Inc. + * Copyright (C) 2007-2009 Advanced Micro Devices, Inc. * Author: Joerg Roedel <joerg.roedel@amd.com> * Leo Duran <leo.duran@amd.com> * @@ -25,6 +25,11 @@ #include <linux/spinlock.h> /* + * Maximum number of IOMMUs supported + */ +#define MAX_IOMMUS 32 + +/* * some size calculation constants */ #define DEV_TABLE_ENTRY_SIZE 32 @@ -206,6 +211,9 @@ extern bool amd_iommu_dump; printk(KERN_INFO "AMD-Vi: " format, ## arg); \ } while(0); +/* global flag if IOMMUs cache non-present entries */ +extern bool amd_iommu_np_cache; + /* * Make iterating over all IOMMUs easier */ @@ -226,6 +234,8 @@ extern bool amd_iommu_dump; * independent of their use. */ struct protection_domain { + struct list_head list; /* for list of all protection domains */ + struct list_head dev_list; /* List of all devices in this domain */ spinlock_t lock; /* mostly used to lock the page table*/ u16 id; /* the domain id written to the device table */ int mode; /* paging mode (0-6 levels) */ @@ -233,7 +243,20 @@ struct protection_domain { unsigned long flags; /* flags to find out type of domain */ bool updated; /* complete domain flush required */ unsigned dev_cnt; /* devices assigned to this domain */ + unsigned dev_iommu[MAX_IOMMUS]; /* per-IOMMU reference count */ void *priv; /* private data */ + +}; + +/* + * This struct contains device specific data for the IOMMU + */ +struct iommu_dev_data { + struct list_head list; /* For domain->dev_list */ + struct device *dev; /* Device this data belong to */ + struct device *alias; /* The Alias Device */ + struct protection_domain *domain; /* Domain the device is bound to */ + atomic_t bind; /* Domain attach reverent count */ }; /* @@ -291,6 +314,9 @@ struct dma_ops_domain { struct amd_iommu { struct list_head list; + /* Index within the IOMMU array */ + int index; + /* locks the accesses to the hardware */ spinlock_t lock; @@ -357,6 +383,21 @@ struct amd_iommu { extern struct list_head amd_iommu_list; /* + * Array with pointers to each IOMMU struct + * The indices are referenced in the protection domains + */ +extern struct amd_iommu *amd_iommus[MAX_IOMMUS]; + +/* Number of IOMMUs present in the system */ +extern int amd_iommus_present; + +/* + * Declarations for the global list of all protection domains + */ +extern spinlock_t amd_iommu_pd_lock; +extern struct list_head amd_iommu_pd_list; + +/* * Structure defining one entry in the device table */ struct dev_table_entry { @@ -416,15 +457,9 @@ extern unsigned amd_iommu_aperture_order; /* largest PCI device id we expect translation requests for */ extern u16 amd_iommu_last_bdf; -/* data structures for protection domain handling */ -extern struct protection_domain **amd_iommu_pd_table; - /* allocation bitmap for domain ids */ extern unsigned long *amd_iommu_pd_alloc_bitmap; -/* will be 1 if device isolation is enabled */ -extern bool amd_iommu_isolate; - /* * If true, the addresses will be flushed on unmap time, not when * they are reused @@ -462,11 +497,6 @@ struct __iommu_counter { #define ADD_STATS_COUNTER(name, x) #define SUB_STATS_COUNTER(name, x) -static inline void amd_iommu_stats_init(void) { } - #endif /* CONFIG_AMD_IOMMU_STATS */ -/* some function prototypes */ -extern void amd_iommu_reset_cmd_buffer(struct amd_iommu *iommu); - #endif /* _ASM_X86_AMD_IOMMU_TYPES_H */ diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 474d80d3e6cc..b4ac2cdcb64f 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -297,20 +297,20 @@ struct apic { int disable_esr; int dest_logical; - unsigned long (*check_apicid_used)(physid_mask_t bitmap, int apicid); + unsigned long (*check_apicid_used)(physid_mask_t *map, int apicid); unsigned long (*check_apicid_present)(int apicid); void (*vector_allocation_domain)(int cpu, struct cpumask *retmask); void (*init_apic_ldr)(void); - physid_mask_t (*ioapic_phys_id_map)(physid_mask_t map); + void (*ioapic_phys_id_map)(physid_mask_t *phys_map, physid_mask_t *retmap); void (*setup_apic_routing)(void); int (*multi_timer_check)(int apic, int irq); int (*apicid_to_node)(int logical_apicid); int (*cpu_to_logical_apicid)(int cpu); int (*cpu_present_to_apicid)(int mps_cpu); - physid_mask_t (*apicid_to_cpu_present)(int phys_apicid); + void (*apicid_to_cpu_present)(int phys_apicid, physid_mask_t *retmap); void (*setup_portio_remap)(void); int (*check_phys_apicid_present)(int phys_apicid); void (*enable_apic_mode)(void); @@ -488,6 +488,8 @@ static inline unsigned int read_apic_id(void) extern void default_setup_apic_routing(void); +extern struct apic apic_noop; + #ifdef CONFIG_X86_32 extern struct apic apic_default; @@ -532,9 +534,9 @@ default_cpu_mask_to_apicid_and(const struct cpumask *cpumask, return (unsigned int)(mask1 & mask2 & mask3); } -static inline unsigned long default_check_apicid_used(physid_mask_t bitmap, int apicid) +static inline unsigned long default_check_apicid_used(physid_mask_t *map, int apicid) { - return physid_isset(apicid, bitmap); + return physid_isset(apicid, *map); } static inline unsigned long default_check_apicid_present(int bit) @@ -542,9 +544,9 @@ static inline unsigned long default_check_apicid_present(int bit) return physid_isset(bit, phys_cpu_present_map); } -static inline physid_mask_t default_ioapic_phys_id_map(physid_mask_t phys_map) +static inline void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap) { - return phys_map; + *retmap = *phys_map; } /* Mapping from cpu number to logical apicid */ @@ -583,11 +585,6 @@ extern int default_cpu_present_to_apicid(int mps_cpu); extern int default_check_phys_apicid_present(int phys_apicid); #endif -static inline physid_mask_t default_apicid_to_cpu_present(int phys_apicid) -{ - return physid_mask_of_physid(phys_apicid); -} - #endif /* CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_32 diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h index 3b62da926de9..7fe3b3060f08 100644 --- a/arch/x86/include/asm/apicdef.h +++ b/arch/x86/include/asm/apicdef.h @@ -11,6 +11,12 @@ #define IO_APIC_DEFAULT_PHYS_BASE 0xfec00000 #define APIC_DEFAULT_PHYS_BASE 0xfee00000 +/* + * This is the IO-APIC register space as specified + * by Intel docs: + */ +#define IO_APIC_SLOT_SIZE 1024 + #define APIC_ID 0x20 #define APIC_LVR 0x30 diff --git a/arch/x86/include/asm/apicnum.h b/arch/x86/include/asm/apicnum.h deleted file mode 100644 index 82f613c607ce..000000000000 --- a/arch/x86/include/asm/apicnum.h +++ /dev/null @@ -1,12 +0,0 @@ -#ifndef _ASM_X86_APICNUM_H -#define _ASM_X86_APICNUM_H - -/* define MAX_IO_APICS */ -#ifdef CONFIG_X86_32 -# define MAX_IO_APICS 64 -#else -# define MAX_IO_APICS 128 -# define MAX_LOCAL_APIC 32768 -#endif - -#endif /* _ASM_X86_APICNUM_H */ diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index d9cf1cd156d2..f654d1bb17fb 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -22,14 +22,14 @@ do { \ ".popsection" \ : : "i" (__FILE__), "i" (__LINE__), \ "i" (sizeof(struct bug_entry))); \ - for (;;) ; \ + unreachable(); \ } while (0) #else #define BUG() \ do { \ asm volatile("ud2"); \ - for (;;) ; \ + unreachable(); \ } while (0) #endif diff --git a/arch/x86/include/asm/calgary.h b/arch/x86/include/asm/calgary.h index b03bedb62aa7..0918654305af 100644 --- a/arch/x86/include/asm/calgary.h +++ b/arch/x86/include/asm/calgary.h @@ -62,10 +62,8 @@ struct cal_chipset_ops { extern int use_calgary; #ifdef CONFIG_CALGARY_IOMMU -extern int calgary_iommu_init(void); extern void detect_calgary(void); #else -static inline int calgary_iommu_init(void) { return 1; } static inline void detect_calgary(void) { return; } #endif diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h index ee1931be6593..ffb9bb6b6c37 100644 --- a/arch/x86/include/asm/cmpxchg_32.h +++ b/arch/x86/include/asm/cmpxchg_32.h @@ -8,14 +8,50 @@ * you need to test for the feature in boot_cpu_data. */ -#define xchg(ptr, v) \ - ((__typeof__(*(ptr)))__xchg((unsigned long)(v), (ptr), sizeof(*(ptr)))) +extern void __xchg_wrong_size(void); + +/* + * Note: no "lock" prefix even on SMP: xchg always implies lock anyway + * Note 2: xchg has side effect, so that attribute volatile is necessary, + * but generally the primitive is invalid, *ptr is output argument. --ANK + */ struct __xchg_dummy { unsigned long a[100]; }; #define __xg(x) ((struct __xchg_dummy *)(x)) +#define __xchg(x, ptr, size) \ +({ \ + __typeof(*(ptr)) __x = (x); \ + switch (size) { \ + case 1: \ + asm volatile("xchgb %b0,%1" \ + : "=q" (__x) \ + : "m" (*__xg(ptr)), "0" (__x) \ + : "memory"); \ + break; \ + case 2: \ + asm volatile("xchgw %w0,%1" \ + : "=r" (__x) \ + : "m" (*__xg(ptr)), "0" (__x) \ + : "memory"); \ + break; \ + case 4: \ + asm volatile("xchgl %0,%1" \ + : "=r" (__x) \ + : "m" (*__xg(ptr)), "0" (__x) \ + : "memory"); \ + break; \ + default: \ + __xchg_wrong_size(); \ + } \ + __x; \ +}) + +#define xchg(ptr, v) \ + __xchg((v), (ptr), sizeof(*ptr)) + /* * The semantics of XCHGCMP8B are a bit strange, this is why * there is a loop and the loading of %%eax and %%edx has to @@ -71,57 +107,63 @@ static inline void __set_64bit_var(unsigned long long *ptr, (unsigned int)((value) >> 32)) \ : __set_64bit(ptr, ll_low((value)), ll_high((value)))) -/* - * Note: no "lock" prefix even on SMP: xchg always implies lock anyway - * Note 2: xchg has side effect, so that attribute volatile is necessary, - * but generally the primitive is invalid, *ptr is output argument. --ANK - */ -static inline unsigned long __xchg(unsigned long x, volatile void *ptr, - int size) -{ - switch (size) { - case 1: - asm volatile("xchgb %b0,%1" - : "=q" (x) - : "m" (*__xg(ptr)), "0" (x) - : "memory"); - break; - case 2: - asm volatile("xchgw %w0,%1" - : "=r" (x) - : "m" (*__xg(ptr)), "0" (x) - : "memory"); - break; - case 4: - asm volatile("xchgl %0,%1" - : "=r" (x) - : "m" (*__xg(ptr)), "0" (x) - : "memory"); - break; - } - return x; -} +extern void __cmpxchg_wrong_size(void); /* * Atomic compare and exchange. Compare OLD with MEM, if identical, * store NEW in MEM. Return the initial value in MEM. Success is * indicated by comparing RETURN with OLD. */ +#define __raw_cmpxchg(ptr, old, new, size, lock) \ +({ \ + __typeof__(*(ptr)) __ret; \ + __typeof__(*(ptr)) __old = (old); \ + __typeof__(*(ptr)) __new = (new); \ + switch (size) { \ + case 1: \ + asm volatile(lock "cmpxchgb %b1,%2" \ + : "=a"(__ret) \ + : "q"(__new), "m"(*__xg(ptr)), "0"(__old) \ + : "memory"); \ + break; \ + case 2: \ + asm volatile(lock "cmpxchgw %w1,%2" \ + : "=a"(__ret) \ + : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \ + : "memory"); \ + break; \ + case 4: \ + asm volatile(lock "cmpxchgl %1,%2" \ + : "=a"(__ret) \ + : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \ + : "memory"); \ + break; \ + default: \ + __cmpxchg_wrong_size(); \ + } \ + __ret; \ +}) + +#define __cmpxchg(ptr, old, new, size) \ + __raw_cmpxchg((ptr), (old), (new), (size), LOCK_PREFIX) + +#define __sync_cmpxchg(ptr, old, new, size) \ + __raw_cmpxchg((ptr), (old), (new), (size), "lock; ") + +#define __cmpxchg_local(ptr, old, new, size) \ + __raw_cmpxchg((ptr), (old), (new), (size), "") #ifdef CONFIG_X86_CMPXCHG #define __HAVE_ARCH_CMPXCHG 1 -#define cmpxchg(ptr, o, n) \ - ((__typeof__(*(ptr)))__cmpxchg((ptr), (unsigned long)(o), \ - (unsigned long)(n), \ - sizeof(*(ptr)))) -#define sync_cmpxchg(ptr, o, n) \ - ((__typeof__(*(ptr)))__sync_cmpxchg((ptr), (unsigned long)(o), \ - (unsigned long)(n), \ - sizeof(*(ptr)))) -#define cmpxchg_local(ptr, o, n) \ - ((__typeof__(*(ptr)))__cmpxchg_local((ptr), (unsigned long)(o), \ - (unsigned long)(n), \ - sizeof(*(ptr)))) + +#define cmpxchg(ptr, old, new) \ + __cmpxchg((ptr), (old), (new), sizeof(*ptr)) + +#define sync_cmpxchg(ptr, old, new) \ + __sync_cmpxchg((ptr), (old), (new), sizeof(*ptr)) + +#define cmpxchg_local(ptr, old, new) \ + __cmpxchg_local((ptr), (old), (new), sizeof(*ptr)) #endif #ifdef CONFIG_X86_CMPXCHG64 @@ -133,94 +175,6 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, (unsigned long long)(n))) #endif -static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, - unsigned long new, int size) -{ - unsigned long prev; - switch (size) { - case 1: - asm volatile(LOCK_PREFIX "cmpxchgb %b1,%2" - : "=a"(prev) - : "q"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 2: - asm volatile(LOCK_PREFIX "cmpxchgw %w1,%2" - : "=a"(prev) - : "r"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 4: - asm volatile(LOCK_PREFIX "cmpxchgl %1,%2" - : "=a"(prev) - : "r"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - } - return old; -} - -/* - * Always use locked operations when touching memory shared with a - * hypervisor, since the system may be SMP even if the guest kernel - * isn't. - */ -static inline unsigned long __sync_cmpxchg(volatile void *ptr, - unsigned long old, - unsigned long new, int size) -{ - unsigned long prev; - switch (size) { - case 1: - asm volatile("lock; cmpxchgb %b1,%2" - : "=a"(prev) - : "q"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 2: - asm volatile("lock; cmpxchgw %w1,%2" - : "=a"(prev) - : "r"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 4: - asm volatile("lock; cmpxchgl %1,%2" - : "=a"(prev) - : "r"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - } - return old; -} - -static inline unsigned long __cmpxchg_local(volatile void *ptr, - unsigned long old, - unsigned long new, int size) -{ - unsigned long prev; - switch (size) { - case 1: - asm volatile("cmpxchgb %b1,%2" - : "=a"(prev) - : "q"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 2: - asm volatile("cmpxchgw %w1,%2" - : "=a"(prev) - : "r"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 4: - asm volatile("cmpxchgl %1,%2" - : "=a"(prev) - : "r"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - } - return old; -} - static inline unsigned long long __cmpxchg64(volatile void *ptr, unsigned long long old, unsigned long long new) diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h index 52de72e0de8c..485ae415faec 100644 --- a/arch/x86/include/asm/cmpxchg_64.h +++ b/arch/x86/include/asm/cmpxchg_64.h @@ -3,9 +3,6 @@ #include <asm/alternative.h> /* Provides LOCK_PREFIX */ -#define xchg(ptr, v) ((__typeof__(*(ptr)))__xchg((unsigned long)(v), \ - (ptr), sizeof(*(ptr)))) - #define __xg(x) ((volatile long *)(x)) static inline void set_64bit(volatile unsigned long *ptr, unsigned long val) @@ -15,167 +12,118 @@ static inline void set_64bit(volatile unsigned long *ptr, unsigned long val) #define _set_64bit set_64bit +extern void __xchg_wrong_size(void); +extern void __cmpxchg_wrong_size(void); + /* * Note: no "lock" prefix even on SMP: xchg always implies lock anyway * Note 2: xchg has side effect, so that attribute volatile is necessary, * but generally the primitive is invalid, *ptr is output argument. --ANK */ -static inline unsigned long __xchg(unsigned long x, volatile void *ptr, - int size) -{ - switch (size) { - case 1: - asm volatile("xchgb %b0,%1" - : "=q" (x) - : "m" (*__xg(ptr)), "0" (x) - : "memory"); - break; - case 2: - asm volatile("xchgw %w0,%1" - : "=r" (x) - : "m" (*__xg(ptr)), "0" (x) - : "memory"); - break; - case 4: - asm volatile("xchgl %k0,%1" - : "=r" (x) - : "m" (*__xg(ptr)), "0" (x) - : "memory"); - break; - case 8: - asm volatile("xchgq %0,%1" - : "=r" (x) - : "m" (*__xg(ptr)), "0" (x) - : "memory"); - break; - } - return x; -} +#define __xchg(x, ptr, size) \ +({ \ + __typeof(*(ptr)) __x = (x); \ + switch (size) { \ + case 1: \ + asm volatile("xchgb %b0,%1" \ + : "=q" (__x) \ + : "m" (*__xg(ptr)), "0" (__x) \ + : "memory"); \ + break; \ + case 2: \ + asm volatile("xchgw %w0,%1" \ + : "=r" (__x) \ + : "m" (*__xg(ptr)), "0" (__x) \ + : "memory"); \ + break; \ + case 4: \ + asm volatile("xchgl %k0,%1" \ + : "=r" (__x) \ + : "m" (*__xg(ptr)), "0" (__x) \ + : "memory"); \ + break; \ + case 8: \ + asm volatile("xchgq %0,%1" \ + : "=r" (__x) \ + : "m" (*__xg(ptr)), "0" (__x) \ + : "memory"); \ + break; \ + default: \ + __xchg_wrong_size(); \ + } \ + __x; \ +}) + +#define xchg(ptr, v) \ + __xchg((v), (ptr), sizeof(*ptr)) + +#define __HAVE_ARCH_CMPXCHG 1 /* * Atomic compare and exchange. Compare OLD with MEM, if identical, * store NEW in MEM. Return the initial value in MEM. Success is * indicated by comparing RETURN with OLD. */ +#define __raw_cmpxchg(ptr, old, new, size, lock) \ +({ \ + __typeof__(*(ptr)) __ret; \ + __typeof__(*(ptr)) __old = (old); \ + __typeof__(*(ptr)) __new = (new); \ + switch (size) { \ + case 1: \ + asm volatile(lock "cmpxchgb %b1,%2" \ + : "=a"(__ret) \ + : "q"(__new), "m"(*__xg(ptr)), "0"(__old) \ + : "memory"); \ + break; \ + case 2: \ + asm volatile(lock "cmpxchgw %w1,%2" \ + : "=a"(__ret) \ + : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \ + : "memory"); \ + break; \ + case 4: \ + asm volatile(lock "cmpxchgl %k1,%2" \ + : "=a"(__ret) \ + : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \ + : "memory"); \ + break; \ + case 8: \ + asm volatile(lock "cmpxchgq %1,%2" \ + : "=a"(__ret) \ + : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \ + : "memory"); \ + break; \ + default: \ + __cmpxchg_wrong_size(); \ + } \ + __ret; \ +}) -#define __HAVE_ARCH_CMPXCHG 1 +#define __cmpxchg(ptr, old, new, size) \ + __raw_cmpxchg((ptr), (old), (new), (size), LOCK_PREFIX) -static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, - unsigned long new, int size) -{ - unsigned long prev; - switch (size) { - case 1: - asm volatile(LOCK_PREFIX "cmpxchgb %b1,%2" - : "=a"(prev) - : "q"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 2: - asm volatile(LOCK_PREFIX "cmpxchgw %w1,%2" - : "=a"(prev) - : "r"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 4: - asm volatile(LOCK_PREFIX "cmpxchgl %k1,%2" - : "=a"(prev) - : "r"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 8: - asm volatile(LOCK_PREFIX "cmpxchgq %1,%2" - : "=a"(prev) - : "r"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - } - return old; -} +#define __sync_cmpxchg(ptr, old, new, size) \ + __raw_cmpxchg((ptr), (old), (new), (size), "lock; ") -/* - * Always use locked operations when touching memory shared with a - * hypervisor, since the system may be SMP even if the guest kernel - * isn't. - */ -static inline unsigned long __sync_cmpxchg(volatile void *ptr, - unsigned long old, - unsigned long new, int size) -{ - unsigned long prev; - switch (size) { - case 1: - asm volatile("lock; cmpxchgb %b1,%2" - : "=a"(prev) - : "q"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 2: - asm volatile("lock; cmpxchgw %w1,%2" - : "=a"(prev) - : "r"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 4: - asm volatile("lock; cmpxchgl %1,%2" - : "=a"(prev) - : "r"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - } - return old; -} +#define __cmpxchg_local(ptr, old, new, size) \ + __raw_cmpxchg((ptr), (old), (new), (size), "") -static inline unsigned long __cmpxchg_local(volatile void *ptr, - unsigned long old, - unsigned long new, int size) -{ - unsigned long prev; - switch (size) { - case 1: - asm volatile("cmpxchgb %b1,%2" - : "=a"(prev) - : "q"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 2: - asm volatile("cmpxchgw %w1,%2" - : "=a"(prev) - : "r"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 4: - asm volatile("cmpxchgl %k1,%2" - : "=a"(prev) - : "r"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 8: - asm volatile("cmpxchgq %1,%2" - : "=a"(prev) - : "r"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - } - return old; -} +#define cmpxchg(ptr, old, new) \ + __cmpxchg((ptr), (old), (new), sizeof(*ptr)) + +#define sync_cmpxchg(ptr, old, new) \ + __sync_cmpxchg((ptr), (old), (new), sizeof(*ptr)) + +#define cmpxchg_local(ptr, old, new) \ + __cmpxchg_local((ptr), (old), (new), sizeof(*ptr)) -#define cmpxchg(ptr, o, n) \ - ((__typeof__(*(ptr)))__cmpxchg((ptr), (unsigned long)(o), \ - (unsigned long)(n), sizeof(*(ptr)))) #define cmpxchg64(ptr, o, n) \ ({ \ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ cmpxchg((ptr), (o), (n)); \ }) -#define cmpxchg_local(ptr, o, n) \ - ((__typeof__(*(ptr)))__cmpxchg_local((ptr), (unsigned long)(o), \ - (unsigned long)(n), \ - sizeof(*(ptr)))) -#define sync_cmpxchg(ptr, o, n) \ - ((__typeof__(*(ptr)))__sync_cmpxchg((ptr), (unsigned long)(o), \ - (unsigned long)(n), \ - sizeof(*(ptr)))) + #define cmpxchg64_local(ptr, o, n) \ ({ \ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h index 3ea6f37be9e2..8240f76b531e 100644 --- a/arch/x86/include/asm/debugreg.h +++ b/arch/x86/include/asm/debugreg.h @@ -18,6 +18,7 @@ #define DR_TRAP1 (0x2) /* db1 */ #define DR_TRAP2 (0x4) /* db2 */ #define DR_TRAP3 (0x8) /* db3 */ +#define DR_TRAP_BITS (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3) #define DR_STEP (0x4000) /* single-step */ #define DR_SWITCH (0x8000) /* task switch */ @@ -49,6 +50,8 @@ #define DR_LOCAL_ENABLE_SHIFT 0 /* Extra shift to the local enable bit */ #define DR_GLOBAL_ENABLE_SHIFT 1 /* Extra shift to the global enable bit */ +#define DR_LOCAL_ENABLE (0x1) /* Local enable for reg 0 */ +#define DR_GLOBAL_ENABLE (0x2) /* Global enable for reg 0 */ #define DR_ENABLE_SIZE 2 /* 2 enable bits per register */ #define DR_LOCAL_ENABLE_MASK (0x55) /* Set local bits for all 4 regs */ @@ -67,4 +70,34 @@ #define DR_LOCAL_SLOWDOWN (0x100) /* Local slow the pipeline */ #define DR_GLOBAL_SLOWDOWN (0x200) /* Global slow the pipeline */ +/* + * HW breakpoint additions + */ +#ifdef __KERNEL__ + +DECLARE_PER_CPU(unsigned long, cpu_dr7); + +static inline void hw_breakpoint_disable(void) +{ + /* Zero the control register for HW Breakpoint */ + set_debugreg(0UL, 7); + + /* Zero-out the individual HW breakpoint address registers */ + set_debugreg(0UL, 0); + set_debugreg(0UL, 1); + set_debugreg(0UL, 2); + set_debugreg(0UL, 3); +} + +static inline int hw_breakpoint_active(void) +{ + return __get_cpu_var(cpu_dr7) & DR_GLOBAL_ENABLE_MASK; +} + +extern void aout_dump_debugregs(struct user *dump); + +extern void hw_breakpoint_restore(void); + +#endif /* __KERNEL__ */ + #endif /* _ASM_X86_DEBUGREG_H */ diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h index cee34e9ca45b..029f230ab637 100644 --- a/arch/x86/include/asm/device.h +++ b/arch/x86/include/asm/device.h @@ -8,7 +8,7 @@ struct dev_archdata { #ifdef CONFIG_X86_64 struct dma_map_ops *dma_ops; #endif -#ifdef CONFIG_DMAR +#if defined(CONFIG_DMAR) || defined(CONFIG_AMD_IOMMU) void *iommu; /* hook for IOMMU specific extension */ #endif }; diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index 6a25d5d42836..0f6c02f3b7d4 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -20,7 +20,8 @@ # define ISA_DMA_BIT_MASK DMA_BIT_MASK(32) #endif -extern dma_addr_t bad_dma_address; +#define DMA_ERROR_CODE 0 + extern int iommu_merge; extern struct device x86_dma_fallback_dev; extern int panic_on_overflow; @@ -48,7 +49,7 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) if (ops->mapping_error) return ops->mapping_error(dev, dma_addr); - return (dma_addr == bad_dma_address); + return (dma_addr == DMA_ERROR_CODE); } #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f) diff --git a/arch/x86/include/asm/gart.h b/arch/x86/include/asm/gart.h index 6cfdafa409d8..4ac5b0f33fc1 100644 --- a/arch/x86/include/asm/gart.h +++ b/arch/x86/include/asm/gart.h @@ -35,8 +35,7 @@ extern int gart_iommu_aperture_allowed; extern int gart_iommu_aperture_disabled; extern void early_gart_iommu_check(void); -extern void gart_iommu_init(void); -extern void gart_iommu_shutdown(void); +extern int gart_iommu_init(void); extern void __init gart_parse_options(char *); extern void gart_iommu_hole_init(void); @@ -48,12 +47,6 @@ extern void gart_iommu_hole_init(void); static inline void early_gart_iommu_check(void) { } -static inline void gart_iommu_init(void) -{ -} -static inline void gart_iommu_shutdown(void) -{ -} static inline void gart_parse_options(char *options) { } diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index 82e3e8f01043..108eb6fd1ae7 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -20,11 +20,11 @@ typedef struct { unsigned int irq_call_count; unsigned int irq_tlb_count; #endif -#ifdef CONFIG_X86_MCE +#ifdef CONFIG_X86_THERMAL_VECTOR unsigned int irq_thermal_count; -# ifdef CONFIG_X86_MCE_THRESHOLD +#endif +#ifdef CONFIG_X86_MCE_THRESHOLD unsigned int irq_threshold_count; -# endif #endif } ____cacheline_aligned irq_cpustat_t; diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h new file mode 100644 index 000000000000..0675a7c4c20e --- /dev/null +++ b/arch/x86/include/asm/hw_breakpoint.h @@ -0,0 +1,73 @@ +#ifndef _I386_HW_BREAKPOINT_H +#define _I386_HW_BREAKPOINT_H + +#ifdef __KERNEL__ +#define __ARCH_HW_BREAKPOINT_H + +/* + * The name should probably be something dealt in + * a higher level. While dealing with the user + * (display/resolving) + */ +struct arch_hw_breakpoint { + char *name; /* Contains name of the symbol to set bkpt */ + unsigned long address; + u8 len; + u8 type; +}; + +#include <linux/kdebug.h> +#include <linux/percpu.h> +#include <linux/list.h> + +/* Available HW breakpoint length encodings */ +#define X86_BREAKPOINT_LEN_1 0x40 +#define X86_BREAKPOINT_LEN_2 0x44 +#define X86_BREAKPOINT_LEN_4 0x4c +#define X86_BREAKPOINT_LEN_EXECUTE 0x40 + +#ifdef CONFIG_X86_64 +#define X86_BREAKPOINT_LEN_8 0x48 +#endif + +/* Available HW breakpoint type encodings */ + +/* trigger on instruction execute */ +#define X86_BREAKPOINT_EXECUTE 0x80 +/* trigger on memory write */ +#define X86_BREAKPOINT_WRITE 0x81 +/* trigger on memory read or write */ +#define X86_BREAKPOINT_RW 0x83 + +/* Total number of available HW breakpoint registers */ +#define HBP_NUM 4 + +struct perf_event; +struct pmu; + +extern int arch_check_va_in_userspace(unsigned long va, u8 hbp_len); +extern int arch_validate_hwbkpt_settings(struct perf_event *bp, + struct task_struct *tsk); +extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused, + unsigned long val, void *data); + + +int arch_install_hw_breakpoint(struct perf_event *bp); +void arch_uninstall_hw_breakpoint(struct perf_event *bp); +void hw_breakpoint_pmu_read(struct perf_event *bp); +void hw_breakpoint_pmu_unthrottle(struct perf_event *bp); + +extern void +arch_fill_perf_breakpoint(struct perf_event *bp); + +unsigned long encode_dr7(int drnum, unsigned int len, unsigned int type); +int decode_dr7(unsigned long dr7, int bpnum, unsigned *len, unsigned *type); + +extern int arch_bp_generic_fields(int x86_len, int x86_type, + int *gen_len, int *gen_type); + +extern struct pmu perf_ops_bp; + +#endif /* __KERNEL__ */ +#endif /* _I386_HW_BREAKPOINT_H */ + diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index ba180d93b08c..6e124269fd4b 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -79,14 +79,32 @@ static inline void set_io_apic_irq_attr(struct io_apic_irq_attr *irq_attr, int ioapic, int ioapic_pin, int trigger, int polarity) { - irq_attr->ioapic = ioapic; - irq_attr->ioapic_pin = ioapic_pin; - irq_attr->trigger = trigger; - irq_attr->polarity = polarity; + irq_attr->ioapic = ioapic; + irq_attr->ioapic_pin = ioapic_pin; + irq_attr->trigger = trigger; + irq_attr->polarity = polarity; } -extern int IO_APIC_get_PCI_irq_vector(int bus, int devfn, int pin, - struct io_apic_irq_attr *irq_attr); +/* + * This is performance-critical, we want to do it O(1) + * + * Most irqs are mapped 1:1 with pins. + */ +struct irq_cfg { + struct irq_pin_list *irq_2_pin; + cpumask_var_t domain; + cpumask_var_t old_domain; + u8 vector; + u8 move_in_progress : 1; +}; + +extern struct irq_cfg *irq_cfg(unsigned int); +extern int assign_irq_vector(int, struct irq_cfg *, const struct cpumask *); +extern void send_cleanup_vector(struct irq_cfg *); + +struct irq_desc; +extern unsigned int set_desc_affinity(struct irq_desc *, const struct cpumask *); +extern int IO_APIC_get_PCI_irq_vector(int bus, int devfn, int pin, struct io_apic_irq_attr *irq_attr); extern void setup_ioapic_dest(void); extern void enable_IO_APIC(void); diff --git a/arch/x86/include/asm/inat.h b/arch/x86/include/asm/inat.h new file mode 100644 index 000000000000..205b063e3e32 --- /dev/null +++ b/arch/x86/include/asm/inat.h @@ -0,0 +1,220 @@ +#ifndef _ASM_X86_INAT_H +#define _ASM_X86_INAT_H +/* + * x86 instruction attributes + * + * Written by Masami Hiramatsu <mhiramat@redhat.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + */ +#include <asm/inat_types.h> + +/* + * Internal bits. Don't use bitmasks directly, because these bits are + * unstable. You should use checking functions. + */ + +#define INAT_OPCODE_TABLE_SIZE 256 +#define INAT_GROUP_TABLE_SIZE 8 + +/* Legacy last prefixes */ +#define INAT_PFX_OPNDSZ 1 /* 0x66 */ /* LPFX1 */ +#define INAT_PFX_REPE 2 /* 0xF3 */ /* LPFX2 */ +#define INAT_PFX_REPNE 3 /* 0xF2 */ /* LPFX3 */ +/* Other Legacy prefixes */ +#define INAT_PFX_LOCK 4 /* 0xF0 */ +#define INAT_PFX_CS 5 /* 0x2E */ +#define INAT_PFX_DS 6 /* 0x3E */ +#define INAT_PFX_ES 7 /* 0x26 */ +#define INAT_PFX_FS 8 /* 0x64 */ +#define INAT_PFX_GS 9 /* 0x65 */ +#define INAT_PFX_SS 10 /* 0x36 */ +#define INAT_PFX_ADDRSZ 11 /* 0x67 */ +/* x86-64 REX prefix */ +#define INAT_PFX_REX 12 /* 0x4X */ +/* AVX VEX prefixes */ +#define INAT_PFX_VEX2 13 /* 2-bytes VEX prefix */ +#define INAT_PFX_VEX3 14 /* 3-bytes VEX prefix */ + +#define INAT_LSTPFX_MAX 3 +#define INAT_LGCPFX_MAX 11 + +/* Immediate size */ +#define INAT_IMM_BYTE 1 +#define INAT_IMM_WORD 2 +#define INAT_IMM_DWORD 3 +#define INAT_IMM_QWORD 4 +#define INAT_IMM_PTR 5 +#define INAT_IMM_VWORD32 6 +#define INAT_IMM_VWORD 7 + +/* Legacy prefix */ +#define INAT_PFX_OFFS 0 +#define INAT_PFX_BITS 4 +#define INAT_PFX_MAX ((1 << INAT_PFX_BITS) - 1) +#define INAT_PFX_MASK (INAT_PFX_MAX << INAT_PFX_OFFS) +/* Escape opcodes */ +#define INAT_ESC_OFFS (INAT_PFX_OFFS + INAT_PFX_BITS) +#define INAT_ESC_BITS 2 +#define INAT_ESC_MAX ((1 << INAT_ESC_BITS) - 1) +#define INAT_ESC_MASK (INAT_ESC_MAX << INAT_ESC_OFFS) +/* Group opcodes (1-16) */ +#define INAT_GRP_OFFS (INAT_ESC_OFFS + INAT_ESC_BITS) +#define INAT_GRP_BITS 5 +#define INAT_GRP_MAX ((1 << INAT_GRP_BITS) - 1) +#define INAT_GRP_MASK (INAT_GRP_MAX << INAT_GRP_OFFS) +/* Immediates */ +#define INAT_IMM_OFFS (INAT_GRP_OFFS + INAT_GRP_BITS) +#define INAT_IMM_BITS 3 +#define INAT_IMM_MASK (((1 << INAT_IMM_BITS) - 1) << INAT_IMM_OFFS) +/* Flags */ +#define INAT_FLAG_OFFS (INAT_IMM_OFFS + INAT_IMM_BITS) +#define INAT_MODRM (1 << (INAT_FLAG_OFFS)) +#define INAT_FORCE64 (1 << (INAT_FLAG_OFFS + 1)) +#define INAT_SCNDIMM (1 << (INAT_FLAG_OFFS + 2)) +#define INAT_MOFFSET (1 << (INAT_FLAG_OFFS + 3)) +#define INAT_VARIANT (1 << (INAT_FLAG_OFFS + 4)) +#define INAT_VEXOK (1 << (INAT_FLAG_OFFS + 5)) +#define INAT_VEXONLY (1 << (INAT_FLAG_OFFS + 6)) +/* Attribute making macros for attribute tables */ +#define INAT_MAKE_PREFIX(pfx) (pfx << INAT_PFX_OFFS) +#define INAT_MAKE_ESCAPE(esc) (esc << INAT_ESC_OFFS) +#define INAT_MAKE_GROUP(grp) ((grp << INAT_GRP_OFFS) | INAT_MODRM) +#define INAT_MAKE_IMM(imm) (imm << INAT_IMM_OFFS) + +/* Attribute search APIs */ +extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode); +extern insn_attr_t inat_get_escape_attribute(insn_byte_t opcode, + insn_byte_t last_pfx, + insn_attr_t esc_attr); +extern insn_attr_t inat_get_group_attribute(insn_byte_t modrm, + insn_byte_t last_pfx, + insn_attr_t esc_attr); +extern insn_attr_t inat_get_avx_attribute(insn_byte_t opcode, + insn_byte_t vex_m, + insn_byte_t vex_pp); + +/* Attribute checking functions */ +static inline int inat_is_legacy_prefix(insn_attr_t attr) +{ + attr &= INAT_PFX_MASK; + return attr && attr <= INAT_LGCPFX_MAX; +} + +static inline int inat_is_address_size_prefix(insn_attr_t attr) +{ + return (attr & INAT_PFX_MASK) == INAT_PFX_ADDRSZ; +} + +static inline int inat_is_operand_size_prefix(insn_attr_t attr) +{ + return (attr & INAT_PFX_MASK) == INAT_PFX_OPNDSZ; +} + +static inline int inat_is_rex_prefix(insn_attr_t attr) +{ + return (attr & INAT_PFX_MASK) == INAT_PFX_REX; +} + +static inline int inat_last_prefix_id(insn_attr_t attr) +{ + if ((attr & INAT_PFX_MASK) > INAT_LSTPFX_MAX) + return 0; + else + return attr & INAT_PFX_MASK; +} + +static inline int inat_is_vex_prefix(insn_attr_t attr) +{ + attr &= INAT_PFX_MASK; + return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3; +} + +static inline int inat_is_vex3_prefix(insn_attr_t attr) +{ + return (attr & INAT_PFX_MASK) == INAT_PFX_VEX3; +} + +static inline int inat_is_escape(insn_attr_t attr) +{ + return attr & INAT_ESC_MASK; +} + +static inline int inat_escape_id(insn_attr_t attr) +{ + return (attr & INAT_ESC_MASK) >> INAT_ESC_OFFS; +} + +static inline int inat_is_group(insn_attr_t attr) +{ + return attr & INAT_GRP_MASK; +} + +static inline int inat_group_id(insn_attr_t attr) +{ + return (attr & INAT_GRP_MASK) >> INAT_GRP_OFFS; +} + +static inline int inat_group_common_attribute(insn_attr_t attr) +{ + return attr & ~INAT_GRP_MASK; +} + +static inline int inat_has_immediate(insn_attr_t attr) +{ + return attr & INAT_IMM_MASK; +} + +static inline int inat_immediate_size(insn_attr_t attr) +{ + return (attr & INAT_IMM_MASK) >> INAT_IMM_OFFS; +} + +static inline int inat_has_modrm(insn_attr_t attr) +{ + return attr & INAT_MODRM; +} + +static inline int inat_is_force64(insn_attr_t attr) +{ + return attr & INAT_FORCE64; +} + +static inline int inat_has_second_immediate(insn_attr_t attr) +{ + return attr & INAT_SCNDIMM; +} + +static inline int inat_has_moffset(insn_attr_t attr) +{ + return attr & INAT_MOFFSET; +} + +static inline int inat_has_variant(insn_attr_t attr) +{ + return attr & INAT_VARIANT; +} + +static inline int inat_accept_vex(insn_attr_t attr) +{ + return attr & INAT_VEXOK; +} + +static inline int inat_must_vex(insn_attr_t attr) +{ + return attr & INAT_VEXONLY; +} +#endif diff --git a/arch/x86/include/asm/inat_types.h b/arch/x86/include/asm/inat_types.h new file mode 100644 index 000000000000..cb3c20ce39cf --- /dev/null +++ b/arch/x86/include/asm/inat_types.h @@ -0,0 +1,29 @@ +#ifndef _ASM_X86_INAT_TYPES_H +#define _ASM_X86_INAT_TYPES_H +/* + * x86 instruction attributes + * + * Written by Masami Hiramatsu <mhiramat@redhat.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + */ + +/* Instruction attributes */ +typedef unsigned int insn_attr_t; +typedef unsigned char insn_byte_t; +typedef signed int insn_value_t; + +#endif diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h new file mode 100644 index 000000000000..96c2e0ad04ca --- /dev/null +++ b/arch/x86/include/asm/insn.h @@ -0,0 +1,184 @@ +#ifndef _ASM_X86_INSN_H +#define _ASM_X86_INSN_H +/* + * x86 instruction analysis + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) IBM Corporation, 2009 + */ + +/* insn_attr_t is defined in inat.h */ +#include <asm/inat.h> + +struct insn_field { + union { + insn_value_t value; + insn_byte_t bytes[4]; + }; + /* !0 if we've run insn_get_xxx() for this field */ + unsigned char got; + unsigned char nbytes; +}; + +struct insn { + struct insn_field prefixes; /* + * Prefixes + * prefixes.bytes[3]: last prefix + */ + struct insn_field rex_prefix; /* REX prefix */ + struct insn_field vex_prefix; /* VEX prefix */ + struct insn_field opcode; /* + * opcode.bytes[0]: opcode1 + * opcode.bytes[1]: opcode2 + * opcode.bytes[2]: opcode3 + */ + struct insn_field modrm; + struct insn_field sib; + struct insn_field displacement; + union { + struct insn_field immediate; + struct insn_field moffset1; /* for 64bit MOV */ + struct insn_field immediate1; /* for 64bit imm or off16/32 */ + }; + union { + struct insn_field moffset2; /* for 64bit MOV */ + struct insn_field immediate2; /* for 64bit imm or seg16 */ + }; + + insn_attr_t attr; + unsigned char opnd_bytes; + unsigned char addr_bytes; + unsigned char length; + unsigned char x86_64; + + const insn_byte_t *kaddr; /* kernel address of insn to analyze */ + const insn_byte_t *next_byte; +}; + +#define X86_MODRM_MOD(modrm) (((modrm) & 0xc0) >> 6) +#define X86_MODRM_REG(modrm) (((modrm) & 0x38) >> 3) +#define X86_MODRM_RM(modrm) ((modrm) & 0x07) + +#define X86_SIB_SCALE(sib) (((sib) & 0xc0) >> 6) +#define X86_SIB_INDEX(sib) (((sib) & 0x38) >> 3) +#define X86_SIB_BASE(sib) ((sib) & 0x07) + +#define X86_REX_W(rex) ((rex) & 8) +#define X86_REX_R(rex) ((rex) & 4) +#define X86_REX_X(rex) ((rex) & 2) +#define X86_REX_B(rex) ((rex) & 1) + +/* VEX bit flags */ +#define X86_VEX_W(vex) ((vex) & 0x80) /* VEX3 Byte2 */ +#define X86_VEX_R(vex) ((vex) & 0x80) /* VEX2/3 Byte1 */ +#define X86_VEX_X(vex) ((vex) & 0x40) /* VEX3 Byte1 */ +#define X86_VEX_B(vex) ((vex) & 0x20) /* VEX3 Byte1 */ +#define X86_VEX_L(vex) ((vex) & 0x04) /* VEX3 Byte2, VEX2 Byte1 */ +/* VEX bit fields */ +#define X86_VEX3_M(vex) ((vex) & 0x1f) /* VEX3 Byte1 */ +#define X86_VEX2_M 1 /* VEX2.M always 1 */ +#define X86_VEX_V(vex) (((vex) & 0x78) >> 3) /* VEX3 Byte2, VEX2 Byte1 */ +#define X86_VEX_P(vex) ((vex) & 0x03) /* VEX3 Byte2, VEX2 Byte1 */ +#define X86_VEX_M_MAX 0x1f /* VEX3.M Maximum value */ + +/* The last prefix is needed for two-byte and three-byte opcodes */ +static inline insn_byte_t insn_last_prefix(struct insn *insn) +{ + return insn->prefixes.bytes[3]; +} + +extern void insn_init(struct insn *insn, const void *kaddr, int x86_64); +extern void insn_get_prefixes(struct insn *insn); +extern void insn_get_opcode(struct insn *insn); +extern void insn_get_modrm(struct insn *insn); +extern void insn_get_sib(struct insn *insn); +extern void insn_get_displacement(struct insn *insn); +extern void insn_get_immediate(struct insn *insn); +extern void insn_get_length(struct insn *insn); + +/* Attribute will be determined after getting ModRM (for opcode groups) */ +static inline void insn_get_attribute(struct insn *insn) +{ + insn_get_modrm(insn); +} + +/* Instruction uses RIP-relative addressing */ +extern int insn_rip_relative(struct insn *insn); + +/* Init insn for kernel text */ +static inline void kernel_insn_init(struct insn *insn, const void *kaddr) +{ +#ifdef CONFIG_X86_64 + insn_init(insn, kaddr, 1); +#else /* CONFIG_X86_32 */ + insn_init(insn, kaddr, 0); +#endif +} + +static inline int insn_is_avx(struct insn *insn) +{ + if (!insn->prefixes.got) + insn_get_prefixes(insn); + return (insn->vex_prefix.value != 0); +} + +static inline insn_byte_t insn_vex_m_bits(struct insn *insn) +{ + if (insn->vex_prefix.nbytes == 2) /* 2 bytes VEX */ + return X86_VEX2_M; + else + return X86_VEX3_M(insn->vex_prefix.bytes[1]); +} + +static inline insn_byte_t insn_vex_p_bits(struct insn *insn) +{ + if (insn->vex_prefix.nbytes == 2) /* 2 bytes VEX */ + return X86_VEX_P(insn->vex_prefix.bytes[1]); + else + return X86_VEX_P(insn->vex_prefix.bytes[2]); +} + +/* Offset of each field from kaddr */ +static inline int insn_offset_rex_prefix(struct insn *insn) +{ + return insn->prefixes.nbytes; +} +static inline int insn_offset_vex_prefix(struct insn *insn) +{ + return insn_offset_rex_prefix(insn) + insn->rex_prefix.nbytes; +} +static inline int insn_offset_opcode(struct insn *insn) +{ + return insn_offset_vex_prefix(insn) + insn->vex_prefix.nbytes; +} +static inline int insn_offset_modrm(struct insn *insn) +{ + return insn_offset_opcode(insn) + insn->opcode.nbytes; +} +static inline int insn_offset_sib(struct insn *insn) +{ + return insn_offset_modrm(insn) + insn->modrm.nbytes; +} +static inline int insn_offset_displacement(struct insn *insn) +{ + return insn_offset_sib(insn) + insn->sib.nbytes; +} +static inline int insn_offset_immediate(struct insn *insn) +{ + return insn_offset_displacement(insn) + insn->displacement.nbytes; +} + +#endif /* _ASM_X86_INSN_H */ diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h index fd6d21bbee6c..345c99cef152 100644 --- a/arch/x86/include/asm/iommu.h +++ b/arch/x86/include/asm/iommu.h @@ -1,8 +1,6 @@ #ifndef _ASM_X86_IOMMU_H #define _ASM_X86_IOMMU_H -extern void pci_iommu_shutdown(void); -extern void no_iommu_init(void); extern struct dma_map_ops nommu_dma_ops; extern int force_iommu, no_iommu; extern int iommu_detected; diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index ddda6cbed6f4..ffd700ff5dcb 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -34,6 +34,7 @@ static inline int irq_canonicalize(int irq) #ifdef CONFIG_HOTPLUG_CPU #include <linux/cpumask.h> extern void fixup_irqs(void); +extern void irq_force_complete_move(int); #endif extern void (*generic_interrupt_extension)(void); diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index f1363b72364f..858baa061cfc 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -108,6 +108,8 @@ struct mce_log { #define K8_MCE_THRESHOLD_BANK_5 (MCE_THRESHOLD_BASE + 5 * 9) #define K8_MCE_THRESHOLD_DRAM_ECC (MCE_THRESHOLD_BANK_4 + 0) +extern struct atomic_notifier_head x86_mce_decoder_chain; + #ifdef __KERNEL__ #include <linux/percpu.h> @@ -118,9 +120,11 @@ extern int mce_disabled; extern int mce_p5_enabled; #ifdef CONFIG_X86_MCE -void mcheck_init(struct cpuinfo_x86 *c); +int mcheck_init(void); +void mcheck_cpu_init(struct cpuinfo_x86 *c); #else -static inline void mcheck_init(struct cpuinfo_x86 *c) {} +static inline int mcheck_init(void) { return 0; } +static inline void mcheck_cpu_init(struct cpuinfo_x86 *c) {} #endif #ifdef CONFIG_X86_ANCIENT_MCE @@ -214,5 +218,11 @@ void intel_init_thermal(struct cpuinfo_x86 *c); void mce_log_therm_throt_event(__u64 status); +#ifdef CONFIG_X86_THERMAL_VECTOR +extern void mcheck_intel_therm_init(void); +#else +static inline void mcheck_intel_therm_init(void) { } +#endif + #endif /* __KERNEL__ */ #endif /* _ASM_X86_MCE_H */ diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h index 79c94500c0bb..61d90b1331c3 100644 --- a/arch/x86/include/asm/mpspec.h +++ b/arch/x86/include/asm/mpspec.h @@ -163,14 +163,16 @@ typedef struct physid_mask physid_mask_t; #define physids_shift_left(d, s, n) \ bitmap_shift_left((d).mask, (s).mask, n, MAX_APICS) -#define physids_coerce(map) ((map).mask[0]) +static inline unsigned long physids_coerce(physid_mask_t *map) +{ + return map->mask[0]; +} -#define physids_promote(physids) \ - ({ \ - physid_mask_t __physid_mask = PHYSID_MASK_NONE; \ - __physid_mask.mask[0] = physids; \ - __physid_mask; \ - }) +static inline void physids_promote(unsigned long physids, physid_mask_t *map) +{ + physids_clear(*map); + map->mask[0] = physids; +} /* Note: will create very large stack frames if physid_mask_t is big */ #define physid_mask_of_physid(physid) \ diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 7e2b6ba962ff..5bef931f8b14 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -247,8 +247,8 @@ do { \ #ifdef CONFIG_SMP int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h); int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h); -void rdmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs); -void wrmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs); +void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs); +void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs); int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h); int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h); int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]); @@ -264,12 +264,12 @@ static inline int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) wrmsr(msr_no, l, h); return 0; } -static inline void rdmsr_on_cpus(const cpumask_t *m, u32 msr_no, +static inline void rdmsr_on_cpus(const struct cpumask *m, u32 msr_no, struct msr *msrs) { rdmsr_on_cpu(0, msr_no, &(msrs[0].l), &(msrs[0].h)); } -static inline void wrmsr_on_cpus(const cpumask_t *m, u32 msr_no, +static inline void wrmsr_on_cpus(const struct cpumask *m, u32 msr_no, struct msr *msrs) { wrmsr_on_cpu(0, msr_no, msrs[0].l, msrs[0].h); diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index ad7ce3fd5065..8d9f8548a870 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -28,9 +28,20 @@ */ #define ARCH_PERFMON_EVENT_MASK 0xffff +/* + * filter mask to validate fixed counter events. + * the following filters disqualify for fixed counters: + * - inv + * - edge + * - cnt-mask + * The other filters are supported by fixed counters. + * The any-thread option is supported starting with v3. + */ +#define ARCH_PERFMON_EVENT_FILTER_MASK 0xff840000 + #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL 0x3c #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK (0x00 << 8) -#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX 0 +#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX 0 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT \ (1 << (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX)) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index c9786480f0fe..6f8ec1c37e0a 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -30,6 +30,7 @@ struct mm_struct; #include <linux/math64.h> #include <linux/init.h> +#define HBP_NUM 4 /* * Default implementation of macro that returns current * instruction pointer ("program counter"). @@ -422,6 +423,8 @@ extern unsigned int xstate_size; extern void free_thread_xstate(struct task_struct *); extern struct kmem_cache *task_xstate_cachep; +struct perf_event; + struct thread_struct { /* Cached TLS descriptors: */ struct desc_struct tls_array[GDT_ENTRY_TLS_ENTRIES]; @@ -443,13 +446,10 @@ struct thread_struct { unsigned long fs; #endif unsigned long gs; - /* Hardware debugging registers: */ - unsigned long debugreg0; - unsigned long debugreg1; - unsigned long debugreg2; - unsigned long debugreg3; - unsigned long debugreg6; - unsigned long debugreg7; + /* Save middle states of ptrace breakpoints */ + struct perf_event *ptrace_bps[HBP_NUM]; + /* Debug status used for traps, single steps, etc... */ + unsigned long debugreg6; /* Fault info: */ unsigned long cr2; unsigned long trap_no; diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 0f0d908349aa..3d11fd0f44c5 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -7,6 +7,7 @@ #ifdef __KERNEL__ #include <asm/segment.h> +#include <asm/page_types.h> #endif #ifndef __ASSEMBLY__ @@ -216,6 +217,67 @@ static inline unsigned long user_stack_pointer(struct pt_regs *regs) return regs->sp; } +/* Query offset/name of register from its name/offset */ +extern int regs_query_register_offset(const char *name); +extern const char *regs_query_register_name(unsigned int offset); +#define MAX_REG_OFFSET (offsetof(struct pt_regs, ss)) + +/** + * regs_get_register() - get register value from its offset + * @regs: pt_regs from which register value is gotten. + * @offset: offset number of the register. + * + * regs_get_register returns the value of a register. The @offset is the + * offset of the register in struct pt_regs address which specified by @regs. + * If @offset is bigger than MAX_REG_OFFSET, this returns 0. + */ +static inline unsigned long regs_get_register(struct pt_regs *regs, + unsigned int offset) +{ + if (unlikely(offset > MAX_REG_OFFSET)) + return 0; + return *(unsigned long *)((unsigned long)regs + offset); +} + +/** + * regs_within_kernel_stack() - check the address in the stack + * @regs: pt_regs which contains kernel stack pointer. + * @addr: address which is checked. + * + * regs_within_kernel_stack() checks @addr is within the kernel stack page(s). + * If @addr is within the kernel stack, it returns true. If not, returns false. + */ +static inline int regs_within_kernel_stack(struct pt_regs *regs, + unsigned long addr) +{ + return ((addr & ~(THREAD_SIZE - 1)) == + (kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1))); +} + +/** + * regs_get_kernel_stack_nth() - get Nth entry of the stack + * @regs: pt_regs which contains kernel stack pointer. + * @n: stack entry number. + * + * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which + * is specified by @regs. If the @n th entry is NOT in the kernel stack, + * this returns 0. + */ +static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, + unsigned int n) +{ + unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs); + addr += n; + if (regs_within_kernel_stack(regs, (unsigned long)addr)) + return *addr; + else + return 0; +} + +/* Get Nth argument at function call */ +extern unsigned long regs_get_argument_nth(struct pt_regs *regs, + unsigned int n); + /* * These are defined as per linux/ptrace.h, which see. */ diff --git a/arch/x86/include/asm/string_32.h b/arch/x86/include/asm/string_32.h index ae907e617181..3d3e8353ee5c 100644 --- a/arch/x86/include/asm/string_32.h +++ b/arch/x86/include/asm/string_32.h @@ -177,10 +177,15 @@ static inline void *__memcpy3d(void *to, const void *from, size_t len) */ #ifndef CONFIG_KMEMCHECK + +#if (__GNUC__ >= 4) +#define memcpy(t, f, n) __builtin_memcpy(t, f, n) +#else #define memcpy(t, f, n) \ (__builtin_constant_p((n)) \ ? __constant_memcpy((t), (f), (n)) \ : __memcpy((t), (f), (n))) +#endif #else /* * kmemcheck becomes very happy if we use the REP instructions unconditionally, @@ -316,11 +321,15 @@ void *__constant_c_and_count_memset(void *s, unsigned long pattern, : __memset_generic((s), (c), (count))) #define __HAVE_ARCH_MEMSET +#if (__GNUC__ >= 4) +#define memset(s, c, count) __builtin_memset(s, c, count) +#else #define memset(s, c, count) \ (__builtin_constant_p(c) \ ? __constant_c_x_memset((s), (0x01010101UL * (unsigned char)(c)), \ (count)) \ : __memset((s), (c), (count))) +#endif /* * find the first occurrence of byte 'c', or 1 past the area if none diff --git a/arch/x86/include/asm/swiotlb.h b/arch/x86/include/asm/swiotlb.h index b9e4e20174fb..87ffcb12a1b8 100644 --- a/arch/x86/include/asm/swiotlb.h +++ b/arch/x86/include/asm/swiotlb.h @@ -3,17 +3,14 @@ #include <linux/swiotlb.h> -/* SWIOTLB interface */ - -extern int swiotlb_force; - #ifdef CONFIG_SWIOTLB extern int swiotlb; -extern void pci_swiotlb_init(void); +extern int pci_swiotlb_init(void); #else #define swiotlb 0 -static inline void pci_swiotlb_init(void) +static inline int pci_swiotlb_init(void) { + return 0; } #endif diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h index 72a6dcd1299b..9af9decb38c3 100644 --- a/arch/x86/include/asm/sys_ia32.h +++ b/arch/x86/include/asm/sys_ia32.h @@ -51,11 +51,6 @@ asmlinkage long sys32_sched_rr_get_interval(compat_pid_t, asmlinkage long sys32_rt_sigpending(compat_sigset_t __user *, compat_size_t); asmlinkage long sys32_rt_sigqueueinfo(int, int, compat_siginfo_t __user *); -#ifdef CONFIG_SYSCTL_SYSCALL -struct sysctl_ia32; -asmlinkage long sys32_sysctl(struct sysctl_ia32 __user *); -#endif - asmlinkage long sys32_pread(unsigned int, char __user *, u32, u32, u32); asmlinkage long sys32_pwrite(unsigned int, char __user *, u32, u32, u32); diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h index f08f97374892..022a84386de8 100644 --- a/arch/x86/include/asm/system.h +++ b/arch/x86/include/asm/system.h @@ -128,8 +128,6 @@ do { \ "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */ \ "movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */ \ "call __switch_to\n\t" \ - ".globl thread_return\n" \ - "thread_return:\n\t" \ "movq "__percpu_arg([current_task])",%%rsi\n\t" \ __switch_canary \ "movq %P[thread_info](%%rsi),%%r8\n\t" \ @@ -157,19 +155,22 @@ extern void native_load_gs_index(unsigned); * Load a segment. Fall back on loading the zero * segment if something goes wrong.. */ -#define loadsegment(seg, value) \ - asm volatile("\n" \ - "1:\t" \ - "movl %k0,%%" #seg "\n" \ - "2:\n" \ - ".section .fixup,\"ax\"\n" \ - "3:\t" \ - "movl %k1, %%" #seg "\n\t" \ - "jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE(1b,3b) \ - : :"r" (value), "r" (0) : "memory") - +#define loadsegment(seg, value) \ +do { \ + unsigned short __val = (value); \ + \ + asm volatile(" \n" \ + "1: movl %k0,%%" #seg " \n" \ + \ + ".section .fixup,\"ax\" \n" \ + "2: xorl %k0,%k0 \n" \ + " jmp 1b \n" \ + ".previous \n" \ + \ + _ASM_EXTABLE(1b, 2b) \ + \ + : "+r" (__val) : : "memory"); \ +} while (0) /* * Save a segment register away diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index d2c6c930b491..abd3e0ea762a 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -570,7 +570,6 @@ extern struct movsl_mask { #ifdef CONFIG_X86_32 # include "uaccess_32.h" #else -# define ARCH_HAS_SEARCH_EXTABLE # include "uaccess_64.h" #endif diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h index 632fb44b4cb5..0c9825e97f36 100644 --- a/arch/x86/include/asm/uaccess_32.h +++ b/arch/x86/include/asm/uaccess_32.h @@ -187,9 +187,34 @@ __copy_from_user_inatomic_nocache(void *to, const void __user *from, unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n); -unsigned long __must_check copy_from_user(void *to, +unsigned long __must_check _copy_from_user(void *to, const void __user *from, unsigned long n); + + +extern void copy_from_user_overflow(void) +#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS + __compiletime_error("copy_from_user() buffer size is not provably correct") +#else + __compiletime_warning("copy_from_user() buffer size is not provably correct") +#endif +; + +static inline unsigned long __must_check copy_from_user(void *to, + const void __user *from, + unsigned long n) +{ + int sz = __compiletime_object_size(to); + int ret = -EFAULT; + + if (likely(sz == -1 || sz >= n)) + ret = _copy_from_user(to, from, n); + else + copy_from_user_overflow(); + + return ret; +} + long __must_check strncpy_from_user(char *dst, const char __user *src, long count); long __must_check __strncpy_from_user(char *dst, diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index db24b215fc50..46324c6a4f6e 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -19,12 +19,37 @@ __must_check unsigned long copy_user_generic(void *to, const void *from, unsigned len); __must_check unsigned long -copy_to_user(void __user *to, const void *from, unsigned len); +_copy_to_user(void __user *to, const void *from, unsigned len); __must_check unsigned long -copy_from_user(void *to, const void __user *from, unsigned len); +_copy_from_user(void *to, const void __user *from, unsigned len); __must_check unsigned long copy_in_user(void __user *to, const void __user *from, unsigned len); +static inline unsigned long __must_check copy_from_user(void *to, + const void __user *from, + unsigned long n) +{ + int sz = __compiletime_object_size(to); + int ret = -EFAULT; + + might_fault(); + if (likely(sz == -1 || sz >= n)) + ret = _copy_from_user(to, from, n); +#ifdef CONFIG_DEBUG_VM + else + WARN(1, "Buffer overflow detected!\n"); +#endif + return ret; +} + +static __always_inline __must_check +int copy_to_user(void __user *dst, const void *src, unsigned size) +{ + might_fault(); + + return _copy_to_user(dst, src, size); +} + static __always_inline __must_check int __copy_from_user(void *dst, const void __user *src, unsigned size) { @@ -176,8 +201,11 @@ __must_check long strlen_user(const char __user *str); __must_check unsigned long clear_user(void __user *mem, unsigned long len); __must_check unsigned long __clear_user(void __user *mem, unsigned long len); -__must_check long __copy_from_user_inatomic(void *dst, const void __user *src, - unsigned size); +static __must_check __always_inline int +__copy_from_user_inatomic(void *dst, const void __user *src, unsigned size) +{ + return copy_user_generic(dst, (__force const void *)src, size); +} static __must_check __always_inline int __copy_to_user_inatomic(void __user *dst, const void *src, unsigned size) diff --git a/arch/x86/include/asm/uv/uv_irq.h b/arch/x86/include/asm/uv/uv_irq.h index 9613c8c0b647..d6b17c760622 100644 --- a/arch/x86/include/asm/uv/uv_irq.h +++ b/arch/x86/include/asm/uv/uv_irq.h @@ -25,12 +25,14 @@ struct uv_IO_APIC_route_entry { dest : 32; }; -extern struct irq_chip uv_irq_chip; - -extern int arch_enable_uv_irq(char *, unsigned int, int, int, unsigned long); -extern void arch_disable_uv_irq(int, unsigned long); +enum { + UV_AFFINITY_ALL, + UV_AFFINITY_NODE, + UV_AFFINITY_CPU +}; -extern int uv_setup_irq(char *, int, int, unsigned long); -extern void uv_teardown_irq(unsigned int, int, unsigned long); +extern int uv_irq_2_mmr_info(int, unsigned long *, int *); +extern int uv_setup_irq(char *, int, int, unsigned long, int); +extern void uv_teardown_irq(unsigned int); #endif /* _ASM_X86_UV_UV_IRQ_H */ diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 2c756fd4ab0e..d8e71459f025 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -91,6 +91,14 @@ struct x86_init_timers { }; /** + * struct x86_init_iommu - platform specific iommu setup + * @iommu_init: platform specific iommu setup + */ +struct x86_init_iommu { + int (*iommu_init)(void); +}; + +/** * struct x86_init_ops - functions for platform specific setup * */ @@ -101,6 +109,7 @@ struct x86_init_ops { struct x86_init_oem oem; struct x86_init_paging paging; struct x86_init_timers timers; + struct x86_init_iommu iommu; }; /** @@ -121,6 +130,7 @@ struct x86_platform_ops { unsigned long (*calibrate_tsc)(void); unsigned long (*get_wallclock)(void); int (*set_wallclock)(unsigned long nowtime); + void (*iommu_shutdown)(void); }; extern struct x86_init_ops x86_init; diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index d8e5d0cdd678..4f2e66e29ecc 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -40,7 +40,7 @@ obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o obj-$(CONFIG_X86_64) += syscall_64.o vsyscall_64.o obj-y += bootflag.o e820.o obj-y += pci-dma.o quirks.o i8237.o topology.o kdebugfs.o -obj-y += alternative.o i8253.o pci-nommu.o +obj-y += alternative.o i8253.o pci-nommu.o hw_breakpoint.o obj-y += tsc.o io_delay.o rtc.o obj-$(CONFIG_X86_TRAMPOLINE) += trampoline.o diff --git a/arch/x86/kernel/acpi/processor.c b/arch/x86/kernel/acpi/processor.c index d296f4a195c9..d85d1b2432ba 100644 --- a/arch/x86/kernel/acpi/processor.c +++ b/arch/x86/kernel/acpi/processor.c @@ -79,7 +79,8 @@ void arch_acpi_processor_init_pdc(struct acpi_processor *pr) struct cpuinfo_x86 *c = &cpu_data(pr->id); pr->pdc = NULL; - if (c->x86_vendor == X86_VENDOR_INTEL) + if (c->x86_vendor == X86_VENDOR_INTEL || + c->x86_vendor == X86_VENDOR_CENTAUR) init_intel_pdc(pr, c); return; diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index 0285521e0a99..32fb09102a13 100644 --- a/arch/x86/kernel/amd_iommu.c +++ b/arch/x86/kernel/amd_iommu.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2008 Advanced Micro Devices, Inc. + * Copyright (C) 2007-2009 Advanced Micro Devices, Inc. * Author: Joerg Roedel <joerg.roedel@amd.com> * Leo Duran <leo.duran@amd.com> * @@ -28,6 +28,7 @@ #include <asm/proto.h> #include <asm/iommu.h> #include <asm/gart.h> +#include <asm/amd_iommu_proto.h> #include <asm/amd_iommu_types.h> #include <asm/amd_iommu.h> @@ -56,20 +57,115 @@ struct iommu_cmd { u32 data[4]; }; -static int dma_ops_unity_map(struct dma_ops_domain *dma_dom, - struct unity_map_entry *e); -static struct dma_ops_domain *find_protection_domain(u16 devid); -static u64 *alloc_pte(struct protection_domain *domain, - unsigned long address, int end_lvl, - u64 **pte_page, gfp_t gfp); -static void dma_ops_reserve_addresses(struct dma_ops_domain *dom, - unsigned long start_page, - unsigned int pages); static void reset_iommu_command_buffer(struct amd_iommu *iommu); -static u64 *fetch_pte(struct protection_domain *domain, - unsigned long address, int map_size); static void update_domain(struct protection_domain *domain); +/**************************************************************************** + * + * Helper functions + * + ****************************************************************************/ + +static inline u16 get_device_id(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + + return calc_devid(pdev->bus->number, pdev->devfn); +} + +static struct iommu_dev_data *get_dev_data(struct device *dev) +{ + return dev->archdata.iommu; +} + +/* + * In this function the list of preallocated protection domains is traversed to + * find the domain for a specific device + */ +static struct dma_ops_domain *find_protection_domain(u16 devid) +{ + struct dma_ops_domain *entry, *ret = NULL; + unsigned long flags; + u16 alias = amd_iommu_alias_table[devid]; + + if (list_empty(&iommu_pd_list)) + return NULL; + + spin_lock_irqsave(&iommu_pd_list_lock, flags); + + list_for_each_entry(entry, &iommu_pd_list, list) { + if (entry->target_dev == devid || + entry->target_dev == alias) { + ret = entry; + break; + } + } + + spin_unlock_irqrestore(&iommu_pd_list_lock, flags); + + return ret; +} + +/* + * This function checks if the driver got a valid device from the caller to + * avoid dereferencing invalid pointers. + */ +static bool check_device(struct device *dev) +{ + u16 devid; + + if (!dev || !dev->dma_mask) + return false; + + /* No device or no PCI device */ + if (!dev || dev->bus != &pci_bus_type) + return false; + + devid = get_device_id(dev); + + /* Out of our scope? */ + if (devid > amd_iommu_last_bdf) + return false; + + if (amd_iommu_rlookup_table[devid] == NULL) + return false; + + return true; +} + +static int iommu_init_device(struct device *dev) +{ + struct iommu_dev_data *dev_data; + struct pci_dev *pdev; + u16 devid, alias; + + if (dev->archdata.iommu) + return 0; + + dev_data = kzalloc(sizeof(*dev_data), GFP_KERNEL); + if (!dev_data) + return -ENOMEM; + + dev_data->dev = dev; + + devid = get_device_id(dev); + alias = amd_iommu_alias_table[devid]; + pdev = pci_get_bus_and_slot(PCI_BUS(alias), alias & 0xff); + if (pdev) + dev_data->alias = &pdev->dev; + + atomic_set(&dev_data->bind, 0); + + dev->archdata.iommu = dev_data; + + + return 0; +} + +static void iommu_uninit_device(struct device *dev) +{ + kfree(dev->archdata.iommu); +} #ifdef CONFIG_AMD_IOMMU_STATS /* @@ -90,7 +186,6 @@ DECLARE_STATS_COUNTER(alloced_io_mem); DECLARE_STATS_COUNTER(total_map_requests); static struct dentry *stats_dir; -static struct dentry *de_isolate; static struct dentry *de_fflush; static void amd_iommu_stats_add(struct __iommu_counter *cnt) @@ -108,9 +203,6 @@ static void amd_iommu_stats_init(void) if (stats_dir == NULL) return; - de_isolate = debugfs_create_bool("isolation", 0444, stats_dir, - (u32 *)&amd_iommu_isolate); - de_fflush = debugfs_create_bool("fullflush", 0444, stats_dir, (u32 *)&amd_iommu_unmap_flush); @@ -130,12 +222,6 @@ static void amd_iommu_stats_init(void) #endif -/* returns !0 if the IOMMU is caching non-present entries in its TLB */ -static int iommu_has_npcache(struct amd_iommu *iommu) -{ - return iommu->cap & (1UL << IOMMU_CAP_NPCACHE); -} - /**************************************************************************** * * Interrupt handling functions @@ -199,6 +285,7 @@ static void iommu_print_event(struct amd_iommu *iommu, void *__evt) break; case EVENT_TYPE_ILL_CMD: printk("ILLEGAL_COMMAND_ERROR address=0x%016llx]\n", address); + iommu->reset_in_progress = true; reset_iommu_command_buffer(iommu); dump_command(address); break; @@ -321,11 +408,8 @@ static void __iommu_wait_for_completion(struct amd_iommu *iommu) status &= ~MMIO_STATUS_COM_WAIT_INT_MASK; writel(status, iommu->mmio_base + MMIO_STATUS_OFFSET); - if (unlikely(i == EXIT_LOOP_COUNT)) { - spin_unlock(&iommu->lock); - reset_iommu_command_buffer(iommu); - spin_lock(&iommu->lock); - } + if (unlikely(i == EXIT_LOOP_COUNT)) + iommu->reset_in_progress = true; } /* @@ -372,26 +456,46 @@ static int iommu_completion_wait(struct amd_iommu *iommu) out: spin_unlock_irqrestore(&iommu->lock, flags); + if (iommu->reset_in_progress) + reset_iommu_command_buffer(iommu); + return 0; } +static void iommu_flush_complete(struct protection_domain *domain) +{ + int i; + + for (i = 0; i < amd_iommus_present; ++i) { + if (!domain->dev_iommu[i]) + continue; + + /* + * Devices of this domain are behind this IOMMU + * We need to wait for completion of all commands. + */ + iommu_completion_wait(amd_iommus[i]); + } +} + /* * Command send function for invalidating a device table entry */ -static int iommu_queue_inv_dev_entry(struct amd_iommu *iommu, u16 devid) +static int iommu_flush_device(struct device *dev) { + struct amd_iommu *iommu; struct iommu_cmd cmd; - int ret; + u16 devid; - BUG_ON(iommu == NULL); + devid = get_device_id(dev); + iommu = amd_iommu_rlookup_table[devid]; + /* Build command */ memset(&cmd, 0, sizeof(cmd)); CMD_SET_TYPE(&cmd, CMD_INV_DEV_ENTRY); cmd.data[0] = devid; - ret = iommu_queue_command(iommu, &cmd); - - return ret; + return iommu_queue_command(iommu, &cmd); } static void __iommu_build_inv_iommu_pages(struct iommu_cmd *cmd, u64 address, @@ -430,11 +534,11 @@ static int iommu_queue_inv_iommu_pages(struct amd_iommu *iommu, * It invalidates a single PTE if the range to flush is within a single * page. Otherwise it flushes the whole TLB of the IOMMU. */ -static int iommu_flush_pages(struct amd_iommu *iommu, u16 domid, - u64 address, size_t size) +static void __iommu_flush_pages(struct protection_domain *domain, + u64 address, size_t size, int pde) { - int s = 0; - unsigned pages = iommu_num_pages(address, size, PAGE_SIZE); + int s = 0, i; + unsigned long pages = iommu_num_pages(address, size, PAGE_SIZE); address &= PAGE_MASK; @@ -447,142 +551,212 @@ static int iommu_flush_pages(struct amd_iommu *iommu, u16 domid, s = 1; } - iommu_queue_inv_iommu_pages(iommu, address, domid, 0, s); - return 0; + for (i = 0; i < amd_iommus_present; ++i) { + if (!domain->dev_iommu[i]) + continue; + + /* + * Devices of this domain are behind this IOMMU + * We need a TLB flush + */ + iommu_queue_inv_iommu_pages(amd_iommus[i], address, + domain->id, pde, s); + } + + return; } -/* Flush the whole IO/TLB for a given protection domain */ -static void iommu_flush_tlb(struct amd_iommu *iommu, u16 domid) +static void iommu_flush_pages(struct protection_domain *domain, + u64 address, size_t size) { - u64 address = CMD_INV_IOMMU_ALL_PAGES_ADDRESS; - - INC_STATS_COUNTER(domain_flush_single); + __iommu_flush_pages(domain, address, size, 0); +} - iommu_queue_inv_iommu_pages(iommu, address, domid, 0, 1); +/* Flush the whole IO/TLB for a given protection domain */ +static void iommu_flush_tlb(struct protection_domain *domain) +{ + __iommu_flush_pages(domain, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, 0); } /* Flush the whole IO/TLB for a given protection domain - including PDE */ -static void iommu_flush_tlb_pde(struct amd_iommu *iommu, u16 domid) +static void iommu_flush_tlb_pde(struct protection_domain *domain) { - u64 address = CMD_INV_IOMMU_ALL_PAGES_ADDRESS; - - INC_STATS_COUNTER(domain_flush_single); - - iommu_queue_inv_iommu_pages(iommu, address, domid, 1, 1); + __iommu_flush_pages(domain, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, 1); } + /* - * This function flushes one domain on one IOMMU + * This function flushes the DTEs for all devices in domain */ -static void flush_domain_on_iommu(struct amd_iommu *iommu, u16 domid) +static void iommu_flush_domain_devices(struct protection_domain *domain) { - struct iommu_cmd cmd; + struct iommu_dev_data *dev_data; unsigned long flags; - __iommu_build_inv_iommu_pages(&cmd, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, - domid, 1, 1); + spin_lock_irqsave(&domain->lock, flags); - spin_lock_irqsave(&iommu->lock, flags); - __iommu_queue_command(iommu, &cmd); - __iommu_completion_wait(iommu); - __iommu_wait_for_completion(iommu); - spin_unlock_irqrestore(&iommu->lock, flags); + list_for_each_entry(dev_data, &domain->dev_list, list) + iommu_flush_device(dev_data->dev); + + spin_unlock_irqrestore(&domain->lock, flags); } -static void flush_all_domains_on_iommu(struct amd_iommu *iommu) +static void iommu_flush_all_domain_devices(void) { - int i; + struct protection_domain *domain; + unsigned long flags; - for (i = 1; i < MAX_DOMAIN_ID; ++i) { - if (!test_bit(i, amd_iommu_pd_alloc_bitmap)) - continue; - flush_domain_on_iommu(iommu, i); + spin_lock_irqsave(&amd_iommu_pd_lock, flags); + + list_for_each_entry(domain, &amd_iommu_pd_list, list) { + iommu_flush_domain_devices(domain); + iommu_flush_complete(domain); } + spin_unlock_irqrestore(&amd_iommu_pd_lock, flags); +} + +void amd_iommu_flush_all_devices(void) +{ + iommu_flush_all_domain_devices(); } /* - * This function is used to flush the IO/TLB for a given protection domain - * on every IOMMU in the system + * This function uses heavy locking and may disable irqs for some time. But + * this is no issue because it is only called during resume. */ -static void iommu_flush_domain(u16 domid) +void amd_iommu_flush_all_domains(void) { - struct amd_iommu *iommu; + struct protection_domain *domain; + unsigned long flags; - INC_STATS_COUNTER(domain_flush_all); + spin_lock_irqsave(&amd_iommu_pd_lock, flags); - for_each_iommu(iommu) - flush_domain_on_iommu(iommu, domid); + list_for_each_entry(domain, &amd_iommu_pd_list, list) { + spin_lock(&domain->lock); + iommu_flush_tlb_pde(domain); + iommu_flush_complete(domain); + spin_unlock(&domain->lock); + } + + spin_unlock_irqrestore(&amd_iommu_pd_lock, flags); } -void amd_iommu_flush_all_domains(void) +static void reset_iommu_command_buffer(struct amd_iommu *iommu) { - struct amd_iommu *iommu; + pr_err("AMD-Vi: Resetting IOMMU command buffer\n"); - for_each_iommu(iommu) - flush_all_domains_on_iommu(iommu); + if (iommu->reset_in_progress) + panic("AMD-Vi: ILLEGAL_COMMAND_ERROR while resetting command buffer\n"); + + amd_iommu_reset_cmd_buffer(iommu); + amd_iommu_flush_all_devices(); + amd_iommu_flush_all_domains(); + + iommu->reset_in_progress = false; } -static void flush_all_devices_for_iommu(struct amd_iommu *iommu) +/**************************************************************************** + * + * The functions below are used the create the page table mappings for + * unity mapped regions. + * + ****************************************************************************/ + +/* + * This function is used to add another level to an IO page table. Adding + * another level increases the size of the address space by 9 bits to a size up + * to 64 bits. + */ +static bool increase_address_space(struct protection_domain *domain, + gfp_t gfp) { - int i; + u64 *pte; - for (i = 0; i <= amd_iommu_last_bdf; ++i) { - if (iommu != amd_iommu_rlookup_table[i]) - continue; + if (domain->mode == PAGE_MODE_6_LEVEL) + /* address space already 64 bit large */ + return false; - iommu_queue_inv_dev_entry(iommu, i); - iommu_completion_wait(iommu); - } + pte = (void *)get_zeroed_page(gfp); + if (!pte) + return false; + + *pte = PM_LEVEL_PDE(domain->mode, + virt_to_phys(domain->pt_root)); + domain->pt_root = pte; + domain->mode += 1; + domain->updated = true; + + return true; } -static void flush_devices_by_domain(struct protection_domain *domain) +static u64 *alloc_pte(struct protection_domain *domain, + unsigned long address, + int end_lvl, + u64 **pte_page, + gfp_t gfp) { - struct amd_iommu *iommu; - int i; + u64 *pte, *page; + int level; - for (i = 0; i <= amd_iommu_last_bdf; ++i) { - if ((domain == NULL && amd_iommu_pd_table[i] == NULL) || - (amd_iommu_pd_table[i] != domain)) - continue; + while (address > PM_LEVEL_SIZE(domain->mode)) + increase_address_space(domain, gfp); - iommu = amd_iommu_rlookup_table[i]; - if (!iommu) - continue; + level = domain->mode - 1; + pte = &domain->pt_root[PM_LEVEL_INDEX(level, address)]; - iommu_queue_inv_dev_entry(iommu, i); - iommu_completion_wait(iommu); + while (level > end_lvl) { + if (!IOMMU_PTE_PRESENT(*pte)) { + page = (u64 *)get_zeroed_page(gfp); + if (!page) + return NULL; + *pte = PM_LEVEL_PDE(level, virt_to_phys(page)); + } + + level -= 1; + + pte = IOMMU_PTE_PAGE(*pte); + + if (pte_page && level == end_lvl) + *pte_page = pte; + + pte = &pte[PM_LEVEL_INDEX(level, address)]; } + + return pte; } -static void reset_iommu_command_buffer(struct amd_iommu *iommu) +/* + * This function checks if there is a PTE for a given dma address. If + * there is one, it returns the pointer to it. + */ +static u64 *fetch_pte(struct protection_domain *domain, + unsigned long address, int map_size) { - pr_err("AMD-Vi: Resetting IOMMU command buffer\n"); + int level; + u64 *pte; - if (iommu->reset_in_progress) - panic("AMD-Vi: ILLEGAL_COMMAND_ERROR while resetting command buffer\n"); + level = domain->mode - 1; + pte = &domain->pt_root[PM_LEVEL_INDEX(level, address)]; - iommu->reset_in_progress = true; + while (level > map_size) { + if (!IOMMU_PTE_PRESENT(*pte)) + return NULL; - amd_iommu_reset_cmd_buffer(iommu); - flush_all_devices_for_iommu(iommu); - flush_all_domains_on_iommu(iommu); + level -= 1; - iommu->reset_in_progress = false; -} + pte = IOMMU_PTE_PAGE(*pte); + pte = &pte[PM_LEVEL_INDEX(level, address)]; -void amd_iommu_flush_all_devices(void) -{ - flush_devices_by_domain(NULL); -} + if ((PM_PTE_LEVEL(*pte) == 0) && level != map_size) { + pte = NULL; + break; + } + } -/**************************************************************************** - * - * The functions below are used the create the page table mappings for - * unity mapped regions. - * - ****************************************************************************/ + return pte; +} /* * Generic mapping functions. It maps a physical address into a DMA @@ -654,28 +828,6 @@ static int iommu_for_unity_map(struct amd_iommu *iommu, } /* - * Init the unity mappings for a specific IOMMU in the system - * - * Basically iterates over all unity mapping entries and applies them to - * the default domain DMA of that IOMMU if necessary. - */ -static int iommu_init_unity_mappings(struct amd_iommu *iommu) -{ - struct unity_map_entry *entry; - int ret; - - list_for_each_entry(entry, &amd_iommu_unity_map, list) { - if (!iommu_for_unity_map(iommu, entry)) - continue; - ret = dma_ops_unity_map(iommu->default_dom, entry); - if (ret) - return ret; - } - - return 0; -} - -/* * This function actually applies the mapping to the page table of the * dma_ops domain. */ @@ -704,6 +856,28 @@ static int dma_ops_unity_map(struct dma_ops_domain *dma_dom, } /* + * Init the unity mappings for a specific IOMMU in the system + * + * Basically iterates over all unity mapping entries and applies them to + * the default domain DMA of that IOMMU if necessary. + */ +static int iommu_init_unity_mappings(struct amd_iommu *iommu) +{ + struct unity_map_entry *entry; + int ret; + + list_for_each_entry(entry, &amd_iommu_unity_map, list) { + if (!iommu_for_unity_map(iommu, entry)) + continue; + ret = dma_ops_unity_map(iommu->default_dom, entry); + if (ret) + return ret; + } + + return 0; +} + +/* * Inits the unity mappings required for a specific device */ static int init_unity_mappings_for_device(struct dma_ops_domain *dma_dom, @@ -740,34 +914,23 @@ static int init_unity_mappings_for_device(struct dma_ops_domain *dma_dom, */ /* - * This function checks if there is a PTE for a given dma address. If - * there is one, it returns the pointer to it. + * Used to reserve address ranges in the aperture (e.g. for exclusion + * ranges. */ -static u64 *fetch_pte(struct protection_domain *domain, - unsigned long address, int map_size) +static void dma_ops_reserve_addresses(struct dma_ops_domain *dom, + unsigned long start_page, + unsigned int pages) { - int level; - u64 *pte; - - level = domain->mode - 1; - pte = &domain->pt_root[PM_LEVEL_INDEX(level, address)]; - - while (level > map_size) { - if (!IOMMU_PTE_PRESENT(*pte)) - return NULL; - - level -= 1; + unsigned int i, last_page = dom->aperture_size >> PAGE_SHIFT; - pte = IOMMU_PTE_PAGE(*pte); - pte = &pte[PM_LEVEL_INDEX(level, address)]; + if (start_page + pages > last_page) + pages = last_page - start_page; - if ((PM_PTE_LEVEL(*pte) == 0) && level != map_size) { - pte = NULL; - break; - } + for (i = start_page; i < start_page + pages; ++i) { + int index = i / APERTURE_RANGE_PAGES; + int page = i % APERTURE_RANGE_PAGES; + __set_bit(page, dom->aperture[index]->bitmap); } - - return pte; } /* @@ -775,11 +938,11 @@ static u64 *fetch_pte(struct protection_domain *domain, * aperture in case of dma_ops domain allocation or address allocation * failure. */ -static int alloc_new_range(struct amd_iommu *iommu, - struct dma_ops_domain *dma_dom, +static int alloc_new_range(struct dma_ops_domain *dma_dom, bool populate, gfp_t gfp) { int index = dma_dom->aperture_size >> APERTURE_RANGE_SHIFT; + struct amd_iommu *iommu; int i; #ifdef CONFIG_IOMMU_STRESS @@ -819,14 +982,17 @@ static int alloc_new_range(struct amd_iommu *iommu, dma_dom->aperture_size += APERTURE_RANGE_SIZE; /* Intialize the exclusion range if necessary */ - if (iommu->exclusion_start && - iommu->exclusion_start >= dma_dom->aperture[index]->offset && - iommu->exclusion_start < dma_dom->aperture_size) { - unsigned long startpage = iommu->exclusion_start >> PAGE_SHIFT; - int pages = iommu_num_pages(iommu->exclusion_start, - iommu->exclusion_length, - PAGE_SIZE); - dma_ops_reserve_addresses(dma_dom, startpage, pages); + for_each_iommu(iommu) { + if (iommu->exclusion_start && + iommu->exclusion_start >= dma_dom->aperture[index]->offset + && iommu->exclusion_start < dma_dom->aperture_size) { + unsigned long startpage; + int pages = iommu_num_pages(iommu->exclusion_start, + iommu->exclusion_length, + PAGE_SIZE); + startpage = iommu->exclusion_start >> PAGE_SHIFT; + dma_ops_reserve_addresses(dma_dom, startpage, pages); + } } /* @@ -928,7 +1094,7 @@ static unsigned long dma_ops_alloc_addresses(struct device *dev, } if (unlikely(address == -1)) - address = bad_dma_address; + address = DMA_ERROR_CODE; WARN_ON((address + (PAGE_SIZE*pages)) > dom->aperture_size); @@ -973,6 +1139,31 @@ static void dma_ops_free_addresses(struct dma_ops_domain *dom, * ****************************************************************************/ +/* + * This function adds a protection domain to the global protection domain list + */ +static void add_domain_to_list(struct protection_domain *domain) +{ + unsigned long flags; + + spin_lock_irqsave(&amd_iommu_pd_lock, flags); + list_add(&domain->list, &amd_iommu_pd_list); + spin_unlock_irqrestore(&amd_iommu_pd_lock, flags); +} + +/* + * This function removes a protection domain to the global + * protection domain list + */ +static void del_domain_from_list(struct protection_domain *domain) +{ + unsigned long flags; + + spin_lock_irqsave(&amd_iommu_pd_lock, flags); + list_del(&domain->list); + spin_unlock_irqrestore(&amd_iommu_pd_lock, flags); +} + static u16 domain_id_alloc(void) { unsigned long flags; @@ -1000,26 +1191,6 @@ static void domain_id_free(int id) write_unlock_irqrestore(&amd_iommu_devtable_lock, flags); } -/* - * Used to reserve address ranges in the aperture (e.g. for exclusion - * ranges. - */ -static void dma_ops_reserve_addresses(struct dma_ops_domain *dom, - unsigned long start_page, - unsigned int pages) -{ - unsigned int i, last_page = dom->aperture_size >> PAGE_SHIFT; - - if (start_page + pages > last_page) - pages = last_page - start_page; - - for (i = start_page; i < start_page + pages; ++i) { - int index = i / APERTURE_RANGE_PAGES; - int page = i % APERTURE_RANGE_PAGES; - __set_bit(page, dom->aperture[index]->bitmap); - } -} - static void free_pagetable(struct protection_domain *domain) { int i, j; @@ -1061,6 +1232,8 @@ static void dma_ops_domain_free(struct dma_ops_domain *dom) if (!dom) return; + del_domain_from_list(&dom->domain); + free_pagetable(&dom->domain); for (i = 0; i < APERTURE_MAX_RANGES; ++i) { @@ -1078,7 +1251,7 @@ static void dma_ops_domain_free(struct dma_ops_domain *dom) * It also intializes the page table and the address allocator data * structures required for the dma_ops interface */ -static struct dma_ops_domain *dma_ops_domain_alloc(struct amd_iommu *iommu) +static struct dma_ops_domain *dma_ops_domain_alloc(void) { struct dma_ops_domain *dma_dom; @@ -1091,6 +1264,7 @@ static struct dma_ops_domain *dma_ops_domain_alloc(struct amd_iommu *iommu) dma_dom->domain.id = domain_id_alloc(); if (dma_dom->domain.id == 0) goto free_dma_dom; + INIT_LIST_HEAD(&dma_dom->domain.dev_list); dma_dom->domain.mode = PAGE_MODE_2_LEVEL; dma_dom->domain.pt_root = (void *)get_zeroed_page(GFP_KERNEL); dma_dom->domain.flags = PD_DMA_OPS_MASK; @@ -1101,7 +1275,9 @@ static struct dma_ops_domain *dma_ops_domain_alloc(struct amd_iommu *iommu) dma_dom->need_flush = false; dma_dom->target_dev = 0xffff; - if (alloc_new_range(iommu, dma_dom, true, GFP_KERNEL)) + add_domain_to_list(&dma_dom->domain); + + if (alloc_new_range(dma_dom, true, GFP_KERNEL)) goto free_dma_dom; /* @@ -1129,22 +1305,6 @@ static bool dma_ops_domain(struct protection_domain *domain) return domain->flags & PD_DMA_OPS_MASK; } -/* - * Find out the protection domain structure for a given PCI device. This - * will give us the pointer to the page table root for example. - */ -static struct protection_domain *domain_for_device(u16 devid) -{ - struct protection_domain *dom; - unsigned long flags; - - read_lock_irqsave(&amd_iommu_devtable_lock, flags); - dom = amd_iommu_pd_table[devid]; - read_unlock_irqrestore(&amd_iommu_devtable_lock, flags); - - return dom; -} - static void set_dte_entry(u16 devid, struct protection_domain *domain) { u64 pte_root = virt_to_phys(domain->pt_root); @@ -1156,42 +1316,123 @@ static void set_dte_entry(u16 devid, struct protection_domain *domain) amd_iommu_dev_table[devid].data[2] = domain->id; amd_iommu_dev_table[devid].data[1] = upper_32_bits(pte_root); amd_iommu_dev_table[devid].data[0] = lower_32_bits(pte_root); +} + +static void clear_dte_entry(u16 devid) +{ + /* remove entry from the device table seen by the hardware */ + amd_iommu_dev_table[devid].data[0] = IOMMU_PTE_P | IOMMU_PTE_TV; + amd_iommu_dev_table[devid].data[1] = 0; + amd_iommu_dev_table[devid].data[2] = 0; - amd_iommu_pd_table[devid] = domain; + amd_iommu_apply_erratum_63(devid); +} + +static void do_attach(struct device *dev, struct protection_domain *domain) +{ + struct iommu_dev_data *dev_data; + struct amd_iommu *iommu; + u16 devid; + + devid = get_device_id(dev); + iommu = amd_iommu_rlookup_table[devid]; + dev_data = get_dev_data(dev); + + /* Update data structures */ + dev_data->domain = domain; + list_add(&dev_data->list, &domain->dev_list); + set_dte_entry(devid, domain); + + /* Do reference counting */ + domain->dev_iommu[iommu->index] += 1; + domain->dev_cnt += 1; + + /* Flush the DTE entry */ + iommu_flush_device(dev); +} + +static void do_detach(struct device *dev) +{ + struct iommu_dev_data *dev_data; + struct amd_iommu *iommu; + u16 devid; + + devid = get_device_id(dev); + iommu = amd_iommu_rlookup_table[devid]; + dev_data = get_dev_data(dev); + + /* decrease reference counters */ + dev_data->domain->dev_iommu[iommu->index] -= 1; + dev_data->domain->dev_cnt -= 1; + + /* Update data structures */ + dev_data->domain = NULL; + list_del(&dev_data->list); + clear_dte_entry(devid); + + /* Flush the DTE entry */ + iommu_flush_device(dev); } /* * If a device is not yet associated with a domain, this function does * assigns it visible for the hardware */ -static void __attach_device(struct amd_iommu *iommu, - struct protection_domain *domain, - u16 devid) +static int __attach_device(struct device *dev, + struct protection_domain *domain) { + struct iommu_dev_data *dev_data, *alias_data; + + dev_data = get_dev_data(dev); + alias_data = get_dev_data(dev_data->alias); + + if (!alias_data) + return -EINVAL; + /* lock domain */ spin_lock(&domain->lock); - /* update DTE entry */ - set_dte_entry(devid, domain); + /* Some sanity checks */ + if (alias_data->domain != NULL && + alias_data->domain != domain) + return -EBUSY; - domain->dev_cnt += 1; + if (dev_data->domain != NULL && + dev_data->domain != domain) + return -EBUSY; + + /* Do real assignment */ + if (dev_data->alias != dev) { + alias_data = get_dev_data(dev_data->alias); + if (alias_data->domain == NULL) + do_attach(dev_data->alias, domain); + + atomic_inc(&alias_data->bind); + } + + if (dev_data->domain == NULL) + do_attach(dev, domain); + + atomic_inc(&dev_data->bind); /* ready */ spin_unlock(&domain->lock); + + return 0; } /* * If a device is not yet associated with a domain, this function does * assigns it visible for the hardware */ -static void attach_device(struct amd_iommu *iommu, - struct protection_domain *domain, - u16 devid) +static int attach_device(struct device *dev, + struct protection_domain *domain) { unsigned long flags; + int ret; write_lock_irqsave(&amd_iommu_devtable_lock, flags); - __attach_device(iommu, domain, devid); + ret = __attach_device(dev, domain); write_unlock_irqrestore(&amd_iommu_devtable_lock, flags); /* @@ -1199,98 +1440,125 @@ static void attach_device(struct amd_iommu *iommu, * left the caches in the IOMMU dirty. So we have to flush * here to evict all dirty stuff. */ - iommu_queue_inv_dev_entry(iommu, devid); - iommu_flush_tlb_pde(iommu, domain->id); + iommu_flush_tlb_pde(domain); + + return ret; } /* * Removes a device from a protection domain (unlocked) */ -static void __detach_device(struct protection_domain *domain, u16 devid) +static void __detach_device(struct device *dev) { + struct iommu_dev_data *dev_data = get_dev_data(dev); + struct iommu_dev_data *alias_data; + unsigned long flags; - /* lock domain */ - spin_lock(&domain->lock); - - /* remove domain from the lookup table */ - amd_iommu_pd_table[devid] = NULL; + BUG_ON(!dev_data->domain); - /* remove entry from the device table seen by the hardware */ - amd_iommu_dev_table[devid].data[0] = IOMMU_PTE_P | IOMMU_PTE_TV; - amd_iommu_dev_table[devid].data[1] = 0; - amd_iommu_dev_table[devid].data[2] = 0; + spin_lock_irqsave(&dev_data->domain->lock, flags); - amd_iommu_apply_erratum_63(devid); + if (dev_data->alias != dev) { + alias_data = get_dev_data(dev_data->alias); + if (atomic_dec_and_test(&alias_data->bind)) + do_detach(dev_data->alias); + } - /* decrease reference counter */ - domain->dev_cnt -= 1; + if (atomic_dec_and_test(&dev_data->bind)) + do_detach(dev); - /* ready */ - spin_unlock(&domain->lock); + spin_unlock_irqrestore(&dev_data->domain->lock, flags); /* * If we run in passthrough mode the device must be assigned to the * passthrough domain if it is detached from any other domain */ - if (iommu_pass_through) { - struct amd_iommu *iommu = amd_iommu_rlookup_table[devid]; - __attach_device(iommu, pt_domain, devid); - } + if (iommu_pass_through && dev_data->domain == NULL) + __attach_device(dev, pt_domain); } /* * Removes a device from a protection domain (with devtable_lock held) */ -static void detach_device(struct protection_domain *domain, u16 devid) +static void detach_device(struct device *dev) { unsigned long flags; /* lock device table */ write_lock_irqsave(&amd_iommu_devtable_lock, flags); - __detach_device(domain, devid); + __detach_device(dev); write_unlock_irqrestore(&amd_iommu_devtable_lock, flags); } +/* + * Find out the protection domain structure for a given PCI device. This + * will give us the pointer to the page table root for example. + */ +static struct protection_domain *domain_for_device(struct device *dev) +{ + struct protection_domain *dom; + struct iommu_dev_data *dev_data, *alias_data; + unsigned long flags; + u16 devid, alias; + + devid = get_device_id(dev); + alias = amd_iommu_alias_table[devid]; + dev_data = get_dev_data(dev); + alias_data = get_dev_data(dev_data->alias); + if (!alias_data) + return NULL; + + read_lock_irqsave(&amd_iommu_devtable_lock, flags); + dom = dev_data->domain; + if (dom == NULL && + alias_data->domain != NULL) { + __attach_device(dev, alias_data->domain); + dom = alias_data->domain; + } + + read_unlock_irqrestore(&amd_iommu_devtable_lock, flags); + + return dom; +} + static int device_change_notifier(struct notifier_block *nb, unsigned long action, void *data) { struct device *dev = data; - struct pci_dev *pdev = to_pci_dev(dev); - u16 devid = calc_devid(pdev->bus->number, pdev->devfn); + u16 devid; struct protection_domain *domain; struct dma_ops_domain *dma_domain; struct amd_iommu *iommu; unsigned long flags; - if (devid > amd_iommu_last_bdf) - goto out; - - devid = amd_iommu_alias_table[devid]; - - iommu = amd_iommu_rlookup_table[devid]; - if (iommu == NULL) - goto out; - - domain = domain_for_device(devid); + if (!check_device(dev)) + return 0; - if (domain && !dma_ops_domain(domain)) - WARN_ONCE(1, "AMD IOMMU WARNING: device %s already bound " - "to a non-dma-ops domain\n", dev_name(dev)); + devid = get_device_id(dev); + iommu = amd_iommu_rlookup_table[devid]; switch (action) { case BUS_NOTIFY_UNBOUND_DRIVER: + + domain = domain_for_device(dev); + if (!domain) goto out; if (iommu_pass_through) break; - detach_device(domain, devid); + detach_device(dev); break; case BUS_NOTIFY_ADD_DEVICE: + + iommu_init_device(dev); + + domain = domain_for_device(dev); + /* allocate a protection domain if a device is added */ dma_domain = find_protection_domain(devid); if (dma_domain) goto out; - dma_domain = dma_ops_domain_alloc(iommu); + dma_domain = dma_ops_domain_alloc(); if (!dma_domain) goto out; dma_domain->target_dev = devid; @@ -1300,11 +1568,15 @@ static int device_change_notifier(struct notifier_block *nb, spin_unlock_irqrestore(&iommu_pd_list_lock, flags); break; + case BUS_NOTIFY_DEL_DEVICE: + + iommu_uninit_device(dev); + default: goto out; } - iommu_queue_inv_dev_entry(iommu, devid); + iommu_flush_device(dev); iommu_completion_wait(iommu); out: @@ -1322,106 +1594,46 @@ static struct notifier_block device_nb = { *****************************************************************************/ /* - * This function checks if the driver got a valid device from the caller to - * avoid dereferencing invalid pointers. - */ -static bool check_device(struct device *dev) -{ - if (!dev || !dev->dma_mask) - return false; - - return true; -} - -/* - * In this function the list of preallocated protection domains is traversed to - * find the domain for a specific device - */ -static struct dma_ops_domain *find_protection_domain(u16 devid) -{ - struct dma_ops_domain *entry, *ret = NULL; - unsigned long flags; - - if (list_empty(&iommu_pd_list)) - return NULL; - - spin_lock_irqsave(&iommu_pd_list_lock, flags); - - list_for_each_entry(entry, &iommu_pd_list, list) { - if (entry->target_dev == devid) { - ret = entry; - break; - } - } - - spin_unlock_irqrestore(&iommu_pd_list_lock, flags); - - return ret; -} - -/* * In the dma_ops path we only have the struct device. This function * finds the corresponding IOMMU, the protection domain and the * requestor id for a given device. * If the device is not yet associated with a domain this is also done * in this function. */ -static int get_device_resources(struct device *dev, - struct amd_iommu **iommu, - struct protection_domain **domain, - u16 *bdf) +static struct protection_domain *get_domain(struct device *dev) { + struct protection_domain *domain; struct dma_ops_domain *dma_dom; - struct pci_dev *pcidev; - u16 _bdf; - - *iommu = NULL; - *domain = NULL; - *bdf = 0xffff; - - if (dev->bus != &pci_bus_type) - return 0; + u16 devid = get_device_id(dev); - pcidev = to_pci_dev(dev); - _bdf = calc_devid(pcidev->bus->number, pcidev->devfn); + if (!check_device(dev)) + return ERR_PTR(-EINVAL); - /* device not translated by any IOMMU in the system? */ - if (_bdf > amd_iommu_last_bdf) - return 0; + domain = domain_for_device(dev); + if (domain != NULL && !dma_ops_domain(domain)) + return ERR_PTR(-EBUSY); - *bdf = amd_iommu_alias_table[_bdf]; + if (domain != NULL) + return domain; - *iommu = amd_iommu_rlookup_table[*bdf]; - if (*iommu == NULL) - return 0; - *domain = domain_for_device(*bdf); - if (*domain == NULL) { - dma_dom = find_protection_domain(*bdf); - if (!dma_dom) - dma_dom = (*iommu)->default_dom; - *domain = &dma_dom->domain; - attach_device(*iommu, *domain, *bdf); - DUMP_printk("Using protection domain %d for device %s\n", - (*domain)->id, dev_name(dev)); - } - - if (domain_for_device(_bdf) == NULL) - attach_device(*iommu, *domain, _bdf); + /* Device not bount yet - bind it */ + dma_dom = find_protection_domain(devid); + if (!dma_dom) + dma_dom = amd_iommu_rlookup_table[devid]->default_dom; + attach_device(dev, &dma_dom->domain); + DUMP_printk("Using protection domain %d for device %s\n", + dma_dom->domain.id, dev_name(dev)); - return 1; + return &dma_dom->domain; } static void update_device_table(struct protection_domain *domain) { - unsigned long flags; - int i; + struct iommu_dev_data *dev_data; - for (i = 0; i <= amd_iommu_last_bdf; ++i) { - if (amd_iommu_pd_table[i] != domain) - continue; - write_lock_irqsave(&amd_iommu_devtable_lock, flags); - set_dte_entry(i, domain); - write_unlock_irqrestore(&amd_iommu_devtable_lock, flags); + list_for_each_entry(dev_data, &domain->dev_list, list) { + u16 devid = get_device_id(dev_data->dev); + set_dte_entry(devid, domain); } } @@ -1431,76 +1643,13 @@ static void update_domain(struct protection_domain *domain) return; update_device_table(domain); - flush_devices_by_domain(domain); - iommu_flush_domain(domain->id); + iommu_flush_domain_devices(domain); + iommu_flush_tlb_pde(domain); domain->updated = false; } /* - * This function is used to add another level to an IO page table. Adding - * another level increases the size of the address space by 9 bits to a size up - * to 64 bits. - */ -static bool increase_address_space(struct protection_domain *domain, - gfp_t gfp) -{ - u64 *pte; - - if (domain->mode == PAGE_MODE_6_LEVEL) - /* address space already 64 bit large */ - return false; - - pte = (void *)get_zeroed_page(gfp); - if (!pte) - return false; - - *pte = PM_LEVEL_PDE(domain->mode, - virt_to_phys(domain->pt_root)); - domain->pt_root = pte; - domain->mode += 1; - domain->updated = true; - - return true; -} - -static u64 *alloc_pte(struct protection_domain *domain, - unsigned long address, - int end_lvl, - u64 **pte_page, - gfp_t gfp) -{ - u64 *pte, *page; - int level; - - while (address > PM_LEVEL_SIZE(domain->mode)) - increase_address_space(domain, gfp); - - level = domain->mode - 1; - pte = &domain->pt_root[PM_LEVEL_INDEX(level, address)]; - - while (level > end_lvl) { - if (!IOMMU_PTE_PRESENT(*pte)) { - page = (u64 *)get_zeroed_page(gfp); - if (!page) - return NULL; - *pte = PM_LEVEL_PDE(level, virt_to_phys(page)); - } - - level -= 1; - - pte = IOMMU_PTE_PAGE(*pte); - - if (pte_page && level == end_lvl) - *pte_page = pte; - - pte = &pte[PM_LEVEL_INDEX(level, address)]; - } - - return pte; -} - -/* * This function fetches the PTE for a given address in the aperture */ static u64* dma_ops_get_pte(struct dma_ops_domain *dom, @@ -1530,8 +1679,7 @@ static u64* dma_ops_get_pte(struct dma_ops_domain *dom, * This is the generic map function. It maps one 4kb page at paddr to * the given address in the DMA address space for the domain. */ -static dma_addr_t dma_ops_domain_map(struct amd_iommu *iommu, - struct dma_ops_domain *dom, +static dma_addr_t dma_ops_domain_map(struct dma_ops_domain *dom, unsigned long address, phys_addr_t paddr, int direction) @@ -1544,7 +1692,7 @@ static dma_addr_t dma_ops_domain_map(struct amd_iommu *iommu, pte = dma_ops_get_pte(dom, address); if (!pte) - return bad_dma_address; + return DMA_ERROR_CODE; __pte = paddr | IOMMU_PTE_P | IOMMU_PTE_FC; @@ -1565,8 +1713,7 @@ static dma_addr_t dma_ops_domain_map(struct amd_iommu *iommu, /* * The generic unmapping function for on page in the DMA address space. */ -static void dma_ops_domain_unmap(struct amd_iommu *iommu, - struct dma_ops_domain *dom, +static void dma_ops_domain_unmap(struct dma_ops_domain *dom, unsigned long address) { struct aperture_range *aperture; @@ -1597,7 +1744,6 @@ static void dma_ops_domain_unmap(struct amd_iommu *iommu, * Must be called with the domain lock held. */ static dma_addr_t __map_single(struct device *dev, - struct amd_iommu *iommu, struct dma_ops_domain *dma_dom, phys_addr_t paddr, size_t size, @@ -1625,7 +1771,7 @@ static dma_addr_t __map_single(struct device *dev, retry: address = dma_ops_alloc_addresses(dev, dma_dom, pages, align_mask, dma_mask); - if (unlikely(address == bad_dma_address)) { + if (unlikely(address == DMA_ERROR_CODE)) { /* * setting next_address here will let the address * allocator only scan the new allocated range in the @@ -1633,7 +1779,7 @@ retry: */ dma_dom->next_address = dma_dom->aperture_size; - if (alloc_new_range(iommu, dma_dom, false, GFP_ATOMIC)) + if (alloc_new_range(dma_dom, false, GFP_ATOMIC)) goto out; /* @@ -1645,8 +1791,8 @@ retry: start = address; for (i = 0; i < pages; ++i) { - ret = dma_ops_domain_map(iommu, dma_dom, start, paddr, dir); - if (ret == bad_dma_address) + ret = dma_ops_domain_map(dma_dom, start, paddr, dir); + if (ret == DMA_ERROR_CODE) goto out_unmap; paddr += PAGE_SIZE; @@ -1657,10 +1803,10 @@ retry: ADD_STATS_COUNTER(alloced_io_mem, size); if (unlikely(dma_dom->need_flush && !amd_iommu_unmap_flush)) { - iommu_flush_tlb(iommu, dma_dom->domain.id); + iommu_flush_tlb(&dma_dom->domain); dma_dom->need_flush = false; - } else if (unlikely(iommu_has_npcache(iommu))) - iommu_flush_pages(iommu, dma_dom->domain.id, address, size); + } else if (unlikely(amd_iommu_np_cache)) + iommu_flush_pages(&dma_dom->domain, address, size); out: return address; @@ -1669,20 +1815,19 @@ out_unmap: for (--i; i >= 0; --i) { start -= PAGE_SIZE; - dma_ops_domain_unmap(iommu, dma_dom, start); + dma_ops_domain_unmap(dma_dom, start); } dma_ops_free_addresses(dma_dom, address, pages); - return bad_dma_address; + return DMA_ERROR_CODE; } /* * Does the reverse of the __map_single function. Must be called with * the domain lock held too */ -static void __unmap_single(struct amd_iommu *iommu, - struct dma_ops_domain *dma_dom, +static void __unmap_single(struct dma_ops_domain *dma_dom, dma_addr_t dma_addr, size_t size, int dir) @@ -1690,7 +1835,7 @@ static void __unmap_single(struct amd_iommu *iommu, dma_addr_t i, start; unsigned int pages; - if ((dma_addr == bad_dma_address) || + if ((dma_addr == DMA_ERROR_CODE) || (dma_addr + size > dma_dom->aperture_size)) return; @@ -1699,7 +1844,7 @@ static void __unmap_single(struct amd_iommu *iommu, start = dma_addr; for (i = 0; i < pages; ++i) { - dma_ops_domain_unmap(iommu, dma_dom, start); + dma_ops_domain_unmap(dma_dom, start); start += PAGE_SIZE; } @@ -1708,7 +1853,7 @@ static void __unmap_single(struct amd_iommu *iommu, dma_ops_free_addresses(dma_dom, dma_addr, pages); if (amd_iommu_unmap_flush || dma_dom->need_flush) { - iommu_flush_pages(iommu, dma_dom->domain.id, dma_addr, size); + iommu_flush_pages(&dma_dom->domain, dma_addr, size); dma_dom->need_flush = false; } } @@ -1722,36 +1867,29 @@ static dma_addr_t map_page(struct device *dev, struct page *page, struct dma_attrs *attrs) { unsigned long flags; - struct amd_iommu *iommu; struct protection_domain *domain; - u16 devid; dma_addr_t addr; u64 dma_mask; phys_addr_t paddr = page_to_phys(page) + offset; INC_STATS_COUNTER(cnt_map_single); - if (!check_device(dev)) - return bad_dma_address; - - dma_mask = *dev->dma_mask; - - get_device_resources(dev, &iommu, &domain, &devid); - - if (iommu == NULL || domain == NULL) - /* device not handled by any AMD IOMMU */ + domain = get_domain(dev); + if (PTR_ERR(domain) == -EINVAL) return (dma_addr_t)paddr; + else if (IS_ERR(domain)) + return DMA_ERROR_CODE; - if (!dma_ops_domain(domain)) - return bad_dma_address; + dma_mask = *dev->dma_mask; spin_lock_irqsave(&domain->lock, flags); - addr = __map_single(dev, iommu, domain->priv, paddr, size, dir, false, + + addr = __map_single(dev, domain->priv, paddr, size, dir, false, dma_mask); - if (addr == bad_dma_address) + if (addr == DMA_ERROR_CODE) goto out; - iommu_completion_wait(iommu); + iommu_flush_complete(domain); out: spin_unlock_irqrestore(&domain->lock, flags); @@ -1766,25 +1904,19 @@ static void unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size, enum dma_data_direction dir, struct dma_attrs *attrs) { unsigned long flags; - struct amd_iommu *iommu; struct protection_domain *domain; - u16 devid; INC_STATS_COUNTER(cnt_unmap_single); - if (!check_device(dev) || - !get_device_resources(dev, &iommu, &domain, &devid)) - /* device not handled by any AMD IOMMU */ - return; - - if (!dma_ops_domain(domain)) + domain = get_domain(dev); + if (IS_ERR(domain)) return; spin_lock_irqsave(&domain->lock, flags); - __unmap_single(iommu, domain->priv, dma_addr, size, dir); + __unmap_single(domain->priv, dma_addr, size, dir); - iommu_completion_wait(iommu); + iommu_flush_complete(domain); spin_unlock_irqrestore(&domain->lock, flags); } @@ -1816,9 +1948,7 @@ static int map_sg(struct device *dev, struct scatterlist *sglist, struct dma_attrs *attrs) { unsigned long flags; - struct amd_iommu *iommu; struct protection_domain *domain; - u16 devid; int i; struct scatterlist *s; phys_addr_t paddr; @@ -1827,25 +1957,20 @@ static int map_sg(struct device *dev, struct scatterlist *sglist, INC_STATS_COUNTER(cnt_map_sg); - if (!check_device(dev)) + domain = get_domain(dev); + if (PTR_ERR(domain) == -EINVAL) + return map_sg_no_iommu(dev, sglist, nelems, dir); + else if (IS_ERR(domain)) return 0; dma_mask = *dev->dma_mask; - get_device_resources(dev, &iommu, &domain, &devid); - - if (!iommu || !domain) - return map_sg_no_iommu(dev, sglist, nelems, dir); - - if (!dma_ops_domain(domain)) - return 0; - spin_lock_irqsave(&domain->lock, flags); for_each_sg(sglist, s, nelems, i) { paddr = sg_phys(s); - s->dma_address = __map_single(dev, iommu, domain->priv, + s->dma_address = __map_single(dev, domain->priv, paddr, s->length, dir, false, dma_mask); @@ -1856,7 +1981,7 @@ static int map_sg(struct device *dev, struct scatterlist *sglist, goto unmap; } - iommu_completion_wait(iommu); + iommu_flush_complete(domain); out: spin_unlock_irqrestore(&domain->lock, flags); @@ -1865,7 +1990,7 @@ out: unmap: for_each_sg(sglist, s, mapped_elems, i) { if (s->dma_address) - __unmap_single(iommu, domain->priv, s->dma_address, + __unmap_single(domain->priv, s->dma_address, s->dma_length, dir); s->dma_address = s->dma_length = 0; } @@ -1884,30 +2009,25 @@ static void unmap_sg(struct device *dev, struct scatterlist *sglist, struct dma_attrs *attrs) { unsigned long flags; - struct amd_iommu *iommu; struct protection_domain *domain; struct scatterlist *s; - u16 devid; int i; INC_STATS_COUNTER(cnt_unmap_sg); - if (!check_device(dev) || - !get_device_resources(dev, &iommu, &domain, &devid)) - return; - - if (!dma_ops_domain(domain)) + domain = get_domain(dev); + if (IS_ERR(domain)) return; spin_lock_irqsave(&domain->lock, flags); for_each_sg(sglist, s, nelems, i) { - __unmap_single(iommu, domain->priv, s->dma_address, + __unmap_single(domain->priv, s->dma_address, s->dma_length, dir); s->dma_address = s->dma_length = 0; } - iommu_completion_wait(iommu); + iommu_flush_complete(domain); spin_unlock_irqrestore(&domain->lock, flags); } @@ -1920,49 +2040,44 @@ static void *alloc_coherent(struct device *dev, size_t size, { unsigned long flags; void *virt_addr; - struct amd_iommu *iommu; struct protection_domain *domain; - u16 devid; phys_addr_t paddr; u64 dma_mask = dev->coherent_dma_mask; INC_STATS_COUNTER(cnt_alloc_coherent); - if (!check_device(dev)) + domain = get_domain(dev); + if (PTR_ERR(domain) == -EINVAL) { + virt_addr = (void *)__get_free_pages(flag, get_order(size)); + *dma_addr = __pa(virt_addr); + return virt_addr; + } else if (IS_ERR(domain)) return NULL; - if (!get_device_resources(dev, &iommu, &domain, &devid)) - flag &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32); + dma_mask = dev->coherent_dma_mask; + flag &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32); + flag |= __GFP_ZERO; - flag |= __GFP_ZERO; virt_addr = (void *)__get_free_pages(flag, get_order(size)); if (!virt_addr) return NULL; paddr = virt_to_phys(virt_addr); - if (!iommu || !domain) { - *dma_addr = (dma_addr_t)paddr; - return virt_addr; - } - - if (!dma_ops_domain(domain)) - goto out_free; - if (!dma_mask) dma_mask = *dev->dma_mask; spin_lock_irqsave(&domain->lock, flags); - *dma_addr = __map_single(dev, iommu, domain->priv, paddr, + *dma_addr = __map_single(dev, domain->priv, paddr, size, DMA_BIDIRECTIONAL, true, dma_mask); - if (*dma_addr == bad_dma_address) { + if (*dma_addr == DMA_ERROR_CODE) { spin_unlock_irqrestore(&domain->lock, flags); goto out_free; } - iommu_completion_wait(iommu); + iommu_flush_complete(domain); spin_unlock_irqrestore(&domain->lock, flags); @@ -1982,28 +2097,19 @@ static void free_coherent(struct device *dev, size_t size, void *virt_addr, dma_addr_t dma_addr) { unsigned long flags; - struct amd_iommu *iommu; struct protection_domain *domain; - u16 devid; INC_STATS_COUNTER(cnt_free_coherent); - if (!check_device(dev)) - return; - - get_device_resources(dev, &iommu, &domain, &devid); - - if (!iommu || !domain) - goto free_mem; - - if (!dma_ops_domain(domain)) + domain = get_domain(dev); + if (IS_ERR(domain)) goto free_mem; spin_lock_irqsave(&domain->lock, flags); - __unmap_single(iommu, domain->priv, dma_addr, size, DMA_BIDIRECTIONAL); + __unmap_single(domain->priv, dma_addr, size, DMA_BIDIRECTIONAL); - iommu_completion_wait(iommu); + iommu_flush_complete(domain); spin_unlock_irqrestore(&domain->lock, flags); @@ -2017,22 +2123,7 @@ free_mem: */ static int amd_iommu_dma_supported(struct device *dev, u64 mask) { - u16 bdf; - struct pci_dev *pcidev; - - /* No device or no PCI device */ - if (!dev || dev->bus != &pci_bus_type) - return 0; - - pcidev = to_pci_dev(dev); - - bdf = calc_devid(pcidev->bus->number, pcidev->devfn); - - /* Out of our scope? */ - if (bdf > amd_iommu_last_bdf) - return 0; - - return 1; + return check_device(dev); } /* @@ -2046,25 +2137,30 @@ static void prealloc_protection_domains(void) { struct pci_dev *dev = NULL; struct dma_ops_domain *dma_dom; - struct amd_iommu *iommu; u16 devid; while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) { - devid = calc_devid(dev->bus->number, dev->devfn); - if (devid > amd_iommu_last_bdf) - continue; - devid = amd_iommu_alias_table[devid]; - if (domain_for_device(devid)) + + /* Do we handle this device? */ + if (!check_device(&dev->dev)) continue; - iommu = amd_iommu_rlookup_table[devid]; - if (!iommu) + + iommu_init_device(&dev->dev); + + /* Is there already any domain for it? */ + if (domain_for_device(&dev->dev)) continue; - dma_dom = dma_ops_domain_alloc(iommu); + + devid = get_device_id(&dev->dev); + + dma_dom = dma_ops_domain_alloc(); if (!dma_dom) continue; init_unity_mappings_for_device(dma_dom, devid); dma_dom->target_dev = devid; + attach_device(&dev->dev, &dma_dom->domain); + list_add_tail(&dma_dom->list, &iommu_pd_list); } } @@ -2093,7 +2189,7 @@ int __init amd_iommu_init_dma_ops(void) * protection domain will be assigned to the default one. */ for_each_iommu(iommu) { - iommu->default_dom = dma_ops_domain_alloc(iommu); + iommu->default_dom = dma_ops_domain_alloc(); if (iommu->default_dom == NULL) return -ENOMEM; iommu->default_dom->domain.flags |= PD_DEFAULT_MASK; @@ -2103,15 +2199,12 @@ int __init amd_iommu_init_dma_ops(void) } /* - * If device isolation is enabled, pre-allocate the protection - * domains for each device. + * Pre-allocate the protection domains for each device. */ - if (amd_iommu_isolate) - prealloc_protection_domains(); + prealloc_protection_domains(); iommu_detected = 1; - force_iommu = 1; - bad_dma_address = 0; + swiotlb = 0; #ifdef CONFIG_GART_IOMMU gart_iommu_aperture_disabled = 1; gart_iommu_aperture = 0; @@ -2150,14 +2243,17 @@ free_domains: static void cleanup_domain(struct protection_domain *domain) { + struct iommu_dev_data *dev_data, *next; unsigned long flags; - u16 devid; write_lock_irqsave(&amd_iommu_devtable_lock, flags); - for (devid = 0; devid <= amd_iommu_last_bdf; ++devid) - if (amd_iommu_pd_table[devid] == domain) - __detach_device(domain, devid); + list_for_each_entry_safe(dev_data, next, &domain->dev_list, list) { + struct device *dev = dev_data->dev; + + do_detach(dev); + atomic_set(&dev_data->bind, 0); + } write_unlock_irqrestore(&amd_iommu_devtable_lock, flags); } @@ -2167,6 +2263,8 @@ static void protection_domain_free(struct protection_domain *domain) if (!domain) return; + del_domain_from_list(domain); + if (domain->id) domain_id_free(domain->id); @@ -2185,6 +2283,9 @@ static struct protection_domain *protection_domain_alloc(void) domain->id = domain_id_alloc(); if (!domain->id) goto out_err; + INIT_LIST_HEAD(&domain->dev_list); + + add_domain_to_list(domain); return domain; @@ -2241,26 +2342,23 @@ static void amd_iommu_domain_destroy(struct iommu_domain *dom) static void amd_iommu_detach_device(struct iommu_domain *dom, struct device *dev) { - struct protection_domain *domain = dom->priv; + struct iommu_dev_data *dev_data = dev->archdata.iommu; struct amd_iommu *iommu; - struct pci_dev *pdev; u16 devid; - if (dev->bus != &pci_bus_type) + if (!check_device(dev)) return; - pdev = to_pci_dev(dev); - - devid = calc_devid(pdev->bus->number, pdev->devfn); + devid = get_device_id(dev); - if (devid > 0) - detach_device(domain, devid); + if (dev_data->domain != NULL) + detach_device(dev); iommu = amd_iommu_rlookup_table[devid]; if (!iommu) return; - iommu_queue_inv_dev_entry(iommu, devid); + iommu_flush_device(dev); iommu_completion_wait(iommu); } @@ -2268,35 +2366,30 @@ static int amd_iommu_attach_device(struct iommu_domain *dom, struct device *dev) { struct protection_domain *domain = dom->priv; - struct protection_domain *old_domain; + struct iommu_dev_data *dev_data; struct amd_iommu *iommu; - struct pci_dev *pdev; + int ret; u16 devid; - if (dev->bus != &pci_bus_type) + if (!check_device(dev)) return -EINVAL; - pdev = to_pci_dev(dev); + dev_data = dev->archdata.iommu; - devid = calc_devid(pdev->bus->number, pdev->devfn); - - if (devid >= amd_iommu_last_bdf || - devid != amd_iommu_alias_table[devid]) - return -EINVAL; + devid = get_device_id(dev); iommu = amd_iommu_rlookup_table[devid]; if (!iommu) return -EINVAL; - old_domain = domain_for_device(devid); - if (old_domain) - detach_device(old_domain, devid); + if (dev_data->domain) + detach_device(dev); - attach_device(iommu, domain, devid); + ret = attach_device(dev, domain); iommu_completion_wait(iommu); - return 0; + return ret; } static int amd_iommu_map_range(struct iommu_domain *dom, @@ -2342,7 +2435,7 @@ static void amd_iommu_unmap_range(struct iommu_domain *dom, iova += PAGE_SIZE; } - iommu_flush_domain(domain->id); + iommu_flush_tlb_pde(domain); } static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom, @@ -2393,8 +2486,9 @@ static struct iommu_ops amd_iommu_ops = { int __init amd_iommu_init_passthrough(void) { + struct amd_iommu *iommu; struct pci_dev *dev = NULL; - u16 devid, devid2; + u16 devid; /* allocate passthroug domain */ pt_domain = protection_domain_alloc(); @@ -2404,20 +2498,17 @@ int __init amd_iommu_init_passthrough(void) pt_domain->mode |= PAGE_MODE_NONE; while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) { - struct amd_iommu *iommu; - devid = calc_devid(dev->bus->number, dev->devfn); - if (devid > amd_iommu_last_bdf) + if (!check_device(&dev->dev)) continue; - devid2 = amd_iommu_alias_table[devid]; + devid = get_device_id(&dev->dev); - iommu = amd_iommu_rlookup_table[devid2]; + iommu = amd_iommu_rlookup_table[devid]; if (!iommu) continue; - __attach_device(iommu, pt_domain, devid); - __attach_device(iommu, pt_domain, devid2); + attach_device(&dev->dev, pt_domain); } pr_info("AMD-Vi: Initialized for Passthrough Mode\n"); diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c index c20001e4f556..7ffc39965233 100644 --- a/arch/x86/kernel/amd_iommu_init.c +++ b/arch/x86/kernel/amd_iommu_init.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2008 Advanced Micro Devices, Inc. + * Copyright (C) 2007-2009 Advanced Micro Devices, Inc. * Author: Joerg Roedel <joerg.roedel@amd.com> * Leo Duran <leo.duran@amd.com> * @@ -25,10 +25,12 @@ #include <linux/interrupt.h> #include <linux/msi.h> #include <asm/pci-direct.h> +#include <asm/amd_iommu_proto.h> #include <asm/amd_iommu_types.h> #include <asm/amd_iommu.h> #include <asm/iommu.h> #include <asm/gart.h> +#include <asm/x86_init.h> /* * definitions for the ACPI scanning code @@ -123,18 +125,24 @@ u16 amd_iommu_last_bdf; /* largest PCI device id we have to handle */ LIST_HEAD(amd_iommu_unity_map); /* a list of required unity mappings we find in ACPI */ -#ifdef CONFIG_IOMMU_STRESS -bool amd_iommu_isolate = false; -#else -bool amd_iommu_isolate = true; /* if true, device isolation is - enabled */ -#endif - bool amd_iommu_unmap_flush; /* if true, flush on every unmap */ LIST_HEAD(amd_iommu_list); /* list of all AMD IOMMUs in the system */ +/* Array to assign indices to IOMMUs*/ +struct amd_iommu *amd_iommus[MAX_IOMMUS]; +int amd_iommus_present; + +/* IOMMUs have a non-present cache? */ +bool amd_iommu_np_cache __read_mostly; + +/* + * List of protection domains - used during resume + */ +LIST_HEAD(amd_iommu_pd_list); +spinlock_t amd_iommu_pd_lock; + /* * Pointer to the device table which is shared by all AMD IOMMUs * it is indexed by the PCI device id or the HT unit id and contains @@ -157,12 +165,6 @@ u16 *amd_iommu_alias_table; struct amd_iommu **amd_iommu_rlookup_table; /* - * The pd table (protection domain table) is used to find the protection domain - * data structure a device belongs to. Indexed with the PCI device id too. - */ -struct protection_domain **amd_iommu_pd_table; - -/* * AMD IOMMU allows up to 2^16 differend protection domains. This is a bitmap * to know which ones are already in use. */ @@ -838,7 +840,18 @@ static void __init free_iommu_all(void) static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h) { spin_lock_init(&iommu->lock); + + /* Add IOMMU to internal data structures */ list_add_tail(&iommu->list, &amd_iommu_list); + iommu->index = amd_iommus_present++; + + if (unlikely(iommu->index >= MAX_IOMMUS)) { + WARN(1, "AMD-Vi: System has more IOMMUs than supported by this driver\n"); + return -ENOSYS; + } + + /* Index is fine - add IOMMU to the array */ + amd_iommus[iommu->index] = iommu; /* * Copy data from ACPI table entry to the iommu struct @@ -868,6 +881,9 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h) init_iommu_from_acpi(iommu, h); init_iommu_devices(iommu); + if (iommu->cap & (1UL << IOMMU_CAP_NPCACHE)) + amd_iommu_np_cache = true; + return pci_enable_device(iommu->dev); } @@ -925,7 +941,7 @@ static int __init init_iommu_all(struct acpi_table_header *table) * ****************************************************************************/ -static int __init iommu_setup_msi(struct amd_iommu *iommu) +static int iommu_setup_msi(struct amd_iommu *iommu) { int r; @@ -1176,19 +1192,10 @@ static struct sys_device device_amd_iommu = { * functions. Finally it prints some information about AMD IOMMUs and * the driver state and enables the hardware. */ -int __init amd_iommu_init(void) +static int __init amd_iommu_init(void) { int i, ret = 0; - - if (no_iommu) { - printk(KERN_INFO "AMD-Vi disabled by kernel command line\n"); - return 0; - } - - if (!amd_iommu_detected) - return -ENODEV; - /* * First parse ACPI tables to find the largest Bus/Dev/Func * we need to handle. Upon this information the shared data @@ -1225,15 +1232,6 @@ int __init amd_iommu_init(void) if (amd_iommu_rlookup_table == NULL) goto free; - /* - * Protection Domain table - maps devices to protection domains - * This table has the same size as the rlookup_table - */ - amd_iommu_pd_table = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, - get_order(rlookup_table_size)); - if (amd_iommu_pd_table == NULL) - goto free; - amd_iommu_pd_alloc_bitmap = (void *)__get_free_pages( GFP_KERNEL | __GFP_ZERO, get_order(MAX_DOMAIN_ID/8)); @@ -1255,6 +1253,8 @@ int __init amd_iommu_init(void) */ amd_iommu_pd_alloc_bitmap[0] = 1; + spin_lock_init(&amd_iommu_pd_lock); + /* * now the data structures are allocated and basically initialized * start the real acpi table scan @@ -1286,17 +1286,12 @@ int __init amd_iommu_init(void) if (iommu_pass_through) goto out; - printk(KERN_INFO "AMD-Vi: device isolation "); - if (amd_iommu_isolate) - printk("enabled\n"); - else - printk("disabled\n"); - if (amd_iommu_unmap_flush) printk(KERN_INFO "AMD-Vi: IO/TLB flush on unmap enabled\n"); else printk(KERN_INFO "AMD-Vi: Lazy IO/TLB flushing enabled\n"); + x86_platform.iommu_shutdown = disable_iommus; out: return ret; @@ -1304,9 +1299,6 @@ free: free_pages((unsigned long)amd_iommu_pd_alloc_bitmap, get_order(MAX_DOMAIN_ID/8)); - free_pages((unsigned long)amd_iommu_pd_table, - get_order(rlookup_table_size)); - free_pages((unsigned long)amd_iommu_rlookup_table, get_order(rlookup_table_size)); @@ -1323,11 +1315,6 @@ free: goto out; } -void amd_iommu_shutdown(void) -{ - disable_iommus(); -} - /**************************************************************************** * * Early detect code. This code runs at IOMMU detection time in the DMA @@ -1342,16 +1329,13 @@ static int __init early_amd_iommu_detect(struct acpi_table_header *table) void __init amd_iommu_detect(void) { - if (swiotlb || no_iommu || (iommu_detected && !gart_iommu_aperture)) + if (no_iommu || (iommu_detected && !gart_iommu_aperture)) return; if (acpi_table_parse("IVRS", early_amd_iommu_detect) == 0) { iommu_detected = 1; amd_iommu_detected = 1; -#ifdef CONFIG_GART_IOMMU - gart_iommu_aperture_disabled = 1; - gart_iommu_aperture = 0; -#endif + x86_init.iommu.iommu_init = amd_iommu_init; } } @@ -1372,10 +1356,6 @@ static int __init parse_amd_iommu_dump(char *str) static int __init parse_amd_iommu_options(char *str) { for (; *str; ++str) { - if (strncmp(str, "isolate", 7) == 0) - amd_iommu_isolate = true; - if (strncmp(str, "share", 5) == 0) - amd_iommu_isolate = false; if (strncmp(str, "fullflush", 9) == 0) amd_iommu_unmap_flush = true; } diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 128111d8ffe0..e0dfb6856aa2 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -28,6 +28,7 @@ #include <asm/pci-direct.h> #include <asm/dma.h> #include <asm/k8.h> +#include <asm/x86_init.h> int gart_iommu_aperture; int gart_iommu_aperture_disabled __initdata; @@ -400,6 +401,7 @@ void __init gart_iommu_hole_init(void) iommu_detected = 1; gart_iommu_aperture = 1; + x86_init.iommu.iommu_init = gart_iommu_init; aper_order = (read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL) >> 1) & 7; aper_size = (32 * 1024 * 1024) << aper_order; @@ -456,7 +458,7 @@ out: if (aper_alloc) { /* Got the aperture from the AGP bridge */ - } else if (swiotlb && !valid_agp) { + } else if (!valid_agp) { /* Do nothing */ } else if ((!no_iommu && max_pfn > MAX_DMA32_PFN) || force_iommu || diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile index da7b7b9f8bd8..565c1bfc507d 100644 --- a/arch/x86/kernel/apic/Makefile +++ b/arch/x86/kernel/apic/Makefile @@ -2,7 +2,7 @@ # Makefile for local APIC drivers and for the IO-APIC code # -obj-$(CONFIG_X86_LOCAL_APIC) += apic.o probe_$(BITS).o ipi.o nmi.o +obj-$(CONFIG_X86_LOCAL_APIC) += apic.o apic_noop.o probe_$(BITS).o ipi.o nmi.o obj-$(CONFIG_X86_IO_APIC) += io_apic.o obj-$(CONFIG_SMP) += ipi.o diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 894aa97f0717..ad8c75b9e453 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -241,28 +241,13 @@ static int modern_apic(void) } /* - * bare function to substitute write operation - * and it's _that_ fast :) - */ -static void native_apic_write_dummy(u32 reg, u32 v) -{ - WARN_ON_ONCE((cpu_has_apic || !disable_apic)); -} - -static u32 native_apic_read_dummy(u32 reg) -{ - WARN_ON_ONCE((cpu_has_apic && !disable_apic)); - return 0; -} - -/* - * right after this call apic->write/read doesn't do anything - * note that there is no restore operation it works one way + * right after this call apic become NOOP driven + * so apic->write/read doesn't do anything */ void apic_disable(void) { - apic->read = native_apic_read_dummy; - apic->write = native_apic_write_dummy; + pr_info("APIC: switched to apic NOOP\n"); + apic = &apic_noop; } void native_apic_wait_icr_idle(void) @@ -459,7 +444,7 @@ static void lapic_timer_setup(enum clock_event_mode mode, v = apic_read(APIC_LVTT); v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR); apic_write(APIC_LVTT, v); - apic_write(APIC_TMICT, 0xffffffff); + apic_write(APIC_TMICT, 0); break; case CLOCK_EVT_MODE_RESUME: /* Nothing to do here */ @@ -1392,14 +1377,11 @@ void __init enable_IR_x2apic(void) unsigned long flags; struct IO_APIC_route_entry **ioapic_entries = NULL; int ret, x2apic_enabled = 0; - int dmar_table_init_ret = 0; + int dmar_table_init_ret; -#ifdef CONFIG_INTR_REMAP dmar_table_init_ret = dmar_table_init(); - if (dmar_table_init_ret) - pr_debug("dmar_table_init() failed with %d:\n", - dmar_table_init_ret); -#endif + if (dmar_table_init_ret && !x2apic_supported()) + return; ioapic_entries = alloc_ioapic_entries(); if (!ioapic_entries) { diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c new file mode 100644 index 000000000000..d9acc3bee0f4 --- /dev/null +++ b/arch/x86/kernel/apic/apic_noop.c @@ -0,0 +1,200 @@ +/* + * NOOP APIC driver. + * + * Does almost nothing and should be substituted by a real apic driver via + * probe routine. + * + * Though in case if apic is disabled (for some reason) we try + * to not uglify the caller's code and allow to call (some) apic routines + * like self-ipi, etc... + */ + +#include <linux/threads.h> +#include <linux/cpumask.h> +#include <linux/module.h> +#include <linux/string.h> +#include <linux/kernel.h> +#include <linux/ctype.h> +#include <linux/init.h> +#include <linux/errno.h> +#include <asm/fixmap.h> +#include <asm/mpspec.h> +#include <asm/apicdef.h> +#include <asm/apic.h> +#include <asm/setup.h> + +#include <linux/smp.h> +#include <asm/ipi.h> + +#include <linux/interrupt.h> +#include <asm/acpi.h> +#include <asm/e820.h> + +static void noop_init_apic_ldr(void) { } +static void noop_send_IPI_mask(const struct cpumask *cpumask, int vector) { } +static void noop_send_IPI_mask_allbutself(const struct cpumask *cpumask, int vector) { } +static void noop_send_IPI_allbutself(int vector) { } +static void noop_send_IPI_all(int vector) { } +static void noop_send_IPI_self(int vector) { } +static void noop_apic_wait_icr_idle(void) { } +static void noop_apic_icr_write(u32 low, u32 id) { } + +static int noop_wakeup_secondary_cpu(int apicid, unsigned long start_eip) +{ + return -1; +} + +static u32 noop_safe_apic_wait_icr_idle(void) +{ + return 0; +} + +static u64 noop_apic_icr_read(void) +{ + return 0; +} + +static int noop_cpu_to_logical_apicid(int cpu) +{ + return 0; +} + +static int noop_phys_pkg_id(int cpuid_apic, int index_msb) +{ + return 0; +} + +static unsigned int noop_get_apic_id(unsigned long x) +{ + return 0; +} + +static int noop_probe(void) +{ + /* + * NOOP apic should not ever be + * enabled via probe routine + */ + return 0; +} + +static int noop_apic_id_registered(void) +{ + /* + * if we would be really "pedantic" + * we should pass read_apic_id() here + * but since NOOP suppose APIC ID = 0 + * lets save a few cycles + */ + return physid_isset(0, phys_cpu_present_map); +} + +static const struct cpumask *noop_target_cpus(void) +{ + /* only BSP here */ + return cpumask_of(0); +} + +static unsigned long noop_check_apicid_used(physid_mask_t *map, int apicid) +{ + return physid_isset(apicid, *map); +} + +static unsigned long noop_check_apicid_present(int bit) +{ + return physid_isset(bit, phys_cpu_present_map); +} + +static void noop_vector_allocation_domain(int cpu, struct cpumask *retmask) +{ + if (cpu != 0) + pr_warning("APIC: Vector allocated for non-BSP cpu\n"); + cpumask_clear(retmask); + cpumask_set_cpu(cpu, retmask); +} + +int noop_apicid_to_node(int logical_apicid) +{ + /* we're always on node 0 */ + return 0; +} + +static u32 noop_apic_read(u32 reg) +{ + WARN_ON_ONCE((cpu_has_apic && !disable_apic)); + return 0; +} + +static void noop_apic_write(u32 reg, u32 v) +{ + WARN_ON_ONCE((cpu_has_apic || !disable_apic)); +} + +struct apic apic_noop = { + .name = "noop", + .probe = noop_probe, + .acpi_madt_oem_check = NULL, + + .apic_id_registered = noop_apic_id_registered, + + .irq_delivery_mode = dest_LowestPrio, + /* logical delivery broadcast to all CPUs: */ + .irq_dest_mode = 1, + + .target_cpus = noop_target_cpus, + .disable_esr = 0, + .dest_logical = APIC_DEST_LOGICAL, + .check_apicid_used = noop_check_apicid_used, + .check_apicid_present = noop_check_apicid_present, + + .vector_allocation_domain = noop_vector_allocation_domain, + .init_apic_ldr = noop_init_apic_ldr, + + .ioapic_phys_id_map = default_ioapic_phys_id_map, + .setup_apic_routing = NULL, + .multi_timer_check = NULL, + .apicid_to_node = noop_apicid_to_node, + + .cpu_to_logical_apicid = noop_cpu_to_logical_apicid, + .cpu_present_to_apicid = default_cpu_present_to_apicid, + .apicid_to_cpu_present = physid_set_mask_of_physid, + + .setup_portio_remap = NULL, + .check_phys_apicid_present = default_check_phys_apicid_present, + .enable_apic_mode = NULL, + + .phys_pkg_id = noop_phys_pkg_id, + + .mps_oem_check = NULL, + + .get_apic_id = noop_get_apic_id, + .set_apic_id = NULL, + .apic_id_mask = 0x0F << 24, + + .cpu_mask_to_apicid = default_cpu_mask_to_apicid, + .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + + .send_IPI_mask = noop_send_IPI_mask, + .send_IPI_mask_allbutself = noop_send_IPI_mask_allbutself, + .send_IPI_allbutself = noop_send_IPI_allbutself, + .send_IPI_all = noop_send_IPI_all, + .send_IPI_self = noop_send_IPI_self, + + .wakeup_secondary_cpu = noop_wakeup_secondary_cpu, + + /* should be safe */ + .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, + .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, + + .wait_for_init_deassert = NULL, + + .smp_callin_clear_local_apic = NULL, + .inquire_remote_apic = NULL, + + .read = noop_apic_read, + .write = noop_apic_write, + .icr_read = noop_apic_icr_read, + .icr_write = noop_apic_icr_write, + .wait_icr_idle = noop_apic_wait_icr_idle, + .safe_wait_icr_idle = noop_safe_apic_wait_icr_idle, +}; diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index 77a06413b6b2..38dcecfa5818 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -35,7 +35,7 @@ static const struct cpumask *bigsmp_target_cpus(void) #endif } -static unsigned long bigsmp_check_apicid_used(physid_mask_t bitmap, int apicid) +static unsigned long bigsmp_check_apicid_used(physid_mask_t *map, int apicid) { return 0; } @@ -93,11 +93,6 @@ static int bigsmp_cpu_present_to_apicid(int mps_cpu) return BAD_APICID; } -static physid_mask_t bigsmp_apicid_to_cpu_present(int phys_apicid) -{ - return physid_mask_of_physid(phys_apicid); -} - /* Mapping from cpu number to logical apicid */ static inline int bigsmp_cpu_to_logical_apicid(int cpu) { @@ -106,10 +101,10 @@ static inline int bigsmp_cpu_to_logical_apicid(int cpu) return cpu_physical_id(cpu); } -static physid_mask_t bigsmp_ioapic_phys_id_map(physid_mask_t phys_map) +static void bigsmp_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap) { /* For clustered we don't have a good way to do this yet - hack */ - return physids_promote(0xFFL); + physids_promote(0xFFL, retmap); } static int bigsmp_check_phys_apicid_present(int phys_apicid) @@ -230,7 +225,7 @@ struct apic apic_bigsmp = { .apicid_to_node = bigsmp_apicid_to_node, .cpu_to_logical_apicid = bigsmp_cpu_to_logical_apicid, .cpu_present_to_apicid = bigsmp_cpu_present_to_apicid, - .apicid_to_cpu_present = bigsmp_apicid_to_cpu_present, + .apicid_to_cpu_present = physid_set_mask_of_physid, .setup_portio_remap = NULL, .check_phys_apicid_present = bigsmp_check_phys_apicid_present, .enable_apic_mode = NULL, diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c index 89174f847b49..e85f8fb7f8e7 100644 --- a/arch/x86/kernel/apic/es7000_32.c +++ b/arch/x86/kernel/apic/es7000_32.c @@ -466,11 +466,11 @@ static const struct cpumask *es7000_target_cpus(void) return cpumask_of(smp_processor_id()); } -static unsigned long -es7000_check_apicid_used(physid_mask_t bitmap, int apicid) +static unsigned long es7000_check_apicid_used(physid_mask_t *map, int apicid) { return 0; } + static unsigned long es7000_check_apicid_present(int bit) { return physid_isset(bit, phys_cpu_present_map); @@ -539,14 +539,10 @@ static int es7000_cpu_present_to_apicid(int mps_cpu) static int cpu_id; -static physid_mask_t es7000_apicid_to_cpu_present(int phys_apicid) +static void es7000_apicid_to_cpu_present(int phys_apicid, physid_mask_t *retmap) { - physid_mask_t mask; - - mask = physid_mask_of_physid(cpu_id); + physid_set_mask_of_physid(cpu_id, retmap); ++cpu_id; - - return mask; } /* Mapping from cpu number to logical apicid */ @@ -561,10 +557,10 @@ static int es7000_cpu_to_logical_apicid(int cpu) #endif } -static physid_mask_t es7000_ioapic_phys_id_map(physid_mask_t phys_map) +static void es7000_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap) { /* For clustered we don't have a good way to do this yet - hack */ - return physids_promote(0xff); + physids_promote(0xFFL, retmap); } static int es7000_check_phys_apicid_present(int cpu_physical_apicid) diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index dc69f28489f5..c0b4468683f9 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -60,8 +60,6 @@ #include <asm/irq_remapping.h> #include <asm/hpet.h> #include <asm/hw_irq.h> -#include <asm/uv/uv_hub.h> -#include <asm/uv/uv_irq.h> #include <asm/apic.h> @@ -140,20 +138,6 @@ static struct irq_pin_list *get_one_free_irq_2_pin(int node) return pin; } -/* - * This is performance-critical, we want to do it O(1) - * - * Most irqs are mapped 1:1 with pins. - */ -struct irq_cfg { - struct irq_pin_list *irq_2_pin; - cpumask_var_t domain; - cpumask_var_t old_domain; - unsigned move_cleanup_count; - u8 vector; - u8 move_in_progress : 1; -}; - /* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */ #ifdef CONFIG_SPARSE_IRQ static struct irq_cfg irq_cfgx[] = { @@ -209,7 +193,7 @@ int __init arch_early_irq_init(void) } #ifdef CONFIG_SPARSE_IRQ -static struct irq_cfg *irq_cfg(unsigned int irq) +struct irq_cfg *irq_cfg(unsigned int irq) { struct irq_cfg *cfg = NULL; struct irq_desc *desc; @@ -361,7 +345,7 @@ void arch_free_chip_data(struct irq_desc *old_desc, struct irq_desc *desc) /* end for move_irq_desc */ #else -static struct irq_cfg *irq_cfg(unsigned int irq) +struct irq_cfg *irq_cfg(unsigned int irq) { return irq < nr_irqs ? irq_cfgx + irq : NULL; } @@ -555,23 +539,41 @@ static void __init replace_pin_at_irq_node(struct irq_cfg *cfg, int node, add_pin_to_irq_node(cfg, node, newapic, newpin); } +static void __io_apic_modify_irq(struct irq_pin_list *entry, + int mask_and, int mask_or, + void (*final)(struct irq_pin_list *entry)) +{ + unsigned int reg, pin; + + pin = entry->pin; + reg = io_apic_read(entry->apic, 0x10 + pin * 2); + reg &= mask_and; + reg |= mask_or; + io_apic_modify(entry->apic, 0x10 + pin * 2, reg); + if (final) + final(entry); +} + static void io_apic_modify_irq(struct irq_cfg *cfg, int mask_and, int mask_or, void (*final)(struct irq_pin_list *entry)) { - int pin; struct irq_pin_list *entry; - for_each_irq_pin(entry, cfg->irq_2_pin) { - unsigned int reg; - pin = entry->pin; - reg = io_apic_read(entry->apic, 0x10 + pin * 2); - reg &= mask_and; - reg |= mask_or; - io_apic_modify(entry->apic, 0x10 + pin * 2, reg); - if (final) - final(entry); - } + for_each_irq_pin(entry, cfg->irq_2_pin) + __io_apic_modify_irq(entry, mask_and, mask_or, final); +} + +static void __mask_and_edge_IO_APIC_irq(struct irq_pin_list *entry) +{ + __io_apic_modify_irq(entry, ~IO_APIC_REDIR_LEVEL_TRIGGER, + IO_APIC_REDIR_MASKED, NULL); +} + +static void __unmask_and_level_IO_APIC_irq(struct irq_pin_list *entry) +{ + __io_apic_modify_irq(entry, ~IO_APIC_REDIR_MASKED, + IO_APIC_REDIR_LEVEL_TRIGGER, NULL); } static void __unmask_IO_APIC_irq(struct irq_cfg *cfg) @@ -595,18 +597,6 @@ static void __mask_IO_APIC_irq(struct irq_cfg *cfg) io_apic_modify_irq(cfg, ~0, IO_APIC_REDIR_MASKED, &io_apic_sync); } -static void __mask_and_edge_IO_APIC_irq(struct irq_cfg *cfg) -{ - io_apic_modify_irq(cfg, ~IO_APIC_REDIR_LEVEL_TRIGGER, - IO_APIC_REDIR_MASKED, NULL); -} - -static void __unmask_and_level_IO_APIC_irq(struct irq_cfg *cfg) -{ - io_apic_modify_irq(cfg, ~IO_APIC_REDIR_MASKED, - IO_APIC_REDIR_LEVEL_TRIGGER, NULL); -} - static void mask_IO_APIC_irq_desc(struct irq_desc *desc) { struct irq_cfg *cfg = desc->chip_data; @@ -1177,7 +1167,7 @@ __assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask) int cpu, err; cpumask_var_t tmp_mask; - if ((cfg->move_in_progress) || cfg->move_cleanup_count) + if (cfg->move_in_progress) return -EBUSY; if (!alloc_cpumask_var(&tmp_mask, GFP_ATOMIC)) @@ -1237,8 +1227,7 @@ next: return err; } -static int -assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask) +int assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask) { int err; unsigned long flags; @@ -1599,9 +1588,6 @@ __apicdebuginit(void) print_IO_APIC(void) struct irq_desc *desc; unsigned int irq; - if (apic_verbosity == APIC_QUIET) - return; - printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries); for (i = 0; i < nr_ioapics; i++) printk(KERN_DEBUG "number of IO-APIC #%d registers: %d.\n", @@ -1708,9 +1694,6 @@ __apicdebuginit(void) print_APIC_field(int base) { int i; - if (apic_verbosity == APIC_QUIET) - return; - printk(KERN_DEBUG); for (i = 0; i < 8; i++) @@ -1724,9 +1707,6 @@ __apicdebuginit(void) print_local_APIC(void *dummy) unsigned int i, v, ver, maxlvt; u64 icr; - if (apic_verbosity == APIC_QUIET) - return; - printk(KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n", smp_processor_id(), hard_smp_processor_id()); v = apic_read(APIC_ID); @@ -1824,13 +1804,19 @@ __apicdebuginit(void) print_local_APIC(void *dummy) printk("\n"); } -__apicdebuginit(void) print_all_local_APICs(void) +__apicdebuginit(void) print_local_APICs(int maxcpu) { int cpu; + if (!maxcpu) + return; + preempt_disable(); - for_each_online_cpu(cpu) + for_each_online_cpu(cpu) { + if (cpu >= maxcpu) + break; smp_call_function_single(cpu, print_local_APIC, NULL, 1); + } preempt_enable(); } @@ -1839,7 +1825,7 @@ __apicdebuginit(void) print_PIC(void) unsigned int v; unsigned long flags; - if (apic_verbosity == APIC_QUIET || !nr_legacy_irqs) + if (!nr_legacy_irqs) return; printk(KERN_DEBUG "\nprinting PIC contents\n"); @@ -1866,21 +1852,41 @@ __apicdebuginit(void) print_PIC(void) printk(KERN_DEBUG "... PIC ELCR: %04x\n", v); } -__apicdebuginit(int) print_all_ICs(void) +static int __initdata show_lapic = 1; +static __init int setup_show_lapic(char *arg) { + int num = -1; + + if (strcmp(arg, "all") == 0) { + show_lapic = CONFIG_NR_CPUS; + } else { + get_option(&arg, &num); + if (num >= 0) + show_lapic = num; + } + + return 1; +} +__setup("show_lapic=", setup_show_lapic); + +__apicdebuginit(int) print_ICs(void) +{ + if (apic_verbosity == APIC_QUIET) + return 0; + print_PIC(); /* don't print out if apic is not there */ if (!cpu_has_apic && !apic_from_smp_config()) return 0; - print_all_local_APICs(); + print_local_APICs(show_lapic); print_IO_APIC(); return 0; } -fs_initcall(print_all_ICs); +fs_initcall(print_ICs); /* Where if anywhere is the i8259 connect in external int mode */ @@ -2031,7 +2037,7 @@ void __init setup_ioapic_ids_from_mpc(void) * This is broken; anything with a real cpu count has to * circumvent this idiocy regardless. */ - phys_id_present_map = apic->ioapic_phys_id_map(phys_cpu_present_map); + apic->ioapic_phys_id_map(&phys_cpu_present_map, &phys_id_present_map); /* * Set the IOAPIC ID to the value stored in the MPC table. @@ -2058,7 +2064,7 @@ void __init setup_ioapic_ids_from_mpc(void) * system must have a unique ID or we get lots of nice * 'stuck on smp_invalidate_needed IPI wait' messages. */ - if (apic->check_apicid_used(phys_id_present_map, + if (apic->check_apicid_used(&phys_id_present_map, mp_ioapics[apic_id].apicid)) { printk(KERN_ERR "BIOS bug, IO-APIC#%d ID %d is already used!...\n", apic_id, mp_ioapics[apic_id].apicid); @@ -2073,7 +2079,7 @@ void __init setup_ioapic_ids_from_mpc(void) mp_ioapics[apic_id].apicid = i; } else { physid_mask_t tmp; - tmp = apic->apicid_to_cpu_present(mp_ioapics[apic_id].apicid); + apic->apicid_to_cpu_present(mp_ioapics[apic_id].apicid, &tmp); apic_printk(APIC_VERBOSE, "Setting %d in the " "phys_id_present_map\n", mp_ioapics[apic_id].apicid); @@ -2228,20 +2234,16 @@ static int ioapic_retrigger_irq(unsigned int irq) */ #ifdef CONFIG_SMP -static void send_cleanup_vector(struct irq_cfg *cfg) +void send_cleanup_vector(struct irq_cfg *cfg) { cpumask_var_t cleanup_mask; if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) { unsigned int i; - cfg->move_cleanup_count = 0; - for_each_cpu_and(i, cfg->old_domain, cpu_online_mask) - cfg->move_cleanup_count++; for_each_cpu_and(i, cfg->old_domain, cpu_online_mask) apic->send_IPI_mask(cpumask_of(i), IRQ_MOVE_CLEANUP_VECTOR); } else { cpumask_and(cleanup_mask, cfg->old_domain, cpu_online_mask); - cfg->move_cleanup_count = cpumask_weight(cleanup_mask); apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR); free_cpumask_var(cleanup_mask); } @@ -2272,15 +2274,12 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq } } -static int -assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask); - /* * Either sets desc->affinity to a valid value, and returns * ->cpu_mask_to_apicid of that, or returns BAD_APICID and * leaves desc->affinity untouched. */ -static unsigned int +unsigned int set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask) { struct irq_cfg *cfg; @@ -2433,8 +2432,6 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void) cfg = irq_cfg(irq); spin_lock(&desc->lock); - if (!cfg->move_cleanup_count) - goto unlock; if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain)) goto unlock; @@ -2452,7 +2449,6 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void) goto unlock; } __get_cpu_var(vector_irq)[vector] = -1; - cfg->move_cleanup_count--; unlock: spin_unlock(&desc->lock); } @@ -2460,21 +2456,33 @@ unlock: irq_exit(); } -static void irq_complete_move(struct irq_desc **descp) +static void __irq_complete_move(struct irq_desc **descp, unsigned vector) { struct irq_desc *desc = *descp; struct irq_cfg *cfg = desc->chip_data; - unsigned vector, me; + unsigned me; if (likely(!cfg->move_in_progress)) return; - vector = ~get_irq_regs()->orig_ax; me = smp_processor_id(); if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain)) send_cleanup_vector(cfg); } + +static void irq_complete_move(struct irq_desc **descp) +{ + __irq_complete_move(descp, ~get_irq_regs()->orig_ax); +} + +void irq_force_complete_move(int irq) +{ + struct irq_desc *desc = irq_to_desc(irq); + struct irq_cfg *cfg = desc->chip_data; + + __irq_complete_move(&desc, cfg->vector); +} #else static inline void irq_complete_move(struct irq_desc **descp) {} #endif @@ -2490,6 +2498,59 @@ static void ack_apic_edge(unsigned int irq) atomic_t irq_mis_count; +/* + * IO-APIC versions below 0x20 don't support EOI register. + * For the record, here is the information about various versions: + * 0Xh 82489DX + * 1Xh I/OAPIC or I/O(x)APIC which are not PCI 2.2 Compliant + * 2Xh I/O(x)APIC which is PCI 2.2 Compliant + * 30h-FFh Reserved + * + * Some of the Intel ICH Specs (ICH2 to ICH5) documents the io-apic + * version as 0x2. This is an error with documentation and these ICH chips + * use io-apic's of version 0x20. + * + * For IO-APIC's with EOI register, we use that to do an explicit EOI. + * Otherwise, we simulate the EOI message manually by changing the trigger + * mode to edge and then back to level, with RTE being masked during this. +*/ +static void __eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg) +{ + struct irq_pin_list *entry; + + for_each_irq_pin(entry, cfg->irq_2_pin) { + if (mp_ioapics[entry->apic].apicver >= 0x20) { + /* + * Intr-remapping uses pin number as the virtual vector + * in the RTE. Actual vector is programmed in + * intr-remapping table entry. Hence for the io-apic + * EOI we use the pin number. + */ + if (irq_remapped(irq)) + io_apic_eoi(entry->apic, entry->pin); + else + io_apic_eoi(entry->apic, cfg->vector); + } else { + __mask_and_edge_IO_APIC_irq(entry); + __unmask_and_level_IO_APIC_irq(entry); + } + } +} + +static void eoi_ioapic_irq(struct irq_desc *desc) +{ + struct irq_cfg *cfg; + unsigned long flags; + unsigned int irq; + + irq = desc->irq; + cfg = desc->chip_data; + + spin_lock_irqsave(&ioapic_lock, flags); + __eoi_ioapic_irq(irq, cfg); + spin_unlock_irqrestore(&ioapic_lock, flags); +} + static void ack_apic_level(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); @@ -2525,6 +2586,19 @@ static void ack_apic_level(unsigned int irq) * level-triggered interrupt. We mask the source for the time of the * operation to prevent an edge-triggered interrupt escaping meanwhile. * The idea is from Manfred Spraul. --macro + * + * Also in the case when cpu goes offline, fixup_irqs() will forward + * any unhandled interrupt on the offlined cpu to the new cpu + * destination that is handling the corresponding interrupt. This + * interrupt forwarding is done via IPI's. Hence, in this case also + * level-triggered io-apic interrupt will be seen as an edge + * interrupt in the IRR. And we can't rely on the cpu's EOI + * to be broadcasted to the IO-APIC's which will clear the remoteIRR + * corresponding to the level-triggered interrupt. Hence on IO-APIC's + * supporting EOI register, we do an explicit EOI to clear the + * remote IRR and on IO-APIC's which don't have an EOI register, + * we use the above logic (mask+edge followed by unmask+level) from + * Manfred Spraul to clear the remote IRR. */ cfg = desc->chip_data; i = cfg->vector; @@ -2536,6 +2610,19 @@ static void ack_apic_level(unsigned int irq) */ ack_APIC_irq(); + /* + * Tail end of clearing remote IRR bit (either by delivering the EOI + * message via io-apic EOI register write or simulating it using + * mask+edge followed by unnask+level logic) manually when the + * level triggered interrupt is seen as the edge triggered interrupt + * at the cpu. + */ + if (!(v & (1 << (i & 0x1f)))) { + atomic_inc(&irq_mis_count); + + eoi_ioapic_irq(desc); + } + /* Now we can move and renable the irq */ if (unlikely(do_unmask_irq)) { /* Only migrate the irq if the ack has been received. @@ -2569,41 +2656,9 @@ static void ack_apic_level(unsigned int irq) move_masked_irq(irq); unmask_IO_APIC_irq_desc(desc); } - - /* Tail end of version 0x11 I/O APIC bug workaround */ - if (!(v & (1 << (i & 0x1f)))) { - atomic_inc(&irq_mis_count); - spin_lock(&ioapic_lock); - __mask_and_edge_IO_APIC_irq(cfg); - __unmask_and_level_IO_APIC_irq(cfg); - spin_unlock(&ioapic_lock); - } } #ifdef CONFIG_INTR_REMAP -static void __eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg) -{ - struct irq_pin_list *entry; - - for_each_irq_pin(entry, cfg->irq_2_pin) - io_apic_eoi(entry->apic, entry->pin); -} - -static void -eoi_ioapic_irq(struct irq_desc *desc) -{ - struct irq_cfg *cfg; - unsigned long flags; - unsigned int irq; - - irq = desc->irq; - cfg = desc->chip_data; - - spin_lock_irqsave(&ioapic_lock, flags); - __eoi_ioapic_irq(irq, cfg); - spin_unlock_irqrestore(&ioapic_lock, flags); -} - static void ir_ack_apic_edge(unsigned int irq) { ack_APIC_irq(); @@ -3157,6 +3212,7 @@ unsigned int create_irq_nr(unsigned int irq_want, int node) continue; desc_new = move_irq_desc(desc_new, node); + cfg_new = desc_new->chip_data; if (__assign_irq_vector(new, cfg_new, apic->target_cpus()) == 0) irq = new; @@ -3708,75 +3764,6 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev) } #endif /* CONFIG_HT_IRQ */ -#ifdef CONFIG_X86_UV -/* - * Re-target the irq to the specified CPU and enable the specified MMR located - * on the specified blade to allow the sending of MSIs to the specified CPU. - */ -int arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade, - unsigned long mmr_offset) -{ - const struct cpumask *eligible_cpu = cpumask_of(cpu); - struct irq_cfg *cfg; - int mmr_pnode; - unsigned long mmr_value; - struct uv_IO_APIC_route_entry *entry; - unsigned long flags; - int err; - - BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long)); - - cfg = irq_cfg(irq); - - err = assign_irq_vector(irq, cfg, eligible_cpu); - if (err != 0) - return err; - - spin_lock_irqsave(&vector_lock, flags); - set_irq_chip_and_handler_name(irq, &uv_irq_chip, handle_percpu_irq, - irq_name); - spin_unlock_irqrestore(&vector_lock, flags); - - mmr_value = 0; - entry = (struct uv_IO_APIC_route_entry *)&mmr_value; - entry->vector = cfg->vector; - entry->delivery_mode = apic->irq_delivery_mode; - entry->dest_mode = apic->irq_dest_mode; - entry->polarity = 0; - entry->trigger = 0; - entry->mask = 0; - entry->dest = apic->cpu_mask_to_apicid(eligible_cpu); - - mmr_pnode = uv_blade_to_pnode(mmr_blade); - uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value); - - if (cfg->move_in_progress) - send_cleanup_vector(cfg); - - return irq; -} - -/* - * Disable the specified MMR located on the specified blade so that MSIs are - * longer allowed to be sent. - */ -void arch_disable_uv_irq(int mmr_blade, unsigned long mmr_offset) -{ - unsigned long mmr_value; - struct uv_IO_APIC_route_entry *entry; - int mmr_pnode; - - BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long)); - - mmr_value = 0; - entry = (struct uv_IO_APIC_route_entry *)&mmr_value; - entry->mask = 1; - - mmr_pnode = uv_blade_to_pnode(mmr_blade); - uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value); -} -#endif /* CONFIG_X86_64 */ - int __init io_apic_get_redir_entries (int ioapic) { union IO_APIC_reg_01 reg_01; @@ -3944,7 +3931,7 @@ int __init io_apic_get_unique_id(int ioapic, int apic_id) */ if (physids_empty(apic_id_map)) - apic_id_map = apic->ioapic_phys_id_map(phys_cpu_present_map); + apic->ioapic_phys_id_map(&phys_cpu_present_map, &apic_id_map); spin_lock_irqsave(&ioapic_lock, flags); reg_00.raw = io_apic_read(ioapic, 0); @@ -3960,10 +3947,10 @@ int __init io_apic_get_unique_id(int ioapic, int apic_id) * Every APIC in a system must have a unique ID or we get lots of nice * 'stuck on smp_invalidate_needed IPI wait' messages. */ - if (apic->check_apicid_used(apic_id_map, apic_id)) { + if (apic->check_apicid_used(&apic_id_map, apic_id)) { for (i = 0; i < get_physical_broadcast(); i++) { - if (!apic->check_apicid_used(apic_id_map, i)) + if (!apic->check_apicid_used(&apic_id_map, i)) break; } @@ -3976,7 +3963,7 @@ int __init io_apic_get_unique_id(int ioapic, int apic_id) apic_id = i; } - tmp = apic->apicid_to_cpu_present(apic_id); + apic->apicid_to_cpu_present(apic_id, &tmp); physids_or(apic_id_map, apic_id_map, tmp); if (reg_00.bits.ID != apic_id) { @@ -4106,7 +4093,7 @@ static struct resource * __init ioapic_setup_resources(int nr_ioapics) for (i = 0; i < nr_ioapics; i++) { res[i].name = mem; res[i].flags = IORESOURCE_MEM | IORESOURCE_BUSY; - sprintf(mem, "IOAPIC %u", i); + snprintf(mem, IOAPIC_RESOURCE_NAME_SIZE, "IOAPIC %u", i); mem += IOAPIC_RESOURCE_NAME_SIZE; } @@ -4140,18 +4127,17 @@ void __init ioapic_init_mappings(void) #ifdef CONFIG_X86_32 fake_ioapic_page: #endif - ioapic_phys = (unsigned long) - alloc_bootmem_pages(PAGE_SIZE); + ioapic_phys = (unsigned long)alloc_bootmem_pages(PAGE_SIZE); ioapic_phys = __pa(ioapic_phys); } set_fixmap_nocache(idx, ioapic_phys); - apic_printk(APIC_VERBOSE, - "mapped IOAPIC to %08lx (%08lx)\n", - __fix_to_virt(idx), ioapic_phys); + apic_printk(APIC_VERBOSE, "mapped IOAPIC to %08lx (%08lx)\n", + __fix_to_virt(idx) + (ioapic_phys & ~PAGE_MASK), + ioapic_phys); idx++; ioapic_res->start = ioapic_phys; - ioapic_res->end = ioapic_phys + (4 * 1024) - 1; + ioapic_res->end = ioapic_phys + IO_APIC_SLOT_SIZE - 1; ioapic_res++; } } diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c index 7ff61d6a188a..6389432a9dbf 100644 --- a/arch/x86/kernel/apic/nmi.c +++ b/arch/x86/kernel/apic/nmi.c @@ -39,7 +39,8 @@ int unknown_nmi_panic; int nmi_watchdog_enabled; -static cpumask_t backtrace_mask __read_mostly; +/* For reliability, we're prepared to waste bits here. */ +static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly; /* nmi_active: * >0: the lapic NMI watchdog is active, but can be disabled @@ -414,7 +415,7 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason) } /* We can be called before check_nmi_watchdog, hence NULL check. */ - if (cpumask_test_cpu(cpu, &backtrace_mask)) { + if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) { static DEFINE_SPINLOCK(lock); /* Serialise the printks */ spin_lock(&lock); @@ -422,7 +423,7 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason) show_regs(regs); dump_stack(); spin_unlock(&lock); - cpumask_clear_cpu(cpu, &backtrace_mask); + cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask)); rc = 1; } @@ -558,14 +559,14 @@ void arch_trigger_all_cpu_backtrace(void) { int i; - cpumask_copy(&backtrace_mask, cpu_online_mask); + cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask); printk(KERN_INFO "sending NMI to all CPUs:\n"); apic->send_IPI_all(NMI_VECTOR); /* Wait for up to 10 seconds for all CPUs to do the backtrace */ for (i = 0; i < 10 * 1000; i++) { - if (cpumask_empty(&backtrace_mask)) + if (cpumask_empty(to_cpumask(backtrace_mask))) break; mdelay(1); } diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index efa00e2b8505..07cdbdcd7a92 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -334,10 +334,9 @@ static inline const struct cpumask *numaq_target_cpus(void) return cpu_all_mask; } -static inline unsigned long -numaq_check_apicid_used(physid_mask_t bitmap, int apicid) +static unsigned long numaq_check_apicid_used(physid_mask_t *map, int apicid) { - return physid_isset(apicid, bitmap); + return physid_isset(apicid, *map); } static inline unsigned long numaq_check_apicid_present(int bit) @@ -371,10 +370,10 @@ static inline int numaq_multi_timer_check(int apic, int irq) return apic != 0 && irq == 0; } -static inline physid_mask_t numaq_ioapic_phys_id_map(physid_mask_t phys_map) +static inline void numaq_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap) { /* We don't have a good way to do this yet - hack */ - return physids_promote(0xFUL); + return physids_promote(0xFUL, retmap); } static inline int numaq_cpu_to_logical_apicid(int cpu) @@ -402,12 +401,12 @@ static inline int numaq_apicid_to_node(int logical_apicid) return logical_apicid >> 4; } -static inline physid_mask_t numaq_apicid_to_cpu_present(int logical_apicid) +static void numaq_apicid_to_cpu_present(int logical_apicid, physid_mask_t *retmap) { int node = numaq_apicid_to_node(logical_apicid); int cpu = __ffs(logical_apicid & 0xf); - return physid_mask_of_physid(cpu + 4*node); + physid_set_mask_of_physid(cpu + 4*node, retmap); } /* Where the IO area was mapped on multiquad, always 0 otherwise */ diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 0c0182cc947d..1a6559f6768c 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -108,7 +108,7 @@ struct apic apic_default = { .apicid_to_node = default_apicid_to_node, .cpu_to_logical_apicid = default_cpu_to_logical_apicid, .cpu_present_to_apicid = default_cpu_present_to_apicid, - .apicid_to_cpu_present = default_apicid_to_cpu_present, + .apicid_to_cpu_present = physid_set_mask_of_physid, .setup_portio_remap = NULL, .check_phys_apicid_present = default_check_phys_apicid_present, .enable_apic_mode = NULL, diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c index 645ecc4ff0be..9b419263d90d 100644 --- a/arch/x86/kernel/apic/summit_32.c +++ b/arch/x86/kernel/apic/summit_32.c @@ -183,7 +183,7 @@ static const struct cpumask *summit_target_cpus(void) return cpumask_of(0); } -static unsigned long summit_check_apicid_used(physid_mask_t bitmap, int apicid) +static unsigned long summit_check_apicid_used(physid_mask_t *map, int apicid) { return 0; } @@ -261,15 +261,15 @@ static int summit_cpu_present_to_apicid(int mps_cpu) return BAD_APICID; } -static physid_mask_t summit_ioapic_phys_id_map(physid_mask_t phys_id_map) +static void summit_ioapic_phys_id_map(physid_mask_t *phys_id_map, physid_mask_t *retmap) { /* For clustered we don't have a good way to do this yet - hack */ - return physids_promote(0x0F); + physids_promote(0x0FL, retmap); } -static physid_mask_t summit_apicid_to_cpu_present(int apicid) +static void summit_apicid_to_cpu_present(int apicid, physid_mask_t *retmap) { - return physid_mask_of_physid(0); + physid_set_mask_of_physid(0, retmap); } static int summit_check_phys_apicid_present(int physical_apicid) diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 326c25477d3d..130c4b934877 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -409,6 +409,12 @@ static __init void map_mmioh_high(int max_pnode) map_high("MMIOH", mmioh.s.base, shift, max_pnode, map_uc); } +static __init void map_low_mmrs(void) +{ + init_extra_mapping_uc(UV_GLOBAL_MMR32_BASE, UV_GLOBAL_MMR32_SIZE); + init_extra_mapping_uc(UV_LOCAL_MMR_BASE, UV_LOCAL_MMR_SIZE); +} + static __init void uv_rtc_init(void) { long status; @@ -550,6 +556,8 @@ void __init uv_system_init(void) unsigned long mmr_base, present, paddr; unsigned short pnode_mask; + map_low_mmrs(); + m_n_config.v = uv_read_local_mmr(UVH_SI_ADDR_MAP_CONFIG); m_val = m_n_config.s.m_skt; n_val = m_n_config.s.n_skt; diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 151ace69a5aa..b5b6b23bce53 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -204,7 +204,6 @@ #include <linux/module.h> #include <linux/poll.h> -#include <linux/smp_lock.h> #include <linux/types.h> #include <linux/stddef.h> #include <linux/timer.h> @@ -403,6 +402,7 @@ static DECLARE_WAIT_QUEUE_HEAD(apm_waitqueue); static DECLARE_WAIT_QUEUE_HEAD(apm_suspend_waitqueue); static struct apm_user *user_list; static DEFINE_SPINLOCK(user_list_lock); +static DEFINE_MUTEX(apm_mutex); /* * Set up a segment that references the real mode segment 0x40 @@ -1531,7 +1531,7 @@ static long do_ioctl(struct file *filp, u_int cmd, u_long arg) return -EPERM; switch (cmd) { case APM_IOC_STANDBY: - lock_kernel(); + mutex_lock(&apm_mutex); if (as->standbys_read > 0) { as->standbys_read--; as->standbys_pending--; @@ -1540,10 +1540,10 @@ static long do_ioctl(struct file *filp, u_int cmd, u_long arg) queue_event(APM_USER_STANDBY, as); if (standbys_pending <= 0) standby(); - unlock_kernel(); + mutex_unlock(&apm_mutex); break; case APM_IOC_SUSPEND: - lock_kernel(); + mutex_lock(&apm_mutex); if (as->suspends_read > 0) { as->suspends_read--; as->suspends_pending--; @@ -1552,13 +1552,14 @@ static long do_ioctl(struct file *filp, u_int cmd, u_long arg) queue_event(APM_USER_SUSPEND, as); if (suspends_pending <= 0) { ret = suspend(1); + mutex_unlock(&apm_mutex); } else { as->suspend_wait = 1; + mutex_unlock(&apm_mutex); wait_event_interruptible(apm_suspend_waitqueue, as->suspend_wait == 0); ret = as->suspend_result; } - unlock_kernel(); return ret; default: return -ENOTTY; @@ -1608,12 +1609,10 @@ static int do_open(struct inode *inode, struct file *filp) { struct apm_user *as; - lock_kernel(); as = kmalloc(sizeof(*as), GFP_KERNEL); if (as == NULL) { printk(KERN_ERR "apm: cannot allocate struct of size %d bytes\n", sizeof(*as)); - unlock_kernel(); return -ENOMEM; } as->magic = APM_BIOS_MAGIC; @@ -1635,7 +1634,6 @@ static int do_open(struct inode *inode, struct file *filp) user_list = as; spin_unlock(&user_list_lock); filp->private_data = as; - unlock_kernel(); return 0; } diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 68537e957a9b..1d2cb383410e 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -5,6 +5,7 @@ # Don't trace early stages of a secondary CPU boot ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_common.o = -pg +CFLAGS_REMOVE_perf_event.o = -pg endif # Make sure load_percpu_segment has no stackprotector diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index c910a716a71c..7128b3799cec 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -535,7 +535,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) } } - display_cacheinfo(c); + cpu_detect_cache_sizes(c); /* Multi core CPU? */ if (c->extended_cpuid_level >= 0x80000008) { diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index c95e831bb095..e58d978e0758 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -294,7 +294,7 @@ static void __cpuinit init_c3(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_REP_GOOD); } - display_cacheinfo(c); + cpu_detect_cache_sizes(c); } enum { diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index cc25c2b4a567..a4ec8b647544 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -61,7 +61,7 @@ void __init setup_cpu_local_masks(void) static void __cpuinit default_init(struct cpuinfo_x86 *c) { #ifdef CONFIG_X86_64 - display_cacheinfo(c); + cpu_detect_cache_sizes(c); #else /* Not much we can do here... */ /* Check if at least it has cpuid */ @@ -383,7 +383,7 @@ static void __cpuinit get_model_name(struct cpuinfo_x86 *c) } } -void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c) +void __cpuinit cpu_detect_cache_sizes(struct cpuinfo_x86 *c) { unsigned int n, dummy, ebx, ecx, edx, l2size; @@ -391,8 +391,6 @@ void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c) if (n >= 0x80000005) { cpuid(0x80000005, &dummy, &ebx, &ecx, &edx); - printk(KERN_INFO "CPU: L1 I Cache: %dK (%d bytes/line), D cache %dK (%d bytes/line)\n", - edx>>24, edx&0xFF, ecx>>24, ecx&0xFF); c->x86_cache_size = (ecx>>24) + (edx>>24); #ifdef CONFIG_X86_64 /* On K8 L1 TLB is inclusive, so don't count it */ @@ -422,9 +420,6 @@ void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c) #endif c->x86_cache_size = l2size; - - printk(KERN_INFO "CPU: L2 Cache: %dK (%d bytes/line)\n", - l2size, ecx & 0xFF); } void __cpuinit detect_ht(struct cpuinfo_x86 *c) @@ -659,24 +654,31 @@ void __init early_cpu_init(void) const struct cpu_dev *const *cdev; int count = 0; +#ifdef PROCESSOR_SELECT printk(KERN_INFO "KERNEL supported cpus:\n"); +#endif + for (cdev = __x86_cpu_dev_start; cdev < __x86_cpu_dev_end; cdev++) { const struct cpu_dev *cpudev = *cdev; - unsigned int j; if (count >= X86_VENDOR_NUM) break; cpu_devs[count] = cpudev; count++; - for (j = 0; j < 2; j++) { - if (!cpudev->c_ident[j]) - continue; - printk(KERN_INFO " %s %s\n", cpudev->c_vendor, - cpudev->c_ident[j]); +#ifdef PROCESSOR_SELECT + { + unsigned int j; + + for (j = 0; j < 2; j++) { + if (!cpudev->c_ident[j]) + continue; + printk(KERN_INFO " %s %s\n", cpudev->c_vendor, + cpudev->c_ident[j]); + } } +#endif } - early_identify_cpu(&boot_cpu_data); } @@ -837,10 +839,8 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c) boot_cpu_data.x86_capability[i] &= c->x86_capability[i]; } -#ifdef CONFIG_X86_MCE /* Init Machine Check Exception if available. */ - mcheck_init(c); -#endif + mcheck_cpu_init(c); select_idle_routine(c); diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 6de9a908e400..3624e8a0f71b 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -32,6 +32,6 @@ struct cpu_dev { extern const struct cpu_dev *const __x86_cpu_dev_start[], *const __x86_cpu_dev_end[]; -extern void display_cacheinfo(struct cpuinfo_x86 *c); +extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c); #endif diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index 19807b89f058..4fbd384fb645 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -373,7 +373,7 @@ static void __cpuinit init_nsc(struct cpuinfo_x86 *c) /* Handle the GX (Formally known as the GX2) */ if (c->x86 == 5 && c->x86_model == 5) - display_cacheinfo(c); + cpu_detect_cache_sizes(c); else init_cyrix(c); } diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 804c40e2bc3e..0df4c2b7107f 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -488,22 +488,6 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) #endif } - if (trace) - printk(KERN_INFO "CPU: Trace cache: %dK uops", trace); - else if (l1i) - printk(KERN_INFO "CPU: L1 I cache: %dK", l1i); - - if (l1d) - printk(KERN_CONT ", L1 D cache: %dK\n", l1d); - else - printk(KERN_CONT "\n"); - - if (l2) - printk(KERN_INFO "CPU: L2 cache: %dK\n", l2); - - if (l3) - printk(KERN_INFO "CPU: L3 cache: %dK\n", l3); - c->x86_cache_size = l3 ? l3 : (l2 ? l2 : (l1i+l1d)); return l2; diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 721a77ca8115..0bcaa3875863 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -46,6 +46,9 @@ #include "mce-internal.h" +#define CREATE_TRACE_POINTS +#include <trace/events/mce.h> + int mce_disabled __read_mostly; #define MISC_MCELOG_MINOR 227 @@ -85,18 +88,26 @@ static DECLARE_WAIT_QUEUE_HEAD(mce_wait); static DEFINE_PER_CPU(struct mce, mces_seen); static int cpu_missing; -static void default_decode_mce(struct mce *m) +/* + * CPU/chipset specific EDAC code can register a notifier call here to print + * MCE errors in a human-readable form. + */ +ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain); +EXPORT_SYMBOL_GPL(x86_mce_decoder_chain); + +static int default_decode_mce(struct notifier_block *nb, unsigned long val, + void *data) { pr_emerg("No human readable MCE decoding support on this CPU type.\n"); pr_emerg("Run the message through 'mcelog --ascii' to decode.\n"); + + return NOTIFY_STOP; } -/* - * CPU/chipset specific EDAC code can register a callback here to print - * MCE errors in a human-readable form: - */ -void (*x86_mce_decode_callback)(struct mce *m) = default_decode_mce; -EXPORT_SYMBOL(x86_mce_decode_callback); +static struct notifier_block mce_dec_nb = { + .notifier_call = default_decode_mce, + .priority = -1, +}; /* MCA banks polled by the period polling timer for corrected events */ DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = { @@ -141,6 +152,9 @@ void mce_log(struct mce *mce) { unsigned next, entry; + /* Emit the trace record: */ + trace_mce_record(mce); + mce->finished = 0; wmb(); for (;;) { @@ -204,9 +218,9 @@ static void print_mce(struct mce *m) /* * Print out human-readable details about the MCE error, - * (if the CPU has an implementation for that): + * (if the CPU has an implementation for that) */ - x86_mce_decode_callback(m); + atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m); } static void print_mce_head(void) @@ -1122,7 +1136,7 @@ static int check_interval = 5 * 60; /* 5 minutes */ static DEFINE_PER_CPU(int, mce_next_interval); /* in jiffies */ static DEFINE_PER_CPU(struct timer_list, mce_timer); -static void mcheck_timer(unsigned long data) +static void mce_start_timer(unsigned long data) { struct timer_list *t = &per_cpu(mce_timer, data); int *n; @@ -1187,7 +1201,7 @@ int mce_notify_irq(void) } EXPORT_SYMBOL_GPL(mce_notify_irq); -static int mce_banks_init(void) +static int __cpuinit __mcheck_cpu_mce_banks_init(void) { int i; @@ -1206,7 +1220,7 @@ static int mce_banks_init(void) /* * Initialize Machine Checks for a CPU. */ -static int __cpuinit mce_cap_init(void) +static int __cpuinit __mcheck_cpu_cap_init(void) { unsigned b; u64 cap; @@ -1228,7 +1242,7 @@ static int __cpuinit mce_cap_init(void) WARN_ON(banks != 0 && b != banks); banks = b; if (!mce_banks) { - int err = mce_banks_init(); + int err = __mcheck_cpu_mce_banks_init(); if (err) return err; @@ -1244,7 +1258,7 @@ static int __cpuinit mce_cap_init(void) return 0; } -static void mce_init(void) +static void __mcheck_cpu_init_generic(void) { mce_banks_t all_banks; u64 cap; @@ -1273,7 +1287,7 @@ static void mce_init(void) } /* Add per CPU specific workarounds here */ -static int __cpuinit mce_cpu_quirks(struct cpuinfo_x86 *c) +static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) { if (c->x86_vendor == X86_VENDOR_UNKNOWN) { pr_info("MCE: unknown CPU type - not enabling MCE support.\n"); @@ -1341,7 +1355,7 @@ static int __cpuinit mce_cpu_quirks(struct cpuinfo_x86 *c) return 0; } -static void __cpuinit mce_ancient_init(struct cpuinfo_x86 *c) +static void __cpuinit __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c) { if (c->x86 != 5) return; @@ -1355,7 +1369,7 @@ static void __cpuinit mce_ancient_init(struct cpuinfo_x86 *c) } } -static void mce_cpu_features(struct cpuinfo_x86 *c) +static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) { switch (c->x86_vendor) { case X86_VENDOR_INTEL: @@ -1369,7 +1383,7 @@ static void mce_cpu_features(struct cpuinfo_x86 *c) } } -static void mce_init_timer(void) +static void __mcheck_cpu_init_timer(void) { struct timer_list *t = &__get_cpu_var(mce_timer); int *n = &__get_cpu_var(mce_next_interval); @@ -1380,7 +1394,7 @@ static void mce_init_timer(void) *n = check_interval * HZ; if (!*n) return; - setup_timer(t, mcheck_timer, smp_processor_id()); + setup_timer(t, mce_start_timer, smp_processor_id()); t->expires = round_jiffies(jiffies + *n); add_timer_on(t, smp_processor_id()); } @@ -1400,27 +1414,28 @@ void (*machine_check_vector)(struct pt_regs *, long error_code) = * Called for each booted CPU to set up machine checks. * Must be called with preempt off: */ -void __cpuinit mcheck_init(struct cpuinfo_x86 *c) +void __cpuinit mcheck_cpu_init(struct cpuinfo_x86 *c) { if (mce_disabled) return; - mce_ancient_init(c); + __mcheck_cpu_ancient_init(c); if (!mce_available(c)) return; - if (mce_cap_init() < 0 || mce_cpu_quirks(c) < 0) { + if (__mcheck_cpu_cap_init() < 0 || __mcheck_cpu_apply_quirks(c) < 0) { mce_disabled = 1; return; } machine_check_vector = do_machine_check; - mce_init(); - mce_cpu_features(c); - mce_init_timer(); + __mcheck_cpu_init_generic(); + __mcheck_cpu_init_vendor(c); + __mcheck_cpu_init_timer(); INIT_WORK(&__get_cpu_var(mce_work), mce_process_work); + } /* @@ -1640,6 +1655,15 @@ static int __init mcheck_enable(char *str) } __setup("mce", mcheck_enable); +int __init mcheck_init(void) +{ + atomic_notifier_chain_register(&x86_mce_decoder_chain, &mce_dec_nb); + + mcheck_intel_therm_init(); + + return 0; +} + /* * Sysfs support */ @@ -1648,7 +1672,7 @@ __setup("mce", mcheck_enable); * Disable machine checks on suspend and shutdown. We can't really handle * them later. */ -static int mce_disable(void) +static int mce_disable_error_reporting(void) { int i; @@ -1663,12 +1687,12 @@ static int mce_disable(void) static int mce_suspend(struct sys_device *dev, pm_message_t state) { - return mce_disable(); + return mce_disable_error_reporting(); } static int mce_shutdown(struct sys_device *dev) { - return mce_disable(); + return mce_disable_error_reporting(); } /* @@ -1678,8 +1702,8 @@ static int mce_shutdown(struct sys_device *dev) */ static int mce_resume(struct sys_device *dev) { - mce_init(); - mce_cpu_features(¤t_cpu_data); + __mcheck_cpu_init_generic(); + __mcheck_cpu_init_vendor(¤t_cpu_data); return 0; } @@ -1689,8 +1713,8 @@ static void mce_cpu_restart(void *data) del_timer_sync(&__get_cpu_var(mce_timer)); if (!mce_available(¤t_cpu_data)) return; - mce_init(); - mce_init_timer(); + __mcheck_cpu_init_generic(); + __mcheck_cpu_init_timer(); } /* Reinit MCEs after user configuration changes */ @@ -1716,7 +1740,7 @@ static void mce_enable_ce(void *all) cmci_reenable(); cmci_recheck(); if (all) - mce_init_timer(); + __mcheck_cpu_init_timer(); } static struct sysdev_class mce_sysclass = { @@ -1929,13 +1953,14 @@ static __cpuinit void mce_remove_device(unsigned int cpu) } /* Make sure there are no machine checks on offlined CPUs. */ -static void mce_disable_cpu(void *h) +static void __cpuinit mce_disable_cpu(void *h) { unsigned long action = *(unsigned long *)h; int i; if (!mce_available(¤t_cpu_data)) return; + if (!(action & CPU_TASKS_FROZEN)) cmci_clear(); for (i = 0; i < banks; i++) { @@ -1946,7 +1971,7 @@ static void mce_disable_cpu(void *h) } } -static void mce_reenable_cpu(void *h) +static void __cpuinit mce_reenable_cpu(void *h) { unsigned long action = *(unsigned long *)h; int i; @@ -2025,7 +2050,7 @@ static __init void mce_init_banks(void) } } -static __init int mce_init_device(void) +static __init int mcheck_init_device(void) { int err; int i = 0; @@ -2053,7 +2078,7 @@ static __init int mce_init_device(void) return err; } -device_initcall(mce_init_device); +device_initcall(mcheck_init_device); /* * Old style boot options parsing. Only for compatibility. @@ -2101,7 +2126,7 @@ static int fake_panic_set(void *data, u64 val) DEFINE_SIMPLE_ATTRIBUTE(fake_panic_fops, fake_panic_get, fake_panic_set, "%llu\n"); -static int __init mce_debugfs_init(void) +static int __init mcheck_debugfs_init(void) { struct dentry *dmce, *ffake_panic; @@ -2115,5 +2140,5 @@ static int __init mce_debugfs_init(void) return 0; } -late_initcall(mce_debugfs_init); +late_initcall(mcheck_debugfs_init); #endif diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index b3a1dba75330..4fef985fc221 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -49,6 +49,8 @@ static DEFINE_PER_CPU(struct thermal_state, thermal_state); static atomic_t therm_throt_en = ATOMIC_INIT(0); +static u32 lvtthmr_init __read_mostly; + #ifdef CONFIG_SYSFS #define define_therm_throt_sysdev_one_ro(_name) \ static SYSDEV_ATTR(_name, 0444, therm_throt_sysdev_show_##_name, NULL) @@ -254,6 +256,18 @@ asmlinkage void smp_thermal_interrupt(struct pt_regs *regs) ack_APIC_irq(); } +void __init mcheck_intel_therm_init(void) +{ + /* + * This function is only called on boot CPU. Save the init thermal + * LVT value on BSP and use that value to restore APs' thermal LVT + * entry BIOS programmed later + */ + if (cpu_has(&boot_cpu_data, X86_FEATURE_ACPI) && + cpu_has(&boot_cpu_data, X86_FEATURE_ACC)) + lvtthmr_init = apic_read(APIC_LVTTHMR); +} + void intel_init_thermal(struct cpuinfo_x86 *c) { unsigned int cpu = smp_processor_id(); @@ -270,7 +284,20 @@ void intel_init_thermal(struct cpuinfo_x86 *c) * since it might be delivered via SMI already: */ rdmsr(MSR_IA32_MISC_ENABLE, l, h); - h = apic_read(APIC_LVTTHMR); + + /* + * The initial value of thermal LVT entries on all APs always reads + * 0x10000 because APs are woken up by BSP issuing INIT-SIPI-SIPI + * sequence to them and LVT registers are reset to 0s except for + * the mask bits which are set to 1s when APs receive INIT IPI. + * Always restore the value that BIOS has programmed on AP based on + * BSP's info we saved since BIOS is always setting the same value + * for all threads/cores + */ + apic_write(APIC_LVTTHMR, lvtthmr_init); + + h = lvtthmr_init; + if ((l & MSR_IA32_MISC_ENABLE_TM1) && (h & APIC_DM_SMI)) { printk(KERN_DEBUG "CPU%d: Thermal monitoring handled by SMI\n", cpu); diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index b5801c311846..c1bbed1021d9 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -77,6 +77,18 @@ struct cpu_hw_events { struct debug_store *ds; }; +struct event_constraint { + unsigned long idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; + int code; +}; + +#define EVENT_CONSTRAINT(c, m) { .code = (c), .idxmsk[0] = (m) } +#define EVENT_CONSTRAINT_END { .code = 0, .idxmsk[0] = 0 } + +#define for_each_event_constraint(e, c) \ + for ((e) = (c); (e)->idxmsk[0]; (e)++) + + /* * struct x86_pmu - generic x86 pmu */ @@ -102,6 +114,8 @@ struct x86_pmu { u64 intel_ctrl; void (*enable_bts)(u64 config); void (*disable_bts)(void); + int (*get_event_idx)(struct cpu_hw_events *cpuc, + struct hw_perf_event *hwc); }; static struct x86_pmu x86_pmu __read_mostly; @@ -110,6 +124,8 @@ static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { .enabled = 1, }; +static const struct event_constraint *event_constraints; + /* * Not sure about some of these */ @@ -155,6 +171,16 @@ static u64 p6_pmu_raw_event(u64 hw_event) return hw_event & P6_EVNTSEL_MASK; } +static const struct event_constraint intel_p6_event_constraints[] = +{ + EVENT_CONSTRAINT(0xc1, 0x1), /* FLOPS */ + EVENT_CONSTRAINT(0x10, 0x1), /* FP_COMP_OPS_EXE */ + EVENT_CONSTRAINT(0x11, 0x1), /* FP_ASSIST */ + EVENT_CONSTRAINT(0x12, 0x2), /* MUL */ + EVENT_CONSTRAINT(0x13, 0x2), /* DIV */ + EVENT_CONSTRAINT(0x14, 0x1), /* CYCLES_DIV_BUSY */ + EVENT_CONSTRAINT_END +}; /* * Intel PerfMon v3. Used on Core2 and later. @@ -170,6 +196,35 @@ static const u64 intel_perfmon_event_map[] = [PERF_COUNT_HW_BUS_CYCLES] = 0x013c, }; +static const struct event_constraint intel_core_event_constraints[] = +{ + EVENT_CONSTRAINT(0x10, 0x1), /* FP_COMP_OPS_EXE */ + EVENT_CONSTRAINT(0x11, 0x2), /* FP_ASSIST */ + EVENT_CONSTRAINT(0x12, 0x2), /* MUL */ + EVENT_CONSTRAINT(0x13, 0x2), /* DIV */ + EVENT_CONSTRAINT(0x14, 0x1), /* CYCLES_DIV_BUSY */ + EVENT_CONSTRAINT(0x18, 0x1), /* IDLE_DURING_DIV */ + EVENT_CONSTRAINT(0x19, 0x2), /* DELAYED_BYPASS */ + EVENT_CONSTRAINT(0xa1, 0x1), /* RS_UOPS_DISPATCH_CYCLES */ + EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED */ + EVENT_CONSTRAINT_END +}; + +static const struct event_constraint intel_nehalem_event_constraints[] = +{ + EVENT_CONSTRAINT(0x40, 0x3), /* L1D_CACHE_LD */ + EVENT_CONSTRAINT(0x41, 0x3), /* L1D_CACHE_ST */ + EVENT_CONSTRAINT(0x42, 0x3), /* L1D_CACHE_LOCK */ + EVENT_CONSTRAINT(0x43, 0x3), /* L1D_ALL_REF */ + EVENT_CONSTRAINT(0x4e, 0x3), /* L1D_PREFETCH */ + EVENT_CONSTRAINT(0x4c, 0x3), /* LOAD_HIT_PRE */ + EVENT_CONSTRAINT(0x51, 0x3), /* L1D */ + EVENT_CONSTRAINT(0x52, 0x3), /* L1D_CACHE_PREFETCH_LOCK_FB_HIT */ + EVENT_CONSTRAINT(0x53, 0x3), /* L1D_CACHE_LOCK_FB_HIT */ + EVENT_CONSTRAINT(0xc5, 0x3), /* CACHE_LOCK_CYCLES */ + EVENT_CONSTRAINT_END +}; + static u64 intel_pmu_event_map(int hw_event) { return intel_perfmon_event_map[hw_event]; @@ -190,7 +245,7 @@ static u64 __read_mostly hw_cache_event_ids [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX]; -static const u64 nehalem_hw_cache_event_ids +static __initconst u64 nehalem_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = @@ -281,7 +336,7 @@ static const u64 nehalem_hw_cache_event_ids }, }; -static const u64 core2_hw_cache_event_ids +static __initconst u64 core2_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = @@ -372,7 +427,7 @@ static const u64 core2_hw_cache_event_ids }, }; -static const u64 atom_hw_cache_event_ids +static __initconst u64 atom_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = @@ -469,7 +524,7 @@ static u64 intel_pmu_raw_event(u64 hw_event) #define CORE_EVNTSEL_UNIT_MASK 0x0000FF00ULL #define CORE_EVNTSEL_EDGE_MASK 0x00040000ULL #define CORE_EVNTSEL_INV_MASK 0x00800000ULL -#define CORE_EVNTSEL_REG_MASK 0xFF000000ULL +#define CORE_EVNTSEL_REG_MASK 0xFF000000ULL #define CORE_EVNTSEL_MASK \ (CORE_EVNTSEL_EVENT_MASK | \ @@ -481,7 +536,7 @@ static u64 intel_pmu_raw_event(u64 hw_event) return hw_event & CORE_EVNTSEL_MASK; } -static const u64 amd_hw_cache_event_ids +static __initconst u64 amd_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = @@ -932,6 +987,8 @@ static int __hw_perf_event_init(struct perf_event *event) */ hwc->config = ARCH_PERFMON_EVENTSEL_INT; + hwc->idx = -1; + /* * Count user and OS events unless requested not to. */ @@ -1334,8 +1391,7 @@ static void amd_pmu_enable_event(struct hw_perf_event *hwc, int idx) x86_pmu_enable_event(hwc, idx); } -static int -fixed_mode_idx(struct perf_event *event, struct hw_perf_event *hwc) +static int fixed_mode_idx(struct hw_perf_event *hwc) { unsigned int hw_event; @@ -1349,6 +1405,12 @@ fixed_mode_idx(struct perf_event *event, struct hw_perf_event *hwc) if (!x86_pmu.num_events_fixed) return -1; + /* + * fixed counters do not take all possible filters + */ + if (hwc->config & ARCH_PERFMON_EVENT_FILTER_MASK) + return -1; + if (unlikely(hw_event == x86_pmu.event_map(PERF_COUNT_HW_INSTRUCTIONS))) return X86_PMC_IDX_FIXED_INSTRUCTIONS; if (unlikely(hw_event == x86_pmu.event_map(PERF_COUNT_HW_CPU_CYCLES))) @@ -1360,22 +1422,57 @@ fixed_mode_idx(struct perf_event *event, struct hw_perf_event *hwc) } /* - * Find a PMC slot for the freshly enabled / scheduled in event: + * generic counter allocator: get next free counter */ -static int x86_pmu_enable(struct perf_event *event) +static int +gen_get_event_idx(struct cpu_hw_events *cpuc, struct hw_perf_event *hwc) +{ + int idx; + + idx = find_first_zero_bit(cpuc->used_mask, x86_pmu.num_events); + return idx == x86_pmu.num_events ? -1 : idx; +} + +/* + * intel-specific counter allocator: check event constraints + */ +static int +intel_get_event_idx(struct cpu_hw_events *cpuc, struct hw_perf_event *hwc) +{ + const struct event_constraint *event_constraint; + int i, code; + + if (!event_constraints) + goto skip; + + code = hwc->config & CORE_EVNTSEL_EVENT_MASK; + + for_each_event_constraint(event_constraint, event_constraints) { + if (code == event_constraint->code) { + for_each_bit(i, event_constraint->idxmsk, X86_PMC_IDX_MAX) { + if (!test_and_set_bit(i, cpuc->used_mask)) + return i; + } + return -1; + } + } +skip: + return gen_get_event_idx(cpuc, hwc); +} + +static int +x86_schedule_event(struct cpu_hw_events *cpuc, struct hw_perf_event *hwc) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - struct hw_perf_event *hwc = &event->hw; int idx; - idx = fixed_mode_idx(event, hwc); + idx = fixed_mode_idx(hwc); if (idx == X86_PMC_IDX_FIXED_BTS) { /* BTS is already occupied. */ if (test_and_set_bit(idx, cpuc->used_mask)) return -EAGAIN; hwc->config_base = 0; - hwc->event_base = 0; + hwc->event_base = 0; hwc->idx = idx; } else if (idx >= 0) { /* @@ -1396,20 +1493,35 @@ static int x86_pmu_enable(struct perf_event *event) } else { idx = hwc->idx; /* Try to get the previous generic event again */ - if (test_and_set_bit(idx, cpuc->used_mask)) { + if (idx == -1 || test_and_set_bit(idx, cpuc->used_mask)) { try_generic: - idx = find_first_zero_bit(cpuc->used_mask, - x86_pmu.num_events); - if (idx == x86_pmu.num_events) + idx = x86_pmu.get_event_idx(cpuc, hwc); + if (idx == -1) return -EAGAIN; set_bit(idx, cpuc->used_mask); hwc->idx = idx; } - hwc->config_base = x86_pmu.eventsel; - hwc->event_base = x86_pmu.perfctr; + hwc->config_base = x86_pmu.eventsel; + hwc->event_base = x86_pmu.perfctr; } + return idx; +} + +/* + * Find a PMC slot for the freshly enabled / scheduled in event: + */ +static int x86_pmu_enable(struct perf_event *event) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct hw_perf_event *hwc = &event->hw; + int idx; + + idx = x86_schedule_event(cpuc, hwc); + if (idx < 0) + return idx; + perf_events_lapic_init(); x86_pmu.disable(hwc, idx); @@ -1852,7 +1964,7 @@ static __read_mostly struct notifier_block perf_event_nmi_notifier = { .priority = 1 }; -static struct x86_pmu p6_pmu = { +static __initconst struct x86_pmu p6_pmu = { .name = "p6", .handle_irq = p6_pmu_handle_irq, .disable_all = p6_pmu_disable_all, @@ -1877,9 +1989,10 @@ static struct x86_pmu p6_pmu = { */ .event_bits = 32, .event_mask = (1ULL << 32) - 1, + .get_event_idx = intel_get_event_idx, }; -static struct x86_pmu intel_pmu = { +static __initconst struct x86_pmu intel_pmu = { .name = "Intel", .handle_irq = intel_pmu_handle_irq, .disable_all = intel_pmu_disable_all, @@ -1900,9 +2013,10 @@ static struct x86_pmu intel_pmu = { .max_period = (1ULL << 31) - 1, .enable_bts = intel_pmu_enable_bts, .disable_bts = intel_pmu_disable_bts, + .get_event_idx = intel_get_event_idx, }; -static struct x86_pmu amd_pmu = { +static __initconst struct x86_pmu amd_pmu = { .name = "AMD", .handle_irq = amd_pmu_handle_irq, .disable_all = amd_pmu_disable_all, @@ -1920,9 +2034,10 @@ static struct x86_pmu amd_pmu = { .apic = 1, /* use highest bit to detect overflow */ .max_period = (1ULL << 47) - 1, + .get_event_idx = gen_get_event_idx, }; -static int p6_pmu_init(void) +static __init int p6_pmu_init(void) { switch (boot_cpu_data.x86_model) { case 1: @@ -1932,10 +2047,12 @@ static int p6_pmu_init(void) case 7: case 8: case 11: /* Pentium III */ + event_constraints = intel_p6_event_constraints; break; case 9: case 13: /* Pentium M */ + event_constraints = intel_p6_event_constraints; break; default: pr_cont("unsupported p6 CPU model %d ", @@ -1954,7 +2071,7 @@ static int p6_pmu_init(void) return 0; } -static int intel_pmu_init(void) +static __init int intel_pmu_init(void) { union cpuid10_edx edx; union cpuid10_eax eax; @@ -2007,12 +2124,14 @@ static int intel_pmu_init(void) sizeof(hw_cache_event_ids)); pr_cont("Core2 events, "); + event_constraints = intel_core_event_constraints; break; default: case 26: memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + event_constraints = intel_nehalem_event_constraints; pr_cont("Nehalem/Corei7 events, "); break; case 28: @@ -2025,7 +2144,7 @@ static int intel_pmu_init(void) return 0; } -static int amd_pmu_init(void) +static __init int amd_pmu_init(void) { /* Performance-monitoring supported from K7 and later: */ if (boot_cpu_data.x86 < 6) @@ -2105,11 +2224,47 @@ static const struct pmu pmu = { .unthrottle = x86_pmu_unthrottle, }; +static int +validate_event(struct cpu_hw_events *cpuc, struct perf_event *event) +{ + struct hw_perf_event fake_event = event->hw; + + if (event->pmu && event->pmu != &pmu) + return 0; + + return x86_schedule_event(cpuc, &fake_event) >= 0; +} + +static int validate_group(struct perf_event *event) +{ + struct perf_event *sibling, *leader = event->group_leader; + struct cpu_hw_events fake_pmu; + + memset(&fake_pmu, 0, sizeof(fake_pmu)); + + if (!validate_event(&fake_pmu, leader)) + return -ENOSPC; + + list_for_each_entry(sibling, &leader->sibling_list, group_entry) { + if (!validate_event(&fake_pmu, sibling)) + return -ENOSPC; + } + + if (!validate_event(&fake_pmu, event)) + return -ENOSPC; + + return 0; +} + const struct pmu *hw_perf_event_init(struct perf_event *event) { int err; err = __hw_perf_event_init(event); + if (!err) { + if (event->group_leader != event) + err = validate_group(event); + } if (err) { if (event->destroy) event->destroy(event); diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c index fab786f60ed6..898df9719afb 100644 --- a/arch/x86/kernel/cpu/perfctr-watchdog.c +++ b/arch/x86/kernel/cpu/perfctr-watchdog.c @@ -712,7 +712,7 @@ static void probe_nmi_watchdog(void) switch (boot_cpu_data.x86_vendor) { case X86_VENDOR_AMD: if (boot_cpu_data.x86 != 6 && boot_cpu_data.x86 != 15 && - boot_cpu_data.x86 != 16) + boot_cpu_data.x86 != 16 && boot_cpu_data.x86 != 17) return; wd_ops = &k7_wd_ops; break; diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c index bb62b3e5caad..28000743bbb0 100644 --- a/arch/x86/kernel/cpu/transmeta.c +++ b/arch/x86/kernel/cpu/transmeta.c @@ -26,7 +26,7 @@ static void __cpuinit init_transmeta(struct cpuinfo_x86 *c) early_init_transmeta(c); - display_cacheinfo(c); + cpu_detect_cache_sizes(c); /* Print CMS and CPU revision */ max = cpuid_eax(0x80860000); diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index 6a52d4b36a30..7ef24a796992 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -116,21 +116,16 @@ static int cpuid_open(struct inode *inode, struct file *file) { unsigned int cpu; struct cpuinfo_x86 *c; - int ret = 0; - - lock_kernel(); cpu = iminor(file->f_path.dentry->d_inode); - if (cpu >= nr_cpu_ids || !cpu_online(cpu)) { - ret = -ENXIO; /* No such CPU */ - goto out; - } + if (cpu >= nr_cpu_ids || !cpu_online(cpu)) + return -ENXIO; /* No such CPU */ + c = &cpu_data(cpu); if (c->cpuid_level < 0) - ret = -EIO; /* CPUID not supported */ -out: - unlock_kernel(); - return ret; + return -EIO; /* CPUID not supported */ + + return 0; } /* diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 5e409dc298a4..a4849c10a77e 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -27,8 +27,7 @@ #include <asm/cpu.h> #include <asm/reboot.h> #include <asm/virtext.h> -#include <asm/iommu.h> - +#include <asm/x86_init.h> #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC) @@ -106,7 +105,7 @@ void native_machine_crash_shutdown(struct pt_regs *regs) #endif #ifdef CONFIG_X86_64 - pci_iommu_shutdown(); + x86_platform.iommu_shutdown(); #endif crash_save_cpu(regs, safe_smp_processor_id()); diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 2d8a371d4339..b8ce165dde5d 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -268,11 +268,12 @@ int __kprobes __die(const char *str, struct pt_regs *regs, long err) show_registers(regs); #ifdef CONFIG_X86_32 - sp = (unsigned long) (®s->sp); - savesegment(ss, ss); - if (user_mode(regs)) { + if (user_mode_vm(regs)) { sp = regs->sp; ss = regs->ss & 0xffff; + } else { + sp = kernel_stack_pointer(regs); + savesegment(ss, ss); } printk(KERN_EMERG "EIP: [<%08lx>] ", regs->ip); print_symbol("%s", regs->ip); diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index f7dd2a7c3bf4..e0ed4c7abb62 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -10,9 +10,9 @@ #include <linux/module.h> #include <linux/ptrace.h> #include <linux/kexec.h> +#include <linux/sysfs.h> #include <linux/bug.h> #include <linux/nmi.h> -#include <linux/sysfs.h> #include <asm/stacktrace.h> @@ -35,6 +35,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, if (!stack) { unsigned long dummy; + stack = &dummy; if (task && task != current) stack = (unsigned long *)task->thread.sp; @@ -57,8 +58,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, context = (struct thread_info *) ((unsigned long)stack & (~(THREAD_SIZE - 1))); - bp = print_context_stack(context, stack, bp, ops, - data, NULL, &graph); + bp = print_context_stack(context, stack, bp, ops, data, NULL, &graph); stack = (unsigned long *)context->previous_esp; if (!stack) @@ -72,7 +72,7 @@ EXPORT_SYMBOL(dump_trace); void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *sp, unsigned long bp, char *log_lvl) + unsigned long *sp, unsigned long bp, char *log_lvl) { unsigned long *stack; int i; @@ -156,4 +156,3 @@ int is_valid_bugaddr(unsigned long ip) return ud2 == 0x0b0f; } - diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index a071e6be177e..8e740934bd1f 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -10,26 +10,28 @@ #include <linux/module.h> #include <linux/ptrace.h> #include <linux/kexec.h> +#include <linux/sysfs.h> #include <linux/bug.h> #include <linux/nmi.h> -#include <linux/sysfs.h> #include <asm/stacktrace.h> #include "dumpstack.h" +#define N_EXCEPTION_STACKS_END \ + (N_EXCEPTION_STACKS + DEBUG_STKSZ/EXCEPTION_STKSZ - 2) static char x86_stack_ids[][8] = { - [DEBUG_STACK - 1] = "#DB", - [NMI_STACK - 1] = "NMI", - [DOUBLEFAULT_STACK - 1] = "#DF", - [STACKFAULT_STACK - 1] = "#SS", - [MCE_STACK - 1] = "#MC", + [ DEBUG_STACK-1 ] = "#DB", + [ NMI_STACK-1 ] = "NMI", + [ DOUBLEFAULT_STACK-1 ] = "#DF", + [ STACKFAULT_STACK-1 ] = "#SS", + [ MCE_STACK-1 ] = "#MC", #if DEBUG_STKSZ > EXCEPTION_STKSZ - [N_EXCEPTION_STACKS ... - N_EXCEPTION_STACKS + DEBUG_STKSZ / EXCEPTION_STKSZ - 2] = "#DB[?]" + [ N_EXCEPTION_STACKS ... + N_EXCEPTION_STACKS_END ] = "#DB[?]" #endif - }; +}; int x86_is_stack_id(int id, char *name) { @@ -37,7 +39,7 @@ int x86_is_stack_id(int id, char *name) } static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack, - unsigned *usedp, char **idp) + unsigned *usedp, char **idp) { unsigned k; @@ -202,21 +204,24 @@ EXPORT_SYMBOL(dump_trace); void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *sp, unsigned long bp, char *log_lvl) + unsigned long *sp, unsigned long bp, char *log_lvl) { + unsigned long *irq_stack_end; + unsigned long *irq_stack; unsigned long *stack; + int cpu; int i; - const int cpu = smp_processor_id(); - unsigned long *irq_stack_end = - (unsigned long *)(per_cpu(irq_stack_ptr, cpu)); - unsigned long *irq_stack = - (unsigned long *)(per_cpu(irq_stack_ptr, cpu) - IRQ_STACK_SIZE); + + preempt_disable(); + cpu = smp_processor_id(); + + irq_stack_end = (unsigned long *)(per_cpu(irq_stack_ptr, cpu)); + irq_stack = (unsigned long *)(per_cpu(irq_stack_ptr, cpu) - IRQ_STACK_SIZE); /* - * debugging aid: "show_stack(NULL, NULL);" prints the - * back trace for this cpu. + * Debugging aid: "show_stack(NULL, NULL);" prints the + * back trace for this cpu: */ - if (sp == NULL) { if (task) sp = (unsigned long *)task->thread.sp; @@ -240,6 +245,8 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, printk(" %016lx", *stack++); touch_nmi_watchdog(); } + preempt_enable(); + printk("\n"); show_trace_log_lvl(task, regs, sp, bp, log_lvl); } @@ -303,4 +310,3 @@ int is_valid_bugaddr(unsigned long ip) return ud2 == 0x0b0f; } - diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index c097e7d607c6..50b9c220e121 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -334,6 +334,10 @@ ENTRY(ret_from_fork) END(ret_from_fork) /* + * Interrupt exit functions should be protected against kprobes + */ + .pushsection .kprobes.text, "ax" +/* * Return to user mode is not as complex as all this looks, * but we want the default path for a system call return to * go as quickly as possible which is why some of this is @@ -383,6 +387,10 @@ need_resched: END(resume_kernel) #endif CFI_ENDPROC +/* + * End of kprobes section + */ + .popsection /* SYSENTER_RETURN points to after the "sysenter" instruction in the vsyscall page. See vsyscall-sysentry.S, which defines the symbol. */ @@ -513,6 +521,10 @@ sysexit_audit: PTGS_TO_GS_EX ENDPROC(ia32_sysenter_target) +/* + * syscall stub including irq exit should be protected against kprobes + */ + .pushsection .kprobes.text, "ax" # system call handler stub ENTRY(system_call) RING0_INT_FRAME # can't unwind into user space anyway @@ -705,6 +717,10 @@ syscall_badsys: jmp resume_userspace END(syscall_badsys) CFI_ENDPROC +/* + * End of kprobes section + */ + .popsection /* * System calls that need a pt_regs pointer. @@ -814,6 +830,10 @@ common_interrupt: ENDPROC(common_interrupt) CFI_ENDPROC +/* + * Irq entries should be protected against kprobes + */ + .pushsection .kprobes.text, "ax" #define BUILD_INTERRUPT3(name, nr, fn) \ ENTRY(name) \ RING0_INT_FRAME; \ @@ -980,6 +1000,10 @@ ENTRY(spurious_interrupt_bug) jmp error_code CFI_ENDPROC END(spurious_interrupt_bug) +/* + * End of kprobes section + */ + .popsection ENTRY(kernel_thread_helper) pushl $0 # fake return address for unwinder @@ -1185,17 +1209,14 @@ END(ftrace_graph_caller) .globl return_to_handler return_to_handler: - pushl $0 pushl %eax - pushl %ecx pushl %edx movl %ebp, %eax call ftrace_return_to_handler - movl %eax, 0xc(%esp) + movl %eax, %ecx popl %edx - popl %ecx popl %eax - ret + jmp *%ecx #endif .section .rodata,"a" diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index b5c061f8f358..4deb8fc849dd 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -155,11 +155,11 @@ GLOBAL(return_to_handler) call ftrace_return_to_handler - movq %rax, 16(%rsp) + movq %rax, %rdi movq 8(%rsp), %rdx movq (%rsp), %rax - addq $16, %rsp - retq + addq $24, %rsp + jmp *%rdi #endif @@ -803,6 +803,10 @@ END(interrupt) call \func .endm +/* + * Interrupt entry/exit should be protected against kprobes + */ + .pushsection .kprobes.text, "ax" /* * The interrupt stubs push (~vector+0x80) onto the stack and * then jump to common_interrupt. @@ -941,6 +945,10 @@ ENTRY(retint_kernel) CFI_ENDPROC END(common_interrupt) +/* + * End of kprobes section + */ + .popsection /* * APIC interrupts. @@ -1491,12 +1499,17 @@ error_kernelspace: leaq irq_return(%rip),%rcx cmpq %rcx,RIP+8(%rsp) je error_swapgs - movl %ecx,%ecx /* zero extend */ - cmpq %rcx,RIP+8(%rsp) - je error_swapgs + movl %ecx,%eax /* zero extend */ + cmpq %rax,RIP+8(%rsp) + je bstep_iret cmpq $gs_change,RIP+8(%rsp) je error_swapgs jmp error_sti + +bstep_iret: + /* Fix truncated RIP */ + movq %rcx,RIP+8(%rsp) + jmp error_swapgs END(error_entry) diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 9dbb527e1652..5a1b9758fd62 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -9,6 +9,8 @@ * the dangers of modifying code on the run. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/spinlock.h> #include <linux/hardirq.h> #include <linux/uaccess.h> @@ -336,15 +338,15 @@ int __init ftrace_dyn_arch_init(void *data) switch (faulted) { case 0: - pr_info("ftrace: converting mcount calls to 0f 1f 44 00 00\n"); + pr_info("converting mcount calls to 0f 1f 44 00 00\n"); memcpy(ftrace_nop, ftrace_test_p6nop, MCOUNT_INSN_SIZE); break; case 1: - pr_info("ftrace: converting mcount calls to 66 66 66 66 90\n"); + pr_info("converting mcount calls to 66 66 66 66 90\n"); memcpy(ftrace_nop, ftrace_test_nop5, MCOUNT_INSN_SIZE); break; case 2: - pr_info("ftrace: converting mcount calls to jmp . + 5\n"); + pr_info("converting mcount calls to jmp . + 5\n"); memcpy(ftrace_nop, ftrace_test_jmp, MCOUNT_INSN_SIZE); break; } @@ -468,82 +470,10 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, #ifdef CONFIG_FTRACE_SYSCALLS -extern unsigned long __start_syscalls_metadata[]; -extern unsigned long __stop_syscalls_metadata[]; extern unsigned long *sys_call_table; -static struct syscall_metadata **syscalls_metadata; - -static struct syscall_metadata *find_syscall_meta(unsigned long *syscall) -{ - struct syscall_metadata *start; - struct syscall_metadata *stop; - char str[KSYM_SYMBOL_LEN]; - - - start = (struct syscall_metadata *)__start_syscalls_metadata; - stop = (struct syscall_metadata *)__stop_syscalls_metadata; - kallsyms_lookup((unsigned long) syscall, NULL, NULL, NULL, str); - - for ( ; start < stop; start++) { - if (start->name && !strcmp(start->name, str)) - return start; - } - return NULL; -} - -struct syscall_metadata *syscall_nr_to_meta(int nr) -{ - if (!syscalls_metadata || nr >= NR_syscalls || nr < 0) - return NULL; - - return syscalls_metadata[nr]; -} - -int syscall_name_to_nr(char *name) +unsigned long __init arch_syscall_addr(int nr) { - int i; - - if (!syscalls_metadata) - return -1; - - for (i = 0; i < NR_syscalls; i++) { - if (syscalls_metadata[i]) { - if (!strcmp(syscalls_metadata[i]->name, name)) - return i; - } - } - return -1; -} - -void set_syscall_enter_id(int num, int id) -{ - syscalls_metadata[num]->enter_id = id; -} - -void set_syscall_exit_id(int num, int id) -{ - syscalls_metadata[num]->exit_id = id; -} - -static int __init arch_init_ftrace_syscalls(void) -{ - int i; - struct syscall_metadata *meta; - unsigned long **psys_syscall_table = &sys_call_table; - - syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) * - NR_syscalls, GFP_KERNEL); - if (!syscalls_metadata) { - WARN_ON(1); - return -ENOMEM; - } - - for (i = 0; i < NR_syscalls; i++) { - meta = find_syscall_meta(psys_syscall_table[i]); - syscalls_metadata[i] = meta; - } - return 0; + return (unsigned long)(&sys_call_table)[nr]; } -arch_initcall(arch_init_ftrace_syscalls); #endif diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 780cd928fcd5..22db86a37643 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -212,8 +212,8 @@ ENTRY(secondary_startup_64) */ lgdt early_gdt_descr(%rip) - /* set up data segments. actually 0 would do too */ - movl $__KERNEL_DS,%eax + /* set up data segments */ + xorl %eax,%eax movl %eax,%ds movl %eax,%ss movl %eax,%es diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c new file mode 100644 index 000000000000..d42f65ac4927 --- /dev/null +++ b/arch/x86/kernel/hw_breakpoint.c @@ -0,0 +1,555 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) 2007 Alan Stern + * Copyright (C) 2009 IBM Corporation + * Copyright (C) 2009 Frederic Weisbecker <fweisbec@gmail.com> + * + * Authors: Alan Stern <stern@rowland.harvard.edu> + * K.Prasad <prasad@linux.vnet.ibm.com> + * Frederic Weisbecker <fweisbec@gmail.com> + */ + +/* + * HW_breakpoint: a unified kernel/user-space hardware breakpoint facility, + * using the CPU's debug registers. + */ + +#include <linux/perf_event.h> +#include <linux/hw_breakpoint.h> +#include <linux/irqflags.h> +#include <linux/notifier.h> +#include <linux/kallsyms.h> +#include <linux/kprobes.h> +#include <linux/percpu.h> +#include <linux/kdebug.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <linux/init.h> +#include <linux/smp.h> + +#include <asm/hw_breakpoint.h> +#include <asm/processor.h> +#include <asm/debugreg.h> + +/* Per cpu debug control register value */ +DEFINE_PER_CPU(unsigned long, cpu_dr7); +EXPORT_PER_CPU_SYMBOL(cpu_dr7); + +/* Per cpu debug address registers values */ +static DEFINE_PER_CPU(unsigned long, cpu_debugreg[HBP_NUM]); + +/* + * Stores the breakpoints currently in use on each breakpoint address + * register for each cpus + */ +static DEFINE_PER_CPU(struct perf_event *, bp_per_reg[HBP_NUM]); + + +static inline unsigned long +__encode_dr7(int drnum, unsigned int len, unsigned int type) +{ + unsigned long bp_info; + + bp_info = (len | type) & 0xf; + bp_info <<= (DR_CONTROL_SHIFT + drnum * DR_CONTROL_SIZE); + bp_info |= (DR_GLOBAL_ENABLE << (drnum * DR_ENABLE_SIZE)); + + return bp_info; +} + +/* + * Encode the length, type, Exact, and Enable bits for a particular breakpoint + * as stored in debug register 7. + */ +unsigned long encode_dr7(int drnum, unsigned int len, unsigned int type) +{ + return __encode_dr7(drnum, len, type) | DR_GLOBAL_SLOWDOWN; +} + +/* + * Decode the length and type bits for a particular breakpoint as + * stored in debug register 7. Return the "enabled" status. + */ +int decode_dr7(unsigned long dr7, int bpnum, unsigned *len, unsigned *type) +{ + int bp_info = dr7 >> (DR_CONTROL_SHIFT + bpnum * DR_CONTROL_SIZE); + + *len = (bp_info & 0xc) | 0x40; + *type = (bp_info & 0x3) | 0x80; + + return (dr7 >> (bpnum * DR_ENABLE_SIZE)) & 0x3; +} + +/* + * Install a perf counter breakpoint. + * + * We seek a free debug address register and use it for this + * breakpoint. Eventually we enable it in the debug control register. + * + * Atomic: we hold the counter->ctx->lock and we only handle variables + * and registers local to this cpu. + */ +int arch_install_hw_breakpoint(struct perf_event *bp) +{ + struct arch_hw_breakpoint *info = counter_arch_bp(bp); + unsigned long *dr7; + int i; + + for (i = 0; i < HBP_NUM; i++) { + struct perf_event **slot = &__get_cpu_var(bp_per_reg[i]); + + if (!*slot) { + *slot = bp; + break; + } + } + + if (WARN_ONCE(i == HBP_NUM, "Can't find any breakpoint slot")) + return -EBUSY; + + set_debugreg(info->address, i); + __get_cpu_var(cpu_debugreg[i]) = info->address; + + dr7 = &__get_cpu_var(cpu_dr7); + *dr7 |= encode_dr7(i, info->len, info->type); + + set_debugreg(*dr7, 7); + + return 0; +} + +/* + * Uninstall the breakpoint contained in the given counter. + * + * First we search the debug address register it uses and then we disable + * it. + * + * Atomic: we hold the counter->ctx->lock and we only handle variables + * and registers local to this cpu. + */ +void arch_uninstall_hw_breakpoint(struct perf_event *bp) +{ + struct arch_hw_breakpoint *info = counter_arch_bp(bp); + unsigned long *dr7; + int i; + + for (i = 0; i < HBP_NUM; i++) { + struct perf_event **slot = &__get_cpu_var(bp_per_reg[i]); + + if (*slot == bp) { + *slot = NULL; + break; + } + } + + if (WARN_ONCE(i == HBP_NUM, "Can't find any breakpoint slot")) + return; + + dr7 = &__get_cpu_var(cpu_dr7); + *dr7 &= ~__encode_dr7(i, info->len, info->type); + + set_debugreg(*dr7, 7); +} + +static int get_hbp_len(u8 hbp_len) +{ + unsigned int len_in_bytes = 0; + + switch (hbp_len) { + case X86_BREAKPOINT_LEN_1: + len_in_bytes = 1; + break; + case X86_BREAKPOINT_LEN_2: + len_in_bytes = 2; + break; + case X86_BREAKPOINT_LEN_4: + len_in_bytes = 4; + break; +#ifdef CONFIG_X86_64 + case X86_BREAKPOINT_LEN_8: + len_in_bytes = 8; + break; +#endif + } + return len_in_bytes; +} + +/* + * Check for virtual address in user space. + */ +int arch_check_va_in_userspace(unsigned long va, u8 hbp_len) +{ + unsigned int len; + + len = get_hbp_len(hbp_len); + + return (va <= TASK_SIZE - len); +} + +/* + * Check for virtual address in kernel space. + */ +static int arch_check_va_in_kernelspace(unsigned long va, u8 hbp_len) +{ + unsigned int len; + + len = get_hbp_len(hbp_len); + + return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE); +} + +/* + * Store a breakpoint's encoded address, length, and type. + */ +static int arch_store_info(struct perf_event *bp) +{ + struct arch_hw_breakpoint *info = counter_arch_bp(bp); + /* + * For kernel-addresses, either the address or symbol name can be + * specified. + */ + if (info->name) + info->address = (unsigned long) + kallsyms_lookup_name(info->name); + if (info->address) + return 0; + + return -EINVAL; +} + +int arch_bp_generic_fields(int x86_len, int x86_type, + int *gen_len, int *gen_type) +{ + /* Len */ + switch (x86_len) { + case X86_BREAKPOINT_LEN_1: + *gen_len = HW_BREAKPOINT_LEN_1; + break; + case X86_BREAKPOINT_LEN_2: + *gen_len = HW_BREAKPOINT_LEN_2; + break; + case X86_BREAKPOINT_LEN_4: + *gen_len = HW_BREAKPOINT_LEN_4; + break; +#ifdef CONFIG_X86_64 + case X86_BREAKPOINT_LEN_8: + *gen_len = HW_BREAKPOINT_LEN_8; + break; +#endif + default: + return -EINVAL; + } + + /* Type */ + switch (x86_type) { + case X86_BREAKPOINT_EXECUTE: + *gen_type = HW_BREAKPOINT_X; + break; + case X86_BREAKPOINT_WRITE: + *gen_type = HW_BREAKPOINT_W; + break; + case X86_BREAKPOINT_RW: + *gen_type = HW_BREAKPOINT_W | HW_BREAKPOINT_R; + break; + default: + return -EINVAL; + } + + return 0; +} + + +static int arch_build_bp_info(struct perf_event *bp) +{ + struct arch_hw_breakpoint *info = counter_arch_bp(bp); + + info->address = bp->attr.bp_addr; + + /* Len */ + switch (bp->attr.bp_len) { + case HW_BREAKPOINT_LEN_1: + info->len = X86_BREAKPOINT_LEN_1; + break; + case HW_BREAKPOINT_LEN_2: + info->len = X86_BREAKPOINT_LEN_2; + break; + case HW_BREAKPOINT_LEN_4: + info->len = X86_BREAKPOINT_LEN_4; + break; +#ifdef CONFIG_X86_64 + case HW_BREAKPOINT_LEN_8: + info->len = X86_BREAKPOINT_LEN_8; + break; +#endif + default: + return -EINVAL; + } + + /* Type */ + switch (bp->attr.bp_type) { + case HW_BREAKPOINT_W: + info->type = X86_BREAKPOINT_WRITE; + break; + case HW_BREAKPOINT_W | HW_BREAKPOINT_R: + info->type = X86_BREAKPOINT_RW; + break; + case HW_BREAKPOINT_X: + info->type = X86_BREAKPOINT_EXECUTE; + break; + default: + return -EINVAL; + } + + return 0; +} +/* + * Validate the arch-specific HW Breakpoint register settings + */ +int arch_validate_hwbkpt_settings(struct perf_event *bp, + struct task_struct *tsk) +{ + struct arch_hw_breakpoint *info = counter_arch_bp(bp); + unsigned int align; + int ret; + + + ret = arch_build_bp_info(bp); + if (ret) + return ret; + + ret = -EINVAL; + + if (info->type == X86_BREAKPOINT_EXECUTE) + /* + * Ptrace-refactoring code + * For now, we'll allow instruction breakpoint only for user-space + * addresses + */ + if ((!arch_check_va_in_userspace(info->address, info->len)) && + info->len != X86_BREAKPOINT_EXECUTE) + return ret; + + switch (info->len) { + case X86_BREAKPOINT_LEN_1: + align = 0; + break; + case X86_BREAKPOINT_LEN_2: + align = 1; + break; + case X86_BREAKPOINT_LEN_4: + align = 3; + break; +#ifdef CONFIG_X86_64 + case X86_BREAKPOINT_LEN_8: + align = 7; + break; +#endif + default: + return ret; + } + + if (bp->callback) + ret = arch_store_info(bp); + + if (ret < 0) + return ret; + /* + * Check that the low-order bits of the address are appropriate + * for the alignment implied by len. + */ + if (info->address & align) + return -EINVAL; + + /* Check that the virtual address is in the proper range */ + if (tsk) { + if (!arch_check_va_in_userspace(info->address, info->len)) + return -EFAULT; + } else { + if (!arch_check_va_in_kernelspace(info->address, info->len)) + return -EFAULT; + } + + return 0; +} + +/* + * Dump the debug register contents to the user. + * We can't dump our per cpu values because it + * may contain cpu wide breakpoint, something that + * doesn't belong to the current task. + * + * TODO: include non-ptrace user breakpoints (perf) + */ +void aout_dump_debugregs(struct user *dump) +{ + int i; + int dr7 = 0; + struct perf_event *bp; + struct arch_hw_breakpoint *info; + struct thread_struct *thread = ¤t->thread; + + for (i = 0; i < HBP_NUM; i++) { + bp = thread->ptrace_bps[i]; + + if (bp && !bp->attr.disabled) { + dump->u_debugreg[i] = bp->attr.bp_addr; + info = counter_arch_bp(bp); + dr7 |= encode_dr7(i, info->len, info->type); + } else { + dump->u_debugreg[i] = 0; + } + } + + dump->u_debugreg[4] = 0; + dump->u_debugreg[5] = 0; + dump->u_debugreg[6] = current->thread.debugreg6; + + dump->u_debugreg[7] = dr7; +} +EXPORT_SYMBOL_GPL(aout_dump_debugregs); + +/* + * Release the user breakpoints used by ptrace + */ +void flush_ptrace_hw_breakpoint(struct task_struct *tsk) +{ + int i; + struct thread_struct *t = &tsk->thread; + + for (i = 0; i < HBP_NUM; i++) { + unregister_hw_breakpoint(t->ptrace_bps[i]); + t->ptrace_bps[i] = NULL; + } +} + +void hw_breakpoint_restore(void) +{ + set_debugreg(__get_cpu_var(cpu_debugreg[0]), 0); + set_debugreg(__get_cpu_var(cpu_debugreg[1]), 1); + set_debugreg(__get_cpu_var(cpu_debugreg[2]), 2); + set_debugreg(__get_cpu_var(cpu_debugreg[3]), 3); + set_debugreg(current->thread.debugreg6, 6); + set_debugreg(__get_cpu_var(cpu_dr7), 7); +} +EXPORT_SYMBOL_GPL(hw_breakpoint_restore); + +/* + * Handle debug exception notifications. + * + * Return value is either NOTIFY_STOP or NOTIFY_DONE as explained below. + * + * NOTIFY_DONE returned if one of the following conditions is true. + * i) When the causative address is from user-space and the exception + * is a valid one, i.e. not triggered as a result of lazy debug register + * switching + * ii) When there are more bits than trap<n> set in DR6 register (such + * as BD, BS or BT) indicating that more than one debug condition is + * met and requires some more action in do_debug(). + * + * NOTIFY_STOP returned for all other cases + * + */ +static int __kprobes hw_breakpoint_handler(struct die_args *args) +{ + int i, cpu, rc = NOTIFY_STOP; + struct perf_event *bp; + unsigned long dr7, dr6; + unsigned long *dr6_p; + + /* The DR6 value is pointed by args->err */ + dr6_p = (unsigned long *)ERR_PTR(args->err); + dr6 = *dr6_p; + + /* Do an early return if no trap bits are set in DR6 */ + if ((dr6 & DR_TRAP_BITS) == 0) + return NOTIFY_DONE; + + get_debugreg(dr7, 7); + /* Disable breakpoints during exception handling */ + set_debugreg(0UL, 7); + /* + * Assert that local interrupts are disabled + * Reset the DRn bits in the virtualized register value. + * The ptrace trigger routine will add in whatever is needed. + */ + current->thread.debugreg6 &= ~DR_TRAP_BITS; + cpu = get_cpu(); + + /* Handle all the breakpoints that were triggered */ + for (i = 0; i < HBP_NUM; ++i) { + if (likely(!(dr6 & (DR_TRAP0 << i)))) + continue; + + /* + * The counter may be concurrently released but that can only + * occur from a call_rcu() path. We can then safely fetch + * the breakpoint, use its callback, touch its counter + * while we are in an rcu_read_lock() path. + */ + rcu_read_lock(); + + bp = per_cpu(bp_per_reg[i], cpu); + if (bp) + rc = NOTIFY_DONE; + /* + * Reset the 'i'th TRAP bit in dr6 to denote completion of + * exception handling + */ + (*dr6_p) &= ~(DR_TRAP0 << i); + /* + * bp can be NULL due to lazy debug register switching + * or due to concurrent perf counter removing. + */ + if (!bp) { + rcu_read_unlock(); + break; + } + + (bp->callback)(bp, args->regs); + + rcu_read_unlock(); + } + if (dr6 & (~DR_TRAP_BITS)) + rc = NOTIFY_DONE; + + set_debugreg(dr7, 7); + put_cpu(); + + return rc; +} + +/* + * Handle debug exception notifications. + */ +int __kprobes hw_breakpoint_exceptions_notify( + struct notifier_block *unused, unsigned long val, void *data) +{ + if (val != DIE_DEBUG) + return NOTIFY_DONE; + + return hw_breakpoint_handler(data); +} + +void hw_breakpoint_pmu_read(struct perf_event *bp) +{ + /* TODO */ +} + +void hw_breakpoint_pmu_unthrottle(struct perf_event *bp) +{ + /* TODO */ +} diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 04bbd5278568..fee6cc2b2079 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -92,17 +92,17 @@ static int show_other_interrupts(struct seq_file *p, int prec) seq_printf(p, "%10u ", irq_stats(j)->irq_tlb_count); seq_printf(p, " TLB shootdowns\n"); #endif -#ifdef CONFIG_X86_MCE +#ifdef CONFIG_X86_THERMAL_VECTOR seq_printf(p, "%*s: ", prec, "TRM"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_thermal_count); seq_printf(p, " Thermal event interrupts\n"); -# ifdef CONFIG_X86_MCE_THRESHOLD +#endif +#ifdef CONFIG_X86_MCE_THRESHOLD seq_printf(p, "%*s: ", prec, "THR"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_threshold_count); seq_printf(p, " Threshold APIC interrupts\n"); -# endif #endif #ifdef CONFIG_X86_MCE seq_printf(p, "%*s: ", prec, "MCE"); @@ -194,11 +194,11 @@ u64 arch_irq_stat_cpu(unsigned int cpu) sum += irq_stats(cpu)->irq_call_count; sum += irq_stats(cpu)->irq_tlb_count; #endif -#ifdef CONFIG_X86_MCE +#ifdef CONFIG_X86_THERMAL_VECTOR sum += irq_stats(cpu)->irq_thermal_count; -# ifdef CONFIG_X86_MCE_THRESHOLD +#endif +#ifdef CONFIG_X86_MCE_THRESHOLD sum += irq_stats(cpu)->irq_threshold_count; -# endif #endif #ifdef CONFIG_X86_MCE sum += per_cpu(mce_exception_count, cpu); @@ -274,3 +274,93 @@ void smp_generic_interrupt(struct pt_regs *regs) } EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq); + +#ifdef CONFIG_HOTPLUG_CPU +/* A cpu has been removed from cpu_online_mask. Reset irq affinities. */ +void fixup_irqs(void) +{ + unsigned int irq, vector; + static int warned; + struct irq_desc *desc; + + for_each_irq_desc(irq, desc) { + int break_affinity = 0; + int set_affinity = 1; + const struct cpumask *affinity; + + if (!desc) + continue; + if (irq == 2) + continue; + + /* interrupt's are disabled at this point */ + spin_lock(&desc->lock); + + affinity = desc->affinity; + if (!irq_has_action(irq) || + cpumask_equal(affinity, cpu_online_mask)) { + spin_unlock(&desc->lock); + continue; + } + + /* + * Complete the irq move. This cpu is going down and for + * non intr-remapping case, we can't wait till this interrupt + * arrives at this cpu before completing the irq move. + */ + irq_force_complete_move(irq); + + if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) { + break_affinity = 1; + affinity = cpu_all_mask; + } + + if (!(desc->status & IRQ_MOVE_PCNTXT) && desc->chip->mask) + desc->chip->mask(irq); + + if (desc->chip->set_affinity) + desc->chip->set_affinity(irq, affinity); + else if (!(warned++)) + set_affinity = 0; + + if (!(desc->status & IRQ_MOVE_PCNTXT) && desc->chip->unmask) + desc->chip->unmask(irq); + + spin_unlock(&desc->lock); + + if (break_affinity && set_affinity) + printk("Broke affinity for irq %i\n", irq); + else if (!set_affinity) + printk("Cannot set affinity for irq %i\n", irq); + } + + /* + * We can remove mdelay() and then send spuriuous interrupts to + * new cpu targets for all the irqs that were handled previously by + * this cpu. While it works, I have seen spurious interrupt messages + * (nothing wrong but still...). + * + * So for now, retain mdelay(1) and check the IRR and then send those + * interrupts to new targets as this cpu is already offlined... + */ + mdelay(1); + + for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { + unsigned int irr; + + if (__get_cpu_var(vector_irq)[vector] < 0) + continue; + + irr = apic_read(APIC_IRR + (vector / 32 * 0x10)); + if (irr & (1 << (vector % 32))) { + irq = __get_cpu_var(vector_irq)[vector]; + + desc = irq_to_desc(irq); + spin_lock(&desc->lock); + if (desc->chip->retrigger) + desc->chip->retrigger(irq); + spin_unlock(&desc->lock); + } + } +} +#endif diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 7d35d0fe2329..10709f29d166 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -211,48 +211,3 @@ bool handle_irq(unsigned irq, struct pt_regs *regs) return true; } - -#ifdef CONFIG_HOTPLUG_CPU - -/* A cpu has been removed from cpu_online_mask. Reset irq affinities. */ -void fixup_irqs(void) -{ - unsigned int irq; - struct irq_desc *desc; - - for_each_irq_desc(irq, desc) { - const struct cpumask *affinity; - - if (!desc) - continue; - if (irq == 2) - continue; - - affinity = desc->affinity; - if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) { - printk("Breaking affinity for irq %i\n", irq); - affinity = cpu_all_mask; - } - if (desc->chip->set_affinity) - desc->chip->set_affinity(irq, affinity); - else if (desc->action) - printk_once("Cannot set affinity for irq %i\n", irq); - } - -#if 0 - barrier(); - /* Ingo Molnar says: "after the IO-APIC masks have been redirected - [note the nop - the interrupt-enable boundary on x86 is two - instructions from sti] - to flush out pending hardirqs and - IPIs. After this point nothing is supposed to reach this CPU." */ - __asm__ __volatile__("sti; nop; cli"); - barrier(); -#else - /* That doesn't seem sufficient. Give it 1ms. */ - local_irq_enable(); - mdelay(1); - local_irq_disable(); -#endif -} -#endif - diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index 977d8b43a0dd..acf8fbf8fbda 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -62,64 +62,6 @@ bool handle_irq(unsigned irq, struct pt_regs *regs) return true; } -#ifdef CONFIG_HOTPLUG_CPU -/* A cpu has been removed from cpu_online_mask. Reset irq affinities. */ -void fixup_irqs(void) -{ - unsigned int irq; - static int warned; - struct irq_desc *desc; - - for_each_irq_desc(irq, desc) { - int break_affinity = 0; - int set_affinity = 1; - const struct cpumask *affinity; - - if (!desc) - continue; - if (irq == 2) - continue; - - /* interrupt's are disabled at this point */ - spin_lock(&desc->lock); - - affinity = desc->affinity; - if (!irq_has_action(irq) || - cpumask_equal(affinity, cpu_online_mask)) { - spin_unlock(&desc->lock); - continue; - } - - if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) { - break_affinity = 1; - affinity = cpu_all_mask; - } - - if (desc->chip->mask) - desc->chip->mask(irq); - - if (desc->chip->set_affinity) - desc->chip->set_affinity(irq, affinity); - else if (!(warned++)) - set_affinity = 0; - - if (desc->chip->unmask) - desc->chip->unmask(irq); - - spin_unlock(&desc->lock); - - if (break_affinity && set_affinity) - printk("Broke affinity for irq %i\n", irq); - else if (!set_affinity) - printk("Cannot set affinity for irq %i\n", irq); - } - - /* That doesn't seem sufficient. Give it 1ms. */ - local_irq_enable(); - mdelay(1); - local_irq_disable(); -} -#endif extern void call_softirq(void); diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 8d82a77a3f3b..20a5b3689463 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -43,6 +43,7 @@ #include <linux/smp.h> #include <linux/nmi.h> +#include <asm/debugreg.h> #include <asm/apicdef.h> #include <asm/system.h> @@ -88,7 +89,6 @@ void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs) gdb_regs[GDB_SS] = __KERNEL_DS; gdb_regs[GDB_FS] = 0xFFFF; gdb_regs[GDB_GS] = 0xFFFF; - gdb_regs[GDB_SP] = (int)®s->sp; #else gdb_regs[GDB_R8] = regs->r8; gdb_regs[GDB_R9] = regs->r9; @@ -101,8 +101,8 @@ void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs) gdb_regs32[GDB_PS] = regs->flags; gdb_regs32[GDB_CS] = regs->cs; gdb_regs32[GDB_SS] = regs->ss; - gdb_regs[GDB_SP] = regs->sp; #endif + gdb_regs[GDB_SP] = kernel_stack_pointer(regs); } /** @@ -434,6 +434,11 @@ single_step_cont(struct pt_regs *regs, struct die_args *args) "resuming...\n"); kgdb_arch_handle_exception(args->trapnr, args->signr, args->err, "c", "", regs); + /* + * Reset the BS bit in dr6 (pointed by args->err) to + * denote completion of processing + */ + (*(unsigned long *)ERR_PTR(args->err)) &= ~DR_STEP; return NOTIFY_STOP; } diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 7b5169d2b000..1f3186ce213c 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -48,31 +48,22 @@ #include <linux/preempt.h> #include <linux/module.h> #include <linux/kdebug.h> +#include <linux/kallsyms.h> #include <asm/cacheflush.h> #include <asm/desc.h> #include <asm/pgtable.h> #include <asm/uaccess.h> #include <asm/alternative.h> +#include <asm/insn.h> +#include <asm/debugreg.h> void jprobe_return_end(void); DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); -#ifdef CONFIG_X86_64 -#define stack_addr(regs) ((unsigned long *)regs->sp) -#else -/* - * "®s->sp" looks wrong, but it's correct for x86_32. x86_32 CPUs - * don't save the ss and esp registers if the CPU is already in kernel - * mode when it traps. So for kprobes, regs->sp and regs->ss are not - * the [nonexistent] saved stack pointer and ss register, but rather - * the top 8 bytes of the pre-int3 stack. So ®s->sp happens to - * point to the top of the pre-int3 stack. - */ -#define stack_addr(regs) ((unsigned long *)®s->sp) -#endif +#define stack_addr(regs) ((unsigned long *)kernel_stack_pointer(regs)) #define W(row, b0, b1, b2, b3, b4, b5, b6, b7, b8, b9, ba, bb, bc, bd, be, bf)\ (((b0##UL << 0x0)|(b1##UL << 0x1)|(b2##UL << 0x2)|(b3##UL << 0x3) | \ @@ -106,50 +97,6 @@ static const u32 twobyte_is_boostable[256 / 32] = { /* ----------------------------------------------- */ /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ }; -static const u32 onebyte_has_modrm[256 / 32] = { - /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ - /* ----------------------------------------------- */ - W(0x00, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0) | /* 00 */ - W(0x10, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0) , /* 10 */ - W(0x20, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0) | /* 20 */ - W(0x30, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0) , /* 30 */ - W(0x40, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* 40 */ - W(0x50, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 50 */ - W(0x60, 0, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0) | /* 60 */ - W(0x70, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 70 */ - W(0x80, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 80 */ - W(0x90, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 90 */ - W(0xa0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* a0 */ - W(0xb0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* b0 */ - W(0xc0, 1, 1, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0) | /* c0 */ - W(0xd0, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1) , /* d0 */ - W(0xe0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* e0 */ - W(0xf0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1) /* f0 */ - /* ----------------------------------------------- */ - /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ -}; -static const u32 twobyte_has_modrm[256 / 32] = { - /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ - /* ----------------------------------------------- */ - W(0x00, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1) | /* 0f */ - W(0x10, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0) , /* 1f */ - W(0x20, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1) | /* 2f */ - W(0x30, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 3f */ - W(0x40, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 4f */ - W(0x50, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 5f */ - W(0x60, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 6f */ - W(0x70, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1) , /* 7f */ - W(0x80, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* 8f */ - W(0x90, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 9f */ - W(0xa0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 1) | /* af */ - W(0xb0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1) , /* bf */ - W(0xc0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0) | /* cf */ - W(0xd0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* df */ - W(0xe0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* ef */ - W(0xf0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0) /* ff */ - /* ----------------------------------------------- */ - /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ -}; #undef W struct kretprobe_blackpoint kretprobe_blacklist[] = { @@ -244,6 +191,75 @@ retry: } } +/* Recover the probed instruction at addr for further analysis. */ +static int recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr) +{ + struct kprobe *kp; + kp = get_kprobe((void *)addr); + if (!kp) + return -EINVAL; + + /* + * Basically, kp->ainsn.insn has an original instruction. + * However, RIP-relative instruction can not do single-stepping + * at different place, fix_riprel() tweaks the displacement of + * that instruction. In that case, we can't recover the instruction + * from the kp->ainsn.insn. + * + * On the other hand, kp->opcode has a copy of the first byte of + * the probed instruction, which is overwritten by int3. And + * the instruction at kp->addr is not modified by kprobes except + * for the first byte, we can recover the original instruction + * from it and kp->opcode. + */ + memcpy(buf, kp->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); + buf[0] = kp->opcode; + return 0; +} + +/* Dummy buffers for kallsyms_lookup */ +static char __dummy_buf[KSYM_NAME_LEN]; + +/* Check if paddr is at an instruction boundary */ +static int __kprobes can_probe(unsigned long paddr) +{ + int ret; + unsigned long addr, offset = 0; + struct insn insn; + kprobe_opcode_t buf[MAX_INSN_SIZE]; + + if (!kallsyms_lookup(paddr, NULL, &offset, NULL, __dummy_buf)) + return 0; + + /* Decode instructions */ + addr = paddr - offset; + while (addr < paddr) { + kernel_insn_init(&insn, (void *)addr); + insn_get_opcode(&insn); + + /* + * Check if the instruction has been modified by another + * kprobe, in which case we replace the breakpoint by the + * original instruction in our buffer. + */ + if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) { + ret = recover_probed_instruction(buf, addr); + if (ret) + /* + * Another debugging subsystem might insert + * this breakpoint. In that case, we can't + * recover it. + */ + return 0; + kernel_insn_init(&insn, buf); + } + insn_get_length(&insn); + addr += insn.length; + } + + return (addr == paddr); +} + /* * Returns non-zero if opcode modifies the interrupt flag. */ @@ -277,68 +293,30 @@ static int __kprobes is_IF_modifier(kprobe_opcode_t *insn) static void __kprobes fix_riprel(struct kprobe *p) { #ifdef CONFIG_X86_64 - u8 *insn = p->ainsn.insn; - s64 disp; - int need_modrm; - - /* Skip legacy instruction prefixes. */ - while (1) { - switch (*insn) { - case 0x66: - case 0x67: - case 0x2e: - case 0x3e: - case 0x26: - case 0x64: - case 0x65: - case 0x36: - case 0xf0: - case 0xf3: - case 0xf2: - ++insn; - continue; - } - break; - } + struct insn insn; + kernel_insn_init(&insn, p->ainsn.insn); - /* Skip REX instruction prefix. */ - if (is_REX_prefix(insn)) - ++insn; - - if (*insn == 0x0f) { - /* Two-byte opcode. */ - ++insn; - need_modrm = test_bit(*insn, - (unsigned long *)twobyte_has_modrm); - } else - /* One-byte opcode. */ - need_modrm = test_bit(*insn, - (unsigned long *)onebyte_has_modrm); - - if (need_modrm) { - u8 modrm = *++insn; - if ((modrm & 0xc7) == 0x05) { - /* %rip+disp32 addressing mode */ - /* Displacement follows ModRM byte. */ - ++insn; - /* - * The copied instruction uses the %rip-relative - * addressing mode. Adjust the displacement for the - * difference between the original location of this - * instruction and the location of the copy that will - * actually be run. The tricky bit here is making sure - * that the sign extension happens correctly in this - * calculation, since we need a signed 32-bit result to - * be sign-extended to 64 bits when it's added to the - * %rip value and yield the same 64-bit result that the - * sign-extension of the original signed 32-bit - * displacement would have given. - */ - disp = (u8 *) p->addr + *((s32 *) insn) - - (u8 *) p->ainsn.insn; - BUG_ON((s64) (s32) disp != disp); /* Sanity check. */ - *(s32 *)insn = (s32) disp; - } + if (insn_rip_relative(&insn)) { + s64 newdisp; + u8 *disp; + insn_get_displacement(&insn); + /* + * The copied instruction uses the %rip-relative addressing + * mode. Adjust the displacement for the difference between + * the original location of this instruction and the location + * of the copy that will actually be run. The tricky bit here + * is making sure that the sign extension happens correctly in + * this calculation, since we need a signed 32-bit result to + * be sign-extended to 64 bits when it's added to the %rip + * value and yield the same 64-bit result that the sign- + * extension of the original signed 32-bit displacement would + * have given. + */ + newdisp = (u8 *) p->addr + (s64) insn.displacement.value - + (u8 *) p->ainsn.insn; + BUG_ON((s64) (s32) newdisp != newdisp); /* Sanity check. */ + disp = (u8 *) p->ainsn.insn + insn_offset_displacement(&insn); + *(s32 *) disp = (s32) newdisp; } #endif } @@ -359,6 +337,8 @@ static void __kprobes arch_copy_kprobe(struct kprobe *p) int __kprobes arch_prepare_kprobe(struct kprobe *p) { + if (!can_probe((unsigned long)p->addr)) + return -EILSEQ; /* insn: must be on special executable page on x86. */ p->ainsn.insn = get_insn_slot(); if (!p->ainsn.insn) @@ -472,17 +452,6 @@ static int __kprobes reenter_kprobe(struct kprobe *p, struct pt_regs *regs, { switch (kcb->kprobe_status) { case KPROBE_HIT_SSDONE: -#ifdef CONFIG_X86_64 - /* TODO: Provide re-entrancy from post_kprobes_handler() and - * avoid exception stack corruption while single-stepping on - * the instruction of the new probe. - */ - arch_disarm_kprobe(p); - regs->ip = (unsigned long)p->addr; - reset_current_kprobe(); - preempt_enable_no_resched(); - break; -#endif case KPROBE_HIT_ACTIVE: save_previous_kprobe(kcb); set_current_kprobe(p, regs, kcb); @@ -491,18 +460,16 @@ static int __kprobes reenter_kprobe(struct kprobe *p, struct pt_regs *regs, kcb->kprobe_status = KPROBE_REENTER; break; case KPROBE_HIT_SS: - if (p == kprobe_running()) { - regs->flags &= ~X86_EFLAGS_TF; - regs->flags |= kcb->kprobe_saved_flags; - return 0; - } else { - /* A probe has been hit in the codepath leading up - * to, or just after, single-stepping of a probed - * instruction. This entire codepath should strictly - * reside in .kprobes.text section. Raise a warning - * to highlight this peculiar case. - */ - } + /* A probe has been hit in the codepath leading up to, or just + * after, single-stepping of a probed instruction. This entire + * codepath should strictly reside in .kprobes.text section. + * Raise a BUG or we'll continue in an endless reentering loop + * and eventually a stack overflow. + */ + printk(KERN_WARNING "Unrecoverable kprobe detected at %p.\n", + p->addr); + dump_kprobe(p); + BUG(); default: /* impossible cases */ WARN_ON(1); @@ -967,8 +934,14 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, ret = NOTIFY_STOP; break; case DIE_DEBUG: - if (post_kprobe_handler(args->regs)) + if (post_kprobe_handler(args->regs)) { + /* + * Reset the BS bit in dr6 (pointed by args->err) to + * denote completion of processing + */ + (*(unsigned long *)ERR_PTR(args->err)) &= ~DR_STEP; ret = NOTIFY_STOP; + } break; case DIE_GPF: /* diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index c1c429d00130..c843f8406da2 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -25,6 +25,7 @@ #include <asm/desc.h> #include <asm/system.h> #include <asm/cacheflush.h> +#include <asm/debugreg.h> static void set_idt(void *newidt, __u16 limit) { @@ -202,6 +203,7 @@ void machine_kexec(struct kimage *image) /* Interrupts aren't acceptable while we reboot */ local_irq_disable(); + hw_breakpoint_disable(); if (image->preserve_context) { #ifdef CONFIG_X86_IO_APIC diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 84c3bf209e98..4a8bb82248ae 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -18,6 +18,7 @@ #include <asm/pgtable.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> +#include <asm/debugreg.h> static int init_one_level2_page(struct kimage *image, pgd_t *pgd, unsigned long addr) @@ -282,6 +283,7 @@ void machine_kexec(struct kimage *image) /* Interrupts aren't acceptable while we reboot */ local_irq_disable(); + hw_breakpoint_disable(); if (image->preserve_context) { #ifdef CONFIG_X86_IO_APIC diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c index 378e9a8f1bf8..2bcad3926edb 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -73,7 +73,6 @@ #include <linux/platform_device.h> #include <linux/miscdevice.h> #include <linux/capability.h> -#include <linux/smp_lock.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/mutex.h> @@ -201,7 +200,6 @@ static int do_microcode_update(const void __user *buf, size_t size) static int microcode_open(struct inode *unused1, struct file *unused2) { - cycle_kernel_lock(); return capable(CAP_SYS_RAWIO) ? 0 : -EPERM; } diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index 6a3cefc7dda1..553449951b84 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -174,21 +174,17 @@ static int msr_open(struct inode *inode, struct file *file) { unsigned int cpu = iminor(file->f_path.dentry->d_inode); struct cpuinfo_x86 *c = &cpu_data(cpu); - int ret = 0; - lock_kernel(); cpu = iminor(file->f_path.dentry->d_inode); - if (cpu >= nr_cpu_ids || !cpu_online(cpu)) { - ret = -ENXIO; /* No such CPU */ - goto out; - } + if (cpu >= nr_cpu_ids || !cpu_online(cpu)) + return -ENXIO; /* No such CPU */ + c = &cpu_data(cpu); if (!cpu_has(c, X86_FEATURE_MSR)) - ret = -EIO; /* MSR not supported */ -out: - unlock_kernel(); - return ret; + return -EIO; /* MSR not supported */ + + return 0; } /* diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index 971a3bec47a8..c563e4c8ff39 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -46,6 +46,7 @@ #include <asm/dma.h> #include <asm/rio.h> #include <asm/bios_ebda.h> +#include <asm/x86_init.h> #ifdef CONFIG_CALGARY_IOMMU_ENABLED_BY_DEFAULT int use_calgary __read_mostly = 1; @@ -244,7 +245,7 @@ static unsigned long iommu_range_alloc(struct device *dev, if (panic_on_overflow) panic("Calgary: fix the allocator.\n"); else - return bad_dma_address; + return DMA_ERROR_CODE; } } @@ -260,12 +261,15 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl, void *vaddr, unsigned int npages, int direction) { unsigned long entry; - dma_addr_t ret = bad_dma_address; + dma_addr_t ret; entry = iommu_range_alloc(dev, tbl, npages); - if (unlikely(entry == bad_dma_address)) - goto error; + if (unlikely(entry == DMA_ERROR_CODE)) { + printk(KERN_WARNING "Calgary: failed to allocate %u pages in " + "iommu %p\n", npages, tbl); + return DMA_ERROR_CODE; + } /* set the return dma address */ ret = (entry << PAGE_SHIFT) | ((unsigned long)vaddr & ~PAGE_MASK); @@ -273,13 +277,7 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl, /* put the TCEs in the HW table */ tce_build(tbl, entry, npages, (unsigned long)vaddr & PAGE_MASK, direction); - return ret; - -error: - printk(KERN_WARNING "Calgary: failed to allocate %u pages in " - "iommu %p\n", npages, tbl); - return bad_dma_address; } static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, @@ -290,8 +288,8 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, unsigned long flags; /* were we called with bad_dma_address? */ - badend = bad_dma_address + (EMERGENCY_PAGES * PAGE_SIZE); - if (unlikely((dma_addr >= bad_dma_address) && (dma_addr < badend))) { + badend = DMA_ERROR_CODE + (EMERGENCY_PAGES * PAGE_SIZE); + if (unlikely((dma_addr >= DMA_ERROR_CODE) && (dma_addr < badend))) { WARN(1, KERN_ERR "Calgary: driver tried unmapping bad DMA " "address 0x%Lx\n", dma_addr); return; @@ -318,13 +316,15 @@ static inline struct iommu_table *find_iommu_table(struct device *dev) pdev = to_pci_dev(dev); + /* search up the device tree for an iommu */ pbus = pdev->bus; - - /* is the device behind a bridge? Look for the root bus */ - while (pbus->parent) + do { + tbl = pci_iommu(pbus); + if (tbl && tbl->it_busno == pbus->number) + break; + tbl = NULL; pbus = pbus->parent; - - tbl = pci_iommu(pbus); + } while (pbus); BUG_ON(tbl && (tbl->it_busno != pbus->number)); @@ -373,7 +373,7 @@ static int calgary_map_sg(struct device *dev, struct scatterlist *sg, npages = iommu_num_pages(vaddr, s->length, PAGE_SIZE); entry = iommu_range_alloc(dev, tbl, npages); - if (entry == bad_dma_address) { + if (entry == DMA_ERROR_CODE) { /* makes sure unmap knows to stop */ s->dma_length = 0; goto error; @@ -391,7 +391,7 @@ static int calgary_map_sg(struct device *dev, struct scatterlist *sg, error: calgary_unmap_sg(dev, sg, nelems, dir, NULL); for_each_sg(sg, s, nelems, i) { - sg->dma_address = bad_dma_address; + sg->dma_address = DMA_ERROR_CODE; sg->dma_length = 0; } return 0; @@ -446,7 +446,7 @@ static void* calgary_alloc_coherent(struct device *dev, size_t size, /* set up tces to cover the allocated range */ mapping = iommu_alloc(dev, tbl, ret, npages, DMA_BIDIRECTIONAL); - if (mapping == bad_dma_address) + if (mapping == DMA_ERROR_CODE) goto free; *dma_handle = mapping; return ret; @@ -727,7 +727,7 @@ static void __init calgary_reserve_regions(struct pci_dev *dev) struct iommu_table *tbl = pci_iommu(dev->bus); /* reserve EMERGENCY_PAGES from bad_dma_address and up */ - iommu_range_reserve(tbl, bad_dma_address, EMERGENCY_PAGES); + iommu_range_reserve(tbl, DMA_ERROR_CODE, EMERGENCY_PAGES); /* avoid the BIOS/VGA first 640KB-1MB region */ /* for CalIOC2 - avoid the entire first MB */ @@ -1344,6 +1344,23 @@ static void __init get_tce_space_from_tar(void) return; } +static int __init calgary_iommu_init(void) +{ + int ret; + + /* ok, we're trying to use Calgary - let's roll */ + printk(KERN_INFO "PCI-DMA: Using Calgary IOMMU\n"); + + ret = calgary_init(); + if (ret) { + printk(KERN_ERR "PCI-DMA: Calgary init failed %d, " + "falling back to no_iommu\n", ret); + return ret; + } + + return 0; +} + void __init detect_calgary(void) { int bus; @@ -1357,7 +1374,7 @@ void __init detect_calgary(void) * if the user specified iommu=off or iommu=soft or we found * another HW IOMMU already, bail out. */ - if (swiotlb || no_iommu || iommu_detected) + if (no_iommu || iommu_detected) return; if (!use_calgary) @@ -1442,9 +1459,7 @@ void __init detect_calgary(void) printk(KERN_INFO "PCI-DMA: Calgary TCE table spec is %d\n", specified_table_size); - /* swiotlb for devices that aren't behind the Calgary. */ - if (max_pfn > MAX_DMA32_PFN) - swiotlb = 1; + x86_init.iommu.iommu_init = calgary_iommu_init; } return; @@ -1457,35 +1472,6 @@ cleanup: } } -int __init calgary_iommu_init(void) -{ - int ret; - - if (no_iommu || (swiotlb && !calgary_detected)) - return -ENODEV; - - if (!calgary_detected) - return -ENODEV; - - /* ok, we're trying to use Calgary - let's roll */ - printk(KERN_INFO "PCI-DMA: Using Calgary IOMMU\n"); - - ret = calgary_init(); - if (ret) { - printk(KERN_ERR "PCI-DMA: Calgary init failed %d, " - "falling back to no_iommu\n", ret); - return ret; - } - - force_iommu = 1; - bad_dma_address = 0x0; - /* dma_ops is set to swiotlb or nommu */ - if (!dma_ops) - dma_ops = &nommu_dma_ops; - - return 0; -} - static int __init calgary_parse_options(char *p) { unsigned int bridge; diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index a6e804d16c35..afcc58b69c7c 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -11,10 +11,11 @@ #include <asm/gart.h> #include <asm/calgary.h> #include <asm/amd_iommu.h> +#include <asm/x86_init.h> static int forbid_dac __read_mostly; -struct dma_map_ops *dma_ops; +struct dma_map_ops *dma_ops = &nommu_dma_ops; EXPORT_SYMBOL(dma_ops); static int iommu_sac_force __read_mostly; @@ -42,9 +43,6 @@ int iommu_detected __read_mostly = 0; */ int iommu_pass_through __read_mostly; -dma_addr_t bad_dma_address __read_mostly = 0; -EXPORT_SYMBOL(bad_dma_address); - /* Dummy device used for NULL arguments (normally ISA). */ struct device x86_dma_fallback_dev = { .init_name = "fallback device", @@ -126,20 +124,17 @@ void __init pci_iommu_alloc(void) /* free the range so iommu could get some range less than 4G */ dma32_free_bootmem(); #endif + if (pci_swiotlb_init()) + return; - /* - * The order of these functions is important for - * fall-back/fail-over reasons - */ gart_iommu_hole_init(); detect_calgary(); detect_intel_iommu(); + /* needs to be called after gart_iommu_hole_init */ amd_iommu_detect(); - - pci_swiotlb_init(); } void *dma_generic_alloc_coherent(struct device *dev, size_t size, @@ -214,7 +209,7 @@ static __init int iommu_setup(char *p) if (!strncmp(p, "allowdac", 8)) forbid_dac = 0; if (!strncmp(p, "nodac", 5)) - forbid_dac = -1; + forbid_dac = 1; if (!strncmp(p, "usedac", 6)) { forbid_dac = -1; return 1; @@ -289,25 +284,17 @@ static int __init pci_iommu_init(void) #ifdef CONFIG_PCI dma_debug_add_bus(&pci_bus_type); #endif + x86_init.iommu.iommu_init(); - calgary_iommu_init(); - - intel_iommu_init(); + if (swiotlb) { + printk(KERN_INFO "PCI-DMA: " + "Using software bounce buffering for IO (SWIOTLB)\n"); + swiotlb_print_info(); + } else + swiotlb_free(); - amd_iommu_init(); - - gart_iommu_init(); - - no_iommu_init(); return 0; } - -void pci_iommu_shutdown(void) -{ - gart_iommu_shutdown(); - - amd_iommu_shutdown(); -} /* Must execute after PCI subsystem */ rootfs_initcall(pci_iommu_init); diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index a7f1b64f86e0..e6a0d402f171 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -39,6 +39,7 @@ #include <asm/swiotlb.h> #include <asm/dma.h> #include <asm/k8.h> +#include <asm/x86_init.h> static unsigned long iommu_bus_base; /* GART remapping area (physical) */ static unsigned long iommu_size; /* size of remapping area bytes */ @@ -46,6 +47,8 @@ static unsigned long iommu_pages; /* .. and in pages */ static u32 *iommu_gatt_base; /* Remapping table */ +static dma_addr_t bad_dma_addr; + /* * If this is disabled the IOMMU will use an optimized flushing strategy * of only flushing when an mapping is reused. With it true the GART is @@ -92,7 +95,7 @@ static unsigned long alloc_iommu(struct device *dev, int size, base_index = ALIGN(iommu_bus_base & dma_get_seg_boundary(dev), PAGE_SIZE) >> PAGE_SHIFT; - boundary_size = ALIGN((unsigned long long)dma_get_seg_boundary(dev) + 1, + boundary_size = ALIGN((u64)dma_get_seg_boundary(dev) + 1, PAGE_SIZE) >> PAGE_SHIFT; spin_lock_irqsave(&iommu_bitmap_lock, flags); @@ -216,7 +219,7 @@ static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem, if (panic_on_overflow) panic("dma_map_area overflow %lu bytes\n", size); iommu_full(dev, size, dir); - return bad_dma_address; + return bad_dma_addr; } for (i = 0; i < npages; i++) { @@ -294,7 +297,7 @@ static int dma_map_sg_nonforce(struct device *dev, struct scatterlist *sg, int i; #ifdef CONFIG_IOMMU_DEBUG - printk(KERN_DEBUG "dma_map_sg overflow\n"); + pr_debug("dma_map_sg overflow\n"); #endif for_each_sg(sg, s, nents, i) { @@ -302,7 +305,7 @@ static int dma_map_sg_nonforce(struct device *dev, struct scatterlist *sg, if (nonforced_iommu(dev, addr, s->length)) { addr = dma_map_area(dev, addr, s->length, dir, 0); - if (addr == bad_dma_address) { + if (addr == bad_dma_addr) { if (i > 0) gart_unmap_sg(dev, sg, i, dir, NULL); nents = 0; @@ -389,12 +392,14 @@ static int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, if (!dev) dev = &x86_dma_fallback_dev; - out = 0; - start = 0; - start_sg = sgmap = sg; - seg_size = 0; - max_seg_size = dma_get_max_seg_size(dev); - ps = NULL; /* shut up gcc */ + out = 0; + start = 0; + start_sg = sg; + sgmap = sg; + seg_size = 0; + max_seg_size = dma_get_max_seg_size(dev); + ps = NULL; /* shut up gcc */ + for_each_sg(sg, s, nents, i) { dma_addr_t addr = sg_phys(s); @@ -417,11 +422,12 @@ static int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, sgmap, pages, need) < 0) goto error; out++; - seg_size = 0; - sgmap = sg_next(sgmap); - pages = 0; - start = i; - start_sg = s; + + seg_size = 0; + sgmap = sg_next(sgmap); + pages = 0; + start = i; + start_sg = s; } } @@ -455,7 +461,7 @@ error: iommu_full(dev, pages << PAGE_SHIFT, dir); for_each_sg(sg, s, nents, i) - s->dma_address = bad_dma_address; + s->dma_address = bad_dma_addr; return 0; } @@ -479,7 +485,7 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr, DMA_BIDIRECTIONAL, align_mask); flush_gart(); - if (paddr != bad_dma_address) { + if (paddr != bad_dma_addr) { *dma_addr = paddr; return page_address(page); } @@ -499,6 +505,11 @@ gart_free_coherent(struct device *dev, size_t size, void *vaddr, free_pages((unsigned long)vaddr, get_order(size)); } +static int gart_mapping_error(struct device *dev, dma_addr_t dma_addr) +{ + return (dma_addr == bad_dma_addr); +} + static int no_agp; static __init unsigned long check_iommu_size(unsigned long aper, u64 aper_size) @@ -515,7 +526,7 @@ static __init unsigned long check_iommu_size(unsigned long aper, u64 aper_size) iommu_size -= round_up(a, PMD_PAGE_SIZE) - a; if (iommu_size < 64*1024*1024) { - printk(KERN_WARNING + pr_warning( "PCI-DMA: Warning: Small IOMMU %luMB." " Consider increasing the AGP aperture in BIOS\n", iommu_size >> 20); @@ -570,28 +581,32 @@ void set_up_gart_resume(u32 aper_order, u32 aper_alloc) aperture_alloc = aper_alloc; } -static int gart_resume(struct sys_device *dev) +static void gart_fixup_northbridges(struct sys_device *dev) { - printk(KERN_INFO "PCI-DMA: Resuming GART IOMMU\n"); + int i; - if (fix_up_north_bridges) { - int i; + if (!fix_up_north_bridges) + return; - printk(KERN_INFO "PCI-DMA: Restoring GART aperture settings\n"); + pr_info("PCI-DMA: Restoring GART aperture settings\n"); - for (i = 0; i < num_k8_northbridges; i++) { - struct pci_dev *dev = k8_northbridges[i]; + for (i = 0; i < num_k8_northbridges; i++) { + struct pci_dev *dev = k8_northbridges[i]; - /* - * Don't enable translations just yet. That is the next - * step. Restore the pre-suspend aperture settings. - */ - pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, - aperture_order << 1); - pci_write_config_dword(dev, AMD64_GARTAPERTUREBASE, - aperture_alloc >> 25); - } + /* + * Don't enable translations just yet. That is the next + * step. Restore the pre-suspend aperture settings. + */ + pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, aperture_order << 1); + pci_write_config_dword(dev, AMD64_GARTAPERTUREBASE, aperture_alloc >> 25); } +} + +static int gart_resume(struct sys_device *dev) +{ + pr_info("PCI-DMA: Resuming GART IOMMU\n"); + + gart_fixup_northbridges(dev); enable_gart_translations(); @@ -604,15 +619,14 @@ static int gart_suspend(struct sys_device *dev, pm_message_t state) } static struct sysdev_class gart_sysdev_class = { - .name = "gart", - .suspend = gart_suspend, - .resume = gart_resume, + .name = "gart", + .suspend = gart_suspend, + .resume = gart_resume, }; static struct sys_device device_gart = { - .id = 0, - .cls = &gart_sysdev_class, + .cls = &gart_sysdev_class, }; /* @@ -627,7 +641,8 @@ static __init int init_k8_gatt(struct agp_kern_info *info) void *gatt; int i, error; - printk(KERN_INFO "PCI-DMA: Disabling AGP.\n"); + pr_info("PCI-DMA: Disabling AGP.\n"); + aper_size = aper_base = info->aper_size = 0; dev = NULL; for (i = 0; i < num_k8_northbridges; i++) { @@ -645,6 +660,7 @@ static __init int init_k8_gatt(struct agp_kern_info *info) } if (!aper_base) goto nommu; + info->aper_base = aper_base; info->aper_size = aper_size >> 20; @@ -667,14 +683,14 @@ static __init int init_k8_gatt(struct agp_kern_info *info) flush_gart(); - printk(KERN_INFO "PCI-DMA: aperture base @ %x size %u KB\n", + pr_info("PCI-DMA: aperture base @ %x size %u KB\n", aper_base, aper_size>>10); return 0; nommu: /* Should not happen anymore */ - printk(KERN_WARNING "PCI-DMA: More than 4GB of RAM and no IOMMU\n" + pr_warning("PCI-DMA: More than 4GB of RAM and no IOMMU\n" "falling back to iommu=soft.\n"); return -1; } @@ -686,14 +702,15 @@ static struct dma_map_ops gart_dma_ops = { .unmap_page = gart_unmap_page, .alloc_coherent = gart_alloc_coherent, .free_coherent = gart_free_coherent, + .mapping_error = gart_mapping_error, }; -void gart_iommu_shutdown(void) +static void gart_iommu_shutdown(void) { struct pci_dev *dev; int i; - if (no_agp && (dma_ops != &gart_dma_ops)) + if (no_agp) return; for (i = 0; i < num_k8_northbridges; i++) { @@ -708,7 +725,7 @@ void gart_iommu_shutdown(void) } } -void __init gart_iommu_init(void) +int __init gart_iommu_init(void) { struct agp_kern_info info; unsigned long iommu_start; @@ -718,7 +735,7 @@ void __init gart_iommu_init(void) long i; if (cache_k8_northbridges() < 0 || num_k8_northbridges == 0) - return; + return 0; #ifndef CONFIG_AGP_AMD64 no_agp = 1; @@ -730,35 +747,28 @@ void __init gart_iommu_init(void) (agp_copy_info(agp_bridge, &info) < 0); #endif - if (swiotlb) - return; - - /* Did we detect a different HW IOMMU? */ - if (iommu_detected && !gart_iommu_aperture) - return; - if (no_iommu || (!force_iommu && max_pfn <= MAX_DMA32_PFN) || !gart_iommu_aperture || (no_agp && init_k8_gatt(&info) < 0)) { if (max_pfn > MAX_DMA32_PFN) { - printk(KERN_WARNING "More than 4GB of memory " - "but GART IOMMU not available.\n"); - printk(KERN_WARNING "falling back to iommu=soft.\n"); + pr_warning("More than 4GB of memory but GART IOMMU not available.\n"); + pr_warning("falling back to iommu=soft.\n"); } - return; + return 0; } /* need to map that range */ - aper_size = info.aper_size << 20; - aper_base = info.aper_base; - end_pfn = (aper_base>>PAGE_SHIFT) + (aper_size>>PAGE_SHIFT); + aper_size = info.aper_size << 20; + aper_base = info.aper_base; + end_pfn = (aper_base>>PAGE_SHIFT) + (aper_size>>PAGE_SHIFT); + if (end_pfn > max_low_pfn_mapped) { start_pfn = (aper_base>>PAGE_SHIFT); init_memory_mapping(start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT); } - printk(KERN_INFO "PCI-DMA: using GART IOMMU.\n"); + pr_info("PCI-DMA: using GART IOMMU.\n"); iommu_size = check_iommu_size(info.aper_base, aper_size); iommu_pages = iommu_size >> PAGE_SHIFT; @@ -773,8 +783,7 @@ void __init gart_iommu_init(void) ret = dma_debug_resize_entries(iommu_pages); if (ret) - printk(KERN_DEBUG - "PCI-DMA: Cannot trace all the entries\n"); + pr_debug("PCI-DMA: Cannot trace all the entries\n"); } #endif @@ -784,15 +793,14 @@ void __init gart_iommu_init(void) */ iommu_area_reserve(iommu_gart_bitmap, 0, EMERGENCY_PAGES); - agp_memory_reserved = iommu_size; - printk(KERN_INFO - "PCI-DMA: Reserving %luMB of IOMMU area in the AGP aperture\n", + pr_info("PCI-DMA: Reserving %luMB of IOMMU area in the AGP aperture\n", iommu_size >> 20); - iommu_start = aper_size - iommu_size; - iommu_bus_base = info.aper_base + iommu_start; - bad_dma_address = iommu_bus_base; - iommu_gatt_base = agp_gatt_table + (iommu_start>>PAGE_SHIFT); + agp_memory_reserved = iommu_size; + iommu_start = aper_size - iommu_size; + iommu_bus_base = info.aper_base + iommu_start; + bad_dma_addr = iommu_bus_base; + iommu_gatt_base = agp_gatt_table + (iommu_start>>PAGE_SHIFT); /* * Unmap the IOMMU part of the GART. The alias of the page is @@ -814,7 +822,7 @@ void __init gart_iommu_init(void) * the pages as Not-Present: */ wbinvd(); - + /* * Now all caches are flushed and we can safely enable * GART hardware. Doing it early leaves the possibility @@ -838,6 +846,10 @@ void __init gart_iommu_init(void) flush_gart(); dma_ops = &gart_dma_ops; + x86_platform.iommu_shutdown = gart_iommu_shutdown; + swiotlb = 0; + + return 0; } void __init gart_parse_options(char *p) @@ -856,7 +868,7 @@ void __init gart_parse_options(char *p) #endif if (isdigit(*p) && get_option(&p, &arg)) iommu_size = arg; - if (!strncmp(p, "fullflush", 8)) + if (!strncmp(p, "fullflush", 9)) iommu_fullflush = 1; if (!strncmp(p, "nofullflush", 11)) iommu_fullflush = 0; diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c index a3933d4330cd..22be12b60a8f 100644 --- a/arch/x86/kernel/pci-nommu.c +++ b/arch/x86/kernel/pci-nommu.c @@ -33,7 +33,7 @@ static dma_addr_t nommu_map_page(struct device *dev, struct page *page, dma_addr_t bus = page_to_phys(page) + offset; WARN_ON(size == 0); if (!check_addr("map_single", dev, bus, size)) - return bad_dma_address; + return DMA_ERROR_CODE; flush_write_buffers(); return bus; } @@ -103,12 +103,3 @@ struct dma_map_ops nommu_dma_ops = { .sync_sg_for_device = nommu_sync_sg_for_device, .is_phys = 1, }; - -void __init no_iommu_init(void) -{ - if (dma_ops) - return; - - force_iommu = 0; /* no HW IOMMU */ - dma_ops = &nommu_dma_ops; -} diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index aaa6b7839f1e..e3c0a66b9e77 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -42,18 +42,28 @@ static struct dma_map_ops swiotlb_dma_ops = { .dma_supported = NULL, }; -void __init pci_swiotlb_init(void) +/* + * pci_swiotlb_init - initialize swiotlb if necessary + * + * This returns non-zero if we are forced to use swiotlb (by the boot + * option). + */ +int __init pci_swiotlb_init(void) { + int use_swiotlb = swiotlb | swiotlb_force; + /* don't initialize swiotlb if iommu=off (no_iommu=1) */ #ifdef CONFIG_X86_64 - if ((!iommu_detected && !no_iommu && max_pfn > MAX_DMA32_PFN)) + if (!no_iommu && max_pfn > MAX_DMA32_PFN) swiotlb = 1; #endif if (swiotlb_force) swiotlb = 1; + if (swiotlb) { - printk(KERN_INFO "PCI-DMA: Using software bounce buffering for IO (SWIOTLB)\n"); - swiotlb_init(); + swiotlb_init(0); dma_ops = &swiotlb_dma_ops; } + + return use_swiotlb; } diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 5284cd2b5776..744508e7cfdd 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -10,6 +10,7 @@ #include <linux/clockchips.h> #include <linux/random.h> #include <trace/events/power.h> +#include <linux/hw_breakpoint.h> #include <asm/system.h> #include <asm/apic.h> #include <asm/syscalls.h> @@ -17,6 +18,7 @@ #include <asm/uaccess.h> #include <asm/i387.h> #include <asm/ds.h> +#include <asm/debugreg.h> unsigned long idle_halt; EXPORT_SYMBOL(idle_halt); @@ -103,14 +105,7 @@ void flush_thread(void) } #endif - clear_tsk_thread_flag(tsk, TIF_DEBUG); - - tsk->thread.debugreg0 = 0; - tsk->thread.debugreg1 = 0; - tsk->thread.debugreg2 = 0; - tsk->thread.debugreg3 = 0; - tsk->thread.debugreg6 = 0; - tsk->thread.debugreg7 = 0; + flush_ptrace_hw_breakpoint(tsk); memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array)); /* * Forget coprocessor state.. @@ -192,16 +187,6 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, else if (next->debugctlmsr != prev->debugctlmsr) update_debugctlmsr(next->debugctlmsr); - if (test_tsk_thread_flag(next_p, TIF_DEBUG)) { - set_debugreg(next->debugreg0, 0); - set_debugreg(next->debugreg1, 1); - set_debugreg(next->debugreg2, 2); - set_debugreg(next->debugreg3, 3); - /* no 4 and 5 */ - set_debugreg(next->debugreg6, 6); - set_debugreg(next->debugreg7, 7); - } - if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^ test_tsk_thread_flag(next_p, TIF_NOTSC)) { /* prev and next are different */ diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 4cf79567cdab..075580b35682 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -58,6 +58,7 @@ #include <asm/idle.h> #include <asm/syscalls.h> #include <asm/ds.h> +#include <asm/debugreg.h> asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); @@ -134,7 +135,7 @@ void __show_regs(struct pt_regs *regs, int all) ss = regs->ss & 0xffff; gs = get_user_gs(regs); } else { - sp = (unsigned long) (®s->sp); + sp = kernel_stack_pointer(regs); savesegment(ss, ss); savesegment(gs, gs); } @@ -187,7 +188,7 @@ void __show_regs(struct pt_regs *regs, int all) void show_regs(struct pt_regs *regs) { - __show_regs(regs, 1); + show_registers(regs); show_trace(NULL, regs, ®s->sp, regs->bp); } @@ -259,7 +260,12 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, task_user_gs(p) = get_user_gs(regs); + p->thread.io_bitmap_ptr = NULL; tsk = current; + err = -ENOMEM; + + memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); + if (unlikely(test_tsk_thread_flag(tsk, TIF_IO_BITMAP))) { p->thread.io_bitmap_ptr = kmemdup(tsk->thread.io_bitmap_ptr, IO_BITMAP_BYTES, GFP_KERNEL); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index eb62cbcaa490..a98fe88fab64 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -52,6 +52,7 @@ #include <asm/idle.h> #include <asm/syscalls.h> #include <asm/ds.h> +#include <asm/debugreg.h> asmlinkage extern void ret_from_fork(void); @@ -226,8 +227,7 @@ void __show_regs(struct pt_regs *regs, int all) void show_regs(struct pt_regs *regs) { - printk(KERN_INFO "CPU %d:", smp_processor_id()); - __show_regs(regs, 1); + show_registers(regs); show_trace(NULL, regs, (void *)(regs + 1), regs->bp); } @@ -297,12 +297,16 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, p->thread.fs = me->thread.fs; p->thread.gs = me->thread.gs; + p->thread.io_bitmap_ptr = NULL; savesegment(gs, p->thread.gsindex); savesegment(fs, p->thread.fsindex); savesegment(es, p->thread.es); savesegment(ds, p->thread.ds); + err = -ENOMEM; + memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); + if (unlikely(test_tsk_thread_flag(me, TIF_IO_BITMAP))) { p->thread.io_bitmap_ptr = kmalloc(IO_BITMAP_BYTES, GFP_KERNEL); if (!p->thread.io_bitmap_ptr) { @@ -341,6 +345,7 @@ out: kfree(p->thread.io_bitmap_ptr); p->thread.io_bitmap_max = 0; } + return err; } @@ -495,6 +500,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) */ if (preload_fpu) __math_state_restore(); + return prev_p; } diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 7b058a2dc66a..04d182a7cfdb 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -22,6 +22,8 @@ #include <linux/seccomp.h> #include <linux/signal.h> #include <linux/workqueue.h> +#include <linux/perf_event.h> +#include <linux/hw_breakpoint.h> #include <asm/uaccess.h> #include <asm/pgtable.h> @@ -34,6 +36,7 @@ #include <asm/prctl.h> #include <asm/proto.h> #include <asm/ds.h> +#include <asm/hw_breakpoint.h> #include "tls.h" @@ -49,6 +52,118 @@ enum x86_regset { REGSET_IOPERM32, }; +struct pt_regs_offset { + const char *name; + int offset; +}; + +#define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)} +#define REG_OFFSET_END {.name = NULL, .offset = 0} + +static const struct pt_regs_offset regoffset_table[] = { +#ifdef CONFIG_X86_64 + REG_OFFSET_NAME(r15), + REG_OFFSET_NAME(r14), + REG_OFFSET_NAME(r13), + REG_OFFSET_NAME(r12), + REG_OFFSET_NAME(r11), + REG_OFFSET_NAME(r10), + REG_OFFSET_NAME(r9), + REG_OFFSET_NAME(r8), +#endif + REG_OFFSET_NAME(bx), + REG_OFFSET_NAME(cx), + REG_OFFSET_NAME(dx), + REG_OFFSET_NAME(si), + REG_OFFSET_NAME(di), + REG_OFFSET_NAME(bp), + REG_OFFSET_NAME(ax), +#ifdef CONFIG_X86_32 + REG_OFFSET_NAME(ds), + REG_OFFSET_NAME(es), + REG_OFFSET_NAME(fs), + REG_OFFSET_NAME(gs), +#endif + REG_OFFSET_NAME(orig_ax), + REG_OFFSET_NAME(ip), + REG_OFFSET_NAME(cs), + REG_OFFSET_NAME(flags), + REG_OFFSET_NAME(sp), + REG_OFFSET_NAME(ss), + REG_OFFSET_END, +}; + +/** + * regs_query_register_offset() - query register offset from its name + * @name: the name of a register + * + * regs_query_register_offset() returns the offset of a register in struct + * pt_regs from its name. If the name is invalid, this returns -EINVAL; + */ +int regs_query_register_offset(const char *name) +{ + const struct pt_regs_offset *roff; + for (roff = regoffset_table; roff->name != NULL; roff++) + if (!strcmp(roff->name, name)) + return roff->offset; + return -EINVAL; +} + +/** + * regs_query_register_name() - query register name from its offset + * @offset: the offset of a register in struct pt_regs. + * + * regs_query_register_name() returns the name of a register from its + * offset in struct pt_regs. If the @offset is invalid, this returns NULL; + */ +const char *regs_query_register_name(unsigned int offset) +{ + const struct pt_regs_offset *roff; + for (roff = regoffset_table; roff->name != NULL; roff++) + if (roff->offset == offset) + return roff->name; + return NULL; +} + +static const int arg_offs_table[] = { +#ifdef CONFIG_X86_32 + [0] = offsetof(struct pt_regs, ax), + [1] = offsetof(struct pt_regs, dx), + [2] = offsetof(struct pt_regs, cx) +#else /* CONFIG_X86_64 */ + [0] = offsetof(struct pt_regs, di), + [1] = offsetof(struct pt_regs, si), + [2] = offsetof(struct pt_regs, dx), + [3] = offsetof(struct pt_regs, cx), + [4] = offsetof(struct pt_regs, r8), + [5] = offsetof(struct pt_regs, r9) +#endif +}; + +/** + * regs_get_argument_nth() - get Nth argument at function call + * @regs: pt_regs which contains registers at function entry. + * @n: argument number. + * + * regs_get_argument_nth() returns @n th argument of a function call. + * Since usually the kernel stack will be changed right after function entry, + * you must use this at function entry. If the @n th entry is NOT in the + * kernel stack or pt_regs, this returns 0. + */ +unsigned long regs_get_argument_nth(struct pt_regs *regs, unsigned int n) +{ + if (n < ARRAY_SIZE(arg_offs_table)) + return *(unsigned long *)((char *)regs + arg_offs_table[n]); + else { + /* + * The typical case: arg n is on the stack. + * (Note: stack[0] = return address, so skip it) + */ + n -= ARRAY_SIZE(arg_offs_table); + return regs_get_kernel_stack_nth(regs, 1 + n); + } +} + /* * does not yet catch signals sent when the child dies. * in exit.c or in signal.c. @@ -137,11 +252,6 @@ static int set_segment_reg(struct task_struct *task, return 0; } -static unsigned long debugreg_addr_limit(struct task_struct *task) -{ - return TASK_SIZE - 3; -} - #else /* CONFIG_X86_64 */ #define FLAG_MASK (FLAG_MASK_32 | X86_EFLAGS_NT) @@ -266,15 +376,6 @@ static int set_segment_reg(struct task_struct *task, return 0; } -static unsigned long debugreg_addr_limit(struct task_struct *task) -{ -#ifdef CONFIG_IA32_EMULATION - if (test_tsk_thread_flag(task, TIF_IA32)) - return IA32_PAGE_OFFSET - 3; -#endif - return TASK_SIZE_MAX - 7; -} - #endif /* CONFIG_X86_32 */ static unsigned long get_flags(struct task_struct *task) @@ -454,99 +555,239 @@ static int genregs_set(struct task_struct *target, return ret; } +static void ptrace_triggered(struct perf_event *bp, void *data) +{ + int i; + struct thread_struct *thread = &(current->thread); + + /* + * Store in the virtual DR6 register the fact that the breakpoint + * was hit so the thread's debugger will see it. + */ + for (i = 0; i < HBP_NUM; i++) { + if (thread->ptrace_bps[i] == bp) + break; + } + + thread->debugreg6 |= (DR_TRAP0 << i); +} + /* - * This function is trivial and will be inlined by the compiler. - * Having it separates the implementation details of debug - * registers from the interface details of ptrace. + * Walk through every ptrace breakpoints for this thread and + * build the dr7 value on top of their attributes. + * */ -static unsigned long ptrace_get_debugreg(struct task_struct *child, int n) +static unsigned long ptrace_get_dr7(struct perf_event *bp[]) { - switch (n) { - case 0: return child->thread.debugreg0; - case 1: return child->thread.debugreg1; - case 2: return child->thread.debugreg2; - case 3: return child->thread.debugreg3; - case 6: return child->thread.debugreg6; - case 7: return child->thread.debugreg7; + int i; + int dr7 = 0; + struct arch_hw_breakpoint *info; + + for (i = 0; i < HBP_NUM; i++) { + if (bp[i] && !bp[i]->attr.disabled) { + info = counter_arch_bp(bp[i]); + dr7 |= encode_dr7(i, info->len, info->type); + } } - return 0; + + return dr7; } -static int ptrace_set_debugreg(struct task_struct *child, - int n, unsigned long data) +static struct perf_event * +ptrace_modify_breakpoint(struct perf_event *bp, int len, int type, + struct task_struct *tsk, int disabled) { - int i; + int err; + int gen_len, gen_type; + DEFINE_BREAKPOINT_ATTR(attr); - if (unlikely(n == 4 || n == 5)) - return -EIO; + /* + * We shoud have at least an inactive breakpoint at this + * slot. It means the user is writing dr7 without having + * written the address register first + */ + if (!bp) + return ERR_PTR(-EINVAL); - if (n < 4 && unlikely(data >= debugreg_addr_limit(child))) - return -EIO; + err = arch_bp_generic_fields(len, type, &gen_len, &gen_type); + if (err) + return ERR_PTR(err); - switch (n) { - case 0: child->thread.debugreg0 = data; break; - case 1: child->thread.debugreg1 = data; break; - case 2: child->thread.debugreg2 = data; break; - case 3: child->thread.debugreg3 = data; break; + attr = bp->attr; + attr.bp_len = gen_len; + attr.bp_type = gen_type; + attr.disabled = disabled; - case 6: - if ((data & ~0xffffffffUL) != 0) - return -EIO; - child->thread.debugreg6 = data; - break; + return modify_user_hw_breakpoint(bp, &attr, bp->callback, tsk); +} + +/* + * Handle ptrace writes to debug register 7. + */ +static int ptrace_write_dr7(struct task_struct *tsk, unsigned long data) +{ + struct thread_struct *thread = &(tsk->thread); + unsigned long old_dr7; + int i, orig_ret = 0, rc = 0; + int enabled, second_pass = 0; + unsigned len, type; + struct perf_event *bp; + + data &= ~DR_CONTROL_RESERVED; + old_dr7 = ptrace_get_dr7(thread->ptrace_bps); +restore: + /* + * Loop through all the hardware breakpoints, making the + * appropriate changes to each. + */ + for (i = 0; i < HBP_NUM; i++) { + enabled = decode_dr7(data, i, &len, &type); + bp = thread->ptrace_bps[i]; + + if (!enabled) { + if (bp) { + /* + * Don't unregister the breakpoints right-away, + * unless all register_user_hw_breakpoint() + * requests have succeeded. This prevents + * any window of opportunity for debug + * register grabbing by other users. + */ + if (!second_pass) + continue; + + thread->ptrace_bps[i] = NULL; + bp = ptrace_modify_breakpoint(bp, len, type, + tsk, 1); + if (IS_ERR(bp)) { + rc = PTR_ERR(bp); + thread->ptrace_bps[i] = NULL; + break; + } + thread->ptrace_bps[i] = bp; + } + continue; + } + + bp = ptrace_modify_breakpoint(bp, len, type, tsk, 0); + + /* Incorrect bp, or we have a bug in bp API */ + if (IS_ERR(bp)) { + rc = PTR_ERR(bp); + thread->ptrace_bps[i] = NULL; + break; + } + thread->ptrace_bps[i] = bp; + } + /* + * Make a second pass to free the remaining unused breakpoints + * or to restore the original breakpoints if an error occurred. + */ + if (!second_pass) { + second_pass = 1; + if (rc < 0) { + orig_ret = rc; + data = old_dr7; + } + goto restore; + } + return ((orig_ret < 0) ? orig_ret : rc); +} + +/* + * Handle PTRACE_PEEKUSR calls for the debug register area. + */ +static unsigned long ptrace_get_debugreg(struct task_struct *tsk, int n) +{ + struct thread_struct *thread = &(tsk->thread); + unsigned long val = 0; - case 7: + if (n < HBP_NUM) { + struct perf_event *bp; + bp = thread->ptrace_bps[n]; + if (!bp) + return 0; + val = bp->hw.info.address; + } else if (n == 6) { + val = thread->debugreg6; + } else if (n == 7) { + val = ptrace_get_dr7(thread->ptrace_bps); + } + return val; +} + +static int ptrace_set_breakpoint_addr(struct task_struct *tsk, int nr, + unsigned long addr) +{ + struct perf_event *bp; + struct thread_struct *t = &tsk->thread; + DEFINE_BREAKPOINT_ATTR(attr); + + if (!t->ptrace_bps[nr]) { /* - * Sanity-check data. Take one half-byte at once with - * check = (val >> (16 + 4*i)) & 0xf. It contains the - * R/Wi and LENi bits; bits 0 and 1 are R/Wi, and bits - * 2 and 3 are LENi. Given a list of invalid values, - * we do mask |= 1 << invalid_value, so that - * (mask >> check) & 1 is a correct test for invalid - * values. - * - * R/Wi contains the type of the breakpoint / - * watchpoint, LENi contains the length of the watched - * data in the watchpoint case. - * - * The invalid values are: - * - LENi == 0x10 (undefined), so mask |= 0x0f00. [32-bit] - * - R/Wi == 0x10 (break on I/O reads or writes), so - * mask |= 0x4444. - * - R/Wi == 0x00 && LENi != 0x00, so we have mask |= - * 0x1110. - * - * Finally, mask = 0x0f00 | 0x4444 | 0x1110 == 0x5f54. - * - * See the Intel Manual "System Programming Guide", - * 15.2.4 - * - * Note that LENi == 0x10 is defined on x86_64 in long - * mode (i.e. even for 32-bit userspace software, but - * 64-bit kernel), so the x86_64 mask value is 0x5454. - * See the AMD manual no. 24593 (AMD64 System Programming) + * Put stub len and type to register (reserve) an inactive but + * correct bp */ -#ifdef CONFIG_X86_32 -#define DR7_MASK 0x5f54 -#else -#define DR7_MASK 0x5554 -#endif - data &= ~DR_CONTROL_RESERVED; - for (i = 0; i < 4; i++) - if ((DR7_MASK >> ((data >> (16 + 4*i)) & 0xf)) & 1) - return -EIO; - child->thread.debugreg7 = data; - if (data) - set_tsk_thread_flag(child, TIF_DEBUG); - else - clear_tsk_thread_flag(child, TIF_DEBUG); - break; + attr.bp_addr = addr; + attr.bp_len = HW_BREAKPOINT_LEN_1; + attr.bp_type = HW_BREAKPOINT_W; + attr.disabled = 1; + + bp = register_user_hw_breakpoint(&attr, ptrace_triggered, tsk); + } else { + bp = t->ptrace_bps[nr]; + t->ptrace_bps[nr] = NULL; + + attr = bp->attr; + attr.bp_addr = addr; + bp = modify_user_hw_breakpoint(bp, &attr, bp->callback, tsk); } + /* + * CHECKME: the previous code returned -EIO if the addr wasn't a + * valid task virtual addr. The new one will return -EINVAL in this + * case. + * -EINVAL may be what we want for in-kernel breakpoints users, but + * -EIO looks better for ptrace, since we refuse a register writing + * for the user. And anyway this is the previous behaviour. + */ + if (IS_ERR(bp)) + return PTR_ERR(bp); + + t->ptrace_bps[nr] = bp; return 0; } /* + * Handle PTRACE_POKEUSR calls for the debug register area. + */ +int ptrace_set_debugreg(struct task_struct *tsk, int n, unsigned long val) +{ + struct thread_struct *thread = &(tsk->thread); + int rc = 0; + + /* There are no DR4 or DR5 registers */ + if (n == 4 || n == 5) + return -EIO; + + if (n == 6) { + thread->debugreg6 = val; + goto ret_path; + } + if (n < HBP_NUM) { + rc = ptrace_set_breakpoint_addr(tsk, n, val); + if (rc) + return rc; + } + /* All that's left is DR7 */ + if (n == 7) + rc = ptrace_write_dr7(tsk, val); + +ret_path: + return rc; +} + +/* * These access the current or another (stopped) task's io permission * bitmap for debugging or core dump. */ diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index f93078746e00..2b97fc5b124e 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -23,7 +23,7 @@ # include <linux/ctype.h> # include <linux/mc146818rtc.h> #else -# include <asm/iommu.h> +# include <asm/x86_init.h> #endif /* @@ -622,7 +622,7 @@ void native_machine_shutdown(void) #endif #ifdef CONFIG_X86_64 - pci_iommu_shutdown(); + x86_platform.iommu_shutdown(); #endif } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 2a34f9c5be21..82e88cdda9bc 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -109,6 +109,7 @@ #ifdef CONFIG_X86_64 #include <asm/numa_64.h> #endif +#include <asm/mce.h> /* * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries. @@ -247,7 +248,7 @@ EXPORT_SYMBOL(edd); * from boot_params into a safe place. * */ -static inline void copy_edd(void) +static inline void __init copy_edd(void) { memcpy(edd.mbr_signature, boot_params.edd_mbr_sig_buffer, sizeof(edd.mbr_signature)); @@ -256,7 +257,7 @@ static inline void copy_edd(void) edd.edd_info_nr = boot_params.eddbuf_entries; } #else -static inline void copy_edd(void) +static inline void __init copy_edd(void) { } #endif @@ -1031,6 +1032,8 @@ void __init setup_arch(char **cmdline_p) #endif #endif x86_init.oem.banner(); + + mcheck_init(); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 6a44a76055ad..fbf3b07c8567 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -799,15 +799,6 @@ static void do_signal(struct pt_regs *regs) signr = get_signal_to_deliver(&info, &ka, regs, NULL); if (signr > 0) { - /* - * Re-enable any watchpoints before delivering the - * signal to user space. The processor register will - * have been cleared if the watchpoint triggered - * inside the kernel. - */ - if (current->thread.debugreg7) - set_debugreg(current->thread.debugreg7, 7); - /* Whee! Actually deliver the signal. */ if (handle_signal(signr, &info, &ka, oldset, regs) == 0) { /* diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 565ebc65920e..324f2a44c221 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1250,16 +1250,7 @@ static void __ref remove_cpu_from_maps(int cpu) void cpu_disable_common(void) { int cpu = smp_processor_id(); - /* - * HACK: - * Allow any queued timer interrupts to get serviced - * This is only a temporary solution until we cleanup - * fixup_irqs as we do for IA64. - */ - local_irq_enable(); - mdelay(1); - local_irq_disable(); remove_siblinginfo(cpu); /* It's now safe to remove this processor from the online map */ diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 7e37dcee0cc3..33399176512a 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -529,77 +529,56 @@ asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs) dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) { struct task_struct *tsk = current; - unsigned long condition; + unsigned long dr6; int si_code; - get_debugreg(condition, 6); + get_debugreg(dr6, 6); /* Catch kmemcheck conditions first of all! */ - if (condition & DR_STEP && kmemcheck_trap(regs)) + if ((dr6 & DR_STEP) && kmemcheck_trap(regs)) return; + /* DR6 may or may not be cleared by the CPU */ + set_debugreg(0, 6); /* * The processor cleared BTF, so don't mark that we need it set. */ clear_tsk_thread_flag(tsk, TIF_DEBUGCTLMSR); tsk->thread.debugctlmsr = 0; - if (notify_die(DIE_DEBUG, "debug", regs, condition, error_code, - SIGTRAP) == NOTIFY_STOP) + /* Store the virtualized DR6 value */ + tsk->thread.debugreg6 = dr6; + + if (notify_die(DIE_DEBUG, "debug", regs, PTR_ERR(&dr6), error_code, + SIGTRAP) == NOTIFY_STOP) return; /* It's safe to allow irq's after DR6 has been saved */ preempt_conditional_sti(regs); - /* Mask out spurious debug traps due to lazy DR7 setting */ - if (condition & (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3)) { - if (!tsk->thread.debugreg7) - goto clear_dr7; + if (regs->flags & X86_VM_MASK) { + handle_vm86_trap((struct kernel_vm86_regs *) regs, + error_code, 1); + return; } -#ifdef CONFIG_X86_32 - if (regs->flags & X86_VM_MASK) - goto debug_vm86; -#endif - - /* Save debug status register where ptrace can see it */ - tsk->thread.debugreg6 = condition; - /* - * Single-stepping through TF: make sure we ignore any events in - * kernel space (but re-enable TF when returning to user mode). + * Single-stepping through system calls: ignore any exceptions in + * kernel space, but re-enable TF when returning to user mode. + * + * We already checked v86 mode above, so we can check for kernel mode + * by just checking the CPL of CS. */ - if (condition & DR_STEP) { - if (!user_mode(regs)) - goto clear_TF_reenable; + if ((dr6 & DR_STEP) && !user_mode(regs)) { + tsk->thread.debugreg6 &= ~DR_STEP; + set_tsk_thread_flag(tsk, TIF_SINGLESTEP); + regs->flags &= ~X86_EFLAGS_TF; } - - si_code = get_si_code(condition); - /* Ok, finally something we can handle */ - send_sigtrap(tsk, regs, error_code, si_code); - - /* - * Disable additional traps. They'll be re-enabled when - * the signal is delivered. - */ -clear_dr7: - set_debugreg(0, 7); + si_code = get_si_code(tsk->thread.debugreg6); + if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS)) + send_sigtrap(tsk, regs, error_code, si_code); preempt_conditional_cli(regs); - return; -#ifdef CONFIG_X86_32 -debug_vm86: - /* reenable preemption: handle_vm86_trap() might sleep */ - dec_preempt_count(); - handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, 1); - conditional_cli(regs); - return; -#endif - -clear_TF_reenable: - set_tsk_thread_flag(tsk, TIF_SINGLESTEP); - regs->flags &= ~X86_EFLAGS_TF; - preempt_conditional_cli(regs); return; } diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index f37930954d15..eed156851f5d 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -114,13 +114,12 @@ void __cpuinit check_tsc_sync_source(int cpu) return; if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) { - printk_once(KERN_INFO "Skipping synchronization checks as TSC is reliable.\n"); + if (cpu == (nr_cpu_ids-1) || system_state != SYSTEM_BOOTING) + pr_info( + "Skipped synchronization checks as TSC is reliable.\n"); return; } - pr_info("checking TSC synchronization [CPU#%d -> CPU#%d]:", - smp_processor_id(), cpu); - /* * Reset it - in case this is a second bootup: */ @@ -142,12 +141,14 @@ void __cpuinit check_tsc_sync_source(int cpu) cpu_relax(); if (nr_warps) { - printk("\n"); + pr_warning("TSC synchronization [CPU#%d -> CPU#%d]:\n", + smp_processor_id(), cpu); pr_warning("Measured %Ld cycles TSC warp between CPUs, " "turning off TSC clock.\n", max_warp); mark_tsc_unstable("check_tsc_sync_source failed"); } else { - printk(" passed.\n"); + pr_debug("TSC synchronization [CPU#%d -> CPU#%d]: passed\n", + smp_processor_id(), cpu); } /* diff --git a/arch/x86/kernel/uv_irq.c b/arch/x86/kernel/uv_irq.c index aeef529917e4..61d805df4c91 100644 --- a/arch/x86/kernel/uv_irq.c +++ b/arch/x86/kernel/uv_irq.c @@ -9,10 +9,25 @@ */ #include <linux/module.h> +#include <linux/rbtree.h> #include <linux/irq.h> #include <asm/apic.h> #include <asm/uv/uv_irq.h> +#include <asm/uv/uv_hub.h> + +/* MMR offset and pnode of hub sourcing interrupts for a given irq */ +struct uv_irq_2_mmr_pnode{ + struct rb_node list; + unsigned long offset; + int pnode; + int irq; +}; + +static spinlock_t uv_irq_lock; +static struct rb_root uv_irq_root; + +static int uv_set_irq_affinity(unsigned int, const struct cpumask *); static void uv_noop(unsigned int irq) { @@ -39,25 +54,214 @@ struct irq_chip uv_irq_chip = { .unmask = uv_noop, .eoi = uv_ack_apic, .end = uv_noop, + .set_affinity = uv_set_irq_affinity, }; /* + * Add offset and pnode information of the hub sourcing interrupts to the + * rb tree for a specific irq. + */ +static int uv_set_irq_2_mmr_info(int irq, unsigned long offset, unsigned blade) +{ + struct rb_node **link = &uv_irq_root.rb_node; + struct rb_node *parent = NULL; + struct uv_irq_2_mmr_pnode *n; + struct uv_irq_2_mmr_pnode *e; + unsigned long irqflags; + + n = kmalloc_node(sizeof(struct uv_irq_2_mmr_pnode), GFP_KERNEL, + uv_blade_to_memory_nid(blade)); + if (!n) + return -ENOMEM; + + n->irq = irq; + n->offset = offset; + n->pnode = uv_blade_to_pnode(blade); + spin_lock_irqsave(&uv_irq_lock, irqflags); + /* Find the right place in the rbtree: */ + while (*link) { + parent = *link; + e = rb_entry(parent, struct uv_irq_2_mmr_pnode, list); + + if (unlikely(irq == e->irq)) { + /* irq entry exists */ + e->pnode = uv_blade_to_pnode(blade); + e->offset = offset; + spin_unlock_irqrestore(&uv_irq_lock, irqflags); + kfree(n); + return 0; + } + + if (irq < e->irq) + link = &(*link)->rb_left; + else + link = &(*link)->rb_right; + } + + /* Insert the node into the rbtree. */ + rb_link_node(&n->list, parent, link); + rb_insert_color(&n->list, &uv_irq_root); + + spin_unlock_irqrestore(&uv_irq_lock, irqflags); + return 0; +} + +/* Retrieve offset and pnode information from the rb tree for a specific irq */ +int uv_irq_2_mmr_info(int irq, unsigned long *offset, int *pnode) +{ + struct uv_irq_2_mmr_pnode *e; + struct rb_node *n; + unsigned long irqflags; + + spin_lock_irqsave(&uv_irq_lock, irqflags); + n = uv_irq_root.rb_node; + while (n) { + e = rb_entry(n, struct uv_irq_2_mmr_pnode, list); + + if (e->irq == irq) { + *offset = e->offset; + *pnode = e->pnode; + spin_unlock_irqrestore(&uv_irq_lock, irqflags); + return 0; + } + + if (irq < e->irq) + n = n->rb_left; + else + n = n->rb_right; + } + spin_unlock_irqrestore(&uv_irq_lock, irqflags); + return -1; +} + +/* + * Re-target the irq to the specified CPU and enable the specified MMR located + * on the specified blade to allow the sending of MSIs to the specified CPU. + */ +static int +arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade, + unsigned long mmr_offset, int restrict) +{ + const struct cpumask *eligible_cpu = cpumask_of(cpu); + struct irq_desc *desc = irq_to_desc(irq); + struct irq_cfg *cfg; + int mmr_pnode; + unsigned long mmr_value; + struct uv_IO_APIC_route_entry *entry; + int err; + + BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != + sizeof(unsigned long)); + + cfg = irq_cfg(irq); + + err = assign_irq_vector(irq, cfg, eligible_cpu); + if (err != 0) + return err; + + if (restrict == UV_AFFINITY_CPU) + desc->status |= IRQ_NO_BALANCING; + else + desc->status |= IRQ_MOVE_PCNTXT; + + set_irq_chip_and_handler_name(irq, &uv_irq_chip, handle_percpu_irq, + irq_name); + + mmr_value = 0; + entry = (struct uv_IO_APIC_route_entry *)&mmr_value; + entry->vector = cfg->vector; + entry->delivery_mode = apic->irq_delivery_mode; + entry->dest_mode = apic->irq_dest_mode; + entry->polarity = 0; + entry->trigger = 0; + entry->mask = 0; + entry->dest = apic->cpu_mask_to_apicid(eligible_cpu); + + mmr_pnode = uv_blade_to_pnode(mmr_blade); + uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value); + + if (cfg->move_in_progress) + send_cleanup_vector(cfg); + + return irq; +} + +/* + * Disable the specified MMR located on the specified blade so that MSIs are + * longer allowed to be sent. + */ +static void arch_disable_uv_irq(int mmr_pnode, unsigned long mmr_offset) +{ + unsigned long mmr_value; + struct uv_IO_APIC_route_entry *entry; + + BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != + sizeof(unsigned long)); + + mmr_value = 0; + entry = (struct uv_IO_APIC_route_entry *)&mmr_value; + entry->mask = 1; + + uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value); +} + +static int uv_set_irq_affinity(unsigned int irq, const struct cpumask *mask) +{ + struct irq_desc *desc = irq_to_desc(irq); + struct irq_cfg *cfg = desc->chip_data; + unsigned int dest; + unsigned long mmr_value; + struct uv_IO_APIC_route_entry *entry; + unsigned long mmr_offset; + unsigned mmr_pnode; + + dest = set_desc_affinity(desc, mask); + if (dest == BAD_APICID) + return -1; + + mmr_value = 0; + entry = (struct uv_IO_APIC_route_entry *)&mmr_value; + + entry->vector = cfg->vector; + entry->delivery_mode = apic->irq_delivery_mode; + entry->dest_mode = apic->irq_dest_mode; + entry->polarity = 0; + entry->trigger = 0; + entry->mask = 0; + entry->dest = dest; + + /* Get previously stored MMR and pnode of hub sourcing interrupts */ + if (uv_irq_2_mmr_info(irq, &mmr_offset, &mmr_pnode)) + return -1; + + uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value); + + if (cfg->move_in_progress) + send_cleanup_vector(cfg); + + return 0; +} + +/* * Set up a mapping of an available irq and vector, and enable the specified * MMR that defines the MSI that is to be sent to the specified CPU when an * interrupt is raised. */ int uv_setup_irq(char *irq_name, int cpu, int mmr_blade, - unsigned long mmr_offset) + unsigned long mmr_offset, int restrict) { - int irq; - int ret; + int irq, ret; + + irq = create_irq_nr(NR_IRQS_LEGACY, uv_blade_to_memory_nid(mmr_blade)); - irq = create_irq(); if (irq <= 0) return -EBUSY; - ret = arch_enable_uv_irq(irq_name, irq, cpu, mmr_blade, mmr_offset); - if (ret != irq) + ret = arch_enable_uv_irq(irq_name, irq, cpu, mmr_blade, mmr_offset, + restrict); + if (ret == irq) + uv_set_irq_2_mmr_info(irq, mmr_offset, mmr_blade); + else destroy_irq(irq); return ret; @@ -71,9 +275,28 @@ EXPORT_SYMBOL_GPL(uv_setup_irq); * * Set mmr_blade and mmr_offset to what was passed in on uv_setup_irq(). */ -void uv_teardown_irq(unsigned int irq, int mmr_blade, unsigned long mmr_offset) +void uv_teardown_irq(unsigned int irq) { - arch_disable_uv_irq(mmr_blade, mmr_offset); + struct uv_irq_2_mmr_pnode *e; + struct rb_node *n; + unsigned long irqflags; + + spin_lock_irqsave(&uv_irq_lock, irqflags); + n = uv_irq_root.rb_node; + while (n) { + e = rb_entry(n, struct uv_irq_2_mmr_pnode, list); + if (e->irq == irq) { + arch_disable_uv_irq(e->pnode, e->offset); + rb_erase(n, &uv_irq_root); + kfree(e); + break; + } + if (irq < e->irq) + n = n->rb_left; + else + n = n->rb_right; + } + spin_unlock_irqrestore(&uv_irq_lock, irqflags); destroy_irq(irq); } EXPORT_SYMBOL_GPL(uv_teardown_irq); diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c index f068553a1b17..abda6f53e71e 100644 --- a/arch/x86/kernel/visws_quirks.c +++ b/arch/x86/kernel/visws_quirks.c @@ -183,7 +183,7 @@ static void __init MP_processor_info(struct mpc_cpu *m) return; } - apic_cpus = apic->apicid_to_cpu_present(m->apicid); + apic->apicid_to_cpu_present(m->apicid, &apic_cpus); physids_or(phys_cpu_present_map, phys_cpu_present_map, apic_cpus); /* * Validate version @@ -486,7 +486,7 @@ static void end_cobalt_irq(unsigned int irq) } static struct irq_chip cobalt_irq_type = { - .typename = "Cobalt-APIC", + .name = "Cobalt-APIC", .startup = startup_cobalt_irq, .shutdown = disable_cobalt_irq, .enable = enable_cobalt_irq, @@ -523,7 +523,7 @@ static void end_piix4_master_irq(unsigned int irq) } static struct irq_chip piix4_master_irq_type = { - .typename = "PIIX4-master", + .name = "PIIX4-master", .startup = startup_piix4_master_irq, .ack = ack_cobalt_irq, .end = end_piix4_master_irq, @@ -531,7 +531,7 @@ static struct irq_chip piix4_master_irq_type = { static struct irq_chip piix4_virtual_irq_type = { - .typename = "PIIX4-virtual", + .name = "PIIX4-virtual", .shutdown = disable_8259A_irq, .enable = enable_8259A_irq, .disable = disable_8259A_irq, diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 8cb4974ff599..e02d92d12bcd 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -237,7 +237,7 @@ static ctl_table kernel_table2[] = { }; static ctl_table kernel_root_table2[] = { - { .ctl_name = CTL_KERN, .procname = "kernel", .mode = 0555, + { .procname = "kernel", .mode = 0555, .child = kernel_table2 }, {} }; diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index 3909e3ba5ce3..a1029769b6f2 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -30,9 +30,8 @@ EXPORT_SYMBOL(__put_user_8); EXPORT_SYMBOL(copy_user_generic); EXPORT_SYMBOL(__copy_user_nocache); -EXPORT_SYMBOL(copy_from_user); -EXPORT_SYMBOL(copy_to_user); -EXPORT_SYMBOL(__copy_from_user_inatomic); +EXPORT_SYMBOL(_copy_from_user); +EXPORT_SYMBOL(_copy_to_user); EXPORT_SYMBOL(copy_page); EXPORT_SYMBOL(clear_page); diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 4449a4a2c2ed..d11c5ff7c65e 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -14,10 +14,13 @@ #include <asm/time.h> #include <asm/irq.h> #include <asm/tsc.h> +#include <asm/iommu.h> void __cpuinit x86_init_noop(void) { } void __init x86_init_uint_noop(unsigned int unused) { } void __init x86_init_pgd_noop(pgd_t *unused) { } +int __init iommu_init_noop(void) { return 0; } +void iommu_shutdown_noop(void) { } /* * The platform setup functions are preset with the default functions @@ -62,6 +65,10 @@ struct x86_init_ops x86_init __initdata = { .tsc_pre_init = x86_init_noop, .timer_init = hpet_time_init, }, + + .iommu = { + .iommu_init = iommu_init_noop, + }, }; struct x86_cpuinit_ops x86_cpuinit __cpuinitdata = { @@ -72,4 +79,5 @@ struct x86_platform_ops x86_platform = { .calibrate_tsc = native_calibrate_tsc, .get_wallclock = mach_get_cmos_time, .set_wallclock = mach_set_rtc_mmss, + .iommu_shutdown = iommu_shutdown_noop, }; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ae07d261527c..4fc80174191c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -42,6 +42,7 @@ #define CREATE_TRACE_POINTS #include "trace.h" +#include <asm/debugreg.h> #include <asm/uaccess.h> #include <asm/msr.h> #include <asm/desc.h> @@ -3643,14 +3644,15 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) trace_kvm_entry(vcpu->vcpu_id); kvm_x86_ops->run(vcpu, kvm_run); - if (unlikely(vcpu->arch.switch_db_regs || test_thread_flag(TIF_DEBUG))) { - set_debugreg(current->thread.debugreg0, 0); - set_debugreg(current->thread.debugreg1, 1); - set_debugreg(current->thread.debugreg2, 2); - set_debugreg(current->thread.debugreg3, 3); - set_debugreg(current->thread.debugreg6, 6); - set_debugreg(current->thread.debugreg7, 7); - } + /* + * If the guest has used debug registers, at least dr7 + * will be disabled while returning to the host. + * If we don't have active breakpoints in the host, we don't + * care about the messed up debug address registers. But if + * we have some of them active, restore the old state. + */ + if (hw_breakpoint_active()) + hw_breakpoint_restore(); set_bit(KVM_REQ_KICK, &vcpu->requests); local_irq_enable(); diff --git a/arch/x86/lib/.gitignore b/arch/x86/lib/.gitignore new file mode 100644 index 000000000000..8df89f0a3fe6 --- /dev/null +++ b/arch/x86/lib/.gitignore @@ -0,0 +1 @@ +inat-tables.c diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 85f5db95c60f..a2d6472895fb 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -2,12 +2,25 @@ # Makefile for x86 specific library files. # +inat_tables_script = $(srctree)/arch/x86/tools/gen-insn-attr-x86.awk +inat_tables_maps = $(srctree)/arch/x86/lib/x86-opcode-map.txt +quiet_cmd_inat_tables = GEN $@ + cmd_inat_tables = $(AWK) -f $(inat_tables_script) $(inat_tables_maps) > $@ + +$(obj)/inat-tables.c: $(inat_tables_script) $(inat_tables_maps) + $(call cmd,inat_tables) + +$(obj)/inat.o: $(obj)/inat-tables.c + +clean-files := inat-tables.c + obj-$(CONFIG_SMP) := msr.o lib-y := delay.o lib-y += thunk_$(BITS).o lib-y += usercopy_$(BITS).o getuser.o putuser.o lib-y += memcpy_$(BITS).o +lib-y += insn.o inat.o obj-y += msr-reg.o msr-reg-export.o diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index 6ba0f7bb85ea..cf889d4e076a 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -65,7 +65,7 @@ .endm /* Standard copy_to_user with segment limit checking */ -ENTRY(copy_to_user) +ENTRY(_copy_to_user) CFI_STARTPROC GET_THREAD_INFO(%rax) movq %rdi,%rcx @@ -75,10 +75,10 @@ ENTRY(copy_to_user) jae bad_to_user ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string CFI_ENDPROC -ENDPROC(copy_to_user) +ENDPROC(_copy_to_user) /* Standard copy_from_user with segment limit checking */ -ENTRY(copy_from_user) +ENTRY(_copy_from_user) CFI_STARTPROC GET_THREAD_INFO(%rax) movq %rsi,%rcx @@ -88,7 +88,7 @@ ENTRY(copy_from_user) jae bad_from_user ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string CFI_ENDPROC -ENDPROC(copy_from_user) +ENDPROC(_copy_from_user) ENTRY(copy_user_generic) CFI_STARTPROC @@ -96,12 +96,6 @@ ENTRY(copy_user_generic) CFI_ENDPROC ENDPROC(copy_user_generic) -ENTRY(__copy_from_user_inatomic) - CFI_STARTPROC - ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string - CFI_ENDPROC -ENDPROC(__copy_from_user_inatomic) - .section .fixup,"ax" /* must zero dest */ ENTRY(bad_from_user) diff --git a/arch/x86/lib/inat.c b/arch/x86/lib/inat.c new file mode 100644 index 000000000000..46fc4ee09fc4 --- /dev/null +++ b/arch/x86/lib/inat.c @@ -0,0 +1,90 @@ +/* + * x86 instruction attribute tables + * + * Written by Masami Hiramatsu <mhiramat@redhat.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + */ +#include <asm/insn.h> + +/* Attribute tables are generated from opcode map */ +#include "inat-tables.c" + +/* Attribute search APIs */ +insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode) +{ + return inat_primary_table[opcode]; +} + +insn_attr_t inat_get_escape_attribute(insn_byte_t opcode, insn_byte_t last_pfx, + insn_attr_t esc_attr) +{ + const insn_attr_t *table; + insn_attr_t lpfx_attr; + int n, m = 0; + + n = inat_escape_id(esc_attr); + if (last_pfx) { + lpfx_attr = inat_get_opcode_attribute(last_pfx); + m = inat_last_prefix_id(lpfx_attr); + } + table = inat_escape_tables[n][0]; + if (!table) + return 0; + if (inat_has_variant(table[opcode]) && m) { + table = inat_escape_tables[n][m]; + if (!table) + return 0; + } + return table[opcode]; +} + +insn_attr_t inat_get_group_attribute(insn_byte_t modrm, insn_byte_t last_pfx, + insn_attr_t grp_attr) +{ + const insn_attr_t *table; + insn_attr_t lpfx_attr; + int n, m = 0; + + n = inat_group_id(grp_attr); + if (last_pfx) { + lpfx_attr = inat_get_opcode_attribute(last_pfx); + m = inat_last_prefix_id(lpfx_attr); + } + table = inat_group_tables[n][0]; + if (!table) + return inat_group_common_attribute(grp_attr); + if (inat_has_variant(table[X86_MODRM_REG(modrm)]) && m) { + table = inat_group_tables[n][m]; + if (!table) + return inat_group_common_attribute(grp_attr); + } + return table[X86_MODRM_REG(modrm)] | + inat_group_common_attribute(grp_attr); +} + +insn_attr_t inat_get_avx_attribute(insn_byte_t opcode, insn_byte_t vex_m, + insn_byte_t vex_p) +{ + const insn_attr_t *table; + if (vex_m > X86_VEX_M_MAX || vex_p > INAT_LSTPFX_MAX) + return 0; + table = inat_avx_tables[vex_m][vex_p]; + if (!table) + return 0; + return table[opcode]; +} + diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c new file mode 100644 index 000000000000..9f33b984d0ef --- /dev/null +++ b/arch/x86/lib/insn.c @@ -0,0 +1,516 @@ +/* + * x86 instruction analysis + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) IBM Corporation, 2002, 2004, 2009 + */ + +#include <linux/string.h> +#include <asm/inat.h> +#include <asm/insn.h> + +#define get_next(t, insn) \ + ({t r; r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); r; }) + +#define peek_next(t, insn) \ + ({t r; r = *(t*)insn->next_byte; r; }) + +#define peek_nbyte_next(t, insn, n) \ + ({t r; r = *(t*)((insn)->next_byte + n); r; }) + +/** + * insn_init() - initialize struct insn + * @insn: &struct insn to be initialized + * @kaddr: address (in kernel memory) of instruction (or copy thereof) + * @x86_64: !0 for 64-bit kernel or 64-bit app + */ +void insn_init(struct insn *insn, const void *kaddr, int x86_64) +{ + memset(insn, 0, sizeof(*insn)); + insn->kaddr = kaddr; + insn->next_byte = kaddr; + insn->x86_64 = x86_64 ? 1 : 0; + insn->opnd_bytes = 4; + if (x86_64) + insn->addr_bytes = 8; + else + insn->addr_bytes = 4; +} + +/** + * insn_get_prefixes - scan x86 instruction prefix bytes + * @insn: &struct insn containing instruction + * + * Populates the @insn->prefixes bitmap, and updates @insn->next_byte + * to point to the (first) opcode. No effect if @insn->prefixes.got + * is already set. + */ +void insn_get_prefixes(struct insn *insn) +{ + struct insn_field *prefixes = &insn->prefixes; + insn_attr_t attr; + insn_byte_t b, lb; + int i, nb; + + if (prefixes->got) + return; + + nb = 0; + lb = 0; + b = peek_next(insn_byte_t, insn); + attr = inat_get_opcode_attribute(b); + while (inat_is_legacy_prefix(attr)) { + /* Skip if same prefix */ + for (i = 0; i < nb; i++) + if (prefixes->bytes[i] == b) + goto found; + if (nb == 4) + /* Invalid instruction */ + break; + prefixes->bytes[nb++] = b; + if (inat_is_address_size_prefix(attr)) { + /* address size switches 2/4 or 4/8 */ + if (insn->x86_64) + insn->addr_bytes ^= 12; + else + insn->addr_bytes ^= 6; + } else if (inat_is_operand_size_prefix(attr)) { + /* oprand size switches 2/4 */ + insn->opnd_bytes ^= 6; + } +found: + prefixes->nbytes++; + insn->next_byte++; + lb = b; + b = peek_next(insn_byte_t, insn); + attr = inat_get_opcode_attribute(b); + } + /* Set the last prefix */ + if (lb && lb != insn->prefixes.bytes[3]) { + if (unlikely(insn->prefixes.bytes[3])) { + /* Swap the last prefix */ + b = insn->prefixes.bytes[3]; + for (i = 0; i < nb; i++) + if (prefixes->bytes[i] == lb) + prefixes->bytes[i] = b; + } + insn->prefixes.bytes[3] = lb; + } + + /* Decode REX prefix */ + if (insn->x86_64) { + b = peek_next(insn_byte_t, insn); + attr = inat_get_opcode_attribute(b); + if (inat_is_rex_prefix(attr)) { + insn->rex_prefix.value = b; + insn->rex_prefix.nbytes = 1; + insn->next_byte++; + if (X86_REX_W(b)) + /* REX.W overrides opnd_size */ + insn->opnd_bytes = 8; + } + } + insn->rex_prefix.got = 1; + + /* Decode VEX prefix */ + b = peek_next(insn_byte_t, insn); + attr = inat_get_opcode_attribute(b); + if (inat_is_vex_prefix(attr)) { + insn_byte_t b2 = peek_nbyte_next(insn_byte_t, insn, 1); + if (!insn->x86_64) { + /* + * In 32-bits mode, if the [7:6] bits (mod bits of + * ModRM) on the second byte are not 11b, it is + * LDS or LES. + */ + if (X86_MODRM_MOD(b2) != 3) + goto vex_end; + } + insn->vex_prefix.bytes[0] = b; + insn->vex_prefix.bytes[1] = b2; + if (inat_is_vex3_prefix(attr)) { + b2 = peek_nbyte_next(insn_byte_t, insn, 2); + insn->vex_prefix.bytes[2] = b2; + insn->vex_prefix.nbytes = 3; + insn->next_byte += 3; + if (insn->x86_64 && X86_VEX_W(b2)) + /* VEX.W overrides opnd_size */ + insn->opnd_bytes = 8; + } else { + insn->vex_prefix.nbytes = 2; + insn->next_byte += 2; + } + } +vex_end: + insn->vex_prefix.got = 1; + + prefixes->got = 1; + return; +} + +/** + * insn_get_opcode - collect opcode(s) + * @insn: &struct insn containing instruction + * + * Populates @insn->opcode, updates @insn->next_byte to point past the + * opcode byte(s), and set @insn->attr (except for groups). + * If necessary, first collects any preceding (prefix) bytes. + * Sets @insn->opcode.value = opcode1. No effect if @insn->opcode.got + * is already 1. + */ +void insn_get_opcode(struct insn *insn) +{ + struct insn_field *opcode = &insn->opcode; + insn_byte_t op, pfx; + if (opcode->got) + return; + if (!insn->prefixes.got) + insn_get_prefixes(insn); + + /* Get first opcode */ + op = get_next(insn_byte_t, insn); + opcode->bytes[0] = op; + opcode->nbytes = 1; + + /* Check if there is VEX prefix or not */ + if (insn_is_avx(insn)) { + insn_byte_t m, p; + m = insn_vex_m_bits(insn); + p = insn_vex_p_bits(insn); + insn->attr = inat_get_avx_attribute(op, m, p); + if (!inat_accept_vex(insn->attr)) + insn->attr = 0; /* This instruction is bad */ + goto end; /* VEX has only 1 byte for opcode */ + } + + insn->attr = inat_get_opcode_attribute(op); + while (inat_is_escape(insn->attr)) { + /* Get escaped opcode */ + op = get_next(insn_byte_t, insn); + opcode->bytes[opcode->nbytes++] = op; + pfx = insn_last_prefix(insn); + insn->attr = inat_get_escape_attribute(op, pfx, insn->attr); + } + if (inat_must_vex(insn->attr)) + insn->attr = 0; /* This instruction is bad */ +end: + opcode->got = 1; +} + +/** + * insn_get_modrm - collect ModRM byte, if any + * @insn: &struct insn containing instruction + * + * Populates @insn->modrm and updates @insn->next_byte to point past the + * ModRM byte, if any. If necessary, first collects the preceding bytes + * (prefixes and opcode(s)). No effect if @insn->modrm.got is already 1. + */ +void insn_get_modrm(struct insn *insn) +{ + struct insn_field *modrm = &insn->modrm; + insn_byte_t pfx, mod; + if (modrm->got) + return; + if (!insn->opcode.got) + insn_get_opcode(insn); + + if (inat_has_modrm(insn->attr)) { + mod = get_next(insn_byte_t, insn); + modrm->value = mod; + modrm->nbytes = 1; + if (inat_is_group(insn->attr)) { + pfx = insn_last_prefix(insn); + insn->attr = inat_get_group_attribute(mod, pfx, + insn->attr); + } + } + + if (insn->x86_64 && inat_is_force64(insn->attr)) + insn->opnd_bytes = 8; + modrm->got = 1; +} + + +/** + * insn_rip_relative() - Does instruction use RIP-relative addressing mode? + * @insn: &struct insn containing instruction + * + * If necessary, first collects the instruction up to and including the + * ModRM byte. No effect if @insn->x86_64 is 0. + */ +int insn_rip_relative(struct insn *insn) +{ + struct insn_field *modrm = &insn->modrm; + + if (!insn->x86_64) + return 0; + if (!modrm->got) + insn_get_modrm(insn); + /* + * For rip-relative instructions, the mod field (top 2 bits) + * is zero and the r/m field (bottom 3 bits) is 0x5. + */ + return (modrm->nbytes && (modrm->value & 0xc7) == 0x5); +} + +/** + * insn_get_sib() - Get the SIB byte of instruction + * @insn: &struct insn containing instruction + * + * If necessary, first collects the instruction up to and including the + * ModRM byte. + */ +void insn_get_sib(struct insn *insn) +{ + insn_byte_t modrm; + + if (insn->sib.got) + return; + if (!insn->modrm.got) + insn_get_modrm(insn); + if (insn->modrm.nbytes) { + modrm = (insn_byte_t)insn->modrm.value; + if (insn->addr_bytes != 2 && + X86_MODRM_MOD(modrm) != 3 && X86_MODRM_RM(modrm) == 4) { + insn->sib.value = get_next(insn_byte_t, insn); + insn->sib.nbytes = 1; + } + } + insn->sib.got = 1; +} + + +/** + * insn_get_displacement() - Get the displacement of instruction + * @insn: &struct insn containing instruction + * + * If necessary, first collects the instruction up to and including the + * SIB byte. + * Displacement value is sign-expanded. + */ +void insn_get_displacement(struct insn *insn) +{ + insn_byte_t mod, rm, base; + + if (insn->displacement.got) + return; + if (!insn->sib.got) + insn_get_sib(insn); + if (insn->modrm.nbytes) { + /* + * Interpreting the modrm byte: + * mod = 00 - no displacement fields (exceptions below) + * mod = 01 - 1-byte displacement field + * mod = 10 - displacement field is 4 bytes, or 2 bytes if + * address size = 2 (0x67 prefix in 32-bit mode) + * mod = 11 - no memory operand + * + * If address size = 2... + * mod = 00, r/m = 110 - displacement field is 2 bytes + * + * If address size != 2... + * mod != 11, r/m = 100 - SIB byte exists + * mod = 00, SIB base = 101 - displacement field is 4 bytes + * mod = 00, r/m = 101 - rip-relative addressing, displacement + * field is 4 bytes + */ + mod = X86_MODRM_MOD(insn->modrm.value); + rm = X86_MODRM_RM(insn->modrm.value); + base = X86_SIB_BASE(insn->sib.value); + if (mod == 3) + goto out; + if (mod == 1) { + insn->displacement.value = get_next(char, insn); + insn->displacement.nbytes = 1; + } else if (insn->addr_bytes == 2) { + if ((mod == 0 && rm == 6) || mod == 2) { + insn->displacement.value = + get_next(short, insn); + insn->displacement.nbytes = 2; + } + } else { + if ((mod == 0 && rm == 5) || mod == 2 || + (mod == 0 && base == 5)) { + insn->displacement.value = get_next(int, insn); + insn->displacement.nbytes = 4; + } + } + } +out: + insn->displacement.got = 1; +} + +/* Decode moffset16/32/64 */ +static void __get_moffset(struct insn *insn) +{ + switch (insn->addr_bytes) { + case 2: + insn->moffset1.value = get_next(short, insn); + insn->moffset1.nbytes = 2; + break; + case 4: + insn->moffset1.value = get_next(int, insn); + insn->moffset1.nbytes = 4; + break; + case 8: + insn->moffset1.value = get_next(int, insn); + insn->moffset1.nbytes = 4; + insn->moffset2.value = get_next(int, insn); + insn->moffset2.nbytes = 4; + break; + } + insn->moffset1.got = insn->moffset2.got = 1; +} + +/* Decode imm v32(Iz) */ +static void __get_immv32(struct insn *insn) +{ + switch (insn->opnd_bytes) { + case 2: + insn->immediate.value = get_next(short, insn); + insn->immediate.nbytes = 2; + break; + case 4: + case 8: + insn->immediate.value = get_next(int, insn); + insn->immediate.nbytes = 4; + break; + } +} + +/* Decode imm v64(Iv/Ov) */ +static void __get_immv(struct insn *insn) +{ + switch (insn->opnd_bytes) { + case 2: + insn->immediate1.value = get_next(short, insn); + insn->immediate1.nbytes = 2; + break; + case 4: + insn->immediate1.value = get_next(int, insn); + insn->immediate1.nbytes = 4; + break; + case 8: + insn->immediate1.value = get_next(int, insn); + insn->immediate1.nbytes = 4; + insn->immediate2.value = get_next(int, insn); + insn->immediate2.nbytes = 4; + break; + } + insn->immediate1.got = insn->immediate2.got = 1; +} + +/* Decode ptr16:16/32(Ap) */ +static void __get_immptr(struct insn *insn) +{ + switch (insn->opnd_bytes) { + case 2: + insn->immediate1.value = get_next(short, insn); + insn->immediate1.nbytes = 2; + break; + case 4: + insn->immediate1.value = get_next(int, insn); + insn->immediate1.nbytes = 4; + break; + case 8: + /* ptr16:64 is not exist (no segment) */ + return; + } + insn->immediate2.value = get_next(unsigned short, insn); + insn->immediate2.nbytes = 2; + insn->immediate1.got = insn->immediate2.got = 1; +} + +/** + * insn_get_immediate() - Get the immediates of instruction + * @insn: &struct insn containing instruction + * + * If necessary, first collects the instruction up to and including the + * displacement bytes. + * Basically, most of immediates are sign-expanded. Unsigned-value can be + * get by bit masking with ((1 << (nbytes * 8)) - 1) + */ +void insn_get_immediate(struct insn *insn) +{ + if (insn->immediate.got) + return; + if (!insn->displacement.got) + insn_get_displacement(insn); + + if (inat_has_moffset(insn->attr)) { + __get_moffset(insn); + goto done; + } + + if (!inat_has_immediate(insn->attr)) + /* no immediates */ + goto done; + + switch (inat_immediate_size(insn->attr)) { + case INAT_IMM_BYTE: + insn->immediate.value = get_next(char, insn); + insn->immediate.nbytes = 1; + break; + case INAT_IMM_WORD: + insn->immediate.value = get_next(short, insn); + insn->immediate.nbytes = 2; + break; + case INAT_IMM_DWORD: + insn->immediate.value = get_next(int, insn); + insn->immediate.nbytes = 4; + break; + case INAT_IMM_QWORD: + insn->immediate1.value = get_next(int, insn); + insn->immediate1.nbytes = 4; + insn->immediate2.value = get_next(int, insn); + insn->immediate2.nbytes = 4; + break; + case INAT_IMM_PTR: + __get_immptr(insn); + break; + case INAT_IMM_VWORD32: + __get_immv32(insn); + break; + case INAT_IMM_VWORD: + __get_immv(insn); + break; + default: + break; + } + if (inat_has_second_immediate(insn->attr)) { + insn->immediate2.value = get_next(char, insn); + insn->immediate2.nbytes = 1; + } +done: + insn->immediate.got = 1; +} + +/** + * insn_get_length() - Get the length of instruction + * @insn: &struct insn containing instruction + * + * If necessary, first collects the instruction up to and including the + * immediates bytes. + */ +void insn_get_length(struct insn *insn) +{ + if (insn->length) + return; + if (!insn->immediate.got) + insn_get_immediate(insn); + insn->length = (unsigned char)((unsigned long)insn->next_byte + - (unsigned long)insn->kaddr); +} diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c index 33a1e3ca22d8..41628b104b9e 100644 --- a/arch/x86/lib/msr.c +++ b/arch/x86/lib/msr.c @@ -71,14 +71,9 @@ int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) } EXPORT_SYMBOL(wrmsr_on_cpu); -/* rdmsr on a bunch of CPUs - * - * @mask: which CPUs - * @msr_no: which MSR - * @msrs: array of MSR values - * - */ -void rdmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs) +static void __rwmsr_on_cpus(const struct cpumask *mask, u32 msr_no, + struct msr *msrs, + void (*msr_func) (void *info)) { struct msr_info rv; int this_cpu; @@ -92,11 +87,23 @@ void rdmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs) this_cpu = get_cpu(); if (cpumask_test_cpu(this_cpu, mask)) - __rdmsr_on_cpu(&rv); + msr_func(&rv); - smp_call_function_many(mask, __rdmsr_on_cpu, &rv, 1); + smp_call_function_many(mask, msr_func, &rv, 1); put_cpu(); } + +/* rdmsr on a bunch of CPUs + * + * @mask: which CPUs + * @msr_no: which MSR + * @msrs: array of MSR values + * + */ +void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs) +{ + __rwmsr_on_cpus(mask, msr_no, msrs, __rdmsr_on_cpu); +} EXPORT_SYMBOL(rdmsr_on_cpus); /* @@ -107,24 +114,9 @@ EXPORT_SYMBOL(rdmsr_on_cpus); * @msrs: array of MSR values * */ -void wrmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs) +void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs) { - struct msr_info rv; - int this_cpu; - - memset(&rv, 0, sizeof(rv)); - - rv.off = cpumask_first(mask); - rv.msrs = msrs; - rv.msr_no = msr_no; - - this_cpu = get_cpu(); - - if (cpumask_test_cpu(this_cpu, mask)) - __wrmsr_on_cpu(&rv); - - smp_call_function_many(mask, __wrmsr_on_cpu, &rv, 1); - put_cpu(); + __rwmsr_on_cpus(mask, msr_no, msrs, __wrmsr_on_cpu); } EXPORT_SYMBOL(wrmsr_on_cpus); diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c index 1f118d462acc..e218d5df85ff 100644 --- a/arch/x86/lib/usercopy_32.c +++ b/arch/x86/lib/usercopy_32.c @@ -874,7 +874,7 @@ EXPORT_SYMBOL(copy_to_user); * data to the requested size using zero bytes. */ unsigned long -copy_from_user(void *to, const void __user *from, unsigned long n) +_copy_from_user(void *to, const void __user *from, unsigned long n) { if (access_ok(VERIFY_READ, from, n)) n = __copy_from_user(to, from, n); @@ -882,4 +882,10 @@ copy_from_user(void *to, const void __user *from, unsigned long n) memset(to, 0, n); return n; } -EXPORT_SYMBOL(copy_from_user); +EXPORT_SYMBOL(_copy_from_user); + +void copy_from_user_overflow(void) +{ + WARN(1, "Buffer overflow detected!\n"); +} +EXPORT_SYMBOL(copy_from_user_overflow); diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt new file mode 100644 index 000000000000..a793da5e560e --- /dev/null +++ b/arch/x86/lib/x86-opcode-map.txt @@ -0,0 +1,893 @@ +# x86 Opcode Maps +# +#<Opcode maps> +# Table: table-name +# Referrer: escaped-name +# AVXcode: avx-code +# opcode: mnemonic|GrpXXX [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...] +# (or) +# opcode: escape # escaped-name +# EndTable +# +#<group maps> +# GrpTable: GrpXXX +# reg: mnemonic [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...] +# EndTable +# +# AVX Superscripts +# (VEX): this opcode can accept VEX prefix. +# (oVEX): this opcode requires VEX prefix. +# (o128): this opcode only supports 128bit VEX. +# (o256): this opcode only supports 256bit VEX. +# + +Table: one byte opcode +Referrer: +AVXcode: +# 0x00 - 0x0f +00: ADD Eb,Gb +01: ADD Ev,Gv +02: ADD Gb,Eb +03: ADD Gv,Ev +04: ADD AL,Ib +05: ADD rAX,Iz +06: PUSH ES (i64) +07: POP ES (i64) +08: OR Eb,Gb +09: OR Ev,Gv +0a: OR Gb,Eb +0b: OR Gv,Ev +0c: OR AL,Ib +0d: OR rAX,Iz +0e: PUSH CS (i64) +0f: escape # 2-byte escape +# 0x10 - 0x1f +10: ADC Eb,Gb +11: ADC Ev,Gv +12: ADC Gb,Eb +13: ADC Gv,Ev +14: ADC AL,Ib +15: ADC rAX,Iz +16: PUSH SS (i64) +17: POP SS (i64) +18: SBB Eb,Gb +19: SBB Ev,Gv +1a: SBB Gb,Eb +1b: SBB Gv,Ev +1c: SBB AL,Ib +1d: SBB rAX,Iz +1e: PUSH DS (i64) +1f: POP DS (i64) +# 0x20 - 0x2f +20: AND Eb,Gb +21: AND Ev,Gv +22: AND Gb,Eb +23: AND Gv,Ev +24: AND AL,Ib +25: AND rAx,Iz +26: SEG=ES (Prefix) +27: DAA (i64) +28: SUB Eb,Gb +29: SUB Ev,Gv +2a: SUB Gb,Eb +2b: SUB Gv,Ev +2c: SUB AL,Ib +2d: SUB rAX,Iz +2e: SEG=CS (Prefix) +2f: DAS (i64) +# 0x30 - 0x3f +30: XOR Eb,Gb +31: XOR Ev,Gv +32: XOR Gb,Eb +33: XOR Gv,Ev +34: XOR AL,Ib +35: XOR rAX,Iz +36: SEG=SS (Prefix) +37: AAA (i64) +38: CMP Eb,Gb +39: CMP Ev,Gv +3a: CMP Gb,Eb +3b: CMP Gv,Ev +3c: CMP AL,Ib +3d: CMP rAX,Iz +3e: SEG=DS (Prefix) +3f: AAS (i64) +# 0x40 - 0x4f +40: INC eAX (i64) | REX (o64) +41: INC eCX (i64) | REX.B (o64) +42: INC eDX (i64) | REX.X (o64) +43: INC eBX (i64) | REX.XB (o64) +44: INC eSP (i64) | REX.R (o64) +45: INC eBP (i64) | REX.RB (o64) +46: INC eSI (i64) | REX.RX (o64) +47: INC eDI (i64) | REX.RXB (o64) +48: DEC eAX (i64) | REX.W (o64) +49: DEC eCX (i64) | REX.WB (o64) +4a: DEC eDX (i64) | REX.WX (o64) +4b: DEC eBX (i64) | REX.WXB (o64) +4c: DEC eSP (i64) | REX.WR (o64) +4d: DEC eBP (i64) | REX.WRB (o64) +4e: DEC eSI (i64) | REX.WRX (o64) +4f: DEC eDI (i64) | REX.WRXB (o64) +# 0x50 - 0x5f +50: PUSH rAX/r8 (d64) +51: PUSH rCX/r9 (d64) +52: PUSH rDX/r10 (d64) +53: PUSH rBX/r11 (d64) +54: PUSH rSP/r12 (d64) +55: PUSH rBP/r13 (d64) +56: PUSH rSI/r14 (d64) +57: PUSH rDI/r15 (d64) +58: POP rAX/r8 (d64) +59: POP rCX/r9 (d64) +5a: POP rDX/r10 (d64) +5b: POP rBX/r11 (d64) +5c: POP rSP/r12 (d64) +5d: POP rBP/r13 (d64) +5e: POP rSI/r14 (d64) +5f: POP rDI/r15 (d64) +# 0x60 - 0x6f +60: PUSHA/PUSHAD (i64) +61: POPA/POPAD (i64) +62: BOUND Gv,Ma (i64) +63: ARPL Ew,Gw (i64) | MOVSXD Gv,Ev (o64) +64: SEG=FS (Prefix) +65: SEG=GS (Prefix) +66: Operand-Size (Prefix) +67: Address-Size (Prefix) +68: PUSH Iz (d64) +69: IMUL Gv,Ev,Iz +6a: PUSH Ib (d64) +6b: IMUL Gv,Ev,Ib +6c: INS/INSB Yb,DX +6d: INS/INSW/INSD Yz,DX +6e: OUTS/OUTSB DX,Xb +6f: OUTS/OUTSW/OUTSD DX,Xz +# 0x70 - 0x7f +70: JO Jb +71: JNO Jb +72: JB/JNAE/JC Jb +73: JNB/JAE/JNC Jb +74: JZ/JE Jb +75: JNZ/JNE Jb +76: JBE/JNA Jb +77: JNBE/JA Jb +78: JS Jb +79: JNS Jb +7a: JP/JPE Jb +7b: JNP/JPO Jb +7c: JL/JNGE Jb +7d: JNL/JGE Jb +7e: JLE/JNG Jb +7f: JNLE/JG Jb +# 0x80 - 0x8f +80: Grp1 Eb,Ib (1A) +81: Grp1 Ev,Iz (1A) +82: Grp1 Eb,Ib (1A),(i64) +83: Grp1 Ev,Ib (1A) +84: TEST Eb,Gb +85: TEST Ev,Gv +86: XCHG Eb,Gb +87: XCHG Ev,Gv +88: MOV Eb,Gb +89: MOV Ev,Gv +8a: MOV Gb,Eb +8b: MOV Gv,Ev +8c: MOV Ev,Sw +8d: LEA Gv,M +8e: MOV Sw,Ew +8f: Grp1A (1A) | POP Ev (d64) +# 0x90 - 0x9f +90: NOP | PAUSE (F3) | XCHG r8,rAX +91: XCHG rCX/r9,rAX +92: XCHG rDX/r10,rAX +93: XCHG rBX/r11,rAX +94: XCHG rSP/r12,rAX +95: XCHG rBP/r13,rAX +96: XCHG rSI/r14,rAX +97: XCHG rDI/r15,rAX +98: CBW/CWDE/CDQE +99: CWD/CDQ/CQO +9a: CALLF Ap (i64) +9b: FWAIT/WAIT +9c: PUSHF/D/Q Fv (d64) +9d: POPF/D/Q Fv (d64) +9e: SAHF +9f: LAHF +# 0xa0 - 0xaf +a0: MOV AL,Ob +a1: MOV rAX,Ov +a2: MOV Ob,AL +a3: MOV Ov,rAX +a4: MOVS/B Xb,Yb +a5: MOVS/W/D/Q Xv,Yv +a6: CMPS/B Xb,Yb +a7: CMPS/W/D Xv,Yv +a8: TEST AL,Ib +a9: TEST rAX,Iz +aa: STOS/B Yb,AL +ab: STOS/W/D/Q Yv,rAX +ac: LODS/B AL,Xb +ad: LODS/W/D/Q rAX,Xv +ae: SCAS/B AL,Yb +af: SCAS/W/D/Q rAX,Xv +# 0xb0 - 0xbf +b0: MOV AL/R8L,Ib +b1: MOV CL/R9L,Ib +b2: MOV DL/R10L,Ib +b3: MOV BL/R11L,Ib +b4: MOV AH/R12L,Ib +b5: MOV CH/R13L,Ib +b6: MOV DH/R14L,Ib +b7: MOV BH/R15L,Ib +b8: MOV rAX/r8,Iv +b9: MOV rCX/r9,Iv +ba: MOV rDX/r10,Iv +bb: MOV rBX/r11,Iv +bc: MOV rSP/r12,Iv +bd: MOV rBP/r13,Iv +be: MOV rSI/r14,Iv +bf: MOV rDI/r15,Iv +# 0xc0 - 0xcf +c0: Grp2 Eb,Ib (1A) +c1: Grp2 Ev,Ib (1A) +c2: RETN Iw (f64) +c3: RETN +c4: LES Gz,Mp (i64) | 3bytes-VEX (Prefix) +c5: LDS Gz,Mp (i64) | 2bytes-VEX (Prefix) +c6: Grp11 Eb,Ib (1A) +c7: Grp11 Ev,Iz (1A) +c8: ENTER Iw,Ib +c9: LEAVE (d64) +ca: RETF Iw +cb: RETF +cc: INT3 +cd: INT Ib +ce: INTO (i64) +cf: IRET/D/Q +# 0xd0 - 0xdf +d0: Grp2 Eb,1 (1A) +d1: Grp2 Ev,1 (1A) +d2: Grp2 Eb,CL (1A) +d3: Grp2 Ev,CL (1A) +d4: AAM Ib (i64) +d5: AAD Ib (i64) +d6: +d7: XLAT/XLATB +d8: ESC +d9: ESC +da: ESC +db: ESC +dc: ESC +dd: ESC +de: ESC +df: ESC +# 0xe0 - 0xef +e0: LOOPNE/LOOPNZ Jb (f64) +e1: LOOPE/LOOPZ Jb (f64) +e2: LOOP Jb (f64) +e3: JrCXZ Jb (f64) +e4: IN AL,Ib +e5: IN eAX,Ib +e6: OUT Ib,AL +e7: OUT Ib,eAX +e8: CALL Jz (f64) +e9: JMP-near Jz (f64) +ea: JMP-far Ap (i64) +eb: JMP-short Jb (f64) +ec: IN AL,DX +ed: IN eAX,DX +ee: OUT DX,AL +ef: OUT DX,eAX +# 0xf0 - 0xff +f0: LOCK (Prefix) +f1: +f2: REPNE (Prefix) +f3: REP/REPE (Prefix) +f4: HLT +f5: CMC +f6: Grp3_1 Eb (1A) +f7: Grp3_2 Ev (1A) +f8: CLC +f9: STC +fa: CLI +fb: STI +fc: CLD +fd: STD +fe: Grp4 (1A) +ff: Grp5 (1A) +EndTable + +Table: 2-byte opcode (0x0f) +Referrer: 2-byte escape +AVXcode: 1 +# 0x0f 0x00-0x0f +00: Grp6 (1A) +01: Grp7 (1A) +02: LAR Gv,Ew +03: LSL Gv,Ew +04: +05: SYSCALL (o64) +06: CLTS +07: SYSRET (o64) +08: INVD +09: WBINVD +0a: +0b: UD2 (1B) +0c: +0d: NOP Ev | GrpP +0e: FEMMS +# 3DNow! uses the last imm byte as opcode extension. +0f: 3DNow! Pq,Qq,Ib +# 0x0f 0x10-0x1f +10: movups Vps,Wps (VEX) | movss Vss,Wss (F3),(VEX),(o128) | movupd Vpd,Wpd (66),(VEX) | movsd Vsd,Wsd (F2),(VEX),(o128) +11: movups Wps,Vps (VEX) | movss Wss,Vss (F3),(VEX),(o128) | movupd Wpd,Vpd (66),(VEX) | movsd Wsd,Vsd (F2),(VEX),(o128) +12: movlps Vq,Mq (VEX),(o128) | movlpd Vq,Mq (66),(VEX),(o128) | movhlps Vq,Uq (VEX),(o128) | movddup Vq,Wq (F2),(VEX) | movsldup Vq,Wq (F3),(VEX) +13: mpvlps Mq,Vq (VEX),(o128) | movlpd Mq,Vq (66),(VEX),(o128) +14: unpcklps Vps,Wq (VEX) | unpcklpd Vpd,Wq (66),(VEX) +15: unpckhps Vps,Wq (VEX) | unpckhpd Vpd,Wq (66),(VEX) +16: movhps Vq,Mq (VEX),(o128) | movhpd Vq,Mq (66),(VEX),(o128) | movlsps Vq,Uq (VEX),(o128) | movshdup Vq,Wq (F3),(VEX) +17: movhps Mq,Vq (VEX),(o128) | movhpd Mq,Vq (66),(VEX),(o128) +18: Grp16 (1A) +19: +1a: +1b: +1c: +1d: +1e: +1f: NOP Ev +# 0x0f 0x20-0x2f +20: MOV Rd,Cd +21: MOV Rd,Dd +22: MOV Cd,Rd +23: MOV Dd,Rd +24: +25: +26: +27: +28: movaps Vps,Wps (VEX) | movapd Vpd,Wpd (66),(VEX) +29: movaps Wps,Vps (VEX) | movapd Wpd,Vpd (66),(VEX) +2a: cvtpi2ps Vps,Qpi | cvtsi2ss Vss,Ed/q (F3),(VEX),(o128) | cvtpi2pd Vpd,Qpi (66) | cvtsi2sd Vsd,Ed/q (F2),(VEX),(o128) +2b: movntps Mps,Vps (VEX) | movntpd Mpd,Vpd (66),(VEX) +2c: cvttps2pi Ppi,Wps | cvttss2si Gd/q,Wss (F3),(VEX),(o128) | cvttpd2pi Ppi,Wpd (66) | cvttsd2si Gd/q,Wsd (F2),(VEX),(o128) +2d: cvtps2pi Ppi,Wps | cvtss2si Gd/q,Wss (F3),(VEX),(o128) | cvtpd2pi Qpi,Wpd (66) | cvtsd2si Gd/q,Wsd (F2),(VEX),(o128) +2e: ucomiss Vss,Wss (VEX),(o128) | ucomisd Vsd,Wsd (66),(VEX),(o128) +2f: comiss Vss,Wss (VEX),(o128) | comisd Vsd,Wsd (66),(VEX),(o128) +# 0x0f 0x30-0x3f +30: WRMSR +31: RDTSC +32: RDMSR +33: RDPMC +34: SYSENTER +35: SYSEXIT +36: +37: GETSEC +38: escape # 3-byte escape 1 +39: +3a: escape # 3-byte escape 2 +3b: +3c: +3d: +3e: +3f: +# 0x0f 0x40-0x4f +40: CMOVO Gv,Ev +41: CMOVNO Gv,Ev +42: CMOVB/C/NAE Gv,Ev +43: CMOVAE/NB/NC Gv,Ev +44: CMOVE/Z Gv,Ev +45: CMOVNE/NZ Gv,Ev +46: CMOVBE/NA Gv,Ev +47: CMOVA/NBE Gv,Ev +48: CMOVS Gv,Ev +49: CMOVNS Gv,Ev +4a: CMOVP/PE Gv,Ev +4b: CMOVNP/PO Gv,Ev +4c: CMOVL/NGE Gv,Ev +4d: CMOVNL/GE Gv,Ev +4e: CMOVLE/NG Gv,Ev +4f: CMOVNLE/G Gv,Ev +# 0x0f 0x50-0x5f +50: movmskps Gd/q,Ups (VEX) | movmskpd Gd/q,Upd (66),(VEX) +51: sqrtps Vps,Wps (VEX) | sqrtss Vss,Wss (F3),(VEX),(o128) | sqrtpd Vpd,Wpd (66),(VEX) | sqrtsd Vsd,Wsd (F2),(VEX),(o128) +52: rsqrtps Vps,Wps (VEX) | rsqrtss Vss,Wss (F3),(VEX),(o128) +53: rcpps Vps,Wps (VEX) | rcpss Vss,Wss (F3),(VEX),(o128) +54: andps Vps,Wps (VEX) | andpd Vpd,Wpd (66),(VEX) +55: andnps Vps,Wps (VEX) | andnpd Vpd,Wpd (66),(VEX) +56: orps Vps,Wps (VEX) | orpd Vpd,Wpd (66),(VEX) +57: xorps Vps,Wps (VEX) | xorpd Vpd,Wpd (66),(VEX) +58: addps Vps,Wps (VEX) | addss Vss,Wss (F3),(VEX),(o128) | addpd Vpd,Wpd (66),(VEX) | addsd Vsd,Wsd (F2),(VEX),(o128) +59: mulps Vps,Wps (VEX) | mulss Vss,Wss (F3),(VEX),(o128) | mulpd Vpd,Wpd (66),(VEX) | mulsd Vsd,Wsd (F2),(VEX),(o128) +5a: cvtps2pd Vpd,Wps (VEX) | cvtss2sd Vsd,Wss (F3),(VEX),(o128) | cvtpd2ps Vps,Wpd (66),(VEX) | cvtsd2ss Vsd,Wsd (F2),(VEX),(o128) +5b: cvtdq2ps Vps,Wdq (VEX) | cvtps2dq Vdq,Wps (66),(VEX) | cvttps2dq Vdq,Wps (F3),(VEX) +5c: subps Vps,Wps (VEX) | subss Vss,Wss (F3),(VEX),(o128) | subpd Vpd,Wpd (66),(VEX) | subsd Vsd,Wsd (F2),(VEX),(o128) +5d: minps Vps,Wps (VEX) | minss Vss,Wss (F3),(VEX),(o128) | minpd Vpd,Wpd (66),(VEX) | minsd Vsd,Wsd (F2),(VEX),(o128) +5e: divps Vps,Wps (VEX) | divss Vss,Wss (F3),(VEX),(o128) | divpd Vpd,Wpd (66),(VEX) | divsd Vsd,Wsd (F2),(VEX),(o128) +5f: maxps Vps,Wps (VEX) | maxss Vss,Wss (F3),(VEX),(o128) | maxpd Vpd,Wpd (66),(VEX) | maxsd Vsd,Wsd (F2),(VEX),(o128) +# 0x0f 0x60-0x6f +60: punpcklbw Pq,Qd | punpcklbw Vdq,Wdq (66),(VEX),(o128) +61: punpcklwd Pq,Qd | punpcklwd Vdq,Wdq (66),(VEX),(o128) +62: punpckldq Pq,Qd | punpckldq Vdq,Wdq (66),(VEX),(o128) +63: packsswb Pq,Qq | packsswb Vdq,Wdq (66),(VEX),(o128) +64: pcmpgtb Pq,Qq | pcmpgtb Vdq,Wdq (66),(VEX),(o128) +65: pcmpgtw Pq,Qq | pcmpgtw Vdq,Wdq (66),(VEX),(o128) +66: pcmpgtd Pq,Qq | pcmpgtd Vdq,Wdq (66),(VEX),(o128) +67: packuswb Pq,Qq | packuswb Vdq,Wdq (66),(VEX),(o128) +68: punpckhbw Pq,Qd | punpckhbw Vdq,Wdq (66),(VEX),(o128) +69: punpckhwd Pq,Qd | punpckhwd Vdq,Wdq (66),(VEX),(o128) +6a: punpckhdq Pq,Qd | punpckhdq Vdq,Wdq (66),(VEX),(o128) +6b: packssdw Pq,Qd | packssdw Vdq,Wdq (66),(VEX),(o128) +6c: punpcklqdq Vdq,Wdq (66),(VEX),(o128) +6d: punpckhqdq Vdq,Wdq (66),(VEX),(o128) +6e: movd/q/ Pd,Ed/q | movd/q Vdq,Ed/q (66),(VEX),(o128) +6f: movq Pq,Qq | movdqa Vdq,Wdq (66),(VEX) | movdqu Vdq,Wdq (F3),(VEX) +# 0x0f 0x70-0x7f +70: pshufw Pq,Qq,Ib | pshufd Vdq,Wdq,Ib (66),(VEX),(o128) | pshufhw Vdq,Wdq,Ib (F3),(VEX),(o128) | pshuflw VdqWdq,Ib (F2),(VEX),(o128) +71: Grp12 (1A) +72: Grp13 (1A) +73: Grp14 (1A) +74: pcmpeqb Pq,Qq | pcmpeqb Vdq,Wdq (66),(VEX),(o128) +75: pcmpeqw Pq,Qq | pcmpeqw Vdq,Wdq (66),(VEX),(o128) +76: pcmpeqd Pq,Qq | pcmpeqd Vdq,Wdq (66),(VEX),(o128) +77: emms/vzeroupper/vzeroall (VEX) +78: VMREAD Ed/q,Gd/q +79: VMWRITE Gd/q,Ed/q +7a: +7b: +7c: haddps Vps,Wps (F2),(VEX) | haddpd Vpd,Wpd (66),(VEX) +7d: hsubps Vps,Wps (F2),(VEX) | hsubpd Vpd,Wpd (66),(VEX) +7e: movd/q Ed/q,Pd | movd/q Ed/q,Vdq (66),(VEX),(o128) | movq Vq,Wq (F3),(VEX),(o128) +7f: movq Qq,Pq | movdqa Wdq,Vdq (66),(VEX) | movdqu Wdq,Vdq (F3),(VEX) +# 0x0f 0x80-0x8f +80: JO Jz (f64) +81: JNO Jz (f64) +82: JB/JNAE/JC Jz (f64) +83: JNB/JAE/JNC Jz (f64) +84: JZ/JE Jz (f64) +85: JNZ/JNE Jz (f64) +86: JBE/JNA Jz (f64) +87: JNBE/JA Jz (f64) +88: JS Jz (f64) +89: JNS Jz (f64) +8a: JP/JPE Jz (f64) +8b: JNP/JPO Jz (f64) +8c: JL/JNGE Jz (f64) +8d: JNL/JGE Jz (f64) +8e: JLE/JNG Jz (f64) +8f: JNLE/JG Jz (f64) +# 0x0f 0x90-0x9f +90: SETO Eb +91: SETNO Eb +92: SETB/C/NAE Eb +93: SETAE/NB/NC Eb +94: SETE/Z Eb +95: SETNE/NZ Eb +96: SETBE/NA Eb +97: SETA/NBE Eb +98: SETS Eb +99: SETNS Eb +9a: SETP/PE Eb +9b: SETNP/PO Eb +9c: SETL/NGE Eb +9d: SETNL/GE Eb +9e: SETLE/NG Eb +9f: SETNLE/G Eb +# 0x0f 0xa0-0xaf +a0: PUSH FS (d64) +a1: POP FS (d64) +a2: CPUID +a3: BT Ev,Gv +a4: SHLD Ev,Gv,Ib +a5: SHLD Ev,Gv,CL +a6: GrpPDLK +a7: GrpRNG +a8: PUSH GS (d64) +a9: POP GS (d64) +aa: RSM +ab: BTS Ev,Gv +ac: SHRD Ev,Gv,Ib +ad: SHRD Ev,Gv,CL +ae: Grp15 (1A),(1C) +af: IMUL Gv,Ev +# 0x0f 0xb0-0xbf +b0: CMPXCHG Eb,Gb +b1: CMPXCHG Ev,Gv +b2: LSS Gv,Mp +b3: BTR Ev,Gv +b4: LFS Gv,Mp +b5: LGS Gv,Mp +b6: MOVZX Gv,Eb +b7: MOVZX Gv,Ew +b8: JMPE | POPCNT Gv,Ev (F3) +b9: Grp10 (1A) +ba: Grp8 Ev,Ib (1A) +bb: BTC Ev,Gv +bc: BSF Gv,Ev +bd: BSR Gv,Ev +be: MOVSX Gv,Eb +bf: MOVSX Gv,Ew +# 0x0f 0xc0-0xcf +c0: XADD Eb,Gb +c1: XADD Ev,Gv +c2: cmpps Vps,Wps,Ib (VEX) | cmpss Vss,Wss,Ib (F3),(VEX),(o128) | cmppd Vpd,Wpd,Ib (66),(VEX) | cmpsd Vsd,Wsd,Ib (F2),(VEX) +c3: movnti Md/q,Gd/q +c4: pinsrw Pq,Rd/q/Mw,Ib | pinsrw Vdq,Rd/q/Mw,Ib (66),(VEX),(o128) +c5: pextrw Gd,Nq,Ib | pextrw Gd,Udq,Ib (66),(VEX),(o128) +c6: shufps Vps,Wps,Ib (VEX) | shufpd Vpd,Wpd,Ib (66),(VEX) +c7: Grp9 (1A) +c8: BSWAP RAX/EAX/R8/R8D +c9: BSWAP RCX/ECX/R9/R9D +ca: BSWAP RDX/EDX/R10/R10D +cb: BSWAP RBX/EBX/R11/R11D +cc: BSWAP RSP/ESP/R12/R12D +cd: BSWAP RBP/EBP/R13/R13D +ce: BSWAP RSI/ESI/R14/R14D +cf: BSWAP RDI/EDI/R15/R15D +# 0x0f 0xd0-0xdf +d0: addsubps Vps,Wps (F2),(VEX) | addsubpd Vpd,Wpd (66),(VEX) +d1: psrlw Pq,Qq | psrlw Vdq,Wdq (66),(VEX),(o128) +d2: psrld Pq,Qq | psrld Vdq,Wdq (66),(VEX),(o128) +d3: psrlq Pq,Qq | psrlq Vdq,Wdq (66),(VEX),(o128) +d4: paddq Pq,Qq | paddq Vdq,Wdq (66),(VEX),(o128) +d5: pmullw Pq,Qq | pmullw Vdq,Wdq (66),(VEX),(o128) +d6: movq Wq,Vq (66),(VEX),(o128) | movq2dq Vdq,Nq (F3) | movdq2q Pq,Uq (F2) +d7: pmovmskb Gd,Nq | pmovmskb Gd,Udq (66),(VEX),(o128) +d8: psubusb Pq,Qq | psubusb Vdq,Wdq (66),(VEX),(o128) +d9: psubusw Pq,Qq | psubusw Vdq,Wdq (66),(VEX),(o128) +da: pminub Pq,Qq | pminub Vdq,Wdq (66),(VEX),(o128) +db: pand Pq,Qq | pand Vdq,Wdq (66),(VEX),(o128) +dc: paddusb Pq,Qq | paddusb Vdq,Wdq (66),(VEX),(o128) +dd: paddusw Pq,Qq | paddusw Vdq,Wdq (66),(VEX),(o128) +de: pmaxub Pq,Qq | pmaxub Vdq,Wdq (66),(VEX),(o128) +df: pandn Pq,Qq | pandn Vdq,Wdq (66),(VEX),(o128) +# 0x0f 0xe0-0xef +e0: pavgb Pq,Qq | pavgb Vdq,Wdq (66),(VEX),(o128) +e1: psraw Pq,Qq | psraw Vdq,Wdq (66),(VEX),(o128) +e2: psrad Pq,Qq | psrad Vdq,Wdq (66),(VEX),(o128) +e3: pavgw Pq,Qq | pavgw Vdq,Wdq (66),(VEX),(o128) +e4: pmulhuw Pq,Qq | pmulhuw Vdq,Wdq (66),(VEX),(o128) +e5: pmulhw Pq,Qq | pmulhw Vdq,Wdq (66),(VEX),(o128) +e6: cvtpd2dq Vdq,Wpd (F2),(VEX) | cvttpd2dq Vdq,Wpd (66),(VEX) | cvtdq2pd Vpd,Wdq (F3),(VEX) +e7: movntq Mq,Pq | movntdq Mdq,Vdq (66),(VEX) +e8: psubsb Pq,Qq | psubsb Vdq,Wdq (66),(VEX),(o128) +e9: psubsw Pq,Qq | psubsw Vdq,Wdq (66),(VEX),(o128) +ea: pminsw Pq,Qq | pminsw Vdq,Wdq (66),(VEX),(o128) +eb: por Pq,Qq | por Vdq,Wdq (66),(VEX),(o128) +ec: paddsb Pq,Qq | paddsb Vdq,Wdq (66),(VEX),(o128) +ed: paddsw Pq,Qq | paddsw Vdq,Wdq (66),(VEX),(o128) +ee: pmaxsw Pq,Qq | pmaxsw Vdq,Wdq (66),(VEX),(o128) +ef: pxor Pq,Qq | pxor Vdq,Wdq (66),(VEX),(o128) +# 0x0f 0xf0-0xff +f0: lddqu Vdq,Mdq (F2),(VEX) +f1: psllw Pq,Qq | psllw Vdq,Wdq (66),(VEX),(o128) +f2: pslld Pq,Qq | pslld Vdq,Wdq (66),(VEX),(o128) +f3: psllq Pq,Qq | psllq Vdq,Wdq (66),(VEX),(o128) +f4: pmuludq Pq,Qq | pmuludq Vdq,Wdq (66),(VEX),(o128) +f5: pmaddwd Pq,Qq | pmaddwd Vdq,Wdq (66),(VEX),(o128) +f6: psadbw Pq,Qq | psadbw Vdq,Wdq (66),(VEX),(o128) +f7: maskmovq Pq,Nq | maskmovdqu Vdq,Udq (66),(VEX),(o128) +f8: psubb Pq,Qq | psubb Vdq,Wdq (66),(VEX),(o128) +f9: psubw Pq,Qq | psubw Vdq,Wdq (66),(VEX),(o128) +fa: psubd Pq,Qq | psubd Vdq,Wdq (66),(VEX),(o128) +fb: psubq Pq,Qq | psubq Vdq,Wdq (66),(VEX),(o128) +fc: paddb Pq,Qq | paddb Vdq,Wdq (66),(VEX),(o128) +fd: paddw Pq,Qq | paddw Vdq,Wdq (66),(VEX),(o128) +fe: paddd Pq,Qq | paddd Vdq,Wdq (66),(VEX),(o128) +ff: +EndTable + +Table: 3-byte opcode 1 (0x0f 0x38) +Referrer: 3-byte escape 1 +AVXcode: 2 +# 0x0f 0x38 0x00-0x0f +00: pshufb Pq,Qq | pshufb Vdq,Wdq (66),(VEX),(o128) +01: phaddw Pq,Qq | phaddw Vdq,Wdq (66),(VEX),(o128) +02: phaddd Pq,Qq | phaddd Vdq,Wdq (66),(VEX),(o128) +03: phaddsw Pq,Qq | phaddsw Vdq,Wdq (66),(VEX),(o128) +04: pmaddubsw Pq,Qq | pmaddubsw Vdq,Wdq (66),(VEX),(o128) +05: phsubw Pq,Qq | phsubw Vdq,Wdq (66),(VEX),(o128) +06: phsubd Pq,Qq | phsubd Vdq,Wdq (66),(VEX),(o128) +07: phsubsw Pq,Qq | phsubsw Vdq,Wdq (66),(VEX),(o128) +08: psignb Pq,Qq | psignb Vdq,Wdq (66),(VEX),(o128) +09: psignw Pq,Qq | psignw Vdq,Wdq (66),(VEX),(o128) +0a: psignd Pq,Qq | psignd Vdq,Wdq (66),(VEX),(o128) +0b: pmulhrsw Pq,Qq | pmulhrsw Vdq,Wdq (66),(VEX),(o128) +0c: Vpermilps /r (66),(oVEX) +0d: Vpermilpd /r (66),(oVEX) +0e: vtestps /r (66),(oVEX) +0f: vtestpd /r (66),(oVEX) +# 0x0f 0x38 0x10-0x1f +10: pblendvb Vdq,Wdq (66) +11: +12: +13: +14: blendvps Vdq,Wdq (66) +15: blendvpd Vdq,Wdq (66) +16: +17: ptest Vdq,Wdq (66),(VEX) +18: vbroadcastss /r (66),(oVEX) +19: vbroadcastsd /r (66),(oVEX),(o256) +1a: vbroadcastf128 /r (66),(oVEX),(o256) +1b: +1c: pabsb Pq,Qq | pabsb Vdq,Wdq (66),(VEX),(o128) +1d: pabsw Pq,Qq | pabsw Vdq,Wdq (66),(VEX),(o128) +1e: pabsd Pq,Qq | pabsd Vdq,Wdq (66),(VEX),(o128) +1f: +# 0x0f 0x38 0x20-0x2f +20: pmovsxbw Vdq,Udq/Mq (66),(VEX),(o128) +21: pmovsxbd Vdq,Udq/Md (66),(VEX),(o128) +22: pmovsxbq Vdq,Udq/Mw (66),(VEX),(o128) +23: pmovsxwd Vdq,Udq/Mq (66),(VEX),(o128) +24: pmovsxwq Vdq,Udq/Md (66),(VEX),(o128) +25: pmovsxdq Vdq,Udq/Mq (66),(VEX),(o128) +26: +27: +28: pmuldq Vdq,Wdq (66),(VEX),(o128) +29: pcmpeqq Vdq,Wdq (66),(VEX),(o128) +2a: movntdqa Vdq,Mdq (66),(VEX),(o128) +2b: packusdw Vdq,Wdq (66),(VEX),(o128) +2c: vmaskmovps(ld) /r (66),(oVEX) +2d: vmaskmovpd(ld) /r (66),(oVEX) +2e: vmaskmovps(st) /r (66),(oVEX) +2f: vmaskmovpd(st) /r (66),(oVEX) +# 0x0f 0x38 0x30-0x3f +30: pmovzxbw Vdq,Udq/Mq (66),(VEX),(o128) +31: pmovzxbd Vdq,Udq/Md (66),(VEX),(o128) +32: pmovzxbq Vdq,Udq/Mw (66),(VEX),(o128) +33: pmovzxwd Vdq,Udq/Mq (66),(VEX),(o128) +34: pmovzxwq Vdq,Udq/Md (66),(VEX),(o128) +35: pmovzxdq Vdq,Udq/Mq (66),(VEX),(o128) +36: +37: pcmpgtq Vdq,Wdq (66),(VEX),(o128) +38: pminsb Vdq,Wdq (66),(VEX),(o128) +39: pminsd Vdq,Wdq (66),(VEX),(o128) +3a: pminuw Vdq,Wdq (66),(VEX),(o128) +3b: pminud Vdq,Wdq (66),(VEX),(o128) +3c: pmaxsb Vdq,Wdq (66),(VEX),(o128) +3d: pmaxsd Vdq,Wdq (66),(VEX),(o128) +3e: pmaxuw Vdq,Wdq (66),(VEX),(o128) +3f: pmaxud Vdq,Wdq (66),(VEX),(o128) +# 0x0f 0x38 0x40-0x8f +40: pmulld Vdq,Wdq (66),(VEX),(o128) +41: phminposuw Vdq,Wdq (66),(VEX),(o128) +80: INVEPT Gd/q,Mdq (66) +81: INVPID Gd/q,Mdq (66) +# 0x0f 0x38 0x90-0xbf (FMA) +96: vfmaddsub132pd/ps /r (66),(VEX) +97: vfmsubadd132pd/ps /r (66),(VEX) +98: vfmadd132pd/ps /r (66),(VEX) +99: vfmadd132sd/ss /r (66),(VEX),(o128) +9a: vfmsub132pd/ps /r (66),(VEX) +9b: vfmsub132sd/ss /r (66),(VEX),(o128) +9c: vfnmadd132pd/ps /r (66),(VEX) +9d: vfnmadd132sd/ss /r (66),(VEX),(o128) +9e: vfnmsub132pd/ps /r (66),(VEX) +9f: vfnmsub132sd/ss /r (66),(VEX),(o128) +a6: vfmaddsub213pd/ps /r (66),(VEX) +a7: vfmsubadd213pd/ps /r (66),(VEX) +a8: vfmadd213pd/ps /r (66),(VEX) +a9: vfmadd213sd/ss /r (66),(VEX),(o128) +aa: vfmsub213pd/ps /r (66),(VEX) +ab: vfmsub213sd/ss /r (66),(VEX),(o128) +ac: vfnmadd213pd/ps /r (66),(VEX) +ad: vfnmadd213sd/ss /r (66),(VEX),(o128) +ae: vfnmsub213pd/ps /r (66),(VEX) +af: vfnmsub213sd/ss /r (66),(VEX),(o128) +b6: vfmaddsub231pd/ps /r (66),(VEX) +b7: vfmsubadd231pd/ps /r (66),(VEX) +b8: vfmadd231pd/ps /r (66),(VEX) +b9: vfmadd231sd/ss /r (66),(VEX),(o128) +ba: vfmsub231pd/ps /r (66),(VEX) +bb: vfmsub231sd/ss /r (66),(VEX),(o128) +bc: vfnmadd231pd/ps /r (66),(VEX) +bd: vfnmadd231sd/ss /r (66),(VEX),(o128) +be: vfnmsub231pd/ps /r (66),(VEX) +bf: vfnmsub231sd/ss /r (66),(VEX),(o128) +# 0x0f 0x38 0xc0-0xff +db: aesimc Vdq,Wdq (66),(VEX),(o128) +dc: aesenc Vdq,Wdq (66),(VEX),(o128) +dd: aesenclast Vdq,Wdq (66),(VEX),(o128) +de: aesdec Vdq,Wdq (66),(VEX),(o128) +df: aesdeclast Vdq,Wdq (66),(VEX),(o128) +f0: MOVBE Gv,Mv | CRC32 Gd,Eb (F2) +f1: MOVBE Mv,Gv | CRC32 Gd,Ev (F2) +EndTable + +Table: 3-byte opcode 2 (0x0f 0x3a) +Referrer: 3-byte escape 2 +AVXcode: 3 +# 0x0f 0x3a 0x00-0xff +04: vpermilps /r,Ib (66),(oVEX) +05: vpermilpd /r,Ib (66),(oVEX) +06: vperm2f128 /r,Ib (66),(oVEX),(o256) +08: roundps Vdq,Wdq,Ib (66),(VEX) +09: roundpd Vdq,Wdq,Ib (66),(VEX) +0a: roundss Vss,Wss,Ib (66),(VEX),(o128) +0b: roundsd Vsd,Wsd,Ib (66),(VEX),(o128) +0c: blendps Vdq,Wdq,Ib (66),(VEX) +0d: blendpd Vdq,Wdq,Ib (66),(VEX) +0e: pblendw Vdq,Wdq,Ib (66),(VEX),(o128) +0f: palignr Pq,Qq,Ib | palignr Vdq,Wdq,Ib (66),(VEX),(o128) +14: pextrb Rd/Mb,Vdq,Ib (66),(VEX),(o128) +15: pextrw Rd/Mw,Vdq,Ib (66),(VEX),(o128) +16: pextrd/pextrq Ed/q,Vdq,Ib (66),(VEX),(o128) +17: extractps Ed,Vdq,Ib (66),(VEX),(o128) +18: vinsertf128 /r,Ib (66),(oVEX),(o256) +19: vextractf128 /r,Ib (66),(oVEX),(o256) +20: pinsrb Vdq,Rd/q/Mb,Ib (66),(VEX),(o128) +21: insertps Vdq,Udq/Md,Ib (66),(VEX),(o128) +22: pinsrd/pinsrq Vdq,Ed/q,Ib (66),(VEX),(o128) +40: dpps Vdq,Wdq,Ib (66),(VEX) +41: dppd Vdq,Wdq,Ib (66),(VEX),(o128) +42: mpsadbw Vdq,Wdq,Ib (66),(VEX),(o128) +44: pclmulq Vdq,Wdq,Ib (66),(VEX),(o128) +4a: vblendvps /r,Ib (66),(oVEX) +4b: vblendvpd /r,Ib (66),(oVEX) +4c: vpblendvb /r,Ib (66),(oVEX),(o128) +60: pcmpestrm Vdq,Wdq,Ib (66),(VEX),(o128) +61: pcmpestri Vdq,Wdq,Ib (66),(VEX),(o128) +62: pcmpistrm Vdq,Wdq,Ib (66),(VEX),(o128) +63: pcmpistri Vdq,Wdq,Ib (66),(VEX),(o128) +df: aeskeygenassist Vdq,Wdq,Ib (66),(VEX),(o128) +EndTable + +GrpTable: Grp1 +0: ADD +1: OR +2: ADC +3: SBB +4: AND +5: SUB +6: XOR +7: CMP +EndTable + +GrpTable: Grp1A +0: POP +EndTable + +GrpTable: Grp2 +0: ROL +1: ROR +2: RCL +3: RCR +4: SHL/SAL +5: SHR +6: +7: SAR +EndTable + +GrpTable: Grp3_1 +0: TEST Eb,Ib +1: +2: NOT Eb +3: NEG Eb +4: MUL AL,Eb +5: IMUL AL,Eb +6: DIV AL,Eb +7: IDIV AL,Eb +EndTable + +GrpTable: Grp3_2 +0: TEST Ev,Iz +1: +2: NOT Ev +3: NEG Ev +4: MUL rAX,Ev +5: IMUL rAX,Ev +6: DIV rAX,Ev +7: IDIV rAX,Ev +EndTable + +GrpTable: Grp4 +0: INC Eb +1: DEC Eb +EndTable + +GrpTable: Grp5 +0: INC Ev +1: DEC Ev +2: CALLN Ev (f64) +3: CALLF Ep +4: JMPN Ev (f64) +5: JMPF Ep +6: PUSH Ev (d64) +7: +EndTable + +GrpTable: Grp6 +0: SLDT Rv/Mw +1: STR Rv/Mw +2: LLDT Ew +3: LTR Ew +4: VERR Ew +5: VERW Ew +EndTable + +GrpTable: Grp7 +0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) +1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001) +2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) +3: LIDT Ms +4: SMSW Mw/Rv +5: +6: LMSW Ew +7: INVLPG Mb | SWAPGS (o64),(000),(11B) | RDTSCP (001),(11B) +EndTable + +GrpTable: Grp8 +4: BT +5: BTS +6: BTR +7: BTC +EndTable + +GrpTable: Grp9 +1: CMPXCHG8B/16B Mq/Mdq +6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3) +7: VMPTRST Mq +EndTable + +GrpTable: Grp10 +EndTable + +GrpTable: Grp11 +0: MOV +EndTable + +GrpTable: Grp12 +2: psrlw Nq,Ib (11B) | psrlw Udq,Ib (66),(11B),(VEX),(o128) +4: psraw Nq,Ib (11B) | psraw Udq,Ib (66),(11B),(VEX),(o128) +6: psllw Nq,Ib (11B) | psllw Udq,Ib (66),(11B),(VEX),(o128) +EndTable + +GrpTable: Grp13 +2: psrld Nq,Ib (11B) | psrld Udq,Ib (66),(11B),(VEX),(o128) +4: psrad Nq,Ib (11B) | psrad Udq,Ib (66),(11B),(VEX),(o128) +6: pslld Nq,Ib (11B) | pslld Udq,Ib (66),(11B),(VEX),(o128) +EndTable + +GrpTable: Grp14 +2: psrlq Nq,Ib (11B) | psrlq Udq,Ib (66),(11B),(VEX),(o128) +3: psrldq Udq,Ib (66),(11B),(VEX),(o128) +6: psllq Nq,Ib (11B) | psllq Udq,Ib (66),(11B),(VEX),(o128) +7: pslldq Udq,Ib (66),(11B),(VEX),(o128) +EndTable + +GrpTable: Grp15 +0: fxsave +1: fxstor +2: ldmxcsr (VEX) +3: stmxcsr (VEX) +4: XSAVE +5: XRSTOR | lfence (11B) +6: mfence (11B) +7: clflush | sfence (11B) +EndTable + +GrpTable: Grp16 +0: prefetch NTA +1: prefetch T0 +2: prefetch T1 +3: prefetch T2 +EndTable + +# AMD's Prefetch Group +GrpTable: GrpP +0: PREFETCH +1: PREFETCHW +EndTable + +GrpTable: GrpPDLK +0: MONTMUL +1: XSHA1 +2: XSHA2 +EndTable + +GrpTable: GrpRNG +0: xstore-rng +1: xcrypt-ecb +2: xcrypt-cbc +4: xcrypt-cfb +5: xcrypt-ofb +EndTable diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index 61b41ca3b5a2..d0474ad2a6e5 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -35,34 +35,3 @@ int fixup_exception(struct pt_regs *regs) return 0; } - -#ifdef CONFIG_X86_64 -/* - * Need to defined our own search_extable on X86_64 to work around - * a B stepping K8 bug. - */ -const struct exception_table_entry * -search_extable(const struct exception_table_entry *first, - const struct exception_table_entry *last, - unsigned long value) -{ - /* B stepping K8 bug */ - if ((value >> 32) == 0) - value |= 0xffffffffUL << 32; - - while (first <= last) { - const struct exception_table_entry *mid; - long diff; - - mid = (last - first) / 2 + first; - diff = mid->insn - value; - if (diff == 0) - return mid; - else if (diff < 0) - first = mid+1; - else - last = mid-1; - } - return NULL; -} -#endif diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index f4cee9028cf0..f62777940dfb 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -38,7 +38,8 @@ enum x86_pf_error_code { * Returns 0 if mmiotrace is disabled, or if the fault is not * handled by mmiotrace: */ -static inline int kmmio_fault(struct pt_regs *regs, unsigned long addr) +static inline int __kprobes +kmmio_fault(struct pt_regs *regs, unsigned long addr) { if (unlikely(is_kmmio_active())) if (kmmio_handler(regs, addr) == 1) @@ -46,7 +47,7 @@ static inline int kmmio_fault(struct pt_regs *regs, unsigned long addr) return 0; } -static inline int notify_page_fault(struct pt_regs *regs) +static inline int __kprobes notify_page_fault(struct pt_regs *regs) { int ret = 0; @@ -240,7 +241,7 @@ void vmalloc_sync_all(void) * * Handle a fault on the vmalloc or module mapping area */ -static noinline int vmalloc_fault(unsigned long address) +static noinline __kprobes int vmalloc_fault(unsigned long address) { unsigned long pgd_paddr; pmd_t *pmd_k; @@ -357,7 +358,7 @@ void vmalloc_sync_all(void) * * This assumes no large pages in there. */ -static noinline int vmalloc_fault(unsigned long address) +static noinline __kprobes int vmalloc_fault(unsigned long address) { pgd_t *pgd, *pgd_ref; pud_t *pud, *pud_ref; @@ -658,7 +659,7 @@ no_context(struct pt_regs *regs, unsigned long error_code, show_fault_oops(regs, error_code, address); stackend = end_of_stack(tsk); - if (*stackend != STACK_END_MAGIC) + if (tsk != &init_task && *stackend != STACK_END_MAGIC) printk(KERN_ALERT "Thread overran stack, or stack corrupted\n"); tsk->thread.cr2 = address; @@ -860,7 +861,7 @@ static int spurious_fault_check(unsigned long error_code, pte_t *pte) * There are no security implications to leaving a stale TLB when * increasing the permissions on a page. */ -static noinline int +static noinline __kprobes int spurious_fault(unsigned long error_code, unsigned long address) { pgd_t *pgd; diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index 16ccbd77917f..11a4ad4d6253 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -540,8 +540,14 @@ kmmio_die_notifier(struct notifier_block *nb, unsigned long val, void *args) struct die_args *arg = args; if (val == DIE_DEBUG && (arg->err & DR_STEP)) - if (post_kmmio_handler(arg->err, arg->regs) == 1) + if (post_kmmio_handler(arg->err, arg->regs) == 1) { + /* + * Reset the BS bit in dr6 (pointed by args->err) to + * denote completion of processing + */ + (*(unsigned long *)ERR_PTR(arg->err)) &= ~DR_STEP; return NOTIFY_STOP; + } return NOTIFY_DONE; } diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c index dbb5381f7b3b..9d7ce96e5a5c 100644 --- a/arch/x86/mm/srat_64.c +++ b/arch/x86/mm/srat_64.c @@ -136,7 +136,7 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa) apicid_to_node[apic_id] = node; node_set(node, cpu_nodes_parsed); acpi_numa = 1; - printk(KERN_INFO "SRAT: PXM %u -> APIC %u -> Node %u\n", + printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%04x -> Node %u\n", pxm, apic_id, node); } @@ -170,7 +170,7 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) apicid_to_node[apic_id] = node; node_set(node, cpu_nodes_parsed); acpi_numa = 1; - printk(KERN_INFO "SRAT: PXM %u -> APIC %u -> Node %u\n", + printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%02x -> Node %u\n", pxm, apic_id, node); } diff --git a/arch/x86/mm/testmmiotrace.c b/arch/x86/mm/testmmiotrace.c index 427fd1b56df5..8565d944f7cf 100644 --- a/arch/x86/mm/testmmiotrace.c +++ b/arch/x86/mm/testmmiotrace.c @@ -1,12 +1,13 @@ /* * Written by Pekka Paalanen, 2008-2009 <pq@iki.fi> */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/io.h> #include <linux/mmiotrace.h> -#define MODULE_NAME "testmmiotrace" - static unsigned long mmio_address; module_param(mmio_address, ulong, 0); MODULE_PARM_DESC(mmio_address, " Start address of the mapping of 16 kB " @@ -30,7 +31,7 @@ static unsigned v32(unsigned i) static void do_write_test(void __iomem *p) { unsigned int i; - pr_info(MODULE_NAME ": write test.\n"); + pr_info("write test.\n"); mmiotrace_printk("Write test.\n"); for (i = 0; i < 256; i++) @@ -47,7 +48,7 @@ static void do_read_test(void __iomem *p) { unsigned int i; unsigned errs[3] = { 0 }; - pr_info(MODULE_NAME ": read test.\n"); + pr_info("read test.\n"); mmiotrace_printk("Read test.\n"); for (i = 0; i < 256; i++) @@ -68,7 +69,7 @@ static void do_read_test(void __iomem *p) static void do_read_far_test(void __iomem *p) { - pr_info(MODULE_NAME ": read far test.\n"); + pr_info("read far test.\n"); mmiotrace_printk("Read far test.\n"); ioread32(p + read_far); @@ -78,7 +79,7 @@ static void do_test(unsigned long size) { void __iomem *p = ioremap_nocache(mmio_address, size); if (!p) { - pr_err(MODULE_NAME ": could not ioremap, aborting.\n"); + pr_err("could not ioremap, aborting.\n"); return; } mmiotrace_printk("ioremap returned %p.\n", p); @@ -94,24 +95,22 @@ static int __init init(void) unsigned long size = (read_far) ? (8 << 20) : (16 << 10); if (mmio_address == 0) { - pr_err(MODULE_NAME ": you have to use the module argument " - "mmio_address.\n"); - pr_err(MODULE_NAME ": DO NOT LOAD THIS MODULE UNLESS" - " YOU REALLY KNOW WHAT YOU ARE DOING!\n"); + pr_err("you have to use the module argument mmio_address.\n"); + pr_err("DO NOT LOAD THIS MODULE UNLESS YOU REALLY KNOW WHAT YOU ARE DOING!\n"); return -ENXIO; } - pr_warning(MODULE_NAME ": WARNING: mapping %lu kB @ 0x%08lx in PCI " - "address space, and writing 16 kB of rubbish in there.\n", - size >> 10, mmio_address); + pr_warning("WARNING: mapping %lu kB @ 0x%08lx in PCI address space, " + "and writing 16 kB of rubbish in there.\n", + size >> 10, mmio_address); do_test(size); - pr_info(MODULE_NAME ": All done.\n"); + pr_info("All done.\n"); return 0; } static void __exit cleanup(void) { - pr_debug(MODULE_NAME ": unloaded.\n"); + pr_debug("unloaded.\n"); } module_init(init); diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 8aa85f17667e..0a979f3e5b8a 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -18,6 +18,7 @@ #include <asm/mce.h> #include <asm/xcr.h> #include <asm/suspend.h> +#include <asm/debugreg.h> #ifdef CONFIG_X86_32 static struct saved_context saved_context; @@ -142,31 +143,6 @@ static void fix_processor_context(void) #endif load_TR_desc(); /* This does ltr */ load_LDT(¤t->active_mm->context); /* This does lldt */ - - /* - * Now maybe reload the debug registers - */ - if (current->thread.debugreg7) { -#ifdef CONFIG_X86_32 - set_debugreg(current->thread.debugreg0, 0); - set_debugreg(current->thread.debugreg1, 1); - set_debugreg(current->thread.debugreg2, 2); - set_debugreg(current->thread.debugreg3, 3); - /* no 4 and 5 */ - set_debugreg(current->thread.debugreg6, 6); - set_debugreg(current->thread.debugreg7, 7); -#else - /* CONFIG_X86_64 */ - loaddebug(¤t->thread, 0); - loaddebug(¤t->thread, 1); - loaddebug(¤t->thread, 2); - loaddebug(¤t->thread, 3); - /* no 4 and 5 */ - loaddebug(¤t->thread, 6); - loaddebug(¤t->thread, 7); -#endif - } - } /** diff --git a/arch/x86/tools/Makefile b/arch/x86/tools/Makefile new file mode 100644 index 000000000000..f82082677337 --- /dev/null +++ b/arch/x86/tools/Makefile @@ -0,0 +1,31 @@ +PHONY += posttest + +ifeq ($(KBUILD_VERBOSE),1) + posttest_verbose = -v +else + posttest_verbose = +endif + +ifeq ($(CONFIG_64BIT),y) + posttest_64bit = -y +else + posttest_64bit = -n +endif + +distill_awk = $(srctree)/arch/x86/tools/distill.awk +chkobjdump = $(srctree)/arch/x86/tools/chkobjdump.awk + +quiet_cmd_posttest = TEST $@ + cmd_posttest = ($(OBJDUMP) -v | $(AWK) -f $(chkobjdump)) || $(OBJDUMP) -d -j .text $(objtree)/vmlinux | $(AWK) -f $(distill_awk) | $(obj)/test_get_len $(posttest_64bit) $(posttest_verbose) + +posttest: $(obj)/test_get_len vmlinux + $(call cmd,posttest) + +hostprogs-y := test_get_len + +# -I needed for generated C source and C source which in the kernel tree. +HOSTCFLAGS_test_get_len.o := -Wall -I$(objtree)/arch/x86/lib/ -I$(srctree)/arch/x86/include/ -I$(srctree)/arch/x86/lib/ -I$(srctree)/include/ + +# Dependencies are also needed. +$(obj)/test_get_len.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/inat.c $(srctree)/arch/x86/include/asm/inat_types.h $(srctree)/arch/x86/include/asm/inat.h $(srctree)/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c + diff --git a/arch/x86/tools/chkobjdump.awk b/arch/x86/tools/chkobjdump.awk new file mode 100644 index 000000000000..0d13cd9fdcff --- /dev/null +++ b/arch/x86/tools/chkobjdump.awk @@ -0,0 +1,23 @@ +# GNU objdump version checker +# +# Usage: +# objdump -v | awk -f chkobjdump.awk +BEGIN { + # objdump version 2.19 or later is OK for the test. + od_ver = 2; + od_sver = 19; +} + +/^GNU/ { + split($4, ver, "."); + if (ver[1] > od_ver || + (ver[1] == od_ver && ver[2] >= od_sver)) { + exit 1; + } else { + printf("Warning: objdump version %s is older than %d.%d\n", + $4, od_ver, od_sver); + print("Warning: Skipping posttest."); + # Logic is inverted, because we just skip test without error. + exit 0; + } +} diff --git a/arch/x86/tools/distill.awk b/arch/x86/tools/distill.awk new file mode 100644 index 000000000000..c13c0ee48ab4 --- /dev/null +++ b/arch/x86/tools/distill.awk @@ -0,0 +1,47 @@ +#!/bin/awk -f +# Usage: objdump -d a.out | awk -f distill.awk | ./test_get_len +# Distills the disassembly as follows: +# - Removes all lines except the disassembled instructions. +# - For instructions that exceed 1 line (7 bytes), crams all the hex bytes +# into a single line. +# - Remove bad(or prefix only) instructions + +BEGIN { + prev_addr = "" + prev_hex = "" + prev_mnemonic = "" + bad_expr = "(\\(bad\\)|^rex|^.byte|^rep(z|nz)$|^lock$|^es$|^cs$|^ss$|^ds$|^fs$|^gs$|^data(16|32)$|^addr(16|32|64))" + fwait_expr = "^9b " + fwait_str="9b\tfwait" +} + +/^ *[0-9a-f]+ <[^>]*>:/ { + # Symbol entry + printf("%s%s\n", $2, $1) +} + +/^ *[0-9a-f]+:/ { + if (split($0, field, "\t") < 3) { + # This is a continuation of the same insn. + prev_hex = prev_hex field[2] + } else { + # Skip bad instructions + if (match(prev_mnemonic, bad_expr)) + prev_addr = "" + # Split fwait from other f* instructions + if (match(prev_hex, fwait_expr) && prev_mnemonic != "fwait") { + printf "%s\t%s\n", prev_addr, fwait_str + sub(fwait_expr, "", prev_hex) + } + if (prev_addr != "") + printf "%s\t%s\t%s\n", prev_addr, prev_hex, prev_mnemonic + prev_addr = field[1] + prev_hex = field[2] + prev_mnemonic = field[3] + } +} + +END { + if (prev_addr != "") + printf "%s\t%s\t%s\n", prev_addr, prev_hex, prev_mnemonic +} diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk new file mode 100644 index 000000000000..e34e92a28eb6 --- /dev/null +++ b/arch/x86/tools/gen-insn-attr-x86.awk @@ -0,0 +1,380 @@ +#!