diff options
1272 files changed, 22647 insertions, 20660 deletions
diff --git a/Documentation/DocBook/kernel-hacking.tmpl b/Documentation/DocBook/kernel-hacking.tmpl index da5c087462b1..c3c705591532 100644 --- a/Documentation/DocBook/kernel-hacking.tmpl +++ b/Documentation/DocBook/kernel-hacking.tmpl @@ -819,7 +819,7 @@ printk(KERN_INFO "my ip: %pI4\n", &ipaddress); certain condition is true. They must be used carefully to ensure there is no race condition. You declare a <type>wait_queue_head_t</type>, and then processes which want to - wait for that condition declare a <type>wait_queue_t</type> + wait for that condition declare a <type>wait_queue_entry_t</type> referring to themselves, and place that in the queue. </para> diff --git a/Documentation/RCU/00-INDEX b/Documentation/RCU/00-INDEX index 1672573b037a..f46980c060aa 100644 --- a/Documentation/RCU/00-INDEX +++ b/Documentation/RCU/00-INDEX @@ -28,8 +28,6 @@ stallwarn.txt - RCU CPU stall warnings (module parameter rcu_cpu_stall_suppress) torture.txt - RCU Torture Test Operation (CONFIG_RCU_TORTURE_TEST) -trace.txt - - CONFIG_RCU_TRACE debugfs files and formats UP.txt - RCU on Uniprocessor Systems whatisRCU.txt diff --git a/Documentation/RCU/Design/Requirements/Requirements.html b/Documentation/RCU/Design/Requirements/Requirements.html index f60adf112663..95b30fa25d56 100644 --- a/Documentation/RCU/Design/Requirements/Requirements.html +++ b/Documentation/RCU/Design/Requirements/Requirements.html @@ -559,9 +559,7 @@ The <tt>rcu_access_pointer()</tt> on line 6 is similar to For <tt>remove_gp_synchronous()</tt>, as long as all modifications to <tt>gp</tt> are carried out while holding <tt>gp_lock</tt>, the above optimizations are harmless. - However, - with <tt>CONFIG_SPARSE_RCU_POINTER=y</tt>, - <tt>sparse</tt> will complain if you + However, <tt>sparse</tt> will complain if you define <tt>gp</tt> with <tt>__rcu</tt> and then access it without using either <tt>rcu_access_pointer()</tt> or <tt>rcu_dereference()</tt>. @@ -1849,7 +1847,8 @@ mass storage, or user patience, whichever comes first. If the nesting is not visible to the compiler, as is the case with mutually recursive functions each in its own translation unit, stack overflow will result. -If the nesting takes the form of loops, either the control variable +If the nesting takes the form of loops, perhaps in the guise of tail +recursion, either the control variable will overflow or (in the Linux kernel) you will get an RCU CPU stall warning. Nevertheless, this class of RCU implementations is one of the most composable constructs in existence. @@ -1977,9 +1976,8 @@ guard against mishaps and misuse: and <tt>rcu_dereference()</tt>, perhaps (incorrectly) substituting a simple assignment. To catch this sort of error, a given RCU-protected pointer may be - tagged with <tt>__rcu</tt>, after which running sparse - with <tt>CONFIG_SPARSE_RCU_POINTER=y</tt> will complain - about simple-assignment accesses to that pointer. + tagged with <tt>__rcu</tt>, after which sparse + will complain about simple-assignment accesses to that pointer. Arnd Bergmann made me aware of this requirement, and also supplied the needed <a href="https://lwn.net/Articles/376011/">patch series</a>. @@ -2036,7 +2034,7 @@ guard against mishaps and misuse: some other synchronization mechanism, for example, reference counting. <li> In kernels built with <tt>CONFIG_RCU_TRACE=y</tt>, RCU-related - information is provided via both debugfs and event tracing. + information is provided via event tracing. <li> Open-coded use of <tt>rcu_assign_pointer()</tt> and <tt>rcu_dereference()</tt> to create typical linked data structures can be surprisingly error-prone. @@ -2519,11 +2517,7 @@ It is similarly socially unacceptable to interrupt an <tt>nohz_full</tt> CPU running in userspace. RCU must therefore track <tt>nohz_full</tt> userspace execution. -And in -<a href="https://lwn.net/Articles/558284/"><tt>CONFIG_NO_HZ_FULL_SYSIDLE=y</tt></a> -kernels, RCU must separately track idle CPUs on the one hand and -CPUs that are either idle or executing in userspace on the other. -In both cases, RCU must be able to sample state at two points in +RCU must therefore be able to sample state at two points in time, and be able to determine whether or not some other CPU spent any time idle and/or executing in userspace. @@ -2936,6 +2930,20 @@ to whether or not a CPU is online, which means that <tt>srcu_barrier()</tt> need not exclude CPU-hotplug operations. <p> +SRCU also differs from other RCU flavors in that SRCU's expedited and +non-expedited grace periods are implemented by the same mechanism. +This means that in the current SRCU implementation, expediting a +future grace period has the side effect of expediting all prior +grace periods that have not yet completed. +(But please note that this is a property of the current implementation, +not necessarily of future implementations.) +In addition, if SRCU has been idle for longer than the interval +specified by the <tt>srcutree.exp_holdoff</tt> kernel boot parameter +(25 microseconds by default), +and if a <tt>synchronize_srcu()</tt> invocation ends this idle period, +that invocation will be automatically expedited. + +<p> As of v4.12, SRCU's callbacks are maintained per-CPU, eliminating a locking bottleneck present in prior kernel versions. Although this will allow users to put much heavier stress on diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt index 877947130ebe..6beda556faf3 100644 --- a/Documentation/RCU/checklist.txt +++ b/Documentation/RCU/checklist.txt @@ -413,11 +413,11 @@ over a rather long period of time, but improvements are always welcome! read-side critical sections. It is the responsibility of the RCU update-side primitives to deal with this. -17. Use CONFIG_PROVE_RCU, CONFIG_DEBUG_OBJECTS_RCU_HEAD, and the - __rcu sparse checks (enabled by CONFIG_SPARSE_RCU_POINTER) to - validate your RCU code. These can help find problems as follows: +17. Use CONFIG_PROVE_LOCKING, CONFIG_DEBUG_OBJECTS_RCU_HEAD, and the + __rcu sparse checks to validate your RCU code. These can help + find problems as follows: - CONFIG_PROVE_RCU: check that accesses to RCU-protected data + CONFIG_PROVE_LOCKING: check that accesses to RCU-protected data structures are carried out under the proper RCU read-side critical section, while holding the right combination of locks, or whatever other conditions diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt deleted file mode 100644 index 6549012033f9..000000000000 --- a/Documentation/RCU/trace.txt +++ /dev/null @@ -1,535 +0,0 @@ -CONFIG_RCU_TRACE debugfs Files and Formats - - -The rcutree and rcutiny 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. -The following sections describe the debugfs files and formats, first -for rcutree and next for rcutiny. - - -CONFIG_TREE_RCU and CONFIG_PREEMPT_RCU debugfs Files and Formats - -These implementations of RCU provide several debugfs directories under the -top-level directory "rcu": - -rcu/rcu_bh -rcu/rcu_preempt -rcu/rcu_sched - -Each directory contains files for the corresponding flavor of RCU. -Note that rcu/rcu_preempt is only present for CONFIG_PREEMPT_RCU. -For CONFIG_TREE_RCU, the RCU flavor maps onto the RCU-sched flavor, -so that activity for both appears in rcu/rcu_sched. - -In addition, the following file appears in the top-level directory: -rcu/rcutorture. This file displays rcutorture test progress. The output -of "cat rcu/rcutorture" looks as follows: - -rcutorture test sequence: 0 (test in progress) -rcutorture update version number: 615 - -The first line shows the number of rcutorture tests that have completed -since boot. If a test is currently running, the "(test in progress)" -string will appear as shown above. The second line shows the number of -update cycles that the current test has started, or zero if there is -no test in progress. - - -Within each flavor directory (rcu/rcu_bh, rcu/rcu_sched, and possibly -also rcu/rcu_preempt) the following files will be present: - -rcudata: - Displays fields in struct rcu_data. -rcuexp: - Displays statistics for expedited grace periods. -rcugp: - Displays grace-period counters. -rcuhier: - Displays the struct rcu_node hierarchy. -rcu_pending: - Displays counts of the reasons rcu_pending() decided that RCU had - work to do. -rcuboost: - Displays RCU boosting statistics. Only present if - CONFIG_RCU_BOOST=y. - -The output of "cat rcu/rcu_preempt/rcudata" looks as follows: - - 0!c=30455 g=30456 cnq=1/0:1 dt=126535/140000000000000/0 df=2002 of=4 ql=0/0 qs=N... b=10 ci=74572 nci=0 co=1131 ca=716 - 1!c=30719 g=30720 cnq=1/0:0 dt=132007/140000000000000/0 df=1874 of=10 ql=0/0 qs=N... b=10 ci=123209 nci=0 co=685 ca=982 - 2!c=30150 g=30151 cnq=1/1:1 dt=138537/140000000000000/0 df=1707 of=8 ql=0/0 qs=N... b=10 ci=80132 nci=0 co=1328 ca=1458 - 3 c=31249 g=31250 cnq=1/1:0 dt=107255/140000000000000/0 df=1749 of=6 ql=0/450 qs=NRW. b=10 ci=151700 nci=0 co=509 ca=622 - 4!c=29502 g=29503 cnq=1/0:1 dt=83647/140000000000000/0 df=965 of=5 ql=0/0 qs=N... b=10 ci=65643 nci=0 co=1373 ca=1521 - 5 c=31201 g=31202 cnq=1/0:1 dt=70422/0/0 df=535 of=7 ql=0/0 qs=.... b=10 ci=58500 nci=0 co=764 ca=698 - 6!c=30253 g=30254 cnq=1/0:1 dt=95363/140000000000000/0 df=780 of=5 ql=0/0 qs=N... b=10 ci=100607 nci=0 co=1414 ca=1353 - 7 c=31178 g=31178 cnq=1/0:0 dt=91536/0/0 df=547 of=4 ql=0/0 qs=.... b=10 ci=109819 nci=0 co=1115 ca=969 - -This file 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, - but have been online at least once since boot. There will be - no output for CPUs that have never been online, which can be - a good thing in the surprisingly common case where NR_CPUS is - substantially larger than the number of actual CPUs. - -o "c" is the count of grace periods that this CPU believes have - completed. Offlined CPUs and CPUs in dynticks idle mode may lag - quite a ways behind, for example, CPU 4 under "rcu_sched" above, - which has been offline through 16 RCU grace periods. It is not - unusual to see offline CPUs lagging by thousands of grace periods. - Note that although the grace-period number is an unsigned long, - it is printed out as a signed long to allow more human-friendly - representation near boot time. - -o "g" is the count of grace periods that this CPU believes have - started. Again, offlined CPUs and CPUs in dynticks idle mode - may lag behind. If the "c" and "g" values are equal, this CPU - has already reported a quiescent state for the last RCU grace - period that it is aware of, otherwise, the CPU believes that it - owes RCU a quiescent state. - -o "pq" indicates that this CPU has passed through a quiescent state - for the current grace period. It is possible for "pq" to be - "1" and "c" different than "g", which indicates that although - the CPU has passed through a quiescent state, either (1) this - CPU has not yet reported that fact, (2) some other CPU has not - yet reported for this grace period, or (3) both. - -o "qp" indicates that RCU still expects a quiescent state from - this CPU. Offlined CPUs and CPUs in dyntick idle mode might - well have qp=1, which is OK: RCU is still ignoring them. - -o "dt" is the current value of the dyntick counter that is incremented - when entering or leaving idle, either due to a context switch or - due to an interrupt. This number is even if the CPU is in idle - from RCU's viewpoint and odd otherwise. The number after the - first "/" is the interrupt nesting depth when in idle state, - or a large number added to the interrupt-nesting depth when - running a non-idle task. Some architectures do not accurately - count interrupt nesting when running in non-idle kernel context, - which can result in interesting anomalies such as negative - interrupt-nesting levels. The number after the second "/" - is the NMI nesting depth. - -o "df" is the number of times that some other CPU has forced a - quiescent state on behalf of this CPU due to this CPU being in - idle state. - -o "of" is the number of times that some other CPU has forced a - quiescent state on behalf of this CPU due to this CPU being - offline. In a perfect world, this might never happen, but it - turns out that offlining and onlining a CPU can take several grace - periods, and so there is likely to be an extended period of time - when RCU believes that the CPU is online when it really is not. - Please note that erring in the other direction (RCU believing a - CPU is offline when it is really alive and kicking) is a fatal - error, so it makes sense to err conservatively. - -o "ql" is the number of RCU callbacks currently residing on - this CPU. The first number is the number of "lazy" callbacks - that are known to RCU to only be freeing memory, and the number - after the "/" is the total number of callbacks, lazy or not. - These counters count callbacks regardless of what phase of - grace-period processing that they are in (new, waiting for - grace period to start, waiting for grace period to end, ready - to invoke). - -o "qs" gives an indication of the state of the callback queue - with four characters: - - "N" Indicates that there are callbacks queued that are not - ready to be handled by the next grace period, and thus - will be handled by the grace period following the next - one. - - "R" Indicates that there are callbacks queued that are - ready to be handled by the next grace period. - - "W" Indicates that there are callbacks queued that are - waiting on the current grace period. - - "D" Indicates that there are callbacks queued that have - already been handled by a prior grace period, and are - thus waiting to be invoked. Note that callbacks in - the process of being invoked are not counted here. - Callbacks in the process of being invoked are those - that have been removed from the rcu_data structures - queues by rcu_do_batch(), but which have not yet been - invoked. - - If there are no callbacks in a given one of the above states, - the corresponding character is replaced by ".". - -o "b" is the batch limit for this CPU. If more than this number - of RCU callbacks is ready to invoke, then the remainder will - be deferred. - -o "ci" is the number of RCU callbacks that have been invoked for - this CPU. Note that ci+nci+ql is the number of callbacks that have - been registered in absence of CPU-hotplug activity. - -o "nci" is the number of RCU callbacks that have been offloaded from - this CPU. This will always be zero unless the kernel was built - with CONFIG_RCU_NOCB_CPU=y and the "rcu_nocbs=" kernel boot - parameter was specified. - -o "co" is the number of RCU callbacks that have been orphaned due to - this CPU going offline. These orphaned callbacks have been moved - to an arbitrarily chosen online CPU. - -o "ca" is the number of RCU callbacks that have been adopted by this - CPU due to other CPUs going offline. Note that ci+co-ca+ql is - the number of RCU callbacks registered on this CPU. - - -Kernels compiled with CONFIG_RCU_BOOST=y display the following from -/debug/rcu/rcu_preempt/rcudata: - - 0!c=12865 g=12866 cnq=1/0:1 dt=83113/140000000000000/0 df=288 of=11 ql=0/0 qs=N... kt=0/O ktl=944 b=10 ci=60709 nci=0 co=748 ca=871 - 1 c=14407 g=14408 cnq=1/0:0 dt=100679/140000000000000/0 df=378 of=7 ql=0/119 qs=NRW. kt=0/W ktl=9b6 b=10 ci=109740 nci=0 co=589 ca=485 - 2 c=14407 g=14408 cnq=1/0:0 dt=105486/0/0 df=90 of=9 ql=0/89 qs=NRW. kt=0/W ktl=c0c b=10 ci=83113 nci=0 co=533 ca=490 - 3 c=14407 g=14408 cnq=1/0:0 dt=107138/0/0 df=142 of=8 ql=0/188 qs=NRW. kt=0/W ktl=b96 b=10 ci=121114 nci=0 co=426 ca=290 - 4 c=14405 g=14406 cnq=1/0:1 dt=50238/0/0 df=706 of=7 ql=0/0 qs=.... kt=0/W ktl=812 b=10 ci=34929 nci=0 co=643 ca=114 - 5!c=14168 g=14169 cnq=1/0:0 dt=45465/140000000000000/0 df=161 of=11 ql=0/0 qs=N... kt=0/O ktl=b4d b=10 ci=47712 nci=0 co=677 ca=722 - 6 c=14404 g=14405 cnq=1/0:0 dt=59454/0/0 df=94 of=6 ql=0/0 qs=.... kt=0/W ktl=e57 b=10 ci=55597 nci=0 co=701 ca=811 - 7 c=14407 g=14408 cnq=1/0:1 dt=68850/0/0 df=31 of=8 ql=0/0 qs=.... kt=0/W ktl=14bd b=10 ci=77475 nci=0 co=508 ca=1042 - -This is similar to the output discussed above, but contains the following -additional fields: - -o "kt" is the per-CPU kernel-thread state. The digit preceding - the first slash is zero if there is no work pending and 1 - otherwise. The character between the first pair of slashes is - as follows: - - "S" The kernel thread is stopped, in other words, all - CPUs corresponding to this rcu_node structure are - offline. - - "R" The kernel thread is running. - - "W" The kernel thread is waiting because there is no work - for it to do. - - "O" The kernel thread is waiting because it has been - forced off of its designated CPU or because its - ->cpus_allowed mask permits it to run on other than - its designated CPU. - - "Y" The kernel thread is yielding to avoid hogging CPU. - - "?" Unknown value, indicates a bug. - - The number after the final slash is the CPU that the kthread - is actually running on. - - This field is displayed only for CONFIG_RCU_BOOST kernels. - -o "ktl" is the low-order 16 bits (in hexadecimal) of the count of - the number of times that this CPU's per-CPU kthread has gone - through its loop servicing invoke_rcu_cpu_kthread() requests. - - This field is displayed only for CONFIG_RCU_BOOST kernels. - - -The output of "cat rcu/rcu_preempt/rcuexp" looks as follows: - -s=21872 wd1=0 wd2=0 wd3=5 enq=0 sc=21872 - -These fields are as follows: - -o "s" is the sequence number, with an odd number indicating that - an expedited grace period is in progress. - -o "wd1", "wd2", and "wd3" are the number of times that an attempt - to start an expedited grace period found that someone else had - completed an expedited grace period that satisfies the attempted - request. "Our work is done." - -o "enq" is the number of quiescent states still outstanding. - -o "sc" is the number of times that the attempt to start a - new expedited grace period succeeded. - - -The output of "cat rcu/rcu_preempt/rcugp" looks as follows: - -completed=31249 gpnum=31250 age=1 max=18 - -These 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 - CPU whose "c" field matches the value of "completed" is aware - that the corresponding RCU grace period has completed. - -o "gpnum" is the number of grace periods that have started. It is - similarly comparable to the "g" field from rcu/rcudata in that - a CPU whose "g" field matches the value of "gpnum" is aware that - the corresponding RCU grace period has started. - - If these two fields are equal, 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 are above), then an RCU grace - period is in progress. - -o "age" is the number of jiffies that the current grace period - has extended for, or zero if there is no grace period currently - in effect. - -o "max" is the age in jiffies of the longest-duration grace period - thus far. - -The output of "cat rcu/rcu_preempt/rcuhier" looks as follows: - -c=14407 g=14408 s=0 jfq=2 j=c863 nfqs=12040/nfqsng=0(12040) fqlh=1051 oqlen=0/0 -3/3 ..>. 0:7 ^0 -e/e ..>. 0:3 ^0 d/d ..>. 4:7 ^1 - -The fields are as follows: - -o "c" is exactly the same as "completed" under rcu/rcu_preempt/rcugp. - -o "g" is exactly the same as "gpnum" under rcu/rcu_preempt/rcugp. - -o "s" is the current state of the force_quiescent_state() - state machine. - -o "jfq" is the number of jiffies remaining for this grace period - before force_quiescent_state() is invoked to help push things - along. Note that CPUs in idle mode throughout the grace period - will not report on their own, but rather must be check by some - other CPU via force_quiescent_state(). - -o "j" is the low-order four hex digits of the jiffies counter. - Yes, Paul did run into a number of problems that turned out to - be due to the jiffies counter no longer counting. Why do you ask? - -o "nfqs" is the number of calls to force_quiescent_state() since - boot. - -o "nfqsng" is the number of useless calls to force_quiescent_state(), - where there wasn't actually a grace period active. This can - no longer happen due to grace-period processing being pushed - into a kthread. The number in parentheses is the difference - between "nfqs" and "nfqsng", or the number of times that - force_quiescent_state() actually did some real work. - -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 Each element of the form "3/3 ..>. 0:7 ^0" represents one rcu_node - structure. Each line represents one level of the hierarchy, - from root to leaves. It is best to think of the rcu_data - structures as forming yet another level after the leaves. - Note that there might be either one, two, three, or even four - levels of rcu_node structures, depending on the relationship - between CONFIG_RCU_FANOUT, CONFIG_RCU_FANOUT_LEAF (possibly - adjusted using the rcu_fanout_leaf kernel boot parameter), and - CONFIG_NR_CPUS (possibly adjusted using the nr_cpu_ids count of - possible CPUs for the booting hardware). - - 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 has - not yet checked in for the current grace period ("e" - indicating CPUs 5, 6, and 7 in the example above). - The qsmaskinit will have one bit for each entity that is - currently expected to check in during each grace period. - The value of qsmaskinit is assigned to that of qsmask - at the beginning of each grace period. - - o The characters separated by the ">" indicate the state - of the blocked-tasks lists. A "G" preceding the ">" - indicates that at least one task blocked in an RCU - read-side critical section blocks the current grace - period, while a "E" preceding the ">" indicates that - at least one task blocked in an RCU read-side critical - section blocks the current expedited grace period. - A "T" character following the ">" indicates that at - least one task is blocked within an RCU read-side - critical section, regardless of whether any current - grace period (expedited or normal) is inconvenienced. - A "." character appears if the corresponding condition - does not hold, so that "..>." indicates that no tasks - are blocked. In contrast, "GE>T" indicates maximal - inconvenience from blocked tasks. CONFIG_TREE_RCU - builds of the kernel will always show "..>.". - - o The numbers separated by the ":" are the range of CPUs - served by this struct rcu_node. This can be helpful - in working out how the hierarchy is wired together. - - For example, the example rcu_node structure shown above - has "0:7", indicating that it covers CPUs 0 through 7. - - o The number after the "^" indicates the bit in the - next higher level rcu_node structure that this rcu_node - structure corresponds to. For example, the "d/d ..>. 4:7 - ^1" has a "1" in this position, indicating that it - corresponds to the "1" bit in the "3" shown in the - "3/3 ..>. 0:7 ^0" entry on the next level up. - - -The output of "cat rcu/rcu_sched/rcu_pending" looks as follows: - - 0!np=26111 qsp=29 rpq=5386 cbr=1 cng=570 gpc=3674 gps=577 nn=15903 ndw=0 - 1!np=28913 qsp=35 rpq=6097 cbr=1 cng=448 gpc=3700 gps=554 nn=18113 ndw=0 - 2!np=32740 qsp=37 rpq=6202 cbr=0 cng=476 gpc=4627 gps=546 nn=20889 ndw=0 - 3 np=23679 qsp=22 rpq=5044 cbr=1 cng=415 gpc=3403 gps=347 nn=14469 ndw=0 - 4!np=30714 qsp=4 rpq=5574 cbr=0 cng=528 gpc=3931 gps=639 nn=20042 ndw=0 - 5 np=28910 qsp=2 rpq=5246 cbr=0 cng=428 gpc=4105 gps=709 nn=18422 ndw=0 - 6!np=38648 qsp=5 rpq=7076 cbr=0 cng=840 gpc=4072 gps=961 nn=25699 ndw=0 - 7 np=37275 qsp=2 rpq=6873 cbr=0 cng=868 gpc=3416 gps=971 nn=25147 ndw=0 - -The fields are as follows: - -o The leading number is the CPU number, with "!" indicating - an offline CPU. - -o "np" is the number of times that __rcu_pending() has been invoked - for the corresponding flavor of RCU. - -o "qsp" is the number of times that the RCU was waiting for a - quiescent state from this CPU. - -o "rpq" is the number of times that the CPU had passed through - a quiescent state, but not yet reported it to RCU. - -o "cbr" is the number of times that this CPU had RCU callbacks - that had passed through a grace period, and were thus ready - to be invoked. - -o "cng" is the number of times that this CPU needed another - grace period while RCU was idle. - -o "gpc" is the number of times that an old grace period had - completed, but this CPU was not yet aware of it. - -o "gps" is the number of times that a new grace period had started, - but this CPU was not yet aware of it. - -o "ndw" is the number of times that a wakeup of an rcuo - callback-offload kthread had to be deferred in order to avoid - deadlock. - -o "nn" is the number of times that this CPU needed nothing. - - -The output of "cat rcu/rcuboost" looks as follows: - -0:3 tasks=.... kt=W ntb=0 neb=0 nnb=0 j=c864 bt=c894 - balk: nt=0 egt=4695 bt=0 nb=0 ny=56 nos=0 -4:7 tasks=.... kt=W ntb=0 neb=0 nnb=0 j=c864 bt=c894 - balk: nt=0 egt=6541 bt=0 nb=0 ny=126 nos=0 - -This information is output only for rcu_preempt. Each two-line entry -corresponds to a leaf rcu_node structure. The fields are as follows: - -o "n:m" is the CPU-number range for the corresponding two-line - entry. In the sample output above, the first entry covers - CPUs zero through three and the second entry covers CPUs four - through seven. - -o "tasks=TNEB" gives the state of the various segments of the - rnp->blocked_tasks list: - - "T" This indicates that there are some tasks that blocked - while running on one of the corresponding CPUs while - in an RCU read-side critical section. - - "N" This indicates that some of the blocked tasks are preventing - the current normal (non-expedited) grace period from - completing. - - "E" This indicates that some of the blocked tasks are preventing - the current expedited grace period from completing. - - "B" This indicates that some of the blocked tasks are in - need of RCU priority boosting. - - Each character is replaced with "." if the corresponding - condition does not hold. - -o "kt" is the state of the RCU priority-boosting kernel - thread associated with the corresponding rcu_node structure. - The state can be one of the following: - - "S" The kernel thread is stopped, in other words, all - CPUs corresponding to this rcu_node structure are - offline. - - "R" The kernel thread is running. - - "W" The kernel thread is waiting because there is no work - for it to do. - - "Y" The kernel thread is yielding to avoid hogging CPU. - - "?" Unknown value, indicates a bug. - -o "ntb" is the number of tasks boosted. - -o "neb" is the number of tasks boosted in order to complete an - expedited grace period. - -o "nnb" is the number of tasks boosted in order to complete a - normal (non-expedited) grace period. When boosting a task - that was blocking both an expedited and a normal grace period, - it is counted against the expedited total above. - -o "j" is the low-order 16 bits of the jiffies counter in - hexadecimal. - -o "bt" is the low-order 16 bits of the value that the jiffies - counter will have when we next start boosting, assuming that - the current grace period does not end beforehand. This is - also in hexadecimal. - -o "balk: nt" counts the number of times we didn't boost (in - other words, we balked) even though it was time to boost because - there were no blocked tasks to boost. This situation occurs - when there is one blocked task on one rcu_node structure and - none on some other rcu_node structure. - -o "egt" counts the number of times we balked because although - there were blocked tasks, none of them were blocking the - current grace period, whether expedited or otherwise. - -o "bt" counts the number of times we balked because boosting - had already been initiated for the current grace period. - -o "nb" counts the number of times we balked because there - was at least one task blocking the current non-expedited grace - period that never had blocked. If it is already running, it - just won't help to boost its priority! - -o "ny" counts the number of times we balked because it was - not yet time to start boosting. - -o "nos" counts the number of times we balked for other - reasons, e.g., the grace period ended first. - - -CONFIG_TINY_RCU debugfs Files and Formats - -These implementations of RCU provides a single debugfs file under the -top-level directory RCU, namely rcu/rcudata, which displays fields in -rcu_bh_ctrlblk and rcu_sched_ctrlblk. - -The output of "cat rcu/rcudata" is as follows: - -rcu_sched: qlen: 0 -rcu_bh: qlen: 0 - -This is split into rcu_sched and rcu_bh sections. The field is as -follows: - -o "qlen" is the number of RCU callbacks currently waiting either - for an RCU grace period or waiting to be invoked. This is the - only field present for rcu_sched and rcu_bh, due to the - short-circuiting of grace period in those two cases. diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 7737ab5d04b2..9b0b3dea6326 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2136,6 +2136,12 @@ memmap=nn[KMG]@ss[KMG] [KNL] Force usage of a specific region of memory. Region of memory to be used is from ss to ss+nn. + If @ss[KMG] is omitted, it is equivalent to mem=nn[KMG], + which limits max address to nn[KMG]. + Multiple different regions can be specified, + comma delimited. + Example: + memmap=100M@2G,100M#3G,1G!1024G memmap=nn[KMG]#ss[KMG] [KNL,ACPI] Mark specific memory as ACPI data. @@ -2148,6 +2154,9 @@ memmap=64K$0x18690000 or memmap=0x10000$0x18690000 + Some bootloaders may need an escape character before '$', + like Grub2, otherwise '$' and the following number + will be eaten. memmap=nn[KMG]!ss[KMG] [KNL,X86] Mark specific memory as protected. @@ -3238,21 +3247,17 @@ rcutree.gp_cleanup_delay= [KNL] Set the number of jiffies to delay each step of - RCU grace-period cleanup. This only has effect - when CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP is set. + RCU grace-period cleanup. rcutree.gp_init_delay= [KNL] Set the number of jiffies to delay each step of - RCU grace-period initialization. This only has - effect when CONFIG_RCU_TORTURE_TEST_SLOW_INIT - is set. + RCU grace-period initialization. rcutree.gp_preinit_delay= [KNL] Set the number of jiffies to delay each step of RCU grace-period pre-initialization, that is, the propagation of recent CPU-hotplug changes up - the rcu_node combining tree. This only has effect - when CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT is set. + the rcu_node combining tree. rcutree.rcu_fanout_exact= [KNL] Disable autobalancing of the rcu_node combining @@ -3328,6 +3333,17 @@ This wake_up() will be accompanied by a WARN_ONCE() splat and an ftrace_dump(). + rcuperf.gp_async= [KNL] + Measure performance of asynchronous + grace-period primitives such as call_rcu(). + + rcuperf.gp_async_max= [KNL] + Specify the maximum number of outstanding + callbacks per writer thread. When a writer + thread exceeds this limit, it invokes the + corresponding flavor of rcu_barrier() to allow + previously posted callbacks to drain. + rcuperf.gp_exp= [KNL] Measure performance of expedited synchronous grace-period primitives. @@ -3355,17 +3371,22 @@ rcuperf.perf_runnable= [BOOT] Start rcuperf running at boot time. + rcuperf.perf_type= [KNL] + Specify the RCU implementation to test. + rcuperf.shutdown= [KNL] Shut the system down after performance tests complete. This is useful for hands-off automated testing. - rcuperf.perf_type= [KNL] - Specify the RCU implementation to test. - rcuperf.verbose= [KNL] Enable additional printk() statements. + rcuperf.writer_holdoff= [KNL] + Write-side holdoff between grace periods, + in microseconds. The default of zero says + no holdoff. + rcutorture.cbflood_inter_holdoff= [KNL] Set holdoff time (jiffies) between successive callback-flood tests. @@ -3803,6 +3824,15 @@ spia_pedr= spia_peddr= + srcutree.counter_wrap_check [KNL] + Specifies how frequently to check for + grace-period sequence counter wrap for the + srcu_data structure's ->srcu_gp_seq_needed field. + The greater the number of bits set in this kernel + parameter, the less frequently counter wrap will + be checked for. Note that the bottom two bits + are ignored. + srcutree.exp_holdoff [KNL] Specifies how many nanoseconds must elapse since the end of the last SRCU grace period for diff --git a/Documentation/block/biodoc.txt b/Documentation/block/biodoc.txt index 01ddeaf64b0f..9490f2845f06 100644 --- a/Documentation/block/biodoc.txt +++ b/Documentation/block/biodoc.txt @@ -632,7 +632,7 @@ to i/o submission, if the bio fields are likely to be accessed after the i/o is issued (since the bio may otherwise get freed in case i/o completion happens in the meantime). -The bio_clone() routine may be used to duplicate a bio, where the clone +The bio_clone_fast() routine may be used to duplicate a bio, where the clone shares the bio_vec_list with the original bio (i.e. both point to the same bio_vec_list). This would typically be used for splitting i/o requests in lvm or md. diff --git a/Documentation/core-api/atomic_ops.rst b/Documentation/core-api/atomic_ops.rst index 55e43f1c80de..fce929144ccd 100644 --- a/Documentation/core-api/atomic_ops.rst +++ b/Documentation/core-api/atomic_ops.rst @@ -303,6 +303,11 @@ defined which accomplish this:: void smp_mb__before_atomic(void); void smp_mb__after_atomic(void); +Preceding a non-value-returning read-modify-write atomic operation with +smp_mb__before_atomic() and following it with smp_mb__after_atomic() +provides the same full ordering that is provided by value-returning +read-modify-write atomic operations. + For example, smp_mb__before_atomic() can be used like so:: obj->dead = 1; diff --git a/Documentation/dev-tools/sparse.rst b/Documentation/dev-tools/sparse.rst index ffdcc97f6f5a..78aa00a604a0 100644 --- a/Documentation/dev-tools/sparse.rst +++ b/Documentation/dev-tools/sparse.rst @@ -103,9 +103,3 @@ have already built it. The optional make variable CF can be used to pass arguments to sparse. The build system passes -Wbitwise to sparse automatically. - -Checking RCU annotations -~~~~~~~~~~~~~~~~~~~~~~~~ - -RCU annotations are not checked by default. To enable RCU annotation -checks, include -DCONFIG_SPARSE_RCU_POINTER in your CF flags. diff --git a/Documentation/devicetree/bindings/clock/sunxi-ccu.txt b/Documentation/devicetree/bindings/clock/sunxi-ccu.txt index e9c5a1d9834a..f465647a4dd2 100644 --- a/Documentation/devicetree/bindings/clock/sunxi-ccu.txt +++ b/Documentation/devicetree/bindings/clock/sunxi-ccu.txt @@ -22,7 +22,8 @@ Required properties : - #clock-cells : must contain 1 - #reset-cells : must contain 1 -For the PRCM CCUs on H3/A64, one more clock is needed: +For the PRCM CCUs on H3/A64, two more clocks are needed: +- "pll-periph": the SoC's peripheral PLL from the main CCU - "iosc": the SoC's internal frequency oscillator Example for generic CCU: @@ -39,8 +40,8 @@ Example for PRCM CCU: r_ccu: clock@01f01400 { compatible = "allwinner,sun50i-a64-r-ccu"; reg = <0x01f01400 0x100>; - clocks = <&osc24M>, <&osc32k>, <&iosc>; - clock-names = "hosc", "losc", "iosc"; + clocks = <&osc24M>, <&osc32k>, <&iosc>, <&ccu CLK_PLL_PERIPH0>; + clock-names = "hosc", "losc", "iosc", "pll-periph"; #clock-cells = <1>; #reset-cells = <1>; }; diff --git a/Documentation/devicetree/bindings/gpio/gpio-mvebu.txt b/Documentation/devicetree/bindings/gpio/gpio-mvebu.txt index 42c3bb2d53e8..01e331a5f3e7 100644 --- a/Documentation/devicetree/bindings/gpio/gpio-mvebu.txt +++ b/Documentation/devicetree/bindings/gpio/gpio-mvebu.txt @@ -41,9 +41,9 @@ Required properties: Optional properties: In order to use the GPIO lines in PWM mode, some additional optional -properties are required. Only Armada 370 and XP support these properties. +properties are required. -- compatible: Must contain "marvell,armada-370-xp-gpio" +- compatible: Must contain "marvell,armada-370-gpio" - reg: an additional register set is needed, for the GPIO Blink Counter on/off registers. @@ -71,7 +71,7 @@ Example: }; gpio1: gpio@18140 { - compatible = "marvell,armada-370-xp-gpio"; + compatible = "marvell,armada-370-gpio"; reg = <0x18140 0x40>, <0x181c8 0x08>; reg-names = "gpio", "pwm"; ngpios = <17>; diff --git a/Documentation/devicetree/bindings/mfd/stm32-timers.txt b/Documentation/devicetree/bindings/mfd/stm32-timers.txt index bbd083f5600a..1db6e0057a63 100644 --- a/Documentation/devicetree/bindings/mfd/stm32-timers.txt +++ b/Documentation/devicetree/bindings/mfd/stm32-timers.txt @@ -31,7 +31,7 @@ Example: compatible = "st,stm32-timers"; reg = <0x40010000 0x400>; clocks = <&rcc 0 160>; - clock-names = "clk_int"; + clock-names = "int"; pwm { compatible = "st,stm32-pwm"; diff --git a/Documentation/devicetree/bindings/net/dsa/b53.txt b/Documentation/devicetree/bindings/net/dsa/b53.txt index d6c6e41648d4..8ec2ca21adeb 100644 --- a/Documentation/devicetree/bindings/net/dsa/b53.txt +++ b/Documentation/devicetree/bindings/net/dsa/b53.txt @@ -34,7 +34,7 @@ Required properties: "brcm,bcm6328-switch" "brcm,bcm6368-switch" and the mandatory "brcm,bcm63xx-switch" -See Documentation/devicetree/bindings/dsa/dsa.txt for a list of additional +See Documentation/devicetree/bindings/net/dsa/dsa.txt for a list of additional required and optional properties. Examples: diff --git a/Documentation/devicetree/bindings/net/smsc911x.txt b/Documentation/devicetree/bindings/net/smsc911x.txt index 16c3a9501f5d..acfafc8e143c 100644 --- a/Documentation/devicetree/bindings/net/smsc911x.txt +++ b/Documentation/devicetree/bindings/net/smsc911x.txt @@ -27,6 +27,7 @@ Optional properties: of the device. On many systems this is wired high so the device goes out of reset at power-on, but if it is under program control, this optional GPIO can wake up in response to it. +- vdd33a-supply, vddvario-supply : 3.3V analog and IO logic power supplies Examples: diff --git a/Documentation/filesystems/autofs4.txt b/Documentation/filesystems/autofs4.txt index f10dd590f69f..8444dc3d57e8 100644 --- a/Documentation/filesystems/autofs4.txt +++ b/Documentation/filesystems/autofs4.txt @@ -316,7 +316,7 @@ For version 5, the format of the message is: struct autofs_v5_packet { int proto_version; /* Protocol version */ int type; /* Type of packet */ - autofs_wqt_t wait_queue_token; + autofs_wqt_t wait_queue_entry_token; __u32 dev; __u64 ino; __u32 uid; @@ -341,12 +341,12 @@ The pipe will be set to "packet mode" (equivalent to passing `O_DIRECT`) to _pipe2(2)_ so that a read from the pipe will return at most one packet, and any unread portion of a packet will be discarded. -The `wait_queue_token` is a unique number which can identify a +The `wait_queue_entry_token` is a unique number which can identify a particular request to be acknowledged. When a message is sent over the pipe the affected dentry is marked as either "active" or "expiring" and other accesses to it block until the message is acknowledged using one of the ioctls below and the relevant -`wait_queue_token`. +`wait_queue_entry_token`. Communicating with autofs: root directory ioctls ------------------------------------------------ @@ -358,7 +358,7 @@ capability, or must be the automount daemon. The available ioctl commands are: - **AUTOFS_IOC_READY**: a notification has been handled. The argument - to the ioctl command is the "wait_queue_token" number + to the ioctl command is the "wait_queue_entry_token" number corresponding to the notification being acknowledged. - **AUTOFS_IOC_FAIL**: similar to above, but indicates failure with the error code `ENOENT`. @@ -382,14 +382,14 @@ The available ioctl commands are: struct autofs_packet_expire_multi { int proto_version; /* Protocol version */ int type; /* Type of packet */ - autofs_wqt_t wait_queue_token; + autofs_wqt_t wait_queue_entry_token; int len; char name[NAME_MAX+1]; }; is required. This is filled in with the name of something that can be unmounted or removed. If nothing can be expired, - `errno` is set to `EAGAIN`. Even though a `wait_queue_token` + `errno` is set to `EAGAIN`. Even though a `wait_queue_entry_token` is present in the structure, no "wait queue" is established and no acknowledgment is needed. - **AUTOFS_IOC_EXPIRE_MULTI**: This is similar to diff --git a/Documentation/kernel-per-CPU-kthreads.txt b/Documentation/kernel-per-CPU-kthreads.txt index df31e30b6a02..2cb7dc5c0e0d 100644 --- a/Documentation/kernel-per-CPU-kthreads.txt +++ b/Documentation/kernel-per-CPU-kthreads.txt @@ -109,13 +109,12 @@ SCHED_SOFTIRQ: Do all of the following: on that CPU. If a thread that expects to run on the de-jittered CPU awakens, the scheduler will send an IPI that can result in a subsequent SCHED_SOFTIRQ. -2. Build with CONFIG_RCU_NOCB_CPU=y, CONFIG_RCU_NOCB_CPU_ALL=y, - CONFIG_NO_HZ_FULL=y, and, in addition, ensure that the CPU - to be de-jittered is marked as an adaptive-ticks CPU using the - "nohz_full=" boot parameter. This reduces the number of - scheduler-clock interrupts that the de-jittered CPU receives, - minimizing its chances of being selected to do the load balancing - work that runs in SCHED_SOFTIRQ context. +2. CONFIG_NO_HZ_FULL=y and ensure that the CPU to be de-jittered + is marked as an adaptive-ticks CPU using the "nohz_full=" + boot parameter. This reduces the number of scheduler-clock + interrupts that the de-jittered CPU receives, minimizing its + chances of being selected to do the load balancing work that + runs in SCHED_SOFTIRQ context. 3. To the extent possible, keep the CPU out of the kernel when it is non-idle, for example, by avoiding system calls and by forcing both kernel threads and interrupts to execute elsewhere. @@ -135,11 +134,10 @@ HRTIMER_SOFTIRQ: Do all of the following: RCU_SOFTIRQ: Do at least one of the following: 1. Offload callbacks and keep the CPU in either dyntick-idle or adaptive-ticks state by doing all of the following: - a. Build with CONFIG_RCU_NOCB_CPU=y, CONFIG_RCU_NOCB_CPU_ALL=y, - CONFIG_NO_HZ_FULL=y, and, in addition ensure that the CPU - to be de-jittered is marked as an adaptive-ticks CPU using - the "nohz_full=" boot parameter. Bind the rcuo kthreads - to housekeeping CPUs, which can tolerate OS jitter. + a. CONFIG_NO_HZ_FULL=y and ensure that the CPU to be + de-jittered is marked as an adaptive-ticks CPU using the + "nohz_full=" boot parameter. Bind the rcuo kthreads to + housekeeping CPUs, which can tolerate OS jitter. b. To the extent possible, keep the CPU out of the kernel when it is non-idle, for example, by avoiding system calls and by forcing both kernel threads and interrupts @@ -236,11 +234,10 @@ To reduce its OS jitter, do at least one of the following: is feasible only if your workload never requires RCU priority boosting, for example, if you ensure frequent idle time on all CPUs that might execute within the kernel. -3. Build with CONFIG_RCU_NOCB_CPU=y and CONFIG_RCU_NOCB_CPU_ALL=y, - which offloads all RCU callbacks to kthreads that can be moved - off of CPUs susceptible to OS jitter. This approach prevents the - rcuc/%u kthreads from having any work to do, so that they are - never awakened. +3. Build with CONFIG_RCU_NOCB_CPU=y and boot with the rcu_nocbs= + boot parameter offloading RCU callbacks from all CPUs susceptible + to OS jitter. This approach prevents the rcuc/%u kthreads from + having any work to do, so that they are never awakened. 4. Ensure that the CPU never enters the kernel, and, in particular, avoid initiating any CPU hotplug operations on this CPU. This is another way of preventing any callbacks from being queued on the diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt index 732f10ea382e..9d5e0f853f08 100644 --- a/Documentation/memory-barriers.txt +++ b/Documentation/memory-barriers.txt @@ -27,7 +27,7 @@ The purpose of this document is twofold: (2) to provide a guide as to how to use the barriers that are available. Note that an architecture can provide more than the minimum requirement -for any particular barrier, but if the architecure provides less than +for any particular barrier, but if the architecture provides less than that, that architecture is incorrect. Note also that it is possible that a barrier may be a no-op for an diff --git a/Documentation/scheduler/sched-deadline.txt b/Documentation/scheduler/sched-deadline.txt index cbc1b46cbf70..e89e36ec15a5 100644 --- a/Documentation/scheduler/sched-deadline.txt +++ b/Documentation/scheduler/sched-deadline.txt @@ -7,6 +7,8 @@ CONTENTS 0. WARNING 1. Overview 2. Scheduling algorithm + 2.1 Main algorithm + 2.2 Bandwidth reclaiming 3. Scheduling Real-Time Tasks 3.1 Definitions 3.2 Schedulability Analysis for Uniprocessor Systems @@ -44,6 +46,9 @@ CONTENTS 2. Scheduling algorithm ================== +2.1 Main algorithm +------------------ + SCHED_DEADLINE uses three parameters, named "runtime", "period", and "deadline", to schedule tasks. A SCHED_DEADLINE task should receive "runtime" microseconds of execution time every "period" microseconds, and @@ -113,6 +118,160 @@ CONTENTS remaining runtime = remaining runtime + runtime +2.2 Bandwidth reclaiming +------------------------ + + Bandwidth reclaiming for deadline tasks is based on the GRUB (Greedy + Reclamation of Unused Bandwidth) algorithm [15, 16, 17] and it is enabled + when flag SCHED_FLAG_RECLAIM is set. + + The following diagram illustrates the state names for tasks handled by GRUB: + + ------------ + (d) | Active | + ------------->| | + | | Contending | + | ------------ + | A | + ---------- | | + | | | | + | Inactive | |(b) | (a) + | | | | + ---------- | | + A | V + | ------------ + | | Active | + --------------| Non | + (c) | Contending | + ------------ + + A task can be in one of the following states: + + - ActiveContending: if it is ready for execution (or executing); + + - ActiveNonContending: if it just blocked and has not yet surpassed the 0-lag + time; + + - Inactive: if it is blocked and has surpassed the 0-lag time. + + State transitions: + + (a) When a task blocks, it does not become immediately inactive since its + bandwidth cannot be immediately reclaimed without breaking the + real-time guarantees. It therefore enters a transitional state called + ActiveNonContending. The scheduler arms the "inactive timer" to fire at + the 0-lag time, when the task's bandwidth can be reclaimed without + breaking the real-time guarantees. + + The 0-lag time for a task entering the ActiveNonContending state is + computed as + + (runtime * dl_period) + deadline - --------------------- + dl_runtime + + where runtime is the remaining runtime, while dl_runtime and dl_period + are the reservation parameters. + + (b) If the task wakes up before the inactive timer fires, the task re-enters + the ActiveContending state and the "inactive timer" is canceled. + In addition, if the task wakes up on a different runqueue, then + the task's utilization must be removed from the previous runqueue's active + utilization and must be added to the new runqueue's active utilization. + In order to avoid races between a task waking up on a runqueue while the + "inactive timer" is running on a different CPU, the "dl_non_contending" + flag is used to indicate that a task is not on a runqueue but is active + (so, the flag is set when the task blocks and is cleared when the + "inactive timer" fires or when the task wakes up). + + (c) When the "inactive timer" fires, the task enters the Inactive state and + its utilization is removed from the runqueue's active utilization. + + (d) When an inactive task wakes up, it enters the ActiveContending state and + its utilization is added to the active utilization of the runqueue where + it has been enqueued. + + For each runqueue, the algorithm GRUB keeps track of two different bandwidths: + + - Active bandwidth (running_bw): this is the sum of the bandwidths of all + tasks in active state (i.e., ActiveContending or ActiveNonContending); + + - Total bandwidth (this_bw): this is the sum of all tasks "belonging" to the + runqueue, including the tasks in Inactive state. + + + The algorithm reclaims the bandwidth of the tasks in Inactive state. + It does so by decrementing the runtime of the executing task Ti at a pace equal + to + + dq = -max{ Ui, (1 - Uinact) } dt + + where Uinact is the inactive utilization, computed as (this_bq - running_bw), + and Ui is the bandwidth of task Ti. + + + Let's now see a trivial example of two deadline tasks with runtime equal + to 4 and period equal to 8 (i.e., bandwidth equal to 0.5): + + A Task T1 + | + | | + | | + |-------- |---- + | | V + |---|---|---|---|---|---|---|---|--------->t + 0 1 2 3 4 5 6 7 8 + + + A Task T2 + | + | | + | | + | ------------------------| + | | V + |---|---|---|---|---|---|---|---|--------->t + 0 1 2 3 4 5 6 7 8 + + + A running_bw + | + 1 ----------------- ------ + | | | + 0.5- ----------------- + | | + |---|---|---|---|---|---|---|---|--------->t + 0 1 2 3 4 5 6 7 8 + + + - Time t = 0: + + Both tasks are ready for execution and therefore in ActiveContending state. + Suppose Task T1 is the first task to start execution. + Since there are no inactive tasks, its runtime is decreased as dq = -1 dt. + + - Time t = 2: + + Suppose that task T1 blocks + Task T1 therefore enters the ActiveNonContending state. Since its remaining + runtime is equal to 2, its 0-lag time is equal to t = 4. + Task T2 start execution, with runtime still decreased as dq = -1 dt since + there are no inactive tasks. + + - Time t = 4: + + This is the 0-lag time for Task T1. Since it didn't woken up in the + meantime, it enters the Inactive state. Its bandwidth is removed from + running_bw. + Task T2 continues its execution. However, its runtime is now decreased as + dq = - 0.5 dt because Uinact = 0.5. + Task T2 therefore reclaims the bandwidth unused by Task T1. + + - Time t = 8: + + Task T1 wakes up. It enters the ActiveContending state again, and the + running_bw is incremented. + + 3. Scheduling Real-Time Tasks ============================= @@ -330,6 +489,15 @@ CONTENTS 14 - J. Erickson, U. Devi and S. Baruah. Improved tardiness bounds for Global EDF. Proceedings of the 22nd Euromicro Conference on Real-Time Systems, 2010. + 15 - G. Lipari, S. Baruah, Greedy reclamation of unused bandwidth in + constant-bandwidth servers, 12th IEEE Euromicro Conference on Real-Time + Systems, 2000. + 16 - L. Abeni, J. Lelli, C. Scordino, L. Palopoli, Greedy CPU reclaiming for + SCHED DEADLINE. In Proceedings of the Real-Time Linux Workshop (RTLWS), + Dusseldorf, Germany, 2014. + 17 - L. Abeni, G. Lipari, A. Parri, Y. Sun, Multicore CPU reclaiming: parallel + or sequential?. In Proceedings of the 31st Annual ACM Symposium on Applied + Computing, 2016. 4. Bandwidth management diff --git a/Documentation/timers/NO_HZ.txt b/Documentation/timers/NO_HZ.txt index 6eaf576294f3..2dcaf9adb7a7 100644 --- a/Documentation/timers/NO_HZ.txt +++ b/Documentation/timers/NO_HZ.txt @@ -194,32 +194,9 @@ that the RCU callbacks are processed in a timely fashion. Another approach is to offload RCU callback processing to "rcuo" kthreads using the CONFIG_RCU_NOCB_CPU=y Kconfig option. The specific CPUs to -offload may be selected via several methods: - -1. One of three mutually exclusive Kconfig options specify a - build-time default for the CPUs to offload: - - a. The CONFIG_RCU_NOCB_CPU_NONE=y Kconfig option results in - no CPUs being offloaded. - - b. The CONFIG_RCU_NOCB_CPU_ZERO=y Kconfig option causes - CPU 0 to be offloaded. - - c. The CONFIG_RCU_NOCB_CPU_ALL=y Kconfig option causes all - CPUs to be offloaded. Note that the callbacks will be - offloaded to "rcuo" kthreads, and that those kthreads - will in fact run on some CPU. However, this approach - gives fine-grained control on exactly which CPUs the - callbacks run on, along with their scheduling priority - (including the default of SCHED_OTHER), and it further - allows this control to be varied dynamically at runtime. - -2. The "rcu_nocbs=" kernel boot parameter, which takes a comma-separated - list of CPUs and CPU ranges, for example, "1,3-5" selects CPUs 1, - 3, 4, and 5. The specified CPUs will be offloaded in addition to - any CPUs specified as offloaded by CONFIG_RCU_NOCB_CPU_ZERO=y or - CONFIG_RCU_NOCB_CPU_ALL=y. This means that the "rcu_nocbs=" boot - parameter has no effect for kernels built with RCU_NOCB_CPU_ALL=y. +offload may be selected using The "rcu_nocbs=" kernel boot parameter, +which takes a comma-separated list of CPUs and CPU ranges, for example, +"1,3-5" selects CPUs 1, 3, 4, and 5. The offloaded CPUs will never queue RCU callbacks, and therefore RCU never prevents offloaded CPUs from entering either dyntick-idle mode diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt index 94a987bd2bc5..fff8ff6d4893 100644 --- a/Documentation/trace/ftrace.txt +++ b/Documentation/trace/ftrace.txt @@ -1609,7 +1609,7 @@ Doing the same with chrt -r 5 and function-trace set. <idle>-0 3dN.2 14us : sched_avg_update <-__cpu_load_update <idle>-0 3dN.2 14us : _raw_spin_unlock <-cpu_load_update_nohz <idle>-0 3dN.2 14us : sub_preempt_count <-_raw_spin_unlock - <idle>-0 3dN.1 15us : calc_load_exit_idle <-tick_nohz_idle_exit + <idle>-0 3dN.1 15us : calc_load_nohz_stop <-tick_nohz_idle_exit <idle>-0 3dN.1 15us : touch_softlockup_watchdog <-tick_nohz_idle_exit <idle>-0 3dN.1 15us : hrtimer_cancel <-tick_nohz_idle_exit <idle>-0 3dN.1 15us : hrtimer_try_to_cancel <-hrtimer_cancel diff --git a/MAINTAINERS b/MAINTAINERS index 09b5ab6a8a5c..d357695ee4fe 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2322,6 +2322,15 @@ F: Documentation/devicetree/bindings/input/atmel,maxtouch.txt F: drivers/input/touchscreen/atmel_mxt_ts.c F: include/linux/platform_data/atmel_mxt_ts.h +ATOMIC INFRASTRUCTURE +M: Will Deacon <will.deacon@arm.com> +M: Peter Zijlstra <peterz@infradead.org> +R: Boqun Feng <boqun.feng@gmail.com> +L: linux-kernel@vger.kernel.org +S: Maintained +F: arch/*/include/asm/atomic*.h +F: include/*/atomic*.h + ATTO EXPRESSSAS SAS/SATA RAID SCSI DRIVER M: Bradley Grove <linuxdrivers@attotech.com> L: linux-scsi@vger.kernel.org @@ -2964,7 +2973,7 @@ F: sound/pci/oxygen/ C6X ARCHITECTURE M: Mark Salter <msalter@redhat.com> -M: Aurelien Jacquiot <a-jacquiot@ti.com> +M: Aurelien Jacquiot <jacquiot.aurelien@gmail.com> L: linux-c6x-dev@linux-c6x.org W: http://www.linux-c6x.org/wiki/index.php/Main_Page S: Maintained @@ -7555,7 +7564,7 @@ S: Maintained F: drivers/ata/sata_promise.* LIBLOCKDEP -M: Sasha Levin <sasha.levin@oracle.com> +M: Sasha Levin <alexander.levin@verizon.com> S: Maintained F: tools/lib/lockdep/ @@ -13462,6 +13471,17 @@ W: http://en.wikipedia.org/wiki/Util-linux T: git git://git.kernel.org/pub/scm/utils/util-linux/util-linux.git S: Maintained +UUID HELPERS +M: Christoph Hellwig <hch@lst.de> +R: Andy Shevchenko <andriy.shevchenko@linux.intel.com> +L: linux-kernel@vger.kernel.org +T: git git://git.infradead.org/users/hch/uuid.git +F: lib/uuid.c +F: lib/test_uuid.c +F: include/linux/uuid.h +F: include/uapi/linux/uuid.h +S: Maintained + UVESAFB DRIVER M: Michal Januszewski <spock@gentoo.org> L: linux-fbdev@vger.kernel.org @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 12 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = NAME = Fearless Coyote # *DOCUMENTATION* @@ -1437,7 +1437,7 @@ help: @echo ' make V=0|1 [targets] 0 => quiet build (default), 1 => verbose build' @echo ' make V=2 [targets] 2 => give reason for rebuild of target' @echo ' make O=dir [targets] Locate all output files in "dir", including .config' - @echo ' make C=1 [targets] Check all c source with $$CHECK (sparse by default)' + @echo ' make C=1 [targets] Check re-compiled c source with $$CHECK (sparse by default)' @echo ' make C=2 [targets] Force check of all c source with $$CHECK' @echo ' make RECORDMCOUNT_WARN=1 [targets] Warn about ignored mcount sections' @echo ' make W=n [targets] Enable extra gcc checks, n=1,2,3 where' diff --git a/arch/Kconfig b/arch/Kconfig index 6c00e5b00f8b..f76b214cf7ad 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -867,4 +867,13 @@ config STRICT_MODULE_RWX config ARCH_WANT_RELAX_ORDER bool +config REFCOUNT_FULL + bool "Perform full reference count validation at the expense of speed" + help + Enabling this switches the refcounting infrastructure from a fast + unchecked atomic_t implementation to a fully state checked + implementation, which can be (slightly) slower but provides protections + against various use-after-free conditions that can be used in + security flaw exploits. + source "kernel/gcov/Kconfig" diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h index 6e1242da0159..4104a0839214 100644 --- a/arch/arc/include/asm/processor.h +++ b/arch/arc/include/asm/processor.h @@ -86,8 +86,6 @@ struct task_struct; #define TSK_K_BLINK(tsk) TSK_K_REG(tsk, 4) #define TSK_K_FP(tsk) TSK_K_REG(tsk, 0) -#define thread_saved_pc(tsk) TSK_K_BLINK(tsk) - extern void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long usp); diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 1c7e165b0a93..6281c3e5a673 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1416,6 +1416,7 @@ choice config VMSPLIT_3G bool "3G/1G user/kernel split" config VMSPLIT_3G_OPT + depends on !ARM_LPAE bool "3G/1G user/kernel split (for full 1G low memory)" config VMSPLIT_2G bool "2G/2G user/kernel split" @@ -1637,7 +1638,7 @@ config ARCH_SELECT_MEMORY_MODEL config HAVE_ARCH_PFN_VALID def_bool ARCH_HAS_HOLES_MEMORYMODEL || !SPARSEMEM -config HAVE_GENERIC_RCU_GUP +config HAVE_GENERIC_GUP def_bool y depends on ARM_LPAE @@ -2061,6 +2062,23 @@ config EFI is only useful for kernels that may run on systems that have UEFI firmware. +config DMI + bool "Enable support for SMBIOS (DMI) tables" + depends on EFI + default y + help + This enables SMBIOS/DMI feature for systems. + + This option is only useful on systems that have UEFI firmware. + However, even with this option, the resultant kernel should + continue to boot on existing non-UEFI platforms. + + NOTE: This does *NOT* enable or encourage the use of DMI quirks, + i.e., the the practice of identifying the platform via DMI to + decide whether certain workarounds for buggy hardware and/or + firmware need to be enabled. This would require the DMI subsystem + to be enabled much earlier than we do on ARM, which is non-trivial. + endmenu menu "CPU Power Management" diff --git a/arch/arm/boot/compressed/efi-header.S b/arch/arm/boot/compressed/efi-header.S index 3f7d1b74c5e0..a17ca8d78656 100644 --- a/arch/arm/boot/compressed/efi-header.S +++ b/arch/arm/boot/compressed/efi-header.S @@ -17,7 +17,8 @@ @ there. .inst 'M' | ('Z' << 8) | (0x1310 << 16) @ tstne r0, #0x4d000 #else - W(mov) r0, r0 + AR_CLASS( mov r0, r0 ) + M_CLASS( nop.w ) #endif .endm diff --git a/arch/arm/include/asm/dmi.h b/arch/arm/include/asm/dmi.h new file mode 100644 index 000000000000..df2d2ff06f5b --- /dev/null +++ b/arch/arm/include/asm/dmi.h @@ -0,0 +1,19 @@ +/* + * 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 __ASM_DMI_H +#define __ASM_DMI_H + +#include <linux/io.h> +#include <linux/slab.h> + +#define dmi_early_remap(x, l) memremap(x, l, MEMREMAP_WB) +#define dmi_early_unmap(x, l) memunmap(x) +#define dmi_remap(x, l) memremap(x, l, MEMREMAP_WB) +#define dmi_unmap(x) memunmap(x) +#define dmi_alloc(l) kzalloc(l, GFP_KERNEL) + +#endif diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 32e1a9513dc7..4e80bf7420d4 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -315,7 +315,7 @@ static void __init cacheid_init(void) if (arch >= CPU_ARCH_ARMv6) { unsigned int cachetype = read_cpuid_cachetype(); - if ((arch == CPU_ARCH_ARMv7M) && !cachetype) { + if ((arch == CPU_ARCH_ARMv7M) && !(cachetype & 0xf000f)) { cacheid = 0; } else if ((cachetype & (7 << 29)) == 4 << 29) { /* ARMv7 register format */ diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 572a8df1b766..c9a0a5299827 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -555,8 +555,7 @@ static DEFINE_RAW_SPINLOCK(stop_lock); */ static void ipi_cpu_stop(unsigned int cpu) { - if (system_state == SYSTEM_BOOTING || - system_state == SYSTEM_RUNNING) { + if (system_state <= SYSTEM_RUNNING) { raw_spin_lock(&stop_lock); pr_crit("CPU%u: stopping\n", cpu); dump_stack(); diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 31af3cb59a60..e46a6a446cdd 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -1218,15 +1218,15 @@ void __init adjust_lowmem_bounds(void) high_memory = __va(arm_lowmem_limit - 1) + 1; + if (!memblock_limit) + memblock_limit = arm_lowmem_limit; + /* * Round the memblock limit down to a pmd size. This * helps to ensure that we will allocate memory from the * last full pmd, which should be mapped. */ - if (memblock_limit) - memblock_limit = round_down(memblock_limit, PMD_SIZE); - if (!memblock_limit) - memblock_limit = arm_lowmem_limit; + memblock_limit = round_down(memblock_limit, PMD_SIZE); if (!IS_ENABLED(CONFIG_HIGHMEM) || cache_is_vipt_aliasing()) { if (memblock_end_of_DRAM() > arm_lowmem_limit) { diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index b2024db225a9..95c7ed392003 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -205,7 +205,7 @@ config GENERIC_CALIBRATE_DELAY config ZONE_DMA def_bool y -config HAVE_GENERIC_RCU_GUP +config HAVE_GENERIC_GUP def_bool y config ARCH_DMA_ADDR_T_64BIT diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index 5d17f377d905..82cd07592519 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -11,7 +11,6 @@ * */ -#include <linux/dmi.h> #include <linux/efi.h> #include <linux/init.h> @@ -117,20 +116,6 @@ int __init efi_set_mapping_permissions(struct mm_struct *mm, set_permissions, md); } -static int __init arm64_dmi_init(void) -{ - /* - * On arm64, DMI depends on UEFI, and dmi_scan_machine() needs to - * be called early because dmi_id_init(), which is an arch_initcall - * itself, depends on dmi_scan_machine() having been called already. - */ - dmi_scan_machine(); - if (dmi_available) - dmi_set_dump_stack_arch_desc(); - return 0; -} -core_initcall(arm64_dmi_init); - /* * UpdateCapsule() depends on the system being shutdown via * ResetSystem(). diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 6e0e16a3a7d4..321119881abf 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -961,8 +961,7 @@ void smp_send_stop(void) cpumask_copy(&mask, cpu_online_mask); cpumask_clear_cpu(smp_processor_id(), &mask); - if (system_state == SYSTEM_BOOTING || - system_state == SYSTEM_RUNNING) + if (system_state <= SYSTEM_RUNNING) pr_crit("SMP: stopping secondary CPUs\n"); smp_cross_call(&mask, IPI_CPU_STOP); } diff --git a/arch/blackfin/include/asm/processor.h b/arch/blackfin/include/asm/processor.h index 85d4af97c986..dbdbb8a558df 100644 --- a/arch/blackfin/include/asm/processor.h +++ b/arch/blackfin/include/asm/processor.h @@ -75,11 +75,6 @@ static inline void release_thread(struct task_struct *dead_task) { } -/* - * Return saved PC of a blocked thread. - */ -#define thread_saved_pc(tsk) (tsk->thread.pc) - unsigned long get_wchan(struct task_struct *p); #define KSTK_EIP(tsk) \ diff --git a/arch/c6x/include/asm/processor.h b/arch/c6x/include/asm/processor.h index b9eb3da7f278..7c87b5be53b5 100644 --- a/arch/c6x/include/asm/processor.h +++ b/arch/c6x/include/asm/processor.h @@ -96,11 +96,6 @@ static inline void release_thread(struct task_struct *dead_task) #define release_segments(mm) do { } while (0) /* - * saved PC of a blocked thread. - */ -#define thread_saved_pc(tsk) (task_pt_regs(tsk)->pc) - -/* * saved kernel SP and DP of a blocked thread. */ #ifdef _BIG_ENDIAN diff --git a/arch/cris/arch-v10/kernel/process.c b/arch/cris/arch-v10/kernel/process.c index e299d30105b5..a2cdb1521aca 100644 --- a/arch/cris/arch-v10/kernel/process.c +++ b/arch/cris/arch-v10/kernel/process.c @@ -69,14 +69,6 @@ void hard_reset_now (void) while(1) /* waiting for RETRIBUTION! */ ; } -/* - * Return saved PC of a blocked thread. - */ -unsigned long thread_saved_pc(struct task_struct *t) -{ - return task_pt_regs(t)->irp; -} - /* setup the child's kernel stack with a pt_regs and switch_stack on it. * it will be un-nested during _resume and _ret_from_sys_call when the * new thread is scheduled. diff --git a/arch/cris/arch-v32/kernel/process.c b/arch/cris/arch-v32/kernel/process.c index c530a8fa87ce..fe87b383fbf3 100644 --- a/arch/cris/arch-v32/kernel/process.c +++ b/arch/cris/arch-v32/kernel/process.c @@ -85,14 +85,6 @@ hard_reset_now(void) } /* - * Return saved PC of a blocked thread. - */ -unsigned long thread_saved_pc(struct task_struct *t) -{ - return task_pt_regs(t)->erp; -} - -/* * Setup the child's kernel stack with a pt_regs and call switch_stack() on it. * It will be unnested during _resume and _ret_from_sys_call when the new thread * is scheduled. diff --git a/arch/cris/include/asm/processor.h b/arch/cris/include/asm/processor.h index 15b815df29c1..bc2729e4b2c9 100644 --- a/arch/cris/include/asm/processor.h +++ b/arch/cris/include/asm/processor.h @@ -52,8 +52,6 @@ unsigned long get_wchan(struct task_struct *p); #define KSTK_ESP(tsk) ((tsk) == current ? rdusp() : (tsk)->thread.usp) -extern unsigned long thread_saved_pc(struct task_struct *tsk); - /* Free all resources held by a thread. */ static inline void release_thread(struct task_struct *dead_task) { diff --git a/arch/frv/include/asm/processor.h b/arch/frv/include/asm/processor.h index ddaeb9cc9143..e4d08d74ed9f 100644 --- a/arch/frv/include/asm/processor.h +++ b/arch/frv/include/asm/processor.h @@ -96,11 +96,6 @@ extern asmlinkage void *restore_user_regs(const struct user_context *target, ... #define release_segments(mm) do { } while (0) #define forget_segments() do { } while (0) -/* - * Return saved PC of a blocked thread. - */ -extern unsigned long thread_saved_pc(struct task_struct *tsk); - unsigned long get_wchan(struct task_struct *p); #define KSTK_EIP(tsk) ((tsk)->thread.frame0->pc) diff --git a/arch/frv/kernel/process.c b/arch/frv/kernel/process.c index 5a4c92abc99e..a957b374e3a6 100644 --- a/arch/frv/kernel/process.c +++ b/arch/frv/kernel/process.c @@ -198,15 +198,6 @@ unsigned long get_wchan(struct task_struct *p) return 0; } -unsigned long thread_saved_pc(struct task_struct *tsk) -{ - /* Check whether the thread is blocked in resume() */ - if (in_sched_functions(tsk->thread.pc)) - return ((unsigned long *)tsk->thread.fp)[2]; - else - return tsk->thread.pc; -} - int elf_check_arch(const struct elf32_hdr *hdr) { unsigned long hsr0 = __get_HSR(0); diff --git a/arch/h8300/include/asm/processor.h b/arch/h8300/include/asm/processor.h index 65132d7ae9e5..afa53147e66a 100644 --- a/arch/h8300/include/asm/processor.h +++ b/arch/h8300/include/asm/processor.h @@ -110,10 +110,6 @@ static inline void release_thread(struct task_struct *dead_task) { } -/* - * Return saved PC of a blocked thread. - */ -unsigned long thread_saved_pc(struct task_struct *tsk); unsigned long get_wchan(struct task_struct *p); #define KSTK_EIP(tsk) \ diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c index 0f5db5bb561b..d1ddcabbbe83 100644 --- a/arch/h8300/kernel/process.c +++ b/arch/h8300/kernel/process.c @@ -129,11 +129,6 @@ int copy_thread(unsigned long clone_flags, return 0; } -unsigned long thread_saved_pc(struct task_struct *tsk) -{ - return ((struct pt_regs *)tsk->thread.esp0)->pc; -} - unsigned long get_wchan(struct task_struct *p) { unsigned long fp, pc; diff --git a/arch/hexagon/include/asm/processor.h b/arch/hexagon/include/asm/processor.h index 45a825402f63..ce67940860a5 100644 --- a/arch/hexagon/include/asm/processor.h +++ b/arch/hexagon/include/asm/processor.h @@ -33,9 +33,6 @@ /* task_struct, defined elsewhere, is the "process descriptor" */ struct task_struct; -/* this is defined in arch/process.c */ -extern unsigned long thread_saved_pc(struct task_struct *tsk); - extern void start_thread(struct pt_regs *, unsigned long, unsigned long); /* diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c index de715bab7956..656050c2e6a0 100644 --- a/arch/hexagon/kernel/process.c +++ b/arch/hexagon/kernel/process.c @@ -61,14 +61,6 @@ void arch_cpu_idle(void) } /* - * Return saved PC of a blocked thread - */ -unsigned long thread_saved_pc(struct task_struct *tsk) -{ - return 0; -} - -/* * Copy architecture-specific thread state */ int copy_thread(unsigned long clone_flags, unsigned long usp, diff --git a/arch/ia64/include/asm/processor.h b/arch/ia64/include/asm/processor.h index 26a63d69c599..ab982f07ea68 100644 --- a/arch/ia64/include/asm/processor.h +++ b/arch/ia64/include/asm/processor.h @@ -602,23 +602,6 @@ ia64_set_unat (__u64 *unat, void *spill_addr, unsigned long nat) } /* - * Return saved PC of a blocked thread. - * Note that the only way T can block is through a call to schedule() -> switch_to(). - */ -static inline unsigned long -thread_saved_pc (struct task_struct *t) -{ - struct unw_frame_info info; - unsigned long ip; - - unw_init_from_blocked_task(&info, t); - if (unw_unwind(&info) < 0) - return 0; - unw_get_ip(&info, &ip); - return ip; -} - -/* * Get the current instruction/program counter value. */ #define current_text_addr() \ diff --git a/arch/m32r/include/asm/processor.h b/arch/m32r/include/asm/processor.h index 5767367550c6..657874eeeccc 100644 --- a/arch/m32r/include/asm/processor.h +++ b/arch/m32r/include/asm/processor.h @@ -122,8 +122,6 @@ extern void release_thread(struct task_struct *); extern void copy_segments(struct task_struct *p, struct mm_struct * mm); extern void release_segments(struct mm_struct * mm); -extern unsigned long thread_saved_pc(struct task_struct *); - /* Copy and release all segment info associated with a VM */ #define copy_segments(p, mm) do { } while (0) #define release_segments(mm) do { } while (0) diff --git a/arch/m32r/kernel/process.c b/arch/m32r/kernel/process.c index d8ffcfec599c..8cd7e03f4370 100644 --- a/arch/m32r/kernel/process.c +++ b/arch/m32r/kernel/process.c @@ -39,14 +39,6 @@ #include <linux/err.h> -/* - * Return saved PC of a blocked thread. - */ -unsigned long thread_saved_pc(struct task_struct *tsk) -{ - return tsk->thread.lr; -} - void (*pm_power_off)(void) = NULL; EXPORT_SYMBOL(pm_power_off); diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig index 531cb9eb3319..ddff1164aff0 100644 --- a/arch/m68k/configs/amiga_defconfig +++ b/arch/m68k/configs/amiga_defconfig @@ -26,6 +26,8 @@ CONFIG_SUN_PARTITION=y CONFIG_SYSV68_PARTITION=y CONFIG_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_DEADLINE=m +CONFIG_MQ_IOSCHED_KYBER=m +CONFIG_IOSCHED_BFQ=m CONFIG_KEXEC=y CONFIG_BOOTINFO_PROC=y CONFIG_M68020=y @@ -349,7 +351,6 @@ CONFIG_SCSI_A4000T=y CONFIG_SCSI_ZORRO7XX=y CONFIG_MD=y CONFIG_MD_LINEAR=m -CONFIG_MD_RAID0=m CONFIG_BLK_DEV_DM=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m @@ -361,6 +362,7 @@ CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_UEVENT=y CONFIG_DM_LOG_WRITES=m +CONFIG_DM_INTEGRITY=m CONFIG_TARGET_CORE=m CONFIG_TCM_IBLOCK=m CONFIG_TCM_FILEIO=m @@ -414,6 +416,7 @@ CONFIG_ZORRO8390=y # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -572,6 +575,8 @@ CONFIG_DLM=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_TEST_LIST_SORT=m +CONFIG_TEST_SORT=m CONFIG_ATOMIC64_SELFTEST=m CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m @@ -590,6 +595,7 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m +CONFIG_HARDENED_USERCOPY=y CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig index ca91d39555da..17384dc959a5 100644 --- a/arch/m68k/configs/apollo_defconfig +++ b/arch/m68k/configs/apollo_defconfig @@ -27,6 +27,8 @@ CONFIG_SUN_PARTITION=y CONFIG_SYSV68_PARTITION=y CONFIG_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_DEADLINE=m +CONFIG_MQ_IOSCHED_KYBER=m +CONFIG_IOSCHED_BFQ=m CONFIG_KEXEC=y CONFIG_BOOTINFO_PROC=y CONFIG_M68020=y @@ -331,7 +333,6 @@ CONFIG_ISCSI_TCP=m CONFIG_ISCSI_BOOT_SYSFS=m CONFIG_MD=y CONFIG_MD_LINEAR=m -CONFIG_MD_RAID0=m CONFIG_BLK_DEV_DM=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m @@ -343,6 +344,7 @@ CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_UEVENT=y CONFIG_DM_LOG_WRITES=m +CONFIG_DM_INTEGRITY=m CONFIG_TARGET_CORE=m CONFIG_TCM_IBLOCK=m CONFIG_TCM_FILEIO=m @@ -388,6 +390,7 @@ CONFIG_VETH=m # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -531,6 +534,8 @@ CONFIG_DLM=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_TEST_LIST_SORT=m +CONFIG_TEST_SORT=m CONFIG_ATOMIC64_SELFTEST=m CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m @@ -549,6 +554,7 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m +CONFIG_HARDENED_USERCOPY=y CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig index 23a3d8a691e2..53a641d62f85 100644 --- a/arch/m68k/configs/atari_defconfig +++ b/arch/m68k/configs/atari_defconfig @@ -26,6 +26,8 @@ CONFIG_SUN_PARTITION=y CONFIG_SYSV68_PARTITION=y CONFIG_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_DEADLINE=m +CONFIG_MQ_IOSCHED_KYBER=m +CONFIG_IOSCHED_BFQ=m CONFIG_KEXEC=y CONFIG_BOOTINFO_PROC=y CONFIG_M68020=y @@ -340,7 +342,6 @@ CONFIG_ISCSI_BOOT_SYSFS=m CONFIG_ATARI_SCSI=y CONFIG_MD=y CONFIG_MD_LINEAR=m -CONFIG_MD_RAID0=m CONFIG_BLK_DEV_DM=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m @@ -352,6 +353,7 @@ CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_UEVENT=y CONFIG_DM_LOG_WRITES=m +CONFIG_DM_INTEGRITY=m CONFIG_TARGET_CORE=m CONFIG_TCM_IBLOCK=m CONFIG_TCM_FILEIO=m @@ -399,6 +401,7 @@ CONFIG_SMC91X=y # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -552,6 +555,8 @@ CONFIG_DLM=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_TEST_LIST_SORT=m +CONFIG_TEST_SORT=m CONFIG_ATOMIC64_SELFTEST=m CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m @@ -570,6 +575,7 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m +CONFIG_HARDENED_USERCOPY=y CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig index 95deb95140fe..3925ae3a5eb3 100644 --- a/arch/m68k/configs/bvme6000_defconfig +++ b/arch/m68k/configs/bvme6000_defconfig @@ -26,6 +26,8 @@ CONFIG_SUN_PARTITION=y # CONFIG_EFI_PARTITION is not set CONFIG_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_DEADLINE=m +CONFIG_MQ_IOSCHED_KYBER=m +CONFIG_IOSCHED_BFQ=m CONFIG_KEXEC=y CONFIG_BOOTINFO_PROC=y CONFIG_M68040=y @@ -330,7 +332,6 @@ CONFIG_ISCSI_BOOT_SYSFS=m CONFIG_BVME6000_SCSI=y CONFIG_MD=y CONFIG_MD_LINEAR=m -CONFIG_MD_RAID0=m CONFIG_BLK_DEV_DM=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m @@ -342,6 +343,7 @@ CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_UEVENT=y CONFIG_DM_LOG_WRITES=m +CONFIG_DM_INTEGRITY=m CONFIG_TARGET_CORE=m CONFIG_TCM_IBLOCK=m CONFIG_TCM_FILEIO=m @@ -387,6 +389,7 @@ CONFIG_BVME6000_NET=y # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -523,6 +526,8 @@ CONFIG_DLM=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_TEST_LIST_SORT=m +CONFIG_TEST_SORT=m CONFIG_ATOMIC64_SELFTEST=m CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m @@ -541,6 +546,7 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m +CONFIG_HARDENED_USERCOPY=y CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig index afae6958db2d..f4a134b390b4 100644 --- a/arch/m68k/configs/hp300_defconfig +++ b/arch/m68k/configs/hp300_defconfig @@ -27,6 +27,8 @@ CONFIG_SUN_PARTITION=y CONFIG_SYSV68_PARTITION=y CONFIG_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_DEADLINE=m +CONFIG_MQ_IOSCHED_KYBER=m +CONFIG_IOSCHED_BFQ=m CONFIG_KEXEC=y CONFIG_BOOTINFO_PROC=y CONFIG_M68020=y @@ -331,7 +333,6 @@ CONFIG_ISCSI_TCP=m CONFIG_ISCSI_BOOT_SYSFS=m CONFIG_MD=y CONFIG_MD_LINEAR=m -CONFIG_MD_RAID0=m CONFIG_BLK_DEV_DM=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m @@ -343,6 +344,7 @@ CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_UEVENT=y CONFIG_DM_LOG_WRITES=m +CONFIG_DM_INTEGRITY=m CONFIG_TARGET_CORE=m CONFIG_TCM_IBLOCK=m CONFIG_TCM_FILEIO=m @@ -389,6 +391,7 @@ CONFIG_HPLANCE=y # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -533,6 +536,8 @@ CONFIG_DLM=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_TEST_LIST_SORT=m +CONFIG_TEST_SORT=m CONFIG_ATOMIC64_SELFTEST=m CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m @@ -551,6 +556,7 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m +CONFIG_HARDENED_USERCOPY=y CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig index b010734729a7..9ed0cef632b7 100644 --- a/arch/m68k/configs/mac_defconfig +++ b/arch/m68k/configs/mac_defconfig @@ -26,6 +26,8 @@ CONFIG_SUN_PARTITION=y CONFIG_SYSV68_PARTITION=y CONFIG_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_DEADLINE=m +CONFIG_MQ_IOSCHED_KYBER=m +CONFIG_IOSCHED_BFQ=m CONFIG_KEXEC=y CONFIG_BOOTINFO_PROC=y CONFIG_M68020=y @@ -340,7 +342,6 @@ CONFIG_MAC_SCSI=y CONFIG_SCSI_MAC_ESP=y CONFIG_MD=y CONFIG_MD_LINEAR=m -CONFIG_MD_RAID0=m CONFIG_BLK_DEV_DM=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m @@ -352,6 +353,7 @@ CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_UEVENT=y CONFIG_DM_LOG_WRITES=m +CONFIG_DM_INTEGRITY=m CONFIG_TARGET_CORE=m CONFIG_TCM_IBLOCK=m CONFIG_TCM_FILEIO=m @@ -408,6 +410,7 @@ CONFIG_MAC8390=y # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -555,6 +558,8 @@ CONFIG_DLM=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_TEST_LIST_SORT=m +CONFIG_TEST_SORT=m CONFIG_ATOMIC64_SELFTEST=m CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m @@ -573,6 +578,7 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m +CONFIG_HARDENED_USERCOPY=y CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig index 0e414549b235..efed0d48fd53 100644 --- a/arch/m68k/configs/multi_defconfig +++ b/arch/m68k/configs/multi_defconfig @@ -22,6 +22,8 @@ CONFIG_UNIXWARE_DISKLABEL=y # CONFIG_EFI_PARTITION is not set CONFIG_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_DEADLINE=m +CONFIG_MQ_IOSCHED_KYBER=m +CONFIG_IOSCHED_BFQ=m CONFIG_KEXEC=y CONFIG_BOOTINFO_PROC=y CONFIG_M68020=y @@ -373,7 +375,6 @@ CONFIG_BVME6000_SCSI=y CONFIG_SUN3X_ESP=y CONFIG_MD=y CONFIG_MD_LINEAR=m -CONFIG_MD_RAID0=m CONFIG_BLK_DEV_DM=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m @@ -385,6 +386,7 @@ CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_UEVENT=y CONFIG_DM_LOG_WRITES=m +CONFIG_DM_INTEGRITY=m CONFIG_TARGET_CORE=m CONFIG_TCM_IBLOCK=m CONFIG_TCM_FILEIO=m @@ -454,6 +456,7 @@ CONFIG_SMC91X=y # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PLIP=m CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m @@ -635,6 +638,8 @@ CONFIG_DLM=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_TEST_LIST_SORT=m +CONFIG_TEST_SORT=m CONFIG_ATOMIC64_SELFTEST=m CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m @@ -653,6 +658,7 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m +CONFIG_HARDENED_USERCOPY=y CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig index b2e687a0ec3d..9040457c7f9c 100644 --- a/arch/m68k/configs/mvme147_defconfig +++ b/arch/m68k/configs/mvme147_defconfig @@ -26,6 +26,8 @@ CONFIG_SUN_PARTITION=y # CONFIG_EFI_PARTITION is not set CONFIG_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_DEADLINE=m +CONFIG_MQ_IOSCHED_KYBER=m +CONFIG_IOSCHED_BFQ=m CONFIG_KEXEC=y CONFIG_BOOTINFO_PROC=y CONFIG_M68030=y @@ -329,7 +331,6 @@ CONFIG_ISCSI_BOOT_SYSFS=m CONFIG_MVME147_SCSI=y CONFIG_MD=y CONFIG_MD_LINEAR=m -CONFIG_MD_RAID0=m CONFIG_BLK_DEV_DM=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m @@ -341,6 +342,7 @@ CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_UEVENT=y CONFIG_DM_LOG_WRITES=m +CONFIG_DM_INTEGRITY=m CONFIG_TARGET_CORE=m CONFIG_TCM_IBLOCK=m CONFIG_TCM_FILEIO=m @@ -387,6 +389,7 @@ CONFIG_MVME147_NET=y # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -523,6 +526,8 @@ CONFIG_DLM=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_TEST_LIST_SORT=m +CONFIG_TEST_SORT=m CONFIG_ATOMIC64_SELFTEST=m CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m @@ -541,6 +546,7 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m +CONFIG_HARDENED_USERCOPY=y CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig index cbd8ee24d1bc..8b17f00e0484 100644 --- a/arch/m68k/configs/mvme16x_defconfig +++ b/arch/m68k/configs/mvme16x_defconfig @@ -26,6 +26,8 @@ CONFIG_SUN_PARTITION=y # CONFIG_EFI_PARTITION is not set CONFIG_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_DEADLINE=m +CONFIG_MQ_IOSCHED_KYBER=m +CONFIG_IOSCHED_BFQ=m CONFIG_KEXEC=y CONFIG_BOOTINFO_PROC=y CONFIG_M68040=y @@ -330,7 +332,6 @@ CONFIG_ISCSI_BOOT_SYSFS=m CONFIG_MVME16x_SCSI=y CONFIG_MD=y CONFIG_MD_LINEAR=m -CONFIG_MD_RAID0=m CONFIG_BLK_DEV_DM=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m @@ -342,6 +343,7 @@ CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_UEVENT=y CONFIG_DM_LOG_WRITES=m +CONFIG_DM_INTEGRITY=m CONFIG_TARGET_CORE=m CONFIG_TCM_IBLOCK=m CONFIG_TCM_FILEIO=m @@ -387,6 +389,7 @@ CONFIG_MVME16x_NET=y # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -523,6 +526,8 @@ CONFIG_DLM=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_TEST_LIST_SORT=m +CONFIG_TEST_SORT=m CONFIG_ATOMIC64_SELFTEST=m CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m @@ -541,6 +546,7 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m +CONFIG_HARDENED_USERCOPY=y CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig index 1e82cc944339..5f3718c62c85 100644 --- a/arch/m68k/configs/q40_defconfig +++ b/arch/m68k/configs/q40_defconfig @@ -27,6 +27,8 @@ CONFIG_SUN_PARTITION=y CONFIG_SYSV68_PARTITION=y CONFIG_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_DEADLINE=m +CONFIG_MQ_IOSCHED_KYBER=m +CONFIG_IOSCHED_BFQ=m CONFIG_KEXEC=y CONFIG_BOOTINFO_PROC=y CONFIG_M68040=y @@ -336,7 +338,6 @@ CONFIG_ISCSI_TCP=m CONFIG_ISCSI_BOOT_SYSFS=m CONFIG_MD=y CONFIG_MD_LINEAR=m -CONFIG_MD_RAID0=m CONFIG_BLK_DEV_DM=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m @@ -348,6 +349,7 @@ CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_UEVENT=y CONFIG_DM_LOG_WRITES=m +CONFIG_DM_INTEGRITY=m CONFIG_TARGET_CORE=m CONFIG_TCM_IBLOCK=m CONFIG_TCM_FILEIO=m @@ -398,6 +400,7 @@ CONFIG_NE2000=y # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PLIP=m CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m @@ -546,6 +549,8 @@ CONFIG_DLM=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_TEST_LIST_SORT=m +CONFIG_TEST_SORT=m CONFIG_ATOMIC64_SELFTEST=m CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m @@ -564,6 +569,7 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m +CONFIG_HARDENED_USERCOPY=y CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig index f9e77f57a972..8c979a68fca5 100644 --- a/arch/m68k/configs/sun3_defconfig +++ b/arch/m68k/configs/sun3_defconfig @@ -26,6 +26,8 @@ CONFIG_UNIXWARE_DISKLABEL=y CONFIG_SYSV68_PARTITION=y CONFIG_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_DEADLINE=m +CONFIG_MQ_IOSCHED_KYBER=m +CONFIG_IOSCHED_BFQ=m CONFIG_KEXEC=y CONFIG_BOOTINFO_PROC=y CONFIG_SUN3=y @@ -327,7 +329,6 @@ CONFIG_ISCSI_BOOT_SYSFS=m CONFIG_SUN3_SCSI=y CONFIG_MD=y CONFIG_MD_LINEAR=m -CONFIG_MD_RAID0=m CONFIG_BLK_DEV_DM=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m @@ -339,6 +340,7 @@ CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_UEVENT=y CONFIG_DM_LOG_WRITES=m +CONFIG_DM_INTEGRITY=m CONFIG_TARGET_CORE=m CONFIG_TCM_IBLOCK=m CONFIG_TCM_FILEIO=m @@ -385,6 +387,7 @@ CONFIG_SUN3_82586=y # CONFIG_NET_VENDOR_SUN is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -525,6 +528,8 @@ CONFIG_DLM=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_TEST_LIST_SORT=m +CONFIG_TEST_SORT=m CONFIG_ATOMIC64_SELFTEST=m CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m @@ -542,6 +547,7 @@ CONFIG_TEST_FIRMWARE=m CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_ENCRYPTED_KEYS=m +CONFIG_HARDENED_USERCOPY=y CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig index 3c394fcfb368..a1e79530e806 100644 --- a/arch/m68k/configs/sun3x_defconfig +++ b/arch/m68k/configs/sun3x_defconfig @@ -26,6 +26,8 @@ CONFIG_UNIXWARE_DISKLABEL=y CONFIG_SYSV68_PARTITION=y CONFIG_IOSCHED_DEADLINE=m CONFIG_MQ_IOSCHED_DEADLINE=m +CONFIG_MQ_IOSCHED_KYBER=m +CONFIG_IOSCHED_BFQ=m CONFIG_KEXEC=y CONFIG_BOOTINFO_PROC=y CONFIG_SUN3X=y @@ -327,7 +329,6 @@ CONFIG_ISCSI_BOOT_SYSFS=m CONFIG_SUN3X_ESP=y CONFIG_MD=y CONFIG_MD_LINEAR=m -CONFIG_MD_RAID0=m CONFIG_BLK_DEV_DM=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m @@ -339,6 +340,7 @@ CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_UEVENT=y CONFIG_DM_LOG_WRITES=m +CONFIG_DM_INTEGRITY=m CONFIG_TARGET_CORE=m CONFIG_TCM_IBLOCK=m CONFIG_TCM_FILEIO=m @@ -385,6 +387,7 @@ CONFIG_SUN3LANCE=y # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -525,6 +528,8 @@ CONFIG_DLM=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_TEST_LIST_SORT=m +CONFIG_TEST_SORT=m CONFIG_ATOMIC64_SELFTEST=m CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m @@ -543,6 +548,7 @@ CONFIG_TEST_UDELAY=m CONFIG_TEST_STATIC_KEYS=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m +CONFIG_HARDENED_USERCOPY=y CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m diff --git a/arch/m68k/include/asm/processor.h b/arch/m68k/include/asm/processor.h index 77239e81379b..94c36030440c 100644 --- a/arch/m68k/include/asm/processor.h +++ b/arch/m68k/include/asm/processor.h @@ -130,8 +130,6 @@ static inline void release_thread(struct task_struct *dead_task) { } -extern unsigned long thread_saved_pc(struct task_struct *tsk); - unsigned long get_wchan(struct task_struct *p); #define KSTK_EIP(tsk) \ diff --git a/arch/m68k/include/asm/signal.h b/arch/m68k/include/asm/signal.h index 8c8ce5e1ee0e..3bc64d02ba5f 100644 --- a/arch/m68k/include/asm/signal.h +++ b/arch/m68k/include/asm/signal.h @@ -62,9 +62,4 @@ static inline int __gen_sigismember(sigset_t *set, int _sig) #endif /* !CONFIG_CPU_HAS_NO_BITFIELDS */ -#ifndef __uClinux__ -extern void ptrace_signal_deliver(void); -#define ptrace_signal_deliver ptrace_signal_deliver -#endif /* __uClinux__ */ - #endif /* _M68K_SIGNAL_H */ diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c index e475c945c8b2..7df92f8b0781 100644 --- a/arch/m68k/kernel/process.c +++ b/arch/m68k/kernel/process.c @@ -40,20 +40,6 @@ asmlinkage void ret_from_fork(void); asmlinkage void ret_from_kernel_thread(void); - -/* - * Return saved PC from a blocked thread - */ -unsigned long thread_saved_pc(struct task_struct *tsk) -{ - struct switch_stack *sw = (struct switch_stack *)tsk->thread.ksp; - /* Check whether the thread is blocked in resume() */ - if (in_sched_functions(sw->retpc)) - return ((unsigned long *)sw->a6)[1]; - else - return sw->retpc; -} - void arch_cpu_idle(void) { #if defined(MACH_ATARI_ONLY) diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c index 6f945bb5ffbd..e79421f5b9cd 100644 --- a/arch/m68k/kernel/signal.c +++ b/arch/m68k/kernel/signal.c @@ -109,22 +109,6 @@ int fixup_exception(struct pt_regs *regs) return 1; } -void ptrace_signal_deliver(void) -{ - struct pt_regs *regs = signal_pt_regs(); - if (regs->orig_d0 < 0) - return; - switch (regs->d0) { - case -ERESTARTNOHAND: - case -ERESTARTSYS: - case -ERESTARTNOINTR: - regs->d0 = regs->orig_d0; - regs->orig_d0 = -1; - regs->pc -= 2; - break; - } -} - static inline void push_cache (unsigned long vaddr) { /* diff --git a/arch/metag/kernel/smp.c b/arch/metag/kernel/smp.c index 232a12bf3f99..2dbbb7c66043 100644 --- a/arch/metag/kernel/smp.c +++ b/arch/metag/kernel/smp.c @@ -567,8 +567,7 @@ static void stop_this_cpu(void *data) { unsigned int cpu = smp_processor_id(); - if (system_state == SYSTEM_BOOTING || - system_state == SYSTEM_RUNNING) { + if (system_state <= SYSTEM_RUNNING) { spin_lock(&stop_lock); pr_crit("CPU%u: stopping\n", cpu); dump_stack(); diff --git a/arch/microblaze/configs/mmu_defconfig b/arch/microblaze/configs/mmu_defconfig index dc5dd5b69fde..92fd4e95b488 100644 --- a/arch/microblaze/configs/mmu_defconfig +++ b/arch/microblaze/configs/mmu_defconfig @@ -1,8 +1,6 @@ CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y -CONFIG_FHANDLE=y CONFIG_AUDIT=y -CONFIG_AUDIT_LOGINUID_IMMUTABLE=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_SYSFS_DEPRECATED=y @@ -33,10 +31,12 @@ CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y CONFIG_INET=y -# CONFIG_INET_LRO is not set # CONFIG_IPV6 is not set +CONFIG_BRIDGE=m CONFIG_MTD=y -CONFIG_PROC_DEVICETREE=y +CONFIG_MTD_CFI=y +CONFIG_MTD_CFI_INTELEXT=y +CONFIG_MTD_CFI_AMDSTD=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=8192 CONFIG_NETDEVICES=y @@ -47,9 +47,9 @@ CONFIG_XILINX_LL_TEMAC=y # CONFIG_VT is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_OF_PLATFORM=y CONFIG_SERIAL_UARTLITE=y CONFIG_SERIAL_UARTLITE_CONSOLE=y -CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set CONFIG_XILINX_HWICAP=y CONFIG_I2C=y @@ -66,7 +66,6 @@ CONFIG_FB=y CONFIG_FB_XILINX=y # CONFIG_USB_SUPPORT is not set CONFIG_UIO=y -CONFIG_UIO_PDRV=y CONFIG_UIO_PDRV_GENIRQ=y CONFIG_UIO_DMEM_GENIRQ=y CONFIG_EXT2_FS=y @@ -77,14 +76,13 @@ CONFIG_NFS_FS=y CONFIG_CIFS=y CONFIG_CIFS_STATS=y CONFIG_CIFS_STATS2=y -CONFIG_DETECT_HUNG_TASK=y +CONFIG_DEBUG_INFO=y CONFIG_DEBUG_SLAB=y +CONFIG_DETECT_HUNG_TASK=y CONFIG_DEBUG_SPINLOCK=y -CONFIG_DEBUG_INFO=y CONFIG_KGDB=y CONFIG_KGDB_TESTS=y CONFIG_KGDB_KDB=y CONFIG_EARLY_PRINTK=y CONFIG_KEYS=y CONFIG_ENCRYPTED_KEYS=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/microblaze/configs/nommu_defconfig b/arch/microblaze/configs/nommu_defconfig index 4cdaf565e638..06d69a6e192d 100644 --- a/arch/microblaze/configs/nommu_defconfig +++ b/arch/microblaze/configs/nommu_defconfig @@ -1,9 +1,6 @@ -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y -CONFIG_FHANDLE=y CONFIG_AUDIT=y -CONFIG_AUDIT_LOGINUID_IMMUTABLE=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_BSD_PROCESS_ACCT_V3=y CONFIG_IKCONFIG=y @@ -34,18 +31,15 @@ CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y CONFIG_INET=y -# CONFIG_INET_LRO is not set # CONFIG_IPV6 is not set CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_INTELEXT=y CONFIG_MTD_CFI_AMDSTD=y CONFIG_MTD_RAM=y CONFIG_MTD_UCLINUX=y -CONFIG_PROC_DEVICETREE=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=8192 CONFIG_NETDEVICES=y @@ -56,9 +50,9 @@ CONFIG_XILINX_LL_TEMAC=y # CONFIG_VT is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_OF_PLATFORM=y CONFIG_SERIAL_UARTLITE=y CONFIG_SERIAL_UARTLITE_CONSOLE=y -CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set CONFIG_XILINX_HWICAP=y CONFIG_I2C=y @@ -74,10 +68,6 @@ CONFIG_XILINX_WATCHDOG=y CONFIG_FB=y CONFIG_FB_XILINX=y # CONFIG_USB_SUPPORT is not set -CONFIG_UIO=y -CONFIG_UIO_PDRV=y -CONFIG_UIO_PDRV_GENIRQ=y -CONFIG_UIO_DMEM_GENIRQ=y CONFIG_EXT2_FS=y # CONFIG_DNOTIFY is not set CONFIG_CRAMFS=y @@ -85,10 +75,10 @@ CONFIG_ROMFS_FS=y CONFIG_NFS_FS=y CONFIG_NFS_V3_ACL=y CONFIG_NLS=y -CONFIG_DETECT_HUNG_TASK=y +CONFIG_DEBUG_INFO=y CONFIG_DEBUG_SLAB=y +CONFIG_DETECT_HUNG_TASK=y CONFIG_DEBUG_SPINLOCK=y -CONFIG_DEBUG_INFO=y CONFIG_EARLY_PRINTK=y CONFIG_KEYS=y CONFIG_ENCRYPTED_KEYS=y @@ -97,4 +87,3 @@ CONFIG_CRYPTO_MD4=y CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_ARC4=y CONFIG_CRYPTO_DES=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild index 56830ff65333..83a4ef3a2495 100644 --- a/arch/microblaze/include/asm/Kbuild +++ b/arch/microblaze/include/asm/Kbuild @@ -1,14 +1,57 @@ generic-y += barrier.h +generic-y += bitops.h +generic-y += bitsperlong.h +generic-y += bug.h +generic-y += bugs.h generic-y += clkdev.h generic-y += device.h +generic-y += div64.h +generic-y += emergency-restart.h +generic-y += errno.h generic-y += exec.h generic-y += extable.h +generic-y += fb.h +generic-y += fcntl.h +generic-y += hardirq.h +generic-y += ioctl.h +generic-y += ioctls.h +generic-y += ipcbuf.h +generic-y += irq_regs.h generic-y += irq_work.h +generic-y += kdebug.h +generic-y += kmap_types.h +generic-y += kprobes.h +generic-y += linkage.h +generic-y += local.h +generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h +generic-y += mman.h +generic-y += msgbuf.h +generic-y += param.h +generic-y += parport.h +generic-y += percpu.h +generic-y += poll.h generic-y += preempt.h +generic-y += resource.h +generic-y += sembuf.h +generic-y += serial.h +generic-y += shmbuf.h +generic-y += shmparam.h +generic-y += siginfo.h +generic-y += signal.h +generic-y += socket.h +generic-y += sockios.h +generic-y += stat.h +generic-y += statfs.h +generic-y += swab.h generic-y += syscalls.h +generic-y += termbits.h +generic-y += termios.h +generic-y += topology.h generic-y += trace_clock.h +generic-y += ucontext.h +generic-y += vga.h generic-y += word-at-a-time.h -generic-y += kprobes.h +generic-y += xor.h diff --git a/arch/microblaze/include/asm/bitops.h b/arch/microblaze/include/asm/bitops.h deleted file mode 100644 index a72468f15c8b..000000000000 --- a/arch/microblaze/include/asm/bitops.