/bin/awk -f +# gen-insn-attr-x86.awk: Instruction attribute table generator +# Written by Masami Hiramatsu <mhiramat@redhat.com> +# +# Usage: awk -f gen-insn-attr-x86.awk x86-opcode-map.txt > inat-tables.c + +# Awk implementation sanity check +function check_awk_implement() { + if (!match("abc", "[[:lower:]]+")) + return "Your awk doesn't support charactor-class." + if (sprintf("%x", 0) != "0") + return "Your awk has a printf-format problem." + return "" +} + +# Clear working vars +function clear_vars() { + delete table + delete lptable2 + delete lptable1 + delete lptable3 + eid = -1 # escape id + gid = -1 # group id + aid = -1 # AVX id + tname = "" +} + +BEGIN { + # Implementation error checking + awkchecked = check_awk_implement() + if (awkchecked != "") { + print "Error: " awkchecked > "/dev/stderr" + print "Please try to use gawk." > "/dev/stderr" + exit 1 + } + + # Setup generating tables + print "/* x86 opcode map generated from x86-opcode-map.txt */" + print "/* Do not change this code. */\n" + ggid = 1 + geid = 1 + gaid = 0 + delete etable + delete gtable + delete atable + + opnd_expr = "^[[:alpha:]/]" + ext_expr = "^\\(" + sep_expr = "^\\|$" + group_expr = "^Grp[[:alnum:]]+" + + imm_expr = "^[IJAO][[:lower:]]" + imm_flag["Ib"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)" + imm_flag["Jb"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)" + imm_flag["Iw"] = "INAT_MAKE_IMM(INAT_IMM_WORD)" + imm_flag["Id"] = "INAT_MAKE_IMM(INAT_IMM_DWORD)" + imm_flag["Iq"] = "INAT_MAKE_IMM(INAT_IMM_QWORD)" + imm_flag["Ap"] = "INAT_MAKE_IMM(INAT_IMM_PTR)" + imm_flag["Iz"] = "INAT_MAKE_IMM(INAT_IMM_VWORD32)" + imm_flag["Jz"] = "INAT_MAKE_IMM(INAT_IMM_VWORD32)" + imm_flag["Iv"] = "INAT_MAKE_IMM(INAT_IMM_VWORD)" + imm_flag["Ob"] = "INAT_MOFFSET" + imm_flag["Ov"] = "INAT_MOFFSET" + + modrm_expr = "^([CDEGMNPQRSUVW/][[:lower:]]+|NTA|T[012])" + force64_expr = "\\([df]64\\)" + rex_expr = "^REX(\\.[XRWB]+)*" + fpu_expr = "^ESC" # TODO + + lprefix1_expr = "\\(66\\)" + lprefix2_expr = "\\(F3\\)" + lprefix3_expr = "\\(F2\\)" + max_lprefix = 4 + + vexok_expr = "\\(VEX\\)" + vexonly_expr = "\\(oVEX\\)" + + prefix_expr = "\\(Prefix\\)" + prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ" + prefix_num["REPNE"] = "INAT_PFX_REPNE" + prefix_num["REP/REPE"] = "INAT_PFX_REPE" + prefix_num["LOCK"] = "INAT_PFX_LOCK" + prefix_num["SEG=CS"] = "INAT_PFX_CS" + prefix_num["SEG=DS"] = "INAT_PFX_DS" + prefix_num["SEG=ES"] = "INAT_PFX_ES" + prefix_num["SEG=FS"] = "INAT_PFX_FS" + prefix_num["SEG=GS"] = "INAT_PFX_GS" + prefix_num["SEG=SS"] = "INAT_PFX_SS" + prefix_num["Address-Size"] = "INAT_PFX_ADDRSZ" + prefix_num["2bytes-VEX"] = "INAT_PFX_VEX2" + prefix_num["3bytes-VEX"] = "INAT_PFX_VEX3" + + clear_vars() +} + +function semantic_error(msg) { + print "Semantic error at " NR ": " msg > "/dev/stderr" + exit 1 +} + +function debug(msg) { + print "DEBUG: " msg +} + +function array_size(arr, i,c) { + c = 0 + for (i in arr) + c++ + return c +} + +/^Table:/ { + print "/* " $0 " */" + if (tname != "") + semantic_error("Hit Table: before EndTable:."); +} + +/^Referrer:/ { + if (NF != 1) { + # escape opcode table + ref = "" + for (i = 2; i <= NF; i++) + ref = ref $i + eid = escape[ref] + tname = sprintf("inat_escape_table_%d", eid) + } +} + +/^AVXcode:/ { + if (NF != 1) { + # AVX/escape opcode table + aid = $2 + if (gaid <= aid) + gaid = aid + 1 + if (tname == "") # AVX only opcode table + tname = sprintf("inat_avx_table_%d", $2) + } + if (aid == -1 && eid == -1) # primary opcode table + tname = "inat_primary_table" +} + +/^GrpTable:/ { + print "/* " $0 " */" + if (!($2 in group)) + semantic_error("No group: " $2 ) + gid = group[$2] + tname = "inat_group_table_" gid +} + +function print_table(tbl,name,fmt,n) +{ + print "const insn_attr_t " name " = {" + for (i = 0; i < n; i++) { + id = sprintf(fmt, i) + if (tbl[id]) + print " [" id "] = " tbl[id] "," + } + print "};" +} + +/^EndTable/ { + if (gid != -1) { + # print group tables + if (array_size(table) != 0) { + print_table(table, tname "[INAT_GROUP_TABLE_SIZE]", + "0x%x", 8) + gtable[gid,0] = tname + } + if (array_size(lptable1) != 0) { + print_table(lptable1, tname "_1[INAT_GROUP_TABLE_SIZE]", + "0x%x", 8) + gtable[gid,1] = tname "_1" + } + if (array_size(lptable2) != 0) { + print_table(lptable2, tname "_2[INAT_GROUP_TABLE_SIZE]", + "0x%x", 8) + gtable[gid,2] = tname "_2" + } + if (array_size(lptable3) != 0) { + print_table(lptable3, tname "_3[INAT_GROUP_TABLE_SIZE]", + "0x%x", 8) + gtable[gid,3] = tname "_3" + } + } else { + # print primary/escaped tables + if (array_size(table) != 0) { + print_table(table, tname "[INAT_OPCODE_TABLE_SIZE]", + "0x%02x", 256) + etable[eid,0] = tname + if (aid >= 0) + atable[aid,0] = tname + } + if (array_size(lptable1) != 0) { + print_table(lptable1,tname "_1[INAT_OPCODE_TABLE_SIZE]", + "0x%02x", 256) + etable[eid,1] = tname "_1" + if (aid >= 0) + atable[aid,1] = tname "_1" + } + if (array_size(lptable2) != 0) { + print_table(lptable2,tname "_2[INAT_OPCODE_TABLE_SIZE]", + "0x%02x", 256) + etable[eid,2] = tname "_2" + if (aid >= 0) + atable[aid,2] = tname "_2" + } + if (array_size(lptable3) != 0) { + print_table(lptable3,tname "_3[INAT_OPCODE_TABLE_SIZE]", + "0x%02x", 256) + etable[eid,3] = tname "_3" + if (aid >= 0) + atable[aid,3] = tname "_3" + } + } + print "" + clear_vars() +} + +function add_flags(old,new) { + if (old && new) + return old " | " new + else if (old) + return old + else + return new +} + +# convert operands to flags. +function convert_operands(opnd, i,imm,mod) +{ + imm = null + mod = null + for (i in opnd) { + i = opnd[i] + if (match(i, imm_expr) == 1) { + if (!imm_flag[i]) + semantic_error("Unknown imm opnd: " i) + if (imm) { + if (i != "Ib") + semantic_error("Second IMM error") + imm = add_flags(imm, "INAT_SCNDIMM") + } else + imm = imm_flag[i] + } else if (match(i, modrm_expr)) + mod = "INAT_MODRM" + } + return add_flags(imm, mod) +} + +/^[0-9a-f]+\:/ { + if (NR == 1) + next + # get index + idx = "0x" substr($1, 1, index($1,":") - 1) + if (idx in table) + semantic_error("Redefine " idx " in " tname) + + # check if escaped opcode + if ("escape" == $2) { + if ($3 != "#") + semantic_error("No escaped name") + ref = "" + for (i = 4; i <= NF; i++) + ref = ref $i + if (ref in escape) + semantic_error("Redefine escape (" ref ")") + escape[ref] = geid + geid++ + table[idx] = "INAT_MAKE_ESCAPE(" escape[ref] ")" + next + } + + variant = null + # converts + i = 2 + while (i <= NF) { + opcode = $(i++) + delete opnds + ext = null + flags = null + opnd = null + # parse one opcode + if (match($i, opnd_expr)) { + opnd = $i + split($(i++), opnds, ",") + flags = convert_operands(opnds) + } + if (match($i, ext_expr)) + ext = $(i++) + if (match($i, sep_expr)) + i++ + else if (i < NF) + semantic_error($i " is not a separator") + + # check if group opcode + if (match(opcode, group_expr)) { + if (!(opcode in group)) { + group[opcode] = ggid + ggid++ + } + flags = add_flags(flags, "INAT_MAKE_GROUP(" group[opcode] ")") + } + # check force(or default) 64bit + if (match(ext, force64_expr)) + flags = add_flags(flags, "INAT_FORCE64") + + # check REX prefix + if (match(opcode, rex_expr)) + flags = add_flags(flags, "INAT_MAKE_PREFIX(INAT_PFX_REX)") + + # check coprocessor escape : TODO + if (match(opcode, fpu_expr)) + flags = add_flags(flags, "INAT_MODRM") + + # check VEX only code + if (match(ext, vexonly_expr)) + flags = add_flags(flags, "INAT_VEXOK | INAT_VEXONLY") + + # check VEX only code + if (match(ext, vexok_expr)) + flags = add_flags(flags, "INAT_VEXOK") + + # check prefixes + if (match(ext, prefix_expr)) { + if (!prefix_num[opcode]) + semantic_error("Unknown prefix: " opcode) + flags = add_flags(flags, "INAT_MAKE_PREFIX(" prefix_num[opcode] ")") + } + if (length(flags) == 0) + continue + # check if last prefix + if (match(ext, lprefix1_expr)) { + lptable1[idx] = add_flags(lptable1[idx],flags) + variant = "INAT_VARIANT" + } else if (match(ext, lprefix2_expr)) { + lptable2[idx] = add_flags(lptable2[idx],flags) + variant = "INAT_VARIANT" + } else if (match(ext, lprefix3_expr)) { + lptable3[idx] = add_flags(lptable3[idx],flags) + variant = "INAT_VARIANT" + } else { + table[idx] = add_flags(table[idx],flags) + } + } + if (variant) + table[idx] = add_flags(table[idx],variant) +} + +END { + if (awkchecked != "") + exit 1 + # print escape opcode map's array + print "/* Escape opcode map array */" + print "const insn_attr_t const *inat_escape_tables[INAT_ESC_MAX + 1]" \ + "[INAT_LSTPFX_MAX + 1] = {" + for (i = 0; i < geid; i++) + for (j = 0; j < max_lprefix; j++) + if (etable[i,j]) + print " ["i"]["j"] = "etable[i,j]"," + print "};\n" + # print group opcode map's array + print "/* Group opcode map array */" + print "const insn_attr_t const *inat_group_tables[INAT_GRP_MAX + 1]"\ + "[INAT_LSTPFX_MAX + 1] = {" + for (i = 0; i < ggid; i++) + for (j = 0; j < max_lprefix; j++) + if (gtable[i,j]) + print " ["i"]["j"] = "gtable[i,j]"," + print "};\n" + # print AVX opcode map's array + print "/* AVX opcode map array */" + print "const insn_attr_t const *inat_avx_tables[X86_VEX_M_MAX + 1]"\ + "[INAT_LSTPFX_MAX + 1] = {" + for (i = 0; i < gaid; i++) + for (j = 0; j < max_lprefix; j++) + if (atable[i,j]) + print " ["i"]["j"] = "atable[i,j]"," + print "};" +} + diff --git a/arch/x86/tools/test_get_len.c b/arch/x86/tools/test_get_len.c new file mode 100644 index 000000000000..d8214dc03fa7 --- /dev/null +++ b/arch/x86/tools/test_get_len.c @@ -0,0 +1,173 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) IBM Corporation, 2009 + */ + +#include <stdlib.h> +#include <stdio.h> +#include <string.h> +#include <assert.h> +#include <unistd.h> + +#define unlikely(cond) (cond) + +#include <asm/insn.h> +#include <inat.c> +#include <insn.c> + +/* + * Test of instruction analysis in general and insn_get_length() in + * particular. See if insn_get_length() and the disassembler agree + * on the length of each instruction in an elf disassembly. + * + * Usage: objdump -d a.out | awk -f distill.awk | ./test_get_len + */ + +const char *prog; +static int verbose; +static int x86_64; + +static void usage(void) +{ + fprintf(stderr, "Usage: objdump -d a.out | awk -f distill.awk |" + " %s [-y|-n] [-v] \n", prog); + fprintf(stderr, "\t-y 64bit mode\n"); + fprintf(stderr, "\t-n 32bit mode\n"); + fprintf(stderr, "\t-v verbose mode\n"); + exit(1); +} + +static void malformed_line(const char *line, int line_nr) +{ + fprintf(stderr, "%s: malformed line %d:\n%s", prog, line_nr, line); + exit(3); +} + +static void dump_field(FILE *fp, const char *name, const char *indent, + struct insn_field *field) +{ + fprintf(fp, "%s.%s = {\n", indent, name); + fprintf(fp, "%s\t.value = %d, bytes[] = {%x, %x, %x, %x},\n", + indent, field->value, field->bytes[0], field->bytes[1], + field->bytes[2], field->bytes[3]); + fprintf(fp, "%s\t.got = %d, .nbytes = %d},\n", indent, + field->got, field->nbytes); +} + +static void dump_insn(FILE *fp, struct insn *insn) +{ + fprintf(fp, "Instruction = { \n"); + dump_field(fp, "prefixes", "\t", &insn->prefixes); + dump_field(fp, "rex_prefix", "\t", &insn->rex_prefix); + dump_field(fp, "vex_prefix", "\t", &insn->vex_prefix); + dump_field(fp, "opcode", "\t", &insn->opcode); + dump_field(fp, "modrm", "\t", &insn->modrm); + dump_field(fp, "sib", "\t", &insn->sib); + dump_field(fp, "displacement", "\t", &insn->displacement); + dump_field(fp, "immediate1", "\t", &insn->immediate1); + dump_field(fp, "immediate2", "\t", &insn->immediate2); + fprintf(fp, "\t.attr = %x, .opnd_bytes = %d, .addr_bytes = %d,\n", + insn->attr, insn->opnd_bytes, insn->addr_bytes); + fprintf(fp, "\t.length = %d, .x86_64 = %d, .kaddr = %p}\n", + insn->length, insn->x86_64, insn->kaddr); +} + +static void parse_args(int argc, char **argv) +{ + int c; + prog = argv[0]; + while ((c = getopt(argc, argv, "ynv")) != -1) { + switch (c) { + case 'y': + x86_64 = 1; + break; + case 'n': + x86_64 = 0; + break; + case 'v': + verbose = 1; + break; + default: + usage(); + } + } +} + +#define BUFSIZE 256 + +int main(int argc, char **argv) +{ + char line[BUFSIZE], sym[BUFSIZE] = "<unknown>"; + unsigned char insn_buf[16]; + struct insn insn; + int insns = 0, c; + int warnings = 0; + + parse_args(argc, argv); + + while (fgets(line, BUFSIZE, stdin)) { + char copy[BUFSIZE], *s, *tab1, *tab2; + int nb = 0; + unsigned int b; + + if (line[0] == '<') { + /* Symbol line */ + strcpy(sym, line); + continue; + } + + insns++; + memset(insn_buf, 0, 16); + strcpy(copy, line); + tab1 = strchr(copy, '\t'); + if (!tab1) + malformed_line(line, insns); + s = tab1 + 1; + s += strspn(s, " "); + tab2 = strchr(s, '\t'); + if (!tab2) + malformed_line(line, insns); + *tab2 = '\0'; /* Characters beyond tab2 aren't examined */ + while (s < tab2) { + if (sscanf(s, "%x", &b) == 1) { + insn_buf[nb++] = (unsigned char) b; + s += 3; + } else + break; + } + /* Decode an instruction */ + insn_init(&insn, insn_buf, x86_64); + insn_get_length(&insn); + if (insn.length != nb) { + warnings++; + fprintf(stderr, "Warning: %s found difference at %s\n", + prog, sym); + fprintf(stderr, "Warning: %s", line); + fprintf(stderr, "Warning: objdump says %d bytes, but " + "insn_get_length() says %d\n", nb, + insn.length); + if (verbose) + dump_insn(stderr, &insn); + } + } + if (warnings) + fprintf(stderr, "Warning: decoded and checked %d" + " instructions with %d warnings\n", insns, warnings); + else + fprintf(stderr, "Succeed: decoded and checked %d" + " instructions\n", insns); + return 0; +} diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c index 58bc00f68b12..02b442e92007 100644 --- a/arch/x86/vdso/vdso32-setup.c +++ b/arch/x86/vdso/vdso32-setup.c @@ -393,7 +393,6 @@ static ctl_table abi_table2[] = { static ctl_table abi_root_table2[] = { { - .ctl_name = CTL_ABI, .procname = "abi", .mode = 0555, .child = abi_table2 diff --git a/crypto/async_tx/Kconfig b/crypto/async_tx/Kconfig index e5aeb2b79e6f..e28e276ac611 100644 --- a/crypto/async_tx/Kconfig +++ b/crypto/async_tx/Kconfig @@ -23,3 +23,8 @@ config ASYNC_RAID6_RECOV select ASYNC_CORE select ASYNC_PQ +config ASYNC_TX_DISABLE_PQ_VAL_DMA + bool + +config ASYNC_TX_DISABLE_XOR_VAL_DMA + bool diff --git a/crypto/async_tx/async_pq.c b/crypto/async_tx/async_pq.c index 6b5cc4fba59f..ec87f53d5059 100644 --- a/crypto/async_tx/async_pq.c +++ b/crypto/async_tx/async_pq.c @@ -240,6 +240,16 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks, } EXPORT_SYMBOL_GPL(async_gen_syndrome); +static inline struct dma_chan * +pq_val_chan(struct async_submit_ctl *submit, struct page **blocks, int disks, size_t len) +{ + #ifdef CONFIG_ASYNC_TX_DISABLE_PQ_VAL_DMA + return NULL; + #endif + return async_tx_find_channel(submit, DMA_PQ_VAL, NULL, 0, blocks, + disks, len); +} + /** * async_syndrome_val - asynchronously validate a raid6 syndrome * @blocks: source blocks from idx 0..disks-3, P @ disks-2 and Q @ disks-1 @@ -260,9 +270,7 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks, size_t len, enum sum_check_flags *pqres, struct page *spare, struct async_submit_ctl *submit) { - struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ_VAL, - NULL, 0, blocks, disks, - len); + struct dma_chan *chan = pq_val_chan(submit, blocks, disks, len); struct dma_device *device = chan ? chan->device : NULL; struct dma_async_tx_descriptor *tx; unsigned char coefs[disks-2]; diff --git a/crypto/async_tx/async_xor.c b/crypto/async_tx/async_xor.c index 79182dcb91b7..079ae8ca590b 100644 --- a/crypto/async_tx/async_xor.c +++ b/crypto/async_tx/async_xor.c @@ -234,6 +234,17 @@ static int page_is_zero(struct page *p, unsigned int offset, size_t len) memcmp(a, a + 4, len - 4) == 0); } +static inline struct dma_chan * +xor_val_chan(struct async_submit_ctl *submit, struct page *dest, + struct page **src_list, int src_cnt, size_t len) +{ + #ifdef CONFIG_ASYNC_TX_DISABLE_XOR_VAL_DMA + return NULL; + #endif + return async_tx_find_channel(submit, DMA_XOR_VAL, &dest, 1, src_list, + src_cnt, len); +} + /** * async_xor_val - attempt a xor parity check with a dma engine. * @dest: destination page used if the xor is performed synchronously @@ -255,9 +266,7 @@ async_xor_val(struct page *dest, struct page **src_list, unsigned int offset, int src_cnt, size_t len, enum sum_check_flags *result, struct async_submit_ctl *submit) { - struct dma_chan *chan = async_tx_find_channel(submit, DMA_XOR_VAL, - &dest, 1, src_list, - src_cnt, len); + struct dma_chan *chan = xor_val_chan(submit, dest, src_list, src_cnt, len); struct dma_device *device = chan ? chan->device : NULL; struct dma_async_tx_descriptor *tx = NULL; dma_addr_t *dma_src = NULL; diff --git a/crypto/gcm.c b/crypto/gcm.c index 5fc3292483ef..c6547130624c 100644 --- a/crypto/gcm.c +++ b/crypto/gcm.c @@ -40,7 +40,7 @@ struct crypto_rfc4106_ctx { struct crypto_gcm_ghash_ctx { unsigned int cryptlen; struct scatterlist *src; - crypto_completion_t complete; + void (*complete)(struct aead_request *req, int err); }; struct crypto_gcm_req_priv_ctx { @@ -267,23 +267,26 @@ static int gcm_hash_final(struct aead_request *req, return crypto_ahash_final(ahreq); } -static void gcm_hash_final_done(struct crypto_async_request *areq, - int err) +static void __gcm_hash_final_done(struct aead_request *req, int err) { - struct aead_request *req = areq->data; struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req); struct crypto_gcm_ghash_ctx *gctx = &pctx->ghash_ctx; if (!err) crypto_xor(pctx->auth_tag, pctx->iauth_tag, 16); - gctx->complete(areq, err); + gctx->complete(req, err); } -static void gcm_hash_len_done(struct crypto_async_request *areq, - int err) +static void gcm_hash_final_done(struct crypto_async_request *areq, int err) { struct aead_request *req = areq->data; + + __gcm_hash_final_done(req, err); +} + +static void __gcm_hash_len_done(struct aead_request *req, int err) +{ struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req); if (!err) { @@ -292,13 +295,18 @@ static void gcm_hash_len_done(struct crypto_async_request *areq, return; } - gcm_hash_final_done(areq, err); + __gcm_hash_final_done(req, err); } -static void gcm_hash_crypt_remain_done(struct crypto_async_request *areq, - int err) +static void gcm_hash_len_done(struct crypto_async_request *areq, int err) { struct aead_request *req = areq->data; + + __gcm_hash_len_done(req, err); +} + +static void __gcm_hash_crypt_remain_done(struct aead_request *req, int err) +{ struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req); if (!err) { @@ -307,13 +315,19 @@ static void gcm_hash_crypt_remain_done(struct crypto_async_request *areq, return; } - gcm_hash_len_done(areq, err); + __gcm_hash_len_done(req, err); } -static void gcm_hash_crypt_done(struct crypto_async_request *areq, - int err) +static void gcm_hash_crypt_remain_done(struct crypto_async_request *areq, + int err) { struct aead_request *req = areq->data; + + __gcm_hash_crypt_remain_done(req, err); +} + +static void __gcm_hash_crypt_done(struct aead_request *req, int err) +{ struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req); struct crypto_gcm_ghash_ctx *gctx = &pctx->ghash_ctx; unsigned int remain; @@ -327,13 +341,18 @@ static void gcm_hash_crypt_done(struct crypto_async_request *areq, return; } - gcm_hash_crypt_remain_done(areq, err); + __gcm_hash_crypt_remain_done(req, err); } -static void gcm_hash_assoc_remain_done(struct crypto_async_request *areq, - int err) +static void gcm_hash_crypt_done(struct crypto_async_request *areq, int err) { struct aead_request *req = areq->data; + + __gcm_hash_crypt_done(req, err); +} + +static void __gcm_hash_assoc_remain_done(struct aead_request *req, int err) +{ struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req); struct crypto_gcm_ghash_ctx *gctx = &pctx->ghash_ctx; crypto_completion_t complete; @@ -350,15 +369,21 @@ static void gcm_hash_assoc_remain_done(struct crypto_async_request *areq, } if (remain) - gcm_hash_crypt_done(areq, err); + __gcm_hash_crypt_done(req, err); else - gcm_hash_crypt_remain_done(areq, err); + __gcm_hash_crypt_remain_done(req, err); } -static void gcm_hash_assoc_done(struct crypto_async_request *areq, - int err) +static void gcm_hash_assoc_remain_done(struct crypto_async_request *areq, + int err) { struct aead_request *req = areq->data; + + __gcm_hash_assoc_remain_done(req, err); +} + +static void __gcm_hash_assoc_done(struct aead_request *req, int err) +{ struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req); unsigned int remain; @@ -371,13 +396,18 @@ static void gcm_hash_assoc_done(struct crypto_async_request *areq, return; } - gcm_hash_assoc_remain_done(areq, err); + __gcm_hash_assoc_remain_done(req, err); } -static void gcm_hash_init_done(struct crypto_async_request *areq, - int err) +static void gcm_hash_assoc_done(struct crypto_async_request *areq, int err) { struct aead_request *req = areq->data; + + __gcm_hash_assoc_done(req, err); +} + +static void __gcm_hash_init_done(struct aead_request *req, int err) +{ struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req); crypto_completion_t complete; unsigned int remain = 0; @@ -393,9 +423,16 @@ static void gcm_hash_init_done(struct crypto_async_request *areq, } if (remain) - gcm_hash_assoc_done(areq, err); + __gcm_hash_assoc_done(req, err); else - gcm_hash_assoc_remain_done(areq, err); + __gcm_hash_assoc_remain_done(req, err); +} + +static void gcm_hash_init_done(struct crypto_async_request *areq, int err) +{ + struct aead_request *req = areq->data; + + __gcm_hash_init_done(req, err); } static int gcm_hash(struct aead_request *req, @@ -457,10 +494,8 @@ static void gcm_enc_copy_hash(struct aead_request *req, crypto_aead_authsize(aead), 1); } -static void gcm_enc_hash_done(struct crypto_async_request *areq, - int err) +static void gcm_enc_hash_done(struct aead_request *req, int err) { - struct aead_request *req = areq->data; struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req); if (!err) @@ -469,8 +504,7 @@ static void gcm_enc_hash_done(struct crypto_async_request *areq, aead_request_complete(req, err); } -static void gcm_encrypt_done(struct crypto_async_request *areq, - int err) +static void gcm_encrypt_done(struct crypto_async_request *areq, int err) { struct aead_request *req = areq->data; struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req); @@ -479,9 +513,13 @@ static void gcm_encrypt_done(struct crypto_async_request *areq, err = gcm_hash(req, pctx); if (err == -EINPROGRESS || err == -EBUSY) return; + else if (!err) { + crypto_xor(pctx->auth_tag, pctx->iauth_tag, 16); + gcm_enc_copy_hash(req, pctx); + } } - gcm_enc_hash_done(areq, err); + aead_request_complete(req, err); } static int crypto_gcm_encrypt(struct aead_request *req) @@ -538,9 +576,8 @@ static void gcm_decrypt_done(struct crypto_async_request *areq, int err) aead_request_complete(req, err); } -static void gcm_dec_hash_done(struct crypto_async_request *areq, int err) +static void gcm_dec_hash_done(struct aead_request *req, int err) { - struct aead_request *req = areq->data; struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req); struct ablkcipher_request *abreq = &pctx->u.abreq; struct crypto_gcm_ghash_ctx *gctx = &pctx->ghash_ctx; @@ -552,9 +589,11 @@ static void gcm_dec_hash_done(struct crypto_async_request *areq, int err) err = crypto_ablkcipher_decrypt(abreq); if (err == -EINPROGRESS || err == -EBUSY) return; + else if (!err) + err = crypto_gcm_verify(req, pctx); } - gcm_decrypt_done(areq, err); + aead_request_complete(req, err); } static int crypto_gcm_decrypt(struct aead_request *req) diff --git a/crypto/proc.c b/crypto/proc.c index 5dc07e442fca..1c38733c224d 100644 --- a/crypto/proc.c +++ b/crypto/proc.c @@ -25,28 +25,22 @@ #ifdef CONFIG_CRYPTO_FIPS static struct ctl_table crypto_sysctl_table[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "fips_enabled", .data = &fips_enabled, .maxlen = sizeof(int), .mode = 0444, - .proc_handler = &proc_dointvec - }, - { - .ctl_name = 0, + .proc_handler = proc_dointvec }, + {} }; static struct ctl_table crypto_dir_table[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "crypto", .mode = 0555, .child = crypto_sysctl_table }, - { - .ctl_name = 0, - }, + {} }; static struct ctl_table_header *crypto_sysctls; diff --git a/drivers/acpi/acpica/acpredef.h b/drivers/acpi/acpica/acpredef.h index cd80d1dd1950..57bdaf6ffab1 100644 --- a/drivers/acpi/acpica/acpredef.h +++ b/drivers/acpi/acpica/acpredef.h @@ -203,8 +203,9 @@ static const union acpi_predefined_info predefined_names[] = {{"_BCT", 1, ACPI_RTYPE_INTEGER}}, {{"_BDN", 0, ACPI_RTYPE_INTEGER}}, {{"_BFS", 1, 0}}, - {{"_BIF", 0, ACPI_RTYPE_PACKAGE}}, /* Fixed-length (9 Int),(4 Str) */ - {{{ACPI_PTYPE1_FIXED, ACPI_RTYPE_INTEGER, 9, ACPI_RTYPE_STRING}, 4,0}}, + {{"_BIF", 0, ACPI_RTYPE_PACKAGE} }, /* Fixed-length (9 Int),(4 Str/Buf) */ + {{{ACPI_PTYPE1_FIXED, ACPI_RTYPE_INTEGER, 9, + ACPI_RTYPE_STRING | ACPI_RTYPE_BUFFER}, 4, 0} }, {{"_BIX", 0, ACPI_RTYPE_PACKAGE}}, /* Fixed-length (16 Int),(4 Str) */ {{{ACPI_PTYPE1_FIXED, ACPI_RTYPE_INTEGER, 16, ACPI_RTYPE_STRING}, 4, diff --git a/drivers/acpi/blacklist.c b/drivers/acpi/blacklist.c index e56b2a7b53db..23e5a0519af5 100644 --- a/drivers/acpi/blacklist.c +++ b/drivers/acpi/blacklist.c @@ -224,6 +224,7 @@ static struct dmi_system_id acpi_osi_dmi_table[] __initdata = { * _OSI(Linux) helps sound * DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad R61"), * DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T61"), + * T400, T500 * _OSI(Linux) has Linux specific hooks * DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X61"), * _OSI(Linux) is a NOP: @@ -254,6 +255,22 @@ static struct dmi_system_id acpi_osi_dmi_table[] __initdata = { DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X61"), }, }, + { + .callback = dmi_enable_osi_linux, + .ident = "Lenovo ThinkPad T400", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T400"), + }, + }, + { + .callback = dmi_enable_osi_linux, + .ident = "Lenovo ThinkPad T500", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T500"), + }, + }, {} }; diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 4cc1b8116e76..5f2c379ab7bf 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -430,6 +430,14 @@ static struct dmi_system_id __initdata acpisleep_dmi_table[] = { }, { .callback = init_set_sci_en_on_resume, + .ident = "Hewlett-Packard Compaq Presario C700 Notebook PC", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "Compaq Presario C700 Notebook PC"), + }, + }, + { + .callback = init_set_sci_en_on_resume, .ident = "Hewlett-Packard Compaq Presario CQ40 Notebook PC", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), diff --git a/drivers/ata/pata_pcmcia.c b/drivers/ata/pata_pcmcia.c index dc99e26f8e5b..1b392c9e8531 100644 --- a/drivers/ata/pata_pcmcia.c +++ b/drivers/ata/pata_pcmcia.c @@ -177,9 +177,6 @@ static struct ata_port_operations pcmcia_8bit_port_ops = { .drain_fifo = pcmcia_8bit_drain_fifo, }; -#define CS_CHECK(fn, ret) \ -do { last_fn = (fn); if ((last_ret = (ret)) != 0) goto cs_failed; } while (0) - struct pcmcia_config_check { unsigned long ctl_base; @@ -252,7 +249,7 @@ static int pcmcia_init_one(struct pcmcia_device *pdev) struct ata_port *ap; struct ata_pcmcia_info *info; struct pcmcia_config_check *stk = NULL; - int last_ret = 0, last_fn = 0, is_kme = 0, ret = -ENOMEM, p; + int is_kme = 0, ret = -ENOMEM, p; unsigned long io_base, ctl_base; void __iomem *io_addr, *ctl_addr; int n_ports = 1; @@ -271,7 +268,6 @@ static int pcmcia_init_one(struct pcmcia_device *pdev) pdev->io.Attributes2 = IO_DATA_PATH_WIDTH_8; pdev->io.IOAddrLines = 3; pdev->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; - pdev->irq.IRQInfo1 = IRQ_LEVEL_ID; pdev->conf.Attributes = CONF_ENABLE_IRQ; pdev->conf.IntType = INT_MEMORY_AND_IO; @@ -296,8 +292,13 @@ static int pcmcia_init_one(struct pcmcia_device *pdev) } io_base = pdev->io.BasePort1; ctl_base = stk->ctl_base; - CS_CHECK(RequestIRQ, pcmcia_request_irq(pdev, &pdev->irq)); - CS_CHECK(RequestConfiguration, pcmcia_request_configuration(pdev, &pdev->conf)); + ret = pcmcia_request_irq(pdev, &pdev->irq); + if (ret) + goto failed; + + ret = pcmcia_request_configuration(pdev, &pdev->conf); + if (ret) + goto failed; /* iomap */ ret = -ENOMEM; @@ -351,8 +352,6 @@ static int pcmcia_init_one(struct pcmcia_device *pdev) kfree(stk); return 0; -cs_failed: - cs_error(pdev, last_fn, last_ret); failed: kfree(stk); info->ndev = 0; diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c index d344db42a002..172b57e6543f 100644 --- a/drivers/ata/sata_fsl.c +++ b/drivers/ata/sata_fsl.c @@ -707,34 +707,17 @@ static unsigned int sata_fsl_dev_classify(struct ata_port *ap) return ata_dev_classify(&tf); } -static int sata_fsl_prereset(struct ata_link *link, unsigned long deadline) -{ - /* FIXME: Never skip softreset, sata_fsl_softreset() is - * combination of soft and hard resets. sata_fsl_softreset() - * needs to be splitted into soft and hard resets. - */ - return 0; -} - -static int sata_fsl_softreset(struct ata_link *link, unsigned int *class, +static int sata_fsl_hardreset(struct ata_link *link, unsigned int *class, unsigned long deadline) { struct ata_port *ap = link->ap; - struct sata_fsl_port_priv *pp = ap->private_data; struct sata_fsl_host_priv *host_priv = ap->host->private_data; void __iomem *hcr_base = host_priv->hcr_base; - int pmp = sata_srst_pmp(link); u32 temp; - struct ata_taskfile tf; - u8 *cfis; - u32 Serror; int i = 0; unsigned long start_jiffies; - DPRINTK("in xx_softreset\n"); - - if (pmp != SATA_PMP_CTRL_PORT) - goto issue_srst; + DPRINTK("in xx_hardreset\n"); try_offline_again: /* @@ -749,7 +732,7 @@ try_offline_again: if (temp & ONLINE) { ata_port_printk(ap, KERN_ERR, - "Softreset failed, not off-lined %d\n", i); + "Hardreset failed, not off-lined %d\n", i); /* * Try to offline controller atleast twice @@ -761,7 +744,7 @@ try_offline_again: goto try_offline_again; } - DPRINTK("softreset, controller off-lined\n"); + DPRINTK("hardreset, controller off-lined\n"); VPRINTK("HStatus = 0x%x\n", ioread32(hcr_base + HSTATUS)); VPRINTK("HControl = 0x%x\n", ioread32(hcr_base + HCONTROL)); @@ -786,11 +769,11 @@ try_offline_again: if (!(temp & ONLINE)) { ata_port_printk(ap, KERN_ERR, - "Softreset failed, not on-lined\n"); + "Hardreset failed, not on-lined\n"); goto err; } - DPRINTK("softreset, controller off-lined & on-lined\n"); + DPRINTK("hardreset, controller off-lined & on-lined\n"); VPRINTK("HStatus = 0x%x\n", ioread32(hcr_base + HSTATUS)); VPRINTK("HControl = 0x%x\n", ioread32(hcr_base + HCONTROL)); @@ -806,7 +789,7 @@ try_offline_again: "No Device OR PHYRDY change,Hstatus = 0x%x\n", ioread32(hcr_base + HSTATUS)); *class = ATA_DEV_NONE; - goto out; + return 0; } /* @@ -819,11 +802,44 @@ try_offline_again: if ((temp & 0xFF) != 0x18) { ata_port_printk(ap, KERN_WARNING, "No Signature Update\n"); *class = ATA_DEV_NONE; - goto out; + goto do_followup_srst; } else { ata_port_printk(ap, KERN_INFO, "Signature Update detected @ %d msecs\n", jiffies_to_msecs(jiffies - start_jiffies)); + *class = sata_fsl_dev_classify(ap); + return 0; + } + +do_followup_srst: + /* + * request libATA to perform follow-up softreset + */ + return -EAGAIN; + +err: + return -EIO; +} + +static int sata_fsl_softreset(struct ata_link *link, unsigned int *class, + unsigned long deadline) +{ + struct ata_port *ap = link->ap; + struct sata_fsl_port_priv *pp = ap->private_data; + struct sata_fsl_host_priv *host_priv = ap->host->private_data; + void __iomem *hcr_base = host_priv->hcr_base; + int pmp = sata_srst_pmp(link); + u32 temp; + struct ata_taskfile tf; + u8 *cfis; + u32 Serror; + + DPRINTK("in xx_softreset\n"); + + if (ata_link_offline(link)) { + DPRINTK("PHY reports no device\n"); + *class = ATA_DEV_NONE; + return 0; } /* @@ -834,7 +850,6 @@ try_offline_again: * reached here, we can send a command to the target device */ -issue_srst: DPRINTK("Sending SRST/device reset\n"); ata_tf_init(link->device, &tf); @@ -860,6 +875,8 @@ issue_srst: ioread32(CA + hcr_base), ioread32(CC + hcr_base)); iowrite32(0xFFFF, CC + hcr_base); + if (pmp != SATA_PMP_CTRL_PORT) + iowrite32(pmp, CQPMP + hcr_base); iowrite32(1, CQ + hcr_base); temp = ata_wait_register(CQ + hcr_base, 0x1, 0x1, 1, 5000); @@ -926,7 +943,6 @@ issue_srst: VPRINTK("cereg = 0x%x\n", ioread32(hcr_base + CE)); } -out: return 0; err: @@ -988,18 +1004,6 @@ static void sata_fsl_error_intr(struct ata_port *ap) ehi->err_mask |= AC_ERR_ATA_BUS; ehi->action |= ATA_EH_SOFTRESET; - /* - * Ignore serror in case of fatal errors as we always want - * to do a soft-reset of the FSL SATA controller. Analyzing - * serror may cause libata to schedule a hard-reset action, - * and hard-reset currently does not do controller - * offline/online, causing command timeouts and leads to an - * un-recoverable state, hence make libATA ignore - * autopsy in case of fatal errors. - */ - - ehi->flags |= ATA_EHI_NO_AUTOPSY; - freeze = 1; } @@ -1267,8 +1271,8 @@ static struct ata_port_operations sata_fsl_ops = { .freeze = sata_fsl_freeze, .thaw = sata_fsl_thaw, - .prereset = sata_fsl_prereset, .softreset = sata_fsl_softreset, + .hardreset = sata_fsl_hardreset, .pmp_softreset = sata_fsl_softreset, .error_handler = sata_fsl_error_handler, .post_internal_cmd = sata_fsl_post_internal_cmd, diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index a770498a74ec..846d89e3d122 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -328,11 +328,11 @@ int __pm_runtime_resume(struct device *dev, bool from_wq) * necessary. */ parent = dev->parent; - spin_unlock_irq(&dev->power.lock); + spin_unlock(&dev->power.lock); pm_runtime_get_noresume(parent); - spin_lock_irq(&parent->power.lock); + spin_lock(&parent->power.lock); /* * We can resume if the parent's run-time PM is disabled or it * is set to ignore children. @@ -343,9 +343,9 @@ int __pm_runtime_resume(struct device *dev, bool from_wq) if (parent->power.runtime_status != RPM_ACTIVE) retval = -EBUSY; } - spin_unlock_irq(&parent->power.lock); + spin_unlock(&parent->power.lock); - spin_lock_irq(&dev->power.lock); + spin_lock(&dev->power.lock); if (retval) goto out; goto repeat; @@ -777,7 +777,7 @@ int __pm_runtime_set_status(struct device *dev, unsigned int status) } if (parent) { - spin_lock_irq(&parent->power.lock); + spin_lock(&parent->power.lock); /* * It is invalid to put an active child under a parent that is @@ -793,7 +793,7 @@ int __pm_runtime_set_status(struct device *dev, unsigned int status) atomic_inc(&parent->power.child_count); } - spin_unlock_irq(&parent->power.lock); + spin_unlock(&parent->power.lock); if (error) goto out; diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c index 965ece2c7e4d..13bb69d2abb3 100644 --- a/drivers/block/aoe/aoecmd.c +++ b/drivers/block/aoe/aoecmd.c @@ -735,6 +735,21 @@ diskstats(struct gendisk *disk, struct bio *bio, ulong duration, sector_t sector part_stat_unlock(); } +/* + * Ensure we don't create aliases in VI caches + */ +static inline void +killalias(struct bio *bio) +{ + struct bio_vec *bv; + int i; + + if (bio_data_dir(bio) == READ) + __bio_for_each_segment(bv, bio, i, 0) { + flush_dcache_page(bv->bv_page); + } +} + void aoecmd_ata_rsp(struct sk_buff *skb) { @@ -853,8 +868,12 @@ aoecmd_ata_rsp(struct sk_buff *skb) if (buf && --buf->nframesout == 0 && buf->resid == 0) { diskstats(d->gd, buf->bio, jiffies - buf->stime, buf->sector); - n = (buf->flags & BUFFL_FAIL) ? -EIO : 0; - bio_endio(buf->bio, n); + if (buf->flags & BUFFL_FAIL) + bio_endio(buf->bio, -EIO); + else { + killalias(buf->bio); + bio_endio(buf->bio, 0); + } mempool_free(buf, d->bufpool); } diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c index 6399e5090df4..92b126394fa1 100644 --- a/drivers/block/cciss.c +++ b/drivers/block/cciss.c @@ -482,7 +482,7 @@ static ssize_t host_store_rescan(struct device *dev, return count; } -DEVICE_ATTR(rescan, S_IWUSR, NULL, host_store_rescan); +static DEVICE_ATTR(rescan, S_IWUSR, NULL, host_store_rescan); static ssize_t dev_show_unique_id(struct device *dev, struct device_attribute *attr, @@ -512,7 +512,7 @@ static ssize_t dev_show_unique_id(struct device *dev, sn[8], sn[9], sn[10], sn[11], sn[12], sn[13], sn[14], sn[15]); } -DEVICE_ATTR(unique_id, S_IRUGO, dev_show_unique_id, NULL); +static DEVICE_ATTR(unique_id, S_IRUGO, dev_show_unique_id, NULL); static ssize_t dev_show_vendor(struct device *dev, struct device_attribute *attr, @@ -536,7 +536,7 @@ static ssize_t dev_show_vendor(struct device *dev, else return snprintf(buf, sizeof(vendor) + 1, "%s\n", drv->vendor); } -DEVICE_ATTR(vendor, S_IRUGO, dev_show_vendor, NULL); +static DEVICE_ATTR(vendor, S_IRUGO, dev_show_vendor, NULL); static ssize_t dev_show_model(struct device *dev, struct device_attribute *attr, @@ -560,7 +560,7 @@ static ssize_t dev_show_model(struct device *dev, else return snprintf(buf, sizeof(model) + 1, "%s\n", drv->model); } -DEVICE_ATTR(model, S_IRUGO, dev_show_model, NULL); +static DEVICE_ATTR(model, S_IRUGO, dev_show_model, NULL); static ssize_t dev_show_rev(struct device *dev, struct device_attribute *attr, @@ -584,7 +584,7 @@ static ssize_t dev_show_rev(struct device *dev, else return snprintf(buf, sizeof(rev) + 1, "%s\n", drv->rev); } -DEVICE_ATTR(rev, S_IRUGO, dev_show_rev, NULL); +static DEVICE_ATTR(rev, S_IRUGO, dev_show_rev, NULL); static ssize_t cciss_show_lunid(struct device *dev, struct device_attribute *attr, char *buf) @@ -609,7 +609,7 @@ static ssize_t cciss_show_lunid(struct device *dev, lunid[0], lunid[1], lunid[2], lunid[3], lunid[4], lunid[5], lunid[6], lunid[7]); } -DEVICE_ATTR(lunid, S_IRUGO, cciss_show_lunid, NULL); +static DEVICE_ATTR(lunid, S_IRUGO, cciss_show_lunid, NULL); static ssize_t cciss_show_raid_level(struct device *dev, struct device_attribute *attr, char *buf) @@ -632,7 +632,7 @@ static ssize_t cciss_show_raid_level(struct device *dev, return snprintf(buf, strlen(raid_label[raid]) + 7, "RAID %s\n", raid_label[raid]); } -DEVICE_ATTR(raid_level, S_IRUGO, cciss_show_raid_level, NULL); +static DEVICE_ATTR(raid_level, S_IRUGO, cciss_show_raid_level, NULL); static ssize_t cciss_show_usage_count(struct device *dev, struct device_attribute *attr, char *buf) @@ -651,7 +651,7 @@ static ssize_t cciss_show_usage_count(struct device *dev, spin_unlock_irqrestore(CCISS_LOCK(h->ctlr), flags); return snprintf(buf, 20, "%d\n", count); } -DEVICE_ATTR(usage_count, S_IRUGO, cciss_show_usage_count, NULL); +static DEVICE_ATTR(usage_count, S_IRUGO, cciss_show_usage_count, NULL); static struct attribute *cciss_host_attrs[] = { &dev_attr_rescan.attr, diff --git a/drivers/bluetooth/bluecard_cs.c b/drivers/bluetooth/bluecard_cs.c index b0e569ba730d..2acdc605cb4b 100644 --- a/drivers/bluetooth/bluecard_cs.c +++ b/drivers/bluetooth/bluecard_cs.c @@ -867,11 +867,9 @@ static int bluecard_probe(struct pcmcia_device *link) link->io.Attributes1 = IO_DATA_PATH_WIDTH_8; link->io.NumPorts1 = 8; - link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING | IRQ_HANDLE_PRESENT; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; + link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; link->irq.Handler = bluecard_interrupt; - link->irq.Instance = info; link->conf.Attributes = CONF_ENABLE_IRQ; link->conf.IntType = INT_MEMORY_AND_IO; @@ -905,22 +903,16 @@ static int bluecard_config(struct pcmcia_device *link) break; } - if (i != 0) { - cs_error(link, RequestIO, i); + if (i != 0) goto failed; - } i = pcmcia_request_irq(link, &link->irq); - if (i != 0) { - cs_error(link, RequestIRQ, i); + if (i != 0) link->irq.AssignedIRQ = 0; - } i = pcmcia_request_configuration(link, &link->conf); - if (i != 0) { - cs_error(link, RequestConfiguration, i); + if (i != 0) goto failed; - } if (bluecard_open(info) != 0) goto failed; diff --git a/drivers/bluetooth/bt3c_cs.c b/drivers/bluetooth/bt3c_cs.c index d58e22b9f06a..d814a2755ccb 100644 --- a/drivers/bluetooth/bt3c_cs.c +++ b/drivers/bluetooth/bt3c_cs.c @@ -659,11 +659,9 @@ static int bt3c_probe(struct pcmcia_device *link) link->io.Attributes1 = IO_DATA_PATH_WIDTH_8; link->io.NumPorts1 = 8; - link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING | IRQ_HANDLE_PRESENT; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; + link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; link->irq.Handler = bt3c_interrupt; - link->irq.Instance = info; link->conf.Attributes = CONF_ENABLE_IRQ; link->conf.IntType = INT_MEMORY_AND_IO; @@ -740,21 +738,16 @@ static int bt3c_config(struct pcmcia_device *link) goto found_port; BT_ERR("No usable port range found"); - cs_error(link, RequestIO, -ENODEV); goto failed; found_port: i = pcmcia_request_irq(link, &link->irq); - if (i != 0) { - cs_error(link, RequestIRQ, i); + if (i != 0) link->irq.AssignedIRQ = 0; - } i = pcmcia_request_configuration(link, &link->conf); - if (i != 0) { - cs_error(link, RequestConfiguration, i); + if (i != 0) goto failed; - } if (bt3c_open(info) != 0) goto failed; diff --git a/drivers/bluetooth/btuart_cs.c b/drivers/bluetooth/btuart_cs.c index efd689a062eb..d339464dc15e 100644 --- a/drivers/bluetooth/btuart_cs.c +++ b/drivers/bluetooth/btuart_cs.c @@ -588,11 +588,9 @@ static int btuart_probe(struct pcmcia_device *link) link->io.Attributes1 = IO_DATA_PATH_WIDTH_8; link->io.NumPorts1 = 8; - link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING | IRQ_HANDLE_PRESENT; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; + link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; link->irq.Handler = btuart_interrupt; - link->irq.Instance = info; link->conf.Attributes = CONF_ENABLE_IRQ; link->conf.IntType = INT_MEMORY_AND_IO; @@ -669,21 +667,16 @@ static int btuart_config(struct pcmcia_device *link) goto found_port; BT_ERR("No usable port range found"); - cs_error(link, RequestIO, -ENODEV); goto failed; found_port: i = pcmcia_request_irq(link, &link->irq); - if (i != 0) { - cs_error(link, RequestIRQ, i); + if (i != 0) link->irq.AssignedIRQ = 0; - } i = pcmcia_request_configuration(link, &link->conf); - if (i != 0) { - cs_error(link, RequestConfiguration, i); + if (i != 0) goto failed; - } if (btuart_open(info) != 0) goto failed; diff --git a/drivers/bluetooth/dtl1_cs.c b/drivers/bluetooth/dtl1_cs.c index b881a9cd8741..4f02a6f3c980 100644 --- a/drivers/bluetooth/dtl1_cs.c +++ b/drivers/bluetooth/dtl1_cs.c @@ -573,11 +573,9 @@ static int dtl1_probe(struct pcmcia_device *link) link->io.Attributes1 = IO_DATA_PATH_WIDTH_8; link->io.NumPorts1 = 8; - link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING | IRQ_HANDLE_PRESENT; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; + link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; link->irq.Handler = dtl1_interrupt; - link->irq.Instance = info; link->conf.Attributes = CONF_ENABLE_IRQ; link->conf.IntType = INT_MEMORY_AND_IO; @@ -622,16 +620,12 @@ static int dtl1_config(struct pcmcia_device *link) goto failed; i = pcmcia_request_irq(link, &link->irq); - if (i != 0) { - cs_error(link, RequestIRQ, i); + if (i != 0) link->irq.AssignedIRQ = 0; - } i = pcmcia_request_configuration(link, &link->conf); - if (i != 0) { - cs_error(link, RequestConfiguration, i); + if (i != 0) goto failed; - } if (dtl1_open(info) != 0) goto failed; diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 614da5b8613a..e3749d0ba68b 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -3557,67 +3557,65 @@ static ctl_table cdrom_table[] = { .data = &cdrom_sysctl_settings.info, .maxlen = CDROM_STR_SIZE, .mode = 0444, - .proc_handler = &cdrom_sysctl_info, + .proc_handler = cdrom_sysctl_info, }, { .procname = "autoclose", .data = &cdrom_sysctl_settings.autoclose, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &cdrom_sysctl_handler, + .proc_handler = cdrom_sysctl_handler, }, { .procname = "autoeject", .data = &cdrom_sysctl_settings.autoeject, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &cdrom_sysctl_handler, + .proc_handler = cdrom_sysctl_handler, }, { .procname = "debug", .data = &cdrom_sysctl_settings.debug, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &cdrom_sysctl_handler, + .proc_handler = cdrom_sysctl_handler, }, { .procname = "lock", .data = &cdrom_sysctl_settings.lock, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &cdrom_sysctl_handler, + .proc_handler = cdrom_sysctl_handler, }, { .procname = "check_media", .data = &cdrom_sysctl_settings.check, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &cdrom_sysctl_handler + .proc_handler = cdrom_sysctl_handler }, - { .ctl_name = 0 } + { } }; static ctl_table cdrom_cdrom_table[] = { { - .ctl_name = DEV_CDROM, .procname = "cdrom", .maxlen = 0, .mode = 0555, .child = cdrom_table, }, - { .ctl_name = 0 } + { } }; /* Make sure that /proc/sys/dev is there */ static ctl_table cdrom_root_table[] = { { - .ctl_name = CTL_DEV, .procname = "dev", .maxlen = 0, .mode = 0555, .child = cdrom_cdrom_table, }, - { .ctl_name = 0 } + { } }; static struct ctl_table_header *cdrom_sysctl_header; diff --git a/drivers/char/agp/Kconfig b/drivers/char/agp/Kconfig index ccb1fa89de29..2fb3a480f6b0 100644 --- a/drivers/char/agp/Kconfig +++ b/drivers/char/agp/Kconfig @@ -56,9 +56,8 @@ config AGP_AMD X on AMD Irongate, 761, and 762 chipsets. config AGP_AMD64 - tristate "AMD Opteron/Athlon64 on-CPU GART support" if !GART_IOMMU + tristate "AMD Opteron/Athlon64 on-CPU GART support" depends on AGP && X86 - default y if GART_IOMMU help This option gives you AGP support for the GLX component of X using the on-CPU northbridge of the AMD Athlon64/Opteron CPUs. diff --git a/drivers/char/agp/intel-agp.c b/drivers/char/agp/intel-agp.c index 10e1f0390bbb..3cb56a049e24 100644 --- a/drivers/char/agp/intel-agp.c +++ b/drivers/char/agp/intel-agp.c @@ -62,6 +62,7 @@ #define PCI_DEVICE_ID_INTEL_IGDNG_D_IG 0x0042 #define PCI_DEVICE_ID_INTEL_IGDNG_M_HB 0x0044 #define PCI_DEVICE_ID_INTEL_IGDNG_MA_HB 0x0062 +#define PCI_DEVICE_ID_INTEL_IGDNG_MC2_HB 0x006a #define PCI_DEVICE_ID_INTEL_IGDNG_M_IG 0x0046 /* cover 915 and 945 variants */ @@ -96,7 +97,8 @@ agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_B43_HB || \ agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_IGDNG_D_HB || \ agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_IGDNG_M_HB || \ - agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_IGDNG_MA_HB) + agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_IGDNG_MA_HB || \ + agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_IGDNG_MC2_HB) extern int agp_memory_reserved; @@ -1358,6 +1360,7 @@ static void intel_i965_get_gtt_range(int *gtt_offset, int *gtt_size) case PCI_DEVICE_ID_INTEL_IGDNG_D_HB: case PCI_DEVICE_ID_INTEL_IGDNG_M_HB: case PCI_DEVICE_ID_INTEL_IGDNG_MA_HB: + case PCI_DEVICE_ID_INTEL_IGDNG_MC2_HB: *gtt_offset = *gtt_size = MB(2); break; default: @@ -2359,6 +2362,8 @@ static const struct intel_driver_description { "IGDNG/M", NULL, &intel_i965_driver }, { PCI_DEVICE_ID_INTEL_IGDNG_MA_HB, PCI_DEVICE_ID_INTEL_IGDNG_M_IG, 0, "IGDNG/MA", NULL, &intel_i965_driver }, + { PCI_DEVICE_ID_INTEL_IGDNG_MC2_HB, PCI_DEVICE_ID_INTEL_IGDNG_M_IG, 0, + "IGDNG/MC2", NULL, &intel_i965_driver }, { 0, 0, 0, NULL, NULL, NULL } }; @@ -2560,6 +2565,7 @@ static struct pci_device_id agp_intel_pci_table[] = { ID(PCI_DEVICE_ID_INTEL_IGDNG_D_HB), ID(PCI_DEVICE_ID_INTEL_IGDNG_M_HB), ID(PCI_DEVICE_ID_INTEL_IGDNG_MA_HB), + ID(PCI_DEVICE_ID_INTEL_IGDNG_MC2_HB), { } }; diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c index 70a770ac0138..e481c5938bad 100644 --- a/drivers/char/hpet.c +++ b/drivers/char/hpet.c @@ -675,36 +675,33 @@ static int hpet_is_known(struct hpet_data *hdp) static ctl_table hpet_table[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "max-user-freq", .data = &hpet_max_freq, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, - {.ctl_name = 0} + {} }; static ctl_table hpet_root[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "hpet", .maxlen = 0, .mode = 0555, .child = hpet_table, }, - {.ctl_name = 0} + {} }; static ctl_table dev_root[] = { { - .ctl_name = CTL_DEV, .procname = "dev", .maxlen = 0, .mode = 0555, .child = hpet_root, }, - {.ctl_name = 0} + {} }; static struct ctl_table_header *sysctl_header; diff --git a/drivers/char/ipmi/ipmi_poweroff.c b/drivers/char/ipmi/ipmi_poweroff.c index 2e66b5f773dd..0dec5da000ef 100644 --- a/drivers/char/ipmi/ipmi_poweroff.c +++ b/drivers/char/ipmi/ipmi_poweroff.c @@ -660,26 +660,23 @@ static struct ipmi_smi_watcher smi_watcher = { #include <linux/sysctl.h> static ctl_table ipmi_table[] = { - { .ctl_name = DEV_IPMI_POWEROFF_POWERCYCLE, - .procname = "poweroff_powercycle", + { .procname = "poweroff_powercycle", .data = &poweroff_powercycle, .maxlen = sizeof(poweroff_powercycle), .mode = 0644, - .proc_handler = &proc_dointvec }, + .proc_handler = proc_dointvec }, { } }; static ctl_table ipmi_dir_table[] = { - { .ctl_name = DEV_IPMI, - .procname = "ipmi", + { .procname = "ipmi", .mode = 0555, .child = ipmi_table }, { } }; static ctl_table ipmi_root_table[] = { - { .ctl_name = CTL_DEV, - .procname = "dev", + { .procname = "dev", .mode = 0555, .child = ipmi_dir_table }, { } diff --git a/drivers/char/keyboard.c b/drivers/char/keyboard.c index 737be953cc58..950837cf9e9c 100644 --- a/drivers/char/keyboard.c +++ b/drivers/char/keyboard.c @@ -1249,7 +1249,7 @@ static void kbd_keycode(unsigned int keycode, int down, int hw_raw) if (keycode >= NR_KEYS) if (keycode >= KEY_BRL_DOT1 && keycode <= KEY_BRL_DOT8) - keysym = K(KT_BRL, keycode - KEY_BRL_DOT1 + 1); + keysym = U(K(KT_BRL, keycode - KEY_BRL_DOT1 + 1)); else return; else diff --git a/drivers/char/pcmcia/cm4000_cs.c b/drivers/char/pcmcia/cm4000_cs.c index c250a31efa53..2db4c0a29b05 100644 --- a/drivers/char/pcmcia/cm4000_cs.c +++ b/drivers/char/pcmcia/cm4000_cs.c @@ -23,8 +23,6 @@ * All rights reserved. Licensed under dual BSD/GPL license. */ -/* #define PCMCIA_DEBUG 6 */ - #include <linux/kernel.h> #include <linux/module.h> #include <linux/slab.h> @@ -47,18 +45,17 @@ /* #define ATR_CSUM */ -#ifdef PCMCIA_DEBUG -#define reader_to_dev(x) (&handle_to_dev(x->p_dev)) -static int pc_debug = PCMCIA_DEBUG; -module_param(pc_debug, int, 0600); -#define DEBUGP(n, rdr, x, args...) do { \ - if (pc_debug >= (n)) \ - dev_printk(KERN_DEBUG, reader_to_dev(rdr), "%s:" x, \ - __func__ , ## args); \ +#define reader_to_dev(x) (&x->p_dev->dev) + +/* n (debug level) is ignored */ +/* additional debug output may be enabled by re-compiling with + * CM4000_DEBUG set */ +/* #define CM4000_DEBUG */ +#define DEBUGP(n, rdr, x, args...) do { \ + dev_dbg(reader_to_dev(rdr), "%s:" x, \ + __func__ , ## args); \ } while (0) -#else -#define DEBUGP(n, rdr, x, args...) -#endif + static char *version = "cm4000_cs.c v2.4.0gm6 - All bugs added by Harald Welte"; #define T_1SEC (HZ) @@ -174,14 +171,13 @@ static unsigned char fi_di_table[10][14] = { /* 9 */ {0x09,0x19,0x29,0x39,0x49,0x59,0x69,0x11,0x11,0x99,0xA9,0xB9,0xC9,0xD9} }; -#ifndef PCMCIA_DEBUG +#ifndef CM4000_DEBUG #define xoutb outb #define xinb inb #else static inline void xoutb(unsigned char val, unsigned short port) { - if (pc_debug >= 7) - printk(KERN_DEBUG "outb(val=%.2x,port=%.4x)\n", val, port); + pr_debug("outb(val=%.2x,port=%.4x)\n", val, port); outb(val, port); } static inline unsigned char xinb(unsigned short port) @@ -189,8 +185,7 @@ static inline unsigned char xinb(unsigned short port) unsigned char val; val = inb(port); - if (pc_debug >= 7) - printk(KERN_DEBUG "%.2x=inb(%.4x)\n", val, port); + pr_debug("%.2x=inb(%.4x)\n", val, port); return val; } @@ -514,12 +509,10 @@ static int set_protocol(struct cm4000_dev *dev, struct ptsreq *ptsreq) for (i = 0; i < 4; i++) { xoutb(i, REG_BUF_ADDR(iobase)); xoutb(dev->pts[i], REG_BUF_DATA(iobase)); /* buf data */ -#ifdef PCMCIA_DEBUG - if (pc_debug >= 5) - printk("0x%.2x ", dev->pts[i]); +#ifdef CM4000_DEBUG + pr_debug("0x%.2x ", dev->pts[i]); } - if (pc_debug >= 5) - printk("\n"); + pr_debug("\n"); #else } #endif @@ -579,14 +572,13 @@ static int set_protocol(struct cm4000_dev *dev, struct ptsreq *ptsreq) pts_reply[i] = inb(REG_BUF_DATA(iobase)); } -#ifdef PCMCIA_DEBUG +#ifdef CM4000_DEBUG DEBUGP(2, dev, "PTSreply: "); for (i = 0; i < num_bytes_read; i++) { - if (pc_debug >= 5) - printk("0x%.2x ", pts_reply[i]); + pr_debug("0x%.2x ", pts_reply[i]); } - printk("\n"); -#endif /* PCMCIA_DEBUG */ + pr_debug("\n"); +#endif /* CM4000_DEBUG */ DEBUGP(5, dev, "Clear Tactive in Flags1\n"); xoutb(0x20, REG_FLAGS1(iobase)); @@ -655,7 +647,7 @@ static void terminate_monitor(struct cm4000_dev *dev) DEBUGP(5, dev, "Delete timer\n"); del_timer_sync(&dev->timer); -#ifdef PCMCIA_DEBUG +#ifdef CM4000_DEBUG dev->monitor_running = 0; #endif @@ -898,7 +890,7 @@ static void monitor_card(unsigned long p) DEBUGP(4, dev, "ATR checksum (0x%.2x, should " "be zero) failed\n", dev->atr_csum); } -#ifdef PCMCIA_DEBUG +#ifdef CM4000_DEBUG else if (test_bit(IS_BAD_LENGTH, &dev->flags)) { DEBUGP(4, dev, "ATR length error\n"); } else { @@ -1415,7 +1407,7 @@ static long cmm_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) int size; int rc; void __user *argp = (void __user *)arg; -#ifdef PCMCIA_DEBUG +#ifdef CM4000_DEBUG char *ioctl_names[CM_IOC_MAXNR + 1] = { [_IOC_NR(CM_IOCGSTATUS)] "CM_IOCGSTATUS", [_IOC_NR(CM_IOCGATR)] "CM_IOCGATR", @@ -1423,9 +1415,9 @@ static long cmm_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) [_IOC_NR(CM_IOCSPTS)] "CM_IOCSPTS", [_IOC_NR(CM_IOSDBGLVL)] "CM4000_DBGLVL", }; -#endif DEBUGP(3, dev, "cmm_ioctl(device=%d.%d) %s\n", imajor(inode), iminor(inode), ioctl_names[_IOC_NR(cmd)]); +#endif lock_kernel(); rc = -ENODEV; @@ -1523,7 +1515,7 @@ static long cmm_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) } case CM_IOCARDOFF: -#ifdef PCMCIA_DEBUG +#ifdef CM4000_DEBUG DEBUGP(4, dev, "... in CM_IOCARDOFF\n"); if (dev->flags0 & 0x01) { DEBUGP(4, dev, " Card inserted\n"); @@ -1625,18 +1617,9 @@ static long cmm_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) } break; -#ifdef PCMCIA_DEBUG - case CM_IOSDBGLVL: /* set debug log level */ - { - int old_pc_debug = 0; - - old_pc_debug = pc_debug; - if (copy_from_user(&pc_debug, argp, sizeof(int))) - rc = -EFAULT; - else if (old_pc_debug != pc_debug) - DEBUGP(0, dev, "Changed debug log level " - "to %i\n", pc_debug); - } +#ifdef CM4000_DEBUG + case CM_IOSDBGLVL: + rc = -ENOTTY; break; #endif default: diff --git a/drivers/char/pcmcia/cm4040_cs.c b/drivers/char/pcmcia/cm4040_cs.c index 4f0723b07974..a6a70e476bea 100644 --- a/drivers/char/pcmcia/cm4040_cs.c +++ b/drivers/char/pcmcia/cm4040_cs.c @@ -17,8 +17,6 @@ * All rights reserved, Dual BSD/GPL Licensed. */ -/* #define PCMCIA_DEBUG 6 */ - #include <linux/kernel.h> #include <linux/module.h> #include <linux/slab.h> @@ -41,18 +39,16 @@ #include "cm4040_cs.h" -#ifdef PCMCIA_DEBUG -#define reader_to_dev(x) (&handle_to_dev(x->p_dev)) -static int pc_debug = PCMCIA_DEBUG; -module_param(pc_debug, int, 0600); -#define DEBUGP(n, rdr, x, args...) do { \ - if (pc_debug >= (n)) \ - dev_printk(KERN_DEBUG, reader_to_dev(rdr), "%s:" x, \ - __func__ , ##args); \ +#define reader_to_dev(x) (&x->p_dev->dev) + +/* n (debug level) is ignored */ +/* additional debug output may be enabled by re-compiling with + * CM4040_DEBUG set */ +/* #define CM4040_DEBUG */ +#define DEBUGP(n, rdr, x, args...) do { \ + dev_dbg(reader_to_dev(rdr), "%s:" x, \ + __func__ , ## args); \ } while (0) -#else -#define DEBUGP(n, rdr, x, args...) -#endif static char *version = "OMNIKEY CardMan 4040 v1.1.0gm5 - All bugs added by Harald Welte"; @@ -90,14 +86,13 @@ struct reader_dev { static struct pcmcia_device *dev_table[CM_MAX_DEV]; -#ifndef PCMCIA_DEBUG +#ifndef CM4040_DEBUG #define xoutb outb #define xinb inb #else static inline void xoutb(unsigned char val, unsigned short port) { - if (pc_debug >= 7) - printk(KERN_DEBUG "outb(val=%.2x,port=%.4x)\n", val, port); + pr_debug("outb(val=%.2x,port=%.4x)\n", val, port); outb(val, port); } @@ -106,8 +101,7 @@ static inline unsigned char xinb(unsigned short port) unsigned char val; val = inb(port); - if (pc_debug >= 7) - printk(KERN_DEBUG "%.2x=inb(%.4x)\n", val, port); + pr_debug("%.2x=inb(%.4x)\n", val, port); return val; } #endif @@ -260,23 +254,22 @@ static ssize_t cm4040_read(struct file *filp, char __user *buf, return -EIO; } dev->r_buf[i] = xinb(iobase + REG_OFFSET_BULK_IN); -#ifdef PCMCIA_DEBUG - if (pc_debug >= 6) - printk(KERN_DEBUG "%lu:%2x ", i, dev->r_buf[i]); +#ifdef CM4040_DEBUG + pr_debug("%lu:%2x ", i, dev->r_buf[i]); } - printk("\n"); + pr_debug("\n"); #else } #endif bytes_to_read = 5 + le32_to_cpu(*(__le32 *)&dev->r_buf[1]); - DEBUGP(6, dev, "BytesToRead=%lu\n", bytes_to_read); + DEBUGP(6, dev, "BytesToRead=%zu\n", bytes_to_read); min_bytes_to_read = min(count, bytes_to_read + 5); min_bytes_to_read = min_t(size_t, min_bytes_to_read, READ_WRITE_BUFFER_SIZE); - DEBUGP(6, dev, "Min=%lu\n", min_bytes_to_read); + DEBUGP(6, dev, "Min=%zu\n", min_bytes_to_read); for (i = 0; i < (min_bytes_to_read-5); i++) { rc = wait_for_bulk_in_ready(dev); @@ -288,11 +281,10 @@ static ssize_t cm4040_read(struct file *filp, char __user *buf, return -EIO; } dev->r_buf[i+5] = xinb(iobase + REG_OFFSET_BULK_IN); -#ifdef PCMCIA_DEBUG - if (pc_debug >= 6) - printk(KERN_DEBUG "%lu:%2x ", i, dev->r_buf[i]); +#ifdef CM4040_DEBUG + pr_debug("%lu:%2x ", i, dev->r_buf[i]); } - printk("\n"); + pr_debug("\n"); #else } #endif @@ -547,7 +539,7 @@ static int cm4040_config_check(struct pcmcia_device *p_dev, p_dev->io.IOAddrLines = cfg->io.flags & CISTPL_IO_LINES_MASK; rc = pcmcia_request_io(p_dev, &p_dev->io); - dev_printk(KERN_INFO, &handle_to_dev(p_dev), + dev_printk(KERN_INFO, &p_dev->dev, "pcmcia_request_io returned 0x%x\n", rc); return rc; } @@ -569,7 +561,7 @@ static int reader_config(struct pcmcia_device *link, int devno) fail_rc = pcmcia_request_configuration(link, &link->conf); if (fail_rc != 0) { - dev_printk(KERN_INFO, &handle_to_dev(link), + dev_printk(KERN_INFO, &link->dev, "pcmcia_request_configuration failed 0x%x\n", fail_rc); goto cs_release; diff --git a/drivers/char/pcmcia/ipwireless/hardware.c b/drivers/char/pcmcia/ipwireless/hardware.c index 4c1820cad712..99cffdab1056 100644 --- a/drivers/char/pcmcia/ipwireless/hardware.c +++ b/drivers/char/pcmcia/ipwireless/hardware.c @@ -1213,12 +1213,12 @@ static irqreturn_t ipwireless_handle_v2_v3_interrupt(int irq, irqreturn_t ipwireless_interrupt(int irq, void *dev_id) { - struct ipw_hardware *hw = dev_id; + struct ipw_dev *ipw = dev_id; - if (hw->hw_version == HW_VERSION_1) - return ipwireless_handle_v1_interrupt(irq, hw); + if (ipw->hardware->hw_version == HW_VERSION_1) + return ipwireless_handle_v1_interrupt(irq, ipw->hardware); else - return ipwireless_handle_v2_v3_interrupt(irq, hw); + return ipwireless_handle_v2_v3_interrupt(irq, ipw->hardware); } static void flush_packets_to_hw(struct ipw_hardware *hw) diff --git a/drivers/char/pcmcia/ipwireless/main.c b/drivers/char/pcmcia/ipwireless/main.c index 5216fce0c62d..dff24dae1485 100644 --- a/drivers/char/pcmcia/ipwireless/main.c +++ b/drivers/char/pcmcia/ipwireless/main.c @@ -65,10 +65,7 @@ static void signalled_reboot_work(struct work_struct *work_reboot) struct ipw_dev *ipw = container_of(work_reboot, struct ipw_dev, work_reboot); struct pcmcia_device *link = ipw->link; - int ret = pcmcia_reset_card(link->socket); - - if (ret != 0) - cs_error(link, ResetCard, ret); + pcmcia_reset_card(link->socket); } static void signalled_reboot_callback(void *callback_data) @@ -79,208 +76,127 @@ static void signalled_reboot_callback(void *callback_data) schedule_work(&ipw->work_reboot); } -static int config_ipwireless(struct ipw_dev *ipw) +static int ipwireless_probe(struct pcmcia_device *p_dev, + cistpl_cftable_entry_t *cfg, + cistpl_cftable_entry_t *dflt, + unsigned int vcc, + void *priv_data) { - struct pcmcia_device *link = ipw->link; - int ret; - tuple_t tuple; - unsigned short buf[64]; - cisparse_t parse; - unsigned short cor_value; + struct ipw_dev *ipw = priv_data; + struct resource *io_resource; memreq_t memreq_attr_memory; memreq_t memreq_common_memory; + int ret; - ipw->is_v2_card = 0; - - tuple.Attributes = 0; - tuple.TupleData = (cisdata_t *) buf; - tuple.TupleDataMax = sizeof(buf); - tuple.TupleOffset = 0; - - tuple.DesiredTuple = RETURN_FIRST_TUPLE; - - ret = pcmcia_get_first_tuple(link, &tuple); - - while (ret == 0) { - ret = pcmcia_get_tuple_data(link, &tuple); - - if (ret != 0) { - cs_error(link, GetTupleData, ret); - goto exit0; - } - ret = pcmcia_get_next_tuple(link, &tuple); - } - - tuple.DesiredTuple = CISTPL_CFTABLE_ENTRY; - - ret = pcmcia_get_first_tuple(link, &tuple); - - if (ret != 0) { - cs_error(link, GetFirstTuple, ret); - goto exit0; - } - - ret = pcmcia_get_tuple_data(link, &tuple); - - if (ret != 0) { - cs_error(link, GetTupleData, ret); - goto exit0; - } - - ret = pcmcia_parse_tuple(&tuple, &parse); - - if (ret != 0) { - cs_error(link, ParseTuple, ret); - goto exit0; - } - - link->io.Attributes1 = IO_DATA_PATH_WIDTH_AUTO; - link->io.BasePort1 = parse.cftable_entry.io.win[0].base; - link->io.NumPorts1 = parse.cftable_entry.io.win[0].len; - link->io.IOAddrLines = 16; - - link->irq.IRQInfo1 = parse.cftable_entry.irq.IRQInfo1; + p_dev->io.Attributes1 = IO_DATA_PATH_WIDTH_AUTO; + p_dev->io.BasePort1 = cfg->io.win[0].base; + p_dev->io.NumPorts1 = cfg->io.win[0].len; + p_dev->io.IOAddrLines = 16; /* 0x40 causes it to generate level mode interrupts. */ /* 0x04 enables IREQ pin. */ - cor_value = parse.cftable_entry.index | 0x44; - link->conf.ConfigIndex = cor_value; + p_dev->conf.ConfigIndex = cfg->index | 0x44; + ret = pcmcia_request_io(p_dev, &p_dev->io); + if (ret) + return ret; - /* IRQ and I/O settings */ - tuple.DesiredTuple = CISTPL_CONFIG; + io_resource = request_region(p_dev->io.BasePort1, p_dev->io.NumPorts1, + IPWIRELESS_PCCARD_NAME); - ret = pcmcia_get_first_tuple(link, &tuple); + if (cfg->mem.nwin == 0) + return 0; - if (ret != 0) { - cs_error(link, GetFirstTuple, ret); - goto exit0; - } + ipw->request_common_memory.Attributes = + WIN_DATA_WIDTH_16 | WIN_MEMORY_TYPE_CM | WIN_ENABLE; + ipw->request_common_memory.Base = cfg->mem.win[0].host_addr; + ipw->request_common_memory.Size = cfg->mem.win[0].len; + if (ipw->request_common_memory.Size < 0x1000) + ipw->request_common_memory.Size = 0x1000; + ipw->request_common_memory.AccessSpeed = 0; - ret = pcmcia_get_tuple_data(link, &tuple); - - if (ret != 0) { - cs_error(link, GetTupleData, ret); - goto exit0; - } + ret = pcmcia_request_window(p_dev, &ipw->request_common_memory, + &ipw->handle_common_memory); - ret = pcmcia_parse_tuple(&tuple, &parse); + if (ret != 0) + goto exit1; - if (ret != 0) { - cs_error(link, GetTupleData, ret); - goto exit0; - } - link->conf.Attributes = CONF_ENABLE_IRQ; - link->conf.ConfigBase = parse.config.base; - link->conf.Present = parse.config.rmask[0]; - link->conf.IntType = INT_MEMORY_AND_IO; + memreq_common_memory.CardOffset = cfg->mem.win[0].card_addr; + memreq_common_memory.Page = 0; - link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING | IRQ_HANDLE_PRESENT; - link->irq.Handler = ipwireless_interrupt; - link->irq.Instance = ipw->hardware; + ret = pcmcia_map_mem_page(p_dev, ipw->handle_common_memory, + &memreq_common_memory); - ret = pcmcia_request_io(link, &link->io); + if (ret != 0) + goto exit2; - if (ret != 0) { - cs_error(link, RequestIO, ret); - goto exit0; - } + ipw->is_v2_card = cfg->mem.win[0].len == 0x100; - request_region(link->io.BasePort1, link->io.NumPorts1, + ipw->common_memory = ioremap(ipw->request_common_memory.Base, + ipw->request_common_memory.Size); + request_mem_region(ipw->request_common_memory.Base, + ipw->request_common_memory.Size, IPWIRELESS_PCCARD_NAME); - /* memory settings */ - - tuple.DesiredTuple = CISTPL_CFTABLE_ENTRY; - - ret = pcmcia_get_first_tuple(link, &tuple); - - if (ret != 0) { - cs_error(link, GetFirstTuple, ret); - goto exit1; - } - - ret = pcmcia_get_tuple_data(link, &tuple); + ipw->request_attr_memory.Attributes = + WIN_DATA_WIDTH_16 | WIN_MEMORY_TYPE_AM | WIN_ENABLE; + ipw->request_attr_memory.Base = 0; + ipw->request_attr_memory.Size = 0; /* this used to be 0x1000 */ + ipw->request_attr_memory.AccessSpeed = 0; - if (ret != 0) { - cs_error(link, GetTupleData, ret); - goto exit1; - } - - ret = pcmcia_parse_tuple(&tuple, &parse); - - if (ret != 0) { - cs_error(link, ParseTuple, ret); - goto exit1; - } + ret = pcmcia_request_window(p_dev, &ipw->request_attr_memory, + &ipw->handle_attr_memory); - if (parse.cftable_entry.mem.nwin > 0) { - ipw->request_common_memory.Attributes = - WIN_DATA_WIDTH_16 | WIN_MEMORY_TYPE_CM | WIN_ENABLE; - ipw->request_common_memory.Base = - parse.cftable_entry.mem.win[0].host_addr; - ipw->request_common_memory.Size = parse.cftable_entry.mem.win[0].len; - if (ipw->request_common_memory.Size < 0x1000) - ipw->request_common_memory.Size = 0x1000; - ipw->request_common_memory.AccessSpeed = 0; - - ret = pcmcia_request_window(&link, &ipw->request_common_memory, - &ipw->handle_common_memory); + if (ret != 0) + goto exit2; - if (ret != 0) { - cs_error(link, RequestWindow, ret); - goto exit1; - } + memreq_attr_memory.CardOffset = 0; + memreq_attr_memory.Page = 0; - memreq_common_memory.CardOffset = - parse.cftable_entry.mem.win[0].card_addr; - memreq_common_memory.Page = 0; + ret = pcmcia_map_mem_page(p_dev, ipw->handle_attr_memory, + &memreq_attr_memory); - ret = pcmcia_map_mem_page(ipw->handle_common_memory, - &memreq_common_memory); + if (ret != 0) + goto exit3; - if (ret != 0) { - cs_error(link, MapMemPage, ret); - goto exit1; - } + ipw->attr_memory = ioremap(ipw->request_attr_memory.Base, + ipw->request_attr_memory.Size); + request_mem_region(ipw->request_attr_memory.Base, + ipw->request_attr_memory.Size, IPWIRELESS_PCCARD_NAME); - ipw->is_v2_card = - parse.cftable_entry.mem.win[0].len == 0x100; + return 0; - ipw->common_memory = ioremap(ipw->request_common_memory.Base, +exit3: + pcmcia_release_window(p_dev, ipw->handle_attr_memory); +exit2: + if (ipw->common_memory) { + release_mem_region(ipw->request_common_memory.Base, ipw->request_common_memory.Size); - request_mem_region(ipw->request_common_memory.Base, - ipw->request_common_memory.Size, IPWIRELESS_PCCARD_NAME); - - ipw->request_attr_memory.Attributes = - WIN_DATA_WIDTH_16 | WIN_MEMORY_TYPE_AM | WIN_ENABLE; - ipw->request_attr_memory.Base = 0; - ipw->request_attr_memory.Size = 0; /* this used to be 0x1000 */ - ipw->request_attr_memory.AccessSpeed = 0; - - ret = pcmcia_request_window(&link, &ipw->request_attr_memory, - &ipw->handle_attr_memory); + iounmap(ipw->common_memory); + pcmcia_release_window(p_dev, ipw->handle_common_memory); + } else + pcmcia_release_window(p_dev, ipw->handle_common_memory); +exit1: + release_resource(io_resource); + pcmcia_disable_device(p_dev); + return -1; +} - if (ret != 0) { - cs_error(link, RequestWindow, ret); - goto exit2; - } +static int config_ipwireless(struct ipw_dev *ipw) +{ + struct pcmcia_device *link = ipw->link; + int ret = 0; - memreq_attr_memory.CardOffset = 0; - memreq_attr_memory.Page = 0; + ipw->is_v2_card = 0; - ret = pcmcia_map_mem_page(ipw->handle_attr_memory, - &memreq_attr_memory); + ret = pcmcia_loop_config(link, ipwireless_probe, ipw); + if (ret != 0) + return ret; - if (ret != 0) { - cs_error(link, MapMemPage, ret); - goto exit2; - } + link->conf.Attributes = CONF_ENABLE_IRQ; + link->conf.IntType = INT_MEMORY_AND_IO; - ipw->attr_memory = ioremap(ipw->request_attr_memory.Base, - ipw->request_attr_memory.Size); - request_mem_region(ipw->request_attr_memory.Base, ipw->request_attr_memory.Size, - IPWIRELESS_PCCARD_NAME); - } + link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; + link->irq.Handler = ipwireless_interrupt; INIT_WORK(&ipw->work_reboot, signalled_reboot_work); @@ -291,10 +207,8 @@ static int config_ipwireless(struct ipw_dev *ipw) ret = pcmcia_request_irq(link, &link->irq); - if (ret != 0) { - cs_error(link, RequestIRQ, ret); - goto exit3; - } + if (ret != 0) + goto exit; printk(KERN_INFO IPWIRELESS_PCCARD_NAME ": Card type %s\n", ipw->is_v2_card ? "V2/V3" : "V1"); @@ -316,12 +230,12 @@ static int config_ipwireless(struct ipw_dev *ipw) ipw->network = ipwireless_network_create(ipw->hardware); if (!ipw->network) - goto exit3; + goto exit; ipw->tty = ipwireless_tty_create(ipw->hardware, ipw->network, ipw->nodes); if (!ipw->tty) - goto exit3; + goto exit; ipwireless_init_hardware_v2_v3(ipw->hardware); @@ -331,35 +245,27 @@ static int config_ipwireless(struct ipw_dev *ipw) */ ret = pcmcia_request_configuration(link, &link->conf); - if (ret != 0) { - cs_error(link, RequestConfiguration, ret); - goto exit4; - } + if (ret != 0) + goto exit; link->dev_node = &ipw->nodes[0]; return 0; -exit4: - pcmcia_disable_device(link); -exit3: +exit: if (ipw->attr_memory) { release_mem_region(ipw->request_attr_memory.Base, ipw->request_attr_memory.Size); iounmap(ipw->attr_memory); - pcmcia_release_window(ipw->handle_attr_memory); - pcmcia_disable_device(link); + pcmcia_release_window(link, ipw->handle_attr_memory); } -exit2: if (ipw->common_memory) { release_mem_region(ipw->request_common_memory.Base, ipw->request_common_memory.Size); iounmap(ipw->common_memory); - pcmcia_release_window(ipw->handle_common_memory); + pcmcia_release_window(link, ipw->handle_common_memory); } -exit1: pcmcia_disable_device(link); -exit0: return -1; } @@ -378,9 +284,9 @@ static void release_ipwireless(struct ipw_dev *ipw) iounmap(ipw->attr_memory); } if (ipw->common_memory) - pcmcia_release_window(ipw->handle_common_memory); + pcmcia_release_window(ipw->link, ipw->handle_common_memory); if (ipw->attr_memory) - pcmcia_release_window(ipw->handle_attr_memory); + pcmcia_release_window(ipw->link, ipw->handle_attr_memory); /* Break the link with Card Services */ pcmcia_disable_device(ipw->link); @@ -406,7 +312,6 @@ static int ipwireless_attach(struct pcmcia_device *link) ipw->link = link; link->priv = ipw; - link->irq.Instance = ipw; /* Link this device into our device list. */ link->dev_node = &ipw->nodes[0]; @@ -421,7 +326,6 @@ static int ipwireless_attach(struct pcmcia_device *link) ret = config_ipwireless(ipw); if (ret != 0) { - cs_error(link, RegisterClient, ret); ipwireless_detach(link); return ret; } diff --git a/drivers/char/pcmcia/synclink_cs.c b/drivers/char/pcmcia/synclink_cs.c index caf6e4d19469..c31a0d913d37 100644 --- a/drivers/char/pcmcia/synclink_cs.c +++ b/drivers/char/pcmcia/synclink_cs.c @@ -554,7 +554,6 @@ static int mgslpc_probe(struct pcmcia_device *link) /* Interrupt setup */ link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; link->irq.Handler = NULL; link->conf.Attributes = 0; @@ -572,69 +571,51 @@ static int mgslpc_probe(struct pcmcia_device *link) /* Card has been inserted. */ -#define CS_CHECK(fn, ret) \ -do { last_fn = (fn); if ((last_ret = (ret)) != 0) goto cs_failed; } while (0) +static int mgslpc_ioprobe(struct pcmcia_device *p_dev, + cistpl_cftable_entry_t *cfg, + cistpl_cftable_entry_t *dflt, + unsigned int vcc, + void *priv_data) +{ + if (cfg->io.nwin > 0) { + p_dev->io.Attributes1 = IO_DATA_PATH_WIDTH_AUTO; + if (!(cfg->io.flags & CISTPL_IO_8BIT)) + p_dev->io.Attributes1 = IO_DATA_PATH_WIDTH_16; + if (!(cfg->io.flags & CISTPL_IO_16BIT)) + p_dev->io.Attributes1 = IO_DATA_PATH_WIDTH_8; + p_dev->io.IOAddrLines = cfg->io.flags & CISTPL_IO_LINES_MASK; + p_dev->io.BasePort1 = cfg->io.win[0].base; + p_dev->io.NumPorts1 = cfg->io.win[0].len; + return pcmcia_request_io(p_dev, &p_dev->io); + } + return -ENODEV; +} static int mgslpc_config(struct pcmcia_device *link) { MGSLPC_INFO *info = link->priv; - tuple_t tuple; - cisparse_t parse; - int last_fn, last_ret; - u_char buf[64]; - cistpl_cftable_entry_t dflt = { 0 }; - cistpl_cftable_entry_t *cfg; + int ret; if (debug_level >= DEBUG_LEVEL_INFO) printk("mgslpc_config(0x%p)\n", link); - tuple.Attributes = 0; - tuple.TupleData = buf; - tuple.TupleDataMax = sizeof(buf); - tuple.TupleOffset = 0; - - /* get CIS configuration entry */ - - tuple.DesiredTuple = CISTPL_CFTABLE_ENTRY; - CS_CHECK(GetFirstTuple, pcmcia_get_first_tuple(link, &tuple)); - - cfg = &(parse.cftable_entry); - CS_CHECK(GetTupleData, pcmcia_get_tuple_data(link, &tuple)); - CS_CHECK(ParseTuple, pcmcia_parse_tuple(&tuple, &parse)); - - if (cfg->flags & CISTPL_CFTABLE_DEFAULT) dflt = *cfg; - if (cfg->index == 0) - goto cs_failed; - - link->conf.ConfigIndex = cfg->index; - link->conf.Attributes |= CONF_ENABLE_IRQ; - - /* IO window settings */ - link->io.NumPorts1 = 0; - if ((cfg->io.nwin > 0) || (dflt.io.nwin > 0)) { - cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt.io; - link->io.Attributes1 = IO_DATA_PATH_WIDTH_AUTO; - if (!(io->flags & CISTPL_IO_8BIT)) - link->io.Attributes1 = IO_DATA_PATH_WIDTH_16; - if (!(io->flags & CISTPL_IO_16BIT)) - link->io.Attributes1 = IO_DATA_PATH_WIDTH_8; - link->io.IOAddrLines = io->flags & CISTPL_IO_LINES_MASK; - link->io.BasePort1 = io->win[0].base; - link->io.NumPorts1 = io->win[0].len; - CS_CHECK(RequestIO, pcmcia_request_io(link, &link->io)); - } + ret = pcmcia_loop_config(link, mgslpc_ioprobe, NULL); + if (ret != 0) + goto failed; link->conf.Attributes = CONF_ENABLE_IRQ; link->conf.IntType = INT_MEMORY_AND_IO; link->conf.ConfigIndex = 8; link->conf.Present = PRESENT_OPTION; - link->irq.Attributes |= IRQ_HANDLE_PRESENT; link->irq.Handler = mgslpc_isr; - link->irq.Instance = info; - CS_CHECK(RequestIRQ, pcmcia_request_irq(link, &link->irq)); - CS_CHECK(RequestConfiguration, pcmcia_request_configuration(link, &link->conf)); + ret = pcmcia_request_irq(link, &link->irq); + if (ret) + goto failed; + ret = pcmcia_request_configuration(link, &link->conf); + if (ret) + goto failed; info->io_base = link->io.BasePort1; info->irq_level = link->irq.AssignedIRQ; @@ -654,8 +635,7 @@ static int mgslpc_config(struct pcmcia_device *link) printk("\n"); return 0; -cs_failed: - cs_error(link, last_fn, last_ret); +failed: mgslpc_release((u_long)link); return -ENODEV; } diff --git a/drivers/char/pty.c b/drivers/char/pty.c index 62f282e67638..d86c0bc05c1c 100644 --- a/drivers/char/pty.c +++ b/drivers/char/pty.c @@ -431,30 +431,25 @@ static struct cdev ptmx_cdev; static struct ctl_table pty_table[] = { { - .ctl_name = PTY_MAX, .procname = "max", .maxlen = sizeof(int), .mode = 0644, .data = &pty_limit, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &pty_limit_min, .extra2 = &pty_limit_max, }, { - .ctl_name = PTY_NR, .procname = "nr", .maxlen = sizeof(int), .mode = 0444, .data = &pty_count, - .proc_handler = &proc_dointvec, - }, { - .ctl_name = 0 - } + .proc_handler = proc_dointvec, + }, + {} }; static struct ctl_table pty_kern_table[] = { { - .ctl_name = KERN_PTY, .procname = "pty", .mode = 0555, .child = pty_table, @@ -464,7 +459,6 @@ static struct ctl_table pty_kern_table[] = { static struct ctl_table pty_root_table[] = { { - .ctl_name = CTL_KERN, .procname = "kernel", .mode = 0555, .child = pty_kern_table, diff --git a/drivers/char/random.c b/drivers/char/random.c index 04b505e5a5e2..dcd08635cf1b 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1257,94 +1257,54 @@ static int proc_do_uuid(ctl_table *table, int write, return proc_dostring(&fake_table, write, buffer, lenp, ppos); } -static int uuid_strategy(ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - unsigned char tmp_uuid[16], *uuid; - unsigned int len; - - if (!oldval || !oldlenp) - return 1; - - uuid = table->data; - if (!uuid) { - uuid = tmp_uuid; - uuid[8] = 0; - } - if (uuid[8] == 0) - generate_random_uuid(uuid); - - if (get_user(len, oldlenp)) - return -EFAULT; - if (len) { - if (len > 16) - len = 16; - if (copy_to_user(oldval, uuid, len) || - put_user(len, oldlenp)) - return -EFAULT; - } - return 1; -} - static int sysctl_poolsize = INPUT_POOL_WORDS * 32; ctl_table random_table[] = { { - .ctl_name = RANDOM_POOLSIZE, .procname = "poolsize", .data = &sysctl_poolsize, .maxlen = sizeof(int), .mode = 0444, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = RANDOM_ENTROPY_COUNT, .procname = "entropy_avail", .maxlen = sizeof(int), .mode = 0444, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, .data = &input_pool.entropy_count, }, { - .ctl_name = RANDOM_READ_THRESH, .procname = "read_wakeup_threshold", .data = &random_read_wakeup_thresh, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &min_read_thresh, .extra2 = &max_read_thresh, }, { - .ctl_name = RANDOM_WRITE_THRESH, .procname = "write_wakeup_threshold", .data = &random_write_wakeup_thresh, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &min_write_thresh, .extra2 = &max_write_thresh, }, { - .ctl_name = RANDOM_BOOT_ID, .procname = "boot_id", .data = &sysctl_bootid, .maxlen = 16, .mode = 0444, - .proc_handler = &proc_do_uuid, - .strategy = &uuid_strategy, + .proc_handler = proc_do_uuid, }, { - .ctl_name = RANDOM_UUID, .procname = "uuid", .maxlen = 16, .mode = 0444, - .proc_handler = &proc_do_uuid, - .strategy = &uuid_strategy, + .proc_handler = proc_do_uuid, }, - { .ctl_name = 0 } + { } }; #endif /* CONFIG_SYSCTL */ diff --git a/drivers/char/rtc.c b/drivers/char/rtc.c index bc4ab3e54550..95acb8c880f4 100644 --- a/drivers/char/rtc.c +++ b/drivers/char/rtc.c @@ -282,34 +282,31 @@ static irqreturn_t rtc_interrupt(int irq, void *dev_id) */ static ctl_table rtc_table[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "max-user-freq", .data = &rtc_max_user_freq, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, - { .ctl_name = 0 } + { } }; static ctl_table rtc_root[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "rtc", .mode = 0555, .child = rtc_table, }, - { .ctl_name = 0 } + { } }; static ctl_table dev_root[] = { { - .ctl_name = CTL_DEV, .procname = "dev", .mode = 0555, .child = rtc_root, }, - { .ctl_name = 0 } + { } }; static struct ctl_table_header *sysctl_header; diff --git a/drivers/char/tpm/tpm.c b/drivers/char/tpm/tpm.c index 47c2d2763456..f06bb37defb1 100644 --- a/drivers/char/tpm/tpm.c +++ b/drivers/char/tpm/tpm.c @@ -31,7 +31,7 @@ enum tpm_const { TPM_MINOR = 224, /* officially assigned */ - TPM_BUFSIZE = 2048, + TPM_BUFSIZE = 4096, TPM_NUM_DEVICES = 256, }; diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c index 0b73e4ec1add..2405f17b29dd 100644 --- a/drivers/char/tpm/tpm_tis.c +++ b/drivers/char/tpm/tpm_tis.c @@ -257,6 +257,10 @@ out: return size; } +static int itpm; +module_param(itpm, bool, 0444); +MODULE_PARM_DESC(itpm, "Force iTPM workarounds (found on some Lenovo laptops)"); + /* * If interrupts are used (signaled by an irq set in the vendor structure) * tpm.c can skip polling for the data to be available as the interrupt is @@ -293,7 +297,7 @@ static int tpm_tis_send(struct tpm_chip *chip, u8 *buf, size_t len) wait_for_stat(chip, TPM_STS_VALID, chip->vendor.timeout_c, &chip->vendor.int_queue); status = tpm_tis_status(chip); - if ((status & TPM_STS_DATA_EXPECT) == 0) { + if (!itpm && (status & TPM_STS_DATA_EXPECT) == 0) { rc = -EIO; goto out_err; } @@ -467,6 +471,10 @@ static int tpm_tis_init(struct device *dev, resource_size_t start, "1.2 TPM (device-id 0x%X, rev-id %d)\n", vendor >> 16, ioread8(chip->vendor.iobase + TPM_RID(0))); + if (itpm) + dev_info(dev, "Intel iTPM workaround enabled\n"); + + /* Figure out the capabilities */ intfcaps = ioread32(chip->vendor.iobase + @@ -629,6 +637,7 @@ static struct pnp_device_id tpm_pnp_tbl[] __devinitdata = { {"", 0}, /* User Specified */ {"", 0} /* Terminator */ }; +MODULE_DEVICE_TABLE(pnp, tpm_pnp_tbl); static __devexit void tpm_tis_pnp_remove(struct pnp_dev *dev) { diff --git a/drivers/char/tty_port.c b/drivers/char/tty_port.c index 2e8552dc5eda..c63f3d33914a 100644 --- a/drivers/char/tty_port.c +++ b/drivers/char/tty_port.c @@ -219,8 +219,11 @@ int tty_port_block_til_ready(struct tty_port *port, /* if non-blocking mode is set we can pass directly to open unless the port has just hung up or is in another error state */ - if ((filp->f_flags & O_NONBLOCK) || - (tty->flags & (1 << TTY_IO_ERROR))) { + if (tty->flags & (1 << TTY_IO_ERROR)) { + port->flags |= ASYNC_NORMAL_ACTIVE; + return 0; + } + if (filp->f_flags & O_NONBLOCK) { /* Indicate we are open */ if (tty->termios->c_cflag & CBAUD) tty_port_raise_dtr_rts(port); diff --git a/drivers/crypto/padlock-aes.c b/drivers/crypto/padlock-aes.c index a9952b1236b0..84c51e177269 100644 --- a/drivers/crypto/padlock-aes.c +++ b/drivers/crypto/padlock-aes.c @@ -236,7 +236,7 @@ static inline void ecb_crypt(const u8 *in, u8 *out, u32 *key, /* Padlock in ECB mode fetches at least ecb_fetch_bytes of data. * We could avoid some copying here but it's probably not worth it. */ - if (unlikely(((unsigned long)in & PAGE_SIZE) + ecb_fetch_bytes > PAGE_SIZE)) { + if (unlikely(((unsigned long)in & ~PAGE_MASK) + ecb_fetch_bytes > PAGE_SIZE)) { ecb_crypt_copy(in, out, key, cword, count); return; } @@ -248,7 +248,7 @@ static inline u8 *cbc_crypt(const u8 *in, u8 *out, u32 *key, u8 *iv, struct cword *cword, int count) { /* Padlock in CBC mode fetches at least cbc_fetch_bytes of data. */ - if (unlikely(((unsigned long)in & PAGE_SIZE) + cbc_fetch_bytes > PAGE_SIZE)) + if (unlikely(((unsigned long)in & ~PAGE_MASK) + cbc_fetch_bytes > PAGE_SIZE)) return cbc_crypt_copy(in, out, key, iv, cword, count); return rep_xcrypt_cbc(in, out, key, iv, cword, count); diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index 5903a88351bf..b401dadad4a8 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -26,6 +26,8 @@ config INTEL_IOATDMA select DMA_ENGINE select DCA select ASYNC_TX_DISABLE_CHANNEL_SWITCH + select ASYNC_TX_DISABLE_PQ_VAL_DMA + select ASYNC_TX_DISABLE_XOR_VAL_DMA help Enable support for the Intel(R) I/OAT DMA engine present in recent Intel Xeon chipsets. diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index bd0b248de2cf..8f99354082ce 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -632,11 +632,21 @@ static bool device_has_all_tx_types(struct dma_device *device) #if defined(CONFIG_ASYNC_XOR) || defined(CONFIG_ASYNC_XOR_MODULE) if (!dma_has_cap(DMA_XOR, device->cap_mask)) return false; + + #ifndef CONFIG_ASYNC_TX_DISABLE_XOR_VAL_DMA + if (!dma_has_cap(DMA_XOR_VAL, device->cap_mask)) + return false; + #endif #endif #if defined(CONFIG_ASYNC_PQ) || defined(CONFIG_ASYNC_PQ_MODULE) if (!dma_has_cap(DMA_PQ, device->cap_mask)) return false; + + #ifndef CONFIG_ASYNC_TX_DISABLE_PQ_VAL_DMA + if (!dma_has_cap(DMA_PQ_VAL, device->cap_mask)) + return false; + #endif #endif return true; diff --git a/drivers/dma/ioat/dca.c b/drivers/dma/ioat/dca.c index 69d02615c4d6..abd9038e06b1 100644 --- a/drivers/dma/ioat/dca.c +++ b/drivers/dma/ioat/dca.c @@ -98,17 +98,17 @@ static int dca_enabled_in_bios(struct pci_dev *pdev) cpuid_level_9 = cpuid_eax(9); res = test_bit(0, &cpuid_level_9); if (!res) - dev_err(&pdev->dev, "DCA is disabled in BIOS\n"); + dev_dbg(&pdev->dev, "DCA is disabled in BIOS\n"); return res; } -static int system_has_dca_enabled(struct pci_dev *pdev) +int system_has_dca_enabled(struct pci_dev *pdev) { if (boot_cpu_has(X86_FEATURE_DCA)) return dca_enabled_in_bios(pdev); - dev_err(&pdev->dev, "boot cpu doesn't have X86_FEATURE_DCA\n"); + dev_dbg(&pdev->dev, "boot cpu doesn't have X86_FEATURE_DCA\n"); return 0; } diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h index c14fdfeb7f33..45edde996480 100644 --- a/drivers/dma/ioat/dma.h +++ b/drivers/dma/ioat/dma.h @@ -297,9 +297,7 @@ static inline bool is_ioat_suspended(unsigned long status) /* channel was fatally programmed */ static inline bool is_ioat_bug(unsigned long err) { - return !!(err & (IOAT_CHANERR_SRC_ADDR_ERR|IOAT_CHANERR_DEST_ADDR_ERR| - IOAT_CHANERR_NEXT_ADDR_ERR|IOAT_CHANERR_CONTROL_ERR| - IOAT_CHANERR_LENGTH_ERR)); + return !!err; } static inline void ioat_unmap(struct pci_dev *pdev, dma_addr_t addr, size_t len, diff --git a/drivers/dma/ioat/dma_v2.c b/drivers/dma/ioat/dma_v2.c index 96ffab7d37a7..8f1f7f05deaa 100644 --- a/drivers/dma/ioat/dma_v2.c +++ b/drivers/dma/ioat/dma_v2.c @@ -279,6 +279,8 @@ void ioat2_timer_event(unsigned long data) u32 chanerr; chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET); + dev_err(to_dev(chan), "%s: Channel halted (%x)\n", + __func__, chanerr); BUG_ON(is_ioat_bug(chanerr)); } diff --git a/drivers/dma/ioat/dma_v3.c b/drivers/dma/ioat/dma_v3.c index 35d1e33afd5b..42f6f10fb0cc 100644 --- a/drivers/dma/ioat/dma_v3.c +++ b/drivers/dma/ioat/dma_v3.c @@ -378,6 +378,8 @@ static void ioat3_timer_event(unsigned long data) u32 chanerr; chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET); + dev_err(to_dev(chan), "%s: Channel halted (%x)\n", + __func__, chanerr); BUG_ON(is_ioat_bug(chanerr)); } @@ -569,7 +571,7 @@ __ioat3_prep_xor_lock(struct dma_chan *c, enum sum_check_flags *result, dump_desc_dbg(ioat, compl_desc); /* we leave the channel locked to ensure in order submission */ - return &desc->txd; + return &compl_desc->txd; } static struct dma_async_tx_descriptor * @@ -728,7 +730,7 @@ __ioat3_prep_pq_lock(struct dma_chan *c, enum sum_check_flags *result, dump_desc_dbg(ioat, compl_desc); /* we leave the channel locked to ensure in order submission */ - return &desc->txd; + return &compl_desc->txd; } static struct dma_async_tx_descriptor * @@ -736,10 +738,16 @@ ioat3_prep_pq(struct dma_chan *chan, dma_addr_t *dst, dma_addr_t *src, unsigned int src_cnt, const unsigned char *scf, size_t len, unsigned long flags) { + /* specify valid address for disabled result */ + if (flags & DMA_PREP_PQ_DISABLE_P) + dst[0] = dst[1]; + if (flags & DMA_PREP_PQ_DISABLE_Q) + dst[1] = dst[0]; + /* handle the single source multiply case from the raid6 * recovery path */ - if (unlikely((flags & DMA_PREP_PQ_DISABLE_P) && src_cnt == 1)) { + if ((flags & DMA_PREP_PQ_DISABLE_P) && src_cnt == 1) { dma_addr_t single_source[2]; unsigned char single_source_coef[2]; @@ -761,6 +769,12 @@ ioat3_prep_pq_val(struct dma_chan *chan, dma_addr_t *pq, dma_addr_t *src, unsigned int src_cnt, const unsigned char *scf, size_t len, enum sum_check_flags *pqres, unsigned long flags) { + /* specify valid address for disabled result */ + if (flags & DMA_PREP_PQ_DISABLE_P) + pq[0] = pq[1]; + if (flags & DMA_PREP_PQ_DISABLE_Q) + pq[1] = pq[0]; + /* the cleanup routine only sets bits on validate failure, it * does not clear bits on validate success... so clear it here */ @@ -778,9 +792,9 @@ ioat3_prep_pqxor(struct dma_chan *chan, dma_addr_t dst, dma_addr_t *src, dma_addr_t pq[2]; memset(scf, 0, src_cnt); - flags |= DMA_PREP_PQ_DISABLE_Q; pq[0] = dst; - pq[1] = ~0; + flags |= DMA_PREP_PQ_DISABLE_Q; + pq[1] = dst; /* specify valid address for disabled result */ return __ioat3_prep_pq_lock(chan, NULL, pq, src, src_cnt, scf, len, flags); @@ -800,9 +814,9 @@ ioat3_prep_pqxor_val(struct dma_chan *chan, dma_addr_t *src, *result = 0; memset(scf, 0, src_cnt); - flags |= DMA_PREP_PQ_DISABLE_Q; pq[0] = src[0]; - pq[1] = ~0; + flags |= DMA_PREP_PQ_DISABLE_Q; + pq[1] = pq[0]; /* specify valid address for disabled result */ return __ioat3_prep_pq_lock(chan, result, pq, &src[1], src_cnt - 1, scf, len, flags); @@ -1117,6 +1131,7 @@ static int __devinit ioat3_dma_self_test(struct ioatdma_device *device) int __devinit ioat3_dma_probe(struct ioatdma_device *device, int dca) { struct pci_dev *pdev = device->pdev; + int dca_en = system_has_dca_enabled(pdev); struct dma_device *dma; struct dma_chan *c; struct ioat_chan_common *chan; @@ -1137,6 +1152,11 @@ int __devinit ioat3_dma_probe(struct ioatdma_device *device, int dca) dma->device_prep_dma_interrupt = ioat3_prep_interrupt_lock; cap = readl(device->reg_base + IOAT_DMA_CAP_OFFSET); + + /* dca is incompatible with raid operations */ + if (dca_en && (cap & (IOAT_CAP_XOR|IOAT_CAP_PQ))) + cap &= ~(IOAT_CAP_XOR|IOAT_CAP_PQ); + if (cap & IOAT_CAP_XOR) { is_raid_device = true; dma->max_xor = 8; @@ -1186,6 +1206,16 @@ int __devinit ioat3_dma_probe(struct ioatdma_device *device, int dca) device->timer_fn = ioat2_timer_event; } + #ifdef CONFIG_ASYNC_TX_DISABLE_PQ_VAL_DMA + dma_cap_clear(DMA_PQ_VAL, dma->cap_mask); + dma->device_prep_dma_pq_val = NULL; + #endif + + #ifdef CONFIG_ASYNC_TX_DISABLE_XOR_VAL_DMA + dma_cap_clear(DMA_XOR_VAL, dma->cap_mask); + dma->device_prep_dma_xor_val = NULL; + #endif + /* -= IOAT ver.3 workarounds =- */ /* Write CHANERRMSK_INT with 3E07h to mask out the errors * that can cause stability issues for IOAT ver.3 diff --git a/drivers/dma/ioat/hw.h b/drivers/dma/ioat/hw.h index 99afb12bd409..60e675455b6a 100644 --- a/drivers/dma/ioat/hw.h +++ b/drivers/dma/ioat/hw.h @@ -39,6 +39,8 @@ #define IOAT_VER_3_0 0x30 /* Version 3.0 */ #define IOAT_VER_3_2 0x32 /* Version 3.2 */ +int system_has_dca_enabled(struct pci_dev *pdev); + struct ioat_dma_descriptor { uint32_t size; union { diff --git a/drivers/dma/ioat/registers.h b/drivers/dma/ioat/registers.h index 63038e18ab03..f015ec196700 100644 --- a/drivers/dma/ioat/registers.h +++ b/drivers/dma/ioat/registers.h @@ -92,9 +92,7 @@ #define IOAT_CHANCTRL_ERR_COMPLETION_EN 0x0004 #define IOAT_CHANCTRL_INT_REARM 0x0001 #define IOAT_CHANCTRL_RUN (IOAT_CHANCTRL_INT_REARM |\ - IOAT_CHANCTRL_ERR_COMPLETION_EN |\ - IOAT_CHANCTRL_ANY_ERR_ABORT_EN |\ - IOAT_CHANCTRL_ERR_INT_EN) + IOAT_CHANCTRL_ANY_ERR_ABORT_EN) #define IOAT_DMA_COMP_OFFSET 0x02 /* 16-bit DMA channel compatibility */ #define IOAT_DMA_COMP_V1 0x0001 /* Compatibility with DMA version 1 */ diff --git a/drivers/dma/shdma.c b/drivers/dma/shdma.c index b3b065c4e5c1..034ecf0ace03 100644 --- a/drivers/dma/shdma.c +++ b/drivers/dma/shdma.c @@ -640,17 +640,16 @@ static int __init sh_dmae_probe(struct platform_device *pdev) #endif struct sh_dmae_device *shdev; + /* get platform data */ + if (!pdev->dev.platform_data) + return -ENODEV; + shdev = kzalloc(sizeof(struct sh_dmae_device), GFP_KERNEL); if (!shdev) { dev_err(&pdev->dev, "No enough memory\n"); - err = -ENOMEM; - goto shdev_err; + return -ENOMEM; } - /* get platform data */ - if (!pdev->dev.platform_data) - goto shdev_err; - /* platform data */ memcpy(&shdev->pdata, pdev->dev.platform_data, sizeof(struct sh_dmae_pdata)); @@ -722,7 +721,6 @@ eirq_err: rst_err: kfree(shdev); -shdev_err: return err; } diff --git a/drivers/edac/edac_mce_amd.c b/drivers/edac/edac_mce_amd.c index 713ed7d37247..689cc6a6214d 100644 --- a/drivers/edac/edac_mce_amd.c +++ b/drivers/edac/edac_mce_amd.c @@ -3,7 +3,6 @@ static bool report_gart_errors; static void (*nb_bus_decoder)(int node_id, struct err_regs *regs); -static void (*orig_mce_callback)(struct mce *m); void amd_report_gart_errors(bool v) { @@ -363,8 +362,10 @@ static inline void amd_decode_err_code(unsigned int ec) pr_warning("Huh? Unknown MCE error 0x%x\n", ec); } -static void amd_decode_mce(struct mce *m) +static int amd_decode_mce(struct notifier_block *nb, unsigned long val, + void *data) { + struct mce *m = (struct mce *)data; struct err_regs regs; int node, ecc; @@ -420,20 +421,22 @@ static void amd_decode_mce(struct mce *m) } amd_decode_err_code(m->status & 0xffff); + + return NOTIFY_STOP; } +static struct notifier_block amd_mce_dec_nb = { + .notifier_call = amd_decode_mce, +}; + static int __init mce_amd_init(void) { /* * We can decode MCEs for Opteron and later CPUs: */ if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && - (boot_cpu_data.x86 >= 0xf)) { - /* safe the default decode mce callback */ - orig_mce_callback = x86_mce_decode_callback; - - x86_mce_decode_callback = amd_decode_mce; - } + (boot_cpu_data.x86 >= 0xf)) + atomic_notifier_chain_register(&x86_mce_decoder_chain, &amd_mce_dec_nb); return 0; } @@ -442,7 +445,7 @@ early_initcall(mce_amd_init); #ifdef MODULE static void __exit mce_amd_exit(void) { - x86_mce_decode_callback = orig_mce_callback; + atomic_notifier_chain_unregister(&x86_mce_decoder_chain, &amd_mce_dec_nb); } MODULE_DESCRIPTION("AMD MCE decoder"); diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index 5d524254499e..94260aa76aa3 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -275,7 +275,7 @@ static void log_irqs(u32 evt) !(evt & OHCI1394_busReset)) return; - fw_notify("IRQ %08x%s%s%s%s%s%s%s%s%s%s%s%s%s\n", evt, + fw_notify("IRQ %08x%s%s%s%s%s%s%s%s%s%s%s%s%s%s\n", evt, evt & OHCI1394_selfIDComplete ? " selfID" : "", evt & OHCI1394_RQPkt ? " AR_req" : "", evt & OHCI1394_RSPkt ? " AR_resp" : "", @@ -286,6 +286,7 @@ static void log_irqs(u32 evt) evt & OHCI1394_postedWriteErr ? " postedWriteErr" : "", evt & OHCI1394_cycleTooLong ? " cycleTooLong" : "", evt & OHCI1394_cycle64Seconds ? " cycle64Seconds" : "", + evt & OHCI1394_cycleInconsistent ? " cycleInconsistent" : "", evt & OHCI1394_regAccessFail ? " regAccessFail" : "", evt & OHCI1394_busReset ? " busReset" : "", evt & ~(OHCI1394_selfIDComplete | OHCI1394_RQPkt | @@ -293,6 +294,7 @@ static void log_irqs(u32 evt) OHCI1394_respTxComplete | OHCI1394_isochRx | OHCI1394_isochTx | OHCI1394_postedWriteErr | OHCI1394_cycleTooLong | OHCI1394_cycle64Seconds | + OHCI1394_cycleInconsistent | OHCI1394_regAccessFail | OHCI1394_busReset) ? " ?" : ""); } @@ -1439,6 +1441,17 @@ static irqreturn_t irq_handler(int irq, void *data) OHCI1394_LinkControl_cycleMaster); } + if (unlikely(event & OHCI1394_cycleInconsistent)) { + /* + * We need to clear this event bit in order to make + * cycleMatch isochronous I/O work. In theory we should + * stop active cycleMatch iso contexts now and restart + * them at least two cycles later. (FIXME?) + */ + if (printk_ratelimit()) + fw_notify("isochronous cycle inconsistent\n"); + } + if (event & OHCI1394_cycle64Seconds) { cycle_time = reg_read(ohci, OHCI1394_IsochronousCycleTimer); if ((cycle_time & 0x80000000) == 0) @@ -1528,6 +1541,7 @@ static int ohci_enable(struct fw_card *card, u32 *config_rom, size_t length) OHCI1394_reqTxComplete | OHCI1394_respTxComplete | OHCI1394_isochRx | OHCI1394_isochTx | OHCI1394_postedWriteErr | OHCI1394_cycleTooLong | + OHCI1394_cycleInconsistent | OHCI1394_cycle64Seconds | OHCI1394_regAccessFail | OHCI1394_masterIntEnable); if (param_debug & OHCI_PARAM_DEBUG_BUSRESETS) @@ -1890,15 +1904,30 @@ static int handle_it_packet(struct context *context, { struct iso_context *ctx = container_of(context, struct iso_context, context); + int i; + struct descriptor *pd; - if (last->transfer_status == 0) - /* This descriptor isn't done yet, stop iteration. */ + for (pd = d; pd <= last; pd++) + if (pd->transfer_status) + break; + if (pd > last) + /* Descriptor(s) not done yet, stop iteration */ return 0; - if (le16_to_cpu(last->control) & DESCRIPTOR_IRQ_ALWAYS) + i = ctx->header_length; + if (i + 4 < PAGE_SIZE) { + /* Present this value as big-endian to match the receive code */ + *(__be32 *)(ctx->header + i) = cpu_to_be32( + ((u32)le16_to_cpu(pd->transfer_status) << 16) | + le16_to_cpu(pd->res_count)); + ctx->header_length += 4; + } + if (le16_to_cpu(last->control) & DESCRIPTOR_IRQ_ALWAYS) { ctx->base.callback(&ctx->base, le16_to_cpu(last->res_count), - 0, NULL, ctx->base.callback_data); - + ctx->header_length, ctx->header, + ctx->base.callback_data); + ctx->header_length = 0; + } return 1; } diff --git a/drivers/gpio/langwell_gpio.c b/drivers/gpio/langwell_gpio.c index 5711ce5353c6..4baf3d7d0f8e 100644 --- a/drivers/gpio/langwell_gpio.c +++ b/drivers/gpio/langwell_gpio.c @@ -144,13 +144,6 @@ static int lnw_irq_type(unsigned irq, unsigned type) static void lnw_irq_unmask(unsigned irq) { - struct lnw_gpio *lnw = get_irq_chip_data(irq); - u32 gpio = irq - lnw->irq_base; - u8 reg = gpio / 32; - void __iomem *gedr; - - gedr = (void __iomem *)(&lnw->reg_base->GEDR[reg]); - writel(BIT(gpio % 32), gedr); }; static void lnw_irq_mask(unsigned irq) @@ -183,13 +176,11 @@ static void lnw_irq_handler(unsigned irq, struct irq_desc *desc) gedr_v = readl(gedr); if (!gedr_v) continue; - for (gpio = reg*32; gpio < reg*32+32; gpio++) { - gedr_v = readl(gedr); + for (gpio = reg*32; gpio < reg*32+32; gpio++) if (gedr_v & BIT(gpio % 32)) { pr_debug("pin %d triggered\n", gpio); generic_handle_irq(lnw->irq_base + gpio); } - } /* clear the edge detect status bit */ writel(gedr_v, gedr); } diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index f831ea159291..96eddd17e050 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -92,6 +92,7 @@ config DRM_I830 config DRM_I915 tristate "i915 driver" depends on AGP_INTEL + select SHMEM select DRM_KMS_HELPER select FB_CFB_FILLRECT select FB_CFB_COPYAREA diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index cea665d86dd3..b54ba63d506e 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -662,6 +662,12 @@ static struct drm_display_mode *drm_mode_detailed(struct drm_device *dev, return NULL; } + /* Some EDIDs have bogus h/vtotal values */ + if (mode->hsync_end > mode->htotal) + mode->htotal = mode->hsync_end + 1; + if (mode->vsync_end > mode->vtotal) + mode->vtotal = mode->vsync_end + 1; + drm_mode_set_name(mode); if (pt->misc & DRM_EDID_PT_INTERLACED) diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index dc8e374a0b55..65ef011fa8ba 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -599,7 +599,7 @@ int drm_fb_helper_check_var(struct fb_var_screeninfo *var, struct drm_framebuffer *fb = fb_helper->fb; int depth; - if (var->pixclock == -1 || !var->pixclock) + if (var->pixclock != 0) return -EINVAL; /* Need to resize the fb object !!! */ @@ -691,7 +691,7 @@ int drm_fb_helper_set_par(struct fb_info *info) int ret; int i; - if (var->pixclock != -1) { + if (var->pixclock != 0) { DRM_ERROR("PIXEL CLCOK SET\n"); return -EINVAL; } @@ -904,7 +904,7 @@ int drm_fb_helper_single_fb_probe(struct drm_device *dev, fb_helper->fb = fb; if (new_fb) { - info->var.pixclock = -1; + info->var.pixclock = 0; if (register_framebuffer(info) < 0) return -EINVAL; } else { diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 80391995bdec..e9dbb481c469 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -552,7 +552,7 @@ int drm_gem_mmap(struct file *filp, struct vm_area_struct *vma) vma->vm_flags |= VM_RESERVED | VM_IO | VM_PFNMAP | VM_DONTEXPAND; vma->vm_ops = obj->dev->driver->gem_vm_ops; vma->vm_private_data = map->handle; - vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot); + vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags)); /* Take a ref for this mapping of the object, so that the fault * handler can dereference the mmap offset's pointer to the object. diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c index c861d80fd779..97dc5a4f0de4 100644 --- a/drivers/gpu/drm/drm_mm.c +++ b/drivers/gpu/drm/drm_mm.c @@ -103,6 +103,11 @@ static struct drm_mm_node *drm_mm_kmalloc(struct drm_mm *mm, int atomic) return child; } +/* drm_mm_pre_get() - pre allocate drm_mm_node structure + * drm_mm: memory manager struct we are pre-allocating for + * + * Returns 0 on success or -ENOMEM if allocation fails. + */ int drm_mm_pre_get(struct drm_mm *mm) { struct drm_mm_node *node; @@ -253,12 +258,14 @@ void drm_mm_put_block(struct drm_mm_node *cur) prev_node->size += next_node->size; list_del(&next_node->ml_entry); list_del(&next_node->fl_entry); + spin_lock(&mm->unused_lock); if (mm->num_unused < MM_UNUSED_TARGET) { list_add(&next_node->fl_entry, &mm->unused_nodes); ++mm->num_unused; } else kfree(next_node); + spin_unlock(&mm->unused_lock); } else { next_node->size += cur->size; next_node->start = cur->start; @@ -271,11 +278,13 @@ void drm_mm_put_block(struct drm_mm_node *cur) list_add(&cur->fl_entry, &mm->fl_entry); } else { list_del(&cur->ml_entry); + spin_lock(&mm->unused_lock); if (mm->num_unused < MM_UNUSED_TARGET) { list_add(&cur->fl_entry, &mm->unused_nodes); ++mm->num_unused; } else kfree(cur); + spin_unlock(&mm->unused_lock); } } diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index f8ce9a3a420d..26bf0552b3cb 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -267,10 +267,10 @@ static void i915_dump_pages(struct seq_file *m, struct page **pages, int page_co uint32_t *mem; for (page = 0; page < page_count; page++) { - mem = kmap(pages[page]); + mem = kmap_atomic(pages[page], KM_USER0); for (i = 0; i < PAGE_SIZE; i += 4) seq_printf(m, "%08x : %08x\n", i, mem[i / 4]); - kunmap(pages[page]); + kunmap_atomic(pages[page], KM_USER0); } } diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 57204e298975..a725f6591192 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -296,6 +296,7 @@ typedef struct drm_i915_private { u32 saveVBLANK_A; u32 saveVSYNC_A; u32 saveBCLRPAT_A; + u32 saveTRANSACONF; u32 saveTRANS_HTOTAL_A; u32 saveTRANS_HBLANK_A; u32 saveTRANS_HSYNC_A; @@ -326,6 +327,7 @@ typedef struct drm_i915_private { u32 saveVBLANK_B; u32 saveVSYNC_B; u32 saveBCLRPAT_B; + u32 saveTRANSBCONF; u32 saveTRANS_HTOTAL_B; u32 saveTRANS_HBLANK_B; u32 saveTRANS_HSYNC_B; @@ -414,6 +416,16 @@ typedef struct drm_i915_private { u32 savePFB_WIN_SZ; u32 savePFA_WIN_POS; u32 savePFB_WIN_POS; + u32 savePCH_DREF_CONTROL; + u32 saveDISP_ARB_CTL; + u32 savePIPEA_DATA_M1; + u32 savePIPEA_DATA_N1; + u32 savePIPEA_LINK_M1; + u32 savePIPEA_LINK_N1; + u32 savePIPEB_DATA_M1; + u32 savePIPEB_DATA_N1; + u32 savePIPEB_LINK_M1; + u32 savePIPEB_LINK_N1; struct { struct drm_mm gtt_space; diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index c3ceffa46ea0..aa7fd82aa6eb 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -254,10 +254,15 @@ irqreturn_t igdng_irq_handler(struct drm_device *dev) { drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; int ret = IRQ_NONE; - u32 de_iir, gt_iir; + u32 de_iir, gt_iir, de_ier; u32 new_de_iir, new_gt_iir; struct drm_i915_master_private *master_priv; + /* disable master interrupt before clearing iir */ + de_ier = I915_READ(DEIER); + I915_WRITE(DEIER, de_ier & ~DE_MASTER_IRQ_CONTROL); + (void)I915_READ(DEIER); + de_iir = I915_READ(DEIIR); gt_iir = I915_READ(GTIIR); @@ -290,6 +295,9 @@ irqreturn_t igdng_irq_handler(struct drm_device *dev) gt_iir = new_gt_iir; } + I915_WRITE(DEIER, de_ier); + (void)I915_READ(DEIER); + return ret; } diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c index 992d5617e798..6eec8171a44e 100644 --- a/drivers/gpu/drm/i915/i915_suspend.c +++ b/drivers/gpu/drm/i915/i915_suspend.c @@ -239,6 +239,11 @@ static void i915_save_modeset_reg(struct drm_device *dev) if (drm_core_check_feature(dev, DRIVER_MODESET)) return; + if (IS_IGDNG(dev)) { + dev_priv->savePCH_DREF_CONTROL = I915_READ(PCH_DREF_CONTROL); + dev_priv->saveDISP_ARB_CTL = I915_READ(DISP_ARB_CTL); + } + /* Pipe & plane A info */ dev_priv->savePIPEACONF = I915_READ(PIPEACONF); dev_priv->savePIPEASRC = I915_READ(PIPEASRC); @@ -263,6 +268,11 @@ static void i915_save_modeset_reg(struct drm_device *dev) dev_priv->saveBCLRPAT_A = I915_READ(BCLRPAT_A); if (IS_IGDNG(dev)) { + dev_priv->savePIPEA_DATA_M1 = I915_READ(PIPEA_DATA_M1); + dev_priv->savePIPEA_DATA_N1 = I915_READ(PIPEA_DATA_N1); + dev_priv->savePIPEA_LINK_M1 = I915_READ(PIPEA_LINK_M1); + dev_priv->savePIPEA_LINK_N1 = I915_READ(PIPEA_LINK_N1); + dev_priv->saveFDI_TXA_CTL = I915_READ(FDI_TXA_CTL); dev_priv->saveFDI_RXA_CTL = I915_READ(FDI_RXA_CTL); @@ -270,6 +280,7 @@ static void i915_save_modeset_reg(struct drm_device *dev) dev_priv->savePFA_WIN_SZ = I915_READ(PFA_WIN_SZ); dev_priv->savePFA_WIN_POS = I915_READ(PFA_WIN_POS); + dev_priv->saveTRANSACONF = I915_READ(TRANSACONF); dev_priv->saveTRANS_HTOTAL_A = I915_READ(TRANS_HTOTAL_A); dev_priv->saveTRANS_HBLANK_A = I915_READ(TRANS_HBLANK_A); dev_priv->saveTRANS_HSYNC_A = I915_READ(TRANS_HSYNC_A); @@ -314,6 +325,11 @@ static void i915_save_modeset_reg(struct drm_device *dev) dev_priv->saveBCLRPAT_B = I915_READ(BCLRPAT_B); if (IS_IGDNG(dev)) { + dev_priv->savePIPEB_DATA_M1 = I915_READ(PIPEB_DATA_M1); + dev_priv->savePIPEB_DATA_N1 = I915_READ(PIPEB_DATA_N1); + dev_priv->savePIPEB_LINK_M1 = I915_READ(PIPEB_LINK_M1); + dev_priv->savePIPEB_LINK_N1 = I915_READ(PIPEB_LINK_N1); + dev_priv->saveFDI_TXB_CTL = I915_READ(FDI_TXB_CTL); dev_priv->saveFDI_RXB_CTL = I915_READ(FDI_RXB_CTL); @@ -321,6 +337,7 @@ static void i915_save_modeset_reg(struct drm_device *dev) dev_priv->savePFB_WIN_SZ = I915_READ(PFB_WIN_SZ); dev_priv->savePFB_WIN_POS = I915_READ(PFB_WIN_POS); + dev_priv->saveTRANSBCONF = I915_READ(TRANSBCONF); dev_priv->saveTRANS_HTOTAL_B = I915_READ(TRANS_HTOTAL_B); dev_priv->saveTRANS_HBLANK_B = I915_READ(TRANS_HBLANK_B); dev_priv->saveTRANS_HSYNC_B = I915_READ(TRANS_HSYNC_B); @@ -368,6 +385,11 @@ static void i915_restore_modeset_reg(struct drm_device *dev) fpb1_reg = FPB1; } + if (IS_IGDNG(dev)) { + I915_WRITE(PCH_DREF_CONTROL, dev_priv->savePCH_DREF_CONTROL); + I915_WRITE(DISP_ARB_CTL, dev_priv->saveDISP_ARB_CTL); + } + /* Pipe & plane A info */ /* Prime the clock */ if (dev_priv->saveDPLL_A & DPLL_VCO_ENABLE) { @@ -395,6 +417,11 @@ static void i915_restore_modeset_reg(struct drm_device *dev) I915_WRITE(BCLRPAT_A, dev_priv->saveBCLRPAT_A); if (IS_IGDNG(dev)) { + I915_WRITE(PIPEA_DATA_M1, dev_priv->savePIPEA_DATA_M1); + I915_WRITE(PIPEA_DATA_N1, dev_priv->savePIPEA_DATA_N1); + I915_WRITE(PIPEA_LINK_M1, dev_priv->savePIPEA_LINK_M1); + I915_WRITE(PIPEA_LINK_N1, dev_priv->savePIPEA_LINK_N1); + I915_WRITE(FDI_RXA_CTL, dev_priv->saveFDI_RXA_CTL); I915_WRITE(FDI_TXA_CTL, dev_priv->saveFDI_TXA_CTL); @@ -402,6 +429,7 @@ static void i915_restore_modeset_reg(struct drm_device *dev) I915_WRITE(PFA_WIN_SZ, dev_priv->savePFA_WIN_SZ); I915_WRITE(PFA_WIN_POS, dev_priv->savePFA_WIN_POS); + I915_WRITE(TRANSACONF, dev_priv->saveTRANSACONF); I915_WRITE(TRANS_HTOTAL_A, dev_priv->saveTRANS_HTOTAL_A); I915_WRITE(TRANS_HBLANK_A, dev_priv->saveTRANS_HBLANK_A); I915_WRITE(TRANS_HSYNC_A, dev_priv->saveTRANS_HSYNC_A); @@ -439,7 +467,7 @@ static void i915_restore_modeset_reg(struct drm_device *dev) /* Actually enable it */ I915_WRITE(dpll_b_reg, dev_priv->saveDPLL_B); DRM_UDELAY(150); - if (IS_I965G(dev)) + if (IS_I965G(dev) && !IS_IGDNG(dev)) I915_WRITE(DPLL_B_MD, dev_priv->saveDPLL_B_MD); DRM_UDELAY(150); @@ -454,6 +482,11 @@ static void i915_restore_modeset_reg(struct drm_device *dev) I915_WRITE(BCLRPAT_B, dev_priv->saveBCLRPAT_B); if (IS_IGDNG(dev)) { + I915_WRITE(PIPEB_DATA_M1, dev_priv->savePIPEB_DATA_M1); + I915_WRITE(PIPEB_DATA_N1, dev_priv->savePIPEB_DATA_N1); + I915_WRITE(PIPEB_LINK_M1, dev_priv->savePIPEB_LINK_M1); + I915_WRITE(PIPEB_LINK_N1, dev_priv->savePIPEB_LINK_N1); + I915_WRITE(FDI_RXB_CTL, dev_priv->saveFDI_RXB_CTL); I915_WRITE(FDI_TXB_CTL, dev_priv->saveFDI_TXB_CTL); @@ -461,6 +494,7 @@ static void i915_restore_modeset_reg(struct drm_device *dev) I915_WRITE(PFB_WIN_SZ, dev_priv->savePFB_WIN_SZ); I915_WRITE(PFB_WIN_POS, dev_priv->savePFB_WIN_POS); + I915_WRITE(TRANSBCONF, dev_priv->saveTRANSBCONF); I915_WRITE(TRANS_HTOTAL_B, dev_priv->saveTRANS_HTOTAL_B); I915_WRITE(TRANS_HBLANK_B, dev_priv->saveTRANS_HBLANK_B); I915_WRITE(TRANS_HSYNC_B, dev_priv->saveTRANS_HSYNC_B); diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index 212e22740fc1..e5051446c48e 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -262,8 +262,8 @@ static bool intel_crt_detect_hotplug(struct drm_connector *connector) } while (time_after(timeout, jiffies)); } - if ((I915_READ(PORT_HOTPLUG_STAT) & CRT_HOTPLUG_MONITOR_MASK) == - CRT_HOTPLUG_MONITOR_COLOR) + if ((I915_READ(PORT_HOTPLUG_STAT) & CRT_HOTPLUG_MONITOR_MASK) != + CRT_HOTPLUG_MONITOR_NONE) return true; return false; diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 3ba6546b7c7f..099f420de57a 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -863,10 +863,8 @@ intel_igdng_find_best_PLL(const intel_limit_t *limit, struct drm_crtc *crtc, struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; intel_clock_t clock; - int max_n; - bool found; int err_most = 47; - found = false; + int err_min = 10000; /* eDP has only 2 clock choice, no n/m/p setting */ if (HAS_eDP) @@ -890,10 +888,9 @@ intel_igdng_find_best_PLL(const intel_limit_t *limit, struct drm_crtc *crtc, } memset(best_clock, 0, sizeof(*best_clock)); - max_n = limit->n.max; for (clock.p1 = limit->p1.max; clock.p1 >= limit->p1.min; clock.p1--) { /* based on hardware requriment prefer smaller n to precision */ - for (clock.n = limit->n.min; clock.n <= max_n; clock.n++) { + for (clock.n = limit->n.min; clock.n <= limit->n.max; clock.n++) { /* based on hardware requirment prefere larger m1,m2 */ for (clock.m1 = limit->m1.max; clock.m1 >= limit->m1.min; clock.m1--) { @@ -907,18 +904,18 @@ intel_igdng_find_best_PLL(const intel_limit_t *limit, struct drm_crtc *crtc, this_err = abs((10000 - (target*10000/clock.dot))); if (this_err < err_most) { *best_clock = clock; - err_most = this_err; - max_n = clock.n; - found = true; /* found on first matching */ goto out; + } else if (this_err < err_min) { + *best_clock = clock; + err_min = this_err; } } } } } out: - return found; + return true; } /* DisplayPort has only two frequencies, 162MHz and 270MHz */ diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index 663ab6de0b58..c33451aec1bd 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -77,14 +77,32 @@ static void intel_hdmi_dpms(struct drm_encoder *encoder, int mode) struct intel_hdmi_priv *hdmi_priv = intel_output->dev_priv; u32 temp; - if (mode != DRM_MODE_DPMS_ON) { - temp = I915_READ(hdmi_priv->sdvox_reg); + temp = I915_READ(hdmi_priv->sdvox_reg); + + /* HW workaround, need to toggle enable bit off and on for 12bpc, but + * we do this anyway which shows more stable in testing. + */ + if (IS_IGDNG(dev)) { I915_WRITE(hdmi_priv->sdvox_reg, temp & ~SDVO_ENABLE); + POSTING_READ(hdmi_priv->sdvox_reg); + } + + if (mode != DRM_MODE_DPMS_ON) { + temp &= ~SDVO_ENABLE; } else { - temp = I915_READ(hdmi_priv->sdvox_reg); - I915_WRITE(hdmi_priv->sdvox_reg, temp | SDVO_ENABLE); + temp |= SDVO_ENABLE; } + + I915_WRITE(hdmi_priv->sdvox_reg, temp); POSTING_READ(hdmi_priv->sdvox_reg); + + /* HW workaround, need to write this twice for issue that may result + * in first write getting masked. + */ + if (IS_IGDNG(dev)) { + I915_WRITE(hdmi_priv->sdvox_reg, temp); + POSTING_READ(hdmi_priv->sdvox_reg); + } } static void intel_hdmi_save(struct drm_connector *connector) diff --git a/drivers/gpu/drm/radeon/atom.c b/drivers/gpu/drm/radeon/atom.c index 901befe03da2..d67c42555ab9 100644 --- a/drivers/gpu/drm/radeon/atom.c +++ b/drivers/gpu/drm/radeon/atom.c @@ -107,6 +107,7 @@ static uint32_t atom_iio_execute(struct atom_context *ctx, int base, base += 3; break; case ATOM_IIO_WRITE: + (void)ctx->card->reg_read(ctx->card, CU16(base + 1)); ctx->card->reg_write(ctx->card, CU16(base + 1), temp); base += 3; break; diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 757f5cd37744..224506a2f7b1 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -519,6 +519,7 @@ typedef int (*radeon_packet3_check_t)(struct radeon_cs_parser *p, * AGP */ int radeon_agp_init(struct radeon_device *rdev); +void radeon_agp_resume(struct radeon_device *rdev); void radeon_agp_fini(struct radeon_device *rdev); diff --git a/drivers/gpu/drm/radeon/radeon_agp.c b/drivers/gpu/drm/radeon/radeon_agp.c index 23ea9955ac59..54bf49a6d676 100644 --- a/drivers/gpu/drm/radeon/radeon_agp.c +++ b/drivers/gpu/drm/radeon/radeon_agp.c @@ -237,6 +237,18 @@ int radeon_agp_init(struct radeon_device *rdev) #endif } +void radeon_agp_resume(struct radeon_device *rdev) +{ +#if __OS_HAS_AGP + int r; + if (rdev->flags & RADEON_IS_AGP) { + r = radeon_agp_init(rdev); + if (r) + dev_warn(rdev->dev, "radeon AGP reinit failed\n"); + } +#endif +} + void radeon_agp_fini(struct radeon_device *rdev) { #if __OS_HAS_AGP diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c index fce4c4087fda..29763ceae3af 100644 --- a/drivers/gpu/drm/radeon/radeon_connectors.c +++ b/drivers/gpu/drm/radeon/radeon_connectors.c @@ -566,8 +566,9 @@ static enum drm_connector_status radeon_vga_detect(struct drm_connector *connect radeon_i2c_do_lock(radeon_connector, 0); if (!radeon_connector->edid) { - DRM_ERROR("DDC responded but not EDID found for %s\n", - drm_get_connector_name(connector)); + DRM_ERROR("%s: probed a monitor but no|invalid EDID\n", + drm_get_connector_name(connector)); + ret = connector_status_connected; } else { radeon_connector->use_digital = !!(radeon_connector->edid->input & DRM_EDID_INPUT_DIGITAL); @@ -720,8 +721,8 @@ static enum drm_connector_status radeon_dvi_detect(struct drm_connector *connect radeon_i2c_do_lock(radeon_connector, 0); if (!radeon_connector->edid) { - DRM_ERROR("DDC responded but not EDID found for %s\n", - drm_get_connector_name(connector)); + DRM_ERROR("%s: probed a monitor but no|invalid EDID\n", + drm_get_connector_name(connector)); } else { radeon_connector->use_digital = !!(radeon_connector->edid->input & DRM_EDID_INPUT_DIGITAL); @@ -1149,6 +1150,13 @@ radeon_add_legacy_connector(struct drm_device *dev, if (ret) goto failed; radeon_connector->dac_load_detect = true; + /* RS400,RC410,RS480 chipset seems to report a lot + * of false positive on load detect, we haven't yet + * found a way to make load detect reliable on those + * chipset, thus just disable it for TV. + */ + if (rdev->family == CHIP_RS400 || rdev->family == CHIP_RS480) + radeon_connector->dac_load_detect = false; drm_connector_attach_property(&radeon_connector->base, rdev->mode_info.load_detect_property, 1); diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index e3f9edfa40fe..41bb76fbe734 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -688,6 +688,8 @@ int radeon_resume_kms(struct drm_device *dev) return -1; } pci_set_master(dev->pdev); + /* resume AGP if in use */ + radeon_agp_resume(rdev); radeon_resume(rdev); radeon_restore_bios_scratch_regs(rdev); fb_set_suspend(rdev->fbdev_info, 0); diff --git a/drivers/gpu/drm/radeon/rv515.c b/drivers/gpu/drm/radeon/rv515.c index 7935f793bf62..ba68c9fe90a1 100644 --- a/drivers/gpu/drm/radeon/rv515.c +++ b/drivers/gpu/drm/radeon/rv515.c @@ -137,8 +137,6 @@ int rv515_mc_wait_for_idle(struct radeon_device *rdev) void rv515_vga_render_disable(struct radeon_device *rdev) { - WREG32(R_000330_D1VGA_CONTROL, 0); - WREG32(R_000338_D2VGA_CONTROL, 0); WREG32(R_000300_VGA_RENDER_CONTROL, RREG32(R_000300_VGA_RENDER_CONTROL) & C_000300_VGA_VSTATUS_CNTL); } @@ -382,7 +380,6 @@ void rv515_mc_stop(struct radeon_device *rdev, struct rv515_mc_save *save) save->d2crtc_control = RREG32(R_006880_D2CRTC_CONTROL); /* Stop all video */ - WREG32(R_000330_D1VGA_CONTROL, 0); WREG32(R_0068E8_D2CRTC_UPDATE_LOCK, 0); WREG32(R_000300_VGA_RENDER_CONTROL, 0); WREG32(R_0060E8_D1CRTC_UPDATE_LOCK, 1); @@ -391,6 +388,8 @@ void rv515_mc_stop(struct radeon_device *rdev, struct rv515_mc_save *save) WREG32(R_006880_D2CRTC_CONTROL, 0); WREG32(R_0060E8_D1CRTC_UPDATE_LOCK, 0); WREG32(R_0068E8_D2CRTC_UPDATE_LOCK, 0); + WREG32(R_000330_D1VGA_CONTROL, 0); + WREG32(R_000338_D2VGA_CONTROL, 0); } void rv515_mc_resume(struct radeon_device *rdev, struct rv515_mc_save *save) @@ -404,14 +403,14 @@ void rv515_mc_resume(struct radeon_device *rdev, struct rv515_mc_save *save) WREG32(R_000328_VGA_HDP_CONTROL, save->vga_hdp_control); mdelay(1); /* Restore video state */ + WREG32(R_000330_D1VGA_CONTROL, save->d1vga_control); + WREG32(R_000338_D2VGA_CONTROL, save->d2vga_control); WREG32(R_0060E8_D1CRTC_UPDATE_LOCK, 1); WREG32(R_0068E8_D2CRTC_UPDATE_LOCK, 1); WREG32(R_006080_D1CRTC_CONTROL, save->d1crtc_control); WREG32(R_006880_D2CRTC_CONTROL, save->d2crtc_control); WREG32(R_0060E8_D1CRTC_UPDATE_LOCK, 0); WREG32(R_0068E8_D2CRTC_UPDATE_LOCK, 0); - WREG32(R_000330_D1VGA_CONTROL, save->d1vga_control); - WREG32(R_000338_D2VGA_CONTROL, save->d2vga_control); WREG32(R_000300_VGA_RENDER_CONTROL, save->vga_render_control); } diff --git a/drivers/i2c/busses/i2c-pnx.c b/drivers/i2c/busses/i2c-pnx.c index 6ff6c20f1e78..fbab6846ae64 100644 --- a/drivers/i2c/busses/i2c-pnx.c +++ b/drivers/i2c/busses/i2c-pnx.c @@ -19,7 +19,9 @@ #include <linux/completion.h> #include <linux/platform_device.h> #include <linux/i2c-pnx.h> +#include <linux/io.h> #include <mach/hardware.h> +#include <mach/i2c.h> #include <asm/irq.h> #include <asm/uaccess.h> @@ -54,6 +56,9 @@ static inline void i2c_pnx_arm_timer(struct i2c_adapter *adap) struct timer_list *timer = &data->mif.timer; int expires = I2C_PNX_TIMEOUT / (1000 / HZ); + if (expires <= 1) + expires = 2; + del_timer_sync(timer); dev_dbg(&adap->dev, "Timer armed at %lu plus %u jiffies.\n", @@ -645,7 +650,7 @@ static int __devinit i2c_pnx_probe(struct platform_device *pdev) return 0; out_irq: - free_irq(alg_data->irq, alg_data); + free_irq(alg_data->irq, i2c_pnx->adapter); out_clock: i2c_pnx->set_clock_stop(pdev); out_unmap: @@ -664,7 +669,7 @@ static int __devexit i2c_pnx_remove(struct platform_device *pdev) struct i2c_adapter *adap = i2c_pnx->adapter; struct i2c_pnx_algo_data *alg_data = adap->algo_data; - free_irq(alg_data->irq, alg_data); + free_irq(alg_data->irq, i2c_pnx->adapter); i2c_del_adapter(adap); i2c_pnx->set_clock_stop(pdev); iounmap((void *)alg_data->ioaddr); diff --git a/drivers/i2c/chips/tsl2550.c b/drivers/i2c/chips/tsl2550.c index aa96bd2d27ea..a0702f36a72f 100644 --- a/drivers/i2c/chips/tsl2550.c +++ b/drivers/i2c/chips/tsl2550.c @@ -257,6 +257,7 @@ static DEVICE_ATTR(operating_mode, S_IWUSR | S_IRUGO, static ssize_t __tsl2550_show_lux(struct i2c_client *client, char *buf) { + struct tsl2550_data *data = i2c_get_clientdata(client); u8 ch0, ch1; int ret; @@ -274,6 +275,8 @@ static ssize_t __tsl2550_show_lux(struct i2c_client *client, char *buf) ret = tsl2550_calculate_lux(ch0, ch1); if (ret < 0) return ret; + if (data->operating_mode == 1) + ret *= 5; return sprintf(buf, "%d\n", ret); } diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c index 8d80fceca6a4..296504355142 100644 --- a/drivers/i2c/i2c-core.c +++ b/drivers/i2c/i2c-core.c @@ -762,6 +762,7 @@ int i2c_del_adapter(struct i2c_adapter *adap) { int res = 0; struct i2c_adapter *found; + struct i2c_client *client, *next; /* First make sure that this adapter was ever added */ mutex_lock(&core_lock); @@ -781,6 +782,16 @@ int i2c_del_adapter(struct i2c_adapter *adap) if (res) return res; + /* Remove devices instantiated from sysfs */ + list_for_each_entry_safe(client, next, &userspace_devices, detected) { + if (client->adapter == adap) { + dev_dbg(&adap->dev, "Removing %s at 0x%x\n", + client->name, client->addr); + list_del(&client->detected); + i2c_unregister_device(client); + } + } + /* Detach any active clients. This can't fail, thus we do not checking the returned value. */ res = device_for_each_child(&adap->dev, NULL, __unregister_client); diff --git a/drivers/ide/ide-cs.c b/drivers/ide/ide-cs.c index 063b933d864a..dd6396384c25 100644 --- a/drivers/ide/ide-cs.c +++ b/drivers/ide/ide-cs.c @@ -60,15 +60,6 @@ MODULE_AUTHOR("David Hinds <dahinds@users.sourceforge.net>"); MODULE_DESCRIPTION("PCMCIA ATA/IDE card driver"); MODULE_LICENSE("Dual MPL/GPL"); -#define INT_MODULE_PARM(n, v) static int n = v; module_param(n, int, 0) - -#ifdef CONFIG_PCMCIA_DEBUG -INT_MODULE_PARM(pc_debug, 0); -#define DEBUG(n, args...) if (pc_debug>(n)) printk(KERN_DEBUG args) -#else -#define DEBUG(n, args...) -#endif - /*====================================================================*/ typedef struct ide_info_t { @@ -98,7 +89,7 @@ static int ide_probe(struct pcmcia_device *link) { ide_info_t *info; - DEBUG(0, "ide_attach()\n"); + dev_dbg(&link->dev, "ide_attach()\n"); /* Create new ide device */ info = kzalloc(sizeof(*info), GFP_KERNEL); @@ -112,7 +103,6 @@ static int ide_probe(struct pcmcia_device *link) link->io.Attributes2 = IO_DATA_PATH_WIDTH_8; link->io.IOAddrLines = 3; link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; link->conf.Attributes = CONF_ENABLE_IRQ; link->conf.IntType = INT_MEMORY_AND_IO; @@ -134,7 +124,7 @@ static void ide_detach(struct pcmcia_device *link) ide_hwif_t *hwif = info->host->ports[0]; unsigned long data_addr, ctl_addr; - DEBUG(0, "ide_detach(0x%p)\n", link); + dev_dbg(&link->dev, "ide_detach(0x%p)\n", link); data_addr = hwif->io_ports.data_addr; ctl_addr = hwif->io_ports.ctl_addr; @@ -217,9 +207,6 @@ out_release: ======================================================================*/ -#define CS_CHECK(fn, ret) \ -do { last_fn = (fn); if ((last_ret = (ret)) != 0) goto cs_failed; } while (0) - struct pcmcia_config_check { unsigned long ctl_base; int skip_vcc; @@ -282,11 +269,11 @@ static int ide_config(struct pcmcia_device *link) { ide_info_t *info = link->priv; struct pcmcia_config_check *stk = NULL; - int last_ret = 0, last_fn = 0, is_kme = 0; + int ret = 0, is_kme = 0; unsigned long io_base, ctl_base; struct ide_host *host; - DEBUG(0, "ide_config(0x%p)\n", link); + dev_dbg(&link->dev, "ide_config(0x%p)\n", link); is_kme = ((link->manf_id == MANFID_KME) && ((link->card_id == PRODID_KME_KXLC005_A) || @@ -306,8 +293,12 @@ static int ide_config(struct pcmcia_device *link) io_base = link->io.BasePort1; ctl_base = stk->ctl_base; - CS_CHECK(RequestIRQ, pcmcia_request_irq(link, &link->irq)); - CS_CHECK(RequestConfiguration, pcmcia_request_configuration(link, &link->conf)); + ret = pcmcia_request_irq(link, &link->irq); + if (ret) + goto failed; + ret = pcmcia_request_configuration(link, &link->conf); + if (ret) + goto failed; /* disable drive interrupts during IDE probe */ outb(0x02, ctl_base); @@ -342,8 +333,6 @@ err_mem: printk(KERN_NOTICE "ide-cs: ide_config failed memory allocation\n"); goto failed; -cs_failed: - cs_error(link, last_fn, last_ret); failed: kfree(stk); ide_release(link); @@ -363,7 +352,7 @@ static void ide_release(struct pcmcia_device *link) ide_info_t *info = link->priv; struct ide_host *host = info->host; - DEBUG(0, "ide_release(0x%p)\n", link); + dev_dbg(&link->dev, "ide_release(0x%p)\n", link); if (info->ndev) /* FIXME: if this fails we need to queue the cleanup somehow diff --git a/drivers/ide/ide-ioctls.c b/drivers/ide/ide-ioctls.c index d3440b5010a5..6e7ae2b6cfc6 100644 --- a/drivers/ide/ide-ioctls.c +++ b/drivers/ide/ide-ioctls.c @@ -162,7 +162,7 @@ static int ide_cmd_ioctl(ide_drive_t *drive, unsigned long arg) if (tf->command == ATA_CMD_SET_FEATURES && tf->feature == SETFEATURES_XFER && tf->nsect >= XFER_SW_DMA_0) { - xfer_rate = ide_find_dma_mode(drive, XFER_UDMA_6); + xfer_rate = ide_find_dma_mode(drive, tf->nsect); if (xfer_rate != tf->nsect) { err = -EINVAL; goto abort; diff --git a/drivers/ieee802154/fakehard.c b/drivers/ieee802154/fakehard.c index 96a2959ce877..7c544f7c74c4 100644 --- a/drivers/ieee802154/fakehard.c +++ b/drivers/ieee802154/fakehard.c @@ -260,15 +260,12 @@ static int ieee802154_fake_close(struct net_device *dev) static netdev_tx_t ieee802154_fake_xmit(struct sk_buff *skb, struct net_device *dev) { - skb->iif = dev->ifindex; - skb->dev = dev; dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; - dev->trans_start = jiffies; - /* FIXME: do hardware work here ... */ + dev_kfree_skb(skb); return NETDEV_TX_OK; } diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index a537925f7651..2bcf1ace27c0 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -447,6 +447,27 @@ static struct dmi_system_id __initdata i8042_dmi_reset_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "N10"), }, }, + { + .ident = "Dell Vostro 1320", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 1320"), + }, + }, + { + .ident = "Dell Vostro 1520", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 1520"), + }, + }, + { + .ident = "Dell Vostro 1720", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 1720"), + }, + }, { } }; diff --git a/drivers/isdn/hardware/avm/avm_cs.c b/drivers/isdn/hardware/avm/avm_cs.c index c72565520e41..5a6ae646a636 100644 --- a/drivers/isdn/hardware/avm/avm_cs.c +++ b/drivers/isdn/hardware/avm/avm_cs.c @@ -111,8 +111,6 @@ static int avmcs_probe(struct pcmcia_device *p_dev) p_dev->irq.Attributes = IRQ_TYPE_EXCLUSIVE; p_dev->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING|IRQ_FIRST_SHARED; - p_dev->irq.IRQInfo1 = IRQ_LEVEL_ID; - /* General socket configuration */ p_dev->conf.Attributes = CONF_ENABLE_IRQ; p_dev->conf.IntType = INT_MEMORY_AND_IO; @@ -198,7 +196,6 @@ static int avmcs_config(struct pcmcia_device *link) */ i = pcmcia_request_irq(link, &link->irq); if (i != 0) { - cs_error(link, RequestIRQ, i); /* undo */ pcmcia_disable_device(link); break; @@ -209,7 +206,6 @@ static int avmcs_config(struct pcmcia_device *link) */ i = pcmcia_request_configuration(link, &link->conf); if (i != 0) { - cs_error(link, RequestConfiguration, i); pcmcia_disable_device(link); break; } diff --git a/drivers/isdn/hisax/avma1_cs.c b/drivers/isdn/hisax/avma1_cs.c index 23560c897ec3..f9bdff39cf4a 100644 --- a/drivers/isdn/hisax/avma1_cs.c +++ b/drivers/isdn/hisax/avma1_cs.c @@ -30,22 +30,6 @@ MODULE_DESCRIPTION("ISDN4Linux: PCMCIA client driver for AVM A1/Fritz!PCMCIA car MODULE_AUTHOR("Carsten Paeth"); MODULE_LICENSE("GPL"); -/* - All the PCMCIA modules use PCMCIA_DEBUG to control debugging. If - you do not define PCMCIA_DEBUG at all, all the debug code will be - left out. If you compile with PCMCIA_DEBUG=0, the debug code will - be present but disabled -- but it can then be enabled for specific - modules at load time with a 'pc_debug=#' option to insmod. -*/ -#ifdef PCMCIA_DEBUG -static int pc_debug = PCMCIA_DEBUG; -module_param(pc_debug, int, 0); -#define DEBUG(n, args...) if (pc_debug>(n)) printk(KERN_DEBUG args); -static char *version = -"avma1_cs.c 1.00 1998/01/23 10:00:00 (Carsten Paeth)"; -#else -#define DEBUG(n, args...) -#endif /*====================================================================*/ @@ -119,7 +103,7 @@ static int avma1cs_probe(struct pcmcia_device *p_dev) { local_info_t *local; - DEBUG(0, "avma1cs_attach()\n"); + dev_dbg(&p_dev->dev, "avma1cs_attach()\n"); /* Allocate space for private device-specific data */ local = kzalloc(sizeof(local_info_t), GFP_KERNEL); @@ -139,8 +123,6 @@ static int avma1cs_probe(struct pcmcia_device *p_dev) p_dev->irq.Attributes = IRQ_TYPE_EXCLUSIVE; p_dev->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING|IRQ_FIRST_SHARED; - p_dev->irq.IRQInfo1 = IRQ_LEVEL_ID; - /* General socket configuration */ p_dev->conf.Attributes = CONF_ENABLE_IRQ; p_dev->conf.IntType = INT_MEMORY_AND_IO; @@ -161,7 +143,7 @@ static int avma1cs_probe(struct pcmcia_device *p_dev) static void avma1cs_detach(struct pcmcia_device *link) { - DEBUG(0, "avma1cs_detach(0x%p)\n", link); + dev_dbg(&link->dev, "avma1cs_detach(0x%p)\n", link); avma1cs_release(link); kfree(link->priv); } /* avma1cs_detach */ @@ -203,7 +185,7 @@ static int avma1cs_config(struct pcmcia_device *link) dev = link->priv; - DEBUG(0, "avma1cs_config(0x%p)\n", link); + dev_dbg(&link->dev, "avma1cs_config(0x%p)\n", link); devname[0] = 0; if (link->prod_id[1]) @@ -218,7 +200,6 @@ static int avma1cs_config(struct pcmcia_device *link) */ i = pcmcia_request_irq(link, &link->irq); if (i != 0) { - cs_error(link, RequestIRQ, i); /* undo */ pcmcia_disable_device(link); break; @@ -229,7 +210,6 @@ static int avma1cs_config(struct pcmcia_device *link) */ i = pcmcia_request_configuration(link, &link->conf); if (i != 0) { - cs_error(link, RequestConfiguration, i); pcmcia_disable_device(link); break; } @@ -281,7 +261,7 @@ static void avma1cs_release(struct pcmcia_device *link) { local_info_t *local = link->priv; - DEBUG(0, "avma1cs_release(0x%p)\n", link); + dev_dbg(&link->dev, "avma1cs_release(0x%p)\n", link); /* now unregister function with hisax */ HiSax_closecard(local->node.minor); diff --git a/drivers/isdn/hisax/elsa_cs.c b/drivers/isdn/hisax/elsa_cs.c index f4d0fe29bcf8..a2f709f53974 100644 --- a/drivers/isdn/hisax/elsa_cs.c +++ b/drivers/isdn/hisax/elsa_cs.c @@ -57,23 +57,6 @@ MODULE_DESCRIPTION("ISDN4Linux: PCMCIA client driver for Elsa PCM cards"); MODULE_AUTHOR("Klaus Lichtenwalder"); MODULE_LICENSE("Dual MPL/GPL"); -/* - All the PCMCIA modules use PCMCIA_DEBUG to control debugging. If - you do not define PCMCIA_DEBUG at all, all the debug code will be - left out. If you compile with PCMCIA_DEBUG=0, the debug code will - be present but disabled -- but it can then be enabled for specific - modules at load time with a 'pc_debug=#' option to insmod. -*/ - -#ifdef PCMCIA_DEBUG -static int pc_debug = PCMCIA_DEBUG; -module_param(pc_debug, int, 0); -#define DEBUG(n, args...) if (pc_debug>(n)) printk(KERN_DEBUG args); -static char *version = -"elsa_cs.c $Revision: 1.2.2.4 $ $Date: 2004/01/25 15:07:06 $ (K.Lichtenwalder)"; -#else -#define DEBUG(n, args...) -#endif /*====================================================================*/ @@ -142,7 +125,7 @@ static int elsa_cs_probe(struct pcmcia_device *link) { local_info_t *local; - DEBUG(0, "elsa_cs_attach()\n"); + dev_dbg(&link->dev, "elsa_cs_attach()\n"); /* Allocate space for private device-specific data */ local = kzalloc(sizeof(local_info_t), GFP_KERNEL); @@ -155,7 +138,6 @@ static int elsa_cs_probe(struct pcmcia_device *link) /* Interrupt setup */ link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING|IRQ_FIRST_SHARED; - link->irq.IRQInfo1 = IRQ_LEVEL_ID|IRQ_SHARE_ID; link->irq.Handler = NULL; /* @@ -188,7 +170,7 @@ static void elsa_cs_detach(struct pcmcia_device *link) { local_info_t *info = link->priv; - DEBUG(0, "elsa_cs_detach(0x%p)\n", link); + dev_dbg(&link->dev, "elsa_cs_detach(0x%p)\n", link); info->busy = 1; elsa_cs_release(link); @@ -231,30 +213,25 @@ static int elsa_cs_configcheck(struct pcmcia_device *p_dev, static int elsa_cs_config(struct pcmcia_device *link) { local_info_t *dev; - int i, last_fn; + int i; IsdnCard_t icard; - DEBUG(0, "elsa_config(0x%p)\n", link); + dev_dbg(&link->dev, "elsa_config(0x%p)\n", link); dev = link->priv; i = pcmcia_loop_config(link, elsa_cs_configcheck, NULL); - if (i != 0) { - last_fn = RequestIO; - goto cs_failed; - } + if (i != 0) + goto failed; i = pcmcia_request_irq(link, &link->irq); if (i != 0) { link->irq.AssignedIRQ = 0; - last_fn = RequestIRQ; - goto cs_failed; + goto failed; } i = pcmcia_request_configuration(link, &link->conf); - if (i != 0) { - last_fn = RequestConfiguration; - goto cs_failed; - } + if (i != 0) + goto failed; /* At this point, the dev_node_t structure(s) should be initialized and arranged in a linked list at link->dev. *//* */ @@ -290,8 +267,7 @@ static int elsa_cs_config(struct pcmcia_device *link) ((local_info_t*)link->priv)->cardnr = i; return 0; -cs_failed: - cs_error(link, last_fn, i); +failed: elsa_cs_release(link); return -ENODEV; } /* elsa_cs_config */ @@ -308,7 +284,7 @@ static void elsa_cs_release(struct pcmcia_device *link) { local_info_t *local = link->priv; - DEBUG(0, "elsa_cs_release(0x%p)\n", link); + dev_dbg(&link->dev, "elsa_cs_release(0x%p)\n", link); if (local) { if (local->cardnr >= 0) { diff --git a/drivers/isdn/hisax/sedlbauer_cs.c b/drivers/isdn/hisax/sedlbauer_cs.c index 9a3c9f5e4fe8..af5d393cc2d0 100644 --- a/drivers/isdn/hisax/sedlbauer_cs.c +++ b/drivers/isdn/hisax/sedlbauer_cs.c @@ -57,24 +57,6 @@ MODULE_DESCRIPTION("ISDN4Linux: PCMCIA client driver for Sedlbauer cards"); MODULE_AUTHOR("Marcus Niemann"); MODULE_LICENSE("Dual MPL/GPL"); -/* - All the PCMCIA modules use PCMCIA_DEBUG to control debugging. If - you do not define PCMCIA_DEBUG at all, all the debug code will be - left out. If you compile with PCMCIA_DEBUG=0, the debug code will - be present but disabled -- but it can then be enabled for specific - modules at load time with a 'pc_debug=#' option to insmod. -*/ - -#ifdef PCMCIA_DEBUG -static int pc_debug = PCMCIA_DEBUG; -module_param(pc_debug, int, 0); -#define DEBUG(n, args...) if (pc_debug>(n)) printk(KERN_DEBUG args); -static char *version = -"sedlbauer_cs.c 1.1a 2001/01/28 15:04:04 (M.Niemann)"; -#else -#define DEBUG(n, args...) -#endif - /*====================================================================*/ @@ -151,7 +133,7 @@ static int sedlbauer_probe(struct pcmcia_device *link) { local_info_t *local; - DEBUG(0, "sedlbauer_attach()\n"); + dev_dbg(&link->dev, "sedlbauer_attach()\n"); /* Allocate space for private device-specific data */ local = kzalloc(sizeof(local_info_t), GFP_KERNEL); @@ -163,7 +145,6 @@ static int sedlbauer_probe(struct pcmcia_device *link) /* Interrupt setup */ link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING|IRQ_FIRST_SHARED; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; link->irq.Handler = NULL; /* @@ -198,7 +179,7 @@ static int sedlbauer_probe(struct pcmcia_device *link) static void sedlbauer_detach(struct pcmcia_device *link) { - DEBUG(0, "sedlbauer_detach(0x%p)\n", link); + dev_dbg(&link->dev, "sedlbauer_detach(0x%p)\n", link); ((local_info_t *)link->priv)->stop = 1; sedlbauer_release(link); @@ -214,9 +195,6 @@ static void sedlbauer_detach(struct pcmcia_device *link) device available to the system. ======================================================================*/ -#define CS_CHECK(fn, ret) \ -do { last_fn = (fn); if ((last_ret = (ret)) != 0) goto cs_failed; } while (0) - static int sedlbauer_config_check(struct pcmcia_device *p_dev, cistpl_cftable_entry_t *cfg, cistpl_cftable_entry_t *dflt, @@ -293,11 +271,11 @@ static int sedlbauer_config_check(struct pcmcia_device *p_dev, req->Base = mem->win[0].host_addr; req->Size = mem->win[0].len; req->AccessSpeed = 0; - if (pcmcia_request_window(&p_dev, req, &p_dev->win) != 0) + if (pcmcia_request_window(p_dev, req, &p_dev->win) != 0) return -ENODEV; map.Page = 0; map.CardOffset = mem->win[0].card_addr; - if (pcmcia_map_mem_page(p_dev->win, &map) != 0) + if (pcmcia_map_mem_page(p_dev, p_dev->win, &map) != 0) return -ENODEV; } return 0; @@ -309,10 +287,10 @@ static int sedlbauer_config(struct pcmcia_device *link) { local_info_t *dev = link->priv; win_req_t *req; - int last_fn, last_ret; + int ret; IsdnCard_t icard; - DEBUG(0, "sedlbauer_config(0x%p)\n", link); + dev_dbg(&link->dev, "sedlbauer_config(0x%p)\n", link); req = kzalloc(sizeof(win_req_t), GFP_KERNEL); if (!req) @@ -330,8 +308,8 @@ static int sedlbauer_config(struct pcmcia_device *link) these things without consulting the CIS, and most client drivers will only use the CIS to fill in implementation-defined details. */ - last_ret = pcmcia_loop_config(link, sedlbauer_config_check, req); - if (last_ret) + ret = pcmcia_loop_config(link, sedlbauer_config_check, req); + if (ret) goto failed; /* @@ -339,15 +317,20 @@ static int sedlbauer_config(struct pcmcia_device *link) handler to the interrupt, unless the 'Handler' member of the irq structure is initialized. */ - if (link->conf.Attributes & CONF_ENABLE_IRQ) - CS_CHECK(RequestIRQ, pcmcia_request_irq(link, &link->irq)); + if (link->conf.Attributes & CONF_ENABLE_IRQ) { + ret = pcmcia_request_irq(link, &link->irq); + if (ret) + goto failed; + } /* This actually configures the PCMCIA socket -- setting up the I/O windows and the interrupt mapping, and putting the card and host interface into "Memory and IO" mode. */ - CS_CHECK(RequestConfiguration, pcmcia_request_configuration(link, &link->conf)); + ret = pcmcia_request_configuration(link, &link->conf); + if (ret) + goto failed; /* At this point, the dev_node_t structure(s) need to be @@ -380,19 +363,18 @@ static int sedlbauer_config(struct pcmcia_device *link) icard.protocol = protocol; icard.typ = ISDN_CTYPE_SEDLBAUER_PCMCIA; - last_ret = hisax_init_pcmcia(link, &(((local_info_t*)link->priv)->stop), &icard); - if (last_ret < 0) { - printk(KERN_ERR "sedlbauer_cs: failed to initialize SEDLBAUER PCMCIA %d at i/o %#x\n", - last_ret, link->io.BasePort1); + ret = hisax_init_pcmcia(link, + &(((local_info_t *)link->priv)->stop), &icard); + if (ret < 0) { + printk(KERN_ERR "sedlbauer_cs: failed to initialize SEDLBAUER PCMCIA %d at i/o %#x\n", + ret, link->io.BasePort1); sedlbauer_release(link); return -ENODEV; } else - ((local_info_t*)link->priv)->cardnr = last_ret; + ((local_info_t *)link->priv)->cardnr = ret; return 0; -cs_failed: - cs_error(link, last_fn, last_ret); failed: sedlbauer_release(link); return -ENODEV; @@ -410,7 +392,7 @@ failed: static void sedlbauer_release(struct pcmcia_device *link) { local_info_t *local = link->priv; - DEBUG(0, "sedlbauer_release(0x%p)\n", link); + dev_dbg(&link->dev, "sedlbauer_release(0x%p)\n", link); if (local) { if (local->cardnr >= 0) { diff --git a/drivers/isdn/hisax/teles_cs.c b/drivers/isdn/hisax/teles_cs.c index 623d111544d4..ea705394ce2b 100644 --- a/drivers/isdn/hisax/teles_cs.c +++ b/drivers/isdn/hisax/teles_cs.c @@ -38,23 +38,6 @@ MODULE_DESCRIPTION("ISDN4Linux: PCMCIA client driver for Teles PCMCIA cards"); MODULE_AUTHOR("Christof Petig, christof.petig@wtal.de, Karsten Keil, kkeil@suse.de"); MODULE_LICENSE("GPL"); -/* - All the PCMCIA modules use PCMCIA_DEBUG to control debugging. If - you do not define PCMCIA_DEBUG at all, all the debug code will be - left out. If you compile with PCMCIA_DEBUG=0, the debug code will - be present but disabled -- but it can then be enabled for specific - modules at load time with a 'pc_debug=#' option to insmod. -*/ - -#ifdef PCMCIA_DEBUG -static int pc_debug = PCMCIA_DEBUG; -module_param(pc_debug, int, 0); -#define DEBUG(n, args...) if (pc_debug>(n)) printk(KERN_DEBUG args); -static char *version = -"teles_cs.c 2.10 2002/07/30 22:23:34 kkeil"; -#else -#define DEBUG(n, args...) -#endif /*====================================================================*/ @@ -133,7 +116,7 @@ static int teles_probe(struct pcmcia_device *link) { local_info_t *local; - DEBUG(0, "teles_attach()\n"); + dev_dbg(&link->dev, "teles_attach()\n"); /* Allocate space for private device-specific data */ local = kzalloc(sizeof(local_info_t), GFP_KERNEL); @@ -145,7 +128,6 @@ static int teles_probe(struct pcmcia_device *link) /* Interrupt setup */ link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING|IRQ_FIRST_SHARED; - link->irq.IRQInfo1 = IRQ_LEVEL_ID|IRQ_SHARE_ID; link->irq.Handler = NULL; /* @@ -178,7 +160,7 @@ static void teles_detach(struct pcmcia_device *link) { local_info_t *info = link->priv; - DEBUG(0, "teles_detach(0x%p)\n", link); + dev_dbg(&link->dev, "teles_detach(0x%p)\n", link); info->busy = 1; teles_cs_release(link); @@ -221,30 +203,25 @@ static int teles_cs_configcheck(struct pcmcia_device *p_dev, static int teles_cs_config(struct pcmcia_device *link) { local_info_t *dev; - int i, last_fn; + int i; IsdnCard_t icard; - DEBUG(0, "teles_config(0x%p)\n", link); + dev_dbg(&link->dev, "teles_config(0x%p)\n", link); dev = link->priv; i = pcmcia_loop_config(link, teles_cs_configcheck, NULL); - if (i != 0) { - last_fn = RequestIO; + if (i != 0) goto cs_failed; - } i = pcmcia_request_irq(link, &link->irq); if (i != 0) { link->irq.AssignedIRQ = 0; - last_fn = RequestIRQ; goto cs_failed; } i = pcmcia_request_configuration(link, &link->conf); - if (i != 0) { - last_fn = RequestConfiguration; + if (i != 0) goto cs_failed; - } /* At this point, the dev_node_t structure(s) should be initialized and arranged in a linked list at link->dev. *//* */ @@ -283,7 +260,6 @@ static int teles_cs_config(struct pcmcia_device *link) return 0; cs_failed: - cs_error(link, last_fn, i); teles_cs_release(link); return -ENODEV; } /* teles_cs_config */ @@ -300,7 +276,7 @@ static void teles_cs_release(struct pcmcia_device *link) { local_info_t *local = link->priv; - DEBUG(0, "teles_cs_release(0x%p)\n", link); + dev_dbg(&link->dev, "teles_cs_release(0x%p)\n", link); if (local) { if (local->cardnr >= 0) { diff --git a/drivers/macintosh/mac_hid.c b/drivers/macintosh/mac_hid.c index cc9f27514aef..7b4ef5bb556b 100644 --- a/drivers/macintosh/mac_hid.c +++ b/drivers/macintosh/mac_hid.c @@ -27,54 +27,49 @@ static int mouse_last_keycode; /* file(s) in /proc/sys/dev/mac_hid */ static ctl_table mac_hid_files[] = { { - .ctl_name = DEV_MAC_HID_MOUSE_BUTTON_EMULATION, .procname = "mouse_button_emulation", .data = &mouse_emulate_buttons, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = DEV_MAC_HID_MOUSE_BUTTON2_KEYCODE, .procname = "mouse_button2_keycode", .data = &mouse_button2_keycode, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = DEV_MAC_HID_MOUSE_BUTTON3_KEYCODE, .procname = "mouse_button3_keycode", .data = &mouse_button3_keycode, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, - { .ctl_name = 0 } + { } }; /* dir in /proc/sys/dev */ static ctl_table mac_hid_dir[] = { { - .ctl_name = DEV_MAC_HID, .procname = "mac_hid", .maxlen = 0, .mode = 0555, .child = mac_hid_files, }, - { .ctl_name = 0 } + { } }; /* /proc/sys/dev itself, in case that is not there yet */ static ctl_table mac_hid_root_dir[] = { { - .ctl_name = CTL_DEV, .procname = "dev", .maxlen = 0, .mode = 0555, .child = mac_hid_dir, }, - { .ctl_name = 0 } + { } }; static struct ctl_table_header *mac_hid_sysctl_header; diff --git a/drivers/md/md.c b/drivers/md/md.c index b182f86a19dd..5f154ef1e4be 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -98,44 +98,40 @@ static struct ctl_table_header *raid_table_header; static ctl_table raid_table[] = { { - .ctl_name = DEV_RAID_SPEED_LIMIT_MIN, .procname = "speed_limit_min", .data = &sysctl_speed_limit_min, .maxlen = sizeof(int), .mode = S_IRUGO|S_IWUSR, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = DEV_RAID_SPEED_LIMIT_MAX, .procname = "speed_limit_max", .data = &sysctl_speed_limit_max, .maxlen = sizeof(int), .mode = S_IRUGO|S_IWUSR, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, - { .ctl_name = 0 } + { } }; static ctl_table raid_dir_table[] = { { - .ctl_name = DEV_RAID, .procname = "raid", .maxlen = 0, .mode = S_IRUGO|S_IXUGO, .child = raid_table, }, - { .ctl_name = 0 } + { } }; static ctl_table raid_root_table[] = { { - .ctl_name = CTL_DEV, .procname = "dev", .maxlen = 0, .mode = 0555, .child = raid_dir_table, }, - { .ctl_name = 0 } + { } }; static const struct block_device_operations md_fops; diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index a053423785c9..e07ce2e033a9 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1650,11 +1650,12 @@ static void raid1d(mddev_t *mddev) r1_bio->sector, r1_bio->sectors); unfreeze_array(conf); - } + } else + md_error(mddev, + conf->mirrors[r1_bio->read_disk].rdev); bio = r1_bio->bios[r1_bio->read_disk]; - if ((disk=read_balance(conf, r1_bio)) == -1 || - disk == r1_bio->read_disk) { + if ((disk=read_balance(conf, r1_bio)) == -1) { printk(KERN_ALERT "raid1: %s: unrecoverable I/O" " read error for block %llu\n", bdevname(bio->bi_bdev,b), diff --git a/drivers/media/common/ir-functions.c b/drivers/media/common/ir-functions.c index 655474b29e21..abd4791acb0e 100644 --- a/drivers/media/common/ir-functions.c +++ b/drivers/media/common/ir-functions.c @@ -64,7 +64,7 @@ void ir_input_init(struct input_dev *dev, struct ir_input_state *ir, ir->ir_type = ir_type; - memset(ir->ir_codes, sizeof(ir->ir_codes), 0); + memset(ir->ir_codes, 0, sizeof(ir->ir_codes)); /* * FIXME: This is a temporary workaround to use the new IR tables diff --git a/drivers/media/dvb/dvb-core/dvb_frontend.c b/drivers/media/dvb/dvb-core/dvb_frontend.c index ddf639ed2fd8..98082416aa52 100644 --- a/drivers/media/dvb/dvb-core/dvb_frontend.c +++ b/drivers/media/dvb/dvb-core/dvb_frontend.c @@ -31,6 +31,7 @@ #include <linux/wait.h> #include <linux/slab.h> #include <linux/poll.h> +#include <linux/semaphore.h> #include <linux/module.h> #include <linux/list.h> #include <linux/freezer.h> diff --git a/drivers/media/dvb/dvb-usb/cxusb.c b/drivers/media/dvb/dvb-usb/cxusb.c index f65591fb7cec..2a53dd096eef 100644 --- a/drivers/media/dvb/dvb-usb/cxusb.c +++ b/drivers/media/dvb/dvb-usb/cxusb.c @@ -663,6 +663,14 @@ static struct zl10353_config cxusb_zl10353_xc3028_config = { .parallel_ts = 1, }; +static struct zl10353_config cxusb_zl10353_xc3028_config_no_i2c_gate = { + .demod_address = 0x0f, + .if2 = 45600, + .no_tuner = 1, + .parallel_ts = 1, + .disable_i2c_gate_ctrl = 1, +}; + static struct mt352_config cxusb_mt352_xc3028_config = { .demod_address = 0x0f, .if2 = 4560, @@ -894,7 +902,7 @@ static int cxusb_dualdig4_frontend_attach(struct dvb_usb_adapter *adap) cxusb_bluebird_gpio_pulse(adap->dev, 0x02, 1); if ((adap->fe = dvb_attach(zl10353_attach, - &cxusb_zl10353_xc3028_config, + &cxusb_zl10353_xc3028_config_no_i2c_gate, &adap->dev->i2c_adap)) == NULL) return -EIO; diff --git a/drivers/media/dvb/siano/Kconfig b/drivers/media/dvb/siano/Kconfig index 8c1aed77ea30..85a222c4eaa0 100644 --- a/drivers/media/dvb/siano/Kconfig +++ b/drivers/media/dvb/siano/Kconfig @@ -4,7 +4,7 @@ config SMS_SIANO_MDTV tristate "Siano SMS1xxx based MDTV receiver" - depends on DVB_CORE && INPUT + depends on DVB_CORE && INPUT && HAS_DMA ---help--- Choose Y or M here if you have MDTV receiver with a Siano chipset. diff --git a/drivers/media/radio/radio-gemtek-pci.c b/drivers/media/radio/radio-gemtek-pci.c index c3f579de6e71..c6cf11661868 100644 --- a/drivers/media/radio/radio-gemtek-pci.c +++ b/drivers/media/radio/radio-gemtek-pci.c @@ -181,12 +181,10 @@ static void gemtek_pci_mute(struct gemtek_pci *card) static void gemtek_pci_unmute(struct gemtek_pci *card) { - mutex_lock(&card->lock); if (card->mute) { gemtek_pci_setfrequency(card, card->current_frequency); card->mute = false; } - mutex_unlock(&card->lock); } static int gemtek_pci_getsignal(struct gemtek_pci *card) diff --git a/drivers/media/video/davinci/vpif_display.c b/drivers/media/video/davinci/vpif_display.c index c015da813dda..d14cfb200ed0 100644 --- a/drivers/media/video/davinci/vpif_display.c +++ b/drivers/media/video/davinci/vpif_display.c @@ -1426,7 +1426,6 @@ static __init int vpif_probe(struct platform_device *pdev) struct vpif_display_config *config; int i, j = 0, k, q, m, err = 0; struct i2c_adapter *i2c_adap; - struct vpif_config *config; struct common_obj *common; struct channel_obj *ch; struct video_device *vfd; diff --git a/drivers/media/video/em28xx/em28xx-cards.c b/drivers/media/video/em28xx/em28xx-cards.c index bdb249bd9d5d..c0fd5c6feeac 100644 --- a/drivers/media/video/em28xx/em28xx-cards.c +++ b/drivers/media/video/em28xx/em28xx-cards.c @@ -1584,8 +1584,8 @@ struct em28xx_board em28xx_boards[] = { [EM2870_BOARD_REDDO_DVB_C_USB_BOX] = { .name = "Reddo DVB-C USB TV Box", .tuner_type = TUNER_ABSENT, + .tuner_gpio = reddo_dvb_c_usb_box, .has_dvb = 1, - .dvb_gpio = reddo_dvb_c_usb_box, }, }; const unsigned int em28xx_bcount = ARRAY_SIZE(em28xx_boards); diff --git a/drivers/media/video/mx1_camera.c b/drivers/media/video/mx1_camera.c index 5f37952c75cf..72802291e812 100644 --- a/drivers/media/video/mx1_camera.c +++ b/drivers/media/video/mx1_camera.c @@ -28,6 +28,7 @@ #include <linux/moduleparam.h> #include <linux/mutex.h> #include <linux/platform_device.h> +#include <linux/sched.h> #include <linux/time.h> #include <linux/version.h> #include <linux/videodev2.h> diff --git a/drivers/media/video/mx3_camera.c b/drivers/media/video/mx3_camera.c index dff2e5e2d8c6..7db82bdf6f31 100644 --- a/drivers/media/video/mx3_camera.c +++ b/drivers/media/video/mx3_camera.c @@ -17,6 +17,7 @@ #include <linux/clk.h> #include <linux/vmalloc.h> #include <linux/interrupt.h> +#include <linux/sched.h> #include <media/v4l2-common.h> #include <media/v4l2-dev.h> diff --git a/drivers/media/video/sh_mobile_ceu_camera.c b/drivers/media/video/sh_mobile_ceu_camera.c index 2f78b4f263f5..9c8b7c7b89ee 100644 --- a/drivers/media/video/sh_mobile_ceu_camera.c +++ b/drivers/media/video/sh_mobile_ceu_camera.c @@ -31,6 +31,7 @@ #include <linux/platform_device.h> #include <linux/videodev2.h> #include <linux/pm_runtime.h> +#include <linux/sched.h> #include <media/v4l2-common.h> #include <media/v4l2-dev.h> @@ -1723,11 +1724,12 @@ static int __devinit sh_mobile_ceu_probe(struct platform_device *pdev) err = soc_camera_host_register(&pcdev->ici); if (err) - goto exit_free_irq; + goto exit_free_clk; return 0; -exit_free_irq: +exit_free_clk: + pm_runtime_disable(&pdev->dev); free_irq(pcdev->irq, pcdev); exit_release_mem: if (platform_get_resource(pdev, IORESOURCE_MEM, 1)) @@ -1747,6 +1749,7 @@ static int __devexit sh_mobile_ceu_remove(struct platform_device *pdev) struct sh_mobile_ceu_dev, ici); soc_camera_host_unregister(soc_host); + pm_runtime_disable(&pdev->dev); free_irq(pcdev->irq, pcdev); if (platform_get_resource(pdev, IORESOURCE_MEM, 1)) dma_release_declared_memory(&pdev->dev); diff --git a/drivers/media/video/soc_camera.c b/drivers/media/video/soc_camera.c index 36e617bd13c7..95fdeb23c2c1 100644 --- a/drivers/media/video/soc_camera.c +++ b/drivers/media/video/soc_camera.c @@ -1097,6 +1097,13 @@ static int default_s_crop(struct soc_camera_device *icd, struct v4l2_crop *a) return v4l2_subdev_call(sd, video, s_crop, a); } +static void soc_camera_device_init(struct device *dev, void *pdata) +{ + dev->platform_data = pdata; + dev->bus = &soc_camera_bus_type; + dev->release = dummy_release; +} + int soc_camera_host_register(struct soc_camera_host *ici) { struct soc_camera_host *ix; @@ -1158,6 +1165,7 @@ void soc_camera_host_unregister(struct soc_camera_host *ici) list_for_each_entry(icd, &devices, list) { if (icd->iface == ici->nr) { + void *pdata = icd->dev.platform_data; /* The bus->remove will be called */ device_unregister(&icd->dev); /* @@ -1169,6 +1177,7 @@ void soc_camera_host_unregister(struct soc_camera_host *ici) * device private data. */ memset(&icd->dev, 0, sizeof(icd->dev)); + soc_camera_device_init(&icd->dev, pdata); } } @@ -1200,10 +1209,7 @@ static int soc_camera_device_register(struct soc_camera_device *icd) * man, stay reasonable... */ return -ENOMEM; - icd->devnum = num; - icd->dev.bus = &soc_camera_bus_type; - - icd->dev.release = dummy_release; + icd->devnum = num; icd->use_count = 0; icd->host_priv = NULL; mutex_init(&icd->video_lock); @@ -1311,12 +1317,13 @@ static int __devinit soc_camera_pdrv_probe(struct platform_device *pdev) icd->iface = icl->bus_id; icd->pdev = &pdev->dev; platform_set_drvdata(pdev, icd); - icd->dev.platform_data = icl; ret = soc_camera_device_register(icd); if (ret < 0) goto escdevreg; + soc_camera_device_init(&icd->dev, icl); + icd->user_width = DEFAULT_WIDTH; icd->user_height = DEFAULT_HEIGHT; diff --git a/drivers/media/video/videobuf-dma-contig.c b/drivers/media/video/videobuf-dma-contig.c index 635ffc7b0391..c3065c4bcba9 100644 --- a/drivers/media/video/videobuf-dma-contig.c +++ b/drivers/media/video/videobuf-dma-contig.c @@ -19,6 +19,7 @@ #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/dma-mapping.h> +#include <linux/sched.h> #include <media/videobuf-dma-contig.h> struct videobuf_dma_contig_memory { diff --git a/drivers/mfd/wm831x-core.c b/drivers/mfd/wm831x-core.c index 49b7885c2702..7f27576ca046 100644 --- a/drivers/mfd/wm831x-core.c +++ b/drivers/mfd/wm831x-core.c @@ -29,7 +29,7 @@ /* Current settings - values are 2*2^(reg_val/4) microamps. These are * exported since they are used by multiple drivers. */ -int wm831x_isinkv_values[WM831X_ISINK_MAX_ISEL] = { +int wm831x_isinkv_values[WM831X_ISINK_MAX_ISEL + 1] = { 2, 2, 3, diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c index db39f4a52f53..2cb2736d65aa 100644 --- a/drivers/misc/eeprom/at24.c +++ b/drivers/misc/eeprom/at24.c @@ -158,6 +158,7 @@ static ssize_t at24_eeprom_read(struct at24_data *at24, char *buf, struct i2c_msg msg[2]; u8 msgbuf[2]; struct i2c_client *client; + unsigned long timeout, read_time; int status, i; memset(msg, 0, sizeof(msg)); @@ -183,47 +184,60 @@ static ssize_t at24_eeprom_read(struct at24_data *at24, char *buf, if (count > io_limit) count = io_limit; - /* Smaller eeproms can work given some SMBus extension calls */ if (at24->use_smbus) { + /* Smaller eeproms can work given some SMBus extension calls */ if (count > I2C_SMBUS_BLOCK_MAX) count = I2C_SMBUS_BLOCK_MAX; - status = i2c_smbus_read_i2c_block_data(client, offset, - count, buf); - dev_dbg(&client->dev, "smbus read %zu@%d --> %d\n", - count, offset, status); - return (status < 0) ? -EIO : status; + } else { + /* + * When we have a better choice than SMBus calls, use a + * combined I2C message. Write address; then read up to + * io_limit data bytes. Note that read page rollover helps us + * here (unlike writes). msgbuf is u8 and will cast to our + * needs. + */ + i = 0; + if (at24->chip.flags & AT24_FLAG_ADDR16) + msgbuf[i++] = offset >> 8; + msgbuf[i++] = offset; + + msg[0].addr = client->addr; + msg[0].buf = msgbuf; + msg[0].len = i; + + msg[1].addr = client->addr; + msg[1].flags = I2C_M_RD; + msg[1].buf = buf; + msg[1].len = count; } /* - * When we have a better choice than SMBus calls, use a combined - * I2C message. Write address; then read up to io_limit data bytes. - * Note that read page rollover helps us here (unlike writes). - * msgbuf is u8 and will cast to our needs. + * Reads fail if the previous write didn't complete yet. We may + * loop a few times until this one succeeds, waiting at least + * long enough for one entire page write to work. */ - i = 0; - if (at24->chip.flags & AT24_FLAG_ADDR16) - msgbuf[i++] = offset >> 8; - msgbuf[i++] = offset; - - msg[0].addr = client->addr; - msg[0].buf = msgbuf; - msg[0].len = i; + timeout = jiffies + msecs_to_jiffies(write_timeout); + do { + read_time = jiffies; + if (at24->use_smbus) { + status = i2c_smbus_read_i2c_block_data(client, offset, + count, buf); + } else { + status = i2c_transfer(client->adapter, msg, 2); + if (status == 2) + status = count; + } + dev_dbg(&client->dev, "read %zu@%d --> %d (%ld)\n", + count, offset, status, jiffies); - msg[1].addr = client->addr; - msg[1].flags = I2C_M_RD; - msg[1].buf = buf; - msg[1].len = count; + if (status == count) + return count; - status = i2c_transfer(client->adapter, msg, 2); - dev_dbg(&client->dev, "i2c read %zu@%d --> %d\n", - count, offset, status); + /* REVISIT: at HZ=100, this is sloooow */ + msleep(1); + } while (time_before(read_time, timeout)); - if (status == 2) - return count; - else if (status >= 0) - return -EIO; - else - return status; + return -ETIMEDOUT; } static ssize_t at24_read(struct at24_data *at24, diff --git a/drivers/misc/sgi-xp/xpc_main.c b/drivers/misc/sgi-xp/xpc_main.c index fd3688a3e23f..832ed4c88cf7 100644 --- a/drivers/misc/sgi-xp/xpc_main.c +++ b/drivers/misc/sgi-xp/xpc_main.c @@ -89,48 +89,40 @@ static int xpc_disengage_max_timelimit = 120; static ctl_table xpc_sys_xpc_hb_dir[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "hb_interval", .data = &xpc_hb_interval, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &xpc_hb_min_interval, .extra2 = &xpc_hb_max_interval}, { - .ctl_name = CTL_UNNUMBERED, .procname = "hb_check_interval", .data = &xpc_hb_check_interval, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &xpc_hb_check_min_interval, .extra2 = &xpc_hb_check_max_interval}, {} }; static ctl_table xpc_sys_xpc_dir[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "hb", .mode = 0555, .child = xpc_sys_xpc_hb_dir}, { - .ctl_name = CTL_UNNUMBERED, .procname = "disengage_timelimit", .data = &xpc_disengage_timelimit, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &xpc_disengage_min_timelimit, .extra2 = &xpc_disengage_max_timelimit}, {} }; static ctl_table xpc_sys_dir[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "xpc", .mode = 0555, .child = xpc_sys_xpc_dir}, diff --git a/drivers/misc/sgi-xp/xpc_uv.c b/drivers/misc/sgi-xp/xpc_uv.c index c76677afda1b..b5bbe59f9c57 100644 --- a/drivers/misc/sgi-xp/xpc_uv.c +++ b/drivers/misc/sgi-xp/xpc_uv.c @@ -106,7 +106,8 @@ xpc_get_gru_mq_irq_uv(struct xpc_gru_mq_uv *mq, int cpu, char *irq_name) int mmr_pnode = uv_blade_to_pnode(mq->mmr_blade); #if defined CONFIG_X86_64 - mq->irq = uv_setup_irq(irq_name, cpu, mq->mmr_blade, mq->mmr_offset); + mq->irq = uv_setup_irq(irq_name, cpu, mq->mmr_blade, mq->mmr_offset, + UV_AFFINITY_CPU); if (mq->irq < 0) { dev_err(xpc_part, "uv_setup_irq() returned error=%d\n", -mq->irq); @@ -136,7 +137,7 @@ static void xpc_release_gru_mq_irq_uv(struct xpc_gru_mq_uv *mq) { #if defined CONFIG_X86_64 - uv_teardown_irq(mq->irq, mq->mmr_blade, mq->mmr_offset); + uv_teardown_irq(mq->irq); #elif defined CONFIG_IA64_GENERIC || defined CONFIG_IA64_SGI_UV int mmr_pnode; diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c index b00d67319058..9fb480bb0e0a 100644 --- a/drivers/mmc/host/pxamci.c +++ b/drivers/mmc/host/pxamci.c @@ -760,6 +760,8 @@ static int pxamci_remove(struct platform_device *pdev) if (mmc) { struct pxamci_host *host = mmc_priv(mmc); + mmc_remove_host(mmc); + if (host->pdata) { gpio_cd = host->pdata->gpio_card_detect; gpio_ro = host->pdata->gpio_card_ro; @@ -779,8 +781,6 @@ static int pxamci_remove(struct platform_device *pdev) if (host->pdata && host->pdata->exit) host->pdata->exit(&pdev->dev, mmc); - mmc_remove_host(mmc); - pxamci_stop_clock(host); writel(TXFIFO_WR_REQ|RXFIFO_RD_REQ|CLK_IS_OFF|STOP_CMD| END_CMD_RES|PRG_DONE|DATA_TRAN_DONE, diff --git a/drivers/mtd/maps/pcmciamtd.c b/drivers/mtd/maps/pcmciamtd.c index d600c2deff73..689d6a79ffc0 100644 --- a/drivers/mtd/maps/pcmciamtd.c +++ b/drivers/mtd/maps/pcmciamtd.c @@ -118,11 +118,9 @@ static caddr_t remap_window(struct map_info *map, unsigned long to) DEBUG(2, "Remapping window from 0x%8.8x to 0x%8.8x", dev->offset, mrq.CardOffset); mrq.Page = 0; - ret = pcmcia_map_mem_page(win, &mrq); - if (ret != 0) { - cs_error(dev->p_dev, MapMemPage, ret); + ret = pcmcia_map_mem_page(dev->p_dev, win, &mrq); + if (ret != 0) return NULL; - } dev->offset = mrq.CardOffset; } return dev->win_base + (to & (dev->win_size-1)); @@ -327,8 +325,6 @@ static void pcmciamtd_set_vpp(struct map_info *map, int on) DEBUG(2, "dev = %p on = %d vpp = %d\n", dev, on, dev->vpp); ret = pcmcia_modify_configuration(link, &mod); - if (ret != 0) - cs_error(link, ModifyConfiguration, ret); } @@ -348,107 +344,116 @@ static void pcmciamtd_release(struct pcmcia_device *link) iounmap(dev->win_base); dev->win_base = NULL; } - pcmcia_release_window(link->win); + pcmcia_release_window(link, link->win); } pcmcia_disable_device(link); } -static void card_settings(struct pcmciamtd_dev *dev, struct pcmcia_device *link, int *new_name) +#ifdef CONFIG_MTD_DEBUG +static int pcmciamtd_cistpl_format(struct pcmcia_device *p_dev, + tuple_t *tuple, + void *priv_data) { - int rc; - tuple_t tuple; cisparse_t parse; - u_char buf[64]; - - tuple.Attributes = 0; - tuple.TupleData = (cisdata_t *)buf; - tuple.TupleDataMax = sizeof(buf); - tuple.TupleOffset = 0; - tuple.DesiredTuple = RETURN_FIRST_TUPLE; - - rc = pcmcia_get_first_tuple(link, &tuple); - while (rc == 0) { - rc = pcmcia_get_tuple_data(link, &tuple); - if (rc != 0) { - cs_error(link, GetTupleData, rc); - break; - } - rc = pcmcia_parse_tuple(&tuple, &parse); - if (rc != 0) { - cs_error(link, ParseTuple, rc); - break; - } - switch(tuple.TupleCode) { - case CISTPL_FORMAT: { - cistpl_format_t *t = &parse.format; - (void)t; /* Shut up, gcc */ - DEBUG(2, "Format type: %u, Error Detection: %u, offset = %u, length =%u", - t->type, t->edc, t->offset, t->length); - break; + if (!pcmcia_parse_tuple(tuple, &parse)) { + cistpl_format_t *t = &parse.format; + (void)t; /* Shut up, gcc */ + DEBUG(2, "Format type: %u, Error Detection: %u, offset = %u, length =%u", + t->type, t->edc, t->offset, t->length); + } + return -ENOSPC; +} - } +static int pcmciamtd_cistpl_jedec(struct pcmcia_device *p_dev, + tuple_t *tuple, + void *priv_data) +{ + cisparse_t parse; + int i; - case CISTPL_DEVICE: { - cistpl_device_t *t = &parse.device; - int i; - DEBUG(2, "Common memory:"); - dev->pcmcia_map.size = t->dev[0].size; - for(i = 0; i < t->ndev; i++) { - DEBUG(2, "Region %d, type = %u", i, t->dev[i].type); - DEBUG(2, "Region %d, wp = %u", i, t->dev[i].wp); - DEBUG(2, "Region %d, speed = %u ns", i, t->dev[i].speed); - DEBUG(2, "Region %d, size = %u bytes", i, t->dev[i].size); - } - break; - } + if (!pcmcia_parse_tuple(tuple, &parse)) { + cistpl_jedec_t *t = &parse.jedec; + for (i = 0; i < t->nid; i++) + DEBUG(2, "JEDEC: 0x%02x 0x%02x", t->id[i].mfr, t->id[i].info); + } + return -ENOSPC; +} +#endif - case CISTPL_VERS_1: { - cistpl_vers_1_t *t = &parse.version_1; - int i; - if(t->ns) { - dev->mtd_name[0] = '\0'; - for(i = 0; i < t->ns; i++) { - if(i) - strcat(dev->mtd_name, " "); - strcat(dev->mtd_name, t->str+t->ofs[i]); - } - } - DEBUG(2, "Found name: %s", dev->mtd_name); - break; - } +static int pcmciamtd_cistpl_device(struct pcmcia_device *p_dev, + tuple_t *tuple, + void *priv_data) +{ + struct pcmciamtd_dev *dev = priv_data; + cisparse_t parse; + cistpl_device_t *t = &parse.device; + int i; - case CISTPL_JEDEC_C: { - cistpl_jedec_t *t = &parse.jedec; - int i; - for(i = 0; i < t->nid; i++) { - DEBUG(2, "JEDEC: 0x%02x 0x%02x", t->id[i].mfr, t->id[i].info); - } - break; - } + if (pcmcia_parse_tuple(tuple, &parse)) + return -EINVAL; + + DEBUG(2, "Common memory:"); + dev->pcmcia_map.size = t->dev[0].size; + /* from here on: DEBUG only */ + for (i = 0; i < t->ndev; i++) { + DEBUG(2, "Region %d, type = %u", i, t->dev[i].type); + DEBUG(2, "Region %d, wp = %u", i, t->dev[i].wp); + DEBUG(2, "Region %d, speed = %u ns", i, t->dev[i].speed); + DEBUG(2, "Region %d, size = %u bytes", i, t->dev[i].size); + } + return 0; +} - case CISTPL_DEVICE_GEO: { - cistpl_device_geo_t *t = &parse.device_geo; - int i; - dev->pcmcia_map.bankwidth = t->geo[0].buswidth; - for(i = 0; i < t->ngeo; i++) { - DEBUG(2, "region: %d bankwidth = %u", i, t->geo[i].buswidth); - DEBUG(2, "region: %d erase_block = %u", i, t->geo[i].erase_block); - DEBUG(2, "region: %d read_block = %u", i, t->geo[i].read_block); - DEBUG(2, "region: %d write_block = %u", i, t->geo[i].write_block); - DEBUG(2, "region: %d partition = %u", i, t->geo[i].partition); - DEBUG(2, "region: %d interleave = %u", i, t->geo[i].interleave); - } - break; - } +static int pcmciamtd_cistpl_geo(struct pcmcia_device *p_dev, + tuple_t *tuple, + void *priv_data) +{ + struct pcmciamtd_dev *dev = priv_data; + cisparse_t parse; + cistpl_device_geo_t *t = &parse.device_geo; + int i; - default: - DEBUG(2, "Unknown tuple code %d", tuple.TupleCode); - } + if (pcmcia_parse_tuple(tuple, &parse)) + return -EINVAL; + + dev->pcmcia_map.bankwidth = t->geo[0].buswidth; + /* from here on: DEBUG only */ + for (i = 0; i < t->ngeo; i++) { + DEBUG(2, "region: %d bankwidth = %u", i, t->geo[i].buswidth); + DEBUG(2, "region: %d erase_block = %u", i, t->geo[i].erase_block); + DEBUG(2, "region: %d read_block = %u", i, t->geo[i].read_block); + DEBUG(2, "region: %d write_block = %u", i, t->geo[i].write_block); + DEBUG(2, "region: %d partition = %u", i, t->geo[i].partition); + DEBUG(2, "region: %d interleave = %u", i, t->geo[i].interleave); + } + return 0; +} + + +static void card_settings(struct pcmciamtd_dev *dev, struct pcmcia_device *link, int *new_name) +{ + int i; - rc = pcmcia_get_next_tuple(link, &tuple); + if (p_dev->prod_id[0]) { + dev->mtd_name[0] = '\0'; + for (i = 0; i < 4; i++) { + if (i) + strcat(dev->mtd_name, " "); + if (p_dev->prod_id[i]) + strcat(dev->mtd_name, p_dev->prod_id[i]); + } + DEBUG(2, "Found name: %s", dev->mtd_name); } + +#ifdef CONFIG_MTD_DEBUG + pcmcia_loop_tuple(p_dev, CISTPL_FORMAT, pcmciamtd_cistpl_format, NULL); + pcmcia_loop_tuple(p_dev, CISTPL_JEDEC_C, pcmciamtd_cistpl_jedec, NULL); +#endif + pcmcia_loop_tuple(p_dev, CISTPL_DEVICE, pcmciamtd_cistpl_device, dev); + pcmcia_loop_tuple(p_dev, CISTPL_DEVICE_GEO, pcmciamtd_cistpl_geo, dev); + if(!dev->pcmcia_map.size) dev->pcmcia_map.size = MAX_PCMCIA_ADDR; @@ -481,16 +486,12 @@ static void card_settings(struct pcmciamtd_dev *dev, struct pcmcia_device *link, * MTD device available to the system. */ -#define CS_CHECK(fn, ret) \ -do { last_fn = (fn); if ((last_ret = (ret)) != 0) goto cs_failed; } while (0) - static int pcmciamtd_config(struct pcmcia_device *link) { struct pcmciamtd_dev *dev = link->priv; struct mtd_info *mtd = NULL; cs_status_t status; win_req_t req; - int last_ret = 0, last_fn = 0; int ret; int i; static char *probes[] = { "jedec_probe", "cfi_probe" }; @@ -529,7 +530,7 @@ static int pcmciamtd_config(struct pcmcia_device *link) int ret; DEBUG(2, "requesting window with size = %dKiB memspeed = %d", req.Size >> 10, req.AccessSpeed); - ret = pcmcia_request_window(&link, &req, &link->win); + ret = pcmcia_request_window(link, &req, &link->win); DEBUG(2, "ret = %d dev->win_size = %d", ret, dev->win_size); if(ret) { req.Size >>= 1; @@ -577,7 +578,6 @@ static int pcmciamtd_config(struct pcmcia_device *link) DEBUG(2, "Setting Configuration"); ret = pcmcia_request_configuration(link, &link->conf); if (ret != 0) { - cs_error(link, RequestConfiguration, ret); if (dev->win_base) { iounmap(dev->win_base); dev->win_base = NULL; @@ -652,8 +652,7 @@ static int pcmciamtd_config(struct pcmcia_device *link) link->dev_node = &dev->node; return 0; - cs_failed: - cs_error(link, last_fn, last_ret); + failed: err("CS Error, exiting"); pcmciamtd_release(link); return -ENODEV; diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index e19ca4bb7510..b2f71f79baaf 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -975,7 +975,7 @@ config ENC28J60_WRITEVERIFY config ETHOC tristate "OpenCores 10/100 Mbps Ethernet MAC support" - depends on NET_ETHERNET && HAS_IOMEM + depends on NET_ETHERNET && HAS_IOMEM && HAS_DMA select MII select PHYLIB select CRC32 diff --git a/drivers/net/arm/ep93xx_eth.c b/drivers/net/arm/ep93xx_eth.c index 2be49c817995..b25467ac895c 100644 --- a/drivers/net/arm/ep93xx_eth.c +++ b/drivers/net/arm/ep93xx_eth.c @@ -628,15 +628,6 @@ static int ep93xx_open(struct net_device *dev) if (ep93xx_alloc_buffers(ep)) return -ENOMEM; - if (is_zero_ether_addr(dev->dev_addr)) { - random_ether_addr(dev->dev_addr); - printk(KERN_INFO "%s: generated random MAC address " - "%.2x:%.2x:%.2x:%.2x:%.2x:%.2x.\n", dev->name, - dev->dev_addr[0], dev->dev_addr[1], - dev->dev_addr[2], dev->dev_addr[3], - dev->dev_addr[4], dev->dev_addr[5]); - } - napi_enable(&ep->napi); if (ep93xx_start_hw(dev)) { @@ -877,6 +868,9 @@ static int ep93xx_eth_probe(struct platform_device *pdev) ep->mii.mdio_write = ep93xx_mdio_write; ep->mdc_divisor = 40; /* Max HCLK 100 MHz, min MDIO clk 2.5 MHz. */ + if (is_zero_ether_addr(dev->dev_addr)) + random_ether_addr(dev->dev_addr); + err = register_netdev(dev); if (err) { dev_err(&pdev->dev, "Failed to register netdev\n"); diff --git a/drivers/net/au1000_eth.c b/drivers/net/au1000_eth.c index ce6f1ac25df8..3f4b4300f533 100644 --- a/drivers/net/au1000_eth.c +++ b/drivers/net/au1000_eth.c @@ -1088,7 +1088,14 @@ static struct net_device * au1000_probe(int port_num) return NULL; } - if ((err = register_netdev(dev)) != 0) { + dev->base_addr = base; + dev->irq = irq; + dev->netdev_ops = &au1000_netdev_ops; + SET_ETHTOOL_OPS(dev, &au1000_ethtool_ops); + dev->watchdog_timeo = ETH_TX_TIMEOUT; + + err = register_netdev(dev); + if (err != 0) { printk(KERN_ERR "%s: Cannot register net device, error %d\n", DRV_NAME, err); free_netdev(dev); @@ -1209,12 +1216,6 @@ static struct net_device * au1000_probe(int port_num) aup->tx_db_inuse[i] = pDB; } - dev->base_addr = base; - dev->irq = irq; - dev->netdev_ops = &au1000_netdev_ops; - SET_ETHTOOL_OPS(dev, &au1000_ethtool_ops); - dev->watchdog_timeo = ETH_TX_TIMEOUT; - /* * The boot code uses the ethernet controller, so reset it to start * fresh. au1000_init() expects that the device is in reset state. diff --git a/drivers/net/b44.c b/drivers/net/b44.c index e046943ef29d..2a9132343b66 100644 --- a/drivers/net/b44.c +++ b/drivers/net/b44.c @@ -912,9 +912,6 @@ static irqreturn_t b44_interrupt(int irq, void *dev_id) bp->istat = istat; __b44_disable_ints(bp); __napi_schedule(&bp->napi); - } else { - printk(KERN_ERR PFX "%s: Error, poll already scheduled\n", - dev->name); } irq_ack: diff --git a/drivers/net/davinci_emac.c b/drivers/net/davinci_emac.c index db6380379478..e3478314c002 100644 --- a/drivers/net/davinci_emac.c +++ b/drivers/net/davinci_emac.c @@ -164,16 +164,14 @@ static const char emac_version_string[] = "TI DaVinci EMAC Linux v6.1"; # define EMAC_MBP_MCASTCHAN(ch) ((ch) & 0x7) /* EMAC mac_control register */ -#define EMAC_MACCONTROL_TXPTYPE (0x200) -#define EMAC_MACCONTROL_TXPACEEN (0x40) -#define EMAC_MACCONTROL_MIIEN (0x20) -#define EMAC_MACCONTROL_GIGABITEN (0x80) -#define EMAC_MACCONTROL_GIGABITEN_SHIFT (7) -#define EMAC_MACCONTROL_FULLDUPLEXEN (0x1) +#define EMAC_MACCONTROL_TXPTYPE BIT(9) +#define EMAC_MACCONTROL_TXPACEEN BIT(6) +#define EMAC_MACCONTROL_GMIIEN BIT(5) +#define EMAC_MACCONTROL_GIGABITEN BIT(7) +#define EMAC_MACCONTROL_FULLDUPLEXEN BIT(0) #define EMAC_MACCONTROL_RMIISPEED_MASK BIT(15) /* GIGABIT MODE related bits */ -#define EMAC_DM646X_MACCONTORL_GMIIEN BIT(5) #define EMAC_DM646X_MACCONTORL_GIG BIT(7) #define EMAC_DM646X_MACCONTORL_GIGFORCE BIT(17) @@ -192,10 +190,10 @@ static const char emac_version_string[] = "TI DaVinci EMAC Linux v6.1"; #define EMAC_RX_BUFFER_OFFSET_MASK (0xFFFF) /* MAC_IN_VECTOR (0x180) register bit fields */ -#define EMAC_DM644X_MAC_IN_VECTOR_HOST_INT (0x20000) -#define EMAC_DM644X_MAC_IN_VECTOR_STATPEND_INT (0x10000) -#define EMAC_DM644X_MAC_IN_VECTOR_RX_INT_VEC (0x0100) -#define EMAC_DM644X_MAC_IN_VECTOR_TX_INT_VEC (0x01) +#define EMAC_DM644X_MAC_IN_VECTOR_HOST_INT BIT(17) +#define EMAC_DM644X_MAC_IN_VECTOR_STATPEND_INT BIT(16) +#define EMAC_DM644X_MAC_IN_VECTOR_RX_INT_VEC BIT(8) +#define EMAC_DM644X_MAC_IN_VECTOR_TX_INT_VEC BIT(0) /** NOTE:: For DM646x the IN_VECTOR has changed */ #define EMAC_DM646X_MAC_IN_VECTOR_RX_INT_VEC BIT(EMAC_DEF_RX_CH) @@ -203,7 +201,6 @@ static const char emac_version_string[] = "TI DaVinci EMAC Linux v6.1"; #define EMAC_DM646X_MAC_IN_VECTOR_HOST_INT BIT(26) #define EMAC_DM646X_MAC_IN_VECTOR_STATPEND_INT BIT(27) - /* CPPI bit positions */ #define EMAC_CPPI_SOP_BIT BIT(31) #define EMAC_CPPI_EOP_BIT BIT(30) @@ -750,8 +747,7 @@ static void emac_update_phystatus(struct emac_priv *priv) if (priv->speed == SPEED_1000 && (priv->version == EMAC_VERSION_2)) { mac_control = emac_read(EMAC_MACCONTROL); - mac_control |= (EMAC_DM646X_MACCONTORL_GMIIEN | - EMAC_DM646X_MACCONTORL_GIG | + mac_control |= (EMAC_DM646X_MACCONTORL_GIG | EMAC_DM646X_MACCONTORL_GIGFORCE); } else { /* Clear the GIG bit and GIGFORCE bit */ @@ -2108,7 +2104,7 @@ static int emac_hw_enable(struct emac_priv *priv) /* Enable MII */ val = emac_read(EMAC_MACCONTROL); - val |= (EMAC_MACCONTROL_MIIEN); + val |= (EMAC_MACCONTROL_GMIIEN); emac_write(EMAC_MACCONTROL, val); /* Enable NAPI and interrupts */ diff --git a/drivers/net/e100.c b/drivers/net/e100.c index 3c29a20b751e..d269a68ce354 100644 --- a/drivers/net/e100.c +++ b/drivers/net/e100.c @@ -157,6 +157,7 @@ #include <linux/init.h> #include <linux/pci.h> #include <linux/dma-mapping.h> +#include <linux/dmapool.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/mii.h> @@ -602,6 +603,7 @@ struct nic { struct mem *mem; dma_addr_t dma_addr; + struct pci_pool *cbs_pool; dma_addr_t cbs_dma_addr; u8 adaptive_ifs; u8 tx_threshold; @@ -1793,9 +1795,7 @@ static void e100_clean_cbs(struct nic *nic) nic->cb_to_clean = nic->cb_to_clean->next; nic->cbs_avail++; } - pci_free_consistent(nic->pdev, - sizeof(struct cb) * nic->params.cbs.count, - nic->cbs, nic->cbs_dma_addr); + pci_pool_free(nic->cbs_pool, nic->cbs, nic->cbs_dma_addr); nic->cbs = NULL; nic->cbs_avail = 0; } @@ -1813,8 +1813,8 @@ static int e100_alloc_cbs(struct nic *nic) nic->cb_to_use = nic->cb_to_send = nic->cb_to_clean = NULL; nic->cbs_avail = 0; - nic->cbs = pci_alloc_consistent(nic->pdev, - sizeof(struct cb) * count, &nic->cbs_dma_addr); + nic->cbs = pci_pool_alloc(nic->cbs_pool, GFP_KERNEL, + &nic->cbs_dma_addr); if (!nic->cbs) return -ENOMEM; @@ -2841,7 +2841,11 @@ static int __devinit e100_probe(struct pci_dev *pdev, DPRINTK(PROBE, ERR, "Cannot register net device, aborting.\n"); goto err_out_free; } - + nic->cbs_pool = pci_pool_create(netdev->name, + nic->pdev, + nic->params.cbs.count * sizeof(struct cb), + sizeof(u32), + 0); DPRINTK(PROBE, INFO, "addr 0x%llx, irq %d, MAC addr %pM\n", (unsigned long long)pci_resource_start(pdev, use_io ? 1 : 0), pdev->irq, netdev->dev_addr); @@ -2871,6 +2875,7 @@ static void __devexit e100_remove(struct pci_dev *pdev) unregister_netdev(netdev); e100_free(nic); pci_iounmap(pdev, nic->csr); + pci_pool_destroy(nic->cbs_pool); free_netdev(netdev); pci_release_regions(pdev); pci_disable_device(pdev); diff --git a/drivers/net/e1000e/e1000.h b/drivers/net/e1000e/e1000.h index 189dfa2d6c76..3e187b0e4203 100644 --- a/drivers/net/e1000e/e1000.h +++ b/drivers/net/e1000e/e1000.h @@ -141,6 +141,8 @@ struct e1000_info; #define HV_TNCRS_UPPER PHY_REG(778, 29) /* Transmit with no CRS */ #define HV_TNCRS_LOWER PHY_REG(778, 30) +#define E1000_FCRTV_PCH 0x05F40 /* PCH Flow Control Refresh Timer Value */ + /* BM PHY Copper Specific Status */ #define BM_CS_STATUS 17 #define BM_CS_STATUS_LINK_UP 0x0400 diff --git a/drivers/net/e1000e/ethtool.c b/drivers/net/e1000e/ethtool.c index 1bf4d2a5d34f..e82638ecae88 100644 --- a/drivers/net/e1000e/ethtool.c +++ b/drivers/net/e1000e/ethtool.c @@ -327,10 +327,18 @@ static int e1000_set_pauseparam(struct net_device *netdev, hw->fc.current_mode = hw->fc.requested_mode; - retval = ((hw->phy.media_type == e1000_media_type_fiber) ? - hw->mac.ops.setup_link(hw) : e1000e_force_mac_fc(hw)); + if (hw->phy.media_type == e1000_media_type_fiber) { + retval = hw->mac.ops.setup_link(hw); + /* implicit goto out */ + } else { + retval = e1000e_force_mac_fc(hw); + if (retval) + goto out; + e1000e_set_fc_watermarks(hw); + } } +out: clear_bit(__E1000_RESETTING, &adapter->state); return retval; } diff --git a/drivers/net/e1000e/ich8lan.c b/drivers/net/e1000e/ich8lan.c index 51ddb04ab195..eff3f4783655 100644 --- a/drivers/net/e1000e/ich8lan.c +++ b/drivers/net/e1000e/ich8lan.c @@ -1118,7 +1118,8 @@ static s32 e1000_oem_bits_config_ich8lan(struct e1000_hw *hw, bool d0_state) oem_reg |= HV_OEM_BITS_LPLU; } /* Restart auto-neg to activate the bits */ - oem_reg |= HV_OEM_BITS_RESTART_AN; + if (!e1000_check_reset_block(hw)) + oem_reg |= HV_OEM_BITS_RESTART_AN; ret_val = hw->phy.ops.write_phy_reg_locked(hw, HV_OEM_BITS, oem_reg); out: @@ -3558,6 +3559,7 @@ struct e1000_info e1000_pch_info = { | FLAG_HAS_AMT | FLAG_HAS_FLASH | FLAG_HAS_JUMBO_FRAMES + | FLAG_DISABLE_FC_PAUSE_TIME /* errata */ | FLAG_APME_IN_WUC, .pba = 26, .max_hw_frame_size = 4096, diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c index 0687c6aa4e46..fad8f9ea0043 100644 --- a/drivers/net/e1000e/netdev.c +++ b/drivers/net/e1000e/netdev.c @@ -2769,25 +2769,38 @@ void e1000e_reset(struct e1000_adapter *adapter) /* * flow control settings * - * The high water mark must be low enough to fit two full frame + * The high water mark must be low enough to fit one full frame * (or the size used for early receive) above it in the Rx FIFO. * Set it to the lower of: * - 90% of the Rx FIFO size, and * - the full Rx FIFO size minus the early receive size (for parts * with ERT support assuming ERT set to E1000_ERT_2048), or - * - the full Rx FIFO size minus two full frames + * - the full Rx FIFO size minus one full frame */ - if ((adapter->flags & FLAG_HAS_ERT) && - (adapter->netdev->mtu > ETH_DATA_LEN)) - hwm = min(((pba << 10) * 9 / 10), - ((pba << 10) - (E1000_ERT_2048 << 3))); - else - hwm = min(((pba << 10) * 9 / 10), - ((pba << 10) - (2 * adapter->max_frame_size))); + if (hw->mac.type == e1000_pchlan) { + /* + * Workaround PCH LOM adapter hangs with certain network + * loads. If hangs persist, try disabling Tx flow control. + */ + if (adapter->netdev->mtu > ETH_DATA_LEN) { + fc->high_water = 0x3500; + fc->low_water = 0x1500; + } else { + fc->high_water = 0x5000; + fc->low_water = 0x3000; + } + } else { + if ((adapter->flags & FLAG_HAS_ERT) && + (adapter->netdev->mtu > ETH_DATA_LEN)) + hwm = min(((pba << 10) * 9 / 10), + ((pba << 10) - (E1000_ERT_2048 << 3))); + else + hwm = min(((pba << 10) * 9 / 10), + ((pba << 10) - adapter->max_frame_size)); - fc->high_water = hwm & E1000_FCRTH_RTH; /* 8-byte granularity */ - fc->low_water = (fc->high_water - (2 * adapter->max_frame_size)); - fc->low_water &= E1000_FCRTL_RTL; /* 8-byte granularity */ + fc->high_water = hwm & E1000_FCRTH_RTH; /* 8-byte granularity */ + fc->low_water = fc->high_water - 8; + } if (adapter->flags & FLAG_DISABLE_FC_PAUSE_TIME) fc->pause_time = 0xFFFF; @@ -2813,6 +2826,10 @@ void e1000e_reset(struct e1000_adapter *adapter) if (mac->ops.init_hw(hw)) e_err("Hardware Error\n"); + /* additional part of the flow-control workaround above */ + if (hw->mac.type == e1000_pchlan) + ew32(FCRTV_PCH, 0x1000); + e1000_update_mng_vlan(adapter); /* Enable h/w to recognize an 802.1Q VLAN Ethernet packet */ @@ -3610,7 +3627,7 @@ static void e1000_watchdog_task(struct work_struct *work) case SPEED_100: txb2b = 0; netdev->tx_queue_len = 100; - /* maybe add some timeout factor ? */ + adapter->tx_timeout_factor = 10; break; } @@ -4288,8 +4305,10 @@ static int e1000_change_mtu(struct net_device *netdev, int new_mtu) while (test_and_set_bit(__E1000_RESETTING, &adapter->state)) msleep(1); - /* e1000e_down has a dependency on max_frame_size */ + /* e1000e_down -> e1000e_reset dependent on max_frame_size & mtu */ adapter->max_frame_size = max_frame; + e_info("changing MTU from %d to %d\n", netdev->mtu, new_mtu); + netdev->mtu = new_mtu; if (netif_running(netdev)) e1000e_down(adapter); @@ -4319,9 +4338,6 @@ static int e1000_change_mtu(struct net_device *netdev, int new_mtu) adapter->rx_buffer_len = ETH_FRAME_LEN + VLAN_HLEN + ETH_FCS_LEN; - e_info("changing MTU from %d to %d\n", netdev->mtu, new_mtu); - netdev->mtu = new_mtu; - if (netif_running(netdev)) e1000e_up(adapter); else diff --git a/drivers/net/e1000e/phy.c b/drivers/net/e1000e/phy.c index 03175b3a2c9e..85f955f70417 100644 --- a/drivers/net/e1000e/phy.c +++ b/drivers/net/e1000e/phy.c @@ -71,7 +71,6 @@ static const u16 e1000_igp_2_cable_length_table[] = #define I82577_CFG_ASSERT_CRS_ON_TX (1 << 15) #define I82577_CFG_ENABLE_DOWNSHIFT (3 << 10) /* auto downshift 100/10 */ #define I82577_CTRL_REG 23 -#define I82577_CTRL_DOWNSHIFT_MASK (7 << 10) /* 82577 specific PHY registers */ #define I82577_PHY_CTRL_2 18 @@ -660,15 +659,6 @@ s32 e1000_copper_link_setup_82577(struct e1000_hw *hw) phy_data |= I82577_CFG_ENABLE_DOWNSHIFT; ret_val = phy->ops.write_phy_reg(hw, I82577_CFG_REG, phy_data); - if (ret_val) - goto out; - - /* Set number of link attempts before downshift */ - ret_val = phy->ops.read_phy_reg(hw, I82577_CTRL_REG, &phy_data); - if (ret_val) - goto out; - phy_data &= ~I82577_CTRL_DOWNSHIFT_MASK; - ret_val = phy->ops.write_phy_reg(hw, I82577_CTRL_REG, phy_data); out: return ret_val; @@ -2658,19 +2648,18 @@ static s32 __e1000_read_phy_reg_hv(struct e1000_hw *hw, u32 offset, u16 *data, page = 0; if (reg > MAX_PHY_MULTI_PAGE_REG) { - if ((hw->phy.type != e1000_phy_82578) || - ((reg != I82578_ADDR_REG) && - (reg != I82578_ADDR_REG + 1))) { - u32 phy_addr = hw->phy.addr; + u32 phy_addr = hw->phy.addr; - hw->phy.addr = 1; + hw->phy.addr = 1; - /* Page is shifted left, PHY expects (page x 32) */ - ret_val = e1000e_write_phy_reg_mdic(hw, - IGP01E1000_PHY_PAGE_SELECT, - (page << IGP_PAGE_SHIFT)); - hw->phy.addr = phy_addr; - } + /* Page is shifted left, PHY expects (page x 32) */ + ret_val = e1000e_write_phy_reg_mdic(hw, + IGP01E1000_PHY_PAGE_SELECT, + (page << IGP_PAGE_SHIFT)); + hw->phy.addr = phy_addr; + + if (ret_val) + goto out; } ret_val = e1000e_read_phy_reg_mdic(hw, MAX_PHY_REG_ADDRESS & reg, @@ -2678,7 +2667,7 @@ static s32 __e1000_read_phy_reg_hv(struct e1000_hw *hw, u32 offset, u16 *data, out: /* Revert to MDIO fast mode, if applicable */ if ((hw->phy.type == e1000_phy_82577) && in_slow_mode) - ret_val = e1000_set_mdio_slow_mode_hv(hw, false); + ret_val |= e1000_set_mdio_slow_mode_hv(hw, false); if (!locked) hw->phy.ops.release_phy(hw); @@ -2784,19 +2773,18 @@ static s32 __e1000_write_phy_reg_hv(struct e1000_hw *hw, u32 offset, u16 data, } if (reg > MAX_PHY_MULTI_PAGE_REG) { - if ((hw->phy.type != e1000_phy_82578) || - ((reg != I82578_ADDR_REG) && - (reg != I82578_ADDR_REG + 1))) { - u32 phy_addr = hw->phy.addr; + u32 phy_addr = hw->phy.addr; - hw->phy.addr = 1; + hw->phy.addr = 1; - /* Page is shifted left, PHY expects (page x 32) */ - ret_val = e1000e_write_phy_reg_mdic(hw, - IGP01E1000_PHY_PAGE_SELECT, - (page << IGP_PAGE_SHIFT)); - hw->phy.addr = phy_addr; - } + /* Page is shifted left, PHY expects (page x 32) */ + ret_val = e1000e_write_phy_reg_mdic(hw, + IGP01E1000_PHY_PAGE_SELECT, + (page << IGP_PAGE_SHIFT)); + hw->phy.addr = phy_addr; + + if (ret_val) + goto out; } ret_val = e1000e_write_phy_reg_mdic(hw, MAX_PHY_REG_ADDRESS & reg, @@ -2805,7 +2793,7 @@ static s32 __e1000_write_phy_reg_hv(struct e1000_hw *hw, u32 offset, u16 data, out: /* Revert to MDIO fast mode, if applicable */ if ((hw->phy.type == e1000_phy_82577) && in_slow_mode) - ret_val = e1000_set_mdio_slow_mode_hv(hw, false); + ret_val |= e1000_set_mdio_slow_mode_hv(hw, false); if (!locked) hw->phy.ops.release_phy(hw); diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c index a5036f7c1923..a456578b8578 100644 --- a/drivers/net/ixgbe/ixgbe_main.c +++ b/drivers/net/ixgbe/ixgbe_main.c @@ -240,11 +240,11 @@ static void ixgbe_unmap_and_free_tx_resource(struct ixgbe_adapter *adapter, static inline bool ixgbe_tx_is_paused(struct ixgbe_adapter *adapter, struct ixgbe_ring *tx_ring) { - int tc; u32 txoff = IXGBE_TFCS_TXOFF; #ifdef CONFIG_IXGBE_DCB if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) { + int tc; int reg_idx = tx_ring->reg_idx; int dcb_i = adapter->ring_feature[RING_F_DCB].indices; diff --git a/drivers/net/ks8851_mll.c b/drivers/net/ks8851_mll.c index 0be14d702beb..c146304d8d6c 100644 --- a/drivers/net/ks8851_mll.c +++ b/drivers/net/ks8851_mll.c @@ -568,6 +568,16 @@ static inline void ks_outblk(struct ks_net *ks, u16 *wptr, u32 len) iowrite16(*wptr++, ks->hw_addr); } +static void ks_disable_int(struct ks_net *ks) +{ + ks_wrreg16(ks, KS_IER, 0x0000); +} /* ks_disable_int */ + +static void ks_enable_int(struct ks_net *ks) +{ + ks_wrreg16(ks, KS_IER, ks->rc_ier); +} /* ks_enable_int */ + /** * ks_tx_fifo_space - return the available hardware buffer size. * @ks: The chip information @@ -681,6 +691,47 @@ static void ks_soft_reset(struct ks_net *ks, unsigned op) } +void ks_enable_qmu(struct ks_net *ks) +{ + u16 w; + + w = ks_rdreg16(ks, KS_TXCR); + /* Enables QMU Transmit (TXCR). */ + ks_wrreg16(ks, KS_TXCR, w | TXCR_TXE); + + /* + * RX Frame Count Threshold Enable and Auto-Dequeue RXQ Frame + * Enable + */ + + w = ks_rdreg16(ks, KS_RXQCR); + ks_wrreg16(ks, KS_RXQCR, w | RXQCR_RXFCTE); + + /* Enables QMU Receive (RXCR1). */ + w = ks_rdreg16(ks, KS_RXCR1); + ks_wrreg16(ks, KS_RXCR1, w | RXCR1_RXE); + ks->enabled = true; +} /* ks_enable_qmu */ + +static void ks_disable_qmu(struct ks_net *ks) +{ + u16 w; + + w = ks_rdreg16(ks, KS_TXCR); + + /* Disables QMU Transmit (TXCR). */ + w &= ~TXCR_TXE; + ks_wrreg16(ks, KS_TXCR, w); + + /* Disables QMU Receive (RXCR1). */ + w = ks_rdreg16(ks, KS_RXCR1); + w &= ~RXCR1_RXE ; + ks_wrreg16(ks, KS_RXCR1, w); + + ks->enabled = false; + +} /* ks_disable_qmu */ + /** * ks_read_qmu - read 1 pkt data from the QMU. * @ks: The chip information @@ -752,7 +803,7 @@ static void ks_rcv(struct ks_net *ks, struct net_device *netdev) (frame_hdr->len < RX_BUF_SIZE) && frame_hdr->len)) { skb_reserve(skb, 2); /* read data block including CRC 4 bytes */ - ks_read_qmu(ks, (u16 *)skb->data, frame_hdr->len + 4); + ks_read_qmu(ks, (u16 *)skb->data, frame_hdr->len); skb_put(skb, frame_hdr->len); skb->dev = netdev; skb->protocol = eth_type_trans(skb, netdev); @@ -861,7 +912,7 @@ static int ks_net_open(struct net_device *netdev) ks_dbg(ks, "%s - entry\n", __func__); /* reset the HW */ - err = request_irq(ks->irq, ks_irq, KS_INT_FLAGS, DRV_NAME, ks); + err = request_irq(ks->irq, ks_irq, KS_INT_FLAGS, DRV_NAME, netdev); if (err) { printk(KERN_ERR "Failed to request IRQ: %d: %d\n", @@ -869,6 +920,15 @@ static int ks_net_open(struct net_device *netdev) return err; } + /* wake up powermode to normal mode */ + ks_set_powermode(ks, PMECR_PM_NORMAL); + mdelay(1); /* wait for normal mode to take effect */ + + ks_wrreg16(ks, KS_ISR, 0xffff); + ks_enable_int(ks); + ks_enable_qmu(ks); + netif_start_queue(ks->netdev); + if (netif_msg_ifup(ks)) ks_dbg(ks, "network device %s up\n", netdev->name); @@ -892,19 +952,14 @@ static int ks_net_stop(struct net_device *netdev) netif_stop_queue(netdev); - kfree(ks->frame_head_info); - mutex_lock(&ks->lock); /* turn off the IRQs and ack any outstanding */ ks_wrreg16(ks, KS_IER, 0x0000); ks_wrreg16(ks, KS_ISR, 0xffff); - /* shutdown RX process */ - ks_wrreg16(ks, KS_RXCR1, 0x0000); - - /* shutdown TX process */ - ks_wrreg16(ks, KS_TXCR, 0x0000); + /* shutdown RX/TX QMU */ + ks_disable_qmu(ks); /* set powermode to soft power down to save power */ ks_set_powermode(ks, PMECR_PM_SOFTDOWN); @@ -929,17 +984,8 @@ static int ks_net_stop(struct net_device *netdev) */ static void ks_write_qmu(struct ks_net *ks, u8 *pdata, u16 len) { - unsigned fid = ks->fid; - - fid = ks->fid; - ks->fid = (ks->fid + 1) & TXFR_TXFID_MASK; - - /* reduce the tx interrupt occurrances. */ - if (!fid) - fid |= TXFR_TXIC; /* irq on completion */ - /* start header at txb[0] to align txw entries */ - ks->txh.txw[0] = cpu_to_le16(fid); + ks->txh.txw[0] = 0; ks->txh.txw[1] = cpu_to_le16(len); /* 1. set sudo-DMA mode */ @@ -957,16 +1003,6 @@ static void ks_write_qmu(struct ks_net *ks, u8 *pdata, u16 len) ; } -static void ks_disable_int(struct ks_net *ks) -{ - ks_wrreg16(ks, KS_IER, 0x0000); -} /* ks_disable_int */ - -static void ks_enable_int(struct ks_net *ks) -{ - ks_wrreg16(ks, KS_IER, ks->rc_ier); -} /* ks_enable_int */ - /** * ks_start_xmit - transmit packet * @skb : The buffer to transmit @@ -1410,25 +1446,6 @@ static int ks_read_selftest(struct ks_net *ks) return ret; } -static void ks_disable(struct ks_net *ks) -{ - u16 w; - - w = ks_rdreg16(ks, KS_TXCR); - - /* Disables QMU Transmit (TXCR). */ - w &= ~TXCR_TXE; - ks_wrreg16(ks, KS_TXCR, w); - - /* Disables QMU Receive (RXCR1). */ - w = ks_rdreg16(ks, KS_RXCR1); - w &= ~RXCR1_RXE ; - ks_wrreg16(ks, KS_RXCR1, w); - - ks->enabled = false; - -} /* ks_disable */ - static void ks_setup(struct ks_net *ks) { u16 w; @@ -1463,7 +1480,7 @@ static void ks_setup(struct ks_net *ks) w = TXCR_TXFCE | TXCR_TXPE | TXCR_TXCRC | TXCR_TCGIP; ks_wrreg16(ks, KS_TXCR, w); - w = RXCR1_RXFCE | RXCR1_RXBE | RXCR1_RXUE; + w = RXCR1_RXFCE | RXCR1_RXBE | RXCR1_RXUE | RXCR1_RXME | RXCR1_RXIPFCC; if (ks->promiscuous) /* bPromiscuous */ w |= (RXCR1_RXAE | RXCR1_RXINVF); @@ -1486,28 +1503,6 @@ static void ks_setup_int(struct ks_net *ks) ks->rc_ier = (IRQ_LCI | IRQ_TXI | IRQ_RXI); } /* ks_setup_int */ -void ks_enable(struct ks_net *ks) -{ - u16 w; - - w = ks_rdreg16(ks, KS_TXCR); - /* Enables QMU Transmit (TXCR). */ - ks_wrreg16(ks, KS_TXCR, w | TXCR_TXE); - - /* - * RX Frame Count Threshold Enable and Auto-Dequeue RXQ Frame - * Enable - */ - - w = ks_rdreg16(ks, KS_RXQCR); - ks_wrreg16(ks, KS_RXQCR, w | RXQCR_RXFCTE); - - /* Enables QMU Receive (RXCR1). */ - w = ks_rdreg16(ks, KS_RXCR1); - ks_wrreg16(ks, KS_RXCR1, w | RXCR1_RXE); - ks->enabled = true; -} /* ks_enable */ - static int ks_hw_init(struct ks_net *ks) { #define MHEADER_SIZE (sizeof(struct type_frame_head) * MAX_RECV_FRAMES) @@ -1612,11 +1607,9 @@ static int __devinit ks8851_probe(struct platform_device *pdev) ks_soft_reset(ks, GRR_GSR); ks_hw_init(ks); - ks_disable(ks); + ks_disable_qmu(ks); ks_setup(ks); ks_setup_int(ks); - ks_enable_int(ks); - ks_enable(ks); memcpy(netdev->dev_addr, ks->mac_addr, 6); data = ks_rdreg16(ks, KS_OBCR); @@ -1658,6 +1651,7 @@ static int __devexit ks8851_remove(struct platform_device *pdev) struct ks_net *ks = netdev_priv(netdev); struct resource *iomem = platform_get_resource(pdev, IORESOURCE_MEM, 0); + kfree(ks->frame_head_info); unregister_netdev(netdev); iounmap(ks->hw_addr); free_netdev(netdev); diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 3aabfd9dd212..2490aa39804c 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -360,6 +360,7 @@ static int macvlan_init(struct net_device *dev) dev->state = (dev->state & ~MACVLAN_STATE_MASK) | (lowerdev->state & MACVLAN_STATE_MASK); dev->features = lowerdev->features & MACVLAN_FEATURES; + dev->gso_max_size = lowerdev->gso_max_size; dev->iflink = lowerdev->ifindex; dev->hard_header_len = lowerdev->hard_header_len; @@ -596,6 +597,7 @@ static int macvlan_device_event(struct notifier_block *unused, case NETDEV_FEAT_CHANGE: list_for_each_entry(vlan, &port->vlans, list) { vlan->dev->features = dev->features & MACVLAN_FEATURES; + vlan->dev->gso_max_size = dev->gso_max_size; netdev_features_change(vlan->dev); } break; diff --git a/drivers/net/netxen/netxen_nic.h b/drivers/net/netxen/netxen_nic.h index 7384f59df615..e1237b802872 100644 --- a/drivers/net/netxen/netxen_nic.h +++ b/drivers/net/netxen/netxen_nic.h @@ -1163,6 +1163,8 @@ struct netxen_adapter { u32 int_vec_bit; u32 heartbit; + u8 mac_addr[ETH_ALEN]; + struct netxen_adapter_stats stats; struct netxen_recv_context recv_ctx; diff --git a/drivers/net/netxen/netxen_nic_hdr.h b/drivers/net/netxen/netxen_nic_hdr.h index 1c46da632125..17bb3818d84e 100644 --- a/drivers/net/netxen/netxen_nic_hdr.h +++ b/drivers/net/netxen/netxen_nic_hdr.h @@ -545,6 +545,8 @@ enum { #define NETXEN_NIU_TEST_MUX_CTL (NETXEN_CRB_NIU + 0x00094) #define NETXEN_NIU_XG_PAUSE_CTL (NETXEN_CRB_NIU + 0x00098) #define NETXEN_NIU_XG_PAUSE_LEVEL (NETXEN_CRB_NIU + 0x000dc) +#define NETXEN_NIU_FRAME_COUNT_SELECT (NETXEN_CRB_NIU + 0x000ac) +#define NETXEN_NIU_FRAME_COUNT (NETXEN_CRB_NIU + 0x000b0) #define NETXEN_NIU_XG_SEL (NETXEN_CRB_NIU + 0x00128) #define NETXEN_NIU_GB_PAUSE_CTL (NETXEN_CRB_NIU + 0x0030c) diff --git a/drivers/net/netxen/netxen_nic_hw.c b/drivers/net/netxen/netxen_nic_hw.c index 3185a98b0917..52a3798d8d94 100644 --- a/drivers/net/netxen/netxen_nic_hw.c +++ b/drivers/net/netxen/netxen_nic_hw.c @@ -383,24 +383,51 @@ int netxen_niu_disable_xg_port(struct netxen_adapter *adapter) int netxen_p2_nic_set_promisc(struct netxen_adapter *adapter, u32 mode) { - __u32 reg; + u32 mac_cfg; + u32 cnt = 0; + __u32 reg = 0x0200; u32 port = adapter->physical_port; + u16 board_type = adapter->ahw.board_type; if (port > NETXEN_NIU_MAX_XG_PORTS) return -EINVAL; - reg = NXRD32(adapter, NETXEN_NIU_XGE_CONFIG_1 + (0x10000 * port)); - if (mode == NETXEN_NIU_PROMISC_MODE) - reg = (reg | 0x2000UL); - else - reg = (reg & ~0x2000UL); + mac_cfg = NXRD32(adapter, NETXEN_NIU_XGE_CONFIG_0 + (0x10000 * port)); + mac_cfg &= ~0x4; + NXWR32(adapter, NETXEN_NIU_XGE_CONFIG_0 + (0x10000 * port), mac_cfg); - if (mode == NETXEN_NIU_ALLMULTI_MODE) - reg = (reg | 0x1000UL); - else - reg = (reg & ~0x1000UL); + if ((board_type == NETXEN_BRDTYPE_P2_SB31_10G_IMEZ) || + (board_type == NETXEN_BRDTYPE_P2_SB31_10G_HMEZ)) + reg = (0x20 << port); + + NXWR32(adapter, NETXEN_NIU_FRAME_COUNT_SELECT, reg); + + mdelay(10); + + while (NXRD32(adapter, NETXEN_NIU_FRAME_COUNT) && ++cnt < 20) + mdelay(10); + + if (cnt < 20) { + + reg = NXRD32(adapter, + NETXEN_NIU_XGE_CONFIG_1 + (0x10000 * port)); + + if (mode == NETXEN_NIU_PROMISC_MODE) + reg = (reg | 0x2000UL); + else + reg = (reg & ~0x2000UL); + + if (mode == NETXEN_NIU_ALLMULTI_MODE) + reg = (reg | 0x1000UL); + else + reg = (reg & ~0x1000UL); + + NXWR32(adapter, + NETXEN_NIU_XGE_CONFIG_1 + (0x10000 * port), reg); + } - NXWR32(adapter, NETXEN_NIU_XGE_CONFIG_1 + (0x10000 * port), reg); + mac_cfg |= 0x4; + NXWR32(adapter, NETXEN_NIU_XGE_CONFIG_0 + (0x10000 * port), mac_cfg); return 0; } @@ -436,7 +463,7 @@ netxen_nic_enable_mcast_filter(struct netxen_adapter *adapter) { u32 val = 0; u16 port = adapter->physical_port; - u8 *addr = adapter->netdev->dev_addr; + u8 *addr = adapter->mac_addr; if (adapter->mc_enabled) return 0; @@ -465,7 +492,7 @@ netxen_nic_disable_mcast_filter(struct netxen_adapter *adapter) { u32 val = 0; u16 port = adapter->physical_port; - u8 *addr = adapter->netdev->dev_addr; + u8 *addr = adapter->mac_addr; if (!adapter->mc_enabled) return 0; @@ -660,7 +687,7 @@ void netxen_p3_nic_set_multi(struct net_device *netdev) list_splice_tail_init(&adapter->mac_list, &del_list); - nx_p3_nic_add_mac(adapter, netdev->dev_addr, &del_list); + nx_p3_nic_add_mac(adapter, adapter->mac_addr, &del_list); nx_p3_nic_add_mac(adapter, bcast_addr, &del_list); if (netdev->flags & IFF_PROMISC) { diff --git a/drivers/net/netxen/netxen_nic_init.c b/drivers/net/netxen/netxen_nic_init.c index e40b914d6faf..8a0904368e08 100644 --- a/drivers/net/netxen/netxen_nic_init.c +++ b/drivers/net/netxen/netxen_nic_init.c @@ -544,6 +544,8 @@ int netxen_pinit_from_rom(struct netxen_adapter *adapter, int verbose) continue; if (off == (ROMUSB_GLB + 0x1c)) /* MS clock */ continue; + if ((off & 0x0ff00000) == NETXEN_CRB_DDR_NET) + continue; if (off == (NETXEN_CRB_PEG_NET_1 + 0x18)) buf[i].data = 0x1020; /* skip the function enable register */ diff --git a/drivers/net/netxen/netxen_nic_main.c b/drivers/net/netxen/netxen_nic_main.c index 0b4a56a8c8d5..3bf78dbfbf0f 100644 --- a/drivers/net/netxen/netxen_nic_main.c +++ b/drivers/net/netxen/netxen_nic_main.c @@ -437,6 +437,7 @@ netxen_read_mac_addr(struct netxen_adapter *adapter) netdev->dev_addr[i] = *(p + 5 - i); memcpy(netdev->perm_addr, netdev->dev_addr, netdev->addr_len); + memcpy(adapter->mac_addr, netdev->dev_addr, netdev->addr_len); /* set station address */ @@ -459,6 +460,7 @@ int netxen_nic_set_mac(struct net_device *netdev, void *p) netxen_napi_disable(adapter); } + memcpy(adapter->mac_addr, addr->sa_data, netdev->addr_len); memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len); adapter->macaddr_set(adapter, addr->sa_data); @@ -956,7 +958,7 @@ netxen_nic_up(struct netxen_adapter *adapter, struct net_device *netdev) return err; } if (NX_IS_REVISION_P2(adapter->ahw.revision_id)) - adapter->macaddr_set(adapter, netdev->dev_addr); + adapter->macaddr_set(adapter, adapter->mac_addr); adapter->set_multi(netdev); adapter->set_mtu(adapter, netdev->mtu); diff --git a/drivers/net/pcmcia/3c574_cs.c b/drivers/net/pcmcia/3c574_cs.c index b58965a2b3ae..17a27225cc98 100644 --- a/drivers/net/pcmcia/3c574_cs.c +++ b/drivers/net/pcmcia/3c574_cs.c @@ -118,14 +118,6 @@ INT_MODULE_PARM(full_duplex, 0); /* Autodetect link polarity reversal? */ INT_MODULE_PARM(auto_polarity, 1); -#ifdef PCMCIA_DEBUG -INT_MODULE_PARM(pc_debug, PCMCIA_DEBUG); -#define DEBUG(n, args...) if (pc_debug>(n)) printk(KERN_DEBUG args) -static char *version = -"3c574_cs.c 1.65ac1 2003/04/07 Donald Becker/David Hinds, becker@scyld.com.\n"; -#else -#define DEBUG(n, args...) -#endif /*====================================================================*/ @@ -278,7 +270,7 @@ static int tc574_probe(struct pcmcia_device *link) struct el3_private *lp; struct net_device *dev; - DEBUG(0, "3c574_attach()\n"); + dev_dbg(&link->dev, "3c574_attach()\n"); /* Create the PC card device object. */ dev = alloc_etherdev(sizeof(struct el3_private)); @@ -291,10 +283,8 @@ static int tc574_probe(struct pcmcia_device *link) spin_lock_init(&lp->window_lock); link->io.NumPorts1 = 32; link->io.Attributes1 = IO_DATA_PATH_WIDTH_16; - link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING|IRQ_HANDLE_PRESENT; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; + link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; link->irq.Handler = &el3_interrupt; - link->irq.Instance = dev; link->conf.Attributes = CONF_ENABLE_IRQ; link->conf.IntType = INT_MEMORY_AND_IO; link->conf.ConfigIndex = 1; @@ -319,7 +309,7 @@ static void tc574_detach(struct pcmcia_device *link) { struct net_device *dev = link->priv; - DEBUG(0, "3c574_detach(0x%p)\n", link); + dev_dbg(&link->dev, "3c574_detach()\n"); if (link->dev_node) unregister_netdev(dev); @@ -335,26 +325,23 @@ static void tc574_detach(struct pcmcia_device *link) ethernet device available to the system. */ -#define CS_CHECK(fn, ret) \ - do { last_fn = (fn); if ((last_ret = (ret)) != 0) goto cs_failed; } while (0) - static const char *ram_split[] = {"5:3", "3:1", "1:1", "3:5"}; static int tc574_config(struct pcmcia_device *link) { struct net_device *dev = link->priv; struct el3_private *lp = netdev_priv(dev); - tuple_t tuple; - __le16 buf[32]; - int last_fn, last_ret, i, j; + int ret, i, j; unsigned int ioaddr; __be16 *phys_addr; char *cardname; __u32 config; + u8 *buf; + size_t len; phys_addr = (__be16 *)dev->dev_addr; - DEBUG(0, "3c574_config(0x%p)\n", link); + dev_dbg(&link->dev, "3c574_config()\n"); link->io.IOAddrLines = 16; for (i = j = 0; j < 0x400; j += 0x20) { @@ -363,12 +350,16 @@ static int tc574_config(struct pcmcia_device *link) if (i == 0) break; } - if (i != 0) { - cs_error(link, RequestIO, i); + if (i != 0) + goto failed; + + ret = pcmcia_request_irq(link, &link->irq); + if (ret) + goto failed; + + ret = pcmcia_request_configuration(link, &link->conf); + if (ret) goto failed; - } - CS_CHECK(RequestIRQ, pcmcia_request_irq(link, &link->irq)); - CS_CHECK(RequestConfiguration, pcmcia_request_configuration(link, &link->conf)); dev->irq = link->irq.AssignedIRQ; dev->base_addr = link->io.BasePort1; @@ -378,16 +369,14 @@ static int tc574_config(struct pcmcia_device *link) /* The 3c574 normally uses an EEPROM for configuration info, including the hardware address. The future products may include a modem chip and put the address in the CIS. */ - tuple.Attributes = 0; - tuple.TupleData = (cisdata_t *)buf; - tuple.TupleDataMax = 64; - tuple.TupleOffset = 0; - tuple.DesiredTuple = 0x88; - if (pcmcia_get_first_tuple(link, &tuple) == 0) { - pcmcia_get_tuple_data(link, &tuple); + + len = pcmcia_get_tuple(link, 0x88, &buf); + if (buf && len >= 6) { for (i = 0; i < 3; i++) - phys_addr[i] = htons(le16_to_cpu(buf[i])); + phys_addr[i] = htons(le16_to_cpu(buf[i * 2])); + kfree(buf); } else { + kfree(buf); /* 0 < len < 6 */ EL3WINDOW(0); for (i = 0; i < 3; i++) phys_addr[i] = htons(read_eeprom(ioaddr, i + 10)); @@ -435,7 +424,8 @@ static int tc574_config(struct pcmcia_device *link) mii_status = mdio_read(ioaddr, phy & 0x1f, 1); if (mii_status != 0xffff) { lp->phys = phy & 0x1f; - DEBUG(0, " MII transceiver at index %d, status %x.\n", + dev_dbg(&link->dev, " MII transceiver at " + "index %d, status %x.\n", phy, mii_status); if ((mii_status & 0x0040) == 0) mii_preamble_required = 1; @@ -457,7 +447,7 @@ static int tc574_config(struct pcmcia_device *link) } link->dev_node = &lp->node; - SET_NETDEV_DEV(dev, &handle_to_dev(link)); + SET_NETDEV_DEV(dev, &link->dev); if (register_netdev(dev) != 0) { printk(KERN_NOTICE "3c574_cs: register_netdev() failed\n"); @@ -478,8 +468,6 @@ static int tc574_config(struct pcmcia_device *link) return 0; -cs_failed: - cs_error(link, last_fn, last_ret); failed: tc574_release(link); return -ENODEV; @@ -738,7 +726,7 @@ static int el3_open(struct net_device *dev) lp->media.expires = jiffies + HZ; add_timer(&lp->media); - DEBUG(2, "%s: opened, status %4.4x.\n", + dev_dbg(&link->dev, "%s: opened, status %4.4x.\n", dev->name, inw(dev->base_addr + EL3_STATUS)); return 0; @@ -772,7 +760,7 @@ static void pop_tx_status(struct net_device *dev) if (tx_status & 0x30) tc574_wait_for_completion(dev, TxReset); if (tx_status & 0x38) { - DEBUG(1, "%s: transmit error: status 0x%02x\n", + pr_debug("%s: transmit error: status 0x%02x\n", dev->name, tx_status); outw(TxEnable, ioaddr + EL3_CMD); dev->stats.tx_aborted_errors++; @@ -788,7 +776,7 @@ static netdev_tx_t el3_start_xmit(struct sk_buff *skb, struct el3_private *lp = netdev_priv(dev); unsigned long flags; - DEBUG(3, "%s: el3_start_xmit(length = %ld) called, " + pr_debug("%s: el3_start_xmit(length = %ld) called, " "status %4.4x.\n", dev->name, (long)skb->len, inw(ioaddr + EL3_STATUS)); @@ -827,7 +815,7 @@ static irqreturn_t el3_interrupt(int irq, void *dev_id) return IRQ_NONE; ioaddr = dev->base_addr; - DEBUG(3, "%s: interrupt, status %4.4x.\n", + pr_debug("%s: interrupt, status %4.4x.\n", dev->name, inw(ioaddr + EL3_STATUS)); spin_lock(&lp->window_lock); @@ -836,7 +824,7 @@ static irqreturn_t el3_interrupt(int irq, void *dev_id) (IntLatch | RxComplete | RxEarly | StatsFull)) { if (!netif_device_present(dev) || ((status & 0xe000) != 0x2000)) { - DEBUG(1, "%s: Interrupt from dead card\n", dev->name); + pr_debug("%s: Interrupt from dead card\n", dev->name); break; } @@ -846,7 +834,7 @@ static irqreturn_t el3_interrupt(int irq, void *dev_id) work_budget = el3_rx(dev, work_budget); if (status & TxAvailable) { - DEBUG(3, " TX room bit was handled.\n"); + pr_debug(" TX room bit was handled.\n"); /* There's room in the FIFO for a full-sized packet. */ outw(AckIntr | TxAvailable, ioaddr + EL3_CMD); netif_wake_queue(dev); @@ -886,7 +874,7 @@ static irqreturn_t el3_interrupt(int irq, void *dev_id) } if (--work_budget < 0) { - DEBUG(0, "%s: Too much work in interrupt, " + pr_debug("%s: Too much work in interrupt, " "status %4.4x.\n", dev->name, status); /* Clear all interrupts */ outw(AckIntr | 0xFF, ioaddr + EL3_CMD); @@ -896,7 +884,7 @@ static irqreturn_t el3_interrupt(int irq, void *dev_id) outw(AckIntr | IntReq | IntLatch, ioaddr + EL3_CMD); } - DEBUG(3, "%s: exiting interrupt, status %4.4x.\n", + pr_debug("%s: exiting interrupt, status %4.4x.\n", dev->name, inw(ioaddr + EL3_STATUS)); spin_unlock(&lp->window_lock); @@ -1003,7 +991,7 @@ static void update_stats(struct net_device *dev) unsigned int ioaddr = dev->base_addr; u8 rx, tx, up; - DEBUG(2, "%s: updating the statistics.\n", dev->name); + pr_debug("%s: updating the statistics.\n", dev->name); if (inw(ioaddr+EL3_STATUS) == 0xffff) /* No card. */ return; @@ -1039,7 +1027,7 @@ static int el3_rx(struct net_device *dev, int worklimit) unsigned int ioaddr = dev->base_addr; short rx_status; - DEBUG(3, "%s: in rx_packet(), status %4.4x, rx_status %4.4x.\n", + pr_debug("%s: in rx_packet(), status %4.4x, rx_status %4.4x.\n", dev->name, inw(ioaddr+EL3_STATUS), inw(ioaddr+RxStatus)); while (!((rx_status = inw(ioaddr + RxStatus)) & 0x8000) && worklimit > 0) { @@ -1061,7 +1049,7 @@ static int el3_rx(struct net_device *dev, int worklimit) skb = dev_alloc_skb(pkt_len+5); - DEBUG(3, " Receiving packet size %d status %4.4x.\n", + pr_debug(" Receiving packet size %d status %4.4x.\n", pkt_len, rx_status); if (skb != NULL) { skb_reserve(skb, 2); @@ -1072,7 +1060,7 @@ static int el3_rx(struct net_device *dev, int worklimit) dev->stats.rx_packets++; dev->stats.rx_bytes += pkt_len; } else { - DEBUG(1, "%s: couldn't allocate a sk_buff of" + pr_debug("%s: couldn't allocate a sk_buff of" " size %d.\n", dev->name, pkt_len); dev->stats.rx_dropped++; } @@ -1101,7 +1089,7 @@ static int el3_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) struct mii_ioctl_data *data = if_mii(rq); int phy = lp->phys & 0x1f; - DEBUG(2, "%s: In ioct(%-.6s, %#4.4x) %4.4x %4.4x %4.4x %4.4x.\n", + pr_debug("%s: In ioct(%-.6s, %#4.4x) %4.4x %4.4x %4.4x %4.4x.\n", dev->name, rq->ifr_ifrn.ifrn_name, cmd, data->phy_id, data->reg_num, data->val_in, data->val_out); @@ -1178,7 +1166,7 @@ static int el3_close(struct net_device *dev) struct el3_private *lp = netdev_priv(dev); struct pcmcia_device *link = lp->p_dev; - DEBUG(2, "%s: shutting down ethercard.\n", dev->name); + dev_dbg(&link->dev, "%s: shutting down ethercard.\n", dev->name); if (pcmcia_dev_present(link)) { unsigned long flags; diff --git a/drivers/net/pcmcia/3c589_cs.c b/drivers/net/pcmcia/3c589_cs.c index 569fb06793cf..6f8d7e2e5922 100644 --- a/drivers/net/pcmcia/3c589_cs.c +++ b/drivers/net/pcmcia/3c589_cs.c @@ -130,14 +130,6 @@ MODULE_LICENSE("GPL"); /* Special hook for setting if_port when module is loaded */ INT_MODULE_PARM(if_port, 0); -#ifdef PCMCIA_DEBUG -INT_MODULE_PARM(pc_debug, PCMCIA_DEBUG); -#define DEBUG(n, args...) if (pc_debug>(n)) printk(KERN_DEBUG args) -static char *version = -DRV_NAME ".c " DRV_VERSION " 2001/10/13 00:08:50 (David Hinds)"; -#else -#define DEBUG(n, args...) -#endif /*====================================================================*/ @@ -189,7 +181,7 @@ static int tc589_probe(struct pcmcia_device *link) struct el3_private *lp; struct net_device *dev; - DEBUG(0, "3c589_attach()\n"); + dev_dbg(&link->dev, "3c589_attach()\n"); /* Create new ethernet device */ dev = alloc_etherdev(sizeof(struct el3_private)); @@ -202,10 +194,8 @@ static int tc589_probe(struct pcmcia_device *link) spin_lock_init(&lp->lock); link->io.NumPorts1 = 16; link->io.Attributes1 = IO_DATA_PATH_WIDTH_16; - link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING|IRQ_HANDLE_PRESENT; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; + link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; link->irq.Handler = &el3_interrupt; - link->irq.Instance = dev; link->conf.Attributes = CONF_ENABLE_IRQ; link->conf.IntType = INT_MEMORY_AND_IO; link->conf.ConfigIndex = 1; @@ -231,7 +221,7 @@ static void tc589_detach(struct pcmcia_device *link) { struct net_device *dev = link->priv; - DEBUG(0, "3c589_detach(0x%p)\n", link); + dev_dbg(&link->dev, "3c589_detach\n"); if (link->dev_node) unregister_netdev(dev); @@ -249,29 +239,20 @@ static void tc589_detach(struct pcmcia_device *link) ======================================================================*/ -#define CS_CHECK(fn, ret) \ -do { last_fn = (fn); if ((last_ret = (ret)) != 0) goto cs_failed; } while (0) - static int tc589_config(struct pcmcia_device *link) { struct net_device *dev = link->priv; struct el3_private *lp = netdev_priv(dev); - tuple_t tuple; - __le16 buf[32]; __be16 *phys_addr; - int last_fn, last_ret, i, j, multi = 0, fifo; + int ret, i, j, multi = 0, fifo; unsigned int ioaddr; char *ram_split[] = {"5:3", "3:1", "1:1", "3:5"}; + u8 *buf; + size_t len; - DEBUG(0, "3c589_config(0x%p)\n", link); + dev_dbg(&link->dev, "3c589_config\n"); phys_addr = (__be16 *)dev->dev_addr; - tuple.Attributes = 0; - tuple.TupleData = (cisdata_t *)buf; - tuple.TupleDataMax = sizeof(buf); - tuple.TupleOffset = 0; - tuple.Attributes = TUPLE_RETURN_COMMON; - /* Is this a 3c562? */ if (link->manf_id != MANFID_3COM) printk(KERN_INFO "3c589_cs: hmmm, is this really a " @@ -287,12 +268,16 @@ static int tc589_config(struct pcmcia_device *link) if (i == 0) break; } - if (i != 0) { - cs_error(link, RequestIO, i); + if (i != 0) goto failed; - } - CS_CHECK(RequestIRQ, pcmcia_request_irq(link, &link->irq)); - CS_CHECK(RequestConfiguration, pcmcia_request_configuration(link, &link->conf)); + + ret = pcmcia_request_irq(link, &link->irq); + if (ret) + goto failed; + + ret = pcmcia_request_configuration(link, &link->conf); + if (ret) + goto failed; dev->irq = link->irq.AssignedIRQ; dev->base_addr = link->io.BasePort1; @@ -301,12 +286,13 @@ static int tc589_config(struct pcmcia_device *link) /* The 3c589 has an extra EEPROM for configuration info, including the hardware address. The 3c562 puts the address in the CIS. */ - tuple.DesiredTuple = 0x88; - if (pcmcia_get_first_tuple(link, &tuple) == 0) { - pcmcia_get_tuple_data(link, &tuple); - for (i = 0; i < 3; i++) - phys_addr[i] = htons(le16_to_cpu(buf[i])); + len = pcmcia_get_tuple(link, 0x88, &buf); + if (buf && len >= 6) { + for (i = 0; i < 3; i++) + phys_addr[i] = htons(le16_to_cpu(buf[i*2])); + kfree(buf); } else { + kfree(buf); /* 0 < len < 6 */ for (i = 0; i < 3; i++) phys_addr[i] = htons(read_eeprom(ioaddr, i)); if (phys_addr[0] == htons(0x6060)) { @@ -328,7 +314,7 @@ static int tc589_config(struct pcmcia_device *link) printk(KERN_ERR "3c589_cs: invalid if_port requested\n"); link->dev_node = &lp->node; - SET_NETDEV_DEV(dev, &handle_to_dev(link)); + SET_NETDEV_DEV(dev, &link->dev); if (register_netdev(dev) != 0) { printk(KERN_ERR "3c589_cs: register_netdev() failed\n"); @@ -347,8 +333,6 @@ static int tc589_config(struct pcmcia_device *link) if_names[dev->if_port]); return 0; -cs_failed: - cs_error(link, last_fn, last_ret); failed: tc589_release(link); return -ENODEV; @@ -511,24 +495,8 @@ static void netdev_get_drvinfo(struct net_device *dev, sprintf(info->bus_info, "PCMCIA 0x%lx", dev->base_addr); } -#ifdef PCMCIA_DEBUG -static u32 netdev_get_msglevel(struct net_device *dev) -{ - return pc_debug; -} - -static void netdev_set_msglevel(struct net_device *dev, u32 level) -{ - pc_debug = level; -} -#endif /* PCMCIA_DEBUG */ - static const struct ethtool_ops netdev_ethtool_ops = { .get_drvinfo = netdev_get_drvinfo, -#ifdef PCMCIA_DEBUG - .get_msglevel = netdev_get_msglevel, - .set_msglevel = netdev_set_msglevel, -#endif /* PCMCIA_DEBUG */ }; static int el3_config(struct net_device *dev, struct ifmap *map) @@ -563,7 +531,7 @@ static int el3_open(struct net_device *dev) lp->media.expires = jiffies + HZ; add_timer(&lp->media); - DEBUG(1, "%s: opened, status %4.4x.\n", + dev_dbg(&link->dev, "%s: opened, status %4.4x.\n", dev->name, inw(dev->base_addr + EL3_STATUS)); return 0; @@ -596,7 +564,7 @@ static void pop_tx_status(struct net_device *dev) if (tx_status & 0x30) tc589_wait_for_completion(dev, TxReset); if (tx_status & 0x38) { - DEBUG(1, "%s: transmit error: status 0x%02x\n", + pr_debug("%s: transmit error: status 0x%02x\n", dev->name, tx_status); outw(TxEnable, ioaddr + EL3_CMD); dev->stats.tx_aborted_errors++; @@ -612,7 +580,7 @@ static netdev_tx_t el3_start_xmit(struct sk_buff *skb, struct el3_private *priv = netdev_priv(dev); unsigned long flags; - DEBUG(3, "%s: el3_start_xmit(length = %ld) called, " + pr_debug("%s: el3_start_xmit(length = %ld) called, " "status %4.4x.\n", dev->name, (long)skb->len, inw(ioaddr + EL3_STATUS)); @@ -654,14 +622,14 @@ static irqreturn_t el3_interrupt(int irq, void *dev_id) ioaddr = dev->base_addr; - DEBUG(3, "%s: interrupt, status %4.4x.\n", + pr_debug("%s: interrupt, status %4.4x.\n", dev->name, inw(ioaddr + EL3_STATUS)); spin_lock(&lp->lock); while ((status = inw(ioaddr + EL3_STATUS)) & (IntLatch | RxComplete | StatsFull)) { if ((status & 0xe000) != 0x2000) { - DEBUG(1, "%s: interrupt from dead card\n", dev->name); + pr_debug("%s: interrupt from dead card\n", dev->name); handled = 0; break; } @@ -670,7 +638,7 @@ static irqreturn_t el3_interrupt(int irq, void *dev_id) el3_rx(dev); if (status & TxAvailable) { - DEBUG(3, " TX room bit was handled.\n"); + pr_debug(" TX room bit was handled.\n"); /* There's room in the FIFO for a full-sized packet. */ outw(AckIntr | TxAvailable, ioaddr + EL3_CMD); netif_wake_queue(dev); @@ -722,7 +690,7 @@ static irqreturn_t el3_interrupt(int irq, void *dev_id) lp->last_irq = jiffies; spin_unlock(&lp->lock); - DEBUG(3, "%s: exiting interrupt, status %4.4x.\n", + pr_debug("%s: exiting interrupt, status %4.4x.\n", dev->name, inw(ioaddr + EL3_STATUS)); return IRQ_RETVAL(handled); } @@ -833,7 +801,7 @@ static void update_stats(struct net_device *dev) { unsigned int ioaddr = dev->base_addr; - DEBUG(2, "%s: updating the statistics.\n", dev->name); + pr_debug("%s: updating the statistics.\n", dev->name); /* Turn off statistics updates while reading. */ outw(StatsDisable, ioaddr + EL3_CMD); /* Switch to the stats window, and read everything. */ @@ -861,7 +829,7 @@ static int el3_rx(struct net_device *dev) int worklimit = 32; short rx_status; - DEBUG(3, "%s: in rx_packet(), status %4.4x, rx_status %4.4x.\n", + pr_debug("%s: in rx_packet(), status %4.4x, rx_status %4.4x.\n", dev->name, inw(ioaddr+EL3_STATUS), inw(ioaddr+RX_STATUS)); while (!((rx_status = inw(ioaddr + RX_STATUS)) & 0x8000) && worklimit > 0) { @@ -883,7 +851,7 @@ static int el3_rx(struct net_device *dev) skb = dev_alloc_skb(pkt_len+5); - DEBUG(3, " Receiving packet size %d status %4.4x.\n", + pr_debug(" Receiving packet size %d status %4.4x.\n", pkt_len, rx_status); if (skb != NULL) { skb_reserve(skb, 2); @@ -894,7 +862,7 @@ static int el3_rx(struct net_device *dev) dev->stats.rx_packets++; dev->stats.rx_bytes += pkt_len; } else { - DEBUG(1, "%s: couldn't allocate a sk_buff of" + pr_debug("%s: couldn't allocate a sk_buff of" " size %d.\n", dev->name, pkt_len); dev->stats.rx_dropped++; } @@ -935,7 +903,7 @@ static int el3_close(struct net_device *dev) struct pcmcia_device *link = lp->p_dev; unsigned int ioaddr = dev->base_addr; - DEBUG(1, "%s: shutting down ethercard.\n", dev->name); + dev_dbg(&link->dev, "%s: shutting down ethercard.\n", dev->name); if (pcmcia_dev_present(link)) { /* Turn off statistics ASAP. We update dev->stats below. */ diff --git a/drivers/net/pcmcia/axnet_cs.c b/drivers/net/pcmcia/axnet_cs.c index 3131a59a8d32..800597b82d18 100644 --- a/drivers/net/pcmcia/axnet_cs.c +++ b/drivers/net/pcmcia/axnet_cs.c @@ -75,16 +75,6 @@ MODULE_AUTHOR("David Hinds <dahinds@users.sourceforge.net>"); MODULE_DESCRIPTION("Asix AX88190 PCMCIA ethernet driver"); MODULE_LICENSE("GPL"); -#ifdef PCMCIA_DEBUG -#define INT_MODULE_PARM(n, v) static int n = v; module_param(n, int, 0) - -INT_MODULE_PARM(pc_debug, PCMCIA_DEBUG); -#define DEBUG(n, args...) if (pc_debug>(n)) printk(KERN_DEBUG args) -static char *version = -"axnet_cs.c 1.28 2002/06/29 06:27:37 (David Hinds)"; -#else -#define DEBUG(n, args...) -#endif /*====================================================================*/ @@ -167,7 +157,7 @@ static int axnet_probe(struct pcmcia_device *link) struct net_device *dev; struct ei_device *ei_local; - DEBUG(0, "axnet_attach()\n"); + dev_dbg(&link->dev, "axnet_attach()\n"); dev = alloc_etherdev(sizeof(struct ei_device) + sizeof(axnet_dev_t)); if (!dev) @@ -180,7 +170,6 @@ static int axnet_probe(struct pcmcia_device *link) info->p_dev = link; link->priv = dev; link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; link->conf.Attributes = CONF_ENABLE_IRQ; link->conf.IntType = INT_MEMORY_AND_IO; @@ -205,7 +194,7 @@ static void axnet_detach(struct pcmcia_device *link) { struct net_device *dev = link->priv; - DEBUG(0, "axnet_detach(0x%p)\n", link); + dev_dbg(&link->dev, "axnet_detach(0x%p)\n", link); if (link->dev_node) unregister_netdev(dev); @@ -272,9 +261,6 @@ static int get_prom(struct pcmcia_device *link) ======================================================================*/ -#define CS_CHECK(fn, ret) \ -do { last_fn = (fn); if ((last_ret = (ret)) != 0) goto cs_failed; } while (0) - static int try_io_port(struct pcmcia_device *link) { int j, ret; @@ -341,26 +327,29 @@ static int axnet_config(struct pcmcia_device *link) { struct net_device *dev = link->priv; axnet_dev_t *info = PRIV(dev); - int i, j, j2, last_ret, last_fn; + int i, j, j2, ret; - DEBUG(0, "axnet_config(0x%p)\n", link); + dev_dbg(&link->dev, "axnet_config(0x%p)\n", link); /* don't trust the CIS on this; Linksys got it wrong */ link->conf.Present = 0x63; - last_ret = pcmcia_loop_config(link, axnet_configcheck, NULL); - if (last_ret != 0) { - cs_error(link, RequestIO, last_ret); + ret = pcmcia_loop_config(link, axnet_configcheck, NULL); + if (ret != 0) goto failed; - } - CS_CHECK(RequestIRQ, pcmcia_request_irq(link, &link->irq)); + ret = pcmcia_request_irq(link, &link->irq); + if (ret) + goto failed; if (link->io.NumPorts2 == 8) { link->conf.Attributes |= CONF_ENABLE_SPKR; link->conf.Status = CCSR_AUDIO_ENA; } - CS_CHECK(RequestConfiguration, pcmcia_request_configuration(link, &link->conf)); + ret = pcmcia_request_configuration(link, &link->conf); + if (ret) + goto failed; + dev->irq = link->irq.AssignedIRQ; dev->base_addr = link->io.BasePort1; @@ -410,7 +399,7 @@ static int axnet_config(struct pcmcia_device *link) info->phy_id = (i < 32) ? i : -1; link->dev_node = &info->node; - SET_NETDEV_DEV(dev, &handle_to_dev(link)); + SET_NETDEV_DEV(dev, &link->dev); if (register_netdev(dev) != 0) { printk(KERN_NOTICE "axnet_cs: register_netdev() failed\n"); @@ -426,14 +415,12 @@ static int axnet_config(struct pcmcia_device *link) dev->base_addr, dev->irq, dev->dev_addr); if (info->phy_id != -1) { - DEBUG(0, " MII transceiver at index %d, status %x.\n", info->phy_id, j); + dev_dbg(&link->dev, " MII transceiver at index %d, status %x.\n", info->phy_id, j); } else { printk(KERN_NOTICE " No MII transceivers found!\n"); } return 0; -cs_failed: - cs_error(link, last_fn, last_ret); failed: axnet_release(link); return -ENODEV; @@ -543,7 +530,7 @@ static int axnet_open(struct net_device *dev) struct pcmcia_device *link = info->p_dev; unsigned int nic_base = dev->base_addr; - DEBUG(2, "axnet_open('%s')\n", dev->name); + dev_dbg(&link->dev, "axnet_open('%s')\n", dev->name); if (!pcmcia_dev_present(link)) return -ENODEV; @@ -572,7 +559,7 @@ static int axnet_close(struct net_device *dev) axnet_dev_t *info = PRIV(dev); struct pcmcia_device *link = info->p_dev; - DEBUG(2, "axnet_close('%s')\n", dev->name); + dev_dbg(&link->dev, "axnet_close('%s')\n", dev->name); ax_close(dev); free_irq(dev->irq, dev); @@ -741,10 +728,8 @@ static void block_input(struct net_device *dev, int count, int xfer_count = count; char *buf = skb->data; -#ifdef PCMCIA_DEBUG if ((ei_debug > 4) && (count != 4)) - printk(KERN_DEBUG "%s: [bi=%d]\n", dev->name, count+4); -#endif + pr_debug("%s: [bi=%d]\n", dev->name, count+4); outb_p(ring_offset & 0xff, nic_base + EN0_RSARLO); outb_p(ring_offset >> 8, nic_base + EN0_RSARHI); outb_p(E8390_RREAD+E8390_START, nic_base + AXNET_CMD); @@ -762,10 +747,7 @@ static void block_output(struct net_device *dev, int count, { unsigned int nic_base = dev->base_addr; -#ifdef PCMCIA_DEBUG - if (ei_debug > 4) - printk(KERN_DEBUG "%s: [bo=%d]\n", dev->name, count); -#endif + pr_debug("%s: [bo=%d]\n", dev->name, count); /* Round the count up for word writes. Do we need to do this? What effect will an odd byte count have on the 8390? diff --git a/drivers/net/pcmcia/com20020_cs.c b/drivers/net/pcmcia/com20020_cs.c index 7b5c77b7bd27..21d9c9d815d1 100644 --- a/drivers/net/pcmcia/com20020_cs.c +++ b/drivers/net/pcmcia/com20020_cs.c @@ -53,11 +53,7 @@ #define VERSION "arcnet: COM20020 PCMCIA support loaded.\n" -#ifdef PCMCIA_DEBUG - -static int pc_debug = PCMCIA_DEBUG; -module_param(pc_debug, int, 0); -#define DEBUG(n, args...) if (pc_debug>(n)) printk(KERN_DEBUG args) +#ifdef DEBUG static void regdump(struct net_device *dev) { @@ -92,7 +88,6 @@ static void regdump(struct net_device *dev) #else -#define DEBUG(n, args...) do { } while (0) static inline void regdump(struct net_device *dev) { } #endif @@ -144,7 +139,7 @@ static int com20020_probe(struct pcmcia_device *p_dev) struct net_device *dev; struct arcnet_local *lp; - DEBUG(0, "com20020_attach()\n"); + dev_dbg(&p_dev->dev, "com20020_attach()\n"); /* Create new network device */ info = kzalloc(sizeof(struct com20020_dev_t), GFP_KERNEL); @@ -169,11 +164,10 @@ static int com20020_probe(struct pcmcia_device *p_dev) p_dev->io.NumPorts1 = 16; p_dev->io.IOAddrLines = 16; p_dev->irq.Attributes = IRQ_TYPE_EXCLUSIVE; - p_dev->irq.IRQInfo1 = IRQ_LEVEL_ID; p_dev->conf.Attributes = CONF_ENABLE_IRQ; p_dev->conf.IntType = INT_MEMORY_AND_IO; - p_dev->irq.Instance = info->dev = dev; + info->dev = dev; p_dev->priv = info; return com20020_config(p_dev); @@ -198,12 +192,12 @@ static void com20020_detach(struct pcmcia_device *link) struct com20020_dev_t *info = link->priv; struct net_device *dev = info->dev; - DEBUG(1,"detach...\n"); + dev_dbg(&link->dev, "detach...\n"); - DEBUG(0, "com20020_detach(0x%p)\n", link); + dev_dbg(&link->dev, "com20020_detach\n"); if (link->dev_node) { - DEBUG(1,"unregister...\n"); + dev_dbg(&link->dev, "unregister...\n"); unregister_netdev(dev); @@ -218,16 +212,16 @@ static void com20020_detach(struct pcmcia_device *link) com20020_release(link); /* Unlink device structure, free bits */ - DEBUG(1,"unlinking...\n"); + dev_dbg(&link->dev, "unlinking...\n"); if (link->priv) { dev = info->dev; if (dev) { - DEBUG(1,"kfree...\n"); + dev_dbg(&link->dev, "kfree...\n"); free_netdev(dev); } - DEBUG(1,"kfree2...\n"); + dev_dbg(&link->dev, "kfree2...\n"); kfree(info); } @@ -241,25 +235,22 @@ static void com20020_detach(struct pcmcia_device *link) ======================================================================*/ -#define CS_CHECK(fn, ret) \ -do { last_fn = (fn); if ((last_ret = (ret)) != 0) goto cs_failed; } while (0) - static int com20020_config(struct pcmcia_device *link) { struct arcnet_local *lp; com20020_dev_t *info; struct net_device *dev; - int i, last_ret, last_fn; + int i, ret; int ioaddr; info = link->priv; dev = info->dev; - DEBUG(1,"config...\n"); + dev_dbg(&link->dev, "config...\n"); - DEBUG(0, "com20020_config(0x%p)\n", link); + dev_dbg(&link->dev, "com20020_config\n"); - DEBUG(1,"arcnet: baseport1 is %Xh\n", link->io.BasePort1); + dev_dbg(&link->dev, "baseport1 is %Xh\n", link->io.BasePort1); i = -ENODEV; if (!link->io.BasePort1) { @@ -276,26 +267,27 @@ static int com20020_config(struct pcmcia_device *link) if (i != 0) { - DEBUG(1,"arcnet: requestIO failed totally!\n"); + dev_dbg(&link->dev, "requestIO failed totally!\n"); goto failed; } ioaddr = dev->base_addr = link->io.BasePort1; - DEBUG(1,"arcnet: got ioaddr %Xh\n", ioaddr); + dev_dbg(&link->dev, "got ioaddr %Xh\n", ioaddr); - DEBUG(1,"arcnet: request IRQ %d (%Xh/%Xh)\n", - link->irq.AssignedIRQ, - link->irq.IRQInfo1, link->irq.IRQInfo2); + dev_dbg(&link->dev, "request IRQ %d\n", + link->irq.AssignedIRQ); i = pcmcia_request_irq(link, &link->irq); if (i != 0) { - DEBUG(1,"arcnet: requestIRQ failed totally!\n"); + dev_dbg(&link->dev, "requestIRQ failed totally!\n"); goto failed; } dev->irq = link->irq.AssignedIRQ; - CS_CHECK(RequestConfiguration, pcmcia_request_configuration(link, &link->conf)); + ret = pcmcia_request_configuration(link, &link->conf); + if (ret) + goto failed; if (com20020_check(dev)) { @@ -308,26 +300,25 @@ static int com20020_config(struct pcmcia_device *link) lp->card_flags = ARC_CAN_10MBIT; /* pretend all of them can 10Mbit */ link->dev_node = &info->node; - SET_NETDEV_DEV(dev, &handle_to_dev(link)); + SET_NETDEV_DEV(dev, &link->dev); i = com20020_found(dev, 0); /* calls register_netdev */ if (i != 0) { - DEBUG(1,KERN_NOTICE "com20020_cs: com20020_found() failed\n"); + dev_printk(KERN_NOTICE, &link->dev, + "com20020_cs: com20020_found() failed\n"); link->dev_node = NULL; goto failed; } strcpy(info->node.dev_name, dev->name); - DEBUG(1,KERN_INFO "%s: port %#3lx, irq %d\n", + dev_dbg(&link->dev,KERN_INFO "%s: port %#3lx, irq %d\n", dev->name, dev->base_addr, dev->irq); return 0; -cs_failed: - cs_error(link, last_fn, last_ret); failed: - DEBUG(1,"com20020_config failed...\n"); + dev_dbg(&link->dev, "com20020_config failed...\n"); com20020_release(link); return -ENODEV; } /* com20020_config */ @@ -342,7 +333,7 @@ failed: static void com20020_release(struct pcmcia_device *link) { - DEBUG(0, "com20020_release(0x%p)\n", link); + dev_dbg(&link->dev, "com20020_release\n"); pcmcia_disable_device(link); } diff --git a/drivers/net/pcmcia/fmvj18x_cs.c b/drivers/net/pcmcia/fmvj18x_cs.c index 7e01fbdb87e0..6e3e1ced6db4 100644 --- a/drivers/net/pcmcia/fmvj18x_cs.c +++ b/drivers/net/pcmcia/fmvj18x_cs.c @@ -72,13 +72,6 @@ MODULE_LICENSE("GPL"); /* 0:4KB*2 TX buffer else:8KB*2 TX buffer */ INT_MODULE_PARM(sram_config, 0); -#ifdef PCMCIA_DEBUG -INT_MODULE_PARM(pc_debug, PCMCIA_DEBUG); -#define DEBUG(n, args...) if (pc_debug>(n)) printk(KERN_DEBUG args) -static char *version = DRV_NAME ".c " DRV_VERSION " 2002/03/23"; -#else -#define DEBUG(n, args...) -#endif /*====================================================================*/ /* @@ -245,7 +238,7 @@ static int fmvj18x_probe(struct pcmcia_device *link) local_info_t *lp; struct net_device *dev; - DEBUG(0, "fmvj18x_attach()\n"); + dev_dbg(&link->dev, "fmvj18x_attach()\n"); /* Make up a FMVJ18x specific data structure */ dev = alloc_etherdev(sizeof(local_info_t)); @@ -262,10 +255,8 @@ static int fmvj18x_probe(struct pcmcia_device *link) link->io.IOAddrLines = 5; /* Interrupt setup */ - link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING|IRQ_HANDLE_PRESENT; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; + link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; link->irq.Handler = &fjn_interrupt; - link->irq.Instance = dev; /* General socket configuration */ link->conf.Attributes = CONF_ENABLE_IRQ; @@ -285,7 +276,7 @@ static void fmvj18x_detach(struct pcmcia_device *link) { struct net_device *dev = link->priv; - DEBUG(0, "fmvj18x_detach(0x%p)\n", link); + dev_dbg(&link->dev, "fmvj18x_detach\n"); if (link->dev_node) unregister_netdev(dev); @@ -297,9 +288,6 @@ static void fmvj18x_detach(struct pcmcia_device *link) /*====================================================================*/ -#define CS_CHECK(fn, ret) \ -do { last_fn = (fn); if ((last_ret = (ret)) != 0) goto cs_failed; } while (0) - static int mfc_try_io_port(struct pcmcia_device *link) { int i, ret; @@ -341,33 +329,38 @@ static int ungermann_try_io_port(struct pcmcia_device *link) return ret; /* RequestIO failed */ } +static int fmvj18x_ioprobe(struct pcmcia_device *p_dev, + cistpl_cftable_entry_t *cfg, + cistpl_cftable_entry_t *dflt, + unsigned int vcc, + void *priv_data) +{ + return 0; /* strange, but that's what the code did already before... */ +} + static int fmvj18x_config(struct pcmcia_device *link) { struct net_device *dev = link->priv; local_info_t *lp = netdev_priv(dev); - tuple_t tuple; - cisparse_t parse; - u_short buf[32]; - int i, last_fn = 0, last_ret = 0, ret; + int i, ret; unsigned int ioaddr; cardtype_t cardtype; char *card_name = "unknown"; - u_char *node_id; + u8 *buf; + size_t len; + u_char buggybuf[32]; + + dev_dbg(&link->dev, "fmvj18x_config\n"); - DEBUG(0, "fmvj18x_config(0x%p)\n", link); + len = pcmcia_get_tuple(link, CISTPL_FUNCE, &buf); + kfree(buf); - tuple.TupleData = (u_char *)buf; - tuple.TupleDataMax = 64; - tuple.TupleOffset = 0; - tuple.DesiredTuple = CISTPL_FUNCE; - tuple.TupleOffset = 0; - if (pcmcia_get_first_tuple(link, &tuple) == 0) { + if (len) { /* Yes, I have CISTPL_FUNCE. Let's check CISTPL_MANFID */ - tuple.DesiredTuple = CISTPL_CFTABLE_ENTRY; - CS_CHECK(GetFirstTuple, pcmcia_get_first_tuple(link, &tuple)); - CS_CHECK(GetTupleData, pcmcia_get_tuple_data(link, &tuple)); - CS_CHECK(ParseTuple, pcmcia_parse_tuple(&tuple, &parse)); - link->conf.ConfigIndex = parse.cftable_entry.index; + ret = pcmcia_loop_config(link, fmvj18x_ioprobe, NULL); + if (ret != 0) + goto failed; + switch (link->manf_id) { case MANFID_TDK: cardtype = TDK; @@ -433,17 +426,24 @@ static int fmvj18x_config(struct pcmcia_device *link) if (link->io.NumPorts2 != 0) { link->irq.Attributes = - IRQ_TYPE_DYNAMIC_SHARING|IRQ_FIRST_SHARED|IRQ_HANDLE_PRESENT; + IRQ_TYPE_DYNAMIC_SHARING|IRQ_FIRST_SHARED; ret = mfc_try_io_port(link); - if (ret != 0) goto cs_failed; + if (ret != 0) goto failed; } else if (cardtype == UNGERMANN) { ret = ungermann_try_io_port(link); - if (ret != 0) goto cs_failed; + if (ret != 0) goto failed; } else { - CS_CHECK(RequestIO, pcmcia_request_io(link, &link->io)); + ret = pcmcia_request_io(link, &link->io); + if (ret) + goto failed; } - CS_CHECK(RequestIRQ, pcmcia_request_irq(link, &link->irq)); - CS_CHECK(RequestConfiguration, pcmcia_request_configuration(link, &link->conf)); + ret = pcmcia_request_irq(link, &link->irq); + if (ret) + goto failed; + ret = pcmcia_request_configuration(link, &link->conf); + if (ret) + goto failed; + dev->irq = link->irq.AssignedIRQ; dev->base_addr = link->io.BasePort1; @@ -474,21 +474,21 @@ static int fmvj18x_config(struct pcmcia_device *link) case CONTEC: case NEC: case KME: - tuple.DesiredTuple = CISTPL_FUNCE; - tuple.TupleOffset = 0; - CS_CHECK(GetFirstTuple, pcmcia_get_first_tuple(link, &tuple)); - tuple.TupleOffset = 0; - CS_CHECK(GetTupleData, pcmcia_get_tuple_data(link, &tuple)); if (cardtype == MBH10304) { - /* MBH10304's CIS_FUNCE is corrupted */ - node_id = &(tuple.TupleData[5]); card_name = "FMV-J182"; - } else { - while (tuple.TupleData[0] != CISTPL_FUNCE_LAN_NODE_ID ) { - CS_CHECK(GetNextTuple, pcmcia_get_next_tuple(link, &tuple)); - CS_CHECK(GetTupleData, pcmcia_get_tuple_data(link, &tuple)); + + len = pcmcia_get_tuple(link, CISTPL_FUNCE, &buf); + if (len < 11) { + kfree(buf); + goto failed; } - node_id = &(tuple.TupleData[2]); + /* Read MACID from CIS */ + for (i = 5; i < 11; i++) + dev->dev_addr[i] = buf[i]; + kfree(buf); + } else { + if (pcmcia_get_mac_from_cis(link, dev)) + goto failed; if( cardtype == TDK ) { card_name = "TDK LAK-CD021"; } else if( cardtype == LA501 ) { @@ -501,9 +501,6 @@ static int fmvj18x_config(struct pcmcia_device *link) card_name = "C-NET(PC)C"; } } - /* Read MACID from CIS */ - for (i = 0; i < 6; i++) - dev->dev_addr[i] = node_id[i]; break; case UNGERMANN: /* Read MACID from register */ @@ -513,12 +510,12 @@ static int fmvj18x_config(struct pcmcia_device *link) break; case XXX10304: /* Read MACID from Buggy CIS */ - if (fmvj18x_get_hwinfo(link, tuple.TupleData) == -1) { + if (fmvj18x_get_hwinfo(link, buggybuf) == -1) { printk(KERN_NOTICE "fmvj18x_cs: unable to read hardware net address.\n"); goto failed; } for (i = 0 ; i < 6; i++) { - dev->dev_addr[i] = tuple.TupleData[i]; + dev->dev_addr[i] = buggybuf[i]; } card_name = "FMV-J182"; break; @@ -533,7 +530,7 @@ static int fmvj18x_config(struct pcmcia_device *link) lp->cardtype = cardtype; link->dev_node = &lp->node; - SET_NETDEV_DEV(dev, &handle_to_dev(link)); + SET_NETDEV_DEV(dev, &link->dev); if (register_netdev(dev) != 0) { printk(KERN_NOTICE "fmvj18x_cs: register_netdev() failed\n"); @@ -551,9 +548,6 @@ static int fmvj18x_config(struct pcmcia_device *link) return 0; -cs_failed: - /* All Card Services errors end up here */ - cs_error(link, last_fn, last_ret); failed: fmvj18x_release(link); return -ENODEV; @@ -571,16 +565,14 @@ static int fmvj18x_get_hwinfo(struct pcmcia_device *link, u_char *node_id) req.Attributes = WIN_DATA_WIDTH_8|WIN_MEMORY_TYPE_AM|WIN_ENABLE; req.Base = 0; req.Size = 0; req.AccessSpeed = 0; - i = pcmcia_request_window(&link, &req, &link->win); - if (i != 0) { - cs_error(link, RequestWindow, i); + i = pcmcia_request_window(link, &req, &link->win); + if (i != 0) return -1; - } base = ioremap(req.Base, req.Size); mem.Page = 0; mem.CardOffset = 0; - pcmcia_map_mem_page(link->win, &mem); + pcmcia_map_mem_page(link, link->win, &mem); /* * MBH10304 CISTPL_FUNCE_LAN_NODE_ID format @@ -605,9 +597,7 @@ static int fmvj18x_get_hwinfo(struct pcmcia_device *link, u_char *node_id) } iounmap(base); - j = pcmcia_release_window(link->win); - if (j != 0) - cs_error(link, ReleaseWindow, j); + j = pcmcia_release_window(link, link->win); return (i != 0x200) ? 0 : -1; } /* fmvj18x_get_hwinfo */ @@ -626,11 +616,9 @@ static int fmvj18x_setup_mfc(struct pcmcia_device *link) req.Attributes = WIN_DATA_WIDTH_8|WIN_MEMORY_TYPE_AM|WIN_ENABLE; req.Base = 0; req.Size = 0; req.AccessSpeed = 0; - i = pcmcia_request_window(&link, &req, &link->win); - if (i != 0) { - cs_error(link, RequestWindow, i); + i = pcmcia_request_window(link, &req, &link->win); + if (i != 0) return -1; - } lp->base = ioremap(req.Base, req.Size); if (lp->base == NULL) { @@ -640,11 +628,10 @@ static int fmvj18x_setup_mfc(struct pcmcia_device *link) mem.Page = 0; mem.CardOffset = 0; - i = pcmcia_map_mem_page(link->win, &mem); + i = pcmcia_map_mem_page(link, link->win, &mem); if (i != 0) { iounmap(lp->base); lp->base = NULL; - cs_error(link, MapMemPage, i); return -1; } @@ -671,15 +658,13 @@ static void fmvj18x_release(struct pcmcia_device *link) u_char __iomem *tmp; int j; - DEBUG(0, "fmvj18x_release(0x%p)\n", link); + dev_dbg(&link->dev, "fmvj18x_release\n"); if (lp->base != NULL) { tmp = lp->base; lp->base = NULL; /* set NULL before iounmap */ iounmap(tmp); - j = pcmcia_release_window(link->win); - if (j != 0) - cs_error(link, ReleaseWindow, j); + j = pcmcia_release_window(link, link->win); } pcmcia_disable_device(link); @@ -788,8 +773,8 @@ static irqreturn_t fjn_interrupt(int dummy, void *dev_id) outb(tx_stat, ioaddr + TX_STATUS); outb(rx_stat, ioaddr + RX_STATUS); - DEBUG(4, "%s: interrupt, rx_status %02x.\n", dev->name, rx_stat); - DEBUG(4, " tx_status %02x.\n", tx_stat); + pr_debug("%s: interrupt, rx_status %02x.\n", dev->name, rx_stat); + pr_debug(" tx_status %02x.\n", tx_stat); if (rx_stat || (inb(ioaddr + RX_MODE) & F_BUF_EMP) == 0) { /* there is packet(s) in rx buffer */ @@ -809,8 +794,8 @@ static irqreturn_t fjn_interrupt(int dummy, void *dev_id) } netif_wake_queue(dev); } - DEBUG(4, "%s: exiting interrupt,\n", dev->name); - DEBUG(4, " tx_status %02x, rx_status %02x.\n", tx_stat, rx_stat); + pr_debug("%s: exiting interrupt,\n", dev->name); + pr_debug(" tx_status %02x, rx_status %02x.\n", tx_stat, rx_stat); outb(D_TX_INTR, ioaddr + TX_INTR); outb(D_RX_INTR, ioaddr + RX_INTR); @@ -882,7 +867,7 @@ static netdev_tx_t fjn_start_xmit(struct sk_buff *skb, return NETDEV_TX_BUSY; } - DEBUG(4, "%s: Transmitting a packet of length %lu.\n", + pr_debug("%s: Transmitting a packet of length %lu.\n", dev->name, (unsigned long)skb->len); dev->stats.tx_bytes += skb->len; @@ -937,7 +922,7 @@ static void fjn_reset(struct net_device *dev) unsigned int ioaddr = dev->base_addr; int i; - DEBUG(4, "fjn_reset(%s) called.\n",dev->name); + pr_debug("fjn_reset(%s) called.\n",dev->name); /* Reset controller */ if( sram_config == 0 ) @@ -1015,13 +1000,13 @@ static void fjn_rx(struct net_device *dev) unsigned int ioaddr = dev->base_addr; int boguscount = 10; /* 5 -> 10: by agy 19940922 */ - DEBUG(4, "%s: in rx_packet(), rx_status %02x.\n", + pr_debug("%s: in rx_packet(), rx_status %02x.\n", dev->name, inb(ioaddr + RX_STATUS)); while ((inb(ioaddr + RX_MODE) & F_BUF_EMP) == 0) { u_short status = inw(ioaddr + DATAPORT); - DEBUG(4, "%s: Rxing packet mode %02x status %04x.\n", + pr_debug("%s: Rxing packet mode %02x status %04x.\n", dev->name, inb(ioaddr + RX_MODE), status); #ifndef final_version if (status == 0) { @@ -1061,16 +1046,14 @@ static void fjn_rx(struct net_device *dev) (pkt_len + 1) >> 1); skb->protocol = eth_type_trans(skb, dev); -#ifdef PCMCIA_DEBUG - if (pc_debug > 5) { + { int i; - printk(KERN_DEBUG "%s: Rxed packet of length %d: ", - dev->name, pkt_len); + pr_debug("%s: Rxed packet of length %d: ", + dev->name, pkt_len); for (i = 0; i < 14; i++) - printk(" %02x", skb->data[i]); - printk(".\n"); + pr_debug(" %02x", skb->data[i]); + pr_debug(".\n"); } -#endif netif_rx(skb); dev->stats.rx_packets++; @@ -1094,7 +1077,7 @@ static void fjn_rx(struct net_device *dev) } if (i > 0) - DEBUG(5, "%s: Exint Rx packet with mode %02x after " + pr_debug("%s: Exint Rx packet with mode %02x after " "%d ticks.\n", dev->name, inb(ioaddr + RX_MODE), i); } */ @@ -1112,24 +1095,8 @@ static void netdev_get_drvinfo(struct net_device *dev, sprintf(info->bus_info, "PCMCIA 0x%lx", dev->base_addr); } -#ifdef PCMCIA_DEBUG -static u32 netdev_get_msglevel(struct net_device *dev) -{ - return pc_debug; -} - -static void netdev_set_msglevel(struct net_device *dev, u32 level) -{ - pc_debug = level; -} -#endif /* PCMCIA_DEBUG */ - static const struct ethtool_ops netdev_ethtool_ops = { .get_drvinfo = netdev_get_drvinfo, -#ifdef PCMCIA_DEBUG - .get_msglevel = netdev_get_msglevel, - .set_msglevel = netdev_set_msglevel, -#endif /* PCMCIA_DEBUG */ }; static int fjn_config(struct net_device *dev, struct ifmap *map){ @@ -1141,7 +1108,7 @@ static int fjn_open(struct net_device *dev) struct local_info_t *lp = netdev_priv(dev); struct pcmcia_device *link = lp->p_dev; - DEBUG(4, "fjn_open('%s').\n", dev->name); + pr_debug("fjn_open('%s').\n", dev->name); if (!pcmcia_dev_present(link)) return -ENODEV; @@ -1167,7 +1134,7 @@ static int fjn_close(struct net_device *dev) struct pcmcia_device *link = lp->p_dev; unsigned int ioaddr = dev->base_addr; - DEBUG(4, "fjn_close('%s').\n", dev->name); + pr_debug("fjn_close('%s').\n", dev->name); lp->open_time = 0; netif_stop_queue(dev); diff --git a/drivers/net/pcmcia/ibmtr_cs.c b/drivers/net/pcmcia/ibmtr_cs.c index 06618af1a468..37f4a6fdc3ef 100644 --- a/drivers/net/pcmcia/ibmtr_cs.c +++ b/drivers/net/pcmcia/ibmtr_cs.c @@ -69,17 +69,6 @@ #define PCMCIA #include "../tokenring/ibmtr.c" -#ifdef PCMCIA_DEBUG -static int pc_debug = PCMCIA_DEBUG; -module_param(pc_debug, int, 0); -#define DEBUG(n, args...) if (pc_debug>(n)) printk(KERN_DEBUG args) -static char *version = -"ibmtr_cs.c 1.10 1996/01/06 05:19:00 (Steve Kipisz)\n" -" 2.2.7 1999/05/03 12:00:00 (Mike Phillips)\n" -" 2.4.2 2001/30/28 Midnight (Burt Silverman)\n"; -#else -#define DEBUG(n, args...) -#endif /*====================================================================*/ @@ -130,6 +119,12 @@ static const struct ethtool_ops netdev_ethtool_ops = { .get_drvinfo = netdev_get_drvinfo, }; +static irqreturn_t ibmtr_interrupt(int irq, void *dev_id) { + ibmtr_dev_t *info = dev_id; + struct net_device *dev = info->dev; + return tok_interrupt(irq, dev); +}; + /*====================================================================== ibmtr_attach() creates an "instance" of the driver, allocating @@ -143,7 +138,7 @@ static int __devinit ibmtr_attach(struct pcmcia_device *link) ibmtr_dev_t *info; struct net_device *dev; - DEBUG(0, "ibmtr_attach()\n"); + dev_dbg(&link->dev, "ibmtr_attach()\n"); /* Create new token-ring device */ info = kzalloc(sizeof(*info), GFP_KERNEL); @@ -161,14 +156,13 @@ static int __devinit ibmtr_attach(struct pcmcia_device *link) link->io.Attributes1 = IO_DATA_PATH_WIDTH_8; link->io.NumPorts1 = 4; link->io.IOAddrLines = 16; - link->irq.Attributes = IRQ_TYPE_EXCLUSIVE | IRQ_HANDLE_PRESENT; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; - link->irq.Handler = &tok_interrupt; + link->irq.Attributes = IRQ_TYPE_EXCLUSIVE; + link->irq.Handler = ibmtr_interrupt; link->conf.Attributes = CONF_ENABLE_IRQ; link->conf.IntType = INT_MEMORY_AND_IO; link->conf.Present = PRESENT_OPTION; - link->irq.Instance = info->dev = dev; + info->dev = dev; SET_ETHTOOL_OPS(dev, &netdev_ethtool_ops); @@ -190,7 +184,7 @@ static void ibmtr_detach(struct pcmcia_device *link) struct net_device *dev = info->dev; struct tok_info *ti = netdev_priv(dev); - DEBUG(0, "ibmtr_detach(0x%p)\n", link); + dev_dbg(&link->dev, "ibmtr_detach\n"); /* * When the card removal interrupt hits tok_interrupt(), @@ -217,9 +211,6 @@ static void ibmtr_detach(struct pcmcia_device *link) ======================================================================*/ -#define CS_CHECK(fn, ret) \ -do { last_fn = (fn); if ((last_ret = (ret)) != 0) goto cs_failed; } while (0) - static int __devinit ibmtr_config(struct pcmcia_device *link) { ibmtr_dev_t *info = link->priv; @@ -227,9 +218,9 @@ static int __devinit ibmtr_config(struct pcmcia_device *link) struct tok_info *ti = netdev_priv(dev); win_req_t req; memreq_t mem; - int i, last_ret, last_fn; + int i, ret; - DEBUG(0, "ibmtr_config(0x%p)\n", link); + dev_dbg(&link->dev, "ibmtr_config\n"); link->conf.ConfigIndex = 0x61; @@ -241,11 +232,15 @@ static int __devinit ibmtr_config(struct pcmcia_device *link) if (i != 0) { /* Couldn't get 0xA20-0xA23. Try ALTERNATE at 0xA24-0xA27. */ link->io.BasePort1 = 0xA24; - CS_CHECK(RequestIO, pcmcia_request_io(link, &link->io)); + ret = pcmcia_request_io(link, &link->io); + if (ret) + goto failed; } dev->base_addr = link->io.BasePort1; - CS_CHECK(RequestIRQ, pcmcia_request_irq(link, &link->irq)); + ret = pcmcia_request_irq(link, &link->irq); + if (ret) + goto failed; dev->irq = link->irq.AssignedIRQ; ti->irq = link->irq.AssignedIRQ; ti->global_int_enable=GLOBAL_INT_ENABLE+((dev->irq==9) ? 2 : dev->irq); @@ -256,11 +251,15 @@ static int __devinit ibmtr_config(struct pcmcia_device *link) req.Base = 0; req.Size = 0x2000; req.AccessSpeed = 250; - CS_CHECK(RequestWindow, pcmcia_request_window(&link, &req, &link->win)); + ret = pcmcia_request_window(link, &req, &link->win); + if (ret) + goto failed; mem.CardOffset = mmiobase; mem.Page = 0; - CS_CHECK(MapMemPage, pcmcia_map_mem_page(link->win, &mem)); + ret = pcmcia_map_mem_page(link, link->win, &mem); + if (ret) + goto failed; ti->mmio = ioremap(req.Base, req.Size); /* Allocate the SRAM memory window */ @@ -269,17 +268,23 @@ static int __devinit ibmtr_config(struct pcmcia_device *link) req.Base = 0; req.Size = sramsize * 1024; req.AccessSpeed = 250; - CS_CHECK(RequestWindow, pcmcia_request_window(&link, &req, &info->sram_win_handle)); + ret = pcmcia_request_window(link, &req, &info->sram_win_handle); + if (ret) + goto failed; mem.CardOffset = srambase; mem.Page = 0; - CS_CHECK(MapMemPage, pcmcia_map_mem_page(info->sram_win_handle, &mem)); + ret = pcmcia_map_mem_page(link, info->sram_win_handle, &mem); + if (ret) + goto failed; ti->sram_base = mem.CardOffset >> 12; ti->sram_virt = ioremap(req.Base, req.Size); ti->sram_phys = req.Base; - CS_CHECK(RequestConfiguration, pcmcia_request_configuration(link, &link->conf)); + ret = pcmcia_request_configuration(link, &link->conf); + if (ret) + goto failed; /* Set up the Token-Ring Controller Configuration Register and turn on the card. Check the "Local Area Network Credit Card @@ -287,7 +292,7 @@ static int __devinit ibmtr_config(struct pcmcia_device *link) ibmtr_hw_setup(dev, mmiobase); link->dev_node = &info->node; - SET_NETDEV_DEV(dev, &handle_to_dev(link)); + SET_NETDEV_DEV(dev, &link->dev); i = ibmtr_probe_card(dev); if (i != 0) { @@ -305,8 +310,6 @@ static int __devinit ibmtr_config(struct pcmcia_device *link) dev->dev_addr); return 0; -cs_failed: - cs_error(link, last_fn, last_ret); failed: ibmtr_release(link); return -ENODEV; @@ -325,12 +328,12 @@ static void ibmtr_release(struct pcmcia_device *link) ibmtr_dev_t *info = link->priv; struct net_device *dev = info->dev; - DEBUG(0, "ibmtr_release(0x%p)\n", link); + dev_dbg(&link->dev, "ibmtr_release\n"); if (link->win) { struct tok_info *ti = netdev_priv(dev); iounmap(ti->mmio); - pcmcia_release_window(info->sram_win_handle); + pcmcia_release_window(link, info->sram_win_handle); } pcmcia_disable_device(link); } diff --git a/drivers/net/pcmcia/nmclan_cs.c b/drivers/net/pcmcia/nmclan_cs.c index 5ed6339c52bc..dae5ef6b2609 100644 --- a/drivers/net/pcmcia/nmclan_cs.c +++ b/drivers/net/pcmcia/nmclan_cs.c @@ -381,13 +381,6 @@ typedef struct _mace_private { Private Global Variables ---------------------------------------------------------------------------- */ -#ifdef PCMCIA_DEBUG -static char rcsid[] = -"nmclan_cs.c,v 0.16 1995/07/01 06:42:17 rpao Exp rpao"; -static char *version = -DRV_NAME " " DRV_VERSION " (Roger C. Pao)"; -#endif - static const char *if_names[]={ "Auto", "10baseT", "BNC", }; @@ -406,12 +399,6 @@ MODULE_LICENSE("GPL"); /* 0=auto, 1=10baseT, 2 = 10base2, default=auto */ INT_MODULE_PARM(if_port, 0); -#ifdef PCMCIA_DEBUG -INT_MODULE_PARM(pc_debug, PCMCIA_DEBUG); -#define DEBUG(n, args...) if (pc_debug>(n)) printk(KERN_DEBUG args) -#else -#define DEBUG(n, args...) -#endif /* ---------------------------------------------------------------------------- Function Prototypes @@ -462,8 +449,7 @@ static int nmclan_probe(struct pcmcia_device *link) mace_private *lp; struct net_device *dev; - DEBUG(0, "nmclan_attach()\n"); - DEBUG(1, "%s\n", rcsid); + dev_dbg(&link->dev, "nmclan_attach()\n"); /* Create new ethernet device */ dev = alloc_etherdev(sizeof(mace_private)); @@ -477,10 +463,8 @@ static int nmclan_probe(struct pcmcia_device *link) link->io.NumPorts1 = 32; link->io.Attributes1 = IO_DATA_PATH_WIDTH_AUTO; link->io.IOAddrLines = 5; - link->irq.Attributes = IRQ_TYPE_EXCLUSIVE | IRQ_HANDLE_PRESENT; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; + link->irq.Attributes = IRQ_TYPE_EXCLUSIVE; link->irq.Handler = &mace_interrupt; - link->irq.Instance = dev; link->conf.Attributes = CONF_ENABLE_IRQ; link->conf.IntType = INT_MEMORY_AND_IO; link->conf.ConfigIndex = 1; @@ -507,7 +491,7 @@ static void nmclan_detach(struct pcmcia_device *link) { struct net_device *dev = link->priv; - DEBUG(0, "nmclan_detach(0x%p)\n", link); + dev_dbg(&link->dev, "nmclan_detach\n"); if (link->dev_node) unregister_netdev(dev); @@ -654,37 +638,40 @@ nmclan_config ethernet device available to the system. ---------------------------------------------------------------------------- */ -#define CS_CHECK(fn, ret) \ - do { last_fn = (fn); if ((last_ret = (ret)) != 0) goto cs_failed; } while (0) - static int nmclan_config(struct pcmcia_device *link) { struct net_device *dev = link->priv; mace_private *lp = netdev_priv(dev); - tuple_t tuple; - u_char buf[64]; - int i, last_ret, last_fn; + u8 *buf; + size_t len; + int i, ret; unsigned int ioaddr; - DEBUG(0, "nmclan_config(0x%p)\n", link); + dev_dbg(&link->dev, "nmclan_config\n"); + + ret = pcmcia_request_io(link, &link->io); + if (ret) + goto failed; + ret = pcmcia_request_irq(link, &link->irq); + if (ret) + goto failed; + ret = pcmcia_request_configuration(link, &link->conf); + if (ret) + goto failed; - CS_CHECK(RequestIO, pcmcia_request_io(link, &link->io)); - CS_CHECK(RequestIRQ, pcmcia_request_irq(link, &link->irq)); - CS_CHECK(RequestConfiguration, pcmcia_request_configuration(link, &link->conf)); dev->irq = link->irq.AssignedIRQ; dev->base_addr = link->io.BasePort1; ioaddr = dev->base_addr; /* Read the ethernet address from the CIS. */ - tuple.DesiredTuple = 0x80 /* CISTPL_CFTABLE_ENTRY_MISC */; - tuple.TupleData = buf; - tuple.TupleDataMax = 64; - tuple.TupleOffset = 0; - tuple.Attributes = 0; - CS_CHECK(GetFirstTuple, pcmcia_get_first_tuple(link, &tuple)); - CS_CHECK(GetTupleData, pcmcia_get_tuple_data(link, &tuple)); - memcpy(dev->dev_addr, tuple.TupleData, ETHER_ADDR_LEN); + len = pcmcia_get_tuple(link, 0x80, &buf); + if (!buf || len < ETHER_ADDR_LEN) { + kfree(buf); + goto failed; + } + memcpy(dev->dev_addr, buf, ETHER_ADDR_LEN); + kfree(buf); /* Verify configuration by reading the MACE ID. */ { @@ -693,7 +680,7 @@ static int nmclan_config(struct pcmcia_device *link) sig[0] = mace_read(lp, ioaddr, MACE_CHIPIDL); sig[1] = mace_read(lp, ioaddr, MACE_CHIPIDH); if ((sig[0] == 0x40) && ((sig[1] & 0x0F) == 0x09)) { - DEBUG(0, "nmclan_cs configured: mace id=%x %x\n", + dev_dbg(&link->dev, "nmclan_cs configured: mace id=%x %x\n", sig[0], sig[1]); } else { printk(KERN_NOTICE "nmclan_cs: mace id not found: %x %x should" @@ -712,7 +699,7 @@ static int nmclan_config(struct pcmcia_device *link) printk(KERN_NOTICE "nmclan_cs: invalid if_port requested\n"); link->dev_node = &lp->node; - SET_NETDEV_DEV(dev, &handle_to_dev(link)); + SET_NETDEV_DEV(dev, &link->dev); i = register_netdev(dev); if (i != 0) { @@ -729,8 +716,6 @@ static int nmclan_config(struct pcmcia_device *link) dev->dev_addr); return 0; -cs_failed: - cs_error(link, last_fn, last_ret); failed: nmclan_release(link); return -ENODEV; @@ -744,7 +729,7 @@ nmclan_release ---------------------------------------------------------------------------- */ static void nmclan_release(struct pcmcia_device *link) { - DEBUG(0, "nmclan_release(0x%p)\n", link); + dev_dbg(&link->dev, "nmclan_release\n"); pcmcia_disable_device(link); } @@ -795,7 +780,7 @@ static void nmclan_reset(struct net_device *dev) /* Reset Xilinx */ reg.Action = CS_WRITE; reg.Offset = CISREG_COR; - DEBUG(1, "nmclan_reset: OrigCorValue=0x%lX, resetting...\n", + dev_dbg(&link->dev, "nmclan_reset: OrigCorValue=0x%lX, resetting...\n", OrigCorValue); reg.Value = COR_SOFT_RESET; pcmcia_access_configuration_register(link, ®); @@ -872,7 +857,7 @@ static int mace_close(struct net_device *dev) mace_private *lp = netdev_priv(dev); struct pcmcia_device *link = lp->p_dev; - DEBUG(2, "%s: shutting down ethercard.\n", dev->name); + dev_dbg(&link->dev, "%s: shutting down ethercard.\n", dev->name); /* Mask off all interrupts from the MACE chip. */ outb(0xFF, ioaddr + AM2150_MACE_BASE + MACE_IMR); @@ -891,24 +876,8 @@ static void netdev_get_drvinfo(struct net_device *dev, sprintf(info->bus_info, "PCMCIA 0x%lx", dev->base_addr); } -#ifdef PCMCIA_DEBUG -static u32 netdev_get_msglevel(struct net_device *dev) -{ - return pc_debug; -} - -static void netdev_set_msglevel(struct net_device *dev, u32 level) -{ - pc_debug = level; -} -#endif /* PCMCIA_DEBUG */ - static const struct ethtool_ops netdev_ethtool_ops = { .get_drvinfo = netdev_get_drvinfo, -#ifdef PCMCIA_DEBUG - .get_msglevel = netdev_get_msglevel, - .set_msglevel = netdev_set_msglevel, -#endif /* PCMCIA_DEBUG */ }; /* ---------------------------------------------------------------------------- @@ -946,7 +915,7 @@ static netdev_tx_t mace_start_xmit(struct sk_buff *skb, netif_stop_queue(dev); - DEBUG(3, "%s: mace_start_xmit(length = %ld) called.\n", + pr_debug("%s: mace_start_xmit(length = %ld) called.\n", dev->name, (long)skb->len); #if (!TX_INTERRUPTABLE) @@ -1008,7 +977,7 @@ static irqreturn_t mace_interrupt(int irq, void *dev_id) int IntrCnt = MACE_MAX_IR_ITERATIONS; if (dev == NULL) { - DEBUG(2, "mace_interrupt(): irq 0x%X for unknown device.\n", + pr_debug("mace_interrupt(): irq 0x%X for unknown device.\n", irq); return IRQ_NONE; } @@ -1031,7 +1000,7 @@ static irqreturn_t mace_interrupt(int irq, void *dev_id) } if (!netif_device_present(dev)) { - DEBUG(2, "%s: interrupt from dead card\n", dev->name); + pr_debug("%s: interrupt from dead card\n", dev->name); return IRQ_NONE; } @@ -1039,7 +1008,7 @@ static irqreturn_t mace_interrupt(int irq, void *dev_id) /* WARNING: MACE_IR is a READ/CLEAR port! */ status = inb(ioaddr + AM2150_MACE_BASE + MACE_IR); - DEBUG(3, "mace_interrupt: irq 0x%X status 0x%X.\n", irq, status); + pr_debug("mace_interrupt: irq 0x%X status 0x%X.\n", irq, status); if (status & MACE_IR_RCVINT) { mace_rx(dev, MACE_MAX_RX_ITERATIONS); @@ -1158,7 +1127,7 @@ static int mace_rx(struct net_device *dev, unsigned char RxCnt) ) { rx_status = inw(ioaddr + AM2150_RCV); - DEBUG(3, "%s: in mace_rx(), framecnt 0x%X, rx_status" + pr_debug("%s: in mace_rx(), framecnt 0x%X, rx_status" " 0x%X.\n", dev->name, rx_framecnt, rx_status); if (rx_status & MACE_RCVFS_RCVSTS) { /* Error, update stats. */ @@ -1185,7 +1154,7 @@ static int mace_rx(struct net_device *dev, unsigned char RxCnt) lp->mace_stats.rfs_rcvcc += inb(ioaddr + AM2150_RCV); /* rcv collision count */ - DEBUG(3, " receiving packet size 0x%X rx_status" + pr_debug(" receiving packet size 0x%X rx_status" " 0x%X.\n", pkt_len, rx_status); skb = dev_alloc_skb(pkt_len+2); @@ -1204,7 +1173,7 @@ static int mace_rx(struct net_device *dev, unsigned char RxCnt) outb(0xFF, ioaddr + AM2150_RCV_NEXT); /* skip to next frame */ continue; } else { - DEBUG(1, "%s: couldn't allocate a sk_buff of size" + pr_debug("%s: couldn't allocate a sk_buff of size" " %d.\n", dev->name, pkt_len); lp->linux_stats.rx_dropped++; } @@ -1220,28 +1189,28 @@ pr_linux_stats ---------------------------------------------------------------------------- */ static void pr_linux_stats(struct net_device_stats *pstats) { - DEBUG(2, "pr_linux_stats\n"); - DEBUG(2, " rx_packets=%-7ld tx_packets=%ld\n", + pr_debug("pr_linux_stats\n"); + pr_debug(" rx_packets=%-7ld tx_packets=%ld\n", (long)pstats->rx_packets, (long)pstats->tx_packets); - DEBUG(2, " rx_errors=%-7ld tx_errors=%ld\n", + pr_debug(" rx_errors=%-7ld tx_errors=%ld\n", (long)pstats->rx_errors, (long)pstats->tx_errors); - DEBUG(2, " rx_dropped=%-7ld tx_dropped=%ld\n", + pr_debug(" rx_dropped=%-7ld tx_dropped=%ld\n", (long)pstats->rx_dropped, (long)pstats->tx_dropped); - DEBUG(2, " multicast=%-7ld collisions=%ld\n", + pr_debug(" multicast=%-7ld collisions=%ld\n", (long)pstats->multicast, (long)pstats->collisions); - DEBUG(2, " rx_length_errors=%-7ld rx_over_errors=%ld\n", + pr_debug(" rx_length_errors=%-7ld rx_over_errors=%ld\n", (long)pstats->rx_length_errors, (long)pstats->rx_over_errors); - DEBUG(2, " rx_crc_errors=%-7ld rx_frame_errors=%ld\n", + pr_debug(" rx_crc_errors=%-7ld rx_frame_errors=%ld\n", (long)pstats->rx_crc_errors, (long)pstats->rx_frame_errors); - DEBUG(2, " rx_fifo_errors=%-7ld rx_missed_errors=%ld\n", + pr_debug(" rx_fifo_errors=%-7ld rx_missed_errors=%ld\n", (long)pstats->rx_fifo_errors, (long)pstats->rx_missed_errors); - DEBUG(2, " tx_aborted_errors=%-7ld tx_carrier_errors=%ld\n", + pr_debug(" tx_aborted_errors=%-7ld tx_carrier_errors=%ld\n", (long)pstats->tx_aborted_errors, (long)pstats->tx_carrier_errors); - DEBUG(2, " tx_fifo_errors=%-7ld tx_heartbeat_errors=%ld\n", + pr_debug(" tx_fifo_errors=%-7ld tx_heartbeat_errors=%ld\n", (long)pstats->tx_fifo_errors, (long)pstats->tx_heartbeat_errors); - DEBUG(2, " tx_window_errors=%ld\n", + pr_debug(" tx_window_errors=%ld\n", (long)pstats->tx_window_errors); } /* pr_linux_stats */ @@ -1250,48 +1219,48 @@ pr_mace_stats ---------------------------------------------------------------------------- */ static void pr_mace_stats(mace_statistics *pstats) { - DEBUG(2, "pr_mace_stats\n"); + pr_debug("pr_mace_stats\n"); - DEBUG(2, " xmtsv=%-7d uflo=%d\n", + pr_debug(" xmtsv=%-7d uflo=%d\n", pstats->xmtsv, pstats->uflo); - DEBUG(2, " lcol=%-7d more=%d\n", + pr_debug(" lcol=%-7d more=%d\n", pstats->lcol, pstats->more); - DEBUG(2, " one=%-7d defer=%d\n", + pr_debug(" one=%-7d defer=%d\n", pstats->one, pstats->defer); - DEBUG(2, " lcar=%-7d rtry=%d\n", + pr_debug(" lcar=%-7d rtry=%d\n", pstats->lcar, pstats->rtry); /* MACE_XMTRC */ - DEBUG(2, " exdef=%-7d xmtrc=%d\n", + pr_debug(" exdef=%-7d xmtrc=%d\n", pstats->exdef, pstats->xmtrc); /* RFS1--Receive Status (RCVSTS) */ - DEBUG(2, " oflo=%-7d clsn=%d\n", + pr_debug(" oflo=%-7d clsn=%d\n", pstats->oflo, pstats->clsn); - DEBUG(2, " fram=%-7d fcs=%d\n", + pr_debug(" fram=%-7d fcs=%d\n", pstats->fram, pstats->fcs); /* RFS2--Runt Packet Count (RNTPC) */ /* RFS3--Receive Collision Count (RCVCC) */ - DEBUG(2, " rfs_rntpc=%-7d rfs_rcvcc=%d\n", + pr_debug(" rfs_rntpc=%-7d rfs_rcvcc=%d\n", pstats->rfs_rntpc, pstats->rfs_rcvcc); /* MACE_IR */ - DEBUG(2, " jab=%-7d babl=%d\n", + pr_debug(" jab=%-7d babl=%d\n", pstats->jab, pstats->babl); - DEBUG(2, " cerr=%-7d rcvcco=%d\n", + pr_debug(" cerr=%-7d rcvcco=%d\n", pstats->cerr, pstats->rcvcco); - DEBUG(2, " rntpco=%-7d mpco=%d\n", + pr_debug(" rntpco=%-7d mpco=%d\n", pstats->rntpco, pstats->mpco); /* MACE_MPC */ - DEBUG(2, " mpc=%d\n", pstats->mpc); + pr_debug(" mpc=%d\n", pstats->mpc); /* MACE_RNTPC */ - DEBUG(2, " rntpc=%d\n", pstats->rntpc); + pr_debug(" rntpc=%d\n", pstats->rntpc); /* MACE_RCVCC */ - DEBUG(2, " rcvcc=%d\n", pstats->rcvcc); + pr_debug(" rcvcc=%d\n", pstats->rcvcc); } /* pr_mace_stats */ @@ -1360,7 +1329,7 @@ static struct net_device_stats *mace_get_stats(struct net_device *dev) update_stats(dev->base_addr, dev); - DEBUG(1, "%s: updating the statistics.\n", dev->name); + pr_debug("%s: updating the statistics.\n", dev->name); pr_linux_stats(&lp->linux_stats); pr_mace_stats(&lp->mace_stats); @@ -1427,7 +1396,7 @@ static void BuildLAF(int *ladrf, int *adr) ladrf[byte] |= (1 << (hashcode & 7)); #ifdef PCMCIA_DEBUG - if (pc_debug > 2) + if (0) printk(KERN_DEBUG " adr =%pM\n", adr); printk(KERN_DEBUG " hashcode = %d(decimal), ladrf[0:63] =", hashcode); for (i = 0; i < 8; i++) @@ -1454,12 +1423,12 @@ static void restore_multicast_list(struct net_device *dev) unsigned int ioaddr = dev->base_addr; int i; - DEBUG(2, "%s: restoring Rx mode to %d addresses.\n", + pr_debug("%s: restoring Rx mode to %d addresses.\n", dev->name, num_addrs); if (num_addrs > 0) { - DEBUG(1, "Attempt to restore multicast list detected.\n"); + pr_debug("Attempt to restore multicast list detected.\n"); mace_write(lp, ioaddr, MACE_IAC, MACE_IAC_ADDRCHG | MACE_IAC_LOGADDR); /* Poll ADDRCHG bit */ @@ -1511,11 +1480,11 @@ static void set_multicast_list(struct net_device *dev) struct dev_mc_list *dmi = dev->mc_list; #ifdef PCMCIA_DEBUG - if (pc_debug > 1) { + { static int old; if (dev->mc_count != old) { old = dev->mc_count; - DEBUG(0, "%s: setting Rx mode to %d addresses.\n", + pr_debug("%s: setting Rx mode to %d addresses.\n", dev->name, old); } } @@ -1546,7 +1515,7 @@ static void restore_multicast_list(struct net_device *dev) unsigned int ioaddr = dev->base_addr; mace_private *lp = netdev_priv(dev); - DEBUG(2, "%s: restoring Rx mode to %d addresses.\n", dev->name, + pr_debug("%s: restoring Rx mode to %d addresses.\n", dev->name, lp->multicast_num_addrs); if (dev->flags & IFF_PROMISC) { @@ -1567,11 +1536,11 @@ static void set_multicast_list(struct net_device *dev) mace_private *lp = netdev_priv(dev); #ifdef PCMCIA_DEBUG - if (pc_debug > 1) { + { static int old; if (dev->mc_count != old) { old = dev->mc_count; - DEBUG(0, "%s: setting Rx mode to %d addresses.\n", + pr_debug("%s: setting Rx mode to %d addresses.\n", dev->name, old); } } diff --git a/drivers/net/pcmcia/pcnet_cs.c b/drivers/net/pcmcia/pcnet_cs.c index 94c9ad2746bc..cbe462ed221f 100644 --- a/drivers/net/pcmcia/pcnet_cs.c +++ b/drivers/net/pcmcia/pcnet_cs.c @@ -71,15 +71,6 @@ static const char *if_names[] = { "auto", "10baseT", "10base2"}; -#ifdef PCMCIA_DEBUG -static int pc_debug = PCMCIA_DEBUG; -module_param(pc_debug, int, 0); -#define DEBUG(n, args...) if (pc_debug>(n)) printk(KERN_DEBUG args) -static char *version = -"pcnet_cs.c 1.153 2003/11/09 18:53:09 (David Hinds)"; -#else -#define DEBUG(n, args...) -#endif /*====================================================================*/ @@ -265,7 +256,7 @@ static int pcnet_probe(struct pcmcia_device *link) pcnet_dev_t *info; struct net_device *dev; - DEBUG(0, "pcnet_attach()\n"); + dev_dbg(&link->dev, "pcnet_attach()\n"); /* Create new ethernet device */ dev = __alloc_ei_netdev(sizeof(pcnet_dev_t)); @@ -275,7 +266,6 @@ static int pcnet_probe(struct pcmcia_device *link) link->priv = dev; link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; link->conf.Attributes = CONF_ENABLE_IRQ; link->conf.IntType = INT_MEMORY_AND_IO; @@ -297,7 +287,7 @@ static void pcnet_detach(struct pcmcia_device *link) { struct net_device *dev = link->priv; - DEBUG(0, "pcnet_detach(0x%p)\n", link); + dev_dbg(&link->dev, "pcnet_detach\n"); if (link->dev_node) unregister_netdev(dev); @@ -326,17 +316,15 @@ static hw_info_t *get_hwinfo(struct pcmcia_device *link) req.Attributes = WIN_DATA_WIDTH_8|WIN_MEMORY_TYPE_AM|WIN_ENABLE; req.Base = 0; req.Size = 0; req.AccessSpeed = 0; - i = pcmcia_request_window(&link, &req, &link->win); - if (i != 0) { - cs_error(link, RequestWindow, i); + i = pcmcia_request_window(link, &req, &link->win); + if (i != 0) return NULL; - } virt = ioremap(req.Base, req.Size); mem.Page = 0; for (i = 0; i < NR_INFO; i++) { mem.CardOffset = hw_info[i].offset & ~(req.Size-1); - pcmcia_map_mem_page(link->win, &mem); + pcmcia_map_mem_page(link, link->win, &mem); base = &virt[hw_info[i].offset & (req.Size-1)]; if ((readb(base+0) == hw_info[i].a0) && (readb(base+2) == hw_info[i].a1) && @@ -348,9 +336,7 @@ static hw_info_t *get_hwinfo(struct pcmcia_device *link) } iounmap(virt); - j = pcmcia_release_window(link->win); - if (j != 0) - cs_error(link, ReleaseWindow, j); + j = pcmcia_release_window(link, link->win); return (i < NR_INFO) ? hw_info+i : NULL; } /* get_hwinfo */ @@ -495,9 +481,6 @@ static hw_info_t *get_hwired(struct pcmcia_device *link) ======================================================================*/ -#define CS_CHECK(fn, ret) \ -do { last_fn = (fn); if ((last_ret = (ret)) != 0) goto cs_failed; } while (0) - static int try_io_port(struct pcmcia_device *link) { int j, ret; @@ -567,19 +550,19 @@ static int pcnet_config(struct pcmcia_device *link) { struct net_device *dev = link->priv; pcnet_dev_t *info = PRIV(dev); - int last_ret, last_fn, start_pg, stop_pg, cm_offset; + int ret, start_pg, stop_pg, cm_offset; int has_shmem = 0; hw_info_t *local_hw_info; - DEBUG(0, "pcnet_config(0x%p)\n", link); + dev_dbg(&link->dev, "pcnet_config\n"); - last_ret = pcmcia_loop_config(link, pcnet_confcheck, &has_shmem); - if (last_ret) { - cs_error(link, RequestIO, last_ret); + ret = pcmcia_loop_config(link, pcnet_confcheck, &has_shmem); + if (ret) goto failed; - } - CS_CHECK(RequestIRQ, pcmcia_request_irq(link, &link->irq)); + ret = pcmcia_request_irq(link, &link->irq); + if (ret) + goto failed; if (link->io.NumPorts2 == 8) { link->conf.Attributes |= CONF_ENABLE_SPKR; @@ -589,7 +572,9 @@ static int pcnet_config(struct pcmcia_device *link) (link->card_id == PRODID_IBM_HOME_AND_AWAY)) link->conf.ConfigIndex |= 0x10; - CS_CHECK(RequestConfiguration, pcmcia_request_configuration(link, &link->conf)); + ret = pcmcia_request_configuration(link, &link->conf); + if (ret) + goto failed; dev->irq = link->irq.AssignedIRQ; dev->base_addr = link->io.BasePort1; if (info->flags & HAS_MISC_REG) { @@ -660,7 +645,7 @@ static int pcnet_config(struct pcmcia_device *link) mii_phy_probe(dev); link->dev_node = &info->node; - SET_NETDEV_DEV(dev, &handle_to_dev(link)); + SET_NETDEV_DEV(dev, &link->dev); if (register_netdev(dev) != 0) { printk(KERN_NOTICE "pcnet_cs: register_netdev() failed\n"); @@ -687,8 +672,6 @@ static int pcnet_config(struct pcmcia_device *link) printk(" hw_addr %pM\n", dev->dev_addr); return 0; -cs_failed: - cs_error(link, last_fn, last_ret); failed: pcnet_release(link); return -ENODEV; @@ -706,7 +689,7 @@ static void pcnet_release(struct pcmcia_device *link) { pcnet_dev_t *info = PRIV(link->priv); - DEBUG(0, "pcnet_release(0x%p)\n", link); + dev_dbg(&link->dev, "pcnet_release\n"); if (info->flags & USE_SHMEM) iounmap(info->base); @@ -960,7 +943,7 @@ static void mii_phy_probe(struct net_device *dev) phyid = tmp << 16; phyid |= mdio_read(mii_addr, i, MII_PHYID_REG2); phyid &= MII_PHYID_REV_MASK; - DEBUG(0, "%s: MII at %d is 0x%08x\n", dev->name, i, phyid); + pr_debug("%s: MII at %d is 0x%08x\n", dev->name, i, phyid); if (phyid == AM79C9XX_HOME_PHY) { info->pna_phy = i; } else if (phyid != AM79C9XX_ETH_PHY) { @@ -976,7 +959,7 @@ static int pcnet_open(struct net_device *dev) struct pcmcia_device *link = info->p_dev; unsigned int nic_base = dev->base_addr; - DEBUG(2, "pcnet_open('%s')\n", dev->name); + dev_dbg(&link->dev, "pcnet_open('%s')\n", dev->name); if (!pcmcia_dev_present(link)) return -ENODEV; @@ -1008,7 +991,7 @@ static int pcnet_close(struct net_device *dev) pcnet_dev_t *info = PRIV(dev); struct pcmcia_device *link = info->p_dev; - DEBUG(2, "pcnet_close('%s')\n", dev->name); + dev_dbg(&link->dev, "pcnet_close('%s')\n", dev->name); ei_close(dev); free_irq(dev->irq, dev); @@ -1251,10 +1234,8 @@ static void dma_block_input(struct net_device *dev, int count, int xfer_count = count; char *buf = skb->data; -#ifdef PCMCIA_DEBUG if ((ei_debug > 4) && (count != 4)) - printk(KERN_DEBUG "%s: [bi=%d]\n", dev->name, count+4); -#endif + pr_debug("%s: [bi=%d]\n", dev->name, count+4); if (ei_status.dmaing) { printk(KERN_NOTICE "%s: DMAing conflict in dma_block_input." "[DMAstat:%1x][irqlock:%1x]\n", @@ -1495,7 +1476,7 @@ static int setup_shmem_window(struct pcmcia_device *link, int start_pg, pcnet_dev_t *info = PRIV(dev); win_req_t req; memreq_t mem; - int i, window_size, offset, last_ret, last_fn; + int i, window_size, offset, ret; window_size = (stop_pg - start_pg) << 8; if (window_size > 32 * 1024) @@ -1509,13 +1490,17 @@ static int setup_shmem_window(struct pcmcia_device *link, int start_pg, req.Attributes |= WIN_USE_WAIT; req.Base = 0; req.Size = window_size; req.AccessSpeed = mem_speed; - CS_CHECK(RequestWindow, pcmcia_request_window(&link, &req, &link->win)); + ret = pcmcia_request_window(link, &req, &link->win); + if (ret) + goto failed; mem.CardOffset = (start_pg << 8) + cm_offset; offset = mem.CardOffset % window_size; mem.CardOffset -= offset; mem.Page = 0; - CS_CHECK(MapMemPage, pcmcia_map_mem_page(link->win, &mem)); + ret = pcmcia_map_mem_page(link, link->win, &mem); + if (ret) + goto failed; /* Try scribbling on the buffer */ info->base = ioremap(req.Base, window_size); @@ -1527,8 +1512,8 @@ static int setup_shmem_window(struct pcmcia_device *link, int start_pg, pcnet_reset_8390(dev); if (i != (TX_PAGES<<8)) { iounmap(info->base); - pcmcia_release_window(link->win); - info->base = NULL; link->win = NULL; + pcmcia_release_window(link, link->win); + info->base = NULL; link->win = 0; goto failed; } @@ -1549,8 +1534,6 @@ static int setup_shmem_window(struct pcmcia_device *link, int start_pg, info->flags |= USE_SHMEM; return 0; -cs_failed: - cs_error(link, last_fn, last_ret); failed: return 1; } @@ -1788,7 +1771,6 @@ static int __init init_pcnet_cs(void) static void __exit exit_pcnet_cs(void) { - DEBUG(0, "pcnet_cs: unloading\n"); pcmcia_unregister_driver(&pcnet_driver); } diff --git a/drivers/net/pcmcia/smc91c92_cs.c b/drivers/net/pcmcia/smc91c92_cs.c index 7bde2cd34c7e..9e0da370912e 100644 --- a/drivers/net/pcmcia/smc91c92_cs.c +++ b/drivers/net/pcmcia/smc91c92_cs.c @@ -79,14 +79,6 @@ MODULE_FIRMWARE(FIRMWARE_NAME); */ INT_MODULE_PARM(if_port, 0); -#ifdef PCMCIA_DEBUG -INT_MODULE_PARM(pc_debug, PCMCIA_DEBUG); -static const char *version = -"smc91c92_cs.c 1.123 2006/11/09 Donald Becker, becker@scyld.com.\n"; -#define DEBUG(n, args...) if (pc_debug>(n)) printk(KERN_DEBUG args) -#else -#define DEBUG(n, args...) -#endif #define DRV_NAME "smc91c92_cs" #define DRV_VERSION "1.123" @@ -126,12 +118,6 @@ struct smc_private { int rx_ovrn; }; -struct smc_cfg_mem { - tuple_t tuple; - cisparse_t parse; - u_char buf[255]; -}; - /* Special definitions for Megahertz multifunction cards */ #define MEGAHERTZ_ISR 0x0380 @@ -329,7 +315,7 @@ static int smc91c92_probe(struct pcmcia_device *link) struct smc_private *smc; struct net_device *dev; - DEBUG(0, "smc91c92_attach()\n"); + dev_dbg(&link->dev, "smc91c92_attach()\n"); /* Create new ethernet device */ dev = alloc_etherdev(sizeof(struct smc_private)); @@ -343,10 +329,8 @@ static int smc91c92_probe(struct pcmcia_device *link) link->io.NumPorts1 = 16; link->io.Attributes1 = IO_DATA_PATH_WIDTH_AUTO; link->io.IOAddrLines = 4; - link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING|IRQ_HANDLE_PRESENT; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; + link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; link->irq.Handler = &smc_interrupt; - link->irq.Instance = dev; link->conf.Attributes = CONF_ENABLE_IRQ; link->conf.IntType = INT_MEMORY_AND_IO; @@ -377,7 +361,7 @@ static void smc91c92_detach(struct pcmcia_device *link) { struct net_device *dev = link->priv; - DEBUG(0, "smc91c92_detach(0x%p)\n", link); + dev_dbg(&link->dev, "smc91c92_detach\n"); if (link->dev_node) unregister_netdev(dev); @@ -408,34 +392,7 @@ static int cvt_ascii_address(struct net_device *dev, char *s) return 0; } -/*====================================================================*/ - -static int first_tuple(struct pcmcia_device *handle, tuple_t *tuple, - cisparse_t *parse) -{ - int i; - - i = pcmcia_get_first_tuple(handle, tuple); - if (i != 0) - return i; - i = pcmcia_get_tuple_data(handle, tuple); - if (i != 0) - return i; - return pcmcia_parse_tuple(tuple, parse); -} - -static int next_tuple(struct pcmcia_device *handle, tuple_t *tuple, - cisparse_t *parse) -{ - int i; - - if ((i = pcmcia_get_next_tuple(handle, tuple)) != 0 || - (i = pcmcia_get_tuple_data(handle, tuple)) != 0) - return i; - return pcmcia_parse_tuple(tuple, parse); -} - -/*====================================================================== +/*==================================================================== Configuration stuff for Megahertz cards @@ -490,19 +447,14 @@ static int mhz_mfc_config(struct pcmcia_device *link) { struct net_device *dev = link->priv; struct smc_private *smc = netdev_priv(dev); - struct smc_cfg_mem *cfg_mem; win_req_t req; memreq_t mem; int i; - cfg_mem = kmalloc(sizeof(struct smc_cfg_mem), GFP_KERNEL); - if (!cfg_mem) - return -ENOMEM; - link->conf.Attributes |= CONF_ENABLE_SPKR; link->conf.Status = CCSR_AUDIO_ENA; link->irq.Attributes = - IRQ_TYPE_DYNAMIC_SHARING|IRQ_FIRST_SHARED|IRQ_HANDLE_PRESENT; + IRQ_TYPE_DYNAMIC_SHARING|IRQ_FIRST_SHARED; link->io.IOAddrLines = 16; link->io.Attributes2 = IO_DATA_PATH_WIDTH_8; link->io.NumPorts2 = 8; @@ -510,91 +462,80 @@ static int mhz_mfc_config(struct pcmcia_device *link) /* The Megahertz combo cards have modem-like CIS entries, so we have to explicitly try a bunch of port combinations. */ if (pcmcia_loop_config(link, mhz_mfc_config_check, NULL)) - goto free_cfg_mem; + return -ENODEV; + dev->base_addr = link->io.BasePort1; /* Allocate a memory window, for accessing the ISR */ req.Attributes = WIN_DATA_WIDTH_8|WIN_MEMORY_TYPE_AM|WIN_ENABLE; req.Base = req.Size = 0; req.AccessSpeed = 0; - i = pcmcia_request_window(&link, &req, &link->win); + i = pcmcia_request_window(link, &req, &link->win); if (i != 0) - goto free_cfg_mem; + return -ENODEV; + smc->base = ioremap(req.Base, req.Size); mem.CardOffset = mem.Page = 0; if (smc->manfid == MANFID_MOTOROLA) mem.CardOffset = link->conf.ConfigBase; - i = pcmcia_map_mem_page(link->win, &mem); + i = pcmcia_map_mem_page(link, link->win, &mem); if ((i == 0) && (smc->manfid == MANFID_MEGAHERTZ) && (smc->cardid == PRODID_MEGAHERTZ_EM3288)) mhz_3288_power(link); -free_cfg_mem: - kfree(cfg_mem); - return -ENODEV; + return 0; } -static int mhz_setup(struct pcmcia_device *link) +static int pcmcia_get_versmac(struct pcmcia_device *p_dev, + tuple_t *tuple, + void *priv) { - struct net_device *dev = link->priv; - struct smc_cfg_mem *cfg_mem; - tuple_t *tuple; - cisparse_t *parse; - u_char *buf, *station_addr; - int rc; + struct net_device *dev = priv; + cisparse_t parse; - cfg_mem = kmalloc(sizeof(struct smc_cfg_mem), GFP_KERNEL); - if (!cfg_mem) - return -1; + if (pcmcia_parse_tuple(tuple, &parse)) + return -EINVAL; - tuple = &cfg_mem->tuple; - parse = &cfg_mem->parse; - buf = cfg_mem->buf; + if ((parse.version_1.ns > 3) && + (cvt_ascii_address(dev, + (parse.version_1.str + parse.version_1.ofs[3])))) + return 0; - tuple->Attributes = tuple->TupleOffset = 0; - tuple->TupleData = (cisdata_t *)buf; - tuple->TupleDataMax = 255; + return -EINVAL; +}; + +static int mhz_setup(struct pcmcia_device *link) +{ + struct net_device *dev = link->priv; + size_t len; + u8 *buf; + int rc; /* Read the station address from the CIS. It is stored as the last (fourth) string in the Version 1 Version/ID tuple. */ - tuple->DesiredTuple = CISTPL_VERS_1; - if (first_tuple(link, tuple, parse) != 0) { - rc = -1; - goto free_cfg_mem; - } + if ((link->prod_id[3]) && + (cvt_ascii_address(dev, link->prod_id[3]) == 0)) + return 0; + + /* Workarounds for broken cards start here. */ /* Ugh -- the EM1144 card has two VERS_1 tuples!?! */ - if (next_tuple(link, tuple, parse) != 0) - first_tuple(link, tuple, parse); - if (parse->version_1.ns > 3) { - station_addr = parse->version_1.str + parse->version_1.ofs[3]; - if (cvt_ascii_address(dev, station_addr) == 0) { - rc = 0; - goto free_cfg_mem; - } - } + if (!pcmcia_loop_tuple(link, CISTPL_VERS_1, pcmcia_get_versmac, dev)) + return 0; /* Another possibility: for the EM3288, in a special tuple */ - tuple->DesiredTuple = 0x81; - if (pcmcia_get_first_tuple(link, tuple) != 0) { - rc = -1; - goto free_cfg_mem; - } - if (pcmcia_get_tuple_data(link, tuple) != 0) { - rc = -1; - goto free_cfg_mem; - } - buf[12] = '\0'; - if (cvt_ascii_address(dev, buf) == 0) { - rc = 0; - goto free_cfg_mem; - } rc = -1; -free_cfg_mem: - kfree(cfg_mem); - return rc; -} + len = pcmcia_get_tuple(link, 0x81, &buf); + if (buf && len >= 13) { + buf[12] = '\0'; + if (cvt_ascii_address(dev, buf)) + rc = 0; + } + kfree(buf); + + return rc; +}; /*====================================================================== @@ -684,58 +625,21 @@ static int smc_config(struct pcmcia_device *link) return i; } + static int smc_setup(struct pcmcia_device *link) { struct net_device *dev = link->priv; - struct smc_cfg_mem *cfg_mem; - tuple_t *tuple; - cisparse_t *parse; - cistpl_lan_node_id_t *node_id; - u_char *buf, *station_addr; - int i, rc; - - cfg_mem = kmalloc(sizeof(struct smc_cfg_mem), GFP_KERNEL); - if (!cfg_mem) - return -ENOMEM; - - tuple = &cfg_mem->tuple; - parse = &cfg_mem->parse; - buf = cfg_mem->buf; - - tuple->Attributes = tuple->TupleOffset = 0; - tuple->TupleData = (cisdata_t *)buf; - tuple->TupleDataMax = 255; /* Check for a LAN function extension tuple */ - tuple->DesiredTuple = CISTPL_FUNCE; - i = first_tuple(link, tuple, parse); - while (i == 0) { - if (parse->funce.type == CISTPL_FUNCE_LAN_NODE_ID) - break; - i = next_tuple(link, tuple, parse); - } - if (i == 0) { - node_id = (cistpl_lan_node_id_t *)parse->funce.data; - if (node_id->nb == 6) { - for (i = 0; i < 6; i++) - dev->dev_addr[i] = node_id->id[i]; - rc = 0; - goto free_cfg_mem; - } - } + if (!pcmcia_get_mac_from_cis(link, dev)) + return 0; + /* Try the third string in the Version 1 Version/ID tuple. */ if (link->prod_id[2]) { - station_addr = link->prod_id[2]; - if (cvt_ascii_address(dev, station_addr) == 0) { - rc = 0; - goto free_cfg_mem; - } + if (cvt_ascii_address(dev, link->prod_id[2]) == 0) + return 0; } - - rc = -1; -free_cfg_mem: - kfree(cfg_mem); - return rc; + return -1; } /*====================================================================*/ @@ -749,7 +653,7 @@ static int osi_config(struct pcmcia_device *link) link->conf.Attributes |= CONF_ENABLE_SPKR; link->conf.Status = CCSR_AUDIO_ENA; link->irq.Attributes = - IRQ_TYPE_DYNAMIC_SHARING|IRQ_FIRST_SHARED|IRQ_HANDLE_PRESENT; + IRQ_TYPE_DYNAMIC_SHARING|IRQ_FIRST_SHARED; link->io.NumPorts1 = 64; link->io.Attributes2 = IO_DATA_PATH_WIDTH_8; link->io.NumPorts2 = 8; @@ -794,41 +698,31 @@ static int osi_load_firmware(struct pcmcia_device *link) return err; } -static int osi_setup(struct pcmcia_device *link, u_short manfid, u_short cardid) +static int pcmcia_osi_mac(struct pcmcia_device *p_dev, + tuple_t *tuple, + void *priv) { - struct net_device *dev = link->priv; - struct smc_cfg_mem *cfg_mem; - tuple_t *tuple; - u_char *buf; - int i, rc; + struct net_device *dev = priv; + int i; - cfg_mem = kmalloc(sizeof(struct smc_cfg_mem), GFP_KERNEL); - if (!cfg_mem) - return -1; + if (tuple->TupleDataLen < 8) + return -EINVAL; + if (tuple->TupleData[0] != 0x04) + return -EINVAL; + for (i = 0; i < 6; i++) + dev->dev_addr[i] = tuple->TupleData[i+2]; + return 0; +}; - tuple = &cfg_mem->tuple; - buf = cfg_mem->buf; - tuple->Attributes = TUPLE_RETURN_COMMON; - tuple->TupleData = (cisdata_t *)buf; - tuple->TupleDataMax = 255; - tuple->TupleOffset = 0; +static int osi_setup(struct pcmcia_device *link, u_short manfid, u_short cardid) +{ + struct net_device *dev = link->priv; + int rc; /* Read the station address from tuple 0x90, subtuple 0x04 */ - tuple->DesiredTuple = 0x90; - i = pcmcia_get_first_tuple(link, tuple); - while (i == 0) { - i = pcmcia_get_tuple_data(link, tuple); - if ((i != 0) || (buf[0] == 0x04)) - break; - i = pcmcia_get_next_tuple(link, tuple); - } - if (i != 0) { - rc = -1; - goto free_cfg_mem; - } - for (i = 0; i < 6; i++) - dev->dev_addr[i] = buf[i+2]; + if (pcmcia_loop_tuple(link, 0x90, pcmcia_osi_mac, dev)) + return -1; if (((manfid == MANFID_OSITECH) && (cardid == PRODID_OSITECH_SEVEN)) || @@ -836,20 +730,17 @@ static int osi_setup(struct pcmcia_device *link, u_short manfid, u_short cardid) (cardid == PRODID_PSION_NET100))) { rc = osi_load_firmware(link); if (rc) - goto free_cfg_mem; + return rc; } else if (manfid == MANFID_OSITECH) { /* Make sure both functions are powered up */ set_bits(0x300, link->io.BasePort1 + OSITECH_AUI_PWR); /* Now, turn on the interrupt for both card functions */ set_bits(0x300, link->io.BasePort1 + OSITECH_RESET_ISR); - DEBUG(2, "AUI/PWR: %4.4x RESET/ISR: %4.4x\n", + dev_dbg(&link->dev, "AUI/PWR: %4.4x RESET/ISR: %4.4x\n", inw(link->io.BasePort1 + OSITECH_AUI_PWR), inw(link->io.BasePort1 + OSITECH_RESET_ISR)); } - rc = 0; -free_cfg_mem: - kfree(cfg_mem); - return rc; + return 0; } static int smc91c92_suspend(struct pcmcia_device *link) @@ -959,12 +850,6 @@ static int check_sig(struct pcmcia_device *link) ======================================================================*/ -#define CS_EXIT_TEST(ret, svc, label) \ -if (ret != 0) { \ - cs_error(link, svc, ret); \ - goto label; \ -} - static int smc91c92_config(struct pcmcia_device *link) { struct net_device *dev = link->priv; @@ -974,7 +859,7 @@ static int smc91c92_config(struct pcmcia_device *link) unsigned int ioaddr; u_long mir; - DEBUG(0, "smc91c92_config(0x%p)\n", link); + dev_dbg(&link->dev, "smc91c92_config\n"); smc->manfid = link->manf_id; smc->cardid = link->card_id; @@ -990,12 +875,15 @@ static int smc91c92_config(struct pcmcia_device *link) } else { i = smc_config(link); } - CS_EXIT_TEST(i, RequestIO, config_failed); + if (i) + goto config_failed; i = pcmcia_request_irq(link, &link->irq); - CS_EXIT_TEST(i, RequestIRQ, config_failed); + if (i) + goto config_failed; i = pcmcia_request_configuration(link, &link->conf); - CS_EXIT_TEST(i, RequestConfiguration, config_failed); + if (i) + goto config_failed; if (smc->manfid == MANFID_MOTOROLA) mot_config(link); @@ -1074,7 +962,7 @@ static int smc91c92_config(struct pcmcia_device *link) } link->dev_node = &smc->node; - SET_NETDEV_DEV(dev, &handle_to_dev(link)); + SET_NETDEV_DEV(dev, &link->dev); if (register_netdev(dev) != 0) { printk(KERN_ERR "smc91c92_cs: register_netdev() failed\n"); @@ -1100,7 +988,7 @@ static int smc91c92_config(struct pcmcia_device *link) if (smc->cfg & CFG_MII_SELECT) { if (smc->mii_if.phy_id != -1) { - DEBUG(0, " MII transceiver at index %d, status %x.\n", + dev_dbg(&link->dev, " MII transceiver at index %d, status %x.\n", smc->mii_if.phy_id, j); } else { printk(KERN_NOTICE " No MII transceivers found!\n"); @@ -1110,7 +998,7 @@ static int smc91c92_config(struct pcmcia_device *link) config_undo: unregister_netdev(dev); -config_failed: /* CS_EXIT_TEST() calls jump to here... */ +config_failed: smc91c92_release(link); return -ENODEV; } /* smc91c92_config */ @@ -1125,7 +1013,7 @@ config_failed: /* CS_EXIT_TEST() calls jump to here... */ static void smc91c92_release(struct pcmcia_device *link) { - DEBUG(0, "smc91c92_release(0x%p)\n", link); + dev_dbg(&link->dev, "smc91c92_release\n"); if (link->win) { struct net_device *dev = link->priv; struct smc_private *smc = netdev_priv(dev); @@ -1222,10 +1110,10 @@ static int smc_open(struct net_device *dev) struct smc_private *smc = netdev_priv(dev); struct pcmcia_device *link = smc->p_dev; -#ifdef PCMCIA_DEBUG - DEBUG(0, "%s: smc_open(%p), ID/Window %4.4x.\n", + dev_dbg(&link->dev, "%s: smc_open(%p), ID/Window %4.4x.\n", dev->name, dev, inw(dev->base_addr + BANK_SELECT)); - if (pc_debug > 1) smc_dump(dev); +#ifdef PCMCIA_DEBUG + smc_dump(dev); #endif /* Check that the PCMCIA card is still here. */ @@ -1260,7 +1148,7 @@ static int smc_close(struct net_device *dev) struct pcmcia_device *link = smc->p_dev; unsigned int ioaddr = dev->base_addr; - DEBUG(0, "%s: smc_close(), status %4.4x.\n", + dev_dbg(&link->dev, "%s: smc_close(), status %4.4x.\n", dev->name, inw(ioaddr + BANK_SELECT)); netif_stop_queue(dev); @@ -1327,7 +1215,7 @@ static void smc_hardware_send_packet(struct net_device * dev) u_char *buf = skb->data; u_int length = skb->len; /* The chip will pad to ethernet min. */ - DEBUG(2, "%s: Trying to xmit packet of length %d.\n", + pr_debug("%s: Trying to xmit packet of length %d.\n", dev->name, length); /* send the packet length: +6 for status word, length, and ctl */ @@ -1382,7 +1270,7 @@ static netdev_tx_t smc_start_xmit(struct sk_buff *skb, netif_stop_queue(dev); - DEBUG(2, "%s: smc_start_xmit(length = %d) called," + pr_debug("%s: smc_start_xmit(length = %d) called," " status %4.4x.\n", dev->name, skb->len, inw(ioaddr + 2)); if (smc->saved_skb) { @@ -1429,7 +1317,7 @@ static netdev_tx_t smc_start_xmit(struct sk_buff *skb, } /* Otherwise defer until the Tx-space-allocated interrupt. */ - DEBUG(2, "%s: memory allocation deferred.\n", dev->name); + pr_debug("%s: memory allocation deferred.\n", dev->name); outw((IM_ALLOC_INT << 8) | (ir & 0xff00), ioaddr + INTERRUPT); spin_unlock_irqrestore(&smc->lock, flags); @@ -1494,7 +1382,7 @@ static void smc_eph_irq(struct net_device *dev) SMC_SELECT_BANK(0); ephs = inw(ioaddr + EPH); - DEBUG(2, "%s: Ethernet protocol handler interrupt, status" + pr_debug("%s: Ethernet protocol handler interrupt, status" " %4.4x.\n", dev->name, ephs); /* Could be a counter roll-over warning: update stats. */ card_stats = inw(ioaddr + COUNTER); @@ -1534,7 +1422,7 @@ static irqreturn_t smc_interrupt(int irq, void *dev_id) ioaddr = dev->base_addr; - DEBUG(3, "%s: SMC91c92 interrupt %d at %#x.\n", dev->name, + pr_debug("%s: SMC91c92 interrupt %d at %#x.\n", dev->name, irq, ioaddr); spin_lock(&smc->lock); @@ -1543,7 +1431,7 @@ static irqreturn_t smc_interrupt(int irq, void *dev_id) if ((saved_bank & 0xff00) != 0x3300) { /* The device does not exist -- the card could be off-line, or maybe it has been ejected. */ - DEBUG(1, "%s: SMC91c92 interrupt %d for non-existent" + pr_debug("%s: SMC91c92 interrupt %d for non-existent" "/ejected device.\n", dev->name, irq); handled = 0; goto irq_done; @@ -1557,7 +1445,7 @@ static irqreturn_t smc_interrupt(int irq, void *dev_id) do { /* read the status flag, and mask it */ status = inw(ioaddr + INTERRUPT) & 0xff; - DEBUG(3, "%s: Status is %#2.2x (mask %#2.2x).\n", dev->name, + pr_debug("%s: Status is %#2.2x (mask %#2.2x).\n", dev->name, status, mask); if ((status & mask) == 0) { if (bogus_cnt == INTR_WORK) @@ -1602,7 +1490,7 @@ static irqreturn_t smc_interrupt(int irq, void *dev_id) smc_eph_irq(dev); } while (--bogus_cnt); - DEBUG(3, " Restoring saved registers mask %2.2x bank %4.4x" + pr_debug(" Restoring saved registers mask %2.2x bank %4.4x" " pointer %4.4x.\n", mask, saved_bank, saved_pointer); /* restore state register */ @@ -1610,7 +1498,7 @@ static irqreturn_t smc_interrupt(int irq, void *dev_id) outw(saved_pointer, ioaddr + POINTER); SMC_SELECT_BANK(saved_bank); - DEBUG(3, "%s: Exiting interrupt IRQ%d.\n", dev->name, irq); + pr_debug("%s: Exiting interrupt IRQ%d.\n", dev->name, irq); irq_done: @@ -1661,7 +1549,7 @@ static void smc_rx(struct net_device *dev) rx_status = inw(ioaddr + DATA_1); packet_length = inw(ioaddr + DATA_1) & 0x07ff; - DEBUG(2, "%s: Receive status %4.4x length %d.\n", + pr_debug("%s: Receive status %4.4x length %d.\n", dev->name, rx_status, packet_length); if (!(rx_status & RS_ERRORS)) { @@ -1672,7 +1560,7 @@ static void smc_rx(struct net_device *dev) skb = dev_alloc_skb(packet_length+2); if (skb == NULL) { - DEBUG(1, "%s: Low memory, packet dropped.\n", dev->name); + pr_debug("%s: Low memory, packet dropped.\n", dev->name); dev->stats.rx_dropped++; outw(MC_RELEASE, ioaddr + MMU_CMD); return; @@ -1832,7 +1720,7 @@ static void smc_reset(struct net_device *dev) struct smc_private *smc = netdev_priv(dev); int i; - DEBUG(0, "%s: smc91c92 reset called.\n", dev->name); + pr_debug("%s: smc91c92 reset called.\n", dev->name); /* The first interaction must be a write to bring the chip out of sleep mode. */ @@ -2149,18 +2037,6 @@ static u32 smc_get_link(struct net_device *dev) return ret; } -#ifdef PCMCIA_DEBUG -static u32 smc_get_msglevel(struct net_device *dev) -{ - return pc_debug; -} - -static void smc_set_msglevel(struct net_device *dev, u32 val) -{ - pc_debug = val; -} -#endif - static int smc_nway_reset(struct net_device *dev) { struct smc_private *smc = netdev_priv(dev); @@ -2184,10 +2060,6 @@ static const struct ethtool_ops ethtool_ops = { .get_settings = smc_get_settings, .set_settings = smc_set_settings, .get_link = smc_get_link, -#ifdef PCMCIA_DEBUG - .get_msglevel = smc_get_msglevel, - .set_msglevel = smc_set_msglevel, -#endif .nway_reset = smc_nway_reset, }; diff --git a/drivers/net/pcmcia/xirc2ps_cs.c b/drivers/net/pcmcia/xirc2ps_cs.c index cf8423102538..fe504b7f369f 100644 --- a/drivers/net/pcmcia/xirc2ps_cs.c +++ b/drivers/net/pcmcia/xirc2ps_cs.c @@ -211,20 +211,6 @@ enum xirc_cmd { /* Commands */ static const char *if_names[] = { "Auto", "10BaseT", "10Base2", "AUI", "100BaseT" }; -/**************** - * All the PCMCIA modules use PCMCIA_DEBUG to control debugging. If - * you do not define PCMCIA_DEBUG at all, all the debug code will be - * left out. If you compile with PCMCIA_DEBUG=0, the debug code will - * be present but disabled -- but it can then be enabled for specific - * modules at load time with a 'pc_debug=#' option to insmod. - */ -#ifdef PCMCIA_DEBUG -static int pc_debug = PCMCIA_DEBUG; -module_param(pc_debug, int, 0); -#define DEBUG(n, args...) if (pc_debug>(n)) printk(KDBG_XIRC args) -#else -#define DEBUG(n, args...) -#endif #define KDBG_XIRC KERN_DEBUG "xirc2ps_cs: " #define KERR_XIRC KERN_ERR "xirc2ps_cs: " @@ -359,7 +345,7 @@ static void xirc_tx_timeout(struct net_device *dev); static void xirc2ps_tx_timeout_task(struct work_struct *work); static void set_addresses(struct net_device *dev); static void set_multicast_list(struct net_device *dev); -static int set_card_type(struct pcmcia_device *link, const void *s); +static int set_card_type(struct pcmcia_device *link); static int do_config(struct net_device *dev, struct ifmap *map); static int do_open(struct net_device *dev); static int do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd); @@ -371,28 +357,6 @@ static void do_powerdown(struct net_device *dev); static int do_stop(struct net_device *dev); /*=============== Helper functions =========================*/ -static int -first_tuple(struct pcmcia_device *handle, tuple_t *tuple, cisparse_t *parse) -{ - int err; - - if ((err = pcmcia_get_first_tuple(handle, tuple)) == 0 && - (err = pcmcia_get_tuple_data(handle, tuple)) == 0) - err = pcmcia_parse_tuple(tuple, parse); - return err; -} - -static int -next_tuple(struct pcmcia_device *handle, tuple_t *tuple, cisparse_t *parse) -{ - int err; - - if ((err = pcmcia_get_next_tuple(handle, tuple)) == 0 && - (err = pcmcia_get_tuple_data(handle, tuple)) == 0) - err = pcmcia_parse_tuple(tuple, parse); - return err; -} - #define SelectPage(pgnr) outb((pgnr), ioaddr + XIRCREG_PR) #define GetByte(reg) ((unsigned)inb(ioaddr + (reg))) #define GetWord(reg) ((unsigned)inw(ioaddr + (reg))) @@ -400,7 +364,7 @@ next_tuple(struct pcmcia_device *handle, tuple_t *tuple, cisparse_t *parse) #define PutWord(reg,value) outw((value), ioaddr+(reg)) /*====== Functions used for debugging =================================*/ -#if defined(PCMCIA_DEBUG) && 0 /* reading regs may change system status */ +#if 0 /* reading regs may change system status */ static void PrintRegisters(struct net_device *dev) { @@ -432,7 +396,7 @@ PrintRegisters(struct net_device *dev) } } } -#endif /* PCMCIA_DEBUG */ +#endif /* 0 */ /*============== MII Management functions ===============*/ @@ -576,7 +540,7 @@ xirc2ps_probe(struct pcmcia_device *link) struct net_device *dev; local_info_t *local; - DEBUG(0, "attach()\n"); + dev_dbg(&link->dev, "attach()\n"); /* Allocate the device structure */ dev = alloc_etherdev(sizeof(local_info_t)); @@ -592,7 +556,6 @@ xirc2ps_probe(struct pcmcia_device *link) link->conf.IntType = INT_MEMORY_AND_IO; link->conf.ConfigIndex = 1; link->irq.Handler = xirc2ps_interrupt; - link->irq.Instance = dev; /* Fill in card specific entries */ dev->netdev_ops = &netdev_ops; @@ -615,7 +578,7 @@ xirc2ps_detach(struct pcmcia_device *link) { struct net_device *dev = link->priv; - DEBUG(0, "detach(0x%p)\n", link); + dev_dbg(&link->dev, "detach\n"); if (link->dev_node) unregister_netdev(dev); @@ -644,17 +607,25 @@ xirc2ps_detach(struct pcmcia_device *link) * */ static int -set_card_type(struct pcmcia_device *link, const void *s) +set_card_type(struct pcmcia_device *link) { struct net_device *dev = link->priv; local_info_t *local = netdev_priv(dev); - #ifdef PCMCIA_DEBUG - unsigned cisrev = ((const unsigned char *)s)[2]; - #endif - unsigned mediaid= ((const unsigned char *)s)[3]; - unsigned prodid = ((const unsigned char *)s)[4]; + u8 *buf; + unsigned int cisrev, mediaid, prodid; + size_t len; + + len = pcmcia_get_tuple(link, CISTPL_MANFID, &buf); + if (len < 5) { + dev_err(&link->dev, "invalid CIS -- sorry\n"); + return 0; + } - DEBUG(0, "cisrev=%02x mediaid=%02x prodid=%02x\n", + cisrev = buf[2]; + mediaid = buf[3]; + prodid = buf[4]; + + dev_dbg(&link->dev, "cisrev=%02x mediaid=%02x prodid=%02x\n", cisrev, mediaid, prodid); local->mohawk = 0; @@ -761,6 +732,26 @@ xirc2ps_config_check(struct pcmcia_device *p_dev, } + +static int pcmcia_get_mac_ce(struct pcmcia_device *p_dev, + tuple_t *tuple, + void *priv) +{ + struct net_device *dev = priv; + int i; + + if (tuple->TupleDataLen != 13) + return -EINVAL; + if ((tuple->TupleData[0] != 2) || (tuple->TupleData[1] != 1) || + (tuple->TupleData[2] != 6)) + return -EINVAL; + /* another try (James Lehmer's CE2 version 4.1)*/ + for (i = 2; i < 6; i++) + dev->dev_addr[i] = tuple->TupleData[i+2]; + return 0; +}; + + /**************** * xirc2ps_config() is scheduled to run after a CARD_INSERTION event * is received, to configure the PCMCIA socket, and to make the @@ -772,33 +763,21 @@ xirc2ps_config(struct pcmcia_device * link) struct net_device *dev = link->priv; local_info_t *local = netdev_priv(dev); unsigned int ioaddr; - tuple_t tuple; - cisparse_t parse; - int err, i; - u_char buf[64]; - cistpl_lan_node_id_t *node_id = (cistpl_lan_node_id_t*)parse.funce.data; + int err; + u8 *buf; + size_t len; local->dingo_ccr = NULL; - DEBUG(0, "config(0x%p)\n", link); - - /* - * This reads the card's CONFIG tuple to find its configuration - * registers. - */ - tuple.Attributes = 0; - tuple.TupleData = buf; - tuple.TupleDataMax = 64; - tuple.TupleOffset = 0; + dev_dbg(&link->dev, "config\n"); /* Is this a valid card */ - tuple.DesiredTuple = CISTPL_MANFID; - if ((err=first_tuple(link, &tuple, &parse))) { + if (link->has_manf_id == 0) { printk(KNOT_XIRC "manfid not found in CIS\n"); goto failure; } - switch(parse.manfid.manf) { + switch (link->manf_id) { case MANFID_XIRCOM: local->manf_str = "Xircom"; break; @@ -817,65 +796,44 @@ xirc2ps_config(struct pcmcia_device * link) break; default: printk(KNOT_XIRC "Unknown Card Manufacturer ID: 0x%04x\n", - (unsigned)parse.manfid.manf); + (unsigned)link->manf_id); goto failure; } - DEBUG(0, "found %s card\n", local->manf_str); + dev_dbg(&link->dev, "found %s card\n", local->manf_str); - if (!set_card_type(link, buf)) { + if (!set_card_type(link)) { printk(KNOT_XIRC "this card is not supported\n"); goto failure; } /* get the ethernet address from the CIS */ - tuple.DesiredTuple = CISTPL_FUNCE; - for (err = first_tuple(link, &tuple, &parse); !err; - err = next_tuple(link, &tuple, &parse)) { - /* Once I saw two CISTPL_FUNCE_LAN_NODE_ID entries: - * the first one with a length of zero the second correct - - * so I skip all entries with length 0 */ - if (parse.funce.type == CISTPL_FUNCE_LAN_NODE_ID - && ((cistpl_lan_node_id_t *)parse.funce.data)->nb) - break; - } - if (err) { /* not found: try to get the node-id from tuple 0x89 */ - tuple.DesiredTuple = 0x89; /* data layout looks like tuple 0x22 */ - if ((err = pcmcia_get_first_tuple(link, &tuple)) == 0 && - (err = pcmcia_get_tuple_data(link, &tuple)) == 0) { - if (tuple.TupleDataLen == 8 && *buf == CISTPL_FUNCE_LAN_NODE_ID) - memcpy(&parse, buf, 8); - else - err = -1; - } - } - if (err) { /* another try (James Lehmer's CE2 version 4.1)*/ - tuple.DesiredTuple = CISTPL_FUNCE; - for (err = first_tuple(link, &tuple, &parse); !err; - err = next_tuple(link, &tuple, &parse)) { - if (parse.funce.type == 0x02 && parse.funce.data[0] == 1 - && parse.funce.data[1] == 6 && tuple.TupleDataLen == 13) { - buf[1] = 4; - memcpy(&parse, buf+1, 8); - break; + err = pcmcia_get_mac_from_cis(link, dev); + + /* not found: try to get the node-id from tuple 0x89 */ + if (err) { + len = pcmcia_get_tuple(link, 0x89, &buf); + /* data layout looks like tuple 0x22 */ + if (buf && len == 8) { + if (*buf == CISTPL_FUNCE_LAN_NODE_ID) { + int i; + for (i = 2; i < 6; i++) + dev->dev_addr[i] = buf[i+2]; + } else + err = -1; } - } + kfree(buf); } + + if (err) + err = pcmcia_loop_tuple(link, CISTPL_FUNCE, pcmcia_get_mac_ce, dev); + if (err) { printk(KNOT_XIRC "node-id not found in CIS\n"); goto failure; } - node_id = (cistpl_lan_node_id_t *)parse.funce.data; - if (node_id->nb != 6) { - printk(KNOT_XIRC "malformed node-id in CIS\n"); - goto failure; - } - for (i=0; i < 6; i++) - dev->dev_addr[i] = node_id->id[i]; link->io.IOAddrLines =10; link->io.Attributes1 = IO_DATA_PATH_WIDTH_16; - link->irq.Attributes = IRQ_HANDLE_PRESENT; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; if (local->modem) { int pass; @@ -916,10 +874,8 @@ xirc2ps_config(struct pcmcia_device * link) goto port_found; } link->io.BasePort1 = 0; /* let CS decide */ - if ((err=pcmcia_request_io(link, &link->io))) { - cs_error(link, RequestIO, err); + if ((err=pcmcia_request_io(link, &link->io))) goto config_error; - } } port_found: if (err) @@ -929,19 +885,15 @@ xirc2ps_config(struct pcmcia_device * link) * Now allocate an interrupt line. Note that this does not * actually assign a handler to the interrupt. */ - if ((err=pcmcia_request_irq(link, &link->irq))) { - cs_error(link, RequestIRQ, err); + if ((err=pcmcia_request_irq(link, &link->irq))) goto config_error; - } /**************** * This actually configures the PCMCIA socket -- setting up * the I/O windows and the interrupt mapping. */ - if ((err=pcmcia_request_configuration(link, &link->conf))) { - cs_error(link, RequestConfiguration, err); + if ((err=pcmcia_request_configuration(link, &link->conf))) goto config_error; - } if (local->dingo) { conf_reg_t reg; @@ -956,17 +908,13 @@ xirc2ps_config(struct pcmcia_device * link) reg.Action = CS_WRITE; reg.Offset = CISREG_IOBASE_0; reg.Value = link->io.BasePort2 & 0xff; - if ((err = pcmcia_access_configuration_register(link, ®))) { - cs_error(link, AccessConfigurationRegister, err); + if ((err = pcmcia_access_configuration_register(link, ®))) goto config_error; - } reg.Action = CS_WRITE; reg.Offset = CISREG_IOBASE_1; reg.Value = (link->io.BasePort2 >> 8) & 0xff; - if ((err = pcmcia_access_configuration_register(link, ®))) { - cs_error(link, AccessConfigurationRegister, err); + if ((err = pcmcia_access_configuration_register(link, ®))) goto config_error; - } /* There is no config entry for the Ethernet part which * is at 0x0800. So we allocate a window into the attribute @@ -975,17 +923,14 @@ xirc2ps_config(struct pcmcia_device * link) req.Attributes = WIN_DATA_WIDTH_8|WIN_MEMORY_TYPE_AM|WIN_ENABLE; req.Base = req.Size = 0; req.AccessSpeed = 0; - if ((err = pcmcia_request_window(&link, &req, &link->win))) { - cs_error(link, RequestWindow, err); + if ((err = pcmcia_request_window(link, &req, &link->win))) goto config_error; - } + local->dingo_ccr = ioremap(req.Base,0x1000) + 0x0800; mem.CardOffset = 0x0; mem.Page = 0; - if ((err = pcmcia_map_mem_page(link->win, &mem))) { - cs_error(link, MapMemPage, err); + if ((err = pcmcia_map_mem_page(link, link->win, &mem))) goto config_error; - } /* Setup the CCRs; there are no infos in the CIS about the Ethernet * part. @@ -1044,7 +989,7 @@ xirc2ps_config(struct pcmcia_device * link) do_reset(dev, 1); /* a kludge to make the cem56 work */ link->dev_node = &local->node; - SET_NETDEV_DEV(dev, &handle_to_dev(link)); + SET_NETDEV_DEV(dev, &link->dev); if ((err=register_netdev(dev))) { printk(KNOT_XIRC "register_netdev() failed\n"); @@ -1077,7 +1022,7 @@ xirc2ps_config(struct pcmcia_device * link) static void xirc2ps_release(struct pcmcia_device *link) { - DEBUG(0, "release(0x%p)\n", link); + dev_dbg(&link->dev, "release\n"); if (link->win) { struct net_device *dev = link->priv; @@ -1144,7 +1089,7 @@ xirc2ps_interrupt(int irq, void *dev_id) PutByte(XIRCREG_CR, 0); } - DEBUG(6, "%s: interrupt %d at %#x.\n", dev->name, irq, ioaddr); + pr_debug("%s: interrupt %d at %#x.\n", dev->name, irq, ioaddr); saved_page = GetByte(XIRCREG_PR); /* Read the ISR to see whats the cause for the interrupt. @@ -1154,7 +1099,7 @@ xirc2ps_interrupt(int irq, void *dev_id) bytes_rcvd = 0; loop_entry: if (int_status == 0xff) { /* card may be ejected */ - DEBUG(3, "%s: interrupt %d for dead card\n", dev->name, irq); + pr_debug("%s: interrupt %d for dead card\n", dev->name, irq); goto leave; } eth_status = GetByte(XIRCREG_ESR); @@ -1167,7 +1112,7 @@ xirc2ps_interrupt(int irq, void *dev_id) PutByte(XIRCREG40_TXST0, 0); PutByte(XIRCREG40_TXST1, 0); - DEBUG(3, "%s: ISR=%#2.2x ESR=%#2.2x RSR=%#2.2x TSR=%#4.4x\n", + pr_debug("%s: ISR=%#2.2x ESR=%#2.2x RSR=%#2.2x TSR=%#4.4x\n", dev->name, int_status, eth_status, rx_status, tx_status); /***** receive section ******/ @@ -1178,14 +1123,14 @@ xirc2ps_interrupt(int irq, void *dev_id) /* too many bytes received during this int, drop the rest of the * packets */ dev->stats.rx_dropped++; - DEBUG(2, "%s: RX drop, too much done\n", dev->name); + pr_debug("%s: RX drop, too much done\n", dev->name); } else if (rsr & PktRxOk) { struct sk_buff *skb; pktlen = GetWord(XIRCREG0_RBC); bytes_rcvd += pktlen; - DEBUG(5, "rsr=%#02x packet_length=%u\n", rsr, pktlen); + pr_debug("rsr=%#02x packet_length=%u\n", rsr, pktlen); skb = dev_alloc_skb(pktlen+3); /* 1 extra so we can use insw */ if (!skb) { @@ -1253,19 +1198,19 @@ xirc2ps_interrupt(int irq, void *dev_id) dev->stats.multicast++; } } else { /* bad packet */ - DEBUG(5, "rsr=%#02x\n", rsr); + pr_debug("rsr=%#02x\n", rsr); } if (rsr & PktTooLong) { dev->stats.rx_frame_errors++; - DEBUG(3, "%s: Packet too long\n", dev->name); + pr_debug("%s: Packet too long\n", dev->name); } if (rsr & CRCErr) { dev->stats.rx_crc_errors++; - DEBUG(3, "%s: CRC error\n", dev->name); + pr_debug("%s: CRC error\n", dev->name); } if (rsr & AlignErr) { dev->stats.rx_fifo_errors++; /* okay ? */ - DEBUG(3, "%s: Alignment error\n", dev->name); + pr_debug("%s: Alignment error\n", dev->name); } /* clear the received/dropped/error packet */ @@ -1277,7 +1222,7 @@ xirc2ps_interrupt(int irq, void *dev_id) if (rx_status & 0x10) { /* Receive overrun */ dev->stats.rx_over_errors++; PutByte(XIRCREG_CR, ClearRxOvrun); - DEBUG(3, "receive overrun cleared\n"); + pr_debug("receive overrun cleared\n"); } /***** transmit section ******/ @@ -1290,13 +1235,13 @@ xirc2ps_interrupt(int irq, void *dev_id) if (nn < n) /* rollover */ dev->stats.tx_packets += 256 - n; else if (n == nn) { /* happens sometimes - don't know why */ - DEBUG(0, "PTR not changed?\n"); + pr_debug("PTR not changed?\n"); } else dev->stats.tx_packets += lp->last_ptr_value - n; netif_wake_queue(dev); } if (tx_status & 0x0002) { /* Execessive collissions */ - DEBUG(0, "tx restarted due to execssive collissions\n"); + pr_debug("tx restarted due to execssive collissions\n"); PutByte(XIRCREG_CR, RestartTx); /* restart transmitter process */ } if (tx_status & 0x0040) @@ -1315,14 +1260,14 @@ xirc2ps_interrupt(int irq, void *dev_id) maxrx_bytes = 2000; else if (maxrx_bytes > 22000) maxrx_bytes = 22000; - DEBUG(1, "set maxrx=%u (rcvd=%u ticks=%lu)\n", + pr_debug("set maxrx=%u (rcvd=%u ticks=%lu)\n", maxrx_bytes, bytes_rcvd, duration); } else if (!duration && maxrx_bytes < 22000) { /* now much faster */ maxrx_bytes += 2000; if (maxrx_bytes > 22000) maxrx_bytes = 22000; - DEBUG(1, "set maxrx=%u\n", maxrx_bytes); + pr_debug("set maxrx=%u\n", maxrx_bytes); } } @@ -1372,7 +1317,7 @@ do_start_xmit(struct sk_buff *skb, struct net_device *dev) unsigned freespace; unsigned pktlen = skb->len; - DEBUG(1, "do_start_xmit(skb=%p, dev=%p) len=%u\n", + pr_debug("do_start_xmit(skb=%p, dev=%p) len=%u\n", skb, dev, pktlen); @@ -1398,7 +1343,7 @@ do_start_xmit(struct sk_buff *skb, struct net_device *dev) freespace &= 0x7fff; /* TRS doesn't work - (indeed it is eliminated with sil-rev 1) */ okay = pktlen +2 < freespace; - DEBUG(2 + (okay ? 2 : 0), "%s: avail. tx space=%u%s\n", + pr_debug("%s: avail. tx space=%u%s\n", dev->name, freespace, okay ? " (okay)":" (not enough)"); if (!okay) { /* not enough space */ return NETDEV_TX_BUSY; /* upper layer may decide to requeue this packet */ @@ -1500,7 +1445,7 @@ do_config(struct net_device *dev, struct ifmap *map) { local_info_t *local = netdev_priv(dev); - DEBUG(0, "do_config(%p)\n", dev); + pr_debug("do_config(%p)\n", dev); if (map->port != 255 && map->port != dev->if_port) { if (map->port > 4) return -EINVAL; @@ -1527,7 +1472,7 @@ do_open(struct net_device *dev) local_info_t *lp = netdev_priv(dev); struct pcmcia_device *link = lp->p_dev; - DEBUG(0, "do_open(%p)\n", dev); + dev_dbg(&link->dev, "do_open(%p)\n", dev); /* Check that the PCMCIA card is still here. */ /* Physical device present signature. */ @@ -1561,7 +1506,7 @@ do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) unsigned int ioaddr = dev->base_addr; struct mii_ioctl_data *data = if_mii(rq); - DEBUG(1, "%s: ioctl(%-.6s, %#04x) %04x %04x %04x %04x\n", + pr_debug("%s: ioctl(%-.6s, %#04x) %04x %04x %04x %04x\n", dev->name, rq->ifr_ifrn.ifrn_name, cmd, data->phy_id, data->reg_num, data->val_in, data->val_out); @@ -1610,7 +1555,7 @@ do_reset(struct net_device *dev, int full) unsigned int ioaddr = dev->base_addr; unsigned value; - DEBUG(0, "%s: do_reset(%p,%d)\n", dev? dev->name:"eth?", dev, full); + pr_debug("%s: do_reset(%p,%d)\n", dev? dev->name:"eth?", dev, full); hardreset(dev); PutByte(XIRCREG_CR, SoftReset); /* set */ @@ -1648,8 +1593,8 @@ do_reset(struct net_device *dev, int full) } msleep(40); /* wait 40 msec to let it complete */ - #ifdef PCMCIA_DEBUG - if (pc_debug) { + #if 0 + { SelectPage(0); value = GetByte(XIRCREG_ESR); /* read the ESR */ printk(KERN_DEBUG "%s: ESR is: %#02x\n", dev->name, value); @@ -1666,7 +1611,7 @@ do_reset(struct net_device *dev, int full) value |= DisableLinkPulse; PutByte(XIRCREG1_ECR, value); #endif - DEBUG(0, "%s: ECR is: %#02x\n", dev->name, value); + pr_debug("%s: ECR is: %#02x\n", dev->name, value); SelectPage(0x42); PutByte(XIRCREG42_SWC0, 0x20); /* disable source insertion */ @@ -1844,7 +1789,7 @@ do_powerdown(struct net_device *dev) unsigned int ioaddr = dev->base_addr; - DEBUG(0, "do_powerdown(%p)\n", dev); + pr_debug("do_powerdown(%p)\n", dev); SelectPage(4); PutByte(XIRCREG4_GPR1, 0); /* clear bit 0: power down */ @@ -1858,7 +1803,7 @@ do_stop(struct net_device *dev) local_info_t *lp = netdev_priv(dev); struct pcmcia_device *link = lp->p_dev; - DEBUG(0, "do_stop(%p)\n", dev); + dev_dbg(&link->dev, "do_stop(%p)\n", dev); if (!link) return -ENODEV; diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c index b9221bdc7184..0fe2fc90f207 100644 --- a/drivers/net/r8169.c +++ b/drivers/net/r8169.c @@ -3235,6 +3235,10 @@ static void __devexit rtl8169_remove_one(struct pci_dev *pdev) flush_scheduled_work(); unregister_netdev(dev); + + /* restore original MAC address */ + rtl_rar_set(tp, dev->perm_addr); + rtl_disable_msi(pdev, tp); rtl8169_release_board(pdev, dev, tp->mmio_addr); pci_set_drvdata(pdev, NULL); @@ -4881,6 +4885,9 @@ static void rtl_shutdown(struct pci_dev *pdev) rtl8169_net_suspend(dev); + /* restore original MAC address */ + rtl_rar_set(tp, dev->perm_addr); + spin_lock_irq(&tp->lock); rtl8169_asic_down(ioaddr); diff --git a/drivers/net/smc91x.c b/drivers/net/smc91x.c index 05c91ee6921e..f12206bdbb75 100644 --- a/drivers/net/smc91x.c +++ b/drivers/net/smc91x.c @@ -2283,7 +2283,7 @@ static int __devinit smc_drv_probe(struct platform_device *pdev) ndev->irq = ires->start; - if (ires->flags & IRQF_TRIGGER_MASK) + if (irq_flags == -1 || ires->flags & IRQF_TRIGGER_MASK) irq_flags = ires->flags & IRQF_TRIGGER_MASK; ret = smc_request_attrib(pdev, ndev); diff --git a/drivers/net/smsc9420.c b/drivers/net/smsc9420.c index b4909a2dec66..0f7909276237 100644 --- a/drivers/net/smsc9420.c +++ b/drivers/net/smsc9420.c @@ -252,6 +252,9 @@ static int smsc9420_ethtool_get_settings(struct net_device *dev, { struct smsc9420_pdata *pd = netdev_priv(dev); + if (!pd->phy_dev) + return -ENODEV; + cmd->maxtxpkt = 1; cmd->maxrxpkt = 1; return phy_ethtool_gset(pd->phy_dev, cmd); @@ -262,6 +265,9 @@ static int smsc9420_ethtool_set_settings(struct net_device *dev, { struct smsc9420_pdata *pd = netdev_priv(dev); + if (!pd->phy_dev) + return -ENODEV; + return phy_ethtool_sset(pd->phy_dev, cmd); } @@ -290,6 +296,10 @@ static void smsc9420_ethtool_set_msglevel(struct net_device *netdev, u32 data) static int smsc9420_ethtool_nway_reset(struct net_device *netdev) { struct smsc9420_pdata *pd = netdev_priv(netdev); + + if (!pd->phy_dev) + return -ENODEV; + return phy_start_aneg(pd->phy_dev); } @@ -312,6 +322,10 @@ smsc9420_ethtool_getregs(struct net_device *dev, struct ethtool_regs *regs, for (i = 0; i < 0x100; i += (sizeof(u32))) data[j++] = smsc9420_reg_read(pd, i); + // cannot read phy registers if the net device is down + if (!phy_dev) + return; + for (i = 0; i <= 31; i++) data[j++] = smsc9420_mii_read(phy_dev->bus, phy_dev->addr, i); } diff --git a/drivers/net/stmmac/stmmac_main.c b/drivers/net/stmmac/stmmac_main.c index c2f14dc9ba28..9542995ba667 100644 --- a/drivers/net/stmmac/stmmac_main.c +++ b/drivers/net/stmmac/stmmac_main.c @@ -416,13 +416,8 @@ static void init_dma_desc_rings(struct net_device *dev) unsigned int txsize = priv->dma_tx_size; unsigned int rxsize = priv->dma_rx_size; unsigned int bfsize = priv->dma_buf_sz; - int buff2_needed = 0; - int dis_ic = 0; + int buff2_needed = 0, dis_ic = 0; -#ifdef CONFIG_STMMAC_TIMER - /* Using Timers disable interrupts on completion for the reception */ - dis_ic = 1; -#endif /* Set the Buffer size according to the MTU; * indeed, in case of jumbo we need to bump-up the buffer sizes. */ @@ -437,6 +432,11 @@ static void init_dma_desc_rings(struct net_device *dev) else bfsize = DMA_BUFFER_SIZE; +#ifdef CONFIG_STMMAC_TIMER + /* Disable interrupts on completion for the reception if timer is on */ + if (likely(priv->tm->enable)) + dis_ic = 1; +#endif /* If the MTU exceeds 8k so use the second buffer in the chain */ if (bfsize >= BUF_SIZE_8KiB) buff2_needed = 1; @@ -809,20 +809,22 @@ static void stmmac_tx(struct stmmac_priv *priv) static inline void stmmac_enable_irq(struct stmmac_priv *priv) { -#ifndef CONFIG_STMMAC_TIMER - writel(DMA_INTR_DEFAULT_MASK, priv->dev->base_addr + DMA_INTR_ENA); -#else - priv->tm->timer_start(tmrate); +#ifdef CONFIG_STMMAC_TIMER + if (likely(priv->tm->enable)) + priv->tm->timer_start(tmrate); + else #endif + writel(DMA_INTR_DEFAULT_MASK, priv->dev->base_addr + DMA_INTR_ENA); } static inline void stmmac_disable_irq(struct stmmac_priv *priv) { -#ifndef CONFIG_STMMAC_TIMER - writel(0, priv->dev->base_addr + DMA_INTR_ENA); -#else - priv->tm->timer_stop(); +#ifdef CONFIG_STMMAC_TIMER + if (likely(priv->tm->enable)) + priv->tm->timer_stop(); + else #endif + writel(0, priv->dev->base_addr + DMA_INTR_ENA); } static int stmmac_has_work(struct stmmac_priv *priv) @@ -1031,22 +1033,23 @@ static int stmmac_open(struct net_device *dev) } #ifdef CONFIG_STMMAC_TIMER - priv->tm = kmalloc(sizeof(struct stmmac_timer *), GFP_KERNEL); + priv->tm = kzalloc(sizeof(struct stmmac_timer *), GFP_KERNEL); if (unlikely(priv->tm == NULL)) { pr_err("%s: ERROR: timer memory alloc failed \n", __func__); return -ENOMEM; } priv->tm->freq = tmrate; - /* Test if the HW timer can be actually used. - * In case of failure continue with no timer. */ + /* Test if the external timer can be actually used. + * In case of failure continue without timer. */ if (unlikely((stmmac_open_ext_timer(dev, priv->tm)) < 0)) { - pr_warning("stmmaceth: cannot attach the HW timer\n"); + pr_warning("stmmaceth: cannot attach the external timer.\n"); tmrate = 0; priv->tm->freq = 0; priv->tm->timer_start = stmmac_no_timer_started; priv->tm->timer_stop = stmmac_no_timer_stopped; - } + } else + priv->tm->enable = 1; #endif /* Create and initialize the TX/RX descriptors chains. */ @@ -1322,9 +1325,11 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) /* Interrupt on completition only for the latest segment */ priv->mac_type->ops->close_tx_desc(desc); + #ifdef CONFIG_STMMAC_TIMER - /* Clean IC while using timers */ - priv->mac_type->ops->clear_tx_ic(desc); + /* Clean IC while using timer */ + if (likely(priv->tm->enable)) + priv->mac_type->ops->clear_tx_ic(desc); #endif /* To avoid raise condition */ priv->mac_type->ops->set_tx_owner(first); @@ -2028,7 +2033,8 @@ static int stmmac_suspend(struct platform_device *pdev, pm_message_t state) #ifdef CONFIG_STMMAC_TIMER priv->tm->timer_stop(); - dis_ic = 1; + if (likely(priv->tm->enable)) + dis_ic = 1; #endif napi_disable(&priv->napi); diff --git a/drivers/net/stmmac/stmmac_timer.c b/drivers/net/stmmac/stmmac_timer.c index b838c6582077..679f61ffb1f8 100644 --- a/drivers/net/stmmac/stmmac_timer.c +++ b/drivers/net/stmmac/stmmac_timer.c @@ -63,7 +63,7 @@ int stmmac_open_ext_timer(struct net_device *dev, struct stmmac_timer *tm) stmmac_rtc = rtc_class_open(CONFIG_RTC_HCTOSYS_DEVICE); if (stmmac_rtc == NULL) { - pr_error("open rtc device failed\n"); + pr_err("open rtc device failed\n"); return -ENODEV; } @@ -71,7 +71,7 @@ int stmmac_open_ext_timer(struct net_device *dev, struct stmmac_timer *tm) /* Periodic mode is not supported */ if ((rtc_irq_set_freq(stmmac_rtc, &stmmac_task, tm->freq) < 0)) { - pr_error("set periodic failed\n"); + pr_err("set periodic failed\n"); rtc_irq_unregister(stmmac_rtc, &stmmac_task); rtc_class_close(stmmac_rtc); return -1; diff --git a/drivers/net/stmmac/stmmac_timer.h b/drivers/net/stmmac/stmmac_timer.h index f795cae33725..6863590d184b 100644 --- a/drivers/net/stmmac/stmmac_timer.h +++ b/drivers/net/stmmac/stmmac_timer.h @@ -26,6 +26,7 @@ struct stmmac_timer { void (*timer_start) (unsigned int new_freq); void (*timer_stop) (void); unsigned int freq; + unsigned int enable; }; /* Open the HW timer device and return 0 in case of success */ diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index fa4e58196c21..43bc3fcc0d85 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -378,7 +378,7 @@ static void dbg_dump(int line_count, const char *func_name, unsigned char *buf, } #define DUMP(buf_, len_) \ - dbg_dump(__LINE__, __func__, buf_, len_) + dbg_dump(__LINE__, __func__, (unsigned char *)buf_, len_) #define DUMP1(buf_, len_) \ do { \ @@ -1363,7 +1363,7 @@ static void hso_serial_close(struct tty_struct *tty, struct file *filp) /* reset the rts and dtr */ /* do the actual close */ serial->open_count--; - kref_put(&serial->parent->ref, hso_serial_ref_free); + if (serial->open_count <= 0) { serial->open_count = 0; spin_lock_irq(&serial->serial_lock); @@ -1383,6 +1383,8 @@ static void hso_serial_close(struct tty_struct *tty, struct file *filp) usb_autopm_put_interface(serial->parent->interface); mutex_unlock(&serial->parent->mutex); + + kref_put(&serial->parent->ref, hso_serial_ref_free); } /* close the requested serial port */ @@ -1527,7 +1529,7 @@ static void tiocmget_intr_callback(struct urb *urb) dev_warn(&usb->dev, "hso received invalid serial state notification\n"); DUMP(serial_state_notification, - sizeof(hso_serial_state_notifation)) + sizeof(struct hso_serial_state_notification)); } else { UART_state_bitmap = le16_to_cpu(serial_state_notification-> diff --git a/drivers/net/veth.c b/drivers/net/veth.c index ade5b344f75d..52af5017c46b 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -210,32 +210,29 @@ rx_drop: static struct net_device_stats *veth_get_stats(struct net_device *dev) { struct veth_priv *priv; - struct net_device_stats *dev_stats; int cpu; - struct veth_net_stats *stats; + struct veth_net_stats *stats, total = {0}; priv = netdev_priv(dev); - dev_stats = &dev->stats; - - dev_stats->rx_packets = 0; - dev_stats->tx_packets = 0; - dev_stats->rx_bytes = 0; - dev_stats->tx_bytes = 0; - dev_stats->tx_dropped = 0; - dev_stats->rx_dropped = 0; - for_each_online_cpu(cpu) { + for_each_possible_cpu(cpu) { stats = per_cpu_ptr(priv->stats, cpu); - dev_stats->rx_packets += stats->rx_packets; - dev_stats->tx_packets += stats->tx_packets; - dev_stats->rx_bytes += stats->rx_bytes; - dev_stats->tx_bytes += stats->tx_bytes; - dev_stats->tx_dropped += stats->tx_dropped; - dev_stats->rx_dropped += stats->rx_dropped; + total.rx_packets += stats->rx_packets; + total.tx_packets += stats->tx_packets; + total.rx_bytes += stats->rx_bytes; + total.tx_bytes += stats->tx_bytes; + total.tx_dropped += stats->tx_dropped; + total.rx_dropped += stats->rx_dropped; } - - return dev_stats; + dev->stats.rx_packets = total.rx_packets; + dev->stats.tx_packets = total.tx_packets; + dev->stats.rx_bytes = total.rx_bytes; + dev->stats.tx_bytes = total.tx_bytes; + dev->stats.tx_dropped = total.tx_dropped; + dev->stats.rx_dropped = total.rx_dropped; + + return &dev->stats; } static int veth_open(struct net_device *dev) diff --git a/drivers/net/wan/cosa.c b/drivers/net/wan/cosa.c index e2c33c06190b..8e25ca7080c7 100644 --- a/drivers/net/wan/cosa.c +++ b/drivers/net/wan/cosa.c @@ -907,6 +907,7 @@ static ssize_t cosa_write(struct file *file, current->state = TASK_RUNNING; chan->tx_status = 1; spin_unlock_irqrestore(&cosa->lock, flags); + up(&chan->wsem); return -ERESTARTSYS; } } diff --git a/drivers/net/wireless/airo_cs.c b/drivers/net/wireless/airo_cs.c index d0593ed9170e..f6036fb42319 100644 --- a/drivers/net/wireless/airo_cs.c +++ b/drivers/net/wireless/airo_cs.c @@ -43,21 +43,6 @@ #include "airo.h" -/* - All the PCMCIA modules use PCMCIA_DEBUG to control debugging. If - you do not define PCMCIA_DEBUG at all, all the debug code will be - left out. If you compile with PCMCIA_DEBUG=0, the debug code will - be present but disabled -- but it can then be enabled for specific - modules at load time with a 'pc_debug=#' option to insmod. -*/ -#ifdef PCMCIA_DEBUG -static int pc_debug = PCMCIA_DEBUG; -module_param(pc_debug, int, 0); -static char *version = "$Revision: 1.2 $"; -#define DEBUG(n, args...) if (pc_debug > (n)) printk(KERN_DEBUG args); -#else -#define DEBUG(n, args...) -#endif /*====================================================================*/ @@ -145,11 +130,10 @@ static int airo_probe(struct pcmcia_device *p_dev) { local_info_t *local; - DEBUG(0, "airo_attach()\n"); + dev_dbg(&p_dev->dev, "airo_attach()\n"); /* Interrupt setup */ p_dev->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; - p_dev->irq.IRQInfo1 = IRQ_LEVEL_ID; p_dev->irq.Handler = NULL; /* @@ -184,7 +168,7 @@ static int airo_probe(struct pcmcia_device *p_dev) static void airo_detach(struct pcmcia_device *link) { - DEBUG(0, "airo_detach(0x%p)\n", link); + dev_dbg(&link->dev, "airo_detach\n"); airo_release(link); @@ -204,9 +188,6 @@ static void airo_detach(struct pcmcia_device *link) ======================================================================*/ -#define CS_CHECK(fn, ret) \ -do { last_fn = (fn); if ((last_ret = (ret)) != 0) goto cs_failed; } while (0) - static int airo_cs_config_check(struct pcmcia_device *p_dev, cistpl_cftable_entry_t *cfg, cistpl_cftable_entry_t *dflt, @@ -275,11 +256,11 @@ static int airo_cs_config_check(struct pcmcia_device *p_dev, req->Base = mem->win[0].host_addr; req->Size = mem->win[0].len; req->AccessSpeed = 0; - if (pcmcia_request_window(&p_dev, req, &p_dev->win) != 0) + if (pcmcia_request_window(p_dev, req, &p_dev->win) != 0) return -ENODEV; map.Page = 0; map.CardOffset = mem->win[0].card_addr; - if (pcmcia_map_mem_page(p_dev->win, &map) != 0) + if (pcmcia_map_mem_page(p_dev, p_dev->win, &map) != 0) return -ENODEV; } /* If we got this far, we're cool! */ @@ -291,11 +272,11 @@ static int airo_config(struct pcmcia_device *link) { local_info_t *dev; win_req_t *req; - int last_fn, last_ret; + int ret; dev = link->priv; - DEBUG(0, "airo_config(0x%p)\n", link); + dev_dbg(&link->dev, "airo_config\n"); req = kzalloc(sizeof(win_req_t), GFP_KERNEL); if (!req) @@ -315,8 +296,8 @@ static int airo_config(struct pcmcia_device *link) * and most client drivers will only use the CIS to fill in * implementation-defined details. */ - last_ret = pcmcia_loop_config(link, airo_cs_config_check, req); - if (last_ret) + ret = pcmcia_loop_config(link, airo_cs_config_check, req); + if (ret) goto failed; /* @@ -324,21 +305,25 @@ static int airo_config(struct pcmcia_device *link) handler to the interrupt, unless the 'Handler' member of the irq structure is initialized. */ - if (link->conf.Attributes & CONF_ENABLE_IRQ) - CS_CHECK(RequestIRQ, pcmcia_request_irq(link, &link->irq)); + if (link->conf.Attributes & CONF_ENABLE_IRQ) { + ret = pcmcia_request_irq(link, &link->irq); + if (ret) + goto failed; + } /* This actually configures the PCMCIA socket -- setting up the I/O windows and the interrupt mapping, and putting the card and host interface into "Memory and IO" mode. */ - CS_CHECK(RequestConfiguration, - pcmcia_request_configuration(link, &link->conf)); + ret = pcmcia_request_configuration(link, &link->conf); + if (ret) + goto failed; ((local_info_t *)link->priv)->eth_dev = init_airo_card(link->irq.AssignedIRQ, - link->io.BasePort1, 1, &handle_to_dev(link)); + link->io.BasePort1, 1, &link->dev); if (!((local_info_t *)link->priv)->eth_dev) - goto cs_failed; + goto failed; /* At this point, the dev_node_t structure(s) need to be @@ -368,8 +353,6 @@ static int airo_config(struct pcmcia_device *link) kfree(req); return 0; - cs_failed: - cs_error(link, last_fn, last_ret); failed: airo_release(link); kfree(req); @@ -386,7 +369,7 @@ static int airo_config(struct pcmcia_device *link) static void airo_release(struct pcmcia_device *link) { - DEBUG(0, "airo_release(0x%p)\n", link); + dev_dbg(&link->dev, "airo_release\n"); pcmcia_disable_device(link); } diff --git a/drivers/net/wireless/arlan-proc.c b/drivers/net/wireless/arlan-proc.c index a8b689635a3b..b22983e6c0cf 100644 --- a/drivers/net/wireless/arlan-proc.c +++ b/drivers/net/wireless/arlan-proc.c @@ -816,84 +816,83 @@ static int arlan_sysctl_reset(ctl_table * ctl, int write, /* Place files in /proc/sys/dev/arlan */ -#define CTBLN(num,card,nam) \ - { .ctl_name = num,\ - .procname = #nam,\ +#define CTBLN(card,nam) \ + { .procname = #nam,\ .data = &(arlan_conf[card].nam),\ - .maxlen = sizeof(int), .mode = 0600, .proc_handler = &proc_dointvec} + .maxlen = sizeof(int), .mode = 0600, .proc_handler = proc_dointvec} #ifdef ARLAN_DEBUGGING #define ARLAN_PROC_DEBUG_ENTRIES \ - { .ctl_name = 48, .procname = "entry_exit_debug",\ + { .procname = "entry_exit_debug",\ .data = &arlan_entry_and_exit_debug,\ - .maxlen = sizeof(int), .mode = 0600, .proc_handler = &proc_dointvec},\ - { .ctl_name = 49, .procname = "debug", .data = &arlan_debug,\ - .maxlen = sizeof(int), .mode = 0600, .proc_handler = &proc_dointvec}, + .maxlen = sizeof(int), .mode = 0600, .proc_handler = proc_dointvec},\ + { .procname = "debug", .data = &arlan_debug,\ + .maxlen = sizeof(int), .mode = 0600, .proc_handler = proc_dointvec}, #else #define ARLAN_PROC_DEBUG_ENTRIES #endif #define ARLAN_SYSCTL_TABLE_TOTAL(cardNo)\ - CTBLN(1,cardNo,spreadingCode),\ - CTBLN(2,cardNo, channelNumber),\ - CTBLN(3,cardNo, scramblingDisable),\ - CTBLN(4,cardNo, txAttenuation),\ - CTBLN(5,cardNo, systemId), \ - CTBLN(6,cardNo, maxDatagramSize),\ - CTBLN(7,cardNo, maxFrameSize),\ - CTBLN(8,cardNo, maxRetries),\ - CTBLN(9,cardNo, receiveMode),\ - CTBLN(10,cardNo, priority),\ - CTBLN(11,cardNo, rootOrRepeater),\ - CTBLN(12,cardNo, SID),\ - CTBLN(13,cardNo, registrationMode),\ - CTBLN(14,cardNo, registrationFill),\ - CTBLN(15,cardNo, localTalkAddress),\ - CTBLN(16,cardNo, codeFormat),\ - CTBLN(17,cardNo, numChannels),\ - CTBLN(18,cardNo, channel1),\ - CTBLN(19,cardNo, channel2),\ - CTBLN(20,cardNo, channel3),\ - CTBLN(21,cardNo, channel4),\ - CTBLN(22,cardNo, txClear),\ - CTBLN(23,cardNo, txRetries),\ - CTBLN(24,cardNo, txRouting),\ - CTBLN(25,cardNo, txScrambled),\ - CTBLN(26,cardNo, rxParameter),\ - CTBLN(27,cardNo, txTimeoutMs),\ - CTBLN(28,cardNo, waitCardTimeout),\ - CTBLN(29,cardNo, channelSet), \ - {.ctl_name = 30, .procname = "name",\ + CTBLN(cardNo,spreadingCode),\ + CTBLN(cardNo, channelNumber),\ + CTBLN(cardNo, scramblingDisable),\ + CTBLN(cardNo, txAttenuation),\ + CTBLN(cardNo, systemId), \ + CTBLN(cardNo, maxDatagramSize),\ + CTBLN(cardNo, maxFrameSize),\ + CTBLN(cardNo, maxRetries),\ + CTBLN(cardNo, receiveMode),\ + CTBLN(cardNo, priority),\ + CTBLN(cardNo, rootOrRepeater),\ + CTBLN(cardNo, SID),\ + CTBLN(cardNo, registrationMode),\ + CTBLN(cardNo, registrationFill),\ + CTBLN(cardNo, localTalkAddress),\ + CTBLN(cardNo, codeFormat),\ + CTBLN(cardNo, numChannels),\ + CTBLN(cardNo, channel1),\ + CTBLN(cardNo, channel2),\ + CTBLN(cardNo, channel3),\ + CTBLN(cardNo, channel4),\ + CTBLN(cardNo, txClear),\ + CTBLN(cardNo, txRetries),\ + CTBLN(cardNo, txRouting),\ + CTBLN(cardNo, txScrambled),\ + CTBLN(cardNo, rxParameter),\ + CTBLN(cardNo, txTimeoutMs),\ + CTBLN(cardNo, waitCardTimeout),\ + CTBLN(cardNo, channelSet), \ + { .procname = "name",\ .data = arlan_conf[cardNo].siteName,\ - .maxlen = 16, .mode = 0600, .proc_handler = &proc_dostring},\ - CTBLN(31,cardNo,waitTime),\ - CTBLN(32,cardNo,lParameter),\ - CTBLN(33,cardNo,_15),\ - CTBLN(34,cardNo,headerSize),\ - CTBLN(36,cardNo,tx_delay_ms),\ - CTBLN(37,cardNo,retries),\ - CTBLN(38,cardNo,ReTransmitPacketMaxSize),\ - CTBLN(39,cardNo,waitReTransmitPacketMaxSize),\ - CTBLN(40,cardNo,fastReTransCount),\ - CTBLN(41,cardNo,driverRetransmissions),\ - CTBLN(42,cardNo,txAckTimeoutMs),\ - CTBLN(43,cardNo,registrationInterrupts),\ - CTBLN(44,cardNo,hardwareType),\ - CTBLN(45,cardNo,radioType),\ - CTBLN(46,cardNo,writeEEPROM),\ - CTBLN(47,cardNo,writeRadioType),\ + .maxlen = 16, .mode = 0600, .proc_handler = proc_dostring},\ + CTBLN(cardNo,waitTime),\ + CTBLN(cardNo,lParameter),\ + CTBLN(cardNo,_15),\ + CTBLN(cardNo,headerSize),\ + CTBLN(cardNo,tx_delay_ms),\ + CTBLN(cardNo,retries),\ + CTBLN(cardNo,ReTransmitPacketMaxSize),\ + CTBLN(cardNo,waitReTransmitPacketMaxSize),\ + CTBLN(cardNo,fastReTransCount),\ + CTBLN(cardNo,driverRetransmissions),\ + CTBLN(cardNo,txAckTimeoutMs),\ + CTBLN(cardNo,registrationInterrupts),\ + CTBLN(cardNo,hardwareType),\ + CTBLN(cardNo,radioType),\ + CTBLN(cardNo,writeEEPROM),\ + CTBLN(cardNo,writeRadioType),\ ARLAN_PROC_DEBUG_ENTRIES\ - CTBLN(50,cardNo,in_speed),\ - CTBLN(51,cardNo,out_speed),\ - CTBLN(52,cardNo,in_speed10),\ - CTBLN(53,cardNo,out_speed10),\ - CTBLN(54,cardNo,in_speed_max),\ - CTBLN(55,cardNo,out_speed_max),\ - CTBLN(56,cardNo,measure_rate),\ - CTBLN(57,cardNo,pre_Command_Wait),\ - CTBLN(58,cardNo,rx_tweak1),\ - CTBLN(59,cardNo,rx_tweak2),\ - CTBLN(60,cardNo,tx_queue_len),\ + CTBLN(cardNo,in_speed),\ + CTBLN(cardNo,out_speed),\ + CTBLN(cardNo,in_speed10),\ + CTBLN(cardNo,out_speed10),\ + CTBLN(cardNo,in_speed_max),\ + CTBLN(cardNo,out_speed_max),\ + CTBLN(cardNo,measure_rate),\ + CTBLN(cardNo,pre_Command_Wait),\ + CTBLN(cardNo,rx_tweak1),\ + CTBLN(cardNo,rx_tweak2),\ + CTBLN(cardNo,tx_queue_len),\ @@ -903,63 +902,56 @@ static ctl_table arlan_conf_table0[] = #ifdef ARLAN_PROC_SHM_DUMP { - .ctl_name = 150, .procname = "arlan0-txRing", .data = &arlan_drive_info, .maxlen = ARLAN_STR_SIZE, .mode = 0400, - .proc_handler = &arlan_sysctl_infotxRing, + .proc_handler = arlan_sysctl_infotxRing, }, { - .ctl_name = 151, .procname = "arlan0-rxRing", .data = &arlan_drive_info, .maxlen = ARLAN_STR_SIZE, .mode = 0400, - .proc_handler = &arlan_sysctl_inforxRing, + .proc_handler = arlan_sysctl_inforxRing, }, { - .ctl_name = 152, .procname = "arlan0-18", .data = &arlan_drive_info, .maxlen = ARLAN_STR_SIZE, .mode = 0400, - .proc_handler = &arlan_sysctl_info18, + .proc_handler = arlan_sysctl_info18, }, { - .ctl_name = 153, .procname = "arlan0-ring", .data = &arlan_drive_info, .maxlen = ARLAN_STR_SIZE, .mode = 0400, - .proc_handler = &arlan_sysctl_info161719, + .proc_handler = arlan_sysctl_info161719, }, { - .ctl_name = 154, .procname = "arlan0-shm-cpy", .data = &arlan_drive_info, .maxlen = ARLAN_STR_SIZE, .mode = 0400, - .proc_handler = &arlan_sysctl_info, + .proc_handler = arlan_sysctl_info, }, #endif { - .ctl_name = 155, .procname = "config0", .data = &conf_reset_result, .maxlen = 100, .mode = 0400, - .proc_handler = &arlan_configure + .proc_handler = arlan_configure }, { - .ctl_name = 156, .procname = "reset0", .data = &conf_reset_result, .maxlen = 100, .mode = 0400, - .proc_handler = &arlan_sysctl_reset, + .proc_handler = arlan_sysctl_reset, }, - { .ctl_name = 0 } + { } }; static ctl_table arlan_conf_table1[] = @@ -969,63 +961,56 @@ static ctl_table arlan_conf_table1[] = #ifdef ARLAN_PROC_SHM_DUMP { - .ctl_name = 150, .procname = "arlan1-txRing", .data = &arlan_drive_info, .maxlen = ARLAN_STR_SIZE, .mode = 0400, - .proc_handler = &arlan_sysctl_infotxRing, + .proc_handler = arlan_sysctl_infotxRing, }, { - .ctl_name = 151, .procname = "arlan1-rxRing", .data = &arlan_drive_info, .maxlen = ARLAN_STR_SIZE, .mode = 0400, - .proc_handler = &arlan_sysctl_inforxRing, + .proc_handler = arlan_sysctl_inforxRing, }, { - .ctl_name = 152, .procname = "arlan1-18", .data = &arlan_drive_info, .maxlen = ARLAN_STR_SIZE, .mode = 0400, - .proc_handler = &arlan_sysctl_info18, + .proc_handler = arlan_sysctl_info18, }, { - .ctl_name = 153, .procname = "arlan1-ring", .data = &arlan_drive_info, .maxlen = ARLAN_STR_SIZE, .mode = 0400, - .proc_handler = &arlan_sysctl_info161719, + .proc_handler = arlan_sysctl_info161719, }, { - .ctl_name = 154, .procname = "arlan1-shm-cpy", .data = &arlan_drive_info, .maxlen = ARLAN_STR_SIZE, .mode = 0400, - .proc_handler = &arlan_sysctl_info, + .proc_handler = arlan_sysctl_info, }, #endif { - .ctl_name = 155, .procname = "config1", .data = &conf_reset_result, .maxlen = 100, .mode = 0400, - .proc_handler = &arlan_configure, + .proc_handler = arlan_configure, }, { - .ctl_name = 156, .procname = "reset1", .data = &conf_reset_result, .maxlen = 100, .mode = 0400, - .proc_handler = &arlan_sysctl_reset, + .proc_handler = arlan_sysctl_reset, }, - { .ctl_name = 0 } + { } }; static ctl_table arlan_conf_table2[] = @@ -1035,63 +1020,56 @@ static ctl_table arlan_conf_table2[] = #ifdef ARLAN_PROC_SHM_DUMP { - .ctl_name = 150, .procname = "arlan2-txRing", .data = &arlan_drive_info, .maxlen = ARLAN_STR_SIZE, .mode = 0400, - .proc_handler = &arlan_sysctl_infotxRing, + .proc_handler = arlan_sysctl_infotxRing, }, { - .ctl_name = 151, .procname = "arlan2-rxRing", .data = &arlan_drive_info, .maxlen = ARLAN_STR_SIZE, .mode = 0400, - .proc_handler = &arlan_sysctl_inforxRing, + .proc_handler = arlan_sysctl_inforxRing, }, { - .ctl_name = 152, .procname = "arlan2-18", .data = &arlan_drive_info, .maxlen = ARLAN_STR_SIZE, .mode = 0400, - .proc_handler = &arlan_sysctl_info18, + .proc_handler = arlan_sysctl_info18, }, { - .ctl_name = 153, .procname = "arlan2-ring", .data = &arlan_drive_info, .maxlen = ARLAN_STR_SIZE, .mode = 0400, - .proc_handler = &arlan_sysctl_info161719, + .proc_handler = arlan_sysctl_info161719, }, { - .ctl_name = 154, .procname = "arlan2-shm-cpy", .data = &arlan_drive_info, .maxlen = ARLAN_STR_SIZE, .mode = 0400, - .proc_handler = &arlan_sysctl_info, + .proc_handler = arlan_sysctl_info, }, #endif { - .ctl_name = 155, .procname = "config2", .data = &conf_reset_result, .maxlen = 100, .mode = 0400, - .proc_handler = &arlan_configure, + .proc_handler = arlan_configure, }, { - .ctl_name = 156, .procname = "reset2", .data = &conf_reset_result, .maxlen = 100, .mode = 0400, - .proc_handler = &arlan_sysctl_reset, + .proc_handler = arlan_sysctl_reset, }, - { .ctl_name = 0 } + { } }; static ctl_table arlan_conf_table3[] = @@ -1101,63 +1079,56 @@ static ctl_table arlan_conf_table3[] = #ifdef ARLAN_PROC_SHM_DUMP { - .ctl_name = 150, .procname = "arlan3-txRing", .data = &arlan_drive_info, .maxlen = ARLAN_STR_SIZE, .mode = 0400, - .proc_handler = &arlan_sysctl_infotxRing, + .proc_handler = arlan_sysctl_infotxRing, }, { - .ctl_name = 151, .procname = "arlan3-rxRing", .data = &arlan_drive_info, .maxlen = ARLAN_STR_SIZE, .mode = 0400, - .proc_handler = &arlan_sysctl_inforxRing, + .proc_handler = arlan_sysctl_inforxRing, }, { - .ctl_name = 152, .procname = "arlan3-18", .data = &arlan_drive_info, .maxlen = ARLAN_STR_SIZE, .mode = 0400, - .proc_handler = &arlan_sysctl_info18, + .proc_handler = arlan_sysctl_info18, }, { - .ctl_name = 153, .procname = "arlan3-ring", .data = &arlan_drive_info, .maxlen = ARLAN_STR_SIZE, .mode = 0400, - .proc_handler = &arlan_sysctl_info161719, + .proc_handler = arlan_sysctl_info161719, }, { - .ctl_name = 154, .procname = "arlan3-shm-cpy", .data = &arlan_drive_info, .maxlen = ARLAN_STR_SIZE, .mode = 0400, - .proc_handler = &arlan_sysctl_info, + .proc_handler = arlan_sysctl_info, }, #endif { - .ctl_name = 155, .procname = "config3", .data = &conf_reset_result, .maxlen = 100, .mode = 0400, - .proc_handler = &arlan_configure, + .proc_handler = arlan_configure, }, { - .ctl_name = 156, .procname = "reset3", .data = &conf_reset_result, .maxlen = 100, .mode = 0400, - .proc_handler = &arlan_sysctl_reset, + .proc_handler = arlan_sysctl_reset, }, - { .ctl_name = 0 } + { } }; @@ -1165,41 +1136,37 @@ static ctl_table arlan_conf_table3[] = static ctl_table arlan_table[] = { { - .ctl_name = 0, .procname = "arlan0", .maxlen = 0, .mode = 0600, .child = arlan_conf_table0, }, { - .ctl_name = 0, .procname = "arlan1", .maxlen = 0, .mode = 0600, .child = arlan_conf_table1, }, { - .ctl_name = 0, .procname = "arlan2", .maxlen = 0, .mode = 0600, .child = arlan_conf_table2, }, { - .ctl_name = 0, .procname = "arlan3", .maxlen = 0, .mode = 0600, .child = arlan_conf_table3, }, - { .ctl_name = 0 } + { } }; #else -static ctl_table arlan_table[MAX_ARLANS + 1] = +static ctl_table arlan_table[] = { - { .ctl_name = 0 } + { } }; #endif @@ -1209,22 +1176,14 @@ static ctl_table arlan_table[MAX_ARLANS + 1] = static ctl_table arlan_root_table[] = { { - .ctl_name = CTL_ARLAN, .procname = "arlan", .maxlen = 0, .mode = 0555, .child = arlan_table, }, - { .ctl_name = 0 } + { } }; -/* Make sure that /proc/sys/dev is there */ -//static ctl_table arlan_device_root_table[] = -//{ -// {CTL_DEV, "dev", NULL, 0, 0555, arlan_root_table}, -// {0} -//}; - static struct ctl_table_header *arlan_device_sysctl_header; @@ -1234,8 +1193,6 @@ int __init init_arlan_proc(void) int i = 0; if (arlan_device_sysctl_header) return 0; - for (i = 0; i < MAX_ARLANS && arlan_device[i]; i++) - arlan_table[i].ctl_name = i + 1; arlan_device_sysctl_header = register_sysctl_table(arlan_root_table); if (!arlan_device_sysctl_header) return -1; diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c index 52bed89063d4..43d2be9867fc 100644 --- a/drivers/net/wireless/ath/ath9k/main.c +++ b/drivers/net/wireless/ath/ath9k/main.c @@ -1555,6 +1555,8 @@ void ath_set_hw_capab(struct ath_softc *sc, struct ieee80211_hw *hw) BIT(NL80211_IFTYPE_ADHOC) | BIT(NL80211_IFTYPE_MESH_POINT); + hw->wiphy->ps_default = false; + hw->queues = 4; hw->max_rates = 4; hw->channel_change_time = 5000; diff --git a/drivers/net/wireless/atmel_cs.c b/drivers/net/wireless/atmel_cs.c index ddaa859c3491..32407911842f 100644 --- a/drivers/net/wireless/atmel_cs.c +++ b/drivers/net/wireless/atmel_cs.c @@ -55,22 +55,6 @@ #include "atmel.h" -/* - All the PCMCIA modules use PCMCIA_DEBUG to control debugging. If - you do not define PCMCIA_DEBUG at all, all the debug code will be - left out. If you compile with PCMCIA_DEBUG=0, the debug code will - be present but disabled -- but it can then be enabled for specific - modules at load time with a 'pc_debug=#' option to insmod. -*/ - -#ifdef PCMCIA_DEBUG -static int pc_debug = PCMCIA_DEBUG; -module_param(pc_debug, int, 0); -static char *version = "$Revision: 1.2 $"; -#define DEBUG(n, args...) if (pc_debug>(n)) printk(KERN_DEBUG args); -#else -#define DEBUG(n, args...) -#endif /*====================================================================*/ @@ -155,11 +139,10 @@ static int atmel_probe(struct pcmcia_device *p_dev) { local_info_t *local; - DEBUG(0, "atmel_attach()\n"); + dev_dbg(&p_dev->dev, "atmel_attach()\n"); /* Interrupt setup */ p_dev->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; - p_dev->irq.IRQInfo1 = IRQ_LEVEL_ID; p_dev->irq.Handler = NULL; /* @@ -194,7 +177,7 @@ static int atmel_probe(struct pcmcia_device *p_dev) static void atmel_detach(struct pcmcia_device *link) { - DEBUG(0, "atmel_detach(0x%p)\n", link); + dev_dbg(&link->dev, "atmel_detach\n"); atmel_release(link); @@ -209,9 +192,6 @@ static void atmel_detach(struct pcmcia_device *link) ======================================================================*/ -#define CS_CHECK(fn, ret) \ -do { last_fn = (fn); if ((last_ret = (ret)) != 0) goto cs_failed; } while (0) - /* Call-back function to interrogate PCMCIA-specific information about the current existance of the card */ static int card_present(void *arg) @@ -275,13 +255,13 @@ static int atmel_config_check(struct pcmcia_device *p_dev, static int atmel_config(struct pcmcia_device *link) { local_info_t *dev; - int last_fn, last_ret; + int ret; struct pcmcia_device_id *did; dev = link->priv; - did = dev_get_drvdata(&handle_to_dev(link)); + did = dev_get_drvdata(&link->dev); - DEBUG(0, "atmel_config(0x%p)\n", link); + dev_dbg(&link->dev, "atmel_config\n"); /* In this loop, we scan the CIS for configuration table entries, @@ -303,31 +283,36 @@ static int atmel_config(struct pcmcia_device *link) handler to the interrupt, unless the 'Handler' member of the irq structure is initialized. */ - if (link->conf.Attributes & CONF_ENABLE_IRQ) - CS_CHECK(RequestIRQ, pcmcia_request_irq(link, &link->irq)); + if (link->conf.Attributes & CONF_ENABLE_IRQ) { + ret = pcmcia_request_irq(link, &link->irq); + if (ret) + goto failed; + } /* This actually configures the PCMCIA socket -- setting up the I/O windows and the interrupt mapping, and putting the card and host interface into "Memory and IO" mode. */ - CS_CHECK(RequestConfiguration, pcmcia_request_configuration(link, &link->conf)); + ret = pcmcia_request_configuration(link, &link->conf); + if (ret) + goto failed; if (link->irq.AssignedIRQ == 0) { printk(KERN_ALERT "atmel: cannot assign IRQ: check that CONFIG_ISA is set in kernel config."); - goto cs_failed; + goto failed; } ((local_info_t*)link->priv)->eth_dev = init_atmel_card(link->irq.AssignedIRQ, link->io.BasePort1, did ? did->driver_info : ATMEL_FW_TYPE_NONE, - &handle_to_dev(link), + &link->dev, card_present, link); if (!((local_info_t*)link->priv)->eth_dev) - goto cs_failed; + goto failed; /* @@ -340,8 +325,6 @@ static int atmel_config(struct pcmcia_device *link) return 0; - cs_failed: - cs_error(link, last_fn, last_ret); failed: atmel_release(link); return -ENODEV; @@ -359,7 +342,7 @@ static void atmel_release(struct pcmcia_device *link) { struct net_device *dev = ((local_info_t*)link->priv)->eth_dev; - DEBUG(0, "atmel_release(0x%p)\n", link); + dev_dbg(&link->dev, "atmel_release\n"); if (dev) stop_atmel_card(dev); diff --git a/drivers/net/wireless/b43/pcmcia.c b/drivers/net/wireless/b43/pcmcia.c index 6c3a74964ab8..984174bc7b0f 100644 --- a/drivers/net/wireless/b43/pcmcia.c +++ b/drivers/net/wireless/b43/pcmcia.c @@ -65,35 +65,15 @@ static int __devinit b43_pcmcia_probe(struct pcmcia_device *dev) struct ssb_bus *ssb; win_req_t win; memreq_t mem; - tuple_t tuple; - cisparse_t parse; int err = -ENOMEM; int res = 0; - unsigned char buf[64]; ssb = kzalloc(sizeof(*ssb), GFP_KERNEL); if (!ssb) goto out_error; err = -ENODEV; - tuple.DesiredTuple = CISTPL_CONFIG; - tuple.Attributes = 0; - tuple.TupleData = buf; - tuple.TupleDataMax = sizeof(buf); - tuple.TupleOffset = 0; - res = pcmcia_get_first_tuple(dev, &tuple); - if (res != 0) - goto err_kfree_ssb; - res = pcmcia_get_tuple_data(dev, &tuple); - if (res != 0) - goto err_kfree_ssb; - res = pcmcia_parse_tuple(&tuple, &parse); - if (res != 0) - goto err_kfree_ssb; - - dev->conf.ConfigBase = parse.config.base; - dev->conf.Present = parse.config.rmask[0]; dev->conf.Attributes = CONF_ENABLE_IRQ; dev->conf.IntType = INT_MEMORY_AND_IO; @@ -107,20 +87,18 @@ static int __devinit b43_pcmcia_probe(struct pcmcia_device *dev) win.Base = 0; win.Size = SSB_CORE_SIZE; win.AccessSpeed = 250; - res = pcmcia_request_window(&dev, &win, &dev->win); + res = pcmcia_request_window(dev, &win, &dev->win); if (res != 0) goto err_kfree_ssb; mem.CardOffset = 0; mem.Page = 0; - res = pcmcia_map_mem_page(dev->win, &mem); + res = pcmcia_map_mem_page(dev, dev->win, &mem); if (res != 0) goto err_disable; dev->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; - dev->irq.IRQInfo1 = IRQ_LEVEL_ID; dev->irq.Handler = NULL; /* The handler is registered later. */ - dev->irq.Instance = NULL; res = pcmcia_request_irq(dev, &dev->irq); if (res != 0) goto err_disable; diff --git a/drivers/net/wireless/hostap/hostap_cs.c b/drivers/net/wireless/hostap/hostap_cs.c index ad8eab4a639b..c9640a3e02c9 100644 --- a/drivers/net/wireless/hostap/hostap_cs.c +++ b/drivers/net/wireless/hostap/hostap_cs.c @@ -274,9 +274,6 @@ static int sandisk_enable_wireless(struct net_device *dev) conf_reg_t reg; struct hostap_interface *iface = netdev_priv(dev); local_info_t *local = iface->local; - tuple_t tuple; - cisparse_t *parse = NULL; - u_char buf[64]; struct hostap_cs_priv *hw_priv = local->hw_priv; if (hw_priv->link->io.NumPorts1 < 0x42) { @@ -285,28 +282,13 @@ static int sandisk_enable_wireless(struct net_device *dev) goto done; } - parse = kmalloc(sizeof(cisparse_t), GFP_KERNEL); - if (parse == NULL) { - ret = -ENOMEM; - goto done; - } - - tuple.Attributes = TUPLE_RETURN_COMMON; - tuple.TupleData = buf; - tuple.TupleDataMax = sizeof(buf); - tuple.TupleOffset = 0; - if (hw_priv->link->manf_id != 0xd601 || hw_priv->link->card_id != 0x0101) { /* No SanDisk manfid found */ ret = -ENODEV; goto done; } - tuple.DesiredTuple = CISTPL_LONGLINK_MFC; - if (pcmcia_get_first_tuple(hw_priv->link, &tuple) || - pcmcia_get_tuple_data(hw_priv->link, &tuple) || - pcmcia_parse_tuple(&tuple, parse) || - parse->longlink_mfc.nfn < 2) { + if (hw_priv->link->socket->functions < 2) { /* No multi-function links found */ ret = -ENODEV; goto done; @@ -354,7 +336,6 @@ static int sandisk_enable_wireless(struct net_device *dev) udelay(10); done: - kfree(parse); return ret; } @@ -529,10 +510,6 @@ static void prism2_detach(struct pcmcia_device *link) } -#define CS_CHECK(fn, ret) \ -do { last_fn = (fn); if ((last_ret = (ret)) != 0) goto cs_failed; } while (0) - - /* run after a CARD_INSERTION event is received to configure the PCMCIA * socket and make the device available to the system */ @@ -624,7 +601,6 @@ static int prism2_config(struct pcmcia_device *link) struct hostap_interface *iface; local_info_t *local; int ret = 1; - int last_fn, last_ret; struct hostap_cs_priv *hw_priv; PDEBUG(DEBUG_FLOW, "prism2_config()\n"); @@ -636,19 +612,18 @@ static int prism2_config(struct pcmcia_device *link) } /* Look for an appropriate configuration table entry in the CIS */ - last_ret = pcmcia_loop_config(link, prism2_config_check, NULL); - if (last_ret) { + ret = pcmcia_loop_config(link, prism2_config_check, NULL); + if (ret) { if (!ignore_cis_vcc) printk(KERN_ERR "GetNextTuple(): No matching " "CIS configuration. Maybe you need the " "ignore_cis_vcc=1 parameter.\n"); - cs_error(link, RequestIO, last_ret); goto failed; } /* Need to allocate net_device before requesting IRQ handler */ dev = prism2_init_local_data(&prism2_pccard_funcs, 0, - &handle_to_dev(link)); + &link->dev); if (dev == NULL) goto failed; link->priv = dev; @@ -666,13 +641,11 @@ static int prism2_config(struct pcmcia_device *link) * irq structure is initialized. */ if (link->conf.Attributes & CONF_ENABLE_IRQ) { - link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING | - IRQ_HANDLE_PRESENT; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; + link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; link->irq.Handler = prism2_interrupt; - link->irq.Instance = dev; - CS_CHECK(RequestIRQ, - pcmcia_request_irq(link, &link->irq)); + ret = pcmcia_request_irq(link, &link->irq); + if (ret) + goto failed; } /* @@ -680,8 +653,9 @@ static int prism2_config(struct pcmcia_device *link) * the I/O windows and the interrupt mapping, and putting the * card and host interface into "Memory and IO" mode. */ - CS_CHECK(RequestConfiguration, - pcmcia_request_configuration(link, &link->conf)); + ret = pcmcia_request_configuration(link, &link->conf); + if (ret) + goto failed; dev->irq = link->irq.AssignedIRQ; dev->base_addr = link->io.BasePort1; @@ -714,9 +688,6 @@ static int prism2_config(struct pcmcia_device *link) } return ret; - cs_failed: - cs_error(link, last_fn, last_ret); - failed: kfree(hw_priv); prism2_release((u_long)link); diff --git a/drivers/net/wireless/iwlwifi/iwl-tx.c b/drivers/net/wireless/iwlwifi/iwl-tx.c index fb9bcfa6d947..b7e196e3c8d3 100644 --- a/drivers/net/wireless/iwlwifi/iwl-tx.c +++ b/drivers/net/wireless/iwlwifi/iwl-tx.c @@ -1277,8 +1277,16 @@ int iwl_tx_agg_stop(struct iwl_priv *priv , const u8 *ra, u16 tid) return -ENXIO; } + if (priv->stations[sta_id].tid[tid].agg.state == + IWL_EMPTYING_HW_QUEUE_ADDBA) { + IWL_DEBUG_HT(priv, "AGG stop before setup done\n"); + ieee80211_stop_tx_ba_cb_irqsafe(priv->hw, ra, tid); + priv->stations[sta_id].tid[tid].agg.state = IWL_AGG_OFF; + return 0; + } + if (priv->stations[sta_id].tid[tid].agg.state != IWL_AGG_ON) - IWL_WARN(priv, "Stopping AGG while state not IWL_AGG_ON\n"); + IWL_WARN(priv, "Stopping AGG while state not ON or starting\n"); tid_data = &priv->stations[sta_id].tid[tid]; ssn = (tid_data->seq_number & IEEE80211_SCTL_SEQ) >> 4; diff --git a/drivers/net/wireless/libertas/if_cs.c b/drivers/net/wireless/libertas/if_cs.c index 62381768f2d5..b1d84592b959 100644 --- a/drivers/net/wireless/libertas/if_cs.c +++ b/drivers/net/wireless/libertas/if_cs.c @@ -590,7 +590,7 @@ static int if_cs_prog_helper(struct if_cs_card *card) /* TODO: make firmware file configurable */ ret = request_firmware(&fw, "libertas_cs_helper.fw", - &handle_to_dev(card->p_dev)); + &card->p_dev->dev); if (ret) { lbs_pr_err("can't load helper firmware\n"); ret = -ENODEV; @@ -663,7 +663,7 @@ static int if_cs_prog_real(struct if_cs_card *card) /* TODO: make firmware file configurable */ ret = request_firmware(&fw, "libertas_cs.fw", - &handle_to_dev(card->p_dev)); + &card->p_dev->dev); if (ret) { lbs_pr_err("can't load firmware\n"); ret = -ENODEV; @@ -793,18 +793,37 @@ static void if_cs_release(struct pcmcia_device *p_dev) * configure the card at this point -- we wait until we receive a card * insertion event. */ + +static int if_cs_ioprobe(struct pcmcia_device *p_dev, + cistpl_cftable_entry_t *cfg, + cistpl_cftable_entry_t *dflt, + unsigned int vcc, + void *priv_data) +{ + p_dev->io.Attributes1 = IO_DATA_PATH_WIDTH_AUTO; + p_dev->io.BasePort1 = cfg->io.win[0].base; + p_dev->io.NumPorts1 = cfg->io.win[0].len; + + /* Do we need to allocate an interrupt? */ + if (cfg->irq.IRQInfo1) + p_dev->conf.Attributes |= CONF_ENABLE_IRQ; + + /* IO window settings */ + if (cfg->io.nwin != 1) { + lbs_pr_err("wrong CIS (check number of IO windows)\n"); + return -ENODEV; + } + + /* This reserves IO space but doesn't actually enable it */ + return pcmcia_request_io(p_dev, &p_dev->io); +} + static int if_cs_probe(struct pcmcia_device *p_dev) { int ret = -ENOMEM; unsigned int prod_id; struct lbs_private *priv; struct if_cs_card *card; - /* CIS parsing */ - tuple_t tuple; - cisparse_t parse; - cistpl_cftable_entry_t *cfg = &parse.cftable_entry; - cistpl_io_t *io = &cfg->io; - u_char buf[64]; lbs_deb_enter(LBS_DEB_CS); @@ -818,48 +837,15 @@ static int if_cs_probe(struct pcmcia_device *p_dev) p_dev->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; p_dev->irq.Handler = NULL; - p_dev->irq.IRQInfo1 = IRQ_INFO2_VALID | IRQ_LEVEL_ID; p_dev->conf.Attributes = 0; p_dev->conf.IntType = INT_MEMORY_AND_IO; - tuple.Attributes = 0; - tuple.TupleData = buf; - tuple.TupleDataMax = sizeof(buf); - tuple.TupleOffset = 0; - - tuple.DesiredTuple = CISTPL_CFTABLE_ENTRY; - if ((ret = pcmcia_get_first_tuple(p_dev, &tuple)) != 0 || - (ret = pcmcia_get_tuple_data(p_dev, &tuple)) != 0 || - (ret = pcmcia_parse_tuple(&tuple, &parse)) != 0) - { - lbs_pr_err("error in pcmcia_get_first_tuple etc\n"); - goto out1; - } - - p_dev->conf.ConfigIndex = cfg->index; - - /* Do we need to allocate an interrupt? */ - if (cfg->irq.IRQInfo1) { - p_dev->conf.Attributes |= CONF_ENABLE_IRQ; - } - - /* IO window settings */ - if (cfg->io.nwin != 1) { - lbs_pr_err("wrong CIS (check number of IO windows)\n"); - ret = -ENODEV; + if (pcmcia_loop_config(p_dev, if_cs_ioprobe, NULL)) { + lbs_pr_err("error in pcmcia_loop_config\n"); goto out1; } - p_dev->io.Attributes1 = IO_DATA_PATH_WIDTH_AUTO; - p_dev->io.BasePort1 = io->win[0].base; - p_dev->io.NumPorts1 = io->win[0].len; - /* This reserves IO space but doesn't actually enable it */ - ret = pcmcia_request_io(p_dev, &p_dev->io); - if (ret) { - lbs_pr_err("error in pcmcia_request_io\n"); - goto out1; - } /* * Allocate an interrupt line. Note that this does not assign diff --git a/drivers/net/wireless/netwave_cs.c b/drivers/net/wireless/netwave_cs.c index 9498b46c99a4..e61e6b9440ab 100644 --- a/drivers/net/wireless/netwave_cs.c +++ b/drivers/net/wireless/netwave_cs.c @@ -145,23 +145,6 @@ static const unsigned int txConfEUD = 0x10; /* Enable Uni-Data packets */ static const unsigned int txConfKey = 0x02; /* Scramble data packets */ static const unsigned int txConfLoop = 0x01; /* Loopback mode */ -/* - All the PCMCIA modules use PCMCIA_DEBUG to control debugging. If - you do not define PCMCIA_DEBUG at all, all the debug code will be - left out. If you compile with PCMCIA_DEBUG=0, the debug code will - be present but disabled -- but it can then be enabled for specific - modules at load time with a 'pc_debug=#' option to insmod. -*/ - -#ifdef PCMCIA_DEBUG -static int pc_debug = PCMCIA_DEBUG; -module_param(pc_debug, int, 0); -#define DEBUG(n, args...) if (pc_debug>(n)) printk(KERN_DEBUG args) -static char *version = -"netwave_cs.c 0.3.0 Thu Jul 17 14:36:02 1997 (John Markus Bjørndalen)\n"; -#else -#define DEBUG(n, args...) -#endif /*====================================================================*/ @@ -383,7 +366,7 @@ static int netwave_probe(struct pcmcia_device *link) struct net_device *dev; netwave_private *priv; - DEBUG(0, "netwave_attach()\n"); + dev_dbg(&link->dev, "netwave_attach()\n"); /* Initialize the struct pcmcia_device structure */ dev = alloc_etherdev(sizeof(netwave_private)); @@ -401,8 +384,7 @@ static int netwave_probe(struct pcmcia_device *link) link->io.IOAddrLines = 5; /* Interrupt setup */ - link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING | IRQ_HANDLE_PRESENT; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; + link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; link->irq.Handler = &netwave_interrupt; /* General socket configuration */ @@ -421,8 +403,6 @@ static int netwave_probe(struct pcmcia_device *link) dev->watchdog_timeo = TX_TIMEOUT; - link->irq.Instance = dev; - return netwave_pcmcia_config( link); } /* netwave_attach */ @@ -438,7 +418,7 @@ static void netwave_detach(struct pcmcia_device *link) { struct net_device *dev = link->priv; - DEBUG(0, "netwave_detach(0x%p)\n", link); + dev_dbg(&link->dev, "netwave_detach\n"); netwave_release(link); @@ -725,18 +705,15 @@ static const struct iw_handler_def netwave_handler_def = * */ -#define CS_CHECK(fn, ret) \ -do { last_fn = (fn); if ((last_ret = (ret)) != 0) goto cs_failed; } while (0) - static int netwave_pcmcia_config(struct pcmcia_device *link) { struct net_device *dev = link->priv; netwave_private *priv = netdev_priv(dev); - int i, j, last_ret, last_fn; + int i, j, ret; win_req_t req; memreq_t mem; u_char __iomem *ramBase = NULL; - DEBUG(0, "netwave_pcmcia_config(0x%p)\n", link); + dev_dbg(&link->dev, "netwave_pcmcia_config\n"); /* * Try allocating IO ports. This tries a few fixed addresses. @@ -749,22 +726,24 @@ static int netwave_pcmcia_config(struct pcmcia_device *link) { if (i == 0) break; } - if (i != 0) { - cs_error(link, RequestIO, i); + if (i != 0) goto failed; - } /* * Now allocate an interrupt line. Note that this does not * actually assign a handler to the interrupt. */ - CS_CHECK(RequestIRQ, pcmcia_request_irq(link, &link->irq)); + ret = pcmcia_request_irq(link, &link->irq); + if (ret) + goto failed; /* * This actually configures the PCMCIA socket -- setting up * the I/O windows and the interrupt mapping. */ - CS_CHECK(RequestConfiguration, pcmcia_request_configuration(link, &link->conf)); + ret = pcmcia_request_configuration(link, &link->conf); + if (ret) + goto failed; /* * Allocate a 32K memory window. Note that the struct pcmcia_device @@ -772,14 +751,18 @@ static int netwave_pcmcia_config(struct pcmcia_device *link) { * device needs several windows, you'll need to keep track of * the handles in your private data structure, dev->priv. */ - DEBUG(1, "Setting mem speed of %d\n", mem_speed); + dev_dbg(&link->dev, "Setting mem speed of %d\n", mem_speed); req.Attributes = WIN_DATA_WIDTH_8|WIN_MEMORY_TYPE_CM|WIN_ENABLE; req.Base = 0; req.Size = 0x8000; req.AccessSpeed = mem_speed; - CS_CHECK(RequestWindow, pcmcia_request_window(&link, &req, &link->win)); + ret = pcmcia_request_window(link, &req, &link->win); + if (ret) + goto failed; mem.CardOffset = 0x20000; mem.Page = 0; - CS_CHECK(MapMemPage, pcmcia_map_mem_page(link->win, &mem)); + ret = pcmcia_map_mem_page(link, link->win, &mem); + if (ret) + goto failed; /* Store base address of the common window frame */ ramBase = ioremap(req.Base, 0x8000); @@ -787,7 +770,7 @@ static int netwave_pcmcia_config(struct pcmcia_device *link) { dev->irq = link->irq.AssignedIRQ; dev->base_addr = link->io.BasePort1; - SET_NETDEV_DEV(dev, &handle_to_dev(link)); + SET_NETDEV_DEV(dev, &link->dev); if (register_netdev(dev) != 0) { printk(KERN_DEBUG "netwave_cs: register_netdev() failed\n"); @@ -818,8 +801,6 @@ static int netwave_pcmcia_config(struct pcmcia_device *link) { get_uint16(ramBase + NETWAVE_EREG_ARW+2)); return 0; -cs_failed: - cs_error(link, last_fn, last_ret); failed: netwave_release(link); return -ENODEV; @@ -837,7 +818,7 @@ static void netwave_release(struct pcmcia_device *link) struct net_device *dev = link->priv; netwave_private *priv = netdev_priv(dev); - DEBUG(0, "netwave_release(0x%p)\n", link); + dev_dbg(&link->dev, "netwave_release\n"); pcmcia_disable_device(link); if (link->win) @@ -892,7 +873,7 @@ static void netwave_reset(struct net_device *dev) { u_char __iomem *ramBase = priv->ramBase; unsigned int iobase = dev->base_addr; - DEBUG(0, "netwave_reset: Done with hardware reset\n"); + pr_debug("netwave_reset: Done with hardware reset\n"); priv->timeoutCounter = 0; @@ -988,7 +969,7 @@ static int netwave_hw_xmit(unsigned char* data, int len, dev->stats.tx_bytes += len; - DEBUG(3, "Transmitting with SPCQ %x SPU %x LIF %x ISPLQ %x\n", + pr_debug("Transmitting with SPCQ %x SPU %x LIF %x ISPLQ %x\n", readb(ramBase + NETWAVE_EREG_SPCQ), readb(ramBase + NETWAVE_EREG_SPU), readb(ramBase + NETWAVE_EREG_LIF), @@ -1000,7 +981,7 @@ static int netwave_hw_xmit(unsigned char* data, int len, MaxData = get_uint16(ramBase + NETWAVE_EREG_TDP+2); DataOffset = get_uint16(ramBase + NETWAVE_EREG_TDP+4); - DEBUG(3, "TxFreeList %x, MaxData %x, DataOffset %x\n", + pr_debug("TxFreeList %x, MaxData %x, DataOffset %x\n", TxFreeList, MaxData, DataOffset); /* Copy packet to the adapter fragment buffers */ @@ -1088,7 +1069,7 @@ static irqreturn_t netwave_interrupt(int irq, void* dev_id) status = inb(iobase + NETWAVE_REG_ASR); if (!pcmcia_dev_present(link)) { - DEBUG(1, "netwave_interrupt: Interrupt with status 0x%x " + pr_debug("netwave_interrupt: Interrupt with status 0x%x " "from removed or suspended card!\n", status); break; } @@ -1132,7 +1113,7 @@ static irqreturn_t netwave_interrupt(int irq, void* dev_id) int txStatus; txStatus = readb(ramBase + NETWAVE_EREG_TSER); - DEBUG(3, "Transmit done. TSER = %x id %x\n", + pr_debug("Transmit done. TSER = %x id %x\n", txStatus, readb(ramBase + NETWAVE_EREG_TSER + 1)); if (txStatus & 0x20) { @@ -1156,7 +1137,7 @@ static irqreturn_t netwave_interrupt(int irq, void* dev_id) * TxGU and TxNOAP is set. (Those are the only ones * to set TxErr). */ - DEBUG(3, "netwave_interrupt: TxDN with error status %x\n", + pr_debug("netwave_interrupt: TxDN with error status %x\n", txStatus); /* Clear out TxGU, TxNOAP, TxErr and TxTrys */ @@ -1164,7 +1145,7 @@ static irqreturn_t netwave_interrupt(int irq, void* dev_id) writeb(0xdf & txStatus, ramBase+NETWAVE_EREG_TSER+4); ++dev->stats.tx_errors; } - DEBUG(3, "New status is TSER %x ASR %x\n", + pr_debug("New status is TSER %x ASR %x\n", readb(ramBase + NETWAVE_EREG_TSER), inb(iobase + NETWAVE_REG_ASR)); @@ -1172,7 +1153,7 @@ static irqreturn_t netwave_interrupt(int irq, void* dev_id) } /* TxBA, this would trigger on all error packets received */ /* if (status & 0x01) { - DEBUG(4, "Transmit buffers available, %x\n", status); + pr_debug("Transmit buffers available, %x\n", status); } */ } @@ -1190,7 +1171,7 @@ static irqreturn_t netwave_interrupt(int irq, void* dev_id) */ static void netwave_watchdog(struct net_device *dev) { - DEBUG(1, "%s: netwave_watchdog: watchdog timer expired\n", dev->name); + pr_debug("%s: netwave_watchdog: watchdog timer expired\n", dev->name); netwave_reset(dev); dev->trans_start = jiffies; netif_wake_queue(dev); @@ -1211,7 +1192,7 @@ static int netwave_rx(struct net_device *dev) int i; u_char *ptr; - DEBUG(3, "xinw_rx: Receiving ... \n"); + pr_debug("xinw_rx: Receiving ... \n"); /* Receive max 10 packets for now. */ for (i = 0; i < 10; i++) { @@ -1237,7 +1218,7 @@ static int netwave_rx(struct net_device *dev) skb = dev_alloc_skb(rcvLen+5); if (skb == NULL) { - DEBUG(1, "netwave_rx: Could not allocate an sk_buff of " + pr_debug("netwave_rx: Could not allocate an sk_buff of " "length %d\n", rcvLen); ++dev->stats.rx_dropped; /* Tell the adapter to skip the packet */ @@ -1279,7 +1260,7 @@ static int netwave_rx(struct net_device *dev) wait_WOC(iobase); writeb(NETWAVE_CMD_SRP, ramBase + NETWAVE_EREG_CB + 0); writeb(NETWAVE_CMD_EOC, ramBase + NETWAVE_EREG_CB + 1); - DEBUG(3, "Packet reception ok\n"); + pr_debug("Packet reception ok\n"); } return 0; } @@ -1288,7 +1269,7 @@ static int netwave_open(struct net_device *dev) { netwave_private *priv = netdev_priv(dev); struct pcmcia_device *link = priv->p_dev; - DEBUG(1, "netwave_open: starting.\n"); + dev_dbg(&link->dev, "netwave_open: starting.\n"); if (!pcmcia_dev_present(link)) return -ENODEV; @@ -1305,7 +1286,7 @@ static int netwave_close(struct net_device *dev) { netwave_private *priv = netdev_priv(dev); struct pcmcia_device *link = priv->p_dev; - DEBUG(1, "netwave_close: finishing.\n"); + dev_dbg(&link->dev, "netwave_close: finishing.\n"); link->open--; netif_stop_queue(dev); @@ -1358,11 +1339,11 @@ static void set_multicast_list(struct net_device *dev) u_char rcvMode = 0; #ifdef PCMCIA_DEBUG - if (pc_debug > 2) { - static int old; + { + xstatic int old; if (old != dev->mc_count) { old = dev->mc_count; - DEBUG(0, "%s: setting Rx mode to %d addresses.\n", + pr_debug("%s: setting Rx mode to %d addresses.\n", dev->name, dev->mc_count); } } diff --git a/drivers/net/wireless/orinoco/orinoco_cs.c b/drivers/net/wireless/orinoco/orinoco_cs.c index 38c1c9d2abb8..f27bb8367c98 100644 --- a/drivers/net/wireless/orinoco/orinoco_cs.c +++ b/drivers/net/wireless/orinoco/orinoco_cs.c @@ -109,7 +109,7 @@ orinoco_cs_probe(struct pcmcia_device *link) struct orinoco_private *priv; struct orinoco_pccard *card; - priv = alloc_orinocodev(sizeof(*card), &handle_to_dev(link), + priv = alloc_orinocodev(sizeof(*card), &link->dev, orinoco_cs_hard_reset, NULL); if (!priv) return -ENOMEM; @@ -120,10 +120,8 @@ orinoco_cs_probe(struct pcmcia_device *link) link->priv = priv; /* Interrupt setup */ - link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING | IRQ_HANDLE_PRESENT; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; + link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; link->irq.Handler = orinoco_interrupt; - link->irq.Instance = priv; /* General socket configuration defaults can go here. In this * client, we assume very little, and rely on the CIS for @@ -160,12 +158,6 @@ static void orinoco_cs_detach(struct pcmcia_device *link) * device available to the system. */ -#define CS_CHECK(fn, ret) do { \ - last_fn = (fn); \ - if ((last_ret = (ret)) != 0) \ - goto cs_failed; \ -} while (0) - static int orinoco_cs_config_check(struct pcmcia_device *p_dev, cistpl_cftable_entry_t *cfg, cistpl_cftable_entry_t *dflt, @@ -240,7 +232,7 @@ orinoco_cs_config(struct pcmcia_device *link) struct orinoco_private *priv = link->priv; struct orinoco_pccard *card = priv->card; hermes_t *hw = &priv->hw; - int last_fn, last_ret; + int ret; void __iomem *mem; /* @@ -257,13 +249,12 @@ orinoco_cs_config(struct pcmcia_device *link) * and most client drivers will only use the CIS to fill in * implementation-defined details. */ - last_ret = pcmcia_loop_config(link, orinoco_cs_config_check, NULL); - if (last_ret) { + ret = pcmcia_loop_config(link, orinoco_cs_config_check, NULL); + if (ret) { if (!ignore_cis_vcc) printk(KERN_ERR PFX "GetNextTuple(): No matching " "CIS configuration. Maybe you need the " "ignore_cis_vcc=1 parameter.\n"); - cs_error(link, RequestIO, last_ret); goto failed; } @@ -272,14 +263,16 @@ orinoco_cs_config(struct pcmcia_device *link) * a handler to the interrupt, unless the 'Handler' member of * the irq structure is initialized. */ - CS_CHECK(RequestIRQ, pcmcia_request_irq(link, &link->irq)); + ret = pcmcia_request_irq(link, &link->irq); + if (ret) + goto failed; /* We initialize the hermes structure before completing PCMCIA * configuration just in case the interrupt handler gets * called. */ mem = ioport_map(link->io.BasePort1, link->io.NumPorts1); if (!mem) - goto cs_failed; + goto failed; hermes_struct_init(hw, mem, HERMES_16BIT_REGSPACING); @@ -288,8 +281,9 @@ orinoco_cs_config(struct pcmcia_device *link) * the I/O windows and the interrupt mapping, and putting the * card and host interface into "Memory and IO" mode. */ - CS_CHECK(RequestConfiguration, - pcmcia_request_configuration(link, &link->conf)); + ret = pcmcia_request_configuration(link, &link->conf); + if (ret) + goto failed; /* Ok, we have the configuration, prepare to register the netdev */ card->node.major = card->node.minor = 0; @@ -315,9 +309,6 @@ orinoco_cs_config(struct pcmcia_device *link) * net_device has been registered */ return 0; - cs_failed: - cs_error(link, last_fn, last_ret); - failed: orinoco_cs_release(link); return -ENODEV; diff --git a/drivers/net/wireless/orinoco/spectrum_cs.c b/drivers/net/wireless/orinoco/spectrum_cs.c index c361310b885d..59bda240fdc2 100644 --- a/drivers/net/wireless/orinoco/spectrum_cs.c +++ b/drivers/net/wireless/orinoco/spectrum_cs.c @@ -73,9 +73,6 @@ static void spectrum_cs_release(struct pcmcia_device *link); #define HCR_MEM16 0x10 /* memory width bit, should be preserved */ -#define CS_CHECK(fn, ret) \ - do { last_fn = (fn); if ((last_ret = (ret)) != 0) goto cs_failed; } while (0) - /* * Reset the card using configuration registers COR and CCSR. * If IDLE is 1, stop the firmware, so that it can be safely rewritten. @@ -83,7 +80,7 @@ static void spectrum_cs_release(struct pcmcia_device *link); static int spectrum_reset(struct pcmcia_device *link, int idle) { - int last_ret, last_fn; + int ret; conf_reg_t reg; u_int save_cor; @@ -95,23 +92,26 @@ spectrum_reset(struct pcmcia_device *link, int idle) reg.Function = 0; reg.Action = CS_READ; reg.Offset = CISREG_COR; - CS_CHECK(AccessConfigurationRegister, - pcmcia_access_configuration_register(link, ®)); + ret = pcmcia_access_configuration_register(link, ®); + if (ret) + goto failed; save_cor = reg.Value; /* Soft-Reset card */ reg.Action = CS_WRITE; reg.Offset = CISREG_COR; reg.Value = (save_cor | COR_SOFT_RESET); - CS_CHECK(AccessConfigurationRegister, - pcmcia_access_configuration_register(link, ®)); + ret = pcmcia_access_configuration_register(link, ®); + if (ret) + goto failed; udelay(1000); /* Read CCSR */ reg.Action = CS_READ; reg.Offset = CISREG_CCSR; - CS_CHECK(AccessConfigurationRegister, - pcmcia_access_configuration_register(link, ®)); + ret = pcmcia_access_configuration_register(link, ®); + if (ret) + goto failed; /* * Start or stop the firmware. Memory width bit should be @@ -120,21 +120,22 @@ spectrum_reset(struct pcmcia_device *link, int idle) reg.Action = CS_WRITE; reg.Offset = CISREG_CCSR; reg.Value = (idle ? HCR_IDLE : HCR_RUN) | (reg.Value & HCR_MEM16); - CS_CHECK(AccessConfigurationRegister, - pcmcia_access_configuration_register(link, ®)); + ret = pcmcia_access_configuration_register(link, ®); + if (ret) + goto failed; udelay(1000); /* Restore original COR configuration index */ reg.Action = CS_WRITE; reg.Offset = CISREG_COR; reg.Value = (save_cor & ~COR_SOFT_RESET); - CS_CHECK(AccessConfigurationRegister, - pcmcia_access_configuration_register(link, ®)); + ret = pcmcia_access_configuration_register(link, ®); + if (ret) + goto failed; udelay(1000); return 0; -cs_failed: - cs_error(link, last_fn, last_ret); +failed: return -ENODEV; } @@ -181,7 +182,7 @@ spectrum_cs_probe(struct pcmcia_device *link) struct orinoco_private *priv; struct orinoco_pccard *card; - priv = alloc_orinocodev(sizeof(*card), &handle_to_dev(link), + priv = alloc_orinocodev(sizeof(*card), &link->dev, spectrum_cs_hard_reset, spectrum_cs_stop_firmware); if (!priv) @@ -193,10 +194,8 @@ spectrum_cs_probe(struct pcmcia_device *link) link->priv = priv; /* Interrupt setup */ - link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING | IRQ_HANDLE_PRESENT; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; + link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; link->irq.Handler = orinoco_interrupt; - link->irq.Instance = priv; /* General socket configuration defaults can go here. In this * client, we assume very little, and rely on the CIS for @@ -307,7 +306,7 @@ spectrum_cs_config(struct pcmcia_device *link) struct orinoco_private *priv = link->priv; struct orinoco_pccard *card = priv->card; hermes_t *hw = &priv->hw; - int last_fn, last_ret; + int ret; void __iomem *mem; /* @@ -324,13 +323,12 @@ spectrum_cs_config(struct pcmcia_device *link) * and most client drivers will only use the CIS to fill in * implementation-defined details. */ - last_ret = pcmcia_loop_config(link, spectrum_cs_config_check, NULL); - if (last_ret) { + ret = pcmcia_loop_config(link, spectrum_cs_config_check, NULL); + if (ret) { if (!ignore_cis_vcc) printk(KERN_ERR PFX "GetNextTuple(): No matching " "CIS configuration. Maybe you need the " "ignore_cis_vcc=1 parameter.\n"); - cs_error(link, RequestIO, last_ret); goto failed; } @@ -339,14 +337,16 @@ spectrum_cs_config(struct pcmcia_device *link) * a handler to the interrupt, unless the 'Handler' member of * the irq structure is initialized. */ - CS_CHECK(RequestIRQ, pcmcia_request_irq(link, &link->irq)); + ret = pcmcia_request_irq(link, &link->irq); + if (ret) + goto failed; /* We initialize the hermes structure before completing PCMCIA * configuration just in case the interrupt handler gets * called. */ mem = ioport_map(link->io.BasePort1, link->io.NumPorts1); if (!mem) - goto cs_failed; + goto failed; hermes_struct_init(hw, mem, HERMES_16BIT_REGSPACING); @@ -355,8 +355,9 @@ spectrum_cs_config(struct pcmcia_device *link) * the I/O windows and the interrupt mapping, and putting the * card and host interface into "Memory and IO" mode. */ - CS_CHECK(RequestConfiguration, - pcmcia_request_configuration(link, &link->conf)); + ret = pcmcia_request_configuration(link, &link->conf); + if (ret) + goto failed; /* Ok, we have the configuration, prepare to register the netdev */ card->node.major = card->node.minor = 0; @@ -386,9 +387,6 @@ spectrum_cs_config(struct pcmcia_device *link) * net_device has been registered */ return 0; - cs_failed: - cs_error(link, last_fn, last_ret); - failed: spectrum_cs_release(link); return -ENODEV; diff --git a/drivers/net/wireless/ray_cs.c b/drivers/net/wireless/ray_cs.c index 1c88c2ea59aa..5b8e3e4cdd9f 100644 --- a/drivers/net/wireless/ray_cs.c +++ b/drivers/net/wireless/ray_cs.c @@ -71,25 +71,7 @@ typedef u_char mac_addr[ETH_ALEN]; /* Hardware address */ #include "rayctl.h" #include "ray_cs.h" -/* All the PCMCIA modules use PCMCIA_DEBUG to control debugging. If - you do not define PCMCIA_DEBUG at all, all the debug code will be - left out. If you compile with PCMCIA_DEBUG=0, the debug code will - be present but disabled -- but it can then be enabled for specific - modules at load time with a 'pc_debug=#' option to insmod. -*/ -#ifdef RAYLINK_DEBUG -#define PCMCIA_DEBUG RAYLINK_DEBUG -#endif -#ifdef PCMCIA_DEBUG -static int ray_debug; -static int pc_debug = PCMCIA_DEBUG; -module_param(pc_debug, int, 0); -/* #define DEBUG(n, args...) if (pc_debug>(n)) printk(KERN_DEBUG args); */ -#define DEBUG(n, args...) if (pc_debug > (n)) printk(args); -#else -#define DEBUG(n, args...) -#endif /** Prototypes based on PCMCIA skeleton driver *******************************/ static int ray_config(struct pcmcia_device *link); static void ray_release(struct pcmcia_device *link); @@ -325,7 +307,7 @@ static int ray_probe(struct pcmcia_device *p_dev) ray_dev_t *local; struct net_device *dev; - DEBUG(1, "ray_attach()\n"); + dev_dbg(&p_dev->dev, "ray_attach()\n"); /* Allocate space for private device-specific data */ dev = alloc_etherdev(sizeof(ray_dev_t)); @@ -341,8 +323,7 @@ static int ray_probe(struct pcmcia_device *p_dev) p_dev->io.IOAddrLines = 5; /* Interrupt setup. For PCMCIA, driver takes what's given */ - p_dev->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING | IRQ_HANDLE_PRESENT; - p_dev->irq.IRQInfo1 = IRQ_LEVEL_ID; + p_dev->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; p_dev->irq.Handler = &ray_interrupt; /* General socket configuration */ @@ -351,13 +332,12 @@ static int ray_probe(struct pcmcia_device *p_dev) p_dev->conf.ConfigIndex = 1; p_dev->priv = dev; - p_dev->irq.Instance = dev; local->finder = p_dev; local->card_status = CARD_INSERTED; local->authentication_state = UNAUTHENTICATED; local->num_multi = 0; - DEBUG(2, "ray_attach p_dev = %p, dev = %p, local = %p, intr = %p\n", + dev_dbg(&p_dev->dev, "ray_attach p_dev = %p, dev = %p, local = %p, intr = %p\n", p_dev, dev, local, &ray_interrupt); /* Raylink entries in the device structure */ @@ -370,7 +350,7 @@ static int ray_probe(struct pcmcia_device *p_dev) #endif /* WIRELESS_SPY */ - DEBUG(2, "ray_cs ray_attach calling ether_setup.)\n"); + dev_dbg(&p_dev->dev, "ray_cs ray_attach calling ether_setup.)\n"); netif_stop_queue(dev); init_timer(&local->timer); @@ -393,7 +373,7 @@ static void ray_detach(struct pcmcia_device *link) struct net_device *dev; ray_dev_t *local; - DEBUG(1, "ray_detach(0x%p)\n", link); + dev_dbg(&link->dev, "ray_detach\n"); this_device = NULL; dev = link->priv; @@ -408,7 +388,7 @@ static void ray_detach(struct pcmcia_device *link) unregister_netdev(dev); free_netdev(dev); } - DEBUG(2, "ray_cs ray_detach ending\n"); + dev_dbg(&link->dev, "ray_cs ray_detach ending\n"); } /* ray_detach */ /*============================================================================= @@ -416,19 +396,17 @@ static void ray_detach(struct pcmcia_device *link) is received, to configure the PCMCIA socket, and to make the ethernet device available to the system. =============================================================================*/ -#define CS_CHECK(fn, ret) \ -do { last_fn = (fn); if ((last_ret = (ret)) != 0) goto cs_failed; } while (0) #define MAX_TUPLE_SIZE 128 static int ray_config(struct pcmcia_device *link) { - int last_fn = 0, last_ret = 0; + int ret = 0; int i; win_req_t req; memreq_t mem; struct net_device *dev = (struct net_device *)link->priv; ray_dev_t *local = netdev_priv(dev); - DEBUG(1, "ray_config(0x%p)\n", link); + dev_dbg(&link->dev, "ray_config\n"); /* Determine card type and firmware version */ printk(KERN_INFO "ray_cs Detected: %s%s%s%s\n", @@ -440,14 +418,17 @@ static int ray_config(struct pcmcia_device *link) /* Now allocate an interrupt line. Note that this does not actually assign a handler to the interrupt. */ - CS_CHECK(RequestIRQ, pcmcia_request_irq(link, &link->irq)); + ret = pcmcia_request_irq(link, &link->irq); + if (ret) + goto failed; dev->irq = link->irq.AssignedIRQ; /* This actually configures the PCMCIA socket -- setting up the I/O windows and the interrupt mapping. */ - CS_CHECK(RequestConfiguration, - pcmcia_request_configuration(link, &link->conf)); + ret = pcmcia_request_configuration(link, &link->conf); + if (ret) + goto failed; /*** Set up 32k window for shared memory (transmit and control) ************/ req.Attributes = @@ -455,10 +436,14 @@ static int ray_config(struct pcmcia_device *link) req.Base = 0; req.Size = 0x8000; req.AccessSpeed = ray_mem_speed; - CS_CHECK(RequestWindow, pcmcia_request_window(&link, &req, &link->win)); + ret = pcmcia_request_window(link, &req, &link->win); + if (ret) + goto failed; mem.CardOffset = 0x0000; mem.Page = 0; - CS_CHECK(MapMemPage, pcmcia_map_mem_page(link->win, &mem)); + ret = pcmcia_map_mem_page(link, link->win, &mem); + if (ret) + goto failed; local->sram = ioremap(req.Base, req.Size); /*** Set up 16k window for shared memory (receive buffer) ***************/ @@ -467,11 +452,14 @@ static int ray_config(struct pcmcia_device *link) req.Base = 0; req.Size = 0x4000; req.AccessSpeed = ray_mem_speed; - CS_CHECK(RequestWindow, - pcmcia_request_window(&link, &req, &local->rmem_handle)); + ret = pcmcia_request_window(link, &req, &local->rmem_handle); + if (ret) + goto failed; mem.CardOffset = 0x8000; mem.Page = 0; - CS_CHECK(MapMemPage, pcmcia_map_mem_page(local->rmem_handle, &mem)); + ret = pcmcia_map_mem_page(link, local->rmem_handle, &mem); + if (ret) + goto failed; local->rmem = ioremap(req.Base, req.Size); /*** Set up window for attribute memory ***********************************/ @@ -480,22 +468,25 @@ static int ray_config(struct pcmcia_device *link) req.Base = 0; req.Size = 0x1000; req.AccessSpeed = ray_mem_speed; - CS_CHECK(RequestWindow, - pcmcia_request_window(&link, &req, &local->amem_handle)); + ret = pcmcia_request_window(link, &req, &local->amem_handle); + if (ret) + goto failed; mem.CardOffset = 0x0000; mem.Page = 0; - CS_CHECK(MapMemPage, pcmcia_map_mem_page(local->amem_handle, &mem)); + ret = pcmcia_map_mem_page(link, local->amem_handle, &mem); + if (ret) + goto failed; local->amem = ioremap(req.Base, req.Size); - DEBUG(3, "ray_config sram=%p\n", local->sram); - DEBUG(3, "ray_config rmem=%p\n", local->rmem); - DEBUG(3, "ray_config amem=%p\n", local->amem); + dev_dbg(&link->dev, "ray_config sram=%p\n", local->sram); + dev_dbg(&link->dev, "ray_config rmem=%p\n", local->rmem); + dev_dbg(&link->dev, "ray_config amem=%p\n", local->amem); if (ray_init(dev) < 0) { ray_release(link); return -ENODEV; } - SET_NETDEV_DEV(dev, &handle_to_dev(link)); + SET_NETDEV_DEV(dev, &link->dev); i = register_netdev(dev); if (i != 0) { printk("ray_config register_netdev() failed\n"); @@ -511,9 +502,7 @@ static int ray_config(struct pcmcia_device *link) return 0; -cs_failed: - cs_error(link, last_fn, last_ret); - +failed: ray_release(link); return -ENODEV; } /* ray_config */ @@ -543,9 +532,9 @@ static int ray_init(struct net_device *dev) struct ccs __iomem *pccs; ray_dev_t *local = netdev_priv(dev); struct pcmcia_device *link = local->finder; - DEBUG(1, "ray_init(0x%p)\n", dev); + dev_dbg(&link->dev, "ray_init(0x%p)\n", dev); if (!(pcmcia_dev_present(link))) { - DEBUG(0, "ray_init - device not present\n"); + dev_dbg(&link->dev, "ray_init - device not present\n"); return -1; } @@ -567,13 +556,13 @@ static int ray_init(struct net_device *dev) local->fw_ver = local->startup_res.firmware_version[0]; local->fw_bld = local->startup_res.firmware_version[1]; local->fw_var = local->startup_res.firmware_version[2]; - DEBUG(1, "ray_init firmware version %d.%d \n", local->fw_ver, + dev_dbg(&link->dev, "ray_init firmware version %d.%d \n", local->fw_ver, local->fw_bld); local->tib_length = 0x20; if ((local->fw_ver == 5) && (local->fw_bld >= 30)) local->tib_length = local->startup_res.tib_length; - DEBUG(2, "ray_init tib_length = 0x%02x\n", local->tib_length); + dev_dbg(&link->dev, "ray_init tib_length = 0x%02x\n", local->tib_length); /* Initialize CCS's to buffer free state */ pccs = ccs_base(local); for (i = 0; i < NUMBER_OF_CCS; i++) { @@ -592,7 +581,7 @@ static int ray_init(struct net_device *dev) clear_interrupt(local); /* Clear any interrupt from the card */ local->card_status = CARD_AWAITING_PARAM; - DEBUG(2, "ray_init ending\n"); + dev_dbg(&link->dev, "ray_init ending\n"); return 0; } /* ray_init */ @@ -605,9 +594,9 @@ static int dl_startup_params(struct net_device *dev) struct ccs __iomem *pccs; struct pcmcia_device *link = local->finder; - DEBUG(1, "dl_startup_params entered\n"); + dev_dbg(&link->dev, "dl_startup_params entered\n"); if (!(pcmcia_dev_present(link))) { - DEBUG(2, "ray_cs dl_startup_params - device not present\n"); + dev_dbg(&link->dev, "ray_cs dl_startup_params - device not present\n"); return -1; } @@ -625,7 +614,7 @@ static int dl_startup_params(struct net_device *dev) local->dl_param_ccs = ccsindex; pccs = ccs_base(local) + ccsindex; writeb(CCS_DOWNLOAD_STARTUP_PARAMS, &pccs->cmd); - DEBUG(2, "dl_startup_params start ccsindex = %d\n", + dev_dbg(&link->dev, "dl_startup_params start ccsindex = %d\n", local->dl_param_ccs); /* Interrupt the firmware to process the command */ if (interrupt_ecf(local, ccsindex)) { @@ -641,7 +630,7 @@ static int dl_startup_params(struct net_device *dev) local->timer.data = (long)local; local->timer.function = &verify_dl_startup; add_timer(&local->timer); - DEBUG(2, + dev_dbg(&link->dev, "ray_cs dl_startup_params started timer for verify_dl_startup\n"); return 0; } /* dl_startup_params */ @@ -717,11 +706,11 @@ static void verify_dl_startup(u_long data) struct pcmcia_device *link = local->finder; if (!(pcmcia_dev_present(link))) { - DEBUG(2, "ray_cs verify_dl_startup - device not present\n"); + dev_dbg(&link->dev, "ray_cs verify_dl_startup - device not present\n"); return; } -#ifdef PCMCIA_DEBUG - if (pc_debug > 2) { +#if 0 + { int i; printk(KERN_DEBUG "verify_dl_startup parameters sent via ccs %d:\n", @@ -760,7 +749,7 @@ static void start_net(u_long data) int ccsindex; struct pcmcia_device *link = local->finder; if (!(pcmcia_dev_present(link))) { - DEBUG(2, "ray_cs start_net - device not present\n"); + dev_dbg(&link->dev, "ray_cs start_net - device not present\n"); return; } /* Fill in the CCS fields for the ECF */ @@ -771,7 +760,7 @@ static void start_net(u_long data) writeb(0, &pccs->var.start_network.update_param); /* Interrupt the firmware to process the command */ if (interrupt_ecf(local, ccsindex)) { - DEBUG(1, "ray start net failed - card not ready for intr\n"); + dev_dbg(&link->dev, "ray start net failed - card not ready for intr\n"); writeb(CCS_BUFFER_FREE, &(pccs++)->buffer_status); return; } @@ -790,7 +779,7 @@ static void join_net(u_long data) struct pcmcia_device *link = local->finder; if (!(pcmcia_dev_present(link))) { - DEBUG(2, "ray_cs join_net - device not present\n"); + dev_dbg(&link->dev, "ray_cs join_net - device not present\n"); return; } /* Fill in the CCS fields for the ECF */ @@ -802,7 +791,7 @@ static void join_net(u_long data) writeb(0, &pccs->var.join_network.net_initiated); /* Interrupt the firmware to process the command */ if (interrupt_ecf(local, ccsindex)) { - DEBUG(1, "ray join net failed - card not ready for intr\n"); + dev_dbg(&link->dev, "ray join net failed - card not ready for intr\n"); writeb(CCS_BUFFER_FREE, &(pccs++)->buffer_status); return; } @@ -821,7 +810,7 @@ static void ray_release(struct pcmcia_device *link) ray_dev_t *local = netdev_priv(dev); int i; - DEBUG(1, "ray_release(0x%p)\n", link); + dev_dbg(&link->dev, "ray_release\n"); del_timer(&local->timer); @@ -829,15 +818,15 @@ static void ray_release(struct pcmcia_device *link) iounmap(local->rmem); iounmap(local->amem); /* Do bother checking to see if these succeed or not */ - i = pcmcia_release_window(local->amem_handle); + i = pcmcia_release_window(link, local->amem_handle); if (i != 0) - DEBUG(0, "ReleaseWindow(local->amem) ret = %x\n", i); - i = pcmcia_release_window(local->rmem_handle); + dev_dbg(&link->dev, "ReleaseWindow(local->amem) ret = %x\n", i); + i = pcmcia_release_window(link, local->rmem_handle); if (i != 0) - DEBUG(0, "ReleaseWindow(local->rmem) ret = %x\n", i); + dev_dbg(&link->dev, "ReleaseWindow(local->rmem) ret = %x\n", i); pcmcia_disable_device(link); - DEBUG(2, "ray_release ending\n"); + dev_dbg(&link->dev, "ray_release ending\n"); } static int ray_suspend(struct pcmcia_device *link) @@ -871,9 +860,9 @@ static int ray_dev_init(struct net_device *dev) ray_dev_t *local = netdev_priv(dev); struct pcmcia_device *link = local->finder; - DEBUG(1, "ray_dev_init(dev=%p)\n", dev); + dev_dbg(&link->dev, "ray_dev_init(dev=%p)\n", dev); if (!(pcmcia_dev_present(link))) { - DEBUG(2, "ray_dev_init - device not present\n"); + dev_dbg(&link->dev, "ray_dev_init - device not present\n"); return -1; } #ifdef RAY_IMMEDIATE_INIT @@ -887,7 +876,7 @@ static int ray_dev_init(struct net_device *dev) /* Postpone the card init so that we can still configure the card, * for example using the Wireless Extensions. The init will happen * in ray_open() - Jean II */ - DEBUG(1, + dev_dbg(&link->dev, "ray_dev_init: postponing card init to ray_open() ; Status = %d\n", local->card_status); #endif /* RAY_IMMEDIATE_INIT */ @@ -896,7 +885,7 @@ static int ray_dev_init(struct net_device *dev) memcpy(dev->dev_addr, &local->sparm.b4.a_mac_addr, ADDRLEN); memset(dev->broadcast, 0xff, ETH_ALEN); - DEBUG(2, "ray_dev_init ending\n"); + dev_dbg(&link->dev, "ray_dev_init ending\n"); return 0; } @@ -906,9 +895,9 @@ static int ray_dev_config(struct net_device *dev, struct ifmap *map) ray_dev_t *local = netdev_priv(dev); struct pcmcia_device *link = local->finder; /* Dummy routine to satisfy device structure */ - DEBUG(1, "ray_dev_config(dev=%p,ifmap=%p)\n", dev, map); + dev_dbg(&link->dev, "ray_dev_config(dev=%p,ifmap=%p)\n", dev, map); if (!(pcmcia_dev_present(link))) { - DEBUG(2, "ray_dev_config - device not present\n"); + dev_dbg(&link->dev, "ray_dev_config - device not present\n"); return -1; } @@ -924,14 +913,14 @@ static netdev_tx_t ray_dev_start_xmit(struct sk_buff *skb, short length = skb->len; if (!pcmcia_dev_present(link)) { - DEBUG(2, "ray_dev_start_xmit - device not present\n"); + dev_dbg(&link->dev, "ray_dev_start_xmit - device not present\n"); dev_kfree_skb(skb); return NETDEV_TX_OK; } - DEBUG(3, "ray_dev_start_xmit(skb=%p, dev=%p)\n", skb, dev); + dev_dbg(&link->dev, "ray_dev_start_xmit(skb=%p, dev=%p)\n", skb, dev); if (local->authentication_state == NEED_TO_AUTH) { - DEBUG(0, "ray_cs Sending authentication request.\n"); + dev_dbg(&link->dev, "ray_cs Sending authentication request.\n"); if (!build_auth_frame(local, local->auth_id, OPEN_AUTH_REQUEST)) { local->authentication_state = AUTHENTICATED; netif_stop_queue(dev); @@ -971,7 +960,7 @@ static int ray_hw_xmit(unsigned char *data, int len, struct net_device *dev, struct tx_msg __iomem *ptx; /* Address of xmit buffer in PC space */ short int addr; /* Address of xmit buffer in card space */ - DEBUG(3, "ray_hw_xmit(data=%p, len=%d, dev=%p)\n", data, len, dev); + pr_debug("ray_hw_xmit(data=%p, len=%d, dev=%p)\n", data, len, dev); if (len + TX_HEADER_LENGTH > TX_BUF_SIZE) { printk(KERN_INFO "ray_hw_xmit packet too large: %d bytes\n", len); @@ -979,9 +968,9 @@ static int ray_hw_xmit(unsigned char *data, int len, struct net_device *dev, } switch (ccsindex = get_free_tx_ccs(local)) { case ECCSBUSY: - DEBUG(2, "ray_hw_xmit tx_ccs table busy\n"); + pr_debug("ray_hw_xmit tx_ccs table busy\n"); case ECCSFULL: - DEBUG(2, "ray_hw_xmit No free tx ccs\n"); + pr_debug("ray_hw_xmit No free tx ccs\n"); case ECARDGONE: netif_stop_queue(dev); return XMIT_NO_CCS; @@ -1018,12 +1007,12 @@ static int ray_hw_xmit(unsigned char *data, int len, struct net_device *dev, writeb(PSM_CAM, &pccs->var.tx_request.pow_sav_mode); writeb(local->net_default_tx_rate, &pccs->var.tx_request.tx_rate); writeb(0, &pccs->var.tx_request.antenna); - DEBUG(3, "ray_hw_xmit default_tx_rate = 0x%x\n", + pr_debug("ray_hw_xmit default_tx_rate = 0x%x\n", local->net_default_tx_rate); /* Interrupt the firmware to process the command */ if (interrupt_ecf(local, ccsindex)) { - DEBUG(2, "ray_hw_xmit failed - ECF not ready for intr\n"); + pr_debug("ray_hw_xmit failed - ECF not ready for intr\n"); /* TBD very inefficient to copy packet to buffer, and then not send it, but the alternative is to queue the messages and that won't be done for a while. Maybe set tbusy until a CCS is free? @@ -1040,7 +1029,7 @@ static int translate_frame(ray_dev_t *local, struct tx_msg __iomem *ptx, { __be16 proto = ((struct ethhdr *)data)->h_proto; if (ntohs(proto) >= 1536) { /* DIX II ethernet frame */ - DEBUG(3, "ray_cs translate_frame DIX II\n"); + pr_debug("ray_cs translate_frame DIX II\n"); /* Copy LLC header to card buffer */ memcpy_toio(&ptx->var, eth2_llc, sizeof(eth2_llc)); memcpy_toio(((void __iomem *)&ptx->var) + sizeof(eth2_llc), @@ -1056,9 +1045,9 @@ static int translate_frame(ray_dev_t *local, struct tx_msg __iomem *ptx, len - ETH_HLEN); return (int)sizeof(struct snaphdr_t) - ETH_HLEN; } else { /* already 802 type, and proto is length */ - DEBUG(3, "ray_cs translate_frame 802\n"); + pr_debug("ray_cs translate_frame 802\n"); if (proto == htons(0xffff)) { /* evil netware IPX 802.3 without LLC */ - DEBUG(3, "ray_cs translate_frame evil IPX\n"); + pr_debug("ray_cs translate_frame evil IPX\n"); memcpy_toio(&ptx->var, data + ETH_HLEN, len - ETH_HLEN); return 0 - ETH_HLEN; } @@ -1603,7 +1592,7 @@ static int ray_open(struct net_device *dev) struct pcmcia_device *link; link = local->finder; - DEBUG(1, "ray_open('%s')\n", dev->name); + dev_dbg(&link->dev, "ray_open('%s')\n", dev->name); if (link->open == 0) local->num_multi = 0; @@ -1613,7 +1602,7 @@ static int ray_open(struct net_device *dev) if (local->card_status == CARD_AWAITING_PARAM) { int i; - DEBUG(1, "ray_open: doing init now !\n"); + dev_dbg(&link->dev, "ray_open: doing init now !\n"); /* Download startup parameters */ if ((i = dl_startup_params(dev)) < 0) { @@ -1629,7 +1618,7 @@ static int ray_open(struct net_device *dev) else netif_start_queue(dev); - DEBUG(2, "ray_open ending\n"); + dev_dbg(&link->dev, "ray_open ending\n"); return 0; } /* end ray_open */ @@ -1640,7 +1629,7 @@ static int ray_dev_close(struct net_device *dev) struct pcmcia_device *link; link = local->finder; - DEBUG(1, "ray_dev_close('%s')\n", dev->name); + dev_dbg(&link->dev, "ray_dev_close('%s')\n", dev->name); link->open--; netif_stop_queue(dev); @@ -1656,7 +1645,7 @@ static int ray_dev_close(struct net_device *dev) /*===========================================================================*/ static void ray_reset(struct net_device *dev) { - DEBUG(1, "ray_reset entered\n"); + pr_debug("ray_reset entered\n"); return; } @@ -1669,17 +1658,17 @@ static int interrupt_ecf(ray_dev_t *local, int ccs) struct pcmcia_device *link = local->finder; if (!(pcmcia_dev_present(link))) { - DEBUG(2, "ray_cs interrupt_ecf - device not present\n"); + dev_dbg(&link->dev, "ray_cs interrupt_ecf - device not present\n"); return -1; } - DEBUG(2, "interrupt_ecf(local=%p, ccs = 0x%x\n", local, ccs); + dev_dbg(&link->dev, "interrupt_ecf(local=%p, ccs = 0x%x\n", local, ccs); while (i && (readb(local->amem + CIS_OFFSET + ECF_INTR_OFFSET) & ECF_INTR_SET)) i--; if (i == 0) { - DEBUG(2, "ray_cs interrupt_ecf card not ready for interrupt\n"); + dev_dbg(&link->dev, "ray_cs interrupt_ecf card not ready for interrupt\n"); return -1; } /* Fill the mailbox, then kick the card */ @@ -1698,12 +1687,12 @@ static int get_free_tx_ccs(ray_dev_t *local) struct pcmcia_device *link = local->finder; if (!(pcmcia_dev_present(link))) { - DEBUG(2, "ray_cs get_free_tx_ccs - device not present\n"); + dev_dbg(&link->dev, "ray_cs get_free_tx_ccs - device not present\n"); return ECARDGONE; } if (test_and_set_bit(0, &local->tx_ccs_lock)) { - DEBUG(1, "ray_cs tx_ccs_lock busy\n"); + dev_dbg(&link->dev, "ray_cs tx_ccs_lock busy\n"); return ECCSBUSY; } @@ -1716,7 +1705,7 @@ static int get_free_tx_ccs(ray_dev_t *local) } } local->tx_ccs_lock = 0; - DEBUG(2, "ray_cs ERROR no free tx CCS for raylink card\n"); + dev_dbg(&link->dev, "ray_cs ERROR no free tx CCS for raylink card\n"); return ECCSFULL; } /* get_free_tx_ccs */ @@ -1730,11 +1719,11 @@ static int get_free_ccs(ray_dev_t *local) struct pcmcia_device *link = local->finder; if (!(pcmcia_dev_present(link))) { - DEBUG(2, "ray_cs get_free_ccs - device not present\n"); + dev_dbg(&link->dev, "ray_cs get_free_ccs - device not present\n"); return ECARDGONE; } if (test_and_set_bit(0, &local->ccs_lock)) { - DEBUG(1, "ray_cs ccs_lock busy\n"); + dev_dbg(&link->dev, "ray_cs ccs_lock busy\n"); return ECCSBUSY; } @@ -1747,7 +1736,7 @@ static int get_free_ccs(ray_dev_t *local) } } local->ccs_lock = 0; - DEBUG(1, "ray_cs ERROR no free CCS for raylink card\n"); + dev_dbg(&link->dev, "ray_cs ERROR no free CCS for raylink card\n"); return ECCSFULL; } /* get_free_ccs */ @@ -1823,7 +1812,7 @@ static struct net_device_stats *ray_get_stats(struct net_device *dev) struct pcmcia_device *link = local->finder; struct status __iomem *p = local->sram + STATUS_BASE; if (!(pcmcia_dev_present(link))) { - DEBUG(2, "ray_cs net_device_stats - device not present\n"); + dev_dbg(&link->dev, "ray_cs net_device_stats - device not present\n"); return &local->stats; } if (readb(&p->mrx_overflow_for_host)) { @@ -1856,12 +1845,12 @@ static void ray_update_parm(struct net_device *dev, UCHAR objid, UCHAR *value, struct ccs __iomem *pccs; if (!(pcmcia_dev_present(link))) { - DEBUG(2, "ray_update_parm - device not present\n"); + dev_dbg(&link->dev, "ray_update_parm - device not present\n"); return; } if ((ccsindex = get_free_ccs(local)) < 0) { - DEBUG(0, "ray_update_parm - No free ccs\n"); + dev_dbg(&link->dev, "ray_update_parm - No free ccs\n"); return; } pccs = ccs_base(local) + ccsindex; @@ -1874,7 +1863,7 @@ static void ray_update_parm(struct net_device *dev, UCHAR objid, UCHAR *value, } /* Interrupt the firmware to process the command */ if (interrupt_ecf(local, ccsindex)) { - DEBUG(0, "ray_cs associate failed - ECF not ready for intr\n"); + dev_dbg(&link->dev, "ray_cs associate failed - ECF not ready for intr\n"); writeb(CCS_BUFFER_FREE, &(pccs++)->buffer_status); } } @@ -1891,12 +1880,12 @@ static void ray_update_multi_list(struct net_device *dev, int all) void __iomem *p = local->sram + HOST_TO_ECF_BASE; if (!(pcmcia_dev_present(link))) { - DEBUG(2, "ray_update_multi_list - device not present\n"); + dev_dbg(&link->dev, "ray_update_multi_list - device not present\n"); return; } else - DEBUG(2, "ray_update_multi_list(%p)\n", dev); + dev_dbg(&link->dev, "ray_update_multi_list(%p)\n", dev); if ((ccsindex = get_free_ccs(local)) < 0) { - DEBUG(1, "ray_update_multi - No free ccs\n"); + dev_dbg(&link->dev, "ray_update_multi - No free ccs\n"); return; } pccs = ccs_base(local) + ccsindex; @@ -1910,7 +1899,7 @@ static void ray_update_multi_list(struct net_device *dev, int all) for (dmip = &dev->mc_list; (dmi = *dmip) != NULL; dmip = &dmi->next) { memcpy_toio(p, dmi->dmi_addr, ETH_ALEN); - DEBUG(1, + dev_dbg(&link->dev, "ray_update_multi add addr %02x%02x%02x%02x%02x%02x\n", dmi->dmi_addr[0], dmi->dmi_addr[1], dmi->dmi_addr[2], dmi->dmi_addr[3], @@ -1921,12 +1910,12 @@ static void ray_update_multi_list(struct net_device *dev, int all) if (i > 256 / ADDRLEN) i = 256 / ADDRLEN; writeb((UCHAR) i, &pccs->var); - DEBUG(1, "ray_cs update_multi %d addresses in list\n", i); + dev_dbg(&link->dev, "ray_cs update_multi %d addresses in list\n", i); /* Interrupt the firmware to process the command */ local->num_multi = i; } if (interrupt_ecf(local, ccsindex)) { - DEBUG(1, + dev_dbg(&link->dev, "ray_cs update_multi failed - ECF not ready for intr\n"); writeb(CCS_BUFFER_FREE, &(pccs++)->buffer_status); } @@ -1938,11 +1927,11 @@ static void set_multicast_list(struct net_device *dev) ray_dev_t *local = netdev_priv(dev); UCHAR promisc; - DEBUG(2, "ray_cs set_multicast_list(%p)\n", dev); + pr_debug("ray_cs set_multicast_list(%p)\n", dev); if (dev->flags & IFF_PROMISC) { if (local->sparm.b5.a_promiscuous_mode == 0) { - DEBUG(1, "ray_cs set_multicast_list promisc on\n"); + pr_debug("ray_cs set_multicast_list promisc on\n"); local->sparm.b5.a_promiscuous_mode = 1; promisc = 1; ray_update_parm(dev, OBJID_promiscuous_mode, @@ -1950,7 +1939,7 @@ static void set_multicast_list(struct net_device *dev) } } else { if (local->sparm.b5.a_promiscuous_mode == 1) { - DEBUG(1, "ray_cs set_multicast_list promisc off\n"); + pr_debug("ray_cs set_multicast_list promisc off\n"); local->sparm.b5.a_promiscuous_mode = 0; promisc = 0; ray_update_parm(dev, OBJID_promiscuous_mode, @@ -1984,19 +1973,19 @@ static irqreturn_t ray_interrupt(int irq, void *dev_id) if (dev == NULL) /* Note that we want interrupts with dev->start == 0 */ return IRQ_NONE; - DEBUG(4, "ray_cs: interrupt for *dev=%p\n", dev); + pr_debug("ray_cs: interrupt for *dev=%p\n", dev); local = netdev_priv(dev); link = (struct pcmcia_device *)local->finder; if (!pcmcia_dev_present(link)) { - DEBUG(2, - "ray_cs interrupt from device not present or suspended.\n"); + pr_debug( + "ray_cs interrupt from device not present or suspended.\n"); return IRQ_NONE; } rcsindex = readb(&((struct scb __iomem *)(local->sram))->rcs_index); if (rcsindex >= (NUMBER_OF_CCS + NUMBER_OF_RCS)) { - DEBUG(1, "ray_cs interrupt bad rcsindex = 0x%x\n", rcsindex); + dev_dbg(&link->dev, "ray_cs interrupt bad rcsindex = 0x%x\n", rcsindex); clear_interrupt(local); return IRQ_HANDLED; } @@ -2008,33 +1997,33 @@ static irqreturn_t ray_interrupt(int irq, void *dev_id) case CCS_DOWNLOAD_STARTUP_PARAMS: /* Happens in firmware someday */ del_timer(&local->timer); if (status == CCS_COMMAND_COMPLETE) { - DEBUG(1, + dev_dbg(&link->dev, "ray_cs interrupt download_startup_parameters OK\n"); } else { - DEBUG(1, + dev_dbg(&link->dev, "ray_cs interrupt download_startup_parameters fail\n"); } break; case CCS_UPDATE_PARAMS: - DEBUG(1, "ray_cs interrupt update params done\n"); + dev_dbg(&link->dev, "ray_cs interrupt update params done\n"); if (status != CCS_COMMAND_COMPLETE) { tmp = readb(&pccs->var.update_param. failure_cause); - DEBUG(0, + dev_dbg(&link->dev, "ray_cs interrupt update params failed - reason %d\n", tmp); } break; case CCS_REPORT_PARAMS: - DEBUG(1, "ray_cs interrupt report params done\n"); + dev_dbg(&link->dev, "ray_cs interrupt report params done\n"); break; case CCS_UPDATE_MULTICAST_LIST: /* Note that this CCS isn't returned */ - DEBUG(1, + dev_dbg(&link->dev, "ray_cs interrupt CCS Update Multicast List done\n"); break; case CCS_UPDATE_POWER_SAVINGS_MODE: - DEBUG(1, + dev_dbg(&link->dev, "ray_cs interrupt update power save mode done\n"); break; case CCS_START_NETWORK: @@ -2043,11 +2032,11 @@ static irqreturn_t ray_interrupt(int irq, void *dev_id) if (readb (&pccs->var.start_network.net_initiated) == 1) { - DEBUG(0, + dev_dbg(&link->dev, "ray_cs interrupt network \"%s\" started\n", local->sparm.b4.a_current_ess_id); } else { - DEBUG(0, + dev_dbg(&link->dev, "ray_cs interrupt network \"%s\" joined\n", local->sparm.b4.a_current_ess_id); } @@ -2075,12 +2064,12 @@ static irqreturn_t ray_interrupt(int irq, void *dev_id) local->timer.expires = jiffies + HZ * 5; local->timer.data = (long)local; if (status == CCS_START_NETWORK) { - DEBUG(0, + dev_dbg(&link->dev, "ray_cs interrupt network \"%s\" start failed\n", local->sparm.b4.a_current_ess_id); local->timer.function = &start_net; } else { - DEBUG(0, + dev_dbg(&link->dev, "ray_cs interrupt network \"%s\" join failed\n", local->sparm.b4.a_current_ess_id); local->timer.function = &join_net; @@ -2091,19 +2080,19 @@ static irqreturn_t ray_interrupt(int irq, void *dev_id) case CCS_START_ASSOCIATION: if (status == CCS_COMMAND_COMPLETE) { local->card_status = CARD_ASSOC_COMPLETE; - DEBUG(0, "ray_cs association successful\n"); + dev_dbg(&link->dev, "ray_cs association successful\n"); } else { - DEBUG(0, "ray_cs association failed,\n"); + dev_dbg(&link->dev, "ray_cs association failed,\n"); local->card_status = CARD_ASSOC_FAILED; join_net((u_long) local); } break; case CCS_TX_REQUEST: if (status == CCS_COMMAND_COMPLETE) { - DEBUG(3, + dev_dbg(&link->dev, "ray_cs interrupt tx request complete\n"); } else { - DEBUG(1, + dev_dbg(&link->dev, "ray_cs interrupt tx request failed\n"); } if (!sniffer) @@ -2111,21 +2100,21 @@ static irqreturn_t ray_interrupt(int irq, void *dev_id) netif_wake_queue(dev); break; case CCS_TEST_MEMORY: - DEBUG(1, "ray_cs interrupt mem test done\n"); + dev_dbg(&link->dev, "ray_cs interrupt mem test done\n"); break; case CCS_SHUTDOWN: - DEBUG(1, + dev_dbg(&link->dev, "ray_cs interrupt Unexpected CCS returned - Shutdown\n"); break; case CCS_DUMP_MEMORY: - DEBUG(1, "ray_cs interrupt dump memory done\n"); + dev_dbg(&link->dev, "ray_cs interrupt dump memory done\n"); break; case CCS_START_TIMER: - DEBUG(2, + dev_dbg(&link->dev, "ray_cs interrupt DING - raylink timer expired\n"); break; default: - DEBUG(1, + dev_dbg(&link->dev, "ray_cs interrupt Unexpected CCS 0x%x returned 0x%x\n", rcsindex, cmd); } @@ -2139,7 +2128,7 @@ static irqreturn_t ray_interrupt(int irq, void *dev_id) ray_rx(dev, local, prcs); break; case REJOIN_NET_COMPLETE: - DEBUG(1, "ray_cs interrupt rejoin net complete\n"); + dev_dbg(&link->dev, "ray_cs interrupt rejoin net complete\n"); local->card_status = CARD_ACQ_COMPLETE; /* do we need to clear tx buffers CCS's? */ if (local->sparm.b4.a_network_type == ADHOC) { @@ -2149,7 +2138,7 @@ static irqreturn_t ray_interrupt(int irq, void *dev_id) memcpy_fromio(&local->bss_id, prcs->var.rejoin_net_complete. bssid, ADDRLEN); - DEBUG(1, + dev_dbg(&link->dev, "ray_cs new BSSID = %02x%02x%02x%02x%02x%02x\n", local->bss_id[0], local->bss_id[1], local->bss_id[2], local->bss_id[3], @@ -2159,15 +2148,15 @@ static irqreturn_t ray_interrupt(int irq, void *dev_id) } break; case ROAMING_INITIATED: - DEBUG(1, "ray_cs interrupt roaming initiated\n"); + dev_dbg(&link->dev, "ray_cs interrupt roaming initiated\n"); netif_stop_queue(dev); local->card_status = CARD_DOING_ACQ; break; case JAPAN_CALL_SIGN_RXD: - DEBUG(1, "ray_cs interrupt japan call sign rx\n"); + dev_dbg(&link->dev, "ray_cs interrupt japan call sign rx\n"); break; default: - DEBUG(1, + dev_dbg(&link->dev, "ray_cs Unexpected interrupt for RCS 0x%x cmd = 0x%x\n", rcsindex, (unsigned int)readb(&prcs->interrupt_id)); @@ -2186,7 +2175,7 @@ static void ray_rx(struct net_device *dev, ray_dev_t *local, int rx_len; unsigned int pkt_addr; void __iomem *pmsg; - DEBUG(4, "ray_rx process rx packet\n"); + pr_debug("ray_rx process rx packet\n"); /* Calculate address of packet within Rx buffer */ pkt_addr = ((readb(&prcs->var.rx_packet.rx_data_ptr[0]) << 8) @@ -2199,28 +2188,28 @@ static void ray_rx(struct net_device *dev, ray_dev_t *local, pmsg = local->rmem + pkt_addr; switch (readb(pmsg)) { case DATA_TYPE: - DEBUG(4, "ray_rx data type\n"); + pr_debug("ray_rx data type\n"); rx_data(dev, prcs, pkt_addr, rx_len); break; case AUTHENTIC_TYPE: - DEBUG(4, "ray_rx authentic type\n"); + pr_debug("ray_rx authentic type\n"); if (sniffer) rx_data(dev, prcs, pkt_addr, rx_len); else rx_authenticate(local, prcs, pkt_addr, rx_len); break; case DEAUTHENTIC_TYPE: - DEBUG(4, "ray_rx deauth type\n"); + pr_debug("ray_rx deauth type\n"); if (sniffer) rx_data(dev, prcs, pkt_addr, rx_len); else rx_deauthenticate(local, prcs, pkt_addr, rx_len); break; case NULL_MSG_TYPE: - DEBUG(3, "ray_cs rx NULL msg\n"); + pr_debug("ray_cs rx NULL msg\n"); break; case BEACON_TYPE: - DEBUG(4, "ray_rx beacon type\n"); + pr_debug("ray_rx beacon type\n"); if (sniffer) rx_data(dev, prcs, pkt_addr, rx_len); @@ -2233,7 +2222,7 @@ static void ray_rx(struct net_device *dev, ray_dev_t *local, ray_get_stats(dev); break; default: - DEBUG(0, "ray_cs unknown pkt type %2x\n", + pr_debug("ray_cs unknown pkt type %2x\n", (unsigned int)readb(pmsg)); break; } @@ -2262,7 +2251,7 @@ static void rx_data(struct net_device *dev, struct rcs __iomem *prcs, rx_len > (dev->mtu + RX_MAC_HEADER_LENGTH + ETH_HLEN + FCS_LEN)) { - DEBUG(0, + pr_debug( "ray_cs invalid packet length %d received \n", rx_len); return; @@ -2273,17 +2262,17 @@ static void rx_data(struct net_device *dev, struct rcs __iomem *prcs, rx_len > (dev->mtu + RX_MAC_HEADER_LENGTH + ETH_HLEN + FCS_LEN)) { - DEBUG(0, + pr_debug( "ray_cs invalid packet length %d received \n", rx_len); return; } } } - DEBUG(4, "ray_cs rx_data packet\n"); + pr_debug("ray_cs rx_data packet\n"); /* If fragmented packet, verify sizes of fragments add up */ if (readb(&prcs->var.rx_packet.next_frag_rcs_index) != 0xFF) { - DEBUG(1, "ray_cs rx'ed fragment\n"); + pr_debug("ray_cs rx'ed fragment\n"); tmp = (readb(&prcs->var.rx_packet.totalpacketlength[0]) << 8) + readb(&prcs->var.rx_packet.totalpacketlength[1]); total_len = tmp; @@ -2301,7 +2290,7 @@ static void rx_data(struct net_device *dev, struct rcs __iomem *prcs, } while (1); if (tmp < 0) { - DEBUG(0, + pr_debug( "ray_cs rx_data fragment lengths don't add up\n"); local->stats.rx_dropped++; release_frag_chain(local, prcs); @@ -2313,7 +2302,7 @@ static void rx_data(struct net_device *dev, struct rcs __iomem *prcs, skb = dev_alloc_skb(total_len + 5); if (skb == NULL) { - DEBUG(0, "ray_cs rx_data could not allocate skb\n"); + pr_debug("ray_cs rx_data could not allocate skb\n"); local->stats.rx_dropped++; if (readb(&prcs->var.rx_packet.next_frag_rcs_index) != 0xFF) release_frag_chain(local, prcs); @@ -2321,7 +2310,7 @@ static void rx_data(struct net_device *dev, struct rcs __iomem *prcs, } skb_reserve(skb, 2); /* Align IP on 16 byte (TBD check this) */ - DEBUG(4, "ray_cs rx_data total_len = %x, rx_len = %x\n", total_len, + pr_debug("ray_cs rx_data total_len = %x, rx_len = %x\n", total_len, rx_len); /************************/ @@ -2354,7 +2343,7 @@ static void rx_data(struct net_device *dev, struct rcs __iomem *prcs, tmp = 17; if (readb(&prcs->var.rx_packet.next_frag_rcs_index) != 0xFF) { prcslink = prcs; - DEBUG(1, "ray_cs rx_data in fragment loop\n"); + pr_debug("ray_cs rx_data in fragment loop\n"); do { prcslink = rcs_base(local) + @@ -2426,8 +2415,8 @@ static void untranslate(ray_dev_t *local, struct sk_buff *skb, int len) memcpy(destaddr, ieee80211_get_DA(pmac), ADDRLEN); memcpy(srcaddr, ieee80211_get_SA(pmac), ADDRLEN); -#ifdef PCMCIA_DEBUG - if (pc_debug > 3) { +#if 0 + if { print_hex_dump(KERN_DEBUG, "skb->data before untranslate: ", DUMP_PREFIX_NONE, 16, 1, skb->data, 64, true); @@ -2441,7 +2430,7 @@ static void untranslate(ray_dev_t *local, struct sk_buff *skb, int len) if (psnap->dsap != 0xaa || psnap->ssap != 0xaa || psnap->ctrl != 3) { /* not a snap type so leave it alone */ - DEBUG(3, "ray_cs untranslate NOT SNAP %02x %02x %02x\n", + pr_debug("ray_cs untranslate NOT SNAP %02x %02x %02x\n", psnap->dsap, psnap->ssap, psnap->ctrl); delta = RX_MAC_HEADER_LENGTH - ETH_HLEN; @@ -2450,7 +2439,7 @@ static void untranslate(ray_dev_t *local, struct sk_buff *skb, int len) } else { /* Its a SNAP */ if (memcmp(psnap->org, org_bridge, 3) == 0) { /* EtherII and nuke the LLC */ - DEBUG(3, "ray_cs untranslate Bridge encap\n"); + pr_debug("ray_cs untranslate Bridge encap\n"); delta = RX_MAC_HEADER_LENGTH + sizeof(struct snaphdr_t) - ETH_HLEN; peth = (struct ethhdr *)(skb->data + delta); @@ -2459,14 +2448,14 @@ static void untranslate(ray_dev_t *local, struct sk_buff *skb, int len) switch (ntohs(type)) { case ETH_P_IPX: case ETH_P_AARP: - DEBUG(3, "ray_cs untranslate RFC IPX/AARP\n"); + pr_debug("ray_cs untranslate RFC IPX/AARP\n"); delta = RX_MAC_HEADER_LENGTH - ETH_HLEN; peth = (struct ethhdr *)(skb->data + delta); peth->h_proto = htons(len - RX_MAC_HEADER_LENGTH); break; default: - DEBUG(3, "ray_cs untranslate RFC default\n"); + pr_debug("ray_cs untranslate RFC default\n"); delta = RX_MAC_HEADER_LENGTH + sizeof(struct snaphdr_t) - ETH_HLEN; peth = (struct ethhdr *)(skb->data + delta); @@ -2482,12 +2471,12 @@ static void untranslate(ray_dev_t *local, struct sk_buff *skb, int len) } /* TBD reserve skb_reserve(skb, delta); */ skb_pull(skb, delta); - DEBUG(3, "untranslate after skb_pull(%d), skb->data = %p\n", delta, + pr_debug("untranslate after skb_pull(%d), skb->data = %p\n", delta, skb->data); memcpy(peth->h_dest, destaddr, ADDRLEN); memcpy(peth->h_source, srcaddr, ADDRLEN); -#ifdef PCMCIA_DEBUG - if (pc_debug > 3) { +#if 0 + { int i; printk(KERN_DEBUG "skb->data after untranslate:"); for (i = 0; i < 64; i++) @@ -2529,7 +2518,7 @@ static void release_frag_chain(ray_dev_t *local, struct rcs __iomem *prcs) while (tmp--) { writeb(CCS_BUFFER_FREE, &prcslink->buffer_status); if (rcsindex >= (NUMBER_OF_CCS + NUMBER_OF_RCS)) { - DEBUG(1, "ray_cs interrupt bad rcsindex = 0x%x\n", + pr_debug("ray_cs interrupt bad rcsindex = 0x%x\n", rcsindex); break; } @@ -2543,9 +2532,9 @@ static void release_frag_chain(ray_dev_t *local, struct rcs __iomem *prcs) static void authenticate(ray_dev_t *local) { struct pcmcia_device *link = local->finder; - DEBUG(0, "ray_cs Starting authentication.\n"); + dev_dbg(&link->dev, "ray_cs Starting authentication.\n"); if (!(pcmcia_dev_present(link))) { - DEBUG(2, "ray_cs authenticate - device not present\n"); + dev_dbg(&link->dev, "ray_cs authenticate - device not present\n"); return; } @@ -2573,11 +2562,11 @@ static void rx_authenticate(ray_dev_t *local, struct rcs __iomem *prcs, copy_from_rx_buff(local, buff, pkt_addr, rx_len & 0xff); /* if we are trying to get authenticated */ if (local->sparm.b4.a_network_type == ADHOC) { - DEBUG(1, "ray_cs rx_auth var= %02x %02x %02x %02x %02x %02x\n", + pr_debug("ray_cs rx_auth var= %02x %02x %02x %02x %02x %02x\n", msg->var[0], msg->var[1], msg->var[2], msg->var[3], msg->var[4], msg->var[5]); if (msg->var[2] == 1) { - DEBUG(0, "ray_cs Sending authentication response.\n"); + pr_debug("ray_cs Sending authentication response.\n"); if (!build_auth_frame (local, msg->mac.addr_2, OPEN_AUTH_RESPONSE)) { local->authentication_state = NEED_TO_AUTH; @@ -2591,13 +2580,13 @@ static void rx_authenticate(ray_dev_t *local, struct rcs __iomem *prcs, /* Verify authentication sequence #2 and success */ if (msg->var[2] == 2) { if ((msg->var[3] | msg->var[4]) == 0) { - DEBUG(1, "Authentication successful\n"); + pr_debug("Authentication successful\n"); local->card_status = CARD_AUTH_COMPLETE; associate(local); local->authentication_state = AUTHENTICATED; } else { - DEBUG(0, "Authentication refused\n"); + pr_debug("Authentication refused\n"); local->card_status = CARD_AUTH_REFUSED; join_net((u_long) local); local->authentication_state = @@ -2617,22 +2606,22 @@ static void associate(ray_dev_t *local) struct net_device *dev = link->priv; int ccsindex; if (!(pcmcia_dev_present(link))) { - DEBUG(2, "ray_cs associate - device not present\n"); + dev_dbg(&link->dev, "ray_cs associate - device not present\n"); return; } /* If no tx buffers available, return */ if ((ccsindex = get_free_ccs(local)) < 0) { /* TBD should never be here but... what if we are? */ - DEBUG(1, "ray_cs associate - No free ccs\n"); + dev_dbg(&link->dev, "ray_cs associate - No free ccs\n"); return; } - DEBUG(1, "ray_cs Starting association with access point\n"); + dev_dbg(&link->dev, "ray_cs Starting association with access point\n"); pccs = ccs_base(local) + ccsindex; /* fill in the CCS */ writeb(CCS_START_ASSOCIATION, &pccs->cmd); /* Interrupt the firmware to process the command */ if (interrupt_ecf(local, ccsindex)) { - DEBUG(1, "ray_cs associate failed - ECF not ready for intr\n"); + dev_dbg(&link->dev, "ray_cs associate failed - ECF not ready for intr\n"); writeb(CCS_BUFFER_FREE, &(pccs++)->buffer_status); del_timer(&local->timer); @@ -2655,7 +2644,7 @@ static void rx_deauthenticate(ray_dev_t *local, struct rcs __iomem *prcs, /* UCHAR buff[256]; struct rx_msg *msg = (struct rx_msg *)buff; */ - DEBUG(0, "Deauthentication frame received\n"); + pr_debug("Deauthentication frame received\n"); local->authentication_state = UNAUTHENTICATED; /* Need to reauthenticate or rejoin depending on reason code */ /* copy_from_rx_buff(local, buff, pkt_addr, rx_len & 0xff); @@ -2823,7 +2812,7 @@ static int build_auth_frame(ray_dev_t *local, UCHAR *dest, int auth_type) /* If no tx buffers available, return */ if ((ccsindex = get_free_tx_ccs(local)) < 0) { - DEBUG(1, "ray_cs send authenticate - No free tx ccs\n"); + pr_debug("ray_cs send authenticate - No free tx ccs\n"); return -1; } @@ -2855,7 +2844,7 @@ static int build_auth_frame(ray_dev_t *local, UCHAR *dest, int auth_type) /* Interrupt the firmware to process the command */ if (interrupt_ecf(local, ccsindex)) { - DEBUG(1, + pr_debug( "ray_cs send authentication request failed - ECF not ready for intr\n"); writeb(CCS_BUFFER_FREE, &(pccs++)->buffer_status); return -1; @@ -2942,9 +2931,9 @@ static int __init init_ray_cs(void) { int rc; - DEBUG(1, "%s\n", rcsid); + pr_debug("%s\n", rcsid); rc = pcmcia_register_driver(&ray_driver); - DEBUG(1, "raylink init_module register_pcmcia_driver returns 0x%x\n", + pr_debug("raylink init_module register_pcmcia_driver returns 0x%x\n", rc); #ifdef CONFIG_PROC_FS @@ -2964,7 +2953,7 @@ static int __init init_ray_cs(void) static void __exit exit_ray_cs(void) { - DEBUG(0, "ray_cs: cleanup_module\n"); + pr_debug("ray_cs: cleanup_module\n"); #ifdef CONFIG_PROC_FS remove_proc_entry("driver/ray_cs/ray_cs", NULL); diff --git a/drivers/net/wireless/wavelan_cs.c b/drivers/net/wireless/wavelan_cs.c index 431a20ec6db6..33918fd5b231 100644 --- a/drivers/net/wireless/wavelan_cs.c +++ b/drivers/net/wireless/wavelan_cs.c @@ -3656,10 +3656,7 @@ wv_pcmcia_reset(struct net_device * dev) i = pcmcia_access_configuration_register(link, ®); if (i != 0) - { - cs_error(link, AccessConfigurationRegister, i); return FALSE; - } #ifdef DEBUG_CONFIG_INFO printk(KERN_DEBUG "%s: wavelan_pcmcia_reset(): Config reg is 0x%x\n", @@ -3670,19 +3667,13 @@ wv_pcmcia_reset(struct net_device * dev) reg.Value = reg.Value | COR_SW_RESET; i = pcmcia_access_configuration_register(link, ®); if (i != 0) - { - cs_error(link, AccessConfigurationRegister, i); return FALSE; - } reg.Action = CS_WRITE; reg.Value = COR_LEVEL_IRQ | COR_CONFIG; i = pcmcia_access_configuration_register(link, ®); if (i != 0) - { - cs_error(link, AccessConfigurationRegister, i); return FALSE; - } #ifdef DEBUG_CONFIG_TRACE printk(KERN_DEBUG "%s: <-wv_pcmcia_reset()\n", dev->name); @@ -3857,10 +3848,7 @@ wv_pcmcia_config(struct pcmcia_device * link) { i = pcmcia_request_io(link, &link->io); if (i != 0) - { - cs_error(link, RequestIO, i); break; - } /* * Now allocate an interrupt line. Note that this does not @@ -3868,10 +3856,7 @@ wv_pcmcia_config(struct pcmcia_device * link) */ i = pcmcia_request_irq(link, &link->irq); if (i != 0) - { - cs_error(link, RequestIRQ, i); break; - } /* * This actually configures the PCMCIA socket -- setting up @@ -3880,10 +3865,7 @@ wv_pcmcia_config(struct pcmcia_device * link) link->conf.ConfigIndex = 1; i = pcmcia_request_configuration(link, &link->conf); if (i != 0) - { - cs_error(link, RequestConfiguration, i); break; - } /* * Allocate a small memory window. Note that the struct pcmcia_device @@ -3894,24 +3876,18 @@ wv_pcmcia_config(struct pcmcia_device * link) req.Attributes = WIN_DATA_WIDTH_8|WIN_MEMORY_TYPE_AM|WIN_ENABLE; req.Base = req.Size = 0; req.AccessSpeed = mem_speed; - i = pcmcia_request_window(&link, &req, &link->win); + i = pcmcia_request_window(link, &req, &link->win); if (i != 0) - { - cs_error(link, RequestWindow, i); break; - } lp->mem = ioremap(req.Base, req.Size); dev->mem_start = (u_long)lp->mem; dev->mem_end = dev->mem_start + req.Size; mem.CardOffset = 0; mem.Page = 0; - i = pcmcia_map_mem_page(link->win, &mem); + i = pcmcia_map_mem_page(link, link->win, &mem); if (i != 0) - { - cs_error(link, MapMemPage, i); break; - } /* Feed device with this info... */ dev->irq = link->irq.AssignedIRQ; @@ -3923,7 +3899,7 @@ wv_pcmcia_config(struct pcmcia_device * link) lp->mem, dev->irq, (u_int) dev->base_addr); #endif - SET_NETDEV_DEV(dev, &handle_to_dev(link)); + SET_NETDEV_DEV(dev, &link->dev); i = register_netdev(dev); if(i != 0) { @@ -4462,8 +4438,7 @@ wavelan_probe(struct pcmcia_device *p_dev) p_dev->io.IOAddrLines = 3; /* Interrupt setup */ - p_dev->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING | IRQ_HANDLE_PRESENT; - p_dev->irq.IRQInfo1 = IRQ_LEVEL_ID; + p_dev->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; p_dev->irq.Handler = wavelan_interrupt; /* General socket configuration */ @@ -4475,7 +4450,7 @@ wavelan_probe(struct pcmcia_device *p_dev) if (!dev) return -ENOMEM; - p_dev->priv = p_dev->irq.Instance = dev; + p_dev->priv = dev; lp = netdev_priv(dev); diff --git a/drivers/net/wireless/wl3501_cs.c b/drivers/net/wireless/wl3501_cs.c index 4f1e0cfe609b..5f0401a52cff 100644 --- a/drivers/net/wireless/wl3501_cs.c +++ b/drivers/net/wireless/wl3501_cs.c @@ -67,23 +67,7 @@ /* For rough constant delay */ #define WL3501_NOPLOOP(n) { int x = 0; while (x++ < n) slow_down_io(); } -/* - * All the PCMCIA modules use PCMCIA_DEBUG to control debugging. If you do not - * define PCMCIA_DEBUG at all, all the debug code will be left out. If you - * compile with PCMCIA_DEBUG=0, the debug code will be present but disabled -- - * but it can then be enabled for specific modules at load time with a - * 'pc_debug=#' option to insmod. - */ -#define PCMCIA_DEBUG 0 -#ifdef PCMCIA_DEBUG -static int pc_debug = PCMCIA_DEBUG; -module_param(pc_debug, int, 0); -#define dprintk(n, format, args...) \ - { if (pc_debug > (n)) \ - printk(KERN_INFO "%s: " format "\n", __func__ , ##args); } -#else -#define dprintk(n, format, args...) -#endif + #define wl3501_outb(a, b) { outb(a, b); slow_down_io(); } #define wl3501_outb_p(a, b) { outb_p(a, b); slow_down_io(); } @@ -684,10 +668,10 @@ static void wl3501_mgmt_scan_confirm(struct wl3501_card *this, u16 addr) int matchflag = 0; struct wl3501_scan_confirm sig; - dprintk(3, "entry"); + pr_debug("entry"); wl3501_get_from_wla(this, addr, &sig, sizeof(sig)); if (sig.status == WL3501_STATUS_SUCCESS) { - dprintk(3, "success"); + pr_debug("success"); if ((this->net_type == IW_MODE_INFRA && (sig.cap_info & WL3501_MGMT_CAPABILITY_ESS)) || (this->net_type == IW_MODE_ADHOC && @@ -722,7 +706,7 @@ static void wl3501_mgmt_scan_confirm(struct wl3501_card *this, u16 addr) } } } else if (sig.status == WL3501_STATUS_TIMEOUT) { - dprintk(3, "timeout"); + pr_debug("timeout"); this->join_sta_bss = 0; for (i = this->join_sta_bss; i < this->bss_cnt; i++) if (!wl3501_mgmt_join(this, i)) @@ -879,7 +863,7 @@ static int wl3501_mgmt_auth(struct wl3501_card *this) .timeout = 1000, }; - dprintk(3, "entry"); + pr_debug("entry"); memcpy(sig.mac_addr, this->bssid, ETH_ALEN); return wl3501_esbq_exec(this, &sig, sizeof(sig)); } @@ -893,7 +877,7 @@ static int wl3501_mgmt_association(struct wl3501_card *this) .cap_info = this->cap_info, }; - dprintk(3, "entry"); + pr_debug("entry"); memcpy(sig.mac_addr, this->bssid, ETH_ALEN); return wl3501_esbq_exec(this, &sig, sizeof(sig)); } @@ -903,7 +887,7 @@ static void wl3501_mgmt_join_confirm(struct net_device *dev, u16 addr) struct wl3501_card *this = netdev_priv(dev); struct wl3501_join_confirm sig; - dprintk(3, "entry"); + pr_debug("entry"); wl3501_get_from_wla(this, addr, &sig, sizeof(sig)); if (sig.status == WL3501_STATUS_SUCCESS) { if (this->net_type == IW_MODE_INFRA) { @@ -962,7 +946,7 @@ static inline void wl3501_md_confirm_interrupt(struct net_device *dev, { struct wl3501_md_confirm sig; - dprintk(3, "entry"); + pr_debug("entry"); wl3501_get_from_wla(this, addr, &sig, sizeof(sig)); wl3501_free_tx_buffer(this, sig.data); if (netif_queue_stopped(dev)) @@ -1017,7 +1001,7 @@ static inline void wl3501_md_ind_interrupt(struct net_device *dev, static inline void wl3501_get_confirm_interrupt(struct wl3501_card *this, u16 addr, void *sig, int size) { - dprintk(3, "entry"); + pr_debug("entry"); wl3501_get_from_wla(this, addr, &this->sig_get_confirm, sizeof(this->sig_get_confirm)); wake_up(&this->wait); @@ -1029,7 +1013,7 @@ static inline void wl3501_start_confirm_interrupt(struct net_device *dev, { struct wl3501_start_confirm sig; - dprintk(3, "entry"); + pr_debug("entry"); wl3501_get_from_wla(this, addr, &sig, sizeof(sig)); if (sig.status == WL3501_STATUS_SUCCESS) netif_wake_queue(dev); @@ -1041,7 +1025,7 @@ static inline void wl3501_assoc_confirm_interrupt(struct net_device *dev, struct wl3501_card *this = netdev_priv(dev); struct wl3501_assoc_confirm sig; - dprintk(3, "entry"); + pr_debug("entry"); wl3501_get_from_wla(this, addr, &sig, sizeof(sig)); if (sig.status == WL3501_STATUS_SUCCESS) @@ -1053,7 +1037,7 @@ static inline void wl3501_auth_confirm_interrupt(struct wl3501_card *this, { struct wl3501_auth_confirm sig; - dprintk(3, "entry"); + pr_debug("entry"); wl3501_get_from_wla(this, addr, &sig, sizeof(sig)); if (sig.status == WL3501_STATUS_SUCCESS) @@ -1069,7 +1053,7 @@ static inline void wl3501_rx_interrupt(struct net_device *dev) u8 sig_id; struct wl3501_card *this = netdev_priv(dev); - dprintk(3, "entry"); + pr_debug("entry"); loop: morepkts = 0; if (!wl3501_esbq_confirm(this)) @@ -1302,7 +1286,7 @@ static int wl3501_reset(struct net_device *dev) wl3501_ack_interrupt(this); wl3501_unblock_interrupt(this); wl3501_mgmt_scan(this, 100); - dprintk(1, "%s: device reset", dev->name); + pr_debug("%s: device reset", dev->name); rc = 0; out: return rc; @@ -1376,7 +1360,7 @@ static int wl3501_open(struct net_device *dev) link->open++; /* Initial WL3501 firmware */ - dprintk(1, "%s: Initialize WL3501 firmware...", dev->name); + pr_debug("%s: Initialize WL3501 firmware...", dev->name); if (wl3501_init_firmware(this)) goto fail; /* Initial device variables */ @@ -1388,7 +1372,7 @@ static int wl3501_open(struct net_device *dev) wl3501_unblock_interrupt(this); wl3501_mgmt_scan(this, 100); rc = 0; - dprintk(1, "%s: WL3501 opened", dev->name); + pr_debug("%s: WL3501 opened", dev->name); printk(KERN_INFO "%s: Card Name: %s\n" "%s: Firmware Date: %s\n", dev->name, this->card_name, @@ -1914,8 +1898,7 @@ static int wl3501_probe(struct pcmcia_device *p_dev) p_dev->io.IOAddrLines = 5; /* Interrupt setup */ - p_dev->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING | IRQ_HANDLE_PRESENT; - p_dev->irq.IRQInfo1 = IRQ_LEVEL_ID; + p_dev->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; p_dev->irq.Handler = wl3501_interrupt; /* General socket configuration */ @@ -1938,16 +1921,13 @@ static int wl3501_probe(struct pcmcia_device *p_dev) dev->wireless_handlers = &wl3501_handler_def; SET_ETHTOOL_OPS(dev, &ops); netif_stop_queue(dev); - p_dev->priv = p_dev->irq.Instance = dev; + p_dev->priv = dev; return wl3501_config(p_dev); out_link: return -ENOMEM; } -#define CS_CHECK(fn, ret) \ -do { last_fn = (fn); if ((last_ret = (ret)) != 0) goto cs_failed; } while (0) - /** * wl3501_config - configure the PCMCIA socket and make eth device available * @link - FILL_IN @@ -1959,7 +1939,7 @@ do { last_fn = (fn); if ((last_ret = (ret)) != 0) goto cs_failed; } while (0) static int wl3501_config(struct pcmcia_device *link) { struct net_device *dev = link->priv; - int i = 0, j, last_fn, last_ret; + int i = 0, j, ret; struct wl3501_card *this; /* Try allocating IO ports. This tries a few fixed addresses. If you @@ -1975,24 +1955,26 @@ static int wl3501_config(struct pcmcia_device *link) if (i == 0) break; } - if (i != 0) { - cs_error(link, RequestIO, i); + if (i != 0) goto failed; - } /* Now allocate an interrupt line. Note that this does not actually * assign a handler to the interrupt. */ - CS_CHECK(RequestIRQ, pcmcia_request_irq(link, &link->irq)); + ret = pcmcia_request_irq(link, &link->irq); + if (ret) + goto failed; /* This actually configures the PCMCIA socket -- setting up the I/O * windows and the interrupt mapping. */ - CS_CHECK(RequestConfiguration, pcmcia_request_configuration(link, &link->conf)); + ret = pcmcia_request_configuration(link, &link->conf); + if (ret) + goto failed; dev->irq = link->irq.AssignedIRQ; dev->base_addr = link->io.BasePort1; - SET_NETDEV_DEV(dev, &handle_to_dev(link)); + SET_NETDEV_DEV(dev, &link->dev); if (register_netdev(dev)) { printk(KERN_NOTICE "wl3501_cs: register_netdev() failed\n"); goto failed; @@ -2041,8 +2023,6 @@ static int wl3501_config(struct pcmcia_device *link) netif_start_queue(dev); return 0; -cs_failed: - cs_error(link, last_fn, last_ret); failed: wl3501_release(link); return -ENODEV; diff --git a/drivers/of/base.c b/drivers/of/base.c index ddf224d456b2..e6627b2320f1 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -9,7 +9,8 @@ * * Adapted for sparc and sparc64 by David S. Miller davem@davemloft.net * - * Reconsolidated from arch/x/kernel/prom.c by Stephen Rothwell. + * Reconsolidated from arch/x/kernel/prom.c by Stephen Rothwell and + * Grant Likely. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -82,6 +83,29 @@ struct property *of_find_property(const struct device_node *np, } EXPORT_SYMBOL(of_find_property); +/** + * of_find_all_nodes - Get next node in global list + * @prev: Previous node or NULL to start iteration + * of_node_put() will be called on it + * + * Returns a node pointer with refcount incremented, use + * of_node_put() on it when done. + */ +struct device_node *of_find_all_nodes(struct device_node *prev) +{ + struct device_node *np; + + read_lock(&devtree_lock); + np = prev ? prev->allnext : allnodes; + for (; np != NULL; np = np->allnext) + if (of_node_get(np)) + break; + of_node_put(prev); + read_unlock(&devtree_lock); + return np; +} +EXPORT_SYMBOL(of_find_all_nodes); + /* * Find a property with a given name for a given node * and return the value. diff --git a/drivers/parport/parport_cs.c b/drivers/parport/parport_cs.c index 8fdfa4f537a6..7dd370fa3439 100644 --- a/drivers/parport/parport_cs.c +++ b/drivers/parport/parport_cs.c @@ -67,14 +67,6 @@ MODULE_LICENSE("Dual MPL/GPL"); INT_MODULE_PARM(epp_mode, 1); -#ifdef PCMCIA_DEBUG -INT_MODULE_PARM(pc_debug, PCMCIA_DEBUG); -#define DEBUG(n, args...) if (pc_debug>(n)) printk(KERN_DEBUG args) -static char *version = -"parport_cs.c 1.29 2002/10/11 06:57:41 (David Hinds)"; -#else -#define DEBUG(n, args...) -#endif /*====================================================================*/ @@ -103,7 +95,7 @@ static int parport_probe(struct pcmcia_device *link) { parport_info_t *info; - DEBUG(0, "parport_attach()\n"); + dev_dbg(&link->dev, "parport_attach()\n"); /* Create new parport device */ info = kzalloc(sizeof(*info), GFP_KERNEL); @@ -114,7 +106,6 @@ static int parport_probe(struct pcmcia_device *link) link->io.Attributes1 = IO_DATA_PATH_WIDTH_8; link->io.Attributes2 = IO_DATA_PATH_WIDTH_8; link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; link->conf.Attributes = CONF_ENABLE_IRQ; link->conf.IntType = INT_MEMORY_AND_IO; @@ -132,7 +123,7 @@ static int parport_probe(struct pcmcia_device *link) static void parport_detach(struct pcmcia_device *link) { - DEBUG(0, "parport_detach(0x%p)\n", link); + dev_dbg(&link->dev, "parport_detach\n"); parport_cs_release(link); @@ -147,9 +138,6 @@ static void parport_detach(struct pcmcia_device *link) ======================================================================*/ -#define CS_CHECK(fn, ret) \ -do { last_fn = (fn); if ((last_ret = (ret)) != 0) goto cs_failed; } while (0) - static int parport_config_check(struct pcmcia_device *p_dev, cistpl_cftable_entry_t *cfg, cistpl_cftable_entry_t *dflt, @@ -178,18 +166,20 @@ static int parport_config(struct pcmcia_device *link) { parport_info_t *info = link->priv; struct parport *p; - int last_ret, last_fn; + int ret; - DEBUG(0, "parport_config(0x%p)\n", link); + dev_dbg(&link->dev, "parport_config\n"); - last_ret = pcmcia_loop_config(link, parport_config_check, NULL); - if (last_ret) { - cs_error(link, RequestIO, last_ret); + ret = pcmcia_loop_config(link, parport_config_check, NULL); + if (ret) goto failed; - } - CS_CHECK(RequestIRQ, pcmcia_request_irq(link, &link->irq)); - CS_CHECK(RequestConfiguration, pcmcia_request_configuration(link, &link->conf)); + ret = pcmcia_request_irq(link, &link->irq); + if (ret) + goto failed; + ret = pcmcia_request_configuration(link, &link->conf); + if (ret) + goto failed; p = parport_pc_probe_port(link->io.BasePort1, link->io.BasePort2, link->irq.AssignedIRQ, PARPORT_DMA_NONE, @@ -213,8 +203,6 @@ static int parport_config(struct pcmcia_device *link) return 0; -cs_failed: - cs_error(link, last_fn, last_ret); failed: parport_cs_release(link); return -ENODEV; @@ -232,7 +220,7 @@ static void parport_cs_release(struct pcmcia_device *link) { parport_info_t *info = link->priv; - DEBUG(0, "parport_release(0x%p)\n", link); + dev_dbg(&link->dev, "parport_release\n"); if (info->ndev) { struct parport *p = info->port; diff --git a/drivers/parport/procfs.c b/drivers/parport/procfs.c index 8eefe56f1cbe..3f56bc086cb5 100644 --- a/drivers/parport/procfs.c +++ b/drivers/parport/procfs.c @@ -233,10 +233,10 @@ static int do_hardware_modes (ctl_table *table, int write, return copy_to_user(result, buffer, len) ? -EFAULT : 0; } -#define PARPORT_PORT_DIR(CHILD) { .ctl_name = 0, .procname = NULL, .mode = 0555, .child = CHILD } -#define PARPORT_PARPORT_DIR(CHILD) { .ctl_name = DEV_PARPORT, .procname = "parport", \ +#define PARPORT_PORT_DIR(CHILD) { .procname = NULL, .mode = 0555, .child = CHILD } +#define PARPORT_PARPORT_DIR(CHILD) { .procname = "parport", \ .mode = 0555, .child = CHILD } -#define PARPORT_DEV_DIR(CHILD) { .ctl_name = CTL_DEV, .procname = "dev", .mode = 0555, .child = CHILD } +#define PARPORT_DEV_DIR(CHILD) { .procname = "dev", .mode = 0555, .child = CHILD } #define PARPORT_DEVICES_ROOT_DIR { .procname = "devices", \ .mode = 0555, .child = NULL } @@ -270,7 +270,7 @@ static const struct parport_sysctl_table parport_sysctl_template = { .data = NULL, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, + .proc_handler = proc_dointvec_minmax, .extra1 = (void*) &parport_min_spintime_value, .extra2 = (void*) &parport_max_spintime_value }, @@ -279,28 +279,28 @@ static const struct parport_sysctl_table parport_sysctl_template = { .data = NULL, .maxlen = 0, .mode = 0444, - .proc_handler = &do_hardware_base_addr + .proc_handler = do_hardware_base_addr }, { .procname = "irq", .data = NULL, .maxlen = 0, .mode = 0444, - .proc_handler = &do_hardware_irq + .proc_handler = do_hardware_irq }, { .procname = "dma", .data = NULL, .maxlen = 0, .mode = 0444, - .proc_handler = &do_hardware_dma + .proc_handler = do_hardware_dma }, { .procname = "modes", .data = NULL, .maxlen = 0, .mode = 0444, - .proc_handler = &do_hardware_modes + .proc_handler = do_hardware_modes }, PARPORT_DEVICES_ROOT_DIR, #ifdef CONFIG_PARPORT_1284 @@ -309,35 +309,35 @@ static const struct parport_sysctl_table parport_sysctl_template = { .data = NULL, .maxlen = 0, .mode = 0444, - .proc_handler = &do_autoprobe + .proc_handler = do_autoprobe }, { .procname = "autoprobe0", .data = NULL, .maxlen = 0, .mode = 0444, - .proc_handler = &do_autoprobe + .proc_handler = do_autoprobe }, { .procname = "autoprobe1", .data = NULL, .maxlen = 0, .mode = 0444, - .proc_handler = &do_autoprobe + .proc_handler = do_autoprobe }, { .procname = "autoprobe2", .data = NULL, .maxlen = 0, .mode = 0444, - .proc_handler = &do_autoprobe + .proc_handler = do_autoprobe }, { .procname = "autoprobe3", .data = NULL, .maxlen = 0, .mode = 0444, - .proc_handler = &do_autoprobe + .proc_handler = do_autoprobe }, #endif /* IEEE 1284 support */ {} @@ -348,7 +348,7 @@ static const struct parport_sysctl_table parport_sysctl_template = { .data = NULL, .maxlen = 0, .mode = 0444, - .proc_handler = &do_active_device + .proc_handler = do_active_device }, {} }, @@ -386,14 +386,13 @@ parport_device_sysctl_template = { .data = NULL, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &proc_doulongvec_ms_jiffies_minmax, + .proc_handler = proc_doulongvec_ms_jiffies_minmax, .extra1 = (void*) &parport_min_timeslice_value, .extra2 = (void*) &parport_max_timeslice_value }, }, { { - .ctl_name = 0, .procname = NULL, .data = NULL, .maxlen = 0, @@ -438,7 +437,7 @@ parport_default_sysctl_table = { .data = &parport_default_timeslice, .maxlen = sizeof(parport_default_timeslice), .mode = 0644, - .proc_handler = &proc_doulongvec_ms_jiffies_minmax, + .proc_handler = proc_doulongvec_ms_jiffies_minmax, .extra1 = (void*) &parport_min_timeslice_value, .extra2 = (void*) &parport_max_timeslice_value }, @@ -447,7 +446,7 @@ parport_default_sysctl_table = { .data = &parport_default_spintime, .maxlen = sizeof(parport_default_spintime), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, + .proc_handler = proc_dointvec_minmax, .extra1 = (void*) &parport_min_spintime_value, .extra2 = (void*) &parport_max_spintime_value }, @@ -455,7 +454,6 @@ parport_default_sysctl_table = { }, { { - .ctl_name = DEV_PARPORT_DEFAULT, .procname = "default", .mode = 0555, .child = parport_default_sysctl_table.vars @@ -495,7 +493,6 @@ int parport_proc_register(struct parport *port) t->vars[6 + i].extra2 = &port->probe_info[i]; t->port_dir[0].procname = port->name; - t->port_dir[0].ctl_name = 0; t->port_dir[0].child = t->vars; t->parport_dir[0].child = t->port_dir; @@ -534,11 +531,9 @@ int parport_device_proc_register(struct pardevice *device) t->dev_dir[0].child = t->parport_dir; t->parport_dir[0].child = t->port_dir; t->port_dir[0].procname = port->name; - t->port_dir[0].ctl_name = 0; t->port_dir[0].child = t->devices_root_dir; t->devices_root_dir[0].child = t->device_dir; - t->device_dir[0].ctl_name = 0; t->device_dir[0].procname = device->name; t->device_dir[0].child = t->vars; t->vars[0].data = &device->timeslice; diff --git a/drivers/pci/dmar.c b/drivers/pci/dmar.c index b952ebc7a78b..416f6ac65b76 100644 --- a/drivers/pci/dmar.c +++ b/drivers/pci/dmar.c @@ -645,10 +645,13 @@ void __init detect_intel_iommu(void) "x2apic and Intr-remapping.\n"); #endif #ifdef CONFIG_DMAR - if (ret && !no_iommu && !iommu_detected && !swiotlb && - !dmar_disabled) + if (ret && !no_iommu && !iommu_detected && !dmar_disabled) iommu_detected = 1; #endif +#ifdef CONFIG_X86 + if (ret) + x86_init.iommu.iommu_init = intel_iommu_init; +#endif } early_acpi_os_unmap_memory(dmar_tbl, dmar_tbl_size); dmar_tbl = NULL; diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c index 1840a0578a42..9261327b49f3 100644 --- a/drivers/pci/intel-iommu.c +++ b/drivers/pci/intel-iommu.c @@ -3266,7 +3266,7 @@ int __init intel_iommu_init(void) * Check the need for DMA-remapping initialization now. * Above initialization will also be used by Interrupt-remapping. */ - if (no_iommu || swiotlb || dmar_disabled) + if (no_iommu || dmar_disabled) return -ENODEV; iommu_init_mempool(); @@ -3287,7 +3287,9 @@ int __init intel_iommu_init(void) "PCI-DMA: Intel(R) Virtualization Technology for Directed I/O\n"); init_timer(&unmap_timer); - force_iommu = 1; +#ifdef CONFIG_SWIOTLB + swiotlb = 0; +#endif dma_ops = &intel_dma_ops; init_iommu_sysfs(); diff --git a/drivers/pcmcia/Kconfig b/drivers/pcmcia/Kconfig index 17f38a781d47..f3ccbccf5f21 100644 --- a/drivers/pcmcia/Kconfig +++ b/drivers/pcmcia/Kconfig @@ -17,24 +17,6 @@ menuconfig PCCARD if PCCARD -config PCMCIA_DEBUG - bool "Enable PCCARD debugging" - help - Say Y here to enable PCMCIA subsystem debugging. You - will need to choose the debugging level either via the - kernel command line, or module options depending whether - you build the PCMCIA as modules. - - The kernel command line options are: - pcmcia_core.pc_debug=N - pcmcia.pc_debug=N - sa11xx_core.pc_debug=N - - The module option is called pc_debug=N - - In all the above examples, N is the debugging verbosity - level. - config PCMCIA tristate "16-bit PCMCIA support" select CRC32 @@ -196,9 +178,13 @@ config PCMCIA_BCM63XX tristate "bcm63xx pcmcia support" depends on BCM63XX && PCMCIA +config PCMCIA_SOC_COMMON + bool + config PCMCIA_SA1100 tristate "SA1100 support" depends on ARM && ARCH_SA1100 && PCMCIA + select PCMCIA_SOC_COMMON help Say Y here to include support for SA11x0-based PCMCIA or CF sockets, found on HP iPAQs, Yopy, and other StrongARM(R)/ @@ -209,6 +195,7 @@ config PCMCIA_SA1100 config PCMCIA_SA1111 tristate "SA1111 support" depends on ARM && ARCH_SA1100 && SA1111 && PCMCIA + select PCMCIA_SOC_COMMON help Say Y here to include support for SA1111-based PCMCIA or CF sockets, found on the Jornada 720, Graphicsmaster and other @@ -222,9 +209,28 @@ config PCMCIA_PXA2XX depends on (ARCH_LUBBOCK || MACH_MAINSTONE || PXA_SHARPSL \ || MACH_ARMCORE || ARCH_PXA_PALM || TRIZEPS_PCMCIA \ || ARCH_VIPER || ARCH_PXA_ESERIES || MACH_STARGATE2) + select PCMCIA_SOC_COMMON help Say Y here to include support for the PXA2xx PCMCIA controller +config PCMCIA_DEBUG + bool "Enable debugging" + depends on (PCMCIA_SA1111 || PCMCIA_SA1100 || PCMCIA_PXA2XX) + help + Say Y here to enable debugging for the SoC PCMCIA layer. + You will need to choose the debugging level either via the + kernel command line, or module options depending whether + you build the drivers as modules. + + The kernel command line options are: + sa11xx_core.pc_debug=N + pxa2xx_core.pc_debug=N + + The module option is called pc_debug=N + + In all the above examples, N is the debugging verbosity + level. + config PCMCIA_PROBE bool default y if ISA && !ARCH_SA1100 && !ARCH_CLPS711X && !PARISC diff --git a/drivers/pcmcia/Makefile b/drivers/pcmcia/Makefile index a03a38acd77d..382938313991 100644 --- a/drivers/pcmcia/Makefile +++ b/drivers/pcmcia/Makefile @@ -22,8 +22,9 @@ obj-$(CONFIG_I82365) += i82365.o obj-$(CONFIG_I82092) += i82092.o obj-$(CONFIG_TCIC) += tcic.o obj-$(CONFIG_PCMCIA_M8XX) += m8xx_pcmcia.o -obj-$(CONFIG_PCMCIA_SA1100) += sa11xx_core.o sa1100_cs.o -obj-$(CONFIG_PCMCIA_SA1111) += sa11xx_core.o sa1111_cs.o +obj-$(CONFIG_PCMCIA_SOC_COMMON) += soc_common.o +obj-$(CONFIG_PCMCIA_SA1100) += sa11xx_base.o sa1100_cs.o +obj-$(CONFIG_PCMCIA_SA1111) += sa11xx_base.o sa1111_cs.o obj-$(CONFIG_M32R_PCC) += m32r_pcc.o obj-$(CONFIG_M32R_CFC) += m32r_cfc.o obj-$(CONFIG_PCMCIA_AU1X00) += au1x00_ss.o @@ -35,9 +36,6 @@ obj-$(CONFIG_BFIN_CFPCMCIA) += bfin_cf_pcmcia.o obj-$(CONFIG_AT91_CF) += at91_cf.o obj-$(CONFIG_ELECTRA_CF) += electra_cf.o -sa11xx_core-y += soc_common.o sa11xx_base.o -pxa2xx_core-y += soc_common.o pxa2xx_base.o - au1x00_ss-y += au1000_generic.o au1x00_ss-$(CONFIG_MIPS_PB1000) += au1000_pb1x00.o au1x00_ss-$(CONFIG_MIPS_PB1100) += au1000_pb1x00.o @@ -77,4 +75,4 @@ pxa2xx-obj-$(CONFIG_MACH_PALMLD) += pxa2xx_palmld.o pxa2xx-obj-$(CONFIG_MACH_E740) += pxa2xx_e740.o pxa2xx-obj-$(CONFIG_MACH_STARGATE2) += pxa2xx_stargate2.o -obj-$(CONFIG_PCMCIA_PXA2XX) += pxa2xx_core.o $(pxa2xx-obj-y) +obj-$(CONFIG_PCMCIA_PXA2XX) += pxa2xx_base.o $(pxa2xx-obj-y) diff --git a/drivers/pcmcia/cardbus.c b/drivers/pcmcia/cardbus.c index db77e1f3309a..4cd70d056810 100644 --- a/drivers/pcmcia/cardbus.c +++ b/drivers/pcmcia/cardbus.c @@ -91,7 +91,7 @@ static u_int xlate_rom_addr(void __iomem *b, u_int addr) static void cb_release_cis_mem(struct pcmcia_socket * s) { if (s->cb_cis_virt) { - cs_dbg(s, 1, "cb_release_cis_mem()\n"); + dev_dbg(&s->dev, "cb_release_cis_mem()\n"); iounmap(s->cb_cis_virt); s->cb_cis_virt = NULL; s->cb_cis_res = NULL; @@ -132,7 +132,7 @@ int read_cb_mem(struct pcmcia_socket * s, int space, u_int addr, u_int len, void struct pci_dev *dev; struct resource *res; - cs_dbg(s, 3, "read_cb_mem(%d, %#x, %u)\n", space, addr, len); + dev_dbg(&s->dev, "read_cb_mem(%d, %#x, %u)\n", space, addr, len); dev = pci_get_slot(s->cb_dev->subordinate, 0); if (!dev) diff --git a/drivers/pcmcia/cirrus.h b/drivers/pcmcia/cirrus.h index ecd4fc7f666f..446a4576e73e 100644 --- a/drivers/pcmcia/cirrus.h +++ b/drivers/pcmcia/cirrus.h @@ -30,16 +30,6 @@ #ifndef _LINUX_CIRRUS_H #define _LINUX_CIRRUS_H -#ifndef PCI_VENDOR_ID_CIRRUS -#define PCI_VENDOR_ID_CIRRUS 0x1013 -#endif -#ifndef PCI_DEVICE_ID_CIRRUS_6729 -#define PCI_DEVICE_ID_CIRRUS_6729 0x1100 -#endif -#ifndef PCI_DEVICE_ID_CIRRUS_6832 -#define PCI_DEVICE_ID_CIRRUS_6832 0x1110 -#endif - #define PD67_MISC_CTL_1 0x16 /* Misc control 1 */ #define PD67_FIFO_CTL 0x17 /* FIFO control */ #define PD67_MISC_CTL_2 0x1E /* Misc control 2 */ diff --git a/drivers/pcmcia/cistpl.c b/drivers/pcmcia/cistpl.c index 6c4a4fc83630..8c1b73cf021b 100644 --- a/drivers/pcmcia/cistpl.c +++ b/drivers/pcmcia/cistpl.c @@ -138,7 +138,7 @@ int pcmcia_read_cis_mem(struct pcmcia_socket *s, int attr, u_int addr, void __iomem *sys, *end; unsigned char *buf = ptr; - cs_dbg(s, 3, "pcmcia_read_cis_mem(%d, %#x, %u)\n", attr, addr, len); + dev_dbg(&s->dev, "pcmcia_read_cis_mem(%d, %#x, %u)\n", attr, addr, len); if (attr & IS_INDIRECT) { /* Indirect accesses use a bunch of special registers at fixed @@ -190,7 +190,7 @@ int pcmcia_read_cis_mem(struct pcmcia_socket *s, int attr, u_int addr, addr = 0; } } - cs_dbg(s, 3, " %#2.2x %#2.2x %#2.2x %#2.2x ...\n", + dev_dbg(&s->dev, " %#2.2x %#2.2x %#2.2x %#2.2x ...\n", *(u_char *)(ptr+0), *(u_char *)(ptr+1), *(u_char *)(ptr+2), *(u_char *)(ptr+3)); return 0; @@ -204,7 +204,7 @@ void pcmcia_write_cis_mem(struct pcmcia_socket *s, int attr, u_int addr, void __iomem *sys, *end; unsigned char *buf = ptr; - cs_dbg(s, 3, "pcmcia_write_cis_mem(%d, %#x, %u)\n", attr, addr, len); + dev_dbg(&s->dev, "pcmcia_write_cis_mem(%d, %#x, %u)\n", attr, addr, len); if (attr & IS_INDIRECT) { /* Indirect accesses use a bunch of special registers at fixed @@ -584,7 +584,7 @@ int pccard_get_next_tuple(struct pcmcia_socket *s, unsigned int function, tuple_ ofs += link[1] + 2; } if (i == MAX_TUPLES) { - cs_dbg(s, 1, "cs: overrun in pcmcia_get_next_tuple\n"); + dev_dbg(&s->dev, "cs: overrun in pcmcia_get_next_tuple\n"); return -ENOSPC; } @@ -1440,7 +1440,7 @@ int pcmcia_parse_tuple(tuple_t *tuple, cisparse_t *parse) break; } if (ret) - __cs_dbg(0, "parse_tuple failed %d\n", ret); + pr_debug("parse_tuple failed %d\n", ret); return ret; } EXPORT_SYMBOL(pcmcia_parse_tuple); @@ -1482,6 +1482,67 @@ done: } EXPORT_SYMBOL(pccard_read_tuple); + +/** + * pccard_loop_tuple() - loop over tuples in the CIS + * @s: the struct pcmcia_socket where the card is inserted + * @function: the device function we loop for + * @code: which CIS code shall we look for? + * @parse: buffer where the tuple shall be parsed (or NULL, if no parse) + * @priv_data: private data to be passed to the loop_tuple function. + * @loop_tuple: function to call for each CIS entry of type @function. IT + * gets passed the raw tuple, the paresed tuple (if @parse is + * set) and @priv_data. + * + * pccard_loop_tuple() loops over all CIS entries of type @function, and + * calls the @loop_tuple function for each entry. If the call to @loop_tuple + * returns 0, the loop exits. Returns 0 on success or errorcode otherwise. + */ +int pccard_loop_tuple(struct pcmcia_socket *s, unsigned int function, + cisdata_t code, cisparse_t *parse, void *priv_data, + int (*loop_tuple) (tuple_t *tuple, + cisparse_t *parse, + void *priv_data)) +{ + tuple_t tuple; + cisdata_t *buf; + int ret; + + buf = kzalloc(256, GFP_KERNEL); + if (buf == NULL) { + dev_printk(KERN_WARNING, &s->dev, "no memory to read tuple\n"); + return -ENOMEM; + } + + tuple.TupleData = buf; + tuple.TupleDataMax = 255; + tuple.TupleOffset = 0; + tuple.DesiredTuple = code; + tuple.Attributes = 0; + + ret = pccard_get_first_tuple(s, function, &tuple); + while (!ret) { + if (pccard_get_tuple_data(s, &tuple)) + goto next_entry; + + if (parse) + if (pcmcia_parse_tuple(&tuple, parse)) + goto next_entry; + + ret = loop_tuple(&tuple, parse, priv_data); + if (!ret) + break; + +next_entry: + ret = pccard_get_next_tuple(s, function, &tuple); + } + + kfree(buf); + return ret; +} +EXPORT_SYMBOL(pccard_loop_tuple); + + /*====================================================================== This tries to determine if a card has a sensible CIS. It returns diff --git a/drivers/pcmcia/cs.c b/drivers/pcmcia/cs.c index 698d75cda084..790af87a922f 100644 --- a/drivers/pcmcia/cs.c +++ b/drivers/pcmcia/cs.c @@ -61,17 +61,6 @@ INT_MODULE_PARM(unreset_limit, 30); /* unreset_check's */ /* Access speed for attribute memory windows */ INT_MODULE_PARM(cis_speed, 300); /* ns */ -#ifdef CONFIG_PCMCIA_DEBUG -static int pc_debug; - -module_param(pc_debug, int, 0644); - -int cs_debug_level(int level) -{ - return pc_debug > level; -} -#endif - socket_state_t dead_socket = { .csc_mask = SS_DETECT, @@ -190,7 +179,7 @@ int pcmcia_register_socket(struct pcmcia_socket *socket) if (!socket || !socket->ops || !socket->dev.parent || !socket->resource_ops) return -EINVAL; - cs_dbg(socket, 0, "pcmcia_register_socket(0x%p)\n", socket->ops); + dev_dbg(&socket->dev, "pcmcia_register_socket(0x%p)\n", socket->ops); spin_lock_init(&socket->lock); @@ -262,6 +251,13 @@ int pcmcia_register_socket(struct pcmcia_socket *socket) pcmcia_parse_events(socket, SS_DETECT); + /* + * Let's try to get the PCMCIA module for 16-bit PCMCIA support. + * If it fails, it doesn't matter -- we still have 32-bit CardBus + * support to offer, so this is not a failure mode. + */ + request_module_nowait("pcmcia"); + return 0; err: @@ -282,7 +278,7 @@ void pcmcia_unregister_socket(struct pcmcia_socket *socket) if (!socket) return; - cs_dbg(socket, 0, "pcmcia_unregister_socket(0x%p)\n", socket->ops); + dev_dbg(&socket->dev, "pcmcia_unregister_socket(0x%p)\n", socket->ops); if (socket->thread) kthread_stop(socket->thread); @@ -335,7 +331,7 @@ static int send_event(struct pcmcia_socket *s, event_t event, int priority) if (s->state & SOCKET_CARDBUS) return 0; - cs_dbg(s, 1, "send_event(event %d, pri %d, callback 0x%p)\n", + dev_dbg(&s->dev, "send_event(event %d, pri %d, callback 0x%p)\n", event, priority, s->callback); if (!s->callback) @@ -352,7 +348,7 @@ static int send_event(struct pcmcia_socket *s, event_t event, int priority) static void socket_remove_drivers(struct pcmcia_socket *skt) { - cs_dbg(skt, 4, "remove_drivers\n"); + dev_dbg(&skt->dev, "remove_drivers\n"); send_event(skt, CS_EVENT_CARD_REMOVAL, CS_EVENT_PRI_HIGH); } @@ -361,7 +357,7 @@ static int socket_reset(struct pcmcia_socket *skt) { int status, i; - cs_dbg(skt, 4, "reset\n"); + dev_dbg(&skt->dev, "reset\n"); skt->socket.flags |= SS_OUTPUT_ENA | SS_RESET; skt->ops->set_socket(skt, &skt->socket); @@ -383,7 +379,7 @@ static int socket_reset(struct pcmcia_socket *skt) msleep(unreset_check * 10); } - cs_err(skt, "time out after reset.\n"); + dev_printk(KERN_ERR, &skt->dev, "time out after reset.\n"); return -ETIMEDOUT; } @@ -397,7 +393,7 @@ static void socket_shutdown(struct pcmcia_socket *s) { int status; - cs_dbg(s, 4, "shutdown\n"); + dev_dbg(&s->dev, "shutdown\n"); socket_remove_drivers(s); s->state &= SOCKET_INUSE | SOCKET_PRESENT; @@ -432,7 +428,7 @@ static int socket_setup(struct pcmcia_socket *skt, int initial_delay) { int status, i; - cs_dbg(skt, 4, "setup\n"); + dev_dbg(&skt->dev, "setup\n"); skt->ops->get_status(skt, &status); if (!(status & SS_DETECT)) @@ -452,13 +448,15 @@ static int socket_setup(struct pcmcia_socket *skt, int initial_delay) } if (status & SS_PENDING) { - cs_err(skt, "voltage interrogation timed out.\n"); + dev_printk(KERN_ERR, &skt->dev, + "voltage interrogation timed out.\n"); return -ETIMEDOUT; } if (status & SS_CARDBUS) { if (!(skt->features & SS_CAP_CARDBUS)) { - cs_err(skt, "cardbus cards are not supported.\n"); + dev_printk(KERN_ERR, &skt->dev, + "cardbus cards are not supported.\n"); return -EINVAL; } skt->state |= SOCKET_CARDBUS; @@ -472,7 +470,7 @@ static int socket_setup(struct pcmcia_socket *skt, int initial_delay) else if (!(status & SS_XVCARD)) skt->socket.Vcc = skt->socket.Vpp = 50; else { - cs_err(skt, "unsupported voltage key.\n"); + dev_printk(KERN_ERR, &skt->dev, "unsupported voltage key.\n"); return -EIO; } @@ -489,7 +487,7 @@ static int socket_setup(struct pcmcia_socket *skt, int initial_delay) skt->ops->get_status(skt, &status); if (!(status & SS_POWERON)) { - cs_err(skt, "unable to apply power.\n"); + dev_printk(KERN_ERR, &skt->dev, "unable to apply power.\n"); return -EIO; } @@ -509,7 +507,7 @@ static int socket_insert(struct pcmcia_socket *skt) { int ret; - cs_dbg(skt, 4, "insert\n"); + dev_dbg(&skt->dev, "insert\n"); if (!cs_socket_get(skt)) return -ENODEV; @@ -529,7 +527,7 @@ static int socket_insert(struct pcmcia_socket *skt) skt->state |= SOCKET_CARDBUS_CONFIG; } #endif - cs_dbg(skt, 4, "insert done\n"); + dev_dbg(&skt->dev, "insert done\n"); send_event(skt, CS_EVENT_CARD_INSERTION, CS_EVENT_PRI_LOW); } else { @@ -576,7 +574,7 @@ static int socket_late_resume(struct pcmcia_socket *skt) * FIXME: need a better check here for cardbus cards. */ if (verify_cis_cache(skt) != 0) { - cs_dbg(skt, 4, "cis mismatch - different card\n"); + dev_dbg(&skt->dev, "cis mismatch - different card\n"); socket_remove_drivers(skt); destroy_cis_cache(skt); /* @@ -587,7 +585,7 @@ static int socket_late_resume(struct pcmcia_socket *skt) msleep(200); send_event(skt, CS_EVENT_CARD_INSERTION, CS_EVENT_PRI_LOW); } else { - cs_dbg(skt, 4, "cis matches cache\n"); + dev_dbg(&skt->dev, "cis matches cache\n"); send_event(skt, CS_EVENT_PM_RESUME, CS_EVENT_PRI_LOW); } } else { @@ -723,7 +721,7 @@ static int pccardd(void *__skt) void pcmcia_parse_events(struct pcmcia_socket *s, u_int events) { unsigned long flags; - cs_dbg(s, 4, "parse_events: events %08x\n", events); + dev_dbg(&s->dev, "parse_events: events %08x\n", events); if (s->thread) { spin_lock_irqsave(&s->thread_lock, flags); s->thread_events |= events; @@ -773,19 +771,22 @@ int pcmcia_reset_card(struct pcmcia_socket *skt) { int ret; - cs_dbg(skt, 1, "resetting socket\n"); + dev_dbg(&skt->dev, "resetting socket\n"); mutex_lock(&skt->skt_mutex); do { if (!(skt->state & SOCKET_PRESENT)) { + dev_dbg(&skt->dev, "can't reset, not present\n"); ret = -ENODEV; break; } if (skt->state & SOCKET_SUSPEND) { + dev_dbg(&skt->dev, "can't reset, suspended\n"); ret = -EBUSY; break; } if (skt->state & SOCKET_CARDBUS) { + dev_dbg(&skt->dev, "can't reset, is cardbus\n"); ret = -EPERM; break; } @@ -818,7 +819,7 @@ int pcmcia_suspend_card(struct pcmcia_socket *skt) { int ret; - cs_dbg(skt, 1, "suspending socket\n"); + dev_dbg(&skt->dev, "suspending socket\n"); mutex_lock(&skt->skt_mutex); do { @@ -848,7 +849,7 @@ int pcmcia_resume_card(struct pcmcia_socket *skt) { int ret; - cs_dbg(skt, 1, "waking up socket\n"); + dev_dbg(&skt->dev, "waking up socket\n"); mutex_lock(&skt->skt_mutex); do { @@ -876,7 +877,7 @@ int pcmcia_eject_card(struct pcmcia_socket *skt) { int ret; - cs_dbg(skt, 1, "user eject request\n"); + dev_dbg(&skt->dev, "user eject request\n"); mutex_lock(&skt->skt_mutex); do { @@ -905,7 +906,7 @@ int pcmcia_insert_card(struct pcmcia_socket *skt) { int ret; - cs_dbg(skt, 1, "user insert request\n"); + dev_dbg(&skt->dev, "user insert request\n"); mutex_lock(&skt->skt_mutex); do { diff --git a/drivers/pcmcia/cs_internal.h b/drivers/pcmcia/cs_internal.h index 1f4098f1354d..3bc02d53a3a3 100644 --- a/drivers/pcmcia/cs_internal.h +++ b/drivers/pcmcia/cs_internal.h @@ -107,28 +107,6 @@ static inline void cs_socket_put(struct pcmcia_socket *skt) } } -#ifdef CONFIG_PCMCIA_DEBUG -extern int cs_debug_level(int); - -#define cs_dbg(skt, lvl, fmt, arg...) do { \ - if (cs_debug_level(lvl)) \ - dev_printk(KERN_DEBUG, &skt->dev, \ - "cs: " fmt, ## arg); \ -} while (0) -#define __cs_dbg(lvl, fmt, arg...) do { \ - if (cs_debug_level(lvl)) \ - printk(KERN_DEBUG \ - "cs: " fmt, ## arg); \ -} while (0) - -#else -#define cs_dbg(skt, lvl, fmt, arg...) do { } while (0) -#define __cs_dbg(lvl, fmt, arg...) do { } while (0) -#endif - -#define cs_err(skt, fmt, arg...) \ - dev_printk(KERN_ERR, &skt->dev, "cs: " fmt, ## arg) - /* * Stuff internal to module "pcmcia_core": @@ -170,10 +148,6 @@ extern struct rw_semaphore pcmcia_socket_list_rwsem; extern struct list_head pcmcia_socket_list; extern struct class pcmcia_socket_class; -int pcmcia_get_window(struct pcmcia_socket *s, - window_handle_t *handle, - int idx, - win_req_t *req); int pccard_register_pcmcia(struct pcmcia_socket *s, struct pcmcia_callback *c); struct pcmcia_socket *pcmcia_get_socket_by_nr(unsigned int nr); @@ -199,6 +173,22 @@ int pcmcia_replace_cis(struct pcmcia_socket *s, const u8 *data, const size_t len); int pccard_validate_cis(struct pcmcia_socket *s, unsigned int *count); +/* loop over CIS entries */ +int pccard_loop_tuple(struct pcmcia_socket *s, unsigned int function, + cisdata_t code, cisparse_t *parse, void *priv_data, + int (*loop_tuple) (tuple_t *tuple, + cisparse_t *parse, + void *priv_data)); + +int pccard_get_first_tuple(struct pcmcia_socket *s, unsigned int function, + tuple_t *tuple); + +int pccard_get_next_tuple(struct pcmcia_socket *s, unsigned int function, + tuple_t *tuple); + +int pccard_get_tuple_data(struct pcmcia_socket *s, tuple_t *tuple); + + /* rsrc_mgr.c */ int pcmcia_validate_mem(struct pcmcia_socket *s); struct resource *pcmcia_find_io_region(unsigned long base, diff --git a/drivers/pcmcia/ds.c b/drivers/pcmcia/ds.c index f5b7079f13d3..05893d41dd41 100644 --- a/drivers/pcmcia/ds.c +++ b/drivers/pcmcia/ds.c @@ -41,129 +41,11 @@ MODULE_AUTHOR("David Hinds <dahinds@users.sourceforge.net>"); MODULE_DESCRIPTION("PCMCIA Driver Services"); MODULE_LICENSE("GPL"); -#ifdef CONFIG_PCMCIA_DEBUG -int ds_pc_debug; - -module_param_named(pc_debug, ds_pc_debug, int, 0644); - -#define ds_dbg(lvl, fmt, arg...) do { \ - if (ds_pc_debug > (lvl)) \ - printk(KERN_DEBUG "ds: " fmt , ## arg); \ -} while (0) -#define ds_dev_dbg(lvl, dev, fmt, arg...) do { \ - if (ds_pc_debug > (lvl)) \ - dev_printk(KERN_DEBUG, dev, "ds: " fmt , ## arg); \ -} while (0) -#else -#define ds_dbg(lvl, fmt, arg...) do { } while (0) -#define ds_dev_dbg(lvl, dev, fmt, arg...) do { } while (0) -#endif spinlock_t pcmcia_dev_list_lock; /*====================================================================*/ -/* code which was in cs.c before */ - -/* String tables for error messages */ - -typedef struct lookup_t { - const int key; - const char *msg; -} lookup_t; - -static const lookup_t error_table[] = { - { 0, "Operation succeeded" }, - { -EIO, "Input/Output error" }, - { -ENODEV, "No card present" }, - { -EINVAL, "Bad parameter" }, - { -EACCES, "Configuration locked" }, - { -EBUSY, "Resource in use" }, - { -ENOSPC, "No more items" }, - { -ENOMEM, "Out of resource" }, -}; - - -static const lookup_t service_table[] = { - { AccessConfigurationRegister, "AccessConfigurationRegister" }, - { AddSocketServices, "AddSocketServices" }, - { AdjustResourceInfo, "AdjustResourceInfo" }, - { CheckEraseQueue, "CheckEraseQueue" }, - { CloseMemory, "CloseMemory" }, - { DeregisterClient, "DeregisterClient" }, - { DeregisterEraseQueue, "DeregisterEraseQueue" }, - { GetCardServicesInfo, "GetCardServicesInfo" }, - { GetClientInfo, "GetClientInfo" }, - { GetConfigurationInfo, "GetConfigurationInfo" }, - { GetEventMask, "GetEventMask" }, - { GetFirstClient, "GetFirstClient" }, - { GetFirstRegion, "GetFirstRegion" }, - { GetFirstTuple, "GetFirstTuple" }, - { GetNextClient, "GetNextClient" }, - { GetNextRegion, "GetNextRegion" }, - { GetNextTuple, "GetNextTuple" }, - { GetStatus, "GetStatus" }, - { GetTupleData, "GetTupleData" }, - { MapMemPage, "MapMemPage" }, - { ModifyConfiguration, "ModifyConfiguration" }, - { ModifyWindow, "ModifyWindow" }, - { OpenMemory, "OpenMemory" }, - { ParseTuple, "ParseTuple" }, - { ReadMemory, "ReadMemory" }, - { RegisterClient, "RegisterClient" }, - { RegisterEraseQueue, "RegisterEraseQueue" }, - { RegisterMTD, "RegisterMTD" }, - { ReleaseConfiguration, "ReleaseConfiguration" }, - { ReleaseIO, "ReleaseIO" }, - { ReleaseIRQ, "ReleaseIRQ" }, - { ReleaseWindow, "ReleaseWindow" }, - { RequestConfiguration, "RequestConfiguration" }, - { RequestIO, "RequestIO" }, - { RequestIRQ, "RequestIRQ" }, - { RequestSocketMask, "RequestSocketMask" }, - { RequestWindow, "RequestWindow" }, - { ResetCard, "ResetCard" }, - { SetEventMask, "SetEventMask" }, - { ValidateCIS, "ValidateCIS" }, - { WriteMemory, "WriteMemory" }, - { BindDevice, "BindDevice" }, - { BindMTD, "BindMTD" }, - { ReportError, "ReportError" }, - { SuspendCard, "SuspendCard" }, - { ResumeCard, "ResumeCard" }, - { EjectCard, "EjectCard" }, - { InsertCard, "InsertCard" }, - { ReplaceCIS, "ReplaceCIS" } -}; - -const char *pcmcia_error_func(int func) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(service_table); i++) - if (service_table[i].key == func) - return service_table[i].msg; - - return "Unknown service number"; -} -EXPORT_SYMBOL(pcmcia_error_func); - -const char *pcmcia_error_ret(int ret) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(error_table); i++) - if (error_table[i].key == ret) - return error_table[i].msg; - - return "unknown"; -} -EXPORT_SYMBOL(pcmcia_error_ret); - -/*======================================================================*/ - - - static void pcmcia_check_driver(struct pcmcia_driver *p_drv) { struct pcmcia_device_id *did = p_drv->id_table; @@ -303,7 +185,7 @@ int pcmcia_register_driver(struct pcmcia_driver *driver) spin_lock_init(&driver->dynids.lock); INIT_LIST_HEAD(&driver->dynids.list); - ds_dbg(3, "registering driver %s\n", driver->drv.name); + pr_debug("registering driver %s\n", driver->drv.name); error = driver_register(&driver->drv); if (error < 0) @@ -323,7 +205,7 @@ EXPORT_SYMBOL(pcmcia_register_driver); */ void pcmcia_unregister_driver(struct pcmcia_driver *driver) { - ds_dbg(3, "unregistering driver %s\n", driver->drv.name); + pr_debug("unregistering driver %s\n", driver->drv.name); driver_unregister(&driver->drv); pcmcia_free_dynids(driver); } @@ -350,14 +232,14 @@ void pcmcia_put_dev(struct pcmcia_device *p_dev) static void pcmcia_release_function(struct kref *ref) { struct config_t *c = container_of(ref, struct config_t, ref); - ds_dbg(1, "releasing config_t\n"); + pr_debug("releasing config_t\n"); kfree(c); } static void pcmcia_release_dev(struct device *dev) { struct pcmcia_device *p_dev = to_pcmcia_dev(dev); - ds_dev_dbg(1, dev, "releasing device\n"); + dev_dbg(dev, "releasing device\n"); pcmcia_put_socket(p_dev->socket); kfree(p_dev->devname); kref_put(&p_dev->function_config->ref, pcmcia_release_function); @@ -367,7 +249,7 @@ static void pcmcia_release_dev(struct device *dev) static void pcmcia_add_device_later(struct pcmcia_socket *s, int mfc) { if (!s->pcmcia_state.device_add_pending) { - ds_dev_dbg(1, &s->dev, "scheduling to add %s secondary" + dev_dbg(&s->dev, "scheduling to add %s secondary" " device to %d\n", mfc ? "mfc" : "pfc", s->sock); s->pcmcia_state.device_add_pending = 1; s->pcmcia_state.mfc_pfc = mfc; @@ -405,7 +287,7 @@ static int pcmcia_device_probe(struct device * dev) */ did = dev_get_drvdata(&p_dev->dev); - ds_dev_dbg(1, dev, "trying to bind to %s\n", p_drv->drv.name); + dev_dbg(dev, "trying to bind to %s\n", p_drv->drv.name); if ((!p_drv->probe) || (!p_dev->function_config) || (!try_module_get(p_drv->owner))) { @@ -428,7 +310,7 @@ static int pcmcia_device_probe(struct device * dev) ret = p_drv->probe(p_dev); if (ret) { - ds_dev_dbg(1, dev, "binding to %s failed with %d\n", + dev_dbg(dev, "binding to %s failed with %d\n", p_drv->drv.name, ret); goto put_module; } @@ -456,7 +338,7 @@ static void pcmcia_card_remove(struct pcmcia_socket *s, struct pcmcia_device *le struct pcmcia_device *tmp; unsigned long flags; - ds_dev_dbg(2, leftover ? &leftover->dev : &s->dev, + dev_dbg(leftover ? &leftover->dev : &s->dev, "pcmcia_card_remove(%d) %s\n", s->sock, leftover ? leftover->devname : ""); @@ -475,7 +357,7 @@ static void pcmcia_card_remove(struct pcmcia_socket *s, struct pcmcia_device *le p_dev->_removed=1; spin_unlock_irqrestore(&pcmcia_dev_list_lock, flags); - ds_dev_dbg(2, &p_dev->dev, "unregistering device\n"); + dev_dbg(&p_dev->dev, "unregistering device\n"); device_unregister(&p_dev->dev); } @@ -492,7 +374,7 @@ static int pcmcia_device_remove(struct device * dev) p_dev = to_pcmcia_dev(dev); p_drv = to_pcmcia_drv(dev->driver); - ds_dev_dbg(1, dev, "removing device\n"); + dev_dbg(dev, "removing device\n"); /* If we're removing the primary module driving a * pseudo multi-function card, we need to unbind @@ -572,7 +454,7 @@ static int pcmcia_device_query(struct pcmcia_device *p_dev) } if (!pccard_read_tuple(p_dev->socket, p_dev->func, CISTPL_DEVICE_GEO, devgeo)) { - ds_dev_dbg(0, &p_dev->dev, + dev_dbg(&p_dev->dev, "mem device geometry probably means " "FUNCID_MEMORY\n"); p_dev->func_id = CISTPL_FUNCID_MEMORY; @@ -628,7 +510,7 @@ struct pcmcia_device * pcmcia_device_add(struct pcmcia_socket *s, unsigned int f mutex_lock(&device_add_lock); - ds_dbg(3, "adding device to %d, function %d\n", s->sock, function); + pr_debug("adding device to %d, function %d\n", s->sock, function); /* max of 4 devices per card */ if (s->device_count == 4) @@ -654,7 +536,7 @@ struct pcmcia_device * pcmcia_device_add(struct pcmcia_socket *s, unsigned int f p_dev->devname = kasprintf(GFP_KERNEL, "pcmcia%s", dev_name(&p_dev->dev)); if (!p_dev->devname) goto err_free; - ds_dev_dbg(3, &p_dev->dev, "devname is %s\n", p_dev->devname); + dev_dbg(&p_dev->dev, "devname is %s\n", p_dev->devname); spin_lock_irqsave(&pcmcia_dev_list_lock, flags); @@ -677,7 +559,7 @@ struct pcmcia_device * pcmcia_device_add(struct pcmcia_socket *s, unsigned int f spin_unlock_irqrestore(&pcmcia_dev_list_lock, flags); if (!p_dev->function_config) { - ds_dev_dbg(3, &p_dev->dev, "creating config_t\n"); + dev_dbg(&p_dev->dev, "creating config_t\n"); p_dev->function_config = kzalloc(sizeof(struct config_t), GFP_KERNEL); if (!p_dev->function_config) @@ -722,20 +604,20 @@ static int pcmcia_card_add(struct pcmcia_socket *s) int ret = 0; if (!(s->resource_setup_done)) { - ds_dev_dbg(3, &s->dev, + dev_dbg(&s->dev, "no resources available, delaying card_add\n"); return -EAGAIN; /* try again, but later... */ } if (pcmcia_validate_mem(s)) { - ds_dev_dbg(3, &s->dev, "validating mem resources failed, " + dev_dbg(&s->dev, "validating mem resources failed, " "delaying card_add\n"); return -EAGAIN; /* try again, but later... */ } ret = pccard_validate_cis(s, &no_chains); if (ret || !no_chains) { - ds_dev_dbg(0, &s->dev, "invalid CIS or invalid resources\n"); + dev_dbg(&s->dev, "invalid CIS or invalid resources\n"); return -ENODEV; } @@ -756,7 +638,7 @@ static void pcmcia_delayed_add_device(struct work_struct *work) { struct pcmcia_socket *s = container_of(work, struct pcmcia_socket, device_add); - ds_dev_dbg(1, &s->dev, "adding additional device to %d\n", s->sock); + dev_dbg(&s->dev, "adding additional device to %d\n", s->sock); pcmcia_device_add(s, s->pcmcia_state.mfc_pfc); s->pcmcia_state.device_add_pending = 0; s->pcmcia_state.mfc_pfc = 0; @@ -766,7 +648,7 @@ static int pcmcia_requery(struct device *dev, void * _data) { struct pcmcia_device *p_dev = to_pcmcia_dev(dev); if (!p_dev->dev.driver) { - ds_dev_dbg(1, dev, "update device information\n"); + dev_dbg(dev, "update device information\n"); pcmcia_device_query(p_dev); } @@ -780,7 +662,7 @@ static void pcmcia_bus_rescan(struct pcmcia_socket *skt, int new_cis) unsigned long flags; /* must be called with skt_mutex held */ - ds_dev_dbg(0, &skt->dev, "re-scanning socket %d\n", skt->sock); + dev_dbg(&skt->dev, "re-scanning socket %d\n", skt->sock); spin_lock_irqsave(&pcmcia_dev_list_lock, flags); if (list_empty(&skt->devices_list)) @@ -835,7 +717,7 @@ static int pcmcia_load_firmware(struct pcmcia_device *dev, char * filename) if (!filename) return -EINVAL; - ds_dev_dbg(1, &dev->dev, "trying to load CIS file %s\n", filename); + dev_dbg(&dev->dev, "trying to load CIS file %s\n", filename); if (request_firmware(&fw, filename, &dev->dev) == 0) { if (fw->size >= CISTPL_MAX_CIS_SIZE) { @@ -953,14 +835,14 @@ static inline int pcmcia_devmatch(struct pcmcia_device *dev, * after it has re-checked that there is no possible module * with a prod_id/manf_id/card_id match. */ - ds_dev_dbg(0, &dev->dev, + dev_dbg(&dev->dev, "skipping FUNC_ID match until userspace interaction\n"); if (!dev->allow_func_id_match) return 0; } if (did->match_flags & PCMCIA_DEV_ID_MATCH_FAKE_CIS) { - ds_dev_dbg(0, &dev->dev, "device needs a fake CIS\n"); + dev_dbg(&dev->dev, "device needs a fake CIS\n"); if (!dev->socket->fake_cis) pcmcia_load_firmware(dev, did->cisfile); @@ -992,9 +874,9 @@ static int pcmcia_bus_match(struct device * dev, struct device_driver * drv) { /* match dynamic devices first */ spin_lock(&p_drv->dynids.lock); list_for_each_entry(dynid, &p_drv->dynids.list, node) { - ds_dev_dbg(3, dev, "trying to match to %s\n", drv->name); + dev_dbg(dev, "trying to match to %s\n", drv->name); if (pcmcia_devmatch(p_dev, &dynid->id)) { - ds_dev_dbg(0, dev, "matched to %s\n", drv->name); + dev_dbg(dev, "matched to %s\n", drv->name); spin_unlock(&p_drv->dynids.lock); return 1; } @@ -1004,15 +886,15 @@ static int pcmcia_bus_match(struct device * dev, struct device_driver * drv) { #ifdef CONFIG_PCMCIA_IOCTL /* matching by cardmgr */ if (p_dev->cardmgr == p_drv) { - ds_dev_dbg(0, dev, "cardmgr matched to %s\n", drv->name); + dev_dbg(dev, "cardmgr matched to %s\n", drv->name); return 1; } #endif while (did && did->match_flags) { - ds_dev_dbg(3, dev, "trying to match to %s\n", drv->name); + dev_dbg(dev, "trying to match to %s\n", drv->name); if (pcmcia_devmatch(p_dev, did)) { - ds_dev_dbg(0, dev, "matched to %s\n", drv->name); + dev_dbg(dev, "matched to %s\n", drv->name); return 1; } did++; @@ -1218,7 +1100,7 @@ static int pcmcia_dev_suspend(struct device * dev, pm_message_t state) if (p_dev->suspended) return 0; - ds_dev_dbg(2, dev, "suspending\n"); + dev_dbg(dev, "suspending\n"); if (dev->driver) p_drv = to_pcmcia_drv(dev->driver); @@ -1238,7 +1120,7 @@ static int pcmcia_dev_suspend(struct device * dev, pm_message_t state) } if (p_dev->device_no == p_dev->func) { - ds_dev_dbg(2, dev, "releasing configuration\n"); + dev_dbg(dev, "releasing configuration\n"); pcmcia_release_configuration(p_dev); } @@ -1258,7 +1140,7 @@ static int pcmcia_dev_resume(struct device * dev) if (!p_dev->suspended) return 0; - ds_dev_dbg(2, dev, "resuming\n"); + dev_dbg(dev, "resuming\n"); if (dev->driver) p_drv = to_pcmcia_drv(dev->driver); @@ -1267,7 +1149,7 @@ static int pcmcia_dev_resume(struct device * dev) goto out; if (p_dev->device_no == p_dev->func) { - ds_dev_dbg(2, dev, "requesting configuration\n"); + dev_dbg(dev, "requesting configuration\n"); ret = pcmcia_request_configuration(p_dev, &p_dev->conf); if (ret) goto out; @@ -1309,14 +1191,14 @@ static int pcmcia_bus_resume_callback(struct device *dev, void * _data) static int pcmcia_bus_resume(struct pcmcia_socket *skt) { - ds_dev_dbg(2, &skt->dev, "resuming socket %d\n", skt->sock); + dev_dbg(&skt->dev, "resuming socket %d\n", skt->sock); bus_for_each_dev(&pcmcia_bus_type, NULL, skt, pcmcia_bus_resume_callback); return 0; } static int pcmcia_bus_suspend(struct pcmcia_socket *skt) { - ds_dev_dbg(2, &skt->dev, "suspending socket %d\n", skt->sock); + dev_dbg(&skt->dev, "suspending socket %d\n", skt->sock); if (bus_for_each_dev(&pcmcia_bus_type, NULL, skt, pcmcia_bus_suspend_callback)) { pcmcia_bus_resume(skt); @@ -1348,7 +1230,7 @@ static int ds_event(struct pcmcia_socket *skt, event_t event, int priority) return -ENODEV; } - ds_dev_dbg(1, &skt->dev, "ds_event(0x%06x, %d, 0x%p)\n", + dev_dbg(&skt->dev, "ds_event(0x%06x, %d, 0x%p)\n", event, priority, skt); switch (event) { diff --git a/drivers/pcmcia/i82365.c b/drivers/pcmcia/i82365.c index a4aacb830b80..c13fd9360511 100644 --- a/drivers/pcmcia/i82365.c +++ b/drivers/pcmcia/i82365.c @@ -63,21 +63,6 @@ #include "vg468.h" #include "ricoh.h" -#ifdef CONFIG_PCMCIA_DEBUG -static const char version[] = -"i82365.c 1.265 1999/11/10 18:36:21 (David Hinds)"; - -static int pc_debug; - -module_param(pc_debug, int, 0644); - -#define debug(lvl, fmt, arg...) do { \ - if (pc_debug > (lvl)) \ - printk(KERN_DEBUG "i82365: " fmt , ## arg); \ -} while (0) -#else -#define debug(lvl, fmt, arg...) do { } while (0) -#endif static irqreturn_t i365_count_irq(int, void *); static inline int _check_irq(int irq, int flags) @@ -501,13 +486,13 @@ static irqreturn_t i365_count_irq(int irq, void *dev) { i365_get(irq_sock, I365_CSC); irq_hits++; - debug(2, "-> hit on irq %d\n", irq); + pr_debug("i82365: -> hit on irq %d\n", irq); return IRQ_HANDLED; } static u_int __init test_irq(u_short sock, int irq) { - debug(2, " testing ISA irq %d\n", irq); + pr_debug("i82365: testing ISA irq %d\n", irq); if (request_irq(irq, i365_count_irq, IRQF_PROBE_SHARED, "scan", i365_count_irq) != 0) return 1; @@ -515,7 +500,7 @@ static u_int __init test_irq(u_short sock, int irq) msleep(10); if (irq_hits) { free_irq(irq, i365_count_irq); - debug(2, " spurious hit!\n"); + pr_debug("i82365: spurious hit!\n"); return 1; } @@ -528,7 +513,7 @@ static u_int __init test_irq(u_short sock, int irq) /* mask all interrupts */ i365_set(sock, I365_CSCINT, 0); - debug(2, " hits = %d\n", irq_hits); + pr_debug("i82365: hits = %d\n", irq_hits); return (irq_hits != 1); } @@ -854,7 +839,7 @@ static irqreturn_t pcic_interrupt(int irq, void *dev) u_long flags = 0; int handled = 0; - debug(4, "pcic_interrupt(%d)\n", irq); + pr_debug("pcic_interrupt(%d)\n", irq); for (j = 0; j < 20; j++) { active = 0; @@ -878,7 +863,7 @@ static irqreturn_t pcic_interrupt(int irq, void *dev) events |= (csc & I365_CSC_READY) ? SS_READY : 0; } ISA_UNLOCK(i, flags); - debug(2, "socket %d event 0x%02x\n", i, events); + pr_debug("socket %d event 0x%02x\n", i, events); if (events) pcmcia_parse_events(&socket[i].socket, events); @@ -890,7 +875,7 @@ static irqreturn_t pcic_interrupt(int irq, void *dev) if (j == 20) printk(KERN_NOTICE "i82365: infinite loop in interrupt handler\n"); - debug(4, "interrupt done\n"); + pr_debug("pcic_interrupt done\n"); return IRQ_RETVAL(handled); } /* pcic_interrupt */ @@ -932,7 +917,7 @@ static int i365_get_status(u_short sock, u_int *value) } } - debug(1, "GetStatus(%d) = %#4.4x\n", sock, *value); + pr_debug("GetStatus(%d) = %#4.4x\n", sock, *value); return 0; } /* i365_get_status */ @@ -943,7 +928,7 @@ static int i365_set_socket(u_short sock, socket_state_t *state) struct i82365_socket *t = &socket[sock]; u_char reg; - debug(1, "SetSocket(%d, flags %#3.3x, Vcc %d, Vpp %d, " + pr_debug("SetSocket(%d, flags %#3.3x, Vcc %d, Vpp %d, " "io_irq %d, csc_mask %#2.2x)\n", sock, state->flags, state->Vcc, state->Vpp, state->io_irq, state->csc_mask); @@ -1052,7 +1037,7 @@ static int i365_set_io_map(u_short sock, struct pccard_io_map *io) { u_char map, ioctl; - debug(1, "SetIOMap(%d, %d, %#2.2x, %d ns, " + pr_debug("SetIOMap(%d, %d, %#2.2x, %d ns, " "%#llx-%#llx)\n", sock, io->map, io->flags, io->speed, (unsigned long long)io->start, (unsigned long long)io->stop); map = io->map; @@ -1082,7 +1067,7 @@ static int i365_set_mem_map(u_short sock, struct pccard_mem_map *mem) u_short base, i; u_char map; - debug(1, "SetMemMap(%d, %d, %#2.2x, %d ns, %#llx-%#llx, " + pr_debug("SetMemMap(%d, %d, %#2.2x, %d ns, %#llx-%#llx, " "%#x)\n", sock, mem->map, mem->flags, mem->speed, (unsigned long long)mem->res->start, (unsigned long long)mem->res->end, mem->card_start); diff --git a/drivers/pcmcia/m32r_cfc.c b/drivers/pcmcia/m32r_cfc.c index 7dfbee1dcd76..26a621c9e2fc 100644 --- a/drivers/pcmcia/m32r_cfc.c +++ b/drivers/pcmcia/m32r_cfc.c @@ -38,17 +38,6 @@ #include "m32r_cfc.h" -#ifdef CONFIG_PCMCIA_DEBUG -static int m32r_cfc_debug; -module_param(m32r_cfc_debug, int, 0644); -#define debug(lvl, fmt, arg...) do { \ - if (m32r_cfc_debug > (lvl)) \ - printk(KERN_DEBUG "m32r_cfc: " fmt , ## arg); \ -} while (0) -#else -#define debug(n, args...) do { } while (0) -#endif - /* Poll status interval -- 0 means default to interrupt */ static int poll_interval = 0; @@ -123,7 +112,7 @@ void pcc_ioread_byte(int sock, unsigned long port, void *buf, size_t size, unsigned char *bp = (unsigned char *)buf; unsigned long flags; - debug(3, "m32r_cfc: pcc_ioread_byte: sock=%d, port=%#lx, buf=%p, " + pr_debug("m32r_cfc: pcc_ioread_byte: sock=%d, port=%#lx, buf=%p, " "size=%u, nmemb=%d, flag=%d\n", sock, port, buf, size, nmemb, flag); @@ -132,7 +121,7 @@ void pcc_ioread_byte(int sock, unsigned long port, void *buf, size_t size, printk("m32r_cfc:ioread_byte null port :%#lx\n",port); return; } - debug(3, "m32r_cfc: pcc_ioread_byte: addr=%#lx\n", addr); + pr_debug("m32r_cfc: pcc_ioread_byte: addr=%#lx\n", addr); spin_lock_irqsave(&pcc_lock, flags); /* read Byte */ @@ -148,7 +137,7 @@ void pcc_ioread_word(int sock, unsigned long port, void *buf, size_t size, unsigned short *bp = (unsigned short *)buf; unsigned long flags; - debug(3, "m32r_cfc: pcc_ioread_word: sock=%d, port=%#lx, " + pr_debug("m32r_cfc: pcc_ioread_word: sock=%d, port=%#lx, " "buf=%p, size=%u, nmemb=%d, flag=%d\n", sock, port, buf, size, nmemb, flag); @@ -163,7 +152,7 @@ void pcc_ioread_word(int sock, unsigned long port, void *buf, size_t size, printk("m32r_cfc:ioread_word null port :%#lx\n",port); return; } - debug(3, "m32r_cfc: pcc_ioread_word: addr=%#lx\n", addr); + pr_debug("m32r_cfc: pcc_ioread_word: addr=%#lx\n", addr); spin_lock_irqsave(&pcc_lock, flags); /* read Word */ @@ -179,7 +168,7 @@ void pcc_iowrite_byte(int sock, unsigned long port, void *buf, size_t size, unsigned char *bp = (unsigned char *)buf; unsigned long flags; - debug(3, "m32r_cfc: pcc_iowrite_byte: sock=%d, port=%#lx, " + pr_debug("m32r_cfc: pcc_iowrite_byte: sock=%d, port=%#lx, " "buf=%p, size=%u, nmemb=%d, flag=%d\n", sock, port, buf, size, nmemb, flag); @@ -189,7 +178,7 @@ void pcc_iowrite_byte(int sock, unsigned long port, void *buf, size_t size, printk("m32r_cfc:iowrite_byte null port:%#lx\n",port); return; } - debug(3, "m32r_cfc: pcc_iowrite_byte: addr=%#lx\n", addr); + pr_debug("m32r_cfc: pcc_iowrite_byte: addr=%#lx\n", addr); spin_lock_irqsave(&pcc_lock, flags); while (nmemb--) @@ -204,7 +193,7 @@ void pcc_iowrite_word(int sock, unsigned long port, void *buf, size_t size, unsigned short *bp = (unsigned short *)buf; unsigned long flags; - debug(3, "m32r_cfc: pcc_iowrite_word: sock=%d, port=%#lx, " + pr_debug("m32r_cfc: pcc_iowrite_word: sock=%d, port=%#lx, " "buf=%p, size=%u, nmemb=%d, flag=%d\n", sock, port, buf, size, nmemb, flag); @@ -226,7 +215,7 @@ void pcc_iowrite_word(int sock, unsigned long port, void *buf, size_t size, return; } #endif - debug(3, "m32r_cfc: pcc_iowrite_word: addr=%#lx\n", addr); + pr_debug("m32r_cfc: pcc_iowrite_word: addr=%#lx\n", addr); spin_lock_irqsave(&pcc_lock, flags); while (nmemb--) @@ -262,7 +251,7 @@ static struct timer_list poll_timer; static unsigned int pcc_get(u_short sock, unsigned int reg) { unsigned int val = inw(reg); - debug(3, "m32r_cfc: pcc_get: reg(0x%08x)=0x%04x\n", reg, val); + pr_debug("m32r_cfc: pcc_get: reg(0x%08x)=0x%04x\n", reg, val); return val; } @@ -270,7 +259,7 @@ static unsigned int pcc_get(u_short sock, unsigned int reg) static void pcc_set(u_short sock, unsigned int reg, unsigned int data) { outw(data, reg); - debug(3, "m32r_cfc: pcc_set: reg(0x%08x)=0x%04x\n", reg, data); + pr_debug("m32r_cfc: pcc_set: reg(0x%08x)=0x%04x\n", reg, data); } /*====================================================================== @@ -286,14 +275,14 @@ static int __init is_alive(u_short sock) { unsigned int stat; - debug(3, "m32r_cfc: is_alive:\n"); + pr_debug("m32r_cfc: is_alive:\n"); printk("CF: "); stat = pcc_get(sock, (unsigned int)PLD_CFSTS); if (!stat) printk("No "); printk("Card is detected at socket %d : stat = 0x%08x\n", sock, stat); - debug(3, "m32r_cfc: is_alive: sock stat is 0x%04x\n", stat); + pr_debug("m32r_cfc: is_alive: sock stat is 0x%04x\n", stat); return 0; } @@ -303,7 +292,7 @@ static void add_pcc_socket(ulong base, int irq, ulong mapaddr, { pcc_socket_t *t = &socket[pcc_sockets]; - debug(3, "m32r_cfc: add_pcc_socket: base=%#lx, irq=%d, " + pr_debug("m32r_cfc: add_pcc_socket: base=%#lx, irq=%d, " "mapaddr=%#lx, ioaddr=%08x\n", base, irq, mapaddr, ioaddr); @@ -358,7 +347,7 @@ static void add_pcc_socket(ulong base, int irq, ulong mapaddr, /* eject interrupt */ request_irq(irq+1, pcc_interrupt, 0, "m32r_cfc", pcc_interrupt); #endif - debug(3, "m32r_cfc: enable CFMSK, RDYSEL\n"); + pr_debug("m32r_cfc: enable CFMSK, RDYSEL\n"); pcc_set(pcc_sockets, (unsigned int)PLD_CFIMASK, 0x01); #endif /* CONFIG_PLAT_USRV */ #if defined(CONFIG_PLAT_M32700UT) || defined(CONFIG_PLAT_USRV) || defined(CONFIG_PLAT_OPSPUT) @@ -378,26 +367,26 @@ static irqreturn_t pcc_interrupt(int irq, void *dev) u_int events = 0; int handled = 0; - debug(3, "m32r_cfc: pcc_interrupt: irq=%d, dev=%p\n", irq, dev); + pr_debug("m32r_cfc: pcc_interrupt: irq=%d, dev=%p\n", irq, dev); for (i = 0; i < pcc_sockets; i++) { if (socket[i].cs_irq1 != irq && socket[i].cs_irq2 != irq) continue; handled = 1; - debug(3, "m32r_cfc: pcc_interrupt: socket %d irq 0x%02x ", + pr_debug("m32r_cfc: pcc_interrupt: socket %d irq 0x%02x ", i, irq); events |= SS_DETECT; /* insert or eject */ if (events) pcmcia_parse_events(&socket[i].socket, events); } - debug(3, "m32r_cfc: pcc_interrupt: done\n"); + pr_debug("m32r_cfc: pcc_interrupt: done\n"); return IRQ_RETVAL(handled); } /* pcc_interrupt */ static void pcc_interrupt_wrapper(u_long data) { - debug(3, "m32r_cfc: pcc_interrupt_wrapper:\n"); + pr_debug("m32r_cfc: pcc_interrupt_wrapper:\n"); pcc_interrupt(0, NULL); init_timer(&poll_timer); poll_timer.expires = jiffies + poll_interval; @@ -410,17 +399,17 @@ static int _pcc_get_status(u_short sock, u_int *value) { u_int status; - debug(3, "m32r_cfc: _pcc_get_status:\n"); + pr_debug("m32r_cfc: _pcc_get_status:\n"); status = pcc_get(sock, (unsigned int)PLD_CFSTS); *value = (status) ? SS_DETECT : 0; - debug(3, "m32r_cfc: _pcc_get_status: status=0x%08x\n", status); + pr_debug("m32r_cfc: _pcc_get_status: status=0x%08x\n", status); #if defined(CONFIG_PLAT_M32700UT) || defined(CONFIG_PLAT_USRV) || defined(CONFIG_PLAT_OPSPUT) if ( status ) { /* enable CF power */ status = inw((unsigned int)PLD_CPCR); if (!(status & PLD_CPCR_CF)) { - debug(3, "m32r_cfc: _pcc_get_status: " + pr_debug("m32r_cfc: _pcc_get_status: " "power on (CPCR=0x%08x)\n", status); status |= PLD_CPCR_CF; outw(status, (unsigned int)PLD_CPCR); @@ -439,7 +428,7 @@ static int _pcc_get_status(u_short sock, u_int *value) status &= ~PLD_CPCR_CF; outw(status, (unsigned int)PLD_CPCR); udelay(100); - debug(3, "m32r_cfc: _pcc_get_status: " + pr_debug("m32r_cfc: _pcc_get_status: " "power off (CPCR=0x%08x)\n", status); } #elif defined(CONFIG_PLAT_MAPPI2) || defined(CONFIG_PLAT_MAPPI3) @@ -465,13 +454,13 @@ static int _pcc_get_status(u_short sock, u_int *value) /* disable CF power */ pcc_set(sock, (unsigned int)PLD_CPCR, 0); udelay(100); - debug(3, "m32r_cfc: _pcc_get_status: " + pr_debug("m32r_cfc: _pcc_get_status: " "power off (CPCR=0x%08x)\n", status); } #else #error no platform configuration #endif - debug(3, "m32r_cfc: _pcc_get_status: GetStatus(%d) = %#4.4x\n", + pr_debug("m32r_cfc: _pcc_get_status: GetStatus(%d) = %#4.4x\n", sock, *value); return 0; } /* _get_status */ @@ -480,7 +469,7 @@ static int _pcc_get_status(u_short sock, u_int *value) static int _pcc_set_socket(u_short sock, socket_state_t *state) { - debug(3, "m32r_cfc: SetSocket(%d, flags %#3.3x, Vcc %d, Vpp %d, " + pr_debug("m32r_cfc: SetSocket(%d, flags %#3.3x, Vcc %d, Vpp %d, " "io_irq %d, csc_mask %#2.2x)\n", sock, state->flags, state->Vcc, state->Vpp, state->io_irq, state->csc_mask); @@ -492,41 +481,39 @@ static int _pcc_set_socket(u_short sock, socket_state_t *state) } #endif if (state->flags & SS_RESET) { - debug(3, ":RESET\n"); + pr_debug(":RESET\n"); pcc_set(sock,(unsigned int)PLD_CFRSTCR,0x101); }else{ pcc_set(sock,(unsigned int)PLD_CFRSTCR,0x100); } if (state->flags & SS_OUTPUT_ENA){ - debug(3, ":OUTPUT_ENA\n"); + pr_debug(":OUTPUT_ENA\n"); /* bit clear */ pcc_set(sock,(unsigned int)PLD_CFBUFCR,0); } else { pcc_set(sock,(unsigned int)PLD_CFBUFCR,1); } -#ifdef CONFIG_PCMCIA_DEBUG if(state->flags & SS_IOCARD){ - debug(3, ":IOCARD"); + pr_debug(":IOCARD"); } if (state->flags & SS_PWR_AUTO) { - debug(3, ":PWR_AUTO"); + pr_debug(":PWR_AUTO"); } if (state->csc_mask & SS_DETECT) - debug(3, ":csc-SS_DETECT"); + pr_debug(":csc-SS_DETECT"); if (state->flags & SS_IOCARD) { if (state->csc_mask & SS_STSCHG) - debug(3, ":STSCHG"); + pr_debug(":STSCHG"); } else { if (state->csc_mask & SS_BATDEAD) - debug(3, ":BATDEAD"); + pr_debug(":BATDEAD"); if (state->csc_mask & SS_BATWARN) - debug(3, ":BATWARN"); + pr_debug(":BATWARN"); if (state->csc_mask & SS_READY) - debug(3, ":READY"); + pr_debug(":READY"); } - debug(3, "\n"); -#endif + pr_debug("\n"); return 0; } /* _set_socket */ @@ -536,7 +523,7 @@ static int _pcc_set_io_map(u_short sock, struct pccard_io_map *io) { u_char map; - debug(3, "m32r_cfc: SetIOMap(%d, %d, %#2.2x, %d ns, " + pr_debug("m32r_cfc: SetIOMap(%d, %d, %#2.2x, %d ns, " "%#llx-%#llx)\n", sock, io->map, io->flags, io->speed, (unsigned long long)io->start, (unsigned long long)io->stop); @@ -554,7 +541,7 @@ static int _pcc_set_mem_map(u_short sock, struct pccard_mem_map *mem) u_long addr; pcc_socket_t *t = &socket[sock]; - debug(3, "m32r_cfc: SetMemMap(%d, %d, %#2.2x, %d ns, " + pr_debug("m32r_cfc: SetMemMap(%d, %d, %#2.2x, %d ns, " "%#llx, %#x)\n", sock, map, mem->flags, mem->speed, (unsigned long long)mem->static_start, mem->card_start); @@ -640,11 +627,11 @@ static int pcc_get_status(struct pcmcia_socket *s, u_int *value) unsigned int sock = container_of(s, struct pcc_socket, socket)->number; if (socket[sock].flags & IS_ALIVE) { - debug(3, "m32r_cfc: pcc_get_status: sock(%d) -EINVAL\n", sock); + dev_dbg(&s->dev, "pcc_get_status: sock(%d) -EINVAL\n", sock); *value = 0; return -EINVAL; } - debug(3, "m32r_cfc: pcc_get_status: sock(%d)\n", sock); + dev_dbg(&s->dev, "pcc_get_status: sock(%d)\n", sock); LOCKED(_pcc_get_status(sock, value)); } @@ -653,10 +640,10 @@ static int pcc_set_socket(struct pcmcia_socket *s, socket_state_t *state) unsigned int sock = container_of(s, struct pcc_socket, socket)->number; if (socket[sock].flags & IS_ALIVE) { - debug(3, "m32r_cfc: pcc_set_socket: sock(%d) -EINVAL\n", sock); + dev_dbg(&s->dev, "pcc_set_socket: sock(%d) -EINVAL\n", sock); return -EINVAL; } - debug(3, "m32r_cfc: pcc_set_socket: sock(%d)\n", sock); + dev_dbg(&s->dev, "pcc_set_socket: sock(%d)\n", sock); LOCKED(_pcc_set_socket(sock, state)); } @@ -665,10 +652,10 @@ static int pcc_set_io_map(struct pcmcia_socket *s, struct pccard_io_map *io) unsigned int sock = container_of(s, struct pcc_socket, socket)->number; if (socket[sock].flags & IS_ALIVE) { - debug(3, "m32r_cfc: pcc_set_io_map: sock(%d) -EINVAL\n", sock); + dev_dbg(&s->dev, "pcc_set_io_map: sock(%d) -EINVAL\n", sock); return -EINVAL; } - debug(3, "m32r_cfc: pcc_set_io_map: sock(%d)\n", sock); + dev_dbg(&s->dev, "pcc_set_io_map: sock(%d)\n", sock); LOCKED(_pcc_set_io_map(sock, io)); } @@ -677,16 +664,16 @@ static int pcc_set_mem_map(struct pcmcia_socket *s, struct pccard_mem_map *mem) unsigned int sock = container_of(s, struct pcc_socket, socket)->number; if (socket[sock].flags & IS_ALIVE) { - debug(3, "m32r_cfc: pcc_set_mem_map: sock(%d) -EINVAL\n", sock); + dev_dbg(&s->dev, "pcc_set_mem_map: sock(%d) -EINVAL\n", sock); return -EINVAL; } - debug(3, "m32r_cfc: pcc_set_mem_map: sock(%d)\n", sock); + dev_dbg(&s->dev, "pcc_set_mem_map: sock(%d)\n", sock); LOCKED(_pcc_set_mem_map(sock, mem)); } static int pcc_init(struct pcmcia_socket *s) { - debug(3, "m32r_cfc: pcc_init()\n"); + dev_dbg(&s->dev, "pcc_init()\n"); return 0; } diff --git a/drivers/pcmcia/m32r_pcc.c b/drivers/pcmcia/m32r_pcc.c index c6524f99ccc3..72844c5a6d05 100644 --- a/drivers/pcmcia/m32r_pcc.c +++ b/drivers/pcmcia/m32r_pcc.c @@ -45,16 +45,6 @@ #define PCC_DEBUG_DBEX -#ifdef CONFIG_PCMCIA_DEBUG -static int m32r_pcc_debug; -module_param(m32r_pcc_debug, int, 0644); -#define debug(lvl, fmt, arg...) do { \ - if (m32r_pcc_debug > (lvl)) \ - printk(KERN_DEBUG "m32r_pcc: " fmt , ## arg); \ -} while (0) -#else -#define debug(n, args...) do { } while (0) -#endif /* Poll status interval -- 0 means default to interrupt */ static int poll_interval = 0; @@ -358,7 +348,7 @@ static irqreturn_t pcc_interrupt(int irq, void *dev) u_int events, active; int handled = 0; - debug(4, "m32r: pcc_interrupt(%d)\n", irq); + pr_debug("m32r_pcc: pcc_interrupt(%d)\n", irq); for (j = 0; j < 20; j++) { active = 0; @@ -369,13 +359,14 @@ static irqreturn_t pcc_interrupt(int irq, void *dev) handled = 1; irc = pcc_get(i, PCIRC); irc >>=16; - debug(2, "m32r-pcc:interrupt: socket %d pcirc 0x%02x ", i, irc); + pr_debug("m32r_pcc: interrupt: socket %d pcirc 0x%02x ", + i, irc); if (!irc) continue; events = (irc) ? SS_DETECT : 0; events |= (pcc_get(i,PCCR) & PCCR_PCEN) ? SS_READY : 0; - debug(2, " event 0x%02x\n", events); + pr_debug("m32r_pcc: event 0x%02x\n", events); if (events) pcmcia_parse_events(&socket[i].socket, events); @@ -388,7 +379,7 @@ static irqreturn_t pcc_interrupt(int irq, void *dev) if (j == 20) printk(KERN_NOTICE "m32r-pcc: infinite loop in interrupt handler\n"); - debug(4, "m32r-pcc: interrupt done\n"); + pr_debug("m32r_pcc: interrupt done\n"); return IRQ_RETVAL(handled); } /* pcc_interrupt */ @@ -422,7 +413,7 @@ static int _pcc_get_status(u_short sock, u_int *value) status = pcc_get(sock,PCCSIGCR); *value |= (status & PCCSIGCR_VEN) ? SS_POWERON : 0; - debug(3, "m32r-pcc: GetStatus(%d) = %#4.4x\n", sock, *value); + pr_debug("m32r_pcc: GetStatus(%d) = %#4.4x\n", sock, *value); return 0; } /* _get_status */ @@ -432,7 +423,7 @@ static int _pcc_set_socket(u_short sock, socket_state_t *state) { u_long reg = 0; - debug(3, "m32r-pcc: SetSocket(%d, flags %#3.3x, Vcc %d, Vpp %d, " + pr_debug("m32r_pcc: SetSocket(%d, flags %#3.3x, Vcc %d, Vpp %d, " "io_irq %d, csc_mask %#2.2x)", sock, state->flags, state->Vcc, state->Vpp, state->io_irq, state->csc_mask); @@ -448,11 +439,11 @@ static int _pcc_set_socket(u_short sock, socket_state_t *state) } if (state->flags & SS_RESET) { - debug(3, ":RESET\n"); + pr_debug("m32r_pcc: :RESET\n"); reg |= PCCSIGCR_CRST; } if (state->flags & SS_OUTPUT_ENA){ - debug(3, ":OUTPUT_ENA\n"); + pr_debug("m32r_pcc: :OUTPUT_ENA\n"); /* bit clear */ } else { reg |= PCCSIGCR_SEN; @@ -460,28 +451,26 @@ static int _pcc_set_socket(u_short sock, socket_state_t *state) pcc_set(sock,PCCSIGCR,reg); -#ifdef CONFIG_PCMCIA_DEBUG if(state->flags & SS_IOCARD){ - debug(3, ":IOCARD"); + pr_debug("m32r_pcc: :IOCARD"); } if (state->flags & SS_PWR_AUTO) { - debug(3, ":PWR_AUTO"); + pr_debug("m32r_pcc: :PWR_AUTO"); } if (state->csc_mask & SS_DETECT) - debug(3, ":csc-SS_DETECT"); + pr_debug("m32r_pcc: :csc-SS_DETECT"); if (state->flags & SS_IOCARD) { if (state->csc_mask & SS_STSCHG) - debug(3, ":STSCHG"); + pr_debug("m32r_pcc: :STSCHG"); } else { if (state->csc_mask & SS_BATDEAD) - debug(3, ":BATDEAD"); + pr_debug("m32r_pcc: :BATDEAD"); if (state->csc_mask & SS_BATWARN) - debug(3, ":BATWARN"); + pr_debug("m32r_pcc: :BATWARN"); if (state->csc_mask & SS_READY) - debug(3, ":READY"); + pr_debug("m32r_pcc: :READY"); } - debug(3, "\n"); -#endif + pr_debug("m32r_pcc: \n"); return 0; } /* _set_socket */ @@ -491,7 +480,7 @@ static int _pcc_set_io_map(u_short sock, struct pccard_io_map *io) { u_char map; - debug(3, "m32r-pcc: SetIOMap(%d, %d, %#2.2x, %d ns, " + pr_debug("m32r_pcc: SetIOMap(%d, %d, %#2.2x, %d ns, " "%#llx-%#llx)\n", sock, io->map, io->flags, io->speed, (unsigned long long)io->start, (unsigned long long)io->stop); @@ -515,7 +504,7 @@ static int _pcc_set_mem_map(u_short sock, struct pccard_mem_map *mem) #endif #endif - debug(3, "m32r-pcc: SetMemMap(%d, %d, %#2.2x, %d ns, " + pr_debug("m32r_pcc: SetMemMap(%d, %d, %#2.2x, %d ns, " "%#llx, %#x)\n", sock, map, mem->flags, mem->speed, (unsigned long long)mem->static_start, mem->card_start); @@ -662,7 +651,7 @@ static int pcc_set_mem_map(struct pcmcia_socket *s, struct pccard_mem_map *mem) static int pcc_init(struct pcmcia_socket *s) { - debug(4, "m32r-pcc: init call\n"); + pr_debug("m32r_pcc: init call\n"); return 0; } diff --git a/drivers/pcmcia/m8xx_pcmcia.c b/drivers/pcmcia/m8xx_pcmcia.c index 403559ba49dd..7f79c4e169ae 100644 --- a/drivers/pcmcia/m8xx_pcmcia.c +++ b/drivers/pcmcia/m8xx_pcmcia.c @@ -64,14 +64,6 @@ #include <pcmcia/cs.h> #include <pcmcia/ss.h> -#ifdef CONFIG_PCMCIA_DEBUG -static int pc_debug; -module_param(pc_debug, int, 0); -#define dprintk(args...) printk(KERN_DEBUG "m8xx_pcmcia: " args); -#else -#define dprintk(args...) -#endif - #define pcmcia_info(args...) printk(KERN_INFO "m8xx_pcmcia: "args) #define pcmcia_error(args...) printk(KERN_ERR "m8xx_pcmcia: "args) @@ -565,7 +557,7 @@ static irqreturn_t m8xx_interrupt(int irq, void *dev) unsigned int i, events, pscr, pipr, per; pcmconf8xx_t *pcmcia = socket[0].pcmcia; - dprintk("Interrupt!\n"); + pr_debug("m8xx_pcmcia: Interrupt!\n"); /* get interrupt sources */ pscr = in_be32(&pcmcia->pcmc_pscr); @@ -614,7 +606,7 @@ static irqreturn_t m8xx_interrupt(int irq, void *dev) /* call the handler */ - dprintk("slot %u: events = 0x%02x, pscr = 0x%08x, " + pr_debug("m8xx_pcmcia: slot %u: events = 0x%02x, pscr = 0x%08x, " "pipr = 0x%08x\n", i, events, pscr, pipr); if (events) { @@ -641,7 +633,7 @@ static irqreturn_t m8xx_interrupt(int irq, void *dev) /* clear the interrupt sources */ out_be32(&pcmcia->pcmc_pscr, pscr); - dprintk("Interrupt done.\n"); + pr_debug("m8xx_pcmcia: Interrupt done.\n"); return IRQ_HANDLED; } @@ -815,7 +807,7 @@ static int m8xx_get_status(struct pcmcia_socket *sock, unsigned int *value) }; } - dprintk("GetStatus(%d) = %#2.2x\n", lsock, *value); + pr_debug("m8xx_pcmcia: GetStatus(%d) = %#2.2x\n", lsock, *value); return 0; } @@ -828,7 +820,7 @@ static int m8xx_set_socket(struct pcmcia_socket *sock, socket_state_t * state) unsigned long flags; pcmconf8xx_t *pcmcia = socket[0].pcmcia; - dprintk("SetSocket(%d, flags %#3.3x, Vcc %d, Vpp %d, " + pr_debug("m8xx_pcmcia: SetSocket(%d, flags %#3.3x, Vcc %d, Vpp %d, " "io_irq %d, csc_mask %#2.2x)\n", lsock, state->flags, state->Vcc, state->Vpp, state->io_irq, state->csc_mask); @@ -974,7 +966,7 @@ static int m8xx_set_io_map(struct pcmcia_socket *sock, struct pccard_io_map *io) #define M8XX_SIZE (io->stop - io->start + 1) #define M8XX_BASE (PCMCIA_IO_WIN_BASE + io->start) - dprintk("SetIOMap(%d, %d, %#2.2x, %d ns, " + pr_debug("m8xx_pcmcia: SetIOMap(%d, %d, %#2.2x, %d ns, " "%#4.4llx-%#4.4llx)\n", lsock, io->map, io->flags, io->speed, (unsigned long long)io->start, (unsigned long long)io->stop); @@ -988,7 +980,7 @@ static int m8xx_set_io_map(struct pcmcia_socket *sock, struct pccard_io_map *io) if (io->flags & MAP_ACTIVE) { - dprintk("io->flags & MAP_ACTIVE\n"); + pr_debug("m8xx_pcmcia: io->flags & MAP_ACTIVE\n"); winnr = (PCMCIA_MEM_WIN_NO * PCMCIA_SOCKETS_NO) + (lsock * PCMCIA_IO_WIN_NO) + io->map; @@ -1018,8 +1010,8 @@ static int m8xx_set_io_map(struct pcmcia_socket *sock, struct pccard_io_map *io) out_be32(&w->or, reg); - dprintk("Socket %u: Mapped io window %u at %#8.8x, " - "OR = %#8.8x.\n", lsock, io->map, w->br, w->or); + pr_debug("m8xx_pcmcia: Socket %u: Mapped io window %u at " + "%#8.8x, OR = %#8.8x.\n", lsock, io->map, w->br, w->or); } else { /* shutdown IO window */ winnr = (PCMCIA_MEM_WIN_NO * PCMCIA_SOCKETS_NO) @@ -1033,14 +1025,14 @@ static int m8xx_set_io_map(struct pcmcia_socket *sock, struct pccard_io_map *io) out_be32(&w->or, 0); /* turn off window */ out_be32(&w->br, 0); /* turn off base address */ - dprintk("Socket %u: Unmapped io window %u at %#8.8x, " - "OR = %#8.8x.\n", lsock, io->map, w->br, w->or); + pr_debug("m8xx_pcmcia: Socket %u: Unmapped io window %u at " + "%#8.8x, OR = %#8.8x.\n", lsock, io->map, w->br, w->or); } /* copy the struct and modify the copy */ s->io_win[io->map] = *io; s->io_win[io->map].flags &= (MAP_WRPROT | MAP_16BIT | MAP_ACTIVE); - dprintk("SetIOMap exit\n"); + pr_debug("m8xx_pcmcia: SetIOMap exit\n"); return 0; } @@ -1055,7 +1047,7 @@ static int m8xx_set_mem_map(struct pcmcia_socket *sock, unsigned int reg, winnr; pcmconf8xx_t *pcmcia = s->pcmcia; - dprintk("SetMemMap(%d, %d, %#2.2x, %d ns, " + pr_debug("m8xx_pcmcia: SetMemMap(%d, %d, %#2.2x, %d ns, " "%#5.5llx, %#5.5x)\n", lsock, mem->map, mem->flags, mem->speed, (unsigned long long)mem->static_start, mem->card_start); @@ -1098,7 +1090,7 @@ static int m8xx_set_mem_map(struct pcmcia_socket *sock, out_be32(&w->or, reg); - dprintk("Socket %u: Mapped memory window %u at %#8.8x, " + pr_debug("m8xx_pcmcia: Socket %u: Mapped memory window %u at %#8.8x, " "OR = %#8.8x.\n", lsock, mem->map, w->br, w->or); if (mem->flags & MAP_ACTIVE) { @@ -1108,7 +1100,7 @@ static int m8xx_set_mem_map(struct pcmcia_socket *sock, + mem->card_start; } - dprintk("SetMemMap(%d, %d, %#2.2x, %d ns, " + pr_debug("m8xx_pcmcia: SetMemMap(%d, %d, %#2.2x, %d ns, " "%#5.5llx, %#5.5x)\n", lsock, mem->map, mem->flags, mem->speed, (unsigned long long)mem->static_start, mem->card_start); @@ -1129,7 +1121,7 @@ static int m8xx_sock_init(struct pcmcia_socket *sock) pccard_io_map io = { 0, 0, 0, 0, 1 }; pccard_mem_map mem = { 0, 0, 0, 0, 0, 0 }; - dprintk("sock_init(%d)\n", s); + pr_debug("m8xx_pcmcia: sock_init(%d)\n", s); m8xx_set_socket(sock, &dead_socket); for (i = 0; i < PCMCIA_IO_WIN_NO; i++) { diff --git a/drivers/pcmcia/o2micro.h b/drivers/pcmcia/o2micro.h index 72188c462c9c..624442fc0d35 100644 --- a/drivers/pcmcia/o2micro.h +++ b/drivers/pcmcia/o2micro.h @@ -30,28 +30,6 @@ #ifndef _LINUX_O2MICRO_H #define _LINUX_O2MICRO_H -#ifndef PCI_VENDOR_ID_O2 -#define PCI_VENDOR_ID_O2 0x1217 -#endif -#ifndef PCI_DEVICE_ID_O2_6729 -#define PCI_DEVICE_ID_O2_6729 0x6729 -#endif -#ifndef PCI_DEVICE_ID_O2_6730 -#define PCI_DEVICE_ID_O2_6730 0x673a -#endif -#ifndef PCI_DEVICE_ID_O2_6832 -#define PCI_DEVICE_ID_O2_6832 0x6832 -#endif -#ifndef PCI_DEVICE_ID_O2_6836 -#define PCI_DEVICE_ID_O2_6836 0x6836 -#endif -#ifndef PCI_DEVICE_ID_O2_6812 -#define PCI_DEVICE_ID_O2_6812 0x6872 -#endif -#ifndef PCI_DEVICE_ID_O2_6933 -#define PCI_DEVICE_ID_O2_6933 0x6933 -#endif - /* Additional PCI configuration registers */ #define O2_MUX_CONTROL 0x90 /* 32 bit */ diff --git a/drivers/pcmcia/pcmcia_ioctl.c b/drivers/pcmcia/pcmcia_ioctl.c index 30cf71d2ee23..c4d7908fa37f 100644 --- a/drivers/pcmcia/pcmcia_ioctl.c +++ b/drivers/pcmcia/pcmcia_ioctl.c @@ -58,17 +58,6 @@ typedef struct user_info_t { } user_info_t; -#ifdef CONFIG_PCMCIA_DEBUG -extern int ds_pc_debug; - -#define ds_dbg(lvl, fmt, arg...) do { \ - if (ds_pc_debug >= lvl) \ - printk(KERN_DEBUG "ds: " fmt , ## arg); \ -} while (0) -#else -#define ds_dbg(lvl, fmt, arg...) do { } while (0) -#endif - static struct pcmcia_device *get_pcmcia_device(struct pcmcia_socket *s, unsigned int function) { @@ -229,6 +218,61 @@ static int pcmcia_adjust_resource_info(adjust_t *adj) return (ret); } + +/** pcmcia_get_window + */ +static int pcmcia_get_window(struct pcmcia_socket *s, window_handle_t *wh_out, + window_handle_t wh, win_req_t *req) +{ + pccard_mem_map *win; + window_handle_t w; + + wh--; + if (!s || !(s->state & SOCKET_PRESENT)) + return -ENODEV; + if (wh >= MAX_WIN) + return -EINVAL; + for (w = wh; w < MAX_WIN; w++) + if (s->state & SOCKET_WIN_REQ(w)) + break; + if (w == MAX_WIN) + return -EINVAL; + win = &s->win[w]; + req->Base = win->res->start; + req->Size = win->res->end - win->res->start + 1; + req->AccessSpeed = win->speed; + req->Attributes = 0; + if (win->flags & MAP_ATTRIB) + req->Attributes |= WIN_MEMORY_TYPE_AM; + if (win->flags & MAP_ACTIVE) + req->Attributes |= WIN_ENABLE; + if (win->flags & MAP_16BIT) + req->Attributes |= WIN_DATA_WIDTH_16; + if (win->flags & MAP_USE_WAIT) + req->Attributes |= WIN_USE_WAIT; + + *wh_out = w + 1; + return 0; +} /* pcmcia_get_window */ + + +/** pcmcia_get_mem_page + * + * Change the card address of an already open memory window. + */ +static int pcmcia_get_mem_page(struct pcmcia_socket *skt, window_handle_t wh, + memreq_t *req) +{ + wh--; + if (wh >= MAX_WIN) + return -EINVAL; + + req->Page = 0; + req->CardOffset = skt->win[wh].card_start; + return 0; +} /* pcmcia_get_mem_page */ + + /** pccard_get_status * * Get the current socket state bits. We don't support the latched @@ -431,7 +475,7 @@ static int bind_request(struct pcmcia_socket *s, bind_info_t *bind_info) if (!s) return -EINVAL; - ds_dbg(2, "bind_request(%d, '%s')\n", s->sock, + pr_debug("bind_request(%d, '%s')\n", s->sock, (char *)bind_info->dev_info); p_drv = get_pcmcia_driver(&bind_info->dev_info); @@ -623,7 +667,7 @@ static int ds_open(struct inode *inode, struct file *file) static int warning_printed = 0; int ret = 0; - ds_dbg(0, "ds_open(socket %d)\n", i); + pr_debug("ds_open(socket %d)\n", i); lock_kernel(); s = pcmcia_get_socket_by_nr(i); @@ -685,7 +729,7 @@ static int ds_release(struct inode *inode, struct file *file) struct pcmcia_socket *s; user_info_t *user, **link; - ds_dbg(0, "ds_release(socket %d)\n", iminor(inode)); + pr_debug("ds_release(socket %d)\n", iminor(inode)); user = file->private_data; if (CHECK_USER(user)) @@ -719,7 +763,7 @@ static ssize_t ds_read(struct file *file, char __user *buf, user_info_t *user; int ret; - ds_dbg(2, "ds_read(socket %d)\n", iminor(file->f_path.dentry->d_inode)); + pr_debug("ds_read(socket %d)\n", iminor(file->f_path.dentry->d_inode)); if (count < 4) return -EINVAL; @@ -744,7 +788,7 @@ static ssize_t ds_read(struct file *file, char __user *buf, static ssize_t ds_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - ds_dbg(2, "ds_write(socket %d)\n", iminor(file->f_path.dentry->d_inode)); + pr_debug("ds_write(socket %d)\n", iminor(file->f_path.dentry->d_inode)); if (count != 4) return -EINVAL; @@ -762,7 +806,7 @@ static u_int ds_poll(struct file *file, poll_table *wait) struct pcmcia_socket *s; user_info_t *user; - ds_dbg(2, "ds_poll(socket %d)\n", iminor(file->f_path.dentry->d_inode)); + pr_debug("ds_poll(socket %d)\n", iminor(file->f_path.dentry->d_inode)); user = file->private_data; if (CHECK_USER(user)) @@ -790,7 +834,7 @@ static int ds_ioctl(struct inode * inode, struct file * file, ds_ioctl_arg_t *buf; user_info_t *user; - ds_dbg(2, "ds_ioctl(socket %d, %#x, %#lx)\n", iminor(inode), cmd, arg); + pr_debug("ds_ioctl(socket %d, %#x, %#lx)\n", iminor(inode), cmd, arg); user = file->private_data; if (CHECK_USER(user)) @@ -809,13 +853,13 @@ static int ds_ioctl(struct inode * inode, struct file * file, if (cmd & IOC_IN) { if (!access_ok(VERIFY_READ, uarg, size)) { - ds_dbg(3, "ds_ioctl(): verify_read = %d\n", -EFAULT); + pr_debug("ds_ioctl(): verify_read = %d\n", -EFAULT); return -EFAULT; } } if (cmd & IOC_OUT) { if (!access_ok(VERIFY_WRITE, uarg, size)) { - ds_dbg(3, "ds_ioctl(): verify_write = %d\n", -EFAULT); + pr_debug("ds_ioctl(): verify_write = %d\n", -EFAULT); return -EFAULT; } } @@ -927,15 +971,15 @@ static int ds_ioctl(struct inode * inode, struct file * file, goto free_out; break; case DS_GET_FIRST_WINDOW: - ret = pcmcia_get_window(s, &buf->win_info.handle, 0, + ret = pcmcia_get_window(s, &buf->win_info.handle, 1, &buf->win_info.window); break; case DS_GET_NEXT_WINDOW: ret = pcmcia_get_window(s, &buf->win_info.handle, - buf->win_info.handle->index + 1, &buf->win_info.window); + buf->win_info.handle + 1, &buf->win_info.window); break; case DS_GET_MEM_PAGE: - ret = pcmcia_get_mem_page(buf->win_info.handle, + ret = pcmcia_get_mem_page(s, buf->win_info.handle, &buf->win_info.map); break; case DS_REPLACE_CIS: @@ -962,7 +1006,7 @@ static int ds_ioctl(struct inode * inode, struct file * file, } if ((err == 0) && (ret != 0)) { - ds_dbg(2, "ds_ioctl: ret = %d\n", ret); + pr_debug("ds_ioctl: ret = %d\n", ret); switch (ret) { case -ENODEV: case -EINVAL: diff --git a/drivers/pcmcia/pcmcia_resource.c b/drivers/pcmcia/pcmcia_resource.c index d919e96c0afd..a8bf8c1b45ed 100644 --- a/drivers/pcmcia/pcmcia_resource.c +++ b/drivers/pcmcia/pcmcia_resource.c @@ -20,6 +20,7 @@ #include <linux/delay.h> #include <linux/pci.h> #include <linux/device.h> +#include <linux/netdevice.h> #include <pcmcia/cs_types.h> #include <pcmcia/ss.h> @@ -43,21 +44,6 @@ static u8 pcmcia_used_irq[NR_IRQS]; #endif -#ifdef CONFIG_PCMCIA_DEBUG -extern int ds_pc_debug; - -#define ds_dbg(skt, lvl, fmt, arg...) do { \ - if (ds_pc_debug >= lvl) \ - dev_printk(KERN_DEBUG, &skt->dev, \ - "pcmcia_resource: " fmt, \ - ## arg); \ -} while (0) -#else -#define ds_dbg(skt, lvl, fmt, arg...) do { } while (0) -#endif - - - /** alloc_io_space * * Special stuff for managing IO windows, because they are scarce @@ -72,14 +58,14 @@ static int alloc_io_space(struct pcmcia_socket *s, u_int attr, align = (*base) ? (lines ? 1<<lines : 0) : 1; if (align && (align < num)) { if (*base) { - ds_dbg(s, 0, "odd IO request: num %#x align %#x\n", + dev_dbg(&s->dev, "odd IO request: num %#x align %#x\n", num, align); align = 0; } else while (align && (align < num)) align <<= 1; } if (*base & ~(align-1)) { - ds_dbg(s, 0, "odd IO request: base %#x align %#x\n", + dev_dbg(&s->dev, "odd IO request: base %#x align %#x\n", *base, align); align = 0; } @@ -173,8 +159,10 @@ int pcmcia_access_configuration_register(struct pcmcia_device *p_dev, s = p_dev->socket; c = p_dev->function_config; - if (!(c->state & CONFIG_LOCKED)) + if (!(c->state & CONFIG_LOCKED)) { + dev_dbg(&s->dev, "Configuration isnt't locked\n"); return -EACCES; + } addr = (c->ConfigBase + reg->Offset) >> 1; @@ -188,6 +176,7 @@ int pcmcia_access_configuration_register(struct pcmcia_device *p_dev, pcmcia_write_cis_mem(s, 1, addr, 1, &val); break; default: + dev_dbg(&s->dev, "Invalid conf register request\n"); return -EINVAL; break; } @@ -196,68 +185,21 @@ int pcmcia_access_configuration_register(struct pcmcia_device *p_dev, EXPORT_SYMBOL(pcmcia_access_configuration_register); -/** pcmcia_get_window - */ -int pcmcia_get_window(struct pcmcia_socket *s, window_handle_t *handle, - int idx, win_req_t *req) -{ - window_t *win; - int w; - - if (!s || !(s->state & SOCKET_PRESENT)) - return -ENODEV; - for (w = idx; w < MAX_WIN; w++) - if (s->state & SOCKET_WIN_REQ(w)) - break; - if (w == MAX_WIN) - return -EINVAL; - win = &s->win[w]; - req->Base = win->ctl.res->start; - req->Size = win->ctl.res->end - win->ctl.res->start + 1; - req->AccessSpeed = win->ctl.speed; - req->Attributes = 0; - if (win->ctl.flags & MAP_ATTRIB) - req->Attributes |= WIN_MEMORY_TYPE_AM; - if (win->ctl.flags & MAP_ACTIVE) - req->Attributes |= WIN_ENABLE; - if (win->ctl.flags & MAP_16BIT) - req->Attributes |= WIN_DATA_WIDTH_16; - if (win->ctl.flags & MAP_USE_WAIT) - req->Attributes |= WIN_USE_WAIT; - *handle = win; - return 0; -} /* pcmcia_get_window */ -EXPORT_SYMBOL(pcmcia_get_window); - - -/** pcmcia_get_mem_page - * - * Change the card address of an already open memory window. - */ -int pcmcia_get_mem_page(window_handle_t win, memreq_t *req) +int pcmcia_map_mem_page(struct pcmcia_device *p_dev, window_handle_t wh, + memreq_t *req) { - if ((win == NULL) || (win->magic != WINDOW_MAGIC)) - return -EINVAL; - req->Page = 0; - req->CardOffset = win->ctl.card_start; - return 0; -} /* pcmcia_get_mem_page */ -EXPORT_SYMBOL(pcmcia_get_mem_page); - + struct pcmcia_socket *s = p_dev->socket; -int pcmcia_map_mem_page(window_handle_t win, memreq_t *req) -{ - struct pcmcia_socket *s; - if ((win == NULL) || (win->magic != WINDOW_MAGIC)) + wh--; + if (wh >= MAX_WIN) return -EINVAL; - s = win->sock; if (req->Page != 0) { - ds_dbg(s, 0, "failure: requested page is zero\n"); + dev_dbg(&s->dev, "failure: requested page is zero\n"); return -EINVAL; } - win->ctl.card_start = req->CardOffset; - if (s->ops->set_mem_map(s, &win->ctl) != 0) { - ds_dbg(s, 0, "failed to set_mem_map\n"); + s->win[wh].card_start = req->CardOffset; + if (s->ops->set_mem_map(s, &s->win[wh]) != 0) { + dev_dbg(&s->dev, "failed to set_mem_map\n"); return -EIO; } return 0; @@ -278,10 +220,14 @@ int pcmcia_modify_configuration(struct pcmcia_device *p_dev, s = p_dev->socket; c = p_dev->function_config; - if (!(s->state & SOCKET_PRESENT)) + if (!(s->state & SOCKET_PRESENT)) { + dev_dbg(&s->dev, "No card present\n"); return -ENODEV; - if (!(c->state & CONFIG_LOCKED)) + } + if (!(c->state & CONFIG_LOCKED)) { + dev_dbg(&s->dev, "Configuration isnt't locked\n"); return -EACCES; + } if (mod->Attributes & CONF_IRQ_CHANGE_VALID) { if (mod->Attributes & CONF_ENABLE_IRQ) { @@ -295,7 +241,7 @@ int pcmcia_modify_configuration(struct pcmcia_device *p_dev, } if (mod->Attributes & CONF_VCC_CHANGE_VALID) { - ds_dbg(s, 0, "changing Vcc is not allowed at this time\n"); + dev_dbg(&s->dev, "changing Vcc is not allowed at this time\n"); return -EINVAL; } @@ -303,7 +249,7 @@ int pcmcia_modify_configuration(struct pcmcia_device *p_dev, if ((mod->Attributes & CONF_VPP1_CHANGE_VALID) && (mod->Attributes & CONF_VPP2_CHANGE_VALID)) { if (mod->Vpp1 != mod->Vpp2) { - ds_dbg(s, 0, "Vpp1 and Vpp2 must be the same\n"); + dev_dbg(&s->dev, "Vpp1 and Vpp2 must be the same\n"); return -EINVAL; } s->socket.Vpp = mod->Vpp1; @@ -314,7 +260,7 @@ int pcmcia_modify_configuration(struct pcmcia_device *p_dev, } } else if ((mod->Attributes & CONF_VPP1_CHANGE_VALID) || (mod->Attributes & CONF_VPP2_CHANGE_VALID)) { - ds_dbg(s, 0, "changing Vcc is not allowed at this time\n"); + dev_dbg(&s->dev, "changing Vcc is not allowed at this time\n"); return -EINVAL; } @@ -425,11 +371,11 @@ static int pcmcia_release_irq(struct pcmcia_device *p_dev, irq_req_t *req) if (c->state & CONFIG_LOCKED) return -EACCES; if (c->irq.Attributes != req->Attributes) { - ds_dbg(s, 0, "IRQ attributes must match assigned ones\n"); + dev_dbg(&s->dev, "IRQ attributes must match assigned ones\n"); return -EINVAL; } if (s->irq.AssignedIRQ != req->AssignedIRQ) { - ds_dbg(s, 0, "IRQ must match assigned one\n"); + dev_dbg(&s->dev, "IRQ must match assigned one\n"); return -EINVAL; } if (--s->irq.Config == 0) { @@ -437,8 +383,8 @@ static int pcmcia_release_irq(struct pcmcia_device *p_dev, irq_req_t *req) s->irq.AssignedIRQ = 0; } - if (req->Attributes & IRQ_HANDLE_PRESENT) { - free_irq(req->AssignedIRQ, req->Instance); + if (req->Handler) { + free_irq(req->AssignedIRQ, p_dev->priv); } #ifdef CONFIG_PCMCIA_PROBE @@ -449,30 +395,34 @@ static int pcmcia_release_irq(struct pcmcia_device *p_dev, irq_req_t *req) } /* pcmcia_release_irq */ -int pcmcia_release_window(window_handle_t win) +int pcmcia_release_window(struct pcmcia_device *p_dev, window_handle_t wh) { - struct pcmcia_socket *s; + struct pcmcia_socket *s = p_dev->socket; + pccard_mem_map *win; - if ((win == NULL) || (win->magic != WINDOW_MAGIC)) + wh--; + if (wh >= MAX_WIN) return -EINVAL; - s = win->sock; - if (!(win->handle->_win & CLIENT_WIN_REQ(win->index))) + + win = &s->win[wh]; + + if (!(p_dev->_win & CLIENT_WIN_REQ(wh))) { + dev_dbg(&s->dev, "not releasing unknown window\n"); return -EINVAL; + } /* Shut down memory window */ - win->ctl.flags &= ~MAP_ACTIVE; - s->ops->set_mem_map(s, &win->ctl); - s->state &= ~SOCKET_WIN_REQ(win->index); + win->flags &= ~MAP_ACTIVE; + s->ops->set_mem_map(s, win); + s->state &= ~SOCKET_WIN_REQ(wh); /* Release system memory */ - if (win->ctl.res) { - release_resource(win->ctl.res); - kfree(win->ctl.res); - win->ctl.res = NULL; + if (win->res) { + release_resource(win->res); + kfree(win->res); + win->res = NULL; } - win->handle->_win &= ~CLIENT_WIN_REQ(win->index); - - win->magic = 0; + p_dev->_win &= ~CLIENT_WIN_REQ(wh); return 0; } /* pcmcia_release_window */ @@ -492,12 +442,14 @@ int pcmcia_request_configuration(struct pcmcia_device *p_dev, return -ENODEV; if (req->IntType & INT_CARDBUS) { - ds_dbg(p_dev->socket, 0, "IntType may not be INT_CARDBUS\n"); + dev_dbg(&s->dev, "IntType may not be INT_CARDBUS\n"); return -EINVAL; } c = p_dev->function_config; - if (c->state & CONFIG_LOCKED) + if (c->state & CONFIG_LOCKED) { + dev_dbg(&s->dev, "Configuration is locked\n"); return -EACCES; + } /* Do power control. We don't allow changes in Vcc. */ s->socket.Vpp = req->Vpp; @@ -609,40 +561,44 @@ int pcmcia_request_io(struct pcmcia_device *p_dev, io_req_t *req) struct pcmcia_socket *s = p_dev->socket; config_t *c; - if (!(s->state & SOCKET_PRESENT)) + if (!(s->state & SOCKET_PRESENT)) { + dev_dbg(&s->dev, "No card present\n"); return -ENODEV; + } if (!req) return -EINVAL; c = p_dev->function_config; - if (c->state & CONFIG_LOCKED) + if (c->state & CONFIG_LOCKED) { + dev_dbg(&s->dev, "Configuration is locked\n"); return -EACCES; + } if (c->state & CONFIG_IO_REQ) { - ds_dbg(s, 0, "IO already configured\n"); + dev_dbg(&s->dev, "IO already configured\n"); return -EBUSY; } if (req->Attributes1 & (IO_SHARED | IO_FORCE_ALIAS_ACCESS)) { - ds_dbg(s, 0, "bad attribute setting for IO region 1\n"); + dev_dbg(&s->dev, "bad attribute setting for IO region 1\n"); return -EINVAL; } if ((req->NumPorts2 > 0) && (req->Attributes2 & (IO_SHARED | IO_FORCE_ALIAS_ACCESS))) { - ds_dbg(s, 0, "bad attribute setting for IO region 2\n"); + dev_dbg(&s->dev, "bad attribute setting for IO region 2\n"); return -EINVAL; } - ds_dbg(s, 1, "trying to allocate resource 1\n"); + dev_dbg(&s->dev, "trying to allocate resource 1\n"); if (alloc_io_space(s, req->Attributes1, &req->BasePort1, req->NumPorts1, req->IOAddrLines)) { - ds_dbg(s, 0, "allocation of resource 1 failed\n"); + dev_dbg(&s->dev, "allocation of resource 1 failed\n"); return -EBUSY; } if (req->NumPorts2) { - ds_dbg(s, 1, "trying to allocate resource 2\n"); + dev_dbg(&s->dev, "trying to allocate resource 2\n"); if (alloc_io_space(s, req->Attributes2, &req->BasePort2, req->NumPorts2, req->IOAddrLines)) { - ds_dbg(s, 0, "allocation of resource 2 failed\n"); + dev_dbg(&s->dev, "allocation of resource 2 failed\n"); release_io_space(s, req->BasePort1, req->NumPorts1); return -EBUSY; } @@ -680,13 +636,17 @@ int pcmcia_request_irq(struct pcmcia_device *p_dev, irq_req_t *req) int ret = -EINVAL, irq = 0; int type; - if (!(s->state & SOCKET_PRESENT)) + if (!(s->state & SOCKET_PRESENT)) { + dev_dbg(&s->dev, "No card present\n"); return -ENODEV; + } c = p_dev->function_config; - if (c->state & CONFIG_LOCKED) + if (c->state & CONFIG_LOCKED) { + dev_dbg(&s->dev, "Configuration is locked\n"); return -EACCES; + } if (c->state & CONFIG_IRQ_REQ) { - ds_dbg(s, 0, "IRQ already configured\n"); + dev_dbg(&s->dev, "IRQ already configured\n"); return -EBUSY; } @@ -704,7 +664,7 @@ int pcmcia_request_irq(struct pcmcia_device *p_dev, irq_req_t *req) /* if the underlying IRQ infrastructure allows for it, only allocate * the IRQ, but do not enable it */ - if (!(req->Attributes & IRQ_HANDLE_PRESENT)) + if (!(req->Handler)) type |= IRQ_NOAUTOEN; #endif /* IRQ_NOAUTOEN */ @@ -714,7 +674,7 @@ int pcmcia_request_irq(struct pcmcia_device *p_dev, irq_req_t *req) } else { int try; u32 mask = s->irq_mask; - void *data = &p_dev->dev.driver; /* something unique to this device */ + void *data = p_dev; /* something unique to this device */ for (try = 0; try < 64; try++) { irq = try % 32; @@ -731,12 +691,12 @@ int pcmcia_request_irq(struct pcmcia_device *p_dev, irq_req_t *req) * registering a dummy handle works, i.e. if the IRQ isn't * marked as used by the kernel resource management core */ ret = request_irq(irq, - (req->Attributes & IRQ_HANDLE_PRESENT) ? req->Handler : test_action, + (req->Handler) ? req->Handler : test_action, type, p_dev->devname, - (req->Attributes & IRQ_HANDLE_PRESENT) ? req->Instance : data); + (req->Handler) ? p_dev->priv : data); if (!ret) { - if (!(req->Attributes & IRQ_HANDLE_PRESENT)) + if (!req->Handler) free_irq(irq, data); break; } @@ -745,17 +705,22 @@ int pcmcia_request_irq(struct pcmcia_device *p_dev, irq_req_t *req) #endif /* only assign PCI irq if no IRQ already assigned */ if (ret && !s->irq.AssignedIRQ) { - if (!s->pci_irq) + if (!s->pci_irq) { + dev_printk(KERN_INFO, &s->dev, "no IRQ found\n"); return ret; + } type = IRQF_SHARED; irq = s->pci_irq; } - if (ret && (req->Attributes & IRQ_HANDLE_PRESENT)) { + if (ret && req->Handler) { ret = request_irq(irq, req->Handler, type, - p_dev->devname, req->Instance); - if (ret) + p_dev->devname, p_dev->priv); + if (ret) { + dev_printk(KERN_INFO, &s->dev, + "request_irq() failed\n"); return ret; + } } /* Make sure the fact the request type was overridden is passed back */ @@ -787,17 +752,19 @@ EXPORT_SYMBOL(pcmcia_request_irq); * Request_window() establishes a mapping between card memory space * and system memory space. */ -int pcmcia_request_window(struct pcmcia_device **p_dev, win_req_t *req, window_handle_t *wh) +int pcmcia_request_window(struct pcmcia_device *p_dev, win_req_t *req, window_handle_t *wh) { - struct pcmcia_socket *s = (*p_dev)->socket; - window_t *win; + struct pcmcia_socket *s = p_dev->socket; + pccard_mem_map *win; u_long align; int w; - if (!(s->state & SOCKET_PRESENT)) + if (!(s->state & SOCKET_PRESENT)) { + dev_dbg(&s->dev, "No card present\n"); return -ENODEV; + } if (req->Attributes & (WIN_PAGED | WIN_SHARED)) { - ds_dbg(s, 0, "bad attribute setting for iomem region\n"); + dev_dbg(&s->dev, "bad attribute setting for iomem region\n"); return -EINVAL; } @@ -808,12 +775,12 @@ int pcmcia_request_window(struct pcmcia_device **p_dev, win_req_t *req, window_h (req->Attributes & WIN_STRICT_ALIGN)) ? req->Size : s->map_size); if (req->Size & (s->map_size-1)) { - ds_dbg(s, 0, "invalid map size\n"); + dev_dbg(&s->dev, "invalid map size\n"); return -EINVAL; } if ((req->Base && (s->features & SS_CAP_STATIC_MAP)) || (req->Base & (align-1))) { - ds_dbg(s, 0, "invalid base address\n"); + dev_dbg(&s->dev, "invalid base address\n"); return -EINVAL; } if (req->Base) @@ -823,52 +790,48 @@ int pcmcia_request_window(struct pcmcia_device **p_dev, win_req_t *req, window_h for (w = 0; w < MAX_WIN; w++) if (!(s->state & SOCKET_WIN_REQ(w))) break; if (w == MAX_WIN) { - ds_dbg(s, 0, "all windows are used already\n"); + dev_dbg(&s->dev, "all windows are used already\n"); return -EINVAL; } win = &s->win[w]; - win->magic = WINDOW_MAGIC; - win->index = w; - win->handle = *p_dev; - win->sock = s; if (!(s->features & SS_CAP_STATIC_MAP)) { - win->ctl.res = pcmcia_find_mem_region(req->Base, req->Size, align, + win->res = pcmcia_find_mem_region(req->Base, req->Size, align, (req->Attributes & WIN_MAP_BELOW_1MB), s); - if (!win->ctl.res) { - ds_dbg(s, 0, "allocating mem region failed\n"); + if (!win->res) { + dev_dbg(&s->dev, "allocating mem region failed\n"); return -EINVAL; } } - (*p_dev)->_win |= CLIENT_WIN_REQ(w); + p_dev->_win |= CLIENT_WIN_REQ(w); /* Configure the socket controller */ - win->ctl.map = w+1; - win->ctl.flags = 0; - win->ctl.speed = req->AccessSpeed; + win->map = w+1; + win->flags = 0; + win->speed = req->AccessSpeed; if (req->Attributes & WIN_MEMORY_TYPE) - win->ctl.flags |= MAP_ATTRIB; + win->flags |= MAP_ATTRIB; if (req->Attributes & WIN_ENABLE) - win->ctl.flags |= MAP_ACTIVE; + win->flags |= MAP_ACTIVE; if (req->Attributes & WIN_DATA_WIDTH_16) - win->ctl.flags |= MAP_16BIT; + win->flags |= MAP_16BIT; if (req->Attributes & WIN_USE_WAIT) - win->ctl.flags |= MAP_USE_WAIT; - win->ctl.card_start = 0; - if (s->ops->set_mem_map(s, &win->ctl) != 0) { - ds_dbg(s, 0, "failed to set memory mapping\n"); + win->flags |= MAP_USE_WAIT; + win->card_start = 0; + if (s->ops->set_mem_map(s, win) != 0) { + dev_dbg(&s->dev, "failed to set memory mapping\n"); return -EIO; } s->state |= SOCKET_WIN_REQ(w); /* Return window handle */ if (s->features & SS_CAP_STATIC_MAP) { - req->Base = win->ctl.static_start; + req->Base = win->static_start; } else { - req->Base = win->ctl.res->start; + req->Base = win->res->start; } - *wh = win; + *wh = w + 1; return 0; } /* pcmcia_request_window */ @@ -879,19 +842,46 @@ void pcmcia_disable_device(struct pcmcia_device *p_dev) { pcmcia_release_io(p_dev, &p_dev->io); pcmcia_release_irq(p_dev, &p_dev->irq); if (p_dev->win) - pcmcia_release_window(p_dev->win); + pcmcia_release_window(p_dev, p_dev->win); } EXPORT_SYMBOL(pcmcia_disable_device); struct pcmcia_cfg_mem { - tuple_t tuple; + struct pcmcia_device *p_dev; + void *priv_data; + int (*conf_check) (struct pcmcia_device *p_dev, + cistpl_cftable_entry_t *cfg, + cistpl_cftable_entry_t *dflt, + unsigned int vcc, + void *priv_data); cisparse_t parse; - u8 buf[256]; cistpl_cftable_entry_t dflt; }; /** + * pcmcia_do_loop_config() - internal helper for pcmcia_loop_config() + * + * pcmcia_do_loop_config() is the internal callback for the call from + * pcmcia_loop_config() to pccard_loop_tuple(). Data is transferred + * by a struct pcmcia_cfg_mem. + */ +static int pcmcia_do_loop_config(tuple_t *tuple, cisparse_t *parse, void *priv) +{ + cistpl_cftable_entry_t *cfg = &parse->cftable_entry; + struct pcmcia_cfg_mem *cfg_mem = priv; + + /* default values */ + cfg_mem->p_dev->conf.ConfigIndex = cfg->index; + if (cfg->flags & CISTPL_CFTABLE_DEFAULT) + cfg_mem->dflt = *cfg; + + return cfg_mem->conf_check(cfg_mem->p_dev, cfg, &cfg_mem->dflt, + cfg_mem->p_dev->socket->socket.Vcc, + cfg_mem->priv_data); +} + +/** * pcmcia_loop_config() - loop over configuration options * @p_dev: the struct pcmcia_device which we need to loop for. * @conf_check: function to call for each configuration option. @@ -913,48 +903,174 @@ int pcmcia_loop_config(struct pcmcia_device *p_dev, void *priv_data) { struct pcmcia_cfg_mem *cfg_mem; - - tuple_t *tuple; int ret; - unsigned int vcc; cfg_mem = kzalloc(sizeof(struct pcmcia_cfg_mem), GFP_KERNEL); if (cfg_mem == NULL) return -ENOMEM; - /* get the current Vcc setting */ - vcc = p_dev->socket->socket.Vcc; + cfg_mem->p_dev = p_dev; + cfg_mem->conf_check = conf_check; + cfg_mem->priv_data = priv_data; - tuple = &cfg_mem->tuple; - tuple->TupleData = cfg_mem->buf; - tuple->TupleDataMax = 255; - tuple->TupleOffset = 0; - tuple->DesiredTuple = CISTPL_CFTABLE_ENTRY; - tuple->Attributes = 0; + ret = pccard_loop_tuple(p_dev->socket, p_dev->func, + CISTPL_CFTABLE_ENTRY, &cfg_mem->parse, + cfg_mem, pcmcia_do_loop_config); - ret = pcmcia_get_first_tuple(p_dev, tuple); - while (!ret) { - cistpl_cftable_entry_t *cfg = &cfg_mem->parse.cftable_entry; + kfree(cfg_mem); + return ret; +} +EXPORT_SYMBOL(pcmcia_loop_config); + + +struct pcmcia_loop_mem { + struct pcmcia_device *p_dev; + void *priv_data; + int (*loop_tuple) (struct pcmcia_device *p_dev, + tuple_t *tuple, + void *priv_data); +}; + +/** + * pcmcia_do_loop_tuple() - internal helper for pcmcia_loop_config() + * + * pcmcia_do_loop_tuple() is the internal callback for the call from + * pcmcia_loop_tuple() to pccard_loop_tuple(). Data is transferred + * by a struct pcmcia_cfg_mem. + */ +static int pcmcia_do_loop_tuple(tuple_t *tuple, cisparse_t *parse, void *priv) +{ + struct pcmcia_loop_mem *loop = priv; + + return loop->loop_tuple(loop->p_dev, tuple, loop->priv_data); +}; + +/** + * pcmcia_loop_tuple() - loop over tuples in the CIS + * @p_dev: the struct pcmcia_device which we need to loop for. + * @code: which CIS code shall we look for? + * @priv_data: private data to be passed to the loop_tuple function. + * @loop_tuple: function to call for each CIS entry of type @function. IT + * gets passed the raw tuple and @priv_data. + * + * pcmcia_loop_tuple() loops over all CIS entries of type @function, and + * calls the @loop_tuple function for each entry. If the call to @loop_tuple + * returns 0, the loop exits. Returns 0 on success or errorcode otherwise. + */ +int pcmcia_loop_tuple(struct pcmcia_device *p_dev, cisdata_t code, + int (*loop_tuple) (struct pcmcia_device *p_dev, + tuple_t *tuple, + void *priv_data), + void *priv_data) +{ + struct pcmcia_loop_mem loop = { + .p_dev = p_dev, + .loop_tuple = loop_tuple, + .priv_data = priv_data}; - if (pcmcia_get_tuple_data(p_dev, tuple)) - goto next_entry; + return pccard_loop_tuple(p_dev->socket, p_dev->func, code, NULL, + &loop, pcmcia_do_loop_tuple); +}; +EXPORT_SYMBOL(pcmcia_loop_tuple); - if (pcmcia_parse_tuple(tuple, &cfg_mem->parse)) - goto next_entry; - /* default values */ - p_dev->conf.ConfigIndex = cfg->index; - if (cfg->flags & CISTPL_CFTABLE_DEFAULT) - cfg_mem->dflt = *cfg; +struct pcmcia_loop_get { + size_t len; + cisdata_t **buf; +}; - ret = conf_check(p_dev, cfg, &cfg_mem->dflt, vcc, priv_data); - if (!ret) - break; +/** + * pcmcia_do_get_tuple() - internal helper for pcmcia_get_tuple() + * + * pcmcia_do_get_tuple() is the internal callback for the call from + * pcmcia_get_tuple() to pcmcia_loop_tuple(). As we're only interested in + * the first tuple, return 0 unconditionally. Create a memory buffer large + * enough to hold the content of the tuple, and fill it with the tuple data. + * The caller is responsible to free the buffer. + */ +static int pcmcia_do_get_tuple(struct pcmcia_device *p_dev, tuple_t *tuple, + void *priv) +{ + struct pcmcia_loop_get *get = priv; + + *get->buf = kzalloc(tuple->TupleDataLen, GFP_KERNEL); + if (*get->buf) { + get->len = tuple->TupleDataLen; + memcpy(*get->buf, tuple->TupleData, tuple->TupleDataLen); + } else + dev_dbg(&p_dev->dev, "do_get_tuple: out of memory\n"); + return 0; +}; -next_entry: - ret = pcmcia_get_next_tuple(p_dev, tuple); +/** + * pcmcia_get_tuple() - get first tuple from CIS + * @p_dev: the struct pcmcia_device which we need to loop for. + * @code: which CIS code shall we look for? + * @buf: pointer to store the buffer to. + * + * pcmcia_get_tuple() gets the content of the first CIS entry of type @code. + * It returns the buffer length (or zero). The caller is responsible to free + * the buffer passed in @buf. + */ +size_t pcmcia_get_tuple(struct pcmcia_device *p_dev, cisdata_t code, + unsigned char **buf) +{ + struct pcmcia_loop_get get = { + .len = 0, + .buf = buf, + }; + + *get.buf = NULL; + pcmcia_loop_tuple(p_dev, code, pcmcia_do_get_tuple, &get); + + return get.len; +}; +EXPORT_SYMBOL(pcmcia_get_tuple); + + +/** + * pcmcia_do_get_mac() - internal helper for pcmcia_get_mac_from_cis() + * + * pcmcia_do_get_mac() is the internal callback for the call from + * pcmcia_get_mac_from_cis() to pcmcia_loop_tuple(). We check whether the + * tuple contains a proper LAN_NODE_ID of length 6, and copy the data + * to struct net_device->dev_addr[i]. + */ +static int pcmcia_do_get_mac(struct pcmcia_device *p_dev, tuple_t *tuple, + void *priv) +{ + struct net_device *dev = priv; + int i; + + if (tuple->TupleData[0] != CISTPL_FUNCE_LAN_NODE_ID) + return -EINVAL; + if (tuple->TupleDataLen < ETH_ALEN + 2) { + dev_warn(&p_dev->dev, "Invalid CIS tuple length for " + "LAN_NODE_ID\n"); + return -EINVAL; } - return ret; -} -EXPORT_SYMBOL(pcmcia_loop_config); + if (tuple->TupleData[1] != ETH_ALEN) { + dev_warn(&p_dev->dev, "Invalid header for LAN_NODE_ID\n"); + return -EINVAL; + } + for (i = 0; i < 6; i++) + dev->dev_addr[i] = tuple->TupleData[i+2]; + return 0; +}; + +/** + * pcmcia_get_mac_from_cis() - read out MAC address from CISTPL_FUNCE + * @p_dev: the struct pcmcia_device for which we want the address. + * @dev: a properly prepared struct net_device to store the info to. + * + * pcmcia_get_mac_from_cis() reads out the hardware MAC address from + * CISTPL_FUNCE and stores it into struct net_device *dev->dev_addr which + * must be set up properly by the driver (see examples!). + */ +int pcmcia_get_mac_from_cis(struct pcmcia_device *p_dev, struct net_device *dev) +{ + return pcmcia_loop_tuple(p_dev, CISTPL_FUNCE, pcmcia_do_get_mac, dev); +}; +EXPORT_SYMBOL(pcmcia_get_mac_from_cis); + diff --git a/drivers/pcmcia/pd6729.c b/drivers/pcmcia/pd6729.c index 70a33468bcd0..e1741cd875aa 100644 --- a/drivers/pcmcia/pd6729.c +++ b/drivers/pcmcia/pd6729.c @@ -213,7 +213,8 @@ static irqreturn_t pd6729_interrupt(int irq, void *dev) if (csc & I365_CSC_DETECT) { events |= SS_DETECT; - dprintk("Card detected in socket %i!\n", i); + dev_vdbg(&socket[i].socket.dev, + "Card detected in socket %i!\n", i); } if (indirect_read(&socket[i], I365_INTCTL) @@ -331,11 +332,11 @@ static int pd6729_set_socket(struct pcmcia_socket *sock, socket_state_t *state) reg = I365_PWR_NORESET; /* default: disable resetdrv on resume */ if (state->flags & SS_PWR_AUTO) { - dprintk("Auto power\n"); + dev_dbg(&sock->dev, "Auto power\n"); reg |= I365_PWR_AUTO; /* automatic power mngmnt */ } if (state->flags & SS_OUTPUT_ENA) { - dprintk("Power Enabled\n"); + dev_dbg(&sock->dev, "Power Enabled\n"); reg |= I365_PWR_OUT; /* enable power */ } @@ -343,40 +344,44 @@ static int pd6729_set_socket(struct pcmcia_socket *sock, socket_state_t *state) case 0: break; case 33: - dprintk("setting voltage to Vcc to 3.3V on socket %i\n", + dev_dbg(&sock->dev, + "setting voltage to Vcc to 3.3V on socket %i\n", socket->number); reg |= I365_VCC_5V; indirect_setbit(socket, PD67_MISC_CTL_1, PD67_MC1_VCC_3V); break; case 50: - dprintk("setting voltage to Vcc to 5V on socket %i\n", + dev_dbg(&sock->dev, + "setting voltage to Vcc to 5V on socket %i\n", socket->number); reg |= I365_VCC_5V; indirect_resetbit(socket, PD67_MISC_CTL_1, PD67_MC1_VCC_3V); break; default: - dprintk("pd6729: pd6729_set_socket called with " - "invalid VCC power value: %i\n", - state->Vcc); + dev_dbg(&sock->dev, + "pd6729_set_socket called with invalid VCC power " + "value: %i\n", state->Vcc); return -EINVAL; } switch (state->Vpp) { case 0: - dprintk("not setting Vpp on socket %i\n", socket->number); + dev_dbg(&sock->dev, "not setting Vpp on socket %i\n", + socket->number); break; case 33: case 50: - dprintk("setting Vpp to Vcc for socket %i\n", socket->number); + dev_dbg(&sock->dev, "setting Vpp to Vcc for socket %i\n", + socket->number); reg |= I365_VPP1_5V; break; case 120: - dprintk("setting Vpp to 12.0\n"); + dev_dbg(&sock->dev, "setting Vpp to 12.0\n"); reg |= I365_VPP1_12V; break; default: - dprintk("pd6729: pd6729_set_socket called with invalid VPP power value: %i\n", - state->Vpp); + dev_dbg(&sock->dev, "pd6729: pd6729_set_socket called with " + "invalid VPP power value: %i\n", state->Vpp); return -EINVAL; } @@ -438,7 +443,7 @@ static int pd6729_set_io_map(struct pcmcia_socket *sock, /* Check error conditions */ if (map > 1) { - dprintk("pd6729_set_io_map with invalid map"); + dev_dbg(&sock->dev, "pd6729_set_io_map with invalid map\n"); return -EINVAL; } @@ -446,7 +451,7 @@ static int pd6729_set_io_map(struct pcmcia_socket *sock, if (indirect_read(socket, I365_ADDRWIN) & I365_ENA_IO(map)) indirect_resetbit(socket, I365_ADDRWIN, I365_ENA_IO(map)); - /* dprintk("set_io_map: Setting range to %x - %x\n", + /* dev_dbg(&sock->dev, "set_io_map: Setting range to %x - %x\n", io->start, io->stop);*/ /* write the new values */ @@ -478,12 +483,12 @@ static int pd6729_set_mem_map(struct pcmcia_socket *sock, map = mem->map; if (map > 4) { - printk("pd6729_set_mem_map: invalid map"); + dev_warn(&sock->dev, "invalid map requested\n"); return -EINVAL; } if ((mem->res->start > mem->res->end) || (mem->speed > 1000)) { - printk("pd6729_set_mem_map: invalid address / speed"); + dev_warn(&sock->dev, "invalid invalid address / speed\n"); return -EINVAL; } @@ -529,12 +534,12 @@ static int pd6729_set_mem_map(struct pcmcia_socket *sock, if (mem->flags & MAP_WRPROT) i |= I365_MEM_WRPROT; if (mem->flags & MAP_ATTRIB) { - /* dprintk("requesting attribute memory for socket %i\n", - socket->number);*/ + /* dev_dbg(&sock->dev, "requesting attribute memory for " + "socket %i\n", socket->number);*/ i |= I365_MEM_REG; } else { - /* dprintk("requesting normal memory for socket %i\n", - socket->number);*/ + /* dev_dbg(&sock->dev, "requesting normal memory for " + "socket %i\n", socket->number);*/ } indirect_write16(socket, base + I365_W_OFF, i); @@ -577,7 +582,7 @@ static struct pccard_operations pd6729_operations = { static irqreturn_t pd6729_test(int irq, void *dev) { - dprintk("-> hit on irq %d\n", irq); + pr_devel("-> hit on irq %d\n", irq); return IRQ_HANDLED; } @@ -642,13 +647,13 @@ static int __devinit pd6729_pci_probe(struct pci_dev *dev, goto err_out_free_mem; if (!pci_resource_start(dev, 0)) { - printk(KERN_INFO "pd6729: refusing to load the driver " - "as the io_base is 0.\n"); + dev_warn(&dev->dev, "refusing to load the driver as the " + "io_base is NULL.\n"); goto err_out_free_mem; } - printk(KERN_INFO "pd6729: Cirrus PD6729 PCI to PCMCIA Bridge " - "at 0x%llx on irq %d\n", + dev_info(&dev->dev, "Cirrus PD6729 PCI to PCMCIA Bridge at 0x%llx " + "on irq %d\n", (unsigned long long)pci_resource_start(dev, 0), dev->irq); /* * Since we have no memory BARs some firmware may not @@ -656,14 +661,14 @@ static int __devinit pd6729_pci_probe(struct pci_dev *dev, */ pci_read_config_byte(dev, PCI_COMMAND, &configbyte); if (!(configbyte & PCI_COMMAND_MEMORY)) { - printk(KERN_DEBUG "pd6729: Enabling PCI_COMMAND_MEMORY.\n"); + dev_dbg(&dev->dev, "pd6729: Enabling PCI_COMMAND_MEMORY.\n"); configbyte |= PCI_COMMAND_MEMORY; pci_write_config_byte(dev, PCI_COMMAND, configbyte); } ret = pci_request_regions(dev, "pd6729"); if (ret) { - printk(KERN_INFO "pd6729: pci request region failed.\n"); + dev_warn(&dev->dev, "pci request region failed.\n"); goto err_out_disable; } @@ -672,7 +677,7 @@ static int __devinit pd6729_pci_probe(struct pci_dev *dev, mask = pd6729_isa_scan(); if (irq_mode == 0 && mask == 0) { - printk(KERN_INFO "pd6729: no ISA interrupt is available.\n"); + dev_warn(&dev->dev, "no ISA interrupt is available.\n"); goto err_out_free_res; } @@ -697,8 +702,8 @@ static int __devinit pd6729_pci_probe(struct pci_dev *dev, /* Register the interrupt handler */ if ((ret = request_irq(dev->irq, pd6729_interrupt, IRQF_SHARED, "pd6729", socket))) { - printk(KERN_ERR "pd6729: Failed to register irq %d, " - "aborting\n", dev->irq); + dev_err(&dev->dev, "Failed to register irq %d\n", + dev->irq); goto err_out_free_res; } } else { @@ -713,8 +718,7 @@ static int __devinit pd6729_pci_probe(struct pci_dev *dev, for (i = 0; i < MAX_SOCKETS; i++) { ret = pcmcia_register_socket(&socket[i].socket); if (ret) { - printk(KERN_INFO "pd6729: pcmcia_register_socket " - "failed.\n"); + dev_warn(&dev->dev, "pcmcia_register_socket failed.\n"); for (j = 0; j < i ; j++) pcmcia_unregister_socket(&socket[j].socket); goto err_out_free_res2; diff --git a/drivers/pcmcia/pd6729.h b/drivers/pcmcia/pd6729.h index f392e458cdfd..41418d394c55 100644 --- a/drivers/pcmcia/pd6729.h +++ b/drivers/pcmcia/pd6729.h @@ -1,13 +1,6 @@ #ifndef _INCLUDE_GUARD_PD6729_H_ #define _INCLUDE_GUARD_PD6729_H_ -/* Debuging defines */ -#ifdef NOTRACE -#define dprintk(fmt, args...) printk(fmt , ## args) -#else -#define dprintk(fmt, args...) do {} while (0) -#endif - /* Flags for I365_GENCTL */ #define I365_DF_VS1 0x40 /* DF-step Voltage Sense */ #define I365_DF_VS2 0x80 diff --git a/drivers/pcmcia/pxa2xx_base.c b/drivers/pcmcia/pxa2xx_base.c index 0e35acb1366b..84dde7768ad5 100644 --- a/drivers/pcmcia/pxa2xx_base.c +++ b/drivers/pcmcia/pxa2xx_base.c @@ -228,9 +228,43 @@ static const char *skt_names[] = { #define SKT_DEV_INFO_SIZE(n) \ (sizeof(struct skt_dev_info) + (n)*sizeof(struct soc_pcmcia_socket)) +int pxa2xx_drv_pcmcia_add_one(struct soc_pcmcia_socket *skt) +{ + skt->res_skt.start = _PCMCIA(skt->nr); + skt->res_skt.end = _PCMCIA(skt->nr) + PCMCIASp - 1; + skt->res_skt.name = skt_names[skt->nr]; + skt->res_skt.flags = IORESOURCE_MEM; + + skt->res_io.start = _PCMCIAIO(skt->nr); + skt->res_io.end = _PCMCIAIO(skt->nr) + PCMCIAIOSp - 1; + skt->res_io.name = "io"; + skt->res_io.flags = IORESOURCE_MEM | IORESOURCE_BUSY; + + skt->res_mem.start = _PCMCIAMem(skt->nr); + skt->res_mem.end = _PCMCIAMem(skt->nr) + PCMCIAMemSp - 1; + skt->res_mem.name = "memory"; + skt->res_mem.flags = IORESOURCE_MEM; + + skt->res_attr.start = _PCMCIAAttr(skt->nr); + skt->res_attr.end = _PCMCIAAttr(skt->nr) + PCMCIAAttrSp - 1; + skt->res_attr.name = "attribute"; + skt->res_attr.flags = IORESOURCE_MEM; + + return soc_pcmcia_add_one(skt); +} + +void pxa2xx_drv_pcmcia_ops(struct pcmcia_low_level *ops) +{ + /* Provide our PXA2xx specific timing routines. */ + ops->set_timing = pxa2xx_pcmcia_set_timing; +#ifdef CONFIG_CPU_FREQ + ops->frequency_change = pxa2xx_pcmcia_frequency_change; +#endif +} + int __pxa2xx_drv_pcmcia_probe(struct device *dev) { - int i, ret; + int i, ret = 0; struct pcmcia_low_level *ops; struct skt_dev_info *sinfo; struct soc_pcmcia_socket *skt; @@ -240,6 +274,8 @@ int __pxa2xx_drv_pcmcia_probe(struct device *dev) ops = (struct pcmcia_low_level *)dev->platform_data; + pxa2xx_drv_pcmcia_ops(ops); + sinfo = kzalloc(SKT_DEV_INFO_SIZE(ops->nr), GFP_KERNEL); if (!sinfo) return -ENOMEM; @@ -250,40 +286,25 @@ int __pxa2xx_drv_pcmcia_probe(struct device *dev) for (i = 0; i < ops->nr; i++) { skt = &sinfo->skt[i]; - skt->nr = ops->first + i; - skt->irq = NO_IRQ; - - skt->res_skt.start = _PCMCIA(skt->nr); - skt->res_skt.end = _PCMCIA(skt->nr) + PCMCIASp - 1; - skt->res_skt.name = skt_names[skt->nr]; - skt->res_skt.flags = IORESOURCE_MEM; - - skt->res_io.start = _PCMCIAIO(skt->nr); - skt->res_io.end = _PCMCIAIO(skt->nr) + PCMCIAIOSp - 1; - skt->res_io.name = "io"; - skt->res_io.flags = IORESOURCE_MEM | IORESOURCE_BUSY; + skt->nr = ops->first + i; + skt->ops = ops; + skt->socket.owner = ops->owner; + skt->socket.dev.parent = dev; + skt->socket.pci_irq = NO_IRQ; - skt->res_mem.start = _PCMCIAMem(skt->nr); - skt->res_mem.end = _PCMCIAMem(skt->nr) + PCMCIAMemSp - 1; - skt->res_mem.name = "memory"; - skt->res_mem.flags = IORESOURCE_MEM; - - skt->res_attr.start = _PCMCIAAttr(skt->nr); - skt->res_attr.end = _PCMCIAAttr(skt->nr) + PCMCIAAttrSp - 1; - skt->res_attr.name = "attribute"; - skt->res_attr.flags = IORESOURCE_MEM; + ret = pxa2xx_drv_pcmcia_add_one(skt); + if (ret) + break; } - /* Provide our PXA2xx specific timing routines. */ - ops->set_timing = pxa2xx_pcmcia_set_timing; -#ifdef CONFIG_CPU_FREQ - ops->frequency_change = pxa2xx_pcmcia_frequency_change; -#endif - - ret = soc_common_drv_pcmcia_probe(dev, ops, sinfo); - - if (!ret) + if (ret) { + while (--i >= 0) + soc_pcmcia_remove_one(&sinfo->skt[i]); + kfree(sinfo); + } else { pxa2xx_configure_sockets(dev); + dev_set_drvdata(dev, sinfo); + } return ret; } @@ -297,7 +318,16 @@ static int pxa2xx_drv_pcmcia_probe(struct platform_device *dev) static int pxa2xx_drv_pcmcia_remove(struct platform_device *dev) { - return soc_common_drv_pcmcia_remove(&dev->dev); + struct skt_dev_info *sinfo = platform_get_drvdata(dev); + int i; + + platform_set_drvdata(dev, NULL); + + for (i = 0; i < sinfo->nskt; i++) + soc_pcmcia_remove_one(&sinfo->skt[i]); + + kfree(sinfo); + return 0; } static int pxa2xx_drv_pcmcia_suspend(struct device *dev) diff --git a/drivers/pcmcia/pxa2xx_base.h b/drivers/pcmcia/pxa2xx_base.h index 235d681652c3..cb5efaec886f 100644 --- a/drivers/pcmcia/pxa2xx_base.h +++ b/drivers/pcmcia/pxa2xx_base.h @@ -1,3 +1,6 @@ /* temporary measure */ extern int __pxa2xx_drv_pcmcia_probe(struct device *); +int pxa2xx_drv_pcmcia_add_one(struct soc_pcmcia_socket *skt); +void pxa2xx_drv_pcmcia_ops(struct pcmcia_low_level *ops); + diff --git a/drivers/pcmcia/pxa2xx_cm_x255.c b/drivers/pcmcia/pxa2xx_cm_x255.c index 5143a760153b..05913d0bbdbe 100644 --- a/drivers/pcmcia/pxa2xx_cm_x255.c +++ b/drivers/pcmcia/pxa2xx_cm_x255.c @@ -44,7 +44,7 @@ static int cmx255_pcmcia_hw_init(struct soc_pcmcia_socket *skt) return ret; gpio_direction_output(GPIO_PCMCIA_RESET, 0); - skt->irq = skt->nr == 0 ? PCMCIA_S0_RDYINT : PCMCIA_S1_RDYINT; + skt->socket.pci_irq = skt->nr == 0 ? PCMCIA_S0_RDYINT : PCMCIA_S1_RDYINT; ret = soc_pcmcia_request_irqs(skt, irqs, ARRAY_SIZE(irqs)); if (!ret) gpio_free(GPIO_PCMCIA_RESET); diff --git a/drivers/pcmcia/pxa2xx_cm_x270.c b/drivers/pcmcia/pxa2xx_cm_x270.c index a7b943d01e34..5662646b84da 100644 --- a/drivers/pcmcia/pxa2xx_cm_x270.c +++ b/drivers/pcmcia/pxa2xx_cm_x270.c @@ -38,7 +38,7 @@ static int cmx270_pcmcia_hw_init(struct soc_pcmcia_socket *skt) return ret; gpio_direction_output(GPIO_PCMCIA_RESET, 0); - skt->irq = PCMCIA_S0_RDYINT; + skt->socket.pci_irq = PCMCIA_S0_RDYINT; ret = soc_pcmcia_request_irqs(skt, irqs, ARRAY_SIZE(irqs)); if (!ret) gpio_free(GPIO_PCMCIA_RESET); diff --git a/drivers/pcmcia/pxa2xx_e740.c b/drivers/pcmcia/pxa2xx_e740.c index d09c0dc4a31a..8bfbd4dca131 100644 --- a/drivers/pcmcia/pxa2xx_e740.c +++ b/drivers/pcmcia/pxa2xx_e740.c @@ -38,7 +38,7 @@ static struct pcmcia_irqs cd_irqs[] = { static int e740_pcmcia_hw_init(struct soc_pcmcia_socket *skt) { - skt->irq = skt->nr == 0 ? IRQ_GPIO(GPIO_E740_PCMCIA_RDY0) : + skt->socket.pci_irq = skt->nr == 0 ? IRQ_GPIO(GPIO_E740_PCMCIA_RDY0) : IRQ_GPIO(GPIO_E740_PCMCIA_RDY1); return soc_pcmcia_request_irqs(skt, &cd_irqs[skt->nr], 1); diff --git a/drivers/pcmcia/pxa2xx_lubbock.c b/drivers/pcmcia/pxa2xx_lubbock.c index 6cbb1b1f7cfd..b9f8c8fb42bd 100644 --- a/drivers/pcmcia/pxa2xx_lubbock.c +++ b/drivers/pcmcia/pxa2xx_lubbock.c @@ -32,6 +32,7 @@ static int lubbock_pcmcia_configure_socket(struct soc_pcmcia_socket *skt, const socket_state_t *state) { + struct sa1111_pcmcia_socket *s = to_skt(skt); unsigned int pa_dwr_mask, pa_dwr_set, misc_mask, misc_set; int ret = 0; @@ -149,7 +150,7 @@ lubbock_pcmcia_configure_socket(struct soc_pcmcia_socket *skt, if (ret == 0) { lubbock_set_misc_wr(misc_mask, misc_set); - sa1111_set_io(SA1111_DEV(skt->dev), pa_dwr_mask, pa_dwr_set); + sa1111_set_io(s->dev, pa_dwr_mask, pa_dwr_set); } #if 1 @@ -175,7 +176,7 @@ lubbock_pcmcia_configure_socket(struct soc_pcmcia_socket *skt, * Switch to 5V, Configure socket with 5V voltage */ lubbock_set_misc_wr(misc_mask, 0); - sa1111_set_io(SA1111_DEV(skt->dev), pa_dwr_mask, 0); + sa1111_set_io(s->dev, pa_dwr_mask, 0); /* * It takes about 100ms to turn off Vcc. @@ -200,12 +201,8 @@ lubbock_pcmcia_configure_socket(struct soc_pcmcia_socket *skt, static struct pcmcia_low_level lubbock_pcmcia_ops = { .owner = THIS_MODULE, - .hw_init = sa1111_pcmcia_hw_init, - .hw_shutdown = sa1111_pcmcia_hw_shutdown, - .socket_state = sa1111_pcmcia_socket_state, .configure_socket = lubbock_pcmcia_configure_socket, .socket_init = sa1111_pcmcia_socket_init, - .socket_suspend = sa1111_pcmcia_socket_suspend, .first = 0, .nr = 2, }; @@ -228,8 +225,9 @@ int pcmcia_lubbock_init(struct sa1111_dev *sadev) /* Set CF Socket 1 power to standby mode. */ lubbock_set_misc_wr((1 << 15) | (1 << 14), 0); - sadev->dev.platform_data = &lubbock_pcmcia_ops; - ret = __pxa2xx_drv_pcmcia_probe(&sadev->dev); + pxa2xx_drv_pcmcia_ops(&lubbock_pcmcia_ops); + ret = sa1111_pcmcia_add(sadev, &lubbock_pcmcia_ops, + pxa2xx_drv_pcmcia_add_one); } return ret; diff --git a/drivers/pcmcia/pxa2xx_mainstone.c b/drivers/pcmcia/pxa2xx_mainstone.c index 1138551ba8f6..92016fe932b4 100644 --- a/drivers/pcmcia/pxa2xx_mainstone.c +++ b/drivers/pcmcia/pxa2xx_mainstone.c @@ -44,7 +44,7 @@ static int mst_pcmcia_hw_init(struct soc_pcmcia_socket *skt) * before we enable them as outputs. */ - skt->irq = (skt->nr == 0) ? MAINSTONE_S0_IRQ : MAINSTONE_S1_IRQ; + skt->socket.pci_irq = (skt->nr == 0) ? MAINSTONE_S0_IRQ : MAINSTONE_S1_IRQ; return soc_pcmcia_request_irqs(skt, irqs, ARRAY_SIZE(irqs)); } diff --git a/drivers/pcmcia/pxa2xx_palmld.c b/drivers/pcmcia/pxa2xx_palmld.c index 5ba9b3664a00..6fb6f7f0672e 100644 --- a/drivers/pcmcia/pxa2xx_palmld.c +++ b/drivers/pcmcia/pxa2xx_palmld.c @@ -45,7 +45,7 @@ static int palmld_pcmcia_hw_init(struct soc_pcmcia_socket *skt) if (ret) goto err4; - skt->irq = IRQ_GPIO(GPIO_NR_PALMLD_PCMCIA_READY); + skt->socket.pci_irq = IRQ_GPIO(GPIO_NR_PALMLD_PCMCIA_READY); return 0; err4: diff --git a/drivers/pcmcia/pxa2xx_palmtx.c b/drivers/pcmcia/pxa2xx_palmtx.c index e07b5c51ec5b..b07b247a399f 100644 --- a/drivers/pcmcia/pxa2xx_palmtx.c +++ b/drivers/pcmcia/pxa2xx_palmtx.c @@ -53,7 +53,7 @@ static int palmtx_pcmcia_hw_init(struct soc_pcmcia_socket *skt) if (ret) goto err5; - skt->irq = gpio_to_irq(GPIO_NR_PALMTX_PCMCIA_READY); + skt->socket.pci_irq = gpio_to_irq(GPIO_NR_PALMTX_PCMCIA_READY); return 0; err5: diff --git a/drivers/pcmcia/pxa2xx_sharpsl.c b/drivers/pcmcia/pxa2xx_sharpsl.c index bc43f78f6f0b..0ea3b29440e6 100644 --- a/drivers/pcmcia/pxa2xx_sharpsl.c +++ b/drivers/pcmcia/pxa2xx_sharpsl.c @@ -66,7 +66,7 @@ static int sharpsl_pcmcia_hw_init(struct soc_pcmcia_socket *skt) } } - skt->irq = SCOOP_DEV[skt->nr].irq; + skt->socket.pci_irq = SCOOP_DEV[skt->nr].irq; return 0; } diff --git a/drivers/pcmcia/pxa2xx_trizeps4.c b/drivers/pcmcia/pxa2xx_trizeps4.c index e0e5cb339b4a..b7e596620db1 100644 --- a/drivers/pcmcia/pxa2xx_trizeps4.c +++ b/drivers/pcmcia/pxa2xx_trizeps4.c @@ -53,7 +53,7 @@ static int trizeps_pcmcia_hw_init(struct soc_pcmcia_socket *skt) gpio_free(GPIO_PRDY); return -EINVAL; } - skt->irq = IRQ_GPIO(GPIO_PRDY); + skt->socket.pci_irq = IRQ_GPIO(GPIO_PRDY); break; #ifndef CONFIG_MACH_TRIZEPS_CONXS @@ -63,7 +63,7 @@ static int trizeps_pcmcia_hw_init(struct soc_pcmcia_socket *skt) break; } /* release the reset of this card */ - pr_debug("%s: sock %d irq %d\n", __func__, skt->nr, skt->irq); + pr_debug("%s: sock %d irq %d\n", __func__, skt->nr, skt->socket.pci_irq); /* supplementory irqs for the socket */ for (i = 0; i < ARRAY_SIZE(irqs); i++) { diff --git a/drivers/pcmcia/pxa2xx_viper.c b/drivers/pcmcia/pxa2xx_viper.c index 17871360fe99..27be2e154df2 100644 --- a/drivers/pcmcia/pxa2xx_viper.c +++ b/drivers/pcmcia/pxa2xx_viper.c @@ -40,7 +40,7 @@ static int viper_pcmcia_hw_init(struct soc_pcmcia_socket *skt) { unsigned long flags; - skt->irq = gpio_to_irq(VIPER_CF_RDY_GPIO); + skt->socket.pci_irq = gpio_to_irq(VIPER_CF_RDY_GPIO); if (gpio_request(VIPER_CF_CD_GPIO, "CF detect")) goto err_request_cd; diff --git a/drivers/pcmcia/rsrc_mgr.c b/drivers/pcmcia/rsrc_mgr.c index e592e0e0d7ed..de0e770ce6a3 100644 --- a/drivers/pcmcia/rsrc_mgr.c +++ b/drivers/pcmcia/rsrc_mgr.c @@ -18,6 +18,7 @@ #include <pcmcia/cs_types.h> #include <pcmcia/ss.h> #include <pcmcia/cs.h> +#include <pcmcia/cistpl.h> #include "cs_internal.h" diff --git a/drivers/pcmcia/sa1100_assabet.c b/drivers/pcmcia/sa1100_assabet.c index ac8aa09ba0da..fd013a1ef47a 100644 --- a/drivers/pcmcia/sa1100_assabet.c +++ b/drivers/pcmcia/sa1100_assabet.c @@ -27,7 +27,7 @@ static struct pcmcia_irqs irqs[] = { static int assabet_pcmcia_hw_init(struct soc_pcmcia_socket *skt) { - skt->irq = ASSABET_IRQ_GPIO_CF_IRQ; + skt->socket.pci_irq = ASSABET_IRQ_GPIO_CF_IRQ; return soc_pcmcia_request_irqs(skt, irqs, ARRAY_SIZE(irqs)); } diff --git a/drivers/pcmcia/sa1100_badge4.c b/drivers/pcmcia/sa1100_badge4.c index 1ca9737ea79e..1ce53f493bef 100644 --- a/drivers/pcmcia/sa1100_badge4.c +++ b/drivers/pcmcia/sa1100_badge4.c @@ -127,13 +127,10 @@ badge4_pcmcia_configure_socket(struct soc_pcmcia_socket *skt, const socket_state static struct pcmcia_low_level badge4_pcmcia_ops = { .owner = THIS_MODULE, - .hw_init = sa1111_pcmcia_hw_init, - .hw_shutdown = sa1111_pcmcia_hw_shutdown, - .socket_state = sa1111_pcmcia_socket_state, .configure_socket = badge4_pcmcia_configure_socket, - .socket_init = sa1111_pcmcia_socket_init, - .socket_suspend = sa1111_pcmcia_socket_suspend, + .first = 0, + .nr = 2, }; int pcmcia_badge4_init(struct device *dev) @@ -146,7 +143,9 @@ int pcmcia_badge4_init(struct device *dev) __func__, badge4_pcmvcc, badge4_pcmvpp, badge4_cfvcc); - ret = sa11xx_drv_pcmcia_probe(dev, &badge4_pcmcia_ops, 0, 2); + sa11xx_drv_pcmcia_ops(&badge4_pcmcia_ops); + ret = sa1111_pcmcia_add(dev, &badge4_pcmcia_ops, + sa11xx_drv_pcmcia_add_one); } return ret; diff --git a/drivers/pcmcia/sa1100_cerf.c b/drivers/pcmcia/sa1100_cerf.c index 63e6bc431a0d..9bf088b17275 100644 --- a/drivers/pcmcia/sa1100_cerf.c +++ b/drivers/pcmcia/sa1100_cerf.c @@ -27,7 +27,7 @@ static struct pcmcia_irqs irqs[] = { static int cerf_pcmcia_hw_init(struct soc_pcmcia_socket *skt) { - skt->irq = CERF_IRQ_GPIO_CF_IRQ; + skt->socket.pci_irq = CERF_IRQ_GPIO_CF_IRQ; return soc_pcmcia_request_irqs(skt, irqs, ARRAY_SIZE(irqs)); } diff --git a/drivers/pcmcia/sa1100_generic.c b/drivers/pcmcia/sa1100_generic.c index 2d0e99751530..11cc3ba1260a 100644 --- a/drivers/pcmcia/sa1100_generic.c +++ b/drivers/pcmcia/sa1100_generic.c @@ -83,7 +83,16 @@ static int sa11x0_drv_pcmcia_probe(struct platform_device *dev) static int sa11x0_drv_pcmcia_remove(struct platform_device *dev) { - return soc_common_drv_pcmcia_remove(&dev->dev); + struct skt_dev_info *sinfo = platform_get_drvdata(dev); + int i; + + platform_set_drvdata(dev, NULL); + + for (i = 0; i < sinfo->nskt; i++) + soc_pcmcia_remove_one(&sinfo->skt[i]); + + kfree(sinfo); + return 0; } static int sa11x0_drv_pcmcia_suspend(struct platform_device *dev, diff --git a/drivers/pcmcia/sa1100_h3600.c b/drivers/pcmcia/sa1100_h3600.c index 0cc3748f3758..3a121ac697d6 100644 --- a/drivers/pcmcia/sa1100_h3600.c +++ b/drivers/pcmcia/sa1100_h3600.c @@ -25,8 +25,8 @@ static struct pcmcia_irqs irqs[] = { static int h3600_pcmcia_hw_init(struct soc_pcmcia_socket *skt) { - skt->irq = skt->nr ? IRQ_GPIO_H3600_PCMCIA_IRQ1 - : IRQ_GPIO_H3600_PCMCIA_IRQ0; + skt->socket.pci_irq = skt->nr ? IRQ_GPIO_H3600_PCMCIA_IRQ1 + : IRQ_GPIO_H3600_PCMCIA_IRQ0; return soc_pcmcia_request_irqs(skt, irqs, ARRAY_SIZE(irqs)); diff --git a/drivers/pcmcia/sa1100_jornada720.c b/drivers/pcmcia/sa1100_jornada720.c index 7eedb42f800c..6bcabee6bde4 100644 --- a/drivers/pcmcia/sa1100_jornada720.c +++ b/drivers/pcmcia/sa1100_jornada720.c @@ -22,25 +22,10 @@ #define SOCKET1_POWER (GPIO_GPIO1 | GPIO_GPIO3) #define SOCKET1_3V GPIO_GPIO3 -static int jornada720_pcmcia_hw_init(struct soc_pcmcia_socket *skt) -{ - unsigned int pin = GPIO_A0 | GPIO_A1 | GPIO_A2 | GPIO_A3; - - /* - * What is all this crap for? - */ - GRER |= 0x00000002; - /* Set GPIO_A<3:1> to be outputs for PCMCIA/CF power controller: */ - sa1111_set_io_dir(SA1111_DEV(skt->dev), pin, 0, 0); - sa1111_set_io(SA1111_DEV(skt->dev), pin, 0); - sa1111_set_sleep_io(SA1111_DEV(skt->dev), pin, 0); - - return sa1111_pcmcia_hw_init(skt); -} - static int jornada720_pcmcia_configure_socket(struct soc_pcmcia_socket *skt, const socket_state_t *state) { + struct sa1111_pcmcia_socket *s = to_skt(skt); unsigned int pa_dwr_mask, pa_dwr_set; int ret; @@ -97,7 +82,7 @@ jornada720_pcmcia_configure_socket(struct soc_pcmcia_socket *skt, const socket_s unsigned long flags; local_irq_save(flags); - sa1111_set_io(SA1111_DEV(skt->dev), pa_dwr_mask, pa_dwr_set); + sa1111_set_io(s->dev, pa_dwr_mask, pa_dwr_set); local_irq_restore(flags); } @@ -106,21 +91,30 @@ jornada720_pcmcia_configure_socket(struct soc_pcmcia_socket *skt, const socket_s static struct pcmcia_low_level jornada720_pcmcia_ops = { .owner = THIS_MODULE, - .hw_init = jornada720_pcmcia_hw_init, - .hw_shutdown = sa1111_pcmcia_hw_shutdown, - .socket_state = sa1111_pcmcia_socket_state, .configure_socket = jornada720_pcmcia_configure_socket, - .socket_init = sa1111_pcmcia_socket_init, - .socket_suspend = sa1111_pcmcia_socket_suspend, + .first = 0, + .nr = 2, }; int __devinit pcmcia_jornada720_init(struct device *dev) { int ret = -ENODEV; - if (machine_is_jornada720()) - ret = sa11xx_drv_pcmcia_probe(dev, &jornada720_pcmcia_ops, 0, 2); + if (machine_is_jornada720()) { + unsigned int pin = GPIO_A0 | GPIO_A1 | GPIO_A2 | GPIO_A3; + + GRER |= 0x00000002; + + /* Set GPIO_A<3:1> to be outputs for PCMCIA/CF power controller: */ + sa1111_set_io_dir(dev, pin, 0, 0); + sa1111_set_io(dev, pin, 0); + sa1111_set_sleep_io(dev, pin, 0); + + sa11xx_drv_pcmcia_ops(&jornada720_pcmcia_ops); + ret = sa1111_pcmcia_add(dev, &jornada720_pcmcia_ops, + sa11xx_drv_pcmcia_add_one); + } return ret; } diff --git a/drivers/pcmcia/sa1100_neponset.c b/drivers/pcmcia/sa1100_neponset.c index 0c76d337815b..c95639b5f2a0 100644 --- a/drivers/pcmcia/sa1100_neponset.c +++ b/drivers/pcmcia/sa1100_neponset.c @@ -43,6 +43,7 @@ static int neponset_pcmcia_configure_socket(struct soc_pcmcia_socket *skt, const socket_state_t *state) { + struct sa1111_pcmcia_socket *s = to_skt(skt); unsigned int ncr_mask, ncr_set, pa_dwr_mask, pa_dwr_set; int ret; @@ -99,7 +100,7 @@ neponset_pcmcia_configure_socket(struct soc_pcmcia_socket *skt, const socket_sta NCR_0 = (NCR_0 & ~ncr_mask) | ncr_set; local_irq_restore(flags); - sa1111_set_io(SA1111_DEV(skt->dev), pa_dwr_mask, pa_dwr_set); + sa1111_set_io(s->dev, pa_dwr_mask, pa_dwr_set); } return 0; @@ -115,12 +116,10 @@ static void neponset_pcmcia_socket_init(struct soc_pcmcia_socket *skt) static struct pcmcia_low_level neponset_pcmcia_ops = { .owner = THIS_MODULE, - .hw_init = sa1111_pcmcia_hw_init, - .hw_shutdown = sa1111_pcmcia_hw_shutdown, - .socket_state = sa1111_pcmcia_socket_state, .configure_socket = neponset_pcmcia_configure_socket, .socket_init = neponset_pcmcia_socket_init, - .socket_suspend = sa1111_pcmcia_socket_suspend, + .first = 0, + .nr = 2, }; int pcmcia_neponset_init(struct sa1111_dev *sadev) @@ -135,7 +134,9 @@ int pcmcia_neponset_init(struct sa1111_dev *sadev) sa1111_set_io_dir(sadev, GPIO_A0|GPIO_A1|GPIO_A2|GPIO_A3, 0, 0); sa1111_set_io(sadev, GPIO_A0|GPIO_A1|GPIO_A2|GPIO_A3, 0); sa1111_set_sleep_io(sadev, GPIO_A0|GPIO_A1|GPIO_A2|GPIO_A3, 0); - ret = sa11xx_drv_pcmcia_probe(&sadev->dev, &neponset_pcmcia_ops, 0, 2); + sa11xx_drv_pcmcia_ops(&neponset_pcmcia_ops); + ret = sa1111_pcmcia_add(sadev, &neponset_pcmcia_ops, + sa11xx_drv_pcmcia_add_one); } return ret; diff --git a/drivers/pcmcia/sa1100_shannon.c b/drivers/pcmcia/sa1100_shannon.c index 46d8c1977c2a..c4d51867a050 100644 --- a/drivers/pcmcia/sa1100_shannon.c +++ b/drivers/pcmcia/sa1100_shannon.c @@ -28,7 +28,7 @@ static int shannon_pcmcia_hw_init(struct soc_pcmcia_socket *skt) GAFR &= ~(SHANNON_GPIO_EJECT_0 | SHANNON_GPIO_EJECT_1 | SHANNON_GPIO_RDY_0 | SHANNON_GPIO_RDY_1); - skt->irq = skt->nr ? SHANNON_IRQ_GPIO_RDY_1 : SHANNON_IRQ_GPIO_RDY_0; + skt->socket.pci_irq = skt->nr ? SHANNON_IRQ_GPIO_RDY_1 : SHANNON_IRQ_GPIO_RDY_0; return soc_pcmcia_request_irqs(skt, irqs, ARRAY_SIZE(irqs)); } diff --git a/drivers/pcmcia/sa1100_simpad.c b/drivers/pcmcia/sa1100_simpad.c index 33a08ae09fdf..05bd504e6f18 100644 --- a/drivers/pcmcia/sa1100_simpad.c +++ b/drivers/pcmcia/sa1100_simpad.c @@ -28,7 +28,7 @@ static int simpad_pcmcia_hw_init(struct soc_pcmcia_socket *skt) clear_cs3_bit(VCC_3V_EN|VCC_5V_EN|EN0|EN1); - skt->irq = IRQ_GPIO_CF_IRQ; + skt->socket.pci_irq = IRQ_GPIO_CF_IRQ; return soc_pcmcia_request_irqs(skt, irqs, ARRAY_SIZE(irqs)); } diff --git a/drivers/pcmcia/sa1111_generic.c b/drivers/pcmcia/sa1111_generic.c index 4be4e172ffa1..de6bc333d299 100644 --- a/drivers/pcmcia/sa1111_generic.c +++ b/drivers/pcmcia/sa1111_generic.c @@ -28,23 +28,20 @@ static struct pcmcia_irqs irqs[] = { { 1, IRQ_S1_BVD1_STSCHG, "SA1111 CF BVD1" }, }; -int sa1111_pcmcia_hw_init(struct soc_pcmcia_socket *skt) +static int sa1111_pcmcia_hw_init(struct soc_pcmcia_socket *skt) { - if (skt->irq == NO_IRQ) - skt->irq = skt->nr ? IRQ_S1_READY_NINT : IRQ_S0_READY_NINT; - return soc_pcmcia_request_irqs(skt, irqs, ARRAY_SIZE(irqs)); } -void sa1111_pcmcia_hw_shutdown(struct soc_pcmcia_socket *skt) +static void sa1111_pcmcia_hw_shutdown(struct soc_pcmcia_socket *skt) { soc_pcmcia_free_irqs(skt, irqs, ARRAY_SIZE(irqs)); } void sa1111_pcmcia_socket_state(struct soc_pcmcia_socket *skt, struct pcmcia_state *state) { - struct sa1111_dev *sadev = SA1111_DEV(skt->dev); - unsigned long status = sa1111_readl(sadev->mapbase + SA1111_PCSR); + struct sa1111_pcmcia_socket *s = to_skt(skt); + unsigned long status = sa1111_readl(s->dev->mapbase + SA1111_PCSR); switch (skt->nr) { case 0: @@ -71,7 +68,7 @@ void sa1111_pcmcia_socket_state(struct soc_pcmcia_socket *skt, struct pcmcia_sta int sa1111_pcmcia_configure_socket(struct soc_pcmcia_socket *skt, const socket_state_t *state) { - struct sa1111_dev *sadev = SA1111_DEV(skt->dev); + struct sa1111_pcmcia_socket *s = to_skt(skt); unsigned int pccr_skt_mask, pccr_set_mask, val; unsigned long flags; @@ -100,10 +97,10 @@ int sa1111_pcmcia_configure_socket(struct soc_pcmcia_socket *skt, const socket_s pccr_set_mask |= PCCR_S0_FLT|PCCR_S1_FLT; local_irq_save(flags); - val = sa1111_readl(sadev->mapbase + SA1111_PCCR); + val = sa1111_readl(s->dev->mapbase + SA1111_PCCR); val &= ~pccr_skt_mask; val |= pccr_set_mask & pccr_skt_mask; - sa1111_writel(val, sadev->mapbase + SA1111_PCCR); + sa1111_writel(val, s->dev->mapbase + SA1111_PCCR); local_irq_restore(flags); return 0; @@ -114,15 +111,51 @@ void sa1111_pcmcia_socket_init(struct soc_pcmcia_socket *skt) soc_pcmcia_enable_irqs(skt, irqs, ARRAY_SIZE(irqs)); } -void sa1111_pcmcia_socket_suspend(struct soc_pcmcia_socket *skt) +static void sa1111_pcmcia_socket_suspend(struct soc_pcmcia_socket *skt) { soc_pcmcia_disable_irqs(skt, irqs, ARRAY_SIZE(irqs)); } +int sa1111_pcmcia_add(struct sa1111_dev *dev, struct pcmcia_low_level *ops, + int (*add)(struct soc_pcmcia_socket *)) +{ + struct sa1111_pcmcia_socket *s; + int i, ret = 0; + + ops->hw_init = sa1111_pcmcia_hw_init; + ops->hw_shutdown = sa1111_pcmcia_hw_shutdown; + ops->socket_state = sa1111_pcmcia_socket_state; + ops->socket_suspend = sa1111_pcmcia_socket_suspend; + + for (i = 0; i < ops->nr; i++) { + s = kzalloc(sizeof(*s), GFP_KERNEL); + if (!s) + return -ENOMEM; + + s->soc.nr = ops->first + i; + s->soc.ops = ops; + s->soc.socket.owner = ops->owner; + s->soc.socket.dev.parent = &dev->dev; + s->soc.socket.pci_irq = s->soc.nr ? IRQ_S1_READY_NINT : IRQ_S0_READY_NINT; + s->dev = dev; + + ret = add(&s->soc); + if (ret == 0) { + s->next = dev_get_drvdata(&dev->dev); + dev_set_drvdata(&dev->dev, s); + } else + kfree(s); + } + + return ret; +} + static int pcmcia_probe(struct sa1111_dev *dev) { void __iomem *base; + dev_set_drvdata(&dev->dev, NULL); + if (!request_mem_region(dev->res.start, 512, SA1111_DRIVER_NAME(dev))) return -EBUSY; @@ -152,7 +185,15 @@ static int pcmcia_probe(struct sa1111_dev *dev) static int __devexit pcmcia_remove(struct sa1111_dev *dev) { - soc_common_drv_pcmcia_remove(&dev->dev); + struct sa1111_pcmcia_socket *next, *s = dev_get_drvdata(&dev->dev); + + dev_set_drvdata(&dev->dev, NULL); + + for (; next = s->next, s; s = next) { + soc_pcmcia_remove_one(&s->soc); + kfree(s); + } + release_mem_region(dev->res.start, 512); return 0; } diff --git a/drivers/pcmcia/sa1111_generic.h b/drivers/pcmcia/sa1111_generic.h index 10ced4a210d7..02dc8577cdaf 100644 --- a/drivers/pcmcia/sa1111_generic.h +++ b/drivers/pcmcia/sa1111_generic.h @@ -1,12 +1,23 @@ #include "soc_common.h" #include "sa11xx_base.h" -extern int sa1111_pcmcia_hw_init(struct soc_pcmcia_socket *); -extern void sa1111_pcmcia_hw_shutdown(struct soc_pcmcia_socket *); +struct sa1111_pcmcia_socket { + struct soc_pcmcia_socket soc; + struct sa1111_dev *dev; + struct sa1111_pcmcia_socket *next; +}; + +static inline struct sa1111_pcmcia_socket *to_skt(struct soc_pcmcia_socket *s) +{ + return container_of(s, struct sa1111_pcmcia_socket, soc); +} + +int sa1111_pcmcia_add(struct sa1111_dev *dev, struct pcmcia_low_level *ops, + int (*add)(struct soc_pcmcia_socket *)); + extern void sa1111_pcmcia_socket_state(struct soc_pcmcia_socket *, struct pcmcia_state *); extern int sa1111_pcmcia_configure_socket(struct soc_pcmcia_socket *, const socket_state_t *); extern void sa1111_pcmcia_socket_init(struct soc_pcmcia_socket *); -extern void sa1111_pcmcia_socket_suspend(struct soc_pcmcia_socket *); extern int pcmcia_badge4_init(struct device *); extern int pcmcia_jornada720_init(struct device *); diff --git a/drivers/pcmcia/sa11xx_base.c b/drivers/pcmcia/sa11xx_base.c index e15d59f2d8a9..fc9a6527019b 100644 --- a/drivers/pcmcia/sa11xx_base.c +++ b/drivers/pcmcia/sa11xx_base.c @@ -171,12 +171,58 @@ static const char *skt_names[] = { #define SKT_DEV_INFO_SIZE(n) \ (sizeof(struct skt_dev_info) + (n)*sizeof(struct soc_pcmcia_socket)) +int sa11xx_drv_pcmcia_add_one(struct soc_pcmcia_socket *skt) +{ + skt->res_skt.start = _PCMCIA(skt->nr); + skt->res_skt.end = _PCMCIA(skt->nr) + PCMCIASp - 1; + skt->res_skt.name = skt_names[skt->nr]; + skt->res_skt.flags = IORESOURCE_MEM; + + skt->res_io.start = _PCMCIAIO(skt->nr); + skt->res_io.end = _PCMCIAIO(skt->nr) + PCMCIAIOSp - 1; + skt->res_io.name = "io"; + skt->res_io.flags = IORESOURCE_MEM | IORESOURCE_BUSY; + + skt->res_mem.start = _PCMCIAMem(skt->nr); + skt->res_mem.end = _PCMCIAMem(skt->nr) + PCMCIAMemSp - 1; + skt->res_mem.name = "memory"; + skt->res_mem.flags = IORESOURCE_MEM; + + skt->res_attr.start = _PCMCIAAttr(skt->nr); + skt->res_attr.end = _PCMCIAAttr(skt->nr) + PCMCIAAttrSp - 1; + skt->res_attr.name = "attribute"; + skt->res_attr.flags = IORESOURCE_MEM; + + return soc_pcmcia_add_one(skt); +} +EXPORT_SYMBOL(sa11xx_drv_pcmcia_add_one); + +void sa11xx_drv_pcmcia_ops(struct pcmcia_low_level *ops) +{ + /* + * set default MECR calculation if the board specific + * code did not specify one... + */ + if (!ops->get_timing) + ops->get_timing = sa1100_pcmcia_default_mecr_timing; + + /* Provide our SA11x0 specific timing routines. */ + ops->set_timing = sa1100_pcmcia_set_timing; + ops->show_timing = sa1100_pcmcia_show_timing; +#ifdef CONFIG_CPU_FREQ + ops->frequency_change = sa1100_pcmcia_frequency_change; +#endif +} +EXPORT_SYMBOL(sa11xx_drv_pcmcia_ops); + int sa11xx_drv_pcmcia_probe(struct device *dev, struct pcmcia_low_level *ops, int first, int nr) { struct skt_dev_info *sinfo; struct soc_pcmcia_socket *skt; - int i; + int i, ret = 0; + + sa11xx_drv_pcmcia_ops(ops); sinfo = kzalloc(SKT_DEV_INFO_SIZE(nr), GFP_KERNEL); if (!sinfo) @@ -188,45 +234,26 @@ int sa11xx_drv_pcmcia_probe(struct device *dev, struct pcmcia_low_level *ops, for (i = 0; i < nr; i++) { skt = &sinfo->skt[i]; - skt->nr = first + i; - skt->irq = NO_IRQ; - - skt->res_skt.start = _PCMCIA(skt->nr); - skt->res_skt.end = _PCMCIA(skt->nr) + PCMCIASp - 1; - skt->res_skt.name = skt_names[skt->nr]; - skt->res_skt.flags = IORESOURCE_MEM; - - skt->res_io.start = _PCMCIAIO(skt->nr); - skt->res_io.end = _PCMCIAIO(skt->nr) + PCMCIAIOSp - 1; - skt->res_io.name = "io"; - skt->res_io.flags = IORESOURCE_MEM | IORESOURCE_BUSY; + skt->nr = first + i; + skt->ops = ops; + skt->socket.owner = ops->owner; + skt->socket.dev.parent = dev; + skt->socket.pci_irq = NO_IRQ; - skt->res_mem.start = _PCMCIAMem(skt->nr); - skt->res_mem.end = _PCMCIAMem(skt->nr) + PCMCIAMemSp - 1; - skt->res_mem.name = "memory"; - skt->res_mem.flags = IORESOURCE_MEM; - - skt->res_attr.start = _PCMCIAAttr(skt->nr); - skt->res_attr.end = _PCMCIAAttr(skt->nr) + PCMCIAAttrSp - 1; - skt->res_attr.name = "attribute"; - skt->res_attr.flags = IORESOURCE_MEM; + ret = sa11xx_drv_pcmcia_add_one(skt); + if (ret) + break; } - /* - * set default MECR calculation if the board specific - * code did not specify one... - */ - if (!ops->get_timing) - ops->get_timing = sa1100_pcmcia_default_mecr_timing; - - /* Provide our SA11x0 specific timing routines. */ - ops->set_timing = sa1100_pcmcia_set_timing; - ops->show_timing = sa1100_pcmcia_show_timing; -#ifdef CONFIG_CPU_FREQ - ops->frequency_change = sa1100_pcmcia_frequency_change; -#endif + if (ret) { + while (--i >= 0) + soc_pcmcia_remove_one(&sinfo->skt[i]); + kfree(sinfo); + } else { + dev_set_drvdata(dev, sinfo); + } - return soc_common_drv_pcmcia_probe(dev, ops, sinfo); + return ret; } EXPORT_SYMBOL(sa11xx_drv_pcmcia_probe); diff --git a/drivers/pcmcia/sa11xx_base.h b/drivers/pcmcia/sa11xx_base.h index 7bc208280527..3d76d720f463 100644 --- a/drivers/pcmcia/sa11xx_base.h +++ b/drivers/pcmcia/sa11xx_base.h @@ -118,6 +118,8 @@ static inline unsigned int sa1100_pcmcia_cmd_time(unsigned int cpu_clock_khz, } +int sa11xx_drv_pcmcia_add_one(struct soc_pcmcia_socket *skt); +void sa11xx_drv_pcmcia_ops(struct pcmcia_low_level *ops); extern int sa11xx_drv_pcmcia_probe(struct device *dev, struct pcmcia_low_level *ops, int first, int nr); #endif /* !defined(_PCMCIA_SA1100_H) */ diff --git a/drivers/pcmcia/soc_common.c b/drivers/pcmcia/soc_common.c index ef7e9e58782b..6f1a86b43c60 100644 --- a/drivers/pcmcia/soc_common.c +++ b/drivers/pcmcia/soc_common.c @@ -144,10 +144,10 @@ soc_common_pcmcia_config_skt(struct soc_pcmcia_socket *skt, socket_state_t *stat */ if (skt->irq_state != 1 && state->io_irq) { skt->irq_state = 1; - set_irq_type(skt->irq, IRQ_TYPE_EDGE_FALLING); + set_irq_type(skt->socket.pci_irq, IRQ_TYPE_EDGE_FALLING); } else if (skt->irq_state == 1 && state->io_irq == 0) { skt->irq_state = 0; - set_irq_type(skt->irq, IRQ_TYPE_NONE); + set_irq_type(skt->socket.pci_irq, IRQ_TYPE_NONE); } skt->cs_state = *state; @@ -492,7 +492,8 @@ static ssize_t show_status(struct device *dev, struct device_attribute *attr, ch p+=sprintf(p, "Vcc : %d\n", skt->cs_state.Vcc); p+=sprintf(p, "Vpp : %d\n", skt->cs_state.Vpp); - p+=sprintf(p, "IRQ : %d (%d)\n", skt->cs_state.io_irq, skt->irq); + p+=sprintf(p, "IRQ : %d (%d)\n", skt->cs_state.io_irq, + skt->socket.pci_irq); if (skt->ops->show_timing) p+=skt->ops->show_timing(skt, p); @@ -574,7 +575,7 @@ void soc_pcmcia_enable_irqs(struct soc_pcmcia_socket *skt, EXPORT_SYMBOL(soc_pcmcia_enable_irqs); -LIST_HEAD(soc_pcmcia_sockets); +static LIST_HEAD(soc_pcmcia_sockets); static DEFINE_MUTEX(soc_pcmcia_sockets_lock); #ifdef CONFIG_CPU_FREQ @@ -609,177 +610,137 @@ static int soc_pcmcia_cpufreq_register(void) "notifier for PCMCIA (%d)\n", ret); return ret; } +fs_initcall(soc_pcmcia_cpufreq_register); static void soc_pcmcia_cpufreq_unregister(void) { cpufreq_unregister_notifier(&soc_pcmcia_notifier_block, CPUFREQ_TRANSITION_NOTIFIER); } +module_exit(soc_pcmcia_cpufreq_unregister); -#else -static int soc_pcmcia_cpufreq_register(void) { return 0; } -static void soc_pcmcia_cpufreq_unregister(void) {} #endif -int soc_common_drv_pcmcia_probe(struct device *dev, struct pcmcia_low_level *ops, - struct skt_dev_info *sinfo) +void soc_pcmcia_remove_one(struct soc_pcmcia_socket *skt) { - struct soc_pcmcia_socket *skt; - int ret, i; - mutex_lock(&soc_pcmcia_sockets_lock); + del_timer_sync(&skt->poll_timer); - /* - * Initialise the per-socket structure. - */ - for (i = 0; i < sinfo->nskt; i++) { - skt = &sinfo->skt[i]; + pcmcia_unregister_socket(&skt->socket); - skt->socket.ops = &soc_common_pcmcia_operations; - skt->socket.owner = ops->owner; - skt->socket.dev.parent = dev; + flush_scheduled_work(); - init_timer(&skt->poll_timer); - skt->poll_timer.function = soc_common_pcmcia_poll_event; - skt->poll_timer.data = (unsigned long)skt; - skt->poll_timer.expires = jiffies + SOC_PCMCIA_POLL_PERIOD; + skt->ops->hw_shutdown(skt); - skt->dev = dev; - skt->ops = ops; + soc_common_pcmcia_config_skt(skt, &dead_socket); - ret = request_resource(&iomem_resource, &skt->res_skt); - if (ret) - goto out_err_1; + list_del(&skt->node); + mutex_unlock(&soc_pcmcia_sockets_lock); - ret = request_resource(&skt->res_skt, &skt->res_io); - if (ret) - goto out_err_2; + iounmap(skt->virt_io); + skt->virt_io = NULL; + release_resource(&skt->res_attr); + release_resource(&skt->res_mem); + release_resource(&skt->res_io); + release_resource(&skt->res_skt); +} +EXPORT_SYMBOL(soc_pcmcia_remove_one); - ret = request_resource(&skt->res_skt, &skt->res_mem); - if (ret) - goto out_err_3; +int soc_pcmcia_add_one(struct soc_pcmcia_socket *skt) +{ + int ret; - ret = request_resource(&skt->res_skt, &skt->res_attr); - if (ret) - goto out_err_4; + init_timer(&skt->poll_timer); + skt->poll_timer.function = soc_common_pcmcia_poll_event; + skt->poll_timer.data = (unsigned long)skt; + skt->poll_timer.expires = jiffies + SOC_PCMCIA_POLL_PERIOD; - skt->virt_io = ioremap(skt->res_io.start, 0x10000); - if (skt->virt_io == NULL) { - ret = -ENOMEM; - goto out_err_5; - } + ret = request_resource(&iomem_resource, &skt->res_skt); + if (ret) + goto out_err_1; - if (list_empty(&soc_pcmcia_sockets)) - soc_pcmcia_cpufreq_register(); + ret = request_resource(&skt->res_skt, &skt->res_io); + if (ret) + goto out_err_2; - list_add(&skt->node, &soc_pcmcia_sockets); + ret = request_resource(&skt->res_skt, &skt->res_mem); + if (ret) + goto out_err_3; - /* - * We initialize default socket timing here, because - * we are not guaranteed to see a SetIOMap operation at - * runtime. - */ - ops->set_timing(skt); + ret = request_resource(&skt->res_skt, &skt->res_attr); + if (ret) + goto out_err_4; - ret = ops->hw_init(skt); - if (ret) - goto out_err_6; + skt->virt_io = ioremap(skt->res_io.start, 0x10000); + if (skt->virt_io == NULL) { + ret = -ENOMEM; + goto out_err_5; + } - skt->socket.features = SS_CAP_STATIC_MAP|SS_CAP_PCCARD; - skt->socket.resource_ops = &pccard_static_ops; - skt->socket.irq_mask = 0; - skt->socket.map_size = PAGE_SIZE; - skt->socket.pci_irq = skt->irq; - skt->socket.io_offset = (unsigned long)skt->virt_io; + mutex_lock(&soc_pcmcia_sockets_lock); - skt->status = soc_common_pcmcia_skt_state(skt); + list_add(&skt->node, &soc_pcmcia_sockets); - ret = pcmcia_register_socket(&skt->socket); - if (ret) - goto out_err_7; + /* + * We initialize default socket timing here, because + * we are not guaranteed to see a SetIOMap operation at + * runtime. + */ + skt->ops->set_timing(skt); - WARN_ON(skt->socket.sock != i); + ret = skt->ops->hw_init(skt); + if (ret) + goto out_err_6; - add_timer(&skt->poll_timer); + skt->socket.ops = &soc_common_pcmcia_operations; + skt->socket.features = SS_CAP_STATIC_MAP|SS_CAP_PCCARD; + skt->socket.resource_ops = &pccard_static_ops; + skt->socket.irq_mask = 0; + skt->socket.map_size = PAGE_SIZE; + skt->socket.io_offset = (unsigned long)skt->virt_io; - ret = device_create_file(&skt->socket.dev, &dev_attr_status); - if (ret) - goto out_err_8; - } + skt->status = soc_common_pcmcia_skt_state(skt); - dev_set_drvdata(dev, sinfo); - ret = 0; - goto out; + ret = pcmcia_register_socket(&skt->socket); + if (ret) + goto out_err_7; - do { - skt = &sinfo->skt[i]; + add_timer(&skt->poll_timer); + + mutex_unlock(&soc_pcmcia_sockets_lock); + + ret = device_create_file(&skt->socket.dev, &dev_attr_status); + if (ret) + goto out_err_8; + + return ret; - device_remove_file(&skt->socket.dev, &dev_attr_status); out_err_8: - del_timer_sync(&skt->poll_timer); - pcmcia_unregister_socket(&skt->socket); + mutex_lock(&soc_pcmcia_sockets_lock); + del_timer_sync(&skt->poll_timer); + pcmcia_unregister_socket(&skt->socket); out_err_7: - flush_scheduled_work(); + flush_scheduled_work(); - ops->hw_shutdown(skt); + skt->ops->hw_shutdown(skt); out_err_6: - list_del(&skt->node); - iounmap(skt->virt_io); + list_del(&skt->node); + mutex_unlock(&soc_pcmcia_sockets_lock); + iounmap(skt->virt_io); out_err_5: - release_resource(&skt->res_attr); + release_resource(&skt->res_attr); out_err_4: - release_resource(&skt->res_mem); + release_resource(&skt->res_mem); out_err_3: - release_resource(&skt->res_io); + release_resource(&skt->res_io); out_err_2: - release_resource(&skt->res_skt); + release_resource(&skt->res_skt); out_err_1: - i--; - } while (i > 0); - kfree(sinfo); - - out: - mutex_unlock(&soc_pcmcia_sockets_lock); return ret; } +EXPORT_SYMBOL(soc_pcmcia_add_one); -int soc_common_drv_pcmcia_remove(struct device *dev) -{ - struct skt_dev_info *sinfo = dev_get_drvdata(dev); - int i; - - dev_set_drvdata(dev, NULL); - - mutex_lock(&soc_pcmcia_sockets_lock); - for (i = 0; i < sinfo->nskt; i++) { - struct soc_pcmcia_socket *skt = &sinfo->skt[i]; - - del_timer_sync(&skt->poll_timer); - - pcmcia_unregister_socket(&skt->socket); - - flush_scheduled_work(); - - skt->ops->hw_shutdown(skt); - - soc_common_pcmcia_config_skt(skt, &dead_socket); - - list_del(&skt->node); - iounmap(skt->virt_io); - skt->virt_io = NULL; - release_resource(&skt->res_attr); - release_resource(&skt->res_mem); - release_resource(&skt->res_io); - release_resource(&skt->res_skt); - } - if (list_empty(&soc_pcmcia_sockets)) - soc_pcmcia_cpufreq_unregister(); - - mutex_unlock(&soc_pcmcia_sockets_lock); - - kfree(sinfo); - - return 0; -} -EXPORT_SYMBOL(soc_common_drv_pcmcia_remove); +MODULE_AUTHOR("John Dorsey <john+@cs.cmu.edu>"); +MODULE_DESCRIPTION("Linux PCMCIA Card Services: Common SoC support"); +MODULE_LICENSE("Dual MPL/GPL"); diff --git a/drivers/pcmcia/soc_common.h b/drivers/pcmcia/soc_common.h index 290e143839ee..e40824ce6b0b 100644 --- a/drivers/pcmcia/soc_common.h +++ b/drivers/pcmcia/soc_common.h @@ -30,14 +30,12 @@ struct soc_pcmcia_socket { /* * Info from low level handler */ - struct device *dev; unsigned int nr; - unsigned int irq; /* * Core PCMCIA state */ - struct pcmcia_low_level *ops; + const struct pcmcia_low_level *ops; unsigned int status; socket_state_t cs_state; @@ -135,10 +133,8 @@ extern void soc_pcmcia_enable_irqs(struct soc_pcmcia_socket *skt, struct pcmcia_ extern void soc_common_pcmcia_get_timing(struct soc_pcmcia_socket *, struct soc_pcmcia_timing *); -extern struct list_head soc_pcmcia_sockets; - -extern int soc_common_drv_pcmcia_probe(struct device *dev, struct pcmcia_low_level *ops, struct skt_dev_info *sinfo); -extern int soc_common_drv_pcmcia_remove(struct device *dev); +void soc_pcmcia_remove_one(struct soc_pcmcia_socket *skt); +int soc_pcmcia_add_one(struct soc_pcmcia_socket *skt); #ifdef CONFIG_PCMCIA_DEBUG diff --git a/drivers/pcmcia/tcic.c b/drivers/pcmcia/tcic.c index 6918849d511e..12c49ee135e1 100644 --- a/drivers/pcmcia/tcic.c +++ b/drivers/pcmcia/tcic.c @@ -55,21 +55,6 @@ #include <pcmcia/ss.h> #include "tcic.h" -#ifdef CONFIG_PCMCIA_DEBUG -static int pc_debug; - -module_param(pc_debug, int, 0644); -static const char version[] = -"tcic.c 1.111 2000/02/15 04:13:12 (David Hinds)"; - -#define debug(lvl, fmt, arg...) do { \ - if (pc_debug > (lvl)) \ - printk(KERN_DEBUG "tcic: " fmt , ## arg); \ -} while (0) -#else -#define debug(lvl, fmt, arg...) do { } while (0) -#endif - MODULE_AUTHOR("David Hinds <dahinds@users.sourceforge.net>"); MODULE_DESCRIPTION("Databook TCIC-2 PCMCIA socket driver"); MODULE_LICENSE("Dual MPL/GPL"); @@ -574,7 +559,7 @@ static irqreturn_t tcic_interrupt(int irq, void *dev) } else active = 1; - debug(2, "tcic_interrupt()\n"); + pr_debug("tcic_interrupt()\n"); for (i = 0; i < sockets; i++) { psock = socket_table[i].psock; @@ -611,13 +596,13 @@ static irqreturn_t tcic_interrupt(int irq, void *dev) } active = 0; - debug(2, "interrupt done\n"); + pr_debug("interrupt done\n"); return IRQ_HANDLED; } /* tcic_interrupt */ static void tcic_timer(u_long data) { - debug(2, "tcic_timer()\n"); + pr_debug("tcic_timer()\n"); tcic_timer_pending = 0; tcic_interrupt(0, NULL); } /* tcic_timer */ @@ -644,7 +629,7 @@ static int tcic_get_status(struct pcmcia_socket *sock, u_int *value) reg = tcic_getb(TCIC_PWR); if (reg & (TCIC_PWR_VCC(psock)|TCIC_PWR_VPP(psock))) *value |= SS_POWERON; - debug(1, "GetStatus(%d) = %#2.2x\n", psock, *value); + dev_dbg(&sock->dev, "GetStatus(%d) = %#2.2x\n", psock, *value); return 0; } /* tcic_get_status */ @@ -656,7 +641,7 @@ static int tcic_set_socket(struct pcmcia_socket *sock, socket_state_t *state) u_char reg; u_short scf1, scf2; - debug(1, "SetSocket(%d, flags %#3.3x, Vcc %d, Vpp %d, " + dev_dbg(&sock->dev, "SetSocket(%d, flags %#3.3x, Vcc %d, Vpp %d, " "io_irq %d, csc_mask %#2.2x)\n", psock, state->flags, state->Vcc, state->Vpp, state->io_irq, state->csc_mask); tcic_setw(TCIC_ADDR+2, (psock << TCIC_SS_SHFT) | TCIC_ADR2_INDREG); @@ -731,7 +716,7 @@ static int tcic_set_io_map(struct pcmcia_socket *sock, struct pccard_io_map *io) u_int addr; u_short base, len, ioctl; - debug(1, "SetIOMap(%d, %d, %#2.2x, %d ns, " + dev_dbg(&sock->dev, "SetIOMap(%d, %d, %#2.2x, %d ns, " "%#llx-%#llx)\n", psock, io->map, io->flags, io->speed, (unsigned long long)io->start, (unsigned long long)io->stop); if ((io->map > 1) || (io->start > 0xffff) || (io->stop > 0xffff) || @@ -768,7 +753,7 @@ static int tcic_set_mem_map(struct pcmcia_socket *sock, struct pccard_mem_map *m u_short addr, ctl; u_long base, len, mmap; - debug(1, "SetMemMap(%d, %d, %#2.2x, %d ns, " + dev_dbg(&sock->dev, "SetMemMap(%d, %d, %#2.2x, %d ns, " "%#llx-%#llx, %#x)\n", psock, mem->map, mem->flags, mem->speed, (unsigned long long)mem->res->start, (unsigned long long)mem->res->end, mem->card_start); diff --git a/drivers/pcmcia/topic.h b/drivers/pcmcia/topic.h index edccfa5bb400..615a45a8fe86 100644 --- a/drivers/pcmcia/topic.h +++ b/drivers/pcmcia/topic.h @@ -114,22 +114,17 @@ static void topic97_zoom_video(struct pcmcia_socket *sock, int onoff) reg_zv |= TOPIC97_ZV_CONTROL_ENABLE; config_writeb(socket, TOPIC97_ZOOM_VIDEO_CONTROL, reg_zv); - reg = config_readb(socket, TOPIC97_MISC2); - reg |= TOPIC97_MISC2_ZV_ENABLE; - config_writeb(socket, TOPIC97_MISC2, reg); - - /* not sure this is needed, doc is unclear */ -#if 0 reg = config_readb(socket, TOPIC97_AUDIO_VIDEO_SWITCH); reg |= TOPIC97_AVS_AUDIO_CONTROL | TOPIC97_AVS_VIDEO_CONTROL; config_writeb(socket, TOPIC97_AUDIO_VIDEO_SWITCH, reg); -#endif - } - else { + } else { reg_zv &= ~TOPIC97_ZV_CONTROL_ENABLE; config_writeb(socket, TOPIC97_ZOOM_VIDEO_CONTROL, reg_zv); - } + reg = config_readb(socket, TOPIC97_AUDIO_VIDEO_SWITCH); + reg &= ~(TOPIC97_AVS_AUDIO_CONTROL | TOPIC97_AVS_VIDEO_CONTROL); + config_writeb(socket, TOPIC97_AUDIO_VIDEO_SWITCH, reg); + } } static int topic97_override(struct yenta_socket *socket) diff --git a/drivers/platform/x86/acerhdf.c b/drivers/platform/x86/acerhdf.c index 0a8f735f6c4a..ab64522aaa64 100644 --- a/drivers/platform/x86/acerhdf.c +++ b/drivers/platform/x86/acerhdf.c @@ -52,7 +52,7 @@ */ #undef START_IN_KERNEL_MODE -#define DRV_VER "0.5.17" +#define DRV_VER "0.5.18" /* * According to the Atom N270 datasheet, @@ -61,7 +61,7 @@ * measured by the on-die thermal monitor are within 0 <= Tj <= 90. So, * assume 89°C is critical temperature. */ -#define ACERHDF_TEMP_CRIT 89 +#define ACERHDF_TEMP_CRIT 89000 #define ACERHDF_FAN_OFF 0 #define ACERHDF_FAN_AUTO 1 @@ -69,7 +69,7 @@ * No matter what value the user puts into the fanon variable, turn on the fan * at 80 degree Celsius to prevent hardware damage */ -#define ACERHDF_MAX_FANON 80 +#define ACERHDF_MAX_FANON 80000 /* * Maximum interval between two temperature checks is 15 seconds, as the die @@ -85,8 +85,8 @@ static int kernelmode; #endif static unsigned int interval = 10; -static unsigned int fanon = 63; -static unsigned int fanoff = 58; +static unsigned int fanon = 63000; +static unsigned int fanoff = 58000; static unsigned int verbose; static unsigned int fanstate = ACERHDF_FAN_AUTO; static char force_bios[16]; @@ -171,7 +171,7 @@ static int acerhdf_get_temp(int *temp) if (ec_read(bios_cfg->tempreg, &read_temp)) return -EINVAL; - *temp = read_temp; + *temp = read_temp * 1000; return 0; } diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index d93108d148fc..a848c7e20aeb 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -1680,36 +1680,48 @@ static void tpacpi_remove_driver_attributes(struct device_driver *drv) | (__bv1) << 8 | (__bv2) } #define TPV_Q_X(__v, __bid1, __bid2, __bv1, __bv2, \ - __eid1, __eid2, __ev1, __ev2) \ + __eid, __ev1, __ev2) \ { .vendor = (__v), \ .bios = TPID(__bid1, __bid2), \ - .ec = TPID(__eid1, __eid2), \ + .ec = __eid, \ .quirks = (__ev1) << 24 | (__ev2) << 16 \ | (__bv1) << 8 | (__bv2) } #define TPV_QI0(__id1, __id2, __bv1, __bv2) \ TPV_Q(PCI_VENDOR_ID_IBM, __id1, __id2, __bv1, __bv2) +/* Outdated IBM BIOSes often lack the EC id string */ #define TPV_QI1(__id1, __id2, __bv1, __bv2, __ev1, __ev2) \ TPV_Q_X(PCI_VENDOR_ID_IBM, __id1, __id2, \ - __bv1, __bv2, __id1, __id2, __ev1, __ev2) + __bv1, __bv2, TPID(__id1, __id2), \ + __ev1, __ev2), \ + TPV_Q_X(PCI_VENDOR_ID_IBM, __id1, __id2, \ + __bv1, __bv2, TPACPI_MATCH_UNKNOWN, \ + __ev1, __ev2) +/* Outdated IBM BIOSes often lack the EC id string */ #define TPV_QI2(__bid1, __bid2, __bv1, __bv2, \ __eid1, __eid2, __ev1, __ev2) \ TPV_Q_X(PCI_VENDOR_ID_IBM, __bid1, __bid2, \ - __bv1, __bv2, __eid1, __eid2, __ev1, __ev2) + __bv1, __bv2, TPID(__eid1, __eid2), \ + __ev1, __ev2), \ + TPV_Q_X(PCI_VENDOR_ID_IBM, __bid1, __bid2, \ + __bv1, __bv2, TPACPI_MATCH_UNKNOWN, \ + __ev1, __ev2) #define TPV_QL0(__id1, __id2, __bv1, __bv2) \ TPV_Q(PCI_VENDOR_ID_LENOVO, __id1, __id2, __bv1, __bv2) #define TPV_QL1(__id1, __id2, __bv1, __bv2, __ev1, __ev2) \ TPV_Q_X(PCI_VENDOR_ID_LENOVO, __id1, __id2, \ - __bv1, __bv2, __id1, __id2, __ev1, __ev2) + __bv1, __bv2, TPID(__id1, __id2), \ + __ev1, __ev2) #define TPV_QL2(__bid1, __bid2, __bv1, __bv2, \ __eid1, __eid2, __ev1, __ev2) \ TPV_Q_X(PCI_VENDOR_ID_LENOVO, __bid1, __bid2, \ - __bv1, __bv2, __eid1, __eid2, __ev1, __ev2) + __bv1, __bv2, TPID(__eid1, __eid2), \ + __ev1, __ev2) static const struct tpacpi_quirk tpacpi_bios_version_qtable[] __initconst = { /* Numeric models ------------------ */ @@ -6313,7 +6325,7 @@ static int brightness_write(char *buf) * Doing it this way makes the syscall restartable in case of EINTR */ rc = brightness_set(level); - return (rc == -EINTR)? ERESTARTSYS : rc; + return (rc == -EINTR)? -ERESTARTSYS : rc; } static struct ibm_struct brightness_driver_data = { diff --git a/drivers/regulator/wm831x-isink.c b/drivers/regulator/wm831x-isink.c index 1d8d9879d3a1..48857008758c 100644 --- a/drivers/regulator/wm831x-isink.c +++ b/drivers/regulator/wm831x-isink.c @@ -167,6 +167,8 @@ static __devinit int wm831x_isink_probe(struct platform_device *pdev) return -ENOMEM; } + isink->wm831x = wm831x; + res = platform_get_resource(pdev, IORESOURCE_IO, 0); if (res == NULL) { dev_err(&pdev->dev, "No I/O resource\n"); diff --git a/drivers/rtc/rtc-pcf50633.c b/drivers/rtc/rtc-pcf50633.c index 33a10c47260e..4c5d5d0c4cfc 100644 --- a/drivers/rtc/rtc-pcf50633.c +++ b/drivers/rtc/rtc-pcf50633.c @@ -292,8 +292,9 @@ static int __devinit pcf50633_rtc_probe(struct platform_device *pdev) &pcf50633_rtc_ops, THIS_MODULE); if (IS_ERR(rtc->rtc_dev)) { + int ret = PTR_ERR(rtc->rtc_dev); kfree(rtc); - return PTR_ERR(rtc->rtc_dev); + return ret; } pcf50633_register_irq(rtc->pcf, PCF50633_IRQ_ALARM, diff --git a/drivers/rtc/rtc-x1205.c b/drivers/rtc/rtc-x1205.c index 310c10795e9a..6583c1a8b070 100644 --- a/drivers/rtc/rtc-x1205.c +++ b/drivers/rtc/rtc-x1205.c @@ -195,7 +195,7 @@ static int x1205_set_datetime(struct i2c_client *client, struct rtc_time *tm, /* year, since the rtc epoch*/ buf[CCR_YEAR] = bin2bcd(tm->tm_year % 100); buf[CCR_WDAY] = tm->tm_wday & 0x07; - buf[CCR_Y2K] = bin2bcd(tm->tm_year / 100); + buf[CCR_Y2K] = bin2bcd((tm->tm_year + 1900) / 100); } /* If writing alarm registers, set compare bits on registers 0-4 */ @@ -280,9 +280,9 @@ static int x1205_fix_osc(struct i2c_client *client) int err; struct rtc_time tm; - tm.tm_hour = tm.tm_min = tm.tm_sec = 0; + memset(&tm, 0, sizeof(tm)); - err = x1205_set_datetime(client, &tm, 0, X1205_CCR_BASE, 0); + err = x1205_set_datetime(client, &tm, 1, X1205_CCR_BASE, 0); if (err < 0) dev_err(&client->dev, "unable to restart the oscillator\n"); diff --git a/drivers/s390/char/sclp_async.c b/drivers/s390/char/sclp_async.c index b44462a6c6d3..740fe405c395 100644 --- a/drivers/s390/char/sclp_async.c +++ b/drivers/s390/char/sclp_async.c @@ -101,18 +101,17 @@ static struct ctl_table callhome_table[] = { .mode = 0644, .proc_handler = proc_handler_callhome, }, - { .ctl_name = 0 } + {} }; static struct ctl_table kern_dir_table[] = { { - .ctl_name = CTL_KERN, .procname = "kernel", .maxlen = 0, .mode = 0555, .child = callhome_table, }, - { .ctl_name = 0 } + {} }; /* diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index 5fd2da494d08..c968cc31cd86 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -164,8 +164,8 @@ void scsi_remove_host(struct Scsi_Host *shost) return; } spin_unlock_irqrestore(shost->host_lock, flags); - mutex_unlock(&shost->scan_mutex); scsi_forget_host(shost); + mutex_unlock(&shost->scan_mutex); scsi_proc_host_rm(shost); spin_lock_irqsave(shost->host_lock, flags); diff --git a/drivers/scsi/pcmcia/aha152x_stub.c b/drivers/scsi/pcmcia/aha152x_stub.c index 67cde0138061..528733b4a392 100644 --- a/drivers/scsi/pcmcia/aha152x_stub.c +++ b/drivers/scsi/pcmcia/aha152x_stub.c @@ -54,15 +54,6 @@ #include <pcmcia/cistpl.h> #include <pcmcia/ds.h> -#ifdef PCMCIA_DEBUG -static int pc_debug = PCMCIA_DEBUG; -module_param(pc_debug, int, 0644); -#define DEBUG(n, args...) if (pc_debug>(n)) printk(KERN_DEBUG args) -static char *version = -"aha152x_cs.c 1.54 2000/06/12 21:27:25 (David Hinds)"; -#else -#define DEBUG(n, args...) -#endif /*====================================================================*/ @@ -103,7 +94,7 @@ static int aha152x_probe(struct pcmcia_device *link) { scsi_info_t *info; - DEBUG(0, "aha152x_attach()\n"); + dev_dbg(&link->dev, "aha152x_attach()\n"); /* Create new SCSI device */ info = kzalloc(sizeof(*info), GFP_KERNEL); @@ -115,7 +106,6 @@ static int aha152x_probe(struct pcmcia_device *link) link->io.Attributes1 = IO_DATA_PATH_WIDTH_AUTO; link->io.IOAddrLines = 10; link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; link->conf.Attributes = CONF_ENABLE_IRQ; link->conf.IntType = INT_MEMORY_AND_IO; link->conf.Present = PRESENT_OPTION; @@ -127,7 +117,7 @@ static int aha152x_probe(struct pcmcia_device *link) static void aha152x_detach(struct pcmcia_device *link) { - DEBUG(0, "aha152x_detach(0x%p)\n", link); + dev_dbg(&link->dev, "aha152x_detach\n"); aha152x_release_cs(link); @@ -137,9 +127,6 @@ static void aha152x_detach(struct pcmcia_device *link) /*====================================================================*/ -#define CS_CHECK(fn, ret) \ -do { last_fn = (fn); if ((last_ret = (ret)) != 0) goto cs_failed; } while (0) - static int aha152x_config_check(struct pcmcia_device *p_dev, cistpl_cftable_entry_t *cfg, cistpl_cftable_entry_t *dflt, @@ -164,19 +151,22 @@ static int aha152x_config_cs(struct pcmcia_device *link) { scsi_info_t *info = link->priv; struct aha152x_setup s; - int last_ret, last_fn; + int ret; struct Scsi_Host *host; - DEBUG(0, "aha152x_config(0x%p)\n", link); + dev_dbg(&link->dev, "aha152x_config\n"); - last_ret = pcmcia_loop_config(link, aha152x_config_check, NULL); - if (last_ret) { - cs_error(link, RequestIO, last_ret); - goto failed; - } + ret = pcmcia_loop_config(link, aha152x_config_check, NULL); + if (ret) + goto failed; - CS_CHECK(RequestIRQ, pcmcia_request_irq(link, &link->irq)); - CS_CHECK(RequestConfiguration, pcmcia_request_configuration(link, &link->conf)); + ret = pcmcia_request_irq(link, &link->irq); + if (ret) + goto failed; + + ret = pcmcia_request_configuration(link, &link->conf); + if (ret) + goto failed; /* Set configuration options for the aha152x driver */ memset(&s, 0, sizeof(s)); @@ -194,7 +184,7 @@ static int aha152x_config_cs(struct pcmcia_device *link) host = aha152x_probe_one(&s); if (host == NULL) { printk(KERN_INFO "aha152x_cs: no SCSI devices found\n"); - goto cs_failed; + goto failed; } sprintf(info->node.dev_name, "scsi%d", host->host_no); @@ -203,8 +193,6 @@ static int aha152x_config_cs(struct pcmcia_device *link) return 0; -cs_failed: - cs_error(link, last_fn, last_ret); failed: aha152x_release_cs(link); return -ENODEV; diff --git a/drivers/scsi/pcmcia/fdomain_stub.c b/drivers/scsi/pcmcia/fdomain_stub.c index 06254f46a0dd..914040684079 100644 --- a/drivers/scsi/pcmcia/fdomain_stub.c +++ b/drivers/scsi/pcmcia/fdomain_stub.c @@ -59,16 +59,6 @@ MODULE_AUTHOR("David Hinds <dahinds@users.sourceforge.net>"); MODULE_DESCRIPTION("Future Domain PCMCIA SCSI driver"); MODULE_LICENSE("Dual MPL/GPL"); -#ifdef PCMCIA_DEBUG -static int pc_debug = PCMCIA_DEBUG; -module_param(pc_debug, int, 0); -#define DEBUG(n, args...) if (pc_debug>(n)) printk(KERN_DEBUG args) -static char *version = -"fdomain_cs.c 1.47 2001/10/13 00:08:52 (David Hinds)"; -#else -#define DEBUG(n, args...) -#endif - /*====================================================================*/ typedef struct scsi_info_t { @@ -86,7 +76,7 @@ static int fdomain_probe(struct pcmcia_device *link) { scsi_info_t *info; - DEBUG(0, "fdomain_attach()\n"); + dev_dbg(&link->dev, "fdomain_attach()\n"); /* Create new SCSI device */ info = kzalloc(sizeof(*info), GFP_KERNEL); @@ -99,7 +89,6 @@ static int fdomain_probe(struct pcmcia_device *link) link->io.Attributes1 = IO_DATA_PATH_WIDTH_AUTO; link->io.IOAddrLines = 10; link->irq.Attributes = IRQ_TYPE_EXCLUSIVE; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; link->conf.Attributes = CONF_ENABLE_IRQ; link->conf.IntType = INT_MEMORY_AND_IO; link->conf.Present = PRESENT_OPTION; @@ -111,7 +100,7 @@ static int fdomain_probe(struct pcmcia_device *link) static void fdomain_detach(struct pcmcia_device *link) { - DEBUG(0, "fdomain_detach(0x%p)\n", link); + dev_dbg(&link->dev, "fdomain_detach\n"); fdomain_release(link); @@ -120,9 +109,6 @@ static void fdomain_detach(struct pcmcia_device *link) /*====================================================================*/ -#define CS_CHECK(fn, ret) \ -do { last_fn = (fn); if ((last_ret = (ret)) != 0) goto cs_failed; } while (0) - static int fdomain_config_check(struct pcmcia_device *p_dev, cistpl_cftable_entry_t *cfg, cistpl_cftable_entry_t *dflt, @@ -137,20 +123,22 @@ static int fdomain_config_check(struct pcmcia_device *p_dev, static int fdomain_config(struct pcmcia_device *link) { scsi_info_t *info = link->priv; - int last_ret, last_fn; + int ret; char str[22]; struct Scsi_Host *host; - DEBUG(0, "fdomain_config(0x%p)\n", link); + dev_dbg(&link->dev, "fdomain_config\n"); - last_ret = pcmcia_loop_config(link, fdomain_config_check, NULL); - if (last_ret) { - cs_error(link, RequestIO, last_ret); + ret = pcmcia_loop_config(link, fdomain_config_check, NULL); + if (ret) goto failed; - } - CS_CHECK(RequestIRQ, pcmcia_request_irq(link, &link->irq)); - CS_CHECK(RequestConfiguration, pcmcia_request_configuration(link, &link->conf)); + ret = pcmcia_request_irq(link, &link->irq); + if (ret) + goto failed; + ret = pcmcia_request_configuration(link, &link->conf); + if (ret) + goto failed; /* A bad hack... */ release_region(link->io.BasePort1, link->io.NumPorts1); @@ -162,11 +150,11 @@ static int fdomain_config(struct pcmcia_device *link) host = __fdomain_16x0_detect(&fdomain_driver_template); if (!host) { printk(KERN_INFO "fdomain_cs: no SCSI devices found\n"); - goto cs_failed; + goto failed; } if (scsi_add_host(host, NULL)) - goto cs_failed; + goto failed; scsi_scan_host(host); sprintf(info->node.dev_name, "scsi%d", host->host_no); @@ -175,8 +163,6 @@ static int fdomain_config(struct pcmcia_device *link) return 0; -cs_failed: - cs_error(link, last_fn, last_ret); failed: fdomain_release(link); return -ENODEV; @@ -188,7 +174,7 @@ static void fdomain_release(struct pcmcia_device *link) { scsi_info_t *info = link->priv; - DEBUG(0, "fdomain_release(0x%p)\n", link); + dev_dbg(&link->dev, "fdomain_release\n"); scsi_remove_host(info->host); pcmcia_disable_device(link); diff --git a/drivers/scsi/pcmcia/nsp_cs.c b/drivers/scsi/pcmcia/nsp_cs.c index e32c344d7ad8..c2341af587a3 100644 --- a/drivers/scsi/pcmcia/nsp_cs.c +++ b/drivers/scsi/pcmcia/nsp_cs.c @@ -1564,12 +1564,10 @@ static int nsp_cs_probe(struct pcmcia_device *link) link->io.IOAddrLines = 10; /* not used */ /* Interrupt setup */ - link->irq.Attributes = IRQ_TYPE_EXCLUSIVE | IRQ_HANDLE_PRESENT; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; + link->irq.Attributes = IRQ_TYPE_EXCLUSIVE; /* Interrupt handler */ link->irq.Handler = &nspintr; - link->irq.Instance = info; link->irq.Attributes |= IRQF_SHARED; /* General socket configuration */ @@ -1684,10 +1682,10 @@ static int nsp_cs_config_check(struct pcmcia_device *p_dev, if (cfg_mem->req.Size < 0x1000) cfg_mem->req.Size = 0x1000; cfg_mem->req.AccessSpeed = 0; - if (pcmcia_request_window(&p_dev, &cfg_mem->req, &p_dev->win) != 0) + if (pcmcia_request_window(p_dev, &cfg_mem->req, &p_dev->win) != 0) goto next_entry; map.Page = 0; map.CardOffset = mem->win[0].card_addr; - if (pcmcia_map_mem_page(p_dev->win, &map) != 0) + if (pcmcia_map_mem_page(p_dev, p_dev->win, &map) != 0) goto next_entry; cfg_mem->data->MmioAddress = (unsigned long) ioremap_nocache(cfg_mem->req.Base, cfg_mem->req.Size); diff --git a/drivers/scsi/pcmcia/qlogic_stub.c b/drivers/scsi/pcmcia/qlogic_stub.c index 20c3e5e6d88a..f85f094870b4 100644 --- a/drivers/scsi/pcmcia/qlogic_stub.c +++ b/drivers/scsi/pcmcia/qlogic_stub.c @@ -62,15 +62,6 @@ static char qlogic_name[] = "qlogic_cs"; -#ifdef PCMCIA_DEBUG -static int pc_debug = PCMCIA_DEBUG; -module_param(pc_debug, int, 0644); -#define DEBUG(n, args...) if (pc_debug>(n)) printk(KERN_DEBUG args) -static char *version = "qlogic_cs.c 1.79-ac 2002/10/26 (David Hinds)"; -#else -#define DEBUG(n, args...) -#endif - static struct scsi_host_template qlogicfas_driver_template = { .module = THIS_MODULE, .name = qlogic_name, @@ -159,7 +150,7 @@ static int qlogic_probe(struct pcmcia_device *link) { scsi_info_t *info; - DEBUG(0, "qlogic_attach()\n"); + dev_dbg(&link->dev, "qlogic_attach()\n"); /* Create new SCSI device */ info = kzalloc(sizeof(*info), GFP_KERNEL); @@ -171,7 +162,6 @@ static int qlogic_probe(struct pcmcia_device *link) link->io.Attributes1 = IO_DATA_PATH_WIDTH_AUTO; link->io.IOAddrLines = 10; link->irq.Attributes = IRQ_TYPE_EXCLUSIVE; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; link->conf.Attributes = CONF_ENABLE_IRQ; link->conf.IntType = INT_MEMORY_AND_IO; link->conf.Present = PRESENT_OPTION; @@ -183,7 +173,7 @@ static int qlogic_probe(struct pcmcia_device *link) static void qlogic_detach(struct pcmcia_device *link) { - DEBUG(0, "qlogic_detach(0x%p)\n", link); + dev_dbg(&link->dev, "qlogic_detach\n"); qlogic_release(link); kfree(link->priv); @@ -192,9 +182,6 @@ static void qlogic_detach(struct pcmcia_device *link) /*====================================================================*/ -#define CS_CHECK(fn, ret) \ -do { last_fn = (fn); if ((last_ret = (ret)) != 0) goto cs_failed; } while (0) - static int qlogic_config_check(struct pcmcia_device *p_dev, cistpl_cftable_entry_t *cfg, cistpl_cftable_entry_t *dflt, @@ -213,19 +200,22 @@ static int qlogic_config_check(struct pcmcia_device *p_dev, static int qlogic_config(struct pcmcia_device * link) { scsi_info_t *info = link->priv; - int last_ret, last_fn; + int ret; struct Scsi_Host *host; - DEBUG(0, "qlogic_config(0x%p)\n", link); + dev_dbg(&link->dev, "qlogic_config\n"); - last_ret = pcmcia_loop_config(link, qlogic_config_check, NULL); - if (last_ret) { - cs_error(link, RequestIO, last_ret); + ret = pcmcia_loop_config(link, qlogic_config_check, NULL); + if (ret) + goto failed; + + ret = pcmcia_request_irq(link, &link->irq); + if (ret) goto failed; - } - CS_CHECK(RequestIRQ, pcmcia_request_irq(link, &link->irq)); - CS_CHECK(RequestConfiguration, pcmcia_request_configuration(link, &link->conf)); + ret = pcmcia_request_configuration(link, &link->conf); + if (ret) + goto failed; if ((info->manf_id == MANFID_MACNICA) || (info->manf_id == MANFID_PIONEER) || (info->manf_id == 0x0098)) { /* set ATAcmd */ @@ -244,7 +234,7 @@ static int qlogic_config(struct pcmcia_device * link) if (!host) { printk(KERN_INFO "%s: no SCSI devices found\n", qlogic_name); - goto cs_failed; + goto failed; } sprintf(info->node.dev_name, "scsi%d", host->host_no); @@ -253,12 +243,9 @@ static int qlogic_config(struct pcmcia_device * link) return 0; -cs_failed: - cs_error(link, last_fn, last_ret); - pcmcia_disable_device(link); failed: + pcmcia_disable_device(link); return -ENODEV; - } /* qlogic_config */ /*====================================================================*/ @@ -267,7 +254,7 @@ static void qlogic_release(struct pcmcia_device *link) { scsi_info_t *info = link->priv; - DEBUG(0, "qlogic_release(0x%p)\n", link); + dev_dbg(&link->dev, "qlogic_release\n"); scsi_remove_host(info->host); diff --git a/drivers/scsi/pcmcia/sym53c500_cs.c b/drivers/scsi/pcmcia/sym53c500_cs.c index b330c11a1752..e7564d8f0cbf 100644 --- a/drivers/scsi/pcmcia/sym53c500_cs.c +++ b/drivers/scsi/pcmcia/sym53c500_cs.c @@ -77,17 +77,6 @@ #include <pcmcia/ds.h> #include <pcmcia/ciscode.h> -/* ================================================================== */ - -#ifdef PCMCIA_DEBUG -static int pc_debug = PCMCIA_DEBUG; -module_param(pc_debug, int, 0); -#define DEBUG(n, args...) if (pc_debug>(n)) printk(KERN_DEBUG args) -static char *version = -"sym53c500_cs.c 0.9c 2004/10/27 (Bob Tracy)"; -#else -#define DEBUG(n, args...) -#endif /* ================================================================== */ @@ -525,7 +514,7 @@ SYM53C500_release(struct pcmcia_device *link) struct scsi_info_t *info = link->priv; struct Scsi_Host *shost = info->host; - DEBUG(0, "SYM53C500_release(0x%p)\n", link); + dev_dbg(&link->dev, "SYM53C500_release\n"); /* * Do this before releasing/freeing resources. @@ -697,9 +686,6 @@ static struct scsi_host_template sym53c500_driver_template = { .shost_attrs = SYM53C500_shost_attrs }; -#define CS_CHECK(fn, ret) \ -do { last_fn = (fn); if ((last_ret = (ret)) != 0) goto cs_failed; } while (0) - static int SYM53C500_config_check(struct pcmcia_device *p_dev, cistpl_cftable_entry_t *cfg, cistpl_cftable_entry_t *dflt, @@ -719,24 +705,27 @@ static int SYM53C500_config(struct pcmcia_device *link) { struct scsi_info_t *info = link->priv; - int last_ret, last_fn; + int ret; int irq_level, port_base; struct Scsi_Host *host; struct scsi_host_template *tpnt = &sym53c500_driver_template; struct sym53c500_data *data; - DEBUG(0, "SYM53C500_config(0x%p)\n", link); + dev_dbg(&link->dev, "SYM53C500_config\n"); info->manf_id = link->manf_id; - last_ret = pcmcia_loop_config(link, SYM53C500_config_check, NULL); - if (last_ret) { - cs_error(link, RequestIO, last_ret); + ret = pcmcia_loop_config(link, SYM53C500_config_check, NULL); + if (ret) + goto failed; + + ret = pcmcia_request_irq(link, &link->irq); + if (ret) goto failed; - } - CS_CHECK(RequestIRQ, pcmcia_request_irq(link, &link->irq)); - CS_CHECK(RequestConfiguration, pcmcia_request_configuration(link, &link->conf)); + ret = pcmcia_request_configuration(link, &link->conf); + if (ret) + goto failed; /* * That's the trouble with copying liberally from another driver. @@ -824,8 +813,6 @@ err_release: printk(KERN_INFO "sym53c500_cs: no SCSI devices found\n"); return -ENODEV; -cs_failed: - cs_error(link, last_fn, last_ret); failed: SYM53C500_release(link); return -ENODEV; @@ -855,7 +842,7 @@ static int sym53c500_resume(struct pcmcia_device *link) static void SYM53C500_detach(struct pcmcia_device *link) { - DEBUG(0, "SYM53C500_detach(0x%p)\n", link); + dev_dbg(&link->dev, "SYM53C500_detach\n"); SYM53C500_release(link); @@ -868,7 +855,7 @@ SYM53C500_probe(struct pcmcia_device *link) { struct scsi_info_t *info; - DEBUG(0, "SYM53C500_attach()\n"); + dev_dbg(&link->dev, "SYM53C500_attach()\n"); /* Create new SCSI device */ info = kzalloc(sizeof(*info), GFP_KERNEL); @@ -880,7 +867,6 @@ SYM53C500_probe(struct pcmcia_device *link) link->io.Attributes1 = IO_DATA_PATH_WIDTH_AUTO; link->io.IOAddrLines = 10; link->irq.Attributes = IRQ_TYPE_EXCLUSIVE; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; link->conf.Attributes = CONF_ENABLE_IRQ; link->conf.IntType = INT_MEMORY_AND_IO; diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index 0547a7f44d42..47291bcff0d5 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -952,16 +952,6 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result, return SCSI_SCAN_LUN_PRESENT; } -static inline void scsi_destroy_sdev(struct scsi_device *sdev) -{ - scsi_device_set_state(sdev, SDEV_DEL); - if (sdev->host->hostt->slave_destroy) - sdev->host->hostt->slave_destroy(sdev); - transport_destroy_device(&sdev->sdev_gendev); - put_device(&sdev->sdev_dev); - put_device(&sdev->sdev_gendev); -} - #ifdef CONFIG_SCSI_LOGGING /** * scsi_inq_str - print INQUIRY data from min to max index, strip trailing whitespace @@ -1139,7 +1129,7 @@ static int scsi_probe_and_add_lun(struct scsi_target *starget, } } } else - scsi_destroy_sdev(sdev); + __scsi_remove_device(sdev); out: return res; } @@ -1500,7 +1490,7 @@ static int scsi_report_lun_scan(struct scsi_target *starget, int bflags, /* * the sdev we used didn't appear in the report luns scan */ - scsi_destroy_sdev(sdev); + __scsi_remove_device(sdev); return ret; } @@ -1710,7 +1700,7 @@ static void scsi_sysfs_add_devices(struct Scsi_Host *shost) shost_for_each_device(sdev, shost) { if (!scsi_host_scan_allowed(shost) || scsi_sysfs_add_sdev(sdev) != 0) - scsi_destroy_sdev(sdev); + __scsi_remove_device(sdev); } } @@ -1943,7 +1933,7 @@ void scsi_free_host_dev(struct scsi_device *sdev) { BUG_ON(sdev->id != sdev->host->this_id); - scsi_destroy_sdev(sdev); + __scsi_remove_device(sdev); } EXPORT_SYMBOL(scsi_free_host_dev); diff --git a/drivers/scsi/scsi_sysctl.c b/drivers/scsi/scsi_sysctl.c index 63a30f566f3a..2b6b93f7d8ef 100644 --- a/drivers/scsi/scsi_sysctl.c +++ b/drivers/scsi/scsi_sysctl.c @@ -13,26 +13,23 @@ static ctl_table scsi_table[] = { - { .ctl_name = DEV_SCSI_LOGGING_LEVEL, - .procname = "logging_level", + { .procname = "logging_level", .data = &scsi_logging_level, .maxlen = sizeof(scsi_logging_level), .mode = 0644, - .proc_handler = &proc_dointvec }, + .proc_handler = proc_dointvec }, { } }; static ctl_table scsi_dir_table[] = { - { .ctl_name = DEV_SCSI, - .procname = "scsi", + { .procname = "scsi", .mode = 0555, .child = scsi_table }, { } }; static ctl_table scsi_root_table[] = { - { .ctl_name = CTL_DEV, - .procname = "dev", + { .procname = "dev", .mode = 0555, .child = scsi_dir_table }, { } diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 5c7eb63a19d1..392d8db33905 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -854,82 +854,73 @@ int scsi_sysfs_add_sdev(struct scsi_device *sdev) transport_configure_device(&starget->dev); error = device_add(&sdev->sdev_gendev); if (error) { - put_device(sdev->sdev_gendev.parent); printk(KERN_INFO "error 1\n"); - return error; + goto out_remove; } error = device_add(&sdev->sdev_dev); if (error) { printk(KERN_INFO "error 2\n"); - goto clean_device; + device_del(&sdev->sdev_gendev); + goto out_remove; } + transport_add_device(&sdev->sdev_gendev); + sdev->is_visible = 1; /* create queue files, which may be writable, depending on the host */ if (sdev->host->hostt->change_queue_depth) error = device_create_file(&sdev->sdev_gendev, &sdev_attr_queue_depth_rw); else error = device_create_file(&sdev->sdev_gendev, &dev_attr_queue_depth); - if (error) { - __scsi_remove_device(sdev); - goto out; - } + if (error) + goto out_remove; + if (sdev->host->hostt->change_queue_type) error = device_create_file(&sdev->sdev_gendev, &sdev_attr_queue_type_rw); else error = device_create_file(&sdev->sdev_gendev, &dev_attr_queue_type); - if (error) { - __scsi_remove_device(sdev); - goto out; - } + if (error) + goto out_remove; error = bsg_register_queue(rq, &sdev->sdev_gendev, NULL, NULL); if (error) + /* we're treating error on bsg register as non-fatal, + * so pretend nothing went wrong */ sdev_printk(KERN_INFO, sdev, "Failed to register bsg queue, errno=%d\n", error); - /* we're treating error on bsg register as non-fatal, so pretend - * nothing went wrong */ - error = 0; - /* add additional host specific attributes */ if (sdev->host->hostt->sdev_attrs) { for (i = 0; sdev->host->hostt->sdev_attrs[i]; i++) { error = device_create_file(&sdev->sdev_gendev, sdev->host->hostt->sdev_attrs[i]); - if (error) { - __scsi_remove_device(sdev); - goto out; - } + if (error) + goto out_remove; } } - transport_add_device(&sdev->sdev_gendev); - out: - return error; - - clean_device: - scsi_device_set_state(sdev, SDEV_CANCEL); - - device_del(&sdev->sdev_gendev); - transport_destroy_device(&sdev->sdev_gendev); - put_device(&sdev->sdev_dev); - put_device(&sdev->sdev_gendev); + return 0; + out_remove: + __scsi_remove_device(sdev); return error; + } void __scsi_remove_device(struct scsi_device *sdev) { struct device *dev = &sdev->sdev_gendev; - if (scsi_device_set_state(sdev, SDEV_CANCEL) != 0) - return; + if (sdev->is_visible) { + if (scsi_device_set_state(sdev, SDEV_CANCEL) != 0) + return; - bsg_unregister_queue(sdev->request_queue); - device_unregister(&sdev->sdev_dev); - transport_remove_device(dev); - device_del(dev); + bsg_unregister_queue(sdev->request_queue); + device_unregister(&sdev->sdev_dev); + transport_remove_device(dev); + device_del(dev); + } else + put_device(&sdev->sdev_dev); scsi_device_set_state(sdev, SDEV_DEL); if (sdev->host->hostt->slave_destroy) sdev->host->hostt->slave_destroy(sdev); diff --git a/drivers/scsi/sd_dif.c b/drivers/scsi/sd_dif.c index 88da97745710..84be62149c6c 100644 --- a/drivers/scsi/sd_dif.c +++ b/drivers/scsi/sd_dif.c @@ -418,7 +418,7 @@ error: __func__, virt, phys, be32_to_cpu(sdt->ref_tag), be16_to_cpu(sdt->app_tag)); - return -EIO; + return -EILSEQ; } /* diff --git a/drivers/serial/bcm63xx_uart.c b/drivers/serial/bcm63xx_uart.c index beddaa6e9069..37ad0c449937 100644 --- a/drivers/serial/bcm63xx_uart.c +++ b/drivers/serial/bcm63xx_uart.c @@ -242,7 +242,7 @@ static void bcm_uart_do_rx(struct uart_port *port) * higher than fifo size anyway since we're much faster than * serial port */ max_count = 32; - tty = port->info->port.tty; + tty = port->state->port.tty; do { unsigned int iestat, c, cstat; char flag; @@ -318,7 +318,7 @@ static void bcm_uart_do_tx(struct uart_port *port) return; } - xmit = &port->info->xmit; + xmit = &port->state->xmit; if (uart_circ_empty(xmit)) goto txq_empty; diff --git a/drivers/serial/of_serial.c b/drivers/serial/of_serial.c index 02406ba6da1c..cdf172eda2e3 100644 --- a/drivers/serial/of_serial.c +++ b/drivers/serial/of_serial.c @@ -161,6 +161,7 @@ static int of_platform_serial_remove(struct of_device *ofdev) static struct of_device_id __devinitdata of_platform_serial_table[] = { { .type = "serial", .compatible = "ns8250", .data = (void *)PORT_8250, }, { .type = "serial", .compatible = "ns16450", .data = (void *)PORT_16450, }, + { .type = "serial", .compatible = "ns16550a", .data = (void *)PORT_16550A, }, { .type = "serial", .compatible = "ns16550", .data = (void *)PORT_16550, }, { .type = "serial", .compatible = "ns16750", .data = (void *)PORT_16750, }, { .type = "serial", .compatible = "ns16850", .data = (void *)PORT_16850, }, diff --git a/drivers/serial/serial_cs.c b/drivers/serial/serial_cs.c index 7c7914f5fa02..fc413f0f8dd2 100644 --- a/drivers/serial/serial_cs.c +++ b/drivers/serial/serial_cs.c @@ -54,14 +54,6 @@ #include "8250.h" -#ifdef PCMCIA_DEBUG -static int pc_debug = PCMCIA_DEBUG; -module_param(pc_debug, int, 0644); -#define DEBUG(n, args...) if (pc_debug>(n)) printk(KERN_DEBUG args) -static char *version = "serial_cs.c 1.134 2002/05/04 05:48:53 (David Hinds)"; -#else -#define DEBUG(n, args...) -#endif /*====================================================================*/ @@ -121,24 +113,20 @@ static void quirk_setup_brainboxes_0104(struct pcmcia_device *link, struct uart_ static int quirk_post_ibm(struct pcmcia_device *link) { conf_reg_t reg = { 0, CS_READ, 0x800, 0 }; - int last_ret, last_fn; + int ret; + + ret = pcmcia_access_configuration_register(link, ®); + if (ret) + goto failed; - last_ret = pcmcia_access_configuration_register(link, ®); - if (last_ret) { - last_fn = AccessConfigurationRegister; - goto cs_failed; - } reg.Action = CS_WRITE; reg.Value = reg.Value | 1; - last_ret = pcmcia_access_configuration_register(link, ®); - if (last_ret) { - last_fn = AccessConfigurationRegister; - goto cs_failed; - } + ret = pcmcia_access_configuration_register(link, ®); + if (ret) + goto failed; return 0; - cs_failed: - cs_error(link, last_fn, last_ret); + failed: return -ENODEV; } @@ -283,7 +271,7 @@ static void serial_remove(struct pcmcia_device *link) struct serial_info *info = link->priv; int i; - DEBUG(0, "serial_release(0x%p)\n", link); + dev_dbg(&link->dev, "serial_release\n"); /* * Recheck to see if the device is still configured. @@ -334,7 +322,7 @@ static int serial_probe(struct pcmcia_device *link) { struct serial_info *info; - DEBUG(0, "serial_attach()\n"); + dev_dbg(&link->dev, "serial_attach()\n"); /* Create new serial device */ info = kzalloc(sizeof (*info), GFP_KERNEL); @@ -346,7 +334,6 @@ static int serial_probe(struct pcmcia_device *link) link->io.Attributes1 = IO_DATA_PATH_WIDTH_8; link->io.NumPorts1 = 8; link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; link->conf.Attributes = CONF_ENABLE_IRQ; if (do_sound) { link->conf.Attributes |= CONF_ENABLE_SPKR; @@ -370,7 +357,7 @@ static void serial_detach(struct pcmcia_device *link) { struct serial_info *info = link->priv; - DEBUG(0, "serial_detach(0x%p)\n", link); + dev_dbg(&link->dev, "serial_detach\n"); /* * Ensure any outstanding scheduled tasks are completed. @@ -399,7 +386,7 @@ static int setup_serial(struct pcmcia_device *handle, struct serial_info * info, port.irq = irq; port.flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST | UPF_SHARE_IRQ; port.uartclk = 1843200; - port.dev = &handle_to_dev(handle); + port.dev = &handle->dev; if (buggy_uart) port.flags |= UPF_BUGGY_UART; @@ -426,21 +413,6 @@ static int setup_serial(struct pcmcia_device *handle, struct serial_info * info, /*====================================================================*/ -static int -first_tuple(struct pcmcia_device *handle, tuple_t * tuple, cisparse_t * parse) -{ - int i; - i = pcmcia_get_first_tuple(handle, tuple); - if (i != 0) - return i; - i = pcmcia_get_tuple_data(handle, tuple); - if (i != 0) - return i; - return pcmcia_parse_tuple(tuple, parse); -} - -/*====================================================================*/ - static int simple_config_check(struct pcmcia_device *p_dev, cistpl_cftable_entry_t *cf, cistpl_cftable_entry_t *dflt, @@ -522,15 +494,13 @@ static int simple_config(struct pcmcia_device *link) printk(KERN_NOTICE "serial_cs: no usable port range found, giving up\n"); - cs_error(link, RequestIO, i); return -1; found_port: i = pcmcia_request_irq(link, &link->irq); - if (i != 0) { - cs_error(link, RequestIRQ, i); + if (i != 0) link->irq.AssignedIRQ = 0; - } + if (info->multi && (info->manfid == MANFID_3COM)) link->conf.ConfigIndex &= ~(0x08); @@ -541,10 +511,8 @@ found_port: info->quirk->config(link); i = pcmcia_request_configuration(link, &link->conf); - if (i != 0) { - cs_error(link, RequestConfiguration, i); + if (i != 0) return -1; - } return setup_serial(link, info, link->io.BasePort1, link->irq.AssignedIRQ); } @@ -613,7 +581,6 @@ static int multi_config(struct pcmcia_device *link) /* FIXME: comment does not fit, error handling does not fit */ printk(KERN_NOTICE "serial_cs: no usable port range found, giving up\n"); - cs_error(link, RequestIRQ, i); link->irq.AssignedIRQ = 0; } @@ -624,10 +591,8 @@ static int multi_config(struct pcmcia_device *link) info->quirk->config(link); i = pcmcia_request_configuration(link, &link->conf); - if (i != 0) { - cs_error(link, RequestConfiguration, i); + if (i != 0) return -ENODEV; - } /* The Oxford Semiconductor OXCF950 cards are in fact single-port: * 8 registers are for the UART, the others are extra registers. @@ -665,6 +630,25 @@ static int multi_config(struct pcmcia_device *link) return 0; } +static int serial_check_for_multi(struct pcmcia_device *p_dev, + cistpl_cftable_entry_t *cf, + cistpl_cftable_entry_t *dflt, + unsigned int vcc, + void *priv_data) +{ + struct serial_info *info = p_dev->priv; + + if ((cf->io.nwin == 1) && (cf->io.win[0].len % 8 == 0)) + info->multi = cf->io.win[0].len >> 3; + + if ((cf->io.nwin == 2) && (cf->io.win[0].len == 8) && + (cf->io.win[1].len == 8)) + info->multi = 2; + + return 0; /* break */ +} + + /*====================================================================== serial_config() is scheduled to run after a CARD_INSERTION event @@ -676,46 +660,14 @@ static int multi_config(struct pcmcia_device *link) static int serial_config(struct pcmcia_device * link) { struct serial_info *info = link->priv; - struct serial_cfg_mem *cfg_mem; - tuple_t *tuple; - u_char *buf; - cisparse_t *parse; - cistpl_cftable_entry_t *cf; - int i, last_ret, last_fn; - - DEBUG(0, "serial_config(0x%p)\n", link); - - cfg_mem = kmalloc(sizeof(struct serial_cfg_mem), GFP_KERNEL); - if (!cfg_mem) - goto failed; + int i; - tuple = &cfg_mem->tuple; - parse = &cfg_mem->parse; - cf = &parse->cftable_entry; - buf = cfg_mem->buf; - - tuple->TupleData = (cisdata_t *) buf; - tuple->TupleOffset = 0; - tuple->TupleDataMax = 255; - tuple->Attributes = 0; - - /* Get configuration register information */ - tuple->DesiredTuple = CISTPL_CONFIG; - last_ret = first_tuple(link, tuple, parse); - if (last_ret != 0) { - last_fn = ParseTuple; - goto cs_failed; - } - link->conf.ConfigBase = parse->config.base; - link->conf.Present = parse->config.rmask[0]; + dev_dbg(&link->dev, "serial_config\n"); /* Is this a compliant multifunction card? */ - tuple->DesiredTuple = CISTPL_LONGLINK_MFC; - tuple->Attributes = TUPLE_RETURN_COMMON | TUPLE_RETURN_LINK; - info->multi = (first_tuple(link, tuple, parse) == 0); + info->multi = (link->socket->functions > 1); /* Is this a multiport card? */ - tuple->DesiredTuple = CISTPL_MANFID; info->manfid = link->manf_id; info->prodid = link->card_id; @@ -730,20 +682,11 @@ static int serial_config(struct pcmcia_device * link) /* Another check for dual-serial cards: look for either serial or multifunction cards that ask for appropriate IO port ranges */ - tuple->DesiredTuple = CISTPL_FUNCID; if ((info->multi == 0) && (link->has_func_id) && ((link->func_id == CISTPL_FUNCID_MULTI) || - (link->func_id == CISTPL_FUNCID_SERIAL))) { - tuple->DesiredTuple = CISTPL_CFTABLE_ENTRY; - if (first_tuple(link, tuple, parse) == 0) { - if ((cf->io.nwin == 1) && (cf->io.win[0].len % 8 == 0)) - info->multi = cf->io.win[0].len >> 3; - if ((cf->io.nwin == 2) && (cf->io.win[0].len == 8) && - (cf->io.win[1].len == 8)) - info->multi = 2; - } - } + (link->func_id == CISTPL_FUNCID_SERIAL))) + pcmcia_loop_config(link, serial_check_for_multi, info); /* * Apply any multi-port quirk. @@ -768,14 +711,10 @@ static int serial_config(struct pcmcia_device * link) goto failed; link->dev_node = &info->node[0]; - kfree(cfg_mem); return 0; -cs_failed: - cs_error(link, last_fn, last_ret); failed: serial_remove(link); - kfree(cfg_mem); return -ENODEV; } diff --git a/drivers/serial/suncore.c b/drivers/serial/suncore.c index a2d4a19550ab..ed7d958b0a01 100644 --- a/drivers/serial/suncore.c +++ b/drivers/serial/suncore.c @@ -53,20 +53,21 @@ void sunserial_unregister_minors(struct uart_driver *drv, int count) EXPORT_SYMBOL(sunserial_unregister_minors); int sunserial_console_match(struct console *con, struct device_node *dp, - struct uart_driver *drv, int line) + struct uart_driver *drv, int line, bool ignore_line) { - int off; - if (!con || of_console_device != dp) return 0; - off = 0; - if (of_console_options && - *of_console_options == 'b') - off = 1; + if (!ignore_line) { + int off = 0; - if ((line & 1) != off) - return 0; + if (of_console_options && + *of_console_options == 'b') + off = 1; + + if ((line & 1) != off) + return 0; + } con->index = line; drv->cons = con; @@ -76,23 +77,24 @@ int sunserial_console_match(struct console *con, struct device_node *dp, } EXPORT_SYMBOL(sunserial_console_match); -void -sunserial_console_termios(struct console *con) +void sunserial_console_termios(struct console *con, struct device_node *uart_dp) { - struct device_node *dp; - const char *od, *mode, *s; + const char *mode, *s; char mode_prop[] = "ttyX-mode"; int baud, bits, stop, cflag; char parity; - dp = of_find_node_by_path("/options"); - od = of_get_property(dp, "output-device", NULL); - if (!strcmp(od, "rsc")) { - mode = of_get_property(of_console_device, + if (!strcmp(uart_dp->name, "rsc") || + !strcmp(uart_dp->name, "rsc-console") || + !strcmp(uart_dp->name, "rsc-control")) { + mode = of_get_property(uart_dp, "ssp-console-modes", NULL); if (!mode) mode = "115200,8,n,1,-"; + } else if (!strcmp(uart_dp->name, "lom-console")) { + mode = "9600,8,n,1,-"; } else { + struct device_node *dp; char c; c = 'a'; @@ -101,6 +103,7 @@ sunserial_console_termios(struct console *con) mode_prop[3] = c; + dp = of_find_node_by_path("/options"); mode = of_get_property(dp, mode_prop, NULL); if (!mode) mode = "9600,8,n,1,-"; diff --git a/drivers/serial/suncore.h b/drivers/serial/suncore.h index 042668aa602e..db2057936c31 100644 --- a/drivers/serial/suncore.h +++ b/drivers/serial/suncore.h @@ -26,7 +26,8 @@ extern int sunserial_register_minors(struct uart_driver *, int); extern void sunserial_unregister_minors(struct uart_driver *, int); extern int sunserial_console_match(struct console *, struct device_node *, - struct uart_driver *, int); -extern void sunserial_console_termios(struct console *); + struct uart_driver *, int, bool); +extern void sunserial_console_termios(struct console *, + struct device_node *); #endif /* !(_SERIAL_SUN_H) */ diff --git a/drivers/serial/sunhv.c b/drivers/serial/sunhv.c index d548652dee50..d14cca7fb88d 100644 --- a/drivers/serial/sunhv.c +++ b/drivers/serial/sunhv.c @@ -566,7 +566,7 @@ static int __devinit hv_probe(struct of_device *op, const struct of_device_id *m goto out_free_con_read_page; sunserial_console_match(&sunhv_console, op->node, - &sunhv_reg, port->line); + &sunhv_reg, port->line, false); err = uart_add_one_port(&sunhv_reg, port); if (err) diff --git a/drivers/serial/sunsab.c b/drivers/serial/sunsab.c index d1ad34128635..d514e28d0755 100644 --- a/drivers/serial/sunsab.c +++ b/drivers/serial/sunsab.c @@ -883,7 +883,7 @@ static int sunsab_console_setup(struct console *con, char *options) printk("Console: ttyS%d (SAB82532)\n", (sunsab_reg.minor - 64) + con->index); - sunserial_console_termios(con); + sunserial_console_termios(con, to_of_device(up->port.dev)->node); switch (con->cflag & CBAUD) { case B150: baud = 150; break; @@ -1027,10 +1027,12 @@ static int __devinit sab_probe(struct of_device *op, const struct of_device_id * goto out1; sunserial_console_match(SUNSAB_CONSOLE(), op->node, - &sunsab_reg, up[0].port.line); + &sunsab_reg, up[0].port.line, + false); sunserial_console_match(SUNSAB_CONSOLE(), op->node, - &sunsab_reg, up[1].port.line); + &sunsab_reg, up[1].port.line, + false); err = uart_add_one_port(&sunsab_reg, &up[0].port); if (err) @@ -1116,7 +1118,6 @@ static int __init sunsab_init(void) if (!sunsab_ports) return -ENOMEM; - sunsab_reg.cons = SUNSAB_CONSOLE(); err = sunserial_register_minors(&sunsab_reg, num_channels); if (err) { kfree(sunsab_ports); diff --git a/drivers/serial/sunsu.c b/drivers/serial/sunsu.c index 68d262b15749..170d3d68c8f0 100644 --- a/drivers/serial/sunsu.c +++ b/drivers/serial/sunsu.c @@ -1329,11 +1329,9 @@ static void sunsu_console_write(struct console *co, const char *s, */ static int __init sunsu_console_setup(struct console *co, char *options) { + static struct ktermios dummy; + struct ktermios termios; struct uart_port *port; - int baud = 9600; - int bits = 8; - int parity = 'n'; - int flow = 'n'; printk("Console: ttyS%d (SU)\n", (sunsu_reg.minor - 64) + co->index); @@ -1352,10 +1350,15 @@ static int __init sunsu_console_setup(struct console *co, char *options) */ spin_lock_init(&port->lock); - if (options) - uart_parse_options(options, &baud, &parity, &bits, &flow); + /* Get firmware console settings. */ + sunserial_console_termios(co, to_of_device(port->dev)->node); - return uart_set_options(port, co, baud, parity, bits, flow); + memset(&termios, 0, sizeof(struct ktermios)); + termios.c_cflag = co->cflag; + port->mctrl |= TIOCM_DTR; + port->ops->set_termios(port, &termios, &dummy); + + return 0; } static struct console sunsu_console = { @@ -1409,6 +1412,7 @@ static int __devinit su_probe(struct of_device *op, const struct of_device_id *m struct uart_sunsu_port *up; struct resource *rp; enum su_type type; + bool ignore_line; int err; type = su_get_type(dp); @@ -1467,8 +1471,14 @@ static int __devinit su_probe(struct of_device *op, const struct of_device_id *m up->port.ops = &sunsu_pops; + ignore_line = false; + if (!strcmp(dp->name, "rsc-console") || + !strcmp(dp->name, "lom-console")) + ignore_line = true; + sunserial_console_match(SUNSU_CONSOLE(), dp, - &sunsu_reg, up->port.line); + &sunsu_reg, up->port.line, + ignore_line); err = uart_add_one_port(&sunsu_reg, &up->port); if (err) goto out_unmap; @@ -1517,6 +1527,10 @@ static const struct of_device_id su_match[] = { .name = "serial", .compatible = "su", }, + { + .type = "serial", + .compatible = "su", + }, {}, }; MODULE_DEVICE_TABLE(of, su_match); @@ -1548,6 +1562,12 @@ static int __init sunsu_init(void) num_uart++; } } + for_each_node_by_type(dp, "serial") { + if (of_device_is_compatible(dp, "su")) { + if (su_get_type(dp) == SU_PORT_PORT) + num_uart++; + } + } if (num_uart) { err = sunserial_register_minors(&sunsu_reg, num_uart); diff --git a/drivers/serial/sunzilog.c b/drivers/serial/sunzilog.c index ef693ae22e7f..2c7a66af4f52 100644 --- a/drivers/serial/sunzilog.c +++ b/drivers/serial/sunzilog.c @@ -1180,7 +1180,7 @@ static int __init sunzilog_console_setup(struct console *con, char *options) (sunzilog_reg.minor - 64) + con->index, con->index); /* Get firmware console settings. */ - sunserial_console_termios(con); + sunserial_console_termios(con, to_of_device(up->port.dev)->node); /* Firmware console speed is limited to 150-->38400 baud so * this hackish cflag thing is OK. @@ -1416,7 +1416,8 @@ static int __devinit zs_probe(struct of_device *op, const struct of_device_id *m if (!keyboard_mouse) { if (sunserial_console_match(SUNZILOG_CONSOLE(), op->node, - &sunzilog_reg, up[0].port.line)) + &sunzilog_reg, up[0].port.line, + false)) up->flags |= SUNZILOG_FLAG_IS_CONS; err = uart_add_one_port(&sunzilog_reg, &up[0].port); if (err) { @@ -1425,7 +1426,8 @@ static int __devinit zs_probe(struct of_device *op, const struct of_device_id *m return err; } if (sunserial_console_match(SUNZILOG_CONSOLE(), op->node, - &sunzilog_reg, up[1].port.line)) + &sunzilog_reg, up[1].port.line, + false)) up->flags |= SUNZILOG_FLAG_IS_CONS; err = uart_add_one_port(&sunzilog_reg, &up[1].port); if (err) { diff --git a/drivers/spi/spi_txx9.c b/drivers/spi/spi_txx9.c index 96057de133ad..19f75627c3de 100644 --- a/drivers/spi/spi_txx9.c +++ b/drivers/spi/spi_txx9.c @@ -29,6 +29,8 @@ #define SPI_FIFO_SIZE 4 +#define SPI_MAX_DIVIDER 0xff /* Max. value for SPCR1.SER */ +#define SPI_MIN_DIVIDER 1 /* Min. value for SPCR1.SER */ #define TXx9_SPMCR 0x00 #define TXx9_SPCR0 0x04 @@ -193,11 +195,8 @@ static void txx9spi_work_one(struct txx9spi *c, struct spi_message *m) if (prev_speed_hz != speed_hz || prev_bits_per_word != bits_per_word) { - u32 n = (c->baseclk + speed_hz - 1) / speed_hz; - if (n < 1) - n = 1; - else if (n > 0xff) - n = 0xff; + int n = DIV_ROUND_UP(c->baseclk, speed_hz) - 1; + n = clamp(n, SPI_MIN_DIVIDER, SPI_MAX_DIVIDER); /* enter config mode */ txx9spi_wr(c, mcr | TXx9_SPMCR_CONFIG | TXx9_SPMCR_BCLR, TXx9_SPMCR); @@ -370,8 +369,8 @@ static int __init txx9spi_probe(struct platform_device *dev) goto exit; } c->baseclk = clk_get_rate(c->clk); - c->min_speed_hz = (c->baseclk + 0xff - 1) / 0xff; - c->max_speed_hz = c->baseclk; + c->min_speed_hz = DIV_ROUND_UP(c->baseclk, SPI_MAX_DIVIDER + 1); + c->max_speed_hz = c->baseclk / (SPI_MIN_DIVIDER + 1); res = platform_get_resource(dev, IORESOURCE_MEM, 0); if (!res) diff --git a/drivers/ssb/pcmcia.c b/drivers/ssb/pcmcia.c index 100e7a5c5ea1..e72f4046a5e0 100644 --- a/drivers/ssb/pcmcia.c +++ b/drivers/ssb/pcmcia.c @@ -617,136 +617,140 @@ static int ssb_pcmcia_sprom_check_crc(const u16 *sprom, size_t size) } \ } while (0) -int ssb_pcmcia_get_invariants(struct ssb_bus *bus, - struct ssb_init_invariants *iv) +static int ssb_pcmcia_get_mac(struct pcmcia_device *p_dev, + tuple_t *tuple, + void *priv) { - tuple_t tuple; - int res; - unsigned char buf[32]; + struct ssb_sprom *sprom = priv; + + if (tuple->TupleData[0] != CISTPL_FUNCE_LAN_NODE_ID) + return -EINVAL; + if (tuple->TupleDataLen != ETH_ALEN + 2) + return -EINVAL; + if (tuple->TupleData[1] != ETH_ALEN) + return -EINVAL; + memcpy(sprom->il0mac, &tuple->TupleData[2], ETH_ALEN); + return 0; +}; + +static int ssb_pcmcia_do_get_invariants(struct pcmcia_device *p_dev, + tuple_t *tuple, + void *priv) +{ + struct ssb_init_invariants *iv = priv; struct ssb_sprom *sprom = &iv->sprom; struct ssb_boardinfo *bi = &iv->boardinfo; const char *error_description; + GOTO_ERROR_ON(tuple->TupleDataLen < 1, "VEN tpl < 1"); + switch (tuple->TupleData[0]) { + case SSB_PCMCIA_CIS_ID: + GOTO_ERROR_ON((tuple->TupleDataLen != 5) && + (tuple->TupleDataLen != 7), + "id tpl size"); + bi->vendor = tuple->TupleData[1] | + ((u16)tuple->TupleData[2] << 8); + break; + case SSB_PCMCIA_CIS_BOARDREV: + GOTO_ERROR_ON(tuple->TupleDataLen != 2, + "boardrev tpl size"); + sprom->board_rev = tuple->TupleData[1]; + break; + case SSB_PCMCIA_CIS_PA: + GOTO_ERROR_ON((tuple->TupleDataLen != 9) && + (tuple->TupleDataLen != 10), + "pa tpl size"); + sprom->pa0b0 = tuple->TupleData[1] | + ((u16)tuple->TupleData[2] << 8); + sprom->pa0b1 = tuple->TupleData[3] | + ((u16)tuple->TupleData[4] << 8); + sprom->pa0b2 = tuple->TupleData[5] | + ((u16)tuple->TupleData[6] << 8); + sprom->itssi_a = tuple->TupleData[7]; + sprom->itssi_bg = tuple->TupleData[7]; + sprom->maxpwr_a = tuple->TupleData[8]; + sprom->maxpwr_bg = tuple->TupleData[8]; + break; + case SSB_PCMCIA_CIS_OEMNAME: + /* We ignore this. */ + break; + case SSB_PCMCIA_CIS_CCODE: + GOTO_ERROR_ON(tuple->TupleDataLen != 2, + "ccode tpl size"); + sprom->country_code = tuple->TupleData[1]; + break; + case SSB_PCMCIA_CIS_ANTENNA: + GOTO_ERROR_ON(tuple->TupleDataLen != 2, + "ant tpl size"); + sprom->ant_available_a = tuple->TupleData[1]; + sprom->ant_available_bg = tuple->TupleData[1]; + break; + case SSB_PCMCIA_CIS_ANTGAIN: + GOTO_ERROR_ON(tuple->TupleDataLen != 2, + "antg tpl size"); + sprom->antenna_gain.ghz24.a0 = tuple->TupleData[1]; + sprom->antenna_gain.ghz24.a1 = tuple->TupleData[1]; + sprom->antenna_gain.ghz24.a2 = tuple->TupleData[1]; + sprom->antenna_gain.ghz24.a3 = tuple->TupleData[1]; + sprom->antenna_gain.ghz5.a0 = tuple->TupleData[1]; + sprom->antenna_gain.ghz5.a1 = tuple->TupleData[1]; + sprom->antenna_gain.ghz5.a2 = tuple->TupleData[1]; + sprom->antenna_gain.ghz5.a3 = tuple->TupleData[1]; + break; + case SSB_PCMCIA_CIS_BFLAGS: + GOTO_ERROR_ON((tuple->TupleDataLen != 3) && + (tuple->TupleDataLen != 5), + "bfl tpl size"); + sprom->boardflags_lo = tuple->TupleData[1] | + ((u16)tuple->TupleData[2] << 8); + break; + case SSB_PCMCIA_CIS_LEDS: + GOTO_ERROR_ON(tuple->TupleDataLen != 5, + "leds tpl size"); + sprom->gpio0 = tuple->TupleData[1]; + sprom->gpio1 = tuple->TupleData[2]; + sprom->gpio2 = tuple->TupleData[3]; + sprom->gpio3 = tuple->TupleData[4]; + break; + } + return -ENOSPC; /* continue with next entry */ + +error: + ssb_printk(KERN_ERR PFX + "PCMCIA: Failed to fetch device invariants: %s\n", + error_description); + return -ENODEV; +} + + +int ssb_pcmcia_get_invariants(struct ssb_bus *bus, + struct ssb_init_invariants *iv) +{ + struct ssb_sprom *sprom = &iv->sprom; + int res; + memset(sprom, 0xFF, sizeof(*sprom)); sprom->revision = 1; sprom->boardflags_lo = 0; sprom->boardflags_hi = 0; /* First fetch the MAC address. */ - memset(&tuple, 0, sizeof(tuple)); - tuple.DesiredTuple = CISTPL_FUNCE; - tuple.TupleData = buf; - tuple.TupleDataMax = sizeof(buf); - res = pcmcia_get_first_tuple(bus->host_pcmcia, &tuple); - GOTO_ERROR_ON(res != 0, "MAC first tpl"); - res = pcmcia_get_tuple_data(bus->host_pcmcia, &tuple); - GOTO_ERROR_ON(res != 0, "MAC first tpl data"); - while (1) { - GOTO_ERROR_ON(tuple.TupleDataLen < 1, "MAC tpl < 1"); - if (tuple.TupleData[0] == CISTPL_FUNCE_LAN_NODE_ID) - break; - res = pcmcia_get_next_tuple(bus->host_pcmcia, &tuple); - GOTO_ERROR_ON(res != 0, "MAC next tpl"); - res = pcmcia_get_tuple_data(bus->host_pcmcia, &tuple); - GOTO_ERROR_ON(res != 0, "MAC next tpl data"); + res = pcmcia_loop_tuple(bus->host_pcmcia, CISTPL_FUNCE, + ssb_pcmcia_get_mac, sprom); + if (res != 0) { + ssb_printk(KERN_ERR PFX + "PCMCIA: Failed to fetch MAC address\n"); + return -ENODEV; } - GOTO_ERROR_ON(tuple.TupleDataLen != ETH_ALEN + 2, "MAC tpl size"); - memcpy(sprom->il0mac, &tuple.TupleData[2], ETH_ALEN); /* Fetch the vendor specific tuples. */ - memset(&tuple, 0, sizeof(tuple)); - tuple.DesiredTuple = SSB_PCMCIA_CIS; - tuple.TupleData = buf; - tuple.TupleDataMax = sizeof(buf); - res = pcmcia_get_first_tuple(bus->host_pcmcia, &tuple); - GOTO_ERROR_ON(res != 0, "VEN first tpl"); - res = pcmcia_get_tuple_data(bus->host_pcmcia, &tuple); - GOTO_ERROR_ON(res != 0, "VEN first tpl data"); - while (1) { - GOTO_ERROR_ON(tuple.TupleDataLen < 1, "VEN tpl < 1"); - switch (tuple.TupleData[0]) { - case SSB_PCMCIA_CIS_ID: - GOTO_ERROR_ON((tuple.TupleDataLen != 5) && - (tuple.TupleDataLen != 7), - "id tpl size"); - bi->vendor = tuple.TupleData[1] | - ((u16)tuple.TupleData[2] << 8); - break; - case SSB_PCMCIA_CIS_BOARDREV: - GOTO_ERROR_ON(tuple.TupleDataLen != 2, - "boardrev tpl size"); - sprom->board_rev = tuple.TupleData[1]; - break; - case SSB_PCMCIA_CIS_PA: - GOTO_ERROR_ON((tuple.TupleDataLen != 9) && - (tuple.TupleDataLen != 10), - "pa tpl size"); - sprom->pa0b0 = tuple.TupleData[1] | - ((u16)tuple.TupleData[2] << 8); - sprom->pa0b1 = tuple.TupleData[3] | - ((u16)tuple.TupleData[4] << 8); - sprom->pa0b2 = tuple.TupleData[5] | - ((u16)tuple.TupleData[6] << 8); - sprom->itssi_a = tuple.TupleData[7]; - sprom->itssi_bg = tuple.TupleData[7]; - sprom->maxpwr_a = tuple.TupleData[8]; - sprom->maxpwr_bg = tuple.TupleData[8]; - break; - case SSB_PCMCIA_CIS_OEMNAME: - /* We ignore this. */ - break; - case SSB_PCMCIA_CIS_CCODE: - GOTO_ERROR_ON(tuple.TupleDataLen != 2, - "ccode tpl size"); - sprom->country_code = tuple.TupleData[1]; - break; - case SSB_PCMCIA_CIS_ANTENNA: - GOTO_ERROR_ON(tuple.TupleDataLen != 2, - "ant tpl size"); - sprom->ant_available_a = tuple.TupleData[1]; - sprom->ant_available_bg = tuple.TupleData[1]; - break; - case SSB_PCMCIA_CIS_ANTGAIN: - GOTO_ERROR_ON(tuple.TupleDataLen != 2, - "antg tpl size"); - sprom->antenna_gain.ghz24.a0 = tuple.TupleData[1]; - sprom->antenna_gain.ghz24.a1 = tuple.TupleData[1]; - sprom->antenna_gain.ghz24.a2 = tuple.TupleData[1]; - sprom->antenna_gain.ghz24.a3 = tuple.TupleData[1]; - sprom->antenna_gain.ghz5.a0 = tuple.TupleData[1]; - sprom->antenna_gain.ghz5.a1 = tuple.TupleData[1]; - sprom->antenna_gain.ghz5.a2 = tuple.TupleData[1]; - sprom->antenna_gain.ghz5.a3 = tuple.TupleData[1]; - break; - case SSB_PCMCIA_CIS_BFLAGS: - GOTO_ERROR_ON((tuple.TupleDataLen != 3) && - (tuple.TupleDataLen != 5), - "bfl tpl size"); - sprom->boardflags_lo = tuple.TupleData[1] | - ((u16)tuple.TupleData[2] << 8); - break; - case SSB_PCMCIA_CIS_LEDS: - GOTO_ERROR_ON(tuple.TupleDataLen != 5, - "leds tpl size"); - sprom->gpio0 = tuple.TupleData[1]; - sprom->gpio1 = tuple.TupleData[2]; - sprom->gpio2 = tuple.TupleData[3]; - sprom->gpio3 = tuple.TupleData[4]; - break; - } - res = pcmcia_get_next_tuple(bus->host_pcmcia, &tuple); - if (res == -ENOSPC) - break; - GOTO_ERROR_ON(res != 0, "VEN next tpl"); - res = pcmcia_get_tuple_data(bus->host_pcmcia, &tuple); - GOTO_ERROR_ON(res != 0, "VEN next tpl data"); - } + res = pcmcia_loop_tuple(bus->host_pcmcia, SSB_PCMCIA_CIS, + ssb_pcmcia_do_get_invariants, sprom); + if ((res == 0) || (res == -ENOSPC)) + return 0; - return 0; -error: ssb_printk(KERN_ERR PFX - "PCMCIA: Failed to fetch device invariants: %s\n", - error_description); + "PCMCIA: Failed to fetch device invariants\n"); return -ENODEV; } diff --git a/drivers/staging/comedi/drivers/cb_das16_cs.c b/drivers/staging/comedi/drivers/cb_das16_cs.c index 80c0df8656f3..39923cb388be 100644 --- a/drivers/staging/comedi/drivers/cb_das16_cs.c +++ b/drivers/staging/comedi/drivers/cb_das16_cs.c @@ -141,37 +141,14 @@ static int das16cs_timer_insn_config(struct comedi_device *dev, struct comedi_insn *insn, unsigned int *data); -static int get_prodid(struct comedi_device *dev, struct pcmcia_device *link) -{ - tuple_t tuple; - u_short buf[128]; - int prodid = 0; - - tuple.TupleData = (cisdata_t *) buf; - tuple.TupleOffset = 0; - tuple.TupleDataMax = 255; - tuple.DesiredTuple = CISTPL_MANFID; - tuple.Attributes = TUPLE_RETURN_COMMON; - if ((pcmcia_get_first_tuple(link, &tuple) == 0) && - (pcmcia_get_tuple_data(link, &tuple) == 0)) { - prodid = le16_to_cpu(buf[1]); - } - - return prodid; -} - static const struct das16cs_board *das16cs_probe(struct comedi_device *dev, struct pcmcia_device *link) { - int id; int i; - id = get_prodid(dev, link); - for (i = 0; i < n_boards; i++) { - if (das16cs_boards[i].device_id == id) { + if (das16cs_boards[i].device_id == link->card_id) return das16cs_boards + i; - } } printk("unknown board!\n"); @@ -660,27 +637,8 @@ static int das16cs_timer_insn_config(struct comedi_device *dev, ======================================================================*/ -/* - All the PCMCIA modules use PCMCIA_DEBUG to control debugging. If - you do not define PCMCIA_DEBUG at all, all the debug code will be - left out. If you compile with PCMCIA_DEBUG=0, the debug code will - be present but disabled -- but it can then be enabled for specific - modules at load time with a 'pc_debug=#' option to insmod. -*/ #if defined(CONFIG_PCMCIA) || defined(CONFIG_PCMCIA_MODULE) -#ifdef PCMCIA_DEBUG -static int pc_debug = PCMCIA_DEBUG; -module_param(pc_debug, int, 0644); -#define DEBUG(n, args...) if (pc_debug>(n)) printk(KERN_DEBUG args) -static char *version = - "cb_das16_cs.c pcmcia code (David Schleef), modified from dummy_cs.c 1.31 2001/08/24 12:13:13 (David Hinds)"; -#else -#define DEBUG(n, args...) -#endif - -/*====================================================================*/ - static void das16cs_pcmcia_config(struct pcmcia_device *link); static void das16cs_pcmcia_release(struct pcmcia_device *link); static int das16cs_pcmcia_suspend(struct pcmcia_device *p_dev); @@ -733,7 +691,7 @@ static int das16cs_pcmcia_attach(struct pcmcia_device *link) { struct local_info_t *local; - DEBUG(0, "das16cs_pcmcia_attach()\n"); + dev_dbg(&link->dev, "das16cs_pcmcia_attach()\n"); /* Allocate space for private device-specific data */ local = kzalloc(sizeof(struct local_info_t), GFP_KERNEL); @@ -745,7 +703,6 @@ static int das16cs_pcmcia_attach(struct pcmcia_device *link) /* Initialize the pcmcia_device structure */ /* Interrupt setup */ link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; link->irq.Handler = NULL; link->conf.Attributes = 0; @@ -760,7 +717,7 @@ static int das16cs_pcmcia_attach(struct pcmcia_device *link) static void das16cs_pcmcia_detach(struct pcmcia_device *link) { - DEBUG(0, "das16cs_pcmcia_detach(0x%p)\n", link); + dev_dbg(&link->dev, "das16cs_pcmcia_detach\n"); if (link->dev_node) { ((struct local_info_t *)link->priv)->stop = 1; @@ -771,118 +728,55 @@ static void das16cs_pcmcia_detach(struct pcmcia_device *link) kfree(link->priv); } /* das16cs_pcmcia_detach */ -static void das16cs_pcmcia_config(struct pcmcia_device *link) -{ - struct local_info_t *dev = link->priv; - tuple_t tuple; - cisparse_t parse; - int last_fn, last_ret; - u_char buf[64]; - cistpl_cftable_entry_t dflt = { 0 }; - DEBUG(0, "das16cs_pcmcia_config(0x%p)\n", link); - - /* - This reads the card's CONFIG tuple to find its configuration - registers. - */ - tuple.DesiredTuple = CISTPL_CONFIG; - tuple.Attributes = 0; - tuple.TupleData = buf; - tuple.TupleDataMax = sizeof(buf); - tuple.TupleOffset = 0; - - last_fn = GetFirstTuple; - last_ret = pcmcia_get_first_tuple(link, &tuple); - if (last_ret != 0) - goto cs_failed; - - last_fn = GetTupleData; - last_ret = pcmcia_get_tuple_data(link, &tuple); - if (last_ret != 0) - goto cs_failed; - - last_fn = ParseTuple; - last_ret = pcmcia_parse_tuple(&tuple, &parse); - if (last_ret != 0) - goto cs_failed; - - link->conf.ConfigBase = parse.config.base; - link->conf.Present = parse.config.rmask[0]; +static int das16cs_pcmcia_config_loop(struct pcmcia_device *p_dev, + cistpl_cftable_entry_t *cfg, + cistpl_cftable_entry_t *dflt, + unsigned int vcc, + void *priv_data) +{ + if (cfg->index == 0) + return -EINVAL; - /* - In this loop, we scan the CIS for configuration table entries, - each of which describes a valid card configuration, including - voltage, IO window, memory window, and interrupt settings. - - We make no assumptions about the card to be configured: we use - just the information available in the CIS. In an ideal world, - this would work for any PCMCIA card, but it requires a complete - and accurate CIS. In practice, a driver usually "knows" most of - these things without consulting the CIS, and most client drivers - will only use the CIS to fill in implementation-defined details. - */ - tuple.DesiredTuple = CISTPL_CFTABLE_ENTRY; - last_fn = GetFirstTuple; - - last_ret = pcmcia_get_first_tuple(link, &tuple); - if (last_ret) - goto cs_failed; - - while (1) { - cistpl_cftable_entry_t *cfg = &(parse.cftable_entry); - if (pcmcia_get_tuple_data(link, &tuple)) - goto next_entry; - if (pcmcia_parse_tuple(&tuple, &parse)) - goto next_entry; - - if (cfg->flags & CISTPL_CFTABLE_DEFAULT) - dflt = *cfg; - if (cfg->index == 0) - goto next_entry; - link->conf.ConfigIndex = cfg->index; - - /* Does this card need audio output? */ -/* if (cfg->flags & CISTPL_CFTABLE_AUDIO) { - link->conf.Attributes |= CONF_ENABLE_SPKR; - link->conf.Status = CCSR_AUDIO_ENA; - } -*/ - /* Do we need to allocate an interrupt? */ - if (cfg->irq.IRQInfo1 || dflt.irq.IRQInfo1) - link->conf.Attributes |= CONF_ENABLE_IRQ; - - /* IO window settings */ - link->io.NumPorts1 = link->io.NumPorts2 = 0; - if ((cfg->io.nwin > 0) || (dflt.io.nwin > 0)) { - cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt.io; - link->io.Attributes1 = IO_DATA_PATH_WIDTH_AUTO; - if (!(io->flags & CISTPL_IO_8BIT)) - link->io.Attributes1 = IO_DATA_PATH_WIDTH_16; - if (!(io->flags & CISTPL_IO_16BIT)) - link->io.Attributes1 = IO_DATA_PATH_WIDTH_8; - link->io.IOAddrLines = io->flags & CISTPL_IO_LINES_MASK; - link->io.BasePort1 = io->win[0].base; - link->io.NumPorts1 = io->win[0].len; - if (io->nwin > 1) { - link->io.Attributes2 = link->io.Attributes1; - link->io.BasePort2 = io->win[1].base; - link->io.NumPorts2 = io->win[1].len; - } - /* This reserves IO space but doesn't actually enable it */ - if (pcmcia_request_io(link, &link->io)) - goto next_entry; + /* Do we need to allocate an interrupt? */ + if (cfg->irq.IRQInfo1 || dflt->irq.IRQInfo1) + p_dev->conf.Attributes |= CONF_ENABLE_IRQ; + + /* IO window settings */ + p_dev->io.NumPorts1 = p_dev->io.NumPorts2 = 0; + if ((cfg->io.nwin > 0) || (dflt->io.nwin > 0)) { + cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt->io; + p_dev->io.Attributes1 = IO_DATA_PATH_WIDTH_AUTO; + if (!(io->flags & CISTPL_IO_8BIT)) + p_dev->io.Attributes1 = IO_DATA_PATH_WIDTH_16; + if (!(io->flags & CISTPL_IO_16BIT)) + p_dev->io.Attributes1 = IO_DATA_PATH_WIDTH_8; + p_dev->io.IOAddrLines = io->flags & CISTPL_IO_LINES_MASK; + p_dev->io.BasePort1 = io->win[0].base; + p_dev->io.NumPorts1 = io->win[0].len; + if (io->nwin > 1) { + p_dev->io.Attributes2 = p_dev->io.Attributes1; + p_dev->io.BasePort2 = io->win[1].base; + p_dev->io.NumPorts2 = io->win[1].len; } + /* This reserves IO space but doesn't actually enable it */ + return pcmcia_request_io(p_dev, &p_dev->io); + } - /* If we got this far, we're cool! */ - break; + return 0; +} + +static void das16cs_pcmcia_config(struct pcmcia_device *link) +{ + struct local_info_t *dev = link->priv; + int ret; -next_entry: - last_fn = GetNextTuple; + dev_dbg(&link->dev, "das16cs_pcmcia_config\n"); - last_ret = pcmcia_get_next_tuple(link, &tuple); - if (last_ret) - goto cs_failed; + ret = pcmcia_loop_config(link, das16cs_pcmcia_config_loop, NULL); + if (ret) { + dev_warn(&link->dev, "no configuration found\n"); + goto failed; } /* @@ -891,21 +785,18 @@ next_entry: irq structure is initialized. */ if (link->conf.Attributes & CONF_ENABLE_IRQ) { - last_fn = RequestIRQ; - - last_ret = pcmcia_request_irq(link, &link->irq); - if (last_ret) - goto cs_failed; + ret = pcmcia_request_irq(link, &link->irq); + if (ret) + goto failed; } /* This actually configures the PCMCIA socket -- setting up the I/O windows and the interrupt mapping, and putting the card and host interface into "Memory and IO" mode. */ - last_fn = RequestConfiguration; - last_ret = pcmcia_request_configuration(link, &link->conf); - if (last_ret) - goto cs_failed; + ret = pcmcia_request_configuration(link, &link->conf); + if (ret) + goto failed; /* At this point, the dev_node_t structure(s) need to be @@ -930,14 +821,13 @@ next_entry: return; -cs_failed: - cs_error(link, last_fn, last_ret); +failed: das16cs_pcmcia_release(link); } /* das16cs_pcmcia_config */ static void das16cs_pcmcia_release(struct pcmcia_device *link) { - DEBUG(0, "das16cs_pcmcia_release(0x%p)\n", link); + dev_dbg(&link->dev, "das16cs_pcmcia_release\n"); pcmcia_disable_device(link); } /* das16cs_pcmcia_release */ @@ -983,14 +873,13 @@ struct pcmcia_driver das16cs_driver = { static int __init init_das16cs_pcmcia_cs(void) { - DEBUG(0, "%s\n", version); pcmcia_register_driver(&das16cs_driver); return 0; } static void __exit exit_das16cs_pcmcia_cs(void) { - DEBUG(0, "das16cs_pcmcia_cs: unloading\n"); + pr_debug("das16cs_pcmcia_cs: unloading\n"); pcmcia_unregister_driver(&das16cs_driver); } diff --git a/drivers/staging/comedi/drivers/das08_cs.c b/drivers/staging/comedi/drivers/das08_cs.c index 9cab21eaaa18..9b945e5fdd32 100644 --- a/drivers/staging/comedi/drivers/das08_cs.c +++ b/drivers/staging/comedi/drivers/das08_cs.c @@ -110,25 +110,6 @@ static int das08_cs_attach(struct comedi_device *dev, ======================================================================*/ -/* - All the PCMCIA modules use PCMCIA_DEBUG to control debugging. If - you do not define PCMCIA_DEBUG at all, all the debug code will be - left out. If you compile with PCMCIA_DEBUG=0, the debug code will - be present but disabled -- but it can then be enabled for specific - modules at load time with a 'pc_debug=#' option to insmod. -*/ - -#ifdef PCMCIA_DEBUG -static int pc_debug = PCMCIA_DEBUG; -module_param(pc_debug, int, 0644); -#define DEBUG(n, args...) if (pc_debug>(n)) printk(KERN_DEBUG args) -static const char *version = - "das08.c pcmcia code (Frank Hess), modified from dummy_cs.c 1.31 2001/08/24 12:13:13 (David Hinds)"; -#else -#define DEBUG(n, args...) -#endif - -/*====================================================================*/ static void das08_pcmcia_config(struct pcmcia_device *link); static void das08_pcmcia_release(struct pcmcia_device *link); static int das08_pcmcia_suspend(struct pcmcia_device *p_dev); @@ -181,7 +162,7 @@ static int das08_pcmcia_attach(struct pcmcia_device *link) { struct local_info_t *local; - DEBUG(0, "das08_pcmcia_attach()\n"); + dev_dbg(&link->dev, "das08_pcmcia_attach()\n"); /* Allocate space for private device-specific data */ local = kzalloc(sizeof(struct local_info_t), GFP_KERNEL); @@ -192,7 +173,6 @@ static int das08_pcmcia_attach(struct pcmcia_device *link) /* Interrupt setup */ link->irq.Attributes = IRQ_TYPE_EXCLUSIVE; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; link->irq.Handler = NULL; /* @@ -224,7 +204,7 @@ static int das08_pcmcia_attach(struct pcmcia_device *link) static void das08_pcmcia_detach(struct pcmcia_device *link) { - DEBUG(0, "das08_pcmcia_detach(0x%p)\n", link); + dev_dbg(&link->dev, "das08_pcmcia_detach\n"); if (link->dev_node) { ((struct local_info_t *)link->priv)->stop = 1; @@ -237,6 +217,44 @@ static void das08_pcmcia_detach(struct pcmcia_device *link) } /* das08_pcmcia_detach */ + +static int das08_pcmcia_config_loop(struct pcmcia_device *p_dev, + cistpl_cftable_entry_t *cfg, + cistpl_cftable_entry_t *dflt, + unsigned int vcc, + void *priv_data) +{ + if (cfg->index == 0) + return -ENODEV; + + /* Do we need to allocate an interrupt? */ + if (cfg->irq.IRQInfo1 || dflt->irq.IRQInfo1) + p_dev->conf.Attributes |= CONF_ENABLE_IRQ; + + /* IO window settings */ + p_dev->io.NumPorts1 = p_dev->io.NumPorts2 = 0; + if ((cfg->io.nwin > 0) || (dflt->io.nwin > 0)) { + cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt->io; + p_dev->io.Attributes1 = IO_DATA_PATH_WIDTH_AUTO; + if (!(io->flags & CISTPL_IO_8BIT)) + p_dev->io.Attributes1 = IO_DATA_PATH_WIDTH_16; + if (!(io->flags & CISTPL_IO_16BIT)) + p_dev->io.Attributes1 = IO_DATA_PATH_WIDTH_8; + p_dev->io.IOAddrLines = io->flags & CISTPL_IO_LINES_MASK; + p_dev->io.BasePort1 = io->win[0].base; + p_dev->io.NumPorts1 = io->win[0].len; + if (io->nwin > 1) { + p_dev->io.Attributes2 = p_dev->io.Attributes1; + p_dev->io.BasePort2 = io->win[1].base; + p_dev->io.NumPorts2 = io->win[1].len; + } + /* This reserves IO space but doesn't actually enable it */ + return pcmcia_request_io(p_dev, &p_dev->io); + } + return 0; +} + + /*====================================================================== das08_pcmcia_config() is scheduled to run after a CARD_INSERTION event @@ -248,128 +266,20 @@ static void das08_pcmcia_detach(struct pcmcia_device *link) static void das08_pcmcia_config(struct pcmcia_device *link) { struct local_info_t *dev = link->priv; - tuple_t tuple; - cisparse_t parse; - int last_fn, last_ret; - u_char buf[64]; - cistpl_cftable_entry_t dflt = { 0 }; - - DEBUG(0, "das08_pcmcia_config(0x%p)\n", link); - - /* - This reads the card's CONFIG tuple to find its configuration - registers. - */ - tuple.DesiredTuple = CISTPL_CONFIG; - tuple.Attributes = 0; - tuple.TupleData = buf; - tuple.TupleDataMax = sizeof(buf); - tuple.TupleOffset = 0; - last_fn = GetFirstTuple; - - last_ret = pcmcia_get_first_tuple(link, &tuple); - if (last_ret) - goto cs_failed; - - last_fn = GetTupleData; - - last_ret = pcmcia_get_tuple_data(link, &tuple); - if (last_ret) - goto cs_failed; - - last_fn = ParseTuple; - - last_ret = pcmcia_parse_tuple(&tuple, &parse); - if (last_ret) - goto cs_failed; - - link->conf.ConfigBase = parse.config.base; - link->conf.Present = parse.config.rmask[0]; - - /* - In this loop, we scan the CIS for configuration table entries, - each of which describes a valid card configuration, including - voltage, IO window, memory window, and interrupt settings. - - We make no assumptions about the card to be configured: we use - just the information available in the CIS. In an ideal world, - this would work for any PCMCIA card, but it requires a complete - and accurate CIS. In practice, a driver usually "knows" most of - these things without consulting the CIS, and most client drivers - will only use the CIS to fill in implementation-defined details. - */ - tuple.DesiredTuple = CISTPL_CFTABLE_ENTRY; - last_fn = GetFirstTuple; - - last_ret = pcmcia_get_first_tuple(link, &tuple); - if (last_ret) - goto cs_failed; - - while (1) { - cistpl_cftable_entry_t *cfg = &(parse.cftable_entry); - - last_ret = pcmcia_get_tuple_data(link, &tuple); - if (last_ret) - goto next_entry; - - last_ret = pcmcia_parse_tuple(&tuple, &parse); - if (last_ret) - goto next_entry; - - if (cfg->flags & CISTPL_CFTABLE_DEFAULT) - dflt = *cfg; - if (cfg->index == 0) - goto next_entry; - link->conf.ConfigIndex = cfg->index; - - /* Does this card need audio output? */ -/* if (cfg->flags & CISTPL_CFTABLE_AUDIO) { - link->conf.Attributes |= CONF_ENABLE_SPKR; - link->conf.Status = CCSR_AUDIO_ENA; - } -*/ - /* Do we need to allocate an interrupt? */ - if (cfg->irq.IRQInfo1 || dflt.irq.IRQInfo1) - link->conf.Attributes |= CONF_ENABLE_IRQ; - - /* IO window settings */ - link->io.NumPorts1 = link->io.NumPorts2 = 0; - if ((cfg->io.nwin > 0) || (dflt.io.nwin > 0)) { - cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt.io; - link->io.Attributes1 = IO_DATA_PATH_WIDTH_AUTO; - if (!(io->flags & CISTPL_IO_8BIT)) - link->io.Attributes1 = IO_DATA_PATH_WIDTH_16; - if (!(io->flags & CISTPL_IO_16BIT)) - link->io.Attributes1 = IO_DATA_PATH_WIDTH_8; - link->io.IOAddrLines = io->flags & CISTPL_IO_LINES_MASK; - link->io.BasePort1 = io->win[0].base; - link->io.NumPorts1 = io->win[0].len; - if (io->nwin > 1) { - link->io.Attributes2 = link->io.Attributes1; - link->io.BasePort2 = io->win[1].base; - link->io.NumPorts2 = io->win[1].len; - } - /* This reserves IO space but doesn't actually enable it */ - if (pcmcia_request_io(link, &link->io) != 0) - goto next_entry; - } - - /* If we got this far, we're cool! */ - break; + int ret; -next_entry: - last_fn = GetNextTuple; + dev_dbg(&link->dev, "das08_pcmcia_config\n"); - last_ret = pcmcia_get_next_tuple(link, &tuple); - if (last_ret) - goto cs_failed; + ret = pcmcia_loop_config(link, das08_pcmcia_config_loop, NULL); + if (ret) { + dev_warn(&link->dev, "no configuration found\n"); + goto failed; } if (link->conf.Attributes & CONF_ENABLE_IRQ) { - last_fn = RequestIRQ; - last_ret = pcmcia_request_irq(link, &link->irq); - if (last_ret) - goto cs_failed; + ret = pcmcia_request_irq(link, &link->irq); + if (ret) + goto failed; } /* @@ -377,10 +287,9 @@ next_entry: the I/O windows and the interrupt mapping, and putting the card and host interface into "Memory and IO" mode. */ - last_fn = RequestConfiguration; - last_ret = pcmcia_request_configuration(link, &link->conf); - if (last_ret) - goto cs_failed; + ret = pcmcia_request_configuration(link, &link->conf); + if (ret) + goto failed; /* At this point, the dev_node_t structure(s) need to be @@ -405,8 +314,7 @@ next_entry: return; -cs_failed: - cs_error(link, last_fn, last_ret); +failed: das08_pcmcia_release(link); } /* das08_pcmcia_config */ @@ -421,7 +329,7 @@ cs_failed: static void das08_pcmcia_release(struct pcmcia_device *link) { - DEBUG(0, "das08_pcmcia_release(0x%p)\n", link); + dev_dbg(&link->dev, "das08_pcmcia_release\n"); pcmcia_disable_device(link); } /* das08_pcmcia_release */ @@ -477,14 +385,13 @@ struct pcmcia_driver das08_cs_driver = { static int __init init_das08_pcmcia_cs(void) { - DEBUG(0, "%s\n", version); pcmcia_register_driver(&das08_cs_driver); return 0; } static void __exit exit_das08_pcmcia_cs(void) { - DEBUG(0, "das08_pcmcia_cs: unloading\n"); + pr_debug("das08_pcmcia_cs: unloading\n"); pcmcia_unregister_driver(&das08_cs_driver); } diff --git a/drivers/staging/comedi/drivers/ni_daq_700.c b/drivers/staging/comedi/drivers/ni_daq_700.c index ec31a3970664..ef5e1183d47d 100644 --- a/drivers/staging/comedi/drivers/ni_daq_700.c +++ b/drivers/staging/comedi/drivers/ni_daq_700.c @@ -436,25 +436,7 @@ static int dio700_detach(struct comedi_device *dev) return 0; }; -/* PCMCIA crap */ - -/* - All the PCMCIA modules use PCMCIA_DEBUG to control debugging. If - you do not define PCMCIA_DEBUG at all, all the debug code will be - left out. If you compile with PCMCIA_DEBUG=0, the debug code will - be present but disabled -- but it can then be enabled for specific - modules at load time with a 'pc_debug=#' option to insmod. -*/ -#ifdef PCMCIA_DEBUG -static int pc_debug = PCMCIA_DEBUG; -module_param(pc_debug, int, 0644); -#define DEBUG(n, args...) if (pc_debug>(n)) printk(KERN_DEBUG args) -static char *version = "ni_daq_700.c, based on dummy_cs.c"; -#else -#define DEBUG(n, args...) -#endif - -/*====================================================================*/ +/* PCMCIA crap -- watch your words, please! */ static void dio700_config(struct pcmcia_device *link); static void dio700_release(struct pcmcia_device *link); @@ -510,7 +492,7 @@ static int dio700_cs_attach(struct pcmcia_device *link) printk(KERN_INFO "ni_daq_700: cs-attach\n"); - DEBUG(0, "dio700_cs_attach()\n"); + dev_dbg(&link->dev, "dio700_cs_attach()\n"); /* Allocate space for private device-specific data */ local = kzalloc(sizeof(struct local_info_t), GFP_KERNEL); @@ -521,7 +503,6 @@ static int dio700_cs_attach(struct pcmcia_device *link) /* Interrupt setup */ link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; link->irq.Handler = NULL; /* @@ -555,7 +536,7 @@ static void dio700_cs_detach(struct pcmcia_device *link) printk(KERN_INFO "ni_daq_700: cs-detach!\n"); - DEBUG(0, "dio700_cs_detach(0x%p)\n", link); + dev_dbg(&link->dev, "dio700_cs_detach\n"); if (link->dev_node) { ((struct local_info_t *)link->priv)->stop = 1; @@ -576,141 +557,85 @@ static void dio700_cs_detach(struct pcmcia_device *link) ======================================================================*/ -static void dio700_config(struct pcmcia_device *link) +static int dio700_pcmcia_config_loop(struct pcmcia_device *p_dev, + cistpl_cftable_entry_t *cfg, + cistpl_cftable_entry_t *dflt, + unsigned int vcc, + void *priv_data) { - struct local_info_t *dev = link->priv; - tuple_t tuple; - cisparse_t parse; - int last_ret; - u_char buf[64]; - win_req_t req; + win_req_t *req = priv_data; memreq_t map; - cistpl_cftable_entry_t dflt = { 0 }; - printk(KERN_INFO "ni_daq_700: cs-config\n"); - - DEBUG(0, "dio700_config(0x%p)\n", link); + if (cfg->index == 0) + return -ENODEV; - /* - This reads the card's CONFIG tuple to find its configuration - registers. - */ - tuple.DesiredTuple = CISTPL_CONFIG; - tuple.Attributes = 0; - tuple.TupleData = buf; - tuple.TupleDataMax = sizeof(buf); - tuple.TupleOffset = 0; - - last_ret = pcmcia_get_first_tuple(link, &tuple); - if (last_ret) { - cs_error(link, GetFirstTuple, last_ret); - goto cs_failed; + /* Does this card need audio output? */ + if (cfg->flags & CISTPL_CFTABLE_AUDIO) { + p_dev->conf.Attributes |= CONF_ENABLE_SPKR; + p_dev->conf.Status = CCSR_AUDIO_ENA; } - last_ret = pcmcia_get_tuple_data(link, &tuple); - if (last_ret) { - cs_error(link, GetTupleData, last_ret); - goto cs_failed; + /* Do we need to allocate an interrupt? */ + if (cfg->irq.IRQInfo1 || dflt->irq.IRQInfo1) + p_dev->conf.Attributes |= CONF_ENABLE_IRQ; + + /* IO window settings */ + p_dev->io.NumPorts1 = p_dev->io.NumPorts2 = 0; + if ((cfg->io.nwin > 0) || (dflt->io.nwin > 0)) { + cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt->io; + p_dev->io.Attributes1 = IO_DATA_PATH_WIDTH_AUTO; + if (!(io->flags & CISTPL_IO_8BIT)) + p_dev->io.Attributes1 = IO_DATA_PATH_WIDTH_16; + if (!(io->flags & CISTPL_IO_16BIT)) + p_dev->io.Attributes1 = IO_DATA_PATH_WIDTH_8; + p_dev->io.IOAddrLines = io->flags & CISTPL_IO_LINES_MASK; + p_dev->io.BasePort1 = io->win[0].base; + p_dev->io.NumPorts1 = io->win[0].len; + if (io->nwin > 1) { + p_dev->io.Attributes2 = p_dev->io.Attributes1; + p_dev->io.BasePort2 = io->win[1].base; + p_dev->io.NumPorts2 = io->win[1].len; + } + /* This reserves IO space but doesn't actually enable it */ + if (pcmcia_request_io(p_dev, &p_dev->io) != 0) + return -ENODEV; } - last_ret = pcmcia_parse_tuple(&tuple, &parse); - if (last_ret) { - cs_error(link, ParseTuple, last_ret); - goto cs_failed; + if ((cfg->mem.nwin > 0) || (dflt->mem.nwin > 0)) { + cistpl_mem_t *mem = + (cfg->mem.nwin) ? &cfg->mem : &dflt->mem; + req->Attributes = WIN_DATA_WIDTH_16 | WIN_MEMORY_TYPE_CM; + req->Attributes |= WIN_ENABLE; + req->Base = mem->win[0].host_addr; + req->Size = mem->win[0].len; + if (req->Size < 0x1000) + req->Size = 0x1000; + req->AccessSpeed = 0; + if (pcmcia_request_window(p_dev, req, &p_dev->win)) + return -ENODEV; + map.Page = 0; + map.CardOffset = mem->win[0].card_addr; + if (pcmcia_map_mem_page(p_dev, p_dev->win, &map)) + return -ENODEV; } - link->conf.ConfigBase = parse.config.base; - link->conf.Present = parse.config.rmask[0]; - - /* - In this loop, we scan the CIS for configuration table entries, - each of which describes a valid card configuration, including - voltage, IO window, memory window, and interrupt settings. - - We make no assumptions about the card to be configured: we use - just the information available in the CIS. In an ideal world, - this would work for any PCMCIA card, but it requires a complete - and accurate CIS. In practice, a driver usually "knows" most of - these things without consulting the CIS, and most client drivers - will only use the CIS to fill in implementation-defined details. - */ - tuple.DesiredTuple = CISTPL_CFTABLE_ENTRY; - last_ret = pcmcia_get_first_tuple(link, &tuple); - if (last_ret != 0) { - cs_error(link, GetFirstTuple, last_ret); - goto cs_failed; - } - while (1) { - cistpl_cftable_entry_t *cfg = &(parse.cftable_entry); - if (pcmcia_get_tuple_data(link, &tuple) != 0) - goto next_entry; - if (pcmcia_parse_tuple(&tuple, &parse) != 0) - goto next_entry; - - if (cfg->flags & CISTPL_CFTABLE_DEFAULT) - dflt = *cfg; - if (cfg->index == 0) - goto next_entry; - link->conf.ConfigIndex = cfg->index; - - /* Does this card need audio output? */ - if (cfg->flags & CISTPL_CFTABLE_AUDIO) { - link->conf.Attributes |= CONF_ENABLE_SPKR; - link->conf.Status = CCSR_AUDIO_ENA; - } + /* If we got this far, we're cool! */ + return 0; +} - /* Do we need to allocate an interrupt? */ - if (cfg->irq.IRQInfo1 || dflt.irq.IRQInfo1) - link->conf.Attributes |= CONF_ENABLE_IRQ; - - /* IO window settings */ - link->io.NumPorts1 = link->io.NumPorts2 = 0; - if ((cfg->io.nwin > 0) || (dflt.io.nwin > 0)) { - cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt.io; - link->io.Attributes1 = IO_DATA_PATH_WIDTH_AUTO; - if (!(io->flags & CISTPL_IO_8BIT)) - link->io.Attributes1 = IO_DATA_PATH_WIDTH_16; - if (!(io->flags & CISTPL_IO_16BIT)) - link->io.Attributes1 = IO_DATA_PATH_WIDTH_8; - link->io.IOAddrLines = io->flags & CISTPL_IO_LINES_MASK; - link->io.BasePort1 = io->win[0].base; - link->io.NumPorts1 = io->win[0].len; - if (io->nwin > 1) { - link->io.Attributes2 = link->io.Attributes1; - link->io.BasePort2 = io->win[1].base; - link->io.NumPorts2 = io->win[1].len; - } - /* This reserves IO space but doesn't actually enable it */ - if (pcmcia_request_io(link, &link->io) != 0) - goto next_entry; - } +static void dio700_config(struct pcmcia_device *link) +{ + struct local_info_t *dev = link->priv; + win_req_t req; + int ret; - if ((cfg->mem.nwin > 0) || (dflt.mem.nwin > 0)) { - cistpl_mem_t *mem = - (cfg->mem.nwin) ? &cfg->mem : &dflt.mem; - req.Attributes = WIN_DATA_WIDTH_16 | WIN_MEMORY_TYPE_CM; - req.Attributes |= WIN_ENABLE; - req.Base = mem->win[0].host_addr; - req.Size = mem->win[0].len; - if (req.Size < 0x1000) - req.Size = 0x1000; - req.AccessSpeed = 0; - if (pcmcia_request_window(&link, &req, &link->win)) - goto next_entry; - map.Page = 0; - map.CardOffset = mem->win[0].card_addr; - if (pcmcia_map_mem_page(link->win, &map)) - goto next_entry; - } - /* If we got this far, we're cool! */ - break; + printk(KERN_INFO "ni_daq_700: cs-config\n"); -next_entry: + dev_dbg(&link->dev, "dio700_config\n"); - last_ret = pcmcia_get_next_tuple(link, &tuple); - if (last_ret) { - cs_error(link, GetNextTuple, last_ret); - goto cs_failed; - } + ret = pcmcia_loop_config(link, dio700_pcmcia_config_loop, &req); + if (ret) { + dev_warn(&link->dev, "no configuration found\n"); + goto failed; } /* @@ -719,11 +644,9 @@ next_entry: irq structure is initialized. */ if (link->conf.Attributes & CONF_ENABLE_IRQ) { - last_ret = pcmcia_request_irq(link, &link->irq); - if (last_ret) { - cs_error(link, RequestIRQ, last_ret); - goto cs_failed; - } + ret = pcmcia_request_irq(link, &link->irq); + if (ret) + goto failed; } /* @@ -731,11 +654,9 @@ next_entry: the I/O windows and the interrupt mapping, and putting the card and host interface into "Memory and IO" mode. */ - last_ret = pcmcia_request_configuration(link, &link->conf); - if (last_ret != 0) { - cs_error(link, RequestConfiguration, last_ret); - goto cs_failed; - } + ret = pcmcia_request_configuration(link, &link->conf); + if (ret != 0) + goto failed; /* At this point, the dev_node_t structure(s) need to be @@ -763,7 +684,7 @@ next_entry: return; -cs_failed: +failed: printk(KERN_INFO "ni_daq_700 cs failed"); dio700_release(link); @@ -771,7 +692,7 @@ cs_failed: static void dio700_release(struct pcmcia_device *link) { - DEBUG(0, "dio700_release(0x%p)\n", link); + dev_dbg(&link->dev, "dio700_release\n"); pcmcia_disable_device(link); } /* dio700_release */ @@ -830,15 +751,13 @@ struct pcmcia_driver dio700_cs_driver = { static int __init init_dio700_cs(void) { - printk("ni_daq_700: cs-init \n"); - DEBUG(0, "%s\n", version); pcmcia_register_driver(&dio700_cs_driver); return 0; } static void __exit exit_dio700_cs(void) { - DEBUG(0, "ni_daq_700: unloading\n"); + pr_debug("ni_daq_700: unloading\n"); pcmcia_unregister_driver(&dio700_cs_driver); } diff --git a/drivers/staging/comedi/drivers/ni_daq_dio24.c b/drivers/staging/comedi/drivers/ni_daq_dio24.c index 0700a8bddd1e..9017be3a92f1 100644 --- a/drivers/staging/comedi/drivers/ni_daq_dio24.c +++ b/drivers/staging/comedi/drivers/ni_daq_dio24.c @@ -187,25 +187,7 @@ static int dio24_detach(struct comedi_device *dev) return 0; }; -/* PCMCIA crap */ - -/* - All the PCMCIA modules use PCMCIA_DEBUG to control debugging. If - you do not define PCMCIA_DEBUG at all, all the debug code will be - left out. If you compile with PCMCIA_DEBUG=0, the debug code will - be present but disabled -- but it can then be enabled for specific - modules at load time with a 'pc_debug=#' option to insmod. -*/ -#ifdef PCMCIA_DEBUG -static int pc_debug = PCMCIA_DEBUG; -module_param(pc_debug, int, 0644); -#define DEBUG(n, args...) if (pc_debug>(n)) printk(KERN_DEBUG args) -static char *version = "ni_daq_dio24.c, based on dummy_cs.c"; -#else -#define DEBUG(n, args...) -#endif - -/*====================================================================*/ +/* PCMCIA crap -- watch your words! */ static void dio24_config(struct pcmcia_device *link); static void dio24_release(struct pcmcia_device *link); @@ -261,7 +243,7 @@ static int dio24_cs_attach(struct pcmcia_device *link) printk(KERN_INFO "ni_daq_dio24: HOLA SOY YO - CS-attach!\n"); - DEBUG(0, "dio24_cs_attach()\n"); + dev_dbg(&link->dev, "dio24_cs_attach()\n"); /* Allocate space for private device-specific data */ local = kzalloc(sizeof(struct local_info_t), GFP_KERNEL); @@ -272,7 +254,6 @@ static int dio24_cs_attach(struct pcmcia_device *link) /* Interrupt setup */ link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; link->irq.Handler = NULL; /* @@ -306,7 +287,7 @@ static void dio24_cs_detach(struct pcmcia_device *link) printk(KERN_INFO "ni_daq_dio24: HOLA SOY YO - cs-detach!\n"); - DEBUG(0, "dio24_cs_detach(0x%p)\n", link); + dev_dbg(&link->dev, "dio24_cs_detach\n"); if (link->dev_node) { ((struct local_info_t *)link->priv)->stop = 1; @@ -327,142 +308,85 @@ static void dio24_cs_detach(struct pcmcia_device *link) ======================================================================*/ -static void dio24_config(struct pcmcia_device *link) +static int dio24_pcmcia_config_loop(struct pcmcia_device *p_dev, + cistpl_cftable_entry_t *cfg, + cistpl_cftable_entry_t *dflt, + unsigned int vcc, + void *priv_data) { - struct local_info_t *dev = link->priv; - tuple_t tuple; - cisparse_t parse; - int last_ret; - u_char buf[64]; - win_req_t req; + win_req_t *req = priv_data; memreq_t map; - cistpl_cftable_entry_t dflt = { 0 }; - printk(KERN_INFO "ni_daq_dio24: HOLA SOY YO! - config\n"); - - DEBUG(0, "dio24_config(0x%p)\n", link); - - /* - This reads the card's CONFIG tuple to find its configuration - registers. - */ - tuple.DesiredTuple = CISTPL_CONFIG; - tuple.Attributes = 0; - tuple.TupleData = buf; - tuple.TupleDataMax = sizeof(buf); - tuple.TupleOffset = 0; - - last_ret = pcmcia_get_first_tuple(link, &tuple); - if (last_ret) { - cs_error(link, GetFirstTuple, last_ret); - goto cs_failed; - } + if (cfg->index == 0) + return -ENODEV; - last_ret = pcmcia_get_tuple_data(link, &tuple); - if (last_ret) { - cs_error(link, GetTupleData, last_ret); - goto cs_failed; + /* Does this card need audio output? */ + if (cfg->flags & CISTPL_CFTABLE_AUDIO) { + p_dev->conf.Attributes |= CONF_ENABLE_SPKR; + p_dev->conf.Status = CCSR_AUDIO_ENA; } - last_ret = pcmcia_parse_tuple(&tuple, &parse); - if (last_ret) { - cs_error(link, ParseTuple, last_ret); - goto cs_failed; + /* Do we need to allocate an interrupt? */ + if (cfg->irq.IRQInfo1 || dflt->irq.IRQInfo1) + p_dev->conf.Attributes |= CONF_ENABLE_IRQ; + + /* IO window settings */ + p_dev->io.NumPorts1 = p_dev->io.NumPorts2 = 0; + if ((cfg->io.nwin > 0) || (dflt->io.nwin > 0)) { + cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt->io; + p_dev->io.Attributes1 = IO_DATA_PATH_WIDTH_AUTO; + if (!(io->flags & CISTPL_IO_8BIT)) + p_dev->io.Attributes1 = IO_DATA_PATH_WIDTH_16; + if (!(io->flags & CISTPL_IO_16BIT)) + p_dev->io.Attributes1 = IO_DATA_PATH_WIDTH_8; + p_dev->io.IOAddrLines = io->flags & CISTPL_IO_LINES_MASK; + p_dev->io.BasePort1 = io->win[0].base; + p_dev->io.NumPorts1 = io->win[0].len; + if (io->nwin > 1) { + p_dev->io.Attributes2 = p_dev->io.Attributes1; + p_dev->io.BasePort2 = io->win[1].base; + p_dev->io.NumPorts2 = io->win[1].len; + } + /* This reserves IO space but doesn't actually enable it */ + if (pcmcia_request_io(p_dev, &p_dev->io) != 0) + return -ENODEV; } - link->conf.ConfigBase = parse.config.base; - link->conf.Present = parse.config.rmask[0]; - - /* - In this loop, we scan the CIS for configuration table entries, - each of which describes a valid card configuration, including - voltage, IO window, memory window, and interrupt settings. - - We make no assumptions about the card to be configured: we use - just the information available in the CIS. In an ideal world, - this would work for any PCMCIA card, but it requires a complete - and accurate CIS. In practice, a driver usually "knows" most of - these things without consulting the CIS, and most client drivers - will only use the CIS to fill in implementation-defined details. - */ - tuple.DesiredTuple = CISTPL_CFTABLE_ENTRY; - last_ret = pcmcia_get_first_tuple(link, &tuple); - if (last_ret) { - cs_error(link, GetFirstTuple, last_ret); - goto cs_failed; + if ((cfg->mem.nwin > 0) || (dflt->mem.nwin > 0)) { + cistpl_mem_t *mem = + (cfg->mem.nwin) ? &cfg->mem : &dflt->mem; + req->Attributes = WIN_DATA_WIDTH_16 | WIN_MEMORY_TYPE_CM; + req->Attributes |= WIN_ENABLE; + req->Base = mem->win[0].host_addr; + req->Size = mem->win[0].len; + if (req->Size < 0x1000) + req->Size = 0x1000; + req->AccessSpeed = 0; + if (pcmcia_request_window(p_dev, req, &p_dev->win)) + return -ENODEV; + map.Page = 0; + map.CardOffset = mem->win[0].card_addr; + if (pcmcia_map_mem_page(p_dev, p_dev->win, &map)) + return -ENODEV; } - while (1) { - cistpl_cftable_entry_t *cfg = &(parse.cftable_entry); - if (pcmcia_get_tuple_data(link, &tuple) != 0) - goto next_entry; - if (pcmcia_parse_tuple(&tuple, &parse) != 0) - goto next_entry; - - if (cfg->flags & CISTPL_CFTABLE_DEFAULT) - dflt = *cfg; - if (cfg->index == 0) - goto next_entry; - link->conf.ConfigIndex = cfg->index; - - /* Does this card need audio output? */ - if (cfg->flags & CISTPL_CFTABLE_AUDIO) { - link->conf.Attributes |= CONF_ENABLE_SPKR; - link->conf.Status = CCSR_AUDIO_ENA; - } + /* If we got this far, we're cool! */ + return 0; +} - /* Do we need to allocate an interrupt? */ - if (cfg->irq.IRQInfo1 || dflt.irq.IRQInfo1) - link->conf.Attributes |= CONF_ENABLE_IRQ; - - /* IO window settings */ - link->io.NumPorts1 = link->io.NumPorts2 = 0; - if ((cfg->io.nwin > 0) || (dflt.io.nwin > 0)) { - cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt.io; - link->io.Attributes1 = IO_DATA_PATH_WIDTH_AUTO; - if (!(io->flags & CISTPL_IO_8BIT)) - link->io.Attributes1 = IO_DATA_PATH_WIDTH_16; - if (!(io->flags & CISTPL_IO_16BIT)) - link->io.Attributes1 = IO_DATA_PATH_WIDTH_8; - link->io.IOAddrLines = io->flags & CISTPL_IO_LINES_MASK; - link->io.BasePort1 = io->win[0].base; - link->io.NumPorts1 = io->win[0].len; - if (io->nwin > 1) { - link->io.Attributes2 = link->io.Attributes1; - link->io.BasePort2 = io->win[1].base; - link->io.NumPorts2 = io->win[1].len; - } - /* This reserves IO space but doesn't actually enable it */ - if (pcmcia_request_io(link, &link->io) != 0) - goto next_entry; - } +static void dio24_config(struct pcmcia_device *link) +{ + struct local_info_t *dev = link->priv; + int ret; + win_req_t req; - if ((cfg->mem.nwin > 0) || (dflt.mem.nwin > 0)) { - cistpl_mem_t *mem = - (cfg->mem.nwin) ? &cfg->mem : &dflt.mem; - req.Attributes = WIN_DATA_WIDTH_16 | WIN_MEMORY_TYPE_CM; - req.Attributes |= WIN_ENABLE; - req.Base = mem->win[0].host_addr; - req.Size = mem->win[0].len; - if (req.Size < 0x1000) - req.Size = 0x1000; - req.AccessSpeed = 0; - if (pcmcia_request_window(&link, &req, &link->win)) - goto next_entry; - map.Page = 0; - map.CardOffset = mem->win[0].card_addr; - if (pcmcia_map_mem_page(link->win, &map)) - goto next_entry; - } - /* If we got this far, we're cool! */ - break; + printk(KERN_INFO "ni_daq_dio24: HOLA SOY YO! - config\n"); -next_entry: + dev_dbg(&link->dev, "dio24_config\n"); - last_ret = pcmcia_get_next_tuple(link, &tuple); - if (last_ret) { - cs_error(link, GetNextTuple, last_ret); - goto cs_failed; - } + ret = pcmcia_loop_config(link, dio24_pcmcia_config_loop, &req); + if (ret) { + dev_warn(&link->dev, "no configuration found\n"); + goto failed; } /* @@ -471,11 +395,9 @@ next_entry: irq structure is initialized. */ if (link->conf.Attributes & CONF_ENABLE_IRQ) { - last_ret = pcmcia_request_irq(link, &link->irq); - if (last_ret) { - cs_error(link, RequestIRQ, last_ret); - goto cs_failed; - } + ret = pcmcia_request_irq(link, &link->irq); + if (ret) + goto failed; } /* @@ -483,11 +405,9 @@ next_entry: the I/O windows and the interrupt mapping, and putting the card and host interface into "Memory and IO" mode. */ - last_ret = pcmcia_request_configuration(link, &link->conf); - if (last_ret) { - cs_error(link, RequestConfiguration, last_ret); - goto cs_failed; - } + ret = pcmcia_request_configuration(link, &link->conf); + if (ret) + goto failed; /* At this point, the dev_node_t structure(s) need to be @@ -515,7 +435,7 @@ next_entry: return; -cs_failed: +failed: printk(KERN_INFO "Fallo"); dio24_release(link); @@ -523,7 +443,7 @@ cs_failed: static void dio24_release(struct pcmcia_device *link) { - DEBUG(0, "dio24_release(0x%p)\n", link); + dev_dbg(&link->dev, "dio24_release\n"); pcmcia_disable_device(link); } /* dio24_release */ @@ -582,14 +502,12 @@ struct pcmcia_driver dio24_cs_driver = { static int __init init_dio24_cs(void) { printk("ni_daq_dio24: HOLA SOY YO!\n"); - DEBUG(0, "%s\n", version); pcmcia_register_driver(&dio24_cs_driver); return 0; } static void __exit exit_dio24_cs(void) { - DEBUG(0, "ni_dio24: unloading\n"); pcmcia_unregister_driver(&dio24_cs_driver); } diff --git a/drivers/staging/comedi/drivers/ni_labpc_cs.c b/drivers/staging/comedi/drivers/ni_labpc_cs.c index a3053b8da1c6..7d514b3ee754 100644 --- a/drivers/staging/comedi/drivers/ni_labpc_cs.c +++ b/drivers/staging/comedi/drivers/ni_labpc_cs.c @@ -153,23 +153,6 @@ static int labpc_attach(struct comedi_device *dev, struct comedi_devconfig *it) return labpc_common_attach(dev, iobase, irq, 0); } -/* - All the PCMCIA modules use PCMCIA_DEBUG to control debugging. If - you do not define PCMCIA_DEBUG at all, all the debug code will be - left out. If you compile with PCMCIA_DEBUG=0, the debug code will - be present but disabled -- but it can then be enabled for specific - modules at load time with a 'pc_debug=#' option to insmod. -*/ -#ifdef PCMCIA_DEBUG -static int pc_debug = PCMCIA_DEBUG; -module_param(pc_debug, int, 0644); -#define DEBUG(n, args...) if (pc_debug>(n)) printk(KERN_DEBUG args) -static const char *version = - "ni_labpc.c, based on dummy_cs.c 1.31 2001/08/24 12:13:13"; -#else -#define DEBUG(n, args...) -#endif - /*====================================================================*/ /* @@ -236,7 +219,7 @@ static int labpc_cs_attach(struct pcmcia_device *link) { struct local_info_t *local; - DEBUG(0, "labpc_cs_attach()\n"); + dev_dbg(&link->dev, "labpc_cs_attach()\n"); /* Allocate space for private device-specific data */ local = kzalloc(sizeof(struct local_info_t), GFP_KERNEL); @@ -247,7 +230,6 @@ static int labpc_cs_attach(struct pcmcia_device *link) /* Interrupt setup */ link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING | IRQ_FORCED_PULSE; - link->irq.IRQInfo1 = IRQ_INFO2_VALID | IRQ_PULSE_ID; link->irq.Handler = NULL; /* @@ -278,7 +260,7 @@ static int labpc_cs_attach(struct pcmcia_device *link) static void labpc_cs_detach(struct pcmcia_device *link) { - DEBUG(0, "labpc_cs_detach(0x%p)\n", link); + dev_dbg(&link->dev, "labpc_cs_detach\n"); /* If the device is currently configured and active, we won't @@ -305,135 +287,84 @@ static void labpc_cs_detach(struct pcmcia_device *link) ======================================================================*/ -static void labpc_config(struct pcmcia_device *link) +static int labpc_pcmcia_config_loop(struct pcmcia_device *p_dev, + cistpl_cftable_entry_t *cfg, + cistpl_cftable_entry_t *dflt, + unsigned int vcc, + void *priv_data) { - struct local_info_t *dev = link->priv; - tuple_t tuple; - cisparse_t parse; - int last_ret; - u_char buf[64]; - win_req_t req; + win_req_t *req = priv_data; memreq_t map; - cistpl_cftable_entry_t dflt = { 0 }; - DEBUG(0, "labpc_config(0x%p)\n", link); + if (cfg->index == 0) + return -ENODEV; - /* - This reads the card's CONFIG tuple to find its configuration - registers. - */ - tuple.DesiredTuple = CISTPL_CONFIG; - tuple.Attributes = 0; - tuple.TupleData = buf; - tuple.TupleDataMax = sizeof(buf); - tuple.TupleOffset = 0; - - last_ret = pcmcia_get_first_tuple(link, &tuple); - if (last_ret) { - cs_error(link, GetFirstTuple, last_ret); - goto cs_failed; + /* Does this card need audio output? */ + if (cfg->flags & CISTPL_CFTABLE_AUDIO) { + p_dev->conf.Attributes |= CONF_ENABLE_SPKR; + p_dev->conf.Status = CCSR_AUDIO_ENA; } - last_ret = pcmcia_get_tuple_data(link, &tuple); - if (last_ret) { - cs_error(link, GetTupleData, last_ret); - goto cs_failed; + /* Do we need to allocate an interrupt? */ + if (cfg->irq.IRQInfo1 || dflt->irq.IRQInfo1) + p_dev->conf.Attributes |= CONF_ENABLE_IRQ; + + /* IO window settings */ + p_dev->io.NumPorts1 = p_dev->io.NumPorts2 = 0; + if ((cfg->io.nwin > 0) || (dflt->io.nwin > 0)) { + cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt->io; + p_dev->io.Attributes1 = IO_DATA_PATH_WIDTH_AUTO; + if (!(io->flags & CISTPL_IO_8BIT)) + p_dev->io.Attributes1 = IO_DATA_PATH_WIDTH_16; + if (!(io->flags & CISTPL_IO_16BIT)) + p_dev->io.Attributes1 = IO_DATA_PATH_WIDTH_8; + p_dev->io.IOAddrLines = io->flags & CISTPL_IO_LINES_MASK; + p_dev->io.BasePort1 = io->win[0].base; + p_dev->io.NumPorts1 = io->win[0].len; + if (io->nwin > 1) { + p_dev->io.Attributes2 = p_dev->io.Attributes1; + p_dev->io.BasePort2 = io->win[1].base; + p_dev->io.NumPorts2 = io->win[1].len; + } + /* This reserves IO space but doesn't actually enable it */ + if (pcmcia_request_io(p_dev, &p_dev->io) != 0) + return -ENODEV; } - last_ret = pcmcia_parse_tuple(&tuple, &parse); - if (last_ret) { - cs_error(link, ParseTuple, last_ret); - goto cs_failed; + if ((cfg->mem.nwin > 0) || (dflt->mem.nwin > 0)) { + cistpl_mem_t *mem = + (cfg->mem.nwin) ? &cfg->mem : &dflt->mem; + req->Attributes = WIN_DATA_WIDTH_16 | WIN_MEMORY_TYPE_CM; + req->Attributes |= WIN_ENABLE; + req->Base = mem->win[0].host_addr; + req->Size = mem->win[0].len; + if (req->Size < 0x1000) + req->Size = 0x1000; + req->AccessSpeed = 0; + if (pcmcia_request_window(p_dev, req, &p_dev->win)) + return -ENODEV; + map.Page = 0; + map.CardOffset = mem->win[0].card_addr; + if (pcmcia_map_mem_page(p_dev, p_dev->win, &map)) + return -ENODEV; } - link->conf.ConfigBase = parse.config.base; - link->conf.Present = parse.config.rmask[0]; + /* If we got this far, we're cool! */ + return 0; +} - /* - In this loop, we scan the CIS for configuration table entries, - each of which describes a valid card configuration, including - voltage, IO window, memory window, and interrupt settings. - - We make no assumptions about the card to be configured: we use - just the information available in the CIS. In an ideal world, - this would work for any PCMCIA card, but it requires a complete - and accurate CIS. In practice, a driver usually "knows" most of - these things without consulting the CIS, and most client drivers - will only use the CIS to fill in implementation-defined details. - */ - tuple.DesiredTuple = CISTPL_CFTABLE_ENTRY; - last_ret = pcmcia_get_first_tuple(link, &tuple); - if (last_ret) { - cs_error(link, GetFirstTuple, last_ret); - goto cs_failed; - } - while (1) { - cistpl_cftable_entry_t *cfg = &(parse.cftable_entry); - if (pcmcia_get_tuple_data(link, &tuple)) - goto next_entry; - if (pcmcia_parse_tuple(&tuple, &parse)) - goto next_entry; - - if (cfg->flags & CISTPL_CFTABLE_DEFAULT) - dflt = *cfg; - if (cfg->index == 0) - goto next_entry; - link->conf.ConfigIndex = cfg->index; - - /* Does this card need audio output? */ - if (cfg->flags & CISTPL_CFTABLE_AUDIO) { - link->conf.Attributes |= CONF_ENABLE_SPKR; - link->conf.Status = CCSR_AUDIO_ENA; - } - /* Do we need to allocate an interrupt? */ - if (cfg->irq.IRQInfo1 || dflt.irq.IRQInfo1) - link->conf.Attributes |= CONF_ENABLE_IRQ; - - /* IO window settings */ - link->io.NumPorts1 = link->io.NumPorts2 = 0; - if ((cfg->io.nwin > 0) || (dflt.io.nwin > 0)) { - cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt.io; - link->io.Attributes1 = IO_DATA_PATH_WIDTH_8; - link->io.IOAddrLines = io->flags & CISTPL_IO_LINES_MASK; - link->io.BasePort1 = io->win[0].base; - link->io.NumPorts1 = io->win[0].len; - if (io->nwin > 1) { - link->io.Attributes2 = link->io.Attributes1; - link->io.BasePort2 = io->win[1].base; - link->io.NumPorts2 = io->win[1].len; - } - /* This reserves IO space but doesn't actually enable it */ - if (pcmcia_request_io(link, &link->io)) - goto next_entry; - } +static void labpc_config(struct pcmcia_device *link) +{ + struct local_info_t *dev = link->priv; + int ret; + win_req_t req; - if ((cfg->mem.nwin > 0) || (dflt.mem.nwin > 0)) { - cistpl_mem_t *mem = - (cfg->mem.nwin) ? &cfg->mem : &dflt.mem; - req.Attributes = WIN_DATA_WIDTH_16 | WIN_MEMORY_TYPE_CM; - req.Attributes |= WIN_ENABLE; - req.Base = mem->win[0].host_addr; - req.Size = mem->win[0].len; - if (req.Size < 0x1000) - req.Size = 0x1000; - req.AccessSpeed = 0; - link->win = (window_handle_t) link; - if (pcmcia_request_window(&link, &req, &link->win)) - goto next_entry; - map.Page = 0; - map.CardOffset = mem->win[0].card_addr; - if (pcmcia_map_mem_page(link->win, &map)) - goto next_entry; - } - /* If we got this far, we're cool! */ - break; + dev_dbg(&link->dev, "labpc_config\n"); -next_entry: - last_ret = pcmcia_get_next_tuple(link, &tuple); - if (last_ret) { - cs_error(link, GetNextTuple, last_ret); - goto cs_failed; - } + ret = pcmcia_loop_config(link, labpc_pcmcia_config_loop, &req); + if (ret) { + dev_warn(&link->dev, "no configuration found\n"); + goto failed; } /* @@ -442,11 +373,9 @@ next_entry: irq structure is initialized. */ if (link->conf.Attributes & CONF_ENABLE_IRQ) { - last_ret = pcmcia_request_irq(link, &link->irq); - if (last_ret) { - cs_error(link, RequestIRQ, last_ret); - goto cs_failed; - } + ret = pcmcia_request_irq(link, &link->irq); + if (ret) + goto failed; } /* @@ -454,11 +383,9 @@ next_entry: the I/O windows and the interrupt mapping, and putting the card and host interface into "Memory and IO" mode. */ - last_ret = pcmcia_request_configuration(link, &link->conf); - if (last_ret) { - cs_error(link, RequestConfiguration, last_ret); - goto cs_failed; - } + ret = pcmcia_request_configuration(link, &link->conf); + if (ret) + goto failed; /* At this point, the dev_node_t structure(s) need to be @@ -486,14 +413,14 @@ next_entry: return; -cs_failed: +failed: labpc_release(link); } /* labpc_config */ static void labpc_release(struct pcmcia_device *link) { - DEBUG(0, "labpc_release(0x%p)\n", link); + dev_dbg(&link->dev, "labpc_release\n"); pcmcia_disable_device(link); } /* labpc_release */ @@ -551,14 +478,12 @@ struct pcmcia_driver labpc_cs_driver = { static int __init init_labpc_cs(void) { - DEBUG(0, "%s\n", version); pcmcia_register_driver(&labpc_cs_driver); return 0; } static void __exit exit_labpc_cs(void) { - DEBUG(0, "ni_labpc: unloading\n"); pcmcia_unregister_driver(&labpc_cs_driver); } diff --git a/drivers/staging/comedi/drivers/ni_mio_cs.c b/drivers/staging/comedi/drivers/ni_mio_cs.c index 9aef87fc81dc..d692f4bb47ea 100644 --- a/drivers/staging/comedi/drivers/ni_mio_cs.c +++ b/drivers/staging/comedi/drivers/ni_mio_cs.c @@ -274,7 +274,6 @@ static int cs_attach(struct pcmcia_device *link) link->io.Attributes1 = IO_DATA_PATH_WIDTH_16; link->io.NumPorts1 = 16; link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; link->conf.Attributes = CONF_ENABLE_IRQ; link->conf.IntType = INT_MEMORY_AND_IO; @@ -312,96 +311,47 @@ static int mio_cs_resume(struct pcmcia_device *link) return 0; } -static void mio_cs_config(struct pcmcia_device *link) -{ - tuple_t tuple; - u_short buf[128]; - cisparse_t parse; - int manfid = 0, prodid = 0; - int ret; - - DPRINTK("mio_cs_config(link=%p)\n", link); - tuple.TupleData = (cisdata_t *) buf; - tuple.TupleOffset = 0; - tuple.TupleDataMax = 255; - tuple.Attributes = 0; +static int mio_pcmcia_config_loop(struct pcmcia_device *p_dev, + cistpl_cftable_entry_t *cfg, + cistpl_cftable_entry_t *dflt, + unsigned int vcc, + void *priv_data) +{ + int base, ret; - tuple.DesiredTuple = CISTPL_CONFIG; - ret = pcmcia_get_first_tuple(link, &tuple); - ret = pcmcia_get_tuple_data(link, &tuple); - ret = pcmcia_parse_tuple(&tuple, &parse); - link->conf.ConfigBase = parse.config.base; - link->conf.Present = parse.config.rmask[0]; + p_dev->io.NumPorts1 = cfg->io.win[0].len; + p_dev->io.IOAddrLines = cfg->io.flags & CISTPL_IO_LINES_MASK; + p_dev->io.NumPorts2 = 0; -#if 0 - tuple.DesiredTuple = CISTPL_LONGLINK_MFC; - tuple.Attributes = TUPLE_RETURN_COMMON | TUPLE_RETURN_LINK; - info->multi(first_tuple(link, &tuple, &parse) == 0); -#endif - - tuple.DesiredTuple = CISTPL_MANFID; - tuple.Attributes = TUPLE_RETURN_COMMON; - if ((pcmcia_get_first_tuple(link, &tuple) == 0) && - (pcmcia_get_tuple_data(link, &tuple) == 0)) { - manfid = le16_to_cpu(buf[0]); - prodid = le16_to_cpu(buf[1]); + for (base = 0x000; base < 0x400; base += 0x20) { + p_dev->io.BasePort1 = base; + ret = pcmcia_request_io(p_dev, &p_dev->io); + if (!ret) + return 0; } - /* printk("manfid = 0x%04x, 0x%04x\n",manfid,prodid); */ + return -ENODEV; +} - tuple.DesiredTuple = CISTPL_CFTABLE_ENTRY; - tuple.Attributes = 0; - ret = pcmcia_get_first_tuple(link, &tuple); - ret = pcmcia_get_tuple_data(link, &tuple); - ret = pcmcia_parse_tuple(&tuple, &parse); -#if 0 - printk(" index: 0x%x\n", parse.cftable_entry.index); - printk(" flags: 0x%x\n", parse.cftable_entry.flags); - printk(" io flags: 0x%x\n", parse.cftable_entry.io.flags); - printk(" io nwin: 0x%x\n", parse.cftable_entry.io.nwin); - printk(" io base: 0x%x\n", parse.cftable_entry.io.win[0].base); - printk(" io len: 0x%x\n", parse.cftable_entry.io.win[0].len); - printk(" irq1: 0x%x\n", parse.cftable_entry.irq.IRQInfo1); - printk(" irq2: 0x%x\n", parse.cftable_entry.irq.IRQInfo2); - printk(" mem flags: 0x%x\n", parse.cftable_entry.mem.flags); - printk(" mem nwin: 0x%x\n", parse.cftable_entry.mem.nwin); - printk(" subtuples: 0x%x\n", parse.cftable_entry.subtuples); -#endif +static void mio_cs_config(struct pcmcia_device *link) +{ + int ret; -#if 0 - link->io.NumPorts1 = 0x20; - link->io.IOAddrLines = 5; - link->io.Attributes1 = IO_DATA_PATH_WIDTH_AUTO; -#endif - link->io.NumPorts1 = parse.cftable_entry.io.win[0].len; - link->io.IOAddrLines = - parse.cftable_entry.io.flags & CISTPL_IO_LINES_MASK; - link->io.NumPorts2 = 0; + DPRINTK("mio_cs_config(link=%p)\n", link); - { - int base; - for (base = 0x000; base < 0x400; base += 0x20) { - link->io.BasePort1 = base; - ret = pcmcia_request_io(link, &link->io); - /* printk("RequestIO 0x%02x\n",ret); */ - if (!ret) - break; - } + ret = pcmcia_loop_config(link, mio_pcmcia_config_loop, NULL); + if (ret) { + dev_warn(&link->dev, "no configuration found\n"); + return; } - link->irq.IRQInfo1 = parse.cftable_entry.irq.IRQInfo1; - link->irq.IRQInfo2 = parse.cftable_entry.irq.IRQInfo2; ret = pcmcia_request_irq(link, &link->irq); if (ret) { printk("pcmcia_request_irq() returned error: %i\n", ret); } - /* printk("RequestIRQ 0x%02x\n",ret); */ - - link->conf.ConfigIndex = 1; ret = pcmcia_request_configuration(link, &link->conf); - /* printk("RequestConfiguration %d\n",ret); */ link->dev_node = &dev_node; } @@ -475,40 +425,17 @@ static int mio_cs_attach(struct comedi_device *dev, struct comedi_devconfig *it) return 0; } -static int get_prodid(struct comedi_device *dev, struct pcmcia_device *link) -{ - tuple_t tuple; - u_short buf[128]; - int prodid = 0; - - tuple.TupleData = (cisdata_t *) buf; - tuple.TupleOffset = 0; - tuple.TupleDataMax = 255; - tuple.DesiredTuple = CISTPL_MANFID; - tuple.Attributes = TUPLE_RETURN_COMMON; - if ((pcmcia_get_first_tuple(link, &tuple) == 0) && - (pcmcia_get_tuple_data(link, &tuple) == 0)) { - prodid = le16_to_cpu(buf[1]); - } - - return prodid; -} - static int ni_getboardtype(struct comedi_device *dev, struct pcmcia_device *link) { - int id; int i; - id = get_prodid(dev, link); - for (i = 0; i < n_ni_boards; i++) { - if (ni_boards[i].device_id == id) { + if (ni_boards[i].device_id == link->card_id) return i; - } } - printk("unknown board 0x%04x -- pretend it is a ", id); + printk("unknown board 0x%04x -- pretend it is a ", link->card_id); return 0; } diff --git a/drivers/staging/comedi/drivers/quatech_daqp_cs.c b/drivers/staging/comedi/drivers/quatech_daqp_cs.c index 344b82353e08..5256fd933162 100644 --- a/drivers/staging/comedi/drivers/quatech_daqp_cs.c +++ b/drivers/staging/comedi/drivers/quatech_daqp_cs.c @@ -55,23 +55,6 @@ Devices: [Quatech] DAQP-208 (daqp), DAQP-308 #include <pcmcia/cisreg.h> #include <pcmcia/ds.h> -/* - All the PCMCIA modules use PCMCIA_DEBUG to control debugging. If - you do not define PCMCIA_DEBUG at all, all the debug code will be - left out. If you compile with PCMCIA_DEBUG=0, the debug code will - be present but disabled -- but it can then be enabled for specific - modules at load time with a 'pc_debug=#' option to insmod. -*/ - -#ifdef PCMCIA_DEBUG -static int pc_debug = PCMCIA_DEBUG; -module_param(pc_debug, int, 0644); -#define DEBUG(n, args...) if (pc_debug>(n)) printk(KERN_DEBUG args) -static char *version = "quatech_daqp_cs.c 1.10 2003/04/21 (Brent Baccala)"; -#else -#define DEBUG(n, args...) -#endif - /* Maximum number of separate DAQP devices we'll allow */ #define MAX_DEV 4 @@ -863,8 +846,6 @@ static int daqp_attach(struct comedi_device *dev, struct comedi_devconfig *it) { int ret; struct local_info_t *local = dev_table[it->options[0]]; - tuple_t tuple; - int i; struct comedi_subdevice *s; if (it->options[0] < 0 || it->options[0] >= MAX_DEV || !local) { @@ -883,29 +864,10 @@ static int daqp_attach(struct comedi_device *dev, struct comedi_devconfig *it) strcpy(local->board_name, "DAQP"); dev->board_name = local->board_name; - - tuple.DesiredTuple = CISTPL_VERS_1; - if (pcmcia_get_first_tuple(local->link, &tuple) == 0) { - u_char buf[128]; - - buf[0] = buf[sizeof(buf) - 1] = 0; - tuple.TupleData = buf; - tuple.TupleDataMax = sizeof(buf); - tuple.TupleOffset = 2; - if (pcmcia_get_tuple_data(local->link, &tuple) == 0) { - - for (i = 0; i < tuple.TupleDataLen - 4; i++) - if (buf[i] == 0) - break; - for (i++; i < tuple.TupleDataLen - 4; i++) - if (buf[i] == 0) - break; - i++; - if ((i < tuple.TupleDataLen - 4) - && (strncmp(buf + i, "DAQP", 4) == 0)) { - strncpy(local->board_name, buf + i, - sizeof(local->board_name)); - } + if (local->link->prod_id[2]) { + if (strncmp(local->link->prod_id[2], "DAQP", 4) == 0) { + strncpy(local->board_name, local->link->prod_id[2], + sizeof(local->board_name)); } } @@ -1058,7 +1020,7 @@ static int daqp_cs_attach(struct pcmcia_device *link) struct local_info_t *local; int i; - DEBUG(0, "daqp_cs_attach()\n"); + dev_dbg(&link->dev, "daqp_cs_attach()\n"); for (i = 0; i < MAX_DEV; i++) if (dev_table[i] == NULL) @@ -1079,10 +1041,8 @@ static int daqp_cs_attach(struct pcmcia_device *link) link->priv = local; /* Interrupt setup */ - link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING | IRQ_HANDLE_PRESENT; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; + link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING; link->irq.Handler = daqp_interrupt; - link->irq.Instance = local; /* General socket configuration defaults can go here. In this @@ -1112,7 +1072,7 @@ static void daqp_cs_detach(struct pcmcia_device *link) { struct local_info_t *dev = link->priv; - DEBUG(0, "daqp_cs_detach(0x%p)\n", link); + dev_dbg(&link->dev, "daqp_cs_detach\n"); if (link->dev_node) { dev->stop = 1; @@ -1134,115 +1094,54 @@ static void daqp_cs_detach(struct pcmcia_device *link) ======================================================================*/ -static void daqp_cs_config(struct pcmcia_device *link) -{ - struct local_info_t *dev = link->priv; - tuple_t tuple; - cisparse_t parse; - int last_ret; - u_char buf[64]; - - DEBUG(0, "daqp_cs_config(0x%p)\n", link); - - /* - This reads the card's CONFIG tuple to find its configuration - registers. - */ - tuple.DesiredTuple = CISTPL_CONFIG; - tuple.Attributes = 0; - tuple.TupleData = buf; - tuple.TupleDataMax = sizeof(buf); - tuple.TupleOffset = 0; - - last_ret = pcmcia_get_first_tuple(link, &tuple); - if (last_ret) { - cs_error(link, GetFirstTuple, last_ret); - goto cs_failed; - } - last_ret = pcmcia_get_tuple_data(link, &tuple); - if (last_ret) { - cs_error(link, GetTupleData, last_ret); - goto cs_failed; - } - - last_ret = pcmcia_parse_tuple(&tuple, &parse); - if (last_ret) { - cs_error(link, ParseTuple, last_ret); - goto cs_failed; - } - link->conf.ConfigBase = parse.config.base; - link->conf.Present = parse.config.rmask[0]; +static int daqp_pcmcia_config_loop(struct pcmcia_device *p_dev, + cistpl_cftable_entry_t *cfg, + cistpl_cftable_entry_t *dflt, + unsigned int vcc, + void *priv_data) +{ + if (cfg->index == 0) + return -ENODEV; - /* - In this loop, we scan the CIS for configuration table entries, - each of which describes a valid card configuration, including - voltage, IO window, memory window, and interrupt settings. - - We make no assumptions about the card to be configured: we use - just the information available in the CIS. In an ideal world, - this would work for any PCMCIA card, but it requires a complete - and accurate CIS. In practice, a driver usually "knows" most of - these things without consulting the CIS, and most client drivers - will only use the CIS to fill in implementation-defined details. - */ - tuple.DesiredTuple = CISTPL_CFTABLE_ENTRY; - last_ret = pcmcia_get_first_tuple(link, &tuple); - if (last_ret) { - cs_error(link, GetFirstTuple, last_ret); - goto cs_failed; + /* Do we need to allocate an interrupt? */ + if (cfg->irq.IRQInfo1 || dflt->irq.IRQInfo1) + p_dev->conf.Attributes |= CONF_ENABLE_IRQ; + + /* IO window settings */ + p_dev->io.NumPorts1 = p_dev->io.NumPorts2 = 0; + if ((cfg->io.nwin > 0) || (dflt->io.nwin > 0)) { + cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt->io; + p_dev->io.Attributes1 = IO_DATA_PATH_WIDTH_AUTO; + if (!