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/bitops.h> diff --git a/arch/microblaze/include/asm/bug.h b/arch/microblaze/include/asm/bug.h deleted file mode 100644 index b12fd89e42e9..000000000000 --- a/arch/microblaze/include/asm/bug.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/bug.h> diff --git a/arch/microblaze/include/asm/bugs.h b/arch/microblaze/include/asm/bugs.h deleted file mode 100644 index 61791e1ad9f5..000000000000 --- a/arch/microblaze/include/asm/bugs.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/bugs.h> diff --git a/arch/microblaze/include/asm/div64.h b/arch/microblaze/include/asm/div64.h deleted file mode 100644 index 6cd978cefb28..000000000000 --- a/arch/microblaze/include/asm/div64.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/div64.h> diff --git a/arch/microblaze/include/asm/emergency-restart.h b/arch/microblaze/include/asm/emergency-restart.h deleted file mode 100644 index 3711bd9d50bd..000000000000 --- a/arch/microblaze/include/asm/emergency-restart.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/emergency-restart.h> diff --git a/arch/microblaze/include/asm/fb.h b/arch/microblaze/include/asm/fb.h deleted file mode 100644 index 3a4988e8df45..000000000000 --- a/arch/microblaze/include/asm/fb.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/fb.h> diff --git a/arch/microblaze/include/asm/hardirq.h b/arch/microblaze/include/asm/hardirq.h deleted file mode 100644 index fb3c05a0cbbf..000000000000 --- a/arch/microblaze/include/asm/hardirq.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/hardirq.h> diff --git a/arch/microblaze/include/asm/irq_regs.h b/arch/microblaze/include/asm/irq_regs.h deleted file mode 100644 index 3dd9c0b70270..000000000000 --- a/arch/microblaze/include/asm/irq_regs.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/irq_regs.h> diff --git a/arch/microblaze/include/asm/kdebug.h b/arch/microblaze/include/asm/kdebug.h deleted file mode 100644 index 6ece1b037665..000000000000 --- a/arch/microblaze/include/asm/kdebug.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/kdebug.h> diff --git a/arch/microblaze/include/asm/kmap_types.h b/arch/microblaze/include/asm/kmap_types.h deleted file mode 100644 index 25975252d83d..000000000000 --- a/arch/microblaze/include/asm/kmap_types.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _ASM_MICROBLAZE_KMAP_TYPES_H -#define _ASM_MICROBLAZE_KMAP_TYPES_H - -#include <asm-generic/kmap_types.h> - -#endif /* _ASM_MICROBLAZE_KMAP_TYPES_H */ diff --git a/arch/microblaze/include/asm/linkage.h b/arch/microblaze/include/asm/linkage.h deleted file mode 100644 index 0540bbaad897..000000000000 --- a/arch/microblaze/include/asm/linkage.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/linkage.h> diff --git a/arch/microblaze/include/asm/local.h b/arch/microblaze/include/asm/local.h deleted file mode 100644 index c11c530f74d0..000000000000 --- a/arch/microblaze/include/asm/local.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/local.h> diff --git a/arch/microblaze/include/asm/local64.h b/arch/microblaze/include/asm/local64.h deleted file mode 100644 index 36c93b5cc239..000000000000 --- a/arch/microblaze/include/asm/local64.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/local64.h> diff --git a/arch/microblaze/include/asm/parport.h b/arch/microblaze/include/asm/parport.h deleted file mode 100644 index cf252af64590..000000000000 --- a/arch/microblaze/include/asm/parport.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/parport.h> diff --git a/arch/microblaze/include/asm/percpu.h b/arch/microblaze/include/asm/percpu.h deleted file mode 100644 index 06a959d67234..000000000000 --- a/arch/microblaze/include/asm/percpu.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/percpu.h> diff --git a/arch/microblaze/include/asm/processor.h b/arch/microblaze/include/asm/processor.h index 37ef196e4519..330d556860ba 100644 --- a/arch/microblaze/include/asm/processor.h +++ b/arch/microblaze/include/asm/processor.h @@ -69,8 +69,6 @@ static inline void release_thread(struct task_struct *dead_task) { } -extern unsigned long thread_saved_pc(struct task_struct *t); - extern unsigned long get_wchan(struct task_struct *p); # define KSTK_EIP(tsk) (0) @@ -121,10 +119,6 @@ static inline void release_thread(struct task_struct *dead_task) { } -/* Return saved (kernel) PC of a blocked thread. */ -# define thread_saved_pc(tsk) \ - ((tsk)->thread.regs ? (tsk)->thread.regs->r15 : 0) - unsigned long get_wchan(struct task_struct *p); /* The size allocated for kernel stacks. This _must_ be a power of two! */ diff --git a/arch/microblaze/include/asm/serial.h b/arch/microblaze/include/asm/serial.h deleted file mode 100644 index a0cb0caff152..000000000000 --- a/arch/microblaze/include/asm/serial.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/serial.h> diff --git a/arch/microblaze/include/asm/shmparam.h b/arch/microblaze/include/asm/shmparam.h deleted file mode 100644 index 93f30deb95d0..000000000000 --- a/arch/microblaze/include/asm/shmparam.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/shmparam.h> diff --git a/arch/microblaze/include/asm/topology.h b/arch/microblaze/include/asm/topology.h deleted file mode 100644 index 5428f333a02c..000000000000 --- a/arch/microblaze/include/asm/topology.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/topology.h> diff --git a/arch/microblaze/include/asm/ucontext.h b/arch/microblaze/include/asm/ucontext.h deleted file mode 100644 index 9bc07b9f30fb..000000000000 --- a/arch/microblaze/include/asm/ucontext.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/ucontext.h> diff --git a/arch/microblaze/include/asm/unistd.h b/arch/microblaze/include/asm/unistd.h index 032fed71223f..9774e1d9507b 100644 --- a/arch/microblaze/include/asm/unistd.h +++ b/arch/microblaze/include/asm/unistd.h @@ -38,6 +38,6 @@ #endif /* __ASSEMBLY__ */ -#define __NR_syscalls 398 +#define __NR_syscalls 399 #endif /* _ASM_MICROBLAZE_UNISTD_H */ diff --git a/arch/microblaze/include/asm/vga.h b/arch/microblaze/include/asm/vga.h deleted file mode 100644 index 89d82fd8fcf1..000000000000 --- a/arch/microblaze/include/asm/vga.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/vga.h> diff --git a/arch/microblaze/include/asm/xor.h b/arch/microblaze/include/asm/xor.h deleted file mode 100644 index c82eb12a5b18..000000000000 --- a/arch/microblaze/include/asm/xor.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/xor.h> diff --git a/arch/microblaze/include/uapi/asm/bitsperlong.h b/arch/microblaze/include/uapi/asm/bitsperlong.h deleted file mode 100644 index 6dc0bb0c13b2..000000000000 --- a/arch/microblaze/include/uapi/asm/bitsperlong.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/bitsperlong.h> diff --git a/arch/microblaze/include/uapi/asm/errno.h b/arch/microblaze/include/uapi/asm/errno.h deleted file mode 100644 index 4c82b503d92f..000000000000 --- a/arch/microblaze/include/uapi/asm/errno.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/errno.h> diff --git a/arch/microblaze/include/uapi/asm/fcntl.h b/arch/microblaze/include/uapi/asm/fcntl.h deleted file mode 100644 index 46ab12db5739..000000000000 --- a/arch/microblaze/include/uapi/asm/fcntl.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/fcntl.h> diff --git a/arch/microblaze/include/uapi/asm/ioctl.h b/arch/microblaze/include/uapi/asm/ioctl.h deleted file mode 100644 index b279fe06dfe5..000000000000 --- a/arch/microblaze/include/uapi/asm/ioctl.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/ioctl.h> diff --git a/arch/microblaze/include/uapi/asm/ioctls.h b/arch/microblaze/include/uapi/asm/ioctls.h deleted file mode 100644 index ec34c760665e..000000000000 --- a/arch/microblaze/include/uapi/asm/ioctls.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/ioctls.h> diff --git a/arch/microblaze/include/uapi/asm/ipcbuf.h b/arch/microblaze/include/uapi/asm/ipcbuf.h deleted file mode 100644 index 84c7e51cb6d0..000000000000 --- a/arch/microblaze/include/uapi/asm/ipcbuf.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/ipcbuf.h> diff --git a/arch/microblaze/include/uapi/asm/kvm_para.h b/arch/microblaze/include/uapi/asm/kvm_para.h deleted file mode 100644 index 14fab8f0b957..000000000000 --- a/arch/microblaze/include/uapi/asm/kvm_para.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/kvm_para.h> diff --git a/arch/microblaze/include/uapi/asm/mman.h b/arch/microblaze/include/uapi/asm/mman.h deleted file mode 100644 index 8eebf89f5ab1..000000000000 --- a/arch/microblaze/include/uapi/asm/mman.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/mman.h> diff --git a/arch/microblaze/include/uapi/asm/msgbuf.h b/arch/microblaze/include/uapi/asm/msgbuf.h deleted file mode 100644 index 809134c644a6..000000000000 --- a/arch/microblaze/include/uapi/asm/msgbuf.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/msgbuf.h> diff --git a/arch/microblaze/include/uapi/asm/param.h b/arch/microblaze/include/uapi/asm/param.h deleted file mode 100644 index 965d45427975..000000000000 --- a/arch/microblaze/include/uapi/asm/param.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/param.h> diff --git a/arch/microblaze/include/uapi/asm/poll.h b/arch/microblaze/include/uapi/asm/poll.h deleted file mode 100644 index c98509d3149e..000000000000 --- a/arch/microblaze/include/uapi/asm/poll.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/poll.h> diff --git a/arch/microblaze/include/uapi/asm/resource.h b/arch/microblaze/include/uapi/asm/resource.h deleted file mode 100644 index 04bc4db8921b..000000000000 --- a/arch/microblaze/include/uapi/asm/resource.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/resource.h> diff --git a/arch/microblaze/include/uapi/asm/sembuf.h b/arch/microblaze/include/uapi/asm/sembuf.h deleted file mode 100644 index 7673b83cfef7..000000000000 --- a/arch/microblaze/include/uapi/asm/sembuf.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/sembuf.h> diff --git a/arch/microblaze/include/uapi/asm/shmbuf.h b/arch/microblaze/include/uapi/asm/shmbuf.h deleted file mode 100644 index 83c05fc2de38..000000000000 --- a/arch/microblaze/include/uapi/asm/shmbuf.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/shmbuf.h> diff --git a/arch/microblaze/include/uapi/asm/signal.h b/arch/microblaze/include/uapi/asm/signal.h deleted file mode 100644 index 7b1573ce19de..000000000000 --- a/arch/microblaze/include/uapi/asm/signal.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/signal.h> diff --git a/arch/microblaze/include/uapi/asm/socket.h b/arch/microblaze/include/uapi/asm/socket.h deleted file mode 100644 index 6b71384b9d8b..000000000000 --- a/arch/microblaze/include/uapi/asm/socket.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/socket.h> diff --git a/arch/microblaze/include/uapi/asm/sockios.h b/arch/microblaze/include/uapi/asm/sockios.h deleted file mode 100644 index def6d4746ee7..000000000000 --- a/arch/microblaze/include/uapi/asm/sockios.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/sockios.h> diff --git a/arch/microblaze/include/uapi/asm/stat.h b/arch/microblaze/include/uapi/asm/stat.h deleted file mode 100644 index 3dc90fa92c70..000000000000 --- a/arch/microblaze/include/uapi/asm/stat.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/stat.h> diff --git a/arch/microblaze/include/uapi/asm/statfs.h b/arch/microblaze/include/uapi/asm/statfs.h deleted file mode 100644 index 0b91fe198c20..000000000000 --- a/arch/microblaze/include/uapi/asm/statfs.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/statfs.h> diff --git a/arch/microblaze/include/uapi/asm/swab.h b/arch/microblaze/include/uapi/asm/swab.h deleted file mode 100644 index 7847e563ab66..000000000000 --- a/arch/microblaze/include/uapi/asm/swab.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/swab.h> diff --git a/arch/microblaze/include/uapi/asm/termbits.h b/arch/microblaze/include/uapi/asm/termbits.h deleted file mode 100644 index 3935b106de79..000000000000 --- a/arch/microblaze/include/uapi/asm/termbits.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/termbits.h> diff --git a/arch/microblaze/include/uapi/asm/termios.h b/arch/microblaze/include/uapi/asm/termios.h deleted file mode 100644 index 280d78a9d966..000000000000 --- a/arch/microblaze/include/uapi/asm/termios.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/termios.h> diff --git a/arch/microblaze/include/uapi/asm/unistd.h b/arch/microblaze/include/uapi/asm/unistd.h index d8086159d996..a88b3c11cc20 100644 --- a/arch/microblaze/include/uapi/asm/unistd.h +++ b/arch/microblaze/include/uapi/asm/unistd.h @@ -413,5 +413,6 @@ #define __NR_pkey_mprotect 395 #define __NR_pkey_alloc 396 #define __NR_pkey_free 397 +#define __NR_statx 398 #endif /* _UAPI_ASM_MICROBLAZE_UNISTD_H */ diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c index 12e093a03e60..e45ada8fb006 100644 --- a/arch/microblaze/kernel/dma.c +++ b/arch/microblaze/kernel/dma.c @@ -65,8 +65,7 @@ static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, if (attrs & DMA_ATTR_SKIP_CPU_SYNC) continue; - __dma_sync(page_to_phys(sg_page(sg)) + sg->offset, - sg->length, direction); + __dma_sync(sg_phys(sg), sg->length, direction); } return nents; diff --git a/arch/microblaze/kernel/entry.S b/arch/microblaze/kernel/entry.S index ef548510b951..4e1b567becd6 100644 --- a/arch/microblaze/kernel/entry.S +++ b/arch/microblaze/kernel/entry.S @@ -208,9 +208,7 @@ syscall_debug_table: mfs r11, rmsr; /* save MSR */ \ swi r11, r1, PT_MSR; -#define RESTORE_REGS \ - lwi r11, r1, PT_MSR; \ - mts rmsr , r11; \ +#define RESTORE_REGS_GP \ lwi r2, r1, PT_R2; /* restore SDA */ \ lwi r3, r1, PT_R3; \ lwi r4, r1, PT_R4; \ @@ -242,6 +240,18 @@ syscall_debug_table: lwi r30, r1, PT_R30; \ lwi r31, r1, PT_R31; /* Restore cur task reg */ +#define RESTORE_REGS \ + lwi r11, r1, PT_MSR; \ + mts rmsr , r11; \ + RESTORE_REGS_GP + +#define RESTORE_REGS_RTBD \ + lwi r11, r1, PT_MSR; \ + andni r11, r11, MSR_EIP; /* clear EIP */ \ + ori r11, r11, MSR_EE | MSR_BIP; /* set EE and BIP */ \ + mts rmsr , r11; \ + RESTORE_REGS_GP + #define SAVE_STATE \ swi r1, r0, TOPHYS(PER_CPU(ENTRY_SP)); /* save stack */ \ /* See if already in kernel mode.*/ \ @@ -427,7 +437,7 @@ C_ENTRY(ret_from_trap): swi CURRENT_TASK, r0, PER_CPU(CURRENT_SAVE); /* save current */ VM_OFF; tophys(r1,r1); - RESTORE_REGS; + RESTORE_REGS_RTBD; addik r1, r1, PT_SIZE /* Clean up stack space. */ lwi r1, r1, PT_R1 - PT_SIZE;/* Restore user stack pointer. */ bri 6f; @@ -436,7 +446,7 @@ C_ENTRY(ret_from_trap): 2: set_bip; /* Ints masked for state restore */ VM_OFF; tophys(r1,r1); - RESTORE_REGS; + RESTORE_REGS_RTBD; addik r1, r1, PT_SIZE /* Clean up stack space. */ tovirt(r1,r1); 6: @@ -612,7 +622,7 @@ C_ENTRY(ret_from_exc): VM_OFF; tophys(r1,r1); - RESTORE_REGS; + RESTORE_REGS_RTBD; addik r1, r1, PT_SIZE /* Clean up stack space. */ lwi r1, r1, PT_R1 - PT_SIZE; /* Restore user stack pointer. */ @@ -621,7 +631,7 @@ C_ENTRY(ret_from_exc): 2: set_bip; /* Ints masked for state restore */ VM_OFF; tophys(r1,r1); - RESTORE_REGS; + RESTORE_REGS_RTBD; addik r1, r1, PT_SIZE /* Clean up stack space. */ tovirt(r1,r1); @@ -847,7 +857,7 @@ dbtrap_call: /* Return point for kernel/user entry + 8 because of rtsd r15, 8 */ VM_OFF; tophys(r1,r1); /* MS: Restore all regs */ - RESTORE_REGS + RESTORE_REGS_RTBD addik r1, r1, PT_SIZE /* Clean up stack space */ lwi r1, r1, PT_R1 - PT_SIZE; /* Restore user stack pointer */ DBTRAP_return_user: /* MS: Make global symbol for debugging */ @@ -858,7 +868,7 @@ DBTRAP_return_user: /* MS: Make global symbol for debugging */ 2: VM_OFF; tophys(r1,r1); /* MS: Restore all regs */ - RESTORE_REGS + RESTORE_REGS_RTBD lwi r14, r1, PT_R14; lwi r16, r1, PT_PC; addik r1, r1, PT_SIZE; /* MS: Clean up stack space */ diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c index e92a817e645f..6527ec22f158 100644 --- a/arch/microblaze/kernel/process.c +++ b/arch/microblaze/kernel/process.c @@ -119,23 +119,6 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, return 0; } -#ifndef CONFIG_MMU -/* - * Return saved PC of a blocked thread. - */ -unsigned long thread_saved_pc(struct task_struct *tsk) -{ - struct cpu_context *ctx = - &(((struct thread_info *)(tsk->stack))->cpu_context); - - /* Check whether the thread is blocked in resume() */ - if (in_sched_functions(ctx->r15)) - return (unsigned long)ctx->r15; - else - return ctx->r14; -} -#endif - unsigned long get_wchan(struct task_struct *p) { /* TBD (used by procfs) */ diff --git a/arch/microblaze/kernel/syscall_table.S b/arch/microblaze/kernel/syscall_table.S index 6841c2df14d9..c48ff4ad2070 100644 --- a/arch/microblaze/kernel/syscall_table.S +++ b/arch/microblaze/kernel/syscall_table.S @@ -398,3 +398,4 @@ ENTRY(sys_call_table) .long sys_pkey_mprotect /* 395 */ .long sys_pkey_alloc .long sys_pkey_free + .long sys_statx diff --git a/arch/microblaze/kernel/timer.c b/arch/microblaze/kernel/timer.c index 873a1ccd9040..ea2d83f1f4bb 100644 --- a/arch/microblaze/kernel/timer.c +++ b/arch/microblaze/kernel/timer.c @@ -178,8 +178,10 @@ static __init int xilinx_clockevent_init(void) clockevent_xilinx_timer.shift); clockevent_xilinx_timer.max_delta_ns = clockevent_delta2ns((u32)~0, &clockevent_xilinx_timer); + clockevent_xilinx_timer.max_delta_ticks = (u32)~0; clockevent_xilinx_timer.min_delta_ns = clockevent_delta2ns(1, &clockevent_xilinx_timer); + clockevent_xilinx_timer.min_delta_ticks = 1; clockevent_xilinx_timer.cpumask = cpumask_of(0); clockevents_register_device(&clockevent_xilinx_timer); diff --git a/arch/microblaze/mm/highmem.c b/arch/microblaze/mm/highmem.c index 2fcc5a52d84d..ed4454c5ce35 100644 --- a/arch/microblaze/mm/highmem.c +++ b/arch/microblaze/mm/highmem.c @@ -60,6 +60,7 @@ void __kunmap_atomic(void *kvaddr) { unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK; int type; + unsigned int idx; if (vaddr < __fix_to_virt(FIX_KMAP_END)) { pagefault_enable(); @@ -68,21 +69,18 @@ void __kunmap_atomic(void *kvaddr) } type = kmap_atomic_idx(); -#ifdef CONFIG_DEBUG_HIGHMEM - { - unsigned int idx; - - idx = type + KM_TYPE_NR * smp_processor_id(); - BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx)); - /* - * force other mappings to Oops if they'll try to access - * this pte without first remap it - */ - pte_clear(&init_mm, vaddr, kmap_pte-idx); - local_flush_tlb_page(NULL, vaddr); - } + idx = type + KM_TYPE_NR * smp_processor_id(); +#ifdef CONFIG_DEBUG_HIGHMEM + BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx)); #endif + /* + * force other mappings to Oops if they'll try to access + * this pte without first remap it + */ + pte_clear(&init_mm, vaddr, kmap_pte-idx); + local_flush_tlb_page(NULL, vaddr); + kmap_atomic_idx_pop(); pagefault_enable(); preempt_enable(); diff --git a/arch/mips/kernel/entry.S b/arch/mips/kernel/entry.S index 8d83fc2a96b7..38a302919e6b 100644 --- a/arch/mips/kernel/entry.S +++ b/arch/mips/kernel/entry.S @@ -11,6 +11,7 @@ #include <asm/asm.h> #include <asm/asmmacro.h> #include <asm/compiler.h> +#include <asm/irqflags.h> #include <asm/regdef.h> #include <asm/mipsregs.h> #include <asm/stackframe.h> @@ -119,6 +120,7 @@ work_pending: andi t0, a2, _TIF_NEED_RESCHED # a2 is preloaded with TI_FLAGS beqz t0, work_notifysig work_resched: + TRACE_IRQS_OFF jal schedule local_irq_disable # make sure need_resched and @@ -155,6 +157,7 @@ syscall_exit_work: beqz t0, work_pending # trace bit set? local_irq_enable # could let syscall_trace_leave() # call schedule() instead + TRACE_IRQS_ON move a0, sp jal syscall_trace_leave b resume_userspace diff --git a/arch/mips/kernel/head.S b/arch/mips/kernel/head.S index cf052204eb0a..d1bb506adc10 100644 --- a/arch/mips/kernel/head.S +++ b/arch/mips/kernel/head.S @@ -106,8 +106,8 @@ NESTED(kernel_entry, 16, sp) # kernel entry point beq t0, t1, dtb_found #endif li t1, -2 - beq a0, t1, dtb_found move t2, a1 + beq a0, t1, dtb_found li t2, 0 dtb_found: diff --git a/arch/mips/kernel/pm-cps.c b/arch/mips/kernel/pm-cps.c index 5f928c34c148..d99416094ba9 100644 --- a/arch/mips/kernel/pm-cps.c +++ b/arch/mips/kernel/pm-cps.c @@ -56,7 +56,6 @@ DECLARE_BITMAP(state_support, CPS_PM_STATE_COUNT); * state. Actually per-core rather than per-CPU. */ static DEFINE_PER_CPU_ALIGNED(u32*, ready_count); -static DEFINE_PER_CPU_ALIGNED(void*, ready_count_alloc); /* Indicates online CPUs coupled with the current CPU */ static DEFINE_PER_CPU_ALIGNED(cpumask_t, online_coupled); @@ -642,7 +641,6 @@ static int cps_pm_online_cpu(unsigned int cpu) { enum cps_pm_state state; unsigned core = cpu_data[cpu].core; - unsigned dlinesz = cpu_data[cpu].dcache.linesz; void *entry_fn, *core_rc; for (state = CPS_PM_NC_WAIT; state < CPS_PM_STATE_COUNT; state++) { @@ -662,16 +660,11 @@ static int cps_pm_online_cpu(unsigned int cpu) } if (!per_cpu(ready_count, core)) { - core_rc = kmalloc(dlinesz * 2, GFP_KERNEL); + core_rc = kmalloc(sizeof(u32), GFP_KERNEL); if (!core_rc) { pr_err("Failed allocate core %u ready_count\n", core); return -ENOMEM; } - per_cpu(ready_count_alloc, core) = core_rc; - - /* Ensure ready_count is aligned to a cacheline boundary */ - core_rc += dlinesz - 1; - core_rc = (void *)((unsigned long)core_rc & ~(dlinesz - 1)); per_cpu(ready_count, core) = core_rc; } diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 9681b5877140..38dfa27730ff 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -201,6 +201,8 @@ void show_stack(struct task_struct *task, unsigned long *sp) { struct pt_regs regs; mm_segment_t old_fs = get_fs(); + + regs.cp0_status = KSU_KERNEL; if (sp) { regs.regs[29] = (unsigned long)sp; regs.regs[31] = 0; diff --git a/arch/mips/kvm/tlb.c b/arch/mips/kvm/tlb.c index 7c6336dd2638..7cd92166a0b9 100644 --- a/arch/mips/kvm/tlb.c +++ b/arch/mips/kvm/tlb.c @@ -166,7 +166,11 @@ static int _kvm_mips_host_tlb_inv(unsigned long entryhi) int kvm_mips_host_tlb_inv(struct kvm_vcpu *vcpu, unsigned long va, bool user, bool kernel) { - int idx_user, idx_kernel; + /* + * Initialize idx_user and idx_kernel to workaround bogus + * maybe-initialized warning when using GCC 6. + */ + int idx_user = 0, idx_kernel = 0; unsigned long flags, old_entryhi; local_irq_save(flags); diff --git a/arch/mips/math-emu/dp_maddf.c b/arch/mips/math-emu/dp_maddf.c index 4a2d03c72959..caa62f20a888 100644 --- a/arch/mips/math-emu/dp_maddf.c +++ b/arch/mips/math-emu/dp_maddf.c @@ -54,7 +54,7 @@ static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x, return ieee754dp_nanxcpt(z); case IEEE754_CLASS_DNORM: DPDNORMZ; - /* QNAN is handled separately below */ + /* QNAN and ZERO cases are handled separately below */ } switch (CLPAIR(xc, yc)) { @@ -210,6 +210,9 @@ static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x, } assert(rm & (DP_HIDDEN_BIT << 3)); + if (zc == IEEE754_CLASS_ZERO) + return ieee754dp_format(rs, re, rm); + /* And now the addition */ assert(zm & DP_HIDDEN_BIT); diff --git a/arch/mips/math-emu/sp_maddf.c b/arch/mips/math-emu/sp_maddf.c index a8cd8b4f235e..c91d5e5d9b5f 100644 --- a/arch/mips/math-emu/sp_maddf.c +++ b/arch/mips/math-emu/sp_maddf.c @@ -54,7 +54,7 @@ static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x, return ieee754sp_nanxcpt(z); case IEEE754_CLASS_DNORM: SPDNORMZ; - /* QNAN is handled separately below */ + /* QNAN and ZERO cases are handled separately below */ } switch (CLPAIR(xc, yc)) { @@ -203,6 +203,9 @@ static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x, } assert(rm & (SP_HIDDEN_BIT << 3)); + if (zc == IEEE754_CLASS_ZERO) + return ieee754sp_format(rs, re, rm); + /* And now the addition */ assert(zm & SP_HIDDEN_BIT); diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c index fe8df14b6169..e08598c70b3e 100644 --- a/arch/mips/mm/dma-default.c +++ b/arch/mips/mm/dma-default.c @@ -68,12 +68,25 @@ static inline struct page *dma_addr_to_page(struct device *dev, * systems and only the R10000 and R12000 are used in such systems, the * SGI IP28 Indigo² rsp. SGI IP32 aka O2. */ -static inline int cpu_needs_post_dma_flush(struct device *dev) +static inline bool cpu_needs_post_dma_flush(struct device *dev) { - return !plat_device_is_coherent(dev) && - (boot_cpu_type() == CPU_R10000 || - boot_cpu_type() == CPU_R12000 || - boot_cpu_type() == CPU_BMIPS5000); + if (plat_device_is_coherent(dev)) + return false; + + switch (boot_cpu_type()) { + case CPU_R10000: + case CPU_R12000: + case CPU_BMIPS5000: + return true; + + default: + /* + * Presence of MAARs suggests that the CPU supports + * speculatively prefetching data, and therefore requires + * the post-DMA flush/invalidate. + */ + return cpu_has_maar; + } } static gfp_t massage_gfp_flags(const struct device *dev, gfp_t gfp) diff --git a/arch/mn10300/include/asm/processor.h b/arch/mn10300/include/asm/processor.h index 18e17abf7664..3ae479117b42 100644 --- a/arch/mn10300/include/asm/processor.h +++ b/arch/mn10300/include/asm/processor.h @@ -132,11 +132,6 @@ static inline void start_thread(struct pt_regs *regs, /* Free all resources held by a thread. */ extern void release_thread(struct task_struct *); -/* - * Return saved PC of a blocked thread. - */ -extern unsigned long thread_saved_pc(struct task_struct *tsk); - unsigned long get_wchan(struct task_struct *p); #define task_pt_regs(task) ((task)->thread.uregs) diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c index c9fa42619c6a..89e8027e07fb 100644 --- a/arch/mn10300/kernel/process.c +++ b/arch/mn10300/kernel/process.c @@ -40,14 +40,6 @@ #include "internal.h" /* - * return saved PC of a blocked thread. - */ -unsigned long thread_saved_pc(struct task_struct *tsk) -{ - return ((unsigned long *) tsk->thread.sp)[3]; -} - -/* * power off function, if any */ void (*pm_power_off)(void); diff --git a/arch/nios2/include/asm/processor.h b/arch/nios2/include/asm/processor.h index 3bbbc3d798e5..4944e2e1d8b0 100644 --- a/arch/nios2/include/asm/processor.h +++ b/arch/nios2/include/asm/processor.h @@ -75,9 +75,6 @@ static inline void release_thread(struct task_struct *dead_task) { } -/* Return saved PC of a blocked thread. */ -#define thread_saved_pc(tsk) ((tsk)->thread.kregs->ea) - extern unsigned long get_wchan(struct task_struct *p); #define task_pt_regs(p) \ diff --git a/arch/openrisc/include/asm/processor.h b/arch/openrisc/include/asm/processor.h index a908e6c30a00..396d8f306c21 100644 --- a/arch/openrisc/include/asm/processor.h +++ b/arch/openrisc/include/asm/processor.h @@ -84,11 +84,6 @@ void start_thread(struct pt_regs *regs, unsigned long nip, unsigned long sp); void release_thread(struct task_struct *); unsigned long get_wchan(struct task_struct *p); -/* - * Return saved PC of a blocked thread. For now, this is the "user" PC - */ -extern unsigned long thread_saved_pc(struct task_struct *t); - #define init_stack (init_thread_union.stack) #define cpu_relax() barrier() diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c index 106859ae27ff..f9b77003f113 100644 --- a/arch/openrisc/kernel/process.c +++ b/arch/openrisc/kernel/process.c @@ -110,11 +110,6 @@ void show_regs(struct pt_regs *regs) show_registers(regs); } -unsigned long thread_saved_pc(struct task_struct *t) -{ - return (unsigned long)user_regs(t->stack)->pc; -} - void release_thread(struct task_struct *dead_task) { } diff --git a/arch/parisc/include/asm/dma-mapping.h b/arch/parisc/include/asm/dma-mapping.h index 5404c6a726b2..9a2a8956a695 100644 --- a/arch/parisc/include/asm/dma-mapping.h +++ b/arch/parisc/include/asm/dma-mapping.h @@ -20,6 +20,8 @@ ** flush/purge and allocate "regular" cacheable pages for everything. */ +#define DMA_ERROR_CODE (~(dma_addr_t)0) + #ifdef CONFIG_PA11 extern const struct dma_map_ops pcxl_dma_ops; extern const struct dma_map_ops pcx_dma_ops; @@ -54,12 +56,13 @@ parisc_walk_tree(struct device *dev) break; } } - BUG_ON(!dev->platform_data); return dev->platform_data; } - -#define GET_IOC(dev) (HBA_DATA(parisc_walk_tree(dev))->iommu) - + +#define GET_IOC(dev) ({ \ + void *__pdata = parisc_walk_tree(dev); \ + __pdata ? HBA_DATA(__pdata)->iommu : NULL; \ +}) #ifdef CONFIG_IOMMU_CCIO struct parisc_device; diff --git a/arch/parisc/include/asm/io.h b/arch/parisc/include/asm/io.h index 1a16f1d1075f..af98254f7257 100644 --- a/arch/parisc/include/asm/io.h +++ b/arch/parisc/include/asm/io.h @@ -34,10 +34,10 @@ static inline unsigned char gsc_readb(unsigned long addr) unsigned char ret; __asm__ __volatile__( - " rsm 2,%0\n" + " rsm %3,%0\n" " ldbx 0(%2),%1\n" " mtsm %0\n" - : "=&r" (flags), "=r" (ret) : "r" (addr) ); + : "=&r" (flags), "=r" (ret) : "r" (addr), "i" (PSW_SM_D) ); return ret; } @@ -48,10 +48,10 @@ static inline unsigned short gsc_readw(unsigned long addr) unsigned short ret; __asm__ __volatile__( - " rsm 2,%0\n" + " rsm %3,%0\n" " ldhx 0(%2),%1\n" " mtsm %0\n" - : "=&r" (flags), "=r" (ret) : "r" (addr) ); + : "=&r" (flags), "=r" (ret) : "r" (addr), "i" (PSW_SM_D) ); return ret; } @@ -87,20 +87,20 @@ static inline void gsc_writeb(unsigned char val, unsigned long addr) { long flags; __asm__ __volatile__( - " rsm 2,%0\n" + " rsm %3,%0\n" " stbs %1,0(%2)\n" " mtsm %0\n" - : "=&r" (flags) : "r" (val), "r" (addr) ); + : "=&r" (flags) : "r" (val), "r" (addr), "i" (PSW_SM_D) ); } static inline void gsc_writew(unsigned short val, unsigned long addr) { long flags; __asm__ __volatile__( - " rsm 2,%0\n" + " rsm %3,%0\n" " sths %1,0(%2)\n" " mtsm %0\n" - : "=&r" (flags) : "r" (val), "r" (addr) ); + : "=&r" (flags) : "r" (val), "r" (addr), "i" (PSW_SM_D) ); } static inline void gsc_writel(unsigned int val, unsigned long addr) diff --git a/arch/parisc/include/asm/mmu_context.h b/arch/parisc/include/asm/mmu_context.h index 59be25764433..a81226257878 100644 --- a/arch/parisc/include/asm/mmu_context.h +++ b/arch/parisc/include/asm/mmu_context.h @@ -49,15 +49,26 @@ static inline void load_context(mm_context_t context) mtctl(__space_to_prot(context), 8); } -static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) +static inline void switch_mm_irqs_off(struct mm_struct *prev, + struct mm_struct *next, struct task_struct *tsk) { - if (prev != next) { mtctl(__pa(next->pgd), 25); load_context(next->context); } } +static inline void switch_mm(struct mm_struct *prev, + struct mm_struct *next, struct task_struct *tsk) +{ + unsigned long flags; + + local_irq_save(flags); + switch_mm_irqs_off(prev, next, tsk); + local_irq_restore(flags); +} +#define switch_mm_irqs_off switch_mm_irqs_off + #define deactivate_mm(tsk,mm) do { } while (0) static inline void activate_mm(struct mm_struct *prev, struct mm_struct *next) diff --git a/arch/parisc/include/asm/pdc.h b/arch/parisc/include/asm/pdc.h index 451906d78136..7569627a032b 100644 --- a/arch/parisc/include/asm/pdc.h +++ b/arch/parisc/include/asm/pdc.h @@ -6,6 +6,8 @@ #if !defined(__ASSEMBLY__) extern int pdc_type; +extern unsigned long parisc_cell_num; /* cell number the CPU runs on (PAT) */ +extern unsigned long parisc_cell_loc; /* cell location of CPU (PAT) */ /* Values for pdc_type */ #define PDC_TYPE_ILLEGAL -1 @@ -143,6 +145,18 @@ struct pdc_btlb_info { /* PDC_BLOCK_TLB, return of PDC_BTLB_INFO */ #endif /* !CONFIG_PA20 */ +struct pdc_mem_retinfo { /* PDC_MEM/PDC_MEM_MEMINFO (return info) */ + unsigned long pdt_size; + unsigned long pdt_entries; + unsigned long pdt_status; + unsigned long first_dbe_loc; + unsigned long good_mem; +}; + +struct pdc_mem_read_pdt { /* PDC_MEM/PDC_MEM_READ_PDT (return info) */ + unsigned long pdt_entries; +}; + #ifdef CONFIG_64BIT struct pdc_memory_table_raddr { /* PDC_MEM/PDC_MEM_TABLE (return info) */ unsigned long entries_returned; @@ -301,6 +315,10 @@ int pdc_get_initiator(struct hardware_path *, struct pdc_initiator *); int pdc_tod_read(struct pdc_tod *tod); int pdc_tod_set(unsigned long sec, unsigned long usec); +void pdc_pdt_init(void); /* in pdt.c */ +int pdc_mem_pdt_info(struct pdc_mem_retinfo *rinfo); +int pdc_mem_pdt_read_entries(struct pdc_mem_read_pdt *rpdt_read, + unsigned long *pdt_entries_ptr); #ifdef CONFIG_64BIT int pdc_mem_mem_table(struct pdc_memory_table_raddr *r_addr, struct pdc_memory_table *tbl, unsigned long entries); diff --git a/arch/parisc/include/asm/pdcpat.h b/arch/parisc/include/asm/pdcpat.h index e1d289092705..32e105fb8adb 100644 --- a/arch/parisc/include/asm/pdcpat.h +++ b/arch/parisc/include/asm/pdcpat.h @@ -147,9 +147,9 @@ #define PDC_PAT_MEM_CELL_CLEAR 6L /* Clear PDT For Cell */ #define PDC_PAT_MEM_CELL_READ 7L /* Read PDT entries For Cell */ #define PDC_PAT_MEM_CELL_RESET 8L /* Reset clear bit For Cell */ -#define PDC_PAT_MEM_SETGM 9L /* Set Golden Memory value */ -#define PDC_PAT_MEM_ADD_PAGE 10L /* ADDs a page to the cell */ -#define PDC_PAT_MEM_ADDRESS 11L /* Get Physical Location From */ +#define PDC_PAT_MEM_SETGM 9L /* Set Good Memory value */ +#define PDC_PAT_MEM_ADD_PAGE 10L /* ADDs a page to the cell */ +#define PDC_PAT_MEM_ADDRESS 11L /* Get Physical Location From */ /* Memory Address */ #define PDC_PAT_MEM_GET_TXT_SIZE 12L /* Get Formatted Text Size */ #define PDC_PAT_MEM_GET_PD_TXT 13L /* Get PD Formatted Text */ @@ -212,6 +212,23 @@ struct pdc_pat_cpu_num { unsigned long cpu_loc; }; +struct pdc_pat_mem_retinfo { /* PDC_PAT_MEM/PDC_PAT_MEM_PD_INFO (return info) */ + unsigned int ke; /* bit 0: memory inside good memory? */ + unsigned int current_pdt_entries:16; + unsigned int max_pdt_entries:16; + unsigned long Cs_bitmap; + unsigned long Ic_bitmap; + unsigned long good_mem; + unsigned long first_dbe_loc; /* first location of double bit error */ + unsigned long clear_time; /* last PDT clear time (since Jan 1970) */ +}; + +struct pdc_pat_mem_read_pd_retinfo { /* PDC_PAT_MEM/PDC_PAT_MEM_PD_READ */ + unsigned long actual_count_bytes; + unsigned long pdt_entries; +}; + + struct pdc_pat_pd_addr_map_entry { unsigned char entry_type; /* 1 = Memory Descriptor Entry Type */ unsigned char reserve1[5]; @@ -293,15 +310,15 @@ extern int pdc_pat_cpu_get_number(struct pdc_pat_cpu_num *cpu_info, unsigned lon extern int pdc_pat_pd_get_addr_map(unsigned long *actual_len, void *mem_addr, unsigned long count, unsigned long offset); - extern int pdc_pat_io_pci_cfg_read(unsigned long pci_addr, int pci_size, u32 *val); extern int pdc_pat_io_pci_cfg_write(unsigned long pci_addr, int pci_size, u32 val); - -/* Flag to indicate this is a PAT box...don't use this unless you -** really have to...it might go away some day. -*/ -extern int pdc_pat; /* arch/parisc/kernel/inventory.c */ +extern int pdc_pat_mem_pdt_info(struct pdc_pat_mem_retinfo *rinfo); +extern int pdc_pat_mem_read_cell_pdt(struct pdc_pat_mem_read_pd_retinfo *pret, + unsigned long *pdt_entries_ptr, unsigned long max_entries); +extern int pdc_pat_mem_read_pd_pdt(struct pdc_pat_mem_read_pd_retinfo *pret, + unsigned long *pdt_entries_ptr, unsigned long count, + unsigned long offset); #endif /* __ASSEMBLY__ */ diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index 3a4ed9f91d57..71ca86cb0f16 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -511,6 +511,9 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, #define pte_same(A,B) (pte_val(A) == pte_val(B)) +struct seq_file; +extern void arch_report_meminfo(struct seq_file *m); + #endif /* !__ASSEMBLY__ */ diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h index a3661ee6b060..b3b66c3d6f3c 100644 --- a/arch/parisc/include/asm/processor.h +++ b/arch/parisc/include/asm/processor.h @@ -103,6 +103,8 @@ struct cpuinfo_parisc { unsigned long bh_count; /* number of times bh was invoked */ unsigned long fp_rev; unsigned long fp_model; + unsigned long cpu_num; /* CPU number from PAT firmware */ + unsigned long cpu_loc; /* CPU location from PAT firmware */ unsigned int state; struct parisc_device *dev; unsigned long loops_per_jiffy; @@ -163,12 +165,7 @@ struct thread_struct { .flags = 0 \ } -/* - * Return saved PC of a blocked thread. This is used by ps mostly. - */ - struct task_struct; -unsigned long thread_saved_pc(struct task_struct *t); void show_trace(struct task_struct *task, unsigned long *stack); /* diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h index 6b113f39f30c..c3e114f67485 100644 --- a/arch/parisc/include/asm/uaccess.h +++ b/arch/parisc/include/asm/uaccess.h @@ -69,17 +69,6 @@ struct exception_table_entry { ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr + 1) /* - * The page fault handler stores, in a per-cpu area, the following information - * if a fixup routine is available. - */ -struct exception_data { - unsigned long fault_ip; - unsigned long fault_gp; - unsigned long fault_space; - unsigned long fault_addr; -}; - -/* * load_sr2() preloads the space register %%sr2 - based on the value of * get_fs() - with either a value of 0 to access kernel space (KERNEL_DS which * is 0), or with the current value of %%sr3 to access user space (USER_DS) diff --git a/arch/parisc/include/uapi/asm/pdc.h b/arch/parisc/include/uapi/asm/pdc.h index 0609ff117f67..1f30b49772aa 100644 --- a/arch/parisc/include/uapi/asm/pdc.h +++ b/arch/parisc/include/uapi/asm/pdc.h @@ -131,12 +131,12 @@ #define PDC_TLB_SETUP 1 /* set up miss handling */ #define PDC_MEM 20 /* Manage memory */ -#define PDC_MEM_MEMINFO 0 -#define PDC_MEM_ADD_PAGE 1 -#define PDC_MEM_CLEAR_PDT 2 -#define PDC_MEM_READ_PDT 3 -#define PDC_MEM_RESET_CLEAR 4 -#define PDC_MEM_GOODMEM 5 +#define PDC_MEM_MEMINFO 0 /* Return PDT info */ +#define PDC_MEM_ADD_PAGE 1 /* Add page to PDT */ +#define PDC_MEM_CLEAR_PDT 2 /* Clear PDT */ +#define PDC_MEM_READ_PDT 3 /* Read PDT entry */ +#define PDC_MEM_RESET_CLEAR 4 /* Reset PDT clear flag */ +#define PDC_MEM_GOODMEM 5 /* Set good_mem value */ #define PDC_MEM_TABLE 128 /* Non contig mem map (sprockets) */ #define PDC_MEM_RETURN_ADDRESS_TABLE PDC_MEM_TABLE #define PDC_MEM_GET_MEMORY_SYSTEM_TABLES_SIZE 131 diff --git a/arch/parisc/kernel/Makefile b/arch/parisc/kernel/Makefile index 69a11183d48d..c4294df69fb6 100644 --- a/arch/parisc/kernel/Makefile +++ b/arch/parisc/kernel/Makefile @@ -4,7 +4,7 @@ extra-y := head.o vmlinux.lds -obj-y := cache.o pacache.o setup.o traps.o time.o irq.o \ +obj-y := cache.o pacache.o setup.o pdt.o traps.o time.o irq.o \ pa7300lc.o syscall.o entry.o sys_parisc.o firmware.o \ ptrace.o hardware.o inventory.o drivers.o \ signal.o hpmc.o real2.o parisc_ksyms.o unaligned.o \ diff --git a/arch/parisc/kernel/asm-offsets.c b/arch/parisc/kernel/asm-offsets.c index 1c4fe61a592b..dfff8a0d6fd1 100644 --- a/arch/parisc/kernel/asm-offsets.c +++ b/arch/parisc/kernel/asm-offsets.c @@ -298,11 +298,6 @@ int main(void) DEFINE(HUGEPAGE_SIZE, PAGE_SIZE); #endif BLANK(); - DEFINE(EXCDATA_IP, offsetof(struct exception_data, fault_ip)); - DEFINE(EXCDATA_GP, offsetof(struct exception_data, fault_gp)); - DEFINE(EXCDATA_SPACE, offsetof(struct exception_data, fault_space)); - DEFINE(EXCDATA_ADDR, offsetof(struct exception_data, fault_addr)); - BLANK(); DEFINE(ASM_PDC_RESULT_SIZE, NUM_PDC_RESULT * sizeof(unsigned long)); BLANK(); return 0; diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c index 9d797ae4fa22..98190252c12f 100644 --- a/arch/parisc/kernel/firmware.c +++ b/arch/parisc/kernel/firmware.c @@ -957,6 +957,41 @@ int pdc_tod_read(struct pdc_tod *tod) } EXPORT_SYMBOL(pdc_tod_read); +int pdc_mem_pdt_info(struct pdc_mem_retinfo *rinfo) +{ + int retval; + unsigned long flags; + + spin_lock_irqsave(&pdc_lock, flags); + retval = mem_pdc_call(PDC_MEM, PDC_MEM_MEMINFO, __pa(pdc_result), 0); + convert_to_wide(pdc_result); + memcpy(rinfo, pdc_result, sizeof(*rinfo)); + spin_unlock_irqrestore(&pdc_lock, flags); + + return retval; +} + +int pdc_mem_pdt_read_entries(struct pdc_mem_read_pdt *pret, + unsigned long *pdt_entries_ptr) +{ + int retval; + unsigned long flags; + + spin_lock_irqsave(&pdc_lock, flags); + retval = mem_pdc_call(PDC_MEM, PDC_MEM_READ_PDT, __pa(pdc_result), + __pa(pdc_result2)); + if (retval == PDC_OK) { + convert_to_wide(pdc_result); + memcpy(pret, pdc_result, sizeof(*pret)); + convert_to_wide(pdc_result2); + memcpy(pdt_entries_ptr, pdc_result2, + pret->pdt_entries * sizeof(*pdt_entries_ptr)); + } + spin_unlock_irqrestore(&pdc_lock, flags); + + return retval; +} + /** * pdc_tod_set - Set the Time-Of-Day clock. * @sec: The number of seconds since epoch. @@ -1383,6 +1418,79 @@ int pdc_pat_io_pci_cfg_write(unsigned long pci_addr, int pci_size, u32 val) return retval; } + +/** + * pdc_pat_mem_pdc_info - Retrieve information about page deallocation table + * @rinfo: memory pdt information + * + */ +int pdc_pat_mem_pdt_info(struct pdc_pat_mem_retinfo *rinfo) +{ + int retval; + unsigned long flags; + + spin_lock_irqsave(&pdc_lock, flags); + retval = mem_pdc_call(PDC_PAT_MEM, PDC_PAT_MEM_PD_INFO, + __pa(&pdc_result)); + if (retval == PDC_OK) + memcpy(rinfo, &pdc_result, sizeof(*rinfo)); + spin_unlock_irqrestore(&pdc_lock, flags); + + return retval; +} + +/** + * pdc_pat_mem_read_cell_pdt - Read PDT entries from (old) PAT firmware + * @pret: array of PDT entries + * @pdt_entries_ptr: ptr to hold number of PDT entries + * @max_entries: maximum number of entries to be read + * + */ +int pdc_pat_mem_read_cell_pdt(struct pdc_pat_mem_read_pd_retinfo *pret, + unsigned long *pdt_entries_ptr, unsigned long max_entries) +{ + int retval; + unsigned long flags, entries; + + spin_lock_irqsave(&pdc_lock, flags); + /* PDC_PAT_MEM_CELL_READ is available on early PAT machines only */ + retval = mem_pdc_call(PDC_PAT_MEM, PDC_PAT_MEM_CELL_READ, + __pa(&pdc_result), parisc_cell_num, __pa(&pdc_result2)); + + if (retval == PDC_OK) { + /* build up return value as for PDC_PAT_MEM_PD_READ */ + entries = min(pdc_result[0], max_entries); + pret->pdt_entries = entries; + pret->actual_count_bytes = entries * sizeof(unsigned long); + memcpy(pdt_entries_ptr, &pdc_result2, pret->actual_count_bytes); + } + + spin_unlock_irqrestore(&pdc_lock, flags); + WARN_ON(retval == PDC_OK && pdc_result[0] > max_entries); + + return retval; +} +/** + * pdc_pat_mem_read_pd_pdt - Read PDT entries from (newer) PAT firmware + * @pret: array of PDT entries + * @pdt_entries_ptr: ptr to hold number of PDT entries + * + */ +int pdc_pat_mem_read_pd_pdt(struct pdc_pat_mem_read_pd_retinfo *pret, + unsigned long *pdt_entries_ptr, unsigned long count, + unsigned long offset) +{ + int retval; + unsigned long flags; + + spin_lock_irqsave(&pdc_lock, flags); + retval = mem_pdc_call(PDC_PAT_MEM, PDC_PAT_MEM_PD_READ, + __pa(&pret), __pa(pdt_entries_ptr), + count, offset); + spin_unlock_irqrestore(&pdc_lock, flags); + + return retval; +} #endif /* CONFIG_64BIT */ diff --git a/arch/parisc/kernel/hpmc.S b/arch/parisc/kernel/hpmc.S index 0fbd0a0e1cda..e3a8e5e4d5de 100644 --- a/arch/parisc/kernel/hpmc.S +++ b/arch/parisc/kernel/hpmc.S @@ -44,6 +44,7 @@ #include <asm/assembly.h> #include <asm/pdc.h> +#include <asm/psw.h> #include <linux/linkage.h> #include <linux/init.h> @@ -135,7 +136,7 @@ ENTRY_CFI(os_hpmc) * So turn on the Q bit and turn off the M bit. */ - ldo 8(%r0),%r4 /* PSW Q on, PSW M off */ + ldi PSW_SM_Q,%r4 /* PSW Q on, PSW M off */ mtctl %r4,ipsw mtctl %r0,pcsq mtctl %r0,pcsq @@ -257,7 +258,7 @@ os_hpmc_5: tovirt_r1 %r30 /* make sp virtual */ - rsm 8,%r0 /* Clear Q bit */ + rsm PSW_SM_Q,%r0 /* Clear Q bit */ ldi 1,%r8 /* Set trap code to "1" for HPMC */ load32 PA(intr_save),%r1 be 0(%sr7,%r1) diff --git a/arch/parisc/kernel/inventory.c b/arch/parisc/kernel/inventory.c index c9789d9c73b4..b0fe19ac4d78 100644 --- a/arch/parisc/kernel/inventory.c +++ b/arch/parisc/kernel/inventory.c @@ -40,6 +40,11 @@ int pdc_type __read_mostly = PDC_TYPE_ILLEGAL; +/* cell number and location (PAT firmware only) */ +unsigned long parisc_cell_num __read_mostly; +unsigned long parisc_cell_loc __read_mostly; + + void __init setup_pdc(void) { long status; @@ -78,6 +83,10 @@ void __init setup_pdc(void) if (status == PDC_OK) { pdc_type = PDC_TYPE_PAT; pr_cont("64 bit PAT.\n"); + parisc_cell_num = cell_info.cell_num; + parisc_cell_loc = cell_info.cell_loc; + pr_info("PAT: Running on cell %lu and location %lu.\n", + parisc_cell_num, parisc_cell_loc); return; } #endif diff --git a/arch/parisc/kernel/pdt.c b/arch/parisc/kernel/pdt.c new file mode 100644 index 000000000000..f3a797e670b0 --- /dev/null +++ b/arch/parisc/kernel/pdt.c @@ -0,0 +1,143 @@ +/* + * Page Deallocation Table (PDT) support + * + * The Page Deallocation Table (PDT) holds a table with pointers to bad + * memory (broken RAM modules) which is maintained by firmware. + * + * Copyright 2017 by Helge Deller <deller@gmx.de> + * + * TODO: + * - check regularily for new bad memory + * - add userspace interface with procfs or sysfs + * - increase number of PDT entries dynamically + */ + +#include <linux/memblock.h> +#include <linux/seq_file.h> + +#include <asm/pdc.h> +#include <asm/pdcpat.h> +#include <asm/sections.h> +#include <asm/pgtable.h> + +enum pdt_access_type { + PDT_NONE, + PDT_PDC, + PDT_PAT_NEW, + PDT_PAT_OLD +}; + +static enum pdt_access_type pdt_type; + +/* global PDT status information */ +static struct pdc_mem_retinfo pdt_status; + +#define MAX_PDT_TABLE_SIZE PAGE_SIZE +#define MAX_PDT_ENTRIES (MAX_PDT_TABLE_SIZE / sizeof(unsigned long)) +static unsigned long pdt_entry[MAX_PDT_ENTRIES] __page_aligned_bss; + + +/* report PDT entries via /proc/meminfo */ +void arch_report_meminfo(struct seq_file *m) +{ + if (pdt_type == PDT_NONE) + return; + + seq_printf(m, "PDT_max_entries: %7lu\n", + pdt_status.pdt_size); + seq_printf(m, "PDT_cur_entries: %7lu\n", + pdt_status.pdt_entries); +} + +/* + * pdc_pdt_init() + * + * Initialize kernel PDT structures, read initial PDT table from firmware, + * report all current PDT entries and mark bad memory with memblock_reserve() + * to avoid that the kernel will use broken memory areas. + * + */ +void __init pdc_pdt_init(void) +{ + int ret, i; + unsigned long entries; + struct pdc_mem_read_pdt pdt_read_ret; + + if (is_pdc_pat()) { + struct pdc_pat_mem_retinfo pat_rinfo; + + pdt_type = PDT_PAT_NEW; + ret = pdc_pat_mem_pdt_info(&pat_rinfo); + pdt_status.pdt_size = pat_rinfo.max_pdt_entries; + pdt_status.pdt_entries = pat_rinfo.current_pdt_entries; + pdt_status.pdt_status = 0; + pdt_status.first_dbe_loc = pat_rinfo.first_dbe_loc; + pdt_status.good_mem = pat_rinfo.good_mem; + } else { + pdt_type = PDT_PDC; + ret = pdc_mem_pdt_info(&pdt_status); + } + + if (ret != PDC_OK) { + pdt_type = PDT_NONE; + pr_info("PDT: Firmware does not provide any page deallocation" + " information.\n"); + return; + } + + entries = pdt_status.pdt_entries; + WARN_ON(entries > MAX_PDT_ENTRIES); + + pr_info("PDT: size %lu, entries %lu, status %lu, dbe_loc 0x%lx," + " good_mem %lu\n", + pdt_status.pdt_size, pdt_status.pdt_entries, + pdt_status.pdt_status, pdt_status.first_dbe_loc, + pdt_status.good_mem); + + if (entries == 0) { + pr_info("PDT: Firmware reports all memory OK.\n"); + return; + } + + if (pdt_status.first_dbe_loc && + pdt_status.first_dbe_loc <= __pa((unsigned long)&_end)) + pr_crit("CRITICAL: Bad memory inside kernel image memory area!\n"); + + pr_warn("PDT: Firmware reports %lu entries of faulty memory:\n", + entries); + + if (pdt_type == PDT_PDC) + ret = pdc_mem_pdt_read_entries(&pdt_read_ret, pdt_entry); + else { +#ifdef CONFIG_64BIT + struct pdc_pat_mem_read_pd_retinfo pat_pret; + + ret = pdc_pat_mem_read_cell_pdt(&pat_pret, pdt_entry, + MAX_PDT_ENTRIES); + if (ret != PDC_OK) { + pdt_type = PDT_PAT_OLD; + ret = pdc_pat_mem_read_pd_pdt(&pat_pret, pdt_entry, + MAX_PDT_TABLE_SIZE, 0); + } +#else + ret = PDC_BAD_PROC; +#endif + } + + if (ret != PDC_OK) { + pdt_type = PDT_NONE; + pr_debug("PDT type %d, retval = %d\n", pdt_type, ret); + return; + } + + for (i = 0; i < pdt_status.pdt_entries; i++) { + if (i < 20) + pr_warn("PDT: BAD PAGE #%d at 0x%08lx (error_type = %lu)\n", + i, + pdt_entry[i] & PAGE_MASK, + pdt_entry[i] & 1); + + /* mark memory page bad */ + memblock_reserve(pdt_entry[i] & PAGE_MASK, PAGE_SIZE); + } +} diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 4516a5b53f38..b64d7d21646e 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -239,11 +239,6 @@ copy_thread(unsigned long clone_flags, unsigned long usp, return 0; } -unsigned long thread_saved_pc(struct task_struct *t) -{ - return t->thread.regs.kpc; -} - unsigned long get_wchan(struct task_struct *p) { diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c index 85de47f4eb59..0ab32779dfa7 100644 --- a/arch/parisc/kernel/processor.c +++ b/arch/parisc/kernel/processor.c @@ -94,7 +94,7 @@ static int processor_probe(struct parisc_device *dev) unsigned long txn_addr; unsigned long cpuid; struct cpuinfo_parisc *p; - struct pdc_pat_cpu_num cpu_info __maybe_unused; + struct pdc_pat_cpu_num cpu_info = { }; #ifdef CONFIG_SMP if (num_online_cpus() >= nr_cpu_ids) { @@ -113,6 +113,7 @@ static int processor_probe(struct parisc_device *dev) */ cpuid = boot_cpu_data.cpu_count; txn_addr = dev->hpa.start; /* for legacy PDC */ + cpu_info.cpu_num = cpu_info.cpu_loc = cpuid; #ifdef CONFIG_64BIT if (is_pdc_pat()) { @@ -180,6 +181,8 @@ static int processor_probe(struct parisc_device *dev) p->hpa = dev->hpa.start; /* save CPU hpa */ p->cpuid = cpuid; /* save CPU id */ p->txn_addr = txn_addr; /* save CPU IRQ address */ + p->cpu_num = cpu_info.cpu_num; + p->cpu_loc = cpu_info.cpu_loc; #ifdef CONFIG_SMP /* ** FIXME: review if any other initialization is clobbered diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S index 44aeaa9c039f..6308749359e4 100644 --- a/arch/parisc/kernel/syscall_table.S +++ b/arch/parisc/kernel/syscall_table.S @@ -361,7 +361,7 @@ ENTRY_SAME(ni_syscall) /* 263: reserved for vserver */ ENTRY_SAME(add_key) ENTRY_SAME(request_key) /* 265 */ - ENTRY_SAME(keyctl) + ENTRY_COMP(keyctl) ENTRY_SAME(ioprio_set) ENTRY_SAME(ioprio_get) ENTRY_SAME(inotify_init) diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c index 89421df70160..2d956aa0a38a 100644 --- a/arch/parisc/kernel/time.c +++ b/arch/parisc/kernel/time.c @@ -243,14 +243,30 @@ void __init time_init(void) static int __init init_cr16_clocksource(void) { /* - * The cr16 interval timers are not syncronized across CPUs, so mark - * them unstable and lower rating on SMP systems. + * The cr16 interval timers are not syncronized across CPUs on + * different sockets, so mark them unstable and lower rating on + * multi-socket SMP systems. */ if (num_online_cpus() > 1) { - clocksource_cr16.flags = CLOCK_SOURCE_UNSTABLE; - clocksource_cr16.rating = 0; + int cpu; + unsigned long cpu0_loc; + cpu0_loc = per_cpu(cpu_data, 0).cpu_loc; + + for_each_online_cpu(cpu) { + if (cpu0_loc == per_cpu(cpu_data, cpu).cpu_loc) + continue; + + clocksource_cr16.name = "cr16_unstable"; + clocksource_cr16.flags = CLOCK_SOURCE_UNSTABLE; + clocksource_cr16.rating = 0; + break; + } } + /* XXX: We may want to mark sched_clock stable here if cr16 clocks are + * in sync: + * (clocksource_cr16.flags == CLOCK_SOURCE_IS_CONTINUOUS) */ + /* register at clocksource framework */ clocksource_register_hz(&clocksource_cr16, 100 * PAGE0->mem_10msec); diff --git a/arch/parisc/lib/lusercopy.S b/arch/parisc/lib/lusercopy.S index 85c28bb80fb7..d4fe19806d57 100644 --- a/arch/parisc/lib/lusercopy.S +++ b/arch/parisc/lib/lusercopy.S @@ -56,12 +56,6 @@ mtsp %r1,%sr1 .endm - .macro fixup_branch lbl - ldil L%\lbl, %r1 - ldo R%\lbl(%r1), %r1 - bv %r0(%r1) - .endm - /* * unsigned long lclear_user(void *to, unsigned long n) * @@ -82,16 +76,16 @@ $lclu_loop: $lclu_done: bv %r0(%r2) copy %r25,%r28 - .exit -ENDPROC_CFI(lclear_user) - .section .fixup,"ax" -2: fixup_branch $lclu_done - ldo 1(%r25),%r25 - .previous +2: b $lclu_done + ldo 1(%r25),%r25 ASM_EXCEPTIONTABLE_ENTRY(1b,2b) + .exit +ENDPROC_CFI(lclear_user) + + .procend /* @@ -122,16 +116,15 @@ $lslen_done: $lslen_nzero: b $lslen_done ldo 1(%r26),%r26 /* special case for N == 0 */ -ENDPROC_CFI(lstrnlen_user) - .section .fixup,"ax" -3: fixup_branch $lslen_done +3: b $lslen_done copy %r24,%r26 /* reset r26 so 0 is returned on fault */ - .previous ASM_EXCEPTIONTABLE_ENTRY(1b,3b) ASM_EXCEPTIONTABLE_ENTRY(2b,3b) +ENDPROC_CFI(lstrnlen_user) + .procend diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index 32ec22146141..5b101f6a5607 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -29,8 +29,6 @@ #define BITSSET 0x1c0 /* for identifying LDCW */ -DEFINE_PER_CPU(struct exception_data, exception_data); - int show_unhandled_signals = 1; /* @@ -143,13 +141,6 @@ int fixup_exception(struct pt_regs *regs) fix = search_exception_tables(regs->iaoq[0]); if (fix) { - struct exception_data *d; - d = this_cpu_ptr(&exception_data); - d->fault_ip = regs->iaoq[0]; - d->fault_gp = regs->gr[27]; - d->fault_space = regs->isr; - d->fault_addr = regs->ior; - /* * Fix up get_user() and put_user(). * ASM_EXCEPTIONTABLE_ENTRY_EFAULT() sets the least-significant @@ -163,6 +154,7 @@ int fixup_exception(struct pt_regs *regs) /* zero target register for get_user() */ if (parisc_acctyp(0, regs->iir) == VM_READ) { int treg = regs->iir & 0x1f; + BUG_ON(treg == 0); regs->gr[treg] = 0; } } @@ -367,7 +359,7 @@ bad_area: case 15: /* Data TLB miss fault/Data page fault */ /* send SIGSEGV when outside of vma */ if (!vma || - address < vma->vm_start || address > vma->vm_end) { + address < vma->vm_start || address >= vma->vm_end) { si.si_signo = SIGSEGV; si.si_code = SEGV_MAPERR; break; diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index 66f3a6345105..1ca9a2b4239f 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -381,6 +381,9 @@ static void __init setup_bootmem(void) request_resource(res, &data_resource); } request_resource(&sysram_resources[0], &pdcdata_resource); + + /* Initialize Page Deallocation Table (PDT) and check for bad memory. */ + pdc_pdt_init(); } static int __init parisc_text_address(unsigned long vaddr) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index bf4391d18923..6189238e69f8 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -184,7 +184,7 @@ config PPC select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER select HAVE_GCC_PLUGINS - select HAVE_GENERIC_RCU_GUP + select HAVE_GENERIC_GUP select HAVE_HW_BREAKPOINT if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx) select HAVE_IDE select HAVE_IOREMAP_PROT diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h index a83821f33ea3..8814a7249ceb 100644 --- a/arch/powerpc/include/asm/kprobes.h +++ b/arch/powerpc/include/asm/kprobes.h @@ -103,6 +103,7 @@ extern int kprobe_exceptions_notify(struct notifier_block *self, extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr); extern int kprobe_handler(struct pt_regs *regs); extern int kprobe_post_handler(struct pt_regs *regs); +extern int is_current_kprobe_addr(unsigned long addr); #ifdef CONFIG_KPROBES_ON_FTRACE extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb); diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index bb99b651085a..1189d04f3bd1 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -378,12 +378,6 @@ struct thread_struct { } #endif -/* - * Return saved PC of a blocked thread. For now, this is the "user" PC - */ -#define thread_saved_pc(tsk) \ - ((tsk)->thread.regs? (tsk)->thread.regs->nip: 0) - #define task_pt_regs(tsk) ((struct pt_regs *)(tsk)->thread.regs) unsigned long get_wchan(struct task_struct *p); diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 5c0d8a8cdae5..41e88d3ce36b 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -267,13 +267,7 @@ do { \ extern unsigned long __copy_tofrom_user(void __user *to, const void __user *from, unsigned long size); -#ifndef __powerpc64__ - -#define INLINE_COPY_FROM_USER -#define INLINE_COPY_TO_USER - -#else /* __powerpc64__ */ - +#ifdef __powerpc64__ static inline unsigned long raw_copy_in_user(void __user *to, const void __user *from, unsigned long n) { diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index ae418b85c17c..b886795060fd 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1411,10 +1411,8 @@ USE_TEXT_SECTION() .balign IFETCH_ALIGN_BYTES do_hash_page: #ifdef CONFIG_PPC_STD_MMU_64 - andis. r0,r4,0xa410 /* weird error? */ + andis. r0,r4,0xa450 /* weird error? */ bne- handle_page_fault /* if not, try to insert a HPTE */ - andis. r0,r4,DSISR_DABRMATCH@h - bne- handle_dabr_fault CURRENT_THREAD_INFO(r11, r1) lwz r0,TI_PREEMPT(r11) /* If we're in an "NMI" */ andis. r0,r0,NMI_MASK@h /* (i.e. an irq when soft-disabled) */ @@ -1438,11 +1436,16 @@ do_hash_page: /* Error */ blt- 13f + + /* Reload DSISR into r4 for the DABR check below */ + ld r4,_DSISR(r1) #endif /* CONFIG_PPC_STD_MMU_64 */ /* Here we have a page fault that hash_page can't handle. */ handle_page_fault: -11: ld r4,_DAR(r1) +11: andis. r0,r4,DSISR_DABRMATCH@h + bne- handle_dabr_fault + ld r4,_DAR(r1) ld r5,_DSISR(r1) addi r3,r1,STACK_FRAME_OVERHEAD bl do_page_fault diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index fc4343514bed..01addfb0ed0a 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -43,6 +43,12 @@ DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); struct kretprobe_blackpoint kretprobe_blacklist[] = {{NULL, NULL}}; +int is_current_kprobe_addr(unsigned long addr) +{ + struct kprobe *p = kprobe_running(); + return (p && (unsigned long)p->addr == addr) ? 1 : 0; +} + bool arch_within_kprobe_blacklist(unsigned long addr) { return (addr >= (unsigned long)__kprobes_text_start && @@ -617,6 +623,15 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) regs->gpr[2] = (unsigned long)(((func_descr_t *)jp->entry)->toc); #endif + /* + * jprobes use jprobe_return() which skips the normal return + * path of the function, and this messes up the accounting of the + * function graph tracer. + * + * Pause function graph tracing while performing the jprobe function. + */ + pause_graph_tracing(); + return 1; } NOKPROBE_SYMBOL(setjmp_pre_handler); @@ -642,6 +657,8 @@ int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) * saved regs... */ memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs)); + /* It's OK to start function graph tracing again */ + unpause_graph_tracing(); preempt_enable_no_resched(); return 1; } diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index a8c1f99e9607..4640f6d64f8b 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -616,6 +616,24 @@ void __init exc_lvl_early_init(void) #endif /* + * Emergency stacks are used for a range of things, from asynchronous + * NMIs (system reset, machine check) to synchronous, process context. + * We set preempt_count to zero, even though that isn't necessarily correct. To + * get the right value we'd need to copy it from the previous thread_info, but + * doing that might fault causing more problems. + * TODO: what to do with accounting? + */ +static void emerg_stack_init_thread_info(struct thread_info *ti, int cpu) +{ + ti->task = NULL; + ti->cpu = cpu; + ti->preempt_count = 0; + ti->local_flags = 0; + ti->flags = 0; + klp_init_thread_info(ti); +} + +/* * Stack space used when we detect a bad kernel stack pointer, and * early in SMP boots before relocation is enabled. Exclusive emergency * stack for machine checks. @@ -633,24 +651,31 @@ void __init emergency_stack_init(void) * Since we use these as temporary stacks during secondary CPU * bringup, we need to get at them in real mode. This means they * must also be within the RMO region. + * + * The IRQ stacks allocated elsewhere in this file are zeroed and + * initialized in kernel/irq.c. These are initialized here in order + * to have emergency stacks available as early as possible. */ limit = min(safe_stack_limit(), ppc64_rma_size); for_each_possible_cpu(i) { struct thread_info *ti; ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit)); - klp_init_thread_info(ti); + memset(ti, 0, THREAD_SIZE); + emerg_stack_init_thread_info(ti, i); paca[i].emergency_sp = (void *)ti + THREAD_SIZE; #ifdef CONFIG_PPC_BOOK3S_64 /* emergency stack for NMI exception handling. */ ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit)); - klp_init_thread_info(ti); + memset(ti, 0, THREAD_SIZE); + emerg_stack_init_thread_info(ti, i); paca[i].nmi_emergency_sp = (void *)ti + THREAD_SIZE; /* emergency stack for machine check exception handling. */ ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit)); - klp_init_thread_info(ti); + memset(ti, 0, THREAD_SIZE); + emerg_stack_init_thread_info(ti, i); paca[i].mc_emergency_sp = (void *)ti + THREAD_SIZE; #endif } diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index df2a41647d8e..1069f74fca47 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -97,7 +97,7 @@ int smp_generic_cpu_bootable(unsigned int nr) /* Special case - we inhibit secondary thread startup * during boot if the user requests it. */ - if (system_state == SYSTEM_BOOTING && cpu_has_feature(CPU_FTR_SMT)) { + if (system_state < SYSTEM_RUNNING && cpu_has_feature(CPU_FTR_SMT)) { if (!smt_enabled_at_boot && cpu_thread_in_core(nr) != 0) return 0; if (smt_enabled_at_boot diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S index 7c933a99f5d5..c98e90b4ea7b 100644 --- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S +++ b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S @@ -45,10 +45,14 @@ _GLOBAL(ftrace_caller) stdu r1,-SWITCH_FRAME_SIZE(r1) /* Save all gprs to pt_regs */ - SAVE_8GPRS(0,r1) - SAVE_8GPRS(8,r1) - SAVE_8GPRS(16,r1) - SAVE_8GPRS(24,r1) + SAVE_GPR(0, r1) + SAVE_10GPRS(2, r1) + SAVE_10GPRS(12, r1) + SAVE_10GPRS(22, r1) + + /* Save previous stack pointer (r1) */ + addi r8, r1, SWITCH_FRAME_SIZE + std r8, GPR1(r1) /* Load special regs for save below */ mfmsr r8 @@ -95,18 +99,44 @@ ftrace_call: bl ftrace_stub nop - /* Load ctr with the possibly modified NIP */ - ld r3, _NIP(r1) - mtctr r3 + /* Load the possibly modified NIP */ + ld r15, _NIP(r1) + #ifdef CONFIG_LIVEPATCH - cmpd r14,r3 /* has NIP been altered? */ + cmpd r14, r15 /* has NIP been altered? */ +#endif + +#if defined(CONFIG_LIVEPATCH) && defined(CONFIG_KPROBES_ON_FTRACE) + /* NIP has not been altered, skip over further checks */ + beq 1f + + /* Check if there is an active kprobe on us */ + subi r3, r14, 4 + bl is_current_kprobe_addr + nop + + /* + * If r3 == 1, then this is a kprobe/jprobe. + * else, this is livepatched function. + * + * The conditional branch for livepatch_handler below will use the + * result of this comparison. For kprobe/jprobe, we just need to branch to + * the new NIP, not call livepatch_handler. The branch below is bne, so we + * want CR0[EQ] to be true if this is a kprobe/jprobe. Which means we want + * CR0[EQ] = (r3 == 1). + */ + cmpdi r3, 1 +1: #endif + /* Load CTR with the possibly modified NIP */ + mtctr r15 + /* Restore gprs */ - REST_8GPRS(0,r1) - REST_8GPRS(8,r1) - REST_8GPRS(16,r1) - REST_8GPRS(24,r1) + REST_GPR(0,r1) + REST_10GPRS(2,r1) + REST_10GPRS(12,r1) + REST_10GPRS(22,r1) /* Restore possibly modified LR */ ld r0, _LINK(r1) @@ -119,7 +149,10 @@ ftrace_call: addi r1, r1, SWITCH_FRAME_SIZE #ifdef CONFIG_LIVEPATCH - /* Based on the cmpd above, if the NIP was altered handle livepatch */ + /* + * Based on the cmpd or cmpdi above, if the NIP was altered and we're + * not on a kprobe/jprobe, then handle livepatch. + */ bne- livepatch_handler #endif diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 42b7a4fd57d9..8d1a365b8edc 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -1486,6 +1486,14 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, r = set_vpa(vcpu, &vcpu->arch.dtl, addr, len); break; case KVM_REG_PPC_TB_OFFSET: + /* + * POWER9 DD1 has an erratum where writing TBU40 causes + * the timebase to lose ticks. So we don't let the + * timebase offset be changed on P9 DD1. (It is + * initialized to zero.) + */ + if (cpu_has_feature(CPU_FTR_POWER9_DD1)) + break; /* round up to multiple of 2^24 */ vcpu->arch.vcore->tb_offset = ALIGN(set_reg_val(id, *val), 1UL << 24); @@ -2907,12 +2915,36 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu) { int r; int srcu_idx; + unsigned long ebb_regs[3] = {}; /* shut up GCC */ + unsigned long user_tar = 0; + unsigned int user_vrsave; if (!vcpu->arch.sane) { run->exit_reason = KVM_EXIT_INTERNAL_ERROR; return -EINVAL; } + /* + * Don't allow entry with a suspended transaction, because + * the guest entry/exit code will lose it. + * If the guest has TM enabled, save away their TM-related SPRs + * (they will get restored by the TM unavailable interrupt). + */ +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (cpu_has_feature(CPU_FTR_TM) && current->thread.regs && + (current->thread.regs->msr & MSR_TM)) { + if (MSR_TM_ACTIVE(current->thread.regs->msr)) { + run->exit_reason = KVM_EXIT_FAIL_ENTRY; + run->fail_entry.hardware_entry_failure_reason = 0; + return -EINVAL; + } + current->thread.tm_tfhar = mfspr(SPRN_TFHAR); + current->thread.tm_tfiar = mfspr(SPRN_TFIAR); + current->thread.tm_texasr = mfspr(SPRN_TEXASR); + current->thread.regs->msr &= ~MSR_TM; + } +#endif + kvmppc_core_prepare_to_enter(vcpu); /* No need to go into the guest when all we'll do is come back out */ @@ -2934,6 +2966,15 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu) flush_all_to_thread(current); + /* Save userspace EBB and other register values */ + if (cpu_has_feature(CPU_FTR_ARCH_207S)) { + ebb_regs[0] = mfspr(SPRN_EBBHR); + ebb_regs[1] = mfspr(SPRN_EBBRR); + ebb_regs[2] = mfspr(SPRN_BESCR); + user_tar = mfspr(SPRN_TAR); + } + user_vrsave = mfspr(SPRN_VRSAVE); + vcpu->arch.wqp = &vcpu->arch.vcore->wq; vcpu->arch.pgdir = current->mm->pgd; vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST; @@ -2960,6 +3001,16 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu) } } while (is_kvmppc_resume_guest(r)); + /* Restore userspace EBB and other register values */ + if (cpu_has_feature(CPU_FTR_ARCH_207S)) { + mtspr(SPRN_EBBHR, ebb_regs[0]); + mtspr(SPRN_EBBRR, ebb_regs[1]); + mtspr(SPRN_BESCR, ebb_regs[2]); + mtspr(SPRN_TAR, user_tar); + mtspr(SPRN_FSCR, current->thread.fscr); + } + mtspr(SPRN_VRSAVE, user_vrsave); + out: vcpu->arch.state = KVMPPC_VCPU_NOTREADY; atomic_dec(&vcpu->kvm->arch.vcpus_running); diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S index 0fdc4a28970b..404deb512844 100644 --- a/arch/powerpc/kvm/book3s_hv_interrupts.S +++ b/arch/powerpc/kvm/book3s_hv_interrupts.S @@ -121,10 +121,20 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) * Put whatever is in the decrementer into the * hypervisor decrementer. */ +BEGIN_FTR_SECTION + ld r5, HSTATE_KVM_VCORE(r13) + ld r6, VCORE_KVM(r5) + ld r9, KVM_HOST_LPCR(r6) + andis. r9, r9, LPCR_LD@h +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) mfspr r8,SPRN_DEC mftb r7 - mtspr SPRN_HDEC,r8 +BEGIN_FTR_SECTION + /* On POWER9, don't sign-extend if host LPCR[LD] bit is set */ + bne 32f +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) extsw r8,r8 +32: mtspr SPRN_HDEC,r8 add r8,r8,r7 std r8,HSTATE_DECEXP(r13) diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index bdb3f76ceb6b..4888dd494604 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -32,12 +32,29 @@ #include <asm/opal.h> #include <asm/xive-regs.h> +/* Sign-extend HDEC if not on POWER9 */ +#define EXTEND_HDEC(reg) \ +BEGIN_FTR_SECTION; \ + extsw reg, reg; \ +END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300) + #define VCPU_GPRS_TM(reg) (((reg) * ULONG_SIZE) + VCPU_GPR_TM) /* Values in HSTATE_NAPPING(r13) */ #define NAPPING_CEDE 1 #define NAPPING_NOVCPU 2 +/* Stack frame offsets for kvmppc_hv_entry */ +#define SFS 144 +#define STACK_SLOT_TRAP (SFS-4) +#define STACK_SLOT_TID (SFS-16) +#define STACK_SLOT_PSSCR (SFS-24) +#define STACK_SLOT_PID (SFS-32) +#define STACK_SLOT_IAMR (SFS-40) +#define STACK_SLOT_CIABR (SFS-48) +#define STACK_SLOT_DAWR (SFS-56) +#define STACK_SLOT_DAWRX (SFS-64) + /* * Call kvmppc_hv_entry in real mode. * Must be called with interrupts hard-disabled. @@ -214,6 +231,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) kvmppc_primary_no_guest: /* We handle this much like a ceded vcpu */ /* put the HDEC into the DEC, since HDEC interrupts don't wake us */ + /* HDEC may be larger than DEC for arch >= v3.00, but since the */ + /* HDEC value came from DEC in the first place, it will fit */ mfspr r3, SPRN_HDEC mtspr SPRN_DEC, r3 /* @@ -295,8 +314,9 @@ kvm_novcpu_wakeup: /* See if our timeslice has expired (HDEC is negative) */ mfspr r0, SPRN_HDEC + EXTEND_HDEC(r0) li r12, BOOK3S_INTERRUPT_HV_DECREMENTER - cmpwi r0, 0 + cmpdi r0, 0 blt kvm_novcpu_exit /* Got an IPI but other vcpus aren't yet exiting, must be a latecomer */ @@ -319,10 +339,10 @@ kvm_novcpu_exit: bl kvmhv_accumulate_time #endif 13: mr r3, r12 - stw r12, 112-4(r1) + stw r12, STACK_SLOT_TRAP(r1) bl kvmhv_commence_exit nop - lwz r12, 112-4(r1) + lwz r12, STACK_SLOT_TRAP(r1) b kvmhv_switch_to_host /* @@ -390,8 +410,8 @@ kvm_secondary_got_guest: lbz r4, HSTATE_PTID(r13) cmpwi r4, 0 bne 63f - lis r6, 0x7fff - ori r6, r6, 0xffff + LOAD_REG_ADDR(r6, decrementer_max) + ld r6, 0(r6) mtspr SPRN_HDEC, r6 /* and set per-LPAR registers, if doing dynamic micro-threading */ ld r6, HSTATE_SPLIT_MODE(r13) @@ -545,11 +565,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) * * *****************************************************************************/ -/* Stack frame offsets */ -#define STACK_SLOT_TID (112-16) -#define STACK_SLOT_PSSCR (112-24) -#define STACK_SLOT_PID (112-32) - .global kvmppc_hv_entry kvmppc_hv_entry: @@ -565,7 +580,7 @@ kvmppc_hv_entry: */ mflr r0 std r0, PPC_LR_STKOFF(r1) - stdu r1, -112(r1) + stdu r1, -SFS(r1) /* Save R1 in the PACA */ std r1, HSTATE_HOST_R1(r13) @@ -749,10 +764,20 @@ BEGIN_FTR_SECTION mfspr r5, SPRN_TIDR mfspr r6, SPRN_PSSCR mfspr r7, SPRN_PID + mfspr r8, SPRN_IAMR std r5, STACK_SLOT_TID(r1) std r6, STACK_SLOT_PSSCR(r1) std r7, STACK_SLOT_PID(r1) + std r8, STACK_SLOT_IAMR(r1) END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) +BEGIN_FTR_SECTION + mfspr r5, SPRN_CIABR + mfspr r6, SPRN_DAWR + mfspr r7, SPRN_DAWRX + std r5, STACK_SLOT_CIABR(r1) + std r6, STACK_SLOT_DAWR(r1) + std r7, STACK_SLOT_DAWRX(r1) +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) BEGIN_FTR_SECTION /* Set partition DABR */ @@ -968,7 +993,8 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300) /* Check if HDEC expires soon */ mfspr r3, SPRN_HDEC - cmpwi r3, 512 /* 1 microsecond */ + EXTEND_HDEC(r3) + cmpdi r3, 512 /* 1 microsecond */ blt hdec_soon #ifdef CONFIG_KVM_XICS @@ -1505,11 +1531,10 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300) * set by the guest could disrupt the host. */ li r0, 0 - mtspr SPRN_IAMR, r0 - mtspr SPRN_CIABR, r0 - mtspr SPRN_DAWRX, r0 + mtspr SPRN_PSPB, r0 mtspr SPRN_WORT, r0 BEGIN_FTR_SECTION + mtspr SPRN_IAMR, r0 mtspr SPRN_TCSCR, r0 /* Set MMCRS to 1<<31 to freeze and disable the SPMC counters */ li r0, 1 @@ -1525,6 +1550,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300) std r6,VCPU_UAMOR(r9) li r6,0 mtspr SPRN_AMR,r6 + mtspr SPRN_UAMOR, r6 /* Switch DSCR back to host value */ mfspr r8, SPRN_DSCR @@ -1670,12 +1696,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) /* Restore host values of some registers */ BEGIN_FTR_SECTION + ld r5, STACK_SLOT_CIABR(r1) + ld r6, STACK_SLOT_DAWR(r1) + ld r7, STACK_SLOT_DAWRX(r1) + mtspr SPRN_CIABR, r5 + mtspr SPRN_DAWR, r6 + mtspr SPRN_DAWRX, r7 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) +BEGIN_FTR_SECTION ld r5, STACK_SLOT_TID(r1) ld r6, STACK_SLOT_PSSCR(r1) ld r7, STACK_SLOT_PID(r1) + ld r8, STACK_SLOT_IAMR(r1) mtspr SPRN_TIDR, r5 mtspr SPRN_PSSCR, r6 mtspr SPRN_PID, r7 + mtspr SPRN_IAMR, r8 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) BEGIN_FTR_SECTION PPC_INVALIDATE_ERAT @@ -1819,8 +1855,8 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX) li r0, KVM_GUEST_MODE_NONE stb r0, HSTATE_IN_GUEST(r13) - ld r0, 112+PPC_LR_STKOFF(r1) - addi r1, r1, 112 + ld r0, SFS+PPC_LR_STKOFF(r1) + addi r1, r1, SFS mtlr r0 blr @@ -2366,12 +2402,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM) mfspr r3, SPRN_DEC mfspr r4, SPRN_HDEC mftb r5 - cmpw r3, r4 + extsw r3, r3 + EXTEND_HDEC(r4) + cmpd r3, r4 ble 67f mtspr SPRN_DEC, r4 67: /* save expiry time of guest decrementer */ - extsw r3, r3 add r3, r3, r5 ld r4, HSTATE_KVM_VCPU(r13) ld r5, HSTATE_KVM_VCORE(r13) diff --git a/arch/powerpc/perf/perf_regs.c b/arch/powerpc/perf/perf_regs.c index cbd82fde5770..09ceea6175ba 100644 --- a/arch/powerpc/perf/perf_regs.c +++ b/arch/powerpc/perf/perf_regs.c @@ -101,5 +101,6 @@ void perf_get_regs_user(struct perf_regs *regs_user, struct pt_regs *regs_user_copy) { regs_user->regs = task_pt_regs(current); - regs_user->abi = perf_reg_abi(current); + regs_user->abi = (regs_user->regs) ? perf_reg_abi(current) : + PERF_SAMPLE_REGS_ABI_NONE; } diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c index e6f444b46207..b5d960d6db3d 100644 --- a/arch/powerpc/platforms/powernv/npu-dma.c +++ b/arch/powerpc/platforms/powernv/npu-dma.c @@ -449,7 +449,7 @@ static int mmio_launch_invalidate(struct npu *npu, unsigned long launch, return mmio_atsd_reg; } -static int mmio_invalidate_pid(struct npu *npu, unsigned long pid) +static int mmio_invalidate_pid(struct npu *npu, unsigned long pid, bool flush) { unsigned long launch; @@ -465,12 +465,15 @@ static int mmio_invalidate_pid(struct npu *npu, unsigned long pid) /* PID */ launch |= pid << PPC_BITLSHIFT(38); + /* No flush */ + launch |= !flush << PPC_BITLSHIFT(39); + /* Invalidating the entire process doesn't use a va */ return mmio_launch_invalidate(npu, launch, 0); } static int mmio_invalidate_va(struct npu *npu, unsigned long va, - unsigned long pid) + unsigned long pid, bool flush) { unsigned long launch; @@ -486,26 +489,60 @@ static int mmio_invalidate_va(struct npu *npu, unsigned long va, /* PID */ launch |= pid << PPC_BITLSHIFT(38); + /* No flush */ + launch |= !flush << PPC_BITLSHIFT(39); + return mmio_launch_invalidate(npu, launch, va); } #define mn_to_npu_context(x) container_of(x, struct npu_context, mn) +struct mmio_atsd_reg { + struct npu *npu; + int reg; +}; + +static void mmio_invalidate_wait( + struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS], bool flush) +{ + struct npu *npu; + int i, reg; + + /* Wait for all invalidations to complete */ + for (i = 0; i <= max_npu2_index; i++) { + if (mmio_atsd_reg[i].reg < 0) + continue; + + /* Wait for completion */ + npu = mmio_atsd_reg[i].npu; + reg = mmio_atsd_reg[i].reg; + while (__raw_readq(npu->mmio_atsd_regs[reg] + XTS_ATSD_STAT)) + cpu_relax(); + + put_mmio_atsd_reg(npu, reg); + + /* + * The GPU requires two flush ATSDs to ensure all entries have + * been flushed. We use PID 0 as it will never be used for a + * process on the GPU. + */ + if (flush) + mmio_invalidate_pid(npu, 0, true); + } +} + /* * Invalidate either a single address or an entire PID depending on * the value of va. */ static void mmio_invalidate(struct npu_context *npu_context, int va, - unsigned long address) + unsigned long address, bool flush) { - int i, j, reg; + int i, j; struct npu *npu; struct pnv_phb *nphb; struct pci_dev *npdev; - struct { - struct npu *npu; - int reg; - } mmio_atsd_reg[NV_MAX_NPUS]; + struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS]; unsigned long pid = npu_context->mm->context.id; /* @@ -525,10 +562,11 @@ static void mmio_invalidate(struct npu_context *npu_context, int va, if (va) mmio_atsd_reg[i].reg = - mmio_invalidate_va(npu, address, pid); + mmio_invalidate_va(npu, address, pid, + flush); else mmio_atsd_reg[i].reg = - mmio_invalidate_pid(npu, pid); + mmio_invalidate_pid(npu, pid, flush); /* * The NPU hardware forwards the shootdown to all GPUs @@ -544,18 +582,10 @@ static void mmio_invalidate(struct npu_context *npu_context, int va, */ flush_tlb_mm(npu_context->mm); - /* Wait for all invalidations to complete */ - for (i = 0; i <= max_npu2_index; i++) { - if (mmio_atsd_reg[i].reg < 0) - continue; - - /* Wait for completion */ - npu = mmio_atsd_reg[i].npu; - reg = mmio_atsd_reg[i].reg; - while (__raw_readq(npu->mmio_atsd_regs[reg] + XTS_ATSD_STAT)) - cpu_relax(); - put_mmio_atsd_reg(npu, reg); - } + mmio_invalidate_wait(mmio_atsd_reg, flush); + if (flush) + /* Wait for the flush to complete */ + mmio_invalidate_wait(mmio_atsd_reg, false); } static void pnv_npu2_mn_release(struct mmu_notifier *mn, @@ -571,7 +601,7 @@ static void pnv_npu2_mn_release(struct mmu_notifier *mn, * There should be no more translation requests for this PID, but we * need to ensure any entries for it are removed from the TLB. */ - mmio_invalidate(npu_context, 0, 0); + mmio_invalidate(npu_context, 0, 0, true); } static void pnv_npu2_mn_change_pte(struct mmu_notifier *mn, @@ -581,7 +611,7 @@ static void pnv_npu2_mn_change_pte(struct mmu_notifier *mn, { struct npu_context *npu_context = mn_to_npu_context(mn); - mmio_invalidate(npu_context, 1, address); + mmio_invalidate(npu_context, 1, address, true); } static void pnv_npu2_mn_invalidate_page(struct mmu_notifier *mn, @@ -590,7 +620,7 @@ static void pnv_npu2_mn_invalidate_page(struct mmu_notifier *mn, { struct npu_context *npu_context = mn_to_npu_context(mn); - mmio_invalidate(npu_context, 1, address); + mmio_invalidate(npu_context, 1, address, true); } static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn, @@ -600,8 +630,11 @@ static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn, struct npu_context *npu_context = mn_to_npu_context(mn); unsigned long address; - for (address = start; address <= end; address += PAGE_SIZE) - mmio_invalidate(npu_context, 1, address); + for (address = start; address < end; address += PAGE_SIZE) + mmio_invalidate(npu_context, 1, address, false); + + /* Do the flush only on the final addess == end */ + mmio_invalidate(npu_context, 1, address, true); } static const struct mmu_notifier_ops nv_nmmu_notifier_ops = { @@ -651,8 +684,11 @@ struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev, /* No nvlink associated with this GPU device */ return ERR_PTR(-ENODEV); - if (!mm) { - /* kernel thread contexts are not supported */ + if (!mm || mm->context.id == 0) { + /* + * Kernel thread contexts are not supported and context id 0 is + * reserved on the GPU. + */ return ERR_PTR(-EINVAL); } diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 6967addc6a89..37abe86e5bc9 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -64,6 +64,7 @@ config ARCH_SUPPORTS_UPROBES config S390 def_bool y + select ARCH_BINFMT_ELF_STATE select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_GCOV_PROFILE_ALL @@ -184,7 +185,7 @@ config SCHED_OMIT_FRAME_POINTER config PGTABLE_LEVELS int - default 4 + default 5 source "init/Kconfig" diff --git a/arch/s390/crypto/Makefile b/arch/s390/crypto/Makefile index 678d9863e3f0..ad4bd777768d 100644 --- a/arch/s390/crypto/Makefile +++ b/arch/s390/crypto/Makefile @@ -6,7 +6,8 @@ obj-$(CONFIG_CRYPTO_SHA1_S390) += sha1_s390.o sha_common.o obj-$(CONFIG_CRYPTO_SHA256_S390) += sha256_s390.o sha_common.o obj-$(CONFIG_CRYPTO_SHA512_S390) += sha512_s390.o sha_common.o obj-$(CONFIG_CRYPTO_DES_S390) += des_s390.o -obj-$(CONFIG_CRYPTO_AES_S390) += aes_s390.o paes_s390.o +obj-$(CONFIG_CRYPTO_AES_S390) += aes_s390.o +obj-$(CONFIG_CRYPTO_PAES_S390) += paes_s390.o obj-$(CONFIG_S390_PRNG) += prng.o obj-$(CONFIG_CRYPTO_GHASH_S390) += ghash_s390.o obj-$(CONFIG_CRYPTO_CRC32_S390) += crc32-vx_s390.o diff --git a/arch/s390/crypto/arch_random.c b/arch/s390/crypto/arch_random.c index 9317b3e645e2..36aefc07d10c 100644 --- a/arch/s390/crypto/arch_random.c +++ b/arch/s390/crypto/arch_random.c @@ -12,6 +12,7 @@ #include <linux/kernel.h> #include <linux/atomic.h> +#include <linux/random.h> #include <linux/static_key.h> #include <asm/cpacf.h> diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild index 45092b12f54f..b3c88479feba 100644 --- a/arch/s390/include/asm/Kbuild +++ b/arch/s390/include/asm/Kbuild @@ -1,10 +1,12 @@ generic-y += asm-offsets.h generic-y += cacheflush.h generic-y += clkdev.h +generic-y += device.h generic-y += dma-contiguous.h generic-y += div64.h generic-y += emergency-restart.h generic-y += export.h +generic-y += fb.h generic-y += irq_regs.h generic-y += irq_work.h generic-y += kmap_types.h diff --git a/arch/s390/include/asm/device.h b/arch/s390/include/asm/device.h deleted file mode 100644 index 5203fc87f080..000000000000 --- a/arch/s390/include/asm/device.h +++ /dev/null @@ -1,10 +0,0 @@ -/* - * Arch specific extensions to struct device - * - * This file is released under the GPLv2 - */ -struct dev_archdata { -}; - -struct pdev_archdata { -}; diff --git a/arch/s390/include/asm/eadm.h b/arch/s390/include/asm/eadm.h index 67026300c88e..144809a3f4f6 100644 --- a/arch/s390/include/asm/eadm.h +++ b/arch/s390/include/asm/eadm.h @@ -3,6 +3,7 @@ #include <linux/types.h> #include <linux/device.h> +#include <linux/blkdev.h> struct arqb { u64 data; @@ -105,13 +106,14 @@ struct scm_driver { int (*probe) (struct scm_device *scmdev); int (*remove) (struct scm_device *scmdev); void (*notify) (struct scm_device *scmdev, enum scm_event event); - void (*handler) (struct scm_device *scmdev, void *data, int error); + void (*handler) (struct scm_device *scmdev, void *data, + blk_status_t error); }; int scm_driver_register(struct scm_driver *scmdrv); void scm_driver_unregister(struct scm_driver *scmdrv); int eadm_start_aob(struct aob *aob); -void scm_irq_handler(struct aob *aob, int error); +void scm_irq_handler(struct aob *aob, blk_status_t error); #endif /* _ASM_S390_EADM_H */ diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h index e8f623041769..ec024c08dabe 100644 --- a/arch/s390/include/asm/elf.h +++ b/arch/s390/include/asm/elf.h @@ -117,6 +117,9 @@ #define ELF_DATA ELFDATA2MSB #define ELF_ARCH EM_S390 +/* s390 specific phdr types */ +#define PT_S390_PGSTE 0x70000000 + /* * ELF register definitions.. */ @@ -151,6 +154,35 @@ extern unsigned int vdso_enabled; && (x)->e_ident[EI_CLASS] == ELF_CLASS) #define compat_start_thread start_thread31 +struct arch_elf_state { + int rc; +}; + +#define INIT_ARCH_ELF_STATE { .rc = 0 } + +#define arch_check_elf(ehdr, interp, interp_ehdr, state) (0) +#ifdef CONFIG_PGSTE +#define arch_elf_pt_proc(ehdr, phdr, elf, interp, state) \ +({ \ + struct arch_elf_state *_state = state; \ + if ((phdr)->p_type == PT_S390_PGSTE && \ + !page_table_allocate_pgste && \ + !test_thread_flag(TIF_PGSTE) && \ + !current->mm->context.alloc_pgste) { \ + set_thread_flag(TIF_PGSTE); \ + set_pt_regs_flag(task_pt_regs(current), \ + PIF_SYSCALL_RESTART); \ + _state->rc = -EAGAIN; \ + } \ + _state->rc; \ +}) +#else +#define arch_elf_pt_proc(ehdr, phdr, elf, interp, state) \ +({ \ + (state)->rc; \ +}) +#endif + /* For SVR4/S390 the function pointer to be registered with `atexit` is passed in R14. */ #define ELF_PLAT_INIT(_r, load_addr) \ diff --git a/arch/s390/include/asm/fb.h b/arch/s390/include/asm/fb.h deleted file mode 100644 index c7df38030992..000000000000 --- a/arch/s390/include/asm/fb.h +++ /dev/null @@ -1,12 +0,0 @@ -#ifndef _ASM_FB_H_ -#define _ASM_FB_H_ -#include <linux/fb.h> - -#define fb_pgprotect(...) do {} while (0) - -static inline int fb_is_primary_device(struct fb_info *info) -{ - return 0; -} - -#endif /* _ASM_FB_H_ */ diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h index 437e9af96688..904e4b3af95d 100644 --- a/arch/s390/include/asm/io.h +++ b/arch/s390/include/asm/io.h @@ -25,8 +25,6 @@ void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr); #define IO_SPACE_LIMIT 0 -#ifdef CONFIG_PCI - #define ioremap_nocache(addr, size) ioremap(addr, size) #define ioremap_wc ioremap_nocache #define ioremap_wt ioremap_nocache @@ -49,6 +47,8 @@ static inline void ioport_unmap(void __iomem *p) { } +#ifdef CONFIG_PCI + /* * s390 needs a private implementation of pci_iomap since ioremap with its * offset parameter isn't sufficient. That's because BAR spaces are not diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 65d07ac34647..6baae236f461 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -107,6 +107,20 @@ struct esca_block { struct esca_entry cpu[KVM_S390_ESCA_CPU_SLOTS]; } __packed; +/* + * This struct is used to store some machine check info from lowcore + * for machine checks that happen while the guest is running. + * This info in host's lowcore might be overwritten by a second machine + * check from host when host is in the machine check's high-level handling. + * The size is 24 bytes. + */ +struct mcck_volatile_info { + __u64 mcic; + __u64 failing_storage_address; + __u32 ext_damage_code; + __u32 reserved; +}; + #define CPUSTAT_STOPPED 0x80000000 #define CPUSTAT_WAIT 0x10000000 #define CPUSTAT_ECALL_PEND 0x08000000 @@ -264,7 +278,8 @@ struct kvm_s390_itdb { struct sie_page { struct kvm_s390_sie_block sie_block; - __u8 reserved200[1024]; /* 0x0200 */ + struct mcck_volatile_info mcck_info; /* 0x0200 */ + __u8 reserved218[1000]; /* 0x0218 */ struct kvm_s390_itdb itdb; /* 0x0600 */ __u8 reserved700[2304]; /* 0x0700 */ } __packed; diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index 8712e11bead4..4541ac44b35f 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -25,7 +25,9 @@ static inline int init_new_context(struct task_struct *tsk, mm->context.gmap_asce = 0; mm->context.flush_mm = 0; #ifdef CONFIG_PGSTE - mm->context.alloc_pgste = page_table_allocate_pgste; + mm->context.alloc_pgste = page_table_allocate_pgste || + test_thread_flag(TIF_PGSTE) || + current->mm->context.alloc_pgste; mm->context.has_pgste = 0; mm->context.use_skey = 0; mm->context.use_cmma = 0; diff --git a/arch/s390/include/asm/nmi.h b/arch/s390/include/asm/nmi.h index e3e8895f5d3e..13623b9991d4 100644 --- a/arch/s390/include/asm/nmi.h +++ b/arch/s390/include/asm/nmi.h @@ -14,7 +14,14 @@ #include <linux/const.h> #include <linux/types.h> +#define MCIC_SUBCLASS_MASK (1ULL<<63 | 1ULL<<62 | 1ULL<<61 | \ + 1ULL<<59 | 1ULL<<58 | 1ULL<<56 | \ + 1ULL<<55 | 1ULL<<54 | 1ULL<<53 | \ + 1ULL<<52 | 1ULL<<47 | 1ULL<<46 | \ + 1ULL<<45 | 1ULL<<44) #define MCCK_CODE_SYSTEM_DAMAGE _BITUL(63) +#define MCCK_CODE_EXT_DAMAGE _BITUL(63 - 5) +#define MCCK_CODE_CP _BITUL(63 - 9) #define MCCK_CODE_CPU_TIMER_VALID _BITUL(63 - 46) #define MCCK_CODE_PSW_MWP_VALID _BITUL(63 - 20) #define MCCK_CODE_PSW_IA_VALID _BITUL(63 - 23) diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index 69b8a41fca84..624deaa44230 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -74,6 +74,7 @@ typedef struct { unsigned long pgste; } pgste_t; typedef struct { unsigned long pte; } pte_t; typedef struct { unsigned long pmd; } pmd_t; typedef struct { unsigned long pud; } pud_t; +typedef struct { unsigned long p4d; } p4d_t; typedef struct { unsigned long pgd; } pgd_t; typedef pte_t *pgtable_t; @@ -82,12 +83,14 @@ typedef pte_t *pgtable_t; #define pte_val(x) ((x).pte) #define pmd_val(x) ((x).pmd) #define pud_val(x) ((x).pud) +#define p4d_val(x) ((x).p4d) #define pgd_val(x) ((x).pgd) #define __pgste(x) ((pgste_t) { (x) } ) #define __pte(x) ((pte_t) { (x) } ) #define __pmd(x) ((pmd_t) { (x) } ) #define __pud(x) ((pud_t) { (x) } ) +#define __p4d(x) ((p4d_t) { (x) } ) #define __pgd(x) ((pgd_t) { (x) } ) #define __pgprot(x) ((pgprot_t) { (x) } ) diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index 4e3186649578..f36b4b726057 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -70,11 +70,10 @@ struct zpci_fmb { } __packed __aligned(128); enum zpci_state { - ZPCI_FN_STATE_RESERVED, - ZPCI_FN_STATE_STANDBY, - ZPCI_FN_STATE_CONFIGURED, - ZPCI_FN_STATE_ONLINE, - NR_ZPCI_FN_STATES, + ZPCI_FN_STATE_STANDBY = 0, + ZPCI_FN_STATE_CONFIGURED = 1, + ZPCI_FN_STATE_RESERVED = 2, + ZPCI_FN_STATE_ONLINE = 3, }; struct zpci_bar_struct { @@ -109,7 +108,7 @@ struct zpci_dev { u64 msi_addr; /* MSI address */ unsigned int max_msi; /* maximum number of MSI's */ struct airq_iv *aibv; /* adapter interrupt bit vector */ - unsigned int aisb; /* number of the summary bit */ + unsigned long aisb; /* number of the summary bit */ /* DMA stuff */ unsigned long *dma_table; @@ -159,11 +158,12 @@ extern const struct attribute_group *zpci_attr_groups[]; ----------------------------------------------------------------------------- */ /* Base stuff */ int zpci_create_device(struct zpci_dev *); +void zpci_remove_device(struct zpci_dev *zdev); int zpci_enable_device(struct zpci_dev *); int zpci_disable_device(struct zpci_dev *); -void zpci_stop_device(struct zpci_dev *); int zpci_register_ioat(struct zpci_dev *, u8, u64, u64, u64); int zpci_unregister_ioat(struct zpci_dev *, u8); +void zpci_remove_reserved_devices(void); /* CLP */ int clp_scan_pci_devices(void); @@ -172,6 +172,7 @@ int clp_rescan_pci_devices_simple(void); int clp_add_pci_device(u32, u32, int); int clp_enable_fh(struct zpci_dev *, u8); int clp_disable_fh(struct zpci_dev *); +int clp_get_state(u32 fid, enum zpci_state *state); #ifdef CONFIG_PCI /* Error handling and recovery */ diff --git a/arch/s390/include/asm/pci_insn.h b/arch/s390/include/asm/pci_insn.h index 649eb62c52b3..34abcf275799 100644 --- a/arch/s390/include/asm/pci_insn.h +++ b/arch/s390/include/asm/pci_insn.h @@ -76,7 +76,7 @@ struct zpci_fib { u32 gd; } __packed __aligned(8); -int zpci_mod_fc(u64 req, struct zpci_fib *fib); +u8 zpci_mod_fc(u64 req, struct zpci_fib *fib, u8 *status); int zpci_refresh_trans(u64 fn, u64 addr, u64 range); int zpci_load(u64 *data, u64 req, u64 offset); int zpci_store(u64 data, u64 req, u64 offset); diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index 166f703dad7c..bb0ff1bb0c4a 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -51,12 +51,24 @@ static inline unsigned long pgd_entry_type(struct mm_struct *mm) return _SEGMENT_ENTRY_EMPTY; if (mm->context.asce_limit <= (1UL << 42)) return _REGION3_ENTRY_EMPTY; - return _REGION2_ENTRY_EMPTY; + if (mm->context.asce_limit <= (1UL << 53)) + return _REGION2_ENTRY_EMPTY; + return _REGION1_ENTRY_EMPTY; } -int crst_table_upgrade(struct mm_struct *); +int crst_table_upgrade(struct mm_struct *mm, unsigned long limit); void crst_table_downgrade(struct mm_struct *); +static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long address) +{ + unsigned long *table = crst_table_alloc(mm); + + if (table) + crst_table_init(table, _REGION2_ENTRY_EMPTY); + return (p4d_t *) table; +} +#define p4d_free(mm, p4d) crst_table_free(mm, (unsigned long *) p4d) + static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) { unsigned long *table = crst_table_alloc(mm); @@ -86,9 +98,14 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) crst_table_free(mm, (unsigned long *) pmd); } -static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) +static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d) +{ + pgd_val(*pgd) = _REGION1_ENTRY | __pa(p4d); +} + +static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4d, pud_t *pud) { - pgd_val(*pgd) = _REGION2_ENTRY | __pa(pud); + p4d_val(*p4d) = _REGION2_ENTRY | __pa(pud); } static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index e6e3b887bee3..57057fb1cc07 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -24,7 +24,6 @@ * the S390 page table tree. */ #ifndef __ASSEMBLY__ -#include <asm-generic/5level-fixup.h> #include <linux/sched.h> #include <linux/mm_types.h> #include <linux/page-flags.h> @@ -87,12 +86,15 @@ extern unsigned long zero_page_mask; */ #define PMD_SHIFT 20 #define PUD_SHIFT 31 -#define PGDIR_SHIFT 42 +#define P4D_SHIFT 42 +#define PGDIR_SHIFT 53 #define PMD_SIZE (1UL << PMD_SHIFT) #define PMD_MASK (~(PMD_SIZE-1)) #define PUD_SIZE (1UL << PUD_SHIFT) #define PUD_MASK (~(PUD_SIZE-1)) +#define P4D_SIZE (1UL << P4D_SHIFT) +#define P4D_MASK (~(P4D_SIZE-1)) #define PGDIR_SIZE (1UL << PGDIR_SHIFT) #define PGDIR_MASK (~(PGDIR_SIZE-1)) @@ -105,6 +107,7 @@ extern unsigned long zero_page_mask; #define PTRS_PER_PTE 256 #define PTRS_PER_PMD 2048 #define PTRS_PER_PUD 2048 +#define PTRS_PER_P4D 2048 #define PTRS_PER_PGD 2048 #define FIRST_USER_ADDRESS 0UL @@ -115,6 +118,8 @@ extern unsigned long zero_page_mask; printk("%s:%d: bad pmd %p.\n", __FILE__, __LINE__, (void *) pmd_val(e)) #define pud_ERROR(e) \ printk("%s:%d: bad pud %p.\n", __FILE__, __LINE__, (void *) pud_val(e)) +#define p4d_ERROR(e) \ + printk("%s:%d: bad p4d %p.\n", __FILE__, __LINE__, (void *) p4d_val(e)) #define pgd_ERROR(e) \ printk("%s:%d: bad pgd %p.\n", __FILE__, __LINE__, (void *) pgd_val(e)) @@ -296,8 +301,6 @@ static inline int is_module_addr(void *addr) #define _REGION3_ENTRY_EMPTY (_REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_INVALID) #define _REGION3_ENTRY_ORIGIN_LARGE ~0x7fffffffUL /* large page address */ -#define _REGION3_ENTRY_ORIGIN ~0x7ffUL/* region third table origin */ - #define _REGION3_ENTRY_DIRTY 0x2000 /* SW region dirty bit */ #define _REGION3_ENTRY_YOUNG 0x1000 /* SW region young bit */ #define _REGION3_ENTRY_LARGE 0x0400 /* RTTE-format control, large page */ @@ -310,8 +313,8 @@ static inline int is_module_addr(void *addr) #define _REGION3_ENTRY_SOFT_DIRTY 0x0000 /* SW region soft dirty bit */ #endif -#define _REGION_ENTRY_BITS 0xfffffffffffff227UL -#define _REGION_ENTRY_BITS_LARGE 0xffffffff8000fe27UL +#define _REGION_ENTRY_BITS 0xfffffffffffff22fUL +#define _REGION_ENTRY_BITS_LARGE 0xffffffff8000fe2fUL /* Bits in the segment table entry */ #define _SEGMENT_ENTRY_BITS 0xfffffffffffffe33UL @@ -560,18 +563,23 @@ static inline void crdte(unsigned long old, unsigned long new, } /* - * pgd/pmd/pte query functions + * pgd/p4d/pud/pmd/pte query functions */ +static inline int pgd_folded(pgd_t pgd) +{ + return (pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R1; +} + static inline int pgd_present(pgd_t pgd) { - if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R2) + if (pgd_folded(pgd)) return 1; return (pgd_val(pgd) & _REGION_ENTRY_ORIGIN) != 0UL; } static inline int pgd_none(pgd_t pgd) { - if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R2) + if (pgd_folded(pgd)) return 0; return (pgd_val(pgd) & _REGION_ENTRY_INVALID) != 0UL; } @@ -589,16 +597,48 @@ static inline int pgd_bad(pgd_t pgd) return (pgd_val(pgd) & mask) != 0; } +static inline int p4d_folded(p4d_t p4d) +{ + return (p4d_val(p4d) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R2; +} + +static inline int p4d_present(p4d_t p4d) +{ + if (p4d_folded(p4d)) + return 1; + return (p4d_val(p4d) & _REGION_ENTRY_ORIGIN) != 0UL; +} + +static inline int p4d_none(p4d_t p4d) +{ + if (p4d_folded(p4d)) + return 0; + return p4d_val(p4d) == _REGION2_ENTRY_EMPTY; +} + +static inline unsigned long p4d_pfn(p4d_t p4d) +{ + unsigned long origin_mask; + + origin_mask = _REGION_ENTRY_ORIGIN; + return (p4d_val(p4d) & origin_mask) >> PAGE_SHIFT; +} + +static inline int pud_folded(pud_t pud) +{ + return (pud_val(pud) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R3; +} + static inline int pud_present(pud_t pud) { - if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R3) + if (pud_folded(pud)) return 1; return (pud_val(pud) & _REGION_ENTRY_ORIGIN) != 0UL; } static inline int pud_none(pud_t pud) { - if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R3) + if (pud_folded(pud)) return 0; return pud_val(pud) == _REGION3_ENTRY_EMPTY; } @@ -614,7 +654,7 @@ static inline unsigned long pud_pfn(pud_t pud) { unsigned long origin_mask; - origin_mask = _REGION3_ENTRY_ORIGIN; + origin_mask = _REGION_ENTRY_ORIGIN; if (pud_large(pud)) origin_mask = _REGION3_ENTRY_ORIGIN_LARGE; return (pud_val(pud) & origin_mask) >> PAGE_SHIFT; @@ -641,6 +681,13 @@ static inline int pud_bad(pud_t pud) return (pud_val(pud) & ~_REGION_ENTRY_BITS) != 0; } +static inline int p4d_bad(p4d_t p4d) +{ + if ((p4d_val(p4d) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R2) + return pud_bad(__pud(p4d_val(p4d))); + return (p4d_val(p4d) & ~_REGION_ENTRY_BITS) != 0; +} + static inline int pmd_present(pmd_t pmd) { return pmd_val(pmd) != _SEGMENT_ENTRY_EMPTY; @@ -794,8 +841,14 @@ static inline int pte_unused(pte_t pte) static inline void pgd_clear(pgd_t *pgd) { - if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2) - pgd_val(*pgd) = _REGION2_ENTRY_EMPTY; + if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R1) + pgd_val(*pgd) = _REGION1_ENTRY_EMPTY; +} + +static inline void p4d_clear(p4d_t *p4d) +{ + if ((p4d_val(*p4d) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2) + p4d_val(*p4d) = _REGION2_ENTRY_EMPTY; } static inline void pud_clear(pud_t *pud) @@ -1089,6 +1142,7 @@ static inline pte_t mk_pte(struct page *page, pgprot_t pgprot) } #define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD-1)) +#define p4d_index(address) (((address) >> P4D_SHIFT) & (PTRS_PER_P4D-1)) #define pud_index(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD-1)) #define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1)) #define pte_index(address) (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE-1)) @@ -1098,19 +1152,31 @@ static inline pte_t mk_pte(struct page *page, pgprot_t pgprot) #define pmd_deref(pmd) (pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN) #define pud_deref(pud) (pud_val(pud) & _REGION_ENTRY_ORIGIN) +#define p4d_deref(pud) (p4d_val(pud) & _REGION_ENTRY_ORIGIN) #define pgd_deref(pgd) (pgd_val(pgd) & _REGION_ENTRY_ORIGIN) -static inline pud_t *pud_offset(pgd_t *pgd, unsigned long address) +static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) { - pud_t *pud = (pud_t *) pgd; - if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2) - pud = (pud_t *) pgd_deref(*pgd); - return pud + pud_index(address); + p4d_t *p4d = (p4d_t *) pgd; + + if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R1) + p4d = (p4d_t *) pgd_deref(*pgd); + return p4d + p4d_index(address); +} + +static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address) +{ + pud_t *pud = (pud_t *) p4d; + + if ((p4d_val(*p4d) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2) + pud = (pud_t *) p4d_deref(*p4d); + return pud + pud_index(address); } static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) { pmd_t *pmd = (pmd_t *) pud; + if ((pud_val(*pud) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3) pmd = (pmd_t *) pud_deref(*pud); return pmd + pmd_index(address); @@ -1122,6 +1188,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) #define pmd_page(pmd) pfn_to_page(pmd_pfn(pmd)) #define pud_page(pud) pfn_to_page(pud_pfn(pud)) +#define p4d_page(pud) pfn_to_page(p4d_pfn(p4d)) /* Find an entry in the lowest level page table.. */ #define pte_offset(pmd, addr) ((pte_t *) pmd_deref(*(pmd)) + pte_index(addr)) diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 60d395fdc864..c25d57e0aad3 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -20,6 +20,7 @@ #define CIF_FPU 4 /* restore FPU registers */ #define CIF_IGNORE_IRQ 5 /* ignore interrupt (for udelay) */ #define CIF_ENABLED_WAIT 6 /* in enabled wait state */ +#define CIF_MCCK_GUEST 7 /* machine check happening in guest */ #define _CIF_MCCK_PENDING _BITUL(CIF_MCCK_PENDING) #define _CIF_ASCE_PRIMARY _BITUL(CIF_ASCE_PRIMARY) @@ -28,6 +29,7 @@ #define _CIF_FPU _BITUL(CIF_FPU) #define _CIF_IGNORE_IRQ _BITUL(CIF_IGNORE_IRQ) #define _CIF_ENABLED_WAIT _BITUL(CIF_ENABLED_WAIT) +#define _CIF_MCCK_GUEST _BITUL(CIF_MCCK_GUEST) #ifndef __ASSEMBLY__ @@ -92,11 +94,11 @@ extern void execve_tail(void); */ #define TASK_SIZE_OF(tsk) (test_tsk_thread_flag(tsk, TIF_31BIT) ? \ - (1UL << 31) : (1UL << 53)) + (1UL << 31) : -PAGE_SIZE) #define TASK_UNMAPPED_BASE (test_thread_flag(TIF_31BIT) ? \ (1UL << 30) : (1UL << 41)) #define TASK_SIZE TASK_SIZE_OF(current) -#define TASK_SIZE_MAX (1UL << 53) +#define TASK_SIZE_MAX (-PAGE_SIZE) #define STACK_TOP (test_thread_flag(TIF_31BIT) ? \ (1UL << 31) : (1UL << 42)) @@ -221,11 +223,6 @@ extern void release_thread(struct task_struct *); /* Free guarded storage control block for current */ void exit_thread_gs(void); -/* - * Return saved PC of a blocked thread. - */ -extern unsigned long thread_saved_pc(struct task_struct *t); - unsigned long get_wchan(struct task_struct *p); #define task_pt_regs(tsk) ((struct pt_regs *) \ (task_stack_page(tsk) + THREAD_SIZE) - 1) diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h index 99bc456cc26a..853b01245c20 100644 --- a/arch/s390/include/asm/ptrace.h +++ b/arch/s390/include/asm/ptrace.h @@ -11,9 +11,11 @@ #define PIF_SYSCALL 0 /* inside a system call */ #define PIF_PER_TRAP 1 /* deliver sigtrap on return to user */ +#define PIF_SYSCALL_RESTART 2 /* restart the current system call */ #define _PIF_SYSCALL _BITUL(PIF_SYSCALL) #define _PIF_PER_TRAP _BITUL(PIF_PER_TRAP) +#define _PIF_SYSCALL_RESTART _BITUL(PIF_SYSCALL_RESTART) #ifndef __ASSEMBLY__ @@ -24,38 +26,38 @@ PSW_MASK_PSTATE | PSW_ASC_PRIMARY) struct psw_bits { - unsigned long : 1; - unsigned long r : 1; /* PER-Mask */ - unsigned long : 3; - unsigned long t : 1; /* DAT Mode */ - unsigned long i : 1; /* Input/Output Mask */ - unsigned long e : 1; /* External Mask */ - unsigned long key : 4; /* PSW Key */ - unsigned long : 1; - unsigned long m : 1; /* Machine-Check Mask */ - unsigned long w : 1; /* Wait State */ - unsigned long p : 1; /* Problem State */ - unsigned long as : 2; /* Address Space Control */ - unsigned long cc : 2; /* Condition Code */ - unsigned long pm : 4; /* Program Mask */ - unsigned long ri : 1; /* Runtime Instrumentation */ - unsigned long : 6; - unsigned long eaba : 2; /* Addressing Mode */ - unsigned long : 31; - unsigned long ia : 64; /* Instruction Address */ + unsigned long : 1; + unsigned long per : 1; /* PER-Mask */ + unsigned long : 3; + unsigned long dat : 1; /* DAT Mode */ + unsigned long io : 1; /* Input/Output Mask */ + unsigned long ext : 1; /* External Mask */ + unsigned long key : 4; /* PSW Key */ + unsigned long : 1; + unsigned long mcheck : 1; /* Machine-Check Mask */ + unsigned long wait : 1; /* Wait State */ + unsigned long pstate : 1; /* Problem State */ + unsigned long as : 2; /* Address Space Control */ + unsigned long cc : 2; /* Condition Code */ + unsigned long pm : 4; /* Program Mask */ + unsigned long ri : 1; /* Runtime Instrumentation */ + unsigned long : 6; + unsigned long eaba : 2; /* Addressing Mode */ + unsigned long : 31; + unsigned long ia : 64; /* Instruction Address */ }; enum { - PSW_AMODE_24BIT = 0, - PSW_AMODE_31BIT = 1, - PSW_AMODE_64BIT = 3 + PSW_BITS_AMODE_24BIT = 0, + PSW_BITS_AMODE_31BIT = 1, + PSW_BITS_AMODE_64BIT = 3 }; enum { - PSW_AS_PRIMARY = 0, - PSW_AS_ACCREG = 1, - PSW_AS_SECONDARY = 2, - PSW_AS_HOME = 3 + PSW_BITS_AS_PRIMARY = 0, + PSW_BITS_AS_ACCREG = 1, + PSW_BITS_AS_SECONDARY = 2, + PSW_BITS_AS_HOME = 3 }; #define psw_bits(__psw) (*({ \ diff --git a/arch/s390/include/asm/sigp.h b/arch/s390/include/asm/sigp.h index 72df5f2de6b0..020a8814d511 100644 --- a/arch/s390/include/asm/sigp.h +++ b/arch/s390/include/asm/sigp.h @@ -59,7 +59,7 @@ static inline int __pcpu_sigp(u16 addr, u8 order, unsigned long parm, int cc; cc = ____pcpu_sigp(addr, order, parm, &_status); - if (status && cc == 1) + if (status && cc == SIGP_CC_STATUS_STORED) *status = _status; return cc; } diff --git a/arch/s390/include/asm/sysinfo.h b/arch/s390/include/asm/sysinfo.h index e784bed6ed7f..2b498e58b914 100644 --- a/arch/s390/include/asm/sysinfo.h +++ b/arch/s390/include/asm/sysinfo.h @@ -109,7 +109,7 @@ struct sysinfo_2_2_2 { unsigned short cpus_shared; char reserved_4[3]; unsigned char vsne; - uuid_be uuid; + uuid_t uuid; char reserved_5[160]; char ext_name[256]; }; @@ -134,7 +134,7 @@ struct sysinfo_3_2_2 { char reserved_1[3]; unsigned char evmne; unsigned int reserved_2; - uuid_be uuid; + uuid_t uuid; } vm[8]; char reserved_3[1504]; char ext_names[8][256]; diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h index 0b3ee083a665..1aecf432c48d 100644 --- a/arch/s390/include/asm/thread_info.h +++ b/arch/s390/include/asm/thread_info.h @@ -58,6 +58,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); #define TIF_UPROBE 3 /* breakpointed or single-stepping */ #define TIF_GUARDED_STORAGE 4 /* load guarded storage control block */ #define TIF_PATCH_PENDING 5 /* pending live patching update */ +#define TIF_PGSTE 6 /* New mm's will use 4K page tables */ #define TIF_31BIT 16 /* 32bit process */ #define TIF_MEMDIE 17 /* is terminating due to OOM killer */ diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index 853b2a3d8dee..7317b3108a88 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -137,6 +137,21 @@ static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, } /* + * p4d_free_tlb frees a pud table and clears the CRSTE for the + * region second table entry from the tlb. + * If the mm uses a four level page table the single p4d is freed + * as the pgd. p4d_free_tlb checks the asce_limit against 8PB + * to avoid the double free of the p4d in this case. + */ +static inline void p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d, + unsigned long address) +{ + if (tlb->mm->context.asce_limit <= (1UL << 53)) + return; + tlb_remove_table(tlb, p4d); +} + +/* * pud_free_tlb frees a pud table and clears the CRSTE for the * region third table entry from the tlb. * If the mm uses a three level page table the single pud is freed diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 6bb29633e1f1..b65c414b6c0e 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -58,6 +58,9 @@ int main(void) OFFSET(__SF_BACKCHAIN, stack_frame, back_chain); OFFSET(__SF_GPRS, stack_frame, gprs); OFFSET(__SF_EMPTY, stack_frame, empty1); + OFFSET(__SF_SIE_CONTROL, stack_frame, empty1[0]); + OFFSET(__SF_SIE_SAVEAREA, stack_frame, empty1[1]); + OFFSET(__SF_SIE_REASON, stack_frame, empty1[2]); BLANK(); /* timeval/timezone offsets for use by vdso */ OFFSET(__VDSO_UPD_COUNT, vdso_data, tb_update_count); diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c index 829e1c53005c..dab78babfab6 100644 --- a/arch/s390/kernel/dumpstack.c +++ b/arch/s390/kernel/dumpstack.c @@ -98,8 +98,10 @@ static int show_address(void *data, unsigned long address, int reliable) return 0; } -static void show_trace(struct task_struct *task, unsigned long sp) +void show_stack(struct task_struct *task, unsigned long *stack) { + unsigned long sp = (unsigned long) stack; + if (!sp) sp = task ? task->thread.ksp : current_stack_pointer(); printk("Call Trace:\n"); @@ -109,29 +111,6 @@ static void show_trace(struct task_struct *task, unsigned long sp) debug_show_held_locks(task); } -void show_stack(struct task_struct *task, unsigned long *sp) -{ - unsigned long *stack; - int i; - - stack = sp; - if (!stack) { - if (!task) - stack = (unsigned long *)current_stack_pointer(); - else - stack = (unsigned long *)task->thread.ksp; - } - printk(KERN_DEFAULT "Stack:\n"); - for (i = 0; i < 20; i++) { - if (((addr_t) stack & (THREAD_SIZE-1)) == 0) - break; - if (i % 4 == 0) - printk(KERN_DEFAULT " "); - pr_cont("%016lx%c", *stack++, i % 4 == 3 ? '\n' : ' '); - } - show_trace(task, (unsigned long)sp); -} - static void show_last_breaking_event(struct pt_regs *regs) { printk("Last Breaking-Event-Address:\n"); @@ -149,8 +128,8 @@ void show_registers(struct pt_regs *regs) pr_cont(" (%pSR)", (void *)regs->psw.addr); pr_cont("\n"); printk(" R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x " - "P:%x AS:%x CC:%x PM:%x", psw->r, psw->t, psw->i, psw->e, - psw->key, psw->m, psw->w, psw->p, psw->as, psw->cc, psw->pm); + "P:%x AS:%x CC:%x PM:%x", psw->per, psw->dat, psw->io, psw->ext, + psw->key, psw->mcheck, psw->wait, psw->pstate, psw->as, psw->cc, psw->pm); pr_cont(" RI:%x EA:%x\n", psw->ri, psw->eaba); printk("%s GPRS: %016lx %016lx %016lx %016lx\n", mode, regs->gprs[0], regs->gprs[1], regs->gprs[2], regs->gprs[3]); @@ -169,7 +148,7 @@ void show_regs(struct pt_regs *regs) show_registers(regs); /* Show stack backtrace if pt_regs is from kernel mode */ if (!user_mode(regs)) - show_trace(NULL, regs->gprs[15]); + show_stack(NULL, (unsigned long *) regs->gprs[15]); show_last_breaking_event(regs); } diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 6315037335ba..21900e1cee9c 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -52,7 +52,7 @@ _TIF_TRACE = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \ _TIF_SYSCALL_TRACEPOINT) _CIF_WORK = (_CIF_MCCK_PENDING | _CIF_ASCE_PRIMARY | \ _CIF_ASCE_SECONDARY | _CIF_FPU) -_PIF_WORK = (_PIF_PER_TRAP) +_PIF_WORK = (_PIF_PER_TRAP | _PIF_SYSCALL_RESTART) #define BASED(name) name-cleanup_critical(%r13) @@ -225,6 +225,7 @@ ENTRY(sie64a) jnz .Lsie_skip TSTMSK __LC_CPU_FLAGS,_CIF_FPU jo .Lsie_skip # exit if fp/vx regs changed +.Lsie_entry: sie 0(%r14) .Lsie_skip: ni __SIE_PROG0C+3(%r14),0xfe # no longer in SIE @@ -334,6 +335,8 @@ ENTRY(system_call) jo .Lsysc_mcck_pending TSTMSK __TI_flags(%r12),_TIF_NEED_RESCHED jo .Lsysc_reschedule + TSTMSK __PT_FLAGS(%r11),_PIF_SYSCALL_RESTART + jo .Lsysc_syscall_restart #ifdef CONFIG_UPROBES TSTMSK __TI_flags(%r12),_TIF_UPROBE jo .Lsysc_uprobe_notify @@ -347,6 +350,8 @@ ENTRY(system_call) jo .Lsysc_patch_pending # handle live patching just before # signals and possible syscall restart #endif + TSTMSK __PT_FLAGS(%r11),_PIF_SYSCALL_RESTART + jo .Lsysc_syscall_restart TSTMSK __TI_flags(%r12),_TIF_SIGPENDING jo .Lsysc_sigpending TSTMSK __TI_flags(%r12),_TIF_NOTIFY_RESUME @@ -448,6 +453,15 @@ ENTRY(system_call) jg do_per_trap # +# _PIF_SYSCALL_RESTART is set, repeat the current system call +# +.Lsysc_syscall_restart: + ni __PT_FLAGS+7(%r11),255-_PIF_SYSCALL_RESTART + lmg %r1,%r7,__PT_R1(%r11) # load svc arguments + lg %r2,__PT_ORIG_GPR2(%r11) + j .Lsysc_do_svc + +# # call tracehook_report_syscall_entry/tracehook_report_syscall_exit before # and after the system call # @@ -881,9 +895,7 @@ ENTRY(save_fpu_regs) oi __LC_CPU_FLAGS+7,_CIF_FPU br %r14 .Lsave_fpu_regs_end: -#if IS_ENABLED(CONFIG_KVM) EXPORT_SYMBOL(save_fpu_regs) -#endif /* * Load floating-point controls and floating-point or vector registers. @@ -1111,7 +1123,13 @@ cleanup_critical: .quad .Lsie_done .Lcleanup_sie: - lg %r9,__SF_EMPTY(%r15) # get control block pointer + cghi %r11,__LC_SAVE_AREA_ASYNC #Is this in normal interrupt? + je 1f + slg %r9,BASED(.Lsie_crit_mcck_start) + clg %r9,BASED(.Lsie_crit_mcck_length) + jh 1f + oi __LC_CPU_FLAGS+7, _CIF_MCCK_GUEST +1: lg %r9,__SF_EMPTY(%r15) # get control block pointer ni __SIE_PROG0C+3(%r9),0xfe # no longer in SIE lctlg %c1,%c1,__LC_USER_ASCE # load primary asce larl %r9,sie_exit # skip forward to sie_exit @@ -1296,6 +1314,10 @@ cleanup_critical: .quad .Lsie_gmap .Lsie_critical_length: .quad .Lsie_done - .Lsie_gmap +.Lsie_crit_mcck_start: + .quad .Lsie_entry +.Lsie_crit_mcck_length: + .quad .Lsie_skip - .Lsie_entry #endif .section .rodata, "a" diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index e545ffe5155a..8e622bb52f7a 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -564,8 +564,6 @@ static struct kset *ipl_kset; static void __ipl_run(void *unused) { - if (MACHINE_IS_LPAR && ipl_info.type == IPL_TYPE_CCW) - diag308(DIAG308_LOAD_NORMAL_DUMP, NULL); diag308(DIAG308_LOAD_CLEAR, NULL); if (MACHINE_IS_VM) __cpcmd("IPL", NULL, 0, NULL); @@ -1088,10 +1086,7 @@ static void __reipl_run(void *unused) break; case REIPL_METHOD_CCW_DIAG: diag308(DIAG308_SET, reipl_block_ccw); - if (MACHINE_IS_LPAR) - diag308(DIAG308_LOAD_NORMAL_DUMP, NULL); - else - diag308(DIAG308_LOAD_CLEAR, NULL); + diag308(DIAG308_LOAD_CLEAR, NULL); break; case REIPL_METHOD_FCP_RW_DIAG: diag308(DIAG308_SET, reipl_block_fcp); diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c index 985589523970..31d03a84126c 100644 --- a/arch/s390/kernel/nmi.c +++ b/arch/s390/kernel/nmi.c @@ -25,6 +25,8 @@ #include <asm/crw.h> #include <asm/switch_to.h> #include <asm/ctl_reg.h> +#include <asm/asm-offsets.h> +#include <linux/kvm_host.h> struct mcck_struct { unsigned int kill_task : 1; @@ -274,12 +276,39 @@ static int notrace s390_validate_registers(union mci mci, int umode) return kill_task; } +/* + * Backup the guest's machine check info to its description block + */ +static void notrace s390_backup_mcck_info(struct pt_regs *regs) +{ + struct mcck_volatile_info *mcck_backup; + struct sie_page *sie_page; + + /* r14 contains the sie block, which was set in sie64a */ + struct kvm_s390_sie_block *sie_block = + (struct kvm_s390_sie_block *) regs->gprs[14]; + + if (sie_block == NULL) + /* Something's seriously wrong, stop system. */ + s390_handle_damage(); + + sie_page = container_of(sie_block, struct sie_page, sie_block); + mcck_backup = &sie_page->mcck_info; + mcck_backup->mcic = S390_lowcore.mcck_interruption_code & + ~(MCCK_CODE_CP | MCCK_CODE_EXT_DAMAGE); + mcck_backup->ext_damage_code = S390_lowcore.external_damage_code; + mcck_backup->failing_storage_address + = S390_lowcore.failing_storage_address; +} + #define MAX_IPD_COUNT 29 #define MAX_IPD_TIME (5 * 60 * USEC_PER_SEC) /* 5 minutes */ #define ED_STP_ISLAND 6 /* External damage STP island check */ #define ED_STP_SYNC 7 /* External damage STP sync check */ +#define MCCK_CODE_NO_GUEST (MCCK_CODE_CP | MCCK_CODE_EXT_DAMAGE) + /* * machine check handler. */ @@ -291,6 +320,7 @@ void notrace s390_do_machine_check(struct pt_regs *regs) struct mcck_struct *mcck; unsigned long long tmp; union mci mci; + unsigned long mcck_dam_code; nmi_enter(); inc_irq_stat(NMI_NMI); @@ -301,7 +331,13 @@ void notrace s390_do_machine_check(struct pt_regs *regs) /* System damage -> stopping machine */ s390_handle_damage(); } - if (mci.pd) { + + /* + * Reinject the instruction processing damages' machine checks + * including Delayed Access Exception into the guest + * instead of damaging the host if they happen in the guest. + */ + if (mci.pd && !test_cpu_flag(CIF_MCCK_GUEST)) { if (mci.b) { /* Processing backup -> verify if we can survive this */ u64 z_mcic, o_mcic, t_mcic; @@ -345,6 +381,14 @@ void notrace s390_do_machine_check(struct pt_regs *regs) mcck->mcck_code = mci.val; set_cpu_flag(CIF_MCCK_PENDING); } + + /* + * Backup the machine check's info if it happens when the guest + * is running. + */ + if (test_cpu_flag(CIF_MCCK_GUEST)) + s390_backup_mcck_info(regs); + if (mci.cd) { /* Timing facility damage */ s390_handle_damage(); @@ -358,15 +402,22 @@ void notrace s390_do_machine_check(struct pt_regs *regs) if (mcck->stp_queue) set_cpu_flag(CIF_MCCK_PENDING); } - if (mci.se) - /* Storage error uncorrected */ - s390_handle_damage(); - if (mci.ke) - /* Storage key-error uncorrected */ - s390_handle_damage(); - if (mci.ds && mci.fa) - /* Storage degradation */ - s390_handle_damage(); + + /* + * Reinject storage related machine checks into the guest if they + * happen when the guest is running. + */ + if (!test_cpu_flag(CIF_MCCK_GUEST)) { + if (mci.se) + /* Storage error uncorrected */ + s390_handle_damage(); + if (mci.ke) + /* Storage key-error uncorrected */ + s390_handle_damage(); + if (mci.ds && mci.fa) + /* Storage degradation */ + s390_handle_damage(); + } if (mci.cp) { /* Channel report word pending */ mcck->channel_report = 1; @@ -377,6 +428,19 @@ void notrace s390_do_machine_check(struct pt_regs *regs) mcck->warning = 1; set_cpu_flag(CIF_MCCK_PENDING); } + + /* + * If there are only Channel Report Pending and External Damage + * machine checks, they will not be reinjected into the guest + * because they refer to host conditions only. + */ + mcck_dam_code = (mci.val & MCIC_SUBCLASS_MASK); + if (test_cpu_flag(CIF_MCCK_GUEST) && + (mcck_dam_code & MCCK_CODE_NO_GUEST) != mcck_dam_code) { + /* Set exit reason code for host's later handling */ + *((long *)(regs->gprs[15] + __SF_SIE_REASON)) = -EINTR; + } + clear_cpu_flag(CIF_MCCK_GUEST); nmi_exit(); } diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index ca960d0370d5..0c82f7903fc7 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -995,11 +995,11 @@ static int perf_push_sample(struct perf_event *event, struct sf_raw_sample *sfr) regs.int_parm = CPU_MF_INT_SF_PRA; sde_regs = (struct perf_sf_sde_regs *) ®s.int_parm_long; - psw_bits(regs.psw).ia = sfr->basic.ia; - psw_bits(regs.psw).t = sfr->basic.T; - psw_bits(regs.psw).w = sfr->basic.W; - psw_bits(regs.psw).p = sfr->basic.P; - psw_bits(regs.psw).as = sfr->basic.AS; + psw_bits(regs.psw).ia = sfr->basic.ia; + psw_bits(regs.psw).dat = sfr->basic.T; + psw_bits(regs.psw).wait = sfr->basic.W; + psw_bits(regs.psw).per = sfr->basic.P; + psw_bits(regs.psw).as = sfr->basic.AS; /* * Use the hardware provided configuration level to decide if the diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c index 955a7b6fa0a4..93a386f4a3b5 100644 --- a/arch/s390/kernel/perf_event.c +++ b/arch/s390/kernel/perf_event.c @@ -245,6 +245,5 @@ ssize_t cpumf_events_sysfs_show(struct device *dev, struct perf_pmu_events_attr *pmu_attr; pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr); - return sprintf(page, "event=0x%04llx,name=%s\n", - pmu_attr->id, attr->attr.name); + return sprintf(page, "event=0x%04llx\n", pmu_attr->id); } diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 999d7154bbdc..bb32b8618bf6 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -41,31 +41,6 @@ asmlinkage void ret_from_fork(void) asm ("ret_from_fork"); -/* - * Return saved PC of a blocked thread. used in kernel/sched. - * resume in entry.S does not create a new stack frame, it - * just stores the registers %r6-%r15 to the frame given by - * schedule. We want to return the address of the caller of - * schedule, so we have to walk the backchain one time to - * find the frame schedule() store its return address. - */ -unsigned long thread_saved_pc(struct task_struct *tsk) -{ - struct stack_frame *sf, *low, *high; - - if (!tsk || !task_stack_page(tsk)) - return 0; - low = task_stack_page(tsk); - high = (struct stack_frame *) task_pt_regs(tsk); - sf = (struct stack_frame *) tsk->thread.ksp; - if (sf <= low || sf > high) - return 0; - sf = (struct stack_frame *) sf->back_chain; - if (sf <= low || sf > high) - return 0; - return sf->gprs[8]; -} - extern void kernel_thread_starter(void); /* diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index 488c5bb8dc77..252ed61a128b 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -1160,6 +1160,8 @@ static int s390_gs_cb_get(struct task_struct *target, return -ENODEV; if (!data) return -ENODATA; + if (target == current) + save_gs_cb(data); return user_regset_copyout(&pos, &count, &kbuf, &ubuf, data, 0, sizeof(struct gs_cb)); } @@ -1170,6 +1172,7 @@ static int s390_gs_cb_set(struct task_struct *target, const void *kbuf, const void __user *ubuf) { struct gs_cb *data = target->thread.gs_cb; + int rc; if (!MACHINE_HAS_GS) return -ENODEV; @@ -1177,10 +1180,18 @@ static int s390_gs_cb_set(struct task_struct *target, data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; + data->gsd = 25; target->thread.gs_cb = data; + if (target == current) + __ctl_set_bit(2, 4); + } else if (target == current) { + save_gs_cb(data); } - return user_regset_copyin(&pos, &count, &kbuf, &ubuf, - data, 0, sizeof(struct gs_cb)); + rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + data, 0, sizeof(struct gs_cb)); + if (target == current) + restore_gs_cb(data); + return rc; } static int s390_gs_bc_get(struct task_struct *target, diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 363000a77ffc..1020a11a24e5 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -26,6 +26,7 @@ #include <linux/err.h> #include <linux/spinlock.h> #include <linux/kernel_stat.h> +#include <linux/kmemleak.h> #include <linux/delay.h> #include <linux/interrupt.h> #include <linux/irqflags.h> @@ -207,6 +208,8 @@ static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu) kmem_cache_alloc(pcpu_mcesa_cache, GFP_KERNEL); if (!mcesa_origin) goto out; + /* The pointer is stored with mcesa_bits ORed in */ + kmemleak_not_leak((void *) mcesa_origin); mcesa_bits = MACHINE_HAS_GS ? 11 : 0; } } else { diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c index eefcb54872a5..fb869b103825 100644 --- a/arch/s390/kernel/sysinfo.c +++ b/arch/s390/kernel/sysinfo.c @@ -242,7 +242,7 @@ static void print_ext_name(struct seq_file *m, int lvl, static void print_uuid(struct seq_file *m, int i, struct sysinfo_3_2_2 *info) { - if (!memcmp(&info->vm[i].uuid, &NULL_UUID_BE, sizeof(uuid_be))) + if (uuid_is_null(&info->vm[i].uuid)) return; seq_printf(m, "VM%02d UUID: %pUb\n", i, &info->vm[i].uuid); } diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c index f787b9d8f54c..442e5423ce3d 100644 --- a/arch/s390/kernel/traps.c +++ b/arch/s390/kernel/traps.c @@ -21,6 +21,7 @@ #include <linux/mm.h> #include <linux/slab.h> #include <linux/uaccess.h> +#include <linux/cpu.h> #include <asm/fpu/api.h> #include "entry.h" diff --git a/arch/s390/kernel/uprobes.c b/arch/s390/kernel/uprobes.c index 314e0ee3016a..d94baa8db507 100644 --- a/arch/s390/kernel/uprobes.c +++ b/arch/s390/kernel/uprobes.c @@ -27,12 +27,12 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) { - if (psw_bits(regs->psw).eaba == PSW_AMODE_24BIT) + if (psw_bits(regs->psw).eaba == PSW_BITS_AMODE_24BIT) return -EINVAL; - if (!is_compat_task() && psw_bits(regs->psw).eaba == PSW_AMODE_31BIT) + if (!is_compat_task() && psw_bits(regs->psw).eaba == PSW_BITS_AMODE_31BIT) return -EINVAL; clear_pt_regs_flag(regs, PIF_PER_TRAP); - auprobe->saved_per = psw_bits(regs->psw).r; + auprobe->saved_per = psw_bits(regs->psw).per; auprobe->saved_int_code = regs->int_code; regs->int_code = UPROBE_TRAP_NR; regs->psw.addr = current->utask->xol_vaddr; @@ -81,7 +81,7 @@ int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) clear_tsk_thread_flag(current, TIF_UPROBE_SINGLESTEP); update_cr_regs(current); - psw_bits(regs->psw).r = auprobe->saved_per; + psw_bits(regs->psw).per = auprobe->saved_per; regs->int_code = auprobe->saved_int_code; if (fixup & FIXUP_PSW_NORMAL) @@ -372,8 +372,8 @@ static void handle_insn_ril(struct arch_uprobe *auprobe, struct pt_regs *regs) bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) { - if ((psw_bits(regs->psw).eaba == PSW_AMODE_24BIT) || - ((psw_bits(regs->psw).eaba == PSW_AMODE_31BIT) && + if ((psw_bits(regs->psw).eaba == PSW_BITS_AMODE_24BIT) || + ((psw_bits(regs->psw).eaba == PSW_BITS_AMODE_31BIT) && !is_compat_task())) { regs->psw.addr = __rewind_psw(regs->psw, UPROBE_SWBP_INSN_SIZE); do_report_trap(regs, SIGILL, ILL_ILLADR, NULL); diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c index 10516ae3b55e..b89d19f6f2ab 100644 --- a/arch/s390/kernel/vdso.c +++ b/arch/s390/kernel/vdso.c @@ -50,6 +50,56 @@ static struct page **vdso64_pagelist; */ unsigned int __read_mostly vdso_enabled = 1; +static int vdso_fault(const struct vm_special_mapping *sm, + struct vm_area_struct *vma, struct vm_fault *vmf) +{ + struct page **vdso_pagelist; + unsigned long vdso_pages; + + vdso_pagelist = vdso64_pagelist; + vdso_pages = vdso64_pages; +#ifdef CONFIG_COMPAT + if (is_compat_task()) { + vdso_pagelist = vdso32_pagelist; + vdso_pages = vdso32_pages; + } +#endif + + if (vmf->pgoff >= vdso_pages) + return VM_FAULT_SIGBUS; + + vmf->page = vdso_pagelist[vmf->pgoff]; + get_page(vmf->page); + return 0; +} + +static int vdso_mremap(const struct vm_special_mapping *sm, + struct vm_area_struct *vma) +{ + unsigned long vdso_pages; + + vdso_pages = vdso64_pages; +#ifdef CONFIG_COMPAT + if (is_compat_task()) + vdso_pages = vdso32_pages; +#endif + + if ((vdso_pages << PAGE_SHIFT) != vma->vm_end - vma->vm_start) + return -EINVAL; + + if (WARN_ON_ONCE(current->mm != vma->vm_mm)) + return -EFAULT; + + current->mm->context.vdso_base = vma->vm_start; + return 0; +} + +static const struct vm_special_mapping vdso_mapping = { + .name = "[vdso]", + .fault = vdso_fault, + .mremap = vdso_mremap, +}; + static int __init vdso_setup(char *s) { unsigned long val; @@ -181,7 +231,7 @@ static void vdso_init_cr5(void) int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { struct mm_struct *mm = current->mm; - struct page **vdso_pagelist; + struct vm_area_struct *vma; unsigned long vdso_pages; unsigned long vdso_base; int rc; @@ -194,13 +244,10 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) if (!uses_interp) return 0; - vdso_pagelist = vdso64_pagelist; vdso_pages = vdso64_pages; #ifdef CONFIG_COMPAT - if (is_compat_task()) { - vdso_pagelist = vdso32_pagelist; + if (is_compat_task()) vdso_pages = vdso32_pages; - } #endif /* * vDSO has a problem and was disabled, just don't "enable" it for @@ -209,8 +256,6 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) if (vdso_pages == 0) return 0; - current->mm->context.vdso_base = 0; - /* * pick a base address for the vDSO in process space. We try to put * it at vdso_base which is the "natural" base for it, but we might @@ -225,13 +270,6 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) } /* - * Put vDSO base into mm struct. We need to do this before calling - * install_special_mapping or the perf counter mmap tracking code - * will fail to recognise it as a vDSO (since arch_vma_name fails). - */ - current->mm->context.vdso_base = vdso_base; - - /* * our vma flags don't have VM_WRITE so by default, the process * isn't allowed to write those pages. * gdb can break that with ptrace interface, and thus trigger COW @@ -241,24 +279,23 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) * It's fine to use that for setting breakpoints in the vDSO code * pages though. */ - rc = install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT, - VM_READ|VM_EXEC| - VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, - vdso_pagelist); - if (rc) - current->mm->context.vdso_base = 0; + vma = _install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT, + VM_READ|VM_EXEC| + VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, + &vdso_mapping); + if (IS_ERR(vma)) { + rc = PTR_ERR(vma); + goto out_up; + } + + current->mm->context.vdso_base = vdso_base; + rc = 0; + out_up: up_write(&mm->mmap_sem); return rc; } -const char *arch_vma_name(struct vm_area_struct *vma) -{ - if (vma->vm_mm && vma->vm_start == vma->vm_mm->context.vdso_base) - return "[vdso]"; - return NULL; -} - static int __init vdso_init(void) { int i; diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index 072d84ba42a3..dd7178fbb4f3 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -110,11 +110,10 @@ static inline u64 scale_vtime(u64 vtime) return vtime; } -static void account_system_index_scaled(struct task_struct *p, - u64 cputime, u64 scaled, +static void account_system_index_scaled(struct task_struct *p, u64 cputime, enum cpu_usage_stat index) { - p->stimescaled += cputime_to_nsecs(scaled); + p->stimescaled += cputime_to_nsecs(scale_vtime(cputime)); account_system_index_time(p, cputime_to_nsecs(cputime), index); } @@ -176,14 +175,11 @@ static int do_account_vtime(struct task_struct *tsk) } if (system) - account_system_index_scaled(tsk, system, scale_vtime(system), - CPUTIME_SYSTEM); + account_system_index_scaled(tsk, system, CPUTIME_SYSTEM); if (hardirq) - account_system_index_scaled(tsk, hardirq, scale_vtime(hardirq), - CPUTIME_IRQ); + account_system_index_scaled(tsk, hardirq, CPUTIME_IRQ); if (softirq) - account_system_index_scaled(tsk, softirq, scale_vtime(softirq), - CPUTIME_SOFTIRQ); + account_system_index_scaled(tsk, softirq, CPUTIME_SOFTIRQ); steal = S390_lowcore.steal_timer; if ((s64) steal > 0) { diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index 9da243d94cc3..875f8bea8c67 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -551,26 +551,26 @@ static int get_vcpu_asce(struct kvm_vcpu *vcpu, union asce *asce, int rc; struct psw_bits psw = psw_bits(vcpu->arch.sie_block->gpsw); - if (!psw.t) { + if (!psw.dat) { asce->val = 0; asce->r = 1; return 0; } - if (mode == GACC_IFETCH) - psw.as = psw.as == PSW_AS_HOME ? PSW_AS_HOME : PSW_AS_PRIMARY; + if ((mode == GACC_IFETCH) && (psw.as != PSW_BITS_AS_HOME)) + psw.as = PSW_BITS_AS_PRIMARY; switch (psw.as) { - case PSW_AS_PRIMARY: + case PSW_BITS_AS_PRIMARY: asce->val = vcpu->arch.sie_block->gcr[1]; return 0; - case PSW_AS_SECONDARY: + case PSW_BITS_AS_SECONDARY: asce->val = vcpu->arch.sie_block->gcr[7]; return 0; - case PSW_AS_HOME: + case PSW_BITS_AS_HOME: asce->val = vcpu->arch.sie_block->gcr[13]; return 0; - case PSW_AS_ACCREG: + case PSW_BITS_AS_ACCREG: rc = ar_translation(vcpu, asce, ar, mode); if (rc > 0) return trans_exc(vcpu, rc, ga, ar, mode, PROT_TYPE_ALC); @@ -771,7 +771,7 @@ static int low_address_protection_enabled(struct kvm_vcpu *vcpu, if (!ctlreg0.lap) return 0; - if (psw_bits(*psw).t && asce.p) + if (psw_bits(*psw).dat && asce.p) return 0; return 1; } @@ -790,7 +790,7 @@ static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, return trans_exc(vcpu, PGM_PROTECTION, ga, ar, mode, PROT_TYPE_LA); ga &= PAGE_MASK; - if (psw_bits(*psw).t) { + if (psw_bits(*psw).dat) { rc = guest_translate(vcpu, ga, pages, asce, mode); if (rc < 0) return rc; @@ -831,7 +831,7 @@ int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, void *data, pages = vmalloc(nr_pages * sizeof(unsigned long)); if (!pages) return -ENOMEM; - need_ipte_lock = psw_bits(*psw).t && !asce.r; + need_ipte_lock = psw_bits(*psw).dat && !asce.r; if (need_ipte_lock) ipte_lock(vcpu); rc = guest_page_range(vcpu, ga, ar, pages, nr_pages, asce, mode); @@ -899,7 +899,7 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar, mode, PROT_TYPE_LA); } - if (psw_bits(*psw).t && !asce.r) { /* Use DAT? */ + if (psw_bits(*psw).dat && !asce.r) { /* Use DAT? */ rc = guest_translate(vcpu, gva, gpa, asce, mode); if (rc > 0) return trans_exc(vcpu, rc, gva, 0, mode, PROT_TYPE_DAT); @@ -977,11 +977,12 @@ static int kvm_s390_shadow_tables(struct gmap *sg, unsigned long saddr, ptr = asce.origin * 4096; if (asce.r) { *fake = 1; + ptr = 0; asce.dt = ASCE_TYPE_REGION1; } switch (asce.dt) { case ASCE_TYPE_REGION1: - if (vaddr.rfx01 > asce.tl && !asce.r) + if (vaddr.rfx01 > asce.tl && !*fake) return PGM_REGION_FIRST_TRANS; break; case ASCE_TYPE_REGION2: @@ -1009,8 +1010,7 @@ static int kvm_s390_shadow_tables(struct gmap *sg, unsigned long saddr, union region1_table_entry rfte; if (*fake) { - /* offset in 16EB guest memory block */ - ptr = ptr + ((unsigned long) vaddr.rsx << 53UL); + ptr += (unsigned long) vaddr.rfx << 53; rfte.val = ptr; goto shadow_r2t; } @@ -1036,8 +1036,7 @@ shadow_r2t: union region2_table_entry rste; if (*fake) { - /* offset in 8PB guest memory block */ - ptr = ptr + ((unsigned long) vaddr.rtx << 42UL); + ptr += (unsigned long) vaddr.rsx << 42; rste.val = ptr; goto shadow_r3t; } @@ -1064,8 +1063,7 @@ shadow_r3t: union region3_table_entry rtte; if (*fake) { - /* offset in 4TB guest memory block */ - ptr = ptr + ((unsigned long) vaddr.sx << 31UL); + ptr += (unsigned long) vaddr.rtx << 31; rtte.val = ptr; goto shadow_sgt; } @@ -1101,8 +1099,7 @@ shadow_sgt: union segment_table_entry ste; if (*fake) { - /* offset in 2G guest memory block */ - ptr = ptr + ((unsigned long) vaddr.sx << 20UL); + ptr += (unsigned long) vaddr.sx << 20; ste.val = ptr; goto shadow_pgt; } diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h index 7ce47fd36f28..bec42b852246 100644 --- a/arch/s390/kvm/gaccess.h +++ b/arch/s390/kvm/gaccess.h @@ -57,9 +57,9 @@ static inline unsigned long kvm_s390_logical_to_effective(struct kvm_vcpu *vcpu, { psw_t *psw = &vcpu->arch.sie_block->gpsw; - if (psw_bits(*psw).eaba == PSW_AMODE_64BIT) + if (psw_bits(*psw).eaba == PSW_BITS_AMODE_64BIT) return ga; - if (psw_bits(*psw).eaba == PSW_AMODE_31BIT) + if (psw_bits(*psw).eaba == PSW_BITS_AMODE_31BIT) return ga & ((1UL << 31) - 1); return ga & ((1UL << 24) - 1); } diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c index 23d9a4e12da1..c2e0ddc1356e 100644 --- a/arch/s390/kvm/guestdbg.c +++ b/arch/s390/kvm/guestdbg.c @@ -613,15 +613,15 @@ int kvm_s390_handle_per_event(struct kvm_vcpu *vcpu) * instruction. Check primary and home space-switch-event * controls. (theoretically home -> home produced no event) */ - if (((new_as == PSW_AS_HOME) ^ old_as_is_home(vcpu)) && - (pssec(vcpu) || hssec(vcpu))) + if (((new_as == PSW_BITS_AS_HOME) ^ old_as_is_home(vcpu)) && + (pssec(vcpu) || hssec(vcpu))) vcpu->arch.sie_block->iprcc = PGM_SPACE_SWITCH; /* * PT, PTI, PR, PC instruction operate on primary AS only. Check * if the primary-space-switch-event control was or got set. */ - if (new_as == PSW_AS_PRIMARY && !old_as_is_home(vcpu) && + if (new_as == PSW_BITS_AS_PRIMARY && !old_as_is_home(vcpu) && (pssec(vcpu) || old_ssec(vcpu))) vcpu->arch.sie_block->iprcc = PGM_SPACE_SWITCH; } diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index f28e2e776931..b0d7de5a533d 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2067,6 +2067,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, if (!vcpu) goto out; + BUILD_BUG_ON(sizeof(struct sie_page) != 4096); sie_page = (struct sie_page *) get_zeroed_page(GFP_KERNEL); if (!sie_page) goto out_free_cpu; diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index c03106c428cf..e53292a89257 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -361,7 +361,7 @@ static int handle_sske(struct kvm_vcpu *vcpu) } } if (m3 & SSKE_MB) { - if (psw_bits(vcpu->arch.sie_block->gpsw).eaba == PSW_AMODE_64BIT) + if (psw_bits(vcpu->arch.sie_block->gpsw).eaba == PSW_BITS_AMODE_64BIT) vcpu->run->s.regs.gprs[reg2] &= ~PAGE_MASK; else vcpu->run->s.regs.gprs[reg2] &= ~0xfffff000UL; @@ -374,7 +374,7 @@ static int handle_sske(struct kvm_vcpu *vcpu) static int handle_ipte_interlock(struct kvm_vcpu *vcpu) { vcpu->stat.instruction_ipte_interlock++; - if (psw_bits(vcpu->arch.sie_block->gpsw).p) + if (psw_bits(vcpu->arch.sie_block->gpsw).pstate) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); wait_event(vcpu->kvm->arch.ipte_wq, !ipte_lock_held(vcpu)); kvm_s390_retry_instr(vcpu); @@ -901,7 +901,7 @@ static int handle_pfmf(struct kvm_vcpu *vcpu) /* only support 2G frame size if EDAT2 is available and we are not in 24-bit addressing mode */ if (!test_kvm_facility(vcpu->kvm, 78) || - psw_bits(vcpu->arch.sie_block->gpsw).eaba == PSW_AMODE_24BIT) + psw_bits(vcpu->arch.sie_block->gpsw).eaba == PSW_BITS_AMODE_24BIT) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); end = (start + (1UL << 31)) & ~((1UL << 31) - 1); break; @@ -938,7 +938,7 @@ static int handle_pfmf(struct kvm_vcpu *vcpu) start += PAGE_SIZE; } if (vcpu->run->s.regs.gprs[reg1] & PFMF_FSC) { - if (psw_bits(vcpu->arch.sie_block->gpsw).eaba == PSW_AMODE_64BIT) { + if (psw_bits(vcpu->arch.sie_block->gpsw).eaba == PSW_BITS_AMODE_64BIT) { vcpu->run->s.regs.gprs[reg2] = end; } else { vcpu->run->s.regs.gprs[reg2] &= ~0xffffffffUL; diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c index 1b553d847140..049c3c455b32 100644 --- a/arch/s390/mm/dump_pagetables.c +++ b/arch/s390/mm/dump_pagetables.c @@ -149,7 +149,7 @@ static void walk_pmd_level(struct seq_file *m, struct pg_state *st, } static void walk_pud_level(struct seq_file *m, struct pg_state *st, - pgd_t *pgd, unsigned long addr) + p4d_t *p4d, unsigned long addr) { unsigned int prot; pud_t *pud; @@ -157,7 +157,7 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, for (i = 0; i < PTRS_PER_PUD && addr < max_addr; i++) { st->current_address = addr; - pud = pud_offset(pgd, addr); + pud = pud_offset(p4d, addr); if (!pud_none(*pud)) if (pud_large(*pud)) { prot = pud_val(*pud) & @@ -172,6 +172,23 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, } } +static void walk_p4d_level(struct seq_file *m, struct pg_state *st, + pgd_t *pgd, unsigned long addr) +{ + p4d_t *p4d; + int i; + + for (i = 0; i < PTRS_PER_P4D && addr < max_addr; i++) { + st->current_address = addr; + p4d = p4d_offset(pgd, addr); + if (!p4d_none(*p4d)) + walk_pud_level(m, st, p4d, addr); + else + note_page(m, st, _PAGE_INVALID, 2); + addr += P4D_SIZE; + } +} + static void walk_pgd_level(struct seq_file *m) { unsigned long addr = 0; @@ -184,7 +201,7 @@ static void walk_pgd_level(struct seq_file *m) st.current_address = addr; pgd = pgd_offset_k(addr); if (!pgd_none(*pgd)) - walk_pud_level(m, &st, pgd, addr); + walk_p4d_level(m, &st, pgd, addr); else note_page(m, &st, _PAGE_INVALID, 1); addr += PGDIR_SIZE; diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 5845d3028ffc..14f25798b001 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -130,7 +130,7 @@ static int bad_address(void *p) static void dump_pagetable(unsigned long asce, unsigned long address) { - unsigned long *table = __va(asce & PAGE_MASK); + unsigned long *table = __va(asce & _ASCE_ORIGIN); pr_alert("AS:%016lx ", asce); switch (asce & _ASCE_TYPE_MASK) { diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 7f6db1e6c048..4fb3d3cdb370 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -125,7 +125,7 @@ static void gmap_radix_tree_free(struct radix_tree_root *root) struct radix_tree_iter iter; unsigned long indices[16]; unsigned long index; - void **slot; + void __rcu **slot; int i, nr; /* A radix tree is freed by deleting all of its entries */ @@ -150,7 +150,7 @@ static void gmap_rmap_radix_tree_free(struct radix_tree_root *root) struct radix_tree_iter iter; unsigned long indices[16]; unsigned long index; - void **slot; + void __rcu **slot; int i, nr; /* A radix tree is freed by deleting all of its entries */ @@ -537,6 +537,7 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr) unsigned long *table; spinlock_t *ptl; pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; int rc; @@ -573,7 +574,9 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr) mm = gmap->mm; pgd = pgd_offset(mm, vmaddr); VM_BUG_ON(pgd_none(*pgd)); - pud = pud_offset(pgd, vmaddr); + p4d = p4d_offset(pgd, vmaddr); + VM_BUG_ON(p4d_none(*p4d)); + pud = pud_offset(p4d, vmaddr); VM_BUG_ON(pud_none(*pud)); /* large puds cannot yet be handled */ if (pud_large(*pud)) @@ -1008,7 +1011,7 @@ EXPORT_SYMBOL_GPL(gmap_read_table); static inline void gmap_insert_rmap(struct gmap *sg, unsigned long vmaddr, struct gmap_rmap *rmap) { - void **slot; + void __rcu **slot; BUG_ON(!gmap_is_shadow(sg)); slot = radix_tree_lookup_slot(&sg->host_to_rmap, vmaddr >> PAGE_SHIFT); diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c index b7b779c40a5b..8ecc25e760fa 100644 --- a/arch/s390/mm/gup.c +++ b/arch/s390/mm/gup.c @@ -166,15 +166,15 @@ static int gup_huge_pud(pud_t *pudp, pud_t pud, unsigned long addr, return 1; } -static inline int gup_pud_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr, +static inline int gup_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { unsigned long next; pud_t *pudp, pud; - pudp = (pud_t *) pgdp; - if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2) - pudp = (pud_t *) pgd_deref(pgd); + pudp = (pud_t *) p4dp; + if ((p4d_val(p4d) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2) + pudp = (pud_t *) p4d_deref(p4d); pudp += pud_index(addr); do { pud = *pudp; @@ -194,6 +194,29 @@ static inline int gup_pud_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr, return 1; } +static inline int gup_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr, + unsigned long end, int write, struct page **pages, int *nr) +{ + unsigned long next; + p4d_t *p4dp, p4d; + + p4dp = (p4d_t *) pgdp; + if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R1) + p4dp = (p4d_t *) pgd_deref(pgd); + p4dp += p4d_index(addr); + do { + p4d = *p4dp; + barrier(); + next = p4d_addr_end(addr, end); + if (p4d_none(p4d)) + return 0; + if (!gup_pud_range(p4dp, p4d, addr, next, write, pages, nr)) + return 0; + } while (p4dp++, addr = next, addr != end); + + return 1; +} + /* * Like get_user_pages_fast() except its IRQ-safe in that it won't fall * back to the regular GUP. @@ -228,7 +251,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, next = pgd_addr_end(addr, end); if (pgd_none(pgd)) break; - if (!gup_pud_range(pgdp, pgd, addr, next, write, pages, &nr)) + if (!gup_p4d_range(pgdp, pgd, addr, next, write, pages, &nr)) break; } while (pgdp++, addr = next, addr != end); local_irq_restore(flags); diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index 9b4050caa4e9..d3a5e39756f6 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -162,16 +162,20 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz) { pgd_t *pgdp; + p4d_t *p4dp; pud_t *pudp; pmd_t *pmdp = NULL; pgdp = pgd_offset(mm, addr); - pudp = pud_alloc(mm, pgdp, addr); - if (pudp) { - if (sz == PUD_SIZE) - return (pte_t *) pudp; - else if (sz == PMD_SIZE) - pmdp = pmd_alloc(mm, pudp, addr); + p4dp = p4d_alloc(mm, pgdp, addr); + if (p4dp) { + pudp = pud_alloc(mm, p4dp, addr); + if (pudp) { + if (sz == PUD_SIZE) + return (pte_t *) pudp; + else if (sz == PMD_SIZE) + pmdp = pmd_alloc(mm, pudp, addr); + } } return (pte_t *) pmdp; } @@ -179,16 +183,20 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) { pgd_t *pgdp; + p4d_t *p4dp; pud_t *pudp; pmd_t *pmdp = NULL; pgdp = pgd_offset(mm, addr); if (pgd_present(*pgdp)) { - pudp = pud_offset(pgdp, addr); - if (pud_present(*pudp)) { - if (pud_large(*pudp)) - return (pte_t *) pudp; - pmdp = pmd_offset(pudp, addr); + p4dp = p4d_offset(pgdp, addr); + if (p4d_present(*p4dp)) { + pudp = pud_offset(p4dp, addr); + if (pud_present(*pudp)) { + if (pud_large(*pudp)) + return (pte_t *) pudp; + pmdp = pmd_offset(pudp, addr); + } } } return (pte_t *) pmdp; diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index ee6a1d3d4983..3348e60dd8ad 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -81,6 +81,7 @@ void __init paging_init(void) { unsigned long max_zone_pfns[MAX_NR_ZONES]; unsigned long pgd_type, asce_bits; + psw_t psw; init_mm.pgd = swapper_pg_dir; if (VMALLOC_END > (1UL << 42)) { @@ -100,7 +101,10 @@ void __init paging_init(void) __ctl_load(S390_lowcore.kernel_asce, 1, 1); __ctl_load(S390_lowcore.kernel_asce, 7, 7); __ctl_load(S390_lowcore.kernel_asce, 13, 13); - __arch_local_irq_stosm(0x04); + psw.mask = __extract_psw(); + psw_bits(psw).dat = 1; + psw_bits(psw).as = PSW_BITS_AS_HOME; + __load_psw_mask(psw.mask); sparse_memory_present_with_active_regions(MAX_NUMNODES); sparse_init(); diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index b854b1da281a..2e10d2b8ad35 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -120,7 +120,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, check_asce_limit: if (addr + len > current->mm->context.asce_limit) { - rc = crst_table_upgrade(mm); + rc = crst_table_upgrade(mm, addr + len); if (rc) return (unsigned long) rc; } @@ -184,7 +184,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, check_asce_limit: if (addr + len > current->mm->context.asce_limit) { - rc = crst_table_upgrade(mm); + rc = crst_table_upgrade(mm, addr + len); if (rc) return (unsigned long) rc; } diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c index 49e721f3645e..180481589246 100644 --- a/arch/s390/mm/pageattr.c +++ b/arch/s390/mm/pageattr.c @@ -229,14 +229,14 @@ static void modify_pud_page(pud_t *pudp, unsigned long addr, pgt_set((unsigned long *)pudp, pud_val(new), addr, CRDTE_DTT_REGION3); } -static int walk_pud_level(pgd_t *pgd, unsigned long addr, unsigned long end, +static int walk_pud_level(p4d_t *p4d, unsigned long addr, unsigned long end, unsigned long flags) { unsigned long next; pud_t *pudp; int rc = 0; - pudp = pud_offset(pgd, addr); + pudp = pud_offset(p4d, addr); do { if (pud_none(*pudp)) return -EINVAL; @@ -259,6 +259,26 @@ static int walk_pud_level(pgd_t *pgd, unsigned long addr, unsigned long end, return rc; } +static int walk_p4d_level(pgd_t *pgd, unsigned long addr, unsigned long end, + unsigned long flags) +{ + unsigned long next; + p4d_t *p4dp; + int rc = 0; + + p4dp = p4d_offset(pgd, addr); + do { + if (p4d_none(*p4dp)) + return -EINVAL; + next = p4d_addr_end(addr, end); + rc = walk_pud_level(p4dp, addr, next, flags); + p4dp++; + addr = next; + cond_resched(); + } while (addr < end && !rc); + return rc; +} + static DEFINE_MUTEX(cpa_mutex); static int change_page_attr(unsigned long addr, unsigned long end, @@ -278,7 +298,7 @@ static int change_page_attr(unsigned long addr, unsigned long end, if (pgd_none(*pgdp)) break; next = pgd_addr_end(addr, end); - rc = walk_pud_level(pgdp, addr, next, flags); + rc = walk_p4d_level(pgdp, addr, next, flags); if (rc) break; cond_resched(); @@ -319,6 +339,7 @@ void __kernel_map_pages(struct page *page, int numpages, int enable) unsigned long address; int nr, i, j; pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -326,7 +347,8 @@ void __kernel_map_pages(struct page *page, int numpages, int enable) for (i = 0; i < numpages;) { address = page_to_phys(page + i); pgd = pgd_offset_k(address); - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + pud = pud_offset(p4d, address); pmd = pmd_offset(pud, address); pte = pte_offset_kernel(pmd, address); nr = (unsigned long)pte >> ilog2(sizeof(long)); diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index f502cbe657af..18918e394ce4 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -76,29 +76,46 @@ static void __crst_table_upgrade(void *arg) __tlb_flush_local(); } -int crst_table_upgrade(struct mm_struct *mm) +int crst_table_upgrade(struct mm_struct *mm, unsigned long end) { unsigned long *table, *pgd; + int rc, notify; - /* upgrade should only happen from 3 to 4 levels */ - BUG_ON(mm->context.asce_limit != (1UL << 42)); - - table = crst_table_alloc(mm); - if (!table) + /* upgrade should only happen from 3 to 4, 3 to 5, or 4 to 5 levels */ + BUG_ON(mm->context.asce_limit < (1UL << 42)); + if (end >= TASK_SIZE_MAX) return -ENOMEM; - - spin_lock_bh(&mm->page_table_lock); - pgd = (unsigned long *) mm->pgd; - crst_table_init(table, _REGION2_ENTRY_EMPTY); - pgd_populate(mm, (pgd_t *) table, (pud_t *) pgd); - mm->pgd = (pgd_t *) table; - mm->context.asce_limit = 1UL << 53; - mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | - _ASCE_USER_BITS | _ASCE_TYPE_REGION2; - spin_unlock_bh(&mm->page_table_lock); - - on_each_cpu(__crst_table_upgrade, mm, 0); - return 0; + rc = 0; + notify = 0; + while (mm->context.asce_limit < end) { + table = crst_table_alloc(mm); + if (!table) { + rc = -ENOMEM; + break; + } + spin_lock_bh(&mm->page_table_lock); + pgd = (unsigned long *) mm->pgd; + if (mm->context.asce_limit == (1UL << 42)) { + crst_table_init(table, _REGION2_ENTRY_EMPTY); + p4d_populate(mm, (p4d_t *) table, (pud_t *) pgd); + mm->pgd = (pgd_t *) table; + mm->context.asce_limit = 1UL << 53; + mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_REGION2; + } else { + crst_table_init(table, _REGION1_ENTRY_EMPTY); + pgd_populate(mm, (pgd_t *) table, (p4d_t *) pgd); + mm->pgd = (pgd_t *) table; + mm->context.asce_limit = -PAGE_SIZE; + mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_REGION1; + } + notify = 1; + spin_unlock_bh(&mm->page_table_lock); + } + if (notify) + on_each_cpu(__crst_table_upgrade, mm, 0); + return rc; } void crst_table_downgrade(struct mm_struct *mm) @@ -274,7 +291,7 @@ static void __tlb_remove_table(void *_table) struct page *page = pfn_to_page(__pa(table) >> PAGE_SHIFT); switch (mask) { - case 0: /* pmd or pud */ + case 0: /* pmd, pud, or p4d */ free_pages((unsigned long) table, 2); break; case 1: /* lower 2K of a 4K page table */ diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 947b66a5cdba..d4d409ba206b 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -610,6 +610,7 @@ bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long addr) { spinlock_t *ptl; pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgste_t pgste; @@ -618,7 +619,10 @@ bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long addr) bool dirty; pgd = pgd_offset(mm, addr); - pud = pud_alloc(mm, pgd, addr); + p4d = p4d_alloc(mm, pgd, addr); + if (!p4d) + return false; + pud = pud_alloc(mm, p4d, addr); if (!pud) return false; pmd = pmd_alloc(mm, pud, addr); diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index c33c94b4be60..d8398962a723 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -38,6 +38,17 @@ static void __ref *vmem_alloc_pages(unsigned int order) return (void *) memblock_alloc(size, size); } +static inline p4d_t *vmem_p4d_alloc(void) +{ + p4d_t *p4d = NULL; + + p4d = vmem_alloc_pages(2); + if (!p4d) + return NULL; + clear_table((unsigned long *) p4d, _REGION2_ENTRY_EMPTY, PAGE_SIZE * 4); + return p4d; +} + static inline pud_t *vmem_pud_alloc(void) { pud_t *pud = NULL; @@ -85,6 +96,7 @@ static int vmem_add_mem(unsigned long start, unsigned long size) unsigned long end = start + size; unsigned long address = start; pgd_t *pg_dir; + p4d_t *p4_dir; pud_t *pu_dir; pmd_t *pm_dir; pte_t *pt_dir; @@ -102,12 +114,19 @@ static int vmem_add_mem(unsigned long start, unsigned long size) while (address < end) { pg_dir = pgd_offset_k(address); if (pgd_none(*pg_dir)) { + p4_dir = vmem_p4d_alloc(); + if (!p4_dir) + goto out; + pgd_populate(&init_mm, pg_dir, p4_dir); + } + p4_dir = p4d_offset(pg_dir, address); + if (p4d_none(*p4_dir)) { pu_dir = vmem_pud_alloc(); if (!pu_dir) goto out; - pgd_populate(&init_mm, pg_dir, pu_dir); + p4d_populate(&init_mm, p4_dir, pu_dir); } - pu_dir = pud_offset(pg_dir, address); + pu_dir = pud_offset(p4_dir, address); if (MACHINE_HAS_EDAT2 && pud_none(*pu_dir) && address && !(address & ~PUD_MASK) && (address + PUD_SIZE <= end) && !debug_pagealloc_enabled()) { @@ -161,6 +180,7 @@ static void vmem_remove_range(unsigned long start, unsigned long size) unsigned long end = start + size; unsigned long address = start; pgd_t *pg_dir; + p4d_t *p4_dir; pud_t *pu_dir; pmd_t *pm_dir; pte_t *pt_dir; @@ -172,7 +192,12 @@ static void vmem_remove_range(unsigned long start, unsigned long size) address += PGDIR_SIZE; continue; } - pu_dir = pud_offset(pg_dir, address); + p4_dir = p4d_offset(pg_dir, address); + if (p4d_none(*p4_dir)) { + address += P4D_SIZE; + continue; + } + pu_dir = pud_offset(p4_dir, address); if (pud_none(*pu_dir)) { address += PUD_SIZE; continue; @@ -213,6 +238,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) unsigned long pgt_prot, sgt_prot; unsigned long address = start; pgd_t *pg_dir; + p4d_t *p4_dir; pud_t *pu_dir; pmd_t *pm_dir; pte_t *pt_dir; @@ -227,13 +253,21 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) for (address = start; address < end;) { pg_dir = pgd_offset_k(address); if (pgd_none(*pg_dir)) { + p4_dir = vmem_p4d_alloc(); + if (!p4_dir) + goto out; + pgd_populate(&init_mm, pg_dir, p4_dir); + } + + p4_dir = p4d_offset(pg_dir, address); + if (p4d_none(*p4_dir)) { pu_dir = vmem_pud_alloc(); if (!pu_dir) goto out; - pgd_populate(&init_mm, pg_dir, pu_dir); + p4d_populate(&init_mm, p4_dir, pu_dir); } - pu_dir = pud_offset(pg_dir, address); + pu_dir = pud_offset(p4_dir, address); if (pud_none(*pu_dir)) { pm_dir = vmem_pmd_alloc(); if (!pm_dir) diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 8051df109db3..7b30af5da222 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -86,6 +86,25 @@ struct zpci_dev *get_zdev_by_fid(u32 fid) return zdev; } +void zpci_remove_reserved_devices(void) +{ + struct zpci_dev *tmp, *zdev; + enum zpci_state state; + LIST_HEAD(remove); + + spin_lock(&zpci_list_lock); + list_for_each_entry_safe(zdev, tmp, &zpci_list, entry) { + if (zdev->state == ZPCI_FN_STATE_STANDBY && + !clp_get_state(zdev->fid, &state) && + state == ZPCI_FN_STATE_RESERVED) + list_move_tail(&zdev->entry, &remove); + } + spin_unlock(&zpci_list_lock); + + list_for_each_entry_safe(zdev, tmp, &remove, entry) + zpci_remove_device(zdev); +} + static struct zpci_dev *get_zdev_by_bus(struct pci_bus *bus) { return (bus && bus->sysdata) ? (struct zpci_dev *) bus->sysdata : NULL; @@ -108,6 +127,7 @@ static int zpci_set_airq(struct zpci_dev *zdev) { u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_REG_INT); struct zpci_fib fib = {0}; + u8 status; fib.isc = PCI_ISC; fib.sum = 1; /* enable summary notifications */ @@ -117,60 +137,58 @@ static int zpci_set_airq(struct zpci_dev *zdev) fib.aisb = (unsigned long) zpci_aisb_iv->vector + (zdev->aisb/64)*8; fib.aisbo = zdev->aisb & 63; - return zpci_mod_fc(req, &fib); + return zpci_mod_fc(req, &fib, &status) ? -EIO : 0; } -struct mod_pci_args { - u64 base; - u64 limit; - u64 iota; - u64 fmb_addr; -}; - -static int mod_pci(struct zpci_dev *zdev, int fn, u8 dmaas, struct mod_pci_args *args) +/* Modify PCI: Unregister adapter interruptions */ +static int zpci_clear_airq(struct zpci_dev *zdev) { - u64 req = ZPCI_CREATE_REQ(zdev->fh, dmaas, fn); + u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_DEREG_INT); struct zpci_fib fib = {0}; + u8 cc, status; - fib.pba = args->base; - fib.pal = args->limit; - fib.iota = args->iota; - fib.fmb_addr = args->fmb_addr; + cc = zpci_mod_fc(req, &fib, &status); + if (cc == 3 || (cc == 1 && status == 24)) + /* Function already gone or IRQs already deregistered. */ + cc = 0; - return zpci_mod_fc(req, &fib); + return cc ? -EIO : 0; } /* Modify PCI: Register I/O address translation parameters */ int zpci_register_ioat(struct zpci_dev *zdev, u8 dmaas, u64 base, u64 limit, u64 iota) { - struct mod_pci_args args = { base, limit, iota, 0 }; + u64 req = ZPCI_CREATE_REQ(zdev->fh, dmaas, ZPCI_MOD_FC_REG_IOAT); + struct zpci_fib fib = {0}; + u8 status; WARN_ON_ONCE(iota & 0x3fff); - args.iota |= ZPCI_IOTA_RTTO_FLAG; - return mod_pci(zdev, ZPCI_MOD_FC_REG_IOAT, dmaas, &args); + fib.pba = base; + fib.pal = limit; + fib.iota = iota | ZPCI_IOTA_RTTO_FLAG; + return zpci_mod_fc(req, &fib, &status) ? -EIO : 0; } /* Modify PCI: Unregister I/O address translation parameters */ int zpci_unregister_ioat(struct zpci_dev *zdev, u8 dmaas) { - struct mod_pci_args args = { 0, 0, 0, 0 }; - - return mod_pci(zdev, ZPCI_MOD_FC_DEREG_IOAT, dmaas, &args); -} - -/* Modify PCI: Unregister adapter interruptions */ -static int zpci_clear_airq(struct zpci_dev *zdev) -{ - struct mod_pci_args args = { 0, 0, 0, 0 }; + u64 req = ZPCI_CREATE_REQ(zdev->fh, dmaas, ZPCI_MOD_FC_DEREG_IOAT); + struct zpci_fib fib = {0}; + u8 cc, status; - return mod_pci(zdev, ZPCI_MOD_FC_DEREG_INT, 0, &args); + cc = zpci_mod_fc(req, &fib, &status); + if (cc == 3) /* Function already gone. */ + cc = 0; + return cc ? -EIO : 0; } /* Modify PCI: Set PCI function measurement parameters */ int zpci_fmb_enable_device(struct zpci_dev *zdev) { - struct mod_pci_args args = { 0, 0, 0, 0 }; + u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_SET_MEASURE); + struct zpci_fib fib = {0}; + u8 cc, status; if (zdev->fmb || sizeof(*zdev->fmb) < zdev->fmb_length) return -EINVAL; @@ -185,25 +203,35 @@ int zpci_fmb_enable_device(struct zpci_dev *zdev) atomic64_set(&zdev->mapped_pages, 0); atomic64_set(&zdev->unmapped_pages, 0); - args.fmb_addr = virt_to_phys(zdev->fmb); - return mod_pci(zdev, ZPCI_MOD_FC_SET_MEASURE, 0, &args); + fib.fmb_addr = virt_to_phys(zdev->fmb); + cc = zpci_mod_fc(req, &fib, &status); + if (cc) { + kmem_cache_free(zdev_fmb_cache, zdev->fmb); + zdev->fmb = NULL; + } + return cc ? -EIO : 0; } /* Modify PCI: Disable PCI function measurement */ int zpci_fmb_disable_device(struct zpci_dev *zdev) { - struct mod_pci_args args = { 0, 0, 0, 0 }; - int rc; + u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_SET_MEASURE); + struct zpci_fib fib = {0}; + u8 cc, status; if (!zdev->fmb) return -EINVAL; /* Function measurement is disabled if fmb address is zero */ - rc = mod_pci(zdev, ZPCI_MOD_FC_SET_MEASURE, 0, &args); + cc = zpci_mod_fc(req, &fib, &status); + if (cc == 3) /* Function already gone. */ + cc = 0; - kmem_cache_free(zdev_fmb_cache, zdev->fmb); - zdev->fmb = NULL; - return rc; + if (!cc) { + kmem_cache_free(zdev_fmb_cache, zdev->fmb); + zdev->fmb = NULL; + } + return cc ? -EIO : 0; } static int zpci_cfg_load(struct zpci_dev *zdev, int offset, u32 *val, u8 len) @@ -372,22 +400,21 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) struct msi_msg msg; int rc, irq; + zdev->aisb = -1UL; if (type == PCI_CAP_ID_MSI && nvec > 1) return 1; msi_vecs = min_t(unsigned int, nvec, zdev->max_msi); /* Allocate adapter summary indicator bit */ - rc = -EIO; aisb = airq_iv_alloc_bit(zpci_aisb_iv); if (aisb == -1UL) - goto out; + return -EIO; zdev->aisb = aisb; /* Create adapter interrupt vector */ - rc = -ENOMEM; zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK); if (!zdev->aibv) - goto out_si; + return -ENOMEM; /* Wire up shortcut pointer */ zpci_aibv[aisb] = zdev->aibv; @@ -398,10 +425,10 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) rc = -EIO; irq = irq_alloc_desc(0); /* Alloc irq on node 0 */ if (irq < 0) - goto out_msi; + return -ENOMEM; rc = irq_set_msi_desc(irq, msi); if (rc) - goto out_msi; + return rc; irq_set_chip_and_handler(irq, &zpci_irq_chip, handle_simple_irq); msg.data = hwirq; @@ -415,27 +442,9 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) /* Enable adapter interrupts */ rc = zpci_set_airq(zdev); if (rc) - goto out_msi; + return rc; return (msi_vecs == nvec) ? 0 : msi_vecs; - -out_msi: - for_each_pci_msi_entry(msi, pdev) { - if (hwirq-- == 0) - break; - irq_set_msi_desc(msi->irq, NULL); - irq_free_desc(msi->irq); - msi->msg.address_lo = 0; - msi->msg.address_hi = 0; - msi->msg.data = 0; - msi->irq = 0; - } - zpci_aibv[aisb] = NULL; - airq_iv_release(zdev->aibv); -out_si: - airq_iv_free_bit(zpci_aisb_iv, aisb); -out: - return rc; } void arch_teardown_msi_irqs(struct pci_dev *pdev) @@ -451,6 +460,8 @@ void arch_teardown_msi_irqs(struct pci_dev *pdev) /* Release MSI interrupts */ for_each_pci_msi_entry(msi, pdev) { + if (!msi->irq) + continue; if (msi->msi_attrib.is_msix) __pci_msix_desc_mask_irq(msi, 1); else @@ -463,9 +474,15 @@ void arch_teardown_msi_irqs(struct pci_dev *pdev) msi->irq = 0; } - zpci_aibv[zdev->aisb] = NULL; - airq_iv_release(zdev->aibv); - airq_iv_free_bit(zpci_aisb_iv, zdev->aisb); + if (zdev->aisb != -1UL) { + zpci_aibv[zdev->aisb] = NULL; + airq_iv_free_bit(zpci_aisb_iv, zdev->aisb); + zdev->aisb = -1UL; + } + if (zdev->aibv) { + airq_iv_release(zdev->aibv); + zdev->aibv = NULL; + } } static void zpci_map_resources(struct pci_dev *pdev) @@ -719,6 +736,16 @@ static int zpci_alloc_domain(struct zpci_dev *zdev) { if (zpci_unique_uid) { zdev->domain = (u16) zdev->uid; + if (zdev->domain >= ZPCI_NR_DEVICES) + return 0; + + spin_lock(&zpci_domain_lock); + if (test_bit(zdev->domain, zpci_domain)) { + spin_unlock(&zpci_domain_lock); + return -EEXIST; + } + set_bit(zdev->domain, zpci_domain); + spin_unlock(&zpci_domain_lock); return 0; } @@ -735,7 +762,7 @@ static int zpci_alloc_domain(struct zpci_dev *zdev) static void zpci_free_domain(struct zpci_dev *zdev) { - if (zpci_unique_uid) + if (zdev->domain >= ZPCI_NR_DEVICES) return; spin_lock(&zpci_domain_lock); @@ -755,6 +782,7 @@ void pcibios_remove_bus(struct pci_bus *bus) list_del(&zdev->entry); spin_unlock(&zpci_list_lock); + zpci_dbg(3, "rem fid:%x\n", zdev->fid); kfree(zdev); } @@ -847,15 +875,14 @@ out: return rc; } -void zpci_stop_device(struct zpci_dev *zdev) +void zpci_remove_device(struct zpci_dev *zdev) { - zpci_dma_exit_device(zdev); - /* - * Note: SCLP disables fh via set-pci-fn so don't - * do that here. - */ + if (!zdev->bus) + return; + + pci_stop_root_bus(zdev->bus); + pci_remove_root_bus(zdev->bus); } -EXPORT_SYMBOL_GPL(zpci_stop_device); int zpci_report_error(struct pci_dev *pdev, struct zpci_report_error_header *report) diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c index 1c3332ac1957..bd534b4d40e3 100644 --- a/arch/s390/pci/pci_clp.c +++ b/arch/s390/pci/pci_clp.c @@ -193,12 +193,12 @@ out: int clp_add_pci_device(u32 fid, u32 fh, int configured) { struct zpci_dev *zdev; - int rc; + int rc = -ENOMEM; zpci_dbg(3, "add fid:%x, fh:%x, c:%d\n", fid, fh, configured); zdev = kzalloc(sizeof(*zdev), GFP_KERNEL); if (!zdev) - return -ENOMEM; + goto error; zdev->fh = fh; zdev->fid = fid; @@ -219,6 +219,7 @@ int clp_add_pci_device(u32 fid, u32 fh, int configured) return 0; error: + zpci_dbg(0, "add fid:%x, rc:%d\n", fid, rc); kfree(zdev); return rc; } @@ -295,8 +296,8 @@ int clp_disable_fh(struct zpci_dev *zdev) return rc; } -static int clp_list_pci(struct clp_req_rsp_list_pci *rrb, - void (*cb)(struct clp_fh_list_entry *entry)) +static int clp_list_pci(struct clp_req_rsp_list_pci *rrb, void *data, + void (*cb)(struct clp_fh_list_entry *, void *)) { u64 resume_token = 0; int entries, i, rc; @@ -327,21 +328,13 @@ static int clp_list_pci(struct clp_req_rsp_list_pci *rrb, resume_token = rrb->response.resume_token; for (i = 0; i < entries; i++) - cb(&rrb->response.fh_list[i]); + cb(&rrb->response.fh_list[i], data); } while (resume_token); out: return rc; } -static void __clp_add(struct clp_fh_list_entry *entry) -{ - if (!entry->vendor_id) - return; - - clp_add_pci_device(entry->fid, entry->fh, entry->config_state); -} - -static void __clp_rescan(struct clp_fh_list_entry *entry) +static void __clp_add(struct clp_fh_list_entry *entry, void *data) { struct zpci_dev *zdev; @@ -349,22 +342,11 @@ static void __clp_rescan(struct clp_fh_list_entry *entry) return; zdev = get_zdev_by_fid(entry->fid); - if (!zdev) { + if (!zdev) clp_add_pci_device(entry->fid, entry->fh, entry->config_state); - return; - } - - if (!entry->config_state) { - /* - * The handle is already disabled, that means no iota/irq freeing via - * the firmware interfaces anymore. Need to free resources manually - * (DMA memory, debug, sysfs)... - */ - zpci_stop_device(zdev); - } } -static void __clp_update(struct clp_fh_list_entry *entry) +static void __clp_update(struct clp_fh_list_entry *entry, void *data) { struct zpci_dev *zdev; @@ -387,7 +369,7 @@ int clp_scan_pci_devices(void) if (!rrb) return -ENOMEM; - rc = clp_list_pci(rrb, __clp_add); + rc = clp_list_pci(rrb, NULL, __clp_add); clp_free_block(rrb); return rc; @@ -398,11 +380,13 @@ int clp_rescan_pci_devices(void) struct clp_req_rsp_list_pci *rrb; int rc; + zpci_remove_reserved_devices(); + rrb = clp_alloc_block(GFP_KERNEL); if (!rrb) return -ENOMEM; - rc = clp_list_pci(rrb, __clp_rescan); + rc = clp_list_pci(rrb, NULL, __clp_add); clp_free_block(rrb); return rc; @@ -417,7 +401,40 @@ int clp_rescan_pci_devices_simple(void) if (!rrb) return -ENOMEM; - rc = clp_list_pci(rrb, __clp_update); + rc = clp_list_pci(rrb, NULL, __clp_update); + + clp_free_block(rrb); + return rc; +} + +struct clp_state_data { + u32 fid; + enum zpci_state state; +}; + +static void __clp_get_state(struct clp_fh_list_entry *entry, void *data) +{ + struct clp_state_data *sd = data; + + if (entry->fid != sd->fid) + return; + + sd->state = entry->config_state; +} + +int clp_get_state(u32 fid, enum zpci_state *state) +{ + struct clp_req_rsp_list_pci *rrb; + struct clp_state_data sd = {fid, ZPCI_FN_STATE_RESERVED}; + int rc; + + rrb = clp_alloc_block(GFP_KERNEL); + if (!rrb) + return -ENOMEM; + + rc = clp_list_pci(rrb, &sd, __clp_get_state); + if (!rc) + *state = sd.state; clp_free_block(rrb); return rc; diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c index 9081a57fa340..8eb1cc341dab 100644 --- a/arch/s390/pci/pci_dma.c +++ b/arch/s390/pci/pci_dma.c @@ -601,7 +601,9 @@ void zpci_dma_exit_device(struct zpci_dev *zdev) */ WARN_ON(zdev->s390_domain); - zpci_unregister_ioat(zdev, 0); + if (zpci_unregister_ioat(zdev, 0)) + return; + dma_cleanup_tables(zdev->dma_table); zdev->dma_table = NULL; vfree(zdev->iommu_bitmap); diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index c2b27ad8e94d..0bbc04af4418 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -74,6 +74,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) { struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid); struct pci_dev *pdev = NULL; + enum zpci_state state; int ret; if (zdev) @@ -108,6 +109,8 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) clp_add_pci_device(ccdf->fid, ccdf->fh, 0); break; case 0x0303: /* Deconfiguration requested */ + if (!zdev) + break; if (pdev) pci_stop_and_remove_bus_device_locked(pdev); @@ -121,7 +124,9 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) zdev->state = ZPCI_FN_STATE_STANDBY; break; - case 0x0304: /* Configured -> Standby */ + case 0x0304: /* Configured -> Standby|Reserved */ + if (!zdev) + break; if (pdev) { /* Give the driver a hint that the function is * already unusable. */ @@ -132,6 +137,10 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) zdev->fh = ccdf->fh; zpci_disable_device(zdev); zdev->state = ZPCI_FN_STATE_STANDBY; + if (!clp_get_state(ccdf->fid, &state) && + state == ZPCI_FN_STATE_RESERVED) { + zpci_remove_device(zdev); + } break; case 0x0306: /* 0x308 or 0x302 for multiple devices */ clp_rescan_pci_devices(); @@ -139,8 +148,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) case 0x0308: /* Standby -> Reserved */ if (!zdev) break; - pci_stop_root_bus(zdev->bus); - pci_remove_root_bus(zdev->bus); + zpci_remove_device(zdev); break; default: break; diff --git a/arch/s390/pci/pci_insn.c b/arch/s390/pci/pci_insn.c index fa8d7d4b9751..ea34086c8674 100644 --- a/arch/s390/pci/pci_insn.c +++ b/arch/s390/pci/pci_insn.c @@ -40,20 +40,20 @@ static inline u8 __mpcifc(u64 req, struct zpci_fib *fib, u8 *status) return cc; } -int zpci_mod_fc(u64 req, struct zpci_fib *fib) +u8 zpci_mod_fc(u64 req, struct zpci_fib *fib, u8 *status) { - u8 cc, status; + u8 cc; do { - cc = __mpcifc(req, fib, &status); + cc = __mpcifc(req, fib, status); if (cc == 2) msleep(ZPCI_INSN_BUSY_DELAY); } while (cc == 2); if (cc) - zpci_err_insn(cc, status, req, 0); + zpci_err_insn(cc, *status, req, 0); - return (cc) ? -EIO : 0; + return cc; } /* Refresh PCI Translations */ diff --git a/arch/s390/tools/gen_facilities.c b/arch/s390/tools/gen_facilities.c index be63fbd699fd..025ea20fc4b4 100644 --- a/arch/s390/tools/gen_facilities.c +++ b/arch/s390/tools/gen_facilities.c @@ -34,8 +34,6 @@ static struct facility_def facility_defs[] = { 18, /* long displacement facility */ #endif #ifdef CONFIG_HAVE_MARCH_Z9_109_FEATURES - 7, /* stfle */ - 17, /* message security assist */ 21, /* extended-immediate facility */ 25, /* store clock fast */ #endif diff --git a/arch/score/include/asm/processor.h b/arch/score/include/asm/processor.h index d9a922d8711b..299274581968 100644 --- a/arch/score/include/asm/processor.h +++ b/arch/score/include/asm/processor.h @@ -13,7 +13,6 @@ struct task_struct; */ extern void (*cpu_wait)(void); -extern unsigned long thread_saved_pc(struct task_struct *tsk); extern void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp); extern unsigned long get_wchan(struct task_struct *p); diff --git a/arch/score/kernel/process.c b/arch/score/kernel/process.c index eb64d7a677cb..6e20241a1ed4 100644 --- a/arch/score/kernel/process.c +++ b/arch/score/kernel/process.c @@ -101,11 +101,6 @@ int dump_fpu(struct pt_regs *regs, elf_fpregset_t *r) return 1; } -unsigned long thread_saved_pc(struct task_struct *tsk) -{ - return task_pt_regs(tsk)->cp0_epc; -} - unsigned long get_wchan(struct task_struct *task) { if (!task || task == current || task->state == TASK_RUNNING) diff --git a/arch/sparc/include/asm/processor_32.h b/arch/sparc/include/asm/processor_32.h index dd27159819eb..b395e5620c0b 100644 --- a/arch/sparc/include/asm/processor_32.h +++ b/arch/sparc/include/asm/processor_32.h @@ -67,9 +67,6 @@ struct thread_struct { .current_ds = KERNEL_DS, \ } -/* Return saved PC of a blocked thread. */ -unsigned long thread_saved_pc(struct task_struct *t); - /* Do necessary setup to start up a newly executed thread. */ static inline void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long sp) diff --git a/arch/sparc/include/asm/processor_64.h b/arch/sparc/include/asm/processor_64.h index b58ee9018433..f04dc5a43062 100644 --- a/arch/sparc/include/asm/processor_64.h +++ b/arch/sparc/include/asm/processor_64.h @@ -89,9 +89,7 @@ struct thread_struct { #include <linux/types.h> #include <asm/fpumacro.h> -/* Return saved PC of a blocked thread. */ struct task_struct; -unsigned long thread_saved_pc(struct task_struct *); /* On Uniprocessor, even in RMO processes see TSO semantics */ #ifdef CONFIG_SMP diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c index b6dac8e980f0..9245f93398c7 100644 --- a/arch/sparc/kernel/process_32.c +++ b/arch/sparc/kernel/process_32.c @@ -177,14 +177,6 @@ void show_stack(struct task_struct *tsk, unsigned long *_ksp) } /* - * Note: sparc64 has a pretty intricated thread_saved_pc, check it out. - */ -unsigned long thread_saved_pc(struct task_struct *tsk) -{ - return task_thread_info(tsk)->kpc; -} - -/* * Free current thread data structures etc.. */ void exit_thread(struct task_struct *tsk) diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index 1badc493e62e..b96104da5bd6 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -400,25 +400,6 @@ core_initcall(sparc_sysrq_init); #endif -unsigned long thread_saved_pc(struct task_struct *tsk) -{ - struct thread_info *ti = task_thread_info(tsk); - unsigned long ret = 0xdeadbeefUL; - - if (ti && ti->ksp) { - unsigned long *sp; - sp = (unsigned long *)(ti->ksp + STACK_BIAS); - if (((unsigned long)sp & (sizeof(long) - 1)) == 0UL && - sp[14]) { - unsigned long *fp; - fp = (unsigned long *)(sp[14] + STACK_BIAS); - if (((unsigned long)fp & (sizeof(long) - 1)) == 0UL) - ret = fp[15]; - } - } - return ret; -} - /* Free current thread data structures etc.. */ void exit_thread(struct task_struct *tsk) { diff --git a/arch/tile/include/asm/processor.h b/arch/tile/include/asm/processor.h index 0bc9968b97a1..f71e5206650b 100644 --- a/arch/tile/include/asm/processor.h +++ b/arch/tile/include/asm/processor.h @@ -214,13 +214,6 @@ static inline void release_thread(struct task_struct *dead_task) extern void prepare_exit_to_usermode(struct pt_regs *regs, u32 flags); - -/* - * Return saved (kernel) PC of a blocked thread. - * Only used in a printk() in kernel/sched/core.c, so don't work too hard. - */ -#define thread_saved_pc(t) ((t)->thread.pc) - unsigned long get_wchan(struct task_struct *p); /* Return initial ksp value for given task. */ diff --git a/arch/tile/lib/atomic_asm_32.S b/arch/tile/lib/atomic_asm_32.S index 1a70e6c0f259..94709ab41ed8 100644 --- a/arch/tile/lib/atomic_asm_32.S +++ b/arch/tile/lib/atomic_asm_32.S @@ -24,8 +24,7 @@ * has an opportunity to return -EFAULT to the user if needed. * The 64-bit routines just return a "long long" with the value, * since they are only used from kernel space and don't expect to fault. - * Support for 16-bit ops is included in the framework but we don't provide - * any (x86_64 has an atomic_inc_short(), so we might want to some day). + * Support for 16-bit ops is included in the framework but we don't provide any. * * Note that the caller is advised to issue a suitable L1 or L2 * prefetch on the address being manipulated to avoid extra stalls. diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 85410279beab..b55fe9bf5d3e 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -534,7 +534,7 @@ static void ubd_handler(void) for (count = 0; count < n/sizeof(struct io_thread_req *); count++) { blk_end_request( (*irq_req_buffer)[count]->req, - 0, + BLK_STS_OK, (*irq_req_buffer)[count]->length ); kfree((*irq_req_buffer)[count]); diff --git a/arch/um/include/asm/processor-generic.h b/arch/um/include/asm/processor-generic.h index 2d1e0dd5bb0b..f6d1a3f747a9 100644 --- a/arch/um/include/asm/processor-generic.h +++ b/arch/um/include/asm/processor-generic.h @@ -58,8 +58,6 @@ static inline void release_thread(struct task_struct *task) { } -extern unsigned long thread_saved_pc(struct task_struct *t); - static inline void mm_copy_segments(struct mm_struct *from_mm, struct mm_struct *new_mm) { diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 64a1fd06f3fd..7b5640117325 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -56,12 +56,6 @@ union thread_union cpu0_irqstack __attribute__((__section__(".data..init_irqstack"))) = { INIT_THREAD_INFO(init_task) }; -unsigned long thread_saved_pc(struct task_struct *task) -{ - /* FIXME: Need to look up userspace_pid by cpu */ - return os_process_pc(userspace_pid[0]); -} - /* Changed in setup_arch, which is called in early boot */ static char host_info[(__NEW_UTS_LEN + 1) * 5]; diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 0efb4c9497bc..737212c0333e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -69,7 +69,7 @@ config X86 select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_QUEUED_RWLOCKS select ARCH_USE_QUEUED_SPINLOCKS - select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH if SMP + select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH select ARCH_WANT_FRAME_POINTERS select ARCH_WANTS_DYNAMIC_TASK_STRUCT select BUILDTIME_EXTABLE_SORT @@ -2793,6 +2793,9 @@ config X86_DMA_REMAP bool depends on STA2X11 +config HAVE_GENERIC_GUP + def_bool y + source "net/Kconfig" source "drivers/Kconfig" diff --git a/arch/x86/boot/compressed/cmdline.c b/arch/x86/boot/compressed/cmdline.c index 73ccf63b0f48..9dc1ce6ba3c0 100644 --- a/arch/x86/boot/compressed/cmdline.c +++ b/arch/x86/boot/compressed/cmdline.c @@ -13,7 +13,7 @@ static inline char rdfs8(addr_t addr) return *((char *)(fs + addr)); } #include "../cmdline.c" -static unsigned long get_cmd_line_ptr(void) +unsigned long get_cmd_line_ptr(void) { unsigned long cmd_line_ptr = boot_params->hdr.cmd_line_ptr; diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index cbf4b87f55b9..c3e869eaef0c 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -1046,9 +1046,31 @@ struct boot_params *efi_main(struct efi_config *c, memset((char *)gdt->address, 0x0, gdt->size); desc = (struct desc_struct *)gdt->address; - /* The first GDT is a dummy and the second is unused. */ - desc += 2; + /* The first GDT is a dummy. */ + desc++; + + if (IS_ENABLED(CONFIG_X86_64)) { + /* __KERNEL32_CS */ + desc->limit0 = 0xffff; + desc->base0 = 0x0000; + desc->base1 = 0x0000; + desc->type = SEG_TYPE_CODE | SEG_TYPE_EXEC_READ; + desc->s = DESC_TYPE_CODE_DATA; + desc->dpl = 0; + desc->p = 1; + desc->limit = 0xf; + desc->avl = 0; + desc->l = 0; + desc->d = SEG_OP_SIZE_32BIT; + desc->g = SEG_GRANULARITY_4KB; + desc->base2 = 0x00; + desc++; + } else { + /* Second entry is unused on 32-bit */ + desc++; + } + /* __KERNEL_CS */ desc->limit0 = 0xffff; desc->base0 = 0x0000; desc->base1 = 0x0000; @@ -1058,12 +1080,18 @@ struct boot_params *efi_main(struct efi_config *c, desc->p = 1; desc->limit = 0xf; desc->avl = 0; - desc->l = 0; - desc->d = SEG_OP_SIZE_32BIT; + if (IS_ENABLED(CONFIG_X86_64)) { + desc->l = 1; + desc->d = 0; + } else { + desc->l = 0; + desc->d = SEG_OP_SIZE_32BIT; + } desc->g = SEG_GRANULARITY_4KB; desc->base2 = 0x00; - desc++; + + /* __KERNEL_DS */ desc->limit0 = 0xffff; desc->base0 = 0x0000; desc->base1 = 0x0000; @@ -1077,24 +1105,25 @@ struct boot_params *efi_main(struct efi_config *c, desc->d = SEG_OP_SIZE_32BIT; desc->g = SEG_GRANULARITY_4KB; desc->base2 = 0x00; - -#ifdef CONFIG_X86_64 - /* Task segment value */ desc++; - desc->limit0 = 0x0000; - desc->base0 = 0x0000; - desc->base1 = 0x0000; - desc->type = SEG_TYPE_TSS; - desc->s = 0; - desc->dpl = 0; - desc->p = 1; - desc->limit = 0x0; - desc->avl = 0; - desc->l = 0; - desc->d = 0; - desc->g = SEG_GRANULARITY_4KB; - desc->base2 = 0x00; -#endif /* CONFIG_X86_64 */ + + if (IS_ENABLED(CONFIG_X86_64)) { + /* Task segment value */ + desc->limit0 = 0x0000; + desc->base0 = 0x0000; + desc->base1 = 0x0000; + desc->type = SEG_TYPE_TSS; + desc->s = 0; + desc->dpl = 0; + desc->p = 1; + desc->limit = 0x0; + desc->avl = 0; + desc->l = 0; + desc->d = 0; + desc->g = SEG_GRANULARITY_4KB; + desc->base2 = 0x00; + desc++; + } asm volatile("cli"); asm volatile ("lgdt %0" : : "m" (*gdt)); diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index d2ae1f821e0c..fbf4c32d0b62 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -346,6 +346,48 @@ preferred_addr: /* Set up the stack */ leaq boot_stack_end(%rbx), %rsp +#ifdef CONFIG_X86_5LEVEL + /* Check if 5-level paging has already enabled */ + movq %cr4, %rax + testl $X86_CR4_LA57, %eax + jnz lvl5 + + /* + * At this point we are in long mode with 4-level paging enabled, + * but we want to enable 5-level paging. + * + * The problem is that we cannot do it directly. Setting LA57 in + * long mode would trigger #GP. So we need to switch off long mode + * first. + * + * NOTE: This is not going to work if bootloader put us above 4G + * limit. + * + * The first step is go into compatibility mode. + */ + + /* Clear additional page table */ + leaq lvl5_pgtable(%rbx), %rdi + xorq %rax, %rax + movq $(PAGE_SIZE/8), %rcx + rep stosq + + /* + * Setup current CR3 as the first and only entry in a new top level + * page table. + */ + movq %cr3, %rdi + leaq 0x7 (%rdi), %rax + movq %rax, lvl5_pgtable(%rbx) + + /* Switch to compatibility mode (CS.L = 0 CS.D = 1) via far return */ + pushq $__KERNEL32_CS + leaq compatible_mode(%rip), %rax + pushq %rax + lretq +lvl5: +#endif + /* Zero EFLAGS */ pushq $0 popfq @@ -429,6 +471,44 @@ relocated: jmp *%rax .code32 +#ifdef CONFIG_X86_5LEVEL +compatible_mode: + /* Setup data and stack segments */ + movl $__KERNEL_DS, %eax + movl %eax, %ds + movl %eax, %ss + + /* Disable paging */ + movl %cr0, %eax + btrl $X86_CR0_PG_BIT, %eax + movl %eax, %cr0 + + /* Point CR3 to 5-level paging */ + leal lvl5_pgtable(%ebx), %eax + movl %eax, %cr3 + + /* Enable PAE and LA57 mode */ + movl %cr4, %eax + orl $(X86_CR4_PAE | X86_CR4_LA57), %eax + movl %eax, %cr4 + + /* Calculate address we are running at */ + call 1f +1: popl %edi + subl $1b, %edi + + /* Prepare stack for far return to Long Mode */ + pushl $__KERNEL_CS + leal lvl5(%edi), %eax + push %eax + + /* Enable paging back */ + movl $(X86_CR0_PG | X86_CR0_PE), %eax + movl %eax, %cr0 + + lret +#endif + no_longmode: /* This isn't an x86-64 CPU so hang */ 1: @@ -442,7 +522,7 @@ gdt: .word gdt_end - gdt .long gdt .word 0 - .quad 0x0000000000000000 /* NULL descriptor */ + .quad 0x00cf9a000000ffff /* __KERNEL32_CS */ .quad 0x00af9a000000ffff /* __KERNEL_CS */ .quad 0x00cf92000000ffff /* __KERNEL_DS */ .quad 0x0080890000000000 /* TS descriptor */ @@ -486,3 +566,7 @@ boot_stack_end: .balign 4096 pgtable: .fill BOOT_PGT_SIZE, 1, 0 +#ifdef CONFIG_X86_5LEVEL +lvl5_pgtable: + .fill PAGE_SIZE, 1, 0 +#endif diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index 54c24f0a43d3..91f27ab970ef 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -9,16 +9,42 @@ * contain the entire properly aligned running kernel image. * */ + +/* + * isspace() in linux/ctype.h is expected by next_args() to filter + * out "space/lf/tab". While boot/ctype.h conflicts with linux/ctype.h, + * since isdigit() is implemented in both of them. Hence disable it + * here. + */ +#define BOOT_CTYPE_H + +/* + * _ctype[] in lib/ctype.c is needed by isspace() of linux/ctype.h. + * While both lib/ctype.c and lib/cmdline.c will bring EXPORT_SYMBOL + * which is meaningless and will cause compiling error in some cases. + * So do not include linux/export.h and define EXPORT_SYMBOL(sym) + * as empty. + */ +#define _LINUX_EXPORT_H +#define EXPORT_SYMBOL(sym) + #include "misc.h" #include "error.h" -#include "../boot.h" +#include "../string.h" #include <generated/compile.h> #include <linux/module.h> #include <linux/uts.h> #include <linux/utsname.h> +#include <linux/ctype.h> #include <generated/utsrelease.h> +/* Macros used by the included decompressor code below. */ +#define STATIC +#include <linux/decompress/mm.h> + +extern unsigned long get_cmd_line_ptr(void); + /* Simplified build-specific string for starting entropy. */ static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@" LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION; @@ -62,6 +88,11 @@ struct mem_vector { static bool memmap_too_large; + +/* Store memory