(io->flags & CISTPL_IO_8BIT)) + p_dev->io.Attributes1 = IO_DATA_PATH_WIDTH_16; + if (!(io->flags & CISTPL_IO_16BIT)) + p_dev->io.Attributes1 = IO_DATA_PATH_WIDTH_8; + p_dev->io.IOAddrLines = io->flags & CISTPL_IO_LINES_MASK; + p_dev->io.BasePort1 = io->win[0].base; + p_dev->io.NumPorts1 = io->win[0].len; + if (io->nwin > 1) { + p_dev->io.Attributes2 = p_dev->io.Attributes1; + p_dev->io.BasePort2 = io->win[1].base; + p_dev->io.NumPorts2 = io->win[1].len; + } } - while (1) { - cistpl_cftable_entry_t dflt = { 0 }; - cistpl_cftable_entry_t *cfg = &(parse.cftable_entry); - if (pcmcia_get_tuple_data(link, &tuple)) - goto next_entry; - if (pcmcia_parse_tuple(&tuple, &parse)) - goto next_entry; - - if (cfg->flags & CISTPL_CFTABLE_DEFAULT) - dflt = *cfg; - if (cfg->index == 0) - goto next_entry; - link->conf.ConfigIndex = cfg->index; - - /* Do we need to allocate an interrupt? */ - if (cfg->irq.IRQInfo1 || dflt.irq.IRQInfo1) - link->conf.Attributes |= CONF_ENABLE_IRQ; - - /* IO window settings */ - link->io.NumPorts1 = link->io.NumPorts2 = 0; - if ((cfg->io.nwin > 0) || (dflt.io.nwin > 0)) { - cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt.io; - link->io.Attributes1 = IO_DATA_PATH_WIDTH_AUTO; - if (!(io->flags & CISTPL_IO_8BIT)) - link->io.Attributes1 = IO_DATA_PATH_WIDTH_16; - if (!(io->flags & CISTPL_IO_16BIT)) - link->io.Attributes1 = IO_DATA_PATH_WIDTH_8; - link->io.IOAddrLines = io->flags & CISTPL_IO_LINES_MASK; - link->io.BasePort1 = io->win[0].base; - link->io.NumPorts1 = io->win[0].len; - if (io->nwin > 1) { - link->io.Attributes2 = link->io.Attributes1; - link->io.BasePort2 = io->win[1].base; - link->io.NumPorts2 = io->win[1].len; - } - } + /* This reserves IO space but doesn't actually enable it */ + return pcmcia_request_io(p_dev, &p_dev->io); +} - /* This reserves IO space but doesn't actually enable it */ - if (pcmcia_request_io(link, &link->io)) - goto next_entry; +static void daqp_cs_config(struct pcmcia_device *link) +{ + struct local_info_t *dev = link->priv; + int ret; - /* If we got this far, we're cool! */ - break; + dev_dbg(&link->dev, "daqp_cs_config\n"); -next_entry: - last_ret = pcmcia_get_next_tuple(link, &tuple); - if (last_ret) { - cs_error(link, GetNextTuple, last_ret); - goto cs_failed; - } + ret = pcmcia_loop_config(link, daqp_pcmcia_config_loop, NULL); + if (ret) { + dev_warn(&link->dev, "no configuration found\n"); + goto failed; } /* @@ -1251,11 +1150,9 @@ next_entry: irq structure is initialized. */ if (link->conf.Attributes & CONF_ENABLE_IRQ) { - last_ret = pcmcia_request_irq(link, &link->irq); - if (last_ret) { - cs_error(link, RequestIRQ, last_ret); - goto cs_failed; - } + ret = pcmcia_request_irq(link, &link->irq); + if (ret) + goto failed; } /* @@ -1263,11 +1160,9 @@ next_entry: the I/O windows and the interrupt mapping, and putting the card and host interface into "Memory and IO" mode. */ - last_ret = pcmcia_request_configuration(link, &link->conf); - if (last_ret) { - cs_error(link, RequestConfiguration, last_ret); - goto cs_failed; - } + ret = pcmcia_request_configuration(link, &link->conf); + if (ret) + goto failed; /* At this point, the dev_node_t structure(s) need to be @@ -1296,14 +1191,14 @@ next_entry: return; -cs_failed: +failed: daqp_cs_release(link); } /* daqp_cs_config */ static void daqp_cs_release(struct pcmcia_device *link) { - DEBUG(0, "daqp_cs_release(0x%p)\n", link); + dev_dbg(&link->dev, "daqp_cs_release\n"); pcmcia_disable_device(link); } /* daqp_cs_release */ @@ -1363,7 +1258,6 @@ struct pcmcia_driver daqp_cs_driver = { int __init init_module(void) { - DEBUG(0, "%s\n", version); pcmcia_register_driver(&daqp_cs_driver); comedi_driver_register(&driver_daqp); return 0; @@ -1371,7 +1265,6 @@ int __init init_module(void) void __exit cleanup_module(void) { - DEBUG(0, "daqp_cs: unloading\n"); comedi_driver_unregister(&driver_daqp); pcmcia_unregister_driver(&daqp_cs_driver); } diff --git a/drivers/staging/go7007/s2250-board.c b/drivers/staging/go7007/s2250-board.c index 8c85a9c3665a..f4a6541c3e60 100644 --- a/drivers/staging/go7007/s2250-board.c +++ b/drivers/staging/go7007/s2250-board.c @@ -261,7 +261,7 @@ static int read_reg_fp(struct i2c_client *client, u16 addr, u16 *val) memset(buf, 0xcd, 6); usb = go->hpi_context; - if (down_interruptible(&usb->i2c_lock) != 0) { + if (mutex_lock_interruptible(&usb->i2c_lock) != 0) { printk(KERN_INFO "i2c lock failed\n"); kfree(buf); return -EINTR; @@ -270,7 +270,7 @@ static int read_reg_fp(struct i2c_client *client, u16 addr, u16 *val) kfree(buf); return -EFAULT; } - up(&usb->i2c_lock); + mutex_unlock(&usb->i2c_lock); *val = (buf[0] << 8) | buf[1]; kfree(buf); diff --git a/drivers/staging/go7007/s2250-loader.h b/drivers/staging/go7007/s2250-loader.h new file mode 100644 index 000000000000..b7c301af16cc --- /dev/null +++ b/drivers/staging/go7007/s2250-loader.h @@ -0,0 +1,24 @@ +/* + * Copyright (C) 2005-2006 Micronas USA Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (Version 2) as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software Foundation, + * Inc., 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. + */ + +#ifndef _S2250_LOADER_H_ +#define _S2250_LOADER_H_ + +extern int s2250loader_init(void); +extern void s2250loader_cleanup(void); + +#endif diff --git a/drivers/staging/hv/BlkVsc.c b/drivers/staging/hv/BlkVsc.c index 51aa861292fc..a48ee3a12646 100644 --- a/drivers/staging/hv/BlkVsc.c +++ b/drivers/staging/hv/BlkVsc.c @@ -16,6 +16,7 @@ * Place - Suite 330, Boston, MA 02111-1307 USA. * * Authors: + * Haiyang Zhang <haiyangz@microsoft.com> * Hank Janssen <hjanssen@microsoft.com> * */ diff --git a/drivers/staging/hv/Channel.c b/drivers/staging/hv/Channel.c index d649ee169d95..746370e82115 100644 --- a/drivers/staging/hv/Channel.c +++ b/drivers/staging/hv/Channel.c @@ -611,7 +611,7 @@ void VmbusChannelClose(struct vmbus_channel *Channel) /* Stop callback and cancel the timer asap */ Channel->OnChannelCallback = NULL; - del_timer(&Channel->poll_timer); + del_timer_sync(&Channel->poll_timer); /* Send a closing message */ info = kmalloc(sizeof(*info) + @@ -978,14 +978,10 @@ void VmbusChannelOnChannelEvent(struct vmbus_channel *Channel) { DumpVmbusChannel(Channel); ASSERT(Channel->OnChannelCallback); -#ifdef ENABLE_POLLING - del_timer(&Channel->poll_timer); - Channel->OnChannelCallback(Channel->ChannelCallbackContext); - channel->poll_timer.expires(jiffies + usecs_to_jiffies(100); - add_timer(&channel->poll_timer); -#else + Channel->OnChannelCallback(Channel->ChannelCallbackContext); -#endif + + mod_timer(&Channel->poll_timer, jiffies + usecs_to_jiffies(100)); } /** @@ -997,10 +993,6 @@ void VmbusChannelOnTimer(unsigned long data) if (channel->OnChannelCallback) { channel->OnChannelCallback(channel->ChannelCallbackContext); -#ifdef ENABLE_POLLING - channel->poll_timer.expires(jiffies + usecs_to_jiffies(100); - add_timer(&channel->poll_timer); -#endif } } diff --git a/drivers/staging/hv/ChannelMgmt.c b/drivers/staging/hv/ChannelMgmt.c index 3db62caedcff..ef38467ed4e2 100644 --- a/drivers/staging/hv/ChannelMgmt.c +++ b/drivers/staging/hv/ChannelMgmt.c @@ -119,7 +119,7 @@ static inline void ReleaseVmbusChannel(void *context) */ void FreeVmbusChannel(struct vmbus_channel *Channel) { - del_timer(&Channel->poll_timer); + del_timer_sync(&Channel->poll_timer); /* * We have to release the channel's workqueue/thread in the vmbus's diff --git a/drivers/staging/hv/NetVsc.c b/drivers/staging/hv/NetVsc.c index d384c0ddf069..1c717f9a554e 100644 --- a/drivers/staging/hv/NetVsc.c +++ b/drivers/staging/hv/NetVsc.c @@ -15,6 +15,7 @@ * Place - Suite 330, Boston, MA 02111-1307 USA. * * Authors: + * Haiyang Zhang <haiyangz@microsoft.com> * Hank Janssen <hjanssen@microsoft.com> */ #include <linux/kernel.h> diff --git a/drivers/staging/hv/NetVsc.h b/drivers/staging/hv/NetVsc.h index 3e7112f7c755..6e0e03494126 100644 --- a/drivers/staging/hv/NetVsc.h +++ b/drivers/staging/hv/NetVsc.h @@ -16,6 +16,7 @@ * Place - Suite 330, Boston, MA 02111-1307 USA. * * Authors: + * Haiyang Zhang <haiyangz@microsoft.com> * Hank Janssen <hjanssen@microsoft.com> * */ diff --git a/drivers/staging/hv/StorVsc.c b/drivers/staging/hv/StorVsc.c index 14015c927940..2f7c425896f7 100644 --- a/drivers/staging/hv/StorVsc.c +++ b/drivers/staging/hv/StorVsc.c @@ -196,7 +196,7 @@ static int StorVscChannelInit(struct hv_device *Device) * Now, initiate the vsc/vsp initialization protocol on the open * channel */ - memset(request, sizeof(struct storvsc_request_extension), 0); + memset(request, 0, sizeof(struct storvsc_request_extension)); request->WaitEvent = osd_WaitEventCreate(); vstorPacket->Operation = VStorOperationBeginInitialization; @@ -233,7 +233,7 @@ static int StorVscChannelInit(struct hv_device *Device) DPRINT_INFO(STORVSC, "QUERY_PROTOCOL_VERSION_OPERATION..."); /* reuse the packet for version range supported */ - memset(vstorPacket, sizeof(struct vstor_packet), 0); + memset(vstorPacket, 0, sizeof(struct vstor_packet)); vstorPacket->Operation = VStorOperationQueryProtocolVersion; vstorPacket->Flags = REQUEST_COMPLETION_FLAG; @@ -266,7 +266,7 @@ static int StorVscChannelInit(struct hv_device *Device) /* Query channel properties */ DPRINT_INFO(STORVSC, "QUERY_PROPERTIES_OPERATION..."); - memset(vstorPacket, sizeof(struct vstor_packet), 0); + memset(vstorPacket, 0, sizeof(struct vstor_packet)); vstorPacket->Operation = VStorOperationQueryProperties; vstorPacket->Flags = REQUEST_COMPLETION_FLAG; vstorPacket->StorageChannelProperties.PortNumber = @@ -305,7 +305,7 @@ static int StorVscChannelInit(struct hv_device *Device) DPRINT_INFO(STORVSC, "END_INITIALIZATION_OPERATION..."); - memset(vstorPacket, sizeof(struct vstor_packet), 0); + memset(vstorPacket, 0, sizeof(struct vstor_packet)); vstorPacket->Operation = VStorOperationEndInitialization; vstorPacket->Flags = REQUEST_COMPLETION_FLAG; @@ -508,7 +508,7 @@ static int StorVscConnectToVsp(struct hv_device *Device) int ret; storDriver = (struct storvsc_driver_object *)Device->Driver; - memset(&props, sizeof(struct vmstorage_channel_properties), 0); + memset(&props, 0, sizeof(struct vmstorage_channel_properties)); /* Open the channel */ ret = Device->Driver->VmbusChannelInterface.Open(Device, diff --git a/drivers/staging/hv/blkvsc_drv.c b/drivers/staging/hv/blkvsc_drv.c index 99c49261a8b4..62b282844a53 100644 --- a/drivers/staging/hv/blkvsc_drv.c +++ b/drivers/staging/hv/blkvsc_drv.c @@ -15,6 +15,7 @@ * Place - Suite 330, Boston, MA 02111-1307 USA. * * Authors: + * Haiyang Zhang <haiyangz@microsoft.com> * Hank Janssen <hjanssen@microsoft.com> */ #include <linux/init.h> diff --git a/drivers/staging/hv/netvsc_drv.c b/drivers/staging/hv/netvsc_drv.c index 3192d50f7251..0d7459e2d036 100644 --- a/drivers/staging/hv/netvsc_drv.c +++ b/drivers/staging/hv/netvsc_drv.c @@ -15,6 +15,7 @@ * Place - Suite 330, Boston, MA 02111-1307 USA. * * Authors: + * Haiyang Zhang <haiyangz@microsoft.com> * Hank Janssen <hjanssen@microsoft.com> */ #include <linux/init.h> diff --git a/drivers/staging/octeon/ethernet-mdio.c b/drivers/staging/octeon/ethernet-mdio.c index 42230e62a222..31a58e508924 100644 --- a/drivers/staging/octeon/ethernet-mdio.c +++ b/drivers/staging/octeon/ethernet-mdio.c @@ -170,7 +170,7 @@ static u32 cvm_oct_get_link(struct net_device *dev) return ret; } -struct const ethtool_ops cvm_oct_ethtool_ops = { +const struct ethtool_ops cvm_oct_ethtool_ops = { .get_drvinfo = cvm_oct_get_drvinfo, .get_settings = cvm_oct_get_settings, .set_settings = cvm_oct_set_settings, diff --git a/drivers/staging/octeon/ethernet-spi.c b/drivers/staging/octeon/ethernet-spi.c index 66190b0cb68f..00dc0f4bad19 100644 --- a/drivers/staging/octeon/ethernet-spi.c +++ b/drivers/staging/octeon/ethernet-spi.c @@ -317,6 +317,6 @@ void cvm_oct_spi_uninit(struct net_device *dev) cvmx_write_csr(CVMX_SPXX_INT_MSK(interface), 0); cvmx_write_csr(CVMX_STXX_INT_MSK(interface), 0); } - free_irq(8 + 46, &number_spi_ports); + free_irq(OCTEON_IRQ_RML, &number_spi_ports); } } diff --git a/drivers/staging/octeon/ethernet.c b/drivers/staging/octeon/ethernet.c index b8479517dce2..492c5029992d 100644 --- a/drivers/staging/octeon/ethernet.c +++ b/drivers/staging/octeon/ethernet.c @@ -111,6 +111,16 @@ MODULE_PARM_DESC(disable_core_queueing, "\n" "\tallows packets to be sent without lock contention in the packet\n" "\tscheduler resulting in some cases in improved throughput.\n"); + +/* + * The offset from mac_addr_base that should be used for the next port + * that is configured. By convention, if any mgmt ports exist on the + * chip, they get the first mac addresses, The ports controlled by + * this driver are numbered sequencially following any mgmt addresses + * that may exist. + */ +static unsigned int cvm_oct_mac_addr_offset; + /** * Periodic timer to check auto negotiation */ @@ -474,16 +484,30 @@ static int cvm_oct_common_set_mac_address(struct net_device *dev, void *addr) */ int cvm_oct_common_init(struct net_device *dev) { - static int count; - char mac[8] = { 0x00, 0x00, - octeon_bootinfo->mac_addr_base[0], - octeon_bootinfo->mac_addr_base[1], - octeon_bootinfo->mac_addr_base[2], - octeon_bootinfo->mac_addr_base[3], - octeon_bootinfo->mac_addr_base[4], - octeon_bootinfo->mac_addr_base[5] + count - }; struct octeon_ethernet *priv = netdev_priv(dev); + struct sockaddr sa; + u64 mac = ((u64)(octeon_bootinfo->mac_addr_base[0] & 0xff) << 40) | + ((u64)(octeon_bootinfo->mac_addr_base[1] & 0xff) << 32) | + ((u64)(octeon_bootinfo->mac_addr_base[2] & 0xff) << 24) | + ((u64)(octeon_bootinfo->mac_addr_base[3] & 0xff) << 16) | + ((u64)(octeon_bootinfo->mac_addr_base[4] & 0xff) << 8) | + (u64)(octeon_bootinfo->mac_addr_base[5] & 0xff); + + mac += cvm_oct_mac_addr_offset; + sa.sa_data[0] = (mac >> 40) & 0xff; + sa.sa_data[1] = (mac >> 32) & 0xff; + sa.sa_data[2] = (mac >> 24) & 0xff; + sa.sa_data[3] = (mac >> 16) & 0xff; + sa.sa_data[4] = (mac >> 8) & 0xff; + sa.sa_data[5] = mac & 0xff; + + if (cvm_oct_mac_addr_offset >= octeon_bootinfo->mac_addr_count) + printk(KERN_DEBUG "%s: Using MAC outside of the assigned range:" + " %02x:%02x:%02x:%02x:%02x:%02x\n", dev->name, + sa.sa_data[0] & 0xff, sa.sa_data[1] & 0xff, + sa.sa_data[2] & 0xff, sa.sa_data[3] & 0xff, + sa.sa_data[4] & 0xff, sa.sa_data[5] & 0xff); + cvm_oct_mac_addr_offset++; /* * Force the interface to use the POW send if always_use_pow @@ -496,14 +520,12 @@ int cvm_oct_common_init(struct net_device *dev) if (priv->queue != -1 && USE_HW_TCPUDP_CHECKSUM) dev->features |= NETIF_F_IP_CSUM; - count++; - /* We do our own locking, Linux doesn't need to */ dev->features |= NETIF_F_LLTX; SET_ETHTOOL_OPS(dev, &cvm_oct_ethtool_ops); cvm_oct_mdio_setup_device(dev); - dev->netdev_ops->ndo_set_mac_address(dev, mac); + dev->netdev_ops->ndo_set_mac_address(dev, &sa); dev->netdev_ops->ndo_change_mtu(dev, dev->mtu); /* @@ -620,6 +642,13 @@ static int __init cvm_oct_init_module(void) pr_notice("cavium-ethernet %s\n", OCTEON_ETHERNET_VERSION); + if (OCTEON_IS_MODEL(OCTEON_CN52XX)) + cvm_oct_mac_addr_offset = 2; /* First two are the mgmt ports. */ + else if (OCTEON_IS_MODEL(OCTEON_CN56XX)) + cvm_oct_mac_addr_offset = 1; /* First one is the mgmt port. */ + else + cvm_oct_mac_addr_offset = 0; + cvm_oct_proc_initialize(); cvm_oct_rx_initialize(); cvm_oct_configure_common_hw(); diff --git a/drivers/staging/rtl8187se/TODO b/drivers/staging/rtl8187se/TODO index c09a9160739d..a762e79873e9 100644 --- a/drivers/staging/rtl8187se/TODO +++ b/drivers/staging/rtl8187se/TODO @@ -11,5 +11,4 @@ TODO: - sparse fixes - integrate with drivers/net/wireless/rtl818x -Please send any patches to Greg Kroah-Hartman <greg@kroah.com> and -Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>. +Please send any patches to Greg Kroah-Hartman <greg@kroah.com>. diff --git a/drivers/staging/rtl8192su/TODO b/drivers/staging/rtl8192su/TODO index b13be9edb278..f11eec700030 100644 --- a/drivers/staging/rtl8192su/TODO +++ b/drivers/staging/rtl8192su/TODO @@ -14,5 +14,4 @@ TODO: - sparse fixes - integrate with drivers/net/wireless/rtl818x -Please send any patches to Greg Kroah-Hartman <greg@kroah.com> and -Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>. +Please send any patches to Greg Kroah-Hartman <greg@kroah.com>. diff --git a/drivers/staging/vt6655/TODO b/drivers/staging/vt6655/TODO index 8462cd17eb61..cb04aaafc46f 100644 --- a/drivers/staging/vt6655/TODO +++ b/drivers/staging/vt6655/TODO @@ -16,6 +16,5 @@ TODO: - sparse fixes - integrate with drivers/net/wireless -Please send any patches to Greg Kroah-Hartman <greg@kroah.com>, -Forest Bond <forest@alittletooquiet.net> and Bartlomiej Zolnierkiewicz -<bzolnier@gmail.com>. +Please send any patches to Greg Kroah-Hartman <greg@kroah.com> +and Forest Bond <forest@alittletooquiet.net>. diff --git a/drivers/staging/vt6656/TODO b/drivers/staging/vt6656/TODO index 17cf50c6735e..a318995ba07f 100644 --- a/drivers/staging/vt6656/TODO +++ b/drivers/staging/vt6656/TODO @@ -15,6 +15,5 @@ TODO: - sparse fixes - integrate with drivers/net/wireless -Please send any patches to Greg Kroah-Hartman <greg@kroah.com>, -Forest Bond <forest@alittletooquiet.net> and Bartlomiej Zolnierkiewicz -<bzolnier@gmail.com>. +Please send any patches to Greg Kroah-Hartman <greg@kroah.com> +and Forest Bond <forest@alittletooquiet.net>. diff --git a/drivers/telephony/ixj_pcmcia.c b/drivers/telephony/ixj_pcmcia.c index 347c3ed1d9f1..d442fd35620a 100644 --- a/drivers/telephony/ixj_pcmcia.c +++ b/drivers/telephony/ixj_pcmcia.c @@ -19,13 +19,6 @@ * PCMCIA service support for Quicknet cards */ -#ifdef PCMCIA_DEBUG -static int pc_debug = PCMCIA_DEBUG; -module_param(pc_debug, int, 0644); -#define DEBUG(n, args...) if (pc_debug>(n)) printk(KERN_DEBUG args) -#else -#define DEBUG(n, args...) -#endif typedef struct ixj_info_t { int ndev; @@ -39,7 +32,7 @@ static void ixj_cs_release(struct pcmcia_device * link); static int ixj_probe(struct pcmcia_device *p_dev) { - DEBUG(0, "ixj_attach()\n"); + dev_dbg(&p_dev->dev, "ixj_attach()\n"); /* Create new ixj device */ p_dev->io.Attributes1 = IO_DATA_PATH_WIDTH_8; p_dev->io.Attributes2 = IO_DATA_PATH_WIDTH_8; @@ -55,33 +48,30 @@ static int ixj_probe(struct pcmcia_device *p_dev) static void ixj_detach(struct pcmcia_device *link) { - DEBUG(0, "ixj_detach(0x%p)\n", link); + dev_dbg(&link->dev, "ixj_detach\n"); ixj_cs_release(link); kfree(link->priv); } -#define CS_CHECK(fn, ret) \ -do { last_fn = (fn); if ((last_ret = (ret)) != 0) goto cs_failed; } while (0) - static void ixj_get_serial(struct pcmcia_device * link, IXJ * j) { char *str; int i, place; - DEBUG(0, "ixj_get_serial(0x%p)\n", link); + dev_dbg(&link->dev, "ixj_get_serial\n"); str = link->prod_id[0]; if (!str) - goto cs_failed; + goto failed; printk("%s", str); str = link->prod_id[1]; if (!str) - goto cs_failed; + goto failed; printk(" %s", str); str = link->prod_id[2]; if (!str) - goto cs_failed; + goto failed; place = 1; for (i = strlen(str) - 1; i >= 0; i--) { switch (str[i]) { @@ -118,9 +108,9 @@ static void ixj_get_serial(struct pcmcia_device * link, IXJ * j) } str = link->prod_id[3]; if (!str) - goto cs_failed; + goto failed; printk(" version %s\n", str); - cs_failed: +failed: return; } @@ -151,13 +141,13 @@ static int ixj_config(struct pcmcia_device * link) cistpl_cftable_entry_t dflt = { 0 }; info = link->priv; - DEBUG(0, "ixj_config(0x%p)\n", link); + dev_dbg(&link->dev, "ixj_config\n"); if (pcmcia_loop_config(link, ixj_config_check, &dflt)) - goto cs_failed; + goto failed; if (pcmcia_request_configuration(link, &link->conf)) - goto cs_failed; + goto failed; /* * Register the card with the core. @@ -170,7 +160,7 @@ static int ixj_config(struct pcmcia_device * link) ixj_get_serial(link, j); return 0; - cs_failed: +failed: ixj_cs_release(link); return -ENODEV; } @@ -178,7 +168,7 @@ static int ixj_config(struct pcmcia_device * link) static void ixj_cs_release(struct pcmcia_device *link) { ixj_info_t *info = link->priv; - DEBUG(0, "ixj_cs_release(0x%p)\n", link); + dev_dbg(&link->dev, "ixj_cs_release\n"); info->ndev = 0; pcmcia_disable_device(link); } diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 5ce839137ad6..0f857e645058 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -444,7 +444,7 @@ resubmit: static inline int hub_clear_tt_buffer (struct usb_device *hdev, u16 devinfo, u16 tt) { - return usb_control_msg(hdev, usb_rcvctrlpipe(hdev, 0), + return usb_control_msg(hdev, usb_sndctrlpipe(hdev, 0), HUB_CLEAR_TT_BUFFER, USB_RT_PORT, devinfo, tt, NULL, 0, 1000); } diff --git a/drivers/usb/gadget/amd5536udc.c b/drivers/usb/gadget/amd5536udc.c index d5b65962dd36..731150d4b1d9 100644 --- a/drivers/usb/gadget/amd5536udc.c +++ b/drivers/usb/gadget/amd5536udc.c @@ -1213,7 +1213,12 @@ udc_queue(struct usb_ep *usbep, struct usb_request *usbreq, gfp_t gfp) tmp &= AMD_UNMASK_BIT(ep->num); writel(tmp, &dev->regs->ep_irqmsk); } - } + } else if (ep->in) { + /* enable ep irq */ + tmp = readl(&dev->regs->ep_irqmsk); + tmp &= AMD_UNMASK_BIT(ep->num); + writel(tmp, &dev->regs->ep_irqmsk); + } } else if (ep->dma) { @@ -2005,18 +2010,17 @@ __acquires(dev->lock) { int tmp; - /* empty queues and init hardware */ - udc_basic_init(dev); - for (tmp = 0; tmp < UDC_EP_NUM; tmp++) { - empty_req_queue(&dev->ep[tmp]); - } - if (dev->gadget.speed != USB_SPEED_UNKNOWN) { spin_unlock(&dev->lock); driver->disconnect(&dev->gadget); spin_lock(&dev->lock); } - /* init */ + + /* empty queues and init hardware */ + udc_basic_init(dev); + for (tmp = 0; tmp < UDC_EP_NUM; tmp++) + empty_req_queue(&dev->ep[tmp]); + udc_setup_endpoints(dev); } @@ -2472,6 +2476,13 @@ static irqreturn_t udc_data_in_isr(struct udc *dev, int ep_ix) } } + } else if (!use_dma && ep->in) { + /* disable interrupt */ + tmp = readl( + &dev->regs->ep_irqmsk); + tmp |= AMD_BIT(ep->num); + writel(tmp, + &dev->regs->ep_irqmsk); } } /* clear status bits */ @@ -3279,6 +3290,17 @@ static int udc_pci_probe( goto finished; } + spin_lock_init(&dev->lock); + /* udc csr registers base */ + dev->csr = dev->virt_addr + UDC_CSR_ADDR; + /* dev registers base */ + dev->regs = dev->virt_addr + UDC_DEVCFG_ADDR; + /* ep registers base */ + dev->ep_regs = dev->virt_addr + UDC_EPREGS_ADDR; + /* fifo's base */ + dev->rxfifo = (u32 __iomem *)(dev->virt_addr + UDC_RXFIFO_ADDR); + dev->txfifo = (u32 __iomem *)(dev->virt_addr + UDC_TXFIFO_ADDR); + if (request_irq(pdev->irq, udc_irq, IRQF_SHARED, name, dev) != 0) { dev_dbg(&dev->pdev->dev, "request_irq(%d) fail\n", pdev->irq); kfree(dev); @@ -3331,7 +3353,6 @@ static int udc_probe(struct udc *dev) udc_pollstall_timer.data = 0; /* device struct setup */ - spin_lock_init(&dev->lock); dev->gadget.ops = &udc_ops; dev_set_name(&dev->gadget.dev, "gadget"); @@ -3340,16 +3361,6 @@ static int udc_probe(struct udc *dev) dev->gadget.name = name; dev->gadget.is_dualspeed = 1; - /* udc csr registers base */ - dev->csr = dev->virt_addr + UDC_CSR_ADDR; - /* dev registers base */ - dev->regs = dev->virt_addr + UDC_DEVCFG_ADDR; - /* ep registers base */ - dev->ep_regs = dev->virt_addr + UDC_EPREGS_ADDR; - /* fifo's base */ - dev->rxfifo = (u32 __iomem *)(dev->virt_addr + UDC_RXFIFO_ADDR); - dev->txfifo = (u32 __iomem *)(dev->virt_addr + UDC_TXFIFO_ADDR); - /* init registers, interrupts, ... */ startup_registers(dev); diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c index 9835e0713943..f5f5601701c9 100644 --- a/drivers/usb/host/ehci-hcd.c +++ b/drivers/usb/host/ehci-hcd.c @@ -28,6 +28,7 @@ #include <linux/errno.h> #include <linux/init.h> #include <linux/timer.h> +#include <linux/ktime.h> #include <linux/list.h> #include <linux/interrupt.h> #include <linux/usb.h> @@ -676,6 +677,7 @@ static int ehci_run (struct usb_hcd *hcd) ehci_readl(ehci, &ehci->regs->command); /* unblock posted writes */ msleep(5); up_write(&ehci_cf_port_reset_rwsem); + ehci->last_periodic_enable = ktime_get_real(); temp = HC_VERSION(ehci_readl(ehci, &ehci->caps->hc_capbase)); ehci_info (ehci, diff --git a/drivers/usb/host/ehci-pci.c b/drivers/usb/host/ehci-pci.c index 378861b9d79a..ead5f4f2aa5a 100644 --- a/drivers/usb/host/ehci-pci.c +++ b/drivers/usb/host/ehci-pci.c @@ -111,6 +111,10 @@ static int ehci_pci_setup(struct usb_hcd *hcd) switch (pdev->vendor) { case PCI_VENDOR_ID_INTEL: ehci->need_io_watchdog = 0; + if (pdev->device == 0x27cc) { + ehci->broken_periodic = 1; + ehci_info(ehci, "using broken periodic workaround\n"); + } break; case PCI_VENDOR_ID_TDI: if (pdev->device == PCI_DEVICE_ID_TDI_EHCI) { diff --git a/drivers/usb/host/ehci-q.c b/drivers/usb/host/ehci-q.c index 00ad9ce392ed..139a2cc3f641 100644 --- a/drivers/usb/host/ehci-q.c +++ b/drivers/usb/host/ehci-q.c @@ -487,8 +487,20 @@ halt: * we must clear the TT buffer (11.17.5). */ if (unlikely(last_status != -EINPROGRESS && - last_status != -EREMOTEIO)) - ehci_clear_tt_buffer(ehci, qh, urb, token); + last_status != -EREMOTEIO)) { + /* The TT's in some hubs malfunction when they + * receive this request following a STALL (they + * stop sending isochronous packets). Since a + * STALL can't leave the TT buffer in a busy + * state (if you believe Figures 11-48 - 11-51 + * in the USB 2.0 spec), we won't clear the TT + * buffer in this case. Strictly speaking this + * is a violation of the spec. + */ + if (last_status != -EPIPE) + ehci_clear_tt_buffer(ehci, qh, urb, + token); + } } /* if we're removing something not at the queue head, diff --git a/drivers/usb/host/ehci-sched.c b/drivers/usb/host/ehci-sched.c index b25cdea93a1f..a5535b5e3fe2 100644 --- a/drivers/usb/host/ehci-sched.c +++ b/drivers/usb/host/ehci-sched.c @@ -475,6 +475,8 @@ static int enable_periodic (struct ehci_hcd *ehci) /* make sure ehci_work scans these */ ehci->next_uframe = ehci_readl(ehci, &ehci->regs->frame_index) % (ehci->periodic_size << 3); + if (unlikely(ehci->broken_periodic)) + ehci->last_periodic_enable = ktime_get_real(); return 0; } @@ -486,6 +488,16 @@ static int disable_periodic (struct ehci_hcd *ehci) if (--ehci->periodic_sched) return 0; + if (unlikely(ehci->broken_periodic)) { + /* delay experimentally determined */ + ktime_t safe = ktime_add_us(ehci->last_periodic_enable, 1000); + ktime_t now = ktime_get_real(); + s64 delay = ktime_us_delta(safe, now); + + if (unlikely(delay > 0)) + udelay(delay); + } + /* did setting PSE not take effect yet? * takes effect only at frame boundaries... */ diff --git a/drivers/usb/host/ehci.h b/drivers/usb/host/ehci.h index 064e76821ff5..2d85e21ff282 100644 --- a/drivers/usb/host/ehci.h +++ b/drivers/usb/host/ehci.h @@ -118,6 +118,7 @@ struct ehci_hcd { /* one per controller */ unsigned stamp; unsigned random_frame; unsigned long next_statechange; + ktime_t last_periodic_enable; u32 command; /* SILICON QUIRKS */ @@ -127,6 +128,7 @@ struct ehci_hcd { /* one per controller */ unsigned big_endian_desc:1; unsigned has_amcc_usb23:1; unsigned need_io_watchdog:1; + unsigned broken_periodic:1; /* required for usb32 quirk */ #define OHCI_CTRL_HCFS (3 << 6) diff --git a/drivers/usb/host/sl811_cs.c b/drivers/usb/host/sl811_cs.c index 516848dd9b48..39d253e841f6 100644 --- a/drivers/usb/host/sl811_cs.c +++ b/drivers/usb/host/sl811_cs.c @@ -37,28 +37,8 @@ MODULE_LICENSE("GPL"); /* MACROS */ /*====================================================================*/ -#if defined(DEBUG) || defined(PCMCIA_DEBUG) - -static int pc_debug = 0; -module_param(pc_debug, int, 0644); - -#define DBG(n, args...) if (pc_debug>(n)) printk(KERN_DEBUG "sl811_cs: " args) - -#else -#define DBG(n, args...) do{}while(0) -#endif /* no debugging */ - #define INFO(args...) printk(KERN_INFO "sl811_cs: " args) -#define INT_MODULE_PARM(n, v) static int n = v; module_param(n, int, 0444) - -#define CS_CHECK(fn, ret) \ - do { \ - last_fn = (fn); \ - if ((last_ret = (ret)) != 0) \ - goto cs_failed; \ - } while (0) - /*====================================================================*/ /* VARIABLES */ /*====================================================================*/ @@ -76,7 +56,7 @@ static void sl811_cs_release(struct pcmcia_device * link); static void release_platform_dev(struct device * dev) { - DBG(0, "sl811_cs platform_dev release\n"); + dev_dbg(dev, "sl811_cs platform_dev release\n"); dev->parent = NULL; } @@ -140,7 +120,7 @@ static int sl811_hc_init(struct device *parent, resource_size_t base_addr, static void sl811_cs_detach(struct pcmcia_device *link) { - DBG(0, "sl811_cs_detach(0x%p)\n", link); + dev_dbg(&link->dev, "sl811_cs_detach\n"); sl811_cs_release(link); @@ -150,7 +130,7 @@ static void sl811_cs_detach(struct pcmcia_device *link) static void sl811_cs_release(struct pcmcia_device * link) { - DBG(0, "sl811_cs_release(0x%p)\n", link); + dev_dbg(&link->dev, "sl811_cs_release\n"); pcmcia_disable_device(link); platform_device_unregister(&platform_dev); @@ -205,11 +185,11 @@ static int sl811_cs_config_check(struct pcmcia_device *p_dev, static int sl811_cs_config(struct pcmcia_device *link) { - struct device *parent = &handle_to_dev(link); + struct device *parent = &link->dev; local_info_t *dev = link->priv; - int last_fn, last_ret; + int ret; - DBG(0, "sl811_cs_config(0x%p)\n", link); + dev_dbg(&link->dev, "sl811_cs_config\n"); if (pcmcia_loop_config(link, sl811_cs_config_check, NULL)) goto failed; @@ -217,14 +197,16 @@ static int sl811_cs_config(struct pcmcia_device *link) /* require an IRQ and two registers */ if (!link->io.NumPorts1 || link->io.NumPorts1 < 2) goto failed; - if (link->conf.Attributes & CONF_ENABLE_IRQ) - CS_CHECK(RequestIRQ, - pcmcia_request_irq(link, &link->irq)); - else + if (link->conf.Attributes & CONF_ENABLE_IRQ) { + ret = pcmcia_request_irq(link, &link->irq); + if (ret) + goto failed; + } else goto failed; - CS_CHECK(RequestConfiguration, - pcmcia_request_configuration(link, &link->conf)); + ret = pcmcia_request_configuration(link, &link->conf); + if (ret) + goto failed; sprintf(dev->node.dev_name, driver_name); dev->node.major = dev->node.minor = 0; @@ -241,8 +223,6 @@ static int sl811_cs_config(struct pcmcia_device *link) if (sl811_hc_init(parent, link->io.BasePort1, link->irq.AssignedIRQ) < 0) { -cs_failed: - cs_error(link, last_fn, last_ret); failed: printk(KERN_WARNING "sl811_cs_config failed\n"); sl811_cs_release(link); @@ -263,7 +243,6 @@ static int sl811_cs_probe(struct pcmcia_device *link) /* Initialize */ link->irq.Attributes = IRQ_TYPE_EXCLUSIVE; - link->irq.IRQInfo1 = IRQ_INFO2_VALID|IRQ_LEVEL_ID; link->irq.Handler = NULL; link->conf.Attributes = 0; diff --git a/drivers/usb/musb/cppi_dma.c b/drivers/usb/musb/cppi_dma.c index c3577bbbae6c..ef2332a9941d 100644 --- a/drivers/usb/musb/cppi_dma.c +++ b/drivers/usb/musb/cppi_dma.c @@ -1442,11 +1442,6 @@ static int cppi_channel_abort(struct dma_channel *channel) musb_writew(regs, MUSB_TXCSR, value); musb_writew(regs, MUSB_TXCSR, value); - /* re-enable interrupt */ - if (enabled) - musb_writel(tibase, DAVINCI_TXCPPI_INTENAB_REG, - (1 << cppi_ch->index)); - /* While we scrub the TX state RAM, ensure that we clean * up any interrupt that's currently asserted: * 1. Write to completion Ptr value 0x1(bit 0 set) @@ -1459,6 +1454,11 @@ static int cppi_channel_abort(struct dma_channel *channel) cppi_reset_tx(tx_ram, 1); musb_writel(&tx_ram->tx_complete, 0, 0); + /* re-enable interrupt */ + if (enabled) + musb_writel(tibase, DAVINCI_TXCPPI_INTENAB_REG, + (1 << cppi_ch->index)); + cppi_dump_tx(5, cppi_ch, " (done teardown)"); /* REVISIT tx side _should_ clean up the same way diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c index 3a61ddb62bd2..547e0e390726 100644 --- a/drivers/usb/musb/musb_core.c +++ b/drivers/usb/musb/musb_core.c @@ -1450,7 +1450,7 @@ static int __init musb_core_init(u16 musb_type, struct musb *musb) #endif if (hw_ep->max_packet_sz_tx) { - printk(KERN_DEBUG + DBG(1, "%s: hw_ep %d%s, %smax %d\n", musb_driver_name, i, hw_ep->is_shared_fifo ? "shared" : "tx", @@ -1459,7 +1459,7 @@ static int __init musb_core_init(u16 musb_type, struct musb *musb) hw_ep->max_packet_sz_tx); } if (hw_ep->max_packet_sz_rx && !hw_ep->is_shared_fifo) { - printk(KERN_DEBUG + DBG(1, "%s: hw_ep %d%s, %smax %d\n", musb_driver_name, i, "rx", diff --git a/drivers/usb/musb/musb_gadget.c b/drivers/usb/musb/musb_gadget.c index 8b3c4e2ed7b8..74073f9a43f0 100644 --- a/drivers/usb/musb/musb_gadget.c +++ b/drivers/usb/musb/musb_gadget.c @@ -4,6 +4,7 @@ * Copyright 2005 Mentor Graphics Corporation * Copyright (C) 2005-2006 by Texas Instruments * Copyright (C) 2006-2007 Nokia Corporation + * Copyright (C) 2009 MontaVista Software, Inc. <source@mvista.com> * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -436,14 +437,6 @@ void musb_g_tx(struct musb *musb, u8 epnum) csr |= MUSB_TXCSR_P_WZC_BITS; csr &= ~MUSB_TXCSR_P_SENTSTALL; musb_writew(epio, MUSB_TXCSR, csr); - if (dma_channel_status(dma) == MUSB_DMA_STATUS_BUSY) { - dma->status = MUSB_DMA_STATUS_CORE_ABORT; - musb->dma_controller->channel_abort(dma); - } - - if (request) - musb_g_giveback(musb_ep, request, -EPIPE); - break; } @@ -582,15 +575,25 @@ void musb_g_tx(struct musb *musb, u8 epnum) */ static void rxstate(struct musb *musb, struct musb_request *req) { - u16 csr = 0; const u8 epnum = req->epnum; struct usb_request *request = &req->request; struct musb_ep *musb_ep = &musb->endpoints[epnum].ep_out; void __iomem *epio = musb->endpoints[epnum].regs; unsigned fifo_count = 0; u16 len = musb_ep->packet_sz; + u16 csr = musb_readw(epio, MUSB_RXCSR); - csr = musb_readw(epio, MUSB_RXCSR); + /* We shouldn't get here while DMA is active, but we do... */ + if (dma_channel_status(musb_ep->dma) == MUSB_DMA_STATUS_BUSY) { + DBG(4, "DMA pending...\n"); + return; + } + + if (csr & MUSB_RXCSR_P_SENDSTALL) { + DBG(5, "%s stalling, RXCSR %04x\n", + musb_ep->end_point.name, csr); + return; + } if (is_cppi_enabled() && musb_ep->dma) { struct dma_controller *c = musb->dma_controller; @@ -761,19 +764,10 @@ void musb_g_rx(struct musb *musb, u8 epnum) csr, dma ? " (dma)" : "", request); if (csr & MUSB_RXCSR_P_SENTSTALL) { - if (dma_channel_status(dma) == MUSB_DMA_STATUS_BUSY) { - dma->status = MUSB_DMA_STATUS_CORE_ABORT; - (void) musb->dma_controller->channel_abort(dma); - request->actual += musb_ep->dma->actual_len; - } - csr |= MUSB_RXCSR_P_WZC_BITS; csr &= ~MUSB_RXCSR_P_SENTSTALL; musb_writew(epio, MUSB_RXCSR, csr); - - if (request) - musb_g_giveback(musb_ep, request, -EPIPE); - goto done; + return; } if (csr & MUSB_RXCSR_P_OVERRUN) { @@ -795,7 +789,7 @@ void musb_g_rx(struct musb *musb, u8 epnum) DBG((csr & MUSB_RXCSR_DMAENAB) ? 4 : 1, "%s busy, csr %04x\n", musb_ep->end_point.name, csr); - goto done; + return; } if (dma && (csr & MUSB_RXCSR_DMAENAB)) { @@ -826,22 +820,15 @@ void musb_g_rx(struct musb *musb, u8 epnum) if ((request->actual < request->length) && (musb_ep->dma->actual_len == musb_ep->packet_sz)) - goto done; + return; #endif musb_g_giveback(musb_ep, request, 0); request = next_request(musb_ep); if (!request) - goto done; - - /* don't start more i/o till the stall clears */ - musb_ep_select(mbase, epnum); - csr = musb_readw(epio, MUSB_RXCSR); - if (csr & MUSB_RXCSR_P_SENDSTALL) - goto done; + return; } - /* analyze request if the ep is hot */ if (request) rxstate(musb, to_musb_request(request)); @@ -849,8 +836,6 @@ void musb_g_rx(struct musb *musb, u8 epnum) DBG(3, "packet waiting for %s%s request\n", musb_ep->desc ? "" : "inactive ", musb_ep->end_point.name); - -done: return; } @@ -1244,7 +1229,7 @@ int musb_gadget_set_halt(struct usb_ep *ep, int value) void __iomem *mbase; unsigned long flags; u16 csr; - struct musb_request *request = NULL; + struct musb_request *request; int status = 0; if (!ep) @@ -1260,24 +1245,29 @@ int musb_gadget_set_halt(struct usb_ep *ep, int value) musb_ep_select(mbase, epnum); - /* cannot portably stall with non-empty FIFO */ request = to_musb_request(next_request(musb_ep)); - if (value && musb_ep->is_in) { - csr = musb_readw(epio, MUSB_TXCSR); - if (csr & MUSB_TXCSR_FIFONOTEMPTY) { - DBG(3, "%s fifo busy, cannot halt\n", ep->name); - spin_unlock_irqrestore(&musb->lock, flags); - return -EAGAIN; + if (value) { + if (request) { + DBG(3, "request in progress, cannot halt %s\n", + ep->name); + status = -EAGAIN; + goto done; + } + /* Cannot portably stall with non-empty FIFO */ + if (musb_ep->is_in) { + csr = musb_readw(epio, MUSB_TXCSR); + if (csr & MUSB_TXCSR_FIFONOTEMPTY) { + DBG(3, "FIFO busy, cannot halt %s\n", ep->name); + status = -EAGAIN; + goto done; + } } - } /* set/clear the stall and toggle bits */ DBG(2, "%s: %s stall\n", ep->name, value ? "set" : "clear"); if (musb_ep->is_in) { csr = musb_readw(epio, MUSB_TXCSR); - if (csr & MUSB_TXCSR_FIFONOTEMPTY) - csr |= MUSB_TXCSR_FLUSHFIFO; csr |= MUSB_TXCSR_P_WZC_BITS | MUSB_TXCSR_CLRDATATOG; if (value) @@ -1300,14 +1290,13 @@ int musb_gadget_set_halt(struct usb_ep *ep, int value) musb_writew(epio, MUSB_RXCSR, csr); } -done: - /* maybe start the first request in the queue */ if (!musb_ep->busy && !value && request) { DBG(3, "restarting the request\n"); musb_ep_restart(musb, request); } +done: spin_unlock_irqrestore(&musb->lock, flags); return status; } diff --git a/drivers/usb/musb/musb_gadget_ep0.c b/drivers/usb/musb/musb_gadget_ep0.c index 7a6778675ad3..522efb31b56b 100644 --- a/drivers/usb/musb/musb_gadget_ep0.c +++ b/drivers/usb/musb/musb_gadget_ep0.c @@ -511,7 +511,8 @@ static void ep0_txstate(struct musb *musb) /* update the flags */ if (fifo_count < MUSB_MAX_END0_PACKET - || request->actual == request->length) { + || (request->actual == request->length + && !request->zero)) { musb->ep0_state = MUSB_EP0_STAGE_STATUSOUT; csr |= MUSB_CSR0_P_DATAEND; } else diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c index cf94511485f2..e3ab40a966eb 100644 --- a/drivers/usb/musb/musb_host.c +++ b/drivers/usb/musb/musb_host.c @@ -1301,8 +1301,11 @@ void musb_host_tx(struct musb *musb, u8 epnum) return; } else if (usb_pipeisoc(pipe) && dma) { if (musb_tx_dma_program(musb->dma_controller, hw_ep, qh, urb, - offset, length)) + offset, length)) { + if (is_cppi_enabled() || tusb_dma_omap()) + musb_h_tx_dma_start(hw_ep); return; + } } else if (tx_csr & MUSB_TXCSR_DMAENAB) { DBG(1, "not complete, but DMA enabled?\n"); return; diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 9c60d6d4908a..ebcc6d0e2e91 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -1937,7 +1937,7 @@ static void ftdi_write_bulk_callback(struct urb *urb) return; } /* account for transferred data */ - countback = urb->actual_length; + countback = urb->transfer_buffer_length; data_offset = priv->write_offset; if (data_offset > 0) { /* Subtract the control bytes */ @@ -1950,7 +1950,6 @@ static void ftdi_write_bulk_callback(struct urb *urb) if (status) { dbg("nonzero write bulk status received: %d", status); - return; } usb_serial_port_softint(port); diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 319aaf9725b3..0577e4b61114 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -336,6 +336,10 @@ static int option_resume(struct usb_serial *serial); #define AIRPLUS_VENDOR_ID 0x1011 #define AIRPLUS_PRODUCT_MCD650 0x3198 +/* 4G Systems products */ +#define FOUR_G_SYSTEMS_VENDOR_ID 0x1c9e +#define FOUR_G_SYSTEMS_PRODUCT_W14 0x9603 + static struct usb_device_id option_ids[] = { { USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_COLT) }, { USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_RICOLA) }, @@ -599,6 +603,7 @@ static struct usb_device_id option_ids[] = { { USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_X060S) }, { USB_DEVICE(AIRPLUS_VENDOR_ID, AIRPLUS_PRODUCT_MCD650) }, { USB_DEVICE(TLAYTECH_VENDOR_ID, TLAYTECH_PRODUCT_TEU800) }, + { USB_DEVICE(FOUR_G_SYSTEMS_VENDOR_ID, FOUR_G_SYSTEMS_PRODUCT_W14) }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, option_ids); diff --git a/drivers/video/da8xx-fb.c b/drivers/video/da8xx-fb.c index 035d56835b75..ea1fd3f47511 100644 --- a/drivers/video/da8xx-fb.c +++ b/drivers/video/da8xx-fb.c @@ -554,11 +554,11 @@ static int fb_check_var(struct fb_var_screeninfo *var, var->transp.length = 0; break; case 16: /* RGB 565 */ - var->red.offset = 0; + var->red.offset = 11; var->red.length = 5; var->green.offset = 5; var->green.length = 6; - var->blue.offset = 11; + var->blue.offset = 0; var->blue.length = 5; var->transp.offset = 0; var->transp.length = 0; @@ -591,7 +591,7 @@ static int __devexit fb_remove(struct platform_device *dev) unregister_framebuffer(info); fb_dealloc_cmap(&info->cmap); dma_free_coherent(NULL, par->databuf_sz + PAGE_SIZE, - info->screen_base, + info->screen_base - PAGE_SIZE, info->fix.smem_start); free_irq(par->irq, par); clk_disable(par->lcdc_clk); @@ -749,6 +749,7 @@ static int __init fb_probe(struct platform_device *device) (PAGE_SIZE - par->palette_sz); /* the rest of the frame buffer is pixel data */ + da8xx_fb_info->screen_base = par->v_palette_base + par->palette_sz; da8xx_fb_fix.smem_start = par->p_palette_base + par->palette_sz; da8xx_fb_fix.smem_len = par->databuf_sz - par->palette_sz; da8xx_fb_fix.line_length = (lcdc_info->width * lcd_cfg->bpp) / 8; @@ -787,6 +788,8 @@ static int __init fb_probe(struct platform_device *device) da8xx_fb_info->var = da8xx_fb_var; da8xx_fb_info->fbops = &da8xx_fb_ops; da8xx_fb_info->pseudo_palette = par->pseudo_palette; + da8xx_fb_info->fix.visual = (da8xx_fb_info->var.bits_per_pixel <= 8) ? + FB_VISUAL_PSEUDOCOLOR : FB_VISUAL_TRUECOLOR; ret = fb_alloc_cmap(&da8xx_fb_info->cmap, PALETTE_SIZE, 0); if (ret) @@ -825,7 +828,7 @@ err_free_irq: err_release_fb_mem: dma_free_coherent(NULL, par->databuf_sz + PAGE_SIZE, - da8xx_fb_info->screen_base, + da8xx_fb_info->screen_base - PAGE_SIZE, da8xx_fb_info->fix.smem_start); err_release_fb: diff --git a/drivers/video/gbefb.c b/drivers/video/gbefb.c index 1a83709f9611..f67db4268374 100644 --- a/drivers/video/gbefb.c +++ b/drivers/video/gbefb.c @@ -1147,7 +1147,7 @@ static int __init gbefb_probe(struct platform_device *p_dev) gbefb_setup(options); #endif - if (!request_region(GBE_BASE, sizeof(struct sgi_gbe), "GBE")) { + if (!request_mem_region(GBE_BASE, sizeof(struct sgi_gbe), "GBE")) { printk(KERN_ERR "gbefb: couldn't reserve mmio region\n"); ret = -EBUSY; goto out_release_framebuffer; diff --git a/drivers/watchdog/pnx4008_wdt.c b/drivers/watchdog/pnx4008_wdt.c index f24d04132eda..4d227b152001 100644 --- a/drivers/watchdog/pnx4008_wdt.c +++ b/drivers/watchdog/pnx4008_wdt.c @@ -317,7 +317,7 @@ static int __devexit pnx4008_wdt_remove(struct platform_device *pdev) static struct platform_driver platform_wdt_driver = { .driver = { - .name = "watchdog", + .name = "pnx4008-watchdog", .owner = THIS_MODULE, }, .probe = pnx4008_wdt_probe, @@ -352,4 +352,4 @@ MODULE_PARM_DESC(nowayout, MODULE_LICENSE("GPL"); MODULE_ALIAS_MISCDEV(WATCHDOG_MINOR); -MODULE_ALIAS("platform:watchdog"); +MODULE_ALIAS("platform:pnx4008-watchdog"); diff --git a/drivers/watchdog/rc32434_wdt.c b/drivers/watchdog/rc32434_wdt.c index f6cccc9df022..bf12d06b5877 100644 --- a/drivers/watchdog/rc32434_wdt.c +++ b/drivers/watchdog/rc32434_wdt.c @@ -62,7 +62,7 @@ extern unsigned int idt_cpu_freq; static int timeout = WATCHDOG_TIMEOUT; module_param(timeout, int, 0); MODULE_PARM_DESC(timeout, "Watchdog timeout value, in seconds (default=" - WATCHDOG_TIMEOUT ")"); + __MODULE_STRING(WATCHDOG_TIMEOUT) ")"); static int nowayout = WATCHDOG_NOWAYOUT; module_param(nowayout, int, 0); @@ -276,7 +276,7 @@ static int __devinit rc32434_wdt_probe(struct platform_device *pdev) return -ENODEV; } - wdt_reg = ioremap_nocache(r->start, r->end - r->start); + wdt_reg = ioremap_nocache(r->start, resource_size(r)); if (!wdt_reg) { printk(KERN_ERR PFX "failed to remap I/O resources\n"); return -ENXIO; diff --git a/fs/9p/cache.c b/fs/9p/cache.c index 51c94e26a346..e777961939f3 100644 --- a/fs/9p/cache.c +++ b/fs/9p/cache.c @@ -343,18 +343,7 @@ int __v9fs_fscache_release_page(struct page *page, gfp_t gfp) BUG_ON(!vcookie->fscache); - if (PageFsCache(page)) { - if (fscache_check_page_write(vcookie->fscache, page)) { - if (!(gfp & __GFP_WAIT)) - return 0; - fscache_wait_on_page_write(vcookie->fscache, page); - } - - fscache_uncache_page(vcookie->fscache, page); - ClearPageFsCache(page); - } - - return 1; + return fscache_maybe_release_page(vcookie->fscache, page, gfp); } void __v9fs_fscache_invalidate_page(struct page *page) @@ -368,7 +357,6 @@ void __v9fs_fscache_invalidate_page(struct page *page) fscache_wait_on_page_write(vcookie->fscache, page); BUG_ON(!PageLocked(page)); fscache_uncache_page(vcookie->fscache, page); - ClearPageFsCache(page); } } diff --git a/fs/afs/file.c b/fs/afs/file.c index 681c2a7b013f..39b301662f22 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -315,7 +315,6 @@ static void afs_invalidatepage(struct page *page, unsigned long offset) struct afs_vnode *vnode = AFS_FS_I(page->mapping->host); fscache_wait_on_page_write(vnode->cache, page); fscache_uncache_page(vnode->cache, page); - ClearPageFsCache(page); } #endif @@ -349,17 +348,9 @@ static int afs_releasepage(struct page *page, gfp_t gfp_flags) /* deny if page is being written to the cache and the caller hasn't * elected to wait */ #ifdef CONFIG_AFS_FSCACHE - if (PageFsCache(page)) { - if (fscache_check_page_write(vnode->cache, page)) { - if (!(gfp_flags & __GFP_WAIT)) { - _leave(" = F [cache busy]"); - return 0; - } - fscache_wait_on_page_write(vnode->cache, page); - } - - fscache_uncache_page(vnode->cache, page); - ClearPageFsCache(page); + if (!fscache_maybe_release_page(vnode->cache, page, gfp_flags)) { + _leave(" = F [cache busy]"); + return 0; } #endif diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c index 431accd475a7..27089311fbea 100644 --- a/fs/cachefiles/interface.c +++ b/fs/cachefiles/interface.c @@ -114,8 +114,9 @@ nomem_lookup_data: /* * attempt to look up the nominated node in this cache + * - return -ETIMEDOUT to be scheduled again */ -static void cachefiles_lookup_object(struct fscache_object *_object) +static int cachefiles_lookup_object(struct fscache_object *_object) { struct cachefiles_lookup_data *lookup_data; struct cachefiles_object *parent, *object; @@ -145,13 +146,15 @@ static void cachefiles_lookup_object(struct fscache_object *_object) object->fscache.cookie->def->type != FSCACHE_COOKIE_TYPE_INDEX) cachefiles_attr_changed(&object->fscache); - if (ret < 0) { - printk(KERN_WARNING "CacheFiles: Lookup failed error %d\n", - ret); + if (ret < 0 && ret != -ETIMEDOUT) { + if (ret != -ENOBUFS) + printk(KERN_WARNING + "CacheFiles: Lookup failed error %d\n", ret); fscache_object_lookup_error(&object->fscache); } _leave(" [%d]", ret); + return ret; } /* @@ -331,6 +334,7 @@ static void cachefiles_put_object(struct fscache_object *_object) } cache = object->fscache.cache; + fscache_object_destroy(&object->fscache); kmem_cache_free(cachefiles_object_jar, object); fscache_object_destroyed(cache); } @@ -403,12 +407,26 @@ static int cachefiles_attr_changed(struct fscache_object *_object) if (oi_size == ni_size) return 0; - newattrs.ia_size = ni_size; - newattrs.ia_valid = ATTR_SIZE; - cachefiles_begin_secure(cache, &saved_cred); mutex_lock(&object->backer->d_inode->i_mutex); + + /* if there's an extension to a partial page at the end of the backing + * file, we need to discard the partial page so that we pick up new + * data after it */ + if (oi_size & ~PAGE_MASK && ni_size > oi_size) { + _debug("discard tail %llx", oi_size); + newattrs.ia_valid = ATTR_SIZE; + newattrs.ia_size = oi_size & PAGE_MASK; + ret = notify_change(object->backer, &newattrs); + if (ret < 0) + goto truncate_failed; + } + + newattrs.ia_valid = ATTR_SIZE; + newattrs.ia_size = ni_size; ret = notify_change(object->backer, &newattrs); + +truncate_failed: mutex_unlock(&object->backer->d_inode->i_mutex); cachefiles_end_secure(cache, saved_cred); diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index 4ce818ae39ea..14ac4806e291 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -21,17 +21,81 @@ #include <linux/security.h> #include "internal.h" -static int cachefiles_wait_bit(void *flags) +#define CACHEFILES_KEYBUF_SIZE 512 + +/* + * dump debugging info about an object + */ +static noinline +void __cachefiles_printk_object(struct cachefiles_object *object, + const char *prefix, + u8 *keybuf) { - schedule(); - return 0; + struct fscache_cookie *cookie; + unsigned keylen, loop; + + printk(KERN_ERR "%sobject: OBJ%x\n", + prefix, object->fscache.debug_id); + printk(KERN_ERR "%sobjstate=%s fl=%lx swfl=%lx ev=%lx[%lx]\n", + prefix, fscache_object_states[object->fscache.state], + object->fscache.flags, object->fscache.work.flags, + object->fscache.events, + object->fscache.event_mask & FSCACHE_OBJECT_EVENTS_MASK); + printk(KERN_ERR "%sops=%u inp=%u exc=%u\n", + prefix, object->fscache.n_ops, object->fscache.n_in_progress, + object->fscache.n_exclusive); + printk(KERN_ERR "%sparent=%p\n", + prefix, object->fscache.parent); + + spin_lock(&object->fscache.lock); + cookie = object->fscache.cookie; + if (cookie) { + printk(KERN_ERR "%scookie=%p [pr=%p nd=%p fl=%lx]\n", + prefix, + object->fscache.cookie, + object->fscache.cookie->parent, + object->fscache.cookie->netfs_data, + object->fscache.cookie->flags); + if (keybuf) + keylen = cookie->def->get_key(cookie->netfs_data, keybuf, + CACHEFILES_KEYBUF_SIZE); + else + keylen = 0; + } else { + printk(KERN_ERR "%scookie=NULL\n", prefix); + keylen = 0; + } + spin_unlock(&object->fscache.lock); + + if (keylen) { + printk(KERN_ERR "%skey=[%u] '", prefix, keylen); + for (loop = 0; loop < keylen; loop++) + printk("%02x", keybuf[loop]); + printk("'\n"); + } +} + +/* + * dump debugging info about a pair of objects + */ +static noinline void cachefiles_printk_object(struct cachefiles_object *object, + struct cachefiles_object *xobject) +{ + u8 *keybuf; + + keybuf = kmalloc(CACHEFILES_KEYBUF_SIZE, GFP_NOIO); + if (object) + __cachefiles_printk_object(object, "", keybuf); + if (xobject) + __cachefiles_printk_object(xobject, "x", keybuf); + kfree(keybuf); } /* * record the fact that an object is now active */ -static void cachefiles_mark_object_active(struct cachefiles_cache *cache, - struct cachefiles_object *object) +static int cachefiles_mark_object_active(struct cachefiles_cache *cache, + struct cachefiles_object *object) { struct cachefiles_object *xobject; struct rb_node **_p, *_parent = NULL; @@ -42,8 +106,11 @@ static void cachefiles_mark_object_active(struct cachefiles_cache *cache, try_again: write_lock(&cache->active_lock); - if (test_and_set_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags)) + if (test_and_set_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags)) { + printk(KERN_ERR "CacheFiles: Error: Object already active\n"); + cachefiles_printk_object(object, NULL); BUG(); + } dentry = object->dentry; _p = &cache->active_nodes.rb_node; @@ -66,8 +133,8 @@ try_again: rb_insert_color(&object->active_node, &cache->active_nodes); write_unlock(&cache->active_lock); - _leave(""); - return; + _leave(" = 0"); + return 0; /* an old object from a previous incarnation is hogging the slot - we * need to wait for it to be destroyed */ @@ -76,44 +143,70 @@ wait_for_old_object: printk(KERN_ERR "\n"); printk(KERN_ERR "CacheFiles: Error:" " Unexpected object collision\n"); - printk(KERN_ERR "xobject: OBJ%x\n", - xobject->fscache.debug_id); - printk(KERN_ERR "xobjstate=%s\n", - fscache_object_states[xobject->fscache.state]); - printk(KERN_ERR "xobjflags=%lx\n", xobject->fscache.flags); - printk(KERN_ERR "xobjevent=%lx [%lx]\n", - xobject->fscache.events, xobject->fscache.event_mask); - printk(KERN_ERR "xops=%u inp=%u exc=%u\n", - xobject->fscache.n_ops, xobject->fscache.n_in_progress, - xobject->fscache.n_exclusive); - printk(KERN_ERR "xcookie=%p [pr=%p nd=%p fl=%lx]\n", - xobject->fscache.cookie, - xobject->fscache.cookie->parent, - xobject->fscache.cookie->netfs_data, - xobject->fscache.cookie->flags); - printk(KERN_ERR "xparent=%p\n", - xobject->fscache.parent); - printk(KERN_ERR "object: OBJ%x\n", - object->fscache.debug_id); - printk(KERN_ERR "cookie=%p [pr=%p nd=%p fl=%lx]\n", - object->fscache.cookie, - object->fscache.cookie->parent, - object->fscache.cookie->netfs_data, - object->fscache.cookie->flags); - printk(KERN_ERR "parent=%p\n", - object->fscache.parent); + cachefiles_printk_object(object, xobject); BUG(); } atomic_inc(&xobject->usage); write_unlock(&cache->active_lock); - _debug(">>> wait"); - wait_on_bit(&xobject->flags, CACHEFILES_OBJECT_ACTIVE, - cachefiles_wait_bit, TASK_UNINTERRUPTIBLE); - _debug("<<< waited"); + if (test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags)) { + wait_queue_head_t *wq; + + signed long timeout = 60 * HZ; + wait_queue_t wait; + bool requeue; + + /* if the object we're waiting for is queued for processing, + * then just put ourselves on the queue behind it */ + if (slow_work_is_queued(&xobject->fscache.work)) { + _debug("queue OBJ%x behind OBJ%x immediately", + object->fscache.debug_id, + xobject->fscache.debug_id); + goto requeue; + } + + /* otherwise we sleep until either the object we're waiting for + * is done, or the slow-work facility wants the thread back to + * do other work */ + wq = bit_waitqueue(&xobject->flags, CACHEFILES_OBJECT_ACTIVE); + init_wait(&wait); + requeue = false; + do { + prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE); + if (!test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags)) + break; + requeue = slow_work_sleep_till_thread_needed( + &object->fscache.work, &timeout); + } while (timeout > 0 && !requeue); + finish_wait(wq, &wait); + + if (requeue && + test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags)) { + _debug("queue OBJ%x behind OBJ%x after wait", + object->fscache.debug_id, + xobject->fscache.debug_id); + goto requeue; + } + + if (timeout <= 0) { + printk(KERN_ERR "\n"); + printk(KERN_ERR "CacheFiles: Error: Overlong" + " wait for old active object to go away\n"); + cachefiles_printk_object(object, xobject); + goto requeue; + } + } + + ASSERT(!test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags)); cache->cache.ops->put_object(&xobject->fscache); goto try_again; + +requeue: + clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags); + cache->cache.ops->put_object(&xobject->fscache); + _leave(" = -ETIMEDOUT"); + return -ETIMEDOUT; } /* @@ -254,7 +347,7 @@ int cachefiles_delete_object(struct cachefiles_cache *cache, dir = dget_parent(object->dentry); - mutex_lock(&dir->d_inode->i_mutex); + mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT); ret = cachefiles_bury_object(cache, dir, object->dentry); dput(dir); @@ -307,7 +400,7 @@ lookup_again: /* search the current directory for the element name */ _debug("lookup '%s'", name); - mutex_lock(&dir->d_inode->i_mutex); + mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT); start = jiffies; next = lookup_one_len(name, dir, nlen); @@ -418,12 +511,15 @@ lookup_again: } /* note that we're now using this object */ - cachefiles_mark_object_active(cache, object); + ret = cachefiles_mark_object_active(cache, object); mutex_unlock(&dir->d_inode->i_mutex); dput(dir); dir = NULL; + if (ret == -ETIMEDOUT) + goto mark_active_timed_out; + _debug("=== OBTAINED_OBJECT ==="); if (object->new) { @@ -467,6 +563,10 @@ create_error: cachefiles_io_error(cache, "Create/mkdir failed"); goto error; +mark_active_timed_out: + _debug("mark active timed out"); + goto release_dentry; + check_error: _debug("check error %d", ret); write_lock(&cache->active_lock); @@ -474,7 +574,7 @@ check_error: clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags); wake_up_bit(&object->flags, CACHEFILES_OBJECT_ACTIVE); write_unlock(&cache->active_lock); - +release_dentry: dput(object->dentry); object->dentry = NULL; goto error_out; @@ -495,9 +595,6 @@ error: error_out2: dput(dir); error_out: - if (ret == -ENOSPC) - ret = -ENOBUFS; - _leave(" = error %d", -ret); return ret; } diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index a69787e7dd96..a6c8c6fe8df9 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -11,6 +11,7 @@ #include <linux/mount.h> #include <linux/file.h> +#include <linux/ima.h> #include "internal.h" /* @@ -40,8 +41,10 @@ static int cachefiles_read_waiter(wait_queue_t *wait, unsigned mode, _debug("--- monitor %p %lx ---", page, page->flags); - if (!PageUptodate(page) && !PageError(page)) - dump_stack(); + if (!PageUptodate(page) && !PageError(page)) { + /* unlocked, not uptodate and not erronous? */ + _debug("page probably truncated"); + } /* remove from the waitqueue */ list_del(&wait->task_list); @@ -61,6 +64,84 @@ static int cachefiles_read_waiter(wait_queue_t *wait, unsigned mode, } /* + * handle a probably truncated page + * - check to see if the page is still relevant and reissue the read if + * possible + * - return -EIO on error, -ENODATA if the page is gone, -EINPROGRESS if we + * must wait again and 0 if successful + */ +static int cachefiles_read_reissue(struct cachefiles_object *object, + struct cachefiles_one_read *monitor) +{ + struct address_space *bmapping = object->backer->d_inode->i_mapping; + struct page *backpage = monitor->back_page, *backpage2; + int ret; + + kenter("{ino=%lx},{%lx,%lx}", + object->backer->d_inode->i_ino, + backpage->index, backpage->flags); + + /* skip if the page was truncated away completely */ + if (backpage->mapping != bmapping) { + kleave(" = -ENODATA [mapping]"); + return -ENODATA; + } + + backpage2 = find_get_page(bmapping, backpage->index); + if (!backpage2) { + kleave(" = -ENODATA [gone]"); + return -ENODATA; + } + + if (backpage != backpage2) { + put_page(backpage2); + kleave(" = -ENODATA [different]"); + return -ENODATA; + } + + /* the page is still there and we already have a ref on it, so we don't + * need a second */ + put_page(backpage2); + + INIT_LIST_HEAD(&monitor->op_link); + add_page_wait_queue(backpage, &monitor->monitor); + + if (trylock_page(backpage)) { + ret = -EIO; + if (PageError(backpage)) + goto unlock_discard; + ret = 0; + if (PageUptodate(backpage)) + goto unlock_discard; + + kdebug("reissue read"); + ret = bmapping->a_ops->readpage(NULL, backpage); + if (ret < 0) + goto unlock_discard; + } + + /* but the page may have been read before the monitor was installed, so + * the monitor may miss the event - so we have to ensure that we do get + * one in such a case */ + if (trylock_page(backpage)) { + _debug("jumpstart %p {%lx}", backpage, backpage->flags); + unlock_page(backpage); + } + + /* it'll reappear on the todo list */ + kleave(" = -EINPROGRESS"); + return -EINPROGRESS; + +unlock_discard: + unlock_page(backpage); + spin_lock_irq(&object->work_lock); + list_del(&monitor->op_link); + spin_unlock_irq(&object->work_lock); + kleave(" = %d", ret); + return ret; +} + +/* * copy data from backing pages to netfs pages to complete a read operation * - driven by FS-Cache's thread pool */ @@ -92,20 +173,26 @@ static void cachefiles_read_copier(struct fscache_operation *_op) _debug("- copy {%lu}", monitor->back_page->index); - error = -EIO; + recheck: if (PageUptodate(monitor->back_page)) { copy_highpage(monitor->netfs_page, monitor->back_page); pagevec_add(&pagevec, monitor->netfs_page); fscache_mark_pages_cached(monitor->op, &pagevec); error = 0; - } - - if (error) + } else if (!PageError(monitor->back_page)) { + /* the page has probably been truncated */ + error = cachefiles_read_reissue(object, monitor); + if (error == -EINPROGRESS) + goto next; + goto recheck; + } else { cachefiles_io_error_obj( object, "Readpage failed on backing file %lx", (unsigned long) monitor->back_page->flags); + error = -EIO; + } page_cache_release(monitor->back_page); @@ -114,6 +201,7 @@ static void cachefiles_read_copier(struct fscache_operation *_op) fscache_put_retrieval(op); kfree(monitor); + next: /* let the thread pool have some air occasionally */ max--; if (max < 0 || need_resched()) { @@ -333,7 +421,8 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op, shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits; - op->op.flags = FSCACHE_OP_FAST; + op->op.flags &= FSCACHE_OP_KEEP_FLAGS; + op->op.flags |= FSCACHE_OP_FAST; op->op.processor = cachefiles_read_copier; pagevec_init(&pagevec, 0); @@ -639,7 +728,8 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op, pagevec_init(&pagevec, 0); - op->op.flags = FSCACHE_OP_FAST; + op->op.flags &= FSCACHE_OP_KEEP_FLAGS; + op->op.flags |= FSCACHE_OP_FAST; op->op.processor = cachefiles_read_copier; INIT_LIST_HEAD(&backpages); @@ -801,7 +891,8 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page) struct cachefiles_cache *cache; mm_segment_t old_fs; struct file *file; - loff_t pos; + loff_t pos, eof; + size_t len; void *data; int ret; @@ -832,18 +923,33 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page) if (IS_ERR(file)) { ret = PTR_ERR(file); } else { + ima_counts_get(file); ret = -EIO; if (file->f_op->write) { pos = (loff_t) page->index << PAGE_SHIFT; + + /* we mustn't write more data than we have, so we have + * to beware of a partial page at EOF */ + eof = object->fscache.store_limit_l; + len = PAGE_SIZE; + if (eof & ~PAGE_MASK) { + ASSERTCMP(pos, <, eof); + if (eof - pos < PAGE_SIZE) { + _debug("cut short %llx to %llx", + pos, eof); + len = eof - pos; + ASSERTCMP(pos + len, ==, eof); + } + } + data = kmap(page); old_fs = get_fs(); set_fs(KERNEL_DS); ret = file->f_op->write( - file, (const void __user *) data, PAGE_SIZE, - &pos); + file, (const void __user *) data, len, &pos); set_fs(old_fs); kunmap(page); - if (ret != PAGE_SIZE) + if (ret != len) ret = -EIO; } fput(file); diff --git a/fs/cifs/CHANGES b/fs/cifs/CHANGES index 145540a316ab..094ea65afc85 100644 --- a/fs/cifs/CHANGES +++ b/fs/cifs/CHANGES @@ -1,3 +1,12 @@ +Version 1.61 +------------ +Fix append problem to Samba servers (files opened with O_APPEND could +have duplicated data). Fix oops in cifs_lookup. Workaround problem +mounting to OS/400 Netserve. Fix oops in cifs_get_tcp_session. +Disable use of server inode numbers when server only +partially supports them (e.g. for one server querying inode numbers on +FindFirst fails but QPathInfo queries works). + Version 1.60 ------------- Fix memory leak in reconnect. Fix oops in DFS mount error path. diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 9a5e4f5f3122..29f1da761bbf 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -1037,7 +1037,7 @@ init_cifs(void) if (rc) goto out_unregister_key_type; #endif - rc = slow_work_register_user(); + rc = slow_work_register_user(THIS_MODULE); if (rc) goto out_unregister_resolver_key; diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 627a60a6c1b1..1f42f772865a 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -214,8 +214,6 @@ int cifs_posix_open(char *full_path, struct inode **pinode, posix_flags |= SMB_O_EXCL; if (oflags & O_TRUNC) posix_flags |= SMB_O_TRUNC; - if (oflags & O_APPEND) - posix_flags |= SMB_O_APPEND; if (oflags & O_SYNC) posix_flags |= SMB_O_SYNC; if (oflags & O_DIRECTORY) @@ -643,9 +641,9 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, * O_EXCL: optimize away the lookup, but don't hash the dentry. Let * the VFS handle the create. */ - if (nd->flags & LOOKUP_EXCL) { + if (nd && (nd->flags & LOOKUP_EXCL)) { d_instantiate(direntry, NULL); - return 0; + return NULL; } /* can not grab the rename sem here since it would @@ -675,7 +673,7 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, * reduction in network traffic in the other paths. */ if (pTcon->unix_ext) { - if (!(nd->flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY)) && + if (nd && !(nd->flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY)) && (nd->flags & LOOKUP_OPEN) && !pTcon->broken_posix_open && (nd->intent.open.flags & O_CREAT)) { rc = cifs_posix_open(full_path, &newInode, nd->path.mnt, diff --git a/fs/coda/sysctl.c b/fs/coda/sysctl.c index 43c96ce29614..c6405ce3c50e 100644 --- a/fs/coda/sysctl.c +++ b/fs/coda/sysctl.c @@ -17,28 +17,25 @@ static struct ctl_table_header *fs_table_header; static ctl_table coda_table[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "timeout", .data = &coda_timeout, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { - .ctl_name = CTL_UNNUMBERED, .procname = "hard", .data = &coda_hard, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { - .ctl_name = CTL_UNNUMBERED, .procname = "fake_statfs", .data = &coda_fake_statfs, .maxlen = sizeof(int), .mode = 0600, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, {} }; @@ -46,7 +43,6 @@ static ctl_table coda_table[] = { #ifdef CONFIG_SYSCTL static ctl_table fs_table[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "coda", .mode = 0555, .child = coda_table diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 085c5c063420..366c503f9657 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -251,10 +251,10 @@ ctl_table epoll_table[] = { .data = &max_user_watches, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero, }, - { .ctl_name = 0 } + { } }; #endif /* CONFIG_SYSCTL */ diff --git a/fs/exec.c b/fs/exec.c index ba112bd4a339..c0c636e34f60 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -46,7 +46,6 @@ #include <linux/proc_fs.h> #include <linux/mount.h> #include <linux/security.h> -#include <linux/ima.h> #include <linux/syscalls.h> #include <linux/tsacct_kern.h> #include <linux/cn_proc.h> @@ -1209,9 +1208,6 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs) retval = security_bprm_check(bprm); if (retval) return retval; - retval = ima_bprm_check(bprm); - if (retval) - return retval; /* kernel module loader fixup */ /* so we don't try to load run modprobe in kernel space. */ diff --git a/fs/file_table.c b/fs/file_table.c index 8eb44042e009..4bef4c01ec6f 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -13,7 +13,6 @@ #include <linux/module.h> #include <linux/fs.h> #include <linux/security.h> -#include <linux/ima.h> #include <linux/eventpoll.h> #include <linux/rcupdate.h> #include <linux/mount.h> @@ -280,7 +279,6 @@ void __fput(struct file *file) if (file->f_op && file->f_op->release) file->f_op->release(inode, file); security_file_free(file); - ima_file_free(file); if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL)) cdev_put(inode->i_cdev); fops_put(file->f_op); diff --git a/fs/fscache/Kconfig b/fs/fscache/Kconfig index 9bbb8ce7bea0..864dac20a242 100644 --- a/fs/fscache/Kconfig +++ b/fs/fscache/Kconfig @@ -54,3 +54,10 @@ config FSCACHE_DEBUG enabled by setting bits in /sys/modules/fscache/parameter/debug. See Documentation/filesystems/caching/fscache.txt for more information. + +config FSCACHE_OBJECT_LIST + bool "Maintain global object list for debugging purposes" + depends on FSCACHE && PROC_FS + help + Maintain a global list of active fscache objects that can be + retrieved through /proc/fs/fscache/objects for debugging purposes diff --git a/fs/fscache/Makefile b/fs/fscache/Makefile index 91571b95aacc..6d561531cb36 100644 --- a/fs/fscache/Makefile +++ b/fs/fscache/Makefile @@ -15,5 +15,6 @@ fscache-y := \ fscache-$(CONFIG_PROC_FS) += proc.o fscache-$(CONFIG_FSCACHE_STATS) += stats.o fscache-$(CONFIG_FSCACHE_HISTOGRAM) += histogram.o +fscache-$(CONFIG_FSCACHE_OBJECT_LIST) += object-list.o obj-$(CONFIG_FSCACHE) := fscache.o diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c index e21985bbb1fb..6a3c48abd677 100644 --- a/fs/fscache/cache.c +++ b/fs/fscache/cache.c @@ -263,6 +263,7 @@ int fscache_add_cache(struct fscache_cache *cache, spin_lock(&cache->object_list_lock); list_add_tail(&ifsdef->cache_link, &cache->object_list); spin_unlock(&cache->object_list_lock); + fscache_objlist_add(ifsdef); /* add the cache's netfs definition index object to the top level index * cookie as a known backing object */ @@ -380,11 +381,15 @@ void fscache_withdraw_cache(struct fscache_cache *cache) /* make sure all pages pinned by operations on behalf of the netfs are * written to disk */ + fscache_stat(&fscache_n_cop_sync_cache); cache->ops->sync_cache(cache); + fscache_stat_d(&fscache_n_cop_sync_cache); /* dissociate all the netfs pages backed by this cache from the block * mappings in the cache */ + fscache_stat(&fscache_n_cop_dissociate_pages); cache->ops->dissociate_pages(cache); + fscache_stat_d(&fscache_n_cop_dissociate_pages); /* we now have to destroy all the active objects pertaining to this * cache - which we do by passing them off to thread pool to be diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 72fd18f6c71f..990535071a8a 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -36,6 +36,7 @@ void fscache_cookie_init_once(void *_cookie) memset(cookie, 0, sizeof(*cookie)); spin_lock_init(&cookie->lock); + spin_lock_init(&cookie->stores_lock); INIT_HLIST_HEAD(&cookie->backing_objects); } @@ -102,7 +103,9 @@ struct fscache_cookie *__fscache_acquire_cookie( cookie->netfs_data = netfs_data; cookie->flags = 0; - INIT_RADIX_TREE(&cookie->stores, GFP_NOFS); + /* radix tree insertion won't use the preallocation pool unless it's + * told it may not wait */ + INIT_RADIX_TREE(&cookie->stores, GFP_NOFS & ~__GFP_WAIT); switch (cookie->def->type) { case FSCACHE_COOKIE_TYPE_INDEX: @@ -249,7 +252,9 @@ static int fscache_alloc_object(struct fscache_cache *cache, /* ask the cache to allocate an object (we may end up with duplicate * objects at this stage, but we sort that out later) */ + fscache_stat(&fscache_n_cop_alloc_object); object = cache->ops->alloc_object(cache, cookie); + fscache_stat_d(&fscache_n_cop_alloc_object); if (IS_ERR(object)) { fscache_stat(&fscache_n_object_no_alloc); ret = PTR_ERR(object); @@ -270,8 +275,11 @@ static int fscache_alloc_object(struct fscache_cache *cache, /* only attach if we managed to allocate all we needed, otherwise * discard the object we just allocated and instead use the one * attached to the cookie */ - if (fscache_attach_object(cookie, object) < 0) + if (fscache_attach_object(cookie, object) < 0) { + fscache_stat(&fscache_n_cop_put_object); cache->ops->put_object(object); + fscache_stat_d(&fscache_n_cop_put_object); + } _leave(" = 0"); return 0; @@ -287,7 +295,9 @@ object_already_extant: return 0; error_put: + fscache_stat(&fscache_n_cop_put_object); cache->ops->put_object(object); + fscache_stat_d(&fscache_n_cop_put_object); error: _leave(" = %d", ret); return ret; @@ -349,6 +359,8 @@ static int fscache_attach_object(struct fscache_cookie *cookie, object->cookie = cookie; atomic_inc(&cookie->usage); hlist_add_head(&object->cookie_link, &cookie->backing_objects); + + fscache_objlist_add(object); ret = 0; cant_attach_object: @@ -403,6 +415,8 @@ void __fscache_relinquish_cookie(struct fscache_cookie *cookie, int retire) unsigned long event; fscache_stat(&fscache_n_relinquishes); + if (retire) + fscache_stat(&fscache_n_relinquishes_retire); if (!cookie) { fscache_stat(&fscache_n_relinquishes_null); @@ -428,12 +442,8 @@ void __fscache_relinquish_cookie(struct fscache_cookie *cookie, int retire) event = retire ? FSCACHE_OBJECT_EV_RETIRE : FSCACHE_OBJECT_EV_RELEASE; - /* detach pointers back to the netfs */ spin_lock(&cookie->lock); - cookie->netfs_data = NULL; - cookie->def = NULL; - /* break links with all the active objects */ while (!hlist_empty(&cookie->backing_objects)) { object = hlist_entry(cookie->backing_objects.first, @@ -456,6 +466,10 @@ void __fscache_relinquish_cookie(struct fscache_cookie *cookie, int retire) BUG(); } + /* detach pointers back to the netfs */ + cookie->netfs_data = NULL; + cookie->def = NULL; + spin_unlock(&cookie->lock); if (cookie->parent) { diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index 1c341304621f..edd7434ab6e5 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -17,6 +17,7 @@ * - cache->object_list_lock * - object->lock * - object->parent->lock + * - cookie->stores_lock * - fscache_thread_lock * */ @@ -88,17 +89,31 @@ extern int fscache_wait_bit_interruptible(void *); /* * object.c */ +extern const char fscache_object_states_short[FSCACHE_OBJECT__NSTATES][5]; + extern void fscache_withdrawing_object(struct fscache_cache *, struct fscache_object *); extern void fscache_enqueue_object(struct fscache_object *); /* + * object-list.c + */ +#ifdef CONFIG_FSCACHE_OBJECT_LIST +extern const struct file_operations fscache_objlist_fops; + +extern void fscache_objlist_add(struct fscache_object *); +#else +#define fscache_objlist_add(object) do {} while(0) +#endif + +/* * operation.c */ extern int fscache_submit_exclusive_op(struct fscache_object *, struct fscache_operation *); extern int fscache_submit_op(struct fscache_object *, struct fscache_operation *); +extern int fscache_cancel_op(struct fscache_operation *); extern void fscache_abort_object(struct fscache_object *); extern void fscache_start_operations(struct fscache_object *); extern void fscache_operation_gc(struct work_struct *); @@ -127,6 +142,8 @@ extern atomic_t fscache_n_op_enqueue; extern atomic_t fscache_n_op_deferred_release; extern atomic_t fscache_n_op_release; extern atomic_t fscache_n_op_gc; +extern atomic_t fscache_n_op_cancelled; +extern atomic_t fscache_n_op_rejected; extern atomic_t fscache_n_attr_changed; extern atomic_t fscache_n_attr_changed_ok; @@ -138,6 +155,8 @@ extern atomic_t fscache_n_allocs; extern atomic_t fscache_n_allocs_ok; extern atomic_t fscache_n_allocs_wait; extern atomic_t fscache_n_allocs_nobufs; +extern atomic_t fscache_n_allocs_intr; +extern atomic_t fscache_n_allocs_object_dead; extern atomic_t fscache_n_alloc_ops; extern atomic_t fscache_n_alloc_op_waits; @@ -148,6 +167,7 @@ extern atomic_t fscache_n_retrievals_nodata; extern atomic_t fscache_n_retrievals_nobufs; extern atomic_t fscache_n_retrievals_intr; extern atomic_t fscache_n_retrievals_nomem; +extern atomic_t fscache_n_retrievals_object_dead; extern atomic_t fscache_n_retrieval_ops; extern atomic_t fscache_n_retrieval_op_waits; @@ -158,6 +178,14 @@ extern atomic_t fscache_n_stores_nobufs; extern atomic_t fscache_n_stores_oom; extern atomic_t fscache_n_store_ops; extern atomic_t fscache_n_store_calls; +extern atomic_t fscache_n_store_pages; +extern atomic_t fscache_n_store_radix_deletes; +extern atomic_t fscache_n_store_pages_over_limit; + +extern atomic_t fscache_n_store_vmscan_not_storing; +extern atomic_t fscache_n_store_vmscan_gone; +extern atomic_t fscache_n_store_vmscan_busy; +extern atomic_t fscache_n_store_vmscan_cancelled; extern atomic_t fscache_n_marks; extern atomic_t fscache_n_uncaches; @@ -176,6 +204,7 @@ extern atomic_t fscache_n_updates_run; extern atomic_t fscache_n_relinquishes; extern atomic_t fscache_n_relinquishes_null; extern atomic_t fscache_n_relinquishes_waitcrt; +extern atomic_t fscache_n_relinquishes_retire; extern atomic_t fscache_n_cookie_index; extern atomic_t fscache_n_cookie_data; @@ -186,6 +215,7 @@ extern atomic_t fscache_n_object_no_alloc; extern atomic_t fscache_n_object_lookups; extern atomic_t fscache_n_object_lookups_negative; extern atomic_t fscache_n_object_lookups_positive; +extern atomic_t fscache_n_object_lookups_timed_out; extern atomic_t fscache_n_object_created; extern atomic_t fscache_n_object_avail; extern atomic_t fscache_n_object_dead; @@ -195,15 +225,41 @@ extern atomic_t fscache_n_checkaux_okay; extern atomic_t fscache_n_checkaux_update; extern atomic_t fscache_n_checkaux_obsolete; +extern atomic_t fscache_n_cop_alloc_object; +extern atomic_t fscache_n_cop_lookup_object; +extern atomic_t fscache_n_cop_lookup_complete; +extern atomic_t fscache_n_cop_grab_object; +extern atomic_t fscache_n_cop_update_object; +extern atomic_t fscache_n_cop_drop_object; +extern atomic_t fscache_n_cop_put_object; +extern atomic_t fscache_n_cop_sync_cache; +extern atomic_t fscache_n_cop_attr_changed; +extern atomic_t fscache_n_cop_read_or_alloc_page; +extern atomic_t fscache_n_cop_read_or_alloc_pages; +extern atomic_t fscache_n_cop_allocate_page; +extern atomic_t fscache_n_cop_allocate_pages; +extern atomic_t fscache_n_cop_write_page; +extern atomic_t fscache_n_cop_uncache_page; +extern atomic_t fscache_n_cop_dissociate_pages; + static inline void fscache_stat(atomic_t *stat) { atomic_inc(stat); } +static inline void fscache_stat_d(atomic_t *stat) +{ + atomic_dec(stat); +} + +#define __fscache_stat(stat) (stat) + extern const struct file_operations fscache_stats_fops; #else +#define __fscache_stat(stat) (NULL) #define fscache_stat(stat) do {} while (0) +#define fscache_stat_d(stat) do {} while (0) #endif /* diff --git a/fs/fscache/main.c b/fs/fscache/main.c index 4de41b597499..add6bdb53f04 100644 --- a/fs/fscache/main.c +++ b/fs/fscache/main.c @@ -48,7 +48,7 @@ static int __init fscache_init(void) { int ret; - ret = slow_work_register_user(); + ret = slow_work_register_user(THIS_MODULE); if (ret < 0) goto error_slow_work; @@ -80,7 +80,7 @@ error_kobj: error_cookie_jar: fscache_proc_cleanup(); error_proc: - slow_work_unregister_user(); + slow_work_unregister_user(THIS_MODULE); error_slow_work: return ret; } @@ -97,7 +97,7 @@ static void __exit fscache_exit(void) kobject_put(fscache_root); kmem_cache_destroy(fscache_cookie_jar); fscache_proc_cleanup(); - slow_work_unregister_user(); + slow_work_unregister_user(THIS_MODULE); printk(KERN_NOTICE "FS-Cache: Unloaded\n"); } diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c new file mode 100644 index 000000000000..e590242fa41a --- /dev/null +++ b/fs/fscache/object-list.c @@ -0,0 +1,432 @@ +/* Global fscache object list maintainer and viewer + * + * Copyright (C) 2009 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#define FSCACHE_DEBUG_LEVEL COOKIE +#include <linux/module.h> +#include <linux/seq_file.h> +#include <linux/key.h> +#include <keys/user-type.h> +#include "internal.h" + +static struct rb_root fscache_object_list; +static DEFINE_RWLOCK(fscache_object_list_lock); + +struct fscache_objlist_data { + unsigned long config; /* display configuration */ +#define FSCACHE_OBJLIST_CONFIG_KEY 0x00000001 /* show object keys */ +#define FSCACHE_OBJLIST_CONFIG_AUX 0x00000002 /* show object auxdata */ +#define FSCACHE_OBJLIST_CONFIG_COOKIE 0x00000004 /* show objects with cookies */ +#define FSCACHE_OBJLIST_CONFIG_NOCOOKIE 0x00000008 /* show objects without cookies */ +#define FSCACHE_OBJLIST_CONFIG_BUSY 0x00000010 /* show busy objects */ +#define FSCACHE_OBJLIST_CONFIG_IDLE 0x00000020 /* show idle objects */ +#define FSCACHE_OBJLIST_CONFIG_PENDWR 0x00000040 /* show objects with pending writes */ +#define FSCACHE_OBJLIST_CONFIG_NOPENDWR 0x00000080 /* show objects without pending writes */ +#define FSCACHE_OBJLIST_CONFIG_READS 0x00000100 /* show objects with active reads */ +#define FSCACHE_OBJLIST_CONFIG_NOREADS 0x00000200 /* show objects without active reads */ +#define FSCACHE_OBJLIST_CONFIG_EVENTS 0x00000400 /* show objects with events */ +#define FSCACHE_OBJLIST_CONFIG_NOEVENTS 0x00000800 /* show objects without no events */ +#define FSCACHE_OBJLIST_CONFIG_WORK 0x00001000 /* show objects with slow work */ +#define FSCACHE_OBJLIST_CONFIG_NOWORK 0x00002000 /* show objects without slow work */ + + u8 buf[512]; /* key and aux data buffer */ +}; + +/* + * Add an object to the object list + * - we use the address of the fscache_object structure as the key into the + * tree + */ +void fscache_objlist_add(struct fscache_object *obj) +{ + struct fscache_object *xobj; + struct rb_node **p = &fscache_object_list.rb_node, *parent = NULL; + + write_lock(&fscache_object_list_lock); + + while (*p) { + parent = *p; + xobj = rb_entry(parent, struct fscache_object, objlist_link); + + if (obj < xobj) + p = &(*p)->rb_left; + else if (obj > xobj) + p = &(*p)->rb_right; + else + BUG(); + } + + rb_link_node(&obj->objlist_link, parent, p); + rb_insert_color(&obj->objlist_link, &fscache_object_list); + + write_unlock(&fscache_object_list_lock); +} + +/** + * fscache_object_destroy - Note that a cache object is about to be destroyed + * @object: The object to be destroyed + * + * Note the imminent destruction and deallocation of a cache object record. + */ +void fscache_object_destroy(struct fscache_object *obj) +{ + write_lock(&fscache_object_list_lock); + + BUG_ON(RB_EMPTY_ROOT(&fscache_object_list)); + rb_erase(&obj->objlist_link, &fscache_object_list); + + write_unlock(&fscache_object_list_lock); +} +EXPORT_SYMBOL(fscache_object_destroy); + +/* + * find the object in the tree on or after the specified index + */ +static struct fscache_object *fscache_objlist_lookup(loff_t *_pos) +{ + struct fscache_object *pobj, *obj, *minobj = NULL; + struct rb_node *p; + unsigned long pos; + + if (*_pos >= (unsigned long) ERR_PTR(-ENOENT)) + return NULL; + pos = *_pos; + + /* banners (can't represent line 0 by pos 0 as that would involve + * returning a NULL pointer) */ + if (pos == 0) + return (struct fscache_object *) ++(*_pos); + if (pos < 3) + return (struct fscache_object *)pos; + + pobj = (struct fscache_object *)pos; + p = fscache_object_list.rb_node; + while (p) { + obj = rb_entry(p, struct fscache_object, objlist_link); + if (pobj < obj) { + if (!minobj || minobj > obj) + minobj = obj; + p = p->rb_left; + } else if (pobj > obj) { + p = p->rb_right; + } else { + minobj = obj; + break; + } + obj = NULL; + } + + if (!minobj) + *_pos = (unsigned long) ERR_PTR(-ENOENT); + else if (minobj != obj) + *_pos = (unsigned long) minobj; + return minobj; +} + +/* + * set up the iterator to start reading from the first line + */ +static void *fscache_objlist_start(struct seq_file *m, loff_t *_pos) + __acquires(&fscache_object_list_lock) +{ + read_lock(&fscache_object_list_lock); + return fscache_objlist_lookup(_pos); +} + +/* + * move to the next line + */ +static void *fscache_objlist_next(struct seq_file *m, void *v, loff_t *_pos) +{ + (*_pos)++; + return fscache_objlist_lookup(_pos); +} + +/* + * clean up after reading + */ +static void fscache_objlist_stop(struct seq_file *m, void *v) + __releases(&fscache_object_list_lock) +{ + read_unlock(&fscache_object_list_lock); +} + +/* + * display an object + */ +static int fscache_objlist_show(struct seq_file *m, void *v) +{ + struct fscache_objlist_data *data = m->private; + struct fscache_object *obj = v; + unsigned long config = data->config; + uint16_t keylen, auxlen; + char _type[3], *type; + bool no_cookie; + u8 *buf = data->buf, *p; + + if ((unsigned long) v == 1) { + seq_puts(m, "OBJECT PARENT STAT CHLDN OPS OOP IPR EX READS" + " EM EV F S" + " | NETFS_COOKIE_DEF TY FL NETFS_DATA"); + if (config & (FSCACHE_OBJLIST_CONFIG_KEY | + FSCACHE_OBJLIST_CONFIG_AUX)) + seq_puts(m, " "); + if (config & FSCACHE_OBJLIST_CONFIG_KEY) + seq_puts(m, "OBJECT_KEY"); + if ((config & (FSCACHE_OBJLIST_CONFIG_KEY | + FSCACHE_OBJLIST_CONFIG_AUX)) == + (FSCACHE_OBJLIST_CONFIG_KEY | FSCACHE_OBJLIST_CONFIG_AUX)) + seq_puts(m, ", "); + if (config & FSCACHE_OBJLIST_CONFIG_AUX) + seq_puts(m, "AUX_DATA"); + seq_puts(m, "\n"); + return 0; + } + + if ((unsigned long) v == 2) { + seq_puts(m, "======== ======== ==== ===== === === === == =====" + " == == = =" + " | ================ == == ================"); + if (config & (FSCACHE_OBJLIST_CONFIG_KEY | + FSCACHE_OBJLIST_CONFIG_AUX)) + seq_puts(m, " ================"); + seq_puts(m, "\n"); + return 0; + } + + /* filter out any unwanted objects */ +#define FILTER(criterion, _yes, _no) \ + do { \ + unsigned long yes = FSCACHE_OBJLIST_CONFIG_##_yes; \ + unsigned long no = FSCACHE_OBJLIST_CONFIG_##_no; \ + if (criterion) { \ + if (!(config & yes)) \ + return 0; \ + } else { \ + if (!(config & no)) \ + return 0; \ + } \ + } while(0) + + if (~config) { + FILTER(obj->cookie, + COOKIE, NOCOOKIE); + FILTER(obj->state != FSCACHE_OBJECT_ACTIVE || + obj->n_ops != 0 || + obj->n_obj_ops != 0 || + obj->flags || + !list_empty(&obj->dependents), + BUSY, IDLE); + FILTER(test_bit(FSCACHE_OBJECT_PENDING_WRITE, &obj->flags), + PENDWR, NOPENDWR); + FILTER(atomic_read(&obj->n_reads), + READS, NOREADS); + FILTER(obj->events & obj->event_mask, + EVENTS, NOEVENTS); + FILTER(obj->work.flags & ~(1UL << SLOW_WORK_VERY_SLOW), + WORK, NOWORK); + } + + seq_printf(m, + "%8x %8x %s %5u %3u %3u %3u %2u %5u %2lx %2lx %1lx %1lx | ", + obj->debug_id, + obj->parent ? obj->parent->debug_id : -1, + fscache_object_states_short[obj->state], + obj->n_children, + obj->n_ops, + obj->n_obj_ops, + obj->n_in_progress, + obj->n_exclusive, + atomic_read(&obj->n_reads), + obj->event_mask & FSCACHE_OBJECT_EVENTS_MASK, + obj->events, + obj->flags, + obj->work.flags); + + no_cookie = true; + keylen = auxlen = 0; + if (obj->cookie) { + spin_lock(&obj->lock); + if (obj->cookie) { + switch (obj->cookie->def->type) { + case 0: + type = "IX"; + break; + case 1: + type = "DT"; + break; + default: + sprintf(_type, "%02u", + obj->cookie->def->type); + type = _type; + break; + } + + seq_printf(m, "%-16s %s %2lx %16p", + obj->cookie->def->name, + type, + obj->cookie->flags, + obj->cookie->netfs_data); + + if (obj->cookie->def->get_key && + config & FSCACHE_OBJLIST_CONFIG_KEY) + keylen = obj->cookie->def->get_key( + obj->cookie->netfs_data, + buf, 400); + + if (obj->cookie->def->get_aux && + config & FSCACHE_OBJLIST_CONFIG_AUX) + auxlen = obj->cookie->def->get_aux( + obj->cookie->netfs_data, + buf + keylen, 512 - keylen); + + no_cookie = false; + } + spin_unlock(&obj->lock); + + if (!no_cookie && (keylen > 0 || auxlen > 0)) { + seq_printf(m, " "); + for (p = buf; keylen > 0; keylen--) + seq_printf(m, "%02x", *p++); + if (auxlen > 0) { + if (config & FSCACHE_OBJLIST_CONFIG_KEY) + seq_printf(m, ", "); + for (; auxlen > 0; auxlen--) + seq_printf(m, "%02x", *p++); + } + } + } + + if (no_cookie) + seq_printf(m, "<no_cookie>\n"); + else + seq_printf(m, "\n"); + return 0; +} + +static const struct seq_operations fscache_objlist_ops = { + .start = fscache_objlist_start, + .stop = fscache_objlist_stop, + .next = fscache_objlist_next, + .show = fscache_objlist_show, +}; + +/* + * get the configuration for filtering the list + */ +static void fscache_objlist_config(struct fscache_objlist_data *data) +{ +#ifdef CONFIG_KEYS + struct user_key_payload *confkey; + unsigned long config; + struct key *key; + const char *buf; + int len; + + key = request_key(&key_type_user, "fscache:objlist", NULL); + if (IS_ERR(key)) + goto no_config; + + config = 0; + rcu_read_lock(); + + confkey = key->payload.data; + buf = confkey->data; + + for (len = confkey->datalen - 1; len >= 0; len--) { + switch (buf[len]) { + case 'K': config |= FSCACHE_OBJLIST_CONFIG_KEY; break; + case 'A': config |= FSCACHE_OBJLIST_CONFIG_AUX; break; + case 'C': config |= FSCACHE_OBJLIST_CONFIG_COOKIE; break; + case 'c': config |= FSCACHE_OBJLIST_CONFIG_NOCOOKIE; break; + case 'B': config |= FSCACHE_OBJLIST_CONFIG_BUSY; break; + case 'b': config |= FSCACHE_OBJLIST_CONFIG_IDLE; break; + case 'W': config |= FSCACHE_OBJLIST_CONFIG_PENDWR; break; + case 'w': config |= FSCACHE_OBJLIST_CONFIG_NOPENDWR; break; + case 'R': config |= FSCACHE_OBJLIST_CONFIG_READS; break; + case 'r': config |= FSCACHE_OBJLIST_CONFIG_NOREADS; break; + case 'S': config |= FSCACHE_OBJLIST_CONFIG_WORK; break; + case 's': config |= FSCACHE_OBJLIST_CONFIG_NOWORK; break; + } + } + + rcu_read_unlock(); + key_put(key); + + if (!(config & (FSCACHE_OBJLIST_CONFIG_COOKIE | FSCACHE_OBJLIST_CONFIG_NOCOOKIE))) + config |= FSCACHE_OBJLIST_CONFIG_COOKIE | FSCACHE_OBJLIST_CONFIG_NOCOOKIE; + if (!(config & (FSCACHE_OBJLIST_CONFIG_BUSY | FSCACHE_OBJLIST_CONFIG_IDLE))) + config |= FSCACHE_OBJLIST_CONFIG_BUSY | FSCACHE_OBJLIST_CONFIG_IDLE; + if (!(config & (FSCACHE_OBJLIST_CONFIG_PENDWR | FSCACHE_OBJLIST_CONFIG_NOPENDWR))) + config |= FSCACHE_OBJLIST_CONFIG_PENDWR | FSCACHE_OBJLIST_CONFIG_NOPENDWR; + if (!(config & (FSCACHE_OBJLIST_CONFIG_READS | FSCACHE_OBJLIST_CONFIG_NOREADS))) + config |= FSCACHE_OBJLIST_CONFIG_READS | FSCACHE_OBJLIST_CONFIG_NOREADS; + if (!(config & (FSCACHE_OBJLIST_CONFIG_EVENTS | FSCACHE_OBJLIST_CONFIG_NOEVENTS))) + config |= FSCACHE_OBJLIST_CONFIG_EVENTS | FSCACHE_OBJLIST_CONFIG_NOEVENTS; + if (!(config & (FSCACHE_OBJLIST_CONFIG_WORK | FSCACHE_OBJLIST_CONFIG_NOWORK))) + config |= FSCACHE_OBJLIST_CONFIG_WORK | FSCACHE_OBJLIST_CONFIG_NOWORK; + + data->config = config; + return; + +no_config: +#endif + data->config = ULONG_MAX; +} + +/* + * open "/proc/fs/fscache/objects" to provide a list of active objects + * - can be configured by a user-defined key added to the caller's keyrings + */ +static int fscache_objlist_open(struct inode *inode, struct file *file) +{ + struct fscache_objlist_data *data; + struct seq_file *m; + int ret; + + ret = seq_open(file, &fscache_objlist_ops); + if (ret < 0) + return ret; + + m = file->private_data; + + /* buffer for key extraction */ + data = kmalloc(sizeof(struct fscache_objlist_data), GFP_KERNEL); + if (!data) { + seq_release(inode, file); + return -ENOMEM; + } + + /* get the configuration key */ + fscache_objlist_config(data); + + m->private = data; + return 0; +} + +/* + * clean up on close + */ +static int fscache_objlist_release(struct inode *inode, struct file *file) +{ + struct seq_file *m = file->private_data; + + kfree(m->private); + m->private = NULL; + return seq_release(inode, file); +} + +const struct file_operations fscache_objlist_fops = { + .owner = THIS_MODULE, + .open = fscache_objlist_open, + .read = seq_read, + .llseek = seq_lseek, + .release = fscache_objlist_release, +}; diff --git a/fs/fscache/object.c b/fs/fscache/object.c index 392a41b1b79d..e513ac599c8e 100644 --- a/fs/fscache/object.c +++ b/fs/fscache/object.c @@ -14,9 +14,10 @@ #define FSCACHE_DEBUG_LEVEL COOKIE #include <linux/module.h> +#include <linux/seq_file.h> #include "internal.h" -const char *fscache_object_states[] = { +const char *fscache_object_states[FSCACHE_OBJECT__NSTATES] = { [FSCACHE_OBJECT_INIT] = "OBJECT_INIT", [FSCACHE_OBJECT_LOOKING_UP] = "OBJECT_LOOKING_UP", [FSCACHE_OBJECT_CREATING] = "OBJECT_CREATING", @@ -33,9 +34,28 @@ const char *fscache_object_states[] = { }; EXPORT_SYMBOL(fscache_object_states); +const char fscache_object_states_short[FSCACHE_OBJECT__NSTATES][5] = { + [FSCACHE_OBJECT_INIT] = "INIT", + [FSCACHE_OBJECT_LOOKING_UP] = "LOOK", + [FSCACHE_OBJECT_CREATING] = "CRTN", + [FSCACHE_OBJECT_AVAILABLE] = "AVBL", + [FSCACHE_OBJECT_ACTIVE] = "ACTV", + [FSCACHE_OBJECT_UPDATING] = "UPDT", + [FSCACHE_OBJECT_DYING] = "DYNG", + [FSCACHE_OBJECT_LC_DYING] = "LCDY", + [FSCACHE_OBJECT_ABORT_INIT] = "ABTI", + [FSCACHE_OBJECT_RELEASING] = "RELS", + [FSCACHE_OBJECT_RECYCLING] = "RCYC", + [FSCACHE_OBJECT_WITHDRAWING] = "WTHD", + [FSCACHE_OBJECT_DEAD] = "DEAD", +}; + static void fscache_object_slow_work_put_ref(struct slow_work *); static int fscache_object_slow_work_get_ref(struct slow_work *); static void fscache_object_slow_work_execute(struct slow_work *); +#ifdef CONFIG_SLOW_WORK_PROC +static void fscache_object_slow_work_desc(struct slow_work *, struct seq_file *); +#endif static void fscache_initialise_object(struct fscache_object *); static void fscache_lookup_object(struct fscache_object *); static void fscache_object_available(struct fscache_object *); @@ -45,9 +65,13 @@ static void fscache_enqueue_dependents(struct fscache_object *); static void fscache_dequeue_object(struct fscache_object *); const struct slow_work_ops fscache_object_slow_work_ops = { + .owner = THIS_MODULE, .get_ref = fscache_object_slow_work_get_ref, .put_ref = fscache_object_slow_work_put_ref, .execute = fscache_object_slow_work_execute, +#ifdef CONFIG_SLOW_WORK_PROC + .desc = fscache_object_slow_work_desc, +#endif }; EXPORT_SYMBOL(fscache_object_slow_work_ops); @@ -81,6 +105,7 @@ static inline void fscache_done_parent_op(struct fscache_object *object) static void fscache_object_state_machine(struct fscache_object *object) { enum fscache_object_state new_state; + struct fscache_cookie *cookie; ASSERT(object != NULL); @@ -120,20 +145,31 @@ static void fscache_object_state_machine(struct fscache_object *object) case FSCACHE_OBJECT_UPDATING: clear_bit(FSCACHE_OBJECT_EV_UPDATE, &object->events); fscache_stat(&fscache_n_updates_run); + fscache_stat(&fscache_n_cop_update_object); object->cache->ops->update_object(object); + fscache_stat_d(&fscache_n_cop_update_object); goto active_transit; /* handle an object dying during lookup or creation */ case FSCACHE_OBJECT_LC_DYING: object->event_mask &= ~(1 << FSCACHE_OBJECT_EV_UPDATE); + fscache_stat(&fscache_n_cop_lookup_complete); object->cache->ops->lookup_complete(object); + fscache_stat_d(&fscache_n_cop_lookup_complete); spin_lock(&object->lock); object->state = FSCACHE_OBJECT_DYING; - if (test_and_clear_bit(FSCACHE_COOKIE_CREATING, - &object->cookie->flags)) - wake_up_bit(&object->cookie->flags, - FSCACHE_COOKIE_CREATING); + cookie = object->cookie; + if (cookie) { + if (test_and_clear_bit(FSCACHE_COOKIE_LOOKING_UP, + &cookie->flags)) + wake_up_bit(&cookie->flags, + FSCACHE_COOKIE_LOOKING_UP); + if (test_and_clear_bit(FSCACHE_COOKIE_CREATING, + &cookie->flags)) + wake_up_bit(&cookie->flags, + FSCACHE_COOKIE_CREATING); + } spin_unlock(&object->lock); fscache_done_parent_op(object); @@ -165,6 +201,7 @@ static void fscache_object_state_machine(struct fscache_object *object) } spin_unlock(&object->lock); fscache_enqueue_dependents(object); + fscache_start_operations(object); goto terminal_transit; /* handle an abort during initialisation */ @@ -316,14 +353,29 @@ static void fscache_object_slow_work_execute(struct slow_work *work) _enter("{OBJ%x}", object->debug_id); - clear_bit(FSCACHE_OBJECT_EV_REQUEUE, &object->events); - start = jiffies; fscache_object_state_machine(object); fscache_hist(fscache_objs_histogram, start); if (object->events & object->event_mask) fscache_enqueue_object(object); + clear_bit(FSCACHE_OBJECT_EV_REQUEUE, &object->events); +} + +/* + * describe an object for slow-work debugging + */ +#ifdef CONFIG_SLOW_WORK_PROC +static void fscache_object_slow_work_desc(struct slow_work *work, + struct seq_file *m) +{ + struct fscache_object *object = + container_of(work, struct fscache_object, work); + + seq_printf(m, "FSC: OBJ%x: %s", + object->debug_id, + fscache_object_states_short[object->state]); } +#endif /* * initialise an object @@ -376,7 +428,9 @@ static void fscache_initialise_object(struct fscache_object *object) * binding on to us, so we need to make sure we don't * add ourself to the list multiple times */ if (list_empty(&object->dep_link)) { + fscache_stat(&fscache_n_cop_grab_object); object->cache->ops->grab_object(object); + fscache_stat_d(&fscache_n_cop_grab_object); list_add(&object->dep_link, &parent->dependents); @@ -414,6 +468,7 @@ static void fscache_lookup_object(struct fscache_object *object) { struct fscache_cookie *cookie = object->cookie; struct fscache_object *parent; + int ret; _enter(""); @@ -438,11 +493,20 @@ static void fscache_lookup_object(struct fscache_object *object) object->cache->tag->name); fscache_stat(&fscache_n_object_lookups); - object->cache->ops->lookup_object(object); + fscache_stat(&fscache_n_cop_lookup_object); + ret = object->cache->ops->lookup_object(object); + fscache_stat_d(&fscache_n_cop_lookup_object); if (test_bit(FSCACHE_OBJECT_EV_ERROR, &object->events)) set_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags); + if (ret == -ETIMEDOUT) { + /* probably stuck behind another object, so move this one to + * the back of the queue */ + fscache_stat(&fscache_n_object_lookups_timed_out); + set_bit(FSCACHE_OBJECT_EV_REQUEUE, &object->events); + } + _leave(""); } @@ -546,7 +610,8 @@ static void fscache_object_available(struct fscache_object *object) spin_lock(&object->lock); - if (test_and_clear_bit(FSCACHE_COOKIE_CREATING, &object->cookie->flags)) + if (object->cookie && + test_and_clear_bit(FSCACHE_COOKIE_CREATING, &object->cookie->flags)) wake_up_bit(&object->cookie->flags, FSCACHE_COOKIE_CREATING); fscache_done_parent_op(object); @@ -562,7 +627,9 @@ static void fscache_object_available(struct fscache_object *object) } spin_unlock(&object->lock); + fscache_stat(&fscache_n_cop_lookup_complete); object->cache->ops->lookup_complete(object); + fscache_stat_d(&fscache_n_cop_lookup_complete); fscache_enqueue_dependents(object); fscache_hist(fscache_obj_instantiate_histogram, object->lookup_jif); @@ -581,11 +648,16 @@ static void fscache_drop_object(struct fscache_object *object) _enter("{OBJ%x,%d}", object->debug_id, object->n_children); + ASSERTCMP(object->cookie, ==, NULL); + ASSERT(hlist_unhashed(&object->cookie_link)); + spin_lock(&cache->object_list_lock); list_del_init(&object->cache_link); spin_unlock(&cache->object_list_lock); + fscache_stat(&fscache_n_cop_drop_object); cache->ops->drop_object(object); + fscache_stat_d(&fscache_n_cop_drop_object); if (parent) { _debug("release parent OBJ%x {%d}", @@ -600,7 +672,9 @@ static void fscache_drop_object(struct fscache_object *object) } /* this just shifts the object release to the slow work processor */ + fscache_stat(&fscache_n_cop_put_object); object->cache->ops->put_object(object); + fscache_stat_d(&fscache_n_cop_put_object); _leave(""); } @@ -690,8 +764,12 @@ static int fscache_object_slow_work_get_ref(struct slow_work *work) { struct fscache_object *object = container_of(work, struct fscache_object, work); + int ret; - return object->cache->ops->grab_object(object) ? 0 : -EAGAIN; + fscache_stat(&fscache_n_cop_grab_object); + ret = object->cache->ops->grab_object(object) ? 0 : -EAGAIN; + fscache_stat_d(&fscache_n_cop_grab_object); + return ret; } /* @@ -702,7 +780,9 @@ static void fscache_object_slow_work_put_ref(struct slow_work *work) struct fscache_object *object = container_of(work, struct fscache_object, work); - return object->cache->ops->put_object(object); + fscache_stat(&fscache_n_cop_put_object); + object->cache->ops->put_object(object); + fscache_stat_d(&fscache_n_cop_put_object); } /* @@ -739,7 +819,9 @@ static void fscache_enqueue_dependents(struct fscache_object *object) /* sort onto appropriate lists */ fscache_enqueue_object(dep); + fscache_stat(&fscache_n_cop_put_object); dep->cache->ops->put_object(dep); + fscache_stat_d(&fscache_n_cop_put_object); if (!list_empty(&object->dependents)) cond_resched_lock(&object->lock); diff --git a/fs/fscache/operation.c b/fs/fscache/operation.c index e7f8d53b8b6b..313e79a14266 100644 --- a/fs/fscache/operation.c +++ b/fs/fscache/operation.c @@ -13,6 +13,7 @@ #define FSCACHE_DEBUG_LEVEL OPERATION #include <linux/module.h> +#include <linux/seq_file.h> #include "internal.h" atomic_t fscache_op_debug_id; @@ -31,32 +32,33 @@ void fscache_enqueue_operation(struct fscache_operation *op) _enter("{OBJ%x OP%x,%u}", op->object->debug_id, op->debug_id, atomic_read(&op->usage)); + fscache_set_op_state(op, "EnQ"); + + ASSERT(list_empty(&op->pend_link)); ASSERT(op->processor != NULL); ASSERTCMP(op->object->state, >=, FSCACHE_OBJECT_AVAILABLE); ASSERTCMP(atomic_read(&op->usage), >, 0); - if (list_empty(&op->pend_link)) { - switch (op->flags & FSCACHE_OP_TYPE) { - case FSCACHE_OP_FAST: - _debug("queue fast"); - atomic_inc(&op->usage); - if (!schedule_work(&op->fast_work)) - fscache_put_operation(op); - break; - case FSCACHE_OP_SLOW: - _debug("queue slow"); - slow_work_enqueue(&op->slow_work); - break; - case FSCACHE_OP_MYTHREAD: - _debug("queue for caller's attention"); - break; - default: - printk(KERN_ERR "FS-Cache: Unexpected op type %lx", - op->flags); - BUG(); - break; - } - fscache_stat(&fscache_n_op_enqueue); + fscache_stat(&fscache_n_op_enqueue); + switch (op->flags & FSCACHE_OP_TYPE) { + case FSCACHE_OP_FAST: + _debug("queue fast"); + atomic_inc(&op->usage); + if (!schedule_work(&op->fast_work)) + fscache_put_operation(op); + break; + case FSCACHE_OP_SLOW: + _debug("queue slow"); + slow_work_enqueue(&op->slow_work); + break; + case FSCACHE_OP_MYTHREAD: + _debug("queue for caller's attention"); + break; + default: + printk(KERN_ERR "FS-Cache: Unexpected op type %lx", + op->flags); + BUG(); + break; } } EXPORT_SYMBOL(fscache_enqueue_operation); @@ -67,6 +69,8 @@ EXPORT_SYMBOL(fscache_enqueue_operation); static void fscache_run_op(struct fscache_object *object, struct fscache_operation *op) { + fscache_set_op_state(op, "Run"); + object->n_in_progress++; if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags)) wake_up_bit(&op->flags, FSCACHE_OP_WAITING); @@ -87,9 +91,12 @@ int fscache_submit_exclusive_op(struct fscache_object *object, _enter("{OBJ%x OP%x},", object->debug_id, op->debug_id); + fscache_set_op_state(op, "SubmitX"); + spin_lock(&object->lock); ASSERTCMP(object->n_ops, >=, object->n_in_progress); ASSERTCMP(object->n_ops, >=, object->n_exclusive); + ASSERT(list_empty(&op->pend_link)); ret = -ENOBUFS; if (fscache_object_is_active(object)) { @@ -190,9 +197,12 @@ int fscache_submit_op(struct fscache_object *object, ASSERTCMP(atomic_read(&op->usage), >, 0); + fscache_set_op_state(op, "Submit"); + spin_lock(&object->lock); ASSERTCMP(object->n_ops, >=, object->n_in_progress); ASSERTCMP(object->n_ops, >=, object->n_exclusive); + ASSERT(list_empty(&op->pend_link)); ostate = object->state; smp_rmb(); @@ -222,6 +232,11 @@ int fscache_submit_op(struct fscache_object *object, list_add_tail(&op->pend_link, &object->pending_ops); fscache_stat(&fscache_n_op_pend); ret = 0; + } else if (object->state == FSCACHE_OBJECT_DYING || + object->state == FSCACHE_OBJECT_LC_DYING || + object->state == FSCACHE_OBJECT_WITHDRAWING) { + fscache_stat(&fscache_n_op_rejected); + ret = -ENOBUFS; } else if (!test_bit(FSCACHE_IOERROR, &object->cache->flags)) { fscache_report_unexpected_submission(object, op, ostate); ASSERT(!fscache_object_is_active(object)); @@ -264,12 +279,7 @@ void fscache_start_operations(struct fscache_object *object) stop = true; } list_del_init(&op->pend_link); - object->n_in_progress++; - - if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags)) - wake_up_bit(&op->flags, FSCACHE_OP_WAITING); - if (op->processor) - fscache_enqueue_operation(op); + fscache_run_op(object, op); /* the pending queue was holding a ref on the object */ fscache_put_operation(op); @@ -282,6 +292,36 @@ void fscache_start_operations(struct fscache_object *object) } /* + * cancel an operation that's pending on an object + */ +int fscache_cancel_op(struct fscache_operation *op) +{ + struct fscache_object *object = op->object; + int ret; + + _enter("OBJ%x OP%x}", op->object->debug_id, op->debug_id); + + spin_lock(&object->lock); + + ret = -EBUSY; + if (!list_empty(&op->pend_link)) { + fscache_stat(&fscache_n_op_cancelled); + list_del_init(&op->pend_link); + object->n_ops--; + if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags)) + object->n_exclusive--; + if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags)) + wake_up_bit(&op->flags, FSCACHE_OP_WAITING); + fscache_put_operation(op); + ret = 0; + } + + spin_unlock(&object->lock); + _leave(" = %d", ret); + return ret; +} + +/* * release an operation * - queues pending ops if this is the last in-progress op */ @@ -298,6 +338,8 @@ void fscache_put_operation(struct fscache_operation *op) if (!atomic_dec_and_test(&op->usage)) return; + fscache_set_op_state(op, "Put"); + _debug("PUT OP"); if (test_and_set_bit(FSCACHE_OP_DEAD, &op->flags)) BUG(); @@ -311,6 +353,9 @@ void fscache_put_operation(struct fscache_operation *op) object = op->object; + if (test_bit(FSCACHE_OP_DEC_READ_CNT, &op->flags)) + atomic_dec(&object->n_reads); + /* now... we may get called with the object spinlock held, so we * complete the cleanup here only if we can immediately acquire the * lock, and defer it otherwise */ @@ -452,8 +497,27 @@ static void fscache_op_execute(struct slow_work *work) _leave(""); } +/* + * describe an operation for slow-work debugging + */ +#ifdef CONFIG_SLOW_WORK_PROC +static void fscache_op_desc(struct slow_work *work, struct seq_file *m) +{ + struct fscache_operation *op = + container_of(work, struct fscache_operation, slow_work); + + seq_printf(m, "FSC: OBJ%x OP%x: %s/%s fl=%lx", + op->object->debug_id, op->debug_id, + op->name, op->state, op->flags); +} +#endif + const struct slow_work_ops fscache_op_slow_work_ops = { + .owner = THIS_MODULE, .get_ref = fscache_op_get_ref, .put_ref = fscache_op_put_ref, .execute = fscache_op_execute, +#ifdef CONFIG_SLOW_WORK_PROC + .desc = fscache_op_desc, +#endif }; diff --git a/fs/fscache/page.c b/fs/fscache/page.c index 2568e0eb644f..c598ea4c4e7d 100644 --- a/fs/fscache/page.c +++ b/fs/fscache/page.c @@ -43,18 +43,102 @@ void __fscache_wait_on_page_write(struct fscache_cookie *cookie, struct page *pa EXPORT_SYMBOL(__fscache_wait_on_page_write); /* - * note that a page has finished being written to the cache + * decide whether a page can be released, possibly by cancelling a store to it + * - we're allowed to sleep if __GFP_WAIT is flagged */ -static void fscache_end_page_write(struct fscache_cookie *cookie, struct page *page) +bool __fscache_maybe_release_page(struct fscache_cookie *cookie, + struct page *page, + gfp_t gfp) { struct page *xpage; + void *val; + + _enter("%p,%p,%x", cookie, page, gfp); + + rcu_read_lock(); + val = radix_tree_lookup(&cookie->stores, page->index); + if (!val) { + rcu_read_unlock(); + fscache_stat(&fscache_n_store_vmscan_not_storing); + __fscache_uncache_page(cookie, page); + return true; + } + + /* see if the page is actually undergoing storage - if so we can't get + * rid of it till the cache has finished with it */ + if (radix_tree_tag_get(&cookie->stores, page->index, + FSCACHE_COOKIE_STORING_TAG)) { + rcu_read_unlock(); + goto page_busy; + } + + /* the page is pending storage, so we attempt to cancel the store and + * discard the store request so that the page can be reclaimed */ + spin_lock(&cookie->stores_lock); + rcu_read_unlock(); + + if (radix_tree_tag_get(&cookie->stores, page->index, + FSCACHE_COOKIE_STORING_TAG)) { + /* the page started to undergo storage whilst we were looking, + * so now we can only wait or return */ + spin_unlock(&cookie->stores_lock); + goto page_busy; + } - spin_lock(&cookie->lock); xpage = radix_tree_delete(&cookie->stores, page->index); - spin_unlock(&cookie->lock); - ASSERT(xpage != NULL); + spin_unlock(&cookie->stores_lock); + + if (xpage) { + fscache_stat(&fscache_n_store_vmscan_cancelled); + fscache_stat(&fscache_n_store_radix_deletes); + ASSERTCMP(xpage, ==, page); + } else { + fscache_stat(&fscache_n_store_vmscan_gone); + } wake_up_bit(&cookie->flags, 0); + if (xpage) + page_cache_release(xpage); + __fscache_uncache_page(cookie, page); + return true; + +page_busy: + /* we might want to wait here, but that could deadlock the allocator as + * the slow-work threads writing to the cache may all end up sleeping + * on memory allocation */ + fscache_stat(&fscache_n_store_vmscan_busy); + return false; +} +EXPORT_SYMBOL(__fscache_maybe_release_page); + +/* + * note that a page has finished being written to the cache + */ +static void fscache_end_page_write(struct fscache_object *object, + struct page *page) +{ + struct fscache_cookie *cookie; + struct page *xpage = NULL; + + spin_lock(&object->lock); + cookie = object->cookie; + if (cookie) { + /* delete the page from the tree if it is now no longer + * pending */ + spin_lock(&cookie->stores_lock); + radix_tree_tag_clear(&cookie->stores, page->index, + FSCACHE_COOKIE_STORING_TAG); + if (!radix_tree_tag_get(&cookie->stores, page->index, + FSCACHE_COOKIE_PENDING_TAG)) { + fscache_stat(&fscache_n_store_radix_deletes); + xpage = radix_tree_delete(&cookie->stores, page->index); + } + spin_unlock(&cookie->stores_lock); + wake_up_bit(&cookie->flags, 0); + } + spin_unlock(&object->lock); + if (xpage) + page_cache_release(xpage); } /* @@ -63,14 +147,21 @@ static void fscache_end_page_write(struct fscache_cookie *cookie, struct page *p static void fscache_attr_changed_op(struct fscache_operation *op) { struct fscache_object *object = op->object; + int ret; _enter("{OBJ%x OP%x}", object->debug_id, op->debug_id); fscache_stat(&fscache_n_attr_changed_calls); - if (fscache_object_is_active(object) && - object->cache->ops->attr_changed(object) < 0) - fscache_abort_object(object); + if (fscache_object_is_active(object)) { + fscache_set_op_state(op, "CallFS"); + fscache_stat(&fscache_n_cop_attr_changed); + ret = object->cache->ops->attr_changed(object); + fscache_stat_d(&fscache_n_cop_attr_changed); + fscache_set_op_state(op, "Done"); + if (ret < 0) + fscache_abort_object(object); + } _leave(""); } @@ -99,6 +190,7 @@ int __fscache_attr_changed(struct fscache_cookie *cookie) fscache_operation_init(op, NULL); fscache_operation_init_slow(op, fscache_attr_changed_op); op->flags = FSCACHE_OP_SLOW | (1 << FSCACHE_OP_EXCLUSIVE); + fscache_set_op_name(op, "Attr"); spin_lock(&cookie->lock); @@ -184,6 +276,7 @@ static struct fscache_retrieval *fscache_alloc_retrieval( op->start_time = jiffies; INIT_WORK(&op->op.fast_work, fscache_retrieval_work); INIT_LIST_HEAD(&op->to_do); + fscache_set_op_name(&op->op, "Retr"); return op; } @@ -221,6 +314,43 @@ static int fscache_wait_for_deferred_lookup(struct fscache_cookie *cookie) } /* + * wait for an object to become active (or dead) + */ +static int fscache_wait_for_retrieval_activation(struct fscache_object *object, + struct fscache_retrieval *op, + atomic_t *stat_op_waits, + atomic_t *stat_object_dead) +{ + int ret; + + if (!test_bit(FSCACHE_OP_WAITING, &op->op.flags)) + goto check_if_dead; + + _debug(">>> WT"); + fscache_stat(stat_op_waits); + if (wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING, + fscache_wait_bit_interruptible, + TASK_INTERRUPTIBLE) < 0) { + ret = fscache_cancel_op(&op->op); + if (ret == 0) + return -ERESTARTSYS; + + /* it's been removed from the pending queue by another party, + * so we should get to run shortly */ + wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING, + fscache_wait_bit, TASK_UNINTERRUPTIBLE); + } + _debug("<<< GO"); + +check_if_dead: + if (unlikely(fscache_object_is_dead(object))) { + fscache_stat(stat_object_dead); + return -ENOBUFS; + } + return 0; +} + +/* * read a page from the cache or allocate a block in which to store it * - we return: * -ENOMEM - out of memory, nothing done @@ -257,6 +387,7 @@ int __fscache_read_or_alloc_page(struct fscache_cookie *cookie, _leave(" = -ENOMEM"); return -ENOMEM; } + fscache_set_op_name(&op->op, "RetrRA1"); spin_lock(&cookie->lock); @@ -267,6 +398,9 @@ int __fscache_read_or_alloc_page(struct fscache_cookie *cookie, ASSERTCMP(object->state, >, FSCACHE_OBJECT_LOOKING_UP); + atomic_inc(&object->n_reads); + set_bit(FSCACHE_OP_DEC_READ_CNT, &op->op.flags); + if (fscache_submit_op(object, &op->op) < 0) goto nobufs_unlock; spin_unlock(&cookie->lock); @@ -279,23 +413,27 @@ int __fscache_read_or_alloc_page(struct fscache_cookie *cookie, /* we wait for the operation to become active, and then process it * *here*, in this thread, and not in the thread pool */ - if (test_bit(FSCACHE_OP_WAITING, &op->op.flags)) { - _debug(">>> WT"); - fscache_stat(&fscache_n_retrieval_op_waits); - wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING, - fscache_wait_bit, TASK_UNINTERRUPTIBLE); - _debug("<<< GO"); - } + ret = fscache_wait_for_retrieval_activation( + object, op, + __fscache_stat(&fscache_n_retrieval_op_waits), + __fscache_stat(&fscache_n_retrievals_object_dead)); + if (ret < 0) + goto error; /* ask the cache to honour the operation */ if (test_bit(FSCACHE_COOKIE_NO_DATA_YET, &object->cookie->flags)) { + fscache_stat(&fscache_n_cop_allocate_page); ret = object->cache->ops->allocate_page(op, page, gfp); + fscache_stat_d(&fscache_n_cop_allocate_page); if (ret == 0) ret = -ENODATA; } else { + fscache_stat(&fscache_n_cop_read_or_alloc_page); ret = object->cache->ops->read_or_alloc_page(op, page, gfp); + fscache_stat_d(&fscache_n_cop_read_or_alloc_page); } +error: if (ret == -ENOMEM) fscache_stat(&fscache_n_retrievals_nomem); else if (ret == -ERESTARTSYS) @@ -347,7 +485,6 @@ int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie, void *context, gfp_t gfp) { - fscache_pages_retrieval_func_t func; struct fscache_retrieval *op; struct fscache_object *object; int ret; @@ -369,6 +506,7 @@ int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie, op = fscache_alloc_retrieval(mapping, end_io_func, context); if (!op) return -ENOMEM; + fscache_set_op_name(&op->op, "RetrRAN"); spin_lock(&cookie->lock); @@ -377,6 +515,9 @@ int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie, object = hlist_entry(cookie->backing_objects.first, struct fscache_object, cookie_link); + atomic_inc(&object->n_reads); + set_bit(FSCACHE_OP_DEC_READ_CNT, &op->op.flags); + if (fscache_submit_op(object, &op->op) < 0) goto nobufs_unlock; spin_unlock(&cookie->lock); @@ -389,21 +530,27 @@ int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie, /* we wait for the operation to become active, and then process it * *here*, in this thread, and not in the thread pool */ - if (test_bit(FSCACHE_OP_WAITING, &op->op.flags)) { - _debug(">>> WT"); - fscache_stat(&fscache_n_retrieval_op_waits); - wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING, - fscache_wait_bit, TASK_UNINTERRUPTIBLE); - _debug("<<< GO"); - } + ret = fscache_wait_for_retrieval_activation( + object, op, + __fscache_stat(&fscache_n_retrieval_op_waits), + __fscache_stat(&fscache_n_retrievals_object_dead)); + if (ret < 0) + goto error; /* ask the cache to honour the operation */ - if (test_bit(FSCACHE_COOKIE_NO_DATA_YET, &object->cookie->flags)) - func = object->cache->ops->allocate_pages; - else - func = object->cache->ops->read_or_alloc_pages; - ret = func(op, pages, nr_pages, gfp); + if (test_bit(FSCACHE_COOKIE_NO_DATA_YET, &object->cookie->flags)) { + fscache_stat(&fscache_n_cop_allocate_pages); + ret = object->cache->ops->allocate_pages( + op, pages, nr_pages, gfp); + fscache_stat_d(&fscache_n_cop_allocate_pages); + } else { + fscache_stat(&fscache_n_cop_read_or_alloc_pages); + ret = object->cache->ops->read_or_alloc_pages( + op, pages, nr_pages, gfp); + fscache_stat_d(&fscache_n_cop_read_or_alloc_pages); + } +error: if (ret == -ENOMEM) fscache_stat(&fscache_n_retrievals_nomem); else if (ret == -ERESTARTSYS) @@ -461,6 +608,7 @@ int __fscache_alloc_page(struct fscache_cookie *cookie, op = fscache_alloc_retrieval(page->mapping, NULL, NULL); if (!op) return -ENOMEM; + fscache_set_op_name(&op->op, "RetrAL1"); spin_lock(&cookie->lock); @@ -475,18 +623,22 @@ int __fscache_alloc_page(struct fscache_cookie *cookie, fscache_stat(&fscache_n_alloc_ops); - if (test_bit(FSCACHE_OP_WAITING, &op->op.flags)) { - _debug(">>> WT"); - fscache_stat(&fscache_n_alloc_op_waits); - wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING, - fscache_wait_bit, TASK_UNINTERRUPTIBLE); - _debug("<<< GO"); - } + ret = fscache_wait_for_retrieval_activation( + object, op, + __fscache_stat(&fscache_n_alloc_op_waits), + __fscache_stat(&fscache_n_allocs_object_dead)); + if (ret < 0) + goto error; /* ask the cache to honour the operation */ + fscache_stat(&fscache_n_cop_allocate_page); ret = object->cache->ops->allocate_page(op, page, gfp); + fscache_stat_d(&fscache_n_cop_allocate_page); - if (ret < 0) +error: + if (ret == -ERESTARTSYS) + fscache_stat(&fscache_n_allocs_intr); + else if (ret < 0) fscache_stat(&fscache_n_allocs_nobufs); else fscache_stat(&fscache_n_allocs_ok); @@ -521,7 +673,7 @@ static void fscache_write_op(struct fscache_operation *_op) struct fscache_storage *op = container_of(_op, struct fscache_storage, op); struct fscache_object *object = op->op.object; - struct fscache_cookie *cookie = object->cookie; + struct fscache_cookie *cookie; struct page *page; unsigned n; void *results[1]; @@ -529,16 +681,19 @@ static void fscache_write_op(struct fscache_operation *_op) _enter("{OP%x,%d}", op->op.debug_id, atomic_read(&op->op.usage)); - spin_lock(&cookie->lock); + fscache_set_op_state(&op->op, "GetPage"); + spin_lock(&object->lock); + cookie = object->cookie; - if (!fscache_object_is_active(object)) { + if (!fscache_object_is_active(object) || !cookie) { spin_unlock(&object->lock); - spin_unlock(&cookie->lock); _leave(""); return; } + spin_lock(&cookie->stores_lock); + fscache_stat(&fscache_n_store_calls); /* find a page to store */ @@ -549,23 +704,35 @@ static void fscache_write_op(struct fscache_operation *_op) goto superseded; page = results[0]; _debug("gang %d [%lx]", n, page->index); - if (page->index > op->store_limit) + if (page->index > op->store_limit) { + fscache_stat(&fscache_n_store_pages_over_limit); goto superseded; + } - radix_tree_tag_clear(&cookie->stores, page->index, - FSCACHE_COOKIE_PENDING_TAG); + if (page) { + radix_tree_tag_set(&cookie->stores, page->index, + FSCACHE_COOKIE_STORING_TAG); + radix_tree_tag_clear(&cookie->stores, page->index, + FSCACHE_COOKIE_PENDING_TAG); + } + spin_unlock(&cookie->stores_lock); spin_unlock(&object->lock); - spin_unlock(&cookie->lock); if (page) { + fscache_set_op_state(&op->op, "Store"); + fscache_stat(&fscache_n_store_pages); + fscache_stat(&fscache_n_cop_write_page); ret = object->cache->ops->write_page(op, page); - fscache_end_page_write(cookie, page); - page_cache_release(page); - if (ret < 0) + fscache_stat_d(&fscache_n_cop_write_page); + fscache_set_op_state(&op->op, "EndWrite"); + fscache_end_page_write(object, page); + if (ret < 0) { + fscache_set_op_state(&op->op, "Abort"); fscache_abort_object(object); - else + } else { fscache_enqueue_operation(&op->op); + } } _leave(""); @@ -575,9 +742,9 @@ superseded: /* this writer is going away and there aren't any more things to * write */ _debug("cease"); + spin_unlock(&cookie->stores_lock); clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags); spin_unlock(&object->lock); - spin_unlock(&cookie->lock); _leave(""); } @@ -634,6 +801,7 @@ int __fscache_write_page(struct fscache_cookie *cookie, fscache_operation_init(&op->op, fscache_release_write_op); fscache_operation_init_slow(&op->op, fscache_write_op); op->op.flags = FSCACHE_OP_SLOW | (1 << FSCACHE_OP_WAITING); + fscache_set_op_name(&op->op, "Write1"); ret = radix_tree_preload(gfp & ~__GFP_HIGHMEM); if (ret < 0) @@ -652,6 +820,7 @@ int __fscache_write_page(struct fscache_cookie *cookie, /* add the page to the pending-storage radix tree on the backing * object */ spin_lock(&object->lock); + spin_lock(&cookie->stores_lock); _debug("store limit %llx", (unsigned long long) object->store_limit); @@ -672,6 +841,7 @@ int __fscache_write_page(struct fscache_cookie *cookie, if (test_and_set_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags)) goto already_pending; + spin_unlock(&cookie->stores_lock); spin_unlock(&object->lock); op->op.debug_id = atomic_inc_return(&fscache_op_debug_id); @@ -693,6 +863,7 @@ int __fscache_write_page(struct fscache_cookie *cookie, already_queued: fscache_stat(&fscache_n_stores_again); already_pending: + spin_unlock(&cookie->stores_lock); spin_unlock(&object->lock); spin_unlock(&cookie->lock); radix_tree_preload_end(); @@ -702,7 +873,9 @@ already_pending: return 0; submit_failed: + spin_lock(&cookie->stores_lock); radix_tree_delete(&cookie->stores, page->index); + spin_unlock(&cookie->stores_lock); page_cache_release(page); ret = -ENOBUFS; goto nobufs; @@ -763,7 +936,9 @@ void __fscache_uncache_page(struct fscache_cookie *cookie, struct page *page) if (TestClearPageFsCache(page) && object->cache->ops->uncache_page) { /* the cache backend releases the cookie lock */ + fscache_stat(&fscache_n_cop_uncache_page); object->cache->ops->uncache_page(object, page); + fscache_stat_d(&fscache_n_cop_uncache_page); goto done; } diff --git a/fs/fscache/proc.c b/fs/fscache/proc.c index beeab44bc31a..1d9e4951a597 100644 --- a/fs/fscache/proc.c +++ b/fs/fscache/proc.c @@ -37,10 +37,20 @@ int __init fscache_proc_init(void) goto error_histogram; #endif +#ifdef CONFIG_FSCACHE_OBJECT_LIST + if (!proc_create("fs/fscache/objects", S_IFREG | 0444, NULL, + &fscache_objlist_fops)) + goto error_objects; +#endif + _leave(" = 0"); return 0; +#ifdef CONFIG_FSCACHE_OBJECT_LIST +error_objects: +#endif #ifdef CONFIG_FSCACHE_HISTOGRAM + remove_proc_entry("fs/fscache/histogram", NULL); error_histogram: #endif #ifdef CONFIG_FSCACHE_STATS @@ -58,6 +68,9 @@ error_dir: */ void fscache_proc_cleanup(void) { +#ifdef CONFIG_FSCACHE_OBJECT_LIST + remove_proc_entry("fs/fscache/objects", NULL); +#endif #ifdef CONFIG_FSCACHE_HISTOGRAM remove_proc_entry("fs/fscache/histogram", NULL); #endif diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c index 65deb99e756b..46435f3aae68 100644 --- a/fs/fscache/stats.c +++ b/fs/fscache/stats.c @@ -25,6 +25,8 @@ atomic_t fscache_n_op_requeue; atomic_t fscache_n_op_deferred_release; atomic_t fscache_n_op_release; atomic_t fscache_n_op_gc; +atomic_t fscache_n_op_cancelled; +atomic_t fscache_n_op_rejected; atomic_t fscache_n_attr_changed; atomic_t fscache_n_attr_changed_ok; @@ -36,6 +38,8 @@ atomic_t fscache_n_allocs; atomic_t fscache_n_allocs_ok; atomic_t fscache_n_allocs_wait; atomic_t fscache_n_allocs_nobufs; +atomic_t fscache_n_allocs_intr; +atomic_t fscache_n_allocs_object_dead; atomic_t fscache_n_alloc_ops; atomic_t fscache_n_alloc_op_waits; @@ -46,6 +50,7 @@ atomic_t fscache_n_retrievals_nodata; atomic_t fscache_n_retrievals_nobufs; atomic_t fscache_n_retrievals_intr; atomic_t fscache_n_retrievals_nomem; +atomic_t fscache_n_retrievals_object_dead; atomic_t fscache_n_retrieval_ops; atomic_t fscache_n_retrieval_op_waits; @@ -56,6 +61,14 @@ atomic_t fscache_n_stores_nobufs; atomic_t fscache_n_stores_oom; atomic_t fscache_n_store_ops; atomic_t fscache_n_store_calls; +atomic_t fscache_n_store_pages; +atomic_t fscache_n_store_radix_deletes; +atomic_t fscache_n_store_pages_over_limit; + +atomic_t fscache_n_store_vmscan_not_storing; +atomic_t fscache_n_store_vmscan_gone; +atomic_t fscache_n_store_vmscan_busy; +atomic_t fscache_n_store_vmscan_cancelled; atomic_t fscache_n_marks; atomic_t fscache_n_uncaches; @@ -74,6 +87,7 @@ atomic_t fscache_n_updates_run; atomic_t fscache_n_relinquishes; atomic_t fscache_n_relinquishes_null; atomic_t fscache_n_relinquishes_waitcrt; +atomic_t fscache_n_relinquishes_retire; atomic_t fscache_n_cookie_index; atomic_t fscache_n_cookie_data; @@ -84,6 +98,7 @@ atomic_t fscache_n_object_no_alloc; atomic_t fscache_n_object_lookups; atomic_t fscache_n_object_lookups_negative; atomic_t fscache_n_object_lookups_positive; +atomic_t fscache_n_object_lookups_timed_out; atomic_t fscache_n_object_created; atomic_t fscache_n_object_avail; atomic_t fscache_n_object_dead; @@ -93,6 +108,23 @@ atomic_t fscache_n_checkaux_okay; atomic_t fscache_n_checkaux_update; atomic_t fscache_n_checkaux_obsolete; +atomic_t fscache_n_cop_alloc_object; +atomic_t fscache_n_cop_lookup_object; +atomic_t fscache_n_cop_lookup_complete; +atomic_t fscache_n_cop_grab_object; +atomic_t fscache_n_cop_update_object; +atomic_t fscache_n_cop_drop_object; +atomic_t fscache_n_cop_put_object; +atomic_t fscache_n_cop_sync_cache; +atomic_t fscache_n_cop_attr_changed; +atomic_t fscache_n_cop_read_or_alloc_page; +atomic_t fscache_n_cop_read_or_alloc_pages; +atomic_t fscache_n_cop_allocate_page; +atomic_t fscache_n_cop_allocate_pages; +atomic_t fscache_n_cop_write_page; +atomic_t fscache_n_cop_uncache_page; +atomic_t fscache_n_cop_dissociate_pages; + /* * display the general statistics */ @@ -129,10 +161,11 @@ static int fscache_stats_show(struct seq_file *m, void *v) atomic_read(&fscache_n_acquires_nobufs), atomic_read(&fscache_n_acquires_oom)); - seq_printf(m, "Lookups: n=%u neg=%u pos=%u crt=%u\n", + seq_printf(m, "Lookups: n=%u neg=%u pos=%u crt=%u tmo=%u\n", atomic_read(&fscache_n_object_lookups), atomic_read(&fscache_n_object_lookups_negative), atomic_read(&fscache_n_object_lookups_positive), + atomic_read(&fscache_n_object_lookups_timed_out), atomic_read(&fscache_n_object_created)); seq_printf(m, "Updates: n=%u nul=%u run=%u\n", @@ -140,10 +173,11 @@ static int fscache_stats_show(struct seq_file *m, void *v) atomic_read(&fscache_n_updates_null), atomic_read(&fscache_n_updates_run)); - seq_printf(m, "Relinqs: n=%u nul=%u wcr=%u\n", + seq_printf(m, "Relinqs: n=%u nul=%u wcr=%u rtr=%u\n", atomic_read(&fscache_n_relinquishes), atomic_read(&fscache_n_relinquishes_null), - atomic_read(&fscache_n_relinquishes_waitcrt)); + atomic_read(&fscache_n_relinquishes_waitcrt), + atomic_read(&fscache_n_relinquishes_retire)); seq_printf(m, "AttrChg: n=%u ok=%u nbf=%u oom=%u run=%u\n", atomic_read(&fscache_n_attr_changed), @@ -152,14 +186,16 @@ static int fscache_stats_show(struct seq_file *m, void *v) atomic_read(&fscache_n_attr_changed_nomem), atomic_read(&fscache_n_attr_changed_calls)); - seq_printf(m, "Allocs : n=%u ok=%u wt=%u nbf=%u\n", + seq_printf(m, "Allocs : n=%u ok=%u wt=%u nbf=%u int=%u\n", atomic_read(&fscache_n_allocs), atomic_read(&fscache_n_allocs_ok), atomic_read(&fscache_n_allocs_wait), - atomic_read(&fscache_n_allocs_nobufs)); - seq_printf(m, "Allocs : ops=%u owt=%u\n", + atomic_read(&fscache_n_allocs_nobufs), + atomic_read(&fscache_n_allocs_intr)); + seq_printf(m, "Allocs : ops=%u owt=%u abt=%u\n", atomic_read(&fscache_n_alloc_ops), - atomic_read(&fscache_n_alloc_op_waits)); + atomic_read(&fscache_n_alloc_op_waits), + atomic_read(&fscache_n_allocs_object_dead)); seq_printf(m, "Retrvls: n=%u ok=%u wt=%u nod=%u nbf=%u" " int=%u oom=%u\n", @@ -170,9 +206,10 @@ static int fscache_stats_show(struct seq_file *m, void *v) atomic_read(&fscache_n_retrievals_nobufs), atomic_read(&fscache_n_retrievals_intr), atomic_read(&fscache_n_retrievals_nomem)); - seq_printf(m, "Retrvls: ops=%u owt=%u\n", + seq_printf(m, "Retrvls: ops=%u owt=%u abt=%u\n", atomic_read(&fscache_n_retrieval_ops), - atomic_read(&fscache_n_retrieval_op_waits)); + atomic_read(&fscache_n_retrieval_op_waits), + atomic_read(&fscache_n_retrievals_object_dead)); seq_printf(m, "Stores : n=%u ok=%u agn=%u nbf=%u oom=%u\n", atomic_read(&fscache_n_stores), @@ -180,18 +217,49 @@ static int fscache_stats_show(struct seq_file *m, void *v) atomic_read(&fscache_n_stores_again), atomic_read(&fscache_n_stores_nobufs), atomic_read(&fscache_n_stores_oom)); - seq_printf(m, "Stores : ops=%u run=%u\n", + seq_printf(m, "Stores : ops=%u run=%u pgs=%u rxd=%u olm=%u\n", atomic_read(&fscache_n_store_ops), - atomic_read(&fscache_n_store_calls)); + atomic_read(&fscache_n_store_calls), + atomic_read(&fscache_n_store_pages), + atomic_read(&fscache_n_store_radix_deletes), + atomic_read(&fscache_n_store_pages_over_limit)); - seq_printf(m, "Ops : pend=%u run=%u enq=%u\n", + seq_printf(m, "VmScan : nos=%u gon=%u bsy=%u can=%u\n", + atomic_read(&fscache_n_store_vmscan_not_storing), + atomic_read(&fscache_n_store_vmscan_gone), + atomic_read(&fscache_n_store_vmscan_busy), + atomic_read(&fscache_n_store_vmscan_cancelled)); + + seq_printf(m, "Ops : pend=%u run=%u enq=%u can=%u rej=%u\n", atomic_read(&fscache_n_op_pend), atomic_read(&fscache_n_op_run), - atomic_read(&fscache_n_op_enqueue)); + atomic_read(&fscache_n_op_enqueue), + atomic_read(&fscache_n_op_cancelled), + atomic_read(&fscache_n_op_rejected)); seq_printf(m, "Ops : dfr=%u rel=%u gc=%u\n", atomic_read(&fscache_n_op_deferred_release), atomic_read(&fscache_n_op_release), atomic_read(&fscache_n_op_gc)); + + seq_printf(m, "CacheOp: alo=%d luo=%d luc=%d gro=%d\n", + atomic_read(&fscache_n_cop_alloc_object), + atomic_read(&fscache_n_cop_lookup_object), + atomic_read(&fscache_n_cop_lookup_complete), + atomic_read(&fscache_n_cop_grab_object)); + seq_printf(m, "CacheOp: upo=%d dro=%d pto=%d atc=%d syn=%d\n", + atomic_read(&fscache_n_cop_update_object), + atomic_read(&fscache_n_cop_drop_object), + atomic_read(&fscache_n_cop_put_object), + atomic_read(&fscache_n_cop_attr_changed), + atomic_read(&fscache_n_cop_sync_cache)); + seq_printf(m, "CacheOp: rap=%d ras=%d alp=%d als=%d wrp=%d ucp=%d dsp=%d\n", + atomic_read(&fscache_n_cop_read_or_alloc_page), + atomic_read(&fscache_n_cop_read_or_alloc_pages), + atomic_read(&fscache_n_cop_allocate_page), + atomic_read(&fscache_n_cop_allocate_pages), + atomic_read(&fscache_n_cop_write_page), + atomic_read(&fscache_n_cop_uncache_page), + atomic_read(&fscache_n_cop_dissociate_pages)); return 0; } diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 8ada78aade58..4787ae6c5c1c 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -385,6 +385,9 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode, if (fc->no_create) return -ENOSYS; + if (flags & O_DIRECT) + return -EINVAL; + forget_req = fuse_get_req(fc); if (IS_ERR(forget_req)) return PTR_ERR(forget_req); diff --git a/fs/gfs2/Kconfig b/fs/gfs2/Kconfig index 5971359d2090..4dcddf83326f 100644 --- a/fs/gfs2/Kconfig +++ b/fs/gfs2/Kconfig @@ -8,6 +8,8 @@ config GFS2_FS select FS_POSIX_ACL select CRC32 select SLOW_WORK + select QUOTA + select QUOTACTL help A cluster filesystem. diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c index 3fc4e3ac7d84..3eb1ea846173 100644 --- a/fs/gfs2/acl.c +++ b/fs/gfs2/acl.c @@ -12,6 +12,7 @@ #include <linux/spinlock.h> #include <linux/completion.h> #include <linux/buffer_head.h> +#include <linux/xattr.h> #include <linux/posix_acl.h> #include <linux/posix_acl_xattr.h> #include <linux/gfs2_ondisk.h> @@ -26,108 +27,44 @@ #include "trans.h" #include "util.h" -#define ACL_ACCESS 1 -#define ACL_DEFAULT 0 - -int gfs2_acl_validate_set(struct gfs2_inode *ip, int access, - struct gfs2_ea_request *er, int *remove, mode_t *mode) +static const char *gfs2_acl_name(int type) { - struct posix_acl *acl; - int error; - - error = gfs2_acl_validate_remove(ip, access); - if (error) - return error; - - if (!er->er_data) - return -EINVAL; - - acl = posix_acl_from_xattr(er->er_data, er->er_data_len); - if (IS_ERR(acl)) - return PTR_ERR(acl); - if (!acl) { - *remove = 1; - return 0; - } - - error = posix_acl_valid(acl); - if (error) - goto out; - - if (access) { - error = posix_acl_equiv_mode(acl, mode); - if (!error) - *remove = 1; - else if (error > 0) - error = 0; + switch (type) { + case ACL_TYPE_ACCESS: + return GFS2_POSIX_ACL_ACCESS; + case ACL_TYPE_DEFAULT: + return GFS2_POSIX_ACL_DEFAULT; } - -out: - posix_acl_release(acl); - return error; -} - -int gfs2_acl_validate_remove(struct gfs2_inode *ip, int access) -{ - if (!GFS2_SB(&ip->i_inode)->sd_args.ar_posix_acl) - return -EOPNOTSUPP; - if (!is_owner_or_cap(&ip->i_inode)) - return -EPERM; - if (S_ISLNK(ip->i_inode.i_mode)) - return -EOPNOTSUPP; - if (!access && !S_ISDIR(ip->i_inode.i_mode)) - return -EACCES; - - return 0; + return NULL; } -static int acl_get(struct gfs2_inode *ip, const char *name, - struct posix_acl **acl, struct gfs2_ea_location *el, - char **datap, unsigned int *lenp) +static struct posix_acl *gfs2_acl_get(struct gfs2_inode *ip, int type) { + struct posix_acl *acl; + const char *name; char *data; - unsigned int len; - int error; - - el->el_bh = NULL; + int len; if (!ip->i_eattr) - return 0; - - error = gfs2_ea_find(ip, GFS2_EATYPE_SYS, name, el); - if (error) - return error; - if (!el->el_ea) - return 0; - if (!GFS2_EA_DATA_LEN(el->el_ea)) - goto out; + return NULL; - len = GFS2_EA_DATA_LEN(el->el_ea); - data = kmalloc(len, GFP_NOFS); - error = -ENOMEM; - if (!data) - goto out; + acl = get_cached_acl(&ip->i_inode, type); + if (acl != ACL_NOT_CACHED) + return acl; - error = gfs2_ea_get_copy(ip, el, data, len); - if (error < 0) - goto out_kfree; - error = 0; + name = gfs2_acl_name(type); + if (name == NULL) + return ERR_PTR(-EINVAL); - if (acl) { - *acl = posix_acl_from_xattr(data, len); - if (IS_ERR(*acl)) - error = PTR_ERR(*acl); - } + len = gfs2_xattr_acl_get(ip, name, &data); + if (len < 0) + return ERR_PTR(len); + if (len == 0) + return NULL; -out_kfree: - if (error || !datap) { - kfree(data); - } else { - *datap = data; - *lenp = len; - } -out: - return error; + acl = posix_acl_from_xattr(data, len); + kfree(data); + return acl; } /** @@ -140,14 +77,12 @@ out: int gfs2_check_acl(struct inode *inode, int mask) { - struct gfs2_ea_location el; - struct posix_acl *acl = NULL; + struct posix_acl *acl; int error; - error = acl_get(GFS2_I(inode), GFS2_POSIX_ACL_ACCESS, &acl, &el, NULL, NULL); - brelse(el.el_bh); - if (error) - return error; + acl = gfs2_acl_get(GFS2_I(inode), ACL_TYPE_ACCESS); + if (IS_ERR(acl)) + return PTR_ERR(acl); if (acl) { error = posix_acl_permission(inode, acl, mask); @@ -158,57 +93,75 @@ int gfs2_check_acl(struct inode *inode, int mask) return -EAGAIN; } -static int munge_mode(struct gfs2_inode *ip, mode_t mode) +static int gfs2_set_mode(struct inode *inode, mode_t mode) { - struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - struct buffer_head *dibh; - int error; + int error = 0; - error = gfs2_trans_begin(sdp, RES_DINODE, 0); - if (error) - return error; + if (mode != inode->i_mode) { + struct iattr iattr; - error = gfs2_meta_inode_buffer(ip, &dibh); - if (!error) { - gfs2_assert_withdraw(sdp, - (ip->i_inode.i_mode & S_IFMT) == (mode & S_IFMT)); - ip->i_inode.i_mode = mode; - gfs2_trans_add_bh(ip->i_gl, dibh, 1); - gfs2_dinode_out(ip, dibh->b_data); - brelse(dibh); + iattr.ia_valid = ATTR_MODE; + iattr.ia_mode = mode; + + error = gfs2_setattr_simple(GFS2_I(inode), &iattr); } - gfs2_trans_end(sdp); + return error; +} + +static int gfs2_acl_set(struct inode *inode, int type, struct posix_acl *acl) +{ + int error; + int len; + char *data; + const char *name = gfs2_acl_name(type); - return 0; + BUG_ON(name == NULL); + len = posix_acl_to_xattr(acl, NULL, 0); + if (len == 0) + return 0; + data = kmalloc(len, GFP_NOFS); + if (data == NULL) + return -ENOMEM; + error = posix_acl_to_xattr(acl, data, len); + if (error < 0) + goto out; + error = gfs2_xattr_set(inode, GFS2_EATYPE_SYS, name, data, len, 0); + if (!error) + set_cached_acl(inode, type, acl); +out: + kfree(data); + return error; } -int gfs2_acl_create(struct gfs2_inode *dip, struct gfs2_inode *ip) +int gfs2_acl_create(struct gfs2_inode *dip, struct inode *inode) { - struct gfs2_ea_location el; struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode); - struct posix_acl *acl = NULL, *clone; - mode_t mode = ip->i_inode.i_mode; - char *data = NULL; - unsigned int len; - int error; + struct posix_acl *acl, *clone; + mode_t mode = inode->i_mode; + int error = 0; if (!sdp->sd_args.ar_posix_acl) return 0; - if (S_ISLNK(ip->i_inode.i_mode)) + if (S_ISLNK(inode->i_mode)) return 0; - error = acl_get(dip, GFS2_POSIX_ACL_DEFAULT, &acl, &el, &data, &len); - brelse(el.el_bh); - if (error) - return error; + acl = gfs2_acl_get(dip, ACL_TYPE_DEFAULT); + if (IS_ERR(acl)) + return PTR_ERR(acl); if (!acl) { mode &= ~current_umask(); - if (mode != ip->i_inode.i_mode) - error = munge_mode(ip, mode); + if (mode != inode->i_mode) + error = gfs2_set_mode(inode, mode); return error; } + if (S_ISDIR(inode->i_mode)) { + error = gfs2_acl_set(inode, ACL_TYPE_DEFAULT, acl); + if (error) + goto out; + } + clone = posix_acl_clone(acl, GFP_NOFS); error = -ENOMEM; if (!clone) @@ -216,43 +169,32 @@ int gfs2_acl_create(struct gfs2_inode *dip, struct gfs2_inode *ip) posix_acl_release(acl); acl = clone; - if (S_ISDIR(ip->i_inode.i_mode)) { - error = gfs2_xattr_set(&ip->i_inode, GFS2_EATYPE_SYS, - GFS2_POSIX_ACL_DEFAULT, data, len, 0); - if (error) - goto out; - } - error = posix_acl_create_masq(acl, &mode); if (error < 0) goto out; if (error == 0) goto munge; - posix_acl_to_xattr(acl, data, len); - error = gfs2_xattr_set(&ip->i_inode, GFS2_EATYPE_SYS, - GFS2_POSIX_ACL_ACCESS, data, len, 0); + error = gfs2_acl_set(inode, ACL_TYPE_ACCESS, acl); if (error) goto out; munge: - error = munge_mode(ip, mode); + error = gfs2_set_mode(inode, mode); out: posix_acl_release(acl); - kfree(data); return error; } int gfs2_acl_chmod(struct gfs2_inode *ip, struct iattr *attr) { - struct posix_acl *acl = NULL, *clone; - struct gfs2_ea_location el; + struct posix_acl *acl, *clone; char *data; unsigned int len; int error; - error = acl_get(ip, GFS2_POSIX_ACL_ACCESS, &acl, &el, &data, &len); - if (error) - goto out_brelse; + acl = gfs2_acl_get(ip, ACL_TYPE_ACCESS); + if (IS_ERR(acl)) + return PTR_ERR(acl); if (!acl) return gfs2_setattr_simple(ip, attr); @@ -265,15 +207,134 @@ int gfs2_acl_chmod(struct gfs2_inode *ip, struct iattr *attr) error = posix_acl_chmod_masq(acl, attr->ia_mode); if (!error) { + len = posix_acl_to_xattr(acl, NULL, 0); + data = kmalloc(len, GFP_NOFS); + error = -ENOMEM; + if (data == NULL) + goto out; posix_acl_to_xattr(acl, data, len); - error = gfs2_ea_acl_chmod(ip, &el, attr, data); + error = gfs2_xattr_acl_chmod(ip, attr, data); + kfree(data); + set_cached_acl(&ip->i_inode, ACL_TYPE_ACCESS, acl); } out: posix_acl_release(acl); - kfree(data); -out_brelse: - brelse(el.el_bh); return error; } +static int gfs2_acl_type(const char *name) +{ + if (strcmp(name, GFS2_POSIX_ACL_ACCESS) == 0) + return ACL_TYPE_ACCESS; + if (strcmp(name, GFS2_POSIX_ACL_DEFAULT) == 0) + return ACL_TYPE_DEFAULT; + return -EINVAL; +} + +static int gfs2_xattr_system_get(struct inode *inode, const char *name, + void *buffer, size_t size) +{ + struct posix_acl *acl; + int type; + int error; + + type = gfs2_acl_type(name); + if (type < 0) + return type; + + acl = gfs2_acl_get(GFS2_I(inode), type); + if (IS_ERR(acl)) + return PTR_ERR(acl); + if (acl == NULL) + return -ENODATA; + + error = posix_acl_to_xattr(acl, buffer, size); + posix_acl_release(acl); + + return error; +} + +static int gfs2_xattr_system_set(struct inode *inode, const char *name, + const void *value, size_t size, int flags) +{ + struct gfs2_sbd *sdp = GFS2_SB(inode); + struct posix_acl *acl = NULL; + int error = 0, type; + + if (!sdp->sd_args.ar_posix_acl) + return -EOPNOTSUPP; + + type = gfs2_acl_type(name); + if (type < 0) + return type; + if (flags & XATTR_CREATE) + return -EINVAL; + if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode)) + return value ? -EACCES : 0; + if ((current_fsuid() != inode->i_uid) && !capable(CAP_FOWNER)) + return -EPERM; + if (S_ISLNK(inode->i_mode)) + return -EOPNOTSUPP; + + if (!value) + goto set_acl; + + acl = posix_acl_from_xattr(value, size); + if (!acl) { + /* + * acl_set_file(3) may request that we set default ACLs with + * zero length -- defend (gracefully) against that here. + */ + goto out; + } + if (IS_ERR(acl)) { + error = PTR_ERR(acl); + goto out; + } + + error = posix_acl_valid(acl); + if (error) + goto out_release; + + error = -EINVAL; + if (acl->a_count > GFS2_ACL_MAX_ENTRIES) + goto out_release; + + if (type == ACL_TYPE_ACCESS) { + mode_t mode = inode->i_mode; + error = posix_acl_equiv_mode(acl, &mode); + + if (error <= 0) { + posix_acl_release(acl); + acl = NULL; + + if (error < 0) + return error; + } + + error = gfs2_set_mode(inode, mode); + if (error) + goto out_release; + } + +set_acl: + error = gfs2_xattr_set(inode, GFS2_EATYPE_SYS, name, value, size, 0); + if (!error) { + if (acl) + set_cached_acl(inode, type, acl); + else + forget_cached_acl(inode, type); + } +out_release: + posix_acl_release(acl); +out: + return error; +} + +struct xattr_handler gfs2_xattr_system_handler = { + .prefix = XATTR_SYSTEM_PREFIX, + .get = gfs2_xattr_system_get, + .set = gfs2_xattr_system_set, +}; + diff --git a/fs/gfs2/acl.h b/fs/gfs2/acl.h index 6751930bfb64..9306a2e6620c 100644 --- a/fs/gfs2/acl.h +++ b/fs/gfs2/acl.h @@ -13,26 +13,12 @@ #include "incore.h" #define GFS2_POSIX_ACL_ACCESS "posix_acl_access" -#define GFS2_POSIX_ACL_ACCESS_LEN 16 #define GFS2_POSIX_ACL_DEFAULT "posix_acl_default" -#define GFS2_POSIX_ACL_DEFAULT_LEN 17 +#define GFS2_ACL_MAX_ENTRIES 25 -#define GFS2_ACL_IS_ACCESS(name, len) \ - ((len) == GFS2_POSIX_ACL_ACCESS_LEN && \ - !memcmp(GFS2_POSIX_ACL_ACCESS, (name), (len))) - -#define GFS2_ACL_IS_DEFAULT(name, len) \ - ((len) == GFS2_POSIX_ACL_DEFAULT_LEN && \ - !memcmp(GFS2_POSIX_ACL_DEFAULT, (name), (len))) - -struct gfs2_ea_request; - -int gfs2_acl_validate_set(struct gfs2_inode *ip, int access, - struct gfs2_ea_request *er, - int *remove, mode_t *mode); -int gfs2_acl_validate_remove(struct gfs2_inode *ip, int access); -int gfs2_check_acl(struct inode *inode, int mask); -int gfs2_acl_create(struct gfs2_inode *dip, struct gfs2_inode *ip); -int gfs2_acl_chmod(struct gfs2_inode *ip, struct iattr *attr); +extern int gfs2_check_acl(struct inode *inode, int mask); +extern int gfs2_acl_create(struct gfs2_inode *dip, struct inode *inode); +extern int gfs2_acl_chmod(struct gfs2_inode *ip, struct iattr *attr); +extern struct xattr_handler gfs2_xattr_system_handler; #endif /* __ACL_DOT_H__ */ diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 694b5d48f036..7b8da9415267 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -269,7 +269,6 @@ static int gfs2_write_jdata_pagevec(struct address_space *mapping, pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT; unsigned offset = i_size & (PAGE_CACHE_SIZE-1); unsigned nrblocks = nr_pages * (PAGE_CACHE_SIZE/inode->i_sb->s_blocksize); - struct backing_dev_info *bdi = mapping->backing_dev_info; int i; int ret; @@ -313,11 +312,6 @@ static int gfs2_write_jdata_pagevec(struct address_space *mapping, if (ret || (--(wbc->nr_to_write) <= 0)) ret = 1; - if (wbc->nonblocking && bdi_write_congested(bdi)) { - wbc->encountered_congestion = 1; - ret = 1; - } - } gfs2_trans_end(sdp); return ret; @@ -338,7 +332,6 @@ static int gfs2_write_jdata_pagevec(struct address_space *mapping, static int gfs2_write_cache_jdata(struct address_space *mapping, struct writeback_control *wbc) { - struct backing_dev_info *bdi = mapping->backing_dev_info; int ret = 0; int done = 0; struct pagevec pvec; @@ -348,11 +341,6 @@ static int gfs2_write_cache_jdata(struct address_space *mapping, int scanned = 0; int range_whole = 0; - if (wbc->nonblocking && bdi_write_congested(bdi)) { - wbc->encountered_congestion = 1; - return 0; - } - pagevec_init(&pvec, 0); if (wbc->range_cyclic) { index = mapping->writeback_index; /* Start from prev offset */ @@ -819,8 +807,10 @@ static int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh, mark_inode_dirty(inode); } - if (inode == sdp->sd_rindex) + if (inode == sdp->sd_rindex) { adjust_fs_space(inode); + ip->i_gh.gh_flags |= GL_NOCACHE; + } brelse(dibh); gfs2_trans_end(sdp); @@ -889,8 +879,10 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping, mark_inode_dirty(inode); } - if (inode == sdp->sd_rindex) + if (inode == sdp->sd_rindex) { adjust_fs_space(inode); + ip->i_gh.gh_flags |= GL_NOCACHE; + } brelse(dibh); gfs2_trans_end(sdp); diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index 297d7e5cebad..25fddc100f18 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -525,38 +525,6 @@ consist_inode: return ERR_PTR(-EIO); } - -/** - * dirent_first - Return the first dirent - * @dip: the directory - * @bh: The buffer - * @dent: Pointer to list of dirents - * - * return first dirent whether bh points to leaf or stuffed dinode - * - * Returns: IS_LEAF, IS_DINODE, or -errno - */ - -static int dirent_first(struct gfs2_inode *dip, struct buffer_head *bh, - struct gfs2_dirent **dent) -{ - struct gfs2_meta_header *h = (struct gfs2_meta_header *)bh->b_data; - - if (be32_to_cpu(h->mh_type) == GFS2_METATYPE_LF) { - if (gfs2_meta_check(GFS2_SB(&dip->i_inode), bh)) - return -EIO; - *dent = (struct gfs2_dirent *)(bh->b_data + - sizeof(struct gfs2_leaf)); - return IS_LEAF; - } else { - if (gfs2_metatype_check(GFS2_SB(&dip->i_inode), bh, GFS2_METATYPE_DI)) - return -EIO; - *dent = (struct gfs2_dirent *)(bh->b_data + - sizeof(struct gfs2_dinode)); - return IS_DINODE; - } -} - static int dirent_check_reclen(struct gfs2_inode *dip, const struct gfs2_dirent *d, const void *end_p) { @@ -1006,7 +974,7 @@ static int dir_split_leaf(struct inode *inode, const struct qstr *name) divider = (start + half_len) << (32 - dip->i_depth); /* Copy the entries */ - dirent_first(dip, obh, &dent); + dent = (struct gfs2_dirent *)(obh->b_data + sizeof(struct gfs2_leaf)); do { next = dent; diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 8b674b1f3a55..f455a03a09e2 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -241,15 +241,14 @@ int gfs2_glock_put(struct gfs2_glock *gl) int rv = 0; write_lock(gl_lock_addr(gl->gl_hash)); - if (atomic_dec_and_test(&gl->gl_ref)) { + if (atomic_dec_and_lock(&gl->gl_ref, &lru_lock)) { hlist_del(&gl->gl_list); - write_unlock(gl_lock_addr(gl->gl_hash)); - spin_lock(&lru_lock); if (!list_empty(&gl->gl_lru)) { list_del_init(&gl->gl_lru); atomic_dec(&lru_count); } spin_unlock(&lru_lock); + write_unlock(gl_lock_addr(gl->gl_hash)); GLOCK_BUG_ON(gl, !list_empty(&gl->gl_holders)); glock_free(gl); rv = 1; @@ -513,7 +512,6 @@ retry: GLOCK_BUG_ON(gl, 1); } spin_unlock(&gl->gl_spin); - gfs2_glock_put(gl); return; } @@ -524,8 +522,6 @@ retry: if (glops->go_xmote_bh) { spin_unlock(&gl->gl_spin); rv = glops->go_xmote_bh(gl, gh); - if (rv == -EAGAIN) - return; spin_lock(&gl->gl_spin); if (rv) { do_error(gl, rv); @@ -540,7 +536,6 @@ out: clear_bit(GLF_LOCK, &gl->gl_flags); out_locked: spin_unlock(&gl->gl_spin); - gfs2_glock_put(gl); } static unsigned int gfs2_lm_lock(struct gfs2_sbd *sdp, void *lock, @@ -600,7 +595,6 @@ __acquires(&gl->gl_spin) if (!(ret & LM_OUT_ASYNC)) { finish_xmote(gl, ret); - gfs2_glock_hold(gl); if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) gfs2_glock_put(gl); } else { @@ -672,12 +666,17 @@ out: return; out_sched: + clear_bit(GLF_LOCK, &gl->gl_flags); + smp_mb__after_clear_bit(); gfs2_glock_hold(gl); if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) gfs2_glock_put_nolock(gl); + return; + out_unlock: clear_bit(GLF_LOCK, &gl->gl_flags); - goto out; + smp_mb__after_clear_bit(); + return; } static void delete_work_func(struct work_struct *work) @@ -707,9 +706,12 @@ static void glock_work_func(struct work_struct *work) { unsigned long delay = 0; struct gfs2_glock *gl = container_of(work, struct gfs2_glock, gl_work.work); + int drop_ref = 0; - if (test_and_clear_bit(GLF_REPLY_PENDING, &gl->gl_flags)) + if (test_and_clear_bit(GLF_REPLY_PENDING, &gl->gl_flags)) { finish_xmote(gl, gl->gl_reply); + drop_ref = 1; + } down_read(&gfs2_umount_flush_sem); spin_lock(&gl->gl_spin); if (test_and_clear_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) && @@ -727,6 +729,8 @@ static void glock_work_func(struct work_struct *work) if (!delay || queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0) gfs2_glock_put(gl); + if (drop_ref) + gfs2_glock_put(gl); } /** @@ -1361,10 +1365,6 @@ static int gfs2_shrink_glock_memory(int nr, gfp_t gfp_mask) list_del_init(&gl->gl_lru); atomic_dec(&lru_count); - /* Check if glock is about to be freed */ - if (atomic_read(&gl->gl_ref) == 0) - continue; - /* Test for being demotable */ if (!test_and_set_bit(GLF_LOCK, &gl->gl_flags)) { gfs2_glock_hold(gl); @@ -1375,10 +1375,11 @@ static int gfs2_shrink_glock_memory(int nr, gfp_t gfp_mask) handle_callback(gl, LM_ST_UNLOCKED, 0); nr--; } + clear_bit(GLF_LOCK, &gl->gl_flags); + smp_mb__after_clear_bit(); if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) gfs2_glock_put_nolock(gl); spin_unlock(&gl->gl_spin); - clear_bit(GLF_LOCK, &gl->gl_flags); spin_lock(&lru_lock); continue; } diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h index c609894ec0d0..13f0bd228132 100644 --- a/fs/gfs2/glock.h +++ b/fs/gfs2/glock.h @@ -180,15 +180,6 @@ static inline int gfs2_glock_is_held_shrd(struct gfs2_glock *gl) return gl->gl_state == LM_ST_SHARED; } -static inline int gfs2_glock_is_blocking(struct gfs2_glock *gl) -{ - int ret; - spin_lock(&gl->gl_spin); - ret = test_bit(GLF_DEMOTE, &gl->gl_flags); - spin_unlock(&gl->gl_spin); - return ret; -} - int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, const struct gfs2_glock_operations *glops, int create, struct gfs2_glock **glp); diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 6985eef06c39..78554acc0605 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -13,6 +13,7 @@ #include <linux/buffer_head.h> #include <linux/gfs2_ondisk.h> #include <linux/bio.h> +#include <linux/posix_acl.h> #include "gfs2.h" #include "incore.h" @@ -184,8 +185,10 @@ static void inode_go_inval(struct gfs2_glock *gl, int flags) if (flags & DIO_METADATA) { struct address_space *mapping = gl->gl_aspace->i_mapping; truncate_inode_pages(mapping, 0); - if (ip) + if (ip) { set_bit(GIF_INVALID, &ip->i_flags); + forget_all_cached_acls(&ip->i_inode); + } } if (ip == GFS2_I(gl->gl_sbd->sd_rindex)) diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index 6edb423f90b3..4792200978c8 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -429,7 +429,11 @@ struct gfs2_args { unsigned int ar_meta:1; /* mount metafs */ unsigned int ar_discard:1; /* discard requests */ unsigned int ar_errors:2; /* errors=withdraw | panic */ + unsigned int ar_nobarrier:1; /* do not send barriers */ int ar_commit; /* Commit interval */ + int ar_statfs_quantum; /* The fast statfs interval */ + int ar_quota_quantum; /* The quota interval */ + int ar_statfs_percent; /* The % change to force sync */ }; struct gfs2_tune { @@ -558,6 +562,7 @@ struct gfs2_sbd { spinlock_t sd_statfs_spin; struct gfs2_statfs_change_host sd_statfs_master; struct gfs2_statfs_change_host sd_statfs_local; + int sd_statfs_force_sync; /* Resource group stuff */ diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index fb15d3b1f409..26ba2a4c4a2d 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -871,7 +871,7 @@ struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name, if (error) goto fail_gunlock2; - error = gfs2_acl_create(dip, GFS2_I(inode)); + error = gfs2_acl_create(dip, inode); if (error) goto fail_gunlock2; @@ -947,9 +947,7 @@ void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf) str->di_header.mh_magic = cpu_to_be32(GFS2_MAGIC); str->di_header.mh_type = cpu_to_be32(GFS2_METATYPE_DI); - str->di_header.__pad0 = 0; str->di_header.mh_format = cpu_to_be32(GFS2_FORMAT_DI); - str->di_header.__pad1 = 0; str->di_num.no_addr = cpu_to_be64(ip->i_no_addr); str->di_num.no_formal_ino = cpu_to_be64(ip->i_no_formal_ino); str->di_mode = cpu_to_be32(ip->i_inode.i_mode); diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 13c6237c5f67..4511b08fc451 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -596,7 +596,9 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull) memset(lh, 0, sizeof(struct gfs2_log_header)); lh->lh_header.mh_magic = cpu_to_be32(GFS2_MAGIC); lh->lh_header.mh_type = cpu_to_be32(GFS2_METATYPE_LH); + lh->lh_header.__pad0 = cpu_to_be64(0); lh->lh_header.mh_format = cpu_to_be32(GFS2_FORMAT_LH); + lh->lh_header.mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid); lh->lh_sequence = cpu_to_be64(sdp->sd_log_sequence++); lh->lh_flags = cpu_to_be32(flags); lh->lh_tail = cpu_to_be32(tail); diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 9969ff062c5b..de97632ba32f 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -132,6 +132,7 @@ static struct buffer_head *gfs2_get_log_desc(struct gfs2_sbd *sdp, u32 ld_type) static void buf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le) { struct gfs2_bufdata *bd = container_of(le, struct gfs2_bufdata, bd_le); + struct gfs2_meta_header *mh; struct gfs2_trans *tr; lock_buffer(bd->bd_bh); @@ -148,6 +149,9 @@ static void buf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le) set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags); gfs2_meta_check(sdp, bd->bd_bh); gfs2_pin(sdp, bd->bd_bh); + mh = (struct gfs2_meta_header *)bd->bd_bh->b_data; + mh->__pad0 = cpu_to_be64(0); + mh->mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid); sdp->sd_log_num_buf++; list_add(&le->le_list, &sdp->sd_log_le_buf); tr->tr_num_buf_new++; diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index eacd78a5d082..5b31f7741a8f 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -114,7 +114,7 @@ static int __init init_gfs2_fs(void) if (error) goto fail_unregister; - error = slow_work_register_user(); + error = slow_work_register_user(THIS_MODULE); if (error) goto fail_slow; @@ -163,7 +163,7 @@ static void __exit exit_gfs2_fs(void) gfs2_unregister_debugfs(); unregister_filesystem(&gfs2_fs_type); unregister_filesystem(&gfs2meta_fs_type); - slow_work_unregister_user(); + slow_work_unregister_user(THIS_MODULE); kmem_cache_destroy(gfs2_quotad_cachep); kmem_cache_destroy(gfs2_rgrpd_cachep); diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 52fb6c048981..edfee24f3636 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -18,6 +18,7 @@ #include <linux/mount.h> #include <linux/gfs2_ondisk.h> #include <linux/slow-work.h> +#include <linux/quotaops.h> #include "gfs2.h" #include "incore.h" @@ -62,13 +63,10 @@ static void gfs2_tune_init(struct gfs2_tune *gt) gt->gt_quota_warn_period = 10; gt->gt_quota_scale_num = 1; gt->gt_quota_scale_den = 1; - gt->gt_quota_quantum = 60; gt->gt_new_files_jdata = 0; gt->gt_max_readahead = 1 << 18; gt->gt_stall_secs = 600; gt->gt_complain_secs = 10; - gt->gt_statfs_quantum = 30; - gt->gt_statfs_slow = 0; } static struct gfs2_sbd *init_sbd(struct super_block *sb) @@ -1114,7 +1112,7 @@ void gfs2_online_uevent(struct gfs2_sbd *sdp) * Returns: errno */ -static int fill_super(struct super_block *sb, void *data, int silent) +static int fill_super(struct super_block *sb, struct gfs2_args *args, int silent) { struct gfs2_sbd *sdp; struct gfs2_holder mount_gh; @@ -1125,17 +1123,7 @@ static int fill_super(struct super_block *sb, void *data, int silent) printk(KERN_WARNING "GFS2: can't alloc struct gfs2_sbd\n"); return -ENOMEM; } - - sdp->sd_args.ar_quota = GFS2_QUOTA_DEFAULT; - sdp->sd_args.ar_data = GFS2_DATA_DEFAULT; - sdp->sd_args.ar_commit = 60; - sdp->sd_args.ar_errors = GFS2_ERRORS_DEFAULT; - - error = gfs2_mount_args(sdp, &sdp->sd_args, data); - if (error) { - printk(KERN_WARNING "GFS2: can't parse mount arguments\n"); - goto fail; - } + sdp->sd_args = *args; if (sdp->sd_args.ar_spectator) { sb->s_flags |= MS_RDONLY; @@ -1143,11 +1131,15 @@ static int fill_super(struct super_block *sb, void *data, int silent) } if (sdp->sd_args.ar_posix_acl) sb->s_flags |= MS_POSIXACL; + if (sdp->sd_args.ar_nobarrier) + set_bit(SDF_NOBARRIERS, &sdp->sd_flags); sb->s_magic = GFS2_MAGIC; sb->s_op = &gfs2_super_ops; sb->s_export_op = &gfs2_export_ops; sb->s_xattr = gfs2_xattr_handlers; + sb->s_qcop = &gfs2_quotactl_ops; + sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE; sb->s_time_gran = 1; sb->s_maxbytes = MAX_LFS_FILESIZE; @@ -1160,6 +1152,15 @@ static int fill_super(struct super_block *sb, void *data, int silent) sdp->sd_fsb2bb = 1 << sdp->sd_fsb2bb_shift; sdp->sd_tune.gt_log_flush_secs = sdp->sd_args.ar_commit; + sdp->sd_tune.gt_quota_quantum = sdp->sd_args.ar_quota_quantum; + if (sdp->sd_args.ar_statfs_quantum) { + sdp->sd_tune.gt_statfs_slow = 0; + sdp->sd_tune.gt_statfs_quantum = sdp->sd_args.ar_statfs_quantum; + } + else { + sdp->sd_tune.gt_statfs_slow = 1; + sdp->sd_tune.gt_statfs_quantum = 30; + } error = init_names(sdp, silent); if (error) @@ -1243,18 +1244,127 @@ fail: return error; } -static int gfs2_get_sb(struct file_system_type *fs_type, int flags, - const char *dev_name, void *data, struct vfsmount *mnt) +static int set_gfs2_super(struct super_block *s, void *data) { - return get_sb_bdev(fs_type, flags, dev_name, data, fill_super, mnt); + s->s_bdev = data; + s->s_dev = s->s_bdev->bd_dev; + + /* + * We set the bdi here to the queue backing, file systems can + * overwrite this in ->fill_super() + */ + s->s_bdi = &bdev_get_queue(s->s_bdev)->backing_dev_info; + return 0; } -static int test_meta_super(struct super_block *s, void *ptr) +static int test_gfs2_super(struct super_block *s, void *ptr) { struct block_device *bdev = ptr; return (bdev == s->s_bdev); } +/** + * gfs2_get_sb - Get the GFS2 superblock + * @fs_type: The GFS2 filesystem type + * @flags: Mount flags + * @dev_name: The name of the device + * @data: The mount arguments + * @mnt: The vfsmnt for this mount + * + * Q. Why not use get_sb_bdev() ? + * A. We need to select one of two root directories to mount, independent + * of whether this is the initial, or subsequent, mount of this sb + * + * Returns: 0 or -ve on error + */ + +static int gfs2_get_sb(struct file_system_type *fs_type, int flags, + const char *dev_name, void *data, struct vfsmount *mnt) +{ + struct block_device *bdev; + struct super_block *s; + fmode_t mode = FMODE_READ; + int error; + struct gfs2_args args; + struct gfs2_sbd *sdp; + + if (!(flags & MS_RDONLY)) + mode |= FMODE_WRITE; + + bdev = open_bdev_exclusive(dev_name, mode, fs_type); + if (IS_ERR(bdev)) + return PTR_ERR(bdev); + + /* + * once the super is inserted into the list by sget, s_umount + * will protect the lockfs code from trying to start a snapshot + * while we are mounting + */ + mutex_lock(&bdev->bd_fsfreeze_mutex); + if (bdev->bd_fsfreeze_count > 0) { + mutex_unlock(&bdev->bd_fsfreeze_mutex); + error = -EBUSY; + goto error_bdev; + } + s = sget(fs_type, test_gfs2_super, set_gfs2_super, bdev); + mutex_unlock(&bdev->bd_fsfreeze_mutex); + error = PTR_ERR(s); + if (IS_ERR(s)) + goto error_bdev; + + memset(&args, 0, sizeof(args)); + args.ar_quota = GFS2_QUOTA_DEFAULT; + args.ar_data = GFS2_DATA_DEFAULT; + args.ar_commit = 60; + args.ar_statfs_quantum = 30; + args.ar_quota_quantum = 60; + args.ar_errors = GFS2_ERRORS_DEFAULT; + + error = gfs2_mount_args(&args, data); + if (error) { + printk(KERN_WARNING "GFS2: can't parse mount arguments\n"); + if (s->s_root) + goto error_super; + deactivate_locked_super(s); + return error; + } + + if (s->s_root) { + error = -EBUSY; + if ((flags ^ s->s_flags) & MS_RDONLY) + goto error_super; + close_bdev_exclusive(bdev, mode); + } else { + char b[BDEVNAME_SIZE]; + + s->s_flags = flags; + s->s_mode = mode; + strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id)); + sb_set_blocksize(s, block_size(bdev)); + error = fill_super(s, &args, flags & MS_SILENT ? 1 : 0); + if (error) { + deactivate_locked_super(s); + return error; + } + s->s_flags |= MS_ACTIVE; + bdev->bd_super = s; + } + + sdp = s->s_fs_info; + mnt->mnt_sb = s; + if (args.ar_meta) + mnt->mnt_root = dget(sdp->sd_master_dir); + else + mnt->mnt_root = dget(sdp->sd_root_dir); + return 0; + +error_super: + deactivate_locked_super(s); +error_bdev: + close_bdev_exclusive(bdev, mode); + return error; +} + static int set_meta_super(struct super_block *s, void *ptr) { return -EINVAL; @@ -1274,13 +1384,17 @@ static int gfs2_get_sb_meta(struct file_system_type *fs_type, int flags, dev_name, error); return error; } - s = sget(&gfs2_fs_type, test_meta_super, set_meta_super, + s = sget(&gfs2_fs_type, test_gfs2_super, set_meta_super, path.dentry->d_inode->i_sb->s_bdev); path_put(&path); if (IS_ERR(s)) { printk(KERN_WARNING "GFS2: gfs2 mount does not exist\n"); return PTR_ERR(s); } + if ((flags ^ s->s_flags) & MS_RDONLY) { + deactivate_locked_super(s); + return -EBUSY; + } sdp = s->s_fs_info; mnt->mnt_sb = s; mnt->mnt_root = dget(sdp->sd_master_dir); diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 2e9b9326bfc9..e3bf6eab8750 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -15,7 +15,7 @@ * fuzziness in the current usage value of IDs that are being used on different * nodes in the cluster simultaneously. So, it is possible for a user on * multiple nodes to overrun their quota, but that overrun is controlable. - * Since quota tags are part of transactions, there is no need to a quota check + * Since quota tags are part of transactions, there is no need for a quota check * program to be run on node crashes or anything like that. * * There are couple of knobs that let the administrator manage the quota @@ -47,6 +47,8 @@ #include <linux/gfs2_ondisk.h> #include <linux/kthread.h> #include <linux/freezer.h> +#include <linux/quota.h> +#include <linux/dqblk_xfs.h> #include "gfs2.h" #include "incore.h" @@ -65,13 +67,6 @@ #define QUOTA_USER 1 #define QUOTA_GROUP 0 -struct gfs2_quota_host { - u64 qu_limit; - u64 qu_warn; - s64 qu_value; - u32 qu_ll_next; -}; - struct gfs2_quota_change_host { u64 qc_change; u32 qc_flags; /* GFS2_QCF_... */ @@ -164,7 +159,7 @@ fail: return error; } -static int qd_get(struct gfs2_sbd *sdp, int user, u32 id, int create, +static int qd_get(struct gfs2_sbd *sdp, int user, u32 id, struct gfs2_quota_data **qdp) { struct gfs2_quota_data *qd = NULL, *new_qd = NULL; @@ -202,7 +197,7 @@ static int qd_get(struct gfs2_sbd *sdp, int user, u32 id, int create, spin_unlock(&qd_lru_lock); - if (qd || !create) { + if (qd) { if (new_qd) { gfs2_glock_put(new_qd->qd_gl); kmem_cache_free(gfs2_quotad_cachep, new_qd); @@ -461,12 +456,12 @@ static void qd_unlock(struct gfs2_quota_data *qd) qd_put(qd); } -static int qdsb_get(struct gfs2_sbd *sdp, int user, u32 id, int create, +static int qdsb_get(struct gfs2_sbd *sdp, int user, u32 id, struct gfs2_quota_data **qdp) { int error; - error = qd_get(sdp, user, id, create, qdp); + error = qd_get(sdp, user, id, qdp); if (error) return error; @@ -508,20 +503,20 @@ int gfs2_quota_hold(struct gfs2_inode *ip, u32 uid, u32 gid) if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF) return 0; - error = qdsb_get(sdp, QUOTA_USER, ip->i_inode.i_uid, CREATE, qd); + error = qdsb_get(sdp, QUOTA_USER, ip->i_inode.i_uid, qd); if (error) goto out; al->al_qd_num++; qd++; - error = qdsb_get(sdp, QUOTA_GROUP, ip->i_inode.i_gid, CREATE, qd); + error = qdsb_get(sdp, QUOTA_GROUP, ip->i_inode.i_gid, qd); if (error) goto out; al->al_qd_num++; qd++; if (uid != NO_QUOTA_CHANGE && uid != ip->i_inode.i_uid) { - error = qdsb_get(sdp, QUOTA_USER, uid, CREATE, qd); + error = qdsb_get(sdp, QUOTA_USER, uid, qd); if (error) goto out; al->al_qd_num++; @@ -529,7 +524,7 @@ int gfs2_quota_hold(struct gfs2_inode *ip, u32 uid, u32 gid) } if (gid != NO_QUOTA_CHANGE && gid != ip->i_inode.i_gid) { - error = qdsb_get(sdp, QUOTA_GROUP, gid, CREATE, qd); + error = qdsb_get(sdp, QUOTA_GROUP, gid, qd); if (error) goto out; al->al_qd_num++; @@ -617,48 +612,36 @@ static void do_qc(struct gfs2_quota_data *qd, s64 change) mutex_unlock(&sdp->sd_quota_mutex); } -static void gfs2_quota_in(struct gfs2_quota_host *qu, const void *buf) -{ - const struct gfs2_quota *str = buf; - - qu->qu_limit = be64_to_cpu(str->qu_limit); - qu->qu_warn = be64_to_cpu(str->qu_warn); - qu->qu_value = be64_to_cpu(str->qu_value); - qu->qu_ll_next = be32_to_cpu(str->qu_ll_next); -} - -static void gfs2_quota_out(const struct gfs2_quota_host *qu, void *buf) -{ - struct gfs2_quota *str = buf; - - str->qu_limit = cpu_to_be64(qu->qu_limit); - str->qu_warn = cpu_to_be64(qu->qu_warn); - str->qu_value = cpu_to_be64(qu->qu_value); - str->qu_ll_next = cpu_to_be32(qu->qu_ll_next); - memset(&str->qu_reserved, 0, sizeof(str->qu_reserved)); -} - /** - * gfs2_adjust_quota + * gfs2_adjust_quota - adjust record of current block usage + * @ip: The quota inode + * @loc: Offset of the entry in the quota file + * @change: The amount of usage change to record + * @qd: The quota data + * @fdq: The updated limits to record * * This function was mostly borrowed from gfs2_block_truncate_page which was * in turn mostly borrowed from ext3 + * + * Returns: 0 or -ve on error */ + static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc, - s64 change, struct gfs2_quota_data *qd) + s64 change, struct gfs2_quota_data *qd, + struct fs_disk_quota *fdq) { struct inode *inode = &ip->i_inode; struct address_space *mapping = inode->i_mapping; unsigned long index = loc >> PAGE_CACHE_SHIFT; unsigned offset = loc & (PAGE_CACHE_SIZE - 1); unsigned blocksize, iblock, pos; - struct buffer_head *bh; + struct buffer_head *bh, *dibh; struct page *page; void *kaddr; - char *ptr; - struct gfs2_quota_host qp; + struct gfs2_quota *qp; s64 value; int err = -EIO; + u64 size; if (gfs2_is_stuffed(ip)) gfs2_unstuff_dinode(ip, NULL); @@ -700,18 +683,38 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc, gfs2_trans_add_bh(ip->i_gl, bh, 0); kaddr = kmap_atomic(page, KM_USER0); - ptr = kaddr + offset; - gfs2_quota_in(&qp, ptr); - qp.qu_value += change; - value = qp.qu_value; - gfs2_quota_out(&qp, ptr); + qp = kaddr + offset; + value = (s64)be64_to_cpu(qp->qu_value) + change; + qp->qu_value = cpu_to_be64(value); + qd->qd_qb.qb_value = qp->qu_value; + if (fdq) { + if (fdq->d_fieldmask & FS_DQ_BSOFT) { + qp->qu_warn = cpu_to_be64(fdq->d_blk_softlimit); + qd->qd_qb.qb_warn = qp->qu_warn; + } + if (fdq->d_fieldmask & FS_DQ_BHARD) { + qp->qu_limit = cpu_to_be64(fdq->d_blk_hardlimit); + qd->qd_qb.qb_limit = qp->qu_limit; + } + } flush_dcache_page(page); kunmap_atomic(kaddr, KM_USER0); - err = 0; - qd->qd_qb.qb_magic = cpu_to_be32(GFS2_MAGIC); - qd->qd_qb.qb_value = cpu_to_be64(value); - ((struct gfs2_quota_lvb*)(qd->qd_gl->gl_lvb))->qb_magic = cpu_to_be32(GFS2_MAGIC); - ((struct gfs2_quota_lvb*)(qd->qd_gl->gl_lvb))->qb_value = cpu_to_be64(value); + + err = gfs2_meta_inode_buffer(ip, &dibh); + if (err) + goto unlock; + + size = loc + sizeof(struct gfs2_quota); + if (size > inode->i_size) { + ip->i_disksize = size; + i_size_write(inode, size); + } + inode->i_mtime = inode->i_atime = CURRENT_TIME; + gfs2_trans_add_bh(ip->i_gl, dibh, 1); + gfs2_dinode_out(ip, dibh->b_data); + brelse(dibh); + mark_inode_dirty(inode); + unlock: unlock_page(page); page_cache_release(page); @@ -739,9 +742,9 @@ static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda) return -ENOMEM; sort(qda, num_qd, sizeof(struct gfs2_quota_data *), sort_qd, NULL); + mutex_lock_nested(&ip->i_inode.i_mutex, I_MUTEX_QUOTA); for (qx = 0; qx < num_qd; qx++) { - error = gfs2_glock_nq_init(qda[qx]->qd_gl, - LM_ST_EXCLUSIVE, + error = gfs2_glock_nq_init(qda[qx]->qd_gl, LM_ST_EXCLUSIVE, GL_NOCACHE, &ghs[qx]); if (error) goto out; @@ -795,9 +798,7 @@ static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda) for (x = 0; x < num_qd; x++) { qd = qda[x]; offset = qd2offset(qd); - error = gfs2_adjust_quota(ip, offset, qd->qd_change_sync, - (struct gfs2_quota_data *) - qd); + error = gfs2_adjust_quota(ip, offset, qd->qd_change_sync, qd, NULL); if (error) goto out_end_trans; @@ -817,21 +818,44 @@ out_gunlock: out: while (qx--) gfs2_glock_dq_uninit(&ghs[qx]); + mutex_unlock(&ip->i_inode.i_mutex); kfree(ghs); gfs2_log_flush(ip->i_gl->gl_sbd, ip->i_gl); return error; } +static int update_qd(struct gfs2_sbd *sdp, struct gfs2_quota_data *qd) +{ + struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode); + struct gfs2_quota q; + struct gfs2_quota_lvb *qlvb; + loff_t pos; + int error; + + memset(&q, 0, sizeof(struct gfs2_quota)); + pos = qd2offset(qd); + error = gfs2_internal_read(ip, NULL, (char *)&q, &pos, sizeof(q)); + if (error < 0) + return error; + + qlvb = (struct gfs2_quota_lvb *)qd->qd_gl->gl_lvb; + qlvb->qb_magic = cpu_to_be32(GFS2_MAGIC); + qlvb->__pad = 0; + qlvb->qb_limit = q.qu_limit; + qlvb->qb_warn = q.qu_warn; + qlvb->qb_value = q.qu_value; + qd->qd_qb = *qlvb; + + return 0; +} + static int do_glock(struct gfs2_quota_data *qd, int force_refresh, struct gfs2_holder *q_gh) { struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd; struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode); struct gfs2_holder i_gh; - struct gfs2_quota_host q; - char buf[sizeof(struct gfs2_quota)]; int error; - struct gfs2_quota_lvb *qlvb; restart: error = gfs2_glock_nq_init(qd->qd_gl, LM_ST_SHARED, 0, q_gh); @@ -841,11 +865,9 @@ restart: qd->qd_qb = *(struct gfs2_quota_lvb *)qd->qd_gl->gl_lvb; if (force_refresh || qd->qd_qb.qb_magic != cpu_to_be32(GFS2_MAGIC)) { - loff_t pos; gfs2_glock_dq_uninit(q_gh); - error = gfs2_glock_nq_init(qd->qd_gl, - LM_ST_EXCLUSIVE, GL_NOCACHE, - q_gh); + error = gfs2_glock_nq_init(qd->qd_gl, LM_ST_EXCLUSIVE, + GL_NOCACHE, q_gh); if (error) return error; @@ -853,29 +875,14 @@ restart: if (error) goto fail; - memset(buf, 0, sizeof(struct gfs2_quota)); - pos = qd2offset(qd); - error = gfs2_internal_read(ip, NULL, buf, &pos, - sizeof(struct gfs2_quota)); - if (error < 0) + error = update_qd(sdp, qd); + if (error) goto fail_gunlock; gfs2_glock_dq_uninit(&i_gh); - - gfs2_quota_in(&q, buf); - qlvb = (struct gfs2_quota_lvb *)qd->qd_gl->gl_lvb; - qlvb->qb_magic = cpu_to_be32(GFS2_MAGIC); - qlvb->__pad = 0; - qlvb->qb_limit = cpu_to_be64(q.qu_limit); - qlvb->qb_warn = cpu_to_be64(q.qu_warn); - qlvb->qb_value = cpu_to_be64(q.qu_value); - qd->qd_qb = *qlvb; - - if (gfs2_glock_is_blocking(qd->qd_gl)) { - gfs2_glock_dq_uninit(q_gh); - force_refresh = 0; - goto restart; - } + gfs2_glock_dq_uninit(q_gh); + force_refresh = 0; + goto restart; } return 0; @@ -995,7 +1002,7 @@ static int print_message(struct gfs2_quota_data *qd, char *type) { struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd; - printk(KERN_INFO "GFS2: fsid=%s: quota %s for %s %u\r\n", + printk(KERN_INFO "GFS2: fsid=%s: quota %s for %s %u\n", sdp->sd_fsname, type, (test_bit(QDF_USER, &qd->qd_flags)) ? "user" : "group", qd->qd_id); @@ -1032,6 +1039,10 @@ int gfs2_quota_check(struct gfs2_inode *ip, u32 uid, u32 gid) if (be64_to_cpu(qd->qd_qb.qb_limit) && (s64)be64_to_cpu(qd->qd_qb.qb_limit) < value) { print_message(qd, "exceeded"); + quota_send_warning(test_bit(QDF_USER, &qd->qd_flags) ? + USRQUOTA : GRPQUOTA, qd->qd_id, + sdp->sd_vfs->s_dev, QUOTA_NL_BHARDWARN); + error = -EDQUOT; break; } else if (be64_to_cpu(qd->qd_qb.qb_warn) && @@ -1039,6 +1050,9 @@ int gfs2_quota_check(struct gfs2_inode *ip, u32 uid, u32 gid) time_after_eq(jiffies, qd->qd_last_warn + gfs2_tune_get(sdp, gt_quota_warn_period) * HZ)) { + quota_send_warning(test_bit(QDF_USER, &qd->qd_flags) ? + USRQUOTA : GRPQUOTA, qd->qd_id, + sdp->sd_vfs->s_dev, QUOTA_NL_BSOFTWARN); error = print_message(qd, "warning"); qd->qd_last_warn = jiffies; } @@ -1069,8 +1083,9 @@ void gfs2_quota_change(struct gfs2_inode *ip, s64 change, } } -int gfs2_quota_sync(struct gfs2_sbd *sdp) +int gfs2_quota_sync(struct super_block *sb, int type) { + struct gfs2_sbd *sdp = sb->s_fs_info; struct gfs2_quota_data **qda; unsigned int max_qd = gfs2_tune_get(sdp, gt_quota_simul_sync); unsigned int num_qd; @@ -1118,7 +1133,7 @@ int gfs2_quota_refresh(struct gfs2_sbd *sdp, int user, u32 id) struct gfs2_holder q_gh; int error; - error = qd_get(sdp, user, id, CREATE, &qd); + error = qd_get(sdp, user, id, &qd); if (error) return error; @@ -1127,7 +1142,6 @@ int gfs2_quota_refresh(struct gfs2_sbd *sdp, int user, u32 id) gfs2_glock_dq_uninit(&q_gh); qd_put(qd); - return error; } @@ -1298,12 +1312,12 @@ static void quotad_error(struct gfs2_sbd *sdp, const char *msg, int error) } static void quotad_check_timeo(struct gfs2_sbd *sdp, const char *msg, - int (*fxn)(struct gfs2_sbd *sdp), + int (*fxn)(struct super_block *sb, int type), unsigned long t, unsigned long *timeo, unsigned int *new_timeo) { if (t >= *timeo) { - int error = fxn(sdp); + int error = fxn(sdp->sd_vfs, 0); quotad_error(sdp, msg, error); *timeo = gfs2_tune_get_i(&sdp->sd_tune, new_timeo) * HZ; } else { @@ -1330,6 +1344,14 @@ static void quotad_check_trunc_list(struct gfs2_sbd *sdp) } } +void gfs2_wake_up_statfs(struct gfs2_sbd *sdp) { + if (!sdp->sd_statfs_force_sync) { + sdp->sd_statfs_force_sync = 1; + wake_up(&sdp->sd_quota_wait); + } +} + + /** * gfs2_quotad - Write cached quota changes into the quota file * @sdp: Pointer to GFS2 superblock @@ -1349,8 +1371,15 @@ int gfs2_quotad(void *data) while (!kthread_should_stop()) { /* Update the master statfs file */ - quotad_check_timeo(sdp, "statfs", gfs2_statfs_sync, t, - &statfs_timeo, &tune->gt_statfs_quantum); + if (sdp->sd_statfs_force_sync) { + int error = gfs2_statfs_sync(sdp->sd_vfs, 0); + quotad_error(sdp, "statfs", error); + statfs_timeo = gfs2_tune_get(sdp, gt_statfs_quantum) * HZ; + } + else + quotad_check_timeo(sdp, "statfs", gfs2_statfs_sync, t, + &statfs_timeo, + &tune->gt_statfs_quantum); /* Update quota file */ quotad_check_timeo(sdp, "sync", gfs2_quota_sync, t, @@ -1367,7 +1396,7 @@ int gfs2_quotad(void *data) spin_lock(&sdp->sd_trunc_lock); empty = list_empty(&sdp->sd_trunc_list); spin_unlock(&sdp->sd_trunc_lock); - if (empty) + if (empty && !sdp->sd_statfs_force_sync) t -= schedule_timeout(t); else t = 0; @@ -1377,3 +1406,181 @@ int gfs2_quotad(void *data) return 0; } +static int gfs2_quota_get_xstate(struct super_block *sb, + struct fs_quota_stat *fqs) +{ + struct gfs2_sbd *sdp = sb->s_fs_info; + + memset(fqs, 0, sizeof(struct fs_quota_stat)); + fqs->qs_version = FS_QSTAT_VERSION; + if (sdp->sd_args.ar_quota == GFS2_QUOTA_ON) + fqs->qs_flags = (XFS_QUOTA_UDQ_ENFD | XFS_QUOTA_GDQ_ENFD); + else if (sdp->sd_args.ar_quota == GFS2_QUOTA_ACCOUNT) + fqs->qs_flags = (XFS_QUOTA_UDQ_ACCT | XFS_QUOTA_GDQ_ACCT); + if (sdp->sd_quota_inode) { + fqs->qs_uquota.qfs_ino = GFS2_I(sdp->sd_quota_inode)->i_no_addr; + fqs->qs_uquota.qfs_nblks = sdp->sd_quota_inode->i_blocks; + } + fqs->qs_uquota.qfs_nextents = 1; /* unsupported */ + fqs->qs_gquota = fqs->qs_uquota; /* its the same inode in both cases */ + fqs->qs_incoredqs = atomic_read(&qd_lru_count); + return 0; +} + +static int gfs2_xquota_get(struct super_block *sb, int type, qid_t id, + struct fs_disk_quota *fdq) +{ + struct gfs2_sbd *sdp = sb->s_fs_info; + struct gfs2_quota_lvb *qlvb; + struct gfs2_quota_data *qd; + struct gfs2_holder q_gh; + int error; + + memset(fdq, 0, sizeof(struct fs_disk_quota)); + + if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF) + return -ESRCH; /* Crazy XFS error code */ + + if (type == USRQUOTA) + type = QUOTA_USER; + else if (type == GRPQUOTA) + type = QUOTA_GROUP; + else + return -EINVAL; + + error = qd_get(sdp, type, id, &qd); + if (error) + return error; + error = do_glock(qd, FORCE, &q_gh); + if (error) + goto out; + + qlvb = (struct gfs2_quota_lvb *)qd->qd_gl->gl_lvb; + fdq->d_version = FS_DQUOT_VERSION; + fdq->d_flags = (type == QUOTA_USER) ? XFS_USER_QUOTA : XFS_GROUP_QUOTA; + fdq->d_id = id; + fdq->d_blk_hardlimit = be64_to_cpu(qlvb->qb_limit); + fdq->d_blk_softlimit = be64_to_cpu(qlvb->qb_warn); + fdq->d_bcount = be64_to_cpu(qlvb->qb_value); + + gfs2_glock_dq_uninit(&q_gh); +out: + qd_put(qd); + return error; +} + +/* GFS2 only supports a subset of the XFS fields */ +#define GFS2_FIELDMASK (FS_DQ_BSOFT|FS_DQ_BHARD) + +static int gfs2_xquota_set(struct super_block *sb, int type, qid_t id, + struct fs_disk_quota *fdq) +{ + struct gfs2_sbd *sdp = sb->s_fs_info; + struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode); + struct gfs2_quota_data *qd; + struct gfs2_holder q_gh, i_gh; + unsigned int data_blocks, ind_blocks; + unsigned int blocks = 0; + int alloc_required; + struct gfs2_alloc *al; + loff_t offset; + int error; + + if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF) + return -ESRCH; /* Crazy XFS error code */ + + switch(type) { + case USRQUOTA: + type = QUOTA_USER; + if (fdq->d_flags != XFS_USER_QUOTA) + return -EINVAL; + break; + case GRPQUOTA: + type = QUOTA_GROUP; + if (fdq->d_flags != XFS_GROUP_QUOTA) + return -EINVAL; + break; + default: + return -EINVAL; + } + + if (fdq->d_fieldmask & ~GFS2_FIELDMASK) + return -EINVAL; + if (fdq->d_id != id) + return -EINVAL; + + error = qd_get(sdp, type, id, &qd); + if (error) + return error; + + mutex_lock(&ip->i_inode.i_mutex); + error = gfs2_glock_nq_init(qd->qd_gl, LM_ST_EXCLUSIVE, 0, &q_gh); + if (error) + goto out_put; + error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &i_gh); + if (error) + goto out_q; + + /* Check for existing entry, if none then alloc new blocks */ + error = update_qd(sdp, qd); + if (error) + goto out_i; + + /* If nothing has changed, this is a no-op */ + if ((fdq->d_fieldmask & FS_DQ_BSOFT) && + (fdq->d_blk_softlimit == be64_to_cpu(qd->qd_qb.qb_warn))) + fdq->d_fieldmask ^= FS_DQ_BSOFT; + if ((fdq->d_fieldmask & FS_DQ_BHARD) && + (fdq->d_blk_hardlimit == be64_to_cpu(qd->qd_qb.qb_limit))) + fdq->d_fieldmask ^= FS_DQ_BHARD; + if (fdq->d_fieldmask == 0) + goto out_i; + + offset = qd2offset(qd); + error = gfs2_write_alloc_required(ip, offset, sizeof(struct gfs2_quota), + &alloc_required); + if (error) + goto out_i; + if (alloc_required) { + al = gfs2_alloc_get(ip); + if (al == NULL) + goto out_i; + gfs2_write_calc_reserv(ip, sizeof(struct gfs2_quota), + &data_blocks, &ind_blocks); + blocks = al->al_requested = 1 + data_blocks + ind_blocks; + error = gfs2_inplace_reserve(ip); + if (error) + goto out_alloc; + } + + error = gfs2_trans_begin(sdp, blocks + RES_DINODE + 1, 0); + if (error) + goto out_release; + + /* Apply changes */ + error = gfs2_adjust_quota(ip, offset, 0, qd, fdq); + + gfs2_trans_end(sdp); +out_release: + if (alloc_required) { + gfs2_inplace_release(ip); +out_alloc: + gfs2_alloc_put(ip); + } +out_i: + gfs2_glock_dq_uninit(&i_gh); +out_q: + gfs2_glock_dq_uninit(&q_gh); +out_put: + mutex_unlock(&ip->i_inode.i_mutex); + qd_put(qd); + return error; +} + +const struct quotactl_ops gfs2_quotactl_ops = { + .quota_sync = gfs2_quota_sync, + .get_xstate = gfs2_quota_get_xstate, + .get_xquota = gfs2_xquota_get, + .set_xquota = gfs2_xquota_set, +}; + diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h index 0fa5fa63d0e8..e271fa07ad02 100644 --- a/fs/gfs2/quota.h +++ b/fs/gfs2/quota.h @@ -25,13 +25,15 @@ extern int gfs2_quota_check(struct gfs2_inode *ip, u32 uid, u32 gid); extern void gfs2_quota_change(struct gfs2_inode *ip, s64 change, u32 uid, u32 gid); -extern int gfs2_quota_sync(struct gfs2_sbd *sdp); +extern int gfs2_quota_sync(struct super_block *sb, int type); extern int gfs2_quota_refresh(struct gfs2_sbd *sdp, int user, u32 id); extern int gfs2_quota_init(struct gfs2_sbd *sdp); extern void gfs2_quota_cleanup(struct gfs2_sbd *sdp); extern int gfs2_quotad(void *data); +extern void gfs2_wake_up_statfs(struct gfs2_sbd *sdp); + static inline int gfs2_quota_lock_check(struct gfs2_inode *ip) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); @@ -50,5 +52,6 @@ static inline int gfs2_quota_lock_check(struct gfs2_inode *ip) } extern int gfs2_shrink_qd_memory(int nr, gfp_t gfp_mask); +extern const struct quotactl_ops gfs2_quotactl_ops; #endif /* __QUOTA_DOT_H__ */ diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c index 59d2695509d3..4b9bece3d437 100644 --- a/fs/gfs2/recovery.c +++ b/fs/gfs2/recovery.c @@ -7,6 +7,7 @@ * of the GNU General Public License version 2. */ +#include <linux/module.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/completion.h> @@ -409,7 +410,9 @@ static int clean_journal(struct gfs2_jdesc *jd, struct gfs2_log_header_host *hea memset(lh, 0, sizeof(struct gfs2_log_header)); lh->lh_header.mh_magic = cpu_to_be32(GFS2_MAGIC); lh->lh_header.mh_type = cpu_to_be32(GFS2_METATYPE_LH); + lh->lh_header.__pad0 = cpu_to_be64(0); lh->lh_header.mh_format = cpu_to_be32(GFS2_FORMAT_LH); + lh->lh_header.mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid); lh->lh_sequence = cpu_to_be64(head->lh_sequence + 1); lh->lh_flags = cpu_to_be32(GFS2_LOG_HEAD_UNMOUNT); lh->lh_blkno = cpu_to_be32(lblock); @@ -593,6 +596,7 @@ fail: } struct slow_work_ops gfs2_recover_ops = { + .owner = THIS_MODULE, .get_ref = gfs2_recover_get_ref, .put_ref = gfs2_recover_put_ref, .execute = gfs2_recover_work, diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 8f1cfb02a6cb..0608f490c295 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -1710,11 +1710,16 @@ int gfs2_check_blk_type(struct gfs2_sbd *sdp, u64 no_addr, unsigned int type) { struct gfs2_rgrpd *rgd; struct gfs2_holder ri_gh, rgd_gh; + struct gfs2_inode *ip = GFS2_I(sdp->sd_rindex); + int ri_locked = 0; int error; - error = gfs2_rindex_hold(sdp, &ri_gh); - if (error) - goto fail; + if (!gfs2_glock_is_locked_by_me(ip->i_gl)) { + error = gfs2_rindex_hold(sdp, &ri_gh); + if (error) + goto fail; + ri_locked = 1; + } error = -EINVAL; rgd = gfs2_blk2rgrpd(sdp, no_addr); @@ -1730,7 +1735,8 @@ int gfs2_check_blk_type(struct gfs2_sbd *sdp, u64 no_addr, unsigned int type) gfs2_glock_dq_uninit(&rgd_gh); fail_rindex: - gfs2_glock_dq_uninit(&ri_gh); + if (ri_locked) + gfs2_glock_dq_uninit(&ri_gh); fail: return error; } diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 0ec3ec672de1..c282ad41f3d1 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -70,6 +70,11 @@ enum { Opt_commit, Opt_err_withdraw, Opt_err_panic, + Opt_statfs_quantum, + Opt_statfs_percent, + Opt_quota_quantum, + Opt_barrier, + Opt_nobarrier, Opt_error, }; @@ -101,18 +106,23 @@ static const match_table_t tokens = { {Opt_commit, "commit=%d"}, {Opt_err_withdraw, "errors=withdraw"}, {Opt_err_panic, "errors=panic"}, + {Opt_statfs_quantum, "statfs_quantum=%d"}, + {Opt_statfs_percent, "statfs_percent=%d"}, + {Opt_quota_quantum, "quota_quantum=%d"}, + {Opt_barrier, "barrier"}, + {Opt_nobarrier, "nobarrier"}, {Opt_error, NULL} }; /** * gfs2_mount_args - Parse mount options - * @sdp: - * @data: + * @args: The structure into which the parsed options will be written + * @options: The options to parse * * Return: errno */ -int gfs2_mount_args(struct gfs2_sbd *sdp, struct gfs2_args *args, char *options) +int gfs2_mount_args(struct gfs2_args *args, char *options) { char *o; int token; @@ -157,7 +167,7 @@ int gfs2_mount_args(struct gfs2_sbd *sdp, struct gfs2_args *args, char *options) break; case Opt_debug: if (args->ar_errors == GFS2_ERRORS_PANIC) { - fs_info(sdp, "-o debug and -o errors=panic " + printk(KERN_WARNING "GFS2: -o debug and -o errors=panic " "are mutually exclusive.\n"); return -EINVAL; } @@ -210,7 +220,29 @@ int gfs2_mount_args(struct gfs2_sbd *sdp, struct gfs2_args *args, char *options) case Opt_commit: rv = match_int(&tmp[0], &args->ar_commit); if (rv || args->ar_commit <= 0) { - fs_info(sdp, "commit mount option requires a positive numeric argument\n"); + printk(KERN_WARNING "GFS2: commit mount option requires a positive numeric argument\n"); + return rv ? rv : -EINVAL; + } + break; + case Opt_statfs_quantum: + rv = match_int(&tmp[0], &args->ar_statfs_quantum); + if (rv || args->ar_statfs_quantum < 0) { + printk(KERN_WARNING "GFS2: statfs_quantum mount option requires a non-negative numeric argument\n"); + return rv ? rv : -EINVAL; + } + break; + case Opt_quota_quantum: + rv = match_int(&tmp[0], &args->ar_quota_quantum); + if (rv || args->ar_quota_quantum <= 0) { + printk(KERN_WARNING "GFS2: quota_quantum mount option requires a positive numeric argument\n"); + return rv ? rv : -EINVAL; + } + break; + case Opt_statfs_percent: + rv = match_int(&tmp[0], &args->ar_statfs_percent); + if (rv || args->ar_statfs_percent < 0 || + args->ar_statfs_percent > 100) { + printk(KERN_WARNING "statfs_percent mount option requires a numeric argument between 0 and 100\n"); return rv ? rv : -EINVAL; } break; @@ -219,15 +251,21 @@ int gfs2_mount_args(struct gfs2_sbd *sdp, struct gfs2_args *args, char *options) break; case Opt_err_panic: if (args->ar_debug) { - fs_info(sdp, "-o debug and -o errors=panic " + printk(KERN_WARNING "GFS2: -o debug and -o errors=panic " "are mutually exclusive.\n"); return -EINVAL; } args->ar_errors = GFS2_ERRORS_PANIC; break; + case Opt_barrier: + args->ar_nobarrier = 0; + break; + case Opt_nobarrier: + args->ar_nobarrier = 1; + break; case Opt_error: default: - fs_info(sdp, "invalid mount option: %s\n", o); + printk(KERN_WARNING "GFS2: invalid mount option: %s\n", o); return -EINVAL; } } @@ -442,7 +480,10 @@ void gfs2_statfs_change(struct gfs2_sbd *sdp, s64 total, s64 free, { struct gfs2_inode *l_ip = GFS2_I(sdp->sd_sc_inode); struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local; + struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master; struct buffer_head *l_bh; + s64 x, y; + int need_sync = 0; int error; error = gfs2_meta_inode_buffer(l_ip, &l_bh); @@ -456,9 +497,17 @@ void gfs2_statfs_change(struct gfs2_sbd *sdp, s64 total, s64 free, l_sc->sc_free += free; l_sc->sc_dinodes += dinodes; gfs2_statfs_change_out(l_sc, l_bh->b_data + sizeof(struct gfs2_dinode)); + if (sdp->sd_args.ar_statfs_percent) { + x = 100 * l_sc->sc_free; + y = m_sc->sc_free * sdp->sd_args.ar_statfs_percent; + if (x >= y || x <= -y) + need_sync = 1; + } spin_unlock(&sdp->sd_statfs_spin); brelse(l_bh); + if (need_sync) + gfs2_wake_up_statfs(sdp); } void update_statfs(struct gfs2_sbd *sdp, struct buffer_head *m_bh, @@ -484,8 +533,9 @@ void update_statfs(struct gfs2_sbd *sdp, struct buffer_head *m_bh, gfs2_statfs_change_out(m_sc, m_bh->b_data + sizeof(struct gfs2_dinode)); } -int gfs2_statfs_sync(struct gfs2_sbd *sdp) +int gfs2_statfs_sync(struct super_block *sb, int type) { + struct gfs2_sbd *sdp = sb->s_fs_info; struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode); struct gfs2_inode *l_ip = GFS2_I(sdp->sd_sc_inode); struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master; @@ -521,6 +571,7 @@ int gfs2_statfs_sync(struct gfs2_sbd *sdp) goto out_bh2; update_statfs(sdp, m_bh, l_bh); + sdp->sd_statfs_force_sync = 0; gfs2_trans_end(sdp); @@ -712,8 +763,8 @@ static int gfs2_make_fs_ro(struct gfs2_sbd *sdp) int error; flush_workqueue(gfs2_delete_workqueue); - gfs2_quota_sync(sdp); - gfs2_statfs_sync(sdp); + gfs2_quota_sync(sdp->sd_vfs, 0); + gfs2_statfs_sync(sdp->sd_vfs, 0); error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED, GL_NOCACHE, &t_gh); @@ -1061,8 +1112,13 @@ static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data) spin_lock(>->gt_spin); args.ar_commit = gt->gt_log_flush_secs; + args.ar_quota_quantum = gt->gt_quota_quantum; + if (gt->gt_statfs_slow) + args.ar_statfs_quantum = 0; + else + args.ar_statfs_quantum = gt->gt_statfs_quantum; spin_unlock(>->gt_spin); - error = gfs2_mount_args(sdp, &args, data); + error = gfs2_mount_args(&args, data); if (error) return error; @@ -1097,8 +1153,21 @@ static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data) sb->s_flags |= MS_POSIXACL; else sb->s_flags &= ~MS_POSIXACL; + if (sdp->sd_args.ar_nobarrier) + set_bit(SDF_NOBARRIERS, &sdp->sd_flags); + else + clear_bit(SDF_NOBARRIERS, &sdp->sd_flags); spin_lock(>->gt_spin); gt->gt_log_flush_secs = args.ar_commit; + gt->gt_quota_quantum = args.ar_quota_quantum; + if (args.ar_statfs_quantum) { + gt->gt_statfs_slow = 0; + gt->gt_statfs_quantum = args.ar_statfs_quantum; + } + else { + gt->gt_statfs_slow = 1; + gt->gt_statfs_quantum = 30; + } spin_unlock(>->gt_spin); gfs2_online_uevent(sdp); @@ -1179,7 +1248,7 @@ static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt) { struct gfs2_sbd *sdp = mnt->mnt_sb->s_fs_info; struct gfs2_args *args = &sdp->sd_args; - int lfsecs; + int val; if (is_ancestor(mnt->mnt_root, sdp->sd_master_dir)) seq_printf(s, ",meta"); @@ -1240,9 +1309,17 @@ static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt) } if (args->ar_discard) seq_printf(s, ",discard"); - lfsecs = sdp->sd_tune.gt_log_flush_secs; - if (lfsecs != 60) - seq_printf(s, ",commit=%d", lfsecs); + val = sdp->sd_tune.gt_log_flush_secs; + if (val != 60) + seq_printf(s, ",commit=%d", val); + val = sdp->sd_tune.gt_statfs_quantum; + if (val != 30) + seq_printf(s, ",statfs_quantum=%d", val); + val = sdp->sd_tune.gt_quota_quantum; + if (val != 60) + seq_printf(s, ",quota_quantum=%d", val); + if (args->ar_statfs_percent) + seq_printf(s, ",statfs_percent=%d", args->ar_statfs_percent); if (args->ar_errors != GFS2_ERRORS_DEFAULT) { const char *state; @@ -1259,6 +1336,9 @@ static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt) } seq_printf(s, ",errors=%s", state); } + if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags)) + seq_printf(s, ",nobarrier"); + return 0; } diff --git a/fs/gfs2/super.h b/fs/gfs2/super.h index 235db3682885..3df60f2d84e3 100644 --- a/fs/gfs2/super.h +++ b/fs/gfs2/super.h @@ -27,7 +27,7 @@ static inline unsigned int gfs2_jindex_size(struct gfs2_sbd *sdp) extern void gfs2_jindex_free(struct gfs2_sbd *sdp); -extern int gfs2_mount_args(struct gfs2_sbd *sdp, struct gfs2_args *args, char *data); +extern int gfs2_mount_args(struct gfs2_args *args, char *data); extern struct gfs2_jdesc *gfs2_jdesc_find(struct gfs2_sbd *sdp, unsigned int jid); extern int gfs2_jdesc_check(struct gfs2_jdesc *jd); @@ -44,7 +44,7 @@ extern void gfs2_statfs_change_in(struct gfs2_statfs_change_host *sc, const void *buf); extern void update_statfs(struct gfs2_sbd *sdp, struct buffer_head *m_bh, struct buffer_head *l_bh); -extern int gfs2_statfs_sync(struct gfs2_sbd *sdp); +extern int gfs2_statfs_sync(struct super_block *sb, int type); extern int gfs2_freeze_fs(struct gfs2_sbd *sdp); extern void gfs2_unfreeze_fs(struct gfs2_sbd *sdp); diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index 446329728d52..c5dad1eb7b91 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -158,7 +158,7 @@ static ssize_t statfs_sync_store(struct gfs2_sbd *sdp, const char *buf, if (simple_strtol(buf, NULL, 0) != 1) return -EINVAL; - gfs2_statfs_sync(sdp); + gfs2_statfs_sync(sdp->sd_vfs, 0); return len; } @@ -171,13 +171,14 @@ static ssize_t quota_sync_store(struct gfs2_sbd *sdp, const char *buf, if (simple_strtol(buf, NULL, 0) != 1) return -EINVAL; - gfs2_quota_sync(sdp); + gfs2_quota_sync(sdp->sd_vfs, 0); return len; } static ssize_t quota_refresh_user_store(struct gfs2_sbd *sdp, const char *buf, size_t len) { + int error; u32 id; if (!capable(CAP_SYS_ADMIN)) @@ -185,13 +186,14 @@ static ssize_t quota_refresh_user_store(struct gfs2_sbd *sdp, const char *buf, id = simple_strtoul(buf, NULL, 0); - gfs2_quota_refresh(sdp, 1, id); - return len; + error = gfs2_quota_refresh(sdp, 1, id); + return error ? error : len; } static ssize_t quota_refresh_group_store(struct gfs2_sbd *sdp, const char *buf, size_t len) { + int error; u32 id; if (!capable(CAP_SYS_ADMIN)) @@ -199,8 +201,8 @@ static ssize_t quota_refresh_group_store(struct gfs2_sbd *sdp, const char *buf, id = simple_strtoul(buf, NULL, 0); - gfs2_quota_refresh(sdp, 0, id); - return len; + error = gfs2_quota_refresh(sdp, 0, id); + return error ? error : len; } static ssize_t demote_rq_store(struct gfs2_sbd *sdp, const char *buf, size_t len) diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c index 8a0f8ef6ee27..912f5cbc4740 100644 --- a/fs/gfs2/xattr.c +++ b/fs/gfs2/xattr.c @@ -186,8 +186,8 @@ static int ea_find_i(struct gfs2_inode *ip, struct buffer_head *bh, return 0; } -int gfs2_ea_find(struct gfs2_inode *ip, int type, const char *name, - struct gfs2_ea_location *el) +static int gfs2_ea_find(struct gfs2_inode *ip, int type, const char *name, + struct gfs2_ea_location *el) { struct ea_find ef; int error; @@ -516,8 +516,8 @@ out: return error; } -int gfs2_ea_get_copy(struct gfs2_inode *ip, struct gfs2_ea_location *el, - char *data, size_t size) +static int gfs2_ea_get_copy(struct gfs2_inode *ip, struct gfs2_ea_location *el, + char *data, size_t size) { int ret; size_t len = GFS2_EA_DATA_LEN(el->el_ea); @@ -534,6 +534,36 @@ int gfs2_ea_get_copy(struct gfs2_inode *ip, struct gfs2_ea_location *el, return len; } +int gfs2_xattr_acl_get(struct gfs2_inode *ip, const char *name, char **ppdata) +{ + struct gfs2_ea_location el; + int error; + int len; + char *data; + + error = gfs2_ea_find(ip, GFS2_EATYPE_SYS, name, &el); + if (error) + return error; + if (!el.el_ea) + goto out; + if (!GFS2_EA_DATA_LEN(el.el_ea)) + goto out; + + len = GFS2_EA_DATA_LEN(el.el_ea); + data = kmalloc(len, GFP_NOFS); + error = -ENOMEM; + if (data == NULL) + goto out; + + error = gfs2_ea_get_copy(ip, &el, data, len); + if (error == 0) + error = len; + *ppdata = data; +out: + brelse(el.el_bh); + return error; +} + /** * gfs2_xattr_get - Get a GFS2 extended attribute * @inode: The inode @@ -1259,22 +1289,26 @@ fail: return error; } -int gfs2_ea_acl_chmod(struct gfs2_inode *ip, struct gfs2_ea_location *el, - struct iattr *attr, char *data) +int gfs2_xattr_acl_chmod(struct gfs2_inode *ip, struct iattr *attr, char *data) { + struct gfs2_ea_location el; struct buffer_head *dibh; int error; - if (GFS2_EA_IS_STUFFED(el->el_ea)) { + error = gfs2_ea_find(ip, GFS2_EATYPE_SYS, GFS2_POSIX_ACL_ACCESS, &el); + if (error) + return error; + + if (GFS2_EA_IS_STUFFED(el.el_ea)) { error = gfs2_trans_begin(GFS2_SB(&ip->i_inode), RES_DINODE + RES_EATTR, 0); if (error) return error; - gfs2_trans_add_bh(ip->i_gl, el->el_bh, 1); - memcpy(GFS2_EA2DATA(el->el_ea), data, - GFS2_EA_DATA_LEN(el->el_ea)); + gfs2_trans_add_bh(ip->i_gl, el.el_bh, 1); + memcpy(GFS2_EA2DATA(el.el_ea), data, + GFS2_EA_DATA_LEN(el.el_ea)); } else - error = ea_acl_chmod_unstuffed(ip, el->el_ea, data); + error = ea_acl_chmod_unstuffed(ip, el.el_ea, data); if (error) return error; @@ -1507,18 +1541,6 @@ static int gfs2_xattr_user_set(struct inode *inode, const char *name, return gfs2_xattr_set(inode, GFS2_EATYPE_USR, name, value, size, flags); } -static int gfs2_xattr_system_get(struct inode *inode, const char *name, - void *buffer, size_t size) -{ - return gfs2_xattr_get(inode, GFS2_EATYPE_SYS, name, buffer, size); -} - -static int gfs2_xattr_system_set(struct inode *inode, const char *name, - const void *value, size_t size, int flags) -{ - return gfs2_xattr_set(inode, GFS2_EATYPE_SYS, name, value, size, flags); -} - static int gfs2_xattr_security_get(struct inode *inode, const char *name, void *buffer, size_t size) { @@ -1543,12 +1565,6 @@ static struct xattr_handler gfs2_xattr_security_handler = { .set = gfs2_xattr_security_set, }; -static struct xattr_handler gfs2_xattr_system_handler = { - .prefix = XATTR_SYSTEM_PREFIX, - .get = gfs2_xattr_system_get, - .set = gfs2_xattr_system_set, -}; - struct xattr_handler *gfs2_xattr_handlers[] = { &gfs2_xattr_user_handler, &gfs2_xattr_security_handler, diff --git a/fs/gfs2/xattr.h b/fs/gfs2/xattr.h index cbdfd7743733..8d6ae5813c4d 100644 --- a/fs/gfs2/xattr.h +++ b/fs/gfs2/xattr.h @@ -62,11 +62,7 @@ extern int gfs2_ea_dealloc(struct gfs2_inode *ip); /* Exported to acl.c */ -extern int gfs2_ea_find(struct gfs2_inode *ip, int type, const char *name, - struct gfs2_ea_location *el); -extern int gfs2_ea_get_copy(struct gfs2_inode *ip, struct gfs2_ea_location *el, - char *data, size_t size); -extern int gfs2_ea_acl_chmod(struct gfs2_inode *ip, struct gfs2_ea_location *el, - struct iattr *attr, char *data); +extern int gfs2_xattr_acl_get(struct gfs2_inode *ip, const char *name, char **data); +extern int gfs2_xattr_acl_chmod(struct gfs2_inode *ip, struct iattr *attr, char *data); #endif /* __EATTR_DOT_H__ */ diff --git a/fs/inode.c b/fs/inode.c index 4d8e3be55976..06c1f02de611 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -18,7 +18,6 @@ #include <linux/hash.h> #include <linux/swap.h> #include <linux/security.h> -#include <linux/ima.h> #include <linux/pagemap.h> #include <linux/cdev.h> #include <linux/bootmem.h> @@ -157,11 +156,6 @@ int inode_init_always(struct super_block *sb, struct inode *inode) if (security_inode_alloc(inode)) goto out; - - /* allocate and initialize an i_integrity */ - if (ima_inode_alloc(inode)) - goto out_free_security; - spin_lock_init(&inode->i_lock); lockdep_set_class(&inode->i_lock, &sb->s_type->i_lock_key); @@ -201,9 +195,6 @@ int inode_init_always(struct super_block *sb, struct inode *inode) #endif return 0; - -out_free_security: - security_inode_free(inode); out: return -ENOMEM; } @@ -235,7 +226,6 @@ static struct inode *alloc_inode(struct super_block *sb) void __destroy_inode(struct inode *inode) { BUG_ON(inode_has_buffers(inode)); - ima_inode_free(inode); security_inode_free(inode); fsnotify_inode_delete(inode); #ifdef CONFIG_FS_POSIX_ACL diff --git a/fs/jffs2/read.c b/fs/jffs2/read.c index cfe05c1966a5..3f39be1b0455 100644 --- a/fs/jffs2/read.c +++ b/fs/jffs2/read.c @@ -164,12 +164,15 @@ int jffs2_read_inode_range(struct jffs2_sb_info *c, struct jffs2_inode_info *f, /* XXX FIXME: Where a single physical node actually shows up in two frags, we read it twice. Don't do that. */ - /* Now we're pointing at the first frag which overlaps our page */ + /* Now we're pointing at the first frag which overlaps our page + * (or perhaps is before it, if we've been asked to read off the + * end of the file). */ while(offset < end) { D2(printk(KERN_DEBUG "jffs2_read_inode_range: offset %d, end %d\n", offset, end)); - if (unlikely(!frag || frag->ofs > offset)) { + if (unlikely(!frag || frag->ofs > offset || + frag->ofs + frag->size <= offset)) { uint32_t holesize = end - offset; - if (frag) { + if (frag && frag->ofs > offset) { D1(printk(KERN_NOTICE "Eep. Hole in ino #%u fraglist. frag->ofs = 0x%08x, offset = 0x%08x\n", f->inocache->ino, frag->ofs, offset)); holesize = min(holesize, frag->ofs - offset); } diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 1a54ae14a192..e50cfa3d9654 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -371,82 +371,74 @@ EXPORT_SYMBOL_GPL(lockd_down); static ctl_table nlm_sysctls[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "nlm_grace_period", .data = &nlm_grace_period, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &proc_doulongvec_minmax, + .proc_handler = proc_doulongvec_minmax, .extra1 = (unsigned long *) &nlm_grace_period_min, .extra2 = (unsigned long *) &nlm_grace_period_max, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "nlm_timeout", .data = &nlm_timeout, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &proc_doulongvec_minmax, + .proc_handler = proc_doulongvec_minmax, .extra1 = (unsigned long *) &nlm_timeout_min, .extra2 = (unsigned long *) &nlm_timeout_max, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "nlm_udpport", .data = &nlm_udpport, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, + .proc_handler = proc_dointvec_minmax, .extra1 = (int *) &nlm_port_min, .extra2 = (int *) &nlm_port_max, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "nlm_tcpport", .data = &nlm_tcpport, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, + .proc_handler = proc_dointvec_minmax, .extra1 = (int *) &nlm_port_min, .extra2 = (int *) &nlm_port_max, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "nsm_use_hostnames", .data = &nsm_use_hostnames, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "nsm_local_state", .data = &nsm_local_state, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, - { .ctl_name = 0 } + { } }; static ctl_table nlm_sysctl_dir[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "nfs", .mode = 0555, .child = nlm_sysctls, }, - { .ctl_name = 0 } + { } }; static ctl_table nlm_sysctl_root[] = { { - .ctl_name = CTL_FS, .procname = "fs", .mode = 0555, .child = nlm_sysctl_dir, }, - { .ctl_name = 0 } + { } }; #endif /* CONFIG_SYSCTL */ diff --git a/fs/namespace.c b/fs/namespace.c index bdc3cb4fd222..7d70d63ceb29 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1921,6 +1921,16 @@ long do_mount(char *dev_name, char *dir_name, char *type_page, if (data_page) ((char *)data_page)[PAGE_SIZE - 1] = 0; + /* ... and get the mountpoint */ + retval = kern_path(dir_name, LOOKUP_FOLLOW, &path); + if (retval) + return retval; + + retval = security_sb_mount(dev_name, &path, + type_page, flags, data_page); + if (retval) + goto dput_out; + /* Default to relatime unless overriden */ if (!(flags & MS_NOATIME)) mnt_flags |= MNT_RELATIME; @@ -1945,16 +1955,6 @@ long do_mount(char *dev_name, char *dir_name, char *type_page, MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT | MS_STRICTATIME); - /* ... and get the mountpoint */ - retval = kern_path(dir_name, LOOKUP_FOLLOW, &path); - if (retval) - return retval; - - retval = security_sb_mount(dev_name, &path, - type_page, flags, data_page); - if (retval) - goto dput_out; - if (flags & MS_REMOUNT) retval = do_remount(&path, flags & ~MS_REMOUNT, mnt_flags, data_page); diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index 70fad69eb959..fa588006588d 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -359,17 +359,13 @@ int nfs_fscache_release_page(struct page *page, gfp_t gfp) BUG_ON(!cookie); - if (fscache_check_page_write(cookie, page)) { - if (!(gfp & __GFP_WAIT)) - return 0; - fscache_wait_on_page_write(cookie, page); - } - if (PageFsCache(page)) { dfprintk(FSCACHE, "NFS: fscache releasepage (0x%p/0x%p/0x%p)\n", cookie, page, nfsi); - fscache_uncache_page(cookie, page); + if (!fscache_maybe_release_page(cookie, page, gfp)) + return 0; + nfs_add_fscache_stats(page->mapping->host, NFSIOS_FSCACHE_PAGES_UNCACHED, 1); } diff --git a/fs/nfs/sysctl.c b/fs/nfs/sysctl.c index b62481dabae9..70e1fbbaaeab 100644 --- a/fs/nfs/sysctl.c +++ b/fs/nfs/sysctl.c @@ -22,63 +22,55 @@ static struct ctl_table_header *nfs_callback_sysctl_table; static ctl_table nfs_cb_sysctls[] = { #ifdef CONFIG_NFS_V4 { - .ctl_name = CTL_UNNUMBERED, .procname = "nfs_callback_tcpport", .data = &nfs_callback_set_tcpport, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, + .proc_handler = proc_dointvec_minmax, .extra1 = (int *)&nfs_set_port_min, .extra2 = (int *)&nfs_set_port_max, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "idmap_cache_timeout", .data = &nfs_idmap_cache_timeout, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, }, #endif { - .ctl_name = CTL_UNNUMBERED, .procname = "nfs_mountpoint_timeout", .data = &nfs_mountpoint_expiry_timeout, .maxlen = sizeof(nfs_mountpoint_expiry_timeout), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "nfs_congestion_kb", .data = &nfs_congestion_kb, .maxlen = sizeof(nfs_congestion_kb), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, - { .ctl_name = 0 } + { } }; static ctl_table nfs_cb_sysctl_dir[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "nfs", .mode = 0555, .child = nfs_cb_sysctls, }, - { .ctl_name = 0 } + { } }; static ctl_table nfs_cb_sysctl_root[] = { { - .ctl_name = CTL_FS, .procname = "fs", .mode = 0555, .child = nfs_cb_sysctl_dir, }, - { .ctl_name = 0 } + { } }; int nfs_register_sysctl(void) diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index dcd2040d330c..1d1d1a2765dd 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -69,36 +69,30 @@ static int zero; ctl_table inotify_table[] = { { - .ctl_name = INOTIFY_MAX_USER_INSTANCES, .procname = "max_user_instances", .data = &inotify_max_user_instances, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero, }, { - .ctl_name = INOTIFY_MAX_USER_WATCHES, .procname = "max_user_watches", .data = &inotify_max_user_watches, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero, }, { - .ctl_name = INOTIFY_MAX_QUEUED_EVENTS, .procname = "max_queued_events", .data = &inotify_max_queued_events, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero }, - { .ctl_name = 0 } + { } }; #endif /* CONFIG_SYSCTL */ diff --git a/fs/ntfs/sysctl.c b/fs/ntfs/sysctl.c index 9ef85e628fe1..79a89184cb5e 100644 --- a/fs/ntfs/sysctl.c +++ b/fs/ntfs/sysctl.c @@ -36,12 +36,11 @@ /* Definition of the ntfs sysctl. */ static ctl_table ntfs_sysctls[] = { { - .ctl_name = CTL_UNNUMBERED, /* Binary and text IDs. */ .procname = "ntfs-debug", .data = &debug_msgs, /* Data pointer and size. */ .maxlen = sizeof(debug_msgs), .mode = 0644, /* Mode, proc handler. */ - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, {} }; @@ -49,7 +48,6 @@ static ctl_table ntfs_sysctls[] = { /* Define the parent directory /proc/sys/fs. */ static ctl_table sysctls_root[] = { { - .ctl_name = CTL_FS, .procname = "fs", .mode = 0555, .child = ntfs_sysctls diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 89fc8ee1f5a5..de059f490586 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1712,7 +1712,8 @@ int ocfs2_check_range_for_refcount(struct inode *inode, loff_t pos, struct super_block *sb = inode->i_sb; if (!ocfs2_refcount_tree(OCFS2_SB(inode->i_sb)) || - !(OCFS2_I(inode)->ip_dyn_features & OCFS2_HAS_REFCOUNT_FL)) + !(OCFS2_I(inode)->ip_dyn_features & OCFS2_HAS_REFCOUNT_FL) || + OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) return 0; cpos = pos >> OCFS2_SB(sb)->s_clustersize_bits; diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index eae404602424..d963d8638709 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -35,12 +35,7 @@ #include <linux/kref.h> #include <linux/mutex.h> #include <linux/lockdep.h> -#ifndef CONFIG_OCFS2_COMPAT_JBD -# include <linux/jbd2.h> -#else -# include <linux/jbd.h> -# include "ocfs2_jbd_compat.h" -#endif +#include <linux/jbd2.h> /* For union ocfs2_dlm_lksb */ #include "stackglue.h" diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 60287fc56bcb..3a0df7a1b810 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -3743,6 +3743,9 @@ static int ocfs2_attach_refcount_tree(struct inode *inode, goto out; } + if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) + goto attach_xattr; + ocfs2_init_dinode_extent_tree(&di_et, INODE_CACHE(inode), di_bh); size = i_size_read(inode); @@ -3769,6 +3772,7 @@ static int ocfs2_attach_refcount_tree(struct inode *inode, cpos += num_clusters; } +attach_xattr: if (oi->ip_dyn_features & OCFS2_HAS_XATTR_FL) { ret = ocfs2_xattr_attach_refcount_tree(inode, di_bh, &ref_tree->rf_ci, @@ -3858,6 +3862,49 @@ out: return ret; } +static int ocfs2_duplicate_inline_data(struct inode *s_inode, + struct buffer_head *s_bh, + struct inode *t_inode, + struct buffer_head *t_bh) +{ + int ret; + handle_t *handle; + struct ocfs2_super *osb = OCFS2_SB(s_inode->i_sb); + struct ocfs2_dinode *s_di = (struct ocfs2_dinode *)s_bh->b_data; + struct ocfs2_dinode *t_di = (struct ocfs2_dinode *)t_bh->b_data; + + BUG_ON(!(OCFS2_I(s_inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)); + + handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + mlog_errno(ret); + goto out; + } + + ret = ocfs2_journal_access_di(handle, INODE_CACHE(t_inode), t_bh, + OCFS2_JOURNAL_ACCESS_WRITE); + if (ret) { + mlog_errno(ret); + goto out_commit; + } + + t_di->id2.i_data.id_count = s_di->id2.i_data.id_count; + memcpy(t_di->id2.i_data.id_data, s_di->id2.i_data.id_data, + le16_to_cpu(s_di->id2.i_data.id_count)); + spin_lock(&OCFS2_I(t_inode)->ip_lock); + OCFS2_I(t_inode)->ip_dyn_features |= OCFS2_INLINE_DATA_FL; + t_di->i_dyn_features = cpu_to_le16(OCFS2_I(t_inode)->ip_dyn_features); + spin_unlock(&OCFS2_I(t_inode)->ip_lock); + + ocfs2_journal_dirty(handle, t_bh); + +out_commit: + ocfs2_commit_trans(osb, handle); +out: + return ret; +} + static int ocfs2_duplicate_extent_list(struct inode *s_inode, struct inode *t_inode, struct buffer_head *t_bh, @@ -3997,6 +4044,14 @@ static int ocfs2_create_reflink_node(struct inode *s_inode, goto out; } + if (OCFS2_I(s_inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { + ret = ocfs2_duplicate_inline_data(s_inode, s_bh, + t_inode, t_bh); + if (ret) + mlog_errno(ret); + goto out; + } + ret = ocfs2_lock_refcount_tree(osb, le64_to_cpu(di->i_refcount_loc), 1, &ref_tree, &ref_root_bh); if (ret) { @@ -4013,10 +4068,6 @@ static int ocfs2_create_reflink_node(struct inode *s_inode, goto out_unlock_refcount; } - ret = ocfs2_complete_reflink(s_inode, s_bh, t_inode, t_bh, preserve); - if (ret) - mlog_errno(ret); - out_unlock_refcount: ocfs2_unlock_refcount_tree(osb, ref_tree, 1); brelse(ref_root_bh); @@ -4068,9 +4119,17 @@ static int __ocfs2_reflink(struct dentry *old_dentry, ret = ocfs2_reflink_xattrs(inode, old_bh, new_inode, new_bh, preserve); - if (ret) + if (ret) { mlog_errno(ret); + goto inode_unlock; + } } + + ret = ocfs2_complete_reflink(inode, old_bh, + new_inode, new_bh, preserve); + if (ret) + mlog_errno(ret); + inode_unlock: ocfs2_inode_unlock(new_inode, 1); brelse(new_bh); diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c index 3f2f1c45b7b6..f3df0baa9a48 100644 --- a/fs/ocfs2/stackglue.c +++ b/fs/ocfs2/stackglue.c @@ -620,51 +620,46 @@ error: static ctl_table ocfs2_nm_table[] = { { - .ctl_name = 1, .procname = "hb_ctl_path", .data = ocfs2_hb_ctl_path, .maxlen = OCFS2_MAX_HB_CTL_PATH, .mode = 0644, - .proc_handler = &proc_dostring, - .strategy = &sysctl_string, + .proc_handler = proc_dostring, }, - { .ctl_name = 0 } + { } }; static ctl_table ocfs2_mod_table[] = { { - .ctl_name = FS_OCFS2_NM, .procname = "nm", .data = NULL, .maxlen = 0, .mode = 0555, .child = ocfs2_nm_table }, - { .ctl_name = 0} + { } }; static ctl_table ocfs2_kern_table[] = { { - .ctl_name = FS_OCFS2, .procname = "ocfs2", .data = NULL, .maxlen = 0, .mode = 0555, .child = ocfs2_mod_table }, - { .ctl_name = 0} + { } }; static ctl_table ocfs2_root_table[] = { { - .ctl_name = CTL_FS, .procname = "fs", .data = NULL, .maxlen = 0, .mode = 0555, .child = ocfs2_kern_table }, - { .ctl_name = 0 } + { } }; static struct ctl_table_header *ocfs2_table_header = NULL; diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index c0e48aeebb1c..14f47d2bfe02 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -773,18 +773,20 @@ static int ocfs2_sb_probe(struct super_block *sb, if (tmpstat < 0) { status = tmpstat; mlog_errno(status); - goto bail; + break; } di = (struct ocfs2_dinode *) (*bh)->b_data; memset(stats, 0, sizeof(struct ocfs2_blockcheck_stats)); spin_lock_init(&stats->b_lock); - status = ocfs2_verify_volume(di, *bh, blksize, stats); - if (status >= 0) - goto bail; - brelse(*bh); - *bh = NULL; - if (status != -EAGAIN) + tmpstat = ocfs2_verify_volume(di, *bh, blksize, stats); + if (tmpstat < 0) { + brelse(*bh); + *bh = NULL; + } + if (tmpstat != -EAGAIN) { + status = tmpstat; break; + } } bail: @@ -1645,6 +1647,10 @@ static int ocfs2_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_bavail = buf->f_bfree; buf->f_files = numbits; buf->f_ffree = freebits; + buf->f_fsid.val[0] = crc32_le(0, osb->uuid_str, OCFS2_VOL_UUID_LEN) + & 0xFFFFFFFFUL; + buf->f_fsid.val[1] = crc32_le(0, osb->uuid_str + OCFS2_VOL_UUID_LEN, + OCFS2_VOL_UUID_LEN) & 0xFFFFFFFFUL; brelse(bh); diff --git a/fs/ocfs2/uptodate.c b/fs/ocfs2/uptodate.c index b6284f235d2f..c61369342a27 100644 --- a/fs/ocfs2/uptodate.c +++ b/fs/ocfs2/uptodate.c @@ -53,11 +53,6 @@ #include <linux/highmem.h> #include <linux/buffer_head.h> #include <linux/rbtree.h> -#ifndef CONFIG_OCFS2_COMPAT_JBD -# include <linux/jbd2.h> -#else -# include <linux/jbd.h> -#endif #define MLOG_MASK_PREFIX ML_UPTODATE diff --git a/fs/open.c b/fs/open.c index 4f01e06227c6..b4b31d277f3a 100644 --- a/fs/open.c +++ b/fs/open.c @@ -587,6 +587,9 @@ SYSCALL_DEFINE1(chroot, const char __user *, filename) error = -EPERM; if (!capable(CAP_SYS_CHROOT)) goto dput_and_out; + error = security_path_chroot(&path); + if (error) + goto dput_and_out; set_fs_root(current->fs, &path); error = 0; @@ -617,11 +620,15 @@ SYSCALL_DEFINE2(fchmod, unsigned int, fd, mode_t, mode) if (err) goto out_putf; mutex_lock(&inode->i_mutex); + err = security_path_chmod(dentry, file->f_vfsmnt, mode); + if (err) + goto out_unlock; if (mode == (mode_t) -1) mode = inode->i_mode; newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO); newattrs.ia_valid = ATTR_MODE | ATTR_CTIME; err = notify_change(dentry, &newattrs); +out_unlock: mutex_unlock(&inode->i_mutex); mnt_drop_write(file->f_path.mnt); out_putf: @@ -646,11 +653,15 @@ SYSCALL_DEFINE3(fchmodat, int, dfd, const char __user *, filename, mode_t, mode) if (error) goto dput_and_out; mutex_lock(&inode->i_mutex); + error = security_path_chmod(path.dentry, path.mnt, mode); + if (error) + goto out_unlock; if (mode == (mode_t) -1) mode = inode->i_mode; newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO); newattrs.ia_valid = ATTR_MODE | ATTR_CTIME; error = notify_change(path.dentry, &newattrs); +out_unlock: mutex_unlock(&inode->i_mutex); mnt_drop_write(path.mnt); dput_and_out: @@ -664,9 +675,9 @@ SYSCALL_DEFINE2(chmod, const char __user *, filename, mode_t, mode) return sys_fchmodat(AT_FDCWD, filename, mode); } -static int chown_common(struct dentry * dentry, uid_t user, gid_t group) +static int chown_common(struct path *path, uid_t user, gid_t group) { - struct inode *inode = dentry->d_inode; + struct inode *inode = path->dentry->d_inode; int error; struct iattr newattrs; @@ -683,7 +694,9 @@ static int chown_common(struct dentry * dentry, uid_t user, gid_t group) newattrs.ia_valid |= ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV; mutex_lock(&inode->i_mutex); - error = notify_change(dentry, &newattrs); + error = security_path_chown(path, user, group); + if (!error) + error = notify_change(path->dentry, &newattrs); mutex_unlock(&inode->i_mutex); return error; @@ -700,7 +713,7 @@ SYSCALL_DEFINE3(chown, const char __user *, filename, uid_t, user, gid_t, group) error = mnt_want_write(path.mnt); if (error) goto out_release; - error = chown_common(path.dentry, user, group); + error = chown_common(&path, user, group); mnt_drop_write(path.mnt); out_release: path_put(&path); @@ -725,7 +738,7 @@ SYSCALL_DEFINE5(fchownat, int, dfd, const char __user *, filename, uid_t, user, error = mnt_want_write(path.mnt); if (error) goto out_release; - error = chown_common(path.dentry, user, group); + error = chown_common(&path, user, group); mnt_drop_write(path.mnt); out_release: path_put(&path); @@ -744,7 +757,7 @@ SYSCALL_DEFINE3(lchown, const char __user *, filename, uid_t, user, gid_t, group error = mnt_want_write(path.mnt); if (error) goto out_release; - error = chown_common(path.dentry, user, group); + error = chown_common(&path, user, group); mnt_drop_write(path.mnt); out_release: path_put(&path); @@ -767,7 +780,7 @@ SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group) goto out_fput; dentry = file->f_path.dentry; audit_inode(NULL, dentry); - error = chown_common(dentry, user, group); + error = chown_common(&file->f_path, user, group); mnt_drop_write(file->f_path.mnt); out_fput: fput(file); diff --git a/fs/proc/array.c b/fs/proc/array.c index 822c2d506518..4badde179b18 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -410,6 +410,16 @@ static void task_show_stack_usage(struct seq_file *m, struct task_struct *task) } #endif /* CONFIG_MMU */ +static void task_cpus_allowed(struct seq_file *m, struct task_struct *task) +{ + seq_printf(m, "Cpus_allowed:\t"); + seq_cpumask(m, &task->cpus_allowed); + seq_printf(m, "\n"); + seq_printf(m, "Cpus_allowed_list:\t"); + seq_cpumask_list(m, &task->cpus_allowed); + seq_printf(m, "\n"); +} + int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { @@ -424,6 +434,7 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, } task_sig(m, task); task_cap(m, task); + task_cpus_allowed(m, task); cpuset_task_status_allowed(m, task); #if defined(CONFIG_S390) task_show_regs(m, task); @@ -495,20 +506,17 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, /* add up live thread stats at the group level */ if (whole) { - struct task_cputime cputime; struct task_struct *t = task; do { min_flt += t->min_flt; maj_flt += t->maj_flt; - gtime = cputime_add(gtime, task_gtime(t)); + gtime = cputime_add(gtime, t->gtime); t = next_thread(t); } while (t != task); min_flt += sig->min_flt; maj_flt += sig->maj_flt; - thread_group_cputime(task, &cputime); - utime = cputime.utime; - stime = cputime.stime; + thread_group_times(task, &utime, &stime); gtime = cputime_add(gtime, sig->gtime); } @@ -524,9 +532,8 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, if (!whole) { min_flt = task->min_flt; maj_flt = task->maj_flt; - utime = task_utime(task); - stime = task_stime(task); - gtime = task_gtime(task); + task_times(task, &utime, &stime); + gtime = task->gtime; } /* scale priority and nice values from timeslices to -20..20 */ diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index f667e8aeabdf..6ff9981f0a18 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -48,7 +48,7 @@ out: static struct ctl_table *find_in_table(struct ctl_table *p, struct qstr *name) { int len; - for ( ; p->ctl_name || p->procname; p++) { + for ( ; p->procname; p++) { if (!p->procname) continue; @@ -218,7 +218,7 @@ static int scan(struct ctl_table_header *head, ctl_table *table, void *dirent, filldir_t filldir) { - for (; table->ctl_name || table->procname; table++, (*pos)++) { + for (; table->procname; table++, (*pos)++) { int res; /* Can't do anything without a proc name */ diff --git a/fs/proc/stat.c b/fs/proc/stat.c index 7cc726c6d70a..b9b7aad2003d 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -27,7 +27,7 @@ static int show_stat(struct seq_file *p, void *v) int i, j; unsigned long jif; cputime64_t user, nice, system, idle, iowait, irq, softirq, steal; - cputime64_t guest; + cputime64_t guest, guest_nice; u64 sum = 0; u64 sum_softirq = 0; unsigned int per_softirq_sums[NR_SOFTIRQS] = {0}; @@ -36,7 +36,7 @@ static int show_stat(struct seq_file *p, void *v) user = nice = system = idle = iowait = irq = softirq = steal = cputime64_zero; - guest = cputime64_zero; + guest = guest_nice = cputime64_zero; getboottime(&boottime); jif = boottime.tv_sec; @@ -51,6 +51,8 @@ static int show_stat(struct seq_file *p, void *v) softirq = cputime64_add(softirq, kstat_cpu(i).cpustat.softirq); steal = cputime64_add(steal, kstat_cpu(i).cpustat.steal); guest = cputime64_add(guest, kstat_cpu(i).cpustat.guest); + guest_nice = cputime64_add(guest_nice, + kstat_cpu(i).cpustat.guest_nice); for_each_irq_nr(j) { sum += kstat_irqs_cpu(j, i); } @@ -65,7 +67,8 @@ static int show_stat(struct seq_file *p, void *v) } sum += arch_irq_stat(); - seq_printf(p, "cpu %llu %llu %llu %llu %llu %llu %llu %llu %llu\n", + seq_printf(p, "cpu %llu %llu %llu %llu %llu %llu %llu %llu %llu " + "%llu\n", (unsigned long long)cputime64_to_clock_t(user), (unsigned long long)cputime64_to_clock_t(nice), (unsigned long long)cputime64_to_clock_t(system), @@ -74,7 +77,8 @@ static int show_stat(struct seq_file *p, void *v) (unsigned long long)cputime64_to_clock_t(irq), (unsigned long long)cputime64_to_clock_t(softirq), (unsigned long long)cputime64_to_clock_t(steal), - (unsigned long long)cputime64_to_clock_t(guest)); + (unsigned long long)cputime64_to_clock_t(guest), + (unsigned long long)cputime64_to_clock_t(guest_nice)); for_each_online_cpu(i) { /* Copy values here to work around gcc-2.95.3, gcc-2.96 */ @@ -88,8 +92,10 @@ static int show_stat(struct seq_file *p, void *v) softirq = kstat_cpu(i).cpustat.softirq; steal = kstat_cpu(i).cpustat.steal; guest = kstat_cpu(i).cpustat.guest; + guest_nice = kstat_cpu(i).cpustat.guest_nice; seq_printf(p, - "cpu%d %llu %llu %llu %llu %llu %llu %llu %llu %llu\n", + "cpu%d %llu %llu %llu %llu %llu %llu %llu %llu %llu " + "%llu\n", i, (unsigned long long)cputime64_to_clock_t(user), (unsigned long long)cputime64_to_clock_t(nice), @@ -99,7 +105,8 @@ static int show_stat(struct seq_file *p, void *v) (unsigned long long)cputime64_to_clock_t(irq), (unsigned long long)cputime64_to_clock_t(softirq), (unsigned long long)cputime64_to_clock_t(steal), - (unsigned long long)cputime64_to_clock_t(guest)); + (unsigned long long)cputime64_to_clock_t(guest), + (unsigned long long)cputime64_to_clock_t(guest_nice)); } seq_printf(p, "intr %llu", (unsigned long long)sum); diff --git a/fs/quota/Kconfig b/fs/quota/Kconfig index 8047e01ef46b..353e78a9ebee 100644 --- a/fs/quota/Kconfig +++ b/fs/quota/Kconfig @@ -17,7 +17,7 @@ config QUOTA config QUOTA_NETLINK_INTERFACE bool "Report quota messages through netlink interface" - depends on QUOTA && NET + depends on QUOTACTL && NET help If you say Y here, quota warnings (about exceeding softlimit, reaching hardlimit, etc.) will be reported through netlink interface. If unsure, diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 39b49c42a7ed..eb5a755718f6 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -77,10 +77,6 @@ #include <linux/capability.h> #include <linux/quotaops.h> #include <linux/writeback.h> /* for inode_lock, oddly enough.. */ -#ifdef CONFIG_QUOTA_NETLINK_INTERFACE -#include <net/netlink.h> -#include <net/genetlink.h> -#endif #include <asm/uaccess.h> @@ -1071,73 +1067,6 @@ static void print_warning(struct dquot *dquot, const int warntype) } #endif -#ifdef CONFIG_QUOTA_NETLINK_INTERFACE - -/* Netlink family structure for quota */ -static struct genl_family quota_genl_family = { - .id = GENL_ID_GENERATE, - .hdrsize = 0, - .name = "VFS_DQUOT", - .version = 1, - .maxattr = QUOTA_NL_A_MAX, -}; - -/* Send warning to userspace about user which exceeded quota */ -static void send_warning(const struct dquot *dquot, const char warntype) -{ - static atomic_t seq; - struct sk_buff *skb; - void *msg_head; - int ret; - int msg_size = 4 * nla_total_size(sizeof(u32)) + - 2 * nla_total_size(sizeof(u64)); - - /* We have to allocate using GFP_NOFS as we are called from a - * filesystem performing write and thus further recursion into - * the fs to free some data could cause deadlocks. */ - skb = genlmsg_new(msg_size, GFP_NOFS); - if (!skb) { - printk(KERN_ERR - "VFS: Not enough memory to send quota warning.\n"); - return; - } - msg_head = genlmsg_put(skb, 0, atomic_add_return(1, &seq), - "a_genl_family, 0, QUOTA_NL_C_WARNING); - if (!msg_head) { - printk(KERN_ERR - "VFS: Cannot store netlink header in quota warning.\n"); - goto err_out; - } - ret = nla_put_u32(skb, QUOTA_NL_A_QTYPE, dquot->dq_type); - if (ret) - goto attr_err_out; - ret = nla_put_u64(skb, QUOTA_NL_A_EXCESS_ID, dquot->dq_id); - if (ret) - goto attr_err_out; - ret = nla_put_u32(skb, QUOTA_NL_A_WARNING, warntype); - if (ret) - goto attr_err_out; - ret = nla_put_u32(skb, QUOTA_NL_A_DEV_MAJOR, - MAJOR(dquot->dq_sb->s_dev)); - if (ret) - goto attr_err_out; - ret = nla_put_u32(skb, QUOTA_NL_A_DEV_MINOR, - MINOR(dquot->dq_sb->s_dev)); - if (ret) - goto attr_err_out; - ret = nla_put_u64(skb, QUOTA_NL_A_CAUSED_ID, current_uid()); - if (ret) - goto attr_err_out; - genlmsg_end(skb, msg_head); - - genlmsg_multicast(skb, 0, quota_genl_family.id, GFP_NOFS); - return; -attr_err_out: - printk(KERN_ERR "VFS: Not enough space to compose quota message!\n"); -err_out: - kfree_skb(skb); -} -#endif /* * Write warnings to the console and send warning messages over netlink. * @@ -1145,18 +1074,20 @@ err_out: */ static void flush_warnings(struct dquot *const *dquots, char *warntype) { + struct dquot *dq; int i; - for (i = 0; i < MAXQUOTAS; i++) - if (dquots[i] && warntype[i] != QUOTA_NL_NOWARN && - !warning_issued(dquots[i], warntype[i])) { + for (i = 0; i < MAXQUOTAS; i++) { + dq = dquots[i]; + if (dq && warntype[i] != QUOTA_NL_NOWARN && + !warning_issued(dq, warntype[i])) { #ifdef CONFIG_PRINT_QUOTA_WARNING - print_warning(dquots[i], warntype[i]); -#endif -#ifdef CONFIG_QUOTA_NETLINK_INTERFACE - send_warning(dquots[i], warntype[i]); + print_warning(dq, warntype[i]); #endif + quota_send_warning(dq->dq_type, dq->dq_id, + dq->dq_sb->s_dev, warntype[i]); } + } } static int ignore_hardlimit(struct dquot *dquot) @@ -2473,100 +2404,89 @@ const struct quotactl_ops vfs_quotactl_ops = { static ctl_table fs_dqstats_table[] = { { - .ctl_name = FS_DQ_LOOKUPS, .procname = "lookups", .data = &dqstats.lookups, .maxlen = sizeof(int), .mode = 0444, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = FS_DQ_DROPS, .procname = "drops", .data = &dqstats.drops, .maxlen = sizeof(int), .mode = 0444, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = FS_DQ_READS, .procname = "reads", .data = &dqstats.reads, .maxlen = sizeof(int), .mode = 0444, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = FS_DQ_WRITES, .procname = "writes", .data = &dqstats.writes, .maxlen = sizeof(int), .mode = 0444, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = FS_DQ_CACHE_HITS, .procname = "cache_hits", .data = &dqstats.cache_hits, .maxlen = sizeof(int), .mode = 0444, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = FS_DQ_ALLOCATED, .procname = "allocated_dquots", .data = &dqstats.allocated_dquots, .maxlen = sizeof(int), .mode = 0444, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = FS_DQ_FREE, .procname = "free_dquots", .data = &dqstats.free_dquots, .maxlen = sizeof(int), .mode = 0444, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = FS_DQ_SYNCS, .procname = "syncs", .data = &dqstats.syncs, .maxlen = sizeof(int), .mode = 0444, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #ifdef CONFIG_PRINT_QUOTA_WARNING { - .ctl_name = FS_DQ_WARNINGS, .procname = "warnings", .data = &flag_print_warnings, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif - { .ctl_name = 0 }, + { }, }; static ctl_table fs_table[] = { { - .ctl_name = FS_DQSTATS, .procname = "quota", .mode = 0555, .child = fs_dqstats_table, }, - { .ctl_name = 0 }, + { }, }; static ctl_table sys_table[] = { { - .ctl_name = CTL_FS, .procname = "fs", .mode = 0555, .child = fs_table, }, - { .ctl_name = 0 }, + { }, }; static int __init dquot_init(void) @@ -2607,12 +2527,6 @@ static int __init dquot_init(void) register_shrinker(&dqcache_shrinker); -#ifdef CONFIG_QUOTA_NETLINK_INTERFACE - if (genl_register_family("a_genl_family) != 0) - printk(KERN_ERR - "VFS: Failed to create quota netlink interface.\n"); -#endif - return 0; } module_init(dquot_init); diff --git a/fs/quota/quota.c b/fs/quota/quota.c index 95c5b42384b2..ee91e2756950 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -18,6 +18,8 @@ #include <linux/capability.h> #include <linux/quotaops.h> #include <linux/types.h> +#include <net/netlink.h> +#include <net/genetlink.h> /* Check validity of generic quotactl commands */ static int generic_quotactl_valid(struct super_block *sb, int type, int cmd, @@ -525,3 +527,94 @@ asmlinkage long sys32_quotactl(unsigned int cmd, const char __user *special, return ret; } #endif + + +#ifdef CONFIG_QUOTA_NETLINK_INTERFACE + +/* Netlink family structure for quota */ +static struct genl_family quota_genl_family = { + .id = GENL_ID_GENERATE, + .hdrsize = 0, + .name = "VFS_DQUOT", + .version = 1, + .maxattr = QUOTA_NL_A_MAX, +}; + +/** + * quota_send_warning - Send warning to userspace about exceeded quota + * @type: The quota type: USRQQUOTA, GRPQUOTA,... + * @id: The user or group id of the quota that was exceeded + * @dev: The device on which the fs is mounted (sb->s_dev) + * @warntype: The type of the warning: QUOTA_NL_... + * + * This can be used by filesystems (including those which don't use + * dquot) to send a message to userspace relating to quota limits. + * + */ + +void quota_send_warning(short type, unsigned int id, dev_t dev, + const char warntype) +{ + static atomic_t seq; + struct sk_buff *skb; + void *msg_head; + int ret; + int msg_size = 4 * nla_total_size(sizeof(u32)) + + 2 * nla_total_size(sizeof(u64)); + + /* We have to allocate using GFP_NOFS as we are called from a + * filesystem performing write and thus further recursion into + * the fs to free some data could cause deadlocks. */ + skb = genlmsg_new(msg_size, GFP_NOFS); + if (!skb) { + printk(KERN_ERR + "VFS: Not enough memory to send quota warning.\n"); + return; + } + msg_head = genlmsg_put(skb, 0, atomic_add_return(1, &seq), + "a_genl_family, 0, QUOTA_NL_C_WARNING); + if (!msg_head) { + printk(KERN_ERR + "VFS: Cannot store netlink header in quota warning.\n"); + goto err_out; + } + ret = nla_put_u32(skb, QUOTA_NL_A_QTYPE, type); + if (ret) + goto attr_err_out; + ret = nla_put_u64(skb, QUOTA_NL_A_EXCESS_ID, id); + if (ret) + goto attr_err_out; + ret = nla_put_u32(skb, QUOTA_NL_A_WARNING, warntype); + if (ret) + goto attr_err_out; + ret = nla_put_u32(skb, QUOTA_NL_A_DEV_MAJOR, MAJOR(dev)); + if (ret) + goto attr_err_out; + ret = nla_put_u32(skb, QUOTA_NL_A_DEV_MINOR, MINOR(dev)); + if (ret) + goto attr_err_out; + ret = nla_put_u64(skb, QUOTA_NL_A_CAUSED_ID, current_uid()); + if (ret) + goto attr_err_out; + genlmsg_end(skb, msg_head); + + genlmsg_multicast(skb, 0, quota_genl_family.id, GFP_NOFS); + return; +attr_err_out: + printk(KERN_ERR "VFS: Not enough space to compose quota message!\n"); +err_out: + kfree_skb(skb); +} +EXPORT_SYMBOL(quota_send_warning); + +static int __init quota_init(void) +{ + if (genl_register_family("a_genl_family) != 0) + printk(KERN_ERR + "VFS: Failed to create quota netlink interface.\n"); + return 0; +}; + +module_init(quota_init); +#endif + diff --git a/fs/xattr_acl.c b/fs/xattr_acl.c index c6ad7c7e3ee9..05ac0fe9c4d3 100644 --- a/fs/xattr_acl.c +++ b/fs/xattr_acl.c @@ -36,7 +36,7 @@ posix_acl_from_xattr(const void *value, size_t size) if (count == 0) return NULL; - acl = posix_acl_alloc(count, GFP_KERNEL); + acl = posix_acl_alloc(count, GFP_NOFS); if (!acl) return ERR_PTR(-ENOMEM); acl_e = acl->a_entries; diff --git a/fs/xfs/linux-2.6/xfs_sysctl.c b/fs/xfs/linux-2.6/xfs_sysctl.c index c5bc67c4e3bb..7bb5092d6ae4 100644 --- a/fs/xfs/linux-2.6/xfs_sysctl.c +++ b/fs/xfs/linux-2.6/xfs_sysctl.c @@ -55,170 +55,140 @@ xfs_stats_clear_proc_handler( static ctl_table xfs_table[] = { { - .ctl_name = XFS_SGID_INHERIT, .procname = "irix_sgid_inherit", .data = &xfs_params.sgid_inherit.val, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &xfs_params.sgid_inherit.min, .extra2 = &xfs_params.sgid_inherit.max }, { - .ctl_name = XFS_SYMLINK_MODE, .procname = "irix_symlink_mode", .data = &xfs_params.symlink_mode.val, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &xfs_params.symlink_mode.min, .extra2 = &xfs_params.symlink_mode.max }, { - .ctl_name = XFS_PANIC_MASK, .procname = "panic_mask", .data = &xfs_params.panic_mask.val, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &xfs_params.panic_mask.min, .extra2 = &xfs_params.panic_mask.max }, { - .ctl_name = XFS_ERRLEVEL, .procname = "error_level", .data = &xfs_params.error_level.val, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &xfs_params.error_level.min, .extra2 = &xfs_params.error_level.max }, { - .ctl_name = XFS_SYNCD_TIMER, .procname = "xfssyncd_centisecs", .data = &xfs_params.syncd_timer.val, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &xfs_params.syncd_timer.min, .extra2 = &xfs_params.syncd_timer.max }, { - .ctl_name = XFS_INHERIT_SYNC, .procname = "inherit_sync", .data = &xfs_params.inherit_sync.val, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &xfs_params.inherit_sync.min, .extra2 = &xfs_params.inherit_sync.max }, { - .ctl_name = XFS_INHERIT_NODUMP, .procname = "inherit_nodump", .data = &xfs_params.inherit_nodump.val, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &xfs_params.inherit_nodump.min, .extra2 = &xfs_params.inherit_nodump.max }, { - .ctl_name = XFS_INHERIT_NOATIME, .procname = "inherit_noatime", .data = &xfs_params.inherit_noatim.val, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &xfs_params.inherit_noatim.min, .extra2 = &xfs_params.inherit_noatim.max }, { - .ctl_name = XFS_BUF_TIMER, .procname = "xfsbufd_centisecs", .data = &xfs_params.xfs_buf_timer.val, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &xfs_params.xfs_buf_timer.min, .extra2 = &xfs_params.xfs_buf_timer.max }, { - .ctl_name = XFS_BUF_AGE, .procname = "age_buffer_centisecs", .data = &xfs_params.xfs_buf_age.val, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &xfs_params.xfs_buf_age.min, .extra2 = &xfs_params.xfs_buf_age.max }, { - .ctl_name = XFS_INHERIT_NOSYM, .procname = "inherit_nosymlinks", .data = &xfs_params.inherit_nosym.val, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &xfs_params.inherit_nosym.min, .extra2 = &xfs_params.inherit_nosym.max }, { - .ctl_name = XFS_ROTORSTEP, .procname = "rotorstep", .data = &xfs_params.rotorstep.val, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &xfs_params.rotorstep.min, .extra2 = &xfs_params.rotorstep.max }, { - .ctl_name = XFS_INHERIT_NODFRG, .procname = "inherit_nodefrag", .data = &xfs_params.inherit_nodfrg.val, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &xfs_params.inherit_nodfrg.min, .extra2 = &xfs_params.inherit_nodfrg.max }, { - .ctl_name = XFS_FILESTREAM_TIMER, .procname = "filestream_centisecs", .data = &xfs_params.fstrm_timer.val, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &xfs_params.fstrm_timer.min, .extra2 = &xfs_params.fstrm_timer.max, }, /* please keep this the last entry */ #ifdef CONFIG_PROC_FS { - .ctl_name = XFS_STATS_CLEAR, .procname = "stats_clear", .data = &xfs_params.stats_clear.val, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &xfs_stats_clear_proc_handler, - .strategy = &sysctl_intvec, + .proc_handler = xfs_stats_clear_proc_handler, .extra1 = &xfs_params.stats_clear.min, .extra2 = &xfs_params.stats_clear.max }, @@ -229,7 +199,6 @@ static ctl_table xfs_table[] = { static ctl_table xfs_dir_table[] = { { - .ctl_name = FS_XFS, .procname = "xfs", .mode = 0555, .child = xfs_table @@ -239,7 +208,6 @@ static ctl_table xfs_dir_table[] = { static ctl_table xfs_root_table[] = { { - .ctl_name = CTL_FS, .procname = "fs", .mode = 0555, .child = xfs_dir_table diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 1feed71551c9..5a5385749e16 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -330,6 +330,7 @@ unifdef-y += scc.h unifdef-y += sched.h unifdef-y += screen_info.h unifdef-y += sdla.h +unifdef-y += securebits.h unifdef-y += selinux_netlink.h unifdef-y += sem.h unifdef-y += serial_core.h diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index dd97fb8408a8..b10ec49ee2dd 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -53,6 +53,7 @@ extern void free_bootmem_node(pg_data_t *pgdat, unsigned long addr, unsigned long size); extern void free_bootmem(unsigned long addr, unsigned long size); +extern void free_bootmem_late(unsigned long addr, unsigned long size); /* * Flags for reserve_bootmem (also if CONFIG_HAVE_ARCH_BOOTMEM_NODE, diff --git a/include/linux/capability.h b/include/linux/capability.h index c8f2a5f70ed5..39e5ff512fbe 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -92,9 +92,7 @@ struct vfs_cap_data { #define _KERNEL_CAPABILITY_VERSION _LINUX_CAPABILITY_VERSION_3 #define _KERNEL_CAPABILITY_U32S _LINUX_CAPABILITY_U32S_3 -#ifdef CONFIG_SECURITY_FILE_CAPABILITIES extern int file_caps_enabled; -#endif typedef struct kernel_cap_struct { __u32 cap[_KERNEL_CAPABILITY_U32S]; diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index a3ed7cb8ca34..73dcf804bc94 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -79,6 +79,7 @@ #define noinline __attribute__((noinline)) #define __attribute_const__ __attribute__((__const__)) #define __maybe_unused __attribute__((unused)) +#define __always_unused __attribute__((unused)) #define __gcc_header(x) #x #define _gcc_header(x) __gcc_header(linux/compiler-gcc##x.h) diff --git a/include/linux/compiler-gcc4.h b/include/linux/compiler-gcc4.h index 450fa597c94d..94dea3ffbfa1 100644 --- a/include/linux/compiler-gcc4.h +++ b/include/linux/compiler-gcc4.h @@ -36,4 +36,26 @@ the kernel context */ #define __cold __attribute__((__cold__)) + +#if __GNUC_MINOR__ >= 5 +/* + * Mark a position in code as unreachable. This can be used to + * suppress control flow warnings after asm blocks that transfer + * control elsewhere. + * + * Early snapshots of gcc 4.5 don't support this and we can't detect + * this in the preprocessor, but we can live with this because they're + * unreleased. Really, we need to have autoconf for the kernel. + */ +#define unreachable() __builtin_unreachable() +#endif + +#endif + +#if __GNUC_MINOR__ > 0 +#define __compiletime_object_size(obj) __builtin_object_size(obj, 0) +#endif +#if __GNUC_MINOR__ >= 4 +#define __compiletime_warning(message) __attribute__((warning(message))) +#define __compiletime_error(message) __attribute__((error(message))) #endif diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 04fb5135b4e1..5be3dab4a695 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -144,6 +144,11 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); # define barrier() __memory_barrier() #endif +/* Unreachable code */ +#ifndef unreachable +# define unreachable() do { } while (1) +#endif + #ifndef RELOC_HIDE # define RELOC_HIDE(ptr, off) \ ({ unsigned long __ptr; \ @@ -213,6 +218,10 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); # define __maybe_unused /* unimplemented */ #endif +#ifndef __always_unused +# define __always_unused /* unimplemented */ +#endif + #ifndef noinline #define noinline #endif @@ -266,6 +275,17 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); # define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) #endif +/* Compile time object size, -1 for unknown */ +#ifndef __compiletime_object_size +# define __compiletime_object_size(obj) -1 +#endif +#ifndef __compiletime_warning +# define __compiletime_warning(message) +#endif +#ifndef __compiletime_error +# define __compiletime_error(message) +#endif + /* * Prevent the compiler from merging or refetching accesses. The compiler * is also forbidden from reordering successive instances of ACCESS_ONCE(), diff --git a/include/linux/dmar.h b/include/linux/dmar.h index 4a2b162c256a..5de4c9e5856d 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -208,16 +208,9 @@ struct dmar_atsr_unit { u8 include_all:1; /* include all ports */ }; -/* Intel DMAR initialization functions */ extern int intel_iommu_init(void); -#else -static inline int intel_iommu_init(void) -{ -#ifdef CONFIG_INTR_REMAP - return dmar_dev_scope_init(); -#else - return -ENODEV; -#endif -} -#endif /* !CONFIG_DMAR */ +#else /* !CONFIG_DMAR: */ +static inline int intel_iommu_init(void) { return -ENODEV; } +#endif /* CONFIG_DMAR */ + #endif /* __DMAR_H__ */ diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 84d3532dd3ea..7be0c6fbe880 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -91,6 +91,8 @@ struct fscache_operation { #define FSCACHE_OP_WAITING 4 /* cleared when op is woken */ #define FSCACHE_OP_EXCLUSIVE 5 /* exclusive op, other ops must wait */ #define FSCACHE_OP_DEAD 6 /* op is now dead */ +#define FSCACHE_OP_DEC_READ_CNT 7 /* decrement object->n_reads on destruction */ +#define FSCACHE_OP_KEEP_FLAGS 0xc0 /* flags to keep when repurposing an op */ atomic_t usage; unsigned debug_id; /* debugging ID */ @@ -102,6 +104,16 @@ struct fscache_operation { /* operation releaser */ fscache_operation_release_t release; + +#ifdef CONFIG_SLOW_WORK_PROC + const char *name; /* operation name */ + const char *state; /* operation state */ +#define fscache_set_op_name(OP, N) do { (OP)->name = (N); } while(0) +#define fscache_set_op_state(OP, S) do { (OP)->state = (S); } while(0) +#else +#define fscache_set_op_name(OP, N) do { } while(0) +#define fscache_set_op_state(OP, S) do { } while(0) +#endif }; extern atomic_t fscache_op_debug_id; @@ -125,6 +137,7 @@ static inline void fscache_operation_init(struct fscache_operation *op, op->debug_id = atomic_inc_return(&fscache_op_debug_id); op->release = release; INIT_LIST_HEAD(&op->pend_link); + fscache_set_op_state(op, "Init"); } /** @@ -221,8 +234,10 @@ struct fscache_cache_ops { struct fscache_object *(*alloc_object)(struct fscache_cache *cache, struct fscache_cookie *cookie); - /* look up the object for a cookie */ - void (*lookup_object)(struct fscache_object *object); + /* look up the object for a cookie + * - return -ETIMEDOUT to be requeued + */ + int (*lookup_object)(struct fscache_object *object); /* finished looking up */ void (*lookup_complete)(struct fscache_object *object); @@ -297,12 +312,14 @@ struct fscache_cookie { atomic_t usage; /* number of users of this cookie */ atomic_t n_children; /* number of children of this cookie */ spinlock_t lock; + spinlock_t stores_lock; /* lock on page store tree */ struct hlist_head backing_objects; /* object(s) backing this file/index */ const struct fscache_cookie_def *def; /* definition */ struct fscache_cookie *parent; /* parent of this entry */ void *netfs_data; /* back pointer to netfs */ struct radix_tree_root stores; /* pages to be stored on this cookie */ #define FSCACHE_COOKIE_PENDING_TAG 0 /* pages tag: pending write to cache */ +#define FSCACHE_COOKIE_STORING_TAG 1 /* pages tag: writing to cache */ unsigned long flags; #define FSCACHE_COOKIE_LOOKING_UP 0 /* T if non-index cookie being looked up still */ @@ -337,6 +354,7 @@ struct fscache_object { FSCACHE_OBJECT_RECYCLING, /* retiring object */ FSCACHE_OBJECT_WITHDRAWING, /* withdrawing object */ FSCACHE_OBJECT_DEAD, /* object is now dead */ + FSCACHE_OBJECT__NSTATES } state; int debug_id; /* debugging ID */ @@ -345,6 +363,7 @@ struct fscache_object { int n_obj_ops; /* number of object ops outstanding on object */ int n_in_progress; /* number of ops in progress */ int n_exclusive; /* number of exclusive ops queued */ + atomic_t n_reads; /* number of read ops in progress */ spinlock_t lock; /* state and operations lock */ unsigned long lookup_jif; /* time at which lookup started */ @@ -358,6 +377,7 @@ struct fscache_object { #define FSCACHE_OBJECT_EV_RELEASE 4 /* T if netfs requested object release */ #define FSCACHE_OBJECT_EV_RETIRE 5 /* T if netfs requested object retirement */ #define FSCACHE_OBJECT_EV_WITHDRAW 6 /* T if cache requested object withdrawal */ +#define FSCACHE_OBJECT_EVENTS_MASK 0x7f /* mask of all events*/ unsigned long flags; #define FSCACHE_OBJECT_LOCK 0 /* T if object is busy being processed */ @@ -373,7 +393,11 @@ struct fscache_object { struct list_head dependents; /* FIFO of dependent objects */ struct list_head dep_link; /* link in parent's dependents list */ struct list_head pending_ops; /* unstarted operations on this object */ +#ifdef CONFIG_FSCACHE_OBJECT_LIST + struct rb_node objlist_link; /* link in global object list */ +#endif pgoff_t store_limit; /* current storage limit */ + loff_t store_limit_l; /* current storage limit */ }; extern const char *fscache_object_states[]; @@ -383,6 +407,10 @@ extern const char *fscache_object_states[]; (obj)->state >= FSCACHE_OBJECT_AVAILABLE && \ (obj)->state < FSCACHE_OBJECT_DYING) +#define fscache_object_is_dead(obj) \ + (test_bit(FSCACHE_IOERROR, &(obj)->cache->flags) && \ + (obj)->state >= FSCACHE_OBJECT_DYING) + extern const struct slow_work_ops fscache_object_slow_work_ops; /** @@ -414,6 +442,7 @@ void fscache_object_init(struct fscache_object *object, object->events = object->event_mask = 0; object->flags = 0; object->store_limit = 0; + object->store_limit_l = 0; object->cache = cache; object->cookie = cookie; object->parent = NULL; @@ -422,6 +451,12 @@ void fscache_object_init(struct fscache_object *object, extern void fscache_object_lookup_negative(struct fscache_object *object); extern void fscache_obtained_object(struct fscache_object *object); +#ifdef CONFIG_FSCACHE_OBJECT_LIST +extern void fscache_object_destroy(struct fscache_object *object); +#else +#define fscache_object_destroy(object) do {} while(0) +#endif + /** * fscache_object_destroyed - Note destruction of an object in a cache * @cache: The cache from which the object came @@ -460,6 +495,7 @@ static inline void fscache_object_lookup_error(struct fscache_object *object) static inline void fscache_set_store_limit(struct fscache_object *object, loff_t i_size) { + object->store_limit_l = i_size; object->store_limit = i_size >> PAGE_SHIFT; if (i_size & ~PAGE_MASK) object->store_limit++; diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 6d8ee466e0a0..595ce49288b7 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -202,6 +202,8 @@ extern int __fscache_write_page(struct fscache_cookie *, struct page *, gfp_t); extern void __fscache_uncache_page(struct fscache_cookie *, struct page *); extern bool __fscache_check_page_write(struct fscache_cookie *, struct page *); extern void __fscache_wait_on_page_write(struct fscache_cookie *, struct page *); +extern bool __fscache_maybe_release_page(struct fscache_cookie *, struct page *, + gfp_t); /** * fscache_register_netfs - Register a filesystem as desiring caching services @@ -615,4 +617,29 @@ void fscache_wait_on_page_write(struct fscache_cookie *cookie, __fscache_wait_on_page_write(cookie, page); } +/** + * fscache_maybe_release_page - Consider releasing a page, cancelling a store + * @cookie: The cookie representing the cache object + * @page: The netfs page that is being cached. + * @gfp: The gfp flags passed to releasepage() + * + * Consider releasing a page for the vmscan algorithm, on behalf of the netfs's + * releasepage() call. A storage request on the page may cancelled if it is + * not currently being processed. + * + * The function returns true if the page no longer has a storage request on it, + * and false if a storage request is left in place. If true is returned, the + * page will have been passed to fscache_uncache_page(). If false is returned + * the page cannot be freed yet. + */ +static inline +bool fscache_maybe_release_page(struct fscache_cookie *cookie, + struct page *page, + gfp_t gfp) +{ + if (fscache_cookie_valid(cookie) && PageFsCache(page)) + return __fscache_maybe_release_page(cookie, page, gfp); + return false; +} + #endif /* _LINUX_FSCACHE_H */ diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 4ec5e67e18cf..47bbdf9c38d0 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -117,12 +117,12 @@ struct ftrace_event_call { struct dentry *dir; struct trace_event *event; int enabled; - int (*regfunc)(void *); - void (*unregfunc)(void *); + int (*regfunc)(struct ftrace_event_call *); + void (*unregfunc)(struct ftrace_event_call *); int id; - int (*raw_init)(void); - int (*show_format)(struct ftrace_event_call *call, - struct trace_seq *s); + int (*raw_init)(struct ftrace_event_call *); + int (*show_format)(struct ftrace_event_call *, + struct trace_seq *); int (*define_fields)(struct ftrace_event_call *); struct list_head fields; int filter_active; @@ -131,20 +131,20 @@ struct ftrace_event_call { void *data; atomic_t profile_count; - int (*profile_enable)(void); - void (*profile_disable)(void); + int (*profile_enable)(struct ftrace_event_call *); + void (*profile_disable)(struct ftrace_event_call *); }; #define FTRACE_MAX_PROFILE_SIZE 2048 -extern char *trace_profile_buf; -extern char *trace_profile_buf_nmi; +extern char *perf_trace_buf; +extern char *perf_trace_buf_nmi; #define MAX_FILTER_PRED 32 #define MAX_FILTER_STR_VAL 256 /* Should handle KSYM_SYMBOL_LEN */ extern void destroy_preds(struct ftrace_event_call *call); -extern int filter_match_preds(struct ftrace_event_call *call, void *rec); +extern int filter_match_preds(struct event_filter *filter, void *rec); extern int filter_current_check_discard(struct ring_buffer *buffer, struct ftrace_event_call *call, void *rec, @@ -157,11 +157,12 @@ enum { FILTER_PTR_STRING, }; -extern int trace_define_field(struct ftrace_event_call *call, - const char *type, const char *name, - int offset, int size, int is_signed, - int filter_type); extern int trace_define_common_fields(struct ftrace_event_call *call); +extern int trace_define_field(struct ftrace_event_call *call, const char *type, + const char *name, int offset, int size, + int is_signed, int filter_type); +extern int trace_add_event_call(struct ftrace_event_call *call); +extern void trace_remove_event_call(struct ftrace_event_call *call); #define is_signed_type(type) (((type)(-1)) < 0) @@ -186,4 +187,13 @@ do { \ __trace_printk(ip, fmt, ##args); \ } while (0) +#ifdef CONFIG_EVENT_PROFILE +struct perf_event; +extern int ftrace_profile_enable(int event_id); +extern void ftrace_profile_disable(int event_id); +extern int ftrace_profile_set_filter(struct perf_event *event, int event_id, + char *filter_str); +extern void ftrace_profile_free_filter(struct perf_event *event); +#endif + #endif /* _LINUX_FTRACE_EVENT_H */ diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h index b80c88dedbbb..81f90a59cda6 100644 --- a/include/linux/gfs2_ondisk.h +++ b/include/linux/gfs2_ondisk.h @@ -81,7 +81,11 @@ struct gfs2_meta_header { __be32 mh_type; __be64 __pad0; /* Was generation number in gfs1 */ __be32 mh_format; - __be32 __pad1; /* Was incarnation number in gfs1 */ + /* This union is to keep userspace happy */ + union { + __be32 mh_jid; /* Was incarnation number in gfs1 */ + __be32 __pad1; + }; }; /* diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 6d527ee82b2b..d5b387669dab 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -139,10 +139,34 @@ static inline void account_system_vtime(struct task_struct *tsk) #endif #if defined(CONFIG_NO_HZ) +#if defined(CONFIG_TINY_RCU) +extern void rcu_enter_nohz(void); +extern void rcu_exit_nohz(void); + +static inline void rcu_irq_enter(void) +{ + rcu_exit_nohz(); +} + +static inline void rcu_irq_exit(void) +{ + rcu_enter_nohz(); +} + +static inline void rcu_nmi_enter(void) +{ +} + +static inline void rcu_nmi_exit(void) +{ +} + +#else extern void rcu_irq_enter(void); extern void rcu_irq_exit(void); extern void rcu_nmi_enter(void); extern void rcu_nmi_exit(void); +#endif #else # define rcu_irq_enter() do { } while (0) # define rcu_irq_exit() do { } while (0) diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h new file mode 100644 index 000000000000..a03daed08c59 --- /dev/null +++ b/include/linux/hw_breakpoint.h @@ -0,0 +1,131 @@ +#ifndef _LINUX_HW_BREAKPOINT_H +#define _LINUX_HW_BREAKPOINT_H + +enum { + HW_BREAKPOINT_LEN_1 = 1, + HW_BREAKPOINT_LEN_2 = 2, + HW_BREAKPOINT_LEN_4 = 4, + HW_BREAKPOINT_LEN_8 = 8, +}; + +enum { + HW_BREAKPOINT_R = 1, + HW_BREAKPOINT_W = 2, + HW_BREAKPOINT_X = 4, +}; + +#ifdef __KERNEL__ + +#include <linux/perf_event.h> + +#ifdef CONFIG_HAVE_HW_BREAKPOINT + +/* As it's for in-kernel or ptrace use, we want it to be pinned */ +#define DEFINE_BREAKPOINT_ATTR(name) \ +struct perf_event_attr name = { \ + .type = PERF_TYPE_BREAKPOINT, \ + .size = sizeof(name), \ + .pinned = 1, \ +}; + +static inline void hw_breakpoint_init(struct perf_event_attr *attr) +{ + attr->type = PERF_TYPE_BREAKPOINT; + attr->size = sizeof(*attr); + attr->pinned = 1; +} + +static inline unsigned long hw_breakpoint_addr(struct perf_event *bp) +{ + return bp->attr.bp_addr; +} + +static inline int hw_breakpoint_type(struct perf_event *bp) +{ + return bp->attr.bp_type; +} + +static inline int hw_breakpoint_len(struct perf_event *bp) +{ + return bp->attr.bp_len; +} + +extern struct perf_event * +register_user_hw_breakpoint(struct perf_event_attr *attr, + perf_callback_t triggered, + struct task_struct *tsk); + +/* FIXME: only change from the attr, and don't unregister */ +extern struct perf_event * +modify_user_hw_breakpoint(struct perf_event *bp, + struct perf_event_attr *attr, + perf_callback_t triggered, + struct task_struct *tsk); + +/* + * Kernel breakpoints are not associated with any particular thread. + */ +extern struct perf_event * +register_wide_hw_breakpoint_cpu(struct perf_event_attr *attr, + perf_callback_t triggered, + int cpu); + +extern struct perf_event ** +register_wide_hw_breakpoint(struct perf_event_attr *attr, + perf_callback_t triggered); + +extern int register_perf_hw_breakpoint(struct perf_event *bp); +extern int __register_perf_hw_breakpoint(struct perf_event *bp); +extern void unregister_hw_breakpoint(struct perf_event *bp); +extern void unregister_wide_hw_breakpoint(struct perf_event **cpu_events); + +extern int reserve_bp_slot(struct perf_event *bp); +extern void release_bp_slot(struct perf_event *bp); + +extern void flush_ptrace_hw_breakpoint(struct task_struct *tsk); + +static inline struct arch_hw_breakpoint *counter_arch_bp(struct perf_event *bp) +{ + return &bp->hw.info; +} + +#else /* !CONFIG_HAVE_HW_BREAKPOINT */ + +static inline struct perf_event * +register_user_hw_breakpoint(struct perf_event_attr *attr, + perf_callback_t triggered, + struct task_struct *tsk) { return NULL; } +static inline struct perf_event * +modify_user_hw_breakpoint(struct perf_event *bp, + struct perf_event_attr *attr, + perf_callback_t triggered, + struct task_struct *tsk) { return NULL; } +static inline struct perf_event * +register_wide_hw_breakpoint_cpu(struct perf_event_attr *attr, + perf_callback_t triggered, + int cpu) { return NULL; } +static inline struct perf_event ** +register_wide_hw_breakpoint(struct perf_event_attr *attr, + perf_callback_t triggered) { return NULL; } +static inline int +register_perf_hw_breakpoint(struct perf_event *bp) { return -ENOSYS; } +static inline int +__register_perf_hw_breakpoint(struct perf_event *bp) { return -ENOSYS; } +static inline void unregister_hw_breakpoint(struct perf_event *bp) { } +static inline void +unregister_wide_hw_breakpoint(struct perf_event **cpu_events) { } +static inline int +reserve_bp_slot(struct perf_event *bp) {return -ENOSYS; } +static inline void release_bp_slot(struct perf_event *bp) { } + +static inline void flush_ptrace_hw_breakpoint(struct task_struct *tsk) { } + +static inline struct arch_hw_breakpoint *counter_arch_bp(struct perf_event *bp) +{ + return NULL; +} + +#endif /* CONFIG_HAVE_HW_BREAKPOINT */ +#endif /* __KERNEL__ */ + +#endif /* _LINUX_HW_BREAKPOINT_H */ diff --git a/include/linux/i2c-pnx.h b/include/linux/i2c-pnx.h index f13255e06406..9eb07bbc6522 100644 --- a/include/linux/i2c-pnx.h +++ b/include/linux/i2c-pnx.h @@ -21,7 +21,7 @@ struct i2c_pnx_mif { int mode; /* Interface mode */ struct completion complete; /* I/O completion */ struct timer_list timer; /* Timeout */ - char * buf; /* Data buffer */ + u8 * buf; /* Data buffer */ int len; /* Length of data buffer */ }; diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 21a6f5d9af22..8d10aa7fd4c9 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -83,16 +83,12 @@ extern struct group_info init_groups; #define INIT_IDS #endif -#ifdef CONFIG_SECURITY_FILE_CAPABILITIES /* * Because of the reduced scope of CAP_SETPCAP when filesystem * capabilities are in effect, it is safe to allow CAP_SETPCAP to * be available in the default configuration. */ # define CAP_INIT_BSET CAP_FULL_SET -#else -# define CAP_INIT_BSET CAP_INIT_EFF_SET -#endif #ifdef CONFIG_TREE_PREEMPT_RCU #define INIT_TASK_RCU_PREEMPT(tsk) \ diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 7ca72b74eec7..75f3f00ac1e5 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -603,12 +603,6 @@ static inline void init_irq_proc(void) } #endif -#if defined(CONFIG_GENERIC_HARDIRQS) && defined(CONFIG_DEBUG_SHIRQ) -extern void debug_poll_all_shared_irqs(void); -#else -static inline void debug_poll_all_shared_irqs(void) { } -#endif - struct seq_file; int show_interrupts(struct seq_file *p, void *v); diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index b02a3f1d46a0..006bf45eae30 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -124,6 +124,6 @@ typecheck(unsigned long, flags); \ raw_irqs_disabled_flags(flags); \ }) -#endif /* CONFIG_X86 */ +#endif /* CONFIG_TRACE_IRQFLAGS_SUPPORT */ #endif diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index 1a9cf78bfce5..6811f4bfc6e7 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -307,6 +307,7 @@ extern clock_t jiffies_to_clock_t(long x); extern unsigned long clock_t_to_jiffies(unsigned long x); extern u64 jiffies_64_to_clock_t(u64 x); extern u64 nsec_to_clock_t(u64 x); +extern unsigned long nsecs_to_jiffies(u64 n); #define TIMESTAMP_SIZE 30 diff --git a/include/linux/kernel.h b/include/linux/kernel.h index f4e3184fa054..3fa4c590cf12 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -15,7 +15,6 @@ #include <linux/bitops.h> #include <linux/log2.h> #include <linux/typecheck.h> -#include <linux/ratelimit.h> #include <linux/dynamic_debug.h> #include <asm/byteorder.h> #include <asm/bug.h> @@ -241,8 +240,8 @@ asmlinkage int vprintk(const char *fmt, va_list args) asmlinkage int printk(const char * fmt, ...) __attribute__ ((format (printf, 1, 2))) __cold; -extern struct ratelimit_state printk_ratelimit_state; -extern int printk_ratelimit(void); +extern int __printk_ratelimit(const char *func); +#define printk_ratelimit() __printk_ratelimit(__func__) extern bool printk_timed_ratelimit(unsigned long *caller_jiffies, unsigned int interval_msec); diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index 348fa8874b52..c059044bc6dc 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -25,6 +25,7 @@ struct cpu_usage_stat { cputime64_t iowait; cputime64_t steal; cputime64_t guest; + cputime64_t guest_nice; }; struct kernel_stat { diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 3a46b7b7abb2..1b672f74a32f 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -296,6 +296,8 @@ void recycle_rp_inst(struct kretprobe_instance *ri, struct hlist_head *head); int disable_kprobe(struct kprobe *kp); int enable_kprobe(struct kprobe *kp); +void dump_kprobe(struct kprobe *kp); + #else /* !CONFIG_KPROBES: */ static inline int kprobes_built_in(void) diff --git a/include/linux/lsm_audit.h b/include/linux/lsm_audit.h index 190c37854870..f78f83d7663f 100644 --- a/include/linux/lsm_audit.h +++ b/include/linux/lsm_audit.h @@ -26,14 +26,15 @@ /* Auxiliary data to use in generating the audit record. */ struct common_audit_data { - char type; -#define LSM_AUDIT_DATA_FS 1 -#define LSM_AUDIT_DATA_NET 2 -#define LSM_AUDIT_DATA_CAP 3 -#define LSM_AUDIT_DATA_IPC 4 -#define LSM_AUDIT_DATA_TASK 5 -#define LSM_AUDIT_DATA_KEY 6 -#define LSM_AUDIT_NO_AUDIT 7 + char type; +#define LSM_AUDIT_DATA_FS 1 +#define LSM_AUDIT_DATA_NET 2 +#define LSM_AUDIT_DATA_CAP 3 +#define LSM_AUDIT_DATA_IPC 4 +#define LSM_AUDIT_DATA_TASK 5 +#define LSM_AUDIT_DATA_KEY 6 +#define LSM_AUDIT_NO_AUDIT 7 +#define LSM_AUDIT_DATA_KMOD 8 struct task_struct *tsk; union { struct { @@ -66,6 +67,7 @@ struct common_audit_data { char *key_desc; } key_struct; #endif + char *kmod_name; } u; /* this union contains LSM specific data */ union { diff --git a/include/linux/mfd/wm831x/regulator.h b/include/linux/mfd/wm831x/regulator.h index f95466343fb2..955d30fc6a27 100644 --- a/include/linux/mfd/wm831x/regulator.h +++ b/include/linux/mfd/wm831x/regulator.h @@ -1212,7 +1212,7 @@ #define WM831X_LDO1_OK_SHIFT 0 /* LDO1_OK */ #define WM831X_LDO1_OK_WIDTH 1 /* LDO1_OK */ -#define WM831X_ISINK_MAX_ISEL 56 -extern int wm831x_isinkv_values[WM831X_ISINK_MAX_ISEL]; +#define WM831X_ISINK_MAX_ISEL 55 +extern int wm831x_isinkv_values[WM831X_ISINK_MAX_ISEL + 1]; #endif diff --git a/include/linux/net.h b/include/linux/net.h index 529a0931711d..d7e26e30c8c2 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -358,6 +358,7 @@ static const struct proto_ops name##_ops = { \ #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> +#include <linux/ratelimit.h> extern struct ratelimit_state net_ratelimit_state; #endif diff --git a/include/linux/of.h b/include/linux/of.h index 7be2d1043c16..e7facd8fbce8 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -17,14 +17,117 @@ */ #include <linux/types.h> #include <linux/bitops.h> +#include <linux/kref.h> #include <linux/mod_devicetable.h> +typedef u32 phandle; +typedef u32 ihandle; + +struct property { + char *name; + int length; + void *value; + struct property *next; + unsigned long _flags; + unsigned int unique_id; +}; + +#if defined(CONFIG_SPARC) +struct of_irq_controller; +#endif + +struct device_node { + const char *name; + const char *type; + phandle node; +#if !defined(CONFIG_SPARC) + phandle linux_phandle; +#endif + char *full_name; + + struct property *properties; + struct property *deadprops; /* removed properties */ + struct device_node *parent; + struct device_node *child; + struct device_node *sibling; + struct device_node *next; /* next device of same type */ + struct device_node *allnext; /* next in list of all nodes */ + struct proc_dir_entry *pde; /* this node's proc directory */ + struct kref kref; + unsigned long _flags; + void *data; +#if defined(CONFIG_SPARC) + char *path_component_name; + unsigned int unique_id; + struct of_irq_controller *irq_trans; +#endif +}; + +static inline int of_node_check_flag(struct device_node *n, unsigned long flag) +{ + return test_bit(flag, &n->_flags); +} + +static inline void of_node_set_flag(struct device_node *n, unsigned long flag) +{ + set_bit(flag, &n->_flags); +} + +static inline void +set_node_proc_entry(struct device_node *dn, struct proc_dir_entry *de) +{ + dn->pde = de; +} + +extern struct device_node *of_find_all_nodes(struct device_node *prev); + +#if defined(CONFIG_SPARC) +/* Dummy ref counting routines - to be implemented later */ +static inline struct device_node *of_node_get(struct device_node *node) +{ + return node; +} +static inline void of_node_put(struct device_node *node) +{ +} + +#else +extern struct device_node *of_node_get(struct device_node *node); +extern void of_node_put(struct device_node *node); +#endif + +/* + * OF address retreival & translation + */ + +/* Helper to read a big number; size is in cells (not bytes) */ +static inline u64 of_read_number(const u32 *cell, int size) +{ + u64 r = 0; + while (size--) + r = (r << 32) | *(cell++); + return r; +} + +/* Like of_read_number, but we want an unsigned long result */ +#ifdef CONFIG_PPC32 +static inline unsigned long of_read_ulong(const u32 *cell, int size) +{ + return cell[size-1]; +} +#else +#define of_read_ulong(cell, size) of_read_number(cell, size) +#endif + #include <asm/prom.h> /* flag descriptions */ #define OF_DYNAMIC 1 /* node and properties were allocated via kmalloc */ #define OF_DETACHED 2 /* node has been detached from the device tree */ +#define OF_IS_DYNAMIC(x) test_bit(OF_DYNAMIC, &x->_flags) +#define OF_MARK_DYNAMIC(x) set_bit(OF_DYNAMIC, &x->_flags) + #define OF_BAD_ADDR ((u64)-1) extern struct device_node *of_find_node_by_name(struct device_node *from, diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h new file mode 100644 index 000000000000..41d432b13553 --- /dev/null +++ b/include/linux/of_fdt.h @@ -0,0 +1,86 @@ +/* + * Definitions for working with the Flattened Device Tree data format + * + * Copyright 2009 Benjamin Herrenschmidt, IBM Corp + * benh@kernel.crashing.org + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + */ + +#ifndef _LINUX_OF_FDT_H +#define _LINUX_OF_FDT_H + +#include <linux/types.h> +#include <linux/init.h> + +/* Definitions used by the flattened device tree */ +#define OF_DT_HEADER 0xd00dfeed /* marker */ +#define OF_DT_BEGIN_NODE 0x1 /* Start of node, full name */ +#define OF_DT_END_NODE 0x2 /* End node */ +#define OF_DT_PROP 0x3 /* Property: name off, size, + * content */ +#define OF_DT_NOP 0x4 /* nop */ +#define OF_DT_END 0x9 + +#define OF_DT_VERSION 0x10 + +#ifndef __ASSEMBLY__ +/* + * This is what gets passed to the kernel by prom_init or kexec + * + * The dt struct contains the device tree structure, full pathes and + * property contents. The dt strings contain a separate block with just + * the strings for the property names, and is fully page aligned and + * self contained in a page, so that it can be kept around by the kernel, + * each property name appears only once in this page (cheap compression) + * + * the mem_rsvmap contains a map of reserved ranges of physical memory, + * passing it here instead of in the device-tree itself greatly simplifies + * the job of everybody. It's just a list of u64 pairs (base/size) that + * ends when size is 0 + */ +struct boot_param_header { + u32 magic; /* magic word OF_DT_HEADER */ + u32 totalsize; /* total size of DT block */ + u32 off_dt_struct; /* offset to structure */ + u32 off_dt_strings; /* offset to strings */ + u32 off_mem_rsvmap; /* offset to memory reserve map */ + u32 version; /* format version */ + u32 last_comp_version; /* last compatible version */ + /* version 2 fields below */ + u32 boot_cpuid_phys; /* Physical CPU id we're booting on */ + /* version 3 fields below */ + u32 dt_strings_size; /* size of the DT strings block */ + /* version 17 fields below */ + u32 dt_struct_size; /* size of the DT structure block */ +}; + +/* For scanning the flat device-tree at boot time */ +extern int __init of_scan_flat_dt(int (*it)(unsigned long node, + const char *uname, int depth, + void *data), + void *data); +extern void __init *of_get_flat_dt_prop(unsigned long node, const char *name, + unsigned long *size); +extern int __init of_flat_dt_is_compatible(unsigned long node, + const char *name); +extern unsigned long __init of_get_flat_dt_root(void); + +/* Other Prototypes */ +extern void finish_device_tree(void); +extern void unflatten_device_tree(void); +extern void early_init_devtree(void *); +extern int machine_is_compatible(const char *compat); +extern void print_properties(struct device_node *node); +extern int prom_n_intr_cells(struct device_node* np); +extern void prom_get_irq_senses(unsigned char *senses, int off, int max); +extern int prom_add_property(struct device_node* np, struct property* prop); +extern int prom_remove_property(struct device_node *np, struct property *prop); +extern int prom_update_property(struct device_node *np, + struct property *newprop, + struct property *oldprop); + +#endif /* __ASSEMBLY__ */ +#endif /* _LINUX_OF_FDT_H */ diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 84cf1f3b7838..daecca3c8300 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1633,6 +1633,8 @@ #define PCI_DEVICE_ID_O2_6730 0x673a #define PCI_DEVICE_ID_O2_6832 0x6832 #define PCI_DEVICE_ID_O2_6836 0x6836 +#define PCI_DEVICE_ID_O2_6812 0x6872 +#define PCI_DEVICE_ID_O2_6933 0x6933 #define PCI_VENDOR_ID_3DFX 0x121a #define PCI_DEVICE_ID_3DFX_VOODOO 0x0001 diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h index 7b7fbf433cff..e3fb25606706 100644 --- a/include/linux/perf_counter.h +++ b/include/linux/perf_counter.h @@ -106,6 +106,8 @@ enum perf_sw_ids { PERF_COUNT_SW_CPU_MIGRATIONS = 4, PERF_COUNT_SW_PAGE_FAULTS_MIN = 5, PERF_COUNT_SW_PAGE_FAULTS_MAJ = 6, + PERF_COUNT_SW_ALIGNMENT_FAULTS = 7, + PERF_COUNT_SW_EMULATION_FAULTS = 8, PERF_COUNT_SW_MAX, /* non-ABI */ }; @@ -225,6 +227,7 @@ struct perf_counter_attr { #define PERF_COUNTER_IOC_RESET _IO ('$', 3) #define PERF_COUNTER_IOC_PERIOD _IOW('$', 4, u64) #define PERF_COUNTER_IOC_SET_OUTPUT _IO ('$', 5) +#define PERF_COUNTER_IOC_SET_FILTER _IOW('$', 6, char *) enum perf_counter_ioc_flags { PERF_IOC_FLAG_GROUP = 1U << 0, diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 9e7012689a84..43adbd7f0010 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -18,6 +18,10 @@ #include <linux/ioctl.h> #include <asm/byteorder.h> +#ifdef CONFIG_HAVE_HW_BREAKPOINT +#include <asm/hw_breakpoint.h> +#endif + /* * User-space ABI bits: */ @@ -31,6 +35,7 @@ enum perf_type_id { PERF_TYPE_TRACEPOINT = 2, PERF_TYPE_HW_CACHE = 3, PERF_TYPE_RAW = 4, + PERF_TYPE_BREAKPOINT = 5, PERF_TYPE_MAX, /* non-ABI */ }; @@ -102,6 +107,8 @@ enum perf_sw_ids { PERF_COUNT_SW_CPU_MIGRATIONS = 4, PERF_COUNT_SW_PAGE_FAULTS_MIN = 5, PERF_COUNT_SW_PAGE_FAULTS_MAJ = 6, + PERF_COUNT_SW_ALIGNMENT_FAULTS = 7, + PERF_COUNT_SW_EMULATION_FAULTS = 8, PERF_COUNT_SW_MAX, /* non-ABI */ }; @@ -207,6 +214,15 @@ struct perf_event_attr { __u32 wakeup_events; /* wakeup every n events */ __u32 wakeup_watermark; /* bytes before wakeup */ }; + + union { + struct { /* Hardware breakpoint info */ + __u64 bp_addr; + __u32 bp_type; + __u32 bp_len; + }; + }; + __u32 __reserved_2; __u64 __reserved_3; @@ -219,8 +235,9 @@ struct perf_event_attr { #define PERF_EVENT_IOC_DISABLE _IO ('$', 1) #define PERF_EVENT_IOC_REFRESH _IO ('$', 2) #define PERF_EVENT_IOC_RESET _IO ('$', 3) -#define PERF_EVENT_IOC_PERIOD _IOW('$', 4, u64) +#define PERF_EVENT_IOC_PERIOD _IOW('$', 4, __u64) #define PERF_EVENT_IOC_SET_OUTPUT _IO ('$', 5) +#define PERF_EVENT_IOC_SET_FILTER _IOW('$', 6, char *) enum perf_event_ioc_flags { PERF_IOC_FLAG_GROUP = 1U << 0, @@ -475,6 +492,11 @@ struct hw_perf_event { s64 remaining; struct hrtimer hrtimer; }; +#ifdef CONFIG_HAVE_HW_BREAKPOINT + union { /* breakpoint */ + struct arch_hw_breakpoint info; + }; +#endif }; atomic64_t prev_count; u64 sample_period; @@ -543,6 +565,10 @@ struct perf_pending_entry { void (*func)(struct perf_pending_entry *); }; +typedef void (*perf_callback_t)(struct perf_event *, void *); + +struct perf_sample_data; + /** * struct perf_event - performance event kernel representation: */ @@ -585,7 +611,7 @@ struct perf_event { u64 tstamp_running; u64 tstamp_stopped; - struct perf_event_attr attr; + struct perf_event_attr attr; struct hw_perf_event hw; struct perf_event_context *ctx; @@ -633,7 +659,20 @@ struct perf_event { struct pid_namespace *ns; u64 id; + + void (*overflow_handler)(struct perf_event *event, + int nmi, struct perf_sample_data *data, + struct pt_regs *regs); + +#ifdef CONFIG_EVENT_PROFILE + struct event_filter *filter; #endif + + perf_callback_t callback; + + perf_callback_t event_callback; + +#endif /* CONFIG_PERF_EVENTS */ }; /** @@ -706,7 +745,6 @@ struct perf_output_handle { int nmi; int sample; int locked; - unsigned long flags; }; #ifdef CONFIG_PERF_EVENTS @@ -738,6 +776,14 @@ extern int hw_perf_group_sched_in(struct perf_event *group_leader, struct perf_cpu_context *cpuctx, struct perf_event_context *ctx, int cpu); extern void perf_event_update_userpage(struct perf_event *event); +extern int perf_event_release_kernel(struct perf_event *event); +extern struct perf_event * +perf_event_create_kernel_counter(struct perf_event_attr *attr, + int cpu, + pid_t pid, + perf_callback_t callback); +extern u64 perf_event_read_value(struct perf_event *event, + u64 *enabled, u64 *running); struct perf_sample_data { u64 type; @@ -814,6 +860,7 @@ extern int sysctl_perf_event_sample_rate; extern void perf_event_init(void); extern void perf_tp_event(int event_id, u64 addr, u64 count, void *record, int entry_size); +extern void perf_bp_event(struct perf_event *event, void *data); #ifndef perf_misc_flags #define perf_misc_flags(regs) (user_mode(regs) ? PERF_RECORD_MISC_USER : \ @@ -827,6 +874,8 @@ extern int perf_output_begin(struct perf_output_handle *handle, extern void perf_output_end(struct perf_output_handle *handle); extern void perf_output_copy(struct perf_output_handle *handle, const void *buf, unsigned int len); +extern int perf_swevent_get_recursion_context(void); +extern void perf_swevent_put_recursion_context(int rctx); #else static inline void perf_event_task_sched_in(struct task_struct *task, int cpu) { } @@ -848,11 +897,15 @@ static inline int perf_event_task_enable(void) { return -EINVAL; } static inline void perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr) { } +static inline void +perf_bp_event(struct perf_event *event, void *data) { } static inline void perf_event_mmap(struct vm_area_struct *vma) { } static inline void perf_event_comm(struct task_struct *tsk) { } static inline void perf_event_fork(struct task_struct *tsk) { } static inline void perf_event_init(void) { } +static inline int perf_swevent_get_recursion_context(void) { return -1; } +static inline void perf_swevent_put_recursion_context(int rctx) { } #endif diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 065a3652a3ea..67608161df6b 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -147,6 +147,20 @@ static inline void forget_cached_acl(struct inode *inode, int type) if (old != ACL_NOT_CACHED) posix_acl_release(old); } + +static inline void forget_all_cached_acls(struct inode *inode) +{ + struct posix_acl *old_access, *old_default; + spin_lock(&inode->i_lock); + old_access = inode->i_acl; + old_default = inode->i_default_acl; + inode->i_acl = inode->i_default_acl = ACL_NOT_CACHED; + spin_unlock(&inode->i_lock); + if (old_access != ACL_NOT_CACHED) + posix_acl_release(old_access); + if (old_default != ACL_NOT_CACHED) + posix_acl_release(old_default); +} #endif static inline void cache_no_acl(struct inode *inode) diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 72b1a10a59b6..2e681d9555bd 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -105,6 +105,11 @@ struct preempt_notifier; * @sched_out: we've just been preempted * notifier: struct preempt_notifier for the task being preempted * next: the task that's kicking us out + * + * Please note that sched_in and out are called under different + * contexts. sched_out is called with rq lock held and irq disabled + * while sched_in is called without rq lock and irq enabled. This + * difference is intentional and depended upon by its users. */ struct preempt_ops { void (*sched_in)(struct preempt_notifier *notifier, int cpu); diff --git a/include/linux/quota.h b/include/linux/quota.h index 78c48895b12a..ce9a9b2e5cd4 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -376,6 +376,17 @@ static inline unsigned int dquot_generic_flag(unsigned int flags, int type) return flags >> _DQUOT_STATE_FLAGS; } +#ifdef CONFIG_QUOTA_NETLINK_INTERFACE +extern void quota_send_warning(short type, unsigned int id, dev_t dev, + const char warntype); +#else +static inline void quota_send_warning(short type, unsigned int id, dev_t dev, + const char warntype) +{ + return; +} +#endif /* CONFIG_QUOTA_NETLINK_INTERFACE */ + struct quota_info { unsigned int flags; /* Flags for diskquotas on this device */ struct mutex dqio_mutex; /* lock device while I/O in progress */ diff --git a/include/linux/ratelimit.h b/include/linux/ratelimit.h index 00044b856453..668cf1bef030 100644 --- a/include/linux/ratelimit.h +++ b/include/linux/ratelimit.h @@ -1,20 +1,31 @@ #ifndef _LINUX_RATELIMIT_H #define _LINUX_RATELIMIT_H + #include <linux/param.h> +#include <linux/spinlock_types.h> -#define DEFAULT_RATELIMIT_INTERVAL (5 * HZ) -#define DEFAULT_RATELIMIT_BURST 10 +#define DEFAULT_RATELIMIT_INTERVAL (5 * HZ) +#define DEFAULT_RATELIMIT_BURST 10 struct ratelimit_state { - int interval; - int burst; - int printed; - int missed; - unsigned long begin; + spinlock_t lock; /* protect the state */ + + int interval; + int burst; + int printed; + int missed; + unsigned long begin; }; -#define DEFINE_RATELIMIT_STATE(name, interval, burst) \ - struct ratelimit_state name = {interval, burst,} +#define DEFINE_RATELIMIT_STATE(name, interval_init, burst_init) \ + \ + struct ratelimit_state name = { \ + .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ + .interval = interval_init, \ + .burst = burst_init, \ + } + +extern int ___ratelimit(struct ratelimit_state *rs, const char *func); +#define __ratelimit(state) ___ratelimit(state, __func__) -extern int __ratelimit(struct ratelimit_state *rs); -#endif +#endif /* _LINUX_RATELIMIT_H */ diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 3ebd0b7bcb08..24440f4bf476 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -52,11 +52,6 @@ struct rcu_head { }; /* Exported common interfaces */ -#ifdef CONFIG_TREE_PREEMPT_RCU -extern void synchronize_rcu(void); -#else /* #ifdef CONFIG_TREE_PREEMPT_RCU */ -#define synchronize_rcu synchronize_sched -#endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */ extern void synchronize_rcu_bh(void); extern void synchronize_sched(void); extern void rcu_barrier(void); @@ -67,12 +62,11 @@ extern int sched_expedited_torture_stats(char *page); /* Internal to kernel */ extern void rcu_init(void); -extern void rcu_scheduler_starting(void); -extern int rcu_needs_cpu(int cpu); -extern int rcu_scheduler_active; #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU) #include <linux/rcutree.h> +#elif defined(CONFIG_TINY_RCU) +#include <linux/rcutiny.h> #else #error "Unknown RCU implementation specified to kernel configuration" #endif diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h new file mode 100644 index 000000000000..c4ba9a78721e --- /dev/null +++ b/include/linux/rcutiny.h @@ -0,0 +1,104 @@ +/* + * Read-Copy Update mechanism for mutual exclusion, the Bloatwatch edition. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright IBM Corporation, 2008 + * + * Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com> + * + * For detailed explanation of Read-Copy Update mechanism see - + * Documentation/RCU + */ +#ifndef __LINUX_TINY_H +#define __LINUX_TINY_H + +#include <linux/cache.h> + +void rcu_sched_qs(int cpu); +void rcu_bh_qs(int cpu); + +#define __rcu_read_lock() preempt_disable() +#define __rcu_read_unlock() preempt_enable() +#define __rcu_read_lock_bh() local_bh_disable() +#define __rcu_read_unlock_bh() local_bh_enable() +#define call_rcu_sched call_rcu + +#define rcu_init_sched() do { } while (0) +extern void rcu_check_callbacks(int cpu, int user); + +static inline int rcu_needs_cpu(int cpu) +{ + return 0; +} + +/* + * Return the number of grace periods. + */ +static inline long rcu_batches_completed(void) +{ + return 0; +} + +/* + * Return the number of bottom-half grace periods. + */ +static inline long rcu_batches_completed_bh(void) +{ + return 0; +} + +extern int rcu_expedited_torture_stats(char *page); + +#define synchronize_rcu synchronize_sched + +static inline void synchronize_rcu_expedited(void) +{ + synchronize_sched(); +} + +static inline void synchronize_rcu_bh_expedited(void) +{ + synchronize_sched(); +} + +struct notifier_block; + +#ifdef CONFIG_NO_HZ + +extern void rcu_enter_nohz(void); +extern void rcu_exit_nohz(void); + +#else /* #ifdef CONFIG_NO_HZ */ + +static inline void rcu_enter_nohz(void) +{ +} + +static inline void rcu_exit_nohz(void) +{ +} + +#endif /* #else #ifdef CONFIG_NO_HZ */ + +static inline void rcu_scheduler_starting(void) +{ +} + +static inline void exit_rcu(void) +{ +} + +#endif /* __LINUX_RCUTINY_H */ diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 9642c6bcb399..c93eee5911b0 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -34,15 +34,15 @@ struct notifier_block; extern void rcu_sched_qs(int cpu); extern void rcu_bh_qs(int cpu); -extern int rcu_cpu_notify(struct notifier_block *self, - unsigned long action, void *hcpu); extern int rcu_needs_cpu(int cpu); +extern void rcu_scheduler_starting(void); extern int rcu_expedited_torture_stats(char *page); #ifdef CONFIG_TREE_PREEMPT_RCU extern void __rcu_read_lock(void); extern void __rcu_read_unlock(void); +extern void synchronize_rcu(void); extern void exit_rcu(void); #else /* #ifdef CONFIG_TREE_PREEMPT_RCU */ @@ -57,7 +57,7 @@ static inline void __rcu_read_unlock(void) preempt_enable(); } -#define __synchronize_sched() synchronize_rcu() +#define synchronize_rcu synchronize_sched static inline void exit_rcu(void) { @@ -83,7 +83,6 @@ static inline void synchronize_rcu_bh_expedited(void) synchronize_sched_expedited(); } -extern void __rcu_init(void); extern void rcu_check_callbacks(int cpu, int user); extern long rcu_batches_completed(void); diff --git a/include/linux/sched.h b/include/linux/sched.h index 75e6e60bf583..89115ec7d43f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -145,7 +145,6 @@ extern unsigned long this_cpu_load(void); extern void calc_global_load(void); -extern u64 cpu_nr_migrations(int cpu); extern unsigned long get_parent_ip(unsigned long addr); @@ -171,8 +170,6 @@ print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) } #endif -extern unsigned long long time_sync_thresh; - /* * Task state bitmask. NOTE! These bits are also * encoded in fs/proc/array.c: get_task_state(). @@ -349,7 +346,6 @@ extern signed long schedule_timeout(signed long timeout); extern signed long schedule_timeout_interruptible(signed long timeout); extern signed long schedule_timeout_killable(signed long timeout); extern signed long schedule_timeout_uninterruptible(signed long timeout); -asmlinkage void __schedule(void); asmlinkage void schedule(void); extern int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner); @@ -628,6 +624,9 @@ struct signal_struct { cputime_t utime, stime, cutime, cstime; cputime_t gtime; cputime_t cgtime; +#ifndef CONFIG_VIRT_CPU_ACCOUNTING + cputime_t prev_utime, prev_stime; +#endif unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt; unsigned long inblock, oublock, cinblock, coublock; @@ -1013,9 +1012,13 @@ static inline struct cpumask *sched_domain_span(struct sched_domain *sd) return to_cpumask(sd->span); } -extern void partition_sched_domains(int ndoms_new, struct cpumask *doms_new, +extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], struct sched_domain_attr *dattr_new); +/* Allocate an array of sched domains, for partition_sched_domains(). */ +cpumask_var_t *alloc_sched_domains(unsigned int ndoms); +void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms); + /* Test a flag in parent sched domain */ static inline int test_sd_parent(struct sched_domain *sd, int flag) { @@ -1033,7 +1036,7 @@ unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu); struct sched_domain_attr; static inline void -partition_sched_domains(int ndoms_new, struct cpumask *doms_new, +partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], struct sched_domain_attr *dattr_new) { } @@ -1331,7 +1334,9 @@ struct task_struct { cputime_t utime, stime, utimescaled, stimescaled; cputime_t gtime; +#ifndef CONFIG_VIRT_CPU_ACCOUNTING cputime_t prev_utime, prev_stime; +#endif unsigned long nvcsw, nivcsw; /* context switch counts */ struct timespec start_time; /* monotonic time */ struct timespec real_start_time; /* boot based time */ @@ -1421,17 +1426,17 @@ struct task_struct { #endif #ifdef CONFIG_TRACE_IRQFLAGS unsigned int irq_events; - int hardirqs_enabled; unsigned long hardirq_enable_ip; - unsigned int hardirq_enable_event; unsigned long hardirq_disable_ip; + unsigned int hardirq_enable_event; unsigned int hardirq_disable_event; - int softirqs_enabled; + int hardirqs_enabled; + int hardirq_context; unsigned long softirq_disable_ip; - unsigned int softirq_disable_event; unsigned long softirq_enable_ip; + unsigned int softirq_disable_event; unsigned int softirq_enable_event; - int hardirq_context; + int softirqs_enabled; int softirq_context; #endif #ifdef CONFIG_LOCKDEP @@ -1720,9 +1725,8 @@ static inline void put_task_struct(struct task_struct *t) __put_task_struct(t); } -extern cputime_t task_utime(struct task_struct *p); -extern cputime_t task_stime(struct task_struct *p); -extern cputime_t task_gtime(struct task_struct *p); +extern void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st); +extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st); /* * Per process flags @@ -2086,11 +2090,18 @@ static inline int is_si_special(const struct siginfo *info) return info <= SEND_SIG_FORCED; } -/* True if we are on the alternate signal stack. */ - +/* + * True if we are on the alternate signal stack. + */ static inline int on_sig_stack(unsigned long sp) { - return (sp - current->sas_ss_sp < current->sas_ss_size); +#ifdef CONFIG_STACK_GROWSUP + return sp >= current->sas_ss_sp && + sp - current->sas_ss_sp < current->sas_ss_size; +#else + return sp > current->sas_ss_sp && + sp - current->sas_ss_sp <= current->sas_ss_size; +#endif } static inline int sas_ss_flags(unsigned long sp) diff --git a/include/linux/securebits.h b/include/linux/securebits.h index d2c5ed845bcc..33406174cbe8 100644 --- a/include/linux/securebits.h +++ b/include/linux/securebits.h @@ -1,6 +1,15 @@ #ifndef _LINUX_SECUREBITS_H #define _LINUX_SECUREBITS_H 1 +/* Each securesetting is implemented using two bits. One bit specifies + whether the setting is on or off. The other bit specify whether the + setting is locked or not. A setting which is locked cannot be + changed from user-level. */ +#define issecure_mask(X) (1 << (X)) +#ifdef __KERNEL__ +#define issecure(X) (issecure_mask(X) & current_cred_xxx(securebits)) +#endif + #define SECUREBITS_DEFAULT 0x00000000 /* When set UID 0 has no special privileges. When unset, we support @@ -12,6 +21,9 @@ #define SECURE_NOROOT 0 #define SECURE_NOROOT_LOCKED 1 /* make bit-0 immutable */ +#define SECBIT_NOROOT (issecure_mask(SECURE_NOROOT)) +#define SECBIT_NOROOT_LOCKED (issecure_mask(SECURE_NOROOT_LOCKED)) + /* When set, setuid to/from uid 0 does not trigger capability-"fixup". When unset, to provide compatiblility with old programs relying on set*uid to gain/lose privilege, transitions to/from uid 0 cause @@ -19,6 +31,10 @@ #define SECURE_NO_SETUID_FIXUP 2 #define SECURE_NO_SETUID_FIXUP_LOCKED 3 /* make bit-2 immutable */ +#define SECBIT_NO_SETUID_FIXUP (issecure_mask(SECURE_NO_SETUID_FIXUP)) +#define SECBIT_NO_SETUID_FIXUP_LOCKED \ + (issecure_mask(SECURE_NO_SETUID_FIXUP_LOCKED)) + /* When set, a process can retain its capabilities even after transitioning to a non-root user (the set-uid fixup suppressed by bit 2). Bit-4 is cleared when a process calls exec(); setting both @@ -27,12 +43,8 @@ #define SECURE_KEEP_CAPS 4 #define SECURE_KEEP_CAPS_LOCKED 5 /* make bit-4 immutable */ -/* Each securesetting is implemented using two bits. One bit specifies - whether the setting is on or off. The other bit specify whether the - setting is locked or not. A setting which is locked cannot be - changed from user-level. */ -#define issecure_mask(X) (1 << (X)) -#define issecure(X) (issecure_mask(X) & current_cred_xxx(securebits)) +#define SECBIT_KEEP_CAPS (issecure_mask(SECURE_KEEP_CAPS)) +#define SECBIT_KEEP_CAPS_LOCKED (issecure_mask(SECURE_KEEP_CAPS_LOCKED)) #define SECURE_ALL_BITS (issecure_mask(SECURE_NOROOT) | \ issecure_mask(SECURE_NO_SETUID_FIXUP) | \ diff --git a/include/linux/security.h b/include/linux/security.h index 239e40d0450b..466cbadbd1ef 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -447,6 +447,22 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * @new_dir contains the path structure for parent of the new link. * @new_dentry contains the dentry structure of the new link. * Return 0 if permission is granted. + * @path_chmod: + * Check for permission to change DAC's permission of a file or directory. + * @dentry contains the dentry structure. + * @mnt contains the vfsmnt structure. + * @mode contains DAC's mode. + * Return 0 if permission is granted. + * @path_chown: + * Check for permission to change owner/group of a file or directory. + * @path contains the path structure. + * @uid contains new owner's ID. + * @gid contains new group's ID. + * Return 0 if permission is granted. + * @path_chroot: + * Check for permission to change root directory. + * @path contains the path structure. + * Return 0 if permission is granted. * @inode_readlink: * Check the permission to read the symbolic link. * @dentry contains the dentry structure for the file link. @@ -690,6 +706,7 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * @kernel_module_request: * Ability to trigger the kernel to automatically upcall to userspace for * userspace to load a kernel module with the given name. + * @kmod_name name of the module requested by the kernel * Return 0 if successful. * @task_setuid: * Check permission before setting one or more of the user identity @@ -1488,6 +1505,10 @@ struct security_operations { struct dentry *new_dentry); int (*path_rename) (struct path *old_dir, struct dentry *old_dentry, struct path *new_dir, struct dentry *new_dentry); + int (*path_chmod) (struct dentry *dentry, struct vfsmount *mnt, + mode_t mode); + int (*path_chown) (struct path *path, uid_t uid, gid_t gid); + int (*path_chroot) (struct path *path); #endif int (*inode_alloc_security) (struct inode *inode); @@ -1557,7 +1578,7 @@ struct security_operations { void (*cred_transfer)(struct cred *new, const struct cred *old); int (*kernel_act_as)(struct cred *new, u32 secid); int (*kernel_create_files_as)(struct cred *new, struct inode *inode); - int (*kernel_module_request)(void); + int (*kernel_module_request)(char *kmod_name); int (*task_setuid) (uid_t id0, uid_t id1, uid_t id2, int flags); int (*task_fix_setuid) (struct cred *new, const struct cred *old, int flags); @@ -1822,7 +1843,7 @@ void security_commit_creds(struct cred *new, const struct cred *old); void security_transfer_creds(struct cred *new, const struct cred *old); int security_kernel_act_as(struct cred *new, u32 secid); int security_kernel_create_files_as(struct cred *new, struct inode *inode); -int security_kernel_module_request(void); +int security_kernel_module_request(char *kmod_name); int security_task_setuid(uid_t id0, uid_t id1, uid_t id2, int flags); int security_task_fix_setuid(struct cred *new, const struct cred *old, int flags); @@ -2387,7 +2408,7 @@ static inline int security_kernel_create_files_as(struct cred *cred, return 0; } -static inline int security_kernel_module_request(void) +static inline int security_kernel_module_request(char *kmod_name) { return 0; } @@ -2952,6 +2973,10 @@ int security_path_link(struct dentry *old_dentry, struct path *new_dir, struct dentry *new_dentry); int security_path_rename(struct path *old_dir, struct dentry *old_dentry, struct path *new_dir, struct dentry *new_dentry); +int security_path_chmod(struct dentry *dentry, struct vfsmount *mnt, + mode_t mode); +int security_path_chown(struct path *path, uid_t uid, gid_t gid); +int security_path_chroot(struct path *path); #else /* CONFIG_SECURITY_PATH */ static inline int security_path_unlink(struct path *dir, struct dentry *dentry) { @@ -3001,6 +3026,23 @@ static inline int security_path_rename(struct path *old_dir, { return 0; } + +static inline int security_path_chmod(struct dentry *dentry, + struct vfsmount *mnt, + mode_t mode) +{ + return 0; +} + +static inline int security_path_chown(struct path *path, uid_t uid, gid_t gid) +{ + return 0; +} + +static inline int security_path_chroot(struct path *path) +{ + return 0; +} #endif /* CONFIG_SECURITY_PATH */ #ifdef CONFIG_KEYS diff --git a/include/linux/slow-work.h b/include/linux/slow-work.h index b65c8881f07a..13337bf6c3f5 100644 --- a/include/linux/slow-work.h +++ b/include/linux/slow-work.h @@ -17,13 +17,20 @@ #ifdef CONFIG_SLOW_WORK #include <linux/sysctl.h> +#include <linux/timer.h> struct slow_work; +#ifdef CONFIG_SLOW_WORK_DEBUG +struct seq_file; +#endif /* * The operations used to support slow work items */ struct slow_work_ops { + /* owner */ + struct module *owner; + /* get a ref on a work item * - return 0 if successful, -ve if not */ @@ -34,6 +41,11 @@ struct slow_work_ops { /* execute a work item */ void (*execute)(struct slow_work *work); + +#ifdef CONFIG_SLOW_WORK_DEBUG + /* describe a work item for debugfs */ + void (*desc)(struct slow_work *work, struct seq_file *m); +#endif }; /* @@ -42,13 +54,24 @@ struct slow_work_ops { * queued */ struct slow_work { + struct module *owner; /* the owning module */ unsigned long flags; #define SLOW_WORK_PENDING 0 /* item pending (further) execution */ #define SLOW_WORK_EXECUTING 1 /* item currently executing */ #define SLOW_WORK_ENQ_DEFERRED 2 /* item enqueue deferred */ #define SLOW_WORK_VERY_SLOW 3 /* item is very slow */ +#define SLOW_WORK_CANCELLING 4 /* item is being cancelled, don't enqueue */ +#define SLOW_WORK_DELAYED 5 /* item is struct delayed_slow_work with active timer */ const struct slow_work_ops *ops; /* operations table for this item */ struct list_head link; /* link in queue */ +#ifdef CONFIG_SLOW_WORK_DEBUG + struct timespec mark; /* jiffies at which queued or exec begun */ +#endif +}; + +struct delayed_slow_work { + struct slow_work work; + struct timer_list timer; }; /** @@ -67,6 +90,20 @@ static inline void slow_work_init(struct slow_work *work, } /** + * slow_work_init - Initialise a delayed slow work item + * @work: The work item to initialise + * @ops: The operations to use to handle the slow work item + * + * Initialise a delayed slow work item. + */ +static inline void delayed_slow_work_init(struct delayed_slow_work *dwork, + const struct slow_work_ops *ops) +{ + init_timer(&dwork->timer); + slow_work_init(&dwork->work, ops); +} + +/** * vslow_work_init - Initialise a very slow work item * @work: The work item to initialise * @ops: The operations to use to handle the slow work item @@ -83,9 +120,40 @@ static inline void vslow_work_init(struct slow_work *work, INIT_LIST_HEAD(&work->link); } +/** + * slow_work_is_queued - Determine if a slow work item is on the work queue + * work: The work item to test + * + * Determine if the specified slow-work item is on the work queue. This + * returns true if it is actually on the queue. + * + * If the item is executing and has been marked for requeue when execution + * finishes, then false will be returned. + * + * Anyone wishing to wait for completion of execution can wait on the + * SLOW_WORK_EXECUTING bit. + */ +static inline bool slow_work_is_queued(struct slow_work *work) +{ + unsigned long flags = work->flags; + return flags & SLOW_WORK_PENDING && !(flags & SLOW_WORK_EXECUTING); +} + extern int slow_work_enqueue(struct slow_work *work); -extern int slow_work_register_user(void); -extern void slow_work_unregister_user(void); +extern void slow_work_cancel(struct slow_work *work); +extern int slow_work_register_user(struct module *owner); +extern void slow_work_unregister_user(struct module *owner); + +extern int delayed_slow_work_enqueue(struct delayed_slow_work *dwork, + unsigned long delay); + +static inline void delayed_slow_work_cancel(struct delayed_slow_work *dwork) +{ + slow_work_cancel(&dwork->work); +} + +extern bool slow_work_sleep_till_thread_needed(struct slow_work *work, + signed long *_timeout); #ifdef CONFIG_SYSCTL extern ctl_table slow_work_sysctls[]; diff --git a/include/linux/smp.h b/include/linux/smp.h index 39c64bae776d..7a0570e6a596 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -76,6 +76,9 @@ void smp_call_function_many(const struct cpumask *mask, void __smp_call_function_single(int cpuid, struct call_single_data *data, int wait); +int smp_call_function_any(const struct cpumask *mask, + void (*func)(void *info), void *info, int wait); + /* * Generic and arch helpers */ @@ -137,9 +140,15 @@ static inline void smp_send_reschedule(int cpu) { } #define smp_prepare_boot_cpu() do {} while (0) #define smp_call_function_many(mask, func, info, wait) \ (up_smp_call_function(func, info)) -static inline void init_call_single_data(void) +static inline void init_call_single_data(void) { } + +static inline int +smp_call_function_any(const struct cpumask *mask, void (*func)(void *info), + void *info, int wait) { + return smp_call_function_single(0, func, info, wait); } + #endif /* !SMP */ /* diff --git a/include/linux/smp_lock.h b/include/linux/smp_lock.h index 813be59bf345..2ea1dd1ba21c 100644 --- a/include/linux/smp_lock.h +++ b/include/linux/smp_lock.h @@ -24,8 +24,21 @@ static inline int reacquire_kernel_lock(struct task_struct *task) return 0; } -extern void __lockfunc lock_kernel(void) __acquires(kernel_lock); -extern void __lockfunc unlock_kernel(void) __releases(kernel_lock); +extern void __lockfunc +_lock_kernel(const char *func, const char *file, int line) +__acquires(kernel_lock); + +extern void __lockfunc +_unlock_kernel(const char *func, const char *file, int line) +__releases(kernel_lock); + +#define lock_kernel() do { \ + _lock_kernel(__func__, __FILE__, __LINE__); \ +} while (0) + +#define unlock_kernel() do { \ + _unlock_kernel(__func__, __FILE__, __LINE__); \ +} while (0) /* * Various legacy drivers don't really need the BKL in a specific @@ -41,8 +54,8 @@ static inline void cycle_kernel_lock(void) #else -#define lock_kernel() do { } while(0) -#define unlock_kernel() do { } while(0) +#define lock_kernel() +#define unlock_kernel() #define release_kernel_lock(task) do { } while(0) #define cycle_kernel_lock() do { } while(0) #define reacquire_kernel_lock(task) 0 diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index f0ca7a7a1757..71dccfeb0d88 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -79,8 +79,6 @@ */ #include <linux/spinlock_types.h> -extern int __lockfunc generic__raw_read_trylock(raw_rwlock_t *lock); - /* * Pull the __raw*() functions/declarations (UP-nondebug doesnt need them): */ @@ -102,7 +100,7 @@ do { \ #else # define spin_lock_init(lock) \ - do { *(lock) = SPIN_LOCK_UNLOCKED; } while (0) + do { *(lock) = __SPIN_LOCK_UNLOCKED(lock); } while (0) #endif #ifdef CONFIG_DEBUG_SPINLOCK @@ -116,7 +114,7 @@ do { \ } while (0) #else # define rwlock_init(lock) \ - do { *(lock) = RW_LOCK_UNLOCKED; } while (0) + do { *(lock) = __RW_LOCK_UNLOCKED(lock); } while (0) #endif #define spin_is_locked(lock) __raw_spin_is_locked(&(lock)->raw_lock) diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h index 7a7e18fc2415..8264a7f459bc 100644 --- a/include/linux/spinlock_api_smp.h +++ b/include/linux/spinlock_api_smp.h @@ -60,137 +60,118 @@ void __lockfunc _read_unlock_irqrestore(rwlock_t *lock, unsigned long flags) void __lockfunc _write_unlock_irqrestore(rwlock_t *lock, unsigned long flags) __releases(lock); -/* - * We inline the unlock functions in the nondebug case: - */ -#if !defined(CONFIG_DEBUG_SPINLOCK) && !defined(CONFIG_PREEMPT) -#define __always_inline__spin_unlock -#define __always_inline__read_unlock -#define __always_inline__write_unlock -#define __always_inline__spin_unlock_irq -#define __always_inline__read_unlock_irq -#define __always_inline__write_unlock_irq -#endif - -#ifndef CONFIG_DEBUG_SPINLOCK -#ifndef CONFIG_GENERIC_LOCKBREAK - -#ifdef __always_inline__spin_lock +#ifdef CONFIG_INLINE_SPIN_LOCK #define _spin_lock(lock) __spin_lock(lock) #endif -#ifdef __always_inline__read_lock +#ifdef CONFIG_INLINE_READ_LOCK #define _read_lock(lock) __read_lock(lock) #endif -#ifdef __always_inline__write_lock +#ifdef CONFIG_INLINE_WRITE_LOCK #define _write_lock(lock) __write_lock(lock) #endif -#ifdef __always_inline__spin_lock_bh +#ifdef CONFIG_INLINE_SPIN_LOCK_BH #define _spin_lock_bh(lock) __spin_lock_bh(lock) #endif -#ifdef __always_inline__read_lock_bh +#ifdef CONFIG_INLINE_READ_LOCK_BH #define _read_lock_bh(lock) __read_lock_bh(lock) #endif -#ifdef __always_inline__write_lock_bh +#ifdef CONFIG_INLINE_WRITE_LOCK_BH #define _write_lock_bh(lock) __write_lock_bh(lock) #endif -#ifdef __always_inline__spin_lock_irq +#ifdef CONFIG_INLINE_SPIN_LOCK_IRQ #define _spin_lock_irq(lock) __spin_lock_irq(lock) #endif -#ifdef __always_inline__read_lock_irq +#ifdef CONFIG_INLINE_READ_LOCK_IRQ #define _read_lock_irq(lock) __read_lock_irq(lock) #endif -#ifdef __always_inline__write_lock_irq +#ifdef CONFIG_INLINE_WRITE_LOCK_IRQ #define _write_lock_irq(lock) __write_lock_irq(lock) #endif -#ifdef __always_inline__spin_lock_irqsave +#ifdef CONFIG_INLINE_SPIN_LOCK_IRQSAVE #define _spin_lock_irqsave(lock) __spin_lock_irqsave(lock) #endif -#ifdef __always_inline__read_lock_irqsave +#ifdef CONFIG_INLINE_READ_LOCK_IRQSAVE #define _read_lock_irqsave(lock) __read_lock_irqsave(lock) #endif -#ifdef __always_inline__write_lock_irqsave +#ifdef CONFIG_INLINE_WRITE_LOCK_IRQSAVE #define _write_lock_irqsave(lock) __write_lock_irqsave(lock) #endif -#endif /* !CONFIG_GENERIC_LOCKBREAK */ - -#ifdef __always_inline__spin_trylock +#ifdef CONFIG_INLINE_SPIN_TRYLOCK #define _spin_trylock(lock) __spin_trylock(lock) #endif -#ifdef __always_inline__read_trylock +#ifdef CONFIG_INLINE_READ_TRYLOCK #define _read_trylock(lock) __read_trylock(lock) #endif -#ifdef __always_inline__write_trylock +#ifdef CONFIG_INLINE_WRITE_TRYLOCK #define _write_trylock(lock) __write_trylock(lock) #endif -#ifdef __always_inline__spin_trylock_bh +#ifdef CONFIG_INLINE_SPIN_TRYLOCK_BH #define _spin_trylock_bh(lock) __spin_trylock_bh(lock) #endif -#ifdef __always_inline__spin_unlock +#ifdef CONFIG_INLINE_SPIN_UNLOCK #define _spin_unlock(lock) __spin_unlock(lock) #endif -#ifdef __always_inline__read_unlock +#ifdef CONFIG_INLINE_READ_UNLOCK #define _read_unlock(lock) __read_unlock(lock) #endif -#ifdef __always_inline__write_unlock +#ifdef CONFIG_INLINE_WRITE_UNLOCK #define _write_unlock(lock) __write_unlock(lock) #endif -#ifdef __always_inline__spin_unlock_bh +#ifdef CONFIG_INLINE_SPIN_UNLOCK_BH #define _spin_unlock_bh(lock) __spin_unlock_bh(lock) #endif -#ifdef __always_inline__read_unlock_bh +#ifdef CONFIG_INLINE_READ_UNLOCK_BH #define _read_unlock_bh(lock) __read_unlock_bh(lock) #endif -#ifdef __always_inline__write_unlock_bh +#ifdef CONFIG_INLINE_WRITE_UNLOCK_BH #define _write_unlock_bh(lock) __write_unlock_bh(lock) #endif -#ifdef __always_inline__spin_unlock_irq +#ifdef CONFIG_INLINE_SPIN_UNLOCK_IRQ #define _spin_unlock_irq(lock) __spin_unlock_irq(lock) #endif -#ifdef __always_inline__read_unlock_irq +#ifdef CONFIG_INLINE_READ_UNLOCK_IRQ #define _read_unlock_irq(lock) __read_unlock_irq(lock) #endif -#ifdef __always_inline__write_unlock_irq +#ifdef CONFIG_INLINE_WRITE_UNLOCK_IRQ #define _write_unlock_irq(lock) __write_unlock_irq(lock) #endif -#ifdef __always_inline__spin_unlock_irqrestore +#ifdef CONFIG_INLINE_SPIN_UNLOCK_IRQRESTORE #define _spin_unlock_irqrestore(lock, flags) __spin_unlock_irqrestore(lock, flags) #endif -#ifdef __always_inline__read_unlock_irqrestore +#ifdef CONFIG_INLINE_READ_UNLOCK_IRQRESTORE #define _read_unlock_irqrestore(lock, flags) __read_unlock_irqrestore(lock, flags) #endif -#ifdef __always_inline__write_unlock_irqrestore +#ifdef CONFIG_INLINE_WRITE_UNLOCK_IRQRESTORE #define _write_unlock_irqrestore(lock, flags) __write_unlock_irqrestore(lock, flags) #endif -#endif /* CONFIG_DEBUG_SPINLOCK */ - static inline int __spin_trylock(spinlock_t *lock) { preempt_disable(); diff --git a/include/linux/srcu.h b/include/linux/srcu.h index aca0eee53930..4765d97dcafb 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -48,6 +48,7 @@ void cleanup_srcu_struct(struct srcu_struct *sp); int srcu_read_lock(struct srcu_struct *sp) __acquires(sp); void srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp); void synchronize_srcu(struct srcu_struct *sp); +void synchronize_srcu_expedited(struct srcu_struct *sp); long srcu_batches_completed(struct srcu_struct *sp); #endif diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 73b1f1cec423..febedcf67c7e 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -7,6 +7,8 @@ struct device; struct dma_attrs; struct scatterlist; +extern int swiotlb_force; + /* * Maximum allowable number of contiguous slabs to map, * must be a power of 2. What is the appropriate value ? @@ -20,8 +22,7 @@ struct scatterlist; */ #define IO_TLB_SHIFT 11 -extern void -swiotlb_init(void); +extern void swiotlb_init(int verbose); extern void *swiotlb_alloc_coherent(struct device *hwdev, size_t size, @@ -88,4 +89,11 @@ swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr); extern int swiotlb_dma_supported(struct device *hwdev, u64 mask); +#ifdef CONFIG_SWIOTLB +extern void __init swiotlb_free(void); +#else +static inline void swiotlb_free(void) { } +#endif + +extern void swiotlb_print_info(void); #endif /* __LINUX_SWIOTLB_H */ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index a990ace1a838..e79e2f3ccc51 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -99,37 +99,16 @@ struct perf_event_attr; #define __SC_TEST6(t6, a6, ...) __SC_TEST(t6); __SC_TEST5(__VA_ARGS__) #ifdef CONFIG_EVENT_PROFILE -#define TRACE_SYS_ENTER_PROFILE(sname) \ -static int prof_sysenter_enable_##sname(void) \ -{ \ - return reg_prof_syscall_enter("sys"#sname); \ -} \ - \ -static void prof_sysenter_disable_##sname(void) \ -{ \ - unreg_prof_syscall_enter("sys"#sname); \ -} - -#define TRACE_SYS_EXIT_PROFILE(sname) \ -static int prof_sysexit_enable_##sname(void) \ -{ \ - return reg_prof_syscall_exit("sys"#sname); \ -} \ - \ -static void prof_sysexit_disable_##sname(void) \ -{ \ - unreg_prof_syscall_exit("sys"#sname); \ -} #define TRACE_SYS_ENTER_PROFILE_INIT(sname) \ .profile_count = ATOMIC_INIT(-1), \ - .profile_enable = prof_sysenter_enable_##sname, \ - .profile_disable = prof_sysenter_disable_##sname, + .profile_enable = prof_sysenter_enable, \ + .profile_disable = prof_sysenter_disable, #define TRACE_SYS_EXIT_PROFILE_INIT(sname) \ .profile_count = ATOMIC_INIT(-1), \ - .profile_enable = prof_sysexit_enable_##sname, \ - .profile_disable = prof_sysexit_disable_##sname, + .profile_enable = prof_sysexit_enable, \ + .profile_disable = prof_sysexit_disable, #else #define TRACE_SYS_ENTER_PROFILE(sname) #define TRACE_SYS_ENTER_PROFILE_INIT(sname) @@ -153,74 +132,46 @@ static void prof_sysexit_disable_##sname(void) \ #define __SC_STR_TDECL6(t, a, ...) #t, __SC_STR_TDECL5(__VA_ARGS__) #define SYSCALL_TRACE_ENTER_EVENT(sname) \ + static const struct syscall_metadata __syscall_meta_##sname; \ static struct ftrace_event_call event_enter_##sname; \ - struct trace_event enter_syscall_print_##sname = { \ + static struct trace_event enter_syscall_print_##sname = { \ .trace = print_syscall_enter, \ }; \ - static int init_enter_##sname(void) \ - { \ - int num, id; \ - num = syscall_name_to_nr("sys"#sname); \ - if (num < 0) \ - return -ENOSYS; \ - id = register_ftrace_event(&enter_syscall_print_##sname);\ - if (!id) \ - return -ENODEV; \ - event_enter_##sname.id = id; \ - set_syscall_enter_id(num, id); \ - INIT_LIST_HEAD(&event_enter_##sname.fields); \ - return 0; \ - } \ - TRACE_SYS_ENTER_PROFILE(sname); \ static struct ftrace_event_call __used \ __attribute__((__aligned__(4))) \ __attribute__((section("_ftrace_events"))) \ event_enter_##sname = { \ .name = "sys_enter"#sname, \ .system = "syscalls", \ - .event = &event_syscall_enter, \ - .raw_init = init_enter_##sname, \ + .event = &enter_syscall_print_##sname, \ + .raw_init = init_syscall_trace, \ .show_format = syscall_enter_format, \ .define_fields = syscall_enter_define_fields, \ .regfunc = reg_event_syscall_enter, \ .unregfunc = unreg_event_syscall_enter, \ - .data = "sys"#sname, \ + .data = (void *)&__syscall_meta_##sname,\ TRACE_SYS_ENTER_PROFILE_INIT(sname) \ } #define SYSCALL_TRACE_EXIT_EVENT(sname) \ + static const struct syscall_metadata __syscall_meta_##sname; \ static struct ftrace_event_call event_exit_##sname; \ - struct trace_event exit_syscall_print_##sname = { \ + static struct trace_event exit_syscall_print_##sname = { \ .trace = print_syscall_exit, \ }; \ - static int init_exit_##sname(void) \ - { \ - int num, id; \ - num = syscall_name_to_nr("sys"#sname); \ - if (num < 0) \ - return -ENOSYS; \ - id = register_ftrace_event(&exit_syscall_print_##sname);\ - if (!id) \ - return -ENODEV; \ - event_exit_##sname.id = id; \ - set_syscall_exit_id(num, id); \ - INIT_LIST_HEAD(&event_exit_##sname.fields); \ - return 0; \ - } \ - TRACE_SYS_EXIT_PROFILE(sname); \ static struct ftrace_event_call __used \ __attribute__((__aligned__(4))) \ __attribute__((section("_ftrace_events"))) \ event_exit_##sname = { \ .name = "sys_exit"#sname, \ .system = "syscalls", \ - .event = &event_syscall_exit, \ - .raw_init = init_exit_##sname, \ + .event = &exit_syscall_print_##sname, \ + .raw_init = init_syscall_trace, \ .show_format = syscall_exit_format, \ .define_fields = syscall_exit_define_fields, \ .regfunc = reg_event_syscall_exit, \ .unregfunc = unreg_event_syscall_exit, \ - .data = "sys"#sname, \ + .data = (void *)&__syscall_meta_##sname,\ TRACE_SYS_EXIT_PROFILE_INIT(sname) \ } diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 1e4743ee6831..c83a86a22381 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -15,9 +15,6 @@ ** The kernel will then return -ENOTDIR to any application using ** the old binary interface. ** - ** For new interfaces unless you really need a binary number - ** please use CTL_UNNUMBERED. - ** **************************************************************** **************************************************************** */ @@ -50,12 +47,6 @@ struct __sysctl_args { /* Top-level names: */ -/* For internal pattern-matching use only: */ -#ifdef __KERNEL__ -#define CTL_NONE 0 -#define CTL_UNNUMBERED CTL_NONE /* sysctl without a binary number */ -#endif - enum { CTL_KERN=1, /* General kernel info and control */ @@ -972,10 +963,6 @@ extern int sysctl_perm(struct ctl_table_root *root, typedef struct ctl_table ctl_table; -typedef int ctl_handler (struct ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen); - typedef int proc_handler (struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos); @@ -996,21 +983,10 @@ extern int proc_doulongvec_minmax(struct ctl_table *, int, extern int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int, void __user *, size_t *, loff_t *); -extern int do_sysctl (int __user *name, int nlen, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen); - -extern ctl_handler sysctl_data; -extern ctl_handler sysctl_string; -extern ctl_handler sysctl_intvec; -extern ctl_handler sysctl_jiffies; -extern ctl_handler sysctl_ms_jiffies; - - /* * Register a set of sysctl names by calling register_sysctl_table - * with an initialised array of struct ctl_table's. An entry with zero - * ctl_name and NULL procname terminates the table. table->de will be + * with an initialised array of struct ctl_table's. An entry with + * NULL procname terminates the table. table->de will be * set up by the registration and need not be initialised in advance. * * sysctl names can be mirrored automatically under /proc/sys. The @@ -1023,24 +999,11 @@ extern ctl_handler sysctl_ms_jiffies; * under /proc; non-leaf nodes will be represented by directories. A * null procname disables /proc mirroring at this node. * - * sysctl entries with a zero ctl_name will not be available through - * the binary sysctl interface. - * * sysctl(2) can automatically manage read and write requests through * the sysctl table. The data and maxlen fields of the ctl_table * struct enable minimal validation of the values being written to be * performed, and the mode field allows minimal authentication. * - * More sophisticated management can be enabled by the provision of a - * strategy routine with the table entry. This will be called before - * any automatic read or write of the data is performed. - * - * The strategy routine may return: - * <0: Error occurred (error is passed to user process) - * 0: OK - proceed with automatic read or write. - * >0: OK - read or write has been done by the strategy routine, so - * return immediately. - * * There must be a proc_handler routine for any terminal nodes * mirrored under /proc/sys (non-terminals are handled by a built-in * directory handler). Several default handlers are available to @@ -1050,7 +1013,6 @@ extern ctl_handler sysctl_ms_jiffies; /* A sysctl table is an array of struct ctl_table: */ struct ctl_table { - int ctl_name; /* Binary ID */ const char *procname; /* Text ID for /proc/sys, or zero */ void *data; int maxlen; @@ -1058,7 +1020,6 @@ struct ctl_table struct ctl_table *child; struct ctl_table *parent; /* Automatically set */ proc_handler *proc_handler; /* Callback for text formatting */ - ctl_handler *strategy; /* Callback function for all r/w */ void *extra1; void *extra2; }; @@ -1092,7 +1053,6 @@ struct ctl_table_header /* struct ctl_path describes where in the hierarchy a table is added */ struct ctl_path { const char *procname; - int ctl_name; }; void register_sysctl_root(struct ctl_table_root *root); diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 3338b3f5c21a..ac5d1c1285d9 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -27,9 +27,16 @@ */ #define TPM_ANY_NUM 0xFFFF -#if defined(CONFIG_TCG_TPM) +#if defined(CONFIG_TCG_TPM) || defined(CONFIG_TCG_TPM_MODULE) extern int tpm_pcr_read(u32 chip_num, int pcr_idx, u8 *res_buf); extern int tpm_pcr_extend(u32 chip_num, int pcr_idx, const u8 *hash); +#else +static inline int tpm_pcr_read(u32 chip_num, int pcr_idx, u8 *res_buf) { + return -ENODEV; +} +static inline int tpm_pcr_extend(u32 chip_num, int pcr_idx, const u8 *hash) { + return -ENODEV; +} #endif #endif diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 2aac8a83e89b..f59604ed0ec6 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -280,6 +280,12 @@ static inline void tracepoint_synchronize_unregister(void) * TRACE_EVENT_FN to perform any (un)registration work. */ +#define DECLARE_EVENT_CLASS(name, proto, args, tstruct, assign, print) +#define DEFINE_EVENT(template, name, proto, args) \ + DECLARE_TRACE(name, PARAMS(proto), PARAMS(args)) +#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \ + DECLARE_TRACE(name, PARAMS(proto), PARAMS(args)) + #define TRACE_EVENT(name, proto, args, struct, assign, print) \ DECLARE_TRACE(name, PARAMS(proto), PARAMS(args)) #define TRACE_EVENT_FN(name, proto, args, struct, \ diff --git a/include/net/dn_dev.h b/include/net/dn_dev.h index cee46821dc53..3f781a4cafbe 100644 --- a/include/net/dn_dev.h +++ b/include/net/dn_dev.h @@ -75,7 +75,6 @@ struct dn_dev_parms { unsigned long t3; /* Default value of t3 */ int priority; /* Priority to be a router */ char *name; /* Name for sysctl */ - int ctl_name; /* Index for sysctl */ int (*up)(struct net_device *); void (*down)(struct net_device *); void (*timer3)(struct net_device *, struct dn_ifaddr *ifa); diff --git a/include/net/mac80211.h b/include/net/mac80211.h index c75b960c8ac8..998c30fc8981 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1283,6 +1283,12 @@ enum ieee80211_filter_flags { * * These flags are used with the ampdu_action() callback in * &struct ieee80211_ops to indicate which action is needed. + * + * Note that drivers MUST be able to deal with a TX aggregation + * session being stopped even before they OK'ed starting it by + * calling ieee80211_start_tx_ba_cb(_irqsafe), because the peer + * might receive the addBA frame and send a delBA right away! + * * @IEEE80211_AMPDU_RX_START: start Rx aggregation * @IEEE80211_AMPDU_RX_STOP: stop Rx aggregation * @IEEE80211_AMPDU_TX_START: start Tx aggregation diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 3817fda82a80..da99fdd63cf5 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -264,8 +264,7 @@ extern int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, int p_id, int pdev_id, char *p_name, - proc_handler *proc_handler, - ctl_handler *strategy); + proc_handler *proc_handler); extern void neigh_sysctl_unregister(struct neigh_parms *p); static inline void __neigh_parms_put(struct neigh_parms *parms) diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index cd2e18778f81..0a474568b003 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -893,7 +893,6 @@ struct sctp_transport { */ /* RTO : The current retransmission timeout value. */ unsigned long rto; - unsigned long last_rto; __u32 rtt; /* This is the most recent RTT. */ diff --git a/include/pcmcia/cs.h b/include/pcmcia/cs.h index 904468a191ef..afc2bfb9e917 100644 --- a/include/pcmcia/cs.h +++ b/include/pcmcia/cs.h @@ -15,6 +15,10 @@ #ifndef _LINUX_CS_H #define _LINUX_CS_H +#ifdef __KERNEL__ +#include <linux/interrupt.h> +#endif + /* For AccessConfigurationRegister */ typedef struct conf_reg_t { u_char Function; @@ -111,11 +115,9 @@ typedef struct io_req_t { /* For RequestIRQ and ReleaseIRQ */ typedef struct irq_req_t { - u_int Attributes; - u_int AssignedIRQ; - u_int IRQInfo1, IRQInfo2; /* IRQInfo2 is ignored */ - void *Handler; - void *Instance; + u_int Attributes; + u_int AssignedIRQ; + irq_handler_t Handler; } irq_req_t; /* Attributes for RequestIRQ and ReleaseIRQ */ @@ -125,7 +127,7 @@ typedef struct irq_req_t { #define IRQ_TYPE_DYNAMIC_SHARING 0x02 #define IRQ_FORCED_PULSE 0x04 #define IRQ_FIRST_SHARED 0x08 -#define IRQ_HANDLE_PRESENT 0x10 +//#define IRQ_HANDLE_PRESENT 0x10 #define IRQ_PULSE_ALLOCATED 0x100 /* Bits in IRQInfo1 field */ diff --git a/include/pcmcia/cs_types.h b/include/pcmcia/cs_types.h index 315965a37930..f5e3b8386c8f 100644 --- a/include/pcmcia/cs_types.h +++ b/include/pcmcia/cs_types.h @@ -26,8 +26,7 @@ typedef u_int event_t; typedef u_char cisdata_t; typedef u_short page_t; -struct window_t; -typedef struct window_t *window_handle_t; +typedef unsigned long window_handle_t; struct region_t; typedef struct region_t *memory_handle_t; diff --git a/include/pcmcia/ds.h b/include/pcmcia/ds.h index a2be80b9a095..d403c12f7978 100644 --- a/include/pcmcia/ds.h +++ b/include/pcmcia/ds.h @@ -34,6 +34,7 @@ struct pcmcia_socket; struct pcmcia_device; struct config_t; +struct net_device; /* dynamic device IDs for PCMCIA device drivers. See * Documentation/pcmcia/driver.txt for details. @@ -137,65 +138,39 @@ struct pcmcia_device { #define to_pcmcia_dev(n) container_of(n, struct pcmcia_device, dev) #define to_pcmcia_drv(n) container_of(n, struct pcmcia_driver, drv) -/* deprecated -- don't use! */ -#define handle_to_dev(handle) (handle->dev) - -/* (deprecated) error reporting by PCMCIA devices. Use dev_printk() - * or dev_dbg() directly in the driver, without referring to pcmcia_error_func() - * and/or pcmcia_error_ret() for those functions will go away soon. - */ -enum service { - AccessConfigurationRegister, AddSocketServices, - AdjustResourceInfo, CheckEraseQueue, CloseMemory, CopyMemory, - DeregisterClient, DeregisterEraseQueue, GetCardServicesInfo, - GetClientInfo, GetConfigurationInfo, GetEventMask, - GetFirstClient, GetFirstPartion, GetFirstRegion, GetFirstTuple, - GetNextClient, GetNextPartition, GetNextRegion, GetNextTuple, - GetStatus, GetTupleData, MapLogSocket, MapLogWindow, MapMemPage, - MapPhySocket, MapPhyWindow, ModifyConfiguration, ModifyWindow, - OpenMemory, ParseTuple, ReadMemory, RegisterClient, - RegisterEraseQueue, RegisterMTD, RegisterTimer, - ReleaseConfiguration, ReleaseExclusive, ReleaseIO, ReleaseIRQ, - ReleaseSocketMask, ReleaseWindow, ReplaceSocketServices, - RequestConfiguration, RequestExclusive, RequestIO, RequestIRQ, - RequestSocketMask, RequestWindow, ResetCard, ReturnSSEntry, - SetEventMask, SetRegion, ValidateCIS, VendorSpecific, - WriteMemory, BindDevice, BindMTD, ReportError, - SuspendCard, ResumeCard, EjectCard, InsertCard, ReplaceCIS, - GetFirstWindow, GetNextWindow, GetMemPage -}; -const char *pcmcia_error_func(int func); -const char *pcmcia_error_ret(int ret); - -#define cs_error(p_dev, func, ret) \ - { \ - dev_printk(KERN_NOTICE, &p_dev->dev, \ - "%s : %s\n", \ - pcmcia_error_func(func), \ - pcmcia_error_ret(ret)); \ - } - -/* CIS access. - * Use the pcmcia_* versions in PCMCIA drivers +/* + * CIS access. + * + * Please use the following functions to access CIS tuples: + * - pcmcia_get_tuple() + * - pcmcia_loop_tuple() + * - pcmcia_get_mac_from_cis() + * + * To parse a tuple_t, pcmcia_parse_tuple() exists. Its interface + * might change in future. */ -int pcmcia_parse_tuple(tuple_t *tuple, cisparse_t *parse); -int pccard_get_first_tuple(struct pcmcia_socket *s, unsigned int function, - tuple_t *tuple); -#define pcmcia_get_first_tuple(p_dev, tuple) \ - pccard_get_first_tuple(p_dev->socket, p_dev->func, tuple) +/* get the very first CIS entry of type @code. Note that buf is pointer + * to u8 *buf; and that you need to kfree(buf) afterwards. */ +size_t pcmcia_get_tuple(struct pcmcia_device *p_dev, cisdata_t code, + u8 **buf); -int pccard_get_next_tuple(struct pcmcia_socket *s, unsigned int function, - tuple_t *tuple); -#define pcmcia_get_next_tuple(p_dev, tuple) \ - pccard_get_next_tuple(p_dev->socket, p_dev->func, tuple) +/* loop over CIS entries */ +int pcmcia_loop_tuple(struct pcmcia_device *p_dev, cisdata_t code, + int (*loop_tuple) (struct pcmcia_device *p_dev, + tuple_t *tuple, + void *priv_data), + void *priv_data); -int pccard_get_tuple_data(struct pcmcia_socket *s, tuple_t *tuple); -#define pcmcia_get_tuple_data(p_dev, tuple) \ - pccard_get_tuple_data(p_dev->socket, tuple) +/* get the MAC address from CISTPL_FUNCE */ +int pcmcia_get_mac_from_cis(struct pcmcia_device *p_dev, + struct net_device *dev); +/* parse a tuple_t */ +int pcmcia_parse_tuple(tuple_t *tuple, cisparse_t *parse); + /* loop CIS entries for valid configuration */ int pcmcia_loop_config(struct pcmcia_device *p_dev, int (*conf_check) (struct pcmcia_device *p_dev, @@ -221,12 +196,11 @@ int pcmcia_request_irq(struct pcmcia_device *p_dev, irq_req_t *req); int pcmcia_request_configuration(struct pcmcia_device *p_dev, config_req_t *req); -int pcmcia_request_window(struct pcmcia_device **p_dev, win_req_t *req, +int pcmcia_request_window(struct pcmcia_device *p_dev, win_req_t *req, window_handle_t *wh); -int pcmcia_release_window(window_handle_t win); - -int pcmcia_get_mem_page(window_handle_t win, memreq_t *req); -int pcmcia_map_mem_page(window_handle_t win, memreq_t *req); +int pcmcia_release_window(struct pcmcia_device *p_dev, window_handle_t win); +int pcmcia_map_mem_page(struct pcmcia_device *p_dev, window_handle_t win, + memreq_t *req); int pcmcia_modify_configuration(struct pcmcia_device *p_dev, modconf_t *mod); void pcmcia_disable_device(struct pcmcia_device *p_dev); diff --git a/include/pcmcia/ss.h b/include/pcmcia/ss.h index e0f6feb8588c..7c23be706f12 100644 --- a/include/pcmcia/ss.h +++ b/include/pcmcia/ss.h @@ -107,15 +107,6 @@ typedef struct io_window_t { struct resource *res; } io_window_t; -#define WINDOW_MAGIC 0xB35C -typedef struct window_t { - u_short magic; - u_short index; - struct pcmcia_device *handle; - struct pcmcia_socket *sock; - pccard_mem_map ctl; -} window_t; - /* Maximum number of IO windows per socket */ #define MAX_IO_WIN 2 @@ -155,7 +146,7 @@ struct pcmcia_socket { u_int Config; } irq; io_window_t io[MAX_IO_WIN]; - window_t win[MAX_WIN]; + pccard_mem_map win[MAX_WIN]; struct list_head cis_cache; size_t fake_cis_len; u8 *fake_cis; @@ -172,7 +163,7 @@ struct pcmcia_socket { u_int irq_mask; u_int map_size; u_int io_offset; - u_char pci_irq; + u_int pci_irq; struct pci_dev * cb_dev; diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 9af48cbf0036..f097ae340bc1 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -145,6 +145,7 @@ struct scsi_device { unsigned retry_hwerror:1; /* Retry HARDWARE_ERROR */ unsigned last_sector_bug:1; /* do not use multisector accesses on SD_LAST_BUGGY_SECTORS */ + unsigned is_visible:1; /* is the device visible in sysfs */ DECLARE_BITMAP(supported_events, SDEV_EVT_MAXBITS); /* supported events */ struct list_head event_list; /* asserted events */ diff --git a/include/trace/define_trace.h b/include/trace/define_trace.h index 2a4b3bf74033..5acfb1eb4df9 100644 --- a/include/trace/define_trace.h +++ b/include/trace/define_trace.h @@ -31,6 +31,14 @@ assign, print, reg, unreg) \ DEFINE_TRACE_FN(name, reg, unreg) +#undef DEFINE_EVENT +#define DEFINE_EVENT(template, name, proto, args) \ + DEFINE_TRACE(name) + +#undef DEFINE_EVENT_PRINT +#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \ + DEFINE_TRACE(name) + #undef DECLARE_TRACE #define DECLARE_TRACE(name, proto, args) \ DEFINE_TRACE(name) @@ -63,6 +71,9 @@ #undef TRACE_EVENT #undef TRACE_EVENT_FN +#undef DECLARE_EVENT_CLASS +#undef DEFINE_EVENT +#undef DEFINE_EVENT_PRINT #undef TRACE_HEADER_MULTI_READ /* Only undef what we defined in this file */ diff --git a/include/trace/events/bkl.h b/include/trace/events/bkl.h new file mode 100644 index 000000000000..1af72dc24278 --- /dev/null +++ b/include/trace/events/bkl.h @@ -0,0 +1,61 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM bkl + +#if !defined(_TRACE_BKL_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_BKL_H + +#include <linux/tracepoint.h> + +TRACE_EVENT(lock_kernel, + + TP_PROTO(const char *func, const char *file, int line), + + TP_ARGS(func, file, line), + + TP_STRUCT__entry( + __field( int, depth ) + __field_ext( const char *, func, FILTER_PTR_STRING ) + __field_ext( const char *, file, FILTER_PTR_STRING ) + __field( int, line ) + ), + + TP_fast_assign( + /* We want to record the lock_depth after lock is acquired */ + __entry->depth = current->lock_depth + 1; + __entry->func = func; + __entry->file = file; + __entry->line = line; + ), + + TP_printk("depth=%d file:line=%s:%d func=%s()", __entry->depth, + __entry->file, __entry->line, __entry->func) +); + +TRACE_EVENT(unlock_kernel, + + TP_PROTO(const char *func, const char *file, int line), + + TP_ARGS(func, file, line), + + TP_STRUCT__entry( + __field(int, depth ) + __field(const char *, func ) + __field(const char *, file ) + __field(int, line ) + ), + + TP_fast_assign( + __entry->depth = current->lock_depth; + __entry->func = func; + __entry->file = file; + __entry->line = line; + ), + + TP_printk("depth=%d file:line=%s:%d func=%s()", __entry->depth, + __entry->file, __entry->line, __entry->func) +); + +#endif /* _TRACE_BKL_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/block.h b/include/trace/events/block.h index 00405b5f624a..5fb72733331e 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -8,7 +8,7 @@ #include <linux/blkdev.h> #include <linux/tracepoint.h> -TRACE_EVENT(block_rq_abort, +DECLARE_EVENT_CLASS(block_rq_with_error, TP_PROTO(struct request_queue *q, struct request *rq), @@ -40,41 +40,28 @@ TRACE_EVENT(block_rq_abort, __entry->nr_sector, __entry->errors) ); -TRACE_EVENT(block_rq_insert, +DEFINE_EVENT(block_rq_with_error, block_rq_abort, TP_PROTO(struct request_queue *q, struct request *rq), - TP_ARGS(q, rq), + TP_ARGS(q, rq) +); - TP_STRUCT__entry( - __field( dev_t, dev ) - __field( sector_t, sector ) - __field( unsigned int, nr_sector ) - __field( unsigned int, bytes ) - __array( char, rwbs, 6 ) - __array( char, comm, TASK_COMM_LEN ) - __dynamic_array( char, cmd, blk_cmd_buf_len(rq) ) - ), +DEFINE_EVENT(block_rq_with_error, block_rq_requeue, - TP_fast_assign( - __entry->dev = rq->rq_disk ? disk_devt(rq->rq_disk) : 0; - __entry->sector = blk_pc_request(rq) ? 0 : blk_rq_pos(rq); - __entry->nr_sector = blk_pc_request(rq) ? 0 : blk_rq_sectors(rq); - __entry->bytes = blk_pc_request(rq) ? blk_rq_bytes(rq) : 0; + TP_PROTO(struct request_queue *q, struct request *rq), - blk_fill_rwbs_rq(__entry->rwbs, rq); - blk_dump_cmd(__get_str(cmd), rq); - memcpy(__entry->comm, current->comm, TASK_COMM_LEN); - ), + TP_ARGS(q, rq) +); - TP_printk("%d,%d %s %u (%s) %llu + %u [%s]", - MAJOR(__entry->dev), MINOR(__entry->dev), - __entry->rwbs, __entry->bytes, __get_str(cmd), - (unsigned long long)__entry->sector, - __entry->nr_sector, __entry->comm) +DEFINE_EVENT(block_rq_with_error, block_rq_complete, + + TP_PROTO(struct request_queue *q, struct request *rq), + + TP_ARGS(q, rq) ); -TRACE_EVENT(block_rq_issue, +DECLARE_EVENT_CLASS(block_rq, TP_PROTO(struct request_queue *q, struct request *rq), @@ -86,7 +73,7 @@ TRACE_EVENT(block_rq_issue, __field( unsigned int, nr_sector ) __field( unsigned int, bytes ) __array( char, rwbs, 6 ) - __array( char, comm, TASK_COMM_LEN ) + __array( char, comm, TASK_COMM_LEN ) __dynamic_array( char, cmd, blk_cmd_buf_len(rq) ) ), @@ -108,68 +95,18 @@ TRACE_EVENT(block_rq_issue, __entry->nr_sector, __entry->comm) ); -TRACE_EVENT(block_rq_requeue, +DEFINE_EVENT(block_rq, block_rq_insert, TP_PROTO(struct request_queue *q, struct request *rq), - TP_ARGS(q, rq), - - TP_STRUCT__entry( - __field( dev_t, dev ) - __field( sector_t, sector ) - __field( unsigned int, nr_sector ) - __field( int, errors ) - __array( char, rwbs, 6 ) - __dynamic_array( char, cmd, blk_cmd_buf_len(rq) ) - ), - - TP_fast_assign( - __entry->dev = rq->rq_disk ? disk_devt(rq->rq_disk) : 0; - __entry->sector = blk_pc_request(rq) ? 0 : blk_rq_pos(rq); - __entry->nr_sector = blk_pc_request(rq) ? 0 : blk_rq_sectors(rq); - __entry->errors = rq->errors; - - blk_fill_rwbs_rq(__entry->rwbs, rq); - blk_dump_cmd(__get_str(cmd), rq); - ), - - TP_printk("%d,%d %s (%s) %llu + %u [%d]", - MAJOR(__entry->dev), MINOR(__entry->dev), - __entry->rwbs, __get_str(cmd), - (unsigned long long)__entry->sector, - __entry->nr_sector, __entry->errors) + TP_ARGS(q, rq) ); -TRACE_EVENT(block_rq_complete, +DEFINE_EVENT(block_rq, block_rq_issue, TP_PROTO(struct request_queue *q, struct request *rq), - TP_ARGS(q, rq), - - TP_STRUCT__entry( - __field( dev_t, dev ) - __field( sector_t, sector ) - __field( unsigned int, nr_sector ) - __field( int, errors ) - __array( char, rwbs, 6 ) - __dynamic_array( char, cmd, blk_cmd_buf_len(rq) ) - ), - - TP_fast_assign( - __entry->dev = rq->rq_disk ? disk_devt(rq->rq_disk) : 0; - __entry->sector = blk_pc_request(rq) ? 0 : blk_rq_pos(rq); - __entry->nr_sector = blk_pc_request(rq) ? 