limit specified by "mem=nn[KMG]" or "memmap=nn[KMG]" */ +unsigned long long mem_limit = ULLONG_MAX; + + enum mem_avoid_index { MEM_AVOID_ZO_RANGE = 0, MEM_AVOID_INITRD, @@ -85,49 +116,14 @@ static bool mem_overlaps(struct mem_vector *one, struct mem_vector *two) return true; } -/** - * _memparse - Parse a string with mem suffixes into a number - * @ptr: Where parse begins - * @retptr: (output) Optional pointer to next char after parse completes - * - * Parses a string into a number. The number stored at @ptr is - * potentially suffixed with K, M, G, T, P, E. - */ -static unsigned long long _memparse(const char *ptr, char **retptr) +char *skip_spaces(const char *str) { - char *endptr; /* Local pointer to end of parsed string */ - - unsigned long long ret = simple_strtoull(ptr, &endptr, 0); - - switch (*endptr) { - case 'E': - case 'e': - ret <<= 10; - case 'P': - case 'p': - ret <<= 10; - case 'T': - case 't': - ret <<= 10; - case 'G': - case 'g': - ret <<= 10; - case 'M': - case 'm': - ret <<= 10; - case 'K': - case 'k': - ret <<= 10; - endptr++; - default: - break; - } - - if (retptr) - *retptr = endptr; - - return ret; + while (isspace(*str)) + ++str; + return (char *)str; } +#include "../../../../lib/ctype.c" +#include "../../../../lib/cmdline.c" static int parse_memmap(char *p, unsigned long long *start, unsigned long long *size) @@ -142,40 +138,41 @@ parse_memmap(char *p, unsigned long long *start, unsigned long long *size) return -EINVAL; oldp = p; - *size = _memparse(p, &p); + *size = memparse(p, &p); if (p == oldp) return -EINVAL; switch (*p) { - case '@': - /* Skip this region, usable */ - *start = 0; - *size = 0; - return 0; case '#': case '$': case '!': - *start = _memparse(p + 1, &p); + *start = memparse(p + 1, &p); + return 0; + case '@': + /* memmap=nn@ss specifies usable region, should be skipped */ + *size = 0; + /* Fall through */ + default: + /* + * If w/o offset, only size specified, memmap=nn[KMG] has the + * same behaviour as mem=nn[KMG]. It limits the max address + * system can use. Region above the limit should be avoided. + */ + *start = 0; return 0; } return -EINVAL; } -static void mem_avoid_memmap(void) +static void mem_avoid_memmap(char *str) { - char arg[128]; + static int i; int rc; - int i; - char *str; - /* See if we have any memmap areas */ - rc = cmdline_find_option("memmap", arg, sizeof(arg)); - if (rc <= 0) + if (i >= MAX_MEMMAP_REGIONS) return; - i = 0; - str = arg; while (str && (i < MAX_MEMMAP_REGIONS)) { int rc; unsigned long long start, size; @@ -188,9 +185,14 @@ static void mem_avoid_memmap(void) if (rc < 0) break; str = k; - /* A usable region that should not be skipped */ - if (size == 0) + + if (start == 0) { + /* Store the specified memory limit if size > 0 */ + if (size > 0) + mem_limit = size; + continue; + } mem_avoid[MEM_AVOID_MEMMAP_BEGIN + i].start = start; mem_avoid[MEM_AVOID_MEMMAP_BEGIN + i].size = size; @@ -202,6 +204,57 @@ static void mem_avoid_memmap(void) memmap_too_large = true; } +static int handle_mem_memmap(void) +{ + char *args = (char *)get_cmd_line_ptr(); + size_t len = strlen((char *)args); + char *tmp_cmdline; + char *param, *val; + u64 mem_size; + + if (!strstr(args, "memmap=") && !strstr(args, "mem=")) + return 0; + + tmp_cmdline = malloc(len + 1); + if (!tmp_cmdline ) + error("Failed to allocate space for tmp_cmdline"); + + memcpy(tmp_cmdline, args, len); + tmp_cmdline[len] = 0; + args = tmp_cmdline; + + /* Chew leading spaces */ + args = skip_spaces(args); + + while (*args) { + args = next_arg(args, ¶m, &val); + /* Stop at -- */ + if (!val && strcmp(param, "--") == 0) { + warn("Only '--' specified in cmdline"); + free(tmp_cmdline); + return -1; + } + + if (!strcmp(param, "memmap")) { + mem_avoid_memmap(val); + } else if (!strcmp(param, "mem")) { + char *p = val; + + if (!strcmp(p, "nopentium")) + continue; + mem_size = memparse(p, &p); + if (mem_size == 0) { + free(tmp_cmdline); + return -EINVAL; + } + mem_limit = mem_size; + } + } + + free(tmp_cmdline); + return 0; +} + /* * In theory, KASLR can put the kernel anywhere in the range of [16M, 64T). * The mem_avoid array is used to store the ranges that need to be avoided @@ -323,7 +376,7 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, /* We don't need to set a mapping for setup_data. */ /* Mark the memmap regions we need to avoid */ - mem_avoid_memmap(); + handle_mem_memmap(); #ifdef CONFIG_X86_VERBOSE_BOOTUP /* Make sure video RAM can be used. */ @@ -432,7 +485,8 @@ static void process_e820_entry(struct boot_e820_entry *entry, { struct mem_vector region, overlap; struct slot_area slot_area; - unsigned long start_orig; + unsigned long start_orig, end; + struct boot_e820_entry cur_entry; /* Skip non-RAM entries. */ if (entry->type != E820_TYPE_RAM) @@ -446,8 +500,15 @@ static void process_e820_entry(struct boot_e820_entry *entry, if (entry->addr + entry->size < minimum) return; - region.start = entry->addr; - region.size = entry->size; + /* Ignore entries above memory limit */ + end = min(entry->size + entry->addr, mem_limit); + if (entry->addr >= end) + return; + cur_entry.addr = entry->addr; + cur_entry.size = end - entry->addr; + + region.start = cur_entry.addr; + region.size = cur_entry.size; /* Give up if slot area array is full. */ while (slot_area_index < MAX_SLOT_AREA) { @@ -461,7 +522,7 @@ static void process_e820_entry(struct boot_e820_entry *entry, region.start = ALIGN(region.start, CONFIG_PHYSICAL_ALIGN); /* Did we raise the address above this e820 region? */ - if (region.start > entry->addr + entry->size) + if (region.start > cur_entry.addr + cur_entry.size) return; /* Reduce size by any delta from the original address. */ @@ -564,9 +625,6 @@ void choose_random_location(unsigned long input, { unsigned long random_addr, min_addr; - /* By default, keep output position unchanged. */ - *virt_addr = *output; - if (cmdline_find_option_bool("nokaslr")) { warn("KASLR disabled: 'nokaslr' on cmdline."); return; diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index b3c5a5f030ce..00241c815524 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -338,7 +338,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, unsigned long output_len) { const unsigned long kernel_total_size = VO__end - VO__text; - unsigned long virt_addr = (unsigned long)output; + unsigned long virt_addr = LOAD_PHYSICAL_ADDR; /* Retain x86 boot parameters pointer passed from startup_32/64. */ boot_params = rmode; @@ -390,6 +390,8 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, #ifdef CONFIG_X86_64 if (heap > 0x3fffffffffffUL) error("Destination address too large"); + if (virt_addr + max(output_len, kernel_total_size) > KERNEL_IMAGE_SIZE) + error("Destination virtual address is beyond the kernel mapping area"); #else if (heap > ((-__PAGE_OFFSET-(128<<20)-1) & 0x7fffffff)) error("Destination address too large"); @@ -397,7 +399,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, #ifndef CONFIG_RELOCATABLE if ((unsigned long)output != LOAD_PHYSICAL_ADDR) error("Destination address does not match LOAD_PHYSICAL_ADDR"); - if ((unsigned long)output != virt_addr) + if (virt_addr != LOAD_PHYSICAL_ADDR) error("Destination virtual address changed when not relocatable"); #endif diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 1c8355eadbd1..766a5211f827 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -81,8 +81,6 @@ static inline void choose_random_location(unsigned long input, unsigned long output_size, unsigned long *virt_addr) { - /* No change from existing output location. */ - *virt_addr = *output; } #endif diff --git a/arch/x86/boot/compressed/pagetable.c b/arch/x86/boot/compressed/pagetable.c index 1d78f1739087..28029be47fbb 100644 --- a/arch/x86/boot/compressed/pagetable.c +++ b/arch/x86/boot/compressed/pagetable.c @@ -63,7 +63,7 @@ static void *alloc_pgt_page(void *context) static struct alloc_pgt_data pgt_data; /* The top level page table entry pointer. */ -static unsigned long level4p; +static unsigned long top_level_pgt; /* * Mapping information structure passed to kernel_ident_mapping_init(). @@ -91,9 +91,15 @@ void initialize_identity_maps(void) * If we came here via startup_32(), cr3 will be _pgtable already * and we must append to the existing area instead of entirely * overwriting it. + * + * With 5-level paging, we use '_pgtable' to allocate the p4d page table, + * the top-level page table is allocated separately. + * + * p4d_offset(top_level_pgt, 0) would cover both the 4- and 5-level + * cases. On 4-level paging it's equal to 'top_level_pgt'. */ - level4p = read_cr3(); - if (level4p == (unsigned long)_pgtable) { + top_level_pgt = read_cr3_pa(); + if (p4d_offset((pgd_t *)top_level_pgt, 0) == (p4d_t *)_pgtable) { debug_putstr("booted via startup_32()\n"); pgt_data.pgt_buf = _pgtable + BOOT_INIT_PGT_SIZE; pgt_data.pgt_buf_size = BOOT_PGT_SIZE - BOOT_INIT_PGT_SIZE; @@ -103,7 +109,7 @@ void initialize_identity_maps(void) pgt_data.pgt_buf = _pgtable; pgt_data.pgt_buf_size = BOOT_PGT_SIZE; memset(pgt_data.pgt_buf, 0, pgt_data.pgt_buf_size); - level4p = (unsigned long)alloc_pgt_page(&pgt_data); + top_level_pgt = (unsigned long)alloc_pgt_page(&pgt_data); } } @@ -123,7 +129,7 @@ void add_identity_map(unsigned long start, unsigned long size) return; /* Build the mapping. */ - kernel_ident_mapping_init(&mapping_info, (pgd_t *)level4p, + kernel_ident_mapping_init(&mapping_info, (pgd_t *)top_level_pgt, start, end); } @@ -134,5 +140,5 @@ void add_identity_map(unsigned long start, unsigned long size) */ void finalize_identity_maps(void) { - write_cr3(level4p); + write_cr3(top_level_pgt); } diff --git a/arch/x86/boot/copy.S b/arch/x86/boot/copy.S index 1eb7d298b47d..15d9f74b0008 100644 --- a/arch/x86/boot/copy.S +++ b/arch/x86/boot/copy.S @@ -65,23 +65,3 @@ GLOBAL(copy_to_fs) popw %es retl ENDPROC(copy_to_fs) - -#if 0 /* Not currently used, but can be enabled as needed */ -GLOBAL(copy_from_gs) - pushw %ds - pushw %gs - popw %ds - calll memcpy - popw %ds - retl -ENDPROC(copy_from_gs) - -GLOBAL(copy_to_gs) - pushw %es - pushw %gs - popw %es - calll memcpy - popw %es - retl -ENDPROC(copy_to_gs) -#endif diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c index 5457b02fc050..630e3664906b 100644 --- a/arch/x86/boot/string.c +++ b/arch/x86/boot/string.c @@ -122,6 +122,14 @@ unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int bas return result; } +long simple_strtol(const char *cp, char **endp, unsigned int base) +{ + if (*cp == '-') + return -simple_strtoull(cp + 1, endp, base); + + return simple_strtoull(cp, endp, base); +} + /** * strlen - Find the length of a string * @s: The string to be sized diff --git a/arch/x86/boot/string.h b/arch/x86/boot/string.h index 113588ddb43f..f274a50db5fa 100644 --- a/arch/x86/boot/string.h +++ b/arch/x86/boot/string.h @@ -22,6 +22,7 @@ extern int strcmp(const char *str1, const char *str2); extern int strncmp(const char *cs, const char *ct, size_t count); extern size_t strlen(const char *s); extern char *strstr(const char *s1, const char *s2); +extern char *strchr(const char *s, int c); extern size_t strnlen(const char *s, size_t maxlen); extern unsigned int atou(const char *s); extern unsigned long long simple_strtoull(const char *cp, char **endp, diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile index 34b3fa2889d1..9e32d40d71bd 100644 --- a/arch/x86/crypto/Makefile +++ b/arch/x86/crypto/Makefile @@ -2,6 +2,8 @@ # Arch-specific CryptoAPI modules. # +OBJECT_FILES_NON_STANDARD := y + avx_supported := $(call as-instr,vpxor %xmm0$(comma)%xmm0$(comma)%xmm0,yes,no) avx2_supported := $(call as-instr,vpgatherdd %ymm0$(comma)(%eax$(comma)%ymm1\ $(comma)4)$(comma)%ymm2,yes,no) diff --git a/arch/x86/crypto/sha1-mb/Makefile b/arch/x86/crypto/sha1-mb/Makefile index 2f8756375df5..2e14acc3da25 100644 --- a/arch/x86/crypto/sha1-mb/Makefile +++ b/arch/x86/crypto/sha1-mb/Makefile @@ -2,6 +2,8 @@ # Arch-specific CryptoAPI modules. # +OBJECT_FILES_NON_STANDARD := y + avx2_supported := $(call as-instr,vpgatherdd %ymm0$(comma)(%eax$(comma)%ymm1\ $(comma)4)$(comma)%ymm2,yes,no) ifeq ($(avx2_supported),yes) diff --git a/arch/x86/crypto/sha256-mb/Makefile b/arch/x86/crypto/sha256-mb/Makefile index 41089e7c400c..45b4fca6c4a8 100644 --- a/arch/x86/crypto/sha256-mb/Makefile +++ b/arch/x86/crypto/sha256-mb/Makefile @@ -2,6 +2,8 @@ # Arch-specific CryptoAPI modules. # +OBJECT_FILES_NON_STANDARD := y + avx2_supported := $(call as-instr,vpgatherdd %ymm0$(comma)(%eax$(comma)%ymm1\ $(comma)4)$(comma)%ymm2,yes,no) ifeq ($(avx2_supported),yes) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 4a4c0834f965..a9a8027a6c0e 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -265,7 +265,8 @@ return_from_SYSCALL_64: * If width of "canonical tail" ever becomes variable, this will need * to be updated to remain correct on both old and new CPUs. * - * Change top 16 bits to be the sign-extension of 47th bit + * Change top bits to match most significant bit (47th or 56th bit + * depending on paging mode) in the address. */ shl $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx sar $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 580b60f5ac83..2de0dd73830a 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1750,6 +1750,8 @@ ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event) return ret; } +static struct attribute_group x86_pmu_attr_group; + static int __init init_hw_perf_events(void) { struct x86_pmu_quirk *quirk; @@ -1813,6 +1815,14 @@ static int __init init_hw_perf_events(void) x86_pmu_events_group.attrs = tmp; } + if (x86_pmu.attrs) { + struct attribute **tmp; + + tmp = merge_attr(x86_pmu_attr_group.attrs, x86_pmu.attrs); + if (!WARN_ON(!tmp)) + x86_pmu_attr_group.attrs = tmp; + } + pr_info("... version: %d\n", x86_pmu.version); pr_info("... bit width: %d\n", x86_pmu.cntval_bits); pr_info("... generic registers: %d\n", x86_pmu.num_counters); @@ -2101,8 +2111,7 @@ static int x86_pmu_event_init(struct perf_event *event) static void refresh_pce(void *ignored) { - if (current->active_mm) - load_mm_cr4(current->active_mm); + load_mm_cr4(this_cpu_read(cpu_tlbstate.loaded_mm)); } static void x86_pmu_event_mapped(struct perf_event *event) @@ -2255,7 +2264,7 @@ static struct pmu pmu = { void arch_perf_update_userpage(struct perf_event *event, struct perf_event_mmap_page *userpg, u64 now) { - struct cyc2ns_data *data; + struct cyc2ns_data data; u64 offset; userpg->cap_user_time = 0; @@ -2267,17 +2276,17 @@ void arch_perf_update_userpage(struct perf_event *event, if (!using_native_sched_clock() || !sched_clock_stable()) return; - data = cyc2ns_read_begin(); + cyc2ns_read_begin(&data); - offset = data->cyc2ns_offset + __sched_clock_offset; + offset = data.cyc2ns_offset + __sched_clock_offset; /* * Internal timekeeping for enabled/running/stopped times * is always in the local_clock domain. */ userpg->cap_user_time = 1; - userpg->time_mult = data->cyc2ns_mul; - userpg->time_shift = data->cyc2ns_shift; + userpg->time_mult = data.cyc2ns_mul; + userpg->time_shift = data.cyc2ns_shift; userpg->time_offset = offset - now; /* @@ -2289,7 +2298,7 @@ void arch_perf_update_userpage(struct perf_event *event, userpg->time_zero = offset; } - cyc2ns_read_end(data); + cyc2ns_read_end(); } void @@ -2334,7 +2343,7 @@ static unsigned long get_segment_base(unsigned int segment) /* IRQs are off, so this synchronizes with smp_store_release */ ldt = lockless_dereference(current->active_mm->context.ldt); - if (!ldt || idx > ldt->size) + if (!ldt || idx > ldt->nr_entries) return 0; desc = &ldt->entries[idx]; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index a6d91d4e37a1..31acf2a98394 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -431,11 +431,11 @@ static __initconst const u64 skl_hw_cache_event_ids [ C(DTLB) ] = { [ C(OP_READ) ] = { [ C(RESULT_ACCESS) ] = 0x81d0, /* MEM_INST_RETIRED.ALL_LOADS */ - [ C(RESULT_MISS) ] = 0x608, /* DTLB_LOAD_MISSES.WALK_COMPLETED */ + [ C(RESULT_MISS) ] = 0xe08, /* DTLB_LOAD_MISSES.WALK_COMPLETED */ }, [ C(OP_WRITE) ] = { [ C(RESULT_ACCESS) ] = 0x82d0, /* MEM_INST_RETIRED.ALL_STORES */ - [ C(RESULT_MISS) ] = 0x649, /* DTLB_STORE_MISSES.WALK_COMPLETED */ + [ C(RESULT_MISS) ] = 0xe49, /* DTLB_STORE_MISSES.WALK_COMPLETED */ }, [ C(OP_PREFETCH) ] = { [ C(RESULT_ACCESS) ] = 0x0, @@ -3160,6 +3160,19 @@ err: return -ENOMEM; } +static void flip_smm_bit(void *data) +{ + unsigned long set = *(unsigned long *)data; + + if (set > 0) { + msr_set_bit(MSR_IA32_DEBUGCTLMSR, + DEBUGCTLMSR_FREEZE_IN_SMM_BIT); + } else { + msr_clear_bit(MSR_IA32_DEBUGCTLMSR, + DEBUGCTLMSR_FREEZE_IN_SMM_BIT); + } +} + static void intel_pmu_cpu_starting(int cpu) { struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); @@ -3174,6 +3187,8 @@ static void intel_pmu_cpu_starting(int cpu) cpuc->lbr_sel = NULL; + flip_smm_bit(&x86_pmu.attr_freeze_on_smi); + if (!cpuc->shared_regs) return; @@ -3595,6 +3610,52 @@ static struct attribute *hsw_events_attrs[] = { NULL }; +static ssize_t freeze_on_smi_show(struct device *cdev, + struct device_attribute *attr, + char *buf) +{ + return sprintf(buf, "%lu\n", x86_pmu.attr_freeze_on_smi); +} + +static DEFINE_MUTEX(freeze_on_smi_mutex); + +static ssize_t freeze_on_smi_store(struct device *cdev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + unsigned long val; + ssize_t ret; + + ret = kstrtoul(buf, 0, &val); + if (ret) + return ret; + + if (val > 1) + return -EINVAL; + + mutex_lock(&freeze_on_smi_mutex); + + if (x86_pmu.attr_freeze_on_smi == val) + goto done; + + x86_pmu.attr_freeze_on_smi = val; + + get_online_cpus(); + on_each_cpu(flip_smm_bit, &val, 1); + put_online_cpus(); +done: + mutex_unlock(&freeze_on_smi_mutex); + + return count; +} + +static DEVICE_ATTR_RW(freeze_on_smi); + +static struct attribute *intel_pmu_attrs[] = { + &dev_attr_freeze_on_smi.attr, + NULL, +}; + __init int intel_pmu_init(void) { union cpuid10_edx edx; @@ -3641,6 +3702,8 @@ __init int intel_pmu_init(void) x86_pmu.max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, x86_pmu.num_counters); + + x86_pmu.attrs = intel_pmu_attrs; /* * Quirk: v2 perfmon does not report fixed-purpose events, so * assume at least 3 events, when not running in a hypervisor: diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index f924629836a8..eb261656a320 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -18,7 +18,7 @@ enum { LBR_FORMAT_MAX_KNOWN = LBR_FORMAT_TIME, }; -static enum { +static const enum { LBR_EIP_FLAGS = 1, LBR_TSX = 2, } lbr_desc[LBR_FORMAT_MAX_KNOWN + 1] = { @@ -287,7 +287,7 @@ inline u64 lbr_from_signext_quirk_wr(u64 val) /* * If quirk is needed, ensure sign extension is 61 bits: */ -u64 lbr_from_signext_quirk_rd(u64 val) +static u64 lbr_from_signext_quirk_rd(u64 val) { if (static_branch_unlikely(&lbr_from_quirk_key)) { /* diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 758c1aa5009d..44ec523287f6 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1170,7 +1170,7 @@ static int uncore_event_cpu_online(unsigned int cpu) pmu = type->pmus; for (i = 0; i < type->num_boxes; i++, pmu++) { box = pmu->boxes[pkg]; - if (!box && atomic_inc_return(&box->refcnt) == 1) + if (box && atomic_inc_return(&box->refcnt) == 1) uncore_box_init(box); } } diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index be3d36254040..53728eea1bed 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -562,6 +562,9 @@ struct x86_pmu { ssize_t (*events_sysfs_show)(char *page, u64 config); struct attribute **cpu_events; + unsigned long attr_freeze_on_smi; + struct attribute **attrs; + /* * CPU Hotplug hooks */ diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index caa5798c92f4..33380b871463 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -246,19 +246,6 @@ static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u) return c; } -/** - * atomic_inc_short - increment of a short integer - * @v: pointer to type int - * - * Atomically adds 1 to @v - * Returns the new value of @u - */ -static __always_inline short int atomic_inc_short(short int *v) -{ - asm(LOCK_PREFIX "addw $1, %0" : "+m" (*v)); - return *v; -} - #ifdef CONFIG_X86_32 # include <asm/atomic64_32.h> #else diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 2f77bcefe6b4..d2ff779f347e 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -74,7 +74,7 @@ struct efi_scratch { __kernel_fpu_begin(); \ \ if (efi_scratch.use_pgd) { \ - efi_scratch.prev_cr3 = read_cr3(); \ + efi_scratch.prev_cr3 = __read_cr3(); \ write_cr3((unsigned long)efi_scratch.efi_pgt); \ __flush_tlb_all(); \ } \ diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index 59405a248fc2..9b76cd331990 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -22,8 +22,8 @@ typedef struct { #ifdef CONFIG_SMP unsigned int irq_resched_count; unsigned int irq_call_count; - unsigned int irq_tlb_count; #endif + unsigned int irq_tlb_count; #ifdef CONFIG_X86_THERMAL_VECTOR unsigned int irq_thermal_count; #endif diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 055962615779..722d0e568863 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -296,6 +296,7 @@ struct x86_emulate_ctxt { bool perm_ok; /* do not check permissions if true */ bool ud; /* inject an #UD if host doesn't support insn */ + bool tf; /* TF value before instruction (after for syscall/sysret) */ bool have_exception; struct x86_exception exception; diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index f9813b6d8b80..79b647a7ebd0 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -37,12 +37,6 @@ typedef struct { #endif } mm_context_t; -#ifdef CONFIG_SMP void leave_mm(int cpu); -#else -static inline void leave_mm(int cpu) -{ -} -#endif #endif /* _ASM_X86_MMU_H */ diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 68b329d77b3a..ecfcb6643c9b 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -47,7 +47,7 @@ struct ldt_struct { * allocations, but it's not worth trying to optimize. */ struct desc_struct *entries; - unsigned int size; + unsigned int nr_entries; }; /* @@ -87,22 +87,46 @@ static inline void load_mm_ldt(struct mm_struct *mm) */ if (unlikely(ldt)) - set_ldt(ldt->entries, ldt->size); + set_ldt(ldt->entries, ldt->nr_entries); else clear_LDT(); #else clear_LDT(); #endif +} + +static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next) +{ +#ifdef CONFIG_MODIFY_LDT_SYSCALL + /* + * Load the LDT if either the old or new mm had an LDT. + * + * An mm will never go from having an LDT to not having an LDT. Two + * mms never share an LDT, so we don't gain anything by checking to + * see whether the LDT changed. There's also no guarantee that + * prev->context.ldt actually matches LDTR, but, if LDTR is non-NULL, + * then prev->context.ldt will also be non-NULL. + * + * If we really cared, we could optimize the case where prev == next + * and we're exiting lazy mode. Most of the time, if this happens, + * we don't actually need to reload LDTR, but modify_ldt() is mostly + * used by legacy code and emulators where we don't need this level of + * performance. + * + * This uses | instead of || because it generates better code. + */ + if (unlikely((unsigned long)prev->context.ldt | + (unsigned long)next->context.ldt)) + load_mm_ldt(next); +#endif DEBUG_LOCKS_WARN_ON(preemptible()); } static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) { -#ifdef CONFIG_SMP if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) this_cpu_write(cpu_tlbstate.state, TLBSTATE_LAZY); -#endif } static inline int init_new_context(struct task_struct *tsk, @@ -220,18 +244,6 @@ static inline int vma_pkey(struct vm_area_struct *vma) } #endif -static inline bool __pkru_allows_pkey(u16 pkey, bool write) -{ - u32 pkru = read_pkru(); - - if (!__pkru_allows_read(pkru, pkey)) - return false; - if (write && !__pkru_allows_write(pkru, pkey)) - return false; - - return true; -} - /* * We only want to enforce protection keys on the current process * because we effectively have no access to PKRU for other @@ -268,4 +280,23 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, return __pkru_allows_pkey(vma_pkey(vma), write); } + +/* + * This can be used from process context to figure out what the value of + * CR3 is without needing to do a (slow) __read_cr3(). + * + * It's intended to be used for code like KVM that sneakily changes CR3 + * and needs to restore it. It needs to be used very carefully. + */ +static inline unsigned long __get_current_cr3_fast(void) +{ + unsigned long cr3 = __pa(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd); + + /* For now, be very restrictive about when this can be called. */ + VM_WARN_ON(in_nmi() || !in_atomic()); + + VM_BUG_ON(cr3 != __read_cr3()); + return cr3; +} + #endif /* _ASM_X86_MMU_CONTEXT_H */ diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index fba100713924..d5acc27ed1cc 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -2,8 +2,7 @@ #define _ASM_X86_MSHYPER_H #include <linux/types.h> -#include <linux/interrupt.h> -#include <linux/clocksource.h> +#include <linux/atomic.h> #include <asm/hyperv.h> /* diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 673f9ac50f6d..18b162322eff 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -137,6 +137,8 @@ #define DEBUGCTLMSR_BTS_OFF_OS (1UL << 9) #define DEBUGCTLMSR_BTS_OFF_USR (1UL << 10) #define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI (1UL << 11) +#define DEBUGCTLMSR_FREEZE_IN_SMM_BIT 14 +#define DEBUGCTLMSR_FREEZE_IN_SMM (1UL << DEBUGCTLMSR_FREEZE_IN_SMM_BIT) #define MSR_PEBS_FRONTEND 0x000003f7 diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 55fa56fe4e45..9ccac1926587 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -61,7 +61,7 @@ static inline void write_cr2(unsigned long x) PVOP_VCALL1(pv_mmu_ops.write_cr2, x); } -static inline unsigned long read_cr3(void) +static inline unsigned long __read_cr3(void) { return PVOP_CALL0(unsigned long, pv_mmu_ops.read_cr3); } @@ -118,7 +118,7 @@ static inline u64 paravirt_read_msr(unsigned msr) static inline void paravirt_write_msr(unsigned msr, unsigned low, unsigned high) { - return PVOP_VCALL3(pv_cpu_ops.write_msr, msr, low, high); + PVOP_VCALL3(pv_cpu_ops.write_msr, msr, low, high); } static inline u64 paravirt_read_msr_safe(unsigned msr, int *err) @@ -312,11 +312,9 @@ static inline void __flush_tlb_single(unsigned long addr) } static inline void flush_tlb_others(const struct cpumask *cpumask, - struct mm_struct *mm, - unsigned long start, - unsigned long end) + const struct flush_tlb_info *info) { - PVOP_VCALL4(pv_mmu_ops.flush_tlb_others, cpumask, mm, start, end); + PVOP_VCALL2(pv_mmu_ops.flush_tlb_others, cpumask, info); } static inline int paravirt_pgd_alloc(struct mm_struct *mm) diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 7465d6fe336f..cb976bab6299 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -51,6 +51,7 @@ struct mm_struct; struct desc_struct; struct task_struct; struct cpumask; +struct flush_tlb_info; /* * Wrapper type for pointers to code which uses the non-standard @@ -223,9 +224,7 @@ struct pv_mmu_ops { void (*flush_tlb_kernel)(void); void (*flush_tlb_single)(unsigned long addr); void (*flush_tlb_others)(const struct cpumask *cpus, - struct mm_struct *mm, - unsigned long start, - unsigned long end); + const struct flush_tlb_info *info); /* Hooks for allocating and freeing a pagetable top-level */ int (*pgd_alloc)(struct mm_struct *mm); diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index 50d35e3185f5..c8821bab938f 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -212,4 +212,51 @@ static inline pud_t native_pudp_get_and_clear(pud_t *pudp) #define __pte_to_swp_entry(pte) ((swp_entry_t){ (pte).pte_high }) #define __swp_entry_to_pte(x) ((pte_t){ { .pte_high = (x).val } }) +#define gup_get_pte gup_get_pte +/* + * WARNING: only to be used in the get_user_pages_fast() implementation. + * + * With get_user_pages_fast(), we walk down the pagetables without taking + * any locks. For this we would like to load the pointers atomically, + * but that is not possible (without expensive cmpxchg8b) on PAE. What + * we do have is the guarantee that a PTE will only either go from not + * present to present, or present to not present or both -- it will not + * switch to a completely different present page without a TLB flush in + * between; something that we are blocking by holding interrupts off. + * + * Setting ptes from not present to present goes: + * + * ptep->pte_high = h; + * smp_wmb(); + * ptep->pte_low = l; + * + * And present to not present goes: + * + * ptep->pte_low = 0; + * smp_wmb(); + * ptep->pte_high = 0; + * + * We must ensure here that the load of pte_low sees 'l' iff pte_high + * sees 'h'. We load pte_high *after* loading pte_low, which ensures we + * don't see an older value of pte_high. *Then* we recheck pte_low, + * which ensures that we haven't picked up a changed pte high. We might + * have gotten rubbish values from pte_low and pte_high, but we are + * guaranteed that pte_low will not have the present bit set *unless* + * it is 'l'. Because get_user_pages_fast() only operates on present ptes + * we're safe. + */ +static inline pte_t gup_get_pte(pte_t *ptep) +{ + pte_t pte; + + do { + pte.pte_low = ptep->pte_low; + smp_rmb(); + pte.pte_high = ptep->pte_high; + smp_rmb(); + } while (unlikely(pte.pte_low != ptep->pte_low)); + + return pte; +} + #endif /* _ASM_X86_PGTABLE_3LEVEL_H */ diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index f5af95a0c6b8..77037b6f1caa 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -244,6 +244,11 @@ static inline int pud_devmap(pud_t pud) return 0; } #endif + +static inline int pgd_devmap(pgd_t pgd) +{ + return 0; +} #endif #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ @@ -917,7 +922,7 @@ extern pgd_t trampoline_pgd_entry; static inline void __meminit init_trampoline_default(void) { /* Default trampoline pgd value */ - trampoline_pgd_entry = init_level4_pgt[pgd_index(__PAGE_OFFSET)]; + trampoline_pgd_entry = init_top_pgt[pgd_index(__PAGE_OFFSET)]; } # ifdef CONFIG_RANDOMIZE_MEMORY void __meminit init_trampoline(void); @@ -1185,6 +1190,54 @@ static inline u16 pte_flags_pkey(unsigned long pte_flags) #endif } +static inline bool __pkru_allows_pkey(u16 pkey, bool write) +{ + u32 pkru = read_pkru(); + + if (!__pkru_allows_read(pkru, pkey)) + return false; + if (write && !__pkru_allows_write(pkru, pkey)) + return false; + + return true; +} + +/* + * 'pteval' can come from a PTE, PMD or PUD. We only check + * _PAGE_PRESENT, _PAGE_USER, and _PAGE_RW in here which are the + * same value on all 3 types. + */ +static inline bool __pte_access_permitted(unsigned long pteval, bool write) +{ + unsigned long need_pte_bits = _PAGE_PRESENT|_PAGE_USER; + + if (write) + need_pte_bits |= _PAGE_RW; + + if ((pteval & need_pte_bits) != need_pte_bits) + return 0; + + return __pkru_allows_pkey(pte_flags_pkey(pteval), write); +} + +#define pte_access_permitted pte_access_permitted +static inline bool pte_access_permitted(pte_t pte, bool write) +{ + return __pte_access_permitted(pte_val(pte), write); +} + +#define pmd_access_permitted pmd_access_permitted +static inline bool pmd_access_permitted(pmd_t pmd, bool write) +{ + return __pte_access_permitted(pmd_val(pmd), write); +} + +#define pud_access_permitted pud_access_permitted +static inline bool pud_access_permitted(pud_t pud, bool write) +{ + return __pte_access_permitted(pud_val(pud), write); +} + #include <asm-generic/pgtable.h> #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 9991224f6238..2160c1fee920 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -14,15 +14,17 @@ #include <linux/bitops.h> #include <linux/threads.h> +extern p4d_t level4_kernel_pgt[512]; +extern p4d_t level4_ident_pgt[512]; extern pud_t level3_kernel_pgt[512]; extern pud_t level3_ident_pgt[512]; extern pmd_t level2_kernel_pgt[512]; extern pmd_t level2_fixmap_pgt[512]; extern pmd_t level2_ident_pgt[512]; extern pte_t level1_fixmap_pgt[512]; -extern pgd_t init_level4_pgt[]; +extern pgd_t init_top_pgt[]; -#define swapper_pg_dir init_level4_pgt +#define swapper_pg_dir init_top_pgt extern void paging_init(void); @@ -227,6 +229,20 @@ extern void cleanup_highmap(void); extern void init_extra_mapping_uc(unsigned long phys, unsigned long size); extern void init_extra_mapping_wb(unsigned long phys, unsigned long size); -#endif /* !__ASSEMBLY__ */ +#define gup_fast_permitted gup_fast_permitted +static inline bool gup_fast_permitted(unsigned long start, int nr_pages, + int write) +{ + unsigned long len, end; + + len = (unsigned long)nr_pages << PAGE_SHIFT; + end = start + len; + if (end < start) + return false; + if (end >> __VIRTUAL_MASK_SHIFT) + return false; + return true; +} +#endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_PGTABLE_64_H */ diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h index 39fb618e2211..79aa2f98398d 100644 --- a/arch/x86/include/asm/processor-flags.h +++ b/arch/x86/include/asm/processor-flags.h @@ -8,4 +8,40 @@ #else #define X86_VM_MASK 0 /* No VM86 support */ #endif + +/* + * CR3's layout varies depending on several things. + * + * If CR4.PCIDE is set (64-bit only), then CR3[11:0] is the address space ID. + * If PAE is enabled, then CR3[11:5] is part of the PDPT address + * (i.e. it's 32-byte aligned, not page-aligned) and CR3[4:0] is ignored. + * Otherwise (non-PAE, non-PCID), CR3[3] is PWT, CR3[4] is PCD, and + * CR3[2:0] and CR3[11:5] are ignored. + * + * In all cases, Linux puts zeros in the low ignored bits and in PWT and PCD. + * + * CR3[63] is always read as zero. If CR4.PCIDE is set, then CR3[63] may be + * written as 1 to prevent the write to CR3 from flushing the TLB. + * + * On systems with SME, one bit (in a variable position!) is stolen to indicate + * that the top-level paging structure is encrypted. + * + * All of the remaining bits indicate the physical address of the top-level + * paging structure. + * + * CR3_ADDR_MASK is the mask used by read_cr3_pa(). + */ +#ifdef CONFIG_X86_64 +/* Mask off the address space ID bits. */ +#define CR3_ADDR_MASK 0x7FFFFFFFFFFFF000ull +#define CR3_PCID_MASK 0xFFFull +#else +/* + * CR3_ADDR_MASK needs at least bits 31:5 set on PAE systems, and we save + * a tiny bit of code size by setting all the bits. + */ +#define CR3_ADDR_MASK 0xFFFFFFFFull +#define CR3_PCID_MASK 0ull +#endif + #endif /* _ASM_X86_PROCESSOR_FLAGS_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 3cada998a402..2e1696294af5 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -231,6 +231,14 @@ native_cpuid_reg(ebx) native_cpuid_reg(ecx) native_cpuid_reg(edx) +/* + * Friendlier CR3 helpers. + */ +static inline unsigned long read_cr3_pa(void) +{ + return __read_cr3() & CR3_ADDR_MASK; +} + static inline void load_cr3(pgd_t *pgdir) { write_cr3(__pa(pgdir)); @@ -860,8 +868,6 @@ extern unsigned long KSTK_ESP(struct task_struct *task); #endif /* CONFIG_X86_64 */ -extern unsigned long thread_saved_pc(struct task_struct *tsk); - extern void start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp); diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index 12af3e35edfa..9efaabf5b54b 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -39,7 +39,7 @@ static inline void native_write_cr2(unsigned long val) asm volatile("mov %0,%%cr2": : "r" (val), "m" (__force_order)); } -static inline unsigned long native_read_cr3(void) +static inline unsigned long __native_read_cr3(void) { unsigned long val; asm volatile("mov %%cr3,%0\n\t" : "=r" (val), "=m" (__force_order)); @@ -159,9 +159,13 @@ static inline void write_cr2(unsigned long x) native_write_cr2(x); } -static inline unsigned long read_cr3(void) +/* + * Careful! CR3 contains more than just an address. You probably want + * read_cr3_pa() instead. + */ +static inline unsigned long __read_cr3(void) { - return native_read_cr3(); + return __native_read_cr3(); } static inline void write_cr3(unsigned long x) diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h index 27e9f9d769b8..2016962103df 100644 --- a/arch/x86/include/asm/timer.h +++ b/arch/x86/include/asm/timer.h @@ -29,11 +29,9 @@ struct cyc2ns_data { u32 cyc2ns_mul; u32 cyc2ns_shift; u64 cyc2ns_offset; - u32 __count; - /* u32 hole */ -}; /* 24 bytes -- do not grow */ +}; /* 16 bytes */ -extern struct cyc2ns_data *cyc2ns_read_begin(void); -extern void cyc2ns_read_end(struct cyc2ns_data *); +extern void cyc2ns_read_begin(struct cyc2ns_data *); +extern void cyc2ns_read_end(void); #endif /* _ASM_X86_TIMER_H */ diff --git a/arch/x86/include/asm/tlbbatch.h b/arch/x86/include/asm/tlbbatch.h new file mode 100644 index 000000000000..f4a6ff352a0e --- /dev/null +++ b/arch/x86/include/asm/tlbbatch.h @@ -0,0 +1,14 @@ +#ifndef _ARCH_X86_TLBBATCH_H +#define _ARCH_X86_TLBBATCH_H + +#include <linux/cpumask.h> + +struct arch_tlbflush_unmap_batch { + /* + * Each bit set is a CPU that potentially has a TLB entry for one of + * the PFNs being flushed.. + */ + struct cpumask cpumask; +}; + +#endif /* _ARCH_X86_TLBBATCH_H */ diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 6ed9ea469b48..50ea3482e1d1 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -7,6 +7,7 @@ #include <asm/processor.h> #include <asm/cpufeature.h> #include <asm/special_insns.h> +#include <asm/smp.h> static inline void __invpcid(unsigned long pcid, unsigned long addr, unsigned long type) @@ -65,10 +66,14 @@ static inline void invpcid_flush_all_nonglobals(void) #endif struct tlb_state { -#ifdef CONFIG_SMP - struct mm_struct *active_mm; + /* + * cpu_tlbstate.loaded_mm should match CR3 whenever interrupts + * are on. This means that it may not match current->active_mm, + * which will contain the previous user mm when we're in lazy TLB + * mode even if we've already switched back to swapper_pg_dir. + */ + struct mm_struct *loaded_mm; int state; -#endif /* * Access to this CR4 shadow and to H/W CR4 is protected by @@ -151,7 +156,7 @@ static inline void __native_flush_tlb(void) * back: */ preempt_disable(); - native_write_cr3(native_read_cr3()); + native_write_cr3(__native_read_cr3()); preempt_enable(); } @@ -220,84 +225,16 @@ static inline void __flush_tlb_one(unsigned long addr) * - flush_tlb_page(vma, vmaddr) flushes one page * - flush_tlb_range(vma, start, end) flushes a range of pages * - flush_tlb_kernel_range(start, end) flushes a range of kernel pages - * - flush_tlb_others(cpumask, mm, start, end) flushes TLBs on other cpus + * - flush_tlb_others(cpumask, info) flushes TLBs on other cpus * * ..but the i386 has somewhat limited tlb flushing capabilities, * and page-granular flushes are available only on i486 and up. */ - -#ifndef CONFIG_SMP - -/* "_up" is for UniProcessor. - * - * This is a helper for other header functions. *Not* intended to be called - * directly. All global TLB flushes need to either call this, or to bump the - * vm statistics themselves. - */ -static inline void __flush_tlb_up(void) -{ - count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); - __flush_tlb(); -} - -static inline void flush_tlb_all(void) -{ - count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); - __flush_tlb_all(); -} - -static inline void local_flush_tlb(void) -{ - __flush_tlb_up(); -} - -static inline void flush_tlb_mm(struct mm_struct *mm) -{ - if (mm == current->active_mm) - __flush_tlb_up(); -} - -static inline void flush_tlb_page(struct vm_area_struct *vma, - unsigned long addr) -{ - if (vma->vm_mm == current->active_mm) - __flush_tlb_one(addr); -} - -static inline void flush_tlb_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end) -{ - if (vma->vm_mm == current->active_mm) - __flush_tlb_up(); -} - -static inline void flush_tlb_mm_range(struct mm_struct *mm, - unsigned long start, unsigned long end, unsigned long vmflag) -{ - if (mm == current->active_mm) - __flush_tlb_up(); -} - -static inline void native_flush_tlb_others(const struct cpumask *cpumask, - struct mm_struct *mm, - unsigned long start, - unsigned long end) -{ -} - -static inline void reset_lazy_tlbstate(void) -{ -} - -static inline void flush_tlb_kernel_range(unsigned long start, - unsigned long end) -{ - flush_tlb_all(); -} - -#else /* SMP */ - -#include <asm/smp.h> +struct flush_tlb_info { + struct mm_struct *mm; + unsigned long start; + unsigned long end; +}; #define local_flush_tlb() __flush_tlb() @@ -307,29 +244,32 @@ static inline void flush_tlb_kernel_range(unsigned long start, flush_tlb_mm_range(vma->vm_mm, start, end, vma->vm_flags) extern void flush_tlb_all(void); -extern void flush_tlb_page(struct vm_area_struct *, unsigned long); extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, unsigned long end, unsigned long vmflag); extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); +static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a) +{ + flush_tlb_mm_range(vma->vm_mm, a, a + PAGE_SIZE, VM_NONE); +} + void native_flush_tlb_others(const struct cpumask *cpumask, - struct mm_struct *mm, - unsigned long start, unsigned long end); + const struct flush_tlb_info *info); #define TLBSTATE_OK 1 #define TLBSTATE_LAZY 2 -static inline void reset_lazy_tlbstate(void) +static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch, + struct mm_struct *mm) { - this_cpu_write(cpu_tlbstate.state, 0); - this_cpu_write(cpu_tlbstate.active_mm, &init_mm); + cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm)); } -#endif /* SMP */ +extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch); #ifndef CONFIG_PARAVIRT -#define flush_tlb_others(mask, mm, start, end) \ - native_flush_tlb_others(mask, mm, start, end) +#define flush_tlb_others(mask, info) \ + native_flush_tlb_others(mask, info) #endif #endif /* _ASM_X86_TLBFLUSH_H */ diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h index 6686820feae9..b5a32231abd8 100644 --- a/arch/x86/include/asm/uv/uv.h +++ b/arch/x86/include/asm/uv/uv.h @@ -1,6 +1,8 @@ #ifndef _ASM_X86_UV_UV_H #define _ASM_X86_UV_UV_H +#include <asm/tlbflush.h> + enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC}; struct cpumask; @@ -15,10 +17,7 @@ extern void uv_cpu_init(void); extern void uv_nmi_init(void); extern void uv_system_init(void); extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, - struct mm_struct *mm, - unsigned long start, - unsigned long end, - unsigned int cpu); + const struct flush_tlb_info *info); #else /* X86_UV */ @@ -28,8 +27,8 @@ static inline int is_uv_hubless(void) { return 0; } static inline void uv_cpu_init(void) { } static inline void uv_system_init(void) { } static inline const struct cpumask * -uv_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm, - unsigned long start, unsigned long end, unsigned int cpu) +uv_flush_tlb_others(const struct cpumask *cpumask, + const struct flush_tlb_info *info) { return cpumask; } #endif /* X86_UV */ diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h index 432df4b1baec..f4fef5a24ebd 100644 --- a/arch/x86/include/uapi/asm/hyperv.h +++ b/arch/x86/include/uapi/asm/hyperv.h @@ -34,16 +34,10 @@ #define HV_X64_MSR_REFERENCE_TSC 0x40000021 /* - * There is a single feature flag that signifies the presence of the MSR - * that can be used to retrieve both the local APIC Timer frequency as - * well as the TSC frequency. + * There is a single feature flag that signifies if the partition has access + * to MSRs with local APIC and TSC frequencies. */ - -/* Local APIC timer frequency MSR (HV_X64_MSR_APIC_FREQUENCY) is available */ -#define HV_X64_MSR_APIC_FREQUENCY_AVAILABLE (1 << 11) - -/* TSC frequency MSR (HV_X64_MSR_TSC_FREQUENCY) is available */ -#define HV_X64_MSR_TSC_FREQUENCY_AVAILABLE (1 << 11) +#define HV_X64_ACCESS_FREQUENCY_MSRS (1 << 11) /* * Basic SynIC MSRs (HV_X64_MSR_SCONTROL through HV_X64_MSR_EOM @@ -73,6 +67,9 @@ */ #define HV_X64_MSR_STAT_PAGES_AVAILABLE (1 << 8) +/* Frequency MSRs available */ +#define HV_FEATURE_FREQUENCY_MSRS_AVAILABLE (1 << 8) + /* Crash MSR available */ #define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE (1 << 10) diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h index 567de50a4c2a..185f3d10c194 100644 --- a/arch/x86/include/uapi/asm/processor-flags.h +++ b/arch/x86/include/uapi/asm/processor-flags.h @@ -104,6 +104,8 @@ #define X86_CR4_OSFXSR _BITUL(X86_CR4_OSFXSR_BIT) #define X86_CR4_OSXMMEXCPT_BIT 10 /* enable unmasked SSE exceptions */ #define X86_CR4_OSXMMEXCPT _BITUL(X86_CR4_OSXMMEXCPT_BIT) +#define X86_CR4_LA57_BIT 12 /* enable 5-level page tables */ +#define X86_CR4_LA57 _BITUL(X86_CR4_LA57_BIT) #define X86_CR4_VMXE_BIT 13 /* enable VMX virtualization */ #define X86_CR4_VMXE _BITUL(X86_CR4_VMXE_BIT) #define X86_CR4_SMXE_BIT 14 /* enable safer mode (TXT) */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 4b994232cb57..a01892bdd61a 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -18,6 +18,7 @@ CFLAGS_REMOVE_pvclock.o = -pg CFLAGS_REMOVE_kvmclock.o = -pg CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_early_printk.o = -pg +CFLAGS_REMOVE_head64.o = -pg endif KASAN_SANITIZE_head$(BITS).o := n @@ -29,6 +30,7 @@ OBJECT_FILES_NON_STANDARD_head_$(BITS).o := y OBJECT_FILES_NON_STANDARD_relocate_kernel_$(BITS).o := y OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o := y OBJECT_FILES_NON_STANDARD_test_nx.o := y +OBJECT_FILES_NON_STANDARD_paravirt_patch_$(BITS).o := y # If instrumentation of this dir is enabled, boot hangs during first second. # Probably could be more selective here, but note that files related to irqs, diff --git a/arch/x86/kernel/acpi/Makefile b/arch/x86/kernel/acpi/Makefile index 26b78d86f25a..85a9e17e0dbc 100644 --- a/arch/x86/kernel/acpi/Makefile +++ b/arch/x86/kernel/acpi/Makefile @@ -1,3 +1,5 @@ +OBJECT_FILES_NON_STANDARD_wakeup_$(BITS).o := y + obj-$(CONFIG_ACPI) += boot.o obj-$(CONFIG_ACPI_SLEEP) += sleep.o wakeup_$(BITS).o obj-$(CONFIG_ACPI_APEI) += apei.o diff --git a/arch/x86/kernel/apic/htirq.c b/arch/x86/kernel/apic/htirq.c index ae50d3454d78..81ff48905623 100644 --- a/arch/x86/kernel/apic/htirq.c +++ b/arch/x86/kernel/apic/htirq.c @@ -150,7 +150,7 @@ static const struct irq_domain_ops htirq_domain_ops = { .deactivate = htirq_domain_deactivate, }; -void arch_init_htirq_domain(struct irq_domain *parent) +void __init arch_init_htirq_domain(struct irq_domain *parent) { if (disable_apic) return; diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 347bb9f65737..247880fc29f9 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1200,28 +1200,6 @@ EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector); static struct irq_chip ioapic_chip, ioapic_ir_chip; -#ifdef CONFIG_X86_32 -static inline int IO_APIC_irq_trigger(int irq) -{ - int apic, idx, pin; - - for_each_ioapic_pin(apic, pin) { - idx = find_irq_entry(apic, pin, mp_INT); - if ((idx != -1) && (irq == pin_2_irq(idx, apic, pin, 0))) - return irq_trigger(idx); - } - /* - * nonexistent IRQs are edge default - */ - return 0; -} -#else -static inline int IO_APIC_irq_trigger(int irq) -{ - return 1; -} -#endif - static void __init setup_IO_APIC_irqs(void) { unsigned int ioapic, pin; diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index c61aec7e65f4..4c5d1882bec5 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -136,7 +136,7 @@ static struct msi_domain_info pci_msi_domain_info = { .handler_name = "edge", }; -void arch_init_msi_domain(struct irq_domain *parent) +void __init arch_init_msi_domain(struct irq_domain *parent) { if (disable_apic) return; diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index f3557a1eb562..e66d8e48e456 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -405,7 +405,7 @@ int __init arch_probe_nr_irqs(void) } #ifdef CONFIG_X86_IO_APIC -static void init_legacy_irqs(void) +static void __init init_legacy_irqs(void) { int i, node = cpu_to_node(0); struct apic_chip_data *data; @@ -424,7 +424,7 @@ static void init_legacy_irqs(void) } } #else -static void init_legacy_irqs(void) { } +static inline void init_legacy_irqs(void) { } #endif int __init arch_early_irq_init(void) diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index f5af0cc7eb0d..9257bd9dc664 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -856,11 +856,13 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type, dentry = kernfs_mount(fs_type, flags, rdt_root, RDTGROUP_SUPER_MAGIC, NULL); if (IS_ERR(dentry)) - goto out_cdp; + goto out_destroy; static_branch_enable(&rdt_enable_key); goto out; +out_destroy: + kernfs_remove(kn_info); out_cdp: cdp_disable(); out: diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index e9f4d762aa5b..21b185793c80 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -251,7 +251,7 @@ static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family) #endif } -void __load_ucode_amd(unsigned int cpuid_1_eax, struct cpio_data *ret) +static void __load_ucode_amd(unsigned int cpuid_1_eax, struct cpio_data *ret) { struct ucode_cpu_info *uci; struct cpio_data cp; diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index e53d3c909840..9cb98ee103db 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -290,6 +290,17 @@ struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa) return (struct cpio_data){ NULL, 0, "" }; if (initrd_start) start = initrd_start; + } else { + /* + * The picture with physical addresses is a bit different: we + * need to get the *physical* address to which the ramdisk was + * relocated, i.e., relocated_ramdisk (not initrd_start) and + * since we're running from physical addresses, we need to access + * relocated_ramdisk through its *physical* address too. + */ + u64 *rr = (u64 *)__pa_nodebug(&relocated_ramdisk); + if (*rr) + start = *rr; } return find_cpio_data(path, (void *)start, size, NULL); diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index f522415bf9e5..59edbe9d4ccb 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -42,7 +42,7 @@ static const char ucode_path[] = "kernel/x86/microcode/GenuineIntel.bin"; /* Current microcode patch used in early patching on the APs. */ -struct microcode_intel *intel_ucode_patch; +static struct microcode_intel *intel_ucode_patch; static inline bool cpu_signatures_match(unsigned int s1, unsigned int p1, unsigned int s2, unsigned int p2) @@ -166,7 +166,7 @@ static struct ucode_patch *__alloc_microcode_buf(void *data, unsigned int size) static void save_microcode_patch(void *data, unsigned int size) { struct microcode_header_intel *mc_hdr, *mc_saved_hdr; - struct ucode_patch *iter, *tmp, *p; + struct ucode_patch *iter, *tmp, *p = NULL; bool prev_found = false; unsigned int sig, pf; @@ -202,6 +202,18 @@ static void save_microcode_patch(void *data, unsigned int size) else list_add_tail(&p->plist, µcode_cache); } + + /* + * Save for early loading. On 32-bit, that needs to be a physical + * address as the APs are running from physical addresses, before + * paging has been enabled. + */ + if (p) { + if (IS_ENABLED(CONFIG_X86_32)) + intel_ucode_patch = (struct microcode_intel *)__pa_nodebug(p->data); + else + intel_ucode_patch = p->data; + } } static int microcode_sanity_check(void *mc, int print_err) @@ -607,6 +619,14 @@ int __init save_microcode_in_initrd_intel(void) struct ucode_cpu_info uci; struct cpio_data cp; + /* + * initrd is going away, clear patch ptr. We will scan the microcode one + * last time before jettisoning and save a patch, if found. Then we will + * update that pointer too, with a stable patch address to use when + * resuming the cores. + */ + intel_ucode_patch = NULL; + if (!load_builtin_intel_microcode(&cp)) cp = find_microcode_in_initrd(ucode_path, false); @@ -619,9 +639,6 @@ int __init save_microcode_in_initrd_intel(void) show_saved_mc(); - /* initrd is going away, clear patch ptr. */ - intel_ucode_patch = NULL; - return 0; } diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 04cb8d34ccb8..70e717fccdd6 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -161,6 +161,15 @@ static int hv_nmi_unknown(unsigned int val, struct pt_regs *regs) } #endif +static unsigned long hv_get_tsc_khz(void) +{ + unsigned long freq; + + rdmsrl(HV_X64_MSR_TSC_FREQUENCY, freq); + + return freq / 1000; +} + static void __init ms_hyperv_init_platform(void) { int hv_host_info_eax; @@ -193,8 +202,15 @@ static void __init ms_hyperv_init_platform(void) hv_host_info_edx >> 24, hv_host_info_edx & 0xFFFFFF); } + if (ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS && + ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) { + x86_platform.calibrate_tsc = hv_get_tsc_khz; + x86_platform.calibrate_cpu = hv_get_tsc_khz; + } + #ifdef CONFIG_X86_LOCAL_APIC - if (ms_hyperv.features & HV_X64_MSR_APIC_FREQUENCY_AVAILABLE) { + if (ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS && + ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) { /* * Get the APIC frequency. */ diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index 8e598a1ad986..6b91e2eb8d3f 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -125,7 +125,7 @@ void __init init_espfix_bsp(void) p4d_t *p4d; /* Install the espfix pud into the kernel page directory */ - pgd = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)]; + pgd = &init_top_pgt[pgd_index(ESPFIX_BASE_ADDR)]; p4d = p4d_alloc(&init_mm, pgd, ESPFIX_BASE_ADDR); p4d_populate(&init_mm, p4d, espfix_pud_page); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 43b7002f44fb..46c3c73e7f43 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -33,17 +33,120 @@ /* * Manage page tables very early on. */ -extern pgd_t early_level4_pgt[PTRS_PER_PGD]; +extern pgd_t early_top_pgt[PTRS_PER_PGD]; extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD]; -static unsigned int __initdata next_early_pgt = 2; +static unsigned int __initdata next_early_pgt; pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX); +#define __head __section(.head.text) + +static void __head *fixup_pointer(void *ptr, unsigned long physaddr) +{ + return ptr - (void *)_text + (void *)physaddr; +} + +void __head __startup_64(unsigned long physaddr) +{ + unsigned long load_delta, *p; + pgdval_t *pgd; + p4dval_t *p4d; + pudval_t *pud; + pmdval_t *pmd, pmd_entry; + int i; + + /* Is the address too large? */ + if (physaddr >> MAX_PHYSMEM_BITS) + for (;;); + + /* + * Compute the delta between the address I am compiled to run at + * and the address I am actually running at. + */ + load_delta = physaddr - (unsigned long)(_text - __START_KERNEL_map); + + /* Is the address not 2M aligned? */ + if (load_delta & ~PMD_PAGE_MASK) + for (;;); + + /* Fixup the physical addresses in the page table */ + + pgd = fixup_pointer(&early_top_pgt, physaddr); + pgd[pgd_index(__START_KERNEL_map)] += load_delta; + + if (IS_ENABLED(CONFIG_X86_5LEVEL)) { + p4d = fixup_pointer(&level4_kernel_pgt, physaddr); + p4d[511] += load_delta; + } + + pud = fixup_pointer(&level3_kernel_pgt, physaddr); + pud[510] += load_delta; + pud[511] += load_delta; + + pmd = fixup_pointer(level2_fixmap_pgt, physaddr); + pmd[506] += load_delta; + + /* + * Set up the identity mapping for the switchover. These + * entries should *NOT* have the global bit set! This also + * creates a bunch of nonsense entries but that is fine -- + * it avoids problems around wraparound. + */ + + pud = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr); + pmd = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr); + + if (IS_ENABLED(CONFIG_X86_5LEVEL)) { + p4d = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr); + + i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD; + pgd[i + 0] = (pgdval_t)p4d + _KERNPG_TABLE; + pgd[i + 1] = (pgdval_t)p4d + _KERNPG_TABLE; + + i = (physaddr >> P4D_SHIFT) % PTRS_PER_P4D; + p4d[i + 0] = (pgdval_t)pud + _KERNPG_TABLE; + p4d[i + 1] = (pgdval_t)pud + _KERNPG_TABLE; + } else { + i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD; + pgd[i + 0] = (pgdval_t)pud + _KERNPG_TABLE; + pgd[i + 1] = (pgdval_t)pud + _KERNPG_TABLE; + } + + i = (physaddr >> PUD_SHIFT) % PTRS_PER_PUD; + pud[i + 0] = (pudval_t)pmd + _KERNPG_TABLE; + pud[i + 1] = (pudval_t)pmd + _KERNPG_TABLE; + + pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL; + pmd_entry += physaddr; + + for (i = 0; i < DIV_ROUND_UP(_end - _text, PMD_SIZE); i++) { + int idx = i + (physaddr >> PMD_SHIFT) % PTRS_PER_PMD; + pmd[idx] = pmd_entry + i * PMD_SIZE; + } + + /* + * Fixup the kernel text+data virtual addresses. Note that + * we might write invalid pmds, when the kernel is relocated + * cleanup_highmap() fixes this up along with the mappings + * beyond _end. + */ + + pmd = fixup_pointer(level2_kernel_pgt, physaddr); + for (i = 0; i < PTRS_PER_PMD; i++) { + if (pmd[i] & _PAGE_PRESENT) + pmd[i] += load_delta; + } + + /* Fixup phys_base */ + p = fixup_pointer(&phys_base, physaddr); + *p += load_delta; +} + /* Wipe all early page tables except for the kernel symbol map */ static void __init reset_early_page_tables(void) { - memset(early_level4_pgt, 0, sizeof(pgd_t)*(PTRS_PER_PGD-1)); + memset(early_top_pgt, 0, sizeof(pgd_t)*(PTRS_PER_PGD-1)); next_early_pgt = 0; - write_cr3(__pa_nodebug(early_level4_pgt)); + write_cr3(__pa_nodebug(early_top_pgt)); } /* Create a new PMD entry */ @@ -51,15 +154,16 @@ int __init early_make_pgtable(unsigned long address) { unsigned long physaddr = address - __PAGE_OFFSET; pgdval_t pgd, *pgd_p; + p4dval_t p4d, *p4d_p; pudval_t pud, *pud_p; pmdval_t pmd, *pmd_p; /* Invalid address or early pgt is done ? */ - if (physaddr >= MAXMEM || read_cr3() != __pa_nodebug(early_level4_pgt)) + if (physaddr >= MAXMEM || read_cr3_pa() != __pa_nodebug(early_top_pgt)) return -1; again: - pgd_p = &early_level4_pgt[pgd_index(address)].pgd; + pgd_p = &early_top_pgt[pgd_index(address)].pgd; pgd = *pgd_p; /* @@ -67,8 +171,25 @@ again: * critical -- __PAGE_OFFSET would point us back into the dynamic * range and we might end up looping forever... */ - if (pgd) - pud_p = (pudval_t *)((pgd & PTE_PFN_MASK) + __START_KERNEL_map - phys_base); + if (!IS_ENABLED(CONFIG_X86_5LEVEL)) + p4d_p = pgd_p; + else if (pgd) + p4d_p = (p4dval_t *)((pgd & PTE_PFN_MASK) + __START_KERNEL_map - phys_base); + else { + if (next_early_pgt >= EARLY_DYNAMIC_PAGE_TABLES) { + reset_early_page_tables(); + goto again; + } + + p4d_p = (p4dval_t *)early_dynamic_pgts[next_early_pgt++]; + memset(p4d_p, 0, sizeof(*p4d_p) * PTRS_PER_P4D); + *pgd_p = (pgdval_t)p4d_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE; + } + p4d_p += p4d_index(address); + p4d = *p4d_p; + + if (p4d) + pud_p = (pudval_t *)((p4d & PTE_PFN_MASK) + __START_KERNEL_map - phys_base); else { if (next_early_pgt >= EARLY_DYNAMIC_PAGE_TABLES) { reset_early_page_tables(); @@ -77,7 +198,7 @@ again: pud_p = (pudval_t *)early_dynamic_pgts[next_early_pgt++]; memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD); - *pgd_p = (pgdval_t)pud_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE; + *p4d_p = (p4dval_t)pud_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE; } pud_p += pud_index(address); pud = *pud_p; @@ -156,7 +277,7 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) clear_bss(); - clear_page(init_level4_pgt); + clear_page(init_top_pgt); kasan_early_init(); @@ -171,8 +292,8 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) */ load_ucode_bsp(); - /* set init_level4_pgt kernel high mapping*/ - init_level4_pgt[511] = early_level4_pgt[511]; + /* set init_top_pgt kernel high mapping*/ + init_top_pgt[511] = early_top_pgt[511]; x86_64_start_reservations(real_mode_data); } diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index ac9d327d2e42..6225550883df 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -37,10 +37,11 @@ * */ +#define p4d_index(x) (((x) >> P4D_SHIFT) & (PTRS_PER_P4D-1)) #define pud_index(x) (((x) >> PUD_SHIFT) & (PTRS_PER_PUD-1)) -L4_PAGE_OFFSET = pgd_index(__PAGE_OFFSET_BASE) -L4_START_KERNEL = pgd_index(__START_KERNEL_map) +PGD_PAGE_OFFSET = pgd_index(__PAGE_OFFSET_BASE) +PGD_START_KERNEL = pgd_index(__START_KERNEL_map) L3_START_KERNEL = pud_index(__START_KERNEL_map) .text @@ -72,101 +73,12 @@ startup_64: /* Sanitize CPU configuration */ call verify_cpu - /* - * Compute the delta between the address I am compiled to run at and the - * address I am actually running at. - */ - leaq _text(%rip), %rbp - subq $_text - __START_KERNEL_map, %rbp - - /* Is the address not 2M aligned? */ - testl $~PMD_PAGE_MASK, %ebp - jnz bad_address - - /* - * Is the address too large? - */ - leaq _text(%rip), %rax - shrq $MAX_PHYSMEM_BITS, %rax - jnz bad_address - - /* - * Fixup the physical addresses in the page table - */ - addq %rbp, early_level4_pgt + (L4_START_KERNEL*8)(%rip) - - addq %rbp, level3_kernel_pgt + (510*8)(%rip) - addq %rbp, level3_kernel_pgt + (511*8)(%rip) - - addq %rbp, level2_fixmap_pgt + (506*8)(%rip) - - /* - * Set up the identity mapping for the switchover. These - * entries should *NOT* have the global bit set! This also - * creates a bunch of nonsense entries but that is fine -- - * it avoids problems around wraparound. - */ leaq _text(%rip), %rdi - leaq early_level4_pgt(%rip), %rbx - - movq %rdi, %rax - shrq $PGDIR_SHIFT, %rax - - leaq (PAGE_SIZE + _KERNPG_TABLE)(%rbx), %rdx - movq %rdx, 0(%rbx,%rax,8) - movq %rdx, 8(%rbx,%rax,8) - - addq $PAGE_SIZE, %rdx - movq %rdi, %rax - shrq $PUD_SHIFT, %rax - andl $(PTRS_PER_PUD-1), %eax - movq %rdx, PAGE_SIZE(%rbx,%rax,8) - incl %eax - andl $(PTRS_PER_PUD-1), %eax - movq %rdx, PAGE_SIZE(%rbx,%rax,8) - - addq $PAGE_SIZE * 2, %rbx - movq %rdi, %rax - shrq $PMD_SHIFT, %rdi - addq $(__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL), %rax - leaq (_end - 1)(%rip), %rcx - shrq $PMD_SHIFT, %rcx - subq %rdi, %rcx - incl %ecx - -1: - andq $(PTRS_PER_PMD - 1), %rdi - movq %rax, (%rbx,%rdi,8) - incq %rdi - addq $PMD_SIZE, %rax - decl %ecx - jnz 1b - - test %rbp, %rbp - jz .Lskip_fixup + pushq %rsi + call __startup_64 + popq %rsi - /* - * Fixup the kernel text+data virtual addresses. Note that - * we might write invalid pmds, when the kernel is relocated - * cleanup_highmap() fixes this up along with the mappings - * beyond _end. - */ - leaq level2_kernel_pgt(%rip), %rdi - leaq PAGE_SIZE(%rdi), %r8 - /* See if it is a valid page table entry */ -1: testb $_PAGE_PRESENT, 0(%rdi) - jz 2f - addq %rbp, 0(%rdi) - /* Go to the next page */ -2: addq $8, %rdi - cmp %r8, %rdi - jne 1b - - /* Fixup phys_base */ - addq %rbp, phys_base(%rip) - -.Lskip_fixup: - movq $(early_level4_pgt - __START_KERNEL_map), %rax + movq $(early_top_pgt - __START_KERNEL_map), %rax jmp 1f ENTRY(secondary_startup_64) /* @@ -186,14 +98,17 @@ ENTRY(secondary_startup_64) /* Sanitize CPU configuration */ call verify_cpu - movq $(init_level4_pgt - __START_KERNEL_map), %rax + movq $(init_top_pgt - __START_KERNEL_map), %rax 1: - /* Enable PAE mode and PGE */ + /* Enable PAE mode, PGE and LA57 */ movl $(X86_CR4_PAE | X86_CR4_PGE), %ecx +#ifdef CONFIG_X86_5LEVEL + orl $X86_CR4_LA57, %ecx +#endif movq %rcx, %cr4 - /* Setup early boot stage 4 level pagetables. */ + /* Setup early boot stage 4-/5-level pagetables. */ addq phys_base(%rip), %rax movq %rax, %cr3 @@ -417,9 +332,13 @@ GLOBAL(name) .endr __INITDATA -NEXT_PAGE(early_level4_pgt) +NEXT_PAGE(early_top_pgt) .fill 511,8,0 +#ifdef CONFIG_X86_5LEVEL + .quad level4_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE +#else .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE +#endif NEXT_PAGE(early_dynamic_pgts) .fill 512*EARLY_DYNAMIC_PAGE_TABLES,8,0 @@ -427,14 +346,14 @@ NEXT_PAGE(early_dynamic_pgts) .data #ifndef CONFIG_XEN -NEXT_PAGE(init_level4_pgt) +NEXT_PAGE(init_top_pgt) .fill 512,8,0 #else -NEXT_PAGE(init_level4_pgt) +NEXT_PAGE(init_top_pgt) .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE - .org init_level4_pgt + L4_PAGE_OFFSET*8, 0 + .org init_top_pgt + PGD_PAGE_OFFSET*8, 0 .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE - .org init_level4_pgt + L4_START_KERNEL*8, 0 + .org init_top_pgt + PGD_START_KERNEL*8, 0 /* (2^48-(2*1024*1024*1024))/(2^39) = 511 */ .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE @@ -448,6 +367,12 @@ NEXT_PAGE(level2_ident_pgt) PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD) #endif +#ifdef CONFIG_X86_5LEVEL +NEXT_PAGE(level4_kernel_pgt) + .fill 511,8,0 + .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE +#endif + NEXT_PAGE(level3_kernel_pgt) .fill L3_START_KERNEL,8,0 /* (2^48-(2*1024*1024*1024)-((2^39)*511))/(2^30) = 510 */ diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 901c640d152f..69ea0bc1cfa3 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -28,6 +28,7 @@ #include <linux/kdebug.h> #include <linux/kallsyms.h> #include <linux/ftrace.h> +#include <linux/frame.h> #include <asm/text-patching.h> #include <asm/cacheflush.h> @@ -94,6 +95,7 @@ static void synthesize_set_arg1(kprobe_opcode_t *addr, unsigned long val) } asm ( + "optprobe_template_func:\n" ".global optprobe_template_entry\n" "optprobe_template_entry:\n" #ifdef CONFIG_X86_64 @@ -131,7 +133,12 @@ asm ( " popf\n" #endif ".global optprobe_template_end\n" - "optprobe_template_end:\n"); + "optprobe_template_end:\n" + ".type optprobe_template_func, @function\n" + ".size optprobe_template_func, .-optprobe_template_func\n"); + +void optprobe_template_func(void); +STACK_FRAME_NON_STANDARD(optprobe_template_func); #define TMPL_MOVE_IDX \ ((long)&optprobe_template_val - (long)&optprobe_template_entry) diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index d4a15831ac58..a870910c8565 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -22,24 +22,25 @@ #include <asm/syscalls.h> /* context.lock is held for us, so we don't need any locking. */ -static void flush_ldt(void *current_mm) +static void flush_ldt(void *__mm) { + struct mm_struct *mm = __mm; mm_context_t *pc; - if (current->active_mm != current_mm) + if (this_cpu_read(cpu_tlbstate.loaded_mm) != mm) return; - pc = ¤t->active_mm->context; - set_ldt(pc->ldt->entries, pc->ldt->size); + pc = &mm->context; + set_ldt(pc->ldt->entries, pc->ldt->nr_entries); } /* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */ -static struct ldt_struct *alloc_ldt_struct(unsigned int size) +static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries) { struct ldt_struct *new_ldt; unsigned int alloc_size; - if (size > LDT_ENTRIES) + if (num_entries > LDT_ENTRIES) return NULL; new_ldt = kmalloc(sizeof(struct ldt_struct), GFP_KERNEL); @@ -47,7 +48,7 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int size) return NULL; BUILD_BUG_ON(LDT_ENTRY_SIZE != sizeof(struct desc_struct)); - alloc_size = size * LDT_ENTRY_SIZE; + alloc_size = num_entries * LDT_ENTRY_SIZE; /* * Xen is very picky: it requires a page-aligned LDT that has no @@ -65,14 +66,14 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int size) return NULL; } - new_ldt->size = size; + new_ldt->nr_entries = num_entries; return new_ldt; } /* After calling this, the LDT is immutable. */ static void finalize_ldt_struct(struct ldt_struct *ldt) { - paravirt_alloc_ldt(ldt->entries, ldt->size); + paravirt_alloc_ldt(ldt->entries, ldt->nr_entries); } /* context.lock is held */ @@ -91,8 +92,8 @@ static void free_ldt_struct(struct ldt_struct *ldt) if (likely(!ldt)) return; - paravirt_free_ldt(ldt->entries, ldt->size); - if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE) + paravirt_free_ldt(ldt->entries, ldt->nr_entries); + if (ldt->nr_entries * LDT_ENTRY_SIZE > PAGE_SIZE) vfree_atomic(ldt->entries); else free_page((unsigned long)ldt->entries); @@ -122,14 +123,14 @@ int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm) goto out_unlock; } - new_ldt = alloc_ldt_struct(old_mm->context.ldt->size); + new_ldt = alloc_ldt_struct(old_mm->context.ldt->nr_entries); if (!new_ldt) { retval = -ENOMEM; goto out_unlock; } memcpy(new_ldt->entries, old_mm->context.ldt->entries, - new_ldt->size * LDT_ENTRY_SIZE); + new_ldt->nr_entries * LDT_ENTRY_SIZE); finalize_ldt_struct(new_ldt); mm->context.ldt = new_ldt; @@ -152,9 +153,9 @@ void destroy_context_ldt(struct mm_struct *mm) static int read_ldt(void __user *ptr, unsigned long bytecount) { - int retval; - unsigned long size; struct mm_struct *mm = current->mm; + unsigned long entries_size; + int retval; mutex_lock(&mm->context.lock); @@ -166,18 +167,18 @@ static int read_ldt(void __user *ptr, unsigned long bytecount) if (bytecount > LDT_ENTRY_SIZE * LDT_ENTRIES) bytecount = LDT_ENTRY_SIZE * LDT_ENTRIES; - size = mm->context.ldt->size * LDT_ENTRY_SIZE; - if (size > bytecount) - size = bytecount; + entries_size = mm->context.ldt->nr_entries * LDT_ENTRY_SIZE; + if (entries_size > bytecount) + entries_size = bytecount; - if (copy_to_user(ptr, mm->context.ldt->entries, size)) { + if (copy_to_user(ptr, mm->context.ldt->entries, entries_size)) { retval = -EFAULT; goto out_unlock; } - if (size != bytecount) { + if (entries_size != bytecount) { /* Zero-fill the rest and pretend we read bytecount bytes. */ - if (clear_user(ptr + size, bytecount - size)) { + if (clear_user(ptr + entries_size, bytecount - entries_size)) { retval = -EFAULT; goto out_unlock; } @@ -208,7 +209,7 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) { struct mm_struct *mm = current->mm; struct ldt_struct *new_ldt, *old_ldt; - unsigned int oldsize, newsize; + unsigned int old_nr_entries, new_nr_entries; struct user_desc ldt_info; struct desc_struct ldt; int error; @@ -247,17 +248,18 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) mutex_lock(&mm->context.lock); - old_ldt = mm->context.ldt; - oldsize = old_ldt ? old_ldt->size : 0; - newsize = max(ldt_info.entry_number + 1, oldsize); + old_ldt = mm->context.ldt; + old_nr_entries = old_ldt ? old_ldt->nr_entries : 0; + new_nr_entries = max(ldt_info.entry_number + 1, old_nr_entries); error = -ENOMEM; - new_ldt = alloc_ldt_struct(newsize); + new_ldt = alloc_ldt_struct(new_nr_entries); if (!new_ldt) goto out_unlock; if (old_ldt) - memcpy(new_ldt->entries, old_ldt->entries, oldsize * LDT_ENTRY_SIZE); + memcpy(new_ldt->entries, old_ldt->entries, old_nr_entries * LDT_ENTRY_SIZE); + new_ldt->entries[ldt_info.entry_number] = ldt; finalize_ldt_struct(new_ldt); diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 6f5ca4ebe6e5..cb0a30473c23 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -347,7 +347,7 @@ void machine_kexec(struct kimage *image) void arch_crash_save_vmcoreinfo(void) { VMCOREINFO_NUMBER(phys_base); - VMCOREINFO_SYMBOL(init_level4_pgt); + VMCOREINFO_SYMBOL(init_top_pgt); #ifdef CONFIG_NUMA VMCOREINFO_SYMBOL(node_data); diff --git a/arch/x86/kernel/nmi_selftest.c b/arch/x86/kernel/nmi_selftest.c index 6d9582ec0324..d27f8d84c4ff 100644 --- a/arch/x86/kernel/nmi_selftest.c +++ b/arch/x86/kernel/nmi_selftest.c @@ -78,7 +78,7 @@ static void __init test_nmi_ipi(struct cpumask *mask) /* Don't wait longer than a second */ timeout = USEC_PER_SEC; - while (!cpumask_empty(mask) && timeout--) + while (!cpumask_empty(mask) && --timeout) udelay(1); /* What happens if we timeout, do we still unregister?? */ diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 3586996fc50d..bc0a849589bb 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -391,7 +391,7 @@ struct pv_mmu_ops pv_mmu_ops __ro_after_init = { .read_cr2 = native_read_cr2, .write_cr2 = native_write_cr2, - .read_cr3 = native_read_cr3, + .read_cr3 = __native_read_cr3, .write_cr3 = native_write_cr3, .flush_tlb_user = native_flush_tlb, diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 0bb88428cbf2..3ca198080ea9 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -545,17 +545,6 @@ unsigned long arch_randomize_brk(struct mm_struct *mm) } /* - * Return saved PC of a blocked thread. - * What is this good for? it will be always the scheduler or ret_from_fork. - */ -unsigned long thread_saved_pc(struct task_struct *tsk) -{ - struct inactive_task_frame *frame = - (struct inactive_task_frame *) READ_ONCE(tsk->thread.sp); - return READ_ONCE_NOCHECK(frame->ret_addr); -} - -/* * Called from fs/proc with a reference on @p to find the function * which called into schedule(). This needs to be done carefully * because the task might wake up and we might look at a stack diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index ffeae818aa7a..c6d6dc5f8bb2 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -92,7 +92,7 @@ void __show_regs(struct pt_regs *regs, int all) cr0 = read_cr0(); cr2 = read_cr2(); - cr3 = read_cr3(); + cr3 = __read_cr3(); cr4 = __read_cr4(); printk(KERN_DEFAULT "CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n", cr0, cr2, cr3, cr4); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index b6840bf3940b..c3169be4c596 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -104,7 +104,7 @@ void __show_regs(struct pt_regs *regs, int all) cr0 = read_cr0(); cr2 = read_cr2(); - cr3 = read_cr3(); + cr3 = __read_cr3(); cr4 = __read_cr4(); printk(KERN_DEFAULT "FS: %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n", @@ -142,7 +142,7 @@ void release_thread(struct task_struct *dead_task) pr_warn("WARNING: dead process %s still has LDT? <%p/%d>\n", dead_task->comm, dead_task->mm->context.ldt->entries, - dead_task->mm->context.ldt->size); + dead_task->mm->context.ldt->nr_entries); BUG(); } #endif diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 2544700a2a87..67393fc88353 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -9,6 +9,7 @@ #include <linux/sched.h> #include <linux/tboot.h> #include <linux/delay.h> +#include <linux/frame.h> #include <acpi/reboot.h> #include <asm/io.h> #include <asm/apic.h> @@ -123,6 +124,7 @@ void __noreturn machine_real_restart(unsigned int type) #ifdef CONFIG_APM_MODULE EXPORT_SYMBOL(machine_real_restart); #endif +STACK_FRAME_NON_STANDARD(machine_real_restart); /* * Some Apple MacBook and MacBookPro's needs reboot=p to be able to reboot diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index f81823695014..65622f07e633 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -503,7 +503,7 @@ static int __init reserve_crashkernel_low(void) return 0; } - low_base = memblock_find_in_range(low_size, 1ULL << 32, low_size, CRASH_ALIGN); + low_base = memblock_find_in_range(0, 1ULL << 32, low_size, CRASH_ALIGN); if (!low_base) { pr_err("Cannot reserve %ldMB crashkernel low memory, please try smaller size.\n", (unsigned long)(low_size >> 20)); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index f04479a8f74f..b474c8de7fba 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -863,7 +863,7 @@ static void announce_cpu(int cpu, int apicid) if (cpu == 1) printk(KERN_INFO "x86: Booting SMP configuration:\n"); - if (system_state == SYSTEM_BOOTING) { + if (system_state < SYSTEM_RUNNING) { if (node != current_node) { if (current_node > (-1)) pr_cont("\n"); @@ -1589,7 +1589,6 @@ void native_cpu_die(unsigned int cpu) void play_dead_common(void) { idle_task_exit(); - reset_lazy_tlbstate(); /* Ack it */ (void)cpu_report_death(); diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index f07f83b3611b..5f25cfbd952e 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -34,7 +34,7 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re mutex_lock(&child->mm->context.lock); if (unlikely(!child->mm->context.ldt || - seg >= child->mm->context.ldt->size)) + seg >= child->mm->context.ldt->nr_entries)) addr = -1L; /* bogus selector, access would fault */ else { desc = &child->mm->context.ldt->entries[seg]; diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index 4b1724059909..a4eb27918ceb 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -514,7 +514,7 @@ int tboot_force_iommu(void) if (!tboot_enabled()) return 0; - if (!intel_iommu_tboot_noforce) + if (intel_iommu_tboot_noforce) return 1; if (no_iommu || swiotlb || dmar_disabled) diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 714dfba6a1e7..5270fc0c2df6 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -51,115 +51,34 @@ static u32 art_to_tsc_denominator; static u64 art_to_tsc_offset; struct clocksource *art_related_clocksource; -/* - * Use a ring-buffer like data structure, where a writer advances the head by - * writing a new data entry and a reader advances the tail when it observes a - * new entry. - * - * Writers are made to wait on readers until there's space to write a new - * entry. - * - * This means that we can always use an {offset, mul} pair to compute a ns - * value that is 'roughly' in the right direction, even if we're writing a new - * {offset, mul} pair during the clock read. - * - * The down-side is that we can no longer guarantee strict monotonicity anymore - * (assuming the TSC was that to begin with), because while we compute the - * intersection point of the two clock slopes and make sure the time is - * continuous at the point of switching; we can no longer guarantee a reader is - * strictly before or after the switch point. - * - * It does mean a reader no longer needs to disable IRQs in order to avoid - * CPU-Freq updates messing with his times, and similarly an NMI reader will - * no longer run the risk of hitting half-written state. - */ - struct cyc2ns { - struct cyc2ns_data data[2]; /* 0 + 2*24 = 48 */ - struct cyc2ns_data *head; /* 48 + 8 = 56 */ - struct cyc2ns_data *tail; /* 56 + 8 = 64 */ -}; /* exactly fits one cacheline */ - -static DEFINE_PER_CPU_ALIGNED(struct cyc2ns, cyc2ns); - -struct cyc2ns_data *cyc2ns_read_begin(void) -{ - struct cyc2ns_data *head; - - preempt_disable(); - - head = this_cpu_read(cyc2ns.head); - /* - * Ensure we observe the entry when we observe the pointer to it. - * matches the wmb from cyc2ns_write_end(). - */ - smp_read_barrier_depends(); - head->__count++; - barrier(); + struct cyc2ns_data data[2]; /* 0 + 2*16 = 32 */ + seqcount_t seq; /* 32 + 4 = 36 */ - return head; -} +}; /* fits one cacheline */ -void cyc2ns_read_end(struct cyc2ns_data *head) -{ - barrier(); - /* - * If we're the outer most nested read; update the tail pointer - * when we're done. This notifies possible pending writers - * that we've observed the head pointer and that the other - * entry is now free. - */ - if (!--head->__count) { - /* - * x86-TSO does not reorder writes with older reads; - * therefore once this write becomes visible to another - * cpu, we must be finished reading the cyc2ns_data. - * - * matches with cyc2ns_write_begin(). - */ - this_cpu_write(cyc2ns.tail, head); - } - preempt_enable(); -} +static DEFINE_PER_CPU_ALIGNED(struct cyc2ns, cyc2ns); -/* - * Begin writing a new @data entry for @cpu. - * - * Assumes some sort of write side lock; currently 'provided' by the assumption - * that cpufreq will call its notifiers sequentially. - */ -static struct cyc2ns_data *cyc2ns_write_begin(int cpu) +void cyc2ns_read_begin(struct cyc2ns_data *data) { - struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu); - struct cyc2ns_data *data = c2n->data; + int seq, idx; - if (data == c2n->head) - data++; + preempt_disable_notrace(); - /* XXX send an IPI to @cpu in order to guarantee a read? */ + do { + seq = this_cpu_read(cyc2ns.seq.sequence); + idx = seq & 1; - /* - * When we observe the tail write from cyc2ns_read_end(), - * the cpu must be done with that entry and its safe - * to start writing to it. - */ - while (c2n->tail == data) - cpu_relax(); + data->cyc2ns_offset = this_cpu_read(cyc2ns.data[idx].cyc2ns_offset); + data->cyc2ns_mul = this_cpu_read(cyc2ns.data[idx].cyc2ns_mul); + data->cyc2ns_shift = this_cpu_read(cyc2ns.data[idx].cyc2ns_shift); - return data; + } while (unlikely(seq != this_cpu_read(cyc2ns.seq.sequence))); } -static void cyc2ns_write_end(int cpu, struct cyc2ns_data *data) +void cyc2ns_read_end(void) { - struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu); - - /* - * Ensure the @data writes are visible before we publish the - * entry. Matches the data-depencency in cyc2ns_read_begin(). - */ - smp_wmb(); - - ACCESS_ONCE(c2n->head) = data; + preempt_enable_notrace(); } /* @@ -191,7 +110,6 @@ static void cyc2ns_data_init(struct cyc2ns_data *data) data->cyc2ns_mul = 0; data->cyc2ns_shift = 0; data->cyc2ns_offset = 0; - data->__count = 0; } static void cyc2ns_init(int cpu) @@ -201,51 +119,29 @@ static void cyc2ns_init(int cpu) cyc2ns_data_init(&c2n->data[0]); cyc2ns_data_init(&c2n->data[1]); - c2n->head = c2n->data; - c2n->tail = c2n->data; + seqcount_init(&c2n->seq); } static inline unsigned long long cycles_2_ns(unsigned long long cyc) { - struct cyc2ns_data *data, *tail; + struct cyc2ns_data data; unsigned long long ns; - /* - * See cyc2ns_read_*() for details; replicated in order to avoid - * an extra few instructions that came with the abstraction. - * Notable, it allows us to only do the __count and tail update - * dance when its actually needed. - */ - - preempt_disable_notrace(); - data = this_cpu_read(cyc2ns.head); - tail = this_cpu_read(cyc2ns.tail); - - if (likely(data == tail)) { - ns = data->cyc2ns_offset; - ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, data->cyc2ns_shift); - } else { - data->__count++; - - barrier(); - - ns = data->cyc2ns_offset; - ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, data->cyc2ns_shift); + cyc2ns_read_begin(&data); - barrier(); + ns = data.cyc2ns_offset; + ns += mul_u64_u32_shr(cyc, data.cyc2ns_mul, data.cyc2ns_shift); - if (!--data->__count) - this_cpu_write(cyc2ns.tail, data); - } - preempt_enable_notrace(); + cyc2ns_read_end(); return ns; } -static void set_cyc2ns_scale(unsigned long khz, int cpu) +static void set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_now) { - unsigned long long tsc_now, ns_now; - struct cyc2ns_data *data; + unsigned long long ns_now; + struct cyc2ns_data data; + struct cyc2ns *c2n; unsigned long flags; local_irq_save(flags); @@ -254,9 +150,6 @@ static void set_cyc2ns_scale(unsigned long khz, int cpu) if (!khz) goto done; - data = cyc2ns_write_begin(cpu); - - tsc_now = rdtsc(); ns_now = cycles_2_ns(tsc_now); /* @@ -264,7 +157,7 @@ static void set_cyc2ns_scale(unsigned long khz, int cpu) * time function is continuous; see the comment near struct * cyc2ns_data. */ - clocks_calc_mult_shift(&data->cyc2ns_mul, &data->cyc2ns_shift, khz, + clocks_calc_mult_shift(&data.cyc2ns_mul, &data.cyc2ns_shift, khz, NSEC_PER_MSEC, 0); /* @@ -273,20 +166,26 @@ static void set_cyc2ns_scale(unsigned long khz, int cpu) * conversion algorithm shifting a 32-bit value (now specifies a 64-bit * value) - refer perf_event_mmap_page documentation in perf_event.h. */ - if (data->cyc2ns_shift == 32) { - data->cyc2ns_shift = 31; - data->cyc2ns_mul >>= 1; + if (data.cyc2ns_shift == 32) { + data.cyc2ns_shift = 31; + data.cyc2ns_mul >>= 1; } - data->cyc2ns_offset = ns_now - - mul_u64_u32_shr(tsc_now, data->cyc2ns_mul, data->cyc2ns_shift); + data.cyc2ns_offset = ns_now - + mul_u64_u32_shr(tsc_now, data.cyc2ns_mul, data.cyc2ns_shift); + + c2n = per_cpu_ptr(&cyc2ns, cpu); - cyc2ns_write_end(cpu, data); + raw_write_seqcount_latch(&c2n->seq); + c2n->data[0] = data; + raw_write_seqcount_latch(&c2n->seq); + c2n->data[1] = data; done: - sched_clock_idle_wakeup_event(0); + sched_clock_idle_wakeup_event(); local_irq_restore(flags); } + /* * Scheduler clock - returns current time in nanosec units. */ @@ -374,6 +273,8 @@ static int __init tsc_setup(char *str) tsc_clocksource_reliable = 1; if (!strncmp(str, "noirqtime", 9)) no_sched_irq_time = 1; + if (!strcmp(str, "unstable")) + mark_tsc_unstable("boot parameter"); return 1; } @@ -986,7 +887,6 @@ void tsc_restore_sched_clock_state(void) } #ifdef CONFIG_CPU_FREQ - /* Frequency scaling support. Adjust the TSC based timer when the cpu frequency * changes. * @@ -1027,7 +927,7 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val, if (!(freq->flags & CPUFREQ_CONST_LOOPS)) mark_tsc_unstable("cpufreq changes"); - set_cyc2ns_scale(tsc_khz, freq->cpu); + set_cyc2ns_scale(tsc_khz, freq->cpu, rdtsc()); } return 0; @@ -1127,6 +1027,15 @@ static void tsc_cs_mark_unstable(struct clocksource *cs) pr_info("Marking TSC unstable due to clocksource watchdog\n"); } +static void tsc_cs_tick_stable(struct clocksource *cs) +{ + if (tsc_unstable) + return; + + if (using_native_sched_clock()) + sched_clock_tick_stable(); +} + /* * .mask MUST be CLOCKSOURCE_MASK(64). See comment above read_tsc() */ @@ -1140,6 +1049,7 @@ static struct clocksource clocksource_tsc = { .archdata = { .vclock_mode = VCLOCK_TSC }, .resume = tsc_resume, .mark_unstable = tsc_cs_mark_unstable, + .tick_stable = tsc_cs_tick_stable, }; void mark_tsc_unstable(char *reason) @@ -1255,6 +1165,7 @@ static void tsc_refine_calibration_work(struct work_struct *work) static int hpet; u64 tsc_stop, ref_stop, delta; unsigned long freq; + int cpu; /* Don't bother refining TSC on unstable systems */ if (check_tsc_unstable()) @@ -1305,6 +1216,10 @@ static void tsc_refine_calibration_work(struct work_struct *work) /* Inform the TSC deadline clockevent devices about the recalibration */ lapic_update_tsc_freq(); + /* Update the sched_clock() rate to match the clocksource one */ + for_each_possible_cpu(cpu) + set_cyc2ns_scale(tsc_khz, cpu, tsc_stop); + out: if (boot_cpu_has(X86_FEATURE_ART)) art_related_clocksource = &clocksource_tsc; @@ -1350,7 +1265,7 @@ device_initcall(init_tsc_clocksource); void __init tsc_init(void) { - u64 lpj; + u64 lpj, cyc; int cpu; if (!boot_cpu_has(X86_FEATURE_TSC)) { @@ -1390,9 +1305,10 @@ void __init tsc_init(void) * speed as the bootup CPU. (cpufreq notifiers will fix this * up if their speed diverges) */ + cyc = rdtsc(); for_each_possible_cpu(cpu) { cyc2ns_init(cpu); - set_cyc2ns_scale(tsc_khz, cpu); + set_cyc2ns_scale(tsc_khz, cpu, cyc); } if (tsc_disabled > 0) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 0816ab2e8adc..80890dee66ce 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -2742,6 +2742,7 @@ static int em_syscall(struct x86_emulate_ctxt *ctxt) ctxt->eflags &= ~(X86_EFLAGS_VM | X86_EFLAGS_IF); } + ctxt->tf = (ctxt->eflags & X86_EFLAGS_TF) != 0; return X86EMUL_CONTINUE; } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index ba9891ac5c56..33460fcdeef9 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -36,6 +36,7 @@ #include <linux/slab.h> #include <linux/amd-iommu.h> #include <linux/hashtable.h> +#include <linux/frame.h> #include <asm/apic.h> #include <asm/perf_event.h> @@ -4906,6 +4907,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) mark_all_clean(svm->vmcb); } +STACK_FRAME_NON_STANDARD(svm_vcpu_run); static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root) { diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index ca5d2b93385c..6dcc4873e435 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -33,6 +33,7 @@ #include <linux/slab.h> #include <linux/tboot.h> #include <linux/hrtimer.h> +#include <linux/frame.h> #include "kvm_cache_regs.h" #include "x86.h" @@ -48,6 +49,7 @@ #include <asm/kexec.h> #include <asm/apic.h> #include <asm/irq_remapping.h> +#include <asm/mmu_context.h> #include "trace.h" #include "pmu.h" @@ -596,6 +598,7 @@ struct vcpu_vmx { int gs_ldt_reload_needed; int fs_reload_needed; u64 msr_host_bndcfgs; + unsigned long vmcs_host_cr3; /* May not match real cr3 */ unsigned long vmcs_host_cr4; /* May not match real cr4 */ } host_state; struct { @@ -5012,12 +5015,19 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx) u32 low32, high32; unsigned long tmpl; struct desc_ptr dt; - unsigned long cr0, cr4; + unsigned long cr0, cr3, cr4; cr0 = read_cr0(); WARN_ON(cr0 & X86_CR0_TS); vmcs_writel(HOST_CR0, cr0); /* 22.2.3 */ - vmcs_writel(HOST_CR3, read_cr3()); /* 22.2.3 FIXME: shadow tables */ + + /* + * Save the most likely value for this task's CR3 in the VMCS. + * We can't use __get_current_cr3_fast() because we're not atomic. + */ + cr3 = __read_cr3(); + vmcs_writel(HOST_CR3, cr3); /* 22.2.3 FIXME: shadow tables */ + vmx->host_state.vmcs_host_cr3 = cr3; /* Save the most likely value for this task's CR4 in the VMCS. */ cr4 = cr4_read_shadow(); @@ -8652,6 +8662,7 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) ); } } +STACK_FRAME_NON_STANDARD(vmx_handle_external_intr); static bool vmx_has_high_real_mode_segbase(void) { @@ -8820,7 +8831,7 @@ static void vmx_arm_hv_timer(struct kvm_vcpu *vcpu) static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long debugctlmsr, cr4; + unsigned long debugctlmsr, cr3, cr4; /* Don't enter VMX if guest state is invalid, let the exit handler start emulation until we arrive back to a valid state */ @@ -8842,6 +8853,12 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty)) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); + cr3 = __get_current_cr3_fast(); + if (unlikely(cr3 != vmx->host_state.vmcs_host_cr3)) { + vmcs_writel(HOST_CR3, cr3); + vmx->host_state.vmcs_host_cr3 = cr3; + } + cr4 = cr4_read_shadow(); if (unlikely(cr4 != vmx->host_state.vmcs_host_cr4)) { vmcs_writel(HOST_CR4, cr4); @@ -9028,6 +9045,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx_recover_nmi_blocking(vmx); vmx_complete_interrupts(vmx); } +STACK_FRAME_NON_STANDARD(vmx_vcpu_run); static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs) { diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 87d3cb901935..0e846f0cb83b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5313,6 +5313,8 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); ctxt->eflags = kvm_get_rflags(vcpu); + ctxt->tf = (ctxt->eflags & X86_EFLAGS_TF) != 0; + ctxt->eip = kvm_rip_read(vcpu); ctxt->mode = (!is_protmode(vcpu)) ? X86EMUL_MODE_REAL : (ctxt->eflags & X86_EFLAGS_VM) ? X86EMUL_MODE_VM86 : @@ -5528,36 +5530,25 @@ static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7, return dr6; } -static void kvm_vcpu_check_singlestep(struct kvm_vcpu *vcpu, unsigned long rflags, int *r) +static void kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu, int *r) { struct kvm_run *kvm_run = vcpu->run; - /* - * rflags is the old, "raw" value of the flags. The new value has - * not been saved yet. - * - * This is correct even for TF set by the guest, because "the - * processor will not generate this exception after the instruction - * that sets the TF flag". - */ - if (unlikely(rflags & X86_EFLAGS_TF)) { - if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { - kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1 | - DR6_RTM; - kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip; - kvm_run->debug.arch.exception = DB_VECTOR; - kvm_run->exit_reason = KVM_EXIT_DEBUG; - *r = EMULATE_USER_EXIT; - } else { - /* - * "Certain debug exceptions may clear bit 0-3. The - * remaining contents of the DR6 register are never - * cleared by the processor". - */ - vcpu->arch.dr6 &= ~15; - vcpu->arch.dr6 |= DR6_BS | DR6_RTM; - kvm_queue_exception(vcpu, DB_VECTOR); - } + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { + kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1 | DR6_RTM; + kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip; + kvm_run->debug.arch.exception = DB_VECTOR; + kvm_run->exit_reason = KVM_EXIT_DEBUG; + *r = EMULATE_USER_EXIT; + } else { + /* + * "Certain debug exceptions may clear bit 0-3. The + * remaining contents of the DR6 register are never + * cleared by the processor". + */ + vcpu->arch.dr6 &= ~15; + vcpu->arch.dr6 |= DR6_BS | DR6_RTM; + kvm_queue_exception(vcpu, DB_VECTOR); } } @@ -5567,7 +5558,17 @@ int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu) int r = EMULATE_DONE; kvm_x86_ops->skip_emulated_instruction(vcpu); - kvm_vcpu_check_singlestep(vcpu, rflags, &r); + + /* + * rflags is the old, "raw" value of the flags. The new value has + * not been saved yet. + * + * This is correct even for TF set by the guest, because "the + * processor will not generate this exception after the instruction + * that sets the TF flag". + */ + if (unlikely(rflags & X86_EFLAGS_TF)) + kvm_vcpu_do_singlestep(vcpu, &r); return r == EMULATE_DONE; } EXPORT_SYMBOL_GPL(kvm_skip_emulated_instruction); @@ -5726,8 +5727,9 @@ restart: toggle_interruptibility(vcpu, ctxt->interruptibility); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; kvm_rip_write(vcpu, ctxt->eip); - if (r == EMULATE_DONE) - kvm_vcpu_check_singlestep(vcpu, rflags, &r); + if (r == EMULATE_DONE && + (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP))) + kvm_vcpu_do_singlestep(vcpu, &r); if (!ctxt->have_exception || exception_type(ctxt->exception.vector) == EXCPT_TRAP) __kvm_set_rflags(vcpu, ctxt->eflags); diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index c5959576c315..020f75cc8cf6 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -37,7 +37,7 @@ ENTRY(copy_user_generic_unrolled) movl %edx,%ecx andl $63,%edx shrl $6,%ecx - jz 17f + jz .L_copy_short_string 1: movq (%rsi),%r8 2: movq 1*8(%rsi),%r9 3: movq 2*8(%rsi),%r10 @@ -58,7 +58,8 @@ ENTRY(copy_user_generic_unrolled) leaq 64(%rdi),%rdi decl %ecx jnz 1b -17: movl %edx,%ecx +.L_copy_short_string: + movl %edx,%ecx andl $7,%edx shrl $3,%ecx jz 20f @@ -174,6 +175,8 @@ EXPORT_SYMBOL(copy_user_generic_string) */ ENTRY(copy_user_enhanced_fast_string) ASM_STAC + cmpl $64,%edx + jb .L_copy_short_string /* less then 64 bytes, avoid the costly 'rep' */ movl %edx,%ecx 1: rep movsb diff --git a/arch/x86/lib/msr-reg.S b/arch/x86/lib/msr-reg.S index c81556409bbb..10ffa7e8519f 100644 --- a/arch/x86/lib/msr-reg.S +++ b/arch/x86/lib/msr-reg.S @@ -13,14 +13,14 @@ .macro op_safe_regs op ENTRY(\op\()_safe_regs) pushq %rbx - pushq %rbp + pushq %r12 movq %rdi, %r10 /* Save pointer */ xorl %r11d, %r11d /* Return value */ movl (%rdi), %eax movl 4(%rdi), %ecx movl 8(%rdi), %edx movl 12(%rdi), %ebx - movl 20(%rdi), %ebp + movl 20(%rdi), %r12d movl 24(%rdi), %esi movl 28(%rdi), %edi 1: \op @@ -29,10 +29,10 @@ ENTRY(\op\()_safe_regs) movl %ecx, 4(%r10) movl %edx, 8(%r10) movl %ebx, 12(%r10) - movl %ebp, 20(%r10) + movl %r12d, 20(%r10) movl %esi, 24(%r10) movl %edi, 28(%r10) - popq %rbp + popq %r12 popq %rbx ret 3: diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt index 767be7c76034..12e377184ee4 100644 --- a/arch/x86/lib/x86-opcode-map.txt +++ b/arch/x86/lib/x86-opcode-map.txt @@ -1009,7 +1009,7 @@ GrpTable: Grp15 1: fxstor | RDGSBASE Ry (F3),(11B) 2: vldmxcsr Md (v1) | WRFSBASE Ry (F3),(11B) 3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B) -4: XSAVE +4: XSAVE | ptwrite Ey (F3),(11B) 5: XRSTOR | lfence (11B) 6: XSAVEOPT | clwb (66) | mfence (11B) 7: clflush | clflushopt (66) | sfence (11B) diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h index 5e044d506b7a..a179254a5122 100644 --- a/arch/x86/math-emu/fpu_system.h +++ b/arch/x86/math-emu/fpu_system.h @@ -27,7 +27,7 @@ static inline struct desc_struct FPU_get_ldt_descriptor(unsigned seg) #ifdef CONFIG_MODIFY_LDT_SYSCALL seg >>= 3; mutex_lock(¤t->mm->context.lock); - if (current->mm->context.ldt && seg < current->mm->context.ldt->size) + if (current->mm->context.ldt && seg < current->mm->context.ldt->nr_entries) ret = current->mm->context.ldt->entries[seg]; mutex_unlock(¤t->mm->context.lock); #endif diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 96d2b847e09e..0fbdcb64f9f8 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -2,7 +2,7 @@ KCOV_INSTRUMENT_tlb.o := n obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ - pat.o pgtable.o physaddr.o gup.o setup_nx.o tlb.o + pat.o pgtable.o physaddr.o setup_nx.o tlb.o # Make sure __phys_addr has no stackprotector nostackp := $(call cc-option, -fno-stack-protector) diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index bce6990b1d81..0470826d2bdc 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -431,7 +431,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd, bool checkwx) { #ifdef CONFIG_X86_64 - pgd_t *start = (pgd_t *) &init_level4_pgt; + pgd_t *start = (pgd_t *) &init_top_pgt; #else pgd_t *start = swapper_pg_dir; #endif diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 8ad91a01cbc8..2a1fa10c6a98 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -346,7 +346,7 @@ static noinline int vmalloc_fault(unsigned long address) * Do _not_ use "current" here. We might be inside * an interrupt in the middle of a task switch.. */ - pgd_paddr = read_cr3(); + pgd_paddr = read_cr3_pa(); pmd_k = vmalloc_sync_one(__va(pgd_paddr), address); if (!pmd_k) return -1; @@ -388,7 +388,7 @@ static bool low_pfn(unsigned long pfn) static void dump_pagetable(unsigned long address) { - pgd_t *base = __va(read_cr3()); + pgd_t *base = __va(read_cr3_pa()); pgd_t *pgd = &base[pgd_index(address)]; p4d_t *p4d; pud_t *pud; @@ -451,7 +451,7 @@ static noinline int vmalloc_fault(unsigned long address) * happen within a race in page table update. In the later * case just flush: */ - pgd = (pgd_t *)__va(read_cr3()) + pgd_index(address); + pgd = (pgd_t *)__va(read_cr3_pa()) + pgd_index(address); pgd_ref = pgd_offset_k(address); if (pgd_none(*pgd_ref)) return -1; @@ -555,7 +555,7 @@ static int bad_address(void *p) static void dump_pagetable(unsigned long address) { - pgd_t *base = __va(read_cr3() & PHYSICAL_PAGE_MASK); + pgd_t *base = __va(read_cr3_pa()); pgd_t *pgd = base + pgd_index(address); p4d_t *p4d; pud_t *pud; @@ -700,7 +700,7 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, pgd_t *pgd; pte_t *pte; - pgd = __va(read_cr3() & PHYSICAL_PAGE_MASK); + pgd = __va(read_cr3_pa()); pgd += pgd_index(address); pte = lookup_address_in_pgd(pgd, address, &level); diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c deleted file mode 100644 index 456dfdfd2249..000000000000 --- a/arch/x86/mm/gup.c +++ /dev/null @@ -1,496 +0,0 @@ -/* - * Lockless get_user_pages_fast for x86 - * - * Copyright (C) 2008 Nick Piggin - * Copyright (C) 2008 Novell Inc. - */ -#include <linux/sched.h> -#include <linux/mm.h> -#include <linux/vmstat.h> -#include <linux/highmem.h> -#include <linux/swap.h> -#include <linux/memremap.h> - -#include <asm/mmu_context.h> -#include <asm/pgtable.h> - -static inline pte_t gup_get_pte(pte_t *ptep) -{ -#ifndef CONFIG_X86_PAE - return READ_ONCE(*ptep); -#else - /* - * With get_user_pages_fast, we walk down the pagetables without taking - * any locks. For this we would like to load the pointers atomically, - * but that is not possible (without expensive cmpxchg8b) on PAE. What - * we do have is the guarantee that a pte will only either go from not - * present to present, or present to not present or both -- it will not - * switch to a completely different present page without a TLB flush in - * between; something that we are blocking by holding interrupts off. - * - * Setting ptes from not present to present goes: - * ptep->pte_high = h; - * smp_wmb(); - * ptep->pte_low = l; - * - * And present to not present goes: - * ptep->pte_low = 0; - * smp_wmb(); - * ptep->pte_high = 0; - * - * We must ensure here that the load of pte_low sees l iff pte_high - * sees h. We load pte_high *after* loading pte_low, which ensures we - * don't see an older value of pte_high. *Then* we recheck pte_low, - * which ensures that we haven't picked up a changed pte high. We might - * have got rubbish values from pte_low and pte_high, but we are - * guaranteed that pte_low will not have the present bit set *unless* - * it is 'l'. And get_user_pages_fast only operates on present ptes, so - * we're safe. - * - * gup_get_pte should not be used or copied outside gup.c without being - * very careful -- it does not atomically load the pte or anything that - * is likely to be useful for you. - */ - pte_t pte; - -retry: - pte.pte_low = ptep->pte_low; - smp_rmb(); - pte.pte_high = ptep->pte_high; - smp_rmb(); - if (unlikely(pte.pte_low != ptep->pte_low)) - goto retry; - - return pte; -#endif -} - -static void undo_dev_pagemap(int *nr, int nr_start, struct page **pages) -{ - while ((*nr) - nr_start) { - struct page *page = pages[--(*nr)]; - - ClearPageReferenced(page); - put_page(page); - } -} - -/* - * 'pteval' can come from a pte, pmd, pud or p4d. We only check - * _PAGE_PRESENT, _PAGE_USER, and _PAGE_RW in here which are the - * same value on all 4 types. - */ -static inline int pte_allows_gup(unsigned long pteval, int write) -{ - unsigned long need_pte_bits = _PAGE_PRESENT|_PAGE_USER; - - if (write) - need_pte_bits |= _PAGE_RW; - - if ((pteval & need_pte_bits) != need_pte_bits) - return 0; - - /* Check memory protection keys permissions. */ - if (!__pkru_allows_pkey(pte_flags_pkey(pteval), write)) - return 0; - - return 1; -} - -/* - * The performance critical leaf functions are made noinline otherwise gcc - * inlines everything into a single function which results in too much - * register pressure. - */ -static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, - unsigned long end, int write, struct page **pages, int *nr) -{ - struct dev_pagemap *pgmap = NULL; - int nr_start = *nr, ret = 0; - pte_t *ptep, *ptem; - - /* - * Keep the original mapped PTE value (ptem) around since we - * might increment ptep off the end of the page when finishing - * our loop iteration. - */ - ptem = ptep = pte_offset_map(&pmd, addr); - do { - pte_t pte = gup_get_pte(ptep); - struct page *page; - - /* Similar to the PMD case, NUMA hinting must take slow path */ - if (pte_protnone(pte)) - break; - - if (!pte_allows_gup(pte_val(pte), write)) - break; - - if (pte_devmap(pte)) { - pgmap = get_dev_pagemap(pte_pfn(pte), pgmap); - if (unlikely(!pgmap)) { - undo_dev_pagemap(nr, nr_start, pages); - break; - } - } else if (pte_special(pte)) - break; - - VM_BUG_ON(!pfn_valid(pte_pfn(pte))); - page = pte_page(pte); - get_page(page); - put_dev_pagemap(pgmap); - SetPageReferenced(page); - pages[*nr] = page; - (*nr)++; - - } while (ptep++, addr += PAGE_SIZE, addr != end); - if (addr == end) - ret = 1; - pte_unmap(ptem); - - return ret; -} - -static inline void get_head_page_multiple(struct page *page, int nr) -{ - VM_BUG_ON_PAGE(page != compound_head(page), page); - VM_BUG_ON_PAGE(page_count(page) == 0, page); - page_ref_add(page, nr); - SetPageReferenced(page); -} - -static int __gup_device_huge(unsigned long pfn, unsigned long addr, - unsigned long end, struct page **pages, int *nr) -{ - int nr_start = *nr; - struct dev_pagemap *pgmap = NULL; - - do { - struct page *page = pfn_to_page(pfn); - - pgmap = get_dev_pagemap(pfn, pgmap); - if (unlikely(!pgmap)) { - undo_dev_pagemap(nr, nr_start, pages); - return 0; - } - SetPageReferenced(page); - pages[*nr] = page; - get_page(page); - put_dev_pagemap(pgmap); - (*nr)++; - pfn++; - } while (addr += PAGE_SIZE, addr != end); - return 1; -} - -static int __gup_device_huge_pmd(pmd_t pmd, unsigned long addr, - unsigned long end, struct page **pages, int *nr) -{ - unsigned long fault_pfn; - - fault_pfn = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); - return __gup_device_huge(fault_pfn, addr, end, pages, nr); -} - -static int __gup_device_huge_pud(pud_t pud, unsigned long addr, - unsigned long end, struct page **pages, int *nr) -{ - unsigned long fault_pfn; - - fault_pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); - return __gup_device_huge(fault_pfn, addr, end, pages, nr); -} - -static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr, - unsigned long end, int write, struct page **pages, int *nr) -{ - struct page *head, *page; - int refs; - - if (!pte_allows_gup(pmd_val(pmd), write)) - return 0; - - VM_BUG_ON(!pfn_valid(pmd_pfn(pmd))); - if (pmd_devmap(pmd)) - return __gup_device_huge_pmd(pmd, addr, end, pages, nr); - - /* hugepages are never "special" */ - VM_BUG_ON(pmd_flags(pmd) & _PAGE_SPECIAL); - - refs = 0; - head = pmd_page(pmd); - page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); - do { - VM_BUG_ON_PAGE(compound_head(page) != head, page); - pages[*nr] = page; - (*nr)++; - page++; - refs++; - } while (addr += PAGE_SIZE, addr != end); - get_head_page_multiple(head, refs); - - return 1; -} - -static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) -{ - unsigned long next; - pmd_t *pmdp; - - pmdp = pmd_offset(&pud, addr); - do { - pmd_t pmd = *pmdp; - - next = pmd_addr_end(addr, end); - if (pmd_none(pmd)) - return 0; - if (unlikely(pmd_large(pmd) || !pmd_present(pmd))) { - /* - * NUMA hinting faults need to be handled in the GUP - * slowpath for accounting purposes and so that they - * can be serialised against THP migration. - */ - if (pmd_protnone(pmd)) - return 0; - if (!gup_huge_pmd(pmd, addr, next, write, pages, nr)) - return 0; - } else { - if (!gup_pte_range(pmd, addr, next, write, pages, nr)) - return 0; - } - } while (pmdp++, addr = next, addr != end); - - return 1; -} - -static noinline int gup_huge_pud(pud_t pud, unsigned long addr, - unsigned long end, int write, struct page **pages, int *nr) -{ - struct page *head, *page; - int refs; - - if (!pte_allows_gup(pud_val(pud), write)) - return 0; - - VM_BUG_ON(!pfn_valid(pud_pfn(pud))); - if (pud_devmap(pud)) - return __gup_device_huge_pud(pud, addr, end, pages, nr); - - /* hugepages are never "special" */ - VM_BUG_ON(pud_flags(pud) & _PAGE_SPECIAL); - - refs = 0; - head = pud_page(pud); - page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT); - do { - VM_BUG_ON_PAGE(compound_head(page) != head, page); - pages[*nr] = page; - (*nr)++; - page++; - refs++; - } while (addr += PAGE_SIZE, addr != end); - get_head_page_multiple(head, refs); - - return 1; -} - -static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) -{ - unsigned long next; - pud_t *pudp; - - pudp = pud_offset(&p4d, addr); - do { - pud_t pud = *pudp; - - next = pud_addr_end(addr, end); - if (pud_none(pud)) - return 0; - if (unlikely(pud_large(pud))) { - if (!gup_huge_pud(pud, addr, next, write, pages, nr)) - return 0; - } else { - if (!gup_pmd_range(pud, addr, next, write, pages, nr)) - return 0; - } - } while (pudp++, addr = next, addr != end); - - return 1; -} - -static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) -{ - unsigned long next; - p4d_t *p4dp; - - p4dp = p4d_offset(&pgd, addr); - do { - p4d_t p4d = *p4dp; - - next = p4d_addr_end(addr, end); - if (p4d_none(p4d)) - return 0; - BUILD_BUG_ON(p4d_large(p4d)); - if (!gup_pud_range(p4d, addr, next, write, pages, nr)) - return 0; - } while (p4dp++, addr = next, addr != end); - - return 1; -} - -/* - * Like get_user_pages_fast() except its IRQ-safe in that it won't fall - * back to the regular GUP. - */ -int __get_user_pages_fast(unsigned long start, int nr_pages, int write, - struct page **pages) -{ - struct mm_struct *mm = current->mm; - unsigned long addr, len, end; - unsigned long next; - unsigned long flags; - pgd_t *pgdp; - int nr = 0; - - start &= PAGE_MASK; - addr = start; - len = (unsigned long) nr_pages << PAGE_SHIFT; - end = start + len; - if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ, - (void __user *)start, len))) - return 0; - - /* - * XXX: batch / limit 'nr', to avoid large irq off latency - * needs some instrumenting to determine the common sizes used by - * important workloads (eg. DB2), and whether limiting the batch size - * will decrease performance. - * - * It seems like we're in the clear for the moment. Direct-IO is - * the main guy that batches up lots of get_user_pages, and even - * they are limited to 64-at-a-time which is not so many. - */ - /* - * This doesn't prevent pagetable teardown, but does prevent - * the pagetables and pages from being freed on x86. - * - * So long as we atomically load page table pointers versus teardown - * (which we do on x86, with the above PAE exception), we can follow the - * address down to the the page and take a ref on it. - */ - local_irq_save(flags); - pgdp = pgd_offset(mm, addr); - do { - pgd_t pgd = *pgdp; - - next = pgd_addr_end(addr, end); - if (pgd_none(pgd)) - break; - if (!gup_p4d_range(pgd, addr, next, write, pages, &nr)) - break; - } while (pgdp++, addr = next, addr != end); - local_irq_restore(flags); - - return nr; -} - -/** - * get_user_pages_fast() - pin user pages in memory - * @start: starting user address - * @nr_pages: number of pages from start to pin - * @write: whether pages will be written to - * @pages: array that receives pointers to the pages pinned. - * Should be at least nr_pages long. - * - * Attempt to pin user pages in memory without taking mm->mmap_sem. - * If not successful, it will fall back to taking the lock and - * calling get_user_pages(). - * - * Returns number of pages pinned. This may be fewer than the number - * requested. If nr_pages is 0 or negative, returns 0. If no pages - * were pinned, returns -errno. - */ -int get_user_pages_fast(unsigned long start, int nr_pages, int write, - struct page **pages) -{ - struct mm_struct *mm = current->mm; - unsigned long addr, len, end; - unsigned long next; - pgd_t *pgdp; - int nr = 0; - - start &= PAGE_MASK; - addr = start; - len = (unsigned long) nr_pages << PAGE_SHIFT; - - end = start + len; - if (end < start) - goto slow_irqon; - -#ifdef CONFIG_X86_64 - if (end >> __VIRTUAL_MASK_SHIFT) - goto slow_irqon; -#endif - - /* - * XXX: batch / limit 'nr', to avoid large irq off latency - * needs some instrumenting to determine the common sizes used by - * important workloads (eg. DB2), and whether limiting the batch size - * will decrease performance. - * - * It seems like we're in the clear for the moment. Direct-IO is - * the main guy that batches up lots of get_user_pages, and even - * they are limited to 64-at-a-time which is not so many. - */ - /* - * This doesn't prevent pagetable teardown, but does prevent - * the pagetables and pages from being freed on x86. - * - * So long as we atomically load page table pointers versus teardown - * (which we do on x86, with the above PAE exception), we can follow the - * address down to the the page and take a ref on it. - */ - local_irq_disable(); - pgdp = pgd_offset(mm, addr); - do { - pgd_t pgd = *pgdp; - - next = pgd_addr_end(addr, end); - if (pgd_none(pgd)) - goto slow; - if (!gup_p4d_range(pgd, addr, next, write, pages, &nr)) - goto slow; - } while (pgdp++, addr = next, addr != end); - local_irq_enable(); - - VM_BUG_ON(nr != (end - start) >> PAGE_SHIFT); - return nr; - - { - int ret; - -slow: - local_irq_enable(); -slow_irqon: - /* Try to get the remaining pages with get_user_pages */ - start += nr << PAGE_SHIFT; - pages += nr; - - ret = get_user_pages_unlocked(start, - (end - start) >> PAGE_SHIFT, - pages, write ? FOLL_WRITE : 0); - - /* Have to be a bit careful with return values */ - if (nr > 0) { - if (ret < 0) - ret = nr; - else - ret += nr; - } - - return ret; - } -} diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 9b3f9fa5b283..673541eb3b3f 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -811,10 +811,8 @@ void __init zone_sizes_init(void) } DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = { -#ifdef CONFIG_SMP - .active_mm = &init_mm, + .loaded_mm = &init_mm, .state = 0, -#endif .cr4 = ~0UL, /* fail hard if we screw up cr4 shadow initialization */ }; EXPORT_SYMBOL_GPL(cpu_tlbstate); diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 95651dc58e09..dae6a5e5ad4a 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -92,6 +92,44 @@ __setup("noexec32=", nonx32_setup); * When memory was added make sure all the processes MM have * suitable PGD entries in the local PGD level page. */ +#ifdef CONFIG_X86_5LEVEL +void sync_global_pgds(unsigned long start, unsigned long end) +{ + unsigned long addr; + + for (addr = start; addr <= end; addr = ALIGN(addr + 1, PGDIR_SIZE)) { + const pgd_t *pgd_ref = pgd_offset_k(addr); + struct page *page; + + /* Check for overflow */ + if (addr < start) + break; + + if (pgd_none(*pgd_ref)) + continue; + + spin_lock(&pgd_lock); + list_for_each_entry(page, &pgd_list, lru) { + pgd_t *pgd; + spinlock_t *pgt_lock; + + pgd = (pgd_t *)page_address(page) + pgd_index(addr); + /* the pgt_lock only for Xen */ + pgt_lock = &pgd_page_get_mm(page)->page_table_lock; + spin_lock(pgt_lock); + + if (!pgd_none(*pgd_ref) && !pgd_none(*pgd)) + BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref)); + + if (pgd_none(*pgd)) + set_pgd(pgd, *pgd_ref); + + spin_unlock(pgt_lock); + } + spin_unlock(&pgd_lock); + } +} +#else void sync_global_pgds(unsigned long start, unsigned long end) { unsigned long addr; @@ -135,6 +173,7 @@ void sync_global_pgds(unsigned long start, unsigned long end) spin_unlock(&pgd_lock); } } +#endif /* * NOTE: This function is marked __ref because it calls __init function @@ -585,6 +624,57 @@ phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end, return paddr_last; } +static unsigned long __meminit +phys_p4d_init(p4d_t *p4d_page, unsigned long paddr, unsigned long paddr_end, + unsigned long page_size_mask) +{ + unsigned long paddr_next, paddr_last = paddr_end; + unsigned long vaddr = (unsigned long)__va(paddr); + int i = p4d_index(vaddr); + + if (!IS_ENABLED(CONFIG_X86_5LEVEL)) + return phys_pud_init((pud_t *) p4d_page, paddr, paddr_end, page_size_mask); + + for (; i < PTRS_PER_P4D; i++, paddr = paddr_next) { + p4d_t *p4d; + pud_t *pud; + + vaddr = (unsigned long)__va(paddr); + p4d = p4d_page + p4d_index(vaddr); + paddr_next = (paddr & P4D_MASK) + P4D_SIZE; + + if (paddr >= paddr_end) { + if (!after_bootmem && + !e820__mapped_any(paddr & P4D_MASK, paddr_next, + E820_TYPE_RAM) && + !e820__mapped_any(paddr & P4D_MASK, paddr_next, + E820_TYPE_RESERVED_KERN)) + set_p4d(p4d, __p4d(0)); + continue; + } + + if (!p4d_none(*p4d)) { + pud = pud_offset(p4d, 0); + paddr_last = phys_pud_init(pud, paddr, + paddr_end, + page_size_mask); + __flush_tlb_all(); + continue; + } + + pud = alloc_low_page(); + paddr_last = phys_pud_init(pud, paddr, paddr_end, + page_size_mask); + + spin_lock(&init_mm.page_table_lock); + p4d_populate(&init_mm, p4d, pud); + spin_unlock(&init_mm.page_table_lock); + } + __flush_tlb_all(); + + return paddr_last; +} + /* * Create page table mapping for the physical memory for specific physical * addresses. The virtual and physical addresses have to be aligned on PMD level @@ -606,26 +696,26 @@ kernel_physical_mapping_init(unsigned long paddr_start, for (; vaddr < vaddr_end; vaddr = vaddr_next) { pgd_t *pgd = pgd_offset_k(vaddr); p4d_t *p4d; - pud_t *pud; vaddr_next = (vaddr & PGDIR_MASK) + PGDIR_SIZE; - BUILD_BUG_ON(pgd_none(*pgd)); - p4d = p4d_offset(pgd, vaddr); - if (p4d_val(*p4d)) { - pud = (pud_t *)p4d_page_vaddr(*p4d); - paddr_last = phys_pud_init(pud, __pa(vaddr), + if (pgd_val(*pgd)) { + p4d = (p4d_t *)pgd_page_vaddr(*pgd); + paddr_last = phys_p4d_init(p4d, __pa(vaddr), __pa(vaddr_end), page_size_mask); continue; } - pud = alloc_low_page(); - paddr_last = phys_pud_init(pud, __pa(vaddr), __pa(vaddr_end), + p4d = alloc_low_page(); + paddr_last = phys_p4d_init(p4d, __pa(vaddr), __pa(vaddr_end), page_size_mask); spin_lock(&init_mm.page_table_lock); - p4d_populate(&init_mm, p4d, pud); + if (IS_ENABLED(CONFIG_X86_5LEVEL)) + pgd_populate(&init_mm, pgd, p4d); + else + p4d_populate(&init_mm, p4d_offset(pgd, vaddr), (pud_t *) p4d); spin_unlock(&init_mm.page_table_lock); pgd_changed = true; } @@ -990,7 +1080,13 @@ remove_p4d_table(p4d_t *p4d_start, unsigned long addr, unsigned long end, pud_base = pud_offset(p4d, 0); remove_pud_table(pud_base, addr, next, direct); - free_pud_table(pud_base, p4d); + /* + * For 4-level page tables we do not want to free PUDs, but in the + * 5-level case we should free them. This code will have to change + * to adapt for boot-time switching between 4 and 5 level page tables. + */ + if (CONFIG_PGTABLE_LEVELS == 5) + free_pud_table(pud_base, p4d); } if (direct) diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index bbc558b88a88..4c1b5fd0c7ad 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -424,7 +424,7 @@ static pte_t bm_pte[PAGE_SIZE/sizeof(pte_t)] __page_aligned_bss; static inline pmd_t * __init early_ioremap_pmd(unsigned long addr) { /* Don't assume we're using swapper_pg_dir at this point */ - pgd_t *base = __va(read_cr3()); + pgd_t *base = __va(read_cr3_pa()); pgd_t *pgd = &base[pgd_index(addr)]; p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 0c7d8129bed6..88215ac16b24 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -12,7 +12,7 @@ #include <asm/tlbflush.h> #include <asm/sections.h> -extern pgd_t early_level4_pgt[PTRS_PER_PGD]; +extern pgd_t early_top_pgt[PTRS_PER_PGD]; extern struct range pfn_mapped[E820_MAX_ENTRIES]; static int __init map_range(struct range *range) @@ -109,8 +109,8 @@ void __init kasan_early_init(void) for (i = 0; CONFIG_PGTABLE_LEVELS >= 5 && i < PTRS_PER_P4D; i++) kasan_zero_p4d[i] = __p4d(p4d_val); - kasan_map_early_shadow(early_level4_pgt); - kasan_map_early_shadow(init_level4_pgt); + kasan_map_early_shadow(early_top_pgt); + kasan_map_early_shadow(init_top_pgt); } void __init kasan_init(void) @@ -121,8 +121,8 @@ void __init kasan_init(void) register_die_notifier(&kasan_die_notifier); #endif - memcpy(early_level4_pgt, init_level4_pgt, sizeof(early_level4_pgt)); - load_cr3(early_level4_pgt); + memcpy(early_top_pgt, init_top_pgt, sizeof(early_top_pgt)); + load_cr3(early_top_pgt); __flush_tlb_all(); clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END); @@ -148,7 +148,7 @@ void __init kasan_init(void) kasan_populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END), (void *)KASAN_SHADOW_END); - load_cr3(init_level4_pgt); + load_cr3(init_top_pgt); __flush_tlb_all(); /* diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index aed206475aa7..af599167fe3c 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -6,12 +6,12 @@ * * Entropy is generated using the KASLR early boot functions now shared in * the lib directory (originally written by Kees Cook). Randomization is - * done on PGD & PUD page table levels to increase possible addresses. The - * physical memory mapping code was adapted to support PUD level virtual - * addresses. This implementation on the best configuration provides 30,000 - * possible virtual addresses in average for each memory region. An additional - * low memory page is used to ensure each CPU can start with a PGD aligned - * virtual address (for realmode). + * done on PGD & P4D/PUD page table levels to increase possible addresses. + * The physical memory mapping code was adapted to support P4D/PUD level + * virtual addresses. This implementation on the best configuration provides + * 30,000 possible virtual addresses in average for each memory region. + * An additional low memory page is used to ensure each CPU can start with + * a PGD aligned virtual address (for realmode). * * The order of each memory region is not changed. The feature looks at * the available space for the regions based on different configuration @@ -70,7 +70,7 @@ static __initdata struct kaslr_memory_region { unsigned long *base; unsigned long size_tb; } kaslr_regions[] = { - { &page_offset_base, 64/* Maximum */ }, + { &page_offset_base, 1 << (__PHYSICAL_MASK_SHIFT - TB_SHIFT) /* Maximum */ }, { &vmalloc_base, VMALLOC_SIZE_TB }, { &vmemmap_base, 1 }, }; @@ -142,7 +142,10 @@ void __init kernel_randomize_memory(void) */ entropy = remain_entropy / (ARRAY_SIZE(kaslr_regions) - i); prandom_bytes_state(&rand_state, &rand, sizeof(rand)); - entropy = (rand % (entropy + 1)) & PUD_MASK; + if (IS_ENABLED(CONFIG_X86_5LEVEL)) + entropy = (rand % (entropy + 1)) & P4D_MASK; + else + entropy = (rand % (entropy + 1)) & PUD_MASK; vaddr += entropy; *kaslr_regions[i].base = vaddr; @@ -151,27 +154,21 @@ void __init kernel_randomize_memory(void) * randomization alignment. */ vaddr += get_padding(&kaslr_regions[i]); - vaddr = round_up(vaddr + 1, PUD_SIZE); + if (IS_ENABLED(CONFIG_X86_5LEVEL)) + vaddr = round_up(vaddr + 1, P4D_SIZE); + else + vaddr = round_up(vaddr + 1, PUD_SIZE); remain_entropy -= entropy; } } -/* - * Create PGD aligned trampoline table to allow real mode initialization - * of additional CPUs. Consume only 1 low memory page. - */ -void __meminit init_trampoline(void) +static void __meminit init_trampoline_pud(void) { unsigned long paddr, paddr_next; pgd_t *pgd; pud_t *pud_page, *pud_page_tramp; int i; - if (!kaslr_memory_enabled()) { - init_trampoline_default(); - return; - } - pud_page_tramp = alloc_low_page(); paddr = 0; @@ -192,3 +189,49 @@ void __meminit init_trampoline(void) set_pgd(&trampoline_pgd_entry, __pgd(_KERNPG_TABLE | __pa(pud_page_tramp))); } + +static void __meminit init_trampoline_p4d(void) +{ + unsigned long paddr, paddr_next; + pgd_t *pgd; + p4d_t *p4d_page, *p4d_page_tramp; + int i; + + p4d_page_tramp = alloc_low_page(); + + paddr = 0; + pgd = pgd_offset_k((unsigned long)__va(paddr)); + p4d_page = (p4d_t *) pgd_page_vaddr(*pgd); + + for (i = p4d_index(paddr); i < PTRS_PER_P4D; i++, paddr = paddr_next) { + p4d_t *p4d, *p4d_tramp; + unsigned long vaddr = (unsigned long)__va(paddr); + + p4d_tramp = p4d_page_tramp + p4d_index(paddr); + p4d = p4d_page + p4d_index(vaddr); + paddr_next = (paddr & P4D_MASK) + P4D_SIZE; + + *p4d_tramp = *p4d; + } + + set_pgd(&trampoline_pgd_entry, + __pgd(_KERNPG_TABLE | __pa(p4d_page_tramp))); +} + +/* + * Create PGD aligned trampoline table to allow real mode initialization + * of additional CPUs. Consume only 1 low memory page. + */ +void __meminit init_trampoline(void) +{ + + if (!kaslr_memory_enabled()) { + init_trampoline_default(); + return; + } + + if (IS_ENABLED(CONFIG_X86_5LEVEL)) + init_trampoline_p4d(); + else + init_trampoline_pud(); +} diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 19ad095b41df..797295e792b2 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -74,9 +74,6 @@ static int mmap_is_legacy(void) if (current->personality & ADDR_COMPAT_LAYOUT) return 1; - if (rlimit(RLIMIT_STACK) == RLIM_INFINITY) - return 1; - return sysctl_legacy_va_layout; } diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 6e7bedf69af7..014d07a80053 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -15,7 +15,7 @@ #include <linux/debugfs.h> /* - * Smarter SMP flushing macros. + * TLB flushing, formerly SMP-only * c/o Linus Torvalds. * * These mean you can really definitely utterly forget about @@ -28,39 +28,28 @@ * Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi */ -#ifdef CONFIG_SMP - -struct flush_tlb_info { - struct mm_struct *flush_mm; - unsigned long flush_start; - unsigned long flush_end; -}; - -/* - * We cannot call mmdrop() because we are in interrupt context, - * instead update mm->cpu_vm_mask. - */ void leave_mm(int cpu) { - struct mm_struct *active_mm = this_cpu_read(cpu_tlbstate.active_mm); + struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm); + + /* + * It's plausible that we're in lazy TLB mode while our mm is init_mm. + * If so, our callers still expect us to flush the TLB, but there + * aren't any user TLB entries in init_mm to worry about. + * + * This needs to happen before any other sanity checks due to + * intel_idle's shenanigans. + */ + if (loaded_mm == &init_mm) + return; + if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) BUG(); - if (cpumask_test_cpu(cpu, mm_cpumask(active_mm))) { - cpumask_clear_cpu(cpu, mm_cpumask(active_mm)); - load_cr3(swapper_pg_dir); - /* - * This gets called in the idle path where RCU - * functions differently. Tracing normally - * uses RCU, so we have to call the tracepoint - * specially here. - */ - trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); - } + + switch_mm(NULL, &init_mm, NULL); } EXPORT_SYMBOL_GPL(leave_mm); -#endif /* CONFIG_SMP */ - void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { @@ -75,216 +64,167 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { unsigned cpu = smp_processor_id(); + struct mm_struct *real_prev = this_cpu_read(cpu_tlbstate.loaded_mm); - if (likely(prev != next)) { - if (IS_ENABLED(CONFIG_VMAP_STACK)) { - /* - * If our current stack is in vmalloc space and isn't - * mapped in the new pgd, we'll double-fault. Forcibly - * map it. - */ - unsigned int stack_pgd_index = pgd_index(current_stack_pointer()); - - pgd_t *pgd = next->pgd + stack_pgd_index; - - if (unlikely(pgd_none(*pgd))) - set_pgd(pgd, init_mm.pgd[stack_pgd_index]); - } + /* + * NB: The scheduler will call us with prev == next when + * switching from lazy TLB mode to normal mode if active_mm + * isn't changing. When this happens, there is no guarantee + * that CR3 (and hence cpu_tlbstate.loaded_mm) matches next. + * + * NB: leave_mm() calls us with prev == NULL and tsk == NULL. + */ -#ifdef CONFIG_SMP - this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK); - this_cpu_write(cpu_tlbstate.active_mm, next); -#endif + this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK); - cpumask_set_cpu(cpu, mm_cpumask(next)); + if (real_prev == next) { + /* + * There's nothing to do: we always keep the per-mm control + * regs in sync with cpu_tlbstate.loaded_mm. Just + * sanity-check mm_cpumask. + */ + if (WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(next)))) + cpumask_set_cpu(cpu, mm_cpumask(next)); + return; + } + if (IS_ENABLED(CONFIG_VMAP_STACK)) { /* - * Re-load page tables. - * - * This logic has an ordering constraint: - * - * CPU 0: Write to a PTE for 'next' - * CPU 0: load bit 1 in mm_cpumask. if nonzero, send IPI. - * CPU 1: set bit 1 in next's mm_cpumask - * CPU 1: load from the PTE that CPU 0 writes (implicit) - * - * We need to prevent an outcome in which CPU 1 observes - * the new PTE value and CPU 0 observes bit 1 clear in - * mm_cpumask. (If that occurs, then the IPI will never - * be sent, and CPU 0's TLB will contain a stale entry.) - * - * The bad outcome can occur if either CPU's load is - * reordered before that CPU's store, so both CPUs must - * execute full barriers to prevent this from happening. - * - * Thus, switch_mm needs a full barrier between the - * store to mm_cpumask and any operation that could load - * from next->pgd. TLB fills are special and can happen - * due to instruction fetches or for no reason at all, - * and neither LOCK nor MFENCE orders them. - * Fortunately, load_cr3() is serializing and gives the - * ordering guarantee we need. - * + * If our current stack is in vmalloc space and isn't + * mapped in the new pgd, we'll double-fault. Forcibly + * map it. */ - load_cr3(next->pgd); + unsigned int stack_pgd_index = pgd_index(current_stack_pointer()); - trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); + pgd_t *pgd = next->pgd + stack_pgd_index; - /* Stop flush ipis for the previous mm */ - cpumask_clear_cpu(cpu, mm_cpumask(prev)); + if (unlikely(pgd_none(*pgd))) + set_pgd(pgd, init_mm.pgd[stack_pgd_index]); + } - /* Load per-mm CR4 state */ - load_mm_cr4(next); + this_cpu_write(cpu_tlbstate.loaded_mm, next); -#ifdef CONFIG_MODIFY_LDT_SYSCALL - /* - * Load the LDT, if the LDT is different. - * - * It's possible that prev->context.ldt doesn't match - * the LDT register. This can happen if leave_mm(prev) - * was called and then modify_ldt changed - * prev->context.ldt but suppressed an IPI to this CPU. - * In this case, prev->context.ldt != NULL, because we - * never set context.ldt to NULL while the mm still - * exists. That means that next->context.ldt != - * prev->context.ldt, because mms never share an LDT. - */ - if (unlikely(prev->context.ldt != next->context.ldt)) - load_mm_ldt(next); -#endif + WARN_ON_ONCE(cpumask_test_cpu(cpu, mm_cpumask(next))); + cpumask_set_cpu(cpu, mm_cpumask(next)); + + /* + * Re-load page tables. + * + * This logic has an ordering constraint: + * + * CPU 0: Write to a PTE for 'next' + * CPU 0: load bit 1 in mm_cpumask. if nonzero, send IPI. + * CPU 1: set bit 1 in next's mm_cpumask + * CPU 1: load from the PTE that CPU 0 writes (implicit) + * + * We need to prevent an outcome in which CPU 1 observes + * the new PTE value and CPU 0 observes bit 1 clear in + * mm_cpumask. (If that occurs, then the IPI will never + * be sent, and CPU 0's TLB will contain a stale entry.) + * + * The bad outcome can occur if either CPU's load is + * reordered before that CPU's store, so both CPUs must + * execute full barriers to prevent this from happening. + * + * Thus, switch_mm needs a full barrier between the + * store to mm_cpumask and any operation that could load + * from next->pgd. TLB fills are special and can happen + * due to instruction fetches or for no reason at all, + * and neither LOCK nor MFENCE orders them. + * Fortunately, load_cr3() is serializing and gives the + * ordering guarantee we need. + */ + load_cr3(next->pgd); + + /* + * This gets called via leave_mm() in the idle path where RCU + * functions differently. Tracing normally uses RCU, so we have to + * call the tracepoint specially here. + */ + trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); + + /* Stop flush ipis for the previous mm */ + WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(real_prev)) && + real_prev != &init_mm); + cpumask_clear_cpu(cpu, mm_cpumask(real_prev)); + + /* Load per-mm CR4 and LDTR state */ + load_mm_cr4(next); + switch_ldt(real_prev, next); +} + +static void flush_tlb_func_common(const struct flush_tlb_info *f, + bool local, enum tlb_flush_reason reason) +{ + /* This code cannot presently handle being reentered. */ + VM_WARN_ON(!irqs_disabled()); + + if (this_cpu_read(cpu_tlbstate.state) != TLBSTATE_OK) { + leave_mm(smp_processor_id()); + return; } -#ifdef CONFIG_SMP - else { - this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK); - BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next); - - if (!cpumask_test_cpu(cpu, mm_cpumask(next))) { - /* - * On established mms, the mm_cpumask is only changed - * from irq context, from ptep_clear_flush() while in - * lazy tlb mode, and here. Irqs are blocked during - * schedule, protecting us from simultaneous changes. - */ - cpumask_set_cpu(cpu, mm_cpumask(next)); - /* - * We were in lazy tlb mode and leave_mm disabled - * tlb flush IPI delivery. We must reload CR3 - * to make sure to use no freed page tables. - * - * As above, load_cr3() is serializing and orders TLB - * fills with respect to the mm_cpumask write. - */ - load_cr3(next->pgd); - trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); - load_mm_cr4(next); - load_mm_ldt(next); + if (f->end == TLB_FLUSH_ALL) { + local_flush_tlb(); + if (local) + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); + trace_tlb_flush(reason, TLB_FLUSH_ALL); + } else { + unsigned long addr; + unsigned long nr_pages = (f->end - f->start) >> PAGE_SHIFT; + addr = f->start; + while (addr < f->end) { + __flush_tlb_single(addr); + addr += PAGE_SIZE; } + if (local) + count_vm_tlb_events(NR_TLB_LOCAL_FLUSH_ONE, nr_pages); + trace_tlb_flush(reason, nr_pages); } -#endif } -#ifdef CONFIG_SMP +static void flush_tlb_func_local(void *info, enum tlb_flush_reason reason) +{ + const struct flush_tlb_info *f = info; -/* - * The flush IPI assumes that a thread switch happens in this order: - * [cpu0: the cpu that switches] - * 1) switch_mm() either 1a) or 1b) - * 1a) thread switch to a different mm - * 1a1) set cpu_tlbstate to TLBSTATE_OK - * Now the tlb flush NMI handler flush_tlb_func won't call leave_mm - * if cpu0 was in lazy tlb mode. - * 1a2) update cpu active_mm - * Now cpu0 accepts tlb flushes for the new mm. - * 1a3) cpu_set(cpu, new_mm->cpu_vm_mask); - * Now the other cpus will send tlb flush ipis. - * 1a4) change cr3. - * 1a5) cpu_clear(cpu, old_mm->cpu_vm_mask); - * Stop ipi delivery for the old mm. This is not synchronized with - * the other cpus, but flush_tlb_func ignore flush ipis for the wrong - * mm, and in the worst case we perform a superfluous tlb flush. - * 1b) thread switch without mm change - * cpu active_mm is correct, cpu0 already handles flush ipis. - * 1b1) set cpu_tlbstate to TLBSTATE_OK - * 1b2) test_and_set the cpu bit in cpu_vm_mask. - * Atomically set the bit [other cpus will start sending flush ipis], - * and test the bit. - * 1b3) if the bit was 0: leave_mm was called, flush the tlb. - * 2) switch %%esp, ie current - * - * The interrupt must handle 2 special cases: - * - cr3 is changed before %%esp, ie. it cannot use current->{active_,}mm. - * - the cpu performs speculative tlb reads, i.e. even if the cpu only - * runs in kernel space, the cpu could load tlb entries for user space - * pages. - * - * The good news is that cpu_tlbstate is local to each cpu, no - * write/read ordering problems. - */ + flush_tlb_func_common(f, true, reason); +} -/* - * TLB flush funcation: - * 1) Flush the tlb entries if the cpu uses the mm that's being flushed. - * 2) Leave the mm if we are in the lazy tlb mode. - */ -static void flush_tlb_func(void *info) +static void flush_tlb_func_remote(void *info) { - struct flush_tlb_info *f = info; + const struct flush_tlb_info *f = info; inc_irq_stat(irq_tlb_count); - if (f->flush_mm && f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm)) + if (f->mm && f->mm != this_cpu_read(cpu_tlbstate.loaded_mm)) return; count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); - if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) { - if (f->flush_end == TLB_FLUSH_ALL) { - local_flush_tlb(); - trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, TLB_FLUSH_ALL); - } else { - unsigned long addr; - unsigned long nr_pages = - (f->flush_end - f->flush_start) / PAGE_SIZE; - addr = f->flush_start; - while (addr < f->flush_end) { - __flush_tlb_single(addr); - addr += PAGE_SIZE; - } - trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, nr_pages); - } - } else - leave_mm(smp_processor_id()); - + flush_tlb_func_common(f, false, TLB_REMOTE_SHOOTDOWN); } void native_flush_tlb_others(const struct cpumask *cpumask, - struct mm_struct *mm, unsigned long start, - unsigned long end) + const struct flush_tlb_info *info) { - struct flush_tlb_info info; - - info.flush_mm = mm; - info.flush_start = start; - info.flush_end = end; - count_vm_tlb_event(NR_TLB_REMOTE_FLUSH); - if (end == TLB_FLUSH_ALL) + if (info->end == TLB_FLUSH_ALL) trace_tlb_flush(TLB_REMOTE_SEND_IPI, TLB_FLUSH_ALL); else trace_tlb_flush(TLB_REMOTE_SEND_IPI, - (end - start) >> PAGE_SHIFT); + (info->end - info->start) >> PAGE_SHIFT); if (is_uv_system()) { unsigned int cpu; cpu = smp_processor_id(); - cpumask = uv_flush_tlb_others(cpumask, mm, start, end, cpu); + cpumask = uv_flush_tlb_others(cpumask, info); if (cpumask) - smp_call_function_many(cpumask, flush_tlb_func, - &info, 1); + smp_call_function_many(cpumask, flush_tlb_func_remote, + (void *)info, 1); return; } - smp_call_function_many(cpumask, flush_tlb_func, &info, 1); + smp_call_function_many(cpumask, flush_tlb_func_remote, + (void *)info, 1); } /* @@ -302,85 +242,41 @@ static unsigned long tlb_single_page_flush_ceiling __read_mostly = 33; void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, unsigned long end, unsigned long vmflag) { - unsigned long addr; - /* do a global flush by default */ - unsigned long base_pages_to_flush = TLB_FLUSH_ALL; - - preempt_disable(); + int cpu; - if ((end != TLB_FLUSH_ALL) && !(vmflag & VM_HUGETLB)) - base_pages_to_flush = (end - start) >> PAGE_SHIFT; - if (base_pages_to_flush > tlb_single_page_flush_ceiling) - base_pages_to_flush = TLB_FLUSH_ALL; + struct flush_tlb_info info = { + .mm = mm, + }; - if (current->active_mm != mm) { - /* Synchronize with switch_mm. */ - smp_mb(); + cpu = get_cpu(); - goto out; - } - - if (!current->mm) { - leave_mm(smp_processor_id()); + /* Synchronize with switch_mm. */ + smp_mb(); - /* Synchronize with switch_mm. */ - smp_mb(); - - goto out; - } - - /* - * Both branches below are implicit full barriers (MOV to CR or - * INVLPG) that synchronize with switch_mm. - */ - if (base_pages_to_flush == TLB_FLUSH_ALL) { - count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); - local_flush_tlb(); + /* Should we flush just the requested range? */ + if ((end != TLB_FLUSH_ALL) && + !(vmflag & VM_HUGETLB) && + ((end - start) >> PAGE_SHIFT) <= tlb_single_page_flush_ceiling) { + info.start = start; + info.end = end; } else { - /* flush range by one by one 'invlpg' */ - for (addr = start; addr < end; addr += PAGE_SIZE) { - count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE); - __flush_tlb_single(addr); - } - } - trace_tlb_flush(TLB_LOCAL_MM_SHOOTDOWN, base_pages_to_flush); -out: - if (base_pages_to_flush == TLB_FLUSH_ALL) { - start = 0UL; - end = TLB_FLUSH_ALL; + info.start = 0UL; + info.end = TLB_FLUSH_ALL; } - if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) - flush_tlb_others(mm_cpumask(mm), mm, start, end); - preempt_enable(); -} -void flush_tlb_page(struct vm_area_struct *vma, unsigned long start) -{ - struct mm_struct *mm = vma->vm_mm; - - preempt_disable(); - - if (current->active_mm == mm) { - if (current->mm) { - /* - * Implicit full barrier (INVLPG) that synchronizes - * with switch_mm. - */ - __flush_tlb_one(start); - } else { - leave_mm(smp_processor_id()); - - /* Synchronize with switch_mm. */ - smp_mb(); - } + if (mm == this_cpu_read(cpu_tlbstate.loaded_mm)) { + VM_WARN_ON(irqs_disabled()); + local_irq_disable(); + flush_tlb_func_local(&info, TLB_LOCAL_MM_SHOOTDOWN); + local_irq_enable(); } - if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) - flush_tlb_others(mm_cpumask(mm), mm, start, start + PAGE_SIZE); - - preempt_enable(); + if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids) + flush_tlb_others(mm_cpumask(mm), &info); + put_cpu(); } + static void do_flush_tlb_all(void *info) { count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); @@ -401,7 +297,7 @@ static void do_kernel_range_flush(void *info) unsigned long addr; /* flush range by one by one 'invlpg' */ - for (addr = f->flush_start; addr < f->flush_end; addr += PAGE_SIZE) + for (addr = f->start; addr < f->end; addr += PAGE_SIZE) __flush_tlb_single(addr); } @@ -410,16 +306,40 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end) /* Balance as user space task's flush, a bit conservative */ if (end == TLB_FLUSH_ALL || - (end - start) > tlb_single_page_flush_ceiling * PAGE_SIZE) { + (end - start) > tlb_single_page_flush_ceiling << PAGE_SHIFT) { on_each_cpu(do_flush_tlb_all, NULL, 1); } else { struct flush_tlb_info info; - info.flush_start = start; - info.flush_end = end; + info.start = start; + info.end = end; on_each_cpu(do_kernel_range_flush, &info, 1); } } +void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch) +{ + struct flush_tlb_info info = { + .mm = NULL, + .start = 0UL, + .end = TLB_FLUSH_ALL, + }; + + int cpu = get_cpu(); + + if (cpumask_test_cpu(cpu, &batch->cpumask)) { + VM_WARN_ON(irqs_disabled()); + local_irq_disable(); + flush_tlb_func_local(&info, TLB_LOCAL_SHOOTDOWN); + local_irq_enable(); + } + + if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) + flush_tlb_others(&batch->cpumask, &info); + cpumask_clear(&batch->cpumask); + + put_cpu(); +} + static ssize_t tlbflush_read_file(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { @@ -465,5 +385,3 @@ static int __init create_tlb_single_page_flush_ceiling(void) return 0; } late_initcall(create_tlb_single_page_flush_ceiling); - -#endif /* CONFIG_SMP */ diff --git a/arch/x86/net/Makefile b/arch/x86/net/Makefile index 90568c33ddb0..fefb4b619598 100644 --- a/arch/x86/net/Makefile +++ b/arch/x86/net/Makefile @@ -1,4 +1,6 @@ # # Arch-specific network modules # +OBJECT_FILES_NON_STANDARD_bpf_jit.o += y + obj-$(CONFIG_BPF_JIT) += bpf_jit.o bpf_jit_comp.o diff --git a/arch/x86/platform/efi/Makefile b/arch/x86/platform/efi/Makefile index f1d83b34c329..2f56e1ed61c3 100644 --- a/arch/x86/platform/efi/Makefile +++ b/arch/x86/platform/efi/Makefile @@ -1,4 +1,5 @@ OBJECT_FILES_NON_STANDARD_efi_thunk_$(BITS).o := y +OBJECT_FILES_NON_STANDARD_efi_stub_$(BITS).o := y obj-$(CONFIG_EFI) += quirks.o efi.o efi_$(BITS).o efi_stub_$(BITS).o obj-$(CONFIG_EARLY_PRINTK_EFI) += early_printk.o diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 43b96f5f78ba..f084d8718ac4 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -1014,7 +1014,6 @@ static void __init __efi_enter_virtual_mode(void) * necessary relocation fixups for the new virtual addresses. */ efi_runtime_update_mappings(); - efi_dump_pagetable(); /* clean DUMMY object */ efi_delete_dummy_variable(); @@ -1029,6 +1028,8 @@ void __init efi_enter_virtual_mode(void) kexec_enter_virtual_mode(); else __efi_enter_virtual_mode(); + + efi_dump_pagetable(); } /* diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c index 3481268da3d0..52f7faa1538f 100644 --- a/arch/x86/platform/efi/efi_32.c +++ b/arch/x86/platform/efi/efi_32.c @@ -44,7 +44,14 @@ int __init efi_alloc_page_tables(void) } void efi_sync_low_kernel_mappings(void) {} -void __init efi_dump_pagetable(void) {} + +void __init efi_dump_pagetable(void) +{ +#ifdef CONFIG_EFI_PGT_DUMP + ptdump_walk_pgd_level(NULL, swapper_pg_dir); +#endif +} + int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) { return 0; diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index eb8dff15a7f6..9bf72f5bfedb 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -80,7 +80,7 @@ pgd_t * __init efi_call_phys_prolog(void) int n_pgds, i, j; if (!efi_enabled(EFI_OLD_MEMMAP)) { - save_pgd = (pgd_t *)read_cr3(); + save_pgd = (pgd_t *)__read_cr3(); write_cr3((unsigned long)efi_scratch.efi_pgt); goto out; } @@ -589,7 +589,10 @@ void __init efi_runtime_update_mappings(void) void __init efi_dump_pagetable(void) { #ifdef CONFIG_EFI_PGT_DUMP - ptdump_walk_pgd_level(NULL, efi_pgd); + if (efi_enabled(EFI_OLD_MEMMAP)) + ptdump_walk_pgd_level(NULL, swapper_pg_dir); + else + ptdump_walk_pgd_level(NULL, efi_pgd); #endif } @@ -646,7 +649,7 @@ efi_status_t efi_thunk_set_virtual_address_map( efi_sync_low_kernel_mappings(); local_irq_save(flags); - efi_scratch.prev_cr3 = read_cr3(); + efi_scratch.prev_cr3 = __read_cr3(); write_cr3((unsigned long)efi_scratch.efi_pgt); __flush_tlb_all(); diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index e0cf95a83f3f..8a99a2e96537 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -15,12 +15,66 @@ #include <asm/e820/api.h> #include <asm/efi.h> #include <asm/uv/uv.h> +#include <asm/cpu_device_id.h> #define EFI_MIN_RESERVE 5120 #define EFI_DUMMY_GUID \ EFI_GUID(0x4424ac57, 0xbe4b, 0x47dd, 0x9e, 0x97, 0xed, 0x50, 0xf0, 0x9f, 0x92, 0xa9) +#define QUARK_CSH_SIGNATURE 0x5f435348 /* _CSH */ +#define QUARK_SECURITY_HEADER_SIZE 0x400 + +/* + * Header prepended to the standard EFI capsule on Quark systems the are based + * on Intel firmware BSP. + * @csh_signature: Unique identifier to sanity check signed module + * presence ("_CSH"). + * @version: Current version of CSH used. Should be one for Quark A0. + * @modulesize: Size of the entire module including the module header + * and payload. + * @security_version_number_index: Index of SVN to use for validation of signed + * module. + * @security_version_number: Used to prevent against roll back of modules. + * @rsvd_module_id: Currently unused for Clanton (Quark). + * @rsvd_module_vendor: Vendor Identifier. For Intel products value is + * 0x00008086. + * @rsvd_date: BCD representation of build date as yyyymmdd, where + * yyyy=4 digit year, mm=1-12, dd=1-31. + * @headersize: Total length of the header including including any + * padding optionally added by the signing tool. + * @hash_algo: What Hash is used in the module signing. + * @cryp_algo: What Crypto is used in the module signing. + * @keysize: Total length of the key data including including any + * padding optionally added by the signing tool. + * @signaturesize: Total length of the signature including including any + * padding optionally added by the signing tool. + * @rsvd_next_header: 32-bit pointer to the next Secure Boot Module in the + * chain, if there is a next header. + * @rsvd: Reserved, padding structure to required size. + * + * See also QuartSecurityHeader_t in + * Quark_EDKII_v1.2.1.1/QuarkPlatformPkg/Include/QuarkBootRom.h + * from https://downloadcenter.intel.com/download/23197/Intel-Quark-SoC-X1000-Board-Support-Package-BSP + */ +struct quark_security_header { + u32 csh_signature; + u32 version; + u32 modulesize; + u32 security_version_number_index; + u32 security_version_number; + u32 rsvd_module_id; + u32 rsvd_module_vendor; + u32 rsvd_date; + u32 headersize; + u32 hash_algo; + u32 cryp_algo; + u32 keysize; + u32 signaturesize; + u32 rsvd_next_header; + u32 rsvd[2]; +}; + static efi_char16_t efi_dummy_name[6] = { 'D', 'U', 'M', 'M', 'Y', 0 }; static bool efi_no_storage_paranoia; @@ -504,3 +558,86 @@ bool efi_poweroff_required(void) { return acpi_gbl_reduced_hardware || acpi_no_s5; } + +#ifdef CONFIG_EFI_CAPSULE_QUIRK_QUARK_CSH + +static int qrk_capsule_setup_info(struct capsule_info *cap_info, void **pkbuff, + size_t hdr_bytes) +{ + struct quark_security_header *csh = *pkbuff; + + /* Only process data block that is larger than the security header */ + if (hdr_bytes < sizeof(struct quark_security_header)) + return 0; + + if (csh->csh_signature != QUARK_CSH_SIGNATURE || + csh->headersize != QUARK_SECURITY_HEADER_SIZE) + return 1; + + /* Only process data block if EFI header is included */ + if (hdr_bytes < QUARK_SECURITY_HEADER_SIZE + + sizeof(efi_capsule_header_t)) + return 0; + + pr_debug("Quark security header detected\n"); + + if (csh->rsvd_next_header != 0) { + pr_err("multiple Quark security headers not supported\n"); + return -EINVAL; + } + + *pkbuff += csh->headersize; + cap_info->total_size = csh->headersize; + + /* + * Update the first page pointer to skip over the CSH header. + */ + cap_info->pages[0] += csh->headersize; + + return 1; +} + +#define ICPU(family, model, quirk_handler) \ + { X86_VENDOR_INTEL, family, model, X86_FEATURE_ANY, \ + (unsigned long)&quirk_handler } + +static const struct x86_cpu_id efi_capsule_quirk_ids[] = { + ICPU(5, 9, qrk_capsule_setup_info), /* Intel Quark X1000 */ + { } +}; + +int efi_capsule_setup_info(struct capsule_info *cap_info, void *kbuff, + size_t hdr_bytes) +{ + int (*quirk_handler)(struct capsule_info *, void **, size_t); + const struct x86_cpu_id *id; + int ret; + + if (hdr_bytes < sizeof(efi_capsule_header_t)) + return 0; + + cap_info->total_size = 0; + + id = x86_match_cpu(efi_capsule_quirk_ids); + if (id) { + /* + * The quirk handler is supposed to return + * - a value > 0 if the setup should continue, after advancing + * kbuff as needed + * - 0 if not enough hdr_bytes are available yet + * - a negative error code otherwise + */ + quirk_handler = (typeof(quirk_handler))id->driver_data; + ret = quirk_handler(cap_info, &kbuff, hdr_bytes); + if (ret <= 0) + return ret; + } + + memcpy(&cap_info->header, kbuff, sizeof(cap_info->header)); + + cap_info->total_size += cap_info->header.imagesize; + + return __efi_capsule_setup_info(cap_info); +} + +#endif diff --git a/arch/x86/platform/olpc/olpc-xo1-pm.c b/arch/x86/platform/olpc/olpc-xo1-pm.c index c5350fd27d70..0668aaff8bfe 100644 --- a/arch/x86/platform/olpc/olpc-xo1-pm.c +++ b/arch/x86/platform/olpc/olpc-xo1-pm.c @@ -77,7 +77,7 @@ static int xo1_power_state_enter(suspend_state_t pm_state) asmlinkage __visible int xo1_do_sleep(u8 sleep_state) { - void *pgd_addr = __va(read_cr3()); + void *pgd_addr = __va(read_cr3_pa()); /* Program wakeup mask (using dword access to CS5536_PM1_EN) */ outl(wakeup_mask << 16, acpi_base + CS5536_PM1_STS); diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index 42e65fee5673..2983faab5b18 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -456,12 +456,13 @@ static void reset_with_ipi(struct pnmask *distribution, struct bau_control *bcp) */ static inline unsigned long long cycles_2_ns(unsigned long long cyc) { - struct cyc2ns_data *data = cyc2ns_read_begin(); + struct cyc2ns_data data; unsigned long long ns; - ns = mul_u64_u32_shr(cyc, data->cyc2ns_mul, data->cyc2ns_shift); + cyc2ns_read_begin(&data); + ns = mul_u64_u32_shr(cyc, data.cyc2ns_mul, data.cyc2ns_shift); + cyc2ns_read_end(); - cyc2ns_read_end(data); return ns; } @@ -470,12 +471,13 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc) */ static inline unsigned long long ns_2_cycles(unsigned long long ns) { - struct cyc2ns_data *data = cyc2ns_read_begin(); + struct cyc2ns_data data; unsigned long long cyc; - cyc = (ns << data->cyc2ns_shift) / data->cyc2ns_mul; + cyc2ns_read_begin(&data); + cyc = (ns << data.cyc2ns_shift) / data.cyc2ns_mul; + cyc2ns_read_end(); - cyc2ns_read_end(data); return cyc; } @@ -1121,11 +1123,9 @@ static int set_distrib_bits(struct cpumask *flush_mask, struct bau_control *bcp, * done. The returned pointer is valid till preemption is re-enabled. */ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, - struct mm_struct *mm, - unsigned long start, - unsigned long end, - unsigned int cpu) + const struct flush_tlb_info *info) { + unsigned int cpu = smp_processor_id(); int locals = 0, remotes = 0, hubs = 0; struct bau_desc *bau_desc; struct cpumask *flush_mask; @@ -1179,8 +1179,8 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, record_send_statistics(stat, locals, hubs, remotes, bau_desc); - if (!end || (end - start) <= PAGE_SIZE) - address = start; + if (!info->end || (info->end - info->start) <= PAGE_SIZE) + address = info->start; else address = TLB_FLUSH_ALL; diff --git a/arch/x86/power/Makefile b/arch/x86/power/Makefile index a6a198c33623..05041871ac90 100644 --- a/arch/x86/power/Makefile +++ b/arch/x86/power/Makefile @@ -1,3 +1,5 @@ +OBJECT_FILES_NON_STANDARD_hibernate_asm_$(BITS).o := y + # __restore_processor_state() restores %gs after S3 resume and so should not # itself be stack-protected nostackp := $(call cc-option, -fno-stack-protector) diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 6b05a9219ea2..78459a6d455a 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -129,7 +129,7 @@ static void __save_processor_state(struct saved_context *ctxt) */ ctxt->cr0 = read_cr0(); ctxt->cr2 = read_cr2(); - ctxt->cr3 = read_cr3(); + ctxt->cr3 = __read_cr3(); ctxt->cr4 = __read_cr4(); #ifdef CONFIG_X86_64 ctxt->cr8 = read_cr8(); diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index a6e21fee22ea..e3e62c8a8e70 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -150,7 +150,8 @@ static int relocate_restore_code(void) memcpy((void *)relocated_restore_code, &core_restore_code, PAGE_SIZE); /* Make the page containing the relocated code executable */ - pgd = (pgd_t *)__va(read_cr3()) + pgd_index(relocated_restore_code); + pgd = (pgd_t *)__va(read_cr3_pa()) + + pgd_index(relocated_restore_code); p4d = p4d_offset(pgd, relocated_restore_code); if (p4d_large(*p4d)) { set_p4d(p4d, __p4d(p4d_val(*p4d) & ~_PAGE_NX)); diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index a163a90af4aa..cd4be19c36dc 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -102,7 +102,7 @@ static void __init setup_real_mode(void) trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd); trampoline_pgd[0] = trampoline_pgd_entry.pgd; - trampoline_pgd[511] = init_level4_pgt[511].pgd; + trampoline_pgd[511] = init_top_pgt[511].pgd; #endif } diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index fffb0a16f9e3..bced7a369a11 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -1,3 +1,6 @@ +OBJECT_FILES_NON_STANDARD_xen-asm_$(BITS).o := y +OBJECT_FILES_NON_STANDARD_xen-pvh.o := y + ifdef CONFIG_FUNCTION_TRACER # Do not profile debug and lowlevel utilities CFLAGS_REMOVE_spinlock.o = -pg diff --git a/arch/x86/xen/efi.c b/arch/x86/xen/efi.c index 30bb2e80cfe7..a18703be9ead 100644 --- a/arch/x86/xen/efi.c +++ b/arch/x86/xen/efi.c @@ -54,38 +54,6 @@ static efi_system_table_t efi_systab_xen __initdata = { .tables = EFI_INVALID_TABLE_ADDR /* Initialized later. */ }; -static const struct efi efi_xen __initconst = { - .systab = NULL, /* Initialized later. */ - .runtime_version = 0, /* Initialized later. */ - .mps = EFI_INVALID_TABLE_ADDR, - .acpi = EFI_INVALID_TABLE_ADDR, - .acpi20 = EFI_INVALID_TABLE_ADDR, - .smbios = EFI_INVALID_TABLE_ADDR, - .smbios3 = EFI_INVALID_TABLE_ADDR, - .sal_systab = EFI_INVALID_TABLE_ADDR, - .boot_info = EFI_INVALID_TABLE_ADDR, - .hcdp = EFI_INVALID_TABLE_ADDR, - .uga = EFI_INVALID_TABLE_ADDR, - .uv_systab = EFI_INVALID_TABLE_ADDR, - .fw_vendor = EFI_INVALID_TABLE_ADDR, - .runtime = EFI_INVALID_TABLE_ADDR, - .config_table = EFI_INVALID_TABLE_ADDR, - .get_time = xen_efi_get_time, - .set_time = xen_efi_set_time, - .get_wakeup_time = xen_efi_get_wakeup_time, - .set_wakeup_time = xen_efi_set_wakeup_time, - .get_variable = xen_efi_get_variable, - .get_next_variable = xen_efi_get_next_variable, - .set_variable = xen_efi_set_variable, - .query_variable_info = xen_efi_query_variable_info, - .update_capsule = xen_efi_update_capsule, - .query_capsule_caps = xen_efi_query_capsule_caps, - .get_next_high_mono_count = xen_efi_get_next_high_mono_count, - .reset_system = xen_efi_reset_system, - .set_virtual_address_map = NULL, /* Not used under Xen. */ - .flags = 0 /* Initialized later. */ -}; - static efi_system_table_t __init *xen_efi_probe(void) { struct xen_platform_op op = { @@ -102,7 +70,18 @@ static efi_system_table_t __init *xen_efi_probe(void) /* Here we know that Xen runs on EFI platform. */ - efi = efi_xen; + efi.get_time = xen_efi_get_time; + efi.set_time = xen_efi_set_time; + efi.get_wakeup_time = xen_efi_get_wakeup_time; + efi.set_wakeup_time = xen_efi_set_wakeup_time; + efi.get_variable = xen_efi_get_variable; + efi.get_next_variable = xen_efi_get_next_variable; + efi.set_variable = xen_efi_set_variable; + efi.query_variable_info = xen_efi_query_variable_info; + efi.update_capsule = xen_efi_update_capsule; + efi.query_capsule_caps = xen_efi_query_capsule_caps; + efi.get_next_high_mono_count = xen_efi_get_next_high_mono_count; + efi.reset_system = xen_efi_reset_system; efi_systab_xen.tables = info->cfg.addr; efi_systab_xen.nr_tables = info->cfg.nent; diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 1f386d7fdf70..1d7a7213a310 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -975,37 +975,32 @@ static void xen_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) spin_unlock(&mm->page_table_lock); } - -#ifdef CONFIG_SMP -/* Another cpu may still have their %cr3 pointing at the pagetable, so - we need to repoint it somewhere else before we can unpin it. */ -static void drop_other_mm_ref(void *info) +static void drop_mm_ref_this_cpu(void *info) { struct mm_struct *mm = info; - struct mm_struct *active_mm; - - active_mm = this_cpu_read(cpu_tlbstate.active_mm); - if (active_mm == mm && this_cpu_read(cpu_tlbstate.state) != TLBSTATE_OK) + if (this_cpu_read(cpu_tlbstate.loaded_mm) == mm) leave_mm(smp_processor_id()); - /* If this cpu still has a stale cr3 reference, then make sure - it has been flushed. */ + /* + * If this cpu still has a stale cr3 reference, then make sure + * it has been flushed. + */ if (this_cpu_read(xen_current_cr3) == __pa(mm->pgd)) - load_cr3(swapper_pg_dir); + xen_mc_flush(); } +#ifdef CONFIG_SMP +/* + * Another cpu may still have their %cr3 pointing at the pagetable, so + * we need to repoint it somewhere else before we can unpin it. + */ static void xen_drop_mm_ref(struct mm_struct *mm) { cpumask_var_t mask; unsigned cpu; - if (current->active_mm == mm) { - if (current->mm == mm) - load_cr3(swapper_pg_dir); - else - leave_mm(smp_processor_id()); - } + drop_mm_ref_this_cpu(mm); /* Get the "official" set of cpus referring to our pagetable. */ if (!alloc_cpumask_var(&mask, GFP_ATOMIC)) { @@ -1013,31 +1008,31 @@ static void xen_drop_mm_ref(struct mm_struct *mm) if (!cpumask_test_cpu(cpu, mm_cpumask(mm)) && per_cpu(xen_current_cr3, cpu) != __pa(mm->pgd)) continue; - smp_call_function_single(cpu, drop_other_mm_ref, mm, 1); + smp_call_function_single(cpu, drop_mm_ref_this_cpu, mm, 1); } return; } cpumask_copy(mask, mm_cpumask(mm)); - /* It's possible that a vcpu may have a stale reference to our - cr3, because its in lazy mode, and it hasn't yet flushed - its set of pending hypercalls yet. In this case, we can - look at its actual current cr3 value, and force it to flush - if needed. */ + /* + * It's possible that a vcpu may have a stale reference to our + * cr3, because its in lazy mode, and it hasn't yet flushed + * its set of pending hypercalls yet. In this case, we can + * look at its actual current cr3 value, and force it to flush + * if needed. + */ for_each_online_cpu(cpu) { if (per_cpu(xen_current_cr3, cpu) == __pa(mm->pgd)) cpumask_set_cpu(cpu, mask); } - if (!cpumask_empty(mask)) - smp_call_function_many(mask, drop_other_mm_ref, mm, 1); + smp_call_function_many(mask, drop_mm_ref_this_cpu, mm, 1); free_cpumask_var(mask); } #else static void xen_drop_mm_ref(struct mm_struct *mm) { - if (current->active_mm == mm) - load_cr3(swapper_pg_dir); + drop_mm_ref_this_cpu(mm); } #endif @@ -1366,8 +1361,7 @@ static void xen_flush_tlb_single(unsigned long addr) } static void xen_flush_tlb_others(const struct cpumask *cpus, - struct mm_struct *mm, unsigned long start, - unsigned long end) + const struct flush_tlb_info *info) { struct { struct mmuext_op op; @@ -1379,7 +1373,7 @@ static void xen_flush_tlb_others(const struct cpumask *cpus, } *args; struct multicall_space mcs; - trace_xen_mmu_flush_tlb_others(cpus, mm, start, end); + trace_xen_mmu_flush_tlb_others(cpus, info->mm, info->start, info->end); if (cpumask_empty(cpus)) return; /* nothing to do */ @@ -1393,9 +1387,10 @@ static void xen_flush_tlb_others(const struct cpumask *cpus, cpumask_clear_cpu(smp_processor_id(), to_cpumask(args->mask)); args->op.cmd = MMUEXT_TLB_FLUSH_MULTI; - if (end != TLB_FLUSH_ALL && (end - start) <= PAGE_SIZE) { + if (info->end != TLB_FLUSH_ALL && + (info->end - info->start) <= PAGE_SIZE) { args->op.cmd = MMUEXT_INVLPG_MULTI; - args->op.arg1.linear_addr = start; + args->op.arg1.linear_addr = info->start; } MULTI_mmuext_op(mcs.mc, &args->op, 1, NULL, DOMID_SELF); @@ -1470,8 +1465,8 @@ static void xen_write_cr3(unsigned long cr3) * At the start of the day - when Xen launches a guest, it has already * built pagetables for the guest. We diligently look over them * in xen_setup_kernel_pagetable and graft as appropriate them in the - * init_level4_pgt and its friends. Then when we are happy we load - * the new init_level4_pgt - and continue on. + * init_top_pgt and its friends. Then when we are happy we load + * the new init_top_pgt - and continue on. * * The generic code starts (start_kernel) and 'init_mem_mapping' sets * up the rest of the pagetables. When it has completed it loads the cr3. @@ -1914,12 +1909,12 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) pt_end = pt_base + xen_start_info->nr_pt_frames; /* Zap identity mapping */ - init_level4_pgt[0] = __pgd(0); + init_top_pgt[0] = __pgd(0); /* Pre-constructed entries are in pfn, so convert to mfn */ /* L4[272] -> level3_ident_pgt */ /* L4[511] -> level3_kernel_pgt */ - convert_pfn_mfn(init_level4_pgt); + convert_pfn_mfn(init_top_pgt); /* L3_i[0] -> level2_ident_pgt */ convert_pfn_mfn(level3_ident_pgt); @@ -1950,10 +1945,10 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) /* Copy the initial P->M table mappings if necessary. */ i = pgd_index(xen_start_info->mfn_list); if (i && i < pgd_index(__START_KERNEL_map)) - init_level4_pgt[i] = ((pgd_t *)xen_start_info->pt_base)[i]; + init_top_pgt[i] = ((pgd_t *)xen_start_info->pt_base)[i]; /* Make pagetable pieces RO */ - set_page_prot(init_level4_pgt, PAGE_KERNEL_RO); + set_page_prot(init_top_pgt, PAGE_KERNEL_RO); set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO); set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO); set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO); @@ -1964,7 +1959,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) /* Pin down new L4 */ pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE, - PFN_DOWN(__pa_symbol(init_level4_pgt))); + PFN_DOWN(__pa_symbol(init_top_pgt))); /* Unpin Xen-provided one */ pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd))); @@ -1974,7 +1969,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) * attach it to, so make sure we just set kernel pgd. */ xen_mc_batch(); - __xen_write_cr3(true, __pa(init_level4_pgt)); + __xen_write_cr3(true, __pa(init_top_pgt)); xen_mc_issue(PARAVIRT_LAZY_CPU); /* We can't that easily rip out L3 and L2, as the Xen pagetables are @@ -2022,7 +2017,7 @@ static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr) pmd_t pmd; pte_t pte; - pa = read_cr3(); + pa = read_cr3_pa(); pgd = native_make_pgd(xen_read_phys_ulong(pa + pgd_index(vaddr) * sizeof(pgd))); if (!pgd_present(pgd)) @@ -2102,7 +2097,7 @@ void __init xen_relocate_p2m(void) pt_phys = pmd_phys + PFN_PHYS(n_pmd); p2m_pfn = PFN_DOWN(pt_phys) + n_pt; - pgd = __va(read_cr3()); + pgd = __va(read_cr3_pa()); new_p2m = (unsigned long *)(2 * PGDIR_SIZE); idx_p4d = 0; save_pud = n_pud; @@ -2209,7 +2204,7 @@ static void __init xen_write_cr3_init(unsigned long cr3) { unsigned long pfn = PFN_DOWN(__pa(swapper_pg_dir)); - BUG_ON(read_cr3() != __pa(initial_page_table)); + BUG_ON(read_cr3_pa() != __pa(initial_page_table)); BUG_ON(cr3 != __pa(swapper_pg_dir)); /* diff --git a/arch/x86/xen/xen-pvh.S b/arch/x86/xen/xen-pvh.S index 5e246716d58f..e1a5fbeae08d 100644 --- a/arch/x86/xen/xen-pvh.S +++ b/arch/x86/xen/xen-pvh.S @@ -87,7 +87,7 @@ ENTRY(pvh_start_xen) wrmsr /* Enable pre-constructed page tables. */ - mov $_pa(init_level4_pgt), %eax + mov $_pa(init_top_pgt), %eax mov %eax, %cr3 mov $(X86_CR0_PG | X86_CR0_PE), %eax mov %eax, %cr0 diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h index 003eeee3fbc6..30ee8c608853 100644 --- a/arch/xtensa/include/asm/processor.h +++ b/arch/xtensa/include/asm/processor.h @@ -213,8 +213,6 @@ struct mm_struct; #define release_segments(mm) do { } while(0) #define forget_segments() do { } while (0) -#define thread_saved_pc(tsk) (task_pt_regs(tsk)->pc) - extern unsigned long get_wchan(struct task_struct *p); #define KSTK_EIP(tsk) (task_pt_regs(tsk)->pc) diff --git a/block/badblocks.c b/block/badblocks.c index 6ebcef282314..43c71166e1e2 100644 --- a/block/badblocks.c +++ b/block/badblocks.c @@ -533,6 +533,7 @@ ssize_t badblocks_store(struct badblocks *bb, const char *page, size_t len, case 3: if (newline != '\n') return -EINVAL; + /* fall through */ case 2: if (length <= 0) return -EINVAL; diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index ed93da2462ab..12bbc6b8657d 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -725,8 +725,12 @@ static void bfq_updated_next_req(struct bfq_data *bfqd, } static void -bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_io_cq *bic) +bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd, + struct bfq_io_cq *bic, bool bfq_already_existing) { + unsigned int old_wr_coeff = bfqq->wr_coeff; + bool busy = bfq_already_existing && bfq_bfqq_busy(bfqq); + if (bic->saved_idle_window) bfq_mark_bfqq_idle_window(bfqq); else @@ -754,6 +758,14 @@ bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_io_cq *bic) /* make sure weight will be updated, however we got here */ bfqq->entity.prio_changed = 1; + + if (likely(!busy)) + return; + + if (old_wr_coeff == 1 && bfqq->wr_coeff > 1) + bfqd->wr_busy_queues++; + else if (old_wr_coeff > 1 && bfqq->wr_coeff == 1) + bfqd->wr_busy_queues--; } static int bfqq_process_refs(struct bfq_queue *bfqq) @@ -4290,10 +4302,16 @@ static void bfq_put_rq_priv_body(struct bfq_queue *bfqq) bfq_put_queue(bfqq); } -static void bfq_put_rq_private(struct request_queue *q, struct request *rq) +static void bfq_finish_request(struct request *rq) { - struct bfq_queue *bfqq = RQ_BFQQ(rq); - struct bfq_data *bfqd = bfqq->bfqd; + struct bfq_queue *bfqq; + struct bfq_data *bfqd; + + if (!rq->elv.icq) + return; + + bfqq = RQ_BFQQ(rq); + bfqd = bfqq->bfqd; if (rq->rq_flags & RQF_STARTED) bfqg_stats_update_completion(bfqq_group(bfqq), @@ -4324,7 +4342,7 @@ static void bfq_put_rq_private(struct request_queue *q, struct request *rq) */ if (!RB_EMPTY_NODE(&rq->rb_node)) - bfq_remove_request(q, rq); + bfq_remove_request(rq->q, rq); bfq_put_rq_priv_body(bfqq); } @@ -4394,20 +4412,21 @@ static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd, /* * Allocate bfq data structures associated with this request. */ -static int bfq_get_rq_private(struct request_queue *q, struct request *rq, - struct bio *bio) +static void bfq_prepare_request(struct request *rq, struct bio *bio) { + struct request_queue *q = rq->q; struct bfq_data *bfqd = q->elevator->elevator_data; - struct bfq_io_cq *bic = icq_to_bic(rq->elv.icq); + struct bfq_io_cq *bic; const int is_sync = rq_is_sync(rq); struct bfq_queue *bfqq; bool new_queue = false; - bool split = false; + bool bfqq_already_existing = false, split = false; - spin_lock_irq(&bfqd->lock); + if (!rq->elv.icq) + return; + bic = icq_to_bic(rq->elv.icq); - if (!bic) - goto queue_fail; + spin_lock_irq(&bfqd->lock); bfq_check_ioprio_change(bic, bio); @@ -4432,6 +4451,8 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq, bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio, true, is_sync, NULL); + else + bfqq_already_existing = true; } } @@ -4457,7 +4478,8 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq, * queue: restore the idle window and the * possible weight raising period. */ - bfq_bfqq_resume_state(bfqq, bic); + bfq_bfqq_resume_state(bfqq, bfqd, bic, + bfqq_already_existing); } } @@ -4465,13 +4487,6 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq, bfq_handle_burst(bfqd, bfqq); spin_unlock_irq(&bfqd->lock); - - return 0; - -queue_fail: - spin_unlock_irq(&bfqd->lock); - - return 1; } static void bfq_idle_slice_timer_body(struct bfq_queue *bfqq) @@ -4950,8 +4965,8 @@ static struct elv_fs_entry bfq_attrs[] = { static struct elevator_type iosched_bfq_mq = { .ops.mq = { - .get_rq_priv = bfq_get_rq_private, - .put_rq_priv = bfq_put_rq_private, + .prepare_request = bfq_prepare_request, + .finish_request = bfq_finish_request, .exit_icq = bfq_exit_icq, .insert_requests = bfq_insert_requests, .dispatch_request = bfq_dispatch_request, diff --git a/block/bio-integrity.c b/block/bio-integrity.c index b5009a896a7f..b8a3a65f7364 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -224,7 +224,7 @@ static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi, * @bio: bio to generate/verify integrity metadata for * @proc_fn: Pointer to the relevant processing function */ -static int bio_integrity_process(struct bio *bio, +static blk_status_t bio_integrity_process(struct bio *bio, integrity_processing_fn *proc_fn) { struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev); @@ -232,7 +232,7 @@ static int bio_integrity_process(struct bio *bio, struct bvec_iter bviter; struct bio_vec bv; struct bio_integrity_payload *bip = bio_integrity(bio); - unsigned int ret = 0; + blk_status_t ret = BLK_STS_OK; void *prot_buf = page_address(bip->bip_vec->bv_page) + bip->bip_vec->bv_offset; @@ -369,7 +369,7 @@ static void bio_integrity_verify_fn(struct work_struct *work) struct bio *bio = bip->bip_bio; struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev); - bio->bi_error = bio_integrity_process(bio, bi->profile->verify_fn); + bio->bi_status = bio_integrity_process(bio, bi->profile->verify_fn); /* Restore original bio completion handler */ bio->bi_end_io = bip->bip_end_io; @@ -398,7 +398,7 @@ void bio_integrity_endio(struct bio *bio) * integrity metadata. Restore original bio end_io handler * and run it. */ - if (bio->bi_error) { + if (bio->bi_status) { bio->bi_end_io = bip->bip_end_io; bio_endio(bio); diff --git a/block/bio.c b/block/bio.c index 888e7801c638..1cfcd0df3f30 100644 --- a/block/bio.c +++ b/block/bio.c @@ -240,20 +240,21 @@ fallback: return bvl; } -static void __bio_free(struct bio *bio) +void bio_uninit(struct bio *bio) { bio_disassociate_task(bio); if (bio_integrity(bio)) bio_integrity_free(bio); } +EXPORT_SYMBOL(bio_uninit); static void bio_free(struct bio *bio) { struct bio_set *bs = bio->bi_pool; void *p; - __bio_free(bio); + bio_uninit(bio); if (bs) { bvec_free(bs->bvec_pool, bio->bi_io_vec, BVEC_POOL_IDX(bio)); @@ -271,6 +272,11 @@ static void bio_free(struct bio *bio) } } +/* + * Users of this function have their own bio allocation. Subsequently, + * they must remember to pair any call to bio_init() with bio_uninit() + * when IO has completed, or when the bio is released. + */ void bio_init(struct bio *bio, struct bio_vec *table, unsigned short max_vecs) { @@ -297,7 +303,7 @@ void bio_reset(struct bio *bio) { unsigned long flags = bio->bi_flags & (~0UL << BIO_RESET_BITS); - __bio_free(bio); + bio_uninit(bio); memset(bio, 0, BIO_RESET_BYTES); bio->bi_flags = flags; @@ -309,8 +315,8 @@ static struct bio *__bio_chain_endio(struct bio *bio) { struct bio *parent = bio->bi_private; - if (!parent->bi_error) - parent->bi_error = bio->bi_error; + if (!parent->bi_status) + parent->bi_status = bio->bi_status; bio_put(bio); return parent; } @@ -363,6 +369,8 @@ static void punt_bios_to_rescuer(struct bio_set *bs) struct bio_list punt, nopunt; struct bio *bio; + if (WARN_ON_ONCE(!bs->rescue_workqueue)) + return; /* * In order to guarantee forward progress we must punt only bios that * were allocated from this bio_set; otherwise, if there was a bio on @@ -474,7 +482,8 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, unsigned int nr_iovecs, if (current->bio_list && (!bio_list_empty(¤t->bio_list[0]) || - !bio_list_empty(¤t->bio_list[1]))) + !bio_list_empty(¤t->bio_list[1])) && + bs->rescue_workqueue) gfp_mask &= ~__GFP_DIRECT_RECLAIM; p = mempool_alloc(bs->bio_pool, gfp_mask); @@ -544,7 +553,7 @@ EXPORT_SYMBOL(zero_fill_bio); * * Description: * Put a reference to a &struct bio, either one you have gotten with - * bio_alloc, bio_get or bio_clone. The last put of a bio will free it. + * bio_alloc, bio_get or bio_clone_*. The last put of a bio will free it. **/ void bio_put(struct bio *bio) { @@ -593,6 +602,7 @@ void __bio_clone_fast(struct bio *bio, struct bio *bio_src) bio->bi_bdev = bio_src->bi_bdev; bio_set_flag(bio, BIO_CLONED); bio->bi_opf = bio_src->bi_opf; + bio->bi_write_hint = bio_src->bi_write_hint; bio->bi_iter = bio_src->bi_iter; bio->bi_io_vec = bio_src->bi_io_vec; @@ -676,6 +686,7 @@ struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask, return NULL; bio->bi_bdev = bio_src->bi_bdev; bio->bi_opf = bio_src->bi_opf; + bio->bi_write_hint = bio_src->bi_write_hint; bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector; bio->bi_iter.bi_size = bio_src->bi_iter.bi_size; @@ -918,7 +929,7 @@ static void submit_bio_wait_endio(struct bio *bio) { struct submit_bio_ret *ret = bio->bi_private; - ret->error = bio->bi_error; + ret->error = blk_status_to_errno(bio->bi_status); complete(&ret->event); } @@ -1817,8 +1828,8 @@ again: } if (bio->bi_bdev && bio_flagged(bio, BIO_TRACE_COMPLETION)) { - trace_block_bio_complete(bdev_get_queue(bio->bi_bdev), - bio, bio->bi_error); + trace_block_bio_complete(bdev_get_queue(bio->bi_bdev), bio, + blk_status_to_errno(bio->bi_status)); bio_clear_flag(bio, BIO_TRACE_COMPLETION); } @@ -1921,9 +1932,29 @@ void bioset_free(struct bio_set *bs) } EXPORT_SYMBOL(bioset_free); -static struct bio_set *__bioset_create(unsigned int pool_size, - unsigned int front_pad, - bool create_bvec_pool) +/** + * bioset_create - Create a bio_set + * @pool_size: Number of bio and bio_vecs to cache in the mempool + * @front_pad: Number of bytes to allocate in front of the returned bio + * @flags: Flags to modify behavior, currently %BIOSET_NEED_BVECS + * and %BIOSET_NEED_RESCUER + * + * Description: + * Set up a bio_set to be used with @bio_alloc_bioset. Allows the caller + * to ask for a number of bytes to be allocated in front of the bio. + * Front pad allocation is useful for embedding the bio inside + * another structure, to avoid allocating extra data to go with the bio. + * Note that the bio must be embedded at the END of that structure always, + * or things will break badly. + * If %BIOSET_NEED_BVECS is set in @flags, a separate pool will be allocated + * for allocating iovecs. This pool is not needed e.g. for bio_clone_fast(). + * If %BIOSET_NEED_RESCUER is set, a workqueue is created which can be used to + * dispatch queued requests when the mempool runs out of space. + * + */ +struct bio_set *bioset_create(unsigned int pool_size, + unsigned int front_pad, + int flags) { unsigned int back_pad = BIO_INLINE_VECS * sizeof(struct bio_vec); struct bio_set *bs; @@ -1948,12 +1979,15 @@ static struct bio_set *__bioset_create(unsigned int pool_size, if (!bs->bio_pool) goto bad; - if (create_bvec_pool) { + if (flags & BIOSET_NEED_BVECS) { bs->bvec_pool = biovec_create_pool(pool_size); if (!bs->bvec_pool) goto bad; } + if (!(flags & BIOSET_NEED_RESCUER)) + return bs; + bs->rescue_workqueue = alloc_workqueue("bioset", WQ_MEM_RECLAIM, 0); if (!bs->rescue_workqueue) goto bad; @@ -1963,41 +1997,8 @@ bad: bioset_free(bs); return NULL; } - -/** - * bioset_create - Create a bio_set - * @pool_size: Number of bio and bio_vecs to cache in the mempool - * @front_pad: Number of bytes to allocate in front of the returned bio - * - * Description: - * Set up a bio_set to be used with @bio_alloc_bioset. Allows the caller - * to ask for a number of bytes to be allocated in front of the bio. - * Front pad allocation is useful for embedding the bio inside - * another structure, to avoid allocating extra data to go with the bio. - * Note that the bio must be embedded at the END of that structure always, - * or things will break badly. - */ -struct bio_set *bioset_create(unsigned int pool_size, unsigned int front_pad) -{ - return __bioset_create(pool_size, front_pad, true); -} EXPORT_SYMBOL(bioset_create); -/** - * bioset_create_nobvec - Create a bio_set without bio_vec mempool - * @pool_size: Number of bio to cache in the mempool - * @front_pad: Number of bytes to allocate in front of the returned bio - * - * Description: - * Same functionality as bioset_create() except that mempool is not - * created for bio_vecs. Saving some memory for bio_clone_fast() users. - */ -struct bio_set *bioset_create_nobvec(unsigned int pool_size, unsigned int front_pad) -{ - return __bioset_create(pool_size, front_pad, false); -} -EXPORT_SYMBOL(bioset_create_nobvec); - #ifdef CONFIG_BLK_CGROUP /** @@ -2112,7 +2113,7 @@ static int __init init_bio(void) bio_integrity_init(); biovec_init_slabs(); - fs_bio_set = bioset_create(BIO_POOL_SIZE, 0); + fs_bio_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); if (!fs_bio_set) panic("bio: can't allocate bios\n"); diff --git a/block/blk-core.c b/block/blk-core.c index a7421b772d0e..af393d5a9680 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -129,11 +129,70 @@ void blk_rq_init(struct request_queue *q, struct request *rq) } EXPORT_SYMBOL(blk_rq_init); +static const struct { + int errno; + const char *name; +} blk_errors[] = { + [BLK_STS_OK] = { 0, "" }, + [BLK_STS_NOTSUPP] = { -EOPNOTSUPP, "operation not supported" }, + [BLK_STS_TIMEOUT] = { -ETIMEDOUT, "timeout" }, + [BLK_STS_NOSPC] = { -ENOSPC, "critical space allocation" }, + [BLK_STS_TRANSPORT] = { -ENOLINK, "recoverable transport" }, + [BLK_STS_TARGET] = { -EREMOTEIO, "critical target" }, + [BLK_STS_NEXUS] = { -EBADE, "critical nexus" }, + [BLK_STS_MEDIUM] = { -ENODATA, "critical medium" }, + [BLK_STS_PROTECTION] = { -EILSEQ, "protection" }, + [BLK_STS_RESOURCE] = { -ENOMEM, "kernel resource" }, + [BLK_STS_AGAIN] = { -EAGAIN, "nonblocking retry" }, + + /* device mapper special case, should not leak out: */ + [BLK_STS_DM_REQUEUE] = { -EREMCHG, "dm internal retry" }, + + /* everything else not covered above: */ + [BLK_STS_IOERR] = { -EIO, "I/O" }, +}; + +blk_status_t errno_to_blk_status(int errno) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(blk_errors); i++) { + if (blk_errors[i].errno == errno) + return (__force blk_status_t)i; + } + + return BLK_STS_IOERR; +} +EXPORT_SYMBOL_GPL(errno_to_blk_status); + +int blk_status_to_errno(blk_status_t status) +{ + int idx = (__force int)status; + + if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors))) + return -EIO; + return blk_errors[idx].errno; +} +EXPORT_SYMBOL_GPL(blk_status_to_errno); + +static void print_req_error(struct request *req, blk_status_t status) +{ + int idx = (__force int)status; + + if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors))) + return; + + printk_ratelimited(KERN_ERR "%s: %s error, dev %s, sector %llu\n", + __func__, blk_errors[idx].name, req->rq_disk ? + req->rq_disk->disk_name : "?", + (unsigned long long)blk_rq_pos(req)); +} + static void req_bio_endio(struct request *rq, struct bio *bio, - unsigned int nbytes, int error) + unsigned int nbytes, blk_status_t error) { if (error) - bio->bi_error = error; + bio->bi_status = error; if (unlikely(rq->rq_flags & RQF_QUIET)) bio_set_flag(bio, BIO_QUIET); @@ -177,10 +236,13 @@ static void blk_delay_work(struct work_struct *work) * Description: * Sometimes queueing needs to be postponed for a little while, to allow * resources to come back. This function will make sure that queueing is - * restarted around the specified time. Queue lock must be held. + * restarted around the specified time. */ void blk_delay_queue(struct request_queue *q, unsigned long msecs) { + lockdep_assert_held(q->queue_lock); + WARN_ON_ONCE(q->mq_ops); + if (likely(!blk_queue_dead(q))) queue_delayed_work(kblockd_workqueue, &q->delay_work, msecs_to_jiffies(msecs)); @@ -198,6 +260,9 @@ EXPORT_SYMBOL(blk_delay_queue); **/ void blk_start_queue_async(struct request_queue *q) { + lockdep_assert_held(q->queue_lock); + WARN_ON_ONCE(q->mq_ops); + queue_flag_clear(QUEUE_FLAG_STOPPED, q); blk_run_queue_async(q); } @@ -210,11 +275,13 @@ EXPORT_SYMBOL(blk_start_queue_async); * Description: * blk_start_queue() will clear the stop flag on the queue, and call * the request_fn for the queue if it was in a stopped state when - * entered. Also see blk_stop_queue(). Queue lock must be held. + * entered. Also see blk_stop_queue(). **/ void blk_start_queue(struct request_queue *q) { + lockdep_assert_held(q->queue_lock); WARN_ON(!irqs_disabled()); + WARN_ON_ONCE(q->mq_ops); queue_flag_clear(QUEUE_FLAG_STOPPED, q); __blk_run_queue(q); @@ -233,10 +300,13 @@ EXPORT_SYMBOL(blk_start_queue); * or if it simply chooses not to queue more I/O at one point, it can * call this function to prevent the request_fn from being called until * the driver has signalled it's ready to go again. This happens by calling - * blk_start_queue() to restart queue operations. Queue lock must be held. + * blk_start_queue() to restart queue operations. **/ void blk_stop_queue(struct request_queue *q) { + lockdep_assert_held(q->queue_lock); + WARN_ON_ONCE(q->mq_ops); + cancel_delayed_work(&q->delay_work); queue_flag_set(QUEUE_FLAG_STOPPED, q); } @@ -289,6 +359,9 @@ EXPORT_SYMBOL(blk_sync_queue); */ inline void __blk_run_queue_uncond(struct request_queue *q) { + lockdep_assert_held(q->queue_lock); + WARN_ON_ONCE(q->mq_ops); + if (unlikely(blk_queue_dead(q))) return; @@ -310,11 +383,13 @@ EXPORT_SYMBOL_GPL(__blk_run_queue_uncond); * @q: The queue to run * * Description: - * See @blk_run_queue. This variant must be called with the queue lock - * held and interrupts disabled. + * See @blk_run_queue. */ void __blk_run_queue(struct request_queue *q) { + lockdep_assert_held(q->queue_lock); + WARN_ON_ONCE(q->mq_ops); + if (unlikely(blk_queue_stopped(q))) return; @@ -328,10 +403,18 @@ EXPORT_SYMBOL(__blk_run_queue); * * Description: * Tells kblockd to perform the equivalent of @blk_run_queue on behalf - * of us. The caller must hold the queue lock. + * of us. + * + * Note: + * Since it is not allowed to run q->delay_work after blk_cleanup_queue() + * has canceled q->delay_work, callers must hold the queue lock to avoid + * race conditions between blk_cleanup_queue() and blk_run_queue_async(). */ void blk_run_queue_async(struct request_queue *q) { + lockdep_assert_held(q->queue_lock); + WARN_ON_ONCE(q->mq_ops); + if (likely(!blk_queue_stopped(q) && !blk_queue_dead(q))) mod_delayed_work(kblockd_workqueue, &q->delay_work, 0); } @@ -349,6 +432,8 @@ void blk_run_queue(struct request_queue *q) { unsigned long flags; + WARN_ON_ONCE(q->mq_ops); + spin_lock_irqsave(q->queue_lock, flags); __blk_run_queue(q); spin_unlock_irqrestore(q->queue_lock, flags); @@ -377,6 +462,7 @@ static void __blk_drain_queue(struct request_queue *q, bool drain_all) int i; lockdep_assert_held(q->queue_lock); + WARN_ON_ONCE(q->mq_ops); while (true) { bool drain = false; @@ -455,6 +541,8 @@ static void __blk_drain_queue(struct request_queue *q, bool drain_all) */ void blk_queue_bypass_start(struct request_queue *q) { + WARN_ON_ONCE(q->mq_ops); + spin_lock_irq(q->queue_lock); q->bypass_depth++; queue_flag_set(QUEUE_FLAG_BYPASS, q); @@ -481,6 +569,9 @@ EXPORT_SYMBOL_GPL(blk_queue_bypass_start); * @q: queue of interest * * Leave bypass mode and restore the normal queueing behavior. + * + * Note: although blk_queue_bypass_start() is only called for blk-sq queues, + * this function is called for both blk-sq and blk-mq queues. */ void blk_queue_bypass_end(struct request_queue *q) { @@ -732,7 +823,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) if (q->id < 0) goto fail_q; - q->bio_split = bioset_create(BIO_POOL_SIZE, 0); + q->bio_split = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); if (!q->bio_split) goto fail_id; @@ -878,6 +969,8 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio); int blk_init_allocated_queue(struct request_queue *q) { + WARN_ON_ONCE(q->mq_ops); + q->fq = blk_alloc_flush_queue(q, NUMA_NO_NODE, q->cmd_size); if (!q->fq) return -ENOMEM; @@ -1015,6 +1108,8 @@ int blk_update_nr_requests(struct request_queue *q, unsigned int nr) struct request_list *rl; int on_thresh, off_thresh; + WARN_ON_ONCE(q->mq_ops); + spin_lock_irq(q->queue_lock); q->nr_requests = nr; blk_queue_congestion_threshold(q); @@ -1077,6 +1172,8 @@ static struct request *__get_request(struct request_list *rl, unsigned int op, int may_queue; req_flags_t rq_flags = RQF_ALLOCED; + lockdep_assert_held(q->queue_lock); + if (unlikely(blk_queue_dying(q))) return ERR_PTR(-ENODEV); @@ -1250,12 +1347,20 @@ static struct request *get_request(struct request_queue *q, unsigned int op, struct request_list *rl; struct request *rq; + lockdep_assert_held(q->queue_lock); + WARN_ON_ONCE(q->mq_ops); + rl = blk_get_rl(q, bio); /* transferred to @rq on success */ retry: rq = __get_request(rl, op, bio, gfp_mask); if (!IS_ERR(rq)) return rq; + if (op & REQ_NOWAIT) { + blk_put_rl(rl); + return ERR_PTR(-EAGAIN); + } + if (!gfpflags_allow_blocking(gfp_mask) || unlikely(blk_queue_dying(q))) { blk_put_rl(rl); return rq; @@ -1283,16 +1388,18 @@ retry: goto retry; } -static struct request *blk_old_get_request(struct request_queue *q, int rw, - gfp_t gfp_mask) +static struct request *blk_old_get_request(struct request_queue *q, + unsigned int op, gfp_t gfp_mask) { struct request *rq; + WARN_ON_ONCE(q->mq_ops); + /* create ioc upfront */ create_io_context(gfp_mask, q->node); spin_lock_irq(q->queue_lock); - rq = get_request(q, rw, NULL, gfp_mask); + rq = get_request(q, op, NULL, gfp_mask); if (IS_ERR(rq)) { spin_unlock_irq(q->queue_lock); return rq; @@ -1305,14 +1412,24 @@ static struct request *blk_old_get_request(struct request_queue *q, int rw, return rq; } -struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask) +struct request *blk_get_request(struct request_queue *q, unsigned int op, + gfp_t gfp_mask) { - if (q->mq_ops) - return blk_mq_alloc_request(q, rw, + struct request *req; + + if (q->mq_ops) { + req = blk_mq_alloc_request(q, op, (gfp_mask & __GFP_DIRECT_RECLAIM) ? 