0 : blk_rq_sectors(rq); - __entry->errors = rq->errors; - - blk_fill_rwbs_rq(__entry->rwbs, rq); - blk_dump_cmd(__get_str(cmd), rq); - ), - - TP_printk("%d,%d %s (%s) %llu + %u [%d]", - MAJOR(__entry->dev), MINOR(__entry->dev), - __entry->rwbs, __get_str(cmd), - (unsigned long long)__entry->sector, - __entry->nr_sector, __entry->errors) + TP_ARGS(q, rq) ); TRACE_EVENT(block_bio_bounce, @@ -228,7 +165,7 @@ TRACE_EVENT(block_bio_complete, __entry->nr_sector, __entry->error) ); -TRACE_EVENT(block_bio_backmerge, +DECLARE_EVENT_CLASS(block_bio, TP_PROTO(struct request_queue *q, struct bio *bio), @@ -256,63 +193,28 @@ TRACE_EVENT(block_bio_backmerge, __entry->nr_sector, __entry->comm) ); -TRACE_EVENT(block_bio_frontmerge, +DEFINE_EVENT(block_bio, block_bio_backmerge, TP_PROTO(struct request_queue *q, struct bio *bio), - TP_ARGS(q, bio), - - TP_STRUCT__entry( - __field( dev_t, dev ) - __field( sector_t, sector ) - __field( unsigned, nr_sector ) - __array( char, rwbs, 6 ) - __array( char, comm, TASK_COMM_LEN ) - ), - - TP_fast_assign( - __entry->dev = bio->bi_bdev->bd_dev; - __entry->sector = bio->bi_sector; - __entry->nr_sector = bio->bi_size >> 9; - blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size); - memcpy(__entry->comm, current->comm, TASK_COMM_LEN); - ), - - TP_printk("%d,%d %s %llu + %u [%s]", - MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs, - (unsigned long long)__entry->sector, - __entry->nr_sector, __entry->comm) + TP_ARGS(q, bio) ); -TRACE_EVENT(block_bio_queue, +DEFINE_EVENT(block_bio, block_bio_frontmerge, TP_PROTO(struct request_queue *q, struct bio *bio), - TP_ARGS(q, bio), + TP_ARGS(q, bio) +); - TP_STRUCT__entry( - __field( dev_t, dev ) - __field( sector_t, sector ) - __field( unsigned int, nr_sector ) - __array( char, rwbs, 6 ) - __array( char, comm, TASK_COMM_LEN ) - ), +DEFINE_EVENT(block_bio, block_bio_queue, - TP_fast_assign( - __entry->dev = bio->bi_bdev->bd_dev; - __entry->sector = bio->bi_sector; - __entry->nr_sector = bio->bi_size >> 9; - blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size); - memcpy(__entry->comm, current->comm, TASK_COMM_LEN); - ), + TP_PROTO(struct request_queue *q, struct bio *bio), - TP_printk("%d,%d %s %llu + %u [%s]", - MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs, - (unsigned long long)__entry->sector, - __entry->nr_sector, __entry->comm) + TP_ARGS(q, bio) ); -TRACE_EVENT(block_getrq, +DECLARE_EVENT_CLASS(block_get_rq, TP_PROTO(struct request_queue *q, struct bio *bio, int rw), @@ -341,33 +243,18 @@ TRACE_EVENT(block_getrq, __entry->nr_sector, __entry->comm) ); -TRACE_EVENT(block_sleeprq, +DEFINE_EVENT(block_get_rq, block_getrq, TP_PROTO(struct request_queue *q, struct bio *bio, int rw), - TP_ARGS(q, bio, rw), + TP_ARGS(q, bio, rw) +); - TP_STRUCT__entry( - __field( dev_t, dev ) - __field( sector_t, sector ) - __field( unsigned int, nr_sector ) - __array( char, rwbs, 6 ) - __array( char, comm, TASK_COMM_LEN ) - ), +DEFINE_EVENT(block_get_rq, block_sleeprq, - TP_fast_assign( - __entry->dev = bio ? bio->bi_bdev->bd_dev : 0; - __entry->sector = bio ? bio->bi_sector : 0; - __entry->nr_sector = bio ? bio->bi_size >> 9 : 0; - blk_fill_rwbs(__entry->rwbs, - bio ? bio->bi_rw : 0, __entry->nr_sector); - memcpy(__entry->comm, current->comm, TASK_COMM_LEN); - ), + TP_PROTO(struct request_queue *q, struct bio *bio, int rw), - TP_printk("%d,%d %s %llu + %u [%s]", - MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs, - (unsigned long long)__entry->sector, - __entry->nr_sector, __entry->comm) + TP_ARGS(q, bio, rw) ); TRACE_EVENT(block_plug, @@ -387,7 +274,7 @@ TRACE_EVENT(block_plug, TP_printk("[%s]", __entry->comm) ); -TRACE_EVENT(block_unplug_timer, +DECLARE_EVENT_CLASS(block_unplug, TP_PROTO(struct request_queue *q), @@ -406,23 +293,18 @@ TRACE_EVENT(block_unplug_timer, TP_printk("[%s] %d", __entry->comm, __entry->nr_rq) ); -TRACE_EVENT(block_unplug_io, +DEFINE_EVENT(block_unplug, block_unplug_timer, TP_PROTO(struct request_queue *q), - TP_ARGS(q), + TP_ARGS(q) +); - TP_STRUCT__entry( - __field( int, nr_rq ) - __array( char, comm, TASK_COMM_LEN ) - ), +DEFINE_EVENT(block_unplug, block_unplug_io, - TP_fast_assign( - __entry->nr_rq = q->rq.count[READ] + q->rq.count[WRITE]; - memcpy(__entry->comm, current->comm, TASK_COMM_LEN); - ), + TP_PROTO(struct request_queue *q), - TP_printk("[%s] %d", __entry->comm, __entry->nr_rq) + TP_ARGS(q) ); TRACE_EVENT(block_split, diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index d09550bf3f95..318f76535bd4 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -90,7 +90,7 @@ TRACE_EVENT(ext4_allocate_inode, (unsigned long) __entry->dir, __entry->mode) ); -TRACE_EVENT(ext4_write_begin, +DECLARE_EVENT_CLASS(ext4__write_begin, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, unsigned int flags), @@ -118,7 +118,23 @@ TRACE_EVENT(ext4_write_begin, __entry->pos, __entry->len, __entry->flags) ); -TRACE_EVENT(ext4_ordered_write_end, +DEFINE_EVENT(ext4__write_begin, ext4_write_begin, + + TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, + unsigned int flags), + + TP_ARGS(inode, pos, len, flags) +); + +DEFINE_EVENT(ext4__write_begin, ext4_da_write_begin, + + TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, + unsigned int flags), + + TP_ARGS(inode, pos, len, flags) +); + +DECLARE_EVENT_CLASS(ext4__write_end, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, unsigned int copied), @@ -145,57 +161,36 @@ TRACE_EVENT(ext4_ordered_write_end, __entry->pos, __entry->len, __entry->copied) ); -TRACE_EVENT(ext4_writeback_write_end, +DEFINE_EVENT(ext4__write_end, ext4_ordered_write_end, + TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, unsigned int copied), - TP_ARGS(inode, pos, len, copied), + TP_ARGS(inode, pos, len, copied) +); - TP_STRUCT__entry( - __field( dev_t, dev ) - __field( ino_t, ino ) - __field( loff_t, pos ) - __field( unsigned int, len ) - __field( unsigned int, copied ) - ), +DEFINE_EVENT(ext4__write_end, ext4_writeback_write_end, - TP_fast_assign( - __entry->dev = inode->i_sb->s_dev; - __entry->ino = inode->i_ino; - __entry->pos = pos; - __entry->len = len; - __entry->copied = copied; - ), + TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, + unsigned int copied), - TP_printk("dev %s ino %lu pos %llu len %u copied %u", - jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, - __entry->pos, __entry->len, __entry->copied) + TP_ARGS(inode, pos, len, copied) ); -TRACE_EVENT(ext4_journalled_write_end, +DEFINE_EVENT(ext4__write_end, ext4_journalled_write_end, + TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, unsigned int copied), - TP_ARGS(inode, pos, len, copied), - TP_STRUCT__entry( - __field( dev_t, dev ) - __field( ino_t, ino ) - __field( loff_t, pos ) - __field( unsigned int, len ) - __field( unsigned int, copied ) - ), + TP_ARGS(inode, pos, len, copied) +); - TP_fast_assign( - __entry->dev = inode->i_sb->s_dev; - __entry->ino = inode->i_ino; - __entry->pos = pos; - __entry->len = len; - __entry->copied = copied; - ), +DEFINE_EVENT(ext4__write_end, ext4_da_write_end, - TP_printk("dev %s ino %lu pos %llu len %u copied %u", - jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, - __entry->pos, __entry->len, __entry->copied) + TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, + unsigned int copied), + + TP_ARGS(inode, pos, len, copied) ); TRACE_EVENT(ext4_writepage, @@ -337,60 +332,6 @@ TRACE_EVENT(ext4_da_writepages_result, (unsigned long) __entry->writeback_index) ); -TRACE_EVENT(ext4_da_write_begin, - TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, - unsigned int flags), - - TP_ARGS(inode, pos, len, flags), - - TP_STRUCT__entry( - __field( dev_t, dev ) - __field( ino_t, ino ) - __field( loff_t, pos ) - __field( unsigned int, len ) - __field( unsigned int, flags ) - ), - - TP_fast_assign( - __entry->dev = inode->i_sb->s_dev; - __entry->ino = inode->i_ino; - __entry->pos = pos; - __entry->len = len; - __entry->flags = flags; - ), - - TP_printk("dev %s ino %lu pos %llu len %u flags %u", - jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, - __entry->pos, __entry->len, __entry->flags) -); - -TRACE_EVENT(ext4_da_write_end, - TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, - unsigned int copied), - - TP_ARGS(inode, pos, len, copied), - - TP_STRUCT__entry( - __field( dev_t, dev ) - __field( ino_t, ino ) - __field( loff_t, pos ) - __field( unsigned int, len ) - __field( unsigned int, copied ) - ), - - TP_fast_assign( - __entry->dev = inode->i_sb->s_dev; - __entry->ino = inode->i_ino; - __entry->pos = pos; - __entry->len = len; - __entry->copied = copied; - ), - - TP_printk("dev %s ino %lu pos %llu len %u copied %u", - jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, - __entry->pos, __entry->len, __entry->copied) -); - TRACE_EVENT(ext4_discard_blocks, TP_PROTO(struct super_block *sb, unsigned long long blk, unsigned long long count), diff --git a/include/trace/events/irq.h b/include/trace/events/irq.h index b89f9db4a404..0e4cfb694fe7 100644 --- a/include/trace/events/irq.h +++ b/include/trace/events/irq.h @@ -48,7 +48,7 @@ TRACE_EVENT(irq_handler_entry, __assign_str(name, action->name); ), - TP_printk("irq=%d handler=%s", __entry->irq, __get_str(name)) + TP_printk("irq=%d name=%s", __entry->irq, __get_str(name)) ); /** @@ -78,22 +78,11 @@ TRACE_EVENT(irq_handler_exit, __entry->ret = ret; ), - TP_printk("irq=%d return=%s", + TP_printk("irq=%d ret=%s", __entry->irq, __entry->ret ? "handled" : "unhandled") ); -/** - * softirq_entry - called immediately before the softirq handler - * @h: pointer to struct softirq_action - * @vec: pointer to first struct softirq_action in softirq_vec array - * - * The @h parameter, contains a pointer to the struct softirq_action - * which has a pointer to the action handler that is called. By subtracting - * the @vec pointer from the @h pointer, we can determine the softirq - * number. Also, when used in combination with the softirq_exit tracepoint - * we can determine the softirq latency. - */ -TRACE_EVENT(softirq_entry, +DECLARE_EVENT_CLASS(softirq, TP_PROTO(struct softirq_action *h, struct softirq_action *vec), @@ -107,11 +96,29 @@ TRACE_EVENT(softirq_entry, __entry->vec = (int)(h - vec); ), - TP_printk("softirq=%d action=%s", __entry->vec, + TP_printk("vec=%d [action=%s]", __entry->vec, show_softirq_name(__entry->vec)) ); /** + * softirq_entry - called immediately before the softirq handler + * @h: pointer to struct softirq_action + * @vec: pointer to first struct softirq_action in softirq_vec array + * + * The @h parameter, contains a pointer to the struct softirq_action + * which has a pointer to the action handler that is called. By subtracting + * the @vec pointer from the @h pointer, we can determine the softirq + * number. Also, when used in combination with the softirq_exit tracepoint + * we can determine the softirq latency. + */ +DEFINE_EVENT(softirq, softirq_entry, + + TP_PROTO(struct softirq_action *h, struct softirq_action *vec), + + TP_ARGS(h, vec) +); + +/** * softirq_exit - called immediately after the softirq handler returns * @h: pointer to struct softirq_action * @vec: pointer to first struct softirq_action in softirq_vec array @@ -122,22 +129,11 @@ TRACE_EVENT(softirq_entry, * combination with the softirq_entry tracepoint we can determine the softirq * latency. */ -TRACE_EVENT(softirq_exit, +DEFINE_EVENT(softirq, softirq_exit, TP_PROTO(struct softirq_action *h, struct softirq_action *vec), - TP_ARGS(h, vec), - - TP_STRUCT__entry( - __field( int, vec ) - ), - - TP_fast_assign( - __entry->vec = (int)(h - vec); - ), - - TP_printk("softirq=%d action=%s", __entry->vec, - show_softirq_name(__entry->vec)) + TP_ARGS(h, vec) ); #endif /* _TRACE_IRQ_H */ diff --git a/include/trace/events/jbd2.h b/include/trace/events/jbd2.h index 3c60b75adb9e..96b370a050de 100644 --- a/include/trace/events/jbd2.h +++ b/include/trace/events/jbd2.h @@ -30,7 +30,7 @@ TRACE_EVENT(jbd2_checkpoint, jbd2_dev_to_name(__entry->dev), __entry->result) ); -TRACE_EVENT(jbd2_start_commit, +DECLARE_EVENT_CLASS(jbd2_commit, TP_PROTO(journal_t *journal, transaction_t *commit_transaction), @@ -53,73 +53,32 @@ TRACE_EVENT(jbd2_start_commit, __entry->sync_commit) ); -TRACE_EVENT(jbd2_commit_locking, +DEFINE_EVENT(jbd2_commit, jbd2_start_commit, TP_PROTO(journal_t *journal, transaction_t *commit_transaction), - TP_ARGS(journal, commit_transaction), - - TP_STRUCT__entry( - __field( dev_t, dev ) - __field( char, sync_commit ) - __field( int, transaction ) - ), - - TP_fast_assign( - __entry->dev = journal->j_fs_dev->bd_dev; - __entry->sync_commit = commit_transaction->t_synchronous_commit; - __entry->transaction = commit_transaction->t_tid; - ), - - TP_printk("dev %s transaction %d sync %d", - jbd2_dev_to_name(__entry->dev), __entry->transaction, - __entry->sync_commit) + TP_ARGS(journal, commit_transaction) ); -TRACE_EVENT(jbd2_commit_flushing, +DEFINE_EVENT(jbd2_commit, jbd2_commit_locking, TP_PROTO(journal_t *journal, transaction_t *commit_transaction), - TP_ARGS(journal, commit_transaction), - - TP_STRUCT__entry( - __field( dev_t, dev ) - __field( char, sync_commit ) - __field( int, transaction ) - ), - - TP_fast_assign( - __entry->dev = journal->j_fs_dev->bd_dev; - __entry->sync_commit = commit_transaction->t_synchronous_commit; - __entry->transaction = commit_transaction->t_tid; - ), - - TP_printk("dev %s transaction %d sync %d", - jbd2_dev_to_name(__entry->dev), __entry->transaction, - __entry->sync_commit) + TP_ARGS(journal, commit_transaction) ); -TRACE_EVENT(jbd2_commit_logging, +DEFINE_EVENT(jbd2_commit, jbd2_commit_flushing, TP_PROTO(journal_t *journal, transaction_t *commit_transaction), - TP_ARGS(journal, commit_transaction), + TP_ARGS(journal, commit_transaction) +); - TP_STRUCT__entry( - __field( dev_t, dev ) - __field( char, sync_commit ) - __field( int, transaction ) - ), +DEFINE_EVENT(jbd2_commit, jbd2_commit_logging, - TP_fast_assign( - __entry->dev = journal->j_fs_dev->bd_dev; - __entry->sync_commit = commit_transaction->t_synchronous_commit; - __entry->transaction = commit_transaction->t_tid; - ), + TP_PROTO(journal_t *journal, transaction_t *commit_transaction), - TP_printk("dev %s transaction %d sync %d", - jbd2_dev_to_name(__entry->dev), __entry->transaction, - __entry->sync_commit) + TP_ARGS(journal, commit_transaction) ); TRACE_EVENT(jbd2_end_commit, diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h index eaf46bdd18a5..3adca0ca9dbe 100644 --- a/include/trace/events/kmem.h +++ b/include/trace/events/kmem.h @@ -44,7 +44,7 @@ {(unsigned long)__GFP_MOVABLE, "GFP_MOVABLE"} \ ) : "GFP_NOWAIT" -TRACE_EVENT(kmalloc, +DECLARE_EVENT_CLASS(kmem_alloc, TP_PROTO(unsigned long call_site, const void *ptr, @@ -78,41 +78,23 @@ TRACE_EVENT(kmalloc, show_gfp_flags(__entry->gfp_flags)) ); -TRACE_EVENT(kmem_cache_alloc, +DEFINE_EVENT(kmem_alloc, kmalloc, - TP_PROTO(unsigned long call_site, - const void *ptr, - size_t bytes_req, - size_t bytes_alloc, - gfp_t gfp_flags), + TP_PROTO(unsigned long call_site, const void *ptr, + size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags), - TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags), + TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags) +); - TP_STRUCT__entry( - __field( unsigned long, call_site ) - __field( const void *, ptr ) - __field( size_t, bytes_req ) - __field( size_t, bytes_alloc ) - __field( gfp_t, gfp_flags ) - ), +DEFINE_EVENT(kmem_alloc, kmem_cache_alloc, - TP_fast_assign( - __entry->call_site = call_site; - __entry->ptr = ptr; - __entry->bytes_req = bytes_req; - __entry->bytes_alloc = bytes_alloc; - __entry->gfp_flags = gfp_flags; - ), + TP_PROTO(unsigned long call_site, const void *ptr, + size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags), - TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s", - __entry->call_site, - __entry->ptr, - __entry->bytes_req, - __entry->bytes_alloc, - show_gfp_flags(__entry->gfp_flags)) + TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags) ); -TRACE_EVENT(kmalloc_node, +DECLARE_EVENT_CLASS(kmem_alloc_node, TP_PROTO(unsigned long call_site, const void *ptr, @@ -150,45 +132,25 @@ TRACE_EVENT(kmalloc_node, __entry->node) ); -TRACE_EVENT(kmem_cache_alloc_node, +DEFINE_EVENT(kmem_alloc_node, kmalloc_node, - TP_PROTO(unsigned long call_site, - const void *ptr, - size_t bytes_req, - size_t bytes_alloc, - gfp_t gfp_flags, - int node), + TP_PROTO(unsigned long call_site, const void *ptr, + size_t bytes_req, size_t bytes_alloc, + gfp_t gfp_flags, int node), - TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node), + TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node) +); - TP_STRUCT__entry( - __field( unsigned long, call_site ) - __field( const void *, ptr ) - __field( size_t, bytes_req ) - __field( size_t, bytes_alloc ) - __field( gfp_t, gfp_flags ) - __field( int, node ) - ), +DEFINE_EVENT(kmem_alloc_node, kmem_cache_alloc_node, - TP_fast_assign( - __entry->call_site = call_site; - __entry->ptr = ptr; - __entry->bytes_req = bytes_req; - __entry->bytes_alloc = bytes_alloc; - __entry->gfp_flags = gfp_flags; - __entry->node = node; - ), + TP_PROTO(unsigned long call_site, const void *ptr, + size_t bytes_req, size_t bytes_alloc, + gfp_t gfp_flags, int node), - TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d", - __entry->call_site, - __entry->ptr, - __entry->bytes_req, - __entry->bytes_alloc, - show_gfp_flags(__entry->gfp_flags), - __entry->node) + TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node) ); -TRACE_EVENT(kfree, +DECLARE_EVENT_CLASS(kmem_free, TP_PROTO(unsigned long call_site, const void *ptr), @@ -207,23 +169,18 @@ TRACE_EVENT(kfree, TP_printk("call_site=%lx ptr=%p", __entry->call_site, __entry->ptr) ); -TRACE_EVENT(kmem_cache_free, +DEFINE_EVENT(kmem_free, kfree, TP_PROTO(unsigned long call_site, const void *ptr), - TP_ARGS(call_site, ptr), + TP_ARGS(call_site, ptr) +); - TP_STRUCT__entry( - __field( unsigned long, call_site ) - __field( const void *, ptr ) - ), +DEFINE_EVENT(kmem_free, kmem_cache_free, - TP_fast_assign( - __entry->call_site = call_site; - __entry->ptr = ptr; - ), + TP_PROTO(unsigned long call_site, const void *ptr), - TP_printk("call_site=%lx ptr=%p", __entry->call_site, __entry->ptr) + TP_ARGS(call_site, ptr) ); TRACE_EVENT(mm_page_free_direct, @@ -299,7 +256,7 @@ TRACE_EVENT(mm_page_alloc, show_gfp_flags(__entry->gfp_flags)) ); -TRACE_EVENT(mm_page_alloc_zone_locked, +DECLARE_EVENT_CLASS(mm_page, TP_PROTO(struct page *page, unsigned int order, int migratetype), @@ -325,29 +282,22 @@ TRACE_EVENT(mm_page_alloc_zone_locked, __entry->order == 0) ); -TRACE_EVENT(mm_page_pcpu_drain, +DEFINE_EVENT(mm_page, mm_page_alloc_zone_locked, - TP_PROTO(struct page *page, int order, int migratetype), + TP_PROTO(struct page *page, unsigned int order, int migratetype), - TP_ARGS(page, order, migratetype), + TP_ARGS(page, order, migratetype) +); - TP_STRUCT__entry( - __field( struct page *, page ) - __field( int, order ) - __field( int, migratetype ) - ), +DEFINE_EVENT_PRINT(mm_page, mm_page_pcpu_drain, - TP_fast_assign( - __entry->page = page; - __entry->order = order; - __entry->migratetype = migratetype; - ), + TP_PROTO(struct page *page, unsigned int order, int migratetype), + + TP_ARGS(page, order, migratetype), TP_printk("page=%p pfn=%lu order=%d migratetype=%d", - __entry->page, - page_to_pfn(__entry->page), - __entry->order, - __entry->migratetype) + __entry->page, page_to_pfn(__entry->page), + __entry->order, __entry->migratetype) ); TRACE_EVENT(mm_page_alloc_extfrag, diff --git a/include/trace/events/lockdep.h b/include/trace/events/lock.h index bcf1d209a00d..a870ba125aa8 100644 --- a/include/trace/events/lockdep.h +++ b/include/trace/events/lock.h @@ -1,8 +1,8 @@ #undef TRACE_SYSTEM -#define TRACE_SYSTEM lockdep +#define TRACE_SYSTEM lock -#if !defined(_TRACE_LOCKDEP_H) || defined(TRACE_HEADER_MULTI_READ) -#define _TRACE_LOCKDEP_H +#if !defined(_TRACE_LOCK_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_LOCK_H #include <linux/lockdep.h> #include <linux/tracepoint.h> @@ -90,7 +90,7 @@ TRACE_EVENT(lock_acquired, #endif #endif -#endif /* _TRACE_LOCKDEP_H */ +#endif /* _TRACE_LOCK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> diff --git a/include/trace/events/mce.h b/include/trace/events/mce.h new file mode 100644 index 000000000000..7eee77895cb3 --- /dev/null +++ b/include/trace/events/mce.h @@ -0,0 +1,69 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM mce + +#if !defined(_TRACE_MCE_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_MCE_H + +#include <linux/ktime.h> +#include <linux/tracepoint.h> +#include <asm/mce.h> + +TRACE_EVENT(mce_record, + + TP_PROTO(struct mce *m), + + TP_ARGS(m), + + TP_STRUCT__entry( + __field( u64, mcgcap ) + __field( u64, mcgstatus ) + __field( u8, bank ) + __field( u64, status ) + __field( u64, addr ) + __field( u64, misc ) + __field( u64, ip ) + __field( u8, cs ) + __field( u64, tsc ) + __field( u64, walltime ) + __field( u32, cpu ) + __field( u32, cpuid ) + __field( u32, apicid ) + __field( u32, socketid ) + __field( u8, cpuvendor ) + ), + + TP_fast_assign( + __entry->mcgcap = m->mcgcap; + __entry->mcgstatus = m->mcgstatus; + __entry->bank = m->bank; + __entry->status = m->status; + __entry->addr = m->addr; + __entry->misc = m->misc; + __entry->ip = m->ip; + __entry->cs = m->cs; + __entry->tsc = m->tsc; + __entry->walltime = m->time; + __entry->cpu = m->extcpu; + __entry->cpuid = m->cpuid; + __entry->apicid = m->apicid; + __entry->socketid = m->socketid; + __entry->cpuvendor = m->cpuvendor; + ), + + TP_printk("CPU: %d, MCGc/s: %llx/%llx, MC%d: %016Lx, ADDR/MISC: %016Lx/%016Lx, RIP: %02x:<%016Lx>, TSC: %llx, PROCESSOR: %u:%x, TIME: %llu, SOCKET: %u, APIC: %x", + __entry->cpu, + __entry->mcgcap, __entry->mcgstatus, + __entry->bank, __entry->status, + __entry->addr, __entry->misc, + __entry->cs, __entry->ip, + __entry->tsc, + __entry->cpuvendor, __entry->cpuid, + __entry->walltime, + __entry->socketid, + __entry->apicid) +); + +#endif /* _TRACE_MCE_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/module.h b/include/trace/events/module.h index 84160fb18478..4b0f48ba16a6 100644 --- a/include/trace/events/module.h +++ b/include/trace/events/module.h @@ -51,7 +51,7 @@ TRACE_EVENT(module_free, TP_printk("%s", __get_str(name)) ); -TRACE_EVENT(module_get, +DECLARE_EVENT_CLASS(module_refcnt, TP_PROTO(struct module *mod, unsigned long ip, int refcnt), @@ -73,26 +73,18 @@ TRACE_EVENT(module_get, __get_str(name), (void *)__entry->ip, __entry->refcnt) ); -TRACE_EVENT(module_put, +DEFINE_EVENT(module_refcnt, module_get, TP_PROTO(struct module *mod, unsigned long ip, int refcnt), - TP_ARGS(mod, ip, refcnt), + TP_ARGS(mod, ip, refcnt) +); - TP_STRUCT__entry( - __field( unsigned long, ip ) - __field( int, refcnt ) - __string( name, mod->name ) - ), +DEFINE_EVENT(module_refcnt, module_put, - TP_fast_assign( - __entry->ip = ip; - __entry->refcnt = refcnt; - __assign_str(name, mod->name); - ), + TP_PROTO(struct module *mod, unsigned long ip, int refcnt), - TP_printk("%s call_site=%pf refcnt=%d", - __get_str(name), (void *)__entry->ip, __entry->refcnt) + TP_ARGS(mod, ip, refcnt) ); TRACE_EVENT(module_request, diff --git a/include/trace/events/power.h b/include/trace/events/power.h index ea6d579261ad..c4efe9b8280d 100644 --- a/include/trace/events/power.h +++ b/include/trace/events/power.h @@ -16,9 +16,7 @@ enum { }; #endif - - -TRACE_EVENT(power_start, +DECLARE_EVENT_CLASS(power, TP_PROTO(unsigned int type, unsigned int state), @@ -37,42 +35,36 @@ TRACE_EVENT(power_start, TP_printk("type=%lu state=%lu", (unsigned long)__entry->type, (unsigned long)__entry->state) ); -TRACE_EVENT(power_end, - - TP_PROTO(int dummy), +DEFINE_EVENT(power, power_start, - TP_ARGS(dummy), + TP_PROTO(unsigned int type, unsigned int state), - TP_STRUCT__entry( - __field( u64, dummy ) - ), + TP_ARGS(type, state) +); - TP_fast_assign( - __entry->dummy = 0xffff; - ), +DEFINE_EVENT(power, power_frequency, - TP_printk("dummy=%lu", (unsigned long)__entry->dummy) + TP_PROTO(unsigned int type, unsigned int state), + TP_ARGS(type, state) ); +TRACE_EVENT(power_end, -TRACE_EVENT(power_frequency, - - TP_PROTO(unsigned int type, unsigned int state), + TP_PROTO(int dummy), - TP_ARGS(type, state), + TP_ARGS(dummy), TP_STRUCT__entry( - __field( u64, type ) - __field( u64, state ) + __field( u64, dummy ) ), TP_fast_assign( - __entry->type = type; - __entry->state = state; + __entry->dummy = 0xffff; ), - TP_printk("type=%lu state=%lu", (unsigned long)__entry->type, (unsigned long) __entry->state) + TP_printk("dummy=%lu", (unsigned long)__entry->dummy) + ); #endif /* _TRACE_POWER_H */ diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index 4069c43f4187..cfceb0b73e20 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -26,7 +26,7 @@ TRACE_EVENT(sched_kthread_stop, __entry->pid = t->pid; ), - TP_printk("task %s:%d", __entry->comm, __entry->pid) + TP_printk("comm=%s pid=%d", __entry->comm, __entry->pid) ); /* @@ -46,7 +46,7 @@ TRACE_EVENT(sched_kthread_stop_ret, __entry->ret = ret; ), - TP_printk("ret %d", __entry->ret) + TP_printk("ret=%d", __entry->ret) ); /* @@ -73,7 +73,7 @@ TRACE_EVENT(sched_wait_task, __entry->prio = p->prio; ), - TP_printk("task %s:%d [%d]", + TP_printk("comm=%s pid=%d prio=%d", __entry->comm, __entry->pid, __entry->prio) ); @@ -83,7 +83,7 @@ TRACE_EVENT(sched_wait_task, * (NOTE: the 'rq' argument is not used by generic trace events, * but used by the latency tracer plugin. ) */ -TRACE_EVENT(sched_wakeup, +DECLARE_EVENT_CLASS(sched_wakeup_template, TP_PROTO(struct rq *rq, struct task_struct *p, int success), @@ -94,7 +94,7 @@ TRACE_EVENT(sched_wakeup, __field( pid_t, pid ) __field( int, prio ) __field( int, success ) - __field( int, cpu ) + __field( int, target_cpu ) ), TP_fast_assign( @@ -102,46 +102,27 @@ TRACE_EVENT(sched_wakeup, __entry->pid = p->pid; __entry->prio = p->prio; __entry->success = success; - __entry->cpu = task_cpu(p); + __entry->target_cpu = task_cpu(p); ), - TP_printk("task %s:%d [%d] success=%d [%03d]", + TP_printk("comm=%s pid=%d prio=%d success=%d target_cpu=%03d", __entry->comm, __entry->pid, __entry->prio, - __entry->success, __entry->cpu) + __entry->success, __entry->target_cpu) ); +DEFINE_EVENT(sched_wakeup_template, sched_wakeup, + TP_PROTO(struct rq *rq, struct task_struct *p, int success), + TP_ARGS(rq, p, success)); + /* * Tracepoint for waking up a new task: * * (NOTE: the 'rq' argument is not used by generic trace events, * but used by the latency tracer plugin. ) */ -TRACE_EVENT(sched_wakeup_new, - - TP_PROTO(struct rq *rq, struct task_struct *p, int success), - - TP_ARGS(rq, p, success), - - TP_STRUCT__entry( - __array( char, comm, TASK_COMM_LEN ) - __field( pid_t, pid ) - __field( int, prio ) - __field( int, success ) - __field( int, cpu ) - ), - - TP_fast_assign( - memcpy(__entry->comm, p->comm, TASK_COMM_LEN); - __entry->pid = p->pid; - __entry->prio = p->prio; - __entry->success = success; - __entry->cpu = task_cpu(p); - ), - - TP_printk("task %s:%d [%d] success=%d [%03d]", - __entry->comm, __entry->pid, __entry->prio, - __entry->success, __entry->cpu) -); +DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new, + TP_PROTO(struct rq *rq, struct task_struct *p, int success), + TP_ARGS(rq, p, success)); /* * Tracepoint for task switches, performed by the scheduler: @@ -176,7 +157,7 @@ TRACE_EVENT(sched_switch, __entry->next_prio = next->prio; ), - TP_printk("task %s:%d [%d] (%s) ==> %s:%d [%d]", + TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s ==> next_comm=%s next_pid=%d next_prio=%d", __entry->prev_comm, __entry->prev_pid, __entry->prev_prio, __entry->prev_state ? __print_flags(__entry->prev_state, "|", @@ -211,15 +192,12 @@ TRACE_EVENT(sched_migrate_task, __entry->dest_cpu = dest_cpu; ), - TP_printk("task %s:%d [%d] from: %d to: %d", + TP_printk("comm=%s pid=%d prio=%d orig_cpu=%d dest_cpu=%d", __entry->comm, __entry->pid, __entry->prio, __entry->orig_cpu, __entry->dest_cpu) ); -/* - * Tracepoint for freeing a task: - */ -TRACE_EVENT(sched_process_free, +DECLARE_EVENT_CLASS(sched_process_template, TP_PROTO(struct task_struct *p), @@ -237,34 +215,24 @@ TRACE_EVENT(sched_process_free, __entry->prio = p->prio; ), - TP_printk("task %s:%d [%d]", + TP_printk("comm=%s pid=%d prio=%d", __entry->comm, __entry->pid, __entry->prio) ); /* - * Tracepoint for a task exiting: + * Tracepoint for freeing a task: */ -TRACE_EVENT(sched_process_exit, +DEFINE_EVENT(sched_process_template, sched_process_free, + TP_PROTO(struct task_struct *p), + TP_ARGS(p)); + - TP_PROTO(struct task_struct *p), - - TP_ARGS(p), - - TP_STRUCT__entry( - __array( char, comm, TASK_COMM_LEN ) - __field( pid_t, pid ) - __field( int, prio ) - ), - - TP_fast_assign( - memcpy(__entry->comm, p->comm, TASK_COMM_LEN); - __entry->pid = p->pid; - __entry->prio = p->prio; - ), - - TP_printk("task %s:%d [%d]", - __entry->comm, __entry->pid, __entry->prio) -); +/* + * Tracepoint for a task exiting: + */ +DEFINE_EVENT(sched_process_template, sched_process_exit, + TP_PROTO(struct task_struct *p), + TP_ARGS(p)); /* * Tracepoint for a waiting task: @@ -287,7 +255,7 @@ TRACE_EVENT(sched_process_wait, __entry->prio = current->prio; ), - TP_printk("task %s:%d [%d]", + TP_printk("comm=%s pid=%d prio=%d", __entry->comm, __entry->pid, __entry->prio) ); @@ -314,46 +282,16 @@ TRACE_EVENT(sched_process_fork, __entry->child_pid = child->pid; ), - TP_printk("parent %s:%d child %s:%d", + TP_printk("comm=%s pid=%d child_comm=%s child_pid=%d", __entry->parent_comm, __entry->parent_pid, __entry->child_comm, __entry->child_pid) ); /* - * Tracepoint for sending a signal: - */ -TRACE_EVENT(sched_signal_send, - - TP_PROTO(int sig, struct task_struct *p), - - TP_ARGS(sig, p), - - TP_STRUCT__entry( - __field( int, sig ) - __array( char, comm, TASK_COMM_LEN ) - __field( pid_t, pid ) - ), - - TP_fast_assign( - memcpy(__entry->comm, p->comm, TASK_COMM_LEN); - __entry->pid = p->pid; - __entry->sig = sig; - ), - - TP_printk("sig: %d task %s:%d", - __entry->sig, __entry->comm, __entry->pid) -); - -/* * XXX the below sched_stat tracepoints only apply to SCHED_OTHER/BATCH/IDLE * adding sched_stat support to SCHED_FIFO/RR would be welcome. */ - -/* - * Tracepoint for accounting wait time (time the task is runnable - * but not actually running due to scheduler contention). - */ -TRACE_EVENT(sched_stat_wait, +DECLARE_EVENT_CLASS(sched_stat_template, TP_PROTO(struct task_struct *tsk, u64 delay), @@ -374,11 +312,36 @@ TRACE_EVENT(sched_stat_wait, __perf_count(delay); ), - TP_printk("task: %s:%d wait: %Lu [ns]", + TP_printk("comm=%s pid=%d delay=%Lu [ns]", __entry->comm, __entry->pid, (unsigned long long)__entry->delay) ); + +/* + * Tracepoint for accounting wait time (time the task is runnable + * but not actually running due to scheduler contention). + */ +DEFINE_EVENT(sched_stat_template, sched_stat_wait, + TP_PROTO(struct task_struct *tsk, u64 delay), + TP_ARGS(tsk, delay)); + +/* + * Tracepoint for accounting sleep time (time the task is not runnable, + * including iowait, see below). + */ +DEFINE_EVENT(sched_stat_template, sched_stat_sleep, + TP_PROTO(struct task_struct *tsk, u64 delay), + TP_ARGS(tsk, delay)); + +/* + * Tracepoint for accounting iowait time (time the task is not runnable + * due to waiting on IO to complete). + */ +DEFINE_EVENT(sched_stat_template, sched_stat_iowait, + TP_PROTO(struct task_struct *tsk, u64 delay), + TP_ARGS(tsk, delay)); + /* * Tracepoint for accounting runtime (time the task is executing * on a CPU). @@ -406,72 +369,12 @@ TRACE_EVENT(sched_stat_runtime, __perf_count(runtime); ), - TP_printk("task: %s:%d runtime: %Lu [ns], vruntime: %Lu [ns]", + TP_printk("comm=%s pid=%d runtime=%Lu [ns] vruntime=%Lu [ns]", __entry->comm, __entry->pid, (unsigned long long)__entry->runtime, (unsigned long long)__entry->vruntime) ); -/* - * Tracepoint for accounting sleep time (time the task is not runnable, - * including iowait, see below). - */ -TRACE_EVENT(sched_stat_sleep, - - TP_PROTO(struct task_struct *tsk, u64 delay), - - TP_ARGS(tsk, delay), - - TP_STRUCT__entry( - __array( char, comm, TASK_COMM_LEN ) - __field( pid_t, pid ) - __field( u64, delay ) - ), - - TP_fast_assign( - memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); - __entry->pid = tsk->pid; - __entry->delay = delay; - ) - TP_perf_assign( - __perf_count(delay); - ), - - TP_printk("task: %s:%d sleep: %Lu [ns]", - __entry->comm, __entry->pid, - (unsigned long long)__entry->delay) -); - -/* - * Tracepoint for accounting iowait time (time the task is not runnable - * due to waiting on IO to complete). - */ -TRACE_EVENT(sched_stat_iowait, - - TP_PROTO(struct task_struct *tsk, u64 delay), - - TP_ARGS(tsk, delay), - - TP_STRUCT__entry( - __array( char, comm, TASK_COMM_LEN ) - __field( pid_t, pid ) - __field( u64, delay ) - ), - - TP_fast_assign( - memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); - __entry->pid = tsk->pid; - __entry->delay = delay; - ) - TP_perf_assign( - __perf_count(delay); - ), - - TP_printk("task: %s:%d iowait: %Lu [ns]", - __entry->comm, __entry->pid, - (unsigned long long)__entry->delay) -); - #endif /* _TRACE_SCHED_H */ /* This part must be outside protection */ diff --git a/include/trace/events/signal.h b/include/trace/events/signal.h new file mode 100644 index 000000000000..a510b75ac304 --- /dev/null +++ b/include/trace/events/signal.h @@ -0,0 +1,173 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM signal + +#if !defined(_TRACE_SIGNAL_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_SIGNAL_H + +#include <linux/signal.h> +#include <linux/sched.h> +#include <linux/tracepoint.h> + +#define TP_STORE_SIGINFO(__entry, info) \ + do { \ + if (info == SEND_SIG_NOINFO) { \ + __entry->errno = 0; \ + __entry->code = SI_USER; \ + } else if (info == SEND_SIG_PRIV) { \ + __entry->errno = 0; \ + __entry->code = SI_KERNEL; \ + } else { \ + __entry->errno = info->si_errno; \ + __entry->code = info->si_code; \ + } \ + } while (0) + +/** + * signal_generate - called when a signal is generated + * @sig: signal number + * @info: pointer to struct siginfo + * @task: pointer to struct task_struct + * + * Current process sends a 'sig' signal to 'task' process with + * 'info' siginfo. If 'info' is SEND_SIG_NOINFO or SEND_SIG_PRIV, + * 'info' is not a pointer and you can't access its field. Instead, + * SEND_SIG_NOINFO means that si_code is SI_USER, and SEND_SIG_PRIV + * means that si_code is SI_KERNEL. + */ +TRACE_EVENT(signal_generate, + + TP_PROTO(int sig, struct siginfo *info, struct task_struct *task), + + TP_ARGS(sig, info, task), + + TP_STRUCT__entry( + __field( int, sig ) + __field( int, errno ) + __field( int, code ) + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + ), + + TP_fast_assign( + __entry->sig = sig; + TP_STORE_SIGINFO(__entry, info); + memcpy(__entry->comm, task->comm, TASK_COMM_LEN); + __entry->pid = task->pid; + ), + + TP_printk("sig=%d errno=%d code=%d comm=%s pid=%d", + __entry->sig, __entry->errno, __entry->code, + __entry->comm, __entry->pid) +); + +/** + * signal_deliver - called when a signal is delivered + * @sig: signal number + * @info: pointer to struct siginfo + * @ka: pointer to struct k_sigaction + * + * A 'sig' signal is delivered to current process with 'info' siginfo, + * and it will be handled by 'ka'. ka->sa.sa_handler can be SIG_IGN or + * SIG_DFL. + * Note that some signals reported by signal_generate tracepoint can be + * lost, ignored or modified (by debugger) before hitting this tracepoint. + * This means, this can show which signals are actually delivered, but + * matching generated signals and delivered signals may not be correct. + */ +TRACE_EVENT(signal_deliver, + + TP_PROTO(int sig, struct siginfo *info, struct k_sigaction *ka), + + TP_ARGS(sig, info, ka), + + TP_STRUCT__entry( + __field( int, sig ) + __field( int, errno ) + __field( int, code ) + __field( unsigned long, sa_handler ) + __field( unsigned long, sa_flags ) + ), + + TP_fast_assign( + __entry->sig = sig; + TP_STORE_SIGINFO(__entry, info); + __entry->sa_handler = (unsigned long)ka->sa.sa_handler; + __entry->sa_flags = ka->sa.sa_flags; + ), + + TP_printk("sig=%d errno=%d code=%d sa_handler=%lx sa_flags=%lx", + __entry->sig, __entry->errno, __entry->code, + __entry->sa_handler, __entry->sa_flags) +); + +/** + * signal_overflow_fail - called when signal queue is overflow + * @sig: signal number + * @group: signal to process group or not (bool) + * @info: pointer to struct siginfo + * + * Kernel fails to generate 'sig' signal with 'info' siginfo, because + * siginfo queue is overflow, and the signal is dropped. + * 'group' is not 0 if the signal will be sent to a process group. + * 'sig' is always one of RT signals. + */ +TRACE_EVENT(signal_overflow_fail, + + TP_PROTO(int sig, int group, struct siginfo *info), + + TP_ARGS(sig, group, info), + + TP_STRUCT__entry( + __field( int, sig ) + __field( int, group ) + __field( int, errno ) + __field( int, code ) + ), + + TP_fast_assign( + __entry->sig = sig; + __entry->group = group; + TP_STORE_SIGINFO(__entry, info); + ), + + TP_printk("sig=%d group=%d errno=%d code=%d", + __entry->sig, __entry->group, __entry->errno, __entry->code) +); + +/** + * signal_lose_info - called when siginfo is lost + * @sig: signal number + * @group: signal to process group or not (bool) + * @info: pointer to struct siginfo + * + * Kernel generates 'sig' signal but loses 'info' siginfo, because siginfo + * queue is overflow. + * 'group' is not 0 if the signal will be sent to a process group. + * 'sig' is always one of non-RT signals. + */ +TRACE_EVENT(signal_lose_info, + + TP_PROTO(int sig, int group, struct siginfo *info), + + TP_ARGS(sig, group, info), + + TP_STRUCT__entry( + __field( int, sig ) + __field( int, group ) + __field( int, errno ) + __field( int, code ) + ), + + TP_fast_assign( + __entry->sig = sig; + __entry->group = group; + TP_STORE_SIGINFO(__entry, info); + ), + + TP_printk("sig=%d group=%d errno=%d code=%d", + __entry->sig, __entry->group, __entry->errno, __entry->code) +); +#endif /* _TRACE_SIGNAL_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/syscalls.h b/include/trace/events/syscalls.h index 397dff2dbd5a..fb726ac7caee 100644 --- a/include/trace/events/syscalls.h +++ b/include/trace/events/syscalls.h @@ -1,5 +1,6 @@ #undef TRACE_SYSTEM -#define TRACE_SYSTEM syscalls +#define TRACE_SYSTEM raw_syscalls +#define TRACE_INCLUDE_FILE syscalls #if !defined(_TRACE_EVENTS_SYSCALLS_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_EVENTS_SYSCALLS_H diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h index 1844c48d640e..e5ce87a0498d 100644 --- a/include/trace/events/timer.h +++ b/include/trace/events/timer.h @@ -26,7 +26,7 @@ TRACE_EVENT(timer_init, __entry->timer = timer; ), - TP_printk("timer %p", __entry->timer) + TP_printk("timer=%p", __entry->timer) ); /** @@ -54,7 +54,7 @@ TRACE_EVENT(timer_start, __entry->now = jiffies; ), - TP_printk("timer %p: func %pf, expires %lu, timeout %ld", + TP_printk("timer=%p function=%pf expires=%lu [timeout=%ld]", __entry->timer, __entry->function, __entry->expires, (long)__entry->expires - __entry->now) ); @@ -81,7 +81,7 @@ TRACE_EVENT(timer_expire_entry, __entry->now = jiffies; ), - TP_printk("timer %p: now %lu", __entry->timer, __entry->now) + TP_printk("timer=%p now=%lu", __entry->timer, __entry->now) ); /** @@ -108,7 +108,7 @@ TRACE_EVENT(timer_expire_exit, __entry->timer = timer; ), - TP_printk("timer %p", __entry->timer) + TP_printk("timer=%p", __entry->timer) ); /** @@ -129,7 +129,7 @@ TRACE_EVENT(timer_cancel, __entry->timer = timer; ), - TP_printk("timer %p", __entry->timer) + TP_printk("timer=%p", __entry->timer) ); /** @@ -140,24 +140,24 @@ TRACE_EVENT(timer_cancel, */ TRACE_EVENT(hrtimer_init, - TP_PROTO(struct hrtimer *timer, clockid_t clockid, + TP_PROTO(struct hrtimer *hrtimer, clockid_t clockid, enum hrtimer_mode mode), - TP_ARGS(timer, clockid, mode), + TP_ARGS(hrtimer, clockid, mode), TP_STRUCT__entry( - __field( void *, timer ) + __field( void *, hrtimer ) __field( clockid_t, clockid ) __field( enum hrtimer_mode, mode ) ), TP_fast_assign( - __entry->timer = timer; + __entry->hrtimer = hrtimer; __entry->clockid = clockid; __entry->mode = mode; ), - TP_printk("hrtimer %p, clockid %s, mode %s", __entry->timer, + TP_printk("hrtimer=%p clockid=%s mode=%s", __entry->hrtimer, __entry->clockid == CLOCK_REALTIME ? "CLOCK_REALTIME" : "CLOCK_MONOTONIC", __entry->mode == HRTIMER_MODE_ABS ? @@ -170,26 +170,26 @@ TRACE_EVENT(hrtimer_init, */ TRACE_EVENT(hrtimer_start, - TP_PROTO(struct hrtimer *timer), + TP_PROTO(struct hrtimer *hrtimer), - TP_ARGS(timer), + TP_ARGS(hrtimer), TP_STRUCT__entry( - __field( void *, timer ) + __field( void *, hrtimer ) __field( void *, function ) __field( s64, expires ) __field( s64, softexpires ) ), TP_fast_assign( - __entry->timer = timer; - __entry->function = timer->function; - __entry->expires = hrtimer_get_expires(timer).tv64; - __entry->softexpires = hrtimer_get_softexpires(timer).tv64; + __entry->hrtimer = hrtimer; + __entry->function = hrtimer->function; + __entry->expires = hrtimer_get_expires(hrtimer).tv64; + __entry->softexpires = hrtimer_get_softexpires(hrtimer).tv64; ), - TP_printk("hrtimer %p, func %pf, expires %llu, softexpires %llu", - __entry->timer, __entry->function, + TP_printk("hrtimer=%p function=%pf expires=%llu softexpires=%llu", + __entry->hrtimer, __entry->function, (unsigned long long)ktime_to_ns((ktime_t) { .tv64 = __entry->expires }), (unsigned long long)ktime_to_ns((ktime_t) { @@ -206,23 +206,22 @@ TRACE_EVENT(hrtimer_start, */ TRACE_EVENT(hrtimer_expire_entry, - TP_PROTO(struct hrtimer *timer, ktime_t *now), + TP_PROTO(struct hrtimer *hrtimer, ktime_t *now), - TP_ARGS(timer, now), + TP_ARGS(hrtimer, now), TP_STRUCT__entry( - __field( void *, timer ) + __field( void *, hrtimer ) __field( s64, now ) ), TP_fast_assign( - __entry->timer = timer; - __entry->now = now->tv64; + __entry->hrtimer = hrtimer; + __entry->now = now->tv64; ), - TP_printk("hrtimer %p, now %llu", __entry->timer, - (unsigned long long)ktime_to_ns((ktime_t) { - .tv64 = __entry->now })) + TP_printk("hrtimer=%p now=%llu", __entry->hrtimer, + (unsigned long long)ktime_to_ns((ktime_t) { .tv64 = __entry->now })) ); /** @@ -234,40 +233,40 @@ TRACE_EVENT(hrtimer_expire_entry, */ TRACE_EVENT(hrtimer_expire_exit, - TP_PROTO(struct hrtimer *timer), + TP_PROTO(struct hrtimer *hrtimer), - TP_ARGS(timer), + TP_ARGS(hrtimer), TP_STRUCT__entry( - __field( void *, timer ) + __field( void *, hrtimer ) ), TP_fast_assign( - __entry->timer = timer; + __entry->hrtimer = hrtimer; ), - TP_printk("hrtimer %p", __entry->timer) + TP_printk("hrtimer=%p", __entry->hrtimer) ); /** * hrtimer_cancel - called when the hrtimer is canceled - * @timer: pointer to struct hrtimer + * @hrtimer: pointer to struct hrtimer */ TRACE_EVENT(hrtimer_cancel, - TP_PROTO(struct hrtimer *timer), + TP_PROTO(struct hrtimer *hrtimer), - TP_ARGS(timer), + TP_ARGS(hrtimer), TP_STRUCT__entry( - __field( void *, timer ) + __field( void *, hrtimer ) ), TP_fast_assign( - __entry->timer = timer; + __entry->hrtimer = hrtimer; ), - TP_printk("hrtimer %p", __entry->timer) + TP_printk("hrtimer=%p", __entry->hrtimer) ); /** @@ -302,7 +301,7 @@ TRACE_EVENT(itimer_state, __entry->interval_usec = value->it_interval.tv_usec; ), - TP_printk("which %d, expires %lu, it_value %lu.%lu, it_interval %lu.%lu", + TP_printk("which=%d expires=%lu it_value=%lu.%lu it_interval=%lu.%lu", __entry->which, __entry->expires, __entry->value_sec, __entry->value_usec, __entry->interval_sec, __entry->interval_usec) @@ -332,7 +331,7 @@ TRACE_EVENT(itimer_expire, __entry->pid = pid_nr(pid); ), - TP_printk("which %d, pid %d, now %lu", __entry->which, + TP_printk("which=%d pid=%d now=%lu", __entry->which, (int) __entry->pid, __entry->now) ); diff --git a/include/trace/events/workqueue.h b/include/trace/events/workqueue.h index e4612dbd7ba6..d6c974474e70 100644 --- a/include/trace/events/workqueue.h +++ b/include/trace/events/workqueue.h @@ -8,7 +8,7 @@ #include <linux/sched.h> #include <linux/tracepoint.h> -TRACE_EVENT(workqueue_insertion, +DECLARE_EVENT_CLASS(workqueue, TP_PROTO(struct task_struct *wq_thread, struct work_struct *work), @@ -30,26 +30,18 @@ TRACE_EVENT(workqueue_insertion, __entry->thread_pid, __entry->func) ); -TRACE_EVENT(workqueue_execution, +DEFINE_EVENT(workqueue, workqueue_insertion, TP_PROTO(struct task_struct *wq_thread, struct work_struct *work), - TP_ARGS(wq_thread, work), + TP_ARGS(wq_thread, work) +); - TP_STRUCT__entry( - __array(char, thread_comm, TASK_COMM_LEN) - __field(pid_t, thread_pid) - __field(work_func_t, func) - ), +DEFINE_EVENT(workqueue, workqueue_execution, - TP_fast_assign( - memcpy(__entry->thread_comm, wq_thread->comm, TASK_COMM_LEN); - __entry->thread_pid = wq_thread->pid; - __entry->func = work->func; - ), + TP_PROTO(struct task_struct *wq_thread, struct work_struct *work), - TP_printk("thread=%s:%d func=%pf", __entry->thread_comm, - __entry->thread_pid, __entry->func) + TP_ARGS(wq_thread, work) ); /* Trace the creation of one workqueue thread on a cpu */ diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index cc0d9667e182..d1b3de9c1a71 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -18,6 +18,26 @@ #include <linux/ftrace_event.h> +/* + * DECLARE_EVENT_CLASS can be used to add a generic function + * handlers for events. That is, if all events have the same + * parameters and just have distinct trace points. + * Each tracepoint can be defined with DEFINE_EVENT and that + * will map the DECLARE_EVENT_CLASS to the tracepoint. + * + * TRACE_EVENT is a one to one mapping between tracepoint and template. + */ +#undef TRACE_EVENT +#define TRACE_EVENT(name, proto, args, tstruct, assign, print) \ + DECLARE_EVENT_CLASS(name, \ + PARAMS(proto), \ + PARAMS(args), \ + PARAMS(tstruct), \ + PARAMS(assign), \ + PARAMS(print)); \ + DEFINE_EVENT(name, name, PARAMS(proto), PARAMS(args)); + + #undef __field #define __field(type, item) type item; @@ -36,15 +56,21 @@ #undef TP_STRUCT__entry #define TP_STRUCT__entry(args...) args -#undef TRACE_EVENT -#define TRACE_EVENT(name, proto, args, tstruct, assign, print) \ - struct ftrace_raw_##name { \ - struct trace_entry ent; \ - tstruct \ - char __data[0]; \ - }; \ +#undef DECLARE_EVENT_CLASS +#define DECLARE_EVENT_CLASS(name, proto, args, tstruct, assign, print) \ + struct ftrace_raw_##name { \ + struct trace_entry ent; \ + tstruct \ + char __data[0]; \ + }; +#undef DEFINE_EVENT +#define DEFINE_EVENT(template, name, proto, args) \ static struct ftrace_event_call event_##name +#undef DEFINE_EVENT_PRINT +#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \ + DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args)) + #undef __cpparg #define __cpparg(arg...) arg @@ -89,12 +115,19 @@ #undef __string #define __string(item, src) __dynamic_array(char, item, -1) -#undef TRACE_EVENT -#define TRACE_EVENT(call, proto, args, tstruct, assign, print) \ +#undef DECLARE_EVENT_CLASS +#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ struct ftrace_data_offsets_##call { \ tstruct; \ }; +#undef DEFINE_EVENT +#define DEFINE_EVENT(template, name, proto, args) + +#undef DEFINE_EVENT_PRINT +#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \ + DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args)) + #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) /* @@ -120,9 +153,10 @@ #undef __field #define __field(type, item) \ ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t" \ - "offset:%u;\tsize:%u;\n", \ + "offset:%u;\tsize:%u;\tsigned:%u;\n", \ (unsigned int)offsetof(typeof(field), item), \ - (unsigned int)sizeof(field.item)); \ + (unsigned int)sizeof(field.item), \ + (unsigned int)is_signed_type(type)); \ if (!ret) \ return 0; @@ -132,19 +166,21 @@ #undef __array #define __array(type, item, len) \ ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t" \ - "offset:%u;\tsize:%u;\n", \ + "offset:%u;\tsize:%u;\tsigned:%u;\n", \ (unsigned int)offsetof(typeof(field), item), \ - (unsigned int)sizeof(field.item)); \ + (unsigned int)sizeof(field.item), \ + (unsigned int)is_signed_type(type)); \ if (!ret) \ return 0; #undef __dynamic_array #define __dynamic_array(type, item, len) \ ret = trace_seq_printf(s, "\tfield:__data_loc " #type "[] " #item ";\t"\ - "offset:%u;\tsize:%u;\n", \ + "offset:%u;\tsize:%u;\tsigned:%u;\n", \ (unsigned int)offsetof(typeof(field), \ __data_loc_##item), \ - (unsigned int)sizeof(field.__data_loc_##item)); \ + (unsigned int)sizeof(field.__data_loc_##item), \ + (unsigned int)is_signed_type(type)); \ if (!ret) \ return 0; @@ -159,7 +195,7 @@ #undef __get_str #undef TP_printk -#define TP_printk(fmt, args...) "%s, %s\n", #fmt, __stringify(args) +#define TP_printk(fmt, args...) "\"%s\", %s\n", fmt, __stringify(args) #undef TP_fast_assign #define TP_fast_assign(args...) args @@ -167,17 +203,50 @@ #undef TP_perf_assign #define TP_perf_assign(args...) -#undef TRACE_EVENT -#define TRACE_EVENT(call, proto, args, tstruct, func, print) \ +#undef DECLARE_EVENT_CLASS +#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, func, print) \ static int \ -ftrace_format_##call(struct ftrace_event_call *unused, \ - struct trace_seq *s) \ +ftrace_format_setup_##call(struct ftrace_event_call *unused, \ + struct trace_seq *s) \ { \ struct ftrace_raw_##call field __attribute__((unused)); \ int ret = 0; \ \ tstruct; \ \ + return ret; \ +} \ + \ +static int \ +ftrace_format_##call(struct ftrace_event_call *unused, \ + struct trace_seq *s) \ +{ \ + int ret = 0; \ + \ + ret = ftrace_format_setup_##call(unused, s); \ + if (!ret) \ + return ret; \ + \ + ret = trace_seq_printf(s, "\nprint fmt: " print); \ + \ + return ret; \ +} + +#undef DEFINE_EVENT +#define DEFINE_EVENT(template, name, proto, args) + +#undef DEFINE_EVENT_PRINT +#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \ +static int \ +ftrace_format_##name(struct ftrace_event_call *unused, \ + struct trace_seq *s) \ +{ \ + int ret = 0; \ + \ + ret = ftrace_format_setup_##template(unused, s); \ + if (!ret) \ + return ret; \ + \ trace_seq_printf(s, "\nprint fmt: " print); \ \ return ret; \ @@ -252,10 +321,11 @@ ftrace_format_##call(struct ftrace_event_call *unused, \ ftrace_print_symbols_seq(p, value, symbols); \ }) -#undef TRACE_EVENT -#define TRACE_EVENT(call, proto, args, tstruct, assign, print) \ +#undef DECLARE_EVENT_CLASS +#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ static enum print_line_t \ -ftrace_raw_output_##call(struct trace_iterator *iter, int flags) \ +ftrace_raw_output_id_##call(int event_id, const char *name, \ + struct trace_iterator *iter, int flags) \ { \ struct trace_seq *s = &iter->seq; \ struct ftrace_raw_##call *field; \ @@ -265,6 +335,47 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags) \ \ entry = iter->ent; \ \ + if (entry->type != event_id) { \ + WARN_ON_ONCE(1); \ + return TRACE_TYPE_UNHANDLED; \ + } \ + \ + field = (typeof(field))entry; \ + \ + p = &get_cpu_var(ftrace_event_seq); \ + trace_seq_init(p); \ + ret = trace_seq_printf(s, "%s: ", name); \ + if (ret) \ + ret = trace_seq_printf(s, print); \ + put_cpu(); \ + if (!ret) \ + return TRACE_TYPE_PARTIAL_LINE; \ + \ + return TRACE_TYPE_HANDLED; \ +} + +#undef DEFINE_EVENT +#define DEFINE_EVENT(template, name, proto, args) \ +static enum print_line_t \ +ftrace_raw_output_##name(struct trace_iterator *iter, int flags) \ +{ \ + return ftrace_raw_output_id_##template(event_##name.id, \ + #name, iter, flags); \ +} + +#undef DEFINE_EVENT_PRINT +#define DEFINE_EVENT_PRINT(template, call, proto, args, print) \ +static enum print_line_t \ +ftrace_raw_output_##call(struct trace_iterator *iter, int flags) \ +{ \ + struct trace_seq *s = &iter->seq; \ + struct ftrace_raw_##template *field; \ + struct trace_entry *entry; \ + struct trace_seq *p; \ + int ret; \ + \ + entry = iter->ent; \ + \ if (entry->type != event_##call.id) { \ WARN_ON_ONCE(1); \ return TRACE_TYPE_UNHANDLED; \ @@ -274,14 +385,16 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags) \ \ p = &get_cpu_var(ftrace_event_seq); \ trace_seq_init(p); \ - ret = trace_seq_printf(s, #call ": " print); \ + ret = trace_seq_printf(s, "%s: ", #call); \ + if (ret) \ + ret = trace_seq_printf(s, print); \ put_cpu(); \ if (!ret) \ return TRACE_TYPE_PARTIAL_LINE; \ \ return TRACE_TYPE_HANDLED; \ } - + #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) #undef __field_ext @@ -315,8 +428,8 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags) \ #undef __string #define __string(item, src) __dynamic_array(char, item, -1) -#undef TRACE_EVENT -#define TRACE_EVENT(call, proto, args, tstruct, func, print) \ +#undef DECLARE_EVENT_CLASS +#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, func, print) \ static int \ ftrace_define_fields_##call(struct ftrace_event_call *event_call) \ { \ @@ -332,6 +445,13 @@ ftrace_define_fields_##call(struct ftrace_event_call *event_call) \ return ret; \ } +#undef DEFINE_EVENT +#define DEFINE_EVENT(template, name, proto, args) + +#undef DEFINE_EVENT_PRINT +#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \ + DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args)) + #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) /* @@ -358,10 +478,10 @@ ftrace_define_fields_##call(struct ftrace_event_call *event_call) \ __data_size += (len) * sizeof(type); #undef __string -#define __string(item, src) __dynamic_array(char, item, strlen(src) + 1) \ +#define __string(item, src) __dynamic_array(char, item, strlen(src) + 1) -#undef TRACE_EVENT -#define TRACE_EVENT(call, proto, args, tstruct, assign, print) \ +#undef DECLARE_EVENT_CLASS +#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ static inline int ftrace_get_offsets_##call( \ struct ftrace_data_offsets_##call *__data_offsets, proto) \ { \ @@ -373,6 +493,13 @@ static inline int ftrace_get_offsets_##call( \ return __data_size; \ } +#undef DEFINE_EVENT +#define DEFINE_EVENT(template, name, proto, args) + +#undef DEFINE_EVENT_PRINT +#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \ + DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args)) + #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) #ifdef CONFIG_EVENT_PROFILE @@ -394,21 +521,28 @@ static inline int ftrace_get_offsets_##call( \ * */ -#undef TRACE_EVENT -#define TRACE_EVENT(call, proto, args, tstruct, assign, print) \ +#undef DECLARE_EVENT_CLASS +#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) + +#undef DEFINE_EVENT +#define DEFINE_EVENT(template, name, proto, args) \ \ -static void ftrace_profile_##call(proto); \ +static void ftrace_profile_##name(proto); \ \ -static int ftrace_profile_enable_##call(void) \ +static int ftrace_profile_enable_##name(struct ftrace_event_call *unused)\ { \ - return register_trace_##call(ftrace_profile_##call); \ + return register_trace_##name(ftrace_profile_##name); \ } \ \ -static void ftrace_profile_disable_##call(void) \ +static void ftrace_profile_disable_##name(struct ftrace_event_call *unused)\ { \ - unregister_trace_##call(ftrace_profile_##call); \ + unregister_trace_##name(ftrace_profile_##name); \ } +#undef DEFINE_EVENT_PRINT +#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \ + DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args)) + #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) #endif @@ -423,7 +557,7 @@ static void ftrace_profile_disable_##call(void) \ * event_trace_printk(_RET_IP_, "<call>: " <fmt>); * } * - * static int ftrace_reg_event_<call>(void) + * static int ftrace_reg_event_<call>(struct ftrace_event_call *unused) * { * int ret; * @@ -434,7 +568,7 @@ static void ftrace_profile_disable_##call(void) \ * return ret; * } * - * static void ftrace_unreg_event_<call>(void) + * static void ftrace_unreg_event_<call>(struct ftrace_event_call *unused) * { * unregister_trace_<call>(ftrace_event_<call>); * } @@ -469,7 +603,7 @@ static void ftrace_profile_disable_##call(void) \ * trace_current_buffer_unlock_commit(buffer, event, irq_flags, pc); * } * - * static int ftrace_raw_reg_event_<call>(void) + * static int ftrace_raw_reg_event_<call>(struct ftrace_event_call *unused) * { * int ret; * @@ -480,7 +614,7 @@ static void ftrace_profile_disable_##call(void) \ * return ret; * } * - * static void ftrace_unreg_event_<call>(void) + * static void ftrace_unreg_event_<call>(struct ftrace_event_call *unused) * { * unregister_trace_<call>(ftrace_raw_event_<call>); * } @@ -489,7 +623,7 @@ static void ftrace_profile_disable_##call(void) \ * .trace = ftrace_raw_output_<call>, <-- stage 2 * }; * - * static int ftrace_raw_init_event_<call>(void) + * static int ftrace_raw_init_event_<call>(struct ftrace_event_call *unused) * { * int id; * @@ -547,15 +681,13 @@ static void ftrace_profile_disable_##call(void) \ #define __assign_str(dst, src) \ strcpy(__get_str(dst), src); -#undef TRACE_EVENT -#define TRACE_EVENT(call, proto, args, tstruct, assign, print) \ +#undef DECLARE_EVENT_CLASS +#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ \ -static struct ftrace_event_call event_##call; \ - \ -static void ftrace_raw_event_##call(proto) \ +static void ftrace_raw_event_id_##call(struct ftrace_event_call *event_call, \ + proto) \ { \ struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\ - struct ftrace_event_call *event_call = &event_##call; \ struct ring_buffer_event *event; \ struct ftrace_raw_##call *entry; \ struct ring_buffer *buffer; \ @@ -569,7 +701,7 @@ static void ftrace_raw_event_##call(proto) \ __data_size = ftrace_get_offsets_##call(&__data_offsets, args); \ \ event = trace_current_buffer_lock_reserve(&buffer, \ - event_##call.id, \ + event_call->id, \ sizeof(*entry) + __data_size, \ irq_flags, pc); \ if (!event) \ @@ -584,9 +716,17 @@ static void ftrace_raw_event_##call(proto) \ if (!filter_current_check_discard(buffer, event_call, entry, event)) \ trace_nowake_buffer_unlock_commit(buffer, \ event, irq_flags, pc); \ +} + +#undef DEFINE_EVENT +#define DEFINE_EVENT(template, call, proto, args) \ + \ +static void ftrace_raw_event_##call(proto) \ +{ \ + ftrace_raw_event_id_##template(&event_##call, args); \ } \ \ -static int ftrace_raw_reg_event_##call(void *ptr) \ +static int ftrace_raw_reg_event_##call(struct ftrace_event_call *unused)\ { \ int ret; \ \ @@ -597,7 +737,7 @@ static int ftrace_raw_reg_event_##call(void *ptr) \ return ret; \ } \ \ -static void ftrace_raw_unreg_event_##call(void *ptr) \ +static void ftrace_raw_unreg_event_##call(struct ftrace_event_call *unused)\ { \ unregister_trace_##call(ftrace_raw_event_##call); \ } \ @@ -606,7 +746,7 @@ static struct trace_event ftrace_event_type_##call = { \ .trace = ftrace_raw_output_##call, \ }; \ \ -static int ftrace_raw_init_event_##call(void) \ +static int ftrace_raw_init_event_##call(struct ftrace_event_call *unused)\ { \ int id; \ \ @@ -616,7 +756,36 @@ static int ftrace_raw_init_event_##call(void) \ event_##call.id = id; \ INIT_LIST_HEAD(&event_##call.fields); \ return 0; \ -} \ +} + +#undef DEFINE_EVENT_PRINT +#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \ + DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args)) + +#include TRACE_INCLUDE(TRACE_INCLUDE_FILE) + +#undef DECLARE_EVENT_CLASS +#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) + +#undef DEFINE_EVENT +#define DEFINE_EVENT(template, call, proto, args) \ + \ +static struct ftrace_event_call __used \ +__attribute__((__aligned__(4))) \ +__attribute__((section("_ftrace_events"))) event_##call = { \ + .name = #call, \ + .system = __stringify(TRACE_SYSTEM), \ + .event = &ftrace_event_type_##call, \ + .raw_init = ftrace_raw_init_event_##call, \ + .regfunc = ftrace_raw_reg_event_##call, \ + .unregfunc = ftrace_raw_unreg_event_##call, \ + .show_format = ftrace_format_##template, \ + .define_fields = ftrace_define_fields_##template, \ + _TRACE_PROFILE_INIT(call) \ +} + +#undef DEFINE_EVENT_PRINT +#define DEFINE_EVENT_PRINT(template, call, proto, args, print) \ \ static struct ftrace_event_call __used \ __attribute__((__aligned__(4))) \ @@ -628,7 +797,7 @@ __attribute__((section("_ftrace_events"))) event_##call = { \ .regfunc = ftrace_raw_reg_event_##call, \ .unregfunc = ftrace_raw_unreg_event_##call, \ .show_format = ftrace_format_##call, \ - .define_fields = ftrace_define_fields_##call, \ + .define_fields = ftrace_define_fields_##template, \ _TRACE_PROFILE_INIT(call) \ } @@ -646,6 +815,7 @@ __attribute__((section("_ftrace_events"))) event_##call = { \ * struct ftrace_event_call *event_call = &event_<call>; * extern void perf_tp_event(int, u64, u64, void *, int); * struct ftrace_raw_##call *entry; + * struct perf_trace_buf *trace_buf; * u64 __addr = 0, __count = 1; * unsigned long irq_flags; * struct trace_entry *ent; @@ -670,14 +840,25 @@ __attribute__((section("_ftrace_events"))) event_##call = { \ * __cpu = smp_processor_id(); * * if (in_nmi()) - * raw_data = rcu_dereference(trace_profile_buf_nmi); + * trace_buf = rcu_dereference(perf_trace_buf_nmi); * else - * raw_data = rcu_dereference(trace_profile_buf); + * trace_buf = rcu_dereference(perf_trace_buf); * - * if (!raw_data) + * if (!trace_buf) * goto end; * - * raw_data = per_cpu_ptr(raw_data, __cpu); + * trace_buf = per_cpu_ptr(trace_buf, __cpu); + * + * // Avoid recursion from perf that could mess up the buffer + * if (trace_buf->recursion++) + * goto end_recursion; + * + * raw_data = trace_buf->buf; + * + * // Make recursion update visible before entering perf_tp_event + * // so that we protect from perf recursions. + * + * barrier(); * * //zero dead bytes from alignment to avoid stack leak to userspace: * *(u64 *)(&raw_data[__entry_size - sizeof(u64)]) = 0ULL; @@ -704,21 +885,26 @@ __attribute__((section("_ftrace_events"))) event_##call = { \ #undef __perf_count #define __perf_count(c) __count = (c) -#undef TRACE_EVENT -#define TRACE_EVENT(call, proto, args, tstruct, assign, print) \ -static void ftrace_profile_##call(proto) \ +#undef DECLARE_EVENT_CLASS +#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ +static void \ +ftrace_profile_templ_##call(struct ftrace_event_call *event_call, \ + proto) \ { \ struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\ - struct ftrace_event_call *event_call = &event_##call; \ - extern void perf_tp_event(int, u64, u64, void *, int); \ + extern int perf_swevent_get_recursion_context(void); \ + extern void perf_swevent_put_recursion_context(int rctx); \ + extern void perf_tp_event(int, u64, u64, void *, int); \ struct ftrace_raw_##call *entry; \ u64 __addr = 0, __count = 1; \ unsigned long irq_flags; \ struct trace_entry *ent; \ int __entry_size; \ int __data_size; \ + char *trace_buf; \ char *raw_data; \ int __cpu; \ + int rctx; \ int pc; \ \ pc = preempt_count(); \ @@ -733,17 +919,22 @@ static void ftrace_profile_##call(proto) \ return; \ \ local_irq_save(irq_flags); \ + \ + rctx = perf_swevent_get_recursion_context(); \ + if (rctx < 0) \ + goto end_recursion; \ + \ __cpu = smp_processor_id(); \ \ if (in_nmi()) \ - raw_data = rcu_dereference(trace_profile_buf_nmi); \ + trace_buf = rcu_dereference(perf_trace_buf_nmi); \ else \ - raw_data = rcu_dereference(trace_profile_buf); \ + trace_buf = rcu_dereference(perf_trace_buf); \ \ - if (!raw_data) \ + if (!trace_buf) \ goto end; \ \ - raw_data = per_cpu_ptr(raw_data, __cpu); \ + raw_data = per_cpu_ptr(trace_buf, __cpu); \ \ *(u64 *)(&raw_data[__entry_size - sizeof(u64)]) = 0ULL; \ entry = (struct ftrace_raw_##call *)raw_data; \ @@ -759,10 +950,25 @@ static void ftrace_profile_##call(proto) \ __entry_size); \ \ end: \ + perf_swevent_put_recursion_context(rctx); \ +end_recursion: \ local_irq_restore(irq_flags); \ \ } +#undef DEFINE_EVENT +#define DEFINE_EVENT(template, call, proto, args) \ +static void ftrace_profile_##call(proto) \ +{ \ + struct ftrace_event_call *event_call = &event_##call; \ + \ + ftrace_profile_templ_##template(event_call, args); \ +} + +#undef DEFINE_EVENT_PRINT +#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \ + DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args)) + #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) #endif /* CONFIG_EVENT_PROFILE */ diff --git a/include/trace/power.h b/include/trace/power.h deleted file mode 100644 index ef204666e983..000000000000 --- a/include/trace/power.h +++ /dev/null @@ -1,32 +0,0 @@ -#ifndef _TRACE_POWER_H -#define _TRACE_POWER_H - -#include <linux/ktime.h> -#include <linux/tracepoint.h> - -enum { - POWER_NONE = 0, - POWER_CSTATE = 1, - POWER_PSTATE = 2, -}; - -struct power_trace { - ktime_t stamp; - ktime_t end; - int type; - int state; -}; - -DECLARE_TRACE(power_start, - TP_PROTO(struct power_trace *it, unsigned int type, unsigned int state), - TP_ARGS(it, type, state)); - -DECLARE_TRACE(power_mark, - TP_PROTO(struct power_trace *it, unsigned int type, unsigned int state), - TP_ARGS(it, type, state)); - -DECLARE_TRACE(power_end, - TP_PROTO(struct power_trace *it), - TP_ARGS(it)); - -#endif /* _TRACE_POWER_H */ diff --git a/include/trace/syscall.h b/include/trace/syscall.h index 5dc283ba5ae0..961fda3556bb 100644 --- a/include/trace/syscall.h +++ b/include/trace/syscall.h @@ -12,51 +12,48 @@ * A syscall entry in the ftrace syscalls array. * * @name: name of the syscall + * @syscall_nr: number of the syscall * @nb_args: number of parameters it takes * @types: list of types as strings * @args: list of args as strings (args[i] matches types[i]) - * @enter_id: associated ftrace enter event id - * @exit_id: associated ftrace exit event id * @enter_event: associated syscall_enter trace event * @exit_event: associated syscall_exit trace event */ struct syscall_metadata { const char *name; + int syscall_nr; int nb_args; const char **types; const char **args; - int enter_id; - int exit_id; struct ftrace_event_call *enter_event; struct ftrace_event_call *exit_event; }; #ifdef CONFIG_FTRACE_SYSCALLS -extern struct syscall_metadata *syscall_nr_to_meta(int nr); -extern int syscall_name_to_nr(char *name); -void set_syscall_enter_id(int num, int id); -void set_syscall_exit_id(int num, int id); -extern struct trace_event event_syscall_enter; -extern struct trace_event event_syscall_exit; -extern int reg_event_syscall_enter(void *ptr); -extern void unreg_event_syscall_enter(void *ptr); -extern int reg_event_syscall_exit(void *ptr); -extern void unreg_event_syscall_exit(void *ptr); +extern unsigned long arch_syscall_addr(int nr); +extern int init_syscall_trace(struct ftrace_event_call *call); + extern int syscall_enter_format(struct ftrace_event_call *call, struct trace_seq *s); extern int syscall_exit_format(struct ftrace_event_call *call, struct trace_seq *s); extern int syscall_enter_define_fields(struct ftrace_event_call *call); extern int syscall_exit_define_fields(struct ftrace_event_call *call); +extern int reg_event_syscall_enter(struct ftrace_event_call *call); +extern void unreg_event_syscall_enter(struct ftrace_event_call *call); +extern int reg_event_syscall_exit(struct ftrace_event_call *call); +extern void unreg_event_syscall_exit(struct ftrace_event_call *call); +extern int +ftrace_format_syscall(struct ftrace_event_call *call, struct trace_seq *s); enum print_line_t print_syscall_enter(struct trace_iterator *iter, int flags); enum print_line_t print_syscall_exit(struct trace_iterator *iter, int flags); #endif #ifdef CONFIG_EVENT_PROFILE -int reg_prof_syscall_enter(char *name); -void unreg_prof_syscall_enter(char *name); -int reg_prof_syscall_exit(char *name); -void unreg_prof_syscall_exit(char *name); +int prof_sysenter_enable(struct ftrace_event_call *call); +void prof_sysenter_disable(struct ftrace_event_call *call); +int prof_sysexit_enable(struct ftrace_event_call *call); +void prof_sysexit_disable(struct ftrace_event_call *call); #endif diff --git a/init/Kconfig b/init/Kconfig index 9e03ef8b311e..38899243213d 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -334,6 +334,15 @@ config TREE_PREEMPT_RCU is also required. It also scales down nicely to smaller systems. +config TINY_RCU + bool "UP-only small-memory-footprint RCU" + depends on !SMP + help + This option selects the RCU implementation that is + designed for UP systems from which real-time response + is not required. This option greatly reduces the + memory footprint of RCU. + endchoice config RCU_TRACE @@ -606,7 +615,7 @@ config SYSFS_DEPRECATED bool config SYSFS_DEPRECATED_V2 - bool "remove sysfs features which may confuse old userspace tools" + bool "enable deprecated sysfs features which may confuse old userspace tools" depends on SYSFS default n select SYSFS_DEPRECATED @@ -754,6 +763,7 @@ config UID16 config SYSCTL_SYSCALL bool "Sysctl syscall support" if EMBEDDED + depends on PROC_SYSCTL default y select SYSCTL ---help--- @@ -1098,6 +1108,16 @@ config SLOW_WORK See Documentation/slow-work.txt. +config SLOW_WORK_DEBUG + bool "Slow work debugging through debugfs" + default n + depends on SLOW_WORK && DEBUG_FS + help + Display the contents of the slow work run queue through debugfs, + including items currently executing. + + See Documentation/slow-work.txt. + endmenu # General setup config HAVE_GENERIC_DMA_COHERENT @@ -1210,3 +1230,4 @@ source "block/Kconfig" config PREEMPT_NOTIFIERS bool +source "kernel/Kconfig.locks" diff --git a/init/main.c b/init/main.c index 5988debfc505..4051d75dd2d6 100644 --- a/init/main.c +++ b/init/main.c @@ -251,7 +251,7 @@ early_param("loglevel", loglevel); /* * Unknown boot options get handed to init, unless they look like - * failed parameters + * unused parameters (modprobe will find them in /proc/cmdline). */ static int __init unknown_bootoption(char *param, char *val) { @@ -272,14 +272,9 @@ static int __init unknown_bootoption(char *param, char *val) if (obsolete_checksetup(param)) return 0; - /* - * Preemptive maintenance for "why didn't my misspelled command - * line work?" - */ - if (strchr(param, '.') && (!val || strchr(param, '.') < val)) { - printk(KERN_ERR "Unknown boot option `%s': ignoring\n", param); + /* Unused module parameter. */ + if (strchr(param, '.') && (!val || strchr(param, '.') < val)) return 0; - } if (panic_later) return 0; diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c index 7d3704750efc..56410faa4550 100644 --- a/ipc/ipc_sysctl.c +++ b/ipc/ipc_sysctl.c @@ -129,136 +129,60 @@ static int proc_ipcauto_dointvec_minmax(ctl_table *table, int write, #define proc_ipcauto_dointvec_minmax NULL #endif -#ifdef CONFIG_SYSCTL_SYSCALL -/* The generic sysctl ipc data routine. */ -static int sysctl_ipc_data(ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - size_t len; - void *data; - - /* Get out of I don't have a variable */ - if (!table->data || !table->maxlen) - return -ENOTDIR; - - data = get_ipc(table); - if (!data) - return -ENOTDIR; - - if (oldval && oldlenp) { - if (get_user(len, oldlenp)) - return -EFAULT; - if (len) { - if (len > table->maxlen) - len = table->maxlen; - if (copy_to_user(oldval, data, len)) - return -EFAULT; - if (put_user(len, oldlenp)) - return -EFAULT; - } - } - - if (newval && newlen) { - if (newlen > table->maxlen) - newlen = table->maxlen; - - if (copy_from_user(data, newval, newlen)) - return -EFAULT; - } - return 1; -} - -static int sysctl_ipc_registered_data(ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - int rc; - - rc = sysctl_ipc_data(table, oldval, oldlenp, newval, newlen); - - if (newval && newlen && rc > 0) - /* - * Tunable has successfully been changed from userland - */ - unregister_ipcns_notifier(current->nsproxy->ipc_ns); - - return rc; -} -#else -#define sysctl_ipc_data NULL -#define sysctl_ipc_registered_data NULL -#endif - static int zero; static int one = 1; static struct ctl_table ipc_kern_table[] = { { - .ctl_name = KERN_SHMMAX, .procname = "shmmax", .data = &init_ipc_ns.shm_ctlmax, .maxlen = sizeof (init_ipc_ns.shm_ctlmax), .mode = 0644, .proc_handler = proc_ipc_doulongvec_minmax, - .strategy = sysctl_ipc_data, }, { - .ctl_name = KERN_SHMALL, .procname = "shmall", .data = &init_ipc_ns.shm_ctlall, .maxlen = sizeof (init_ipc_ns.shm_ctlall), .mode = 0644, .proc_handler = proc_ipc_doulongvec_minmax, - .strategy = sysctl_ipc_data, }, { - .ctl_name = KERN_SHMMNI, .procname = "shmmni", .data = &init_ipc_ns.shm_ctlmni, .maxlen = sizeof (init_ipc_ns.shm_ctlmni), .mode = 0644, .proc_handler = proc_ipc_dointvec, - .strategy = sysctl_ipc_data, }, { - .ctl_name = KERN_MSGMAX, .procname = "msgmax", .data = &init_ipc_ns.msg_ctlmax, .maxlen = sizeof (init_ipc_ns.msg_ctlmax), .mode = 0644, .proc_handler = proc_ipc_dointvec, - .strategy = sysctl_ipc_data, }, { - .ctl_name = KERN_MSGMNI, .procname = "msgmni", .data = &init_ipc_ns.msg_ctlmni, .maxlen = sizeof (init_ipc_ns.msg_ctlmni), .mode = 0644, .proc_handler = proc_ipc_callback_dointvec, - .strategy = sysctl_ipc_registered_data, }, { - .ctl_name = KERN_MSGMNB, .procname = "msgmnb", .data = &init_ipc_ns.msg_ctlmnb, .maxlen = sizeof (init_ipc_ns.msg_ctlmnb), .mode = 0644, .proc_handler = proc_ipc_dointvec, - .strategy = sysctl_ipc_data, }, { - .ctl_name = KERN_SEM, .procname = "sem", .data = &init_ipc_ns.sem_ctls, .maxlen = 4*sizeof (int), .mode = 0644, .proc_handler = proc_ipc_dointvec, - .strategy = sysctl_ipc_data, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "auto_msgmni", .data = &init_ipc_ns.auto_msgmni, .maxlen = sizeof(int), @@ -272,7 +196,6 @@ static struct ctl_table ipc_kern_table[] = { static struct ctl_table ipc_root_table[] = { { - .ctl_name = CTL_KERN, .procname = "kernel", .mode = 0555, .child = ipc_kern_table, diff --git a/ipc/mq_sysctl.c b/ipc/mq_sysctl.c index 8a058711fc10..0c09366b96f3 100644 --- a/ipc/mq_sysctl.c +++ b/ipc/mq_sysctl.c @@ -88,7 +88,7 @@ static ctl_table mq_sysctls[] = { .extra1 = &msg_maxsize_limit_min, .extra2 = &msg_maxsize_limit_max, }, - { .ctl_name = 0 } + {} }; static ctl_table mq_sysctl_dir[] = { @@ -97,17 +97,16 @@ static ctl_table mq_sysctl_dir[] = { .mode = 0555, .child = mq_sysctls, }, - { .ctl_name = 0 } + {} }; static ctl_table mq_sysctl_root[] = { { - .ctl_name = CTL_FS, .procname = "fs", .mode = 0555, .child = mq_sysctl_dir, }, - { .ctl_name = 0 } + {} }; struct ctl_table_header *mq_register_sysctl_table(void) diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks new file mode 100644 index 000000000000..88c92fb44618 --- /dev/null +++ b/kernel/Kconfig.locks @@ -0,0 +1,202 @@ +# +# The ARCH_INLINE foo is necessary because select ignores "depends on" +# +config ARCH_INLINE_SPIN_TRYLOCK + bool + +config ARCH_INLINE_SPIN_TRYLOCK_BH + bool + +config ARCH_INLINE_SPIN_LOCK + bool + +config ARCH_INLINE_SPIN_LOCK_BH + bool + +config ARCH_INLINE_SPIN_LOCK_IRQ + bool + +config ARCH_INLINE_SPIN_LOCK_IRQSAVE + bool + +config ARCH_INLINE_SPIN_UNLOCK + bool + +config ARCH_INLINE_SPIN_UNLOCK_BH + bool + +config ARCH_INLINE_SPIN_UNLOCK_IRQ + bool + +config ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE + bool + + +config ARCH_INLINE_READ_TRYLOCK + bool + +config ARCH_INLINE_READ_LOCK + bool + +config ARCH_INLINE_READ_LOCK_BH + bool + +config ARCH_INLINE_READ_LOCK_IRQ + bool + +config ARCH_INLINE_READ_LOCK_IRQSAVE + bool + +config ARCH_INLINE_READ_UNLOCK + bool + +config ARCH_INLINE_READ_UNLOCK_BH + bool + +config ARCH_INLINE_READ_UNLOCK_IRQ + bool + +config ARCH_INLINE_READ_UNLOCK_IRQRESTORE + bool + + +config ARCH_INLINE_WRITE_TRYLOCK + bool + +config ARCH_INLINE_WRITE_LOCK + bool + +config ARCH_INLINE_WRITE_LOCK_BH + bool + +config ARCH_INLINE_WRITE_LOCK_IRQ + bool + +config ARCH_INLINE_WRITE_LOCK_IRQSAVE + bool + +config ARCH_INLINE_WRITE_UNLOCK + bool + +config ARCH_INLINE_WRITE_UNLOCK_BH + bool + +config ARCH_INLINE_WRITE_UNLOCK_IRQ + bool + +config ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE + bool + +# +# lock_* functions are inlined when: +# - DEBUG_SPINLOCK=n and GENERIC_LOCKBREAK=n and ARCH_INLINE_*LOCK=y +# +# trylock_* functions are inlined when: +# - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y +# +# unlock and unlock_irq functions are inlined when: +# - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y +# or +# - DEBUG_SPINLOCK=n and PREEMPT=n +# +# unlock_bh and unlock_irqrestore functions are inlined when: +# - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y +# + +config INLINE_SPIN_TRYLOCK + def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_TRYLOCK + +config INLINE_SPIN_TRYLOCK_BH + def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_TRYLOCK_BH + +config INLINE_SPIN_LOCK + def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && ARCH_INLINE_SPIN_LOCK + +config INLINE_SPIN_LOCK_BH + def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \ + ARCH_INLINE_SPIN_LOCK_BH + +config INLINE_SPIN_LOCK_IRQ + def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \ + ARCH_INLINE_SPIN_LOCK_IRQ + +config INLINE_SPIN_LOCK_IRQSAVE + def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \ + ARCH_INLINE_SPIN_LOCK_IRQSAVE + +config INLINE_SPIN_UNLOCK + def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_SPIN_UNLOCK) + +config INLINE_SPIN_UNLOCK_BH + def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_UNLOCK_BH + +config INLINE_SPIN_UNLOCK_IRQ + def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_SPIN_UNLOCK_BH) + +config INLINE_SPIN_UNLOCK_IRQRESTORE + def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE + + +config INLINE_READ_TRYLOCK + def_bool !DEBUG_SPINLOCK && ARCH_INLINE_READ_TRYLOCK + +config INLINE_READ_LOCK + def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && ARCH_INLINE_READ_LOCK + +config INLINE_READ_LOCK_BH + def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \ + ARCH_INLINE_READ_LOCK_BH + +config INLINE_READ_LOCK_IRQ + def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \ + ARCH_INLINE_READ_LOCK_IRQ + +config INLINE_READ_LOCK_IRQSAVE + def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \ + ARCH_INLINE_READ_LOCK_IRQSAVE + +config INLINE_READ_UNLOCK + def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_READ_UNLOCK) + +config INLINE_READ_UNLOCK_BH + def_bool !DEBUG_SPINLOCK && ARCH_INLINE_READ_UNLOCK_BH + +config INLINE_READ_UNLOCK_IRQ + def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_READ_UNLOCK_BH) + +config INLINE_READ_UNLOCK_IRQRESTORE + def_bool !DEBUG_SPINLOCK && ARCH_INLINE_READ_UNLOCK_IRQRESTORE + + +config INLINE_WRITE_TRYLOCK + def_bool !DEBUG_SPINLOCK && ARCH_INLINE_WRITE_TRYLOCK + +config INLINE_WRITE_LOCK + def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && ARCH_INLINE_WRITE_LOCK + +config INLINE_WRITE_LOCK_BH + def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \ + ARCH_INLINE_WRITE_LOCK_BH + +config INLINE_WRITE_LOCK_IRQ + def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \ + ARCH_INLINE_WRITE_LOCK_IRQ + +config INLINE_WRITE_LOCK_IRQSAVE + def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \ + ARCH_INLINE_WRITE_LOCK_IRQSAVE + +config INLINE_WRITE_UNLOCK + def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_WRITE_UNLOCK) + +config INLINE_WRITE_UNLOCK_BH + def_bool !DEBUG_SPINLOCK && ARCH_INLINE_WRITE_UNLOCK_BH + +config INLINE_WRITE_UNLOCK_IRQ + def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_WRITE_UNLOCK_BH) + +config INLINE_WRITE_UNLOCK_IRQRESTORE + def_bool !DEBUG_SPINLOCK && ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE + +config MUTEX_SPIN_ON_OWNER + def_bool SMP && !DEBUG_MUTEXES && !HAVE_DEFAULT_NO_SPIN_MUTEXES diff --git a/kernel/Makefile b/kernel/Makefile index b8d4cd8ac0b9..9943202b4355 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -4,7 +4,7 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o \ cpu.o exit.o itimer.o time.o softirq.o resource.o \ - sysctl.o capability.o ptrace.o timer.o user.o \ + sysctl.o sysctl_binary.o capability.o ptrace.o timer.o user.o \ signal.o sys.o kmod.o workqueue.o pid.o \ rcupdate.o extable.o params.o posix-timers.o \ kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \ @@ -21,6 +21,7 @@ CFLAGS_REMOVE_mutex-debug.o = -pg CFLAGS_REMOVE_rtmutex-debug.o = -pg CFLAGS_REMOVE_cgroup-debug.o = -pg CFLAGS_REMOVE_sched_clock.o = -pg +CFLAGS_REMOVE_perf_event.o = -pg endif obj-$(CONFIG_FREEZER) += freezer.o @@ -82,6 +83,7 @@ obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o obj-$(CONFIG_TREE_RCU) += rcutree.o obj-$(CONFIG_TREE_PREEMPT_RCU) += rcutree.o obj-$(CONFIG_TREE_RCU_TRACE) += rcutree_trace.o +obj-$(CONFIG_TINY_RCU) += rcutiny.o obj-$(CONFIG_RELAY) += relay.o obj-$(CONFIG_SYSCTL) += utsname_sysctl.o obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o @@ -94,7 +96,9 @@ obj-$(CONFIG_X86_DS) += trace/ obj-$(CONFIG_RING_BUFFER) += trace/ obj-$(CONFIG_SMP) += sched_cpupri.o obj-$(CONFIG_SLOW_WORK) += slow-work.o +obj-$(CONFIG_SLOW_WORK_DEBUG) += slow-work-debugfs.o obj-$(CONFIG_PERF_EVENTS) += perf_event.o +obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y) # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is diff --git a/kernel/capability.c b/kernel/capability.c index 4e17041963f5..7f876e60521f 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -29,7 +29,6 @@ EXPORT_SYMBOL(__cap_empty_set); EXPORT_SYMBOL(__cap_full_set); EXPORT_SYMBOL(__cap_init_eff_set); -#ifdef CONFIG_SECURITY_FILE_CAPABILITIES int file_caps_enabled = 1; static int __init file_caps_disable(char *str) @@ -38,7 +37,6 @@ static int __init file_caps_disable(char *str) return 1; } __setup("no_file_caps", file_caps_disable); -#endif /* * More recent versions of libcap are available from: @@ -169,8 +167,8 @@ SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr) kernel_cap_t pE, pI, pP; ret = cap_validate_magic(header, &tocopy); - if (ret != 0) - return ret; + if ((dataptr == NULL) || (ret != 0)) + return ((dataptr == NULL) && (ret == -EINVAL)) ? 0 : ret; if (get_user(pid, &header->pid)) return -EFAULT; @@ -238,7 +236,7 @@ SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr) SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data) { struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S]; - unsigned i, tocopy; + unsigned i, tocopy, copybytes; kernel_cap_t inheritable, permitted, effective; struct cred *new; int ret; @@ -255,8 +253,11 @@ SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data) if (pid != 0 && pid != task_pid_vnr(current)) return -EPERM; - if (copy_from_user(&kdata, data, - tocopy * sizeof(struct __user_cap_data_struct))) + copybytes = tocopy * sizeof(struct __user_cap_data_struct); + if (copybytes > sizeof(kdata)) + return -EFAULT; + + if (copy_from_user(&kdata, data, copybytes)) return -EFAULT; for (i = 0; i < tocopy; i++) { diff --git a/kernel/cpuset.c b/kernel/cpuset.c index b5cb469d2545..3cf2183b472d 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -537,8 +537,7 @@ update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *c) * element of the partition (one sched domain) to be passed to * partition_sched_domains(). */ -/* FIXME: see the FIXME in partition_sched_domains() */ -static int generate_sched_domains(struct cpumask **domains, +static int generate_sched_domains(cpumask_var_t **domains, struct sched_domain_attr **attributes) { LIST_HEAD(q); /* queue of cpusets to be scanned */ @@ -546,7 +545,7 @@ static int generate_sched_domains(struct cpumask **domains, struct cpuset **csa; /* array of all cpuset ptrs */ int csn; /* how many cpuset ptrs in csa so far */ int i, j, k; /* indices for partition finding loops */ - struct cpumask *doms; /* resulting partition; i.e. sched domains */ + cpumask_var_t *doms; /* resulting partition; i.e. sched domains */ struct sched_domain_attr *dattr; /* attributes for custom domains */ int ndoms = 0; /* number of sched domains in result */ int nslot; /* next empty doms[] struct cpumask slot */ @@ -557,7 +556,8 @@ static int generate_sched_domains(struct cpumask **domains, /* Special case for the 99% of systems with one, full, sched domain */ if (is_sched_load_balance(&top_cpuset)) { - doms = kmalloc(cpumask_size(), GFP_KERNEL); + ndoms = 1; + doms = alloc_sched_domains(ndoms); if (!doms) goto done; @@ -566,9 +566,8 @@ static int generate_sched_domains(struct cpumask **domains, *dattr = SD_ATTR_INIT; update_domain_attr_tree(dattr, &top_cpuset); } - cpumask_copy(doms, top_cpuset.cpus_allowed); + cpumask_copy(doms[0], top_cpuset.cpus_allowed); - ndoms = 1; goto done; } @@ -636,7 +635,7 @@ restart: * Now we know how many domains to create. * Convert <csn, csa> to <ndoms, doms> and populate cpu masks. */ - doms = kmalloc(ndoms * cpumask_size(), GFP_KERNEL); + doms = alloc_sched_domains(ndoms); if (!doms) goto done; @@ -656,7 +655,7 @@ restart: continue; } - dp = doms + nslot; + dp = doms[nslot]; if (nslot == ndoms) { static int warnings = 10; @@ -718,7 +717,7 @@ done: static void do_rebuild_sched_domains(struct work_struct *unused) { struct sched_domain_attr *attr; - struct cpumask *doms; + cpumask_var_t *doms; int ndoms; get_online_cpus(); @@ -2052,7 +2051,7 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb, unsigned long phase, void *unused_cpu) { struct sched_domain_attr *attr; - struct cpumask *doms; + cpumask_var_t *doms; int ndoms; switch (phase) { @@ -2537,15 +2536,9 @@ const struct file_operations proc_cpuset_operations = { }; #endif /* CONFIG_PROC_PID_CPUSET */ -/* Display task cpus_allowed, mems_allowed in /proc/<pid>/status file. */ +/* Display task mems_allowed in /proc/<pid>/status file. */ void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task) { - seq_printf(m, "Cpus_allowed:\t"); - seq_cpumask(m, &task->cpus_allowed); - seq_printf(m, "\n"); - seq_printf(m, "Cpus_allowed_list:\t"); - seq_cpumask_list(m, &task->cpus_allowed); - seq_printf(m, "\n"); seq_printf(m, "Mems_allowed:\t"); seq_nodemask(m, &task->mems_allowed); seq_printf(m, "\n"); diff --git a/kernel/exit.c b/kernel/exit.c index f7864ac2ecc1..80ae941cfd2e 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -49,6 +49,7 @@ #include <linux/init_task.h> #include <linux/perf_event.h> #include <trace/events/sched.h> +#include <linux/hw_breakpoint.h> #include <asm/uaccess.h> #include <asm/unistd.h> @@ -110,9 +111,9 @@ static void __exit_signal(struct task_struct *tsk) * We won't ever get here for the group leader, since it * will have been the last reference on the signal_struct. */ - sig->utime = cputime_add(sig->utime, task_utime(tsk)); - sig->stime = cputime_add(sig->stime, task_stime(tsk)); - sig->gtime = cputime_add(sig->gtime, task_gtime(tsk)); + sig->utime = cputime_add(sig->utime, tsk->utime); + sig->stime = cputime_add(sig->stime, tsk->stime); + sig->gtime = cputime_add(sig->gtime, tsk->gtime); sig->min_flt += tsk->min_flt; sig->maj_flt += tsk->maj_flt; sig->nvcsw += tsk->nvcsw; @@ -978,6 +979,10 @@ NORET_TYPE void do_exit(long code) proc_exit_connector(tsk); /* + * FIXME: do that only when needed, using sched_exit tracepoint + */ + flush_ptrace_hw_breakpoint(tsk); + /* * Flush inherited counters to the parent - before the parent * gets woken up by child-exit notifications. */ @@ -1205,6 +1210,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) struct signal_struct *psig; struct signal_struct *sig; unsigned long maxrss; + cputime_t tgutime, tgstime; /* * The resource counters for the group leader are in its @@ -1220,20 +1226,23 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) * need to protect the access to parent->signal fields, * as other threads in the parent group can be right * here reaping other children at the same time. + * + * We use thread_group_times() to get times for the thread + * group, which consolidates times for all threads in the + * group including the group leader. */ + thread_group_times(p, &tgutime, &tgstime); spin_lock_irq(&p->real_parent->sighand->siglock); psig = p->real_parent->signal; sig = p->signal; psig->cutime = cputime_add(psig->cutime, - cputime_add(p->utime, - cputime_add(sig->utime, - sig->cutime))); + cputime_add(tgutime, + sig->cutime)); psig->cstime = cputime_add(psig->cstime, - cputime_add(p->stime, - cputime_add(sig->stime, - sig->cstime))); + cputime_add(tgstime, + sig->cstime)); psig->cgtime = cputime_add(psig->cgtime, cputime_add(p->gtime, diff --git a/kernel/fork.c b/kernel/fork.c index 166b8c49257c..3d6f121bbe8a 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -884,6 +884,9 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero; sig->gtime = cputime_zero; sig->cgtime = cputime_zero; +#ifndef CONFIG_VIRT_CPU_ACCOUNTING + sig->prev_utime = sig->prev_stime = cputime_zero; +#endif sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0; sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0; sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0; @@ -1066,8 +1069,10 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->gtime = cputime_zero; p->utimescaled = cputime_zero; p->stimescaled = cputime_zero; +#ifndef CONFIG_VIRT_CPU_ACCOUNTING p->prev_utime = cputime_zero; p->prev_stime = cputime_zero; +#endif p->default_timer_slack_ns = current->timer_slack_ns; diff --git a/kernel/hung_task.c b/kernel/hung_task.c index d4e841747400..0c642d51aac2 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -144,7 +144,7 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout) rcu_read_lock(); do_each_thread(g, t) { - if (!--max_count) + if (!max_count--) goto unlock; if (!--batch_count) { batch_count = HUNG_TASK_BATCHING; diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c new file mode 100644 index 000000000000..cf5ee1628411 --- /dev/null +++ b/kernel/hw_breakpoint.c @@ -0,0 +1,423 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) 2007 Alan Stern + * Copyright (C) IBM Corporation, 2009 + * Copyright (C) 2009, Frederic Weisbecker <fweisbec@gmail.com> + * + * Thanks to Ingo Molnar for his many suggestions. + * + * Authors: Alan Stern <stern@rowland.harvard.edu> + * K.Prasad <prasad@linux.vnet.ibm.com> + * Frederic Weisbecker <fweisbec@gmail.com> + */ + +/* + * HW_breakpoint: a unified kernel/user-space hardware breakpoint facility, + * using the CPU's debug registers. + * This file contains the arch-independent routines. + */ + +#include <linux/irqflags.h> +#include <linux/kallsyms.h> +#include <linux/notifier.h> +#include <linux/kprobes.h> +#include <linux/kdebug.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/percpu.h> +#include <linux/sched.h> +#include <linux/init.h> +#include <linux/smp.h> + +#include <linux/hw_breakpoint.h> + +/* + * Constraints data + */ + +/* Number of pinned cpu breakpoints in a cpu */ +static DEFINE_PER_CPU(unsigned int, nr_cpu_bp_pinned); + +/* Number of pinned task breakpoints in a cpu */ +static DEFINE_PER_CPU(unsigned int, task_bp_pinned[HBP_NUM]); + +/* Number of non-pinned cpu/task breakpoints in a cpu */ +static DEFINE_PER_CPU(unsigned int, nr_bp_flexible); + +/* Gather the number of total pinned and un-pinned bp in a cpuset */ +struct bp_busy_slots { + unsigned int pinned; + unsigned int flexible; +}; + +/* Serialize accesses to the above constraints */ +static DEFINE_MUTEX(nr_bp_mutex); + +/* + * Report the maximum number of pinned breakpoints a task + * have in this cpu + */ +static unsigned int max_task_bp_pinned(int cpu) +{ + int i; + unsigned int *tsk_pinned = per_cpu(task_bp_pinned, cpu); + + for (i = HBP_NUM -1; i >= 0; i--) { + if (tsk_pinned[i] > 0) + return i + 1; + } + + return 0; +} + +/* + * Report the number of pinned/un-pinned breakpoints we have in + * a given cpu (cpu > -1) or in all of them (cpu = -1). + */ +static void fetch_bp_busy_slots(struct bp_busy_slots *slots, int cpu) +{ + if (cpu >= 0) { + slots->pinned = per_cpu(nr_cpu_bp_pinned, cpu); + slots->pinned += max_task_bp_pinned(cpu); + slots->flexible = per_cpu(nr_bp_flexible, cpu); + + return; + } + + for_each_online_cpu(cpu) { + unsigned int nr; + + nr = per_cpu(nr_cpu_bp_pinned, cpu); + nr += max_task_bp_pinned(cpu); + + if (nr > slots->pinned) + slots->pinned = nr; + + nr = per_cpu(nr_bp_flexible, cpu); + + if (nr > slots->flexible) + slots->flexible = nr; + } +} + +/* + * Add a pinned breakpoint for the given task in our constraint table + */ +static void toggle_bp_task_slot(struct task_struct *tsk, int cpu, bool enable) +{ + int count = 0; + struct perf_event *bp; + struct perf_event_context *ctx = tsk->perf_event_ctxp; + unsigned int *tsk_pinned; + struct list_head *list; + unsigned long flags; + + if (WARN_ONCE(!ctx, "No perf context for this task")) + return; + + list = &ctx->event_list; + + spin_lock_irqsave(&ctx->lock, flags); + + /* + * The current breakpoint counter is not included in the list + * at the open() callback time + */ + list_for_each_entry(bp, list, event_entry) { + if (bp->attr.type == PERF_TYPE_BREAKPOINT) + count++; + } + + spin_unlock_irqrestore(&ctx->lock, flags); + + if (WARN_ONCE(count < 0, "No breakpoint counter found in the counter list")) + return; + + tsk_pinned = per_cpu(task_bp_pinned, cpu); + if (enable) { + tsk_pinned[count]++; + if (count > 0) + tsk_pinned[count-1]--; + } else { + tsk_pinned[count]--; + if (count > 0) + tsk_pinned[count-1]++; + } +} + +/* + * Add/remove the given breakpoint in our constraint table + */ +static void toggle_bp_slot(struct perf_event *bp, bool enable) +{ + int cpu = bp->cpu; + struct task_struct *tsk = bp->ctx->task; + + /* Pinned counter task profiling */ + if (tsk) { + if (cpu >= 0) { + toggle_bp_task_slot(tsk, cpu, enable); + return; + } + + for_each_online_cpu(cpu) + toggle_bp_task_slot(tsk, cpu, enable); + return; + } + + /* Pinned counter cpu profiling */ + if (enable) + per_cpu(nr_cpu_bp_pinned, bp->cpu)++; + else + per_cpu(nr_cpu_bp_pinned, bp->cpu)--; +} + +/* + * Contraints to check before allowing this new breakpoint counter: + * + * == Non-pinned counter == (Considered as pinned for now) + * + * - If attached to a single cpu, check: + * + * (per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu) + * + max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM + * + * -> If there are already non-pinned counters in this cpu, it means + * there is already a free slot for them. + * Otherwise, we check that the maximum number of per task + * breakpoints (for this cpu) plus the number of per cpu breakpoint + * (for this cpu) doesn't cover every registers. + * + * - If attached to every cpus, check: + * + * (per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *)) + * + max(per_cpu(task_bp_pinned, *)))) < HBP_NUM + * + * -> This is roughly the same, except we check the number of per cpu + * bp for every cpu and we keep the max one. Same for the per tasks + * breakpoints. + * + * + * == Pinned counter == + * + * - If attached to a single cpu, check: + * + * ((per_cpu(nr_bp_flexible, cpu) > 1) + per_cpu(nr_cpu_bp_pinned, cpu) + * + max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM + * + * -> Same checks as before. But now the nr_bp_flexible, if any, must keep + * one register at least (or they will never be fed). + * + * - If attached to every cpus, check: + * + * ((per_cpu(nr_bp_flexible, *) > 1) + max(per_cpu(nr_cpu_bp_pinned, *)) + * + max(per_cpu(task_bp_pinned, *))) < HBP_NUM + */ +int reserve_bp_slot(struct perf_event *bp) +{ + struct bp_busy_slots slots = {0}; + int ret = 0; + + mutex_lock(&nr_bp_mutex); + + fetch_bp_busy_slots(&slots, bp->cpu); + + /* Flexible counters need to keep at least one slot */ + if (slots.pinned + (!!slots.flexible) == HBP_NUM) { + ret = -ENOSPC; + goto end; + } + + toggle_bp_slot(bp, true); + +end: + mutex_unlock(&nr_bp_mutex); + + return ret; +} + +void release_bp_slot(struct perf_event *bp) +{ + mutex_lock(&nr_bp_mutex); + + toggle_bp_slot(bp, false); + + mutex_unlock(&nr_bp_mutex); +} + + +int __register_perf_hw_breakpoint(struct perf_event *bp) +{ + int ret; + + ret = reserve_bp_slot(bp); + if (ret) + return ret; + + /* + * Ptrace breakpoints can be temporary perf events only + * meant to reserve a slot. In this case, it is created disabled and + * we don't want to check the params right now (as we put a null addr) + * But perf tools create events as disabled and we want to check + * the params for them. + * This is a quick hack that will be removed soon, once we remove + * the tmp breakpoints from ptrace + */ + if (!bp->attr.disabled || bp->callback == perf_bp_event) + ret = arch_validate_hwbkpt_settings(bp, bp->ctx->task); + + return ret; +} + +int register_perf_hw_breakpoint(struct perf_event *bp) +{ + bp->callback = perf_bp_event; + + return __register_perf_hw_breakpoint(bp); +} + +/** + * register_user_hw_breakpoint - register a hardware breakpoint for user space + * @attr: breakpoint attributes + * @triggered: callback to trigger when we hit the breakpoint + * @tsk: pointer to 'task_struct' of the process to which the address belongs + */ +struct perf_event * +register_user_hw_breakpoint(struct perf_event_attr *attr, + perf_callback_t triggered, + struct task_struct *tsk) +{ + return perf_event_create_kernel_counter(attr, -1, tsk->pid, triggered); +} +EXPORT_SYMBOL_GPL(register_user_hw_breakpoint); + +/** + * modify_user_hw_breakpoint - modify a user-space hardware breakpoint + * @bp: the breakpoint structure to modify + * @attr: new breakpoint attributes + * @triggered: callback to trigger when we hit the breakpoint + * @tsk: pointer to 'task_struct' of the process to which the address belongs + */ +struct perf_event * +modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr, + perf_callback_t triggered, + struct task_struct *tsk) +{ + /* + * FIXME: do it without unregistering + * - We don't want to lose our slot + * - If the new bp is incorrect, don't lose the older one + */ + unregister_hw_breakpoint(bp); + + return perf_event_create_kernel_counter(attr, -1, tsk->pid, triggered); +} +EXPORT_SYMBOL_GPL(modify_user_hw_breakpoint); + +/** + * unregister_hw_breakpoint - unregister a user-space hardware breakpoint + * @bp: the breakpoint structure to unregister + */ +void unregister_hw_breakpoint(struct perf_event *bp) +{ + if (!bp) + return; + perf_event_release_kernel(bp); +} +EXPORT_SYMBOL_GPL(unregister_hw_breakpoint); + +/** + * register_wide_hw_breakpoint - register a wide breakpoint in the kernel + * @attr: breakpoint attributes + * @triggered: callback to trigger when we hit the breakpoint + * + * @return a set of per_cpu pointers to perf events + */ +struct perf_event ** +register_wide_hw_breakpoint(struct perf_event_attr *attr, + perf_callback_t triggered) +{ + struct perf_event **cpu_events, **pevent, *bp; + long err; + int cpu; + + cpu_events = alloc_percpu(typeof(*cpu_events)); + if (!cpu_events) + return ERR_PTR(-ENOMEM); + + for_each_possible_cpu(cpu) { + pevent = per_cpu_ptr(cpu_events, cpu); + bp = perf_event_create_kernel_counter(attr, cpu, -1, triggered); + + *pevent = bp; + + if (IS_ERR(bp)) { + err = PTR_ERR(bp); + goto fail; + } + } + + return cpu_events; + +fail: + for_each_possible_cpu(cpu) { + pevent = per_cpu_ptr(cpu_events, cpu); + if (IS_ERR(*pevent)) + break; + unregister_hw_breakpoint(*pevent); + } + free_percpu(cpu_events); + /* return the error if any */ + return ERR_PTR(err); +} +EXPORT_SYMBOL_GPL(register_wide_hw_breakpoint); + +/** + * unregister_wide_hw_breakpoint - unregister a wide breakpoint in the kernel + * @cpu_events: the per cpu set of events to unregister + */ +void unregister_wide_hw_breakpoint(struct perf_event **cpu_events) +{ + int cpu; + struct perf_event **pevent; + + for_each_possible_cpu(cpu) { + pevent = per_cpu_ptr(cpu_events, cpu); + unregister_hw_breakpoint(*pevent); + } + free_percpu(cpu_events); +} +EXPORT_SYMBOL_GPL(unregister_wide_hw_breakpoint); + +static struct notifier_block hw_breakpoint_exceptions_nb = { + .notifier_call = hw_breakpoint_exceptions_notify, + /* we need to be notified first */ + .priority = 0x7fffffff +}; + +static int __init init_hw_breakpoint(void) +{ + return register_die_notifier(&hw_breakpoint_exceptions_nb); +} +core_initcall(init_hw_breakpoint); + + +struct pmu perf_ops_bp = { + .enable = arch_install_hw_breakpoint, + .disable = arch_uninstall_hw_breakpoint, + .read = hw_breakpoint_pmu_read, + .unthrottle = hw_breakpoint_pmu_unthrottle +}; diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index c1660194d115..ba566c261adc 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -166,11 +166,11 @@ int set_irq_data(unsigned int irq, void *data) EXPORT_SYMBOL(set_irq_data); /** - * set_irq_data - set irq type data for an irq + * set_irq_msi - set MSI descriptor data for an irq * @irq: Interrupt number * @entry: Pointer to MSI descriptor data * - * Set the hardware irq controller data for an irq + * Set the MSI descriptor entry for an irq */ int set_irq_msi(unsigned int irq, struct msi_desc *entry) { @@ -590,7 +590,7 @@ out_unlock: } /** - * handle_percpu_IRQ - Per CPU local irq handler + * handle_percpu_irq - Per CPU local irq handler * @irq: the interrupt number * @desc: the interrupt description structure for this irq * diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index 692363dd591f..0832145fea97 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -136,7 +136,7 @@ out: static int default_affinity_open(struct inode *inode, struct file *file) { - return single_open(file, default_affinity_show, NULL); + return single_open(file, default_affinity_show, PDE(inode)->data); } static const struct file_operations default_affinity_proc_fops = { @@ -148,18 +148,28 @@ static const struct file_operations default_affinity_proc_fops = { }; #endif -static int irq_spurious_read(char *page, char **start, off_t off, - int count, int *eof, void *data) +static int irq_spurious_proc_show(struct seq_file *m, void *v) { - struct irq_desc *desc = irq_to_desc((long) data); - return sprintf(page, "count %u\n" - "unhandled %u\n" - "last_unhandled %u ms\n", - desc->irq_count, - desc->irqs_unhandled, - jiffies_to_msecs(desc->last_unhandled)); + struct irq_desc *desc = irq_to_desc((long) m->private); + + seq_printf(m, "count %u\n" "unhandled %u\n" "last_unhandled %u ms\n", + desc->irq_count, desc->irqs_unhandled, + jiffies_to_msecs(desc->last_unhandled)); + return 0; +} + +static int irq_spurious_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, irq_spurious_proc_show, NULL); } +static const struct file_operations irq_spurious_proc_fops = { + .open = irq_spurious_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + #define MAX_NAMELEN 128 static int name_unique(unsigned int irq, struct irqaction *new_action) @@ -204,7 +214,6 @@ void register_handler_proc(unsigned int irq, struct irqaction *action) void register_irq_proc(unsigned int irq, struct irq_desc *desc) { char name [MAX_NAMELEN]; - struct proc_dir_entry *entry; if (!root_irq_dir || (desc->chip == &no_irq_chip) || desc->dir) return; @@ -214,6 +223,8 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc) /* create /proc/irq/1234 */ desc->dir = proc_mkdir(name, root_irq_dir); + if (!desc->dir) + return; #ifdef CONFIG_SMP /* create /proc/irq/<irq>/smp_affinity */ @@ -221,11 +232,8 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc) &irq_affinity_proc_fops, (void *)(long)irq); #endif - entry = create_proc_entry("spurious", 0444, desc->dir); - if (entry) { - entry->data = (void *)(long)irq; - entry->read_proc = irq_spurious_read; - } + proc_create_data("spurious", 0444, desc->dir, + &irq_spurious_proc_fops, (void *)(long)irq); } #undef MAX_NAMELEN diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c index bd7273e6282e..22b0a6eedf24 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -104,7 +104,7 @@ static int misrouted_irq(int irq) return ok; } -static void poll_all_shared_irqs(void) +static void poll_spurious_irqs(unsigned long dummy) { struct irq_desc *desc; int i; @@ -125,23 +125,11 @@ static void poll_all_shared_irqs(void) try_one_irq(i, desc); local_irq_enable(); } -} - -static void poll_spurious_irqs(unsigned long dummy) -{ - poll_all_shared_irqs(); mod_timer(&poll_spurious_irq_timer, jiffies + POLL_SPURIOUS_IRQ_INTERVAL); } -#ifdef CONFIG_DEBUG_SHIRQ -void debug_poll_all_shared_irqs(void) -{ - poll_all_shared_irqs(); -} -#endif - /* * If 99,900 of the previous 100,000 interrupts have not been handled * then assume that the IRQ is stuck in some manner. Drop a diagnostic diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 8b6b8b697c68..8e5288a8a355 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -181,6 +181,7 @@ unsigned long kallsyms_lookup_name(const char *name) } return module_kallsyms_lookup_name(name); } +EXPORT_SYMBOL_GPL(kallsyms_lookup_name); int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, unsigned long), diff --git a/kernel/kgdb.c b/kernel/kgdb.c index 9147a3190c9d..7d7014634022 100644 --- a/kernel/kgdb.c +++ b/kernel/kgdb.c @@ -870,7 +870,7 @@ static void gdb_cmd_getregs(struct kgdb_state *ks) /* * All threads that don't have debuggerinfo should be - * in __schedule() sleeping, since all other CPUs + * in schedule() sleeping, since all other CPUs * are in kgdb_wait, and thus have debuggerinfo. */ if (local_debuggerinfo) { diff --git a/kernel/kmod.c b/kernel/kmod.c index 9fcb53a11f87..25b103190364 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -80,16 +80,16 @@ int __request_module(bool wait, const char *fmt, ...) #define MAX_KMOD_CONCURRENT 50 /* Completely arbitrary value - KAO */ static int kmod_loop_msg; - ret = security_kernel_module_request(); - if (ret) - return ret; - va_start(args, fmt); ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args); va_end(args); if (ret >= MODULE_NAME_LEN) return -ENAMETOOLONG; + ret = security_kernel_module_request(module_name); + if (ret) + return ret; + /* If modprobe needs a service that is in a module, we get a recursive * loop. Limit the number of running kmod threads to max_threads/2 or * MAX_KMOD_CONCURRENT, whichever is the smaller. A cleaner method diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 5240d75f4c60..e5342a344c43 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -90,6 +90,9 @@ static spinlock_t *kretprobe_table_lock_ptr(unsigned long hash) */ static struct kprobe_blackpoint kprobe_blacklist[] = { {"preempt_schedule",}, + {"native_get_debugreg",}, + {"irq_entries_start",}, + {"common_interrupt",}, {NULL} /* Terminator */ }; @@ -673,6 +676,40 @@ static kprobe_opcode_t __kprobes *kprobe_addr(struct kprobe *p) return (kprobe_opcode_t *)(((char *)addr) + p->offset); } +/* Check passed kprobe is valid and return kprobe in kprobe_table. */ +static struct kprobe * __kprobes __get_valid_kprobe(struct kprobe *p) +{ + struct kprobe *old_p, *list_p; + + old_p = get_kprobe(p->addr); + if (unlikely(!old_p)) + return NULL; + + if (p != old_p) { + list_for_each_entry_rcu(list_p, &old_p->list, list) + if (list_p == p) + /* kprobe p is a valid probe */ + goto valid; + return NULL; + } +valid: + return old_p; +} + +/* Return error if the kprobe is being re-registered */ +static inline int check_kprobe_rereg(struct kprobe *p) +{ + int ret = 0; + struct kprobe *old_p; + + mutex_lock(&kprobe_mutex); + old_p = __get_valid_kprobe(p); + if (old_p) + ret = -EINVAL; + mutex_unlock(&kprobe_mutex); + return ret; +} + int __kprobes register_kprobe(struct kprobe *p) { int ret = 0; @@ -685,6 +722,10 @@ int __kprobes register_kprobe(struct kprobe *p) return -EINVAL; p->addr = addr; + ret = check_kprobe_rereg(p); + if (ret) + return ret; + preempt_disable(); if (!kernel_text_address((unsigned long) p->addr) || in_kprobes_functions((unsigned long) p->addr)) { @@ -754,26 +795,6 @@ out: } EXPORT_SYMBOL_GPL(register_kprobe); -/* Check passed kprobe is valid and return kprobe in kprobe_table. */ -static struct kprobe * __kprobes __get_valid_kprobe(struct kprobe *p) -{ - struct kprobe *old_p, *list_p; - - old_p = get_kprobe(p->addr); - if (unlikely(!old_p)) - return NULL; - - if (p != old_p) { - list_for_each_entry_rcu(list_p, &old_p->list, list) - if (list_p == p) - /* kprobe p is a valid probe */ - goto valid; - return NULL; - } -valid: - return old_p; -} - /* * Unregister a kprobe without a scheduler synchronization. */ @@ -1014,9 +1035,9 @@ int __kprobes register_kretprobe(struct kretprobe *rp) /* Pre-allocate memory for max kretprobe instances */ if (rp->maxactive <= 0) { #ifdef CONFIG_PREEMPT - rp->maxactive = max(10, 2 * NR_CPUS); + rp->maxactive = max(10, 2 * num_possible_cpus()); #else - rp->maxactive = NR_CPUS; + rp->maxactive = num_possible_cpus(); #endif } spin_lock_init(&rp->lock); @@ -1141,6 +1162,13 @@ static void __kprobes kill_kprobe(struct kprobe *p) arch_remove_kprobe(p); } +void __kprobes dump_kprobe(struct kprobe *kp) +{ + printk(KERN_WARNING "Dumping kprobe:\n"); + printk(KERN_WARNING "Name: %s\nAddress: %p\nOffset: %x\n", + kp->symbol_name, kp->addr, kp->offset); +} + /* Module notifier call back, checking kprobes on the module */ static int __kprobes kprobes_module_callback(struct notifier_block *nb, unsigned long val, void *data) diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 9af56723c096..f5dcd36d3151 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -49,7 +49,7 @@ #include "lockdep_internals.h" #define CREATE_TRACE_POINTS -#include <trace/events/lockdep.h> +#include <trace/events/lock.h> #ifdef CONFIG_PROVE_LOCKING int prove_locking = 1; diff --git a/kernel/module.c b/kernel/module.c index 8b7d8805819d..5842a71cf052 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1187,7 +1187,8 @@ static void add_sect_attrs(struct module *mod, unsigned int nsect, /* Count loaded sections and allocate structures */ for (i = 0; i < nsect; i++) - if (sechdrs[i].sh_flags & SHF_ALLOC) + if (sechdrs[i].sh_flags & SHF_ALLOC + && sechdrs[i].sh_size) nloaded++; size[0] = ALIGN(sizeof(*sect_attrs) + nloaded * sizeof(sect_attrs->attrs[0]), @@ -1207,6 +1208,8 @@ static void add_sect_attrs(struct module *mod, unsigned int nsect, for (i = 0; i < nsect; i++) { if (! (sechdrs[i].sh_flags & SHF_ALLOC)) continue; + if (!sechdrs[i].sh_size) + continue; sattr->address = sechdrs[i].sh_addr; sattr->name = kstrdup(secstrings + sechdrs[i].sh_name, GFP_KERNEL); diff --git a/kernel/mutex.c b/kernel/mutex.c index 947b3ad551f8..632f04c57d82 100644 --- a/kernel/mutex.c +++ b/kernel/mutex.c @@ -148,8 +148,8 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, preempt_disable(); mutex_acquire(&lock->dep_map, subclass, 0, ip); -#if defined(CONFIG_SMP) && !defined(CONFIG_DEBUG_MUTEXES) && \ - !defined(CONFIG_HAVE_DEFAULT_NO_SPIN_MUTEXES) + +#ifdef CONFIG_MUTEX_SPIN_ON_OWNER /* * Optimistic spinning. * diff --git a/kernel/notifier.c b/kernel/notifier.c index 61d5aa5eced3..acd24e7643eb 100644 --- a/kernel/notifier.c +++ b/kernel/notifier.c @@ -558,7 +558,7 @@ EXPORT_SYMBOL(unregister_reboot_notifier); static ATOMIC_NOTIFIER_HEAD(die_chain); -int notrace notify_die(enum die_val val, const char *str, +int notrace __kprobes notify_die(enum die_val val, const char *str, struct pt_regs *regs, long err, int trap, int sig) { struct die_args args = { diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 7f29643c8985..6b7ddba1dd64 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -28,6 +28,8 @@ #include <linux/anon_inodes.h> #include <linux/kernel_stat.h> #include <linux/perf_event.h> +#include <linux/ftrace_event.h> +#include <linux/hw_breakpoint.h> #include <asm/irq_regs.h> @@ -244,6 +246,49 @@ static void perf_unpin_context(struct perf_event_context *ctx) put_ctx(ctx); } +static inline u64 perf_clock(void) +{ + return cpu_clock(smp_processor_id()); +} + +/* + * Update the record of the current time in a context. + */ +static void update_context_time(struct perf_event_context *ctx) +{ + u64 now = perf_clock(); + + ctx->time += now - ctx->timestamp; + ctx->timestamp = now; +} + +/* + * Update the total_time_enabled and total_time_running fields for a event. + */ +static void update_event_times(struct perf_event *event) +{ + struct perf_event_context *ctx = event->ctx; + u64 run_end; + + if (event->state < PERF_EVENT_STATE_INACTIVE || + event->group_leader->state < PERF_EVENT_STATE_INACTIVE) + return; + + if (ctx->is_active) + run_end = ctx->time; + else + run_end = event->tstamp_stopped; + + event->total_time_enabled = run_end - event->tstamp_enabled; + + if (event->state == PERF_EVENT_STATE_INACTIVE) + run_end = event->tstamp_stopped; + else + run_end = ctx->time; + + event->total_time_running = run_end - event->tstamp_running; +} + /* * Add a event from the lists for its context. * Must be called with ctx->mutex and ctx->lock held. @@ -292,6 +337,18 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx) if (event->group_leader != event) event->group_leader->nr_siblings--; + update_event_times(event); + + /* + * If event was in error state, then keep it + * that way, otherwise bogus counts will be + * returned on read(). The only way to get out + * of error state is by explicit re-enabling + * of the event + */ + if (event->state > PERF_EVENT_STATE_OFF) + event->state = PERF_EVENT_STATE_OFF; + /* * If this was a group event with sibling events then * upgrade the siblings to singleton events by adding them @@ -445,50 +502,11 @@ retry: * can remove the event safely, if the call above did not * succeed. */ - if (!list_empty(&event->group_entry)) { + if (!list_empty(&event->group_entry)) list_del_event(event, ctx); - } spin_unlock_irq(&ctx->lock); } -static inline u64 perf_clock(void) -{ - return cpu_clock(smp_processor_id()); -} - -/* - * Update the record of the current time in a context. - */ -static void update_context_time(struct perf_event_context *ctx) -{ - u64 now = perf_clock(); - - ctx->time += now - ctx->timestamp; - ctx->timestamp = now; -} - -/* - * Update the total_time_enabled and total_time_running fields for a event. - */ -static void update_event_times(struct perf_event *event) -{ - struct perf_event_context *ctx = event->ctx; - u64 run_end; - - if (event->state < PERF_EVENT_STATE_INACTIVE || - event->group_leader->state < PERF_EVENT_STATE_INACTIVE) - return; - - event->total_time_enabled = ctx->time - event->tstamp_enabled; - - if (event->state == PERF_EVENT_STATE_INACTIVE) - run_end = event->tstamp_stopped; - else - run_end = ctx->time; - - event->total_time_running = run_end - event->tstamp_running; -} - /* * Update total_time_enabled and total_time_running for all events in a group. */ @@ -1031,10 +1049,10 @@ void __perf_event_sched_out(struct perf_event_context *ctx, update_context_time(ctx); perf_disable(); - if (ctx->nr_active) + if (ctx->nr_active) { list_for_each_entry(event, &ctx->group_list, group_entry) group_sched_out(event, cpuctx, ctx); - + } perf_enable(); out: spin_unlock(&ctx->lock); @@ -1059,8 +1077,6 @@ static int context_equiv(struct perf_event_context *ctx1, && !ctx1->pin_count && !ctx2->pin_count; } -static void __perf_event_read(void *event); - static void __perf_event_sync_stat(struct perf_event *event, struct perf_event *next_event) { @@ -1078,8 +1094,8 @@ static void __perf_event_sync_stat(struct perf_event *event, */ switch (event->state) { case PERF_EVENT_STATE_ACTIVE: - __perf_event_read(event); - break; + event->pmu->read(event); + /* fall-through */ case PERF_EVENT_STATE_INACTIVE: update_event_times(event); @@ -1118,6 +1134,8 @@ static void perf_event_sync_stat(struct perf_event_context *ctx, if (!ctx->nr_stat) return; + update_context_time(ctx); + event = list_first_entry(&ctx->event_list, struct perf_event, event_entry); @@ -1161,8 +1179,6 @@ void perf_event_task_sched_out(struct task_struct *task, if (likely(!ctx || !cpuctx->task_ctx)) return; - update_context_time(ctx); - rcu_read_lock(); parent = rcu_dereference(ctx->parent_ctx); next_ctx = next->perf_event_ctxp; @@ -1515,7 +1531,6 @@ static void __perf_event_read(void *info) struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context); struct perf_event *event = info; struct perf_event_context *ctx = event->ctx; - unsigned long flags; /* * If this is a task context, we need to check whether it is @@ -1527,12 +1542,12 @@ static void __perf_event_read(void *info) if (ctx->task && cpuctx->task_ctx != ctx) return; - local_irq_save(flags); - if (ctx->is_active) - update_context_time(ctx); - event->pmu->read(event); + spin_lock(&ctx->lock); + update_context_time(ctx); update_event_times(event); - local_irq_restore(flags); + spin_unlock(&ctx->lock); + + event->pmu->read(event); } static u64 perf_event_read(struct perf_event *event) @@ -1545,7 +1560,13 @@ static u64 perf_event_read(struct perf_event *event) smp_call_function_single(event->oncpu, __perf_event_read, event, 1); } else if (event->state == PERF_EVENT_STATE_INACTIVE) { + struct perf_event_context *ctx = event->ctx; + unsigned long flags; + + spin_lock_irqsave(&ctx->lock, flags); + update_context_time(ctx); update_event_times(event); + spin_unlock_irqrestore(&ctx->lock, flags); } return atomic64_read(&event->count); @@ -1658,6 +1679,8 @@ static struct perf_event_context *find_get_context(pid_t pid, int cpu) return ERR_PTR(err); } +static void perf_event_free_filter(struct perf_event *event); + static void free_event_rcu(struct rcu_head *head) { struct perf_event *event; @@ -1665,6 +1688,7 @@ static void free_event_rcu(struct rcu_head *head) event = container_of(head, struct perf_event, rcu_head); if (event->ns) put_pid_ns(event->ns); + perf_event_free_filter(event); kfree(event); } @@ -1696,16 +1720,10 @@ static void free_event(struct perf_event *event) call_rcu(&event->rcu_head, free_event_rcu); } -/* - * Called when the last reference to the file is gone. - */ -static int perf_release(struct inode *inode, struct file *file) +int perf_event_release_kernel(struct perf_event *event) { - struct perf_event *event = file->private_data; struct perf_event_context *ctx = event->ctx; - file->private_data = NULL; - WARN_ON_ONCE(ctx->parent_ctx); mutex_lock(&ctx->mutex); perf_event_remove_from_context(event); @@ -1720,6 +1738,19 @@ static int perf_release(struct inode *inode, struct file *file) return 0; } +EXPORT_SYMBOL_GPL(perf_event_release_kernel); + +/* + * Called when the last reference to the file is gone. + */ +static int perf_release(struct inode *inode, struct file *file) +{ + struct perf_event *event = file->private_data; + + file->private_data = NULL; + + return perf_event_release_kernel(event); +} static int perf_event_read_size(struct perf_event *event) { @@ -1746,91 +1777,94 @@ static int perf_event_read_size(struct perf_event *event) return size; } -static u64 perf_event_read_value(struct perf_event *event) +u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running) { struct perf_event *child; u64 total = 0; + *enabled = 0; + *running = 0; + + mutex_lock(&event->child_mutex); total += perf_event_read(event); - list_for_each_entry(child, &event->child_list, child_list) + *enabled += event->total_time_enabled + + atomic64_read(&event->child_total_time_enabled); + *running += event->total_time_running + + atomic64_read(&event->child_total_time_running); + + list_for_each_entry(child, &event->child_list, child_list) { total += perf_event_read(child); + *enabled += child->total_time_enabled; + *running += child->total_time_running; + } + mutex_unlock(&event->child_mutex); return total; } - -static int perf_event_read_entry(struct perf_event *event, - u64 read_format, char __user *buf) -{ - int n = 0, count = 0; - u64 values[2]; - - values[n++] = perf_event_read_value(event); - if (read_format & PERF_FORMAT_ID) - values[n++] = primary_event_id(event); - - count = n * sizeof(u64); - - if (copy_to_user(buf, values, count)) - return -EFAULT; - - return count; -} +EXPORT_SYMBOL_GPL(perf_event_read_value); static int perf_event_read_group(struct perf_event *event, u64 read_format, char __user *buf) { struct perf_event *leader = event->group_leader, *sub; - int n = 0, size = 0, err = -EFAULT; - u64 values[3]; + int n = 0, size = 0, ret = -EFAULT; + struct perf_event_context *ctx = leader->ctx; + u64 values[5]; + u64 count, enabled, running; + + mutex_lock(&ctx->mutex); + count = perf_event_read_value(leader, &enabled, &running); values[n++] = 1 + leader->nr_siblings; - if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) { - values[n++] = leader->total_time_enabled + - atomic64_read(&leader->child_total_time_enabled); - } - if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) { - values[n++] = leader->total_time_running + - atomic64_read(&leader->child_total_time_running); - } + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + values[n++] = enabled; + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + values[n++] = running; + values[n++] = count; + if (read_format & PERF_FORMAT_ID) + values[n++] = primary_event_id(leader); size = n * sizeof(u64); if (copy_to_user(buf, values, size)) - return -EFAULT; - - err = perf_event_read_entry(leader, read_format, buf + size); - if (err < 0) - return err; + goto unlock; - size += err; + ret = size; list_for_each_entry(sub, &leader->sibling_list, group_entry) { - err = perf_event_read_entry(sub, read_format, - buf + size); - if (err < 0) - return err; + n = 0; + + values[n++] = perf_event_read_value(sub, &enabled, &running); + if (read_format & PERF_FORMAT_ID) + values[n++] = primary_event_id(sub); + + size = n * sizeof(u64); - size += err; + if (copy_to_user(buf + ret, values, size)) { + ret = -EFAULT; + goto unlock; + } + + ret += size; } +unlock: + mutex_unlock(&ctx->mutex); - return size; + return ret; } static int perf_event_read_one(struct perf_event *event, u64 read_format, char __user *buf) { + u64 enabled, running; u64 values[4]; int n = 0; - values[n++] = perf_event_read_value(event); - if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) { - values[n++] = event->total_time_enabled + - atomic64_read(&event->child_total_time_enabled); - } - if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) { - values[n++] = event->total_time_running + - atomic64_read(&event->child_total_time_running); - } + values[n++] = perf_event_read_value(event, &enabled, &running); + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + values[n++] = enabled; + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + values[n++] = running; if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(event); @@ -1861,12 +1895,10 @@ perf_read_hw(struct perf_event *event, char __user *buf, size_t count) return -ENOSPC; WARN_ON_ONCE(event->ctx->parent_ctx); - mutex_lock(&event->child_mutex); if (read_format & PERF_FORMAT_GROUP) ret = perf_event_read_group(event, read_format, buf); else ret = perf_event_read_one(event, read_format, buf); - mutex_unlock(&event->child_mutex); return ret; } @@ -1974,7 +2006,8 @@ unlock: return ret; } -int perf_event_set_output(struct perf_event *event, int output_fd); +static int perf_event_set_output(struct perf_event *event, int output_fd); +static int perf_event_set_filter(struct perf_event *event, void __user *arg); static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -2002,6 +2035,9 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case PERF_EVENT_IOC_SET_OUTPUT: return perf_event_set_output(event, arg); + case PERF_EVENT_IOC_SET_FILTER: + return perf_event_set_filter(event, (void __user *)arg); + default: return -ENOTTY; } @@ -2174,6 +2210,7 @@ static void perf_mmap_data_free(struct perf_mmap_data *data) perf_mmap_free_page((unsigned long)data->user_page); for (i = 0; i < data->nr_pages; i++) perf_mmap_free_page((unsigned long)data->data_pages[i]); + kfree(data); } #else @@ -2214,6 +2251,7 @@ static void perf_mmap_data_free_work(struct work_struct *work) perf_mmap_unmark_page(base + (i * PAGE_SIZE)); vfree(base); + kfree(data); } static void perf_mmap_data_free(struct perf_mmap_data *data) @@ -2307,7 +2345,7 @@ perf_mmap_data_init(struct perf_event *event, struct perf_mmap_data *data) } if (!data->watermark) - data->watermark = max_t(long, PAGE_SIZE, max_size / 2); + data->watermark = max_size / 2; rcu_assign_pointer(event->data, data); @@ -2319,7 +2357,6 @@ static void perf_mmap_data_free_rcu(struct rcu_head *rcu_head) data = container_of(rcu_head, struct perf_mmap_data, rcu_head); perf_mmap_data_free(data); - kfree(data); } static void perf_mmap_data_release(struct perf_event *event) @@ -2666,20 +2703,21 @@ static void perf_output_wakeup(struct perf_output_handle *handle) static void perf_output_lock(struct perf_output_handle *handle) { struct perf_mmap_data *data = handle->data; - int cpu; + int cur, cpu = get_cpu(); handle->locked = 0; - local_irq_save(handle->flags); - cpu = smp_processor_id(); - - if (in_nmi() && atomic_read(&data->lock) == cpu) - return; + for (;;) { + cur = atomic_cmpxchg(&data->lock, -1, cpu); + if (cur == -1) { + handle->locked = 1; + break; + } + if (cur == cpu) + break; - while (atomic_cmpxchg(&data->lock, -1, cpu) != -1) cpu_relax(); - - handle->locked = 1; + } } static void perf_output_unlock(struct perf_output_handle *handle) @@ -2725,7 +2763,7 @@ again: if (atomic_xchg(&data->wakeup, 0)) perf_output_wakeup(handle); out: - local_irq_restore(handle->flags); + put_cpu(); } void perf_output_copy(struct perf_output_handle *handle, @@ -3236,15 +3274,10 @@ static void perf_event_task_ctx(struct perf_event_context *ctx, { struct perf_event *event; - if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list)) - return; - - rcu_read_lock(); list_for_each_entry_rcu(event, &ctx->event_list, event_entry) { if (perf_event_task_match(event)) perf_event_task_output(event, task_event); } - rcu_read_unlock(); } static void perf_event_task_event(struct perf_task_event *task_event) @@ -3252,11 +3285,11 @@ static void perf_event_task_event(struct perf_task_event *task_event) struct perf_cpu_context *cpuctx; struct perf_event_context *ctx = task_event->task_ctx; + rcu_read_lock(); cpuctx = &get_cpu_var(perf_cpu_context); perf_event_task_ctx(&cpuctx->ctx, task_event); put_cpu_var(perf_cpu_context); - rcu_read_lock(); if (!ctx) ctx = rcu_dereference(task_event->task->perf_event_ctxp); if (ctx) @@ -3348,15 +3381,10 @@ static void perf_event_comm_ctx(struct perf_event_context *ctx, { struct perf_event *event; - if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list)) - return; - - rcu_read_lock(); list_for_each_entry_rcu(event, &ctx->event_list, event_entry) { if (perf_event_comm_match(event)) perf_event_comm_output(event, comm_event); } - rcu_read_unlock(); } static void perf_event_comm_event(struct perf_comm_event *comm_event) @@ -3367,7 +3395,7 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event) char comm[TASK_COMM_LEN]; memset(comm, 0, sizeof(comm)); - strncpy(comm, comm_event->task->comm, sizeof(comm)); + strlcpy(comm, comm_event->task->comm, sizeof(comm)); size = ALIGN(strlen(comm)+1, sizeof(u64)); comm_event->comm = comm; @@ -3375,11 +3403,11 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event) comm_event->event_id.header.size = sizeof(comm_event->event_id) + size; + rcu_read_lock(); cpuctx = &get_cpu_var(perf_cpu_context); perf_event_comm_ctx(&cpuctx->ctx, comm_event); put_cpu_var(perf_cpu_context); - rcu_read_lock(); /* * doesn't really matter which of the child contexts the * events ends up in. @@ -3472,15 +3500,10 @@ static void perf_event_mmap_ctx(struct perf_event_context *ctx, { struct perf_event *event; - if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list)) - return; - - rcu_read_lock(); list_for_each_entry_rcu(event, &ctx->event_list, event_entry) { if (perf_event_mmap_match(event, mmap_event)) perf_event_mmap_output(event, mmap_event); } - rcu_read_unlock(); } static void perf_event_mmap_event(struct perf_mmap_event *mmap_event) @@ -3536,11 +3559,11 @@ got_name: mmap_event->event_id.header.size = sizeof(mmap_event->event_id) + size; + rcu_read_lock(); cpuctx = &get_cpu_var(perf_cpu_context); perf_event_mmap_ctx(&cpuctx->ctx, mmap_event); put_cpu_var(perf_cpu_context); - rcu_read_lock(); /* * doesn't really matter which of the child contexts the * events ends up in. @@ -3679,7 +3702,11 @@ static int __perf_event_overflow(struct perf_event *event, int nmi, perf_event_disable(event); } - perf_event_output(event, nmi, data, regs); + if (event->overflow_handler) + event->overflow_handler(event, nmi, data, regs); + else + perf_event_output(event, nmi, data, regs); + return ret; } @@ -3724,16 +3751,16 @@ again: return nr; } -static void perf_swevent_overflow(struct perf_event *event, +static void perf_swevent_overflow(struct perf_event *event, u64 overflow, int nmi, struct perf_sample_data *data, struct pt_regs *regs) { struct hw_perf_event *hwc = &event->hw; int throttle = 0; - u64 overflow; data->period = event->hw.last_period; - overflow = perf_swevent_set_period(event); + if (!overflow) + overflow = perf_swevent_set_period(event); if (hwc->interrupts == MAX_INTERRUPTS) return; @@ -3766,14 +3793,19 @@ static void perf_swevent_add(struct perf_event *event, u64 nr, atomic64_add(nr, &event->count); + if (!regs) + return; + if (!hwc->sample_period) return; - if (!regs) + if (nr == 1 && hwc->sample_period == 1 && !event->attr.freq) + return perf_swevent_overflow(event, 1, nmi, data, regs); + + if (atomic64_add_negative(nr, &hwc->period_left)) return; - if (!atomic64_add_negative(nr, &hwc->period_left)) - perf_swevent_overflow(event, nmi, data, regs); + perf_swevent_overflow(event, 0, nmi, data, regs); } static int perf_swevent_is_counting(struct perf_event *event) @@ -3806,25 +3838,44 @@ static int perf_swevent_is_counting(struct perf_event *event) return 1; } +static int perf_tp_event_match(struct perf_event *event, + struct perf_sample_data *data); + +static int perf_exclude_event(struct perf_event *event, + struct pt_regs *regs) +{ + if (regs) { + if (event->attr.exclude_user && user_mode(regs)) + return 1; + + if (event->attr.exclude_kernel && !user_mode(regs)) + return 1; + } + + return 0; +} + static int perf_swevent_match(struct perf_event *event, enum perf_type_id type, - u32 event_id, struct pt_regs *regs) + u32 event_id, + struct perf_sample_data *data, + struct pt_regs *regs) { if (!perf_swevent_is_counting(event)) return 0; if (event->attr.type != type) return 0; + if (event->attr.config != event_id) return 0; - if (regs) { - if (event->attr.exclude_user && user_mode(regs)) - return 0; + if (perf_exclude_event(event, regs)) + return 0; - if (event->attr.exclude_kernel && !user_mode(regs)) - return 0; - } + if (event->attr.type == PERF_TYPE_TRACEPOINT && + !perf_tp_event_match(event, data)) + return 0; return 1; } @@ -3837,49 +3888,59 @@ static void perf_swevent_ctx_event(struct perf_event_context *ctx, { struct perf_event *event; - if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list)) - return; - - rcu_read_lock(); list_for_each_entry_rcu(event, &ctx->event_list, event_entry) { - if (perf_swevent_match(event, type, event_id, regs)) + if (perf_swevent_match(event, type, event_id, data, regs)) perf_swevent_add(event, nr, nmi, data, regs); } - rcu_read_unlock(); } -static int *perf_swevent_recursion_context(struct perf_cpu_context *cpuctx) +int perf_swevent_get_recursion_context(void) { + struct perf_cpu_context *cpuctx = &get_cpu_var(perf_cpu_context); + int rctx; + if (in_nmi()) - return &cpuctx->recursion[3]; + rctx = 3; + else if (in_irq()) + rctx = 2; + else if (in_softirq()) + rctx = 1; + else + rctx = 0; + + if (cpuctx->recursion[rctx]) { + put_cpu_var(perf_cpu_context); + return -1; + } - if (in_irq()) - return &cpuctx->recursion[2]; + cpuctx->recursion[rctx]++; + barrier(); - if (in_softirq()) - return &cpuctx->recursion[1]; + return rctx; +} +EXPORT_SYMBOL_GPL(perf_swevent_get_recursion_context); - return &cpuctx->recursion[0]; +void perf_swevent_put_recursion_context(int rctx) +{ + struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context); + barrier(); + cpuctx->recursion[rctx]--; + put_cpu_var(perf_cpu_context); } +EXPORT_SYMBOL_GPL(perf_swevent_put_recursion_context); static void do_perf_sw_event(enum perf_type_id type, u32 event_id, u64 nr, int nmi, struct perf_sample_data *data, struct pt_regs *regs) { - struct perf_cpu_context *cpuctx = &get_cpu_var(perf_cpu_context); - int *recursion = perf_swevent_recursion_context(cpuctx); + struct perf_cpu_context *cpuctx; struct perf_event_context *ctx; - if (*recursion) - goto out; - - (*recursion)++; - barrier(); - + cpuctx = &__get_cpu_var(perf_cpu_context); + rcu_read_lock(); perf_swevent_ctx_event(&cpuctx->ctx, type, event_id, nr, nmi, data, regs); - rcu_read_lock(); /* * doesn't really matter which of the child contexts the * events ends up in. @@ -3888,23 +3949,24 @@ static void do_perf_sw_event(enum perf_type_id type, u32 event_id, if (ctx) perf_swevent_ctx_event(ctx, type, event_id, nr, nmi, data, regs); rcu_read_unlock(); - - barrier(); - (*recursion)--; - -out: - put_cpu_var(perf_cpu_context); } void __perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr) { - struct perf_sample_data data = { - .addr = addr, - }; + struct perf_sample_data data; + int rctx; - do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, nmi, - &data, regs); + rctx = perf_swevent_get_recursion_context(); + if (rctx < 0) + return; + + data.addr = addr; + data.raw = NULL; + + do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, nmi, &data, regs); + + perf_swevent_put_recursion_context(rctx); } static void perf_swevent_read(struct perf_event *event) @@ -3949,6 +4011,7 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer) event->pmu->read(event); data.addr = 0; + data.period = event->hw.last_period; regs = get_irq_regs(); /* * In case we exclude kernel IPs or are somehow not in interrupt @@ -4108,6 +4171,7 @@ static const struct pmu perf_ops_task_clock = { }; #ifdef CONFIG_EVENT_PROFILE + void perf_tp_event(int event_id, u64 addr, u64 count, void *record, int entry_size) { @@ -4126,13 +4190,21 @@ void perf_tp_event(int event_id, u64 addr, u64 count, void *record, if (!regs) regs = task_pt_regs(current); + /* Trace events already protected against recursion */ do_perf_sw_event(PERF_TYPE_TRACEPOINT, event_id, count, 1, &data, regs); } EXPORT_SYMBOL_GPL(perf_tp_event); -extern int ftrace_profile_enable(int); -extern void ftrace_profile_disable(int); +static int perf_tp_event_match(struct perf_event *event, + struct perf_sample_data *data) +{ + void *record = data->raw->data; + + if (likely(!event->filter) || filter_match_preds(event->filter, record)) + return 1; + return 0; +} static void tp_perf_event_destroy(struct perf_event *event) { @@ -4157,11 +4229,99 @@ static const struct pmu *tp_perf_event_init(struct perf_event *event) return &perf_ops_generic; } + +static int perf_event_set_filter(struct perf_event *event, void __user *arg) +{ + char *filter_str; + int ret; + + if (event->attr.type != PERF_TYPE_TRACEPOINT) + return -EINVAL; + + filter_str = strndup_user(arg, PAGE_SIZE); + if (IS_ERR(filter_str)) + return PTR_ERR(filter_str); + + ret = ftrace_profile_set_filter(event, event->attr.config, filter_str); + + kfree(filter_str); + return ret; +} + +static void perf_event_free_filter(struct perf_event *event) +{ + ftrace_profile_free_filter(event); +} + #else + +static int perf_tp_event_match(struct perf_event *event, + struct perf_sample_data *data) +{ + return 1; +} + static const struct pmu *tp_perf_event_init(struct perf_event *event) { return NULL; } + +static int perf_event_set_filter(struct perf_event *event, void __user *arg) +{ + return -ENOENT; +} + +static void perf_event_free_filter(struct perf_event *event) +{ +} + +#endif /* CONFIG_EVENT_PROFILE */ + +#ifdef CONFIG_HAVE_HW_BREAKPOINT +static void bp_perf_event_destroy(struct perf_event *event) +{ + release_bp_slot(event); +} + +static const struct pmu *bp_perf_event_init(struct perf_event *bp) +{ + int err; + /* + * The breakpoint is already filled if we haven't created the counter + * through perf syscall + * FIXME: manage to get trigerred to NULL if it comes from syscalls + */ + if (!bp->callback) + err = register_perf_hw_breakpoint(bp); + else + err = __register_perf_hw_breakpoint(bp); + if (err) + return ERR_PTR(err); + + bp->destroy = bp_perf_event_destroy; + + return &perf_ops_bp; +} + +void perf_bp_event(struct perf_event *bp, void *data) +{ + struct perf_sample_data sample; + struct pt_regs *regs = data; + + sample.addr = bp->attr.bp_addr; + + if (!perf_exclude_event(bp, regs)) + perf_swevent_add(bp, 1, 1, &sample, regs); +} +#else +static const struct pmu *bp_perf_event_init(struct perf_event *bp) +{ + return NULL; +} + +void perf_bp_event(struct perf_event *bp, void *regs) +{ +} #endif atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX]; @@ -4208,6 +4368,8 @@ static const struct pmu *sw_perf_event_init(struct perf_event *event) case PERF_COUNT_SW_PAGE_FAULTS_MAJ: case PERF_COUNT_SW_CONTEXT_SWITCHES: case PERF_COUNT_SW_CPU_MIGRATIONS: + case PERF_COUNT_SW_ALIGNMENT_FAULTS: + case PERF_COUNT_SW_EMULATION_FAULTS: if (!event->parent) { atomic_inc(&perf_swevent_enabled[event_id]); event->destroy = sw_perf_event_destroy; @@ -4228,6 +4390,7 @@ perf_event_alloc(struct perf_event_attr *attr, struct perf_event_context *ctx, struct perf_event *group_leader, struct perf_event *parent_event, + perf_callback_t callback, gfp_t gfpflags) { const struct pmu *pmu; @@ -4270,6 +4433,11 @@ perf_event_alloc(struct perf_event_attr *attr, event->state = PERF_EVENT_STATE_INACTIVE; + if (!callback && parent_event) + callback = parent_event->callback; + + event->callback = callback; + if (attr->disabled) event->state = PERF_EVENT_STATE_OFF; @@ -4304,6 +4472,11 @@ perf_event_alloc(struct perf_event_attr *attr, pmu = tp_perf_event_init(event); break; + case PERF_TYPE_BREAKPOINT: + pmu = bp_perf_event_init(event); + break; + + default: break; } @@ -4416,7 +4589,7 @@ err_size: goto out; } -int perf_event_set_output(struct perf_event *event, int output_fd) +static int perf_event_set_output(struct perf_event *event, int output_fd) { struct perf_event *output_event = NULL; struct file *output_file = NULL; @@ -4546,7 +4719,7 @@ SYSCALL_DEFINE5(perf_event_open, } event = perf_event_alloc(&attr, cpu, ctx, group_leader, - NULL, GFP_KERNEL); + NULL, NULL, GFP_KERNEL); err = PTR_ERR(event); if (IS_ERR(event)) goto err_put_context; @@ -4594,6 +4767,60 @@ err_put_context: return err; } +/** + * perf_event_create_kernel_counter + * + * @attr: attributes of the counter to create + * @cpu: cpu in which the counter is bound + * @pid: task to profile + */ +struct perf_event * +perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, + pid_t pid, perf_callback_t callback) +{ + struct perf_event *event; + struct perf_event_context *ctx; + int err; + + /* + * Get the target context (task or percpu): + */ + + ctx = find_get_context(pid, cpu); + if (IS_ERR(ctx)) { + err = PTR_ERR(ctx); + goto err_exit; + } + + event = perf_event_alloc(attr, cpu, ctx, NULL, + NULL, callback, GFP_KERNEL); + if (IS_ERR(event)) { + err = PTR_ERR(event); + goto err_put_context; + } + + event->filp = NULL; + WARN_ON_ONCE(ctx->parent_ctx); + mutex_lock(&ctx->mutex); + perf_install_in_context(ctx, event, cpu); + ++ctx->generation; + mutex_unlock(&ctx->mutex); + + event->owner = current; + get_task_struct(current); + mutex_lock(¤t->perf_event_mutex); + list_add_tail(&event->owner_entry, ¤t->perf_event_list); + mutex_unlock(¤t->perf_event_mutex); + + return event; + + err_put_context: + put_ctx(ctx); + err_exit: + return ERR_PTR(err); +} +EXPORT_SYMBOL_GPL(perf_event_create_kernel_counter); + /* * inherit a event from parent task to child task: */ @@ -4619,7 +4846,7 @@ inherit_event(struct perf_event *parent_event, child_event = perf_event_alloc(&parent_event->attr, parent_event->cpu, child_ctx, group_leader, parent_event, - GFP_KERNEL); + NULL, GFP_KERNEL); if (IS_ERR(child_event)) return child_event; get_ctx(child_ctx); @@ -4637,6 +4864,8 @@ inherit_event(struct perf_event *parent_event, if (parent_event->attr.freq) child_event->hw.sample_period = parent_event->hw.sample_period; + child_event->overflow_handler = parent_event->overflow_handler; + /* * Link it up in the child's context: */ @@ -4726,7 +4955,6 @@ __perf_event_exit_task(struct perf_event *child_event, { struct perf_event *parent_event; - update_event_times(child_event); perf_event_remove_from_context(child_event); parent_event = child_event->parent; @@ -4778,6 +5006,7 @@ void perf_event_exit_task(struct task_struct *child) * the events from it. */ unclone_ctx(child_ctx); + update_context_time(child_ctx); spin_unlock_irqrestore(&child_ctx->lock, flags); /* diff --git a/kernel/printk.c b/kernel/printk.c index f38b07f78a4e..b5ac4d99c667 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -33,6 +33,7 @@ #include <linux/bootmem.h> #include <linux/syscalls.h> #include <linux/kexec.h> +#include <linux/ratelimit.h> #include <asm/uaccess.h> @@ -1376,11 +1377,11 @@ late_initcall(disable_boot_consoles); */ DEFINE_RATELIMIT_STATE(printk_ratelimit_state, 5 * HZ, 10); -int printk_ratelimit(void) +int __printk_ratelimit(const char *func) { - return __ratelimit(&printk_ratelimit_state); + return ___ratelimit(&printk_ratelimit_state, func); } -EXPORT_SYMBOL(printk_ratelimit); +EXPORT_SYMBOL(__printk_ratelimit); /** * printk_timed_ratelimit - caller-controlled printk ratelimiting diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index 400183346ad2..9b7fd4723878 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -44,7 +44,6 @@ #include <linux/cpu.h> #include <linux/mutex.h> #include <linux/module.h> -#include <linux/kernel_stat.h> #ifdef CONFIG_DEBUG_LOCK_ALLOC static struct lock_class_key rcu_lock_key; @@ -53,8 +52,6 @@ struct lockdep_map rcu_lock_map = EXPORT_SYMBOL_GPL(rcu_lock_map); #endif -int rcu_scheduler_active __read_mostly; - /* * Awaken the corresponding synchronize_rcu() instance now that a * grace period has elapsed. @@ -66,122 +63,3 @@ void wakeme_after_rcu(struct rcu_head *head) rcu = container_of(head, struct rcu_synchronize, head); complete(&rcu->completion); } - -#ifdef CONFIG_TREE_PREEMPT_RCU - -/** - * synchronize_rcu - wait until a grace period has elapsed. - * - * Control will return to the caller some time after a full grace - * period has elapsed, in other words after all currently executing RCU - * read-side critical sections have completed. RCU read-side critical - * sections are delimited by rcu_read_lock() and rcu_read_unlock(), - * and may be nested. - */ -void synchronize_rcu(void) -{ - struct rcu_synchronize rcu; - - if (!rcu_scheduler_active) - return; - - init_completion(&rcu.completion); - /* Will wake me after RCU finished. */ - call_rcu(&rcu.head, wakeme_after_rcu); - /* Wait for it. */ - wait_for_completion(&rcu.completion); -} -EXPORT_SYMBOL_GPL(synchronize_rcu); - -#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ - -/** - * synchronize_sched - wait until an rcu-sched grace period has elapsed. - * - * Control will return to the caller some time after a full rcu-sched - * grace period has elapsed, in other words after all currently executing - * rcu-sched read-side critical sections have completed. These read-side - * critical sections are delimited by rcu_read_lock_sched() and - * rcu_read_unlock_sched(), and may be nested. Note that preempt_disable(), - * local_irq_disable(), and so on may be used in place of - * rcu_read_lock_sched(). - * - * This means that all preempt_disable code sequences, including NMI and - * hardware-interrupt handlers, in progress on entry will have completed - * before this primitive returns. However, this does not guarantee that - * softirq handlers will have completed, since in some kernels, these - * handlers can run in process context, and can block. - * - * This primitive provides the guarantees made by the (now removed) - * synchronize_kernel() API. In contrast, synchronize_rcu() only - * guarantees that rcu_read_lock() sections will have completed. - * In "classic RCU", these two guarantees happen to be one and - * the same, but can differ in realtime RCU implementations. - */ -void synchronize_sched(void) -{ - struct rcu_synchronize rcu; - - if (rcu_blocking_is_gp()) - return; - - init_completion(&rcu.completion); - /* Will wake me after RCU finished. */ - call_rcu_sched(&rcu.head, wakeme_after_rcu); - /* Wait for it. */ - wait_for_completion(&rcu.completion); -} -EXPORT_SYMBOL_GPL(synchronize_sched); - -/** - * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed. - * - * Control will return to the caller some time after a full rcu_bh grace - * period has elapsed, in other words after all currently executing rcu_bh - * read-side critical sections have completed. RCU read-side critical - * sections are delimited by rcu_read_lock_bh() and rcu_read_unlock_bh(), - * and may be nested. - */ -void synchronize_rcu_bh(void) -{ - struct rcu_synchronize rcu; - - if (rcu_blocking_is_gp()) - return; - - init_completion(&rcu.completion); - /* Will wake me after RCU finished. */ - call_rcu_bh(&rcu.head, wakeme_after_rcu); - /* Wait for it. */ - wait_for_completion(&rcu.completion); -} -EXPORT_SYMBOL_GPL(synchronize_rcu_bh); - -static int __cpuinit rcu_barrier_cpu_hotplug(struct notifier_block *self, - unsigned long action, void *hcpu) -{ - return rcu_cpu_notify(self, action, hcpu); -} - -void __init rcu_init(void) -{ - int i; - - __rcu_init(); - cpu_notifier(rcu_barrier_cpu_hotplug, 0); - - /* - * We don't need protection against CPU-hotplug here because - * this is called early in boot, before either interrupts - * or the scheduler are operational. - */ - for_each_online_cpu(i) - rcu_barrier_cpu_hotplug(NULL, CPU_UP_PREPARE, (void *)(long)i); -} - -void rcu_scheduler_starting(void) -{ - WARN_ON(num_online_cpus() != 1); - WARN_ON(nr_context_switches() > 0); - rcu_scheduler_active = 1; -} diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c new file mode 100644 index 000000000000..9f6d9ff2572c --- /dev/null +++ b/kernel/rcutiny.c @@ -0,0 +1,282 @@ +/* + * Read-Copy Update mechanism for mutual exclusion, the Bloatwatch edition. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright IBM Corporation, 2008 + * + * Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com> + * + * For detailed explanation of Read-Copy Update mechanism see - + * Documentation/RCU + */ +#include <linux/moduleparam.h> +#include <linux/completion.h> +#include <linux/interrupt.h> +#include <linux/notifier.h> +#include <linux/rcupdate.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/sched.h> +#include <linux/types.h> +#include <linux/init.h> +#include <linux/time.h> +#include <linux/cpu.h> + +/* Global control variables for rcupdate callback mechanism. */ +struct rcu_ctrlblk { + struct rcu_head *rcucblist; /* List of pending callbacks (CBs). */ + struct rcu_head **donetail; /* ->next pointer of last "done" CB. */ + struct rcu_head **curtail; /* ->next pointer of last CB. */ +}; + +/* Definition for rcupdate control block. */ +static struct rcu_ctrlblk rcu_ctrlblk = { + .donetail = &rcu_ctrlblk.rcucblist, + .curtail = &rcu_ctrlblk.rcucblist, +}; + +static struct rcu_ctrlblk rcu_bh_ctrlblk = { + .donetail = &rcu_bh_ctrlblk.rcucblist, + .curtail = &rcu_bh_ctrlblk.rcucblist, +}; + +#ifdef CONFIG_NO_HZ + +static long rcu_dynticks_nesting = 1; + +/* + * Enter dynticks-idle mode, which is an extended quiescent state + * if we have fully entered that mode (i.e., if the new value of + * dynticks_nesting is zero). + */ +void rcu_enter_nohz(void) +{ + if (--rcu_dynticks_nesting == 0) + rcu_sched_qs(0); /* implies rcu_bh_qsctr_inc(0) */ +} + +/* + * Exit dynticks-idle mode, so that we are no longer in an extended + * quiescent state. + */ +void rcu_exit_nohz(void) +{ + rcu_dynticks_nesting++; +} + +#endif /* #ifdef CONFIG_NO_HZ */ + +/* + * Helper function for rcu_qsctr_inc() and rcu_bh_qsctr_inc(). + * Also disable irqs to avoid confusion due to interrupt handlers + * invoking call_rcu(). + */ +static int rcu_qsctr_help(struct rcu_ctrlblk *rcp) +{ + unsigned long flags; + + local_irq_save(flags); + if (rcp->rcucblist != NULL && + rcp->donetail != rcp->curtail) { + rcp->donetail = rcp->curtail; + local_irq_restore(flags); + return 1; + } + local_irq_restore(flags); + + return 0; +} + +/* + * Record an rcu quiescent state. And an rcu_bh quiescent state while we + * are at it, given that any rcu quiescent state is also an rcu_bh + * quiescent state. Use "+" instead of "||" to defeat short circuiting. + */ +void rcu_sched_qs(int cpu) +{ + if (rcu_qsctr_help(&rcu_ctrlblk) + rcu_qsctr_help(&rcu_bh_ctrlblk)) + raise_softirq(RCU_SOFTIRQ); +} + +/* + * Record an rcu_bh quiescent state. + */ +void rcu_bh_qs(int cpu) +{ + if (rcu_qsctr_help(&rcu_bh_ctrlblk)) + raise_softirq(RCU_SOFTIRQ); +} + +/* + * Check to see if the scheduling-clock interrupt came from an extended + * quiescent state, and, if so, tell RCU about it. + */ +void rcu_check_callbacks(int cpu, int user) +{ + if (user || + (idle_cpu(cpu) && + !in_softirq() && + hardirq_count() <= (1 << HARDIRQ_SHIFT))) + rcu_sched_qs(cpu); + else if (!in_softirq()) + rcu_bh_qs(cpu); +} + +/* + * Helper function for rcu_process_callbacks() that operates on the + * specified rcu_ctrlkblk structure. + */ +static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp) +{ + struct rcu_head *next, *list; + unsigned long flags; + + /* If no RCU callbacks ready to invoke, just return. */ + if (&rcp->rcucblist == rcp->donetail) + return; + + /* Move the ready-to-invoke callbacks to a local list. */ + local_irq_save(flags); + list = rcp->rcucblist; + rcp->rcucblist = *rcp->donetail; + *rcp->donetail = NULL; + if (rcp->curtail == rcp->donetail) + rcp->curtail = &rcp->rcucblist; + rcp->donetail = &rcp->rcucblist; + local_irq_restore(flags); + + /* Invoke the callbacks on the local list. */ + while (list) { + next = list->next; + prefetch(next); + list->func(list); + list = next; + } +} + +/* + * Invoke any callbacks whose grace period has completed. + */ +static void rcu_process_callbacks(struct softirq_action *unused) +{ + __rcu_process_callbacks(&rcu_ctrlblk); + __rcu_process_callbacks(&rcu_bh_ctrlblk); +} + +/* + * Wait for a grace period to elapse. But it is illegal to invoke + * synchronize_sched() from within an RCU read-side critical section. + * Therefore, any legal call to synchronize_sched() is a quiescent + * state, and so on a UP system, synchronize_sched() need do nothing. + * Ditto for synchronize_rcu_bh(). (But Lai Jiangshan points out the + * benefits of doing might_sleep() to reduce latency.) + * + * Cool, huh? (Due to Josh Triplett.) + * + * But we want to make this a static inline later. + */ +void synchronize_sched(void) +{ + cond_resched(); +} +EXPORT_SYMBOL_GPL(synchronize_sched); + +void synchronize_rcu_bh(void) +{ + synchronize_sched(); +} +EXPORT_SYMBOL_GPL(synchronize_rcu_bh); + +/* + * Helper function for call_rcu() and call_rcu_bh(). + */ +static void __call_rcu(struct rcu_head *head, + void (*func)(struct rcu_head *rcu), + struct rcu_ctrlblk *rcp) +{ + unsigned long flags; + + head->func = func; + head->next = NULL; + + local_irq_save(flags); + *rcp->curtail = head; + rcp->curtail = &head->next; + local_irq_restore(flags); +} + +/* + * Post an RCU callback to be invoked after the end of an RCU grace + * period. But since we have but one CPU, that would be after any + * quiescent state. + */ +void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) +{ + __call_rcu(head, func, &rcu_ctrlblk); +} +EXPORT_SYMBOL_GPL(call_rcu); + +/* + * Post an RCU bottom-half callback to be invoked after any subsequent + * quiescent state. + */ +void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) +{ + __call_rcu(head, func, &rcu_bh_ctrlblk); +} +EXPORT_SYMBOL_GPL(call_rcu_bh); + +void rcu_barrier(void) +{ + struct rcu_synchronize rcu; + + init_completion(&rcu.completion); + /* Will wake me after RCU finished. */ + call_rcu(&rcu.head, wakeme_after_rcu); + /* Wait for it. */ + wait_for_completion(&rcu.completion); +} +EXPORT_SYMBOL_GPL(rcu_barrier); + +void rcu_barrier_bh(void) +{ + struct rcu_synchronize rcu; + + init_completion(&rcu.completion); + /* Will wake me after RCU finished. */ + call_rcu_bh(&rcu.head, wakeme_after_rcu); + /* Wait for it. */ + wait_for_completion(&rcu.completion); +} +EXPORT_SYMBOL_GPL(rcu_barrier_bh); + +void rcu_barrier_sched(void) +{ + struct rcu_synchronize rcu; + + init_completion(&rcu.completion); + /* Will wake me after RCU finished. */ + call_rcu_sched(&rcu.head, wakeme_after_rcu); + /* Wait for it. */ + wait_for_completion(&rcu.completion); +} +EXPORT_SYMBOL_GPL(rcu_barrier_sched); + +void __init rcu_init(void) +{ + open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); +} diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index 697c0a0229d4..a621a67ef4e3 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -327,6 +327,11 @@ rcu_torture_cb(struct rcu_head *p) cur_ops->deferred_free(rp); } +static int rcu_no_completed(void) +{ + return 0; +} + static void rcu_torture_deferred_free(struct rcu_torture *p) { call_rcu(&p->rtort_rcu, rcu_torture_cb); @@ -388,6 +393,21 @@ static struct rcu_torture_ops rcu_sync_ops = { .name = "rcu_sync" }; +static struct rcu_torture_ops rcu_expedited_ops = { + .init = rcu_sync_torture_init, + .cleanup = NULL, + .readlock = rcu_torture_read_lock, + .read_delay = rcu_read_delay, /* just reuse rcu's version. */ + .readunlock = rcu_torture_read_unlock, + .completed = rcu_no_completed, + .deferred_free = rcu_sync_torture_deferred_free, + .sync = synchronize_rcu_expedited, + .cb_barrier = NULL, + .stats = NULL, + .irq_capable = 1, + .name = "rcu_expedited" +}; + /* * Definitions for rcu_bh torture testing. */ @@ -547,6 +567,25 @@ static struct rcu_torture_ops srcu_ops = { .name = "srcu" }; +static void srcu_torture_synchronize_expedited(void) +{ + synchronize_srcu_expedited(&srcu_ctl); +} + +static struct rcu_torture_ops srcu_expedited_ops = { + .init = srcu_torture_init, + .cleanup = srcu_torture_cleanup, + .readlock = srcu_torture_read_lock, + .read_delay = srcu_read_delay, + .readunlock = srcu_torture_read_unlock, + .completed = srcu_torture_completed, + .deferred_free = rcu_sync_torture_deferred_free, + .sync = srcu_torture_synchronize_expedited, + .cb_barrier = NULL, + .stats = srcu_torture_stats, + .name = "srcu_expedited" +}; + /* * Definitions for sched torture testing. */ @@ -562,11 +601,6 @@ static void sched_torture_read_unlock(int idx) preempt_enable(); } -static int sched_torture_completed(void) -{ - return 0; -} - static void rcu_sched_torture_deferred_free(struct rcu_torture *p) { call_rcu_sched(&p->rtort_rcu, rcu_torture_cb); @@ -583,7 +617,7 @@ static struct rcu_torture_ops sched_ops = { .readlock = sched_torture_read_lock, .read_delay = rcu_read_delay, /* just reuse rcu's version. */ .readunlock = sched_torture_read_unlock, - .completed = sched_torture_completed, + .completed = rcu_no_completed, .deferred_free = rcu_sched_torture_deferred_free, .sync = sched_torture_synchronize, .cb_barrier = rcu_barrier_sched, @@ -592,13 +626,13 @@ static struct rcu_torture_ops sched_ops = { .name = "sched" }; -static struct rcu_torture_ops sched_ops_sync = { +static struct rcu_torture_ops sched_sync_ops = { .init = rcu_sync_torture_init, .cleanup = NULL, .readlock = sched_torture_read_lock, .read_delay = rcu_read_delay, /* just reuse rcu's version. */ .readunlock = sched_torture_read_unlock, - .completed = sched_torture_completed, + .completed = rcu_no_completed, .deferred_free = rcu_sync_torture_deferred_free, .sync = sched_torture_synchronize, .cb_barrier = NULL, @@ -612,7 +646,7 @@ static struct rcu_torture_ops sched_expedited_ops = { .readlock = sched_torture_read_lock, .read_delay = rcu_read_delay, /* just reuse rcu's version. */ .readunlock = sched_torture_read_unlock, - .completed = sched_torture_completed, + .completed = rcu_no_completed, .deferred_free = rcu_sync_torture_deferred_free, .sync = synchronize_sched_expedited, .cb_barrier = NULL, @@ -1097,9 +1131,10 @@ rcu_torture_init(void) int cpu; int firsterr = 0; static struct rcu_torture_ops *torture_ops[] = - { &rcu_ops, &rcu_sync_ops, &rcu_bh_ops, &rcu_bh_sync_ops, - &sched_expedited_ops, - &srcu_ops, &sched_ops, &sched_ops_sync, }; + { &rcu_ops, &rcu_sync_ops, &rcu_expedited_ops, + &rcu_bh_ops, &rcu_bh_sync_ops, + &srcu_ops, &srcu_expedited_ops, + &sched_ops, &sched_sync_ops, &sched_expedited_ops, }; mutex_lock(&fullstop_mutex); @@ -1110,8 +1145,12 @@ rcu_torture_init(void) break; } if (i == ARRAY_SIZE(torture_ops)) { - printk(KERN_ALERT "rcutorture: invalid torture type: \"%s\"\n", + printk(KERN_ALERT "rcu-torture: invalid torture type: \"%s\"\n", torture_type); + printk(KERN_ALERT "rcu-torture types:"); + for (i = 0; i < ARRAY_SIZE(torture_ops); i++) + printk(KERN_ALERT " %s", torture_ops[i]->name); + printk(KERN_ALERT "\n"); mutex_unlock(&fullstop_mutex); return -EINVAL; } diff --git a/kernel/rcutree.c b/kernel/rcutree.c index f3077c0ab181..53ae9598f798 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -46,18 +46,22 @@ #include <linux/cpu.h> #include <linux/mutex.h> #include <linux/time.h> +#include <linux/kernel_stat.h> #include "rcutree.h" /* Data structures. */ +static struct lock_class_key rcu_node_class[NUM_RCU_LVLS]; + #define RCU_STATE_INITIALIZER(name) { \ .level = { &name.node[0] }, \ .levelcnt = { \ NUM_RCU_LVL_0, /* root of hierarchy. */ \ NUM_RCU_LVL_1, \ NUM_RCU_LVL_2, \ - NUM_RCU_LVL_3, /* == MAX_RCU_LVLS */ \ + NUM_RCU_LVL_3, \ + NUM_RCU_LVL_4, /* == MAX_RCU_LVLS */ \ }, \ .signaled = RCU_GP_IDLE, \ .gpnum = -300, \ @@ -77,6 +81,8 @@ DEFINE_PER_CPU(struct rcu_data, rcu_sched_data); struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh_state); DEFINE_PER_CPU(struct rcu_data, rcu_bh_data); +static int rcu_scheduler_active __read_mostly; + /* * Return true if an RCU grace period is in progress. The ACCESS_ONCE()s @@ -98,7 +104,7 @@ void rcu_sched_qs(int cpu) struct rcu_data *rdp; rdp = &per_cpu(rcu_sched_data, cpu); - rdp->passed_quiesc_completed = rdp->completed; + rdp->passed_quiesc_completed = rdp->gpnum - 1; barrier(); rdp->passed_quiesc = 1; rcu_preempt_note_context_switch(cpu); @@ -109,7 +115,7 @@ void rcu_bh_qs(int cpu) struct rcu_data *rdp; rdp = &per_cpu(rcu_bh_data, cpu); - rdp->passed_quiesc_completed = rdp->completed; + rdp->passed_quiesc_completed = rdp->gpnum - 1; barrier(); rdp->passed_quiesc = 1; } @@ -335,28 +341,9 @@ void rcu_irq_exit(void) set_need_resched(); } -/* - * Record the specified "completed" value, which is later used to validate - * dynticks counter manipulations. Specify "rsp->completed - 1" to - * unconditionally invalidate any future dynticks manipulations (which is - * useful at the beginning of a grace period). - */ -static void dyntick_record_completed(struct rcu_state *rsp, long comp) -{ - rsp->dynticks_completed = comp; -} - #ifdef CONFIG_SMP /* - * Recall the previously recorded value of the completion for dynticks. - */ -static long dyntick_recall_completed(struct rcu_state *rsp) -{ - return rsp->dynticks_completed; -} - -/* * Snapshot the specified CPU's dynticks counter so that we can later * credit them with an implicit quiescent state. Return 1 if this CPU * is in dynticks idle mode, which is an extended quiescent state. @@ -419,24 +406,8 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) #else /* #ifdef CONFIG_NO_HZ */ -static void dyntick_record_completed(struct rcu_state *rsp, long comp) -{ -} - #ifdef CONFIG_SMP -/* - * If there are no dynticks, then the only way that a CPU can passively - * be in a quiescent state is to be offline. Unlike dynticks idle, which - * is a point in time during the prior (already finished) grace period, - * an offline CPU is always in a quiescent state, and thus can be - * unconditionally applied. So just return the current value of completed. - */ -static long dyntick_recall_completed(struct rcu_state *rsp) -{ - return rsp->completed; -} - static int dyntick_save_progress_counter(struct rcu_data *rdp) { return 0; @@ -553,13 +524,33 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp) /* * Update CPU-local rcu_data state to record the newly noticed grace period. * This is used both when we started the grace period and when we notice - * that someone else started the grace period. + * that someone else started the grace period. The caller must hold the + * ->lock of the leaf rcu_node structure corresponding to the current CPU, + * and must have irqs disabled. */ +static void __note_new_gpnum(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) +{ + if (rdp->gpnum != rnp->gpnum) { + rdp->qs_pending = 1; + rdp->passed_quiesc = 0; + rdp->gpnum = rnp->gpnum; + } +} + static void note_new_gpnum(struct rcu_state *rsp, struct rcu_data *rdp) { - rdp->qs_pending = 1; - rdp->passed_quiesc = 0; - rdp->gpnum = rsp->gpnum; + unsigned long flags; + struct rcu_node *rnp; + + local_irq_save(flags); + rnp = rdp->mynode; + if (rdp->gpnum == ACCESS_ONCE(rnp->gpnum) || /* outside lock. */ + !spin_trylock(&rnp->lock)) { /* irqs already off, retry later. */ + local_irq_restore(flags); + return; + } + __note_new_gpnum(rsp, rnp, rdp); + spin_unlock_irqrestore(&rnp->lock, flags); } /* @@ -583,6 +574,79 @@ check_for_new_grace_period(struct rcu_state *rsp, struct rcu_data *rdp) } /* + * Advance this CPU's callbacks, but only if the current grace period + * has ended. This may be called only from the CPU to whom the rdp + * belongs. In addition, the corresponding leaf rcu_node structure's + * ->lock must be held by the caller, with irqs disabled. + */ +static void +__rcu_process_gp_end(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) +{ + /* Did another grace period end? */ + if (rdp->completed != rnp->completed) { + + /* Advance callbacks. No harm if list empty. */ + rdp->nxttail[RCU_DONE_TAIL] = rdp->nxttail[RCU_WAIT_TAIL]; + rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_READY_TAIL]; + rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; + + /* Remember that we saw this grace-period completion. */ + rdp->completed = rnp->completed; + } +} + +/* + * Advance this CPU's callbacks, but only if the current grace period + * has ended. This may be called only from the CPU to whom the rdp + * belongs. + */ +static void +rcu_process_gp_end(struct rcu_state *rsp, struct rcu_data *rdp) +{ + unsigned long flags; + struct rcu_node *rnp; + + local_irq_save(flags); + rnp = rdp->mynode; + if (rdp->completed == ACCESS_ONCE(rnp->completed) || /* outside lock. */ + !spin_trylock(&rnp->lock)) { /* irqs already off, retry later. */ + local_irq_restore(flags); + return; + } + __rcu_process_gp_end(rsp, rnp, rdp); + spin_unlock_irqrestore(&rnp->lock, flags); +} + +/* + * Do per-CPU grace-period initialization for running CPU. The caller + * must hold the lock of the leaf rcu_node structure corresponding to + * this CPU. + */ +static void +rcu_start_gp_per_cpu(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) +{ + /* Prior grace period ended, so advance callbacks for current CPU. */ + __rcu_process_gp_end(rsp, rnp, rdp); + + /* + * Because this CPU just now started the new grace period, we know + * that all of its callbacks will be covered by this upcoming grace + * period, even the ones that were registered arbitrarily recently. + * Therefore, advance all outstanding callbacks to RCU_WAIT_TAIL. + * + * Other CPUs cannot be sure exactly when the grace period started. + * Therefore, their recently registered callbacks must pass through + * an additional RCU_NEXT_READY stage, so that they will be handled + * by the next RCU grace period. + */ + rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; + rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; + + /* Set state so that this CPU will detect the next quiescent state. */ + __note_new_gpnum(rsp, rnp, rdp); +} + +/* * Start a new RCU grace period if warranted, re-initializing the hierarchy * in preparation for detecting the next grace period. The caller must hold * the root node's ->lock, which is released before return. Hard irqs must @@ -596,7 +660,23 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags) struct rcu_node *rnp = rcu_get_root(rsp); if (!cpu_needs_another_gp(rsp, rdp)) { - spin_unlock_irqrestore(&rnp->lock, flags); + if (rnp->completed == rsp->completed) { + spin_unlock_irqrestore(&rnp->lock, flags); + return; + } + spin_unlock(&rnp->lock); /* irqs remain disabled. */ + + /* + * Propagate new ->completed value to rcu_node structures + * so that other CPUs don't have to wait until the start + * of the next grace period to process their callbacks. + */ + rcu_for_each_node_breadth_first(rsp, rnp) { + spin_lock(&rnp->lock); /* irqs already disabled. */ + rnp->completed = rsp->completed; + spin_unlock(&rnp->lock); /* irqs remain disabled. */ + } + local_irq_restore(flags); return; } @@ -606,29 +686,15 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags) rsp->signaled = RCU_GP_INIT; /* Hold off force_quiescent_state. */ rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS; record_gp_stall_check_time(rsp); - dyntick_record_completed(rsp, rsp->completed - 1); - note_new_gpnum(rsp, rdp); - - /* - * Because this CPU just now started the new grace period, we know - * that all of its callbacks will be covered by this upcoming grace - * period, even the ones that were registered arbitrarily recently. - * Therefore, advance all outstanding callbacks to RCU_WAIT_TAIL. - * - * Other CPUs cannot be sure exactly when the grace period started. - * Therefore, their recently registered callbacks must pass through - * an additional RCU_NEXT_READY stage, so that they will be handled - * by the next RCU grace period. - */ - rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; - rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; /* Special-case the common single-level case. */ if (NUM_RCU_NODES == 1) { rcu_preempt_check_blocked_tasks(rnp); rnp->qsmask = rnp->qsmaskinit; rnp->gpnum = rsp->gpnum; + rnp->completed = rsp->completed; rsp->signaled = RCU_SIGNAL_INIT; /* force_quiescent_state OK. */ + rcu_start_gp_per_cpu(rsp, rnp, rdp); spin_unlock_irqrestore(&rnp->lock, flags); return; } @@ -661,6 +727,9 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags) rcu_preempt_check_blocked_tasks(rnp); rnp->qsmask = rnp->qsmaskinit; rnp->gpnum = rsp->gpnum; + rnp->completed = rsp->completed; + if (rnp == rdp->mynode) + rcu_start_gp_per_cpu(rsp, rnp, rdp); spin_unlock(&rnp->lock); /* irqs remain disabled. */ } @@ -672,58 +741,32 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags) } /* - * Advance this CPU's callbacks, but only if the current grace period - * has ended. This may be called only from the CPU to whom the rdp - * belongs. + * Report a full set of quiescent states to the specified rcu_state + * data structure. This involves cleaning up after the prior grace + * period and letting rcu_start_gp() start up the next grace period + * if one is needed. Note that the caller must hold rnp->lock, as + * required by rcu_start_gp(), which will release it. */ -static void -rcu_process_gp_end(struct rcu_state *rsp, struct rcu_data *rdp) -{ - long completed_snap; - unsigned long flags; - - local_irq_save(flags); - completed_snap = ACCESS_ONCE(rsp->completed); /* outside of lock. */ - - /* Did another grace period end? */ - if (rdp->completed != completed_snap) { - - /* Advance callbacks. No harm if list empty. */ - rdp->nxttail[RCU_DONE_TAIL] = rdp->nxttail[RCU_WAIT_TAIL]; - rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_READY_TAIL]; - rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; - - /* Remember that we saw this grace-period completion. */ - rdp->completed = completed_snap; - } - local_irq_restore(flags); -} - -/* - * Clean up after the prior grace period and let rcu_start_gp() start up - * the next grace period if one is needed. Note that the caller must - * hold rnp->lock, as required by rcu_start_gp(), which will release it. - */ -static void cpu_quiet_msk_finish(struct rcu_state *rsp, unsigned long flags) +static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) __releases(rcu_get_root(rsp)->lock) { WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); rsp->completed = rsp->gpnum; rsp->signaled = RCU_GP_IDLE; - rcu_process_gp_end(rsp, rsp->rda[smp_processor_id()]); rcu_start_gp(rsp, flags); /* releases root node's rnp->lock. */ } /* - * Similar to cpu_quiet(), for which it is a helper function. Allows - * a group of CPUs to be quieted at one go, though all the CPUs in the - * group must be represented by the same leaf rcu_node structure. - * That structure's lock must be held upon entry, and it is released - * before return. + * Similar to rcu_report_qs_rdp(), for which it is a helper function. + * Allows quiescent states for a group of CPUs to be reported at one go + * to the specified rcu_node structure, though all the CPUs in the group + * must be represented by the same rcu_node structure (which need not be + * a leaf rcu_node structure, though it often will be). That structure's + * lock must be held upon entry, and it is released before return. */ static void -cpu_quiet_msk(unsigned long mask, struct rcu_state *rsp, struct rcu_node *rnp, - unsigned long flags) +rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, + struct rcu_node *rnp, unsigned long flags) __releases(rnp->lock) { struct rcu_node *rnp_c; @@ -759,21 +802,23 @@ cpu_quiet_msk(unsigned long mask, struct rcu_state *rsp, struct rcu_node *rnp, /* * Get here if we are the last CPU to pass through a quiescent - * state for this grace period. Invoke cpu_quiet_msk_finish() + * state for this grace period. Invoke rcu_report_qs_rsp() * to clean up and start the next grace period if one is needed. */ - cpu_quiet_msk_finish(rsp, flags); /* releases rnp->lock. */ + rcu_report_qs_rsp(rsp, flags); /* releases rnp->lock. */ } /* - * Record a quiescent state for the specified CPU, which must either be - * the current CPU. The lastcomp argument is used to make sure we are - * still in the grace period of interest. We don't want to end the current - * grace period based on quiescent states detected in an earlier grace - * period! + * Record a quiescent state for the specified CPU to that CPU's rcu_data + * structure. This must be either called from the specified CPU, or + * called when the specified CPU is known to be offline (and when it is + * also known that no other CPU is concurrently trying to help the offline + * CPU). The lastcomp argument is used to make sure we are still in the + * grace period of interest. We don't want to end the current grace period + * based on quiescent states detected in an earlier grace period! */ static void -cpu_quiet(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long lastcomp) +rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long lastcomp) { unsigned long flags; unsigned long mask; @@ -781,15 +826,15 @@ cpu_quiet(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long lastcomp) rnp = rdp->mynode; spin_lock_irqsave(&rnp->lock, flags); - if (lastcomp != ACCESS_ONCE(rsp->completed)) { + if (lastcomp != rnp->completed) { /* * Someone beat us to it for this grace period, so leave. * The race with GP start is resolved by the fact that we * hold the leaf rcu_node lock, so that the per-CPU bits * cannot yet be initialized -- so we would simply find our - * CPU's bit already cleared in cpu_quiet_msk() if this race - * occurred. + * CPU's bit already cleared in rcu_report_qs_rnp() if this + * race occurred. */ rdp->passed_quiesc = 0; /* try again later! */ spin_unlock_irqrestore(&rnp->lock, flags); @@ -807,7 +852,7 @@ cpu_quiet(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long lastcomp) */ rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; - cpu_quiet_msk(mask, rsp, rnp, flags); /* releases rnp->lock */ + rcu_report_qs_rnp(mask, rsp, rnp, flags); /* rlses rnp->lock */ } } @@ -838,8 +883,11 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp) if (!rdp->passed_quiesc) return; - /* Tell RCU we are done (but cpu_quiet() will be the judge of that). */ - cpu_quiet(rdp->cpu, rsp, rdp, rdp->passed_quiesc_completed); + /* + * Tell RCU we are done (but rcu_report_qs_rdp() will be the + * judge of that). + */ + rcu_report_qs_rdp(rdp->cpu, rsp, rdp, rdp->passed_quiesc_completed); } #ifdef CONFIG_HOTPLUG_CPU @@ -899,8 +947,8 @@ static void rcu_adopt_orphan_cbs(struct rcu_state *rsp) static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp) { unsigned long flags; - long lastcomp; unsigned long mask; + int need_report = 0; struct rcu_data *rdp = rsp->rda[cpu]; struct rcu_node *rnp; @@ -914,30 +962,32 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp) spin_lock(&rnp->lock); /* irqs already disabled. */ rnp->qsmaskinit &= ~mask; if (rnp->qsmaskinit != 0) { - spin_unlock(&rnp->lock); /* irqs remain disabled. */ + if (rnp != rdp->mynode) + spin_unlock(&rnp->lock); /* irqs remain disabled. */ break; } - - /* - * If there was a task blocking the current grace period, - * and if all CPUs have checked in, we need to propagate - * the quiescent state up the rcu_node hierarchy. But that - * is inconvenient at the moment due to deadlock issues if - * this should end the current grace period. So set the - * offlined CPU's bit in ->qsmask in order to force the - * next force_quiescent_state() invocation to clean up this - * mess in a deadlock-free manner. - */ - if (rcu_preempt_offline_tasks(rsp, rnp, rdp) && !rnp->qsmask) - rnp->qsmask |= mask; - + if (rnp == rdp->mynode) + need_report = rcu_preempt_offline_tasks(rsp, rnp, rdp); + else + spin_unlock(&rnp->lock); /* irqs remain disabled. */ mask = rnp->grpmask; - spin_unlock(&rnp->lock); /* irqs remain disabled. */ rnp = rnp->parent; } while (rnp != NULL); - lastcomp = rsp->completed; - spin_unlock_irqrestore(&rsp->onofflock, flags); + /* + * We still hold the leaf rcu_node structure lock here, and + * irqs are still disabled. The reason for this subterfuge is + * because invoking rcu_report_unblock_qs_rnp() with ->onofflock + * held leads to deadlock. + */ + spin_unlock(&rsp->onofflock); /* irqs remain disabled. */ + rnp = rdp->mynode; + if (need_report & RCU_OFL_TASKS_NORM_GP) + rcu_report_unblock_qs_rnp(rnp, flags); + else + spin_unlock_irqrestore(&rnp->lock, flags); + if (need_report & RCU_OFL_TASKS_EXP_GP) + rcu_report_exp_rnp(rsp, rnp); rcu_adopt_orphan_cbs(rsp); } @@ -1109,7 +1159,7 @@ static int rcu_process_dyntick(struct rcu_state *rsp, long lastcomp, rcu_for_each_leaf_node(rsp, rnp) { mask = 0; spin_lock_irqsave(&rnp->lock, flags); - if (rsp->completed != lastcomp) { + if (rnp->completed != lastcomp) { spin_unlock_irqrestore(&rnp->lock, flags); return 1; } @@ -1123,10 +1173,10 @@ static int rcu_process_dyntick(struct rcu_state *rsp, long lastcomp, if ((rnp->qsmask & bit) != 0 && f(rsp->rda[cpu])) mask |= bit; } - if (mask != 0 && rsp->completed == lastcomp) { + if (mask != 0 && rnp->completed == lastcomp) { - /* cpu_quiet_msk() releases rnp->lock. */ - cpu_quiet_msk(mask, rsp, rnp, flags); + /* rcu_report_qs_rnp() releases rnp->lock. */ + rcu_report_qs_rnp(mask, rsp, rnp, flags); continue; } spin_unlock_irqrestore(&rnp->lock, flags); @@ -1144,6 +1194,7 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed) long lastcomp; struct rcu_node *rnp = rcu_get_root(rsp); u8 signaled; + u8 forcenow; if (!rcu_gp_in_progress(rsp)) return; /* No grace period in progress, nothing to force. */ @@ -1156,10 +1207,10 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed) goto unlock_ret; /* no emergency and done recently. */ rsp->n_force_qs++; spin_lock(&rnp->lock); - lastcomp = rsp->completed; + lastcomp = rsp->gpnum - 1; signaled = rsp->signaled; rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS; - if (lastcomp == rsp->gpnum) { + if(!rcu_gp_in_progress(rsp)) { rsp->n_force_qs_ngp++; spin_unlock(&rnp->lock); goto unlock_ret; /* no GP in progress, time updated. */ @@ -1180,21 +1231,29 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed) if (rcu_process_dyntick(rsp, lastcomp, dyntick_save_progress_counter)) goto unlock_ret; + /* fall into next case. */ + + case RCU_SAVE_COMPLETED: /* Update state, record completion counter. */ + forcenow = 0; spin_lock(&rnp->lock); - if (lastcomp == rsp->completed && - rsp->signaled == RCU_SAVE_DYNTICK) { + if (lastcomp + 1 == rsp->gpnum && + lastcomp == rsp->completed && + rsp->signaled == signaled) { rsp->signaled = RCU_FORCE_QS; - dyntick_record_completed(rsp, lastcomp); + rsp->completed_fqs = lastcomp; + forcenow = signaled == RCU_SAVE_COMPLETED; } spin_unlock(&rnp->lock); - break; + if (!forcenow) + break; + /* fall into next case. */ case RCU_FORCE_QS: /* Check dyntick-idle state, send IPI to laggarts. */ - if (rcu_process_dyntick(rsp, dyntick_recall_completed(rsp), + if (rcu_process_dyntick(rsp, rsp->completed_fqs, rcu_implicit_dynticks_qs)) goto unlock_ret; @@ -1351,6 +1410,68 @@ void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) } EXPORT_SYMBOL_GPL(call_rcu_bh); +/** + * synchronize_sched - wait until an rcu-sched grace period has elapsed. + * + * Control will return to the caller some time after a full rcu-sched + * grace period has elapsed, in other words after all currently executing + * rcu-sched read-side critical sections have completed. These read-side + * critical sections are delimited by rcu_read_lock_sched() and + * rcu_read_unlock_sched(), and may be nested. Note that preempt_disable(), + * local_irq_disable(), and so on may be used in place of + * rcu_read_lock_sched(). + * + * This means that all preempt_disable code sequences, including NMI and + * hardware-interrupt handlers, in progress on entry will have completed + * before this primitive returns. However, this does not guarantee that + * softirq handlers will have completed, since in some kernels, these + * handlers can run in process context, and can block. + * + * This primitive provides the guarantees made by the (now removed) + * synchronize_kernel() API. In contrast, synchronize_rcu() only + * guarantees that rcu_read_lock() sections will have completed. + * In "classic RCU", these two guarantees happen to be one and + * the same, but can differ in realtime RCU implementations. + */ +void synchronize_sched(void) +{ + struct rcu_synchronize rcu; + + if (rcu_blocking_is_gp()) + return; + + init_completion(&rcu.completion); + /* Will wake me after RCU finished. */ + call_rcu_sched(&rcu.head, wakeme_after_rcu); + /* Wait for it. */ + wait_for_completion(&rcu.completion); +} +EXPORT_SYMBOL_GPL(synchronize_sched); + +/** + * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed. + * + * Control will return to the caller some time after a full rcu_bh grace + * period has elapsed, in other words after all currently executing rcu_bh + * read-side critical sections have completed. RCU read-side critical + * sections are delimited by rcu_read_lock_bh() and rcu_read_unlock_bh(), + * and may be nested. + */ +void synchronize_rcu_bh(void) +{ + struct rcu_synchronize rcu; + + if (rcu_blocking_is_gp()) + return; + + init_completion(&rcu.completion); + /* Will wake me after RCU finished. */ + call_rcu_bh(&rcu.head, wakeme_after_rcu); + /* Wait for it. */ + wait_for_completion(&rcu.completion); +} +EXPORT_SYMBOL_GPL(synchronize_rcu_bh); + /* * Check to see if there is any immediate RCU-related work to be done * by the current CPU, for the specified type of RCU, returning 1 if so. @@ -1360,6 +1481,8 @@ EXPORT_SYMBOL_GPL(call_rcu_bh); */ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) { + struct rcu_node *rnp = rdp->mynode; + rdp->n_rcu_pending++; /* Check for CPU stalls, if enabled. */ @@ -1384,13 +1507,13 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) } /* Has another RCU grace period completed? */ - if (ACCESS_ONCE(rsp->completed) != rdp->completed) { /* outside lock */ + if (ACCESS_ONCE(rnp->completed) != rdp->completed) { /* outside lock */ rdp->n_rp_gp_completed++; return 1; } /* Has a new RCU grace period started? */ - if (ACCESS_ONCE(rsp->gpnum) != rdp->gpnum) { /* outside lock */ + if (ACCESS_ONCE(rnp->gpnum) != rdp->gpnum) { /* outside lock */ rdp->n_rp_gp_started++; return 1; } @@ -1433,6 +1556,21 @@ int rcu_needs_cpu(int cpu) rcu_preempt_needs_cpu(cpu); } +/* + * This function is invoked towards the end of the scheduler's initialization + * process. Before this is called, the idle task might contain + * RCU read-side critical sections (during which time, this idle + * task is booting the system). After this function is called, the + * idle tasks are prohibited from containing RCU read-side critical + * sections. + */ +void rcu_scheduler_starting(void) +{ + WARN_ON(num_online_cpus() != 1); + WARN_ON(nr_context_switches() > 0); + rcu_scheduler_active = 1; +} + static DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL}; static atomic_t rcu_barrier_cpu_count; static DEFINE_MUTEX(rcu_barrier_mutex); @@ -1544,21 +1682,16 @@ static void __cpuinit rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptable) { unsigned long flags; - long lastcomp; unsigned long mask; struct rcu_data *rdp = rsp->rda[cpu]; struct rcu_node *rnp = rcu_get_root(rsp); /* Set up local state, ensuring consistent view of global state. */ spin_lock_irqsave(&rnp->lock, flags); - lastcomp = rsp->completed; - rdp->completed = lastcomp; - rdp->gpnum = lastcomp; rdp->passed_quiesc = 0; /* We could be racing with new GP, */ rdp->qs_pending = 1; /* so set up to respond to current GP. */ rdp->beenonline = 1; /* We have now been online. */ rdp->preemptable = preemptable; - rdp->passed_quiesc_completed = lastcomp - 1; rdp->qlen_last_fqs_check = 0; rdp->n_force_qs_snap = rsp->n_force_qs; rdp->blimit = blimit; @@ -1580,6 +1713,11 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptable) spin_lock(&rnp->lock); /* irqs already disabled. */ rnp->qsmaskinit |= mask; mask = rnp->grpmask; + if (rnp == rdp->mynode) { + rdp->gpnum = rnp->completed; /* if GP in progress... */ + rdp->completed = rnp->completed; + rdp->passed_quiesc_completed = rnp->completed - 1; + } spin_unlock(&rnp->lock); /* irqs already disabled. */ rnp = rnp->parent; } while (rnp != NULL && !(rnp->qsmaskinit & mask)); @@ -1597,8 +1735,8 @@ static void __cpuinit rcu_online_cpu(int cpu) /* * Handle CPU online/offline notification events. */ -int __cpuinit rcu_cpu_notify(struct notifier_block *self, - unsigned long action, void *hcpu) +static int __cpuinit rcu_cpu_notify(struct notifier_block *self, + unsigned long action, void *hcpu) { long cpu = (long)hcpu; @@ -1685,8 +1823,8 @@ static void __init rcu_init_one(struct rcu_state *rsp) cpustride *= rsp->levelspread[i]; rnp = rsp->level[i]; for (j = 0; j < rsp->levelcnt[i]; j++, rnp++) { - if (rnp != rcu_get_root(rsp)) - spin_lock_init(&rnp->lock); + spin_lock_init(&rnp->lock); + lockdep_set_class(&rnp->lock, &rcu_node_class[i]); rnp->gpnum = 0; rnp->qsmask = 0; rnp->qsmaskinit = 0; @@ -1707,9 +1845,10 @@ static void __init rcu_init_one(struct rcu_state *rsp) rnp->level = i; INIT_LIST_HEAD(&rnp->blocked_tasks[0]); INIT_LIST_HEAD(&rnp->blocked_tasks[1]); + INIT_LIST_HEAD(&rnp->blocked_tasks[2]); + INIT_LIST_HEAD(&rnp->blocked_tasks[3]); } } - spin_lock_init(&rcu_get_root(rsp)->lock); } /* @@ -1735,16 +1874,30 @@ do { \ } \ } while (0) -void __init __rcu_init(void) +void __init rcu_init(void) { + int i; + rcu_bootup_announce(); #ifdef CONFIG_RCU_CPU_STALL_DETECTOR printk(KERN_INFO "RCU-based detection of stalled CPUs is enabled.\n"); #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ +#if NUM_RCU_LVL_4 != 0 + printk(KERN_INFO "Experimental four-level hierarchy is enabled.\n"); +#endif /* #if NUM_RCU_LVL_4 != 0 */ RCU_INIT_FLAVOR(&rcu_sched_state, rcu_sched_data); RCU_INIT_FLAVOR(&rcu_bh_state, rcu_bh_data); __rcu_init_preempt(); open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); + + /* + * We don't need protection against CPU-hotplug here because + * this is called early in boot, before either interrupts + * or the scheduler are operational. + */ + cpu_notifier(rcu_cpu_notify, 0); + for_each_online_cpu(i) + rcu_cpu_notify(NULL, CPU_UP_PREPARE, (void *)(long)i); } #include "rcutree_plugin.h" diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 1899023b0962..d2a0046f63b2 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -34,10 +34,11 @@ * In practice, this has not been tested, so there is probably some * bug somewhere. */ -#define MAX_RCU_LVLS 3 +#define MAX_RCU_LVLS 4 #define RCU_FANOUT (CONFIG_RCU_FANOUT) #define RCU_FANOUT_SQ (RCU_FANOUT * RCU_FANOUT) #define RCU_FANOUT_CUBE (RCU_FANOUT_SQ * RCU_FANOUT) +#define RCU_FANOUT_FOURTH (RCU_FANOUT_CUBE * RCU_FANOUT) #if NR_CPUS <= RCU_FANOUT # define NUM_RCU_LVLS 1 @@ -45,23 +46,33 @@ # define NUM_RCU_LVL_1 (NR_CPUS) # define NUM_RCU_LVL_2 0 # define NUM_RCU_LVL_3 0 +# define NUM_RCU_LVL_4 0 #elif NR_CPUS <= RCU_FANOUT_SQ # define NUM_RCU_LVLS 2 # define NUM_RCU_LVL_0 1 # define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT) # define NUM_RCU_LVL_2 (NR_CPUS) # define NUM_RCU_LVL_3 0 +# define NUM_RCU_LVL_4 0 #elif NR_CPUS <= RCU_FANOUT_CUBE # define NUM_RCU_LVLS 3 # define NUM_RCU_LVL_0 1 # define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_SQ) # define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT) # define NUM_RCU_LVL_3 NR_CPUS +# define NUM_RCU_LVL_4 0 +#elif NR_CPUS <= RCU_FANOUT_FOURTH +# define NUM_RCU_LVLS 4 +# define NUM_RCU_LVL_0 1 +# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_CUBE) +# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_SQ) +# define NUM_RCU_LVL_3 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT) +# define NUM_RCU_LVL_4 NR_CPUS #else # error "CONFIG_RCU_FANOUT insufficient for NR_CPUS" #endif /* #if (NR_CPUS) <= RCU_FANOUT */ -#define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3) +#define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3 + NUM_RCU_LVL_4) #define NUM_RCU_NODES (RCU_SUM - NR_CPUS) /* @@ -84,14 +95,21 @@ struct rcu_node { long gpnum; /* Current grace period for this node. */ /* This will either be equal to or one */ /* behind the root rcu_node's gpnum. */ + long completed; /* Last grace period completed for this node. */ + /* This will either be equal to or one */ + /* behind the root rcu_node's gpnum. */ unsigned long qsmask; /* CPUs or groups that need to switch in */ /* order for current grace period to proceed.*/ /* In leaf rcu_node, each bit corresponds to */ /* an rcu_data structure, otherwise, each */ /* bit corresponds to a child rcu_node */ /* structure. */ + unsigned long expmask; /* Groups that have ->blocked_tasks[] */ + /* elements that need to drain to allow the */ + /* current expedited grace period to */ + /* complete (only for TREE_PREEMPT_RCU). */ unsigned long qsmaskinit; - /* Per-GP initialization for qsmask. */ + /* Per-GP initial value for qsmask & expmask. */ unsigned long grpmask; /* Mask to apply to parent qsmask. */ /* Only one bit will be set in this mask. */ int grplo; /* lowest-numbered CPU or group here. */ @@ -99,7 +117,7 @@ struct rcu_node { u8 grpnum; /* CPU/group number for next level up. */ u8 level; /* root is at level 0. */ struct rcu_node *parent; - struct list_head blocked_tasks[2]; + struct list_head blocked_tasks[4]; /* Tasks blocked in RCU read-side critsect. */ /* Grace period number (->gpnum) x blocked */ /* by tasks on the (x & 0x1) element of the */ @@ -114,6 +132,21 @@ struct rcu_node { for ((rnp) = &(rsp)->node[0]; \ (rnp) < &(rsp)->node[NUM_RCU_NODES]; (rnp)++) +/* + * Do a breadth-first scan of the non-leaf rcu_node structures for the + * specified rcu_state structure. Note that if there is a singleton + * rcu_node tree with but one rcu_node structure, this loop is a no-op. + */ +#define rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) \ + for ((rnp) = &(rsp)->node[0]; \ + (rnp) < (rsp)->level[NUM_RCU_LVLS - 1]; (rnp)++) + +/* + * Scan the leaves of the rcu_node hierarchy for the specified rcu_state + * structure. Note that if there is a singleton rcu_node tree with but + * one rcu_node structure, this loop -will- visit the rcu_node structure. + * It is still a leaf node, even if it is also the root node. + */ #define rcu_for_each_leaf_node(rsp, rnp) \ for ((rnp) = (rsp)->level[NUM_RCU_LVLS - 1]; \ (rnp) < &(rsp)->node[NUM_RCU_NODES]; (rnp)++) @@ -204,11 +237,12 @@ struct rcu_data { #define RCU_GP_IDLE 0 /* No grace period in progress. */ #define RCU_GP_INIT 1 /* Grace period being initialized. */ #define RCU_SAVE_DYNTICK 2 /* Need to scan dyntick state. */ -#define RCU_FORCE_QS 3 /* Need to force quiescent state. */ +#define RCU_SAVE_COMPLETED 3 /* Need to save rsp->completed. */ +#define RCU_FORCE_QS 4 /* Need to force quiescent state. */ #ifdef CONFIG_NO_HZ #define RCU_SIGNAL_INIT RCU_SAVE_DYNTICK #else /* #ifdef CONFIG_NO_HZ */ -#define RCU_SIGNAL_INIT RCU_FORCE_QS +#define RCU_SIGNAL_INIT RCU_SAVE_COMPLETED #endif /* #else #ifdef CONFIG_NO_HZ */ #define RCU_JIFFIES_TILL_FORCE_QS 3 /* for rsp->jiffies_force_qs */ @@ -246,7 +280,7 @@ struct rcu_state { long gpnum; /* Current gp number. */ long completed; /* # of last completed gp. */ - /* End of fields guarded by root rcu_node's lock. */ + /* End of fields guarded by root rcu_node's lock. */ spinlock_t onofflock; /* exclude on/offline and */ /* starting new GP. Also */ @@ -260,6 +294,8 @@ struct rcu_state { long orphan_qlen; /* Number of orphaned cbs. */ spinlock_t fqslock; /* Only one task forcing */ /* quiescent states. */ + long completed_fqs; /* Value of completed @ snap. */ + /* Protected by fqslock. */ unsigned long jiffies_force_qs; /* Time at which to invoke */ /* force_quiescent_state(). */ unsigned long n_force_qs; /* Number of calls to */ @@ -274,11 +310,15 @@ struct rcu_state { unsigned long jiffies_stall; /* Time at which to check */ /* for CPU stalls. */ #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ -#ifdef CONFIG_NO_HZ - long dynticks_completed; /* Value of completed @ snap. */ -#endif /* #ifdef CONFIG_NO_HZ */ }; +/* Return values for rcu_preempt_offline_tasks(). */ + +#define RCU_OFL_TASKS_NORM_GP 0x1 /* Tasks blocking normal */ + /* GP were moved to root. */ +#define RCU_OFL_TASKS_EXP_GP 0x2 /* Tasks blocking expedited */ + /* GP were moved to root. */ + #ifdef RCU_TREE_NONCORE /* @@ -298,10 +338,14 @@ DECLARE_PER_CPU(struct rcu_data, rcu_preempt_data); #else /* #ifdef RCU_TREE_NONCORE */ /* Forward declarations for rcutree_plugin.h */ -static inline void rcu_bootup_announce(void); +static void rcu_bootup_announce(void); long rcu_batches_completed(void); static void rcu_preempt_note_context_switch(int cpu); static int rcu_preempted_readers(struct rcu_node *rnp); +#ifdef CONFIG_HOTPLUG_CPU +static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, + unsigned long flags); +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ #ifdef CONFIG_RCU_CPU_STALL_DETECTOR static void rcu_print_task_stall(struct rcu_node *rnp); #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ @@ -315,6 +359,9 @@ static void rcu_preempt_offline_cpu(int cpu); static void rcu_preempt_check_callbacks(int cpu); static void rcu_preempt_process_callbacks(void); void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); +#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU) +static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp); +#endif /* #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU) */ static int rcu_preempt_pending(int cpu); static int rcu_preempt_needs_cpu(int cpu); static void __cpuinit rcu_preempt_init_percpu_data(int cpu); diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index ef2a58c2b9d5..37fbccdf41d5 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -24,16 +24,19 @@ * Paul E. McKenney <paulmck@linux.vnet.ibm.com> */ +#include <linux/delay.h> #ifdef CONFIG_TREE_PREEMPT_RCU struct rcu_state rcu_preempt_state = RCU_STATE_INITIALIZER(rcu_preempt_state); DEFINE_PER_CPU(struct rcu_data, rcu_preempt_data); +static int rcu_preempted_readers_exp(struct rcu_node *rnp); + /* * Tell them what RCU they are running. */ -static inline void rcu_bootup_announce(void) +static void __init rcu_bootup_announce(void) { printk(KERN_INFO "Experimental preemptable hierarchical RCU implementation.\n"); @@ -67,7 +70,7 @@ EXPORT_SYMBOL_GPL(rcu_batches_completed); static void rcu_preempt_qs(int cpu) { struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu); - rdp->passed_quiesc_completed = rdp->completed; + rdp->passed_quiesc_completed = rdp->gpnum - 1; barrier(); rdp->passed_quiesc = 1; } @@ -157,14 +160,58 @@ EXPORT_SYMBOL_GPL(__rcu_read_lock); */ static int rcu_preempted_readers(struct rcu_node *rnp) { - return !list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1]); + int phase = rnp->gpnum & 0x1; + + return !list_empty(&rnp->blocked_tasks[phase]) || + !list_empty(&rnp->blocked_tasks[phase + 2]); +} + +/* + * Record a quiescent state for all tasks that were previously queued + * on the specified rcu_node structure and that were blocking the current + * RCU grace period. The caller must hold the specified rnp->lock with + * irqs disabled, and this lock is released upon return, but irqs remain + * disabled. + */ +static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags) + __releases(rnp->lock) +{ + unsigned long mask; + struct rcu_node *rnp_p; + + if (rnp->qsmask != 0 || rcu_preempted_readers(rnp)) { + spin_unlock_irqrestore(&rnp->lock, flags); + return; /* Still need more quiescent states! */ + } + + rnp_p = rnp->parent; + if (rnp_p == NULL) { + /* + * Either there is only one rcu_node in the tree, + * or tasks were kicked up to root rcu_node due to + * CPUs going offline. + */ + rcu_report_qs_rsp(&rcu_preempt_state, flags); + return; + } + + /* Report up the rest of the hierarchy. */ + mask = rnp->grpmask; + spin_unlock(&rnp->lock); /* irqs remain disabled. */ + spin_lock(&rnp_p->lock); /* irqs already disabled. */ + rcu_report_qs_rnp(mask, &rcu_preempt_state, rnp_p, flags); } +/* + * Handle special cases during rcu_read_unlock(), such as needing to + * notify RCU core processing or task having blocked during the RCU + * read-side critical section. + */ static void rcu_read_unlock_special(struct task_struct *t) { int empty; + int empty_exp; unsigned long flags; - unsigned long mask; struct rcu_node *rnp; int special; @@ -207,36 +254,30 @@ static void rcu_read_unlock_special(struct task_struct *t) spin_unlock(&rnp->lock); /* irqs remain disabled. */ } empty = !rcu_preempted_readers(rnp); + empty_exp = !rcu_preempted_readers_exp(rnp); + smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */ list_del_init(&t->rcu_node_entry); t->rcu_blocked_node = NULL; /* * If this was the last task on the current list, and if * we aren't waiting on any CPUs, report the quiescent state. - * Note that both cpu_quiet_msk_finish() and cpu_quiet_msk() - * drop rnp->lock and restore irq. + * Note that rcu_report_unblock_qs_rnp() releases rnp->lock. */ - if (!empty && rnp->qsmask == 0 && - !rcu_preempted_readers(rnp)) { - struct rcu_node *rnp_p; - - if (rnp->parent == NULL) { - /* Only one rcu_node in the tree. */ - cpu_quiet_msk_finish(&rcu_preempt_state, flags); - return; - } - /* Report up the rest of the hierarchy. */ - mask = rnp->grpmask; + if (empty) spin_unlock_irqrestore(&rnp->lock, flags); - rnp_p = rnp->parent; - spin_lock_irqsave(&rnp_p->lock, flags); - WARN_ON_ONCE(rnp->qsmask); - cpu_quiet_msk(mask, &rcu_preempt_state, rnp_p, flags); - return; - } - spin_unlock(&rnp->lock); + else + rcu_report_unblock_qs_rnp(rnp, flags); + + /* + * If this was the last task on the expedited lists, + * then we need to report up the rcu_node hierarchy. + */ + if (!empty_exp && !rcu_preempted_readers_exp(rnp)) + rcu_report_exp_rnp(&rcu_preempt_state, rnp); + } else { + local_irq_restore(flags); } - local_irq_restore(flags); } /* @@ -303,6 +344,8 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) * rcu_node. The reason for not just moving them to the immediate * parent is to remove the need for rcu_read_unlock_special() to * make more than two attempts to acquire the target rcu_node's lock. + * Returns true if there were tasks blocking the current RCU grace + * period. * * Returns 1 if there was previously a task blocking the current grace * period on the specified rcu_node structure. @@ -316,7 +359,7 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp, int i; struct list_head *lp; struct list_head *lp_root; - int retval = rcu_preempted_readers(rnp); + int retval = 0; struct rcu_node *rnp_root = rcu_get_root(rsp); struct task_struct *tp; @@ -326,7 +369,9 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp, } WARN_ON_ONCE(rnp != rdp->mynode && (!list_empty(&rnp->blocked_tasks[0]) || - !list_empty(&rnp->blocked_tasks[1]))); + !list_empty(&rnp->blocked_tasks[1]) || + !list_empty(&rnp->blocked_tasks[2]) || + !list_empty(&rnp->blocked_tasks[3]))); /* * Move tasks up to root rcu_node. Rely on the fact that the @@ -334,7 +379,11 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp, * rcu_nodes in terms of gp_num value. This fact allows us to * move the blocked_tasks[] array directly, element by element. */ - for (i = 0; i < 2; i++) { + if (rcu_preempted_readers(rnp)) + retval |= RCU_OFL_TASKS_NORM_GP; + if (rcu_preempted_readers_exp(rnp)) + retval |= RCU_OFL_TASKS_EXP_GP; + for (i = 0; i < 4; i++) { lp = &rnp->blocked_tasks[i]; lp_root = &rnp_root->blocked_tasks[i]; while (!list_empty(lp)) { @@ -346,7 +395,6 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp, spin_unlock(&rnp_root->lock); /* irqs remain disabled */ } } - return retval; } @@ -398,14 +446,183 @@ void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) } EXPORT_SYMBOL_GPL(call_rcu); +/** + * synchronize_rcu - wait until a grace period has elapsed. + * + * Control will return to the caller some time after a full grace + * period has elapsed, in other words after all currently executing RCU + * read-side critical sections have completed. RCU read-side critical + * sections are delimited by rcu_read_lock() and rcu_read_unlock(), + * and may be nested. + */ +void synchronize_rcu(void) +{ + struct rcu_synchronize rcu; + + if (!rcu_scheduler_active) + return; + + init_completion(&rcu.completion); + /* Will wake me after RCU finished. */ + call_rcu(&rcu.head, wakeme_after_rcu); + /* Wait for it. */ + wait_for_completion(&rcu.completion); +} +EXPORT_SYMBOL_GPL(synchronize_rcu); + +static DECLARE_WAIT_QUEUE_HEAD(sync_rcu_preempt_exp_wq); +static long sync_rcu_preempt_exp_count; +static DEFINE_MUTEX(sync_rcu_preempt_exp_mutex); + /* - * Wait for an rcu-preempt grace period. We are supposed to expedite the - * grace period, but this is the crude slow compatability hack, so just - * invoke synchronize_rcu(). + * Return non-zero if there are any tasks in RCU read-side critical + * sections blocking the current preemptible-RCU expedited grace period. + * If there is no preemptible-RCU expedited grace period currently in + * progress, returns zero unconditionally. + */ +static int rcu_preempted_readers_exp(struct rcu_node *rnp) +{ + return !list_empty(&rnp->blocked_tasks[2]) || + !list_empty(&rnp->blocked_tasks[3]); +} + +/* + * return non-zero if there is no RCU expedited grace period in progress + * for the specified rcu_node structure, in other words, if all CPUs and + * tasks covered by the specified rcu_node structure have done their bit + * for the current expedited grace period. Works only for preemptible + * RCU -- other RCU implementation use other means. + * + * Caller must hold sync_rcu_preempt_exp_mutex. + */ +static int sync_rcu_preempt_exp_done(struct rcu_node *rnp) +{ + return !rcu_preempted_readers_exp(rnp) && + ACCESS_ONCE(rnp->expmask) == 0; +} + +/* + * Report the exit from RCU read-side critical section for the last task + * that queued itself during or before the current expedited preemptible-RCU + * grace period. This event is reported either to the rcu_node structure on + * which the task was queued or to one of that rcu_node structure's ancestors, + * recursively up the tree. (Calm down, calm down, we do the recursion + * iteratively!) + * + * Caller must hold sync_rcu_preempt_exp_mutex. + */ +static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp) +{ + unsigned long flags; + unsigned long mask; + + spin_lock_irqsave(&rnp->lock, flags); + for (;;) { + if (!sync_rcu_preempt_exp_done(rnp)) + break; + if (rnp->parent == NULL) { + wake_up(&sync_rcu_preempt_exp_wq); + break; + } + mask = rnp->grpmask; + spin_unlock(&rnp->lock); /* irqs remain disabled */ + rnp = rnp->parent; + spin_lock(&rnp->lock); /* irqs already disabled */ + rnp->expmask &= ~mask; + } + spin_unlock_irqrestore(&rnp->lock, flags); +} + +/* + * Snapshot the tasks blocking the newly started preemptible-RCU expedited + * grace period for the specified rcu_node structure. If there are no such + * tasks, report it up the rcu_node hierarchy. + * + * Caller must hold sync_rcu_preempt_exp_mutex and rsp->onofflock. + */ +static void +sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp) +{ + int must_wait; + + spin_lock(&rnp->lock); /* irqs already disabled */ + list_splice_init(&rnp->blocked_tasks[0], &rnp->blocked_tasks[2]); + list_splice_init(&rnp->blocked_tasks[1], &rnp->blocked_tasks[3]); + must_wait = rcu_preempted_readers_exp(rnp); + spin_unlock(&rnp->lock); /* irqs remain disabled */ + if (!must_wait) + rcu_report_exp_rnp(rsp, rnp); +} + +/* + * Wait for an rcu-preempt grace period, but expedite it. The basic idea + * is to invoke synchronize_sched_expedited() to push all the tasks to + * the ->blocked_tasks[] lists, move all entries from the first set of + * ->blocked_tasks[] lists to the second set, and finally wait for this + * second set to drain. */ void synchronize_rcu_expedited(void) { - synchronize_rcu(); + unsigned long flags; + struct rcu_node *rnp; + struct rcu_state *rsp = &rcu_preempt_state; + long snap; + int trycount = 0; + + smp_mb(); /* Caller's modifications seen first by other CPUs. */ + snap = ACCESS_ONCE(sync_rcu_preempt_exp_count) + 1; + smp_mb(); /* Above access cannot bleed into critical section. */ + + /* + * Acquire lock, falling back to synchronize_rcu() if too many + * lock-acquisition failures. Of course, if someone does the + * expedited grace period for us, just leave. + */ + while (!mutex_trylock(&sync_rcu_preempt_exp_mutex)) { + if (trycount++ < 10) + udelay(trycount * num_online_cpus()); + else { + synchronize_rcu(); + return; + } + if ((ACCESS_ONCE(sync_rcu_preempt_exp_count) - snap) > 0) + goto mb_ret; /* Others did our work for us. */ + } + if ((ACCESS_ONCE(sync_rcu_preempt_exp_count) - snap) > 0) + goto unlock_mb_ret; /* Others did our work for us. */ + + /* force all RCU readers onto blocked_tasks[]. */ + synchronize_sched_expedited(); + + spin_lock_irqsave(&rsp->onofflock, flags); + + /* Initialize ->expmask for all non-leaf rcu_node structures. */ + rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) { + spin_lock(&rnp->lock); /* irqs already disabled. */ + rnp->expmask = rnp->qsmaskinit; + spin_unlock(&rnp->lock); /* irqs remain disabled. */ + } + + /* Snapshot current state of ->blocked_tasks[] lists. */ + rcu_for_each_leaf_node(rsp, rnp) + sync_rcu_preempt_exp_init(rsp, rnp); + if (NUM_RCU_NODES > 1) + sync_rcu_preempt_exp_init(rsp, rcu_get_root(rsp)); + + spin_unlock_irqrestore(&rsp->onofflock, flags); + + /* Wait for snapshotted ->blocked_tasks[] lists to drain. */ + rnp = rcu_get_root(rsp); + wait_event(sync_rcu_preempt_exp_wq, + sync_rcu_preempt_exp_done(rnp)); + + /* Clean up and exit. */ + smp_mb(); /* ensure expedited GP seen before counter increment. */ + ACCESS_ONCE(sync_rcu_preempt_exp_count)++; +unlock_mb_ret: + mutex_unlock(&sync_rcu_preempt_exp_mutex); +mb_ret: + smp_mb(); /* ensure subsequent action seen after grace period. */ } EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); @@ -481,7 +698,7 @@ void exit_rcu(void) /* * Tell them what RCU they are running. */ -static inline void rcu_bootup_announce(void) +static void __init rcu_bootup_announce(void) { printk(KERN_INFO "Hierarchical RCU implementation.\n"); } @@ -512,6 +729,16 @@ static int rcu_preempted_readers(struct rcu_node *rnp) return 0; } +#ifdef CONFIG_HOTPLUG_CPU + +/* Because preemptible RCU does not exist, no quieting of tasks. */ +static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags) +{ + spin_unlock_irqrestore(&rnp->lock, flags); +} + +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ + #ifdef CONFIG_RCU_CPU_STALL_DETECTOR /* @@ -594,6 +821,20 @@ void synchronize_rcu_expedited(void) } EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); +#ifdef CONFIG_HOTPLUG_CPU + +/* + * Because preemptable RCU does not exist, there is never any need to + * report on tasks preempted in RCU read-side critical sections during + * expedited RCU grace periods. + */ +static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp) +{ + return; +} + +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ + /* * Because preemptable RCU does not exist, it never has any work to do. */ diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c index 4b31c779e62e..9d2c88423b31 100644 --- a/kernel/rcutree_trace.c +++ b/kernel/rcutree_trace.c @@ -155,12 +155,15 @@ static const struct file_operations rcudata_csv_fops = { static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp) { + long gpnum; int level = 0; + int phase; struct rcu_node *rnp; + gpnum = rsp->gpnum; seq_printf(m, "c=%ld g=%ld s=%d jfq=%ld j=%x " "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld\n", - rsp->completed, rsp->gpnum, rsp->signaled, + rsp->completed, gpnum, rsp->signaled, (long)(rsp->jiffies_force_qs - jiffies), (int)(jiffies & 0xffff), rsp->n_force_qs, rsp->n_force_qs_ngp, @@ -171,8 +174,13 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp) seq_puts(m, "\n"); level = rnp->level; } - seq_printf(m, "%lx/%lx %d:%d ^%d ", + phase = gpnum & 0x1; + seq_printf(m, "%lx/%lx %c%c>%c%c %d:%d ^%d ", rnp->qsmask, rnp->qsmaskinit, + "T."[list_empty(&rnp->blocked_tasks[phase])], + "E."[list_empty(&rnp->blocked_tasks[phase + 2])], + "T."[list_empty(&rnp->blocked_tasks[!phase])], + "E."[list_empty(&rnp->blocked_tasks[!phase + 2])], rnp->grplo, rnp->grphi, rnp->grpnum); } seq_puts(m, "\n"); diff --git a/kernel/sched.c b/kernel/sched.c index 3c11ae0a948d..e7f2cfa6a257 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -535,14 +535,12 @@ struct rq { #define CPU_LOAD_IDX_MAX 5 unsigned long cpu_load[CPU_LOAD_IDX_MAX]; #ifdef CONFIG_NO_HZ - unsigned long last_tick_seen; unsigned char in_nohz_recently; #endif /* capture load from *all* tasks on this cpu: */ struct load_weight load; unsigned long nr_load_updates; u64 nr_switches; - u64 nr_migrations_in; struct cfs_rq cfs; struct rt_rq rt; @@ -591,6 +589,8 @@ struct rq { u64 rt_avg; u64 age_stamp; + u64 idle_stamp; + u64 avg_idle; #endif /* calc_load related fields */ @@ -772,7 +772,7 @@ sched_feat_write(struct file *filp, const char __user *ubuf, if (!sched_feat_names[i]) return -EINVAL; - filp->f_pos += cnt; + *ppos += cnt; return cnt; } @@ -2017,6 +2017,7 @@ void kthread_bind(struct task_struct *p, unsigned int cpu) } spin_lock_irqsave(&rq->lock, flags); + update_rq_clock(rq); set_task_cpu(p, cpu); p->cpus_allowed = cpumask_of_cpu(cpu); p->rt.nr_cpus_allowed = 1; @@ -2078,7 +2079,6 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) #endif if (old_cpu != new_cpu) { p->se.nr_migrations++; - new_rq->nr_migrations_in++; #ifdef CONFIG_SCHEDSTATS if (task_hot(p, old_rq->clock, NULL)) schedstat_inc(p, se.nr_forced2_migrations); @@ -2115,6 +2115,7 @@ migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req) * it is sufficient to simply update the task's cpu field. */ if (!p->se.on_rq && !task_running(rq, p)) { + update_rq_clock(rq); set_task_cpu(p, dest_cpu); return 0; } @@ -2376,14 +2377,15 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, task_rq_unlock(rq, &flags); cpu = p->sched_class->select_task_rq(p, SD_BALANCE_WAKE, wake_flags); - if (cpu != orig_cpu) + if (cpu != orig_cpu) { + local_irq_save(flags); + rq = cpu_rq(cpu); + update_rq_clock(rq); set_task_cpu(p, cpu); - + local_irq_restore(flags); + } rq = task_rq_lock(p, &flags); - if (rq != orig_rq) - update_rq_clock(rq); - WARN_ON(p->state != TASK_WAKING); cpu = task_cpu(p); @@ -2440,6 +2442,17 @@ out_running: #ifdef CONFIG_SMP if (p->sched_class->task_wake_up) p->sched_class->task_wake_up(rq, p); + + if (unlikely(rq->idle_stamp)) { + u64 delta = rq->clock - rq->idle_stamp; + u64 max = 2*sysctl_sched_migration_cost; + + if (delta > max) + rq->avg_idle = max; + else + update_avg(&rq->avg_idle, delta); + rq->idle_stamp = 0; + } #endif out: task_rq_unlock(rq, &flags); @@ -2545,6 +2558,7 @@ static void __sched_fork(struct task_struct *p) void sched_fork(struct task_struct *p, int clone_flags) { int cpu = get_cpu(); + unsigned long flags; __sched_fork(p); @@ -2581,7 +2595,10 @@ void sched_fork(struct task_struct *p, int clone_flags) #ifdef CONFIG_SMP cpu = p->sched_class->select_task_rq(p, SD_BALANCE_FORK, 0); #endif + local_irq_save(flags); + update_rq_clock(cpu_rq(cpu)); set_task_cpu(p, cpu); + local_irq_restore(flags); #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) if (likely(sched_info_on())) @@ -2848,14 +2865,14 @@ context_switch(struct rq *rq, struct task_struct *prev, */ arch_start_context_switch(prev); - if (unlikely(!mm)) { + if (likely(!mm)) { next->active_mm = oldmm; atomic_inc(&oldmm->mm_count); enter_lazy_tlb(oldmm, next); } else switch_mm(oldmm, mm, next); - if (unlikely(!prev->mm)) { + if (likely(!prev->mm)) { prev->active_mm = NULL; rq->prev_mm = oldmm; } @@ -3018,15 +3035,6 @@ static void calc_load_account_active(struct rq *this_rq) } /* - * Externally visible per-cpu scheduler statistics: - * cpu_nr_migrations(cpu) - number of migrations into that cpu - */ -u64 cpu_nr_migrations(int cpu) -{ - return cpu_rq(cpu)->nr_migrations_in; -} - -/* * Update rq->cpu_load[] statistics. This function is usually called every * scheduler tick (TICK_NSEC). */ @@ -4126,7 +4134,7 @@ static int load_balance(int this_cpu, struct rq *this_rq, unsigned long flags; struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask); - cpumask_setall(cpus); + cpumask_copy(cpus, cpu_online_mask); /* * When power savings policy is enabled for the parent domain, idle @@ -4289,7 +4297,7 @@ load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd) int all_pinned = 0; struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask); - cpumask_setall(cpus); + cpumask_copy(cpus, cpu_online_mask); /* * When power savings policy is enabled for the parent domain, idle @@ -4429,6 +4437,11 @@ static void idle_balance(int this_cpu, struct rq *this_rq) int pulled_task = 0; unsigned long next_balance = jiffies + HZ; + this_rq->idle_stamp = this_rq->clock; + + if (this_rq->avg_idle < sysctl_sched_migration_cost) + return; + for_each_domain(this_cpu, sd) { unsigned long interval; @@ -4443,8 +4456,10 @@ static void idle_balance(int this_cpu, struct rq *this_rq) interval = msecs_to_jiffies(sd->balance_interval); if (time_after(next_balance, sd->last_balance + interval)) next_balance = sd->last_balance + interval; - if (pulled_task) + if (pulled_task) { + this_rq->idle_stamp = 0; break; + } } if (pulled_task || time_after(jiffies, this_rq->next_balance)) { /* @@ -5046,8 +5061,13 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime, p->gtime = cputime_add(p->gtime, cputime); /* Add guest time to cpustat. */ - cpustat->user = cputime64_add(cpustat->user, tmp); - cpustat->guest = cputime64_add(cpustat->guest, tmp); + if (TASK_NICE(p) > 0) { + cpustat->nice = cputime64_add(cpustat->nice, tmp); + cpustat->guest_nice = cputime64_add(cpustat->guest_nice, tmp); + } else { + cpustat->user = cputime64_add(cpustat->user, tmp); + cpustat->guest = cputime64_add(cpustat->guest, tmp); + } } /* @@ -5162,60 +5182,86 @@ void account_idle_ticks(unsigned long ticks) * Use precise platform statistics if available: */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING -cputime_t task_utime(struct task_struct *p) +void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) { - return p->utime; + *ut = p->utime; + *st = p->stime; } -cputime_t task_stime(struct task_struct *p) +void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) { - return p->stime; + struct task_cputime cputime; + + thread_group_cputime(p, &cputime); + + *ut = cputime.utime; + *st = cputime.stime; } #else -cputime_t task_utime(struct task_struct *p) + +#ifndef nsecs_to_cputime +# define nsecs_to_cputime(__nsecs) nsecs_to_jiffies(__nsecs) +#endif + +void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) { - clock_t utime = cputime_to_clock_t(p->utime), - total = utime + cputime_to_clock_t(p->stime); - u64 temp; + cputime_t rtime, utime = p->utime, total = cputime_add(utime, p->stime); /* * Use CFS's precise accounting: */ - temp = (u64)nsec_to_clock_t(p->se.sum_exec_runtime); + rtime = nsecs_to_cputime(p->se.sum_exec_runtime); if (total) { - temp *= utime; + u64 temp; + + temp = (u64)(rtime * utime); do_div(temp, total); - } - utime = (clock_t)temp; + utime = (cputime_t)temp; + } else + utime = rtime; + + /* + * Compare with previous values, to keep monotonicity: + */ + p->prev_utime = max(p->prev_utime, utime); + p->prev_stime = max(p->prev_stime, cputime_sub(rtime, p->prev_utime)); - p->prev_utime = max(p->prev_utime, clock_t_to_cputime(utime)); - return p->prev_utime; + *ut = p->prev_utime; + *st = p->prev_stime; } -cputime_t task_stime(struct task_struct *p) +/* + * Must be called with siglock held. + */ +void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) { - clock_t stime; + struct signal_struct *sig = p->signal; + struct task_cputime cputime; + cputime_t rtime, utime, total; - /* - * Use CFS's precise accounting. (we subtract utime from - * the total, to make sure the total observed by userspace - * grows monotonically - apps rely on that): - */ - stime = nsec_to_clock_t(p->se.sum_exec_runtime) - - cputime_to_clock_t(task_utime(p)); + thread_group_cputime(p, &cputime); - if (stime >= 0) - p->prev_stime = max(p->prev_stime, clock_t_to_cputime(stime)); + total = cputime_add(cputime.utime, cputime.stime); + rtime = nsecs_to_cputime(cputime.sum_exec_runtime); - return p->prev_stime; -} -#endif + if (total) { + u64 temp; -inline cputime_t task_gtime(struct task_struct *p) -{ - return p->gtime; + temp = (u64)(rtime * cputime.utime); + do_div(temp, total); + utime = (cputime_t)temp; + } else + utime = rtime; + + sig->prev_utime = max(sig->prev_utime, utime); + sig->prev_stime = max(sig->prev_stime, + cputime_sub(rtime, sig->prev_utime)); + + *ut = sig->prev_utime; + *st = sig->prev_stime; } +#endif /* * This function gets called by the timer code, with HZ frequency. @@ -5481,7 +5527,7 @@ need_resched_nonpreemptible: } EXPORT_SYMBOL(schedule); -#ifdef CONFIG_SMP +#ifdef CONFIG_MUTEX_SPIN_ON_OWNER /* * Look out! "owner" is an entirely speculative pointer * access and not reliable. @@ -6175,22 +6221,14 @@ __setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio) BUG_ON(p->se.on_rq); p->policy = policy; - switch (p->policy) { - case SCHED_NORMAL: - case SCHED_BATCH: - case SCHED_IDLE: - p->sched_class = &fair_sched_class; - break; - case SCHED_FIFO: - case SCHED_RR: - p->sched_class = &rt_sched_class; - break; - } - p->rt_priority = prio; p->normal_prio = normal_prio(p); /* we are holding p->pi_lock already */ p->prio = rt_mutex_getprio(p); + if (rt_prio(p->prio)) + p->sched_class = &rt_sched_class; + else + p->sched_class = &fair_sched_class; set_load_weight(p); } @@ -6935,7 +6973,7 @@ void show_state_filter(unsigned long state_filter) /* * Only show locks if all tasks are dumped: */ - if (state_filter == -1) + if (!state_filter) debug_show_all_locks(); } @@ -7406,17 +7444,16 @@ static struct ctl_table sd_ctl_dir[] = { .procname = "sched_domain", .mode = 0555, }, - {0, }, + {} }; static struct ctl_table sd_ctl_root[] = { { - .ctl_name = CTL_KERN, .procname = "kernel", .mode = 0555, .child = sd_ctl_dir, }, - {0, }, + {} }; static struct ctl_table *sd_alloc_ctl_entry(int n) @@ -7740,6 +7777,16 @@ early_initcall(migration_init); #ifdef CONFIG_SCHED_DEBUG +static __read_mostly int sched_domain_debug_enabled; + +static int __init sched_domain_debug_setup(char *str) +{ + sched_domain_debug_enabled = 1; + + return 0; +} +early_param("sched_debug", sched_domain_debug_setup); + static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, struct cpumask *groupmask) { @@ -7826,6 +7873,9 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu) cpumask_var_t groupmask; int level = 0; + if (!sched_domain_debug_enabled) + return; + if (!sd) { printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu); return; @@ -7905,6 +7955,8 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) static void free_rootdomain(struct root_domain *rd) { + synchronize_sched(); + cpupri_cleanup(&rd->cpupri); free_cpumask_var(rd->rto_mask); @@ -8045,6 +8097,7 @@ static cpumask_var_t cpu_isolated_map; /* Setup the mask of cpus configured for isolated domains */ static int __init isolated_cpu_setup(char *str) { + alloc_bootmem_cpumask_var(&cpu_isolated_map); cpulist_parse(str, cpu_isolated_map); return 1; } @@ -8881,7 +8934,7 @@ static int build_sched_domains(const struct cpumask *cpu_map) return __build_sched_domains(cpu_map, NULL); } -static struct cpumask *doms_cur; /* current sched domains */ +static cpumask_var_t *doms_cur; /* current sched domains */ static int ndoms_cur; /* number of sched domains in 'doms_cur' */ static struct sched_domain_attr *dattr_cur; /* attribues of custom domains in 'doms_cur' */ @@ -8903,6 +8956,31 @@ int __attribute__((weak)) arch_update_cpu_topology(void) return 0; } +cpumask_var_t *alloc_sched_domains(unsigned int ndoms) +{ + int i; + cpumask_var_t *doms; + + doms = kmalloc(sizeof(*doms) * ndoms, GFP_KERNEL); + if (!doms) + return NULL; + for (i = 0; i < ndoms; i++) { + if (!alloc_cpumask_var(&doms[i], GFP_KERNEL)) { + free_sched_domains(doms, i); + return NULL; + } + } + return doms; +} + +void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms) +{ + unsigned int i; + for (i = 0; i < ndoms; i++) + free_cpumask_var(doms[i]); + kfree(doms); +} + /* * Set up scheduler domains and groups. Callers must hold the hotplug lock. * For now this just excludes isolated cpus, but could be used to @@ -8914,12 +8992,12 @@ static int arch_init_sched_domains(const struct cpumask *cpu_map) arch_update_cpu_topology(); ndoms_cur = 1; - doms_cur = kmalloc(cpumask_size(), GFP_KERNEL); + doms_cur = alloc_sched_domains(ndoms_cur); if (!doms_cur) - doms_cur = fallback_doms; - cpumask_andnot(doms_cur, cpu_map, cpu_isolated_map); + doms_cur = &fallback_doms; + cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map); dattr_cur = NULL; - err = build_sched_domains(doms_cur); + err = build_sched_domains(doms_cur[0]); register_sched_domain_sysctl(); return err; @@ -8969,19 +9047,19 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur, * doms_new[] to the current sched domain partitioning, doms_cur[]. * It destroys each deleted domain and builds each new domain. * - * 'doms_new' is an array of cpumask's of length 'ndoms_new'. + * 'doms_new' is an array of cpumask_var_t's of length 'ndoms_new'. * The masks don't intersect (don't overlap.) We should setup one * sched domain for each mask. CPUs not in any of the cpumasks will * not be load balanced. If the same cpumask appears both in the * current 'doms_cur' domains and in the new 'doms_new', we can leave * it as it is. * - * The passed in 'doms_new' should be kmalloc'd. This routine takes - * ownership of it and will kfree it when done with it. If the caller - * failed the kmalloc call, then it can pass in doms_new == NULL && - * ndoms_new == 1, and partition_sched_domains() will fallback to - * the single partition 'fallback_doms', it also forces the domains - * to be rebuilt. + * The passed in 'doms_new' should be allocated using + * alloc_sched_domains. This routine takes ownership of it and will + * free_sched_domains it when done with it. If the caller failed the + * alloc call, then it can pass in doms_new == NULL && ndoms_new == 1, + * and partition_sched_domains() will fallback to the single partition + * 'fallback_doms', it also forces the domains to be rebuilt. * * If doms_new == NULL it will be replaced with cpu_online_mask. * ndoms_new == 0 is a special case for destroying existing domains, @@ -8989,8 +9067,7 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur, * * Call with hotplug lock held */ -/* FIXME: Change to struct cpumask *doms_new[] */ -void partition_sched_domains(int ndoms_new, struct cpumask *doms_new, +void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], struct sched_domain_attr *dattr_new) { int i, j, n; @@ -9009,40 +9086,40 @@ void partition_sched_domains(int ndoms_new, struct cpumask *doms_new, /* Destroy deleted domains */ for (i = 0; i < ndoms_cur; i++) { for (j = 0; j < n && !new_topology; j++) { - if (cpumask_equal(&doms_cur[i], &doms_new[j]) + if (cpumask_equal(doms_cur[i], doms_new[j]) && dattrs_equal(dattr_cur, i, dattr_new, j)) goto match1; } /* no match - a current sched domain not in new doms_new[] */ - detach_destroy_domains(doms_cur + i); + detach_destroy_domains(doms_cur[i]); match1: ; } if (doms_new == NULL) { ndoms_cur = 0; - doms_new = fallback_doms; - cpumask_andnot(&doms_new[0], cpu_online_mask, cpu_isolated_map); + doms_new = &fallback_doms; + cpumask_andnot(doms_new[0], cpu_online_mask, cpu_isolated_map); WARN_ON_ONCE(dattr_new); } /* Build new domains */ for (i = 0; i < ndoms_new; i++) { for (j = 0; j < ndoms_cur && !new_topology; j++) { - if (cpumask_equal(&doms_new[i], &doms_cur[j]) + if (cpumask_equal(doms_new[i], doms_cur[j]) && dattrs_equal(dattr_new, i, dattr_cur, j)) goto match2; } /* no match - add a new doms_new */ - __build_sched_domains(doms_new + i, + __build_sched_domains(doms_new[i], dattr_new ? dattr_new + i : NULL); match2: ; } /* Remember the new sched domains */ - if (doms_cur != fallback_doms) - kfree(doms_cur); + if (doms_cur != &fallback_doms) + free_sched_domains(doms_cur, ndoms_cur); kfree(dattr_cur); /* kfree(NULL) is safe */ doms_cur = doms_new; dattr_cur = dattr_new; @@ -9364,10 +9441,6 @@ void __init sched_init(void) #ifdef CONFIG_CPUMASK_OFFSTACK alloc_size += num_possible_cpus() * cpumask_size(); #endif - /* - * As sched_init() is called before page_alloc is setup, - * we use alloc_bootmem(). - */ if (alloc_size) { ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT); @@ -9522,6 +9595,8 @@ void __init sched_init(void) rq->cpu = i; rq->online = 0; rq->migration_thread = NULL; + rq->idle_stamp = 0; + rq->avg_idle = 2*sysctl_sched_migration_cost; INIT_LIST_HEAD(&rq->migration_queue); rq_attach_root(rq, &def_root_domain); #endif @@ -9571,7 +9646,9 @@ void __init sched_init(void) zalloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT); alloc_cpumask_var(&nohz.ilb_grp_nohz_mask, GFP_NOWAIT); #endif - zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT); + /* May be allocated at isolcpus cmdline parse time */ + if (cpu_isolated_map == NULL) + zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT); #endif /* SMP */ perf_event_init(); @@ -10901,6 +10978,7 @@ void synchronize_sched_expedited(void) spin_unlock_irqrestore(&rq->lock, flags); } rcu_expedited_state = RCU_EXPEDITED_STATE_IDLE; + synchronize_sched_expedited_count++; mutex_unlock(&rcu_sched_expedited_mutex); put_online_cpus(); if (need_full_sync) diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index efb84409bc43..6988cf08f705 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -285,12 +285,16 @@ static void print_cpu(struct seq_file *m, int cpu) #ifdef CONFIG_SCHEDSTATS #define P(n) SEQ_printf(m, " .%-30s: %d\n", #n, rq->n); +#define P64(n) SEQ_printf(m, " .%-30s: %Ld\n", #n, rq->n); P(yld_count); P(sched_switch); P(sched_count); P(sched_goidle); +#ifdef CONFIG_SMP + P64(avg_idle); +#endif P(ttwu_count); P(ttwu_local); diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 37087a7fac22..f61837ad336d 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1345,6 +1345,37 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu) } /* + * Try and locate an idle CPU in the sched_domain. + */ +static int +select_idle_sibling(struct task_struct *p, struct sched_domain *sd, int target) +{ + int cpu = smp_processor_id(); + int prev_cpu = task_cpu(p); + int i; + + /* + * If this domain spans both cpu and prev_cpu (see the SD_WAKE_AFFINE + * test in select_task_rq_fair) and the prev_cpu is idle then that's + * always a better target than the current cpu. + */ + if (target == cpu && !cpu_rq(prev_cpu)->cfs.nr_running) + return prev_cpu; + + /* + * Otherwise, iterate the domain and find an elegible idle cpu. + */ + for_each_cpu_and(i, sched_domain_span(sd), &p->cpus_allowed) { + if (!cpu_rq(i)->cfs.nr_running) { + target = i; + break; + } + } + + return target; +} + +/* * sched_balance_self: balance the current task (running on cpu) in domains * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and * SD_BALANCE_EXEC. @@ -1398,11 +1429,35 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag want_sd = 0; } - if (want_affine && (tmp->flags & SD_WAKE_AFFINE) && - cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) { + /* + * While iterating the domains looking for a spanning + * WAKE_AFFINE domain, adjust the affine target to any idle cpu + * in cache sharing domains along the way. + */ + if (want_affine) { + int target = -1; - affine_sd = tmp; - want_affine = 0; + /* + * If both cpu and prev_cpu are part of this domain, + * cpu is a valid SD_WAKE_AFFINE target. + */ + if (cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) + target = cpu; + + /* + * If there's an idle sibling in this domain, make that + * the wake_affine target instead of the current cpu. + */ + if (tmp->flags & SD_PREFER_SIBLING) + target = select_idle_sibling(p, tmp, target); + + if (target >= 0) { + if (tmp->flags & SD_WAKE_AFFINE) { + affine_sd = tmp; + want_affine = 0; + } + cpu = target; + } } if (!want_sd && !want_affine) @@ -1679,7 +1734,7 @@ static struct task_struct *pick_next_task_fair(struct rq *rq) struct cfs_rq *cfs_rq = &rq->cfs; struct sched_entity *se; - if (unlikely(!cfs_rq->nr_running)) + if (!cfs_rq->nr_running) return NULL; do { diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index a4d790cddb19..5c5fef378415 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -1153,29 +1153,12 @@ static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu) static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask); -static inline int pick_optimal_cpu(int this_cpu, - const struct cpumask *mask) -{ - int first; - - /* "this_cpu" is cheaper to preempt than a remote processor */ - if ((this_cpu != -1) && cpumask_test_cpu(this_cpu, mask)) - return this_cpu; - - first = cpumask_first(mask); - if (first < nr_cpu_ids) - return first; - - return -1; -} - static int find_lowest_rq(struct task_struct *task) { struct sched_domain *sd; struct cpumask *lowest_mask = __get_cpu_var(local_cpu_mask); int this_cpu = smp_processor_id(); int cpu = task_cpu(task); - cpumask_var_t domain_mask; if (task->rt.nr_cpus_allowed == 1) return -1; /* No other targets possible */ @@ -1198,28 +1181,26 @@ static int find_lowest_rq(struct task_struct *task) * Otherwise, we consult the sched_domains span maps to figure * out which cpu is logically closest to our hot cache data. */ - if (this_cpu == cpu) - this_cpu = -1; /* Skip this_cpu opt if the same */ - - if (alloc_cpumask_var(&domain_mask, GFP_ATOMIC)) { - for_each_domain(cpu, sd) { - if (sd->flags & SD_WAKE_AFFINE) { - int best_cpu; + if (!cpumask_test_cpu(this_cpu, lowest_mask)) + this_cpu = -1; /* Skip this_cpu opt if not among lowest */ - cpumask_and(domain_mask, - sched_domain_span(sd), - lowest_mask); + for_each_domain(cpu, sd) { + if (sd->flags & SD_WAKE_AFFINE) { + int best_cpu; - best_cpu = pick_optimal_cpu(this_cpu, - domain_mask); - - if (best_cpu != -1) { - free_cpumask_var(domain_mask); - return best_cpu; - } - } + /* + * "this_cpu" is cheaper to preempt than a + * remote processor. + */ + if (this_cpu != -1 && + cpumask_test_cpu(this_cpu, sched_domain_span(sd))) + return this_cpu; + + best_cpu = cpumask_first_and(lowest_mask, + sched_domain_span(sd)); + if (best_cpu < nr_cpu_ids) + return best_cpu; } - free_cpumask_var(domain_mask); } /* @@ -1227,7 +1208,13 @@ static int find_lowest_rq(struct task_struct *task) * just give the caller *something* to work with from the compatible * locations. */ - return pick_optimal_cpu(this_cpu, lowest_mask); + if (this_cpu != -1) + return this_cpu; + + cpu = cpumask_any(lowest_mask); + if (cpu < nr_cpu_ids) + return cpu; + return -1; } /* Will lock the rq it finds */ diff --git a/kernel/signal.c b/kernel/signal.c index 6705320784fd..6b982f2cf524 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -22,12 +22,14 @@ #include <linux/ptrace.h> #include <linux/signal.h> #include <linux/signalfd.h> +#include <linux/ratelimit.h> #include <linux/tracehook.h> #include <linux/capability.h> #include <linux/freezer.h> #include <linux/pid_namespace.h> #include <linux/nsproxy.h> -#include <trace/events/sched.h> +#define CREATE_TRACE_POINTS +#include <trace/events/signal.h> #include <asm/param.h> #include <asm/uaccess.h> @@ -41,6 +43,8 @@ static struct kmem_cache *sigqueue_cachep; +int print_fatal_signals __read_mostly; + static void __user *sig_handler(struct task_struct *t, int sig) { return t->sighand->action[sig - 1].sa.sa_handler; @@ -159,7 +163,7 @@ int next_signal(struct sigpending *pending, sigset_t *mask) { unsigned long i, *s, *m, x; int sig = 0; - + s = pending->signal.sig; m = mask->sig; switch (_NSIG_WORDS) { @@ -184,17 +188,31 @@ int next_signal(struct sigpending *pending, sigset_t *mask) sig = ffz(~x) + 1; break; } - + return sig; } +static inline void print_dropped_signal(int sig) +{ + static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10); + + if (!print_fatal_signals) + return; + + if (!__ratelimit(&ratelimit_state)) + return; + + printk(KERN_INFO "%s/%d: reached RLIMIT_SIGPENDING, dropped signal %d\n", + current->comm, current->pid, sig); +} + /* * allocate a new signal queue record * - this may be called without locks if and only if t == current, otherwise an * appopriate lock must be held to stop the target task from exiting */ -static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags, - int override_rlimit) +static struct sigqueue * +__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimit) { struct sigqueue *q = NULL; struct user_struct *user; @@ -207,10 +225,15 @@ static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags, */ user = get_uid(__task_cred(t)->user); atomic_inc(&user->sigpending); + if (override_rlimit || atomic_read(&user->sigpending) <= - t->signal->rlim[RLIMIT_SIGPENDING].rlim_cur) + t->signal->rlim[RLIMIT_SIGPENDING].rlim_cur) { q = kmem_cache_alloc(sigqueue_cachep, flags); + } else { + print_dropped_signal(sig); + } + if (unlikely(q == NULL)) { atomic_dec(&user->sigpending); free_uid(user); @@ -834,7 +857,7 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t, struct sigqueue *q; int override_rlimit; - trace_sched_signal_send(sig, t); + trace_signal_generate(sig, info, t); assert_spin_locked(&t->sighand->siglock); @@ -869,7 +892,7 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t, else override_rlimit = 0; - q = __sigqueue_alloc(t, GFP_ATOMIC | __GFP_NOTRACK_FALSE_POSITIVE, + q = __sigqueue_alloc(sig, t, GFP_ATOMIC | __GFP_NOTRACK_FALSE_POSITIVE, override_rlimit); if (q) { list_add_tail(&q->list, &pending->list); @@ -896,12 +919,21 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t, break; } } else if (!is_si_special(info)) { - if (sig >= SIGRTMIN && info->si_code != SI_USER) - /* - * Queue overflow, abort. We may abort if the signal was rt - * and sent by user using something other than kill(). - */ + if (sig >= SIGRTMIN && info->si_code != SI_USER) { + /* + * Queue overflow, abort. We may abort if the + * signal was rt and sent by user using something + * other than kill(). + */ + trace_signal_overflow_fail(sig, group, info); return -EAGAIN; + } else { + /* + * This is a silent loss of information. We still + * send the signal, but the *info bits are lost. + */ + trace_signal_lose_info(sig, group, info); + } } out_set: @@ -925,8 +957,6 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t, return __send_signal(sig, info, t, group, from_ancestor_ns); } -int print_fatal_signals; - static void print_fatal_signal(struct pt_regs *regs, int signr) { printk("%s/%d: potentially unexpected fatal signal %d.\n", @@ -1293,19 +1323,19 @@ EXPORT_SYMBOL(kill_pid); * These functions support sending signals using preallocated sigqueue * structures. This is needed "because realtime applications cannot * afford to lose notifications of asynchronous events, like timer - * expirations or I/O completions". In the case of Posix Timers + * expirations or I/O completions". In the case of Posix Timers * we allocate the sigqueue structure from the timer_create. If this * allocation fails we are able to report the failure to the application * with an EAGAIN error. */ - struct sigqueue *sigqueue_alloc(void) { - struct sigqueue *q; + struct sigqueue *q = __sigqueue_alloc(-1, current, GFP_KERNEL, 0); - if ((q = __sigqueue_alloc(current, GFP_KERNEL, 0))) + if (q) q->flags |= SIGQUEUE_PREALLOC; - return(q); + + return q; } void sigqueue_free(struct sigqueue *q) @@ -1839,6 +1869,9 @@ relock: ka = &sighand->action[signr-1]; } + /* Trace actually delivered signals. */ + trace_signal_deliver(signr, info, ka); + if (ka->sa.sa_handler == SIG_IGN) /* Do nothing. */ continue; if (ka->sa.sa_handler != SIG_DFL) { diff --git a/kernel/slow-work-debugfs.c b/kernel/slow-work-debugfs.c new file mode 100644 index 000000000000..e45c43645298 --- /dev/null +++ b/kernel/slow-work-debugfs.c @@ -0,0 +1,227 @@ +/* Slow work debugging + * + * Copyright (C) 2009 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/slow-work.h> +#include <linux/fs.h> +#include <linux/time.h> +#include <linux/seq_file.h> +#include "slow-work.h" + +#define ITERATOR_SHIFT (BITS_PER_LONG - 4) +#define ITERATOR_SELECTOR (0xfUL << ITERATOR_SHIFT) +#define ITERATOR_COUNTER (~ITERATOR_SELECTOR) + +void slow_work_new_thread_desc(struct slow_work *work, struct seq_file *m) +{ + seq_puts(m, "Slow-work: New thread"); +} + +/* + * Render the time mark field on a work item into a 5-char time with units plus + * a space + */ +static void slow_work_print_mark(struct seq_file *m, struct slow_work *work) +{ + struct timespec now, diff; + + now = CURRENT_TIME; + diff = timespec_sub(now, work->mark); + + if (diff.tv_sec < 0) + seq_puts(m, " -ve "); + else if (diff.tv_sec == 0 && diff.tv_nsec < 1000) + seq_printf(m, "%3luns ", diff.tv_nsec); + else if (diff.tv_sec == 0 && diff.tv_nsec < 1000000) + seq_printf(m, "%3luus ", diff.tv_nsec / 1000); + else if (diff.tv_sec == 0 && diff.tv_nsec < 1000000000) + seq_printf(m, "%3lums ", diff.tv_nsec / 1000000); + else if (diff.tv_sec <= 1) + seq_puts(m, " 1s "); + else if (diff.tv_sec < 60) + seq_printf(m, "%4lus ", diff.tv_sec); + else if (diff.tv_sec < 60 * 60) + seq_printf(m, "%4lum ", diff.tv_sec / 60); + else if (diff.tv_sec < 60 * 60 * 24) + seq_printf(m, "%4luh ", diff.tv_sec / 3600); + else + seq_puts(m, "exces "); +} + +/* + * Describe a slow work item for debugfs + */ +static int slow_work_runqueue_show(struct seq_file *m, void *v) +{ + struct slow_work *work; + struct list_head *p = v; + unsigned long id; + + switch ((unsigned long) v) { + case 1: + seq_puts(m, "THR PID ITEM ADDR FL MARK DESC\n"); + return 0; + case 2: + seq_puts(m, "=== ===== ================ == ===== ==========\n"); + return 0; + + case 3 ... 3 + SLOW_WORK_THREAD_LIMIT - 1: + id = (unsigned long) v - 3; + + read_lock(&slow_work_execs_lock); + work = slow_work_execs[id]; + if (work) { + smp_read_barrier_depends(); + + seq_printf(m, "%3lu %5d %16p %2lx ", + id, slow_work_pids[id], work, work->flags); + slow_work_print_mark(m, work); + + if (work->ops->desc) + work->ops->desc(work, m); + seq_putc(m, '\n'); + } + read_unlock(&slow_work_execs_lock); + return 0; + + default: + work = list_entry(p, struct slow_work, link); + seq_printf(m, "%3s - %16p %2lx ", + work->flags & SLOW_WORK_VERY_SLOW ? "vsq" : "sq", + work, work->flags); + slow_work_print_mark(m, work); + + if (work->ops->desc) + work->ops->desc(work, m); + seq_putc(m, '\n'); + return 0; + } +} + +/* + * map the iterator to a work item + */ +static void *slow_work_runqueue_index(struct seq_file *m, loff_t *_pos) +{ + struct list_head *p; + unsigned long count, id; + + switch (*_pos >> ITERATOR_SHIFT) { + case 0x0: + if (*_pos == 0) + *_pos = 1; + if (*_pos < 3) + return (void *)(unsigned long) *_pos; + if (*_pos < 3 + SLOW_WORK_THREAD_LIMIT) + for (id = *_pos - 3; + id < SLOW_WORK_THREAD_LIMIT; + id++, (*_pos)++) + if (slow_work_execs[id]) + return (void *)(unsigned long) *_pos; + *_pos = 0x1UL << ITERATOR_SHIFT; + + case 0x1: + count = *_pos & ITERATOR_COUNTER; + list_for_each(p, &slow_work_queue) { + if (count == 0) + return p; + count--; + } + *_pos = 0x2UL << ITERATOR_SHIFT; + + case 0x2: + count = *_pos & ITERATOR_COUNTER; + list_for_each(p, &vslow_work_queue) { + if (count == 0) + return p; + count--; + } + *_pos = 0x3UL << ITERATOR_SHIFT; + + default: + return NULL; + } +} + +/* + * set up the iterator to start reading from the first line + */ +static void *slow_work_runqueue_start(struct seq_file *m, loff_t *_pos) +{ + spin_lock_irq(&slow_work_queue_lock); + return slow_work_runqueue_index(m, _pos); +} + +/* + * move to the next line + */ +static void *slow_work_runqueue_next(struct seq_file *m, void *v, loff_t *_pos) +{ + struct list_head *p = v; + unsigned long selector = *_pos >> ITERATOR_SHIFT; + + (*_pos)++; + switch (selector) { + case 0x0: + return slow_work_runqueue_index(m, _pos); + + case 0x1: + if (*_pos >> ITERATOR_SHIFT == 0x1) { + p = p->next; + if (p != &slow_work_queue) + return p; + } + *_pos = 0x2UL << ITERATOR_SHIFT; + p = &vslow_work_queue; + + case 0x2: + if (*_pos >> ITERATOR_SHIFT == 0x2) { + p = p->next; + if (p != &vslow_work_queue) + return p; + } + *_pos = 0x3UL << ITERATOR_SHIFT; + + default: + return NULL; + } +} + +/* + * clean up after reading + */ +static void slow_work_runqueue_stop(struct seq_file *m, void *v) +{ + spin_unlock_irq(&slow_work_queue_lock); +} + +static const struct seq_operations slow_work_runqueue_ops = { + .start = slow_work_runqueue_start, + .stop = slow_work_runqueue_stop, + .next = slow_work_runqueue_next, + .show = slow_work_runqueue_show, +}; + +/* + * open "/sys/kernel/debug/slow_work/runqueue" to list queue contents + */ +static int slow_work_runqueue_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &slow_work_runqueue_ops); +} + +const struct file_operations slow_work_runqueue_fops = { + .owner = THIS_MODULE, + .open = slow_work_runqueue_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; diff --git a/kernel/slow-work.c b/kernel/slow-work.c index 0d31135efbf4..7494bbf5a270 100644 --- a/kernel/slow-work.c +++ b/kernel/slow-work.c @@ -16,11 +16,8 @@ #include <linux/kthread.h> #include <linux/freezer.h> #include <linux/wait.h> - -#define SLOW_WORK_CULL_TIMEOUT (5 * HZ) /* cull threads 5s after running out of - * things to do */ -#define SLOW_WORK_OOM_TIMEOUT (5 * HZ) /* can't start new threads for 5s after - * OOM */ +#include <linux/debugfs.h> +#include "slow-work.h" static void slow_work_cull_timeout(unsigned long); static void slow_work_oom_timeout(unsigned long); @@ -46,13 +43,12 @@ static unsigned vslow_work_proportion = 50; /* % of threads that may process #ifdef CONFIG_SYSCTL static const int slow_work_min_min_threads = 2; -static int slow_work_max_max_threads = 255; +static int slow_work_max_max_threads = SLOW_WORK_THREAD_LIMIT; static const int slow_work_min_vslow = 1; static const int slow_work_max_vslow = 99; ctl_table slow_work_sysctls[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "min-threads", .data = &slow_work_min_threads, .maxlen = sizeof(unsigned), @@ -62,7 +58,6 @@ ctl_table slow_work_sysctls[] = { .extra2 = &slow_work_max_threads, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "max-threads", .data = &slow_work_max_threads, .maxlen = sizeof(unsigned), @@ -72,16 +67,15 @@ ctl_table slow_work_sysctls[] = { .extra2 = (void *) &slow_work_max_max_threads, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "vslow-percentage", .data = &vslow_work_proportion, .maxlen = sizeof(unsigned), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, + .proc_handler = proc_dointvec_minmax, .extra1 = (void *) &slow_work_min_vslow, .extra2 = (void *) &slow_work_max_vslow, }, - { .ctl_name = 0 } + {} }; #endif @@ -98,6 +92,56 @@ static DEFINE_TIMER(slow_work_oom_timer, slow_work_oom_timeout, 0, 0); static struct slow_work slow_work_new_thread; /* new thread starter */ /* + * slow work ID allocation (use slow_work_queue_lock) + */ +static DECLARE_BITMAP(slow_work_ids, SLOW_WORK_THREAD_LIMIT); + +/* + * Unregistration tracking to prevent put_ref() from disappearing during module + * unload + */ +#ifdef CONFIG_MODULES +static struct module *slow_work_thread_processing[SLOW_WORK_THREAD_LIMIT]; +static struct module *slow_work_unreg_module; +static struct slow_work *slow_work_unreg_work_item; +static DECLARE_WAIT_QUEUE_HEAD(slow_work_unreg_wq); +static DEFINE_MUTEX(slow_work_unreg_sync_lock); + +static void slow_work_set_thread_processing(int id, struct slow_work *work) +{ + if (work) + slow_work_thread_processing[id] = work->owner; +} +static void slow_work_done_thread_processing(int id, struct slow_work *work) +{ + struct module *module = slow_work_thread_processing[id]; + + slow_work_thread_processing[id] = NULL; + smp_mb(); + if (slow_work_unreg_work_item == work || + slow_work_unreg_module == module) + wake_up_all(&slow_work_unreg_wq); +} +static void slow_work_clear_thread_processing(int id) +{ + slow_work_thread_processing[id] = NULL; +} +#else +static void slow_work_set_thread_processing(int id, struct slow_work *work) {} +static void slow_work_done_thread_processing(int id, struct slow_work *work) {} +static void slow_work_clear_thread_processing(int id) {} +#endif + +/* + * Data for tracking currently executing items for indication through /proc + */ +#ifdef CONFIG_SLOW_WORK_DEBUG +struct slow_work *slow_work_execs[SLOW_WORK_THREAD_LIMIT]; +pid_t slow_work_pids[SLOW_WORK_THREAD_LIMIT]; +DEFINE_RWLOCK(slow_work_execs_lock); +#endif + +/* * The queues of work items and the lock governing access to them. These are * shared between all the CPUs. It doesn't make sense to have per-CPU queues * as the number of threads bears no relation to the number of CPUs. @@ -105,9 +149,18 @@ static struct slow_work slow_work_new_thread; /* new thread starter */ * There are two queues of work items: one for slow work items, and one for * very slow work items. */ -static LIST_HEAD(slow_work_queue); -static LIST_HEAD(vslow_work_queue); -static DEFINE_SPINLOCK(slow_work_queue_lock); +LIST_HEAD(slow_work_queue); +LIST_HEAD(vslow_work_queue); +DEFINE_SPINLOCK(slow_work_queue_lock); + +/* + * The following are two wait queues that get pinged when a work item is placed + * on an empty queue. These allow work items that are hogging a thread by + * sleeping in a way that could be deferred to yield their thread and enqueue + * themselves. + */ +static DECLARE_WAIT_QUEUE_HEAD(slow_work_queue_waits_for_occupation); +static DECLARE_WAIT_QUEUE_HEAD(vslow_work_queue_waits_for_occupation); /* * The thread controls. A variable used to signal to the threads that they @@ -126,6 +179,20 @@ static DECLARE_COMPLETION(slow_work_last_thread_exited); static int slow_work_user_count; static DEFINE_MUTEX(slow_work_user_lock); +static inline int slow_work_get_ref(struct slow_work *work) +{ + if (work->ops->get_ref) + return work->ops->get_ref(work); + + return 0; +} + +static inline void slow_work_put_ref(struct slow_work *work) +{ + if (work->ops->put_ref) + work->ops->put_ref(work); +} + /* * Calculate the maximum number of active threads in the pool that are * permitted to process very slow work items. @@ -149,7 +216,7 @@ static unsigned slow_work_calc_vsmax(void) * Attempt to execute stuff queued on a slow thread. Return true if we managed * it, false if there was nothing to do. */ -static bool slow_work_execute(void) +static noinline bool slow_work_execute(int id) { struct slow_work *work = NULL; unsigned vsmax; @@ -186,6 +253,13 @@ static bool slow_work_execute(void) } else { very_slow = false; /* avoid the compiler warning */ } + + slow_work_set_thread_processing(id, work); + if (work) { + slow_work_mark_time(work); + slow_work_begin_exec(id, work); + } + spin_unlock_irq(&slow_work_queue_lock); if (!work) @@ -194,12 +268,19 @@ static bool slow_work_execute(void) if (!test_and_clear_bit(SLOW_WORK_PENDING, &work->flags)) BUG(); - work->ops->execute(work); + /* don't execute if the work is in the process of being cancelled */ + if (!test_bit(SLOW_WORK_CANCELLING, &work->flags)) + work->ops->execute(work); if (very_slow) atomic_dec(&vslow_work_executing_count); clear_bit_unlock(SLOW_WORK_EXECUTING, &work->flags); + /* wake up anyone waiting for this work to be complete */ + wake_up_bit(&work->flags, SLOW_WORK_EXECUTING); + + slow_work_end_exec(id, work); + /* if someone tried to enqueue the item whilst we were executing it, * then it'll be left unenqueued to avoid multiple threads trying to * execute it simultaneously @@ -219,7 +300,10 @@ static bool slow_work_execute(void) spin_unlock_irq(&slow_work_queue_lock); } - work->ops->put_ref(work); + /* sort out the race between module unloading and put_ref() */ + slow_work_put_ref(work); + slow_work_done_thread_processing(id, work); + return true; auto_requeue: @@ -227,15 +311,61 @@ auto_requeue: * - we transfer our ref on the item back to the appropriate queue * - don't wake another thread up as we're awake already */ + slow_work_mark_time(work); if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) list_add_tail(&work->link, &vslow_work_queue); else list_add_tail(&work->link, &slow_work_queue); spin_unlock_irq(&slow_work_queue_lock); + slow_work_clear_thread_processing(id); return true; } /** + * slow_work_sleep_till_thread_needed - Sleep till thread needed by other work + * work: The work item under execution that wants to sleep + * _timeout: Scheduler sleep timeout + * + * Allow a requeueable work item to sleep on a slow-work processor thread until + * that thread is needed to do some other work or the sleep is interrupted by + * some other event. + * + * The caller must set up a wake up event before calling this and must have set + * the appropriate sleep mode (such as TASK_UNINTERRUPTIBLE) and tested its own + * condition before calling this function as no test is made here. + * + * False is returned if there is nothing on the queue; true is returned if the + * work item should be requeued + */ +bool slow_work_sleep_till_thread_needed(struct slow_work *work, + signed long *_timeout) +{ + wait_queue_head_t *wfo_wq; + struct list_head *queue; + + DEFINE_WAIT(wait); + + if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) { + wfo_wq = &vslow_work_queue_waits_for_occupation; + queue = &vslow_work_queue; + } else { + wfo_wq = &slow_work_queue_waits_for_occupation; + queue = &slow_work_queue; + } + + if (!list_empty(queue)) + return true; + + add_wait_queue_exclusive(wfo_wq, &wait); + if (list_empty(queue)) + *_timeout = schedule_timeout(*_timeout); + finish_wait(wfo_wq, &wait); + + return !list_empty(queue); +} +EXPORT_SYMBOL(slow_work_sleep_till_thread_needed); + +/** * slow_work_enqueue - Schedule a slow work item for processing * @work: The work item to queue * @@ -260,16 +390,22 @@ auto_requeue: * allowed to pick items to execute. This ensures that very slow items won't * overly block ones that are just ordinarily slow. * - * Returns 0 if successful, -EAGAIN if not. + * Returns 0 if successful, -EAGAIN if not (or -ECANCELED if cancelled work is + * attempted queued) */ int slow_work_enqueue(struct slow_work *work) { + wait_queue_head_t *wfo_wq; + struct list_head *queue; unsigned long flags; + int ret; + + if (test_bit(SLOW_WORK_CANCELLING, &work->flags)) + return -ECANCELED; BUG_ON(slow_work_user_count <= 0); BUG_ON(!work); BUG_ON(!work->ops); - BUG_ON(!work->ops->get_ref); /* when honouring an enqueue request, we only promise that we will run * the work function in the future; we do not promise to run it once @@ -280,8 +416,19 @@ int slow_work_enqueue(struct slow_work *work) * maintaining our promise */ if (!test_and_set_bit_lock(SLOW_WORK_PENDING, &work->flags)) { + if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) { + wfo_wq = &vslow_work_queue_waits_for_occupation; + queue = &vslow_work_queue; + } else { + wfo_wq = &slow_work_queue_waits_for_occupation; + queue = &slow_work_queue; + } + spin_lock_irqsave(&slow_work_queue_lock, flags); + if (unlikely(test_bit(SLOW_WORK_CANCELLING, &work->flags))) + goto cancelled; + /* we promise that we will not attempt to execute the work * function in more than one thread simultaneously * @@ -299,25 +446,221 @@ int slow_work_enqueue(struct slow_work *work) if (test_bit(SLOW_WORK_EXECUTING, &work->flags)) { set_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags); } else { - if (work->ops->get_ref(work) < 0) - goto cant_get_ref; - if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) - list_add_tail(&work->link, &vslow_work_queue); - else - list_add_tail(&work->link, &slow_work_queue); + ret = slow_work_get_ref(work); + if (ret < 0) + goto failed; + slow_work_mark_time(work); + list_add_tail(&work->link, queue); wake_up(&slow_work_thread_wq); + + /* if someone who could be requeued is sleeping on a + * thread, then ask them to yield their thread */ + if (work->link.prev == queue) + wake_up(wfo_wq); } spin_unlock_irqrestore(&slow_work_queue_lock, flags); } return 0; -cant_get_ref: +cancelled: + ret = -ECANCELED; +failed: spin_unlock_irqrestore(&slow_work_queue_lock, flags); - return -EAGAIN; + return ret; } EXPORT_SYMBOL(slow_work_enqueue); +static int slow_work_wait(void *word) +{ + schedule(); + return 0; +} + +/** + * slow_work_cancel - Cancel a slow work item + * @work: The work item to cancel + * + * This function will cancel a previously enqueued work item. If we cannot + * cancel the work item, it is guarenteed to have run when this function + * returns. + */ +void slow_work_cancel(struct slow_work *work) +{ + bool wait = true, put = false; + + set_bit(SLOW_WORK_CANCELLING, &work->flags); + smp_mb(); + + /* if the work item is a delayed work item with an active timer, we + * need to wait for the timer to finish _before_ getting the spinlock, + * lest we deadlock against the timer routine + * + * the timer routine will leave DELAYED set if it notices the + * CANCELLING flag in time + */ + if (test_bit(SLOW_WORK_DELAYED, &work->flags)) { + struct delayed_slow_work *dwork = + container_of(work, struct delayed_slow_work, work); + del_timer_sync(&dwork->timer); + } + + spin_lock_irq(&slow_work_queue_lock); + + if (test_bit(SLOW_WORK_DELAYED, &work->flags)) { + /* the timer routine aborted or never happened, so we are left + * holding the timer's reference on the item and should just + * drop the pending flag and wait for any ongoing execution to + * finish */ + struct delayed_slow_work *dwork = + container_of(work, struct delayed_slow_work, work); + + BUG_ON(timer_pending(&dwork->timer)); + BUG_ON(!list_empty(&work->link)); + + clear_bit(SLOW_WORK_DELAYED, &work->flags); + put = true; + clear_bit(SLOW_WORK_PENDING, &work->flags); + + } else if (test_bit(SLOW_WORK_PENDING, &work->flags) && + !list_empty(&work->link)) { + /* the link in the pending queue holds a reference on the item + * that we will need to release */ + list_del_init(&work->link); + wait = false; + put = true; + clear_bit(SLOW_WORK_PENDING, &work->flags); + + } else if (test_and_clear_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags)) { + /* the executor is holding our only reference on the item, so + * we merely need to wait for it to finish executing */ + clear_bit(SLOW_WORK_PENDING, &work->flags); + } + + spin_unlock_irq(&slow_work_queue_lock); + + /* the EXECUTING flag is set by the executor whilst the spinlock is set + * and before the item is dequeued - so assuming the above doesn't + * actually dequeue it, simply waiting for the EXECUTING flag to be + * released here should be sufficient */ + if (wait) + wait_on_bit(&work->flags, SLOW_WORK_EXECUTING, slow_work_wait, + TASK_UNINTERRUPTIBLE); + + clear_bit(SLOW_WORK_CANCELLING, &work->flags); + if (put) + slow_work_put_ref(work); +} +EXPORT_SYMBOL(slow_work_cancel); + +/* + * Handle expiry of the delay timer, indicating that a delayed slow work item + * should now be queued if not cancelled + */ +static void delayed_slow_work_timer(unsigned long data) +{ + wait_queue_head_t *wfo_wq; + struct list_head *queue; + struct slow_work *work = (struct slow_work *) data; + unsigned long flags; + bool queued = false, put = false, first = false; + + if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) { + wfo_wq = &vslow_work_queue_waits_for_occupation; + queue = &vslow_work_queue; + } else { + wfo_wq = &slow_work_queue_waits_for_occupation; + queue = &slow_work_queue; + } + + spin_lock_irqsave(&slow_work_queue_lock, flags); + if (likely(!test_bit(SLOW_WORK_CANCELLING, &work->flags))) { + clear_bit(SLOW_WORK_DELAYED, &work->flags); + + if (test_bit(SLOW_WORK_EXECUTING, &work->flags)) { + /* we discard the reference the timer was holding in + * favour of the one the executor holds */ + set_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags); + put = true; + } else { + slow_work_mark_time(work); + list_add_tail(&work->link, queue); + queued = true; + if (work->link.prev == queue) + first = true; + } + } + + spin_unlock_irqrestore(&slow_work_queue_lock, flags); + if (put) + slow_work_put_ref(work); + if (first) + wake_up(wfo_wq); + if (queued) + wake_up(&slow_work_thread_wq); +} + +/** + * delayed_slow_work_enqueue - Schedule a delayed slow work item for processing + * @dwork: The delayed work item to queue + * @delay: When to start executing the work, in jiffies from now + * + * This is similar to slow_work_enqueue(), but it adds a delay before the work + * is actually queued for processing. + * + * The item can have delayed processing requested on it whilst it is being + * executed. The delay will begin immediately, and if it expires before the + * item finishes executing, the item will be placed back on the queue when it + * has done executing. + */ +int delayed_slow_work_enqueue(struct delayed_slow_work *dwork, + unsigned long delay) +{ + struct slow_work *work = &dwork->work; + unsigned long flags; + int ret; + + if (delay == 0) + return slow_work_enqueue(&dwork->work); + + BUG_ON(slow_work_user_count <= 0); + BUG_ON(!work); + BUG_ON(!work->ops); + + if (test_bit(SLOW_WORK_CANCELLING, &work->flags)) + return -ECANCELED; + + if (!test_and_set_bit_lock(SLOW_WORK_PENDING, &work->flags)) { + spin_lock_irqsave(&slow_work_queue_lock, flags); + + if (test_bit(SLOW_WORK_CANCELLING, &work->flags)) + goto cancelled; + + /* the timer holds a reference whilst it is pending */ + ret = work->ops->get_ref(work); + if (ret < 0) + goto cant_get_ref; + + if (test_and_set_bit(SLOW_WORK_DELAYED, &work->flags)) + BUG(); + dwork->timer.expires = jiffies + delay; + dwork->timer.data = (unsigned long) work; + dwork->timer.function = delayed_slow_work_timer; + add_timer(&dwork->timer); + + spin_unlock_irqrestore(&slow_work_queue_lock, flags); + } + + return 0; + +cancelled: + ret = -ECANCELED; +cant_get_ref: + spin_unlock_irqrestore(&slow_work_queue_lock, flags); + return ret; +} +EXPORT_SYMBOL(delayed_slow_work_enqueue); + /* * Schedule a cull of the thread pool at some time in the near future */ @@ -368,13 +711,23 @@ static inline bool slow_work_available(int vsmax) */ static int slow_work_thread(void *_data) { - int vsmax; + int vsmax, id; DEFINE_WAIT(wait); set_freezable(); set_user_nice(current, -5); + /* allocate ourselves an ID */ + spin_lock_irq(&slow_work_queue_lock); + id = find_first_zero_bit(slow_work_ids, SLOW_WORK_THREAD_LIMIT); + BUG_ON(id < 0 || id >= SLOW_WORK_THREAD_LIMIT); + __set_bit(id, slow_work_ids); + slow_work_set_thread_pid(id, current->pid); + spin_unlock_irq(&slow_work_queue_lock); + + sprintf(current->comm, "kslowd%03u", id); + for (;;) { vsmax = vslow_work_proportion; vsmax *= atomic_read(&slow_work_thread_count); @@ -395,7 +748,7 @@ static int slow_work_thread(void *_data) vsmax *= atomic_read(&slow_work_thread_count); vsmax /= 100; - if (slow_work_available(vsmax) && slow_work_execute()) { + if (slow_work_available(vsmax) && slow_work_execute(id)) { cond_resched(); if (list_empty(&slow_work_queue) && list_empty(&vslow_work_queue) && @@ -412,6 +765,11 @@ static int slow_work_thread(void *_data) break; } + spin_lock_irq(&slow_work_queue_lock); + slow_work_set_thread_pid(id, 0); + __clear_bit(id, slow_work_ids); + spin_unlock_irq(&slow_work_queue_lock); + if (atomic_dec_and_test(&slow_work_thread_count)) complete_and_exit(&slow_work_last_thread_exited, 0); return 0; @@ -427,21 +785,6 @@ static void slow_work_cull_timeout(unsigned long data) } /* - * Get a reference on slow work thread starter - */ -static int slow_work_new_thread_get_ref(struct slow_work *work) -{ - return 0; -} - -/* - * Drop a reference on slow work thread starter - */ -static void slow_work_new_thread_put_ref(struct slow_work *work) -{ -} - -/* * Start a new slow work thread */ static void slow_work_new_thread_execute(struct slow_work *work) @@ -475,9 +818,11 @@ static void slow_work_new_thread_execute(struct slow_work *work) } static const struct slow_work_ops slow_work_new_thread_ops = { - .get_ref = slow_work_new_thread_get_ref, - .put_ref = slow_work_new_thread_put_ref, + .owner = THIS_MODULE, .execute = slow_work_new_thread_execute, +#ifdef CONFIG_SLOW_WORK_DEBUG + .desc = slow_work_new_thread_desc, +#endif }; /* @@ -546,12 +891,13 @@ static int slow_work_max_threads_sysctl(struct ctl_table *table, int write, /** * slow_work_register_user - Register a user of the facility + * @module: The module about to make use of the facility * * Register a user of the facility, starting up the initial threads if there * aren't any other users at this point. This will return 0 if successful, or * an error if not. */ -int slow_work_register_user(void) +int slow_work_register_user(struct module *module) { struct task_struct *p; int loop; @@ -598,14 +944,81 @@ error: } EXPORT_SYMBOL(slow_work_register_user); +/* + * wait for all outstanding items from the calling module to complete + * - note that more items may be queued whilst we're waiting + */ +static void slow_work_wait_for_items(struct module *module) +{ +#ifdef CONFIG_MODULES + DECLARE_WAITQUEUE(myself, current); + struct slow_work *work; + int loop; + + mutex_lock(&slow_work_unreg_sync_lock); + add_wait_queue(&slow_work_unreg_wq, &myself); + + for (;;) { + spin_lock_irq(&slow_work_queue_lock); + + /* first of all, we wait for the last queued item in each list + * to be processed */ + list_for_each_entry_reverse(work, &vslow_work_queue, link) { + if (work->owner == module) { + set_current_state(TASK_UNINTERRUPTIBLE); + slow_work_unreg_work_item = work; + goto do_wait; + } + } + list_for_each_entry_reverse(work, &slow_work_queue, link) { + if (work->owner == module) { + set_current_state(TASK_UNINTERRUPTIBLE); + slow_work_unreg_work_item = work; + goto do_wait; + } + } + + /* then we wait for the items being processed to finish */ + slow_work_unreg_module = module; + smp_mb(); + for (loop = 0; loop < SLOW_WORK_THREAD_LIMIT; loop++) { + if (slow_work_thread_processing[loop] == module) + goto do_wait; + } + spin_unlock_irq(&slow_work_queue_lock); + break; /* okay, we're done */ + + do_wait: + spin_unlock_irq(&slow_work_queue_lock); + schedule(); + slow_work_unreg_work_item = NULL; + slow_work_unreg_module = NULL; + } + + remove_wait_queue(&slow_work_unreg_wq, &myself); + mutex_unlock(&slow_work_unreg_sync_lock); +#endif /* CONFIG_MODULES */ +} + /** * slow_work_unregister_user - Unregister a user of the facility + * @module: The module whose items should be cleared * * Unregister a user of the facility, killing all the threads if this was the * last one. + * + * This waits for all the work items belonging to the nominated module to go + * away before proceeding. */ -void slow_work_unregister_user(void) +void slow_work_unregister_user(struct module *module) { + /* first of all, wait for all outstanding items from the calling module + * to complete */ + if (module) + slow_work_wait_for_items(module); + + /* then we can actually go about shutting down the facility if need + * be */ mutex_lock(&slow_work_user_lock); BUG_ON(slow_work_user_count <= 0); @@ -639,6 +1052,16 @@ static int __init init_slow_work(void) if (slow_work_max_max_threads < nr_cpus * 2) slow_work_max_max_threads = nr_cpus * 2; #endif +#ifdef CONFIG_SLOW_WORK_DEBUG + { + struct dentry *dbdir; + + dbdir = debugfs_create_dir("slow_work", NULL); + if (dbdir && !IS_ERR(dbdir)) + debugfs_create_file("runqueue", S_IFREG | 0400, dbdir, + NULL, &slow_work_runqueue_fops); + } +#endif return 0; } diff --git a/kernel/slow-work.h b/kernel/slow-work.h new file mode 100644 index 000000000000..321f3c59d732 --- /dev/null +++ b/kernel/slow-work.h @@ -0,0 +1,72 @@ +/* Slow work private definitions + * + * Copyright (C) 2009 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#define SLOW_WORK_CULL_TIMEOUT (5 * HZ) /* cull threads 5s after running out of + * things to do */ +#define SLOW_WORK_OOM_TIMEOUT (5 * HZ) /* can't start new threads for 5s after + * OOM */ + +#define SLOW_WORK_THREAD_LIMIT 255 /* abs maximum number of slow-work threads */ + +/* + * slow-work.c + */ +#ifdef CONFIG_SLOW_WORK_DEBUG +extern struct slow_work *slow_work_execs[]; +extern pid_t slow_work_pids[]; +extern rwlock_t slow_work_execs_lock; +#endif + +extern struct list_head slow_work_queue; +extern struct list_head vslow_work_queue; +extern spinlock_t slow_work_queue_lock; + +/* + * slow-work-debugfs.c + */ +#ifdef CONFIG_SLOW_WORK_DEBUG +extern const struct file_operations slow_work_runqueue_fops; + +extern void slow_work_new_thread_desc(struct slow_work *, struct seq_file *); +#endif + +/* + * Helper functions + */ +static inline void slow_work_set_thread_pid(int id, pid_t pid) +{ +#ifdef CONFIG_SLOW_WORK_PROC + slow_work_pids[id] = pid; +#endif +} + +static inline void slow_work_mark_time(struct slow_work *work) +{ +#ifdef CONFIG_SLOW_WORK_PROC + work->mark = CURRENT_TIME; +#endif +} + +static inline void slow_work_begin_exec(int id, struct slow_work *work) +{ +#ifdef CONFIG_SLOW_WORK_PROC + slow_work_execs[id] = work; +#endif +} + +static inline void slow_work_end_exec(int id, struct slow_work *work) +{ +#ifdef CONFIG_SLOW_WORK_PROC + write_lock(&slow_work_execs_lock); + slow_work_execs[id] = NULL; + write_unlock(&slow_work_execs_lock); +#endif +} diff --git a/kernel/smp.c b/kernel/smp.c index c9d1c7835c2f..a8c76069cf50 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -265,9 +265,7 @@ static DEFINE_PER_CPU(struct call_single_data, csd_data); * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait until function has completed on other CPUs. * - * Returns 0 on success, else a negative status code. Note that @wait - * will be implicitly turned on in case of allocation failures, since - * we fall back to on-stack allocation. + * Returns 0 on success, else a negative status code. */ int smp_call_function_single(int cpu, void (*func) (void *info), void *info, int wait) @@ -321,6 +319,51 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info, } EXPORT_SYMBOL(smp_call_function_single); +/* + * smp_call_function_any - Run a function on any of the given cpus + * @mask: The mask of cpus it can run on. + * @func: The function to run. This must be fast and non-blocking. + * @info: An arbitrary pointer to pass to the function. + * @wait: If true, wait until function has completed. + * + * Returns 0 on success, else a negative status code (if no cpus were online). + * Note that @wait will be implicitly turned on in case of allocation failures, + * since we fall back to on-stack allocation. + * + * Selection preference: + * 1) current cpu if in @mask + * 2) any cpu of current node if in @mask + * 3) any other online cpu in @mask + */ +int smp_call_function_any(const struct cpumask *mask, + void (*func)(void *info), void *info, int wait) +{ + unsigned int cpu; + const struct cpumask *nodemask; + int ret; + + /* Try for same CPU (cheapest) */ + cpu = get_cpu(); + if (cpumask_test_cpu(cpu, mask)) + goto call; + + /* Try for same node. */ + nodemask = cpumask_of_node(cpu); + for (cpu = cpumask_first_and(nodemask, mask); cpu < nr_cpu_ids; + cpu = cpumask_next_and(cpu, nodemask, mask)) { + if (cpu_online(cpu)) + goto call; + } + + /* Any online will do: smp_call_function_single handles nr_cpu_ids. */ + cpu = cpumask_any_and(mask, cpu_online_mask); +call: + ret = smp_call_function_single(cpu, func, info, wait); + put_cpu(); + return ret; +} +EXPORT_SYMBOL_GPL(smp_call_function_any); + /** * __smp_call_function_single(): Run a function on another CPU * @cpu: The CPU to run on. @@ -355,9 +398,7 @@ void __smp_call_function_single(int cpu, struct call_single_data *data, * @wait: If true, wait (atomically) until function has completed * on other CPUs. * - * If @wait is true, then returns once @func has returned. Note that @wait - * will be implicitly turned on in case of allocation failures, since - * we fall back to on-stack allocation. + * If @wait is true, then returns once @func has returned. * * You must not call this function with disabled interrupts or from a * hardware interrupt handler or from a bottom half handler. Preemption @@ -443,8 +484,7 @@ EXPORT_SYMBOL(smp_call_function_many); * Returns 0. * * If @wait is true, then returns once @func has returned; otherwise - * it returns just before the target cpu calls @func. In case of allocation - * failure, @wait will be implicitly turned on. + * it returns just before the target cpu calls @func. * * You must not call this function with disabled interrupts or from a * hardware interrupt handler or from a bottom half handler. diff --git a/kernel/softirq.c b/kernel/softirq.c index f8749e5216e0..21939d9e830e 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -302,9 +302,9 @@ void irq_exit(void) if (!in_interrupt() && local_softirq_pending()) invoke_softirq(); + rcu_irq_exit(); #ifdef CONFIG_NO_HZ /* Make sure that timer wheel updates are propagated */ - rcu_irq_exit(); if (idle_cpu(smp_processor_id()) && !in_interrupt() && !need_resched()) tick_nohz_stop_sched_tick(0); #endif diff --git a/kernel/spinlock.c b/kernel/spinlock.c index 5ddab730cb2f..41e042219ff6 100644 --- a/kernel/spinlock.c +++ b/kernel/spinlock.c @@ -21,145 +21,28 @@ #include <linux/debug_locks.h> #include <linux/module.h> -#ifndef _spin_trylock -int __lockfunc _spin_trylock(spinlock_t *lock) -{ - return __spin_trylock(lock); -} -EXPORT_SYMBOL(_spin_trylock); -#endif - -#ifndef _read_trylock -int __lockfunc _read_trylock(rwlock_t *lock) -{ - return __read_trylock(lock); -} -EXPORT_SYMBOL(_read_trylock); -#endif - -#ifndef _write_trylock -int __lockfunc _write_trylock(rwlock_t *lock) -{ - return __write_trylock(lock); -} -EXPORT_SYMBOL(_write_trylock); -#endif - /* * If lockdep is enabled then we use the non-preemption spin-ops * even on CONFIG_PREEMPT, because lockdep assumes that interrupts are * not re-enabled during lock-acquire (which the preempt-spin-ops do): */ #if !defined(CONFIG_GENERIC_LOCKBREAK) || defined(CONFIG_DEBUG_LOCK_ALLOC) - -#ifndef _read_lock -void __lockfunc _read_lock(rwlock_t *lock) -{ - __read_lock(lock); -} -EXPORT_SYMBOL(_read_lock); -#endif - -#ifndef _spin_lock_irqsave -unsigned long __lockfunc _spin_lock_irqsave(spinlock_t *lock) -{ - return __spin_lock_irqsave(lock); -} -EXPORT_SYMBOL(_spin_lock_irqsave); -#endif - -#ifndef _spin_lock_irq -void __lockfunc _spin_lock_irq(spinlock_t *lock) -{ - __spin_lock_irq(lock); -} -EXPORT_SYMBOL(_spin_lock_irq); -#endif - -#ifndef _spin_lock_bh -void __lockfunc _spin_lock_bh(spinlock_t *lock) -{ - __spin_lock_bh(lock); -} -EXPORT_SYMBOL(_spin_lock_bh); -#endif - -#ifndef _read_lock_irqsave -unsigned long __lockfunc _read_lock_irqsave(rwlock_t *lock) -{ - return __read_lock_irqsave(lock); -} -EXPORT_SYMBOL(_read_lock_irqsave); -#endif - -#ifndef _read_lock_irq -void __lockfunc _read_lock_irq(rwlock_t *lock) -{ - __read_lock_irq(lock); -} -EXPORT_SYMBOL(_read_lock_irq); -#endif - -#ifndef _read_lock_bh -void __lockfunc _read_lock_bh(rwlock_t *lock) -{ - __read_lock_bh(lock); -} -EXPORT_SYMBOL(_read_lock_bh); -#endif - -#ifndef _write_lock_irqsave -unsigned long __lockfunc _write_lock_irqsave(rwlock_t *lock) -{ - return __write_lock_irqsave(lock); -} -EXPORT_SYMBOL(_write_lock_irqsave); -#endif - -#ifndef _write_lock_irq -void __lockfunc _write_lock_irq(rwlock_t *lock) -{ - __write_lock_irq(lock); -} -EXPORT_SYMBOL(_write_lock_irq); -#endif - -#ifndef _write_lock_bh -void __lockfunc _write_lock_bh(rwlock_t *lock) -{ - __write_lock_bh(lock); -} -EXPORT_SYMBOL(_write_lock_bh); -#endif - -#ifndef _spin_lock -void __lockfunc _spin_lock(spinlock_t *lock) -{ - __spin_lock(lock); -} -EXPORT_SYMBOL(_spin_lock); -#endif - -#ifndef _write_lock -void __lockfunc _write_lock(rwlock_t *lock) -{ - __write_lock(lock); -} -EXPORT_SYMBOL(_write_lock); -#endif - -#else /* CONFIG_PREEMPT: */ - /* + * The __lock_function inlines are taken from + * include/linux/spinlock_api_smp.h + */ +#else +/* + * We build the __lock_function inlines here. They are too large for + * inlining all over the place, but here is only one user per function + * which embedds them into the calling _lock_function below. + * * This could be a long-held lock. We both prepare to spin for a long * time (making _this_ CPU preemptable if possible), and we also signal * towards that other CPU that it should break the lock ASAP. - * - * (We do this in a function because inlining it would be excessive.) */ - #define BUILD_LOCK_OPS(op, locktype) \ -void __lockfunc _##op##_lock(locktype##_t *lock) \ +void __lockfunc __##op##_lock(locktype##_t *lock) \ { \ for (;;) { \ preempt_disable(); \ @@ -175,9 +58,7 @@ void __lockfunc _##op##_lock(locktype##_t *lock) \ (lock)->break_lock = 0; \ } \ \ -EXPORT_SYMBOL(_##op##_lock); \ - \ -unsigned long __lockfunc _##op##_lock_irqsave(locktype##_t *lock) \ +unsigned long __lockfunc __##op##_lock_irqsave(locktype##_t *lock) \ { \ unsigned long flags; \ \ @@ -198,16 +79,12 @@ unsigned long __lockfunc _##op##_lock_irqsave(locktype##_t *lock) \ return flags; \ } \ \ -EXPORT_SYMBOL(_##op##_lock_irqsave); \ - \ -void __lockfunc _##op##_lock_irq(locktype##_t *lock) \ +void __lockfunc __##op##_lock_irq(locktype##_t *lock) \ { \ _##op##_lock_irqsave(lock); \ } \ \ -EXPORT_SYMBOL(_##op##_lock_irq); \ - \ -void __lockfunc _##op##_lock_bh(locktype##_t *lock) \ +void __lockfunc __##op##_lock_bh(locktype##_t *lock) \ { \ unsigned long flags; \ \ @@ -220,23 +97,21 @@ void __lockfunc _##op##_lock_bh(locktype##_t *lock) \ local_bh_disable(); \ local_irq_restore(flags); \ } \ - \ -EXPORT_SYMBOL(_##op##_lock_bh) /* * Build preemption-friendly versions of the following * lock-spinning functions: * - * _[spin|read|write]_lock() - * _[spin|read|write]_lock_irq() - * _[spin|read|write]_lock_irqsave() - * _[spin|read|write]_lock_bh() + * __[spin|read|write]_lock() + * __[spin|read|write]_lock_irq() + * __[spin|read|write]_lock_irqsave() + * __[spin|read|write]_lock_bh() */ BUILD_LOCK_OPS(spin, spinlock); BUILD_LOCK_OPS(read, rwlock); BUILD_LOCK_OPS(write, rwlock); -#endif /* CONFIG_PREEMPT */ +#endif #ifdef CONFIG_DEBUG_LOCK_ALLOC @@ -248,7 +123,8 @@ void __lockfunc _spin_lock_nested(spinlock_t *lock, int subclass) } EXPORT_SYMBOL(_spin_lock_nested); -unsigned long __lockfunc _spin_lock_irqsave_nested(spinlock_t *lock, int subclass) +unsigned long __lockfunc _spin_lock_irqsave_nested(spinlock_t *lock, + int subclass) { unsigned long flags; @@ -272,7 +148,127 @@ EXPORT_SYMBOL(_spin_lock_nest_lock); #endif -#ifndef _spin_unlock +#ifndef CONFIG_INLINE_SPIN_TRYLOCK +int __lockfunc _spin_trylock(spinlock_t *lock) +{ + return __spin_trylock(lock); +} +EXPORT_SYMBOL(_spin_trylock); +#endif + +#ifndef CONFIG_INLINE_READ_TRYLOCK +int __lockfunc _read_trylock(rwlock_t *lock) +{ + return __read_trylock(lock); +} +EXPORT_SYMBOL(_read_trylock); +#endif + +#ifndef CONFIG_INLINE_WRITE_TRYLOCK +int __lockfunc _write_trylock(rwlock_t *lock) +{ + return __write_trylock(lock); +} +EXPORT_SYMBOL(_write_trylock); +#endif + +#ifndef CONFIG_INLINE_READ_LOCK +void __lockfunc _read_lock(rwlock_t *lock) +{ + __read_lock(lock); +} +EXPORT_SYMBOL(_read_lock); +#endif + +#ifndef CONFIG_INLINE_SPIN_LOCK_IRQSAVE +unsigned long __lockfunc _spin_lock_irqsave(spinlock_t *lock) +{ + return __spin_lock_irqsave(lock); +} +EXPORT_SYMBOL(_spin_lock_irqsave); +#endif + +#ifndef CONFIG_INLINE_SPIN_LOCK_IRQ +void __lockfunc _spin_lock_irq(spinlock_t *lock) +{ + __spin_lock_irq(lock); +} +EXPORT_SYMBOL(_spin_lock_irq); +#endif + +#ifndef CONFIG_INLINE_SPIN_LOCK_BH +void __lockfunc _spin_lock_bh(spinlock_t *lock) +{ + __spin_lock_bh(lock); +} +EXPORT_SYMBOL(_spin_lock_bh); +#endif + +#ifndef CONFIG_INLINE_READ_LOCK_IRQSAVE +unsigned long __lockfunc _read_lock_irqsave(rwlock_t *lock) +{ + return __read_lock_irqsave(lock); +} +EXPORT_SYMBOL(_read_lock_irqsave); +#endif + +#ifndef CONFIG_INLINE_READ_LOCK_IRQ +void __lockfunc _read_lock_irq(rwlock_t *lock) +{ + __read_lock_irq(lock); +} +EXPORT_SYMBOL(_read_lock_irq); +#endif + +#ifndef CONFIG_INLINE_READ_LOCK_BH +void __lockfunc _read_lock_bh(rwlock_t *lock) +{ + __read_lock_bh(lock); +} +EXPORT_SYMBOL(_read_lock_bh); +#endif + +#ifndef CONFIG_INLINE_WRITE_LOCK_IRQSAVE +unsigned long __lockfunc _write_lock_irqsave(rwlock_t *lock) +{ + return __write_lock_irqsave(lock); +} +EXPORT_SYMBOL(_write_lock_irqsave); +#endif + +#ifndef CONFIG_INLINE_WRITE_LOCK_IRQ +void __lockfunc _write_lock_irq(rwlock_t *lock) +{ + __write_lock_irq(lock); +} +EXPORT_SYMBOL(_write_lock_irq); +#endif + +#ifndef CONFIG_INLINE_WRITE_LOCK_BH +void __lockfunc _write_lock_bh(rwlock_t *lock) +{ + __write_lock_bh(lock); +} +EXPORT_SYMBOL(_write_lock_bh); +#endif + +#ifndef CONFIG_INLINE_SPIN_LOCK +void __lockfunc _spin_lock(spinlock_t *lock) +{ + __spin_lock(lock); +} +EXPORT_SYMBOL(_spin_lock); +#endif + +#ifndef CONFIG_INLINE_WRITE_LOCK +void __lockfunc _write_lock(rwlock_t *lock) +{ + __write_lock(lock); +} +EXPORT_SYMBOL(_write_lock); +#endif + +#ifndef CONFIG_INLINE_SPIN_UNLOCK void __lockfunc _spin_unlock(spinlock_t *lock) { __spin_unlock(lock); @@ -280,7 +276,7 @@ void __lockfunc _spin_unlock(spinlock_t *lock) EXPORT_SYMBOL(_spin_unlock); #endif -#ifndef _write_unlock +#ifndef CONFIG_INLINE_WRITE_UNLOCK void __lockfunc _write_unlock(rwlock_t *lock) { __write_unlock(lock); @@ -288,7 +284,7 @@ void __lockfunc _write_unlock(rwlock_t *lock) EXPORT_SYMBOL(_write_unlock); #endif -#ifndef _read_unlock +#ifndef CONFIG_INLINE_READ_UNLOCK void __lockfunc _read_unlock(rwlock_t *lock) { __read_unlock(lock); @@ -296,7 +292,7 @@ void __lockfunc _read_unlock(rwlock_t *lock) EXPORT_SYMBOL(_read_unlock); #endif -#ifndef _spin_unlock_irqrestore +#ifndef CONFIG_INLINE_SPIN_UNLOCK_IRQRESTORE void __lockfunc _spin_unlock_irqrestore(spinlock_t *lock, unsigned long flags) { __spin_unlock_irqrestore(lock, flags); @@ -304,7 +300,7 @@ void __lockfunc _spin_unlock_irqrestore(spinlock_t *lock, unsigned long flags) EXPORT_SYMBOL(_spin_unlock_irqrestore); #endif -#ifndef _spin_unlock_irq +#ifndef CONFIG_INLINE_SPIN_UNLOCK_IRQ void __lockfunc _spin_unlock_irq(spinlock_t *lock) { __spin_unlock_irq(lock); @@ -312,7 +308,7 @@ void __lockfunc _spin_unlock_irq(spinlock_t *lock) EXPORT_SYMBOL(_spin_unlock_irq); #endif -#ifndef _spin_unlock_bh +#ifndef CONFIG_INLINE_SPIN_UNLOCK_BH void __lockfunc _spin_unlock_bh(spinlock_t *lock) { __spin_unlock_bh(lock); @@ -320,7 +316,7 @@ void __lockfunc _spin_unlock_bh(spinlock_t *lock) EXPORT_SYMBOL(_spin_unlock_bh); #endif -#ifndef _read_unlock_irqrestore +#ifndef CONFIG_INLINE_READ_UNLOCK_IRQRESTORE void __lockfunc _read_unlock_irqrestore(rwlock_t *lock, unsigned long flags) { __read_unlock_irqrestore(lock, flags); @@ -328,7 +324,7 @@ void __lockfunc _read_unlock_irqrestore(rwlock_t *lock, unsigned long flags) EXPORT_SYMBOL(_read_unlock_irqrestore); #endif -#ifndef _read_unlock_irq +#ifndef CONFIG_INLINE_READ_UNLOCK_IRQ void __lockfunc _read_unlock_irq(rwlock_t *lock) { __read_unlock_irq(lock); @@ -336,7 +332,7 @@ void __lockfunc _read_unlock_irq(rwlock_t *lock) EXPORT_SYMBOL(_read_unlock_irq); #endif -#ifndef _read_unlock_bh +#ifndef CONFIG_INLINE_READ_UNLOCK_BH void __lockfunc _read_unlock_bh(rwlock_t *lock) { __read_unlock_bh(lock); @@ -344,7 +340,7 @@ void __lockfunc _read_unlock_bh(rwlock_t *lock) EXPORT_SYMBOL(_read_unlock_bh); #endif -#ifndef _write_unlock_irqrestore +#ifndef CONFIG_INLINE_WRITE_UNLOCK_IRQRESTORE void __lockfunc _write_unlock_irqrestore(rwlock_t *lock, unsigned long flags) { __write_unlock_irqrestore(lock, flags); @@ -352,7 +348,7 @@ void __lockfunc _write_unlock_irqrestore(rwlock_t *lock, unsigned long flags) EXPORT_SYMBOL(_write_unlock_irqrestore); #endif -#ifndef _write_unlock_irq +#ifndef CONFIG_INLINE_WRITE_UNLOCK_IRQ void __lockfunc _write_unlock_irq(rwlock_t *lock) { __write_unlock_irq(lock); @@ -360,7 +356,7 @@ void __lockfunc _write_unlock_irq(rwlock_t *lock) EXPORT_SYMBOL(_write_unlock_irq); #endif -#ifndef _write_unlock_bh +#ifndef CONFIG_INLINE_WRITE_UNLOCK_BH void __lockfunc _write_unlock_bh(rwlock_t *lock) { __write_unlock_bh(lock); @@ -368,7 +364,7 @@ void __lockfunc _write_unlock_bh(rwlock_t *lock) EXPORT_SYMBOL(_write_unlock_bh); #endif -#ifndef _spin_trylock_bh +#ifndef CONFIG_INLINE_SPIN_TRYLOCK_BH int __lockfunc _spin_trylock_bh(spinlock_t *lock) { return __spin_trylock_bh(lock); diff --git a/kernel/srcu.c b/kernel/srcu.c index b0aeeaf22ce4..818d7d9aa03c 100644 --- a/kernel/srcu.c +++ b/kernel/srcu.c @@ -49,6 +49,7 @@ int init_srcu_struct(struct srcu_struct *sp) sp->per_cpu_ref = alloc_percpu(struct srcu_struct_array); return (sp->per_cpu_ref ? 0 : -ENOMEM); } +EXPORT_SYMBOL_GPL(init_srcu_struct); /* * srcu_readers_active_idx -- returns approximate number of readers @@ -97,6 +98,7 @@ void cleanup_srcu_struct(struct srcu_struct *sp) free_percpu(sp->per_cpu_ref); sp->per_cpu_ref = NULL; } +EXPORT_SYMBOL_GPL(cleanup_srcu_struct); /** * srcu_read_lock - register a new reader for an SRCU-protected structure. @@ -118,6 +120,7 @@ int srcu_read_lock(struct srcu_struct *sp) preempt_enable(); return idx; } +EXPORT_SYMBOL_GPL(srcu_read_lock); /** * srcu_read_unlock - unregister a old reader from an SRCU-protected structure. @@ -136,22 +139,12 @@ void srcu_read_unlock(struct srcu_struct *sp, int idx) per_cpu_ptr(sp->per_cpu_ref, smp_processor_id())->c[idx]--; preempt_enable(); } +EXPORT_SYMBOL_GPL(srcu_read_unlock); -/** - * synchronize_srcu - wait for prior SRCU read-side critical-section completion - * @sp: srcu_struct with which to synchronize. - * - * Flip the completed counter, and wait for the old count to drain to zero. - * As with classic RCU, the updater must use some separate means of - * synchronizing concurrent updates. Can block; must be called from - * process context. - * - * Note that it is illegal to call synchornize_srcu() from the corresponding - * SRCU read-side critical section; doing so will result in deadlock. - * However, it is perfectly legal to call synchronize_srcu() on one - * srcu_struct from some other srcu_struct's read-side critical section. +/* + * Helper function for synchronize_srcu() and synchronize_srcu_expedited(). */ -void synchronize_srcu(struct srcu_struct *sp) +void __synchronize_srcu(struct srcu_struct *sp, void (*sync_func)(void)) { int idx; @@ -173,7 +166,7 @@ void synchronize_srcu(struct srcu_struct *sp) return; } - synchronize_sched(); /* Force memory barrier on all CPUs. */ + sync_func(); /* Force memory barrier on all CPUs. */ /* * The preceding synchronize_sched() ensures that any CPU that @@ -190,7 +183,7 @@ void synchronize_srcu(struct srcu_struct *sp) idx = sp->completed & 0x1; sp->completed++; - synchronize_sched(); /* Force memory barrier on all CPUs. */ + sync_func(); /* Force memory barrier on all CPUs. */ /* * At this point, because of the preceding synchronize_sched(), @@ -203,7 +196,7 @@ void synchronize_srcu(struct srcu_struct *sp) while (srcu_readers_active_idx(sp, idx)) schedule_timeout_interruptible(1); - synchronize_sched(); /* Force memory barrier on all CPUs. */ + sync_func(); /* Force memory barrier on all CPUs. */ /* * The preceding synchronize_sched() forces all srcu_read_unlock() @@ -237,6 +230,47 @@ void synchronize_srcu(struct srcu_struct *sp) } /** + * synchronize_srcu - wait for prior SRCU read-side critical-section completion + * @sp: srcu_struct with which to synchronize. + * + * Flip the completed counter, and wait for the old count to drain to zero. + * As with classic RCU, the updater must use some separate means of + * synchronizing concurrent updates. Can block; must be called from + * process context. + * + * Note that it is illegal to call synchronize_srcu() from the corresponding + * SRCU read-side critical section; doing so will result in deadlock. + * However, it is perfectly legal to call synchronize_srcu() on one + * srcu_struct from some other srcu_struct's read-side critical section. + */ +void synchronize_srcu(struct srcu_struct *sp) +{ + __synchronize_srcu(sp, synchronize_sched); +} +EXPORT_SYMBOL_GPL(synchronize_srcu); + +/** + * synchronize_srcu_expedited - like synchronize_srcu, but less patient + * @sp: srcu_struct with which to synchronize. + * + * Flip the completed counter, and wait for the old count to drain to zero. + * As with classic RCU, the updater must use some separate means of + * synchronizing concurrent updates. Can block; must be called from + * process context. + * + * Note that it is illegal to call synchronize_srcu_expedited() + * from the corresponding SRCU read-side critical section; doing so + * will result in deadlock. However, it is perfectly legal to call + * synchronize_srcu_expedited() on one srcu_struct from some other + * srcu_struct's read-side critical section. + */ +void synchronize_srcu_expedited(struct srcu_struct *sp) +{ + __synchronize_srcu(sp, synchronize_sched_expedited); +} +EXPORT_SYMBOL_GPL(synchronize_srcu_expedited); + +/** * srcu_batches_completed - return batches completed. * @sp: srcu_struct on which to report batch completion. * @@ -248,10 +282,4 @@ long srcu_batches_completed(struct srcu_struct *sp) { return sp->completed; } - -EXPORT_SYMBOL_GPL(init_srcu_struct); -EXPORT_SYMBOL_GPL(cleanup_srcu_struct); -EXPORT_SYMBOL_GPL(srcu_read_lock); -EXPORT_SYMBOL_GPL(srcu_read_unlock); -EXPORT_SYMBOL_GPL(synchronize_srcu); EXPORT_SYMBOL_GPL(srcu_batches_completed); diff --git a/kernel/sys.c b/kernel/sys.c index ce17760d9c51..9968c5fb55b9 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -911,16 +911,15 @@ change_okay: void do_sys_times(struct tms *tms) { - struct task_cputime cputime; - cputime_t cutime, cstime; + cputime_t tgutime, tgstime, cutime, cstime; - thread_group_cputime(current, &cputime); spin_lock_irq(¤t->sighand->siglock); + thread_group_times(current, &tgutime, &tgstime); cutime = current->signal->cutime; cstime = current->signal->cstime; spin_unlock_irq(¤t->sighand->siglock); - tms->tms_utime = cputime_to_clock_t(cputime.utime); - tms->tms_stime = cputime_to_clock_t(cputime.stime); + tms->tms_utime = cputime_to_clock_t(tgutime); + tms->tms_stime = cputime_to_clock_t(tgstime); tms->tms_cutime = cputime_to_clock_t(cutime); tms->tms_cstime = cputime_to_clock_t(cstime); } @@ -1338,16 +1337,14 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) { struct task_struct *t; unsigned long flags; - cputime_t utime, stime; - struct task_cputime cputime; + cputime_t tgutime, tgstime, utime, stime; unsigned long maxrss = 0; memset((char *) r, 0, sizeof *r); utime = stime = cputime_zero; if (who == RUSAGE_THREAD) { - utime = task_utime(current); - stime = task_stime(current); + task_times(current, &utime, &stime); accumulate_thread_rusage(p, r); maxrss = p->signal->maxrss; goto out; @@ -1373,9 +1370,9 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) break; case RUSAGE_SELF: - thread_group_cputime(p, &cputime); - utime = cputime_add(utime, cputime.utime); - stime = cputime_add(stime, cputime.stime); + thread_group_times(p, &tgutime, &tgstime); + utime = cputime_add(utime, tgutime); + stime = cputime_add(stime, tgstime); r->ru_nvcsw += p->signal->nvcsw; r->ru_nivcsw += p->signal->nivcsw; r->ru_minflt += p->signal->min_flt; diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index e06d0b8d1951..de5bf1448238 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -139,7 +139,6 @@ cond_syscall(sys_pciconfig_read); cond_syscall(sys_pciconfig_write); cond_syscall(sys_pciconfig_iobase); cond_syscall(sys32_ipc); -cond_syscall(sys32_sysctl); cond_syscall(ppc_rtas); cond_syscall(sys_spu_run); cond_syscall(sys_spu_create); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 0d949c517412..9327a26765c5 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -27,7 +27,6 @@ #include <linux/security.h> #include <linux/ctype.h> #include <linux/kmemcheck.h> -#include <linux/smp_lock.h> #include <linux/fs.h> #include <linux/init.h> #include <linux/kernel.h> @@ -36,6 +35,7 @@ #include <linux/sysrq.h> #include <linux/highuid.h> #include <linux/writeback.h> +#include <linux/ratelimit.h> #include <linux/hugetlb.h> #include <linux/initrd.h> #include <linux/key.h> @@ -60,7 +60,6 @@ #include <asm/io.h> #endif -static int deprecated_sysctl_warning(struct __sysctl_args *args); #if defined(CONFIG_SYSCTL) @@ -158,6 +157,8 @@ extern int no_unaligned_warning; extern int unaligned_dump_stack; #endif +extern struct ratelimit_state printk_ratelimit_state; + #ifdef CONFIG_RT_MUTEXES extern int max_lock_depth; #endif @@ -207,31 +208,26 @@ extern int lock_stat; static struct ctl_table root_table[] = { { - .ctl_name = CTL_KERN, .procname = "kernel", .mode = 0555, .child = kern_table, }, { - .ctl_name = CTL_VM, .procname = "vm", .mode = 0555, .child = vm_table, }, { - .ctl_name = CTL_FS, .procname = "fs", .mode = 0555, .child = fs_table, }, { - .ctl_name = CTL_DEBUG, .procname = "debug", .mode = 0555, .child = debug_table, }, { - .ctl_name = CTL_DEV, .procname = "dev", .mode = 0555, .child = dev_table, @@ -240,7 +236,7 @@ static struct ctl_table root_table[] = { * NOTE: do not add new entries to this table unless you have read * Documentation/sysctl/ctl_unnumbered.txt */ - { .ctl_name = 0 } + { } }; #ifdef CONFIG_SCHED_DEBUG @@ -252,192 +248,166 @@ static int max_wakeup_granularity_ns = NSEC_PER_SEC; /* 1 second */ static struct ctl_table kern_table[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "sched_child_runs_first", .data = &sysctl_sched_child_runs_first, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #ifdef CONFIG_SCHED_DEBUG { - .ctl_name = CTL_UNNUMBERED, .procname = "sched_min_granularity_ns", .data = &sysctl_sched_min_granularity, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &sched_nr_latency_handler, - .strategy = &sysctl_intvec, + .proc_handler = sched_nr_latency_handler, .extra1 = &min_sched_granularity_ns, .extra2 = &max_sched_granularity_ns, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "sched_latency_ns", .data = &sysctl_sched_latency, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &sched_nr_latency_handler, - .strategy = &sysctl_intvec, + .proc_handler = sched_nr_latency_handler, .extra1 = &min_sched_granularity_ns, .extra2 = &max_sched_granularity_ns, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "sched_wakeup_granularity_ns", .data = &sysctl_sched_wakeup_granularity, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &min_wakeup_granularity_ns, .extra2 = &max_wakeup_granularity_ns, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "sched_shares_ratelimit", .data = &sysctl_sched_shares_ratelimit, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "sched_shares_thresh", .data = &sysctl_sched_shares_thresh, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "sched_features", .data = &sysctl_sched_features, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "sched_migration_cost", .data = &sysctl_sched_migration_cost, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "sched_nr_migrate", .data = &sysctl_sched_nr_migrate, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "sched_time_avg", .data = &sysctl_sched_time_avg, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "timer_migration", .data = &sysctl_timer_migration, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero, .extra2 = &one, }, #endif { - .ctl_name = CTL_UNNUMBERED, .procname = "sched_rt_period_us", .data = &sysctl_sched_rt_period, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &sched_rt_handler, + .proc_handler = sched_rt_handler, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "sched_rt_runtime_us", .data = &sysctl_sched_rt_runtime, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &sched_rt_handler, + .proc_handler = sched_rt_handler, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "sched_compat_yield", .data = &sysctl_sched_compat_yield, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #ifdef CONFIG_PROVE_LOCKING { - .ctl_name = CTL_UNNUMBERED, .procname = "prove_locking", .data = &prove_locking, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_LOCK_STAT { - .ctl_name = CTL_UNNUMBERED, .procname = "lock_stat", .data = &lock_stat, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif { - .ctl_name = KERN_PANIC, .procname = "panic", .data = &panic_timeout, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = KERN_CORE_USES_PID, .procname = "core_uses_pid", .data = &core_uses_pid, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = KERN_CORE_PATTERN, .procname = "core_pattern", .data = core_pattern, .maxlen = CORENAME_MAX_SIZE, .mode = 0644, - .proc_handler = &proc_dostring, - .strategy = &sysctl_string, + .proc_handler = proc_dostring, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "core_pipe_limit", .data = &core_pipe_limit, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #ifdef CONFIG_PROC_SYSCTL { .procname = "tainted", .maxlen = sizeof(long), .mode = 0644, - .proc_handler = &proc_taint, + .proc_handler = proc_taint, }, #endif #ifdef CONFIG_LATENCYTOP @@ -446,181 +416,160 @@ static struct ctl_table kern_table[] = { .data = &latencytop_enabled, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_BLK_DEV_INITRD { - .ctl_name = KERN_REALROOTDEV, .procname = "real-root-dev", .data = &real_root_dev, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif { - .ctl_name = CTL_UNNUMBERED, .procname = "print-fatal-signals", .data = &print_fatal_signals, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #ifdef CONFIG_SPARC { - .ctl_name = KERN_SPARC_REBOOT, .procname = "reboot-cmd", .data = reboot_command, .maxlen = 256, .mode = 0644, - .proc_handler = &proc_dostring, - .strategy = &sysctl_string, + .proc_handler = proc_dostring, }, { - .ctl_name = KERN_SPARC_STOP_A, .procname = "stop-a", .data = &stop_a_enabled, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = KERN_SPARC_SCONS_PWROFF, .procname = "scons-poweroff", .data = &scons_pwroff, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_SPARC64 { - .ctl_name = CTL_UNNUMBERED, .procname = "tsb-ratio", .data = &sysctl_tsb_ratio, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef __hppa__ { - .ctl_name = KERN_HPPA_PWRSW, .procname = "soft-power", .data = &pwrsw_enabled, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = KERN_HPPA_UNALIGNED, .procname = "unaligned-trap", .data = &unaligned_enabled, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif { - .ctl_name = KERN_CTLALTDEL, .procname = "ctrl-alt-del", .data = &C_A_D, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #ifdef CONFIG_FUNCTION_TRACER { - .ctl_name = CTL_UNNUMBERED, .procname = "ftrace_enabled", .data = &ftrace_enabled, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &ftrace_enable_sysctl, + .proc_handler = ftrace_enable_sysctl, }, #endif #ifdef CONFIG_STACK_TRACER { - .ctl_name = CTL_UNNUMBERED, .procname = "stack_tracer_enabled", .data = &stack_tracer_enabled, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &stack_trace_sysctl, + .proc_handler = stack_trace_sysctl, }, #endif #ifdef CONFIG_TRACING { - .ctl_name = CTL_UNNUMBERED, .procname = "ftrace_dump_on_oops", .data = &ftrace_dump_on_oops, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_MODULES { - .ctl_name = KERN_MODPROBE, .procname = "modprobe", .data = &modprobe_path, .maxlen = KMOD_PATH_LEN, .mode = 0644, - .proc_handler = &proc_dostring, - .strategy = &sysctl_string, + .proc_handler = proc_dostring, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "modules_disabled", .data = &modules_disabled, .maxlen = sizeof(int), .mode = 0644, /* only handle a transition from default "0" to "1" */ - .proc_handler = &proc_dointvec_minmax, + .proc_handler = proc_dointvec_minmax, .extra1 = &one, .extra2 = &one, }, #endif #if defined(CONFIG_HOTPLUG) && defined(CONFIG_NET) { - .ctl_name = KERN_HOTPLUG, .procname = "hotplug", .data = &uevent_helper, .maxlen = UEVENT_HELPER_PATH_LEN, .mode = 0644, - .proc_handler = &proc_dostring, - .strategy = &sysctl_string, + .proc_handler = proc_dostring, }, #endif #ifdef CONFIG_CHR_DEV_SG { - .ctl_name = KERN_SG_BIG_BUFF, .procname = "sg-big-buff", .data = &sg_big_buff, .maxlen = sizeof (int), .mode = 0444, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_BSD_PROCESS_ACCT { - .ctl_name = KERN_ACCT, .procname = "acct", .data = &acct_parm, .maxlen = 3*sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_MAGIC_SYSRQ { - .ctl_name = KERN_SYSRQ, .procname = "sysrq", .data = &__sysrq_enabled, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_PROC_SYSCTL @@ -629,215 +578,188 @@ static struct ctl_table kern_table[] = { .data = NULL, .maxlen = sizeof (int), .mode = 0600, - .proc_handler = &proc_do_cad_pid, + .proc_handler = proc_do_cad_pid, }, #endif { - .ctl_name = KERN_MAX_THREADS, .procname = "threads-max", .data = &max_threads, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = KERN_RANDOM, .procname = "random", .mode = 0555, .child = random_table, }, { - .ctl_name = KERN_OVERFLOWUID, .procname = "overflowuid", .data = &overflowuid, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &minolduid, .extra2 = &maxolduid, }, { - .ctl_name = KERN_OVERFLOWGID, .procname = "overflowgid", .data = &overflowgid, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &minolduid, .extra2 = &maxolduid, }, #ifdef CONFIG_S390 #ifdef CONFIG_MATHEMU { - .ctl_name = KERN_IEEE_EMULATION_WARNINGS, .procname = "ieee_emulation_warnings", .data = &sysctl_ieee_emulation_warnings, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif { - .ctl_name = KERN_S390_USER_DEBUG_LOGGING, .procname = "userprocess_debug", .data = &sysctl_userprocess_debug, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif { - .ctl_name = KERN_PIDMAX, .procname = "pid_max", .data = &pid_max, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &pid_max_min, .extra2 = &pid_max_max, }, { - .ctl_name = KERN_PANIC_ON_OOPS, .procname = "panic_on_oops", .data = &panic_on_oops, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #if defined CONFIG_PRINTK { - .ctl_name = KERN_PRINTK, .procname = "printk", .data = &console_loglevel, .maxlen = 4*sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = KERN_PRINTK_RATELIMIT, .procname = "printk_ratelimit", .data = &printk_ratelimit_state.interval, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = KERN_PRINTK_RATELIMIT_BURST, .procname = "printk_ratelimit_burst", .data = &printk_ratelimit_state.burst, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "printk_delay", .data = &printk_delay_msec, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero, .extra2 = &ten_thousand, }, #endif { - .ctl_name = KERN_NGROUPS_MAX, .procname = "ngroups_max", .data = &ngroups_max, .maxlen = sizeof (int), .mode = 0444, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86) { - .ctl_name = KERN_UNKNOWN_NMI_PANIC, .procname = "unknown_nmi_panic", .data = &unknown_nmi_panic, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .procname = "nmi_watchdog", .data = &nmi_watchdog_enabled, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_nmi_enabled, + .proc_handler = proc_nmi_enabled, }, #endif #if defined(CONFIG_X86) { - .ctl_name = KERN_PANIC_ON_NMI, .procname = "panic_on_unrecovered_nmi", .data = &panic_on_unrecovered_nmi, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "panic_on_io_nmi", .data = &panic_on_io_nmi, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = KERN_BOOTLOADER_TYPE, .procname = "bootloader_type", .data = &bootloader_type, .maxlen = sizeof (int), .mode = 0444, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "bootloader_version", .data = &bootloader_version, .maxlen = sizeof (int), .mode = 0444, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "kstack_depth_to_print", .data = &kstack_depth_to_print, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "io_delay_type", .data = &io_delay_type, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #if defined(CONFIG_MMU) { - .ctl_name = KERN_RANDOMIZE, .procname = "randomize_va_space", .data = &randomize_va_space, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #if defined(CONFIG_S390) && defined(CONFIG_SMP) { - .ctl_name = KERN_SPIN_RETRY, .procname = "spin_retry", .data = &spin_retry, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #if defined(CONFIG_ACPI_SLEEP) && defined(CONFIG_X86) @@ -846,123 +768,104 @@ static struct ctl_table kern_table[] = { .data = &acpi_realmode_flags, .maxlen = sizeof (unsigned long), .mode = 0644, - .proc_handler = &proc_doulongvec_minmax, + .proc_handler = proc_doulongvec_minmax, }, #endif #ifdef CONFIG_IA64 { - .ctl_name = KERN_IA64_UNALIGNED, .procname = "ignore-unaligned-usertrap", .data = &no_unaligned_warning, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "unaligned-dump-stack", .data = &unaligned_dump_stack, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_DETECT_SOFTLOCKUP { - .ctl_name = CTL_UNNUMBERED, .procname = "softlockup_panic", .data = &softlockup_panic, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero, .extra2 = &one, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "softlockup_thresh", .data = &softlockup_thresh, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dosoftlockup_thresh, - .strategy = &sysctl_intvec, + .proc_handler = proc_dosoftlockup_thresh, .extra1 = &neg_one, .extra2 = &sixty, }, #endif #ifdef CONFIG_DETECT_HUNG_TASK { - .ctl_name = CTL_UNNUMBERED, .procname = "hung_task_panic", .data = &sysctl_hung_task_panic, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero, .extra2 = &one, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "hung_task_check_count", .data = &sysctl_hung_task_check_count, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &proc_doulongvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_doulongvec_minmax, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "hung_task_timeout_secs", .data = &sysctl_hung_task_timeout_secs, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &proc_dohung_task_timeout_secs, - .strategy = &sysctl_intvec, + .proc_handler = proc_dohung_task_timeout_secs, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "hung_task_warnings", .data = &sysctl_hung_task_warnings, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &proc_doulongvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_doulongvec_minmax, }, #endif #ifdef CONFIG_COMPAT { - .ctl_name = KERN_COMPAT_LOG, .procname = "compat-log", .data = &compat_log, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_RT_MUTEXES { - .ctl_name = KERN_MAX_LOCK_DEPTH, .procname = "max_lock_depth", .data = &max_lock_depth, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif { - .ctl_name = CTL_UNNUMBERED, .procname = "poweroff_cmd", .data = &poweroff_cmd, .maxlen = POWEROFF_CMD_PATH_LEN, .mode = 0644, - .proc_handler = &proc_dostring, - .strategy = &sysctl_string, + .proc_handler = proc_dostring, }, #ifdef CONFIG_KEYS { - .ctl_name = CTL_UNNUMBERED, .procname = "keys", .mode = 0555, .child = key_sysctls, @@ -970,17 +873,15 @@ static struct ctl_table kern_table[] = { #endif #ifdef CONFIG_RCU_TORTURE_TEST { - .ctl_name = CTL_UNNUMBERED, .procname = "rcutorture_runnable", .data = &rcutorture_runnable, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_SLOW_WORK { - .ctl_name = CTL_UNNUMBERED, .procname = "slow-work", .mode = 0555, .child = slow_work_sysctls, @@ -988,146 +889,127 @@ static struct ctl_table kern_table[] = { #endif #ifdef CONFIG_PERF_EVENTS { - .ctl_name = CTL_UNNUMBERED, .procname = "perf_event_paranoid", .data = &sysctl_perf_event_paranoid, .maxlen = sizeof(sysctl_perf_event_paranoid), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "perf_event_mlock_kb", .data = &sysctl_perf_event_mlock, .maxlen = sizeof(sysctl_perf_event_mlock), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "perf_event_max_sample_rate", .data = &sysctl_perf_event_sample_rate, .maxlen = sizeof(sysctl_perf_event_sample_rate), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_KMEMCHECK { - .ctl_name = CTL_UNNUMBERED, .procname = "kmemcheck", .data = &kmemcheck_enabled, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_BLOCK { - .ctl_name = CTL_UNNUMBERED, .procname = "blk_iopoll", .data = &blk_iopoll_enabled, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif /* * NOTE: do not add new entries to this table unless you have read * Documentation/sysctl/ctl_unnumbered.txt */ - { .ctl_name = 0 } + { } }; static struct ctl_table vm_table[] = { { - .ctl_name = VM_OVERCOMMIT_MEMORY, .procname = "overcommit_memory", .data = &sysctl_overcommit_memory, .maxlen = sizeof(sysctl_overcommit_memory), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = VM_PANIC_ON_OOM, .procname = "panic_on_oom", .data = &sysctl_panic_on_oom, .maxlen = sizeof(sysctl_panic_on_oom), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "oom_kill_allocating_task", .data = &sysctl_oom_kill_allocating_task, .maxlen = sizeof(sysctl_oom_kill_allocating_task), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "oom_dump_tasks", .data = &sysctl_oom_dump_tasks, .maxlen = sizeof(sysctl_oom_dump_tasks), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = VM_OVERCOMMIT_RATIO, .procname = "overcommit_ratio", .data = &sysctl_overcommit_ratio, .maxlen = sizeof(sysctl_overcommit_ratio), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = VM_PAGE_CLUSTER, .procname = "page-cluster", .data = &page_cluster, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = VM_DIRTY_BACKGROUND, .procname = "dirty_background_ratio", .data = &dirty_background_ratio, .maxlen = sizeof(dirty_background_ratio), .mode = 0644, - .proc_handler = &dirty_background_ratio_handler, - .strategy = &sysctl_intvec, + .proc_handler = dirty_background_ratio_handler, .extra1 = &zero, .extra2 = &one_hundred, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "dirty_background_bytes", .data = &dirty_background_bytes, .maxlen = sizeof(dirty_background_bytes), .mode = 0644, - .proc_handler = &dirty_background_bytes_handler, - .strategy = &sysctl_intvec, + .proc_handler = dirty_background_bytes_handler, .extra1 = &one_ul, }, { - .ctl_name = VM_DIRTY_RATIO, .procname = "dirty_ratio", .data = &vm_dirty_ratio, .maxlen = sizeof(vm_dirty_ratio), .mode = 0644, - .proc_handler = &dirty_ratio_handler, - .strategy = &sysctl_intvec, + .proc_handler = dirty_ratio_handler, .extra1 = &zero, .extra2 = &one_hundred, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "dirty_bytes", .data = &vm_dirty_bytes, .maxlen = sizeof(vm_dirty_bytes), .mode = 0644, - .proc_handler = &dirty_bytes_handler, - .strategy = &sysctl_intvec, + .proc_handler = dirty_bytes_handler, .extra1 = &dirty_bytes_min, }, { @@ -1135,31 +1017,28 @@ static struct ctl_table vm_table[] = { .data = &dirty_writeback_interval, .maxlen = sizeof(dirty_writeback_interval), .mode = 0644, - .proc_handler = &dirty_writeback_centisecs_handler, + .proc_handler = dirty_writeback_centisecs_handler, }, { .procname = "dirty_expire_centisecs", .data = &dirty_expire_interval, .maxlen = sizeof(dirty_expire_interval), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = VM_NR_PDFLUSH_THREADS, .procname = "nr_pdflush_threads", .data = &nr_pdflush_threads, .maxlen = sizeof nr_pdflush_threads, .mode = 0444 /* read-only*/, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = VM_SWAPPINESS, .procname = "swappiness", .data = &vm_swappiness, .maxlen = sizeof(vm_swappiness), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero, .extra2 = &one_hundred, }, @@ -1169,255 +1048,213 @@ static struct ctl_table vm_table[] = { .data = NULL, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &hugetlb_sysctl_handler, + .proc_handler = hugetlb_sysctl_handler, .extra1 = (void *)&hugetlb_zero, .extra2 = (void *)&hugetlb_infinity, }, { - .ctl_name = VM_HUGETLB_GROUP, .procname = "hugetlb_shm_group", .data = &sysctl_hugetlb_shm_group, .maxlen = sizeof(gid_t), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "hugepages_treat_as_movable", .data = &hugepages_treat_as_movable, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &hugetlb_treat_movable_handler, + .proc_handler = hugetlb_treat_movable_handler, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "nr_overcommit_hugepages", .data = NULL, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &hugetlb_overcommit_handler, + .proc_handler = hugetlb_overcommit_handler, .extra1 = (void *)&hugetlb_zero, .extra2 = (void *)&hugetlb_infinity, }, #endif { - .ctl_name = VM_LOWMEM_RESERVE_RATIO, .procname = "lowmem_reserve_ratio", .data = &sysctl_lowmem_reserve_ratio, .maxlen = sizeof(sysctl_lowmem_reserve_ratio), .mode = 0644, - .proc_handler = &lowmem_reserve_ratio_sysctl_handler, - .strategy = &sysctl_intvec, + .proc_handler = lowmem_reserve_ratio_sysctl_handler, }, { - .ctl_name = VM_DROP_PAGECACHE, .procname = "drop_caches", .data = &sysctl_drop_caches, .maxlen = sizeof(int), .mode = 0644, .proc_handler = drop_caches_sysctl_handler, - .strategy = &sysctl_intvec, }, { - .ctl_name = VM_MIN_FREE_KBYTES, .procname = "min_free_kbytes", .data = &min_free_kbytes, .maxlen = sizeof(min_free_kbytes), .mode = 0644, - .proc_handler = &min_free_kbytes_sysctl_handler, - .strategy = &sysctl_intvec, + .proc_handler = min_free_kbytes_sysctl_handler, .extra1 = &zero, }, { - .ctl_name = VM_PERCPU_PAGELIST_FRACTION, .procname = "percpu_pagelist_fraction", .data = &percpu_pagelist_fraction, .maxlen = sizeof(percpu_pagelist_fraction), .mode = 0644, - .proc_handler = &percpu_pagelist_fraction_sysctl_handler, - .strategy = &sysctl_intvec, + .proc_handler = percpu_pagelist_fraction_sysctl_handler, .extra1 = &min_percpu_pagelist_fract, }, #ifdef CONFIG_MMU { - .ctl_name = VM_MAX_MAP_COUNT, .procname = "max_map_count", .data = &sysctl_max_map_count, .maxlen = sizeof(sysctl_max_map_count), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, #else { - .ctl_name = CTL_UNNUMBERED, .procname = "nr_trim_pages", .data = &sysctl_nr_trim_pages, .maxlen = sizeof(sysctl_nr_trim_pages), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero, }, #endif { - .ctl_name = VM_LAPTOP_MODE, .procname = "laptop_mode", .data = &laptop_mode, .maxlen = sizeof(laptop_mode), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = VM_BLOCK_DUMP, .procname = "block_dump", .data = &block_dump, .maxlen = sizeof(block_dump), .mode = 0644, - .proc_handler = &proc_dointvec, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec, .extra1 = &zero, }, { - .ctl_name = VM_VFS_CACHE_PRESSURE, .procname = "vfs_cache_pressure", .data = &sysctl_vfs_cache_pressure, .maxlen = sizeof(sysctl_vfs_cache_pressure), .mode = 0644, - .proc_handler = &proc_dointvec, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec, .extra1 = &zero, }, #ifdef HAVE_ARCH_PICK_MMAP_LAYOUT { - .ctl_name = VM_LEGACY_VA_LAYOUT, .procname = "legacy_va_layout", .data = &sysctl_legacy_va_layout, .maxlen = sizeof(sysctl_legacy_va_layout), .mode = 0644, - .proc_handler = &proc_dointvec, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec, .extra1 = &zero, }, #endif #ifdef CONFIG_NUMA { - .ctl_name = VM_ZONE_RECLAIM_MODE, .procname = "zone_reclaim_mode", .data = &zone_reclaim_mode, .maxlen = sizeof(zone_reclaim_mode), .mode = 0644, - .proc_handler = &proc_dointvec, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec, .extra1 = &zero, }, { - .ctl_name = VM_MIN_UNMAPPED, .procname = "min_unmapped_ratio", .data = &sysctl_min_unmapped_ratio, .maxlen = sizeof(sysctl_min_unmapped_ratio), .mode = 0644, - .proc_handler = &sysctl_min_unmapped_ratio_sysctl_handler, - .strategy = &sysctl_intvec, + .proc_handler = sysctl_min_unmapped_ratio_sysctl_handler, .extra1 = &zero, .extra2 = &one_hundred, }, { - .ctl_name = VM_MIN_SLAB, .procname = "min_slab_ratio", .data = &sysctl_min_slab_ratio, .maxlen = sizeof(sysctl_min_slab_ratio), .mode = 0644, - .proc_handler = &sysctl_min_slab_ratio_sysctl_handler, - .strategy = &sysctl_intvec, + .proc_handler = sysctl_min_slab_ratio_sysctl_handler, .extra1 = &zero, .extra2 = &one_hundred, }, #endif #ifdef CONFIG_SMP { - .ctl_name = CTL_UNNUMBERED, .procname = "stat_interval", .data = &sysctl_stat_interval, .maxlen = sizeof(sysctl_stat_interval), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, }, #endif { - .ctl_name = CTL_UNNUMBERED, .procname = "mmap_min_addr", .data = &dac_mmap_min_addr, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &mmap_min_addr_handler, + .proc_handler = mmap_min_addr_handler, }, #ifdef CONFIG_NUMA { - .ctl_name = CTL_UNNUMBERED, .procname = "numa_zonelist_order", .data = &numa_zonelist_order, .maxlen = NUMA_ZONELIST_ORDER_LEN, .mode = 0644, - .proc_handler = &numa_zonelist_order_handler, - .strategy = &sysctl_string, + .proc_handler = numa_zonelist_order_handler, }, #endif #if (defined(CONFIG_X86_32) && !defined(CONFIG_UML))|| \ (defined(CONFIG_SUPERH) && defined(CONFIG_VSYSCALL)) { - .ctl_name = VM_VDSO_ENABLED, .procname = "vdso_enabled", .data = &vdso_enabled, .maxlen = sizeof(vdso_enabled), .mode = 0644, - .proc_handler = &proc_dointvec, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec, .extra1 = &zero, }, #endif #ifdef CONFIG_HIGHMEM { - .ctl_name = CTL_UNNUMBERED, .procname = "highmem_is_dirtyable", .data = &vm_highmem_is_dirtyable, .maxlen = sizeof(vm_highmem_is_dirtyable), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero, .extra2 = &one, }, #endif { - .ctl_name = CTL_UNNUMBERED, .procname = "scan_unevictable_pages", .data = &scan_unevictable_pages, .maxlen = sizeof(scan_unevictable_pages), .mode = 0644, - .proc_handler = &scan_unevictable_handler, + .proc_handler = scan_unevictable_handler, }, #ifdef CONFIG_MEMORY_FAILURE { - .ctl_name = CTL_UNNUMBERED, .procname = "memory_failure_early_kill", .data = &sysctl_memory_failure_early_kill, .maxlen = sizeof(sysctl_memory_failure_early_kill), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero, .extra2 = &one, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "memory_failure_recovery", .data = &sysctl_memory_failure_recovery, .maxlen = sizeof(sysctl_memory_failure_recovery), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero, .extra2 = &one, }, @@ -1427,116 +1264,104 @@ static struct ctl_table vm_table[] = { * NOTE: do not add new entries to this table unless you have read * Documentation/sysctl/ctl_unnumbered.txt */ - { .ctl_name = 0 } + { } }; #if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE) static struct ctl_table binfmt_misc_table[] = { - { .ctl_name = 0 } + { } }; #endif static struct ctl_table fs_table[] = { { - .ctl_name = FS_NRINODE, .procname = "inode-nr", .data = &inodes_stat, .maxlen = 2*sizeof(int), .mode = 0444, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = FS_STATINODE, .procname = "inode-state", .data = &inodes_stat, .maxlen = 7*sizeof(int), .mode = 0444, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .procname = "file-nr", .data = &files_stat, .maxlen = 3*sizeof(int), .mode = 0444, - .proc_handler = &proc_nr_files, + .proc_handler = proc_nr_files, }, { - .ctl_name = FS_MAXFILE, .procname = "file-max", .data = &files_stat.max_files, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "nr_open", .data = &sysctl_nr_open, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, + .proc_handler = proc_dointvec_minmax, .extra1 = &sysctl_nr_open_min, .extra2 = &sysctl_nr_open_max, }, { - .ctl_name = FS_DENTRY, .procname = "dentry-state", .data = &dentry_stat, .maxlen = 6*sizeof(int), .mode = 0444, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = FS_OVERFLOWUID, .procname = "overflowuid", .data = &fs_overflowuid, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &minolduid, .extra2 = &maxolduid, }, { - .ctl_name = FS_OVERFLOWGID, .procname = "overflowgid", .data = &fs_overflowgid, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &minolduid, .extra2 = &maxolduid, }, #ifdef CONFIG_FILE_LOCKING { - .ctl_name = FS_LEASES, .procname = "leases-enable", .data = &leases_enable, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_DNOTIFY { - .ctl_name = FS_DIR_NOTIFY, .procname = "dir-notify-enable", .data = &dir_notify_enable, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_MMU #ifdef CONFIG_FILE_LOCKING { - .ctl_name = FS_LEASE_TIME, .procname = "lease-break-time", .data = &lease_break_time, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_AIO @@ -1545,19 +1370,18 @@ static struct ctl_table fs_table[] = { .data = &aio_nr, .maxlen = sizeof(aio_nr), .mode = 0444, - .proc_handler = &proc_doulongvec_minmax, + .proc_handler = proc_doulongvec_minmax, }, { .procname = "aio-max-nr", .data = &aio_max_nr, .maxlen = sizeof(aio_max_nr), .mode = 0644, - .proc_handler = &proc_doulongvec_minmax, + .proc_handler = proc_doulongvec_minmax, }, #endif /* CONFIG_AIO */ #ifdef CONFIG_INOTIFY_USER { - .ctl_name = FS_INOTIFY, .procname = "inotify", .mode = 0555, .child = inotify_table, @@ -1572,19 +1396,16 @@ static struct ctl_table fs_table[] = { #endif #endif { - .ctl_name = KERN_SETUID_DUMPABLE, .procname = "suid_dumpable", .data = &suid_dumpable, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero, .extra2 = &two, }, #if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE) { - .ctl_name = CTL_UNNUMBERED, .procname = "binfmt_misc", .mode = 0555, .child = binfmt_misc_table, @@ -1594,13 +1415,12 @@ static struct ctl_table fs_table[] = { * NOTE: do not add new entries to this table unless you have read * Documentation/sysctl/ctl_unnumbered.txt */ - { .ctl_name = 0 } + { } }; static struct ctl_table debug_table[] = { #if defined(CONFIG_X86) || defined(CONFIG_PPC) { - .ctl_name = CTL_UNNUMBERED, .procname = "exception-trace", .data = &show_unhandled_signals, .maxlen = sizeof(int), @@ -1608,11 +1428,11 @@ static struct ctl_table debug_table[] = { .proc_handler = proc_dointvec }, #endif - { .ctl_name = 0 } + { } }; static struct ctl_table dev_table[] = { - { .ctl_name = 0 } + { } }; static DEFINE_SPINLOCK(sysctl_lock); @@ -1766,122 +1586,6 @@ void register_sysctl_root(struct ctl_table_root *root) spin_unlock(&sysctl_lock); } -#ifdef CONFIG_SYSCTL_SYSCALL -/* Perform the actual read/write of a sysctl table entry. */ -static int do_sysctl_strategy(struct ctl_table_root *root, - struct ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - int op = 0, rc; - - if (oldval) - op |= MAY_READ; - if (newval) - op |= MAY_WRITE; - if (sysctl_perm(root, table, op)) - return -EPERM; - - if (table->strategy) { - rc = table->strategy(table, oldval, oldlenp, newval, newlen); - if (rc < 0) - return rc; - if (rc > 0) - return 0; - } - - /* If there is no strategy routine, or if the strategy returns - * zero, proceed with automatic r/w */ - if (table->data && table->maxlen) { - rc = sysctl_data(table, oldval, oldlenp, newval, newlen); - if (rc < 0) - return rc; - } - return 0; -} - -static int parse_table(int __user *name, int nlen, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen, - struct ctl_table_root *root, - struct ctl_table *table) -{ - int n; -repeat: - if (!nlen) - return -ENOTDIR; - if (get_user(n, name)) - return -EFAULT; - for ( ; table->ctl_name || table->procname; table++) { - if (!table->ctl_name) - continue; - if (n == table->ctl_name) { - int error; - if (table->child) { - if (sysctl_perm(root, table, MAY_EXEC)) - return -EPERM; - name++; - nlen--; - table = table->child; - goto repeat; - } - error = do_sysctl_strategy(root, table, - oldval, oldlenp, - newval, newlen); - return error; - } - } - return -ENOTDIR; -} - -int do_sysctl(int __user *name, int nlen, void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - struct ctl_table_header *head; - int error = -ENOTDIR; - - if (nlen <= 0 || nlen >= CTL_MAXNAME) - return -ENOTDIR; - if (oldval) { - int old_len; - if (!oldlenp || get_user(old_len, oldlenp)) - return -EFAULT; - } - - for (head = sysctl_head_next(NULL); head; - head = sysctl_head_next(head)) { - error = parse_table(name, nlen, oldval, oldlenp, - newval, newlen, - head->root, head->ctl_table); - if (error != -ENOTDIR) { - sysctl_head_finish(head); - break; - } - } - return error; -} - -SYSCALL_DEFINE1(sysctl, struct __sysctl_args __user *, args) -{ - struct __sysctl_args tmp; - int error; - - if (copy_from_user(&tmp, args, sizeof(tmp))) - return -EFAULT; - - error = deprecated_sysctl_warning(&tmp); - if (error) - goto out; - - lock_kernel(); - error = do_sysctl(tmp.name, tmp.nlen, tmp.oldval, tmp.oldlenp, - tmp.newval, tmp.newlen); - unlock_kernel(); -out: - return error; -} -#endif /* CONFIG_SYSCTL_SYSCALL */ - /* * sysctl_perm does NOT grant the superuser all rights automatically, because * some sysctl variables are readonly even to root. @@ -1917,7 +1621,7 @@ int sysctl_perm(struct ctl_table_root *root, struct ctl_table *table, int op) static void sysctl_set_parent(struct ctl_table *parent, struct ctl_table *table) { - for (; table->ctl_name || table->procname; table++) { + for (; table->procname; table++) { table->parent = parent; if (table->child) sysctl_set_parent(table, table->child); @@ -1949,11 +1653,11 @@ static struct ctl_table *is_branch_in(struct ctl_table *branch, return NULL; /* ... and nothing else */ - if (branch[1].procname || branch[1].ctl_name) + if (branch[1].procname) return NULL; /* table should contain subdirectory with the same name */ - for (p = table; p->procname || p->ctl_name; p++) { + for (p = table; p->procname; p++) { if (!p->child) continue; if (p->procname && strcmp(p->procname, s) == 0) @@ -1998,9 +1702,6 @@ static void try_attach(struct ctl_table_header *p, struct ctl_table_header *q) * * The members of the &struct ctl_table structure are used as follows: * - * ctl_name - This is the numeric sysctl value used by sysctl(2). The number - * must be unique within that level of sysctl - * * procname - the name of the sysctl file under /proc/sys. Set to %NULL to not * enter a sysctl file * @@ -2015,8 +1716,6 @@ static void try_attach(struct ctl_table_header *p, struct ctl_table_header *q) * * proc_handler - the text handler routine (described below) * - * strategy - the strategy routine (described below) - * * de - for internal use by the sysctl routines * * extra1, extra2 - extra pointers usable by the proc handler routines @@ -2029,19 +1728,6 @@ static void try_attach(struct ctl_table_header *p, struct ctl_table_header *q) * struct enable minimal validation of the values being written to be * performed, and the mode field allows minimal authentication. * - * More sophisticated management can be enabled by the provision of a - * strategy routine with the table entry. This will be called before - * any automatic read or write of the data is performed. - * - * The strategy routine may return - * - * < 0 - Error occurred (error is passed to user process) - * - * 0 - OK - proceed with automatic read or write. - * - * > 0 - OK - read or write has been done by the strategy routine, so - * return immediately. - * * There must be a proc_handler routine for any terminal nodes * mirrored under /proc/sys (non-terminals are handled by a built-in * directory handler). Several default handlers are available to @@ -2068,13 +1754,13 @@ struct ctl_table_header *__register_sysctl_paths( struct ctl_table_set *set; /* Count the path components */ - for (npath = 0; path[npath].ctl_name || path[npath].procname; ++npath) + for (npath = 0; path[npath].procname; ++npath) ; /* * For each path component, allocate a 2-element ctl_table array. * The first array element will be filled with the sysctl entry - * for this, the second will be the sentinel (ctl_name == 0). + * for this, the second will be the sentinel (procname == 0). * * We allocate everything in one go so that we don't have to * worry about freeing additional memory in unregister_sysctl_table. @@ -2091,7 +1777,6 @@ struct ctl_table_header *__register_sysctl_paths( for (n = 0; n < npath; ++n, ++path) { /* Copy the procname */ new->procname = path->procname; - new->ctl_name = path->ctl_name; new->mode = 0555; *prevp = new; @@ -2953,286 +2638,6 @@ int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write, #endif /* CONFIG_PROC_FS */ - -#ifdef CONFIG_SYSCTL_SYSCALL -/* - * General sysctl support routines - */ - -/* The generic sysctl data routine (used if no strategy routine supplied) */ -int sysctl_data(struct ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - size_t len; - - /* Get out of I don't have a variable */ - if (!table->data || !table->maxlen) - return -ENOTDIR; - - if (oldval && oldlenp) { - if (get_user(len, oldlenp)) - return -EFAULT; - if (len) { - if (len > table->maxlen) - len = table->maxlen; - if (copy_to_user(oldval, table->data, len)) - return -EFAULT; - if (put_user(len, oldlenp)) - return -EFAULT; - } - } - - if (newval && newlen) { - if (newlen > table->maxlen) - newlen = table->maxlen; - - if (copy_from_user(table->data, newval, newlen)) - return -EFAULT; - } - return 1; -} - -/* The generic string strategy routine: */ -int sysctl_string(struct ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - if (!table->data || !table->maxlen) - return -ENOTDIR; - - if (oldval && oldlenp) { - size_t bufsize; - if (get_user(bufsize, oldlenp)) - return -EFAULT; - if (bufsize) { - size_t len = strlen(table->data), copied; - - /* This shouldn't trigger for a well-formed sysctl */ - if (len > table->maxlen) - len = table->maxlen; - - /* Copy up to a max of bufsize-1 bytes of the string */ - copied = (len >= bufsize) ? bufsize - 1 : len; - - if (copy_to_user(oldval, table->data, copied) || - put_user(0, (char __user *)(oldval + copied))) - return -EFAULT; - if (put_user(len, oldlenp)) - return -EFAULT; - } - } - if (newval && newlen) { - size_t len = newlen; - if (len > table->maxlen) - len = table->maxlen; - if(copy_from_user(table->data, newval, len)) - return -EFAULT; - if (len == table->maxlen) - len--; - ((char *) table->data)[len] = 0; - } - return 1; -} - -/* - * This function makes sure that all of the integers in the vector - * are between the minimum and maximum values given in the arrays - * table->extra1 and table->extra2, respectively. - */ -int sysctl_intvec(struct ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - - if (newval && newlen) { - int __user *vec = (int __user *) newval; - int *min = (int *) table->extra1; - int *max = (int *) table->extra2; - size_t length; - int i; - - if (newlen % sizeof(int) != 0) - return -EINVAL; - - if (!table->extra1 && !table->extra2) - return 0; - - if (newlen > table->maxlen) - newlen = table->maxlen; - length = newlen / sizeof(int); - - for (i = 0; i < length; i++) { - int value; - if (get_user(value, vec + i)) - return -EFAULT; - if (min && value < min[i]) - return -EINVAL; - if (max && value > max[i]) - return -EINVAL; - } - } - return 0; -} - -/* Strategy function to convert jiffies to seconds */ -int sysctl_jiffies(struct ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - if (oldval && oldlenp) { - size_t olen; - - if (get_user(olen, oldlenp)) - return -EFAULT; - if (olen) { - int val; - - if (olen < sizeof(int)) - return -EINVAL; - - val = *(int *)(table->data) / HZ; - if (put_user(val, (int __user *)oldval)) - return -EFAULT; - if (put_user(sizeof(int), oldlenp)) - return -EFAULT; - } - } - if (newval && newlen) { - int new; - if (newlen != sizeof(int)) - return -EINVAL; - if (get_user(new, (int __user *)newval)) - return -EFAULT; - *(int *)(table->data) = new*HZ; - } - return 1; -} - -/* Strategy function to convert jiffies to seconds */ -int sysctl_ms_jiffies(struct ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - if (oldval && oldlenp) { - size_t olen; - - if (get_user(olen, oldlenp)) - return -EFAULT; - if (olen) { - int val; - - if (olen < sizeof(int)) - return -EINVAL; - - val = jiffies_to_msecs(*(int *)(table->data)); - if (put_user(val, (int __user *)oldval)) - return -EFAULT; - if (put_user(sizeof(int), oldlenp)) - return -EFAULT; - } - } - if (newval && newlen) { - int new; - if (newlen != sizeof(int)) - return -EINVAL; - if (get_user(new, (int __user *)newval)) - return -EFAULT; - *(int *)(table->data) = msecs_to_jiffies(new); - } - return 1; -} - - - -#else /* CONFIG_SYSCTL_SYSCALL */ - - -SYSCALL_DEFINE1(sysctl, struct __sysctl_args __user *, args) -{ - struct __sysctl_args tmp; - int error; - - if (copy_from_user(&tmp, args, sizeof(tmp))) - return -EFAULT; - - error = deprecated_sysctl_warning(&tmp); - - /* If no error reading the parameters then just -ENOSYS ... */ - if (!error) - error = -ENOSYS; - - return error; -} - -int sysctl_data(struct ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - return -ENOSYS; -} - -int sysctl_string(struct ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - return -ENOSYS; -} - -int sysctl_intvec(struct ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - return -ENOSYS; -} - -int sysctl_jiffies(struct ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - return -ENOSYS; -} - -int sysctl_ms_jiffies(struct ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - return -ENOSYS; -} - -#endif /* CONFIG_SYSCTL_SYSCALL */ - -static int deprecated_sysctl_warning(struct __sysctl_args *args) -{ - static int msg_count; - int name[CTL_MAXNAME]; - int i; - - /* Check args->nlen. */ - if (args->nlen < 0 || args->nlen > CTL_MAXNAME) - return -ENOTDIR; - - /* Read in the sysctl name for better debug message logging */ - for (i = 0; i < args->nlen; i++) - if (get_user(name[i], args->name + i)) - return -EFAULT; - - /* Ignore accesses to kernel.version */ - if ((args->nlen == 2) && (name[0] == CTL_KERN) && (name[1] == KERN_VERSION)) - return 0; - - if (msg_count < 5) { - msg_count++; - printk(KERN_INFO - "warning: process `%s' used the deprecated sysctl " - "system call with ", current->comm); - for (i = 0; i < args->nlen; i++) - printk("%d.", name[i]); - printk("\n"); - } - return 0; -} - /* * No sense putting this after each symbol definition, twice, * exception granted :-) @@ -3247,9 +2652,4 @@ EXPORT_SYMBOL(proc_doulongvec_minmax); EXPORT_SYMBOL(proc_doulongvec_ms_jiffies_minmax); EXPORT_SYMBOL(register_sysctl_table); EXPORT_SYMBOL(register_sysctl_paths); -EXPORT_SYMBOL(sysctl_intvec); -EXPORT_SYMBOL(sysctl_jiffies); -EXPORT_SYMBOL(sysctl_ms_jiffies); -EXPORT_SYMBOL(sysctl_string); -EXPORT_SYMBOL(sysctl_data); EXPORT_SYMBOL(unregister_sysctl_table); diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c new file mode 100644 index 000000000000..b75dbf40f573 --- /dev/null +++ b/kernel/sysctl_binary.c @@ -0,0 +1,1507 @@ +#include <linux/stat.h> +#include <linux/sysctl.h> +#include "../fs/xfs/linux-2.6/xfs_sysctl.h" +#include <linux/sunrpc/debug.h> +#include <linux/string.h> +#include <net/ip_vs.h> +#include <linux/syscalls.h> +#include <linux/namei.h> +#include <linux/mount.h> +#include <linux/fs.h> +#include <linux/nsproxy.h> +#include <linux/pid_namespace.h> +#include <linux/file.h> +#include <linux/ctype.h> +#include <linux/netdevice.h> + +#ifdef CONFIG_SYSCTL_SYSCALL + +struct bin_table; +typedef ssize_t bin_convert_t(struct file *file, + void __user *oldval, size_t oldlen, void __user *newval, size_t newlen); + +static bin_convert_t bin_dir; +static bin_convert_t bin_string; +static bin_convert_t bin_intvec; +static bin_convert_t bin_ulongvec; +static bin_convert_t bin_uuid; +static bin_convert_t bin_dn_node_address; + +#define CTL_DIR bin_dir +#define CTL_STR bin_string +#define CTL_INT bin_intvec +#define CTL_ULONG bin_ulongvec +#define CTL_UUID bin_uuid +#define CTL_DNADR bin_dn_node_address + +#define BUFSZ 256 + +struct bin_table { + bin_convert_t *convert; + int ctl_name; + const char *procname; + const struct bin_table *child; +}; + +static const struct bin_table bin_random_table[] = { + { CTL_INT, RANDOM_POOLSIZE, "poolsize" }, + { CTL_INT, RANDOM_ENTROPY_COUNT, "entropy_avail" }, + { CTL_INT, RANDOM_READ_THRESH, "read_wakeup_threshold" }, + { CTL_INT, RANDOM_WRITE_THRESH, "write_wakeup_threshold" }, + { CTL_UUID, RANDOM_BOOT_ID, "boot_id" }, + { CTL_UUID, RANDOM_UUID, "uuid" }, + {} +}; + +static const struct bin_table bin_pty_table[] = { + { CTL_INT, PTY_MAX, "max" }, + { CTL_INT, PTY_NR, "nr" }, + {} +}; + +static const struct bin_table bin_kern_table[] = { + { CTL_STR, KERN_OSTYPE, "ostype" }, + { CTL_STR, KERN_OSRELEASE, "osrelease" }, + /* KERN_OSREV not used */ + { CTL_STR, KERN_VERSION, "version" }, + /* KERN_SECUREMASK not used */ + /* KERN_PROF not used */ + { CTL_STR, KERN_NODENAME, "hostname" }, + { CTL_STR, KERN_DOMAINNAME, "domainname" }, + + { CTL_INT, KERN_PANIC, "panic" }, + { CTL_INT, KERN_REALROOTDEV, "real-root-dev" }, + + { CTL_STR, KERN_SPARC_REBOOT, "reboot-cmd" }, + { CTL_INT, KERN_CTLALTDEL, "ctrl-alt-del" }, + { CTL_INT, KERN_PRINTK, "printk" }, + + /* KERN_NAMETRANS not used */ + /* KERN_PPC_HTABRECLAIM not used */ + /* KERN_PPC_ZEROPAGED not used */ + { CTL_INT, KERN_PPC_POWERSAVE_NAP, "powersave-nap" }, + + { CTL_STR, KERN_MODPROBE, "modprobe" }, + { CTL_INT, KERN_SG_BIG_BUFF, "sg-big-buff" }, + { CTL_INT, KERN_ACCT, "acct" }, + /* KERN_PPC_L2CR "l2cr" no longer used */ + + /* KERN_RTSIGNR not used */ + /* KERN_RTSIGMAX not used */ + + { CTL_ULONG, KERN_SHMMAX, "shmmax" }, + { CTL_INT, KERN_MSGMAX, "msgmax" }, + { CTL_INT, KERN_MSGMNB, "msgmnb" }, + /* KERN_MSGPOOL not used*/ + { CTL_INT, KERN_SYSRQ, "sysrq" }, + { CTL_INT, KERN_MAX_THREADS, "threads-max" }, + { CTL_DIR, KERN_RANDOM, "random", bin_random_table }, + { CTL_ULONG, KERN_SHMALL, "shmall" }, + { CTL_INT, KERN_MSGMNI, "msgmni" }, + { CTL_INT, KERN_SEM, "sem" }, + { CTL_INT, KERN_SPARC_STOP_A, "stop-a" }, + { CTL_INT, KERN_SHMMNI, "shmmni" }, + + { CTL_INT, KERN_OVERFLOWUID, "overflowuid" }, + { CTL_INT, KERN_OVERFLOWGID, "overflowgid" }, + + { CTL_STR, KERN_HOTPLUG, "hotplug", }, + { CTL_INT, KERN_IEEE_EMULATION_WARNINGS, "ieee_emulation_warnings" }, + + { CTL_INT, KERN_S390_USER_DEBUG_LOGGING, "userprocess_debug" }, + { CTL_INT, KERN_CORE_USES_PID, "core_uses_pid" }, + /* KERN_TAINTED "tainted" no longer used */ + { CTL_INT, KERN_CADPID, "cad_pid" }, + { CTL_INT, KERN_PIDMAX, "pid_max" }, + { CTL_STR, KERN_CORE_PATTERN, "core_pattern" }, + { CTL_INT, KERN_PANIC_ON_OOPS, "panic_on_oops" }, + { CTL_INT, KERN_HPPA_PWRSW, "soft-power" }, + { CTL_INT, KERN_HPPA_UNALIGNED, "unaligned-trap" }, + + { CTL_INT, KERN_PRINTK_RATELIMIT, "printk_ratelimit" }, + { CTL_INT, KERN_PRINTK_RATELIMIT_BURST, "printk_ratelimit_burst" }, + + { CTL_DIR, KERN_PTY, "pty", bin_pty_table }, + { CTL_INT, KERN_NGROUPS_MAX, "ngroups_max" }, + { CTL_INT, KERN_SPARC_SCONS_PWROFF, "scons-poweroff" }, + /* KERN_HZ_TIMER "hz_timer" no longer used */ + { CTL_INT, KERN_UNKNOWN_NMI_PANIC, "unknown_nmi_panic" }, + { CTL_INT, KERN_BOOTLOADER_TYPE, "bootloader_type" }, + { CTL_INT, KERN_RANDOMIZE, "randomize_va_space" }, + + { CTL_INT, KERN_SPIN_RETRY, "spin_retry" }, + /* KERN_ACPI_VIDEO_FLAGS "acpi_video_flags" no longer used */ + { CTL_INT, KERN_IA64_UNALIGNED, "ignore-unaligned-usertrap" }, + { CTL_INT, KERN_COMPAT_LOG, "compat-log" }, + { CTL_INT, KERN_MAX_LOCK_DEPTH, "max_lock_depth" }, + { CTL_INT, KERN_NMI_WATCHDOG, "nmi_watchdog" }, + { CTL_INT, KERN_PANIC_ON_NMI, "panic_on_unrecovered_nmi" }, + {} +}; + +static const struct bin_table bin_vm_table[] = { + { CTL_INT, VM_OVERCOMMIT_MEMORY, "overcommit_memory" }, + { CTL_INT, VM_PAGE_CLUSTER, "page-cluster" }, + { CTL_INT, VM_DIRTY_BACKGROUND, "dirty_background_ratio" }, + { CTL_INT, VM_DIRTY_RATIO, "dirty_ratio" }, + /* VM_DIRTY_WB_CS "dirty_writeback_centisecs" no longer used */ + /* VM_DIRTY_EXPIRE_CS "dirty_expire_centisecs" no longer used */ + { CTL_INT, VM_NR_PDFLUSH_THREADS, "nr_pdflush_threads" }, + { CTL_INT, VM_OVERCOMMIT_RATIO, "overcommit_ratio" }, + /* VM_PAGEBUF unused */ + /* VM_HUGETLB_PAGES "nr_hugepages" no longer used */ + { CTL_INT, VM_SWAPPINESS, "swappiness" }, + { CTL_INT, VM_LOWMEM_RESERVE_RATIO, "lowmem_reserve_ratio" }, + { CTL_INT, VM_MIN_FREE_KBYTES, "min_free_kbytes" }, + { CTL_INT, VM_MAX_MAP_COUNT, "max_map_count" }, + { CTL_INT, VM_LAPTOP_MODE, "laptop_mode" }, + { CTL_INT, VM_BLOCK_DUMP, "block_dump" }, + { CTL_INT, VM_HUGETLB_GROUP, "hugetlb_shm_group" }, + { CTL_INT, VM_VFS_CACHE_PRESSURE, "vfs_cache_pressure" }, + { CTL_INT, VM_LEGACY_VA_LAYOUT, "legacy_va_layout" }, + /* VM_SWAP_TOKEN_TIMEOUT unused */ + { CTL_INT, VM_DROP_PAGECACHE, "drop_caches" }, + { CTL_INT, VM_PERCPU_PAGELIST_FRACTION, "percpu_pagelist_fraction" }, + { CTL_INT, VM_ZONE_RECLAIM_MODE, "zone_reclaim_mode" }, + { CTL_INT, VM_MIN_UNMAPPED, "min_unmapped_ratio" }, + { CTL_INT, VM_PANIC_ON_OOM, "panic_on_oom" }, + { CTL_INT, VM_VDSO_ENABLED, "vdso_enabled" }, + { CTL_INT, VM_MIN_SLAB, "min_slab_ratio" }, + + {} +}; + +static const struct bin_table bin_net_core_table[] = { + { CTL_INT, NET_CORE_WMEM_MAX, "wmem_max" }, + { CTL_INT, NET_CORE_RMEM_MAX, "rmem_max" }, + { CTL_INT, NET_CORE_WMEM_DEFAULT, "wmem_default" }, + { CTL_INT, NET_CORE_RMEM_DEFAULT, "rmem_default" }, + /* NET_CORE_DESTROY_DELAY unused */ + { CTL_INT, NET_CORE_MAX_BACKLOG, "netdev_max_backlog" }, + /* NET_CORE_FASTROUTE unused */ + { CTL_INT, NET_CORE_MSG_COST, "message_cost" }, + { CTL_INT, NET_CORE_MSG_BURST, "message_burst" }, + { CTL_INT, NET_CORE_OPTMEM_MAX, "optmem_max" }, + /* NET_CORE_HOT_LIST_LENGTH unused */ + /* NET_CORE_DIVERT_VERSION unused */ + /* NET_CORE_NO_CONG_THRESH unused */ + /* NET_CORE_NO_CONG unused */ + /* NET_CORE_LO_CONG unused */ + /* NET_CORE_MOD_CONG unused */ + { CTL_INT, NET_CORE_DEV_WEIGHT, "dev_weight" }, + { CTL_INT, NET_CORE_SOMAXCONN, "somaxconn" }, + { CTL_INT, NET_CORE_BUDGET, "netdev_budget" }, + { CTL_INT, NET_CORE_AEVENT_ETIME, "xfrm_aevent_etime" }, + { CTL_INT, NET_CORE_AEVENT_RSEQTH, "xfrm_aevent_rseqth" }, + { CTL_INT, NET_CORE_WARNINGS, "warnings" }, + {}, +}; + +static const struct bin_table bin_net_unix_table[] = { + /* NET_UNIX_DESTROY_DELAY unused */ + /* NET_UNIX_DELETE_DELAY unused */ + { CTL_INT, NET_UNIX_MAX_DGRAM_QLEN, "max_dgram_qlen" }, + {} +}; + +static const struct bin_table bin_net_ipv4_route_table[] = { + { CTL_INT, NET_IPV4_ROUTE_FLUSH, "flush" }, + /* NET_IPV4_ROUTE_MIN_DELAY "min_delay" no longer used */ + /* NET_IPV4_ROUTE_MAX_DELAY "max_delay" no longer used */ + { CTL_INT, NET_IPV4_ROUTE_GC_THRESH, "gc_thresh" }, + { CTL_INT, NET_IPV4_ROUTE_MAX_SIZE, "max_size" }, + { CTL_INT, NET_IPV4_ROUTE_GC_MIN_INTERVAL, "gc_min_interval" }, + { CTL_INT, NET_IPV4_ROUTE_GC_MIN_INTERVAL_MS, "gc_min_interval_ms" }, + { CTL_INT, NET_IPV4_ROUTE_GC_TIMEOUT, "gc_timeout" }, + { CTL_INT, NET_IPV4_ROUTE_GC_INTERVAL, "gc_interval" }, + { CTL_INT, NET_IPV4_ROUTE_REDIRECT_LOAD, "redirect_load" }, + { CTL_INT, NET_IPV4_ROUTE_REDIRECT_NUMBER, "redirect_number" }, + { CTL_INT, NET_IPV4_ROUTE_REDIRECT_SILENCE, "redirect_silence" }, + { CTL_INT, NET_IPV4_ROUTE_ERROR_COST, "error_cost" }, + { CTL_INT, NET_IPV4_ROUTE_ERROR_BURST, "error_burst" }, + { CTL_INT, NET_IPV4_ROUTE_GC_ELASTICITY, "gc_elasticity" }, + { CTL_INT, NET_IPV4_ROUTE_MTU_EXPIRES, "mtu_expires" }, + { CTL_INT, NET_IPV4_ROUTE_MIN_PMTU, "min_pmtu" }, + { CTL_INT, NET_IPV4_ROUTE_MIN_ADVMSS, "min_adv_mss" }, + { CTL_INT, NET_IPV4_ROUTE_SECRET_INTERVAL, "secret_interval" }, + {} +}; + +static const struct bin_table bin_net_ipv4_conf_vars_table[] = { + { CTL_INT, NET_IPV4_CONF_FORWARDING, "forwarding" }, + { CTL_INT, NET_IPV4_CONF_MC_FORWARDING, "mc_forwarding" }, + + { CTL_INT, NET_IPV4_CONF_ACCEPT_REDIRECTS, "accept_redirects" }, + { CTL_INT, NET_IPV4_CONF_SECURE_REDIRECTS, "secure_redirects" }, + { CTL_INT, NET_IPV4_CONF_SEND_REDIRECTS, "send_redirects" }, + { CTL_INT, NET_IPV4_CONF_SHARED_MEDIA, "shared_media" }, + { CTL_INT, NET_IPV4_CONF_RP_FILTER, "rp_filter" }, + { CTL_INT, NET_IPV4_CONF_ACCEPT_SOURCE_ROUTE, "accept_source_route" }, + { CTL_INT, NET_IPV4_CONF_PROXY_ARP, "proxy_arp" }, + { CTL_INT, NET_IPV4_CONF_MEDIUM_ID, "medium_id" }, + { CTL_INT, NET_IPV4_CONF_BOOTP_RELAY, "bootp_relay" }, + { CTL_INT, NET_IPV4_CONF_LOG_MARTIANS, "log_martians" }, + { CTL_INT, NET_IPV4_CONF_TAG, "tag" }, + { CTL_INT, NET_IPV4_CONF_ARPFILTER, "arp_filter" }, + { CTL_INT, NET_IPV4_CONF_ARP_ANNOUNCE, "arp_announce" }, + { CTL_INT, NET_IPV4_CONF_ARP_IGNORE, "arp_ignore" }, + { CTL_INT, NET_IPV4_CONF_ARP_ACCEPT, "arp_accept" }, + { CTL_INT, NET_IPV4_CONF_ARP_NOTIFY, "arp_notify" }, + + { CTL_INT, NET_IPV4_CONF_NOXFRM, "disable_xfrm" }, + { CTL_INT, NET_IPV4_CONF_NOPOLICY, "disable_policy" }, + { CTL_INT, NET_IPV4_CONF_FORCE_IGMP_VERSION, "force_igmp_version" }, + { CTL_INT, NET_IPV4_CONF_PROMOTE_SECONDARIES, "promote_secondaries" }, + {} +}; + +static const struct bin_table bin_net_ipv4_conf_table[] = { + { CTL_DIR, NET_PROTO_CONF_ALL, "all", bin_net_ipv4_conf_vars_table }, + { CTL_DIR, NET_PROTO_CONF_DEFAULT, "default", bin_net_ipv4_conf_vars_table }, + { CTL_DIR, 0, NULL, bin_net_ipv4_conf_vars_table }, + {} +}; + +static const struct bin_table bin_net_neigh_vars_table[] = { + { CTL_INT, NET_NEIGH_MCAST_SOLICIT, "mcast_solicit" }, + { CTL_INT, NET_NEIGH_UCAST_SOLICIT, "ucast_solicit" }, + { CTL_INT, NET_NEIGH_APP_SOLICIT, "app_solicit" }, + /* NET_NEIGH_RETRANS_TIME "retrans_time" no longer used */ + { CTL_INT, NET_NEIGH_REACHABLE_TIME, "base_reachable_time" }, + { CTL_INT, NET_NEIGH_DELAY_PROBE_TIME, "delay_first_probe_time" }, + { CTL_INT, NET_NEIGH_GC_STALE_TIME, "gc_stale_time" }, + { CTL_INT, NET_NEIGH_UNRES_QLEN, "unres_qlen" }, + { CTL_INT, NET_NEIGH_PROXY_QLEN, "proxy_qlen" }, + /* NET_NEIGH_ANYCAST_DELAY "anycast_delay" no longer used */ + /* NET_NEIGH_PROXY_DELAY "proxy_delay" no longer used */ + /* NET_NEIGH_LOCKTIME "locktime" no longer used */ + { CTL_INT, NET_NEIGH_GC_INTERVAL, "gc_interval" }, + { CTL_INT, NET_NEIGH_GC_THRESH1, "gc_thresh1" }, + { CTL_INT, NET_NEIGH_GC_THRESH2, "gc_thresh2" }, + { CTL_INT, NET_NEIGH_GC_THRESH3, "gc_thresh3" }, + { CTL_INT, NET_NEIGH_RETRANS_TIME_MS, "retrans_time_ms" }, + { CTL_INT, NET_NEIGH_REACHABLE_TIME_MS, "base_reachable_time_ms" }, + {} +}; + +static const struct bin_table bin_net_neigh_table[] = { + { CTL_DIR, NET_PROTO_CONF_DEFAULT, "default", bin_net_neigh_vars_table }, + { CTL_DIR, 0, NULL, bin_net_neigh_vars_table }, + {} +}; + +static const struct bin_table bin_net_ipv4_netfilter_table[] = { + { CTL_INT, NET_IPV4_NF_CONNTRACK_MAX, "ip_conntrack_max" }, + + /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_SYN_SENT "ip_conntrack_tcp_timeout_syn_sent" no longer used */ + /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_SYN_RECV "ip_conntrack_tcp_timeout_syn_recv" no longer used */ + /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_ESTABLISHED "ip_conntrack_tcp_timeout_established" no longer used */ + /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_FIN_WAIT "ip_conntrack_tcp_timeout_fin_wait" no longer used */ + /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_CLOSE_WAIT "ip_conntrack_tcp_timeout_close_wait" no longer used */ + /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_LAST_ACK "ip_conntrack_tcp_timeout_last_ack" no longer used */ + /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_TIME_WAIT "ip_conntrack_tcp_timeout_time_wait" no longer used */ + /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_CLOSE "ip_conntrack_tcp_timeout_close" no longer used */ + + /* NET_IPV4_NF_CONNTRACK_UDP_TIMEOUT "ip_conntrack_udp_timeout" no longer used */ + /* NET_IPV4_NF_CONNTRACK_UDP_TIMEOUT_STREAM "ip_conntrack_udp_timeout_stream" no longer used */ + /* NET_IPV4_NF_CONNTRACK_ICMP_TIMEOUT "ip_conntrack_icmp_timeout" no longer used */ + /* NET_IPV4_NF_CONNTRACK_GENERIC_TIMEOUT "ip_conntrack_generic_timeout" no longer used */ + + { CTL_INT, NET_IPV4_NF_CONNTRACK_BUCKETS, "ip_conntrack_buckets" }, + { CTL_INT, NET_IPV4_NF_CONNTRACK_LOG_INVALID, "ip_conntrack_log_invalid" }, + /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_MAX_RETRANS "ip_conntrack_tcp_timeout_max_retrans" no longer used */ + { CTL_INT, NET_IPV4_NF_CONNTRACK_TCP_LOOSE, "ip_conntrack_tcp_loose" }, + { CTL_INT, NET_IPV4_NF_CONNTRACK_TCP_BE_LIBERAL, "ip_conntrack_tcp_be_liberal" }, + { CTL_INT, NET_IPV4_NF_CONNTRACK_TCP_MAX_RETRANS, "ip_conntrack_tcp_max_retrans" }, + + /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_CLOSED "ip_conntrack_sctp_timeout_closed" no longer used */ + /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_WAIT "ip_conntrack_sctp_timeout_cookie_wait" no longer used */ + /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_ECHOED "ip_conntrack_sctp_timeout_cookie_echoed" no longer used */ + /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_ESTABLISHED "ip_conntrack_sctp_timeout_established" no longer used */ + /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_SENT "ip_conntrack_sctp_timeout_shutdown_sent" no longer used */ + /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_RECD "ip_conntrack_sctp_timeout_shutdown_recd" no longer used */ + /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_ACK_SENT "ip_conntrack_sctp_timeout_shutdown_ack_sent" no longer used */ + + { CTL_INT, NET_IPV4_NF_CONNTRACK_COUNT, "ip_conntrack_count" }, + { CTL_INT, NET_IPV4_NF_CONNTRACK_CHECKSUM, "ip_conntrack_checksum" }, + {} +}; + +static const struct bin_table bin_net_ipv4_table[] = { + {CTL_INT, NET_IPV4_FORWARD, "ip_forward" }, + + { CTL_DIR, NET_IPV4_CONF, "conf", bin_net_ipv4_conf_table }, + { CTL_DIR, NET_IPV4_NEIGH, "neigh", bin_net_neigh_table }, + { CTL_DIR, NET_IPV4_ROUTE, "route", bin_net_ipv4_route_table }, + /* NET_IPV4_FIB_HASH unused */ + { CTL_DIR, NET_IPV4_NETFILTER, "netfilter", bin_net_ipv4_netfilter_table }, + + { CTL_INT, NET_IPV4_TCP_TIMESTAMPS, "tcp_timestamps" }, + { CTL_INT, NET_IPV4_TCP_WINDOW_SCALING, "tcp_window_scaling" }, + { CTL_INT, NET_IPV4_TCP_SACK, "tcp_sack" }, + { CTL_INT, NET_IPV4_TCP_RETRANS_COLLAPSE, "tcp_retrans_collapse" }, + { CTL_INT, NET_IPV4_DEFAULT_TTL, "ip_default_ttl" }, + /* NET_IPV4_AUTOCONFIG unused */ + { CTL_INT, NET_IPV4_NO_PMTU_DISC, "ip_no_pmtu_disc" }, + { CTL_INT, NET_IPV4_NONLOCAL_BIND, "ip_nonlocal_bind" }, + { CTL_INT, NET_IPV4_TCP_SYN_RETRIES, "tcp_syn_retries" }, + { CTL_INT, NET_TCP_SYNACK_RETRIES, "tcp_synack_retries" }, + { CTL_INT, NET_TCP_MAX_ORPHANS, "tcp_max_orphans" }, + { CTL_INT, NET_TCP_MAX_TW_BUCKETS, "tcp_max_tw_buckets" }, + { CTL_INT, NET_IPV4_DYNADDR, "ip_dynaddr" }, + { CTL_INT, NET_IPV4_TCP_KEEPALIVE_TIME, "tcp_keepalive_time" }, + { CTL_INT, NET_IPV4_TCP_KEEPALIVE_PROBES, "tcp_keepalive_probes" }, + { CTL_INT, NET_IPV4_TCP_KEEPALIVE_INTVL, "tcp_keepalive_intvl" }, + { CTL_INT, NET_IPV4_TCP_RETRIES1, "tcp_retries1" }, + { CTL_INT, NET_IPV4_TCP_RETRIES2, "tcp_retries2" }, + { CTL_INT, NET_IPV4_TCP_FIN_TIMEOUT, "tcp_fin_timeout" }, + { CTL_INT, NET_TCP_SYNCOOKIES, "tcp_syncookies" }, + { CTL_INT, NET_TCP_TW_RECYCLE, "tcp_tw_recycle" }, + { CTL_INT, NET_TCP_ABORT_ON_OVERFLOW, "tcp_abort_on_overflow" }, + { CTL_INT, NET_TCP_STDURG, "tcp_stdurg" }, + { CTL_INT, NET_TCP_RFC1337, "tcp_rfc1337" }, + { CTL_INT, NET_TCP_MAX_SYN_BACKLOG, "tcp_max_syn_backlog" }, + { CTL_INT, NET_IPV4_LOCAL_PORT_RANGE, "ip_local_port_range" }, + { CTL_INT, NET_IPV4_IGMP_MAX_MEMBERSHIPS, "igmp_max_memberships" }, + { CTL_INT, NET_IPV4_IGMP_MAX_MSF, "igmp_max_msf" }, + { CTL_INT, NET_IPV4_INET_PEER_THRESHOLD, "inet_peer_threshold" }, + { CTL_INT, NET_IPV4_INET_PEER_MINTTL, "inet_peer_minttl" }, + { CTL_INT, NET_IPV4_INET_PEER_MAXTTL, "inet_peer_maxttl" }, + { CTL_INT, NET_IPV4_INET_PEER_GC_MINTIME, "inet_peer_gc_mintime" }, + { CTL_INT, NET_IPV4_INET_PEER_GC_MAXTIME, "inet_peer_gc_maxtime" }, + { CTL_INT, NET_TCP_ORPHAN_RETRIES, "tcp_orphan_retries" }, + { CTL_INT, NET_TCP_FACK, "tcp_fack" }, + { CTL_INT, NET_TCP_REORDERING, "tcp_reordering" }, + { CTL_INT, NET_TCP_ECN, "tcp_ecn" }, + { CTL_INT, NET_TCP_DSACK, "tcp_dsack" }, + { CTL_INT, NET_TCP_MEM, "tcp_mem" }, + { CTL_INT, NET_TCP_WMEM, "tcp_wmem" }, + { CTL_INT, NET_TCP_RMEM, "tcp_rmem" }, + { CTL_INT, NET_TCP_APP_WIN, "tcp_app_win" }, + { CTL_INT, NET_TCP_ADV_WIN_SCALE, "tcp_adv_win_scale" }, + { CTL_INT, NET_TCP_TW_REUSE, "tcp_tw_reuse" }, + { CTL_INT, NET_TCP_FRTO, "tcp_frto" }, + { CTL_INT, NET_TCP_FRTO_RESPONSE, "tcp_frto_response" }, + { CTL_INT, NET_TCP_LOW_LATENCY, "tcp_low_latency" }, + { CTL_INT, NET_TCP_NO_METRICS_SAVE, "tcp_no_metrics_save" }, + { CTL_INT, NET_TCP_MODERATE_RCVBUF, "tcp_moderate_rcvbuf" }, + { CTL_INT, NET_TCP_TSO_WIN_DIVISOR, "tcp_tso_win_divisor" }, + { CTL_STR, NET_TCP_CONG_CONTROL, "tcp_congestion_control" }, + { CTL_INT, NET_TCP_ABC, "tcp_abc" }, + { CTL_INT, NET_TCP_MTU_PROBING, "tcp_mtu_probing" }, + { CTL_INT, NET_TCP_BASE_MSS, "tcp_base_mss" }, + { CTL_INT, NET_IPV4_TCP_WORKAROUND_SIGNED_WINDOWS, "tcp_workaround_signed_windows" }, + { CTL_INT, NET_TCP_DMA_COPYBREAK, "tcp_dma_copybreak" }, + { CTL_INT, NET_TCP_SLOW_START_AFTER_IDLE, "tcp_slow_start_after_idle" }, + { CTL_INT, NET_CIPSOV4_CACHE_ENABLE, "cipso_cache_enable" }, + { CTL_INT, NET_CIPSOV4_CACHE_BUCKET_SIZE, "cipso_cache_bucket_size" }, + { CTL_INT, NET_CIPSOV4_RBM_OPTFMT, "cipso_rbm_optfmt" }, + { CTL_INT, NET_CIPSOV4_RBM_STRICTVALID, "cipso_rbm_strictvalid" }, + /* NET_TCP_AVAIL_CONG_CONTROL "tcp_available_congestion_control" no longer used */ + { CTL_STR, NET_TCP_ALLOWED_CONG_CONTROL, "tcp_allowed_congestion_control" }, + { CTL_INT, NET_TCP_MAX_SSTHRESH, "tcp_max_ssthresh" }, + + { CTL_INT, NET_IPV4_ICMP_ECHO_IGNORE_ALL, "icmp_echo_ignore_all" }, + { CTL_INT, NET_IPV4_ICMP_ECHO_IGNORE_BROADCASTS, "icmp_echo_ignore_broadcasts" }, + { CTL_INT, NET_IPV4_ICMP_IGNORE_BOGUS_ERROR_RESPONSES, "icmp_ignore_bogus_error_responses" }, + { CTL_INT, NET_IPV4_ICMP_ERRORS_USE_INBOUND_IFADDR, "icmp_errors_use_inbound_ifaddr" }, + { CTL_INT, NET_IPV4_ICMP_RATELIMIT, "icmp_ratelimit" }, + { CTL_INT, NET_IPV4_ICMP_RATEMASK, "icmp_ratemask" }, + + { CTL_INT, NET_IPV4_IPFRAG_HIGH_THRESH, "ipfrag_high_thresh" }, + { CTL_INT, NET_IPV4_IPFRAG_LOW_THRESH, "ipfrag_low_thresh" }, + { CTL_INT, NET_IPV4_IPFRAG_TIME, "ipfrag_time" }, + + { CTL_INT, NET_IPV4_IPFRAG_SECRET_INTERVAL, "ipfrag_secret_interval" }, + /* NET_IPV4_IPFRAG_MAX_DIST "ipfrag_max_dist" no longer used */ + + { CTL_INT, 2088 /* NET_IPQ_QMAX */, "ip_queue_maxlen" }, + + /* NET_TCP_DEFAULT_WIN_SCALE unused */ + /* NET_TCP_BIC_BETA unused */ + /* NET_IPV4_TCP_MAX_KA_PROBES unused */ + /* NET_IPV4_IP_MASQ_DEBUG unused */ + /* NET_TCP_SYN_TAILDROP unused */ + /* NET_IPV4_ICMP_SOURCEQUENCH_RATE unused */ + /* NET_IPV4_ICMP_DESTUNREACH_RATE unused */ + /* NET_IPV4_ICMP_TIMEEXCEED_RATE unused */ + /* NET_IPV4_ICMP_PARAMPROB_RATE unused */ + /* NET_IPV4_ICMP_ECHOREPLY_RATE unused */ + /* NET_IPV4_ALWAYS_DEFRAG unused */ + {} +}; + +static const struct bin_table bin_net_ipx_table[] = { + { CTL_INT, NET_IPX_PPROP_BROADCASTING, "ipx_pprop_broadcasting" }, + /* NET_IPX_FORWARDING unused */ + {} +}; + +static const struct bin_table bin_net_atalk_table[] = { + { CTL_INT, NET_ATALK_AARP_EXPIRY_TIME, "aarp-expiry-time" }, + { CTL_INT, NET_ATALK_AARP_TICK_TIME, "aarp-tick-time" }, + { CTL_INT, NET_ATALK_AARP_RETRANSMIT_LIMIT, "aarp-retransmit-limit" }, + { CTL_INT, NET_ATALK_AARP_RESOLVE_TIME, "aarp-resolve-time" }, + {}, +}; + +static const struct bin_table bin_net_netrom_table[] = { + { CTL_INT, NET_NETROM_DEFAULT_PATH_QUALITY, "default_path_quality" }, + { CTL_INT, NET_NETROM_OBSOLESCENCE_COUNT_INITIALISER, "obsolescence_count_initialiser" }, + { CTL_INT, NET_NETROM_NETWORK_TTL_INITIALISER, "network_ttl_initialiser" }, + { CTL_INT, NET_NETROM_TRANSPORT_TIMEOUT, "transport_timeout" }, + { CTL_INT, NET_NETROM_TRANSPORT_MAXIMUM_TRIES, "transport_maximum_tries" }, + { CTL_INT, NET_NETROM_TRANSPORT_ACKNOWLEDGE_DELAY, "transport_acknowledge_delay" }, + { CTL_INT, NET_NETROM_TRANSPORT_BUSY_DELAY, "transport_busy_delay" }, + { CTL_INT, NET_NETROM_TRANSPORT_REQUESTED_WINDOW_SIZE, "transport_requested_window_size" }, + { CTL_INT, NET_NETROM_TRANSPORT_NO_ACTIVITY_TIMEOUT, "transport_no_activity_timeout" }, + { CTL_INT, NET_NETROM_ROUTING_CONTROL, "routing_control" }, + { CTL_INT, NET_NETROM_LINK_FAILS_COUNT, "link_fails_count" }, + { CTL_INT, NET_NETROM_RESET, "reset" }, + {} +}; + +static const struct bin_table bin_net_ax25_param_table[] = { + { CTL_INT, NET_AX25_IP_DEFAULT_MODE, "ip_default_mode" }, + { CTL_INT, NET_AX25_DEFAULT_MODE, "ax25_default_mode" }, + { CTL_INT, NET_AX25_BACKOFF_TYPE, "backoff_type" }, + { CTL_INT, NET_AX25_CONNECT_MODE, "connect_mode" }, + { CTL_INT, NET_AX25_STANDARD_WINDOW, "standard_window_size" }, + { CTL_INT, NET_AX25_EXTENDED_WINDOW, "extended_window_size" }, + { CTL_INT, NET_AX25_T1_TIMEOUT, "t1_timeout" }, + { CTL_INT, NET_AX25_T2_TIMEOUT, "t2_timeout" }, + { CTL_INT, NET_AX25_T3_TIMEOUT, "t3_timeout" }, + { CTL_INT, NET_AX25_IDLE_TIMEOUT, "idle_timeout" }, + { CTL_INT, NET_AX25_N2, "maximum_retry_count" }, + { CTL_INT, NET_AX25_PACLEN, "maximum_packet_length" }, + { CTL_INT, NET_AX25_PROTOCOL, "protocol" }, + { CTL_INT, NET_AX25_DAMA_SLAVE_TIMEOUT, "dama_slave_timeout" }, + {} +}; + +static const struct bin_table bin_net_ax25_table[] = { + { CTL_DIR, 0, NULL, bin_net_ax25_param_table }, + {} +}; + +static const struct bin_table bin_net_rose_table[] = { + { CTL_INT, NET_ROSE_RESTART_REQUEST_TIMEOUT, "restart_request_timeout" }, + { CTL_INT, NET_ROSE_CALL_REQUEST_TIMEOUT, "call_request_timeout" }, + { CTL_INT, NET_ROSE_RESET_REQUEST_TIMEOUT, "reset_request_timeout" }, + { CTL_INT, NET_ROSE_CLEAR_REQUEST_TIMEOUT, "clear_request_timeout" }, + { CTL_INT, NET_ROSE_ACK_HOLD_BACK_TIMEOUT, "acknowledge_hold_back_timeout" }, + { CTL_INT, NET_ROSE_ROUTING_CONTROL, "routing_control" }, + { CTL_INT, NET_ROSE_LINK_FAIL_TIMEOUT, "link_fail_timeout" }, + { CTL_INT, NET_ROSE_MAX_VCS, "maximum_virtual_circuits" }, + { CTL_INT, NET_ROSE_WINDOW_SIZE, "window_size" }, + { CTL_INT, NET_ROSE_NO_ACTIVITY_TIMEOUT, "no_activity_timeout" }, + {} +}; + +static const struct bin_table bin_net_ipv6_conf_var_table[] = { + { CTL_INT, NET_IPV6_FORWARDING, "forwarding" }, + { CTL_INT, NET_IPV6_HOP_LIMIT, "hop_limit" }, + { CTL_INT, NET_IPV6_MTU, "mtu" }, + { CTL_INT, NET_IPV6_ACCEPT_RA, "accept_ra" }, + { CTL_INT, NET_IPV6_ACCEPT_REDIRECTS, "accept_redirects" }, + { CTL_INT, NET_IPV6_AUTOCONF, "autoconf" }, + { CTL_INT, NET_IPV6_DAD_TRANSMITS, "dad_transmits" }, + { CTL_INT, NET_IPV6_RTR_SOLICITS, "router_solicitations" }, + { CTL_INT, NET_IPV6_RTR_SOLICIT_INTERVAL, "router_solicitation_interval" }, + { CTL_INT, NET_IPV6_RTR_SOLICIT_DELAY, "router_solicitation_delay" }, + { CTL_INT, NET_IPV6_USE_TEMPADDR, "use_tempaddr" }, + { CTL_INT, NET_IPV6_TEMP_VALID_LFT, "temp_valid_lft" }, + { CTL_INT, NET_IPV6_TEMP_PREFERED_LFT, "temp_prefered_lft" }, + { CTL_INT, NET_IPV6_REGEN_MAX_RETRY, "regen_max_retry" }, + { CTL_INT, NET_IPV6_MAX_DESYNC_FACTOR, "max_desync_factor" }, + { CTL_INT, NET_IPV6_MAX_ADDRESSES, "max_addresses" }, + { CTL_INT, NET_IPV6_FORCE_MLD_VERSION, "force_mld_version" }, + { CTL_INT, NET_IPV6_ACCEPT_RA_DEFRTR, "accept_ra_defrtr" }, + { CTL_INT, NET_IPV6_ACCEPT_RA_PINFO, "accept_ra_pinfo" }, + { CTL_INT, NET_IPV6_ACCEPT_RA_RTR_PREF, "accept_ra_rtr_pref" }, + { CTL_INT, NET_IPV6_RTR_PROBE_INTERVAL, "router_probe_interval" }, + { CTL_INT, NET_IPV6_ACCEPT_RA_RT_INFO_MAX_PLEN, "accept_ra_rt_info_max_plen" }, + { CTL_INT, NET_IPV6_PROXY_NDP, "proxy_ndp" }, + { CTL_INT, NET_IPV6_ACCEPT_SOURCE_ROUTE, "accept_source_route" }, + {} +}; + +static const struct bin_table bin_net_ipv6_conf_table[] = { + { CTL_DIR, NET_PROTO_CONF_ALL, "all", bin_net_ipv6_conf_var_table }, + { CTL_DIR, NET_PROTO_CONF_DEFAULT, "default", bin_net_ipv6_conf_var_table }, + { CTL_DIR, 0, NULL, bin_net_ipv6_conf_var_table }, + {} +}; + +static const struct bin_table bin_net_ipv6_route_table[] = { + /* NET_IPV6_ROUTE_FLUSH "flush" no longer used */ + { CTL_INT, NET_IPV6_ROUTE_GC_THRESH, "gc_thresh" }, + { CTL_INT, NET_IPV6_ROUTE_MAX_SIZE, "max_size" }, + { CTL_INT, NET_IPV6_ROUTE_GC_MIN_INTERVAL, "gc_min_interval" }, + { CTL_INT, NET_IPV6_ROUTE_GC_TIMEOUT, "gc_timeout" }, + { CTL_INT, NET_IPV6_ROUTE_GC_INTERVAL, "gc_interval" }, + { CTL_INT, NET_IPV6_ROUTE_GC_ELASTICITY, "gc_elasticity" }, + { CTL_INT, NET_IPV6_ROUTE_MTU_EXPIRES, "mtu_expires" }, + { CTL_INT, NET_IPV6_ROUTE_MIN_ADVMSS, "min_adv_mss" }, + { CTL_INT, NET_IPV6_ROUTE_GC_MIN_INTERVAL_MS, "gc_min_interval_ms" }, + {} +}; + +static const struct bin_table bin_net_ipv6_icmp_table[] = { + { CTL_INT, NET_IPV6_ICMP_RATELIMIT, "ratelimit" }, + {} +}; + +static const struct bin_table bin_net_ipv6_table[] = { + { CTL_DIR, NET_IPV6_CONF, "conf", bin_net_ipv6_conf_table }, + { CTL_DIR, NET_IPV6_NEIGH, "neigh", bin_net_neigh_table }, + { CTL_DIR, NET_IPV6_ROUTE, "route", bin_net_ipv6_route_table }, + { CTL_DIR, NET_IPV6_ICMP, "icmp", bin_net_ipv6_icmp_table }, + { CTL_INT, NET_IPV6_BINDV6ONLY, "bindv6only" }, + { CTL_INT, NET_IPV6_IP6FRAG_HIGH_THRESH, "ip6frag_high_thresh" }, + { CTL_INT, NET_IPV6_IP6FRAG_LOW_THRESH, "ip6frag_low_thresh" }, + { CTL_INT, NET_IPV6_IP6FRAG_TIME, "ip6frag_time" }, + { CTL_INT, NET_IPV6_IP6FRAG_SECRET_INTERVAL, "ip6frag_secret_interval" }, + { CTL_INT, NET_IPV6_MLD_MAX_MSF, "mld_max_msf" }, + { CTL_INT, 2088 /* IPQ_QMAX */, "ip6_queue_maxlen" }, + {} +}; + +static const struct bin_table bin_net_x25_table[] = { + { CTL_INT, NET_X25_RESTART_REQUEST_TIMEOUT, "restart_request_timeout" }, + { CTL_INT, NET_X25_CALL_REQUEST_TIMEOUT, "call_request_timeout" }, + { CTL_INT, NET_X25_RESET_REQUEST_TIMEOUT, "reset_request_timeout" }, + { CTL_INT, NET_X25_CLEAR_REQUEST_TIMEOUT, "clear_request_timeout" }, + { CTL_INT, NET_X25_ACK_HOLD_BACK_TIMEOUT, "acknowledgement_hold_back_timeout" }, + { CTL_INT, NET_X25_FORWARD, "x25_forward" }, + {} +}; + +static const struct bin_table bin_net_tr_table[] = { + { CTL_INT, NET_TR_RIF_TIMEOUT, "rif_timeout" }, + {} +}; + + +static const struct bin_table bin_net_decnet_conf_vars[] = { + { CTL_INT, NET_DECNET_CONF_DEV_FORWARDING, "forwarding" }, + { CTL_INT, NET_DECNET_CONF_DEV_PRIORITY, "priority" }, + { CTL_INT, NET_DECNET_CONF_DEV_T2, "t2" }, + { CTL_INT, NET_DECNET_CONF_DEV_T3, "t3" }, + {} +}; + +static const struct bin_table bin_net_decnet_conf[] = { + { CTL_DIR, NET_DECNET_CONF_ETHER, "ethernet", bin_net_decnet_conf_vars }, + { CTL_DIR, NET_DECNET_CONF_GRE, "ipgre", bin_net_decnet_conf_vars }, + { CTL_DIR, NET_DECNET_CONF_X25, "x25", bin_net_decnet_conf_vars }, + { CTL_DIR, NET_DECNET_CONF_PPP, "ppp", bin_net_decnet_conf_vars }, + { CTL_DIR, NET_DECNET_CONF_DDCMP, "ddcmp", bin_net_decnet_conf_vars }, + { CTL_DIR, NET_DECNET_CONF_LOOPBACK, "loopback", bin_net_decnet_conf_vars }, + { CTL_DIR, 0, NULL, bin_net_decnet_conf_vars }, + {} +}; + +static const struct bin_table bin_net_decnet_table[] = { + { CTL_DIR, NET_DECNET_CONF, "conf", bin_net_decnet_conf }, + { CTL_DNADR, NET_DECNET_NODE_ADDRESS, "node_address" }, + { CTL_STR, NET_DECNET_NODE_NAME, "node_name" }, + { CTL_STR, NET_DECNET_DEFAULT_DEVICE, "default_device" }, + { CTL_INT, NET_DECNET_TIME_WAIT, "time_wait" }, + { CTL_INT, NET_DECNET_DN_COUNT, "dn_count" }, + { CTL_INT, NET_DECNET_DI_COUNT, "di_count" }, + { CTL_INT, NET_DECNET_DR_COUNT, "dr_count" }, + { CTL_INT, NET_DECNET_DST_GC_INTERVAL, "dst_gc_interval" }, + { CTL_INT, NET_DECNET_NO_FC_MAX_CWND, "no_fc_max_cwnd" }, + { CTL_INT, NET_DECNET_MEM, "decnet_mem" }, + { CTL_INT, NET_DECNET_RMEM, "decnet_rmem" }, + { CTL_INT, NET_DECNET_WMEM, "decnet_wmem" }, + { CTL_INT, NET_DECNET_DEBUG_LEVEL, "debug" }, + {} +}; + +static const struct bin_table bin_net_sctp_table[] = { + { CTL_INT, NET_SCTP_RTO_INITIAL, "rto_initial" }, + { CTL_INT, NET_SCTP_RTO_MIN, "rto_min" }, + { CTL_INT, NET_SCTP_RTO_MAX, "rto_max" }, + { CTL_INT, NET_SCTP_RTO_ALPHA, "rto_alpha_exp_divisor" }, + { CTL_INT, NET_SCTP_RTO_BETA, "rto_beta_exp_divisor" }, + { CTL_INT, NET_SCTP_VALID_COOKIE_LIFE, "valid_cookie_life" }, + { CTL_INT, NET_SCTP_ASSOCIATION_MAX_RETRANS, "association_max_retrans" }, + { CTL_INT, NET_SCTP_PATH_MAX_RETRANS, "path_max_retrans" }, + { CTL_INT, NET_SCTP_MAX_INIT_RETRANSMITS, "max_init_retransmits" }, + { CTL_INT, NET_SCTP_HB_INTERVAL, "hb_interval" }, + { CTL_INT, NET_SCTP_PRESERVE_ENABLE, "cookie_preserve_enable" }, + { CTL_INT, NET_SCTP_MAX_BURST, "max_burst" }, + { CTL_INT, NET_SCTP_ADDIP_ENABLE, "addip_enable" }, + { CTL_INT, NET_SCTP_PRSCTP_ENABLE, "prsctp_enable" }, + { CTL_INT, NET_SCTP_SNDBUF_POLICY, "sndbuf_policy" }, + { CTL_INT, NET_SCTP_SACK_TIMEOUT, "sack_timeout" }, + { CTL_INT, NET_SCTP_RCVBUF_POLICY, "rcvbuf_policy" }, + {} +}; + +static const struct bin_table bin_net_llc_llc2_timeout_table[] = { + { CTL_INT, NET_LLC2_ACK_TIMEOUT, "ack" }, + { CTL_INT, NET_LLC2_P_TIMEOUT, "p" }, + { CTL_INT, NET_LLC2_REJ_TIMEOUT, "rej" }, + { CTL_INT, NET_LLC2_BUSY_TIMEOUT, "busy" }, + {} +}; + +static const struct bin_table bin_net_llc_station_table[] = { + { CTL_INT, NET_LLC_STATION_ACK_TIMEOUT, "ack_timeout" }, + {} +}; + +static const struct bin_table bin_net_llc_llc2_table[] = { + { CTL_DIR, NET_LLC2, "timeout", bin_net_llc_llc2_timeout_table }, + {} +}; + +static const struct bin_table bin_net_llc_table[] = { + { CTL_DIR, NET_LLC2, "llc2", bin_net_llc_llc2_table }, + { CTL_DIR, NET_LLC_STATION, "station", bin_net_llc_station_table }, + {} +}; + +static const struct bin_table bin_net_netfilter_table[] = { + { CTL_INT, NET_NF_CONNTRACK_MAX, "nf_conntrack_max" }, + /* NET_NF_CONNTRACK_TCP_TIMEOUT_SYN_SENT "nf_conntrack_tcp_timeout_syn_sent" no longer used */ + /* NET_NF_CONNTRACK_TCP_TIMEOUT_SYN_RECV "nf_conntrack_tcp_timeout_syn_recv" no longer used */ + /* NET_NF_CONNTRACK_TCP_TIMEOUT_ESTABLISHED "nf_conntrack_tcp_timeout_established" no longer used */ + /* NET_NF_CONNTRACK_TCP_TIMEOUT_FIN_WAIT "nf_conntrack_tcp_timeout_fin_wait" no longer used */ + /* NET_NF_CONNTRACK_TCP_TIMEOUT_CLOSE_WAIT "nf_conntrack_tcp_timeout_close_wait" no longer used */ + /* NET_NF_CONNTRACK_TCP_TIMEOUT_LAST_ACK "nf_conntrack_tcp_timeout_last_ack" no longer used */ + /* NET_NF_CONNTRACK_TCP_TIMEOUT_TIME_WAIT "nf_conntrack_tcp_timeout_time_wait" no longer used */ + /* NET_NF_CONNTRACK_TCP_TIMEOUT_CLOSE "nf_conntrack_tcp_timeout_close" no longer used */ + /* NET_NF_CONNTRACK_UDP_TIMEOUT "nf_conntrack_udp_timeout" no longer used */ + /* NET_NF_CONNTRACK_UDP_TIMEOUT_STREAM "nf_conntrack_udp_timeout_stream" no longer used */ + /* NET_NF_CONNTRACK_ICMP_TIMEOUT "nf_conntrack_icmp_timeout" no longer used */ + /* NET_NF_CONNTRACK_GENERIC_TIMEOUT "nf_conntrack_generic_timeout" no longer used */ + { CTL_INT, NET_NF_CONNTRACK_BUCKETS, "nf_conntrack_buckets" }, + { CTL_INT, NET_NF_CONNTRACK_LOG_INVALID, "nf_conntrack_log_invalid" }, + /* NET_NF_CONNTRACK_TCP_TIMEOUT_MAX_RETRANS "nf_conntrack_tcp_timeout_max_retrans" no longer used */ + { CTL_INT, NET_NF_CONNTRACK_TCP_LOOSE, "nf_conntrack_tcp_loose" }, + { CTL_INT, NET_NF_CONNTRACK_TCP_BE_LIBERAL, "nf_conntrack_tcp_be_liberal" }, + { CTL_INT, NET_NF_CONNTRACK_TCP_MAX_RETRANS, "nf_conntrack_tcp_max_retrans" }, + /* NET_NF_CONNTRACK_SCTP_TIMEOUT_CLOSED "nf_conntrack_sctp_timeout_closed" no longer used */ + /* NET_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_WAIT "nf_conntrack_sctp_timeout_cookie_wait" no longer used */ + /* NET_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_ECHOED "nf_conntrack_sctp_timeout_cookie_echoed" no longer used */ + /* NET_NF_CONNTRACK_SCTP_TIMEOUT_ESTABLISHED "nf_conntrack_sctp_timeout_established" no longer used */ + /* NET_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_SENT "nf_conntrack_sctp_timeout_shutdown_sent" no longer used */ + /* NET_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_RECD "nf_conntrack_sctp_timeout_shutdown_recd" no longer used */ + /* NET_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_ACK_SENT "nf_conntrack_sctp_timeout_shutdown_ack_sent" no longer used */ + { CTL_INT, NET_NF_CONNTRACK_COUNT, "nf_conntrack_count" }, + /* NET_NF_CONNTRACK_ICMPV6_TIMEOUT "nf_conntrack_icmpv6_timeout" no longer used */ + /* NET_NF_CONNTRACK_FRAG6_TIMEOUT "nf_conntrack_frag6_timeout" no longer used */ + { CTL_INT, NET_NF_CONNTRACK_FRAG6_LOW_THRESH, "nf_conntrack_frag6_low_thresh" }, + { CTL_INT, NET_NF_CONNTRACK_FRAG6_HIGH_THRESH, "nf_conntrack_frag6_high_thresh" }, + { CTL_INT, NET_NF_CONNTRACK_CHECKSUM, "nf_conntrack_checksum" }, + + {} +}; + +static const struct bin_table bin_net_irda_table[] = { + { CTL_INT, NET_IRDA_DISCOVERY, "discovery" }, + { CTL_STR, NET_IRDA_DEVNAME, "devname" }, + { CTL_INT, NET_IRDA_DEBUG, "debug" }, + { CTL_INT, NET_IRDA_FAST_POLL, "fast_poll_increase" }, + { CTL_INT, NET_IRDA_DISCOVERY_SLOTS, "discovery_slots" }, + { CTL_INT, NET_IRDA_DISCOVERY_TIMEOUT, "discovery_timeout" }, + { CTL_INT, NET_IRDA_SLOT_TIMEOUT, "slot_timeout" }, + { CTL_INT, NET_IRDA_MAX_BAUD_RATE, "max_baud_rate" }, + { CTL_INT, NET_IRDA_MIN_TX_TURN_TIME, "min_tx_turn_time" }, + { CTL_INT, NET_IRDA_MAX_TX_DATA_SIZE, "max_tx_data_size" }, + { CTL_INT, NET_IRDA_MAX_TX_WINDOW, "max_tx_window" }, + { CTL_INT, NET_IRDA_MAX_NOREPLY_TIME, "max_noreply_time" }, + { CTL_INT, NET_IRDA_WARN_NOREPLY_TIME, "warn_noreply_time" }, + { CTL_INT, NET_IRDA_LAP_KEEPALIVE_TIME, "lap_keepalive_time" }, + {} +}; + +static const struct bin_table bin_net_table[] = { + { CTL_DIR, NET_CORE, "core", bin_net_core_table }, + /* NET_ETHER not used */ + /* NET_802 not used */ + { CTL_DIR, NET_UNIX, "unix", bin_net_unix_table }, + { CTL_DIR, NET_IPV4, "ipv4", bin_net_ipv4_table }, + { CTL_DIR, NET_IPX, "ipx", bin_net_ipx_table }, + { CTL_DIR, NET_ATALK, "appletalk", bin_net_atalk_table }, + { CTL_DIR, NET_NETROM, "netrom", bin_net_netrom_table }, + { CTL_DIR, NET_AX25, "ax25", bin_net_ax25_table }, + /* NET_BRIDGE "bridge" no longer used */ + { CTL_DIR, NET_ROSE, "rose", bin_net_rose_table }, + { CTL_DIR, NET_IPV6, "ipv6", bin_net_ipv6_table }, + { CTL_DIR, NET_X25, "x25", bin_net_x25_table }, + { CTL_DIR, NET_TR, "token-ring", bin_net_tr_table }, + { CTL_DIR, NET_DECNET, "decnet", bin_net_decnet_table }, + /* NET_ECONET not used */ + { CTL_DIR, NET_SCTP, "sctp", bin_net_sctp_table }, + { CTL_DIR, NET_LLC, "llc", bin_net_llc_table }, + { CTL_DIR, NET_NETFILTER, "netfilter", bin_net_netfilter_table }, + /* NET_DCCP "dccp" no longer used */ + { CTL_DIR, NET_IRDA, "irda", bin_net_irda_table }, + { CTL_INT, 2089, "nf_conntrack_max" }, + {} +}; + +static const struct bin_table bin_fs_quota_table[] = { + { CTL_INT, FS_DQ_LOOKUPS, "lookups" }, + { CTL_INT, FS_DQ_DROPS, "drops" }, + { CTL_INT, FS_DQ_READS, "reads" }, + { CTL_INT, FS_DQ_WRITES, "writes" }, + { CTL_INT, FS_DQ_CACHE_HITS, "cache_hits" }, + { CTL_INT, FS_DQ_ALLOCATED, "allocated_dquots" }, + { CTL_INT, FS_DQ_FREE, "free_dquots" }, + { CTL_INT, FS_DQ_SYNCS, "syncs" }, + { CTL_INT, FS_DQ_WARNINGS, "warnings" }, + {} +}; + +static const struct bin_table bin_fs_xfs_table[] = { + { CTL_INT, XFS_SGID_INHERIT, "irix_sgid_inherit" }, + { CTL_INT, XFS_SYMLINK_MODE, "irix_symlink_mode" }, + { CTL_INT, XFS_PANIC_MASK, "panic_mask" }, + + { CTL_INT, XFS_ERRLEVEL, "error_level" }, + { CTL_INT, XFS_SYNCD_TIMER, "xfssyncd_centisecs" }, + { CTL_INT, XFS_INHERIT_SYNC, "inherit_sync" }, + { CTL_INT, XFS_INHERIT_NODUMP, "inherit_nodump" }, + { CTL_INT, XFS_INHERIT_NOATIME, "inherit_noatime" }, + { CTL_INT, XFS_BUF_TIMER, "xfsbufd_centisecs" }, + { CTL_INT, XFS_BUF_AGE, "age_buffer_centisecs" }, + { CTL_INT, XFS_INHERIT_NOSYM, "inherit_nosymlinks" }, + { CTL_INT, XFS_ROTORSTEP, "rotorstep" }, + { CTL_INT, XFS_INHERIT_NODFRG, "inherit_nodefrag" }, + { CTL_INT, XFS_FILESTREAM_TIMER, "filestream_centisecs" }, + { CTL_INT, XFS_STATS_CLEAR, "stats_clear" }, + {} +}; + +static const struct bin_table bin_fs_ocfs2_nm_table[] = { + { CTL_STR, 1, "hb_ctl_path" }, + {} +}; + +static const struct bin_table bin_fs_ocfs2_table[] = { + { CTL_DIR, 1, "nm", bin_fs_ocfs2_nm_table }, + {} +}; + +static const struct bin_table bin_inotify_table[] = { + { CTL_INT, INOTIFY_MAX_USER_INSTANCES, "max_user_instances" }, + { CTL_INT, INOTIFY_MAX_USER_WATCHES, "max_user_watches" }, + { CTL_INT, INOTIFY_MAX_QUEUED_EVENTS, "max_queued_events" }, + {} +}; + +static const struct bin_table bin_fs_table[] = { + { CTL_INT, FS_NRINODE, "inode-nr" }, + { CTL_INT, FS_STATINODE, "inode-state" }, + /* FS_MAXINODE unused */ + /* FS_NRDQUOT unused */ + /* FS_MAXDQUOT unused */ + /* FS_NRFILE "file-nr" no longer used */ + { CTL_INT, FS_MAXFILE, "file-max" }, + { CTL_INT, FS_DENTRY, "dentry-state" }, + /* FS_NRSUPER unused */ + /* FS_MAXUPSER unused */ + { CTL_INT, FS_OVERFLOWUID, "overflowuid" }, + { CTL_INT, FS_OVERFLOWGID, "overflowgid" }, + { CTL_INT, FS_LEASES, "leases-enable" }, + { CTL_INT, FS_DIR_NOTIFY, "dir-notify-enable" }, + { CTL_INT, FS_LEASE_TIME, "lease-break-time" }, + { CTL_DIR, FS_DQSTATS, "quota", bin_fs_quota_table }, + { CTL_DIR, FS_XFS, "xfs", bin_fs_xfs_table }, + { CTL_ULONG, FS_AIO_NR, "aio-nr" }, + { CTL_ULONG, FS_AIO_MAX_NR, "aio-max-nr" }, + { CTL_DIR, FS_INOTIFY, "inotify", bin_inotify_table }, + { CTL_DIR, FS_OCFS2, "ocfs2", bin_fs_ocfs2_table }, + { CTL_INT, KERN_SETUID_DUMPABLE, "suid_dumpable" }, + {} +}; + +static const struct bin_table bin_ipmi_table[] = { + { CTL_INT, DEV_IPMI_POWEROFF_POWERCYCLE, "poweroff_powercycle" }, + {} +}; + +static const struct bin_table bin_mac_hid_files[] = { + /* DEV_MAC_HID_KEYBOARD_SENDS_LINUX_KEYCODES unused */ + /* DEV_MAC_HID_KEYBOARD_LOCK_KEYCODES unused */ + { CTL_INT, DEV_MAC_HID_MOUSE_BUTTON_EMULATION, "mouse_button_emulation" }, + { CTL_INT, DEV_MAC_HID_MOUSE_BUTTON2_KEYCODE, "mouse_button2_keycode" }, + { CTL_INT, DEV_MAC_HID_MOUSE_BUTTON3_KEYCODE, "mouse_button3_keycode" }, + /* DEV_MAC_HID_ADB_MOUSE_SENDS_KEYCODES unused */ + {} +}; + +static const struct bin_table bin_raid_table[] = { + { CTL_INT, DEV_RAID_SPEED_LIMIT_MIN, "speed_limit_min" }, + { CTL_INT, DEV_RAID_SPEED_LIMIT_MAX, "speed_limit_max" }, + {} +}; + +static const struct bin_table bin_scsi_table[] = { + { CTL_INT, DEV_SCSI_LOGGING_LEVEL, "logging_level" }, + {} +}; + +static const struct bin_table bin_dev_table[] = { + /* DEV_CDROM "cdrom" no longer used */ + /* DEV_HWMON unused */ + /* DEV_PARPORT "parport" no longer used */ + { CTL_DIR, DEV_RAID, "raid", bin_raid_table }, + { CTL_DIR, DEV_MAC_HID, "mac_hid", bin_mac_hid_files }, + { CTL_DIR, DEV_SCSI, "scsi", bin_scsi_table }, + { CTL_DIR, DEV_IPMI, "ipmi", bin_ipmi_table }, + {} +}; + +static const struct bin_table bin_bus_isa_table[] = { + { CTL_INT, BUS_ISA_MEM_BASE, "membase" }, + { CTL_INT, BUS_ISA_PORT_BASE, "portbase" }, + { CTL_INT, BUS_ISA_PORT_SHIFT, "portshift" }, + {} +}; + +static const struct bin_table bin_bus_table[] = { + { CTL_DIR, CTL_BUS_ISA, "isa", bin_bus_isa_table }, + {} +}; + + +static const struct bin_table bin_s390dbf_table[] = { + { CTL_INT, 5678 /* CTL_S390DBF_STOPPABLE */, "debug_stoppable" }, + { CTL_INT, 5679 /* CTL_S390DBF_ACTIVE */, "debug_active" }, + {} +}; + +static const struct bin_table bin_sunrpc_table[] = { + /* CTL_RPCDEBUG "rpc_debug" no longer used */ + /* CTL_NFSDEBUG "nfs_debug" no longer used */ + /* CTL_NFSDDEBUG "nfsd_debug" no longer used */ + /* CTL_NLMDEBUG "nlm_debug" no longer used */ + + { CTL_INT, CTL_SLOTTABLE_UDP, "udp_slot_table_entries" }, + { CTL_INT, CTL_SLOTTABLE_TCP, "tcp_slot_table_entries" }, + { CTL_INT, CTL_MIN_RESVPORT, "min_resvport" }, + { CTL_INT, CTL_MAX_RESVPORT, "max_resvport" }, + {} +}; + +static const struct bin_table bin_pm_table[] = { + /* frv specific */ + /* 1 == CTL_PM_SUSPEND "suspend" no longer used" */ + { CTL_INT, 2 /* CTL_PM_CMODE */, "cmode" }, + { CTL_INT, 3 /* CTL_PM_P0 */, "p0" }, + { CTL_INT, 4 /* CTL_PM_CM */, "cm" }, + {} +}; + +static const struct bin_table bin_root_table[] = { + { CTL_DIR, CTL_KERN, "kernel", bin_kern_table }, + { CTL_DIR, CTL_VM, "vm", bin_vm_table }, + { CTL_DIR, CTL_NET, "net", bin_net_table }, + /* CTL_PROC not used */ + { CTL_DIR, CTL_FS, "fs", bin_fs_table }, + /* CTL_DEBUG "debug" no longer used */ + { CTL_DIR, CTL_DEV, "dev", bin_dev_table }, + { CTL_DIR, CTL_BUS, "bus", bin_bus_table }, + { CTL_DIR, CTL_ABI, "abi" }, + /* CTL_CPU not used */ + /* CTL_ARLAN "arlan" no longer used */ + { CTL_DIR, CTL_S390DBF, "s390dbf", bin_s390dbf_table }, + { CTL_DIR, CTL_SUNRPC, "sunrpc", bin_sunrpc_table }, + { CTL_DIR, CTL_PM, "pm", bin_pm_table }, + {} +}; + +static ssize_t bin_dir(struct file *file, + void __user *oldval, size_t oldlen, void __user *newval, size_t newlen) +{ + return -ENOTDIR; +} + + +static ssize_t bin_string(struct file *file, + void __user *oldval, size_t oldlen, void __user *newval, size_t newlen) +{ + ssize_t result, copied = 0; + + if (oldval && oldlen) { + char __user *lastp; + loff_t pos = 0; + int ch; + + result = vfs_read(file, oldval, oldlen, &pos); + if (result < 0) + goto out; + + copied = result; + lastp = oldval + copied - 1; + + result = -EFAULT; + if (get_user(ch, lastp)) + goto out; + + /* Trim off the trailing newline */ + if (ch == '\n') { + result = -EFAULT; + if (put_user('\0', lastp)) + goto out; + copied -= 1; + } + } + + if (newval && newlen) { + loff_t pos = 0; + + result = vfs_write(file, newval, newlen, &pos); + if (result < 0) + goto out; + } + + result = copied; +out: + return result; +} + +static ssize_t bin_intvec(struct file *file, + void __user *oldval, size_t oldlen, void __user *newval, size_t newlen) +{ + mm_segment_t old_fs = get_fs(); + ssize_t copied = 0; + char *buffer; + ssize_t result; + + result = -ENOMEM; + buffer = kmalloc(BUFSZ, GFP_KERNEL); + if (!buffer) + goto out; + + if (oldval && oldlen) { + unsigned __user *vec = oldval; + size_t length = oldlen / sizeof(*vec); + loff_t pos = 0; + char *str, *end; + int i; + + set_fs(KERNEL_DS); + result = vfs_read(file, buffer, BUFSZ - 1, &pos); + set_fs(old_fs); + if (result < 0) + goto out_kfree; + + str = buffer; + end = str + result; + *end++ = '\0'; + for (i = 0; i < length; i++) { + unsigned long value; + + value = simple_strtoul(str, &str, 10); + while (isspace(*str)) + str++; + + result = -EFAULT; + if (put_user(value, vec + i)) + goto out_kfree; + + copied += sizeof(*vec); + if (!isdigit(*str)) + break; + } + } + + if (newval && newlen) { + unsigned __user *vec = newval; + size_t length = newlen / sizeof(*vec); + loff_t pos = 0; + char *str, *end; + int i; + + str = buffer; + end = str + BUFSZ; + for (i = 0; i < length; i++) { + unsigned long value; + + result = -EFAULT; + if (get_user(value, vec + i)) + goto out_kfree; + + str += snprintf(str, end - str, "%lu\t", value); + } + + set_fs(KERNEL_DS); + result = vfs_write(file, buffer, str - buffer, &pos); + set_fs(old_fs); + if (result < 0) + goto out_kfree; + } + result = copied; +out_kfree: + kfree(buffer); +out: + return result; +} + +static ssize_t bin_ulongvec(struct file *file, + void __user *oldval, size_t oldlen, void __user *newval, size_t newlen) +{ + mm_segment_t old_fs = get_fs(); + ssize_t copied = 0; + char *buffer; + ssize_t result; + + result = -ENOMEM; + buffer = kmalloc(BUFSZ, GFP_KERNEL); + if (!buffer) + goto out; + + if (oldval && oldlen) { + unsigned long __user *vec = oldval; + size_t length = oldlen / sizeof(*vec); + loff_t pos = 0; + char *str, *end; + int i; + + set_fs(KERNEL_DS); + result = vfs_read(file, buffer, BUFSZ - 1, &pos); + set_fs(old_fs); + if (result < 0) + goto out_kfree; + + str = buffer; + end = str + result; + *end++ = '\0'; + for (i = 0; i < length; i++) { + unsigned long value; + + value = simple_strtoul(str, &str, 10); + while (isspace(*str)) + str++; + + result = -EFAULT; + if (put_user(value, vec + i)) + goto out_kfree; + + copied += sizeof(*vec); + if (!isdigit(*str)) + break; + } + } + + if (newval && newlen) { + unsigned long __user *vec = newval; + size_t length = newlen / sizeof(*vec); + loff_t pos = 0; + char *str, *end; + int i; + + str = buffer; + end = str + BUFSZ; + for (i = 0; i < length; i++) { + unsigned long value; + + result = -EFAULT; + if (get_user(value, vec + i)) + goto out_kfree; + + str += snprintf(str, end - str, "%lu\t", value); + } + + set_fs(KERNEL_DS); + result = vfs_write(file, buffer, str - buffer, &pos); + set_fs(old_fs); + if (result < 0) + goto out_kfree; + } + result = copied; +out_kfree: + kfree(buffer); +out: + return result; +} + +static unsigned hex_value(int ch) +{ + return isdigit(ch) ? ch - '0' : ((ch | 0x20) - 'a') + 10; +} + +static ssize_t bin_uuid(struct file *file, + void __user *oldval, size_t oldlen, void __user *newval, size_t newlen) +{ + mm_segment_t old_fs = get_fs(); + ssize_t result, copied = 0; + + /* Only supports reads */ + if (oldval && oldlen) { + loff_t pos = 0; + char buf[40], *str = buf; + unsigned char uuid[16]; + int i; + + set_fs(KERNEL_DS); + result = vfs_read(file, buf, sizeof(buf) - 1, &pos); + set_fs(old_fs); + if (result < 0) + goto out; + + buf[result] = '\0'; + + /* Convert the uuid to from a string to binary */ + for (i = 0; i < 16; i++) { + result = -EIO; + if (!isxdigit(str[0]) || !isxdigit(str[1])) + goto out; + + uuid[i] = (hex_value(str[0]) << 4) | hex_value(str[1]); + str += 2; + if (*str == '-') + str++; + } + + if (oldlen > 16) + oldlen = 16; + + result = -EFAULT; + if (copy_to_user(oldval, uuid, oldlen)) + goto out; + + copied = oldlen; + } + result = copied; +out: + return result; +} + +static ssize_t bin_dn_node_address(struct file *file, + void __user *oldval, size_t oldlen, void __user *newval, size_t newlen) +{ + mm_segment_t old_fs = get_fs(); + ssize_t result, copied = 0; + + if (oldval && oldlen) { + loff_t pos = 0; + char buf[15], *nodep; + unsigned long area, node; + __le16 dnaddr; + + set_fs(KERNEL_DS); + result = vfs_read(file, buf, sizeof(buf) - 1, &pos); + set_fs(old_fs); + if (result < 0) + goto out; + + buf[result] = '\0'; + + /* Convert the decnet addresss to binary */ + result = -EIO; + nodep = strchr(buf, '.') + 1; + if (!nodep) + goto out; + + area = simple_strtoul(buf, NULL, 10); + node = simple_strtoul(nodep, NULL, 10); + + result = -EIO; + if ((area > 63)||(node > 1023)) + goto out; + + dnaddr = cpu_to_le16((area << 10) | node); + + result = -EFAULT; + if (put_user(dnaddr, (__le16 __user *)oldval)) + goto out; + + copied = sizeof(dnaddr); + } + + if (newval && newlen) { + loff_t pos = 0; + __le16 dnaddr; + char buf[15]; + int len; + + result = -EINVAL; + if (newlen != sizeof(dnaddr)) + goto out; + + result = -EFAULT; + if (get_user(dnaddr, (__le16 __user *)newval)) + goto out; + + len = snprintf(buf, sizeof(buf), "%hu.