0 : BLK_MQ_REQ_NOWAIT); - else - return blk_old_get_request(q, rw, gfp_mask); + if (!IS_ERR(req) && q->mq_ops->initialize_rq_fn) + q->mq_ops->initialize_rq_fn(req); + } else { + req = blk_old_get_request(q, op, gfp_mask); + if (!IS_ERR(req) && q->initialize_rq_fn) + q->initialize_rq_fn(req); + } + + return req; } EXPORT_SYMBOL(blk_get_request); @@ -1328,6 +1445,9 @@ EXPORT_SYMBOL(blk_get_request); */ void blk_requeue_request(struct request_queue *q, struct request *rq) { + lockdep_assert_held(q->queue_lock); + WARN_ON_ONCE(q->mq_ops); + blk_delete_timer(rq); blk_clear_rq_complete(rq); trace_block_rq_requeue(q, rq); @@ -1402,9 +1522,6 @@ static void blk_pm_put_request(struct request *rq) static inline void blk_pm_put_request(struct request *rq) {} #endif -/* - * queue lock must be held - */ void __blk_put_request(struct request_queue *q, struct request *req) { req_flags_t rq_flags = req->rq_flags; @@ -1417,6 +1534,8 @@ void __blk_put_request(struct request_queue *q, struct request *req) return; } + lockdep_assert_held(q->queue_lock); + blk_pm_put_request(req); elv_completed_request(q, req); @@ -1646,6 +1765,7 @@ void blk_init_request_from_bio(struct request *req, struct bio *bio) req->ioprio = ioc->ioprio; else req->ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0); + req->write_hint = bio->bi_write_hint; blk_rq_bio_prep(req->q, req, bio); } EXPORT_SYMBOL_GPL(blk_init_request_from_bio); @@ -1665,10 +1785,10 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio) */ blk_queue_bounce(q, &bio); - blk_queue_split(q, &bio, q->bio_split); + blk_queue_split(q, &bio); if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) { - bio->bi_error = -EIO; + bio->bi_status = BLK_STS_IOERR; bio_endio(bio); return BLK_QC_T_NONE; } @@ -1726,7 +1846,10 @@ get_rq: req = get_request(q, bio->bi_opf, bio, GFP_NOIO); if (IS_ERR(req)) { __wbt_done(q->rq_wb, wb_acct); - bio->bi_error = PTR_ERR(req); + if (PTR_ERR(req) == -ENOMEM) + bio->bi_status = BLK_STS_RESOURCE; + else + bio->bi_status = BLK_STS_IOERR; bio_endio(bio); goto out_unlock; } @@ -1881,7 +2004,7 @@ generic_make_request_checks(struct bio *bio) { struct request_queue *q; int nr_sectors = bio_sectors(bio); - int err = -EIO; + blk_status_t status = BLK_STS_IOERR; char b[BDEVNAME_SIZE]; struct hd_struct *part; @@ -1900,6 +2023,14 @@ generic_make_request_checks(struct bio *bio) goto end_io; } + /* + * For a REQ_NOWAIT based request, return -EOPNOTSUPP + * if queue is not a request based queue. + */ + + if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_rq_based(q)) + goto not_supported; + part = bio->bi_bdev->bd_part; if (should_fail_request(part, bio->bi_iter.bi_size) || should_fail_request(&part_to_disk(part)->part0, @@ -1924,7 +2055,7 @@ generic_make_request_checks(struct bio *bio) !test_bit(QUEUE_FLAG_WC, &q->queue_flags)) { bio->bi_opf &= ~(REQ_PREFLUSH | REQ_FUA); if (!nr_sectors) { - err = 0; + status = BLK_STS_OK; goto end_io; } } @@ -1976,9 +2107,9 @@ generic_make_request_checks(struct bio *bio) return true; not_supported: - err = -EOPNOTSUPP; + status = BLK_STS_NOTSUPP; end_io: - bio->bi_error = err; + bio->bi_status = status; bio_endio(bio); return false; } @@ -2057,7 +2188,7 @@ blk_qc_t generic_make_request(struct bio *bio) do { struct request_queue *q = bdev_get_queue(bio->bi_bdev); - if (likely(blk_queue_enter(q, false) == 0)) { + if (likely(blk_queue_enter(q, bio->bi_opf & REQ_NOWAIT) == 0)) { struct bio_list lower, same; /* Create a fresh bio_list for all subordinate requests */ @@ -2082,7 +2213,11 @@ blk_qc_t generic_make_request(struct bio *bio) bio_list_merge(&bio_list_on_stack[0], &same); bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]); } else { - bio_io_error(bio); + if (unlikely(!blk_queue_dying(q) && + (bio->bi_opf & REQ_NOWAIT))) + bio_wouldblock_error(bio); + else + bio_io_error(bio); } bio = bio_list_pop(&bio_list_on_stack[0]); } while (bio); @@ -2183,29 +2318,29 @@ static int blk_cloned_rq_check_limits(struct request_queue *q, * @q: the queue to submit the request * @rq: the request being queued */ -int blk_insert_cloned_request(struct request_queue *q, struct request *rq) +blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq) { unsigned long flags; int where = ELEVATOR_INSERT_BACK; if (blk_cloned_rq_check_limits(q, rq)) - return -EIO; + return BLK_STS_IOERR; if (rq->rq_disk && should_fail_request(&rq->rq_disk->part0, blk_rq_bytes(rq))) - return -EIO; + return BLK_STS_IOERR; if (q->mq_ops) { if (blk_queue_io_stat(q)) blk_account_io_start(rq, true); blk_mq_sched_insert_request(rq, false, true, false, false); - return 0; + return BLK_STS_OK; } spin_lock_irqsave(q->queue_lock, flags); if (unlikely(blk_queue_dying(q))) { spin_unlock_irqrestore(q->queue_lock, flags); - return -ENODEV; + return BLK_STS_IOERR; } /* @@ -2222,7 +2357,7 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq) __blk_run_queue(q); spin_unlock_irqrestore(q->queue_lock, flags); - return 0; + return BLK_STS_OK; } EXPORT_SYMBOL_GPL(blk_insert_cloned_request); @@ -2238,9 +2373,6 @@ EXPORT_SYMBOL_GPL(blk_insert_cloned_request); * * Return: * The number of bytes to fail. - * - * Context: - * queue_lock must be held. */ unsigned int blk_rq_err_bytes(const struct request *rq) { @@ -2380,15 +2512,15 @@ void blk_account_io_start(struct request *rq, bool new_io) * Return: * Pointer to the request at the top of @q if available. Null * otherwise. - * - * Context: - * queue_lock must be held. */ struct request *blk_peek_request(struct request_queue *q) { struct request *rq; int ret; + lockdep_assert_held(q->queue_lock); + WARN_ON_ONCE(q->mq_ops); + while ((rq = __elv_next_request(q)) != NULL) { rq = blk_pm_peek_request(q, rq); @@ -2456,15 +2588,14 @@ struct request *blk_peek_request(struct request_queue *q) rq = NULL; break; } else if (ret == BLKPREP_KILL || ret == BLKPREP_INVALID) { - int err = (ret == BLKPREP_INVALID) ? -EREMOTEIO : -EIO; - rq->rq_flags |= RQF_QUIET; /* * Mark this request as started so we don't trigger * any debug logic in the end I/O path. */ blk_start_request(rq); - __blk_end_request_all(rq, err); + __blk_end_request_all(rq, ret == BLKPREP_INVALID ? + BLK_STS_TARGET : BLK_STS_IOERR); } else { printk(KERN_ERR "%s: bad return=%d\n", __func__, ret); break; @@ -2505,12 +2636,12 @@ void blk_dequeue_request(struct request *rq) * * Block internal functions which don't want to start timer should * call blk_dequeue_request(). - * - * Context: - * queue_lock must be held. */ void blk_start_request(struct request *req) { + lockdep_assert_held(req->q->queue_lock); + WARN_ON_ONCE(req->q->mq_ops); + blk_dequeue_request(req); if (test_bit(QUEUE_FLAG_STATS, &req->q->queue_flags)) { @@ -2535,14 +2666,14 @@ EXPORT_SYMBOL(blk_start_request); * Return: * Pointer to the request at the top of @q if available. Null * otherwise. - * - * Context: - * queue_lock must be held. */ struct request *blk_fetch_request(struct request_queue *q) { struct request *rq; + lockdep_assert_held(q->queue_lock); + WARN_ON_ONCE(q->mq_ops); + rq = blk_peek_request(q); if (rq) blk_start_request(rq); @@ -2553,7 +2684,7 @@ EXPORT_SYMBOL(blk_fetch_request); /** * blk_update_request - Special helper function for request stacking drivers * @req: the request being processed - * @error: %0 for success, < %0 for error + * @error: block status code * @nr_bytes: number of bytes to complete @req * * Description: @@ -2572,49 +2703,19 @@ EXPORT_SYMBOL(blk_fetch_request); * %false - this request doesn't have any more data * %true - this request has more data **/ -bool blk_update_request(struct request *req, int error, unsigned int nr_bytes) +bool blk_update_request(struct request *req, blk_status_t error, + unsigned int nr_bytes) { int total_bytes; - trace_block_rq_complete(req, error, nr_bytes); + trace_block_rq_complete(req, blk_status_to_errno(error), nr_bytes); if (!req->bio) return false; - if (error && !blk_rq_is_passthrough(req) && - !(req->rq_flags & RQF_QUIET)) { - char *error_type; - - switch (error) { - case -ENOLINK: - error_type = "recoverable transport"; - break; - case -EREMOTEIO: - error_type = "critical target"; - break; - case -EBADE: - error_type = "critical nexus"; - break; - case -ETIMEDOUT: - error_type = "timeout"; - break; - case -ENOSPC: - error_type = "critical space allocation"; - break; - case -ENODATA: - error_type = "critical medium"; - break; - case -EIO: - default: - error_type = "I/O"; - break; - } - printk_ratelimited(KERN_ERR "%s: %s error, dev %s, sector %llu\n", - __func__, error_type, req->rq_disk ? - req->rq_disk->disk_name : "?", - (unsigned long long)blk_rq_pos(req)); - - } + if (unlikely(error && !blk_rq_is_passthrough(req) && + !(req->rq_flags & RQF_QUIET))) + print_req_error(req, error); blk_account_io_completion(req, nr_bytes); @@ -2680,7 +2781,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes) } EXPORT_SYMBOL_GPL(blk_update_request); -static bool blk_update_bidi_request(struct request *rq, int error, +static bool blk_update_bidi_request(struct request *rq, blk_status_t error, unsigned int nr_bytes, unsigned int bidi_bytes) { @@ -2718,13 +2819,13 @@ void blk_unprep_request(struct request *req) } EXPORT_SYMBOL_GPL(blk_unprep_request); -/* - * queue lock must be held - */ -void blk_finish_request(struct request *req, int error) +void blk_finish_request(struct request *req, blk_status_t error) { struct request_queue *q = req->q; + lockdep_assert_held(req->q->queue_lock); + WARN_ON_ONCE(q->mq_ops); + if (req->rq_flags & RQF_STATS) blk_stat_add(req); @@ -2758,7 +2859,7 @@ EXPORT_SYMBOL(blk_finish_request); /** * blk_end_bidi_request - Complete a bidi request * @rq: the request to complete - * @error: %0 for success, < %0 for error + * @error: block status code * @nr_bytes: number of bytes to complete @rq * @bidi_bytes: number of bytes to complete @rq->next_rq * @@ -2772,12 +2873,14 @@ EXPORT_SYMBOL(blk_finish_request); * %false - we are done with this request * %true - still buffers pending for this request **/ -static bool blk_end_bidi_request(struct request *rq, int error, +static bool blk_end_bidi_request(struct request *rq, blk_status_t error, unsigned int nr_bytes, unsigned int bidi_bytes) { struct request_queue *q = rq->q; unsigned long flags; + WARN_ON_ONCE(q->mq_ops); + if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes)) return true; @@ -2791,7 +2894,7 @@ static bool blk_end_bidi_request(struct request *rq, int error, /** * __blk_end_bidi_request - Complete a bidi request with queue lock held * @rq: the request to complete - * @error: %0 for success, < %0 for error + * @error: block status code * @nr_bytes: number of bytes to complete @rq * @bidi_bytes: number of bytes to complete @rq->next_rq * @@ -2803,9 +2906,12 @@ static bool blk_end_bidi_request(struct request *rq, int error, * %false - we are done with this request * %true - still buffers pending for this request **/ -static bool __blk_end_bidi_request(struct request *rq, int error, +static bool __blk_end_bidi_request(struct request *rq, blk_status_t error, unsigned int nr_bytes, unsigned int bidi_bytes) { + lockdep_assert_held(rq->q->queue_lock); + WARN_ON_ONCE(rq->q->mq_ops); + if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes)) return true; @@ -2817,7 +2923,7 @@ static bool __blk_end_bidi_request(struct request *rq, int error, /** * blk_end_request - Helper function for drivers to complete the request. * @rq: the request being processed - * @error: %0 for success, < %0 for error + * @error: block status code * @nr_bytes: number of bytes to complete * * Description: @@ -2828,8 +2934,10 @@ static bool __blk_end_bidi_request(struct request *rq, int error, * %false - we are done with this request * %true - still buffers pending for this request **/ -bool blk_end_request(struct request *rq, int error, unsigned int nr_bytes) +bool blk_end_request(struct request *rq, blk_status_t error, + unsigned int nr_bytes) { + WARN_ON_ONCE(rq->q->mq_ops); return blk_end_bidi_request(rq, error, nr_bytes, 0); } EXPORT_SYMBOL(blk_end_request); @@ -2837,12 +2945,12 @@ EXPORT_SYMBOL(blk_end_request); /** * blk_end_request_all - Helper function for drives to finish the request. * @rq: the request to finish - * @error: %0 for success, < %0 for error + * @error: block status code * * Description: * Completely finish @rq. */ -void blk_end_request_all(struct request *rq, int error) +void blk_end_request_all(struct request *rq, blk_status_t error) { bool pending; unsigned int bidi_bytes = 0; @@ -2858,7 +2966,7 @@ EXPORT_SYMBOL(blk_end_request_all); /** * __blk_end_request - Helper function for drivers to complete the request. * @rq: the request being processed - * @error: %0 for success, < %0 for error + * @error: block status code * @nr_bytes: number of bytes to complete * * Description: @@ -2868,8 +2976,12 @@ EXPORT_SYMBOL(blk_end_request_all); * %false - we are done with this request * %true - still buffers pending for this request **/ -bool __blk_end_request(struct request *rq, int error, unsigned int nr_bytes) +bool __blk_end_request(struct request *rq, blk_status_t error, + unsigned int nr_bytes) { + lockdep_assert_held(rq->q->queue_lock); + WARN_ON_ONCE(rq->q->mq_ops); + return __blk_end_bidi_request(rq, error, nr_bytes, 0); } EXPORT_SYMBOL(__blk_end_request); @@ -2877,16 +2989,19 @@ EXPORT_SYMBOL(__blk_end_request); /** * __blk_end_request_all - Helper function for drives to finish the request. * @rq: the request to finish - * @error: %0 for success, < %0 for error + * @error: block status code * * Description: * Completely finish @rq. Must be called with queue lock held. */ -void __blk_end_request_all(struct request *rq, int error) +void __blk_end_request_all(struct request *rq, blk_status_t error) { bool pending; unsigned int bidi_bytes = 0; + lockdep_assert_held(rq->q->queue_lock); + WARN_ON_ONCE(rq->q->mq_ops); + if (unlikely(blk_bidi_rq(rq))) bidi_bytes = blk_rq_bytes(rq->next_rq); @@ -2898,7 +3013,7 @@ EXPORT_SYMBOL(__blk_end_request_all); /** * __blk_end_request_cur - Helper function to finish the current request chunk. * @rq: the request to finish the current chunk for - * @error: %0 for success, < %0 for error + * @error: block status code * * Description: * Complete the current consecutively mapped chunk from @rq. Must @@ -2908,7 +3023,7 @@ EXPORT_SYMBOL(__blk_end_request_all); * %false - we are done with this request * %true - still buffers pending for this request */ -bool __blk_end_request_cur(struct request *rq, int error) +bool __blk_end_request_cur(struct request *rq, blk_status_t error) { return __blk_end_request(rq, error, blk_rq_cur_bytes(rq)); } @@ -3151,6 +3266,8 @@ static void queue_unplugged(struct request_queue *q, unsigned int depth, bool from_schedule) __releases(q->queue_lock) { + lockdep_assert_held(q->queue_lock); + trace_block_unplug(q, depth, !from_schedule); if (from_schedule) @@ -3249,7 +3366,7 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule) * Short-circuit if @q is dead */ if (unlikely(blk_queue_dying(q))) { - __blk_end_request_all(rq, -ENODEV); + __blk_end_request_all(rq, BLK_STS_IOERR); continue; } diff --git a/block/blk-exec.c b/block/blk-exec.c index a9451e3b8587..5c0f3dc446dc 100644 --- a/block/blk-exec.c +++ b/block/blk-exec.c @@ -16,7 +16,7 @@ * @rq: request to complete * @error: end I/O status of the request */ -static void blk_end_sync_rq(struct request *rq, int error) +static void blk_end_sync_rq(struct request *rq, blk_status_t error) { struct completion *waiting = rq->end_io_data; @@ -69,7 +69,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk, if (unlikely(blk_queue_dying(q))) { rq->rq_flags |= RQF_QUIET; - __blk_end_request_all(rq, -ENXIO); + __blk_end_request_all(rq, BLK_STS_IOERR); spin_unlock_irq(q->queue_lock); return; } diff --git a/block/blk-flush.c b/block/blk-flush.c index c4e0880b54bb..ed5fe322abba 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -164,7 +164,7 @@ static bool blk_flush_queue_rq(struct request *rq, bool add_front) */ static bool blk_flush_complete_seq(struct request *rq, struct blk_flush_queue *fq, - unsigned int seq, int error) + unsigned int seq, blk_status_t error) { struct request_queue *q = rq->q; struct list_head *pending = &fq->flush_queue[fq->flush_pending_idx]; @@ -216,7 +216,7 @@ static bool blk_flush_complete_seq(struct request *rq, return kicked | queued; } -static void flush_end_io(struct request *flush_rq, int error) +static void flush_end_io(struct request *flush_rq, blk_status_t error) { struct request_queue *q = flush_rq->q; struct list_head *running; @@ -341,11 +341,13 @@ static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq) return blk_flush_queue_rq(flush_rq, false); } -static void flush_data_end_io(struct request *rq, int error) +static void flush_data_end_io(struct request *rq, blk_status_t error) { struct request_queue *q = rq->q; struct blk_flush_queue *fq = blk_get_flush_queue(q, NULL); + lockdep_assert_held(q->queue_lock); + /* * Updating q->in_flight[] here for making this tag usable * early. Because in blk_queue_start_tag(), @@ -382,7 +384,7 @@ static void flush_data_end_io(struct request *rq, int error) blk_run_queue_async(q); } -static void mq_flush_data_end_io(struct request *rq, int error) +static void mq_flush_data_end_io(struct request *rq, blk_status_t error) { struct request_queue *q = rq->q; struct blk_mq_hw_ctx *hctx; @@ -411,9 +413,6 @@ static void mq_flush_data_end_io(struct request *rq, int error) * or __blk_mq_run_hw_queue() to dispatch request. * @rq is being submitted. Analyze what needs to be done and put it on the * right queue. - * - * CONTEXT: - * spin_lock_irq(q->queue_lock) in !mq case */ void blk_insert_flush(struct request *rq) { @@ -422,6 +421,9 @@ void blk_insert_flush(struct request *rq) unsigned int policy = blk_flush_policy(fflags, rq); struct blk_flush_queue *fq = blk_get_flush_queue(q, rq->mq_ctx); + if (!q->mq_ops) + lockdep_assert_held(q->queue_lock); + /* * @policy now records what operations need to be done. Adjust * REQ_PREFLUSH and FUA for the driver. diff --git a/block/blk-integrity.c b/block/blk-integrity.c index 0f891a9aff4d..feb30570eaf5 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -384,9 +384,9 @@ static struct kobj_type integrity_ktype = { .sysfs_ops = &integrity_ops, }; -static int blk_integrity_nop_fn(struct blk_integrity_iter *iter) +static blk_status_t blk_integrity_nop_fn(struct blk_integrity_iter *iter) { - return 0; + return BLK_STS_OK; } static const struct blk_integrity_profile nop_profile = { diff --git a/block/blk-map.c b/block/blk-map.c index 3b5cb863318f..2547016aa7aa 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -16,6 +16,8 @@ */ int blk_rq_append_bio(struct request *rq, struct bio *bio) { + blk_queue_bounce(rq->q, &bio); + if (!rq->bio) { blk_rq_bio_prep(rq->q, rq, bio); } else { @@ -72,15 +74,13 @@ static int __blk_rq_map_user_iov(struct request *rq, map_data->offset += bio->bi_iter.bi_size; orig_bio = bio; - blk_queue_bounce(q, &bio); /* * We link the bounce buffer in and could have to traverse it * later so we have to get a ref to prevent it from being freed */ - bio_get(bio); - ret = blk_rq_append_bio(rq, bio); + bio_get(bio); if (ret) { bio_endio(bio); __blk_rq_unmap_user(orig_bio); @@ -249,7 +249,6 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf, return ret; } - blk_queue_bounce(q, &rq->bio); return 0; } EXPORT_SYMBOL(blk_rq_map_kern); diff --git a/block/blk-merge.c b/block/blk-merge.c index 3990ae406341..99038830fb42 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -108,31 +108,9 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, bool do_split = true; struct bio *new = NULL; const unsigned max_sectors = get_max_io_size(q, bio); - unsigned bvecs = 0; bio_for_each_segment(bv, bio, iter) { /* - * With arbitrary bio size, the incoming bio may be very - * big. We have to split the bio into small bios so that - * each holds at most BIO_MAX_PAGES bvecs because - * bio_clone() can fail to allocate big bvecs. - * - * It should have been better to apply the limit per - * request queue in which bio_clone() is involved, - * instead of globally. The biggest blocker is the - * bio_clone() in bio bounce. - * - * If bio is splitted by this reason, we should have - * allowed to continue bios merging, but don't do - * that now for making the change simple. - * - * TODO: deal with bio bounce's bio_clone() gracefully - * and convert the global limit into per-queue limit. - */ - if (bvecs++ >= BIO_MAX_PAGES) - goto split; - - /* * If the queue doesn't support SG gaps and adding this * offset would create a gap, disallow it. */ @@ -202,8 +180,7 @@ split: return do_split ? new : NULL; } -void blk_queue_split(struct request_queue *q, struct bio **bio, - struct bio_set *bs) +void blk_queue_split(struct request_queue *q, struct bio **bio) { struct bio *split, *res; unsigned nsegs; @@ -211,13 +188,13 @@ void blk_queue_split(struct request_queue *q, struct bio **bio, switch (bio_op(*bio)) { case REQ_OP_DISCARD: case REQ_OP_SECURE_ERASE: - split = blk_bio_discard_split(q, *bio, bs, &nsegs); + split = blk_bio_discard_split(q, *bio, q->bio_split, &nsegs); break; case REQ_OP_WRITE_ZEROES: - split = blk_bio_write_zeroes_split(q, *bio, bs, &nsegs); + split = blk_bio_write_zeroes_split(q, *bio, q->bio_split, &nsegs); break; case REQ_OP_WRITE_SAME: - split = blk_bio_write_same_split(q, *bio, bs, &nsegs); + split = blk_bio_write_same_split(q, *bio, q->bio_split, &nsegs); break; default: split = blk_bio_segment_split(q, *bio, q->bio_split, &nsegs); @@ -671,6 +648,9 @@ static void blk_account_io_merge(struct request *req) static struct request *attempt_merge(struct request_queue *q, struct request *req, struct request *next) { + if (!q->mq_ops) + lockdep_assert_held(q->queue_lock); + if (!rq_mergeable(req) || !rq_mergeable(next)) return NULL; @@ -693,6 +673,13 @@ static struct request *attempt_merge(struct request_queue *q, return NULL; /* + * Don't allow merge of different write hints, or for a hint with + * non-hint IO. + */ + if (req->write_hint != next->write_hint) + return NULL; + + /* * If we are allowed to merge, then append bio list * from next to rq and release next. merge_requests_fn * will have updated segment counts, update sector @@ -811,6 +798,13 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio) !blk_write_same_mergeable(rq->bio, bio)) return false; + /* + * Don't allow merge of different write hints, or for a hint with + * non-hint IO. + */ + if (rq->write_hint != bio->bi_write_hint) + return false; + return true; } diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c index 8e61e8640e17..2cca4fc43f45 100644 --- a/block/blk-mq-cpumap.c +++ b/block/blk-mq-cpumap.c @@ -14,10 +14,15 @@ #include "blk.h" #include "blk-mq.h" -static int cpu_to_queue_index(unsigned int nr_cpus, unsigned int nr_queues, - const int cpu) +static int cpu_to_queue_index(unsigned int nr_queues, const int cpu, + const struct cpumask *online_mask) { - return cpu * nr_queues / nr_cpus; + /* + * Non online CPU will be mapped to queue index 0. + */ + if (!cpumask_test_cpu(cpu, online_mask)) + return 0; + return cpu % nr_queues; } static int get_first_sibling(unsigned int cpu) @@ -36,55 +41,26 @@ int blk_mq_map_queues(struct blk_mq_tag_set *set) unsigned int *map = set->mq_map; unsigned int nr_queues = set->nr_hw_queues; const struct cpumask *online_mask = cpu_online_mask; - unsigned int i, nr_cpus, nr_uniq_cpus, queue, first_sibling; - cpumask_var_t cpus; - - if (!alloc_cpumask_var(&cpus, GFP_ATOMIC)) - return -ENOMEM; - - cpumask_clear(cpus); - nr_cpus = nr_uniq_cpus = 0; - for_each_cpu(i, online_mask) { - nr_cpus++; - first_sibling = get_first_sibling(i); - if (!cpumask_test_cpu(first_sibling, cpus)) - nr_uniq_cpus++; - cpumask_set_cpu(i, cpus); - } - - queue = 0; - for_each_possible_cpu(i) { - if (!cpumask_test_cpu(i, online_mask)) { - map[i] = 0; - continue; - } + unsigned int cpu, first_sibling; + for_each_possible_cpu(cpu) { /* - * Easy case - we have equal or more hardware queues. Or - * there are no thread siblings to take into account. Do - * 1:1 if enough, or sequential mapping if less. + * First do sequential mapping between CPUs and queues. + * In case we still have CPUs to map, and we have some number of + * threads per cores then map sibling threads to the same queue for + * performace optimizations. */ - if (nr_queues >= nr_cpus || nr_cpus == nr_uniq_cpus) { - map[i] = cpu_to_queue_index(nr_cpus, nr_queues, queue); - queue++; - continue; + if (cpu < nr_queues) { + map[cpu] = cpu_to_queue_index(nr_queues, cpu, online_mask); + } else { + first_sibling = get_first_sibling(cpu); + if (first_sibling == cpu) + map[cpu] = cpu_to_queue_index(nr_queues, cpu, online_mask); + else + map[cpu] = map[first_sibling]; } - - /* - * Less then nr_cpus queues, and we have some number of - * threads per cores. Map sibling threads to the same - * queue. - */ - first_sibling = get_first_sibling(i); - if (first_sibling == i) { - map[i] = cpu_to_queue_index(nr_uniq_cpus, nr_queues, - queue); - queue++; - } else - map[i] = map[first_sibling]; } - free_cpumask_var(cpus); return 0; } EXPORT_SYMBOL_GPL(blk_mq_map_queues); diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 803aed4d7221..9ebc2945f991 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -114,10 +114,12 @@ static ssize_t queue_state_write(void *data, const char __user *buf, blk_mq_run_hw_queues(q, true); } else if (strcmp(op, "start") == 0) { blk_mq_start_stopped_hw_queues(q, true); + } else if (strcmp(op, "kick") == 0) { + blk_mq_kick_requeue_list(q); } else { pr_err("%s: unsupported operation '%s'\n", __func__, op); inval: - pr_err("%s: use either 'run' or 'start'\n", __func__); + pr_err("%s: use 'run', 'start' or 'kick'\n", __func__); return -EINVAL; } return count; @@ -133,6 +135,29 @@ static void print_stat(struct seq_file *m, struct blk_rq_stat *stat) } } +static int queue_write_hint_show(void *data, struct seq_file *m) +{ + struct request_queue *q = data; + int i; + + for (i = 0; i < BLK_MAX_WRITE_HINTS; i++) + seq_printf(m, "hint%d: %llu\n", i, q->write_hints[i]); + + return 0; +} + +static ssize_t queue_write_hint_store(void *data, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct request_queue *q = data; + int i; + + for (i = 0; i < BLK_MAX_WRITE_HINTS; i++) + q->write_hints[i] = 0; + + return count; +} + static int queue_poll_stat_show(void *data, struct seq_file *m) { struct request_queue *q = data; @@ -267,6 +292,14 @@ static const char *const rqf_name[] = { }; #undef RQF_NAME +#define RQAF_NAME(name) [REQ_ATOM_##name] = #name +static const char *const rqaf_name[] = { + RQAF_NAME(COMPLETE), + RQAF_NAME(STARTED), + RQAF_NAME(POLL_SLEPT), +}; +#undef RQAF_NAME + int __blk_mq_debugfs_rq_show(struct seq_file *m, struct request *rq) { const struct blk_mq_ops *const mq_ops = rq->q->mq_ops; @@ -283,6 +316,8 @@ int __blk_mq_debugfs_rq_show(struct seq_file *m, struct request *rq) seq_puts(m, ", .rq_flags="); blk_flags_show(m, (__force unsigned int)rq->rq_flags, rqf_name, ARRAY_SIZE(rqf_name)); + seq_puts(m, ", .atomic_flags="); + blk_flags_show(m, rq->atomic_flags, rqaf_name, ARRAY_SIZE(rqaf_name)); seq_printf(m, ", .tag=%d, .internal_tag=%d", rq->tag, rq->internal_tag); if (mq_ops->show_rq) @@ -298,6 +333,37 @@ int blk_mq_debugfs_rq_show(struct seq_file *m, void *v) } EXPORT_SYMBOL_GPL(blk_mq_debugfs_rq_show); +static void *queue_requeue_list_start(struct seq_file *m, loff_t *pos) + __acquires(&q->requeue_lock) +{ + struct request_queue *q = m->private; + + spin_lock_irq(&q->requeue_lock); + return seq_list_start(&q->requeue_list, *pos); +} + +static void *queue_requeue_list_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct request_queue *q = m->private; + + return seq_list_next(v, &q->requeue_list, pos); +} + +static void queue_requeue_list_stop(struct seq_file *m, void *v) + __releases(&q->requeue_lock) +{ + struct request_queue *q = m->private; + + spin_unlock_irq(&q->requeue_lock); +} + +static const struct seq_operations queue_requeue_list_seq_ops = { + .start = queue_requeue_list_start, + .next = queue_requeue_list_next, + .stop = queue_requeue_list_stop, + .show = blk_mq_debugfs_rq_show, +}; + static void *hctx_dispatch_start(struct seq_file *m, loff_t *pos) __acquires(&hctx->lock) { @@ -329,6 +395,36 @@ static const struct seq_operations hctx_dispatch_seq_ops = { .show = blk_mq_debugfs_rq_show, }; +struct show_busy_params { + struct seq_file *m; + struct blk_mq_hw_ctx *hctx; +}; + +/* + * Note: the state of a request may change while this function is in progress, + * e.g. due to a concurrent blk_mq_finish_request() call. + */ +static void hctx_show_busy_rq(struct request *rq, void *data, bool reserved) +{ + const struct show_busy_params *params = data; + + if (blk_mq_map_queue(rq->q, rq->mq_ctx->cpu) == params->hctx && + test_bit(REQ_ATOM_STARTED, &rq->atomic_flags)) + __blk_mq_debugfs_rq_show(params->m, + list_entry_rq(&rq->queuelist)); +} + +static int hctx_busy_show(void *data, struct seq_file *m) +{ + struct blk_mq_hw_ctx *hctx = data; + struct show_busy_params params = { .m = m, .hctx = hctx }; + + blk_mq_tagset_busy_iter(hctx->queue->tag_set, hctx_show_busy_rq, + ¶ms); + + return 0; +} + static int hctx_ctx_map_show(void *data, struct seq_file *m) { struct blk_mq_hw_ctx *hctx = data; @@ -655,7 +751,9 @@ const struct file_operations blk_mq_debugfs_fops = { static const struct blk_mq_debugfs_attr blk_mq_debugfs_queue_attrs[] = { {"poll_stat", 0400, queue_poll_stat_show}, + {"requeue_list", 0400, .seq_ops = &queue_requeue_list_seq_ops}, {"state", 0600, queue_state_show, queue_state_write}, + {"write_hints", 0600, queue_write_hint_show, queue_write_hint_store}, {}, }; @@ -663,6 +761,7 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = { {"state", 0400, hctx_state_show}, {"flags", 0400, hctx_flags_show}, {"dispatch", 0400, .seq_ops = &hctx_dispatch_seq_ops}, + {"busy", 0400, hctx_busy_show}, {"ctx_map", 0400, hctx_ctx_map_show}, {"tags", 0400, hctx_tags_show}, {"tags_bitmap", 0400, hctx_tags_bitmap_show}, diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 1f5b692526ae..7f0dc48ffb40 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -31,11 +31,10 @@ void blk_mq_sched_free_hctx_data(struct request_queue *q, } EXPORT_SYMBOL_GPL(blk_mq_sched_free_hctx_data); -static void __blk_mq_sched_assign_ioc(struct request_queue *q, - struct request *rq, - struct bio *bio, - struct io_context *ioc) +void blk_mq_sched_assign_ioc(struct request *rq, struct bio *bio) { + struct request_queue *q = rq->q; + struct io_context *ioc = rq_ioc(bio); struct io_cq *icq; spin_lock_irq(q->queue_lock); @@ -47,90 +46,47 @@ static void __blk_mq_sched_assign_ioc(struct request_queue *q, if (!icq) return; } - + get_io_context(icq->ioc); rq->elv.icq = icq; - if (!blk_mq_sched_get_rq_priv(q, rq, bio)) { - rq->rq_flags |= RQF_ELVPRIV; - get_io_context(icq->ioc); - return; - } - - rq->elv.icq = NULL; } -static void blk_mq_sched_assign_ioc(struct request_queue *q, - struct request *rq, struct bio *bio) +/* + * Mark a hardware queue as needing a restart. For shared queues, maintain + * a count of how many hardware queues are marked for restart. + */ +static void blk_mq_sched_mark_restart_hctx(struct blk_mq_hw_ctx *hctx) { - struct io_context *ioc; + if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) + return; + + if (hctx->flags & BLK_MQ_F_TAG_SHARED) { + struct request_queue *q = hctx->queue; - ioc = rq_ioc(bio); - if (ioc) - __blk_mq_sched_assign_ioc(q, rq, bio, ioc); + if (!test_and_set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) + atomic_inc(&q->shared_hctx_restart); + } else + set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state); } -struct request *blk_mq_sched_get_request(struct request_queue *q, - struct bio *bio, - unsigned int op, - struct blk_mq_alloc_data *data) +static bool blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx) { - struct elevator_queue *e = q->elevator; - struct request *rq; - - blk_queue_enter_live(q); - data->q = q; - if (likely(!data->ctx)) - data->ctx = blk_mq_get_ctx(q); - if (likely(!data->hctx)) - data->hctx = blk_mq_map_queue(q, data->ctx->cpu); - - if (e) { - data->flags |= BLK_MQ_REQ_INTERNAL; - - /* - * Flush requests are special and go directly to the - * dispatch list. - */ - if (!op_is_flush(op) && e->type->ops.mq.get_request) { - rq = e->type->ops.mq.get_request(q, op, data); - if (rq) - rq->rq_flags |= RQF_QUEUED; - } else - rq = __blk_mq_alloc_request(data, op); - } else { - rq = __blk_mq_alloc_request(data, op); - } - - if (rq) { - if (!op_is_flush(op)) { - rq->elv.icq = NULL; - if (e && e->type->icq_cache) - blk_mq_sched_assign_ioc(q, rq, bio); - } - data->hctx->queued++; - return rq; - } + if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) + return false; - blk_queue_exit(q); - return NULL; -} + if (hctx->flags & BLK_MQ_F_TAG_SHARED) { + struct request_queue *q = hctx->queue; -void blk_mq_sched_put_request(struct request *rq) -{ - struct request_queue *q = rq->q; - struct elevator_queue *e = q->elevator; + if (test_and_clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) + atomic_dec(&q->shared_hctx_restart); + } else + clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state); - if (rq->rq_flags & RQF_ELVPRIV) { - blk_mq_sched_put_rq_priv(rq->q, rq); - if (rq->elv.icq) { - put_io_context(rq->elv.icq->ioc); - rq->elv.icq = NULL; - } + if (blk_mq_hctx_has_pending(hctx)) { + blk_mq_run_hw_queue(hctx, true); + return true; } - if ((rq->rq_flags & RQF_QUEUED) && e && e->type->ops.mq.put_request) - e->type->ops.mq.put_request(rq); - else - blk_mq_finish_request(rq); + return false; } void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx) @@ -141,7 +97,8 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx) bool did_work = false; LIST_HEAD(rq_list); - if (unlikely(blk_mq_hctx_stopped(hctx))) + /* RCU or SRCU read lock is needed before checking quiesced flag */ + if (unlikely(blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q))) return; hctx->run++; @@ -221,19 +178,73 @@ bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio, } EXPORT_SYMBOL_GPL(blk_mq_sched_try_merge); +/* + * Reverse check our software queue for entries that we could potentially + * merge with. Currently includes a hand-wavy stop count of 8, to not spend + * too much time checking for merges. + */ +static bool blk_mq_attempt_merge(struct request_queue *q, + struct blk_mq_ctx *ctx, struct bio *bio) +{ + struct request *rq; + int checked = 8; + + lockdep_assert_held(&ctx->lock); + + list_for_each_entry_reverse(rq, &ctx->rq_list, queuelist) { + bool merged = false; + + if (!checked--) + break; + + if (!blk_rq_merge_ok(rq, bio)) + continue; + + switch (blk_try_merge(rq, bio)) { + case ELEVATOR_BACK_MERGE: + if (blk_mq_sched_allow_merge(q, rq, bio)) + merged = bio_attempt_back_merge(q, rq, bio); + break; + case ELEVATOR_FRONT_MERGE: + if (blk_mq_sched_allow_merge(q, rq, bio)) + merged = bio_attempt_front_merge(q, rq, bio); + break; + case ELEVATOR_DISCARD_MERGE: + merged = bio_attempt_discard_merge(q, rq, bio); + break; + default: + continue; + } + + if (merged) + ctx->rq_merged++; + return merged; + } + + return false; +} + bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio) { struct elevator_queue *e = q->elevator; + struct blk_mq_ctx *ctx = blk_mq_get_ctx(q); + struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu); + bool ret = false; - if (e->type->ops.mq.bio_merge) { - struct blk_mq_ctx *ctx = blk_mq_get_ctx(q); - struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu); - + if (e && e->type->ops.mq.bio_merge) { blk_mq_put_ctx(ctx); return e->type->ops.mq.bio_merge(hctx, bio); } - return false; + if (hctx->flags & BLK_MQ_F_SHOULD_MERGE) { + /* default per sw-queue merge */ + spin_lock(&ctx->lock); + ret = blk_mq_attempt_merge(q, ctx, bio); + spin_unlock(&ctx->lock); + } + + blk_mq_put_ctx(ctx); + return ret; } bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq) @@ -266,18 +277,6 @@ static bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx, return true; } -static bool blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx) -{ - if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) { - clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state); - if (blk_mq_hctx_has_pending(hctx)) { - blk_mq_run_hw_queue(hctx, true); - return true; - } - } - return false; -} - /** * list_for_each_entry_rcu_rr - iterate in a round-robin fashion over rcu list * @pos: loop cursor. @@ -309,6 +308,13 @@ void blk_mq_sched_restart(struct blk_mq_hw_ctx *const hctx) unsigned int i, j; if (set->flags & BLK_MQ_F_TAG_SHARED) { + /* + * If this is 0, then we know that no hardware queues + * have RESTART marked. We're done. + */ + if (!atomic_read(&queue->shared_hctx_restart)) + return; + rcu_read_lock(); list_for_each_entry_rcu_rr(q, queue, &set->tag_list, tag_set_list) { diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h index edafb5383b7b..9267d0b7c197 100644 --- a/block/blk-mq-sched.h +++ b/block/blk-mq-sched.h @@ -7,8 +7,7 @@ void blk_mq_sched_free_hctx_data(struct request_queue *q, void (*exit)(struct blk_mq_hw_ctx *)); -struct request *blk_mq_sched_get_request(struct request_queue *q, struct bio *bio, unsigned int op, struct blk_mq_alloc_data *data); -void blk_mq_sched_put_request(struct request *rq); +void blk_mq_sched_assign_ioc(struct request *rq, struct bio *bio); void blk_mq_sched_request_inserted(struct request *rq); bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio, @@ -38,35 +37,12 @@ int blk_mq_sched_init(struct request_queue *q); static inline bool blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio) { - struct elevator_queue *e = q->elevator; - - if (!e || blk_queue_nomerges(q) || !bio_mergeable(bio)) + if (blk_queue_nomerges(q) || !bio_mergeable(bio)) return false; return __blk_mq_sched_bio_merge(q, bio); } -static inline int blk_mq_sched_get_rq_priv(struct request_queue *q, - struct request *rq, - struct bio *bio) -{ - struct elevator_queue *e = q->elevator; - - if (e && e->type->ops.mq.get_rq_priv) - return e->type->ops.mq.get_rq_priv(q, rq, bio); - - return 0; -} - -static inline void blk_mq_sched_put_rq_priv(struct request_queue *q, - struct request *rq) -{ - struct elevator_queue *e = q->elevator; - - if (e && e->type->ops.mq.put_rq_priv) - e->type->ops.mq.put_rq_priv(q, rq); -} - static inline bool blk_mq_sched_allow_merge(struct request_queue *q, struct request *rq, struct bio *bio) @@ -115,15 +91,6 @@ static inline bool blk_mq_sched_has_work(struct blk_mq_hw_ctx *hctx) return false; } -/* - * Mark a hardware queue as needing a restart. - */ -static inline void blk_mq_sched_mark_restart_hctx(struct blk_mq_hw_ctx *hctx) -{ - if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) - set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state); -} - static inline bool blk_mq_sched_needs_restart(struct blk_mq_hw_ctx *hctx) { return test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state); diff --git a/block/blk-mq.c b/block/blk-mq.c index bb66c96850b1..ced2b000ca02 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -42,7 +42,6 @@ static LIST_HEAD(all_q_list); static void blk_mq_poll_stats_start(struct request_queue *q); static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb); -static void __blk_mq_stop_hw_queues(struct request_queue *q, bool sync); static int blk_mq_poll_stats_bkt(const struct request *rq) { @@ -154,13 +153,28 @@ void blk_mq_unfreeze_queue(struct request_queue *q) } EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue); +/* + * FIXME: replace the scsi_internal_device_*block_nowait() calls in the + * mpt3sas driver such that this function can be removed. + */ +void blk_mq_quiesce_queue_nowait(struct request_queue *q) +{ + unsigned long flags; + + spin_lock_irqsave(q->queue_lock, flags); + queue_flag_set(QUEUE_FLAG_QUIESCED, q); + spin_unlock_irqrestore(q->queue_lock, flags); +} +EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue_nowait); + /** - * blk_mq_quiesce_queue() - wait until all ongoing queue_rq calls have finished + * blk_mq_quiesce_queue() - wait until all ongoing dispatches have finished * @q: request queue. * * Note: this function does not prevent that the struct request end_io() - * callback function is invoked. Additionally, it is not prevented that - * new queue_rq() calls occur unless the queue has been stopped first. + * callback function is invoked. Once this function is returned, we make + * sure no dispatch can happen until the queue is unquiesced via + * blk_mq_unquiesce_queue(). */ void blk_mq_quiesce_queue(struct request_queue *q) { @@ -168,11 +182,11 @@ void blk_mq_quiesce_queue(struct request_queue *q) unsigned int i; bool rcu = false; - __blk_mq_stop_hw_queues(q, true); + blk_mq_quiesce_queue_nowait(q); queue_for_each_hw_ctx(q, hctx, i) { if (hctx->flags & BLK_MQ_F_BLOCKING) - synchronize_srcu(&hctx->queue_rq_srcu); + synchronize_srcu(hctx->queue_rq_srcu); else rcu = true; } @@ -181,6 +195,26 @@ void blk_mq_quiesce_queue(struct request_queue *q) } EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue); +/* + * blk_mq_unquiesce_queue() - counterpart of blk_mq_quiesce_queue() + * @q: request queue. + * + * This function recovers queue into the state before quiescing + * which is done by blk_mq_quiesce_queue. + */ +void blk_mq_unquiesce_queue(struct request_queue *q) +{ + unsigned long flags; + + spin_lock_irqsave(q->queue_lock, flags); + queue_flag_clear(QUEUE_FLAG_QUIESCED, q); + spin_unlock_irqrestore(q->queue_lock, flags); + + /* dispatch requests which are inserted during quiescing */ + blk_mq_run_hw_queues(q, true); +} +EXPORT_SYMBOL_GPL(blk_mq_unquiesce_queue); + void blk_mq_wake_waiters(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; @@ -204,15 +238,33 @@ bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx) } EXPORT_SYMBOL(blk_mq_can_queue); -void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx, - struct request *rq, unsigned int op) +static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, + unsigned int tag, unsigned int op) { + struct blk_mq_tags *tags = blk_mq_tags_from_data(data); + struct request *rq = tags->static_rqs[tag]; + + rq->rq_flags = 0; + + if (data->flags & BLK_MQ_REQ_INTERNAL) { + rq->tag = -1; + rq->internal_tag = tag; + } else { + if (blk_mq_tag_busy(data->hctx)) { + rq->rq_flags = RQF_MQ_INFLIGHT; + atomic_inc(&data->hctx->nr_active); + } + rq->tag = tag; + rq->internal_tag = -1; + data->hctx->tags->rqs[rq->tag] = rq; + } + INIT_LIST_HEAD(&rq->queuelist); /* csd/requeue_work/fifo_time is initialized before use */ - rq->q = q; - rq->mq_ctx = ctx; + rq->q = data->q; + rq->mq_ctx = data->ctx; rq->cmd_flags = op; - if (blk_queue_io_stat(q)) + if (blk_queue_io_stat(data->q)) rq->rq_flags |= RQF_IO_STAT; /* do not touch atomic flags, it needs atomic ops against the timer */ rq->cpu = -1; @@ -241,44 +293,60 @@ void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx, rq->end_io_data = NULL; rq->next_rq = NULL; - ctx->rq_dispatched[op_is_sync(op)]++; + data->ctx->rq_dispatched[op_is_sync(op)]++; + return rq; } -EXPORT_SYMBOL_GPL(blk_mq_rq_ctx_init); -struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data, - unsigned int op) +static struct request *blk_mq_get_request(struct request_queue *q, + struct bio *bio, unsigned int op, + struct blk_mq_alloc_data *data) { + struct elevator_queue *e = q->elevator; struct request *rq; unsigned int tag; - tag = blk_mq_get_tag(data); - if (tag != BLK_MQ_TAG_FAIL) { - struct blk_mq_tags *tags = blk_mq_tags_from_data(data); + blk_queue_enter_live(q); + data->q = q; + if (likely(!data->ctx)) + data->ctx = blk_mq_get_ctx(q); + if (likely(!data->hctx)) + data->hctx = blk_mq_map_queue(q, data->ctx->cpu); + if (op & REQ_NOWAIT) + data->flags |= BLK_MQ_REQ_NOWAIT; - rq = tags->static_rqs[tag]; + if (e) { + data->flags |= BLK_MQ_REQ_INTERNAL; - if (data->flags & BLK_MQ_REQ_INTERNAL) { - rq->tag = -1; - rq->internal_tag = tag; - } else { - if (blk_mq_tag_busy(data->hctx)) { - rq->rq_flags = RQF_MQ_INFLIGHT; - atomic_inc(&data->hctx->nr_active); - } - rq->tag = tag; - rq->internal_tag = -1; - data->hctx->tags->rqs[rq->tag] = rq; - } + /* + * Flush requests are special and go directly to the + * dispatch list. + */ + if (!op_is_flush(op) && e->type->ops.mq.limit_depth) + e->type->ops.mq.limit_depth(op, data); + } - blk_mq_rq_ctx_init(data->q, data->ctx, rq, op); - return rq; + tag = blk_mq_get_tag(data); + if (tag == BLK_MQ_TAG_FAIL) { + blk_queue_exit(q); + return NULL; } - return NULL; + rq = blk_mq_rq_ctx_init(data, tag, op); + if (!op_is_flush(op)) { + rq->elv.icq = NULL; + if (e && e->type->ops.mq.prepare_request) { + if (e->type->icq_cache && rq_ioc(bio)) + blk_mq_sched_assign_ioc(rq, bio); + + e->type->ops.mq.prepare_request(rq, bio); + rq->rq_flags |= RQF_ELVPRIV; + } + } + data->hctx->queued++; + return rq; } -EXPORT_SYMBOL_GPL(__blk_mq_alloc_request); -struct request *blk_mq_alloc_request(struct request_queue *q, int rw, +struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op, unsigned int flags) { struct blk_mq_alloc_data alloc_data = { .flags = flags }; @@ -289,7 +357,7 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw, if (ret) return ERR_PTR(ret); - rq = blk_mq_sched_get_request(q, NULL, rw, &alloc_data); + rq = blk_mq_get_request(q, NULL, op, &alloc_data); blk_mq_put_ctx(alloc_data.ctx); blk_queue_exit(q); @@ -304,8 +372,8 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw, } EXPORT_SYMBOL(blk_mq_alloc_request); -struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int rw, - unsigned int flags, unsigned int hctx_idx) +struct request *blk_mq_alloc_request_hctx(struct request_queue *q, + unsigned int op, unsigned int flags, unsigned int hctx_idx) { struct blk_mq_alloc_data alloc_data = { .flags = flags }; struct request *rq; @@ -340,7 +408,7 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int rw, cpu = cpumask_first(alloc_data.hctx->cpumask); alloc_data.ctx = __blk_mq_get_ctx(q, cpu); - rq = blk_mq_sched_get_request(q, NULL, rw, &alloc_data); + rq = blk_mq_get_request(q, NULL, op, &alloc_data); blk_queue_exit(q); @@ -351,17 +419,28 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int rw, } EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx); -void __blk_mq_finish_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx, - struct request *rq) +void blk_mq_free_request(struct request *rq) { - const int sched_tag = rq->internal_tag; struct request_queue *q = rq->q; + struct elevator_queue *e = q->elevator; + struct blk_mq_ctx *ctx = rq->mq_ctx; + struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu); + const int sched_tag = rq->internal_tag; + + if (rq->rq_flags & RQF_ELVPRIV) { + if (e && e->type->ops.mq.finish_request) + e->type->ops.mq.finish_request(rq); + if (rq->elv.icq) { + put_io_context(rq->elv.icq->ioc); + rq->elv.icq = NULL; + } + } + ctx->rq_completed[rq_is_sync(rq)]++; if (rq->rq_flags & RQF_MQ_INFLIGHT) atomic_dec(&hctx->nr_active); wbt_done(q->rq_wb, &rq->issue_stat); - rq->rq_flags = 0; clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags); clear_bit(REQ_ATOM_POLL_SLEPT, &rq->atomic_flags); @@ -372,29 +451,9 @@ void __blk_mq_finish_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx, blk_mq_sched_restart(hctx); blk_queue_exit(q); } - -static void blk_mq_finish_hctx_request(struct blk_mq_hw_ctx *hctx, - struct request *rq) -{ - struct blk_mq_ctx *ctx = rq->mq_ctx; - - ctx->rq_completed[rq_is_sync(rq)]++; - __blk_mq_finish_request(hctx, ctx, rq); -} - -void blk_mq_finish_request(struct request *rq) -{ - blk_mq_finish_hctx_request(blk_mq_map_queue(rq->q, rq->mq_ctx->cpu), rq); -} -EXPORT_SYMBOL_GPL(blk_mq_finish_request); - -void blk_mq_free_request(struct request *rq) -{ - blk_mq_sched_put_request(rq); -} EXPORT_SYMBOL_GPL(blk_mq_free_request); -inline void __blk_mq_end_request(struct request *rq, int error) +inline void __blk_mq_end_request(struct request *rq, blk_status_t error) { blk_account_io_done(rq); @@ -409,7 +468,7 @@ inline void __blk_mq_end_request(struct request *rq, int error) } EXPORT_SYMBOL(__blk_mq_end_request); -void blk_mq_end_request(struct request *rq, int error) +void blk_mq_end_request(struct request *rq, blk_status_t error) { if (blk_update_request(rq, error, blk_rq_bytes(rq))) BUG(); @@ -753,50 +812,6 @@ static void blk_mq_timeout_work(struct work_struct *work) blk_queue_exit(q); } -/* - * Reverse check our software queue for entries that we could potentially - * merge with. Currently includes a hand-wavy stop count of 8, to not spend - * too much time checking for merges. - */ -static bool blk_mq_attempt_merge(struct request_queue *q, - struct blk_mq_ctx *ctx, struct bio *bio) -{ - struct request *rq; - int checked = 8; - - list_for_each_entry_reverse(rq, &ctx->rq_list, queuelist) { - bool merged = false; - - if (!checked--) - break; - - if (!blk_rq_merge_ok(rq, bio)) - continue; - - switch (blk_try_merge(rq, bio)) { - case ELEVATOR_BACK_MERGE: - if (blk_mq_sched_allow_merge(q, rq, bio)) - merged = bio_attempt_back_merge(q, rq, bio); - break; - case ELEVATOR_FRONT_MERGE: - if (blk_mq_sched_allow_merge(q, rq, bio)) - merged = bio_attempt_front_merge(q, rq, bio); - break; - case ELEVATOR_DISCARD_MERGE: - merged = bio_attempt_discard_merge(q, rq, bio); - break; - default: - continue; - } - - if (merged) - ctx->rq_merged++; - return merged; - } - - return false; -} - struct flush_busy_ctx_data { struct blk_mq_hw_ctx *hctx; struct list_head *list; @@ -926,14 +941,14 @@ static bool reorder_tags_to_front(struct list_head *list) return first != NULL; } -static int blk_mq_dispatch_wake(wait_queue_t *wait, unsigned mode, int flags, +static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode, int flags, void *key) { struct blk_mq_hw_ctx *hctx; hctx = container_of(wait, struct blk_mq_hw_ctx, dispatch_wait); - list_del(&wait->task_list); + list_del(&wait->entry); clear_bit_unlock(BLK_MQ_S_TAG_WAITING, &hctx->state); blk_mq_run_hw_queue(hctx, true); return 1; @@ -968,7 +983,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list) { struct blk_mq_hw_ctx *hctx; struct request *rq; - int errors, queued, ret = BLK_MQ_RQ_QUEUE_OK; + int errors, queued; if (list_empty(list)) return false; @@ -979,6 +994,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list) errors = queued = 0; do { struct blk_mq_queue_data bd; + blk_status_t ret; rq = list_first_entry(list, struct request, queuelist); if (!blk_mq_get_driver_tag(rq, &hctx, false)) { @@ -1019,25 +1035,20 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list) } ret = q->mq_ops->queue_rq(hctx, &bd); - switch (ret) { - case BLK_MQ_RQ_QUEUE_OK: - queued++; - break; - case BLK_MQ_RQ_QUEUE_BUSY: + if (ret == BLK_STS_RESOURCE) { blk_mq_put_driver_tag_hctx(hctx, rq); list_add(&rq->queuelist, list); __blk_mq_requeue_request(rq); break; - default: - pr_err("blk-mq: bad return on queue: %d\n", ret); - case BLK_MQ_RQ_QUEUE_ERROR: + } + + if (unlikely(ret != BLK_STS_OK)) { errors++; - blk_mq_end_request(rq, -EIO); - break; + blk_mq_end_request(rq, BLK_STS_IOERR); + continue; } - if (ret == BLK_MQ_RQ_QUEUE_BUSY) - break; + queued++; } while (!list_empty(list)); hctx->dispatched[queued_to_index(queued)]++; @@ -1075,7 +1086,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list) * - blk_mq_run_hw_queue() checks whether or not a queue has * been stopped before rerunning a queue. * - Some but not all block drivers stop a queue before - * returning BLK_MQ_RQ_QUEUE_BUSY. Two exceptions are scsi-mq + * returning BLK_STS_RESOURCE. Two exceptions are scsi-mq * and dm-rq. */ if (!blk_mq_sched_needs_restart(hctx) && @@ -1100,9 +1111,9 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx) } else { might_sleep(); - srcu_idx = srcu_read_lock(&hctx->queue_rq_srcu); + srcu_idx = srcu_read_lock(hctx->queue_rq_srcu); blk_mq_sched_dispatch_requests(hctx); - srcu_read_unlock(&hctx->queue_rq_srcu, srcu_idx); + srcu_read_unlock(hctx->queue_rq_srcu, srcu_idx); } } @@ -1134,8 +1145,10 @@ static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx) static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async, unsigned long msecs) { - if (unlikely(blk_mq_hctx_stopped(hctx) || - !blk_mq_hw_queue_mapped(hctx))) + if (WARN_ON_ONCE(!blk_mq_hw_queue_mapped(hctx))) + return; + + if (unlikely(blk_mq_hctx_stopped(hctx))) return; if (!async && !(hctx->flags & BLK_MQ_F_BLOCKING)) { @@ -1201,34 +1214,39 @@ bool blk_mq_queue_stopped(struct request_queue *q) } EXPORT_SYMBOL(blk_mq_queue_stopped); -static void __blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx, bool sync) +/* + * This function is often used for pausing .queue_rq() by driver when + * there isn't enough resource or some conditions aren't satisfied, and + * BLK_MQ_RQ_QUEUE_BUSY is usually returned. + * + * We do not guarantee that dispatch can be drained or blocked + * after blk_mq_stop_hw_queue() returns. Please use + * blk_mq_quiesce_queue() for that requirement. + */ +void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx) { - if (sync) - cancel_delayed_work_sync(&hctx->run_work); - else - cancel_delayed_work(&hctx->run_work); + cancel_delayed_work(&hctx->run_work); set_bit(BLK_MQ_S_STOPPED, &hctx->state); } - -void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx) -{ - __blk_mq_stop_hw_queue(hctx, false); -} EXPORT_SYMBOL(blk_mq_stop_hw_queue); -static void __blk_mq_stop_hw_queues(struct request_queue *q, bool sync) +/* + * This function is often used for pausing .queue_rq() by driver when + * there isn't enough resource or some conditions aren't satisfied, and + * BLK_MQ_RQ_QUEUE_BUSY is usually returned. + * + * We do not guarantee that dispatch can be drained or blocked + * after blk_mq_stop_hw_queues() returns. Please use + * blk_mq_quiesce_queue() for that requirement. + */ +void blk_mq_stop_hw_queues(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; int i; queue_for_each_hw_ctx(q, hctx, i) - __blk_mq_stop_hw_queue(hctx, sync); -} - -void blk_mq_stop_hw_queues(struct request_queue *q) -{ - __blk_mq_stop_hw_queues(q, false); + blk_mq_stop_hw_queue(hctx); } EXPORT_SYMBOL(blk_mq_stop_hw_queues); @@ -1295,7 +1313,7 @@ static void blk_mq_run_work_fn(struct work_struct *work) void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs) { - if (unlikely(!blk_mq_hw_queue_mapped(hctx))) + if (WARN_ON_ONCE(!blk_mq_hw_queue_mapped(hctx))) return; /* @@ -1317,6 +1335,8 @@ static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx, { struct blk_mq_ctx *ctx = rq->mq_ctx; + lockdep_assert_held(&ctx->lock); + trace_block_rq_insert(hctx->queue, rq); if (at_head) @@ -1330,6 +1350,8 @@ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, { struct blk_mq_ctx *ctx = rq->mq_ctx; + lockdep_assert_held(&ctx->lock); + __blk_mq_insert_req_list(hctx, rq, at_head); blk_mq_hctx_mark_pending(hctx, ctx); } @@ -1427,30 +1449,13 @@ static inline bool hctx_allow_merges(struct blk_mq_hw_ctx *hctx) !blk_queue_nomerges(hctx->queue); } -static inline bool blk_mq_merge_queue_io(struct blk_mq_hw_ctx *hctx, - struct blk_mq_ctx *ctx, - struct request *rq, struct bio *bio) +static inline void blk_mq_queue_io(struct blk_mq_hw_ctx *hctx, + struct blk_mq_ctx *ctx, + struct request *rq) { - if (!hctx_allow_merges(hctx) || !bio_mergeable(bio)) { - blk_mq_bio_to_request(rq, bio); - spin_lock(&ctx->lock); -insert_rq: - __blk_mq_insert_request(hctx, rq, false); - spin_unlock(&ctx->lock); - return false; - } else { - struct request_queue *q = hctx->queue; - - spin_lock(&ctx->lock); - if (!blk_mq_attempt_merge(q, ctx, bio)) { - blk_mq_bio_to_request(rq, bio); - goto insert_rq; - } - - spin_unlock(&ctx->lock); - __blk_mq_finish_request(hctx, ctx, rq); - return true; - } + spin_lock(&ctx->lock); + __blk_mq_insert_request(hctx, rq, false); + spin_unlock(&ctx->lock); } static blk_qc_t request_to_qc_t(struct blk_mq_hw_ctx *hctx, struct request *rq) @@ -1471,10 +1476,11 @@ static void __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, .last = true, }; blk_qc_t new_cookie; - int ret; + blk_status_t ret; bool run_queue = true; - if (blk_mq_hctx_stopped(hctx)) { + /* RCU or SRCU read lock is needed before checking quiesced flag */ + if (blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)) { run_queue = false; goto insert; } @@ -1493,18 +1499,19 @@ static void __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, * would have done */ ret = q->mq_ops->queue_rq(hctx, &bd); - if (ret == BLK_MQ_RQ_QUEUE_OK) { + switch (ret) { + case BLK_STS_OK: *cookie = new_cookie; return; - } - - if (ret == BLK_MQ_RQ_QUEUE_ERROR) { + case BLK_STS_RESOURCE: + __blk_mq_requeue_request(rq); + goto insert; + default: *cookie = BLK_QC_T_NONE; - blk_mq_end_request(rq, -EIO); + blk_mq_end_request(rq, ret); return; } - __blk_mq_requeue_request(rq); insert: blk_mq_sched_insert_request(rq, false, run_queue, false, may_sleep); } @@ -1521,9 +1528,9 @@ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, might_sleep(); - srcu_idx = srcu_read_lock(&hctx->queue_rq_srcu); + srcu_idx = srcu_read_lock(hctx->queue_rq_srcu); __blk_mq_try_issue_directly(hctx, rq, cookie, true); - srcu_read_unlock(&hctx->queue_rq_srcu, srcu_idx); + srcu_read_unlock(hctx->queue_rq_srcu, srcu_idx); } } @@ -1541,7 +1548,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) blk_queue_bounce(q, &bio); - blk_queue_split(q, &bio, q->bio_split); + blk_queue_split(q, &bio); if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) { bio_io_error(bio); @@ -1559,9 +1566,11 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) trace_block_getrq(q, bio, bio->bi_opf); - rq = blk_mq_sched_get_request(q, bio, bio->bi_opf, &data); + rq = blk_mq_get_request(q, bio, bio->bi_opf, &data); if (unlikely(!rq)) { __wbt_done(q->rq_wb, wb_acct); + if (bio->bi_opf & REQ_NOWAIT) + bio_wouldblock_error(bio); return BLK_QC_T_NONE; } @@ -1639,11 +1648,12 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) blk_mq_put_ctx(data.ctx); blk_mq_bio_to_request(rq, bio); blk_mq_sched_insert_request(rq, false, true, true, true); - } else if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) { + } else { blk_mq_put_ctx(data.ctx); + blk_mq_bio_to_request(rq, bio); + blk_mq_queue_io(data.hctx, data.ctx, rq); blk_mq_run_hw_queue(data.hctx, true); - } else - blk_mq_put_ctx(data.ctx); + } return cookie; } @@ -1866,7 +1876,7 @@ static void blk_mq_exit_hctx(struct request_queue *q, set->ops->exit_hctx(hctx, hctx_idx); if (hctx->flags & BLK_MQ_F_BLOCKING) - cleanup_srcu_struct(&hctx->queue_rq_srcu); + cleanup_srcu_struct(hctx->queue_rq_srcu); blk_mq_remove_cpuhp(hctx); blk_free_flush_queue(hctx->fq); @@ -1900,7 +1910,6 @@ static int blk_mq_init_hctx(struct request_queue *q, spin_lock_init(&hctx->lock); INIT_LIST_HEAD(&hctx->dispatch); hctx->queue = q; - hctx->queue_num = hctx_idx; hctx->flags = set->flags & ~BLK_MQ_F_TAG_SHARED; cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead); @@ -1939,7 +1948,7 @@ static int blk_mq_init_hctx(struct request_queue *q, goto free_fq; if (hctx->flags & BLK_MQ_F_BLOCKING) - init_srcu_struct(&hctx->queue_rq_srcu); + init_srcu_struct(hctx->queue_rq_srcu); blk_mq_debugfs_register_hctx(q, hctx); @@ -2103,20 +2112,30 @@ static void blk_mq_map_swqueue(struct request_queue *q, } } +/* + * Caller needs to ensure that we're either frozen/quiesced, or that + * the queue isn't live yet. + */ static void queue_set_hctx_shared(struct request_queue *q, bool shared) { struct blk_mq_hw_ctx *hctx; int i; queue_for_each_hw_ctx(q, hctx, i) { - if (shared) + if (shared) { + if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) + atomic_inc(&q->shared_hctx_restart); hctx->flags |= BLK_MQ_F_TAG_SHARED; - else + } else { + if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) + atomic_dec(&q->shared_hctx_restart); hctx->flags &= ~BLK_MQ_F_TAG_SHARED; + } } } -static void blk_mq_update_tag_set_depth(struct blk_mq_tag_set *set, bool shared) +static void blk_mq_update_tag_set_depth(struct blk_mq_tag_set *set, + bool shared) { struct request_queue *q; @@ -2214,6 +2233,20 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set) } EXPORT_SYMBOL(blk_mq_init_queue); +static int blk_mq_hw_ctx_size(struct blk_mq_tag_set *tag_set) +{ + int hw_ctx_size = sizeof(struct blk_mq_hw_ctx); + + BUILD_BUG_ON(ALIGN(offsetof(struct blk_mq_hw_ctx, queue_rq_srcu), + __alignof__(struct blk_mq_hw_ctx)) != + sizeof(struct blk_mq_hw_ctx)); + + if (tag_set->flags & BLK_MQ_F_BLOCKING) + hw_ctx_size += sizeof(struct srcu_struct); + + return hw_ctx_size; +} + static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, struct request_queue *q) { @@ -2228,7 +2261,7 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, continue; node = blk_mq_hw_queue_to_node(q->mq_map, i); - hctxs[i] = kzalloc_node(sizeof(struct blk_mq_hw_ctx), + hctxs[i] = kzalloc_node(blk_mq_hw_ctx_size(set), GFP_KERNEL, node); if (!hctxs[i]) break; diff --git a/block/blk-mq.h b/block/blk-mq.h index cc67b48e3551..1a06fdf9fd4d 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -128,17 +128,6 @@ static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data return data->hctx->tags; } -/* - * Internal helpers for request allocation/init/free - */ -void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx, - struct request *rq, unsigned int op); -void __blk_mq_finish_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx, - struct request *rq); -void blk_mq_finish_request(struct request *rq); -struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data, - unsigned int op); - static inline bool blk_mq_hctx_stopped(struct blk_mq_hw_ctx *hctx) { return test_bit(BLK_MQ_S_STOPPED, &hctx->state); diff --git a/block/blk-settings.c b/block/blk-settings.c index 4fa81ed383ca..be1f115b538b 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -172,11 +172,6 @@ void blk_queue_make_request(struct request_queue *q, make_request_fn *mfn) q->nr_batching = BLK_BATCH_REQ; blk_set_default_limits(&q->limits); - - /* - * by default assume old behaviour and bounce for any highmem page - */ - blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH); } EXPORT_SYMBOL(blk_queue_make_request); diff --git a/block/blk-tag.c b/block/blk-tag.c index 07cc329fa4b0..2290f65b9d73 100644 --- a/block/blk-tag.c +++ b/block/blk-tag.c @@ -258,15 +258,14 @@ EXPORT_SYMBOL(blk_queue_resize_tags); * all transfers have been done for a request. It's important to call * this function before end_that_request_last(), as that will put the * request back on the free list thus corrupting the internal tag list. - * - * Notes: - * queue lock must be held. **/ void blk_queue_end_tag(struct request_queue *q, struct request *rq) { struct blk_queue_tag *bqt = q->queue_tags; unsigned tag = rq->tag; /* negative tags invalid */ + lockdep_assert_held(q->queue_lock); + BUG_ON(tag >= bqt->real_max_depth); list_del_init(&rq->queuelist); @@ -307,9 +306,6 @@ EXPORT_SYMBOL(blk_queue_end_tag); * calling this function. The request will also be removed from * the request queue, so it's the drivers responsibility to readd * it if it should need to be restarted for some reason. - * - * Notes: - * queue lock must be held. **/ int blk_queue_start_tag(struct request_queue *q, struct request *rq) { @@ -317,6 +313,8 @@ int blk_queue_start_tag(struct request_queue *q, struct request *rq) unsigned max_depth; int tag; + lockdep_assert_held(q->queue_lock); + if (unlikely((rq->rq_flags & RQF_QUEUED))) { printk(KERN_ERR "%s: request %p for device [%s] already tagged %d", @@ -389,14 +387,13 @@ EXPORT_SYMBOL(blk_queue_start_tag); * Hardware conditions may dictate a need to stop all pending requests. * In this case, we will safely clear the block side of the tag queue and * readd all requests to the request queue in the right order. - * - * Notes: - * queue lock must be held. **/ void blk_queue_invalidate_tags(struct request_queue *q) { struct list_head *tmp, *n; + lockdep_assert_held(q->queue_lock); + list_for_each_safe(tmp, n, &q->tag_busy_list) blk_requeue_request(q, list_entry_rq(tmp)); } diff --git a/block/blk-timeout.c b/block/blk-timeout.c index cbff183f3d9f..17ec83bb0900 100644 --- a/block/blk-timeout.c +++ b/block/blk-timeout.c @@ -189,13 +189,15 @@ unsigned long blk_rq_timeout(unsigned long timeout) * Notes: * Each request has its own timer, and as it is added to the queue, we * set up the timer. When the request completes, we cancel the timer. - * Queue lock must be held for the non-mq case, mq case doesn't care. */ void blk_add_timer(struct request *req) { struct request_queue *q = req->q; unsigned long expiry; + if (!q->mq_ops) + lockdep_assert_held(q->queue_lock); + /* blk-mq has its own handler, so we don't need ->rq_timed_out_fn */ if (!q->mq_ops && !q->rq_timed_out_fn) return; diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 17676f4d7fd1..6a9a0f03a67b 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -503,7 +503,7 @@ static inline unsigned int get_limit(struct rq_wb *rwb, unsigned long rw) } static inline bool may_queue(struct rq_wb *rwb, struct rq_wait *rqw, - wait_queue_t *wait, unsigned long rw) + wait_queue_entry_t *wait, unsigned long rw) { /* * inc it here even if disabled, since we'll dec it at completion. @@ -520,7 +520,7 @@ static inline bool may_queue(struct rq_wb *rwb, struct rq_wait *rqw, * in line to be woken up, wait for our turn. */ if (waitqueue_active(&rqw->wait) && - rqw->wait.task_list.next != &wait->task_list) + rqw->wait.head.next != &wait->entry) return false; return atomic_inc_below(&rqw->inflight, get_limit(rwb, rw)); diff --git a/block/blk.h b/block/blk.h index 83c8e1100525..01ebb8185f6b 100644 --- a/block/blk.h +++ b/block/blk.h @@ -143,6 +143,8 @@ static inline struct request *__elv_next_request(struct request_queue *q) struct request *rq; struct blk_flush_queue *fq = blk_get_flush_queue(q, NULL); + WARN_ON_ONCE(q->mq_ops); + while (1) { if (!list_empty(&q->queue_head)) { rq = list_entry_rq(q->queue_head.next); @@ -334,4 +336,17 @@ static inline void blk_throtl_bio_endio(struct bio *bio) { } static inline void blk_throtl_stat_add(struct request *rq, u64 time) { } #endif +#ifdef CONFIG_BOUNCE +extern int init_emergency_isa_pool(void); +extern void blk_queue_bounce(struct request_queue *q, struct bio **bio); +#else +static inline int init_emergency_isa_pool(void) +{ + return 0; +} +static inline void blk_queue_bounce(struct request_queue *q, struct bio **bio) +{ +} +#endif /* CONFIG_BOUNCE */ + #endif /* BLK_INTERNAL_H */ diff --git a/block/bounce.c b/block/bounce.c index 1cb5dd3a5da1..5793c2dc1a15 100644 --- a/block/bounce.c +++ b/block/bounce.c @@ -22,10 +22,12 @@ #include <asm/tlbflush.h> #include <trace/events/block.h> +#include "blk.h" #define POOL_SIZE 64 #define ISA_POOL_SIZE 16 +static struct bio_set *bounce_bio_set, *bounce_bio_split; static mempool_t *page_pool, *isa_page_pool; #if defined(CONFIG_HIGHMEM) || defined(CONFIG_NEED_BOUNCE_POOL) @@ -40,6 +42,14 @@ static __init int init_emergency_pool(void) BUG_ON(!page_pool); pr_info("pool size: %d pages\n", POOL_SIZE); + bounce_bio_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); + BUG_ON(!bounce_bio_set); + if (bioset_integrity_create(bounce_bio_set, BIO_POOL_SIZE)) + BUG_ON(1); + + bounce_bio_split = bioset_create(BIO_POOL_SIZE, 0, 0); + BUG_ON(!bounce_bio_split); + return 0; } @@ -143,7 +153,7 @@ static void bounce_end_io(struct bio *bio, mempool_t *pool) mempool_free(bvec->bv_page, pool); } - bio_orig->bi_error = bio->bi_error; + bio_orig->bi_status = bio->bi_status; bio_endio(bio_orig); bio_put(bio); } @@ -163,7 +173,7 @@ static void __bounce_end_io_read(struct bio *bio, mempool_t *pool) { struct bio *bio_orig = bio->bi_private; - if (!bio->bi_error) + if (!bio->bi_status) copy_to_high_bio_irq(bio_orig, bio); bounce_end_io(bio, pool); @@ -186,20 +196,31 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig, int rw = bio_data_dir(*bio_orig); struct bio_vec *to, from; struct bvec_iter iter; - unsigned i; - - bio_for_each_segment(from, *bio_orig, iter) - if (page_to_pfn(from.bv_page) > queue_bounce_pfn(q)) - goto bounce; + unsigned i = 0; + bool bounce = false; + int sectors = 0; + + bio_for_each_segment(from, *bio_orig, iter) { + if (i++ < BIO_MAX_PAGES) + sectors += from.bv_len >> 9; + if (page_to_pfn(from.bv_page) > q->limits.bounce_pfn) + bounce = true; + } + if (!bounce) + return; - return; -bounce: - bio = bio_clone_bioset(*bio_orig, GFP_NOIO, fs_bio_set); + if (sectors < bio_sectors(*bio_orig)) { + bio = bio_split(*bio_orig, sectors, GFP_NOIO, bounce_bio_split); + bio_chain(bio, *bio_orig); + generic_make_request(*bio_orig); + *bio_orig = bio; + } + bio = bio_clone_bioset(*bio_orig, GFP_NOIO, bounce_bio_set); bio_for_each_segment_all(to, bio, i) { struct page *page = to->bv_page; - if (page_to_pfn(page) <= queue_bounce_pfn(q)) + if (page_to_pfn(page) <= q->limits.bounce_pfn) continue; to->bv_page = mempool_alloc(pool, q->bounce_gfp); @@ -251,7 +272,7 @@ void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig) * don't waste time iterating over bio segments */ if (!(q->bounce_gfp & GFP_DMA)) { - if (queue_bounce_pfn(q) >= blk_max_pfn) + if (q->limits.bounce_pfn >= blk_max_pfn) return; pool = page_pool; } else { @@ -264,5 +285,3 @@ void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig) */ __blk_queue_bounce(q, bio_orig, pool); } - -EXPORT_SYMBOL(blk_queue_bounce); diff --git a/block/bsg-lib.c b/block/bsg-lib.c index 0a23dbba2d30..c4513b23f57a 100644 --- a/block/bsg-lib.c +++ b/block/bsg-lib.c @@ -37,7 +37,7 @@ static void bsg_destroy_job(struct kref *kref) struct bsg_job *job = container_of(kref, struct bsg_job, kref); struct request *rq = job->req; - blk_end_request_all(rq, scsi_req(rq)->result); + blk_end_request_all(rq, BLK_STS_OK); put_device(job->dev); /* release reference for the request */ @@ -202,7 +202,7 @@ static void bsg_request_fn(struct request_queue *q) ret = bsg_create_job(dev, req); if (ret) { scsi_req(req)->result = ret; - blk_end_request_all(req, ret); + blk_end_request_all(req, BLK_STS_OK); spin_lock_irq(q->queue_lock); continue; } @@ -246,6 +246,7 @@ struct request_queue *bsg_setup_queue(struct device *dev, char *name, q->bsg_job_size = dd_job_size; q->bsg_job_fn = job_fn; queue_flag_set_unlocked(QUEUE_FLAG_BIDI, q); + queue_flag_set_unlocked(QUEUE_FLAG_SCSI_PASSTHROUGH, q); blk_queue_softirq_done(q, bsg_softirq_done); blk_queue_rq_timeout(q, BLK_DEFAULT_SG_TIMEOUT); diff --git a/block/bsg.c b/block/bsg.c index 6fd08544d77e..37663b664666 100644 --- a/block/bsg.c +++ b/block/bsg.c @@ -236,7 +236,6 @@ bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm) rq = blk_get_request(q, op, GFP_KERNEL); if (IS_ERR(rq)) return rq; - scsi_req_init(rq); ret = blk_fill_sgv4_hdr_rq(q, rq, hdr, bd, has_write_perm); if (ret) @@ -294,14 +293,14 @@ out: * async completion call-back from the block layer, when scsi/ide/whatever * calls end_that_request_last() on a request */ -static void bsg_rq_end_io(struct request *rq, int uptodate) +static void bsg_rq_end_io(struct request *rq, blk_status_t status) { struct bsg_command *bc = rq->end_io_data; struct bsg_device *bd = bc->bd; unsigned long flags; - dprintk("%s: finished rq %p bc %p, bio %p stat %d\n", - bd->name, rq, bc, bc->bio, uptodate); + dprintk("%s: finished rq %p bc %p, bio %p\n", + bd->name, rq, bc, bc->bio); bc->hdr.duration = jiffies_to_msecs(jiffies - bc->hdr.duration); @@ -750,6 +749,12 @@ static struct bsg_device *bsg_add_device(struct inode *inode, #ifdef BSG_DEBUG unsigned char buf[32]; #endif + + if (!blk_queue_scsi_passthrough(rq)) { + WARN_ONCE(true, "Attempt to register a non-SCSI queue\n"); + return ERR_PTR(-EINVAL); + } + if (!blk_get_queue(rq)) return ERR_PTR(-ENXIO); diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index b7e9c7feeab2..3d5c28945719 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -982,15 +982,6 @@ static inline u64 max_vdisktime(u64 min_vdisktime, u64 vdisktime) return min_vdisktime; } -static inline u64 min_vdisktime(u64 min_vdisktime, u64 vdisktime) -{ - s64 delta = (s64)(vdisktime - min_vdisktime); - if (delta < 0) - min_vdisktime = vdisktime; - - return min_vdisktime; -} - static void update_min_vdisktime(struct cfq_rb_root *st) { struct cfq_group *cfqg; diff --git a/block/elevator.c b/block/elevator.c index dac99fbfc273..4bb2f0c93fa6 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -681,6 +681,7 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where) */ if (elv_attempt_insert_merge(q, rq)) break; + /* fall through */ case ELEVATOR_INSERT_SORT: BUG_ON(blk_rq_is_passthrough(rq)); rq->rq_flags |= RQF_SORTED; diff --git a/block/genhd.c b/block/genhd.c index d252d29fe837..7f520fa25d16 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -36,7 +36,7 @@ struct kobject *block_depr; static DEFINE_SPINLOCK(ext_devt_lock); static DEFINE_IDR(ext_devt_idr); -static struct device_type disk_type; +static const struct device_type disk_type; static void disk_check_events(struct disk_events *ev, unsigned int *clearing_ptr); @@ -1183,7 +1183,7 @@ static char *block_devnode(struct device *dev, umode_t *mode, return NULL; } -static struct device_type disk_type = { +static const struct device_type disk_type = { .name = "disk", .groups = disk_attr_groups, .release = disk_release, diff --git a/block/ioprio.c b/block/ioprio.c index 4b120c9cf7e8..6f5d0b6625e3 100644 --- a/block/ioprio.c +++ b/block/ioprio.c @@ -75,7 +75,8 @@ SYSCALL_DEFINE3(ioprio_set, int, which, int, who, int, ioprio) case IOPRIO_CLASS_RT: if (!capable(CAP_SYS_ADMIN)) return -EPERM; - /* fall through, rt has prio field too */ + /* fall through */ + /* rt has prio field too */ case IOPRIO_CLASS_BE: if (data >= IOPRIO_BE_NR || data < 0) return -EINVAL; diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c index b9faabc75fdb..f58cab82105b 100644 --- a/block/kyber-iosched.c +++ b/block/kyber-iosched.c @@ -99,7 +99,7 @@ struct kyber_hctx_data { struct list_head rqs[KYBER_NUM_DOMAINS]; unsigned int cur_domain; unsigned int batching; - wait_queue_t domain_wait[KYBER_NUM_DOMAINS]; + wait_queue_entry_t domain_wait[KYBER_NUM_DOMAINS]; atomic_t wait_index[KYBER_NUM_DOMAINS]; }; @@ -385,7 +385,7 @@ static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) for (i = 0; i < KYBER_NUM_DOMAINS; i++) { INIT_LIST_HEAD(&khd->rqs[i]); - INIT_LIST_HEAD(&khd->domain_wait[i].task_list); + INIT_LIST_HEAD(&khd->domain_wait[i].entry); atomic_set(&khd->wait_index[i], 0); } @@ -426,33 +426,29 @@ static void rq_clear_domain_token(struct kyber_queue_data *kqd, } } -static struct request *kyber_get_request(struct request_queue *q, - unsigned int op, - struct blk_mq_alloc_data *data) +static void kyber_limit_depth(unsigned int op, struct blk_mq_alloc_data *data) { - struct kyber_queue_data *kqd = q->elevator->elevator_data; - struct request *rq; - /* * We use the scheduler tags as per-hardware queue queueing tokens. * Async requests can be limited at this stage. */ - if (!op_is_sync(op)) + if (!op_is_sync(op)) { + struct kyber_queue_data *kqd = data->q->elevator->elevator_data; + data->shallow_depth = kqd->async_depth; + } +} - rq = __blk_mq_alloc_request(data, op); - if (rq) - rq_set_domain_token(rq, -1); - return rq; +static void kyber_prepare_request(struct request *rq, struct bio *bio) +{ + rq_set_domain_token(rq, -1); } -static void kyber_put_request(struct request *rq) +static void kyber_finish_request(struct request *rq) { - struct request_queue *q = rq->q; - struct kyber_queue_data *kqd = q->elevator->elevator_data; + struct kyber_queue_data *kqd = rq->q->elevator->elevator_data; rq_clear_domain_token(kqd, rq); - blk_mq_finish_request(rq); } static void kyber_completed_request(struct request *rq) @@ -507,12 +503,12 @@ static void kyber_flush_busy_ctxs(struct kyber_hctx_data *khd, } } -static int kyber_domain_wake(wait_queue_t *wait, unsigned mode, int flags, +static int kyber_domain_wake(wait_queue_entry_t *wait, unsigned mode, int flags, void *key) { struct blk_mq_hw_ctx *hctx = READ_ONCE(wait->private); - list_del_init(&wait->task_list); + list_del_init(&wait->entry); blk_mq_run_hw_queue(hctx, true); return 1; } @@ -523,7 +519,7 @@ static int kyber_get_domain_token(struct kyber_queue_data *kqd, { unsigned int sched_domain = khd->cur_domain; struct sbitmap_queue *domain_tokens = &kqd->domain_tokens[sched_domain]; - wait_queue_t *wait = &khd->domain_wait[sched_domain]; + wait_queue_entry_t *wait = &khd->domain_wait[sched_domain]; struct sbq_wait_state *ws; int nr; @@ -536,7 +532,7 @@ static int kyber_get_domain_token(struct kyber_queue_data *kqd, * run when one becomes available. Note that this is serialized on * khd->lock, but we still need to be careful about the waker. */ - if (list_empty_careful(&wait->task_list)) { + if (list_empty_careful(&wait->entry)) { init_waitqueue_func_entry(wait, kyber_domain_wake); wait->private = hctx; ws = sbq_wait_ptr(domain_tokens, @@ -734,9 +730,9 @@ static int kyber_##name##_waiting_show(void *data, struct seq_file *m) \ { \ struct blk_mq_hw_ctx *hctx = data; \ struct kyber_hctx_data *khd = hctx->sched_data; \ - wait_queue_t *wait = &khd->domain_wait[domain]; \ + wait_queue_entry_t *wait = &khd->domain_wait[domain]; \ \ - seq_printf(m, "%d\n", !list_empty_careful(&wait->task_list)); \ + seq_printf(m, "%d\n", !list_empty_careful(&wait->entry)); \ return 0; \ } KYBER_DEBUGFS_DOMAIN_ATTRS(KYBER_READ, read) @@ -815,8 +811,9 @@ static struct elevator_type kyber_sched = { .exit_sched = kyber_exit_sched, .init_hctx = kyber_init_hctx, .exit_hctx = kyber_exit_hctx, - .get_request = kyber_get_request, - .put_request = kyber_put_request, + .limit_depth = kyber_limit_depth, + .prepare_request = kyber_prepare_request, + .finish_request = kyber_finish_request, .completed_request = kyber_completed_request, .dispatch_request = kyber_dispatch_request, .has_work = kyber_has_work, diff --git a/block/partitions/ldm.c b/block/partitions/ldm.c index edcea70674c9..2a365c756648 100644 --- a/block/partitions/ldm.c +++ b/block/partitions/ldm.c @@ -115,7 +115,7 @@ static bool ldm_parse_privhead(const u8 *data, struct privhead *ph) ldm_error("PRIVHEAD disk size doesn't match real disk size"); return false; } - if (uuid_be_to_bin(data + 0x0030, (uuid_be *)ph->disk_id)) { + if (uuid_parse(data + 0x0030, &ph->disk_id)) { ldm_error("PRIVHEAD contains an invalid GUID."); return false; } @@ -234,7 +234,7 @@ static bool ldm_compare_privheads (const struct privhead *ph1, (ph1->logical_disk_size == ph2->logical_disk_size) && (ph1->config_start == ph2->config_start) && (ph1->config_size == ph2->config_size) && - !memcmp (ph1->disk_id, ph2->disk_id, GUID_SIZE)); + uuid_equal(&ph1->disk_id, &ph2->disk_id)); } /** @@ -557,7 +557,7 @@ static struct vblk * ldm_get_disk_objid (const struct ldmdb *ldb) list_for_each (item, &ldb->v_disk) { struct vblk *v = list_entry (item, struct vblk, list); - if (!memcmp (v->vblk.disk.disk_id, ldb->ph.disk_id, GUID_SIZE)) + if (uuid_equal(&v->vblk.disk.disk_id, &ldb->ph.disk_id)) return v; } @@ -892,7 +892,7 @@ static bool ldm_parse_dsk3 (const u8 *buffer, int buflen, struct vblk *vb) disk = &vb->vblk.disk; ldm_get_vstr (buffer + 0x18 + r_diskid, disk->alt_name, sizeof (disk->alt_name)); - if (uuid_be_to_bin(buffer + 0x19 + r_name, (uuid_be *)disk->disk_id)) + if (uuid_parse(buffer + 0x19 + r_name, &disk->disk_id)) return false; return true; @@ -927,7 +927,7 @@ static bool ldm_parse_dsk4 (const u8 *buffer, int buflen, struct vblk *vb) return false; disk = &vb->vblk.disk; - memcpy (disk->disk_id, buffer + 0x18 + r_name, GUID_SIZE); + uuid_copy(&disk->disk_id, (uuid_t *)(buffer + 0x18 + r_name)); return true; } diff --git a/block/partitions/ldm.h b/block/partitions/ldm.h index 374242c0971a..f4c6055df956 100644 --- a/block/partitions/ldm.h +++ b/block/partitions/ldm.h @@ -112,8 +112,6 @@ struct frag { /* VBLK Fragment handling */ /* In memory LDM database structures. */ -#define GUID_SIZE 16 - struct privhead { /* Offsets and sizes are in sectors. */ u16 ver_major; u16 ver_minor; @@ -121,7 +119,7 @@ struct privhead { /* Offsets and sizes are in sectors. */ u64 logical_disk_size; u64 config_start; u64 config_size; - u8 disk_id[GUID_SIZE]; + uuid_t disk_id; }; struct tocblock { /* We have exactly two bitmaps. */ @@ -154,7 +152,7 @@ struct vblk_dgrp { /* VBLK Disk Group */ }; struct vblk_disk { /* VBLK Disk */ - u8 disk_id[GUID_SIZE]; + uuid_t disk_id; u8 alt_name[128]; }; diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c index 4a294a5f7fab..7440de44dd85 100644 --- a/block/scsi_ioctl.c +++ b/block/scsi_ioctl.c @@ -326,7 +326,6 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk, if (IS_ERR(rq)) return PTR_ERR(rq); req = scsi_req(rq); - scsi_req_init(rq); if (hdr->cmd_len > BLK_MAX_CDB) { req->cmd = kzalloc(hdr->cmd_len, GFP_KERNEL); @@ -456,7 +455,6 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode, goto error_free_buffer; } req = scsi_req(rq); - scsi_req_init(rq); cmdlen = COMMAND_SIZE(opcode); @@ -542,7 +540,6 @@ static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk, rq = blk_get_request(q, REQ_OP_SCSI_OUT, __GFP_RECLAIM); if (IS_ERR(rq)) return PTR_ERR(rq); - scsi_req_init(rq); rq->timeout = BLK_DEFAULT_SG_TIMEOUT; scsi_req(rq)->cmd[0] = cmd; scsi_req(rq)->cmd[4] = data; @@ -744,10 +741,14 @@ int scsi_cmd_blk_ioctl(struct block_device *bd, fmode_t mode, } EXPORT_SYMBOL(scsi_cmd_blk_ioctl); -void scsi_req_init(struct request *rq) +/** + * scsi_req_init - initialize certain fields of a scsi_request structure + * @req: Pointer to a scsi_request structure. + * Initializes .