%hu", + le16_to_cpu(dnaddr) >> 10, + le16_to_cpu(dnaddr) & 0x3ff); + + set_fs(KERNEL_DS); + result = vfs_write(file, buf, len, &pos); + set_fs(old_fs); + if (result < 0) + goto out; + } + + result = copied; +out: + return result; +} + +static const struct bin_table *get_sysctl(const int *name, int nlen, char *path) +{ + const struct bin_table *table = &bin_root_table[0]; + int ctl_name; + + /* The binary sysctl tables have a small maximum depth so + * there is no danger of overflowing our path as it PATH_MAX + * bytes long. + */ + memcpy(path, "sys/", 4); + path += 4; + +repeat: + if (!nlen) + return ERR_PTR(-ENOTDIR); + ctl_name = *name; + name++; + nlen--; + for ( ; table->convert; table++) { + int len = 0; + + /* + * For a wild card entry map from ifindex to network + * device name. + */ + if (!table->ctl_name) { +#ifdef CONFIG_NET + struct net *net = current->nsproxy->net_ns; + struct net_device *dev; + dev = dev_get_by_index(net, ctl_name); + if (dev) { + len = strlen(dev->name); + memcpy(path, dev->name, len); + dev_put(dev); + } +#endif + /* Use the well known sysctl number to proc name mapping */ + } else if (ctl_name == table->ctl_name) { + len = strlen(table->procname); + memcpy(path, table->procname, len); + } + if (len) { + path += len; + if (table->child) { + *path++ = '/'; + table = table->child; + goto repeat; + } + *path = '\0'; + return table; + } + } + return ERR_PTR(-ENOTDIR); +} + +static char *sysctl_getname(const int *name, int nlen, const struct bin_table **tablep) +{ + char *tmp, *result; + + result = ERR_PTR(-ENOMEM); + tmp = __getname(); + if (tmp) { + const struct bin_table *table = get_sysctl(name, nlen, tmp); + result = tmp; + *tablep = table; + if (IS_ERR(table)) { + __putname(tmp); + result = ERR_CAST(table); + } + } + return result; +} + +static ssize_t binary_sysctl(const int *name, int nlen, + void __user *oldval, size_t oldlen, void __user *newval, size_t newlen) +{ + const struct bin_table *table = NULL; + struct nameidata nd; + struct vfsmount *mnt; + struct file *file; + ssize_t result; + char *pathname; + int flags; + int acc_mode, fmode; + + pathname = sysctl_getname(name, nlen, &table); + result = PTR_ERR(pathname); + if (IS_ERR(pathname)) + goto out; + + /* How should the sysctl be accessed? */ + if (oldval && oldlen && newval && newlen) { + flags = O_RDWR; + acc_mode = MAY_READ | MAY_WRITE; + fmode = FMODE_READ | FMODE_WRITE; + } else if (newval && newlen) { + flags = O_WRONLY; + acc_mode = MAY_WRITE; + fmode = FMODE_WRITE; + } else if (oldval && oldlen) { + flags = O_RDONLY; + acc_mode = MAY_READ; + fmode = FMODE_READ; + } else { + result = 0; + goto out_putname; + } + + mnt = current->nsproxy->pid_ns->proc_mnt; + result = vfs_path_lookup(mnt->mnt_root, mnt, pathname, 0, &nd); + if (result) + goto out_putname; + + result = may_open(&nd.path, acc_mode, fmode); + if (result) + goto out_putpath; + + file = dentry_open(nd.path.dentry, nd.path.mnt, flags, current_cred()); + result = PTR_ERR(file); + if (IS_ERR(file)) + goto out_putname; + + result = table->convert(file, oldval, oldlen, newval, newlen); + + fput(file); +out_putname: + putname(pathname); +out: + return result; + +out_putpath: + path_put(&nd.path); + goto out_putname; +} + + +#else /* CONFIG_SYSCTL_SYSCALL */ + +static ssize_t binary_sysctl(const int *name, int nlen, + void __user *oldval, size_t oldlen, void __user *newval, size_t newlen) +{ + return -ENOSYS; +} + +#endif /* CONFIG_SYSCTL_SYSCALL */ + + +static void deprecated_sysctl_warning(const int *name, int nlen) +{ + int i; + + if (printk_ratelimit()) { + printk(KERN_INFO + "warning: process `%s' used the deprecated sysctl " + "system call with ", current->comm); + for (i = 0; i < nlen; i++) + printk("%d.", name[i]); + printk("\n"); + } + return; +} + +static ssize_t do_sysctl(int __user *args_name, int nlen, + void __user *oldval, size_t oldlen, void __user *newval, size_t newlen) +{ + int name[CTL_MAXNAME]; + int i; + + /* Check args->nlen. */ + if (nlen < 0 || nlen > CTL_MAXNAME) + return -ENOTDIR; + /* Read in the sysctl name for simplicity */ + for (i = 0; i < nlen; i++) + if (get_user(name[i], args_name + i)) + return -EFAULT; + + deprecated_sysctl_warning(name, nlen); + + return binary_sysctl(name, nlen, oldval, oldlen, newval, newlen); +} + +SYSCALL_DEFINE1(sysctl, struct __sysctl_args __user *, args) +{ + struct __sysctl_args tmp; + size_t oldlen = 0; + ssize_t result; + + if (copy_from_user(&tmp, args, sizeof(tmp))) + return -EFAULT; + + if (tmp.oldval && !tmp.oldlenp) + return -EFAULT; + + if (tmp.oldlenp && get_user(oldlen, tmp.oldlenp)) + return -EFAULT; + + result = do_sysctl(tmp.name, tmp.nlen, tmp.oldval, oldlen, + tmp.newval, tmp.newlen); + + if (result >= 0) { + oldlen = result; + result = 0; + } + + if (tmp.oldlenp && put_user(oldlen, tmp.oldlenp)) + return -EFAULT; + + return result; +} + + +#ifdef CONFIG_COMPAT +#include <asm/compat.h> + +struct compat_sysctl_args { + compat_uptr_t name; + int nlen; + compat_uptr_t oldval; + compat_uptr_t oldlenp; + compat_uptr_t newval; + compat_size_t newlen; + compat_ulong_t __unused[4]; +}; + +asmlinkage long compat_sys_sysctl(struct compat_sysctl_args __user *args) +{ + struct compat_sysctl_args tmp; + compat_size_t __user *compat_oldlenp; + size_t oldlen = 0; + ssize_t result; + + if (copy_from_user(&tmp, args, sizeof(tmp))) + return -EFAULT; + + if (tmp.oldval && !tmp.oldlenp) + return -EFAULT; + + compat_oldlenp = compat_ptr(tmp.oldlenp); + if (compat_oldlenp && get_user(oldlen, compat_oldlenp)) + return -EFAULT; + + result = do_sysctl(compat_ptr(tmp.name), tmp.nlen, + compat_ptr(tmp.oldval), oldlen, + compat_ptr(tmp.newval), tmp.newlen); + + if (result >= 0) { + oldlen = result; + result = 0; + } + + if (compat_oldlenp && put_user(oldlen, compat_oldlenp)) + return -EFAULT; + + return result; +} + +#endif /* CONFIG_COMPAT */ diff --git a/kernel/sysctl_check.c b/kernel/sysctl_check.c index b6e7aaea4604..04cdcf72c827 100644 --- a/kernel/sysctl_check.c +++ b/kernel/sysctl_check.c @@ -5,1239 +5,6 @@ #include <linux/string.h> #include <net/ip_vs.h> -struct trans_ctl_table { - int ctl_name; - const char *procname; - const struct trans_ctl_table *child; -}; - -static const struct trans_ctl_table trans_random_table[] = { - { RANDOM_POOLSIZE, "poolsize" }, - { RANDOM_ENTROPY_COUNT, "entropy_avail" }, - { RANDOM_READ_THRESH, "read_wakeup_threshold" }, - { RANDOM_WRITE_THRESH, "write_wakeup_threshold" }, - { RANDOM_BOOT_ID, "boot_id" }, - { RANDOM_UUID, "uuid" }, - {} -}; - -static const struct trans_ctl_table trans_pty_table[] = { - { PTY_MAX, "max" }, - { PTY_NR, "nr" }, - {} -}; - -static const struct trans_ctl_table trans_kern_table[] = { - { KERN_OSTYPE, "ostype" }, - { KERN_OSRELEASE, "osrelease" }, - /* KERN_OSREV not used */ - { KERN_VERSION, "version" }, - /* KERN_SECUREMASK not used */ - /* KERN_PROF not used */ - { KERN_NODENAME, "hostname" }, - { KERN_DOMAINNAME, "domainname" }, - - { KERN_PANIC, "panic" }, - { KERN_REALROOTDEV, "real-root-dev" }, - - { KERN_SPARC_REBOOT, "reboot-cmd" }, - { KERN_CTLALTDEL, "ctrl-alt-del" }, - { KERN_PRINTK, "printk" }, - - /* KERN_NAMETRANS not used */ - /* KERN_PPC_HTABRECLAIM not used */ - /* KERN_PPC_ZEROPAGED not used */ - { KERN_PPC_POWERSAVE_NAP, "powersave-nap" }, - - { KERN_MODPROBE, "modprobe" }, - { KERN_SG_BIG_BUFF, "sg-big-buff" }, - { KERN_ACCT, "acct" }, - { KERN_PPC_L2CR, "l2cr" }, - - /* KERN_RTSIGNR not used */ - /* KERN_RTSIGMAX not used */ - - { KERN_SHMMAX, "shmmax" }, - { KERN_MSGMAX, "msgmax" }, - { KERN_MSGMNB, "msgmnb" }, - /* KERN_MSGPOOL not used*/ - { KERN_SYSRQ, "sysrq" }, - { KERN_MAX_THREADS, "threads-max" }, - { KERN_RANDOM, "random", trans_random_table }, - { KERN_SHMALL, "shmall" }, - { KERN_MSGMNI, "msgmni" }, - { KERN_SEM, "sem" }, - { KERN_SPARC_STOP_A, "stop-a" }, - { KERN_SHMMNI, "shmmni" }, - - { KERN_OVERFLOWUID, "overflowuid" }, - { KERN_OVERFLOWGID, "overflowgid" }, - - { KERN_HOTPLUG, "hotplug", }, - { KERN_IEEE_EMULATION_WARNINGS, "ieee_emulation_warnings" }, - - { KERN_S390_USER_DEBUG_LOGGING, "userprocess_debug" }, - { KERN_CORE_USES_PID, "core_uses_pid" }, - { KERN_TAINTED, "tainted" }, - { KERN_CADPID, "cad_pid" }, - { KERN_PIDMAX, "pid_max" }, - { KERN_CORE_PATTERN, "core_pattern" }, - { KERN_PANIC_ON_OOPS, "panic_on_oops" }, - { KERN_HPPA_PWRSW, "soft-power" }, - { KERN_HPPA_UNALIGNED, "unaligned-trap" }, - - { KERN_PRINTK_RATELIMIT, "printk_ratelimit" }, - { KERN_PRINTK_RATELIMIT_BURST, "printk_ratelimit_burst" }, - - { KERN_PTY, "pty", trans_pty_table }, - { KERN_NGROUPS_MAX, "ngroups_max" }, - { KERN_SPARC_SCONS_PWROFF, "scons-poweroff" }, - { KERN_HZ_TIMER, "hz_timer" }, - { KERN_UNKNOWN_NMI_PANIC, "unknown_nmi_panic" }, - { KERN_BOOTLOADER_TYPE, "bootloader_type" }, - { KERN_RANDOMIZE, "randomize_va_space" }, - - { KERN_SPIN_RETRY, "spin_retry" }, - { KERN_ACPI_VIDEO_FLAGS, "acpi_video_flags" }, - { KERN_IA64_UNALIGNED, "ignore-unaligned-usertrap" }, - { KERN_COMPAT_LOG, "compat-log" }, - { KERN_MAX_LOCK_DEPTH, "max_lock_depth" }, - { KERN_NMI_WATCHDOG, "nmi_watchdog" }, - { KERN_PANIC_ON_NMI, "panic_on_unrecovered_nmi" }, - {} -}; - -static const struct trans_ctl_table trans_vm_table[] = { - { VM_OVERCOMMIT_MEMORY, "overcommit_memory" }, - { VM_PAGE_CLUSTER, "page-cluster" }, - { VM_DIRTY_BACKGROUND, "dirty_background_ratio" }, - { VM_DIRTY_RATIO, "dirty_ratio" }, - { VM_DIRTY_WB_CS, "dirty_writeback_centisecs" }, - { VM_DIRTY_EXPIRE_CS, "dirty_expire_centisecs" }, - { VM_NR_PDFLUSH_THREADS, "nr_pdflush_threads" }, - { VM_OVERCOMMIT_RATIO, "overcommit_ratio" }, - /* VM_PAGEBUF unused */ - { VM_HUGETLB_PAGES, "nr_hugepages" }, - { VM_SWAPPINESS, "swappiness" }, - { VM_LOWMEM_RESERVE_RATIO, "lowmem_reserve_ratio" }, - { VM_MIN_FREE_KBYTES, "min_free_kbytes" }, - { VM_MAX_MAP_COUNT, "max_map_count" }, - { VM_LAPTOP_MODE, "laptop_mode" }, - { VM_BLOCK_DUMP, "block_dump" }, - { VM_HUGETLB_GROUP, "hugetlb_shm_group" }, - { VM_VFS_CACHE_PRESSURE, "vfs_cache_pressure" }, - { VM_LEGACY_VA_LAYOUT, "legacy_va_layout" }, - /* VM_SWAP_TOKEN_TIMEOUT unused */ - { VM_DROP_PAGECACHE, "drop_caches" }, - { VM_PERCPU_PAGELIST_FRACTION, "percpu_pagelist_fraction" }, - { VM_ZONE_RECLAIM_MODE, "zone_reclaim_mode" }, - { VM_MIN_UNMAPPED, "min_unmapped_ratio" }, - { VM_PANIC_ON_OOM, "panic_on_oom" }, - { VM_VDSO_ENABLED, "vdso_enabled" }, - { VM_MIN_SLAB, "min_slab_ratio" }, - - {} -}; - -static const struct trans_ctl_table trans_net_core_table[] = { - { NET_CORE_WMEM_MAX, "wmem_max" }, - { NET_CORE_RMEM_MAX, "rmem_max" }, - { NET_CORE_WMEM_DEFAULT, "wmem_default" }, - { NET_CORE_RMEM_DEFAULT, "rmem_default" }, - /* NET_CORE_DESTROY_DELAY unused */ - { NET_CORE_MAX_BACKLOG, "netdev_max_backlog" }, - /* NET_CORE_FASTROUTE unused */ - { NET_CORE_MSG_COST, "message_cost" }, - { NET_CORE_MSG_BURST, "message_burst" }, - { NET_CORE_OPTMEM_MAX, "optmem_max" }, - /* NET_CORE_HOT_LIST_LENGTH unused */ - /* NET_CORE_DIVERT_VERSION unused */ - /* NET_CORE_NO_CONG_THRESH unused */ - /* NET_CORE_NO_CONG unused */ - /* NET_CORE_LO_CONG unused */ - /* NET_CORE_MOD_CONG unused */ - { NET_CORE_DEV_WEIGHT, "dev_weight" }, - { NET_CORE_SOMAXCONN, "somaxconn" }, - { NET_CORE_BUDGET, "netdev_budget" }, - { NET_CORE_AEVENT_ETIME, "xfrm_aevent_etime" }, - { NET_CORE_AEVENT_RSEQTH, "xfrm_aevent_rseqth" }, - { NET_CORE_WARNINGS, "warnings" }, - {}, -}; - -static const struct trans_ctl_table trans_net_unix_table[] = { - /* NET_UNIX_DESTROY_DELAY unused */ - /* NET_UNIX_DELETE_DELAY unused */ - { NET_UNIX_MAX_DGRAM_QLEN, "max_dgram_qlen" }, - {} -}; - -static const struct trans_ctl_table trans_net_ipv4_route_table[] = { - { NET_IPV4_ROUTE_FLUSH, "flush" }, - { NET_IPV4_ROUTE_MIN_DELAY, "min_delay" }, - { NET_IPV4_ROUTE_MAX_DELAY, "max_delay" }, - { NET_IPV4_ROUTE_GC_THRESH, "gc_thresh" }, - { NET_IPV4_ROUTE_MAX_SIZE, "max_size" }, - { NET_IPV4_ROUTE_GC_MIN_INTERVAL, "gc_min_interval" }, - { NET_IPV4_ROUTE_GC_TIMEOUT, "gc_timeout" }, - { NET_IPV4_ROUTE_GC_INTERVAL, "gc_interval" }, - { NET_IPV4_ROUTE_REDIRECT_LOAD, "redirect_load" }, - { NET_IPV4_ROUTE_REDIRECT_NUMBER, "redirect_number" }, - { NET_IPV4_ROUTE_REDIRECT_SILENCE, "redirect_silence" }, - { NET_IPV4_ROUTE_ERROR_COST, "error_cost" }, - { NET_IPV4_ROUTE_ERROR_BURST, "error_burst" }, - { NET_IPV4_ROUTE_GC_ELASTICITY, "gc_elasticity" }, - { NET_IPV4_ROUTE_MTU_EXPIRES, "mtu_expires" }, - { NET_IPV4_ROUTE_MIN_PMTU, "min_pmtu" }, - { NET_IPV4_ROUTE_MIN_ADVMSS, "min_adv_mss" }, - { NET_IPV4_ROUTE_SECRET_INTERVAL, "secret_interval" }, - { NET_IPV4_ROUTE_GC_MIN_INTERVAL_MS, "gc_min_interval_ms" }, - {} -}; - -static const struct trans_ctl_table trans_net_ipv4_conf_vars_table[] = { - { NET_IPV4_CONF_FORWARDING, "forwarding" }, - { NET_IPV4_CONF_MC_FORWARDING, "mc_forwarding" }, - - { NET_IPV4_CONF_PROXY_ARP, "proxy_arp" }, - { NET_IPV4_CONF_ACCEPT_REDIRECTS, "accept_redirects" }, - { NET_IPV4_CONF_SECURE_REDIRECTS, "secure_redirects" }, - { NET_IPV4_CONF_SEND_REDIRECTS, "send_redirects" }, - { NET_IPV4_CONF_SHARED_MEDIA, "shared_media" }, - { NET_IPV4_CONF_RP_FILTER, "rp_filter" }, - { NET_IPV4_CONF_ACCEPT_SOURCE_ROUTE, "accept_source_route" }, - { NET_IPV4_CONF_BOOTP_RELAY, "bootp_relay" }, - { NET_IPV4_CONF_LOG_MARTIANS, "log_martians" }, - { NET_IPV4_CONF_TAG, "tag" }, - { NET_IPV4_CONF_ARPFILTER, "arp_filter" }, - { NET_IPV4_CONF_MEDIUM_ID, "medium_id" }, - { NET_IPV4_CONF_NOXFRM, "disable_xfrm" }, - { NET_IPV4_CONF_NOPOLICY, "disable_policy" }, - { NET_IPV4_CONF_FORCE_IGMP_VERSION, "force_igmp_version" }, - - { NET_IPV4_CONF_ARP_ANNOUNCE, "arp_announce" }, - { NET_IPV4_CONF_ARP_IGNORE, "arp_ignore" }, - { NET_IPV4_CONF_PROMOTE_SECONDARIES, "promote_secondaries" }, - { NET_IPV4_CONF_ARP_ACCEPT, "arp_accept" }, - { NET_IPV4_CONF_ARP_NOTIFY, "arp_notify" }, - {} -}; - -static const struct trans_ctl_table trans_net_ipv4_conf_table[] = { - { NET_PROTO_CONF_ALL, "all", trans_net_ipv4_conf_vars_table }, - { NET_PROTO_CONF_DEFAULT, "default", trans_net_ipv4_conf_vars_table }, - { 0, NULL, trans_net_ipv4_conf_vars_table }, - {} -}; - -static const struct trans_ctl_table trans_net_neigh_vars_table[] = { - { NET_NEIGH_MCAST_SOLICIT, "mcast_solicit" }, - { NET_NEIGH_UCAST_SOLICIT, "ucast_solicit" }, - { NET_NEIGH_APP_SOLICIT, "app_solicit" }, - { NET_NEIGH_RETRANS_TIME, "retrans_time" }, - { NET_NEIGH_REACHABLE_TIME, "base_reachable_time" }, - { NET_NEIGH_DELAY_PROBE_TIME, "delay_first_probe_time" }, - { NET_NEIGH_GC_STALE_TIME, "gc_stale_time" }, - { NET_NEIGH_UNRES_QLEN, "unres_qlen" }, - { NET_NEIGH_PROXY_QLEN, "proxy_qlen" }, - { NET_NEIGH_ANYCAST_DELAY, "anycast_delay" }, - { NET_NEIGH_PROXY_DELAY, "proxy_delay" }, - { NET_NEIGH_LOCKTIME, "locktime" }, - { NET_NEIGH_GC_INTERVAL, "gc_interval" }, - { NET_NEIGH_GC_THRESH1, "gc_thresh1" }, - { NET_NEIGH_GC_THRESH2, "gc_thresh2" }, - { NET_NEIGH_GC_THRESH3, "gc_thresh3" }, - { NET_NEIGH_RETRANS_TIME_MS, "retrans_time_ms" }, - { NET_NEIGH_REACHABLE_TIME_MS, "base_reachable_time_ms" }, - {} -}; - -static const struct trans_ctl_table trans_net_neigh_table[] = { - { NET_PROTO_CONF_DEFAULT, "default", trans_net_neigh_vars_table }, - { 0, NULL, trans_net_neigh_vars_table }, - {} -}; - -static const struct trans_ctl_table trans_net_ipv4_netfilter_table[] = { - { NET_IPV4_NF_CONNTRACK_MAX, "ip_conntrack_max" }, - - { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_SYN_SENT, "ip_conntrack_tcp_timeout_syn_sent" }, - { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_SYN_RECV, "ip_conntrack_tcp_timeout_syn_recv" }, - { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_ESTABLISHED, "ip_conntrack_tcp_timeout_established" }, - { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_FIN_WAIT, "ip_conntrack_tcp_timeout_fin_wait" }, - { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_CLOSE_WAIT, "ip_conntrack_tcp_timeout_close_wait" }, - { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_LAST_ACK, "ip_conntrack_tcp_timeout_last_ack" }, - { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_TIME_WAIT, "ip_conntrack_tcp_timeout_time_wait" }, - { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_CLOSE, "ip_conntrack_tcp_timeout_close" }, - - { NET_IPV4_NF_CONNTRACK_UDP_TIMEOUT, "ip_conntrack_udp_timeout" }, - { NET_IPV4_NF_CONNTRACK_UDP_TIMEOUT_STREAM, "ip_conntrack_udp_timeout_stream" }, - { NET_IPV4_NF_CONNTRACK_ICMP_TIMEOUT, "ip_conntrack_icmp_timeout" }, - { NET_IPV4_NF_CONNTRACK_GENERIC_TIMEOUT, "ip_conntrack_generic_timeout" }, - - { NET_IPV4_NF_CONNTRACK_BUCKETS, "ip_conntrack_buckets" }, - { NET_IPV4_NF_CONNTRACK_LOG_INVALID, "ip_conntrack_log_invalid" }, - { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_MAX_RETRANS, "ip_conntrack_tcp_timeout_max_retrans" }, - { NET_IPV4_NF_CONNTRACK_TCP_LOOSE, "ip_conntrack_tcp_loose" }, - { NET_IPV4_NF_CONNTRACK_TCP_BE_LIBERAL, "ip_conntrack_tcp_be_liberal" }, - { NET_IPV4_NF_CONNTRACK_TCP_MAX_RETRANS, "ip_conntrack_tcp_max_retrans" }, - - { NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_CLOSED, "ip_conntrack_sctp_timeout_closed" }, - { NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_WAIT, "ip_conntrack_sctp_timeout_cookie_wait" }, - { NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_ECHOED, "ip_conntrack_sctp_timeout_cookie_echoed" }, - { NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_ESTABLISHED, "ip_conntrack_sctp_timeout_established" }, - { NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_SENT, "ip_conntrack_sctp_timeout_shutdown_sent" }, - { NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_RECD, "ip_conntrack_sctp_timeout_shutdown_recd" }, - { NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_ACK_SENT, "ip_conntrack_sctp_timeout_shutdown_ack_sent" }, - - { NET_IPV4_NF_CONNTRACK_COUNT, "ip_conntrack_count" }, - { NET_IPV4_NF_CONNTRACK_CHECKSUM, "ip_conntrack_checksum" }, - {} -}; - -static const struct trans_ctl_table trans_net_ipv4_table[] = { - { NET_IPV4_FORWARD, "ip_forward" }, - { NET_IPV4_DYNADDR, "ip_dynaddr" }, - - { NET_IPV4_CONF, "conf", trans_net_ipv4_conf_table }, - { NET_IPV4_NEIGH, "neigh", trans_net_neigh_table }, - { NET_IPV4_ROUTE, "route", trans_net_ipv4_route_table }, - /* NET_IPV4_FIB_HASH unused */ - { NET_IPV4_NETFILTER, "netfilter", trans_net_ipv4_netfilter_table }, - - { NET_IPV4_TCP_TIMESTAMPS, "tcp_timestamps" }, - { NET_IPV4_TCP_WINDOW_SCALING, "tcp_window_scaling" }, - { NET_IPV4_TCP_SACK, "tcp_sack" }, - { NET_IPV4_TCP_RETRANS_COLLAPSE, "tcp_retrans_collapse" }, - { NET_IPV4_DEFAULT_TTL, "ip_default_ttl" }, - /* NET_IPV4_AUTOCONFIG unused */ - { NET_IPV4_NO_PMTU_DISC, "ip_no_pmtu_disc" }, - { NET_IPV4_TCP_SYN_RETRIES, "tcp_syn_retries" }, - { NET_IPV4_IPFRAG_HIGH_THRESH, "ipfrag_high_thresh" }, - { NET_IPV4_IPFRAG_LOW_THRESH, "ipfrag_low_thresh" }, - { NET_IPV4_IPFRAG_TIME, "ipfrag_time" }, - /* NET_IPV4_TCP_MAX_KA_PROBES unused */ - { NET_IPV4_TCP_KEEPALIVE_TIME, "tcp_keepalive_time" }, - { NET_IPV4_TCP_KEEPALIVE_PROBES, "tcp_keepalive_probes" }, - { NET_IPV4_TCP_RETRIES1, "tcp_retries1" }, - { NET_IPV4_TCP_RETRIES2, "tcp_retries2" }, - { NET_IPV4_TCP_FIN_TIMEOUT, "tcp_fin_timeout" }, - /* NET_IPV4_IP_MASQ_DEBUG unused */ - { NET_TCP_SYNCOOKIES, "tcp_syncookies" }, - { NET_TCP_STDURG, "tcp_stdurg" }, - { NET_TCP_RFC1337, "tcp_rfc1337" }, - /* NET_TCP_SYN_TAILDROP unused */ - { NET_TCP_MAX_SYN_BACKLOG, "tcp_max_syn_backlog" }, - { NET_IPV4_LOCAL_PORT_RANGE, "ip_local_port_range" }, - { NET_IPV4_ICMP_ECHO_IGNORE_ALL, "icmp_echo_ignore_all" }, - { NET_IPV4_ICMP_ECHO_IGNORE_BROADCASTS, "icmp_echo_ignore_broadcasts" }, - /* NET_IPV4_ICMP_SOURCEQUENCH_RATE unused */ - /* NET_IPV4_ICMP_DESTUNREACH_RATE unused */ - /* NET_IPV4_ICMP_TIMEEXCEED_RATE unused */ - /* NET_IPV4_ICMP_PARAMPROB_RATE unused */ - /* NET_IPV4_ICMP_ECHOREPLY_RATE unused */ - { NET_IPV4_ICMP_IGNORE_BOGUS_ERROR_RESPONSES, "icmp_ignore_bogus_error_responses" }, - { NET_IPV4_IGMP_MAX_MEMBERSHIPS, "igmp_max_memberships" }, - { NET_TCP_TW_RECYCLE, "tcp_tw_recycle" }, - /* NET_IPV4_ALWAYS_DEFRAG unused */ - { NET_IPV4_TCP_KEEPALIVE_INTVL, "tcp_keepalive_intvl" }, - { NET_IPV4_INET_PEER_THRESHOLD, "inet_peer_threshold" }, - { NET_IPV4_INET_PEER_MINTTL, "inet_peer_minttl" }, - { NET_IPV4_INET_PEER_MAXTTL, "inet_peer_maxttl" }, - { NET_IPV4_INET_PEER_GC_MINTIME, "inet_peer_gc_mintime" }, - { NET_IPV4_INET_PEER_GC_MAXTIME, "inet_peer_gc_maxtime" }, - { NET_TCP_ORPHAN_RETRIES, "tcp_orphan_retries" }, - { NET_TCP_ABORT_ON_OVERFLOW, "tcp_abort_on_overflow" }, - { NET_TCP_SYNACK_RETRIES, "tcp_synack_retries" }, - { NET_TCP_MAX_ORPHANS, "tcp_max_orphans" }, - { NET_TCP_MAX_TW_BUCKETS, "tcp_max_tw_buckets" }, - { NET_TCP_FACK, "tcp_fack" }, - { NET_TCP_REORDERING, "tcp_reordering" }, - { NET_TCP_ECN, "tcp_ecn" }, - { NET_TCP_DSACK, "tcp_dsack" }, - { NET_TCP_MEM, "tcp_mem" }, - { NET_TCP_WMEM, "tcp_wmem" }, - { NET_TCP_RMEM, "tcp_rmem" }, - { NET_TCP_APP_WIN, "tcp_app_win" }, - { NET_TCP_ADV_WIN_SCALE, "tcp_adv_win_scale" }, - { NET_IPV4_NONLOCAL_BIND, "ip_nonlocal_bind" }, - { NET_IPV4_ICMP_RATELIMIT, "icmp_ratelimit" }, - { NET_IPV4_ICMP_RATEMASK, "icmp_ratemask" }, - { NET_TCP_TW_REUSE, "tcp_tw_reuse" }, - { NET_TCP_FRTO, "tcp_frto" }, - { NET_TCP_LOW_LATENCY, "tcp_low_latency" }, - { NET_IPV4_IPFRAG_SECRET_INTERVAL, "ipfrag_secret_interval" }, - { NET_IPV4_IGMP_MAX_MSF, "igmp_max_msf" }, - { NET_TCP_NO_METRICS_SAVE, "tcp_no_metrics_save" }, - /* NET_TCP_DEFAULT_WIN_SCALE unused */ - { NET_TCP_MODERATE_RCVBUF, "tcp_moderate_rcvbuf" }, - { NET_TCP_TSO_WIN_DIVISOR, "tcp_tso_win_divisor" }, - /* NET_TCP_BIC_BETA unused */ - { NET_IPV4_ICMP_ERRORS_USE_INBOUND_IFADDR, "icmp_errors_use_inbound_ifaddr" }, - { NET_TCP_CONG_CONTROL, "tcp_congestion_control" }, - { NET_TCP_ABC, "tcp_abc" }, - { NET_IPV4_IPFRAG_MAX_DIST, "ipfrag_max_dist" }, - { NET_TCP_MTU_PROBING, "tcp_mtu_probing" }, - { NET_TCP_BASE_MSS, "tcp_base_mss" }, - { NET_IPV4_TCP_WORKAROUND_SIGNED_WINDOWS, "tcp_workaround_signed_windows" }, - { NET_TCP_DMA_COPYBREAK, "tcp_dma_copybreak" }, - { NET_TCP_SLOW_START_AFTER_IDLE, "tcp_slow_start_after_idle" }, - { NET_CIPSOV4_CACHE_ENABLE, "cipso_cache_enable" }, - { NET_CIPSOV4_CACHE_BUCKET_SIZE, "cipso_cache_bucket_size" }, - { NET_CIPSOV4_RBM_OPTFMT, "cipso_rbm_optfmt" }, - { NET_CIPSOV4_RBM_STRICTVALID, "cipso_rbm_strictvalid" }, - { NET_TCP_AVAIL_CONG_CONTROL, "tcp_available_congestion_control" }, - { NET_TCP_ALLOWED_CONG_CONTROL, "tcp_allowed_congestion_control" }, - { NET_TCP_MAX_SSTHRESH, "tcp_max_ssthresh" }, - { NET_TCP_FRTO_RESPONSE, "tcp_frto_response" }, - { 2088 /* NET_IPQ_QMAX */, "ip_queue_maxlen" }, - {} -}; - -static const struct trans_ctl_table trans_net_ipx_table[] = { - { NET_IPX_PPROP_BROADCASTING, "ipx_pprop_broadcasting" }, - /* NET_IPX_FORWARDING unused */ - {} -}; - -static const struct trans_ctl_table trans_net_atalk_table[] = { - { NET_ATALK_AARP_EXPIRY_TIME, "aarp-expiry-time" }, - { NET_ATALK_AARP_TICK_TIME, "aarp-tick-time" }, - { NET_ATALK_AARP_RETRANSMIT_LIMIT, "aarp-retransmit-limit" }, - { NET_ATALK_AARP_RESOLVE_TIME, "aarp-resolve-time" }, - {}, -}; - -static const struct trans_ctl_table trans_net_netrom_table[] = { - { NET_NETROM_DEFAULT_PATH_QUALITY, "default_path_quality" }, - { NET_NETROM_OBSOLESCENCE_COUNT_INITIALISER, "obsolescence_count_initialiser" }, - { NET_NETROM_NETWORK_TTL_INITIALISER, "network_ttl_initialiser" }, - { NET_NETROM_TRANSPORT_TIMEOUT, "transport_timeout" }, - { NET_NETROM_TRANSPORT_MAXIMUM_TRIES, "transport_maximum_tries" }, - { NET_NETROM_TRANSPORT_ACKNOWLEDGE_DELAY, "transport_acknowledge_delay" }, - { NET_NETROM_TRANSPORT_BUSY_DELAY, "transport_busy_delay" }, - { NET_NETROM_TRANSPORT_REQUESTED_WINDOW_SIZE, "transport_requested_window_size" }, - { NET_NETROM_TRANSPORT_NO_ACTIVITY_TIMEOUT, "transport_no_activity_timeout" }, - { NET_NETROM_ROUTING_CONTROL, "routing_control" }, - { NET_NETROM_LINK_FAILS_COUNT, "link_fails_count" }, - { NET_NETROM_RESET, "reset" }, - {} -}; - -static const struct trans_ctl_table trans_net_ax25_param_table[] = { - { NET_AX25_IP_DEFAULT_MODE, "ip_default_mode" }, - { NET_AX25_DEFAULT_MODE, "ax25_default_mode" }, - { NET_AX25_BACKOFF_TYPE, "backoff_type" }, - { NET_AX25_CONNECT_MODE, "connect_mode" }, - { NET_AX25_STANDARD_WINDOW, "standard_window_size" }, - { NET_AX25_EXTENDED_WINDOW, "extended_window_size" }, - { NET_AX25_T1_TIMEOUT, "t1_timeout" }, - { NET_AX25_T2_TIMEOUT, "t2_timeout" }, - { NET_AX25_T3_TIMEOUT, "t3_timeout" }, - { NET_AX25_IDLE_TIMEOUT, "idle_timeout" }, - { NET_AX25_N2, "maximum_retry_count" }, - { NET_AX25_PACLEN, "maximum_packet_length" }, - { NET_AX25_PROTOCOL, "protocol" }, - { NET_AX25_DAMA_SLAVE_TIMEOUT, "dama_slave_timeout" }, - {} -}; - -static const struct trans_ctl_table trans_net_ax25_table[] = { - { 0, NULL, trans_net_ax25_param_table }, - {} -}; - -static const struct trans_ctl_table trans_net_bridge_table[] = { - { NET_BRIDGE_NF_CALL_ARPTABLES, "bridge-nf-call-arptables" }, - { NET_BRIDGE_NF_CALL_IPTABLES, "bridge-nf-call-iptables" }, - { NET_BRIDGE_NF_CALL_IP6TABLES, "bridge-nf-call-ip6tables" }, - { NET_BRIDGE_NF_FILTER_VLAN_TAGGED, "bridge-nf-filter-vlan-tagged" }, - { NET_BRIDGE_NF_FILTER_PPPOE_TAGGED, "bridge-nf-filter-pppoe-tagged" }, - {} -}; - -static const struct trans_ctl_table trans_net_rose_table[] = { - { NET_ROSE_RESTART_REQUEST_TIMEOUT, "restart_request_timeout" }, - { NET_ROSE_CALL_REQUEST_TIMEOUT, "call_request_timeout" }, - { NET_ROSE_RESET_REQUEST_TIMEOUT, "reset_request_timeout" }, - { NET_ROSE_CLEAR_REQUEST_TIMEOUT, "clear_request_timeout" }, - { NET_ROSE_ACK_HOLD_BACK_TIMEOUT, "acknowledge_hold_back_timeout" }, - { NET_ROSE_ROUTING_CONTROL, "routing_control" }, - { NET_ROSE_LINK_FAIL_TIMEOUT, "link_fail_timeout" }, - { NET_ROSE_MAX_VCS, "maximum_virtual_circuits" }, - { NET_ROSE_WINDOW_SIZE, "window_size" }, - { NET_ROSE_NO_ACTIVITY_TIMEOUT, "no_activity_timeout" }, - {} -}; - -static const struct trans_ctl_table trans_net_ipv6_conf_var_table[] = { - { NET_IPV6_FORWARDING, "forwarding" }, - { NET_IPV6_HOP_LIMIT, "hop_limit" }, - { NET_IPV6_MTU, "mtu" }, - { NET_IPV6_ACCEPT_RA, "accept_ra" }, - { NET_IPV6_ACCEPT_REDIRECTS, "accept_redirects" }, - { NET_IPV6_AUTOCONF, "autoconf" }, - { NET_IPV6_DAD_TRANSMITS, "dad_transmits" }, - { NET_IPV6_RTR_SOLICITS, "router_solicitations" }, - { NET_IPV6_RTR_SOLICIT_INTERVAL, "router_solicitation_interval" }, - { NET_IPV6_RTR_SOLICIT_DELAY, "router_solicitation_delay" }, - { NET_IPV6_USE_TEMPADDR, "use_tempaddr" }, - { NET_IPV6_TEMP_VALID_LFT, "temp_valid_lft" }, - { NET_IPV6_TEMP_PREFERED_LFT, "temp_prefered_lft" }, - { NET_IPV6_REGEN_MAX_RETRY, "regen_max_retry" }, - { NET_IPV6_MAX_DESYNC_FACTOR, "max_desync_factor" }, - { NET_IPV6_MAX_ADDRESSES, "max_addresses" }, - { NET_IPV6_FORCE_MLD_VERSION, "force_mld_version" }, - { NET_IPV6_ACCEPT_RA_DEFRTR, "accept_ra_defrtr" }, - { NET_IPV6_ACCEPT_RA_PINFO, "accept_ra_pinfo" }, - { NET_IPV6_ACCEPT_RA_RTR_PREF, "accept_ra_rtr_pref" }, - { NET_IPV6_RTR_PROBE_INTERVAL, "router_probe_interval" }, - { NET_IPV6_ACCEPT_RA_RT_INFO_MAX_PLEN, "accept_ra_rt_info_max_plen" }, - { NET_IPV6_PROXY_NDP, "proxy_ndp" }, - { NET_IPV6_ACCEPT_SOURCE_ROUTE, "accept_source_route" }, - {} -}; - -static const struct trans_ctl_table trans_net_ipv6_conf_table[] = { - { NET_PROTO_CONF_ALL, "all", trans_net_ipv6_conf_var_table }, - { NET_PROTO_CONF_DEFAULT, "default", trans_net_ipv6_conf_var_table }, - { 0, NULL, trans_net_ipv6_conf_var_table }, - {} -}; - -static const struct trans_ctl_table trans_net_ipv6_route_table[] = { - { NET_IPV6_ROUTE_FLUSH, "flush" }, - { NET_IPV6_ROUTE_GC_THRESH, "gc_thresh" }, - { NET_IPV6_ROUTE_MAX_SIZE, "max_size" }, - { NET_IPV6_ROUTE_GC_MIN_INTERVAL, "gc_min_interval" }, - { NET_IPV6_ROUTE_GC_TIMEOUT, "gc_timeout" }, - { NET_IPV6_ROUTE_GC_INTERVAL, "gc_interval" }, - { NET_IPV6_ROUTE_GC_ELASTICITY, "gc_elasticity" }, - { NET_IPV6_ROUTE_MTU_EXPIRES, "mtu_expires" }, - { NET_IPV6_ROUTE_MIN_ADVMSS, "min_adv_mss" }, - { NET_IPV6_ROUTE_GC_MIN_INTERVAL_MS, "gc_min_interval_ms" }, - {} -}; - -static const struct trans_ctl_table trans_net_ipv6_icmp_table[] = { - { NET_IPV6_ICMP_RATELIMIT, "ratelimit" }, - {} -}; - -static const struct trans_ctl_table trans_net_ipv6_table[] = { - { NET_IPV6_CONF, "conf", trans_net_ipv6_conf_table }, - { NET_IPV6_NEIGH, "neigh", trans_net_neigh_table }, - { NET_IPV6_ROUTE, "route", trans_net_ipv6_route_table }, - { NET_IPV6_ICMP, "icmp", trans_net_ipv6_icmp_table }, - { NET_IPV6_BINDV6ONLY, "bindv6only" }, - { NET_IPV6_IP6FRAG_HIGH_THRESH, "ip6frag_high_thresh" }, - { NET_IPV6_IP6FRAG_LOW_THRESH, "ip6frag_low_thresh" }, - { NET_IPV6_IP6FRAG_TIME, "ip6frag_time" }, - { NET_IPV6_IP6FRAG_SECRET_INTERVAL, "ip6frag_secret_interval" }, - { NET_IPV6_MLD_MAX_MSF, "mld_max_msf" }, - { 2088 /* IPQ_QMAX */, "ip6_queue_maxlen" }, - {} -}; - -static const struct trans_ctl_table trans_net_x25_table[] = { - { NET_X25_RESTART_REQUEST_TIMEOUT, "restart_request_timeout" }, - { NET_X25_CALL_REQUEST_TIMEOUT, "call_request_timeout" }, - { NET_X25_RESET_REQUEST_TIMEOUT, "reset_request_timeout" }, - { NET_X25_CLEAR_REQUEST_TIMEOUT, "clear_request_timeout" }, - { NET_X25_ACK_HOLD_BACK_TIMEOUT, "acknowledgement_hold_back_timeout" }, - { NET_X25_FORWARD, "x25_forward" }, - {} -}; - -static const struct trans_ctl_table trans_net_tr_table[] = { - { NET_TR_RIF_TIMEOUT, "rif_timeout" }, - {} -}; - - -static const struct trans_ctl_table trans_net_decnet_conf_vars[] = { - { NET_DECNET_CONF_DEV_FORWARDING, "forwarding" }, - { NET_DECNET_CONF_DEV_PRIORITY, "priority" }, - { NET_DECNET_CONF_DEV_T2, "t2" }, - { NET_DECNET_CONF_DEV_T3, "t3" }, - {} -}; - -static const struct trans_ctl_table trans_net_decnet_conf[] = { - { 0, NULL, trans_net_decnet_conf_vars }, - {} -}; - -static const struct trans_ctl_table trans_net_decnet_table[] = { - { NET_DECNET_CONF, "conf", trans_net_decnet_conf }, - { NET_DECNET_NODE_ADDRESS, "node_address" }, - { NET_DECNET_NODE_NAME, "node_name" }, - { NET_DECNET_DEFAULT_DEVICE, "default_device" }, - { NET_DECNET_TIME_WAIT, "time_wait" }, - { NET_DECNET_DN_COUNT, "dn_count" }, - { NET_DECNET_DI_COUNT, "di_count" }, - { NET_DECNET_DR_COUNT, "dr_count" }, - { NET_DECNET_DST_GC_INTERVAL, "dst_gc_interval" }, - { NET_DECNET_NO_FC_MAX_CWND, "no_fc_max_cwnd" }, - { NET_DECNET_MEM, "decnet_mem" }, - { NET_DECNET_RMEM, "decnet_rmem" }, - { NET_DECNET_WMEM, "decnet_wmem" }, - { NET_DECNET_DEBUG_LEVEL, "debug" }, - {} -}; - -static const struct trans_ctl_table trans_net_sctp_table[] = { - { NET_SCTP_RTO_INITIAL, "rto_initial" }, - { NET_SCTP_RTO_MIN, "rto_min" }, - { NET_SCTP_RTO_MAX, "rto_max" }, - { NET_SCTP_RTO_ALPHA, "rto_alpha_exp_divisor" }, - { NET_SCTP_RTO_BETA, "rto_beta_exp_divisor" }, - { NET_SCTP_VALID_COOKIE_LIFE, "valid_cookie_life" }, - { NET_SCTP_ASSOCIATION_MAX_RETRANS, "association_max_retrans" }, - { NET_SCTP_PATH_MAX_RETRANS, "path_max_retrans" }, - { NET_SCTP_MAX_INIT_RETRANSMITS, "max_init_retransmits" }, - { NET_SCTP_HB_INTERVAL, "hb_interval" }, - { NET_SCTP_PRESERVE_ENABLE, "cookie_preserve_enable" }, - { NET_SCTP_MAX_BURST, "max_burst" }, - { NET_SCTP_ADDIP_ENABLE, "addip_enable" }, - { NET_SCTP_PRSCTP_ENABLE, "prsctp_enable" }, - { NET_SCTP_SNDBUF_POLICY, "sndbuf_policy" }, - { NET_SCTP_SACK_TIMEOUT, "sack_timeout" }, - { NET_SCTP_RCVBUF_POLICY, "rcvbuf_policy" }, - {} -}; - -static const struct trans_ctl_table trans_net_llc_llc2_timeout_table[] = { - { NET_LLC2_ACK_TIMEOUT, "ack" }, - { NET_LLC2_P_TIMEOUT, "p" }, - { NET_LLC2_REJ_TIMEOUT, "rej" }, - { NET_LLC2_BUSY_TIMEOUT, "busy" }, - {} -}; - -static const struct trans_ctl_table trans_net_llc_station_table[] = { - { NET_LLC_STATION_ACK_TIMEOUT, "ack_timeout" }, - {} -}; - -static const struct trans_ctl_table trans_net_llc_llc2_table[] = { - { NET_LLC2, "timeout", trans_net_llc_llc2_timeout_table }, - {} -}; - -static const struct trans_ctl_table trans_net_llc_table[] = { - { NET_LLC2, "llc2", trans_net_llc_llc2_table }, - { NET_LLC_STATION, "station", trans_net_llc_station_table }, - {} -}; - -static const struct trans_ctl_table trans_net_netfilter_table[] = { - { NET_NF_CONNTRACK_MAX, "nf_conntrack_max" }, - { NET_NF_CONNTRACK_TCP_TIMEOUT_SYN_SENT, "nf_conntrack_tcp_timeout_syn_sent" }, - { NET_NF_CONNTRACK_TCP_TIMEOUT_SYN_RECV, "nf_conntrack_tcp_timeout_syn_recv" }, - { NET_NF_CONNTRACK_TCP_TIMEOUT_ESTABLISHED, "nf_conntrack_tcp_timeout_established" }, - { NET_NF_CONNTRACK_TCP_TIMEOUT_FIN_WAIT, "nf_conntrack_tcp_timeout_fin_wait" }, - { NET_NF_CONNTRACK_TCP_TIMEOUT_CLOSE_WAIT, "nf_conntrack_tcp_timeout_close_wait" }, - { NET_NF_CONNTRACK_TCP_TIMEOUT_LAST_ACK, "nf_conntrack_tcp_timeout_last_ack" }, - { NET_NF_CONNTRACK_TCP_TIMEOUT_TIME_WAIT, "nf_conntrack_tcp_timeout_time_wait" }, - { NET_NF_CONNTRACK_TCP_TIMEOUT_CLOSE, "nf_conntrack_tcp_timeout_close" }, - { NET_NF_CONNTRACK_UDP_TIMEOUT, "nf_conntrack_udp_timeout" }, - { NET_NF_CONNTRACK_UDP_TIMEOUT_STREAM, "nf_conntrack_udp_timeout_stream" }, - { NET_NF_CONNTRACK_ICMP_TIMEOUT, "nf_conntrack_icmp_timeout" }, - { NET_NF_CONNTRACK_GENERIC_TIMEOUT, "nf_conntrack_generic_timeout" }, - { NET_NF_CONNTRACK_BUCKETS, "nf_conntrack_buckets" }, - { NET_NF_CONNTRACK_LOG_INVALID, "nf_conntrack_log_invalid" }, - { NET_NF_CONNTRACK_TCP_TIMEOUT_MAX_RETRANS, "nf_conntrack_tcp_timeout_max_retrans" }, - { NET_NF_CONNTRACK_TCP_LOOSE, "nf_conntrack_tcp_loose" }, - { NET_NF_CONNTRACK_TCP_BE_LIBERAL, "nf_conntrack_tcp_be_liberal" }, - { NET_NF_CONNTRACK_TCP_MAX_RETRANS, "nf_conntrack_tcp_max_retrans" }, - { NET_NF_CONNTRACK_SCTP_TIMEOUT_CLOSED, "nf_conntrack_sctp_timeout_closed" }, - { NET_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_WAIT, "nf_conntrack_sctp_timeout_cookie_wait" }, - { NET_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_ECHOED, "nf_conntrack_sctp_timeout_cookie_echoed" }, - { NET_NF_CONNTRACK_SCTP_TIMEOUT_ESTABLISHED, "nf_conntrack_sctp_timeout_established" }, - { NET_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_SENT, "nf_conntrack_sctp_timeout_shutdown_sent" }, - { NET_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_RECD, "nf_conntrack_sctp_timeout_shutdown_recd" }, - { NET_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_ACK_SENT, "nf_conntrack_sctp_timeout_shutdown_ack_sent" }, - { NET_NF_CONNTRACK_COUNT, "nf_conntrack_count" }, - { NET_NF_CONNTRACK_ICMPV6_TIMEOUT, "nf_conntrack_icmpv6_timeout" }, - { NET_NF_CONNTRACK_FRAG6_TIMEOUT, "nf_conntrack_frag6_timeout" }, - { NET_NF_CONNTRACK_FRAG6_LOW_THRESH, "nf_conntrack_frag6_low_thresh" }, - { NET_NF_CONNTRACK_FRAG6_HIGH_THRESH, "nf_conntrack_frag6_high_thresh" }, - { NET_NF_CONNTRACK_CHECKSUM, "nf_conntrack_checksum" }, - - {} -}; - -static const struct trans_ctl_table trans_net_dccp_table[] = { - { NET_DCCP_DEFAULT, "default" }, - {} -}; - -static const struct trans_ctl_table trans_net_irda_table[] = { - { NET_IRDA_DISCOVERY, "discovery" }, - { NET_IRDA_DEVNAME, "devname" }, - { NET_IRDA_DEBUG, "debug" }, - { NET_IRDA_FAST_POLL, "fast_poll_increase" }, - { NET_IRDA_DISCOVERY_SLOTS, "discovery_slots" }, - { NET_IRDA_DISCOVERY_TIMEOUT, "discovery_timeout" }, - { NET_IRDA_SLOT_TIMEOUT, "slot_timeout" }, - { NET_IRDA_MAX_BAUD_RATE, "max_baud_rate" }, - { NET_IRDA_MIN_TX_TURN_TIME, "min_tx_turn_time" }, - { NET_IRDA_MAX_TX_DATA_SIZE, "max_tx_data_size" }, - { NET_IRDA_MAX_TX_WINDOW, "max_tx_window" }, - { NET_IRDA_MAX_NOREPLY_TIME, "max_noreply_time" }, - { NET_IRDA_WARN_NOREPLY_TIME, "warn_noreply_time" }, - { NET_IRDA_LAP_KEEPALIVE_TIME, "lap_keepalive_time" }, - {} -}; - -static const struct trans_ctl_table trans_net_table[] = { - { NET_CORE, "core", trans_net_core_table }, - /* NET_ETHER not used */ - /* NET_802 not used */ - { NET_UNIX, "unix", trans_net_unix_table }, - { NET_IPV4, "ipv4", trans_net_ipv4_table }, - { NET_IPX, "ipx", trans_net_ipx_table }, - { NET_ATALK, "appletalk", trans_net_atalk_table }, - { NET_NETROM, "netrom", trans_net_netrom_table }, - { NET_AX25, "ax25", trans_net_ax25_table }, - { NET_BRIDGE, "bridge", trans_net_bridge_table }, - { NET_ROSE, "rose", trans_net_rose_table }, - { NET_IPV6, "ipv6", trans_net_ipv6_table }, - { NET_X25, "x25", trans_net_x25_table }, - { NET_TR, "token-ring", trans_net_tr_table }, - { NET_DECNET, "decnet", trans_net_decnet_table }, - /* NET_ECONET not used */ - { NET_SCTP, "sctp", trans_net_sctp_table }, - { NET_LLC, "llc", trans_net_llc_table }, - { NET_NETFILTER, "netfilter", trans_net_netfilter_table }, - { NET_DCCP, "dccp", trans_net_dccp_table }, - { NET_IRDA, "irda", trans_net_irda_table }, - { 2089, "nf_conntrack_max" }, - {} -}; - -static const struct trans_ctl_table trans_fs_quota_table[] = { - { FS_DQ_LOOKUPS, "lookups" }, - { FS_DQ_DROPS, "drops" }, - { FS_DQ_READS, "reads" }, - { FS_DQ_WRITES, "writes" }, - { FS_DQ_CACHE_HITS, "cache_hits" }, - { FS_DQ_ALLOCATED, "allocated_dquots" }, - { FS_DQ_FREE, "free_dquots" }, - { FS_DQ_SYNCS, "syncs" }, - { FS_DQ_WARNINGS, "warnings" }, - {} -}; - -static const struct trans_ctl_table trans_fs_xfs_table[] = { - { XFS_SGID_INHERIT, "irix_sgid_inherit" }, - { XFS_SYMLINK_MODE, "irix_symlink_mode" }, - { XFS_PANIC_MASK, "panic_mask" }, - - { XFS_ERRLEVEL, "error_level" }, - { XFS_SYNCD_TIMER, "xfssyncd_centisecs" }, - { XFS_INHERIT_SYNC, "inherit_sync" }, - { XFS_INHERIT_NODUMP, "inherit_nodump" }, - { XFS_INHERIT_NOATIME, "inherit_noatime" }, - { XFS_BUF_TIMER, "xfsbufd_centisecs" }, - { XFS_BUF_AGE, "age_buffer_centisecs" }, - { XFS_INHERIT_NOSYM, "inherit_nosymlinks" }, - { XFS_ROTORSTEP, "rotorstep" }, - { XFS_INHERIT_NODFRG, "inherit_nodefrag" }, - { XFS_FILESTREAM_TIMER, "filestream_centisecs" }, - { XFS_STATS_CLEAR, "stats_clear" }, - {} -}; - -static const struct trans_ctl_table trans_fs_ocfs2_nm_table[] = { - { 1, "hb_ctl_path" }, - {} -}; - -static const struct trans_ctl_table trans_fs_ocfs2_table[] = { - { 1, "nm", trans_fs_ocfs2_nm_table }, - {} -}; - -static const struct trans_ctl_table trans_inotify_table[] = { - { INOTIFY_MAX_USER_INSTANCES, "max_user_instances" }, - { INOTIFY_MAX_USER_WATCHES, "max_user_watches" }, - { INOTIFY_MAX_QUEUED_EVENTS, "max_queued_events" }, - {} -}; - -static const struct trans_ctl_table trans_fs_table[] = { - { FS_NRINODE, "inode-nr" }, - { FS_STATINODE, "inode-state" }, - /* FS_MAXINODE unused */ - /* FS_NRDQUOT unused */ - /* FS_MAXDQUOT unused */ - { FS_NRFILE, "file-nr" }, - { FS_MAXFILE, "file-max" }, - { FS_DENTRY, "dentry-state" }, - /* FS_NRSUPER unused */ - /* FS_MAXUPSER unused */ - { FS_OVERFLOWUID, "overflowuid" }, - { FS_OVERFLOWGID, "overflowgid" }, - { FS_LEASES, "leases-enable" }, - { FS_DIR_NOTIFY, "dir-notify-enable" }, - { FS_LEASE_TIME, "lease-break-time" }, - { FS_DQSTATS, "quota", trans_fs_quota_table }, - { FS_XFS, "xfs", trans_fs_xfs_table }, - { FS_AIO_NR, "aio-nr" }, - { FS_AIO_MAX_NR, "aio-max-nr" }, - { FS_INOTIFY, "inotify", trans_inotify_table }, - { FS_OCFS2, "ocfs2", trans_fs_ocfs2_table }, - { KERN_SETUID_DUMPABLE, "suid_dumpable" }, - {} -}; - -static const struct trans_ctl_table trans_debug_table[] = { - {} -}; - -static const struct trans_ctl_table trans_cdrom_table[] = { - { DEV_CDROM_INFO, "info" }, - { DEV_CDROM_AUTOCLOSE, "autoclose" }, - { DEV_CDROM_AUTOEJECT, "autoeject" }, - { DEV_CDROM_DEBUG, "debug" }, - { DEV_CDROM_LOCK, "lock" }, - { DEV_CDROM_CHECK_MEDIA, "check_media" }, - {} -}; - -static const struct trans_ctl_table trans_ipmi_table[] = { - { DEV_IPMI_POWEROFF_POWERCYCLE, "poweroff_powercycle" }, - {} -}; - -static const struct trans_ctl_table trans_mac_hid_files[] = { - /* DEV_MAC_HID_KEYBOARD_SENDS_LINUX_KEYCODES unused */ - /* DEV_MAC_HID_KEYBOARD_LOCK_KEYCODES unused */ - { DEV_MAC_HID_MOUSE_BUTTON_EMULATION, "mouse_button_emulation" }, - { DEV_MAC_HID_MOUSE_BUTTON2_KEYCODE, "mouse_button2_keycode" }, - { DEV_MAC_HID_MOUSE_BUTTON3_KEYCODE, "mouse_button3_keycode" }, - /* DEV_MAC_HID_ADB_MOUSE_SENDS_KEYCODES unused */ - {} -}; - -static const struct trans_ctl_table trans_raid_table[] = { - { DEV_RAID_SPEED_LIMIT_MIN, "speed_limit_min" }, - { DEV_RAID_SPEED_LIMIT_MAX, "speed_limit_max" }, - {} -}; - -static const struct trans_ctl_table trans_scsi_table[] = { - { DEV_SCSI_LOGGING_LEVEL, "logging_level" }, - {} -}; - -static const struct trans_ctl_table trans_parport_default_table[] = { - { DEV_PARPORT_DEFAULT_TIMESLICE, "timeslice" }, - { DEV_PARPORT_DEFAULT_SPINTIME, "spintime" }, - {} -}; - -static const struct trans_ctl_table trans_parport_device_table[] = { - { DEV_PARPORT_DEVICE_TIMESLICE, "timeslice" }, - {} -}; - -static const struct trans_ctl_table trans_parport_devices_table[] = { - { DEV_PARPORT_DEVICES_ACTIVE, "active" }, - { 0, NULL, trans_parport_device_table }, - {} -}; - -static const struct trans_ctl_table trans_parport_parport_table[] = { - { DEV_PARPORT_SPINTIME, "spintime" }, - { DEV_PARPORT_BASE_ADDR, "base-addr" }, - { DEV_PARPORT_IRQ, "irq" }, - { DEV_PARPORT_DMA, "dma" }, - { DEV_PARPORT_MODES, "modes" }, - { DEV_PARPORT_DEVICES, "devices", trans_parport_devices_table }, - { DEV_PARPORT_AUTOPROBE, "autoprobe" }, - { DEV_PARPORT_AUTOPROBE + 1, "autoprobe0" }, - { DEV_PARPORT_AUTOPROBE + 2, "autoprobe1" }, - { DEV_PARPORT_AUTOPROBE + 3, "autoprobe2" }, - { DEV_PARPORT_AUTOPROBE + 4, "autoprobe3" }, - {} -}; -static const struct trans_ctl_table trans_parport_table[] = { - { DEV_PARPORT_DEFAULT, "default", trans_parport_default_table }, - { 0, NULL, trans_parport_parport_table }, - {} -}; - -static const struct trans_ctl_table trans_dev_table[] = { - { DEV_CDROM, "cdrom", trans_cdrom_table }, - /* DEV_HWMON unused */ - { DEV_PARPORT, "parport", trans_parport_table }, - { DEV_RAID, "raid", trans_raid_table }, - { DEV_MAC_HID, "mac_hid", trans_mac_hid_files }, - { DEV_SCSI, "scsi", trans_scsi_table }, - { DEV_IPMI, "ipmi", trans_ipmi_table }, - {} -}; - -static const struct trans_ctl_table trans_bus_isa_table[] = { - { BUS_ISA_MEM_BASE, "membase" }, - { BUS_ISA_PORT_BASE, "portbase" }, - { BUS_ISA_PORT_SHIFT, "portshift" }, - {} -}; - -static const struct trans_ctl_table trans_bus_table[] = { - { CTL_BUS_ISA, "isa", trans_bus_isa_table }, - {} -}; - -static const struct trans_ctl_table trans_arlan_conf_table0[] = { - { 1, "spreadingCode" }, - { 2, "channelNumber" }, - { 3, "scramblingDisable" }, - { 4, "txAttenuation" }, - { 5, "systemId" }, - { 6, "maxDatagramSize" }, - { 7, "maxFrameSize" }, - { 8, "maxRetries" }, - { 9, "receiveMode" }, - { 10, "priority" }, - { 11, "rootOrRepeater" }, - { 12, "SID" }, - { 13, "registrationMode" }, - { 14, "registrationFill" }, - { 15, "localTalkAddress" }, - { 16, "codeFormat" }, - { 17, "numChannels" }, - { 18, "channel1" }, - { 19, "channel2" }, - { 20, "channel3" }, - { 21, "channel4" }, - { 22, "txClear" }, - { 23, "txRetries" }, - { 24, "txRouting" }, - { 25, "txScrambled" }, - { 26, "rxParameter" }, - { 27, "txTimeoutMs" }, - { 28, "waitCardTimeout" }, - { 29, "channelSet" }, - { 30, "name" }, - { 31, "waitTime" }, - { 32, "lParameter" }, - { 33, "_15" }, - { 34, "headerSize" }, - { 36, "tx_delay_ms" }, - { 37, "retries" }, - { 38, "ReTransmitPacketMaxSize" }, - { 39, "waitReTransmitPacketMaxSize" }, - { 40, "fastReTransCount" }, - { 41, "driverRetransmissions" }, - { 42, "txAckTimeoutMs" }, - { 43, "registrationInterrupts" }, - { 44, "hardwareType" }, - { 45, "radioType" }, - { 46, "writeEEPROM" }, - { 47, "writeRadioType" }, - { 48, "entry_exit_debug" }, - { 49, "debug" }, - { 50, "in_speed" }, - { 51, "out_speed" }, - { 52, "in_speed10" }, - { 53, "out_speed10" }, - { 54, "in_speed_max" }, - { 55, "out_speed_max" }, - { 56, "measure_rate" }, - { 57, "pre_Command_Wait" }, - { 58, "rx_tweak1" }, - { 59, "rx_tweak2" }, - { 60, "tx_queue_len" }, - - { 150, "arlan0-txRing" }, - { 151, "arlan0-rxRing" }, - { 152, "arlan0-18" }, - { 153, "arlan0-ring" }, - { 154, "arlan0-shm-cpy" }, - { 155, "config0" }, - { 156, "reset0" }, - {} -}; - -static const struct trans_ctl_table trans_arlan_conf_table1[] = { - { 1, "spreadingCode" }, - { 2, "channelNumber" }, - { 3, "scramblingDisable" }, - { 4, "txAttenuation" }, - { 5, "systemId" }, - { 6, "maxDatagramSize" }, - { 7, "maxFrameSize" }, - { 8, "maxRetries" }, - { 9, "receiveMode" }, - { 10, "priority" }, - { 11, "rootOrRepeater" }, - { 12, "SID" }, - { 13, "registrationMode" }, - { 14, "registrationFill" }, - { 15, "localTalkAddress" }, - { 16, "codeFormat" }, - { 17, "numChannels" }, - { 18, "channel1" }, - { 19, "channel2" }, - { 20, "channel3" }, - { 21, "channel4" }, - { 22, "txClear" }, - { 23, "txRetries" }, - { 24, "txRouting" }, - { 25, "txScrambled" }, - { 26, "rxParameter" }, - { 27, "txTimeoutMs" }, - { 28, "waitCardTimeout" }, - { 29, "channelSet" }, - { 30, "name" }, - { 31, "waitTime" }, - { 32, "lParameter" }, - { 33, "_15" }, - { 34, "headerSize" }, - { 36, "tx_delay_ms" }, - { 37, "retries" }, - { 38, "ReTransmitPacketMaxSize" }, - { 39, "waitReTransmitPacketMaxSize" }, - { 40, "fastReTransCount" }, - { 41, "driverRetransmissions" }, - { 42, "txAckTimeoutMs" }, - { 43, "registrationInterrupts" }, - { 44, "hardwareType" }, - { 45, "radioType" }, - { 46, "writeEEPROM" }, - { 47, "writeRadioType" }, - { 48, "entry_exit_debug" }, - { 49, "debug" }, - { 50, "in_speed" }, - { 51, "out_speed" }, - { 52, "in_speed10" }, - { 53, "out_speed10" }, - { 54, "in_speed_max" }, - { 55, "out_speed_max" }, - { 56, "measure_rate" }, - { 57, "pre_Command_Wait" }, - { 58, "rx_tweak1" }, - { 59, "rx_tweak2" }, - { 60, "tx_queue_len" }, - - { 150, "arlan1-txRing" }, - { 151, "arlan1-rxRing" }, - { 152, "arlan1-18" }, - { 153, "arlan1-ring" }, - { 154, "arlan1-shm-cpy" }, - { 155, "config1" }, - { 156, "reset1" }, - {} -}; - -static const struct trans_ctl_table trans_arlan_conf_table2[] = { - { 1, "spreadingCode" }, - { 2, "channelNumber" }, - { 3, "scramblingDisable" }, - { 4, "txAttenuation" }, - { 5, "systemId" }, - { 6, "maxDatagramSize" }, - { 7, "maxFrameSize" }, - { 8, "maxRetries" }, - { 9, "receiveMode" }, - { 10, "priority" }, - { 11, "rootOrRepeater" }, - { 12, "SID" }, - { 13, "registrationMode" }, - { 14, "registrationFill" }, - { 15, "localTalkAddress" }, - { 16, "codeFormat" }, - { 17, "numChannels" }, - { 18, "channel1" }, - { 19, "channel2" }, - { 20, "channel3" }, - { 21, "channel4" }, - { 22, "txClear" }, - { 23, "txRetries" }, - { 24, "txRouting" }, - { 25, "txScrambled" }, - { 26, "rxParameter" }, - { 27, "txTimeoutMs" }, - { 28, "waitCardTimeout" }, - { 29, "channelSet" }, - { 30, "name" }, - { 31, "waitTime" }, - { 32, "lParameter" }, - { 33, "_15" }, - { 34, "headerSize" }, - { 36, "tx_delay_ms" }, - { 37, "retries" }, - { 38, "ReTransmitPacketMaxSize" }, - { 39, "waitReTransmitPacketMaxSize" }, - { 40, "fastReTransCount" }, - { 41, "driverRetransmissions" }, - { 42, "txAckTimeoutMs" }, - { 43, "registrationInterrupts" }, - { 44, "hardwareType" }, - { 45, "radioType" }, - { 46, "writeEEPROM" }, - { 47, "writeRadioType" }, - { 48, "entry_exit_debug" }, - { 49, "debug" }, - { 50, "in_speed" }, - { 51, "out_speed" }, - { 52, "in_speed10" }, - { 53, "out_speed10" }, - { 54, "in_speed_max" }, - { 55, "out_speed_max" }, - { 56, "measure_rate" }, - { 57, "pre_Command_Wait" }, - { 58, "rx_tweak1" }, - { 59, "rx_tweak2" }, - { 60, "tx_queue_len" }, - - { 150, "arlan2-txRing" }, - { 151, "arlan2-rxRing" }, - { 152, "arlan2-18" }, - { 153, "arlan2-ring" }, - { 154, "arlan2-shm-cpy" }, - { 155, "config2" }, - { 156, "reset2" }, - {} -}; - -static const struct trans_ctl_table trans_arlan_conf_table3[] = { - { 1, "spreadingCode" }, - { 2, "channelNumber" }, - { 3, "scramblingDisable" }, - { 4, "txAttenuation" }, - { 5, "systemId" }, - { 6, "maxDatagramSize" }, - { 7, "maxFrameSize" }, - { 8, "maxRetries" }, - { 9, "receiveMode" }, - { 10, "priority" }, - { 11, "rootOrRepeater" }, - { 12, "SID" }, - { 13, "registrationMode" }, - { 14, "registrationFill" }, - { 15, "localTalkAddress" }, - { 16, "codeFormat" }, - { 17, "numChannels" }, - { 18, "channel1" }, - { 19, "channel2" }, - { 20, "channel3" }, - { 21, "channel4" }, - { 22, "txClear" }, - { 23, "txRetries" }, - { 24, "txRouting" }, - { 25, "txScrambled" }, - { 26, "rxParameter" }, - { 27, "txTimeoutMs" }, - { 28, "waitCardTimeout" }, - { 29, "channelSet" }, - { 30, "name" }, - { 31, "waitTime" }, - { 32, "lParameter" }, - { 33, "_15" }, - { 34, "headerSize" }, - { 36, "tx_delay_ms" }, - { 37, "retries" }, - { 38, "ReTransmitPacketMaxSize" }, - { 39, "waitReTransmitPacketMaxSize" }, - { 40, "fastReTransCount" }, - { 41, "driverRetransmissions" }, - { 42, "txAckTimeoutMs" }, - { 43, "registrationInterrupts" }, - { 44, "hardwareType" }, - { 45, "radioType" }, - { 46, "writeEEPROM" }, - { 47, "writeRadioType" }, - { 48, "entry_exit_debug" }, - { 49, "debug" }, - { 50, "in_speed" }, - { 51, "out_speed" }, - { 52, "in_speed10" }, - { 53, "out_speed10" }, - { 54, "in_speed_max" }, - { 55, "out_speed_max" }, - { 56, "measure_rate" }, - { 57, "pre_Command_Wait" }, - { 58, "rx_tweak1" }, - { 59, "rx_tweak2" }, - { 60, "tx_queue_len" }, - - { 150, "arlan3-txRing" }, - { 151, "arlan3-rxRing" }, - { 152, "arlan3-18" }, - { 153, "arlan3-ring" }, - { 154, "arlan3-shm-cpy" }, - { 155, "config3" }, - { 156, "reset3" }, - {} -}; - -static const struct trans_ctl_table trans_arlan_table[] = { - { 1, "arlan0", trans_arlan_conf_table0 }, - { 2, "arlan1", trans_arlan_conf_table1 }, - { 3, "arlan2", trans_arlan_conf_table2 }, - { 4, "arlan3", trans_arlan_conf_table3 }, - {} -}; - -static const struct trans_ctl_table trans_s390dbf_table[] = { - { 5678 /* CTL_S390DBF_STOPPABLE */, "debug_stoppable" }, - { 5679 /* CTL_S390DBF_ACTIVE */, "debug_active" }, - {} -}; - -static const struct trans_ctl_table trans_sunrpc_table[] = { - { CTL_RPCDEBUG, "rpc_debug" }, - { CTL_NFSDEBUG, "nfs_debug" }, - { CTL_NFSDDEBUG, "nfsd_debug" }, - { CTL_NLMDEBUG, "nlm_debug" }, - { CTL_SLOTTABLE_UDP, "udp_slot_table_entries" }, - { CTL_SLOTTABLE_TCP, "tcp_slot_table_entries" }, - { CTL_MIN_RESVPORT, "min_resvport" }, - { CTL_MAX_RESVPORT, "max_resvport" }, - {} -}; - -static const struct trans_ctl_table trans_pm_table[] = { - { 1 /* CTL_PM_SUSPEND */, "suspend" }, - { 2 /* CTL_PM_CMODE */, "cmode" }, - { 3 /* CTL_PM_P0 */, "p0" }, - { 4 /* CTL_PM_CM */, "cm" }, - {} -}; - -static const struct trans_ctl_table trans_frv_table[] = { - { 1, "cache-mode" }, - { 2, "pin-cxnr" }, - {} -}; - -static const struct trans_ctl_table trans_root_table[] = { - { CTL_KERN, "kernel", trans_kern_table }, - { CTL_VM, "vm", trans_vm_table }, - { CTL_NET, "net", trans_net_table }, - /* CTL_PROC not used */ - { CTL_FS, "fs", trans_fs_table }, - { CTL_DEBUG, "debug", trans_debug_table }, - { CTL_DEV, "dev", trans_dev_table }, - { CTL_BUS, "bus", trans_bus_table }, - { CTL_ABI, "abi" }, - /* CTL_CPU not used */ - { CTL_ARLAN, "arlan", trans_arlan_table }, - { CTL_S390DBF, "s390dbf", trans_s390dbf_table }, - { CTL_SUNRPC, "sunrpc", trans_sunrpc_table }, - { CTL_PM, "pm", trans_pm_table }, - { CTL_FRV, "frv", trans_frv_table }, - {} -}; - - - static int sysctl_depth(struct ctl_table *table) { @@ -1261,47 +28,6 @@ static struct ctl_table *sysctl_parent(struct ctl_table *table, int n) return table; } -static const struct trans_ctl_table *sysctl_binary_lookup(struct ctl_table *table) -{ - struct ctl_table *test; - const struct trans_ctl_table *ref; - int cur_depth; - - cur_depth = sysctl_depth(table); - - ref = trans_root_table; -repeat: - test = sysctl_parent(table, cur_depth); - for (; ref->ctl_name || ref->procname || ref->child; ref++) { - int match = 0; - - if (cur_depth && !ref->child) - continue; - - if (test->procname && ref->procname && - (strcmp(test->procname, ref->procname) == 0)) - match++; - - if (test->ctl_name && ref->ctl_name && - (test->ctl_name == ref->ctl_name)) - match++; - - if (!ref->ctl_name && !ref->procname) - match++; - - if (match) { - if (cur_depth != 0) { - cur_depth--; - ref = ref->child; - goto repeat; - } - goto out; - } - } - ref = NULL; -out: - return ref; -} static void sysctl_print_path(struct ctl_table *table) { @@ -1315,26 +41,6 @@ static void sysctl_print_path(struct ctl_table *table) } } printk(" "); - if (table->ctl_name) { - for (i = depth; i >= 0; i--) { - tmp = sysctl_parent(table, i); - printk(".%d", tmp->ctl_name); - } - } -} - -static void sysctl_repair_table(struct ctl_table *table) -{ - /* Don't complain about the classic default - * sysctl strategy routine. Maybe later we - * can get the tables fixed and complain about - * this. - */ - if (table->ctl_name && table->procname && - (table->proc_handler == proc_dointvec) && - (!table->strategy)) { - table->strategy = sysctl_data; - } } static struct ctl_table *sysctl_check_lookup(struct nsproxy *namespaces, @@ -1352,7 +58,7 @@ static struct ctl_table *sysctl_check_lookup(struct nsproxy *namespaces, ref = head->ctl_table; repeat: test = sysctl_parent(table, cur_depth); - for (; ref->ctl_name || ref->procname; ref++) { + for (; ref->procname; ref++) { int match = 0; if (cur_depth && !ref->child) continue; @@ -1361,10 +67,6 @@ repeat: (strcmp(test->procname, ref->procname) == 0)) match++; - if (test->ctl_name && ref->ctl_name && - (test->ctl_name == ref->ctl_name)) - match++; - if (match) { if (cur_depth != 0) { cur_depth--; @@ -1392,38 +94,6 @@ static void set_fail(const char **fail, struct ctl_table *table, const char *str *fail = str; } -static int sysctl_check_dir(struct nsproxy *namespaces, - struct ctl_table *table) -{ - struct ctl_table *ref; - int error; - - error = 0; - ref = sysctl_check_lookup(namespaces, table); - if (ref) { - int match = 0; - if ((!table->procname && !ref->procname) || - (table->procname && ref->procname && - (strcmp(table->procname, ref->procname) == 0))) - match++; - - if ((!table->ctl_name && !ref->ctl_name) || - (table->ctl_name && ref->ctl_name && - (table->ctl_name == ref->ctl_name))) - match++; - - if (match != 2) { - printk(KERN_ERR "%s: failed: ", __func__); - sysctl_print_path(table); - printk(" ref: "); - sysctl_print_path(ref); - printk("\n"); - error = -EINVAL; - } - } - return error; -} - static void sysctl_check_leaf(struct nsproxy *namespaces, struct ctl_table *table, const char **fail) { @@ -1434,37 +104,15 @@ static void sysctl_check_leaf(struct nsproxy *namespaces, set_fail(fail, table, "Sysctl already exists"); } -static void sysctl_check_bin_path(struct ctl_table *table, const char **fail) -{ - const struct trans_ctl_table *ref; - - ref = sysctl_binary_lookup(table); - if (table->ctl_name && !ref) - set_fail(fail, table, "Unknown sysctl binary path"); - if (ref) { - if (ref->procname && - (!table->procname || - (strcmp(table->procname, ref->procname) != 0))) - set_fail(fail, table, "procname does not match binary path procname"); - - if (ref->ctl_name && table->ctl_name && - (table->ctl_name != ref->ctl_name)) - set_fail(fail, table, "ctl_name does not match binary path ctl_name"); - } -} - int sysctl_check_table(struct nsproxy *namespaces, struct ctl_table *table) { int error = 0; - for (; table->ctl_name || table->procname; table++) { + for (; table->procname; table++) { const char *fail = NULL; - sysctl_repair_table(table); if (table->parent) { if (table->procname && !table->parent->procname) set_fail(&fail, table, "Parent without procname"); - if (table->ctl_name && !table->parent->ctl_name) - set_fail(&fail, table, "Parent without ctl_name"); } if (!table->procname) set_fail(&fail, table, "No procname"); @@ -1477,21 +125,12 @@ int sysctl_check_table(struct nsproxy *namespaces, struct ctl_table *table) set_fail(&fail, table, "Writable sysctl directory"); if (table->proc_handler) set_fail(&fail, table, "Directory with proc_handler"); - if (table->strategy) - set_fail(&fail, table, "Directory with strategy"); if (table->extra1) set_fail(&fail, table, "Directory with extra1"); if (table->extra2) set_fail(&fail, table, "Directory with extra2"); - if (sysctl_check_dir(namespaces, table)) - set_fail(&fail, table, "Inconsistent directory names"); } else { - if ((table->strategy == sysctl_data) || - (table->strategy == sysctl_string) || - (table->strategy == sysctl_intvec) || - (table->strategy == sysctl_jiffies) || - (table->strategy == sysctl_ms_jiffies) || - (table->proc_handler == proc_dostring) || + if ((table->proc_handler == proc_dostring) || (table->proc_handler == proc_dointvec) || (table->proc_handler == proc_dointvec_minmax) || (table->proc_handler == proc_dointvec_jiffies) || @@ -1513,14 +152,6 @@ int sysctl_check_table(struct nsproxy *namespaces, struct ctl_table *table) set_fail(&fail, table, "No max"); } } -#ifdef CONFIG_SYSCTL_SYSCALL - if (table->ctl_name && !table->strategy) - set_fail(&fail, table, "Missing strategy"); -#endif -#if 0 - if (!table->ctl_name && table->strategy) - set_fail(&fail, table, "Strategy without ctl_name"); -#endif #ifdef CONFIG_PROC_SYSCTL if (table->procname && !table->proc_handler) set_fail(&fail, table, "No proc_handler"); @@ -1531,7 +162,6 @@ int sysctl_check_table(struct nsproxy *namespaces, struct ctl_table *table) #endif sysctl_check_leaf(namespaces, table, &fail); } - sysctl_check_bin_path(table, &fail); if (table->mode > 0777) set_fail(&fail, table, "bogus .mode"); if (fail) { diff --git a/kernel/time.c b/kernel/time.c index 2e2e469a7fec..804798005d19 100644 --- a/kernel/time.c +++ b/kernel/time.c @@ -662,6 +662,36 @@ u64 nsec_to_clock_t(u64 x) #endif } +/** + * nsecs_to_jiffies - Convert nsecs in u64 to jiffies + * + * @n: nsecs in u64 + * + * Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64. + * And this doesn't return MAX_JIFFY_OFFSET since this function is designed + * for scheduler, not for use in device drivers to calculate timeout value. + * + * note: + * NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512) + * ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years + */ +unsigned long nsecs_to_jiffies(u64 n) +{ +#if (NSEC_PER_SEC % HZ) == 0 + /* Common case, HZ = 100, 128, 200, 250, 256, 500, 512, 1000 etc. */ + return div_u64(n, NSEC_PER_SEC / HZ); +#elif (HZ % 512) == 0 + /* overflow after 292 years if HZ = 1024 */ + return div_u64(n * HZ / 512, NSEC_PER_SEC / 512); +#else + /* + * Generic case - optimized for cases where HZ is a multiple of 3. + * overflow after 64.99 years, exact for HZ = 60, 72, 90, 120 etc. + */ + return div_u64(n * 9, (9ull * NSEC_PER_SEC + HZ / 2) / HZ); +#endif +} + #if (BITS_PER_LONG < 64) u64 get_jiffies_64(void) { diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index b416512ad17f..d006554888dc 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -339,6 +339,27 @@ config POWER_TRACER power management decisions, specifically the C-state and P-state behavior. +config KSYM_TRACER + bool "Trace read and write access on kernel memory locations" + depends on HAVE_HW_BREAKPOINT + select TRACING + help + This tracer helps find read and write operations on any given kernel + symbol i.e. /proc/kallsyms. + +config PROFILE_KSYM_TRACER + bool "Profile all kernel memory accesses on 'watched' variables" + depends on KSYM_TRACER + help + This tracer profiles kernel accesses on variables watched through the + ksym tracer ftrace plugin. Depending upon the hardware, all read + and write operations on kernel variables can be monitored for + accesses. + + The results will be displayed in: + /debugfs/tracing/profile_ksym + + Say N if unsure. config STACK_TRACER bool "Trace max stack" @@ -428,6 +449,23 @@ config BLK_DEV_IO_TRACE If unsure, say N. +config KPROBE_EVENT + depends on KPROBES + depends on X86 + bool "Enable kprobes-based dynamic events" + select TRACING + default y + help + This allows the user to add tracing events (similar to tracepoints) on the fly + via the ftrace interface. See Documentation/trace/kprobetrace.txt + for more details. + + Those events can be inserted wherever kprobes can probe, and record + various register and memory values. + + This option is also required by perf-probe subcommand of perf tools. If + you want to use perf tools, this option is strongly recommended. + config DYNAMIC_FTRACE bool "enable/disable ftrace tracepoints dynamically" depends on FUNCTION_TRACER diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index 26f03ac07c2b..cd9ecd89ec77 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -53,6 +53,8 @@ obj-$(CONFIG_EVENT_TRACING) += trace_export.o obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o obj-$(CONFIG_EVENT_PROFILE) += trace_event_profile.o obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o +obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o +obj-$(CONFIG_KSYM_TRACER) += trace_ksym.o obj-$(CONFIG_EVENT_TRACING) += power-traces.o libftrace-y := ftrace.o diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 6dc4e5ef7a01..e51a1bcb7bed 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -60,6 +60,13 @@ static int last_ftrace_enabled; /* Quick disabling of function tracer. */ int function_trace_stop; +/* List for set_ftrace_pid's pids. */ +LIST_HEAD(ftrace_pids); +struct ftrace_pid { + struct list_head list; + struct pid *pid; +}; + /* * ftrace_disabled is set when an anomaly is discovered. * ftrace_disabled is much stronger than ftrace_enabled. @@ -78,6 +85,10 @@ ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub; ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub; ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub; +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +static int ftrace_set_func(unsigned long *array, int *idx, char *buffer); +#endif + static void ftrace_list_func(unsigned long ip, unsigned long parent_ip) { struct ftrace_ops *op = ftrace_list; @@ -155,7 +166,7 @@ static int __register_ftrace_function(struct ftrace_ops *ops) else func = ftrace_list_func; - if (ftrace_pid_trace) { + if (!list_empty(&ftrace_pids)) { set_ftrace_pid_function(func); func = ftrace_pid_func; } @@ -203,7 +214,7 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops) if (ftrace_list->next == &ftrace_list_end) { ftrace_func_t func = ftrace_list->func; - if (ftrace_pid_trace) { + if (!list_empty(&ftrace_pids)) { set_ftrace_pid_function(func); func = ftrace_pid_func; } @@ -231,7 +242,7 @@ static void ftrace_update_pid_func(void) func = __ftrace_trace_function; #endif - if (ftrace_pid_trace) { + if (!list_empty(&ftrace_pids)) { set_ftrace_pid_function(func); func = ftrace_pid_func; } else { @@ -821,8 +832,6 @@ static __init void ftrace_profile_debugfs(struct dentry *d_tracer) } #endif /* CONFIG_FUNCTION_PROFILER */ -/* set when tracing only a pid */ -struct pid *ftrace_pid_trace; static struct pid * const ftrace_swapper_pid = &init_struct_pid; #ifdef CONFIG_DYNAMIC_FTRACE @@ -1261,12 +1270,34 @@ static int ftrace_update_code(struct module *mod) ftrace_new_addrs = p->newlist; p->flags = 0L; - /* convert record (i.e, patch mcount-call with NOP) */ - if (ftrace_code_disable(mod, p)) { - p->flags |= FTRACE_FL_CONVERTED; - ftrace_update_cnt++; - } else + /* + * Do the initial record convertion from mcount jump + * to the NOP instructions. + */ + if (!ftrace_code_disable(mod, p)) { ftrace_free_rec(p); + continue; + } + + p->flags |= FTRACE_FL_CONVERTED; + ftrace_update_cnt++; + + /* + * If the tracing is enabled, go ahead and enable the record. + * + * The reason not to enable the record immediatelly is the + * inherent check of ftrace_make_nop/ftrace_make_call for + * correct previous instructions. Making first the NOP + * conversion puts the module to the correct state, thus + * passing the ftrace_make_call check. + */ + if (ftrace_start_up) { + int failed = __ftrace_replace_code(p, 1); + if (failed) { + ftrace_bug(failed, p->ip); + ftrace_free_rec(p); + } + } } stop = ftrace_now(raw_smp_processor_id()); @@ -1656,60 +1687,6 @@ ftrace_regex_lseek(struct file *file, loff_t offset, int origin) return ret; } -enum { - MATCH_FULL, - MATCH_FRONT_ONLY, - MATCH_MIDDLE_ONLY, - MATCH_END_ONLY, -}; - -/* - * (static function - no need for kernel doc) - * - * Pass in a buffer containing a glob and this function will - * set search to point to the search part of the buffer and - * return the type of search it is (see enum above). - * This does modify buff. - * - * Returns enum type. - * search returns the pointer to use for comparison. - * not returns 1 if buff started with a '!' - * 0 otherwise. - */ -static int -ftrace_setup_glob(char *buff, int len, char **search, int *not) -{ - int type = MATCH_FULL; - int i; - - if (buff[0] == '!') { - *not = 1; - buff++; - len--; - } else - *not = 0; - - *search = buff; - - for (i = 0; i < len; i++) { - if (buff[i] == '*') { - if (!i) { - *search = buff + 1; - type = MATCH_END_ONLY; - } else { - if (type == MATCH_END_ONLY) - type = MATCH_MIDDLE_ONLY; - else - type = MATCH_FRONT_ONLY; - buff[i] = 0; - break; - } - } - } - - return type; -} - static int ftrace_match(char *str, char *regex, int len, int type) { int matched = 0; @@ -1758,7 +1735,7 @@ static void ftrace_match_records(char *buff, int len, int enable) int not; flag = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE; - type = ftrace_setup_glob(buff, len, &search, ¬); + type = filter_parse_regex(buff, len, &search, ¬); search_len = strlen(search); @@ -1826,7 +1803,7 @@ static void ftrace_match_module_records(char *buff, char *mod, int enable) } if (strlen(buff)) { - type = ftrace_setup_glob(buff, strlen(buff), &search, ¬); + type = filter_parse_regex(buff, strlen(buff), &search, ¬); search_len = strlen(search); } @@ -1991,7 +1968,7 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, int count = 0; char *search; - type = ftrace_setup_glob(glob, strlen(glob), &search, ¬); + type = filter_parse_regex(glob, strlen(glob), &search, ¬); len = strlen(search); /* we do not support '!' for function probes */ @@ -2068,7 +2045,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, else if (glob) { int not; - type = ftrace_setup_glob(glob, strlen(glob), &search, ¬); + type = filter_parse_regex(glob, strlen(glob), &search, ¬); len = strlen(search); /* we do not support '!' for function probes */ @@ -2312,6 +2289,32 @@ static int __init set_ftrace_filter(char *str) } __setup("ftrace_filter=", set_ftrace_filter); +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata; +static int __init set_graph_function(char *str) +{ + strlcpy(ftrace_graph_buf, str, FTRACE_FILTER_SIZE); + return 1; +} +__setup("ftrace_graph_filter=", set_graph_function); + +static void __init set_ftrace_early_graph(char *buf) +{ + int ret; + char *func; + + while (buf) { + func = strsep(&buf, ","); + /* we allow only one expression at a time */ + ret = ftrace_set_func(ftrace_graph_funcs, &ftrace_graph_count, + func); + if (ret) + printk(KERN_DEBUG "ftrace: function %s not " + "traceable\n", func); + } +} +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + static void __init set_ftrace_early_filter(char *buf, int enable) { char *func; @@ -2328,6 +2331,10 @@ static void __init set_ftrace_early_filters(void) set_ftrace_early_filter(ftrace_filter_buf, 1); if (ftrace_notrace_buf[0]) set_ftrace_early_filter(ftrace_notrace_buf, 0); +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + if (ftrace_graph_buf[0]) + set_ftrace_early_graph(ftrace_graph_buf); +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ } static int @@ -2513,7 +2520,7 @@ ftrace_set_func(unsigned long *array, int *idx, char *buffer) return -ENODEV; /* decode regex */ - type = ftrace_setup_glob(buffer, strlen(buffer), &search, ¬); + type = filter_parse_regex(buffer, strlen(buffer), &search, ¬); if (not) return -EINVAL; @@ -2624,7 +2631,7 @@ static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer) return 0; } -static int ftrace_convert_nops(struct module *mod, +static int ftrace_process_locs(struct module *mod, unsigned long *start, unsigned long *end) { @@ -2684,7 +2691,7 @@ static void ftrace_init_module(struct module *mod, { if (ftrace_disabled || start == end) return; - ftrace_convert_nops(mod, start, end); + ftrace_process_locs(mod, start, end); } static int ftrace_module_notify(struct notifier_block *self, @@ -2745,7 +2752,7 @@ void __init ftrace_init(void) last_ftrace_enabled = ftrace_enabled = 1; - ret = ftrace_convert_nops(NULL, + ret = ftrace_process_locs(NULL, __start_mcount_loc, __stop_mcount_loc); @@ -2778,23 +2785,6 @@ static inline void ftrace_startup_enable(int command) { } # define ftrace_shutdown_sysctl() do { } while (0) #endif /* CONFIG_DYNAMIC_FTRACE */ -static ssize_t -ftrace_pid_read(struct file *file, char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - char buf[64]; - int r; - - if (ftrace_pid_trace == ftrace_swapper_pid) - r = sprintf(buf, "swapper tasks\n"); - else if (ftrace_pid_trace) - r = sprintf(buf, "%u\n", pid_vnr(ftrace_pid_trace)); - else - r = sprintf(buf, "no pid\n"); - - return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); -} - static void clear_ftrace_swapper(void) { struct task_struct *p; @@ -2845,14 +2835,12 @@ static void set_ftrace_pid(struct pid *pid) rcu_read_unlock(); } -static void clear_ftrace_pid_task(struct pid **pid) +static void clear_ftrace_pid_task(struct pid *pid) { - if (*pid == ftrace_swapper_pid) + if (pid == ftrace_swapper_pid) clear_ftrace_swapper(); else - clear_ftrace_pid(*pid); - - *pid = NULL; + clear_ftrace_pid(pid); } static void set_ftrace_pid_task(struct pid *pid) @@ -2863,74 +2851,184 @@ static void set_ftrace_pid_task(struct pid *pid) set_ftrace_pid(pid); } -static ssize_t -ftrace_pid_write(struct file *filp, const char __user *ubuf, - size_t cnt, loff_t *ppos) +static int ftrace_pid_add(int p) { struct pid *pid; - char buf[64]; - long val; - int ret; + struct ftrace_pid *fpid; + int ret = -EINVAL; - if (cnt >= sizeof(buf)) - return -EINVAL; + mutex_lock(&ftrace_lock); - if (copy_from_user(&buf, ubuf, cnt)) - return -EFAULT; + if (!p) + pid = ftrace_swapper_pid; + else + pid = find_get_pid(p); - buf[cnt] = 0; + if (!pid) + goto out; - ret = strict_strtol(buf, 10, &val); - if (ret < 0) - return ret; + ret = 0; - mutex_lock(&ftrace_lock); - if (val < 0) { - /* disable pid tracing */ - if (!ftrace_pid_trace) - goto out; + list_for_each_entry(fpid, &ftrace_pids, list) + if (fpid->pid == pid) + goto out_put; - clear_ftrace_pid_task(&ftrace_pid_trace); + ret = -ENOMEM; - } else { - /* swapper task is special */ - if (!val) { - pid = ftrace_swapper_pid; - if (pid == ftrace_pid_trace) - goto out; - } else { - pid = find_get_pid(val); + fpid = kmalloc(sizeof(*fpid), GFP_KERNEL); + if (!fpid) + goto out_put; - if (pid == ftrace_pid_trace) { - put_pid(pid); - goto out; - } - } + list_add(&fpid->list, &ftrace_pids); + fpid->pid = pid; - if (ftrace_pid_trace) - clear_ftrace_pid_task(&ftrace_pid_trace); + set_ftrace_pid_task(pid); - if (!pid) - goto out; + ftrace_update_pid_func(); + ftrace_startup_enable(0); + + mutex_unlock(&ftrace_lock); + return 0; + +out_put: + if (pid != ftrace_swapper_pid) + put_pid(pid); - ftrace_pid_trace = pid; +out: + mutex_unlock(&ftrace_lock); + return ret; +} + +static void ftrace_pid_reset(void) +{ + struct ftrace_pid *fpid, *safe; - set_ftrace_pid_task(ftrace_pid_trace); + mutex_lock(&ftrace_lock); + list_for_each_entry_safe(fpid, safe, &ftrace_pids, list) { + struct pid *pid = fpid->pid; + + clear_ftrace_pid_task(pid); + + list_del(&fpid->list); + kfree(fpid); } - /* update the function call */ ftrace_update_pid_func(); ftrace_startup_enable(0); - out: mutex_unlock(&ftrace_lock); +} - return cnt; +static void *fpid_start(struct seq_file *m, loff_t *pos) +{ + mutex_lock(&ftrace_lock); + + if (list_empty(&ftrace_pids) && (!*pos)) + return (void *) 1; + + return seq_list_start(&ftrace_pids, *pos); +} + +static void *fpid_next(struct seq_file *m, void *v, loff_t *pos) +{ + if (v == (void *)1) + return NULL; + + return seq_list_next(v, &ftrace_pids, pos); +} + +static void fpid_stop(struct seq_file *m, void *p) +{ + mutex_unlock(&ftrace_lock); +} + +static int fpid_show(struct seq_file *m, void *v) +{ + const struct ftrace_pid *fpid = list_entry(v, struct ftrace_pid, list); + + if (v == (void *)1) { + seq_printf(m, "no pid\n"); + return 0; + } + + if (fpid->pid == ftrace_swapper_pid) + seq_printf(m, "swapper tasks\n"); + else + seq_printf(m, "%u\n", pid_vnr(fpid->pid)); + + return 0; +} + +static const struct seq_operations ftrace_pid_sops = { + .start = fpid_start, + .next = fpid_next, + .stop = fpid_stop, + .show = fpid_show, +}; + +static int +ftrace_pid_open(struct inode *inode, struct file *file) +{ + int ret = 0; + + if ((file->f_mode & FMODE_WRITE) && + (file->f_flags & O_TRUNC)) + ftrace_pid_reset(); + + if (file->f_mode & FMODE_READ) + ret = seq_open(file, &ftrace_pid_sops); + + return ret; +} + +static ssize_t +ftrace_pid_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[64], *tmp; + long val; + int ret; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + /* + * Allow "echo > set_ftrace_pid" or "echo -n '' > set_ftrace_pid" + * to clean the filter quietly. + */ + tmp = strstrip(buf); + if (strlen(tmp) == 0) + return 1; + + ret = strict_strtol(tmp, 10, &val); + if (ret < 0) + return ret; + + ret = ftrace_pid_add(val); + + return ret ? ret : cnt; +} + +static int +ftrace_pid_release(struct inode *inode, struct file *file) +{ + if (file->f_mode & FMODE_READ) + seq_release(inode, file); + + return 0; } static const struct file_operations ftrace_pid_fops = { - .read = ftrace_pid_read, - .write = ftrace_pid_write, + .open = ftrace_pid_open, + .write = ftrace_pid_write, + .read = seq_read, + .llseek = seq_lseek, + .release = ftrace_pid_release, }; static __init int ftrace_init_debugfs(void) @@ -3293,4 +3391,3 @@ void ftrace_graph_stop(void) ftrace_stop(); } #endif - diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 5dd017fea6f5..a1ca4956ab5e 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -397,18 +397,21 @@ int ring_buffer_print_page_header(struct trace_seq *s) int ret; ret = trace_seq_printf(s, "\tfield: u64 timestamp;\t" - "offset:0;\tsize:%u;\n", - (unsigned int)sizeof(field.time_stamp)); + "offset:0;\tsize:%u;\tsigned:%u;\n", + (unsigned int)sizeof(field.time_stamp), + (unsigned int)is_signed_type(u64)); ret = trace_seq_printf(s, "\tfield: local_t commit;\t" - "offset:%u;\tsize:%u;\n", + "offset:%u;\tsize:%u;\tsigned:%u;\n", (unsigned int)offsetof(typeof(field), commit), - (unsigned int)sizeof(field.commit)); + (unsigned int)sizeof(field.commit), + (unsigned int)is_signed_type(long)); ret = trace_seq_printf(s, "\tfield: char data;\t" - "offset:%u;\tsize:%u;\n", + "offset:%u;\tsize:%u;\tsigned:%u;\n", (unsigned int)offsetof(typeof(field), data), - (unsigned int)BUF_PAGE_SIZE); + (unsigned int)BUF_PAGE_SIZE, + (unsigned int)is_signed_type(char)); return ret; } @@ -1787,9 +1790,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, static struct ring_buffer_event * rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer, unsigned long length, unsigned long tail, - struct buffer_page *commit_page, struct buffer_page *tail_page, u64 *ts) { + struct buffer_page *commit_page = cpu_buffer->commit_page; struct ring_buffer *buffer = cpu_buffer->buffer; struct buffer_page *next_page; int ret; @@ -1892,13 +1895,10 @@ static struct ring_buffer_event * __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, unsigned type, unsigned long length, u64 *ts) { - struct buffer_page *tail_page, *commit_page; + struct buffer_page *tail_page; struct ring_buffer_event *event; unsigned long tail, write; - commit_page = cpu_buffer->commit_page; - /* we just need to protect against interrupts */ - barrier(); tail_page = cpu_buffer->tail_page; write = local_add_return(length, &tail_page->write); @@ -1909,7 +1909,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, /* See if we shot pass the end of this buffer page */ if (write > BUF_PAGE_SIZE) return rb_move_tail(cpu_buffer, length, tail, - commit_page, tail_page, ts); + tail_page, ts); /* We reserved something on the buffer */ diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c index 573d3cc762c3..b2477caf09c2 100644 --- a/kernel/trace/ring_buffer_benchmark.c +++ b/kernel/trace/ring_buffer_benchmark.c @@ -35,6 +35,28 @@ static int disable_reader; module_param(disable_reader, uint, 0644); MODULE_PARM_DESC(disable_reader, "only run producer"); +static int write_iteration = 50; +module_param(write_iteration, uint, 0644); +MODULE_PARM_DESC(write_iteration, "# of writes between timestamp readings"); + +static int producer_nice = 19; +static int consumer_nice = 19; + +static int producer_fifo = -1; +static int consumer_fifo = -1; + +module_param(producer_nice, uint, 0644); +MODULE_PARM_DESC(producer_nice, "nice prio for producer"); + +module_param(consumer_nice, uint, 0644); +MODULE_PARM_DESC(consumer_nice, "nice prio for consumer"); + +module_param(producer_fifo, uint, 0644); +MODULE_PARM_DESC(producer_fifo, "fifo prio for producer"); + +module_param(consumer_fifo, uint, 0644); +MODULE_PARM_DESC(consumer_fifo, "fifo prio for consumer"); + static int read_events; static int kill_test; @@ -208,15 +230,18 @@ static void ring_buffer_producer(void) do { struct ring_buffer_event *event; int *entry; - - event = ring_buffer_lock_reserve(buffer, 10); - if (!event) { - missed++; - } else { - hit++; - entry = ring_buffer_event_data(event); - *entry = smp_processor_id(); - ring_buffer_unlock_commit(buffer, event); + int i; + + for (i = 0; i < write_iteration; i++) { + event = ring_buffer_lock_reserve(buffer, 10); + if (!event) { + missed++; + } else { + hit++; + entry = ring_buffer_event_data(event); + *entry = smp_processor_id(); + ring_buffer_unlock_commit(buffer, event); + } } do_gettimeofday(&end_tv); @@ -263,6 +288,27 @@ static void ring_buffer_producer(void) if (kill_test) trace_printk("ERROR!\n"); + + if (!disable_reader) { + if (consumer_fifo < 0) + trace_printk("Running Consumer at nice: %d\n", + consumer_nice); + else + trace_printk("Running Consumer at SCHED_FIFO %d\n", + consumer_fifo); + } + if (producer_fifo < 0) + trace_printk("Running Producer at nice: %d\n", + producer_nice); + else + trace_printk("Running Producer at SCHED_FIFO %d\n", + producer_fifo); + + /* Let the user know that the test is running at low priority */ + if (producer_fifo < 0 && consumer_fifo < 0 && + producer_nice == 19 && consumer_nice == 19) + trace_printk("WARNING!!! This test is running at lowest priority.\n"); + trace_printk("Time: %lld (usecs)\n", time); trace_printk("Overruns: %lld\n", overruns); if (disable_reader) @@ -392,6 +438,27 @@ static int __init ring_buffer_benchmark_init(void) if (IS_ERR(producer)) goto out_kill; + /* + * Run them as low-prio background tasks by default: + */ + if (!disable_reader) { + if (consumer_fifo >= 0) { + struct sched_param param = { + .sched_priority = consumer_fifo + }; + sched_setscheduler(consumer, SCHED_FIFO, ¶m); + } else + set_user_nice(consumer, consumer_nice); + } + + if (producer_fifo >= 0) { + struct sched_param param = { + .sched_priority = consumer_fifo + }; + sched_setscheduler(producer, SCHED_FIFO, ¶m); + } else + set_user_nice(producer, producer_nice); + return 0; out_kill: diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index b20d3ec75de9..874f2893cff0 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -129,7 +129,7 @@ static int tracing_set_tracer(const char *buf); static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata; static char *default_bootup_tracer; -static int __init set_ftrace(char *str) +static int __init set_cmdline_ftrace(char *str) { strncpy(bootup_tracer_buf, str, MAX_TRACER_SIZE); default_bootup_tracer = bootup_tracer_buf; @@ -137,7 +137,7 @@ static int __init set_ftrace(char *str) ring_buffer_expanded = 1; return 1; } -__setup("ftrace=", set_ftrace); +__setup("ftrace=", set_cmdline_ftrace); static int __init set_ftrace_dump_on_oops(char *str) { @@ -1361,10 +1361,11 @@ int trace_array_vprintk(struct trace_array *tr, pause_graph_tracing(); raw_local_irq_save(irq_flags); __raw_spin_lock(&trace_buf_lock); - len = vsnprintf(trace_buf, TRACE_BUF_SIZE, fmt, args); - - len = min(len, TRACE_BUF_SIZE-1); - trace_buf[len] = 0; + if (args == NULL) { + strncpy(trace_buf, fmt, TRACE_BUF_SIZE); + len = strlen(trace_buf); + } else + len = vsnprintf(trace_buf, TRACE_BUF_SIZE, fmt, args); size = sizeof(*entry) + len + 1; buffer = tr->buffer; @@ -1373,10 +1374,10 @@ int trace_array_vprintk(struct trace_array *tr, if (!event) goto out_unlock; entry = ring_buffer_event_data(event); - entry->ip = ip; + entry->ip = ip; memcpy(&entry->buf, trace_buf, len); - entry->buf[len] = 0; + entry->buf[len] = '\0'; if (!filter_check_discard(call, entry, buffer, event)) ring_buffer_unlock_commit(buffer, event); @@ -3319,22 +3320,11 @@ tracing_entries_write(struct file *filp, const char __user *ubuf, return cnt; } -static int mark_printk(const char *fmt, ...) -{ - int ret; - va_list args; - va_start(args, fmt); - ret = trace_vprintk(0, fmt, args); - va_end(args); - return ret; -} - static ssize_t tracing_mark_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *fpos) { char *buf; - char *end; if (tracing_disabled) return -EINVAL; @@ -3342,7 +3332,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, if (cnt > TRACE_BUF_SIZE) cnt = TRACE_BUF_SIZE; - buf = kmalloc(cnt + 1, GFP_KERNEL); + buf = kmalloc(cnt + 2, GFP_KERNEL); if (buf == NULL) return -ENOMEM; @@ -3350,14 +3340,13 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, kfree(buf); return -EFAULT; } + if (buf[cnt-1] != '\n') { + buf[cnt] = '\n'; + buf[cnt+1] = '\0'; + } else + buf[cnt] = '\0'; - /* Cut from the first nil or newline. */ - buf[cnt] = '\0'; - end = strchr(buf, '\n'); - if (end) - *end = '\0'; - - cnt = mark_printk("%s\n", buf); + cnt = trace_vprintk(0, buf, NULL); kfree(buf); *fpos += cnt; @@ -3730,7 +3719,7 @@ tracing_stats_read(struct file *filp, char __user *ubuf, s = kmalloc(sizeof(*s), GFP_KERNEL); if (!s) - return ENOMEM; + return -ENOMEM; trace_seq_init(s); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 405cb850b75d..1d7f4830a80d 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -11,6 +11,7 @@ #include <linux/ftrace.h> #include <trace/boot.h> #include <linux/kmemtrace.h> +#include <linux/hw_breakpoint.h> #include <linux/trace_seq.h> #include <linux/ftrace_event.h> @@ -37,6 +38,7 @@ enum trace_type { TRACE_KMEM_ALLOC, TRACE_KMEM_FREE, TRACE_BLK, + TRACE_KSYM, __TRACE_LAST_TYPE, }; @@ -98,9 +100,32 @@ struct syscall_trace_enter { struct syscall_trace_exit { struct trace_entry ent; int nr; - unsigned long ret; + long ret; }; +struct kprobe_trace_entry { + struct trace_entry ent; + unsigned long ip; + int nargs; + unsigned long args[]; +}; + +#define SIZEOF_KPROBE_TRACE_ENTRY(n) \ + (offsetof(struct kprobe_trace_entry, args) + \ + (sizeof(unsigned long) * (n))) + +struct kretprobe_trace_entry { + struct trace_entry ent; + unsigned long func; + unsigned long ret_ip; + int nargs; + unsigned long args[]; +}; + +#define SIZEOF_KRETPROBE_TRACE_ENTRY(n) \ + (offsetof(struct kretprobe_trace_entry, args) + \ + (sizeof(unsigned long) * (n))) + /* * trace_flag_type is an enumeration that holds different * states when a trace occurs. These are: @@ -209,6 +234,7 @@ extern void __ftrace_bad_type(void); TRACE_KMEM_ALLOC); \ IF_ASSIGN(var, ent, struct kmemtrace_free_entry, \ TRACE_KMEM_FREE); \ + IF_ASSIGN(var, ent, struct ksym_trace_entry, TRACE_KSYM);\ __ftrace_bad_type(); \ } while (0) @@ -364,6 +390,8 @@ int register_tracer(struct tracer *type); void unregister_tracer(struct tracer *type); int is_tracing_stopped(void); +extern int process_new_ksym_entry(char *ksymname, int op, unsigned long addr); + extern unsigned long nsecs_to_usecs(unsigned long nsecs); #ifdef CONFIG_TRACER_MAX_TRACE @@ -438,6 +466,8 @@ extern int trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr); extern int trace_selftest_startup_hw_branches(struct tracer *trace, struct trace_array *tr); +extern int trace_selftest_startup_ksym(struct tracer *trace, + struct trace_array *tr); #endif /* CONFIG_FTRACE_STARTUP_TEST */ extern void *head_page(struct trace_array_cpu *data); @@ -483,10 +513,6 @@ static inline int ftrace_graph_addr(unsigned long addr) return 0; } #else -static inline int ftrace_trace_addr(unsigned long addr) -{ - return 1; -} static inline int ftrace_graph_addr(unsigned long addr) { return 1; @@ -500,12 +526,12 @@ print_graph_function(struct trace_iterator *iter) } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ -extern struct pid *ftrace_pid_trace; +extern struct list_head ftrace_pids; #ifdef CONFIG_FUNCTION_TRACER static inline int ftrace_trace_task(struct task_struct *task) { - if (!ftrace_pid_trace) + if (list_empty(&ftrace_pids)) return 1; return test_tsk_trace_trace(task); @@ -687,7 +713,6 @@ struct event_filter { int n_preds; struct filter_pred **preds; char *filter_string; - bool no_reset; }; struct event_subsystem { @@ -699,22 +724,40 @@ struct event_subsystem { }; struct filter_pred; +struct regex; typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event, int val1, int val2); +typedef int (*regex_match_func)(char *str, struct regex *r, int len); + +enum regex_type { + MATCH_FULL = 0, + MATCH_FRONT_ONLY, + MATCH_MIDDLE_ONLY, + MATCH_END_ONLY, +}; + +struct regex { + char pattern[MAX_FILTER_STR_VAL]; + int len; + int field_len; + regex_match_func match; +}; + struct filter_pred { - filter_pred_fn_t fn; - u64 val; - char str_val[MAX_FILTER_STR_VAL]; - int str_len; - char *field_name; - int offset; - int not; - int op; - int pop_n; + filter_pred_fn_t fn; + u64 val; + struct regex regex; + char *field_name; + int offset; + int not; + int op; + int pop_n; }; +extern enum regex_type +filter_parse_regex(char *buff, int len, char **search, int *not); extern void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s); extern int apply_event_filter(struct ftrace_event_call *call, @@ -730,7 +773,8 @@ filter_check_discard(struct ftrace_event_call *call, void *rec, struct ring_buffer *buffer, struct ring_buffer_event *event) { - if (unlikely(call->filter_active) && !filter_match_preds(call, rec)) { + if (unlikely(call->filter_active) && + !filter_match_preds(call->filter, rec)) { ring_buffer_discard_commit(buffer, event); return 1; } diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c index 20c5f92e28a8..878c03f386ba 100644 --- a/kernel/trace/trace_clock.c +++ b/kernel/trace/trace_clock.c @@ -20,6 +20,8 @@ #include <linux/ktime.h> #include <linux/trace_clock.h> +#include "trace.h" + /* * trace_clock_local(): the simplest and least coherent tracing clock. * @@ -28,17 +30,17 @@ */ u64 notrace trace_clock_local(void) { - unsigned long flags; u64 clock; + int resched; /* * sched_clock() is an architecture implemented, fast, scalable, * lockless clock. It is not guaranteed to be coherent across * CPUs, nor across CPU idle events. */ - raw_local_irq_save(flags); + resched = ftrace_preempt_disable(); clock = sched_clock(); - raw_local_irq_restore(flags); + ftrace_preempt_enable(resched); return clock; } diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index ead3d724599d..c16a08f399df 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -364,3 +364,19 @@ FTRACE_ENTRY(kmem_free, kmemtrace_free_entry, F_printk("type:%u call_site:%lx ptr:%p", __entry->type_id, __entry->call_site, __entry->ptr) ); + +FTRACE_ENTRY(ksym_trace, ksym_trace_entry, + + TRACE_KSYM, + + F_STRUCT( + __field( unsigned long, ip ) + __field( unsigned char, type ) + __array( char , cmd, TASK_COMM_LEN ) + __field( unsigned long, addr ) + ), + + F_printk("ip: %pF type: %d ksym_name: %pS cmd: %s", + (void *)__entry->ip, (unsigned int)__entry->type, + (void *)__entry->addr, __entry->cmd) +); diff --git a/kernel/trace/trace_event_profile.c b/kernel/trace/trace_event_profile.c index 8d5c171cc998..d9c60f80aa0d 100644 --- a/kernel/trace/trace_event_profile.c +++ b/kernel/trace/trace_event_profile.c @@ -8,17 +8,14 @@ #include <linux/module.h> #include "trace.h" -/* - * We can't use a size but a type in alloc_percpu() - * So let's create a dummy type that matches the desired size - */ -typedef struct {char buf[FTRACE_MAX_PROFILE_SIZE];} profile_buf_t; -char *trace_profile_buf; -EXPORT_SYMBOL_GPL(trace_profile_buf); +char *perf_trace_buf; +EXPORT_SYMBOL_GPL(perf_trace_buf); + +char *perf_trace_buf_nmi; +EXPORT_SYMBOL_GPL(perf_trace_buf_nmi); -char *trace_profile_buf_nmi; -EXPORT_SYMBOL_GPL(trace_profile_buf_nmi); +typedef typeof(char [FTRACE_MAX_PROFILE_SIZE]) perf_trace_t ; /* Count the events in use (per event id, not per instance) */ static int total_profile_count; @@ -32,20 +29,20 @@ static int ftrace_profile_enable_event(struct ftrace_event_call *event) return 0; if (!total_profile_count) { - buf = (char *)alloc_percpu(profile_buf_t); + buf = (char *)alloc_percpu(perf_trace_t); if (!buf) goto fail_buf; - rcu_assign_pointer(trace_profile_buf, buf); + rcu_assign_pointer(perf_trace_buf, buf); - buf = (char *)alloc_percpu(profile_buf_t); + buf = (char *)alloc_percpu(perf_trace_t); if (!buf) goto fail_buf_nmi; - rcu_assign_pointer(trace_profile_buf_nmi, buf); + rcu_assign_pointer(perf_trace_buf_nmi, buf); } - ret = event->profile_enable(); + ret = event->profile_enable(event); if (!ret) { total_profile_count++; return 0; @@ -53,10 +50,10 @@ static int ftrace_profile_enable_event(struct ftrace_event_call *event) fail_buf_nmi: if (!total_profile_count) { - free_percpu(trace_profile_buf_nmi); - free_percpu(trace_profile_buf); - trace_profile_buf_nmi = NULL; - trace_profile_buf = NULL; + free_percpu(perf_trace_buf_nmi); + free_percpu(perf_trace_buf); + perf_trace_buf_nmi = NULL; + perf_trace_buf = NULL; } fail_buf: atomic_dec(&event->profile_count); @@ -89,14 +86,14 @@ static void ftrace_profile_disable_event(struct ftrace_event_call *event) if (!atomic_add_negative(-1, &event->profile_count)) return; - event->profile_disable(); + event->profile_disable(event); if (!--total_profile_count) { - buf = trace_profile_buf; - rcu_assign_pointer(trace_profile_buf, NULL); + buf = perf_trace_buf; + rcu_assign_pointer(perf_trace_buf, NULL); - nmi_buf = trace_profile_buf_nmi; - rcu_assign_pointer(trace_profile_buf_nmi, NULL); + nmi_buf = perf_trace_buf_nmi; + rcu_assign_pointer(perf_trace_buf_nmi, NULL); /* * Ensure every events in profiling have finished before diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index d128f65778e6..1d18315dc836 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -93,9 +93,7 @@ int trace_define_common_fields(struct ftrace_event_call *call) } EXPORT_SYMBOL_GPL(trace_define_common_fields); -#ifdef CONFIG_MODULES - -static void trace_destroy_fields(struct ftrace_event_call *call) +void trace_destroy_fields(struct ftrace_event_call *call) { struct ftrace_event_field *field, *next; @@ -107,8 +105,6 @@ static void trace_destroy_fields(struct ftrace_event_call *call) } } -#endif /* CONFIG_MODULES */ - static void ftrace_event_enable_disable(struct ftrace_event_call *call, int enable) { @@ -117,14 +113,14 @@ static void ftrace_event_enable_disable(struct ftrace_event_call *call, if (call->enabled) { call->enabled = 0; tracing_stop_cmdline_record(); - call->unregfunc(call->data); + call->unregfunc(call); } break; case 1: if (!call->enabled) { call->enabled = 1; tracing_start_cmdline_record(); - call->regfunc(call->data); + call->regfunc(call); } break; } @@ -507,7 +503,7 @@ extern char *__bad_type_size(void); #define FIELD(type, name) \ sizeof(type) != sizeof(field.name) ? __bad_type_size() : \ #type, "common_" #name, offsetof(typeof(field), name), \ - sizeof(field.name) + sizeof(field.name), is_signed_type(type) static int trace_write_header(struct trace_seq *s) { @@ -515,17 +511,17 @@ static int trace_write_header(struct trace_seq *s) /* struct trace_entry */ return trace_seq_printf(s, - "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n" - "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n" - "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n" - "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n" - "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n" - "\n", - FIELD(unsigned short, type), - FIELD(unsigned char, flags), - FIELD(unsigned char, preempt_count), - FIELD(int, pid), - FIELD(int, lock_depth)); + "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n" + "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n" + "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n" + "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n" + "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n" + "\n", + FIELD(unsigned short, type), + FIELD(unsigned char, flags), + FIELD(unsigned char, preempt_count), + FIELD(int, pid), + FIELD(int, lock_depth)); } static ssize_t @@ -878,9 +874,9 @@ event_subsystem_dir(const char *name, struct dentry *d_events) "'%s/filter' entry\n", name); } - entry = trace_create_file("enable", 0644, system->entry, - (void *)system->name, - &ftrace_system_enable_fops); + trace_create_file("enable", 0644, system->entry, + (void *)system->name, + &ftrace_system_enable_fops); return system->entry; } @@ -892,7 +888,6 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events, const struct file_operations *filter, const struct file_operations *format) { - struct dentry *entry; int ret; /* @@ -910,12 +905,12 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events, } if (call->regfunc) - entry = trace_create_file("enable", 0644, call->dir, call, - enable); + trace_create_file("enable", 0644, call->dir, call, + enable); if (call->id && call->profile_enable) - entry = trace_create_file("id", 0444, call->dir, call, - id); + trace_create_file("id", 0444, call->dir, call, + id); if (call->define_fields) { ret = call->define_fields(call); @@ -924,41 +919,60 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events, " events/%s\n", call->name); return ret; } - entry = trace_create_file("filter", 0644, call->dir, call, - filter); + trace_create_file("filter", 0644, call->dir, call, + filter); } /* A trace may not want to export its format */ if (!call->show_format) return 0; - entry = trace_create_file("format", 0444, call->dir, call, - format); + trace_create_file("format", 0444, call->dir, call, + format); return 0; } -#define for_each_event(event, start, end) \ - for (event = start; \ - (unsigned long)event < (unsigned long)end; \ - event++) +static int __trace_add_event_call(struct ftrace_event_call *call) +{ + struct dentry *d_events; + int ret; -#ifdef CONFIG_MODULES + if (!call->name) + return -EINVAL; -static LIST_HEAD(ftrace_module_file_list); + if (call->raw_init) { + ret = call->raw_init(call); + if (ret < 0) { + if (ret != -ENOSYS) + pr_warning("Could not initialize trace " + "events/%s\n", call->name); + return ret; + } + } -/* - * Modules must own their file_operations to keep up with - * reference counting. - */ -struct ftrace_module_file_ops { - struct list_head list; - struct module *mod; - struct file_operations id; - struct file_operations enable; - struct file_operations format; - struct file_operations filter; -}; + d_events = event_trace_events_dir(); + if (!d_events) + return -ENOENT; + + ret = event_create_dir(call, d_events, &ftrace_event_id_fops, + &ftrace_enable_fops, &ftrace_event_filter_fops, + &ftrace_event_format_fops); + if (!ret) + list_add(&call->list, &ftrace_events); + + return ret; +} + +/* Add an additional event_call dynamically */ +int trace_add_event_call(struct ftrace_event_call *call) +{ + int ret; + mutex_lock(&event_mutex); + ret = __trace_add_event_call(call); + mutex_unlock(&event_mutex); + return ret; +} static void remove_subsystem_dir(const char *name) { @@ -986,6 +1000,53 @@ static void remove_subsystem_dir(const char *name) } } +/* + * Must be called under locking both of event_mutex and trace_event_mutex. + */ +static void __trace_remove_event_call(struct ftrace_event_call *call) +{ + ftrace_event_enable_disable(call, 0); + if (call->event) + __unregister_ftrace_event(call->event); + debugfs_remove_recursive(call->dir); + list_del(&call->list); + trace_destroy_fields(call); + destroy_preds(call); + remove_subsystem_dir(call->system); +} + +/* Remove an event_call */ +void trace_remove_event_call(struct ftrace_event_call *call) +{ + mutex_lock(&event_mutex); + down_write(&trace_event_mutex); + __trace_remove_event_call(call); + up_write(&trace_event_mutex); + mutex_unlock(&event_mutex); +} + +#define for_each_event(event, start, end) \ + for (event = start; \ + (unsigned long)event < (unsigned long)end; \ + event++) + +#ifdef CONFIG_MODULES + +static LIST_HEAD(ftrace_module_file_list); + +/* + * Modules must own their file_operations to keep up with + * reference counting. + */ +struct ftrace_module_file_ops { + struct list_head list; + struct module *mod; + struct file_operations id; + struct file_operations enable; + struct file_operations format; + struct file_operations filter; +}; + static struct ftrace_module_file_ops * trace_create_file_ops(struct module *mod) { @@ -1043,7 +1104,7 @@ static void trace_module_add_events(struct module *mod) if (!call->name) continue; if (call->raw_init) { - ret = call->raw_init(); + ret = call->raw_init(call); if (ret < 0) { if (ret != -ENOSYS) pr_warning("Could not initialize trace " @@ -1061,10 +1122,11 @@ static void trace_module_add_events(struct module *mod) return; } call->mod = mod; - list_add(&call->list, &ftrace_events); - event_create_dir(call, d_events, - &file_ops->id, &file_ops->enable, - &file_ops->filter, &file_ops->format); + ret = event_create_dir(call, d_events, + &file_ops->id, &file_ops->enable, + &file_ops->filter, &file_ops->format); + if (!ret) + list_add(&call->list, &ftrace_events); } } @@ -1078,14 +1140,7 @@ static void trace_module_remove_events(struct module *mod) list_for_each_entry_safe(call, p, &ftrace_events, list) { if (call->mod == mod) { found = true; - ftrace_event_enable_disable(call, 0); - if (call->event) - __unregister_ftrace_event(call->event); - debugfs_remove_recursive(call->dir); - list_del(&call->list); - trace_destroy_fields(call); - destroy_preds(call); - remove_subsystem_dir(call->system); + __trace_remove_event_call(call); } } @@ -1203,7 +1258,7 @@ static __init int event_trace_init(void) if (!call->name) continue; if (call->raw_init) { - ret = call->raw_init(); + ret = call->raw_init(call); if (ret < 0) { if (ret != -ENOSYS) pr_warning("Could not initialize trace " @@ -1211,10 +1266,12 @@ static __init int event_trace_init(void) continue; } } - list_add(&call->list, &ftrace_events); - event_create_dir(call, d_events, &ftrace_event_id_fops, - &ftrace_enable_fops, &ftrace_event_filter_fops, - &ftrace_event_format_fops); + ret = event_create_dir(call, d_events, &ftrace_event_id_fops, + &ftrace_enable_fops, + &ftrace_event_filter_fops, + &ftrace_event_format_fops); + if (!ret) + list_add(&call->list, &ftrace_events); } while (true) { diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 98a6cc5c64ed..50504cb228de 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -18,11 +18,10 @@ * Copyright (C) 2009 Tom Zanussi <tzanussi@gmail.com> */ -#include <linux/debugfs.h> -#include <linux/uaccess.h> #include <linux/module.h> #include <linux/ctype.h> #include <linux/mutex.h> +#include <linux/perf_event.h> #include "trace.h" #include "trace_output.h" @@ -31,6 +30,7 @@ enum filter_op_ids { OP_OR, OP_AND, + OP_GLOB, OP_NE, OP_EQ, OP_LT, @@ -48,16 +48,17 @@ struct filter_op { }; static struct filter_op filter_ops[] = { - { OP_OR, "||", 1 }, - { OP_AND, "&&", 2 }, - { OP_NE, "!=", 4 }, - { OP_EQ, "==", 4 }, - { OP_LT, "<", 5 }, - { OP_LE, "<=", 5 }, - { OP_GT, ">", 5 }, - { OP_GE, ">=", 5 }, - { OP_NONE, "OP_NONE", 0 }, - { OP_OPEN_PAREN, "(", 0 }, + { OP_OR, "||", 1 }, + { OP_AND, "&&", 2 }, + { OP_GLOB, "~", 4 }, + { OP_NE, "!=", 4 }, + { OP_EQ, "==", 4 }, + { OP_LT, "<", 5 }, + { OP_LE, "<=", 5 }, + { OP_GT, ">", 5 }, + { OP_GE, ">=", 5 }, + { OP_NONE, "OP_NONE", 0 }, + { OP_OPEN_PAREN, "(", 0 }, }; enum { @@ -197,9 +198,9 @@ static int filter_pred_string(struct filter_pred *pred, void *event, char *addr = (char *)(event + pred->offset); int cmp, match; - cmp = strncmp(addr, pred->str_val, pred->str_len); + cmp = pred->regex.match(addr, &pred->regex, pred->regex.field_len); - match = (!cmp) ^ pred->not; + match = cmp ^ pred->not; return match; } @@ -211,9 +212,9 @@ static int filter_pred_pchar(struct filter_pred *pred, void *event, char **addr = (char **)(event + pred->offset); int cmp, match; - cmp = strncmp(*addr, pred->str_val, pred->str_len); + cmp = pred->regex.match(*addr, &pred->regex, pred->regex.field_len); - match = (!cmp) ^ pred->not; + match = cmp ^ pred->not; return match; } @@ -237,9 +238,9 @@ static int filter_pred_strloc(struct filter_pred *pred, void *event, char *addr = (char *)(event + str_loc); int cmp, match; - cmp = strncmp(addr, pred->str_val, str_len); + cmp = pred->regex.match(addr, &pred->regex, str_len); - match = (!cmp) ^ pred->not; + match = cmp ^ pred->not; return match; } @@ -250,10 +251,121 @@ static int filter_pred_none(struct filter_pred *pred, void *event, return 0; } +/* Basic regex callbacks */ +static int regex_match_full(char *str, struct regex *r, int len) +{ + if (strncmp(str, r->pattern, len) == 0) + return 1; + return 0; +} + +static int regex_match_front(char *str, struct regex *r, int len) +{ + if (strncmp(str, r->pattern, len) == 0) + return 1; + return 0; +} + +static int regex_match_middle(char *str, struct regex *r, int len) +{ + if (strstr(str, r->pattern)) + return 1; + return 0; +} + +static int regex_match_end(char *str, struct regex *r, int len) +{ + char *ptr = strstr(str, r->pattern); + + if (ptr && (ptr[r->len] == 0)) + return 1; + return 0; +} + +/** + * filter_parse_regex - parse a basic regex + * @buff: the raw regex + * @len: length of the regex + * @search: will point to the beginning of the string to compare + * @not: tell whether the match will have to be inverted + * + * This passes in a buffer containing a regex and this function will + * set search to point to the search part of the buffer and + * return the type of search it is (see enum above). + * This does modify buff. + * + * Returns enum type. + * search returns the pointer to use for comparison. + * not returns 1 if buff started with a '!' + * 0 otherwise. + */ +enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not) +{ + int type = MATCH_FULL; + int i; + + if (buff[0] == '!') { + *not = 1; + buff++; + len--; + } else + *not = 0; + + *search = buff; + + for (i = 0; i < len; i++) { + if (buff[i] == '*') { + if (!i) { + *search = buff + 1; + type = MATCH_END_ONLY; + } else { + if (type == MATCH_END_ONLY) + type = MATCH_MIDDLE_ONLY; + else + type = MATCH_FRONT_ONLY; + buff[i] = 0; + break; + } + } + } + + return type; +} + +static void filter_build_regex(struct filter_pred *pred) +{ + struct regex *r = &pred->regex; + char *search; + enum regex_type type = MATCH_FULL; + int not = 0; + + if (pred->op == OP_GLOB) { + type = filter_parse_regex(r->pattern, r->len, &search, ¬); + r->len = strlen(search); + memmove(r->pattern, search, r->len+1); + } + + switch (type) { + case MATCH_FULL: + r->match = regex_match_full; + break; + case MATCH_FRONT_ONLY: + r->match = regex_match_front; + break; + case MATCH_MIDDLE_ONLY: + r->match = regex_match_middle; + break; + case MATCH_END_ONLY: + r->match = regex_match_end; + break; + } + + pred->not ^= not; +} + /* return 1 if event matches, 0 otherwise (discard) */ -int filter_match_preds(struct ftrace_event_call *call, void *rec) +int filter_match_preds(struct event_filter *filter, void *rec) { - struct event_filter *filter = call->filter; int match, top = 0, val1 = 0, val2 = 0; int stack[MAX_FILTER_PRED]; struct filter_pred *pred; @@ -396,7 +508,7 @@ static void filter_clear_pred(struct filter_pred *pred) { kfree(pred->field_name); pred->field_name = NULL; - pred->str_len = 0; + pred->regex.len = 0; } static int filter_set_pred(struct filter_pred *dest, @@ -426,9 +538,8 @@ static void filter_disable_preds(struct ftrace_event_call *call) filter->preds[i]->fn = filter_pred_none; } -void destroy_preds(struct ftrace_event_call *call) +static void __free_preds(struct event_filter *filter) { - struct event_filter *filter = call->filter; int i; if (!filter) @@ -441,21 +552,24 @@ void destroy_preds(struct ftrace_event_call *call) kfree(filter->preds); kfree(filter->filter_string); kfree(filter); +} + +void destroy_preds(struct ftrace_event_call *call) +{ + __free_preds(call->filter); call->filter = NULL; + call->filter_active = 0; } -static int init_preds(struct ftrace_event_call *call) +static struct event_filter *__alloc_preds(void) { struct event_filter *filter; struct filter_pred *pred; int i; - if (call->filter) - return 0; - - filter = call->filter = kzalloc(sizeof(*filter), GFP_KERNEL); - if (!call->filter) - return -ENOMEM; + filter = kzalloc(sizeof(*filter), GFP_KERNEL); + if (!filter) + return ERR_PTR(-ENOMEM); filter->n_preds = 0; @@ -471,12 +585,24 @@ static int init_preds(struct ftrace_event_call *call) filter->preds[i] = pred; } - return 0; + return filter; oom: - destroy_preds(call); + __free_preds(filter); + return ERR_PTR(-ENOMEM); +} - return -ENOMEM; +static int init_preds(struct ftrace_event_call *call) +{ + if (call->filter) + return 0; + + call->filter_active = 0; + call->filter = __alloc_preds(); + if (IS_ERR(call->filter)) + return PTR_ERR(call->filter); + + return 0; } static int init_subsystem_preds(struct event_subsystem *system) @@ -499,14 +625,7 @@ static int init_subsystem_preds(struct event_subsystem *system) return 0; } -enum { - FILTER_DISABLE_ALL, - FILTER_INIT_NO_RESET, - FILTER_SKIP_NO_RESET, -}; - -static void filter_free_subsystem_preds(struct event_subsystem *system, - int flag) +static void filter_free_subsystem_preds(struct event_subsystem *system) { struct ftrace_event_call *call; @@ -517,14 +636,6 @@ static void filter_free_subsystem_preds(struct event_subsystem *system, if (strcmp(call->system, system->name) != 0) continue; - if (flag == FILTER_INIT_NO_RESET) { - call->filter->no_reset = false; - continue; - } - - if (flag == FILTER_SKIP_NO_RESET && call->filter->no_reset) - continue; - filter_disable_preds(call); remove_filter_string(call->filter); } @@ -532,10 +643,10 @@ static void filter_free_subsystem_preds(struct event_subsystem *system, static int filter_add_pred_fn(struct filter_parse_state *ps, struct ftrace_event_call *call, + struct event_filter *filter, struct filter_pred *pred, filter_pred_fn_t fn) { - struct event_filter *filter = call->filter; int idx, err; if (filter->n_preds == MAX_FILTER_PRED) { @@ -550,7 +661,6 @@ static int filter_add_pred_fn(struct filter_parse_state *ps, return err; filter->n_preds++; - call->filter_active = 1; return 0; } @@ -575,7 +685,10 @@ static bool is_string_field(struct ftrace_event_field *field) static int is_legal_op(struct ftrace_event_field *field, int op) { - if (is_string_field(field) && (op != OP_EQ && op != OP_NE)) + if (is_string_field(field) && + (op != OP_EQ && op != OP_NE && op != OP_GLOB)) + return 0; + if (!is_string_field(field) && op == OP_GLOB) return 0; return 1; @@ -626,6 +739,7 @@ static filter_pred_fn_t select_comparison_fn(int op, int field_size, static int filter_add_pred(struct filter_parse_state *ps, struct ftrace_event_call *call, + struct event_filter *filter, struct filter_pred *pred, bool dry_run) { @@ -660,21 +774,22 @@ static int filter_add_pred(struct filter_parse_state *ps, } if (is_string_field(field)) { - pred->str_len = field->size; + filter_build_regex(pred); - if (field->filter_type == FILTER_STATIC_STRING) + if (field->filter_type == FILTER_STATIC_STRING) { fn = filter_pred_string; - else if (field->filter_type == FILTER_DYN_STRING) + pred->regex.field_len = field->size; + } else if (field->filter_type == FILTER_DYN_STRING) fn = filter_pred_strloc; else { fn = filter_pred_pchar; - pred->str_len = strlen(pred->str_val); + pred->regex.field_len = strlen(pred->regex.pattern); } } else { if (field->is_signed) - ret = strict_strtoll(pred->str_val, 0, &val); + ret = strict_strtoll(pred->regex.pattern, 0, &val); else - ret = strict_strtoull(pred->str_val, 0, &val); + ret = strict_strtoull(pred->regex.pattern, 0, &val); if (ret) { parse_error(ps, FILT_ERR_ILLEGAL_INTVAL, 0); return -EINVAL; @@ -694,45 +809,7 @@ static int filter_add_pred(struct filter_parse_state *ps, add_pred_fn: if (!dry_run) - return filter_add_pred_fn(ps, call, pred, fn); - return 0; -} - -static int filter_add_subsystem_pred(struct filter_parse_state *ps, - struct event_subsystem *system, - struct filter_pred *pred, - char *filter_string, - bool dry_run) -{ - struct ftrace_event_call *call; - int err = 0; - bool fail = true; - - list_for_each_entry(call, &ftrace_events, list) { - - if (!call->define_fields) - continue; - - if (strcmp(call->system, system->name)) - continue; - - if (call->filter->no_reset) - continue; - - err = filter_add_pred(ps, call, pred, dry_run); - if (err) - call->filter->no_reset = true; - else - fail = false; - - if (!dry_run) - replace_filter_string(call->filter, filter_string); - } - - if (fail) { - parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0); - return err; - } + return filter_add_pred_fn(ps, call, filter, pred, fn); return 0; } @@ -1045,8 +1122,8 @@ static struct filter_pred *create_pred(int op, char *operand1, char *operand2) return NULL; } - strcpy(pred->str_val, operand2); - pred->str_len = strlen(operand2); + strcpy(pred->regex.pattern, operand2); + pred->regex.len = strlen(pred->regex.pattern); pred->op = op; @@ -1090,8 +1167,8 @@ static int check_preds(struct filter_parse_state *ps) return 0; } -static int replace_preds(struct event_subsystem *system, - struct ftrace_event_call *call, +static int replace_preds(struct ftrace_event_call *call, + struct event_filter *filter, struct filter_parse_state *ps, char *filter_string, bool dry_run) @@ -1138,11 +1215,7 @@ static int replace_preds(struct event_subsystem *system, add_pred: if (!pred) return -ENOMEM; - if (call) - err = filter_add_pred(ps, call, pred, false); - else - err = filter_add_subsystem_pred(ps, system, pred, - filter_string, dry_run); + err = filter_add_pred(ps, call, filter, pred, dry_run); filter_free_pred(pred); if (err) return err; @@ -1153,10 +1226,50 @@ add_pred: return 0; } -int apply_event_filter(struct ftrace_event_call *call, char *filter_string) +static int replace_system_preds(struct event_subsystem *system, + struct filter_parse_state *ps, + char *filter_string) { + struct ftrace_event_call *call; + bool fail = true; int err; + list_for_each_entry(call, &ftrace_events, list) { + struct event_filter *filter = call->filter; + + if (!call->define_fields) + continue; + + if (strcmp(call->system, system->name) != 0) + continue; + + /* try to see if the filter can be applied */ + err = replace_preds(call, filter, ps, filter_string, true); + if (err) + continue; + + /* really apply the filter */ + filter_disable_preds(call); + err = replace_preds(call, filter, ps, filter_string, false); + if (err) + filter_disable_preds(call); + else { + call->filter_active = 1; + replace_filter_string(filter, filter_string); + } + fail = false; + } + + if (fail) { + parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0); + return -EINVAL; + } + return 0; +} + +int apply_event_filter(struct ftrace_event_call *call, char *filter_string) +{ + int err; struct filter_parse_state *ps; mutex_lock(&event_mutex); @@ -1168,8 +1281,7 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string) if (!strcmp(strstrip(filter_string), "0")) { filter_disable_preds(call); remove_filter_string(call->filter); - mutex_unlock(&event_mutex); - return 0; + goto out_unlock; } err = -ENOMEM; @@ -1187,10 +1299,11 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string) goto out; } - err = replace_preds(NULL, call, ps, filter_string, false); + err = replace_preds(call, call->filter, ps, filter_string, false); if (err) append_filter_err(ps, call->filter); - + else + call->filter_active = 1; out: filter_opstack_clear(ps); postfix_clear(ps); @@ -1205,7 +1318,6 @@ int apply_subsystem_event_filter(struct event_subsystem *system, char *filter_string) { int err; - struct filter_parse_state *ps; mutex_lock(&event_mutex); @@ -1215,10 +1327,9 @@ int apply_subsystem_event_filter(struct event_subsystem *system, goto out_unlock; if (!strcmp(strstrip(filter_string), "0")) { - filter_free_subsystem_preds(system, FILTER_DISABLE_ALL); + filter_free_subsystem_preds(system); remove_filter_string(system->filter); - mutex_unlock(&event_mutex); - return 0; + goto out_unlock; } err = -ENOMEM; @@ -1235,31 +1346,87 @@ int apply_subsystem_event_filter(struct event_subsystem *system, goto out; } - filter_free_subsystem_preds(system, FILTER_INIT_NO_RESET); - - /* try to see the filter can be applied to which events */ - err = replace_preds(system, NULL, ps, filter_string, true); - if (err) { + err = replace_system_preds(system, ps, filter_string); + if (err) append_filter_err(ps, system->filter); - goto out; + +out: + filter_opstack_clear(ps); + postfix_clear(ps); + kfree(ps); +out_unlock: + mutex_unlock(&event_mutex); + + return err; +} + +#ifdef CONFIG_EVENT_PROFILE + +void ftrace_profile_free_filter(struct perf_event *event) +{ + struct event_filter *filter = event->filter; + + event->filter = NULL; + __free_preds(filter); +} + +int ftrace_profile_set_filter(struct perf_event *event, int event_id, + char *filter_str) +{ + int err; + struct event_filter *filter; + struct filter_parse_state *ps; + struct ftrace_event_call *call = NULL; + + mutex_lock(&event_mutex); + + list_for_each_entry(call, &ftrace_events, list) { + if (call->id == event_id) + break; } - filter_free_subsystem_preds(system, FILTER_SKIP_NO_RESET); + err = -EINVAL; + if (!call) + goto out_unlock; - /* really apply the filter to the events */ - err = replace_preds(system, NULL, ps, filter_string, false); - if (err) { - append_filter_err(ps, system->filter); - filter_free_subsystem_preds(system, 2); + err = -EEXIST; + if (event->filter) + goto out_unlock; + + filter = __alloc_preds(); + if (IS_ERR(filter)) { + err = PTR_ERR(filter); + goto out_unlock; } -out: + err = -ENOMEM; + ps = kzalloc(sizeof(*ps), GFP_KERNEL); + if (!ps) + goto free_preds; + + parse_init(ps, filter_ops, filter_str); + err = filter_parse(ps); + if (err) + goto free_ps; + + err = replace_preds(call, filter, ps, filter_str, false); + if (!err) + event->filter = filter; + +free_ps: filter_opstack_clear(ps); postfix_clear(ps); kfree(ps); + +free_preds: + if (err) + __free_preds(filter); + out_unlock: mutex_unlock(&event_mutex); return err; } +#endif /* CONFIG_EVENT_PROFILE */ + diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index 9753fcc61bc5..dff8c84ddf17 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -48,11 +48,11 @@ struct ____ftrace_##name { \ tstruct \ }; \ -static void __used ____ftrace_check_##name(void) \ +static void __always_unused ____ftrace_check_##name(void) \ { \ struct ____ftrace_##name *__entry = NULL; \ \ - /* force cmpile-time check on F_printk() */ \ + /* force compile-time check on F_printk() */ \ printk(print); \ } @@ -66,44 +66,47 @@ static void __used ____ftrace_check_##name(void) \ #undef __field #define __field(type, item) \ ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t" \ - "offset:%zu;\tsize:%zu;\n", \ + "offset:%zu;\tsize:%zu;\tsigned:%u;\n", \ offsetof(typeof(field), item), \ - sizeof(field.item)); \ + sizeof(field.item), is_signed_type(type)); \ if (!ret) \ return 0; #undef __field_desc #define __field_desc(type, container, item) \ ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t" \ - "offset:%zu;\tsize:%zu;\n", \ + "offset:%zu;\tsize:%zu;\tsigned:%u;\n", \ offsetof(typeof(field), container.item), \ - sizeof(field.container.item)); \ + sizeof(field.container.item), \ + is_signed_type(type)); \ if (!ret) \ return 0; #undef __array #define __array(type, item, len) \ ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t" \ - "offset:%zu;\tsize:%zu;\n", \ - offsetof(typeof(field), item), \ - sizeof(field.item)); \ + "offset:%zu;\tsize:%zu;\tsigned:%u;\n", \ + offsetof(typeof(field), item), \ + sizeof(field.item), is_signed_type(type)); \ if (!ret) \ return 0; #undef __array_desc #define __array_desc(type, container, item, len) \ ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t" \ - "offset:%zu;\tsize:%zu;\n", \ + "offset:%zu;\tsize:%zu;\tsigned:%u;\n", \ offsetof(typeof(field), container.item), \ - sizeof(field.container.item)); \ + sizeof(field.container.item), \ + is_signed_type(type)); \ if (!ret) \ return 0; #undef __dynamic_array #define __dynamic_array(type, item) \ ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t" \ - "offset:%zu;\tsize:0;\n", \ - offsetof(typeof(field), item)); \ + "offset:%zu;\tsize:0;\tsigned:%u;\n", \ + offsetof(typeof(field), item), \ + is_signed_type(type)); \ if (!ret) \ return 0; @@ -131,7 +134,6 @@ ftrace_format_##name(struct ftrace_event_call *unused, \ #include "trace_entries.h" - #undef __field #define __field(type, item) \ ret = trace_define_field(event_call, #type, #item, \ @@ -193,6 +195,11 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call) \ #include "trace_entries.h" +static int ftrace_raw_init_event(struct ftrace_event_call *call) +{ + INIT_LIST_HEAD(&call->fields); + return 0; +} #undef __field #define __field(type, item) @@ -211,7 +218,6 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call) \ #undef FTRACE_ENTRY #define FTRACE_ENTRY(call, struct_name, type, tstruct, print) \ -static int ftrace_raw_init_event_##call(void); \ \ struct ftrace_event_call __used \ __attribute__((__aligned__(4))) \ @@ -219,14 +225,9 @@ __attribute__((section("_ftrace_events"))) event_##call = { \ .name = #call, \ .id = type, \ .system = __stringify(TRACE_SYSTEM), \ - .raw_init = ftrace_raw_init_event_##call, \ + .raw_init = ftrace_raw_init_event, \ .show_format = ftrace_format_##call, \ .define_fields = ftrace_define_fields_##call, \ }; \ -static int ftrace_raw_init_event_##call(void) \ -{ \ - INIT_LIST_HEAD(&event_##call.fields); \ - return 0; \ -} \ #include "trace_entries.h" diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c new file mode 100644 index 000000000000..aff5f80b59b8 --- /dev/null +++ b/kernel/trace/trace_kprobe.c @@ -0,0 +1,1523 @@ +/* + * Kprobes-based tracing events + * + * Created by Masami Hiramatsu <mhiramat@redhat.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include <linux/module.h> +#include <linux/uaccess.h> +#include <linux/kprobes.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/smp.h> +#include <linux/debugfs.h> +#include <linux/types.h> +#include <linux/string.h> +#include <linux/ctype.h> +#include <linux/ptrace.h> +#include <linux/perf_event.h> + +#include "trace.h" +#include "trace_output.h" + +#define MAX_TRACE_ARGS 128 +#define MAX_ARGSTR_LEN 63 +#define MAX_EVENT_NAME_LEN 64 +#define KPROBE_EVENT_SYSTEM "kprobes" + +/* Reserved field names */ +#define FIELD_STRING_IP "__probe_ip" +#define FIELD_STRING_NARGS "__probe_nargs" +#define FIELD_STRING_RETIP "__probe_ret_ip" +#define FIELD_STRING_FUNC "__probe_func" + +const char *reserved_field_names[] = { + "common_type", + "common_flags", + "common_preempt_count", + "common_pid", + "common_tgid", + "common_lock_depth", + FIELD_STRING_IP, + FIELD_STRING_NARGS, + FIELD_STRING_RETIP, + FIELD_STRING_FUNC, +}; + +struct fetch_func { + unsigned long (*func)(struct pt_regs *, void *); + void *data; +}; + +static __kprobes unsigned long call_fetch(struct fetch_func *f, + struct pt_regs *regs) +{ + return f->func(regs, f->data); +} + +/* fetch handlers */ +static __kprobes unsigned long fetch_register(struct pt_regs *regs, + void *offset) +{ + return regs_get_register(regs, (unsigned int)((unsigned long)offset)); +} + +static __kprobes unsigned long fetch_stack(struct pt_regs *regs, + void *num) +{ + return regs_get_kernel_stack_nth(regs, + (unsigned int)((unsigned long)num)); +} + +static __kprobes unsigned long fetch_memory(struct pt_regs *regs, void *addr) +{ + unsigned long retval; + + if (probe_kernel_address(addr, retval)) + return 0; + return retval; +} + +static __kprobes unsigned long fetch_argument(struct pt_regs *regs, void *num) +{ + return regs_get_argument_nth(regs, (unsigned int)((unsigned long)num)); +} + +static __kprobes unsigned long fetch_retvalue(struct pt_regs *regs, + void *dummy) +{ + return regs_return_value(regs); +} + +static __kprobes unsigned long fetch_stack_address(struct pt_regs *regs, + void *dummy) +{ + return kernel_stack_pointer(regs); +} + +/* Memory fetching by symbol */ +struct symbol_cache { + char *symbol; + long offset; + unsigned long addr; +}; + +static unsigned long update_symbol_cache(struct symbol_cache *sc) +{ + sc->addr = (unsigned long)kallsyms_lookup_name(sc->symbol); + if (sc->addr) + sc->addr += sc->offset; + return sc->addr; +} + +static void free_symbol_cache(struct symbol_cache *sc) +{ + kfree(sc->symbol); + kfree(sc); +} + +static struct symbol_cache *alloc_symbol_cache(const char *sym, long offset) +{ + struct symbol_cache *sc; + + if (!sym || strlen(sym) == 0) + return NULL; + sc = kzalloc(sizeof(struct symbol_cache), GFP_KERNEL); + if (!sc) + return NULL; + + sc->symbol = kstrdup(sym, GFP_KERNEL); + if (!sc->symbol) { + kfree(sc); + return NULL; + } + sc->offset = offset; + + update_symbol_cache(sc); + return sc; +} + +static __kprobes unsigned long fetch_symbol(struct pt_regs *regs, void *data) +{ + struct symbol_cache *sc = data; + + if (sc->addr) + return fetch_memory(regs, (void *)sc->addr); + else + return 0; +} + +/* Special indirect memory access interface */ +struct indirect_fetch_data { + struct fetch_func orig; + long offset; +}; + +static __kprobes unsigned long fetch_indirect(struct pt_regs *regs, void *data) +{ + struct indirect_fetch_data *ind = data; + unsigned long addr; + + addr = call_fetch(&ind->orig, regs); + if (addr) { + addr += ind->offset; + return fetch_memory(regs, (void *)addr); + } else + return 0; +} + +static __kprobes void free_indirect_fetch_data(struct indirect_fetch_data *data) +{ + if (data->orig.func == fetch_indirect) + free_indirect_fetch_data(data->orig.data); + else if (data->orig.func == fetch_symbol) + free_symbol_cache(data->orig.data); + kfree(data); +} + +/** + * Kprobe event core functions + */ + +struct probe_arg { + struct fetch_func fetch; + const char *name; +}; + +/* Flags for trace_probe */ +#define TP_FLAG_TRACE 1 +#define TP_FLAG_PROFILE 2 + +struct trace_probe { + struct list_head list; + struct kretprobe rp; /* Use rp.kp for kprobe use */ + unsigned long nhit; + unsigned int flags; /* For TP_FLAG_* */ + const char *symbol; /* symbol name */ + struct ftrace_event_call call; + struct trace_event event; + unsigned int nr_args; + struct probe_arg args[]; +}; + +#define SIZEOF_TRACE_PROBE(n) \ + (offsetof(struct trace_probe, args) + \ + (sizeof(struct probe_arg) * (n))) + +static __kprobes int probe_is_return(struct trace_probe *tp) +{ + return tp->rp.handler != NULL; +} + +static __kprobes const char *probe_symbol(struct trace_probe *tp) +{ + return tp->symbol ? tp->symbol : "unknown"; +} + +static int probe_arg_string(char *buf, size_t n, struct fetch_func *ff) +{ + int ret = -EINVAL; + + if (ff->func == fetch_argument) + ret = snprintf(buf, n, "$arg%lu", (unsigned long)ff->data); + else if (ff->func == fetch_register) { + const char *name; + name = regs_query_register_name((unsigned int)((long)ff->data)); + ret = snprintf(buf, n, "%%%s", name); + } else if (ff->func == fetch_stack) + ret = snprintf(buf, n, "$stack%lu", (unsigned long)ff->data); + else if (ff->func == fetch_memory) + ret = snprintf(buf, n, "@0x%p", ff->data); + else if (ff->func == fetch_symbol) { + struct symbol_cache *sc = ff->data; + if (sc->offset) + ret = snprintf(buf, n, "@%s%+ld", sc->symbol, + sc->offset); + else + ret = snprintf(buf, n, "@%s", sc->symbol); + } else if (ff->func == fetch_retvalue) + ret = snprintf(buf, n, "$retval"); + else if (ff->func == fetch_stack_address) + ret = snprintf(buf, n, "$stack"); + else if (ff->func == fetch_indirect) { + struct indirect_fetch_data *id = ff->data; + size_t l = 0; + ret = snprintf(buf, n, "%+ld(", id->offset); + if (ret >= n) + goto end; + l += ret; + ret = probe_arg_string(buf + l, n - l, &id->orig); + if (ret < 0) + goto end; + l += ret; + ret = snprintf(buf + l, n - l, ")"); + ret += l; + } +end: + if (ret >= n) + return -ENOSPC; + return ret; +} + +static int register_probe_event(struct trace_probe *tp); +static void unregister_probe_event(struct trace_probe *tp); + +static DEFINE_MUTEX(probe_lock); +static LIST_HEAD(probe_list); + +static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs); +static int kretprobe_dispatcher(struct kretprobe_instance *ri, + struct pt_regs *regs); + +/* + * Allocate new trace_probe and initialize it (including kprobes). + */ +static struct trace_probe *alloc_trace_probe(const char *group, + const char *event, + void *addr, + const char *symbol, + unsigned long offs, + int nargs, int is_return) +{ + struct trace_probe *tp; + + tp = kzalloc(SIZEOF_TRACE_PROBE(nargs), GFP_KERNEL); + if (!tp) + return ERR_PTR(-ENOMEM); + + if (symbol) { + tp->symbol = kstrdup(symbol, GFP_KERNEL); + if (!tp->symbol) + goto error; + tp->rp.kp.symbol_name = tp->symbol; + tp->rp.kp.offset = offs; + } else + tp->rp.kp.addr = addr; + + if (is_return) + tp->rp.handler = kretprobe_dispatcher; + else + tp->rp.kp.pre_handler = kprobe_dispatcher; + + if (!event) + goto error; + tp->call.name = kstrdup(event, GFP_KERNEL); + if (!tp->call.name) + goto error; + + if (!group) + goto error; + tp->call.system = kstrdup(group, GFP_KERNEL); + if (!tp->call.system) + goto error; + + INIT_LIST_HEAD(&tp->list); + return tp; +error: + kfree(tp->call.name); + kfree(tp->symbol); + kfree(tp); + return ERR_PTR(-ENOMEM); +} + +static void free_probe_arg(struct probe_arg *arg) +{ + if (arg->fetch.func == fetch_symbol) + free_symbol_cache(arg->fetch.data); + else if (arg->fetch.func == fetch_indirect) + free_indirect_fetch_data(arg->fetch.data); + kfree(arg->name); +} + +static void free_trace_probe(struct trace_probe *tp) +{ + int i; + + for (i = 0; i < tp->nr_args; i++) + free_probe_arg(&tp->args[i]); + + kfree(tp->call.system); + kfree(tp->call.name); + kfree(tp->symbol); + kfree(tp); +} + +static struct trace_probe *find_probe_event(const char *event, + const char *group) +{ + struct trace_probe *tp; + + list_for_each_entry(tp, &probe_list, list) + if (strcmp(tp->call.name, event) == 0 && + strcmp(tp->call.system, group) == 0) + return tp; + return NULL; +} + +/* Unregister a trace_probe and probe_event: call with locking probe_lock */ +static void unregister_trace_probe(struct trace_probe *tp) +{ + if (probe_is_return(tp)) + unregister_kretprobe(&tp->rp); + else + unregister_kprobe(&tp->rp.kp); + list_del(&tp->list); + unregister_probe_event(tp); +} + +/* Register a trace_probe and probe_event */ +static int register_trace_probe(struct trace_probe *tp) +{ + struct trace_probe *old_tp; + int ret; + + mutex_lock(&probe_lock); + + /* register as an event */ + old_tp = find_probe_event(tp->call.name, tp->call.system); + if (old_tp) { + /* delete old event */ + unregister_trace_probe(old_tp); + free_trace_probe(old_tp); + } + ret = register_probe_event(tp); + if (ret) { + pr_warning("Faild to register probe event(%d)\n", ret); + goto end; + } + + tp->rp.kp.flags |= KPROBE_FLAG_DISABLED; + if (probe_is_return(tp)) + ret = register_kretprobe(&tp->rp); + else + ret = register_kprobe(&tp->rp.kp); + + if (ret) { + pr_warning("Could not insert probe(%d)\n", ret); + if (ret == -EILSEQ) { + pr_warning("Probing address(0x%p) is not an " + "instruction boundary.\n", + tp->rp.kp.addr); + ret = -EINVAL; + } + unregister_probe_event(tp); + } else + list_add_tail(&tp->list, &probe_list); +end: + mutex_unlock(&probe_lock); + return ret; +} + +/* Split symbol and offset. */ +static int split_symbol_offset(char *symbol, unsigned long *offset) +{ + char *tmp; + int ret; + + if (!offset) + return -EINVAL; + + tmp = strchr(symbol, '+'); + if (tmp) { + /* skip sign because strict_strtol doesn't accept '+' */ + ret = strict_strtoul(tmp + 1, 0, offset); + if (ret) + return ret; + *tmp = '\0'; + } else + *offset = 0; + return 0; +} + +#define PARAM_MAX_ARGS 16 +#define PARAM_MAX_STACK (THREAD_SIZE / sizeof(unsigned long)) + +static int parse_probe_vars(char *arg, struct fetch_func *ff, int is_return) +{ + int ret = 0; + unsigned long param; + + if (strcmp(arg, "retval") == 0) { + if (is_return) { + ff->func = fetch_retvalue; + ff->data = NULL; + } else + ret = -EINVAL; + } else if (strncmp(arg, "stack", 5) == 0) { + if (arg[5] == '\0') { + ff->func = fetch_stack_address; + ff->data = NULL; + } else if (isdigit(arg[5])) { + ret = strict_strtoul(arg + 5, 10, ¶m); + if (ret || param > PARAM_MAX_STACK) + ret = -EINVAL; + else { + ff->func = fetch_stack; + ff->data = (void *)param; + } + } else + ret = -EINVAL; + } else if (strncmp(arg, "arg", 3) == 0 && isdigit(arg[3])) { + ret = strict_strtoul(arg + 3, 10, ¶m); + if (ret || param > PARAM_MAX_ARGS) + ret = -EINVAL; + else { + ff->func = fetch_argument; + ff->data = (void *)param; + } + } else + ret = -EINVAL; + return ret; +} + +/* Recursive argument parser */ +static int __parse_probe_arg(char *arg, struct fetch_func *ff, int is_return) +{ + int ret = 0; + unsigned long param; + long offset; + char *tmp; + + switch (arg[0]) { + case '$': + ret = parse_probe_vars(arg + 1, ff, is_return); + break; + case '%': /* named register */ + ret = regs_query_register_offset(arg + 1); + if (ret >= 0) { + ff->func = fetch_register; + ff->data = (void *)(unsigned long)ret; + ret = 0; + } + break; + case '@': /* memory or symbol */ + if (isdigit(arg[1])) { + ret = strict_strtoul(arg + 1, 0, ¶m); + if (ret) + break; + ff->func = fetch_memory; + ff->data = (void *)param; + } else { + ret = split_symbol_offset(arg + 1, &offset); + if (ret) + break; + ff->data = alloc_symbol_cache(arg + 1, offset); + if (ff->data) + ff->func = fetch_symbol; + else + ret = -EINVAL; + } + break; + case '+': /* indirect memory */ + case '-': + tmp = strchr(arg, '('); + if (!tmp) { + ret = -EINVAL; + break; + } + *tmp = '\0'; + ret = strict_strtol(arg + 1, 0, &offset); + if (ret) + break; + if (arg[0] == '-') + offset = -offset; + arg = tmp + 1; + tmp = strrchr(arg, ')'); + if (tmp) { + struct indirect_fetch_data *id; + *tmp = '\0'; + id = kzalloc(sizeof(struct indirect_fetch_data), + GFP_KERNEL); + if (!id) + return -ENOMEM; + id->offset = offset; + ret = __parse_probe_arg(arg, &id->orig, is_return); + if (ret) + kfree(id); + else { + ff->func = fetch_indirect; + ff->data = (void *)id; + } + } else + ret = -EINVAL; + break; + default: + /* TODO: support custom handler */ + ret = -EINVAL; + } + return ret; +} + +/* String length checking wrapper */ +static int parse_probe_arg(char *arg, struct fetch_func *ff, int is_return) +{ + if (strlen(arg) > MAX_ARGSTR_LEN) { + pr_info("Argument is too long.: %s\n", arg); + return -ENOSPC; + } + return __parse_probe_arg(arg, ff, is_return); +} + +/* Return 1 if name is reserved or already used by another argument */ +static int conflict_field_name(const char *name, + struct probe_arg *args, int narg) +{ + int i; + for (i = 0; i < ARRAY_SIZE(reserved_field_names); i++) + if (strcmp(reserved_field_names[i], name) == 0) + return 1; + for (i = 0; i < narg; i++) + if (strcmp(args[i].name, name) == 0) + return 1; + return 0; +} + +static int create_trace_probe(int argc, char **argv) +{ + /* + * Argument syntax: + * - Add kprobe: p[:[GRP/]EVENT] KSYM[+OFFS]|KADDR [FETCHARGS] + * - Add kretprobe: r[:[GRP/]EVENT] KSYM[+0] [FETCHARGS] + * Fetch args: + * $argN : fetch Nth of function argument. (N:0-) + * $retval : fetch return value + * $stack : fetch stack address + * $stackN : fetch Nth of stack (N:0-) + * @ADDR : fetch memory at ADDR (ADDR should be in kernel) + * @SYM[+|-offs] : fetch memory at SYM +|- offs (SYM is a data symbol) + * %REG : fetch register REG + * Indirect memory fetch: + * +|-offs(ARG) : fetch memory at ARG +|- offs address. + * Alias name of args: + * NAME=FETCHARG : set NAME as alias of FETCHARG. + */ + struct trace_probe *tp; + int i, ret = 0; + int is_return = 0; + char *symbol = NULL, *event = NULL, *arg = NULL, *group = NULL; + unsigned long offset = 0; + void *addr = NULL; + char buf[MAX_EVENT_NAME_LEN]; + + if (argc < 2) { + pr_info("Probe point is not specified.\n"); + return -EINVAL; + } + + if (argv[0][0] == 'p') + is_return = 0; + else if (argv[0][0] == 'r') + is_return = 1; + else { + pr_info("Probe definition must be started with 'p' or 'r'.\n"); + return -EINVAL; + } + + if (argv[0][1] == ':') { + event = &argv[0][2]; + if (strchr(event, '/')) { + group = event; + event = strchr(group, '/') + 1; + event[-1] = '\0'; + if (strlen(group) == 0) { + pr_info("Group name is not specifiled\n"); + return -EINVAL; + } + } + if (strlen(event) == 0) { + pr_info("Event name is not specifiled\n"); + return -EINVAL; + } + } + + if (isdigit(argv[1][0])) { + if (is_return) { + pr_info("Return probe point must be a symbol.\n"); + return -EINVAL; + } + /* an address specified */ + ret = strict_strtoul(&argv[0][2], 0, (unsigned long *)&addr); + if (ret) { + pr_info("Failed to parse address.\n"); + return ret; + } + } else { + /* a symbol specified */ + symbol = argv[1]; + /* TODO: support .init module functions */ + ret = split_symbol_offset(symbol, &offset); + if (ret) { + pr_info("Failed to parse symbol.\n"); + return ret; + } + if (offset && is_return) { + pr_info("Return probe must be used without offset.\n"); + return -EINVAL; + } + } + argc -= 2; argv += 2; + + /* setup a probe */ + if (!group) + group = KPROBE_EVENT_SYSTEM; + if (!event) { + /* Make a new event name */ + if (symbol) + snprintf(buf, MAX_EVENT_NAME_LEN, "%c@%s%+ld", + is_return ? 'r' : 'p', symbol, offset); + else + snprintf(buf, MAX_EVENT_NAME_LEN, "%c@0x%p", + is_return ? 'r' : 'p', addr); + event = buf; + } + tp = alloc_trace_probe(group, event, addr, symbol, offset, argc, + is_return); + if (IS_ERR(tp)) { + pr_info("Failed to allocate trace_probe.(%d)\n", + (int)PTR_ERR(tp)); + return PTR_ERR(tp); + } + + /* parse arguments */ + ret = 0; + for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) { + /* Parse argument name */ + arg = strchr(argv[i], '='); + if (arg) + *arg++ = '\0'; + else + arg = argv[i]; + + if (conflict_field_name(argv[i], tp->args, i)) { + pr_info("Argument%d name '%s' conflicts with " + "another field.\n", i, argv[i]); + ret = -EINVAL; + goto error; + } + + tp->args[i].name = kstrdup(argv[i], GFP_KERNEL); + if (!tp->args[i].name) { + pr_info("Failed to allocate argument%d name '%s'.\n", + i, argv[i]); + ret = -ENOMEM; + goto error; + } + + /* Parse fetch argument */ + ret = parse_probe_arg(arg, &tp->args[i].fetch, is_return); + if (ret) { + pr_info("Parse error at argument%d. (%d)\n", i, ret); + kfree(tp->args[i].name); + goto error; + } + + tp->nr_args++; + } + + ret = register_trace_probe(tp); + if (ret) + goto error; + return 0; + +error: + free_trace_probe(tp); + return ret; +} + +static void cleanup_all_probes(void) +{ + struct trace_probe *tp; + + mutex_lock(&probe_lock); + /* TODO: Use batch unregistration */ + while (!list_empty(&probe_list)) { + tp = list_entry(probe_list.next, struct trace_probe, list); + unregister_trace_probe(tp); + free_trace_probe(tp); + } + mutex_unlock(&probe_lock); +} + + +/* Probes listing interfaces */ +static void *probes_seq_start(struct seq_file *m, loff_t *pos) +{ + mutex_lock(&probe_lock); + return seq_list_start(&probe_list, *pos); +} + +static void *probes_seq_next(struct seq_file *m, void *v, loff_t *pos) +{ + return seq_list_next(v, &probe_list, pos); +} + +static void probes_seq_stop(struct seq_file *m, void *v) +{ + mutex_unlock(&probe_lock); +} + +static int probes_seq_show(struct seq_file *m, void *v) +{ + struct trace_probe *tp = v; + int i, ret; + char buf[MAX_ARGSTR_LEN + 1]; + + seq_printf(m, "%c", probe_is_return(tp) ? 'r' : 'p'); + seq_printf(m, ":%s/%s", tp->call.system, tp->call.name); + + if (!tp->symbol) + seq_printf(m, " 0x%p", tp->rp.kp.addr); + else if (tp->rp.kp.offset) + seq_printf(m, " %s+%u", probe_symbol(tp), tp->rp.kp.offset); + else + seq_printf(m, " %s", probe_symbol(tp)); + + for (i = 0; i < tp->nr_args; i++) { + ret = probe_arg_string(buf, MAX_ARGSTR_LEN, &tp->args[i].fetch); + if (ret < 0) { + pr_warning("Argument%d decoding error(%d).\n", i, ret); + return ret; + } + seq_printf(m, " %s=%s", tp->args[i].name, buf); + } + seq_printf(m, "\n"); + return 0; +} + +static const struct seq_operations probes_seq_op = { + .start = probes_seq_start, + .next = probes_seq_next, + .stop = probes_seq_stop, + .show = probes_seq_show +}; + +static int probes_open(struct inode *inode, struct file *file) +{ + if ((file->f_mode & FMODE_WRITE) && + (file->f_flags & O_TRUNC)) + cleanup_all_probes(); + + return seq_open(file, &probes_seq_op); +} + +static int command_trace_probe(const char *buf) +{ + char **argv; + int argc = 0, ret = 0; + + argv = argv_split(GFP_KERNEL, buf, &argc); + if (!argv) + return -ENOMEM; + + if (argc) + ret = create_trace_probe(argc, argv); + + argv_free(argv); + return ret; +} + +#define WRITE_BUFSIZE 128 + +static ssize_t probes_write(struct file *file, const char __user *buffer, + size_t count, loff_t *ppos) +{ + char *kbuf, *tmp; + int ret; + size_t done; + size_t size; + + kbuf = kmalloc(WRITE_BUFSIZE, GFP_KERNEL); + if (!kbuf) + return -ENOMEM; + + ret = done = 0; + while (done < count) { + size = count - done; + if (size >= WRITE_BUFSIZE) + size = WRITE_BUFSIZE - 1; + if (copy_from_user(kbuf, buffer + done, size)) { + ret = -EFAULT; + goto out; + } + kbuf[size] = '\0'; + tmp = strchr(kbuf, '\n'); + if (tmp) { + *tmp = '\0'; + size = tmp - kbuf + 1; + } else if (done + size < count) { + pr_warning("Line length is too long: " + "Should be less than %d.", WRITE_BUFSIZE); + ret = -EINVAL; + goto out; + } + done += size; + /* Remove comments */ + tmp = strchr(kbuf, '#'); + if (tmp) + *tmp = '\0'; + + ret = command_trace_probe(kbuf); + if (ret) + goto out; + } + ret = done; +out: + kfree(kbuf); + return ret; +} + +static const struct file_operations kprobe_events_ops = { + .owner = THIS_MODULE, + .open = probes_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, + .write = probes_write, +}; + +/* Probes profiling interfaces */ +static int probes_profile_seq_show(struct seq_file *m, void *v) +{ + struct trace_probe *tp = v; + + seq_printf(m, " %-44s %15lu %15lu\n", tp->call.name, tp->nhit, + tp->rp.kp.nmissed); + + return 0; +} + +static const struct seq_operations profile_seq_op = { + .start = probes_seq_start, + .next = probes_seq_next, + .stop = probes_seq_stop, + .show = probes_profile_seq_show +}; + +static int profile_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &profile_seq_op); +} + +static const struct file_operations kprobe_profile_ops = { + .owner = THIS_MODULE, + .open = profile_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +/* Kprobe handler */ +static __kprobes int kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs) +{ + struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp); + struct kprobe_trace_entry *entry; + struct ring_buffer_event *event; + struct ring_buffer *buffer; + int size, i, pc; + unsigned long irq_flags; + struct ftrace_event_call *call = &tp->call; + + tp->nhit++; + + local_save_flags(irq_flags); + pc = preempt_count(); + + size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args); + + event = trace_current_buffer_lock_reserve(&buffer, call->id, size, + irq_flags, pc); + if (!event) + return 0; + + entry = ring_buffer_event_data(event); + entry->nargs = tp->nr_args; + entry->ip = (unsigned long)kp->addr; + for (i = 0; i < tp->nr_args; i++) + entry->args[i] = call_fetch(&tp->args[i].fetch, regs); + + if (!filter_current_check_discard(buffer, call, entry, event)) + trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc); + return 0; +} + +/* Kretprobe handler */ +static __kprobes int kretprobe_trace_func(struct kretprobe_instance *ri, + struct pt_regs *regs) +{ + struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp); + struct kretprobe_trace_entry *entry; + struct ring_buffer_event *event; + struct ring_buffer *buffer; + int size, i, pc; + unsigned long irq_flags; + struct ftrace_event_call *call = &tp->call; + + local_save_flags(irq_flags); + pc = preempt_count(); + + size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args); + + event = trace_current_buffer_lock_reserve(&buffer, call->id, size, + irq_flags, pc); + if (!event) + return 0; + + entry = ring_buffer_event_data(event); + entry->nargs = tp->nr_args; + entry->func = (unsigned long)tp->rp.kp.addr; + entry->ret_ip = (unsigned long)ri->ret_addr; + for (i = 0; i < tp->nr_args; i++) + entry->args[i] = call_fetch(&tp->args[i].fetch, regs); + + if (!filter_current_check_discard(buffer, call, entry, event)) + trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc); + + return 0; +} + +/* Event entry printers */ +enum print_line_t +print_kprobe_event(struct trace_iterator *iter, int flags) +{ + struct kprobe_trace_entry *field; + struct trace_seq *s = &iter->seq; + struct trace_event *event; + struct trace_probe *tp; + int i; + + field = (struct kprobe_trace_entry *)iter->ent; + event = ftrace_find_event(field->ent.type); + tp = container_of(event, struct trace_probe, event); + + if (!trace_seq_printf(s, "%s: (", tp->call.name)) + goto partial; + + if (!seq_print_ip_sym(s, field->ip, flags | TRACE_ITER_SYM_OFFSET)) + goto partial; + + if (!trace_seq_puts(s, ")")) + goto partial; + + for (i = 0; i < field->nargs; i++) + if (!trace_seq_printf(s, " %s=%lx", + tp->args[i].name, field->args[i])) + goto partial; + + if (!trace_seq_puts(s, "\n")) + goto partial; + + return TRACE_TYPE_HANDLED; +partial: + return TRACE_TYPE_PARTIAL_LINE; +} + +enum print_line_t +print_kretprobe_event(struct trace_iterator *iter, int flags) +{ + struct kretprobe_trace_entry *field; + struct trace_seq *s = &iter->seq; + struct trace_event *event; + struct trace_probe *tp; + int i; + + field = (struct kretprobe_trace_entry *)iter->ent; + event = ftrace_find_event(field->ent.type); + tp = container_of(event, struct trace_probe, event); + + if (!trace_seq_printf(s, "%s: (", tp->call.name)) + goto partial; + + if (!seq_print_ip_sym(s, field->ret_ip, flags | TRACE_ITER_SYM_OFFSET)) + goto partial; + + if (!trace_seq_puts(s, " <- ")) + goto partial; + + if (!seq_print_ip_sym(s, field->func, flags & ~TRACE_ITER_SYM_OFFSET)) + goto partial; + + if (!trace_seq_puts(s, ")")) + goto partial; + + for (i = 0; i < field->nargs; i++) + if (!trace_seq_printf(s, " %s=%lx", + tp->args[i].name, field->args[i])) + goto partial; + + if (!trace_seq_puts(s, "\n")) + goto partial; + + return TRACE_TYPE_HANDLED; +partial: + return TRACE_TYPE_PARTIAL_LINE; +} + +static int probe_event_enable(struct ftrace_event_call *call) +{ + struct trace_probe *tp = (struct trace_probe *)call->data; + + tp->flags |= TP_FLAG_TRACE; + if (probe_is_return(tp)) + return enable_kretprobe(&tp->rp); + else + return enable_kprobe(&tp->rp.kp); +} + +static void probe_event_disable(struct ftrace_event_call *call) +{ + struct trace_probe *tp = (struct trace_probe *)call->data; + + tp->flags &= ~TP_FLAG_TRACE; + if (!(tp->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE))) { + if (probe_is_return(tp)) + disable_kretprobe(&tp->rp); + else + disable_kprobe(&tp->rp.kp); + } +} + +static int probe_event_raw_init(struct ftrace_event_call *event_call) +{ + INIT_LIST_HEAD(&event_call->fields); + + return 0; +} + +#undef DEFINE_FIELD +#define DEFINE_FIELD(type, item, name, is_signed) \ + do { \ + ret = trace_define_field(event_call, #type, name, \ + offsetof(typeof(field), item), \ + sizeof(field.item), is_signed, \ + FILTER_OTHER); \ + if (ret) \ + return ret; \ + } while (0) + +static int kprobe_event_define_fields(struct ftrace_event_call *event_call) +{ + int ret, i; + struct kprobe_trace_entry field; + struct trace_probe *tp = (struct trace_probe *)event_call->data; + + ret = trace_define_common_fields(event_call); + if (!ret) + return ret; + + DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0); + DEFINE_FIELD(int, nargs, FIELD_STRING_NARGS, 1); + /* Set argument names as fields */ + for (i = 0; i < tp->nr_args; i++) + DEFINE_FIELD(unsigned long, args[i], tp->args[i].name, 0); + return 0; +} + +static int kretprobe_event_define_fields(struct ftrace_event_call *event_call) +{ + int ret, i; + struct kretprobe_trace_entry field; + struct trace_probe *tp = (struct trace_probe *)event_call->data; + + ret = trace_define_common_fields(event_call); + if (!ret) + return ret; + + DEFINE_FIELD(unsigned long, func, FIELD_STRING_FUNC, 0); + DEFINE_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP, 0); + DEFINE_FIELD(int, nargs, FIELD_STRING_NARGS, 1); + /* Set argument names as fields */ + for (i = 0; i < tp->nr_args; i++) + DEFINE_FIELD(unsigned long, args[i], tp->args[i].name, 0); + return 0; +} + +static int __probe_event_show_format(struct trace_seq *s, + struct trace_probe *tp, const char *fmt, + const char *arg) +{ + int i; + + /* Show format */ + if (!trace_seq_printf(s, "\nprint fmt: \"%s", fmt)) + return 0; + + for (i = 0; i < tp->nr_args; i++) + if (!trace_seq_printf(s, " %s=%%lx", tp->args[i].name)) + return 0; + + if (!trace_seq_printf(s, "\", %s", arg)) + return 0; + + for (i = 0; i < tp->nr_args; i++) + if (!trace_seq_printf(s, ", REC->%s", tp->args[i].name)) + return 0; + + return trace_seq_puts(s, "\n"); +} + +#undef SHOW_FIELD +#define SHOW_FIELD(type, item, name) \ + do { \ + ret = trace_seq_printf(s, "\tfield: " #type " %s;\t" \ + "offset:%u;\tsize:%u;\n", name, \ + (unsigned int)offsetof(typeof(field), item),\ + (unsigned int)sizeof(type)); \ + if (!ret) \ + return 0; \ + } while (0) + +static int kprobe_event_show_format(struct ftrace_event_call *call, + struct trace_seq *s) +{ + struct kprobe_trace_entry field __attribute__((unused)); + int ret, i; + struct trace_probe *tp = (struct trace_probe *)call->data; + + SHOW_FIELD(unsigned long, ip, FIELD_STRING_IP); + SHOW_FIELD(int, nargs, FIELD_STRING_NARGS); + + /* Show fields */ + for (i = 0; i < tp->nr_args; i++) + SHOW_FIELD(unsigned long, args[i], tp->args[i].name); + trace_seq_puts(s, "\n"); + + return __probe_event_show_format(s, tp, "(%lx)", + "REC->" FIELD_STRING_IP); +} + +static int kretprobe_event_show_format(struct ftrace_event_call *call, + struct trace_seq *s) +{ + struct kretprobe_trace_entry field __attribute__((unused)); + int ret, i; + struct trace_probe *tp = (struct trace_probe *)call->data; + + SHOW_FIELD(unsigned long, func, FIELD_STRING_FUNC); + SHOW_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP); + SHOW_FIELD(int, nargs, FIELD_STRING_NARGS); + + /* Show fields */ + for (i = 0; i < tp->nr_args; i++) + SHOW_FIELD(unsigned long, args[i], tp->args[i].name); + trace_seq_puts(s, "\n"); + + return __probe_event_show_format(s, tp, "(%lx <- %lx)", + "REC->" FIELD_STRING_FUNC + ", REC->" FIELD_STRING_RETIP); +} + +#ifdef CONFIG_EVENT_PROFILE + +/* Kprobe profile handler */ +static __kprobes int kprobe_profile_func(struct kprobe *kp, + struct pt_regs *regs) +{ + struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp); + struct ftrace_event_call *call = &tp->call; + struct kprobe_trace_entry *entry; + struct trace_entry *ent; + int size, __size, i, pc, __cpu; + unsigned long irq_flags; + char *trace_buf; + char *raw_data; + int rctx; + + pc = preempt_count(); + __size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args); + size = ALIGN(__size + sizeof(u32), sizeof(u64)); + size -= sizeof(u32); + if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE, + "profile buffer not large enough")) + return 0; + + /* + * Protect the non nmi buffer + * This also protects the rcu read side + */ + local_irq_save(irq_flags); + + rctx = perf_swevent_get_recursion_context(); + if (rctx < 0) + goto end_recursion; + + __cpu = smp_processor_id(); + + if (in_nmi()) + trace_buf = rcu_dereference(perf_trace_buf_nmi); + else + trace_buf = rcu_dereference(perf_trace_buf); + + if (!trace_buf) + goto end; + + raw_data = per_cpu_ptr(trace_buf, __cpu); + + /* Zero dead bytes from alignment to avoid buffer leak to userspace */ + *(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL; + entry = (struct kprobe_trace_entry *)raw_data; + ent = &entry->ent; + + tracing_generic_entry_update(ent, irq_flags, pc); + ent->type = call->id; + entry->nargs = tp->nr_args; + entry->ip = (unsigned long)kp->addr; + for (i = 0; i < tp->nr_args; i++) + entry->args[i] = call_fetch(&tp->args[i].fetch, regs); + perf_tp_event(call->id, entry->ip, 1, entry, size); + +end: + perf_swevent_put_recursion_context(rctx); +end_recursion: + local_irq_restore(irq_flags); + + return 0; +} + +/* Kretprobe profile handler */ +static __kprobes int kretprobe_profile_func(struct kretprobe_instance *ri, + struct pt_regs *regs) +{ + struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp); + struct ftrace_event_call *call = &tp->call; + struct kretprobe_trace_entry *entry; + struct trace_entry *ent; + int size, __size, i, pc, __cpu; + unsigned long irq_flags; + char *trace_buf; + char *raw_data; + int rctx; + + pc = preempt_count(); + __size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args); + size = ALIGN(__size + sizeof(u32), sizeof(u64)); + size -= sizeof(u32); + if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE, + "profile buffer not large enough")) + return 0; + + /* + * Protect the non nmi buffer + * This also protects the rcu read side + */ + local_irq_save(irq_flags); + + rctx = perf_swevent_get_recursion_context(); + if (rctx < 0) + goto end_recursion; + + __cpu = smp_processor_id(); + + if (in_nmi()) + trace_buf = rcu_dereference(perf_trace_buf_nmi); + else + trace_buf = rcu_dereference(perf_trace_buf); + + if (!trace_buf) + goto end; + + raw_data = per_cpu_ptr(trace_buf, __cpu); + + /* Zero dead bytes from alignment to avoid buffer leak to userspace */ + *(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL; + entry = (struct kretprobe_trace_entry *)raw_data; + ent = &entry->ent; + + tracing_generic_entry_update(ent, irq_flags, pc); + ent->type = call->id; + entry->nargs = tp->nr_args; + entry->func = (unsigned long)tp->rp.kp.addr; + entry->ret_ip = (unsigned long)ri->ret_addr; + for (i = 0; i < tp->nr_args; i++) + entry->args[i] = call_fetch(&tp->args[i].fetch, regs); + perf_tp_event(call->id, entry->ret_ip, 1, entry, size); + +end: + perf_swevent_put_recursion_context(rctx); +end_recursion: + local_irq_restore(irq_flags); + + return 0; +} + +static int probe_profile_enable(struct ftrace_event_call *call) +{ + struct trace_probe *tp = (struct trace_probe *)call->data; + + tp->flags |= TP_FLAG_PROFILE; + + if (probe_is_return(tp)) + return enable_kretprobe(&tp->rp); + else + return enable_kprobe(&tp->rp.kp); +} + +static void probe_profile_disable(struct ftrace_event_call *call) +{ + struct trace_probe *tp = (struct trace_probe *)call->data; + + tp->flags &= ~TP_FLAG_PROFILE; + + if (!(tp->flags & TP_FLAG_TRACE)) { + if (probe_is_return(tp)) + disable_kretprobe(&tp->rp); + else + disable_kprobe(&tp->rp.kp); + } +} +#endif /* CONFIG_EVENT_PROFILE */ + + +static __kprobes +int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs) +{ + struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp); + + if (tp->flags & TP_FLAG_TRACE) + kprobe_trace_func(kp, regs); +#ifdef CONFIG_EVENT_PROFILE + if (tp->flags & TP_FLAG_PROFILE) + kprobe_profile_func(kp, regs); +#endif /* CONFIG_EVENT_PROFILE */ + return 0; /* We don't tweek kernel, so just return 0 */ +} + +static __kprobes +int kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs) +{ + struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp); + + if (tp->flags & TP_FLAG_TRACE) + kretprobe_trace_func(ri, regs); +#ifdef CONFIG_EVENT_PROFILE + if (tp->flags & TP_FLAG_PROFILE) + kretprobe_profile_func(ri, regs); +#endif /* CONFIG_EVENT_PROFILE */ + return 0; /* We don't tweek kernel, so just return 0 */ +} + +static int register_probe_event(struct trace_probe *tp) +{ + struct ftrace_event_call *call = &tp->call; + int ret; + + /* Initialize ftrace_event_call */ + if (probe_is_return(tp)) { + tp->event.trace = print_kretprobe_event; + call->raw_init = probe_event_raw_init; + call->show_format = kretprobe_event_show_format; + call->define_fields = kretprobe_event_define_fields; + } else { + tp->event.trace = print_kprobe_event; + call->raw_init = probe_event_raw_init; + call->show_format = kprobe_event_show_format; + call->define_fields = kprobe_event_define_fields; + } + call->event = &tp->event; + call->id = register_ftrace_event(&tp->event); + if (!call->id) + return -ENODEV; + call->enabled = 0; + call->regfunc = probe_event_enable; + call->unregfunc = probe_event_disable; + +#ifdef CONFIG_EVENT_PROFILE + atomic_set(&call->profile_count, -1); + call->profile_enable = probe_profile_enable; + call->profile_disable = probe_profile_disable; +#endif + call->data = tp; + ret = trace_add_event_call(call); + if (ret) { + pr_info("Failed to register kprobe event: %s\n", call->name); + unregister_ftrace_event(&tp->event); + } + return ret; +} + +static void unregister_probe_event(struct trace_probe *tp) +{ + /* tp->event is unregistered in trace_remove_event_call() */ + trace_remove_event_call(&tp->call); +} + +/* Make a debugfs interface for controling probe points */ +static __init int init_kprobe_trace(void) +{ + struct dentry *d_tracer; + struct dentry *entry; + + d_tracer = tracing_init_dentry(); + if (!d_tracer) + return 0; + + entry = debugfs_create_file("kprobe_events", 0644, d_tracer, + NULL, &kprobe_events_ops); + + /* Event list interface */ + if (!entry) + pr_warning("Could not create debugfs " + "'kprobe_events' entry\n"); + + /* Profile interface */ + entry = debugfs_create_file("kprobe_profile", 0444, d_tracer, + NULL, &kprobe_profile_ops); + + if (!entry) + pr_warning("Could not create debugfs " + "'kprobe_profile' entry\n"); + return 0; +} +fs_initcall(init_kprobe_trace); + + +#ifdef CONFIG_FTRACE_STARTUP_TEST + +static int kprobe_trace_selftest_target(int a1, int a2, int a3, + int a4, int a5, int a6) +{ + return a1 + a2 + a3 + a4 + a5 + a6; +} + +static __init int kprobe_trace_self_tests_init(void) +{ + int ret; + int (*target)(int, int, int, int, int, int); + + target = kprobe_trace_selftest_target; + + pr_info("Testing kprobe tracing: "); + + ret = command_trace_probe("p:testprobe kprobe_trace_selftest_target " + "$arg1 $arg2 $arg3 $arg4 $stack $stack0"); + if (WARN_ON_ONCE(ret)) + pr_warning("error enabling function entry\n"); + + ret = command_trace_probe("r:testprobe2 kprobe_trace_selftest_target " + "$retval"); + if (WARN_ON_ONCE(ret)) + pr_warning("error enabling function return\n"); + + ret = target(1, 2, 3, 4, 5, 6); + + cleanup_all_probes(); + + pr_cont("OK\n"); + return 0; +} + +late_initcall(kprobe_trace_self_tests_init); + +#endif diff --git a/kernel/trace/trace_ksym.c b/kernel/trace/trace_ksym.c new file mode 100644 index 000000000000..ddfa0fd43bc0 --- /dev/null +++ b/kernel/trace/trace_ksym.c @@ -0,0 +1,550 @@ +/* + * trace_ksym.c - Kernel Symbol Tracer + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) IBM Corporation, 2009 + */ + +#include <linux/kallsyms.h> +#include <linux/uaccess.h> +#include <linux/debugfs.h> +#include <linux/ftrace.h> +#include <linux/module.h> +#include <linux/fs.h> + +#include "trace_output.h" +#include "trace_stat.h" +#include "trace.h" + +#include <linux/hw_breakpoint.h> +#include <asm/hw_breakpoint.h> + +/* + * For now, let us restrict the no. of symbols traced simultaneously to number + * of available hardware breakpoint registers. + */ +#define KSYM_TRACER_MAX HBP_NUM + +#define KSYM_TRACER_OP_LEN 3 /* rw- */ + +struct trace_ksym { + struct perf_event **ksym_hbp; + struct perf_event_attr attr; +#ifdef CONFIG_PROFILE_KSYM_TRACER + unsigned long counter; +#endif + struct hlist_node ksym_hlist; +}; + +static struct trace_array *ksym_trace_array; + +static unsigned int ksym_filter_entry_count; +static unsigned int ksym_tracing_enabled; + +static HLIST_HEAD(ksym_filter_head); + +static DEFINE_MUTEX(ksym_tracer_mutex); + +#ifdef CONFIG_PROFILE_KSYM_TRACER + +#define MAX_UL_INT 0xffffffff + +void ksym_collect_stats(unsigned long hbp_hit_addr) +{ + struct hlist_node *node; + struct trace_ksym *entry; + + rcu_read_lock(); + hlist_for_each_entry_rcu(entry, node, &ksym_filter_head, ksym_hlist) { + if ((entry->attr.bp_addr == hbp_hit_addr) && + (entry->counter <= MAX_UL_INT)) { + entry->counter++; + break; + } + } + rcu_read_unlock(); +} +#endif /* CONFIG_PROFILE_KSYM_TRACER */ + +void ksym_hbp_handler(struct perf_event *hbp, void *data) +{ + struct ring_buffer_event *event; + struct ksym_trace_entry *entry; + struct pt_regs *regs = data; + struct ring_buffer *buffer; + int pc; + + if (!ksym_tracing_enabled) + return; + + buffer = ksym_trace_array->buffer; + + pc = preempt_count(); + + event = trace_buffer_lock_reserve(buffer, TRACE_KSYM, + sizeof(*entry), 0, pc); + if (!event) + return; + + entry = ring_buffer_event_data(event); + entry->ip = instruction_pointer(regs); + entry->type = hw_breakpoint_type(hbp); + entry->addr = hw_breakpoint_addr(hbp); + strlcpy(entry->cmd, current->comm, TASK_COMM_LEN); + +#ifdef CONFIG_PROFILE_KSYM_TRACER + ksym_collect_stats(hw_breakpoint_addr(hbp)); +#endif /* CONFIG_PROFILE_KSYM_TRACER */ + + trace_buffer_unlock_commit(buffer, event, 0, pc); +} + +/* Valid access types are represented as + * + * rw- : Set Read/Write Access Breakpoint + * -w- : Set Write Access Breakpoint + * --- : Clear Breakpoints + * --x : Set Execution Break points (Not available yet) + * + */ +static int ksym_trace_get_access_type(char *str) +{ + int access = 0; + + if (str[0] == 'r') + access |= HW_BREAKPOINT_R; + + if (str[1] == 'w') + access |= HW_BREAKPOINT_W; + + if (str[2] == 'x') + access |= HW_BREAKPOINT_X; + + switch (access) { + case HW_BREAKPOINT_R: + case HW_BREAKPOINT_W: + case HW_BREAKPOINT_W | HW_BREAKPOINT_R: + return access; + default: + return -EINVAL; + } +} + +/* + * There can be several possible malformed requests and we attempt to capture + * all of them. We enumerate some of the rules + * 1. We will not allow kernel symbols with ':' since it is used as a delimiter. + * i.e. multiple ':' symbols disallowed. Possible uses are of the form + * <module>:<ksym_name>:<op>. + * 2. No delimiter symbol ':' in the input string + * 3. Spurious operator symbols or symbols not in their respective positions + * 4. <ksym_name>:--- i.e. clear breakpoint request when ksym_name not in file + * 5. Kernel symbol not a part of /proc/kallsyms + * 6. Duplicate requests + */ +static int parse_ksym_trace_str(char *input_string, char **ksymname, + unsigned long *addr) +{ + int ret; + + *ksymname = strsep(&input_string, ":"); + *addr = kallsyms_lookup_name(*ksymname); + + /* Check for malformed request: (2), (1) and (5) */ + if ((!input_string) || + (strlen(input_string) != KSYM_TRACER_OP_LEN) || + (*addr == 0)) + return -EINVAL;; + + ret = ksym_trace_get_access_type(input_string); + + return ret; +} + +int process_new_ksym_entry(char *ksymname, int op, unsigned long addr) +{ + struct trace_ksym *entry; + int ret = -ENOMEM; + + if (ksym_filter_entry_count >= KSYM_TRACER_MAX) { + printk(KERN_ERR "ksym_tracer: Maximum limit:(%d) reached. No" + " new requests for tracing can be accepted now.\n", + KSYM_TRACER_MAX); + return -ENOSPC; + } + + entry = kzalloc(sizeof(struct trace_ksym), GFP_KERNEL); + if (!entry) + return -ENOMEM; + + hw_breakpoint_init(&entry->attr); + + entry->attr.bp_type = op; + entry->attr.bp_addr = addr; + entry->attr.bp_len = HW_BREAKPOINT_LEN_4; + + ret = -EAGAIN; + entry->ksym_hbp = register_wide_hw_breakpoint(&entry->attr, + ksym_hbp_handler); + + if (IS_ERR(entry->ksym_hbp)) { + ret = PTR_ERR(entry->ksym_hbp); + printk(KERN_INFO "ksym_tracer request failed. Try again" + " later!!\n"); + goto err; + } + + hlist_add_head_rcu(&(entry->ksym_hlist), &ksym_filter_head); + ksym_filter_entry_count++; + + return 0; + +err: + kfree(entry); + + return ret; +} + +static ssize_t ksym_trace_filter_read(struct file *filp, char __user *ubuf, + size_t count, loff_t *ppos) +{ + struct trace_ksym *entry; + struct hlist_node *node; + struct trace_seq *s; + ssize_t cnt = 0; + int ret; + + s = kmalloc(sizeof(*s), GFP_KERNEL); + if (!s) + return -ENOMEM; + trace_seq_init(s); + + mutex_lock(&ksym_tracer_mutex); + + hlist_for_each_entry(entry, node, &ksym_filter_head, ksym_hlist) { + ret = trace_seq_printf(s, "%pS:", (void *)entry->attr.bp_addr); + if (entry->attr.bp_type == HW_BREAKPOINT_R) + ret = trace_seq_puts(s, "r--\n"); + else if (entry->attr.bp_type == HW_BREAKPOINT_W) + ret = trace_seq_puts(s, "-w-\n"); + else if (entry->attr.bp_type == (HW_BREAKPOINT_W | HW_BREAKPOINT_R)) + ret = trace_seq_puts(s, "rw-\n"); + WARN_ON_ONCE(!ret); + } + + cnt = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len); + + mutex_unlock(&ksym_tracer_mutex); + + kfree(s); + + return cnt; +} + +static void __ksym_trace_reset(void) +{ + struct trace_ksym *entry; + struct hlist_node *node, *node1; + + mutex_lock(&ksym_tracer_mutex); + hlist_for_each_entry_safe(entry, node, node1, &ksym_filter_head, + ksym_hlist) { + unregister_wide_hw_breakpoint(entry->ksym_hbp); + ksym_filter_entry_count--; + hlist_del_rcu(&(entry->ksym_hlist)); + synchronize_rcu(); + kfree(entry); + } + mutex_unlock(&ksym_tracer_mutex); +} + +static ssize_t ksym_trace_filter_write(struct file *file, + const char __user *buffer, + size_t count, loff_t *ppos) +{ + struct trace_ksym *entry; + struct hlist_node *node; + char *input_string, *ksymname = NULL; + unsigned long ksym_addr = 0; + int ret, op, changed = 0; + + input_string = kzalloc(count + 1, GFP_KERNEL); + if (!input_string) + return -ENOMEM; + + if (copy_from_user(input_string, buffer, count)) { + kfree(input_string); + return -EFAULT; + } + input_string[count] = '\0'; + + strstrip(input_string); + + /* + * Clear all breakpoints if: + * 1: echo > ksym_trace_filter + * 2: echo 0 > ksym_trace_filter + * 3: echo "*:---" > ksym_trace_filter + */ + if (!input_string[0] || !strcmp(input_string, "0") || + !strcmp(input_string, "*:---")) { + __ksym_trace_reset(); + kfree(input_string); + return count; + } + + ret = op = parse_ksym_trace_str(input_string, &ksymname, &ksym_addr); + if (ret < 0) { + kfree(input_string); + return ret; + } + + mutex_lock(&ksym_tracer_mutex); + + ret = -EINVAL; + hlist_for_each_entry(entry, node, &ksym_filter_head, ksym_hlist) { + if (entry->attr.bp_addr == ksym_addr) { + /* Check for malformed request: (6) */ + if (entry->attr.bp_type != op) + changed = 1; + else + goto out; + break; + } + } + if (changed) { + unregister_wide_hw_breakpoint(entry->ksym_hbp); + entry->attr.bp_type = op; + ret = 0; + if (op > 0) { + entry->ksym_hbp = + register_wide_hw_breakpoint(&entry->attr, + ksym_hbp_handler); + if (IS_ERR(entry->ksym_hbp)) + ret = PTR_ERR(entry->ksym_hbp); + else + goto out; + } + /* Error or "symbol:---" case: drop it */ + ksym_filter_entry_count--; + hlist_del_rcu(&(entry->ksym_hlist)); + synchronize_rcu(); + kfree(entry); + goto out; + } else { + /* Check for malformed request: (4) */ + if (op == 0) + goto out; + ret = process_new_ksym_entry(ksymname, op, ksym_addr); + } +out: + mutex_unlock(&ksym_tracer_mutex); + + kfree(input_string); + + if (!ret) + ret = count; + return ret; +} + +static const struct file_operations ksym_tracing_fops = { + .open = tracing_open_generic, + .read = ksym_trace_filter_read, + .write = ksym_trace_filter_write, +}; + +static void ksym_trace_reset(struct trace_array *tr) +{ + ksym_tracing_enabled = 0; + __ksym_trace_reset(); +} + +static int ksym_trace_init(struct trace_array *tr) +{ + int cpu, ret = 0; + + for_each_online_cpu(cpu) + tracing_reset(tr, cpu); + ksym_tracing_enabled = 1; + ksym_trace_array = tr; + + return ret; +} + +static void ksym_trace_print_header(struct seq_file *m) +{ + seq_puts(m, + "# TASK-PID CPU# Symbol " + "Type Function\n"); + seq_puts(m, + "# | | | " + " | |\n"); +} + +static enum print_line_t ksym_trace_output(struct trace_iterator *iter) +{ + struct trace_entry *entry = iter->ent; + struct trace_seq *s = &iter->seq; + struct ksym_trace_entry *field; + char str[KSYM_SYMBOL_LEN]; + int ret; + + if (entry->type != TRACE_KSYM) + return TRACE_TYPE_UNHANDLED; + + trace_assign_type(field, entry); + + ret = trace_seq_printf(s, "%11s-%-5d [%03d] %pS", field->cmd, + entry->pid, iter->cpu, (char *)field->addr); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + switch (field->type) { + case HW_BREAKPOINT_R: + ret = trace_seq_printf(s, " R "); + break; + case HW_BREAKPOINT_W: + ret = trace_seq_printf(s, " W "); + break; + case HW_BREAKPOINT_R | HW_BREAKPOINT_W: + ret = trace_seq_printf(s, " RW "); + break; + default: + return TRACE_TYPE_PARTIAL_LINE; + } + + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + sprint_symbol(str, field->ip); + ret = trace_seq_printf(s, "%s\n", str); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + +struct tracer ksym_tracer __read_mostly = +{ + .name = "ksym_tracer", + .init = ksym_trace_init, + .reset = ksym_trace_reset, +#ifdef CONFIG_FTRACE_SELFTEST + .selftest = trace_selftest_startup_ksym, +#endif + .print_header = ksym_trace_print_header, + .print_line = ksym_trace_output +}; + +__init static int init_ksym_trace(void) +{ + struct dentry *d_tracer; + struct dentry *entry; + + d_tracer = tracing_init_dentry(); + ksym_filter_entry_count = 0; + + entry = debugfs_create_file("ksym_trace_filter", 0644, d_tracer, + NULL, &ksym_tracing_fops); + if (!entry) + pr_warning("Could not create debugfs " + "'ksym_trace_filter' file\n"); + + return register_tracer(&ksym_tracer); +} +device_initcall(init_ksym_trace); + + +#ifdef CONFIG_PROFILE_KSYM_TRACER +static int ksym_tracer_stat_headers(struct seq_file *m) +{ + seq_puts(m, " Access Type "); + seq_puts(m, " Symbol Counter\n"); + seq_puts(m, " ----------- "); + seq_puts(m, " ------ -------\n"); + return 0; +} + +static int ksym_tracer_stat_show(struct seq_file *m, void *v) +{ + struct hlist_node *stat = v; + struct trace_ksym *entry; + int access_type = 0; + char fn_name[KSYM_NAME_LEN]; + + entry = hlist_entry(stat, struct trace_ksym, ksym_hlist); + + access_type = entry->attr.bp_type; + + switch (access_type) { + case HW_BREAKPOINT_R: + seq_puts(m, " R "); + break; + case HW_BREAKPOINT_W: + seq_puts(m, " W "); + break; + case HW_BREAKPOINT_R | HW_BREAKPOINT_W: + seq_puts(m, " RW "); + break; + default: + seq_puts(m, " NA "); + } + + if (lookup_symbol_name(entry->attr.bp_addr, fn_name) >= 0) + seq_printf(m, " %-36s", fn_name); + else + seq_printf(m, " %-36s", "<NA>"); + seq_printf(m, " %15lu\n", entry->counter); + + return 0; +} + +static void *ksym_tracer_stat_start(struct tracer_stat *trace) +{ + return ksym_filter_head.first; +} + +static void * +ksym_tracer_stat_next(void *v, int idx) +{ + struct hlist_node *stat = v; + + return stat->next; +} + +static struct tracer_stat ksym_tracer_stats = { + .name = "ksym_tracer", + .stat_start = ksym_tracer_stat_start, + .stat_next = ksym_tracer_stat_next, + .stat_headers = ksym_tracer_stat_headers, + .stat_show = ksym_tracer_stat_show +}; + +__init static int ksym_tracer_stat_init(void) +{ + int ret; + + ret = register_stat_tracer(&ksym_tracer_stats); + if (ret) { + printk(KERN_WARNING "Warning: could not register " + "ksym tracer stats\n"); + return 1; + } + + return 0; +} +fs_initcall(ksym_tracer_stat_init); +#endif /* CONFIG_PROFILE_KSYM_TRACER */ diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index d2cdbabb4ead..dc98309e839a 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -17,6 +17,7 @@ static inline int trace_valid_entry(struct trace_entry *entry) case TRACE_GRAPH_ENT: case TRACE_GRAPH_RET: case TRACE_HW_BRANCHES: + case TRACE_KSYM: return 1; } return 0; @@ -808,3 +809,57 @@ trace_selftest_startup_hw_branches(struct tracer *trace, return ret; } #endif /* CONFIG_HW_BRANCH_TRACER */ + +#ifdef CONFIG_KSYM_TRACER +static int ksym_selftest_dummy; + +int +trace_selftest_startup_ksym(struct tracer *trace, struct trace_array *tr) +{ + unsigned long count; + int ret; + + /* start the tracing */ + ret = tracer_init(trace, tr); + if (ret) { + warn_failed_init_tracer(trace, ret); + return ret; + } + + ksym_selftest_dummy = 0; + /* Register the read-write tracing request */ + + ret = process_new_ksym_entry("ksym_selftest_dummy", + HW_BREAKPOINT_R | HW_BREAKPOINT_W, + (unsigned long)(&ksym_selftest_dummy)); + + if (ret < 0) { + printk(KERN_CONT "ksym_trace read-write startup test failed\n"); + goto ret_path; + } + /* Perform a read and a write operation over the dummy variable to + * trigger the tracer + */ + if (ksym_selftest_dummy == 0) + ksym_selftest_dummy++; + + /* stop the tracing. */ + tracing_stop(); + /* check the trace buffer */ + ret = trace_test_buffer(tr, &count); + trace->reset(tr); + tracing_start(); + + /* read & write operations - one each is performed on the dummy variable + * triggering two entries in the trace buffer + */ + if (!ret && count != 2) { + printk(KERN_CONT "Ksym tracer startup test failed"); + ret = -1; + } + +ret_path: + return ret; +} +#endif /* CONFIG_KSYM_TRACER */ + diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 527e17eae575..57501d90096a 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -14,6 +14,43 @@ static int sys_refcount_exit; static DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls); static DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls); +extern unsigned long __start_syscalls_metadata[]; +extern unsigned long __stop_syscalls_metadata[]; + +static struct syscall_metadata **syscalls_metadata; + +static struct syscall_metadata *find_syscall_meta(unsigned long syscall) +{ + struct syscall_metadata *start; + struct syscall_metadata *stop; + char str[KSYM_SYMBOL_LEN]; + + + start = (struct syscall_metadata *)__start_syscalls_metadata; + stop = (struct syscall_metadata *)__stop_syscalls_metadata; + kallsyms_lookup(syscall, NULL, NULL, NULL, str); + + for ( ; start < stop; start++) { + /* + * Only compare after the "sys" prefix. Archs that use + * syscall wrappers may have syscalls symbols aliases prefixed + * with "SyS" instead of "sys", leading to an unwanted + * mismatch. + */ + if (start->name && !strcmp(start->name + 3, str + 3)) + return start; + } + return NULL; +} + +static struct syscall_metadata *syscall_nr_to_meta(int nr) +{ + if (!syscalls_metadata || nr >= NR_syscalls || nr < 0) + return NULL; + + return syscalls_metadata[nr]; +} + enum print_line_t print_syscall_enter(struct trace_iterator *iter, int flags) { @@ -30,7 +67,7 @@ print_syscall_enter(struct trace_iterator *iter, int flags) if (!entry) goto end; - if (entry->enter_id != ent->type) { + if (entry->enter_event->id != ent->type) { WARN_ON_ONCE(1); goto end; } @@ -85,7 +122,7 @@ print_syscall_exit(struct trace_iterator *iter, int flags) return TRACE_TYPE_HANDLED; } - if (entry->exit_id != ent->type) { + if (entry->exit_event->id != ent->type) { WARN_ON_ONCE(1); return TRACE_TYPE_UNHANDLED; } @@ -103,24 +140,19 @@ extern char *__bad_type_size(void); #define SYSCALL_FIELD(type, name) \ sizeof(type) != sizeof(trace.name) ? \ __bad_type_size() : \ - #type, #name, offsetof(typeof(trace), name), sizeof(trace.name) + #type, #name, offsetof(typeof(trace), name), \ + sizeof(trace.name), is_signed_type(type) int syscall_enter_format(struct ftrace_event_call *call, struct trace_seq *s) { int i; - int nr; int ret; - struct syscall_metadata *entry; + struct syscall_metadata *entry = call->data; struct syscall_trace_enter trace; int offset = offsetof(struct syscall_trace_enter, args); - nr = syscall_name_to_nr(call->data); - entry = syscall_nr_to_meta(nr); - - if (!entry) - return 0; - - ret = trace_seq_printf(s, "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n", + ret = trace_seq_printf(s, "\tfield:%s %s;\toffset:%zu;\tsize:%zu;" + "\tsigned:%u;\n", SYSCALL_FIELD(int, nr)); if (!ret) return 0; @@ -130,8 +162,10 @@ int syscall_enter_format(struct ftrace_event_call *call, struct trace_seq *s) entry->args[i]); if (!ret) return 0; - ret = trace_seq_printf(s, "\toffset:%d;\tsize:%zu;\n", offset, - sizeof(unsigned long)); + ret = trace_seq_printf(s, "\toffset:%d;\tsize:%zu;" + "\tsigned:%u;\n", offset, + sizeof(unsigned long), + is_signed_type(unsigned long)); if (!ret) return 0; offset += sizeof(unsigned long); @@ -163,8 +197,10 @@ int syscall_exit_format(struct ftrace_event_call *call, struct trace_seq *s) struct syscall_trace_exit trace; ret = trace_seq_printf(s, - "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n" - "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n", + "\tfield:%s %s;\toffset:%zu;\tsize:%zu;" + "\tsigned:%u;\n" + "\tfield:%s %s;\toffset:%zu;\tsize:%zu;" + "\tsigned:%u;\n", SYSCALL_FIELD(int, nr), SYSCALL_FIELD(long, ret)); if (!ret) @@ -176,22 +212,19 @@ int syscall_exit_format(struct ftrace_event_call *call, struct trace_seq *s) int syscall_enter_define_fields(struct ftrace_event_call *call) { struct syscall_trace_enter trace; - struct syscall_metadata *meta; + struct syscall_metadata *meta = call->data; int ret; - int nr; int i; int offset = offsetof(typeof(trace), args); - nr = syscall_name_to_nr(call->data); - meta = syscall_nr_to_meta(nr); - - if (!meta) - return 0; - ret = trace_define_common_fields(call); if (ret) return ret; + ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER); + if (ret) + return ret; + for (i = 0; i < meta->nb_args; i++) { ret = trace_define_field(call, meta->types[i], meta->args[i], offset, @@ -212,7 +245,11 @@ int syscall_exit_define_fields(struct ftrace_event_call *call) if (ret) return ret; - ret = trace_define_field(call, SYSCALL_FIELD(long, ret), 0, + ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER); + if (ret) + return ret; + + ret = trace_define_field(call, SYSCALL_FIELD(long, ret), FILTER_OTHER); return ret; @@ -239,8 +276,8 @@ void ftrace_syscall_enter(struct pt_regs *regs, long id) size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args; - event = trace_current_buffer_lock_reserve(&buffer, sys_data->enter_id, - size, 0, 0); + event = trace_current_buffer_lock_reserve(&buffer, + sys_data->enter_event->id, size, 0, 0); if (!event) return; @@ -271,8 +308,8 @@ void ftrace_syscall_exit(struct pt_regs *regs, long ret) if (!sys_data) return; - event = trace_current_buffer_lock_reserve(&buffer, sys_data->exit_id, - sizeof(*entry), 0, 0); + event = trace_current_buffer_lock_reserve(&buffer, + sys_data->exit_event->id, sizeof(*entry), 0, 0); if (!event) return; @@ -285,14 +322,12 @@ void ftrace_syscall_exit(struct pt_regs *regs, long ret) trace_current_buffer_unlock_commit(buffer, event, 0, 0); } -int reg_event_syscall_enter(void *ptr) +int reg_event_syscall_enter(struct ftrace_event_call *call) { int ret = 0; int num; - char *name; - name = (char *)ptr; - num = syscall_name_to_nr(name); + num = ((struct syscall_metadata *)call->data)->syscall_nr; if (num < 0 || num >= NR_syscalls) return -ENOSYS; mutex_lock(&syscall_trace_lock); @@ -309,13 +344,11 @@ int reg_event_syscall_enter(void *ptr) return ret; } -void unreg_event_syscall_enter(void *ptr) +void unreg_event_syscall_enter(struct ftrace_event_call *call) { int num; - char *name; - name = (char *)ptr; - num = syscall_name_to_nr(name); + num = ((struct syscall_metadata *)call->data)->syscall_nr; if (num < 0 || num >= NR_syscalls) return; mutex_lock(&syscall_trace_lock); @@ -326,14 +359,12 @@ void unreg_event_syscall_enter(void *ptr) mutex_unlock(&syscall_trace_lock); } -int reg_event_syscall_exit(void *ptr) +int reg_event_syscall_exit(struct ftrace_event_call *call) { int ret = 0; int num; - char *name; - name = (char *)ptr; - num = syscall_name_to_nr(name); + num = ((struct syscall_metadata *)call->data)->syscall_nr; if (num < 0 || num >= NR_syscalls) return -ENOSYS; mutex_lock(&syscall_trace_lock); @@ -350,13 +381,11 @@ int reg_event_syscall_exit(void *ptr) return ret; } -void unreg_event_syscall_exit(void *ptr) +void unreg_event_syscall_exit(struct ftrace_event_call *call) { int num; - char *name; - name = (char *)ptr; - num = syscall_name_to_nr(name); + num = ((struct syscall_metadata *)call->data)->syscall_nr; if (num < 0 || num >= NR_syscalls) return; mutex_lock(&syscall_trace_lock); @@ -367,13 +396,44 @@ void unreg_event_syscall_exit(void *ptr) mutex_unlock(&syscall_trace_lock); } -struct trace_event event_syscall_enter = { - .trace = print_syscall_enter, -}; +int init_syscall_trace(struct ftrace_event_call *call) +{ + int id; + + id = register_ftrace_event(call->event); + if (!id) + return -ENODEV; + call->id = id; + INIT_LIST_HEAD(&call->fields); + return 0; +} + +int __init init_ftrace_syscalls(void) +{ + struct syscall_metadata *meta; + unsigned long addr; + int i; + + syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) * + NR_syscalls, GFP_KERNEL); + if (!syscalls_metadata) { + WARN_ON(1); + return -ENOMEM; + } + + for (i = 0; i < NR_syscalls; i++) { + addr = arch_syscall_addr(i); + meta = find_syscall_meta(addr); + if (!meta) + continue; + + meta->syscall_nr = i; + syscalls_metadata[i] = meta; + } -struct trace_event event_syscall_exit = { - .trace = print_syscall_exit, -}; + return 0; +} +core_initcall(init_ftrace_syscalls); #ifdef CONFIG_EVENT_PROFILE @@ -387,8 +447,10 @@ static void prof_syscall_enter(struct pt_regs *regs, long id) struct syscall_metadata *sys_data; struct syscall_trace_enter *rec; unsigned long flags; + char *trace_buf; char *raw_data; int syscall_nr; + int rctx; int size; int cpu; @@ -412,41 +474,42 @@ static void prof_syscall_enter(struct pt_regs *regs, long id) /* Protect the per cpu buffer, begin the rcu read side */ local_irq_save(flags); + rctx = perf_swevent_get_recursion_context(); + if (rctx < 0) + goto end_recursion; + cpu = smp_processor_id(); - if (in_nmi()) - raw_data = rcu_dereference(trace_profile_buf_nmi); - else - raw_data = rcu_dereference(trace_profile_buf); + trace_buf = rcu_dereference(perf_trace_buf); - if (!raw_data) + if (!trace_buf) goto end; - raw_data = per_cpu_ptr(raw_data, cpu); + raw_data = per_cpu_ptr(trace_buf, cpu); /* zero the dead bytes from align to not leak stack to user */ *(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL; rec = (struct syscall_trace_enter *) raw_data; tracing_generic_entry_update(&rec->ent, 0, 0); - rec->ent.type = sys_data->enter_id; + rec->ent.type = sys_data->enter_event->id; rec->nr = syscall_nr; syscall_get_arguments(current, regs, 0, sys_data->nb_args, (unsigned long *)&rec->args); - perf_tp_event(sys_data->enter_id, 0, 1, rec, size); + perf_tp_event(sys_data->enter_event->id, 0, 1, rec, size); end: + perf_swevent_put_recursion_context(rctx); +end_recursion: local_irq_restore(flags); } -int reg_prof_syscall_enter(char *name) +int prof_sysenter_enable(struct ftrace_event_call *call) { int ret = 0; int num; - num = syscall_name_to_nr(name); - if (num < 0 || num >= NR_syscalls) - return -ENOSYS; + num = ((struct syscall_metadata *)call->data)->syscall_nr; mutex_lock(&syscall_trace_lock); if (!sys_prof_refcount_enter) @@ -462,13 +525,11 @@ int reg_prof_syscall_enter(char *name) return ret; } -void unreg_prof_syscall_enter(char *name) +void prof_sysenter_disable(struct ftrace_event_call *call) { int num; - num = syscall_name_to_nr(name); - if (num < 0 || num >= NR_syscalls) - return; + num = ((struct syscall_metadata *)call->data)->syscall_nr; mutex_lock(&syscall_trace_lock); sys_prof_refcount_enter--; @@ -484,7 +545,9 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret) struct syscall_trace_exit *rec; unsigned long flags; int syscall_nr; + char *trace_buf; char *raw_data; + int rctx; int size; int cpu; @@ -510,17 +573,19 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret) /* Protect the per cpu buffer, begin the rcu read side */ local_irq_save(flags); + + rctx = perf_swevent_get_recursion_context(); + if (rctx < 0) + goto end_recursion; + cpu = smp_processor_id(); - if (in_nmi()) - raw_data = rcu_dereference(trace_profile_buf_nmi); - else - raw_data = rcu_dereference(trace_profile_buf); + trace_buf = rcu_dereference(perf_trace_buf); - if (!raw_data) + if (!trace_buf) goto end; - raw_data = per_cpu_ptr(raw_data, cpu); + raw_data = per_cpu_ptr(trace_buf, cpu); /* zero the dead bytes from align to not leak stack to user */ *(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL; @@ -528,24 +593,24 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret) rec = (struct syscall_trace_exit *)raw_data; tracing_generic_entry_update(&rec->ent, 0, 0); - rec->ent.type = sys_data->exit_id; + rec->ent.type = sys_data->exit_event->id; rec->nr = syscall_nr; rec->ret = syscall_get_return_value(current, regs); - perf_tp_event(sys_data->exit_id, 0, 1, rec, size); + perf_tp_event(sys_data->exit_event->id, 0, 1, rec, size); end: + perf_swevent_put_recursion_context(rctx); +end_recursion: local_irq_restore(flags); } -int reg_prof_syscall_exit(char *name) +int prof_sysexit_enable(struct ftrace_event_call *call) { int ret = 0; int num; - num = syscall_name_to_nr(name); - if (num < 0 || num >= NR_syscalls) - return -ENOSYS; + num = ((struct syscall_metadata *)call->data)->syscall_nr; mutex_lock(&syscall_trace_lock); if (!sys_prof_refcount_exit) @@ -561,13 +626,11 @@ int reg_prof_syscall_exit(char *name) return ret; } -void unreg_prof_syscall_exit(char *name) +void prof_sysexit_disable(struct ftrace_event_call *call) { int num; - num = syscall_name_to_nr(name); - if (num < 0 || num >= NR_syscalls) - return; + num = ((struct syscall_metadata *)call->data)->syscall_nr; mutex_lock(&syscall_trace_lock); sys_prof_refcount_exit--; diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c index 69eae358a726..a2cd77e70d4d 100644 --- a/kernel/utsname_sysctl.c +++ b/kernel/utsname_sysctl.c @@ -57,78 +57,47 @@ static int proc_do_uts_string(ctl_table *table, int write, #define proc_do_uts_string NULL #endif - -#ifdef CONFIG_SYSCTL_SYSCALL -/* The generic string strategy routine: */ -static int sysctl_uts_string(ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - struct ctl_table uts_table; - int r, write; - write = newval && newlen; - memcpy(&uts_table, table, sizeof(uts_table)); - uts_table.data = get_uts(table, write); - r = sysctl_string(&uts_table, oldval, oldlenp, newval, newlen); - put_uts(table, write, uts_table.data); - return r; -} -#else -#define sysctl_uts_string NULL -#endif - static struct ctl_table uts_kern_table[] = { { - .ctl_name = KERN_OSTYPE, .procname = "ostype", .data = init_uts_ns.name.sysname, .maxlen = sizeof(init_uts_ns.name.sysname), .mode = 0444, .proc_handler = proc_do_uts_string, - .strategy = sysctl_uts_string, }, { - .ctl_name = KERN_OSRELEASE, .procname = "osrelease", .data = init_uts_ns.name.release, .maxlen = sizeof(init_uts_ns.name.release), .mode = 0444, .proc_handler = proc_do_uts_string, - .strategy = sysctl_uts_string, }, { - .ctl_name = KERN_VERSION, .procname = "version", .data = init_uts_ns.name.version, .maxlen = sizeof(init_uts_ns.name.version), .mode = 0444, .proc_handler = proc_do_uts_string, - .strategy = sysctl_uts_string, }, { - .ctl_name = KERN_NODENAME, .procname = "hostname", .data = init_uts_ns.name.nodename, .maxlen = sizeof(init_uts_ns.name.nodename), .mode = 0644, .proc_handler = proc_do_uts_string, - .strategy = sysctl_uts_string, }, { - .ctl_name = KERN_DOMAINNAME, .procname = "domainname", .data = init_uts_ns.name.domainname, .maxlen = sizeof(init_uts_ns.name.domainname), .mode = 0644, .proc_handler = proc_do_uts_string, - .strategy = sysctl_uts_string, }, {} }; static struct ctl_table uts_root_table[] = { { - .ctl_name = CTL_KERN, .procname = "kernel", .mode = 0555, .child = uts_kern_table, diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 234ceb10861f..0b8f35918a36 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -750,7 +750,7 @@ config RCU_TORTURE_TEST_RUNNABLE config RCU_CPU_STALL_DETECTOR bool "Check for stalled CPUs delaying RCU grace periods" depends on TREE_RCU || TREE_PREEMPT_RCU - default n + default y help This option causes RCU to printk information on which CPUs are delaying the current grace period, but only when @@ -912,7 +912,7 @@ config LATENCYTOP config SYSCTL_SYSCALL_CHECK bool "Sysctl checks" - depends on SYSCTL_SYSCALL + depends on SYSCTL ---help--- sys_sysctl uses binary paths that have been found challenging to properly maintain and use. This enables checks that help diff --git a/lib/kernel_lock.c b/lib/kernel_lock.c index 39f1029e3525..4ebfa5a164d7 100644 --- a/lib/kernel_lock.c +++ b/lib/kernel_lock.c @@ -5,10 +5,13 @@ * relegated to obsolescence, but used by various less * important (or lazy) subsystems. */ -#include <linux/smp_lock.h> #include <linux/module.h> #include <linux/kallsyms.h> #include <linux/semaphore.h> +#include <linux/smp_lock.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/bkl.h> /* * The 'big kernel lock' @@ -113,21 +116,26 @@ static inline void __unlock_kernel(void) * This cannot happen asynchronously, so we only need to * worry about other CPU's. */ -void __lockfunc lock_kernel(void) +void __lockfunc _lock_kernel(const char *func, const char *file, int line) { - int depth = current->lock_depth+1; + int depth = current->lock_depth + 1; + + trace_lock_kernel(func, file, line); + if (likely(!depth)) __lock_kernel(); current->lock_depth = depth; } -void __lockfunc unlock_kernel(void) +void __lockfunc _unlock_kernel(const char *func, const char *file, int line) { BUG_ON(current->lock_depth < 0); if (likely(--current->lock_depth < 0)) __unlock_kernel(); + + trace_unlock_kernel(func, file, line); } -EXPORT_SYMBOL(lock_kernel); -EXPORT_SYMBOL(unlock_kernel); +EXPORT_SYMBOL(_lock_kernel); +EXPORT_SYMBOL(_unlock_kernel); diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 23abbd93cae1..92cdd9936e3d 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -200,6 +200,9 @@ radix_tree_node_free(struct radix_tree_node *node) * ensure that the addition of a single element in the tree cannot fail. On * success, return zero, with preemption disabled. On error, return -ENOMEM * with preemption not disabled. + * + * To make use of this facility, the radix tree must be initialised without + * __GFP_WAIT being passed to INIT_RADIX_TREE(). */ int radix_tree_preload(gfp_t gfp_mask) { @@ -543,7 +546,6 @@ out: } EXPORT_SYMBOL(radix_tree_tag_clear); -#ifndef __KERNEL__ /* Only the test harness uses this at present */ /** * radix_tree_tag_get - get a tag on a radix tree node * @root: radix tree root @@ -606,7 +608,6 @@ int radix_tree_tag_get(struct radix_tree_root *root, } } EXPORT_SYMBOL(radix_tree_tag_get); -#endif /** * radix_tree_next_hole - find the next hole (not-present entry) diff --git a/lib/ratelimit.c b/lib/ratelimit.c index 26187edcc7ea..09f5ce1810dc 100644 --- a/lib/ratelimit.c +++ b/lib/ratelimit.c @@ -7,15 +7,12 @@ * parameter. Now every user can use their own standalone ratelimit_state. * * This file is released under the GPLv2. - * */ -#include <linux/kernel.h> +#include <linux/ratelimit.h> #include <linux/jiffies.h> #include <linux/module.h> -static DEFINE_SPINLOCK(ratelimit_lock); - /* * __ratelimit - rate limiting * @rs: ratelimit_state data @@ -23,35 +20,43 @@ static DEFINE_SPINLOCK(ratelimit_lock); * This enforces a rate limit: not more than @rs->ratelimit_burst callbacks * in every @rs->ratelimit_jiffies */ -int __ratelimit(struct ratelimit_state *rs) +int ___ratelimit(struct ratelimit_state *rs, const char *func) { unsigned long flags; + int ret; if (!rs->interval) return 1; - spin_lock_irqsave(&ratelimit_lock, flags); + /* + * If we contend on this state's lock then almost + * by definition we are too busy to print a message, + * in addition to the one that will be printed by + * the entity that is holding the lock already: + */ + if (!spin_trylock_irqsave(&rs->lock, flags)) + return 1; + if (!rs->begin) rs->begin = jiffies; if (time_is_before_jiffies(rs->begin + rs->interval)) { if (rs->missed) printk(KERN_WARNING "%s: %d callbacks suppressed\n", - __func__, rs->missed); - rs->begin = 0; + func, rs->missed); + rs->begin = 0; rs->printed = 0; - rs->missed = 0; + rs->missed = 0; } - if (rs->burst && rs->burst > rs->printed) - goto print; - - rs->missed++; - spin_unlock_irqrestore(&ratelimit_lock, flags); - return 0; + if (rs->burst && rs->burst > rs->printed) { + rs->printed++; + ret = 1; + } else { + rs->missed++; + ret = 0; + } + spin_unlock_irqrestore(&rs->lock, flags); -print: - rs->printed++; - spin_unlock_irqrestore(&ratelimit_lock, flags); - return 1; + return ret; } -EXPORT_SYMBOL(__ratelimit); +EXPORT_SYMBOL(___ratelimit); diff --git a/lib/swiotlb.c b/lib/swiotlb.c index ac25cd28e807..795472d8ae24 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -97,6 +97,8 @@ static phys_addr_t *io_tlb_orig_addr; */ static DEFINE_SPINLOCK(io_tlb_lock); +static int late_alloc; + static int __init setup_io_tlb_npages(char *str) { @@ -109,6 +111,7 @@ setup_io_tlb_npages(char *str) ++str; if (!strcmp(str, "force")) swiotlb_force = 1; + return 1; } __setup("swiotlb=", setup_io_tlb_npages); @@ -121,8 +124,9 @@ static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev, return phys_to_dma(hwdev, virt_to_phys(address)); } -static void swiotlb_print_info(unsigned long bytes) +void swiotlb_print_info(void) { + unsigned long bytes = io_tlb_nslabs << IO_TLB_SHIFT; phys_addr_t pstart, pend; pstart = virt_to_phys(io_tlb_start); @@ -140,7 +144,7 @@ static void swiotlb_print_info(unsigned long bytes) * structures for the software IO TLB used to implement the DMA API. */ void __init -swiotlb_init_with_default_size(size_t default_size) +swiotlb_init_with_default_size(size_t default_size, int verbose) { unsigned long i, bytes; @@ -176,14 +180,14 @@ swiotlb_init_with_default_size(size_t default_size) io_tlb_overflow_buffer = alloc_bootmem_low(io_tlb_overflow); if (!io_tlb_overflow_buffer) panic("Cannot allocate SWIOTLB overflow buffer!\n"); - - swiotlb_print_info(bytes); + if (verbose) + swiotlb_print_info(); } void __init -swiotlb_init(void) +swiotlb_init(int verbose) { - swiotlb_init_with_default_size(64 * (1<<20)); /* default to 64MB */ + swiotlb_init_with_default_size(64 * (1<<20), verbose); /* default to 64MB */ } /* @@ -260,7 +264,9 @@ swiotlb_late_init_with_default_size(size_t default_size) if (!io_tlb_overflow_buffer) goto cleanup4; - swiotlb_print_info(bytes); + swiotlb_print_info(); + + late_alloc = 1; return 0; @@ -281,6 +287,32 @@ cleanup1: return -ENOMEM; } +void __init swiotlb_free(void) +{ + if (!io_tlb_overflow_buffer) + return; + + if (late_alloc) { + free_pages((unsigned long)io_tlb_overflow_buffer, + get_order(io_tlb_overflow)); + free_pages((unsigned long)io_tlb_orig_addr, + get_order(io_tlb_nslabs * sizeof(phys_addr_t))); + free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs * + sizeof(int))); + free_pages((unsigned long)io_tlb_start, + get_order(io_tlb_nslabs << IO_TLB_SHIFT)); + } else { + free_bootmem_late(__pa(io_tlb_overflow_buffer), + io_tlb_overflow); + free_bootmem_late(__pa(io_tlb_orig_addr), + io_tlb_nslabs * sizeof(phys_addr_t)); + free_bootmem_late(__pa(io_tlb_list), + io_tlb_nslabs * sizeof(int)); + free_bootmem_late(__pa(io_tlb_start), + io_tlb_nslabs << IO_TLB_SHIFT); + } +} + static int is_swiotlb_buffer(phys_addr_t paddr) { return paddr >= virt_to_phys(io_tlb_start) && diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 11aee09dd2a6..67a33a5a1a93 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -604,10 +604,14 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi) /* * Finally, kill the kernel threads. We don't need to be RCU - * safe anymore, since the bdi is gone from visibility. + * safe anymore, since the bdi is gone from visibility. Force + * unfreeze of the thread before calling kthread_stop(), otherwise + * it would never exet if it is currently stuck in the refrigerator. */ - list_for_each_entry(wb, &bdi->wb_list, list) + list_for_each_entry(wb, &bdi->wb_list, list) { + wb->task->flags &= ~PF_FROZEN; kthread_stop(wb->task); + } } /* diff --git a/mm/bootmem.c b/mm/bootmem.c index 555d5d2731c6..d1dc23cc7f10 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -143,6 +143,30 @@ unsigned long __init init_bootmem(unsigned long start, unsigned long pages) return init_bootmem_core(NODE_DATA(0)->bdata, start, 0, pages); } +/* + * free_bootmem_late - free bootmem pages directly to page allocator + * @addr: starting address of the range + * @size: size of the range in bytes + * + * This is only useful when the bootmem allocator has already been torn + * down, but we are still initializing the system. Pages are given directly + * to the page allocator, no bootmem metadata is updated because it is gone. + */ +void __init free_bootmem_late(unsigned long addr, unsigned long size) +{ + unsigned long cursor, end; + + kmemleak_free_part(__va(addr), size); + + cursor = PFN_UP(addr); + end = PFN_DOWN(addr + size); + + for (; cursor < end; cursor++) { + __free_pages_bootmem(pfn_to_page(cursor), 0); + totalram_pages++; + } +} + static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata) { int aligned; diff --git a/mm/mmap.c b/mm/mmap.c index 73f5e4b64010..292ddc3cef9c 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -20,7 +20,6 @@ #include <linux/fs.h> #include <linux/personality.h> #include <linux/security.h> -#include <linux/ima.h> #include <linux/hugetlb.h> #include <linux/profile.h> #include <linux/module.h> @@ -1061,9 +1060,6 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, error = security_file_mmap(file, reqprot, prot, flags, addr, 0); if (error) return error; - error = ima_file_mmap(file, prot); - if (error) - return error; return mmap_region(file, addr, len, flags, vm_flags, pgoff); } diff --git a/net/802/tr.c b/net/802/tr.c index e874447ad144..44acce47fcdc 100644 --- a/net/802/tr.c +++ b/net/802/tr.c @@ -635,19 +635,18 @@ struct net_device *alloc_trdev(int sizeof_priv) #ifdef CONFIG_SYSCTL static struct ctl_table tr_table[] = { { - .ctl_name = NET_TR_RIF_TIMEOUT, .procname = "rif_timeout", .data = &sysctl_tr_rif_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, - { 0 }, + { }, }; static __initdata struct ctl_path tr_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "token-ring", .ctl_name = NET_TR, }, + { .procname = "net", }, + { .procname = "token-ring", }, { } }; #endif diff --git a/net/appletalk/sysctl_net_atalk.c b/net/appletalk/sysctl_net_atalk.c index 8d237b15183b..04e9c0da7aa9 100644 --- a/net/appletalk/sysctl_net_atalk.c +++ b/net/appletalk/sysctl_net_atalk.c @@ -12,25 +12,20 @@ static struct ctl_table atalk_table[] = { { - .ctl_name = NET_ATALK_AARP_EXPIRY_TIME, .procname = "aarp-expiry-time", .data = &sysctl_aarp_expiry_time, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_ATALK_AARP_TICK_TIME, .procname = "aarp-tick-time", .data = &sysctl_aarp_tick_time, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_ATALK_AARP_RETRANSMIT_LIMIT, .procname = "aarp-retransmit-limit", .data = &sysctl_aarp_retransmit_limit, .maxlen = sizeof(int), @@ -38,20 +33,18 @@ static struct ctl_table atalk_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_ATALK_AARP_RESOLVE_TIME, .procname = "aarp-resolve-time", .data = &sysctl_aarp_resolve_time, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, - { 0 }, + { }, }; static struct ctl_path atalk_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "appletalk", .ctl_name = NET_ATALK, }, + { .procname = "net", }, + { .procname = "appletalk", }, { } }; diff --git a/net/ax25/sysctl_net_ax25.c b/net/ax25/sysctl_net_ax25.c index 62ee3fb34732..5159be6b2625 100644 --- a/net/ax25/sysctl_net_ax25.c +++ b/net/ax25/sysctl_net_ax25.c @@ -34,156 +34,128 @@ static ctl_table *ax25_table; static int ax25_table_size; static struct ctl_path ax25_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "ax25", .ctl_name = NET_AX25, }, + { .procname = "net", }, + { .procname = "ax25", }, { } }; static const ctl_table ax25_param_table[] = { { - .ctl_name = NET_AX25_IP_DEFAULT_MODE, .procname = "ip_default_mode", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_ipdefmode, .extra2 = &max_ipdefmode }, { - .ctl_name = NET_AX25_DEFAULT_MODE, .procname = "ax25_default_mode", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_axdefmode, .extra2 = &max_axdefmode }, { - .ctl_name = NET_AX25_BACKOFF_TYPE, .procname = "backoff_type", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_backoff, .extra2 = &max_backoff }, { - .ctl_name = NET_AX25_CONNECT_MODE, .procname = "connect_mode", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_conmode, .extra2 = &max_conmode }, { - .ctl_name = NET_AX25_STANDARD_WINDOW, .procname = "standard_window_size", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_window, .extra2 = &max_window }, { - .ctl_name = NET_AX25_EXTENDED_WINDOW, .procname = "extended_window_size", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_ewindow, .extra2 = &max_ewindow }, { - .ctl_name = NET_AX25_T1_TIMEOUT, .procname = "t1_timeout", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_t1, .extra2 = &max_t1 }, { - .ctl_name = NET_AX25_T2_TIMEOUT, .procname = "t2_timeout", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_t2, .extra2 = &max_t2 }, { - .ctl_name = NET_AX25_T3_TIMEOUT, .procname = "t3_timeout", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_t3, .extra2 = &max_t3 }, { - .ctl_name = NET_AX25_IDLE_TIMEOUT, .procname = "idle_timeout", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_idle, .extra2 = &max_idle }, { - .ctl_name = NET_AX25_N2, .procname = "maximum_retry_count", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_n2, .extra2 = &max_n2 }, { - .ctl_name = NET_AX25_PACLEN, .procname = "maximum_packet_length", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_paclen, .extra2 = &max_paclen }, { - .ctl_name = NET_AX25_PROTOCOL, .procname = "protocol", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_proto, .extra2 = &max_proto }, #ifdef CONFIG_AX25_DAMA_SLAVE { - .ctl_name = NET_AX25_DAMA_SLAVE_TIMEOUT, .procname = "dama_slave_timeout", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_ds_timeout, .extra2 = &max_ds_timeout }, #endif - { .ctl_name = 0 } /* that's all, folks! */ + { } /* that's all, folks! */ }; void ax25_register_sysctl(void) @@ -212,11 +184,9 @@ void ax25_register_sysctl(void) return; } ax25_table[n].child = ax25_dev->systable = child; - ax25_table[n].ctl_name = n + 1; ax25_table[n].procname = ax25_dev->dev->name; ax25_table[n].mode = 0555; - child[AX25_MAX_VALUES].ctl_name = 0; /* just in case... */ for (k = 0; k < AX25_MAX_VALUES; k++) child[k].data = &ax25_dev->values[k]; @@ -233,7 +203,7 @@ void ax25_unregister_sysctl(void) ctl_table *p; unregister_sysctl_table(ax25_table_header); - for (p = ax25_table; p->ctl_name; p++) + for (p = ax25_table; p->procname; p++) kfree(p->child); kfree(ax25_table); } diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index a16a2342f6bf..268e2e725888 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -1013,12 +1013,12 @@ static ctl_table brnf_table[] = { .mode = 0644, .proc_handler = brnf_sysctl_call_tables, }, - { .ctl_name = 0 } + { } }; static struct ctl_path brnf_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "bridge", .ctl_name = NET_BRIDGE, }, + { .procname = "net", }, + { .procname = "bridge", }, { } }; #endif diff --git a/net/core/neighbour.c b/net/core/neighbour.c index e587e6819698..2b54e6c6a7c8 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2566,21 +2566,18 @@ static struct neigh_sysctl_table { } neigh_sysctl_template __read_mostly = { .neigh_vars = { { - .ctl_name = NET_NEIGH_MCAST_SOLICIT, .procname = "mcast_solicit", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { - .ctl_name = NET_NEIGH_UCAST_SOLICIT, .procname = "ucast_solicit", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { - .ctl_name = NET_NEIGH_APP_SOLICIT, .procname = "app_solicit", .maxlen = sizeof(int), .mode = 0644, @@ -2593,38 +2590,30 @@ static struct neigh_sysctl_table { .proc_handler = proc_dointvec_userhz_jiffies, }, { - .ctl_name = NET_NEIGH_REACHABLE_TIME, .procname = "base_reachable_time", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_NEIGH_DELAY_PROBE_TIME, .procname = "delay_first_probe_time", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_NEIGH_GC_STALE_TIME, .procname = "gc_stale_time", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_NEIGH_UNRES_QLEN, .procname = "unres_qlen", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { - .ctl_name = NET_NEIGH_PROXY_QLEN, .procname = "proxy_qlen", .maxlen = sizeof(int), .mode = 0644, @@ -2649,45 +2638,36 @@ static struct neigh_sysctl_table { .proc_handler = proc_dointvec_userhz_jiffies, }, { - .ctl_name = NET_NEIGH_RETRANS_TIME_MS, .procname = "retrans_time_ms", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, - .strategy = sysctl_ms_jiffies, }, { - .ctl_name = NET_NEIGH_REACHABLE_TIME_MS, .procname = "base_reachable_time_ms", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, - .strategy = sysctl_ms_jiffies, }, { - .ctl_name = NET_NEIGH_GC_INTERVAL, .procname = "gc_interval", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_NEIGH_GC_THRESH1, .procname = "gc_thresh1", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { - .ctl_name = NET_NEIGH_GC_THRESH2, .procname = "gc_thresh2", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { - .ctl_name = NET_NEIGH_GC_THRESH3, .procname = "gc_thresh3", .maxlen = sizeof(int), .mode = 0644, @@ -2699,7 +2679,7 @@ static struct neigh_sysctl_table { int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, int p_id, int pdev_id, char *p_name, - proc_handler *handler, ctl_handler *strategy) + proc_handler *handler) { struct neigh_sysctl_table *t; const char *dev_name_source = NULL; @@ -2710,10 +2690,10 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, #define NEIGH_CTL_PATH_DEV 3 struct ctl_path neigh_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "proto", .ctl_name = 0, }, - { .procname = "neigh", .ctl_name = 0, }, - { .procname = "default", .ctl_name = NET_PROTO_CONF_DEFAULT, }, + { .procname = "net", }, + { .procname = "proto", }, + { .procname = "neigh", }, + { .procname = "default", }, { }, }; @@ -2738,7 +2718,6 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, if (dev) { dev_name_source = dev->name; - neigh_path[NEIGH_CTL_PATH_DEV].ctl_name = dev->ifindex; /* Terminate the table early */ memset(&t->neigh_vars[14], 0, sizeof(t->neigh_vars[14])); } else { @@ -2750,31 +2729,19 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, } - if (handler || strategy) { + if (handler) { /* RetransTime */ t->neigh_vars[3].proc_handler = handler; - t->neigh_vars[3].strategy = strategy; t->neigh_vars[3].extra1 = dev; - if (!strategy) - t->neigh_vars[3].ctl_name = CTL_UNNUMBERED; /* ReachableTime */ t->neigh_vars[4].proc_handler = handler; - t->neigh_vars[4].strategy = strategy; t->neigh_vars[4].extra1 = dev; - if (!strategy) - t->neigh_vars[4].ctl_name = CTL_UNNUMBERED; /* RetransTime (in milliseconds)*/ t->neigh_vars[12].proc_handler = handler; - t->neigh_vars[12].strategy = strategy; t->neigh_vars[12].extra1 = dev; - if (!strategy) - t->neigh_vars[12].ctl_name = CTL_UNNUMBERED; /* ReachableTime (in milliseconds) */ t->neigh_vars[13].proc_handler = handler; - t->neigh_vars[13].strategy = strategy; t->neigh_vars[13].extra1 = dev; - if (!strategy) - t->neigh_vars[13].ctl_name = CTL_UNNUMBERED; } t->dev_name = kstrdup(dev_name_source, GFP_KERNEL); @@ -2782,9 +2749,7 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, goto free; neigh_path[NEIGH_CTL_PATH_DEV].procname = t->dev_name; - neigh_path[NEIGH_CTL_PATH_NEIGH].ctl_name = pdev_id; neigh_path[NEIGH_CTL_PATH_PROTO].procname = p_name; - neigh_path[NEIGH_CTL_PATH_PROTO].ctl_name = p_id; t->sysctl_header = register_net_sysctl_table(neigh_parms_net(p), neigh_path, t->neigh_vars); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 6eb8d47cbf3a..6e79e96cb4f2 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -363,6 +363,7 @@ struct pktgen_dev { * device name (not when the inject is * started as it used to do.) */ + char odevname[32]; struct flow_state *flows; unsigned cflows; /* Concurrent flows (config) */ unsigned lflow; /* Flow length (config) */ @@ -426,7 +427,7 @@ static const char version[] = static int pktgen_remove_device(struct pktgen_thread *t, struct pktgen_dev *i); static int pktgen_add_device(struct pktgen_thread *t, const char *ifname); static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t, - const char *ifname); + const char *ifname, bool exact); static int pktgen_device_event(struct notifier_block *, unsigned long, void *); static void pktgen_run_all_threads(void); static void pktgen_reset_all_threads(void); @@ -528,7 +529,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v) seq_printf(seq, " frags: %d delay: %llu clone_skb: %d ifname: %s\n", pkt_dev->nfrags, (unsigned long long) pkt_dev->delay, - pkt_dev->clone_skb, pkt_dev->odev->name); + pkt_dev->clone_skb, pkt_dev->odevname); seq_printf(seq, " flows: %u flowlen: %u\n", pkt_dev->cflows, pkt_dev->lflow); @@ -1688,13 +1689,13 @@ static int pktgen_thread_show(struct seq_file *seq, void *v) if_lock(t); list_for_each_entry(pkt_dev, &t->if_list, list) if (pkt_dev->running) - seq_printf(seq, "%s ", pkt_dev->odev->name); + seq_printf(seq, "%s ", pkt_dev->odevname); seq_printf(seq, "\nStopped: "); list_for_each_entry(pkt_dev, &t->if_list, list) if (!pkt_dev->running) - seq_printf(seq, "%s ", pkt_dev->odev->name); + seq_printf(seq, "%s ", pkt_dev->odevname); if (t->result[0]) seq_printf(seq, "\nResult: %s\n", t->result); @@ -1817,9 +1818,10 @@ static struct pktgen_dev *__pktgen_NN_threads(const char *ifname, int remove) { struct pktgen_thread *t; struct pktgen_dev *pkt_dev = NULL; + bool exact = (remove == FIND); list_for_each_entry(t, &pktgen_threads, th_list) { - pkt_dev = pktgen_find_dev(t, ifname); + pkt_dev = pktgen_find_dev(t, ifname, exact); if (pkt_dev) { if (remove) { if_lock(t); @@ -1994,7 +1996,7 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) "queue_map_min (zero-based) (%d) exceeds valid range " "[0 - %d] for (%d) queues on %s, resetting\n", pkt_dev->queue_map_min, (ntxq ?: 1) - 1, ntxq, - pkt_dev->odev->name); + pkt_dev->odevname); pkt_dev->queue_map_min = ntxq - 1; } if (pkt_dev->queue_map_max >= ntxq) { @@ -2002,7 +2004,7 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) "queue_map_max (zero-based) (%d) exceeds valid range " "[0 - %d] for (%d) queues on %s, resetting\n", pkt_dev->queue_map_max, (ntxq ?: 1) - 1, ntxq, - pkt_dev->odev->name); + pkt_dev->odevname); pkt_dev->queue_map_max = ntxq - 1; } @@ -3262,7 +3264,7 @@ static int pktgen_stop_device(struct pktgen_dev *pkt_dev) if (!pkt_dev->running) { printk(KERN_WARNING "pktgen: interface: %s is already " - "stopped\n", pkt_dev->odev->name); + "stopped\n", pkt_dev->odevname); return -EINVAL; } @@ -3464,7 +3466,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) default: /* Drivers are not supposed to return other values! */ if (net_ratelimit()) pr_info("pktgen: %s xmit error: %d\n", - odev->name, ret); + pkt_dev->odevname, ret); pkt_dev->errors++; /* fallthru */ case NETDEV_TX_LOCKED: @@ -3566,13 +3568,18 @@ static int pktgen_thread_worker(void *arg) } static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t, - const char *ifname) + const char *ifname, bool exact) { struct pktgen_dev *p, *pkt_dev = NULL; - if_lock(t); + size_t len = strlen(ifname); + if_lock(t); list_for_each_entry(p, &t->if_list, list) - if (strncmp(p->odev->name, ifname, IFNAMSIZ) == 0) { + if (strncmp(p->odevname, ifname, len) == 0) { + if (p->odevname[len]) { + if (exact || p->odevname[len] != '@') + continue; + } pkt_dev = p; break; } @@ -3628,6 +3635,7 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) if (!pkt_dev) return -ENOMEM; + strcpy(pkt_dev->odevname, ifname); pkt_dev->flows = vmalloc(MAX_CFLOWS * sizeof(struct flow_state)); if (pkt_dev->flows == NULL) { kfree(pkt_dev); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 7db1de0497c6..267314664813 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -10,14 +10,15 @@ #include <linux/module.h> #include <linux/socket.h> #include <linux/netdevice.h> +#include <linux/ratelimit.h> #include <linux/init.h> + #include <net/ip.h> #include <net/sock.h> static struct ctl_table net_core_table[] = { #ifdef CONFIG_NET { - .ctl_name = NET_CORE_WMEM_MAX, .procname = "wmem_max", .data = &sysctl_wmem_max, .maxlen = sizeof(int), @@ -25,7 +26,6 @@ static struct ctl_table net_core_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_CORE_RMEM_MAX, .procname = "rmem_max", .data = &sysctl_rmem_max, .maxlen = sizeof(int), @@ -33,7 +33,6 @@ static struct ctl_table net_core_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_CORE_WMEM_DEFAULT, .procname = "wmem_default", .data = &sysctl_wmem_default, .maxlen = sizeof(int), @@ -41,7 +40,6 @@ static struct ctl_table net_core_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_CORE_RMEM_DEFAULT, .procname = "rmem_default", .data = &sysctl_rmem_default, .maxlen = sizeof(int), @@ -49,7 +47,6 @@ static struct ctl_table net_core_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_CORE_DEV_WEIGHT, .procname = "dev_weight", .data = &weight_p, .maxlen = sizeof(int), @@ -57,7 +54,6 @@ static struct ctl_table net_core_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_CORE_MAX_BACKLOG, .procname = "netdev_max_backlog", .data = &netdev_max_backlog, .maxlen = sizeof(int), @@ -65,16 +61,13 @@ static struct ctl_table net_core_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_CORE_MSG_COST, .procname = "message_cost", .data = &net_ratelimit_state.interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_CORE_MSG_BURST, .procname = "message_burst", .data = &net_ratelimit_state.burst, .maxlen = sizeof(int), @@ -82,7 +75,6 @@ static struct ctl_table net_core_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_CORE_OPTMEM_MAX, .procname = "optmem_max", .data = &sysctl_optmem_max, .maxlen = sizeof(int), @@ -91,7 +83,6 @@ static struct ctl_table net_core_table[] = { }, #endif /* CONFIG_NET */ { - .ctl_name = NET_CORE_BUDGET, .procname = "netdev_budget", .data = &netdev_budget, .maxlen = sizeof(int), @@ -99,31 +90,29 @@ static struct ctl_table net_core_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_CORE_WARNINGS, .procname = "warnings", .data = &net_msg_warn, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, - { .ctl_name = 0 } + { } }; static struct ctl_table netns_core_table[] = { { - .ctl_name = NET_CORE_SOMAXCONN, .procname = "somaxconn", .data = &init_net.core.sysctl_somaxconn, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, - { .ctl_name = 0 } + { } }; __net_initdata struct ctl_path net_core_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "core", .ctl_name = NET_CORE, }, + { .procname = "net", }, + { .procname = "core", }, { }, }; diff --git a/net/core/utils.c b/net/core/utils.c index 83221aee7084..838250241d26 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -24,6 +24,8 @@ #include <linux/types.h> #include <linux/percpu.h> #include <linux/init.h> +#include <linux/ratelimit.h> + #include <net/sock.h> #include <asm/byteorder.h> diff --git a/net/dccp/sysctl.c b/net/dccp/sysctl.c index a5a1856234e7..563943822e58 100644 --- a/net/dccp/sysctl.c +++ b/net/dccp/sysctl.c @@ -93,13 +93,13 @@ static struct ctl_table dccp_default_table[] = { .proc_handler = proc_dointvec_ms_jiffies, }, - { .ctl_name = 0, } + { } }; static struct ctl_path dccp_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "dccp", .ctl_name = NET_DCCP, }, - { .procname = "default", .ctl_name = NET_DCCP_DEFAULT, }, + { .procname = "net", }, + { .procname = "dccp", }, + { .procname = "default", }, { } }; diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index 6e1f085db06a..1b1daeb151f2 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -89,7 +89,6 @@ static struct dn_dev_parms dn_dev_list[] = { .t2 = 1, .t3 = 10, .name = "ethernet", - .ctl_name = NET_DECNET_CONF_ETHER, .up = dn_eth_up, .down = dn_eth_down, .timer3 = dn_send_brd_hello, @@ -101,7 +100,6 @@ static struct dn_dev_parms dn_dev_list[] = { .t2 = 1, .t3 = 10, .name = "ipgre", - .ctl_name = NET_DECNET_CONF_GRE, .timer3 = dn_send_brd_hello, }, #if 0 @@ -112,7 +110,6 @@ static struct dn_dev_parms dn_dev_list[] = { .t2 = 1, .t3 = 120, .name = "x25", - .ctl_name = NET_DECNET_CONF_X25, .timer3 = dn_send_ptp_hello, }, #endif @@ -124,7 +121,6 @@ static struct dn_dev_parms dn_dev_list[] = { .t2 = 1, .t3 = 10, .name = "ppp", - .ctl_name = NET_DECNET_CONF_PPP, .timer3 = dn_send_brd_hello, }, #endif @@ -135,7 +131,6 @@ static struct dn_dev_parms dn_dev_list[] = { .t2 = 1, .t3 = 120, .name = "ddcmp", - .ctl_name = NET_DECNET_CONF_DDCMP, .timer3 = dn_send_ptp_hello, }, { @@ -145,7 +140,6 @@ static struct dn_dev_parms dn_dev_list[] = { .t2 = 1, .t3 = 10, .name = "loopback", - .ctl_name = NET_DECNET_CONF_LOOPBACK, .timer3 = dn_send_brd_hello, } }; @@ -166,10 +160,6 @@ static int max_priority[] = { 127 }; /* From DECnet spec */ static int dn_forwarding_proc(ctl_table *, int, void __user *, size_t *, loff_t *); -static int dn_forwarding_sysctl(ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen); - static struct dn_dev_sysctl_table { struct ctl_table_header *sysctl_header; ctl_table dn_dev_vars[5]; @@ -177,44 +167,36 @@ static struct dn_dev_sysctl_table { NULL, { { - .ctl_name = NET_DECNET_CONF_DEV_FORWARDING, .procname = "forwarding", .data = (void *)DN_DEV_PARMS_OFFSET(forwarding), .maxlen = sizeof(int), .mode = 0644, .proc_handler = dn_forwarding_proc, - .strategy = dn_forwarding_sysctl, }, { - .ctl_name = NET_DECNET_CONF_DEV_PRIORITY, .procname = "priority", .data = (void *)DN_DEV_PARMS_OFFSET(priority), .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_priority, .extra2 = &max_priority }, { - .ctl_name = NET_DECNET_CONF_DEV_T2, .procname = "t2", .data = (void *)DN_DEV_PARMS_OFFSET(t2), .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_t2, .extra2 = &max_t2 }, { - .ctl_name = NET_DECNET_CONF_DEV_T3, .procname = "t3", .data = (void *)DN_DEV_PARMS_OFFSET(t3), .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_t3, .extra2 = &max_t3 }, @@ -230,9 +212,9 @@ static void dn_dev_sysctl_register(struct net_device *dev, struct dn_dev_parms * #define DN_CTL_PATH_DEV 3 struct ctl_path dn_ctl_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "decnet", .ctl_name = NET_DECNET, }, - { .procname = "conf", .ctl_name = NET_DECNET_CONF, }, + { .procname = "net", }, + { .procname = "decnet", }, + { .procname = "conf", }, { /* to be set */ }, { }, }; @@ -248,10 +230,8 @@ static void dn_dev_sysctl_register(struct net_device *dev, struct dn_dev_parms * if (dev) { dn_ctl_path[DN_CTL_PATH_DEV].procname = dev->name; - dn_ctl_path[DN_CTL_PATH_DEV].ctl_name = dev->ifindex; } else { dn_ctl_path[DN_CTL_PATH_DEV].procname = parms->name; - dn_ctl_path[DN_CTL_PATH_DEV].ctl_name = parms->ctl_name; } t->dn_dev_vars[0].extra1 = (void *)dev; @@ -317,44 +297,6 @@ static int dn_forwarding_proc(ctl_table *table, int write, #endif } -static int dn_forwarding_sysctl(ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ -#ifdef CONFIG_DECNET_ROUTER - struct net_device *dev = table->extra1; - struct dn_dev *dn_db; - int value; - - if (table->extra1 == NULL) - return -EINVAL; - - dn_db = dev->dn_ptr; - - if (newval && newlen) { - if (newlen != sizeof(int)) - return -EINVAL; - - if (get_user(value, (int __user *)newval)) - return -EFAULT; - if (value < 0) - return -EINVAL; - if (value > 2) - return -EINVAL; - - if (dn_db->parms.down) - dn_db->parms.down(dev); - dn_db->parms.forwarding = value; - if (dn_db->parms.up) - dn_db->parms.up(dev); - } - - return 0; -#else - return -EINVAL; -#endif -} - #else /* CONFIG_SYSCTL */ static void dn_dev_sysctl_unregister(struct dn_dev_parms *parms) { diff --git a/net/decnet/sysctl_net_decnet.c b/net/decnet/sysctl_net_decnet.c index 2036568beea9..be3eb8e23288 100644 --- a/net/decnet/sysctl_net_decnet.c +++ b/net/decnet/sysctl_net_decnet.c @@ -131,39 +131,6 @@ static int parse_addr(__le16 *addr, char *str) return 0; } - -static int dn_node_address_strategy(ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - size_t len; - __le16 addr; - - if (oldval && oldlenp) { - if (get_user(len, oldlenp)) - return -EFAULT; - if (len) { - if (len != sizeof(unsigned short)) - return -EINVAL; - if (put_user(decnet_address, (__le16 __user *)oldval)) - return -EFAULT; - } - } - if (newval && newlen) { - if (newlen != sizeof(unsigned short)) - return -EINVAL; - if (get_user(addr, (__le16 __user *)newval)) - return -EFAULT; - - dn_dev_devices_off(); - - decnet_address = addr; - - dn_dev_devices_on(); - } - return 0; -} - static int dn_node_address_handler(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) @@ -215,64 +182,6 @@ static int dn_node_address_handler(ctl_table *table, int write, return 0; } - -static int dn_def_dev_strategy(ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - size_t len; - struct net_device *dev; - char devname[17]; - size_t namel; - int rv = 0; - - devname[0] = 0; - - if (oldval && oldlenp) { - if (get_user(len, oldlenp)) - return -EFAULT; - if (len) { - dev = dn_dev_get_default(); - if (dev) { - strcpy(devname, dev->name); - dev_put(dev); - } - - namel = strlen(devname) + 1; - if (len > namel) len = namel; - - if (copy_to_user(oldval, devname, len)) - return -EFAULT; - - if (put_user(len, oldlenp)) - return -EFAULT; - } - } - - if (newval && newlen) { - if (newlen > 16) - return -E2BIG; - - if (copy_from_user(devname, newval, newlen)) - return -EFAULT; - - devname[newlen] = 0; - - dev = dev_get_by_name(&init_net, devname); - if (dev == NULL) - return -ENODEV; - - rv = -ENODEV; - if (dev->dn_ptr != NULL) - rv = dn_dev_set_default(dev, 1); - if (rv) - dev_put(dev); - } - - return rv; -} - - static int dn_def_dev_handler(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) @@ -338,138 +247,112 @@ static int dn_def_dev_handler(ctl_table *table, int write, static ctl_table dn_table[] = { { - .ctl_name = NET_DECNET_NODE_ADDRESS, .procname = "node_address", .maxlen = 7, .mode = 0644, .proc_handler = dn_node_address_handler, - .strategy = dn_node_address_strategy, }, { - .ctl_name = NET_DECNET_NODE_NAME, .procname = "node_name", .data = node_name, .maxlen = 7, .mode = 0644, .proc_handler = proc_dostring, - .strategy = sysctl_string, }, { - .ctl_name = NET_DECNET_DEFAULT_DEVICE, .procname = "default_device", .maxlen = 16, .mode = 0644, .proc_handler = dn_def_dev_handler, - .strategy = dn_def_dev_strategy, }, { - .ctl_name = NET_DECNET_TIME_WAIT, .procname = "time_wait", .data = &decnet_time_wait, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_decnet_time_wait, .extra2 = &max_decnet_time_wait }, { - .ctl_name = NET_DECNET_DN_COUNT, .procname = "dn_count", .data = &decnet_dn_count, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_state_count, .extra2 = &max_state_count }, { - .ctl_name = NET_DECNET_DI_COUNT, .procname = "di_count", .data = &decnet_di_count, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_state_count, .extra2 = &max_state_count }, { - .ctl_name = NET_DECNET_DR_COUNT, .procname = "dr_count", .data = &decnet_dr_count, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_state_count, .extra2 = &max_state_count }, { - .ctl_name = NET_DECNET_DST_GC_INTERVAL, .procname = "dst_gc_interval", .data = &decnet_dst_gc_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_decnet_dst_gc_interval, .extra2 = &max_decnet_dst_gc_interval }, { - .ctl_name = NET_DECNET_NO_FC_MAX_CWND, .procname = "no_fc_max_cwnd", .data = &decnet_no_fc_max_cwnd, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_decnet_no_fc_max_cwnd, .extra2 = &max_decnet_no_fc_max_cwnd }, { - .ctl_name = NET_DECNET_MEM, .procname = "decnet_mem", .data = &sysctl_decnet_mem, .maxlen = sizeof(sysctl_decnet_mem), .mode = 0644, .proc_handler = proc_dointvec, - .strategy = sysctl_intvec, }, { - .ctl_name = NET_DECNET_RMEM, .procname = "decnet_rmem", .data = &sysctl_decnet_rmem, .maxlen = sizeof(sysctl_decnet_rmem), .mode = 0644, .proc_handler = proc_dointvec, - .strategy = sysctl_intvec, }, { - .ctl_name = NET_DECNET_WMEM, .procname = "decnet_wmem", .data = &sysctl_decnet_wmem, .maxlen = sizeof(sysctl_decnet_wmem), .mode = 0644, .proc_handler = proc_dointvec, - .strategy = sysctl_intvec, }, { - .ctl_name = NET_DECNET_DEBUG_LEVEL, .procname = "debug", .data = &decnet_debug_level, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, - .strategy = sysctl_intvec, }, - {0} + { } }; static struct ctl_path dn_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "decnet", .ctl_name = NET_DECNET, }, + { .procname = "net", }, + { .procname = "decnet", }, { } }; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 4e80f336c0cf..c95cd93acf29 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1240,7 +1240,7 @@ void __init arp_init(void) arp_proc_init(); #ifdef CONFIG_SYSCTL neigh_sysctl_register(NULL, &arp_tbl.parms, NET_IPV4, - NET_IPV4_NEIGH, "ipv4", NULL, NULL); + NET_IPV4_NEIGH, "ipv4", NULL); #endif register_netdevice_notifier(&arp_netdev_notifier); } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 5df2f6a0b0f0..e049da8311b5 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1293,58 +1293,6 @@ static int devinet_conf_proc(ctl_table *ctl, int write, return ret; } -static int devinet_conf_sysctl(ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - struct ipv4_devconf *cnf; - struct net *net; - int *valp = table->data; - int new; - int i; - - if (!newval || !newlen) - return 0; - - if (newlen != sizeof(int)) - return -EINVAL; - - if (get_user(new, (int __user *)newval)) - return -EFAULT; - - if (new == *valp) - return 0; - - if (oldval && oldlenp) { - size_t len; - - if (get_user(len, oldlenp)) - return -EFAULT; - - if (len) { - if (len > table->maxlen) - len = table->maxlen; - if (copy_to_user(oldval, valp, len)) - return -EFAULT; - if (put_user(len, oldlenp)) - return -EFAULT; - } - } - - *valp = new; - - cnf = table->extra1; - net = table->extra2; - i = (int *)table->data - cnf->data; - - set_bit(i, cnf->state); - - if (cnf == net->ipv4.devconf_dflt) - devinet_copy_dflt_conf(net, i); - - return 1; -} - static int devinet_sysctl_forward(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) @@ -1390,47 +1338,28 @@ int ipv4_doint_and_flush(ctl_table *ctl, int write, return ret; } -int ipv4_doint_and_flush_strategy(ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - int ret = devinet_conf_sysctl(table, oldval, oldlenp, newval, newlen); - struct net *net = table->extra2; - - if (ret == 1) - rt_cache_flush(net, 0); - - return ret; -} - - -#define DEVINET_SYSCTL_ENTRY(attr, name, mval, proc, sysctl) \ +#define DEVINET_SYSCTL_ENTRY(attr, name, mval, proc) \ { \ - .ctl_name = NET_IPV4_CONF_ ## attr, \ .procname = name, \ .data = ipv4_devconf.data + \ NET_IPV4_CONF_ ## attr - 1, \ .maxlen = sizeof(int), \ .mode = mval, \ .proc_handler = proc, \ - .strategy = sysctl, \ .extra1 = &ipv4_devconf, \ } #define DEVINET_SYSCTL_RW_ENTRY(attr, name) \ - DEVINET_SYSCTL_ENTRY(attr, name, 0644, devinet_conf_proc, \ - devinet_conf_sysctl) + DEVINET_SYSCTL_ENTRY(attr, name, 0644, devinet_conf_proc) #define DEVINET_SYSCTL_RO_ENTRY(attr, name) \ - DEVINET_SYSCTL_ENTRY(attr, name, 0444, devinet_conf_proc, \ - devinet_conf_sysctl) + DEVINET_SYSCTL_ENTRY(attr, name, 0444, devinet_conf_proc) -#define DEVINET_SYSCTL_COMPLEX_ENTRY(attr, name, proc, sysctl) \ - DEVINET_SYSCTL_ENTRY(attr, name, 0644, proc, sysctl) +#define DEVINET_SYSCTL_COMPLEX_ENTRY(attr, name, proc) \ + DEVINET_SYSCTL_ENTRY(attr, name, 0644, proc) #define DEVINET_SYSCTL_FLUSHING_ENTRY(attr, name) \ - DEVINET_SYSCTL_COMPLEX_ENTRY(attr, name, ipv4_doint_and_flush, \ - ipv4_doint_and_flush_strategy) + DEVINET_SYSCTL_COMPLEX_ENTRY(attr, name, ipv4_doint_and_flush) static struct devinet_sysctl_table { struct ctl_table_header *sysctl_header; @@ -1439,8 +1368,7 @@ static struct devinet_sysctl_table { } devinet_sysctl = { .devinet_vars = { DEVINET_SYSCTL_COMPLEX_ENTRY(FORWARDING, "forwarding", - devinet_sysctl_forward, - devinet_conf_sysctl), + devinet_sysctl_forward), DEVINET_SYSCTL_RO_ENTRY(MC_FORWARDING, "mc_forwarding"), DEVINET_SYSCTL_RW_ENTRY(ACCEPT_REDIRECTS, "accept_redirects"), @@ -1471,7 +1399,7 @@ static struct devinet_sysctl_table { }; static int __devinet_sysctl_register(struct net *net, char *dev_name, - int ctl_name, struct ipv4_devconf *p) + struct ipv4_devconf *p) { int i; struct devinet_sysctl_table *t; @@ -1479,9 +1407,9 @@ static int __devinet_sysctl_register(struct net *net, char *dev_name, #define DEVINET_CTL_PATH_DEV 3 struct ctl_path devinet_ctl_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "ipv4", .ctl_name = NET_IPV4, }, - { .procname = "conf", .ctl_name = NET_IPV4_CONF, }, + { .procname = "net", }, + { .procname = "ipv4", }, + { .procname = "conf", }, { /* to be set */ }, { }, }; @@ -1506,7 +1434,6 @@ static int __devinet_sysctl_register(struct net *net, char *dev_name, goto free; devinet_ctl_path[DEVINET_CTL_PATH_DEV].procname = t->dev_name; - devinet_ctl_path[DEVINET_CTL_PATH_DEV].ctl_name = ctl_name; t->sysctl_header = register_net_sysctl_table(net, devinet_ctl_path, t->devinet_vars); @@ -1540,9 +1467,9 @@ static void __devinet_sysctl_unregister(struct ipv4_devconf *cnf) static void devinet_sysctl_register(struct in_device *idev) { neigh_sysctl_register(idev->dev, idev->arp_parms, NET_IPV4, - NET_IPV4_NEIGH, "ipv4", NULL, NULL); + NET_IPV4_NEIGH, "ipv4", NULL); __devinet_sysctl_register(dev_net(idev->dev), idev->dev->name, - idev->dev->ifindex, &idev->cnf); + &idev->cnf); } static void devinet_sysctl_unregister(struct in_device *idev) @@ -1553,14 +1480,12 @@ static void devinet_sysctl_unregister(struct in_device *idev) static struct ctl_table ctl_forward_entry[] = { { - .ctl_name = NET_IPV4_FORWARD, .procname = "ip_forward", .data = &ipv4_devconf.data[ NET_IPV4_CONF_FORWARDING - 1], .maxlen = sizeof(int), .mode = 0644, .proc_handler = devinet_sysctl_forward, - .strategy = devinet_conf_sysctl, .extra1 = &ipv4_devconf, .extra2 = &init_net, }, @@ -1568,8 +1493,8 @@ static struct ctl_table ctl_forward_entry[] = { }; static __net_initdata struct ctl_path net_ipv4_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "ipv4", .ctl_name = NET_IPV4, }, + { .procname = "net", }, + { .procname = "ipv4", }, { }, }; #endif @@ -1608,13 +1533,11 @@ static __net_init int devinet_init_net(struct net *net) } #ifdef CONFIG_SYSCTL - err = __devinet_sysctl_register(net, "all", - NET_PROTO_CONF_ALL, all); + err = __devinet_sysctl_register(net, "all", all); if (err < 0) goto err_reg_all; - err = __devinet_sysctl_register(net, "default", - NET_PROTO_CONF_DEFAULT, dflt); + err = __devinet_sysctl_register(net, "default", dflt); if (err < 0) goto err_reg_dflt; diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 575f9bd51ccd..301a389fa7fa 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -563,7 +563,7 @@ out_oversize: printk(KERN_INFO "Oversized IP packet from %pI4.\n", &qp->saddr); out_fail: - IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_REASMFAILS); + IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS); return err; } @@ -603,7 +603,6 @@ static int zero; static struct ctl_table ip4_frags_ns_ctl_table[] = { { - .ctl_name = NET_IPV4_IPFRAG_HIGH_THRESH, .procname = "ipfrag_high_thresh", .data = &init_net.ipv4.frags.high_thresh, .maxlen = sizeof(int), @@ -611,7 +610,6 @@ static struct ctl_table ip4_frags_ns_ctl_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_IPV4_IPFRAG_LOW_THRESH, .procname = "ipfrag_low_thresh", .data = &init_net.ipv4.frags.low_thresh, .maxlen = sizeof(int), @@ -619,26 +617,22 @@ static struct ctl_table ip4_frags_ns_ctl_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_IPV4_IPFRAG_TIME, .procname = "ipfrag_time", .data = &init_net.ipv4.frags.timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies }, { } }; static struct ctl_table ip4_frags_ctl_table[] = { { - .ctl_name = NET_IPV4_IPFRAG_SECRET_INTERVAL, .procname = "ipfrag_secret_interval", .data = &ip4_frags.secret_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies }, { .procname = "ipfrag_max_dist", diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 1725dc0ef688..db52c0cb0c11 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -248,9 +248,9 @@ module_exit(ipv4_netfilter_fini); #ifdef CONFIG_SYSCTL struct ctl_path nf_net_ipv4_netfilter_sysctl_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "ipv4", .ctl_name = NET_IPV4, }, - { .procname = "netfilter", .ctl_name = NET_IPV4_NETFILTER, }, + { .procname = "net", }, + { .procname = "ipv4", }, + { .procname = "netfilter", }, { } }; EXPORT_SYMBOL_GPL(nf_net_ipv4_netfilter_sysctl_path); diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c index c156db215987..c9f90e8c5191 100644 --- a/net/ipv4/netfilter/ip_queue.c +++ b/net/ipv4/netfilter/ip_queue.c @@ -516,14 +516,13 @@ static struct ctl_table_header *ipq_sysctl_header; static ctl_table ipq_table[] = { { - .ctl_name = NET_IPQ_QMAX, .procname = NET_IPQ_QMAX_NAME, .data = &queue_maxlen, .maxlen = sizeof(queue_maxlen), .mode = 0644, .proc_handler = proc_dointvec }, - { .ctl_name = 0 } + { } }; #endif diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index aa95bb82ee6c..092d68f916e6 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -195,7 +195,6 @@ static int log_invalid_proto_max = 255; static ctl_table ip_ct_sysctl_table[] = { { - .ctl_name = NET_IPV4_NF_CONNTRACK_MAX, .procname = "ip_conntrack_max", .data = &nf_conntrack_max, .maxlen = sizeof(int), @@ -203,7 +202,6 @@ static ctl_table ip_ct_sysctl_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV4_NF_CONNTRACK_COUNT, .procname = "ip_conntrack_count", .data = &init_net.ct.count, .maxlen = sizeof(int), @@ -211,7 +209,6 @@ static ctl_table ip_ct_sysctl_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV4_NF_CONNTRACK_BUCKETS, .procname = "ip_conntrack_buckets", .data = &nf_conntrack_htable_size, .maxlen = sizeof(unsigned int), @@ -219,7 +216,6 @@ static ctl_table ip_ct_sysctl_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV4_NF_CONNTRACK_CHECKSUM, .procname = "ip_conntrack_checksum", .data = &init_net.ct.sysctl_checksum, .maxlen = sizeof(int), @@ -227,19 +223,15 @@ static ctl_table ip_ct_sysctl_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV4_NF_CONNTRACK_LOG_INVALID, .procname = "ip_conntrack_log_invalid", .data = &init_net.ct.sysctl_log_invalid, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &log_invalid_proto_min, .extra2 = &log_invalid_proto_max, }, - { - .ctl_name = 0 - } + { } }; #endif /* CONFIG_SYSCTL && CONFIG_NF_CONNTRACK_PROC_COMPAT */ diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index d71ba7677344..9072058778b8 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -270,9 +270,7 @@ static struct ctl_table icmp_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { - .ctl_name = 0 - } + { } }; #ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT static struct ctl_table icmp_compat_sysctl_table[] = { @@ -283,9 +281,7 @@ static struct ctl_table icmp_compat_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { - .ctl_name = 0 - } + { } }; #endif /* CONFIG_NF_CONNTRACK_PROC_COMPAT */ #endif /* CONFIG_SYSCTL */ diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 5b1050a5d874..0d9f584a3811 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -3056,23 +3056,6 @@ static int ipv4_sysctl_rtcache_flush(ctl_table *__ctl, int write, return -EINVAL; } -static int ipv4_sysctl_rtcache_flush_strategy(ctl_table *table, - void __user *oldval, - size_t __user *oldlenp, - void __user *newval, - size_t newlen) -{ - int delay; - struct net *net; - if (newlen != sizeof(int)) - return -EINVAL; - if (get_user(delay, (int __user *)newval)) - return -EFAULT; - net = (struct net *)table->extra1; - rt_cache_flush(net, delay); - return 0; -} - static void rt_secret_reschedule(int old) { struct net *net; @@ -3117,23 +3100,8 @@ static int ipv4_sysctl_rt_secret_interval(ctl_table *ctl, int write, return ret; } -static int ipv4_sysctl_rt_secret_interval_strategy(ctl_table *table, - void __user *oldval, - size_t __user *oldlenp, - void __user *newval, - size_t newlen) -{ - int old = ip_rt_secret_interval; - int ret = sysctl_jiffies(table, oldval, oldlenp, newval, newlen); - - rt_secret_reschedule(old); - - return ret; -} - static ctl_table ipv4_route_table[] = { { - .ctl_name = NET_IPV4_ROUTE_GC_THRESH, .procname = "gc_thresh", .data = &ipv4_dst_ops.gc_thresh, .maxlen = sizeof(int), @@ -3141,7 +3109,6 @@ static ctl_table ipv4_route_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV4_ROUTE_MAX_SIZE, .procname = "max_size", .data = &ip_rt_max_size, .maxlen = sizeof(int), @@ -3151,43 +3118,34 @@ static ctl_table ipv4_route_table[] = { { /* Deprecated. Use gc_min_interval_ms */ - .ctl_name = NET_IPV4_ROUTE_GC_MIN_INTERVAL, .procname = "gc_min_interval", .data = &ip_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_IPV4_ROUTE_GC_MIN_INTERVAL_MS, .procname = "gc_min_interval_ms", .data = &ip_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, - .strategy = sysctl_ms_jiffies, }, { - .ctl_name = NET_IPV4_ROUTE_GC_TIMEOUT, .procname = "gc_timeout", .data = &ip_rt_gc_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_IPV4_ROUTE_GC_INTERVAL, .procname = "gc_interval", .data = &ip_rt_gc_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_IPV4_ROUTE_REDIRECT_LOAD, .procname = "redirect_load", .data = &ip_rt_redirect_load, .maxlen = sizeof(int), @@ -3195,7 +3153,6 @@ static ctl_table ipv4_route_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV4_ROUTE_REDIRECT_NUMBER, .procname = "redirect_number", .data = &ip_rt_redirect_number, .maxlen = sizeof(int), @@ -3203,7 +3160,6 @@ static ctl_table ipv4_route_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV4_ROUTE_REDIRECT_SILENCE, .procname = "redirect_silence", .data = &ip_rt_redirect_silence, .maxlen = sizeof(int), @@ -3211,7 +3167,6 @@ static ctl_table ipv4_route_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV4_ROUTE_ERROR_COST, .procname = "error_cost", .data = &ip_rt_error_cost, .maxlen = sizeof(int), @@ -3219,7 +3174,6 @@ static ctl_table ipv4_route_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV4_ROUTE_ERROR_BURST, .procname = "error_burst", .data = &ip_rt_error_burst, .maxlen = sizeof(int), @@ -3227,7 +3181,6 @@ static ctl_table ipv4_route_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV4_ROUTE_GC_ELASTICITY, .procname = "gc_elasticity", .data = &ip_rt_gc_elasticity, .maxlen = sizeof(int), @@ -3235,16 +3188,13 @@ static ctl_table ipv4_route_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV4_ROUTE_MTU_EXPIRES, .procname = "mtu_expires", .data = &ip_rt_mtu_expires, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_IPV4_ROUTE_MIN_PMTU, .procname = "min_pmtu", .data = &ip_rt_min_pmtu, .maxlen = sizeof(int), @@ -3252,7 +3202,6 @@ static ctl_table ipv4_route_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV4_ROUTE_MIN_ADVMSS, .procname = "min_adv_mss", .data = &ip_rt_min_advmss, .maxlen = sizeof(int), @@ -3260,50 +3209,46 @@ static ctl_table ipv4_route_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV4_ROUTE_SECRET_INTERVAL, .procname = "secret_interval", .data = &ip_rt_secret_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = ipv4_sysctl_rt_secret_interval, - .strategy = ipv4_sysctl_rt_secret_interval_strategy, }, - { .ctl_name = 0 } + { } }; static struct ctl_table empty[1]; static struct ctl_table ipv4_skeleton[] = { - { .procname = "route", .ctl_name = NET_IPV4_ROUTE, + { .procname = "route", .mode = 0555, .child = ipv4_route_table}, - { .procname = "neigh", .ctl_name = NET_IPV4_NEIGH, + { .procname = "neigh", .mode = 0555, .child = empty}, { } }; static __net_initdata struct ctl_path ipv4_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "ipv4", .ctl_name = NET_IPV4, }, + { .procname = "net", }, + { .procname = "ipv4", }, { }, }; static struct ctl_table ipv4_route_flush_table[] = { { - .ctl_name = NET_IPV4_ROUTE_FLUSH, .procname = "flush", .maxlen = sizeof(int), .mode = 0200, .proc_handler = ipv4_sysctl_rtcache_flush, - .strategy = ipv4_sysctl_rtcache_flush_strategy, }, - { .ctl_name = 0 }, + { }, }; static __net_initdata struct ctl_path ipv4_route_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "ipv4", .ctl_name = NET_IPV4, }, - { .procname = "route", .ctl_name = NET_IPV4_ROUTE, }, + { .procname = "net", }, + { .procname = "ipv4", }, + { .procname = "route", }, { }, }; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 2dcf04d9b005..300056732953 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -63,34 +63,6 @@ static int ipv4_local_port_range(ctl_table *table, int write, return ret; } -/* Validate changes from sysctl interface. */ -static int ipv4_sysctl_local_port_range(ctl_table *table, - void __user *oldval, - size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - int ret; - int range[2]; - ctl_table tmp = { - .data = &range, - .maxlen = sizeof(range), - .mode = table->mode, - .extra1 = &ip_local_port_range_min, - .extra2 = &ip_local_port_range_max, - }; - - inet_get_local_port_range(range, range + 1); - ret = sysctl_intvec(&tmp, oldval, oldlenp, newval, newlen); - if (ret == 0 && newval && newlen) { - if (range[1] < range[0]) - ret = -EINVAL; - else - set_local_port_range(range); - } - return ret; -} - - static int proc_tcp_congestion_control(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -109,25 +81,6 @@ static int proc_tcp_congestion_control(ctl_table *ctl, int write, return ret; } -static int sysctl_tcp_congestion_control(ctl_table *table, - void __user *oldval, - size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - char val[TCP_CA_NAME_MAX]; - ctl_table tbl = { - .data = val, - .maxlen = TCP_CA_NAME_MAX, - }; - int ret; - - tcp_get_default_congestion_control(val); - ret = sysctl_string(&tbl, oldval, oldlenp, newval, newlen); - if (ret == 1 && newval && newlen) - ret = tcp_set_default_congestion_control(val); - return ret; -} - static int proc_tcp_available_congestion_control(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, @@ -165,32 +118,8 @@ static int proc_allowed_congestion_control(ctl_table *ctl, return ret; } -static int strategy_allowed_congestion_control(ctl_table *table, - void __user *oldval, - size_t __user *oldlenp, - void __user *newval, - size_t newlen) -{ - ctl_table tbl = { .maxlen = TCP_CA_BUF_MAX }; - int ret; - - tbl.data = kmalloc(tbl.maxlen, GFP_USER); - if (!tbl.data) - return -ENOMEM; - - tcp_get_available_congestion_control(tbl.data, tbl.maxlen); - ret = sysctl_string(&tbl, oldval, oldlenp, newval, newlen); - if (ret == 1 && newval && newlen) - ret = tcp_set_allowed_congestion_control(tbl.data); - kfree(tbl.data); - - return ret; - -} - static struct ctl_table ipv4_table[] = { { - .ctl_name = NET_IPV4_TCP_TIMESTAMPS, .procname = "tcp_timestamps", .data = &sysctl_tcp_timestamps, .maxlen = sizeof(int), @@ -198,7 +127,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_IPV4_TCP_WINDOW_SCALING, .procname = "tcp_window_scaling", .data = &sysctl_tcp_window_scaling, .maxlen = sizeof(int), @@ -206,7 +134,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_IPV4_TCP_SACK, .procname = "tcp_sack", .data = &sysctl_tcp_sack, .maxlen = sizeof(int), @@ -214,7 +141,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_IPV4_TCP_RETRANS_COLLAPSE, .procname = "tcp_retrans_collapse", .data = &sysctl_tcp_retrans_collapse, .maxlen = sizeof(int), @@ -222,17 +148,14 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_IPV4_DEFAULT_TTL, .procname = "ip_default_ttl", .data = &sysctl_ip_default_ttl, .maxlen = sizeof(int), .mode = 0644, .proc_handler = ipv4_doint_and_flush, - .strategy = ipv4_doint_and_flush_strategy, .extra2 = &init_net, }, { - .ctl_name = NET_IPV4_NO_PMTU_DISC, .procname = "ip_no_pmtu_disc", .data = &ipv4_config.no_pmtu_disc, .maxlen = sizeof(int), @@ -240,7 +163,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_IPV4_NONLOCAL_BIND, .procname = "ip_nonlocal_bind", .data = &sysctl_ip_nonlocal_bind, .maxlen = sizeof(int), @@ -248,7 +170,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_IPV4_TCP_SYN_RETRIES, .procname = "tcp_syn_retries", .data = &sysctl_tcp_syn_retries, .maxlen = sizeof(int), @@ -256,7 +177,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_TCP_SYNACK_RETRIES, .procname = "tcp_synack_retries", .data = &sysctl_tcp_synack_retries, .maxlen = sizeof(int), @@ -264,7 +184,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_TCP_MAX_ORPHANS, .procname = "tcp_max_orphans", .data = &sysctl_tcp_max_orphans, .maxlen = sizeof(int), @@ -272,7 +191,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_TCP_MAX_TW_BUCKETS, .procname = "tcp_max_tw_buckets", .data = &tcp_death_row.sysctl_max_tw_buckets, .maxlen = sizeof(int), @@ -280,7 +198,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_IPV4_DYNADDR, .procname = "ip_dynaddr", .data = &sysctl_ip_dynaddr, .maxlen = sizeof(int), @@ -288,16 +205,13 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_IPV4_TCP_KEEPALIVE_TIME, .procname = "tcp_keepalive_time", .data = &sysctl_tcp_keepalive_time, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies }, { - .ctl_name = NET_IPV4_TCP_KEEPALIVE_PROBES, .procname = "tcp_keepalive_probes", .data = &sysctl_tcp_keepalive_probes, .maxlen = sizeof(int), @@ -305,26 +219,21 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_IPV4_TCP_KEEPALIVE_INTVL, .procname = "tcp_keepalive_intvl", .data = &sysctl_tcp_keepalive_intvl, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies }, { - .ctl_name = NET_IPV4_TCP_RETRIES1, .procname = "tcp_retries1", .data = &sysctl_tcp_retries1, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra2 = &tcp_retr1_max }, { - .ctl_name = NET_IPV4_TCP_RETRIES2, .procname = "tcp_retries2", .data = &sysctl_tcp_retries2, .maxlen = sizeof(int), @@ -332,17 +241,14 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_IPV4_TCP_FIN_TIMEOUT, .procname = "tcp_fin_timeout", .data = &sysctl_tcp_fin_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies }, #ifdef CONFIG_SYN_COOKIES { - .ctl_name = NET_TCP_SYNCOOKIES, .procname = "tcp_syncookies", .data = &sysctl_tcp_syncookies, .maxlen = sizeof(int), @@ -351,7 +257,6 @@ static struct ctl_table ipv4_table[] = { }, #endif { - .ctl_name = NET_TCP_TW_RECYCLE, .procname = "tcp_tw_recycle", .data = &tcp_death_row.sysctl_tw_recycle, .maxlen = sizeof(int), @@ -359,7 +264,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_TCP_ABORT_ON_OVERFLOW, .procname = "tcp_abort_on_overflow", .data = &sysctl_tcp_abort_on_overflow, .maxlen = sizeof(int), @@ -367,7 +271,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_TCP_STDURG, .procname = "tcp_stdurg", .data = &sysctl_tcp_stdurg, .maxlen = sizeof(int), @@ -375,7 +278,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_TCP_RFC1337, .procname = "tcp_rfc1337", .data = &sysctl_tcp_rfc1337, .maxlen = sizeof(int), @@ -383,7 +285,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_TCP_MAX_SYN_BACKLOG, .procname = "tcp_max_syn_backlog", .data = &sysctl_max_syn_backlog, .maxlen = sizeof(int), @@ -391,17 +292,14 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_IPV4_LOCAL_PORT_RANGE, .procname = "ip_local_port_range", .data = &sysctl_local_ports.range, .maxlen = sizeof(sysctl_local_ports.range), .mode = 0644, .proc_handler = ipv4_local_port_range, - .strategy = ipv4_sysctl_local_port_range, }, #ifdef CONFIG_IP_MULTICAST { - .ctl_name = NET_IPV4_IGMP_MAX_MEMBERSHIPS, .procname = "igmp_max_memberships", .data = &sysctl_igmp_max_memberships, .maxlen = sizeof(int), @@ -411,7 +309,6 @@ static struct ctl_table ipv4_table[] = { #endif { - .ctl_name = NET_IPV4_IGMP_MAX_MSF, .procname = "igmp_max_msf", .data = &sysctl_igmp_max_msf, .maxlen = sizeof(int), @@ -419,7 +316,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_IPV4_INET_PEER_THRESHOLD, .procname = "inet_peer_threshold", .data = &inet_peer_threshold, .maxlen = sizeof(int), @@ -427,43 +323,34 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_IPV4_INET_PEER_MINTTL, .procname = "inet_peer_minttl", .data = &inet_peer_minttl, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies }, { - .ctl_name = NET_IPV4_INET_PEER_MAXTTL, .procname = "inet_peer_maxttl", .data = &inet_peer_maxttl, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies }, { - .ctl_name = NET_IPV4_INET_PEER_GC_MINTIME, .procname = "inet_peer_gc_mintime", .data = &inet_peer_gc_mintime, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies }, { - .ctl_name = NET_IPV4_INET_PEER_GC_MAXTIME, .procname = "inet_peer_gc_maxtime", .data = &inet_peer_gc_maxtime, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies }, { - .ctl_name = NET_TCP_ORPHAN_RETRIES, .procname = "tcp_orphan_retries", .data = &sysctl_tcp_orphan_retries, .maxlen = sizeof(int), @@ -471,7 +358,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_TCP_FACK, .procname = "tcp_fack", .data = &sysctl_tcp_fack, .maxlen = sizeof(int), @@ -479,7 +365,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_TCP_REORDERING, .procname = "tcp_reordering", .data = &sysctl_tcp_reordering, .maxlen = sizeof(int), @@ -487,7 +372,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_TCP_ECN, .procname = "tcp_ecn", .data = &sysctl_tcp_ecn, .maxlen = sizeof(int), @@ -495,7 +379,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_TCP_DSACK, .procname = "tcp_dsack", .data = &sysctl_tcp_dsack, .maxlen = sizeof(int), @@ -503,7 +386,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_TCP_MEM, .procname = "tcp_mem", .data = &sysctl_tcp_mem, .maxlen = sizeof(sysctl_tcp_mem), @@ -511,7 +393,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_TCP_WMEM, .procname = "tcp_wmem", .data = &sysctl_tcp_wmem, .maxlen = sizeof(sysctl_tcp_wmem), @@ -519,7 +400,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_TCP_RMEM, .procname = "tcp_rmem", .data = &sysctl_tcp_rmem, .maxlen = sizeof(sysctl_tcp_rmem), @@ -527,7 +407,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_TCP_APP_WIN, .procname = "tcp_app_win", .data = &sysctl_tcp_app_win, .maxlen = sizeof(int), @@ -535,7 +414,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_TCP_ADV_WIN_SCALE, .procname = "tcp_adv_win_scale", .data = &sysctl_tcp_adv_win_scale, .maxlen = sizeof(int), @@ -543,7 +421,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_TCP_TW_REUSE, .procname = "tcp_tw_reuse", .data = &sysctl_tcp_tw_reuse, .maxlen = sizeof(int), @@ -551,7 +428,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_TCP_FRTO, .procname = "tcp_frto", .data = &sysctl_tcp_frto, .maxlen = sizeof(int), @@ -559,7 +435,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_TCP_FRTO_RESPONSE, .procname = "tcp_frto_response", .data = &sysctl_tcp_frto_response, .maxlen = sizeof(int), @@ -567,7 +442,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_TCP_LOW_LATENCY, .procname = "tcp_low_latency", .data = &sysctl_tcp_low_latency, .maxlen = sizeof(int), @@ -575,7 +449,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_TCP_NO_METRICS_SAVE, .procname = "tcp_no_metrics_save", .data = &sysctl_tcp_nometrics_save, .maxlen = sizeof(int), @@ -583,7 +456,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_TCP_MODERATE_RCVBUF, .procname = "tcp_moderate_rcvbuf", .data = &sysctl_tcp_moderate_rcvbuf, .maxlen = sizeof(int), @@ -591,7 +463,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_TCP_TSO_WIN_DIVISOR, .procname = "tcp_tso_win_divisor", .data = &sysctl_tcp_tso_win_divisor, .maxlen = sizeof(int), @@ -599,15 +470,12 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_TCP_CONG_CONTROL, .procname = "tcp_congestion_control", .mode = 0644, .maxlen = TCP_CA_NAME_MAX, .proc_handler = proc_tcp_congestion_control, - .strategy = sysctl_tcp_congestion_control, }, { - .ctl_name = NET_TCP_ABC, .procname = "tcp_abc", .data = &sysctl_tcp_abc, .maxlen = sizeof(int), @@ -615,7 +483,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_TCP_MTU_PROBING, .procname = "tcp_mtu_probing", .data = &sysctl_tcp_mtu_probing, .maxlen = sizeof(int), @@ -623,7 +490,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_TCP_BASE_MSS, .procname = "tcp_base_mss", .data = &sysctl_tcp_base_mss, .maxlen = sizeof(int), @@ -631,7 +497,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV4_TCP_WORKAROUND_SIGNED_WINDOWS, .procname = "tcp_workaround_signed_windows", .data = &sysctl_tcp_workaround_signed_windows, .maxlen = sizeof(int), @@ -640,7 +505,6 @@ static struct ctl_table ipv4_table[] = { }, #ifdef CONFIG_NET_DMA { - .ctl_name = NET_TCP_DMA_COPYBREAK, .procname = "tcp_dma_copybreak", .data = &sysctl_tcp_dma_copybreak, .maxlen = sizeof(int), @@ -649,7 +513,6 @@ static struct ctl_table ipv4_table[] = { }, #endif { - .ctl_name = NET_TCP_SLOW_START_AFTER_IDLE, .procname = "tcp_slow_start_after_idle", .data = &sysctl_tcp_slow_start_after_idle, .maxlen = sizeof(int), @@ -658,7 +521,6 @@ static struct ctl_table ipv4_table[] = { }, #ifdef CONFIG_NETLABEL { - .ctl_name = NET_CIPSOV4_CACHE_ENABLE, .procname = "cipso_cache_enable", .data = &cipso_v4_cache_enabled, .maxlen = sizeof(int), @@ -666,7 +528,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_CIPSOV4_CACHE_BUCKET_SIZE, .procname = "cipso_cache_bucket_size", .data = &cipso_v4_cache_bucketsize, .maxlen = sizeof(int), @@ -674,7 +535,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_CIPSOV4_RBM_OPTFMT, .procname = "cipso_rbm_optfmt", .data = &cipso_v4_rbm_optfmt, .maxlen = sizeof(int), @@ -682,7 +542,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_CIPSOV4_RBM_STRICTVALID, .procname = "cipso_rbm_strictvalid", .data = &cipso_v4_rbm_strictvalid, .maxlen = sizeof(int), @@ -697,15 +556,12 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_tcp_available_congestion_control, }, { - .ctl_name = NET_TCP_ALLOWED_CONG_CONTROL, .procname = "tcp_allowed_congestion_control", .maxlen = TCP_CA_BUF_MAX, .mode = 0644, .proc_handler = proc_allowed_congestion_control, - .strategy = strategy_allowed_congestion_control, }, { - .ctl_name = NET_TCP_MAX_SSTHRESH, .procname = "tcp_max_ssthresh", .data = &sysctl_tcp_max_ssthresh, .maxlen = sizeof(int), @@ -713,41 +569,34 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "udp_mem", .data = &sysctl_udp_mem, .maxlen = sizeof(sysctl_udp_mem), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &zero }, { - .ctl_name = CTL_UNNUMBERED, .procname = "udp_rmem_min", .data = &sysctl_udp_rmem_min, .maxlen = sizeof(sysctl_udp_rmem_min), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &zero }, { - .ctl_name = CTL_UNNUMBERED, .procname = "udp_wmem_min", .data = &sysctl_udp_wmem_min, .maxlen = sizeof(sysctl_udp_wmem_min), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &zero }, - { .ctl_name = 0 } + { } }; static struct ctl_table ipv4_net_table[] = { { - .ctl_name = NET_IPV4_ICMP_ECHO_IGNORE_ALL, .procname = "icmp_echo_ignore_all", .data = &init_net.ipv4.sysctl_icmp_echo_ignore_all, .maxlen = sizeof(int), @@ -755,7 +604,6 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_IPV4_ICMP_ECHO_IGNORE_BROADCASTS, .procname = "icmp_echo_ignore_broadcasts", .data = &init_net.ipv4.sysctl_icmp_echo_ignore_broadcasts, .maxlen = sizeof(int), @@ -763,7 +611,6 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_IPV4_ICMP_IGNORE_BOGUS_ERROR_RESPONSES, .procname = "icmp_ignore_bogus_error_responses", .data = &init_net.ipv4.sysctl_icmp_ignore_bogus_error_responses, .maxlen = sizeof(int), @@ -771,7 +618,6 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_IPV4_ICMP_ERRORS_USE_INBOUND_IFADDR, .procname = "icmp_errors_use_inbound_ifaddr", .data = &init_net.ipv4.sysctl_icmp_errors_use_inbound_ifaddr, .maxlen = sizeof(int), @@ -779,16 +625,13 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_IPV4_ICMP_RATELIMIT, .procname = "icmp_ratelimit", .data = &init_net.ipv4.sysctl_icmp_ratelimit, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, - .strategy = sysctl_ms_jiffies }, { - .ctl_name = NET_IPV4_ICMP_RATEMASK, .procname = "icmp_ratemask", .data = &init_net.ipv4.sysctl_icmp_ratemask, .maxlen = sizeof(int), @@ -796,7 +639,6 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = CTL_UNNUMBERED, .procname = "rt_cache_rebuild_count", .data = &init_net.ipv4.sysctl_rt_cache_rebuild_count, .maxlen = sizeof(int), @@ -807,8 +649,8 @@ static struct ctl_table ipv4_net_table[] = { }; struct ctl_path net_ipv4_ctl_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "ipv4", .ctl_name = NET_IPV4, }, + { .procname = "net", }, + { .procname = "ipv4", }, { }, }; EXPORT_SYMBOL_GPL(net_ipv4_ctl_path); diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 74fb2eb833ec..8c08a28d8f83 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -267,7 +267,6 @@ static struct xfrm_policy_afinfo xfrm4_policy_afinfo = { #ifdef CONFIG_SYSCTL static struct ctl_table xfrm4_policy_table[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "xfrm4_gc_thresh", .data = &xfrm4_dst_ops.gc_thresh, .maxlen = sizeof(int), diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 1fd0a3d775d2..f918399c985c 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -4000,41 +4000,6 @@ int addrconf_sysctl_forward(ctl_table *ctl, int write, return ret; } -static int addrconf_sysctl_forward_strategy(ctl_table *table, - void __user *oldval, - size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - int *valp = table->data; - int val = *valp; - int new; - - if (!newval || !newlen) - return 0; - if (newlen != sizeof(int)) - return -EINVAL; - if (get_user(new, (int __user *)newval)) - return -EFAULT; - if (new == *valp) - return 0; - if (oldval && oldlenp) { - size_t len; - if (get_user(len, oldlenp)) - return -EFAULT; - if (len) { - if (len > table->maxlen) - len = table->maxlen; - if (copy_to_user(oldval, valp, len)) - return -EFAULT; - if (put_user(len, oldlenp)) - return -EFAULT; - } - } - - *valp = new; - return addrconf_fixup_forwarding(table, valp, val); -} - static void dev_disable_change(struct inet6_dev *idev) { if (!idev || !idev->dev) @@ -4113,16 +4078,13 @@ static struct addrconf_sysctl_table .sysctl_header = NULL, .addrconf_vars = { { - .ctl_name = NET_IPV6_FORWARDING, .procname = "forwarding", .data = &ipv6_devconf.forwarding, .maxlen = sizeof(int), .mode = 0644, .proc_handler = addrconf_sysctl_forward, - .strategy = addrconf_sysctl_forward_strategy, }, { - .ctl_name = NET_IPV6_HOP_LIMIT, .procname = "hop_limit", .data = &ipv6_devconf.hop_limit, .maxlen = sizeof(int), @@ -4130,7 +4092,6 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_MTU, .procname = "mtu", .data = &ipv6_devconf.mtu6, .maxlen = sizeof(int), @@ -4138,7 +4099,6 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_ACCEPT_RA, .procname = "accept_ra", .data = &ipv6_devconf.accept_ra, .maxlen = sizeof(int), @@ -4146,7 +4106,6 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_ACCEPT_REDIRECTS, .procname = "accept_redirects", .data = &ipv6_devconf.accept_redirects, .maxlen = sizeof(int), @@ -4154,7 +4113,6 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_AUTOCONF, .procname = "autoconf", .data = &ipv6_devconf.autoconf, .maxlen = sizeof(int), @@ -4162,7 +4120,6 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_DAD_TRANSMITS, .procname = "dad_transmits", .data = &ipv6_devconf.dad_transmits, .maxlen = sizeof(int), @@ -4170,7 +4127,6 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_RTR_SOLICITS, .procname = "router_solicitations", .data = &ipv6_devconf.rtr_solicits, .maxlen = sizeof(int), @@ -4178,25 +4134,20 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_RTR_SOLICIT_INTERVAL, .procname = "router_solicitation_interval", .data = &ipv6_devconf.rtr_solicit_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_IPV6_RTR_SOLICIT_DELAY, .procname = "router_solicitation_delay", .data = &ipv6_devconf.rtr_solicit_delay, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_IPV6_FORCE_MLD_VERSION, .procname = "force_mld_version", .data = &ipv6_devconf.force_mld_version, .maxlen = sizeof(int), @@ -4205,7 +4156,6 @@ static struct addrconf_sysctl_table }, #ifdef CONFIG_IPV6_PRIVACY { - .ctl_name = NET_IPV6_USE_TEMPADDR, .procname = "use_tempaddr", .data = &ipv6_devconf.use_tempaddr, .maxlen = sizeof(int), @@ -4213,7 +4163,6 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_TEMP_VALID_LFT, .procname = "temp_valid_lft", .data = &ipv6_devconf.temp_valid_lft, .maxlen = sizeof(int), @@ -4221,7 +4170,6 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_TEMP_PREFERED_LFT, .procname = "temp_prefered_lft", .data = &ipv6_devconf.temp_prefered_lft, .maxlen = sizeof(int), @@ -4229,7 +4177,6 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_REGEN_MAX_RETRY, .procname = "regen_max_retry", .data = &ipv6_devconf.regen_max_retry, .maxlen = sizeof(int), @@ -4237,7 +4184,6 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_MAX_DESYNC_FACTOR, .procname = "max_desync_factor", .data = &ipv6_devconf.max_desync_factor, .maxlen = sizeof(int), @@ -4246,7 +4192,6 @@ static struct addrconf_sysctl_table }, #endif { - .ctl_name = NET_IPV6_MAX_ADDRESSES, .procname = "max_addresses", .data = &ipv6_devconf.max_addresses, .maxlen = sizeof(int), @@ -4254,7 +4199,6 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_ACCEPT_RA_DEFRTR, .procname = "accept_ra_defrtr", .data = &ipv6_devconf.accept_ra_defrtr, .maxlen = sizeof(int), @@ -4262,7 +4206,6 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_ACCEPT_RA_PINFO, .procname = "accept_ra_pinfo", .data = &ipv6_devconf.accept_ra_pinfo, .maxlen = sizeof(int), @@ -4271,7 +4214,6 @@ static struct addrconf_sysctl_table }, #ifdef CONFIG_IPV6_ROUTER_PREF { - .ctl_name = NET_IPV6_ACCEPT_RA_RTR_PREF, .procname = "accept_ra_rtr_pref", .data = &ipv6_devconf.accept_ra_rtr_pref, .maxlen = sizeof(int), @@ -4279,17 +4221,14 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_RTR_PROBE_INTERVAL, .procname = "router_probe_interval", .data = &ipv6_devconf.rtr_probe_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, #ifdef CONFIG_IPV6_ROUTE_INFO { - .ctl_name = NET_IPV6_ACCEPT_RA_RT_INFO_MAX_PLEN, .procname = "accept_ra_rt_info_max_plen", .data = &ipv6_devconf.accept_ra_rt_info_max_plen, .maxlen = sizeof(int), @@ -4299,7 +4238,6 @@ static struct addrconf_sysctl_table #endif #endif { - .ctl_name = NET_IPV6_PROXY_NDP, .procname = "proxy_ndp", .data = &ipv6_devconf.proxy_ndp, .maxlen = sizeof(int), @@ -4307,7 +4245,6 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_ACCEPT_SOURCE_ROUTE, .procname = "accept_source_route", .data = &ipv6_devconf.accept_source_route, .maxlen = sizeof(int), @@ -4316,7 +4253,6 @@ static struct addrconf_sysctl_table }, #ifdef CONFIG_IPV6_OPTIMISTIC_DAD { - .ctl_name = CTL_UNNUMBERED, .procname = "optimistic_dad", .data = &ipv6_devconf.optimistic_dad, .maxlen = sizeof(int), @@ -4327,7 +4263,6 @@ static struct addrconf_sysctl_table #endif #ifdef CONFIG_IPV6_MROUTE { - .ctl_name = CTL_UNNUMBERED, .procname = "mc_forwarding", .data = &ipv6_devconf.mc_forwarding, .maxlen = sizeof(int), @@ -4336,16 +4271,13 @@ static struct addrconf_sysctl_table }, #endif { - .ctl_name = CTL_UNNUMBERED, .procname = "disable_ipv6", .data = &ipv6_devconf.disable_ipv6, .maxlen = sizeof(int), .mode = 0644, .proc_handler = addrconf_sysctl_disable, - .strategy = sysctl_intvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "accept_dad", .data = &ipv6_devconf.accept_dad, .maxlen = sizeof(int), @@ -4353,13 +4285,13 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .ctl_name = 0, /* sentinel */ + /* sentinel */ } }, }; static int __addrconf_sysctl_register(struct net *net, char *dev_name, - int ctl_name, struct inet6_dev *idev, struct ipv6_devconf *p) + struct inet6_dev *idev, struct ipv6_devconf *p) { int i; struct addrconf_sysctl_table *t; @@ -4367,9 +4299,9 @@ static int __addrconf_sysctl_register(struct net *net, char *dev_name, #define ADDRCONF_CTL_PATH_DEV 3 struct ctl_path addrconf_ctl_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "ipv6", .ctl_name = NET_IPV6, }, - { .procname = "conf", .ctl_name = NET_IPV6_CONF, }, + { .procname = "net", }, + { .procname = "ipv6", }, + { .procname = "conf", }, { /* to be set */ }, { }, }; @@ -4395,7 +4327,6 @@ static int __addrconf_sysctl_register(struct net *net, char *dev_name, goto free; addrconf_ctl_path[ADDRCONF_CTL_PATH_DEV].procname = t->dev_name; - addrconf_ctl_path[ADDRCONF_CTL_PATH_DEV].ctl_name = ctl_name; t->sysctl_header = register_net_sysctl_table(net, addrconf_ctl_path, t->addrconf_vars); @@ -4431,10 +4362,9 @@ static void addrconf_sysctl_register(struct inet6_dev *idev) { neigh_sysctl_register(idev->dev, idev->nd_parms, NET_IPV6, NET_IPV6_NEIGH, "ipv6", - &ndisc_ifinfo_sysctl_change, - ndisc_ifinfo_sysctl_strategy); + &ndisc_ifinfo_sysctl_change); __addrconf_sysctl_register(dev_net(idev->dev), idev->dev->name, - idev->dev->ifindex, idev, &idev->cnf); + idev, &idev->cnf); } static void addrconf_sysctl_unregister(struct inet6_dev *idev) @@ -4473,13 +4403,11 @@ static int addrconf_init_net(struct net *net) net->ipv6.devconf_dflt = dflt; #ifdef CONFIG_SYSCTL - err = __addrconf_sysctl_register(net, "all", NET_PROTO_CONF_ALL, - NULL, all); + err = __addrconf_sysctl_register(net, "all", NULL, all); if (err < 0) goto err_reg_all; - err = __addrconf_sysctl_register(net, "default", NET_PROTO_CONF_DEFAULT, - NULL, dflt); + err = __addrconf_sysctl_register(net, "default", NULL, dflt); if (err < 0) goto err_reg_dflt; #endif diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index f23ebbec0631..4ae661bc3677 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -942,15 +942,13 @@ EXPORT_SYMBOL(icmpv6_err_convert); #ifdef CONFIG_SYSCTL ctl_table ipv6_icmp_table_template[] = { { - .ctl_name = NET_IPV6_ICMP_RATELIMIT, .procname = "ratelimit", .data = &init_net.ipv6.sysctl.icmpv6_time, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, - .strategy = sysctl_ms_jiffies }, - { .ctl_name = 0 }, + { }, }; struct ctl_table *ipv6_icmp_sysctl_init(struct net *net) diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index f74e4e2cdd06..3d0520e455d8 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1768,42 +1768,6 @@ int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, void __user *bu return ret; } -int ndisc_ifinfo_sysctl_strategy(ctl_table *ctl, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - struct net_device *dev = ctl->extra1; - struct inet6_dev *idev; - int ret; - - if (ctl->ctl_name == NET_NEIGH_RETRANS_TIME || - ctl->ctl_name == NET_NEIGH_REACHABLE_TIME) - ndisc_warn_deprecated_sysctl(ctl, "procfs", dev ? dev->name : "default"); - - switch (ctl->ctl_name) { - case NET_NEIGH_REACHABLE_TIME: - ret = sysctl_jiffies(ctl, oldval, oldlenp, newval, newlen); - break; - case NET_NEIGH_RETRANS_TIME_MS: - case NET_NEIGH_REACHABLE_TIME_MS: - ret = sysctl_ms_jiffies(ctl, oldval, oldlenp, newval, newlen); - break; - default: - ret = 0; - } - - if (newval && newlen && ret > 0 && - dev && (idev = in6_dev_get(dev)) != NULL) { - if (ctl->ctl_name == NET_NEIGH_REACHABLE_TIME || - ctl->ctl_name == NET_NEIGH_REACHABLE_TIME_MS) - idev->nd_parms->reachable_time = neigh_rand_reach_time(idev->nd_parms->base_reachable_time); - idev->tstamp = jiffies; - inet6_ifinfo_notify(RTM_NEWLINK, idev); - in6_dev_put(idev); - } - - return ret; -} #endif @@ -1857,8 +1821,7 @@ int __init ndisc_init(void) #ifdef CONFIG_SYSCTL err = neigh_sysctl_register(NULL, &nd_tbl.parms, NET_IPV6, NET_IPV6_NEIGH, "ipv6", - &ndisc_ifinfo_sysctl_change, - &ndisc_ifinfo_sysctl_strategy); + &ndisc_ifinfo_sysctl_change); if (err) goto out_unregister_pernet; #endif diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c index 1cf3f0c6a959..14e52aa624c2 100644 --- a/net/ipv6/netfilter/ip6_queue.c +++ b/net/ipv6/netfilter/ip6_queue.c @@ -36,7 +36,6 @@ #define IPQ_QMAX_DEFAULT 1024 #define IPQ_PROC_FS_NAME "ip6_queue" -#define NET_IPQ_QMAX 2088 #define NET_IPQ_QMAX_NAME "ip6_queue_maxlen" typedef int (*ipq_cmpfn)(struct nf_queue_entry *, unsigned long); @@ -518,14 +517,13 @@ static struct ctl_table_header *ipq_sysctl_header; static ctl_table ipq_table[] = { { - .ctl_name = NET_IPQ_QMAX, .procname = NET_IPQ_QMAX_NAME, .data = &queue_maxlen, .maxlen = sizeof(queue_maxlen), .mode = 0644, .proc_handler = proc_dointvec }, - { .ctl_name = 0 } + { } }; #endif diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index 642dcb127bab..2acadc8c7883 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -277,9 +277,7 @@ static struct ctl_table icmpv6_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { - .ctl_name = 0 - } + { } }; #endif /* CONFIG_SYSCTL */ diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index f3aba255ad9f..e0b9424fa1b2 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -83,7 +83,6 @@ struct ctl_table nf_ct_ipv6_sysctl_table[] = { .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = NET_NF_CONNTRACK_FRAG6_LOW_THRESH, .procname = "nf_conntrack_frag6_low_thresh", .data = &nf_init_frags.low_thresh, .maxlen = sizeof(unsigned int), @@ -91,14 +90,13 @@ struct ctl_table nf_ct_ipv6_sysctl_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_NF_CONNTRACK_FRAG6_HIGH_THRESH, .procname = "nf_conntrack_frag6_high_thresh", .data = &nf_init_frags.high_thresh, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec, }, - { .ctl_name = 0 } + { } }; #endif diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index da5bd0ed83df..2499e9712031 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -636,7 +636,6 @@ static const struct inet6_protocol frag_protocol = #ifdef CONFIG_SYSCTL static struct ctl_table ip6_frags_ns_ctl_table[] = { { - .ctl_name = NET_IPV6_IP6FRAG_HIGH_THRESH, .procname = "ip6frag_high_thresh", .data = &init_net.ipv6.frags.high_thresh, .maxlen = sizeof(int), @@ -644,7 +643,6 @@ static struct ctl_table ip6_frags_ns_ctl_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_IPV6_IP6FRAG_LOW_THRESH, .procname = "ip6frag_low_thresh", .data = &init_net.ipv6.frags.low_thresh, .maxlen = sizeof(int), @@ -652,26 +650,22 @@ static struct ctl_table ip6_frags_ns_ctl_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_IPV6_IP6FRAG_TIME, .procname = "ip6frag_time", .data = &init_net.ipv6.frags.timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { } }; static struct ctl_table ip6_frags_ctl_table[] = { { - .ctl_name = NET_IPV6_IP6FRAG_SECRET_INTERVAL, .procname = "ip6frag_secret_interval", .data = &ip6_frags.secret_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies }, { } }; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d6fe7646a8ff..6aa202e26f97 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2546,7 +2546,6 @@ ctl_table ipv6_route_table_template[] = { .proc_handler = ipv6_sysctl_rtcache_flush }, { - .ctl_name = NET_IPV6_ROUTE_GC_THRESH, .procname = "gc_thresh", .data = &ip6_dst_ops_template.gc_thresh, .maxlen = sizeof(int), @@ -2554,7 +2553,6 @@ ctl_table ipv6_route_table_template[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_ROUTE_MAX_SIZE, .procname = "max_size", .data = &init_net.ipv6.sysctl.ip6_rt_max_size, .maxlen = sizeof(int), @@ -2562,69 +2560,55 @@ ctl_table ipv6_route_table_template[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_ROUTE_GC_MIN_INTERVAL, .procname = "gc_min_interval", .data = &init_net.ipv6.sysctl.ip6_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_IPV6_ROUTE_GC_TIMEOUT, .procname = "gc_timeout", .data = &init_net.ipv6.sysctl.ip6_rt_gc_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_IPV6_ROUTE_GC_INTERVAL, .procname = "gc_interval", .data = &init_net.ipv6.sysctl.ip6_rt_gc_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_IPV6_ROUTE_GC_ELASTICITY, .procname = "gc_elasticity", .data = &init_net.ipv6.sysctl.ip6_rt_gc_elasticity, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_IPV6_ROUTE_MTU_EXPIRES, .procname = "mtu_expires", .data = &init_net.ipv6.sysctl.ip6_rt_mtu_expires, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_IPV6_ROUTE_MIN_ADVMSS, .procname = "min_adv_mss", .data = &init_net.ipv6.sysctl.ip6_rt_min_advmss, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_IPV6_ROUTE_GC_MIN_INTERVAL_MS, .procname = "gc_min_interval_ms", .data = &init_net.ipv6.sysctl.ip6_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, - .strategy = sysctl_ms_jiffies, }, - { .ctl_name = 0 } + { } }; struct ctl_table *ipv6_route_sysctl_init(struct net *net) diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index 0dc6a4e5ed4a..c690736885b4 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -16,45 +16,41 @@ static ctl_table ipv6_table_template[] = { { - .ctl_name = NET_IPV6_ROUTE, .procname = "route", .maxlen = 0, .mode = 0555, .child = ipv6_route_table_template }, { - .ctl_name = NET_IPV6_ICMP, .procname = "icmp", .maxlen = 0, .mode = 0555, .child = ipv6_icmp_table_template }, { - .ctl_name = NET_IPV6_BINDV6ONLY, .procname = "bindv6only", .data = &init_net.ipv6.sysctl.bindv6only, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, - { .ctl_name = 0 } + { } }; static ctl_table ipv6_rotable[] = { { - .ctl_name = NET_IPV6_MLD_MAX_MSF, .procname = "mld_max_msf", .data = &sysctl_mld_max_msf, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, - { .ctl_name = 0 } + { } }; struct ctl_path net_ipv6_ctl_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "ipv6", .ctl_name = NET_IPV6, }, + { .procname = "net", }, + { .procname = "ipv6", }, { }, }; EXPORT_SYMBOL_GPL(net_ipv6_ctl_path); diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 8ec3d45cd1d9..7254e3f899a7 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -309,7 +309,6 @@ static void xfrm6_policy_fini(void) #ifdef CONFIG_SYSCTL static struct ctl_table xfrm6_policy_table[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "xfrm6_gc_thresh", .data = &xfrm6_dst_ops.gc_thresh, .maxlen = sizeof(int), diff --git a/net/ipx/sysctl_net_ipx.c b/net/ipx/sysctl_net_ipx.c index 633fcab35580..bd6dca00fb85 100644 --- a/net/ipx/sysctl_net_ipx.c +++ b/net/ipx/sysctl_net_ipx.c @@ -18,19 +18,18 @@ extern int sysctl_ipx_pprop_broadcasting; static struct ctl_table ipx_table[] = { { - .ctl_name = NET_IPX_PPROP_BROADCASTING, .procname = "ipx_pprop_broadcasting", .data = &sysctl_ipx_pprop_broadcasting, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, - { 0 }, + { }, }; static struct ctl_path ipx_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "ipx", .ctl_name = NET_IPX, }, + { .procname = "net", }, + { .procname = "ipx", }, { } }; diff --git a/net/irda/irsysctl.c b/net/irda/irsysctl.c index 5c86567e5a78..d0b70dadf73b 100644 --- a/net/irda/irsysctl.c +++ b/net/irda/irsysctl.c @@ -113,26 +113,21 @@ static int do_discovery(ctl_table *table, int write, /* One file */ static ctl_table irda_table[] = { { - .ctl_name = NET_IRDA_DISCOVERY, .procname = "discovery", .data = &sysctl_discovery, .maxlen = sizeof(int), .mode = 0644, .proc_handler = do_discovery, - .strategy = sysctl_intvec }, { - .ctl_name = NET_IRDA_DEVNAME, .procname = "devname", .data = sysctl_devname, .maxlen = 65, .mode = 0644, .proc_handler = do_devname, - .strategy = sysctl_string }, #ifdef CONFIG_IRDA_DEBUG { - .ctl_name = NET_IRDA_DEBUG, .procname = "debug", .data = &irda_debug, .maxlen = sizeof(int), @@ -142,7 +137,6 @@ static ctl_table irda_table[] = { #endif #ifdef CONFIG_IRDA_FAST_RR { - .ctl_name = NET_IRDA_FAST_POLL, .procname = "fast_poll_increase", .data = &sysctl_fast_poll_increase, .maxlen = sizeof(int), @@ -151,18 +145,15 @@ static ctl_table irda_table[] = { }, #endif { - .ctl_name = NET_IRDA_DISCOVERY_SLOTS, .procname = "discovery_slots", .data = &sysctl_discovery_slots, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_discovery_slots, .extra2 = &max_discovery_slots }, { - .ctl_name = NET_IRDA_DISCOVERY_TIMEOUT, .procname = "discovery_timeout", .data = &sysctl_discovery_timeout, .maxlen = sizeof(int), @@ -170,99 +161,83 @@ static ctl_table irda_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_IRDA_SLOT_TIMEOUT, .procname = "slot_timeout", .data = &sysctl_slot_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_slot_timeout, .extra2 = &max_slot_timeout }, { - .ctl_name = NET_IRDA_MAX_BAUD_RATE, .procname = "max_baud_rate", .data = &sysctl_max_baud_rate, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_max_baud_rate, .extra2 = &max_max_baud_rate }, { - .ctl_name = NET_IRDA_MIN_TX_TURN_TIME, .procname = "min_tx_turn_time", .data = &sysctl_min_tx_turn_time, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_min_tx_turn_time, .extra2 = &max_min_tx_turn_time }, { - .ctl_name = NET_IRDA_MAX_TX_DATA_SIZE, .procname = "max_tx_data_size", .data = &sysctl_max_tx_data_size, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_max_tx_data_size, .extra2 = &max_max_tx_data_size }, { - .ctl_name = NET_IRDA_MAX_TX_WINDOW, .procname = "max_tx_window", .data = &sysctl_max_tx_window, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_max_tx_window, .extra2 = &max_max_tx_window }, { - .ctl_name = NET_IRDA_MAX_NOREPLY_TIME, .procname = "max_noreply_time", .data = &sysctl_max_noreply_time, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_max_noreply_time, .extra2 = &max_max_noreply_time }, { - .ctl_name = NET_IRDA_WARN_NOREPLY_TIME, .procname = "warn_noreply_time", .data = &sysctl_warn_noreply_time, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_warn_noreply_time, .extra2 = &max_warn_noreply_time }, { - .ctl_name = NET_IRDA_LAP_KEEPALIVE_TIME, .procname = "lap_keepalive_time", .data = &sysctl_lap_keepalive_time, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_lap_keepalive_time, .extra2 = &max_lap_keepalive_time }, - { .ctl_name = 0 } + { } }; static struct ctl_path irda_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "irda", .ctl_name = NET_IRDA, }, + { .procname = "net", }, + { .procname = "irda", }, { } }; diff --git a/net/llc/sysctl_net_llc.c b/net/llc/sysctl_net_llc.c index 57b9304d444c..e2ebe3586263 100644 --- a/net/llc/sysctl_net_llc.c +++ b/net/llc/sysctl_net_llc.c @@ -15,86 +15,73 @@ static struct ctl_table llc2_timeout_table[] = { { - .ctl_name = NET_LLC2_ACK_TIMEOUT, .procname = "ack", .data = &sysctl_llc2_ack_timeout, .maxlen = sizeof(long), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_LLC2_BUSY_TIMEOUT, .procname = "busy", .data = &sysctl_llc2_busy_timeout, .maxlen = sizeof(long), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_LLC2_P_TIMEOUT, .procname = "p", .data = &sysctl_llc2_p_timeout, .maxlen = sizeof(long), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_LLC2_REJ_TIMEOUT, .procname = "rej", .data = &sysctl_llc2_rej_timeout, .maxlen = sizeof(long), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, - { 0 }, + { }, }; static struct ctl_table llc_station_table[] = { { - .ctl_name = NET_LLC_STATION_ACK_TIMEOUT, .procname = "ack_timeout", .data = &sysctl_llc_station_ack_timeout, .maxlen = sizeof(long), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, - { 0 }, + { }, }; static struct ctl_table llc2_dir_timeout_table[] = { { - .ctl_name = NET_LLC2, .procname = "timeout", .mode = 0555, .child = llc2_timeout_table, }, - { 0 }, + { }, }; static struct ctl_table llc_table[] = { { - .ctl_name = NET_LLC2, .procname = "llc2", .mode = 0555, .child = llc2_dir_timeout_table, }, { - .ctl_name = NET_LLC_STATION, .procname = "station", .mode = 0555, .child = llc_station_table, }, - { 0 }, + { }, }; static struct ctl_path llc_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "llc", .ctl_name = NET_LLC, }, + { .procname = "net", }, + { .procname = "llc", }, { } }; diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index bc064d7933ff..ce8e0e772bab 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -85,10 +85,6 @@ void ieee80211_sta_stop_rx_ba_session(struct ieee80211_sub_if_data *sdata, u8 *r struct ieee80211_local *local = sdata->local; struct sta_info *sta; - /* stop HW Rx aggregation. ampdu_action existence - * already verified in session init so we add the BUG_ON */ - BUG_ON(!local->ops->ampdu_action); - rcu_read_lock(); sta = sta_info_get(local, ra); diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index b09948ceec4a..89e238b001de 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -123,13 +123,18 @@ void ieee80211_send_bar(struct ieee80211_sub_if_data *sdata, u8 *ra, u16 tid, u1 ieee80211_tx_skb(sdata, skb, 0); } -static int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, - enum ieee80211_back_parties initiator) +int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, + enum ieee80211_back_parties initiator) { struct ieee80211_local *local = sta->local; int ret; u8 *state; +#ifdef CONFIG_MAC80211_HT_DEBUG + printk(KERN_DEBUG "Tx BA session stop requested for %pM tid %u\n", + sta->sta.addr, tid); +#endif /* CONFIG_MAC80211_HT_DEBUG */ + state = &sta->ampdu_mlme.tid_state_tx[tid]; if (*state == HT_AGG_STATE_OPERATIONAL) @@ -143,7 +148,6 @@ static int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, /* HW shall not deny going back to legacy */ if (WARN_ON(ret)) { - *state = HT_AGG_STATE_OPERATIONAL; /* * We may have pending packets get stuck in this case... * Not bothering with a workaround for now. @@ -173,12 +177,14 @@ static void sta_addba_resp_timer_expired(unsigned long data) /* check if the TID waits for addBA response */ spin_lock_bh(&sta->lock); - if (!(*state & HT_ADDBA_REQUESTED_MSK)) { + if ((*state & (HT_ADDBA_REQUESTED_MSK | HT_ADDBA_RECEIVED_MSK)) != + HT_ADDBA_REQUESTED_MSK) { spin_unlock_bh(&sta->lock); *state = HT_AGG_STATE_IDLE; #ifdef CONFIG_MAC80211_HT_DEBUG printk(KERN_DEBUG "timer expired on tid %d but we are not " - "expecting addBA response there", tid); + "(or no longer) expecting addBA response there", + tid); #endif return; } @@ -523,11 +529,6 @@ int __ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, goto unlock; } -#ifdef CONFIG_MAC80211_HT_DEBUG - printk(KERN_DEBUG "Tx BA session stop requested for %pM tid %u\n", - sta->sta.addr, tid); -#endif /* CONFIG_MAC80211_HT_DEBUG */ - ret = ___ieee80211_stop_tx_ba_session(sta, tid, initiator); unlock: @@ -543,7 +544,7 @@ int ieee80211_stop_tx_ba_session(struct ieee80211_hw *hw, struct sta_info *sta; int ret = 0; - if (WARN_ON(!local->ops->ampdu_action)) + if (!local->ops->ampdu_action) return -EINVAL; if (tid >= STA_TID_NUM) @@ -666,21 +667,21 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local, state = &sta->ampdu_mlme.tid_state_tx[tid]; - del_timer_sync(&sta->ampdu_mlme.tid_tx[tid]->addba_resp_timer); - spin_lock_bh(&sta->lock); if (!(*state & HT_ADDBA_REQUESTED_MSK)) - goto timer_still_needed; + goto out; if (mgmt->u.action.u.addba_resp.dialog_token != sta->ampdu_mlme.tid_tx[tid]->dialog_token) { #ifdef CONFIG_MAC80211_HT_DEBUG printk(KERN_DEBUG "wrong addBA response token, tid %d\n", tid); #endif /* CONFIG_MAC80211_HT_DEBUG */ - goto timer_still_needed; + goto out; } + del_timer(&sta->ampdu_mlme.tid_tx[tid]->addba_resp_timer); + #ifdef CONFIG_MAC80211_HT_DEBUG printk(KERN_DEBUG "switched off addBA timer for tid %d \n", tid); #endif /* CONFIG_MAC80211_HT_DEBUG */ @@ -699,10 +700,6 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local, ___ieee80211_stop_tx_ba_session(sta, tid, WLAN_BACK_INITIATOR); } - goto out; - - timer_still_needed: - add_timer(&sta->ampdu_mlme.tid_tx[tid]->addba_resp_timer); out: spin_unlock_bh(&sta->lock); } diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index 48ef1a282b91..cdc58e61d921 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -141,7 +141,6 @@ void ieee80211_process_delba(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, struct ieee80211_mgmt *mgmt, size_t len) { - struct ieee80211_local *local = sdata->local; u16 tid, params; u16 initiator; @@ -161,10 +160,9 @@ void ieee80211_process_delba(struct ieee80211_sub_if_data *sdata, WLAN_BACK_INITIATOR, 0); else { /* WLAN_BACK_RECIPIENT */ spin_lock_bh(&sta->lock); - sta->ampdu_mlme.tid_state_tx[tid] = - HT_AGG_STATE_OPERATIONAL; + if (sta->ampdu_mlme.tid_state_tx[tid] & HT_ADDBA_REQUESTED_MSK) + ___ieee80211_stop_tx_ba_session(sta, tid, + WLAN_BACK_RECIPIENT); spin_unlock_bh(&sta->lock); - ieee80211_stop_tx_ba_session(&local->hw, sta->sta.addr, tid, - WLAN_BACK_RECIPIENT); } } diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 588005c84a6d..10d316e455de 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -662,6 +662,14 @@ struct ieee80211_local { bool suspended; /* + * Resuming is true while suspended, but when we're reprogramming the + * hardware -- at that time it's allowed to use ieee80211_queue_work() + * again even though some other parts of the stack are still suspended + * and we still drop received frames to avoid waking the stack. + */ + bool resuming; + + /* * quiescing is true during the suspend process _only_ to * ease timer cancelling etc. */ @@ -1083,6 +1091,8 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, int __ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, enum ieee80211_back_parties initiator); +int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, + enum ieee80211_back_parties initiator); /* Spectrum management */ void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata, diff --git a/net/mac80211/util.c b/net/mac80211/util.c index aeb65b3d2295..e6c08da8da26 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -520,9 +520,9 @@ EXPORT_SYMBOL_GPL(ieee80211_iterate_active_interfaces_atomic); */ static bool ieee80211_can_queue_work(struct ieee80211_local *local) { - if (WARN(local->suspended, "queueing ieee80211 work while " - "going to suspend\n")) - return false; + if (WARN(local->suspended && !local->resuming, + "queueing ieee80211 work while going to suspend\n")) + return false; return true; } @@ -1025,13 +1025,9 @@ int ieee80211_reconfig(struct ieee80211_local *local) struct sta_info *sta; unsigned long flags; int res; - bool from_suspend = local->suspended; - /* - * We're going to start the hardware, at that point - * we are no longer suspended and can RX frames. - */ - local->suspended = false; + if (local->suspended) + local->resuming = true; /* restart hardware */ if (local->open_count) { @@ -1129,11 +1125,14 @@ int ieee80211_reconfig(struct ieee80211_local *local) * If this is for hw restart things are still running. * We may want to change that later, however. */ - if (!from_suspend) + if (!local->suspended) return 0; #ifdef CONFIG_PM + /* first set suspended false, then resuming */ local->suspended = false; + mb(); + local->resuming = false; list_for_each_entry(sdata, &local->interfaces, list) { switch(sdata->vif.type) { diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 5bb34737501f..60ec4e4badaa 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -273,8 +273,8 @@ void __init netfilter_init(void) #ifdef CONFIG_SYSCTL struct ctl_path nf_net_netfilter_sysctl_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "netfilter", .ctl_name = NET_NETFILTER, }, + { .procname = "net", }, + { .procname = "netfilter", }, { } }; EXPORT_SYMBOL_GPL(nf_net_netfilter_sysctl_path); diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 446e9bd4b4bc..e55a6861d26f 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1706,12 +1706,12 @@ static struct ctl_table vs_vars[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { .ctl_name = 0 } + { } }; const struct ctl_path net_vs_ctl_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "ipv4", .ctl_name = NET_IPV4, }, + { .procname = "net", }, + { .procname = "ipv4", }, { .procname = "vs", }, { } }; diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index c1757f3620cd..1b9370db2305 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -121,7 +121,7 @@ static ctl_table vs_vars_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { .ctl_name = 0 } + { } }; static struct ctl_table_header * sysctl_header; diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index 715b57f9540d..f7476b95ab46 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -302,7 +302,7 @@ static ctl_table vs_vars_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { .ctl_name = 0 } + { } }; static struct ctl_table_header * sysctl_header; diff --git a/net/netfilter/nf_conntrack_acct.c b/net/netfilter/nf_conntrack_acct.c index 4a1d94aac20b..018f90db511c 100644 --- a/net/netfilter/nf_conntrack_acct.c +++ b/net/netfilter/nf_conntrack_acct.c @@ -30,7 +30,6 @@ MODULE_PARM_DESC(acct, "Enable connection tracking flow accounting."); #ifdef CONFIG_SYSCTL static struct ctl_table acct_sysctl_table[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "nf_conntrack_acct", .data = &init_net.ct.sysctl_acct, .maxlen = sizeof(unsigned int), diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index aee560b4768d..d5a9bcd7d61b 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -151,7 +151,6 @@ static int nf_ct_events_retry_timeout __read_mostly = 15*HZ; #ifdef CONFIG_SYSCTL static struct ctl_table event_sysctl_table[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "nf_conntrack_events", .data = &init_net.ct.sysctl_events, .maxlen = sizeof(unsigned int), @@ -159,7 +158,6 @@ static struct ctl_table event_sysctl_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "nf_conntrack_events_retry_timeout", .data = &init_net.ct.sysctl_events_retry_timeout, .maxlen = sizeof(unsigned int), diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 1b816a2ea813..7bf1395b4158 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -703,64 +703,54 @@ static int dccp_nlattr_size(void) /* template, data assigned later */ static struct ctl_table dccp_sysctl_table[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "nf_conntrack_dccp_timeout_request", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "nf_conntrack_dccp_timeout_respond", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "nf_conntrack_dccp_timeout_partopen", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "nf_conntrack_dccp_timeout_open", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "nf_conntrack_dccp_timeout_closereq", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "nf_conntrack_dccp_timeout_closing", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "nf_conntrack_dccp_timeout_timewait", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "nf_conntrack_dccp_loose", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, - { - .ctl_name = 0, - } + { } }; #endif /* CONFIG_SYSCTL */ diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index 829374f426c4..e2091d0c7a2f 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -69,9 +69,7 @@ static struct ctl_table generic_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { - .ctl_name = 0 - } + { } }; #ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT static struct ctl_table generic_compat_sysctl_table[] = { @@ -82,9 +80,7 @@ static struct ctl_table generic_compat_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { - .ctl_name = 0 - } + { } }; #endif /* CONFIG_NF_CONNTRACK_PROC_COMPAT */ #endif /* CONFIG_SYSCTL */ diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index c10e6f36e31e..f9d930f80276 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -595,9 +595,7 @@ static struct ctl_table sctp_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { - .ctl_name = 0 - } + { } }; #ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT @@ -651,9 +649,7 @@ static struct ctl_table sctp_compat_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { - .ctl_name = 0 - } + { } }; #endif /* CONFIG_NF_CONNTRACK_PROC_COMPAT */ #endif diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index ba2b76937283..7eda8b8e36a0 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1291,7 +1291,6 @@ static struct ctl_table tcp_sysctl_table[] = { .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = NET_NF_CONNTRACK_TCP_LOOSE, .procname = "nf_conntrack_tcp_loose", .data = &nf_ct_tcp_loose, .maxlen = sizeof(unsigned int), @@ -1299,7 +1298,6 @@ static struct ctl_table tcp_sysctl_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_NF_CONNTRACK_TCP_BE_LIBERAL, .procname = "nf_conntrack_tcp_be_liberal", .data = &nf_ct_tcp_be_liberal, .maxlen = sizeof(unsigned int), @@ -1307,16 +1305,13 @@ static struct ctl_table tcp_sysctl_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_NF_CONNTRACK_TCP_MAX_RETRANS, .procname = "nf_conntrack_tcp_max_retrans", .data = &nf_ct_tcp_max_retrans, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec, }, - { - .ctl_name = 0 - } + { } }; #ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT @@ -1392,7 +1387,6 @@ static struct ctl_table tcp_compat_sysctl_table[] = { .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = NET_IPV4_NF_CONNTRACK_TCP_LOOSE, .procname = "ip_conntrack_tcp_loose", .data = &nf_ct_tcp_loose, .maxlen = sizeof(unsigned int), @@ -1400,7 +1394,6 @@ static struct ctl_table tcp_compat_sysctl_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV4_NF_CONNTRACK_TCP_BE_LIBERAL, .procname = "ip_conntrack_tcp_be_liberal", .data = &nf_ct_tcp_be_liberal, .maxlen = sizeof(unsigned int), @@ -1408,16 +1401,13 @@ static struct ctl_table tcp_compat_sysctl_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV4_NF_CONNTRACK_TCP_MAX_RETRANS, .procname = "ip_conntrack_tcp_max_retrans", .data = &nf_ct_tcp_max_retrans, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec, }, - { - .ctl_name = 0 - } + { } }; #endif /* CONFIG_NF_CONNTRACK_PROC_COMPAT */ #endif /* CONFIG_SYSCTL */ diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 70809d117b91..5c5518bedb4b 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -154,9 +154,7 @@ static struct ctl_table udp_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { - .ctl_name = 0 - } + { } }; #ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT static struct ctl_table udp_compat_sysctl_table[] = { @@ -174,9 +172,7 @@ static struct ctl_table udp_compat_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { - .ctl_name = 0 - } + { } }; #endif /* CONFIG_NF_CONNTRACK_PROC_COMPAT */ #endif /* CONFIG_SYSCTL */ diff --git a/net/netfilter/nf_conntrack_proto_udplite.c b/net/netfilter/nf_conntrack_proto_udplite.c index 0badedc542d3..458655bb2106 100644 --- a/net/netfilter/nf_conntrack_proto_udplite.c +++ b/net/netfilter/nf_conntrack_proto_udplite.c @@ -146,7 +146,6 @@ static unsigned int udplite_sysctl_table_users; static struct ctl_table_header *udplite_sysctl_header; static struct ctl_table udplite_sysctl_table[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "nf_conntrack_udplite_timeout", .data = &nf_ct_udplite_timeout, .maxlen = sizeof(unsigned int), @@ -154,16 +153,13 @@ static struct ctl_table udplite_sysctl_table[] = { .