__cmd[], .cmd, .cmd_len and .sense_len but no other members + * of struct scsi_request. + */ +void scsi_req_init(struct scsi_request *req) { - struct scsi_request *req = scsi_req(rq); - memset(req->__cmd, 0, sizeof(req->__cmd)); req->cmd = req->__cmd; req->cmd_len = BLK_MAX_CDB; diff --git a/block/t10-pi.c b/block/t10-pi.c index 680c6d636298..3416dadf7b15 100644 --- a/block/t10-pi.c +++ b/block/t10-pi.c @@ -46,8 +46,8 @@ static __be16 t10_pi_ip_fn(void *data, unsigned int len) * 16 bit app tag, 32 bit reference tag. Type 3 does not define the ref * tag. */ -static int t10_pi_generate(struct blk_integrity_iter *iter, csum_fn *fn, - unsigned int type) +static blk_status_t t10_pi_generate(struct blk_integrity_iter *iter, + csum_fn *fn, unsigned int type) { unsigned int i; @@ -67,11 +67,11 @@ static int t10_pi_generate(struct blk_integrity_iter *iter, csum_fn *fn, iter->seed++; } - return 0; + return BLK_STS_OK; } -static int t10_pi_verify(struct blk_integrity_iter *iter, csum_fn *fn, - unsigned int type) +static blk_status_t t10_pi_verify(struct blk_integrity_iter *iter, + csum_fn *fn, unsigned int type) { unsigned int i; @@ -91,7 +91,7 @@ static int t10_pi_verify(struct blk_integrity_iter *iter, csum_fn *fn, "(rcvd %u)\n", iter->disk_name, (unsigned long long) iter->seed, be32_to_cpu(pi->ref_tag)); - return -EILSEQ; + return BLK_STS_PROTECTION; } break; case 3: @@ -108,7 +108,7 @@ static int t10_pi_verify(struct blk_integrity_iter *iter, csum_fn *fn, "(rcvd %04x, want %04x)\n", iter->disk_name, (unsigned long long)iter->seed, be16_to_cpu(pi->guard_tag), be16_to_cpu(csum)); - return -EILSEQ; + return BLK_STS_PROTECTION; } next: @@ -117,45 +117,45 @@ next: iter->seed++; } - return 0; + return BLK_STS_OK; } -static int t10_pi_type1_generate_crc(struct blk_integrity_iter *iter) +static blk_status_t t10_pi_type1_generate_crc(struct blk_integrity_iter *iter) { return t10_pi_generate(iter, t10_pi_crc_fn, 1); } -static int t10_pi_type1_generate_ip(struct blk_integrity_iter *iter) +static blk_status_t t10_pi_type1_generate_ip(struct blk_integrity_iter *iter) { return t10_pi_generate(iter, t10_pi_ip_fn, 1); } -static int t10_pi_type1_verify_crc(struct blk_integrity_iter *iter) +static blk_status_t t10_pi_type1_verify_crc(struct blk_integrity_iter *iter) { return t10_pi_verify(iter, t10_pi_crc_fn, 1); } -static int t10_pi_type1_verify_ip(struct blk_integrity_iter *iter) +static blk_status_t t10_pi_type1_verify_ip(struct blk_integrity_iter *iter) { return t10_pi_verify(iter, t10_pi_ip_fn, 1); } -static int t10_pi_type3_generate_crc(struct blk_integrity_iter *iter) +static blk_status_t t10_pi_type3_generate_crc(struct blk_integrity_iter *iter) { return t10_pi_generate(iter, t10_pi_crc_fn, 3); } -static int t10_pi_type3_generate_ip(struct blk_integrity_iter *iter) +static blk_status_t t10_pi_type3_generate_ip(struct blk_integrity_iter *iter) { return t10_pi_generate(iter, t10_pi_ip_fn, 3); } -static int t10_pi_type3_verify_crc(struct blk_integrity_iter *iter) +static blk_status_t t10_pi_type3_verify_crc(struct blk_integrity_iter *iter) { return t10_pi_verify(iter, t10_pi_crc_fn, 3); } -static int t10_pi_type3_verify_ip(struct blk_integrity_iter *iter) +static blk_status_t t10_pi_type3_verify_ip(struct blk_integrity_iter *iter) { return t10_pi_verify(iter, t10_pi_ip_fn, 3); } diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c index 502ea4dc2080..560fdae8cc59 100644 --- a/drivers/acpi/acpi_extlog.c +++ b/drivers/acpi/acpi_extlog.c @@ -141,9 +141,9 @@ static int extlog_print(struct notifier_block *nb, unsigned long val, int cpu = mce->extcpu; struct acpi_hest_generic_status *estatus, *tmp; struct acpi_hest_generic_data *gdata; - const uuid_le *fru_id = &NULL_UUID_LE; + const guid_t *fru_id = &guid_null; char *fru_text = ""; - uuid_le *sec_type; + guid_t *sec_type; static u32 err_seq; estatus = extlog_elog_entry_check(cpu, bank); @@ -165,11 +165,11 @@ static int extlog_print(struct notifier_block *nb, unsigned long val, err_seq++; gdata = (struct acpi_hest_generic_data *)(tmp + 1); if (gdata->validation_bits & CPER_SEC_VALID_FRU_ID) - fru_id = (uuid_le *)gdata->fru_id; + fru_id = (guid_t *)gdata->fru_id; if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT) fru_text = gdata->fru_text; - sec_type = (uuid_le *)gdata->section_type; - if (!uuid_le_cmp(*sec_type, CPER_SEC_PLATFORM_MEM)) { + sec_type = (guid_t *)gdata->section_type; + if (guid_equal(sec_type, &CPER_SEC_PLATFORM_MEM)) { struct cper_sec_mem_err *mem = (void *)(gdata + 1); if (gdata->error_data_length >= sizeof(*mem)) trace_extlog_mem_event(mem, err_seq, fru_id, fru_text, @@ -182,17 +182,17 @@ out: static bool __init extlog_get_l1addr(void) { - u8 uuid[16]; + guid_t guid; acpi_handle handle; union acpi_object *obj; - acpi_str_to_uuid(extlog_dsm_uuid, uuid); - + if (guid_parse(extlog_dsm_uuid, &guid)) + return false; if (ACPI_FAILURE(acpi_get_handle(NULL, "\\_SB", &handle))) return false; - if (!acpi_check_dsm(handle, uuid, EXTLOG_DSM_REV, 1 << EXTLOG_FN_ADDR)) + if (!acpi_check_dsm(handle, &guid, EXTLOG_DSM_REV, 1 << EXTLOG_FN_ADDR)) return false; - obj = acpi_evaluate_dsm_typed(handle, uuid, EXTLOG_DSM_REV, + obj = acpi_evaluate_dsm_typed(handle, &guid, EXTLOG_DSM_REV, EXTLOG_FN_ADDR, NULL, ACPI_TYPE_INTEGER); if (!obj) { return false; diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index d0855c09f32f..980515e029fa 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -431,12 +431,13 @@ static void ghes_do_proc(struct ghes *ghes, { int sev, sec_sev; struct acpi_hest_generic_data *gdata; + guid_t *sec_type; sev = ghes_severity(estatus->error_severity); apei_estatus_for_each_section(estatus, gdata) { + sec_type = (guid_t *)gdata->section_type; sec_sev = ghes_severity(gdata->error_severity); - if (!uuid_le_cmp(*(uuid_le *)gdata->section_type, - CPER_SEC_PLATFORM_MEM)) { + if (guid_equal(sec_type, &CPER_SEC_PLATFORM_MEM)) { struct cper_sec_mem_err *mem_err; mem_err = (struct cper_sec_mem_err *)(gdata+1); ghes_edac_report_mem_error(ghes, sev, mem_err); @@ -445,8 +446,7 @@ static void ghes_do_proc(struct ghes *ghes, ghes_handle_memory_failure(gdata, sev); } #ifdef CONFIG_ACPI_APEI_PCIEAER - else if (!uuid_le_cmp(*(uuid_le *)gdata->section_type, - CPER_SEC_PCIE)) { + else if (guid_equal(sec_type, &CPER_SEC_PCIE)) { struct cper_sec_pcie *pcie_err; pcie_err = (struct cper_sec_pcie *)(gdata+1); if (sev == GHES_SEV_RECOVERABLE && diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index 784bda663d16..5a6fbe0fcaf2 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -196,42 +196,19 @@ static void acpi_print_osc_error(acpi_handle handle, pr_debug("\n"); } -acpi_status acpi_str_to_uuid(char *str, u8 *uuid) -{ - int i; - static int opc_map_to_uuid[16] = {6, 4, 2, 0, 11, 9, 16, 14, 19, 21, - 24, 26, 28, 30, 32, 34}; - - if (strlen(str) != 36) - return AE_BAD_PARAMETER; - for (i = 0; i < 36; i++) { - if (i == 8 || i == 13 || i == 18 || i == 23) { - if (str[i] != '-') - return AE_BAD_PARAMETER; - } else if (!isxdigit(str[i])) - return AE_BAD_PARAMETER; - } - for (i = 0; i < 16; i++) { - uuid[i] = hex_to_bin(str[opc_map_to_uuid[i]]) << 4; - uuid[i] |= hex_to_bin(str[opc_map_to_uuid[i] + 1]); - } - return AE_OK; -} -EXPORT_SYMBOL_GPL(acpi_str_to_uuid); - acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context) { acpi_status status; struct acpi_object_list input; union acpi_object in_params[4]; union acpi_object *out_obj; - u8 uuid[16]; + guid_t guid; u32 errors; struct acpi_buffer output = {ACPI_ALLOCATE_BUFFER, NULL}; if (!context) return AE_ERROR; - if (ACPI_FAILURE(acpi_str_to_uuid(context->uuid_str, uuid))) + if (guid_parse(context->uuid_str, &guid)) return AE_ERROR; context->ret.length = ACPI_ALLOCATE_BUFFER; context->ret.pointer = NULL; @@ -241,7 +218,7 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context) input.pointer = in_params; in_params[0].type = ACPI_TYPE_BUFFER; in_params[0].buffer.length = 16; - in_params[0].buffer.pointer = uuid; + in_params[0].buffer.pointer = (u8 *)&guid; in_params[1].type = ACPI_TYPE_INTEGER; in_params[1].integer.value = context->rev; in_params[2].type = ACPI_TYPE_INTEGER; diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 656acb5d7166..097eff0b963d 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -74,11 +74,11 @@ struct nfit_table_prev { struct list_head flushes; }; -static u8 nfit_uuid[NFIT_UUID_MAX][16]; +static guid_t nfit_uuid[NFIT_UUID_MAX]; -const u8 *to_nfit_uuid(enum nfit_uuids id) +const guid_t *to_nfit_uuid(enum nfit_uuids id) { - return nfit_uuid[id]; + return &nfit_uuid[id]; } EXPORT_SYMBOL(to_nfit_uuid); @@ -222,7 +222,7 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, u32 offset, fw_status = 0; acpi_handle handle; unsigned int func; - const u8 *uuid; + const guid_t *guid; int rc, i; func = cmd; @@ -245,7 +245,7 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, cmd_mask = nvdimm_cmd_mask(nvdimm); dsm_mask = nfit_mem->dsm_mask; desc = nd_cmd_dimm_desc(cmd); - uuid = to_nfit_uuid(nfit_mem->family); + guid = to_nfit_uuid(nfit_mem->family); handle = adev->handle; } else { struct acpi_device *adev = to_acpi_dev(acpi_desc); @@ -254,7 +254,7 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, cmd_mask = nd_desc->cmd_mask; dsm_mask = cmd_mask; desc = nd_cmd_bus_desc(cmd); - uuid = to_nfit_uuid(NFIT_DEV_BUS); + guid = to_nfit_uuid(NFIT_DEV_BUS); handle = adev->handle; dimm_name = "bus"; } @@ -289,7 +289,7 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, in_buf.buffer.pointer, min_t(u32, 256, in_buf.buffer.length), true); - out_obj = acpi_evaluate_dsm(handle, uuid, 1, func, &in_obj); + out_obj = acpi_evaluate_dsm(handle, guid, 1, func, &in_obj); if (!out_obj) { dev_dbg(dev, "%s:%s _DSM failed cmd: %s\n", __func__, dimm_name, cmd_name); @@ -409,7 +409,7 @@ int nfit_spa_type(struct acpi_nfit_system_address *spa) int i; for (i = 0; i < NFIT_UUID_MAX; i++) - if (memcmp(to_nfit_uuid(i), spa->range_guid, 16) == 0) + if (guid_equal(to_nfit_uuid(i), (guid_t *)&spa->range_guid)) return i; return -1; } @@ -1415,7 +1415,7 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc, struct acpi_device *adev, *adev_dimm; struct device *dev = acpi_desc->dev; unsigned long dsm_mask; - const u8 *uuid; + const guid_t *guid; int i; int family = -1; @@ -1444,7 +1444,7 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc, /* * Until standardization materializes we need to consider 4 * different command sets. Note, that checking for function0 (bit0) - * tells us if any commands are reachable through this uuid. + * tells us if any commands are reachable through this GUID. */ for (i = NVDIMM_FAMILY_INTEL; i <= NVDIMM_FAMILY_MSFT; i++) if (acpi_check_dsm(adev_dimm->handle, to_nfit_uuid(i), 1, 1)) @@ -1474,9 +1474,9 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc, return 0; } - uuid = to_nfit_uuid(nfit_mem->family); + guid = to_nfit_uuid(nfit_mem->family); for_each_set_bit(i, &dsm_mask, BITS_PER_LONG) - if (acpi_check_dsm(adev_dimm->handle, uuid, 1, 1ULL << i)) + if (acpi_check_dsm(adev_dimm->handle, guid, 1, 1ULL << i)) set_bit(i, &nfit_mem->dsm_mask); return 0; @@ -1611,7 +1611,7 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc) static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc) { struct nvdimm_bus_descriptor *nd_desc = &acpi_desc->nd_desc; - const u8 *uuid = to_nfit_uuid(NFIT_DEV_BUS); + const guid_t *guid = to_nfit_uuid(NFIT_DEV_BUS); struct acpi_device *adev; int i; @@ -1621,7 +1621,7 @@ static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc) return; for (i = ND_CMD_ARS_CAP; i <= ND_CMD_CLEAR_ERROR; i++) - if (acpi_check_dsm(adev->handle, uuid, 1, 1ULL << i)) + if (acpi_check_dsm(adev->handle, guid, 1, 1ULL << i)) set_bit(i, &nd_desc->cmd_mask); } @@ -3051,19 +3051,19 @@ static __init int nfit_init(void) BUILD_BUG_ON(sizeof(struct acpi_nfit_control_region) != 80); BUILD_BUG_ON(sizeof(struct acpi_nfit_data_region) != 40); - acpi_str_to_uuid(UUID_VOLATILE_MEMORY, nfit_uuid[NFIT_SPA_VOLATILE]); - acpi_str_to_uuid(UUID_PERSISTENT_MEMORY, nfit_uuid[NFIT_SPA_PM]); - acpi_str_to_uuid(UUID_CONTROL_REGION, nfit_uuid[NFIT_SPA_DCR]); - acpi_str_to_uuid(UUID_DATA_REGION, nfit_uuid[NFIT_SPA_BDW]); - acpi_str_to_uuid(UUID_VOLATILE_VIRTUAL_DISK, nfit_uuid[NFIT_SPA_VDISK]); - acpi_str_to_uuid(UUID_VOLATILE_VIRTUAL_CD, nfit_uuid[NFIT_SPA_VCD]); - acpi_str_to_uuid(UUID_PERSISTENT_VIRTUAL_DISK, nfit_uuid[NFIT_SPA_PDISK]); - acpi_str_to_uuid(UUID_PERSISTENT_VIRTUAL_CD, nfit_uuid[NFIT_SPA_PCD]); - acpi_str_to_uuid(UUID_NFIT_BUS, nfit_uuid[NFIT_DEV_BUS]); - acpi_str_to_uuid(UUID_NFIT_DIMM, nfit_uuid[NFIT_DEV_DIMM]); - acpi_str_to_uuid(UUID_NFIT_DIMM_N_HPE1, nfit_uuid[NFIT_DEV_DIMM_N_HPE1]); - acpi_str_to_uuid(UUID_NFIT_DIMM_N_HPE2, nfit_uuid[NFIT_DEV_DIMM_N_HPE2]); - acpi_str_to_uuid(UUID_NFIT_DIMM_N_MSFT, nfit_uuid[NFIT_DEV_DIMM_N_MSFT]); + guid_parse(UUID_VOLATILE_MEMORY, &nfit_uuid[NFIT_SPA_VOLATILE]); + guid_parse(UUID_PERSISTENT_MEMORY, &nfit_uuid[NFIT_SPA_PM]); + guid_parse(UUID_CONTROL_REGION, &nfit_uuid[NFIT_SPA_DCR]); + guid_parse(UUID_DATA_REGION, &nfit_uuid[NFIT_SPA_BDW]); + guid_parse(UUID_VOLATILE_VIRTUAL_DISK, &nfit_uuid[NFIT_SPA_VDISK]); + guid_parse(UUID_VOLATILE_VIRTUAL_CD, &nfit_uuid[NFIT_SPA_VCD]); + guid_parse(UUID_PERSISTENT_VIRTUAL_DISK, &nfit_uuid[NFIT_SPA_PDISK]); + guid_parse(UUID_PERSISTENT_VIRTUAL_CD, &nfit_uuid[NFIT_SPA_PCD]); + guid_parse(UUID_NFIT_BUS, &nfit_uuid[NFIT_DEV_BUS]); + guid_parse(UUID_NFIT_DIMM, &nfit_uuid[NFIT_DEV_DIMM]); + guid_parse(UUID_NFIT_DIMM_N_HPE1, &nfit_uuid[NFIT_DEV_DIMM_N_HPE1]); + guid_parse(UUID_NFIT_DIMM_N_HPE2, &nfit_uuid[NFIT_DEV_DIMM_N_HPE2]); + guid_parse(UUID_NFIT_DIMM_N_MSFT, &nfit_uuid[NFIT_DEV_DIMM_N_MSFT]); nfit_wq = create_singlethread_workqueue("nfit"); if (!nfit_wq) diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h index 58fb7d68e04a..29bdd959517f 100644 --- a/drivers/acpi/nfit/nfit.h +++ b/drivers/acpi/nfit/nfit.h @@ -18,7 +18,6 @@ #include <linux/libnvdimm.h> #include <linux/ndctl.h> #include <linux/types.h> -#include <linux/uuid.h> #include <linux/acpi.h> #include <acpi/acuuid.h> @@ -237,7 +236,7 @@ static inline struct acpi_nfit_desc *to_acpi_desc( return container_of(nd_desc, struct acpi_nfit_desc, nd_desc); } -const u8 *to_nfit_uuid(enum nfit_uuids id); +const guid_t *to_nfit_uuid(enum nfit_uuids id); int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, void *nfit, acpi_size sz); void acpi_nfit_shutdown(void *data); void __acpi_nfit_notify(struct device *dev, acpi_handle handle, u32 event); diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c index 919be0aa2578..240544253ccd 100644 --- a/drivers/acpi/pci_root.c +++ b/drivers/acpi/pci_root.c @@ -523,7 +523,7 @@ static int acpi_pci_root_add(struct acpi_device *device, struct acpi_pci_root *root; acpi_handle handle = device->handle; int no_aspm = 0; - bool hotadd = system_state != SYSTEM_BOOTING; + bool hotadd = system_state == SYSTEM_RUNNING; root = kzalloc(sizeof(struct acpi_pci_root), GFP_KERNEL); if (!root) diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 3a10d7573477..d53162997f32 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -1428,6 +1428,37 @@ static void acpi_init_coherency(struct acpi_device *adev) adev->flags.coherent_dma = cca; } +static int acpi_check_spi_i2c_slave(struct acpi_resource *ares, void *data) +{ + bool *is_spi_i2c_slave_p = data; + + if (ares->type != ACPI_RESOURCE_TYPE_SERIAL_BUS) + return 1; + + /* + * devices that are connected to UART still need to be enumerated to + * platform bus + */ + if (ares->data.common_serial_bus.type != ACPI_RESOURCE_SERIAL_TYPE_UART) + *is_spi_i2c_slave_p = true; + + /* no need to do more checking */ + return -1; +} + +static bool acpi_is_spi_i2c_slave(struct acpi_device *device) +{ + struct list_head resource_list; + bool is_spi_i2c_slave = false; + + INIT_LIST_HEAD(&resource_list); + acpi_dev_get_resources(device, &resource_list, acpi_check_spi_i2c_slave, + &is_spi_i2c_slave); + acpi_dev_free_resource_list(&resource_list); + + return is_spi_i2c_slave; +} + void acpi_init_device_object(struct acpi_device *device, acpi_handle handle, int type, unsigned long long sta) { @@ -1443,6 +1474,7 @@ void acpi_init_device_object(struct acpi_device *device, acpi_handle handle, acpi_bus_get_flags(device); device->flags.match_driver = false; device->flags.initialized = true; + device->flags.spi_i2c_slave = acpi_is_spi_i2c_slave(device); acpi_device_clear_enumerated(device); device_initialize(&device->dev); dev_set_uevent_suppress(&device->dev, true); @@ -1727,38 +1759,13 @@ static acpi_status acpi_bus_check_add(acpi_handle handle, u32 lvl_not_used, return AE_OK; } -static int acpi_check_spi_i2c_slave(struct acpi_resource *ares, void *data) -{ - bool *is_spi_i2c_slave_p = data; - - if (ares->type != ACPI_RESOURCE_TYPE_SERIAL_BUS) - return 1; - - /* - * devices that are connected to UART still need to be enumerated to - * platform bus - */ - if (ares->data.common_serial_bus.type != ACPI_RESOURCE_SERIAL_TYPE_UART) - *is_spi_i2c_slave_p = true; - - /* no need to do more checking */ - return -1; -} - static void acpi_default_enumeration(struct acpi_device *device) { - struct list_head resource_list; - bool is_spi_i2c_slave = false; - /* * Do not enumerate SPI/I2C slaves as they will be enumerated by their * respective parents. */ - INIT_LIST_HEAD(&resource_list); - acpi_dev_get_resources(device, &resource_list, acpi_check_spi_i2c_slave, - &is_spi_i2c_slave); - acpi_dev_free_resource_list(&resource_list); - if (!is_spi_i2c_slave) { + if (!device->flags.spi_i2c_slave) { acpi_create_platform_device(device, NULL); acpi_device_set_enumerated(device); } else { @@ -1854,7 +1861,7 @@ static void acpi_bus_attach(struct acpi_device *device) return; device->flags.match_driver = true; - if (ret > 0) { + if (ret > 0 && !device->flags.spi_i2c_slave) { acpi_device_set_enumerated(device); goto ok; } @@ -1863,10 +1870,10 @@ static void acpi_bus_attach(struct acpi_device *device) if (ret < 0) return; - if (device->pnp.type.platform_id) - acpi_default_enumeration(device); - else + if (!device->pnp.type.platform_id && !device->flags.spi_i2c_slave) acpi_device_set_enumerated(device); + else + acpi_default_enumeration(device); ok: list_for_each_entry(child, &device->children, node) diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c index 27d0dcfcf47d..b9d956c916f5 100644 --- a/drivers/acpi/utils.c +++ b/drivers/acpi/utils.c @@ -613,19 +613,19 @@ acpi_status acpi_evaluate_lck(acpi_handle handle, int lock) /** * acpi_evaluate_dsm - evaluate device's _DSM method * @handle: ACPI device handle - * @uuid: UUID of requested functions, should be 16 bytes + * @guid: GUID of requested functions, should be 16 bytes * @rev: revision number of requested function * @func: requested function number * @argv4: the function specific parameter * - * Evaluate device's _DSM method with specified UUID, revision id and + * Evaluate device's _DSM method with specified GUID, revision id and * function number. Caller needs to free the returned object. * * Though ACPI defines the fourth parameter for _DSM should be a package, * some old BIOSes do expect a buffer or an integer etc. */ union acpi_object * -acpi_evaluate_dsm(acpi_handle handle, const u8 *uuid, u64 rev, u64 func, +acpi_evaluate_dsm(acpi_handle handle, const guid_t *guid, u64 rev, u64 func, union acpi_object *argv4) { acpi_status ret; @@ -638,7 +638,7 @@ acpi_evaluate_dsm(acpi_handle handle, const u8 *uuid, u64 rev, u64 func, params[0].type = ACPI_TYPE_BUFFER; params[0].buffer.length = 16; - params[0].buffer.pointer = (char *)uuid; + params[0].buffer.pointer = (u8 *)guid; params[1].type = ACPI_TYPE_INTEGER; params[1].integer.value = rev; params[2].type = ACPI_TYPE_INTEGER; @@ -666,7 +666,7 @@ EXPORT_SYMBOL(acpi_evaluate_dsm); /** * acpi_check_dsm - check if _DSM method supports requested functions. * @handle: ACPI device handle - * @uuid: UUID of requested functions, should be 16 bytes at least + * @guid: GUID of requested functions, should be 16 bytes at least * @rev: revision number of requested functions * @funcs: bitmap of requested functions * @@ -674,7 +674,7 @@ EXPORT_SYMBOL(acpi_evaluate_dsm); * functions. Currently only support 64 functions at maximum, should be * enough for now. */ -bool acpi_check_dsm(acpi_handle handle, const u8 *uuid, u64 rev, u64 funcs) +bool acpi_check_dsm(acpi_handle handle, const guid_t *guid, u64 rev, u64 funcs) { int i; u64 mask = 0; @@ -683,7 +683,7 @@ bool acpi_check_dsm(acpi_handle handle, const u8 *uuid, u64 rev, u64 funcs) if (funcs == 0) return false; - obj = acpi_evaluate_dsm(handle, uuid, rev, 0, NULL); + obj = acpi_evaluate_dsm(handle, guid, rev, 0, NULL); if (!obj) return false; @@ -697,7 +697,7 @@ bool acpi_check_dsm(acpi_handle handle, const u8 *uuid, u64 rev, u64 funcs) /* * Bit 0 indicates whether there's support for any functions other than - * function 0 for the specified UUID and revision. + * function 0 for the specified GUID and revision. */ if ((mask & 0x1) && (mask & funcs) == funcs) return true; diff --git a/drivers/base/node.c b/drivers/base/node.c index 5548f9686016..0440d95c9b5b 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -377,7 +377,7 @@ static int __ref get_nid_for_pfn(unsigned long pfn) if (!pfn_valid_within(pfn)) return -1; #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT - if (system_state == SYSTEM_BOOTING) + if (system_state < SYSTEM_RUNNING) return early_pfn_to_nid(pfn); #endif page = pfn_to_page(pfn); diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c index 26a51be77227..245a879b036e 100644 --- a/drivers/block/DAC960.c +++ b/drivers/block/DAC960.c @@ -3464,7 +3464,7 @@ static inline bool DAC960_ProcessCompletedRequest(DAC960_Command_T *Command, bool SuccessfulIO) { struct request *Request = Command->Request; - int Error = SuccessfulIO ? 0 : -EIO; + blk_status_t Error = SuccessfulIO ? BLK_STS_OK : BLK_STS_IOERR; pci_unmap_sg(Command->Controller->PCIDevice, Command->cmd_sglist, Command->SegmentCount, Command->DmaDirection); diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c index a328f673adfe..49908c74bfcb 100644 --- a/drivers/block/amiflop.c +++ b/drivers/block/amiflop.c @@ -1378,7 +1378,7 @@ static void redo_fd_request(void) struct amiga_floppy_struct *floppy; char *data; unsigned long flags; - int err; + blk_status_t err; next_req: rq = set_next_request(); @@ -1392,7 +1392,7 @@ next_req: next_segment: /* Here someone could investigate to be more efficient */ - for (cnt = 0, err = 0; cnt < blk_rq_cur_sectors(rq); cnt++) { + for (cnt = 0, err = BLK_STS_OK; cnt < blk_rq_cur_sectors(rq); cnt++) { #ifdef DEBUG printk("fd: sector %ld + %d requested for %s\n", blk_rq_pos(rq), cnt, @@ -1400,7 +1400,7 @@ next_segment: #endif block = blk_rq_pos(rq) + cnt; if ((int)block > floppy->blocks) { - err = -EIO; + err = BLK_STS_IOERR; break; } @@ -1413,7 +1413,7 @@ next_segment: #endif if (get_track(drive, track) == -1) { - err = -EIO; + err = BLK_STS_IOERR; break; } @@ -1424,7 +1424,7 @@ next_segment: /* keep the drive spinning while writes are scheduled */ if (!fd_motor_on(drive)) { - err = -EIO; + err = BLK_STS_IOERR; break; } /* diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c index 027b876370bc..6797e6c23c8a 100644 --- a/drivers/block/aoe/aoeblk.c +++ b/drivers/block/aoe/aoeblk.c @@ -388,6 +388,7 @@ aoeblk_gdalloc(void *vp) d->aoemajor, d->aoeminor); goto err_mempool; } + blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH); spin_lock_irqsave(&d->lock, flags); WARN_ON(!(d->flags & DEVFL_GD_NOW)); diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c index 3c606c09fd5a..dc43254e05a4 100644 --- a/drivers/block/aoe/aoecmd.c +++ b/drivers/block/aoe/aoecmd.c @@ -1070,8 +1070,8 @@ aoe_end_request(struct aoedev *d, struct request *rq, int fastfail) d->ip.rq = NULL; do { bio = rq->bio; - bok = !fastfail && !bio->bi_error; - } while (__blk_end_request(rq, bok ? 0 : -EIO, bio->bi_iter.bi_size)); + bok = !fastfail && !bio->bi_status; + } while (__blk_end_request(rq, bok ? BLK_STS_OK : BLK_STS_IOERR, bio->bi_iter.bi_size)); /* cf. http://lkml.org/lkml/2006/10/31/28 */ if (!fastfail) @@ -1131,7 +1131,7 @@ ktiocomplete(struct frame *f) ahout->cmdstat, ahin->cmdstat, d->aoemajor, d->aoeminor); noskb: if (buf) - buf->bio->bi_error = -EIO; + buf->bio->bi_status = BLK_STS_IOERR; goto out; } @@ -1144,7 +1144,7 @@ noskb: if (buf) "aoe: runt data size in read from", (long) d->aoemajor, d->aoeminor, skb->len, n); - buf->bio->bi_error = -EIO; + buf->bio->bi_status = BLK_STS_IOERR; break; } if (n > f->iter.bi_size) { @@ -1152,7 +1152,7 @@ noskb: if (buf) "aoe: too-large data size in read from", (long) d->aoemajor, d->aoeminor, n, f->iter.bi_size); - buf->bio->bi_error = -EIO; + buf->bio->bi_status = BLK_STS_IOERR; break; } bvcpy(skb, f->buf->bio, f->iter, n); @@ -1654,7 +1654,7 @@ aoe_failbuf(struct aoedev *d, struct buf *buf) if (buf == NULL) return; buf->iter.bi_size = 0; - buf->bio->bi_error = -EIO; + buf->bio->bi_status = BLK_STS_IOERR; if (buf->nframesout == 0) aoe_end_buf(d, buf); } diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c index ffd1947500c6..b28fefb90391 100644 --- a/drivers/block/aoe/aoedev.c +++ b/drivers/block/aoe/aoedev.c @@ -170,7 +170,7 @@ aoe_failip(struct aoedev *d) if (rq == NULL) return; while ((bio = d->ip.nxbio)) { - bio->bi_error = -EIO; + bio->bi_status = BLK_STS_IOERR; d->ip.nxbio = bio->bi_next; n = (unsigned long) rq->special; rq->special = (void *) --n; diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c index fa69ecd52cb5..92da886180aa 100644 --- a/drivers/block/ataflop.c +++ b/drivers/block/ataflop.c @@ -378,7 +378,7 @@ static DEFINE_TIMER(readtrack_timer, fd_readtrack_check, 0, 0); static DEFINE_TIMER(timeout_timer, fd_times_out, 0, 0); static DEFINE_TIMER(fd_timer, check_change, 0, 0); -static void fd_end_request_cur(int err) +static void fd_end_request_cur(blk_status_t err) { if (!__blk_end_request_cur(fd_request, err)) fd_request = NULL; @@ -620,7 +620,7 @@ static void fd_error( void ) fd_request->error_count++; if (fd_request->error_count >= MAX_ERRORS) { printk(KERN_ERR "fd%d: too many errors.\n", SelectedDrive ); - fd_end_request_cur(-EIO); + fd_end_request_cur(BLK_STS_IOERR); } else if (fd_request->error_count == RECALIBRATE_ERRORS) { printk(KERN_WARNING "fd%d: recalibrating\n", SelectedDrive ); @@ -739,7 +739,7 @@ static void do_fd_action( int drive ) } else { /* all sectors finished */ - fd_end_request_cur(0); + fd_end_request_cur(BLK_STS_OK); redo_fd_request(); return; } @@ -1144,7 +1144,7 @@ static void fd_rwsec_done1(int status) } else { /* all sectors finished */ - fd_end_request_cur(0); + fd_end_request_cur(BLK_STS_OK); redo_fd_request(); } return; @@ -1445,7 +1445,7 @@ repeat: if (!UD.connected) { /* drive not connected */ printk(KERN_ERR "Unknown Device: fd%d\n", drive ); - fd_end_request_cur(-EIO); + fd_end_request_cur(BLK_STS_IOERR); goto repeat; } @@ -1461,12 +1461,12 @@ repeat: /* user supplied disk type */ if (--type >= NUM_DISK_MINORS) { printk(KERN_WARNING "fd%d: invalid disk format", drive ); - fd_end_request_cur(-EIO); + fd_end_request_cur(BLK_STS_IOERR); goto repeat; } if (minor2disktype[type].drive_types > DriveType) { printk(KERN_WARNING "fd%d: unsupported disk format", drive ); - fd_end_request_cur(-EIO); + fd_end_request_cur(BLK_STS_IOERR); goto repeat; } type = minor2disktype[type].index; @@ -1476,7 +1476,7 @@ repeat: } if (blk_rq_pos(fd_request) + 1 > UDT->blocks) { - fd_end_request_cur(-EIO); + fd_end_request_cur(BLK_STS_IOERR); goto repeat; } diff --git a/drivers/block/brd.c b/drivers/block/brd.c index 57b574f2f66a..6112e99bedf7 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -418,7 +418,6 @@ static struct brd_device *brd_alloc(int i) blk_queue_make_request(brd->brd_queue, brd_make_request); blk_queue_max_hw_sectors(brd->brd_queue, 1024); - blk_queue_bounce_limit(brd->brd_queue, BLK_BOUNCE_ANY); /* This is so fdisk will align partitions on 4k, because of * direct_access API needing 4k alignment, returning a PFN diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c index cd375503f7b0..02a611993bb4 100644 --- a/drivers/block/cciss.c +++ b/drivers/block/cciss.c @@ -1864,7 +1864,8 @@ static void cciss_softirq_done(struct request *rq) /* set the residual count for pc requests */ if (blk_rq_is_passthrough(rq)) scsi_req(rq)->resid_len = c->err_info->ResidualCnt; - blk_end_request_all(rq, scsi_req(rq)->result ? -EIO : 0); + blk_end_request_all(rq, scsi_req(rq)->result ? + BLK_STS_IOERR : BLK_STS_OK); spin_lock_irqsave(&h->lock, flags); cmd_free(h, c); @@ -1956,6 +1957,7 @@ static int cciss_add_disk(ctlr_info_t *h, struct gendisk *disk, disk->queue->cmd_size = sizeof(struct scsi_request); disk->queue->request_fn = do_cciss_request; disk->queue->queue_lock = &h->lock; + queue_flag_set_unlocked(QUEUE_FLAG_SCSI_PASSTHROUGH, disk->queue); if (blk_init_allocated_queue(disk->queue) < 0) goto cleanup_queue; diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c index 8d7bcfa49c12..e02c45cd3c5a 100644 --- a/drivers/block/drbd/drbd_actlog.c +++ b/drivers/block/drbd/drbd_actlog.c @@ -178,7 +178,7 @@ static int _drbd_md_sync_page_io(struct drbd_device *device, else submit_bio(bio); wait_until_done_or_force_detached(device, bdev, &device->md_io.done); - if (!bio->bi_error) + if (!bio->bi_status) err = device->md_io.error; out: diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c index a804a4107fbc..809fd245c3dc 100644 --- a/drivers/block/drbd/drbd_bitmap.c +++ b/drivers/block/drbd/drbd_bitmap.c @@ -959,16 +959,16 @@ static void drbd_bm_endio(struct bio *bio) !bm_test_page_unchanged(b->bm_pages[idx])) drbd_warn(device, "bitmap page idx %u changed during IO!\n", idx); - if (bio->bi_error) { + if (bio->bi_status) { /* ctx error will hold the completed-last non-zero error code, * in case error codes differ. */ - ctx->error = bio->bi_error; + ctx->error = blk_status_to_errno(bio->bi_status); bm_set_page_io_err(b->bm_pages[idx]); /* Not identical to on disk version of it. * Is BM_PAGE_IO_ERROR enough? */ if (__ratelimit(&drbd_ratelimit_state)) drbd_err(device, "IO ERROR %d on bitmap page idx %u\n", - bio->bi_error, idx); + bio->bi_status, idx); } else { bm_clear_page_io_err(b->bm_pages[idx]); dynamic_drbd_dbg(device, "bitmap page idx %u completed\n", idx); diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index d5da45bb03a6..d17b6e6393c7 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -1441,6 +1441,9 @@ extern struct bio_set *drbd_md_io_bio_set; /* to allocate from that set */ extern struct bio *bio_alloc_drbd(gfp_t gfp_mask); +/* And a bio_set for cloning */ +extern struct bio_set *drbd_io_bio_set; + extern struct mutex resources_mutex; extern int conn_lowest_minor(struct drbd_connection *connection); @@ -1627,7 +1630,7 @@ static inline void drbd_generic_make_request(struct drbd_device *device, __release(local); if (!bio->bi_bdev) { drbd_err(device, "drbd_generic_make_request: bio->bi_bdev == NULL\n"); - bio->bi_error = -ENODEV; + bio->bi_status = BLK_STS_IOERR; bio_endio(bio); return; } diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 84455c365f57..5fb99e06ebe4 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -128,6 +128,7 @@ mempool_t *drbd_request_mempool; mempool_t *drbd_ee_mempool; mempool_t *drbd_md_io_page_pool; struct bio_set *drbd_md_io_bio_set; +struct bio_set *drbd_io_bio_set; /* I do not use a standard mempool, because: 1) I want to hand out the pre-allocated objects first. @@ -2098,6 +2099,8 @@ static void drbd_destroy_mempools(void) /* D_ASSERT(device, atomic_read(&drbd_pp_vacant)==0); */ + if (drbd_io_bio_set) + bioset_free(drbd_io_bio_set); if (drbd_md_io_bio_set) bioset_free(drbd_md_io_bio_set); if (drbd_md_io_page_pool) @@ -2115,6 +2118,7 @@ static void drbd_destroy_mempools(void) if (drbd_al_ext_cache) kmem_cache_destroy(drbd_al_ext_cache); + drbd_io_bio_set = NULL; drbd_md_io_bio_set = NULL; drbd_md_io_page_pool = NULL; drbd_ee_mempool = NULL; @@ -2142,6 +2146,7 @@ static int drbd_create_mempools(void) drbd_pp_pool = NULL; drbd_md_io_page_pool = NULL; drbd_md_io_bio_set = NULL; + drbd_io_bio_set = NULL; /* caches */ drbd_request_cache = kmem_cache_create( @@ -2165,7 +2170,13 @@ static int drbd_create_mempools(void) goto Enomem; /* mempools */ - drbd_md_io_bio_set = bioset_create(DRBD_MIN_POOL_PAGES, 0); + drbd_io_bio_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_RESCUER); + if (drbd_io_bio_set == NULL) + goto Enomem; + + drbd_md_io_bio_set = bioset_create(DRBD_MIN_POOL_PAGES, 0, + BIOSET_NEED_BVECS | + BIOSET_NEED_RESCUER); if (drbd_md_io_bio_set == NULL) goto Enomem; @@ -2839,7 +2850,6 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig /* Setting the max_hw_sectors to an odd value of 8kibyte here This triggers a max_bio_size message upon first attach or connect */ blk_queue_max_hw_sectors(q, DRBD_MAX_BIO_SIZE_SAFE >> 8); - blk_queue_bounce_limit(q, BLK_BOUNCE_ANY); q->queue_lock = &resource->req_lock; device->md_io.page = alloc_page(GFP_KERNEL); diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index 02255a0d68b9..ad0fcb43e45c 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -2294,7 +2294,7 @@ _check_net_options(struct drbd_connection *connection, struct net_conf *old_net_ static enum drbd_ret_code check_net_options(struct drbd_connection *connection, struct net_conf *new_net_conf) { - static enum drbd_ret_code rv; + enum drbd_ret_code rv; struct drbd_peer_device *peer_device; int i; diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 1b0a2be24f39..c7e95e6380fb 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -1229,9 +1229,9 @@ void one_flush_endio(struct bio *bio) struct drbd_device *device = octx->device; struct issue_flush_context *ctx = octx->ctx; - if (bio->bi_error) { - ctx->error = bio->bi_error; - drbd_info(device, "local disk FLUSH FAILED with status %d\n", bio->bi_error); + if (bio->bi_status) { + ctx->error = blk_status_to_errno(bio->bi_status); + drbd_info(device, "local disk FLUSH FAILED with status %d\n", bio->bi_status); } kfree(octx); bio_put(bio); diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index 656624314f0d..f6e865b2d543 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -203,7 +203,7 @@ void start_new_tl_epoch(struct drbd_connection *connection) void complete_master_bio(struct drbd_device *device, struct bio_and_error *m) { - m->bio->bi_error = m->error; + m->bio->bi_status = errno_to_blk_status(m->error); bio_endio(m->bio); dec_ap_bio(device); } @@ -1157,7 +1157,7 @@ static void drbd_process_discard_req(struct drbd_request *req) if (blkdev_issue_zeroout(bdev, req->i.sector, req->i.size >> 9, GFP_NOIO, 0)) - req->private_bio->bi_error = -EIO; + req->private_bio->bi_status = BLK_STS_IOERR; bio_endio(req->private_bio); } @@ -1225,7 +1225,7 @@ drbd_request_prepare(struct drbd_device *device, struct bio *bio, unsigned long /* only pass the error to the upper layers. * if user cannot handle io errors, that's not our business. */ drbd_err(device, "could not kmalloc() req\n"); - bio->bi_error = -ENOMEM; + bio->bi_status = BLK_STS_RESOURCE; bio_endio(bio); return ERR_PTR(-ENOMEM); } @@ -1560,7 +1560,7 @@ blk_qc_t drbd_make_request(struct request_queue *q, struct bio *bio) struct drbd_device *device = (struct drbd_device *) q->queuedata; unsigned long start_jif; - blk_queue_split(q, &bio, q->bio_split); + blk_queue_split(q, &bio); start_jif = jiffies; diff --git a/drivers/block/drbd/drbd_req.h b/drivers/block/drbd/drbd_req.h index eb49e7f2da91..9e1866ab238f 100644 --- a/drivers/block/drbd/drbd_req.h +++ b/drivers/block/drbd/drbd_req.h @@ -263,7 +263,7 @@ enum drbd_req_state_bits { static inline void drbd_req_make_private_bio(struct drbd_request *req, struct bio *bio_src) { struct bio *bio; - bio = bio_clone(bio_src, GFP_NOIO); /* XXX cannot fail?? */ + bio = bio_clone_fast(bio_src, GFP_NOIO, drbd_io_bio_set); req->private_bio = bio; diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c index 1afcb4e02d8d..1d8726a8df34 100644 --- a/drivers/block/drbd/drbd_worker.c +++ b/drivers/block/drbd/drbd_worker.c @@ -63,7 +63,7 @@ void drbd_md_endio(struct bio *bio) struct drbd_device *device; device = bio->bi_private; - device->md_io.error = bio->bi_error; + device->md_io.error = blk_status_to_errno(bio->bi_status); /* We grabbed an extra reference in _drbd_md_sync_page_io() to be able * to timeout on the lower level device, and eventually detach from it. @@ -177,13 +177,13 @@ void drbd_peer_request_endio(struct bio *bio) bool is_discard = bio_op(bio) == REQ_OP_WRITE_ZEROES || bio_op(bio) == REQ_OP_DISCARD; - if (bio->bi_error && __ratelimit(&drbd_ratelimit_state)) + if (bio->bi_status && __ratelimit(&drbd_ratelimit_state)) drbd_warn(device, "%s: error=%d s=%llus\n", is_write ? (is_discard ? "discard" : "write") - : "read", bio->bi_error, + : "read", bio->bi_status, (unsigned long long)peer_req->i.sector); - if (bio->bi_error) + if (bio->bi_status) set_bit(__EE_WAS_ERROR, &peer_req->flags); bio_put(bio); /* no need for the bio anymore */ @@ -243,16 +243,16 @@ void drbd_request_endio(struct bio *bio) if (__ratelimit(&drbd_ratelimit_state)) drbd_emerg(device, "delayed completion of aborted local request; disk-timeout may be too aggressive\n"); - if (!bio->bi_error) + if (!bio->bi_status) drbd_panic_after_delayed_completion_of_aborted_request(device); } /* to avoid recursion in __req_mod */ - if (unlikely(bio->bi_error)) { + if (unlikely(bio->bi_status)) { switch (bio_op(bio)) { case REQ_OP_WRITE_ZEROES: case REQ_OP_DISCARD: - if (bio->bi_error == -EOPNOTSUPP) + if (bio->bi_status == BLK_STS_NOTSUPP) what = DISCARD_COMPLETED_NOTSUPP; else what = DISCARD_COMPLETED_WITH_ERROR; @@ -272,7 +272,7 @@ void drbd_request_endio(struct bio *bio) } bio_put(req->private_bio); - req->private_bio = ERR_PTR(bio->bi_error); + req->private_bio = ERR_PTR(blk_status_to_errno(bio->bi_status)); /* not req_mod(), we need irqsave here! */ spin_lock_irqsave(&device->resource->req_lock, flags); diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 60d4c7653178..ce823647a9c4 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -2202,7 +2202,7 @@ static int do_format(int drive, struct format_descr *tmp_format_req) * ============================= */ -static void floppy_end_request(struct request *req, int error) +static void floppy_end_request(struct request *req, blk_status_t error) { unsigned int nr_sectors = current_count_sectors; unsigned int drive = (unsigned long)req->rq_disk->private_data; @@ -2263,7 +2263,7 @@ static void request_done(int uptodate) DRWE->last_error_generation = DRS->generation; } spin_lock_irqsave(q->queue_lock, flags); - floppy_end_request(req, -EIO); + floppy_end_request(req, BLK_STS_IOERR); spin_unlock_irqrestore(q->queue_lock, flags); } } @@ -3780,9 +3780,9 @@ static void floppy_rb0_cb(struct bio *bio) struct rb0_cbdata *cbdata = (struct rb0_cbdata *)bio->bi_private; int drive = cbdata->drive; - if (bio->bi_error) { + if (bio->bi_status) { pr_info("floppy: error %d while reading block 0\n", - bio->bi_error); + bio->bi_status); set_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags); } complete(&cbdata->complete); @@ -4203,6 +4203,7 @@ static int __init do_floppy_init(void) goto out_put_disk; } + blk_queue_bounce_limit(disks[drive]->queue, BLK_BOUNCE_HIGH); blk_queue_max_hw_sectors(disks[drive]->queue, 64); disks[drive]->major = FLOPPY_MAJOR; disks[drive]->first_minor = TOMINOR(drive); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index ebbd0c3fe0ed..0de11444e317 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -221,7 +221,8 @@ static void __loop_update_dio(struct loop_device *lo, bool dio) } static int -figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit) +figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit, + loff_t logical_blocksize) { loff_t size = get_size(offset, sizelimit, lo->lo_backing_file); sector_t x = (sector_t)size; @@ -233,6 +234,12 @@ figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit) lo->lo_offset = offset; if (lo->lo_sizelimit != sizelimit) lo->lo_sizelimit = sizelimit; + if (lo->lo_flags & LO_FLAGS_BLOCKSIZE) { + lo->lo_logical_blocksize = logical_blocksize; + blk_queue_physical_block_size(lo->lo_queue, lo->lo_blocksize); + blk_queue_logical_block_size(lo->lo_queue, + lo->lo_logical_blocksize); + } set_capacity(lo->lo_disk, x); bd_set_size(bdev, (loff_t)get_capacity(bdev->bd_disk) << 9); /* let user-space know about the new size */ @@ -457,7 +464,7 @@ static void lo_complete_rq(struct request *rq) zero_fill_bio(bio); } - blk_mq_end_request(rq, cmd->ret < 0 ? -EIO : 0); + blk_mq_end_request(rq, cmd->ret < 0 ? BLK_STS_IOERR : BLK_STS_OK); } static void lo_rw_aio_complete(struct kiocb *iocb, long ret, long ret2) @@ -813,6 +820,7 @@ static void loop_config_discard(struct loop_device *lo) struct file *file = lo->lo_backing_file; struct inode *inode = file->f_mapping->host; struct request_queue *q = lo->lo_queue; + int lo_bits = 9; /* * We use punch hole to reclaim the free space used by the @@ -832,8 +840,11 @@ static void loop_config_discard(struct loop_device *lo) q->limits.discard_granularity = inode->i_sb->s_blocksize; q->limits.discard_alignment = 0; - blk_queue_max_discard_sectors(q, UINT_MAX >> 9); - blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> 9); + if (lo->lo_flags & LO_FLAGS_BLOCKSIZE) + lo_bits = blksize_bits(lo->lo_logical_blocksize); + + blk_queue_max_discard_sectors(q, UINT_MAX >> lo_bits); + blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> lo_bits); queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q); } @@ -843,10 +854,16 @@ static void loop_unprepare_queue(struct loop_device *lo) kthread_stop(lo->worker_task); } +static int loop_kthread_worker_fn(void *worker_ptr) +{ + current->flags |= PF_LESS_THROTTLE; + return kthread_worker_fn(worker_ptr); +} + static int loop_prepare_queue(struct loop_device *lo) { kthread_init_worker(&lo->worker); - lo->worker_task = kthread_run(kthread_worker_fn, + lo->worker_task = kthread_run(loop_kthread_worker_fn, &lo->worker, "loop%d", lo->lo_number); if (IS_ERR(lo->worker_task)) return -ENOMEM; @@ -921,6 +938,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, lo->use_dio = false; lo->lo_blocksize = lo_blocksize; + lo->lo_logical_blocksize = 512; lo->lo_device = bdev; lo->lo_flags = lo_flags; lo->lo_backing_file = file; @@ -1086,6 +1104,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) int err; struct loop_func_table *xfer; kuid_t uid = current_uid(); + int lo_flags = lo->lo_flags; if (lo->lo_encrypt_key_size && !uid_eq(lo->lo_key_owner, uid) && @@ -1118,12 +1137,30 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) if (err) goto exit; + if (info->lo_flags & LO_FLAGS_BLOCKSIZE) { + if (!(lo->lo_flags & LO_FLAGS_BLOCKSIZE)) + lo->lo_logical_blocksize = 512; + lo->lo_flags |= LO_FLAGS_BLOCKSIZE; + if (LO_INFO_BLOCKSIZE(info) != 512 && + LO_INFO_BLOCKSIZE(info) != 1024 && + LO_INFO_BLOCKSIZE(info) != 2048 && + LO_INFO_BLOCKSIZE(info) != 4096) + return -EINVAL; + if (LO_INFO_BLOCKSIZE(info) > lo->lo_blocksize) + return -EINVAL; + } + if (lo->lo_offset != info->lo_offset || - lo->lo_sizelimit != info->lo_sizelimit) - if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit)) { + lo->lo_sizelimit != info->lo_sizelimit || + lo->lo_flags != lo_flags || + ((lo->lo_flags & LO_FLAGS_BLOCKSIZE) && + lo->lo_logical_blocksize != LO_INFO_BLOCKSIZE(info))) { + if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit, + LO_INFO_BLOCKSIZE(info))) { err = -EFBIG; goto exit; } + } loop_config_discard(lo); @@ -1306,12 +1343,13 @@ loop_get_status64(struct loop_device *lo, struct loop_info64 __user *arg) { return err; } -static int loop_set_capacity(struct loop_device *lo, struct block_device *bdev) +static int loop_set_capacity(struct loop_device *lo) { if (unlikely(lo->lo_state != Lo_bound)) return -ENXIO; - return figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit); + return figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit, + lo->lo_logical_blocksize); } static int loop_set_dio(struct loop_device *lo, unsigned long arg) @@ -1369,7 +1407,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, case LOOP_SET_CAPACITY: err = -EPERM; if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) - err = loop_set_capacity(lo, bdev); + err = loop_set_capacity(lo); break; case LOOP_SET_DIRECT_IO: err = -EPERM; @@ -1645,7 +1683,7 @@ int loop_unregister_transfer(int number) EXPORT_SYMBOL(loop_register_transfer); EXPORT_SYMBOL(loop_unregister_transfer); -static int loop_queue_rq(struct blk_mq_hw_ctx *hctx, +static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { struct loop_cmd *cmd = blk_mq_rq_to_pdu(bd->rq); @@ -1654,7 +1692,7 @@ static int loop_queue_rq(struct blk_mq_hw_ctx *hctx, blk_mq_start_request(bd->rq); if (lo->lo_state != Lo_bound) - return BLK_MQ_RQ_QUEUE_ERROR; + return BLK_STS_IOERR; switch (req_op(cmd->rq)) { case REQ_OP_FLUSH: @@ -1669,7 +1707,7 @@ static int loop_queue_rq(struct blk_mq_hw_ctx *hctx, kthread_queue_work(&lo->worker, &cmd->work); - return BLK_MQ_RQ_QUEUE_OK; + return BLK_STS_OK; } static void loop_handle_cmd(struct loop_cmd *cmd) diff --git a/drivers/block/loop.h b/drivers/block/loop.h index fecd3f97ef8c..2c096b9a17b8 100644 --- a/drivers/block/loop.h +++ b/drivers/block/loop.h @@ -49,6 +49,7 @@ struct loop_device { struct file * lo_backing_file; struct block_device *lo_device; unsigned lo_blocksize; + unsigned lo_logical_blocksize; void *key_data; gfp_t old_gfp_mask; diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 3a779a4f5653..61b046f256ca 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -532,7 +532,7 @@ static int mtip_read_log_page(struct mtip_port *port, u8 page, u16 *buffer, static int mtip_get_smart_attr(struct mtip_port *port, unsigned int id, struct smart_attr *attrib); -static void mtip_complete_command(struct mtip_cmd *cmd, int status) +static void mtip_complete_command(struct mtip_cmd *cmd, blk_status_t status) { struct request *req = blk_mq_rq_from_pdu(cmd); @@ -568,7 +568,7 @@ static void mtip_handle_tfe(struct driver_data *dd) if (test_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags)) { cmd = mtip_cmd_from_tag(dd, MTIP_TAG_INTERNAL); dbg_printk(MTIP_DRV_NAME " TFE for the internal command\n"); - mtip_complete_command(cmd, -EIO); + mtip_complete_command(cmd, BLK_STS_IOERR); return; } @@ -667,7 +667,7 @@ static void mtip_handle_tfe(struct driver_data *dd) tag, fail_reason != NULL ? fail_reason : "unknown"); - mtip_complete_command(cmd, -ENODATA); + mtip_complete_command(cmd, BLK_STS_MEDIUM); continue; } } @@ -690,7 +690,7 @@ static void mtip_handle_tfe(struct driver_data *dd) dev_warn(&port->dd->pdev->dev, "retiring tag %d\n", tag); - mtip_complete_command(cmd, -EIO); + mtip_complete_command(cmd, BLK_STS_IOERR); } } print_tags(dd, "reissued (TFE)", tagaccum, cmd_cnt); @@ -1063,23 +1063,10 @@ static int mtip_exec_internal_command(struct mtip_port *port, /* insert request and run queue */ blk_execute_rq(rq->q, NULL, rq, true); - rv = int_cmd->status; - if (rv < 0) { - if (rv == -ERESTARTSYS) { /* interrupted */ - dev_err(&dd->pdev->dev, - "Internal command [%02X] was interrupted after %u ms\n", - fis->command, - jiffies_to_msecs(jiffies - start)); - rv = -EINTR; - goto exec_ic_exit; - } else if (rv == 0) /* timeout */ - dev_err(&dd->pdev->dev, - "Internal command did not complete [%02X] within timeout of %lu ms\n", - fis->command, timeout); - else - dev_err(&dd->pdev->dev, - "Internal command [%02X] wait returned code [%d] after %lu ms - unhandled\n", - fis->command, rv, timeout); + if (int_cmd->status) { + dev_err(&dd->pdev->dev, "Internal command [%02X] failed %d\n", + fis->command, int_cmd->status); + rv = -EIO; if (mtip_check_surprise_removal(dd->pdev) || test_bit(MTIP_DDF_REMOVE_PENDING_BIT, @@ -2753,7 +2740,7 @@ static void mtip_abort_cmd(struct request *req, void *data, dbg_printk(MTIP_DRV_NAME " Aborting request, tag = %d\n", req->tag); clear_bit(req->tag, dd->port->cmds_to_issue); - cmd->status = -EIO; + cmd->status = BLK_STS_IOERR; mtip_softirq_done_fn(req); } @@ -3597,7 +3584,7 @@ static int mtip_submit_request(struct blk_mq_hw_ctx *hctx, struct request *rq) int err; err = mtip_send_trim(dd, blk_rq_pos(rq), blk_rq_sectors(rq)); - blk_mq_end_request(rq, err); + blk_mq_end_request(rq, err ? BLK_STS_IOERR : BLK_STS_OK); return 0; } @@ -3633,8 +3620,8 @@ static bool mtip_check_unal_depth(struct blk_mq_hw_ctx *hctx, return false; } -static int mtip_issue_reserved_cmd(struct blk_mq_hw_ctx *hctx, - struct request *rq) +static blk_status_t mtip_issue_reserved_cmd(struct blk_mq_hw_ctx *hctx, + struct request *rq) { struct driver_data *dd = hctx->queue->queuedata; struct mtip_int_cmd *icmd = rq->special; @@ -3642,7 +3629,7 @@ static int mtip_issue_reserved_cmd(struct blk_mq_hw_ctx *hctx, struct mtip_cmd_sg *command_sg; if (mtip_commands_active(dd->port)) - return BLK_MQ_RQ_QUEUE_BUSY; + return BLK_STS_RESOURCE; /* Populate the SG list */ cmd->command_header->opts = @@ -3666,10 +3653,10 @@ static int mtip_issue_reserved_cmd(struct blk_mq_hw_ctx *hctx, blk_mq_start_request(rq); mtip_issue_non_ncq_command(dd->port, rq->tag); - return BLK_MQ_RQ_QUEUE_OK; + return 0; } -static int mtip_queue_rq(struct blk_mq_hw_ctx *hctx, +static blk_status_t mtip_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { struct request *rq = bd->rq; @@ -3681,15 +3668,14 @@ static int mtip_queue_rq(struct blk_mq_hw_ctx *hctx, return mtip_issue_reserved_cmd(hctx, rq); if (unlikely(mtip_check_unal_depth(hctx, rq))) - return BLK_MQ_RQ_QUEUE_BUSY; + return BLK_STS_RESOURCE; blk_mq_start_request(rq); ret = mtip_submit_request(hctx, rq); if (likely(!ret)) - return BLK_MQ_RQ_QUEUE_OK; - - return BLK_MQ_RQ_QUEUE_ERROR; + return BLK_STS_OK; + return BLK_STS_IOERR; } static void mtip_free_cmd(struct blk_mq_tag_set *set, struct request *rq, @@ -3730,7 +3716,7 @@ static enum blk_eh_timer_return mtip_cmd_timeout(struct request *req, if (reserved) { struct mtip_cmd *cmd = blk_mq_rq_to_pdu(req); - cmd->status = -ETIME; + cmd->status = BLK_STS_TIMEOUT; return BLK_EH_HANDLED; } @@ -3961,7 +3947,7 @@ static void mtip_no_dev_cleanup(struct request *rq, void *data, bool reserv) { struct mtip_cmd *cmd = blk_mq_rq_to_pdu(rq); - cmd->status = -ENODEV; + cmd->status = BLK_STS_IOERR; blk_mq_complete_request(rq); } diff --git a/drivers/block/mtip32xx/mtip32xx.h b/drivers/block/mtip32xx/mtip32xx.h index 37b8e3e0bb78..e8286af50e16 100644 --- a/drivers/block/mtip32xx/mtip32xx.h +++ b/drivers/block/mtip32xx/mtip32xx.h @@ -342,7 +342,7 @@ struct mtip_cmd { int retries; /* The number of retries left for this command. */ int direction; /* Data transfer direction */ - int status; + blk_status_t status; }; /* Structure used to describe a port. */ diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index f3f191ba8ca4..977ec960dd2f 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -116,7 +116,7 @@ struct nbd_cmd { int index; int cookie; struct completion send_complete; - int status; + blk_status_t status; }; #if IS_ENABLED(CONFIG_DEBUG_FS) @@ -286,7 +286,7 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req, struct nbd_config *config; if (!refcount_inc_not_zero(&nbd->config_refs)) { - cmd->status = -EIO; + cmd->status = BLK_STS_TIMEOUT; return BLK_EH_HANDLED; } @@ -331,7 +331,7 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req, "Connection timed out\n"); } set_bit(NBD_TIMEDOUT, &config->runtime_flags); - cmd->status = -EIO; + cmd->status = BLK_STS_IOERR; sock_shutdown(nbd); nbd_config_put(nbd); @@ -400,6 +400,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) unsigned long size = blk_rq_bytes(req); struct bio *bio; u32 type; + u32 nbd_cmd_flags = 0; u32 tag = blk_mq_unique_tag(req); int sent = nsock->sent, skip = 0; @@ -429,6 +430,9 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) return -EIO; } + if (req->cmd_flags & REQ_FUA) + nbd_cmd_flags |= NBD_CMD_FLAG_FUA; + /* We did a partial send previously, and we at least sent the whole * request struct, so just go and send the rest of the pages in the * request. @@ -442,7 +446,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) } cmd->index = index; cmd->cookie = nsock->cookie; - request.type = htonl(type); + request.type = htonl(type | nbd_cmd_flags); if (type != NBD_CMD_FLUSH) { request.from = cpu_to_be64((u64)blk_rq_pos(req) << 9); request.len = htonl(size); @@ -465,7 +469,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) nsock->pending = req; nsock->sent = sent; } - return BLK_MQ_RQ_QUEUE_BUSY; + return BLK_STS_RESOURCE; } dev_err_ratelimited(disk_to_dev(nbd->disk), "Send control failed (result %d)\n", result); @@ -506,7 +510,7 @@ send_pages: */ nsock->pending = req; nsock->sent = sent; - return BLK_MQ_RQ_QUEUE_BUSY; + return BLK_STS_RESOURCE; } dev_err(disk_to_dev(nbd->disk), "Send data failed (result %d)\n", @@ -574,7 +578,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) if (ntohl(reply.error)) { dev_err(disk_to_dev(nbd->disk), "Other side returned error (%d)\n", ntohl(reply.error)); - cmd->status = -EIO; + cmd->status = BLK_STS_IOERR; return cmd; } @@ -599,7 +603,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) */ if (nbd_disconnected(config) || config->num_connections <= 1) { - cmd->status = -EIO; + cmd->status = BLK_STS_IOERR; return cmd; } return ERR_PTR(-EIO); @@ -651,7 +655,7 @@ static void nbd_clear_req(struct request *req, void *data, bool reserved) if (!blk_mq_request_started(req)) return; cmd = blk_mq_rq_to_pdu(req); - cmd->status = -EIO; + cmd->status = BLK_STS_IOERR; blk_mq_complete_request(req); } @@ -740,7 +744,7 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index) nbd_config_put(nbd); return -EINVAL; } - cmd->status = 0; + cmd->status = BLK_STS_OK; again: nsock = config->socks[index]; mutex_lock(&nsock->tx_lock); @@ -794,7 +798,7 @@ out: return ret; } -static int nbd_queue_rq(struct blk_mq_hw_ctx *hctx, +static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(bd->rq); @@ -818,13 +822,9 @@ static int nbd_queue_rq(struct blk_mq_hw_ctx *hctx, * appropriate. */ ret = nbd_handle_cmd(cmd, hctx->queue_num); - if (ret < 0) - ret = BLK_MQ_RQ_QUEUE_ERROR; - if (!ret) - ret = BLK_MQ_RQ_QUEUE_OK; complete(&cmd->send_complete); - return ret; + return ret < 0 ? BLK_STS_IOERR : BLK_STS_OK; } static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg, @@ -910,6 +910,7 @@ static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg) continue; } sk_set_memalloc(sock->sk); + sock->sk->sk_sndtimeo = nbd->tag_set.timeout; atomic_inc(&config->recv_threads); refcount_inc(&nbd->config_refs); old = nsock->sock; @@ -957,8 +958,12 @@ static void nbd_parse_flags(struct nbd_device *nbd) set_disk_ro(nbd->disk, false); if (config->flags & NBD_FLAG_SEND_TRIM) queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, nbd->disk->queue); - if (config->flags & NBD_FLAG_SEND_FLUSH) - blk_queue_write_cache(nbd->disk->queue, true, false); + if (config->flags & NBD_FLAG_SEND_FLUSH) { + if (config->flags & NBD_FLAG_SEND_FUA) + blk_queue_write_cache(nbd->disk->queue, true, true); + else + blk_queue_write_cache(nbd->disk->queue, true, false); + } else blk_queue_write_cache(nbd->disk->queue, false, false); } @@ -1071,6 +1076,7 @@ static int nbd_start_device(struct nbd_device *nbd) return -ENOMEM; } sk_set_memalloc(config->socks[i]->sock->sk); + config->socks[i]->sock->sk->sk_sndtimeo = nbd->tag_set.timeout; atomic_inc(&config->recv_threads); refcount_inc(&nbd->config_refs); INIT_WORK(&args->work, recv_work); @@ -1305,6 +1311,8 @@ static int nbd_dbg_flags_show(struct seq_file *s, void *unused) seq_puts(s, "NBD_FLAG_READ_ONLY\n"); if (flags & NBD_FLAG_SEND_FLUSH) seq_puts(s, "NBD_FLAG_SEND_FLUSH\n"); + if (flags & NBD_FLAG_SEND_FUA) + seq_puts(s, "NBD_FLAG_SEND_FUA\n"); if (flags & NBD_FLAG_SEND_TRIM) seq_puts(s, "NBD_FLAG_SEND_TRIM\n"); diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c index d946e1eeac8e..71f4422eba81 100644 --- a/drivers/block/null_blk.c +++ b/drivers/block/null_blk.c @@ -35,7 +35,8 @@ struct nullb { struct request_queue *q; struct gendisk *disk; struct nvm_dev *ndev; - struct blk_mq_tag_set tag_set; + struct blk_mq_tag_set *tag_set; + struct blk_mq_tag_set __tag_set; struct hrtimer timer; unsigned int queue_depth; spinlock_t lock; @@ -50,6 +51,7 @@ static struct mutex lock; static int null_major; static int nullb_indexes; static struct kmem_cache *ppa_cache; +static struct blk_mq_tag_set tag_set; enum { NULL_IRQ_NONE = 0, @@ -109,7 +111,7 @@ static int bs = 512; module_param(bs, int, S_IRUGO); MODULE_PARM_DESC(bs, "Block size (in bytes)"); -static int nr_devices = 2; +static int nr_devices = 1; module_param(nr_devices, int, S_IRUGO); MODULE_PARM_DESC(nr_devices, "Number of devices to register"); @@ -121,6 +123,10 @@ static bool blocking; module_param(blocking, bool, S_IRUGO); MODULE_PARM_DESC(blocking, "Register as a blocking blk-mq driver device"); +static bool shared_tags; +module_param(shared_tags, bool, S_IRUGO); +MODULE_PARM_DESC(shared_tags, "Share tag set between devices for blk-mq"); + static int irqmode = NULL_IRQ_SOFTIRQ; static int null_set_irqmode(const char *str, const struct kernel_param *kp) @@ -229,11 +235,11 @@ static void end_cmd(struct nullb_cmd *cmd) switch (queue_mode) { case NULL_Q_MQ: - blk_mq_end_request(cmd->rq, 0); + blk_mq_end_request(cmd->rq, BLK_STS_OK); return; case NULL_Q_RQ: INIT_LIST_HEAD(&cmd->rq->queuelist); - blk_end_request_all(cmd->rq, 0); + blk_end_request_all(cmd->rq, BLK_STS_OK); break; case NULL_Q_BIO: bio_endio(cmd->bio); @@ -356,7 +362,7 @@ static void null_request_fn(struct request_queue *q) } } -static int null_queue_rq(struct blk_mq_hw_ctx *hctx, +static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { struct nullb_cmd *cmd = blk_mq_rq_to_pdu(bd->rq); @@ -373,34 +379,11 @@ static int null_queue_rq(struct blk_mq_hw_ctx *hctx, blk_mq_start_request(bd->rq); null_handle_cmd(cmd); - return BLK_MQ_RQ_QUEUE_OK; -} - -static void null_init_queue(struct nullb *nullb, struct nullb_queue *nq) -{ - BUG_ON(!nullb); - BUG_ON(!nq); - - init_waitqueue_head(&nq->wait); - nq->queue_depth = nullb->queue_depth; -} - -static int null_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, - unsigned int index) -{ - struct nullb *nullb = data; - struct nullb_queue *nq = &nullb->queues[index]; - - hctx->driver_data = nq; - null_init_queue(nullb, nq); - nullb->nr_queues++; - - return 0; + return BLK_STS_OK; } static const struct blk_mq_ops null_mq_ops = { .queue_rq = null_queue_rq, - .init_hctx = null_init_hctx, .complete = null_softirq_done_fn, }; @@ -422,11 +405,12 @@ static void cleanup_queues(struct nullb *nullb) #ifdef CONFIG_NVM -static void null_lnvm_end_io(struct request *rq, int error) +static void null_lnvm_end_io(struct request *rq, blk_status_t status) { struct nvm_rq *rqd = rq->end_io_data; - rqd->error = error; + /* XXX: lighnvm core seems to expect NVM_RSP_* values here.. */ + rqd->error = status ? -EIO : 0; nvm_end_io(rqd); blk_put_request(rq); @@ -591,8 +575,8 @@ static void null_del_dev(struct nullb *nullb) else del_gendisk(nullb->disk); blk_cleanup_queue(nullb->q); - if (queue_mode == NULL_Q_MQ) - blk_mq_free_tag_set(&nullb->tag_set); + if (queue_mode == NULL_Q_MQ && nullb->tag_set == &nullb->__tag_set) + blk_mq_free_tag_set(nullb->tag_set); if (!use_lightnvm) put_disk(nullb->disk); cleanup_queues(nullb); @@ -614,6 +598,32 @@ static const struct block_device_operations null_fops = { .release = null_release, }; +static void null_init_queue(struct nullb *nullb, struct nullb_queue *nq) +{ + BUG_ON(!nullb); + BUG_ON(!nq); + + init_waitqueue_head(&nq->wait); + nq->queue_depth = nullb->queue_depth; +} + +static void null_init_queues(struct nullb *nullb) +{ + struct request_queue *q = nullb->q; + struct blk_mq_hw_ctx *hctx; + struct nullb_queue *nq; + int i; + + queue_for_each_hw_ctx(q, hctx, i) { + if (!hctx->nr_ctx || !hctx->tags) + continue; + nq = &nullb->queues[i]; + hctx->driver_data = nq; + null_init_queue(nullb, nq); + nullb->nr_queues++; + } +} + static int setup_commands(struct nullb_queue *nq) { struct nullb_cmd *cmd; @@ -694,6 +704,22 @@ static int null_gendisk_register(struct nullb *nullb) return 0; } +static int null_init_tag_set(struct blk_mq_tag_set *set) +{ + set->ops = &null_mq_ops; + set->nr_hw_queues = submit_queues; + set->queue_depth = hw_queue_depth; + set->numa_node = home_node; + set->cmd_size = sizeof(struct nullb_cmd); + set->flags = BLK_MQ_F_SHOULD_MERGE; + set->driver_data = NULL; + + if (blocking) + set->flags |= BLK_MQ_F_BLOCKING; + + return blk_mq_alloc_tag_set(set); +} + static int null_add_dev(void) { struct nullb *nullb; @@ -715,26 +741,23 @@ static int null_add_dev(void) goto out_free_nullb; if (queue_mode == NULL_Q_MQ) { - nullb->tag_set.ops = &null_mq_ops; - nullb->tag_set.nr_hw_queues = submit_queues; - nullb->tag_set.queue_depth = hw_queue_depth; - nullb->tag_set.numa_node = home_node; - nullb->tag_set.cmd_size = sizeof(struct nullb_cmd); - nullb->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; - nullb->tag_set.driver_data = nullb; - - if (blocking) - nullb->tag_set.flags |= BLK_MQ_F_BLOCKING; - - rv = blk_mq_alloc_tag_set(&nullb->tag_set); + if (shared_tags) { + nullb->tag_set = &tag_set; + rv = 0; + } else { + nullb->tag_set = &nullb->__tag_set; + rv = null_init_tag_set(nullb->tag_set); + } + if (rv) goto out_cleanup_queues; - nullb->q = blk_mq_init_queue(&nullb->tag_set); + nullb->q = blk_mq_init_queue(nullb->tag_set); if (IS_ERR(nullb->q)) { rv = -ENOMEM; goto out_cleanup_tags; } + null_init_queues(nullb); } else if (queue_mode == NULL_Q_BIO) { nullb->q = blk_alloc_queue_node(GFP_KERNEL, home_node); if (!nullb->q) { @@ -787,8 +810,8 @@ static int null_add_dev(void) out_cleanup_blk_queue: blk_cleanup_queue(nullb->q); out_cleanup_tags: - if (queue_mode == NULL_Q_MQ) - blk_mq_free_tag_set(&nullb->tag_set); + if (queue_mode == NULL_Q_MQ && nullb->tag_set == &nullb->__tag_set) + blk_mq_free_tag_set(nullb->tag_set); out_cleanup_queues: cleanup_queues(nullb); out_free_nullb: @@ -821,6 +844,9 @@ static int __init null_init(void) queue_mode = NULL_Q_MQ; } + if (queue_mode == NULL_Q_MQ && shared_tags) + null_init_tag_set(&tag_set); + if (queue_mode == NULL_Q_MQ && use_per_node_hctx) { if (submit_queues < nr_online_nodes) { pr_warn("null_blk: submit_queues param is set to %u.", @@ -881,6 +907,9 @@ static void __exit null_exit(void) } mutex_unlock(&lock); + if (queue_mode == NULL_Q_MQ && shared_tags) + blk_mq_free_tag_set(&tag_set); + kmem_cache_destroy(ppa_cache); } diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c index b1267ef34d5a..7b8c6368beb7 100644 --- a/drivers/block/paride/pcd.c +++ b/drivers/block/paride/pcd.c @@ -305,6 +305,7 @@ static void pcd_init_units(void) put_disk(disk); continue; } + blk_queue_bounce_limit(disk->queue, BLK_BOUNCE_HIGH); cd->disk = disk; cd->pi = &cd->pia; cd->present = 0; @@ -783,7 +784,7 @@ static void pcd_request(void) ps_set_intr(do_pcd_read, NULL, 0, nice); return; } else { - __blk_end_request_all(pcd_req, -EIO); + __blk_end_request_all(pcd_req, BLK_STS_IOERR); pcd_req = NULL; } } @@ -794,7 +795,7 @@ static void do_pcd_request(struct request_queue *q) pcd_request(); } -static inline void next_request(int err) +static inline void next_request(blk_status_t err) { unsigned long saved_flags; @@ -837,7 +838,7 @@ static void pcd_start(void) if (pcd_command(pcd_current, rd_cmd, 2048, "read block")) { pcd_bufblk = -1; - next_request(-EIO); + next_request(BLK_STS_IOERR); return; } @@ -871,7 +872,7 @@ static void do_pcd_read_drq(void) return; } pcd_bufblk = -1; - next_request(-EIO); + next_request(BLK_STS_IOERR); return; } diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c index 7d2402f90978..27a44b97393a 100644 --- a/drivers/block/paride/pd.c +++ b/drivers/block/paride/pd.c @@ -438,7 +438,7 @@ static void run_fsm(void) phase = NULL; spin_lock_irqsave(&pd_lock, saved_flags); if (!__blk_end_request_cur(pd_req, - res == Ok ? 0 : -EIO)) { + res == Ok ? 0 : BLK_STS_IOERR)) { if (!set_next_request()) stop = 1; } @@ -863,6 +863,7 @@ static void pd_probe_drive(struct pd_unit *disk) return; } blk_queue_max_hw_sectors(p->queue, cluster); + blk_queue_bounce_limit(p->queue, BLK_BOUNCE_HIGH); if (disk->drive == -1) { for (disk->drive = 0; disk->drive <= 1; disk->drive++) diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c index f24ca7315ddc..eef7a91f667d 100644 --- a/drivers/block/paride/pf.c +++ b/drivers/block/paride/pf.c @@ -293,6 +293,7 @@ static void __init pf_init_units(void) return; } blk_queue_max_segments(disk->queue, cluster); + blk_queue_bounce_limit(disk->queue, BLK_BOUNCE_HIGH); pf->disk = disk; pf->pi = &pf->pia; pf->media_status = PF_NM; @@ -801,7 +802,7 @@ static int set_next_request(void) return pf_req != NULL; } -static void pf_end_request(int err) +static void pf_end_request(blk_status_t err) { if (pf_req && !__blk_end_request_cur(pf_req, err)) pf_req = NULL; @@ -821,7 +822,7 @@ repeat: pf_count = blk_rq_cur_sectors(pf_req); if (pf_block + pf_count > get_capacity(pf_req->rq_disk)) { - pf_end_request(-EIO); + pf_end_request(BLK_STS_IOERR); goto repeat; } @@ -836,7 +837,7 @@ repeat: pi_do_claimed(pf_current->pi, do_pf_write); else { pf_busy = 0; - pf_end_request(-EIO); + pf_end_request(BLK_STS_IOERR); goto repeat; } } @@ -868,7 +869,7 @@ static int pf_next_buf(void) return 0; } -static inline void next_request(int err) +static inline void next_request(blk_status_t err) { unsigned long saved_flags; @@ -896,7 +897,7 @@ static void do_pf_read_start(void) pi_do_claimed(pf_current->pi, do_pf_read_start); return; } - next_request(-EIO); + next_request(BLK_STS_IOERR); return; } pf_mask = STAT_DRQ; @@ -915,7 +916,7 @@ static void do_pf_read_drq(void) pi_do_claimed(pf_current->pi, do_pf_read_start); return; } - next_request(-EIO); + next_request(BLK_STS_IOERR); return; } pi_read_block(pf_current->pi, pf_buf, 512); @@ -942,7 +943,7 @@ static void do_pf_write_start(void) pi_do_claimed(pf_current->pi, do_pf_write_start); return; } - next_request(-EIO); + next_request(BLK_STS_IOERR); return; } @@ -955,7 +956,7 @@ static void do_pf_write_start(void) pi_do_claimed(pf_current->pi, do_pf_write_start); return; } - next_request(-EIO); + next_request(BLK_STS_IOERR); return; } pi_write_block(pf_current->pi, pf_buf, 512); @@ -975,7 +976,7 @@ static void do_pf_write_done(void) pi_do_claimed(pf_current->pi, do_pf_write_start); return; } - next_request(-EIO); + next_request(BLK_STS_IOERR); return; } pi_disconnect(pf_current->pi); diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 205b865ebeb9..467beca397a2 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -98,6 +98,7 @@ static int write_congestion_on = PKT_WRITE_CONGESTION_ON; static int write_congestion_off = PKT_WRITE_CONGESTION_OFF; static struct mutex ctl_mutex; /* Serialize open/close/setup/teardown */ static mempool_t *psd_pool; +static struct bio_set *pkt_bio_set; static struct class *class_pktcdvd = NULL; /* /sys/class/pktcdvd */ static struct dentry *pkt_debugfs_root = NULL; /* /sys/kernel/debug/pktcdvd */ @@ -707,7 +708,6 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command * REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, __GFP_RECLAIM); if (IS_ERR(rq)) return PTR_ERR(rq); - scsi_req_init(rq); if (cgc->buflen) { ret = blk_rq_map_kern(q, rq, cgc->buffer, cgc->buflen, @@ -952,9 +952,9 @@ static void pkt_end_io_read(struct bio *bio) pkt_dbg(2, pd, "bio=%p sec0=%llx sec=%llx err=%d\n", bio, (unsigned long long)pkt->sector, - (unsigned long long)bio->bi_iter.bi_sector, bio->bi_error); + (unsigned long long)bio->bi_iter.bi_sector, bio->bi_status); - if (bio->bi_error) + if (bio->bi_status) atomic_inc(&pkt->io_errors); if (atomic_dec_and_test(&pkt->io_wait)) { atomic_inc(&pkt->run_sm); @@ -969,7 +969,7 @@ static void pkt_end_io_packet_write(struct bio *bio) struct pktcdvd_device *pd = pkt->pd; BUG_ON(!pd); - pkt_dbg(2, pd, "id=%d, err=%d\n", pkt->id, bio->bi_error); + pkt_dbg(2, pd, "id=%d, err=%d\n", pkt->id, bio->bi_status); pd->stats.pkt_ended++; @@ -1305,16 +1305,16 @@ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt) pkt_queue_bio(pd, pkt->w_bio); } -static void pkt_finish_packet(struct packet_data *pkt, int error) +static void pkt_finish_packet(struct packet_data *pkt, blk_status_t status) { struct bio *bio; - if (error) + if (status) pkt->cache_valid = 0; /* Finish all bios corresponding to this packet */ while ((bio = bio_list_pop(&pkt->orig_bios))) { - bio->bi_error = error; + bio->bi_status = status; bio_endio(bio); } } @@ -1349,7 +1349,7 @@ static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data if (atomic_read(&pkt->io_wait) > 0) return; - if (!pkt->w_bio->bi_error) { + if (!pkt->w_bio->bi_status) { pkt_set_state(pkt, PACKET_FINISHED_STATE); } else { pkt_set_state(pkt, PACKET_RECOVERY_STATE); @@ -1366,7 +1366,7 @@ static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data break; case PACKET_FINISHED_STATE: - pkt_finish_packet(pkt, pkt->w_bio->bi_error); + pkt_finish_packet(pkt, pkt->w_bio->bi_status); return; default: @@ -2301,7 +2301,7 @@ static void pkt_end_io_read_cloned(struct bio *bio) struct packet_stacked_data *psd = bio->bi_private; struct pktcdvd_device *pd = psd->pd; - psd->bio->bi_error = bio->bi_error; + psd->bio->bi_status = bio->bi_status; bio_put(bio); bio_endio(psd->bio); mempool_free(psd, psd_pool); @@ -2310,7 +2310,7 @@ static void pkt_end_io_read_cloned(struct bio *bio) static void pkt_make_request_read(struct pktcdvd_device *pd, struct bio *bio) { - struct bio *cloned_bio = bio_clone(bio, GFP_NOIO); + struct bio *cloned_bio = bio_clone_fast(bio, GFP_NOIO, pkt_bio_set); struct packet_stacked_data *psd = mempool_alloc(psd_pool, GFP_NOIO); psd->pd = pd; @@ -2412,9 +2412,7 @@ static blk_qc_t pkt_make_request(struct request_queue *q, struct bio *bio) char b[BDEVNAME_SIZE]; struct bio *split; - blk_queue_bounce(q, &bio); - - blk_queue_split(q, &bio, q->bio_split); + blk_queue_split(q, &bio); pd = q->queuedata; if (!pd) { @@ -2455,7 +2453,7 @@ static blk_qc_t pkt_make_request(struct request_queue *q, struct bio *bio) split = bio_split(bio, last_zone - bio->bi_iter.bi_sector, - GFP_NOIO, fs_bio_set); + GFP_NOIO, pkt_bio_set); bio_chain(split, bio); } else { split = bio; @@ -2583,6 +2581,11 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev) bdev = bdget(dev); if (!bdev) return -ENOMEM; + if (!blk_queue_scsi_passthrough(bdev_get_queue(bdev))) { + WARN_ONCE(true, "Attempt to register a non-SCSI queue\n"); + bdput(bdev); + return -EINVAL; + } ret = blkdev_get(bdev, FMODE_READ | FMODE_NDELAY, NULL); if (ret) return ret; @@ -2919,6 +2922,11 @@ static int __init pkt_init(void) sizeof(struct packet_stacked_data)); if (!psd_pool) return -ENOMEM; + pkt_bio_set = bioset_create(BIO_POOL_SIZE, 0, 0); + if (!pkt_bio_set) { + mempool_destroy(psd_pool); + return -ENOMEM; + } ret = register_blkdev(pktdev_major, DRIVER_NAME); if (ret < 0) { @@ -2951,6 +2959,7 @@ out: unregister_blkdev(pktdev_major, DRIVER_NAME); out2: mempool_destroy(psd_pool); + bioset_free(pkt_bio_set); return ret; } @@ -2964,6 +2973,7 @@ static void __exit pkt_exit(void) unregister_blkdev(pktdev_major, DRIVER_NAME); mempool_destroy(psd_pool); + bioset_free(pkt_bio_set); } MODULE_DESCRIPTION("Packet writing layer for CD/DVD drives"); diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c index a809e3e9feb8..075662f2cf46 100644 --- a/drivers/block/ps3disk.c +++ b/drivers/block/ps3disk.c @@ -158,7 +158,7 @@ static int ps3disk_submit_request_sg(struct ps3_storage_device *dev, if (res) { dev_err(&dev->sbd.core, "%s:%u: %s failed %d\n", __func__, __LINE__, op, res); - __blk_end_request_all(req, -EIO); + __blk_end_request_all(req, BLK_STS_IOERR); return 0; } @@ -180,7 +180,7 @@ static int ps3disk_submit_flush_request(struct ps3_storage_device *dev, if (res) { dev_err(&dev->sbd.core, "%s:%u: sync cache failed 0x%llx\n", __func__, __LINE__, res); - __blk_end_request_all(req, -EIO); + __blk_end_request_all(req, BLK_STS_IOERR); return 0; } @@ -208,7 +208,7 @@ static void ps3disk_do_request(struct ps3_storage_device *dev, break; default: blk_dump_rq_flags(req, DEVICE_NAME " bad request"); - __blk_end_request_all(req, -EIO); + __blk_end_request_all(req, BLK_STS_IOERR); } } } @@ -231,7 +231,8 @@ static irqreturn_t ps3disk_interrupt(int irq, void *data) struct ps3_storage_device *dev = data; struct ps3disk_private *priv; struct request *req; - int res, read, error; + int res, read; + blk_status_t error; u64 tag, status; const char *op; @@ -269,7 +270,7 @@ static irqreturn_t ps3disk_interrupt(int irq, void *data) if (status) { dev_dbg(&dev->sbd.core, "%s:%u: %s failed 0x%llx\n", __func__, __LINE__, op, status); - error = -EIO; + error = BLK_STS_IOERR; } else { dev_dbg(&dev->sbd.core, "%s:%u: %s completed\n", __func__, __LINE__, op); diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c index 456b4fe21559..e0e81cacd781 100644 --- a/drivers/block/ps3vram.c +++ b/drivers/block/ps3vram.c @@ -428,7 +428,7 @@ static void ps3vram_cache_cleanup(struct ps3_system_bus_device *dev) kfree(priv->cache.tags); } -static int ps3vram_read(struct ps3_system_bus_device *dev, loff_t from, +static blk_status_t ps3vram_read(struct ps3_system_bus_device *dev, loff_t from, size_t len, size_t *retlen, u_char *buf) { struct ps3vram_priv *priv = ps3_system_bus_get_drvdata(dev); @@ -438,7 +438,7 @@ static int ps3vram_read(struct ps3_system_bus_device *dev, loff_t from, (unsigned int)from, len); if (from >= priv->size) - return -EIO; + return BLK_STS_IOERR; if (len > priv->size - from) len = priv->size - from; @@ -472,14 +472,14 @@ static int ps3vram_read(struct ps3_system_bus_device *dev, loff_t from, return 0; } -static int ps3vram_write(struct ps3_system_bus_device *dev, loff_t to, +static blk_status_t ps3vram_write(struct ps3_system_bus_device *dev, loff_t to, size_t len, size_t *retlen, const u_char *buf) { struct ps3vram_priv *priv = ps3_system_bus_get_drvdata(dev); unsigned int cached, count; if (to >= priv->size) - return -EIO; + return BLK_STS_IOERR; if (len > priv->size - to) len = priv->size - to; @@ -554,7 +554,7 @@ static struct bio *ps3vram_do_bio(struct ps3_system_bus_device *dev, int write = bio_data_dir(bio) == WRITE; const char *op = write ? "write" : "read"; loff_t offset = bio->bi_iter.bi_sector << 9; - int error = 0; + blk_status_t error = 0; struct bio_vec bvec; struct bvec_iter iter; struct bio *next; @@ -578,7 +578,7 @@ static struct bio *ps3vram_do_bio(struct ps3_system_bus_device *dev, if (retlen != len) { dev_err(&dev->core, "Short %s\n", op); - error = -EIO; + error = BLK_STS_IOERR; goto out; } @@ -593,7 +593,7 @@ out: next = bio_list_peek(&priv->list); spin_unlock_irq(&priv->lock); - bio->bi_error = error; + bio->bi_status = error; bio_endio(bio); return next; } @@ -606,7 +606,7 @@ static blk_qc_t ps3vram_make_request(struct request_queue *q, struct bio *bio) dev_dbg(&dev->core, "%s\n", __func__); - blk_queue_split(q, &bio, q->bio_split); + blk_queue_split(q, &bio); spin_lock_irq(&priv->lock); busy = !bio_list_empty(&priv->list); diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index c16f74547804..b008b6a98098 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -442,6 +442,8 @@ static DEFINE_SPINLOCK(rbd_client_list_lock); static struct kmem_cache *rbd_img_request_cache; static struct kmem_cache *rbd_obj_request_cache; +static struct bio_set *rbd_bio_clone; + static int rbd_major; static DEFINE_IDA(rbd_dev_id_ida); @@ -1363,7 +1365,7 @@ static struct bio *bio_clone_range(struct bio *bio_src, { struct bio *bio; - bio = bio_clone(bio_src, gfpmask); + bio = bio_clone_fast(bio_src, gfpmask, rbd_bio_clone); if (!bio) return NULL; /* ENOMEM */ @@ -2293,11 +2295,13 @@ static bool rbd_img_obj_end_request(struct rbd_obj_request *obj_request) rbd_assert(img_request->obj_request != NULL); more = obj_request->which < img_request->obj_request_count - 1; } else { + blk_status_t status = errno_to_blk_status(result); + rbd_assert(img_request->rq != NULL); - more = blk_update_request(img_request->rq, result, xferred); + more = blk_update_request(img_request->rq, status, xferred); if (!more) - __blk_mq_end_request(img_request->rq, result); + __blk_mq_end_request(img_request->rq, status); } return more; @@ -4150,17 +4154,17 @@ err_rq: obj_op_name(op_type), length, offset, result); ceph_put_snap_context(snapc); err: - blk_mq_end_request(rq, result); + blk_mq_end_request(rq, errno_to_blk_status(result)); } -static int rbd_queue_rq(struct blk_mq_hw_ctx *hctx, +static blk_status_t rbd_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { struct request *rq = bd->rq; struct work_struct *work = blk_mq_rq_to_pdu(rq); queue_work(rbd_wq, work); - return BLK_MQ_RQ_QUEUE_OK; + return BLK_STS_OK; } static void rbd_free_disk(struct rbd_device *rbd_dev) @@ -6414,8 +6418,16 @@ static int rbd_slab_init(void) if (!rbd_obj_request_cache) goto out_err; + rbd_assert(!rbd_bio_clone); + rbd_bio_clone = bioset_create(BIO_POOL_SIZE, 0, 0); + if (!rbd_bio_clone) + goto out_err_clone; + return 0; +out_err_clone: + kmem_cache_destroy(rbd_obj_request_cache); + rbd_obj_request_cache = NULL; out_err: kmem_cache_destroy(rbd_img_request_cache); rbd_img_request_cache = NULL; @@ -6431,6 +6443,10 @@ static void rbd_slab_exit(void) rbd_assert(rbd_img_request_cache); kmem_cache_destroy(rbd_img_request_cache); rbd_img_request_cache = NULL; + + rbd_assert(rbd_bio_clone); + bioset_free(rbd_bio_clone); + rbd_bio_clone = NULL; } static int __init rbd_init(void) diff --git a/drivers/block/rsxx/dev.c b/drivers/block/rsxx/dev.c index 9c566364ac9c..7f4acebf4657 100644 --- a/drivers/block/rsxx/dev.c +++ b/drivers/block/rsxx/dev.c @@ -149,9 +149,9 @@ static blk_qc_t rsxx_make_request(struct request_queue *q, struct bio *bio) { struct rsxx_cardinfo *card = q->queuedata; struct rsxx_bio_meta *bio_meta; - int st = -EINVAL; + blk_status_t st = BLK_STS_IOERR; - blk_queue_split(q, &bio, q->bio_split); + blk_queue_split(q, &bio); might_sleep(); @@ -161,15 +161,11 @@ static blk_qc_t rsxx_make_request(struct request_queue *q, struct bio *bio) if (bio_end_sector(bio) > get_capacity(card->gendisk)) goto req_err; - if (unlikely(card->halt)) { - st = -EFAULT; + if (unlikely(card->halt)) goto req_err; - } - if (unlikely(card->dma_fault)) { - st = (-EFAULT); + if (unlikely(card->dma_fault)) goto req_err; - } if (bio->bi_iter.bi_size == 0) { dev_err(CARD_TO_DEV(card), "size zero BIO!\n"); @@ -178,7 +174,7 @@ static blk_qc_t rsxx_make_request(struct request_queue *q, struct bio *bio) bio_meta = kmem_cache_alloc(bio_meta_pool, GFP_KERNEL); if (!bio_meta) { - st = -ENOMEM; + st = BLK_STS_RESOURCE; goto req_err; } @@ -205,7 +201,7 @@ queue_err: kmem_cache_free(bio_meta_pool, bio_meta); req_err: if (st) - bio->bi_error = st; + bio->bi_status = st; bio_endio(bio); return BLK_QC_T_NONE; } @@ -288,7 +284,6 @@ int rsxx_setup_dev(struct rsxx_cardinfo *card) } blk_queue_make_request(card->queue, rsxx_make_request); - blk_queue_bounce_limit(card->queue, BLK_BOUNCE_ANY); blk_queue_max_hw_sectors(card->queue, blkdev_max_hw_sectors); blk_queue_physical_block_size(card->queue, RSXX_HW_BLK_SIZE); diff --git a/drivers/block/rsxx/dma.c b/drivers/block/rsxx/dma.c index 5a20385f87d0..6a1b2177951c 100644 --- a/drivers/block/rsxx/dma.c +++ b/drivers/block/rsxx/dma.c @@ -611,7 +611,7 @@ static void rsxx_schedule_done(struct work_struct *work) mutex_unlock(&ctrl->work_lock); } -static int rsxx_queue_discard(struct rsxx_cardinfo *card, +static blk_status_t rsxx_queue_discard(struct rsxx_cardinfo *card, struct list_head *q, unsigned int laddr, rsxx_dma_cb cb, @@ -621,7 +621,7 @@ static int rsxx_queue_discard(struct rsxx_cardinfo *card, dma = kmem_cache_alloc(rsxx_dma_pool, GFP_KERNEL); if (!dma) - return -ENOMEM; + return BLK_STS_RESOURCE; dma->cmd = HW_CMD_BLK_DISCARD; dma->laddr = laddr; @@ -640,7 +640,7 @@ static int rsxx_queue_discard(struct rsxx_cardinfo *card, return 0; } -static int rsxx_queue_dma(struct rsxx_cardinfo *card, +static blk_status_t rsxx_queue_dma(struct rsxx_cardinfo *card, struct list_head *q, int dir, unsigned int dma_off, @@ -655,7 +655,7 @@ static int rsxx_queue_dma(struct rsxx_cardinfo *card, dma = kmem_cache_alloc(rsxx_dma_pool, GFP_KERNEL); if (!dma) - return -ENOMEM; + return BLK_STS_RESOURCE; dma->cmd = dir ? HW_CMD_BLK_WRITE : HW_CMD_BLK_READ; dma->laddr = laddr; @@ -677,7 +677,7 @@ static int rsxx_queue_dma(struct rsxx_cardinfo *card, return 0; } -int rsxx_dma_queue_bio(struct rsxx_cardinfo *card, +blk_status_t rsxx_dma_queue_bio(struct rsxx_cardinfo *card, struct bio *bio, atomic_t *n_dmas, rsxx_dma_cb cb, @@ -694,7 +694,7 @@ int rsxx_dma_queue_bio(struct rsxx_cardinfo *card, unsigned int dma_len; int dma_cnt[RSXX_MAX_TARGETS]; int tgt; - int st; + blk_status_t st; int i; addr8 = bio->bi_iter.bi_sector << 9; /* sectors are 512 bytes */ @@ -769,7 +769,6 @@ bvec_err: for (i = 0; i < card->n_targets; i++) rsxx_cleanup_dma_queue(&card->ctrl[i], &dma_list[i], FREE_DMA); - return st; } diff --git a/drivers/block/rsxx/rsxx_priv.h b/drivers/block/rsxx/rsxx_priv.h index 6bbc64d0f690..277f27e673a2 100644 --- a/drivers/block/rsxx/rsxx_priv.h +++ b/drivers/block/rsxx/rsxx_priv.h @@ -391,7 +391,7 @@ int rsxx_dma_cancel(struct rsxx_dma_ctrl *ctrl); void rsxx_dma_cleanup(void); void rsxx_dma_queue_reset(struct rsxx_cardinfo *card); int rsxx_dma_configure(struct rsxx_cardinfo *card); -int rsxx_dma_queue_bio(struct rsxx_cardinfo *card, +blk_status_t rsxx_dma_queue_bio(struct rsxx_cardinfo *card, struct bio *bio, atomic_t *n_dmas, rsxx_dma_cb cb, diff --git a/drivers/block/skd_main.c b/drivers/block/skd_main.c index 27833e4dae2a..d0368682bd43 100644 --- a/drivers/block/skd_main.c +++ b/drivers/block/skd_main.c @@ -451,8 +451,8 @@ static void skd_send_special_fitmsg(struct skd_device *skdev, struct skd_special_context *skspcl); static void skd_request_fn(struct request_queue *rq); static void skd_end_request(struct skd_device *skdev, - struct skd_request_context *skreq, int error); -static int skd_preop_sg_list(struct skd_device *skdev, + struct skd_request_context *skreq, blk_status_t status); +static bool skd_preop_sg_list(struct skd_device *skdev, struct skd_request_context *skreq); static void skd_postop_sg_list(struct skd_device *skdev, struct skd_request_context *skreq); @@ -491,7 +491,7 @@ static void skd_fail_all_pending(struct skd_device *skdev) if (req == NULL) break; blk_start_request(req); - __blk_end_request_all(req, -EIO); + __blk_end_request_all(req, BLK_STS_IOERR); } } @@ -545,7 +545,6 @@ static void skd_request_fn(struct request_queue *q) struct request *req = NULL; struct skd_scsi_request *scsi_req; unsigned long io_flags; - int error; u32 lba; u32 count; int data_dir; @@ -716,9 +715,7 @@ static void skd_request_fn(struct request_queue *q) if (!req->bio) goto skip_sg; - error = skd_preop_sg_list(skdev, skreq); - - if (error != 0) { + if (!skd_preop_sg_list(skdev, skreq)) { /* * Complete the native request with error. * Note that the request context is still at the @@ -730,7 +727,7 @@ static void skd_request_fn(struct request_queue *q) */ pr_debug("%s:%s:%d error Out\n", skdev->name, __func__, __LINE__); - skd_end_request(skdev, skreq, error); + skd_end_request(skdev, skreq, BLK_STS_RESOURCE); continue; } @@ -805,7 +802,7 @@ skip_sg: } static void skd_end_request(struct skd_device *skdev, - struct skd_request_context *skreq, int error) + struct skd_request_context *skreq, blk_status_t error) { if (unlikely(error)) { struct request *req = skreq->req; @@ -822,7 +819,7 @@ static void skd_end_request(struct skd_device *skdev, __blk_end_request_all(skreq->req, error); } -static int skd_preop_sg_list(struct skd_device *skdev, +static bool skd_preop_sg_list(struct skd_device *skdev, struct skd_request_context *skreq) { struct request *req = skreq->req; @@ -839,7 +836,7 @@ static int skd_preop_sg_list(struct skd_device *skdev, n_sg = blk_rq_map_sg(skdev->queue, req, sg); if (n_sg <= 0) - return -EINVAL; + return false; /* * Map scatterlist to PCI bus addresses. @@ -847,7 +844,7 @@ static int skd_preop_sg_list(struct skd_device *skdev, */ n_sg = pci_map_sg(skdev->pdev, sg, n_sg, pci_dir); if (n_sg <= 0) - return -EINVAL; + return false; SKD_ASSERT(n_sg <= skdev->sgs_per_request); @@ -882,7 +879,7 @@ static int skd_preop_sg_list(struct skd_device *skdev, } } - return 0; + return true; } static void skd_postop_sg_list(struct skd_device *skdev, @@ -2333,7 +2330,7 @@ static void skd_resolve_req_exception(struct skd_device *skdev, switch (skd_check_status(skdev, cmp_status, &skreq->err_info)) { case SKD_CHECK_STATUS_REPORT_GOOD: case SKD_CHECK_STATUS_REPORT_SMART_ALERT: - skd_end_request(skdev, skreq, 0); + skd_end_request(skdev, skreq, BLK_STS_OK); break; case SKD_CHECK_STATUS_BUSY_IMMINENT: @@ -2355,7 +2352,7 @@ static void skd_resolve_req_exception(struct skd_device *skdev, case SKD_CHECK_STATUS_REPORT_ERROR: default: - skd_end_request(skdev, skreq, -EIO); + skd_end_request(skdev, skreq, BLK_STS_IOERR); break; } } @@ -2748,7 +2745,7 @@ static int skd_isr_completion_posted(struct skd_device *skdev, * native request. */ if (likely(cmp_status == SAM_STAT_GOOD)) - skd_end_request(skdev, skreq, 0); + skd_end_request(skdev, skreq, BLK_STS_OK); else skd_resolve_req_exception(skdev, skreq); } @@ -3190,7 +3187,7 @@ static void skd_recover_requests(struct skd_device *skdev, int requeue) SKD_MAX_RETRIES) blk_requeue_request(skdev->queue, skreq->req); else - skd_end_request(skdev, skreq, -EIO); + skd_end_request(skdev, skreq, BLK_STS_IOERR); skreq->req = NULL; @@ -4276,6 +4273,7 @@ static int skd_cons_disk(struct skd_device *skdev) rc = -ENOMEM; goto err_out; } + blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH); skdev->queue = q; disk->queue = q; diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c index 3f3a3ab3d50a..6b16ead1da58 100644 --- a/drivers/block/sunvdc.c +++ b/drivers/block/sunvdc.c @@ -316,7 +316,7 @@ static void vdc_end_one(struct vdc_port *port, struct vio_dring_state *dr, rqe->req = NULL; - __blk_end_request(req, (desc->status ? -EIO : 0), desc->size); + __blk_end_request(req, (desc->status ? BLK_STS_IOERR : 0), desc->size); vdc_blk_queue_start(port); } @@ -1023,7 +1023,7 @@ static void vdc_queue_drain(struct vdc_port *port) struct request *req; while ((req = blk_fetch_request(port->disk->queue)) != NULL) - __blk_end_request_all(req, -EIO); + __blk_end_request_all(req, BLK_STS_IOERR); } static void vdc_ldc_reset_timer(unsigned long _arg) diff --git a/drivers/block/swim.c b/drivers/block/swim.c index 3064be6cf375..84434d3ea19b 100644 --- a/drivers/block/swim.c +++ b/drivers/block/swim.c @@ -493,7 +493,7 @@ static inline int swim_read_sector(struct floppy_state *fs, return ret; } -static int floppy_read_sectors(struct floppy_state *fs, +static blk_status_t floppy_read_sectors(struct floppy_state *fs, int req_sector, int sectors_nb, unsigned char *buffer) { @@ -516,7 +516,7 @@ static int floppy_read_sectors(struct floppy_state *fs, ret = swim_read_sector(fs, side, track, sector, buffer); if (try-- == 0) - return -EIO; + return BLK_STS_IOERR; } while (ret != 512); buffer += ret; @@ -553,7 +553,7 @@ static void do_fd_request(struct request_queue *q) req = swim_next_request(swd); while (req) { - int err = -EIO; + blk_status_t err = BLK_STS_IOERR; fs = req->rq_disk->private_data; if (blk_rq_pos(req) >= fs->total_secs) @@ -864,6 +864,8 @@ static int swim_floppy_init(struct swim_priv *swd) put_disk(swd->unit[drive].disk); goto exit_put_disks; } + blk_queue_bounce_limit(swd->unit[drive].disk->queue, + BLK_BOUNCE_HIGH); swd->unit[drive].disk->queue->queuedata = swd; swd->unit[drive].swd = swd; } diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c index ba4809c9bdba..9f931f8f6b4c 100644 --- a/drivers/block/swim3.c +++ b/drivers/block/swim3.c @@ -257,7 +257,7 @@ static unsigned int floppy_check_events(struct gendisk *disk, unsigned int clearing); static int floppy_revalidate(struct gendisk *disk); -static bool swim3_end_request(struct floppy_state *fs, int err, unsigned int nr_bytes) +static bool swim3_end_request(struct floppy_state *fs, blk_status_t err, unsigned int nr_bytes) { struct request *req = fs->cur_req; int rc; @@ -334,7 +334,7 @@ static void start_request(struct floppy_state *fs) if (fs->mdev->media_bay && check_media_bay(fs->mdev->media_bay) != MB_FD) { swim3_dbg("%s", " media bay absent, dropping req\n"); - swim3_end_request(fs, -ENODEV, 0); + swim3_end_request(fs, BLK_STS_IOERR, 0); continue; } @@ -350,12 +350,12 @@ static void start_request(struct floppy_state *fs) if (blk_rq_pos(req) >= fs->total_secs) { swim3_dbg(" pos out of bounds (%ld, max is %ld)\n", (long)blk_rq_pos(req), (long)fs->total_secs); - swim3_end_request(fs, -EIO, 0); + swim3_end_request(fs, BLK_STS_IOERR, 0); continue; } if (fs->ejected) { swim3_dbg("%s", " disk ejected\n"); - swim3_end_request(fs, -EIO, 0); + swim3_end_request(fs, BLK_STS_IOERR, 0); continue; } @@ -364,7 +364,7 @@ static void start_request(struct floppy_state *fs) fs->write_prot = swim3_readbit(fs, WRITE_PROT); if (fs->write_prot) { swim3_dbg("%s", " try to write, disk write protected\n"); - swim3_end_request(fs, -EIO, 0); + swim3_end_request(fs, BLK_STS_IOERR, 0); continue; } } @@ -548,7 +548,7 @@ static void act(struct floppy_state *fs) if (fs->retries > 5) { swim3_err("Wrong cylinder in transfer, want: %d got %d\n", fs->req_cyl, fs->cur_cyl); - swim3_end_request(fs, -EIO, 0); + swim3_end_request(fs, BLK_STS_IOERR, 0); fs->state = idle; return; } @@ -584,7 +584,7 @@ static void scan_timeout(unsigned long data) out_8(&sw->intr_enable, 0); fs->cur_cyl = -1; if (fs->retries > 5) { - swim3_end_request(fs, -EIO, 0); + swim3_end_request(fs, BLK_STS_IOERR, 0); fs->state = idle; start_request(fs); } else { @@ -608,7 +608,7 @@ static void seek_timeout(unsigned long data) out_8(&sw->select, RELAX); out_8(&sw->intr_enable, 0); swim3_err("%s", "Seek timeout\n"); - swim3_end_request(fs, -EIO, 0); + swim3_end_request(fs, BLK_STS_IOERR, 0); fs->state = idle; start_request(fs); spin_unlock_irqrestore(&swim3_lock, flags); @@ -637,7 +637,7 @@ static void settle_timeout(unsigned long data) goto unlock; } swim3_err("%s", "Seek settle timeout\n"); - swim3_end_request(fs, -EIO, 0); + swim3_end_request(fs, BLK_STS_IOERR, 0); fs->state = idle; start_request(fs); unlock: @@ -666,7 +666,7 @@ static void xfer_timeout(unsigned long data) swim3_err("Timeout %sing sector %ld\n", (rq_data_dir(fs->cur_req)==WRITE? "writ": "read"), (long)blk_rq_pos(fs->cur_req)); - swim3_end_request(fs, -EIO, 0); + swim3_end_request(fs, BLK_STS_IOERR, 0); fs->state = idle; start_request(fs); spin_unlock_irqrestore(&swim3_lock, flags); @@ -703,7 +703,7 @@ static irqreturn_t swim3_interrupt(int irq, void *dev_id) swim3_err("%s", "Seen sector but cyl=ff?\n"); fs->cur_cyl = -1; if (fs->retries > 5) { - swim3_end_request(fs, -EIO, 0); + swim3_end_request(fs, BLK_STS_IOERR, 0); fs->state = idle; start_request(fs); } else { @@ -786,7 +786,7 @@ static irqreturn_t swim3_interrupt(int irq, void *dev_id) swim3_err("Error %sing block %ld (err=%x)\n", rq_data_dir(req) == WRITE? "writ": "read", (long)blk_rq_pos(req), err); - swim3_end_request(fs, -EIO, 0); + swim3_end_request(fs, BLK_STS_IOERR, 0); fs->state = idle; } } else { @@ -795,7 +795,7 @@ static irqreturn_t swim3_interrupt(int irq, void *dev_id) swim3_err("fd dma error: stat=%x resid=%d\n", stat, resid); swim3_err(" state=%d, dir=%x, intr=%x, err=%x\n", fs->state, rq_data_dir(req), intr, err); - swim3_end_request(fs, -EIO, 0); + swim3_end_request(fs, BLK_STS_IOERR, 0); fs->state = idle; start_request(fs); break; @@ -1223,6 +1223,7 @@ static int swim3_attach(struct macio_dev *mdev, put_disk(disk); return -ENOMEM; } + blk_queue_bounce_limit(disk->queue, BLK_BOUNCE_HIGH); disk->queue->queuedata = &floppy_states[index]; if (index == 0) { @@ -1245,7 +1246,7 @@ static int swim3_attach(struct macio_dev *mdev, return 0; } -static struct of_device_id swim3_match[] = +static const struct of_device_id swim3_match[] = { { .name = "swim3", diff --git a/drivers/block/sx8.c b/drivers/block/sx8.c index c8e072caf56f..08586dc14e85 100644 --- a/drivers/block/sx8.c +++ b/drivers/block/sx8.c @@ -745,7 +745,7 @@ static unsigned int carm_fill_get_fw_ver(struct carm_host *host, static inline void carm_end_request_queued(struct carm_host *host, struct carm_request *crq, - int error) + blk_status_t error) { struct request *req = crq->rq; int rc; @@ -791,7 +791,7 @@ static inline void carm_round_robin(struct carm_host *host) } static inline void carm_end_rq(struct carm_host *host, struct carm_request *crq, - int error) + blk_status_t error) { carm_end_request_queued(host, crq, error); if (max_queue == 1) @@ -869,14 +869,14 @@ queue_one_request: sg = &crq->sg[0]; n_elem = blk_rq_map_sg(q, rq, sg); if (n_elem <= 0) { - carm_end_rq(host, crq, -EIO); + carm_end_rq(host, crq, BLK_STS_IOERR); return; /* request with no s/g entries? */ } /* map scatterlist to PCI bus addresses */ n_elem = pci_map_sg(host->pdev, sg, n_elem, pci_dir); if (n_elem <= 0) { - carm_end_rq(host, crq, -EIO); + carm_end_rq(host, crq, BLK_STS_IOERR); return; /* request with no s/g entries? */ } crq->n_elem = n_elem; @@ -937,7 +937,7 @@ queue_one_request: static void carm_handle_array_info(struct carm_host *host, struct carm_request *crq, u8 *mem, - int error) + blk_status_t error) { struct carm_port *port; u8 *msg_data = mem + sizeof(struct carm_array_info); @@ -997,7 +997,7 @@ out: static void carm_handle_scan_chan(struct carm_host *host, struct carm_request *crq, u8 *mem, - int error) + blk_status_t error) { u8 *msg_data = mem + IOC_SCAN_CHAN_OFFSET; unsigned int i, dev_count = 0; @@ -1029,7 +1029,7 @@ out: } static void carm_handle_generic(struct carm_host *host, - struct carm_request *crq, int error, + struct carm_request *crq, blk_status_t error, int cur_state, int next_state) { DPRINTK("ENTER\n"); @@ -1045,7 +1045,7 @@ static void carm_handle_generic(struct carm_host *host, } static inline void carm_handle_rw(struct carm_host *host, - struct carm_request *crq, int error) + struct carm_request *crq, blk_status_t error) { int pci_dir; @@ -1067,7 +1067,7 @@ static inline void carm_handle_resp(struct carm_host *host, u32 handle = le32_to_cpu(ret_handle_le); unsigned int msg_idx; struct carm_request *crq; - int error = (status == RMSG_OK) ? 0 : -EIO; + blk_status_t error = (status == RMSG_OK) ? 