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "nf_conntrack_udplite_timeout_stream", .data = &nf_ct_udplite_timeout_stream, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { - .ctl_name = 0 - } + { } }; #endif /* CONFIG_SYSCTL */ diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 193515381970..028aba667ef7 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -340,7 +340,6 @@ static struct ctl_table_header *nf_ct_netfilter_header; static ctl_table nf_ct_sysctl_table[] = { { - .ctl_name = NET_NF_CONNTRACK_MAX, .procname = "nf_conntrack_max", .data = &nf_conntrack_max, .maxlen = sizeof(int), @@ -348,7 +347,6 @@ static ctl_table nf_ct_sysctl_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_NF_CONNTRACK_COUNT, .procname = "nf_conntrack_count", .data = &init_net.ct.count, .maxlen = sizeof(int), @@ -356,7 +354,6 @@ static ctl_table nf_ct_sysctl_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_NF_CONNTRACK_BUCKETS, .procname = "nf_conntrack_buckets", .data = &nf_conntrack_htable_size, .maxlen = sizeof(unsigned int), @@ -364,7 +361,6 @@ static ctl_table nf_ct_sysctl_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_NF_CONNTRACK_CHECKSUM, .procname = "nf_conntrack_checksum", .data = &init_net.ct.sysctl_checksum, .maxlen = sizeof(unsigned int), @@ -372,43 +368,39 @@ static ctl_table nf_ct_sysctl_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_NF_CONNTRACK_LOG_INVALID, .procname = "nf_conntrack_log_invalid", .data = &init_net.ct.sysctl_log_invalid, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &log_invalid_proto_min, .extra2 = &log_invalid_proto_max, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "nf_conntrack_expect_max", .data = &nf_ct_expect_max, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, - { .ctl_name = 0 } + { } }; #define NET_NF_CONNTRACK_MAX 2089 static ctl_table nf_ct_netfilter_table[] = { { - .ctl_name = NET_NF_CONNTRACK_MAX, .procname = "nf_conntrack_max", .data = &nf_conntrack_max, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, - { .ctl_name = 0 } + { } }; static struct ctl_path nf_ct_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, + { .procname = "net", }, { } }; diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index c93494fef8ef..015725a5cd50 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -128,9 +128,8 @@ EXPORT_SYMBOL(nf_log_packet); #ifdef CONFIG_PROC_FS static void *seq_start(struct seq_file *seq, loff_t *pos) - __acquires(RCU) { - rcu_read_lock(); + mutex_lock(&nf_log_mutex); if (*pos >= ARRAY_SIZE(nf_loggers)) return NULL; @@ -149,9 +148,8 @@ static void *seq_next(struct seq_file *s, void *v, loff_t *pos) } static void seq_stop(struct seq_file *s, void *v) - __releases(RCU) { - rcu_read_unlock(); + mutex_unlock(&nf_log_mutex); } static int seq_show(struct seq_file *s, void *v) @@ -161,7 +159,7 @@ static int seq_show(struct seq_file *s, void *v) struct nf_logger *t; int ret; - logger = rcu_dereference(nf_loggers[*pos]); + logger = nf_loggers[*pos]; if (!logger) ret = seq_printf(s, "%2lld NONE (", *pos); @@ -171,22 +169,16 @@ static int seq_show(struct seq_file *s, void *v) if (ret < 0) return ret; - mutex_lock(&nf_log_mutex); list_for_each_entry(t, &nf_loggers_l[*pos], list[*pos]) { ret = seq_printf(s, "%s", t->name); - if (ret < 0) { - mutex_unlock(&nf_log_mutex); + if (ret < 0) return ret; - } if (&t->list[*pos] != nf_loggers_l[*pos].prev) { ret = seq_printf(s, ","); - if (ret < 0) { - mutex_unlock(&nf_log_mutex); + if (ret < 0) return ret; - } } } - mutex_unlock(&nf_log_mutex); return seq_printf(s, ")\n"); } @@ -216,9 +208,9 @@ static const struct file_operations nflog_file_ops = { #ifdef CONFIG_SYSCTL static struct ctl_path nf_log_sysctl_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "netfilter", .ctl_name = NET_NETFILTER, }, - { .procname = "nf_log", .ctl_name = CTL_UNNUMBERED, }, + { .procname = "net", }, + { .procname = "netfilter", }, + { .procname = "nf_log", }, { } }; @@ -273,7 +265,6 @@ static __init int netfilter_log_sysctl_init(void) for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) { snprintf(nf_log_sysctl_fnames[i-NFPROTO_UNSPEC], 3, "%d", i); - nf_log_sysctl_table[i].ctl_name = CTL_UNNUMBERED; nf_log_sysctl_table[i].procname = nf_log_sysctl_fnames[i-NFPROTO_UNSPEC]; nf_log_sysctl_table[i].data = NULL; diff --git a/net/netfilter/xt_limit.c b/net/netfilter/xt_limit.c index 2e8089ecd0af..2773be6a71dd 100644 --- a/net/netfilter/xt_limit.c +++ b/net/netfilter/xt_limit.c @@ -112,7 +112,7 @@ static bool limit_mt_check(const struct xt_mtchk_param *par) priv = kmalloc(sizeof(*priv), GFP_KERNEL); if (priv == NULL) - return -ENOMEM; + return false; /* For SMP, we only want to use one set of state. */ r->master = priv; diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c index 63e190504656..4d1a41bbd5d7 100644 --- a/net/netfilter/xt_osf.c +++ b/net/netfilter/xt_osf.c @@ -118,7 +118,7 @@ static int xt_osf_remove_callback(struct sock *ctnl, struct sk_buff *skb, { struct xt_osf_user_finger *f; struct xt_osf_finger *sf; - int err = ENOENT; + int err = -ENOENT; if (!osf_attrs[OSF_ATTR_FINGER]) return -EINVAL; diff --git a/net/netrom/sysctl_net_netrom.c b/net/netrom/sysctl_net_netrom.c index 7b49591fe87c..1e0fa9e57aac 100644 --- a/net/netrom/sysctl_net_netrom.c +++ b/net/netrom/sysctl_net_netrom.c @@ -36,143 +36,119 @@ static struct ctl_table_header *nr_table_header; static ctl_table nr_table[] = { { - .ctl_name = NET_NETROM_DEFAULT_PATH_QUALITY, .procname = "default_path_quality", .data = &sysctl_netrom_default_path_quality, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_quality, .extra2 = &max_quality }, { - .ctl_name = NET_NETROM_OBSOLESCENCE_COUNT_INITIALISER, .procname = "obsolescence_count_initialiser", .data = &sysctl_netrom_obsolescence_count_initialiser, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_obs, .extra2 = &max_obs }, { - .ctl_name = NET_NETROM_NETWORK_TTL_INITIALISER, .procname = "network_ttl_initialiser", .data = &sysctl_netrom_network_ttl_initialiser, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_ttl, .extra2 = &max_ttl }, { - .ctl_name = NET_NETROM_TRANSPORT_TIMEOUT, .procname = "transport_timeout", .data = &sysctl_netrom_transport_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_t1, .extra2 = &max_t1 }, { - .ctl_name = NET_NETROM_TRANSPORT_MAXIMUM_TRIES, .procname = "transport_maximum_tries", .data = &sysctl_netrom_transport_maximum_tries, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_n2, .extra2 = &max_n2 }, { - .ctl_name = NET_NETROM_TRANSPORT_ACKNOWLEDGE_DELAY, .procname = "transport_acknowledge_delay", .data = &sysctl_netrom_transport_acknowledge_delay, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_t2, .extra2 = &max_t2 }, { - .ctl_name = NET_NETROM_TRANSPORT_BUSY_DELAY, .procname = "transport_busy_delay", .data = &sysctl_netrom_transport_busy_delay, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_t4, .extra2 = &max_t4 }, { - .ctl_name = NET_NETROM_TRANSPORT_REQUESTED_WINDOW_SIZE, .procname = "transport_requested_window_size", .data = &sysctl_netrom_transport_requested_window_size, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_window, .extra2 = &max_window }, { - .ctl_name = NET_NETROM_TRANSPORT_NO_ACTIVITY_TIMEOUT, .procname = "transport_no_activity_timeout", .data = &sysctl_netrom_transport_no_activity_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_idle, .extra2 = &max_idle }, { - .ctl_name = NET_NETROM_ROUTING_CONTROL, .procname = "routing_control", .data = &sysctl_netrom_routing_control, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_route, .extra2 = &max_route }, { - .ctl_name = NET_NETROM_LINK_FAILS_COUNT, .procname = "link_fails_count", .data = &sysctl_netrom_link_fails_count, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_fails, .extra2 = &max_fails }, { - .ctl_name = NET_NETROM_RESET, .procname = "reset", .data = &sysctl_netrom_reset_circuit, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_reset, .extra2 = &max_reset }, - { .ctl_name = 0 } + { } }; static struct ctl_path nr_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "netrom", .ctl_name = NET_NETROM, }, + { .procname = "net", }, + { .procname = "netrom", }, { } }; diff --git a/net/phonet/sysctl.c b/net/phonet/sysctl.c index 2220f3322326..cea1c7dbdae2 100644 --- a/net/phonet/sysctl.c +++ b/net/phonet/sysctl.c @@ -84,20 +84,18 @@ static int proc_local_port_range(ctl_table *table, int write, static struct ctl_table phonet_table[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "local_port_range", .data = &local_port_range, .maxlen = sizeof(local_port_range), .mode = 0644, .proc_handler = proc_local_port_range, - .strategy = NULL, }, - { .ctl_name = 0 } + { } }; static struct ctl_path phonet_ctl_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "phonet", .ctl_name = CTL_UNNUMBERED, }, + { .procname = "net", }, + { .procname = "phonet", }, { }, }; diff --git a/net/rds/ib_sysctl.c b/net/rds/ib_sysctl.c index 84b5ffcb280f..03f01cb4e0fe 100644 --- a/net/rds/ib_sysctl.c +++ b/net/rds/ib_sysctl.c @@ -67,68 +67,62 @@ unsigned int rds_ib_sysctl_flow_control = 0; ctl_table rds_ib_sysctl_table[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "max_send_wr", .data = &rds_ib_sysctl_max_send_wr, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &proc_doulongvec_minmax, + .proc_handler = proc_doulongvec_minmax, .extra1 = &rds_ib_sysctl_max_wr_min, .extra2 = &rds_ib_sysctl_max_wr_max, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "max_recv_wr", .data = &rds_ib_sysctl_max_recv_wr, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &proc_doulongvec_minmax, + .proc_handler = proc_doulongvec_minmax, .extra1 = &rds_ib_sysctl_max_wr_min, .extra2 = &rds_ib_sysctl_max_wr_max, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "max_unsignaled_wr", .data = &rds_ib_sysctl_max_unsig_wrs, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &proc_doulongvec_minmax, + .proc_handler = proc_doulongvec_minmax, .extra1 = &rds_ib_sysctl_max_unsig_wr_min, .extra2 = &rds_ib_sysctl_max_unsig_wr_max, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "max_unsignaled_bytes", .data = &rds_ib_sysctl_max_unsig_bytes, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &proc_doulongvec_minmax, + .proc_handler = proc_doulongvec_minmax, .extra1 = &rds_ib_sysctl_max_unsig_bytes_min, .extra2 = &rds_ib_sysctl_max_unsig_bytes_max, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "max_recv_allocation", .data = &rds_ib_sysctl_max_recv_allocation, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &proc_doulongvec_minmax, + .proc_handler = proc_doulongvec_minmax, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "flow_control", .data = &rds_ib_sysctl_flow_control, .maxlen = sizeof(rds_ib_sysctl_flow_control), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, - { .ctl_name = 0} + { } }; static struct ctl_path rds_ib_sysctl_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "rds", .ctl_name = CTL_UNNUMBERED, }, - { .procname = "ib", .ctl_name = CTL_UNNUMBERED, }, + { .procname = "net", }, + { .procname = "rds", }, + { .procname = "ib", }, { } }; diff --git a/net/rds/iw_sysctl.c b/net/rds/iw_sysctl.c index 9590678cd616..1c4428a61a02 100644 --- a/net/rds/iw_sysctl.c +++ b/net/rds/iw_sysctl.c @@ -57,68 +57,62 @@ unsigned int rds_iw_sysctl_flow_control = 1; ctl_table rds_iw_sysctl_table[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "max_send_wr", .data = &rds_iw_sysctl_max_send_wr, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &proc_doulongvec_minmax, + .proc_handler = proc_doulongvec_minmax, .extra1 = &rds_iw_sysctl_max_wr_min, .extra2 = &rds_iw_sysctl_max_wr_max, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "max_recv_wr", .data = &rds_iw_sysctl_max_recv_wr, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &proc_doulongvec_minmax, + .proc_handler = proc_doulongvec_minmax, .extra1 = &rds_iw_sysctl_max_wr_min, .extra2 = &rds_iw_sysctl_max_wr_max, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "max_unsignaled_wr", .data = &rds_iw_sysctl_max_unsig_wrs, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &proc_doulongvec_minmax, + .proc_handler = proc_doulongvec_minmax, .extra1 = &rds_iw_sysctl_max_unsig_wr_min, .extra2 = &rds_iw_sysctl_max_unsig_wr_max, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "max_unsignaled_bytes", .data = &rds_iw_sysctl_max_unsig_bytes, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &proc_doulongvec_minmax, + .proc_handler = proc_doulongvec_minmax, .extra1 = &rds_iw_sysctl_max_unsig_bytes_min, .extra2 = &rds_iw_sysctl_max_unsig_bytes_max, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "max_recv_allocation", .data = &rds_iw_sysctl_max_recv_allocation, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &proc_doulongvec_minmax, + .proc_handler = proc_doulongvec_minmax, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "flow_control", .data = &rds_iw_sysctl_flow_control, .maxlen = sizeof(rds_iw_sysctl_flow_control), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, - { .ctl_name = 0} + { } }; static struct ctl_path rds_iw_sysctl_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "rds", .ctl_name = CTL_UNNUMBERED, }, - { .procname = "iw", .ctl_name = CTL_UNNUMBERED, }, + { .procname = "net", }, + { .procname = "rds", }, + { .procname = "iw", }, { } }; diff --git a/net/rds/sysctl.c b/net/rds/sysctl.c index 307dc5c1be15..7829a20325d3 100644 --- a/net/rds/sysctl.c +++ b/net/rds/sysctl.c @@ -51,55 +51,50 @@ unsigned int rds_sysctl_ping_enable = 1; static ctl_table rds_sysctl_rds_table[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "reconnect_min_delay_ms", .data = &rds_sysctl_reconnect_min_jiffies, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &proc_doulongvec_ms_jiffies_minmax, + .proc_handler = proc_doulongvec_ms_jiffies_minmax, .extra1 = &rds_sysctl_reconnect_min, .extra2 = &rds_sysctl_reconnect_max_jiffies, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "reconnect_max_delay_ms", .data = &rds_sysctl_reconnect_max_jiffies, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &proc_doulongvec_ms_jiffies_minmax, + .proc_handler = proc_doulongvec_ms_jiffies_minmax, .extra1 = &rds_sysctl_reconnect_min_jiffies, .extra2 = &rds_sysctl_reconnect_max, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "max_unacked_packets", .data = &rds_sysctl_max_unacked_packets, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "max_unacked_bytes", .data = &rds_sysctl_max_unacked_bytes, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "ping_enable", .data = &rds_sysctl_ping_enable, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, - { .ctl_name = 0} + { } }; static struct ctl_path rds_sysctl_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "rds", .ctl_name = CTL_UNNUMBERED, }, + { .procname = "net", }, + { .procname = "rds", }, { } }; diff --git a/net/rfkill/core.c b/net/rfkill/core.c index ba2efb960c60..a001f7c1f711 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -1189,6 +1189,7 @@ static long rfkill_fop_ioctl(struct file *file, unsigned int cmd, #endif static const struct file_operations rfkill_fops = { + .owner = THIS_MODULE, .open = rfkill_fop_open, .read = rfkill_fop_read, .write = rfkill_fop_write, diff --git a/net/rose/sysctl_net_rose.c b/net/rose/sysctl_net_rose.c index 3bfe504faf86..df6d9dac2186 100644 --- a/net/rose/sysctl_net_rose.c +++ b/net/rose/sysctl_net_rose.c @@ -26,121 +26,101 @@ static struct ctl_table_header *rose_table_header; static ctl_table rose_table[] = { { - .ctl_name = NET_ROSE_RESTART_REQUEST_TIMEOUT, .procname = "restart_request_timeout", .data = &sysctl_rose_restart_request_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_timer, .extra2 = &max_timer }, { - .ctl_name = NET_ROSE_CALL_REQUEST_TIMEOUT, .procname = "call_request_timeout", .data = &sysctl_rose_call_request_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_timer, .extra2 = &max_timer }, { - .ctl_name = NET_ROSE_RESET_REQUEST_TIMEOUT, .procname = "reset_request_timeout", .data = &sysctl_rose_reset_request_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_timer, .extra2 = &max_timer }, { - .ctl_name = NET_ROSE_CLEAR_REQUEST_TIMEOUT, .procname = "clear_request_timeout", .data = &sysctl_rose_clear_request_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_timer, .extra2 = &max_timer }, { - .ctl_name = NET_ROSE_NO_ACTIVITY_TIMEOUT, .procname = "no_activity_timeout", .data = &sysctl_rose_no_activity_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_idle, .extra2 = &max_idle }, { - .ctl_name = NET_ROSE_ACK_HOLD_BACK_TIMEOUT, .procname = "acknowledge_hold_back_timeout", .data = &sysctl_rose_ack_hold_back_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_timer, .extra2 = &max_timer }, { - .ctl_name = NET_ROSE_ROUTING_CONTROL, .procname = "routing_control", .data = &sysctl_rose_routing_control, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_route, .extra2 = &max_route }, { - .ctl_name = NET_ROSE_LINK_FAIL_TIMEOUT, .procname = "link_fail_timeout", .data = &sysctl_rose_link_fail_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_ftimer, .extra2 = &max_ftimer }, { - .ctl_name = NET_ROSE_MAX_VCS, .procname = "maximum_virtual_circuits", .data = &sysctl_rose_maximum_vcs, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_maxvcs, .extra2 = &max_maxvcs }, { - .ctl_name = NET_ROSE_WINDOW_SIZE, .procname = "window_size", .data = &sysctl_rose_window_size, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_window, .extra2 = &max_window }, - { .ctl_name = 0 } + { } }; static struct ctl_path rose_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "rose", .ctl_name = NET_ROSE, }, + { .procname = "net", }, + { .procname = "rose", }, { } }; diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index c9f20e28521b..23e5e97aa617 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -423,16 +423,6 @@ void sctp_retransmit_mark(struct sctp_outq *q, if ((reason == SCTP_RTXR_FAST_RTX && (chunk->fast_retransmit == SCTP_NEED_FRTX)) || (reason != SCTP_RTXR_FAST_RTX && !chunk->tsn_gap_acked)) { - /* If this chunk was sent less then 1 rto ago, do not - * retransmit this chunk, but give the peer time - * to acknowlege it. Do this only when - * retransmitting due to T3 timeout. - */ - if (reason == SCTP_RTXR_T3_RTX && - time_before(jiffies, chunk->sent_at + - transport->last_rto)) - continue; - /* RFC 2960 6.2.1 Processing a Received SACK * * C) Any time a DATA chunk is marked for diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 8674d4919556..efa516b47e81 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -480,7 +480,6 @@ static void sctp_do_8_2_transport_strike(struct sctp_association *asoc, * that indicates that we have an outstanding HB. */ if (!is_hb || transport->hb_sent) { - transport->last_rto = transport->rto; transport->rto = min((transport->rto * 2), transport->asoc->rto_max); } } diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index ab7151da120f..d50a042f9552 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -59,180 +59,145 @@ extern int sysctl_sctp_wmem[3]; static ctl_table sctp_table[] = { { - .ctl_name = NET_SCTP_RTO_INITIAL, .procname = "rto_initial", .data = &sctp_rto_initial, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &one, .extra2 = &timer_max }, { - .ctl_name = NET_SCTP_RTO_MIN, .procname = "rto_min", .data = &sctp_rto_min, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &one, .extra2 = &timer_max }, { - .ctl_name = NET_SCTP_RTO_MAX, .procname = "rto_max", .data = &sctp_rto_max, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &one, .extra2 = &timer_max }, { - .ctl_name = NET_SCTP_VALID_COOKIE_LIFE, .procname = "valid_cookie_life", .data = &sctp_valid_cookie_life, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &one, .extra2 = &timer_max }, { - .ctl_name = NET_SCTP_MAX_BURST, .procname = "max_burst", .data = &sctp_max_burst, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &zero, .extra2 = &int_max }, { - .ctl_name = NET_SCTP_ASSOCIATION_MAX_RETRANS, .procname = "association_max_retrans", .data = &sctp_max_retrans_association, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &one, .extra2 = &int_max }, { - .ctl_name = NET_SCTP_SNDBUF_POLICY, .procname = "sndbuf_policy", .data = &sctp_sndbuf_policy, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, - .strategy = sysctl_intvec }, { - .ctl_name = NET_SCTP_RCVBUF_POLICY, .procname = "rcvbuf_policy", .data = &sctp_rcvbuf_policy, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, - .strategy = sysctl_intvec }, { - .ctl_name = NET_SCTP_PATH_MAX_RETRANS, .procname = "path_max_retrans", .data = &sctp_max_retrans_path, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &one, .extra2 = &int_max }, { - .ctl_name = NET_SCTP_MAX_INIT_RETRANSMITS, .procname = "max_init_retransmits", .data = &sctp_max_retrans_init, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &one, .extra2 = &int_max }, { - .ctl_name = NET_SCTP_HB_INTERVAL, .procname = "hb_interval", .data = &sctp_hb_interval, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &one, .extra2 = &timer_max }, { - .ctl_name = NET_SCTP_PRESERVE_ENABLE, .procname = "cookie_preserve_enable", .data = &sctp_cookie_preserve_enable, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, - .strategy = sysctl_intvec }, { - .ctl_name = NET_SCTP_RTO_ALPHA, .procname = "rto_alpha_exp_divisor", .data = &sctp_rto_alpha, .maxlen = sizeof(int), .mode = 0444, .proc_handler = proc_dointvec, - .strategy = sysctl_intvec }, { - .ctl_name = NET_SCTP_RTO_BETA, .procname = "rto_beta_exp_divisor", .data = &sctp_rto_beta, .maxlen = sizeof(int), .mode = 0444, .proc_handler = proc_dointvec, - .strategy = sysctl_intvec }, { - .ctl_name = NET_SCTP_ADDIP_ENABLE, .procname = "addip_enable", .data = &sctp_addip_enable, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, - .strategy = sysctl_intvec }, { - .ctl_name = NET_SCTP_PRSCTP_ENABLE, .procname = "prsctp_enable", .data = &sctp_prsctp_enable, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, - .strategy = sysctl_intvec }, { - .ctl_name = NET_SCTP_SACK_TIMEOUT, .procname = "sack_timeout", .data = &sctp_sack_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &sack_timer_min, .extra2 = &sack_timer_max, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "sctp_mem", .data = &sysctl_sctp_mem, .maxlen = sizeof(sysctl_sctp_mem), @@ -240,7 +205,6 @@ static ctl_table sctp_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "sctp_rmem", .data = &sysctl_sctp_rmem, .maxlen = sizeof(sysctl_sctp_rmem), @@ -248,7 +212,6 @@ static ctl_table sctp_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "sctp_wmem", .data = &sysctl_sctp_wmem, .maxlen = sizeof(sysctl_sctp_wmem), @@ -256,40 +219,34 @@ static ctl_table sctp_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "auth_enable", .data = &sctp_auth_enable, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, - .strategy = sysctl_intvec }, { - .ctl_name = CTL_UNNUMBERED, .procname = "addip_noauth_enable", .data = &sctp_addip_noauth, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, - .strategy = sysctl_intvec }, { - .ctl_name = CTL_UNNUMBERED, .procname = "addr_scope_policy", .data = &sctp_scope_policy, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero, .extra2 = &addr_scope_max, }, - { .ctl_name = 0 } + { } }; static struct ctl_path sctp_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "sctp", .ctl_name = NET_SCTP, }, + { .procname = "net", }, + { .procname = "sctp", }, { } }; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 3b141bb32faf..37a1184d789f 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -74,7 +74,7 @@ static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer, * given destination transport address, set RTO to the protocol * parameter 'RTO.Initial'. */ - peer->last_rto = peer->rto = msecs_to_jiffies(sctp_rto_initial); + peer->rto = msecs_to_jiffies(sctp_rto_initial); peer->rtt = 0; peer->rttvar = 0; peer->srtt = 0; @@ -386,7 +386,6 @@ void sctp_transport_update_rto(struct sctp_transport *tp, __u32 rtt) tp->rto = tp->asoc->rto_max; tp->rtt = rtt; - tp->last_rto = tp->rto; /* Reset rto_pending so that a new RTT measurement is started when a * new data chunk is sent. @@ -602,7 +601,7 @@ void sctp_transport_reset(struct sctp_transport *t) */ t->cwnd = min(4*asoc->pathmtu, max_t(__u32, 2*asoc->pathmtu, 4380)); t->ssthresh = asoc->peer.i.a_rwnd; - t->last_rto = t->rto = asoc->rto_initial; + t->rto = asoc->rto_initial; t->rtt = 0; t->srtt = 0; t->rttvar = 0; diff --git a/net/sunrpc/sysctl.c b/net/sunrpc/sysctl.c index 42f9748ae093..e65dcc613339 100644 --- a/net/sunrpc/sysctl.c +++ b/net/sunrpc/sysctl.c @@ -139,46 +139,45 @@ static ctl_table debug_table[] = { .data = &rpc_debug, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dodebug + .proc_handler = proc_dodebug }, { .procname = "nfs_debug", .data = &nfs_debug, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dodebug + .proc_handler = proc_dodebug }, { .procname = "nfsd_debug", .data = &nfsd_debug, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dodebug + .proc_handler = proc_dodebug }, { .procname = "nlm_debug", .data = &nlm_debug, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dodebug + .proc_handler = proc_dodebug }, { .procname = "transports", .maxlen = 256, .mode = 0444, - .proc_handler = &proc_do_xprt, + .proc_handler = proc_do_xprt, }, - { .ctl_name = 0 } + { } }; static ctl_table sunrpc_table[] = { { - .ctl_name = CTL_SUNRPC, .procname = "sunrpc", .mode = 0555, .child = debug_table }, - { .ctl_name = 0 } + { } }; #endif diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c index 35fb68b9c8ec..5b8a8ff93a25 100644 --- a/net/sunrpc/xprtrdma/svc_rdma.c +++ b/net/sunrpc/xprtrdma/svc_rdma.c @@ -120,8 +120,7 @@ static ctl_table svcrdma_parm_table[] = { .data = &svcrdma_max_requests, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &min_max_requests, .extra2 = &max_max_requests }, @@ -130,8 +129,7 @@ static ctl_table svcrdma_parm_table[] = { .data = &svcrdma_max_req_size, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &min_max_inline, .extra2 = &max_max_inline }, @@ -140,8 +138,7 @@ static ctl_table svcrdma_parm_table[] = { .data = &svcrdma_ord, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &min_ord, .extra2 = &max_ord, }, @@ -151,67 +148,65 @@ static ctl_table svcrdma_parm_table[] = { .data = &rdma_stat_read, .maxlen = sizeof(atomic_t), .mode = 0644, - .proc_handler = &read_reset_stat, + .proc_handler = read_reset_stat, }, { .procname = "rdma_stat_recv", .data = &rdma_stat_recv, .maxlen = sizeof(atomic_t), .mode = 0644, - .proc_handler = &read_reset_stat, + .proc_handler = read_reset_stat, }, { .procname = "rdma_stat_write", .data = &rdma_stat_write, .maxlen = sizeof(atomic_t), .mode = 0644, - .proc_handler = &read_reset_stat, + .proc_handler = read_reset_stat, }, { .procname = "rdma_stat_sq_starve", .data = &rdma_stat_sq_starve, .maxlen = sizeof(atomic_t), .mode = 0644, - .proc_handler = &read_reset_stat, + .proc_handler = read_reset_stat, }, { .procname = "rdma_stat_rq_starve", .data = &rdma_stat_rq_starve, .maxlen = sizeof(atomic_t), .mode = 0644, - .proc_handler = &read_reset_stat, + .proc_handler = read_reset_stat, }, { .procname = "rdma_stat_rq_poll", .data = &rdma_stat_rq_poll, .maxlen = sizeof(atomic_t), .mode = 0644, - .proc_handler = &read_reset_stat, + .proc_handler = read_reset_stat, }, { .procname = "rdma_stat_rq_prod", .data = &rdma_stat_rq_prod, .maxlen = sizeof(atomic_t), .mode = 0644, - .proc_handler = &read_reset_stat, + .proc_handler = read_reset_stat, }, { .procname = "rdma_stat_sq_poll", .data = &rdma_stat_sq_poll, .maxlen = sizeof(atomic_t), .mode = 0644, - .proc_handler = &read_reset_stat, + .proc_handler = read_reset_stat, }, { .procname = "rdma_stat_sq_prod", .data = &rdma_stat_sq_prod, .maxlen = sizeof(atomic_t), .mode = 0644, - .proc_handler = &read_reset_stat, - }, - { - .ctl_name = 0, + .proc_handler = read_reset_stat, }, + { }, }; static ctl_table svcrdma_table[] = { @@ -220,21 +215,16 @@ static ctl_table svcrdma_table[] = { .mode = 0555, .child = svcrdma_parm_table }, - { - .ctl_name = 0, - }, + { }, }; static ctl_table svcrdma_root_table[] = { { - .ctl_name = CTL_SUNRPC, .procname = "sunrpc", .mode = 0555, .child = svcrdma_table }, - { - .ctl_name = 0, - }, + { }, }; void svc_rdma_cleanup(void) diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 9a63f669ece4..7018eef1dcdd 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -86,79 +86,63 @@ static struct ctl_table_header *sunrpc_table_header; static ctl_table xr_tunables_table[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "rdma_slot_table_entries", .data = &xprt_rdma_slot_table_entries, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &min_slot_table_size, .extra2 = &max_slot_table_size }, { - .ctl_name = CTL_UNNUMBERED, .procname = "rdma_max_inline_read", .data = &xprt_rdma_max_inline_read, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "rdma_max_inline_write", .data = &xprt_rdma_max_inline_write, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "rdma_inline_write_padding", .data = &xprt_rdma_inline_write_padding, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero, .extra2 = &max_padding, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "rdma_memreg_strategy", .data = &xprt_rdma_memreg_strategy, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &min_memreg, .extra2 = &max_memreg, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "rdma_pad_optimize", .data = &xprt_rdma_pad_optimize, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec, - }, - { - .ctl_name = 0, + .proc_handler = proc_dointvec, }, + { }, }; static ctl_table sunrpc_table[] = { { - .ctl_name = CTL_SUNRPC, .procname = "sunrpc", .mode = 0555, .child = xr_tunables_table }, - { - .ctl_name = 0, - }, + { }, }; #endif diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 37c5475ba258..04732d09013e 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -81,46 +81,38 @@ static struct ctl_table_header *sunrpc_table_header; */ static ctl_table xs_tunables_table[] = { { - .ctl_name = CTL_SLOTTABLE_UDP, .procname = "udp_slot_table_entries", .data = &xprt_udp_slot_table_entries, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &min_slot_table_size, .extra2 = &max_slot_table_size }, { - .ctl_name = CTL_SLOTTABLE_TCP, .procname = "tcp_slot_table_entries", .data = &xprt_tcp_slot_table_entries, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &min_slot_table_size, .extra2 = &max_slot_table_size }, { - .ctl_name = CTL_MIN_RESVPORT, .procname = "min_resvport", .data = &xprt_min_resvport, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &xprt_min_resvport_limit, .extra2 = &xprt_max_resvport_limit }, { - .ctl_name = CTL_MAX_RESVPORT, .procname = "max_resvport", .data = &xprt_max_resvport, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &xprt_min_resvport_limit, .extra2 = &xprt_max_resvport_limit }, @@ -129,24 +121,18 @@ static ctl_table xs_tunables_table[] = { .data = &xs_tcp_fin_timeout, .maxlen = sizeof(xs_tcp_fin_timeout), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = sysctl_jiffies - }, - { - .ctl_name = 0, + .proc_handler = proc_dointvec_jiffies, }, + { }, }; static ctl_table sunrpc_table[] = { { - .ctl_name = CTL_SUNRPC, .procname = "sunrpc", .mode = 0555, .child = xs_tunables_table }, - { - .ctl_name = 0, - }, + { }, }; #endif diff --git a/net/unix/sysctl_net_unix.c b/net/unix/sysctl_net_unix.c index 83c093077ebc..708f5df6b7f0 100644 --- a/net/unix/sysctl_net_unix.c +++ b/net/unix/sysctl_net_unix.c @@ -16,19 +16,18 @@ static ctl_table unix_table[] = { { - .ctl_name = NET_UNIX_MAX_DGRAM_QLEN, .procname = "max_dgram_qlen", .data = &init_net.unx.sysctl_max_dgram_qlen, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, - { .ctl_name = 0 } + { } }; static struct ctl_path unix_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "unix", .ctl_name = NET_UNIX, }, + { .procname = "net", }, + { .procname = "unix", }, { }, }; diff --git a/net/x25/sysctl_net_x25.c b/net/x25/sysctl_net_x25.c index a5d3416522de..d2efd29f434e 100644 --- a/net/x25/sysctl_net_x25.c +++ b/net/x25/sysctl_net_x25.c @@ -19,62 +19,51 @@ static struct ctl_table_header *x25_table_header; static struct ctl_table x25_table[] = { { - .ctl_name = NET_X25_RESTART_REQUEST_TIMEOUT, .procname = "restart_request_timeout", .data = &sysctl_x25_restart_request_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_timer, .extra2 = &max_timer, }, { - .ctl_name = NET_X25_CALL_REQUEST_TIMEOUT, .procname = "call_request_timeout", .data = &sysctl_x25_call_request_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_timer, .extra2 = &max_timer, }, { - .ctl_name = NET_X25_RESET_REQUEST_TIMEOUT, .procname = "reset_request_timeout", .data = &sysctl_x25_reset_request_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_timer, .extra2 = &max_timer, }, { - .ctl_name = NET_X25_CLEAR_REQUEST_TIMEOUT, .procname = "clear_request_timeout", .data = &sysctl_x25_clear_request_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_timer, .extra2 = &max_timer, }, { - .ctl_name = NET_X25_ACK_HOLD_BACK_TIMEOUT, .procname = "acknowledgement_hold_back_timeout", .data = &sysctl_x25_ack_holdback_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .strategy = sysctl_intvec, .extra1 = &min_timer, .extra2 = &max_timer, }, { - .ctl_name = NET_X25_FORWARD, .procname = "x25_forward", .data = &sysctl_x25_forward, .maxlen = sizeof(int), @@ -85,8 +74,8 @@ static struct ctl_table x25_table[] = { }; static struct ctl_path x25_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "x25", .ctl_name = NET_X25, }, + { .procname = "net", }, + { .procname = "x25", }, { } }; diff --git a/net/xfrm/xfrm_sysctl.c b/net/xfrm/xfrm_sysctl.c index 2e6ffb66f06f..2e221f2cad7e 100644 --- a/net/xfrm/xfrm_sysctl.c +++ b/net/xfrm/xfrm_sysctl.c @@ -13,28 +13,24 @@ static void __xfrm_sysctl_init(struct net *net) #ifdef CONFIG_SYSCTL static struct ctl_table xfrm_table[] = { { - .ctl_name = NET_CORE_AEVENT_ETIME, .procname = "xfrm_aevent_etime", .maxlen = sizeof(u32), .mode = 0644, .proc_handler = proc_dointvec }, { - .ctl_name = NET_CORE_AEVENT_RSEQTH, .procname = "xfrm_aevent_rseqth", .maxlen = sizeof(u32), .mode = 0644, .proc_handler = proc_dointvec }, { - .ctl_name = CTL_UNNUMBERED, .procname = "xfrm_larval_drop", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { - .ctl_name = CTL_UNNUMBERED, .procname = "xfrm_acq_expires", .maxlen = sizeof(int), .mode = 0644, diff --git a/samples/Kconfig b/samples/Kconfig index b92bde3c6a89..e4be84ac3d38 100644 --- a/samples/Kconfig +++ b/samples/Kconfig @@ -40,5 +40,11 @@ config SAMPLE_KRETPROBES default m depends on SAMPLE_KPROBES && KRETPROBES +config SAMPLE_HW_BREAKPOINT + tristate "Build kernel hardware breakpoint examples -- loadable module only" + depends on HAVE_HW_BREAKPOINT && m + help + This builds kernel hardware breakpoint example modules. + endif # SAMPLES diff --git a/samples/Makefile b/samples/Makefile index 43343a03b1f4..0f15e6d77fd6 100644 --- a/samples/Makefile +++ b/samples/Makefile @@ -1,3 +1,4 @@ # Makefile for Linux samples code -obj-$(CONFIG_SAMPLES) += kobject/ kprobes/ tracepoints/ trace_events/ +obj-$(CONFIG_SAMPLES) += kobject/ kprobes/ tracepoints/ trace_events/ \ + hw_breakpoint/ diff --git a/samples/hw_breakpoint/Makefile b/samples/hw_breakpoint/Makefile new file mode 100644 index 000000000000..0f5c31c2fc47 --- /dev/null +++ b/samples/hw_breakpoint/Makefile @@ -0,0 +1 @@ +obj-$(CONFIG_SAMPLE_HW_BREAKPOINT) += data_breakpoint.o diff --git a/samples/hw_breakpoint/data_breakpoint.c b/samples/hw_breakpoint/data_breakpoint.c new file mode 100644 index 000000000000..29525500df00 --- /dev/null +++ b/samples/hw_breakpoint/data_breakpoint.c @@ -0,0 +1,87 @@ +/* + * data_breakpoint.c - Sample HW Breakpoint file to watch kernel data address + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * usage: insmod data_breakpoint.ko ksym=<ksym_name> + * + * This file is a kernel module that places a breakpoint over ksym_name kernel + * variable using Hardware Breakpoint register. The corresponding handler which + * prints a backtrace is invoked everytime a write operation is performed on + * that variable. + * + * Copyright (C) IBM Corporation, 2009 + * + * Author: K.Prasad <prasad@linux.vnet.ibm.com> + */ +#include <linux/module.h> /* Needed by all modules */ +#include <linux/kernel.h> /* Needed for KERN_INFO */ +#include <linux/init.h> /* Needed for the macros */ +#include <linux/kallsyms.h> + +#include <linux/perf_event.h> +#include <linux/hw_breakpoint.h> + +struct perf_event **sample_hbp; + +static char ksym_name[KSYM_NAME_LEN] = "pid_max"; +module_param_string(ksym, ksym_name, KSYM_NAME_LEN, S_IRUGO); +MODULE_PARM_DESC(ksym, "Kernel symbol to monitor; this module will report any" + " write operations on the kernel symbol"); + +static void sample_hbp_handler(struct perf_event *temp, void *data) +{ + printk(KERN_INFO "%s value is changed\n", ksym_name); + dump_stack(); + printk(KERN_INFO "Dump stack from sample_hbp_handler\n"); +} + +static int __init hw_break_module_init(void) +{ + int ret; + DEFINE_BREAKPOINT_ATTR(attr); + + attr.bp_addr = kallsyms_lookup_name(ksym_name); + attr.bp_len = HW_BREAKPOINT_LEN_4; + attr.bp_type = HW_BREAKPOINT_W | HW_BREAKPOINT_R; + + sample_hbp = register_wide_hw_breakpoint(&attr, sample_hbp_handler); + if (IS_ERR(sample_hbp)) { + ret = PTR_ERR(sample_hbp); + goto fail; + } + + printk(KERN_INFO "HW Breakpoint for %s write installed\n", ksym_name); + + return 0; + +fail: + printk(KERN_INFO "Breakpoint registration failed\n"); + + return ret; +} + +static void __exit hw_break_module_exit(void) +{ + unregister_wide_hw_breakpoint(sample_hbp); + printk(KERN_INFO "HW Breakpoint for %s write uninstalled\n", ksym_name); +} + +module_init(hw_break_module_init); +module_exit(hw_break_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("K.Prasad"); +MODULE_DESCRIPTION("ksym breakpoint"); diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile index 6d69c7ccdcc7..80599e3a7994 100644 --- a/scripts/kconfig/Makefile +++ b/scripts/kconfig/Makefile @@ -30,7 +30,7 @@ silentoldconfig: $(obj)/conf $< -s $(Kconfig) localmodconfig: $(obj)/streamline_config.pl $(obj)/conf - $(Q)perl $< $(Kconfig) > .tmp.config + $(Q)perl $< $(srctree) $(Kconfig) > .tmp.config $(Q)if [ -f .config ]; then \ cmp -s .tmp.config .config || \ (mv -f .config .config.old.1; \ @@ -44,7 +44,7 @@ localmodconfig: $(obj)/streamline_config.pl $(obj)/conf $(Q)rm -f .tmp.config localyesconfig: $(obj)/streamline_config.pl $(obj)/conf - $(Q)perl $< $(Kconfig) > .tmp.config + $(Q)perl $< $(srctree) $(Kconfig) > .tmp.config $(Q)sed -i s/=m/=y/ .tmp.config $(Q)if [ -f .config ]; then \ cmp -s .tmp.config .config || \ diff --git a/scripts/kconfig/streamline_config.pl b/scripts/kconfig/streamline_config.pl index 95984db8e1e0..0d800820c3cd 100644 --- a/scripts/kconfig/streamline_config.pl +++ b/scripts/kconfig/streamline_config.pl @@ -43,7 +43,6 @@ # make oldconfig # my $config = ".config"; -my $linuxpath = "."; my $uname = `uname -r`; chomp $uname; @@ -111,7 +110,11 @@ sub find_config { find_config; -my @makefiles = `find $linuxpath -name Makefile`; +# Get the build source and top level Kconfig file (passed in) +my $ksource = $ARGV[0]; +my $kconfig = $ARGV[1]; + +my @makefiles = `find $ksource -name Makefile`; my %depends; my %selects; my %prompts; @@ -119,9 +122,6 @@ my %objects; my $var; my $cont = 0; -# Get the top level Kconfig file (passed in) -my $kconfig = $ARGV[0]; - # prevent recursion my %read_kconfigs; @@ -132,7 +132,7 @@ sub read_kconfig { my $config; my @kconfigs; - open(KIN, $kconfig) || die "Can't open $kconfig"; + open(KIN, "$ksource/$kconfig") || die "Can't open $kconfig"; while (<KIN>) { chomp; diff --git a/scripts/kernel-doc b/scripts/kernel-doc index ea9f8a58678f..241310e59cd6 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -1852,10 +1852,17 @@ sub tracepoint_munge($) { my $tracepointname = 0; my $tracepointargs = 0; - if($prototype =~ m/TRACE_EVENT\((.*?),/) { + if ($prototype =~ m/TRACE_EVENT\((.*?),/) { $tracepointname = $1; } - if($prototype =~ m/TP_PROTO\((.*?)\)/) { + if ($prototype =~ m/DEFINE_SINGLE_EVENT\((.*?),/) { + $tracepointname = $1; + } + if ($prototype =~ m/DEFINE_EVENT\((.*?),(.*?),/) { + $tracepointname = $2; + } + $tracepointname =~ s/^\s+//; #strip leading whitespace + if ($prototype =~ m/TP_PROTO\((.*?)\)/) { $tracepointargs = $1; } if (($tracepointname eq 0) || ($tracepointargs eq 0)) { @@ -1920,7 +1927,9 @@ sub process_state3_function($$) { if ($prototype =~ /SYSCALL_DEFINE/) { syscall_munge(); } - if ($prototype =~ /TRACE_EVENT/) { + if ($prototype =~ /TRACE_EVENT/ || $prototype =~ /DEFINE_EVENT/ || + $prototype =~ /DEFINE_SINGLE_EVENT/) + { tracepoint_munge($file); } dump_function($prototype, $file); diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl index 090d300d7394..f0d14452632b 100755 --- a/scripts/recordmcount.pl +++ b/scripts/recordmcount.pl @@ -6,77 +6,93 @@ # all the offsets to the calls to mcount. # # -# What we want to end up with is a section in vmlinux called -# __mcount_loc that contains a list of pointers to all the -# call sites in the kernel that call mcount. Later on boot up, the kernel -# will read this list, save the locations and turn them into nops. -# When tracing or profiling is later enabled, these locations will then -# be converted back to pointers to some function. +# What we want to end up with this is that each object file will have a +# section called __mcount_loc that will hold the list of pointers to mcount +# callers. After final linking, the vmlinux will have within .init.data the +# list of all callers to mcount between __start_mcount_loc and __stop_mcount_loc. +# Later on boot up, the kernel will read this list, save the locations and turn +# them into nops. When tracing or profiling is later enabled, these locations +# will then be converted back to pointers to some function. # # This is no easy feat. This script is called just after the original # object is compiled and before it is linked. # -# The references to the call sites are offsets from the section of text -# that the call site is in. Hence, all functions in a section that -# has a call site to mcount, will have the offset from the beginning of -# the section and not the beginning of the function. +# When parse this object file using 'objdump', the references to the call +# sites are offsets from the section that the call site is in. Hence, all +# functions in a section that has a call site to mcount, will have the +# offset from the beginning of the section and not the beginning of the +# function. +# +# But where this section will reside finally in vmlinx is undetermined at +# this point. So we can't use this kind of offsets to record the final +# address of this call site. +# +# The trick is to change the call offset referring the start of a section to +# referring a function symbol in this section. During the link step, 'ld' will +# compute the final address according to the information we record. # -# The trick is to find a way to record the beginning of the section. -# The way we do this is to look at the first function in the section -# which will also be the location of that section after final link. # e.g. # # .section ".sched.text", "ax" -# .globl my_func -# my_func: # [...] -# call mcount (offset: 0x5) +# func1: +# [...] +# call mcount (offset: 0x10) # [...] # ret -# other_func: +# .globl fun2 +# func2: (offset: 0x20) # [...] -# call mcount (offset: 0x1b) +# [...] +# ret +# func3: +# [...] +# call mcount (offset: 0x30) # [...] # # Both relocation offsets for the mcounts in the above example will be -# offset from .sched.text. If we make another file called tmp.s with: +# offset from .sched.text. If we choose global symbol func2 as a reference and +# make another file called tmp.s with the new offsets: # # .section __mcount_loc -# .quad my_func + 0x5 -# .quad my_func + 0x1b +# .quad func2 - 0x10 +# .quad func2 + 0x10 # -# We can then compile this tmp.s into tmp.o, and link it to the original +# We can then compile this tmp.s into tmp.o, and link it back to the original # object. # -# But this gets hard if my_func is not globl (a static function). -# In such a case we have: +# In our algorithm, we will choose the first global function we meet in this +# section as the reference. But this gets hard if there is no global functions +# in this section. In such a case we have to select a local one. E.g. func1: # # .section ".sched.text", "ax" -# my_func: +# func1: # [...] -# call mcount (offset: 0x5) +# call mcount (offset: 0x10) # [...] # ret -# other_func: +# func2: # [...] -# call mcount (offset: 0x1b) +# call mcount (offset: 0x20) # [...] +# .section "other.section" # # If we make the tmp.s the same as above, when we link together with -# the original object, we will end up with two symbols for my_func: +# the original object, we will end up with two symbols for func1: # one local, one global. After final compile, we will end up with -# an undefined reference to my_func. +# an undefined reference to func1 or a wrong reference to another global +# func1 in other files. # # Since local objects can reference local variables, we need to find # a way to make tmp.o reference the local objects of the original object -# file after it is linked together. To do this, we convert the my_func +# file after it is linked together. To do this, we convert func1 # into a global symbol before linking tmp.o. Then after we link tmp.o -# we will only have a single symbol for my_func that is global. -# We can convert my_func back into a local symbol and we are done. +# we will only have a single symbol for func1 that is global. +# We can convert func1 back into a local symbol and we are done. # # Here are the steps we take: # -# 1) Record all the local symbols by using 'nm' +# 1) Record all the local and weak symbols by using 'nm' # 2) Use objdump to find all the call site offsets and sections for # mcount. # 3) Compile the list into its own object. @@ -86,10 +102,8 @@ # 6) Link together this new object with the list object. # 7) Convert the local functions back to local symbols and rename # the result as the original object. -# End. # 8) Link the object with the list object. # 9) Move the result back to the original object. -# End. # use strict; @@ -99,7 +113,7 @@ $P =~ s@.*/@@g; my $V = '0.1'; -if ($#ARGV < 7) { +if ($#ARGV != 10) { print "usage: $P arch bits objdump objcopy cc ld nm rm mv is_module inputfile\n"; print "version: $V\n"; exit(1); @@ -109,7 +123,7 @@ my ($arch, $bits, $objdump, $objcopy, $cc, $ld, $nm, $rm, $mv, $is_module, $inputfile) = @ARGV; # This file refers to mcount and shouldn't be ftraced, so lets' ignore it -if ($inputfile eq "kernel/trace/ftrace.o") { +if ($inputfile =~ m,kernel/trace/ftrace\.o$,) { exit(0); } @@ -119,6 +133,7 @@ my %text_sections = ( ".sched.text" => 1, ".spinlock.text" => 1, ".irqentry.text" => 1, + ".text.unlikely" => 1, ); $objdump = "objdump" if ((length $objdump) == 0); @@ -137,13 +152,47 @@ my %weak; # List of weak functions my %convert; # List of local functions used that needs conversion my $type; -my $nm_regex; # Find the local functions (return function) +my $local_regex; # Match a local function (return function) +my $weak_regex; # Match a weak function (return function) my $section_regex; # Find the start of a section my $function_regex; # Find the name of a function # (return offset and func name) my $mcount_regex; # Find the call site to mcount (return offset) my $alignment; # The .align value to use for $mcount_section my $section_type; # Section header plus possible alignment command +my $can_use_local = 0; # If we can use local function references + +# Shut up recordmcount if user has older objcopy +my $quiet_recordmcount = ".tmp_quiet_recordmcount"; +my $print_warning = 1; +$print_warning = 0 if ( -f $quiet_recordmcount); + +## +# check_objcopy - whether objcopy supports --globalize-symbols +# +# --globalize-symbols came out in 2.17, we must test the version +# of objcopy, and if it is less than 2.17, then we can not +# record local functions. +sub check_objcopy +{ + open (IN, "$objcopy --version |") or die "error running $objcopy"; + while (<IN>) { + if (/objcopy.*\s(\d+)\.(\d+)/) { + $can_use_local = 1 if ($1 > 2 || ($1 == 2 && $2 >= 17)); + last; + } + } + close (IN); + + if (!$can_use_local && $print_warning) { + print STDERR "WARNING: could not find objcopy version or version " . + "is less than 2.17.\n" . + "\tLocal function references are disabled.\n"; + open (QUIET, ">$quiet_recordmcount"); + printf QUIET "Disables the warning from recordmcount.pl\n"; + close QUIET; + } +} if ($arch eq "x86") { if ($bits == 64) { @@ -157,7 +206,8 @@ if ($arch eq "x86") { # We base the defaults off of i386, the other archs may # feel free to change them in the below if statements. # -$nm_regex = "^[0-9a-fA-F]+\\s+t\\s+(\\S+)"; +$local_regex = "^[0-9a-fA-F]+\\s+t\\s+(\\S+)"; +$weak_regex = "^[0-9a-fA-F]+\\s+([wW])\\s+(\\S+)"; $section_regex = "Disassembly of section\\s+(\\S+):"; $function_regex = "^([0-9a-fA-F]+)\\s+<(.*?)>:"; $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\smcount\$"; @@ -206,7 +256,7 @@ if ($arch eq "x86_64") { $cc .= " -m32"; } elsif ($arch eq "powerpc") { - $nm_regex = "^[0-9a-fA-F]+\\s+t\\s+(\\.?\\S+)"; + $local_regex = "^[0-9a-fA-F]+\\s+t\\s+(\\.?\\S+)"; $function_regex = "^([0-9a-fA-F]+)\\s+<(\\.?.*?)>:"; $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\s\\.?_mcount\$"; @@ -278,44 +328,17 @@ if ($filename =~ m,^(.*)(\.\S),) { my $mcount_s = $dirname . "/.tmp_mc_" . $prefix . ".s"; my $mcount_o = $dirname . "/.tmp_mc_" . $prefix . ".o"; -# -# --globalize-symbols came out in 2.17, we must test the version -# of objcopy, and if it is less than 2.17, then we can not -# record local functions. -my $use_locals = 01; -my $local_warn_once = 0; -my $found_version = 0; - -open (IN, "$objcopy --version |") || die "error running $objcopy"; -while (<IN>) { - if (/objcopy.*\s(\d+)\.(\d+)/) { - my $major = $1; - my $minor = $2; - - $found_version = 1; - if ($major < 2 || - ($major == 2 && $minor < 17)) { - $use_locals = 0; - } - last; - } -} -close (IN); - -if (!$found_version) { - print STDERR "WARNING: could not find objcopy version.\n" . - "\tDisabling local function references.\n"; -} +check_objcopy(); # # Step 1: find all the local (static functions) and weak symbols. -# 't' is local, 'w/W' is weak (we never use a weak function) +# 't' is local, 'w/W' is weak # open (IN, "$nm $inputfile|") || die "error running $nm"; while (<IN>) { - if (/$nm_regex/) { + if (/$local_regex/) { $locals{$1} = 1; - } elsif (/^[0-9a-fA-F]+\s+([wW])\s+(\S+)/) { + } elsif (/$weak_regex/) { $weak{$2} = $1; } } @@ -333,26 +356,20 @@ my $offset = 0; # offset of ref_func to section beginning # sub update_funcs { - return if ($#offsets < 0); - - defined($ref_func) || die "No function to reference"; + return unless ($ref_func and @offsets); - # A section only had a weak function, to represent it. - # Unfortunately, a weak function may be overwritten by another - # function of the same name, making all these offsets incorrect. - # To be safe, we simply print a warning and bail. + # Sanity check on weak function. A weak function may be overwritten by + # another function of the same name, making all these offsets incorrect. if (defined $weak{$ref_func}) { - print STDERR - "$inputfile: WARNING: referencing weak function" . + die "$inputfile: ERROR: referencing weak function" . " $ref_func for mcount\n"; - return; } # is this function static? If so, note this fact. if (defined $locals{$ref_func}) { # only use locals if objcopy supports globalize-symbols - if (!$use_locals) { + if (!$can_use_local) { return; } $convert{$ref_func} = 1; @@ -378,9 +395,27 @@ open(IN, "$objdump -hdr $inputfile|") || die "error running $objdump"; my $text; + +# read headers first my $read_headers = 1; while (<IN>) { + + if ($read_headers && /$mcount_section/) { + # + # Somehow the make process can execute this script on an + # object twice. If it does, we would duplicate the mcount + # section and it will cause the function tracer self test + # to fail. Check if the mcount section exists, and if it does, + # warn and exit. + # + print STDERR "ERROR: $mcount_section already in $inputfile\n" . + "\tThis may be an indication that your build is corrupted.\n" . + "\tDelete $inputfile and try again. If the same object file\n" . + "\tstill causes an issue, then disable CONFIG_DYNAMIC_FTRACE.\n"; + exit(-1); + } + # is it a section? if (/$section_regex/) { $read_headers = 0; @@ -392,7 +427,7 @@ while (<IN>) { $read_function = 0; } # print out any recorded offsets - update_funcs() if (defined($ref_func)); + update_funcs(); # reset all markers and arrays $text_found = 0; @@ -421,21 +456,7 @@ while (<IN>) { $offset = hex $1; } } - } elsif ($read_headers && /$mcount_section/) { - # - # Somehow the make process can execute this script on an - # object twice. If it does, we would duplicate the mcount - # section and it will cause the function tracer self test - # to fail. Check if the mcount section exists, and if it does, - # warn and exit. - # - print STDERR "ERROR: $mcount_section already in $inputfile\n" . - "\tThis may be an indication that your build is corrupted.\n" . - "\tDelete $inputfile and try again. If the same object file\n" . - "\tstill causes an issue, then disable CONFIG_DYNAMIC_FTRACE.\n"; - exit(-1); } - # is this a call site to mcount? If so, record it to print later if ($text_found && /$mcount_regex/) { $offsets[$#offsets + 1] = hex $1; @@ -443,7 +464,7 @@ while (<IN>) { } # dump out anymore offsets that may have been found -update_funcs() if (defined($ref_func)); +update_funcs(); # If we did not find any mcount callers, we are done (do nothing). if (!$opened) { diff --git a/scripts/selinux/Makefile b/scripts/selinux/Makefile index ca4b1ec01822..e8049da1831f 100644 --- a/scripts/selinux/Makefile +++ b/scripts/selinux/Makefile @@ -1,2 +1,2 @@ -subdir-y := mdp -subdir- += mdp +subdir-y := mdp genheaders +subdir- += mdp genheaders diff --git a/scripts/selinux/genheaders/.gitignore b/scripts/selinux/genheaders/.gitignore new file mode 100644 index 000000000000..4c0b646ff8d5 --- /dev/null +++ b/scripts/selinux/genheaders/.gitignore @@ -0,0 +1 @@ +genheaders diff --git a/scripts/selinux/genheaders/Makefile b/scripts/selinux/genheaders/Makefile new file mode 100644 index 000000000000..417b165008ee --- /dev/null +++ b/scripts/selinux/genheaders/Makefile @@ -0,0 +1,5 @@ +hostprogs-y := genheaders +HOST_EXTRACFLAGS += -Isecurity/selinux/include + +always := $(hostprogs-y) +clean-files := $(hostprogs-y) diff --git a/scripts/selinux/genheaders/genheaders.c b/scripts/selinux/genheaders/genheaders.c new file mode 100644 index 000000000000..24626968055d --- /dev/null +++ b/scripts/selinux/genheaders/genheaders.c @@ -0,0 +1,118 @@ +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <string.h> +#include <errno.h> +#include <ctype.h> + +struct security_class_mapping { + const char *name; + const char *perms[sizeof(unsigned) * 8 + 1]; +}; + +#include "classmap.h" +#include "initial_sid_to_string.h" + +#define max(x, y) (((int)(x) > (int)(y)) ? x : y) + +const char *progname; + +static void usage(void) +{ + printf("usage: %s flask.h av_permissions.h\n", progname); + exit(1); +} + +static char *stoupperx(const char *s) +{ + char *s2 = strdup(s); + char *p; + + if (!s2) { + fprintf(stderr, "%s: out of memory\n", progname); + exit(3); + } + + for (p = s2; *p; p++) + *p = toupper(*p); + return s2; +} + +int main(int argc, char *argv[]) +{ + int i, j, k; + int isids_len; + FILE *fout; + + progname = argv[0]; + + if (argc < 3) + usage(); + + fout = fopen(argv[1], "w"); + if (!fout) { + fprintf(stderr, "Could not open %s for writing: %s\n", + argv[1], strerror(errno)); + exit(2); + } + + for (i = 0; secclass_map[i].name; i++) { + struct security_class_mapping *map = &secclass_map[i]; + map->name = stoupperx(map->name); + for (j = 0; map->perms[j]; j++) + map->perms[j] = stoupperx(map->perms[j]); + } + + isids_len = sizeof(initial_sid_to_string) / sizeof (char *); + for (i = 1; i < isids_len; i++) + initial_sid_to_string[i] = stoupperx(initial_sid_to_string[i]); + + fprintf(fout, "/* This file is automatically generated. Do not edit. */\n"); + fprintf(fout, "#ifndef _SELINUX_FLASK_H_\n#define _SELINUX_FLASK_H_\n\n"); + + for (i = 0; secclass_map[i].name; i++) { + struct security_class_mapping *map = &secclass_map[i]; + fprintf(fout, "#define SECCLASS_%s", map->name); + for (j = 0; j < max(1, 40 - strlen(map->name)); j++) + fprintf(fout, " "); + fprintf(fout, "%2d\n", i+1); + } + + fprintf(fout, "\n"); + + for (i = 1; i < isids_len; i++) { + char *s = initial_sid_to_string[i]; + fprintf(fout, "#define SECINITSID_%s", s); + for (j = 0; j < max(1, 40 - strlen(s)); j++) + fprintf(fout, " "); + fprintf(fout, "%2d\n", i); + } + fprintf(fout, "\n#define SECINITSID_NUM %d\n", i-1); + fprintf(fout, "\n#endif\n"); + fclose(fout); + + fout = fopen(argv[2], "w"); + if (!fout) { + fprintf(stderr, "Could not open %s for writing: %s\n", + argv[2], strerror(errno)); + exit(4); + } + + fprintf(fout, "/* This file is automatically generated. Do not edit. */\n"); + fprintf(fout, "#ifndef _SELINUX_AV_PERMISSIONS_H_\n#define _SELINUX_AV_PERMISSIONS_H_\n\n"); + + for (i = 0; secclass_map[i].name; i++) { + struct security_class_mapping *map = &secclass_map[i]; + for (j = 0; map->perms[j]; j++) { + fprintf(fout, "#define %s__%s", map->name, + map->perms[j]); + for (k = 0; k < max(1, 40 - strlen(map->name) - strlen(map->perms[j])); k++) + fprintf(fout, " "); + fprintf(fout, "0x%08xUL\n", (1<<j)); + } + } + + fprintf(fout, "\n#endif\n"); + fclose(fout); + exit(0); +} diff --git a/scripts/selinux/mdp/mdp.c b/scripts/selinux/mdp/mdp.c index b4ced8562587..62b34ce1f50d 100644 --- a/scripts/selinux/mdp/mdp.c +++ b/scripts/selinux/mdp/mdp.c @@ -29,86 +29,27 @@ #include <unistd.h> #include <string.h> -#include "flask.h" - static void usage(char *name) { printf("usage: %s [-m] policy_file context_file\n", name); exit(1); } -static void find_common_name(char *cname, char *dest, int len) -{ - char *start, *end; - - start = strchr(cname, '_')+1; - end = strchr(start, '_'); - if (!start || !end || start-cname > len || end-start > len) { - printf("Error with commons defines\n"); - exit(1); - } - strncpy(dest, start, end-start); - dest[end-start] = '\0'; -} - -#define S_(x) x, -static char *classlist[] = { -#include "class_to_string.h" - NULL +/* Class/perm mapping support */ +struct security_class_mapping { + const char *name; + const char *perms[sizeof(unsigned) * 8 + 1]; }; -#undef S_ +#include "classmap.h" #include "initial_sid_to_string.h" -#define TB_(x) char *x[] = { -#define TE_(x) NULL }; -#define S_(x) x, -#include "common_perm_to_string.h" -#undef TB_ -#undef TE_ -#undef S_ - -struct common { - char *cname; - char **perms; -}; -struct common common[] = { -#define TB_(x) { #x, x }, -#define S_(x) -#define TE_(x) -#include "common_perm_to_string.h" -#undef TB_ -#undef TE_ -#undef S_ -}; - -#define S_(x, y, z) {x, #y}, -struct av_inherit { - int class; - char *common; -}; -struct av_inherit av_inherit[] = { -#include "av_inherit.h" -}; -#undef S_ - -#include "av_permissions.h" -#define S_(x, y, z) {x, y, z}, -struct av_perms { - int class; - int perm_i; - char *perm_s; -}; -struct av_perms av_perms[] = { -#include "av_perm_to_string.h" -}; -#undef S_ - int main(int argc, char *argv[]) { int i, j, mls = 0; + int initial_sid_to_string_len; char **arg, *polout, *ctxout; - int classlist_len, initial_sid_to_string_len; + FILE *fout; if (argc < 3) @@ -127,64 +68,25 @@ int main(int argc, char *argv[]) usage(argv[0]); } - classlist_len = sizeof(classlist) / sizeof(char *); /* print out the classes */ - for (i=1; i < classlist_len; i++) { - if(classlist[i]) - fprintf(fout, "class %s\n", classlist[i]); - else - fprintf(fout, "class user%d\n", i); - } + for (i = 0; secclass_map[i].name; i++) + fprintf(fout, "class %s\n", secclass_map[i].name); fprintf(fout, "\n"); initial_sid_to_string_len = sizeof(initial_sid_to_string) / sizeof (char *); /* print out the sids */ - for (i=1; i < initial_sid_to_string_len; i++) + for (i = 1; i < initial_sid_to_string_len; i++) fprintf(fout, "sid %s\n", initial_sid_to_string[i]); fprintf(fout, "\n"); - /* print out the commons */ - for (i=0; i< sizeof(common)/sizeof(struct common); i++) { - char cname[101]; - find_common_name(common[i].cname, cname, 100); - cname[100] = '\0'; - fprintf(fout, "common %s\n{\n", cname); - for (j=0; common[i].perms[j]; j++) - fprintf(fout, "\t%s\n", common[i].perms[j]); - fprintf(fout, "}\n\n"); - } - fprintf(fout, "\n"); - /* print out the class permissions */ - for (i=1; i < classlist_len; i++) { - if (classlist[i]) { - int firstperm = -1, numperms = 0; - - fprintf(fout, "class %s\n", classlist[i]); - /* does it inherit from a common? */ - for (j=0; j < sizeof(av_inherit)/sizeof(struct av_inherit); j++) - if (av_inherit[j].class == i) - fprintf(fout, "inherits %s\n", av_inherit[j].common); - - for (j=0; j < sizeof(av_perms)/sizeof(struct av_perms); j++) { - if (av_perms[j].class == i) { - if (firstperm == -1) - firstperm = j; - numperms++; - } - } - if (!numperms) { - fprintf(fout, "\n"); - continue; - } - - fprintf(fout, "{\n"); - /* print out the av_perms */ - for (j=0; j < numperms; j++) { - fprintf(fout, "\t%s\n", av_perms[firstperm+j].perm_s); - } - fprintf(fout, "}\n\n"); - } + for (i = 0; secclass_map[i].name; i++) { + struct security_class_mapping *map = &secclass_map[i]; + fprintf(fout, "class %s\n", map->name); + fprintf(fout, "{\n"); + for (j = 0; map->perms[j]; j++) + fprintf(fout, "\t%s\n", map->perms[j]); + fprintf(fout, "}\n\n"); } fprintf(fout, "\n"); @@ -197,31 +99,34 @@ int main(int argc, char *argv[]) /* types, roles, and allows */ fprintf(fout, "type base_t;\n"); fprintf(fout, "role base_r types { base_t };\n"); - for (i=1; i < classlist_len; i++) { - if (classlist[i]) - fprintf(fout, "allow base_t base_t:%s *;\n", classlist[i]); - else - fprintf(fout, "allow base_t base_t:user%d *;\n", i); - } + for (i = 0; secclass_map[i].name; i++) + fprintf(fout, "allow base_t base_t:%s *;\n", + secclass_map[i].name); fprintf(fout, "user user_u roles { base_r };\n"); fprintf(fout, "\n"); /* default sids */ - for (i=1; i < initial_sid_to_string_len; i++) + for (i = 1; i < initial_sid_to_string_len; i++) fprintf(fout, "sid %s user_u:base_r:base_t\n", initial_sid_to_string[i]); fprintf(fout, "\n"); - fprintf(fout, "fs_use_xattr ext2 user_u:base_r:base_t;\n"); fprintf(fout, "fs_use_xattr ext3 user_u:base_r:base_t;\n"); + fprintf(fout, "fs_use_xattr ext4 user_u:base_r:base_t;\n"); fprintf(fout, "fs_use_xattr jfs user_u:base_r:base_t;\n"); fprintf(fout, "fs_use_xattr xfs user_u:base_r:base_t;\n"); fprintf(fout, "fs_use_xattr reiserfs user_u:base_r:base_t;\n"); + fprintf(fout, "fs_use_xattr jffs2 user_u:base_r:base_t;\n"); + fprintf(fout, "fs_use_xattr gfs2 user_u:base_r:base_t;\n"); + fprintf(fout, "fs_use_xattr lustre user_u:base_r:base_t;\n"); + fprintf(fout, "fs_use_task eventpollfs user_u:base_r:base_t;\n"); fprintf(fout, "fs_use_task pipefs user_u:base_r:base_t;\n"); fprintf(fout, "fs_use_task sockfs user_u:base_r:base_t;\n"); + fprintf(fout, "fs_use_trans mqueue user_u:base_r:base_t;\n"); fprintf(fout, "fs_use_trans devpts user_u:base_r:base_t;\n"); + fprintf(fout, "fs_use_trans hugetlbfs user_u:base_r:base_t;\n"); fprintf(fout, "fs_use_trans tmpfs user_u:base_r:base_t;\n"); fprintf(fout, "fs_use_trans shm user_u:base_r:base_t;\n"); diff --git a/security/Kconfig b/security/Kconfig index fb363cd81cf6..226b9556b25f 100644 --- a/security/Kconfig +++ b/security/Kconfig @@ -91,28 +91,6 @@ config SECURITY_PATH implement pathname based access controls. If you are unsure how to answer this question, answer N. -config SECURITY_FILE_CAPABILITIES - bool "File POSIX Capabilities" - default n - help - This enables filesystem capabilities, allowing you to give - binaries a subset of root's powers without using setuid 0. - - If in doubt, answer N. - -config SECURITY_ROOTPLUG - bool "Root Plug Support" - depends on USB=y && SECURITY - help - This is a sample LSM module that should only be used as such. - It prevents any programs running with egid == 0 if a specific - USB device is not present in the system. - - See <http://www.linuxjournal.com/article.php?sid=6279> for - more information about this module. - - If you are unsure how to answer this question, answer N. - config INTEL_TXT bool "Enable Intel(R) Trusted Execution Technology (Intel(R) TXT)" depends on HAVE_INTEL_TXT @@ -165,5 +143,37 @@ source security/tomoyo/Kconfig source security/integrity/ima/Kconfig +choice + prompt "Default security module" + default DEFAULT_SECURITY_SELINUX if SECURITY_SELINUX + default DEFAULT_SECURITY_SMACK if SECURITY_SMACK + default DEFAULT_SECURITY_TOMOYO if SECURITY_TOMOYO + default DEFAULT_SECURITY_DAC + + help + Select the security module that will be used by default if the + kernel parameter security= is not specified. + + config DEFAULT_SECURITY_SELINUX + bool "SELinux" if SECURITY_SELINUX=y + + config DEFAULT_SECURITY_SMACK + bool "Simplified Mandatory Access Control" if SECURITY_SMACK=y + + config DEFAULT_SECURITY_TOMOYO + bool "TOMOYO" if SECURITY_TOMOYO=y + + config DEFAULT_SECURITY_DAC + bool "Unix Discretionary Access Controls" + +endchoice + +config DEFAULT_SECURITY + string + default "selinux" if DEFAULT_SECURITY_SELINUX + default "smack" if DEFAULT_SECURITY_SMACK + default "tomoyo" if DEFAULT_SECURITY_TOMOYO + default "" if DEFAULT_SECURITY_DAC + endmenu diff --git a/security/Makefile b/security/Makefile index 95ecc06392d7..bb44e350c618 100644 --- a/security/Makefile +++ b/security/Makefile @@ -18,7 +18,6 @@ obj-$(CONFIG_SECURITY_SELINUX) += selinux/built-in.o obj-$(CONFIG_SECURITY_SMACK) += smack/built-in.o obj-$(CONFIG_AUDIT) += lsm_audit.o obj-$(CONFIG_SECURITY_TOMOYO) += tomoyo/built-in.o -obj-$(CONFIG_SECURITY_ROOTPLUG) += root_plug.o obj-$(CONFIG_CGROUP_DEVICE) += device_cgroup.o # Object integrity file lists diff --git a/security/capability.c b/security/capability.c index fce07a7bc825..5c700e1a4fd3 100644 --- a/security/capability.c +++ b/security/capability.c @@ -308,6 +308,22 @@ static int cap_path_truncate(struct path *path, loff_t length, { return 0; } + +static int cap_path_chmod(struct dentry *dentry, struct vfsmount *mnt, + mode_t mode) +{ + return 0; +} + +static int cap_path_chown(struct path *path, uid_t uid, gid_t gid) +{ + return 0; +} + +static int cap_path_chroot(struct path *root) +{ + return 0; +} #endif static int cap_file_permission(struct file *file, int mask) @@ -405,7 +421,7 @@ static int cap_kernel_create_files_as(struct cred *new, struct inode *inode) return 0; } -static int cap_kernel_module_request(void) +static int cap_kernel_module_request(char *kmod_name) { return 0; } @@ -977,6 +993,9 @@ void security_fixup_ops(struct security_operations *ops) set_to_cap_if_null(ops, path_link); set_to_cap_if_null(ops, path_rename); set_to_cap_if_null(ops, path_truncate); + set_to_cap_if_null(ops, path_chmod); + set_to_cap_if_null(ops, path_chown); + set_to_cap_if_null(ops, path_chroot); #endif set_to_cap_if_null(ops, file_permission); set_to_cap_if_null(ops, file_alloc_security); diff --git a/security/commoncap.c b/security/commoncap.c index fe30751a6cd9..f800fdb3de94 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -1,4 +1,4 @@ -/* Common capabilities, needed by capability.o and root_plug.o +/* Common capabilities, needed by capability.o. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -173,7 +173,6 @@ int cap_capget(struct task_struct *target, kernel_cap_t *effective, */ static inline int cap_inh_is_capped(void) { -#ifdef CONFIG_SECURITY_FILE_CAPABILITIES /* they are so limited unless the current task has the CAP_SETPCAP * capability @@ -181,7 +180,6 @@ static inline int cap_inh_is_capped(void) if (cap_capable(current, current_cred(), CAP_SETPCAP, SECURITY_CAP_AUDIT) == 0) return 0; -#endif return 1; } @@ -239,8 +237,6 @@ static inline void bprm_clear_caps(struct linux_binprm *bprm) bprm->cap_effective = false; } -#ifdef CONFIG_SECURITY_FILE_CAPABILITIES - /** * cap_inode_need_killpriv - Determine if inode change affects privileges * @dentry: The inode/dentry in being changed with change marked ATTR_KILL_PRIV @@ -421,49 +417,6 @@ out: return rc; } -#else -int cap_inode_need_killpriv(struct dentry *dentry) -{ - return 0; -} - -int cap_inode_killpriv(struct dentry *dentry) -{ - return 0; -} - -int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps) -{ - memset(cpu_caps, 0, sizeof(struct cpu_vfs_cap_data)); - return -ENODATA; -} - -static inline int get_file_caps(struct linux_binprm *bprm, bool *effective) -{ - bprm_clear_caps(bprm); - return 0; -} -#endif - -/* - * Determine whether a exec'ing process's new permitted capabilities should be - * limited to just what it already has. - * - * This prevents processes that are being ptraced from gaining access to - * CAP_SETPCAP, unless the process they're tracing already has it, and the - * binary they're executing has filecaps that elevate it. - * - * Returns 1 if they should be limited, 0 if they are not. - */ -static inline int cap_limit_ptraced_target(void) -{ -#ifndef CONFIG_SECURITY_FILE_CAPABILITIES - if (capable(CAP_SETPCAP)) - return 0; -#endif - return 1; -} - /** * cap_bprm_set_creds - Set up the proposed credentials for execve(). * @bprm: The execution parameters, including the proposed creds @@ -523,9 +476,8 @@ skip: new->euid = new->uid; new->egid = new->gid; } - if (cap_limit_ptraced_target()) - new->cap_permitted = cap_intersect(new->cap_permitted, - old->cap_permitted); + new->cap_permitted = cap_intersect(new->cap_permitted, + old->cap_permitted); } new->suid = new->fsuid = new->euid; @@ -739,7 +691,6 @@ int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags) return 0; } -#ifdef CONFIG_SECURITY_FILE_CAPABILITIES /* * Rationale: code calling task_setscheduler, task_setioprio, and * task_setnice, assumes that @@ -820,22 +771,6 @@ static long cap_prctl_drop(struct cred *new, unsigned long cap) return 0; } -#else -int cap_task_setscheduler (struct task_struct *p, int policy, - struct sched_param *lp) -{ - return 0; -} -int cap_task_setioprio (struct task_struct *p, int ioprio) -{ - return 0; -} -int cap_task_setnice (struct task_struct *p, int nice) -{ - return 0; -} -#endif - /** * cap_task_prctl - Implement process control functions for this security module * @option: The process control function requested @@ -866,7 +801,6 @@ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3, error = !!cap_raised(new->cap_bset, arg2); goto no_change; -#ifdef CONFIG_SECURITY_FILE_CAPABILITIES case PR_CAPBSET_DROP: error = cap_prctl_drop(new, arg2); if (error < 0) @@ -917,8 +851,6 @@ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3, error = new->securebits; goto no_change; -#endif /* def CONFIG_SECURITY_FILE_CAPABILITIES */ - case PR_GET_KEEPCAPS: if (issecure(SECURE_KEEP_CAPS)) error = 1; diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig index 53d9764e8f09..3d7846de8069 100644 --- a/security/integrity/ima/Kconfig +++ b/security/integrity/ima/Kconfig @@ -3,6 +3,7 @@ config IMA bool "Integrity Measurement Architecture(IMA)" depends on ACPI + depends on SECURITY select SECURITYFS select CRYPTO select CRYPTO_HMAC diff --git a/security/keys/sysctl.c b/security/keys/sysctl.c index 5e05dc09e2db..ee32d181764a 100644 --- a/security/keys/sysctl.c +++ b/security/keys/sysctl.c @@ -17,54 +17,49 @@ static const int zero, one = 1, max = INT_MAX; ctl_table key_sysctls[] = { { - .ctl_name = CTL_UNNUMBERED, .procname = "maxkeys", .data = &key_quota_maxkeys, .maxlen = sizeof(unsigned), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, + .proc_handler = proc_dointvec_minmax, .extra1 = (void *) &one, .extra2 = (void *) &max, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "maxbytes", .data = &key_quota_maxbytes, .maxlen = sizeof(unsigned), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, + .proc_handler = proc_dointvec_minmax, .extra1 = (void *) &one, .extra2 = (void *) &max, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "root_maxkeys", .data = &key_quota_root_maxkeys, .maxlen = sizeof(unsigned), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, + .proc_handler = proc_dointvec_minmax, .extra1 = (void *) &one, .extra2 = (void *) &max, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "root_maxbytes", .data = &key_quota_root_maxbytes, .maxlen = sizeof(unsigned), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, + .proc_handler = proc_dointvec_minmax, .extra1 = (void *) &one, .extra2 = (void *) &max, }, { - .ctl_name = CTL_UNNUMBERED, .procname = "gc_delay", .data = &key_gc_delay, .maxlen = sizeof(unsigned), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, + .proc_handler = proc_dointvec_minmax, .extra1 = (void *) &zero, .extra2 = (void *) &max, }, - { .ctl_name = 0 } + { } }; diff --git a/security/lsm_audit.c b/security/lsm_audit.c index 3bb90b6f1dd3..51bd0fd9c9f0 100644 --- a/security/lsm_audit.c +++ b/security/lsm_audit.c @@ -354,6 +354,10 @@ static void dump_common_audit_data(struct audit_buffer *ab, } break; #endif + case LSM_AUDIT_DATA_KMOD: + audit_log_format(ab, " kmod="); + audit_log_untrustedstring(ab, a->u.kmod_name); + break; } /* switch (a->type) */ } diff --git a/security/min_addr.c b/security/min_addr.c index c844eed7915d..fc43c9d37084 100644 --- a/security/min_addr.c +++ b/security/min_addr.c @@ -33,6 +33,9 @@ int mmap_min_addr_handler(struct ctl_table *table, int write, { int ret; + if (!capable(CAP_SYS_RAWIO)) + return -EPERM; + ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); update_mmap_min_addr(); diff --git a/security/root_plug.c b/security/root_plug.c deleted file mode 100644 index 2f7ffa67c4d2..000000000000 --- a/security/root_plug.c +++ /dev/null @@ -1,90 +0,0 @@ -/* - * Root Plug sample LSM module - * - * Originally written for a Linux Journal. - * - * Copyright (C) 2002 Greg Kroah-Hartman <greg@kroah.com> - * - * Prevents any programs running with egid == 0 if a specific USB device - * is not present in the system. Yes, it can be gotten around, but is a - * nice starting point for people to play with, and learn the LSM - * interface. - * - * If you want to turn this into something with a semblance of security, - * you need to hook the task_* functions also. - * - * See http://www.linuxjournal.com/article.php?sid=6279 for more information - * about this code. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation, version 2 of the - * License. - */ - -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/security.h> -#include <linux/usb.h> -#include <linux/moduleparam.h> - -/* default is a generic type of usb to serial converter */ -static int vendor_id = 0x0557; -static int product_id = 0x2008; - -module_param(vendor_id, uint, 0400); -module_param(product_id, uint, 0400); - -/* should we print out debug messages */ -static int debug = 0; - -module_param(debug, bool, 0600); - -#define MY_NAME "root_plug" - -#define root_dbg(fmt, arg...) \ - do { \ - if (debug) \ - printk(KERN_DEBUG "%s: %s: " fmt , \ - MY_NAME , __func__ , \ - ## arg); \ - } while (0) - -static int rootplug_bprm_check_security (struct linux_binprm *bprm) -{ - struct usb_device *dev; - - root_dbg("file %s, e_uid = %d, e_gid = %d\n", - bprm->filename, bprm->cred->euid, bprm->cred->egid); - - if (bprm->cred->egid == 0) { - dev = usb_find_device(vendor_id, product_id); - if (!dev) { - root_dbg("e_gid = 0, and device not found, " - "task not allowed to run...\n"); - return -EPERM; - } - usb_put_dev(dev); - } - - return 0; -} - -static struct security_operations rootplug_security_ops = { - .bprm_check_security = rootplug_bprm_check_security, -}; - -static int __init rootplug_init (void) -{ - /* register ourselves with the security framework */ - if (register_security (&rootplug_security_ops)) { - printk (KERN_INFO - "Failure registering Root Plug module with the kernel\n"); - return -EINVAL; - } - printk (KERN_INFO "Root Plug module initialized, " - "vendor_id = %4.4x, product id = %4.4x\n", vendor_id, product_id); - return 0; -} - -security_initcall (rootplug_init); diff --git a/security/security.c b/security/security.c index c4c673240c1c..24e060be9fa5 100644 --- a/security/security.c +++ b/security/security.c @@ -16,9 +16,11 @@ #include <linux/init.h> #include <linux/kernel.h> #include <linux/security.h> +#include <linux/ima.h> /* Boot-time LSM user choice */ -static __initdata char chosen_lsm[SECURITY_NAME_MAX + 1]; +static __initdata char chosen_lsm[SECURITY_NAME_MAX + 1] = + CONFIG_DEFAULT_SECURITY; /* things that live in capability.c */ extern struct security_operations default_security_ops; @@ -79,8 +81,10 @@ __setup("security=", choose_lsm); * * Return true if: * -The passed LSM is the one chosen by user at boot time, - * -or user didn't specify a specific LSM and we're the first to ask - * for registration permission, + * -or the passed LSM is configured as the default and the user did not + * choose an alternate LSM at boot time, + * -or there is no default LSM set and the user didn't specify a + * specific LSM and we're the first to ask for registration permission, * -or the passed LSM is currently loaded. * Otherwise, return false. */ @@ -235,7 +239,12 @@ int security_bprm_set_creds(struct linux_binprm *bprm) int security_bprm_check(struct linux_binprm *bprm) { - return security_ops->bprm_check_security(bprm); + int ret; + + ret = security_ops->bprm_check_security(bprm); + if (ret) + return ret; + return ima_bprm_check(bprm); } void security_bprm_committing_creds(struct linux_binprm *bprm) @@ -352,12 +361,21 @@ EXPORT_SYMBOL(security_sb_parse_opts_str); int security_inode_alloc(struct inode *inode) { + int ret; + inode->i_security = NULL; - return security_ops->inode_alloc_security(inode); + ret = security_ops->inode_alloc_security(inode); + if (ret) + return ret; + ret = ima_inode_alloc(inode); + if (ret) + security_inode_free(inode); + return ret; } void security_inode_free(struct inode *inode) { + ima_inode_free(inode); security_ops->inode_free_security(inode); } @@ -434,6 +452,26 @@ int security_path_truncate(struct path *path, loff_t length, return 0; return security_ops->path_truncate(path, length, time_attrs); } + +int security_path_chmod(struct dentry *dentry, struct vfsmount *mnt, + mode_t mode) +{ + if (unlikely(IS_PRIVATE(dentry->d_inode))) + return 0; + return security_ops->path_chmod(dentry, mnt, mode); +} + +int security_path_chown(struct path *path, uid_t uid, gid_t gid) +{ + if (unlikely(IS_PRIVATE(path->dentry->d_inode))) + return 0; + return security_ops->path_chown(path, uid, gid); +} + +int security_path_chroot(struct path *path) +{ + return security_ops->path_chroot(path); +} #endif int security_inode_create(struct inode *dir, struct dentry *dentry, int mode) @@ -628,6 +666,8 @@ int security_file_alloc(struct file *file) void security_file_free(struct file *file) { security_ops->file_free_security(file); + if (file->f_dentry) + ima_file_free(file); } int security_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) @@ -639,7 +679,12 @@ int security_file_mmap(struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags, unsigned long addr, unsigned long addr_only) { - return security_ops->file_mmap(file, reqprot, prot, flags, addr, addr_only); + int ret; + + ret = security_ops->file_mmap(file, reqprot, prot, flags, addr, addr_only); + if (ret) + return ret; + return ima_file_mmap(file, prot); } int security_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, @@ -719,9 +764,9 @@ int security_kernel_create_files_as(struct cred *new, struct inode *inode) return security_ops->kernel_create_files_as(new, inode); } -int security_kernel_module_request(void) +int security_kernel_module_request(char *kmod_name) { - return security_ops->kernel_module_request(); + return security_ops->kernel_module_request(kmod_name); } int security_task_setuid(uid_t id0, uid_t id1, uid_t id2, int flags) diff --git a/security/selinux/.gitignore b/security/selinux/.gitignore new file mode 100644 index 000000000000..2e5040a3d48b --- /dev/null +++ b/security/selinux/.gitignore @@ -0,0 +1,2 @@ +av_permissions.h +flask.h diff --git a/security/selinux/Makefile b/security/selinux/Makefile index d47fc5e545e0..f013982df417 100644 --- a/security/selinux/Makefile +++ b/security/selinux/Makefile @@ -18,5 +18,13 @@ selinux-$(CONFIG_SECURITY_NETWORK_XFRM) += xfrm.o selinux-$(CONFIG_NETLABEL) += netlabel.o -EXTRA_CFLAGS += -Isecurity/selinux/include +EXTRA_CFLAGS += -Isecurity/selinux -Isecurity/selinux/include +$(obj)/avc.o: $(obj)/flask.h + +quiet_cmd_flask = GEN $(obj)/flask.h $(obj)/av_permissions.h + cmd_flask = scripts/selinux/genheaders/genheaders $(obj)/flask.h $(obj)/av_permissions.h + +targets += flask.h +$(obj)/flask.h: $(src)/include/classmap.h FORCE + $(call if_changed,flask) diff --git a/security/selinux/avc.c b/security/selinux/avc.c index b4b5da1c0a42..f2dde268165a 100644 --- a/security/selinux/avc.c +++ b/security/selinux/avc.c @@ -31,43 +31,7 @@ #include <net/ipv6.h> #include "avc.h" #include "avc_ss.h" - -static const struct av_perm_to_string av_perm_to_string[] = { -#define S_(c, v, s) { c, v, s }, -#include "av_perm_to_string.h" -#undef S_ -}; - -static const char *class_to_string[] = { -#define S_(s) s, -#include "class_to_string.h" -#undef S_ -}; - -#define TB_(s) static const char *s[] = { -#define TE_(s) }; -#define S_(s) s, -#include "common_perm_to_string.h" -#undef TB_ -#undef TE_ -#undef S_ - -static const struct av_inherit av_inherit[] = { -#define S_(c, i, b) { .tclass = c,\ - .common_pts = common_##i##_perm_to_string,\ - .common_base = b }, -#include "av_inherit.h" -#undef S_ -}; - -const struct selinux_class_perm selinux_class_perm = { - .av_perm_to_string = av_perm_to_string, - .av_pts_len = ARRAY_SIZE(av_perm_to_string), - .class_to_string = class_to_string, - .cts_len = ARRAY_SIZE(class_to_string), - .av_inherit = av_inherit, - .av_inherit_len = ARRAY_SIZE(av_inherit) -}; +#include "classmap.h" #define AVC_CACHE_SLOTS 512 #define AVC_DEF_CACHE_THRESHOLD 512 @@ -139,52 +103,28 @@ static inline int avc_hash(u32 ssid, u32 tsid, u16 tclass) */ static void avc_dump_av(struct audit_buffer *ab, u16 tclass, u32 av) { - const char **common_pts = NULL; - u32 common_base = 0; - int i, i2, perm; + const char **perms; + int i, perm; if (av == 0) { audit_log_format(ab, " null"); return; } - for (i = 0; i < ARRAY_SIZE(av_inherit); i++) { - if (av_inherit[i].tclass == tclass) { - common_pts = av_inherit[i].common_pts; - common_base = av_inherit[i].common_base; - break; - } - } + perms = secclass_map[tclass-1].perms; audit_log_format(ab, " {"); i = 0; perm = 1; - while (perm < common_base) { - if (perm & av) { - audit_log_format(ab, " %s", common_pts[i]); + while (i < (sizeof(av) * 8)) { + if ((perm & av) && perms[i]) { + audit_log_format(ab, " %s", perms[i]); av &= ~perm; } i++; perm <<= 1; } - while (i < sizeof(av) * 8) { - if (perm & av) { - for (i2 = 0; i2 < ARRAY_SIZE(av_perm_to_string); i2++) { - if ((av_perm_to_string[i2].tclass == tclass) && - (av_perm_to_string[i2].value == perm)) - break; - } - if (i2 < ARRAY_SIZE(av_perm_to_string)) { - audit_log_format(ab, " %s", - av_perm_to_string[i2].name); - av &= ~perm; - } - } - i++; - perm <<= 1; - } - if (av) audit_log_format(ab, " 0x%x", av); @@ -219,8 +159,8 @@ static void avc_dump_query(struct audit_buffer *ab, u32 ssid, u32 tsid, u16 tcla kfree(scontext); } - BUG_ON(tclass >= ARRAY_SIZE(class_to_string) || !class_to_string[tclass]); - audit_log_format(ab, " tclass=%s", class_to_string[tclass]); + BUG_ON(tclass >= ARRAY_SIZE(secclass_map)); + audit_log_format(ab, " tclass=%s", secclass_map[tclass-1].name); } /** diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index bb230d5d7085..c96d63ec4753 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -91,7 +91,6 @@ #define NUM_SEL_MNT_OPTS 5 -extern unsigned int policydb_loaded_version; extern int selinux_nlmsg_lookup(u16 sclass, u16 nlmsg_type, u32 *perm); extern struct security_operations *security_ops; @@ -3338,9 +3337,18 @@ static int selinux_kernel_create_files_as(struct cred *new, struct inode *inode) return 0; } -static int selinux_kernel_module_request(void) +static int selinux_kernel_module_request(char *kmod_name) { - return task_has_system(current, SYSTEM__MODULE_REQUEST); + u32 sid; + struct common_audit_data ad; + + sid = task_sid(current); + + COMMON_AUDIT_DATA_INIT(&ad, KMOD); + ad.u.kmod_name = kmod_name; + + return avc_has_perm(sid, SECINITSID_KERNEL, SECCLASS_SYSTEM, + SYSTEM__MODULE_REQUEST, &ad); } static int selinux_task_setpgid(struct task_struct *p, pid_t pgid) @@ -4714,10 +4722,7 @@ static int selinux_netlink_send(struct sock *sk, struct sk_buff *skb) if (err) return err; - if (policydb_loaded_version >= POLICYDB_VERSION_NLCLASS) - err = selinux_nlmsg_perm(sk, skb); - - return err; + return selinux_nlmsg_perm(sk, skb); } static int selinux_netlink_recv(struct sk_buff *skb, int capability) @@ -5830,12 +5835,12 @@ int selinux_disable(void) selinux_disabled = 1; selinux_enabled = 0; - /* Try to destroy the avc node cache */ - avc_disable(); - /* Reset security_ops to the secondary module, dummy or capability. */ security_ops = secondary_ops; + /* Try to destroy the avc node cache */ + avc_disable(); + /* Unregister netfilter hooks. */ selinux_nf_ip_exit(); diff --git a/security/selinux/include/av_inherit.h b/security/selinux/include/av_inherit.h deleted file mode 100644 index abedcd704dae..000000000000 --- a/security/selinux/include/av_inherit.h +++ /dev/null @@ -1,34 +0,0 @@ -/* This file is automatically generated. Do not edit. */ - S_(SECCLASS_DIR, file, 0x00020000UL) - S_(SECCLASS_FILE, file, 0x00020000UL) - S_(SECCLASS_LNK_FILE, file, 0x00020000UL) - S_(SECCLASS_CHR_FILE, file, 0x00020000UL) - S_(SECCLASS_BLK_FILE, file, 0x00020000UL) - S_(SECCLASS_SOCK_FILE, file, 0x00020000UL) - S_(SECCLASS_FIFO_FILE, file, 0x00020000UL) - S_(SECCLASS_SOCKET, socket, 0x00400000UL) - S_(SECCLASS_TCP_SOCKET, socket, 0x00400000UL) - S_(SECCLASS_UDP_SOCKET, socket, 0x00400000UL) - S_(SECCLASS_RAWIP_SOCKET, socket, 0x00400000UL) - S_(SECCLASS_NETLINK_SOCKET, socket, 0x00400000UL) - S_(SECCLASS_PACKET_SOCKET, socket, 0x00400000UL) - S_(SECCLASS_KEY_SOCKET, socket, 0x00400000UL) - S_(SECCLASS_UNIX_STREAM_SOCKET, socket, 0x00400000UL) - S_(SECCLASS_UNIX_DGRAM_SOCKET, socket, 0x00400000UL) - S_(SECCLASS_TUN_SOCKET, socket, 0x00400000UL) - S_(SECCLASS_IPC, ipc, 0x00000200UL) - S_(SECCLASS_SEM, ipc, 0x00000200UL) - S_(SECCLASS_MSGQ, ipc, 0x00000200UL) - S_(SECCLASS_SHM, ipc, 0x00000200UL) - S_(SECCLASS_NETLINK_ROUTE_SOCKET, socket, 0x00400000UL) - S_(SECCLASS_NETLINK_FIREWALL_SOCKET, socket, 0x00400000UL) - S_(SECCLASS_NETLINK_TCPDIAG_SOCKET, socket, 0x00400000UL) - S_(SECCLASS_NETLINK_NFLOG_SOCKET, socket, 0x00400000UL) - S_(SECCLASS_NETLINK_XFRM_SOCKET, socket, 0x00400000UL) - S_(SECCLASS_NETLINK_SELINUX_SOCKET, socket, 0x00400000UL) - S_(SECCLASS_NETLINK_AUDIT_SOCKET, socket, 0x00400000UL) - S_(SECCLASS_NETLINK_IP6FW_SOCKET, socket, 0x00400000UL) - S_(SECCLASS_NETLINK_DNRT_SOCKET, socket, 0x00400000UL) - S_(SECCLASS_NETLINK_KOBJECT_UEVENT_SOCKET, socket, 0x00400000UL) - S_(SECCLASS_APPLETALK_SOCKET, socket, 0x00400000UL) - S_(SECCLASS_DCCP_SOCKET, socket, 0x00400000UL) diff --git a/security/selinux/include/av_perm_to_string.h b/security/selinux/include/av_perm_to_string.h deleted file mode 100644 index 2b683ad83d21..000000000000 --- a/security/selinux/include/av_perm_to_string.h +++ /dev/null @@ -1,183 +0,0 @@ -/* This file is automatically generated. Do not edit. */ - S_(SECCLASS_FILESYSTEM, FILESYSTEM__MOUNT, "mount") - S_(SECCLASS_FILESYSTEM, FILESYSTEM__REMOUNT, "remount") - S_(SECCLASS_FILESYSTEM, FILESYSTEM__UNMOUNT, "unmount") - S_(SECCLASS_FILESYSTEM, FILESYSTEM__GETATTR, "getattr") - S_(SECCLASS_FILESYSTEM, FILESYSTEM__RELABELFROM, "relabelfrom") - S_(SECCLASS_FILESYSTEM, FILESYSTEM__RELABELTO, "relabelto") - S_(SECCLASS_FILESYSTEM, FILESYSTEM__TRANSITION, "transition") - S_(SECCLASS_FILESYSTEM, FILESYSTEM__ASSOCIATE, "associate") - S_(SECCLASS_FILESYSTEM, FILESYSTEM__QUOTAMOD, "quotamod") - S_(SECCLASS_FILESYSTEM, FILESYSTEM__QUOTAGET, "quotaget") - S_(SECCLASS_DIR, DIR__ADD_NAME, "add_name") - S_(SECCLASS_DIR, DIR__REMOVE_NAME, "remove_name") - S_(SECCLASS_DIR, DIR__REPARENT, "reparent") - S_(SECCLASS_DIR, DIR__SEARCH, "search") - S_(SECCLASS_DIR, DIR__RMDIR, "rmdir") - S_(SECCLASS_DIR, DIR__OPEN, "open") - S_(SECCLASS_FILE, FILE__EXECUTE_NO_TRANS, "execute_no_trans") - S_(SECCLASS_FILE, FILE__ENTRYPOINT, "entrypoint") - S_(SECCLASS_FILE, FILE__EXECMOD, "execmod") - S_(SECCLASS_FILE, FILE__OPEN, "open") - S_(SECCLASS_CHR_FILE, CHR_FILE__EXECUTE_NO_TRANS, "execute_no_trans") - S_(SECCLASS_CHR_FILE, CHR_FILE__ENTRYPOINT, "entrypoint") - S_(SECCLASS_CHR_FILE, CHR_FILE__EXECMOD, "execmod") - S_(SECCLASS_CHR_FILE, CHR_FILE__OPEN, "open") - S_(SECCLASS_BLK_FILE, BLK_FILE__OPEN, "open") - S_(SECCLASS_SOCK_FILE, SOCK_FILE__OPEN, "open") - S_(SECCLASS_FIFO_FILE, FIFO_FILE__OPEN, "open") - S_(SECCLASS_FD, FD__USE, "use") - S_(SECCLASS_TCP_SOCKET, TCP_SOCKET__CONNECTTO, "connectto") - S_(SECCLASS_TCP_SOCKET, TCP_SOCKET__NEWCONN, "newconn") - S_(SECCLASS_TCP_SOCKET, TCP_SOCKET__ACCEPTFROM, "acceptfrom") - S_(SECCLASS_TCP_SOCKET, TCP_SOCKET__NODE_BIND, "node_bind") - S_(SECCLASS_TCP_SOCKET, TCP_SOCKET__NAME_CONNECT, "name_connect") - S_(SECCLASS_UDP_SOCKET, UDP_SOCKET__NODE_BIND, "node_bind") - S_(SECCLASS_RAWIP_SOCKET, RAWIP_SOCKET__NODE_BIND, "node_bind") - S_(SECCLASS_NODE, NODE__TCP_RECV, "tcp_recv") - S_(SECCLASS_NODE, NODE__TCP_SEND, "tcp_send") - S_(SECCLASS_NODE, NODE__UDP_RECV, "udp_recv") - S_(SECCLASS_NODE, NODE__UDP_SEND, "udp_send") - S_(SECCLASS_NODE, NODE__RAWIP_RECV, "rawip_recv") - S_(SECCLASS_NODE, NODE__RAWIP_SEND, "rawip_send") - S_(SECCLASS_NODE, NODE__ENFORCE_DEST, "enforce_dest") - S_(SECCLASS_NODE, NODE__DCCP_RECV, "dccp_recv") - S_(SECCLASS_NODE, NODE__DCCP_SEND, "dccp_send") - S_(SECCLASS_NODE, NODE__RECVFROM, "recvfrom") - S_(SECCLASS_NODE, NODE__SENDTO, "sendto") - S_(SECCLASS_NETIF, NETIF__TCP_RECV, "tcp_recv") - S_(SECCLASS_NETIF, NETIF__TCP_SEND, "tcp_send") - S_(SECCLASS_NETIF, NETIF__UDP_RECV, "udp_recv") - S_(SECCLASS_NETIF, NETIF__UDP_SEND, "udp_send") - S_(SECCLASS_NETIF, NETIF__RAWIP_RECV, "rawip_recv") - S_(SECCLASS_NETIF, NETIF__RAWIP_SEND, "rawip_send") - S_(SECCLASS_NETIF, NETIF__DCCP_RECV, "dccp_recv") - S_(SECCLASS_NETIF, NETIF__DCCP_SEND, "dccp_send") - S_(SECCLASS_NETIF, NETIF__INGRESS, "ingress") - S_(SECCLASS_NETIF, NETIF__EGRESS, "egress") - S_(SECCLASS_UNIX_STREAM_SOCKET, UNIX_STREAM_SOCKET__CONNECTTO, "connectto") - S_(SECCLASS_UNIX_STREAM_SOCKET, UNIX_STREAM_SOCKET__NEWCONN, "newconn") - S_(SECCLASS_UNIX_STREAM_SOCKET, UNIX_STREAM_SOCKET__ACCEPTFROM, "acceptfrom") - S_(SECCLASS_PROCESS, PROCESS__FORK, "fork") - S_(SECCLASS_PROCESS, PROCESS__TRANSITION, "transition") - S_(SECCLASS_PROCESS, PROCESS__SIGCHLD, "sigchld") - S_(SECCLASS_PROCESS, PROCESS__SIGKILL, "sigkill") - S_(SECCLASS_PROCESS, PROCESS__SIGSTOP, "sigstop") - S_(SECCLASS_PROCESS, PROCESS__SIGNULL, "signull") - S_(SECCLASS_PROCESS, PROCESS__SIGNAL, "signal") - S_(SECCLASS_PROCESS, PROCESS__PTRACE, "ptrace") - S_(SECCLASS_PROCESS, PROCESS__GETSCHED, "getsched") - S_(SECCLASS_PROCESS, PROCESS__SETSCHED, "setsched") - S_(SECCLASS_PROCESS, PROCESS__GETSESSION, "getsession") - S_(SECCLASS_PROCESS, PROCESS__GETPGID, "getpgid") - S_(SECCLASS_PROCESS, PROCESS__SETPGID, "setpgid") - S_(SECCLASS_PROCESS, PROCESS__GETCAP, "getcap") - S_(SECCLASS_PROCESS, PROCESS__SETCAP, "setcap") - S_(SECCLASS_PROCESS, PROCESS__SHARE, "share") - S_(SECCLASS_PROCESS, PROCESS__GETATTR, "getattr") - S_(SECCLASS_PROCESS, PROCESS__SETEXEC, "setexec") - S_(SECCLASS_PROCESS, PROCESS__SETFSCREATE, "setfscreate") - S_(SECCLASS_PROCESS, PROCESS__NOATSECURE, "noatsecure") - S_(SECCLASS_PROCESS, PROCESS__SIGINH, "siginh") - S_(SECCLASS_PROCESS, PROCESS__SETRLIMIT, "setrlimit") - S_(SECCLASS_PROCESS, PROCESS__RLIMITINH, "rlimitinh") - S_(SECCLASS_PROCESS, PROCESS__DYNTRANSITION, "dyntransition") - S_(SECCLASS_PROCESS, PROCESS__SETCURRENT, "setcurrent") - S_(SECCLASS_PROCESS, PROCESS__EXECMEM, "execmem") - S_(SECCLASS_PROCESS, PROCESS__EXECSTACK, "execstack") - S_(SECCLASS_PROCESS, PROCESS__EXECHEAP, "execheap") - S_(SECCLASS_PROCESS, PROCESS__SETKEYCREATE, "setkeycreate") - S_(SECCLASS_PROCESS, PROCESS__SETSOCKCREATE, "setsockcreate") - S_(SECCLASS_MSGQ, MSGQ__ENQUEUE, "enqueue") - S_(SECCLASS_MSG, MSG__SEND, "send") - S_(SECCLASS_MSG, MSG__RECEIVE, "receive") - S_(SECCLASS_SHM, SHM__LOCK, "lock") - S_(SECCLASS_SECURITY, SECURITY__COMPUTE_AV, "compute_av") - S_(SECCLASS_SECURITY, SECURITY__COMPUTE_CREATE, "compute_create") - S_(SECCLASS_SECURITY, SECURITY__COMPUTE_MEMBER, "compute_member") - S_(SECCLASS_SECURITY, SECURITY__CHECK_CONTEXT, "check_context") - S_(SECCLASS_SECURITY, SECURITY__LOAD_POLICY, "load_policy") - S_(SECCLASS_SECURITY, SECURITY__COMPUTE_RELABEL, "compute_relabel") - S_(SECCLASS_SECURITY, SECURITY__COMPUTE_USER, "compute_user") - S_(SECCLASS_SECURITY, SECURITY__SETENFORCE, "setenforce") - S_(SECCLASS_SECURITY, SECURITY__SETBOOL, "setbool") - S_(SECCLASS_SECURITY, SECURITY__SETSECPARAM, "setsecparam") - S_(SECCLASS_SECURITY, SECURITY__SETCHECKREQPROT, "setcheckreqprot") - S_(SECCLASS_SYSTEM, SYSTEM__IPC_INFO, "ipc_info") - S_(SECCLASS_SYSTEM, SYSTEM__SYSLOG_READ, "syslog_read") - S_(SECCLASS_SYSTEM, SYSTEM__SYSLOG_MOD, "syslog_mod") - S_(SECCLASS_SYSTEM, SYSTEM__SYSLOG_CONSOLE, "syslog_console") - S_(SECCLASS_SYSTEM, SYSTEM__MODULE_REQUEST, "module_request") - S_(SECCLASS_CAPABILITY, CAPABILITY__CHOWN, "chown") - S_(SECCLASS_CAPABILITY, CAPABILITY__DAC_OVERRIDE, "dac_override") - S_(SECCLASS_CAPABILITY, CAPABILITY__DAC_READ_SEARCH, "dac_read_search") - S_(SECCLASS_CAPABILITY, CAPABILITY__FOWNER, "fowner") - S_(SECCLASS_CAPABILITY, CAPABILITY__FSETID, "fsetid") - S_(SECCLASS_CAPABILITY, CAPABILITY__KILL, "kill") - S_(SECCLASS_CAPABILITY, CAPABILITY__SETGID, "setgid") - S_(SECCLASS_CAPABILITY, CAPABILITY__SETUID, "setuid") - S_(SECCLASS_CAPABILITY, CAPABILITY__SETPCAP, "setpcap") - S_(SECCLASS_CAPABILITY, CAPABILITY__LINUX_IMMUTABLE, "linux_immutable") - S_(SECCLASS_CAPABILITY, CAPABILITY__NET_BIND_SERVICE, "net_bind_service") - S_(SECCLASS_CAPABILITY, CAPABILITY__NET_BROADCAST, "net_broadcast") - S_(SECCLASS_CAPABILITY, CAPABILITY__NET_ADMIN, "net_admin") - S_(SECCLASS_CAPABILITY, CAPABILITY__NET_RAW, "net_raw") - S_(SECCLASS_CAPABILITY, CAPABILITY__IPC_LOCK, "ipc_lock") - S_(SECCLASS_CAPABILITY, CAPABILITY__IPC_OWNER, "ipc_owner") - S_(SECCLASS_CAPABILITY, CAPABILITY__SYS_MODULE, "sys_module") - S_(SECCLASS_CAPABILITY, CAPABILITY__SYS_RAWIO, "sys_rawio") - S_(SECCLASS_CAPABILITY, CAPABILITY__SYS_CHROOT, "sys_chroot") - S_(SECCLASS_CAPABILITY, CAPABILITY__SYS_PTRACE, "sys_ptrace") - S_(SECCLASS_CAPABILITY, CAPABILITY__SYS_PACCT, "sys_pacct") - S_(SECCLASS_CAPABILITY, CAPABILITY__SYS_ADMIN, "sys_admin") - S_(SECCLASS_CAPABILITY, CAPABILITY__SYS_BOOT, "sys_boot") - S_(SECCLASS_CAPABILITY, CAPABILITY__SYS_NICE, "sys_nice") - S_(SECCLASS_CAPABILITY, CAPABILITY__SYS_RESOURCE, "sys_resource") - S_(SECCLASS_CAPABILITY, CAPABILITY__SYS_TIME, "sys_time") - S_(SECCLASS_CAPABILITY, CAPABILITY__SYS_TTY_CONFIG, "sys_tty_config") - S_(SECCLASS_CAPABILITY, CAPABILITY__MKNOD, "mknod") - S_(SECCLASS_CAPABILITY, CAPABILITY__LEASE, "lease") - S_(SECCLASS_CAPABILITY, CAPABILITY__AUDIT_WRITE, "audit_write") - S_(SECCLASS_CAPABILITY, CAPABILITY__AUDIT_CONTROL, "audit_control") - S_(SECCLASS_CAPABILITY, CAPABILITY__SETFCAP, "setfcap") - S_(SECCLASS_CAPABILITY2, CAPABILITY2__MAC_OVERRIDE, "mac_override") - S_(SECCLASS_CAPABILITY2, CAPABILITY2__MAC_ADMIN, "mac_admin") - S_(SECCLASS_NETLINK_ROUTE_SOCKET, NETLINK_ROUTE_SOCKET__NLMSG_READ, "nlmsg_read") - S_(SECCLASS_NETLINK_ROUTE_SOCKET, NETLINK_ROUTE_SOCKET__NLMSG_WRITE, "nlmsg_write") - S_(SECCLASS_NETLINK_FIREWALL_SOCKET, NETLINK_FIREWALL_SOCKET__NLMSG_READ, "nlmsg_read") - S_(SECCLASS_NETLINK_FIREWALL_SOCKET, NETLINK_FIREWALL_SOCKET__NLMSG_WRITE, "nlmsg_write") - S_(SECCLASS_NETLINK_TCPDIAG_SOCKET, NETLINK_TCPDIAG_SOCKET__NLMSG_READ, "nlmsg_read") - S_(SECCLASS_NETLINK_TCPDIAG_SOCKET, NETLINK_TCPDIAG_SOCKET__NLMSG_WRITE, "nlmsg_write") - S_(SECCLASS_NETLINK_XFRM_SOCKET, NETLINK_XFRM_SOCKET__NLMSG_READ, "nlmsg_read") - S_(SECCLASS_NETLINK_XFRM_SOCKET, NETLINK_XFRM_SOCKET__NLMSG_WRITE, "nlmsg_write") - S_(SECCLASS_NETLINK_AUDIT_SOCKET, NETLINK_AUDIT_SOCKET__NLMSG_READ, "nlmsg_read") - S_(SECCLASS_NETLINK_AUDIT_SOCKET, NETLINK_AUDIT_SOCKET__NLMSG_WRITE, "nlmsg_write") - S_(SECCLASS_NETLINK_AUDIT_SOCKET, NETLINK_AUDIT_SOCKET__NLMSG_RELAY, "nlmsg_relay") - S_(SECCLASS_NETLINK_AUDIT_SOCKET, NETLINK_AUDIT_SOCKET__NLMSG_READPRIV, "nlmsg_readpriv") - S_(SECCLASS_NETLINK_AUDIT_SOCKET, NETLINK_AUDIT_SOCKET__NLMSG_TTY_AUDIT, "nlmsg_tty_audit") - S_(SECCLASS_NETLINK_IP6FW_SOCKET, NETLINK_IP6FW_SOCKET__NLMSG_READ, "nlmsg_read") - S_(SECCLASS_NETLINK_IP6FW_SOCKET, NETLINK_IP6FW_SOCKET__NLMSG_WRITE, "nlmsg_write") - S_(SECCLASS_ASSOCIATION, ASSOCIATION__SENDTO, "sendto") - S_(SECCLASS_ASSOCIATION, ASSOCIATION__RECVFROM, "recvfrom") - S_(SECCLASS_ASSOCIATION, ASSOCIATION__SETCONTEXT, "setcontext") - S_(SECCLASS_ASSOCIATION, ASSOCIATION__POLMATCH, "polmatch") - S_(SECCLASS_PACKET, PACKET__SEND, "send") - S_(SECCLASS_PACKET, PACKET__RECV, "recv") - S_(SECCLASS_PACKET, PACKET__RELABELTO, "relabelto") - S_(SECCLASS_PACKET, PACKET__FLOW_IN, "flow_in") - S_(SECCLASS_PACKET, PACKET__FLOW_OUT, "flow_out") - S_(SECCLASS_PACKET, PACKET__FORWARD_IN, "forward_in") - S_(SECCLASS_PACKET, PACKET__FORWARD_OUT, "forward_out") - S_(SECCLASS_KEY, KEY__VIEW, "view") - S_(SECCLASS_KEY, KEY__READ, "read") - S_(SECCLASS_KEY, KEY__WRITE, "write") - S_(SECCLASS_KEY, KEY__SEARCH, "search") - S_(SECCLASS_KEY, KEY__LINK, "link") - S_(SECCLASS_KEY, KEY__SETATTR, "setattr") - S_(SECCLASS_KEY, KEY__CREATE, "create") - S_(SECCLASS_DCCP_SOCKET, DCCP_SOCKET__NODE_BIND, "node_bind") - S_(SECCLASS_DCCP_SOCKET, DCCP_SOCKET__NAME_CONNECT, "name_connect") - S_(SECCLASS_MEMPROTECT, MEMPROTECT__MMAP_ZERO, "mmap_zero") - S_(SECCLASS_PEER, PEER__RECV, "recv") - S_(SECCLASS_KERNEL_SERVICE, KERNEL_SERVICE__USE_AS_OVERRIDE, "use_as_override") - S_(SECCLASS_KERNEL_SERVICE, KERNEL_SERVICE__CREATE_FILES_AS, "create_files_as") diff --git a/security/selinux/include/av_permissions.h b/security/selinux/include/av_permissions.h deleted file mode 100644 index 0546d616ccac..000000000000 --- a/security/selinux/include/av_permissions.h +++ /dev/null @@ -1,870 +0,0 @@ -/* This file is automatically generated. Do not edit. */ -#define COMMON_FILE__IOCTL 0x00000001UL -#define COMMON_FILE__READ 0x00000002UL -#define COMMON_FILE__WRITE 0x00000004UL -#define COMMON_FILE__CREATE 0x00000008UL -#define COMMON_FILE__GETATTR 0x00000010UL -#define COMMON_FILE__SETATTR 0x00000020UL -#define COMMON_FILE__LOCK 0x00000040UL -#define COMMON_FILE__RELABELFROM 0x00000080UL -#define COMMON_FILE__RELABELTO 0x00000100UL -#define COMMON_FILE__APPEND 0x00000200UL -#define COMMON_FILE__UNLINK 0x00000400UL -#define COMMON_FILE__LINK 0x00000800UL -#define COMMON_FILE__RENAME 0x00001000UL -#define COMMON_FILE__EXECUTE 0x00002000UL -#define COMMON_FILE__SWAPON 0x00004000UL -#define COMMON_FILE__QUOTAON 0x00008000UL -#define COMMON_FILE__MOUNTON 0x00010000UL -#define COMMON_SOCKET__IOCTL 0x00000001UL -#define COMMON_SOCKET__READ 0x00000002UL -#define COMMON_SOCKET__WRITE 0x00000004UL -#define COMMON_SOCKET__CREATE 0x00000008UL -#define COMMON_SOCKET__GETATTR 0x00000010UL -#define COMMON_SOCKET__SETATTR 0x00000020UL -#define COMMON_SOCKET__LOCK 0x00000040UL -#define COMMON_SOCKET__RELABELFROM 0x00000080UL -#define COMMON_SOCKET__RELABELTO 0x00000100UL -#define COMMON_SOCKET__APPEND 0x00000200UL -#define COMMON_SOCKET__BIND 0x00000400UL -#define COMMON_SOCKET__CONNECT 0x00000800UL -#define COMMON_SOCKET__LISTEN 0x00001000UL -#define COMMON_SOCKET__ACCEPT 0x00002000UL -#define COMMON_SOCKET__GETOPT 0x00004000UL -#define COMMON_SOCKET__SETOPT 0x00008000UL -#define COMMON_SOCKET__SHUTDOWN 0x00010000UL -#define COMMON_SOCKET__RECVFROM 0x00020000UL -#define COMMON_SOCKET__SENDTO 0x00040000UL -#define COMMON_SOCKET__RECV_MSG 0x00080000UL -#define COMMON_SOCKET__SEND_MSG 0x00100000UL -#define COMMON_SOCKET__NAME_BIND 0x00200000UL -#define COMMON_IPC__CREATE 0x00000001UL -#define COMMON_IPC__DESTROY 0x00000002UL -#define COMMON_IPC__GETATTR 0x00000004UL -#define COMMON_IPC__SETATTR 0x00000008UL -#define COMMON_IPC__READ 0x00000010UL -#define COMMON_IPC__WRITE 0x00000020UL -#define COMMON_IPC__ASSOCIATE 0x00000040UL -#define COMMON_IPC__UNIX_READ 0x00000080UL -#define COMMON_IPC__UNIX_WRITE 0x00000100UL -#define FILESYSTEM__MOUNT 0x00000001UL -#define FILESYSTEM__REMOUNT 0x00000002UL -#define FILESYSTEM__UNMOUNT 0x00000004UL -#define FILESYSTEM__GETATTR 0x00000008UL -#define FILESYSTEM__RELABELFROM 0x00000010UL -#define FILESYSTEM__RELABELTO 0x00000020UL -#define FILESYSTEM__TRANSITION 0x00000040UL -#define FILESYSTEM__ASSOCIATE 0x00000080UL -#define FILESYSTEM__QUOTAMOD 0x00000100UL -#define FILESYSTEM__QUOTAGET 0x00000200UL -#define DIR__IOCTL 0x00000001UL -#define DIR__READ 0x00000002UL -#define DIR__WRITE 0x00000004UL -#define DIR__CREATE 0x00000008UL -#define DIR__GETATTR 0x00000010UL -#define DIR__SETATTR 0x00000020UL -#define DIR__LOCK 0x00000040UL -#define DIR__RELABELFROM 0x00000080UL -#define DIR__RELABELTO 0x00000100UL -#define DIR__APPEND 0x00000200UL -#define DIR__UNLINK 0x00000400UL -#define DIR__LINK 0x00000800UL -#define DIR__RENAME 0x00001000UL -#define DIR__EXECUTE 0x00002000UL -#define DIR__SWAPON 0x00004000UL -#define DIR__QUOTAON 0x00008000UL -#define DIR__MOUNTON 0x00010000UL -#define DIR__ADD_NAME 0x00020000UL -#define DIR__REMOVE_NAME 0x00040000UL -#define DIR__REPARENT 0x00080000UL -#define DIR__SEARCH 0x00100000UL -#define DIR__RMDIR 0x00200000UL -#define DIR__OPEN 0x00400000UL -#define FILE__IOCTL 0x00000001UL -#define FILE__READ 0x00000002UL -#define FILE__WRITE 0x00000004UL -#define FILE__CREATE 0x00000008UL -#define FILE__GETATTR 0x00000010UL -#define FILE__SETATTR 0x00000020UL -#define FILE__LOCK 0x00000040UL -#define FILE__RELABELFROM 0x00000080UL -#define FILE__RELABELTO 0x00000100UL -#define FILE__APPEND 0x00000200UL -#define FILE__UNLINK 0x00000400UL -#define FILE__LINK 0x00000800UL -#define FILE__RENAME 0x00001000UL -#define FILE__EXECUTE 0x00002000UL -#define FILE__SWAPON 0x00004000UL -#define FILE__QUOTAON 0x00008000UL -#define FILE__MOUNTON 0x00010000UL -#define FILE__EXECUTE_NO_TRANS 0x00020000UL -#define FILE__ENTRYPOINT 0x00040000UL -#define FILE__EXECMOD 0x00080000UL -#define FILE__OPEN 0x00100000UL -#define LNK_FILE__IOCTL 0x00000001UL -#define LNK_FILE__READ 0x00000002UL -#define LNK_FILE__WRITE 0x00000004UL -#define LNK_FILE__CREATE 0x00000008UL -#define LNK_FILE__GETATTR 0x00000010UL -#define LNK_FILE__SETATTR 0x00000020UL -#define LNK_FILE__LOCK 0x00000040UL -#define LNK_FILE__RELABELFROM 0x00000080UL -#define LNK_FILE__RELABELTO 0x00000100UL -#define LNK_FILE__APPEND 0x00000200UL -#define LNK_FILE__UNLINK 0x00000400UL -#define LNK_FILE__LINK 0x00000800UL -#define LNK_FILE__RENAME 0x00001000UL -#define LNK_FILE__EXECUTE 0x00002000UL -#define LNK_FILE__SWAPON 0x00004000UL -#define LNK_FILE__QUOTAON 0x00008000UL -#define LNK_FILE__MOUNTON 0x00010000UL -#define CHR_FILE__IOCTL 0x00000001UL -#define CHR_FILE__READ 0x00000002UL -#define CHR_FILE__WRITE 0x00000004UL -#define CHR_FILE__CREATE 0x00000008UL -#define CHR_FILE__GETATTR 0x00000010UL -#define CHR_FILE__SETATTR 0x00000020UL -#define CHR_FILE__LOCK 0x00000040UL -#define CHR_FILE__RELABELFROM 0x00000080UL -#define CHR_FILE__RELABELTO 0x00000100UL -#define CHR_FILE__APPEND 0x00000200UL -#define CHR_FILE__UNLINK 0x00000400UL -#define CHR_FILE__LINK 0x00000800UL -#define CHR_FILE__RENAME 0x00001000UL -#define CHR_FILE__EXECUTE 0x00002000UL -#define CHR_FILE__SWAPON 0x00004000UL -#define CHR_FILE__QUOTAON 0x00008000UL -#define CHR_FILE__MOUNTON 0x00010000UL -#define CHR_FILE__EXECUTE_NO_TRANS 0x00020000UL -#define CHR_FILE__ENTRYPOINT 0x00040000UL -#define CHR_FILE__EXECMOD 0x00080000UL -#define CHR_FILE__OPEN 0x00100000UL -#define BLK_FILE__IOCTL 0x00000001UL -#define BLK_FILE__READ 0x00000002UL -#define BLK_FILE__WRITE 0x00000004UL -#define BLK_FILE__CREATE 0x00000008UL -#define BLK_FILE__GETATTR 0x00000010UL -#define BLK_FILE__SETATTR 0x00000020UL -#define BLK_FILE__LOCK 0x00000040UL -#define BLK_FILE__RELABELFROM 0x00000080UL -#define BLK_FILE__RELABELTO 0x00000100UL -#define BLK_FILE__APPEND 0x00000200UL -#define BLK_FILE__UNLINK 0x00000400UL -#define BLK_FILE__LINK 0x00000800UL -#define BLK_FILE__RENAME 0x00001000UL -#define BLK_FILE__EXECUTE 0x00002000UL -#define BLK_FILE__SWAPON 0x00004000UL -#define BLK_FILE__QUOTAON 0x00008000UL -#define BLK_FILE__MOUNTON 0x00010000UL -#define BLK_FILE__OPEN 0x00020000UL -#define SOCK_FILE__IOCTL 0x00000001UL -#define SOCK_FILE__READ 0x00000002UL -#define SOCK_FILE__WRITE 0x00000004UL -#define SOCK_FILE__CREATE 0x00000008UL -#define SOCK_FILE__GETATTR 0x00000010UL -#define SOCK_FILE__SETATTR 0x00000020UL -#define SOCK_FILE__LOCK 0x00000040UL -#define SOCK_FILE__RELABELFROM 0x00000080UL -#define SOCK_FILE__RELABELTO 0x00000100UL -#define SOCK_FILE__APPEND 0x00000200UL -#define SOCK_FILE__UNLINK 0x00000400UL -#define SOCK_FILE__LINK 0x00000800UL -#define SOCK_FILE__RENAME 0x00001000UL -#define SOCK_FILE__EXECUTE 0x00002000UL -#define SOCK_FILE__SWAPON 0x00004000UL -#define SOCK_FILE__QUOTAON 0x00008000UL -#define SOCK_FILE__MOUNTON 0x00010000UL -#define SOCK_FILE__OPEN 0x00020000UL -#define FIFO_FILE__IOCTL 0x00000001UL -#define FIFO_FILE__READ 0x00000002UL -#define FIFO_FILE__WRITE 0x00000004UL -#define FIFO_FILE__CREATE 0x00000008UL -#define FIFO_FILE__GETATTR 0x00000010UL -#define FIFO_FILE__SETATTR 0x00000020UL -#define FIFO_FILE__LOCK 0x00000040UL -#define FIFO_FILE__RELABELFROM 0x00000080UL -#define FIFO_FILE__RELABELTO 0x00000100UL -#define FIFO_FILE__APPEND 0x00000200UL -#define FIFO_FILE__UNLINK 0x00000400UL -#define FIFO_FILE__LINK 0x00000800UL -#define FIFO_FILE__RENAME 0x00001000UL -#define FIFO_FILE__EXECUTE 0x00002000UL -#define FIFO_FILE__SWAPON 0x00004000UL -#define FIFO_FILE__QUOTAON 0x00008000UL -#define FIFO_FILE__MOUNTON 0x00010000UL -#define FIFO_FILE__OPEN 0x00020000UL -#define FD__USE 0x00000001UL -#define SOCKET__IOCTL 0x00000001UL -#define SOCKET__READ 0x00000002UL -#define SOCKET__WRITE 0x00000004UL -#define SOCKET__CREATE 0x00000008UL -#define SOCKET__GETATTR 0x00000010UL -#define SOCKET__SETATTR 0x00000020UL -#define SOCKET__LOCK 0x00000040UL -#define SOCKET__RELABELFROM 0x00000080UL -#define SOCKET__RELABELTO 0x00000100UL -#define SOCKET__APPEND 0x00000200UL -#define SOCKET__BIND 0x00000400UL -#define SOCKET__CONNECT 0x00000800UL -#define SOCKET__LISTEN 0x00001000UL -#define SOCKET__ACCEPT 0x00002000UL -#define SOCKET__GETOPT 0x00004000UL -#define SOCKET__SETOPT 0x00008000UL -#define SOCKET__SHUTDOWN 0x00010000UL -#define SOCKET__RECVFROM 0x00020000UL -#define SOCKET__SENDTO 0x00040000UL -#define SOCKET__RECV_MSG 0x00080000UL -#define SOCKET__SEND_MSG 0x00100000UL -#define SOCKET__NAME_BIND 0x00200000UL -#define TCP_SOCKET__IOCTL 0x00000001UL -#define TCP_SOCKET__READ 0x00000002UL -#define TCP_SOCKET__WRITE 0x00000004UL -#define TCP_SOCKET__CREATE 0x00000008UL -#define TCP_SOCKET__GETATTR 0x00000010UL -#define TCP_SOCKET__SETATTR 0x00000020UL -#define TCP_SOCKET__LOCK 0x00000040UL -#define TCP_SOCKET__RELABELFROM 0x00000080UL -#define TCP_SOCKET__RELABELTO 0x00000100UL -#define TCP_SOCKET__APPEND 0x00000200UL -#define TCP_SOCKET__BIND 0x00000400UL -#define TCP_SOCKET__CONNECT 0x00000800UL -#define TCP_SOCKET__LISTEN 0x00001000UL -#define TCP_SOCKET__ACCEPT 0x00002000UL -#define TCP_SOCKET__GETOPT 0x00004000UL -#define TCP_SOCKET__SETOPT 0x00008000UL -#define TCP_SOCKET__SHUTDOWN 0x00010000UL -#define TCP_SOCKET__RECVFROM 0x00020000UL -#define TCP_SOCKET__SENDTO 0x00040000UL -#define TCP_SOCKET__RECV_MSG 0x00080000UL -#define TCP_SOCKET__SEND_MSG 0x00100000UL -#define TCP_SOCKET__NAME_BIND 0x00200000UL -#define TCP_SOCKET__CONNECTTO 0x00400000UL -#define TCP_SOCKET__NEWCONN 0x00800000UL -#define TCP_SOCKET__ACCEPTFROM 0x01000000UL -#define TCP_SOCKET__NODE_BIND 0x02000000UL -#define TCP_SOCKET__NAME_CONNECT 0x04000000UL -#define UDP_SOCKET__IOCTL 0x00000001UL -#define UDP_SOCKET__READ 0x00000002UL -#define UDP_SOCKET__WRITE 0x00000004UL -#define UDP_SOCKET__CREATE 0x00000008UL -#define UDP_SOCKET__GETATTR 0x00000010UL -#define UDP_SOCKET__SETATTR 0x00000020UL -#define UDP_SOCKET__LOCK 0x00000040UL -#define UDP_SOCKET__RELABELFROM 0x00000080UL -#define UDP_SOCKET__RELABELTO 0x00000100UL -#define UDP_SOCKET__APPEND 0x00000200UL -#define UDP_SOCKET__BIND 0x00000400UL -#define UDP_SOCKET__CONNECT 0x00000800UL -#define UDP_SOCKET__LISTEN 0x00001000UL -#define UDP_SOCKET__ACCEPT 0x00002000UL -#define UDP_SOCKET__GETOPT 0x00004000UL -#define UDP_SOCKET__SETOPT 0x00008000UL -#define UDP_SOCKET__SHUTDOWN 0x00010000UL -#define UDP_SOCKET__RECVFROM 0x00020000UL -#define UDP_SOCKET__SENDTO 0x00040000UL -#define UDP_SOCKET__RECV_MSG 0x00080000UL -#define UDP_SOCKET__SEND_MSG 0x00100000UL -#define UDP_SOCKET__NAME_BIND 0x00200000UL -#define UDP_SOCKET__NODE_BIND 0x00400000UL -#define RAWIP_SOCKET__IOCTL 0x00000001UL -#define RAWIP_SOCKET__READ 0x00000002UL -#define RAWIP_SOCKET__WRITE 0x00000004UL -#define RAWIP_SOCKET__CREATE 0x00000008UL -#define RAWIP_SOCKET__GETATTR 0x00000010UL -#define RAWIP_SOCKET__SETATTR 0x00000020UL -#define RAWIP_SOCKET__LOCK 0x00000040UL -#define RAWIP_SOCKET__RELABELFROM 0x00000080UL -#define RAWIP_SOCKET__RELABELTO 0x00000100UL -#define RAWIP_SOCKET__APPEND 0x00000200UL -#define RAWIP_SOCKET__BIND 0x00000400UL -#define RAWIP_SOCKET__CONNECT 0x00000800UL -#define RAWIP_SOCKET__LISTEN 0x00001000UL -#define RAWIP_SOCKET__ACCEPT 0x00002000UL -#define RAWIP_SOCKET__GETOPT 0x00004000UL -#define RAWIP_SOCKET__SETOPT 0x00008000UL -#define RAWIP_SOCKET__SHUTDOWN 0x00010000UL -#define RAWIP_SOCKET__RECVFROM 0x00020000UL -#define RAWIP_SOCKET__SENDTO 0x00040000UL -#define RAWIP_SOCKET__RECV_MSG 0x00080000UL -#define RAWIP_SOCKET__SEND_MSG 0x00100000UL -#define RAWIP_SOCKET__NAME_BIND 0x00200000UL -#define RAWIP_SOCKET__NODE_BIND 0x00400000UL -#define NODE__TCP_RECV 0x00000001UL -#define NODE__TCP_SEND 0x00000002UL -#define NODE__UDP_RECV 0x00000004UL -#define NODE__UDP_SEND 0x00000008UL -#define NODE__RAWIP_RECV 0x00000010UL -#define NODE__RAWIP_SEND 0x00000020UL -#define NODE__ENFORCE_DEST 0x00000040UL -#define NODE__DCCP_RECV 0x00000080UL -#define NODE__DCCP_SEND 0x00000100UL -#define NODE__RECVFROM 0x00000200UL -#define NODE__SENDTO 0x00000400UL -#define NETIF__TCP_RECV 0x00000001UL -#define NETIF__TCP_SEND 0x00000002UL -#define NETIF__UDP_RECV 0x00000004UL -#define NETIF__UDP_SEND 0x00000008UL -#define NETIF__RAWIP_RECV 0x00000010UL -#define NETIF__RAWIP_SEND 0x00000020UL -#define NETIF__DCCP_RECV 0x00000040UL -#define NETIF__DCCP_SEND 0x00000080UL -#define NETIF__INGRESS 0x00000100UL -#define NETIF__EGRESS 0x00000200UL -#define NETLINK_SOCKET__IOCTL 0x00000001UL -#define NETLINK_SOCKET__READ 0x00000002UL -#define NETLINK_SOCKET__WRITE 0x00000004UL -#define NETLINK_SOCKET__CREATE 0x00000008UL -#define NETLINK_SOCKET__GETATTR 0x00000010UL -#define NETLINK_SOCKET__SETATTR 0x00000020UL -#define NETLINK_SOCKET__LOCK 0x00000040UL -#define NETLINK_SOCKET__RELABELFROM 0x00000080UL -#define NETLINK_SOCKET__RELABELTO 0x00000100UL -#define NETLINK_SOCKET__APPEND 0x00000200UL -#define NETLINK_SOCKET__BIND 0x00000400UL -#define NETLINK_SOCKET__CONNECT 0x00000800UL -#define NETLINK_SOCKET__LISTEN 0x00001000UL -#define NETLINK_SOCKET__ACCEPT 0x00002000UL -#define NETLINK_SOCKET__GETOPT 0x00004000UL -#define NETLINK_SOCKET__SETOPT 0x00008000UL -#define NETLINK_SOCKET__SHUTDOWN 0x00010000UL -#define NETLINK_SOCKET__RECVFROM 0x00020000UL -#define NETLINK_SOCKET__SENDTO 0x00040000UL -#define NETLINK_SOCKET__RECV_MSG 0x00080000UL -#define NETLINK_SOCKET__SEND_MSG 0x00100000UL -#define NETLINK_SOCKET__NAME_BIND 0x00200000UL -#define PACKET_SOCKET__IOCTL 0x00000001UL -#define PACKET_SOCKET__READ 0x00000002UL -#define PACKET_SOCKET__WRITE 0x00000004UL -#define PACKET_SOCKET__CREATE 0x00000008UL -#define PACKET_SOCKET__GETATTR 0x00000010UL -#define PACKET_SOCKET__SETATTR 0x00000020UL -#define PACKET_SOCKET__LOCK 0x00000040UL -#define PACKET_SOCKET__RELABELFROM 0x00000080UL -#define PACKET_SOCKET__RELABELTO 0x00000100UL -#define PACKET_SOCKET__APPEND 0x00000200UL -#define PACKET_SOCKET__BIND 0x00000400UL -#define PACKET_SOCKET__CONNECT 0x00000800UL -#define PACKET_SOCKET__LISTEN 0x00001000UL -#define PACKET_SOCKET__ACCEPT 0x00002000UL -#define PACKET_SOCKET__GETOPT 0x00004000UL -#define PACKET_SOCKET__SETOPT 0x00008000UL -#define PACKET_SOCKET__SHUTDOWN 0x00010000UL -#define PACKET_SOCKET__RECVFROM 0x00020000UL -#define PACKET_SOCKET__SENDTO 0x00040000UL -#define PACKET_SOCKET__RECV_MSG 0x00080000UL -#define PACKET_SOCKET__SEND_MSG 0x00100000UL -#define PACKET_SOCKET__NAME_BIND 0x00200000UL -#define KEY_SOCKET__IOCTL 0x00000001UL -#define KEY_SOCKET__READ 0x00000002UL -#define KEY_SOCKET__WRITE 0x00000004UL -#define KEY_SOCKET__CREATE 0x00000008UL -#define KEY_SOCKET__GETATTR 0x00000010UL -#define KEY_SOCKET__SETATTR 0x00000020UL -#define KEY_SOCKET__LOCK 0x00000040UL -#define KEY_SOCKET__RELABELFROM 0x00000080UL -#define KEY_SOCKET__RELABELTO 0x00000100UL -#define KEY_SOCKET__APPEND 0x00000200UL -#define KEY_SOCKET__BIND 0x00000400UL -#define KEY_SOCKET__CONNECT 0x00000800UL -#define KEY_SOCKET__LISTEN 0x00001000UL -#define KEY_SOCKET__ACCEPT 0x00002000UL -#define KEY_SOCKET__GETOPT 0x00004000UL -#define KEY_SOCKET__SETOPT 0x00008000UL -#define KEY_SOCKET__SHUTDOWN 0x00010000UL -#define KEY_SOCKET__RECVFROM 0x00020000UL -#define KEY_SOCKET__SENDTO 0x00040000UL -#define KEY_SOCKET__RECV_MSG 0x00080000UL -#define KEY_SOCKET__SEND_MSG 0x00100000UL -#define KEY_SOCKET__NAME_BIND 0x00200000UL -#define UNIX_STREAM_SOCKET__IOCTL 0x00000001UL -#define UNIX_STREAM_SOCKET__READ 0x00000002UL -#define UNIX_STREAM_SOCKET__WRITE 0x00000004UL -#define UNIX_STREAM_SOCKET__CREATE 0x00000008UL -#define UNIX_STREAM_SOCKET__GETATTR 0x00000010UL -#define UNIX_STREAM_SOCKET__SETATTR 0x00000020UL -#define UNIX_STREAM_SOCKET__LOCK 0x00000040UL -#define UNIX_STREAM_SOCKET__RELABELFROM 0x00000080UL -#define UNIX_STREAM_SOCKET__RELABELTO 0x00000100UL -#define UNIX_STREAM_SOCKET__APPEND 0x00000200UL -#define UNIX_STREAM_SOCKET__BIND 0x00000400UL -#define UNIX_STREAM_SOCKET__CONNECT 0x00000800UL -#define UNIX_STREAM_SOCKET__LISTEN 0x00001000UL -#define UNIX_STREAM_SOCKET__ACCEPT 0x00002000UL -#define UNIX_STREAM_SOCKET__GETOPT 0x00004000UL -#define UNIX_STREAM_SOCKET__SETOPT 0x00008000UL -#define UNIX_STREAM_SOCKET__SHUTDOWN 0x00010000UL -#define UNIX_STREAM_SOCKET__RECVFROM 0x00020000UL -#define UNIX_STREAM_SOCKET__SENDTO 0x00040000UL -#define UNIX_STREAM_SOCKET__RECV_MSG 0x00080000UL -#define UNIX_STREAM_SOCKET__SEND_MSG 0x00100000UL -#define UNIX_STREAM_SOCKET__NAME_BIND 0x00200000UL -#define UNIX_STREAM_SOCKET__CONNECTTO 0x00400000UL -#define UNIX_STREAM_SOCKET__NEWCONN 0x00800000UL -#define UNIX_STREAM_SOCKET__ACCEPTFROM 0x01000000UL -#define UNIX_DGRAM_SOCKET__IOCTL 0x00000001UL -#define UNIX_DGRAM_SOCKET__READ 0x00000002UL -#define UNIX_DGRAM_SOCKET__WRITE 0x00000004UL -#define UNIX_DGRAM_SOCKET__CREATE 0x00000008UL -#define UNIX_DGRAM_SOCKET__GETATTR 0x00000010UL -#define UNIX_DGRAM_SOCKET__SETATTR 0x00000020UL -#define UNIX_DGRAM_SOCKET__LOCK 0x00000040UL -#define UNIX_DGRAM_SOCKET__RELABELFROM 0x00000080UL -#define UNIX_DGRAM_SOCKET__RELABELTO 0x00000100UL -#define UNIX_DGRAM_SOCKET__APPEND 0x00000200UL -#define UNIX_DGRAM_SOCKET__BIND 0x00000400UL -#define UNIX_DGRAM_SOCKET__CONNECT 0x00000800UL -#define UNIX_DGRAM_SOCKET__LISTEN 0x00001000UL -#define UNIX_DGRAM_SOCKET__ACCEPT 0x00002000UL -#define UNIX_DGRAM_SOCKET__GETOPT 0x00004000UL -#define UNIX_DGRAM_SOCKET__SETOPT 0x00008000UL -#define UNIX_DGRAM_SOCKET__SHUTDOWN 0x00010000UL -#define UNIX_DGRAM_SOCKET__RECVFROM 0x00020000UL -#define UNIX_DGRAM_SOCKET__SENDTO 0x00040000UL -#define UNIX_DGRAM_SOCKET__RECV_MSG 0x00080000UL -#define UNIX_DGRAM_SOCKET__SEND_MSG 0x00100000UL -#define UNIX_DGRAM_SOCKET__NAME_BIND 0x00200000UL -#define TUN_SOCKET__IOCTL 0x00000001UL -#define TUN_SOCKET__READ 0x00000002UL -#define TUN_SOCKET__WRITE 0x00000004UL -#define TUN_SOCKET__CREATE 0x00000008UL -#define TUN_SOCKET__GETATTR 0x00000010UL -#define TUN_SOCKET__SETATTR 0x00000020UL -#define TUN_SOCKET__LOCK 0x00000040UL -#define TUN_SOCKET__RELABELFROM 0x00000080UL -#define TUN_SOCKET__RELABELTO 0x00000100UL -#define TUN_SOCKET__APPEND 0x00000200UL -#define TUN_SOCKET__BIND 0x00000400UL -#define TUN_SOCKET__CONNECT 0x00000800UL -#define TUN_SOCKET__LISTEN 0x00001000UL -#define TUN_SOCKET__ACCEPT 0x00002000UL -#define TUN_SOCKET__GETOPT 0x00004000UL -#define TUN_SOCKET__SETOPT 0x00008000UL -#define TUN_SOCKET__SHUTDOWN 0x00010000UL -#define TUN_SOCKET__RECVFROM 0x00020000UL -#define TUN_SOCKET__SENDTO 0x00040000UL -#define TUN_SOCKET__RECV_MSG 0x00080000UL -#define TUN_SOCKET__SEND_MSG 0x00100000UL -#define TUN_SOCKET__NAME_BIND 0x00200000UL -#define PROCESS__FORK 0x00000001UL -#define PROCESS__TRANSITION 0x00000002UL -#define PROCESS__SIGCHLD 0x00000004UL -#define PROCESS__SIGKILL 0x00000008UL -#define PROCESS__SIGSTOP 0x00000010UL -#define PROCESS__SIGNULL 0x00000020UL -#define PROCESS__SIGNAL 0x00000040UL -#define PROCESS__PTRACE 0x00000080UL -#define PROCESS__GETSCHED 0x00000100UL -#define PROCESS__SETSCHED 0x00000200UL -#define PROCESS__GETSESSION 0x00000400UL -#define PROCESS__GETPGID 0x00000800UL -#define PROCESS__SETPGID 0x00001000UL -#define PROCESS__GETCAP 0x00002000UL -#define PROCESS__SETCAP 0x00004000UL -#define PROCESS__SHARE 0x00008000UL -#define PROCESS__GETATTR 0x00010000UL -#define PROCESS__SETEXEC 0x00020000UL -#define PROCESS__SETFSCREATE 0x00040000UL -#define PROCESS__NOATSECURE 0x00080000UL -#define PROCESS__SIGINH 0x00100000UL -#define PROCESS__SETRLIMIT 0x00200000UL -#define PROCESS__RLIMITINH 0x00400000UL -#define PROCESS__DYNTRANSITION 0x00800000UL -#define PROCESS__SETCURRENT 0x01000000UL -#define PROCESS__EXECMEM 0x02000000UL -#define PROCESS__EXECSTACK 0x04000000UL -#define PROCESS__EXECHEAP 0x08000000UL -#define PROCESS__SETKEYCREATE 0x10000000UL -#define PROCESS__SETSOCKCREATE 0x20000000UL -#define IPC__CREATE 0x00000001UL -#define IPC__DESTROY 0x00000002UL -#define IPC__GETATTR 0x00000004UL -#define IPC__SETATTR 0x00000008UL -#define IPC__READ 0x00000010UL -#define IPC__WRITE 0x00000020UL -#define IPC__ASSOCIATE 0x00000040UL -#define IPC__UNIX_READ 0x00000080UL -#define IPC__UNIX_WRITE 0x00000100UL -#define SEM__CREATE 0x00000001UL -#define SEM__DESTROY 0x00000002UL -#define SEM__GETATTR 0x00000004UL -#define SEM__SETATTR 0x00000008UL -#define SEM__READ 0x00000010UL -#define SEM__WRITE 0x00000020UL -#define SEM__ASSOCIATE 0x00000040UL -#define SEM__UNIX_READ 0x00000080UL -#define SEM__UNIX_WRITE 0x00000100UL -#define MSGQ__CREATE 0x00000001UL -#define MSGQ__DESTROY 0x00000002UL -#define MSGQ__GETATTR 0x00000004UL -#define MSGQ__SETATTR 0x00000008UL -#define MSGQ__READ 0x00000010UL -#define MSGQ__WRITE 0x00000020UL -#define MSGQ__ASSOCIATE 0x00000040UL -#define MSGQ__UNIX_READ 0x00000080UL -#define MSGQ__UNIX_WRITE 0x00000100UL -#define MSGQ__ENQUEUE 0x00000200UL -#define MSG__SEND 0x00000001UL -#define MSG__RECEIVE 0x00000002UL -#define SHM__CREATE 0x00000001UL -#define SHM__DESTROY 0x00000002UL -#define SHM__GETATTR 0x00000004UL -#define SHM__SETATTR 0x00000008UL -#define SHM__READ 0x00000010UL -#define SHM__WRITE 0x00000020UL -#define SHM__ASSOCIATE 0x00000040UL -#define SHM__UNIX_READ 0x00000080UL -#define SHM__UNIX_WRITE 0x00000100UL -#define SHM__LOCK 0x00000200UL -#define SECURITY__COMPUTE_AV 0x00000001UL -#define SECURITY__COMPUTE_CREATE 0x00000002UL -#define SECURITY__COMPUTE_MEMBER 0x00000004UL -#define SECURITY__CHECK_CONTEXT 0x00000008UL -#define SECURITY__LOAD_POLICY 0x00000010UL -#define SECURITY__COMPUTE_RELABEL 0x00000020UL -#define SECURITY__COMPUTE_USER 0x00000040UL -#define SECURITY__SETENFORCE 0x00000080UL -#define SECURITY__SETBOOL 0x00000100UL -#define SECURITY__SETSECPARAM 0x00000200UL -#define SECURITY__SETCHECKREQPROT 0x00000400UL -#define SYSTEM__IPC_INFO 0x00000001UL -#define SYSTEM__SYSLOG_READ 0x00000002UL -#define SYSTEM__SYSLOG_MOD 0x00000004UL -#define SYSTEM__SYSLOG_CONSOLE 0x00000008UL -#define SYSTEM__MODULE_REQUEST 0x00000010UL -#define CAPABILITY__CHOWN 0x00000001UL -#define CAPABILITY__DAC_OVERRIDE 0x00000002UL -#define CAPABILITY__DAC_READ_SEARCH 0x00000004UL -#define CAPABILITY__FOWNER 0x00000008UL -#define CAPABILITY__FSETID 0x00000010UL -#define CAPABILITY__KILL 0x00000020UL -#define CAPABILITY__SETGID 0x00000040UL -#define CAPABILITY__SETUID 0x00000080UL -#define CAPABILITY__SETPCAP 0x00000100UL -#define CAPABILITY__LINUX_IMMUTABLE 0x00000200UL -#define CAPABILITY__NET_BIND_SERVICE 0x00000400UL -#define CAPABILITY__NET_BROADCAST 0x00000800UL -#define CAPABILITY__NET_ADMIN 0x00001000UL -#define CAPABILITY__NET_RAW 0x00002000UL -#define CAPABILITY__IPC_LOCK 0x00004000UL -#define CAPABILITY__IPC_OWNER 0x00008000UL -#define CAPABILITY__SYS_MODULE 0x00010000UL -#define CAPABILITY__SYS_RAWIO 0x00020000UL -#define CAPABILITY__SYS_CHROOT 0x00040000UL -#define CAPABILITY__SYS_PTRACE 0x00080000UL -#define CAPABILITY__SYS_PACCT 0x00100000UL -#define CAPABILITY__SYS_ADMIN 0x00200000UL -#define CAPABILITY__SYS_BOOT 0x00400000UL -#define CAPABILITY__SYS_NICE 0x00800000UL -#define CAPABILITY__SYS_RESOURCE 0x01000000UL -#define CAPABILITY__SYS_TIME 0x02000000UL -#define CAPABILITY__SYS_TTY_CONFIG 0x04000000UL -#define CAPABILITY__MKNOD 0x08000000UL -#define CAPABILITY__LEASE 0x10000000UL -#define CAPABILITY__AUDIT_WRITE 0x20000000UL -#define CAPABILITY__AUDIT_CONTROL 0x40000000UL -#define CAPABILITY__SETFCAP 0x80000000UL -#define CAPABILITY2__MAC_OVERRIDE 0x00000001UL -#define CAPABILITY2__MAC_ADMIN 0x00000002UL -#define NETLINK_ROUTE_SOCKET__IOCTL 0x00000001UL -#define NETLINK_ROUTE_SOCKET__READ 0x00000002UL -#define NETLINK_ROUTE_SOCKET__WRITE 0x00000004UL -#define NETLINK_ROUTE_SOCKET__CREATE 0x00000008UL -#define NETLINK_ROUTE_SOCKET__GETATTR 0x00000010UL -#define NETLINK_ROUTE_SOCKET__SETATTR 0x00000020UL -#define NETLINK_ROUTE_SOCKET__LOCK 0x00000040UL -#define NETLINK_ROUTE_SOCKET__RELABELFROM 0x00000080UL -#define NETLINK_ROUTE_SOCKET__RELABELTO 0x00000100UL -#define NETLINK_ROUTE_SOCKET__APPEND 0x00000200UL -#define NETLINK_ROUTE_SOCKET__BIND 0x00000400UL -#define NETLINK_ROUTE_SOCKET__CONNECT 0x00000800UL -#define NETLINK_ROUTE_SOCKET__LISTEN 0x00001000UL -#define NETLINK_ROUTE_SOCKET__ACCEPT 0x00002000UL -#define NETLINK_ROUTE_SOCKET__GETOPT 0x00004000UL -#define NETLINK_ROUTE_SOCKET__SETOPT 0x00008000UL -#define NETLINK_ROUTE_SOCKET__SHUTDOWN 0x00010000UL -#define NETLINK_ROUTE_SOCKET__RECVFROM 0x00020000UL -#define NETLINK_ROUTE_SOCKET__SENDTO 0x00040000UL -#define NETLINK_ROUTE_SOCKET__RECV_MSG 0x00080000UL -#define NETLINK_ROUTE_SOCKET__SEND_MSG 0x00100000UL -#define NETLINK_ROUTE_SOCKET__NAME_BIND 0x00200000UL -#define NETLINK_ROUTE_SOCKET__NLMSG_READ 0x00400000UL -#define NETLINK_ROUTE_SOCKET__NLMSG_WRITE 0x00800000UL -#define NETLINK_FIREWALL_SOCKET__IOCTL 0x00000001UL -#define NETLINK_FIREWALL_SOCKET__READ 0x00000002UL -#define NETLINK_FIREWALL_SOCKET__WRITE 0x00000004UL -#define NETLINK_FIREWALL_SOCKET__CREATE 0x00000008UL -#define NETLINK_FIREWALL_SOCKET__GETATTR 0x00000010UL -#define NETLINK_FIREWALL_SOCKET__SETATTR 0x00000020UL -#define NETLINK_FIREWALL_SOCKET__LOCK 0x00000040UL -#define NETLINK_FIREWALL_SOCKET__RELABELFROM 0x00000080UL -#define NETLINK_FIREWALL_SOCKET__RELABELTO 0x00000100UL -#define NETLINK_FIREWALL_SOCKET__APPEND 0x00000200UL -#define NETLINK_FIREWALL_SOCKET__BIND 0x00000400UL -#define NETLINK_FIREWALL_SOCKET__CONNECT 0x00000800UL -#define NETLINK_FIREWALL_SOCKET__LISTEN 0x00001000UL -#define NETLINK_FIREWALL_SOCKET__ACCEPT 0x00002000UL -#define NETLINK_FIREWALL_SOCKET__GETOPT 0x00004000UL -#define NETLINK_FIREWALL_SOCKET__SETOPT 0x00008000UL -#define NETLINK_FIREWALL_SOCKET__SHUTDOWN 0x00010000UL -#define NETLINK_FIREWALL_SOCKET__RECVFROM 0x00020000UL -#define NETLINK_FIREWALL_SOCKET__SENDTO 0x00040000UL -#define NETLINK_FIREWALL_SOCKET__RECV_MSG 0x00080000UL -#define NETLINK_FIREWALL_SOCKET__SEND_MSG 0x00100000UL -#define NETLINK_FIREWALL_SOCKET__NAME_BIND 0x00200000UL -#define NETLINK_FIREWALL_SOCKET__NLMSG_READ 0x00400000UL -#define NETLINK_FIREWALL_SOCKET__NLMSG_WRITE 0x00800000UL -#define NETLINK_TCPDIAG_SOCKET__IOCTL 0x00000001UL -#define NETLINK_TCPDIAG_SOCKET__READ 0x00000002UL -#define NETLINK_TCPDIAG_SOCKET__WRITE 0x00000004UL -#define NETLINK_TCPDIAG_SOCKET__CREATE 0x00000008UL -#define NETLINK_TCPDIAG_SOCKET__GETATTR 0x00000010UL -#define NETLINK_TCPDIAG_SOCKET__SETATTR 0x00000020UL -#define NETLINK_TCPDIAG_SOCKET__LOCK 0x00000040UL -#define NETLINK_TCPDIAG_SOCKET__RELABELFROM 0x00000080UL -#define NETLINK_TCPDIAG_SOCKET__RELABELTO 0x00000100UL -#define NETLINK_TCPDIAG_SOCKET__APPEND 0x00000200UL -#define NETLINK_TCPDIAG_SOCKET__BIND 0x00000400UL -#define NETLINK_TCPDIAG_SOCKET__CONNECT 0x00000800UL -#define NETLINK_TCPDIAG_SOCKET__LISTEN 0x00001000UL -#define NETLINK_TCPDIAG_SOCKET__ACCEPT 0x00002000UL -#define NETLINK_TCPDIAG_SOCKET__GETOPT 0x00004000UL -#define NETLINK_TCPDIAG_SOCKET__SETOPT 0x00008000UL -#define NETLINK_TCPDIAG_SOCKET__SHUTDOWN 0x00010000UL -#define NETLINK_TCPDIAG_SOCKET__RECVFROM 0x00020000UL -#define NETLINK_TCPDIAG_SOCKET__SENDTO 0x00040000UL -#define NETLINK_TCPDIAG_SOCKET__RECV_MSG 0x00080000UL -#define NETLINK_TCPDIAG_SOCKET__SEND_MSG 0x00100000UL -#define NETLINK_TCPDIAG_SOCKET__NAME_BIND 0x00200000UL -#define NETLINK_TCPDIAG_SOCKET__NLMSG_READ 0x00400000UL -#define NETLINK_TCPDIAG_SOCKET__NLMSG_WRITE 0x00800000UL -#define NETLINK_NFLOG_SOCKET__IOCTL 0x00000001UL -#define NETLINK_NFLOG_SOCKET__READ 0x00000002UL -#define NETLINK_NFLOG_SOCKET__WRITE 0x00000004UL -#define NETLINK_NFLOG_SOCKET__CREATE 0x00000008UL -#define NETLINK_NFLOG_SOCKET__GETATTR 0x00000010UL -#define NETLINK_NFLOG_SOCKET__SETATTR 0x00000020UL -#define NETLINK_NFLOG_SOCKET__LOCK 0x00000040UL -#define NETLINK_NFLOG_SOCKET__RELABELFROM 0x00000080UL -#define NETLINK_NFLOG_SOCKET__RELABELTO 0x00000100UL -#define NETLINK_NFLOG_SOCKET__APPEND 0x00000200UL -#define NETLINK_NFLOG_SOCKET__BIND 0x00000400UL -#define NETLINK_NFLOG_SOCKET__CONNECT 0x00000800UL -#define NETLINK_NFLOG_SOCKET__LISTEN 0x00001000UL -#define NETLINK_NFLOG_SOCKET__ACCEPT 0x00002000UL -#define NETLINK_NFLOG_SOCKET__GETOPT 0x00004000UL -#define NETLINK_NFLOG_SOCKET__SETOPT 0x00008000UL -#define NETLINK_NFLOG_SOCKET__SHUTDOWN 0x00010000UL -#define NETLINK_NFLOG_SOCKET__RECVFROM 0x00020000UL -#define NETLINK_NFLOG_SOCKET__SENDTO 0x00040000UL -#define NETLINK_NFLOG_SOCKET__RECV_MSG 0x00080000UL -#define NETLINK_NFLOG_SOCKET__SEND_MSG 0x00100000UL -#define NETLINK_NFLOG_SOCKET__NAME_BIND 0x00200000UL -#define NETLINK_XFRM_SOCKET__IOCTL 0x00000001UL -#define NETLINK_XFRM_SOCKET__READ 0x00000002UL -#define NETLINK_XFRM_SOCKET__WRITE 0x00000004UL -#define NETLINK_XFRM_SOCKET__CREATE 0x00000008UL -#define NETLINK_XFRM_SOCKET__GETATTR 0x00000010UL -#define NETLINK_XFRM_SOCKET__SETATTR 0x00000020UL -#define NETLINK_XFRM_SOCKET__LOCK 0x00000040UL -#define NETLINK_XFRM_SOCKET__RELABELFROM 0x00000080UL -#define NETLINK_XFRM_SOCKET__RELABELTO 0x00000100UL -#define NETLINK_XFRM_SOCKET__APPEND 0x00000200UL -#define NETLINK_XFRM_SOCKET__BIND 0x00000400UL -#define NETLINK_XFRM_SOCKET__CONNECT 0x00000800UL -#define NETLINK_XFRM_SOCKET__LISTEN 0x00001000UL -#define NETLINK_XFRM_SOCKET__ACCEPT 0x00002000UL -#define NETLINK_XFRM_SOCKET__GETOPT 0x00004000UL -#define NETLINK_XFRM_SOCKET__SETOPT 0x00008000UL -#define NETLINK_XFRM_SOCKET__SHUTDOWN 0x00010000UL -#define NETLINK_XFRM_SOCKET__RECVFROM 0x00020000UL -#define NETLINK_XFRM_SOCKET__SENDTO 0x00040000UL -#define NETLINK_XFRM_SOCKET__RECV_MSG 0x00080000UL -#define NETLINK_XFRM_SOCKET__SEND_MSG 0x00100000UL -#define NETLINK_XFRM_SOCKET__NAME_BIND 0x00200000UL -#define NETLINK_XFRM_SOCKET__NLMSG_READ 0x00400000UL -#define NETLINK_XFRM_SOCKET__NLMSG_WRITE 0x00800000UL -#define NETLINK_SELINUX_SOCKET__IOCTL 0x00000001UL -#define NETLINK_SELINUX_SOCKET__READ 0x00000002UL -#define NETLINK_SELINUX_SOCKET__WRITE 0x00000004UL -#define NETLINK_SELINUX_SOCKET__CREATE 0x00000008UL -#define NETLINK_SELINUX_SOCKET__GETATTR 0x00000010UL -#define NETLINK_SELINUX_SOCKET__SETATTR 0x00000020UL -#define NETLINK_SELINUX_SOCKET__LOCK 0x00000040UL -#define NETLINK_SELINUX_SOCKET__RELABELFROM 0x00000080UL -#define NETLINK_SELINUX_SOCKET__RELABELTO 0x00000100UL -#define NETLINK_SELINUX_SOCKET__APPEND 0x00000200UL -#define NETLINK_SELINUX_SOCKET__BIND 0x00000400UL -#define NETLINK_SELINUX_SOCKET__CONNECT 0x00000800UL -#define NETLINK_SELINUX_SOCKET__LISTEN 0x00001000UL -#define NETLINK_SELINUX_SOCKET__ACCEPT 0x00002000UL -#define NETLINK_SELINUX_SOCKET__GETOPT 0x00004000UL -#define NETLINK_SELINUX_SOCKET__SETOPT 0x00008000UL -#define NETLINK_SELINUX_SOCKET__SHUTDOWN 0x00010000UL -#define NETLINK_SELINUX_SOCKET__RECVFROM 0x00020000UL -#define NETLINK_SELINUX_SOCKET__SENDTO 0x00040000UL -#define NETLINK_SELINUX_SOCKET__RECV_MSG 0x00080000UL -#define NETLINK_SELINUX_SOCKET__SEND_MSG 0x00100000UL -#define NETLINK_SELINUX_SOCKET__NAME_BIND 0x00200000UL -#define NETLINK_AUDIT_SOCKET__IOCTL 0x00000001UL -#define NETLINK_AUDIT_SOCKET__READ 0x00000002UL -#define NETLINK_AUDIT_SOCKET__WRITE 0x00000004UL -#define NETLINK_AUDIT_SOCKET__CREATE 0x00000008UL -#define NETLINK_AUDIT_SOCKET__GETATTR 0x00000010UL -#define NETLINK_AUDIT_SOCKET__SETATTR 0x00000020UL -#define NETLINK_AUDIT_SOCKET__LOCK 0x00000040UL -#define NETLINK_AUDIT_SOCKET__RELABELFROM 0x00000080UL -#define NETLINK_AUDIT_SOCKET__RELABELTO 0x00000100UL -#define NETLINK_AUDIT_SOCKET__APPEND 0x00000200UL -#define NETLINK_AUDIT_SOCKET__BIND 0x00000400UL -#define NETLINK_AUDIT_SOCKET__CONNECT 0x00000800UL -#define NETLINK_AUDIT_SOCKET__LISTEN 0x00001000UL -#define NETLINK_AUDIT_SOCKET__ACCEPT 0x00002000UL -#define NETLINK_AUDIT_SOCKET__GETOPT 0x00004000UL -#define NETLINK_AUDIT_SOCKET__SETOPT 0x00008000UL -#define NETLINK_AUDIT_SOCKET__SHUTDOWN 0x00010000UL -#define NETLINK_AUDIT_SOCKET__RECVFROM 0x00020000UL -#define NETLINK_AUDIT_SOCKET__SENDTO 0x00040000UL -#define NETLINK_AUDIT_SOCKET__RECV_MSG 0x00080000UL -#define NETLINK_AUDIT_SOCKET__SEND_MSG 0x00100000UL -#define NETLINK_AUDIT_SOCKET__NAME_BIND 0x00200000UL -#define NETLINK_AUDIT_SOCKET__NLMSG_READ 0x00400000UL -#define NETLINK_AUDIT_SOCKET__NLMSG_WRITE 0x00800000UL -#define NETLINK_AUDIT_SOCKET__NLMSG_RELAY 0x01000000UL -#define NETLINK_AUDIT_SOCKET__NLMSG_READPRIV 0x02000000UL -#define NETLINK_AUDIT_SOCKET__NLMSG_TTY_AUDIT 0x04000000UL -#define NETLINK_IP6FW_SOCKET__IOCTL 0x00000001UL -#define NETLINK_IP6FW_SOCKET__READ 0x00000002UL -#define NETLINK_IP6FW_SOCKET__WRITE 0x00000004UL -#define NETLINK_IP6FW_SOCKET__CREATE 0x00000008UL -#define NETLINK_IP6FW_SOCKET__GETATTR 0x00000010UL -#define NETLINK_IP6FW_SOCKET__SETATTR 0x00000020UL -#define NETLINK_IP6FW_SOCKET__LOCK 0x00000040UL -#define NETLINK_IP6FW_SOCKET__RELABELFROM 0x00000080UL -#define NETLINK_IP6FW_SOCKET__RELABELTO 0x00000100UL -#define NETLINK_IP6FW_SOCKET__APPEND 0x00000200UL -#define NETLINK_IP6FW_SOCKET__BIND 0x00000400UL -#define NETLINK_IP6FW_SOCKET__CONNECT 0x00000800UL -#define NETLINK_IP6FW_SOCKET__LISTEN 0x00001000UL -#define NETLINK_IP6FW_SOCKET__ACCEPT 0x00002000UL -#define NETLINK_IP6FW_SOCKET__GETOPT 0x00004000UL -#define NETLINK_IP6FW_SOCKET__SETOPT 0x00008000UL -#define NETLINK_IP6FW_SOCKET__SHUTDOWN 0x00010000UL -#define NETLINK_IP6FW_SOCKET__RECVFROM 0x00020000UL -#define NETLINK_IP6FW_SOCKET__SENDTO 0x00040000UL -#define NETLINK_IP6FW_SOCKET__RECV_MSG 0x00080000UL -#define NETLINK_IP6FW_SOCKET__SEND_MSG 0x00100000UL -#define NETLINK_IP6FW_SOCKET__NAME_BIND 0x00200000UL -#define NETLINK_IP6FW_SOCKET__NLMSG_READ 0x00400000UL -#define NETLINK_IP6FW_SOCKET__NLMSG_WRITE 0x00800000UL -#define NETLINK_DNRT_SOCKET__IOCTL 0x00000001UL -#define NETLINK_DNRT_SOCKET__READ 0x00000002UL -#define NETLINK_DNRT_SOCKET__WRITE 0x00000004UL -#define NETLINK_DNRT_SOCKET__CREATE 0x00000008UL -#define NETLINK_DNRT_SOCKET__GETATTR 0x00000010UL -#define NETLINK_DNRT_SOCKET__SETATTR 0x00000020UL -#define NETLINK_DNRT_SOCKET__LOCK 0x00000040UL -#define NETLINK_DNRT_SOCKET__RELABELFROM 0x00000080UL -#define NETLINK_DNRT_SOCKET__RELABELTO 0x00000100UL -#define NETLINK_DNRT_SOCKET__APPEND 0x00000200UL -#define NETLINK_DNRT_SOCKET__BIND 0x00000400UL -#define NETLINK_DNRT_SOCKET__CONNECT 0x00000800UL -#define NETLINK_DNRT_SOCKET__LISTEN 0x00001000UL -#define NETLINK_DNRT_SOCKET__ACCEPT 0x00002000UL -#define NETLINK_DNRT_SOCKET__GETOPT 0x00004000UL -#define NETLINK_DNRT_SOCKET__SETOPT 0x00008000UL -#define NETLINK_DNRT_SOCKET__SHUTDOWN 0x00010000UL -#define NETLINK_DNRT_SOCKET__RECVFROM 0x00020000UL -#define NETLINK_DNRT_SOCKET__SENDTO 0x00040000UL -#define NETLINK_DNRT_SOCKET__RECV_MSG 0x00080000UL -#define NETLINK_DNRT_SOCKET__SEND_MSG 0x00100000UL -#define NETLINK_DNRT_SOCKET__NAME_BIND 0x00200000UL -#define ASSOCIATION__SENDTO 0x00000001UL -#define ASSOCIATION__RECVFROM 0x00000002UL -#define ASSOCIATION__SETCONTEXT 0x00000004UL -#define ASSOCIATION__POLMATCH 0x00000008UL -#define NETLINK_KOBJECT_UEVENT_SOCKET__IOCTL 0x00000001UL -#define NETLINK_KOBJECT_UEVENT_SOCKET__READ 0x00000002UL -#define NETLINK_KOBJECT_UEVENT_SOCKET__WRITE 0x00000004UL -#define NETLINK_KOBJECT_UEVENT_SOCKET__CREATE 0x00000008UL -#define NETLINK_KOBJECT_UEVENT_SOCKET__GETATTR 0x00000010UL -#define NETLINK_KOBJECT_UEVENT_SOCKET__SETATTR 0x00000020UL -#define NETLINK_KOBJECT_UEVENT_SOCKET__LOCK 0x00000040UL -#define NETLINK_KOBJECT_UEVENT_SOCKET__RELABELFROM 0x00000080UL -#define NETLINK_KOBJECT_UEVENT_SOCKET__RELABELTO 0x00000100UL -#define NETLINK_KOBJECT_UEVENT_SOCKET__APPEND 0x00000200UL -#define NETLINK_KOBJECT_UEVENT_SOCKET__BIND 0x00000400UL -#define NETLINK_KOBJECT_UEVENT_SOCKET__CONNECT 0x00000800UL -#define NETLINK_KOBJECT_UEVENT_SOCKET__LISTEN 0x00001000UL -#define NETLINK_KOBJECT_UEVENT_SOCKET__ACCEPT 0x00002000UL -#define NETLINK_KOBJECT_UEVENT_SOCKET__GETOPT 0x00004000UL -#define NETLINK_KOBJECT_UEVENT_SOCKET__SETOPT 0x00008000UL -#define NETLINK_KOBJECT_UEVENT_SOCKET__SHUTDOWN 0x00010000UL -#define NETLINK_KOBJECT_UEVENT_SOCKET__RECVFROM 0x00020000UL -#define NETLINK_KOBJECT_UEVENT_SOCKET__SENDTO 0x00040000UL -#define NETLINK_KOBJECT_UEVENT_SOCKET__RECV_MSG 0x00080000UL -#define NETLINK_KOBJECT_UEVENT_SOCKET__SEND_MSG 0x00100000UL -#define NETLINK_KOBJECT_UEVENT_SOCKET__NAME_BIND 0x00200000UL -#define APPLETALK_SOCKET__IOCTL 0x00000001UL -#define APPLETALK_SOCKET__READ 0x00000002UL -#define APPLETALK_SOCKET__WRITE 0x00000004UL -#define APPLETALK_SOCKET__CREATE 0x00000008UL -#define APPLETALK_SOCKET__GETATTR 0x00000010UL -#define APPLETALK_SOCKET__SETATTR 0x00000020UL -#define APPLETALK_SOCKET__LOCK 0x00000040UL -#define APPLETALK_SOCKET__RELABELFROM 0x00000080UL -#define APPLETALK_SOCKET__RELABELTO 0x00000100UL -#define APPLETALK_SOCKET__APPEND 0x00000200UL -#define APPLETALK_SOCKET__BIND 0x00000400UL -#define APPLETALK_SOCKET__CONNECT 0x00000800UL -#define APPLETALK_SOCKET__LISTEN 0x00001000UL -#define APPLETALK_SOCKET__ACCEPT 0x00002000UL -#define APPLETALK_SOCKET__GETOPT 0x00004000UL -#define APPLETALK_SOCKET__SETOPT 0x00008000UL -#define APPLETALK_SOCKET__SHUTDOWN 0x00010000UL -#define APPLETALK_SOCKET__RECVFROM 0x00020000UL -#define APPLETALK_SOCKET__SENDTO 0x00040000UL -#define APPLETALK_SOCKET__RECV_MSG 0x00080000UL -#define APPLETALK_SOCKET__SEND_MSG 0x00100000UL -#define APPLETALK_SOCKET__NAME_BIND 0x00200000UL -#define PACKET__SEND 0x00000001UL -#define PACKET__RECV 0x00000002UL -#define PACKET__RELABELTO 0x00000004UL -#define PACKET__FLOW_IN 0x00000008UL -#define PACKET__FLOW_OUT 0x00000010UL -#define PACKET__FORWARD_IN 0x00000020UL -#define PACKET__FORWARD_OUT 0x00000040UL -#define KEY__VIEW 0x00000001UL -#define KEY__READ 0x00000002UL -#define KEY__WRITE 0x00000004UL -#define KEY__SEARCH 0x00000008UL -#define KEY__LINK 0x00000010UL -#define KEY__SETATTR 0x00000020UL -#define KEY__CREATE 0x00000040UL -#define DCCP_SOCKET__IOCTL 0x00000001UL -#define DCCP_SOCKET__READ 0x00000002UL -#define DCCP_SOCKET__WRITE 0x00000004UL -#define DCCP_SOCKET__CREATE 0x00000008UL -#define DCCP_SOCKET__GETATTR 0x00000010UL -#define DCCP_SOCKET__SETATTR 0x00000020UL -#define DCCP_SOCKET__LOCK 0x00000040UL -#define DCCP_SOCKET__RELABELFROM 0x00000080UL -#define DCCP_SOCKET__RELABELTO 0x00000100UL -#define DCCP_SOCKET__APPEND 0x00000200UL -#define DCCP_SOCKET__BIND 0x00000400UL -#define DCCP_SOCKET__CONNECT 0x00000800UL -#define DCCP_SOCKET__LISTEN 0x00001000UL -#define DCCP_SOCKET__ACCEPT 0x00002000UL -#define DCCP_SOCKET__GETOPT 0x00004000UL -#define DCCP_SOCKET__SETOPT 0x00008000UL -#define DCCP_SOCKET__SHUTDOWN 0x00010000UL -#define DCCP_SOCKET__RECVFROM 0x00020000UL -#define DCCP_SOCKET__SENDTO 0x00040000UL -#define DCCP_SOCKET__RECV_MSG 0x00080000UL -#define DCCP_SOCKET__SEND_MSG 0x00100000UL -#define DCCP_SOCKET__NAME_BIND 0x00200000UL -#define DCCP_SOCKET__NODE_BIND 0x00400000UL -#define DCCP_SOCKET__NAME_CONNECT 0x00800000UL -#define MEMPROTECT__MMAP_ZERO 0x00000001UL -#define PEER__RECV 0x00000001UL -#define KERNEL_SERVICE__USE_AS_OVERRIDE 0x00000001UL -#define KERNEL_SERVICE__CREATE_FILES_AS 0x00000002UL diff --git a/security/selinux/include/avc_ss.h b/security/selinux/include/avc_ss.h index bb1ec801bdfe..4677aa519b04 100644 --- a/security/selinux/include/avc_ss.h +++ b/security/selinux/include/avc_ss.h @@ -10,26 +10,13 @@ int avc_ss_reset(u32 seqno); -struct av_perm_to_string { - u16 tclass; - u32 value; +/* Class/perm mapping support */ +struct security_class_mapping { const char *name; + const char *perms[sizeof(u32) * 8 + 1]; }; -struct av_inherit { - const char **common_pts; - u32 common_base; - u16 tclass; -}; - -struct selinux_class_perm { - const struct av_perm_to_string *av_perm_to_string; - u32 av_pts_len; - u32 cts_len; - const char **class_to_string; - const struct av_inherit *av_inherit; - u32 av_inherit_len; -}; +extern struct security_class_mapping secclass_map[]; #endif /* _SELINUX_AVC_SS_H_ */ diff --git a/security/selinux/include/class_to_string.h b/security/selinux/include/class_to_string.h deleted file mode 100644 index 7ab9299bfb6b..000000000000 --- a/security/selinux/include/class_to_string.h +++ /dev/null @@ -1,80 +0,0 @@ -/* This file is automatically generated. Do not edit. */ -/* - * Security object class definitions - */ - S_(NULL) - S_("security") - S_("process") - S_("system") - S_("capability") - S_("filesystem") - S_("file") - S_("dir") - S_("fd") - S_("lnk_file") - S_("chr_file") - S_("blk_file") - S_("sock_file") - S_("fifo_file") - S_("socket") - S_("tcp_socket") - S_("udp_socket") - S_("rawip_socket") - S_("node") - S_("netif") - S_("netlink_socket") - S_("packet_socket") - S_("key_socket") - S_("unix_stream_socket") - S_("unix_dgram_socket") - S_("sem") - S_("msg") - S_("msgq") - S_("shm") - S_("ipc") - S_(NULL) - S_(NULL) - S_(NULL) - S_(NULL) - S_(NULL) - S_(NULL) - S_(NULL) - S_(NULL) - S_(NULL) - S_(NULL) - S_(NULL) - S_(NULL) - S_(NULL) - S_("netlink_route_socket") - S_("netlink_firewall_socket") - S_("netlink_tcpdiag_socket") - S_("netlink_nflog_socket") - S_("netlink_xfrm_socket") - S_("netlink_selinux_socket") - S_("netlink_audit_socket") - S_("netlink_ip6fw_socket") - S_("netlink_dnrt_socket") - S_(NULL) - S_(NULL) - S_("association") - S_("netlink_kobject_uevent_socket") - S_("appletalk_socket") - S_("packet") - S_("key") - S_(NULL) - S_("dccp_socket") - S_("memprotect") - S_(NULL) - S_(NULL) - S_(NULL) - S_(NULL) - S_(NULL) - S_(NULL) - S_("peer") - S_("capability2") - S_(NULL) - S_(NULL) - S_(NULL) - S_(NULL) - S_("kernel_service") - S_("tun_socket") diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h new file mode 100644 index 000000000000..8b32e959bb2e --- /dev/null +++ b/security/selinux/include/classmap.h @@ -0,0 +1,150 @@ +#define COMMON_FILE_SOCK_PERMS "ioctl", "read", "write", "create", \ + "getattr", "setattr", "lock", "relabelfrom", "relabelto", "append" + +#define COMMON_FILE_PERMS COMMON_FILE_SOCK_PERMS, "unlink", "link", \ + "rename", "execute", "swapon", "quotaon", "mounton" + +#define COMMON_SOCK_PERMS COMMON_FILE_SOCK_PERMS, "bind", "connect", \ + "listen", "accept", "getopt", "setopt", "shutdown", "recvfrom", \ + "sendto", "recv_msg", "send_msg", "name_bind" + +#define COMMON_IPC_PERMS "create", "destroy", "getattr", "setattr", "read", \ + "write", "associate", "unix_read", "unix_write" + +struct security_class_mapping secclass_map[] = { + { "security", + { "compute_av", "compute_create", "compute_member", + "check_context", "load_policy", "compute_relabel", + "compute_user", "setenforce", "setbool", "setsecparam", + "setcheckreqprot", NULL } }, + { "process", + { "fork", "transition", "sigchld", "sigkill", + "sigstop", "signull", "signal", "ptrace", "getsched", "setsched", + "getsession", "getpgid", "setpgid", "getcap", "setcap", "share", + "getattr", "setexec", "setfscreate", "noatsecure", "siginh", + "setrlimit", "rlimitinh", "dyntransition", "setcurrent", + "execmem", "execstack", "execheap", "setkeycreate", + "setsockcreate", NULL } }, + { "system", + { "ipc_info", "syslog_read", "syslog_mod", + "syslog_console", "module_request", NULL } }, + { "capability", + { "chown", "dac_override", "dac_read_search", + "fowner", "fsetid", "kill", "setgid", "setuid", "setpcap", + "linux_immutable", "net_bind_service", "net_broadcast", + "net_admin", "net_raw", "ipc_lock", "ipc_owner", "sys_module", + "sys_rawio", "sys_chroot", "sys_ptrace", "sys_pacct", "sys_admin", + "sys_boot", "sys_nice", "sys_resource", "sys_time", + "sys_tty_config", "mknod", "lease", "audit_write", + "audit_control", "setfcap", NULL } }, + { "filesystem", + { "mount", "remount", "unmount", "getattr", + "relabelfrom", "relabelto", "transition", "associate", "quotamod", + "quotaget", NULL } }, + { "file", + { COMMON_FILE_PERMS, + "execute_no_trans", "entrypoint", "execmod", "open", NULL } }, + { "dir", + { COMMON_FILE_PERMS, "add_name", "remove_name", + "reparent", "search", "rmdir", "open", NULL } }, + { "fd", { "use", NULL } }, + { "lnk_file", + { COMMON_FILE_PERMS, NULL } }, + { "chr_file", + { COMMON_FILE_PERMS, + "execute_no_trans", "entrypoint", "execmod", "open", NULL } }, + { "blk_file", + { COMMON_FILE_PERMS, "open", NULL } }, + { "sock_file", + { COMMON_FILE_PERMS, "open", NULL } }, + { "fifo_file", + { COMMON_FILE_PERMS, "open", NULL } }, + { "socket", + { COMMON_SOCK_PERMS, NULL } }, + { "tcp_socket", + { COMMON_SOCK_PERMS, + "connectto", "newconn", "acceptfrom", "node_bind", "name_connect", + NULL } }, + { "udp_socket", + { COMMON_SOCK_PERMS, + "node_bind", NULL } }, + { "rawip_socket", + { COMMON_SOCK_PERMS, + "node_bind", NULL } }, + { "node", + { "tcp_recv", "tcp_send", "udp_recv", "udp_send", + "rawip_recv", "rawip_send", "enforce_dest", + "dccp_recv", "dccp_send", "recvfrom", "sendto", NULL } }, + { "netif", + { "tcp_recv", "tcp_send", "udp_recv", "udp_send", + "rawip_recv", "rawip_send", "dccp_recv", "dccp_send", + "ingress", "egress", NULL } }, + { "netlink_socket", + { COMMON_SOCK_PERMS, NULL } }, + { "packet_socket", + { COMMON_SOCK_PERMS, NULL } }, + { "key_socket", + { COMMON_SOCK_PERMS, NULL } }, + { "unix_stream_socket", + { COMMON_SOCK_PERMS, "connectto", "newconn", "acceptfrom", NULL + } }, + { "unix_dgram_socket", + { COMMON_SOCK_PERMS, NULL + } }, + { "sem", + { COMMON_IPC_PERMS, NULL } }, + { "msg", { "send", "receive", NULL } }, + { "msgq", + { COMMON_IPC_PERMS, "enqueue", NULL } }, + { "shm", + { COMMON_IPC_PERMS, "lock", NULL } }, + { "ipc", + { COMMON_IPC_PERMS, NULL } }, + { "netlink_route_socket", + { COMMON_SOCK_PERMS, + "nlmsg_read", "nlmsg_write", NULL } }, + { "netlink_firewall_socket", + { COMMON_SOCK_PERMS, + "nlmsg_read", "nlmsg_write", NULL } }, + { "netlink_tcpdiag_socket", + { COMMON_SOCK_PERMS, + "nlmsg_read", "nlmsg_write", NULL } }, + { "netlink_nflog_socket", + { COMMON_SOCK_PERMS, NULL } }, + { "netlink_xfrm_socket", + { COMMON_SOCK_PERMS, + "nlmsg_read", "nlmsg_write", NULL } }, + { "netlink_selinux_socket", + { COMMON_SOCK_PERMS, NULL } }, + { "netlink_audit_socket", + { COMMON_SOCK_PERMS, + "nlmsg_read", "nlmsg_write", "nlmsg_relay", "nlmsg_readpriv", + "nlmsg_tty_audit", NULL } }, + { "netlink_ip6fw_socket", + { COMMON_SOCK_PERMS, + "nlmsg_read", "nlmsg_write", NULL } }, + { "netlink_dnrt_socket", + { COMMON_SOCK_PERMS, NULL } }, + { "association", + { "sendto", "recvfrom", "setcontext", "polmatch", NULL } }, + { "netlink_kobject_uevent_socket", + { COMMON_SOCK_PERMS, NULL } }, + { "appletalk_socket", + { COMMON_SOCK_PERMS, NULL } }, + { "packet", + { "send", "recv", "relabelto", "flow_in", "flow_out", + "forward_in", "forward_out", NULL } }, + { "key", + { "view", "read", "write", "search", "link", "setattr", "create", + NULL } }, + { "dccp_socket", + { COMMON_SOCK_PERMS, + "node_bind", "name_connect", NULL } }, + { "memprotect", { "mmap_zero", NULL } }, + { "peer", { "recv", NULL } }, + { "capability2", { "mac_override", "mac_admin", NULL } }, + { "kernel_service", { "use_as_override", "create_files_as", NULL } }, + { "tun_socket", + { COMMON_SOCK_PERMS, NULL } }, + { NULL } + }; diff --git a/security/selinux/include/common_perm_to_string.h b/security/selinux/include/common_perm_to_string.h deleted file mode 100644 index ce5b6e2fe9dd..000000000000 --- a/security/selinux/include/common_perm_to_string.h +++ /dev/null @@ -1,58 +0,0 @@ -/* This file is automatically generated. Do not edit. */ -TB_(common_file_perm_to_string) - S_("ioctl") - S_("read") - S_("write") - S_("create") - S_("getattr") - S_("setattr") - S_("lock") - S_("relabelfrom") - S_("relabelto") - S_("append") - S_("unlink") - S_("link") - S_("rename") - S_("execute") - S_("swapon") - S_("quotaon") - S_("mounton") -TE_(common_file_perm_to_string) - -TB_(common_socket_perm_to_string) - S_("ioctl") - S_("read") - S_("write") - S_("create") - S_("getattr") - S_("setattr") - S_("lock") - S_("relabelfrom") - S_("relabelto") - S_("append") - S_("bind") - S_("connect") - S_("listen") - S_("accept") - S_("getopt") - S_("setopt") - S_("shutdown") - S_("recvfrom") - S_("sendto") - S_("recv_msg") - S_("send_msg") - S_("name_bind") -TE_(common_socket_perm_to_string) - -TB_(common_ipc_perm_to_string) - S_("create") - S_("destroy") - S_("getattr") - S_("setattr") - S_("read") - S_("write") - S_("associate") - S_("unix_read") - S_("unix_write") -TE_(common_ipc_perm_to_string) - diff --git a/security/selinux/include/flask.h b/security/selinux/include/flask.h deleted file mode 100644 index f248500a1e3c..000000000000 --- a/security/selinux/include/flask.h +++ /dev/null @@ -1,91 +0,0 @@ -/* This file is automatically generated. Do not edit. */ -#ifndef _SELINUX_FLASK_H_ -#define _SELINUX_FLASK_H_ - -/* - * Security object class definitions - */ -#define SECCLASS_SECURITY 1 -#define SECCLASS_PROCESS 2 -#define SECCLASS_SYSTEM 3 -#define SECCLASS_CAPABILITY 4 -#define SECCLASS_FILESYSTEM 5 -#define SECCLASS_FILE 6 -#define SECCLASS_DIR 7 -#define SECCLASS_FD 8 -#define SECCLASS_LNK_FILE 9 -#define SECCLASS_CHR_FILE 10 -#define SECCLASS_BLK_FILE 11 -#define SECCLASS_SOCK_FILE 12 -#define SECCLASS_FIFO_FILE 13 -#define SECCLASS_SOCKET 14 -#define SECCLASS_TCP_SOCKET 15 -#define SECCLASS_UDP_SOCKET 16 -#define SECCLASS_RAWIP_SOCKET 17 -#define SECCLASS_NODE 18 -#define SECCLASS_NETIF 19 -#define SECCLASS_NETLINK_SOCKET 20 -#define SECCLASS_PACKET_SOCKET 21 -#define SECCLASS_KEY_SOCKET 22 -#define SECCLASS_UNIX_STREAM_SOCKET 23 -#define SECCLASS_UNIX_DGRAM_SOCKET 24 -#define SECCLASS_SEM 25 -#define SECCLASS_MSG 26 -#define SECCLASS_MSGQ 27 -#define SECCLASS_SHM 28 -#define SECCLASS_IPC 29 -#define SECCLASS_NETLINK_ROUTE_SOCKET 43 -#define SECCLASS_NETLINK_FIREWALL_SOCKET 44 -#define SECCLASS_NETLINK_TCPDIAG_SOCKET 45 -#define SECCLASS_NETLINK_NFLOG_SOCKET 46 -#define SECCLASS_NETLINK_XFRM_SOCKET 47 -#define SECCLASS_NETLINK_SELINUX_SOCKET 48 -#define SECCLASS_NETLINK_AUDIT_SOCKET 49 -#define SECCLASS_NETLINK_IP6FW_SOCKET 50 -#define SECCLASS_NETLINK_DNRT_SOCKET 51 -#define SECCLASS_ASSOCIATION 54 -#define SECCLASS_NETLINK_KOBJECT_UEVENT_SOCKET 55 -#define SECCLASS_APPLETALK_SOCKET 56 -#define SECCLASS_PACKET 57 -#define SECCLASS_KEY 58 -#define SECCLASS_DCCP_SOCKET 60 -#define SECCLASS_MEMPROTECT 61 -#define SECCLASS_PEER 68 -#define SECCLASS_CAPABILITY2 69 -#define SECCLASS_KERNEL_SERVICE 74 -#define SECCLASS_TUN_SOCKET 75 - -/* - * Security identifier indices for initial entities - */ -#define SECINITSID_KERNEL 1 -#define SECINITSID_SECURITY 2 -#define SECINITSID_UNLABELED 3 -#define SECINITSID_FS 4 -#define SECINITSID_FILE 5 -#define SECINITSID_FILE_LABELS 6 -#define SECINITSID_INIT 7 -#define SECINITSID_ANY_SOCKET 8 -#define SECINITSID_PORT 9 -#define SECINITSID_NETIF 10 -#define SECINITSID_NETMSG 11 -#define SECINITSID_NODE 12 -#define SECINITSID_IGMP_PACKET 13 -#define SECINITSID_ICMP_SOCKET 14 -#define SECINITSID_TCP_SOCKET 15 -#define SECINITSID_SYSCTL_MODPROBE 16 -#define SECINITSID_SYSCTL 17 -#define SECINITSID_SYSCTL_FS 18 -#define SECINITSID_SYSCTL_KERNEL 19 -#define SECINITSID_SYSCTL_NET 20 -#define SECINITSID_SYSCTL_NET_UNIX 21 -#define SECINITSID_SYSCTL_VM 22 -#define SECINITSID_SYSCTL_DEV 23 -#define SECINITSID_KMOD 24 -#define SECINITSID_POLICY 25 -#define SECINITSID_SCMP_PACKET 26 -#define SECINITSID_DEVNULL 27 - -#define SECINITSID_NUM 27 - -#endif diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h index ca835795a8b3..2553266ad793 100644 --- a/security/selinux/include/security.h +++ b/security/selinux/include/security.h @@ -97,11 +97,18 @@ struct av_decision { #define AVD_FLAGS_PERMISSIVE 0x0001 int security_compute_av(u32 ssid, u32 tsid, - u16 tclass, u32 requested, - struct av_decision *avd); + u16 tclass, u32 requested, + struct av_decision *avd); + +int security_compute_av_user(u32 ssid, u32 tsid, + u16 tclass, u32 requested, + struct av_decision *avd); int security_transition_sid(u32 ssid, u32 tsid, - u16 tclass, u32 *out_sid); + u16 tclass, u32 *out_sid); + +int security_transition_sid_user(u32 ssid, u32 tsid, + u16 tclass, u32 *out_sid); int security_member_sid(u32 ssid, u32 tsid, u16 tclass, u32 *out_sid); diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index b4fc506e7a87..fab36fdf2769 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -522,7 +522,7 @@ static ssize_t sel_write_access(struct file *file, char *buf, size_t size) if (length < 0) goto out2; - length = security_compute_av(ssid, tsid, tclass, req, &avd); + length = security_compute_av_user(ssid, tsid, tclass, req, &avd); if (length < 0) goto out2; @@ -571,7 +571,7 @@ static ssize_t sel_write_create(struct file *file, char *buf, size_t size) if (length < 0) goto out2; - length = security_transition_sid(ssid, tsid, tclass, &newsid); + length = security_transition_sid_user(ssid, tsid, tclass, &newsid); if (length < 0) goto out2; diff --git a/security/selinux/ss/Makefile b/security/selinux/ss/Makefile index bad78779b9b0..15d4e62917de 100644 --- a/security/selinux/ss/Makefile +++ b/security/selinux/ss/Makefile @@ -2,7 +2,7 @@ # Makefile for building the SELinux security server as part of the kernel tree. # -EXTRA_CFLAGS += -Isecurity/selinux/include +EXTRA_CFLAGS += -Isecurity/selinux -Isecurity/selinux/include obj-y := ss.o ss-y := ebitmap.o hashtab.o symtab.o sidtab.o avtab.o policydb.o services.o conditional.o mls.o diff --git a/security/selinux/ss/mls.c b/security/selinux/ss/mls.c index b5407f16c2a4..3f2b2706b5bb 100644 --- a/security/selinux/ss/mls.c +++ b/security/selinux/ss/mls.c @@ -532,7 +532,7 @@ int mls_compute_sid(struct context *scontext, } /* Fallthrough */ case AVTAB_CHANGE: - if (tclass == SECCLASS_PROCESS) + if (tclass == policydb.process_class) /* Use the process MLS attributes. */ return mls_context_cpy(newcontext, scontext); else diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c index 72e4a54973aa..f03667213ea8 100644 --- a/security/selinux/ss/policydb.c +++ b/security/selinux/ss/policydb.c @@ -713,7 +713,6 @@ void policydb_destroy(struct policydb *p) ebitmap_destroy(&p->type_attr_map[i]); } kfree(p->type_attr_map); - kfree(p->undefined_perms); ebitmap_destroy(&p->policycaps); ebitmap_destroy(&p->permissive_map); @@ -1640,6 +1639,40 @@ static int policydb_bounds_sanity_check(struct policydb *p) extern int ss_initialized; +u16 string_to_security_class(struct policydb *p, const char *name) +{ + struct class_datum *cladatum; + + cladatum = hashtab_search(p->p_classes.table, name); + if (!cladatum) + return 0; + + return cladatum->value; +} + +u32 string_to_av_perm(struct policydb *p, u16 tclass, const char *name) +{ + struct class_datum *cladatum; + struct perm_datum *perdatum = NULL; + struct common_datum *comdatum; + + if (!tclass || tclass > p->p_classes.nprim) + return 0; + + cladatum = p->class_val_to_struct[tclass-1]; + comdatum = cladatum->comdatum; + if (comdatum) + perdatum = hashtab_search(comdatum->permissions.table, + name); + if (!perdatum) + perdatum = hashtab_search(cladatum->permissions.table, + name); + if (!perdatum) + return 0; + + return 1U << (perdatum->value-1); +} + /* * Read the configuration data from a policy database binary * representation file into a policy database structure. @@ -1861,6 +1894,16 @@ int policydb_read(struct policydb *p, void *fp) if (rc) goto bad; + p->process_class = string_to_security_class(p, "process"); + if (!p->process_class) + goto bad; + p->process_trans_perms = string_to_av_perm(p, p->process_class, + "transition"); + p->process_trans_perms |= string_to_av_perm(p, p->process_class, + "dyntransition"); + if (!p->process_trans_perms) + goto bad; + for (i = 0; i < info->ocon_num; i++) { rc = next_entry(buf, fp, sizeof(u32)); if (rc < 0) @@ -2101,7 +2144,7 @@ int policydb_read(struct policydb *p, void *fp) goto bad; rt->target_class = le32_to_cpu(buf[0]); } else - rt->target_class = SECCLASS_PROCESS; + rt->target_class = p->process_class; if (!policydb_type_isvalid(p, rt->source_type) || !policydb_type_isvalid(p, rt->target_type) || !policydb_class_isvalid(p, rt->target_class)) { diff --git a/security/selinux/ss/policydb.h b/security/selinux/ss/policydb.h index 55152d498b53..cdcc5700946f 100644 --- a/security/selinux/ss/policydb.h +++ b/security/selinux/ss/policydb.h @@ -254,7 +254,9 @@ struct policydb { unsigned int reject_unknown : 1; unsigned int allow_unknown : 1; - u32 *undefined_perms; + + u16 process_class; + u32 process_trans_perms; }; extern void policydb_destroy(struct policydb *p); @@ -295,5 +297,8 @@ static inline int next_entry(void *buf, struct policy_file *fp, size_t bytes) return 0; } +extern u16 string_to_security_class(struct policydb *p, const char *name); +extern u32 string_to_av_perm(struct policydb *p, u16 tclass, const char *name); + #endif /* _SS_POLICYDB_H_ */ diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c index ff17820d35ec..d6bb20cbad62 100644 --- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -65,16 +65,10 @@ #include "audit.h" extern void selnl_notify_policyload(u32 seqno); -unsigned int policydb_loaded_version; int selinux_policycap_netpeer; int selinux_policycap_openperm; -/* - * This is declared in avc.c - */ -extern const struct selinux_class_perm selinux_class_perm; - static DEFINE_RWLOCK(policy_rwlock); static struct sidtab sidtab; @@ -98,6 +92,165 @@ static int context_struct_compute_av(struct context *scontext, u16 tclass, u32 requested, struct av_decision *avd); + +struct selinux_mapping { + u16 value; /* policy value */ + unsigned num_perms; + u32 perms[sizeof(u32) * 8]; +}; + +static struct selinux_mapping *current_mapping; +static u16 current_mapping_size; + +static int selinux_set_mapping(struct policydb *pol, + struct security_class_mapping *map, + struct selinux_mapping **out_map_p, + u16 *out_map_size) +{ + struct selinux_mapping *out_map = NULL; + size_t size = sizeof(struct selinux_mapping); + u16 i, j; + unsigned k; + bool print_unknown_handle = false; + + /* Find number of classes in the input mapping */ + if (!map) + return -EINVAL; + i = 0; + while (map[i].name) + i++; + + /* Allocate space for the class records, plus one for class zero */ + out_map = kcalloc(++i, size, GFP_ATOMIC); + if (!out_map) + return -ENOMEM; + + /* Store the raw class and permission values */ + j = 0; + while (map[j].name) { + struct security_class_mapping *p_in = map + (j++); + struct selinux_mapping *p_out = out_map + j; + + /* An empty class string skips ahead */ + if (!strcmp(p_in->name, "")) { + p_out->num_perms = 0; + continue; + } + + p_out->value = string_to_security_class(pol, p_in->name); + if (!p_out->value) { + printk(KERN_INFO + "SELinux: Class %s not defined in policy.\n", + p_in->name); + if (pol->reject_unknown) + goto err; + p_out->num_perms = 0; + print_unknown_handle = true; + continue; + } + + k = 0; + while (p_in->perms && p_in->perms[k]) { + /* An empty permission string skips ahead */ + if (!*p_in->perms[k]) { + k++; + continue; + } + p_out->perms[k] = string_to_av_perm(pol, p_out->value, + p_in->perms[k]); + if (!p_out->perms[k]) { + printk(KERN_INFO + "SELinux: Permission %s in class %s not defined in policy.\n", + p_in->perms[k], p_in->name); + if (pol->reject_unknown) + goto err; + print_unknown_handle = true; + } + + k++; + } + p_out->num_perms = k; + } + + if (print_unknown_handle) + printk(KERN_INFO "SELinux: the above unknown classes and permissions will be %s\n", + pol->allow_unknown ? "allowed" : "denied"); + + *out_map_p = out_map; + *out_map_size = i; + return 0; +err: + kfree(out_map); + return -EINVAL; +} + +/* + * Get real, policy values from mapped values + */ + +static u16 unmap_class(u16 tclass) +{ + if (tclass < current_mapping_size) + return current_mapping[tclass].value; + + return tclass; +} + +static u32 unmap_perm(u16 tclass, u32 tperm) +{ + if (tclass < current_mapping_size) { + unsigned i; + u32 kperm = 0; + + for (i = 0; i < current_mapping[tclass].num_perms; i++) + if (tperm & (1<<i)) { + kperm |= current_mapping[tclass].perms[i]; + tperm &= ~(1<<i); + } + return kperm; + } + + return tperm; +} + +static void map_decision(u16 tclass, struct av_decision *avd, + int allow_unknown) +{ + if (tclass < current_mapping_size) { + unsigned i, n = current_mapping[tclass].num_perms; + u32 result; + + for (i = 0, result = 0; i < n; i++) { + if (avd->allowed & current_mapping[tclass].perms[i]) + result |= 1<<i; + if (allow_unknown && !current_mapping[tclass].perms[i]) + result |= 1<<i; + } + avd->allowed = result; + + for (i = 0, result = 0; i < n; i++) + if (avd->auditallow & current_mapping[tclass].perms[i]) + result |= 1<<i; + avd->auditallow = result; + + for (i = 0, result = 0; i < n; i++) { + if (avd->auditdeny & current_mapping[tclass].perms[i]) + result |= 1<<i; + if (!allow_unknown && !current_mapping[tclass].perms[i]) + result |= 1<<i; + } + /* + * In case the kernel has a bug and requests a permission + * between num_perms and the maximum permission number, we + * should audit that denial + */ + for (; i < (sizeof(u32)*8); i++) + result |= 1<<i; + avd->auditdeny = result; + } +} + + /* * Return the boolean value of a constraint expression * when it is applied to the specified source and target @@ -467,21 +620,9 @@ static int context_struct_compute_av(struct context *scontext, struct class_datum *tclass_datum; struct ebitmap *sattr, *tattr; struct ebitmap_node *snode, *tnode; - const struct selinux_class_perm *kdefs = &selinux_class_perm; unsigned int i, j; /* - * Remap extended Netlink classes for old policy versions. - * Do this here rather than socket_type_to_security_class() - * in case a newer policy version is loaded, allowing sockets - * to remain in the correct class. - */ - if (policydb_loaded_version < POLICYDB_VERSION_NLCLASS) - if (tclass >= SECCLASS_NETLINK_ROUTE_SOCKET && - tclass <= SECCLASS_NETLINK_DNRT_SOCKET) - tclass = SECCLASS_NETLINK_SOCKET; - - /* * Initialize the access vectors to the default values. */ avd->allowed = 0; @@ -490,33 +631,11 @@ static int context_struct_compute_av(struct context *scontext, avd->seqno = latest_granting; avd->flags = 0; - /* - * Check for all the invalid cases. - * - tclass 0 - * - tclass > policy and > kernel - * - tclass > policy but is a userspace class - * - tclass > policy but we do not allow unknowns - */ - if (unlikely(!tclass)) - goto inval_class; - if (unlikely(tclass > policydb.p_classes.nprim)) - if (tclass > kdefs->cts_len || - !kdefs->class_to_string[tclass] || - !policydb.allow_unknown) - goto inval_class; - - /* - * Kernel class and we allow unknown so pad the allow decision - * the pad will be all 1 for unknown classes. - */ - if (tclass <= kdefs->cts_len && policydb.allow_unknown) - avd->allowed = policydb.undefined_perms[tclass - 1]; - - /* - * Not in policy. Since decision is completed (all 1 or all 0) return. - */ - if (unlikely(tclass > policydb.p_classes.nprim)) - return 0; + if (unlikely(!tclass || tclass > policydb.p_classes.nprim)) { + if (printk_ratelimit()) + printk(KERN_WARNING "SELinux: Invalid class %hu\n", tclass); + return -EINVAL; + } tclass_datum = policydb.class_val_to_struct[tclass - 1]; @@ -568,8 +687,8 @@ static int context_struct_compute_av(struct context *scontext, * role is changing, then check the (current_role, new_role) * pair. */ - if (tclass == SECCLASS_PROCESS && - (avd->allowed & (PROCESS__TRANSITION | PROCESS__DYNTRANSITION)) && + if (tclass == policydb.process_class && + (avd->allowed & policydb.process_trans_perms) && scontext->role != tcontext->role) { for (ra = policydb.role_allow; ra; ra = ra->next) { if (scontext->role == ra->role && @@ -577,8 +696,7 @@ static int context_struct_compute_av(struct context *scontext, break; } if (!ra) - avd->allowed &= ~(PROCESS__TRANSITION | - PROCESS__DYNTRANSITION); + avd->allowed &= ~policydb.process_trans_perms; } /* @@ -590,21 +708,6 @@ static int context_struct_compute_av(struct context *scontext, tclass, requested, avd); return 0; - -inval_class: - if (!tclass || tclass > kdefs->cts_len || - !kdefs->class_to_string[tclass]) { - if (printk_ratelimit()) - printk(KERN_ERR "SELinux: %s: unrecognized class %d\n", - __func__, tclass); - return -EINVAL; - } - - /* - * Known to the kernel, but not to the policy. - * Handle as a denial (allowed is 0). - */ - return 0; } static int security_validtrans_handle_fail(struct context *ocontext, @@ -636,13 +739,14 @@ out: } int security_validate_transition(u32 oldsid, u32 newsid, u32 tasksid, - u16 tclass) + u16 orig_tclass) { struct context *ocontext; struct context *ncontext; struct context *tcontext; struct class_datum *tclass_datum; struct constraint_node *constraint; + u16 tclass; int rc = 0; if (!ss_initialized) @@ -650,16 +754,7 @@ int security_validate_transition(u32 oldsid, u32 newsid, u32 tasksid, read_lock(&policy_rwlock); - /* - * Remap extended Netlink classes for old policy versions. - * Do this here rather than socket_type_to_security_class() - * in case a newer policy version is loaded, allowing sockets - * to remain in the correct class. - */ - if (policydb_loaded_version < POLICYDB_VERSION_NLCLASS) - if (tclass >= SECCLASS_NETLINK_ROUTE_SOCKET && - tclass <= SECCLASS_NETLINK_DNRT_SOCKET) - tclass = SECCLASS_NETLINK_SOCKET; + tclass = unmap_class(orig_tclass); if (!tclass || tclass > policydb.p_classes.nprim) { printk(KERN_ERR "SELinux: %s: unrecognized class %d\n", @@ -792,6 +887,38 @@ out: } +static int security_compute_av_core(u32 ssid, + u32 tsid, + u16 tclass, + u32 requested, + struct av_decision *avd) +{ + struct context *scontext = NULL, *tcontext = NULL; + int rc = 0; + + scontext = sidtab_search(&sidtab, ssid); + if (!scontext) { + printk(KERN_ERR "SELinux: %s: unrecognized SID %d\n", + __func__, ssid); + return -EINVAL; + } + tcontext = sidtab_search(&sidtab, tsid); + if (!tcontext) { + printk(KERN_ERR "SELinux: %s: unrecognized SID %d\n", + __func__, tsid); + return -EINVAL; + } + + rc = context_struct_compute_av(scontext, tcontext, tclass, + requested, avd); + + /* permissive domain? */ + if (ebitmap_get_bit(&policydb.permissive_map, scontext->type)) + avd->flags |= AVD_FLAGS_PERMISSIVE; + + return rc; +} + /** * security_compute_av - Compute access vector decisions. * @ssid: source security identifier @@ -807,12 +934,49 @@ out: */ int security_compute_av(u32 ssid, u32 tsid, - u16 tclass, - u32 requested, + u16 orig_tclass, + u32 orig_requested, struct av_decision *avd) { - struct context *scontext = NULL, *tcontext = NULL; - int rc = 0; + u16 tclass; + u32 requested; + int rc; + + read_lock(&policy_rwlock); + + if (!ss_initialized) + goto allow; + + requested = unmap_perm(orig_tclass, orig_requested); + tclass = unmap_class(orig_tclass); + if (unlikely(orig_tclass && !tclass)) { + if (policydb.allow_unknown) + goto allow; + rc = -EINVAL; + goto out; + } + rc = security_compute_av_core(ssid, tsid, tclass, requested, avd); + map_decision(orig_tclass, avd, policydb.allow_unknown); +out: + read_unlock(&policy_rwlock); + return rc; +allow: + avd->allowed = 0xffffffff; + avd->auditallow = 0; + avd->auditdeny = 0xffffffff; + avd->seqno = latest_granting; + avd->flags = 0; + rc = 0; + goto out; +} + +int security_compute_av_user(u32 ssid, + u32 tsid, + u16 tclass, + u32 requested, + struct av_decision *avd) +{ + int rc; if (!ss_initialized) { avd->allowed = 0xffffffff; @@ -823,29 +987,7 @@ int security_compute_av(u32 ssid, } read_lock(&policy_rwlock); - - scontext = sidtab_search(&sidtab, ssid); - if (!scontext) { - printk(KERN_ERR "SELinux: %s: unrecognized SID %d\n", - __func__, ssid); - rc = -EINVAL; - goto out; - } - tcontext = sidtab_search(&sidtab, tsid); - if (!tcontext) { - printk(KERN_ERR "SELinux: %s: unrecognized SID %d\n", - __func__, tsid); - rc = -EINVAL; - goto out; - } - - rc = context_struct_compute_av(scontext, tcontext, tclass, - requested, avd); - - /* permissive domain? */ - if (ebitmap_get_bit(&policydb.permissive_map, scontext->type)) - avd->flags |= AVD_FLAGS_PERMISSIVE; -out: + rc = security_compute_av_core(ssid, tsid, tclass, requested, avd); read_unlock(&policy_rwlock); return rc; } @@ -1204,20 +1346,22 @@ out: static int security_compute_sid(u32 ssid, u32 tsid, - u16 tclass, + u16 orig_tclass, u32 specified, - u32 *out_sid) + u32 *out_sid, + bool kern) { struct context *scontext = NULL, *tcontext = NULL, newcontext; struct role_trans *roletr = NULL; struct avtab_key avkey; struct avtab_datum *avdatum; struct avtab_node *node; + u16 tclass; int rc = 0; if (!ss_initialized) { - switch (tclass) { - case SECCLASS_PROCESS: + switch (orig_tclass) { + case SECCLASS_PROCESS: /* kernel value */ *out_sid = ssid; break; default: @@ -1231,6 +1375,11 @@ static int security_compute_sid(u32 ssid, read_lock(&policy_rwlock); + if (kern) + tclass = unmap_class(orig_tclass); + else + tclass = orig_tclass; + scontext = sidtab_search(&sidtab, ssid); if (!scontext) { printk(KERN_ERR "SELinux: %s: unrecognized SID %d\n", @@ -1260,13 +1409,11 @@ static int security_compute_sid(u32 ssid, } /* Set the role and type to default values. */ - switch (tclass) { - case SECCLASS_PROCESS: + if (tclass == policydb.process_class) { /* Use the current role and type of process. */ newcontext.role = scontext->role; newcontext.type = scontext->type; - break; - default: + } else { /* Use the well-defined object role. */ newcontext.role = OBJECT_R_VAL; /* Use the type of the related object. */ @@ -1297,8 +1444,7 @@ static int security_compute_sid(u32 ssid, } /* Check for class-specific changes. */ - switch (tclass) { - case SECCLASS_PROCESS: + if (tclass == policydb.process_class) { if (specified & AVTAB_TRANSITION) { /* Look for a role transition rule. */ for (roletr = policydb.role_tr; roletr; @@ -1311,9 +1457,6 @@ static int security_compute_sid(u32 ssid, } } } - break; - default: - break; } /* Set the MLS attributes. @@ -1358,7 +1501,17 @@ int security_transition_sid(u32 ssid, u16 tclass, u32 *out_sid) { - return security_compute_sid(ssid, tsid, tclass, AVTAB_TRANSITION, out_sid); + return security_compute_sid(ssid, tsid, tclass, AVTAB_TRANSITION, + out_sid, true); +} + +int security_transition_sid_user(u32 ssid, + u32 tsid, + u16 tclass, + u32 *out_sid) +{ + return security_compute_sid(ssid, tsid, tclass, AVTAB_TRANSITION, + out_sid, false); } /** @@ -1379,7 +1532,8 @@ int security_member_sid(u32 ssid, u16 tclass, u32 *out_sid) { - return security_compute_sid(ssid, tsid, tclass, AVTAB_MEMBER, out_sid); + return security_compute_sid(ssid, tsid, tclass, AVTAB_MEMBER, out_sid, + false); } /** @@ -1400,144 +1554,8 @@ int security_change_sid(u32 ssid, u16 tclass, u32 *out_sid) { - return security_compute_sid(ssid, tsid, tclass, AVTAB_CHANGE, out_sid); -} - -/* - * Verify that each kernel class that is defined in the - * policy is correct - */ -static int validate_classes(struct policydb *p) -{ - int i, j; - struct class_datum *cladatum; - struct perm_datum *perdatum; - u32 nprim, tmp, common_pts_len, perm_val, pol_val; - u16 class_val; - const struct selinux_class_perm *kdefs = &selinux_class_perm; - const char *def_class, *def_perm, *pol_class; - struct symtab *perms; - bool print_unknown_handle = 0; - - if (p->allow_unknown) { - u32 num_classes = kdefs->cts_len; - p->undefined_perms = kcalloc(num_classes, sizeof(u32), GFP_KERNEL); - if (!p->undefined_perms) - return -ENOMEM; - } - - for (i = 1; i < kdefs->cts_len; i++) { - def_class = kdefs->class_to_string[i]; - if (!def_class) - continue; - if (i > p->p_classes.nprim) { - printk(KERN_INFO - "SELinux: class %s not defined in policy\n", - def_class); - if (p->reject_unknown) - return -EINVAL; - if (p->allow_unknown) - p->undefined_perms[i-1] = ~0U; - print_unknown_handle = 1; - continue; - } - pol_class = p->p_class_val_to_name[i-1]; - if (strcmp(pol_class, def_class)) { - printk(KERN_ERR - "SELinux: class %d is incorrect, found %s but should be %s\n", - i, pol_class, def_class); - return -EINVAL; - } - } - for (i = 0; i < kdefs->av_pts_len; i++) { - class_val = kdefs->av_perm_to_string[i].tclass; - perm_val = kdefs->av_perm_to_string[i].value; - def_perm = kdefs->av_perm_to_string[i].name; - if (class_val > p->p_classes.nprim) - continue; - pol_class = p->p_class_val_to_name[class_val-1]; - cladatum = hashtab_search(p->p_classes.table, pol_class); - BUG_ON(!cladatum); - perms = &cladatum->permissions; - nprim = 1 << (perms->nprim - 1); - if (perm_val > nprim) { - printk(KERN_INFO - "SELinux: permission %s in class %s not defined in policy\n", - def_perm, pol_class); - if (p->reject_unknown) - return -EINVAL; - if (p->allow_unknown) - p->undefined_perms[class_val-1] |= perm_val; - print_unknown_handle = 1; - continue; - } - perdatum = hashtab_search(perms->table, def_perm); - if (perdatum == NULL) { - printk(KERN_ERR - "SELinux: permission %s in class %s not found in policy, bad policy\n", - def_perm, pol_class); - return -EINVAL; - } - pol_val = 1 << (perdatum->value - 1); - if (pol_val != perm_val) { - printk(KERN_ERR - "SELinux: permission %s in class %s has incorrect value\n", - def_perm, pol_class); - return -EINVAL; - } - } - for (i = 0; i < kdefs->av_inherit_len; i++) { - class_val = kdefs->av_inherit[i].tclass; - if (class_val > p->p_classes.nprim) - continue; - pol_class = p->p_class_val_to_name[class_val-1]; - cladatum = hashtab_search(p->p_classes.table, pol_class); - BUG_ON(!cladatum); - if (!cladatum->comdatum) { - printk(KERN_ERR - "SELinux: class %s should have an inherits clause but does not\n", - pol_class); - return -EINVAL; - } - tmp = kdefs->av_inherit[i].common_base; - common_pts_len = 0; - while (!(tmp & 0x01)) { - common_pts_len++; - tmp >>= 1; - } - perms = &cladatum->comdatum->permissions; - for (j = 0; j < common_pts_len; j++) { - def_perm = kdefs->av_inherit[i].common_pts[j]; - if (j >= perms->nprim) { - printk(KERN_INFO - "SELinux: permission %s in class %s not defined in policy\n", - def_perm, pol_class); - if (p->reject_unknown) - return -EINVAL; - if (p->allow_unknown) - p->undefined_perms[class_val-1] |= (1 << j); - print_unknown_handle = 1; - continue; - } - perdatum = hashtab_search(perms->table, def_perm); - if (perdatum == NULL) { - printk(KERN_ERR - "SELinux: permission %s in class %s not found in policy, bad policy\n", - def_perm, pol_class); - return -EINVAL; - } - if (perdatum->value != j + 1) { - printk(KERN_ERR - "SELinux: permission %s in class %s has incorrect value\n", - def_perm, pol_class); - return -EINVAL; - } - } - } - if (print_unknown_handle) - printk(KERN_INFO "SELinux: the above unknown classes and permissions will be %s\n", - (security_get_allow_unknown() ? "allowed" : "denied")); - return 0; + return security_compute_sid(ssid, tsid, tclass, AVTAB_CHANGE, out_sid, + false); } /* Clone the SID into the new SID table. */ @@ -1710,8 +1728,10 @@ int security_load_policy(void *data, size_t len) { struct policydb oldpolicydb, newpolicydb; struct sidtab oldsidtab, newsidtab; + struct selinux_mapping *oldmap, *map = NULL; struct convert_context_args args; u32 seqno; + u16 map_size; int rc = 0; struct policy_file file = { data, len }, *fp = &file; @@ -1721,22 +1741,19 @@ int security_load_policy(void *data, size_t len) avtab_cache_destroy(); return -EINVAL; } - if (policydb_load_isids(&policydb, &sidtab)) { + if (selinux_set_mapping(&policydb, secclass_map, + ¤t_mapping, + ¤t_mapping_size)) { policydb_destroy(&policydb); avtab_cache_destroy(); return -EINVAL; } - /* Verify that the kernel defined classes are correct. */ - if (validate_classes(&policydb)) { - printk(KERN_ERR - "SELinux: the definition of a class is incorrect\n"); - sidtab_destroy(&sidtab); + if (policydb_load_isids(&policydb, &sidtab)) { policydb_destroy(&policydb); avtab_cache_destroy(); return -EINVAL; } security_load_policycaps(); - policydb_loaded_version = policydb.policyvers; ss_initialized = 1; seqno = ++latest_granting; selinux_complete_init(); @@ -1759,13 +1776,9 @@ int security_load_policy(void *data, size_t len) return -ENOMEM; } - /* Verify that the kernel defined classes are correct. */ - if (validate_classes(&newpolicydb)) { - printk(KERN_ERR - "SELinux: the definition of a class is incorrect\n"); - rc = -EINVAL; + if (selinux_set_mapping(&newpolicydb, secclass_map, + &map, &map_size)) goto err; - } rc = security_preserve_bools(&newpolicydb); if (rc) { @@ -1799,13 +1812,16 @@ int security_load_policy(void *data, size_t len) memcpy(&policydb, &newpolicydb, sizeof policydb); sidtab_set(&sidtab, &newsidtab); security_load_policycaps(); + oldmap = current_mapping; + current_mapping = map; + current_mapping_size = map_size; seqno = ++latest_granting; - policydb_loaded_version = policydb.policyvers; write_unlock_irq(&policy_rwlock); /* Free the old policydb and SID table. */ policydb_destroy(&oldpolicydb); sidtab_destroy(&oldsidtab); + kfree(oldmap); avc_ss_reset(seqno); selnl_notify_policyload(seqno); @@ -1815,6 +1831,7 @@ int security_load_policy(void *data, size_t len) return 0; err: + kfree(map); sidtab_destroy(&newsidtab); policydb_destroy(&newpolicydb); return rc; @@ -2091,7 +2108,7 @@ out_unlock: } for (i = 0, j = 0; i < mynel; i++) { rc = avc_has_perm_noaudit(fromsid, mysids[i], - SECCLASS_PROCESS, + SECCLASS_PROCESS, /* kernel value */ PROCESS__TRANSITION, AVC_STRICT, NULL); if (!rc) @@ -2119,10 +2136,11 @@ out: */ int security_genfs_sid(const char *fstype, char *path, - u16 sclass, + u16 orig_sclass, u32 *sid) { int len; + u16 sclass; struct genfs *genfs; struct ocontext *c; int rc = 0, cmp = 0; @@ -2132,6 +2150,8 @@ int security_genfs_sid(const char *fstype, read_lock(&policy_rwlock); + sclass = unmap_class(orig_sclass); + for (genfs = policydb.genfs; genfs; genfs = genfs->next) { cmp = strcmp(fstype, genfs->fstype); if (cmp <= 0) diff --git a/security/tomoyo/common.c b/security/tomoyo/common.c index 3c8bd8ee0b95..e0d0354008b7 100644 --- a/security/tomoyo/common.c +++ b/security/tomoyo/common.c @@ -187,6 +187,8 @@ bool tomoyo_is_correct_path(const char *filename, const s8 start_type, const s8 pattern_type, const s8 end_type, const char *function) { + const char *const start = filename; + bool in_repetition = false; bool contains_pattern = false; unsigned char c; unsigned char d; @@ -212,9 +214,13 @@ bool tomoyo_is_correct_path(const char *filename, const s8 start_type, if (c == '/') goto out; } - while ((c = *filename++) != '\0') { + while (1) { + c = *filename++; + if (!c) + break; if (c == '\\') { - switch ((c = *filename++)) { + c = *filename++; + switch (c) { case '\\': /* "\\" */ continue; case '$': /* "\$" */ @@ -231,6 +237,22 @@ bool tomoyo_is_correct_path(const char *filename, const s8 start_type, break; /* Must not contain pattern */ contains_pattern = true; continue; + case '{': /* "/\{" */ + if (filename - 3 < start || + *(filename - 3) != '/') + break; + if (pattern_type == -1) + break; /* Must not contain pattern */ + contains_pattern = true; + in_repetition = true; + continue; + case '}': /* "\}/" */ + if (*filename != '/') + break; + if (!in_repetition) + break; + in_repetition = false; + continue; case '0': /* "\ooo" */ case '1': case '2': @@ -246,6 +268,8 @@ bool tomoyo_is_correct_path(const char *filename, const s8 start_type, continue; /* pattern is not \000 */ } goto out; + } else if (in_repetition && c == '/') { + goto out; } else if (tomoyo_is_invalid(c)) { goto out; } @@ -254,6 +278,8 @@ bool tomoyo_is_correct_path(const char *filename, const s8 start_type, if (!contains_pattern) goto out; } + if (in_repetition) + goto out; return true; out: printk(KERN_DEBUG "%s: Invalid pathname '%s'\n", function, @@ -360,33 +386,6 @@ struct tomoyo_domain_info *tomoyo_find_domain(const char *domainname) } /** - * tomoyo_path_depth - Evaluate the number of '/' in a string. - * - * @pathname: The string to evaluate. - * - * Returns path depth of the string. - * - * I score 2 for each of the '/' in the @pathname - * and score 1 if the @pathname ends with '/'. - */ -static int tomoyo_path_depth(const char *pathname) -{ - int i = 0; - - if (pathname) { - const char *ep = pathname + strlen(pathname); - if (pathname < ep--) { - if (*ep != '/') - i++; - while (pathname <= ep) - if (*ep-- == '/') - i += 2; - } - } - return i; -} - -/** * tomoyo_const_part_length - Evaluate the initial length without a pattern in a token. * * @filename: The string to evaluate. @@ -444,11 +443,10 @@ void tomoyo_fill_path_info(struct tomoyo_path_info *ptr) ptr->is_dir = len && (name[len - 1] == '/'); ptr->is_patterned = (ptr->const_len < len); ptr->hash = full_name_hash(name, len); - ptr->depth = tomoyo_path_depth(name); } /** - * tomoyo_file_matches_to_pattern2 - Pattern matching without '/' character + * tomoyo_file_matches_pattern2 - Pattern matching without '/' character * and "\-" pattern. * * @filename: The start of string to check. @@ -458,10 +456,10 @@ void tomoyo_fill_path_info(struct tomoyo_path_info *ptr) * * Returns true if @filename matches @pattern, false otherwise. */ -static bool tomoyo_file_matches_to_pattern2(const char *filename, - const char *filename_end, - const char *pattern, - const char *pattern_end) +static bool tomoyo_file_matches_pattern2(const char *filename, + const char *filename_end, + const char *pattern, + const char *pattern_end) { while (filename < filename_end && pattern < pattern_end) { char c; @@ -519,7 +517,7 @@ static bool tomoyo_file_matches_to_pattern2(const char *filename, case '*': case '@': for (i = 0; i <= filename_end - filename; i++) { - if (tomoyo_file_matches_to_pattern2( + if (tomoyo_file_matches_pattern2( filename + i, filename_end, pattern + 1, pattern_end)) return true; @@ -550,7 +548,7 @@ static bool tomoyo_file_matches_to_pattern2(const char *filename, j++; } for (i = 1; i <= j; i++) { - if (tomoyo_file_matches_to_pattern2( + if (tomoyo_file_matches_pattern2( filename + i, filename_end, pattern + 1, pattern_end)) return true; @@ -567,7 +565,7 @@ static bool tomoyo_file_matches_to_pattern2(const char *filename, } /** - * tomoyo_file_matches_to_pattern - Pattern matching without without '/' character. + * tomoyo_file_matches_pattern - Pattern matching without without '/' character. * * @filename: The start of string to check. * @filename_end: The end of string to check. @@ -576,7 +574,7 @@ static bool tomoyo_file_matches_to_pattern2(const char *filename, * * Returns true if @filename matches @pattern, false otherwise. */ -static bool tomoyo_file_matches_to_pattern(const char *filename, +static bool tomoyo_file_matches_pattern(const char *filename, const char *filename_end, const char *pattern, const char *pattern_end) @@ -589,10 +587,10 @@ static bool tomoyo_file_matches_to_pattern(const char *filename, /* Split at "\-" pattern. */ if (*pattern++ != '\\' || *pattern++ != '-') continue; - result = tomoyo_file_matches_to_pattern2(filename, - filename_end, - pattern_start, - pattern - 2); + result = tomoyo_file_matches_pattern2(filename, + filename_end, + pattern_start, + pattern - 2); if (first) result = !result; if (result) @@ -600,13 +598,79 @@ static bool tomoyo_file_matches_to_pattern(const char *filename, first = false; pattern_start = pattern; } - result = tomoyo_file_matches_to_pattern2(filename, filename_end, - pattern_start, pattern_end); + result = tomoyo_file_matches_pattern2(filename, filename_end, + pattern_start, pattern_end); return first ? result : !result; } /** + * tomoyo_path_matches_pattern2 - Do pathname pattern matching. + * + * @f: The start of string to check. + * @p: The start of pattern to compare. + * + * Returns true if @f matches @p, false otherwise. + */ +static bool tomoyo_path_matches_pattern2(const char *f, const char *p) +{ + const char *f_delimiter; + const char *p_delimiter; + + while (*f && *p) { + f_delimiter = strchr(f, '/'); + if (!f_delimiter) + f_delimiter = f + strlen(f); + p_delimiter = strchr(p, '/'); + if (!p_delimiter) + p_delimiter = p + strlen(p); + if (*p == '\\' && *(p + 1) == '{') + goto recursive; + if (!tomoyo_file_matches_pattern(f, f_delimiter, p, + p_delimiter)) + return false; + f = f_delimiter; + if (*f) + f++; + p = p_delimiter; + if (*p) + p++; + } + /* Ignore trailing "\*" and "\@" in @pattern. */ + while (*p == '\\' && + (*(p + 1) == '*' || *(p + 1) == '@')) + p += 2; + return !*f && !*p; + recursive: + /* + * The "\{" pattern is permitted only after '/' character. + * This guarantees that below "*(p - 1)" is safe. + * Also, the "\}" pattern is permitted only before '/' character + * so that "\{" + "\}" pair will not break the "\-" operator. + */ + if (*(p - 1) != '/' || p_delimiter <= p + 3 || *p_delimiter != '/' || + *(p_delimiter - 1) != '}' || *(p_delimiter - 2) != '\\') + return false; /* Bad pattern. */ + do { + /* Compare current component with pattern. */ + if (!tomoyo_file_matches_pattern(f, f_delimiter, p + 2, + p_delimiter - 2)) + break; + /* Proceed to next component. */ + f = f_delimiter; + if (!*f) + break; + f++; + /* Continue comparison. */ + if (tomoyo_path_matches_pattern2(f, p_delimiter + 1)) + return true; + f_delimiter = strchr(f, '/'); + } while (f_delimiter); + return false; /* Not matched. */ +} + +/** * tomoyo_path_matches_pattern - Check whether the given filename matches the given pattern. + * * @filename: The filename to check. * @pattern: The pattern to compare. * @@ -615,24 +679,24 @@ static bool tomoyo_file_matches_to_pattern(const char *filename, * The following patterns are available. * \\ \ itself. * \ooo Octal representation of a byte. - * \* More than or equals to 0 character other than '/'. - * \@ More than or equals to 0 character other than '/' or '.'. + * \* Zero or more repetitions of characters other than '/'. + * \@ Zero or more repetitions of characters other than '/' or '.'. * \? 1 byte character other than '/'. - * \$ More than or equals to 1 decimal digit. + * \$ One or more repetitions of decimal digits. * \+ 1 decimal digit. - * \X More than or equals to 1 hexadecimal digit. + * \X One or more repetitions of hexadecimal digits. * \x 1 hexadecimal digit. - * \A More than or equals to 1 alphabet character. + * \A One or more repetitions of alphabet characters. * \a 1 alphabet character. + * * \- Subtraction operator. + * + * /\{dir\}/ '/' + 'One or more repetitions of dir/' (e.g. /dir/ /dir/dir/ + * /dir/dir/dir/ ). */ bool tomoyo_path_matches_pattern(const struct tomoyo_path_info *filename, const struct tomoyo_path_info *pattern) { - /* - if (!filename || !pattern) - return false; - */ const char *f = filename->name; const char *p = pattern->name; const int len = pattern->const_len; @@ -640,37 +704,15 @@ bool tomoyo_path_matches_pattern(const struct tomoyo_path_info *filename, /* If @pattern doesn't contain pattern, I can use strcmp(). */ if (!pattern->is_patterned) return !tomoyo_pathcmp(filename, pattern); - /* Dont compare if the number of '/' differs. */ - if (filename->depth != pattern->depth) + /* Don't compare directory and non-directory. */ + if (filename->is_dir != pattern->is_dir) return false; /* Compare the initial length without patterns. */ if (strncmp(f, p, len)) return false; f += len; p += len; - /* Main loop. Compare each directory component. */ - while (*f && *p) { - const char *f_delimiter = strchr(f, '/'); - const char *p_delimiter = strchr(p, '/'); - if (!f_delimiter) - f_delimiter = f + strlen(f); - if (!p_delimiter) - p_delimiter = p + strlen(p); - if (!tomoyo_file_matches_to_pattern(f, f_delimiter, - p, p_delimiter)) - return false; - f = f_delimiter; - if (*f) - f++; - p = p_delimiter; - if (*p) - p++; - } - /* Ignore trailing "\*" and "\@" in @pattern. */ - while (*p == '\\' && - (*(p + 1) == '*' || *(p + 1) == '@')) - p += 2; - return !*f && !*p; + return tomoyo_path_matches_pattern2(f, p); } /** diff --git a/security/tomoyo/common.h b/security/tomoyo/common.h index 31df541911f7..92169d29b2db 100644 --- a/security/tomoyo/common.h +++ b/security/tomoyo/common.h @@ -56,9 +56,6 @@ struct tomoyo_page_buffer { * (5) "is_patterned" is a bool which is true if "name" contains wildcard * characters, false otherwise. This allows TOMOYO to use "hash" and * strcmp() for string comparison if "is_patterned" is false. - * (6) "depth" is calculated using the number of "/" characters in "name". - * This allows TOMOYO to avoid comparing two pathnames which never match - * (e.g. whether "/var/www/html/index.html" matches "/tmp/sh-thd-\$"). */ struct tomoyo_path_info { const char *name; @@ -66,7 +63,6 @@ struct tomoyo_path_info { u16 const_len; /* = tomoyo_const_part_length(name) */ bool is_dir; /* = tomoyo_strendswith(name, "/") */ bool is_patterned; /* = tomoyo_path_contains_pattern(name) */ - u16 depth; /* = tomoyo_path_depth(name) */ }; /* diff --git a/security/tomoyo/file.c b/security/tomoyo/file.c index 5ae3a571559f..8346938809b1 100644 --- a/security/tomoyo/file.c +++ b/security/tomoyo/file.c @@ -1096,27 +1096,6 @@ static int tomoyo_check_single_path_permission2(struct tomoyo_domain_info * } /** - * tomoyo_check_file_perm - Check permission for sysctl()'s "read" and "write". - * - * @domain: Pointer to "struct tomoyo_domain_info". - * @filename: Filename to check. - * @perm: Mode ("read" or "write" or "read/write"). - * Returns 0 on success, negative value otherwise. - */ -int tomoyo_check_file_perm(struct tomoyo_domain_info *domain, - const char *filename, const u8 perm) -{ - struct tomoyo_path_info name; - const u8 mode = tomoyo_check_flags(domain, TOMOYO_MAC_FOR_FILE); - - if (!mode) - return 0; - name.name = filename; - tomoyo_fill_path_info(&name); - return tomoyo_check_file_perm2(domain, &name, perm, "sysctl", mode); -} - -/** * tomoyo_check_exec_perm - Check permission for "execute". * * @domain: Pointer to "struct tomoyo_domain_info". diff --git a/security/tomoyo/realpath.c b/security/tomoyo/realpath.c index 5f2e33263371..18369d497eb8 100644 --- a/security/tomoyo/realpath.c +++ b/security/tomoyo/realpath.c @@ -13,6 +13,8 @@ #include <linux/mount.h> #include <linux/mnt_namespace.h> #include <linux/fs_struct.h> +#include <linux/hash.h> + #include "common.h" #include "realpath.h" @@ -108,6 +110,15 @@ int tomoyo_realpath_from_path2(struct path *path, char *newname, spin_unlock(&dcache_lock); path_put(&root); path_put(&ns_root); + /* Prepend "/proc" prefix if using internal proc vfs mount. */ + if (!IS_ERR(sp) && (path->mnt->mnt_parent == path->mnt) && + (strcmp(path->mnt->mnt_sb->s_type->name, "proc") == 0)) { + sp -= 5; + if (sp >= newname) + memcpy(sp, "/proc", 5); + else + sp = ERR_PTR(-ENOMEM); + } } if (IS_ERR(sp)) error = PTR_ERR(sp); @@ -263,7 +274,8 @@ static unsigned int tomoyo_quota_for_savename; * table. Frequency of appending strings is very low. So we don't need * large (e.g. 64k) hash size. 256 will be sufficient. */ -#define TOMOYO_MAX_HASH 256 +#define TOMOYO_HASH_BITS 8 +#define TOMOYO_MAX_HASH (1u<<TOMOYO_HASH_BITS) /* * tomoyo_name_entry is a structure which is used for linking @@ -315,6 +327,7 @@ const struct tomoyo_path_info *tomoyo_save_name(const char *name) struct tomoyo_free_memory_block_list *fmb; int len; char *cp; + struct list_head *head; if (!name) return NULL; @@ -325,9 +338,10 @@ const struct tomoyo_path_info *tomoyo_save_name(const char *name) return NULL; } hash = full_name_hash((const unsigned char *) name, len - 1); + head = &tomoyo_name_list[hash_long(hash, TOMOYO_HASH_BITS)]; + mutex_lock(&lock); - list_for_each_entry(ptr, &tomoyo_name_list[hash % TOMOYO_MAX_HASH], - list) { + list_for_each_entry(ptr, head, list) { if (hash == ptr->entry.hash && !strcmp(name, ptr->entry.name)) goto out; } @@ -365,7 +379,7 @@ const struct tomoyo_path_info *tomoyo_save_name(const char *name) tomoyo_fill_path_info(&ptr->entry); fmb->ptr += len; fmb->len -= len; - list_add_tail(&ptr->list, &tomoyo_name_list[hash % TOMOYO_MAX_HASH]); + list_add_tail(&ptr->list, head); if (fmb->len == 0) { list_del(&fmb->list); kfree(fmb); diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c index 9548a0984cc4..8a00ade85166 100644 --- a/security/tomoyo/tomoyo.c +++ b/security/tomoyo/tomoyo.c @@ -85,83 +85,6 @@ static int tomoyo_bprm_check_security(struct linux_binprm *bprm) return tomoyo_check_open_permission(domain, &bprm->file->f_path, 1); } -#ifdef CONFIG_SYSCTL - -static int tomoyo_prepend(char **buffer, int *buflen, const char *str) -{ - int namelen = strlen(str); - - if (*buflen < namelen) - return -ENOMEM; - *buflen -= namelen; - *buffer -= namelen; - memcpy(*buffer, str, namelen); - return 0; -} - -/** - * tomoyo_sysctl_path - return the realpath of a ctl_table. - * @table: pointer to "struct ctl_table". - * - * Returns realpath(3) of the @table on success. - * Returns NULL on failure. - * - * This function uses tomoyo_alloc(), so the caller must call tomoyo_free() - * if this function didn't return NULL. - */ -static char *tomoyo_sysctl_path(struct ctl_table *table) -{ - int buflen = TOMOYO_MAX_PATHNAME_LEN; - char *buf = tomoyo_alloc(buflen); - char *end = buf + buflen; - int error = -ENOMEM; - - if (!buf) - return NULL; - - *--end = '\0'; - buflen--; - while (table) { - char num[32]; - const char *sp = table->procname; - - if (!sp) { - memset(num, 0, sizeof(num)); - snprintf(num, sizeof(num) - 1, "=%d=", table->ctl_name); - sp = num; - } - if (tomoyo_prepend(&end, &buflen, sp) || - tomoyo_prepend(&end, &buflen, "/")) - goto out; - table = table->parent; - } - if (tomoyo_prepend(&end, &buflen, "/proc/sys")) - goto out; - error = tomoyo_encode(buf, end - buf, end); - out: - if (!error) - return buf; - tomoyo_free(buf); - return NULL; -} - -static int tomoyo_sysctl(struct ctl_table *table, int op) -{ - int error; - char *name; - - op &= MAY_READ | MAY_WRITE; - if (!op) - return 0; - name = tomoyo_sysctl_path(table); - if (!name) - return -ENOMEM; - error = tomoyo_check_file_perm(tomoyo_domain(), name, op); - tomoyo_free(name); - return error; -} -#endif - static int tomoyo_path_truncate(struct path *path, loff_t length, unsigned int time_attrs) { @@ -282,9 +205,6 @@ static struct security_operations tomoyo_security_ops = { .cred_transfer = tomoyo_cred_transfer, .bprm_set_creds = tomoyo_bprm_set_creds, .bprm_check_security = tomoyo_bprm_check_security, -#ifdef CONFIG_SYSCTL - .sysctl = tomoyo_sysctl, -#endif .file_fcntl = tomoyo_file_fcntl, .dentry_open = tomoyo_dentry_open, .path_truncate = tomoyo_path_truncate, diff --git a/security/tomoyo/tomoyo.h b/security/tomoyo/tomoyo.h index cd6ba0bf7069..ed758325b1ae 100644 --- a/security/tomoyo/tomoyo.h +++ b/security/tomoyo/tomoyo.h @@ -18,8 +18,6 @@ struct inode; struct linux_binprm; struct pt_regs; -int tomoyo_check_file_perm(struct tomoyo_domain_info *domain, - const char *filename, const u8 perm); int tomoyo_check_exec_perm(struct tomoyo_domain_info *domain, const struct tomoyo_path_info *filename); int tomoyo_check_open_permission(struct tomoyo_domain_info *domain, diff --git a/sound/pcmcia/pdaudiocf/pdaudiocf.c b/sound/pcmcia/pdaudiocf/pdaudiocf.c index 64b859925c0b..7717e01fc071 100644 --- a/sound/pcmcia/pdaudiocf/pdaudiocf.c +++ b/sound/pcmcia/pdaudiocf/pdaudiocf.c @@ -131,7 +131,7 @@ static int snd_pdacf_probe(struct pcmcia_device *link) return err; } - snd_card_set_dev(card, &handle_to_dev(link)); + snd_card_set_dev(card, &link->dev); pdacf->index = i; card_list[i] = card; @@ -142,12 +142,10 @@ static int snd_pdacf_probe(struct pcmcia_device *link) link->io.Attributes1 = IO_DATA_PATH_WIDTH_AUTO; link->io.NumPorts1 = 16; - link->irq.Attributes = IRQ_TYPE_EXCLUSIVE | IRQ_HANDLE_PRESENT | IRQ_FORCED_PULSE; + link->irq.Attributes = IRQ_TYPE_EXCLUSIVE | IRQ_FORCED_PULSE; // link->irq.Attributes = IRQ_TYPE_DYNAMIC_SHARING|IRQ_FIRST_SHARED; - link->irq.IRQInfo1 = 0 /* | IRQ_LEVEL_ID */; link->irq.Handler = pdacf_interrupt; - link->irq.Instance = pdacf; link->conf.Attributes = CONF_ENABLE_IRQ; link->conf.IntType = INT_MEMORY_AND_IO; link->conf.ConfigIndex = 1; diff --git a/sound/pcmcia/vx/vxpocket.c b/sound/pcmcia/vx/vxpocket.c index 1492744ad67f..7be3b3357045 100644 --- a/sound/pcmcia/vx/vxpocket.c +++ b/sound/pcmcia/vx/vxpocket.c @@ -161,11 +161,9 @@ static int snd_vxpocket_new(struct snd_card *card, int ibl, link->io.Attributes1 = IO_DATA_PATH_WIDTH_AUTO; link->io.NumPorts1 = 16; - link->irq.Attributes = IRQ_TYPE_EXCLUSIVE | IRQ_HANDLE_PRESENT; + link->irq.Attributes = IRQ_TYPE_EXCLUSIVE; - link->irq.IRQInfo1 = IRQ_LEVEL_ID; link->irq.Handler = &snd_vx_irq_handler; - link->irq.Instance = chip; link->conf.Attributes = CONF_ENABLE_IRQ; link->conf.IntType = INT_MEMORY_AND_IO; @@ -244,7 +242,7 @@ static int vxpocket_config(struct pcmcia_device *link) if (ret) goto failed; - chip->dev = &handle_to_dev(link); + chip->dev = &link->dev; snd_card_set_dev(chip->card, chip->dev); if (snd_vxpocket_assign_resources(chip, link->io.BasePort1, link->irq.AssignedIRQ) < 0) diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore index 0854f110bf7f..fe08660ce0bd 100644 --- a/tools/perf/.gitignore +++ b/tools/perf/.gitignore @@ -12,6 +12,7 @@ perf*.1 perf*.xml perf*.html common-cmds.h +perf.data tags TAGS cscope* diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt new file mode 100644 index 000000000000..ae525ac5a2ce --- /dev/null +++ b/tools/perf/Documentation/perf-bench.txt @@ -0,0 +1,120 @@ +perf-bench(1) +============ + +NAME +---- +perf-bench - General framework for benchmark suites + +SYNOPSIS +-------- +[verse] +'perf bench' [<common options>] <subsystem> <suite> [<options>] + +DESCRIPTION +----------- +This 'perf bench' command is general framework for benchmark suites. + +COMMON OPTIONS +-------------- +-f:: +--format=:: +Specify format style. +Current available format styles are, + +'default':: +Default style. This is mainly for human reading. +--------------------- +% perf bench sched pipe # with no style specify +(executing 1000000 pipe operations between two tasks) + Total time:5.855 sec + 5.855061 usecs/op + 170792 ops/sec +--------------------- + +'simple':: +This simple style is friendly for automated +processing by scripts. +--------------------- +% perf bench --format=simple sched pipe # specified simple +5.988 +--------------------- + +SUBSYSTEM +--------- + +'sched':: + Scheduler and IPC mechanisms. + +SUITES FOR 'sched' +~~~~~~~~~~~~~~~~~~ +*messaging*:: +Suite for evaluating performance of scheduler and IPC mechanisms. +Based on hackbench by Rusty Russell. + +Options of *pipe* +^^^^^^^^^^^^^^^^^ +-p:: +--pipe:: +Use pipe() instead of socketpair() + +-t:: +--thread:: +Be multi thread instead of multi process + +-g:: +--group=:: +Specify number of groups + +-l:: +--loop=:: +Specify number of loops + +Example of *messaging* +^^^^^^^^^^^^^^^^^^^^^^ + +--------------------- +% perf bench sched messaging # run with default +options (20 sender and receiver processes per group) +(10 groups == 400 processes run) + + Total time:0.308 sec + +% perf bench sched messaging -t -g 20 # be multi-thread,with 20 groups +(20 sender and receiver threads per group) +(20 groups == 800 threads run) + + Total time:0.582 sec +--------------------- + +*pipe*:: +Suite for pipe() system call. +Based on pipe-test-1m.c by Ingo Molnar. + +Options of *pipe* +^^^^^^^^^^^^^^^^^ +-l:: +--loop=:: +Specify number of loops. + +Example of *pipe* +^^^^^^^^^^^^^^^^^ + +--------------------- +% perf bench sched pipe +(executing 1000000 pipe operations between two tasks) + + Total time:8.091 sec + 8.091833 usecs/op + 123581 ops/sec + +% perf bench sched pipe -l 1000 # loop 1000 +(executing 1000 pipe operations between two tasks) + + Total time:0.016 sec + 16.948000 usecs/op + 59004 ops/sec +--------------------- + +SEE ALSO +-------- +linkperf:perf[1] diff --git a/tools/perf/Documentation/perf-buildid-list.txt b/tools/perf/Documentation/perf-buildid-list.txt new file mode 100644 index 000000000000..01b642c0bf8f --- /dev/null +++ b/tools/perf/Documentation/perf-buildid-list.txt @@ -0,0 +1,34 @@ +perf-buildid-list(1) +==================== + +NAME +---- +perf-buildid-list - List the buildids in a perf.data file + +SYNOPSIS +-------- +[verse] +'perf buildid-list <options>' + +DESCRIPTION +----------- +This command displays the buildids found in a perf.data file, so that other +tools can be used to fetch packages with matching symbol tables for use by +perf report. + +OPTIONS +------- +-i:: +--input=:: + Input file name. (default: perf.data) +-f:: +--force:: + Don't do ownership validation. +-v:: +--verbose:: + Be more verbose. + +SEE ALSO +-------- +linkperf:perf-record[1], linkperf:perf-top[1], +linkperf:perf-report[1] diff --git a/tools/perf/Documentation/perf-kmem.txt b/tools/perf/Documentation/perf-kmem.txt new file mode 100644 index 000000000000..44b0ce35c28a --- /dev/null +++ b/tools/perf/Documentation/perf-kmem.txt @@ -0,0 +1,44 @@ +perf-kmem(1) +============== + +NAME +---- +perf-kmem - Tool to trace/measure kernel memory(slab) properties + +SYNOPSIS +-------- +[verse] +'perf kmem' {record} [<options>] + +DESCRIPTION +----------- +There's two variants of perf kmem: + + 'perf kmem record <command>' to record the kmem events + of an arbitrary workload. + + 'perf kmem' to report kernel memory statistics. + +OPTIONS +------- +-i <file>:: +--input=<file>:: + Select the input file (default: perf.data) + +--stat=<caller|alloc>:: + Select per callsite or per allocation statistics + +-s <key[,key2...]>:: +--sort=<key[,key2...]>:: + Sort the output (default: frag,hit,bytes) + +-l <num>:: +--line=<num>:: + Print n lines only + +--raw-ip:: + Print raw ip instead of symbol + +SEE ALSO +-------- +linkperf:perf-record[1] diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt new file mode 100644 index 000000000000..9270594e6dfd --- /dev/null +++ b/tools/perf/Documentation/perf-probe.txt @@ -0,0 +1,49 @@ +perf-probe(1) +============= + +NAME +---- +perf-probe - Define new dynamic tracepoints + +SYNOPSIS +-------- +[verse] +'perf probe' [options] --add 'PROBE' [--add 'PROBE' ...] +or +'perf probe' [options] 'PROBE' ['PROBE' ...] + + +DESCRIPTION +----------- +This command defines dynamic tracepoint events, by symbol and registers +without debuginfo, or by C expressions (C line numbers, C function names, +and C local variables) with debuginfo. + + +OPTIONS +------- +-k:: +--vmlinux=PATH:: + Specify vmlinux path which has debuginfo (Dwarf binary). + +-v:: +--verbose:: + Be more verbose (show parsed arguments, etc). + +-a:: +--add:: + Define a probe point (see PROBE SYNTAX for detail) + +PROBE SYNTAX +------------ +Probe points are defined by following syntax. + + "FUNC[+OFFS|:RLN|%return][@SRC]|SRC:ALN [ARG ...]" + +'FUNC' specifies a probed function name, and it may have one of the following options; '+OFFS' is the offset from function entry address in bytes, 'RLN' is the relative-line number from function entry line, and '%return' means that it probes function return. In addition, 'SRC' specifies a source file which has that function. +It is also possible to specify a probe point by the source line number by using 'SRC:ALN' syntax, where 'SRC' is the source file path and 'ALN' is the line number. +'ARG' specifies the arguments of this probe point. You can use the name of local variable, or kprobe-tracer argument format (e.g. $retval, %ax, etc). + +SEE ALSO +-------- +linkperf:perf-trace[1], linkperf:perf-record[1] diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 0ff23de9e453..fc46c0b40f6e 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -26,11 +26,19 @@ OPTIONS -e:: --event=:: - Select the PMU event. Selection can be a symbolic event name - (use 'perf list' to list all events) or a raw PMU - event (eventsel+umask) in the form of rNNN where NNN is a - hexadecimal event descriptor. + Select the PMU event. Selection can be: + - a symbolic event name (use 'perf list' to list all events) + + - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a + hexadecimal event descriptor. + + - a hardware breakpoint event in the form of '\mem:addr[:access]' + where addr is the address in memory you want to break in. + Access is the memory access type (read, write, execute) it can + be passed as follows: '\mem:addr[:[r][w][x]]'. + If you want to profile read-write accesses in 0x1000, just set + 'mem:0x1000:rw'. -a:: System-wide collection. diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 59f0b846cd71..9dccb180b7af 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -24,11 +24,11 @@ OPTIONS --dsos=:: Only consider symbols in these dsos. CSV that understands file://filename entries. --n ---show-nr-samples +-n:: +--show-nr-samples:: Show the number of samples for each symbol --T ---threads +-T:: +--threads:: Show per-thread event counters -C:: --comms=:: diff --git a/tools/perf/Documentation/perf-timechart.txt b/tools/perf/Documentation/perf-timechart.txt index a7910099d6fd..4b1788355eca 100644 --- a/tools/perf/Documentation/perf-timechart.txt +++ b/tools/perf/Documentation/perf-timechart.txt @@ -31,9 +31,12 @@ OPTIONS -w:: --width=:: Select the width of the SVG file (default: 1000) --p:: +-P:: --power-only:: Only output the CPU power section of the diagram +-p:: +--process:: + Select the processes to display, by name or PID SEE ALSO diff --git a/tools/perf/Documentation/perf-trace-perl.txt b/tools/perf/Documentation/perf-trace-perl.txt new file mode 100644 index 000000000000..c5f55f439091 --- /dev/null +++ b/tools/perf/Documentation/perf-trace-perl.txt @@ -0,0 +1,219 @@ +perf-trace-perl(1) +================== + +NAME +---- +perf-trace-perl - Process trace data with a Perl script + +SYNOPSIS +-------- +[verse] +'perf trace' [-s [lang]:script[.ext] ] + +DESCRIPTION +----------- + +This perf trace option is used to process perf trace data using perf's +built-in Perl interpreter. It reads and processes the input file and +displays the results of the trace analysis implemented in the given +Perl script, if any. + +STARTER SCRIPTS +--------------- + +You can avoid reading the rest of this document by running 'perf trace +-g perl' in the same directory as an existing perf.data trace file. +That will generate a starter script containing a handler for each of +the event types in the trace file; it simply prints every available +field for each event in the trace file. + +You can also look at the existing scripts in +~/libexec/perf-core/scripts/perl for typical examples showing how to +do basic things like aggregate event data, print results, etc. Also, +the check-perf-trace.pl script, while not interesting for its results, +attempts to exercise all of the main scripting features. + +EVENT HANDLERS +-------------- + +When perf trace is invoked using a trace script, a user-defined +'handler function' is called for each event in the trace. If there's +no handler function defined for a given event type, the event is +ignored (or passed to a 'trace_handled' function, see below) and the +next event is processed. + +Most of the event's field values are passed as arguments to the +handler function; some of the less common ones aren't - those are +available as calls back into the perf executable (see below). + +As an example, the following perf record command can be used to record +all sched_wakeup events in the system: + + # perf record -c 1 -f -a -M -R -e sched:sched_wakeup + +Traces meant to be processed using a script should be recorded with +the above options: -c 1 says to sample every event, -a to enable +system-wide collection, -M to multiplex the output, and -R to collect +raw samples. + +The format file for the sched_wakep event defines the following fields +(see /sys/kernel/debug/tracing/events/sched/sched_wakeup/format): + +---- + format: + field:unsigned short common_type; + field:unsigned char common_flags; + field:unsigned char common_preempt_count; + field:int common_pid; + field:int common_lock_depth; + + field:char comm[TASK_COMM_LEN]; + field:pid_t pid; + field:int prio; + field:int success; + field:int target_cpu; +---- + +The handler function for this event would be defined as: + +---- +sub sched::sched_wakeup +{ + my ($event_name, $context, $common_cpu, $common_secs, + $common_nsecs, $common_pid, $common_comm, + $comm, $pid, $prio, $success, $target_cpu) = @_; +} +---- + +The handler function takes the form subsystem::event_name. + +The $common_* arguments in the handler's argument list are the set of +arguments passed to all event handlers; some of the fields correspond +to the common_* fields in the format file, but some are synthesized, +and some of the common_* fields aren't common enough to to be passed +to every event as arguments but are available as library functions. + +Here's a brief description of each of the invariant event args: + + $event_name the name of the event as text + $context an opaque 'cookie' used in calls back into perf + $common_cpu the cpu the event occurred on + $common_secs the secs portion of the event timestamp + $common_nsecs the nsecs portion of the event timestamp + $common_pid the pid of the current task + $common_comm the name of the current process + +All of the remaining fields in the event's format file have +counterparts as handler function arguments of the same name, as can be +seen in the example above. + +The above provides the basics needed to directly access every field of +every event in a trace, which covers 90% of what you need to know to +write a useful trace script. The sections below cover the rest. + +SCRIPT LAYOUT +------------- + +Every perf trace Perl script should start by setting up a Perl module +search path and 'use'ing a few support modules (see module +descriptions below): + +---- + use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/Perf-Trace-Util/lib"; + use lib "./Perf-Trace-Util/lib"; + use Perf::Trace::Core; + use Perf::Trace::Context; + use Perf::Trace::Util; +---- + +The rest of the script can contain handler functions and support +functions in any order. + +Aside from the event handler functions discussed above, every script +can implement a set of optional functions: + +*trace_begin*, if defined, is called before any event is processed and +gives scripts a chance to do setup tasks: + +---- + sub trace_begin + { + } +---- + +*trace_end*, if defined, is called after all events have been + processed and gives scripts a chance to do end-of-script tasks, such + as display results: + +---- +sub trace_end +{ +} +---- + +*trace_unhandled*, if defined, is called after for any event that + doesn't have a handler explicitly defined for it. The standard set + of common arguments are passed into it: + +---- +sub trace_unhandled +{ + my ($event_name, $context, $common_cpu, $common_secs, + $common_nsecs, $common_pid, $common_comm) = @_; +} +---- + +The remaining sections provide descriptions of each of the available +built-in perf trace Perl modules and their associated functions. + +AVAILABLE MODULES AND FUNCTIONS +------------------------------- + +The following sections describe the functions and variables available +via the various Perf::Trace::* Perl modules. To use the functions and +variables from the given module, add the corresponding 'use +Perf::Trace::XXX' line to your perf trace script. + +Perf::Trace::Core Module +~~~~~~~~~~~~~~~~~~~~~~~~ + +These functions provide some essential functions to user scripts. + +The *flag_str* and *symbol_str* functions provide human-readable +strings for flag and symbolic fields. These correspond to the strings +and values parsed from the 'print fmt' fields of the event format +files: + + flag_str($event_name, $field_name, $field_value) - returns the string represention corresponding to $field_value for the flag field $field_name of event $event_name + symbol_str($event_name, $field_name, $field_value) - returns the string represention corresponding to $field_value for the symbolic field $field_name of event $event_name + +Perf::Trace::Context Module +~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Some of the 'common' fields in the event format file aren't all that +common, but need to be made accessible to user scripts nonetheless. + +Perf::Trace::Context defines a set of functions that can be used to +access this data in the context of the current event. Each of these +functions expects a $context variable, which is the same as the +$context variable passed into every event handler as the second +argument. + + common_pc($context) - returns common_preempt count for the current event + common_flags($context) - returns common_flags for the current event + common_lock_depth($context) - returns common_lock_depth for the current event + +Perf::Trace::Util Module +~~~~~~~~~~~~~~~~~~~~~~~~ + +Various utility functions for use with perf trace: + + nsecs($secs, $nsecs) - returns total nsecs given secs/nsecs pair + nsecs_secs($nsecs) - returns whole secs portion given nsecs + nsecs_nsecs($nsecs) - returns nsecs remainder given nsecs + nsecs_str($nsecs) - returns printable string in the form secs.nsecs + avg($total, $n) - returns average given a sum and a total number of values + +SEE ALSO +-------- +linkperf:perf-trace[1] diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt index 41ed75398ca9..07065efa60e0 100644 --- a/tools/perf/Documentation/perf-trace.txt +++ b/tools/perf/Documentation/perf-trace.txt @@ -20,6 +20,15 @@ OPTIONS --dump-raw-trace=:: Display verbose dump of the trace data. +-s:: +--script=:: + Process trace data with the given script ([lang]:script[.ext]). + +-g:: +--gen-script=:: + Generate perf-trace.[ext] starter script for given language, + using current perf.data. + SEE ALSO -------- -linkperf:perf-record[1] +linkperf:perf-record[1], linkperf:perf-trace-perl[1] diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 7e190d522cd5..23ec66098bdc 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -2,6 +2,7 @@ all:: # Define V=1 to have a more verbose compile. +# Define V=2 to have an even more verbose compile. # # Define SNPRINTF_RETURNS_BOGUS if your are on a system which snprintf() # or vsnprintf() return -1 instead of number of characters which would @@ -145,6 +146,10 @@ all:: # Define NO_EXTERNAL_GREP if you don't want "perf grep" to ever call # your external grep (e.g., if your system lacks grep, if its grep is # broken, or spawning external process is slower than built-in grep perf has). +# +# Define LDFLAGS=-static to build a static binary. +# +# Define EXTRA_CFLAGS=-m64 or EXTRA_CFLAGS=-m32 as appropriate for cross-builds. PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE @$(SHELL_PATH) util/PERF-VERSION-GEN @@ -157,20 +162,6 @@ uname_R := $(shell sh -c 'uname -r 2>/dev/null || echo not') uname_P := $(shell sh -c 'uname -p 2>/dev/null || echo not') uname_V := $(shell sh -c 'uname -v 2>/dev/null || echo not') -# -# Add -m32 for cross-builds: -# -ifdef NO_64BIT - MBITS := -m32 -else - # - # If we're on a 64-bit kernel, use -m64: - # - ifneq ($(patsubst %64,%,$(uname_M)),$(uname_M)) - MBITS := -m64 - endif -endif - # CFLAGS and LDFLAGS are for the users to override from the command line. # @@ -200,8 +191,15 @@ EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wold-style-definition EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wstrict-prototypes EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wdeclaration-after-statement -CFLAGS = $(MBITS) -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -fstack-protector-all -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) -LDFLAGS = -lpthread -lrt -lelf -lm +ifeq ("$(origin DEBUG)", "command line") + PERF_DEBUG = $(DEBUG) +endif +ifndef PERF_DEBUG + CFLAGS_OPTIMIZE = -O6 +endif + +CFLAGS = -ggdb3 -Wall -Wextra -std=gnu99 -Werror $(CFLAGS_OPTIMIZE) -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) +EXTLIBS = -lpthread -lrt -lelf -lm ALL_CFLAGS = $(CFLAGS) ALL_LDFLAGS = $(LDFLAGS) STRIP ?= strip @@ -252,6 +250,9 @@ PTHREAD_LIBS = -lpthread # explicitly what architecture to check for. Fix this up for yours.. SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__ +ifeq ($(shell sh -c "echo 'int foo(void) {char X[2]; return 3;}' | $(CC) -x c -c -Werror -fstack-protector-all - -o /dev/null "$(QUIET_STDERR)" && echo y"), y) + CFLAGS := $(CFLAGS) -fstack-protector-all +endif ### --- END CONFIGURATION SECTION --- @@ -327,8 +328,28 @@ LIB_FILE=libperf.a LIB_H += ../../include/linux/perf_event.h LIB_H += ../../include/linux/rbtree.h LIB_H += ../../include/linux/list.h +LIB_H += ../../include/linux/stringify.h +LIB_H += util/include/linux/bitmap.h +LIB_H += util/include/linux/bitops.h +LIB_H += util/include/linux/compiler.h +LIB_H += util/include/linux/ctype.h +LIB_H += util/include/linux/kernel.h LIB_H += util/include/linux/list.h +LIB_H += util/include/linux/module.h +LIB_H += util/include/linux/poison.h +LIB_H += util/include/linux/prefetch.h +LIB_H += util/include/linux/rbtree.h +LIB_H += util/include/linux/string.h +LIB_H += util/include/linux/types.h +LIB_H += util/include/asm/asm-offsets.h +LIB_H += util/include/asm/bitops.h +LIB_H += util/include/asm/byteorder.h +LIB_H += util/include/asm/swab.h +LIB_H += util/include/asm/system.h +LIB_H += util/include/asm/uaccess.h LIB_H += perf.h +LIB_H += util/debugfs.h +LIB_H += util/event.h LIB_H += util/types.h LIB_H += util/levenshtein.h LIB_H += util/parse-options.h @@ -342,15 +363,22 @@ LIB_H += util/strlist.h LIB_H += util/run-command.h LIB_H += util/sigchain.h LIB_H += util/symbol.h -LIB_H += util/module.h LIB_H += util/color.h LIB_H += util/values.h +LIB_H += util/sort.h +LIB_H += util/hist.h +LIB_H += util/thread.h +LIB_H += util/data_map.h +LIB_H += util/probe-finder.h +LIB_H += util/probe-event.h LIB_OBJS += util/abspath.o LIB_OBJS += util/alias.o LIB_OBJS += util/config.o LIB_OBJS += util/ctype.o +LIB_OBJS += util/debugfs.o LIB_OBJS += util/environment.o +LIB_OBJS += util/event.o LIB_OBJS += util/exec_cmd.o LIB_OBJS += util/help.o LIB_OBJS += util/levenshtein.o @@ -358,6 +386,9 @@ LIB_OBJS += util/parse-options.o LIB_OBJS += util/parse-events.o LIB_OBJS += util/path.o LIB_OBJS += util/rbtree.o +LIB_OBJS += util/bitmap.o +LIB_OBJS += util/hweight.o +LIB_OBJS += util/find_next_bit.o LIB_OBJS += util/run-command.o LIB_OBJS += util/quote.o LIB_OBJS += util/strbuf.o @@ -367,7 +398,6 @@ LIB_OBJS += util/usage.o LIB_OBJS += util/wrapper.o LIB_OBJS += util/sigchain.o LIB_OBJS += util/symbol.o -LIB_OBJS += util/module.o LIB_OBJS += util/color.o LIB_OBJS += util/pager.o LIB_OBJS += util/header.o @@ -379,11 +409,25 @@ LIB_OBJS += util/thread.o LIB_OBJS += util/trace-event-parse.o LIB_OBJS += util/trace-event-read.o LIB_OBJS += util/trace-event-info.o +LIB_OBJS += util/trace-event-perl.o LIB_OBJS += util/svghelper.o +LIB_OBJS += util/sort.o +LIB_OBJS += util/hist.o +LIB_OBJS += util/data_map.o +LIB_OBJS += util/probe-event.o BUILTIN_OBJS += builtin-annotate.o + +BUILTIN_OBJS += builtin-bench.o + +# Benchmark modules +BUILTIN_OBJS += bench/sched-messaging.o +BUILTIN_OBJS += bench/sched-pipe.o +BUILTIN_OBJS += bench/mem-memcpy.o + BUILTIN_OBJS += builtin-help.o BUILTIN_OBJS += builtin-sched.o +BUILTIN_OBJS += builtin-buildid-list.o BUILTIN_OBJS += builtin-list.o BUILTIN_OBJS += builtin-record.o BUILTIN_OBJS += builtin-report.o @@ -391,9 +435,16 @@ BUILTIN_OBJS += builtin-stat.o BUILTIN_OBJS += builtin-timechart.o BUILTIN_OBJS += builtin-top.o BUILTIN_OBJS += builtin-trace.o +BUILTIN_OBJS += builtin-probe.o +BUILTIN_OBJS += builtin-kmem.o PERFLIBS = $(LIB_FILE) +ifeq ($(V), 2) + QUIET_STDERR = ">/dev/null" +else + QUIET_STDERR = ">/dev/null 2>&1" +endif # # Platform specific tweaks # @@ -421,36 +472,58 @@ ifeq ($(uname_S),Darwin) PTHREAD_LIBS = endif -ifeq ($(shell sh -c "(echo '\#include <libelf.h>'; echo 'int main(void) { Elf * elf = elf_begin(0, ELF_C_READ, 0); return (long)elf; }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -o /dev/null $(ALL_LDFLAGS) > /dev/null 2>&1 && echo y"), y) - ifneq ($(shell sh -c "(echo '\#include <libelf.h>'; echo 'int main(void) { Elf * elf = elf_begin(0, ELF_C_READ_MMAP, 0); return (long)elf; }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -o /dev/null $(ALL_LDFLAGS) > /dev/null 2>&1 && echo y"), y) +ifeq ($(shell sh -c "(echo '\#include <libelf.h>'; echo 'int main(void) { Elf * elf = elf_begin(0, ELF_C_READ, 0); return (long)elf; }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -o /dev/null $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y) +ifneq ($(shell sh -c "(echo '\#include <gnu/libc-version.h>'; echo 'int main(void) { const char * version = gnu_get_libc_version(); return (long)version; }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -o /dev/null $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y) + msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static); +endif + + ifneq ($(shell sh -c "(echo '\#include <libelf.h>'; echo 'int main(void) { Elf * elf = elf_begin(0, ELF_C_READ_MMAP, 0); return (long)elf; }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -o /dev/null $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y) BASIC_CFLAGS += -DLIBELF_NO_MMAP endif else msg := $(error No libelf.h/libelf found, please install libelf-dev/elfutils-libelf-devel and glibc-dev[el]); endif +ifneq ($(shell sh -c "(echo '\#include <libdwarf/dwarf.h>'; echo '\#include <libdwarf/libdwarf.h>'; echo 'int main(void) { Dwarf_Debug dbg; Dwarf_Error err; Dwarf_Ranges *rng; dwarf_init(0, DW_DLC_READ, 0, 0, &dbg, &err); dwarf_get_ranges(dbg, 0, &rng, 0, 0, &err); return (long)dbg; }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -ldwarf -lelf -o /dev/null $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y) + msg := $(warning No libdwarf.h found or old libdwarf.h found, disables dwarf support. Please install libdwarf-dev/libdwarf-devel >= 20081231); + BASIC_CFLAGS += -DNO_LIBDWARF +else + EXTLIBS += -lelf -ldwarf + LIB_OBJS += util/probe-finder.o +endif + +PERL_EMBED_LDOPTS = `perl -MExtUtils::Embed -e ldopts 2>/dev/null` +PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null` + +ifneq ($(shell sh -c "(echo '\#include <EXTERN.h>'; echo '\#include <perl.h>'; echo 'int main(void) { perl_alloc(); return 0; }') | $(CC) -x c - $(PERL_EMBED_CCOPTS) -o /dev/null $(PERL_EMBED_LDOPTS) > /dev/null 2>&1 && echo y"), y) + BASIC_CFLAGS += -DNO_LIBPERL +else + ALL_LDFLAGS += $(PERL_EMBED_LDOPTS) + LIB_OBJS += scripts/perl/Perf-Trace-Util/Context.o +endif + ifdef NO_DEMANGLE BASIC_CFLAGS += -DNO_DEMANGLE else - has_bfd := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o /dev/null $(ALL_LDFLAGS) -lbfd > /dev/null 2>&1 && echo y") + has_bfd := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o /dev/null $(ALL_LDFLAGS) $(EXTLIBS) -lbfd "$(QUIET_STDERR)" && echo y") ifeq ($(has_bfd),y) EXTLIBS += -lbfd else - has_bfd_iberty := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o /dev/null $(ALL_LDFLAGS) -lbfd -liberty > /dev/null 2>&1 && echo y") + has_bfd_iberty := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o /dev/null $(ALL_LDFLAGS) $(EXTLIBS) -lbfd -liberty "$(QUIET_STDERR)" && echo y") ifeq ($(has_bfd_iberty),y) EXTLIBS += -lbfd -liberty else - has_bfd_iberty_z := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o /dev/null $(ALL_LDFLAGS) -lbfd -liberty -lz > /dev/null 2>&1 && echo y") + has_bfd_iberty_z := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o /dev/null $(ALL_LDFLAGS) $(EXTLIBS) -lbfd -liberty -lz "$(QUIET_STDERR)" && echo y") ifeq ($(has_bfd_iberty_z),y) EXTLIBS += -lbfd -liberty -lz else - has_cplus_demangle := $(shell sh -c "(echo 'extern char *cplus_demangle(const char *, int);'; echo 'int main(void) { cplus_demangle(0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o /dev/null $(ALL_LDFLAGS) -liberty > /dev/null 2>&1 && echo y") + has_cplus_demangle := $(shell sh -c "(echo 'extern char *cplus_demangle(const char *, int);'; echo 'int main(void) { cplus_demangle(0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o /dev/null $(ALL_LDFLAGS) $(EXTLIBS) -liberty "$(QUIET_STDERR)" && echo y") ifeq ($(has_cplus_demangle),y) EXTLIBS += -liberty BASIC_CFLAGS += -DHAVE_CPLUS_DEMANGLE else - msg := $(warning No bfd.h/libbfd found, install binutils-dev[el] to gain symbol demangling) + msg := $(warning No bfd.h/libbfd found, install binutils-dev[el]/zlib-static to gain symbol demangling) BASIC_CFLAGS += -DNO_DEMANGLE endif endif @@ -787,6 +860,25 @@ util/config.o: util/config.c PERF-CFLAGS util/rbtree.o: ../../lib/rbtree.c PERF-CFLAGS $(QUIET_CC)$(CC) -o util/rbtree.o -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< +# some perf warning policies can't fit to lib/bitmap.c, eg: it warns about variable shadowing +# from <string.h> that comes from kernel headers wrapping. +KBITMAP_FLAGS=`echo $(ALL_CFLAGS) | sed s/-Wshadow// | sed s/-Wswitch-default// | sed s/-Wextra//` + +util/bitmap.o: ../../lib/bitmap.c PERF-CFLAGS + $(QUIET_CC)$(CC) -o util/bitmap.o -c $(KBITMAP_FLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< + +util/hweight.o: ../../lib/hweight.c PERF-CFLAGS + $(QUIET_CC)$(CC) -o util/hweight.o -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< + +util/find_next_bit.o: ../../lib/find_next_bit.c PERF-CFLAGS + $(QUIET_CC)$(CC) -o util/find_next_bit.o -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< + +util/trace-event-perl.o: util/trace-event-perl.c PERF-CFLAGS + $(QUIET_CC)$(CC) -o util/trace-event-perl.o -c $(ALL_CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $< + +scripts/perl/Perf-Trace-Util/Context.o: scripts/perl/Perf-Trace-Util/Context.c PERF-CFLAGS + $(QUIET_CC)$(CC) -o scripts/perl/Perf-Trace-Util/Context.o -c $(ALL_CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $< + perf-%$X: %.o $(PERFLIBS) $(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS) @@ -894,6 +986,13 @@ export perfexec_instdir install: all $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)' $(INSTALL) perf$X '$(DESTDIR_SQ)$(bindir_SQ)' + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace' + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin' + $(INSTALL) scripts/perl/Perf-Trace-Util/lib/Perf/Trace/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace' + $(INSTALL) scripts/perl/*.pl -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl' + $(INSTALL) scripts/perl/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin' + $(INSTALL) scripts/perl/Perf-Trace-Util/Makefile.PL -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util' + $(INSTALL) scripts/perl/Perf-Trace-Util/README -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util' ifdef BUILT_INS $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' $(INSTALL) $(BUILT_INS) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' @@ -979,7 +1078,7 @@ distclean: clean # $(RM) configure clean: - $(RM) *.o */*.o $(LIB_FILE) + $(RM) *.o */*.o */*/*.o */*/*/*.o $(LIB_FILE) $(RM) $(ALL_PROGRAMS) $(BUILT_INS) perf$X $(RM) $(TEST_PROGRAMS) $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo common-cmds.h TAGS tags cscope* diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h new file mode 100644 index 000000000000..f7781c6267c0 --- /dev/null +++ b/tools/perf/bench/bench.h @@ -0,0 +1,17 @@ +#ifndef BENCH_H +#define BENCH_H + +extern int bench_sched_messaging(int argc, const char **argv, const char *prefix); +extern int bench_sched_pipe(int argc, const char **argv, const char *prefix); +extern int bench_mem_memcpy(int argc, const char **argv, const char *prefix __used); + +#define BENCH_FORMAT_DEFAULT_STR "default" +#define BENCH_FORMAT_DEFAULT 0 +#define BENCH_FORMAT_SIMPLE_STR "simple" +#define BENCH_FORMAT_SIMPLE 1 + +#define BENCH_FORMAT_UNKNOWN -1 + +extern int bench_format; + +#endif diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c new file mode 100644 index 000000000000..89773178e894 --- /dev/null +++ b/tools/perf/bench/mem-memcpy.c @@ -0,0 +1,193 @@ +/* + * mem-memcpy.c + * + * memcpy: Simple memory copy in various ways + * + * Written by Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> + */ +#include <ctype.h> + +#include "../perf.h" +#include "../util/util.h" +#include "../util/parse-options.h" +#include "../util/string.h" +#include "../util/header.h" +#include "bench.h" + +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/time.h> +#include <errno.h> + +#define K 1024 + +static const char *length_str = "1MB"; +static const char *routine = "default"; +static int use_clock = 0; +static int clock_fd; + +static const struct option options[] = { + OPT_STRING('l', "length", &length_str, "1MB", + "Specify length of memory to copy. " + "available unit: B, MB, GB (upper and lower)"), + OPT_STRING('r', "routine", &routine, "default", + "Specify routine to copy"), + OPT_BOOLEAN('c', "clock", &use_clock, + "Use CPU clock for measuring"), + OPT_END() +}; + +struct routine { + const char *name; + const char *desc; + void * (*fn)(void *dst, const void *src, size_t len); +}; + +struct routine routines[] = { + { "default", + "Default memcpy() provided by glibc", + memcpy }, + { NULL, + NULL, + NULL } +}; + +static const char * const bench_mem_memcpy_usage[] = { + "perf bench mem memcpy <options>", + NULL +}; + +static struct perf_event_attr clock_attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES +}; + +static void init_clock(void) +{ + clock_fd = sys_perf_event_open(&clock_attr, getpid(), -1, -1, 0); + + if (clock_fd < 0 && errno == ENOSYS) + die("No CONFIG_PERF_EVENTS=y kernel support configured?\n"); + else + BUG_ON(clock_fd < 0); +} + +static u64 get_clock(void) +{ + int ret; + u64 clk; + + ret = read(clock_fd, &clk, sizeof(u64)); + BUG_ON(ret != sizeof(u64)); + + return clk; +} + +static double timeval2double(struct timeval *ts) +{ + return (double)ts->tv_sec + + (double)ts->tv_usec / (double)1000000; +} + +int bench_mem_memcpy(int argc, const char **argv, + const char *prefix __used) +{ + int i; + void *dst, *src; + size_t length; + double bps = 0.0; + struct timeval tv_start, tv_end, tv_diff; + u64 clock_start, clock_end, clock_diff; + + clock_start = clock_end = clock_diff = 0ULL; + argc = parse_options(argc, argv, options, + bench_mem_memcpy_usage, 0); + + tv_diff.tv_sec = 0; + tv_diff.tv_usec = 0; + length = (size_t)perf_atoll((char *)length_str); + + if ((s64)length <= 0) { + fprintf(stderr, "Invalid length:%s\n", length_str); + return 1; + } + + for (i = 0; routines[i].name; i++) { + if (!strcmp(routines[i].name, routine)) + break; + } + if (!routines[i].name) { + printf("Unknown routine:%s\n", routine); + printf("Available routines...\n"); + for (i = 0; routines[i].name; i++) { + printf("\t%s ... %s\n", + routines[i].name, routines[i].desc); + } + return 1; + } + + dst = zalloc(length); + if (!dst) + die("memory allocation failed - maybe length is too large?\n"); + + src = zalloc(length); + if (!src) + die("memory allocation failed - maybe length is too large?\n"); + + if (bench_format == BENCH_FORMAT_DEFAULT) { + printf("# Copying %s Bytes from %p to %p ...\n\n", + length_str, src, dst); + } + + if (use_clock) { + init_clock(); + clock_start = get_clock(); + } else { + BUG_ON(gettimeofday(&tv_start, NULL)); + } + + routines[i].fn(dst, src, length); + + if (use_clock) { + clock_end = get_clock(); + clock_diff = clock_end - clock_start; + } else { + BUG_ON(gettimeofday(&tv_end, NULL)); + timersub(&tv_end, &tv_start, &tv_diff); + bps = (double)((double)length / timeval2double(&tv_diff)); + } + + switch (bench_format) { + case BENCH_FORMAT_DEFAULT: + if (use_clock) { + printf(" %14lf Clock/Byte\n", + (double)clock_diff / (double)length); + } else { + if (bps < K) + printf(" %14lf B/Sec\n", bps); + else if (bps < K * K) + printf(" %14lfd KB/Sec\n", bps / 1024); + else if (bps < K * K * K) + printf(" %14lf MB/Sec\n", bps / 1024 / 1024); + else { + printf(" %14lf GB/Sec\n", + bps / 1024 / 1024 / 1024); + } + } + break; + case BENCH_FORMAT_SIMPLE: + if (use_clock) { + printf("%14lf\n", + (double)clock_diff / (double)length); + } else + printf("%lf\n", bps); + break; + default: + /* reaching this means there's some disaster: */ + die("unknown format: %d\n", bench_format); + break; + } + + return 0; +} diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c new file mode 100644 index 000000000000..605a2a959aa8 --- /dev/null +++ b/tools/perf/bench/sched-messaging.c @@ -0,0 +1,336 @@ +/* + * + * builtin-bench-messaging.c + * + * messaging: Benchmark for scheduler and IPC mechanisms + * + * Based on hackbench by Rusty Russell <rusty@rustcorp.com.au> + * Ported to perf by Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> + * + */ + +#include "../perf.h" +#include "../util/util.h" +#include "../util/parse-options.h" +#include "../builtin.h" +#include "bench.h" + +/* Test groups of 20 processes spraying to 20 receivers */ +#include <pthread.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <errno.h> +#include <unistd.h> +#include <sys/types.h> +#include <sys/socket.h> +#include <sys/wait.h> +#include <sys/time.h> +#include <sys/poll.h> +#include <limits.h> + +#define DATASIZE 100 + +static int use_pipes = 0; +static unsigned int loops = 100; +static unsigned int thread_mode = 0; +static unsigned int num_groups = 10; + +struct sender_context { + unsigned int num_fds; + int ready_out; + int wakefd; + int out_fds[0]; +}; + +struct receiver_context { + unsigned int num_packets; + int in_fds[2]; + int ready_out; + int wakefd; +}; + +static void barf(const char *msg) +{ + fprintf(stderr, "%s (error: %s)\n", msg, strerror(errno)); + exit(1); +} + +static void fdpair(int fds[2]) +{ + if (use_pipes) { + if (pipe(fds) == 0) + return; + } else { + if (socketpair(AF_UNIX, SOCK_STREAM, 0, fds) == 0) + return; + } + + barf(use_pipes ? "pipe()" : "socketpair()"); +} + +/* Block until we're ready to go */ +static void ready(int ready_out, int wakefd) +{ + char dummy; + struct pollfd pollfd = { .fd = wakefd, .events = POLLIN }; + + /* Tell them we're ready. */ + if (write(ready_out, &dummy, 1) != 1) + barf("CLIENT: ready write"); + + /* Wait for "GO" signal */ + if (poll(&pollfd, 1, -1) != 1) + barf("poll"); +} + +/* Sender sprays loops messages down each file descriptor */ +static void *sender(struct sender_context *ctx) +{ + char data[DATASIZE]; + unsigned int i, j; + + ready(ctx->ready_out, ctx->wakefd); + + /* Now pump to every receiver. */ + for (i = 0; i < loops; i++) { + for (j = 0; j < ctx->num_fds; j++) { + int ret, done = 0; + +again: + ret = write(ctx->out_fds[j], data + done, + sizeof(data)-done); + if (ret < 0) + barf("SENDER: write"); + done += ret; + if (done < DATASIZE) + goto again; + } + } + + return NULL; +} + + +/* One receiver per fd */ +static void *receiver(struct receiver_context* ctx) +{ + unsigned int i; + + if (!thread_mode) + close(ctx->in_fds[1]); + + /* Wait for start... */ + ready(ctx->ready_out, ctx->wakefd); + + /* Receive them all */ + for (i = 0; i < ctx->num_packets; i++) { + char data[DATASIZE]; + int ret, done = 0; + +again: + ret = read(ctx->in_fds[0], data + done, DATASIZE - done); + if (ret < 0) + barf("SERVER: read"); + done += ret; + if (done < DATASIZE) + goto again; + } + + return NULL; +} + +static pthread_t create_worker(void *ctx, void *(*func)(void *)) +{ + pthread_attr_t attr; + pthread_t childid; + int err; + + if (!thread_mode) { + /* process mode */ + /* Fork the receiver. */ + switch (fork()) { + case -1: + barf("fork()"); + break; + case 0: + (*func) (ctx); + exit(0); + break; + default: + break; + } + + return (pthread_t)0; + } + + if (pthread_attr_init(&attr) != 0) + barf("pthread_attr_init:"); + +#ifndef __ia64__ + if (pthread_attr_setstacksize(&attr, PTHREAD_STACK_MIN) != 0) + barf("pthread_attr_setstacksize"); +#endif + + err = pthread_create(&childid, &attr, func, ctx); + if (err != 0) { + fprintf(stderr, "pthread_create failed: %s (%d)\n", + strerror(err), err); + exit(-1); + } + return childid; +} + +static void reap_worker(pthread_t id) +{ + int proc_status; + void *thread_status; + + if (!thread_mode) { + /* process mode */ + wait(&proc_status); + if (!WIFEXITED(proc_status)) + exit(1); + } else { + pthread_join(id, &thread_status); + } +} + +/* One group of senders and receivers */ +static unsigned int group(pthread_t *pth, + unsigned int num_fds, + int ready_out, + int wakefd) +{ + unsigned int i; + struct sender_context *snd_ctx = malloc(sizeof(struct sender_context) + + num_fds * sizeof(int)); + + if (!snd_ctx) + barf("malloc()"); + + for (i = 0; i < num_fds; i++) { + int fds[2]; + struct receiver_context *ctx = malloc(sizeof(*ctx)); + + if (!ctx) + barf("malloc()"); + + + /* Create the pipe between client and server */ + fdpair(fds); + + ctx->num_packets = num_fds * loops; + ctx->in_fds[0] = fds[0]; + ctx->in_fds[1] = fds[1]; + ctx->ready_out = ready_out; + ctx->wakefd = wakefd; + + pth[i] = create_worker(ctx, (void *)receiver); + + snd_ctx->out_fds[i] = fds[1]; + if (!thread_mode) + close(fds[0]); + } + + /* Now we have all the fds, fork the senders */ + for (i = 0; i < num_fds; i++) { + snd_ctx->ready_out = ready_out; + snd_ctx->wakefd = wakefd; + snd_ctx->num_fds = num_fds; + + pth[num_fds+i] = create_worker(snd_ctx, (void *)sender); + } + + /* Close the fds we have left */ + if (!thread_mode) + for (i = 0; i < num_fds; i++) + close(snd_ctx->out_fds[i]); + + /* Return number of children to reap */ + return num_fds * 2; +} + +static const struct option options[] = { + OPT_BOOLEAN('p', "pipe", &use_pipes, + "Use pipe() instead of socketpair()"), + OPT_BOOLEAN('t', "thread", &thread_mode, + "Be multi thread instead of multi process"), + OPT_INTEGER('g', "group", &num_groups, + "Specify number of groups"), + OPT_INTEGER('l', "loop", &loops, + "Specify number of loops"), + OPT_END() +}; + +static const char * const bench_sched_message_usage[] = { + "perf bench sched messaging <options>", + NULL +}; + +int bench_sched_messaging(int argc, const char **argv, + const char *prefix __used) +{ + unsigned int i, total_children; + struct timeval start, stop, diff; + unsigned int num_fds = 20; + int readyfds[2], wakefds[2]; + char dummy; + pthread_t *pth_tab; + + argc = parse_options(argc, argv, options, + bench_sched_message_usage, 0); + + pth_tab = malloc(num_fds * 2 * num_groups * sizeof(pthread_t)); + if (!pth_tab) + barf("main:malloc()"); + + fdpair(readyfds); + fdpair(wakefds); + + total_children = 0; + for (i = 0; i < num_groups; i++) + total_children += group(pth_tab+total_children, num_fds, + readyfds[1], wakefds[0]); + + /* Wait for everyone to be ready */ + for (i = 0; i < total_children; i++) + if (read(readyfds[0], &dummy, 1) != 1) + barf("Reading for readyfds"); + + gettimeofday(&start, NULL); + + /* Kick them off */ + if (write(wakefds[1], &dummy, 1) != 1) + barf("Writing to start them"); + + /* Reap them all */ + for (i = 0; i < total_children; i++) + reap_worker(pth_tab[i]); + + gettimeofday(&stop, NULL); + + timersub(&stop, &start, &diff); + + switch (bench_format) { + case BENCH_FORMAT_DEFAULT: + printf("# %d sender and receiver %s per group\n", + num_fds, thread_mode ? "threads" : "processes"); + printf("# %d groups == %d %s run\n\n", + num_groups, num_groups * 2 * num_fds, + thread_mode ? "threads" : "processes"); + printf(" %14s: %lu.%03lu [sec]\n", "Total time", + diff.tv_sec, diff.tv_usec/1000); + break; + case BENCH_FORMAT_SIMPLE: + printf("%lu.%03lu\n", diff.tv_sec, diff.tv_usec/1000); + break; + default: + /* reaching here is something disaster */ + fprintf(stderr, "Unknown format:%d\n", bench_format); + exit(1); + break; + } + + return 0; +} diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c new file mode 100644 index 000000000000..238185f97977 --- /dev/null +++ b/tools/perf/bench/sched-pipe.c @@ -0,0 +1,124 @@ +/* + * + * builtin-bench-pipe.c + * + * pipe: Benchmark for pipe() + * + * Based on pipe-test-1m.c by Ingo Molnar <mingo@redhat.com> + * http://people.redhat.com/mingo/cfs-scheduler/tools/pipe-test-1m.c + * Ported to perf by Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> + * + */ + +#include "../perf.h" +#include "../util/util.h" +#include "../util/parse-options.h" +#include "../builtin.h" +#include "bench.h" + +#include <unistd.h> +#include <stdio.h> +#include <stdlib.h> +#include <signal.h> +#include <sys/wait.h> +#include <linux/unistd.h> +#include <string.h> +#include <errno.h> +#include <assert.h> +#include <sys/time.h> +#include <sys/types.h> + +#define LOOPS_DEFAULT 1000000 +static int loops = LOOPS_DEFAULT; + +static const struct option options[] = { + OPT_INTEGER('l', "loop", &loops, + "Specify number of loops"), + OPT_END() +}; + +static const char * const bench_sched_pipe_usage[] = { + "perf bench sched pipe <options>", + NULL +}; + +int bench_sched_pipe(int argc, const char **argv, + const char *prefix __used) +{ + int pipe_1[2], pipe_2[2]; + int m = 0, i; + struct timeval start, stop, diff; + unsigned long long result_usec = 0; + + /* + * why does "ret" exist? + * discarding returned value of read(), write() + * causes error in building environment for perf + */ + int ret, wait_stat; + pid_t pid, retpid; + + argc = parse_options(argc, argv, options, + bench_sched_pipe_usage, 0); + + assert(!pipe(pipe_1)); + assert(!pipe(pipe_2)); + + pid = fork(); + assert(pid >= 0); + + gettimeofday(&start, NULL); + + if (!pid) { + for (i = 0; i < loops; i++) { + ret = read(pipe_1[0], &m, sizeof(int)); + ret = write(pipe_2[1], &m, sizeof(int)); + } + } else { + for (i = 0; i < loops; i++) { + ret = write(pipe_1[1], &m, sizeof(int)); + ret = read(pipe_2[0], &m, sizeof(int)); + } + } + + gettimeofday(&stop, NULL); + timersub(&stop, &start, &diff); + + if (pid) { + retpid = waitpid(pid, &wait_stat, 0); + assert((retpid == pid) && WIFEXITED(wait_stat)); + return 0; + } + + switch (bench_format) { + case BENCH_FORMAT_DEFAULT: + printf("# Extecuted %d pipe operations between two tasks\n\n", + loops); + + result_usec = diff.tv_sec * 1000000; + result_usec += diff.tv_usec; + + printf(" %14s: %lu.%03lu [sec]\n\n", "Total time", + diff.tv_sec, diff.tv_usec/1000); + + printf(" %14lf usecs/op\n", + (double)result_usec / (double)loops); + printf(" %14d ops/sec\n", + (int)((double)loops / + ((double)result_usec / (double)1000000))); + break; + + case BENCH_FORMAT_SIMPLE: + printf("%lu.%03lu\n", + diff.tv_sec, diff.tv_usec / 1000); + break; + + default: + /* reaching here is something disaster */ + fprintf(stderr, "Unknown format:%d\n", bench_format); + exit(1); + break; + } + + return 0; +} diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 1ec741615814..0bf2e8f9af57 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -19,29 +19,26 @@ #include "perf.h" #include "util/debug.h" +#include "util/event.h" #include "util/parse-options.h" #include "util/parse-events.h" #include "util/thread.h" +#include "util/sort.h" +#include "util/hist.h" +#include "util/data_map.h" static char const *input_name = "perf.data"; -static char default_sort_order[] = "comm,symbol"; -static char *sort_order = default_sort_order; - static int force; -static int input; -static int show_mask = SHOW_KERNEL | SHOW_USER | SHOW_HV; static int full_paths; static int print_line; -static unsigned long page_size; -static unsigned long mmap_window = 32; - -static struct rb_root threads; -static struct thread *last_match; - +struct sym_hist { + u64 sum; + u64 ip[0]; +}; struct sym_ext { struct rb_node node; @@ -49,247 +46,38 @@ struct sym_ext { char *path; }; -/* - * histogram, sorted on item, collects counts - */ - -static struct rb_root hist; - -struct hist_entry { - struct rb_node rb_node; - - struct thread *thread; - struct map *map; - struct dso *dso; - struct symbol *sym; - u64 ip; - char level; - - uint32_t count; -}; - -/* - * configurable sorting bits - */ - -struct sort_entry { - struct list_head list; - - const char *header; - - int64_t (*cmp)(struct hist_entry *, struct hist_entry *); - int64_t (*collapse)(struct hist_entry *, struct hist_entry *); - size_t (*print)(FILE *fp, struct hist_entry *); -}; - -/* --sort pid */ - -static int64_t -sort__thread_cmp(struct hist_entry *left, struct hist_entry *right) -{ - return right->thread->pid - left->thread->pid; -} - -static size_t -sort__thread_print(FILE *fp, struct hist_entry *self) -{ - return fprintf(fp, "%16s:%5d", self->thread->comm ?: "", self->thread->pid); -} - -static struct sort_entry sort_thread = { - .header = " Command: Pid", - .cmp = sort__thread_cmp, - .print = sort__thread_print, -}; - -/* --sort comm */ - -static int64_t -sort__comm_cmp(struct hist_entry *left, struct hist_entry *right) -{ - return right->thread->pid - left->thread->pid; -} - -static int64_t -sort__comm_collapse(struct hist_entry *left, struct hist_entry *right) -{ - char *comm_l = left->thread->comm; - char *comm_r = right->thread->comm; - - if (!comm_l || !comm_r) { - if (!comm_l && !comm_r) - return 0; - else if (!comm_l) - return -1; - else - return 1; - } - - return strcmp(comm_l, comm_r); -} - -static size_t -sort__comm_print(FILE *fp, struct hist_entry *self) -{ - return fprintf(fp, "%16s", self->thread->comm); -} - -static struct sort_entry sort_comm = { - .header = " Command", - .cmp = sort__comm_cmp, - .collapse = sort__comm_collapse, - .print = sort__comm_print, -}; - -/* --sort dso */ - -static int64_t -sort__dso_cmp(struct hist_entry *left, struct hist_entry *right) -{ - struct dso *dso_l = left->dso; - struct dso *dso_r = right->dso; - - if (!dso_l || !dso_r) { - if (!dso_l && !dso_r) - return 0; - else if (!dso_l) - return -1; - else - return 1; - } - - return strcmp(dso_l->name, dso_r->name); -} - -static size_t -sort__dso_print(FILE *fp, struct hist_entry *self) -{ - if (self->dso) - return fprintf(fp, "%-25s", self->dso->name); - - return fprintf(fp, "%016llx ", (u64)self->ip); -} - -static struct sort_entry sort_dso = { - .header = "Shared Object ", - .cmp = sort__dso_cmp, - .print = sort__dso_print, -}; - -/* --sort symbol */ - -static int64_t -sort__sym_cmp(struct hist_entry *left, struct hist_entry *right) -{ - u64 ip_l, ip_r; - - if (left->sym == right->sym) - return 0; - - ip_l = left->sym ? left->sym->start : left->ip; - ip_r = right->sym ? right->sym->start : right->ip; - - return (int64_t)(ip_r - ip_l); -} - -static size_t -sort__sym_print(FILE *fp, struct hist_entry *self) -{ - size_t ret = 0; - - if (verbose) - ret += fprintf(fp, "%#018llx ", (u64)self->ip); - - if (self->sym) { - ret += fprintf(fp, "[%c] %s", - self->dso == kernel_dso ? 'k' : '.', self->sym->name); - } else { - ret += fprintf(fp, "%#016llx", (u64)self->ip); - } - - return ret; -} - -static struct sort_entry sort_sym = { - .header = "Symbol", - .cmp = sort__sym_cmp, - .print = sort__sym_print, -}; - -static int sort__need_collapse = 0; - -struct sort_dimension { - const char *name; - struct sort_entry *entry; - int taken; +struct sym_priv { + struct sym_hist *hist; + struct sym_ext *ext; }; -static struct sort_dimension sort_dimensions[] = { - { .name = "pid", .entry = &sort_thread, }, - { .name = "comm", .entry = &sort_comm, }, - { .name = "dso", .entry = &sort_dso, }, - { .name = "symbol", .entry = &sort_sym, }, +static struct symbol_conf symbol_conf = { + .priv_size = sizeof(struct sym_priv), + .try_vmlinux_path = true, }; -static LIST_HEAD(hist_entry__sort_list); +static const char *sym_hist_filter; -static int sort_dimension__add(char *tok) +static int symbol_filter(struct map *map __used, struct symbol *sym) { - unsigned int i; - - for (i = 0; i < ARRAY_SIZE(sort_dimensions); i++) { - struct sort_dimension *sd = &sort_dimensions[i]; - - if (sd->taken) - continue; - - if (strncasecmp(tok, sd->name, strlen(tok))) - continue; - - if (sd->entry->collapse) - sort__need_collapse = 1; - - list_add_tail(&sd->entry->list, &hist_entry__sort_list); - sd->taken = 1; + if (sym_hist_filter == NULL || + strcmp(sym->name, sym_hist_filter) == 0) { + struct sym_priv *priv = symbol__priv(sym); + const int size = (sizeof(*priv->hist) + + (sym->end - sym->start) * sizeof(u64)); + priv->hist = malloc(size); + if (priv->hist) + memset(priv->hist, 0, size); return 0; } - - return -ESRCH; -} - -static int64_t -hist_entry__cmp(struct hist_entry *left, struct hist_entry *right) -{ - struct sort_entry *se; - int64_t cmp = 0; - - list_for_each_entry(se, &hist_entry__sort_list, list) { - cmp = se->cmp(left, right); - if (cmp) - break; - } - - return cmp; -} - -static int64_t -hist_entry__collapse(struct hist_entry *left, struct hist_entry *right) -{ - struct sort_entry *se; - int64_t cmp = 0; - - list_for_each_entry(se, &hist_entry__sort_list, list) { - int64_t (*f)(struct hist_entry *, struct hist_entry *); - - f = se->collapse ?: se->cmp; - - cmp = f(left, right); - if (cmp) - break; - } - - return cmp; + /* + * FIXME: We should really filter it out, as we don't want to go thru symbols + * we're not interested, and if a DSO ends up with no symbols, delete it too, + * but right now the kernel loading routines in symbol.c bail out if no symbols + * are found, fix it later. + */ + return 0; } /* @@ -299,380 +87,81 @@ static void hist_hit(struct hist_entry *he, u64 ip) { unsigned int sym_size, offset; struct symbol *sym = he->sym; + struct sym_priv *priv; + struct sym_hist *h; he->count++; - if (!sym || !sym->hist) + if (!sym || !he->map) + return; + + priv = symbol__priv(sym); + if (!priv->hist) return; sym_size = sym->end - sym->start; offset = ip - sym->start; + if (verbose) + fprintf(stderr, "%s: ip=%Lx\n", __func__, + he->map->unmap_ip(he->map, ip)); + if (offset >= sym_size) return; - sym->hist_sum++; - sym->hist[offset]++; + h = priv->hist; + h->sum++; + h->ip[offset]++; if (verbose >= 3) printf("%p %s: count++ [ip: %p, %08Lx] => %Ld\n", (void *)(unsigned long)he->sym->start, he->sym->name, (void *)(unsigned long)ip, ip - he->sym->start, - sym->hist[offset]); + h->ip[offset]); } -static int -hist_entry__add(struct thread *thread, struct map *map, struct dso *dso, - struct symbol *sym, u64 ip, char level) +static int hist_entry__add(struct addr_location *al, u64 count) { - struct rb_node **p = &hist.rb_node; - struct rb_node *parent = NULL; - struct hist_entry *he; - struct hist_entry entry = { - .thread = thread, - .map = map, - .dso = dso, - .sym = sym, - .ip = ip, - .level = level, - .count = 1, - }; - int cmp; - - while (*p != NULL) { - parent = *p; - he = rb_entry(parent, struct hist_entry, rb_node); - - cmp = hist_entry__cmp(&entry, he); - - if (!cmp) { - hist_hit(he, ip); - - return 0; - } - - if (cmp < 0) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; - } - - he = malloc(sizeof(*he)); - if (!he) + bool hit; + struct hist_entry *he = __hist_entry__add(al, NULL, count, &hit); + if (he == NULL) return -ENOMEM; - *he = entry; - rb_link_node(&he->rb_node, parent, p); - rb_insert_color(&he->rb_node, &hist); - + hist_hit(he, al->addr); return 0; } -static void hist_entry__free(struct hist_entry *he) -{ - free(he); -} - -/* - * collapse the histogram - */ - -static struct rb_root collapse_hists; - -static void collapse__insert_entry(struct hist_entry *he) -{ - struct rb_node **p = &collapse_hists.rb_node; - struct rb_node *parent = NULL; - struct hist_entry *iter; - int64_t cmp; - - while (*p != NULL) { - parent = *p; - iter = rb_entry(parent, struct hist_entry, rb_node); - - cmp = hist_entry__collapse(iter, he); - - if (!cmp) { - iter->count += he->count; - hist_entry__free(he); - return; - } - - if (cmp < 0) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; - } - - rb_link_node(&he->rb_node, parent, p); - rb_insert_color(&he->rb_node, &collapse_hists); -} - -static void collapse__resort(void) -{ - struct rb_node *next; - struct hist_entry *n; - - if (!sort__need_collapse) - return; - - next = rb_first(&hist); - while (next) { - n = rb_entry(next, struct hist_entry, rb_node); - next = rb_next(&n->rb_node); - - rb_erase(&n->rb_node, &hist); - collapse__insert_entry(n); - } -} - -/* - * reverse the map, sort on count. - */ - -static struct rb_root output_hists; - -static void output__insert_entry(struct hist_entry *he) +static int process_sample_event(event_t *event) { - struct rb_node **p = &output_hists.rb_node; - struct rb_node *parent = NULL; - struct hist_entry *iter; + struct addr_location al; - while (*p != NULL) { - parent = *p; - iter = rb_entry(parent, struct hist_entry, rb_node); + dump_printf("(IP, %d): %d: %p\n", event->header.misc, + event->ip.pid, (void *)(long)event->ip.ip); - if (he->count > iter->count) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; - } - - rb_link_node(&he->rb_node, parent, p); - rb_insert_color(&he->rb_node, &output_hists); -} - -static void output__resort(void) -{ - struct rb_node *next; - struct hist_entry *n; - struct rb_root *tree = &hist; - - if (sort__need_collapse) - tree = &collapse_hists; - - next = rb_first(tree); - - while (next) { - n = rb_entry(next, struct hist_entry, rb_node); - next = rb_next(&n->rb_node); - - rb_erase(&n->rb_node, tree); - output__insert_entry(n); - } -} - -static unsigned long total = 0, - total_mmap = 0, - total_comm = 0, - total_fork = 0, - total_unknown = 0; - -static int -process_sample_event(event_t *event, unsigned long offset, unsigned long head) -{ - char level; - int show = 0; - struct dso *dso = NULL; - struct thread *thread; - u64 ip = event->ip.ip; - struct map *map = NULL; - - thread = threads__findnew(event->ip.pid, &threads, &last_match); - - dump_printf("%p [%p]: PERF_EVENT (IP, %d): %d: %p\n", - (void *)(offset + head), - (void *)(long)(event->header.size), - event->header.misc, - event->ip.pid, - (void *)(long)ip); - - dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid); - - if (thread == NULL) { + if (event__preprocess_sample(event, &al, symbol_filter) < 0) { fprintf(stderr, "problem processing %d event, skipping it.\n", event->header.type); return -1; } - if (event->header.misc & PERF_RECORD_MISC_KERNEL) { - show = SHOW_KERNEL; - level = 'k'; - - dso = kernel_dso; - - dump_printf(" ...... dso: %s\n", dso->name); - - } else if (event->header.misc & PERF_RECORD_MISC_USER) { - - show = SHOW_USER; - level = '.'; - - map = thread__find_map(thread, ip); - if (map != NULL) { - ip = map->map_ip(map, ip); - dso = map->dso; - } else { - /* - * If this is outside of all known maps, - * and is a negative address, try to look it - * up in the kernel dso, as it might be a - * vsyscall (which executes in user-mode): - */ - if ((long long)ip < 0) - dso = kernel_dso; - } - dump_printf(" ...... dso: %s\n", dso ? dso->name : "<not found>"); - - } else { - show = SHOW_HV; - level = 'H'; - dump_printf(" ...... dso: [hypervisor]\n"); - } - - if (show & show_mask) { - struct symbol *sym = NULL; - - if (dso) - sym = dso->find_symbol(dso, ip); - - if (hist_entry__add(thread, map, dso, sym, ip, level)) { - fprintf(stderr, - "problem incrementing symbol count, skipping event\n"); - return -1; - } - } - total++; - - return 0; -} - -static int -process_mmap_event(event_t *event, unsigned long offset, unsigned long head) -{ - struct thread *thread; - struct map *map = map__new(&event->mmap, NULL, 0); - - thread = threads__findnew(event->mmap.pid, &threads, &last_match); - - dump_printf("%p [%p]: PERF_RECORD_MMAP %d: [%p(%p) @ %p]: %s\n", - (void *)(offset + head), - (void *)(long)(event->header.size), - event->mmap.pid, - (void *)(long)event->mmap.start, - (void *)(long)event->mmap.len, - (void *)(long)event->mmap.pgoff, - event->mmap.filename); - - if (thread == NULL || map == NULL) { - dump_printf("problem processing PERF_RECORD_MMAP, skipping event.\n"); - return 0; - } - - thread__insert_map(thread, map); - total_mmap++; - - return 0; -} - -static int -process_comm_event(event_t *event, unsigned long offset, unsigned long head) -{ - struct thread *thread; - - thread = threads__findnew(event->comm.pid, &threads, &last_match); - dump_printf("%p [%p]: PERF_RECORD_COMM: %s:%d\n", - (void *)(offset + head), - (void *)(long)(event->header.size), - event->comm.comm, event->comm.pid); - - if (thread == NULL || - thread__set_comm(thread, event->comm.comm)) { - dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n"); - return -1; - } - total_comm++; - - return 0; -} - -static int -process_fork_event(event_t *event, unsigned long offset, unsigned long head) -{ - struct thread *thread; - struct thread *parent; - - thread = threads__findnew(event->fork.pid, &threads, &last_match); - parent = threads__findnew(event->fork.ppid, &threads, &last_match); - dump_printf("%p [%p]: PERF_RECORD_FORK: %d:%d\n", - (void *)(offset + head), - (void *)(long)(event->header.size), - event->fork.pid, event->fork.ppid); - - /* - * A thread clone will have the same PID for both - * parent and child. - */ - if (thread == parent) - return 0; - - if (!thread || !parent || thread__fork(thread, parent)) { - dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n"); - return -1; - } - total_fork++; - - return 0; -} - -static int -process_event(event_t *event, unsigned long offset, unsigned long head) -{ - switch (event->header.type) { - case PERF_RECORD_SAMPLE: - return process_sample_event(event, offset, head); - - case PERF_RECORD_MMAP: - return process_mmap_event(event, offset, head); - - case PERF_RECORD_COMM: - return process_comm_event(event, offset, head); - - case PERF_RECORD_FORK: - return process_fork_event(event, offset, head); - /* - * We dont process them right now but they are fine: - */ - - case PERF_RECORD_THROTTLE: - case PERF_RECORD_UNTHROTTLE: - return 0; - - default: + if (hist_entry__add(&al, 1)) { + fprintf(stderr, "problem incrementing symbol count, " + "skipping event\n"); return -1; } return 0; } -static int -parse_line(FILE *file, struct symbol *sym, u64 start, u64 len) +static int parse_line(FILE *file, struct hist_entry *he, u64 len) { + struct symbol *sym = he->sym; char *line = NULL, *tmp, *tmp2; static const char *prev_line; static const char *prev_color; unsigned int offset; size_t line_len; + u64 start; s64 line_ip; int ret; char *c; @@ -709,22 +198,26 @@ parse_line(FILE *file, struct symbol *sym, u64 start, u64 len) line_ip = -1; } + start = he->map->unmap_ip(he->map, sym->start); + if (line_ip != -1) { const char *path = NULL; unsigned int hits = 0; double percent = 0.0; const char *color; - struct sym_ext *sym_ext = sym->priv; + struct sym_priv *priv = symbol__priv(sym); + struct sym_ext *sym_ext = priv->ext; + struct sym_hist *h = priv->hist; offset = line_ip - start; if (offset < len) - hits = sym->hist[offset]; + hits = h->ip[offset]; if (offset < len && sym_ext) { path = sym_ext[offset].path; percent = sym_ext[offset].percent; - } else if (sym->hist_sum) - percent = 100.0 * hits / sym->hist_sum; + } else if (h->sum) + percent = 100.0 * hits / h->sum; color = get_percent_color(percent); @@ -777,9 +270,10 @@ static void insert_source_line(struct sym_ext *sym_ext) rb_insert_color(&sym_ext->node, &root_sym_ext); } -static void free_source_line(struct symbol *sym, int len) +static void free_source_line(struct hist_entry *he, int len) { - struct sym_ext *sym_ext = sym->priv; + struct sym_priv *priv = symbol__priv(he->sym); + struct sym_ext *sym_ext = priv->ext; int i; if (!sym_ext) @@ -789,26 +283,30 @@ static void free_source_line(struct symbol *sym, int len) free(sym_ext[i].path); free(sym_ext); - sym->priv = NULL; + priv->ext = NULL; root_sym_ext = RB_ROOT; } /* Get the filename:line for the colored entries */ static void -get_source_line(struct symbol *sym, u64 start, int len, const char *filename) +get_source_line(struct hist_entry *he, int len, const char *filename) { + struct symbol *sym = he->sym; + u64 start; int i; char cmd[PATH_MAX * 2]; struct sym_ext *sym_ext; + struct sym_priv *priv = symbol__priv(sym); + struct sym_hist *h = priv->hist; - if (!sym->hist_sum) + if (!h->sum) return; - sym->priv = calloc(len, sizeof(struct sym_ext)); - if (!sym->priv) + sym_ext = priv->ext = calloc(len, sizeof(struct sym_ext)); + if (!priv->ext) return; - sym_ext = sym->priv; + start = he->map->unmap_ip(he->map, sym->start); for (i = 0; i < len; i++) { char *path = NULL; @@ -816,7 +314,7 @@ get_source_line(struct symbol *sym, u64 start, int len, const char *filename) u64 offset; FILE *fp; - sym_ext[i].percent = 100.0 * sym->hist[i] / sym->hist_sum; + sym_ext[i].percent = 100.0 * h->ip[i] / h->sum; if (sym_ext[i].percent <= 0.5) continue; @@ -870,33 +368,34 @@ static void print_summary(const char *filename) } } -static void annotate_sym(struct dso *dso, struct symbol *sym) +static void annotate_sym(struct hist_entry *he) { - const char *filename = dso->name, *d_filename; - u64 start, end, len; + struct map *map = he->map; + struct dso *dso = map->dso; + struct symbol *sym = he->sym; + const char *filename = dso->long_name, *d_filename; + u64 len; char command[PATH_MAX*2]; FILE *file; if (!filename) return; - if (sym->module) - filename = sym->module->path; - else if (dso == kernel_dso) - filename = vmlinux_name; - - start = sym->obj_start; - if (!start) - start = sym->start; + + if (verbose) + fprintf(stderr, "%s: filename=%s, sym=%s, start=%Lx, end=%Lx\n", + __func__, filename, sym->name, + map->unmap_ip(map, sym->start), + map->unmap_ip(map, sym->end)); + if (full_paths) d_filename = filename; else d_filename = basename(filename); - end = start + sym->end - sym->start + 1; len = sym->end - sym->start; if (print_line) { - get_source_line(sym, start, len, filename); + get_source_line(he, len, filename); print_summary(filename); } @@ -905,10 +404,12 @@ static void annotate_sym(struct dso *dso, struct symbol *sym) printf("------------------------------------------------\n"); if (verbose >= 2) - printf("annotating [%p] %30s : [%p] %30s\n", dso, dso->name, sym, sym->name); + printf("annotating [%p] %30s : [%p] %30s\n", + dso, dso->long_name, sym, sym->name); sprintf(command, "objdump --start-address=0x%016Lx --stop-address=0x%016Lx -dS %s|grep -v %s", - (u64)start, (u64)end, filename, filename); + map->unmap_ip(map, sym->start), map->unmap_ip(map, sym->end), + filename, filename); if (verbose >= 3) printf("doing: %s\n", command); @@ -918,159 +419,78 @@ static void annotate_sym(struct dso *dso, struct symbol *sym) return; while (!feof(file)) { - if (parse_line(file, sym, start, len) < 0) + if (parse_line(file, he, len) < 0) break; } pclose(file); if (print_line) - free_source_line(sym, len); + free_source_line(he, len); } static void find_annotations(void) { struct rb_node *nd; - struct dso *dso; - int count = 0; - - list_for_each_entry(dso, &dsos, node) { - - for (nd = rb_first(&dso->syms); nd; nd = rb_next(nd)) { - struct symbol *sym = rb_entry(nd, struct symbol, rb_node); - - if (sym->hist) { - annotate_sym(dso, sym); - count++; - } - } - } - - if (!count) - printf(" Error: symbol '%s' not present amongst the samples.\n", sym_hist_filter); -} - -static int __cmd_annotate(void) -{ - int ret, rc = EXIT_FAILURE; - unsigned long offset = 0; - unsigned long head = 0; - struct stat input_stat; - event_t *event; - uint32_t size; - char *buf; - - register_idle_thread(&threads, &last_match); - - input = open(input_name, O_RDONLY); - if (input < 0) { - perror("failed to open file"); - exit(-1); - } - - ret = fstat(input, &input_stat); - if (ret < 0) { - perror("failed to stat file"); - exit(-1); - } - - if (!force && input_stat.st_uid && (input_stat.st_uid != geteuid())) { - fprintf(stderr, "file: %s not owned by current user or root\n", input_name); - exit(-1); - } - - if (!input_stat.st_size) { - fprintf(stderr, "zero-sized file, nothing to do!\n"); - exit(0); - } - - if (load_kernel() < 0) { - perror("failed to load kernel symbols"); - return EXIT_FAILURE; - } - -remap: - buf = (char *)mmap(NULL, page_size * mmap_window, PROT_READ, - MAP_SHARED, input, offset); - if (buf == MAP_FAILED) { - perror("failed to mmap file"); - exit(-1); - } - -more: - event = (event_t *)(buf + head); - size = event->header.size; - if (!size) - size = 8; + for (nd = rb_first(&output_hists); nd; nd = rb_next(nd)) { + struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node); + struct sym_priv *priv; - if (head + event->header.size >= page_size * mmap_window) { - unsigned long shift = page_size * (head / page_size); - int munmap_ret; - - munmap_ret = munmap(buf, page_size * mmap_window); - assert(munmap_ret == 0); - - offset += shift; - head -= shift; - goto remap; - } - - size = event->header.size; - - dump_printf("%p [%p]: event: %d\n", - (void *)(offset + head), - (void *)(long)event->header.size, - event->header.type); - - if (!size || process_event(event, offset, head) < 0) { - - dump_printf("%p [%p]: skipping unknown header type: %d\n", - (void *)(offset + head), - (void *)(long)(event->header.size), - event->header.type); + if (he->sym == NULL) + continue; - total_unknown++; + priv = symbol__priv(he->sym); + if (priv->hist == NULL) + continue; + annotate_sym(he); /* - * assume we lost track of the stream, check alignment, and - * increment a single u64 in the hope to catch on again 'soon'. + * Since we have a hist_entry per IP for the same symbol, free + * he->sym->hist to signal we already processed this symbol. */ - - if (unlikely(head & 7)) - head &= ~7ULL; - - size = 8; + free(priv->hist); + priv->hist = NULL; } +} - head += size; +static struct perf_file_handler file_handler = { + .process_sample_event = process_sample_event, + .process_mmap_event = event__process_mmap, + .process_comm_event = event__process_comm, + .process_fork_event = event__process_task, +}; - if (offset + head < (unsigned long)input_stat.st_size) - goto more; +static int __cmd_annotate(void) +{ + struct perf_header *header; + struct thread *idle; + int ret; - rc = EXIT_SUCCESS; - close(input); + idle = register_idle_thread(); + register_perf_file_handler(&file_handler); - dump_printf(" IP events: %10ld\n", total); - dump_printf(" mmap events: %10ld\n", total_mmap); - dump_printf(" comm events: %10ld\n", total_comm); - dump_printf(" fork events: %10ld\n", total_fork); - dump_printf(" unknown events: %10ld\n", total_unknown); + ret = mmap_dispatch_perf_file(&header, input_name, 0, 0, + &event__cwdlen, &event__cwd); + if (ret) + return ret; - if (dump_trace) + if (dump_trace) { + event__print_totals(); return 0; + } - if (verbose >= 3) - threads__fprintf(stdout, &threads); + if (verbose > 3) + threads__fprintf(stdout); - if (verbose >= 2) + if (verbose > 2) dsos__fprintf(stdout); collapse__resort(); - output__resort(); + output__resort(event__total[0]); find_annotations(); - return rc; + return ret; } static const char * const annotate_usage[] = { @@ -1088,8 +508,9 @@ static const struct option options[] = { "be more verbose (show symbol address, etc)"), OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), - OPT_STRING('k', "vmlinux", &vmlinux_name, "file", "vmlinux pathname"), - OPT_BOOLEAN('m', "modules", &modules, + OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name, + "file", "vmlinux pathname"), + OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules, "load module symbols - WARNING: use only with -k and LIVE kernel"), OPT_BOOLEAN('l', "print-line", &print_line, "print matching source lines (may be slow)"), @@ -1115,9 +536,8 @@ static void setup_sorting(void) int cmd_annotate(int argc, const char **argv, const char *prefix __used) { - symbol__init(); - - page_size = getpagesize(); + if (symbol__init(&symbol_conf) < 0) + return -1; argc = parse_options(argc, argv, options, annotate_usage, 0); @@ -1134,10 +554,13 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __used) sym_hist_filter = argv[0]; } - if (!sym_hist_filter) - usage_with_options(annotate_usage, options); - setup_pager(); + if (field_sep && *field_sep == '.') { + fputs("'.' is the only non valid --field-separator argument\n", + stderr); + exit(129); + } + return __cmd_annotate(); } diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c new file mode 100644 index 000000000000..e043eb83092a --- /dev/null +++ b/tools/perf/builtin-bench.c @@ -0,0 +1,196 @@ +/* + * + * builtin-bench.c + * + * General benchmarking subsystem provided by perf + * + * Copyright (C) 2009, Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> + * + */ + +/* + * + * Available subsystem list: + * sched ... scheduler and IPC mechanism + * mem ... memory access performance + * + */ + +#include "perf.h" +#include "util/util.h" +#include "util/parse-options.h" +#include "builtin.h" +#include "bench/bench.h" + +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +struct bench_suite { + const char *name; + const char *summary; + int (*fn)(int, const char **, const char *); +}; + +static struct bench_suite sched_suites[] = { + { "messaging", + "Benchmark for scheduler and IPC mechanisms", + bench_sched_messaging }, + { "pipe", + "Flood of communication over pipe() between two processes", + bench_sched_pipe }, + { NULL, + NULL, + NULL } +}; + +static struct bench_suite mem_suites[] = { + { "memcpy", + "Simple memory copy in various ways", + bench_mem_memcpy }, + { NULL, + NULL, + NULL } +}; + +struct bench_subsys { + const char *name; + const char *summary; + struct bench_suite *suites; +}; + +static struct bench_subsys subsystems[] = { + { "sched", + "scheduler and IPC mechanism", + sched_suites }, + { "mem", + "memory access performance", + mem_suites }, + { NULL, + NULL, + NULL } +}; + +static void dump_suites(int subsys_index) +{ + int i; + + printf("List of available suites for %s...\n\n", + subsystems[subsys_index].name); + + for (i = 0; subsystems[subsys_index].suites[i].name; i++) + printf("\t%s: %s\n", + subsystems[subsys_index].suites[i].name, + subsystems[subsys_index].suites[i].summary); + + printf("\n"); + return; +} + +static char *bench_format_str; +int bench_format = BENCH_FORMAT_DEFAULT; + +static const struct option bench_options[] = { + OPT_STRING('f', "format", &bench_format_str, "default", + "Specify format style"), + OPT_END() +}; + +static const char * const bench_usage[] = { + "perf bench [<common options>] <subsystem> <suite> [<options>]", + NULL +}; + +static void print_usage(void) +{ + int i; + + printf("Usage: \n"); + for (i = 0; bench_usage[i]; i++) + printf("\t%s\n", bench_usage[i]); + printf("\n"); + + printf("List of available subsystems...\n\n"); + + for (i = 0; subsystems[i].name; i++) + printf("\t%s: %s\n", + subsystems[i].name, subsystems[i].summary); + printf("\n"); +} + +static int bench_str2int(char *str) +{ + if (!str) + return BENCH_FORMAT_DEFAULT; + + if (!strcmp(str, BENCH_FORMAT_DEFAULT_STR)) + return BENCH_FORMAT_DEFAULT; + else if (!strcmp(str, BENCH_FORMAT_SIMPLE_STR)) + return BENCH_FORMAT_SIMPLE; + + return BENCH_FORMAT_UNKNOWN; +} + +int cmd_bench(int argc, const char **argv, const char *prefix __used) +{ + int i, j, status = 0; + + if (argc < 2) { + /* No subsystem specified. */ + print_usage(); + goto end; + } + + argc = parse_options(argc, argv, bench_options, bench_usage, + PARSE_OPT_STOP_AT_NON_OPTION); + + bench_format = bench_str2int(bench_format_str); + if (bench_format == BENCH_FORMAT_UNKNOWN) { + printf("Unknown format descriptor:%s\n", bench_format_str); + goto end; + } + + if (argc < 1) { + print_usage(); + goto end; + } + + for (i = 0; subsystems[i].name; i++) { + if (strcmp(subsystems[i].name, argv[0])) + continue; + + if (argc < 2) { + /* No suite specified. */ + dump_suites(i); + goto end; + } + + for (j = 0; subsystems[i].suites[j].name; j++) { + if (strcmp(subsystems[i].suites[j].name, argv[1])) + continue; + + if (bench_format == BENCH_FORMAT_DEFAULT) + printf("# Running %s/%s benchmark...\n", + subsystems[i].name, + subsystems[i].suites[j].name); + status = subsystems[i].suites[j].fn(argc - 1, + argv + 1, prefix); + goto end; + } + + if (!strcmp(argv[1], "-h") || !strcmp(argv[1], "--help")) { + dump_suites(i); + goto end; + } + + printf("Unknown suite:%s for %s\n", argv[1], argv[0]); + status = 1; + goto end; + } + + printf("Unknown subsystem:%s\n", argv[0]); + status = 1; + +end: + return status; +} diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c new file mode 100644 index 000000000000..7dee9d19ab7a --- /dev/null +++ b/tools/perf/builtin-buildid-list.c @@ -0,0 +1,116 @@ +/* + * builtin-buildid-list.c + * + * Builtin buildid-list command: list buildids in perf.data + * + * Copyright (C) 2009, Red Hat Inc. + * Copyright (C) 2009, Arnaldo Carvalho de Melo <acme@redhat.com> + */ +#include "builtin.h" +#include "perf.h" +#include "util/cache.h" +#include "util/data_map.h" +#include "util/debug.h" +#include "util/header.h" +#include "util/parse-options.h" +#include "util/symbol.h" + +static char const *input_name = "perf.data"; +static int force; + +static const char *const buildid_list_usage[] = { + "perf report [<options>]", + NULL +}; + +static const struct option options[] = { + OPT_STRING('i', "input", &input_name, "file", + "input file name"), + OPT_BOOLEAN('f', "force", &force, "don't complain, do it"), + OPT_BOOLEAN('v', "verbose", &verbose, + "be more verbose"), + OPT_END() +}; + +static int perf_file_section__process_buildids(struct perf_file_section *self, + int feat, int fd) +{ + if (feat != HEADER_BUILD_ID) + return 0; + + if (lseek(fd, self->offset, SEEK_SET) < 0) { + pr_warning("Failed to lseek to %Ld offset for buildids!\n", + self->offset); + return -1; + } + + if (perf_header__read_build_ids(fd, self->offset, self->size)) { + pr_warning("Failed to read buildids!\n"); + return -1; + } + + return 0; +} + +static int __cmd_buildid_list(void) +{ + int err = -1; + struct perf_header *header; + struct perf_file_header f_header; + struct stat input_stat; + int input = open(input_name, O_RDONLY); + + if (input < 0) { + pr_err("failed to open file: %s", input_name); + if (!strcmp(input_name, "perf.data")) + pr_err(" (try 'perf record' first)"); + pr_err("\n"); + goto out; + } + + err = fstat(input, &input_stat); + if (err < 0) { + perror("failed to stat file"); + goto out_close; + } + + if (!force && input_stat.st_uid && (input_stat.st_uid != geteuid())) { + pr_err("file %s not owned by current user or root\n", + input_name); + goto out_close; + } + + if (!input_stat.st_size) { + pr_info("zero-sized file, nothing to do!\n"); + goto out_close; + } + + err = -1; + header = perf_header__new(); + if (header == NULL) + goto out_close; + + if (perf_file_header__read(&f_header, header, input) < 0) { + pr_warning("incompatible file format"); + goto out_close; + } + + err = perf_header__process_sections(header, input, + perf_file_section__process_buildids); + + if (err < 0) + goto out_close; + + dsos__fprintf_buildid(stdout); +out_close: + close(input); +out: + return err; +} + +int cmd_buildid_list(int argc, const char **argv, const char *prefix __used) +{ + argc = parse_options(argc, argv, options, buildid_list_usage, 0); + setup_pager(); + return __cmd_buildid_list(); +} diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c index 4fb8734a796e..9f810b17c25c 100644 --- a/tools/perf/builtin-help.c +++ b/tools/perf/builtin-help.c @@ -61,8 +61,7 @@ static const char *get_man_viewer_info(const char *name) { struct man_viewer_info_list *viewer; - for (viewer = man_viewer_info_list; viewer; viewer = viewer->next) - { + for (viewer = man_viewer_info_list; viewer; viewer = viewer->next) { if (!strcasecmp(name, viewer->name)) return viewer->info; } @@ -115,7 +114,7 @@ static int check_emacsclient_version(void) return 0; } -static void exec_woman_emacs(const char* path, const char *page) +static void exec_woman_emacs(const char *path, const char *page) { if (!check_emacsclient_version()) { /* This works only with emacsclient version >= 22. */ @@ -129,7 +128,7 @@ static void exec_woman_emacs(const char* path, const char *page) } } -static void exec_man_konqueror(const char* path, const char *page) +static void exec_man_konqueror(const char *path, const char *page) { const char *display = getenv("DISPLAY"); if (display && *display) { @@ -157,7 +156,7 @@ static void exec_man_konqueror(const char* path, const char *page) } } -static void exec_man_man(const char* path, const char *page) +static void exec_man_man(const char *path, const char *page) { if (!path) path = "man"; @@ -180,7 +179,7 @@ static void add_man_viewer(const char *name) while (*p) p = &((*p)->next); - *p = calloc(1, (sizeof(**p) + len + 1)); + *p = zalloc(sizeof(**p) + len + 1); strncpy((*p)->name, name, len); } @@ -195,7 +194,7 @@ static void do_add_man_viewer_info(const char *name, size_t len, const char *value) { - struct man_viewer_info_list *new = calloc(1, sizeof(*new) + len + 1); + struct man_viewer_info_list *new = zalloc(sizeof(*new) + len + 1); strncpy(new->name, name, len); new->info = strdup(value); @@ -364,9 +363,8 @@ static void show_man_page(const char *perf_cmd) setup_man_path(); for (viewer = man_viewer_list; viewer; viewer = viewer->next) - { exec_viewer(viewer->name, page); /* will return when unable */ - } + if (fallback) exec_viewer(fallback, page); exec_viewer("man", page); diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c new file mode 100644 index 000000000000..047fef74bd52 --- /dev/null +++ b/tools/perf/builtin-kmem.c @@ -0,0 +1,807 @@ +#include "builtin.h" +#include "perf.h" + +#include "util/util.h" +#include "util/cache.h" +#include "util/symbol.h" +#include "util/thread.h" +#include "util/header.h" + +#include "util/parse-options.h" +#include "util/trace-event.h" + +#include "util/debug.h" +#include "util/data_map.h" + +#include <linux/rbtree.h> + +struct alloc_stat; +typedef int (*sort_fn_t)(struct alloc_stat *, struct alloc_stat *); + +static char const *input_name = "perf.data"; + +static struct perf_header *header; +static u64 sample_type; + +static int alloc_flag; +static int caller_flag; + +static int alloc_lines = -1; +static int caller_lines = -1; + +static bool raw_ip; + +static char default_sort_order[] = "frag,hit,bytes"; + +static int *cpunode_map; +static int max_cpu_num; + +struct alloc_stat { + u64 call_site; + u64 ptr; + u64 bytes_req; + u64 bytes_alloc; + u32 hit; + u32 pingpong; + + short alloc_cpu; + + struct rb_node node; +}; + +static struct rb_root root_alloc_stat; +static struct rb_root root_alloc_sorted; +static struct rb_root root_caller_stat; +static struct rb_root root_caller_sorted; + +static unsigned long total_requested, total_allocated; +static unsigned long nr_allocs, nr_cross_allocs; + +struct raw_event_sample { + u32 size; + char data[0]; +}; + +#define PATH_SYS_NODE "/sys/devices/system/node" + +static void init_cpunode_map(void) +{ + FILE *fp; + int i; + + fp = fopen("/sys/devices/system/cpu/kernel_max", "r"); + if (!fp) { + max_cpu_num = 4096; + return; + } + + if (fscanf(fp, "%d", &max_cpu_num) < 1) + die("Failed to read 'kernel_max' from sysfs"); + max_cpu_num++; + + cpunode_map = calloc(max_cpu_num, sizeof(int)); + if (!cpunode_map) + die("calloc"); + for (i = 0; i < max_cpu_num; i++) + cpunode_map[i] = -1; + fclose(fp); +} + +static void setup_cpunode_map(void) +{ + struct dirent *dent1, *dent2; + DIR *dir1, *dir2; + unsigned int cpu, mem; + char buf[PATH_MAX]; + + init_cpunode_map(); + + dir1 = opendir(PATH_SYS_NODE); + if (!dir1) + return; + + while (true) { + dent1 = readdir(dir1); + if (!dent1) + break; + + if (sscanf(dent1->d_name, "node%u", &mem) < 1) + continue; + + snprintf(buf, PATH_MAX, "%s/%s", PATH_SYS_NODE, dent1->d_name); + dir2 = opendir(buf); + if (!dir2) + continue; + while (true) { + dent2 = readdir(dir2); + if (!dent2) + break; + if (sscanf(dent2->d_name, "cpu%u", &cpu) < 1) + continue; + cpunode_map[cpu] = mem; + } + } +} + +static void insert_alloc_stat(unsigned long call_site, unsigned long ptr, + int bytes_req, int bytes_alloc, int cpu) +{ + struct rb_node **node = &root_alloc_stat.rb_node; + struct rb_node *parent = NULL; + struct alloc_stat *data = NULL; + + while (*node) { + parent = *node; + data = rb_entry(*node, struct alloc_stat, node); + + if (ptr > data->ptr) + node = &(*node)->rb_right; + else if (ptr < data->ptr) + node = &(*node)->rb_left; + else + break; + } + + if (data && data->ptr == ptr) { + data->hit++; + data->bytes_req += bytes_req; + data->bytes_alloc += bytes_req; + } else { + data = malloc(sizeof(*data)); + if (!data) + die("malloc"); + data->ptr = ptr; + data->pingpong = 0; + data->hit = 1; + data->bytes_req = bytes_req; + data->bytes_alloc = bytes_alloc; + + rb_link_node(&data->node, parent, node); + rb_insert_color(&data->node, &root_alloc_stat); + } + data->call_site = call_site; + data->alloc_cpu = cpu; +} + +static void insert_caller_stat(unsigned long call_site, + int bytes_req, int bytes_alloc) +{ + struct rb_node **node = &root_caller_stat.rb_node; + struct rb_node *parent = NULL; + struct alloc_stat *data = NULL; + + while (*node) { + parent = *node; + data = rb_entry(*node, struct alloc_stat, node); + + if (call_site > data->call_site) + node = &(*node)->rb_right; + else if (call_site < data->call_site) + node = &(*node)->rb_left; + else + break; + } + + if (data && data->call_site == call_site) { + data->hit++; + data->bytes_req += bytes_req; + data->bytes_alloc += bytes_req; + } else { + data = malloc(sizeof(*data)); + if (!data) + die("malloc"); + data->call_site = call_site; + data->pingpong = 0; + data->hit = 1; + data->bytes_req = bytes_req; + data->bytes_alloc = bytes_alloc; + + rb_link_node(&data->node, parent, node); + rb_insert_color(&data->node, &root_caller_stat); + } +} + +static void process_alloc_event(struct raw_event_sample *raw, + struct event *event, + int cpu, + u64 timestamp __used, + struct thread *thread __used, + int node) +{ + unsigned long call_site; + unsigned long ptr; + int bytes_req; + int bytes_alloc; + int node1, node2; + + ptr = raw_field_value(event, "ptr", raw->data); + call_site = raw_field_value(event, "call_site", raw->data); + bytes_req = raw_field_value(event, "bytes_req", raw->data); + bytes_alloc = raw_field_value(event, "bytes_alloc", raw->data); + + insert_alloc_stat(call_site, ptr, bytes_req, bytes_alloc, cpu); + insert_caller_stat(call_site, bytes_req, bytes_alloc); + + total_requested += bytes_req; + total_allocated += bytes_alloc; + + if (node) { + node1 = cpunode_map[cpu]; + node2 = raw_field_value(event, "node", raw->data); + if (node1 != node2) + nr_cross_allocs++; + } + nr_allocs++; +} + +static int ptr_cmp(struct alloc_stat *, struct alloc_stat *); +static int callsite_cmp(struct alloc_stat *, struct alloc_stat *); + +static struct alloc_stat *search_alloc_stat(unsigned long ptr, + unsigned long call_site, + struct rb_root *root, + sort_fn_t sort_fn) +{ + struct rb_node *node = root->rb_node; + struct alloc_stat key = { .ptr = ptr, .call_site = call_site }; + + while (node) { + struct alloc_stat *data; + int cmp; + + data = rb_entry(node, struct alloc_stat, node); + + cmp = sort_fn(&key, data); + if (cmp < 0) + node = node->rb_left; + else if (cmp > 0) + node = node->rb_right; + else + return data; + } + return NULL; +} + +static void process_free_event(struct raw_event_sample *raw, + struct event *event, + int cpu, + u64 timestamp __used, + struct thread *thread __used) +{ + unsigned long ptr; + struct alloc_stat *s_alloc, *s_caller; + + ptr = raw_field_value(event, "ptr", raw->data); + + s_alloc = search_alloc_stat(ptr, 0, &root_alloc_stat, ptr_cmp); + if (!s_alloc) + return; + + if (cpu != s_alloc->alloc_cpu) { + s_alloc->pingpong++; + + s_caller = search_alloc_stat(0, s_alloc->call_site, + &root_caller_stat, callsite_cmp); + assert(s_caller); + s_caller->pingpong++; + } + s_alloc->alloc_cpu = -1; +} + +static void +process_raw_event(event_t *raw_event __used, void *more_data, + int cpu, u64 timestamp, struct thread *thread) +{ + struct raw_event_sample *raw = more_data; + struct event *event; + int type; + + type = trace_parse_common_type(raw->data); + event = trace_find_event(type); + + if (!strcmp(event->name, "kmalloc") || + !strcmp(event->name, "kmem_cache_alloc")) { + process_alloc_event(raw, event, cpu, timestamp, thread, 0); + return; + } + + if (!strcmp(event->name, "kmalloc_node") || + !strcmp(event->name, "kmem_cache_alloc_node")) { + process_alloc_event(raw, event, cpu, timestamp, thread, 1); + return; + } + + if (!strcmp(event->name, "kfree") || + !strcmp(event->name, "kmem_cache_free")) { + process_free_event(raw, event, cpu, timestamp, thread); + return; + } +} + +static int process_sample_event(event_t *event) +{ + u64 ip = event->ip.ip; + u64 timestamp = -1; + u32 cpu = -1; + u64 period = 1; + void *more_data = event->ip.__more_data; + struct thread *thread = threads__findnew(event->ip.pid); + + if (sample_type & PERF_SAMPLE_TIME) { + timestamp = *(u64 *)more_data; + more_data += sizeof(u64); + } + + if (sample_type & PERF_SAMPLE_CPU) { + cpu = *(u32 *)more_data; + more_data += sizeof(u32); + more_data += sizeof(u32); /* reserved */ + } + + if (sample_type & PERF_SAMPLE_PERIOD) { + period = *(u64 *)more_data; + more_data += sizeof(u64); + } + + dump_printf("(IP, %d): %d/%d: %p period: %Ld\n", + event->header.misc, + event->ip.pid, event->ip.tid, + (void *)(long)ip, + (long long)period); + + if (thread == NULL) { + pr_debug("problem processing %d event, skipping it.\n", + event->header.type); + return -1; + } + + dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid); + + process_raw_event(event, more_data, cpu, timestamp, thread); + + return 0; +} + +static int sample_type_check(u64 type) +{ + sample_type = type; + + if (!(sample_type & PERF_SAMPLE_RAW)) { + fprintf(stderr, + "No trace sample to read. Did you call perf record " + "without -R?"); + return -1; + } + + return 0; +} + +static struct perf_file_handler file_handler = { + .process_sample_event = process_sample_event, + .process_comm_event = event__process_comm, + .sample_type_check = sample_type_check, +}; + +static int read_events(void) +{ + register_idle_thread(); + register_perf_file_handler(&file_handler); + + return mmap_dispatch_perf_file(&header, input_name, 0, 0, + &event__cwdlen, &event__cwd); +} + +static double fragmentation(unsigned long n_req, unsigned long n_alloc) +{ + if (n_alloc == 0) + return 0.0; + else + return 100.0 - (100.0 * n_req / n_alloc); +} + +static void __print_result(struct rb_root *root, int n_lines, int is_caller) +{ + struct rb_node *next; + + printf("%.102s\n", graph_dotted_line); + printf(" %-34s |", is_caller ? "Callsite": "Alloc Ptr"); + printf(" Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag\n"); + printf("%.102s\n", graph_dotted_line); + + next = rb_first(root); + + while (next && n_lines--) { + struct alloc_stat *data = rb_entry(next, struct alloc_stat, + node); + struct symbol *sym = NULL; + char buf[BUFSIZ]; + u64 addr; + + if (is_caller) { + addr = data->call_site; + if (!raw_ip) + sym = thread__find_function(kthread, addr, NULL); + } else + addr = data->ptr; + + if (sym != NULL) + snprintf(buf, sizeof(buf), "%s+%Lx", sym->name, + addr - sym->start); + else + snprintf(buf, sizeof(buf), "%#Lx", addr); + printf(" %-34s |", buf); + + printf(" %9llu/%-5lu | %9llu/%-5lu | %6lu | %8lu | %6.3f%%\n", + (unsigned long long)data->bytes_alloc, + (unsigned long)data->bytes_alloc / data->hit, + (unsigned long long)data->bytes_req, + (unsigned long)data->bytes_req / data->hit, + (unsigned long)data->hit, + (unsigned long)data->pingpong, + fragmentation(data->bytes_req, data->bytes_alloc)); + + next = rb_next(next); + } + + if (n_lines == -1) + printf(" ... | ... | ... | ... | ... | ... \n"); + + printf("%.102s\n", graph_dotted_line); +} + +static void print_summary(void) +{ + printf("\nSUMMARY\n=======\n"); + printf("Total bytes requested: %lu\n", total_requested); + printf("Total bytes allocated: %lu\n", total_allocated); + printf("Total bytes wasted on internal fragmentation: %lu\n", + total_allocated - total_requested); + printf("Internal fragmentation: %f%%\n", + fragmentation(total_requested, total_allocated)); + printf("Cross CPU allocations: %lu/%lu\n", nr_cross_allocs, nr_allocs); +} + +static void print_result(void) +{ + if (caller_flag) + __print_result(&root_caller_sorted, caller_lines, 1); + if (alloc_flag) + __print_result(&root_alloc_sorted, alloc_lines, 0); + print_summary(); +} + +struct sort_dimension { + const char name[20]; + sort_fn_t cmp; + struct list_head list; +}; + +static LIST_HEAD(caller_sort); +static LIST_HEAD(alloc_sort); + +static void sort_insert(struct rb_root *root, struct alloc_stat *data, + struct list_head *sort_list) +{ + struct rb_node **new = &(root->rb_node); + struct rb_node *parent = NULL; + struct sort_dimension *sort; + + while (*new) { + struct alloc_stat *this; + int cmp = 0; + + this = rb_entry(*new, struct alloc_stat, node); + parent = *new; + + list_for_each_entry(sort, sort_list, list) { + cmp = sort->cmp(data, this); + if (cmp) + break; + } + + if (cmp > 0) + new = &((*new)->rb_left); + else + new = &((*new)->rb_right); + } + + rb_link_node(&data->node, parent, new); + rb_insert_color(&data->node, root); +} + +static void __sort_result(struct rb_root *root, struct rb_root *root_sorted, + struct list_head *sort_list) +{ + struct rb_node *node; + struct alloc_stat *data; + + for (;;) { + node = rb_first(root); + if (!node) + break; + + rb_erase(node, root); + data = rb_entry(node, struct alloc_stat, node); + sort_insert(root_sorted, data, sort_list); + } +} + +static void sort_result(void) +{ + __sort_result(&root_alloc_stat, &root_alloc_sorted, &alloc_sort); + __sort_result(&root_caller_stat, &root_caller_sorted, &caller_sort); +} + +static int __cmd_kmem(void) +{ + setup_pager(); + read_events(); + sort_result(); + print_result(); + + return 0; +} + +static const char * const kmem_usage[] = { + "perf kmem [<options>] {record}", + NULL +}; + +static int ptr_cmp(struct alloc_stat *l, struct alloc_stat *r) +{ + if (l->ptr < r->ptr) + return -1; + else if (l->ptr > r->ptr) + return 1; + return 0; +} + +static struct sort_dimension ptr_sort_dimension = { + .name = "ptr", + .cmp = ptr_cmp, +}; + +static int callsite_cmp(struct alloc_stat *l, struct alloc_stat *r) +{ + if (l->call_site < r->call_site) + return -1; + else if (l->call_site > r->call_site) + return 1; + return 0; +} + +static struct sort_dimension callsite_sort_dimension = { + .name = "callsite", + .cmp = callsite_cmp, +}; + +static int hit_cmp(struct alloc_stat *l, struct alloc_stat *r) +{ + if (l->hit < r->hit) + return -1; + else if (l->hit > r->hit) + return 1; + return 0; +} + +static struct sort_dimension hit_sort_dimension = { + .name = "hit", + .cmp = hit_cmp, +}; + +static int bytes_cmp(struct alloc_stat *l, struct alloc_stat *r) +{ + if (l->bytes_alloc < r->bytes_alloc) + return -1; + else if (l->bytes_alloc > r->bytes_alloc) + return 1; + return 0; +} + +static struct sort_dimension bytes_sort_dimension = { + .name = "bytes", + .cmp = bytes_cmp, +}; + +static int frag_cmp(struct alloc_stat *l, struct alloc_stat *r) +{ + double x, y; + + x = fragmentation(l->bytes_req, l->bytes_alloc); + y = fragmentation(r->bytes_req, r->bytes_alloc); + + if (x < y) + return -1; + else if (x > y) + return 1; + return 0; +} + +static struct sort_dimension frag_sort_dimension = { + .name = "frag", + .cmp = frag_cmp, +}; + +static int pingpong_cmp(struct alloc_stat *l, struct alloc_stat *r) +{ + if (l->pingpong < r->pingpong) + return -1; + else if (l->pingpong > r->pingpong) + return 1; + return 0; +} + +static struct sort_dimension pingpong_sort_dimension = { + .name = "pingpong", + .cmp = pingpong_cmp, +}; + +static struct sort_dimension *avail_sorts[] = { + &ptr_sort_dimension, + &callsite_sort_dimension, + &hit_sort_dimension, + &bytes_sort_dimension, + &frag_sort_dimension, + &pingpong_sort_dimension, +}; + +#define NUM_AVAIL_SORTS \ + (int)(sizeof(avail_sorts) / sizeof(struct sort_dimension *)) + +static int sort_dimension__add(const char *tok, struct list_head *list) +{ + struct sort_dimension *sort; + int i; + + for (i = 0; i < NUM_AVAIL_SORTS; i++) { + if (!strcmp(avail_sorts[i]->name, tok)) { + sort = malloc(sizeof(*sort)); + if (!sort) + die("malloc"); + memcpy(sort, avail_sorts[i], sizeof(*sort)); + list_add_tail(&sort->list, list); + return 0; + } + } + + return -1; +} + +static int setup_sorting(struct list_head *sort_list, const char *arg) +{ + char *tok; + char *str = strdup(arg); + + if (!str) + die("strdup"); + + while (true) { + tok = strsep(&str, ","); + if (!tok) + break; + if (sort_dimension__add(tok, sort_list) < 0) { + error("Unknown --sort key: '%s'", tok); + return -1; + } + } + + free(str); + return 0; +} + +static int parse_sort_opt(const struct option *opt __used, + const char *arg, int unset __used) +{ + if (!arg) + return -1; + + if (caller_flag > alloc_flag) + return setup_sorting(&caller_sort, arg); + else + return setup_sorting(&alloc_sort, arg); + + return 0; +} + +static int parse_stat_opt(const struct option *opt __used, + const char *arg, int unset __used) +{ + if (!arg) + return -1; + + if (strcmp(arg, "alloc") == 0) + alloc_flag = (caller_flag + 1); + else if (strcmp(arg, "caller") == 0) + caller_flag = (alloc_flag + 1); + else + return -1; + return 0; +} + +static int parse_line_opt(const struct option *opt __used, + const char *arg, int unset __used) +{ + int lines; + + if (!arg) + return -1; + + lines = strtoul(arg, NULL, 10); + + if (caller_flag > alloc_flag) + caller_lines = lines; + else + alloc_lines = lines; + + return 0; +} + +static const struct option kmem_options[] = { + OPT_STRING('i', "input", &input_name, "file", + "input file name"), + OPT_CALLBACK(0, "stat", NULL, "<alloc>|<caller>", + "stat selector, Pass 'alloc' or 'caller'.", + parse_stat_opt), + OPT_CALLBACK('s', "sort", NULL, "key[,key2...]", + "sort by keys: ptr, call_site, bytes, hit, pingpong, frag", + parse_sort_opt), + OPT_CALLBACK('l', "line", NULL, "num", + "show n lins", + parse_line_opt), + OPT_BOOLEAN(0, "raw-ip", &raw_ip, "show raw ip instead of symbol"), + OPT_END() +}; + +static const char *record_args[] = { + "record", + "-a", + "-R", + "-M", + "-f", + "-c", "1", + "-e", "kmem:kmalloc", + "-e", "kmem:kmalloc_node", + "-e", "kmem:kfree", + "-e", "kmem:kmem_cache_alloc", + "-e", "kmem:kmem_cache_alloc_node", + "-e", "kmem:kmem_cache_free", +}; + +static int __cmd_record(int argc, const char **argv) +{ + unsigned int rec_argc, i, j; + const char **rec_argv; + + rec_argc = ARRAY_SIZE(record_args) + argc - 1; + rec_argv = calloc(rec_argc + 1, sizeof(char *)); + + for (i = 0; i < ARRAY_SIZE(record_args); i++) + rec_argv[i] = strdup(record_args[i]); + + for (j = 1; j < (unsigned int)argc; j++, i++) + rec_argv[i] = argv[j]; + + return cmd_record(i, rec_argv, NULL); +} + +int cmd_kmem(int argc, const char **argv, const char *prefix __used) +{ + symbol__init(0); + + argc = parse_options(argc, argv, kmem_options, kmem_usage, 0); + + if (argc && !strncmp(argv[0], "rec", 3)) + return __cmd_record(argc, argv); + else if (argc) + usage_with_options(kmem_usage, kmem_options); + + if (list_empty(&caller_sort)) + setup_sorting(&caller_sort, default_sort_order); + if (list_empty(&alloc_sort)) + setup_sorting(&alloc_sort, default_sort_order); + + setup_cpunode_map(); + + return __cmd_kmem(); +} + diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c new file mode 100644 index 000000000000..a58e11b7ea80 --- /dev/null +++ b/tools/perf/builtin-probe.c @@ -0,0 +1,242 @@ +/* + * builtin-probe.c + * + * Builtin probe command: Set up probe events by C expression + * + * Written by Masami Hiramatsu <mhiramat@redhat.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + */ +#define _GNU_SOURCE +#include <sys/utsname.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <errno.h> +#include <stdio.h> +#include <unistd.h> +#include <stdlib.h> +#include <string.h> + +#undef _GNU_SOURCE +#include "perf.h" +#include "builtin.h" +#include "util/util.h" +#include "util/event.h" +#include "util/debug.h" +#include "util/parse-options.h" +#include "util/parse-events.h" /* For debugfs_path */ +#include "util/probe-finder.h" +#include "util/probe-event.h" + +/* Default vmlinux search paths */ +#define NR_SEARCH_PATH 3 +const char *default_search_path[NR_SEARCH_PATH] = { +"/lib/modules/%s/build/vmlinux", /* Custom build kernel */ +"/usr/lib/debug/lib/modules/%s/vmlinux", /* Red Hat debuginfo */ +"/boot/vmlinux-debug-%s", /* Ubuntu */ +}; + +#define MAX_PATH_LEN 256 +#define MAX_PROBES 128 + +/* Session management structure */ +static struct { + char *vmlinux; + char *release; + int need_dwarf; + int nr_probe; + struct probe_point probes[MAX_PROBES]; +} session; + +static bool listing; + +/* Parse an event definition. Note that any error must die. */ +static void parse_probe_event(const char *str) +{ + struct probe_point *pp = &session.probes[session.nr_probe]; + + pr_debug("probe-definition(%d): %s\n", session.nr_probe, str); + if (++session.nr_probe == MAX_PROBES) + die("Too many probes (> %d) are specified.", MAX_PROBES); + + /* Parse perf-probe event into probe_point */ + session.need_dwarf = parse_perf_probe_event(str, pp); + + pr_debug("%d arguments\n", pp->nr_args); +} + +static int opt_add_probe_event(const struct option *opt __used, + const char *str, int unset __used) +{ + if (str) + parse_probe_event(str); + return 0; +} + +#ifndef NO_LIBDWARF +static int open_default_vmlinux(void) +{ + struct utsname uts; + char fname[MAX_PATH_LEN]; + int fd, ret, i; + + ret = uname(&uts); + if (ret) { + pr_debug("uname() failed.\n"); + return -errno; + } + session.release = uts.release; + for (i = 0; i < NR_SEARCH_PATH; i++) { + ret = snprintf(fname, MAX_PATH_LEN, + default_search_path[i], session.release); + if (ret >= MAX_PATH_LEN || ret < 0) { + pr_debug("Filename(%d,%s) is too long.\n", i, + uts.release); + errno = E2BIG; + return -E2BIG; + } + pr_debug("try to open %s\n", fname); + fd = open(fname, O_RDONLY); + if (fd >= 0) + break; + } + return fd; +} +#endif + +static const char * const probe_usage[] = { + "perf probe [<options>] 'PROBEDEF' ['PROBEDEF' ...]", + "perf probe [<options>] --add 'PROBEDEF' [--add 'PROBEDEF' ...]", + "perf probe --list", + NULL +}; + +static const struct option options[] = { + OPT_BOOLEAN('v', "verbose", &verbose, + "be more verbose (show parsed arguments, etc)"), +#ifndef NO_LIBDWARF + OPT_STRING('k', "vmlinux", &session.vmlinux, "file", + "vmlinux/module pathname"), +#endif + OPT_BOOLEAN('l', "list", &listing, "list up current probes"), + OPT_CALLBACK('a', "add", NULL, +#ifdef NO_LIBDWARF + "FUNC[+OFFS|%return] [ARG ...]", +#else + "FUNC[+OFFS|%return|:RLN][@SRC]|SRC:ALN [ARG ...]", +#endif + "probe point definition, where\n" + "\t\tGRP:\tGroup name (optional)\n" + "\t\tNAME:\tEvent name\n" + "\t\tFUNC:\tFunction name\n" + "\t\tOFFS:\tOffset from function entry (in byte)\n" + "\t\t%return:\tPut the probe at function return\n" +#ifdef NO_LIBDWARF + "\t\tARG:\tProbe argument (only \n" +#else + "\t\tSRC:\tSource code path\n" + "\t\tRLN:\tRelative line number from function entry.\n" + "\t\tALN:\tAbsolute line number in file.\n" + "\t\tARG:\tProbe argument (local variable name or\n" +#endif + "\t\t\tkprobe-tracer argument format.)\n", + opt_add_probe_event), + OPT_END() +}; + +int cmd_probe(int argc, const char **argv, const char *prefix __used) +{ + int i, j, ret; +#ifndef NO_LIBDWARF + int fd; +#endif + struct probe_point *pp; + + argc = parse_options(argc, argv, options, probe_usage, + PARSE_OPT_STOP_AT_NON_OPTION); + for (i = 0; i < argc; i++) + parse_probe_event(argv[i]); + + if ((session.nr_probe == 0 && !listing) || + (session.nr_probe != 0 && listing)) + usage_with_options(probe_usage, options); + + if (listing) { + show_perf_probe_events(); + return 0; + } + + if (session.need_dwarf) +#ifdef NO_LIBDWARF + die("Debuginfo-analysis is not supported"); +#else /* !NO_LIBDWARF */ + pr_debug("Some probes require debuginfo.\n"); + + if (session.vmlinux) + fd = open(session.vmlinux, O_RDONLY); + else + fd = open_default_vmlinux(); + if (fd < 0) { + if (session.need_dwarf) + die("Could not open vmlinux/module file."); + + pr_warning("Could not open vmlinux/module file." + " Try to use symbols.\n"); + goto end_dwarf; + } + + /* Searching probe points */ + for (j = 0; j < session.nr_probe; j++) { + pp = &session.probes[j]; + if (pp->found) + continue; + + lseek(fd, SEEK_SET, 0); + ret = find_probepoint(fd, pp); + if (ret < 0) { + if (session.need_dwarf) + die("Could not analyze debuginfo."); + + pr_warning("An error occurred in debuginfo analysis. Try to use symbols.\n"); + break; + } + if (ret == 0) /* No error but failed to find probe point. */ + die("No probe point found."); + } + close(fd); + +end_dwarf: +#endif /* !NO_LIBDWARF */ + + /* Synthesize probes without dwarf */ + for (j = 0; j < session.nr_probe; j++) { + pp = &session.probes[j]; + if (pp->found) /* This probe is already found. */ + continue; + + ret = synthesize_trace_kprobe_event(pp); + if (ret == -E2BIG) + die("probe point definition becomes too long."); + else if (ret < 0) + die("Failed to synthesize a probe point."); + } + + /* Settng up probe points */ + add_trace_kprobe_events(session.probes, session.nr_probe); + return 0; +} + diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index a4be453fc8a9..0e519c667e3a 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -17,55 +17,52 @@ #include "util/header.h" #include "util/event.h" #include "util/debug.h" -#include "util/trace-event.h" +#include "util/symbol.h" #include <unistd.h> #include <sched.h> -#define ALIGN(x, a) __ALIGN_MASK(x, (typeof(x))(a)-1) -#define __ALIGN_MASK(x, mask) (((x)+(mask))&~(mask)) - static int fd[MAX_NR_CPUS][MAX_COUNTERS]; -static long default_interval = 100000; +static long default_interval = 0; -static int nr_cpus = 0; +static int nr_cpus = 0; static unsigned int page_size; -static unsigned int mmap_pages = 128; -static int freq = 0; +static unsigned int mmap_pages = 128; +static int freq = 1000; static int output; static const char *output_name = "perf.data"; -static int group = 0; -static unsigned int realtime_prio = 0; -static int raw_samples = 0; -static int system_wide = 0; -static int profile_cpu = -1; -static pid_t target_pid = -1; -static pid_t child_pid = -1; -static int inherit = 1; -static int force = 0; -static int append_file = 0; -static int call_graph = 0; -static int inherit_stat = 0; -static int no_samples = 0; -static int sample_address = 0; -static int multiplex = 0; -static int multiplex_fd = -1; - -static long samples; +static int group = 0; +static unsigned int realtime_prio = 0; +static int raw_samples = 0; +static int system_wide = 0; +static int profile_cpu = -1; +static pid_t target_pid = -1; +static pid_t child_pid = -1; +static int inherit = 1; +static int force = 0; +static int append_file = 0; +static int call_graph = 0; +static int inherit_stat = 0; +static int no_samples = 0; +static int sample_address = 0; +static int multiplex = 0; +static int multiplex_fd = -1; + +static long samples = 0; static struct timeval last_read; static struct timeval this_read; -static u64 bytes_written; +static u64 bytes_written = 0; static struct pollfd event_array[MAX_NR_CPUS * MAX_COUNTERS]; -static int nr_poll; -static int nr_cpu; +static int nr_poll = 0; +static int nr_cpu = 0; -static int file_new = 1; +static int file_new = 1; -struct perf_header *header; +struct perf_header *header = NULL; struct mmap_data { int counter; @@ -113,6 +110,24 @@ static void write_output(void *buf, size_t size) } } +static void write_event(event_t *buf, size_t size) +{ + /* + * Add it to the list of DSOs, so that when we finish this + * record session we can pick the available build-ids. + */ + if (buf->header.type == PERF_RECORD_MMAP) + dsos__findnew(buf->mmap.filename); + + write_output(buf, size); +} + +static int process_synthesized_event(event_t *event) +{ + write_event(event, event->header.size); + return 0; +} + static void mmap_read(struct mmap_data *md) { unsigned int head = mmap_read_head(md); @@ -161,14 +176,14 @@ static void mmap_read(struct mmap_data *md) size = md->mask + 1 - (old & md->mask); old += size; - write_output(buf, size); + write_event(buf, size); } buf = &data[old & md->mask]; size = head - old; old += size; - write_output(buf, size); + write_event(buf, size); md->prev = old; mmap_write_tail(md, old); @@ -195,168 +210,6 @@ static void sig_atexit(void) kill(getpid(), signr); } -static pid_t pid_synthesize_comm_event(pid_t pid, int full) -{ - struct comm_event comm_ev; - char filename[PATH_MAX]; - char bf[BUFSIZ]; - FILE *fp; - size_t size = 0; - DIR *tasks; - struct dirent dirent, *next; - pid_t tgid = 0; - - snprintf(filename, sizeof(filename), "/proc/%d/status", pid); - - fp = fopen(filename, "r"); - if (fp == NULL) { - /* - * We raced with a task exiting - just return: - */ - if (verbose) - fprintf(stderr, "couldn't open %s\n", filename); - return 0; - } - - memset(&comm_ev, 0, sizeof(comm_ev)); - while (!comm_ev.comm[0] || !comm_ev.pid) { - if (fgets(bf, sizeof(bf), fp) == NULL) - goto out_failure; - - if (memcmp(bf, "Name:", 5) == 0) { - char *name = bf + 5; - while (*name && isspace(*name)) - ++name; - size = strlen(name) - 1; - memcpy(comm_ev.comm, name, size++); - } else if (memcmp(bf, "Tgid:", 5) == 0) { - char *tgids = bf + 5; - while (*tgids && isspace(*tgids)) - ++tgids; - tgid = comm_ev.pid = atoi(tgids); - } - } - - comm_ev.header.type = PERF_RECORD_COMM; - size = ALIGN(size, sizeof(u64)); - comm_ev.header.size = sizeof(comm_ev) - (sizeof(comm_ev.comm) - size); - - if (!full) { - comm_ev.tid = pid; - - write_output(&comm_ev, comm_ev.header.size); - goto out_fclose; - } - - snprintf(filename, sizeof(filename), "/proc/%d/task", pid); - - tasks = opendir(filename); - while (!readdir_r(tasks, &dirent, &next) && next) { - char *end; - pid = strtol(dirent.d_name, &end, 10); - if (*end) - continue; - - comm_ev.tid = pid; - - write_output(&comm_ev, comm_ev.header.size); - } - closedir(tasks); - -out_fclose: - fclose(fp); - return tgid; - -out_failure: - fprintf(stderr, "couldn't get COMM and pgid, malformed %s\n", - filename); - exit(EXIT_FAILURE); -} - -static void pid_synthesize_mmap_samples(pid_t pid, pid_t tgid) -{ - char filename[PATH_MAX]; - FILE *fp; - - snprintf(filename, sizeof(filename), "/proc/%d/maps", pid); - - fp = fopen(filename, "r"); - if (fp == NULL) { - /* - * We raced with a task exiting - just return: - */ - if (verbose) - fprintf(stderr, "couldn't open %s\n", filename); - return; - } - while (1) { - char bf[BUFSIZ], *pbf = bf; - struct mmap_event mmap_ev = { - .header = { .type = PERF_RECORD_MMAP }, - }; - int n; - size_t size; - if (fgets(bf, sizeof(bf), fp) == NULL) - break; - - /* 00400000-0040c000 r-xp 00000000 fd:01 41038 /bin/cat */ - n = hex2u64(pbf, &mmap_ev.start); - if (n < 0) - continue; - pbf += n + 1; - n = hex2u64(pbf, &mmap_ev.len); - if (n < 0) - continue; - pbf += n + 3; - if (*pbf == 'x') { /* vm_exec */ - char *execname = strchr(bf, '/'); - - /* Catch VDSO */ - if (execname == NULL) - execname = strstr(bf, "[vdso]"); - - if (execname == NULL) - continue; - - size = strlen(execname); - execname[size - 1] = '\0'; /* Remove \n */ - memcpy(mmap_ev.filename, execname, size); - size = ALIGN(size, sizeof(u64)); - mmap_ev.len -= mmap_ev.start; - mmap_ev.header.size = (sizeof(mmap_ev) - - (sizeof(mmap_ev.filename) - size)); - mmap_ev.pid = tgid; - mmap_ev.tid = pid; - - write_output(&mmap_ev, mmap_ev.header.size); - } - } - - fclose(fp); -} - -static void synthesize_all(void) -{ - DIR *proc; - struct dirent dirent, *next; - - proc = opendir("/proc"); - - while (!readdir_r(proc, &dirent, &next) && next) { - char *end; - pid_t pid, tgid; - - pid = strtol(dirent.d_name, &end, 10); - if (*end) /* only interested in proper numerical dirents */ - continue; - - tgid = pid_synthesize_comm_event(pid, 1); - pid_synthesize_mmap_samples(pid, tgid); - } - - closedir(proc); -} - static int group_fd; static struct perf_header_attr *get_header_attr(struct perf_event_attr *a, int nr) @@ -367,7 +220,11 @@ static struct perf_header_attr *get_header_attr(struct perf_event_attr *a, int n h_attr = header->attr[nr]; } else { h_attr = perf_header_attr__new(a); - perf_header__add_attr(header, h_attr); + if (h_attr != NULL) + if (perf_header__add_attr(header, h_attr) < 0) { + perf_header_attr__delete(h_attr); + h_attr = NULL; + } } return h_attr; @@ -375,9 +232,11 @@ static struct perf_header_attr *get_header_attr(struct perf_event_attr *a, int n static void create_counter(int counter, int cpu, pid_t pid) { + char *filter = filters[counter]; struct perf_event_attr *attr = attrs + counter; struct perf_header_attr *h_attr; int track = !counter; /* only the first counter needs these */ + int ret; struct { u64 count; u64 time_enabled; @@ -448,11 +307,19 @@ try_again: printf("\n"); error("perfcounter syscall returned with %d (%s)\n", fd[nr_cpu][counter], strerror(err)); + +#if defined(__i386__) || defined(__x86_64__) + if (attr->type == PERF_TYPE_HARDWARE && err == EOPNOTSUPP) + die("No hardware sampling interrupt available. No APIC? If so then you can boot the kernel with the \"lapic\" boot parameter to force-enable it.\n"); +#endif + die("No CONFIG_PERF_EVENTS=y kernel support configured?\n"); exit(-1); } h_attr = get_header_attr(attr, counter); + if (h_attr == NULL) + die("nomem\n"); if (!file_new) { if (memcmp(&h_attr->attr, attr, sizeof(*attr))) { @@ -466,7 +333,10 @@ try_again: exit(-1); } - perf_header_attr__add_id(h_attr, read_data.id); + if (perf_header_attr__add_id(h_attr, read_data.id) < 0) { + pr_warning("Not enough memory to add id\n"); + exit(-1); + } assert(fd[nr_cpu][counter] >= 0); fcntl(fd[nr_cpu][counter], F_SETFL, O_NONBLOCK); @@ -480,7 +350,6 @@ try_again: multiplex_fd = fd[nr_cpu][counter]; if (multiplex && fd[nr_cpu][counter] != multiplex_fd) { - int ret; ret = ioctl(fd[nr_cpu][counter], PERF_EVENT_IOC_SET_OUTPUT, multiplex_fd); assert(ret != -1); @@ -500,6 +369,16 @@ try_again: } } + if (filter != NULL) { + ret = ioctl(fd[nr_cpu][counter], + PERF_EVENT_IOC_SET_FILTER, filter); + if (ret) { + error("failed to set filter with %d (%s)\n", errno, + strerror(errno)); + exit(-1); + } + } + ioctl(fd[nr_cpu][counter], PERF_EVENT_IOC_ENABLE); } @@ -518,7 +397,7 @@ static void atexit_header(void) { header->data_size += bytes_written; - perf_header__write(header, output); + perf_header__write(header, output, true); } static int __cmd_record(int argc, const char **argv) @@ -527,7 +406,7 @@ static int __cmd_record(int argc, const char **argv) struct stat st; pid_t pid = 0; int flags; - int ret; + int err; unsigned long waking = 0; page_size = sysconf(_SC_PAGE_SIZE); @@ -561,22 +440,29 @@ static int __cmd_record(int argc, const char **argv) exit(-1); } - if (!file_new) - header = perf_header__read(output); - else - header = perf_header__new(); + header = perf_header__new(); + if (header == NULL) { + pr_err("Not enough memory for reading perf file header\n"); + return -1; + } + if (!file_new) { + err = perf_header__read(header, output); + if (err < 0) + return err; + } if (raw_samples) { - read_tracing_data(attrs, nr_counters); + perf_header__set_feat(header, HEADER_TRACE_INFO); } else { for (i = 0; i < nr_counters; i++) { if (attrs[i].sample_type & PERF_SAMPLE_RAW) { - read_tracing_data(attrs, nr_counters); + perf_header__set_feat(header, HEADER_TRACE_INFO); break; } } } + atexit(atexit_header); if (!system_wide) { @@ -594,25 +480,36 @@ static int __cmd_record(int argc, const char **argv) } } - if (file_new) - perf_header__write(header, output); + if (file_new) { + err = perf_header__write(header, output, false); + if (err < 0) + return err; + } - if (!system_wide) { - pid_t tgid = pid_synthesize_comm_event(pid, 0); - pid_synthesize_mmap_samples(pid, tgid); - } else - synthesize_all(); + if (!system_wide) + event__synthesize_thread(pid, process_synthesized_event); + else + event__synthesize_threads(process_synthesized_event); if (target_pid == -1 && argc) { pid = fork(); if (pid < 0) - perror("failed to fork"); + die("failed to fork"); if (!pid) { if (execvp(argv[0], (char **)argv)) { perror(argv[0]); exit(-1); } + } else { + /* + * Wait a bit for the execv'ed child to appear + * and be updated in /proc + * FIXME: Do you know a less heuristical solution? + */ + usleep(1000); + event__synthesize_thread(pid, + process_synthesized_event); } child_pid = pid; @@ -623,7 +520,7 @@ static int __cmd_record(int argc, const char **argv) param.sched_priority = realtime_prio; if (sched_setscheduler(0, SCHED_FIFO, ¶m)) { - printf("Could not set realtime priority.\n"); + pr_err("Could not set realtime priority.\n"); exit(-1); } } @@ -641,7 +538,7 @@ static int __cmd_record(int argc, const char **argv) if (hits == samples) { if (done) break; - ret = poll(event_array, nr_poll, -1); + err = poll(event_array, nr_poll, -1); waking++; } @@ -677,6 +574,8 @@ static const struct option options[] = { OPT_CALLBACK('e', "event", NULL, "event", "event selector. use 'perf list' to list available events", parse_events), + OPT_CALLBACK(0, "filter", NULL, "filter", + "event filter", parse_filter), OPT_INTEGER('p', "pid", &target_pid, "record events on existing pid"), OPT_INTEGER('r', "realtime", &realtime_prio, @@ -720,6 +619,8 @@ int cmd_record(int argc, const char **argv, const char *prefix __used) { int counter; + symbol__init(0); + argc = parse_options(argc, argv, options, record_usage, PARSE_OPT_STOP_AT_NON_OPTION); if (!argc && target_pid == -1 && !system_wide) @@ -731,6 +632,18 @@ int cmd_record(int argc, const char **argv, const char *prefix __used) attrs[0].config = PERF_COUNT_HW_CPU_CYCLES; } + /* + * User specified count overrides default frequency. + */ + if (default_interval) + freq = 0; + else if (freq) { + default_interval = freq; + } else { + fprintf(stderr, "frequency and count are zero, aborting\n"); + exit(EXIT_FAILURE); + } + for (counter = 0; counter < nr_counters; counter++) { if (attrs[counter].sample_period) continue; diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 19669c20088e..383c4ab4f9af 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -26,20 +26,18 @@ #include "util/parse-options.h" #include "util/parse-events.h" +#include "util/data_map.h" #include "util/thread.h" +#include "util/sort.h" +#include "util/hist.h" static char const *input_name = "perf.data"; -static char default_sort_order[] = "comm,dso,symbol"; -static char *sort_order = default_sort_order; static char *dso_list_str, *comm_list_str, *sym_list_str, *col_width_list_str; static struct strlist *dso_list, *comm_list, *sym_list; -static char *field_sep; static int force; -static int input; -static int show_mask = SHOW_KERNEL | SHOW_USER | SHOW_HV; static int full_paths; static int show_nr_samples; @@ -50,374 +48,38 @@ static struct perf_read_values show_threads_values; static char default_pretty_printing_style[] = "normal"; static char *pretty_printing_style = default_pretty_printing_style; -static unsigned long page_size; -static unsigned long mmap_window = 32; - -static char default_parent_pattern[] = "^sys_|^do_page_fault"; -static char *parent_pattern = default_parent_pattern; -static regex_t parent_regex; - static int exclude_other = 1; static char callchain_default_opt[] = "fractal,0.5"; -static int callchain; - -static char __cwd[PATH_MAX]; -static char *cwd = __cwd; -static int cwdlen; - -static struct rb_root threads; -static struct thread *last_match; - static struct perf_header *header; -static -struct callchain_param callchain_param = { - .mode = CHAIN_GRAPH_REL, - .min_percent = 0.5 -}; - static u64 sample_type; -static int repsep_fprintf(FILE *fp, const char *fmt, ...) -{ - int n; - va_list ap; - - va_start(ap, fmt); - if (!field_sep) - n = vfprintf(fp, fmt, ap); - else { - char *bf = NULL; - n = vasprintf(&bf, fmt, ap); - if (n > 0) { - char *sep = bf; - - while (1) { - sep = strchr(sep, *field_sep); - if (sep == NULL) - break; - *sep = '.'; - } - } - fputs(bf, fp); - free(bf); - } - va_end(ap); - return n; -} - -static unsigned int dsos__col_width, - comms__col_width, - threads__col_width; +struct symbol_conf symbol_conf; -/* - * histogram, sorted on item, collects counts - */ - -static struct rb_root hist; - -struct hist_entry { - struct rb_node rb_node; - - struct thread *thread; - struct map *map; - struct dso *dso; - struct symbol *sym; - struct symbol *parent; - u64 ip; - char level; - struct callchain_node callchain; - struct rb_root sorted_chain; - - u64 count; -}; - -/* - * configurable sorting bits - */ - -struct sort_entry { - struct list_head list; - - const char *header; - - int64_t (*cmp)(struct hist_entry *, struct hist_entry *); - int64_t (*collapse)(struct hist_entry *, struct hist_entry *); - size_t (*print)(FILE *fp, struct hist_entry *, unsigned int width); - unsigned int *width; - bool elide; -}; - -static int64_t cmp_null(void *l, void *r) -{ - if (!l && !r) - return 0; - else if (!l) - return -1; - else - return 1; -} - -/* --sort pid */ - -static int64_t -sort__thread_cmp(struct hist_entry *left, struct hist_entry *right) -{ - return right->thread->pid - left->thread->pid; -} static size_t -sort__thread_print(FILE *fp, struct hist_entry *self, unsigned int width) +callchain__fprintf_left_margin(FILE *fp, int left_margin) { - return repsep_fprintf(fp, "%*s:%5d", width - 6, - self->thread->comm ?: "", self->thread->pid); -} - -static struct sort_entry sort_thread = { - .header = "Command: Pid", - .cmp = sort__thread_cmp, - .print = sort__thread_print, - .width = &threads__col_width, -}; - -/* --sort comm */ - -static int64_t -sort__comm_cmp(struct hist_entry *left, struct hist_entry *right) -{ - return right->thread->pid - left->thread->pid; -} - -static int64_t -sort__comm_collapse(struct hist_entry *left, struct hist_entry *right) -{ - char *comm_l = left->thread->comm; - char *comm_r = right->thread->comm; - - if (!comm_l || !comm_r) - return cmp_null(comm_l, comm_r); - - return strcmp(comm_l, comm_r); -} - -static size_t -sort__comm_print(FILE *fp, struct hist_entry *self, unsigned int width) -{ - return repsep_fprintf(fp, "%*s", width, self->thread->comm); -} - -static struct sort_entry sort_comm = { - .header = "Command", - .cmp = sort__comm_cmp, - .collapse = sort__comm_collapse, - .print = sort__comm_print, - .width = &comms__col_width, -}; - -/* --sort dso */ - -static int64_t -sort__dso_cmp(struct hist_entry *left, struct hist_entry *right) -{ - struct dso *dso_l = left->dso; - struct dso *dso_r = right->dso; - - if (!dso_l || !dso_r) - return cmp_null(dso_l, dso_r); - - return strcmp(dso_l->name, dso_r->name); -} - -static size_t -sort__dso_print(FILE *fp, struct hist_entry *self, unsigned int width) -{ - if (self->dso) - return repsep_fprintf(fp, "%-*s", width, self->dso->name); - - return repsep_fprintf(fp, "%*llx", width, (u64)self->ip); -} - -static struct sort_entry sort_dso = { - .header = "Shared Object", - .cmp = sort__dso_cmp, - .print = sort__dso_print, - .width = &dsos__col_width, -}; - -/* --sort symbol */ - -static int64_t -sort__sym_cmp(struct hist_entry *left, struct hist_entry *right) -{ - u64 ip_l, ip_r; - - if (left->sym == right->sym) - return 0; - - ip_l = left->sym ? left->sym->start : left->ip; - ip_r = right->sym ? right->sym->start : right->ip; - - return (int64_t)(ip_r - ip_l); -} - -static size_t -sort__sym_print(FILE *fp, struct hist_entry *self, unsigned int width __used) -{ - size_t ret = 0; + int i; + int ret; - if (verbose) - ret += repsep_fprintf(fp, "%#018llx %c ", (u64)self->ip, - dso__symtab_origin(self->dso)); + ret = fprintf(fp, " "); - ret += repsep_fprintf(fp, "[%c] ", self->level); - if (self->sym) { - ret += repsep_fprintf(fp, "%s", self->sym->name); - - if (self->sym->module) - ret += repsep_fprintf(fp, "\t[%s]", - self->sym->module->name); - } else { - ret += repsep_fprintf(fp, "%#016llx", (u64)self->ip); - } + for (i = 0; i < left_margin; i++) + ret += fprintf(fp, " "); return ret; } -static struct sort_entry sort_sym = { - .header = "Symbol", - .cmp = sort__sym_cmp, - .print = sort__sym_print, -}; - -/* --sort parent */ - -static int64_t -sort__parent_cmp(struct hist_entry *left, struct hist_entry *right) -{ - struct symbol *sym_l = left->parent; - struct symbol *sym_r = right->parent; - - if (!sym_l || !sym_r) - return cmp_null(sym_l, sym_r); - - return strcmp(sym_l->name, sym_r->name); -} - -static size_t -sort__parent_print(FILE *fp, struct hist_entry *self, unsigned int width) -{ - return repsep_fprintf(fp, "%-*s", width, - self->parent ? self->parent->name : "[other]"); -} - -static unsigned int parent_symbol__col_width; - -static struct sort_entry sort_parent = { - .header = "Parent symbol", - .cmp = sort__parent_cmp, - .print = sort__parent_print, - .width = &parent_symbol__col_width, -}; - -static int sort__need_collapse = 0; -static int sort__has_parent = 0; - -struct sort_dimension { - const char *name; - struct sort_entry *entry; - int taken; -}; - -static struct sort_dimension sort_dimensions[] = { - { .name = "pid", .entry = &sort_thread, }, - { .name = "comm", .entry = &sort_comm, }, - { .name = "dso", .entry = &sort_dso, }, - { .name = "symbol", .entry = &sort_sym, }, - { .name = "parent", .entry = &sort_parent, }, -}; - -static LIST_HEAD(hist_entry__sort_list); - -static int sort_dimension__add(const char *tok) -{ - unsigned int i; - - for (i = 0; i < ARRAY_SIZE(sort_dimensions); i++) { - struct sort_dimension *sd = &sort_dimensions[i]; - - if (sd->taken) - continue; - - if (strncasecmp(tok, sd->name, strlen(tok))) - continue; - - if (sd->entry->collapse) - sort__need_collapse = 1; - - if (sd->entry == &sort_parent) { - int ret = regcomp(&parent_regex, parent_pattern, REG_EXTENDED); - if (ret) { - char err[BUFSIZ]; - - regerror(ret, &parent_regex, err, sizeof(err)); - fprintf(stderr, "Invalid regex: %s\n%s", - parent_pattern, err); - exit(-1); - } - sort__has_parent = 1; - } - - list_add_tail(&sd->entry->list, &hist_entry__sort_list); - sd->taken = 1; - - return 0; - } - - return -ESRCH; -} - -static int64_t -hist_entry__cmp(struct hist_entry *left, struct hist_entry *right) -{ - struct sort_entry *se; - int64_t cmp = 0; - - list_for_each_entry(se, &hist_entry__sort_list, list) { - cmp = se->cmp(left, right); - if (cmp) - break; - } - - return cmp; -} - -static int64_t -hist_entry__collapse(struct hist_entry *left, struct hist_entry *right) -{ - struct sort_entry *se; - int64_t cmp = 0; - - list_for_each_entry(se, &hist_entry__sort_list, list) { - int64_t (*f)(struct hist_entry *, struct hist_entry *); - - f = se->collapse ?: se->cmp; - - cmp = f(left, right); - if (cmp) - break; - } - - return cmp; -} - -static size_t ipchain__fprintf_graph_line(FILE *fp, int depth, int depth_mask) +static size_t ipchain__fprintf_graph_line(FILE *fp, int depth, int depth_mask, + int left_margin) { int i; size_t ret = 0; - ret += fprintf(fp, "%s", " "); + ret += callchain__fprintf_left_margin(fp, left_margin); for (i = 0; i < depth; i++) if (depth_mask & (1 << i)) @@ -432,12 +94,12 @@ static size_t ipchain__fprintf_graph_line(FILE *fp, int depth, int depth_mask) static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain, int depth, int depth_mask, int count, u64 total_samples, - int hits) + int hits, int left_margin) { int i; size_t ret = 0; - ret += fprintf(fp, "%s", " "); + ret += callchain__fprintf_left_margin(fp, left_margin); for (i = 0; i < depth; i++) { if (depth_mask & (1 << i)) ret += fprintf(fp, "|"); @@ -475,8 +137,9 @@ static void init_rem_hits(void) } static size_t -callchain__fprintf_graph(FILE *fp, struct callchain_node *self, - u64 total_samples, int depth, int depth_mask) +__callchain__fprintf_graph(FILE *fp, struct callchain_node *self, + u64 total_samples, int depth, int depth_mask, + int left_margin) { struct rb_node *node, *next; struct callchain_node *child; @@ -517,7 +180,8 @@ callchain__fprintf_graph(FILE *fp, struct callchain_node *self, * But we keep the older depth mask for the line seperator * to keep the level link until we reach the last child */ - ret += ipchain__fprintf_graph_line(fp, depth, depth_mask); + ret += ipchain__fprintf_graph_line(fp, depth, depth_mask, + left_margin); i = 0; list_for_each_entry(chain, &child->val, list) { if (chain->ip >= PERF_CONTEXT_MAX) @@ -525,11 +189,13 @@ callchain__fprintf_graph(FILE *fp, struct callchain_node *self, ret += ipchain__fprintf_graph(fp, chain, depth, new_depth_mask, i++, new_total, - cumul); + cumul, + left_margin); } - ret += callchain__fprintf_graph(fp, child, new_total, - depth + 1, - new_depth_mask | (1 << depth)); + ret += __callchain__fprintf_graph(fp, child, new_total, + depth + 1, + new_depth_mask | (1 << depth), + left_margin); node = next; } @@ -543,9 +209,48 @@ callchain__fprintf_graph(FILE *fp, struct callchain_node *self, ret += ipchain__fprintf_graph(fp, &rem_hits, depth, new_depth_mask, 0, new_total, - remaining); + remaining, left_margin); + } + + return ret; +} + + +static size_t +callchain__fprintf_graph(FILE *fp, struct callchain_node *self, + u64 total_samples, int left_margin) +{ + struct callchain_list *chain; + bool printed = false; + int i = 0; + int ret = 0; + + list_for_each_entry(chain, &self->val, list) { + if (chain->ip >= PERF_CONTEXT_MAX) + continue; + + if (!i++ && sort__first_dimension == SORT_SYM) + continue; + + if (!printed) { + ret += callchain__fprintf_left_margin(fp, left_margin); + ret += fprintf(fp, "|\n"); + ret += callchain__fprintf_left_margin(fp, left_margin); + ret += fprintf(fp, "---"); + + left_margin += 3; + printed = true; + } else + ret += callchain__fprintf_left_margin(fp, left_margin); + + if (chain->sym) + ret += fprintf(fp, " %s\n", chain->sym->name); + else + ret += fprintf(fp, " %p\n", (void *)(long)chain->ip); } + ret += __callchain__fprintf_graph(fp, self, total_samples, 1, 1, left_margin); + return ret; } @@ -577,7 +282,7 @@ callchain__fprintf_flat(FILE *fp, struct callchain_node *self, static size_t hist_entry_callchain__fprintf(FILE *fp, struct hist_entry *self, - u64 total_samples) + u64 total_samples, int left_margin) { struct rb_node *rb_node; struct callchain_node *chain; @@ -597,8 +302,8 @@ hist_entry_callchain__fprintf(FILE *fp, struct hist_entry *self, break; case CHAIN_GRAPH_ABS: /* Falldown */ case CHAIN_GRAPH_REL: - ret += callchain__fprintf_graph(fp, chain, - total_samples, 1, 1); + ret += callchain__fprintf_graph(fp, chain, total_samples, + left_margin); case CHAIN_NONE: default: break; @@ -610,7 +315,6 @@ hist_entry_callchain__fprintf(FILE *fp, struct hist_entry *self, return ret; } - static size_t hist_entry__fprintf(FILE *fp, struct hist_entry *self, u64 total_samples) { @@ -644,8 +348,19 @@ hist_entry__fprintf(FILE *fp, struct hist_entry *self, u64 total_samples) ret += fprintf(fp, "\n"); - if (callchain) - hist_entry_callchain__fprintf(fp, self, total_samples); + if (callchain) { + int left_margin = 0; + + if (sort__first_dimension == SORT_COMM) { + se = list_first_entry(&hist_entry__sort_list, typeof(*se), + list); + left_margin = se->width ? *se->width : 0; + left_margin -= thread__comm_len(self->thread); + } + + hist_entry_callchain__fprintf(fp, self, total_samples, + left_margin); + } return ret; } @@ -693,63 +408,6 @@ static int thread__set_comm_adjust(struct thread *self, const char *comm) return 0; } - -static struct symbol * -resolve_symbol(struct thread *thread, struct map **mapp, - struct dso **dsop, u64 *ipp) -{ - struct dso *dso = dsop ? *dsop : NULL; - struct map *map = mapp ? *mapp : NULL; - u64 ip = *ipp; - - if (!thread) - return NULL; - - if (dso) - goto got_dso; - - if (map) - goto got_map; - - map = thread__find_map(thread, ip); - if (map != NULL) { - /* - * We have to do this here as we may have a dso - * with no symbol hit that has a name longer than - * the ones with symbols sampled. - */ - if (!sort_dso.elide && !map->dso->slen_calculated) - dso__calc_col_width(map->dso); - - if (mapp) - *mapp = map; -got_map: - ip = map->map_ip(map, ip); - - dso = map->dso; - } else { - /* - * If this is outside of all known maps, - * and is a negative address, try to look it - * up in the kernel dso, as it might be a - * vsyscall (which executes in user-mode): - */ - if ((long long)ip < 0) - dso = kernel_dso; - } - dump_printf(" ...... dso: %s\n", dso ? dso->name : "<not found>"); - dump_printf(" ...... map: %Lx -> %Lx\n", *ipp, ip); - *ipp = ip; - - if (dsop) - *dsop = dso; - - if (!dso) - return NULL; -got_dso: - return dso->find_symbol(dso, ip); -} - static int call__match(struct symbol *sym) { if (sym->name && !regexec(&parent_regex, sym->name, 0, NULL, 0)) @@ -758,11 +416,11 @@ static int call__match(struct symbol *sym) return 0; } -static struct symbol ** -resolve_callchain(struct thread *thread, struct map *map __used, - struct ip_callchain *chain, struct hist_entry *entry) +static struct symbol **resolve_callchain(struct thread *thread, + struct ip_callchain *chain, + struct symbol **parent) { - u64 context = PERF_CONTEXT_MAX; + u8 cpumode = PERF_RECORD_MISC_USER; struct symbol **syms = NULL; unsigned int i; @@ -776,34 +434,31 @@ resolve_callchain(struct thread *thread, struct map *map __used, for (i = 0; i < chain->nr; i++) { u64 ip = chain->ips[i]; - struct dso *dso = NULL; - struct symbol *sym; + struct addr_location al; if (ip >= PERF_CONTEXT_MAX) { - context = ip; + switch (ip) { + case PERF_CONTEXT_HV: + cpumode = PERF_RECORD_MISC_HYPERVISOR; break; + case PERF_CONTEXT_KERNEL: + cpumode = PERF_RECORD_MISC_KERNEL; break; + case PERF_CONTEXT_USER: + cpumode = PERF_RECORD_MISC_USER; break; + default: + break; + } continue; } - switch (context) { - case PERF_CONTEXT_HV: - dso = hypervisor_dso; - break; - case PERF_CONTEXT_KERNEL: - dso = kernel_dso; - break; - default: - break; - } - - sym = resolve_symbol(thread, NULL, &dso, &ip); - - if (sym) { - if (sort__has_parent && call__match(sym) && - !entry->parent) - entry->parent = sym; + thread__find_addr_location(thread, cpumode, MAP__FUNCTION, + ip, &al, NULL); + if (al.sym != NULL) { + if (sort__has_parent && !*parent && + call__match(al.sym)) + *parent = al.sym; if (!callchain) break; - syms[i] = sym; + syms[i] = al.sym; } } @@ -814,178 +469,33 @@ resolve_callchain(struct thread *thread, struct map *map __used, * collect histogram counts */ -static int -hist_entry__add(struct thread *thread, struct map *map, struct dso *dso, - struct symbol *sym, u64 ip, struct ip_callchain *chain, - char level, u64 count) +static int hist_entry__add(struct addr_location *al, + struct ip_callchain *chain, u64 count) { - struct rb_node **p = &hist.rb_node; - struct rb_node *parent = NULL; + struct symbol **syms = NULL, *parent = NULL; + bool hit; struct hist_entry *he; - struct symbol **syms = NULL; - struct hist_entry entry = { - .thread = thread, - .map = map, - .dso = dso, - .sym = sym, - .ip = ip, - .level = level, - .count = count, - .parent = NULL, - .sorted_chain = RB_ROOT - }; - int cmp; if ((sort__has_parent || callchain) && chain) - syms = resolve_callchain(thread, map, chain, &entry); + syms = resolve_callchain(al->thread, chain, &parent); - while (*p != NULL) { - parent = *p; - he = rb_entry(parent, struct hist_entry, rb_node); + he = __hist_entry__add(al, parent, count, &hit); + if (he == NULL) + return -ENOMEM; - cmp = hist_entry__cmp(&entry, he); + if (hit) + he->count += count; - if (!cmp) { - he->count += count; - if (callchain) { - append_chain(&he->callchain, chain, syms); - free(syms); - } - return 0; - } - - if (cmp < 0) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; - } - - he = malloc(sizeof(*he)); - if (!he) - return -ENOMEM; - *he = entry; if (callchain) { - callchain_init(&he->callchain); + if (!hit) + callchain_init(&he->callchain); append_chain(&he->callchain, chain, syms); free(syms); } - rb_link_node(&he->rb_node, parent, p); - rb_insert_color(&he->rb_node, &hist); return 0; } -static void hist_entry__free(struct hist_entry *he) -{ - free(he); -} - -/* - * collapse the histogram - */ - -static struct rb_root collapse_hists; - -static void collapse__insert_entry(struct hist_entry *he) -{ - struct rb_node **p = &collapse_hists.rb_node; - struct rb_node *parent = NULL; - struct hist_entry *iter; - int64_t cmp; - - while (*p != NULL) { - parent = *p; - iter = rb_entry(parent, struct hist_entry, rb_node); - - cmp = hist_entry__collapse(iter, he); - - if (!cmp) { - iter->count += he->count; - hist_entry__free(he); - return; - } - - if (cmp < 0) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; - } - - rb_link_node(&he->rb_node, parent, p); - rb_insert_color(&he->rb_node, &collapse_hists); -} - -static void collapse__resort(void) -{ - struct rb_node *next; - struct hist_entry *n; - - if (!sort__need_collapse) - return; - - next = rb_first(&hist); - while (next) { - n = rb_entry(next, struct hist_entry, rb_node); - next = rb_next(&n->rb_node); - - rb_erase(&n->rb_node, &hist); - collapse__insert_entry(n); - } -} - -/* - * reverse the map, sort on count. - */ - -static struct rb_root output_hists; - -static void output__insert_entry(struct hist_entry *he, u64 min_callchain_hits) -{ - struct rb_node **p = &output_hists.rb_node; - struct rb_node *parent = NULL; - struct hist_entry *iter; - - if (callchain) - callchain_param.sort(&he->sorted_chain, &he->callchain, - min_callchain_hits, &callchain_param); - - while (*p != NULL) { - parent = *p; - iter = rb_entry(parent, struct hist_entry, rb_node); - - if (he->count > iter->count) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; - } - - rb_link_node(&he->rb_node, parent, p); - rb_insert_color(&he->rb_node, &output_hists); -} - -static void output__resort(u64 total_samples) -{ - struct rb_node *next; - struct hist_entry *n; - struct rb_root *tree = &hist; - u64 min_callchain_hits; - - min_callchain_hits = total_samples * (callchain_param.min_percent / 100); - - if (sort__need_collapse) - tree = &collapse_hists; - - next = rb_first(tree); - - while (next) { - n = rb_entry(next, struct hist_entry, rb_node); - next = rb_next(&n->rb_node); - - rb_erase(&n->rb_node, tree); - output__insert_entry(n, min_callchain_hits); - } -} - static size_t output__fprintf(FILE *fp, u64 total_samples) { struct hist_entry *pos; @@ -1080,13 +590,6 @@ print_entries: return ret; } -static unsigned long total = 0, - total_mmap = 0, - total_comm = 0, - total_fork = 0, - total_unknown = 0, - total_lost = 0; - static int validate_chain(struct ip_callchain *chain, event_t *event) { unsigned int chain_size; @@ -1100,30 +603,22 @@ static int validate_chain(struct ip_callchain *chain, event_t *event) return 0; } -static int -process_sample_event(event_t *event, unsigned long offset, unsigned long head) +static int process_sample_event(event_t *event) { - char level; - int show = 0; - struct dso *dso = NULL; - struct thread *thread; u64 ip = event->ip.ip; u64 period = 1; - struct map *map = NULL; void *more_data = event->ip.__more_data; struct ip_callchain *chain = NULL; int cpumode; - - thread = threads__findnew(event->ip.pid, &threads, &last_match); + struct addr_location al; + struct thread *thread = threads__findnew(event->ip.pid); if (sample_type & PERF_SAMPLE_PERIOD) { period = *(u64 *)more_data; more_data += sizeof(u64); } - dump_printf("%p [%p]: PERF_RECORD_SAMPLE (IP, %d): %d/%d: %p period: %Ld\n", - (void *)(offset + head), - (void *)(long)(event->header.size), + dump_printf("(IP, %d): %d/%d: %p period: %Ld\n", event->header.misc, event->ip.pid, event->ip.tid, (void *)(long)ip, @@ -1137,7 +632,8 @@ process_sample_event(event_t *event, unsigned long offset, unsigned long head) dump_printf("... chain: nr:%Lu\n", chain->nr); if (validate_chain(chain, event) < 0) { - eprintf("call-chain problem with event, skipping it.\n"); + pr_debug("call-chain problem with event, " + "skipping it.\n"); return 0; } @@ -1147,163 +643,64 @@ process_sample_event(event_t *event, unsigned long offset, unsigned long head) } } - dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid); - if (thread == NULL) { - eprintf("problem processing %d event, skipping it.\n", + pr_debug("problem processing %d event, skipping it.\n", event->header.type); return -1; } + dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid); + if (comm_list && !strlist__has_entry(comm_list, thread->comm)) return 0; cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - if (cpumode == PERF_RECORD_MISC_KERNEL) { - show = SHOW_KERNEL; - level = 'k'; - - dso = kernel_dso; - - dump_printf(" ...... dso: %s\n", dso->name); - - } else if (cpumode == PERF_RECORD_MISC_USER) { - - show = SHOW_USER; - level = '.'; - - } else { - show = SHOW_HV; - level = 'H'; - - dso = hypervisor_dso; - - dump_printf(" ...... dso: [hypervisor]\n"); - } - - if (show & show_mask) { - struct symbol *sym = resolve_symbol(thread, &map, &dso, &ip); - - if (dso_list && (!dso || !dso->name || - !strlist__has_entry(dso_list, dso->name))) - return 0; - - if (sym_list && (!sym || !strlist__has_entry(sym_list, sym->name))) - return 0; - - if (hist_entry__add(thread, map, dso, sym, ip, chain, level, period)) { - eprintf("problem incrementing symbol count, skipping event\n"); - return -1; - } - } - total += period; - - return 0; -} + thread__find_addr_location(thread, cpumode, + MAP__FUNCTION, ip, &al, NULL); + /* + * We have to do this here as we may have a dso with no symbol hit that + * has a name longer than the ones with symbols sampled. + */ + if (al.map && !sort_dso.elide && !al.map->dso->slen_calculated) + dso__calc_col_width(al.map->dso); + + if (dso_list && + (!al.map || !al.map->dso || + !(strlist__has_entry(dso_list, al.map->dso->short_name) || + (al.map->dso->short_name != al.map->dso->long_name && + strlist__has_entry(dso_list, al.map->dso->long_name))))) + return 0; -static int -process_mmap_event(event_t *event, unsigned long offset, unsigned long head) -{ - struct thread *thread; - struct map *map = map__new(&event->mmap, cwd, cwdlen); - - thread = threads__findnew(event->mmap.pid, &threads, &last_match); - - dump_printf("%p [%p]: PERF_RECORD_MMAP %d/%d: [%p(%p) @ %p]: %s\n", - (void *)(offset + head), - (void *)(long)(event->header.size), - event->mmap.pid, - event->mmap.tid, - (void *)(long)event->mmap.start, - (void *)(long)event->mmap.len, - (void *)(long)event->mmap.pgoff, - event->mmap.filename); - - if (thread == NULL || map == NULL) { - dump_printf("problem processing PERF_RECORD_MMAP, skipping event.\n"); + if (sym_list && al.sym && !strlist__has_entry(sym_list, al.sym->name)) return 0; + + if (hist_entry__add(&al, chain, period)) { + pr_debug("problem incrementing symbol count, skipping event\n"); + return -1; } - thread__insert_map(thread, map); - total_mmap++; + event__stats.total += period; return 0; } -static int -process_comm_event(event_t *event, unsigned long offset, unsigned long head) +static int process_comm_event(event_t *event) { - struct thread *thread; - - thread = threads__findnew(event->comm.pid, &threads, &last_match); + struct thread *thread = threads__findnew(event->comm.pid); - dump_printf("%p [%p]: PERF_RECORD_COMM: %s:%d\n", - (void *)(offset + head), - (void *)(long)(event->header.size), - event->comm.comm, event->comm.pid); + dump_printf(": %s:%d\n", event->comm.comm, event->comm.pid); if (thread == NULL || thread__set_comm_adjust(thread, event->comm.comm)) { dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n"); return -1; } - total_comm++; - - return 0; -} - -static int -process_task_event(event_t *event, unsigned long offset, unsigned long head) -{ - struct thread *thread; - struct thread *parent; - - thread = threads__findnew(event->fork.pid, &threads, &last_match); - parent = threads__findnew(event->fork.ppid, &threads, &last_match); - - dump_printf("%p [%p]: PERF_RECORD_%s: (%d:%d):(%d:%d)\n", - (void *)(offset + head), - (void *)(long)(event->header.size), - event->header.type == PERF_RECORD_FORK ? "FORK" : "EXIT", - event->fork.pid, event->fork.tid, - event->fork.ppid, event->fork.ptid); - - /* - * A thread clone will have the same PID for both - * parent and child. - */ - if (thread == parent) - return 0; - - if (event->header.type == PERF_RECORD_EXIT) - return 0; - - if (!thread || !parent || thread__fork(thread, parent)) { - dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n"); - return -1; - } - total_fork++; return 0; } -static int -process_lost_event(event_t *event, unsigned long offset, unsigned long head) -{ - dump_printf("%p [%p]: PERF_RECORD_LOST: id:%Ld: lost:%Ld\n", - (void *)(offset + head), - (void *)(long)(event->header.size), - event->lost.id, - event->lost.lost); - - total_lost += event->lost.lost; - - return 0; -} - -static int -process_read_event(event_t *event, unsigned long offset, unsigned long head) +static int process_read_event(event_t *event) { struct perf_event_attr *attr; @@ -1319,238 +716,91 @@ process_read_event(event_t *event, unsigned long offset, unsigned long head) event->read.value); } - dump_printf("%p [%p]: PERF_RECORD_READ: %d %d %s %Lu\n", - (void *)(offset + head), - (void *)(long)(event->header.size), - event->read.pid, - event->read.tid, - attr ? __event_name(attr->type, attr->config) - : "FAIL", - event->read.value); - - return 0; -} - -static int -process_event(event_t *event, unsigned long offset, unsigned long head) -{ - trace_event(event); - - switch (event->header.type) { - case PERF_RECORD_SAMPLE: - return process_sample_event(event, offset, head); - - case PERF_RECORD_MMAP: - return process_mmap_event(event, offset, head); - - case PERF_RECORD_COMM: - return process_comm_event(event, offset, head); - - case PERF_RECORD_FORK: - case PERF_RECORD_EXIT: - return process_task_event(event, offset, head); - - case PERF_RECORD_LOST: - return process_lost_event(event, offset, head); - - case PERF_RECORD_READ: - return process_read_event(event, offset, head); - - /* - * We dont process them right now but they are fine: - */ - - case PERF_RECORD_THROTTLE: - case PERF_RECORD_UNTHROTTLE: - return 0; - - default: - return -1; - } + dump_printf(": %d %d %s %Lu\n", event->read.pid, event->read.tid, + attr ? __event_name(attr->type, attr->config) : "FAIL", + event->read.value); return 0; } -static int __cmd_report(void) +static int sample_type_check(u64 type) { - int ret, rc = EXIT_FAILURE; - unsigned long offset = 0; - unsigned long head, shift; - struct stat input_stat; - struct thread *idle; - event_t *event; - uint32_t size; - char *buf; - - idle = register_idle_thread(&threads, &last_match); - thread__comm_adjust(idle); - - if (show_threads) - perf_read_values_init(&show_threads_values); - - input = open(input_name, O_RDONLY); - if (input < 0) { - fprintf(stderr, " failed to open file: %s", input_name); - if (!strcmp(input_name, "perf.data")) - fprintf(stderr, " (try 'perf record' first)"); - fprintf(stderr, "\n"); - exit(-1); - } - - ret = fstat(input, &input_stat); - if (ret < 0) { - perror("failed to stat file"); - exit(-1); - } - - if (!force && input_stat.st_uid && (input_stat.st_uid != geteuid())) { - fprintf(stderr, "file: %s not owned by current user or root\n", input_name); - exit(-1); - } - - if (!input_stat.st_size) { - fprintf(stderr, "zero-sized file, nothing to do!\n"); - exit(0); - } - - header = perf_header__read(input); - head = header->data_offset; - - sample_type = perf_header__sample_type(header); + sample_type = type; if (!(sample_type & PERF_SAMPLE_CALLCHAIN)) { if (sort__has_parent) { fprintf(stderr, "selected --sort parent, but no" " callchain data. Did you call" " perf record without -g?\n"); - exit(-1); + return -1; } if (callchain) { fprintf(stderr, "selected -g but no callchain data." " Did you call perf record without" " -g?\n"); - exit(-1); + return -1; } } else if (callchain_param.mode != CHAIN_NONE && !callchain) { callchain = 1; if (register_callchain_param(&callchain_param) < 0) { fprintf(stderr, "Can't register callchain" " params\n"); - exit(-1); + return -1; } } - if (load_kernel() < 0) { - perror("failed to load kernel symbols"); - return EXIT_FAILURE; - } - - if (!full_paths) { - if (getcwd(__cwd, sizeof(__cwd)) == NULL) { - perror("failed to get the current directory"); - return EXIT_FAILURE; - } - cwdlen = strlen(cwd); - } else { - cwd = NULL; - cwdlen = 0; - } - - shift = page_size * (head / page_size); - offset += shift; - head -= shift; - -remap: - buf = (char *)mmap(NULL, page_size * mmap_window, PROT_READ, - MAP_SHARED, input, offset); - if (buf == MAP_FAILED) { - perror("failed to mmap file"); - exit(-1); - } - -more: - event = (event_t *)(buf + head); - - size = event->header.size; - if (!size) - size = 8; - - if (head + event->header.size >= page_size * mmap_window) { - int munmap_ret; - - shift = page_size * (head / page_size); - - munmap_ret = munmap(buf, page_size * mmap_window); - assert(munmap_ret == 0); - - offset += shift; - head -= shift; - goto remap; - } - - size = event->header.size; - - dump_printf("\n%p [%p]: event: %d\n", - (void *)(offset + head), - (void *)(long)event->header.size, - event->header.type); - - if (!size || process_event(event, offset, head) < 0) { - - dump_printf("%p [%p]: skipping unknown header type: %d\n", - (void *)(offset + head), - (void *)(long)(event->header.size), - event->header.type); - - total_unknown++; - - /* - * assume we lost track of the stream, check alignment, and - * increment a single u64 in the hope to catch on again 'soon'. - */ + return 0; +} - if (unlikely(head & 7)) - head &= ~7ULL; +static struct perf_file_handler file_handler = { + .process_sample_event = process_sample_event, + .process_mmap_event = event__process_mmap, + .process_comm_event = process_comm_event, + .process_exit_event = event__process_task, + .process_fork_event = event__process_task, + .process_lost_event = event__process_lost, + .process_read_event = process_read_event, + .sample_type_check = sample_type_check, +}; - size = 8; - } - head += size; +static int __cmd_report(void) +{ + struct thread *idle; + int ret; - if (offset + head >= header->data_offset + header->data_size) - goto done; + idle = register_idle_thread(); + thread__comm_adjust(idle); - if (offset + head < (unsigned long)input_stat.st_size) - goto more; + if (show_threads) + perf_read_values_init(&show_threads_values); -done: - rc = EXIT_SUCCESS; - close(input); + register_perf_file_handler(&file_handler); - dump_printf(" IP events: %10ld\n", total); - dump_printf(" mmap events: %10ld\n", total_mmap); - dump_printf(" comm events: %10ld\n", total_comm); - dump_printf(" fork events: %10ld\n", total_fork); - dump_printf(" lost events: %10ld\n", total_lost); - dump_printf(" unknown events: %10ld\n", total_unknown); + ret = mmap_dispatch_perf_file(&header, input_name, force, + full_paths, &event__cwdlen, &event__cwd); + if (ret) + return ret; - if (dump_trace) + if (dump_trace) { + event__print_totals(); return 0; + } - if (verbose >= 3) - threads__fprintf(stdout, &threads); + if (verbose > 3) + threads__fprintf(stdout); - if (verbose >= 2) + if (verbose > 2) dsos__fprintf(stdout); collapse__resort(); - output__resort(total); - output__fprintf(stdout, total); + output__resort(event__stats.total); + output__fprintf(stdout, event__stats.total); if (show_threads) perf_read_values_destroy(&show_threads_values); - return rc; + return ret; } static int @@ -1606,7 +856,8 @@ setup: return 0; } -static const char * const report_usage[] = { +//static const char * const report_usage[] = { +const char * const report_usage[] = { "perf report [<options>] <command>", NULL }; @@ -1618,9 +869,10 @@ static const struct option options[] = { "be more verbose (show symbol address, etc)"), OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), - OPT_STRING('k', "vmlinux", &vmlinux_name, "file", "vmlinux pathname"), + OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name, + "file", "vmlinux pathname"), OPT_BOOLEAN('f', "force", &force, "don't complain, do it"), - OPT_BOOLEAN('m', "modules", &modules, + OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules, "load module symbols - WARNING: use only with -k and LIVE kernel"), OPT_BOOLEAN('n', "show-nr-samples", &show_nr_samples, "Show a column with the number of samples"), @@ -1690,9 +942,8 @@ static void setup_list(struct strlist **list, const char *list_str, int cmd_report(int argc, const char **argv, const char *prefix __used) { - symbol__init(); - - page_size = getpagesize(); + if (symbol__init(&symbol_conf) < 0) + return -1; argc = parse_options(argc, argv, options, report_usage, 0); diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index ce2d5be4f30e..26b782f26ee1 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -11,6 +11,7 @@ #include "util/trace-event.h" #include "util/debug.h" +#include "util/data_map.h" #include <sys/types.h> #include <sys/prctl.h> @@ -20,14 +21,6 @@ #include <math.h> static char const *input_name = "perf.data"; -static int input; -static unsigned long page_size; -static unsigned long mmap_window = 32; - -static unsigned long total_comm = 0; - -static struct rb_root threads; -static struct thread *last_match; static struct perf_header *header; static u64 sample_type; @@ -35,11 +28,11 @@ static u64 sample_type; static char default_sort_order[] = "avg, max, switch, runtime"; static char *sort_order = default_sort_order; +static int profile_cpu = -1; + #define PR_SET_NAME 15 /* Set process name */ #define MAX_CPUS 4096 -#define BUG_ON(x) assert(!(x)) - static u64 run_measurement_overhead; static u64 sleep_measurement_overhead; @@ -74,6 +67,7 @@ enum sched_event_type { SCHED_EVENT_RUN, SCHED_EVENT_SLEEP, SCHED_EVENT_WAKEUP, + SCHED_EVENT_MIGRATION, }; struct sched_atom { @@ -226,7 +220,7 @@ static void calibrate_sleep_measurement_overhead(void) static struct sched_atom * get_new_event(struct task_desc *task, u64 timestamp) { - struct sched_atom *event = calloc(1, sizeof(*event)); + struct sched_atom *event = zalloc(sizeof(*event)); unsigned long idx = task->nr_events; size_t size; @@ -294,7 +288,7 @@ add_sched_event_wakeup(struct task_desc *task, u64 timestamp, return; } - wakee_event->wait_sem = calloc(1, sizeof(*wakee_event->wait_sem)); + wakee_event->wait_sem = zalloc(sizeof(*wakee_event->wait_sem)); sem_init(wakee_event->wait_sem, 0, 0); wakee_event->specific_wait = 1; event->wait_sem = wakee_event->wait_sem; @@ -324,7 +318,7 @@ static struct task_desc *register_pid(unsigned long pid, const char *comm) if (task) return task; - task = calloc(1, sizeof(*task)); + task = zalloc(sizeof(*task)); task->pid = pid; task->nr = nr_tasks; strcpy(task->comm, comm); @@ -398,6 +392,8 @@ process_sched_event(struct task_desc *this_task __used, struct sched_atom *atom) ret = sem_post(atom->wait_sem); BUG_ON(ret); break; + case SCHED_EVENT_MIGRATION: + break; default: BUG_ON(1); } @@ -632,29 +628,6 @@ static void test_calibrations(void) printf("the sleep test took %Ld nsecs\n", T1-T0); } -static int -process_comm_event(event_t *event, unsigned long offset, unsigned long head) -{ - struct thread *thread; - - thread = threads__findnew(event->comm.pid, &threads, &last_match); - - dump_printf("%p [%p]: perf_event_comm: %s:%d\n", - (void *)(offset + head), - (void *)(long)(event->header.size), - event->comm.comm, event->comm.pid); - - if (thread == NULL || - thread__set_comm(thread, event->comm.comm)) { - dump_printf("problem processing perf_event_comm, skipping event.\n"); - return -1; - } - total_comm++; - - return 0; -} - - struct raw_event_sample { u32 size; char data[0]; @@ -745,6 +718,22 @@ struct trace_fork_event { u32 child_pid; }; +struct trace_migrate_task_event { + u32 size; + + u16 common_type; + u8 common_flags; + u8 common_preempt_count; + u32 common_pid; + u32 common_tgid; + + char comm[16]; + u32 pid; + + u32 prio; + u32 cpu; +}; + struct trace_sched_handler { void (*switch_event)(struct trace_switch_event *, struct event *, @@ -769,6 +758,12 @@ struct trace_sched_handler { int cpu, u64 timestamp, struct thread *thread); + + void (*migrate_task_event)(struct trace_migrate_task_event *, + struct event *, + int cpu, + u64 timestamp, + struct thread *thread); }; @@ -941,9 +936,7 @@ __thread_latency_insert(struct rb_root *root, struct work_atoms *data, static void thread_atoms_insert(struct thread *thread) { - struct work_atoms *atoms; - - atoms = calloc(sizeof(*atoms), 1); + struct work_atoms *atoms = zalloc(sizeof(*atoms)); if (!atoms) die("No memory"); @@ -975,9 +968,7 @@ add_sched_out_event(struct work_atoms *atoms, char run_state, u64 timestamp) { - struct work_atom *atom; - - atom = calloc(sizeof(*atom), 1); + struct work_atom *atom = zalloc(sizeof(*atom)); if (!atom) die("Non memory"); @@ -1058,8 +1049,8 @@ latency_switch_event(struct trace_switch_event *switch_event, die("hm, delta: %Ld < 0 ?\n", delta); - sched_out = threads__findnew(switch_event->prev_pid, &threads, &last_match); - sched_in = threads__findnew(switch_event->next_pid, &threads, &last_match); + sched_out = threads__findnew(switch_event->prev_pid); + sched_in = threads__findnew(switch_event->next_pid); out_events = thread_atoms_search(&atom_root, sched_out, &cmp_pid); if (!out_events) { @@ -1092,13 +1083,10 @@ latency_runtime_event(struct trace_runtime_event *runtime_event, u64 timestamp, struct thread *this_thread __used) { - struct work_atoms *atoms; - struct thread *thread; + struct thread *thread = threads__findnew(runtime_event->pid); + struct work_atoms *atoms = thread_atoms_search(&atom_root, thread, &cmp_pid); BUG_ON(cpu >= MAX_CPUS || cpu < 0); - - thread = threads__findnew(runtime_event->pid, &threads, &last_match); - atoms = thread_atoms_search(&atom_root, thread, &cmp_pid); if (!atoms) { thread_atoms_insert(thread); atoms = thread_atoms_search(&atom_root, thread, &cmp_pid); @@ -1125,7 +1113,7 @@ latency_wakeup_event(struct trace_wakeup_event *wakeup_event, if (!wakeup_event->success) return; - wakee = threads__findnew(wakeup_event->pid, &threads, &last_match); + wakee = threads__findnew(wakeup_event->pid); atoms = thread_atoms_search(&atom_root, wakee, &cmp_pid); if (!atoms) { thread_atoms_insert(wakee); @@ -1139,7 +1127,12 @@ latency_wakeup_event(struct trace_wakeup_event *wakeup_event, atom = list_entry(atoms->work_list.prev, struct work_atom, list); - if (atom->state != THREAD_SLEEPING) + /* + * You WILL be missing events if you've recorded only + * one CPU, or are only looking at only one, so don't + * make useless noise. + */ + if (profile_cpu == -1 && atom->state != THREAD_SLEEPING) nr_state_machine_bugs++; nr_timestamps++; @@ -1152,11 +1145,51 @@ latency_wakeup_event(struct trace_wakeup_event *wakeup_event, atom->wake_up_time = timestamp; } +static void +latency_migrate_task_event(struct trace_migrate_task_event *migrate_task_event, + struct event *__event __used, + int cpu __used, + u64 timestamp, + struct thread *thread __used) +{ + struct work_atoms *atoms; + struct work_atom *atom; + struct thread *migrant; + + /* + * Only need to worry about migration when profiling one CPU. + */ + if (profile_cpu == -1) + return; + + migrant = threads__findnew(migrate_task_event->pid); + atoms = thread_atoms_search(&atom_root, migrant, &cmp_pid); + if (!atoms) { + thread_atoms_insert(migrant); + register_pid(migrant->pid, migrant->comm); + atoms = thread_atoms_search(&atom_root, migrant, &cmp_pid); + if (!atoms) + die("migration-event: Internal tree error"); + add_sched_out_event(atoms, 'R', timestamp); + } + + BUG_ON(list_empty(&atoms->work_list)); + + atom = list_entry(atoms->work_list.prev, struct work_atom, list); + atom->sched_in_time = atom->sched_out_time = atom->wake_up_time = timestamp; + + nr_timestamps++; + + if (atom->sched_out_time > timestamp) + nr_unordered_timestamps++; +} + static struct trace_sched_handler lat_ops = { .wakeup_event = latency_wakeup_event, .switch_event = latency_switch_event, .runtime_event = latency_runtime_event, .fork_event = latency_fork_event, + .migrate_task_event = latency_migrate_task_event, }; static void output_lat_thread(struct work_atoms *work_list) @@ -1385,8 +1418,8 @@ map_switch_event(struct trace_switch_event *switch_event, die("hm, delta: %Ld < 0 ?\n", delta); - sched_out = threads__findnew(switch_event->prev_pid, &threads, &last_match); - sched_in = threads__findnew(switch_event->next_pid, &threads, &last_match); + sched_out = threads__findnew(switch_event->prev_pid); + sched_in = threads__findnew(switch_event->next_pid); curr_thread[this_cpu] = sched_in; @@ -1517,6 +1550,26 @@ process_sched_exit_event(struct event *event, } static void +process_sched_migrate_task_event(struct raw_event_sample *raw, + struct event *event, + int cpu __used, + u64 timestamp __used, + struct thread *thread __used) +{ + struct trace_migrate_task_event migrate_task_event; + + FILL_COMMON_FIELDS(migrate_task_event, event, raw->data); + + FILL_ARRAY(migrate_task_event, comm, event, raw->data); + FILL_FIELD(migrate_task_event, pid, event, raw->data); + FILL_FIELD(migrate_task_event, prio, event, raw->data); + FILL_FIELD(migrate_task_event, cpu, event, raw->data); + + if (trace_handler->migrate_task_event) + trace_handler->migrate_task_event(&migrate_task_event, event, cpu, timestamp, thread); +} + +static void process_raw_event(event_t *raw_event __used, void *more_data, int cpu, u64 timestamp, struct thread *thread) { @@ -1539,23 +1592,23 @@ process_raw_event(event_t *raw_event __used, void *more_data, process_sched_fork_event(raw, event, cpu, timestamp, thread); if (!strcmp(event->name, "sched_process_exit")) process_sched_exit_event(event, cpu, timestamp, thread); + if (!strcmp(event->name, "sched_migrate_task")) + process_sched_migrate_task_event(raw, event, cpu, timestamp, thread); } -static int -process_sample_event(event_t *event, unsigned long offset, unsigned long head) +static int process_sample_event(event_t *event) { - char level; - int show = 0; - struct dso *dso = NULL; struct thread *thread; u64 ip = event->ip.ip; u64 timestamp = -1; u32 cpu = -1; u64 period = 1; void *more_data = event->ip.__more_data; - int cpumode; - thread = threads__findnew(event->ip.pid, &threads, &last_match); + if (!(sample_type & PERF_SAMPLE_RAW)) + return 0; + + thread = threads__findnew(event->ip.pid); if (sample_type & PERF_SAMPLE_TIME) { timestamp = *(u64 *)more_data; @@ -1573,177 +1626,64 @@ process_sample_event(event_t *event, unsigned long offset, unsigned long head) more_data += sizeof(u64); } - dump_printf("%p [%p]: PERF_RECORD_SAMPLE (IP, %d): %d/%d: %p period: %Ld\n", - (void *)(offset + head), - (void *)(long)(event->header.size), + dump_printf("(IP, %d): %d/%d: %p period: %Ld\n", event->header.misc, event->ip.pid, event->ip.tid, (void *)(long)ip, (long long)period); - dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid); - if (thread == NULL) { - eprintf("problem processing %d event, skipping it.\n", - event->header.type); + pr_debug("problem processing %d event, skipping it.\n", + event->header.type); return -1; } - cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - - if (cpumode == PERF_RECORD_MISC_KERNEL) { - show = SHOW_KERNEL; - level = 'k'; - - dso = kernel_dso; - - dump_printf(" ...... dso: %s\n", dso->name); - - } else if (cpumode == PERF_RECORD_MISC_USER) { - - show = SHOW_USER; - level = '.'; - - } else { - show = SHOW_HV; - level = 'H'; - - dso = hypervisor_dso; + dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid); - dump_printf(" ...... dso: [hypervisor]\n"); - } + if (profile_cpu != -1 && profile_cpu != (int) cpu) + return 0; - if (sample_type & PERF_SAMPLE_RAW) - process_raw_event(event, more_data, cpu, timestamp, thread); + process_raw_event(event, more_data, cpu, timestamp, thread); return 0; } -static int -process_event(event_t *event, unsigned long offset, unsigned long head) +static int process_lost_event(event_t *event __used) { - trace_event(event); - - nr_events++; - switch (event->header.type) { - case PERF_RECORD_MMAP: - return 0; - case PERF_RECORD_LOST: - nr_lost_chunks++; - nr_lost_events += event->lost.lost; - return 0; - - case PERF_RECORD_COMM: - return process_comm_event(event, offset, head); + nr_lost_chunks++; + nr_lost_events += event->lost.lost; - case PERF_RECORD_EXIT ... PERF_RECORD_READ: - return 0; + return 0; +} - case PERF_RECORD_SAMPLE: - return process_sample_event(event, offset, head); +static int sample_type_check(u64 type) +{ + sample_type = type; - case PERF_RECORD_MAX: - default: + if (!(sample_type & PERF_SAMPLE_RAW)) { + fprintf(stderr, + "No trace sample to read. Did you call perf record " + "without -R?"); return -1; } return 0; } +static struct perf_file_handler file_handler = { + .process_sample_event = process_sample_event, + .process_comm_event = event__process_comm, + .process_lost_event = process_lost_event, + .sample_type_check = sample_type_check, +}; + static int read_events(void) { - int ret, rc = EXIT_FAILURE; - unsigned long offset = 0; - unsigned long head = 0; - struct stat perf_stat; - event_t *event; - uint32_t size; - char *buf; - - trace_report(); - register_idle_thread(&threads, &last_match); - - input = open(input_name, O_RDONLY); - if (input < 0) { - perror("failed to open file"); - exit(-1); - } - - ret = fstat(input, &perf_stat); - if (ret < 0) { - perror("failed to stat file"); - exit(-1); - } - - if (!perf_stat.st_size) { - fprintf(stderr, "zero-sized file, nothing to do!\n"); - exit(0); - } - header = perf_header__read(input); - head = header->data_offset; - sample_type = perf_header__sample_type(header); - - if (!(sample_type & PERF_SAMPLE_RAW)) - die("No trace sample to read. Did you call perf record " - "without -R?"); - - if (load_kernel() < 0) { - perror("failed to load kernel symbols"); - return EXIT_FAILURE; - } - -remap: - buf = (char *)mmap(NULL, page_size * mmap_window, PROT_READ, - MAP_SHARED, input, offset); - if (buf == MAP_FAILED) { - perror("failed to mmap file"); - exit(-1); - } - -more: - event = (event_t *)(buf + head); - - size = event->header.size; - if (!size) - size = 8; - - if (head + event->header.size >= page_size * mmap_window) { - unsigned long shift = page_size * (head / page_size); - int res; - - res = munmap(buf, page_size * mmap_window); - assert(res == 0); - - offset += shift; - head -= shift; - goto remap; - } - - size = event->header.size; - - - if (!size || process_event(event, offset, head) < 0) { - - /* - * assume we lost track of the stream, check alignment, and - * increment a single u64 in the hope to catch on again 'soon'. - */ - - if (unlikely(head & 7)) - head &= ~7ULL; - - size = 8; - } - - head += size; - - if (offset + head < (unsigned long)perf_stat.st_size) - goto more; - - rc = EXIT_SUCCESS; - close(input); + register_idle_thread(); + register_perf_file_handler(&file_handler); - return rc; + return mmap_dispatch_perf_file(&header, input_name, 0, 0, + &event__cwdlen, &event__cwd); } static void print_bad_events(void) @@ -1883,6 +1823,8 @@ static const struct option latency_options[] = { "sort by key(s): runtime, switch, avg, max"), OPT_BOOLEAN('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), + OPT_INTEGER('C', "CPU", &profile_cpu, + "CPU to profile on"), OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), OPT_END() @@ -1960,8 +1902,7 @@ static int __cmd_record(int argc, const char **argv) int cmd_sched(int argc, const char **argv, const char *prefix __used) { - symbol__init(); - page_size = getpagesize(); + symbol__init(0); argc = parse_options(argc, argv, sched_options, sched_usage, PARSE_OPT_STOP_AT_NON_OPTION); diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 3db31e7bf173..c70d72003557 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -50,15 +50,17 @@ static struct perf_event_attr default_attrs[] = { - { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK }, - { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES}, - { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_MIGRATIONS }, - { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS }, - - { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES }, - { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS }, - { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_REFERENCES}, - { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_MISSES }, + { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK }, + { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES }, + { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_MIGRATIONS }, + { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS }, + + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_REFERENCES }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_MISSES }, }; @@ -125,6 +127,7 @@ struct stats event_res_stats[MAX_COUNTERS][3]; struct stats runtime_nsecs_stats; struct stats walltime_nsecs_stats; struct stats runtime_cycles_stats; +struct stats runtime_branches_stats; #define MATCH_EVENT(t, c, counter) \ (attrs[counter].type == PERF_TYPE_##t && \ @@ -235,6 +238,8 @@ static void read_counter(int counter) update_stats(&runtime_nsecs_stats, count[0]); if (MATCH_EVENT(HARDWARE, HW_CPU_CYCLES, counter)) update_stats(&runtime_cycles_stats, count[0]); + if (MATCH_EVENT(HARDWARE, HW_BRANCH_INSTRUCTIONS, counter)) + update_stats(&runtime_branches_stats, count[0]); } static int run_perf_stat(int argc __used, const char **argv) @@ -352,7 +357,16 @@ static void abs_printout(int counter, double avg) ratio = avg / total; fprintf(stderr, " # %10.3f IPC ", ratio); - } else { + } else if (MATCH_EVENT(HARDWARE, HW_BRANCH_MISSES, counter) && + runtime_branches_stats.n != 0) { + total = avg_stats(&runtime_branches_stats); + + if (total) + ratio = avg * 100 / total; + + fprintf(stderr, " # %10.3f %% ", ratio); + + } else if (runtime_nsecs_stats.n != 0) { total = avg_stats(&runtime_nsecs_stats); if (total) diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c index e8a510d935e5..cb58b6605fcc 100644 --- a/tools/perf/builtin-timechart.c +++ b/tools/perf/builtin-timechart.c @@ -29,14 +29,14 @@ #include "util/header.h" #include "util/parse-options.h" #include "util/parse-events.h" +#include "util/event.h" +#include "util/data_map.h" #include "util/svghelper.h" static char const *input_name = "perf.data"; static char const *output_name = "output.svg"; -static unsigned long page_size; -static unsigned long mmap_window = 32; static u64 sample_type; static unsigned int numcpus; @@ -49,8 +49,6 @@ static u64 first_time, last_time; static int power_only; -static struct perf_header *header; - struct per_pid; struct per_pidcomm; @@ -153,6 +151,17 @@ static struct wake_event *wake_events; struct sample_wrapper *all_samples; + +struct process_filter; +struct process_filter { + char *name; + int pid; + struct process_filter *next; +}; + +static struct process_filter *process_filter; + + static struct per_pid *find_create_pid(int pid) { struct per_pid *cursor = all_data; @@ -763,11 +772,11 @@ static void draw_wakeups(void) c = p->all; while (c) { if (c->Y && c->start_time <= we->time && c->end_time >= we->time) { - if (p->pid == we->waker) { + if (p->pid == we->waker && !from) { from = c->Y; task_from = strdup(c->comm); } - if (p->pid == we->wakee) { + if (p->pid == we->wakee && !to) { to = c->Y; task_to = strdup(c->comm); } @@ -882,12 +891,89 @@ static void draw_process_bars(void) } } +static void add_process_filter(const char *string) +{ + struct process_filter *filt; + int pid; + + pid = strtoull(string, NULL, 10); + filt = malloc(sizeof(struct process_filter)); + if (!filt) + return; + + filt->name = strdup(string); + filt->pid = pid; + filt->next = process_filter; + + process_filter = filt; +} + +static int passes_filter(struct per_pid *p, struct per_pidcomm *c) +{ + struct process_filter *filt; + if (!process_filter) + return 1; + + filt = process_filter; + while (filt) { + if (filt->pid && p->pid == filt->pid) + return 1; + if (strcmp(filt->name, c->comm) == 0) + return 1; + filt = filt->next; + } + return 0; +} + +static int determine_display_tasks_filtered(void) +{ + struct per_pid *p; + struct per_pidcomm *c; + int count = 0; + + p = all_data; + while (p) { + p->display = 0; + if (p->start_time == 1) + p->start_time = first_time; + + /* no exit marker, task kept running to the end */ + if (p->end_time == 0) + p->end_time = last_time; + + c = p->all; + + while (c) { + c->display = 0; + + if (c->start_time == 1) + c->start_time = first_time; + + if (passes_filter(p, c)) { + c->display = 1; + p->display = 1; + count++; + } + + if (c->end_time == 0) + c->end_time = last_time; + + c = c->next; + } + p = p->next; + } + return count; +} + static int determine_display_tasks(u64 threshold) { struct per_pid *p; struct per_pidcomm *c; int count = 0; + if (process_filter) + return determine_display_tasks_filtered(); + p = all_data; while (p) { p->display = 0; @@ -957,36 +1043,6 @@ static void write_svg_file(const char *filename) svg_close(); } -static int -process_event(event_t *event) -{ - - switch (event->header.type) { - - case PERF_RECORD_COMM: - return process_comm_event(event); - case PERF_RECORD_FORK: - return process_fork_event(event); - case PERF_RECORD_EXIT: - return process_exit_event(event); - case PERF_RECORD_SAMPLE: - return queue_sample_event(event); - - /* - * We dont process them right now but they are fine: - */ - case PERF_RECORD_MMAP: - case PERF_RECORD_THROTTLE: - case PERF_RECORD_UNTHROTTLE: - return 0; - - default: - return -1; - } - - return 0; -} - static void process_samples(void) { struct sample_wrapper *cursor; @@ -1002,107 +1058,38 @@ static void process_samples(void) } } - -static int __cmd_timechart(void) +static int sample_type_check(u64 type) { - int ret, rc = EXIT_FAILURE; - unsigned long offset = 0; - unsigned long head, shift; - struct stat statbuf; - event_t *event; - uint32_t size; - char *buf; - int input; - - input = open(input_name, O_RDONLY); - if (input < 0) { - fprintf(stderr, " failed to open file: %s", input_name); - if (!strcmp(input_name, "perf.data")) - fprintf(stderr, " (try 'perf record' first)"); - fprintf(stderr, "\n"); - exit(-1); - } - - ret = fstat(input, &statbuf); - if (ret < 0) { - perror("failed to stat file"); - exit(-1); - } - - if (!statbuf.st_size) { - fprintf(stderr, "zero-sized file, nothing to do!\n"); - exit(0); - } - - header = perf_header__read(input); - head = header->data_offset; - - sample_type = perf_header__sample_type(header); + sample_type = type; - shift = page_size * (head / page_size); - offset += shift; - head -= shift; - -remap: - buf = (char *)mmap(NULL, page_size * mmap_window, PROT_READ, - MAP_SHARED, input, offset); - if (buf == MAP_FAILED) { - perror("failed to mmap file"); - exit(-1); - } - -more: - event = (event_t *)(buf + head); - - size = event->header.size; - if (!size) - size = 8; - - if (head + event->header.size >= page_size * mmap_window) { - int ret2; - - shift = page_size * (head / page_size); - - ret2 = munmap(buf, page_size * mmap_window); - assert(ret2 == 0); - - offset += shift; - head -= shift; - goto remap; - } - - size = event->header.size; - - if (!size || process_event(event) < 0) { - - printf("%p [%p]: skipping unknown header type: %d\n", - (void *)(offset + head), - (void *)(long)(event->header.size), - event->header.type); - - /* - * assume we lost track of the stream, check alignment, and - * increment a single u64 in the hope to catch on again 'soon'. - */ - - if (unlikely(head & 7)) - head &= ~7ULL; - - size = 8; + if (!(sample_type & PERF_SAMPLE_RAW)) { + fprintf(stderr, "No trace samples found in the file.\n" + "Have you used 'perf timechart record' to record it?\n"); + return -1; } - head += size; + return 0; +} - if (offset + head >= header->data_offset + header->data_size) - goto done; +static struct perf_file_handler file_handler = { + .process_comm_event = process_comm_event, + .process_fork_event = process_fork_event, + .process_exit_event = process_exit_event, + .process_sample_event = queue_sample_event, + .sample_type_check = sample_type_check, +}; - if (offset + head < (unsigned long)statbuf.st_size) - goto more; +static int __cmd_timechart(void) +{ + struct perf_header *header; + int ret; -done: - rc = EXIT_SUCCESS; - close(input); + register_perf_file_handler(&file_handler); + ret = mmap_dispatch_perf_file(&header, input_name, 0, 0, + &event__cwdlen, &event__cwd); + if (ret) + return EXIT_FAILURE; process_samples(); @@ -1112,9 +1099,10 @@ done: write_svg_file(output_name); - printf("Written %2.1f seconds of trace to %s.\n", (last_time - first_time) / 1000000000.0, output_name); + pr_info("Written %2.1f seconds of trace to %s.\n", + (last_time - first_time) / 1000000000.0, output_name); - return rc; + return EXIT_SUCCESS; } static const char * const timechart_usage[] = { @@ -1153,6 +1141,14 @@ static int __cmd_record(int argc, const char **argv) return cmd_record(i, rec_argv, NULL); } +static int +parse_process(const struct option *opt __used, const char *arg, int __used unset) +{ + if (arg) + add_process_filter(arg); + return 0; +} + static const struct option options[] = { OPT_STRING('i', "input", &input_name, "file", "input file name"), @@ -1160,17 +1156,18 @@ static const struct option options[] = { "output file name"), OPT_INTEGER('w', "width", &svg_page_width, "page width"), - OPT_BOOLEAN('p', "power-only", &power_only, + OPT_BOOLEAN('P', "power-only", &power_only, "output power data only"), + OPT_CALLBACK('p', "process", NULL, "process", + "process selector. Pass a pid or process name.", + parse_process), OPT_END() }; int cmd_timechart(int argc, const char **argv, const char *prefix __used) { - symbol__init(); - - page_size = getpagesize(); + symbol__init(0); argc = parse_options(argc, argv, options, timechart_usage, PARSE_OPT_STOP_AT_NON_OPTION); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index e23bc74e734f..e0a374d0e43a 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -22,6 +22,7 @@ #include "util/symbol.h" #include "util/color.h" +#include "util/thread.h" #include "util/util.h" #include <linux/rbtree.h> #include "util/parse-options.h" @@ -54,26 +55,31 @@ static int fd[MAX_NR_CPUS][MAX_COUNTERS]; -static int system_wide = 0; +static int system_wide = 0; -static int default_interval = 100000; +static int default_interval = 0; -static int count_filter = 5; -static int print_entries = 15; +static int count_filter = 5; +static int print_entries; -static int target_pid = -1; -static int inherit = 0; -static int profile_cpu = -1; -static int nr_cpus = 0; -static unsigned int realtime_prio = 0; -static int group = 0; +static int target_pid = -1; +static int inherit = 0; +static int profile_cpu = -1; +static int nr_cpus = 0; +static unsigned int realtime_prio = 0; +static int group = 0; static unsigned int page_size; -static unsigned int mmap_pages = 16; -static int freq = 0; +static unsigned int mmap_pages = 16; +static int freq = 1000; /* 1 KHz */ -static int delay_secs = 2; -static int zero; -static int dump_symtab; +static int delay_secs = 2; +static int zero = 0; +static int dump_symtab = 0; + +static bool hide_kernel_symbols = false; +static bool hide_user_symbols = false; +static struct winsize winsize; +struct symbol_conf symbol_conf; /* * Source @@ -86,83 +92,126 @@ struct source_line { struct source_line *next; }; -static char *sym_filter = NULL; -struct sym_entry *sym_filter_entry = NULL; -static int sym_pcnt_filter = 5; -static int sym_counter = 0; -static int display_weighted = -1; +static char *sym_filter = NULL; +struct sym_entry *sym_filter_entry = NULL; +static int sym_pcnt_filter = 5; +static int sym_counter = 0; +static int display_weighted = -1; /* * Symbols */ -static u64 min_ip; -static u64 max_ip = -1ll; +struct sym_entry_source { + struct source_line *source; + struct source_line *lines; + struct source_line **lines_tail; + pthread_mutex_t lock; +}; struct sym_entry { struct rb_node rb_node; struct list_head node; - unsigned long count[MAX_COUNTERS]; unsigned long snap_count; double weight; int skip; - struct source_line *source; - struct source_line *lines; - struct source_line **lines_tail; - pthread_mutex_t source_lock; + u16 name_len; + u8 origin; + struct map *map; + struct sym_entry_source *src; + unsigned long count[0]; }; /* * Source functions */ +static inline struct symbol *sym_entry__symbol(struct sym_entry *self) +{ + return ((void *)self) + symbol_conf.priv_size; +} + +static void get_term_dimensions(struct winsize *ws) +{ + char *s = getenv("LINES"); + + if (s != NULL) { + ws->ws_row = atoi(s); + s = getenv("COLUMNS"); + if (s != NULL) { + ws->ws_col = atoi(s); + if (ws->ws_row && ws->ws_col) + return; + } + } +#ifdef TIOCGWINSZ + if (ioctl(1, TIOCGWINSZ, ws) == 0 && + ws->ws_row && ws->ws_col) + return; +#endif + ws->ws_row = 25; + ws->ws_col = 80; +} + +static void update_print_entries(struct winsize *ws) +{ + print_entries = ws->ws_row; + + if (print_entries > 9) + print_entries -= 9; +} + +static void sig_winch_handler(int sig __used) +{ + get_term_dimensions(&winsize); + update_print_entries(&winsize); +} + static void parse_source(struct sym_entry *syme) { struct symbol *sym; - struct module *module; - struct section *section = NULL; + struct sym_entry_source *source; + struct map *map; FILE *file; char command[PATH_MAX*2]; - const char *path = vmlinux_name; - u64 start, end, len; + const char *path; + u64 len; if (!syme) return; - if (syme->lines) { - pthread_mutex_lock(&syme->source_lock); - goto out_assign; + if (syme->src == NULL) { + syme->src = zalloc(sizeof(*source)); + if (syme->src == NULL) + return; + pthread_mutex_init(&syme->src->lock, NULL); } - sym = (struct symbol *)(syme + 1); - module = sym->module; - - if (module) - path = module->path; - if (!path) - return; - - start = sym->obj_start; - if (!start) - start = sym->start; + source = syme->src; - if (module) { - section = module->sections->find_section(module->sections, ".text"); - if (section) - start -= section->vma; + if (source->lines) { + pthread_mutex_lock(&source->lock); + goto out_assign; } - end = start + sym->end - sym->start + 1; + sym = sym_entry__symbol(syme); + map = syme->map; + path = map->dso->long_name; + len = sym->end - sym->start; - sprintf(command, "objdump --start-address=0x%016Lx --stop-address=0x%016Lx -dS %s", start, end, path); + sprintf(command, + "objdump --start-address=0x%016Lx " + "--stop-address=0x%016Lx -dS %s", + map->unmap_ip(map, sym->start), + map->unmap_ip(map, sym->end), path); file = popen(command, "r"); if (!file) return; - pthread_mutex_lock(&syme->source_lock); - syme->lines_tail = &syme->lines; + pthread_mutex_lock(&source->lock); + source->lines_tail = &source->lines; while (!feof(file)) { struct source_line *src; size_t dummy = 0; @@ -182,24 +231,22 @@ static void parse_source(struct sym_entry *syme) *c = 0; src->next = NULL; - *syme->lines_tail = src; - syme->lines_tail = &src->next; + *source->lines_tail = src; + source->lines_tail = &src->next; if (strlen(src->line)>8 && src->line[8] == ':') { src->eip = strtoull(src->line, NULL, 16); - if (section) - src->eip += section->vma; + src->eip = map->unmap_ip(map, src->eip); } if (strlen(src->line)>8 && src->line[16] == ':') { src->eip = strtoull(src->line, NULL, 16); - if (section) - src->eip += section->vma; + src->eip = map->unmap_ip(map, src->eip); } } pclose(file); out_assign: sym_filter_entry = syme; - pthread_mutex_unlock(&syme->source_lock); + pthread_mutex_unlock(&source->lock); } static void __zero_source_counters(struct sym_entry *syme) @@ -207,7 +254,7 @@ static void __zero_source_counters(struct sym_entry *syme) int i; struct source_line *line; - line = syme->lines; + line = syme->src->lines; while (line) { for (i = 0; i < nr_counters; i++) line->count[i] = 0; @@ -222,13 +269,13 @@ static void record_precise_ip(struct sym_entry *syme, int counter, u64 ip) if (syme != sym_filter_entry) return; - if (pthread_mutex_trylock(&syme->source_lock)) + if (pthread_mutex_trylock(&syme->src->lock)) return; - if (!syme->source) + if (syme->src == NULL || syme->src->source == NULL) goto out_unlock; - for (line = syme->lines; line; line = line->next) { + for (line = syme->src->lines; line; line = line->next) { if (line->eip == ip) { line->count[counter]++; break; @@ -237,32 +284,25 @@ static void record_precise_ip(struct sym_entry *syme, int counter, u64 ip) break; } out_unlock: - pthread_mutex_unlock(&syme->source_lock); + pthread_mutex_unlock(&syme->src->lock); } static void lookup_sym_source(struct sym_entry *syme) { - struct symbol *symbol = (struct symbol *)(syme + 1); + struct symbol *symbol = sym_entry__symbol(syme); struct source_line *line; char pattern[PATH_MAX]; - char *idx; sprintf(pattern, "<%s>:", symbol->name); - if (symbol->module) { - idx = strstr(pattern, "\t"); - if (idx) - *idx = 0; - } - - pthread_mutex_lock(&syme->source_lock); - for (line = syme->lines; line; line = line->next) { + pthread_mutex_lock(&syme->src->lock); + for (line = syme->src->lines; line; line = line->next) { if (strstr(line->line, pattern)) { - syme->source = line; + syme->src->source = line; break; } } - pthread_mutex_unlock(&syme->source_lock); + pthread_mutex_unlock(&syme->src->lock); } static void show_lines(struct source_line *queue, int count, int total) @@ -292,24 +332,24 @@ static void show_details(struct sym_entry *syme) if (!syme) return; - if (!syme->source) + if (!syme->src->source) lookup_sym_source(syme); - if (!syme->source) + if (!syme->src->source) return; - symbol = (struct symbol *)(syme + 1); + symbol = sym_entry__symbol(syme); printf("Showing %s for %s\n", event_name(sym_counter), symbol->name); printf(" Events Pcnt (>=%d%%)\n", sym_pcnt_filter); - pthread_mutex_lock(&syme->source_lock); - line = syme->source; + pthread_mutex_lock(&syme->src->lock); + line = syme->src->source; while (line) { total += line->count[sym_counter]; line = line->next; } - line = syme->source; + line = syme->src->source; while (line) { float pcnt = 0.0; @@ -334,13 +374,13 @@ static void show_details(struct sym_entry *syme) line->count[sym_counter] = zero ? 0 : line->count[sym_counter] * 7 / 8; line = line->next; } - pthread_mutex_unlock(&syme->source_lock); + pthread_mutex_unlock(&syme->src->lock); if (more) printf("%d lines not displayed, maybe increase display entries [e]\n", more); } /* - * Symbols will be added here in record_ip and will get out + * Symbols will be added here in event__process_sample and will get out * after decayed. */ static LIST_HEAD(active_symbols); @@ -411,6 +451,8 @@ static void print_sym_table(void) struct sym_entry *syme, *n; struct rb_root tmp = RB_ROOT; struct rb_node *nd; + int sym_width = 0, dso_width = 0, max_dso_width; + const int win_width = winsize.ws_col - 1; samples = userspace_samples = 0; @@ -422,6 +464,14 @@ static void print_sym_table(void) list_for_each_entry_safe_from(syme, n, &active_symbols, node) { syme->snap_count = syme->count[snap]; if (syme->snap_count != 0) { + + if ((hide_user_symbols && + syme->origin == PERF_RECORD_MISC_USER) || + (hide_kernel_symbols && + syme->origin == PERF_RECORD_MISC_KERNEL)) { + list_remove_active_sym(syme); + continue; + } syme->weight = sym_weight(syme); rb_insert_active_sym(&tmp, syme); sum_ksamples += syme->snap_count; @@ -434,8 +484,7 @@ static void print_sym_table(void) puts(CONSOLE_CLEAR); - printf( -"------------------------------------------------------------------------------\n"); + printf("%-*.*s\n", win_width, win_width, graph_dotted_line); printf( " PerfTop:%8.0f irqs/sec kernel:%4.1f%% [", samples_per_sec, 100.0 - (100.0*((samples_per_sec-ksamples_per_sec)/samples_per_sec))); @@ -473,33 +522,57 @@ static void print_sym_table(void) printf(", %d CPUs)\n", nr_cpus); } - printf("------------------------------------------------------------------------------\n\n"); + printf("%-*.*s\n", win_width, win_width, graph_dotted_line); if (sym_filter_entry) { show_details(sym_filter_entry); return; } + /* + * Find the longest symbol name that will be displayed + */ + for (nd = rb_first(&tmp); nd; nd = rb_next(nd)) { + syme = rb_entry(nd, struct sym_entry, rb_node); + if (++printed > print_entries || + (int)syme->snap_count < count_filter) + continue; + + if (syme->map->dso->long_name_len > dso_width) + dso_width = syme->map->dso->long_name_len; + + if (syme->name_len > sym_width) + sym_width = syme->name_len; + } + + printed = 0; + + max_dso_width = winsize.ws_col - sym_width - 29; + if (dso_width > max_dso_width) + dso_width = max_dso_width; + putchar('\n'); if (nr_counters == 1) - printf(" samples pcnt"); + printf(" samples pcnt"); else - printf(" weight samples pcnt"); + printf(" weight samples pcnt"); if (verbose) printf(" RIP "); - printf(" kernel function\n"); - printf(" %s _______ _____", + printf(" %-*.*s DSO\n", sym_width, sym_width, "function"); + printf(" %s _______ _____", nr_counters == 1 ? " " : "______"); if (verbose) - printf(" ________________"); - printf(" _______________\n\n"); + printf(" ________________"); + printf(" %-*.*s", sym_width, sym_width, graph_line); + printf(" %-*.*s", dso_width, dso_width, graph_line); + puts("\n"); for (nd = rb_first(&tmp); nd; nd = rb_next(nd)) { struct symbol *sym; double pcnt; syme = rb_entry(nd, struct sym_entry, rb_node); - sym = (struct symbol *)(syme + 1); + sym = sym_entry__symbol(syme); if (++printed > print_entries || (int)syme->snap_count < count_filter) continue; @@ -508,17 +581,18 @@ static void print_sym_table(void) sum_ksamples)); if (nr_counters == 1 || !display_weighted) - printf("%20.2f - ", syme->weight); + printf("%20.2f ", syme->weight); else - printf("%9.1f %10ld - ", syme->weight, syme->snap_count); + printf("%9.1f %10ld ", syme->weight, syme->snap_count); percent_color_fprintf(stdout, "%4.1f%%", pcnt); if (verbose) - printf(" - %016llx", sym->start); - printf(" : %s", sym->name); - if (sym->module) - printf("\t[%s]", sym->module->name); - printf("\n"); + printf(" %016llx", sym->start); + printf(" %-*.*s", sym_width, sym_width, sym->name); + printf(" %-*.*s\n", dso_width, dso_width, + dso_width >= syme->map->dso->long_name_len ? + syme->map->dso->long_name : + syme->map->dso->short_name); } } @@ -565,10 +639,10 @@ static void prompt_symbol(struct sym_entry **target, const char *msg) /* zero counters of active symbol */ if (syme) { - pthread_mutex_lock(&syme->source_lock); + pthread_mutex_lock(&syme->src->lock); __zero_source_counters(syme); *target = NULL; - pthread_mutex_unlock(&syme->source_lock); + pthread_mutex_unlock(&syme->src->lock); } fprintf(stdout, "\n%s: ", msg); @@ -584,7 +658,7 @@ static void prompt_symbol(struct sym_entry **target, const char *msg) pthread_mutex_unlock(&active_symbols_lock); list_for_each_entry_safe_from(syme, n, &active_symbols, node) { - struct symbol *sym = (struct symbol *)(syme + 1); + struct symbol *sym = sym_entry__symbol(syme); if (!strcmp(buf, sym->name)) { found = syme; @@ -608,7 +682,7 @@ static void print_mapped_keys(void) char *name = NULL; if (sym_filter_entry) { - struct symbol *sym = (struct symbol *)(sym_filter_entry+1); + struct symbol *sym = sym_entry__symbol(sym_filter_entry); name = sym->name; } @@ -621,7 +695,7 @@ static void print_mapped_keys(void) fprintf(stdout, "\t[f] profile display filter (count). \t(%d)\n", count_filter); - if (vmlinux_name) { + if (symbol_conf.vmlinux_name) { fprintf(stdout, "\t[F] annotate display filter (percent). \t(%d%%)\n", sym_pcnt_filter); fprintf(stdout, "\t[s] annotate symbol. \t(%s)\n", name?: "NULL"); fprintf(stdout, "\t[S] stop annotation.\n"); @@ -630,6 +704,12 @@ static void print_mapped_keys(void) if (nr_counters > 1) fprintf(stdout, "\t[w] toggle display weighted/count[E]r. \t(%d)\n", display_weighted ? 1 : 0); + fprintf(stdout, + "\t[K] hide kernel_symbols symbols. \t(%s)\n", + hide_kernel_symbols ? "yes" : "no"); + fprintf(stdout, + "\t[U] hide user symbols. \t(%s)\n", + hide_user_symbols ? "yes" : "no"); fprintf(stdout, "\t[z] toggle sample zeroing. \t(%d)\n", zero ? 1 : 0); fprintf(stdout, "\t[qQ] quit.\n"); } @@ -643,6 +723,8 @@ static int key_mapped(int c) case 'z': case 'q': case 'Q': + case 'K': + case 'U': return 1; case 'E': case 'w': @@ -650,7 +732,7 @@ static int key_mapped(int c) case 'F': case 's': case 'S': - return vmlinux_name ? 1 : 0; + return symbol_conf.vmlinux_name ? 1 : 0; default: break; } @@ -691,6 +773,11 @@ static void handle_keypress(int c) break; case 'e': prompt_integer(&print_entries, "Enter display entries (lines)"); + if (print_entries == 0) { + sig_winch_handler(SIGWINCH); + signal(SIGWINCH, sig_winch_handler); + } else + signal(SIGWINCH, SIG_DFL); break; case 'E': if (nr_counters > 1) { @@ -715,9 +802,14 @@ static void handle_keypress(int c) case 'F': prompt_percent(&sym_pcnt_filter, "Enter details display event filter (percent)"); break; + case 'K': + hide_kernel_symbols = !hide_kernel_symbols; + break; case 'q': case 'Q': printf("exiting.\n"); + if (dump_symtab) + dsos__fprintf(stderr); exit(0); case 's': prompt_symbol(&sym_filter_entry, "Enter details symbol"); @@ -728,12 +820,15 @@ static void handle_keypress(int c) else { struct sym_entry *syme = sym_filter_entry; - pthread_mutex_lock(&syme->source_lock); + pthread_mutex_lock(&syme->src->lock); sym_filter_entry = NULL; __zero_source_counters(syme); - pthread_mutex_unlock(&syme->source_lock); + pthread_mutex_unlock(&syme->src->lock); } break; + case 'U': + hide_user_symbols = !hide_user_symbols; + break; case 'w': display_weighted = ~display_weighted; break; @@ -790,7 +885,7 @@ static const char *skip_symbols[] = { NULL }; -static int symbol_filter(struct dso *self, struct symbol *sym) +static int symbol_filter(struct map *map, struct symbol *sym) { struct sym_entry *syme; const char *name = sym->name; @@ -812,8 +907,9 @@ static int symbol_filter(struct dso *self, struct symbol *sym) strstr(name, "_text_end")) return 1; - syme = dso__sym_priv(self, sym); - pthread_mutex_init(&syme->source_lock, NULL); + syme = symbol__priv(sym); + syme->map = map; + syme->src = NULL; if (!sym_filter_entry && sym_filter && !strcmp(name, sym_filter)) sym_filter_entry = syme; @@ -824,75 +920,65 @@ static int symbol_filter(struct dso *self, struct symbol *sym) } } - return 0; -} - -static int parse_symbols(void) -{ - struct rb_node *node; - struct symbol *sym; - int use_modules = vmlinux_name ? 1 : 0; - - kernel_dso = dso__new("[kernel]", sizeof(struct sym_entry)); - if (kernel_dso == NULL) - return -1; - - if (dso__load_kernel(kernel_dso, vmlinux_name, symbol_filter, verbose, use_modules) <= 0) - goto out_delete_dso; - - node = rb_first(&kernel_dso->syms); - sym = rb_entry(node, struct symbol, rb_node); - min_ip = sym->start; - - node = rb_last(&kernel_dso->syms); - sym = rb_entry(node, struct symbol, rb_node); - max_ip = sym->end; - - if (dump_symtab) - dso__fprintf(kernel_dso, stderr); + if (!syme->skip) + syme->name_len = strlen(sym->name); return 0; - -out_delete_dso: - dso__delete(kernel_dso); - kernel_dso = NULL; - return -1; } -/* - * Binary search in the histogram table and record the hit: - */ -static void record_ip(u64 ip, int counter) +static void event__process_sample(const event_t *self, int counter) { - struct symbol *sym = dso__find_symbol(kernel_dso, ip); - - if (sym != NULL) { - struct sym_entry *syme = dso__sym_priv(kernel_dso, sym); - - if (!syme->skip) { - syme->count[counter]++; - record_precise_ip(syme, counter, ip); - pthread_mutex_lock(&active_symbols_lock); - if (list_empty(&syme->node) || !syme->node.next) - __list_insert_active_sym(syme); - pthread_mutex_unlock(&active_symbols_lock); + u64 ip = self->ip.ip; + struct sym_entry *syme; + struct addr_location al; + u8 origin = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + + switch (origin) { + case PERF_RECORD_MISC_USER: + if (hide_user_symbols) return; - } + break; + case PERF_RECORD_MISC_KERNEL: + if (hide_kernel_symbols) + return; + break; + default: + return; } - samples--; + if (event__preprocess_sample(self, &al, symbol_filter) < 0 || + al.sym == NULL) + return; + + syme = symbol__priv(al.sym); + if (!syme->skip) { + syme->count[counter]++; + syme->origin = origin; + record_precise_ip(syme, counter, ip); + pthread_mutex_lock(&active_symbols_lock); + if (list_empty(&syme->node) || !syme->node.next) + __list_insert_active_sym(syme); + pthread_mutex_unlock(&active_symbols_lock); + if (origin == PERF_RECORD_MISC_USER) + ++userspace_samples; + ++samples; + } } -static void process_event(u64 ip, int counter, int user) +static int event__process(event_t *event) { - samples++; - - if (user) { - userspace_samples++; - return; + switch (event->header.type) { + case PERF_RECORD_COMM: + event__process_comm(event); + break; + case PERF_RECORD_MMAP: + event__process_mmap(event); + break; + default: + break; } - record_ip(ip, counter); + return 0; } struct mmap_data { @@ -913,8 +999,6 @@ static unsigned int mmap_read_head(struct mmap_data *md) return head; } -struct timeval last_read, this_read; - static void mmap_read_counter(struct mmap_data *md) { unsigned int head = mmap_read_head(md); @@ -922,8 +1006,6 @@ static void mmap_read_counter(struct mmap_data *md) unsigned char *data = md->base + page_size; int diff; - gettimeofday(&this_read, NULL); - /* * If we're further behind than half the buffer, there's a chance * the writer will bite our tail and mess up the samples under us. @@ -934,14 +1016,7 @@ static void mmap_read_counter(struct mmap_data *md) */ diff = head - old; if (diff > md->mask / 2 || diff < 0) { - struct timeval iv; - unsigned long msecs; - - timersub(&this_read, &last_read, &iv); - msecs = iv.tv_sec*1000 + iv.tv_usec/1000; - - fprintf(stderr, "WARNING: failed to keep up with mmap data." - " Last read %lu msecs ago.\n", msecs); + fprintf(stderr, "WARNING: failed to keep up with mmap data.\n"); /* * head points to a known good entry, start there. @@ -949,8 +1024,6 @@ static void mmap_read_counter(struct mmap_data *md) old = head; } - last_read = this_read; - for (; old != head;) { event_t *event = (event_t *)&data[old & md->mask]; @@ -978,13 +1051,11 @@ static void mmap_read_counter(struct mmap_data *md) event = &event_copy; } + if (event->header.type == PERF_RECORD_SAMPLE) + event__process_sample(event, md->counter); + else + event__process(event); old += size; - - if (event->header.type == PERF_RECORD_SAMPLE) { - int user = - (event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK) == PERF_RECORD_MISC_USER; - process_event(event->ip.ip, md->counter, user); - } } md->prev = old; @@ -1018,8 +1089,15 @@ static void start_counter(int i, int counter) attr = attrs + counter; attr->sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID; - attr->freq = freq; + + if (freq) { + attr->sample_type |= PERF_SAMPLE_PERIOD; + attr->freq = 1; + attr->sample_freq = freq; + } + attr->inherit = (cpu < 0) && inherit; + attr->mmap = 1; try_again: fd[i][counter] = sys_perf_event_open(attr, target_pid, cpu, group_fd, 0); @@ -1078,6 +1156,11 @@ static int __cmd_top(void) int i, counter; int ret; + if (target_pid != -1) + event__synthesize_thread(target_pid, event__process); + else + event__synthesize_threads(event__process); + for (i = 0; i < nr_cpus; i++) { group_fd = -1; for (counter = 0; counter < nr_counters; counter++) @@ -1133,7 +1216,10 @@ static const struct option options[] = { "system-wide collection from all CPUs"), OPT_INTEGER('C', "CPU", &profile_cpu, "CPU to profile on"), - OPT_STRING('k', "vmlinux", &vmlinux_name, "file", "vmlinux pathname"), + OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name, + "file", "vmlinux pathname"), + OPT_BOOLEAN('K', "hide_kernel_symbols", &hide_kernel_symbols, + "hide kernel symbols"), OPT_INTEGER('m', "mmap-pages", &mmap_pages, "number of mmap data pages"), OPT_INTEGER('r', "realtime", &realtime_prio, @@ -1156,6 +1242,8 @@ static const struct option options[] = { "profile at this frequency"), OPT_INTEGER('E', "entries", &print_entries, "display this many functions"), + OPT_BOOLEAN('U', "hide_user_symbols", &hide_user_symbols, + "hide user symbols"), OPT_BOOLEAN('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"), OPT_END() @@ -1165,19 +1253,12 @@ int cmd_top(int argc, const char **argv, const char *prefix __used) { int counter; - symbol__init(); - page_size = sysconf(_SC_PAGE_SIZE); argc = parse_options(argc, argv, options, top_usage, 0); if (argc) usage_with_options(top_usage, options); - if (freq) { - default_interval = freq; - freq = 1; - } - /* CPU and PID are mutually exclusive */ if (target_pid != -1 && profile_cpu != -1) { printf("WARNING: PID switch overriding CPU\n"); @@ -1188,13 +1269,31 @@ int cmd_top(int argc, const char **argv, const char *prefix __used) if (!nr_counters) nr_counters = 1; + symbol_conf.priv_size = (sizeof(struct sym_entry) + + (nr_counters + 1) * sizeof(unsigned long)); + if (symbol_conf.vmlinux_name == NULL) + symbol_conf.try_vmlinux_path = true; + if (symbol__init(&symbol_conf) < 0) + return -1; + if (delay_secs < 1) delay_secs = 1; - parse_symbols(); parse_source(sym_filter_entry); /* + * User specified count overrides default frequency. + */ + if (default_interval) + freq = 0; + else if (freq) { + default_interval = freq; + } else { + fprintf(stderr, "frequency and count are zero, aborting\n"); + exit(EXIT_FAILURE); + } + + /* * Fill in the ones not specifically initialized via -c: */ for (counter = 0; counter < nr_counters; counter++) { @@ -1211,5 +1310,11 @@ int cmd_top(int argc, const char **argv, const char *prefix __used) if (target_pid != -1 || profile_cpu != -1) nr_cpus = 1; + get_term_dimensions(&winsize); + if (print_entries == 0) { + update_print_entries(&winsize); + signal(SIGWINCH, sig_winch_handler); + } + return __cmd_top(); } diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 0c5e4f72f2ba..abb914aa7be6 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -5,66 +5,73 @@ #include "util/symbol.h" #include "util/thread.h" #include "util/header.h" +#include "util/exec_cmd.h" +#include "util/trace-event.h" -#include "util/parse-options.h" +static char const *script_name; +static char const *generate_script_lang; -#include "perf.h" -#include "util/debug.h" +static int default_start_script(const char *script __attribute((unused))) +{ + return 0; +} -#include "util/trace-event.h" +static int default_stop_script(void) +{ + return 0; +} -static char const *input_name = "perf.data"; -static int input; -static unsigned long page_size; -static unsigned long mmap_window = 32; +static int default_generate_script(const char *outfile __attribute ((unused))) +{ + return 0; +} -static unsigned long total = 0; -static unsigned long total_comm = 0; +static struct scripting_ops default_scripting_ops = { + .start_script = default_start_script, + .stop_script = default_stop_script, + .process_event = print_event, + .generate_script = default_generate_script, +}; + +static struct scripting_ops *scripting_ops; -static struct rb_root threads; -static struct thread *last_match; +static void setup_scripting(void) +{ + /* make sure PERF_EXEC_PATH is set for scripts */ + perf_set_argv_exec_path(perf_exec_path()); -static struct perf_header *header; -static u64 sample_type; + setup_perl_scripting(); + scripting_ops = &default_scripting_ops; +} -static int -process_comm_event(event_t *event, unsigned long offset, unsigned long head) +static int cleanup_scripting(void) { - struct thread *thread; + return scripting_ops->stop_script(); +} - thread = threads__findnew(event->comm.pid, &threads, &last_match); +#include "util/parse-options.h" - dump_printf("%p [%p]: PERF_RECORD_COMM: %s:%d\n", - (void *)(offset + head), - (void *)(long)(event->header.size), - event->comm.comm, event->comm.pid); +#include "perf.h" +#include "util/debug.h" - if (thread == NULL || - thread__set_comm(thread, event->comm.comm)) { - dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n"); - return -1; - } - total_comm++; +#include "util/trace-event.h" +#include "util/data_map.h" +#include "util/exec_cmd.h" - return 0; -} +static char const *input_name = "perf.data"; -static int -process_sample_event(event_t *event, unsigned long offset, unsigned long head) +static struct perf_header *header; +static u64 sample_type; + +static int process_sample_event(event_t *event) { - char level; - int show = 0; - struct dso *dso = NULL; - struct thread *thread; u64 ip = event->ip.ip; u64 timestamp = -1; u32 cpu = -1; u64 period = 1; void *more_data = event->ip.__more_data; - int cpumode; - - thread = threads__findnew(event->ip.pid, &threads, &last_match); + struct thread *thread = threads__findnew(event->ip.pid); if (sample_type & PERF_SAMPLE_TIME) { timestamp = *(u64 *)more_data; @@ -82,45 +89,19 @@ process_sample_event(event_t *event, unsigned long offset, unsigned long head) more_data += sizeof(u64); } - dump_printf("%p [%p]: PERF_RECORD_SAMPLE (IP, %d): %d/%d: %p period: %Ld\n", - (void *)(offset + head), - (void *)(long)(event->header.size), + dump_printf("(IP, %d): %d/%d: %p period: %Ld\n", event->header.misc, event->ip.pid, event->ip.tid, (void *)(long)ip, (long long)period); - dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid); - if (thread == NULL) { - eprintf("problem processing %d event, skipping it.\n", - event->header.type); + pr_debug("problem processing %d event, skipping it.\n", + event->header.type); return -1; } - cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - - if (cpumode == PERF_RECORD_MISC_KERNEL) { - show = SHOW_KERNEL; - level = 'k'; - - dso = kernel_dso; - - dump_printf(" ...... dso: %s\n", dso->name); - - } else if (cpumode == PERF_RECORD_MISC_USER) { - - show = SHOW_USER; - level = '.'; - - } else { - show = SHOW_HV; - level = 'H'; - - dso = hypervisor_dso; - - dump_printf(" ...... dso: [hypervisor]\n"); - } + dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid); if (sample_type & PERF_SAMPLE_RAW) { struct { @@ -133,128 +114,189 @@ process_sample_event(event_t *event, unsigned long offset, unsigned long head) * field, although it should be the same than this perf * event pid */ - print_event(cpu, raw->data, raw->size, timestamp, thread->comm); + scripting_ops->process_event(cpu, raw->data, raw->size, + timestamp, thread->comm); } - total += period; + event__stats.total += period; return 0; } -static int -process_event(event_t *event, unsigned long offset, unsigned long head) +static int sample_type_check(u64 type) { - trace_event(event); - - switch (event->header.type) { - case PERF_RECORD_MMAP ... PERF_RECORD_LOST: - return 0; - - case PERF_RECORD_COMM: - return process_comm_event(event, offset, head); - - case PERF_RECORD_EXIT ... PERF_RECORD_READ: - return 0; - - case PERF_RECORD_SAMPLE: - return process_sample_event(event, offset, head); + sample_type = type; - case PERF_RECORD_MAX: - default: + if (!(sample_type & PERF_SAMPLE_RAW)) { + fprintf(stderr, + "No trace sample to read. Did you call perf record " + "without -R?"); return -1; } return 0; } +static struct perf_file_handler file_handler = { + .process_sample_event = process_sample_event, + .process_comm_event = event__process_comm, + .sample_type_check = sample_type_check, +}; + static int __cmd_trace(void) { - int ret, rc = EXIT_FAILURE; - unsigned long offset = 0; - unsigned long head = 0; - struct stat perf_stat; - event_t *event; - uint32_t size; - char *buf; - - trace_report(); - register_idle_thread(&threads, &last_match); - - input = open(input_name, O_RDONLY); - if (input < 0) { - perror("failed to open file"); - exit(-1); - } + register_idle_thread(); + register_perf_file_handler(&file_handler); - ret = fstat(input, &perf_stat); - if (ret < 0) { - perror("failed to stat file"); - exit(-1); - } + return mmap_dispatch_perf_file(&header, input_name, + 0, 0, &event__cwdlen, &event__cwd); +} - if (!perf_stat.st_size) { - fprintf(stderr, "zero-sized file, nothing to do!\n"); - exit(0); - } - header = perf_header__read(input); - head = header->data_offset; - sample_type = perf_header__sample_type(header); +struct script_spec { + struct list_head node; + struct scripting_ops *ops; + char spec[0]; +}; - if (!(sample_type & PERF_SAMPLE_RAW)) - die("No trace sample to read. Did you call perf record " - "without -R?"); +LIST_HEAD(script_specs); - if (load_kernel() < 0) { - perror("failed to load kernel symbols"); - return EXIT_FAILURE; - } +static struct script_spec *script_spec__new(const char *spec, + struct scripting_ops *ops) +{ + struct script_spec *s = malloc(sizeof(*s) + strlen(spec) + 1); -remap: - buf = (char *)mmap(NULL, page_size * mmap_window, PROT_READ, - MAP_SHARED, input, offset); - if (buf == MAP_FAILED) { - perror("failed to mmap file"); - exit(-1); + if (s != NULL) { + strcpy(s->spec, spec); + s->ops = ops; } -more: - event = (event_t *)(buf + head); + return s; +} - if (head + event->header.size >= page_size * mmap_window) { - unsigned long shift = page_size * (head / page_size); - int res; +static void script_spec__delete(struct script_spec *s) +{ + free(s->spec); + free(s); +} - res = munmap(buf, page_size * mmap_window); - assert(res == 0); +static void script_spec__add(struct script_spec *s) +{ + list_add_tail(&s->node, &script_specs); +} - offset += shift; - head -= shift; - goto remap; - } +static struct script_spec *script_spec__find(const char *spec) +{ + struct script_spec *s; - size = event->header.size; + list_for_each_entry(s, &script_specs, node) + if (strcasecmp(s->spec, spec) == 0) + return s; + return NULL; +} - if (!size || process_event(event, offset, head) < 0) { +static struct script_spec *script_spec__findnew(const char *spec, + struct scripting_ops *ops) +{ + struct script_spec *s = script_spec__find(spec); - /* - * assume we lost track of the stream, check alignment, and - * increment a single u64 in the hope to catch on again 'soon'. - */ + if (s) + return s; - if (unlikely(head & 7)) - head &= ~7ULL; + s = script_spec__new(spec, ops); + if (!s) + goto out_delete_spec; - size = 8; - } + script_spec__add(s); + + return s; - head += size; +out_delete_spec: + script_spec__delete(s); + + return NULL; +} - if (offset + head < (unsigned long)perf_stat.st_size) - goto more; +int script_spec_register(const char *spec, struct scripting_ops *ops) +{ + struct script_spec *s; + + s = script_spec__find(spec); + if (s) + return -1; - rc = EXIT_SUCCESS; - close(input); + s = script_spec__findnew(spec, ops); + if (!s) + return -1; + + return 0; +} + +static struct scripting_ops *script_spec__lookup(const char *spec) +{ + struct script_spec *s = script_spec__find(spec); + if (!s) + return NULL; - return rc; + return s->ops; +} + +static void list_available_languages(void) +{ + struct script_spec *s; + + fprintf(stderr, "\n"); + fprintf(stderr, "Scripting language extensions (used in " + "perf trace -s [spec:]script.[spec]):\n\n"); + + list_for_each_entry(s, &script_specs, node) + fprintf(stderr, " %-42s [%s]\n", s->spec, s->ops->name); + + fprintf(stderr, "\n"); +} + +static int parse_scriptname(const struct option *opt __used, + const char *str, int unset __used) +{ + char spec[PATH_MAX]; + const char *script, *ext; + int len; + + if (strcmp(str, "list") == 0) { + list_available_languages(); + return 0; + } + + script = strchr(str, ':'); + if (script) { + len = script - str; + if (len >= PATH_MAX) { + fprintf(stderr, "invalid language specifier"); + return -1; + } + strncpy(spec, str, len); + spec[len] = '\0'; + scripting_ops = script_spec__lookup(spec); + if (!scripting_ops) { + fprintf(stderr, "invalid language specifier"); + return -1; + } + script++; + } else { + script = str; + ext = strchr(script, '.'); + if (!ext) { + fprintf(stderr, "invalid script extension"); + return -1; + } + scripting_ops = script_spec__lookup(++ext); + if (!scripting_ops) { + fprintf(stderr, "invalid script extension"); + return -1; + } + } + + script_name = strdup(script); + + return 0; } static const char * const annotate_usage[] = { @@ -267,13 +309,24 @@ static const struct option options[] = { "dump raw trace in ASCII"), OPT_BOOLEAN('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), + OPT_BOOLEAN('l', "latency", &latency_format, + "show latency attributes (irqs/preemption disabled, etc)"), + OPT_CALLBACK('s', "script", NULL, "name", + "script file name (lang:script name, script name, or *)", + parse_scriptname), + OPT_STRING('g', "gen-script", &generate_script_lang, "lang", + "generate perf-trace.xx script in specified language"), + OPT_END() }; int cmd_trace(int argc, const char **argv, const char *prefix __used) { - symbol__init(); - page_size = getpagesize(); + int err; + + symbol__init(0); + + setup_scripting(); argc = parse_options(argc, argv, options, annotate_usage, 0); if (argc) { @@ -287,5 +340,50 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used) setup_pager(); - return __cmd_trace(); + if (generate_script_lang) { + struct stat perf_stat; + + int input = open(input_name, O_RDONLY); + if (input < 0) { + perror("failed to open file"); + exit(-1); + } + + err = fstat(input, &perf_stat); + if (err < 0) { + perror("failed to stat file"); + exit(-1); + } + + if (!perf_stat.st_size) { + fprintf(stderr, "zero-sized file, nothing to do!\n"); + exit(0); + } + + scripting_ops = script_spec__lookup(generate_script_lang); + if (!scripting_ops) { + fprintf(stderr, "invalid language specifier"); + return -1; + } + + header = perf_header__new(); + if (header == NULL) + return -1; + + perf_header__read(header, input); + err = scripting_ops->generate_script("perf-trace"); + goto out; + } + + if (script_name) { + err = scripting_ops->start_script(script_name); + if (err) + goto out; + } + + err = __cmd_trace(); + + cleanup_scripting(); +out: + return err; } diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h index e11d8d231c3b..a3d8bf65f26c 100644 --- a/tools/perf/builtin.h +++ b/tools/perf/builtin.h @@ -15,6 +15,8 @@ extern int read_line_with_nul(char *buf, int size, FILE *file); extern int check_pager_config(const char *cmd); extern int cmd_annotate(int argc, const char **argv, const char *prefix); +extern int cmd_bench(int argc, const char **argv, const char *prefix); +extern int cmd_buildid_list(int argc, const char **argv, const char *prefix); extern int cmd_help(int argc, const char **argv, const char *prefix); extern int cmd_sched(int argc, const char **argv, const char *prefix); extern int cmd_list(int argc, const char **argv, const char *prefix); @@ -25,5 +27,7 @@ extern int cmd_timechart(int argc, const char **argv, const char *prefix); extern int cmd_top(int argc, const char **argv, const char *prefix); extern int cmd_trace(int argc, const char **argv, const char *prefix); extern int cmd_version(int argc, const char **argv, const char *prefix); +extern int cmd_probe(int argc, const char **argv, const char *prefix); +extern int cmd_kmem(int argc, const char **argv, const char *prefix); #endif diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt index 00326e230d87..02b09ea17a3e 100644 --- a/tools/perf/command-list.txt +++ b/tools/perf/command-list.txt @@ -3,6 +3,8 @@ # command name category [deprecated] [common] # perf-annotate mainporcelain common +perf-bench mainporcelain common +perf-buildid-list mainporcelain common perf-list mainporcelain common perf-sched mainporcelain common perf-record mainporcelain common @@ -11,3 +13,5 @@ perf-stat mainporcelain common perf-timechart mainporcelain common perf-top mainporcelain common perf-trace mainporcelain common +perf-probe mainporcelain common +perf-kmem mainporcelain common diff --git a/tools/perf/design.txt b/tools/perf/design.txt index fdd42a824c98..f000c30877ac 100644 --- a/tools/perf/design.txt +++ b/tools/perf/design.txt @@ -137,6 +137,8 @@ enum sw_event_ids { PERF_COUNT_SW_CPU_MIGRATIONS = 4, PERF_COUNT_SW_PAGE_FAULTS_MIN = 5, PERF_COUNT_SW_PAGE_FAULTS_MAJ = 6, + PERF_COUNT_SW_ALIGNMENT_FAULTS = 7, + PERF_COUNT_SW_EMULATION_FAULTS = 8, }; Counters of the type PERF_TYPE_TRACEPOINT are available when the ftrace event diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 19fc7feb9d59..cf64049bc9bd 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -14,6 +14,7 @@ #include "util/run-command.h" #include "util/parse-events.h" #include "util/string.h" +#include "util/debugfs.h" const char perf_usage_string[] = "perf [--version] [--help] COMMAND [ARGS]"; @@ -89,8 +90,8 @@ static int handle_options(const char*** argv, int* argc, int* envchanged) /* * Check remaining flags. */ - if (!prefixcmp(cmd, "--exec-path")) { - cmd += 11; + if (!prefixcmp(cmd, CMD_EXEC_PATH)) { + cmd += strlen(CMD_EXEC_PATH); if (*cmd == '=') perf_set_argv_exec_path(cmd + 1); else { @@ -117,8 +118,8 @@ static int handle_options(const char*** argv, int* argc, int* envchanged) (*argv)++; (*argc)--; handled++; - } else if (!prefixcmp(cmd, "--perf-dir=")) { - setenv(PERF_DIR_ENVIRONMENT, cmd + 10, 1); + } else if (!prefixcmp(cmd, CMD_PERF_DIR)) { + setenv(PERF_DIR_ENVIRONMENT, cmd + strlen(CMD_PERF_DIR), 1); if (envchanged) *envchanged = 1; } else if (!strcmp(cmd, "--work-tree")) { @@ -131,8 +132,8 @@ static int handle_options(const char*** argv, int* argc, int* envchanged) *envchanged = 1; (*argv)++; (*argc)--; - } else if (!prefixcmp(cmd, "--work-tree=")) { - setenv(PERF_WORK_TREE_ENVIRONMENT, cmd + 12, 1); + } else if (!prefixcmp(cmd, CMD_WORK_TREE)) { + setenv(PERF_WORK_TREE_ENVIRONMENT, cmd + strlen(CMD_WORK_TREE), 1); if (envchanged) *envchanged = 1; } else if (!strcmp(cmd, "--debugfs-dir")) { @@ -146,8 +147,8 @@ static int handle_options(const char*** argv, int* argc, int* envchanged) *envchanged = 1; (*argv)++; (*argc)--; - } else if (!prefixcmp(cmd, "--debugfs-dir=")) { - strncpy(debugfs_mntpt, cmd + 14, MAXPATHLEN); + } else if (!prefixcmp(cmd, CMD_DEBUGFS_DIR)) { + strncpy(debugfs_mntpt, cmd + strlen(CMD_DEBUGFS_DIR), MAXPATHLEN); debugfs_mntpt[MAXPATHLEN - 1] = '\0'; if (envchanged) *envchanged = 1; @@ -284,17 +285,21 @@ static void handle_internal_command(int argc, const char **argv) { const char *cmd = argv[0]; static struct cmd_struct commands[] = { - { "help", cmd_help, 0 }, - { "list", cmd_list, 0 }, - { "record", cmd_record, 0 }, - { "report", cmd_report, 0 }, - { "stat", cmd_stat, 0 }, - { "timechart", cmd_timechart, 0 }, - { "top", cmd_top, 0 }, - { "annotate", cmd_annotate, 0 }, - { "version", cmd_version, 0 }, - { "trace", cmd_trace, 0 }, - { "sched", cmd_sched, 0 }, + { "buildid-list", cmd_buildid_list, 0 }, + { "help", cmd_help, 0 }, + { "list", cmd_list, 0 }, + { "record", cmd_record, 0 }, + { "report", cmd_report, 0 }, + { "bench", cmd_bench, 0 }, + { "stat", cmd_stat, 0 }, + { "timechart", cmd_timechart, 0 }, + { "top", cmd_top, 0 }, + { "annotate", cmd_annotate, 0 }, + { "version", cmd_version, 0 }, + { "trace", cmd_trace, 0 }, + { "sched", cmd_sched, 0 }, + { "probe", cmd_probe, 0 }, + { "kmem", cmd_kmem, 0 }, }; unsigned int i; static const char ext[] = STRIP_EXTENSION; @@ -382,45 +387,12 @@ static int run_argv(int *argcp, const char ***argv) /* mini /proc/mounts parser: searching for "^blah /mount/point debugfs" */ static void get_debugfs_mntpt(void) { - FILE *file; - char fs_type[100]; - char debugfs[MAXPATHLEN]; + const char *path = debugfs_find_mountpoint(); - /* - * try the standard location - */ - if (valid_debugfs_mount("/sys/kernel/debug/") == 0) { - strcpy(debugfs_mntpt, "/sys/kernel/debug/"); - return; - } - - /* - * try the sane location - */ - if (valid_debugfs_mount("/debug/") == 0) { - strcpy(debugfs_mntpt, "/debug/"); - return; - } - - /* - * give up and parse /proc/mounts - */ - file = fopen("/proc/mounts", "r"); - if (file == NULL) - return; - - while (fscanf(file, "%*s %" - STR(MAXPATHLEN) - "s %99s %*s %*d %*d\n", - debugfs, fs_type) == 2) { - if (strcmp(fs_type, "debugfs") == 0) - break; - } - fclose(file); - if (strcmp(fs_type, "debugfs") == 0) { - strncpy(debugfs_mntpt, debugfs, MAXPATHLEN); - debugfs_mntpt[MAXPATHLEN - 1] = '\0'; - } + if (path) + strncpy(debugfs_mntpt, path, sizeof(debugfs_mntpt)); + else + debugfs_mntpt[0] = '\0'; } int main(int argc, const char **argv) diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 8cc4623afd6f..454d5d55f32d 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -47,6 +47,18 @@ #define cpu_relax() asm volatile("":::"memory") #endif +#ifdef __alpha__ +#include "../../arch/alpha/include/asm/unistd.h" +#define rmb() asm volatile("mb" ::: "memory") +#define cpu_relax() asm volatile("" ::: "memory") +#endif + +#ifdef __ia64__ +#include "../../arch/ia64/include/asm/unistd.h" +#define rmb() asm volatile ("mf" ::: "memory") +#define cpu_relax() asm volatile ("hint @pause" ::: "memory") +#endif + #include <time.h> #include <unistd.h> #include <sys/types.h> diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/Context.c b/tools/perf/scripts/perl/Perf-Trace-Util/Context.c new file mode 100644 index 000000000000..af78d9a52a7d --- /dev/null +++ b/tools/perf/scripts/perl/Perf-Trace-Util/Context.c @@ -0,0 +1,134 @@ +/* + * This file was generated automatically by ExtUtils::ParseXS version 2.18_02 from the + * contents of Context.xs. Do not edit this file, edit Context.xs instead. + * + * ANY CHANGES MADE HERE WILL BE LOST! + * + */ + +#line 1 "Context.xs" +/* + * Context.xs. XS interfaces for perf trace. + * + * Copyright (C) 2009 Tom Zanussi <tzanussi@gmail.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + */ + +#include "EXTERN.h" +#include "perl.h" +#include "XSUB.h" +#include "../../../util/trace-event-perl.h" + +#ifndef PERL_UNUSED_VAR +# define PERL_UNUSED_VAR(var) if (0) var = var +#endif + +#line 41 "Context.c" + +XS(XS_Perf__Trace__Context_common_pc); /* prototype to pass -Wmissing-prototypes */ +XS(XS_Perf__Trace__Context_common_pc) +{ +#ifdef dVAR + dVAR; dXSARGS; +#else + dXSARGS; +#endif + if (items != 1) + Perl_croak(aTHX_ "Usage: %s(%s)", "Perf::Trace::Context::common_pc", "context"); + PERL_UNUSED_VAR(cv); /* -W */ + { + struct scripting_context * context = INT2PTR(struct scripting_context *,SvIV(ST(0))); + int RETVAL; + dXSTARG; + + RETVAL = common_pc(context); + XSprePUSH; PUSHi((IV)RETVAL); + } + XSRETURN(1); +} + + +XS(XS_Perf__Trace__Context_common_flags); /* prototype to pass -Wmissing-prototypes */ +XS(XS_Perf__Trace__Context_common_flags) +{ +#ifdef dVAR + dVAR; dXSARGS; +#else + dXSARGS; +#endif + if (items != 1) + Perl_croak(aTHX_ "Usage: %s(%s)", "Perf::Trace::Context::common_flags", "context"); + PERL_UNUSED_VAR(cv); /* -W */ + { + struct scripting_context * context = INT2PTR(struct scripting_context *,SvIV(ST(0))); + int RETVAL; + dXSTARG; + + RETVAL = common_flags(context); + XSprePUSH; PUSHi((IV)RETVAL); + } + XSRETURN(1); +} + + +XS(XS_Perf__Trace__Context_common_lock_depth); /* prototype to pass -Wmissing-prototypes */ +XS(XS_Perf__Trace__Context_common_lock_depth) +{ +#ifdef dVAR + dVAR; dXSARGS; +#else + dXSARGS; +#endif + if (items != 1) + Perl_croak(aTHX_ "Usage: %s(%s)", "Perf::Trace::Context::common_lock_depth", "context"); + PERL_UNUSED_VAR(cv); /* -W */ + { + struct scripting_context * context = INT2PTR(struct scripting_context *,SvIV(ST(0))); + int RETVAL; + dXSTARG; + + RETVAL = common_lock_depth(context); + XSprePUSH; PUSHi((IV)RETVAL); + } + XSRETURN(1); +} + +#ifdef __cplusplus +extern "C" +#endif +XS(boot_Perf__Trace__Context); /* prototype to pass -Wmissing-prototypes */ +XS(boot_Perf__Trace__Context) +{ +#ifdef dVAR + dVAR; dXSARGS; +#else + dXSARGS; +#endif + const char* file = __FILE__; + + PERL_UNUSED_VAR(cv); /* -W */ + PERL_UNUSED_VAR(items); /* -W */ + XS_VERSION_BOOTCHECK ; + + newXSproto("Perf::Trace::Context::common_pc", XS_Perf__Trace__Context_common_pc, file, "$"); + newXSproto("Perf::Trace::Context::common_flags", XS_Perf__Trace__Context_common_flags, file, "$"); + newXSproto("Perf::Trace::Context::common_lock_depth", XS_Perf__Trace__Context_common_lock_depth, file, "$"); + if (PL_unitcheckav) + call_list(PL_scopestack_ix, PL_unitcheckav); + XSRETURN_YES; +} + diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/Context.xs b/tools/perf/scripts/perl/Perf-Trace-Util/Context.xs new file mode 100644 index 000000000000..fb78006c165e --- /dev/null +++ b/tools/perf/scripts/perl/Perf-Trace-Util/Context.xs @@ -0,0 +1,41 @@ +/* + * Context.xs. XS interfaces for perf trace. + * + * Copyright (C) 2009 Tom Zanussi <tzanussi@gmail.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + */ + +#include "EXTERN.h" +#include "perl.h" +#include "XSUB.h" +#include "../../../util/trace-event-perl.h" + +MODULE = Perf::Trace::Context PACKAGE = Perf::Trace::Context +PROTOTYPES: ENABLE + +int +common_pc(context) + struct scripting_context * context + +int +common_flags(context) + struct scripting_context * context + +int +common_lock_depth(context) + struct scripting_context * context + diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/Makefile.PL b/tools/perf/scripts/perl/Perf-Trace-Util/Makefile.PL new file mode 100644 index 000000000000..decdeb0f6789 --- /dev/null +++ b/tools/perf/scripts/perl/Perf-Trace-Util/Makefile.PL @@ -0,0 +1,17 @@ +use 5.010000; +use ExtUtils::MakeMaker; +# See lib/ExtUtils/MakeMaker.pm for details of how to influence +# the contents of the Makefile that is written. +WriteMakefile( + NAME => 'Perf::Trace::Context', + VERSION_FROM => 'lib/Perf/Trace/Context.pm', # finds $VERSION + PREREQ_PM => {}, # e.g., Module::Name => 1.1 + ($] >= 5.005 ? ## Add these new keywords supported since 5.005 + (ABSTRACT_FROM => 'lib/Perf/Trace/Context.pm', # retrieve abstract from module + AUTHOR => 'Tom Zanussi <tzanussi@gmail.com>') : ()), + LIBS => [''], # e.g., '-lm' + DEFINE => '-I ../..', # e.g., '-DHAVE_SOMETHING' + INC => '-I.', # e.g., '-I. -I/usr/include/other' + # Un-comment this if you add C files to link with later: + OBJECT => 'Context.o', # link all the C files too +); diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/README b/tools/perf/scripts/perl/Perf-Trace-Util/README new file mode 100644 index 000000000000..9a9707630791 --- /dev/null +++ b/tools/perf/scripts/perl/Perf-Trace-Util/README @@ -0,0 +1,59 @@ +Perf-Trace-Util version 0.01 +============================ + +This module contains utility functions for use with perf trace. + +Core.pm and Util.pm are pure Perl modules; Core.pm contains routines +that the core perf support for Perl calls on and should always be +'used', while Util.pm contains useful but optional utility functions +that scripts may want to use. Context.pm contains the Perl->C +interface that allows scripts to access data in the embedding perf +executable; scripts wishing to do that should 'use Context.pm'. + +The Perl->C perf interface is completely driven by Context.xs. If you +want to add new Perl functions that end up accessing C data in the +perf executable, you add desciptions of the new functions here. +scripting_context is a pointer to the perf data in the perf executable +that you want to access - it's passed as the second parameter, +$context, to all handler functions. + +After you do that: + + perl Makefile.PL # to create a Makefile for the next step + make # to create Context.c + + edit Context.c to add const to the char* file = __FILE__ line in + XS(boot_Perf__Trace__Context) to silence a warning/error. + + You can delete the Makefile, object files and anything else that was + generated e.g. blib and shared library, etc, except for of course + Context.c + + You should then be able to run the normal perf make as usual. + +INSTALLATION + +Building perf with perf trace Perl scripting should install this +module in the right place. + +You should make sure libperl and ExtUtils/Embed.pm are installed first +e.g. apt-get install libperl-dev or yum install perl-ExtUtils-Embed. + +DEPENDENCIES + +This module requires these other modules and libraries: + + None + +COPYRIGHT AND LICENCE + +Copyright (C) 2009 by Tom Zanussi <tzanussi@gmail.com> + +This library is free software; you can redistribute it and/or modify +it under the same terms as Perl itself, either Perl version 5.10.0 or, +at your option, any later version of Perl 5 you may have available. + +Alternatively, this software may be distributed under the terms of the +GNU General Public License ("GPL") version 2 as published by the Free +Software Foundation. + diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Context.pm b/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Context.pm new file mode 100644 index 000000000000..6c7f3659cb17 --- /dev/null +++ b/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Context.pm @@ -0,0 +1,55 @@ +package Perf::Trace::Context; + +use 5.010000; +use strict; +use warnings; + +require Exporter; + +our @ISA = qw(Exporter); + +our %EXPORT_TAGS = ( 'all' => [ qw( +) ] ); + +our @EXPORT_OK = ( @{ $EXPORT_TAGS{'all'} } ); + +our @EXPORT = qw( + common_pc common_flags common_lock_depth +); + +our $VERSION = '0.01'; + +require XSLoader; +XSLoader::load('Perf::Trace::Context', $VERSION); + +1; +__END__ +=head1 NAME + +Perf::Trace::Context - Perl extension for accessing functions in perf. + +=head1 SYNOPSIS + + use Perf::Trace::Context; + +=head1 SEE ALSO + +Perf (trace) documentation + +=head1 AUTHOR + +Tom Zanussi, E<lt>tzanussi@gmail.com<gt> + +=head1 COPYRIGHT AND LICENSE + +Copyright (C) 2009 by Tom Zanussi + +This library is free software; you can redistribute it and/or modify +it under the same terms as Perl itself, either Perl version 5.10.0 or, +at your option, any later version of Perl 5 you may have available. + +Alternatively, this software may be distributed under the terms of the +GNU General Public License ("GPL") version 2 as published by the Free +Software Foundation. + +=cut diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Core.pm b/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Core.pm new file mode 100644 index 000000000000..9df376a9f629 --- /dev/null +++ b/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Core.pm @@ -0,0 +1,192 @@ +package Perf::Trace::Core; + +use 5.010000; +use strict; +use warnings; + +require Exporter; + +our @ISA = qw(Exporter); + +our %EXPORT_TAGS = ( 'all' => [ qw( +) ] ); + +our @EXPORT_OK = ( @{ $EXPORT_TAGS{'all'} } ); + +our @EXPORT = qw( +define_flag_field define_flag_value flag_str dump_flag_fields +define_symbolic_field define_symbolic_value symbol_str dump_symbolic_fields +trace_flag_str +); + +our $VERSION = '0.01'; + +my %trace_flags = (0x00 => "NONE", + 0x01 => "IRQS_OFF", + 0x02 => "IRQS_NOSUPPORT", + 0x04 => "NEED_RESCHED", + 0x08 => "HARDIRQ", + 0x10 => "SOFTIRQ"); + +sub trace_flag_str +{ + my ($value) = @_; + + my $string; + + my $print_delim = 0; + + foreach my $idx (sort {$a <=> $b} keys %trace_flags) { + if (!$value && !$idx) { + $string .= "NONE"; + last; + } + + if ($idx && ($value & $idx) == $idx) { + if ($print_delim) { + $string .= " | "; + } + $string .= "$trace_flags{$idx}"; + $print_delim = 1; + $value &= ~$idx; + } + } + + return $string; +} + +my %flag_fields; +my %symbolic_fields; + +sub flag_str +{ + my ($event_name, $field_name, $value) = @_; + + my $string; + + if ($flag_fields{$event_name}{$field_name}) { + my $print_delim = 0; + foreach my $idx (sort {$a <=> $b} keys %{$flag_fields{$event_name}{$field_name}{"values"}}) { + if (!$value && !$idx) { + $string .= "$flag_fields{$event_name}{$field_name}{'values'}{$idx}"; + last; + } + if ($idx && ($value & $idx) == $idx) { + if ($print_delim && $flag_fields{$event_name}{$field_name}{'delim'}) { + $string .= " $flag_fields{$event_name}{$field_name}{'delim'} "; + } + $string .= "$flag_fields{$event_name}{$field_name}{'values'}{$idx}"; + $print_delim = 1; + $value &= ~$idx; + } + } + } + + return $string; +} + +sub define_flag_field +{ + my ($event_name, $field_name, $delim) = @_; + + $flag_fields{$event_name}{$field_name}{"delim"} = $delim; +} + +sub define_flag_value +{ + my ($event_name, $field_name, $value, $field_str) = @_; + + $flag_fields{$event_name}{$field_name}{"values"}{$value} = $field_str; +} + +sub dump_flag_fields +{ + for my $event (keys %flag_fields) { + print "event $event:\n"; + for my $field (keys %{$flag_fields{$event}}) { + print " field: $field:\n"; + print " delim: $flag_fields{$event}{$field}{'delim'}\n"; + foreach my $idx (sort {$a <=> $b} keys %{$flag_fields{$event}{$field}{"values"}}) { + print " value $idx: $flag_fields{$event}{$field}{'values'}{$idx}\n"; + } + } + } +} + +sub symbol_str +{ + my ($event_name, $field_name, $value) = @_; + + if ($symbolic_fields{$event_name}{$field_name}) { + foreach my $idx (sort {$a <=> $b} keys %{$symbolic_fields{$event_name}{$field_name}{"values"}}) { + if (!$value && !$idx) { + return "$symbolic_fields{$event_name}{$field_name}{'values'}{$idx}"; + last; + } + if ($value == $idx) { + return "$symbolic_fields{$event_name}{$field_name}{'values'}{$idx}"; + } + } + } + + return undef; +} + +sub define_symbolic_field +{ + my ($event_name, $field_name) = @_; + + # nothing to do, really +} + +sub define_symbolic_value +{ + my ($event_name, $field_name, $value, $field_str) = @_; + + $symbolic_fields{$event_name}{$field_name}{"values"}{$value} = $field_str; +} + +sub dump_symbolic_fields +{ + for my $event (keys %symbolic_fields) { + print "event $event:\n"; + for my $field (keys %{$symbolic_fields{$event}}) { + print " field: $field:\n"; + foreach my $idx (sort {$a <=> $b} keys %{$symbolic_fields{$event}{$field}{"values"}}) { + print " value $idx: $symbolic_fields{$event}{$field}{'values'}{$idx}\n"; + } + } + } +} + +1; +__END__ +=head1 NAME + +Perf::Trace::Core - Perl extension for perf trace + +=head1 SYNOPSIS + + use Perf::Trace::Core + +=head1 SEE ALSO + +Perf (trace) documentation + +=head1 AUTHOR + +Tom Zanussi, E<lt>tzanussi@gmail.com<gt> + +=head1 COPYRIGHT AND LICENSE + +Copyright (C) 2009 by Tom Zanussi + +This library is free software; you can redistribute it and/or modify +it under the same terms as Perl itself, either Perl version 5.10.0 or, +at your option, any later version of Perl 5 you may have available. + +Alternatively, this software may be distributed under the terms of the +GNU General Public License ("GPL") version 2 as published by the Free +Software Foundation. + +=cut diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm b/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm new file mode 100644 index 000000000000..052f132ced24 --- /dev/null +++ b/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm @@ -0,0 +1,88 @@ +package Perf::Trace::Util; + +use 5.010000; +use strict; +use warnings; + +require Exporter; + +our @ISA = qw(Exporter); + +our %EXPORT_TAGS = ( 'all' => [ qw( +) ] ); + +our @EXPORT_OK = ( @{ $EXPORT_TAGS{'all'} } ); + +our @EXPORT = qw( +avg nsecs nsecs_secs nsecs_nsecs nsecs_usecs print_nsecs +); + +our $VERSION = '0.01'; + +sub avg +{ + my ($total, $n) = @_; + + return $total / $n; +} + +my $NSECS_PER_SEC = 1000000000; + +sub nsecs +{ + my ($secs, $nsecs) = @_; + + return $secs * $NSECS_PER_SEC + $nsecs; +} + +sub nsecs_secs { + my ($nsecs) = @_; + + return $nsecs / $NSECS_PER_SEC; +} + +sub nsecs_nsecs { + my ($nsecs) = @_; + + return $nsecs - nsecs_secs($nsecs); +} + +sub nsecs_str { + my ($nsecs) = @_; + + my $str = sprintf("%5u.%09u", nsecs_secs($nsecs), nsecs_nsecs($nsecs)); + + return $str; +} + +1; +__END__ +=head1 NAME + +Perf::Trace::Util - Perl extension for perf trace + +=head1 SYNOPSIS + + use Perf::Trace::Util; + +=head1 SEE ALSO + +Perf (trace) documentation + +=head1 AUTHOR + +Tom Zanussi, E<lt>tzanussi@gmail.com<gt> + +=head1 COPYRIGHT AND LICENSE + +Copyright (C) 2009 by Tom Zanussi + +This library is free software; you can redistribute it and/or modify +it under the same terms as Perl itself, either Perl version 5.10.0 or, +at your option, any later version of Perl 5 you may have available. + +Alternatively, this software may be distributed under the terms of the +GNU General Public License ("GPL") version 2 as published by the Free +Software Foundation. + +=cut diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/typemap b/tools/perf/scripts/perl/Perf-Trace-Util/typemap new file mode 100644 index 000000000000..840836804aa7 --- /dev/null +++ b/tools/perf/scripts/perl/Perf-Trace-Util/typemap @@ -0,0 +1 @@ +struct scripting_context * T_PTR diff --git a/tools/perf/scripts/perl/bin/check-perf-trace-record b/tools/perf/scripts/perl/bin/check-perf-trace-record new file mode 100644 index 000000000000..c7ec5de2f535 --- /dev/null +++ b/tools/perf/scripts/perl/bin/check-perf-trace-record @@ -0,0 +1,7 @@ +#!/bin/bash +perf record -c 1 -f -a -M -R -e kmem:kmalloc -e irq:softirq_entry + + + + + diff --git a/tools/perf/scripts/perl/bin/check-perf-trace-report b/tools/perf/scripts/perl/bin/check-perf-trace-report new file mode 100644 index 000000000000..89948b015020 --- /dev/null +++ b/tools/perf/scripts/perl/bin/check-perf-trace-report @@ -0,0 +1,5 @@ +#!/bin/bash +perf trace -s ~/libexec/perf-core/scripts/perl/check-perf-trace.pl + + + diff --git a/tools/perf/scripts/perl/bin/rw-by-file-record b/tools/perf/scripts/perl/bin/rw-by-file-record new file mode 100644 index 000000000000..b25056ebf963 --- /dev/null +++ b/tools/perf/scripts/perl/bin/rw-by-file-record @@ -0,0 +1,2 @@ +#!/bin/bash +perf record -c 1 -f -a -M -R -e syscalls:sys_enter_read -e syscalls:sys_enter_write diff --git a/tools/perf/scripts/perl/bin/rw-by-file-report b/tools/perf/scripts/perl/bin/rw-by-file-report new file mode 100644 index 000000000000..f5dcf9cb5bd2 --- /dev/null +++ b/tools/perf/scripts/perl/bin/rw-by-file-report @@ -0,0 +1,5 @@ +#!/bin/bash +perf trace -s ~/libexec/perf-core/scripts/perl/rw-by-file.pl + + + diff --git a/tools/perf/scripts/perl/bin/rw-by-pid-record b/tools/perf/scripts/perl/bin/rw-by-pid-record new file mode 100644 index 000000000000..8903979c5b6c --- /dev/null +++ b/tools/perf/scripts/perl/bin/rw-by-pid-record @@ -0,0 +1,2 @@ +#!/bin/bash +perf record -c 1 -f -a -M -R -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write diff --git a/tools/perf/scripts/perl/bin/rw-by-pid-report b/tools/perf/scripts/perl/bin/rw-by-pid-report new file mode 100644 index 000000000000..cea16f78a3a2 --- /dev/null +++ b/tools/perf/scripts/perl/bin/rw-by-pid-report @@ -0,0 +1,5 @@ +#!/bin/bash +perf trace -s ~/libexec/perf-core/scripts/perl/rw-by-pid.pl + + + diff --git a/tools/perf/scripts/perl/bin/wakeup-latency-record b/tools/perf/scripts/perl/bin/wakeup-latency-record new file mode 100644 index 000000000000..6abedda911a4 --- /dev/null +++ b/tools/perf/scripts/perl/bin/wakeup-latency-record @@ -0,0 +1,6 @@ +#!/bin/bash +perf record -c 1 -f -a -M -R -e sched:sched_switch -e sched:sched_wakeup + + + + diff --git a/tools/perf/scripts/perl/bin/wakeup-latency-report b/tools/perf/scripts/perl/bin/wakeup-latency-report new file mode 100644 index 000000000000..85769dc456eb --- /dev/null +++ b/tools/perf/scripts/perl/bin/wakeup-latency-report @@ -0,0 +1,5 @@ +#!/bin/bash +perf trace -s ~/libexec/perf-core/scripts/perl/wakeup-latency.pl + + + diff --git a/tools/perf/scripts/perl/bin/workqueue-stats-record b/tools/perf/scripts/perl/bin/workqueue-stats-record new file mode 100644 index 000000000000..fce6637b19ba --- /dev/null +++ b/tools/perf/scripts/perl/bin/workqueue-stats-record @@ -0,0 +1,2 @@ +#!/bin/bash +perf record -c 1 -f -a -M -R -e workqueue:workqueue_creation -e workqueue:workqueue_destruction -e workqueue:workqueue_execution -e workqueue:workqueue_insertion diff --git a/tools/perf/scripts/perl/bin/workqueue-stats-report b/tools/perf/scripts/perl/bin/workqueue-stats-report new file mode 100644 index 000000000000..aa68435be926 --- /dev/null +++ b/tools/perf/scripts/perl/bin/workqueue-stats-report @@ -0,0 +1,6 @@ +#!/bin/bash +perf trace -s ~/libexec/perf-core/scripts/perl/workqueue-stats.pl + + + + diff --git a/tools/perf/scripts/perl/check-perf-trace.pl b/tools/perf/scripts/perl/check-perf-trace.pl new file mode 100644 index 000000000000..4e7dc0a407a5 --- /dev/null +++ b/tools/perf/scripts/perl/check-perf-trace.pl @@ -0,0 +1,106 @@ +# perf trace event handlers, generated by perf trace -g perl +# (c) 2009, Tom Zanussi <tzanussi@gmail.com> +# Licensed under the terms of the GNU GPL License version 2 + +# This script tests basic functionality such as flag and symbol +# strings, common_xxx() calls back into perf, begin, end, unhandled +# events, etc. Basically, if this script runs successfully and +# displays expected results, perl scripting support should be ok. + +use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/Perf-Trace-Util/lib"; +use lib "./Perf-Trace-Util/lib"; +use Perf::Trace::Core; +use Perf::Trace::Context; +use Perf::Trace::Util; + +sub trace_begin +{ + print "trace_begin\n"; +} + +sub trace_end +{ + print "trace_end\n"; + + print_unhandled(); +} + +sub irq::softirq_entry +{ + my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, + $common_pid, $common_comm, + $vec) = @_; + + print_header($event_name, $common_cpu, $common_secs, $common_nsecs, + $common_pid, $common_comm); + + print_uncommon($context); + + printf("vec=%s\n", + symbol_str("irq::softirq_entry", "vec", $vec)); +} + +sub kmem::kmalloc +{ + my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, + $common_pid, $common_comm, + $call_site, $ptr, $bytes_req, $bytes_alloc, + $gfp_flags) = @_; + + print_header($event_name, $common_cpu, $common_secs, $common_nsecs, + $common_pid, $common_comm); + + print_uncommon($context); + + printf("call_site=%p, ptr=%p, bytes_req=%u, bytes_alloc=%u, ". + "gfp_flags=%s\n", + $call_site, $ptr, $bytes_req, $bytes_alloc, + + flag_str("kmem::kmalloc", "gfp_flags", $gfp_flags)); +} + +# print trace fields not included in handler args +sub print_uncommon +{ + my ($context) = @_; + + printf("common_preempt_count=%d, common_flags=%s, common_lock_depth=%d, ", + common_pc($context), trace_flag_str(common_flags($context)), + common_lock_depth($context)); + +} + +my %unhandled; + +sub print_unhandled +{ + if ((scalar keys %unhandled) == 0) { + return; + } + + print "\nunhandled events:\n\n"; + + printf("%-40s %10s\n", "event", "count"); + printf("%-40s %10s\n", "----------------------------------------", + "-----------"); + + foreach my $event_name (keys %unhandled) { + printf("%-40s %10d\n", $event_name, $unhandled{$event_name}); + } +} + +sub trace_unhandled +{ + my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, + $common_pid, $common_comm) = @_; + + $unhandled{$event_name}++; +} + +sub print_header +{ + my ($event_name, $cpu, $secs, $nsecs, $pid, $comm) = @_; + + printf("%-20s %5u %05u.%09u %8u %-20s ", + $event_name, $cpu, $secs, $nsecs, $pid, $comm); +} diff --git a/tools/perf/scripts/perl/rw-by-file.pl b/tools/perf/scripts/perl/rw-by-file.pl new file mode 100644 index 000000000000..61f91561d848 --- /dev/null +++ b/tools/perf/scripts/perl/rw-by-file.pl @@ -0,0 +1,105 @@ +#!/usr/bin/perl -w +# (c) 2009, Tom Zanussi <tzanussi@gmail.com> +# Licensed under the terms of the GNU GPL License version 2 + +# Display r/w activity for files read/written to for a given program + +# The common_* event handler fields are the most useful fields common to +# all events. They don't necessarily correspond to the 'common_*' fields +# in the status files. Those fields not available as handler params can +# be retrieved via script functions of the form get_common_*(). + +use 5.010000; +use strict; +use warnings; + +use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/Perf-Trace-Util/lib"; +use lib "./Perf-Trace-Util/lib"; +use Perf::Trace::Core; +use Perf::Trace::Util; + +# change this to the comm of the program you're interested in +my $for_comm = "perf"; + +my %reads; +my %writes; + +sub syscalls::sys_enter_read +{ + my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, + $common_pid, $common_comm, $nr, $fd, $buf, $count) = @_; + + if ($common_comm eq $for_comm) { + $reads{$fd}{bytes_requested} += $count; + $reads{$fd}{total_reads}++; + } +} + +sub syscalls::sys_enter_write +{ + my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, + $common_pid, $common_comm, $nr, $fd, $buf, $count) = @_; + + if ($common_comm eq $for_comm) { + $writes{$fd}{bytes_written} += $count; + $writes{$fd}{total_writes}++; + } +} + +sub trace_end +{ + printf("file read counts for $for_comm:\n\n"); + + printf("%6s %10s %10s\n", "fd", "# reads", "bytes_requested"); + printf("%6s %10s %10s\n", "------", "----------", "-----------"); + + foreach my $fd (sort {$reads{$b}{bytes_requested} <=> + $reads{$a}{bytes_requested}} keys %reads) { + my $total_reads = $reads{$fd}{total_reads}; + my $bytes_requested = $reads{$fd}{bytes_requested}; + printf("%6u %10u %10u\n", $fd, $total_reads, $bytes_requested); + } + + printf("\nfile write counts for $for_comm:\n\n"); + + printf("%6s %10s %10s\n", "fd", "# writes", "bytes_written"); + printf("%6s %10s %10s\n", "------", "----------", "-----------"); + + foreach my $fd (sort {$writes{$b}{bytes_written} <=> + $writes{$a}{bytes_written}} keys %writes) { + my $total_writes = $writes{$fd}{total_writes}; + my $bytes_written = $writes{$fd}{bytes_written}; + printf("%6u %10u %10u\n", $fd, $total_writes, $bytes_written); + } + + print_unhandled(); +} + +my %unhandled; + +sub print_unhandled +{ + if ((scalar keys %unhandled) == 0) { + return; + } + + print "\nunhandled events:\n\n"; + + printf("%-40s %10s\n", "event", "count"); + printf("%-40s %10s\n", "----------------------------------------", + "-----------"); + + foreach my $event_name (keys %unhandled) { + printf("%-40s %10d\n", $event_name, $unhandled{$event_name}); + } +} + +sub trace_unhandled +{ + my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, + $common_pid, $common_comm) = @_; + + $unhandled{$event_name}++; +} + + diff --git a/tools/perf/scripts/perl/rw-by-pid.pl b/tools/perf/scripts/perl/rw-by-pid.pl new file mode 100644 index 000000000000..da601fae1a00 --- /dev/null +++ b/tools/perf/scripts/perl/rw-by-pid.pl @@ -0,0 +1,170 @@ +#!/usr/bin/perl -w +# (c) 2009, Tom Zanussi <tzanussi@gmail.com> +# Licensed under the terms of the GNU GPL License version 2 + +# Display r/w activity for all processes + +# The common_* event handler fields are the most useful fields common to +# all events. They don't necessarily correspond to the 'common_*' fields +# in the status files. Those fields not available as handler params can +# be retrieved via script functions of the form get_common_*(). + +use 5.010000; +use strict; +use warnings; + +use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/Perf-Trace-Util/lib"; +use lib "./Perf-Trace-Util/lib"; +use Perf::Trace::Core; +use Perf::Trace::Util; + +my %reads; +my %writes; + +sub syscalls::sys_exit_read +{ + my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, + $common_pid, $common_comm, + $nr, $ret) = @_; + + if ($ret > 0) { + $reads{$common_pid}{bytes_read} += $ret; + } else { + if (!defined ($reads{$common_pid}{bytes_read})) { + $reads{$common_pid}{bytes_read} = 0; + } + $reads{$common_pid}{errors}{$ret}++; + } +} + +sub syscalls::sys_enter_read +{ + my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, + $common_pid, $common_comm, + $nr, $fd, $buf, $count) = @_; + + $reads{$common_pid}{bytes_requested} += $count; + $reads{$common_pid}{total_reads}++; + $reads{$common_pid}{comm} = $common_comm; +} + +sub syscalls::sys_exit_write +{ + my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, + $common_pid, $common_comm, + $nr, $ret) = @_; + + if ($ret <= 0) { + $writes{$common_pid}{errors}{$ret}++; + } +} + +sub syscalls::sys_enter_write +{ + my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, + $common_pid, $common_comm, + $nr, $fd, $buf, $count) = @_; + + $writes{$common_pid}{bytes_written} += $count; + $writes{$common_pid}{total_writes}++; + $writes{$common_pid}{comm} = $common_comm; +} + +sub trace_end +{ + printf("read counts by pid:\n\n"); + + printf("%6s %20s %10s %10s %10s\n", "pid", "comm", + "# reads", "bytes_requested", "bytes_read"); + printf("%6s %-20s %10s %10s %10s\n", "------", "--------------------", + "-----------", "----------", "----------"); + + foreach my $pid (sort {$reads{$b}{bytes_read} <=> + $reads{$a}{bytes_read}} keys %reads) { + my $comm = $reads{$pid}{comm}; + my $total_reads = $reads{$pid}{total_reads}; + my $bytes_requested = $reads{$pid}{bytes_requested}; + my $bytes_read = $reads{$pid}{bytes_read}; + + printf("%6s %-20s %10s %10s %10s\n", $pid, $comm, + $total_reads, $bytes_requested, $bytes_read); + } + + printf("\nfailed reads by pid:\n\n"); + + printf("%6s %20s %6s %10s\n", "pid", "comm", "error #", "# errors"); + printf("%6s %20s %6s %10s\n", "------", "--------------------", + "------", "----------"); + + foreach my $pid (keys %reads) { + my $comm = $reads{$pid}{comm}; + foreach my $err (sort {$reads{$b}{comm} cmp $reads{$a}{comm}} + keys %{$reads{$pid}{errors}}) { + my $errors = $reads{$pid}{errors}{$err}; + + printf("%6d %-20s %6d %10s\n", $pid, $comm, $err, $errors); + } + } + + printf("\nwrite counts by pid:\n\n"); + + printf("%6s %20s %10s %10s\n", "pid", "comm", + "# writes", "bytes_written"); + printf("%6s %-20s %10s %10s\n", "------", "--------------------", + "-----------", "----------"); + + foreach my $pid (sort {$writes{$b}{bytes_written} <=> + $writes{$a}{bytes_written}} keys %writes) { + my $comm = $writes{$pid}{comm}; + my $total_writes = $writes{$pid}{total_writes}; + my $bytes_written = $writes{$pid}{bytes_written}; + + printf("%6s %-20s %10s %10s\n", $pid, $comm, + $total_writes, $bytes_written); + } + + printf("\nfailed writes by pid:\n\n"); + + printf("%6s %20s %6s %10s\n", "pid", "comm", "error #", "# errors"); + printf("%6s %20s %6s %10s\n", "------", "--------------------", + "------", "----------"); + + foreach my $pid (keys %writes) { + my $comm = $writes{$pid}{comm}; + foreach my $err (sort {$writes{$b}{comm} cmp $writes{$a}{comm}} + keys %{$writes{$pid}{errors}}) { + my $errors = $writes{$pid}{errors}{$err}; + + printf("%6d %-20s %6d %10s\n", $pid, $comm, $err, $errors); + } + } + + print_unhandled(); +} + +my %unhandled; + +sub print_unhandled +{ + if ((scalar keys %unhandled) == 0) { + return; + } + + print "\nunhandled events:\n\n"; + + printf("%-40s %10s\n", "event", "count"); + printf("%-40s %10s\n", "----------------------------------------", + "-----------"); + + foreach my $event_name (keys %unhandled) { + printf("%-40s %10d\n", $event_name, $unhandled{$event_name}); + } +} + +sub trace_unhandled +{ + my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, + $common_pid, $common_comm) = @_; + + $unhandled{$event_name}++; +} diff --git a/tools/perf/scripts/perl/wakeup-latency.pl b/tools/perf/scripts/perl/wakeup-latency.pl new file mode 100644 index 000000000000..ed58ef284e23 --- /dev/null +++ b/tools/perf/scripts/perl/wakeup-latency.pl @@ -0,0 +1,103 @@ +#!/usr/bin/perl -w +# (c) 2009, Tom Zanussi <tzanussi@gmail.com> +# Licensed under the terms of the GNU GPL License version 2 + +# Display avg/min/max wakeup latency + +# The common_* event handler fields are the most useful fields common to +# all events. They don't necessarily correspond to the 'common_*' fields +# in the status files. Those fields not available as handler params can +# be retrieved via script functions of the form get_common_*(). + +use 5.010000; +use strict; +use warnings; + +use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/Perf-Trace-Util/lib"; +use lib "./Perf-Trace-Util/lib"; +use Perf::Trace::Core; +use Perf::Trace::Util; + +my %last_wakeup; + +my $max_wakeup_latency; +my $min_wakeup_latency; +my $total_wakeup_latency; +my $total_wakeups; + +sub sched::sched_switch +{ + my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, + $common_pid, $common_comm, + $prev_comm, $prev_pid, $prev_prio, $prev_state, $next_comm, $next_pid, + $next_prio) = @_; + + my $wakeup_ts = $last_wakeup{$common_cpu}{ts}; + if ($wakeup_ts) { + my $switch_ts = nsecs($common_secs, $common_nsecs); + my $wakeup_latency = $switch_ts - $wakeup_ts; + if ($wakeup_latency > $max_wakeup_latency) { + $max_wakeup_latency = $wakeup_latency; + } + if ($wakeup_latency < $min_wakeup_latency) { + $min_wakeup_latency = $wakeup_latency; + } + $total_wakeup_latency += $wakeup_latency; + $total_wakeups++; + } + $last_wakeup{$common_cpu}{ts} = 0; +} + +sub sched::sched_wakeup +{ + my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, + $common_pid, $common_comm, + $comm, $pid, $prio, $success, $target_cpu) = @_; + + $last_wakeup{$target_cpu}{ts} = nsecs($common_secs, $common_nsecs); +} + +sub trace_begin +{ + $min_wakeup_latency = 1000000000; + $max_wakeup_latency = 0; +} + +sub trace_end +{ + printf("wakeup_latency stats:\n\n"); + print "total_wakeups: $total_wakeups\n"; + printf("avg_wakeup_latency (ns): %u\n", + avg($total_wakeup_latency, $total_wakeups)); + printf("min_wakeup_latency (ns): %u\n", $min_wakeup_latency); + printf("max_wakeup_latency (ns): %u\n", $max_wakeup_latency); + + print_unhandled(); +} + +my %unhandled; + +sub print_unhandled +{ + if ((scalar keys %unhandled) == 0) { + return; + } + + print "\nunhandled events:\n\n"; + + printf("%-40s %10s\n", "event", "count"); + printf("%-40s %10s\n", "----------------------------------------", + "-----------"); + + foreach my $event_name (keys %unhandled) { + printf("%-40s %10d\n", $event_name, $unhandled{$event_name}); + } +} + +sub trace_unhandled +{ + my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, + $common_pid, $common_comm) = @_; + + $unhandled{$event_name}++; +} diff --git a/tools/perf/scripts/perl/workqueue-stats.pl b/tools/perf/scripts/perl/workqueue-stats.pl new file mode 100644 index 000000000000..511302c8a494 --- /dev/null +++ b/tools/perf/scripts/perl/workqueue-stats.pl @@ -0,0 +1,129 @@ +#!/usr/bin/perl -w +# (c) 2009, Tom Zanussi <tzanussi@gmail.com> +# Licensed under the terms of the GNU GPL License version 2 + +# Displays workqueue stats +# +# Usage: +# +# perf record -c 1 -f -a -R -e workqueue:workqueue_creation -e +# workqueue:workqueue_destruction -e workqueue:workqueue_execution +# -e workqueue:workqueue_insertion +# +# perf trace -p -s tools/perf/scripts/perl/workqueue-stats.pl + +use 5.010000; +use strict; +use warnings; + +use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/Perf-Trace-Util/lib"; +use lib "./Perf-Trace-Util/lib"; +use Perf::Trace::Core; +use Perf::Trace::Util; + +my @cpus; + +sub workqueue::workqueue_destruction +{ + my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, + $common_pid, $common_comm, + $thread_comm, $thread_pid) = @_; + + $cpus[$common_cpu]{$thread_pid}{destroyed}++; + $cpus[$common_cpu]{$thread_pid}{comm} = $thread_comm; +} + +sub workqueue::workqueue_creation +{ + my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, + $common_pid, $common_comm, + $thread_comm, $thread_pid, $cpu) = @_; + + $cpus[$common_cpu]{$thread_pid}{created}++; + $cpus[$common_cpu]{$thread_pid}{comm} = $thread_comm; +} + +sub workqueue::workqueue_execution +{ + my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, + $common_pid, $common_comm, + $thread_comm, $thread_pid, $func) = @_; + + $cpus[$common_cpu]{$thread_pid}{executed}++; + $cpus[$common_cpu]{$thread_pid}{comm} = $thread_comm; +} + +sub workqueue::workqueue_insertion +{ + my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, + $common_pid, $common_comm, + $thread_comm, $thread_pid, $func) = @_; + + $cpus[$common_cpu]{$thread_pid}{inserted}++; + $cpus[$common_cpu]{$thread_pid}{comm} = $thread_comm; +} + +sub trace_end +{ + print "workqueue work stats:\n\n"; + my $cpu = 0; + printf("%3s %6s %6s\t%-20s\n", "cpu", "ins", "exec", "name"); + printf("%3s %6s %6s\t%-20s\n", "---", "---", "----", "----"); + foreach my $pidhash (@cpus) { + while ((my $pid, my $wqhash) = each %$pidhash) { + my $ins = $$wqhash{'inserted'}; + my $exe = $$wqhash{'executed'}; + my $comm = $$wqhash{'comm'}; + if ($ins || $exe) { + printf("%3u %6u %6u\t%-20s\n", $cpu, $ins, $exe, $comm); + } + } + $cpu++; + } + + $cpu = 0; + print "\nworkqueue lifecycle stats:\n\n"; + printf("%3s %6s %6s\t%-20s\n", "cpu", "created", "destroyed", "name"); + printf("%3s %6s %6s\t%-20s\n", "---", "-------", "---------", "----"); + foreach my $pidhash (@cpus) { + while ((my $pid, my $wqhash) = each %$pidhash) { + my $created = $$wqhash{'created'}; + my $destroyed = $$wqhash{'destroyed'}; + my $comm = $$wqhash{'comm'}; + if ($created || $destroyed) { + printf("%3u %6u %6u\t%-20s\n", $cpu, $created, $destroyed, + $comm); + } + } + $cpu++; + } + + print_unhandled(); +} + +my %unhandled; + +sub print_unhandled +{ + if ((scalar keys %unhandled) == 0) { + return; + } + + print "\nunhandled events:\n\n"; + + printf("%-40s %10s\n", "event", "count"); + printf("%-40s %10s\n", "----------------------------------------", + "-----------"); + + foreach my $event_name (keys %unhandled) { + printf("%-40s %10d\n", $event_name, $unhandled{$event_name}); + } +} + +sub trace_unhandled +{ + my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, + $common_pid, $common_comm) = @_; + + $unhandled{$event_name}++; +} diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h index 6f8ea9d210b6..918eb376abe3 100644 --- a/tools/perf/util/cache.h +++ b/tools/perf/util/cache.h @@ -1,10 +1,15 @@ -#ifndef CACHE_H -#define CACHE_H +#ifndef __PERF_CACHE_H +#define __PERF_CACHE_H #include "util.h" #include "strbuf.h" #include "../perf.h" +#define CMD_EXEC_PATH "--exec-path" +#define CMD_PERF_DIR "--perf-dir=" +#define CMD_WORK_TREE "--work-tree=" +#define CMD_DEBUGFS_DIR "--debugfs-dir=" + #define PERF_DIR_ENVIRONMENT "PERF_DIR" #define PERF_WORK_TREE_ENVIRONMENT "PERF_WORK_TREE" #define DEFAULT_PERF_DIR_ENVIRONMENT ".perf" @@ -117,4 +122,4 @@ extern char *perf_pathdup(const char *fmt, ...) extern size_t strlcpy(char *dest, const char *src, size_t size); -#endif /* CACHE_H */ +#endif /* __PERF_CACHE_H */ diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 3b8380f1b478..b3b71258272a 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -206,7 +206,7 @@ fill_node(struct callchain_node *node, struct ip_callchain *chain, } node->val_nr = chain->nr - start; if (!node->val_nr) - printf("Warning: empty node in callchain tree\n"); + pr_warning("Warning: empty node in callchain tree\n"); } static void diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 43cf3ea9e088..ad4626de4c2b 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -58,4 +58,4 @@ static inline u64 cumul_hits(struct callchain_node *node) int register_callchain_param(struct callchain_param *param); void append_chain(struct callchain_node *root, struct ip_callchain *chain, struct symbol **syms); -#endif +#endif /* __PERF_CALLCHAIN_H */ diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h index 58d597564b99..24e8809210bb 100644 --- a/tools/perf/util/color.h +++ b/tools/perf/util/color.h @@ -1,5 +1,5 @@ -#ifndef COLOR_H -#define COLOR_H +#ifndef __PERF_COLOR_H +#define __PERF_COLOR_H /* "\033[1;38;5;2xx;48;5;2xxm\0" is 23 bytes */ #define COLOR_MAXLEN 24 @@ -39,4 +39,4 @@ int color_fwrite_lines(FILE *fp, const char *color, size_t count, const char *bu int percent_color_fprintf(FILE *fp, const char *fmt, double percent); const char *get_percent_color(double percent); -#endif /* COLOR_H */ +#endif /* __PERF_COLOR_H */ diff --git a/tools/perf/util/ctype.c b/tools/perf/util/ctype.c index 0b791bd346bc..35073621e5de 100644 --- a/tools/perf/util/ctype.c +++ b/tools/perf/util/ctype.c @@ -29,3 +29,11 @@ unsigned char sane_ctype[256] = { A, A, A, A, A, A, A, A, A, A, A, R, R, P, P, 0, /* 112..127 */ /* Nothing in the 128.. range */ }; + +const char *graph_line = + "_____________________________________________________________________" + "_____________________________________________________________________"; +const char *graph_dotted_line = + "---------------------------------------------------------------------" + "---------------------------------------------------------------------" + "---------------------------------------------------------------------"; diff --git a/tools/perf/util/data_map.c b/tools/perf/util/data_map.c new file mode 100644 index 000000000000..ca0bedf637c2 --- /dev/null +++ b/tools/perf/util/data_map.c @@ -0,0 +1,291 @@ +#include "data_map.h" +#include "symbol.h" +#include "util.h" +#include "debug.h" + + +static struct perf_file_handler *curr_handler; +static unsigned long mmap_window = 32; +static char __cwd[PATH_MAX]; + +static int process_event_stub(event_t *event __used) +{ + dump_printf(": unhandled!\n"); + return 0; +} + +void register_perf_file_handler(struct perf_file_handler *handler) +{ + if (!handler->process_sample_event) + handler->process_sample_event = process_event_stub; + if (!handler->process_mmap_event) + handler->process_mmap_event = process_event_stub; + if (!handler->process_comm_event) + handler->process_comm_event = process_event_stub; + if (!handler->process_fork_event) + handler->process_fork_event = process_event_stub; + if (!handler->process_exit_event) + handler->process_exit_event = process_event_stub; + if (!handler->process_lost_event) + handler->process_lost_event = process_event_stub; + if (!handler->process_read_event) + handler->process_read_event = process_event_stub; + if (!handler->process_throttle_event) + handler->process_throttle_event = process_event_stub; + if (!handler->process_unthrottle_event) + handler->process_unthrottle_event = process_event_stub; + + curr_handler = handler; +} + +static const char *event__name[] = { + [0] = "TOTAL", + [PERF_RECORD_MMAP] = "MMAP", + [PERF_RECORD_LOST] = "LOST", + [PERF_RECORD_COMM] = "COMM", + [PERF_RECORD_EXIT] = "EXIT", + [PERF_RECORD_THROTTLE] = "THROTTLE", + [PERF_RECORD_UNTHROTTLE] = "UNTHROTTLE", + [PERF_RECORD_FORK] = "FORK", + [PERF_RECORD_READ] = "READ", + [PERF_RECORD_SAMPLE] = "SAMPLE", +}; + +unsigned long event__total[PERF_RECORD_MAX]; + +void event__print_totals(void) +{ + int i; + for (i = 0; i < PERF_RECORD_MAX; ++i) + pr_info("%10s events: %10ld\n", + event__name[i], event__total[i]); +} + +static int +process_event(event_t *event, unsigned long offset, unsigned long head) +{ + trace_event(event); + + if (event->header.type < PERF_RECORD_MAX) { + dump_printf("%p [%p]: PERF_RECORD_%s", + (void *)(offset + head), + (void *)(long)(event->header.size), + event__name[event->header.type]); + ++event__total[0]; + ++event__total[event->header.type]; + } + + switch (event->header.type) { + case PERF_RECORD_SAMPLE: + return curr_handler->process_sample_event(event); + case PERF_RECORD_MMAP: + return curr_handler->process_mmap_event(event); + case PERF_RECORD_COMM: + return curr_handler->process_comm_event(event); + case PERF_RECORD_FORK: + return curr_handler->process_fork_event(event); + case PERF_RECORD_EXIT: + return curr_handler->process_exit_event(event); + case PERF_RECORD_LOST: + return curr_handler->process_lost_event(event); + case PERF_RECORD_READ: + return curr_handler->process_read_event(event); + case PERF_RECORD_THROTTLE: + return curr_handler->process_throttle_event(event); + case PERF_RECORD_UNTHROTTLE: + return curr_handler->process_unthrottle_event(event); + default: + curr_handler->total_unknown++; + return -1; + } +} + +int perf_header__read_build_ids(int input, off_t offset, off_t size) +{ + struct build_id_event bev; + char filename[PATH_MAX]; + off_t limit = offset + size; + int err = -1; + + while (offset < limit) { + struct dso *dso; + ssize_t len; + + if (read(input, &bev, sizeof(bev)) != sizeof(bev)) + goto out; + + len = bev.header.size - sizeof(bev); + if (read(input, filename, len) != len) + goto out; + + dso = dsos__findnew(filename); + if (dso != NULL) + dso__set_build_id(dso, &bev.build_id); + + offset += bev.header.size; + } + err = 0; +out: + return err; +} + +int mmap_dispatch_perf_file(struct perf_header **pheader, + const char *input_name, + int force, + int full_paths, + int *cwdlen, + char **cwd) +{ + int err; + struct perf_header *header; + unsigned long head, shift; + unsigned long offset = 0; + struct stat input_stat; + size_t page_size; + u64 sample_type; + event_t *event; + uint32_t size; + int input; + char *buf; + + if (curr_handler == NULL) { + pr_debug("Forgot to register perf file handler\n"); + return -EINVAL; + } + + page_size = getpagesize(); + + input = open(input_name, O_RDONLY); + if (input < 0) { + pr_err("Failed to open file: %s", input_name); + if (!strcmp(input_name, "perf.data")) + pr_err(" (try 'perf record' first)"); + pr_err("\n"); + return -errno; + } + + if (fstat(input, &input_stat) < 0) { + pr_err("failed to stat file"); + err = -errno; + goto out_close; + } + + err = -EACCES; + if (!force && input_stat.st_uid && (input_stat.st_uid != geteuid())) { + pr_err("file: %s not owned by current user or root\n", + input_name); + goto out_close; + } + + if (input_stat.st_size == 0) { + pr_info("zero-sized file, nothing to do!\n"); + goto done; + } + + err = -ENOMEM; + header = perf_header__new(); + if (header == NULL) + goto out_close; + + err = perf_header__read(header, input); + if (err < 0) + goto out_delete; + *pheader = header; + head = header->data_offset; + + sample_type = perf_header__sample_type(header); + + err = -EINVAL; + if (curr_handler->sample_type_check && + curr_handler->sample_type_check(sample_type) < 0) + goto out_delete; + + if (!full_paths) { + if (getcwd(__cwd, sizeof(__cwd)) == NULL) { + pr_err("failed to get the current directory\n"); + err = -errno; + goto out_delete; + } + *cwd = __cwd; + *cwdlen = strlen(*cwd); + } else { + *cwd = NULL; + *cwdlen = 0; + } + + shift = page_size * (head / page_size); + offset += shift; + head -= shift; + +remap: + buf = mmap(NULL, page_size * mmap_window, PROT_READ, + MAP_SHARED, input, offset); + if (buf == MAP_FAILED) { + pr_err("failed to mmap file\n"); + err = -errno; + goto out_delete; + } + +more: + event = (event_t *)(buf + head); + + size = event->header.size; + if (!size) + size = 8; + + if (head + event->header.size >= page_size * mmap_window) { + int munmap_ret; + + shift = page_size * (head / page_size); + + munmap_ret = munmap(buf, page_size * mmap_window); + assert(munmap_ret == 0); + + offset += shift; + head -= shift; + goto remap; + } + + size = event->header.size; + + dump_printf("\n%p [%p]: event: %d\n", + (void *)(offset + head), + (void *)(long)event->header.size, + event->header.type); + + if (!size || process_event(event, offset, head) < 0) { + + dump_printf("%p [%p]: skipping unknown header type: %d\n", + (void *)(offset + head), + (void *)(long)(event->header.size), + event->header.type); + + /* + * assume we lost track of the stream, check alignment, and + * increment a single u64 in the hope to catch on again 'soon'. + */ + + if (unlikely(head & 7)) + head &= ~7ULL; + + size = 8; + } + + head += size; + + if (offset + head >= header->data_offset + header->data_size) + goto done; + + if (offset + head < (unsigned long)input_stat.st_size) + goto more; + +done: + err = 0; +out_close: + close(input); + + return err; +out_delete: + perf_header__delete(header); + goto out_close; +} diff --git a/tools/perf/util/data_map.h b/tools/perf/util/data_map.h new file mode 100644 index 000000000000..3180ff7e3633 --- /dev/null +++ b/tools/perf/util/data_map.h @@ -0,0 +1,32 @@ +#ifndef __PERF_DATAMAP_H +#define __PERF_DATAMAP_H + +#include "event.h" +#include "header.h" + +typedef int (*event_type_handler_t)(event_t *); + +struct perf_file_handler { + event_type_handler_t process_sample_event; + event_type_handler_t process_mmap_event; + event_type_handler_t process_comm_event; + event_type_handler_t process_fork_event; + event_type_handler_t process_exit_event; + event_type_handler_t process_lost_event; + event_type_handler_t process_read_event; + event_type_handler_t process_throttle_event; + event_type_handler_t process_unthrottle_event; + int (*sample_type_check)(u64 sample_type); + unsigned long total_unknown; +}; + +void register_perf_file_handler(struct perf_file_handler *handler); +int mmap_dispatch_perf_file(struct perf_header **pheader, + const char *input_name, + int force, + int full_paths, + int *cwdlen, + char **cwd); +int perf_header__read_build_ids(int input, off_t offset, off_t file_size); + +#endif diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index e8ca98fe0bd4..28d520d5a1fb 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -13,12 +13,12 @@ int verbose = 0; int dump_trace = 0; -int eprintf(const char *fmt, ...) +int eprintf(int level, const char *fmt, ...) { va_list args; int ret = 0; - if (verbose) { + if (verbose >= level) { va_start(args, fmt); ret = vfprintf(stderr, fmt, args); va_end(args); diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index 437eea58ce40..c6c24c522dea 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -1,8 +1,15 @@ /* For debugging general purposes */ +#ifndef __PERF_DEBUG_H +#define __PERF_DEBUG_H + +#include "event.h" extern int verbose; extern int dump_trace; -int eprintf(const char *fmt, ...) __attribute__((format(printf, 1, 2))); +int eprintf(int level, + const char *fmt, ...) __attribute__((format(printf, 2, 3))); int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2))); void trace_event(event_t *event); + +#endif /* __PERF_DEBUG_H */ diff --git a/tools/perf/util/debugfs.c b/tools/perf/util/debugfs.c new file mode 100644 index 000000000000..06b73ee02c49 --- /dev/null +++ b/tools/perf/util/debugfs.c @@ -0,0 +1,241 @@ +#include "util.h" +#include "debugfs.h" +#include "cache.h" + +static int debugfs_premounted; +static char debugfs_mountpoint[MAX_PATH+1]; + +static const char *debugfs_known_mountpoints[] = { + "/sys/kernel/debug/", + "/debug/", + 0, +}; + +/* use this to force a umount */ +void debugfs_force_cleanup(void) +{ + debugfs_find_mountpoint(); + debugfs_premounted = 0; + debugfs_umount(); +} + +/* construct a full path to a debugfs element */ +int debugfs_make_path(const char *element, char *buffer, int size) +{ + int len; + + if (strlen(debugfs_mountpoint) == 0) { + buffer[0] = '\0'; + return -1; + } + + len = strlen(debugfs_mountpoint) + strlen(element) + 1; + if (len >= size) + return len+1; + + snprintf(buffer, size-1, "%s/%s", debugfs_mountpoint, element); + return 0; +} + +static int debugfs_found; + +/* find the path to the mounted debugfs */ +const char *debugfs_find_mountpoint(void) +{ + const char **ptr; + char type[100]; + FILE *fp; + + if (debugfs_found) + return (const char *) debugfs_mountpoint; + + ptr = debugfs_known_mountpoints; + while (*ptr) { + if (debugfs_valid_mountpoint(*ptr) == 0) { + debugfs_found = 1; + strcpy(debugfs_mountpoint, *ptr); + return debugfs_mountpoint; + } + ptr++; + } + + /* give up and parse /proc/mounts */ + fp = fopen("/proc/mounts", "r"); + if (fp == NULL) + die("Can't open /proc/mounts for read"); + + while (fscanf(fp, "%*s %" + STR(MAX_PATH) + "s %99s %*s %*d %*d\n", + debugfs_mountpoint, type) == 2) { + if (strcmp(type, "debugfs") == 0) + break; + } + fclose(fp); + + if (strcmp(type, "debugfs") != 0) + return NULL; + + debugfs_found = 1; + + return debugfs_mountpoint; +} + +/* verify that a mountpoint is actually a debugfs instance */ + +int debugfs_valid_mountpoint(const char *debugfs) +{ + struct statfs st_fs; + + if (statfs(debugfs, &st_fs) < 0) + return -ENOENT; + else if (st_fs.f_type != (long) DEBUGFS_MAGIC) + return -ENOENT; + + return 0; +} + + +int debugfs_valid_entry(const char *path) +{ + struct stat st; + + if (stat(path, &st)) + return -errno; + + return 0; +} + +/* mount the debugfs somewhere */ + +int debugfs_mount(const char *mountpoint) +{ + char mountcmd[128]; + + /* see if it's already mounted */ + if (debugfs_find_mountpoint()) { + debugfs_premounted = 1; + return 0; + } + + /* if not mounted and no argument */ + if (mountpoint == NULL) { + /* see if environment variable set */ + mountpoint = getenv(PERF_DEBUGFS_ENVIRONMENT); + /* if no environment variable, use default */ + if (mountpoint == NULL) + mountpoint = "/sys/kernel/debug"; + } + + /* save the mountpoint */ + strncpy(debugfs_mountpoint, mountpoint, sizeof(debugfs_mountpoint)); + + /* mount it */ + snprintf(mountcmd, sizeof(mountcmd), + "/bin/mount -t debugfs debugfs %s", mountpoint); + return system(mountcmd); +} + +/* umount the debugfs */ + +int debugfs_umount(void) +{ + char umountcmd[128]; + int ret; + + /* if it was already mounted, leave it */ + if (debugfs_premounted) + return 0; + + /* make sure it's a valid mount point */ + ret = debugfs_valid_mountpoint(debugfs_mountpoint); + if (ret) + return ret; + + snprintf(umountcmd, sizeof(umountcmd), + "/bin/umount %s", debugfs_mountpoint); + return system(umountcmd); +} + +int debugfs_write(const char *entry, const char *value) +{ + char path[MAX_PATH+1]; + int ret, count; + int fd; + + /* construct the path */ + snprintf(path, sizeof(path), "%s/%s", debugfs_mountpoint, entry); + + /* verify that it exists */ + ret = debugfs_valid_entry(path); + if (ret) + return ret; + + /* get how many chars we're going to write */ + count = strlen(value); + + /* open the debugfs entry */ + fd = open(path, O_RDWR); + if (fd < 0) + return -errno; + + while (count > 0) { + /* write it */ + ret = write(fd, value, count); + if (ret <= 0) { + if (ret == EAGAIN) + continue; + close(fd); + return -errno; + } + count -= ret; + } + + /* close it */ + close(fd); + + /* return success */ + return 0; +} + +/* + * read a debugfs entry + * returns the number of chars read or a negative errno + */ +int debugfs_read(const char *entry, char *buffer, size_t size) +{ + char path[MAX_PATH+1]; + int ret; + int fd; + + /* construct the path */ + snprintf(path, sizeof(path), "%s/%s", debugfs_mountpoint, entry); + + /* verify that it exists */ + ret = debugfs_valid_entry(path); + if (ret) + return ret; + + /* open the debugfs entry */ + fd = open(path, O_RDONLY); + if (fd < 0) + return -errno; + + do { + /* read it */ + ret = read(fd, buffer, size); + if (ret == 0) { + close(fd); + return EOF; + } + } while (ret < 0 && errno == EAGAIN); + + /* close it */ + close(fd); + + /* make *sure* there's a null character at the end */ + buffer[ret] = '\0'; + + /* return the number of chars read */ + return ret; +} diff --git a/tools/perf/util/debugfs.h b/tools/perf/util/debugfs.h new file mode 100644 index 000000000000..3cd14f9ae784 --- /dev/null +++ b/tools/perf/util/debugfs.h @@ -0,0 +1,25 @@ +#ifndef __DEBUGFS_H__ +#define __DEBUGFS_H__ + +#include <sys/mount.h> + +#ifndef MAX_PATH +# define MAX_PATH 256 +#endif + +#ifndef STR +# define _STR(x) #x +# define STR(x) _STR(x) +#endif + +extern const char *debugfs_find_mountpoint(void); +extern int debugfs_valid_mountpoint(const char *debugfs); +extern int debugfs_valid_entry(const char *path); +extern int debugfs_mount(const char *mountpoint); +extern int debugfs_umount(void); +extern int debugfs_write(const char *entry, const char *value); +extern int debugfs_read(const char *entry, char *buffer, size_t size); +extern void debugfs_force_cleanup(void); +extern int debugfs_make_path(const char *element, char *buffer, int size); + +#endif /* __DEBUGFS_H__ */ diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c new file mode 100644 index 000000000000..414b89d1bde9 --- /dev/null +++ b/tools/perf/util/event.c @@ -0,0 +1,312 @@ +#include <linux/types.h> +#include "event.h" +#include "debug.h" +#include "string.h" +#include "thread.h" + +static pid_t event__synthesize_comm(pid_t pid, int full, + int (*process)(event_t *event)) +{ + event_t ev; + char filename[PATH_MAX]; + char bf[BUFSIZ]; + FILE *fp; + size_t size = 0; + DIR *tasks; + struct dirent dirent, *next; + pid_t tgid = 0; + + snprintf(filename, sizeof(filename), "/proc/%d/status", pid); + + fp = fopen(filename, "r"); + if (fp == NULL) { +out_race: + /* + * We raced with a task exiting - just return: + */ + pr_debug("couldn't open %s\n", filename); + return 0; + } + + memset(&ev.comm, 0, sizeof(ev.comm)); + while (!ev.comm.comm[0] || !ev.comm.pid) { + if (fgets(bf, sizeof(bf), fp) == NULL) + goto out_failure; + + if (memcmp(bf, "Name:", 5) == 0) { + char *name = bf + 5; + while (*name && isspace(*name)) + ++name; + size = strlen(name) - 1; + memcpy(ev.comm.comm, name, size++); + } else if (memcmp(bf, "Tgid:", 5) == 0) { + char *tgids = bf + 5; + while (*tgids && isspace(*tgids)) + ++tgids; + tgid = ev.comm.pid = atoi(tgids); + } + } + + ev.comm.header.type = PERF_RECORD_COMM; + size = ALIGN(size, sizeof(u64)); + ev.comm.header.size = sizeof(ev.comm) - (sizeof(ev.comm.comm) - size); + + if (!full) { + ev.comm.tid = pid; + + process(&ev); + goto out_fclose; + } + + snprintf(filename, sizeof(filename), "/proc/%d/task", pid); + + tasks = opendir(filename); + if (tasks == NULL) + goto out_race; + + while (!readdir_r(tasks, &dirent, &next) && next) { + char *end; + pid = strtol(dirent.d_name, &end, 10); + if (*end) + continue; + + ev.comm.tid = pid; + + process(&ev); + } + closedir(tasks); + +out_fclose: + fclose(fp); + return tgid; + +out_failure: + pr_warning("couldn't get COMM and pgid, malformed %s\n", filename); + return -1; +} + +static int event__synthesize_mmap_events(pid_t pid, pid_t tgid, + int (*process)(event_t *event)) +{ + char filename[PATH_MAX]; + FILE *fp; + + snprintf(filename, sizeof(filename), "/proc/%d/maps", pid); + + fp = fopen(filename, "r"); + if (fp == NULL) { + /* + * We raced with a task exiting - just return: + */ + pr_debug("couldn't open %s\n", filename); + return -1; + } + + while (1) { + char bf[BUFSIZ], *pbf = bf; + event_t ev = { + .header = { .type = PERF_RECORD_MMAP }, + }; + int n; + size_t size; + if (fgets(bf, sizeof(bf), fp) == NULL) + break; + + /* 00400000-0040c000 r-xp 00000000 fd:01 41038 /bin/cat */ + n = hex2u64(pbf, &ev.mmap.start); + if (n < 0) + continue; + pbf += n + 1; + n = hex2u64(pbf, &ev.mmap.len); + if (n < 0) + continue; + pbf += n + 3; + if (*pbf == 'x') { /* vm_exec */ + char *execname = strchr(bf, '/'); + + /* Catch VDSO */ + if (execname == NULL) + execname = strstr(bf, "[vdso]"); + + if (execname == NULL) + continue; + + size = strlen(execname); + execname[size - 1] = '\0'; /* Remove \n */ + memcpy(ev.mmap.filename, execname, size); + size = ALIGN(size, sizeof(u64)); + ev.mmap.len -= ev.mmap.start; + ev.mmap.header.size = (sizeof(ev.mmap) - + (sizeof(ev.mmap.filename) - size)); + ev.mmap.pid = tgid; + ev.mmap.tid = pid; + + process(&ev); + } + } + + fclose(fp); + return 0; +} + +int event__synthesize_thread(pid_t pid, int (*process)(event_t *event)) +{ + pid_t tgid = event__synthesize_comm(pid, 1, process); + if (tgid == -1) + return -1; + return event__synthesize_mmap_events(pid, tgid, process); +} + +void event__synthesize_threads(int (*process)(event_t *event)) +{ + DIR *proc; + struct dirent dirent, *next; + + proc = opendir("/proc"); + + while (!readdir_r(proc, &dirent, &next) && next) { + char *end; + pid_t pid = strtol(dirent.d_name, &end, 10); + + if (*end) /* only interested in proper numerical dirents */ + continue; + + event__synthesize_thread(pid, process); + } + + closedir(proc); +} + +char *event__cwd; +int event__cwdlen; + +struct events_stats event__stats; + +int event__process_comm(event_t *self) +{ + struct thread *thread = threads__findnew(self->comm.pid); + + dump_printf(": %s:%d\n", self->comm.comm, self->comm.pid); + + if (thread == NULL || thread__set_comm(thread, self->comm.comm)) { + dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n"); + return -1; + } + + return 0; +} + +int event__process_lost(event_t *self) +{ + dump_printf(": id:%Ld: lost:%Ld\n", self->lost.id, self->lost.lost); + event__stats.lost += self->lost.lost; + return 0; +} + +int event__process_mmap(event_t *self) +{ + struct thread *thread = threads__findnew(self->mmap.pid); + struct map *map = map__new(&self->mmap, MAP__FUNCTION, + event__cwd, event__cwdlen); + + dump_printf(" %d/%d: [%p(%p) @ %p]: %s\n", + self->mmap.pid, self->mmap.tid, + (void *)(long)self->mmap.start, + (void *)(long)self->mmap.len, + (void *)(long)self->mmap.pgoff, + self->mmap.filename); + + if (thread == NULL || map == NULL) + dump_printf("problem processing PERF_RECORD_MMAP, skipping event.\n"); + else + thread__insert_map(thread, map); + + return 0; +} + +int event__process_task(event_t *self) +{ + struct thread *thread = threads__findnew(self->fork.pid); + struct thread *parent = threads__findnew(self->fork.ppid); + + dump_printf("(%d:%d):(%d:%d)\n", self->fork.pid, self->fork.tid, + self->fork.ppid, self->fork.ptid); + /* + * A thread clone will have the same PID for both parent and child. + */ + if (thread == parent) + return 0; + + if (self->header.type == PERF_RECORD_EXIT) + return 0; + + if (thread == NULL || parent == NULL || + thread__fork(thread, parent) < 0) { + dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n"); + return -1; + } + + return 0; +} + +void thread__find_addr_location(struct thread *self, u8 cpumode, + enum map_type type, u64 addr, + struct addr_location *al, + symbol_filter_t filter) +{ + struct thread *thread = al->thread = self; + + al->addr = addr; + + if (cpumode & PERF_RECORD_MISC_KERNEL) { + al->level = 'k'; + thread = kthread; + } else if (cpumode & PERF_RECORD_MISC_USER) + al->level = '.'; + else { + al->level = 'H'; + al->map = NULL; + al->sym = NULL; + return; + } +try_again: + al->map = thread__find_map(thread, type, al->addr); + if (al->map == NULL) { + /* + * If this is outside of all known maps, and is a negative + * address, try to look it up in the kernel dso, as it might be + * a vsyscall or vdso (which executes in user-mode). + * + * XXX This is nasty, we should have a symbol list in the + * "[vdso]" dso, but for now lets use the old trick of looking + * in the whole kernel symbol list. + */ + if ((long long)al->addr < 0 && thread != kthread) { + thread = kthread; + goto try_again; + } + al->sym = NULL; + } else { + al->addr = al->map->map_ip(al->map, al->addr); + al->sym = map__find_symbol(al->map, al->addr, filter); + } +} + +int event__preprocess_sample(const event_t *self, struct addr_location *al, + symbol_filter_t filter) +{ + u8 cpumode = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + struct thread *thread = threads__findnew(self->ip.pid); + + if (thread == NULL) + return -1; + + dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid); + + thread__find_addr_location(thread, cpumode, MAP__FUNCTION, + self->ip.ip, al, filter); + dump_printf(" ...... dso: %s\n", + al->map ? al->map->dso->long_name : + al->level == 'H' ? "[hypervisor]" : "<not found>"); + return 0; +} diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 2c9c26d6ded0..a4cc8105cf67 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -1,14 +1,10 @@ #ifndef __PERF_RECORD_H #define __PERF_RECORD_H + #include "../perf.h" #include "util.h" #include <linux/list.h> - -enum { - SHOW_KERNEL = 1, - SHOW_USER = 2, - SHOW_HV = 4, -}; +#include <linux/rbtree.h> /* * PERF_SAMPLE_IP | PERF_SAMPLE_TID | * @@ -65,6 +61,13 @@ struct sample_event{ u64 array[]; }; +#define BUILD_ID_SIZE 20 + +struct build_id_event { + struct perf_event_header header; + u8 build_id[ALIGN(BUILD_ID_SIZE, sizeof(u64))]; + char filename[]; +}; typedef union event_union { struct perf_event_header header; @@ -77,12 +80,30 @@ typedef union event_union { struct sample_event sample; } event_t; +struct events_stats { + unsigned long total; + unsigned long lost; +}; + +void event__print_totals(void); + +enum map_type { + MAP__FUNCTION = 0, + + MAP__NR_TYPES, +}; + struct map { - struct list_head node; + union { + struct rb_node rb_node; + struct list_head node; + }; u64 start; u64 end; + enum map_type type; u64 pgoff; u64 (*map_ip)(struct map *, u64); + u64 (*unmap_ip)(struct map *, u64); struct dso *dso; }; @@ -91,14 +112,48 @@ static inline u64 map__map_ip(struct map *map, u64 ip) return ip - map->start + map->pgoff; } -static inline u64 vdso__map_ip(struct map *map __used, u64 ip) +static inline u64 map__unmap_ip(struct map *map, u64 ip) +{ + return ip + map->start - map->pgoff; +} + +static inline u64 identity__map_ip(struct map *map __used, u64 ip) { return ip; } -struct map *map__new(struct mmap_event *event, char *cwd, int cwdlen); +struct symbol; + +typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym); + +void map__init(struct map *self, enum map_type type, + u64 start, u64 end, u64 pgoff, struct dso *dso); +struct map *map__new(struct mmap_event *event, enum map_type, + char *cwd, int cwdlen); +void map__delete(struct map *self); struct map *map__clone(struct map *self); int map__overlap(struct map *l, struct map *r); size_t map__fprintf(struct map *self, FILE *fp); +struct symbol *map__find_symbol(struct map *self, u64 addr, + symbol_filter_t filter); +void map__fixup_start(struct map *self); +void map__fixup_end(struct map *self); + +int event__synthesize_thread(pid_t pid, int (*process)(event_t *event)); +void event__synthesize_threads(int (*process)(event_t *event)); + +extern char *event__cwd; +extern int event__cwdlen; +extern struct events_stats event__stats; +extern unsigned long event__total[PERF_RECORD_MAX]; + +int event__process_comm(event_t *self); +int event__process_lost(event_t *self); +int event__process_mmap(event_t *self); +int event__process_task(event_t *self); + +struct addr_location; +int event__preprocess_sample(const event_t *self, struct addr_location *al, + symbol_filter_t filter); -#endif +#endif /* __PERF_RECORD_H */ diff --git a/tools/perf/util/exec_cmd.h b/tools/perf/util/exec_cmd.h index effe25eb1545..31647ac92ed1 100644 --- a/tools/perf/util/exec_cmd.h +++ b/tools/perf/util/exec_cmd.h @@ -1,5 +1,5 @@ -#ifndef PERF_EXEC_CMD_H -#define PERF_EXEC_CMD_H +#ifndef __PERF_EXEC_CMD_H +#define __PERF_EXEC_CMD_H extern void perf_set_argv_exec_path(const char *exec_path); extern const char *perf_extract_argv0_path(const char *path); @@ -10,4 +10,4 @@ extern int execv_perf_cmd(const char **argv); /* NULL terminated */ extern int execl_perf_cmd(const char *cmd, ...); extern const char *system_path(const char *path); -#endif /* PERF_EXEC_CMD_H */ +#endif /* __PERF_EXEC_CMD_H */ diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index e306857b2c2b..4805e6dfd23c 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -2,9 +2,15 @@ #include <unistd.h> #include <stdio.h> #include <stdlib.h> +#include <linux/list.h> #include "util.h" #include "header.h" +#include "../perf.h" +#include "trace-event.h" +#include "symbol.h" +#include "data_map.h" +#include "debug.h" /* * Create new perf.data header attribute: @@ -13,32 +19,43 @@ struct perf_header_attr *perf_header_attr__new(struct perf_event_attr *attr) { struct perf_header_attr *self = malloc(sizeof(*self)); - if (!self) - die("nomem"); - - self->attr = *attr; - self->ids = 0; - self->size = 1; - self->id = malloc(sizeof(u64)); - - if (!self->id) - die("nomem"); + if (self != NULL) { + self->attr = *attr; + self->ids = 0; + self->size = 1; + self->id = malloc(sizeof(u64)); + if (self->id == NULL) { + free(self); + self = NULL; + } + } return self; } -void perf_header_attr__add_id(struct perf_header_attr *self, u64 id) +void perf_header_attr__delete(struct perf_header_attr *self) +{ + free(self->id); + free(self); +} + +int perf_header_attr__add_id(struct perf_header_attr *self, u64 id) { int pos = self->ids; self->ids++; if (self->ids > self->size) { - self->size *= 2; - self->id = realloc(self->id, self->size * sizeof(u64)); - if (!self->id) - die("nomem"); + int nsize = self->size * 2; + u64 *nid = realloc(self->id, nsize * sizeof(u64)); + + if (nid == NULL) + return -1; + + self->size = nsize; + self->id = nid; } self->id[pos] = id; + return 0; } /* @@ -46,42 +63,52 @@ void perf_header_attr__add_id(struct perf_header_attr *self, u64 id) */ struct perf_header *perf_header__new(void) { - struct perf_header *self = malloc(sizeof(*self)); + struct perf_header *self = zalloc(sizeof(*self)); - if (!self) - die("nomem"); + if (self != NULL) { + self->size = 1; + self->attr = malloc(sizeof(void *)); - self->frozen = 0; + if (self->attr == NULL) { + free(self); + self = NULL; + } + } - self->attrs = 0; - self->size = 1; - self->attr = malloc(sizeof(void *)); + return self; +} - if (!self->attr) - die("nomem"); +void perf_header__delete(struct perf_header *self) +{ + int i; - self->data_offset = 0; - self->data_size = 0; + for (i = 0; i < self->attrs; ++i) + perf_header_attr__delete(self->attr[i]); - return self; + free(self->attr); + free(self); } -void perf_header__add_attr(struct perf_header *self, - struct perf_header_attr *attr) +int perf_header__add_attr(struct perf_header *self, + struct perf_header_attr *attr) { - int pos = self->attrs; - if (self->frozen) - die("frozen"); + return -1; - self->attrs++; - if (self->attrs > self->size) { - self->size *= 2; - self->attr = realloc(self->attr, self->size * sizeof(void *)); - if (!self->attr) - die("nomem"); + if (self->attrs == self->size) { + int nsize = self->size * 2; + struct perf_header_attr **nattr; + + nattr = realloc(self->attr, nsize * sizeof(void *)); + if (nattr == NULL) + return -1; + + self->size = nsize; + self->attr = nattr; } - self->attr[pos] = attr; + + self->attr[self->attrs++] = attr; + return 0; } #define MAX_EVENT_NAME 64 @@ -97,7 +124,7 @@ static struct perf_trace_event_type *events; void perf_header__push_event(u64 id, const char *name) { if (strlen(name) > MAX_EVENT_NAME) - printf("Event %s will be truncated\n", name); + pr_warning("Event %s will be truncated\n", name); if (!events) { events = malloc(sizeof(struct perf_trace_event_type)); @@ -128,44 +155,137 @@ static const char *__perf_magic = "PERFFILE"; #define PERF_MAGIC (*(u64 *)__perf_magic) -struct perf_file_section { - u64 offset; - u64 size; -}; - struct perf_file_attr { struct perf_event_attr attr; struct perf_file_section ids; }; -struct perf_file_header { - u64 magic; - u64 size; - u64 attr_size; - struct perf_file_section attrs; - struct perf_file_section data; - struct perf_file_section event_types; -}; +void perf_header__set_feat(struct perf_header *self, int feat) +{ + set_bit(feat, self->adds_features); +} -static void do_write(int fd, void *buf, size_t size) +bool perf_header__has_feat(const struct perf_header *self, int feat) +{ + return test_bit(feat, self->adds_features); +} + +static int do_write(int fd, const void *buf, size_t size) { while (size) { int ret = write(fd, buf, size); if (ret < 0) - die("failed to write"); + return -errno; size -= ret; buf += ret; } + + return 0; +} + +static int __dsos__write_buildid_table(struct list_head *head, int fd) +{ + struct dso *pos; + + list_for_each_entry(pos, head, node) { + int err; + struct build_id_event b; + size_t len; + + if (!pos->has_build_id) + continue; + len = pos->long_name_len + 1; + len = ALIGN(len, 64); + memset(&b, 0, sizeof(b)); + memcpy(&b.build_id, pos->build_id, sizeof(pos->build_id)); + b.header.size = sizeof(b) + len; + err = do_write(fd, &b, sizeof(b)); + if (err < 0) + return err; + err = do_write(fd, pos->long_name, len); + if (err < 0) + return err; + } + + return 0; } -void perf_header__write(struct perf_header *self, int fd) +static int dsos__write_buildid_table(int fd) +{ + int err = __dsos__write_buildid_table(&dsos__kernel, fd); + if (err == 0) + err = __dsos__write_buildid_table(&dsos__user, fd); + return err; +} + +static int perf_header__adds_write(struct perf_header *self, int fd) +{ + int nr_sections; + struct perf_file_section *feat_sec; + int sec_size; + u64 sec_start; + int idx = 0, err; + + if (dsos__read_build_ids()) + perf_header__set_feat(self, HEADER_BUILD_ID); + + nr_sections = bitmap_weight(self->adds_features, HEADER_FEAT_BITS); + if (!nr_sections) + return 0; + + feat_sec = calloc(sizeof(*feat_sec), nr_sections); + if (feat_sec == NULL) + return -ENOMEM; + + sec_size = sizeof(*feat_sec) * nr_sections; + + sec_start = self->data_offset + self->data_size; + lseek(fd, sec_start + sec_size, SEEK_SET); + + if (perf_header__has_feat(self, HEADER_TRACE_INFO)) { + struct perf_file_section *trace_sec; + + trace_sec = &feat_sec[idx++]; + + /* Write trace info */ + trace_sec->offset = lseek(fd, 0, SEEK_CUR); + read_tracing_data(fd, attrs, nr_counters); + trace_sec->size = lseek(fd, 0, SEEK_CUR) - trace_sec->offset; + } + + + if (perf_header__has_feat(self, HEADER_BUILD_ID)) { + struct perf_file_section *buildid_sec; + + buildid_sec = &feat_sec[idx++]; + + /* Write build-ids */ + buildid_sec->offset = lseek(fd, 0, SEEK_CUR); + err = dsos__write_buildid_table(fd); + if (err < 0) { + pr_debug("failed to write buildid table\n"); + goto out_free; + } + buildid_sec->size = lseek(fd, 0, SEEK_CUR) - buildid_sec->offset; + } + + lseek(fd, sec_start, SEEK_SET); + err = do_write(fd, feat_sec, sec_size); + if (err < 0) + pr_debug("failed to write feature section\n"); +out_free: + free(feat_sec); + return err; +} + +int perf_header__write(struct perf_header *self, int fd, bool at_exit) { struct perf_file_header f_header; struct perf_file_attr f_attr; struct perf_header_attr *attr; - int i; + int i, err; lseek(fd, sizeof(f_header), SEEK_SET); @@ -174,7 +294,11 @@ void perf_header__write(struct perf_header *self, int fd) attr = self->attr[i]; attr->id_offset = lseek(fd, 0, SEEK_CUR); - do_write(fd, attr->id, attr->ids * sizeof(u64)); + err = do_write(fd, attr->id, attr->ids * sizeof(u64)); + if (err < 0) { + pr_debug("failed to write perf header\n"); + return err; + } } @@ -190,17 +314,31 @@ void perf_header__write(struct perf_header *self, int fd) .size = attr->ids * sizeof(u64), } }; - do_write(fd, &f_attr, sizeof(f_attr)); + err = do_write(fd, &f_attr, sizeof(f_attr)); + if (err < 0) { + pr_debug("failed to write perf header attribute\n"); + return err; + } } self->event_offset = lseek(fd, 0, SEEK_CUR); self->event_size = event_count * sizeof(struct perf_trace_event_type); - if (events) - do_write(fd, events, self->event_size); - + if (events) { + err = do_write(fd, events, self->event_size); + if (err < 0) { + pr_debug("failed to write perf header events\n"); + return err; + } + } self->data_offset = lseek(fd, 0, SEEK_CUR); + if (at_exit) { + err = perf_header__adds_write(self, fd); + if (err < 0) + return err; + } + f_header = (struct perf_file_header){ .magic = PERF_MAGIC, .size = sizeof(f_header), @@ -219,11 +357,18 @@ void perf_header__write(struct perf_header *self, int fd) }, }; + memcpy(&f_header.adds_features, &self->adds_features, sizeof(self->adds_features)); + lseek(fd, 0, SEEK_SET); - do_write(fd, &f_header, sizeof(f_header)); + err = do_write(fd, &f_header, sizeof(f_header)); + if (err < 0) { + pr_debug("failed to write perf header\n"); + return err; + } lseek(fd, self->data_offset + self->data_size, SEEK_SET); self->frozen = 1; + return 0; } static void do_read(int fd, void *buf, size_t size) @@ -241,22 +386,109 @@ static void do_read(int fd, void *buf, size_t size) } } -struct perf_header *perf_header__read(int fd) +int perf_header__process_sections(struct perf_header *self, int fd, + int (*process)(struct perf_file_section *self, + int feat, int fd)) +{ + struct perf_file_section *feat_sec; + int nr_sections; + int sec_size; + int idx = 0; + int err = 0, feat = 1; + + nr_sections = bitmap_weight(self->adds_features, HEADER_FEAT_BITS); + if (!nr_sections) + return 0; + + feat_sec = calloc(sizeof(*feat_sec), nr_sections); + if (!feat_sec) + return -1; + + sec_size = sizeof(*feat_sec) * nr_sections; + + lseek(fd, self->data_offset + self->data_size, SEEK_SET); + + do_read(fd, feat_sec, sec_size); + + while (idx < nr_sections && feat < HEADER_LAST_FEATURE) { + if (perf_header__has_feat(self, feat)) { + struct perf_file_section *sec = &feat_sec[idx++]; + + err = process(sec, feat, fd); + if (err < 0) + break; + } + ++feat; + } + + free(feat_sec); + return err; +}; + +int perf_file_header__read(struct perf_file_header *self, + struct perf_header *ph, int fd) +{ + lseek(fd, 0, SEEK_SET); + do_read(fd, self, sizeof(*self)); + + if (self->magic != PERF_MAGIC || + self->attr_size != sizeof(struct perf_file_attr)) + return -1; + + if (self->size != sizeof(*self)) { + /* Support the previous format */ + if (self->size == offsetof(typeof(*self), adds_features)) + bitmap_zero(self->adds_features, HEADER_FEAT_BITS); + else + return -1; + } + + memcpy(&ph->adds_features, &self->adds_features, + sizeof(self->adds_features)); + + ph->event_offset = self->event_types.offset; + ph->event_size = self->event_types.size; + ph->data_offset = self->data.offset; + ph->data_size = self->data.size; + return 0; +} + +static int perf_file_section__process(struct perf_file_section *self, + int feat, int fd) +{ + if (lseek(fd, self->offset, SEEK_SET) < 0) { + pr_debug("Failed to lseek to %Ld offset for feature %d, " + "continuing...\n", self->offset, feat); + return 0; + } + + switch (feat) { + case HEADER_TRACE_INFO: + trace_report(fd); + break; + + case HEADER_BUILD_ID: + if (perf_header__read_build_ids(fd, self->offset, self->size)) + pr_debug("Failed to read buildids, continuing...\n"); + break; + default: + pr_debug("unknown feature %d, continuing...\n", feat); + } + + return 0; +} + +int perf_header__read(struct perf_header *self, int fd) { - struct perf_header *self = perf_header__new(); struct perf_file_header f_header; struct perf_file_attr f_attr; u64 f_id; - int nr_attrs, nr_ids, i, j; - lseek(fd, 0, SEEK_SET); - do_read(fd, &f_header, sizeof(f_header)); - - if (f_header.magic != PERF_MAGIC || - f_header.size != sizeof(f_header) || - f_header.attr_size != sizeof(f_attr)) - die("incompatible file format"); + if (perf_file_header__read(&f_header, self, fd) < 0) { + pr_debug("incompatible file format\n"); + return -EINVAL; + } nr_attrs = f_header.attrs.size / sizeof(f_attr); lseek(fd, f_header.attrs.offset, SEEK_SET); @@ -269,6 +501,8 @@ struct perf_header *perf_header__read(int fd) tmp = lseek(fd, 0, SEEK_CUR); attr = perf_header_attr__new(&f_attr.attr); + if (attr == NULL) + return -ENOMEM; nr_ids = f_attr.ids.size / sizeof(u64); lseek(fd, f_attr.ids.offset, SEEK_SET); @@ -276,31 +510,34 @@ struct perf_header *perf_header__read(int fd) for (j = 0; j < nr_ids; j++) { do_read(fd, &f_id, sizeof(f_id)); - perf_header_attr__add_id(attr, f_id); + if (perf_header_attr__add_id(attr, f_id) < 0) { + perf_header_attr__delete(attr); + return -ENOMEM; + } } - perf_header__add_attr(self, attr); + if (perf_header__add_attr(self, attr) < 0) { + perf_header_attr__delete(attr); + return -ENOMEM; + } + lseek(fd, tmp, SEEK_SET); } if (f_header.event_types.size) { lseek(fd, f_header.event_types.offset, SEEK_SET); events = malloc(f_header.event_types.size); - if (!events) - die("nomem"); + if (events == NULL) + return -ENOMEM; do_read(fd, events, f_header.event_types.size); event_count = f_header.event_types.size / sizeof(struct perf_trace_event_type); } - self->event_offset = f_header.event_types.offset; - self->event_size = f_header.event_types.size; - self->data_offset = f_header.data.offset; - self->data_size = f_header.data.size; + perf_header__process_sections(self, fd, perf_file_section__process); lseek(fd, self->data_offset, SEEK_SET); self->frozen = 1; - - return self; + return 0; } u64 perf_header__sample_type(struct perf_header *header) diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index a0761bc7863c..d1dbe2b79c42 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -1,10 +1,13 @@ -#ifndef _PERF_HEADER_H -#define _PERF_HEADER_H +#ifndef __PERF_HEADER_H +#define __PERF_HEADER_H #include "../../../include/linux/perf_event.h" #include <sys/types.h> +#include <stdbool.h> #include "types.h" +#include <linux/bitmap.h> + struct perf_header_attr { struct perf_event_attr attr; int ids, size; @@ -12,36 +15,71 @@ struct perf_header_attr { off_t id_offset; }; +enum { + HEADER_TRACE_INFO = 1, + HEADER_BUILD_ID, + HEADER_LAST_FEATURE, +}; + +#define HEADER_FEAT_BITS 256 + +struct perf_file_section { + u64 offset; + u64 size; +}; + +struct perf_file_header { + u64 magic; + u64 size; + u64 attr_size; + struct perf_file_section attrs; + struct perf_file_section data; + struct perf_file_section event_types; + DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS); +}; + +struct perf_header; + +int perf_file_header__read(struct perf_file_header *self, + struct perf_header *ph, int fd); + struct perf_header { - int frozen; - int attrs, size; + int frozen; + int attrs, size; struct perf_header_attr **attr; - s64 attr_offset; - u64 data_offset; - u64 data_size; - u64 event_offset; - u64 event_size; + s64 attr_offset; + u64 data_offset; + u64 data_size; + u64 event_offset; + u64 event_size; + DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS); }; -struct perf_header *perf_header__read(int fd); -void perf_header__write(struct perf_header *self, int fd); +struct perf_header *perf_header__new(void); +void perf_header__delete(struct perf_header *self); -void perf_header__add_attr(struct perf_header *self, - struct perf_header_attr *attr); +int perf_header__read(struct perf_header *self, int fd); +int perf_header__write(struct perf_header *self, int fd, bool at_exit); + +int perf_header__add_attr(struct perf_header *self, + struct perf_header_attr *attr); void perf_header__push_event(u64 id, const char *name); char *perf_header__find_event(u64 id); +struct perf_header_attr *perf_header_attr__new(struct perf_event_attr *attr); +void perf_header_attr__delete(struct perf_header_attr *self); -struct perf_header_attr * -perf_header_attr__new(struct perf_event_attr *attr); -void perf_header_attr__add_id(struct perf_header_attr *self, u64 id); +int perf_header_attr__add_id(struct perf_header_attr *self, u64 id); u64 perf_header__sample_type(struct perf_header *header); struct perf_event_attr * perf_header__find_attr(u64 id, struct perf_header *header); +void perf_header__set_feat(struct perf_header *self, int feat); +bool perf_header__has_feat(const struct perf_header *self, int feat); +int perf_header__process_sections(struct perf_header *self, int fd, + int (*process)(struct perf_file_section *self, + int feat, int fd)); -struct perf_header *perf_header__new(void); - -#endif /* _PERF_HEADER_H */ +#endif /* __PERF_HEADER_H */ diff --git a/tools/perf/util/help.h b/tools/perf/util/help.h index 7128783637b4..7f5c6dedd714 100644 --- a/tools/perf/util/help.h +++ b/tools/perf/util/help.h @@ -1,5 +1,5 @@ -#ifndef HELP_H -#define HELP_H +#ifndef __PERF_HELP_H +#define __PERF_HELP_H struct cmdnames { size_t alloc; @@ -26,4 +26,4 @@ int is_in_cmdlist(struct cmdnames *c, const char *s); void list_commands(const char *title, struct cmdnames *main_cmds, struct cmdnames *other_cmds); -#endif /* HELP_H */ +#endif /* __PERF_HELP_H */ diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c new file mode 100644 index 000000000000..0ebf6ee16caa --- /dev/null +++ b/tools/perf/util/hist.c @@ -0,0 +1,202 @@ +#include "hist.h" + +struct rb_root hist; +struct rb_root collapse_hists; +struct rb_root output_hists; +int callchain; + +struct callchain_param callchain_param = { + .mode = CHAIN_GRAPH_REL, + .min_percent = 0.5 +}; + +/* + * histogram, sorted on item, collects counts + */ + +struct hist_entry *__hist_entry__add(struct addr_location *al, + struct symbol *sym_parent, + u64 count, bool *hit) +{ + struct rb_node **p = &hist.rb_node; + struct rb_node *parent = NULL; + struct hist_entry *he; + struct hist_entry entry = { + .thread = al->thread, + .map = al->map, + .sym = al->sym, + .ip = al->addr, + .level = al->level, + .count = count, + .parent = sym_parent, + }; + int cmp; + + while (*p != NULL) { + parent = *p; + he = rb_entry(parent, struct hist_entry, rb_node); + + cmp = hist_entry__cmp(&entry, he); + + if (!cmp) { + *hit = true; + return he; + } + + if (cmp < 0) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + he = malloc(sizeof(*he)); + if (!he) + return NULL; + *he = entry; + rb_link_node(&he->rb_node, parent, p); + rb_insert_color(&he->rb_node, &hist); + *hit = false; + return he; +} + +int64_t +hist_entry__cmp(struct hist_entry *left, struct hist_entry *right) +{ + struct sort_entry *se; + int64_t cmp = 0; + + list_for_each_entry(se, &hist_entry__sort_list, list) { + cmp = se->cmp(left, right); + if (cmp) + break; + } + + return cmp; +} + +int64_t +hist_entry__collapse(struct hist_entry *left, struct hist_entry *right) +{ + struct sort_entry *se; + int64_t cmp = 0; + + list_for_each_entry(se, &hist_entry__sort_list, list) { + int64_t (*f)(struct hist_entry *, struct hist_entry *); + + f = se->collapse ?: se->cmp; + + cmp = f(left, right); + if (cmp) + break; + } + + return cmp; +} + +void hist_entry__free(struct hist_entry *he) +{ + free(he); +} + +/* + * collapse the histogram + */ + +void collapse__insert_entry(struct hist_entry *he) +{ + struct rb_node **p = &collapse_hists.rb_node; + struct rb_node *parent = NULL; + struct hist_entry *iter; + int64_t cmp; + + while (*p != NULL) { + parent = *p; + iter = rb_entry(parent, struct hist_entry, rb_node); + + cmp = hist_entry__collapse(iter, he); + + if (!cmp) { + iter->count += he->count; + hist_entry__free(he); + return; + } + + if (cmp < 0) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + rb_link_node(&he->rb_node, parent, p); + rb_insert_color(&he->rb_node, &collapse_hists); +} + +void collapse__resort(void) +{ + struct rb_node *next; + struct hist_entry *n; + + if (!sort__need_collapse) + return; + + next = rb_first(&hist); + while (next) { + n = rb_entry(next, struct hist_entry, rb_node); + next = rb_next(&n->rb_node); + + rb_erase(&n->rb_node, &hist); + collapse__insert_entry(n); + } +} + +/* + * reverse the map, sort on count. + */ + +void output__insert_entry(struct hist_entry *he, u64 min_callchain_hits) +{ + struct rb_node **p = &output_hists.rb_node; + struct rb_node *parent = NULL; + struct hist_entry *iter; + + if (callchain) + callchain_param.sort(&he->sorted_chain, &he->callchain, + min_callchain_hits, &callchain_param); + + while (*p != NULL) { + parent = *p; + iter = rb_entry(parent, struct hist_entry, rb_node); + + if (he->count > iter->count) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + rb_link_node(&he->rb_node, parent, p); + rb_insert_color(&he->rb_node, &output_hists); +} + +void output__resort(u64 total_samples) +{ + struct rb_node *next; + struct hist_entry *n; + struct rb_root *tree = &hist; + u64 min_callchain_hits; + + min_callchain_hits = + total_samples * (callchain_param.min_percent / 100); + + if (sort__need_collapse) + tree = &collapse_hists; + + next = rb_first(tree); + + while (next) { + n = rb_entry(next, struct hist_entry, rb_node); + next = rb_next(&n->rb_node); + + rb_erase(&n->rb_node, tree); + output__insert_entry(n, min_callchain_hits); + } +} diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h new file mode 100644 index 000000000000..3020db0c9292 --- /dev/null +++ b/tools/perf/util/hist.h @@ -0,0 +1,50 @@ +#ifndef __PERF_HIST_H +#define __PERF_HIST_H +#include "../builtin.h" + +#include "util.h" + +#include "color.h" +#include <linux/list.h> +#include "cache.h" +#include <linux/rbtree.h> +#include "symbol.h" +#include "string.h" +#include "callchain.h" +#include "strlist.h" +#include "values.h" + +#include "../perf.h" +#include "debug.h" +#include "header.h" + +#include "parse-options.h" +#include "parse-events.h" + +#include "thread.h" +#include "sort.h" + +extern struct rb_root hist; +extern struct rb_root collapse_hists; +extern struct rb_root output_hists; +extern int callchain; +extern struct callchain_param callchain_param; +extern unsigned long total; +extern unsigned long total_mmap; +extern unsigned long total_comm; +extern unsigned long total_fork; +extern unsigned long total_unknown; +extern unsigned long total_lost; + +struct hist_entry *__hist_entry__add(struct addr_location *al, + struct symbol *parent, + u64 count, bool *hit); +extern int64_t hist_entry__cmp(struct hist_entry *, struct hist_entry *); +extern int64_t hist_entry__collapse(struct hist_entry *, struct hist_entry *); +extern void hist_entry__free(struct hist_entry *); +extern void collapse__insert_entry(struct hist_entry *); +extern void collapse__resort(void); +extern void output__insert_entry(struct hist_entry *, u64); +extern void output__resort(u64); + +#endif /* __PERF_HIST_H */ diff --git a/tools/perf/util/include/asm/asm-offsets.h b/tools/perf/util/include/asm/asm-offsets.h new file mode 100644 index 000000000000..ed538942523d --- /dev/null +++ b/tools/perf/util/include/asm/asm-offsets.h @@ -0,0 +1 @@ +/* stub */ diff --git a/tools/perf/util/include/asm/bitops.h b/tools/perf/util/include/asm/bitops.h new file mode 100644 index 000000000000..58e9817ffae0 --- /dev/null +++ b/tools/perf/util/include/asm/bitops.h @@ -0,0 +1,18 @@ +#ifndef _PERF_ASM_BITOPS_H_ +#define _PERF_ASM_BITOPS_H_ + +#include <sys/types.h> +#include "../../types.h" +#include <linux/compiler.h> + +/* CHECKME: Not sure both always match */ +#define BITS_PER_LONG __WORDSIZE + +#include "../../../../include/asm-generic/bitops/__fls.h" +#include "../../../../include/asm-generic/bitops/fls.h" +#include "../../../../include/asm-generic/bitops/fls64.h" +#include "../../../../include/asm-generic/bitops/__ffs.h" +#include "../../../../include/asm-generic/bitops/ffz.h" +#include "../../../../include/asm-generic/bitops/hweight.h" + +#endif diff --git a/tools/perf/util/include/asm/bug.h b/tools/perf/util/include/asm/bug.h new file mode 100644 index 000000000000..7fcc6810adc2 --- /dev/null +++ b/tools/perf/util/include/asm/bug.h @@ -0,0 +1,22 @@ +#ifndef _PERF_ASM_GENERIC_BUG_H +#define _PERF_ASM_GENERIC_BUG_H + +#define __WARN_printf(arg...) do { fprintf(stderr, arg); } while (0) + +#define WARN(condition, format...) ({ \ + int __ret_warn_on = !!(condition); \ + if (unlikely(__ret_warn_on)) \ + __WARN_printf(format); \ + unlikely(__ret_warn_on); \ +}) + +#define WARN_ONCE(condition, format...) ({ \ + static int __warned; \ + int __ret_warn_once = !!(condition); \ + \ + if (unlikely(__ret_warn_once)) \ + if (WARN(!__warned, format)) \ + __warned = 1; \ + unlikely(__ret_warn_once); \ +}) +#endif diff --git a/tools/perf/util/include/asm/byteorder.h b/tools/perf/util/include/asm/byteorder.h new file mode 100644 index 000000000000..b722abe3a626 --- /dev/null +++ b/tools/perf/util/include/asm/byteorder.h @@ -0,0 +1,2 @@ +#include <asm/types.h> +#include "../../../../include/linux/swab.h" diff --git a/tools/perf/util/include/asm/swab.h b/tools/perf/util/include/asm/swab.h new file mode 100644 index 000000000000..ed538942523d --- /dev/null +++ b/tools/perf/util/include/asm/swab.h @@ -0,0 +1 @@ +/* stub */ diff --git a/tools/perf/util/include/asm/uaccess.h b/tools/perf/util/include/asm/uaccess.h new file mode 100644 index 000000000000..d0f72b8fcc35 --- /dev/null +++ b/tools/perf/util/include/asm/uaccess.h @@ -0,0 +1,14 @@ +#ifndef _PERF_ASM_UACCESS_H_ +#define _PERF_ASM_UACCESS_H_ + +#define __get_user(src, dest) \ +({ \ + (src) = *dest; \ + 0; \ +}) + +#define get_user __get_user + +#define access_ok(type, addr, size) 1 + +#endif diff --git a/tools/perf/util/include/linux/bitmap.h b/tools/perf/util/include/linux/bitmap.h new file mode 100644 index 000000000000..94507639a8c4 --- /dev/null +++ b/tools/perf/util/include/linux/bitmap.h @@ -0,0 +1,3 @@ +#include "../../../../include/linux/bitmap.h" +#include "../../../../include/asm-generic/bitops/find.h" +#include <linux/errno.h> diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h new file mode 100644 index 000000000000..8d63116e9435 --- /dev/null +++ b/tools/perf/util/include/linux/bitops.h @@ -0,0 +1,29 @@ +#ifndef _PERF_LINUX_BITOPS_H_ +#define _PERF_LINUX_BITOPS_H_ + +#define __KERNEL__ + +#define CONFIG_GENERIC_FIND_NEXT_BIT +#define CONFIG_GENERIC_FIND_FIRST_BIT +#include "../../../../include/linux/bitops.h" + +#undef __KERNEL__ + +static inline void set_bit(int nr, unsigned long *addr) +{ + addr[nr / BITS_PER_LONG] |= 1UL << (nr % BITS_PER_LONG); +} + +static __always_inline int test_bit(unsigned int nr, const unsigned long *addr) +{ + return ((1UL << (nr % BITS_PER_LONG)) & + (((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0; +} + +unsigned long generic_find_next_zero_le_bit(const unsigned long *addr, unsigned + long size, unsigned long offset); + +unsigned long generic_find_next_le_bit(const unsigned long *addr, unsigned + long size, unsigned long offset); + +#endif diff --git a/tools/perf/util/include/linux/compiler.h b/tools/perf/util/include/linux/compiler.h new file mode 100644 index 000000000000..dfb0713ed47f --- /dev/null +++ b/tools/perf/util/include/linux/compiler.h @@ -0,0 +1,10 @@ +#ifndef _PERF_LINUX_COMPILER_H_ +#define _PERF_LINUX_COMPILER_H_ + +#ifndef __always_inline +#define __always_inline inline +#endif +#define __user +#define __attribute_const__ + +#endif diff --git a/tools/perf/util/include/linux/ctype.h b/tools/perf/util/include/linux/ctype.h new file mode 100644 index 000000000000..a53d4ee1e0b7 --- /dev/null +++ b/tools/perf/util/include/linux/ctype.h @@ -0,0 +1 @@ +#include "../util.h" diff --git a/tools/perf/util/include/linux/kernel.h b/tools/perf/util/include/linux/kernel.h index a6b87390cb52..21c0274c02fa 100644 --- a/tools/perf/util/include/linux/kernel.h +++ b/tools/perf/util/include/linux/kernel.h @@ -1,6 +1,16 @@ #ifndef PERF_LINUX_KERNEL_H_ #define PERF_LINUX_KERNEL_H_ +#include <stdarg.h> +#include <stdio.h> +#include <stdlib.h> +#include <assert.h> + +#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) + +#define ALIGN(x,a) __ALIGN_MASK(x,(typeof(x))(a)-1) +#define __ALIGN_MASK(x,mask) (((x)+(mask))&~(mask)) + #ifndef offsetof #define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER) #endif @@ -26,4 +36,70 @@ _max1 > _max2 ? _max1 : _max2; }) #endif +#ifndef min +#define min(x, y) ({ \ + typeof(x) _min1 = (x); \ + typeof(y) _min2 = (y); \ + (void) (&_min1 == &_min2); \ + _min1 < _min2 ? _min1 : _min2; }) +#endif + +#ifndef BUG_ON +#define BUG_ON(cond) assert(!(cond)) +#endif + +/* + * Both need more care to handle endianness + * (Don't use bitmap_copy_le() for now) + */ +#define cpu_to_le64(x) (x) +#define cpu_to_le32(x) (x) + +static inline int +vscnprintf(char *buf, size_t size, const char *fmt, va_list args) +{ + int i; + ssize_t ssize = size; + + i = vsnprintf(buf, size, fmt, args); + + return (i >= ssize) ? (ssize - 1) : i; +} + +static inline int scnprintf(char * buf, size_t size, const char * fmt, ...) +{ + va_list args; + ssize_t ssize = size; + int i; + + va_start(args, fmt); + i = vsnprintf(buf, size, fmt, args); + va_end(args); + + return (i >= ssize) ? (ssize - 1) : i; +} + +static inline unsigned long +simple_strtoul(const char *nptr, char **endptr, int base) +{ + return strtoul(nptr, endptr, base); +} + +#ifndef pr_fmt +#define pr_fmt(fmt) fmt +#endif + +#define pr_err(fmt, ...) \ + do { fprintf(stderr, pr_fmt(fmt), ##__VA_ARGS__); } while (0) +#define pr_warning(fmt, ...) \ + do { fprintf(stderr, pr_fmt(fmt), ##__VA_ARGS__); } while (0) +#define pr_info(fmt, ...) \ + do { fprintf(stderr, pr_fmt(fmt), ##__VA_ARGS__); } while (0) +#define pr_debug(fmt, ...) \ + eprintf(1, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_debugN(n, fmt, ...) \ + eprintf(n, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_debug2(fmt, ...) pr_debugN(2, pr_fmt(fmt), ##__VA_ARGS__) +#define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__) + #endif diff --git a/tools/perf/util/include/linux/string.h b/tools/perf/util/include/linux/string.h new file mode 100644 index 000000000000..3b2f5900276f --- /dev/null +++ b/tools/perf/util/include/linux/string.h @@ -0,0 +1 @@ +#include <string.h> diff --git a/tools/perf/util/include/linux/types.h b/tools/perf/util/include/linux/types.h new file mode 100644 index 000000000000..196862a81a21 --- /dev/null +++ b/tools/perf/util/include/linux/types.h @@ -0,0 +1,9 @@ +#ifndef _PERF_LINUX_TYPES_H_ +#define _PERF_LINUX_TYPES_H_ + +#include <asm/types.h> + +#define DECLARE_BITMAP(name,bits) \ + unsigned long name[BITS_TO_LONGS(bits)] + +#endif diff --git a/tools/perf/util/levenshtein.h b/tools/perf/util/levenshtein.h index 0173abeef52c..b0fcb6d8a881 100644 --- a/tools/perf/util/levenshtein.h +++ b/tools/perf/util/levenshtein.h @@ -1,8 +1,8 @@ -#ifndef LEVENSHTEIN_H -#define LEVENSHTEIN_H +#ifndef __PERF_LEVENSHTEIN_H +#define __PERF_LEVENSHTEIN_H int levenshtein(const char *string1, const char *string2, int swap_penalty, int substition_penalty, int insertion_penalty, int deletion_penalty); -#endif +#endif /* __PERF_LEVENSHTEIN_H */ diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 804e02382739..69f94fe9db20 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -3,6 +3,7 @@ #include <stdlib.h> #include <string.h> #include <stdio.h> +#include "debug.h" static inline int is_anon_memory(const char *filename) { @@ -19,13 +20,28 @@ static int strcommon(const char *pathname, char *cwd, int cwdlen) return n; } - struct map *map__new(struct mmap_event *event, char *cwd, int cwdlen) +void map__init(struct map *self, enum map_type type, + u64 start, u64 end, u64 pgoff, struct dso *dso) +{ + self->type = type; + self->start = start; + self->end = end; + self->pgoff = pgoff; + self->dso = dso; + self->map_ip = map__map_ip; + self->unmap_ip = map__unmap_ip; + RB_CLEAR_NODE(&self->rb_node); +} + +struct map *map__new(struct mmap_event *event, enum map_type type, + char *cwd, int cwdlen) { struct map *self = malloc(sizeof(*self)); if (self != NULL) { const char *filename = event->filename; char newfilename[PATH_MAX]; + struct dso *dso; int anon; if (cwd) { @@ -45,18 +61,15 @@ static int strcommon(const char *pathname, char *cwd, int cwdlen) filename = newfilename; } - self->start = event->start; - self->end = event->start + event->len; - self->pgoff = event->pgoff; - - self->dso = dsos__findnew(filename); - if (self->dso == NULL) + dso = dsos__findnew(filename); + if (dso == NULL) goto out_delete; + map__init(self, type, event->start, event->start + event->len, + event->pgoff, dso); + if (self->dso == vdso || anon) - self->map_ip = vdso__map_ip; - else - self->map_ip = map__map_ip; + self->map_ip = self->unmap_ip = identity__map_ip; } return self; out_delete: @@ -64,6 +77,72 @@ out_delete: return NULL; } +void map__delete(struct map *self) +{ + free(self); +} + +void map__fixup_start(struct map *self) +{ + struct rb_root *symbols = &self->dso->symbols[self->type]; + struct rb_node *nd = rb_first(symbols); + if (nd != NULL) { + struct symbol *sym = rb_entry(nd, struct symbol, rb_node); + self->start = sym->start; + } +} + +void map__fixup_end(struct map *self) +{ + struct rb_root *symbols = &self->dso->symbols[self->type]; + struct rb_node *nd = rb_last(symbols); + if (nd != NULL) { + struct symbol *sym = rb_entry(nd, struct symbol, rb_node); + self->end = sym->end; + } +} + +#define DSO__DELETED "(deleted)" + +struct symbol *map__find_symbol(struct map *self, u64 addr, + symbol_filter_t filter) +{ + if (!dso__loaded(self->dso, self->type)) { + int nr = dso__load(self->dso, self, filter); + + if (nr < 0) { + if (self->dso->has_build_id) { + char sbuild_id[BUILD_ID_SIZE * 2 + 1]; + + build_id__sprintf(self->dso->build_id, + sizeof(self->dso->build_id), + sbuild_id); + pr_warning("%s with build id %s not found", + self->dso->long_name, sbuild_id); + } else + pr_warning("Failed to open %s", + self->dso->long_name); + pr_warning(", continuing without symbols\n"); + return NULL; + } else if (nr == 0) { + const char *name = self->dso->long_name; + const size_t len = strlen(name); + const size_t real_len = len - sizeof(DSO__DELETED); + + if (len > sizeof(DSO__DELETED) && + strcmp(name + real_len + 1, DSO__DELETED) == 0) { + pr_warning("%.*s was updated, restart the long running apps that use it!\n", + (int)real_len, name); + } else { + pr_warning("no symbols found in %s, maybe install a debug package?\n", name); + } + return NULL; + } + } + + return self->dso->find_symbol(self->dso, self->type, addr); +} + struct map *map__clone(struct map *self) { struct map *map = malloc(sizeof(*self)); diff --git a/tools/perf/util/module.c b/tools/perf/util/module.c deleted file mode 100644 index 0d8c85defcd2..000000000000 --- a/tools/perf/util/module.c +++ /dev/null @@ -1,545 +0,0 @@ -#include "util.h" -#include "../perf.h" -#include "string.h" -#include "module.h" - -#include <libelf.h> -#include <libgen.h> -#include <gelf.h> -#include <elf.h> -#include <dirent.h> -#include <sys/utsname.h> - -static unsigned int crc32(const char *p, unsigned int len) -{ - int i; - unsigned int crc = 0; - - while (len--) { - crc ^= *p++; - for (i = 0; i < 8; i++) - crc = (crc >> 1) ^ ((crc & 1) ? 0xedb88320 : 0); - } - return crc; -} - -/* module section methods */ - -struct sec_dso *sec_dso__new_dso(const char *name) -{ - struct sec_dso *self = malloc(sizeof(*self) + strlen(name) + 1); - - if (self != NULL) { - strcpy(self->name, name); - self->secs = RB_ROOT; - self->find_section = sec_dso__find_section; - } - - return self; -} - -static void sec_dso__delete_section(struct section *self) -{ - free(((void *)self)); -} - -void sec_dso__delete_sections(struct sec_dso *self) -{ - struct section *pos; - struct rb_node *next = rb_first(&self->secs); - - while (next) { - pos = rb_entry(next, struct section, rb_node); - next = rb_next(&pos->rb_node); - rb_erase(&pos->rb_node, &self->secs); - sec_dso__delete_section(pos); - } -} - -void sec_dso__delete_self(struct sec_dso *self) -{ - sec_dso__delete_sections(self); - free(self); -} - -static void sec_dso__insert_section(struct sec_dso *self, struct section *sec) -{ - struct rb_node **p = &self->secs.rb_node; - struct rb_node *parent = NULL; - const u64 hash = sec->hash; - struct section *s; - - while (*p != NULL) { - parent = *p; - s = rb_entry(parent, struct section, rb_node); - if (hash < s->hash) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; - } - rb_link_node(&sec->rb_node, parent, p); - rb_insert_color(&sec->rb_node, &self->secs); -} - -struct section *sec_dso__find_section(struct sec_dso *self, const char *name) -{ - struct rb_node *n; - u64 hash; - int len; - - if (self == NULL) - return NULL; - - len = strlen(name); - hash = crc32(name, len); - - n = self->secs.rb_node; - - while (n) { - struct section *s = rb_entry(n, struct section, rb_node); - - if (hash < s->hash) - n = n->rb_left; - else if (hash > s->hash) - n = n->rb_right; - else { - if (!strcmp(name, s->name)) - return s; - else - n = rb_next(&s->rb_node); - } - } - - return NULL; -} - -static size_t sec_dso__fprintf_section(struct section *self, FILE *fp) -{ - return fprintf(fp, "name:%s vma:%llx path:%s\n", - self->name, self->vma, self->path); -} - -size_t sec_dso__fprintf(struct sec_dso *self, FILE *fp) -{ - size_t ret = fprintf(fp, "dso: %s\n", self->name); - - struct rb_node *nd; - for (nd = rb_first(&self->secs); nd; nd = rb_next(nd)) { - struct section *pos = rb_entry(nd, struct section, rb_node); - ret += sec_dso__fprintf_section(pos, fp); - } - - return ret; -} - -static struct section *section__new(const char *name, const char *path) -{ - struct section *self = calloc(1, sizeof(*self)); - - if (!self) - goto out_failure; - - self->name = calloc(1, strlen(name) + 1); - if (!self->name) - goto out_failure; - - self->path = calloc(1, strlen(path) + 1); - if (!self->path) - goto out_failure; - - strcpy(self->name, name); - strcpy(self->path, path); - self->hash = crc32(self->name, strlen(name)); - - return self; - -out_failure: - if (self) { - if (self->name) - free(self->name); - if (self->path) - free(self->path); - free(self); - } - - return NULL; -} - -/* module methods */ - -struct mod_dso *mod_dso__new_dso(const char *name) -{ - struct mod_dso *self = malloc(sizeof(*self) + strlen(name) + 1); - - if (self != NULL) { - strcpy(self->name, name); - self->mods = RB_ROOT; - self->find_module = mod_dso__find_module; - } - - return self; -} - -static void mod_dso__delete_module(struct module *self) -{ - free(((void *)self)); -} - -void mod_dso__delete_modules(struct mod_dso *self) -{ - struct module *pos; - struct rb_node *next = rb_first(&self->mods); - - while (next) { - pos = rb_entry(next, struct module, rb_node); - next = rb_next(&pos->rb_node); - rb_erase(&pos->rb_node, &self->mods); - mod_dso__delete_module(pos); - } -} - -void mod_dso__delete_self(struct mod_dso *self) -{ - mod_dso__delete_modules(self); - free(self); -} - -static void mod_dso__insert_module(struct mod_dso *self, struct module *mod) -{ - struct rb_node **p = &self->mods.rb_node; - struct rb_node *parent = NULL; - const u64 hash = mod->hash; - struct module *m; - - while (*p != NULL) { - parent = *p; - m = rb_entry(parent, struct module, rb_node); - if (hash < m->hash) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; - } - rb_link_node(&mod->rb_node, parent, p); - rb_insert_color(&mod->rb_node, &self->mods); -} - -struct module *mod_dso__find_module(struct mod_dso *self, const char *name) -{ - struct rb_node *n; - u64 hash; - int len; - - if (self == NULL) - return NULL; - - len = strlen(name); - hash = crc32(name, len); - - n = self->mods.rb_node; - - while (n) { - struct module *m = rb_entry(n, struct module, rb_node); - - if (hash < m->hash) - n = n->rb_left; - else if (hash > m->hash) - n = n->rb_right; - else { - if (!strcmp(name, m->name)) - return m; - else - n = rb_next(&m->rb_node); - } - } - - return NULL; -} - -static size_t mod_dso__fprintf_module(struct module *self, FILE *fp) -{ - return fprintf(fp, "name:%s path:%s\n", self->name, self->path); -} - -size_t mod_dso__fprintf(struct mod_dso *self, FILE *fp) -{ - struct rb_node *nd; - size_t ret; - - ret = fprintf(fp, "dso: %s\n", self->name); - - for (nd = rb_first(&self->mods); nd; nd = rb_next(nd)) { - struct module *pos = rb_entry(nd, struct module, rb_node); - - ret += mod_dso__fprintf_module(pos, fp); - } - - return ret; -} - -static struct module *module__new(const char *name, const char *path) -{ - struct module *self = calloc(1, sizeof(*self)); - - if (!self) - goto out_failure; - - self->name = calloc(1, strlen(name) + 1); - if (!self->name) - goto out_failure; - - self->path = calloc(1, strlen(path) + 1); - if (!self->path) - goto out_failure; - - strcpy(self->name, name); - strcpy(self->path, path); - self->hash = crc32(self->name, strlen(name)); - - return self; - -out_failure: - if (self) { - if (self->name) - free(self->name); - if (self->path) - free(self->path); - free(self); - } - - return NULL; -} - -static int mod_dso__load_sections(struct module *mod) -{ - int count = 0, path_len; - struct dirent *entry; - char *line = NULL; - char *dir_path; - DIR *dir; - size_t n; - - path_len = strlen("/sys/module/"); - path_len += strlen(mod->name); - path_len += strlen("/sections/"); - - dir_path = calloc(1, path_len + 1); - if (dir_path == NULL) - goto out_failure; - - strcat(dir_path, "/sys/module/"); - strcat(dir_path, mod->name); - strcat(dir_path, "/sections/"); - - dir = opendir(dir_path); - if (dir == NULL) - goto out_free; - - while ((entry = readdir(dir))) { - struct section *section; - char *path, *vma; - int line_len; - FILE *file; - - if (!strcmp(".", entry->d_name) || !strcmp("..", entry->d_name)) - continue; - - path = calloc(1, path_len + strlen(entry->d_name) + 1); - if (path == NULL) - break; - strcat(path, dir_path); - strcat(path, entry->d_name); - - file = fopen(path, "r"); - if (file == NULL) { - free(path); - break; - } - - line_len = getline(&line, &n, file); - if (line_len < 0) { - free(path); - fclose(file); - break; - } - - if (!line) { - free(path); - fclose(file); - break; - } - - line[--line_len] = '\0'; /* \n */ - - vma = strstr(line, "0x"); - if (!vma) { - free(path); - fclose(file); - break; - } - vma += 2; - - section = section__new(entry->d_name, path); - if (!section) { - fprintf(stderr, "load_sections: allocation error\n"); - free(path); - fclose(file); - break; - } - - hex2u64(vma, §ion->vma); - sec_dso__insert_section(mod->sections, section); - - free(path); - fclose(file); - count++; - } - - closedir(dir); - free(line); - free(dir_path); - - return count; - -out_free: - free(dir_path); - -out_failure: - return count; -} - -static int mod_dso__load_module_paths(struct mod_dso *self) -{ - struct utsname uts; - int count = 0, len, err = -1; - char *line = NULL; - FILE *file; - char *dpath, *dir; - size_t n; - - if (uname(&uts) < 0) - return err; - - len = strlen("/lib/modules/"); - len += strlen(uts.release); - len += strlen("/modules.dep"); - - dpath = calloc(1, len + 1); - if (dpath == NULL) - return err; - - strcat(dpath, "/lib/modules/"); - strcat(dpath, uts.release); - strcat(dpath, "/modules.dep"); - - file = fopen(dpath, "r"); - if (file == NULL) - goto out_failure; - - dir = dirname(dpath); - if (!dir) - goto out_failure; - strcat(dir, "/"); - - while (!feof(file)) { - struct module *module; - char *name, *path, *tmp; - FILE *modfile; - int line_len; - - line_len = getline(&line, &n, file); - if (line_len < 0) - break; - - if (!line) - break; - - line[--line_len] = '\0'; /* \n */ - - path = strchr(line, ':'); - if (!path) - break; - *path = '\0'; - - path = strdup(line); - if (!path) - break; - - if (!strstr(path, dir)) { - if (strncmp(path, "kernel/", 7)) - break; - - free(path); - path = calloc(1, strlen(dir) + strlen(line) + 1); - if (!path) - break; - strcat(path, dir); - strcat(path, line); - } - - modfile = fopen(path, "r"); - if (modfile == NULL) - break; - fclose(modfile); - - name = strdup(path); - if (!name) - break; - - name = strtok(name, "/"); - tmp = name; - - while (tmp) { - tmp = strtok(NULL, "/"); - if (tmp) - name = tmp; - } - - name = strsep(&name, "."); - if (!name) - break; - - /* Quirk: replace '-' with '_' in all modules */ - for (len = strlen(name); len; len--) { - if (*(name+len) == '-') - *(name+len) = '_'; - } - - module = module__new(name, path); - if (!module) - break; - mod_dso__insert_module(self, module); - - module->sections = sec_dso__new_dso("sections"); - if (!module->sections) - break; - - module->active = mod_dso__load_sections(module); - - if (module->active > 0) - count++; - } - - if (feof(file)) - err = count; - else - fprintf(stderr, "load_module_paths: modules.dep parsing failure!\n"); - -out_failure: - if (dpath) - free(dpath); - if (file) - fclose(file); - if (line) - free(line); - - return err; -} - -int mod_dso__load_modules(struct mod_dso *dso) -{ - int err; - - err = mod_dso__load_module_paths(dso); - - return err; -} diff --git a/tools/perf/util/module.h b/tools/perf/util/module.h deleted file mode 100644 index 8a592ef641ca..000000000000 --- a/tools/perf/util/module.h +++ /dev/null @@ -1,53 +0,0 @@ -#ifndef _PERF_MODULE_ -#define _PERF_MODULE_ 1 - -#include <linux/types.h> -#include "../types.h" -#include <linux/list.h> -#include <linux/rbtree.h> - -struct section { - struct rb_node rb_node; - u64 hash; - u64 vma; - char *name; - char *path; -}; - -struct sec_dso { - struct list_head node; - struct rb_root secs; - struct section *(*find_section)(struct sec_dso *, const char *name); - char name[0]; -}; - -struct module { - struct rb_node rb_node; - u64 hash; - char *name; - char *path; - struct sec_dso *sections; - int active; -}; - -struct mod_dso { - struct list_head node; - struct rb_root mods; - struct module *(*find_module)(struct mod_dso *, const char *name); - char name[0]; -}; - -struct sec_dso *sec_dso__new_dso(const char *name); -void sec_dso__delete_sections(struct sec_dso *self); -void sec_dso__delete_self(struct sec_dso *self); -size_t sec_dso__fprintf(struct sec_dso *self, FILE *fp); -struct section *sec_dso__find_section(struct sec_dso *self, const char *name); - -struct mod_dso *mod_dso__new_dso(const char *name); -void mod_dso__delete_modules(struct mod_dso *self); -void mod_dso__delete_self(struct mod_dso *self); -size_t mod_dso__fprintf(struct mod_dso *self, FILE *fp); -struct module *mod_dso__find_module(struct mod_dso *self, const char *name); -int mod_dso__load_modules(struct mod_dso *dso); - -#endif /* _PERF_MODULE_ */ diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 8cfb48cbbea0..9e5dbd66d34d 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1,4 +1,4 @@ - +#include "../../../include/linux/hw_breakpoint.h" #include "util.h" #include "../perf.h" #include "parse-options.h" @@ -7,10 +7,12 @@ #include "string.h" #include "cache.h" #include "header.h" +#include "debugfs.h" -int nr_counters; +int nr_counters; struct perf_event_attr attrs[MAX_COUNTERS]; +char *filters[MAX_COUNTERS]; struct event_symbol { u8 type; @@ -46,6 +48,8 @@ static struct event_symbol event_symbols[] = { { CSW(PAGE_FAULTS_MAJ), "major-faults", "" }, { CSW(CONTEXT_SWITCHES), "context-switches", "cs" }, { CSW(CPU_MIGRATIONS), "cpu-migrations", "migrations" }, + { CSW(ALIGNMENT_FAULTS), "alignment-faults", "" }, + { CSW(EMULATION_FAULTS), "emulation-faults", "" }, }; #define __PERF_EVENT_FIELD(config, name) \ @@ -74,6 +78,8 @@ static const char *sw_event_names[] = { "CPU-migrations", "minor-faults", "major-faults", + "alignment-faults", + "emulation-faults", }; #define MAX_ALIASES 8 @@ -148,16 +154,6 @@ static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir) #define MAX_EVENT_LENGTH 512 -int valid_debugfs_mount(const char *debugfs) -{ - struct statfs st_fs; - - if (statfs(debugfs, &st_fs) < 0) - return -ENOENT; - else if (st_fs.f_type != (long) DEBUGFS_MAGIC) - return -ENOENT; - return 0; -} struct tracepoint_path *tracepoint_id_to_path(u64 config) { @@ -170,7 +166,7 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) char evt_path[MAXPATHLEN]; char dir_path[MAXPATHLEN]; - if (valid_debugfs_mount(debugfs_path)) + if (debugfs_valid_mountpoint(debugfs_path)) return NULL; sys_dir = opendir(debugfs_path); @@ -201,7 +197,7 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) if (id == config) { closedir(evt_dir); closedir(sys_dir); - path = calloc(1, sizeof(path)); + path = zalloc(sizeof(path)); path->system = malloc(MAX_EVENT_LENGTH); if (!path->system) { free(path); @@ -509,7 +505,7 @@ static enum event_result parse_tracepoint_event(const char **strp, char sys_name[MAX_EVENT_LENGTH]; unsigned int sys_length, evt_length; - if (valid_debugfs_mount(debugfs_path)) + if (debugfs_valid_mountpoint(debugfs_path)) return 0; evt_name = strchr(*strp, ':'); @@ -544,6 +540,81 @@ static enum event_result parse_tracepoint_event(const char **strp, attr, strp); } +static enum event_result +parse_breakpoint_type(const char *type, const char **strp, + struct perf_event_attr *attr) +{ + int i; + + for (i = 0; i < 3; i++) { + if (!type[i]) + break; + + switch (type[i]) { + case 'r': + attr->bp_type |= HW_BREAKPOINT_R; + break; + case 'w': + attr->bp_type |= HW_BREAKPOINT_W; + break; + case 'x': + attr->bp_type |= HW_BREAKPOINT_X; + break; + default: + return EVT_FAILED; + } + } + if (!attr->bp_type) /* Default */ + attr->bp_type = HW_BREAKPOINT_R | HW_BREAKPOINT_W; + + *strp = type + i; + + return EVT_HANDLED; +} + +static enum event_result +parse_breakpoint_event(const char **strp, struct perf_event_attr *attr) +{ + const char *target; + const char *type; + char *endaddr; + u64 addr; + enum event_result err; + + target = strchr(*strp, ':'); + if (!target) + return EVT_FAILED; + + if (strncmp(*strp, "mem", target - *strp) != 0) + return EVT_FAILED; + + target++; + + addr = strtoull(target, &endaddr, 0); + if (target == endaddr) + return EVT_FAILED; + + attr->bp_addr = addr; + *strp = endaddr; + + type = strchr(target, ':'); + + /* If no type is defined, just rw as default */ + if (!type) { + attr->bp_type = HW_BREAKPOINT_R | HW_BREAKPOINT_W; + } else { + err = parse_breakpoint_type(++type, strp, attr); + if (err == EVT_FAILED) + return EVT_FAILED; + } + + /* We should find a nice way to override the access type */ + attr->bp_len = HW_BREAKPOINT_LEN_4; + attr->type = PERF_TYPE_BREAKPOINT; + + return EVT_HANDLED; +} + static int check_events(const char *str, unsigned int i) { int n; @@ -677,6 +748,12 @@ parse_event_symbols(const char **str, struct perf_event_attr *attr) if (ret != EVT_FAILED) goto modifier; + ret = parse_breakpoint_event(str, attr); + if (ret != EVT_FAILED) + goto modifier; + + fprintf(stderr, "invalid or unsupported event: '%s'\n", *str); + fprintf(stderr, "Run 'perf list' for a list of valid events\n"); return EVT_FAILED; modifier: @@ -708,7 +785,6 @@ static void store_event_type(const char *orgname) perf_header__push_event(id, orgname); } - int parse_events(const struct option *opt __used, const char *str, int unset __used) { struct perf_event_attr attr; @@ -745,6 +821,28 @@ int parse_events(const struct option *opt __used, const char *str, int unset __u return 0; } +int parse_filter(const struct option *opt __used, const char *str, + int unset __used) +{ + int i = nr_counters - 1; + int len = strlen(str); + + if (i < 0 || attrs[i].type != PERF_TYPE_TRACEPOINT) { + fprintf(stderr, + "-F option should follow a -e tracepoint option\n"); + return -1; + } + + filters[i] = malloc(len + 1); + if (!filters[i]) { + fprintf(stderr, "not enough memory to hold filter string\n"); + return -1; + } + strcpy(filters[i], str); + + return 0; +} + static const char * const event_type_descriptors[] = { "", "Hardware event", @@ -764,7 +862,7 @@ static void print_tracepoint_events(void) char evt_path[MAXPATHLEN]; char dir_path[MAXPATHLEN]; - if (valid_debugfs_mount(debugfs_path)) + if (debugfs_valid_mountpoint(debugfs_path)) return; sys_dir = opendir(debugfs_path); @@ -782,7 +880,7 @@ static void print_tracepoint_events(void) for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) { snprintf(evt_path, MAXPATHLEN, "%s:%s", sys_dirent.d_name, evt_dirent.d_name); - fprintf(stderr, " %-42s [%s]\n", evt_path, + printf(" %-42s [%s]\n", evt_path, event_type_descriptors[PERF_TYPE_TRACEPOINT+1]); } closedir(evt_dir); @@ -799,8 +897,8 @@ void print_events(void) unsigned int i, type, op, prev_type = -1; char name[40]; - fprintf(stderr, "\n"); - fprintf(stderr, "List of pre-defined events (to be used in -e):\n"); + printf("\n"); + printf("List of pre-defined events (to be used in -e):\n"); for (i = 0; i < ARRAY_SIZE(event_symbols); i++, syms++) { type = syms->type + 1; @@ -808,19 +906,19 @@ void print_events(void) type = 0; if (type != prev_type) - fprintf(stderr, "\n"); + printf("\n"); if (strlen(syms->alias)) sprintf(name, "%s OR %s", syms->symbol, syms->alias); else strcpy(name, syms->symbol); - fprintf(stderr, " %-42s [%s]\n", name, + printf(" %-42s [%s]\n", name, event_type_descriptors[type]); prev_type = type; } - fprintf(stderr, "\n"); + printf("\n"); for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) { for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) { /* skip invalid cache type */ @@ -828,17 +926,20 @@ void print_events(void) continue; for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) { - fprintf(stderr, " %-42s [%s]\n", + printf(" %-42s [%s]\n", event_cache_name(type, op, i), event_type_descriptors[4]); } } } - fprintf(stderr, "\n"); - fprintf(stderr, " %-42s [raw hardware event descriptor]\n", + printf("\n"); + printf(" %-42s [raw hardware event descriptor]\n", "rNNN"); - fprintf(stderr, "\n"); + printf("\n"); + + printf(" %-42s [hardware breakpoint]\n", "mem:<addr>[:access]"); + printf("\n"); print_tracepoint_events(); diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 30c608112845..b8c1f64bc935 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -1,5 +1,5 @@ -#ifndef _PARSE_EVENTS_H -#define _PARSE_EVENTS_H +#ifndef __PERF_PARSE_EVENTS_H +#define __PERF_PARSE_EVENTS_H /* * Parse symbolic events/counts passed in as options: */ @@ -17,11 +17,13 @@ extern struct tracepoint_path *tracepoint_id_to_path(u64 config); extern int nr_counters; extern struct perf_event_attr attrs[MAX_COUNTERS]; +extern char *filters[MAX_COUNTERS]; extern const char *event_name(int ctr); extern const char *__event_name(int type, u64 config); extern int parse_events(const struct option *opt, const char *str, int unset); +extern int parse_filter(const struct option *opt, const char *str, int unset); #define EVENTS_HELP_MAX (128*1024) @@ -31,4 +33,4 @@ extern char debugfs_path[]; extern int valid_debugfs_mount(const char *debugfs); -#endif /* _PARSE_EVENTS_H */ +#endif /* __PERF_PARSE_EVENTS_H */ diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h index 2ee248ff27e5..948805af43c2 100644 --- a/tools/perf/util/parse-options.h +++ b/tools/perf/util/parse-options.h @@ -1,5 +1,5 @@ -#ifndef PARSE_OPTIONS_H -#define PARSE_OPTIONS_H +#ifndef __PERF_PARSE_OPTIONS_H +#define __PERF_PARSE_OPTIONS_H enum parse_opt_type { /* special types */ @@ -174,4 +174,4 @@ extern int parse_opt_verbosity_cb(const struct option *, const char *, int); extern const char *parse_options_fix_filename(const char *prefix, const char *file); -#endif +#endif /* __PERF_PARSE_OPTIONS_H */ diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c new file mode 100644 index 000000000000..cd7fbda5e2a5 --- /dev/null +++ b/tools/perf/util/probe-event.c @@ -0,0 +1,484 @@ +/* + * probe-event.c : perf-probe definition to kprobe_events format converter + * + * Written by Masami Hiramatsu <mhiramat@redhat.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + */ + +#define _GNU_SOURCE +#include <sys/utsname.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <errno.h> +#include <stdio.h> +#include <unistd.h> +#include <stdlib.h> +#include <string.h> +#include <stdarg.h> +#include <limits.h> + +#undef _GNU_SOURCE +#include "event.h" +#include "string.h" +#include "strlist.h" +#include "debug.h" +#include "parse-events.h" /* For debugfs_path */ +#include "probe-event.h" + +#define MAX_CMDLEN 256 +#define MAX_PROBE_ARGS 128 +#define PERFPROBE_GROUP "probe" + +#define semantic_error(msg ...) die("Semantic error :" msg) + +/* If there is no space to write, returns -E2BIG. */ +static int e_snprintf(char *str, size_t size, const char *format, ...) +{ + int ret; + va_list ap; + va_start(ap, format); + ret = vsnprintf(str, size, format, ap); + va_end(ap); + if (ret >= (int)size) + ret = -E2BIG; + return ret; +} + +/* Parse probepoint definition. */ +static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp) +{ + char *ptr, *tmp; + char c, nc = 0; + /* + * <Syntax> + * perf probe SRC:LN + * perf probe FUNC[+OFFS|%return][@SRC] + */ + + ptr = strpbrk(arg, ":+@%"); + if (ptr) { + nc = *ptr; + *ptr++ = '\0'; + } + + /* Check arg is function or file and copy it */ + if (strchr(arg, '.')) /* File */ + pp->file = strdup(arg); + else /* Function */ + pp->function = strdup(arg); + DIE_IF(pp->file == NULL && pp->function == NULL); + + /* Parse other options */ + while (ptr) { + arg = ptr; + c = nc; + ptr = strpbrk(arg, ":+@%"); + if (ptr) { + nc = *ptr; + *ptr++ = '\0'; + } + switch (c) { + case ':': /* Line number */ + pp->line = strtoul(arg, &tmp, 0); + if (*tmp != '\0') + semantic_error("There is non-digit charactor" + " in line number."); + break; + case '+': /* Byte offset from a symbol */ + pp->offset = strtoul(arg, &tmp, 0); + if (*tmp != '\0') + semantic_error("There is non-digit charactor" + " in offset."); + break; + case '@': /* File name */ + if (pp->file) + semantic_error("SRC@SRC is not allowed."); + pp->file = strdup(arg); + DIE_IF(pp->file == NULL); + if (ptr) + semantic_error("@SRC must be the last " + "option."); + break; + case '%': /* Probe places */ + if (strcmp(arg, "return") == 0) { + pp->retprobe = 1; + } else /* Others not supported yet */ + semantic_error("%%%s is not supported.", arg); + break; + default: + DIE_IF("Program has a bug."); + break; + } + } + + /* Exclusion check */ + if (pp->line && pp->offset) + semantic_error("Offset can't be used with line number."); + + if (!pp->line && pp->file && !pp->function) + semantic_error("File always requires line number."); + + if (pp->offset && !pp->function) + semantic_error("Offset requires an entry function."); + + if (pp->retprobe && !pp->function) + semantic_error("Return probe requires an entry function."); + + if ((pp->offset || pp->line) && pp->retprobe) + semantic_error("Offset/Line can't be used with return probe."); + + pr_debug("symbol:%s file:%s line:%d offset:%d, return:%d\n", + pp->function, pp->file, pp->line, pp->offset, pp->retprobe); +} + +/* Parse perf-probe event definition */ +int parse_perf_probe_event(const char *str, struct probe_point *pp) +{ + char **argv; + int argc, i, need_dwarf = 0; + + argv = argv_split(str, &argc); + if (!argv) + die("argv_split failed."); + if (argc > MAX_PROBE_ARGS + 1) + semantic_error("Too many arguments"); + + /* Parse probe point */ + parse_perf_probe_probepoint(argv[0], pp); + if (pp->file || pp->line) + need_dwarf = 1; + + /* Copy arguments and ensure return probe has no C argument */ + pp->nr_args = argc - 1; + pp->args = zalloc(sizeof(char *) * pp->nr_args); + for (i = 0; i < pp->nr_args; i++) { + pp->args[i] = strdup(argv[i + 1]); + if (!pp->args[i]) + die("Failed to copy argument."); + if (is_c_varname(pp->args[i])) { + if (pp->retprobe) + semantic_error("You can't specify local" + " variable for kretprobe"); + need_dwarf = 1; + } + } + + argv_free(argv); + return need_dwarf; +} + +/* Parse kprobe_events event into struct probe_point */ +void parse_trace_kprobe_event(const char *str, char **group, char **event, + struct probe_point *pp) +{ + char pr; + char *p; + int ret, i, argc; + char **argv; + + pr_debug("Parsing kprobe_events: %s\n", str); + argv = argv_split(str, &argc); + if (!argv) + die("argv_split failed."); + if (argc < 2) + semantic_error("Too less arguments."); + + /* Scan event and group name. */ + ret = sscanf(argv[0], "%c:%a[^/ \t]/%a[^ \t]", + &pr, (float *)(void *)group, (float *)(void *)event); + if (ret != 3) + semantic_error("Failed to parse event name: %s", argv[0]); + pr_debug("Group:%s Event:%s probe:%c\n", *group, *event, pr); + + if (!pp) + goto end; + + pp->retprobe = (pr == 'r'); + + /* Scan function name and offset */ + ret = sscanf(argv[1], "%a[^+]+%d", (float *)(void *)&pp->function, &pp->offset); + if (ret == 1) + pp->offset = 0; + + /* kprobe_events doesn't have this information */ + pp->line = 0; + pp->file = NULL; + + pp->nr_args = argc - 2; + pp->args = zalloc(sizeof(char *) * pp->nr_args); + for (i = 0; i < pp->nr_args; i++) { + p = strchr(argv[i + 2], '='); + if (p) /* We don't need which register is assigned. */ + *p = '\0'; + pp->args[i] = strdup(argv[i + 2]); + if (!pp->args[i]) + die("Failed to copy argument."); + } + +end: + argv_free(argv); +} + +int synthesize_perf_probe_event(struct probe_point *pp) +{ + char *buf; + char offs[64] = "", line[64] = ""; + int i, len, ret; + + pp->probes[0] = buf = zalloc(MAX_CMDLEN); + if (!buf) + die("Failed to allocate memory by zalloc."); + if (pp->offset) { + ret = e_snprintf(offs, 64, "+%d", pp->offset); + if (ret <= 0) + goto error; + } + if (pp->line) { + ret = e_snprintf(line, 64, ":%d", pp->line); + if (ret <= 0) + goto error; + } + + if (pp->function) + ret = e_snprintf(buf, MAX_CMDLEN, "%s%s%s%s", pp->function, + offs, pp->retprobe ? "%return" : "", line); + else + ret = e_snprintf(buf, MAX_CMDLEN, "%s%s%s%s", pp->file, line); + if (ret <= 0) + goto error; + len = ret; + + for (i = 0; i < pp->nr_args; i++) { + ret = e_snprintf(&buf[len], MAX_CMDLEN - len, " %s", + pp->args[i]); + if (ret <= 0) + goto error; + len += ret; + } + pp->found = 1; + + return pp->found; +error: + free(pp->probes[0]); + + return ret; +} + +int synthesize_trace_kprobe_event(struct probe_point *pp) +{ + char *buf; + int i, len, ret; + + pp->probes[0] = buf = zalloc(MAX_CMDLEN); + if (!buf) + die("Failed to allocate memory by zalloc."); + ret = e_snprintf(buf, MAX_CMDLEN, "%s+%d", pp->function, pp->offset); + if (ret <= 0) + goto error; + len = ret; + + for (i = 0; i < pp->nr_args; i++) { + ret = e_snprintf(&buf[len], MAX_CMDLEN - len, " %s", + pp->args[i]); + if (ret <= 0) + goto error; + len += ret; + } + pp->found = 1; + + return pp->found; +error: + free(pp->probes[0]); + + return ret; +} + +static int open_kprobe_events(int flags, int mode) +{ + char buf[PATH_MAX]; + int ret; + + ret = e_snprintf(buf, PATH_MAX, "%s/../kprobe_events", debugfs_path); + if (ret < 0) + die("Failed to make kprobe_events path."); + + ret = open(buf, flags, mode); + if (ret < 0) { + if (errno == ENOENT) + die("kprobe_events file does not exist -" + " please rebuild with CONFIG_KPROBE_TRACER."); + else + die("Could not open kprobe_events file: %s", + strerror(errno)); + } + return ret; +} + +/* Get raw string list of current kprobe_events */ +static struct strlist *get_trace_kprobe_event_rawlist(int fd) +{ + int ret, idx; + FILE *fp; + char buf[MAX_CMDLEN]; + char *p; + struct strlist *sl; + + sl = strlist__new(true, NULL); + + fp = fdopen(dup(fd), "r"); + while (!feof(fp)) { + p = fgets(buf, MAX_CMDLEN, fp); + if (!p) + break; + + idx = strlen(p) - 1; + if (p[idx] == '\n') + p[idx] = '\0'; + ret = strlist__add(sl, buf); + if (ret < 0) + die("strlist__add failed: %s", strerror(-ret)); + } + fclose(fp); + + return sl; +} + +/* Free and zero clear probe_point */ +static void clear_probe_point(struct probe_point *pp) +{ + int i; + + if (pp->function) + free(pp->function); + if (pp->file) + free(pp->file); + for (i = 0; i < pp->nr_args; i++) + free(pp->args[i]); + if (pp->args) + free(pp->args); + for (i = 0; i < pp->found; i++) + free(pp->probes[i]); + memset(pp, 0, sizeof(pp)); +} + +/* List up current perf-probe events */ +void show_perf_probe_events(void) +{ + unsigned int i; + int fd; + char *group, *event; + struct probe_point pp; + struct strlist *rawlist; + struct str_node *ent; + + fd = open_kprobe_events(O_RDONLY, 0); + rawlist = get_trace_kprobe_event_rawlist(fd); + close(fd); + + for (i = 0; i < strlist__nr_entries(rawlist); i++) { + ent = strlist__entry(rawlist, i); + parse_trace_kprobe_event(ent->s, &group, &event, &pp); + synthesize_perf_probe_event(&pp); + printf("[%s:%s]\t%s\n", group, event, pp.probes[0]); + free(group); + free(event); + clear_probe_point(&pp); + } + + strlist__delete(rawlist); +} + +/* Get current perf-probe event names */ +static struct strlist *get_perf_event_names(int fd) +{ + unsigned int i; + char *group, *event; + struct strlist *sl, *rawlist; + struct str_node *ent; + + rawlist = get_trace_kprobe_event_rawlist(fd); + + sl = strlist__new(false, NULL); + for (i = 0; i < strlist__nr_entries(rawlist); i++) { + ent = strlist__entry(rawlist, i); + parse_trace_kprobe_event(ent->s, &group, &event, NULL); + strlist__add(sl, event); + free(group); + } + + strlist__delete(rawlist); + + return sl; +} + +static int write_trace_kprobe_event(int fd, const char *buf) +{ + int ret; + + ret = write(fd, buf, strlen(buf)); + if (ret <= 0) + die("Failed to create event."); + else + printf("Added new event: %s\n", buf); + + return ret; +} + +static void get_new_event_name(char *buf, size_t len, const char *base, + struct strlist *namelist) +{ + int i, ret; + for (i = 0; i < MAX_EVENT_INDEX; i++) { + ret = e_snprintf(buf, len, "%s_%d", base, i); + if (ret < 0) + die("snprintf() failed: %s", strerror(-ret)); + if (!strlist__has_entry(namelist, buf)) + break; + } + if (i == MAX_EVENT_INDEX) + die("Too many events are on the same function."); +} + +void add_trace_kprobe_events(struct probe_point *probes, int nr_probes) +{ + int i, j, fd; + struct probe_point *pp; + char buf[MAX_CMDLEN]; + char event[64]; + struct strlist *namelist; + + fd = open_kprobe_events(O_RDWR, O_APPEND); + /* Get current event names */ + namelist = get_perf_event_names(fd); + + for (j = 0; j < nr_probes; j++) { + pp = probes + j; + for (i = 0; i < pp->found; i++) { + /* Get an unused new event name */ + get_new_event_name(event, 64, pp->function, namelist); + snprintf(buf, MAX_CMDLEN, "%c:%s/%s %s\n", + pp->retprobe ? 'r' : 'p', + PERFPROBE_GROUP, event, + pp->probes[i]); + write_trace_kprobe_event(fd, buf); + /* Add added event name to namelist */ + strlist__add(namelist, event); + } + } + close(fd); +} diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h new file mode 100644 index 000000000000..0c6fe56fe38a --- /dev/null +++ b/tools/perf/util/probe-event.h @@ -0,0 +1,18 @@ +#ifndef _PROBE_EVENT_H +#define _PROBE_EVENT_H + +#include "probe-finder.h" +#include "strlist.h" + +extern int parse_perf_probe_event(const char *str, struct probe_point *pp); +extern int synthesize_perf_probe_event(struct probe_point *pp); +extern void parse_trace_kprobe_event(const char *str, char **group, + char **event, struct probe_point *pp); +extern int synthesize_trace_kprobe_event(struct probe_point *pp); +extern void add_trace_kprobe_events(struct probe_point *probes, int nr_probes); +extern void show_perf_probe_events(void); + +/* Maximum index number of event-name postfix */ +#define MAX_EVENT_INDEX 1024 + +#endif /*_PROBE_EVENT_H */ diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c new file mode 100644 index 000000000000..293cdfc1b8ca --- /dev/null +++ b/tools/perf/util/probe-finder.c @@ -0,0 +1,732 @@ +/* + * probe-finder.c : C expression to kprobe event converter + * + * Written by Masami Hiramatsu <mhiramat@redhat.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + */ + +#include <sys/utsname.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <errno.h> +#include <stdio.h> +#include <unistd.h> +#include <getopt.h> +#include <stdlib.h> +#include <string.h> +#include <stdarg.h> +#include <ctype.h> + +#include "event.h" +#include "debug.h" +#include "util.h" +#include "probe-finder.h" + + +/* Dwarf_Die Linkage to parent Die */ +struct die_link { + struct die_link *parent; /* Parent die */ + Dwarf_Die die; /* Current die */ +}; + +static Dwarf_Debug __dw_debug; +static Dwarf_Error __dw_error; + +/* + * Generic dwarf analysis helpers + */ + +#define X86_32_MAX_REGS 8 +const char *x86_32_regs_table[X86_32_MAX_REGS] = { + "%ax", + "%cx", + "%dx", + "%bx", + "$stack", /* Stack address instead of %sp */ + "%bp", + "%si", + "%di", +}; + +#define X86_64_MAX_REGS 16 +const char *x86_64_regs_table[X86_64_MAX_REGS] = { + "%ax", + "%dx", + "%cx", + "%bx", + "%si", + "%di", + "%bp", + "%sp", + "%r8", + "%r9", + "%r10", + "%r11", + "%r12", + "%r13", + "%r14", + "%r15", +}; + +/* TODO: switching by dwarf address size */ +#ifdef __x86_64__ +#define ARCH_MAX_REGS X86_64_MAX_REGS +#define arch_regs_table x86_64_regs_table +#else +#define ARCH_MAX_REGS X86_32_MAX_REGS +#define arch_regs_table x86_32_regs_table +#endif + +/* Return architecture dependent register string (for kprobe-tracer) */ +static const char *get_arch_regstr(unsigned int n) +{ + return (n <= ARCH_MAX_REGS) ? arch_regs_table[n] : NULL; +} + +/* + * Compare the tail of two strings. + * Return 0 if whole of either string is same as another's tail part. + */ +static int strtailcmp(const char *s1, const char *s2) +{ + int i1 = strlen(s1); + int i2 = strlen(s2); + while (--i1 > 0 && --i2 > 0) { + if (s1[i1] != s2[i2]) + return s1[i1] - s2[i2]; + } + return 0; +} + +/* Find the fileno of the target file. */ +static Dwarf_Unsigned cu_find_fileno(Dwarf_Die cu_die, const char *fname) +{ + Dwarf_Signed cnt, i; + Dwarf_Unsigned found = 0; + char **srcs; + int ret; + + if (!fname) + return 0; + + ret = dwarf_srcfiles(cu_die, &srcs, &cnt, &__dw_error); + if (ret == DW_DLV_OK) { + for (i = 0; i < cnt && !found; i++) { + if (strtailcmp(srcs[i], fname) == 0) + found = i + 1; + dwarf_dealloc(__dw_debug, srcs[i], DW_DLA_STRING); + } + for (; i < cnt; i++) + dwarf_dealloc(__dw_debug, srcs[i], DW_DLA_STRING); + dwarf_dealloc(__dw_debug, srcs, DW_DLA_LIST); + } + if (found) + pr_debug("found fno: %d\n", (int)found); + return found; +} + +/* Compare diename and tname */ +static int die_compare_name(Dwarf_Die dw_die, const char *tname) +{ + char *name; + int ret; + ret = dwarf_diename(dw_die, &name, &__dw_error); + DIE_IF(ret == DW_DLV_ERROR); + if (ret == DW_DLV_OK) { + ret = strcmp(tname, name); + dwarf_dealloc(__dw_debug, name, DW_DLA_STRING); + } else + ret = -1; + return ret; +} + +/* Check the address is in the subprogram(function). */ +static int die_within_subprogram(Dwarf_Die sp_die, Dwarf_Addr addr, + Dwarf_Signed *offs) +{ + Dwarf_Addr lopc, hipc; + int ret; + + /* TODO: check ranges */ + ret = dwarf_lowpc(sp_die, &lopc, &__dw_error); + DIE_IF(ret == DW_DLV_ERROR); + if (ret == DW_DLV_NO_ENTRY) + return 0; + ret = dwarf_highpc(sp_die, &hipc, &__dw_error); + DIE_IF(ret != DW_DLV_OK); + if (lopc <= addr && addr < hipc) { + *offs = addr - lopc; + return 1; + } else + return 0; +} + +/* Check the die is inlined function */ +static Dwarf_Bool die_inlined_subprogram(Dwarf_Die dw_die) +{ + /* TODO: check strictly */ + Dwarf_Bool inl; + int ret; + + ret = dwarf_hasattr(dw_die, DW_AT_inline, &inl, &__dw_error); + DIE_IF(ret == DW_DLV_ERROR); + return inl; +} + +/* Get the offset of abstruct_origin */ +static Dwarf_Off die_get_abstract_origin(Dwarf_Die dw_die) +{ + Dwarf_Attribute attr; + Dwarf_Off cu_offs; + int ret; + + ret = dwarf_attr(dw_die, DW_AT_abstract_origin, &attr, &__dw_error); + DIE_IF(ret != DW_DLV_OK); + ret = dwarf_formref(attr, &cu_offs, &__dw_error); + DIE_IF(ret != DW_DLV_OK); + dwarf_dealloc(__dw_debug, attr, DW_DLA_ATTR); + return cu_offs; +} + +/* Get entry pc(or low pc, 1st entry of ranges) of the die */ +static Dwarf_Addr die_get_entrypc(Dwarf_Die dw_die) +{ + Dwarf_Attribute attr; + Dwarf_Addr addr; + Dwarf_Off offs; + Dwarf_Ranges *ranges; + Dwarf_Signed cnt; + int ret; + + /* Try to get entry pc */ + ret = dwarf_attr(dw_die, DW_AT_entry_pc, &attr, &__dw_error); + DIE_IF(ret == DW_DLV_ERROR); + if (ret == DW_DLV_OK) { + ret = dwarf_formaddr(attr, &addr, &__dw_error); + DIE_IF(ret != DW_DLV_OK); + dwarf_dealloc(__dw_debug, attr, DW_DLA_ATTR); + return addr; + } + + /* Try to get low pc */ + ret = dwarf_lowpc(dw_die, &addr, &__dw_error); + DIE_IF(ret == DW_DLV_ERROR); + if (ret == DW_DLV_OK) + return addr; + + /* Try to get ranges */ + ret = dwarf_attr(dw_die, DW_AT_ranges, &attr, &__dw_error); + DIE_IF(ret != DW_DLV_OK); + ret = dwarf_formref(attr, &offs, &__dw_error); + DIE_IF(ret != DW_DLV_OK); + ret = dwarf_get_ranges(__dw_debug, offs, &ranges, &cnt, NULL, + &__dw_error); + DIE_IF(ret != DW_DLV_OK); + addr = ranges[0].dwr_addr1; + dwarf_ranges_dealloc(__dw_debug, ranges, cnt); + return addr; +} + +/* + * Search a Die from Die tree. + * Note: cur_link->die should be deallocated in this function. + */ +static int __search_die_tree(struct die_link *cur_link, + int (*die_cb)(struct die_link *, void *), + void *data) +{ + Dwarf_Die new_die; + struct die_link new_link; + int ret; + + if (!die_cb) + return 0; + + /* Check current die */ + while (!(ret = die_cb(cur_link, data))) { + /* Check child die */ + ret = dwarf_child(cur_link->die, &new_die, &__dw_error); + DIE_IF(ret == DW_DLV_ERROR); + if (ret == DW_DLV_OK) { + new_link.parent = cur_link; + new_link.die = new_die; + ret = __search_die_tree(&new_link, die_cb, data); + if (ret) + break; + } + + /* Move to next sibling */ + ret = dwarf_siblingof(__dw_debug, cur_link->die, &new_die, + &__dw_error); + DIE_IF(ret == DW_DLV_ERROR); + dwarf_dealloc(__dw_debug, cur_link->die, DW_DLA_DIE); + cur_link->die = new_die; + if (ret == DW_DLV_NO_ENTRY) + return 0; + } + dwarf_dealloc(__dw_debug, cur_link->die, DW_DLA_DIE); + return ret; +} + +/* Search a die in its children's die tree */ +static int search_die_from_children(Dwarf_Die parent_die, + int (*die_cb)(struct die_link *, void *), + void *data) +{ + struct die_link new_link; + int ret; + + new_link.parent = NULL; + ret = dwarf_child(parent_die, &new_link.die, &__dw_error); + DIE_IF(ret == DW_DLV_ERROR); + if (ret == DW_DLV_OK) + return __search_die_tree(&new_link, die_cb, data); + else + return 0; +} + +/* Find a locdesc corresponding to the address */ +static int attr_get_locdesc(Dwarf_Attribute attr, Dwarf_Locdesc *desc, + Dwarf_Addr addr) +{ + Dwarf_Signed lcnt; + Dwarf_Locdesc **llbuf; + int ret, i; + + ret = dwarf_loclist_n(attr, &llbuf, &lcnt, &__dw_error); + DIE_IF(ret != DW_DLV_OK); + ret = DW_DLV_NO_ENTRY; + for (i = 0; i < lcnt; ++i) { + if (llbuf[i]->ld_lopc <= addr && + llbuf[i]->ld_hipc > addr) { + memcpy(desc, llbuf[i], sizeof(Dwarf_Locdesc)); + desc->ld_s = + malloc(sizeof(Dwarf_Loc) * llbuf[i]->ld_cents); + DIE_IF(desc->ld_s == NULL); + memcpy(desc->ld_s, llbuf[i]->ld_s, + sizeof(Dwarf_Loc) * llbuf[i]->ld_cents); + ret = DW_DLV_OK; + break; + } + dwarf_dealloc(__dw_debug, llbuf[i]->ld_s, DW_DLA_LOC_BLOCK); + dwarf_dealloc(__dw_debug, llbuf[i], DW_DLA_LOCDESC); + } + /* Releasing loop */ + for (; i < lcnt; ++i) { + dwarf_dealloc(__dw_debug, llbuf[i]->ld_s, DW_DLA_LOC_BLOCK); + dwarf_dealloc(__dw_debug, llbuf[i], DW_DLA_LOCDESC); + } + dwarf_dealloc(__dw_debug, llbuf, DW_DLA_LIST); + return ret; +} + +/* Get decl_file attribute value (file number) */ +static Dwarf_Unsigned die_get_decl_file(Dwarf_Die sp_die) +{ + Dwarf_Attribute attr; + Dwarf_Unsigned fno; + int ret; + + ret = dwarf_attr(sp_die, DW_AT_decl_file, &attr, &__dw_error); + DIE_IF(ret != DW_DLV_OK); + dwarf_formudata(attr, &fno, &__dw_error); + DIE_IF(ret != DW_DLV_OK); + dwarf_dealloc(__dw_debug, attr, DW_DLA_ATTR); + return fno; +} + +/* Get decl_line attribute value (line number) */ +static Dwarf_Unsigned die_get_decl_line(Dwarf_Die sp_die) +{ + Dwarf_Attribute attr; + Dwarf_Unsigned lno; + int ret; + + ret = dwarf_attr(sp_die, DW_AT_decl_line, &attr, &__dw_error); + DIE_IF(ret != DW_DLV_OK); + dwarf_formudata(attr, &lno, &__dw_error); + DIE_IF(ret != DW_DLV_OK); + dwarf_dealloc(__dw_debug, attr, DW_DLA_ATTR); + return lno; +} + +/* + * Probe finder related functions + */ + +/* Show a location */ +static void show_location(Dwarf_Loc *loc, struct probe_finder *pf) +{ + Dwarf_Small op; + Dwarf_Unsigned regn; + Dwarf_Signed offs; + int deref = 0, ret; + const char *regs; + + op = loc->lr_atom; + + /* If this is based on frame buffer, set the offset */ + if (op == DW_OP_fbreg) { + deref = 1; + offs = (Dwarf_Signed)loc->lr_number; + op = pf->fbloc.ld_s[0].lr_atom; + loc = &pf->fbloc.ld_s[0]; + } else + offs = 0; + + if (op >= DW_OP_breg0 && op <= DW_OP_breg31) { + regn = op - DW_OP_breg0; + offs += (Dwarf_Signed)loc->lr_number; + deref = 1; + } else if (op >= DW_OP_reg0 && op <= DW_OP_reg31) { + regn = op - DW_OP_reg0; + } else if (op == DW_OP_bregx) { + regn = loc->lr_number; + offs += (Dwarf_Signed)loc->lr_number2; + deref = 1; + } else if (op == DW_OP_regx) { + regn = loc->lr_number; + } else + die("Dwarf_OP %d is not supported.\n", op); + + regs = get_arch_regstr(regn); + if (!regs) + die("%lld exceeds max register number.\n", regn); + + if (deref) + ret = snprintf(pf->buf, pf->len, + " %s=%+lld(%s)", pf->var, offs, regs); + else + ret = snprintf(pf->buf, pf->len, " %s=%s", pf->var, regs); + DIE_IF(ret < 0); + DIE_IF(ret >= pf->len); +} + +/* Show a variables in kprobe event format */ +static void show_variable(Dwarf_Die vr_die, struct probe_finder *pf) +{ + Dwarf_Attribute attr; + Dwarf_Locdesc ld; + int ret; + + ret = dwarf_attr(vr_die, DW_AT_location, &attr, &__dw_error); + if (ret != DW_DLV_OK) + goto error; + ret = attr_get_locdesc(attr, &ld, (pf->addr - pf->cu_base)); + if (ret != DW_DLV_OK) + goto error; + /* TODO? */ + DIE_IF(ld.ld_cents != 1); + show_location(&ld.ld_s[0], pf); + free(ld.ld_s); + dwarf_dealloc(__dw_debug, attr, DW_DLA_ATTR); + return ; +error: + die("Failed to find the location of %s at this address.\n" + " Perhaps, it has been optimized out.\n", pf->var); +} + +static int variable_callback(struct die_link *dlink, void *data) +{ + struct probe_finder *pf = (struct probe_finder *)data; + Dwarf_Half tag; + int ret; + + ret = dwarf_tag(dlink->die, &tag, &__dw_error); + DIE_IF(ret == DW_DLV_ERROR); + if ((tag == DW_TAG_formal_parameter || + tag == DW_TAG_variable) && + (die_compare_name(dlink->die, pf->var) == 0)) { + show_variable(dlink->die, pf); + return 1; + } + /* TODO: Support struct members and arrays */ + return 0; +} + +/* Find a variable in a subprogram die */ +static void find_variable(Dwarf_Die sp_die, struct probe_finder *pf) +{ + int ret; + + if (!is_c_varname(pf->var)) { + /* Output raw parameters */ + ret = snprintf(pf->buf, pf->len, " %s", pf->var); + DIE_IF(ret < 0); + DIE_IF(ret >= pf->len); + return ; + } + + pr_debug("Searching '%s' variable in context.\n", pf->var); + /* Search child die for local variables and parameters. */ + ret = search_die_from_children(sp_die, variable_callback, pf); + if (!ret) + die("Failed to find '%s' in this function.\n", pf->var); +} + +/* Get a frame base on the address */ +static void get_current_frame_base(Dwarf_Die sp_die, struct probe_finder *pf) +{ + Dwarf_Attribute attr; + int ret; + + ret = dwarf_attr(sp_die, DW_AT_frame_base, &attr, &__dw_error); + DIE_IF(ret != DW_DLV_OK); + ret = attr_get_locdesc(attr, &pf->fbloc, (pf->addr - pf->cu_base)); + DIE_IF(ret != DW_DLV_OK); + dwarf_dealloc(__dw_debug, attr, DW_DLA_ATTR); +} + +static void free_current_frame_base(struct probe_finder *pf) +{ + free(pf->fbloc.ld_s); + memset(&pf->fbloc, 0, sizeof(Dwarf_Locdesc)); +} + +/* Show a probe point to output buffer */ +static void show_probepoint(Dwarf_Die sp_die, Dwarf_Signed offs, + struct probe_finder *pf) +{ + struct probe_point *pp = pf->pp; + char *name; + char tmp[MAX_PROBE_BUFFER]; + int ret, i, len; + + /* Output name of probe point */ + ret = dwarf_diename(sp_die, &name, &__dw_error); + DIE_IF(ret == DW_DLV_ERROR); + if (ret == DW_DLV_OK) { + ret = snprintf(tmp, MAX_PROBE_BUFFER, "%s+%u", name, + (unsigned int)offs); + /* Copy the function name if possible */ + if (!pp->function) { + pp->function = strdup(name); + pp->offset = offs; + } + dwarf_dealloc(__dw_debug, name, DW_DLA_STRING); + } else { + /* This function has no name. */ + ret = snprintf(tmp, MAX_PROBE_BUFFER, "0x%llx", pf->addr); + if (!pp->function) { + /* TODO: Use _stext */ + pp->function = strdup(""); + pp->offset = (int)pf->addr; + } + } + DIE_IF(ret < 0); + DIE_IF(ret >= MAX_PROBE_BUFFER); + len = ret; + pr_debug("Probe point found: %s\n", tmp); + + /* Find each argument */ + get_current_frame_base(sp_die, pf); + for (i = 0; i < pp->nr_args; i++) { + pf->var = pp->args[i]; + pf->buf = &tmp[len]; + pf->len = MAX_PROBE_BUFFER - len; + find_variable(sp_die, pf); + len += strlen(pf->buf); + } + free_current_frame_base(pf); + + pp->probes[pp->found] = strdup(tmp); + pp->found++; +} + +static int probeaddr_callback(struct die_link *dlink, void *data) +{ + struct probe_finder *pf = (struct probe_finder *)data; + Dwarf_Half tag; + Dwarf_Signed offs; + int ret; + + ret = dwarf_tag(dlink->die, &tag, &__dw_error); + DIE_IF(ret == DW_DLV_ERROR); + /* Check the address is in this subprogram */ + if (tag == DW_TAG_subprogram && + die_within_subprogram(dlink->die, pf->addr, &offs)) { + show_probepoint(dlink->die, offs, pf); + return 1; + } + return 0; +} + +/* Find probe point from its line number */ +static void find_by_line(struct probe_finder *pf) +{ + Dwarf_Signed cnt, i, clm; + Dwarf_Line *lines; + Dwarf_Unsigned lineno = 0; + Dwarf_Addr addr; + Dwarf_Unsigned fno; + int ret; + + ret = dwarf_srclines(pf->cu_die, &lines, &cnt, &__dw_error); + DIE_IF(ret != DW_DLV_OK); + + for (i = 0; i < cnt; i++) { + ret = dwarf_line_srcfileno(lines[i], &fno, &__dw_error); + DIE_IF(ret != DW_DLV_OK); + if (fno != pf->fno) + continue; + + ret = dwarf_lineno(lines[i], &lineno, &__dw_error); + DIE_IF(ret != DW_DLV_OK); + if (lineno != pf->lno) + continue; + + ret = dwarf_lineoff(lines[i], &clm, &__dw_error); + DIE_IF(ret != DW_DLV_OK); + + ret = dwarf_lineaddr(lines[i], &addr, &__dw_error); + DIE_IF(ret != DW_DLV_OK); + pr_debug("Probe line found: line[%d]:%u,%d addr:0x%llx\n", + (int)i, (unsigned)lineno, (int)clm, addr); + pf->addr = addr; + /* Search a real subprogram including this line, */ + ret = search_die_from_children(pf->cu_die, + probeaddr_callback, pf); + if (ret == 0) + die("Probe point is not found in subprograms.\n"); + /* Continuing, because target line might be inlined. */ + } + dwarf_srclines_dealloc(__dw_debug, lines, cnt); +} + +/* Search function from function name */ +static int probefunc_callback(struct die_link *dlink, void *data) +{ + struct probe_finder *pf = (struct probe_finder *)data; + struct probe_point *pp = pf->pp; + struct die_link *lk; + Dwarf_Signed offs; + Dwarf_Half tag; + int ret; + + ret = dwarf_tag(dlink->die, &tag, &__dw_error); + DIE_IF(ret == DW_DLV_ERROR); + if (tag == DW_TAG_subprogram) { + if (die_compare_name(dlink->die, pp->function) == 0) { + if (pp->line) { /* Function relative line */ + pf->fno = die_get_decl_file(dlink->die); + pf->lno = die_get_decl_line(dlink->die) + + pp->line; + find_by_line(pf); + return 1; + } + if (die_inlined_subprogram(dlink->die)) { + /* Inlined function, save it. */ + ret = dwarf_die_CU_offset(dlink->die, + &pf->inl_offs, + &__dw_error); + DIE_IF(ret != DW_DLV_OK); + pr_debug("inline definition offset %lld\n", + pf->inl_offs); + return 0; /* Continue to search */ + } + /* Get probe address */ + pf->addr = die_get_entrypc(dlink->die); + pf->addr += pp->offset; + /* TODO: Check the address in this function */ + show_probepoint(dlink->die, pp->offset, pf); + return 1; /* Exit; no same symbol in this CU. */ + } + } else if (tag == DW_TAG_inlined_subroutine && pf->inl_offs) { + if (die_get_abstract_origin(dlink->die) == pf->inl_offs) { + /* Get probe address */ + pf->addr = die_get_entrypc(dlink->die); + pf->addr += pp->offset; + pr_debug("found inline addr: 0x%llx\n", pf->addr); + /* Inlined function. Get a real subprogram */ + for (lk = dlink->parent; lk != NULL; lk = lk->parent) { + tag = 0; + dwarf_tag(lk->die, &tag, &__dw_error); + DIE_IF(ret == DW_DLV_ERROR); + if (tag == DW_TAG_subprogram && + !die_inlined_subprogram(lk->die)) + goto found; + } + die("Failed to find real subprogram.\n"); +found: + /* Get offset from subprogram */ + ret = die_within_subprogram(lk->die, pf->addr, &offs); + DIE_IF(!ret); + show_probepoint(lk->die, offs, pf); + /* Continue to search */ + } + } + return 0; +} + +static void find_by_func(struct probe_finder *pf) +{ + search_die_from_children(pf->cu_die, probefunc_callback, pf); +} + +/* Find a probe point */ +int find_probepoint(int fd, struct probe_point *pp) +{ + Dwarf_Half addr_size = 0; + Dwarf_Unsigned next_cuh = 0; + int cu_number = 0, ret; + struct probe_finder pf = {.pp = pp}; + + ret = dwarf_init(fd, DW_DLC_READ, 0, 0, &__dw_debug, &__dw_error); + if (ret != DW_DLV_OK) { + pr_warning("No dwarf info found in the vmlinux - please rebuild with CONFIG_DEBUG_INFO.\n"); + return -ENOENT; + } + + pp->found = 0; + while (++cu_number) { + /* Search CU (Compilation Unit) */ + ret = dwarf_next_cu_header(__dw_debug, NULL, NULL, NULL, + &addr_size, &next_cuh, &__dw_error); + DIE_IF(ret == DW_DLV_ERROR); + if (ret == DW_DLV_NO_ENTRY) + break; + + /* Get the DIE(Debugging Information Entry) of this CU */ + ret = dwarf_siblingof(__dw_debug, 0, &pf.cu_die, &__dw_error); + DIE_IF(ret != DW_DLV_OK); + + /* Check if target file is included. */ + if (pp->file) + pf.fno = cu_find_fileno(pf.cu_die, pp->file); + + if (!pp->file || pf.fno) { + /* Save CU base address (for frame_base) */ + ret = dwarf_lowpc(pf.cu_die, &pf.cu_base, &__dw_error); + DIE_IF(ret == DW_DLV_ERROR); + if (ret == DW_DLV_NO_ENTRY) + pf.cu_base = 0; + if (pp->function) + find_by_func(&pf); + else { + pf.lno = pp->line; + find_by_line(&pf); + } + } + dwarf_dealloc(__dw_debug, pf.cu_die, DW_DLA_DIE); + } + ret = dwarf_finish(__dw_debug, &__dw_error); + DIE_IF(ret != DW_DLV_OK); + + return pp->found; +} + diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h new file mode 100644 index 000000000000..bdebca6697d2 --- /dev/null +++ b/tools/perf/util/probe-finder.h @@ -0,0 +1,57 @@ +#ifndef _PROBE_FINDER_H +#define _PROBE_FINDER_H + +#define MAX_PATH_LEN 256 +#define MAX_PROBE_BUFFER 1024 +#define MAX_PROBES 128 + +static inline int is_c_varname(const char *name) +{ + /* TODO */ + return isalpha(name[0]) || name[0] == '_'; +} + +struct probe_point { + /* Inputs */ + char *file; /* File name */ + int line; /* Line number */ + + char *function; /* Function name */ + int offset; /* Offset bytes */ + + int nr_args; /* Number of arguments */ + char **args; /* Arguments */ + + int retprobe; /* Return probe */ + + /* Output */ + int found; /* Number of found probe points */ + char *probes[MAX_PROBES]; /* Output buffers (will be allocated)*/ +}; + +#ifndef NO_LIBDWARF +extern int find_probepoint(int fd, struct probe_point *pp); + +#include <libdwarf/dwarf.h> +#include <libdwarf/libdwarf.h> + +struct probe_finder { + struct probe_point *pp; /* Target probe point */ + + /* For function searching */ + Dwarf_Addr addr; /* Address */ + Dwarf_Unsigned fno; /* File number */ + Dwarf_Unsigned lno; /* Line number */ + Dwarf_Off inl_offs; /* Inline offset */ + Dwarf_Die cu_die; /* Current CU */ + + /* For variable searching */ + Dwarf_Addr cu_base; /* Current CU base address */ + Dwarf_Locdesc fbloc; /* Location of Current Frame Base */ + const char *var; /* Current variable name */ + char *buf; /* Current output buffer */ + int len; /* Length of output buffer */ +}; +#endif /* NO_LIBDWARF */ + +#endif /*_PROBE_FINDER_H */ diff --git a/tools/perf/util/quote.h b/tools/perf/util/quote.h index a5454a1d1c13..b6a019733919 100644 --- a/tools/perf/util/quote.h +++ b/tools/perf/util/quote.h @@ -1,5 +1,5 @@ -#ifndef QUOTE_H -#define QUOTE_H +#ifndef __PERF_QUOTE_H +#define __PERF_QUOTE_H #include <stddef.h> #include <stdio.h> @@ -65,4 +65,4 @@ extern void perl_quote_print(FILE *stream, const char *src); extern void python_quote_print(FILE *stream, const char *src); extern void tcl_quote_print(FILE *stream, const char *src); -#endif +#endif /* __PERF_QUOTE_H */ diff --git a/tools/perf/util/run-command.h b/tools/perf/util/run-command.h index cc1837deba88..d79028727ce2 100644 --- a/tools/perf/util/run-command.h +++ b/tools/perf/util/run-command.h @@ -1,5 +1,5 @@ -#ifndef RUN_COMMAND_H -#define RUN_COMMAND_H +#ifndef __PERF_RUN_COMMAND_H +#define __PERF_RUN_COMMAND_H enum { ERR_RUN_COMMAND_FORK = 10000, @@ -85,4 +85,4 @@ struct async { int start_async(struct async *async); int finish_async(struct async *async); -#endif +#endif /* __PERF_RUN_COMMAND_H */ diff --git a/tools/perf/util/sigchain.h b/tools/perf/util/sigchain.h index 618083bce0c6..1a53c11265fd 100644 --- a/tools/perf/util/sigchain.h +++ b/tools/perf/util/sigchain.h @@ -1,5 +1,5 @@ -#ifndef SIGCHAIN_H -#define SIGCHAIN_H +#ifndef __PERF_SIGCHAIN_H +#define __PERF_SIGCHAIN_H typedef void (*sigchain_fun)(int); @@ -8,4 +8,4 @@ int sigchain_pop(int sig); void sigchain_push_common(sigchain_fun f); -#endif /* SIGCHAIN_H */ +#endif /* __PERF_SIGCHAIN_H */ diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c new file mode 100644 index 000000000000..b490354d1b23 --- /dev/null +++ b/tools/perf/util/sort.c @@ -0,0 +1,290 @@ +#include "sort.h" + +regex_t parent_regex; +char default_parent_pattern[] = "^sys_|^do_page_fault"; +char *parent_pattern = default_parent_pattern; +char default_sort_order[] = "comm,dso,symbol"; +char *sort_order = default_sort_order; +int sort__need_collapse = 0; +int sort__has_parent = 0; + +enum sort_type sort__first_dimension; + +unsigned int dsos__col_width; +unsigned int comms__col_width; +unsigned int threads__col_width; +static unsigned int parent_symbol__col_width; +char * field_sep; + +LIST_HEAD(hist_entry__sort_list); + +struct sort_entry sort_thread = { + .header = "Command: Pid", + .cmp = sort__thread_cmp, + .print = sort__thread_print, + .width = &threads__col_width, +}; + +struct sort_entry sort_comm = { + .header = "Command", + .cmp = sort__comm_cmp, + .collapse = sort__comm_collapse, + .print = sort__comm_print, + .width = &comms__col_width, +}; + +struct sort_entry sort_dso = { + .header = "Shared Object", + .cmp = sort__dso_cmp, + .print = sort__dso_print, + .width = &dsos__col_width, +}; + +struct sort_entry sort_sym = { + .header = "Symbol", + .cmp = sort__sym_cmp, + .print = sort__sym_print, +}; + +struct sort_entry sort_parent = { + .header = "Parent symbol", + .cmp = sort__parent_cmp, + .print = sort__parent_print, + .width = &parent_symbol__col_width, +}; + +struct sort_dimension { + const char *name; + struct sort_entry *entry; + int taken; +}; + +static struct sort_dimension sort_dimensions[] = { + { .name = "pid", .entry = &sort_thread, }, + { .name = "comm", .entry = &sort_comm, }, + { .name = "dso", .entry = &sort_dso, }, + { .name = "symbol", .entry = &sort_sym, }, + { .name = "parent", .entry = &sort_parent, }, +}; + +int64_t cmp_null(void *l, void *r) +{ + if (!l && !r) + return 0; + else if (!l) + return -1; + else + return 1; +} + +/* --sort pid */ + +int64_t +sort__thread_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return right->thread->pid - left->thread->pid; +} + +int repsep_fprintf(FILE *fp, const char *fmt, ...) +{ + int n; + va_list ap; + + va_start(ap, fmt); + if (!field_sep) + n = vfprintf(fp, fmt, ap); + else { + char *bf = NULL; + n = vasprintf(&bf, fmt, ap); + if (n > 0) { + char *sep = bf; + + while (1) { + sep = strchr(sep, *field_sep); + if (sep == NULL) + break; + *sep = '.'; + } + } + fputs(bf, fp); + free(bf); + } + va_end(ap); + return n; +} + +size_t +sort__thread_print(FILE *fp, struct hist_entry *self, unsigned int width) +{ + return repsep_fprintf(fp, "%*s:%5d", width - 6, + self->thread->comm ?: "", self->thread->pid); +} + +size_t +sort__comm_print(FILE *fp, struct hist_entry *self, unsigned int width) +{ + return repsep_fprintf(fp, "%*s", width, self->thread->comm); +} + +/* --sort dso */ + +int64_t +sort__dso_cmp(struct hist_entry *left, struct hist_entry *right) +{ + struct dso *dso_l = left->map ? left->map->dso : NULL; + struct dso *dso_r = right->map ? right->map->dso : NULL; + const char *dso_name_l, *dso_name_r; + + if (!dso_l || !dso_r) + return cmp_null(dso_l, dso_r); + + if (verbose) { + dso_name_l = dso_l->long_name; + dso_name_r = dso_r->long_name; + } else { + dso_name_l = dso_l->short_name; + dso_name_r = dso_r->short_name; + } + + return strcmp(dso_name_l, dso_name_r); +} + +size_t +sort__dso_print(FILE *fp, struct hist_entry *self, unsigned int width) +{ + if (self->map && self->map->dso) { + const char *dso_name = !verbose ? self->map->dso->short_name : + self->map->dso->long_name; + return repsep_fprintf(fp, "%-*s", width, dso_name); + } + + return repsep_fprintf(fp, "%*llx", width, (u64)self->ip); +} + +/* --sort symbol */ + +int64_t +sort__sym_cmp(struct hist_entry *left, struct hist_entry *right) +{ + u64 ip_l, ip_r; + + if (left->sym == right->sym) + return 0; + + ip_l = left->sym ? left->sym->start : left->ip; + ip_r = right->sym ? right->sym->start : right->ip; + + return (int64_t)(ip_r - ip_l); +} + + +size_t +sort__sym_print(FILE *fp, struct hist_entry *self, unsigned int width __used) +{ + size_t ret = 0; + + if (verbose) { + char o = self->map ? dso__symtab_origin(self->map->dso) : '!'; + ret += repsep_fprintf(fp, "%#018llx %c ", (u64)self->ip, o); + } + + ret += repsep_fprintf(fp, "[%c] ", self->level); + if (self->sym) + ret += repsep_fprintf(fp, "%s", self->sym->name); + else + ret += repsep_fprintf(fp, "%#016llx", (u64)self->ip); + + return ret; +} + +/* --sort comm */ + +int64_t +sort__comm_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return right->thread->pid - left->thread->pid; +} + +int64_t +sort__comm_collapse(struct hist_entry *left, struct hist_entry *right) +{ + char *comm_l = left->thread->comm; + char *comm_r = right->thread->comm; + + if (!comm_l || !comm_r) + return cmp_null(comm_l, comm_r); + + return strcmp(comm_l, comm_r); +} + +/* --sort parent */ + +int64_t +sort__parent_cmp(struct hist_entry *left, struct hist_entry *right) +{ + struct symbol *sym_l = left->parent; + struct symbol *sym_r = right->parent; + + if (!sym_l || !sym_r) + return cmp_null(sym_l, sym_r); + + return strcmp(sym_l->name, sym_r->name); +} + +size_t +sort__parent_print(FILE *fp, struct hist_entry *self, unsigned int width) +{ + return repsep_fprintf(fp, "%-*s", width, + self->parent ? self->parent->name : "[other]"); +} + +int sort_dimension__add(const char *tok) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(sort_dimensions); i++) { + struct sort_dimension *sd = &sort_dimensions[i]; + + if (sd->taken) + continue; + + if (strncasecmp(tok, sd->name, strlen(tok))) + continue; + + if (sd->entry->collapse) + sort__need_collapse = 1; + + if (sd->entry == &sort_parent) { + int ret = regcomp(&parent_regex, parent_pattern, REG_EXTENDED); + if (ret) { + char err[BUFSIZ]; + + regerror(ret, &parent_regex, err, sizeof(err)); + fprintf(stderr, "Invalid regex: %s\n%s", + parent_pattern, err); + exit(-1); + } + sort__has_parent = 1; + } + + if (list_empty(&hist_entry__sort_list)) { + if (!strcmp(sd->name, "pid")) + sort__first_dimension = SORT_PID; + else if (!strcmp(sd->name, "comm")) + sort__first_dimension = SORT_COMM; + else if (!strcmp(sd->name, "dso")) + sort__first_dimension = SORT_DSO; + else if (!strcmp(sd->name, "symbol")) + sort__first_dimension = SORT_SYM; + else if (!strcmp(sd->name, "parent")) + sort__first_dimension = SORT_PARENT; + } + + list_add_tail(&sd->entry->list, &hist_entry__sort_list); + sd->taken = 1; + + return 0; + } + + return -ESRCH; +} diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h new file mode 100644 index 000000000000..333e664ff45f --- /dev/null +++ b/tools/perf/util/sort.h @@ -0,0 +1,99 @@ +#ifndef __PERF_SORT_H +#define __PERF_SORT_H +#include "../builtin.h" + +#include "util.h" + +#include "color.h" +#include <linux/list.h> +#include "cache.h" +#include <linux/rbtree.h> +#include "symbol.h" +#include "string.h" +#include "callchain.h" +#include "strlist.h" +#include "values.h" + +#include "../perf.h" +#include "debug.h" +#include "header.h" + +#include "parse-options.h" +#include "parse-events.h" + +#include "thread.h" +#include "sort.h" + +extern regex_t parent_regex; +extern char *sort_order; +extern char default_parent_pattern[]; +extern char *parent_pattern; +extern char default_sort_order[]; +extern int sort__need_collapse; +extern int sort__has_parent; +extern char *field_sep; +extern struct sort_entry sort_comm; +extern struct sort_entry sort_dso; +extern struct sort_entry sort_sym; +extern struct sort_entry sort_parent; +extern unsigned int dsos__col_width; +extern unsigned int comms__col_width; +extern unsigned int threads__col_width; +extern enum sort_type sort__first_dimension; + +struct hist_entry { + struct rb_node rb_node; + u64 count; + struct thread *thread; + struct map *map; + struct symbol *sym; + u64 ip; + char level; + struct symbol *parent; + struct callchain_node callchain; + struct rb_root sorted_chain; +}; + +enum sort_type { + SORT_PID, + SORT_COMM, + SORT_DSO, + SORT_SYM, + SORT_PARENT +}; + +/* + * configurable sorting bits + */ + +struct sort_entry { + struct list_head list; + + const char *header; + + int64_t (*cmp)(struct hist_entry *, struct hist_entry *); + int64_t (*collapse)(struct hist_entry *, struct hist_entry *); + size_t (*print)(FILE *fp, struct hist_entry *, unsigned int width); + unsigned int *width; + bool elide; +}; + +extern struct sort_entry sort_thread; +extern struct list_head hist_entry__sort_list; + +extern int repsep_fprintf(FILE *fp, const char *fmt, ...); +extern size_t sort__thread_print(FILE *, struct hist_entry *, unsigned int); +extern size_t sort__comm_print(FILE *, struct hist_entry *, unsigned int); +extern size_t sort__dso_print(FILE *, struct hist_entry *, unsigned int); +extern size_t sort__sym_print(FILE *, struct hist_entry *, unsigned int __used); +extern int64_t cmp_null(void *, void *); +extern int64_t sort__thread_cmp(struct hist_entry *, struct hist_entry *); +extern int64_t sort__comm_cmp(struct hist_entry *, struct hist_entry *); +extern int64_t sort__comm_collapse(struct hist_entry *, struct hist_entry *); +extern int64_t sort__dso_cmp(struct hist_entry *, struct hist_entry *); +extern int64_t sort__sym_cmp(struct hist_entry *, struct hist_entry *); +extern int64_t sort__parent_cmp(struct hist_entry *, struct hist_entry *); +extern size_t sort__parent_print(FILE *, struct hist_entry *, unsigned int); +extern int sort_dimension__add(const char *); + +#endif /* __PERF_SORT_H */ diff --git a/tools/perf/util/strbuf.h b/tools/perf/util/strbuf.h index d2aa86c014c1..a3d121d6c83e 100644 --- a/tools/perf/util/strbuf.h +++ b/tools/perf/util/strbuf.h @@ -1,5 +1,5 @@ -#ifndef STRBUF_H -#define STRBUF_H +#ifndef __PERF_STRBUF_H +#define __PERF_STRBUF_H /* * Strbuf's can be use in many ways: as a byte array, or to store arbitrary @@ -134,4 +134,4 @@ extern int launch_editor(const char *path, struct strbuf *buffer, const char *co extern int strbuf_branchname(struct strbuf *sb, const char *name); extern int strbuf_check_branch_ref(struct strbuf *sb, const char *name); -#endif /* STRBUF_H */ +#endif /* __PERF_STRBUF_H */ diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c index c93eca9a7be3..f24a8cc933d5 100644 --- a/tools/perf/util/string.c +++ b/tools/perf/util/string.c @@ -1,4 +1,5 @@ #include "string.h" +#include "util.h" static int hex(char ch) { @@ -32,3 +33,196 @@ int hex2u64(const char *ptr, u64 *long_val) return p - ptr; } + +char *strxfrchar(char *s, char from, char to) +{ + char *p = s; + + while ((p = strchr(p, from)) != NULL) + *p++ = to; + + return s; +} + +#define K 1024LL +/* + * perf_atoll() + * Parse (\d+)(b|B|kb|KB|mb|MB|gb|GB|tb|TB) (e.g. "256MB") + * and return its numeric value + */ +s64 perf_atoll(const char *str) +{ + unsigned int i; + s64 length = -1, unit = 1; + + if (!isdigit(str[0])) + goto out_err; + + for (i = 1; i < strlen(str); i++) { + switch (str[i]) { + case 'B': + case 'b': + break; + case 'K': + if (str[i + 1] != 'B') + goto out_err; + else + goto kilo; + case 'k': + if (str[i + 1] != 'b') + goto out_err; +kilo: + unit = K; + break; + case 'M': + if (str[i + 1] != 'B') + goto out_err; + else + goto mega; + case 'm': + if (str[i + 1] != 'b') + goto out_err; +mega: + unit = K * K; + break; + case 'G': + if (str[i + 1] != 'B') + goto out_err; + else + goto giga; + case 'g': + if (str[i + 1] != 'b') + goto out_err; +giga: + unit = K * K * K; + break; + case 'T': + if (str[i + 1] != 'B') + goto out_err; + else + goto tera; + case 't': + if (str[i + 1] != 'b') + goto out_err; +tera: + unit = K * K * K * K; + break; + case '\0': /* only specified figures */ + unit = 1; + break; + default: + if (!isdigit(str[i])) + goto out_err; + break; + } + } + + length = atoll(str) * unit; + goto out; + +out_err: + length = -1; +out: + return length; +} + +/* + * Helper function for splitting a string into an argv-like array. + * originaly copied from lib/argv_split.c + */ +static const char *skip_sep(const char *cp) +{ + while (*cp && isspace(*cp)) + cp++; + + return cp; +} + +static const char *skip_arg(const char *cp) +{ + while (*cp && !isspace(*cp)) + cp++; + + return cp; +} + +static int count_argc(const char *str) +{ + int count = 0; + + while (*str) { + str = skip_sep(str); + if (*str) { + count++; + str = skip_arg(str); + } + } + + return count; +} + +/** + * argv_free - free an argv + * @argv - the argument vector to be freed + * + * Frees an argv and the strings it points to. + */ +void argv_free(char **argv) +{ + char **p; + for (p = argv; *p; p++) + free(*p); + + free(argv); +} + +/** + * argv_split - split a string at whitespace, returning an argv + * @str: the string to be split + * @argcp: returned argument count + * + * Returns an array of pointers to strings which are split out from + * @str. This is performed by strictly splitting on white-space; no + * quote processing is performed. Multiple whitespace characters are + * considered to be a single argument separator. The returned array + * is always NULL-terminated. Returns NULL on memory allocation + * failure. + */ +char **argv_split(const char *str, int *argcp) +{ + int argc = count_argc(str); + char **argv = zalloc(sizeof(*argv) * (argc+1)); + char **argvp; + + if (argv == NULL) + goto out; + + if (argcp) + *argcp = argc; + + argvp = argv; + + while (*str) { + str = skip_sep(str); + + if (*str) { + const char *p = str; + char *t; + + str = skip_arg(str); + + t = strndup(p, str-p); + if (t == NULL) + goto fail; + *argvp++ = t; + } + } + *argvp = NULL; + +out: + return argv; + +fail: + argv_free(argv); + return NULL; +} diff --git a/tools/perf/util/string.h b/tools/perf/util/string.h index bf39dfadfd24..bfecec265a1a 100644 --- a/tools/perf/util/string.h +++ b/tools/perf/util/string.h @@ -1,11 +1,15 @@ -#ifndef _PERF_STRING_H_ -#define _PERF_STRING_H_ +#ifndef __PERF_STRING_H_ +#define __PERF_STRING_H_ #include "types.h" int hex2u64(const char *ptr, u64 *val); +char *strxfrchar(char *s, char from, char to); +s64 perf_atoll(const char *str); +char **argv_split(const char *str, int *argcp); +void argv_free(char **argv); #define _STR(x) #x #define STR(x) _STR(x) -#endif +#endif /* __PERF_STRING_H */ diff --git a/tools/perf/util/strlist.h b/tools/perf/util/strlist.h index 921818e44a54..cb4659306d7b 100644 --- a/tools/perf/util/strlist.h +++ b/tools/perf/util/strlist.h @@ -1,5 +1,5 @@ -#ifndef STRLIST_H_ -#define STRLIST_H_ +#ifndef __PERF_STRLIST_H +#define __PERF_STRLIST_H #include <linux/rbtree.h> #include <stdbool.h> @@ -36,4 +36,4 @@ static inline unsigned int strlist__nr_entries(const struct strlist *self) } int strlist__parse_list(struct strlist *self, const char *s); -#endif /* STRLIST_H_ */ +#endif /* __PERF_STRLIST_H */ diff --git a/tools/perf/util/svghelper.h b/tools/perf/util/svghelper.h index cd93195aedb3..e0781989cc31 100644 --- a/tools/perf/util/svghelper.h +++ b/tools/perf/util/svghelper.h @@ -1,5 +1,5 @@ -#ifndef _INCLUDE_GUARD_SVG_HELPER_ -#define _INCLUDE_GUARD_SVG_HELPER_ +#ifndef __PERF_SVGHELPER_H +#define __PERF_SVGHELPER_H #include "types.h" @@ -25,4 +25,4 @@ extern void svg_close(void); extern int svg_page_width; -#endif +#endif /* __PERF_SVGHELPER_H */ diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 226f44a2357d..fffcb937cdcb 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -2,14 +2,20 @@ #include "../perf.h" #include "string.h" #include "symbol.h" +#include "thread.h" #include "debug.h" +#include <asm/bug.h> #include <libelf.h> #include <gelf.h> #include <elf.h> +#include <limits.h> +#include <sys/utsname.h> -const char *sym_hist_filter; +#ifndef NT_GNU_BUILD_ID +#define NT_GNU_BUILD_ID 3 +#endif enum dso_origin { DSO__ORIG_KERNEL = 0, @@ -18,94 +24,189 @@ enum dso_origin { DSO__ORIG_UBUNTU, DSO__ORIG_BUILDID, DSO__ORIG_DSO, + DSO__ORIG_KMODULE, DSO__ORIG_NOT_FOUND, }; -static struct symbol *symbol__new(u64 start, u64 len, - const char *name, unsigned int priv_size, - u64 obj_start, int v) +static void dsos__add(struct list_head *head, struct dso *dso); +static struct map *thread__find_map_by_name(struct thread *self, char *name); +static struct map *map__new2(u64 start, struct dso *dso, enum map_type type); +struct symbol *dso__find_symbol(struct dso *self, enum map_type type, u64 addr); +static int dso__load_kernel_sym(struct dso *self, struct map *map, + struct thread *thread, symbol_filter_t filter); +unsigned int symbol__priv_size; +static int vmlinux_path__nr_entries; +static char **vmlinux_path; + +static struct symbol_conf symbol_conf__defaults = { + .use_modules = true, + .try_vmlinux_path = true, +}; + +static struct thread kthread_mem; +struct thread *kthread = &kthread_mem; + +bool dso__loaded(const struct dso *self, enum map_type type) { - size_t namelen = strlen(name) + 1; - struct symbol *self = calloc(1, priv_size + sizeof(*self) + namelen); + return self->loaded & (1 << type); +} - if (!self) - return NULL; +static void dso__set_loaded(struct dso *self, enum map_type type) +{ + self->loaded |= (1 << type); +} - if (v >= 2) - printf("new symbol: %016Lx [%08lx]: %s, hist: %p, obj_start: %p\n", - (u64)start, (unsigned long)len, name, self->hist, (void *)(unsigned long)obj_start); +static void symbols__fixup_end(struct rb_root *self) +{ + struct rb_node *nd, *prevnd = rb_first(self); + struct symbol *curr, *prev; + + if (prevnd == NULL) + return; - self->obj_start= obj_start; - self->hist = NULL; - self->hist_sum = 0; + curr = rb_entry(prevnd, struct symbol, rb_node); - if (sym_hist_filter && !strcmp(name, sym_hist_filter)) - self->hist = calloc(sizeof(u64), len); + for (nd = rb_next(prevnd); nd; nd = rb_next(nd)) { + prev = curr; + curr = rb_entry(nd, struct symbol, rb_node); - if (priv_size) { - memset(self, 0, priv_size); - self = ((void *)self) + priv_size; + if (prev->end == prev->start) + prev->end = curr->start - 1; } + + /* Last entry */ + if (curr->end == curr->start) + curr->end = roundup(curr->start, 4096); +} + +static void __thread__fixup_maps_end(struct thread *self, enum map_type type) +{ + struct map *prev, *curr; + struct rb_node *nd, *prevnd = rb_first(&self->maps[type]); + + if (prevnd == NULL) + return; + + curr = rb_entry(prevnd, struct map, rb_node); + + for (nd = rb_next(prevnd); nd; nd = rb_next(nd)) { + prev = curr; + curr = rb_entry(nd, struct map, rb_node); + prev->end = curr->start - 1; + } + + /* + * We still haven't the actual symbols, so guess the + * last map final address. + */ + curr->end = ~0UL; +} + +static void thread__fixup_maps_end(struct thread *self) +{ + int i; + for (i = 0; i < MAP__NR_TYPES; ++i) + __thread__fixup_maps_end(self, i); +} + +static struct symbol *symbol__new(u64 start, u64 len, const char *name) +{ + size_t namelen = strlen(name) + 1; + struct symbol *self = zalloc(symbol__priv_size + + sizeof(*self) + namelen); + if (self == NULL) + return NULL; + + if (symbol__priv_size) + self = ((void *)self) + symbol__priv_size; + self->start = start; self->end = len ? start + len - 1 : start; + + pr_debug3("%s: %s %#Lx-%#Lx\n", __func__, name, start, self->end); + memcpy(self->name, name, namelen); return self; } -static void symbol__delete(struct symbol *self, unsigned int priv_size) +static void symbol__delete(struct symbol *self) { - free(((void *)self) - priv_size); + free(((void *)self) - symbol__priv_size); } static size_t symbol__fprintf(struct symbol *self, FILE *fp) { - if (!self->module) - return fprintf(fp, " %llx-%llx %s\n", + return fprintf(fp, " %llx-%llx %s\n", self->start, self->end, self->name); - else - return fprintf(fp, " %llx-%llx %s \t[%s]\n", - self->start, self->end, self->name, self->module->name); } -struct dso *dso__new(const char *name, unsigned int sym_priv_size) +static void dso__set_long_name(struct dso *self, char *name) +{ + if (name == NULL) + return; + self->long_name = name; + self->long_name_len = strlen(name); +} + +static void dso__set_basename(struct dso *self) +{ + self->short_name = basename(self->long_name); +} + +struct dso *dso__new(const char *name) { struct dso *self = malloc(sizeof(*self) + strlen(name) + 1); if (self != NULL) { + int i; strcpy(self->name, name); - self->syms = RB_ROOT; - self->sym_priv_size = sym_priv_size; + dso__set_long_name(self, self->name); + self->short_name = self->name; + for (i = 0; i < MAP__NR_TYPES; ++i) + self->symbols[i] = RB_ROOT; self->find_symbol = dso__find_symbol; self->slen_calculated = 0; self->origin = DSO__ORIG_NOT_FOUND; + self->loaded = 0; + self->has_build_id = 0; } return self; } -static void dso__delete_symbols(struct dso *self) +static void symbols__delete(struct rb_root *self) { struct symbol *pos; - struct rb_node *next = rb_first(&self->syms); + struct rb_node *next = rb_first(self); while (next) { pos = rb_entry(next, struct symbol, rb_node); next = rb_next(&pos->rb_node); - rb_erase(&pos->rb_node, &self->syms); - symbol__delete(pos, self->sym_priv_size); + rb_erase(&pos->rb_node, self); + symbol__delete(pos); } } void dso__delete(struct dso *self) { - dso__delete_symbols(self); + int i; + for (i = 0; i < MAP__NR_TYPES; ++i) + symbols__delete(&self->symbols[i]); + if (self->long_name != self->name) + free(self->long_name); free(self); } -static void dso__insert_symbol(struct dso *self, struct symbol *sym) +void dso__set_build_id(struct dso *self, void *build_id) { - struct rb_node **p = &self->syms.rb_node; + memcpy(self->build_id, build_id, sizeof(self->build_id)); + self->has_build_id = 1; +} + +static void symbols__insert(struct rb_root *self, struct symbol *sym) +{ + struct rb_node **p = &self->rb_node; struct rb_node *parent = NULL; const u64 ip = sym->start; struct symbol *s; @@ -119,17 +220,17 @@ static void dso__insert_symbol(struct dso *self, struct symbol *sym) p = &(*p)->rb_right; } rb_link_node(&sym->rb_node, parent, p); - rb_insert_color(&sym->rb_node, &self->syms); + rb_insert_color(&sym->rb_node, self); } -struct symbol *dso__find_symbol(struct dso *self, u64 ip) +static struct symbol *symbols__find(struct rb_root *self, u64 ip) { struct rb_node *n; if (self == NULL) return NULL; - n = self->syms.rb_node; + n = self->rb_node; while (n) { struct symbol *s = rb_entry(n, struct symbol, rb_node); @@ -145,12 +246,42 @@ struct symbol *dso__find_symbol(struct dso *self, u64 ip) return NULL; } -size_t dso__fprintf(struct dso *self, FILE *fp) +struct symbol *dso__find_symbol(struct dso *self, enum map_type type, u64 addr) { - size_t ret = fprintf(fp, "dso: %s\n", self->name); + return symbols__find(&self->symbols[type], addr); +} + +int build_id__sprintf(u8 *self, int len, char *bf) +{ + char *bid = bf; + u8 *raw = self; + int i; + + for (i = 0; i < len; ++i) { + sprintf(bid, "%02x", *raw); + ++raw; + bid += 2; + } + + return raw - self; +} + +size_t dso__fprintf_buildid(struct dso *self, FILE *fp) +{ + char sbuild_id[BUILD_ID_SIZE * 2 + 1]; + + build_id__sprintf(self->build_id, sizeof(self->build_id), sbuild_id); + return fprintf(fp, "%s", sbuild_id); +} +size_t dso__fprintf(struct dso *self, enum map_type type, FILE *fp) +{ struct rb_node *nd; - for (nd = rb_first(&self->syms); nd; nd = rb_next(nd)) { + size_t ret = fprintf(fp, "dso: %s (", self->short_name); + + ret += dso__fprintf_buildid(self, fp); + ret += fprintf(fp, ")\n"); + for (nd = rb_first(&self->symbols[type]); nd; nd = rb_next(nd)) { struct symbol *pos = rb_entry(nd, struct symbol, rb_node); ret += symbol__fprintf(pos, fp); } @@ -158,13 +289,17 @@ size_t dso__fprintf(struct dso *self, FILE *fp) return ret; } -static int dso__load_kallsyms(struct dso *self, symbol_filter_t filter, int v) +/* + * Loads the function entries in /proc/kallsyms into kernel_map->dso, + * so that we can in the next step set the symbol ->end address and then + * call kernel_maps__split_kallsyms. + */ +static int dso__load_all_kallsyms(struct dso *self, struct map *map) { - struct rb_node *nd, *prevnd; char *line = NULL; size_t n; + struct rb_root *root = &self->symbols[map->type]; FILE *file = fopen("/proc/kallsyms", "r"); - int count = 0; if (file == NULL) goto out_failure; @@ -174,6 +309,7 @@ static int dso__load_kallsyms(struct dso *self, symbol_filter_t filter, int v) struct symbol *sym; int line_len, len; char symbol_type; + char *symbol_name; line_len = getline(&line, &n, file); if (line_len < 0) @@ -196,44 +332,26 @@ static int dso__load_kallsyms(struct dso *self, symbol_filter_t filter, int v) */ if (symbol_type != 'T' && symbol_type != 'W') continue; + + symbol_name = line + len + 2; /* - * Well fix up the end later, when we have all sorted. + * Will fix up the end later, when we have all symbols sorted. */ - sym = symbol__new(start, 0xdead, line + len + 2, - self->sym_priv_size, 0, v); + sym = symbol__new(start, 0, symbol_name); if (sym == NULL) goto out_delete_line; - - if (filter && filter(self, sym)) - symbol__delete(sym, self->sym_priv_size); - else { - dso__insert_symbol(self, sym); - count++; - } - } - - /* - * Now that we have all sorted out, just set the ->end of all - * symbols - */ - prevnd = rb_first(&self->syms); - - if (prevnd == NULL) - goto out_delete_line; - - for (nd = rb_next(prevnd); nd; nd = rb_next(nd)) { - struct symbol *prev = rb_entry(prevnd, struct symbol, rb_node), - *curr = rb_entry(nd, struct symbol, rb_node); - - prev->end = curr->start - 1; - prevnd = nd; + /* + * We will pass the symbols to the filter later, in + * map__split_kallsyms, when we have split the maps per module + */ + symbols__insert(root, sym); } free(line); fclose(file); - return count; + return 0; out_delete_line: free(line); @@ -241,14 +359,114 @@ out_failure: return -1; } -static int dso__load_perf_map(struct dso *self, symbol_filter_t filter, int v) +/* + * Split the symbols into maps, making sure there are no overlaps, i.e. the + * kernel range is broken in several maps, named [kernel].N, as we don't have + * the original ELF section names vmlinux have. + */ +static int dso__split_kallsyms(struct dso *self, struct map *map, struct thread *thread, + symbol_filter_t filter) +{ + struct map *curr_map = map; + struct symbol *pos; + int count = 0; + struct rb_root *root = &self->symbols[map->type]; + struct rb_node *next = rb_first(root); + int kernel_range = 0; + + while (next) { + char *module; + + pos = rb_entry(next, struct symbol, rb_node); + next = rb_next(&pos->rb_node); + + module = strchr(pos->name, '\t'); + if (module) { + if (!thread->use_modules) + goto discard_symbol; + + *module++ = '\0'; + + if (strcmp(self->name, module)) { + curr_map = thread__find_map_by_name(thread, module); + if (curr_map == NULL) { + pr_debug("/proc/{kallsyms,modules} " + "inconsistency!\n"); + return -1; + } + } + /* + * So that we look just like we get from .ko files, + * i.e. not prelinked, relative to map->start. + */ + pos->start = curr_map->map_ip(curr_map, pos->start); + pos->end = curr_map->map_ip(curr_map, pos->end); + } else if (curr_map != map) { + char dso_name[PATH_MAX]; + struct dso *dso; + + snprintf(dso_name, sizeof(dso_name), "[kernel].%d", + kernel_range++); + + dso = dso__new(dso_name); + if (dso == NULL) + return -1; + + curr_map = map__new2(pos->start, dso, map->type); + if (map == NULL) { + dso__delete(dso); + return -1; + } + + curr_map->map_ip = curr_map->unmap_ip = identity__map_ip; + __thread__insert_map(thread, curr_map); + ++kernel_range; + } + + if (filter && filter(curr_map, pos)) { +discard_symbol: rb_erase(&pos->rb_node, root); + symbol__delete(pos); + } else { + if (curr_map != map) { + rb_erase(&pos->rb_node, root); + symbols__insert(&curr_map->dso->symbols[curr_map->type], pos); + } + count++; + } + } + + return count; +} + + +static int dso__load_kallsyms(struct dso *self, struct map *map, + struct thread *thread, symbol_filter_t filter) +{ + if (dso__load_all_kallsyms(self, map) < 0) + return -1; + + symbols__fixup_end(&self->symbols[map->type]); + self->origin = DSO__ORIG_KERNEL; + + return dso__split_kallsyms(self, map, thread, filter); +} + +size_t kernel_maps__fprintf(FILE *fp) +{ + size_t printed = fprintf(fp, "Kernel maps:\n"); + printed += thread__fprintf_maps(kthread, fp); + return printed + fprintf(fp, "END kernel maps\n"); +} + +static int dso__load_perf_map(struct dso *self, struct map *map, + symbol_filter_t filter) { char *line = NULL; size_t n; FILE *file; int nr_syms = 0; - file = fopen(self->name, "r"); + file = fopen(self->long_name, "r"); if (file == NULL) goto out_failure; @@ -278,16 +496,15 @@ static int dso__load_perf_map(struct dso *self, symbol_filter_t filter, int v) if (len + 2 >= line_len) continue; - sym = symbol__new(start, size, line + len, - self->sym_priv_size, start, v); + sym = symbol__new(start, size, line + len); if (sym == NULL) goto out_delete_line; - if (filter && filter(self, sym)) - symbol__delete(sym, self->sym_priv_size); + if (filter && filter(map, sym)) + symbol__delete(sym); else { - dso__insert_symbol(self, sym); + symbols__insert(&self->symbols[map->type], sym); nr_syms++; } } @@ -393,7 +610,8 @@ static Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep, * And always look at the original dso, not at debuginfo packages, that * have the PLT data stripped out (shdr_rel_plt.sh_type == SHT_NOBITS). */ -static int dso__synthesize_plt_symbols(struct dso *self, int v) +static int dso__synthesize_plt_symbols(struct dso *self, struct map *map, + symbol_filter_t filter) { uint32_t nr_rel_entries, idx; GElf_Sym sym; @@ -409,7 +627,7 @@ static int dso__synthesize_plt_symbols(struct dso *self, int v) Elf *elf; int nr = 0, symidx, fd, err = 0; - fd = open(self->name, O_RDONLY); + fd = open(self->long_name, O_RDONLY); if (fd < 0) goto out; @@ -477,12 +695,16 @@ static int dso__synthesize_plt_symbols(struct dso *self, int v) "%s@plt", elf_sym__name(&sym, symstrs)); f = symbol__new(plt_offset, shdr_plt.sh_entsize, - sympltname, self->sym_priv_size, 0, v); + sympltname); if (!f) goto out_elf_end; - dso__insert_symbol(self, f); - ++nr; + if (filter && filter(map, f)) + symbol__delete(f); + else { + symbols__insert(&self->symbols[map->type], f); + ++nr; + } } } else if (shdr_rel_plt.sh_type == SHT_REL) { GElf_Rel pos_mem, *pos; @@ -495,12 +717,16 @@ static int dso__synthesize_plt_symbols(struct dso *self, int v) "%s@plt", elf_sym__name(&sym, symstrs)); f = symbol__new(plt_offset, shdr_plt.sh_entsize, - sympltname, self->sym_priv_size, 0, v); + sympltname); if (!f) goto out_elf_end; - dso__insert_symbol(self, f); - ++nr; + if (filter && filter(map, f)) + symbol__delete(f); + else { + symbols__insert(&self->symbols[map->type], f); + ++nr; + } } } @@ -513,14 +739,18 @@ out_close: if (err == 0) return nr; out: - fprintf(stderr, "%s: problems reading %s PLT info.\n", - __func__, self->name); + pr_warning("%s: problems reading %s PLT info.\n", + __func__, self->long_name); return 0; } -static int dso__load_sym(struct dso *self, int fd, const char *name, - symbol_filter_t filter, int v, struct module *mod) +static int dso__load_sym(struct dso *self, struct map *map, + struct thread *thread, const char *name, int fd, + symbol_filter_t filter, int kernel, int kmodule) { + struct map *curr_map = map; + struct dso *curr_dso = self; + size_t dso_name_len = strlen(self->short_name); Elf_Data *symstrs, *secstrs; uint32_t nr_syms; int err = -1; @@ -531,19 +761,16 @@ static int dso__load_sym(struct dso *self, int fd, const char *name, GElf_Sym sym; Elf_Scn *sec, *sec_strndx; Elf *elf; - int nr = 0, kernel = !strcmp("[kernel]", self->name); + int nr = 0; elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); if (elf == NULL) { - if (v) - fprintf(stderr, "%s: cannot read %s ELF file.\n", - __func__, name); + pr_err("%s: cannot read %s ELF file.\n", __func__, name); goto out_close; } if (gelf_getehdr(elf, &ehdr) == NULL) { - if (v) - fprintf(stderr, "%s: cannot get elf header.\n", __func__); + pr_err("%s: cannot get elf header.\n", __func__); goto out_elf_end; } @@ -587,9 +814,7 @@ static int dso__load_sym(struct dso *self, int fd, const char *name, elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) { struct symbol *f; const char *elf_name; - char *demangled; - u64 obj_start; - struct section *section = NULL; + char *demangled = NULL; int is_label = elf_sym__is_label(&sym); const char *section_name; @@ -605,52 +830,85 @@ static int dso__load_sym(struct dso *self, int fd, const char *name, if (is_label && !elf_sec__is_text(&shdr, secstrs)) continue; + elf_name = elf_sym__name(&sym, symstrs); section_name = elf_sec__name(&shdr, secstrs); - obj_start = sym.st_value; - if (self->adjust_symbols) { - if (v >= 2) - printf("adjusting symbol: st_value: %Lx sh_addr: %Lx sh_offset: %Lx\n", - (u64)sym.st_value, (u64)shdr.sh_addr, (u64)shdr.sh_offset); + if (kernel || kmodule) { + char dso_name[PATH_MAX]; - sym.st_value -= shdr.sh_addr - shdr.sh_offset; - } + if (strcmp(section_name, + curr_dso->short_name + dso_name_len) == 0) + goto new_symbol; - if (mod) { - section = mod->sections->find_section(mod->sections, section_name); - if (section) - sym.st_value += section->vma; - else { - fprintf(stderr, "dso__load_sym() module %s lookup of %s failed\n", - mod->name, section_name); - goto out_elf_end; + if (strcmp(section_name, ".text") == 0) { + curr_map = map; + curr_dso = self; + goto new_symbol; } + + snprintf(dso_name, sizeof(dso_name), + "%s%s", self->short_name, section_name); + + curr_map = thread__find_map_by_name(thread, dso_name); + if (curr_map == NULL) { + u64 start = sym.st_value; + + if (kmodule) + start += map->start + shdr.sh_offset; + + curr_dso = dso__new(dso_name); + if (curr_dso == NULL) + goto out_elf_end; + curr_map = map__new2(start, curr_dso, + MAP__FUNCTION); + if (curr_map == NULL) { + dso__delete(curr_dso); + goto out_elf_end; + } + curr_map->map_ip = identity__map_ip; + curr_map->unmap_ip = identity__map_ip; + curr_dso->origin = DSO__ORIG_KERNEL; + __thread__insert_map(kthread, curr_map); + dsos__add(&dsos__kernel, curr_dso); + } else + curr_dso = curr_map->dso; + + goto new_symbol; + } + + if (curr_dso->adjust_symbols) { + pr_debug2("adjusting symbol: st_value: %Lx sh_addr: " + "%Lx sh_offset: %Lx\n", (u64)sym.st_value, + (u64)shdr.sh_addr, (u64)shdr.sh_offset); + sym.st_value -= shdr.sh_addr - shdr.sh_offset; } /* * We need to figure out if the object was created from C++ sources * DWARF DW_compile_unit has this, but we don't always have access * to it... */ - elf_name = elf_sym__name(&sym, symstrs); demangled = bfd_demangle(NULL, elf_name, DMGL_PARAMS | DMGL_ANSI); if (demangled != NULL) elf_name = demangled; - - f = symbol__new(sym.st_value, sym.st_size, elf_name, - self->sym_priv_size, obj_start, v); +new_symbol: + f = symbol__new(sym.st_value, sym.st_size, elf_name); free(demangled); if (!f) goto out_elf_end; - if (filter && filter(self, f)) - symbol__delete(f, self->sym_priv_size); + if (filter && filter(curr_map, f)) + symbol__delete(f); else { - f->module = mod; - dso__insert_symbol(self, f); + symbols__insert(&curr_dso->symbols[curr_map->type], f); nr++; } } + /* + * For misannotated, zeroed, ASM function sizes. + */ + if (nr > 0) + symbols__fixup_end(&self->symbols[map->type]); err = nr; out_elf_end: elf_end(elf); @@ -658,63 +916,153 @@ out_close: return err; } -#define BUILD_ID_SIZE 128 +static bool dso__build_id_equal(const struct dso *self, u8 *build_id) +{ + return memcmp(self->build_id, build_id, sizeof(self->build_id)) == 0; +} -static char *dso__read_build_id(struct dso *self, int v) +static bool __dsos__read_build_ids(struct list_head *head) { - int i; + bool have_build_id = false; + struct dso *pos; + + list_for_each_entry(pos, head, node) + if (filename__read_build_id(pos->long_name, pos->build_id, + sizeof(pos->build_id)) > 0) { + have_build_id = true; + pos->has_build_id = true; + } + + return have_build_id; +} + +bool dsos__read_build_ids(void) +{ + return __dsos__read_build_ids(&dsos__kernel) || + __dsos__read_build_ids(&dsos__user); +} + +/* + * Align offset to 4 bytes as needed for note name and descriptor data. + */ +#define NOTE_ALIGN(n) (((n) + 3) & -4U) + +int filename__read_build_id(const char *filename, void *bf, size_t size) +{ + int fd, err = -1; GElf_Ehdr ehdr; GElf_Shdr shdr; - Elf_Data *build_id_data; + Elf_Data *data; Elf_Scn *sec; - char *build_id = NULL, *bid; - unsigned char *raw; + Elf_Kind ek; + void *ptr; Elf *elf; - int fd = open(self->name, O_RDONLY); + if (size < BUILD_ID_SIZE) + goto out; + + fd = open(filename, O_RDONLY); if (fd < 0) goto out; elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); if (elf == NULL) { - if (v) - fprintf(stderr, "%s: cannot read %s ELF file.\n", - __func__, self->name); + pr_debug2("%s: cannot read %s ELF file.\n", __func__, filename); goto out_close; } + ek = elf_kind(elf); + if (ek != ELF_K_ELF) + goto out_elf_end; + if (gelf_getehdr(elf, &ehdr) == NULL) { - if (v) - fprintf(stderr, "%s: cannot get elf header.\n", __func__); + pr_err("%s: cannot get elf header.\n", __func__); goto out_elf_end; } - sec = elf_section_by_name(elf, &ehdr, &shdr, ".note.gnu.build-id", NULL); - if (sec == NULL) - goto out_elf_end; + sec = elf_section_by_name(elf, &ehdr, &shdr, + ".note.gnu.build-id", NULL); + if (sec == NULL) { + sec = elf_section_by_name(elf, &ehdr, &shdr, + ".notes", NULL); + if (sec == NULL) + goto out_elf_end; + } - build_id_data = elf_getdata(sec, NULL); - if (build_id_data == NULL) - goto out_elf_end; - build_id = malloc(BUILD_ID_SIZE); - if (build_id == NULL) + data = elf_getdata(sec, NULL); + if (data == NULL) goto out_elf_end; - raw = build_id_data->d_buf + 16; - bid = build_id; - for (i = 0; i < 20; ++i) { - sprintf(bid, "%02x", *raw); - ++raw; - bid += 2; + ptr = data->d_buf; + while (ptr < (data->d_buf + data->d_size)) { + GElf_Nhdr *nhdr = ptr; + int namesz = NOTE_ALIGN(nhdr->n_namesz), + descsz = NOTE_ALIGN(nhdr->n_descsz); + const char *name; + + ptr += sizeof(*nhdr); + name = ptr; + ptr += namesz; + if (nhdr->n_type == NT_GNU_BUILD_ID && + nhdr->n_namesz == sizeof("GNU")) { + if (memcmp(name, "GNU", sizeof("GNU")) == 0) { + memcpy(bf, ptr, BUILD_ID_SIZE); + err = BUILD_ID_SIZE; + break; + } + } + ptr += descsz; } - if (v >= 2) - printf("%s(%s): %s\n", __func__, self->name, build_id); out_elf_end: elf_end(elf); out_close: close(fd); out: - return build_id; + return err; +} + +int sysfs__read_build_id(const char *filename, void *build_id, size_t size) +{ + int fd, err = -1; + + if (size < BUILD_ID_SIZE) + goto out; + + fd = open(filename, O_RDONLY); + if (fd < 0) + goto out; + + while (1) { + char bf[BUFSIZ]; + GElf_Nhdr nhdr; + int namesz, descsz; + + if (read(fd, &nhdr, sizeof(nhdr)) != sizeof(nhdr)) + break; + + namesz = NOTE_ALIGN(nhdr.n_namesz); + descsz = NOTE_ALIGN(nhdr.n_descsz); + if (nhdr.n_type == NT_GNU_BUILD_ID && + nhdr.n_namesz == sizeof("GNU")) { + if (read(fd, bf, namesz) != namesz) + break; + if (memcmp(bf, "GNU", sizeof("GNU")) == 0) { + if (read(fd, build_id, + BUILD_ID_SIZE) == BUILD_ID_SIZE) { + err = 0; + break; + } + } else if (read(fd, bf, descsz) != descsz) + break; + } else { + int n = namesz + descsz; + if (read(fd, bf, n) != n) + break; + } + } + close(fd); +out: + return err; } char dso__symtab_origin(const struct dso *self) @@ -726,6 +1074,7 @@ char dso__symtab_origin(const struct dso *self) [DSO__ORIG_UBUNTU] = 'u', [DSO__ORIG_BUILDID] = 'b', [DSO__ORIG_DSO] = 'd', + [DSO__ORIG_KMODULE] = 'K', }; if (self == NULL || self->origin == DSO__ORIG_NOT_FOUND) @@ -733,20 +1082,27 @@ char dso__symtab_origin(const struct dso *self) return origin[self->origin]; } -int dso__load(struct dso *self, symbol_filter_t filter, int v) +int dso__load(struct dso *self, struct map *map, symbol_filter_t filter) { int size = PATH_MAX; - char *name = malloc(size), *build_id = NULL; + char *name; + u8 build_id[BUILD_ID_SIZE]; int ret = -1; int fd; + dso__set_loaded(self, map->type); + + if (self->kernel) + return dso__load_kernel_sym(self, map, kthread, filter); + + name = malloc(size); if (!name) return -1; self->adjust_symbols = 0; if (strncmp(self->name, "/tmp/perf-", 10) == 0) { - ret = dso__load_perf_map(self, filter, v); + ret = dso__load_perf_map(self, map, filter); self->origin = ret > 0 ? DSO__ORIG_JAVA_JIT : DSO__ORIG_NOT_FOUND; return ret; @@ -759,34 +1115,50 @@ more: self->origin++; switch (self->origin) { case DSO__ORIG_FEDORA: - snprintf(name, size, "/usr/lib/debug%s.debug", self->name); + snprintf(name, size, "/usr/lib/debug%s.debug", + self->long_name); break; case DSO__ORIG_UBUNTU: - snprintf(name, size, "/usr/lib/debug%s", self->name); + snprintf(name, size, "/usr/lib/debug%s", + self->long_name); break; case DSO__ORIG_BUILDID: - build_id = dso__read_build_id(self, v); - if (build_id != NULL) { + if (filename__read_build_id(self->long_name, build_id, + sizeof(build_id))) { + char build_id_hex[BUILD_ID_SIZE * 2 + 1]; + + build_id__sprintf(build_id, sizeof(build_id), + build_id_hex); snprintf(name, size, "/usr/lib/debug/.build-id/%.2s/%s.debug", - build_id, build_id + 2); - free(build_id); + build_id_hex, build_id_hex + 2); + if (self->has_build_id) + goto compare_build_id; break; } self->origin++; /* Fall thru */ case DSO__ORIG_DSO: - snprintf(name, size, "%s", self->name); + snprintf(name, size, "%s", self->long_name); break; default: goto out; } + if (self->has_build_id) { + if (filename__read_build_id(name, build_id, + sizeof(build_id)) < 0) + goto more; +compare_build_id: + if (!dso__build_id_equal(self, build_id)) + goto more; + } + fd = open(name, O_RDONLY); } while (fd < 0); - ret = dso__load_sym(self, fd, name, filter, v, NULL); + ret = dso__load_sym(self, map, NULL, name, fd, filter, 0, 0); close(fd); /* @@ -796,7 +1168,7 @@ more: goto more; if (ret > 0) { - int nr_plt = dso__synthesize_plt_symbols(self, v); + int nr_plt = dso__synthesize_plt_symbols(self, map, filter); if (nr_plt > 0) ret += nr_plt; } @@ -807,151 +1179,279 @@ out: return ret; } -static int dso__load_module(struct dso *self, struct mod_dso *mods, const char *name, - symbol_filter_t filter, int v) +static struct map *thread__find_map_by_name(struct thread *self, char *name) { - struct module *mod = mod_dso__find_module(mods, name); - int err = 0, fd; + struct rb_node *nd; - if (mod == NULL || !mod->active) - return err; + for (nd = rb_first(&self->maps[MAP__FUNCTION]); nd; nd = rb_next(nd)) { + struct map *map = rb_entry(nd, struct map, rb_node); - fd = open(mod->path, O_RDONLY); + if (map->dso && strcmp(map->dso->name, name) == 0) + return map; + } - if (fd < 0) - return err; + return NULL; +} - err = dso__load_sym(self, fd, name, filter, v, mod); - close(fd); +static int dsos__set_modules_path_dir(char *dirname) +{ + struct dirent *dent; + DIR *dir = opendir(dirname); - return err; + if (!dir) { + pr_debug("%s: cannot open %s dir\n", __func__, dirname); + return -1; + } + + while ((dent = readdir(dir)) != NULL) { + char path[PATH_MAX]; + + if (dent->d_type == DT_DIR) { + if (!strcmp(dent->d_name, ".") || + !strcmp(dent->d_name, "..")) + continue; + + snprintf(path, sizeof(path), "%s/%s", + dirname, dent->d_name); + if (dsos__set_modules_path_dir(path) < 0) + goto failure; + } else { + char *dot = strrchr(dent->d_name, '.'), + dso_name[PATH_MAX]; + struct map *map; + char *long_name; + + if (dot == NULL || strcmp(dot, ".ko")) + continue; + snprintf(dso_name, sizeof(dso_name), "[%.*s]", + (int)(dot - dent->d_name), dent->d_name); + + strxfrchar(dso_name, '-', '_'); + map = thread__find_map_by_name(kthread, dso_name); + if (map == NULL) + continue; + + snprintf(path, sizeof(path), "%s/%s", + dirname, dent->d_name); + + long_name = strdup(path); + if (long_name == NULL) + goto failure; + dso__set_long_name(map->dso, long_name); + } + } + + return 0; +failure: + closedir(dir); + return -1; } -int dso__load_modules(struct dso *self, symbol_filter_t filter, int v) +static int dsos__set_modules_path(void) { - struct mod_dso *mods = mod_dso__new_dso("modules"); - struct module *pos; - struct rb_node *next; - int err, count = 0; + struct utsname uts; + char modules_path[PATH_MAX]; - err = mod_dso__load_modules(mods); - - if (err <= 0) - return err; + if (uname(&uts) < 0) + return -1; - /* - * Iterate over modules, and load active symbols. - */ - next = rb_first(&mods->mods); - while (next) { - pos = rb_entry(next, struct module, rb_node); - err = dso__load_module(self, mods, pos->name, filter, v); + snprintf(modules_path, sizeof(modules_path), "/lib/modules/%s/kernel", + uts.release); - if (err < 0) - break; + return dsos__set_modules_path_dir(modules_path); +} - next = rb_next(&pos->rb_node); - count += err; - } +/* + * Constructor variant for modules (where we know from /proc/modules where + * they are loaded) and for vmlinux, where only after we load all the + * symbols we'll know where it starts and ends. + */ +static struct map *map__new2(u64 start, struct dso *dso, enum map_type type) +{ + struct map *self = malloc(sizeof(*self)); - if (err < 0) { - mod_dso__delete_modules(mods); - mod_dso__delete_self(mods); - return err; + if (self != NULL) { + /* + * ->end will be filled after we load all the symbols + */ + map__init(self, type, start, 0, 0, dso); } - return count; + return self; } -static inline void dso__fill_symbol_holes(struct dso *self) +static int thread__create_module_maps(struct thread *self) { - struct symbol *prev = NULL; - struct rb_node *nd; + char *line = NULL; + size_t n; + FILE *file = fopen("/proc/modules", "r"); + struct map *map; - for (nd = rb_last(&self->syms); nd; nd = rb_prev(nd)) { - struct symbol *pos = rb_entry(nd, struct symbol, rb_node); + if (file == NULL) + return -1; - if (prev) { - u64 hole = 0; - int alias = pos->start == prev->start; + while (!feof(file)) { + char name[PATH_MAX]; + u64 start; + struct dso *dso; + char *sep; + int line_len; - if (!alias) - hole = prev->start - pos->end - 1; + line_len = getline(&line, &n, file); + if (line_len < 0) + break; - if (hole || alias) { - if (alias) - pos->end = prev->end; - else if (hole) - pos->end = prev->start - 1; - } + if (!line) + goto out_failure; + + line[--line_len] = '\0'; /* \n */ + + sep = strrchr(line, 'x'); + if (sep == NULL) + continue; + + hex2u64(sep + 1, &start); + + sep = strchr(line, ' '); + if (sep == NULL) + continue; + + *sep = '\0'; + + snprintf(name, sizeof(name), "[%s]", line); + dso = dso__new(name); + + if (dso == NULL) + goto out_delete_line; + + map = map__new2(start, dso, MAP__FUNCTION); + if (map == NULL) { + dso__delete(dso); + goto out_delete_line; } - prev = pos; + + snprintf(name, sizeof(name), + "/sys/module/%s/notes/.note.gnu.build-id", line); + if (sysfs__read_build_id(name, dso->build_id, + sizeof(dso->build_id)) == 0) + dso->has_build_id = true; + + dso->origin = DSO__ORIG_KMODULE; + __thread__insert_map(self, map); + dsos__add(&dsos__kernel, dso); } + + free(line); + fclose(file); + + return dsos__set_modules_path(); + +out_delete_line: + free(line); +out_failure: + return -1; } -static int dso__load_vmlinux(struct dso *self, const char *vmlinux, - symbol_filter_t filter, int v) +static int dso__load_vmlinux(struct dso *self, struct map *map, struct thread *thread, + const char *vmlinux, symbol_filter_t filter) { - int err, fd = open(vmlinux, O_RDONLY); + int err = -1, fd; - if (fd < 0) - return -1; + if (self->has_build_id) { + u8 build_id[BUILD_ID_SIZE]; - err = dso__load_sym(self, fd, vmlinux, filter, v, NULL); + if (filename__read_build_id(vmlinux, build_id, + sizeof(build_id)) < 0) { + pr_debug("No build_id in %s, ignoring it\n", vmlinux); + return -1; + } + if (!dso__build_id_equal(self, build_id)) { + char expected_build_id[BUILD_ID_SIZE * 2 + 1], + vmlinux_build_id[BUILD_ID_SIZE * 2 + 1]; + + build_id__sprintf(self->build_id, + sizeof(self->build_id), + expected_build_id); + build_id__sprintf(build_id, sizeof(build_id), + vmlinux_build_id); + pr_debug("build_id in %s is %s while expected is %s, " + "ignoring it\n", vmlinux, vmlinux_build_id, + expected_build_id); + return -1; + } + } - if (err > 0) - dso__fill_symbol_holes(self); + fd = open(vmlinux, O_RDONLY); + if (fd < 0) + return -1; + dso__set_loaded(self, map->type); + err = dso__load_sym(self, map, thread, self->long_name, fd, filter, 1, 0); close(fd); return err; } -int dso__load_kernel(struct dso *self, const char *vmlinux, - symbol_filter_t filter, int v, int use_modules) +static int dso__load_kernel_sym(struct dso *self, struct map *map, + struct thread *thread, symbol_filter_t filter) { - int err = -1; - - if (vmlinux) { - err = dso__load_vmlinux(self, vmlinux, filter, v); - if (err > 0 && use_modules) { - int syms = dso__load_modules(self, filter, v); - - if (syms < 0) { - fprintf(stderr, "dso__load_modules failed!\n"); - return syms; + int err; + bool is_kallsyms; + + if (vmlinux_path != NULL) { + int i; + pr_debug("Looking at the vmlinux_path (%d entries long)\n", + vmlinux_path__nr_entries); + for (i = 0; i < vmlinux_path__nr_entries; ++i) { + err = dso__load_vmlinux(self, map, thread, + vmlinux_path[i], filter); + if (err > 0) { + pr_debug("Using %s for symbols\n", + vmlinux_path[i]); + dso__set_long_name(self, + strdup(vmlinux_path[i])); + goto out_fixup; } - err += syms; } } - if (err <= 0) - err = dso__load_kallsyms(self, filter, v); + is_kallsyms = self->long_name[0] == '['; + if (is_kallsyms) + goto do_kallsyms; - if (err > 0) - self->origin = DSO__ORIG_KERNEL; + err = dso__load_vmlinux(self, map, thread, self->long_name, filter); + if (err <= 0) { + pr_info("The file %s cannot be used, " + "trying to use /proc/kallsyms...", self->long_name); +do_kallsyms: + err = dso__load_kallsyms(self, map, thread, filter); + if (err > 0 && !is_kallsyms) + dso__set_long_name(self, strdup("[kernel.kallsyms]")); + } + + if (err > 0) { +out_fixup: + map__fixup_start(map); + map__fixup_end(map); + } return err; } -LIST_HEAD(dsos); -struct dso *kernel_dso; -struct dso *vdso; -struct dso *hypervisor_dso; - -const char *vmlinux_name = "vmlinux"; -int modules; +LIST_HEAD(dsos__user); +LIST_HEAD(dsos__kernel); +struct dso *vdso; -static void dsos__add(struct dso *dso) +static void dsos__add(struct list_head *head, struct dso *dso) { - list_add_tail(&dso->node, &dsos); + list_add_tail(&dso->node, head); } -static struct dso *dsos__find(const char *name) +static struct dso *dsos__find(struct list_head *head, const char *name) { struct dso *pos; - list_for_each_entry(pos, &dsos, node) + list_for_each_entry(pos, head, node) if (strcmp(pos->name, name) == 0) return pos; return NULL; @@ -959,79 +1459,170 @@ static struct dso *dsos__find(const char *name) struct dso *dsos__findnew(const char *name) { - struct dso *dso = dsos__find(name); - int nr; - - if (dso) - return dso; - - dso = dso__new(name, 0); - if (!dso) - goto out_delete_dso; + struct dso *dso = dsos__find(&dsos__user, name); - nr = dso__load(dso, NULL, verbose); - if (nr < 0) { - eprintf("Failed to open: %s\n", name); - goto out_delete_dso; + if (!dso) { + dso = dso__new(name); + if (dso != NULL) { + dsos__add(&dsos__user, dso); + dso__set_basename(dso); + } } - if (!nr) - eprintf("No symbols found in: %s, maybe install a debug package?\n", name); - - dsos__add(dso); return dso; +} -out_delete_dso: - dso__delete(dso); - return NULL; +static void __dsos__fprintf(struct list_head *head, FILE *fp) +{ + struct dso *pos; + + list_for_each_entry(pos, head, node) { + int i; + for (i = 0; i < MAP__NR_TYPES; ++i) + dso__fprintf(pos, i, fp); + } } void dsos__fprintf(FILE *fp) { + __dsos__fprintf(&dsos__kernel, fp); + __dsos__fprintf(&dsos__user, fp); +} + +static size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp) +{ struct dso *pos; + size_t ret = 0; - list_for_each_entry(pos, &dsos, node) - dso__fprintf(pos, fp); + list_for_each_entry(pos, head, node) { + ret += dso__fprintf_buildid(pos, fp); + ret += fprintf(fp, " %s\n", pos->long_name); + } + return ret; } -static struct symbol *vdso__find_symbol(struct dso *dso, u64 ip) +size_t dsos__fprintf_buildid(FILE *fp) { - return dso__find_symbol(dso, ip); + return (__dsos__fprintf_buildid(&dsos__kernel, fp) + + __dsos__fprintf_buildid(&dsos__user, fp)); } -int load_kernel(void) +static int thread__create_kernel_map(struct thread *self, const char *vmlinux) { - int err; + struct map *kmap; + struct dso *kernel = dso__new(vmlinux ?: "[kernel.kallsyms]"); - kernel_dso = dso__new("[kernel]", 0); - if (!kernel_dso) + if (kernel == NULL) return -1; - err = dso__load_kernel(kernel_dso, vmlinux_name, NULL, verbose, modules); - if (err <= 0) { - dso__delete(kernel_dso); - kernel_dso = NULL; - } else - dsos__add(kernel_dso); + kmap = map__new2(0, kernel, MAP__FUNCTION); + if (kmap == NULL) + goto out_delete_kernel_dso; - vdso = dso__new("[vdso]", 0); - if (!vdso) - return -1; + kmap->map_ip = kmap->unmap_ip = identity__map_ip; + kernel->short_name = "[kernel]"; + kernel->kernel = 1; - vdso->find_symbol = vdso__find_symbol; + vdso = dso__new("[vdso]"); + if (vdso == NULL) + goto out_delete_kernel_map; + dso__set_loaded(vdso, MAP__FUNCTION); - dsos__add(vdso); + if (sysfs__read_build_id("/sys/kernel/notes", kernel->build_id, + sizeof(kernel->build_id)) == 0) + kernel->has_build_id = true; - hypervisor_dso = dso__new("[hypervisor]", 0); - if (!hypervisor_dso) - return -1; - dsos__add(hypervisor_dso); + __thread__insert_map(self, kmap); + dsos__add(&dsos__kernel, kernel); + dsos__add(&dsos__user, vdso); - return err; + return 0; + +out_delete_kernel_map: + map__delete(kmap); +out_delete_kernel_dso: + dso__delete(kernel); + return -1; +} + +static void vmlinux_path__exit(void) +{ + while (--vmlinux_path__nr_entries >= 0) { + free(vmlinux_path[vmlinux_path__nr_entries]); + vmlinux_path[vmlinux_path__nr_entries] = NULL; + } + + free(vmlinux_path); + vmlinux_path = NULL; } +static int vmlinux_path__init(void) +{ + struct utsname uts; + char bf[PATH_MAX]; + + if (uname(&uts) < 0) + return -1; + + vmlinux_path = malloc(sizeof(char *) * 5); + if (vmlinux_path == NULL) + return -1; + + vmlinux_path[vmlinux_path__nr_entries] = strdup("vmlinux"); + if (vmlinux_path[vmlinux_path__nr_entries] == NULL) + goto out_fail; + ++vmlinux_path__nr_entries; + vmlinux_path[vmlinux_path__nr_entries] = strdup("/boot/vmlinux"); + if (vmlinux_path[vmlinux_path__nr_entries] == NULL) + goto out_fail; + ++vmlinux_path__nr_entries; + snprintf(bf, sizeof(bf), "/boot/vmlinux-%s", uts.release); + vmlinux_path[vmlinux_path__nr_entries] = strdup(bf); + if (vmlinux_path[vmlinux_path__nr_entries] == NULL) + goto out_fail; + ++vmlinux_path__nr_entries; + snprintf(bf, sizeof(bf), "/lib/modules/%s/build/vmlinux", uts.release); + vmlinux_path[vmlinux_path__nr_entries] = strdup(bf); + if (vmlinux_path[vmlinux_path__nr_entries] == NULL) + goto out_fail; + ++vmlinux_path__nr_entries; + snprintf(bf, sizeof(bf), "/usr/lib/debug/lib/modules/%s/vmlinux", + uts.release); + vmlinux_path[vmlinux_path__nr_entries] = strdup(bf); + if (vmlinux_path[vmlinux_path__nr_entries] == NULL) + goto out_fail; + ++vmlinux_path__nr_entries; + + return 0; + +out_fail: + vmlinux_path__exit(); + return -1; +} -void symbol__init(void) +int symbol__init(struct symbol_conf *conf) { + const struct symbol_conf *pconf = conf ?: &symbol_conf__defaults; + elf_version(EV_CURRENT); + symbol__priv_size = pconf->priv_size; + thread__init(kthread, 0); + + if (pconf->try_vmlinux_path && vmlinux_path__init() < 0) + return -1; + + if (thread__create_kernel_map(kthread, pconf->vmlinux_name) < 0) { + vmlinux_path__exit(); + return -1; + } + + kthread->use_modules = pconf->use_modules; + if (pconf->use_modules && thread__create_module_maps(kthread) < 0) + pr_debug("Failed to load list of modules in use, " + "continuing...\n"); + /* + * Now that we have all the maps created, just set the ->end of them: + */ + thread__fixup_maps_end(kthread); + return 0; } diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 829da9edba64..17003efa0b39 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -1,11 +1,11 @@ -#ifndef _PERF_SYMBOL_ -#define _PERF_SYMBOL_ 1 +#ifndef __PERF_SYMBOL +#define __PERF_SYMBOL 1 #include <linux/types.h> +#include <stdbool.h> #include "types.h" #include <linux/list.h> #include <linux/rbtree.h> -#include "module.h" #include "event.h" #ifdef HAVE_CPLUS_DEMANGLE @@ -46,57 +46,75 @@ struct symbol { struct rb_node rb_node; u64 start; u64 end; - u64 obj_start; - u64 hist_sum; - u64 *hist; - struct module *module; - void *priv; char name[0]; }; +struct symbol_conf { + unsigned short priv_size; + bool try_vmlinux_path, + use_modules; + const char *vmlinux_name; +}; + +extern unsigned int symbol__priv_size; + +static inline void *symbol__priv(struct symbol *self) +{ + return ((void *)self) - symbol__priv_size; +} + +struct addr_location { + struct thread *thread; + struct map *map; + struct symbol *sym; + u64 addr; + char level; +}; + struct dso { struct list_head node; - struct rb_root syms; - struct symbol *(*find_symbol)(struct dso *, u64 ip); - unsigned int sym_priv_size; - unsigned char adjust_symbols; - unsigned char slen_calculated; + struct rb_root symbols[MAP__NR_TYPES]; + struct symbol *(*find_symbol)(struct dso *self, + enum map_type type, u64 addr); + u8 adjust_symbols:1; + u8 slen_calculated:1; + u8 has_build_id:1; + u8 kernel:1; unsigned char origin; + u8 loaded; + u8 build_id[BUILD_ID_SIZE]; + u16 long_name_len; + const char *short_name; + char *long_name; char name[0]; }; -extern const char *sym_hist_filter; - -typedef int (*symbol_filter_t)(struct dso *self, struct symbol *sym); - -struct dso *dso__new(const char *name, unsigned int sym_priv_size); +struct dso *dso__new(const char *name); void dso__delete(struct dso *self); -static inline void *dso__sym_priv(struct dso *self, struct symbol *sym) -{ - return ((void *)sym) - self->sym_priv_size; -} - -struct symbol *dso__find_symbol(struct dso *self, u64 ip); +bool dso__loaded(const struct dso *self, enum map_type type); -int dso__load_kernel(struct dso *self, const char *vmlinux, - symbol_filter_t filter, int verbose, int modules); -int dso__load_modules(struct dso *self, symbol_filter_t filter, int verbose); -int dso__load(struct dso *self, symbol_filter_t filter, int verbose); struct dso *dsos__findnew(const char *name); +int dso__load(struct dso *self, struct map *map, symbol_filter_t filter); void dsos__fprintf(FILE *fp); +size_t dsos__fprintf_buildid(FILE *fp); -size_t dso__fprintf(struct dso *self, FILE *fp); +size_t dso__fprintf_buildid(struct dso *self, FILE *fp); +size_t dso__fprintf(struct dso *self, enum map_type type, FILE *fp); char dso__symtab_origin(const struct dso *self); +void dso__set_build_id(struct dso *self, void *build_id); + +int filename__read_build_id(const char *filename, void *bf, size_t size); +int sysfs__read_build_id(const char *filename, void *bf, size_t size); +bool dsos__read_build_ids(void); +int build_id__sprintf(u8 *self, int len, char *bf); -int load_kernel(void); +size_t kernel_maps__fprintf(FILE *fp); -void symbol__init(void); +int symbol__init(struct symbol_conf *conf); -extern struct list_head dsos; -extern struct dso *kernel_dso; +struct thread; +struct thread *kthread; +extern struct list_head dsos__user, dsos__kernel; extern struct dso *vdso; -extern struct dso *hypervisor_dso; -extern const char *vmlinux_name; -extern int modules; -#endif /* _PERF_SYMBOL_ */ +#endif /* __PERF_SYMBOL */ diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 45efb5db0d19..603f5610861b 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -6,16 +6,29 @@ #include "util.h" #include "debug.h" +static struct rb_root threads; +static struct thread *last_match; + +void thread__init(struct thread *self, pid_t pid) +{ + int i; + self->pid = pid; + self->comm = NULL; + for (i = 0; i < MAP__NR_TYPES; ++i) { + self->maps[i] = RB_ROOT; + INIT_LIST_HEAD(&self->removed_maps[i]); + } +} + static struct thread *thread__new(pid_t pid) { - struct thread *self = calloc(1, sizeof(*self)); + struct thread *self = zalloc(sizeof(*self)); if (self != NULL) { - self->pid = pid; + thread__init(self, pid); self->comm = malloc(32); if (self->comm) snprintf(self->comm, 32, ":%d", self->pid); - INIT_LIST_HEAD(&self->maps); } return self; @@ -29,21 +42,84 @@ int thread__set_comm(struct thread *self, const char *comm) return self->comm ? 0 : -ENOMEM; } -static size_t thread__fprintf(struct thread *self, FILE *fp) +int thread__comm_len(struct thread *self) +{ + if (!self->comm_len) { + if (!self->comm) + return 0; + self->comm_len = strlen(self->comm); + } + + return self->comm_len; +} + +static const char *map_type__name[MAP__NR_TYPES] = { + [MAP__FUNCTION] = "Functions", +}; + +static size_t __thread__fprintf_maps(struct thread *self, + enum map_type type, FILE *fp) +{ + size_t printed = fprintf(fp, "%s:\n", map_type__name[type]); + struct rb_node *nd; + + for (nd = rb_first(&self->maps[type]); nd; nd = rb_next(nd)) { + struct map *pos = rb_entry(nd, struct map, rb_node); + printed += fprintf(fp, "Map:"); + printed += map__fprintf(pos, fp); + if (verbose > 1) { + printed += dso__fprintf(pos->dso, type, fp); + printed += fprintf(fp, "--\n"); + } + } + + return printed; +} + +size_t thread__fprintf_maps(struct thread *self, FILE *fp) +{ + size_t printed = 0, i; + for (i = 0; i < MAP__NR_TYPES; ++i) + printed += __thread__fprintf_maps(self, i, fp); + return printed; +} + +static size_t __thread__fprintf_removed_maps(struct thread *self, + enum map_type type, FILE *fp) { struct map *pos; - size_t ret = fprintf(fp, "Thread %d %s\n", self->pid, self->comm); + size_t printed = 0; + + list_for_each_entry(pos, &self->removed_maps[type], node) { + printed += fprintf(fp, "Map:"); + printed += map__fprintf(pos, fp); + if (verbose > 1) { + printed += dso__fprintf(pos->dso, type, fp); + printed += fprintf(fp, "--\n"); + } + } + return printed; +} - list_for_each_entry(pos, &self->maps, node) - ret += map__fprintf(pos, fp); +static size_t thread__fprintf_removed_maps(struct thread *self, FILE *fp) +{ + size_t printed = 0, i; + for (i = 0; i < MAP__NR_TYPES; ++i) + printed += __thread__fprintf_removed_maps(self, i, fp); + return printed; +} - return ret; +static size_t thread__fprintf(struct thread *self, FILE *fp) +{ + size_t printed = fprintf(fp, "Thread %d %s\n", self->pid, self->comm); + printed += thread__fprintf_removed_maps(self, fp); + printed += fprintf(fp, "Removed maps:\n"); + return printed + thread__fprintf_removed_maps(self, fp); } -struct thread * -threads__findnew(pid_t pid, struct rb_root *threads, struct thread **last_match) +struct thread *threads__findnew(pid_t pid) { - struct rb_node **p = &threads->rb_node; + struct rb_node **p = &threads.rb_node; struct rb_node *parent = NULL; struct thread *th; @@ -52,15 +128,15 @@ threads__findnew(pid_t pid, struct rb_root *threads, struct thread **last_match) * so most of the time we dont have to look up * the full rbtree: */ - if (*last_match && (*last_match)->pid == pid) - return *last_match; + if (last_match && last_match->pid == pid) + return last_match; while (*p != NULL) { parent = *p; th = rb_entry(parent, struct thread, rb_node); if (th->pid == pid) { - *last_match = th; + last_match = th; return th; } @@ -73,17 +149,16 @@ threads__findnew(pid_t pid, struct rb_root *threads, struct thread **last_match) th = thread__new(pid); if (th != NULL) { rb_link_node(&th->rb_node, parent, p); - rb_insert_color(&th->rb_node, threads); - *last_match = th; + rb_insert_color(&th->rb_node, &threads); + last_match = th; } return th; } -struct thread * -register_idle_thread(struct rb_root *threads, struct thread **last_match) +struct thread *register_idle_thread(void) { - struct thread *thread = threads__findnew(0, threads, last_match); + struct thread *thread = threads__findnew(0); if (!thread || thread__set_comm(thread, "swapper")) { fprintf(stderr, "problem inserting idle task.\n"); @@ -93,79 +168,116 @@ register_idle_thread(struct rb_root *threads, struct thread **last_match) return thread; } -void thread__insert_map(struct thread *self, struct map *map) +static void thread__remove_overlappings(struct thread *self, struct map *map) { - struct map *pos, *tmp; + struct rb_root *root = &self->maps[map->type]; + struct rb_node *next = rb_first(root); - list_for_each_entry_safe(pos, tmp, &self->maps, node) { - if (map__overlap(pos, map)) { - if (verbose >= 2) { - printf("overlapping maps:\n"); - map__fprintf(map, stdout); - map__fprintf(pos, stdout); - } + while (next) { + struct map *pos = rb_entry(next, struct map, rb_node); + next = rb_next(&pos->rb_node); - if (map->start <= pos->start && map->end > pos->start) - pos->start = map->end; + if (!map__overlap(pos, map)) + continue; - if (map->end >= pos->end && map->start < pos->end) - pos->end = map->start; + if (verbose >= 2) { + fputs("overlapping maps:\n", stderr); + map__fprintf(map, stderr); + map__fprintf(pos, stderr); + } - if (verbose >= 2) { - printf("after collision:\n"); - map__fprintf(pos, stdout); - } + rb_erase(&pos->rb_node, root); + /* + * We may have references to this map, for instance in some + * hist_entry instances, so just move them to a separate + * list. + */ + list_add_tail(&pos->node, &self->removed_maps[map->type]); + } +} - if (pos->start >= pos->end) { - list_del_init(&pos->node); - free(pos); - } - } +void maps__insert(struct rb_root *maps, struct map *map) +{ + struct rb_node **p = &maps->rb_node; + struct rb_node *parent = NULL; + const u64 ip = map->start; + struct map *m; + + while (*p != NULL) { + parent = *p; + m = rb_entry(parent, struct map, rb_node); + if (ip < m->start) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; } - list_add_tail(&map->node, &self->maps); + rb_link_node(&map->rb_node, parent, p); + rb_insert_color(&map->rb_node, maps); } -int thread__fork(struct thread *self, struct thread *parent) +struct map *maps__find(struct rb_root *maps, u64 ip) { - struct map *map; + struct rb_node **p = &maps->rb_node; + struct rb_node *parent = NULL; + struct map *m; - if (self->comm) - free(self->comm); - self->comm = strdup(parent->comm); - if (!self->comm) - return -ENOMEM; + while (*p != NULL) { + parent = *p; + m = rb_entry(parent, struct map, rb_node); + if (ip < m->start) + p = &(*p)->rb_left; + else if (ip > m->end) + p = &(*p)->rb_right; + else + return m; + } + + return NULL; +} + +void thread__insert_map(struct thread *self, struct map *map) +{ + thread__remove_overlappings(self, map); + maps__insert(&self->maps[map->type], map); +} - list_for_each_entry(map, &parent->maps, node) { +static int thread__clone_maps(struct thread *self, struct thread *parent, + enum map_type type) +{ + struct rb_node *nd; + for (nd = rb_first(&parent->maps[type]); nd; nd = rb_next(nd)) { + struct map *map = rb_entry(nd, struct map, rb_node); struct map *new = map__clone(map); - if (!new) + if (new == NULL) return -ENOMEM; thread__insert_map(self, new); } - return 0; } -struct map *thread__find_map(struct thread *self, u64 ip) +int thread__fork(struct thread *self, struct thread *parent) { - struct map *pos; + int i; - if (self == NULL) - return NULL; - - list_for_each_entry(pos, &self->maps, node) - if (ip >= pos->start && ip <= pos->end) - return pos; + if (self->comm) + free(self->comm); + self->comm = strdup(parent->comm); + if (!self->comm) + return -ENOMEM; - return NULL; + for (i = 0; i < MAP__NR_TYPES; ++i) + if (thread__clone_maps(self, parent, i) < 0) + return -ENOMEM; + return 0; } -size_t threads__fprintf(FILE *fp, struct rb_root *threads) +size_t threads__fprintf(FILE *fp) { size_t ret = 0; struct rb_node *nd; - for (nd = rb_first(threads); nd; nd = rb_next(nd)) { + for (nd = rb_first(&threads); nd; nd = rb_next(nd)) { struct thread *pos = rb_entry(nd, struct thread, rb_node); ret += thread__fprintf(pos, fp); @@ -173,3 +285,15 @@ size_t threads__fprintf(FILE *fp, struct rb_root *threads) return ret; } + +struct symbol *thread__find_symbol(struct thread *self, + enum map_type type, u64 addr, + symbol_filter_t filter) +{ + struct map *map = thread__find_map(self, type, addr); + + if (map != NULL) + return map__find_symbol(map, map->map_ip(map, addr), filter); + + return NULL; +} diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 32aea3c1c2ad..686d6e914d9e 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -1,22 +1,56 @@ +#ifndef __PERF_THREAD_H +#define __PERF_THREAD_H + #include <linux/rbtree.h> -#include <linux/list.h> #include <unistd.h> #include "symbol.h" struct thread { struct rb_node rb_node; - struct list_head maps; + struct rb_root maps[MAP__NR_TYPES]; + struct list_head removed_maps[MAP__NR_TYPES]; pid_t pid; + bool use_modules; char shortname[3]; char *comm; + int comm_len; }; +void thread__init(struct thread *self, pid_t pid); int thread__set_comm(struct thread *self, const char *comm); -struct thread * -threads__findnew(pid_t pid, struct rb_root *threads, struct thread **last_match); -struct thread * -register_idle_thread(struct rb_root *threads, struct thread **last_match); +int thread__comm_len(struct thread *self); +struct thread *threads__findnew(pid_t pid); +struct thread *register_idle_thread(void); void thread__insert_map(struct thread *self, struct map *map); int thread__fork(struct thread *self, struct thread *parent); -struct map *thread__find_map(struct thread *self, u64 ip); -size_t threads__fprintf(FILE *fp, struct rb_root *threads); +size_t thread__fprintf_maps(struct thread *self, FILE *fp); +size_t threads__fprintf(FILE *fp); + +void maps__insert(struct rb_root *maps, struct map *map); +struct map *maps__find(struct rb_root *maps, u64 addr); + +static inline struct map *thread__find_map(struct thread *self, + enum map_type type, u64 addr) +{ + return self ? maps__find(&self->maps[type], addr) : NULL; +} + +static inline void __thread__insert_map(struct thread *self, struct map *map) +{ + maps__insert(&self->maps[map->type], map); +} + +void thread__find_addr_location(struct thread *self, u8 cpumode, + enum map_type type, u64 addr, + struct addr_location *al, + symbol_filter_t filter); +struct symbol *thread__find_symbol(struct thread *self, + enum map_type type, u64 addr, + symbol_filter_t filter); + +static inline struct symbol * +thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) +{ + return thread__find_symbol(self, MAP__FUNCTION, addr, filter); +} +#endif /* __PERF_THREAD_H */ diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c index af4b0573b37f..cace35595530 100644 --- a/tools/perf/util/trace-event-info.c +++ b/tools/perf/util/trace-event-info.c @@ -33,11 +33,11 @@ #include <ctype.h> #include <errno.h> #include <stdbool.h> +#include <linux/kernel.h> #include "../perf.h" #include "trace-event.h" - #define VERSION "0.5" #define _STR(x) #x @@ -483,27 +483,33 @@ static struct tracepoint_path * get_tracepoints_path(struct perf_event_attr *pattrs, int nb_events) { struct tracepoint_path path, *ppath = &path; - int i; + int i, nr_tracepoints = 0; for (i = 0; i < nb_events; i++) { if (pattrs[i].type != PERF_TYPE_TRACEPOINT) continue; + ++nr_tracepoints; ppath->next = tracepoint_id_to_path(pattrs[i].config); if (!ppath->next) die("%s\n", "No memory to alloc tracepoints list"); ppath = ppath->next; } - return path.next; + return nr_tracepoints > 0 ? path.next : NULL; } -void read_tracing_data(struct perf_event_attr *pattrs, int nb_events) + +int read_tracing_data(int fd, struct perf_event_attr *pattrs, int nb_events) { char buf[BUFSIZ]; - struct tracepoint_path *tps; + struct tracepoint_path *tps = get_tracepoints_path(pattrs, nb_events); + + /* + * What? No tracepoints? No sense writing anything here, bail out. + */ + if (tps == NULL) + return -1; - output_fd = open(output_file, O_WRONLY | O_CREAT | O_TRUNC | O_LARGEFILE, 0644); - if (output_fd < 0) - die("creating file '%s'", output_file); + output_fd = fd; buf[0] = 23; buf[1] = 8; @@ -530,11 +536,11 @@ void read_tracing_data(struct perf_event_attr *pattrs, int nb_events) page_size = getpagesize(); write_or_die(&page_size, 4); - tps = get_tracepoints_path(pattrs, nb_events); - read_header_files(); read_ftrace_files(tps); read_event_files(tps); read_proc_kallsyms(); read_ftrace_printk(); + + return 0; } diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 55c9659a56e2..0302405aa2ca 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -40,12 +40,19 @@ int header_page_size_size; int header_page_data_offset; int header_page_data_size; +int latency_format; + static char *input_buf; static unsigned long long input_buf_ptr; static unsigned long long input_buf_siz; static int cpus; static int long_size; +static int is_flag_field; +static int is_symbolic_field; + +static struct format_field * +find_any_field(struct event *event, const char *name); static void init_input_buf(char *buf, unsigned long long size) { @@ -284,18 +291,19 @@ void parse_ftrace_printk(char *file, unsigned int size __unused) char *line; char *next = NULL; char *addr_str; - int ret; int i; line = strtok_r(file, "\n", &next); while (line) { + addr_str = strsep(&line, ":"); + if (!line) { + warning("error parsing print strings"); + break; + } item = malloc_or_die(sizeof(*item)); - ret = sscanf(line, "%as : %as", - (float *)(void *)&addr_str, /* workaround gcc warning */ - (float *)(void *)&item->printk); item->addr = strtoull(addr_str, NULL, 16); - free(addr_str); - + /* fmt still has a space, skip it */ + item->printk = strdup(line+1); item->next = list; list = item; line = strtok_r(NULL, "\n", &next); @@ -522,7 +530,10 @@ static enum event_type __read_token(char **tok) last_ch = ch; ch = __read_char(); buf[i++] = ch; - } while (ch != quote_ch && last_ch != '\\'); + /* the '\' '\' will cancel itself */ + if (ch == '\\' && last_ch == '\\') + last_ch = 0; + } while (ch != quote_ch || last_ch == '\\'); /* remove the last quote */ i--; goto out; @@ -610,7 +621,7 @@ static enum event_type read_token_item(char **tok) static int test_type(enum event_type type, enum event_type expect) { if (type != expect) { - die("Error: expected type %d but read %d", + warning("Error: expected type %d but read %d", expect, type); return -1; } @@ -621,13 +632,13 @@ static int test_type_token(enum event_type type, char *token, enum event_type expect, const char *expect_tok) { if (type != expect) { - die("Error: expected type %d but read %d", + warning("Error: expected type %d but read %d", expect, type); return -1; } if (strcmp(token, expect_tok) != 0) { - die("Error: expected '%s' but read '%s'", + warning("Error: expected '%s' but read '%s'", expect_tok, token); return -1; } @@ -665,7 +676,7 @@ static int __read_expected(enum event_type expect, const char *str, int newline_ free_token(token); - return 0; + return ret; } static int read_expected(enum event_type expect, const char *str) @@ -682,10 +693,10 @@ static char *event_read_name(void) { char *token; - if (read_expected(EVENT_ITEM, (char *)"name") < 0) + if (read_expected(EVENT_ITEM, "name") < 0) return NULL; - if (read_expected(EVENT_OP, (char *)":") < 0) + if (read_expected(EVENT_OP, ":") < 0) return NULL; if (read_expect_type(EVENT_ITEM, &token) < 0) @@ -703,10 +714,10 @@ static int event_read_id(void) char *token; int id; - if (read_expected_item(EVENT_ITEM, (char *)"ID") < 0) + if (read_expected_item(EVENT_ITEM, "ID") < 0) return -1; - if (read_expected(EVENT_OP, (char *)":") < 0) + if (read_expected(EVENT_OP, ":") < 0) return -1; if (read_expect_type(EVENT_ITEM, &token) < 0) @@ -721,6 +732,24 @@ static int event_read_id(void) return -1; } +static int field_is_string(struct format_field *field) +{ + if ((field->flags & FIELD_IS_ARRAY) && + (!strstr(field->type, "char") || !strstr(field->type, "u8") || + !strstr(field->type, "s8"))) + return 1; + + return 0; +} + +static int field_is_dynamic(struct format_field *field) +{ + if (!strcmp(field->type, "__data_loc")) + return 1; + + return 0; +} + static int event_read_fields(struct event *event, struct format_field **fields) { struct format_field *field = NULL; @@ -738,7 +767,7 @@ static int event_read_fields(struct event *event, struct format_field **fields) count++; - if (test_type_token(type, token, EVENT_ITEM, (char *)"field")) + if (test_type_token(type, token, EVENT_ITEM, "field")) goto fail; free_token(token); @@ -753,7 +782,7 @@ static int event_read_fields(struct event *event, struct format_field **fields) type = read_token(&token); } - if (test_type_token(type, token, EVENT_OP, (char *)":") < 0) + if (test_type_token(type, token, EVENT_OP, ":") < 0) return -1; if (read_expect_type(EVENT_ITEM, &token) < 0) @@ -865,14 +894,20 @@ static int event_read_fields(struct event *event, struct format_field **fields) free(brackets); } - if (test_type_token(type, token, EVENT_OP, (char *)";")) + if (field_is_string(field)) { + field->flags |= FIELD_IS_STRING; + if (field_is_dynamic(field)) + field->flags |= FIELD_IS_DYNAMIC; + } + + if (test_type_token(type, token, EVENT_OP, ";")) goto fail; free_token(token); - if (read_expected(EVENT_ITEM, (char *)"offset") < 0) + if (read_expected(EVENT_ITEM, "offset") < 0) goto fail_expect; - if (read_expected(EVENT_OP, (char *)":") < 0) + if (read_expected(EVENT_OP, ":") < 0) goto fail_expect; if (read_expect_type(EVENT_ITEM, &token)) @@ -880,13 +915,13 @@ static int event_read_fields(struct event *event, struct format_field **fields) field->offset = strtoul(token, NULL, 0); free_token(token); - if (read_expected(EVENT_OP, (char *)";") < 0) + if (read_expected(EVENT_OP, ";") < 0) goto fail_expect; - if (read_expected(EVENT_ITEM, (char *)"size") < 0) + if (read_expected(EVENT_ITEM, "size") < 0) goto fail_expect; - if (read_expected(EVENT_OP, (char *)":") < 0) + if (read_expected(EVENT_OP, ":") < 0) goto fail_expect; if (read_expect_type(EVENT_ITEM, &token)) @@ -894,11 +929,34 @@ static int event_read_fields(struct event *event, struct format_field **fields) field->size = strtoul(token, NULL, 0); free_token(token); - if (read_expected(EVENT_OP, (char *)";") < 0) + if (read_expected(EVENT_OP, ";") < 0) goto fail_expect; - if (read_expect_type(EVENT_NEWLINE, &token) < 0) - goto fail; + type = read_token(&token); + if (type != EVENT_NEWLINE) { + /* newer versions of the kernel have a "signed" type */ + if (test_type_token(type, token, EVENT_ITEM, "signed")) + goto fail; + + free_token(token); + + if (read_expected(EVENT_OP, ":") < 0) + goto fail_expect; + + if (read_expect_type(EVENT_ITEM, &token)) + goto fail; + + if (strtoul(token, NULL, 0)) + field->flags |= FIELD_IS_SIGNED; + + free_token(token); + if (read_expected(EVENT_OP, ";") < 0) + goto fail_expect; + + if (read_expect_type(EVENT_NEWLINE, &token)) + goto fail; + } + free_token(token); *fields = field; @@ -921,10 +979,10 @@ static int event_read_format(struct event *event) char *token; int ret; - if (read_expected_item(EVENT_ITEM, (char *)"format") < 0) + if (read_expected_item(EVENT_ITEM, "format") < 0) return -1; - if (read_expected(EVENT_OP, (char *)":") < 0) + if (read_expected(EVENT_OP, ":") < 0) return -1; if (read_expect_type(EVENT_NEWLINE, &token)) @@ -984,7 +1042,7 @@ process_cond(struct event *event, struct print_arg *top, char **tok) *tok = NULL; type = process_arg(event, left, &token); - if (test_type_token(type, token, EVENT_OP, (char *)":")) + if (test_type_token(type, token, EVENT_OP, ":")) goto out_free; arg->op.op = token; @@ -1004,6 +1062,35 @@ out_free: return EVENT_ERROR; } +static enum event_type +process_array(struct event *event, struct print_arg *top, char **tok) +{ + struct print_arg *arg; + enum event_type type; + char *token = NULL; + + arg = malloc_or_die(sizeof(*arg)); + memset(arg, 0, sizeof(*arg)); + + *tok = NULL; + type = process_arg(event, arg, &token); + if (test_type_token(type, token, EVENT_OP, "]")) + goto out_free; + + top->op.right = arg; + + free_token(token); + type = read_token_item(&token); + *tok = token; + + return type; + +out_free: + free_token(*tok); + free_arg(arg); + return EVENT_ERROR; +} + static int get_op_prio(char *op) { if (!op[1]) { @@ -1128,6 +1215,8 @@ process_op(struct event *event, struct print_arg *arg, char **tok) strcmp(token, "*") == 0 || strcmp(token, "^") == 0 || strcmp(token, "/") == 0 || + strcmp(token, "<") == 0 || + strcmp(token, ">") == 0 || strcmp(token, "==") == 0 || strcmp(token, "!=") == 0) { @@ -1144,17 +1233,46 @@ process_op(struct event *event, struct print_arg *arg, char **tok) right = malloc_or_die(sizeof(*right)); - type = process_arg(event, right, tok); + type = read_token_item(&token); + *tok = token; + + /* could just be a type pointer */ + if ((strcmp(arg->op.op, "*") == 0) && + type == EVENT_DELIM && (strcmp(token, ")") == 0)) { + if (left->type != PRINT_ATOM) + die("bad pointer type"); + left->atom.atom = realloc(left->atom.atom, + sizeof(left->atom.atom) + 3); + strcat(left->atom.atom, " *"); + *arg = *left; + free(arg); + + return type; + } + + type = process_arg_token(event, right, tok, type); arg->op.right = right; + } else if (strcmp(token, "[") == 0) { + + left = malloc_or_die(sizeof(*left)); + *left = *arg; + + arg->type = PRINT_OP; + arg->op.op = token; + arg->op.left = left; + + arg->op.prio = 0; + type = process_array(event, arg, tok); + } else { - die("unknown op '%s'", token); + warning("unknown op '%s'", token); + event->flags |= EVENT_FL_FAILED; /* the arg is now the left side */ return EVENT_NONE; } - if (type == EVENT_OP) { int prio; @@ -1178,7 +1296,7 @@ process_entry(struct event *event __unused, struct print_arg *arg, char *field; char *token; - if (read_expected(EVENT_OP, (char *)"->") < 0) + if (read_expected(EVENT_OP, "->") < 0) return EVENT_ERROR; if (read_expect_type(EVENT_ITEM, &token) < 0) @@ -1188,6 +1306,16 @@ process_entry(struct event *event __unused, struct print_arg *arg, arg->type = PRINT_FIELD; arg->field.name = field; + if (is_flag_field) { + arg->field.field = find_any_field(event, arg->field.name); + arg->field.field->flags |= FIELD_IS_FLAG; + is_flag_field = 0; + } else if (is_symbolic_field) { + arg->field.field = find_any_field(event, arg->field.name); + arg->field.field->flags |= FIELD_IS_SYMBOLIC; + is_symbolic_field = 0; + } + type = read_token(&token); *tok = token; @@ -1338,14 +1466,14 @@ process_fields(struct event *event, struct print_flag_sym **list, char **tok) do { free_token(token); type = read_token_item(&token); - if (test_type_token(type, token, EVENT_OP, (char *)"{")) + if (test_type_token(type, token, EVENT_OP, "{")) break; arg = malloc_or_die(sizeof(*arg)); free_token(token); type = process_arg(event, arg, &token); - if (test_type_token(type, token, EVENT_DELIM, (char *)",")) + if (test_type_token(type, token, EVENT_DELIM, ",")) goto out_free; field = malloc_or_die(sizeof(*field)); @@ -1356,7 +1484,7 @@ process_fields(struct event *event, struct print_flag_sym **list, char **tok) free_token(token); type = process_arg(event, arg, &token); - if (test_type_token(type, token, EVENT_OP, (char *)"}")) + if (test_type_token(type, token, EVENT_OP, "}")) goto out_free; value = arg_eval(arg); @@ -1391,13 +1519,13 @@ process_flags(struct event *event, struct print_arg *arg, char **tok) memset(arg, 0, sizeof(*arg)); arg->type = PRINT_FLAGS; - if (read_expected_item(EVENT_DELIM, (char *)"(") < 0) + if (read_expected_item(EVENT_DELIM, "(") < 0) return EVENT_ERROR; field = malloc_or_die(sizeof(*field)); type = process_arg(event, field, &token); - if (test_type_token(type, token, EVENT_DELIM, (char *)",")) + if (test_type_token(type, token, EVENT_DELIM, ",")) goto out_free; arg->flags.field = field; @@ -1408,11 +1536,11 @@ process_flags(struct event *event, struct print_arg *arg, char **tok) type = read_token_item(&token); } - if (test_type_token(type, token, EVENT_DELIM, (char *)",")) + if (test_type_token(type, token, EVENT_DELIM, ",")) goto out_free; type = process_fields(event, &arg->flags.flags, &token); - if (test_type_token(type, token, EVENT_DELIM, (char *)")")) + if (test_type_token(type, token, EVENT_DELIM, ")")) goto out_free; free_token(token); @@ -1434,19 +1562,19 @@ process_symbols(struct event *event, struct print_arg *arg, char **tok) memset(arg, 0, sizeof(*arg)); arg->type = PRINT_SYMBOL; - if (read_expected_item(EVENT_DELIM, (char *)"(") < 0) + if (read_expected_item(EVENT_DELIM, "(") < 0) return EVENT_ERROR; field = malloc_or_die(sizeof(*field)); type = process_arg(event, field, &token); - if (test_type_token(type, token, EVENT_DELIM, (char *)",")) + if (test_type_token(type, token, EVENT_DELIM, ",")) goto out_free; arg->symbol.field = field; type = process_fields(event, &arg->symbol.symbols, &token); - if (test_type_token(type, token, EVENT_DELIM, (char *)")")) + if (test_type_token(type, token, EVENT_DELIM, ")")) goto out_free; free_token(token); @@ -1463,7 +1591,6 @@ process_paren(struct event *event, struct print_arg *arg, char **tok) { struct print_arg *item_arg; enum event_type type; - int ptr_cast = 0; char *token; type = process_arg(event, arg, &token); @@ -1471,28 +1598,13 @@ process_paren(struct event *event, struct print_arg *arg, char **tok) if (type == EVENT_ERROR) return EVENT_ERROR; - if (type == EVENT_OP) { - /* handle the ptr casts */ - if (!strcmp(token, "*")) { - /* - * FIXME: should we zapp whitespaces before ')' ? - * (may require a peek_token_item()) - */ - if (__peek_char() == ')') { - ptr_cast = 1; - free_token(token); - type = read_token_item(&token); - } - } - if (!ptr_cast) { - type = process_op(event, arg, &token); + if (type == EVENT_OP) + type = process_op(event, arg, &token); - if (type == EVENT_ERROR) - return EVENT_ERROR; - } - } + if (type == EVENT_ERROR) + return EVENT_ERROR; - if (test_type_token(type, token, EVENT_DELIM, (char *)")")) { + if (test_type_token(type, token, EVENT_DELIM, ")")) { free_token(token); return EVENT_ERROR; } @@ -1516,13 +1628,6 @@ process_paren(struct event *event, struct print_arg *arg, char **tok) item_arg = malloc_or_die(sizeof(*item_arg)); arg->type = PRINT_TYPE; - if (ptr_cast) { - char *old = arg->atom.atom; - - arg->atom.atom = malloc_or_die(strlen(old + 3)); - sprintf(arg->atom.atom, "%s *", old); - free(old); - } arg->typecast.type = arg->atom.atom; arg->typecast.item = item_arg; type = process_arg_token(event, item_arg, &token, type); @@ -1540,7 +1645,7 @@ process_str(struct event *event __unused, struct print_arg *arg, char **tok) enum event_type type; char *token; - if (read_expected(EVENT_DELIM, (char *)"(") < 0) + if (read_expected(EVENT_DELIM, "(") < 0) return EVENT_ERROR; if (read_expect_type(EVENT_ITEM, &token) < 0) @@ -1550,7 +1655,7 @@ process_str(struct event *event __unused, struct print_arg *arg, char **tok) arg->string.string = token; arg->string.offset = -1; - if (read_expected(EVENT_DELIM, (char *)")") < 0) + if (read_expected(EVENT_DELIM, ")") < 0) return EVENT_ERROR; type = read_token(&token); @@ -1578,9 +1683,11 @@ process_arg_token(struct event *event, struct print_arg *arg, type = process_entry(event, arg, &token); } else if (strcmp(token, "__print_flags") == 0) { free_token(token); + is_flag_field = 1; type = process_flags(event, arg, &token); } else if (strcmp(token, "__print_symbolic") == 0) { free_token(token); + is_symbolic_field = 1; type = process_symbols(event, arg, &token); } else if (strcmp(token, "__get_str") == 0) { free_token(token); @@ -1637,12 +1744,18 @@ process_arg_token(struct event *event, struct print_arg *arg, static int event_read_print_args(struct event *event, struct print_arg **list) { - enum event_type type; + enum event_type type = EVENT_ERROR; struct print_arg *arg; char *token; int args = 0; do { + if (type == EVENT_NEWLINE) { + free_token(token); + type = read_token_item(&token); + continue; + } + arg = malloc_or_die(sizeof(*arg)); memset(arg, 0, sizeof(*arg)); @@ -1683,18 +1796,19 @@ static int event_read_print(struct event *event) char *token; int ret; - if (read_expected_item(EVENT_ITEM, (char *)"print") < 0) + if (read_expected_item(EVENT_ITEM, "print") < 0) return -1; - if (read_expected(EVENT_ITEM, (char *)"fmt") < 0) + if (read_expected(EVENT_ITEM, "fmt") < 0) return -1; - if (read_expected(EVENT_OP, (char *)":") < 0) + if (read_expected(EVENT_OP, ":") < 0) return -1; if (read_expect_type(EVENT_DQUOTE, &token) < 0) goto fail; + concat: event->print_fmt.format = token; event->print_fmt.args = NULL; @@ -1704,7 +1818,22 @@ static int event_read_print(struct event *event) if (type == EVENT_NONE) return 0; - if (test_type_token(type, token, EVENT_DELIM, (char *)",")) + /* Handle concatination of print lines */ + if (type == EVENT_DQUOTE) { + char *cat; + + cat = malloc_or_die(strlen(event->print_fmt.format) + + strlen(token) + 1); + strcpy(cat, event->print_fmt.format); + strcat(cat, token); + free_token(token); + free_token(event->print_fmt.format); + event->print_fmt.format = NULL; + token = cat; + goto concat; + } + + if (test_type_token(type, token, EVENT_DELIM, ",")) goto fail; free_token(token); @@ -1713,7 +1842,7 @@ static int event_read_print(struct event *event) if (ret < 0) return -1; - return 0; + return ret; fail: free_token(token); @@ -1759,7 +1888,7 @@ find_any_field(struct event *event, const char *name) return find_field(event, name); } -static unsigned long long read_size(void *ptr, int size) +unsigned long long read_size(void *ptr, int size) { switch (size) { case 1: @@ -1822,37 +1951,67 @@ static int get_common_info(const char *type, int *offset, int *size) return 0; } -int trace_parse_common_type(void *data) +static int __parse_common(void *data, int *size, int *offset, + const char *name) { - static int type_offset; - static int type_size; int ret; - if (!type_size) { - ret = get_common_info("common_type", - &type_offset, - &type_size); + if (!*size) { + ret = get_common_info(name, offset, size); if (ret < 0) return ret; } - return read_size(data + type_offset, type_size); + return read_size(data + *offset, *size); +} + +int trace_parse_common_type(void *data) +{ + static int type_offset; + static int type_size; + + return __parse_common(data, &type_size, &type_offset, + "common_type"); } -static int parse_common_pid(void *data) +int trace_parse_common_pid(void *data) { static int pid_offset; static int pid_size; + + return __parse_common(data, &pid_size, &pid_offset, + "common_pid"); +} + +int parse_common_pc(void *data) +{ + static int pc_offset; + static int pc_size; + + return __parse_common(data, &pc_size, &pc_offset, + "common_preempt_count"); +} + +int parse_common_flags(void *data) +{ + static int flags_offset; + static int flags_size; + + return __parse_common(data, &flags_size, &flags_offset, + "common_flags"); +} + +int parse_common_lock_depth(void *data) +{ + static int ld_offset; + static int ld_size; int ret; - if (!pid_size) { - ret = get_common_info("common_pid", - &pid_offset, - &pid_size); - if (ret < 0) - return ret; - } + ret = __parse_common(data, &ld_size, &ld_offset, + "common_lock_depth"); + if (ret < 0) + return -1; - return read_size(data + pid_offset, pid_size); + return ret; } struct event *trace_find_event(int id) @@ -1866,11 +2025,20 @@ struct event *trace_find_event(int id) return event; } +struct event *trace_find_next_event(struct event *event) +{ + if (!event) + return event_list; + + return event->next; +} + static unsigned long long eval_num_arg(void *data, int size, struct event *event, struct print_arg *arg) { unsigned long long val = 0; unsigned long long left, right; + struct print_arg *larg; switch (arg->type) { case PRINT_NULL: @@ -1897,6 +2065,26 @@ static unsigned long long eval_num_arg(void *data, int size, return 0; break; case PRINT_OP: + if (strcmp(arg->op.op, "[") == 0) { + /* + * Arrays are special, since we don't want + * to read the arg as is. + */ + if (arg->op.left->type != PRINT_FIELD) + goto default_op; /* oops, all bets off */ + larg = arg->op.left; + if (!larg->field.field) { + larg->field.field = + find_any_field(event, larg->field.name); + if (!larg->field.field) + die("field %s not found", larg->field.name); + } + right = eval_num_arg(data, size, event, arg->op.right); + val = read_size(data + larg->field.field->offset + + right * long_size, long_size); + break; + } + default_op: left = eval_num_arg(data, size, event, arg->op.left); right = eval_num_arg(data, size, event, arg->op.right); switch (arg->op.op[0]) { @@ -1947,6 +2135,12 @@ static unsigned long long eval_num_arg(void *data, int size, die("unknown op '%s'", arg->op.op); val = left == right; break; + case '-': + val = left - right; + break; + case '+': + val = left + right; + break; default: die("unknown op '%s'", arg->op.op); } @@ -1978,7 +2172,7 @@ static const struct flag flags[] = { { "HRTIMER_RESTART", 1 }, }; -static unsigned long long eval_flag(const char *flag) +unsigned long long eval_flag(const char *flag) { int i; @@ -2145,8 +2339,9 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc case 'u': case 'x': case 'i': - bptr = (void *)(((unsigned long)bptr + (long_size - 1)) & - ~(long_size - 1)); + /* the pointers are always 4 bytes aligned */ + bptr = (void *)(((unsigned long)bptr + 3) & + ~3); switch (ls) { case 0: case 1: @@ -2270,7 +2465,27 @@ static void pretty_print(void *data, int size, struct event *event) for (; *ptr; ptr++) { ls = 0; - if (*ptr == '%') { + if (*ptr == '\\') { + ptr++; + switch (*ptr) { + case 'n': + printf("\n"); + break; + case 't': + printf("\t"); + break; + case 'r': + printf("\r"); + break; + case '\\': + printf("\\"); + break; + default: + printf("%c", *ptr); + break; + } + + } else if (*ptr == '%') { saveptr = ptr; show_func = 0; cont_process: @@ -2377,6 +2592,41 @@ static inline int log10_cpu(int nb) return 1; } +static void print_lat_fmt(void *data, int size __unused) +{ + unsigned int lat_flags; + unsigned int pc; + int lock_depth; + int hardirq; + int softirq; + + lat_flags = parse_common_flags(data); + pc = parse_common_pc(data); + lock_depth = parse_common_lock_depth(data); + + hardirq = lat_flags & TRACE_FLAG_HARDIRQ; + softirq = lat_flags & TRACE_FLAG_SOFTIRQ; + + printf("%c%c%c", + (lat_flags & TRACE_FLAG_IRQS_OFF) ? 'd' : + (lat_flags & TRACE_FLAG_IRQS_NOSUPPORT) ? + 'X' : '.', + (lat_flags & TRACE_FLAG_NEED_RESCHED) ? + 'N' : '.', + (hardirq && softirq) ? 'H' : + hardirq ? 'h' : softirq ? 's' : '.'); + + if (pc) + printf("%x", pc); + else + printf("."); + + if (lock_depth < 0) + printf("."); + else + printf("%d", lock_depth); +} + /* taken from Linux, written by Frederic Weisbecker */ static void print_graph_cpu(int cpu) { @@ -2452,7 +2702,7 @@ get_return_for_leaf(int cpu, int cur_pid, unsigned long long cur_func, if (!(event->flags & EVENT_FL_ISFUNCRET)) return NULL; - pid = parse_common_pid(next->data); + pid = trace_parse_common_pid(next->data); field = find_field(event, "func"); if (!field) die("function return does not have field func"); @@ -2620,6 +2870,11 @@ pretty_print_func_ent(void *data, int size, struct event *event, printf(" | "); + if (latency_format) { + print_lat_fmt(data, size); + printf(" | "); + } + field = find_field(event, "func"); if (!field) die("function entry does not have func field"); @@ -2663,6 +2918,11 @@ pretty_print_func_ret(void *data, int size __unused, struct event *event, printf(" | "); + if (latency_format) { + print_lat_fmt(data, size); + printf(" | "); + } + field = find_field(event, "rettime"); if (!field) die("can't find rettime in return graph"); @@ -2724,19 +2984,30 @@ void print_event(int cpu, void *data, int size, unsigned long long nsecs, event = trace_find_event(type); if (!event) { - printf("ug! no event found for type %d\n", type); + warning("ug! no event found for type %d", type); return; } - pid = parse_common_pid(data); + pid = trace_parse_common_pid(data); if (event->flags & (EVENT_FL_ISFUNCENT | EVENT_FL_ISFUNCRET)) return pretty_print_func_graph(data, size, event, cpu, pid, comm, secs, usecs); - printf("%16s-%-5d [%03d] %5lu.%09Lu: %s: ", - comm, pid, cpu, - secs, nsecs, event->name); + if (latency_format) { + printf("%8.8s-%-5d %3d", + comm, pid, cpu); + print_lat_fmt(data, size); + } else + printf("%16s-%-5d [%03d]", comm, pid, cpu); + + printf(" %5lu.%06lu: %s: ", secs, usecs, event->name); + + if (event->flags & EVENT_FL_FAILED) { + printf("EVENT '%s' FAILED TO PARSE\n", + event->name); + return; + } pretty_print(data, size, event); printf("\n"); @@ -2807,46 +3078,71 @@ static void print_args(struct print_arg *args) } } -static void parse_header_field(char *type, +static void parse_header_field(const char *field, int *offset, int *size) { char *token; + int type; - if (read_expected(EVENT_ITEM, (char *)"field") < 0) + if (read_expected(EVENT_ITEM, "field") < 0) return; - if (read_expected(EVENT_OP, (char *)":") < 0) + if (read_expected(EVENT_OP, ":") < 0) return; + /* type */ if (read_expect_type(EVENT_ITEM, &token) < 0) - return; + goto fail; free_token(token); - if (read_expected(EVENT_ITEM, type) < 0) + if (read_expected(EVENT_ITEM, field) < 0) return; - if (read_expected(EVENT_OP, (char *)";") < 0) + if (read_expected(EVENT_OP, ";") < 0) return; - if (read_expected(EVENT_ITEM, (char *)"offset") < 0) + if (read_expected(EVENT_ITEM, "offset") < 0) return; - if (read_expected(EVENT_OP, (char *)":") < 0) + if (read_expected(EVENT_OP, ":") < 0) return; if (read_expect_type(EVENT_ITEM, &token) < 0) - return; + goto fail; *offset = atoi(token); free_token(token); - if (read_expected(EVENT_OP, (char *)";") < 0) + if (read_expected(EVENT_OP, ";") < 0) return; - if (read_expected(EVENT_ITEM, (char *)"size") < 0) + if (read_expected(EVENT_ITEM, "size") < 0) return; - if (read_expected(EVENT_OP, (char *)":") < 0) + if (read_expected(EVENT_OP, ":") < 0) return; if (read_expect_type(EVENT_ITEM, &token) < 0) - return; + goto fail; *size = atoi(token); free_token(token); - if (read_expected(EVENT_OP, (char *)";") < 0) - return; - if (read_expect_type(EVENT_NEWLINE, &token) < 0) + if (read_expected(EVENT_OP, ";") < 0) return; + type = read_token(&token); + if (type != EVENT_NEWLINE) { + /* newer versions of the kernel have a "signed" type */ + if (type != EVENT_ITEM) + goto fail; + + if (strcmp(token, "signed") != 0) + goto fail; + + free_token(token); + + if (read_expected(EVENT_OP, ":") < 0) + return; + + if (read_expect_type(EVENT_ITEM, &token)) + goto fail; + + free_token(token); + if (read_expected(EVENT_OP, ";") < 0) + return; + + if (read_expect_type(EVENT_NEWLINE, &token)) + goto fail; + } + fail: free_token(token); } @@ -2854,11 +3150,11 @@ int parse_header_page(char *buf, unsigned long size) { init_input_buf(buf, size); - parse_header_field((char *)"timestamp", &header_page_ts_offset, + parse_header_field("timestamp", &header_page_ts_offset, &header_page_ts_size); - parse_header_field((char *)"commit", &header_page_size_offset, + parse_header_field("commit", &header_page_size_offset, &header_page_size_size); - parse_header_field((char *)"data", &header_page_data_offset, + parse_header_field("data", &header_page_data_offset, &header_page_data_size); return 0; @@ -2909,6 +3205,9 @@ int parse_ftrace_file(char *buf, unsigned long size) if (ret < 0) die("failed to read ftrace event print fmt"); + /* New ftrace handles args */ + if (ret > 0) + return 0; /* * The arguments for ftrace files are parsed by the fields. * Set up the fields as their arguments. @@ -2926,7 +3225,7 @@ int parse_ftrace_file(char *buf, unsigned long size) return 0; } -int parse_event_file(char *buf, unsigned long size, char *system__unused __unused) +int parse_event_file(char *buf, unsigned long size, char *sys) { struct event *event; int ret; @@ -2946,12 +3245,18 @@ int parse_event_file(char *buf, unsigned long size, char *system__unused __unuse die("failed to read event id"); ret = event_read_format(event); - if (ret < 0) - die("failed to read event format"); + if (ret < 0) { + warning("failed to read event format for %s", event->name); + goto event_failed; + } ret = event_read_print(event); - if (ret < 0) - die("failed to read event print fmt"); + if (ret < 0) { + warning("failed to read event print fmt for %s", event->name); + goto event_failed; + } + + event->system = strdup(sys); #define PRINT_ARGS 0 if (PRINT_ARGS && event->print_fmt.args) @@ -2959,6 +3264,12 @@ int parse_event_file(char *buf, unsigned long size, char *system__unused __unuse add_event(event); return 0; + + event_failed: + event->flags |= EVENT_FL_FAILED; + /* still add it even if it failed */ + add_event(event); + return -1; } void parse_set_info(int nr_cpus, int long_sz) diff --git a/tools/perf/util/trace-event-perl.c b/tools/perf/util/trace-event-perl.c new file mode 100644 index 000000000000..51e833fd58c3 --- /dev/null +++ b/tools/perf/util/trace-event-perl.c @@ -0,0 +1,598 @@ +/* + * trace-event-perl. Feed perf trace events to an embedded Perl interpreter. + * + * Copyright (C) 2009 Tom Zanussi <tzanussi@gmail.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + */ + +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <ctype.h> +#include <errno.h> + +#include "../perf.h" +#include "util.h" +#include "trace-event.h" +#include "trace-event-perl.h" + +void xs_init(pTHX); + +void boot_Perf__Trace__Context(pTHX_ CV *cv); +void boot_DynaLoader(pTHX_ CV *cv); + +void xs_init(pTHX) +{ + const char *file = __FILE__; + dXSUB_SYS; + + newXS("Perf::Trace::Context::bootstrap", boot_Perf__Trace__Context, + file); + newXS("DynaLoader::boot_DynaLoader", boot_DynaLoader, file); +} + +INTERP my_perl; + +#define FTRACE_MAX_EVENT \ + ((1 << (sizeof(unsigned short) * 8)) - 1) + +struct event *events[FTRACE_MAX_EVENT]; + +static struct scripting_context *scripting_context; + +static char *cur_field_name; +static int zero_flag_atom; + +static void define_symbolic_value(const char *ev_name, + const char *field_name, + const char *field_value, + const char *field_str) +{ + unsigned long long value; + dSP; + + value = eval_flag(field_value); + + ENTER; + SAVETMPS; + PUSHMARK(SP); + + XPUSHs(sv_2mortal(newSVpv(ev_name, 0))); + XPUSHs(sv_2mortal(newSVpv(field_name, 0))); + XPUSHs(sv_2mortal(newSVuv(value))); + XPUSHs(sv_2mortal(newSVpv(field_str, 0))); + + PUTBACK; + if (get_cv("main::define_symbolic_value", 0)) + call_pv("main::define_symbolic_value", G_SCALAR); + SPAGAIN; + PUTBACK; + FREETMPS; + LEAVE; +} + +static void define_symbolic_values(struct print_flag_sym *field, + const char *ev_name, + const char *field_name) +{ + define_symbolic_value(ev_name, field_name, field->value, field->str); + if (field->next) + define_symbolic_values(field->next, ev_name, field_name); +} + +static void define_symbolic_field(const char *ev_name, + const char *field_name) +{ + dSP; + + ENTER; + SAVETMPS; + PUSHMARK(SP); + + XPUSHs(sv_2mortal(newSVpv(ev_name, 0))); + XPUSHs(sv_2mortal(newSVpv(field_name, 0))); + + PUTBACK; + if (get_cv("main::define_symbolic_field", 0)) + call_pv("main::define_symbolic_field", G_SCALAR); + SPAGAIN; + PUTBACK; + FREETMPS; + LEAVE; +} + +static void define_flag_value(const char *ev_name, + const char *field_name, + const char *field_value, + const char *field_str) +{ + unsigned long long value; + dSP; + + value = eval_flag(field_value); + + ENTER; + SAVETMPS; + PUSHMARK(SP); + + XPUSHs(sv_2mortal(newSVpv(ev_name, 0))); + XPUSHs(sv_2mortal(newSVpv(field_name, 0))); + XPUSHs(sv_2mortal(newSVuv(value))); + XPUSHs(sv_2mortal(newSVpv(field_str, 0))); + + PUTBACK; + if (get_cv("main::define_flag_value", 0)) + call_pv("main::define_flag_value", G_SCALAR); + SPAGAIN; + PUTBACK; + FREETMPS; + LEAVE; +} + +static void define_flag_values(struct print_flag_sym *field, + const char *ev_name, + const char *field_name) +{ + define_flag_value(ev_name, field_name, field->value, field->str); + if (field->next) + define_flag_values(field->next, ev_name, field_name); +} + +static void define_flag_field(const char *ev_name, + const char *field_name, + const char *delim) +{ + dSP; + + ENTER; + SAVETMPS; + PUSHMARK(SP); + + XPUSHs(sv_2mortal(newSVpv(ev_name, 0))); + XPUSHs(sv_2mortal(newSVpv(field_name, 0))); + XPUSHs(sv_2mortal(newSVpv(delim, 0))); + + PUTBACK; + if (get_cv("main::define_flag_field", 0)) + call_pv("main::define_flag_field", G_SCALAR); + SPAGAIN; + PUTBACK; + FREETMPS; + LEAVE; +} + +static void define_event_symbols(struct event *event, + const char *ev_name, + struct print_arg *args) +{ + switch (args->type) { + case PRINT_NULL: + break; + case PRINT_ATOM: + define_flag_value(ev_name, cur_field_name, "0", + args->atom.atom); + zero_flag_atom = 0; + break; + case PRINT_FIELD: + if (cur_field_name) + free(cur_field_name); + cur_field_name = strdup(args->field.name); + break; + case PRINT_FLAGS: + define_event_symbols(event, ev_name, args->flags.field); + define_flag_field(ev_name, cur_field_name, args->flags.delim); + define_flag_values(args->flags.flags, ev_name, cur_field_name); + break; + case PRINT_SYMBOL: + define_event_symbols(event, ev_name, args->symbol.field); + define_symbolic_field(ev_name, cur_field_name); + define_symbolic_values(args->symbol.symbols, ev_name, + cur_field_name); + break; + case PRINT_STRING: + break; + case PRINT_TYPE: + define_event_symbols(event, ev_name, args->typecast.item); + break; + case PRINT_OP: + if (strcmp(args->op.op, ":") == 0) + zero_flag_atom = 1; + define_event_symbols(event, ev_name, args->op.left); + define_event_symbols(event, ev_name, args->op.right); + break; + default: + /* we should warn... */ + return; + } + + if (args->next) + define_event_symbols(event, ev_name, args->next); +} + +static inline struct event *find_cache_event(int type) +{ + static char ev_name[256]; + struct event *event; + + if (events[type]) + return events[type]; + + events[type] = event = trace_find_event(type); + if (!event) + return NULL; + + sprintf(ev_name, "%s::%s", event->system, event->name); + + define_event_symbols(event, ev_name, event->print_fmt.args); + + return event; +} + +int common_pc(struct scripting_context *context) +{ + int pc; + + pc = parse_common_pc(context->event_data); + + return pc; +} + +int common_flags(struct scripting_context *context) +{ + int flags; + + flags = parse_common_flags(context->event_data); + + return flags; +} + +int common_lock_depth(struct scripting_context *context) +{ + int lock_depth; + + lock_depth = parse_common_lock_depth(context->event_data); + + return lock_depth; +} + +static void perl_process_event(int cpu, void *data, + int size __attribute((unused)), + unsigned long long nsecs, char *comm) +{ + struct format_field *field; + static char handler[256]; + unsigned long long val; + unsigned long s, ns; + struct event *event; + int type; + int pid; + + dSP; + + type = trace_parse_common_type(data); + + event = find_cache_event(type); + if (!event) + die("ug! no event found for type %d", type); + + pid = trace_parse_common_pid(data); + + sprintf(handler, "%s::%s", event->system, event->name); + + s = nsecs / NSECS_PER_SEC; + ns = nsecs - s * NSECS_PER_SEC; + + scripting_context->event_data = data; + + ENTER; + SAVETMPS; + PUSHMARK(SP); + + XPUSHs(sv_2mortal(newSVpv(handler, 0))); + XPUSHs(sv_2mortal(newSViv(PTR2IV(scripting_context)))); + XPUSHs(sv_2mortal(newSVuv(cpu))); + XPUSHs(sv_2mortal(newSVuv(s))); + XPUSHs(sv_2mortal(newSVuv(ns))); + XPUSHs(sv_2mortal(newSViv(pid))); + XPUSHs(sv_2mortal(newSVpv(comm, 0))); + + /* common fields other than pid can be accessed via xsub fns */ + + for (field = event->format.fields; field; field = field->next) { + if (field->flags & FIELD_IS_STRING) { + int offset; + if (field->flags & FIELD_IS_DYNAMIC) { + offset = *(int *)(data + field->offset); + offset &= 0xffff; + } else + offset = field->offset; + XPUSHs(sv_2mortal(newSVpv((char *)data + offset, 0))); + } else { /* FIELD_IS_NUMERIC */ + val = read_size(data + field->offset, field->size); + if (field->flags & FIELD_IS_SIGNED) { + XPUSHs(sv_2mortal(newSViv(val))); + } else { + XPUSHs(sv_2mortal(newSVuv(val))); + } + } + } + + PUTBACK; + + if (get_cv(handler, 0)) + call_pv(handler, G_SCALAR); + else if (get_cv("main::trace_unhandled", 0)) { + XPUSHs(sv_2mortal(newSVpv(handler, 0))); + XPUSHs(sv_2mortal(newSViv(PTR2IV(scripting_context)))); + XPUSHs(sv_2mortal(newSVuv(cpu))); + XPUSHs(sv_2mortal(newSVuv(nsecs))); + XPUSHs(sv_2mortal(newSViv(pid))); + XPUSHs(sv_2mortal(newSVpv(comm, 0))); + call_pv("main::trace_unhandled", G_SCALAR); + } + SPAGAIN; + PUTBACK; + FREETMPS; + LEAVE; +} + +static void run_start_sub(void) +{ + dSP; /* access to Perl stack */ + PUSHMARK(SP); + + if (get_cv("main::trace_begin", 0)) + call_pv("main::trace_begin", G_DISCARD | G_NOARGS); +} + +/* + * Start trace script + */ +static int perl_start_script(const char *script) +{ + const char *command_line[2] = { "", NULL }; + + command_line[1] = script; + + my_perl = perl_alloc(); + perl_construct(my_perl); + + if (perl_parse(my_perl, xs_init, 2, (char **)command_line, + (char **)NULL)) + return -1; + + perl_run(my_perl); + if (SvTRUE(ERRSV)) + return -1; + + run_start_sub(); + + fprintf(stderr, "perf trace started with Perl script %s\n\n", script); + + return 0; +} + +/* + * Stop trace script + */ +static int perl_stop_script(void) +{ + dSP; /* access to Perl stack */ + PUSHMARK(SP); + + if (get_cv("main::trace_end", 0)) + call_pv("main::trace_end", G_DISCARD | G_NOARGS); + + perl_destruct(my_perl); + perl_free(my_perl); + + fprintf(stderr, "\nperf trace Perl script stopped\n"); + + return 0; +} + +static int perl_generate_script(const char *outfile) +{ + struct event *event = NULL; + struct format_field *f; + char fname[PATH_MAX]; + int not_first, count; + FILE *ofp; + + sprintf(fname, "%s.pl", outfile); + ofp = fopen(fname, "w"); + if (ofp == NULL) { + fprintf(stderr, "couldn't open %s\n", fname); + return -1; + } + + fprintf(ofp, "# perf trace event handlers, " + "generated by perf trace -g perl\n"); + + fprintf(ofp, "# Licensed under the terms of the GNU GPL" + " License version 2\n\n"); + + fprintf(ofp, "# The common_* event handler fields are the most useful " + "fields common to\n"); + + fprintf(ofp, "# all events. They don't necessarily correspond to " + "the 'common_*' fields\n"); + + fprintf(ofp, "# in the format files. Those fields not available as " + "handler params can\n"); + + fprintf(ofp, "# be retrieved using Perl functions of the form " + "common_*($context).\n"); + + fprintf(ofp, "# See Context.pm for the list of available " + "functions.\n\n"); + + fprintf(ofp, "use lib \"$ENV{'PERF_EXEC_PATH'}/scripts/perl/" + "Perf-Trace-Util/lib\";\n"); + + fprintf(ofp, "use lib \"./Perf-Trace-Util/lib\";\n"); + fprintf(ofp, "use Perf::Trace::Core;\n"); + fprintf(ofp, "use Perf::Trace::Context;\n"); + fprintf(ofp, "use Perf::Trace::Util;\n\n"); + + fprintf(ofp, "sub trace_begin\n{\n\t# optional\n}\n\n"); + fprintf(ofp, "sub trace_end\n{\n\t# optional\n}\n\n"); + + while ((event = trace_find_next_event(event))) { + fprintf(ofp, "sub %s::%s\n{\n", event->system, event->name); + fprintf(ofp, "\tmy ("); + + fprintf(ofp, "$event_name, "); + fprintf(ofp, "$context, "); + fprintf(ofp, "$common_cpu, "); + fprintf(ofp, "$common_secs, "); + fprintf(ofp, "$common_nsecs,\n"); + fprintf(ofp, "\t $common_pid, "); + fprintf(ofp, "$common_comm,\n\t "); + + not_first = 0; + count = 0; + + for (f = event->format.fields; f; f = f->next) { + if (not_first++) + fprintf(ofp, ", "); + if (++count % 5 == 0) + fprintf(ofp, "\n\t "); + + fprintf(ofp, "$%s", f->name); + } + fprintf(ofp, ") = @_;\n\n"); + + fprintf(ofp, "\tprint_header($event_name, $common_cpu, " + "$common_secs, $common_nsecs,\n\t " + "$common_pid, $common_comm);\n\n"); + + fprintf(ofp, "\tprintf(\""); + + not_first = 0; + count = 0; + + for (f = event->format.fields; f; f = f->next) { + if (not_first++) + fprintf(ofp, ", "); + if (count && count % 4 == 0) { + fprintf(ofp, "\".\n\t \""); + } + count++; + + fprintf(ofp, "%s=", f->name); + if (f->flags & FIELD_IS_STRING || + f->flags & FIELD_IS_FLAG || + f->flags & FIELD_IS_SYMBOLIC) + fprintf(ofp, "%%s"); + else if (f->flags & FIELD_IS_SIGNED) + fprintf(ofp, "%%d"); + else + fprintf(ofp, "%%u"); + } + + fprintf(ofp, "\\n\",\n\t "); + + not_first = 0; + count = 0; + + for (f = event->format.fields; f; f = f->next) { + if (not_first++) + fprintf(ofp, ", "); + + if (++count % 5 == 0) + fprintf(ofp, "\n\t "); + + if (f->flags & FIELD_IS_FLAG) { + if ((count - 1) % 5 != 0) { + fprintf(ofp, "\n\t "); + count = 4; + } + fprintf(ofp, "flag_str(\""); + fprintf(ofp, "%s::%s\", ", event->system, + event->name); + fprintf(ofp, "\"%s\", $%s)", f->name, + f->name); + } else if (f->flags & FIELD_IS_SYMBOLIC) { + if ((count - 1) % 5 != 0) { + fprintf(ofp, "\n\t "); + count = 4; + } + fprintf(ofp, "symbol_str(\""); + fprintf(ofp, "%s::%s\", ", event->system, + event->name); + fprintf(ofp, "\"%s\", $%s)", f->name, + f->name); + } else + fprintf(ofp, "$%s", f->name); + } + + fprintf(ofp, ");\n"); + fprintf(ofp, "}\n\n"); + } + + fprintf(ofp, "sub trace_unhandled\n{\n\tmy ($event_name, $context, " + "$common_cpu, $common_secs, $common_nsecs,\n\t " + "$common_pid, $common_comm) = @_;\n\n"); + + fprintf(ofp, "\tprint_header($event_name, $common_cpu, " + "$common_secs, $common_nsecs,\n\t $common_pid, " + "$common_comm);\n}\n\n"); + + fprintf(ofp, "sub print_header\n{\n" + "\tmy ($event_name, $cpu, $secs, $nsecs, $pid, $comm) = @_;\n\n" + "\tprintf(\"%%-20s %%5u %%05u.%%09u %%8u %%-20s \",\n\t " + "$event_name, $cpu, $secs, $nsecs, $pid, $comm);\n}"); + + fclose(ofp); + + fprintf(stderr, "generated Perl script: %s\n", fname); + + return 0; +} + +struct scripting_ops perl_scripting_ops = { + .name = "Perl", + .start_script = perl_start_script, + .stop_script = perl_stop_script, + .process_event = perl_process_event, + .generate_script = perl_generate_script, +}; + +#ifdef NO_LIBPERL +void setup_perl_scripting(void) +{ + fprintf(stderr, "Perl scripting not supported." + " Install libperl and rebuild perf to enable it. e.g. " + "apt-get install libperl-dev (ubuntu), yum install " + "perl-ExtUtils-Embed (Fedora), etc.\n"); +} +#else +void setup_perl_scripting(void) +{ + int err; + err = script_spec_register("Perl", &perl_scripting_ops); + if (err) + die("error registering Perl script extension"); + + err = script_spec_register("pl", &perl_scripting_ops); + if (err) + die("error registering pl script extension"); + + scripting_context = malloc(sizeof(struct scripting_context)); +} +#endif diff --git a/tools/perf/util/trace-event-perl.h b/tools/perf/util/trace-event-perl.h new file mode 100644 index 000000000000..8fe0d866fe1a --- /dev/null +++ b/tools/perf/util/trace-event-perl.h @@ -0,0 +1,51 @@ +#ifndef __PERF_TRACE_EVENT_PERL_H +#define __PERF_TRACE_EVENT_PERL_H +#ifdef NO_LIBPERL +typedef int INTERP; +#define dSP +#define ENTER +#define SAVETMPS +#define PUTBACK +#define SPAGAIN +#define FREETMPS +#define LEAVE +#define SP +#define ERRSV +#define G_SCALAR (0) +#define G_DISCARD (0) +#define G_NOARGS (0) +#define PUSHMARK(a) +#define SvTRUE(a) (0) +#define XPUSHs(s) +#define sv_2mortal(a) +#define newSVpv(a,b) +#define newSVuv(a) +#define newSViv(a) +#define get_cv(a,b) (0) +#define call_pv(a,b) (0) +#define perl_alloc() (0) +#define perl_construct(a) (0) +#define perl_parse(a,b,c,d,e) (0) +#define perl_run(a) (0) +#define perl_destruct(a) (0) +#define perl_free(a) (0) +#define pTHX void +#define CV void +#define dXSUB_SYS +#define pTHX_ +static inline void newXS(const char *a, void *b, const char *c) {} +#else +#include <EXTERN.h> +#include <perl.h> +typedef PerlInterpreter * INTERP; +#endif + +struct scripting_context { + void *event_data; +}; + +int common_pc(struct scripting_context *context); +int common_flags(struct scripting_context *context); +int common_lock_depth(struct scripting_context *context); + +#endif /* __PERF_TRACE_EVENT_PERL_H */ diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c index 1b5c847d2c22..342dfdd43f87 100644 --- a/tools/perf/util/trace-event-read.c +++ b/tools/perf/util/trace-event-read.c @@ -458,9 +458,8 @@ struct record *trace_read_data(int cpu) return data; } -void trace_report(void) +void trace_report(int fd) { - const char *input_file = "trace.info"; char buf[BUFSIZ]; char test[] = { 23, 8, 68 }; char *version; @@ -468,17 +467,15 @@ void trace_report(void) int show_funcs = 0; int show_printk = 0; - input_fd = open(input_file, O_RDONLY); - if (input_fd < 0) - die("opening '%s'\n", input_file); + input_fd = fd; read_or_die(buf, 3); if (memcmp(buf, test, 3) != 0) - die("not an trace data file"); + die("no trace data in the file"); read_or_die(buf, 7); if (memcmp(buf, "tracing", 7) != 0) - die("not a trace file (missing tracing)"); + die("not a trace file (missing 'tracing' tag)"); version = read_string(); if (show_version) diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index 693f815c9429..81698d5e6503 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -1,5 +1,5 @@ -#ifndef _TRACE_EVENTS_H -#define _TRACE_EVENTS_H +#ifndef __PERF_TRACE_EVENTS_H +#define __PERF_TRACE_EVENTS_H #include "parse-events.h" @@ -26,6 +26,11 @@ enum { enum format_flags { FIELD_IS_ARRAY = 1, FIELD_IS_POINTER = 2, + FIELD_IS_SIGNED = 4, + FIELD_IS_STRING = 8, + FIELD_IS_DYNAMIC = 16, + FIELD_IS_FLAG = 32, + FIELD_IS_SYMBOLIC = 64, }; struct format_field { @@ -132,15 +137,18 @@ struct event { int flags; struct format format; struct print_fmt print_fmt; + char *system; }; enum { - EVENT_FL_ISFTRACE = 1, - EVENT_FL_ISPRINT = 2, - EVENT_FL_ISBPRINT = 4, - EVENT_FL_ISFUNC = 8, - EVENT_FL_ISFUNCENT = 16, - EVENT_FL_ISFUNCRET = 32, + EVENT_FL_ISFTRACE = 0x01, + EVENT_FL_ISPRINT = 0x02, + EVENT_FL_ISBPRINT = 0x04, + EVENT_FL_ISFUNC = 0x08, + EVENT_FL_ISFUNCENT = 0x10, + EVENT_FL_ISFUNCRET = 0x20, + + EVENT_FL_FAILED = 0x80000000 }; struct record { @@ -154,7 +162,7 @@ struct record *trace_read_data(int cpu); void parse_set_info(int nr_cpus, int long_sz); -void trace_report(void); +void trace_report(int fd); void *malloc_or_die(unsigned int size); @@ -166,7 +174,7 @@ void print_funcs(void); void print_printk(void); int parse_ftrace_file(char *buf, unsigned long size); -int parse_event_file(char *buf, unsigned long size, char *system); +int parse_event_file(char *buf, unsigned long size, char *sys); void print_event(int cpu, void *data, int size, unsigned long long nsecs, char *comm); @@ -233,13 +241,45 @@ extern int header_page_size_size; extern int header_page_data_offset; extern int header_page_data_size; +extern int latency_format; + int parse_header_page(char *buf, unsigned long size); int trace_parse_common_type(void *data); +int trace_parse_common_pid(void *data); +int parse_common_pc(void *data); +int parse_common_flags(void *data); +int parse_common_lock_depth(void *data); struct event *trace_find_event(int id); +struct event *trace_find_next_event(struct event *event); +unsigned long long read_size(void *ptr, int size); unsigned long long raw_field_value(struct event *event, const char *name, void *data); void *raw_field_ptr(struct event *event, const char *name, void *data); +unsigned long long eval_flag(const char *flag); + +int read_tracing_data(int fd, struct perf_event_attr *pattrs, int nb_events); + +/* taken from kernel/trace/trace.h */ +enum trace_flag_type { + TRACE_FLAG_IRQS_OFF = 0x01, + TRACE_FLAG_IRQS_NOSUPPORT = 0x02, + TRACE_FLAG_NEED_RESCHED = 0x04, + TRACE_FLAG_HARDIRQ = 0x08, + TRACE_FLAG_SOFTIRQ = 0x10, +}; + +struct scripting_ops { + const char *name; + int (*start_script) (const char *); + int (*stop_script) (void); + void (*process_event) (int cpu, void *data, int size, + unsigned long long nsecs, char *comm); + int (*generate_script) (const char *outfile); +}; + +int script_spec_register(const char *spec, struct scripting_ops *ops); -void read_tracing_data(struct perf_event_attr *pattrs, int nb_events); +extern struct scripting_ops perl_scripting_ops; +void setup_perl_scripting(void); -#endif /* _TRACE_EVENTS_H */ +#endif /* __PERF_TRACE_EVENTS_H */ diff --git a/tools/perf/util/types.h b/tools/perf/util/types.h index 5e75f9005940..7d6b8331f898 100644 --- a/tools/perf/util/types.h +++ b/tools/perf/util/types.h @@ -1,5 +1,5 @@ -#ifndef _PERF_TYPES_H -#define _PERF_TYPES_H +#ifndef __PERF_TYPES_H +#define __PERF_TYPES_H /* * We define u64 as unsigned long long for every architecture @@ -14,4 +14,4 @@ typedef signed short s16; typedef unsigned char u8; typedef signed char s8; -#endif /* _PERF_TYPES_H */ +#endif /* __PERF_TYPES_H */ diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 9de2329dd44d..c673d8825883 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -84,6 +84,9 @@ #include <iconv.h> #endif +extern const char *graph_line; +extern const char *graph_dotted_line; + /* On most systems <limits.h> would have given us this, but * not on some systems (e.g. GNU/Hurd). */ @@ -134,6 +137,15 @@ extern void die(const char *err, ...) NORETURN __attribute__((format (printf, 1, extern int error(const char *err, ...) __attribute__((format (printf, 1, 2))); extern void warning(const char *err, ...) __attribute__((format (printf, 1, 2))); +#include "../../../include/linux/stringify.h" + +#define DIE_IF(cnd) \ + do { if (cnd) \ + die(" at (" __FILE__ ":" __stringify(__LINE__) "): " \ + __stringify(cnd) "\n"); \ + } while (0) + + extern void set_die_routine(void (*routine)(const char *err, va_list params) NORETURN); extern int prefixcmp(const char *str, const char *prefix); @@ -278,17 +290,15 @@ static inline char *gitstrchrnul(const char *s, int c) * Wrappers: */ extern char *xstrdup(const char *str); -extern void *xmalloc(size_t size); +extern void *xmalloc(size_t size) __attribute__((weak)); extern void *xmemdupz(const void *data, size_t len); extern char *xstrndup(const char *str, size_t len); -extern void *xrealloc(void *ptr, size_t size); -extern void *xcalloc(size_t nmemb, size_t size); -extern void *xmmap(void *start, size_t length, int prot, int flags, int fd, off_t offset); -extern ssize_t xread(int fd, void *buf, size_t len); -extern ssize_t xwrite(int fd, const void *buf, size_t len); -extern int xdup(int fd); -extern FILE *xfdopen(int fd, const char *mode); -extern int xmkstemp(char *template); +extern void *xrealloc(void *ptr, size_t size) __attribute__((weak)); + +static inline void *zalloc(size_t size) +{ + return calloc(1, size); +} static inline size_t xsize_t(off_t len) { @@ -306,6 +316,7 @@ static inline int has_extension(const char *filename, const char *ext) #undef isascii #undef isspace #undef isdigit +#undef isxdigit #undef isalpha #undef isprint #undef isalnum @@ -323,6 +334,8 @@ extern unsigned char sane_ctype[256]; #define isascii(x) (((x) & ~0x7f) == 0) #define isspace(x) sane_istest(x,GIT_SPACE) #define isdigit(x) sane_istest(x,GIT_DIGIT) +#define isxdigit(x) \ + (sane_istest(toupper(x), GIT_ALPHA | GIT_DIGIT) && toupper(x) < 'G') #define isalpha(x) sane_istest(x,GIT_ALPHA) #define isalnum(x) sane_istest(x,GIT_ALPHA | GIT_DIGIT) #define isprint(x) sane_istest(x,GIT_PRINT) diff --git a/tools/perf/util/values.h b/tools/perf/util/values.h index cadf8cf2a590..2fa967e1a88a 100644 --- a/tools/perf/util/values.h +++ b/tools/perf/util/values.h @@ -1,5 +1,5 @@ -#ifndef _PERF_VALUES_H -#define _PERF_VALUES_H +#ifndef __PERF_VALUES_H +#define __PERF_VALUES_H #include "types.h" @@ -24,4 +24,4 @@ void perf_read_values_add_value(struct perf_read_values *values, void perf_read_values_display(FILE *fp, struct perf_read_values *values, int raw); -#endif /* _PERF_VALUES_H */ +#endif /* __PERF_VALUES_H */ diff --git a/tools/perf/util/wrapper.c b/tools/perf/util/wrapper.c index 4574ac28396f..bf44ca85d23b 100644 --- a/tools/perf/util/wrapper.c +++ b/tools/perf/util/wrapper.c @@ -79,43 +79,12 @@ void *xrealloc(void *ptr, size_t size) return ret; } -void *xcalloc(size_t nmemb, size_t size) -{ - void *ret = calloc(nmemb, size); - if (!ret && (!nmemb || !size)) - ret = calloc(1, 1); - if (!ret) { - release_pack_memory(nmemb * size, -1); - ret = calloc(nmemb, size); - if (!ret && (!nmemb || !size)) - ret = calloc(1, 1); - if (!ret) - die("Out of memory, calloc failed"); - } - return ret; -} - -void *xmmap(void *start, size_t length, - int prot, int flags, int fd, off_t offset) -{ - void *ret = mmap(start, length, prot, flags, fd, offset); - if (ret == MAP_FAILED) { - if (!length) - return NULL; - release_pack_memory(length, fd); - ret = mmap(start, length, prot, flags, fd, offset); - if (ret == MAP_FAILED) - die("Out of memory? mmap failed: %s", strerror(errno)); - } - return ret; -} - /* * xread() is the same a read(), but it automatically restarts read() * operations with a recoverable error (EAGAIN and EINTR). xread() * DOES NOT GUARANTEE that "len" bytes is read even if the data is available. */ -ssize_t xread(int fd, void *buf, size_t len) +static ssize_t xread(int fd, void *buf, size_t len) { ssize_t nr; while (1) { @@ -131,7 +100,7 @@ ssize_t xread(int fd, void *buf, size_t len) * operations with a recoverable error (EAGAIN and EINTR). xwrite() DOES NOT * GUARANTEE that "len" bytes is written even if the operation is successful. */ -ssize_t xwrite(int fd, const void *buf, size_t len) +static ssize_t xwrite(int fd, const void *buf, size_t len) { ssize_t nr; while (1) { @@ -179,29 +148,3 @@ ssize_t write_in_full(int fd, const void *buf, size_t count) return total; } - -int xdup(int fd) -{ - int ret = dup(fd); - if (ret < 0) - die("dup failed: %s", strerror(errno)); - return ret; -} - -FILE *xfdopen(int fd, const char *mode) -{ - FILE *stream = fdopen(fd, mode); - if (stream == NULL) - die("Out of memory? fdopen failed: %s", strerror(errno)); - return stream; -} - -int xmkstemp(char *template) -{ - int fd; - - fd = mkstemp(template); - if (fd < 0) - die("Unable to create temporary file: %s", strerror(errno)); - return fd; -} |