0 : BLK_STS_IOERR; u8 *mem; VPRINTK("ENTER, handle == 0x%x\n", handle); @@ -1155,7 +1155,7 @@ static inline void carm_handle_resp(struct carm_host *host, err_out: printk(KERN_WARNING DRV_NAME "(%s): BUG: unhandled message type %d/%d\n", pci_name(host->pdev), crq->msg_type, crq->msg_subtype); - carm_end_rq(host, crq, -EIO); + carm_end_rq(host, crq, BLK_STS_IOERR); } static inline void carm_handle_responses(struct carm_host *host) diff --git a/drivers/block/umem.c b/drivers/block/umem.c index c141cc3be22b..0677d2514665 100644 --- a/drivers/block/umem.c +++ b/drivers/block/umem.c @@ -454,7 +454,7 @@ static void process_page(unsigned long data) PCI_DMA_TODEVICE : PCI_DMA_FROMDEVICE); if (control & DMASCR_HARD_ERROR) { /* error */ - bio->bi_error = -EIO; + bio->bi_status = BLK_STS_IOERR; dev_printk(KERN_WARNING, &card->dev->dev, "I/O error on sector %d/%d\n", le32_to_cpu(desc->local_addr)>>9, @@ -529,7 +529,7 @@ static blk_qc_t mm_make_request(struct request_queue *q, struct bio *bio) (unsigned long long)bio->bi_iter.bi_sector, bio->bi_iter.bi_size); - blk_queue_split(q, &bio, q->bio_split); + blk_queue_split(q, &bio); spin_lock_irq(&card->lock); *card->biotail = bio; diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 553cc4c542b4..0297ad7c1452 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -64,15 +64,15 @@ struct virtblk_req { struct scatterlist sg[]; }; -static inline int virtblk_result(struct virtblk_req *vbr) +static inline blk_status_t virtblk_result(struct virtblk_req *vbr) { switch (vbr->status) { case VIRTIO_BLK_S_OK: - return 0; + return BLK_STS_OK; case VIRTIO_BLK_S_UNSUPP: - return -ENOTTY; + return BLK_STS_NOTSUPP; default: - return -EIO; + return BLK_STS_IOERR; } } @@ -214,7 +214,7 @@ static void virtblk_done(struct virtqueue *vq) spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags); } -static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, +static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { struct virtio_blk *vblk = hctx->queue->queuedata; @@ -246,7 +246,7 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, break; default: WARN_ON_ONCE(1); - return BLK_MQ_RQ_QUEUE_ERROR; + return BLK_STS_IOERR; } vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, type); @@ -276,8 +276,8 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, /* Out of mem doesn't actually happen, since we fall back * to direct descriptors */ if (err == -ENOMEM || err == -ENOSPC) - return BLK_MQ_RQ_QUEUE_BUSY; - return BLK_MQ_RQ_QUEUE_ERROR; + return BLK_STS_RESOURCE; + return BLK_STS_IOERR; } if (bd->last && virtqueue_kick_prepare(vblk->vqs[qid].vq)) @@ -286,7 +286,7 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, if (notify) virtqueue_notify(vblk->vqs[qid].vq); - return BLK_MQ_RQ_QUEUE_OK; + return BLK_STS_OK; } /* return id (s/n) string for *disk to *id_str @@ -307,7 +307,7 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str) goto out; blk_execute_rq(vblk->disk->queue, vblk->disk, req, false); - err = virtblk_result(blk_mq_rq_to_pdu(req)); + err = blk_status_to_errno(virtblk_result(blk_mq_rq_to_pdu(req))); out: blk_put_request(req); return err; @@ -720,9 +720,6 @@ static int virtblk_probe(struct virtio_device *vdev) /* We can handle whatever the host told us to handle. */ blk_queue_max_segments(q, vblk->sg_elems-2); - /* No need to bounce any requests */ - blk_queue_bounce_limit(q, BLK_BOUNCE_ANY); - /* No real sector limit. */ blk_queue_max_hw_sectors(q, -1U); diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index 726c32e35db9..fe7cd58c43d0 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -609,8 +609,6 @@ int xen_blkif_schedule(void *arg) unsigned long timeout; int ret; - xen_blkif_get(blkif); - set_freezable(); while (!kthread_should_stop()) { if (try_to_freeze()) @@ -665,7 +663,6 @@ purge_gnt_list: print_stats(ring); ring->xenblkd = NULL; - xen_blkif_put(blkif); return 0; } @@ -1069,20 +1066,17 @@ static void xen_blk_drain_io(struct xen_blkif_ring *ring) atomic_set(&blkif->drain, 0); } -/* - * Completion callback on the bio's. Called as bh->b_end_io() - */ - -static void __end_block_io_op(struct pending_req *pending_req, int error) +static void __end_block_io_op(struct pending_req *pending_req, + blk_status_t error) { /* An error fails the entire request. */ - if ((pending_req->operation == BLKIF_OP_FLUSH_DISKCACHE) && - (error == -EOPNOTSUPP)) { + if (pending_req->operation == BLKIF_OP_FLUSH_DISKCACHE && + error == BLK_STS_NOTSUPP) { pr_debug("flush diskcache op failed, not supported\n"); xen_blkbk_flush_diskcache(XBT_NIL, pending_req->ring->blkif->be, 0); pending_req->status = BLKIF_RSP_EOPNOTSUPP; - } else if ((pending_req->operation == BLKIF_OP_WRITE_BARRIER) && - (error == -EOPNOTSUPP)) { + } else if (pending_req->operation == BLKIF_OP_WRITE_BARRIER && + error == BLK_STS_NOTSUPP) { pr_debug("write barrier op failed, not supported\n"); xen_blkbk_barrier(XBT_NIL, pending_req->ring->blkif->be, 0); pending_req->status = BLKIF_RSP_EOPNOTSUPP; @@ -1106,7 +1100,7 @@ static void __end_block_io_op(struct pending_req *pending_req, int error) */ static void end_block_io_op(struct bio *bio) { - __end_block_io_op(bio->bi_private, bio->bi_error); + __end_block_io_op(bio->bi_private, bio->bi_status); bio_put(bio); } @@ -1423,7 +1417,7 @@ static int dispatch_rw_block_io(struct xen_blkif_ring *ring, for (i = 0; i < nbio; i++) bio_put(biolist[i]); atomic_set(&pending_req->pendcnt, 1); - __end_block_io_op(pending_req, -EINVAL); + __end_block_io_op(pending_req, BLK_STS_RESOURCE); msleep(1); /* back off a bit */ return -EIO; } @@ -1436,34 +1430,35 @@ static int dispatch_rw_block_io(struct xen_blkif_ring *ring, static void make_response(struct xen_blkif_ring *ring, u64 id, unsigned short op, int st) { - struct blkif_response resp; + struct blkif_response *resp; unsigned long flags; union blkif_back_rings *blk_rings; int notify; - resp.id = id; - resp.operation = op; - resp.status = st; - spin_lock_irqsave(&ring->blk_ring_lock, flags); blk_rings = &ring->blk_rings; /* Place on the response ring for the relevant domain. */ switch (ring->blkif->blk_protocol) { case BLKIF_PROTOCOL_NATIVE: - memcpy(RING_GET_RESPONSE(&blk_rings->native, blk_rings->native.rsp_prod_pvt), - &resp, sizeof(resp)); + resp = RING_GET_RESPONSE(&blk_rings->native, + blk_rings->native.rsp_prod_pvt); break; case BLKIF_PROTOCOL_X86_32: - memcpy(RING_GET_RESPONSE(&blk_rings->x86_32, blk_rings->x86_32.rsp_prod_pvt), - &resp, sizeof(resp)); + resp = RING_GET_RESPONSE(&blk_rings->x86_32, + blk_rings->x86_32.rsp_prod_pvt); break; case BLKIF_PROTOCOL_X86_64: - memcpy(RING_GET_RESPONSE(&blk_rings->x86_64, blk_rings->x86_64.rsp_prod_pvt), - &resp, sizeof(resp)); + resp = RING_GET_RESPONSE(&blk_rings->x86_64, + blk_rings->x86_64.rsp_prod_pvt); break; default: BUG(); } + + resp->id = id; + resp->operation = op; + resp->status = st; + blk_rings->common.rsp_prod_pvt++; RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&blk_rings->common, notify); spin_unlock_irqrestore(&ring->blk_ring_lock, flags); diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h index dea61f6ab8cb..ecb35fe8ca8d 100644 --- a/drivers/block/xen-blkback/common.h +++ b/drivers/block/xen-blkback/common.h @@ -75,9 +75,8 @@ extern unsigned int xenblk_max_queues; struct blkif_common_request { char dummy; }; -struct blkif_common_response { - char dummy; -}; + +/* i386 protocol version */ struct blkif_x86_32_request_rw { uint8_t nr_segments; /* number of segments */ @@ -129,14 +128,6 @@ struct blkif_x86_32_request { } u; } __attribute__((__packed__)); -/* i386 protocol version */ -#pragma pack(push, 4) -struct blkif_x86_32_response { - uint64_t id; /* copied from request */ - uint8_t operation; /* copied from request */ - int16_t status; /* BLKIF_RSP_??? */ -}; -#pragma pack(pop) /* x86_64 protocol version */ struct blkif_x86_64_request_rw { @@ -193,18 +184,12 @@ struct blkif_x86_64_request { } u; } __attribute__((__packed__)); -struct blkif_x86_64_response { - uint64_t __attribute__((__aligned__(8))) id; - uint8_t operation; /* copied from request */ - int16_t status; /* BLKIF_RSP_??? */ -}; - DEFINE_RING_TYPES(blkif_common, struct blkif_common_request, - struct blkif_common_response); + struct blkif_response); DEFINE_RING_TYPES(blkif_x86_32, struct blkif_x86_32_request, - struct blkif_x86_32_response); + struct blkif_response __packed); DEFINE_RING_TYPES(blkif_x86_64, struct blkif_x86_64_request, - struct blkif_x86_64_response); + struct blkif_response); union blkif_back_rings { struct blkif_back_ring native; @@ -281,6 +266,7 @@ struct xen_blkif_ring { wait_queue_head_t wq; atomic_t inflight; + bool active; /* One thread per blkif ring. */ struct task_struct *xenblkd; unsigned int waiting_reqs; diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index 1f3dfaa54d87..792da683e70d 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -159,7 +159,7 @@ static int xen_blkif_alloc_rings(struct xen_blkif *blkif) init_waitqueue_head(&ring->shutdown_wq); ring->blkif = blkif; ring->st_print = jiffies; - xen_blkif_get(blkif); + ring->active = true; } return 0; @@ -249,10 +249,12 @@ static int xen_blkif_disconnect(struct xen_blkif *blkif) struct xen_blkif_ring *ring = &blkif->rings[r]; unsigned int i = 0; + if (!ring->active) + continue; + if (ring->xenblkd) { kthread_stop(ring->xenblkd); wake_up(&ring->shutdown_wq); - ring->xenblkd = NULL; } /* The above kthread_stop() guarantees that at this point we @@ -296,7 +298,7 @@ static int xen_blkif_disconnect(struct xen_blkif *blkif) BUG_ON(ring->free_pages_num != 0); BUG_ON(ring->persistent_gnt_c != 0); WARN_ON(i != (XEN_BLKIF_REQS_PER_PAGE * blkif->nr_ring_pages)); - xen_blkif_put(blkif); + ring->active = false; } blkif->nr_ring_pages = 0; /* @@ -312,9 +314,10 @@ static int xen_blkif_disconnect(struct xen_blkif *blkif) static void xen_blkif_free(struct xen_blkif *blkif) { - - xen_blkif_disconnect(blkif); + WARN_ON(xen_blkif_disconnect(blkif)); xen_vbd_free(&blkif->vbd); + kfree(blkif->be->mode); + kfree(blkif->be); /* Make sure everything is drained before shutting down */ kmem_cache_free(xen_blkif_cachep, blkif); @@ -511,8 +514,6 @@ static int xen_blkbk_remove(struct xenbus_device *dev) xen_blkif_put(be->blkif); } - kfree(be->mode); - kfree(be); return 0; } diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 39459631667c..c852ed3c01d5 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -110,11 +110,6 @@ struct blk_shadow { unsigned long associated_id; }; -struct split_bio { - struct bio *bio; - atomic_t pending; -}; - struct blkif_req { int error; }; @@ -881,7 +876,7 @@ static inline bool blkif_request_flush_invalid(struct request *req, !info->feature_fua)); } -static int blkif_queue_rq(struct blk_mq_hw_ctx *hctx, +static blk_status_t blkif_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *qd) { unsigned long flags; @@ -904,16 +899,16 @@ static int blkif_queue_rq(struct blk_mq_hw_ctx *hctx, flush_requests(rinfo); spin_unlock_irqrestore(&rinfo->ring_lock, flags); - return BLK_MQ_RQ_QUEUE_OK; + return BLK_STS_OK; out_err: spin_unlock_irqrestore(&rinfo->ring_lock, flags); - return BLK_MQ_RQ_QUEUE_ERROR; + return BLK_STS_IOERR; out_busy: spin_unlock_irqrestore(&rinfo->ring_lock, flags); blk_mq_stop_hw_queue(hctx); - return BLK_MQ_RQ_QUEUE_BUSY; + return BLK_STS_RESOURCE; } static void blkif_complete_rq(struct request *rq) @@ -958,9 +953,6 @@ static void blkif_set_queue_limits(struct blkfront_info *info) /* Make sure buffer addresses are sector-aligned. */ blk_queue_dma_alignment(rq, 511); - - /* Make sure we don't use bounce buffers. */ - blk_queue_bounce_limit(rq, BLK_BOUNCE_ANY); } static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size, @@ -1601,14 +1593,18 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) continue; } - blkif_req(req)->error = (bret->status == BLKIF_RSP_OKAY) ? 0 : -EIO; + if (bret->status == BLKIF_RSP_OKAY) + blkif_req(req)->error = BLK_STS_OK; + else + blkif_req(req)->error = BLK_STS_IOERR; + switch (bret->operation) { case BLKIF_OP_DISCARD: if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) { struct request_queue *rq = info->rq; printk(KERN_WARNING "blkfront: %s: %s op failed\n", info->gd->disk_name, op_name(bret->operation)); - blkif_req(req)->error = -EOPNOTSUPP; + blkif_req(req)->error = BLK_STS_NOTSUPP; info->feature_discard = 0; info->feature_secdiscard = 0; queue_flag_clear(QUEUE_FLAG_DISCARD, rq); @@ -1626,11 +1622,11 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) rinfo->shadow[id].req.u.rw.nr_segments == 0)) { printk(KERN_WARNING "blkfront: %s: empty %s op failed\n", info->gd->disk_name, op_name(bret->operation)); - blkif_req(req)->error = -EOPNOTSUPP; + blkif_req(req)->error = BLK_STS_NOTSUPP; } if (unlikely(blkif_req(req)->error)) { - if (blkif_req(req)->error == -EOPNOTSUPP) - blkif_req(req)->error = 0; + if (blkif_req(req)->error == BLK_STS_NOTSUPP) + blkif_req(req)->error = BLK_STS_OK; info->feature_fua = 0; info->feature_flush = 0; xlvbd_flush(info); @@ -1996,28 +1992,13 @@ static int blkfront_probe(struct xenbus_device *dev, return 0; } -static void split_bio_end(struct bio *bio) -{ - struct split_bio *split_bio = bio->bi_private; - - if (atomic_dec_and_test(&split_bio->pending)) { - split_bio->bio->bi_phys_segments = 0; - split_bio->bio->bi_error = bio->bi_error; - bio_endio(split_bio->bio); - kfree(split_bio); - } - bio_put(bio); -} - static int blkif_recover(struct blkfront_info *info) { - unsigned int i, r_index; + unsigned int r_index; struct request *req, *n; int rc; - struct bio *bio, *cloned_bio; - unsigned int segs, offset; - int pending, size; - struct split_bio *split_bio; + struct bio *bio; + unsigned int segs; blkfront_gather_backend_features(info); /* Reset limits changed by blk_mq_update_nr_hw_queues(). */ @@ -2056,34 +2037,6 @@ static int blkif_recover(struct blkfront_info *info) while ((bio = bio_list_pop(&info->bio_list)) != NULL) { /* Traverse the list of pending bios and re-queue them */ - if (bio_segments(bio) > segs) { - /* - * This bio has more segments than what we can - * handle, we have to split it. - */ - pending = (bio_segments(bio) + segs - 1) / segs; - split_bio = kzalloc(sizeof(*split_bio), GFP_NOIO); - BUG_ON(split_bio == NULL); - atomic_set(&split_bio->pending, pending); - split_bio->bio = bio; - for (i = 0; i < pending; i++) { - offset = (i * segs * XEN_PAGE_SIZE) >> 9; - size = min((unsigned int)(segs * XEN_PAGE_SIZE) >> 9, - (unsigned int)bio_sectors(bio) - offset); - cloned_bio = bio_clone(bio, GFP_NOIO); - BUG_ON(cloned_bio == NULL); - bio_trim(cloned_bio, offset, size); - cloned_bio->bi_private = split_bio; - cloned_bio->bi_end_io = split_bio_end; - submit_bio(cloned_bio); - } - /* - * Now we have to wait for all those smaller bios to - * end, so we can also end the "parent" bio. - */ - continue; - } - /* We don't need to split this bio */ submit_bio(bio); } @@ -2137,7 +2090,7 @@ static int blkfront_resume(struct xenbus_device *dev) merge_bio.tail = shadow[j].request->biotail; bio_list_merge(&info->bio_list, &merge_bio); shadow[j].request->bio = NULL; - blk_mq_end_request(shadow[j].request, 0); + blk_mq_end_request(shadow[j].request, BLK_STS_OK); } } diff --git a/drivers/block/xsysace.c b/drivers/block/xsysace.c index 757dce2147e0..14459d66ef0c 100644 --- a/drivers/block/xsysace.c +++ b/drivers/block/xsysace.c @@ -471,7 +471,7 @@ static struct request *ace_get_next_request(struct request_queue *q) if (!blk_rq_is_passthrough(req)) break; blk_start_request(req); - __blk_end_request_all(req, -EIO); + __blk_end_request_all(req, BLK_STS_IOERR); } return req; } @@ -499,11 +499,11 @@ static void ace_fsm_dostate(struct ace_device *ace) /* Drop all in-flight and pending requests */ if (ace->req) { - __blk_end_request_all(ace->req, -EIO); + __blk_end_request_all(ace->req, BLK_STS_IOERR); ace->req = NULL; } while ((req = blk_fetch_request(ace->queue)) != NULL) - __blk_end_request_all(req, -EIO); + __blk_end_request_all(req, BLK_STS_IOERR); /* Drop back to IDLE state and notify waiters */ ace->fsm_state = ACE_FSM_STATE_IDLE; @@ -728,7 +728,7 @@ static void ace_fsm_dostate(struct ace_device *ace) } /* bio finished; is there another one? */ - if (__blk_end_request_cur(ace->req, 0)) { + if (__blk_end_request_cur(ace->req, BLK_STS_OK)) { /* dev_dbg(ace->dev, "next block; h=%u c=%u\n", * blk_rq_sectors(ace->req), * blk_rq_cur_sectors(ace->req)); @@ -993,6 +993,7 @@ static int ace_setup(struct ace_device *ace) if (ace->queue == NULL) goto err_blk_initq; blk_queue_logical_block_size(ace->queue, 512); + blk_queue_bounce_limit(ace->queue, BLK_BOUNCE_HIGH); /* * Allocate and initialize GD structure diff --git a/drivers/block/z2ram.c b/drivers/block/z2ram.c index 968f9e52effa..41c95c9b2ab4 100644 --- a/drivers/block/z2ram.c +++ b/drivers/block/z2ram.c @@ -74,14 +74,14 @@ static void do_z2_request(struct request_queue *q) while (req) { unsigned long start = blk_rq_pos(req) << 9; unsigned long len = blk_rq_cur_bytes(req); - int err = 0; + blk_status_t err = BLK_STS_OK; if (start + len > z2ram_size) { pr_err(DEVICE_NAME ": bad access: block=%llu, " "count=%u\n", (unsigned long long)blk_rq_pos(req), blk_rq_cur_sectors(req)); - err = -EIO; + err = BLK_STS_IOERR; goto done; } while (len) { diff --git a/drivers/bluetooth/btmrvl_main.c b/drivers/bluetooth/btmrvl_main.c index c38cb5b91291..fe850f0567cb 100644 --- a/drivers/bluetooth/btmrvl_main.c +++ b/drivers/bluetooth/btmrvl_main.c @@ -602,7 +602,7 @@ static int btmrvl_service_main_thread(void *data) struct btmrvl_thread *thread = data; struct btmrvl_private *priv = thread->priv; struct btmrvl_adapter *adapter = priv->adapter; - wait_queue_t wait; + wait_queue_entry_t wait; struct sk_buff *skb; ulong flags; diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 76c952fd9ab9..e36d160c458f 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -2178,6 +2178,12 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf, if (!q) return -ENXIO; + if (!blk_queue_scsi_passthrough(q)) { + WARN_ONCE(true, + "Attempt read CDDA info through a non-SCSI queue\n"); + return -EINVAL; + } + cdi->last_sense = 0; while (nframes) { @@ -2195,7 +2201,6 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf, break; } req = scsi_req(rq); - scsi_req_init(rq); ret = blk_rq_map_user(q, rq, NULL, ubuf, len, GFP_KERNEL); if (ret) { diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c index 1372763a948f..6495b03f576c 100644 --- a/drivers/cdrom/gdrom.c +++ b/drivers/cdrom/gdrom.c @@ -583,7 +583,8 @@ static int gdrom_set_interrupt_handlers(void) */ static void gdrom_readdisk_dma(struct work_struct *work) { - int err, block, block_cnt; + int block, block_cnt; + blk_status_t err; struct packet_command *read_command; struct list_head *elem, *next; struct request *req; @@ -641,7 +642,7 @@ static void gdrom_readdisk_dma(struct work_struct *work) __raw_writeb(1, GDROM_DMA_STATUS_REG); wait_event_interruptible_timeout(request_queue, gd.transfer == 0, GDROM_DEFAULT_TIMEOUT); - err = gd.transfer ? -EIO : 0; + err = gd.transfer ? BLK_STS_IOERR : BLK_STS_OK; gd.transfer = 0; gd.pending = 0; /* now seek to take the request spinlock @@ -670,11 +671,11 @@ static void gdrom_request(struct request_queue *rq) break; case REQ_OP_WRITE: pr_notice("Read only device - write request ignored\n"); - __blk_end_request_all(req, -EIO); + __blk_end_request_all(req, BLK_STS_IOERR); break; default: printk(KERN_DEBUG "gdrom: Non-fs request ignored\n"); - __blk_end_request_all(req, -EIO); + __blk_end_request_all(req, BLK_STS_IOERR); break; } } @@ -812,6 +813,7 @@ static int probe_gdrom(struct platform_device *devptr) err = -ENOMEM; goto probe_fail_requestq; } + blk_queue_bounce_limit(gd.gdrom_rq, BLK_BOUNCE_HIGH); err = probe_gdrom_setupqueue(); if (err) diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c index d165af8abe36..a5c6cfe71a8e 100644 --- a/drivers/char/ipmi/ipmi_watchdog.c +++ b/drivers/char/ipmi/ipmi_watchdog.c @@ -821,7 +821,7 @@ static ssize_t ipmi_read(struct file *file, loff_t *ppos) { int rv = 0; - wait_queue_t wait; + wait_queue_entry_t wait; if (count <= 0) return 0; diff --git a/drivers/char/random.c b/drivers/char/random.c index e870f329db88..01a260f67437 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -803,13 +803,13 @@ static int crng_fast_load(const char *cp, size_t len) p[crng_init_cnt % CHACHA20_KEY_SIZE] ^= *cp; cp++; crng_init_cnt++; len--; } + spin_unlock_irqrestore(&primary_crng.lock, flags); if (crng_init_cnt >= CRNG_INIT_CNT_THRESH) { invalidate_batched_entropy(); crng_init = 1; wake_up_interruptible(&crng_init_wait); pr_notice("random: fast init done\n"); } - spin_unlock_irqrestore(&primary_crng.lock, flags); return 1; } @@ -841,6 +841,7 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r) } memzero_explicit(&buf, sizeof(buf)); crng->init_time = jiffies; + spin_unlock_irqrestore(&primary_crng.lock, flags); if (crng == &primary_crng && crng_init < 2) { invalidate_batched_entropy(); crng_init = 2; @@ -848,7 +849,6 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r) wake_up_interruptible(&crng_init_wait); pr_notice("random: crng init done\n"); } - spin_unlock_irqrestore(&primary_crng.lock, flags); } static inline void crng_wait_ready(void) @@ -2041,8 +2041,8 @@ static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u64); u64 get_random_u64(void) { u64 ret; - bool use_lock = crng_init < 2; - unsigned long flags; + bool use_lock = READ_ONCE(crng_init) < 2; + unsigned long flags = 0; struct batched_entropy *batch; #if BITS_PER_LONG == 64 @@ -2073,8 +2073,8 @@ static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u32); u32 get_random_u32(void) { u32 ret; - bool use_lock = crng_init < 2; - unsigned long flags; + bool use_lock = READ_ONCE(crng_init) < 2; + unsigned long flags = 0; struct batched_entropy *batch; if (arch_get_random_int(&ret)) diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c index b917b9d5f710..c378c7b15d49 100644 --- a/drivers/char/tpm/tpm_crb.c +++ b/drivers/char/tpm/tpm_crb.c @@ -27,10 +27,9 @@ #define ACPI_SIG_TPM2 "TPM2" -static const u8 CRB_ACPI_START_UUID[] = { - /* 0000 */ 0xAB, 0x6C, 0xBF, 0x6B, 0x63, 0x54, 0x14, 0x47, - /* 0008 */ 0xB7, 0xCD, 0xF0, 0x20, 0x3C, 0x03, 0x68, 0xD4 -}; +static const guid_t crb_acpi_start_guid = + GUID_INIT(0x6BBF6CAB, 0x5463, 0x4714, + 0xB7, 0xCD, 0xF0, 0x20, 0x3C, 0x03, 0x68, 0xD4); enum crb_defaults { CRB_ACPI_START_REVISION_ID = 1, @@ -266,7 +265,7 @@ static int crb_do_acpi_start(struct tpm_chip *chip) int rc; obj = acpi_evaluate_dsm(chip->acpi_dev_handle, - CRB_ACPI_START_UUID, + &crb_acpi_start_guid, CRB_ACPI_START_REVISION_ID, CRB_ACPI_START_INDEX, NULL); diff --git a/drivers/char/tpm/tpm_ppi.c b/drivers/char/tpm/tpm_ppi.c index 692a2c6ae036..86dd8521feef 100644 --- a/drivers/char/tpm/tpm_ppi.c +++ b/drivers/char/tpm/tpm_ppi.c @@ -32,20 +32,16 @@ #define PPI_VS_REQ_START 128 #define PPI_VS_REQ_END 255 -static const u8 tpm_ppi_uuid[] = { - 0xA6, 0xFA, 0xDD, 0x3D, - 0x1B, 0x36, - 0xB4, 0x4E, - 0xA4, 0x24, - 0x8D, 0x10, 0x08, 0x9D, 0x16, 0x53 -}; +static const guid_t tpm_ppi_guid = + GUID_INIT(0x3DDDFAA6, 0x361B, 0x4EB4, + 0xA4, 0x24, 0x8D, 0x10, 0x08, 0x9D, 0x16, 0x53); static inline union acpi_object * tpm_eval_dsm(acpi_handle ppi_handle, int func, acpi_object_type type, union acpi_object *argv4) { BUG_ON(!ppi_handle); - return acpi_evaluate_dsm_typed(ppi_handle, tpm_ppi_uuid, + return acpi_evaluate_dsm_typed(ppi_handle, &tpm_ppi_guid, TPM_PPI_REVISION_ID, func, argv4, type); } @@ -107,7 +103,7 @@ static ssize_t tpm_store_ppi_request(struct device *dev, * is updated with function index from SUBREQ to SUBREQ2 since PPI * version 1.1 */ - if (acpi_check_dsm(chip->acpi_dev_handle, tpm_ppi_uuid, + if (acpi_check_dsm(chip->acpi_dev_handle, &tpm_ppi_guid, TPM_PPI_REVISION_ID, 1 << TPM_PPI_FN_SUBREQ2)) func = TPM_PPI_FN_SUBREQ2; @@ -268,7 +264,7 @@ static ssize_t show_ppi_operations(acpi_handle dev_handle, char *buf, u32 start, "User not required", }; - if (!acpi_check_dsm(dev_handle, tpm_ppi_uuid, TPM_PPI_REVISION_ID, + if (!acpi_check_dsm(dev_handle, &tpm_ppi_guid, TPM_PPI_REVISION_ID, 1 << TPM_PPI_FN_GETOPR)) return -EPERM; @@ -341,12 +337,12 @@ void tpm_add_ppi(struct tpm_chip *chip) if (!chip->acpi_dev_handle) return; - if (!acpi_check_dsm(chip->acpi_dev_handle, tpm_ppi_uuid, + if (!acpi_check_dsm(chip->acpi_dev_handle, &tpm_ppi_guid, TPM_PPI_REVISION_ID, 1 << TPM_PPI_FN_VERSION)) return; /* Cache PPI version string. */ - obj = acpi_evaluate_dsm_typed(chip->acpi_dev_handle, tpm_ppi_uuid, + obj = acpi_evaluate_dsm_typed(chip->acpi_dev_handle, &tpm_ppi_guid, TPM_PPI_REVISION_ID, TPM_PPI_FN_VERSION, NULL, ACPI_TYPE_STRING); if (obj) { diff --git a/drivers/clk/meson/Kconfig b/drivers/clk/meson/Kconfig index 19480bcc7046..2f29ee1a4d00 100644 --- a/drivers/clk/meson/Kconfig +++ b/drivers/clk/meson/Kconfig @@ -14,6 +14,7 @@ config COMMON_CLK_MESON8B config COMMON_CLK_GXBB bool depends on COMMON_CLK_AMLOGIC + select RESET_CONTROLLER help Support for the clock controller on AmLogic S905 devices, aka gxbb. Say Y if you want peripherals and CPU frequency scaling to work. diff --git a/drivers/clk/sunxi-ng/Kconfig b/drivers/clk/sunxi-ng/Kconfig index b0d551a8efe4..eb89c7801f00 100644 --- a/drivers/clk/sunxi-ng/Kconfig +++ b/drivers/clk/sunxi-ng/Kconfig @@ -156,6 +156,7 @@ config SUN8I_R_CCU bool "Support for Allwinner SoCs' PRCM CCUs" select SUNXI_CCU_DIV select SUNXI_CCU_GATE + select SUNXI_CCU_MP default MACH_SUN8I || (ARCH_SUNXI && ARM64) endif diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-a64.h b/drivers/clk/sunxi-ng/ccu-sun50i-a64.h index 9b3cd24b78d2..061b6fbb4f95 100644 --- a/drivers/clk/sunxi-ng/ccu-sun50i-a64.h +++ b/drivers/clk/sunxi-ng/ccu-sun50i-a64.h @@ -31,7 +31,9 @@ #define CLK_PLL_VIDEO0_2X 8 #define CLK_PLL_VE 9 #define CLK_PLL_DDR0 10 -#define CLK_PLL_PERIPH0 11 + +/* PLL_PERIPH0 exported for PRCM */ + #define CLK_PLL_PERIPH0_2X 12 #define CLK_PLL_PERIPH1 13 #define CLK_PLL_PERIPH1_2X 14 diff --git a/drivers/clk/sunxi-ng/ccu-sun5i.c b/drivers/clk/sunxi-ng/ccu-sun5i.c index 5c476f966a72..5372bf8be5e6 100644 --- a/drivers/clk/sunxi-ng/ccu-sun5i.c +++ b/drivers/clk/sunxi-ng/ccu-sun5i.c @@ -243,7 +243,7 @@ static SUNXI_CCU_GATE(ahb_ss_clk, "ahb-ss", "ahb", static SUNXI_CCU_GATE(ahb_dma_clk, "ahb-dma", "ahb", 0x060, BIT(6), 0); static SUNXI_CCU_GATE(ahb_bist_clk, "ahb-bist", "ahb", - 0x060, BIT(6), 0); + 0x060, BIT(7), 0); static SUNXI_CCU_GATE(ahb_mmc0_clk, "ahb-mmc0", "ahb", 0x060, BIT(8), 0); static SUNXI_CCU_GATE(ahb_mmc1_clk, "ahb-mmc1", "ahb", diff --git a/drivers/clk/sunxi-ng/ccu-sun6i-a31.c b/drivers/clk/sunxi-ng/ccu-sun6i-a31.c index 89e68d29bf45..df97e25aec76 100644 --- a/drivers/clk/sunxi-ng/ccu-sun6i-a31.c +++ b/drivers/clk/sunxi-ng/ccu-sun6i-a31.c @@ -556,7 +556,7 @@ static SUNXI_CCU_M_WITH_MUX_GATE(lcd0_ch1_clk, "lcd0-ch1", lcd_ch1_parents, 0x12c, 0, 4, 24, 3, BIT(31), CLK_SET_RATE_PARENT); static SUNXI_CCU_M_WITH_MUX_GATE(lcd1_ch1_clk, "lcd1-ch1", lcd_ch1_parents, - 0x12c, 0, 4, 24, 3, BIT(31), + 0x130, 0, 4, 24, 3, BIT(31), CLK_SET_RATE_PARENT); static const char * const csi_sclk_parents[] = { "pll-video0", "pll-video1", diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-h3.h b/drivers/clk/sunxi-ng/ccu-sun8i-h3.h index 85973d1e8165..1b4baea37d81 100644 --- a/drivers/clk/sunxi-ng/ccu-sun8i-h3.h +++ b/drivers/clk/sunxi-ng/ccu-sun8i-h3.h @@ -29,7 +29,9 @@ #define CLK_PLL_VIDEO 6 #define CLK_PLL_VE 7 #define CLK_PLL_DDR 8 -#define CLK_PLL_PERIPH0 9 + +/* PLL_PERIPH0 exported for PRCM */ + #define CLK_PLL_PERIPH0_2X 10 #define CLK_PLL_GPU 11 #define CLK_PLL_PERIPH1 12 diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-v3s.c b/drivers/clk/sunxi-ng/ccu-sun8i-v3s.c index e58706b40ae9..6297add857b5 100644 --- a/drivers/clk/sunxi-ng/ccu-sun8i-v3s.c +++ b/drivers/clk/sunxi-ng/ccu-sun8i-v3s.c @@ -537,7 +537,7 @@ static struct ccu_reset_map sun8i_v3s_ccu_resets[] = { [RST_BUS_EMAC] = { 0x2c0, BIT(17) }, [RST_BUS_HSTIMER] = { 0x2c0, BIT(19) }, [RST_BUS_SPI0] = { 0x2c0, BIT(20) }, - [RST_BUS_OTG] = { 0x2c0, BIT(23) }, + [RST_BUS_OTG] = { 0x2c0, BIT(24) }, [RST_BUS_EHCI0] = { 0x2c0, BIT(26) }, [RST_BUS_OHCI0] = { 0x2c0, BIT(29) }, diff --git a/drivers/cpufreq/pasemi-cpufreq.c b/drivers/cpufreq/pasemi-cpufreq.c index 35dd4d7ffee0..b257fc7d5204 100644 --- a/drivers/cpufreq/pasemi-cpufreq.c +++ b/drivers/cpufreq/pasemi-cpufreq.c @@ -226,7 +226,7 @@ static int pas_cpufreq_cpu_exit(struct cpufreq_policy *policy) * We don't support CPU hotplug. Don't unmap after the system * has already made it to a running state. */ - if (system_state != SYSTEM_BOOTING) + if (system_state >= SYSTEM_RUNNING) return 0; if (sdcasr_mapbase) diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 2706be7ed334..60bb64f4329d 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -220,6 +220,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, entered_state = target_state->enter(dev, drv, index); start_critical_timings(); + sched_clock_idle_wakeup_event(); time_end = ns_to_ktime(local_clock()); trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu); diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig index fb1e60f5002e..9c7951bb05ac 100644 --- a/drivers/crypto/Kconfig +++ b/drivers/crypto/Kconfig @@ -89,6 +89,20 @@ config PKEY requires to have at least one CEX card in coprocessor mode available at runtime. +config CRYPTO_PAES_S390 + tristate "PAES cipher algorithms" + depends on S390 + depends on ZCRYPT + depends on PKEY + select CRYPTO_ALGAPI + select CRYPTO_BLKCIPHER + help + This is the s390 hardware accelerated implementation of the + AES cipher algorithms for use with protected key. + + Select this option if you want to use the paes cipher + for example to use protected key encrypted devices. + config CRYPTO_SHA1_S390 tristate "SHA1 digest algorithm" depends on S390 @@ -137,7 +151,6 @@ config CRYPTO_AES_S390 depends on S390 select CRYPTO_ALGAPI select CRYPTO_BLKCIPHER - select PKEY help This is the s390 hardware accelerated implementation of the AES cipher algorithms (FIPS-197). diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c index 7717b094fabb..db75d4b614f7 100644 --- a/drivers/edac/altera_edac.c +++ b/drivers/edac/altera_edac.c @@ -214,24 +214,16 @@ static void altr_sdr_mc_create_debugfs_nodes(struct mem_ctl_info *mci) static unsigned long get_total_mem(void) { struct device_node *np = NULL; - const unsigned int *reg, *reg_end; - int len, sw, aw; - unsigned long start, size, total_mem = 0; + struct resource res; + int ret; + unsigned long total_mem = 0; for_each_node_by_type(np, "memory") { - aw = of_n_addr_cells(np); - sw = of_n_size_cells(np); - reg = (const unsigned int *)of_get_property(np, "reg", &len); - reg_end = reg + (len / sizeof(u32)); - - total_mem = 0; - do { - start = of_read_number(reg, aw); - reg += aw; - size = of_read_number(reg, sw); - reg += sw; - total_mem += size; - } while (reg < reg_end); + ret = of_address_to_resource(np, 0, &res); + if (ret) + continue; + + total_mem += resource_size(&res); } edac_dbg(0, "total_mem 0x%lx\n", total_mem); return total_mem; @@ -1839,7 +1831,7 @@ static int a10_eccmgr_irqdomain_map(struct irq_domain *d, unsigned int irq, return 0; } -static struct irq_domain_ops a10_eccmgr_ic_ops = { +static const struct irq_domain_ops a10_eccmgr_ic_ops = { .map = a10_eccmgr_irqdomain_map, .xlate = irq_domain_xlate_twocell, }; diff --git a/drivers/edac/i5000_edac.c b/drivers/edac/i5000_edac.c index f683919981b0..8f5a56e25bd2 100644 --- a/drivers/edac/i5000_edac.c +++ b/drivers/edac/i5000_edac.c @@ -227,7 +227,7 @@ #define NREC_RDWR(x) (((x)>>11) & 1) #define NREC_RANK(x) (((x)>>8) & 0x7) #define NRECMEMB 0xC0 -#define NREC_CAS(x) (((x)>>16) & 0xFFFFFF) +#define NREC_CAS(x) (((x)>>16) & 0xFFF) #define NREC_RAS(x) ((x) & 0x7FFF) #define NRECFGLOG 0xC4 #define NREEECFBDA 0xC8 @@ -371,7 +371,7 @@ struct i5000_error_info { /* These registers are input ONLY if there was a * Non-Recoverable Error */ u16 nrecmema; /* Non-Recoverable Mem log A */ - u16 nrecmemb; /* Non-Recoverable Mem log B */ + u32 nrecmemb; /* Non-Recoverable Mem log B */ }; @@ -407,7 +407,7 @@ static void i5000_get_error_info(struct mem_ctl_info *mci, NERR_FAT_FBD, &info->nerr_fat_fbd); pci_read_config_word(pvt->branchmap_werrors, NRECMEMA, &info->nrecmema); - pci_read_config_word(pvt->branchmap_werrors, + pci_read_config_dword(pvt->branchmap_werrors, NRECMEMB, &info->nrecmemb); /* Clear the error bits, by writing them back */ diff --git a/drivers/edac/i5400_edac.c b/drivers/edac/i5400_edac.c index 37a9ba71da44..cd889edc8516 100644 --- a/drivers/edac/i5400_edac.c +++ b/drivers/edac/i5400_edac.c @@ -368,7 +368,7 @@ struct i5400_error_info { /* These registers are input ONLY if there was a Non-Rec Error */ u16 nrecmema; /* Non-Recoverable Mem log A */ - u16 nrecmemb; /* Non-Recoverable Mem log B */ + u32 nrecmemb; /* Non-Recoverable Mem log B */ }; @@ -458,7 +458,7 @@ static void i5400_get_error_info(struct mem_ctl_info *mci, NERR_FAT_FBD, &info->nerr_fat_fbd); pci_read_config_word(pvt->branchmap_werrors, NRECMEMA, &info->nrecmema); - pci_read_config_word(pvt->branchmap_werrors, + pci_read_config_dword(pvt->branchmap_werrors, NRECMEMB, &info->nrecmemb); /* Clear the error bits, by writing them back */ diff --git a/drivers/edac/ie31200_edac.c b/drivers/edac/ie31200_edac.c index 2733fb5938a4..4260579e6901 100644 --- a/drivers/edac/ie31200_edac.c +++ b/drivers/edac/ie31200_edac.c @@ -18,10 +18,12 @@ * 0c04: Xeon E3-1200 v3/4th Gen Core Processor DRAM Controller * 0c08: Xeon E3-1200 v3 Processor DRAM Controller * 1918: Xeon E3-1200 v5 Skylake Host Bridge/DRAM Registers + * 5918: Xeon E3-1200 Xeon E3-1200 v6/7th Gen Core Processor Host Bridge/DRAM Registers * * Based on Intel specification: * http://www.intel.com/content/dam/www/public/us/en/documents/datasheets/xeon-e3-1200v3-vol-2-datasheet.pdf * http://www.intel.com/content/www/us/en/processors/xeon/xeon-e3-1200-family-vol-2-datasheet.html + * http://www.intel.com/content/www/us/en/processors/core/7th-gen-core-family-mobile-h-processor-lines-datasheet-vol-2.html * * According to the above datasheet (p.16): * " @@ -57,6 +59,7 @@ #define PCI_DEVICE_ID_INTEL_IE31200_HB_6 0x0c04 #define PCI_DEVICE_ID_INTEL_IE31200_HB_7 0x0c08 #define PCI_DEVICE_ID_INTEL_IE31200_HB_8 0x1918 +#define PCI_DEVICE_ID_INTEL_IE31200_HB_9 0x5918 #define IE31200_DIMMS 4 #define IE31200_RANKS 8 @@ -376,7 +379,12 @@ static int ie31200_probe1(struct pci_dev *pdev, int dev_idx) void __iomem *window; struct ie31200_priv *priv; u32 addr_decode, mad_offset; - bool skl = (pdev->device == PCI_DEVICE_ID_INTEL_IE31200_HB_8); + + /* + * Kaby Lake seems to work like Skylake. Please re-visit this logic + * when adding new CPU support. + */ + bool skl = (pdev->device >= PCI_DEVICE_ID_INTEL_IE31200_HB_8); edac_dbg(0, "MC:\n"); @@ -560,6 +568,9 @@ static const struct pci_device_id ie31200_pci_tbl[] = { PCI_VEND_DEV(INTEL, IE31200_HB_8), PCI_ANY_ID, PCI_ANY_ID, 0, 0, IE31200}, { + PCI_VEND_DEV(INTEL, IE31200_HB_9), PCI_ANY_ID, PCI_ANY_ID, 0, 0, + IE31200}, + { 0, } /* 0 terminated list. */ }; diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c index ba35b7ea3686..9a2658a256a9 100644 --- a/drivers/edac/mce_amd.c +++ b/drivers/edac/mce_amd.c @@ -161,7 +161,7 @@ static const char * const smca_ls_mce_desc[] = { "Sys Read data error thread 0", "Sys read data error thread 1", "DC tag error type 2", - "DC data error type 1 (poison comsumption)", + "DC data error type 1 (poison consumption)", "DC data error type 2", "DC data error type 3", "DC tag error type 4", diff --git a/drivers/edac/mv64x60_edac.c b/drivers/edac/mv64x60_edac.c index 14b7e7b71eaa..d3650df94fe8 100644 --- a/drivers/edac/mv64x60_edac.c +++ b/drivers/edac/mv64x60_edac.c @@ -32,21 +32,21 @@ static void mv64x60_pci_check(struct edac_pci_ctl_info *pci) struct mv64x60_pci_pdata *pdata = pci->pvt_info; u32 cause; - cause = in_le32(pdata->pci_vbase + MV64X60_PCI_ERROR_CAUSE); + cause = readl(pdata->pci_vbase + MV64X60_PCI_ERROR_CAUSE); if (!cause) return; printk(KERN_ERR "Error in PCI %d Interface\n", pdata->pci_hose); printk(KERN_ERR "Cause register: 0x%08x\n", cause); printk(KERN_ERR "Address Low: 0x%08x\n", - in_le32(pdata->pci_vbase + MV64X60_PCI_ERROR_ADDR_LO)); + readl(pdata->pci_vbase + MV64X60_PCI_ERROR_ADDR_LO)); printk(KERN_ERR "Address High: 0x%08x\n", - in_le32(pdata->pci_vbase + MV64X60_PCI_ERROR_ADDR_HI)); + readl(pdata->pci_vbase + MV64X60_PCI_ERROR_ADDR_HI)); printk(KERN_ERR "Attribute: 0x%08x\n", - in_le32(pdata->pci_vbase + MV64X60_PCI_ERROR_ATTR)); + readl(pdata->pci_vbase + MV64X60_PCI_ERROR_ATTR)); printk(KERN_ERR "Command: 0x%08x\n", - in_le32(pdata->pci_vbase + MV64X60_PCI_ERROR_CMD)); - out_le32(pdata->pci_vbase + MV64X60_PCI_ERROR_CAUSE, ~cause); + readl(pdata->pci_vbase + MV64X60_PCI_ERROR_CMD)); + writel(~cause, pdata->pci_vbase + MV64X60_PCI_ERROR_CAUSE); if (cause & MV64X60_PCI_PE_MASK) edac_pci_handle_pe(pci, pci->ctl_name); @@ -61,7 +61,7 @@ static irqreturn_t mv64x60_pci_isr(int irq, void *dev_id) struct mv64x60_pci_pdata *pdata = pci->pvt_info; u32 val; - val = in_le32(pdata->pci_vbase + MV64X60_PCI_ERROR_CAUSE); + val = readl(pdata->pci_vbase + MV64X60_PCI_ERROR_CAUSE); if (!val) return IRQ_NONE; @@ -93,7 +93,7 @@ static int __init mv64x60_pci_fixup(struct platform_device *pdev) if (!pci_serr) return -ENOMEM; - out_le32(pci_serr, in_le32(pci_serr) & ~0x1); + writel(readl(pci_serr) & ~0x1, pci_serr); iounmap(pci_serr); return 0; @@ -116,7 +116,7 @@ static int mv64x60_pci_err_probe(struct platform_device *pdev) pdata = pci->pvt_info; pdata->pci_hose = pdev->id; - pdata->name = "mpc85xx_pci_err"; + pdata->name = "mv64x60_pci_err"; platform_set_drvdata(pdev, pci); pci->dev = &pdev->dev; pci->dev_name = dev_name(&pdev->dev); @@ -161,10 +161,10 @@ static int mv64x60_pci_err_probe(struct platform_device *pdev) goto err; } - out_le32(pdata->pci_vbase + MV64X60_PCI_ERROR_CAUSE, 0); - out_le32(pdata->pci_vbase + MV64X60_PCI_ERROR_MASK, 0); - out_le32(pdata->pci_vbase + MV64X60_PCI_ERROR_MASK, - MV64X60_PCIx_ERR_MASK_VAL); + writel(0, pdata->pci_vbase + MV64X60_PCI_ERROR_CAUSE); + writel(0, pdata->pci_vbase + MV64X60_PCI_ERROR_MASK); + writel(MV64X60_PCIx_ERR_MASK_VAL, + pdata->pci_vbase + MV64X60_PCI_ERROR_MASK); if (edac_pci_add_device(pci, pdata->edac_idx) > 0) { edac_dbg(3, "failed edac_pci_add_device()\n"); @@ -233,23 +233,23 @@ static void mv64x60_sram_check(struct edac_device_ctl_info *edac_dev) struct mv64x60_sram_pdata *pdata = edac_dev->pvt_info; u32 cause; - cause = in_le32(pdata->sram_vbase + MV64X60_SRAM_ERR_CAUSE); + cause = readl(pdata->sram_vbase + MV64X60_SRAM_ERR_CAUSE); if (!cause) return; printk(KERN_ERR "Error in internal SRAM\n"); printk(KERN_ERR "Cause register: 0x%08x\n", cause); printk(KERN_ERR "Address Low: 0x%08x\n", - in_le32(pdata->sram_vbase + MV64X60_SRAM_ERR_ADDR_LO)); + readl(pdata->sram_vbase + MV64X60_SRAM_ERR_ADDR_LO)); printk(KERN_ERR "Address High: 0x%08x\n", - in_le32(pdata->sram_vbase + MV64X60_SRAM_ERR_ADDR_HI)); + readl(pdata->sram_vbase + MV64X60_SRAM_ERR_ADDR_HI)); printk(KERN_ERR "Data Low: 0x%08x\n", - in_le32(pdata->sram_vbase + MV64X60_SRAM_ERR_DATA_LO)); + readl(pdata->sram_vbase + MV64X60_SRAM_ERR_DATA_LO)); printk(KERN_ERR "Data High: 0x%08x\n", - in_le32(pdata->sram_vbase + MV64X60_SRAM_ERR_DATA_HI)); + readl(pdata->sram_vbase + MV64X60_SRAM_ERR_DATA_HI)); printk(KERN_ERR "Parity: 0x%08x\n", - in_le32(pdata->sram_vbase + MV64X60_SRAM_ERR_PARITY)); - out_le32(pdata->sram_vbase + MV64X60_SRAM_ERR_CAUSE, 0); + readl(pdata->sram_vbase + MV64X60_SRAM_ERR_PARITY)); + writel(0, pdata->sram_vbase + MV64X60_SRAM_ERR_CAUSE); edac_device_handle_ue(edac_dev, 0, 0, edac_dev->ctl_name); } @@ -260,7 +260,7 @@ static irqreturn_t mv64x60_sram_isr(int irq, void *dev_id) struct mv64x60_sram_pdata *pdata = edac_dev->pvt_info; u32 cause; - cause = in_le32(pdata->sram_vbase + MV64X60_SRAM_ERR_CAUSE); + cause = readl(pdata->sram_vbase + MV64X60_SRAM_ERR_CAUSE); if (!cause) return IRQ_NONE; @@ -322,7 +322,7 @@ static int mv64x60_sram_err_probe(struct platform_device *pdev) } /* setup SRAM err registers */ - out_le32(pdata->sram_vbase + MV64X60_SRAM_ERR_CAUSE, 0); + writel(0, pdata->sram_vbase + MV64X60_SRAM_ERR_CAUSE); edac_dev->mod_name = EDAC_MOD_STR; edac_dev->ctl_name = pdata->name; @@ -398,7 +398,7 @@ static void mv64x60_cpu_check(struct edac_device_ctl_info *edac_dev) struct mv64x60_cpu_pdata *pdata = edac_dev->pvt_info; u32 cause; - cause = in_le32(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_CAUSE) & + cause = readl(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_CAUSE) & MV64x60_CPU_CAUSE_MASK; if (!cause) return; @@ -406,16 +406,16 @@ static void mv64x60_cpu_check(struct edac_device_ctl_info *edac_dev) printk(KERN_ERR "Error on CPU interface\n"); printk(KERN_ERR "Cause register: 0x%08x\n", cause); printk(KERN_ERR "Address Low: 0x%08x\n", - in_le32(pdata->cpu_vbase[0] + MV64x60_CPU_ERR_ADDR_LO)); + readl(pdata->cpu_vbase[0] + MV64x60_CPU_ERR_ADDR_LO)); printk(KERN_ERR "Address High: 0x%08x\n", - in_le32(pdata->cpu_vbase[0] + MV64x60_CPU_ERR_ADDR_HI)); + readl(pdata->cpu_vbase[0] + MV64x60_CPU_ERR_ADDR_HI)); printk(KERN_ERR "Data Low: 0x%08x\n", - in_le32(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_DATA_LO)); + readl(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_DATA_LO)); printk(KERN_ERR "Data High: 0x%08x\n", - in_le32(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_DATA_HI)); + readl(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_DATA_HI)); printk(KERN_ERR "Parity: 0x%08x\n", - in_le32(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_PARITY)); - out_le32(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_CAUSE, 0); + readl(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_PARITY)); + writel(0, pdata->cpu_vbase[1] + MV64x60_CPU_ERR_CAUSE); edac_device_handle_ue(edac_dev, 0, 0, edac_dev->ctl_name); } @@ -426,7 +426,7 @@ static irqreturn_t mv64x60_cpu_isr(int irq, void *dev_id) struct mv64x60_cpu_pdata *pdata = edac_dev->pvt_info; u32 cause; - cause = in_le32(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_CAUSE) & + cause = readl(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_CAUSE) & MV64x60_CPU_CAUSE_MASK; if (!cause) return IRQ_NONE; @@ -515,9 +515,9 @@ static int mv64x60_cpu_err_probe(struct platform_device *pdev) } /* setup CPU err registers */ - out_le32(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_CAUSE, 0); - out_le32(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_MASK, 0); - out_le32(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_MASK, 0x000000ff); + writel(0, pdata->cpu_vbase[1] + MV64x60_CPU_ERR_CAUSE); + writel(0, pdata->cpu_vbase[1] + MV64x60_CPU_ERR_MASK); + writel(0x000000ff, pdata->cpu_vbase[1] + MV64x60_CPU_ERR_MASK); edac_dev->mod_name = EDAC_MOD_STR; edac_dev->ctl_name = pdata->name; @@ -596,13 +596,13 @@ static void mv64x60_mc_check(struct mem_ctl_info *mci) u32 comp_ecc; u32 syndrome; - reg = in_le32(pdata->mc_vbase + MV64X60_SDRAM_ERR_ADDR); + reg = readl(pdata->mc_vbase + MV64X60_SDRAM_ERR_ADDR); if (!reg) return; err_addr = reg & ~0x3; - sdram_ecc = in_le32(pdata->mc_vbase + MV64X60_SDRAM_ERR_ECC_RCVD); - comp_ecc = in_le32(pdata->mc_vbase + MV64X60_SDRAM_ERR_ECC_CALC); + sdram_ecc = readl(pdata->mc_vbase + MV64X60_SDRAM_ERR_ECC_RCVD); + comp_ecc = readl(pdata->mc_vbase + MV64X60_SDRAM_ERR_ECC_CALC); syndrome = sdram_ecc ^ comp_ecc; /* first bit clear in ECC Err Reg, 1 bit error, correctable by HW */ @@ -620,7 +620,7 @@ static void mv64x60_mc_check(struct mem_ctl_info *mci) mci->ctl_name, ""); /* clear the error */ - out_le32(pdata->mc_vbase + MV64X60_SDRAM_ERR_ADDR, 0); + writel(0, pdata->mc_vbase + MV64X60_SDRAM_ERR_ADDR); } static irqreturn_t mv64x60_mc_isr(int irq, void *dev_id) @@ -629,7 +629,7 @@ static irqreturn_t mv64x60_mc_isr(int irq, void *dev_id) struct mv64x60_mc_pdata *pdata = mci->pvt_info; u32 reg; - reg = in_le32(pdata->mc_vbase + MV64X60_SDRAM_ERR_ADDR); + reg = readl(pdata->mc_vbase + MV64X60_SDRAM_ERR_ADDR); if (!reg) return IRQ_NONE; @@ -664,7 +664,7 @@ static void mv64x60_init_csrows(struct mem_ctl_info *mci, get_total_mem(pdata); - ctl = in_le32(pdata->mc_vbase + MV64X60_SDRAM_CONFIG); + ctl = readl(pdata->mc_vbase + MV64X60_SDRAM_CONFIG); csrow = mci->csrows[0]; dimm = csrow->channels[0]->dimm; @@ -753,7 +753,7 @@ static int mv64x60_mc_err_probe(struct platform_device *pdev) goto err; } - ctl = in_le32(pdata->mc_vbase + MV64X60_SDRAM_CONFIG); + ctl = readl(pdata->mc_vbase + MV64X60_SDRAM_CONFIG); if (!(ctl & MV64X60_SDRAM_ECC)) { /* Non-ECC RAM? */ printk(KERN_WARNING "%s: No ECC DIMMs discovered\n", __func__); @@ -779,10 +779,10 @@ static int mv64x60_mc_err_probe(struct platform_device *pdev) mv64x60_init_csrows(mci, pdata); /* setup MC registers */ - out_le32(pdata->mc_vbase + MV64X60_SDRAM_ERR_ADDR, 0); - ctl = in_le32(pdata->mc_vbase + MV64X60_SDRAM_ERR_ECC_CNTL); + writel(0, pdata->mc_vbase + MV64X60_SDRAM_ERR_ADDR); + ctl = readl(pdata->mc_vbase + MV64X60_SDRAM_ERR_ECC_CNTL); ctl = (ctl & 0xff00ffff) | 0x10000; - out_le32(pdata->mc_vbase + MV64X60_SDRAM_ERR_ECC_CNTL, ctl); + writel(ctl, pdata->mc_vbase + MV64X60_SDRAM_ERR_ECC_CNTL); res = edac_mc_add_mc(mci); if (res) { @@ -853,10 +853,10 @@ static struct platform_driver * const drivers[] = { static int __init mv64x60_edac_init(void) { - int ret = 0; printk(KERN_INFO "Marvell MV64x60 EDAC driver " MV64x60_REVISION "\n"); printk(KERN_INFO "\t(C) 2006-2007 MontaVista Software\n"); + /* make sure error reporting method is sane */ switch (edac_op_state) { case EDAC_OPSTATE_POLL: diff --git a/drivers/edac/pnd2_edac.c b/drivers/edac/pnd2_edac.c index 1cad5a9af8d0..8e599490f6de 100644 --- a/drivers/edac/pnd2_edac.c +++ b/drivers/edac/pnd2_edac.c @@ -131,7 +131,7 @@ static struct mem_ctl_info *pnd2_mci; #ifdef CONFIG_X86_INTEL_SBI_APL #include "linux/platform_data/sbi_apl.h" -int sbi_send(int port, int off, int op, u32 *data) +static int sbi_send(int port, int off, int op, u32 *data) { struct sbi_apl_message sbi_arg; int ret, read = 0; @@ -160,7 +160,7 @@ int sbi_send(int port, int off, int op, u32 *data) return ret; } #else -int sbi_send(int port, int off, int op, u32 *data) +static int sbi_send(int port, int off, int op, u32 *data) { return -EUNATCH; } @@ -168,14 +168,15 @@ int sbi_send(int port, int off, int op, u32 *data) static int apl_rd_reg(int port, int off, int op, void *data, size_t sz, char *name) { - int ret = 0; + int ret = 0; edac_dbg(2, "Read %s port=%x off=%x op=%x\n", name, port, off, op); switch (sz) { case 8: ret = sbi_send(port, off + 4, op, (u32 *)(data + 4)); + /* fall through */ case 4: - ret = sbi_send(port, off, op, (u32 *)data); + ret |= sbi_send(port, off, op, (u32 *)data); pnd2_printk(KERN_DEBUG, "%s=%x%08x ret=%d\n", name, sz == 8 ? *((u32 *)(data + 4)) : 0, *((u32 *)data), ret); break; @@ -423,16 +424,21 @@ static void dnv_mk_region(char *name, struct region *rp, void *asym) static int apl_get_registers(void) { + int ret = -ENODEV; int i; if (RD_REG(&asym_2way, b_cr_asym_2way_mem_region_mchbar)) return -ENODEV; + /* + * RD_REGP() will fail for unpopulated or non-existent + * DIMM slots. Return success if we find at least one DIMM. + */ for (i = 0; i < APL_NUM_CHANNELS; i++) - if (RD_REGP(&drp0[i], d_cr_drp0, apl_dports[i])) - return -ENODEV; + if (!RD_REGP(&drp0[i], d_cr_drp0, apl_dports[i])) + ret = 0; - return 0; + return ret; } static int dnv_get_registers(void) diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index ea21cb651b3c..80d860cb0746 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -35,7 +35,7 @@ static LIST_HEAD(sbridge_edac_list); /* * Alter this version for the module when modifications are made */ -#define SBRIDGE_REVISION " Ver: 1.1.1 " +#define SBRIDGE_REVISION " Ver: 1.1.2 " #define EDAC_MOD_STR "sbridge_edac" /* @@ -279,7 +279,7 @@ static const u32 correrrthrsld[] = { * sbridge structs */ -#define NUM_CHANNELS 8 /* 2MC per socket, four chan per MC */ +#define NUM_CHANNELS 4 /* Max channels per MC */ #define MAX_DIMMS 3 /* Max DIMMS per channel */ #define KNL_MAX_CHAS 38 /* KNL max num. of Cache Home Agents */ #define KNL_MAX_CHANNELS 6 /* KNL max num. of PCI channels */ @@ -294,6 +294,12 @@ enum type { KNIGHTS_LANDING, }; +enum domain { + IMC0 = 0, + IMC1, + SOCK, +}; + struct sbridge_pvt; struct sbridge_info { enum type type; @@ -324,11 +330,14 @@ struct sbridge_channel { struct pci_id_descr { int dev_id; int optional; + enum domain dom; }; struct pci_id_table { const struct pci_id_descr *descr; - int n_devs; + int n_devs_per_imc; + int n_devs_per_sock; + int n_imcs_per_sock; enum type type; }; @@ -337,7 +346,9 @@ struct sbridge_dev { u8 bus, mc; u8 node_id, source_id; struct pci_dev **pdev; + enum domain dom; int n_devs; + int i_devs; struct mem_ctl_info *mci; }; @@ -352,11 +363,12 @@ struct knl_pvt { }; struct sbridge_pvt { - struct pci_dev *pci_ta, *pci_ddrio, *pci_ras; + /* Devices per socket */ + struct pci_dev *pci_ddrio; struct pci_dev *pci_sad0, *pci_sad1; - struct pci_dev *pci_ha0, *pci_ha1; struct pci_dev *pci_br0, *pci_br1; - struct pci_dev *pci_ha1_ta; + /* Devices per memory controller */ + struct pci_dev *pci_ha, *pci_ta, *pci_ras; struct pci_dev *pci_tad[NUM_CHANNELS]; struct sbridge_dev *sbridge_dev; @@ -373,39 +385,42 @@ struct sbridge_pvt { struct knl_pvt knl; }; -#define PCI_DESCR(device_id, opt) \ +#define PCI_DESCR(device_id, opt, domain) \ .dev_id = (device_id), \ - .optional = opt + .optional = opt, \ + .dom = domain static const struct pci_id_descr pci_dev_descr_sbridge[] = { /* Processor Home Agent */ - { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_HA0, 0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_HA0, 0, IMC0) }, /* Memory controller */ - { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TA, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_RAS, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD0, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD1, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD2, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD3, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_DDRIO, 1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TA, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_RAS, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD0, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD1, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD2, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD3, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_DDRIO, 1, SOCK) }, /* System Address Decoder */ - { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_SAD0, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_SAD1, 0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_SAD0, 0, SOCK) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_SAD1, 0, SOCK) }, /* Broadcast Registers */ - { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_BR, 0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_BR, 0, SOCK) }, }; -#define PCI_ID_TABLE_ENTRY(A, T) { \ +#define PCI_ID_TABLE_ENTRY(A, N, M, T) { \ .descr = A, \ - .n_devs = ARRAY_SIZE(A), \ + .n_devs_per_imc = N, \ + .n_devs_per_sock = ARRAY_SIZE(A), \ + .n_imcs_per_sock = M, \ .type = T \ } static const struct pci_id_table pci_dev_descr_sbridge_table[] = { - PCI_ID_TABLE_ENTRY(pci_dev_descr_sbridge, SANDY_BRIDGE), + PCI_ID_TABLE_ENTRY(pci_dev_descr_sbridge, ARRAY_SIZE(pci_dev_descr_sbridge), 1, SANDY_BRIDGE), {0,} /* 0 terminated list. */ }; @@ -439,40 +454,39 @@ static const struct pci_id_table pci_dev_descr_sbridge_table[] = { static const struct pci_id_descr pci_dev_descr_ibridge[] = { /* Processor Home Agent */ - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0, 0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0, 0, IMC0) }, /* Memory controller */ - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TA, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_RAS, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TAD0, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TAD1, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TAD2, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TAD3, 0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TA, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_RAS, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TAD0, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TAD1, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TAD2, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TAD3, 0, IMC0) }, + + /* Optional, mode 2HA */ + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TA, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_RAS, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD0, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD1, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD2, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD3, 1, IMC1) }, + + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_1HA_DDRIO0, 1, SOCK) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_2HA_DDRIO0, 1, SOCK) }, /* System Address Decoder */ - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_SAD, 0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_SAD, 0, SOCK) }, /* Broadcast Registers */ - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_BR0, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_BR1, 0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_BR0, 1, SOCK) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_BR1, 0, SOCK) }, - /* Optional, mode 2HA */ - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1, 1) }, -#if 0 - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TA, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_RAS, 1) }, -#endif - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD0, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD1, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD2, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD3, 1) }, - - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_1HA_DDRIO0, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_2HA_DDRIO0, 1) }, }; static const struct pci_id_table pci_dev_descr_ibridge_table[] = { - PCI_ID_TABLE_ENTRY(pci_dev_descr_ibridge, IVY_BRIDGE), + PCI_ID_TABLE_ENTRY(pci_dev_descr_ibridge, 12, 2, IVY_BRIDGE), {0,} /* 0 terminated list. */ }; @@ -498,9 +512,9 @@ static const struct pci_id_table pci_dev_descr_ibridge_table[] = { #define PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0 0x2fa0 #define PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1 0x2f60 #define PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TA 0x2fa8 -#define PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_THERMAL 0x2f71 +#define PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TM 0x2f71 #define PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TA 0x2f68 -#define PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_THERMAL 0x2f79 +#define PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TM 0x2f79 #define PCI_DEVICE_ID_INTEL_HASWELL_IMC_CBO_SAD0 0x2ffc #define PCI_DEVICE_ID_INTEL_HASWELL_IMC_CBO_SAD1 0x2ffd #define PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TAD0 0x2faa @@ -517,35 +531,33 @@ static const struct pci_id_table pci_dev_descr_ibridge_table[] = { #define PCI_DEVICE_ID_INTEL_HASWELL_IMC_DDRIO3 0x2fbb static const struct pci_id_descr pci_dev_descr_haswell[] = { /* first item must be the HA */ - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0, 0) }, - - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_CBO_SAD0, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_CBO_SAD1, 0) }, - - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1, 1) }, - - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TA, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_THERMAL, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TAD0, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TAD1, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TAD2, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TAD3, 1) }, - - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_DDRIO0, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_DDRIO1, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_DDRIO2, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_DDRIO3, 1) }, - - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TA, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_THERMAL, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TAD0, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TAD1, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TAD2, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TAD3, 1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1, 1, IMC1) }, + + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TA, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TM, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TAD0, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TAD1, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TAD2, 1, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TAD3, 1, IMC0) }, + + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TA, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TM, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TAD0, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TAD1, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TAD2, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TAD3, 1, IMC1) }, + + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_CBO_SAD0, 0, SOCK) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_CBO_SAD1, 0, SOCK) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_DDRIO0, 1, SOCK) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_DDRIO1, 1, SOCK) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_DDRIO2, 1, SOCK) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_HASWELL_IMC_DDRIO3, 1, SOCK) }, }; static const struct pci_id_table pci_dev_descr_haswell_table[] = { - PCI_ID_TABLE_ENTRY(pci_dev_descr_haswell, HASWELL), + PCI_ID_TABLE_ENTRY(pci_dev_descr_haswell, 13, 2, HASWELL), {0,} /* 0 terminated list. */ }; @@ -559,7 +571,7 @@ static const struct pci_id_table pci_dev_descr_haswell_table[] = { /* Memory controller, TAD tables, error injection - 2-8-0, 2-9-0 (2 of these) */ #define PCI_DEVICE_ID_INTEL_KNL_IMC_MC 0x7840 /* DRAM channel stuff; bank addrs, dimmmtr, etc.. 2-8-2 - 2-9-4 (6 of these) */ -#define PCI_DEVICE_ID_INTEL_KNL_IMC_CHANNEL 0x7843 +#define PCI_DEVICE_ID_INTEL_KNL_IMC_CHAN 0x7843 /* kdrwdbu TAD limits/offsets, MCMTR - 2-10-1, 2-11-1 (2 of these) */ #define PCI_DEVICE_ID_INTEL_KNL_IMC_TA 0x7844 /* CHA broadcast registers, dram rules - 1-29-0 (1 of these) */ @@ -579,17 +591,17 @@ static const struct pci_id_table pci_dev_descr_haswell_table[] = { */ static const struct pci_id_descr pci_dev_descr_knl[] = { - [0] = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_SAD0, 0) }, - [1] = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_SAD1, 0) }, - [2 ... 3] = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_MC, 0)}, - [4 ... 41] = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_CHA, 0) }, - [42 ... 47] = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_CHANNEL, 0) }, - [48] = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_TA, 0) }, - [49] = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_TOLHM, 0) }, + [0 ... 1] = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_MC, 0, IMC0)}, + [2 ... 7] = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_CHAN, 0, IMC0) }, + [8] = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_TA, 0, IMC0) }, + [9] = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_TOLHM, 0, IMC0) }, + [10] = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_SAD0, 0, SOCK) }, + [11] = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_SAD1, 0, SOCK) }, + [12 ... 49] = { PCI_DESCR(PCI_DEVICE_ID_INTEL_KNL_IMC_CHA, 0, SOCK) }, }; static const struct pci_id_table pci_dev_descr_knl_table[] = { - PCI_ID_TABLE_ENTRY(pci_dev_descr_knl, KNIGHTS_LANDING), + PCI_ID_TABLE_ENTRY(pci_dev_descr_knl, ARRAY_SIZE(pci_dev_descr_knl), 1, KNIGHTS_LANDING), {0,} }; @@ -615,9 +627,9 @@ static const struct pci_id_table pci_dev_descr_knl_table[] = { #define PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0 0x6fa0 #define PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1 0x6f60 #define PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TA 0x6fa8 -#define PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_THERMAL 0x6f71 +#define PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TM 0x6f71 #define PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TA 0x6f68 -#define PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_THERMAL 0x6f79 +#define PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TM 0x6f79 #define PCI_DEVICE_ID_INTEL_BROADWELL_IMC_CBO_SAD0 0x6ffc #define PCI_DEVICE_ID_INTEL_BROADWELL_IMC_CBO_SAD1 0x6ffd #define PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TAD0 0x6faa @@ -632,32 +644,30 @@ static const struct pci_id_table pci_dev_descr_knl_table[] = { static const struct pci_id_descr pci_dev_descr_broadwell[] = { /* first item must be the HA */ - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0, 0) }, - - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_CBO_SAD0, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_CBO_SAD1, 0) }, - - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1, 1) }, - - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TA, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_THERMAL, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TAD0, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TAD1, 0) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TAD2, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TAD3, 1) }, - - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_DDRIO0, 1) }, - - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TA, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_THERMAL, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TAD0, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TAD1, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TAD2, 1) }, - { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TAD3, 1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1, 1, IMC1) }, + + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TA, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TM, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TAD0, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TAD1, 0, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TAD2, 1, IMC0) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TAD3, 1, IMC0) }, + + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TA, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TM, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TAD0, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TAD1, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TAD2, 1, IMC1) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TAD3, 1, IMC1) }, + + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_CBO_SAD0, 0, SOCK) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_CBO_SAD1, 0, SOCK) }, + { PCI_DESCR(PCI_DEVICE_ID_INTEL_BROADWELL_IMC_DDRIO0, 1, SOCK) }, }; static const struct pci_id_table pci_dev_descr_broadwell_table[] = { - PCI_ID_TABLE_ENTRY(pci_dev_descr_broadwell, BROADWELL), + PCI_ID_TABLE_ENTRY(pci_dev_descr_broadwell, 10, 2, BROADWELL), {0,} /* 0 terminated list. */ }; @@ -709,7 +719,8 @@ static inline int numcol(u32 mtr) return 1 << cols; } -static struct sbridge_dev *get_sbridge_dev(u8 bus, int multi_bus) +static struct sbridge_dev *get_sbridge_dev(u8 bus, enum domain dom, int multi_bus, + struct sbridge_dev *prev) { struct sbridge_dev *sbridge_dev; @@ -722,16 +733,19 @@ static struct sbridge_dev *get_sbridge_dev(u8 bus, int multi_bus) struct sbridge_dev, list); } - list_for_each_entry(sbridge_dev, &sbridge_edac_list, list) { - if (sbridge_dev->bus == bus) + sbridge_dev = list_entry(prev ? prev->list.next + : sbridge_edac_list.next, struct sbridge_dev, list); + + list_for_each_entry_from(sbridge_dev, &sbridge_edac_list, list) { + if (sbridge_dev->bus == bus && (dom == SOCK || dom == sbridge_dev->dom)) return sbridge_dev; } return NULL; } -static struct sbridge_dev *alloc_sbridge_dev(u8 bus, - const struct pci_id_table *table) +static struct sbridge_dev *alloc_sbridge_dev(u8 bus, enum domain dom, + const struct pci_id_table *table) { struct sbridge_dev *sbridge_dev; @@ -739,15 +753,17 @@ static struct sbridge_dev *alloc_sbridge_dev(u8 bus, if (!sbridge_dev) return NULL; - sbridge_dev->pdev = kzalloc(sizeof(*sbridge_dev->pdev) * table->n_devs, - GFP_KERNEL); + sbridge_dev->pdev = kcalloc(table->n_devs_per_imc, + sizeof(*sbridge_dev->pdev), + GFP_KERNEL); if (!sbridge_dev->pdev) { kfree(sbridge_dev); return NULL; } sbridge_dev->bus = bus; - sbridge_dev->n_devs = table->n_devs; + sbridge_dev->dom = dom; + sbridge_dev->n_devs = table->n_devs_per_imc; list_add_tail(&sbridge_dev->list, &sbridge_edac_list); return sbridge_dev; @@ -1044,79 +1060,6 @@ static int haswell_chan_hash(int idx, u64 addr) return idx; } -/**************************************************************************** - Memory check routines - ****************************************************************************/ -static struct pci_dev *get_pdev_same_bus(u8 bus, u32 id) -{ - struct pci_dev *pdev = NULL; - - do { - pdev = pci_get_device(PCI_VENDOR_ID_INTEL, id, pdev); - if (pdev && pdev->bus->number == bus) - break; - } while (pdev); - - return pdev; -} - -/** - * check_if_ecc_is_active() - Checks if ECC is active - * @bus: Device bus - * @type: Memory controller type - * returns: 0 in case ECC is active, -ENODEV if it can't be determined or - * disabled - */ -static int check_if_ecc_is_active(const u8 bus, enum type type) -{ - struct pci_dev *pdev = NULL; - u32 mcmtr, id; - - switch (type) { - case IVY_BRIDGE: - id = PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TA; - break; - case HASWELL: - id = PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TA; - break; - case SANDY_BRIDGE: - id = PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TA; - break; - case BROADWELL: - id = PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TA; - break; - case KNIGHTS_LANDING: - /* - * KNL doesn't group things by bus the same way - * SB/IB/Haswell does. - */ - id = PCI_DEVICE_ID_INTEL_KNL_IMC_TA; - break; - default: - return -ENODEV; - } - - if (type != KNIGHTS_LANDING) - pdev = get_pdev_same_bus(bus, id); - else - pdev = pci_get_device(PCI_VENDOR_ID_INTEL, id, 0); - - if (!pdev) { - sbridge_printk(KERN_ERR, "Couldn't find PCI device " - "%04x:%04x! on bus %02d\n", - PCI_VENDOR_ID_INTEL, id, bus); - return -ENODEV; - } - - pci_read_config_dword(pdev, - type == KNIGHTS_LANDING ? KNL_MCMTR : MCMTR, &mcmtr); - if (!IS_ECC_ENABLED(mcmtr)) { - sbridge_printk(KERN_ERR, "ECC is disabled. Aborting\n"); - return -ENODEV; - } - return 0; -} - /* Low bits of TAD limit, and some metadata. */ static const u32 knl_tad_dram_limit_lo[] = { 0x400, 0x500, 0x600, 0x700, @@ -1587,25 +1530,13 @@ static int knl_get_dimm_capacity(struct sbridge_pvt *pvt, u64 *mc_sizes) return 0; } -static int get_dimm_config(struct mem_ctl_info *mci) +static void get_source_id(struct mem_ctl_info *mci) { struct sbridge_pvt *pvt = mci->pvt_info; - struct dimm_info *dimm; - unsigned i, j, banks, ranks, rows, cols, npages; - u64 size; u32 reg; - enum edac_type mode; - enum mem_type mtype; - int channels = pvt->info.type == KNIGHTS_LANDING ? - KNL_MAX_CHANNELS : NUM_CHANNELS; - u64 knl_mc_sizes[KNL_MAX_CHANNELS]; - if (pvt->info.type == HASWELL || pvt->info.type == BROADWELL) { - pci_read_config_dword(pvt->pci_ha0, HASWELL_HASYSDEFEATURE2, ®); - pvt->is_chan_hash = GET_BITFIELD(reg, 21, 21); - } if (pvt->info.type == HASWELL || pvt->info.type == BROADWELL || - pvt->info.type == KNIGHTS_LANDING) + pvt->info.type == KNIGHTS_LANDING) pci_read_config_dword(pvt->pci_sad1, SAD_TARGET, ®); else pci_read_config_dword(pvt->pci_br0, SAD_TARGET, ®); @@ -1614,50 +1545,19 @@ static int get_dimm_config(struct mem_ctl_info *mci) pvt->sbridge_dev->source_id = SOURCE_ID_KNL(reg); else pvt->sbridge_dev->source_id = SOURCE_ID(reg); +} - pvt->sbridge_dev->node_id = pvt->info.get_node_id(pvt); - edac_dbg(0, "mc#%d: Node ID: %d, source ID: %d\n", - pvt->sbridge_dev->mc, - pvt->sbridge_dev->node_id, - pvt->sbridge_dev->source_id); - - /* KNL doesn't support mirroring or lockstep, - * and is always closed page - */ - if (pvt->info.type == KNIGHTS_LANDING) { - mode = EDAC_S4ECD4ED; - pvt->is_mirrored = false; - - if (knl_get_dimm_capacity(pvt, knl_mc_sizes) != 0) - return -1; - } else { - pci_read_config_dword(pvt->pci_ras, RASENABLES, ®); - if (IS_MIRROR_ENABLED(reg)) { - edac_dbg(0, "Memory mirror is enabled\n"); - pvt->is_mirrored = true; - } else { - edac_dbg(0, "Memory mirror is disabled\n"); - pvt->is_mirrored = false; - } - - pci_read_config_dword(pvt->pci_ta, MCMTR, &pvt->info.mcmtr); - if (IS_LOCKSTEP_ENABLED(pvt->info.mcmtr)) { - edac_dbg(0, "Lockstep is enabled\n"); - mode = EDAC_S8ECD8ED; - pvt->is_lockstep = true; - } else { - edac_dbg(0, "Lockstep is disabled\n"); - mode = EDAC_S4ECD4ED; - pvt->is_lockstep = false; - } - if (IS_CLOSE_PG(pvt->info.mcmtr)) { - edac_dbg(0, "address map is on closed page mode\n"); - pvt->is_close_pg = true; - } else { - edac_dbg(0, "address map is on open page mode\n"); - pvt->is_close_pg = false; - } - } +static int __populate_dimms(struct mem_ctl_info *mci, + u64 knl_mc_sizes[KNL_MAX_CHANNELS], + enum edac_type mode) +{ + struct sbridge_pvt *pvt = mci->pvt_info; + int channels = pvt->info.type == KNIGHTS_LANDING ? KNL_MAX_CHANNELS + : NUM_CHANNELS; + unsigned int i, j, banks, ranks, rows, cols, npages; + struct dimm_info *dimm; + enum mem_type mtype; + u64 size; mtype = pvt->info.get_memory_type(pvt); if (mtype == MEM_RDDR3 || mtype == MEM_RDDR4) @@ -1688,8 +1588,7 @@ static int get_dimm_config(struct mem_ctl_info *mci) } for (j = 0; j < max_dimms_per_channel; j++) { - dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers, - i, j, 0); + dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers, i, j, 0); if (pvt->info.type == KNIGHTS_LANDING) { pci_read_config_dword(pvt->knl.pci_channel[i], knl_mtr_reg, &mtr); @@ -1699,6 +1598,12 @@ static int get_dimm_config(struct mem_ctl_info *mci) } edac_dbg(4, "Channel #%d MTR%d = %x\n", i, j, mtr); if (IS_DIMM_PRESENT(mtr)) { + if (!IS_ECC_ENABLED(pvt->info.mcmtr)) { + sbridge_printk(KERN_ERR, "CPU SrcID #%d, Ha #%d, Channel #%d has DIMMs, but ECC is disabled\n", + pvt->sbridge_dev->source_id, + pvt->sbridge_dev->dom, i); + return -ENODEV; + } pvt->channel[i].dimms++; ranks = numrank(pvt->info.type, mtr); @@ -1717,7 +1622,7 @@ static int get_dimm_config(struct mem_ctl_info *mci) npages = MiB_TO_PAGES(size); edac_dbg(0, "mc#%d: ha %d channel %d, dimm %d, %lld Mb (%d pages) bank: %d, rank: %d, row: %#x, col: %#x\n", - pvt->sbridge_dev->mc, i/4, i%4, j, + pvt->sbridge_dev->mc, pvt->sbridge_dev->dom, i, j, size, npages, banks, ranks, rows, cols); @@ -1727,8 +1632,8 @@ static int get_dimm_config(struct mem_ctl_info *mci) dimm->mtype = mtype; dimm->edac_mode = mode; snprintf(dimm->label, sizeof(dimm->label), - "CPU_SrcID#%u_Ha#%u_Chan#%u_DIMM#%u", - pvt->sbridge_dev->source_id, i/4, i%4, j); + "CPU_SrcID#%u_Ha#%u_Chan#%u_DIMM#%u", + pvt->sbridge_dev->source_id, pvt->sbridge_dev->dom, i, j); } } } @@ -1736,6 +1641,65 @@ static int get_dimm_config(struct mem_ctl_info *mci) return 0; } +static int get_dimm_config(struct mem_ctl_info *mci) +{ + struct sbridge_pvt *pvt = mci->pvt_info; + u64 knl_mc_sizes[KNL_MAX_CHANNELS]; + enum edac_type mode; + u32 reg; + + if (pvt->info.type == HASWELL || pvt->info.type == BROADWELL) { + pci_read_config_dword(pvt->pci_ha, HASWELL_HASYSDEFEATURE2, ®); + pvt->is_chan_hash = GET_BITFIELD(reg, 21, 21); + } + pvt->sbridge_dev->node_id = pvt->info.get_node_id(pvt); + edac_dbg(0, "mc#%d: Node ID: %d, source ID: %d\n", + pvt->sbridge_dev->mc, + pvt->sbridge_dev->node_id, + pvt->sbridge_dev->source_id); + + /* KNL doesn't support mirroring or lockstep, + * and is always closed page + */ + if (pvt->info.type == KNIGHTS_LANDING) { + mode = EDAC_S4ECD4ED; + pvt->is_mirrored = false; + + if (knl_get_dimm_capacity(pvt, knl_mc_sizes) != 0) + return -1; + pci_read_config_dword(pvt->pci_ta, KNL_MCMTR, &pvt->info.mcmtr); + } else { + pci_read_config_dword(pvt->pci_ras, RASENABLES, ®); + if (IS_MIRROR_ENABLED(reg)) { + edac_dbg(0, "Memory mirror is enabled\n"); + pvt->is_mirrored = true; + } else { + edac_dbg(0, "Memory mirror is disabled\n"); + pvt->is_mirrored = false; + } + + pci_read_config_dword(pvt->pci_ta, MCMTR, &pvt->info.mcmtr); + if (IS_LOCKSTEP_ENABLED(pvt->info.mcmtr)) { + edac_dbg(0, "Lockstep is enabled\n"); + mode = EDAC_S8ECD8ED; + pvt->is_lockstep = true; + } else { + edac_dbg(0, "Lockstep is disabled\n"); + mode = EDAC_S4ECD4ED; + pvt->is_lockstep = false; + } + if (IS_CLOSE_PG(pvt->info.mcmtr)) { + edac_dbg(0, "address map is on closed page mode\n"); + pvt->is_close_pg = true; + } else { + edac_dbg(0, "address map is on open page mode\n"); + pvt->is_close_pg = false; + } + } + + return __populate_dimms(mci, knl_mc_sizes, mode); +} + static void get_memory_layout(const struct mem_ctl_info *mci) { struct sbridge_pvt *pvt = mci->pvt_info; @@ -1816,8 +1780,7 @@ static void get_memory_layout(const struct mem_ctl_info *mci) */ prv = 0; for (n_tads = 0; n_tads < MAX_TAD; n_tads++) { - pci_read_config_dword(pvt->pci_ha0, tad_dram_rule[n_tads], - ®); + pci_read_config_dword(pvt->pci_ha, tad_dram_rule[n_tads], ®); limit = TAD_LIMIT(reg); if (limit <= prv) break; @@ -1899,12 +1862,12 @@ static void get_memory_layout(const struct mem_ctl_info *mci) } } -static struct mem_ctl_info *get_mci_for_node_id(u8 node_id) +static struct mem_ctl_info *get_mci_for_node_id(u8 node_id, u8 ha) { struct sbridge_dev *sbridge_dev; list_for_each_entry(sbridge_dev, &sbridge_edac_list, list) { - if (sbridge_dev->node_id == node_id) + if (sbridge_dev->node_id == node_id && sbridge_dev->dom == ha) return sbridge_dev->mci; } return NULL; @@ -1925,7 +1888,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci, int interleave_mode, shiftup = 0; unsigned sad_interleave[pvt->info.max_interleave]; u32 reg, dram_rule; - u8 ch_way, sck_way, pkg, sad_ha = 0, ch_add = 0; + u8 ch_way, sck_way, pkg, sad_ha = 0; u32 tad_offset; u32 rir_way; u32 mb, gb; @@ -2038,13 +2001,10 @@ static int get_memory_error_data(struct mem_ctl_info *mci, pkg = sad_pkg(pvt->info.interleave_pkg, reg, idx); *socket = sad_pkg_socket(pkg); sad_ha = sad_pkg_ha(pkg); - if (sad_ha) - ch_add = 4; if (a7mode) { /* MCChanShiftUpEnable */ - pci_read_config_dword(pvt->pci_ha0, - HASWELL_HASYSDEFEATURE2, ®); + pci_read_config_dword(pvt->pci_ha, HASWELL_HASYSDEFEATURE2, ®); shiftup = GET_BITFIELD(reg, 22, 22); } @@ -2056,8 +2016,6 @@ static int get_memory_error_data(struct mem_ctl_info *mci, pkg = sad_pkg(pvt->info.interleave_pkg, reg, idx); *socket = sad_pkg_socket(pkg); sad_ha = sad_pkg_ha(pkg); - if (sad_ha) - ch_add = 4; edac_dbg(0, "SAD interleave package: %d = CPU socket %d, HA %d\n", idx, *socket, sad_ha); } @@ -2068,7 +2026,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci, * Move to the proper node structure, in order to access the * right PCI registers */ - new_mci = get_mci_for_node_id(*socket); + new_mci = get_mci_for_node_id(*socket, sad_ha); if (!new_mci) { sprintf(msg, "Struct for socket #%u wasn't initialized", *socket); @@ -2081,14 +2039,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci, * Step 2) Get memory channel */ prv = 0; - if (pvt->info.type == SANDY_BRIDGE) - pci_ha = pvt->pci_ha0; - else { - if (sad_ha) - pci_ha = pvt->pci_ha1; - else - pci_ha = pvt->pci_ha0; - } + pci_ha = pvt->pci_ha; for (n_tads = 0; n_tads < MAX_TAD; n_tads++) { pci_read_config_dword(pci_ha, tad_dram_rule[n_tads], ®); limit = TAD_LIMIT(reg); @@ -2139,9 +2090,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci, } *channel_mask = 1 << base_ch; - pci_read_config_dword(pvt->pci_tad[ch_add + base_ch], - tad_ch_nilv_offset[n_tads], - &tad_offset); + pci_read_config_dword(pvt->pci_tad[base_ch], tad_ch_nilv_offset[n_tads], &tad_offset); if (pvt->is_mirrored) { *channel_mask |= 1 << ((base_ch + 2) % 4); @@ -2192,9 +2141,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci, * Step 3) Decode rank */ for (n_rir = 0; n_rir < MAX_RIR_RANGES; n_rir++) { - pci_read_config_dword(pvt->pci_tad[ch_add + base_ch], - rir_way_limit[n_rir], - ®); + pci_read_config_dword(pvt->pci_tad[base_ch], rir_way_limit[n_rir], ®); if (!IS_RIR_VALID(reg)) continue; @@ -2222,9 +2169,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci, idx = (ch_addr >> 13); /* FIXME: Datasheet says to shift by 15 */ idx %= 1 << rir_way; - pci_read_config_dword(pvt->pci_tad[ch_add + base_ch], - rir_offset[n_rir][idx], - ®); + pci_read_config_dword(pvt->pci_tad[base_ch], rir_offset[n_rir][idx], ®); *rank = RIR_RNK_TGT(pvt->info.type, reg); edac_dbg(0, "RIR#%d: channel address 0x%08Lx < 0x%08Lx, RIR interleave %d, index %d\n", @@ -2277,10 +2222,11 @@ static int sbridge_get_onedevice(struct pci_dev **prev, const unsigned devno, const int multi_bus) { - struct sbridge_dev *sbridge_dev; + struct sbridge_dev *sbridge_dev = NULL; const struct pci_id_descr *dev_descr = &table->descr[devno]; struct pci_dev *pdev = NULL; u8 bus = 0; + int i = 0; sbridge_printk(KERN_DEBUG, "Seeking for: PCI ID %04x:%04x\n", @@ -2311,9 +2257,14 @@ static int sbridge_get_onedevice(struct pci_dev **prev, } bus = pdev->bus->number; - sbridge_dev = get_sbridge_dev(bus, multi_bus); +next_imc: + sbridge_dev = get_sbridge_dev(bus, dev_descr->dom, multi_bus, sbridge_dev); if (!sbridge_dev) { - sbridge_dev = alloc_sbridge_dev(bus, table); + + if (dev_descr->dom == SOCK) + goto out_imc; + + sbridge_dev = alloc_sbridge_dev(bus, dev_descr->dom, table); if (!sbridge_dev) { pci_dev_put(pdev); return -ENOMEM; @@ -2321,7 +2272,7 @@ static int sbridge_get_onedevice(struct pci_dev **prev, (*num_mc)++; } - if (sbridge_dev->pdev[devno]) { + if (sbridge_dev->pdev[sbridge_dev->i_devs]) { sbridge_printk(KERN_ERR, "Duplicated device for %04x:%04x\n", PCI_VENDOR_ID_INTEL, dev_descr->dev_id); @@ -2329,8 +2280,16 @@ static int sbridge_get_onedevice(struct pci_dev **prev, return -ENODEV; } - sbridge_dev->pdev[devno] = pdev; + sbridge_dev->pdev[sbridge_dev->i_devs++] = pdev; + + /* pdev belongs to more than one IMC, do extra gets */ + if (++i > 1) + pci_dev_get(pdev); + if (dev_descr->dom == SOCK && i < table->n_imcs_per_sock) + goto next_imc; + +out_imc: /* Be sure that the device is enabled */ if (unlikely(pci_enable_device(pdev) < 0)) { sbridge_printk(KERN_ERR, @@ -2374,7 +2333,7 @@ static int sbridge_get_all_devices(u8 *num_mc, if (table->type == KNIGHTS_LANDING) allow_dups = multi_bus = 1; while (table && table->descr) { - for (i = 0; i < table->n_devs; i++) { + for (i = 0; i < table->n_devs_per_sock; i++) { if (!allow_dups || i == 0 || table->descr[i].dev_id != table->descr[i-1].dev_id) { @@ -2385,7 +2344,7 @@ static int sbridge_get_all_devices(u8 *num_mc, table, i, multi_bus); if (rc < 0) { if (i == 0) { - i = table->n_devs; + i = table->n_devs_per_sock; break; } sbridge_put_all_devices(); @@ -2399,6 +2358,13 @@ static int sbridge_get_all_devices(u8 *num_mc, return 0; } +/* + * Device IDs for {SBRIDGE,IBRIDGE,HASWELL,BROADWELL}_IMC_HA0_TAD0 are in + * the format: XXXa. So we can convert from a device to the corresponding + * channel like this + */ +#define TAD_DEV_TO_CHAN(dev) (((dev) & 0xf) - 0xa) + static int sbridge_mci_bind_devs(struct mem_ctl_info *mci, struct sbridge_dev *sbridge_dev) { @@ -2423,7 +2389,7 @@ static int sbridge_mci_bind_devs(struct mem_ctl_info *mci, pvt->pci_br0 = pdev; break; case PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_HA0: - pvt->pci_ha0 = pdev; + pvt->pci_ha = pdev; break; case PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TA: pvt->pci_ta = pdev; @@ -2436,7 +2402,7 @@ static int sbridge_mci_bind_devs(struct mem_ctl_info *mci, case PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD2: case PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD3: { - int id = pdev->device - PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD0; + int id = TAD_DEV_TO_CHAN(pdev->device); pvt->pci_tad[id] = pdev; saw_chan_mask |= 1 << id; } @@ -2455,7 +2421,7 @@ static int sbridge_mci_bind_devs(struct mem_ctl_info *mci, } /* Check if everything were registered */ - if (!pvt->pci_sad0 || !pvt->pci_sad1 || !pvt->pci_ha0 || + if (!pvt->pci_sad0 || !pvt->pci_sad1 || !pvt->pci_ha || !pvt->pci_ras || !pvt->pci_ta) goto enodev; @@ -2488,19 +2454,26 @@ static int ibridge_mci_bind_devs(struct mem_ctl_info *mci, switch (pdev->device) { case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0: - pvt->pci_ha0 = pdev; + case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1: + pvt->pci_ha = pdev; break; case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TA: + case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TA: pvt->pci_ta = pdev; case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_RAS: + case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_RAS: pvt->pci_ras = pdev; break; case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TAD0: case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TAD1: case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TAD2: case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TAD3: + case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD0: + case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD1: + case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD2: + case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD3: { - int id = pdev->device - PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TAD0; + int id = TAD_DEV_TO_CHAN(pdev->device); pvt->pci_tad[id] = pdev; saw_chan_mask |= 1 << id; } @@ -2520,19 +2493,6 @@ static int ibridge_mci_bind_devs(struct mem_ctl_info *mci, case PCI_DEVICE_ID_INTEL_IBRIDGE_BR1: pvt->pci_br1 = pdev; break; - case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1: - pvt->pci_ha1 = pdev; - break; - case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD0: - case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD1: - case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD2: - case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD3: - { - int id = pdev->device - PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TAD0 + 4; - pvt->pci_tad[id] = pdev; - saw_chan_mask |= 1 << id; - } - break; default: goto error; } @@ -2544,13 +2504,12 @@ static int ibridge_mci_bind_devs(struct mem_ctl_info *mci, } /* Check if everything were registered */ - if (!pvt->pci_sad0 || !pvt->pci_ha0 || !pvt->pci_br0 || + if (!pvt->pci_sad0 || !pvt->pci_ha || !pvt->pci_br0 || !pvt->pci_br1 || !pvt->pci_ras || !pvt->pci_ta) goto enodev; - if (saw_chan_mask != 0x0f && /* -EN */ - saw_chan_mask != 0x33 && /* -EP */ - saw_chan_mask != 0xff) /* -EX */ + if (saw_chan_mask != 0x0f && /* -EN/-EX */ + saw_chan_mask != 0x03) /* -EP */ goto enodev; return 0; @@ -2593,32 +2552,27 @@ static int haswell_mci_bind_devs(struct mem_ctl_info *mci, pvt->pci_sad1 = pdev; break; case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0: - pvt->pci_ha0 = pdev; + case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1: + pvt->pci_ha = pdev; break; case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TA: + case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TA: pvt->pci_ta = pdev; break; - case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_THERMAL: + case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TM: + case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TM: pvt->pci_ras = pdev; break; case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TAD0: case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TAD1: case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TAD2: case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TAD3: - { - int id = pdev->device - PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0_TAD0; - - pvt->pci_tad[id] = pdev; - saw_chan_mask |= 1 << id; - } - break; case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TAD0: case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TAD1: case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TAD2: case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TAD3: { - int id = pdev->device - PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TAD0 + 4; - + int id = TAD_DEV_TO_CHAN(pdev->device); pvt->pci_tad[id] = pdev; saw_chan_mask |= 1 << id; } @@ -2630,12 +2584,6 @@ static int haswell_mci_bind_devs(struct mem_ctl_info *mci, if (!pvt->pci_ddrio) pvt->pci_ddrio = pdev; break; - case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1: - pvt->pci_ha1 = pdev; - break; - case PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA1_TA: - pvt->pci_ha1_ta = pdev; - break; default: break; } @@ -2647,13 +2595,12 @@ static int haswell_mci_bind_devs(struct mem_ctl_info *mci, } /* Check if everything were registered */ - if (!pvt->pci_sad0 || !pvt->pci_ha0 || !pvt->pci_sad1 || + if (!pvt->pci_sad0 || !pvt->pci_ha || !pvt->pci_sad1 || !pvt->pci_ras || !pvt->pci_ta || !pvt->info.pci_vtd) goto enodev; - if (saw_chan_mask != 0x0f && /* -EN */ - saw_chan_mask != 0x33 && /* -EP */ - saw_chan_mask != 0xff) /* -EX */ + if (saw_chan_mask != 0x0f && /* -EN/-EX */ + saw_chan_mask != 0x03) /* -EP */ goto enodev; return 0; @@ -2690,30 +2637,27 @@ static int broadwell_mci_bind_devs(struct mem_ctl_info *mci, pvt->pci_sad1 = pdev; break; case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0: - pvt->pci_ha0 = pdev; + case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1: + pvt->pci_ha = pdev; break; case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TA: + case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TA: pvt->pci_ta = pdev; break; - case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_THERMAL: + case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TM: + case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TM: pvt->pci_ras = pdev; break; case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TAD0: case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TAD1: case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TAD2: case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TAD3: - { - int id = pdev->device - PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA0_TAD0; - pvt->pci_tad[id] = pdev; - saw_chan_mask |= 1 << id; - } - break; case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TAD0: case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TAD1: case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TAD2: case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TAD3: { - int id = pdev->device - PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TAD0 + 4; + int id = TAD_DEV_TO_CHAN(pdev->device); pvt->pci_tad[id] = pdev; saw_chan_mask |= 1 << id; } @@ -2721,12 +2665,6 @@ static int broadwell_mci_bind_devs(struct mem_ctl_info *mci, case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_DDRIO0: pvt->pci_ddrio = pdev; break; - case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1: - pvt->pci_ha1 = pdev; - break; - case PCI_DEVICE_ID_INTEL_BROADWELL_IMC_HA1_TA: - pvt->pci_ha1_ta = pdev; - break; default: break; } @@ -2738,13 +2676,12 @@ static int broadwell_mci_bind_devs(struct mem_ctl_info *mci, } /* Check if everything were registered */ - if (!pvt->pci_sad0 || !pvt->pci_ha0 || !pvt->pci_sad1 || + if (!pvt->pci_sad0 || !pvt->pci_ha || !pvt->pci_sad1 || !pvt->pci_ras || !pvt->pci_ta || !pvt->info.pci_vtd) goto enodev; - if (saw_chan_mask != 0x0f && /* -EN */ - saw_chan_mask != 0x33 && /* -EP */ - saw_chan_mask != 0xff) /* -EX */ + if (saw_chan_mask != 0x0f && /* -EN/-EX */ + saw_chan_mask != 0x03) /* -EP */ goto enodev; return 0; @@ -2812,7 +2749,7 @@ static int knl_mci_bind_devs(struct mem_ctl_info *mci, pvt->knl.pci_cha[devidx] = pdev; break; - case PCI_DEVICE_ID_INTEL_KNL_IMC_CHANNEL: + case PCI_DEVICE_ID_INTEL_KNL_IMC_CHAN: devidx = -1; /* @@ -3006,7 +2943,7 @@ static void sbridge_mce_output_error(struct mem_ctl_info *mci, if (rc < 0) goto err_parsing; - new_mci = get_mci_for_node_id(socket); + new_mci = get_mci_for_node_id(socket, ha); if (!new_mci) { strcpy(msg, "Error: socket got corrupted!"); goto err_parsing; @@ -3053,7 +2990,7 @@ static void sbridge_mce_output_error(struct mem_ctl_info *mci, /* Call the helper to output message */ edac_mc_handle_error(tp_event, mci, core_err_cnt, m->addr >> PAGE_SHIFT, m->addr & ~PAGE_MASK, 0, - 4*ha+channel, dimm, -1, + channel, dimm, -1, optype, msg); return; err_parsing: @@ -3078,7 +3015,7 @@ static int sbridge_mce_check_error(struct notifier_block *nb, unsigned long val, if (edac_get_report_status() == EDAC_REPORTING_DISABLED) return NOTIFY_DONE; - mci = get_mci_for_node_id(mce->socketid); + mci = get_mci_for_node_id(mce->socketid, IMC0); if (!mci) return NOTIFY_DONE; pvt = mci->pvt_info; @@ -3159,11 +3096,6 @@ static int sbridge_register_mci(struct sbridge_dev *sbridge_dev, enum type type) struct pci_dev *pdev = sbridge_dev->pdev[0]; int rc; - /* Check the number of active and not disabled channels */ - rc = check_if_ecc_is_active(sbridge_dev->bus, type); - if (unlikely(rc < 0)) - return rc; - /* allocate a new MC control structure */ layers[0].type = EDAC_MC_LAYER_CHANNEL; layers[0].size = type == KNIGHTS_LANDING ? @@ -3192,7 +3124,7 @@ static int sbridge_register_mci(struct sbridge_dev *sbridge_dev, enum type type) MEM_FLAG_DDR4 : MEM_FLAG_DDR3; mci->edac_ctl_cap = EDAC_FLAG_NONE; mci->edac_cap = EDAC_FLAG_NONE; - mci->mod_name = "sbridge_edac.c"; + mci->mod_name = "sb_edac.c"; mci->mod_ver = SBRIDGE_REVISION; mci->dev_name = pci_name(pdev); mci->ctl_page_to_phys = NULL; @@ -3215,12 +3147,14 @@ static int sbridge_register_mci(struct sbridge_dev *sbridge_dev, enum type type) pvt->info.max_interleave = ARRAY_SIZE(ibridge_interleave_list); pvt->info.interleave_pkg = ibridge_interleave_pkg; pvt->info.get_width = ibridge_get_width; - mci->ctl_name = kasprintf(GFP_KERNEL, "Ivy Bridge Socket#%d", mci->mc_idx); /* Store pci devices at mci for faster access */ rc = ibridge_mci_bind_devs(mci, sbridge_dev); if (unlikely(rc < 0)) goto fail0; + get_source_id(mci); + mci->ctl_name = kasprintf(GFP_KERNEL, "Ivy Bridge SrcID#%d_Ha#%d", + pvt->sbridge_dev->source_id, pvt->sbridge_dev->dom); break; case SANDY_BRIDGE: pvt->info.rankcfgr = SB_RANK_CFG_A; @@ -3238,12 +3172,14 @@ static int sbridge_register_mci(struct sbridge_dev *sbridge_dev, enum type type) pvt->info.max_interleave = ARRAY_SIZE(sbridge_interleave_list); pvt->info.interleave_pkg = sbridge_interleave_pkg; pvt->info.get_width = sbridge_get_width; - mci->ctl_name = kasprintf(GFP_KERNEL, "Sandy Bridge Socket#%d", mci->mc_idx); /* Store pci devices at mci for faster access */ rc = sbridge_mci_bind_devs(mci, sbridge_dev); if (unlikely(rc < 0)) goto fail0; + get_source_id(mci); + mci->ctl_name = kasprintf(GFP_KERNEL, "Sandy Bridge SrcID#%d_Ha#%d", + pvt->sbridge_dev->source_id, pvt->sbridge_dev->dom); break; case HASWELL: /* rankcfgr isn't used */ @@ -3261,12 +3197,14 @@ static int sbridge_register_mci(struct sbridge_dev *sbridge_dev, enum type type) pvt->info.max_interleave = ARRAY_SIZE(ibridge_interleave_list); pvt->info.interleave_pkg = ibridge_interleave_pkg; pvt->info.get_width = ibridge_get_width; - mci->ctl_name = kasprintf(GFP_KERNEL, "Haswell Socket#%d", mci->mc_idx); /* Store pci devices at mci for faster access */ rc = haswell_mci_bind_devs(mci, sbridge_dev); if (unlikely(rc < 0)) goto fail0; + get_source_id(mci); + mci->ctl_name = kasprintf(GFP_KERNEL, "Haswell SrcID#%d_Ha#%d", + pvt->sbridge_dev->source_id, pvt->sbridge_dev->dom); break; case BROADWELL: /* rankcfgr isn't used */ @@ -3284,12 +3222,14 @@ static int sbridge_register_mci(struct sbridge_dev *sbridge_dev, enum type type) pvt->info.max_interleave = ARRAY_SIZE(ibridge_interleave_list); pvt->info.interleave_pkg = ibridge_interleave_pkg; pvt->info.get_width = broadwell_get_width; - mci->ctl_name = kasprintf(GFP_KERNEL, "Broadwell Socket#%d", mci->mc_idx); /* Store pci devices at mci for faster access */ rc = broadwell_mci_bind_devs(mci, sbridge_dev); if (unlikely(rc < 0)) goto fail0; + get_source_id(mci); + mci->ctl_name = kasprintf(GFP_KERNEL, "Broadwell SrcID#%d_Ha#%d", + pvt->sbridge_dev->source_id, pvt->sbridge_dev->dom); break; case KNIGHTS_LANDING: /* pvt->info.rankcfgr == ??? */ @@ -3307,17 +3247,22 @@ static int sbridge_register_mci(struct sbridge_dev *sbridge_dev, enum type type) pvt->info.max_interleave = ARRAY_SIZE(knl_interleave_list); pvt->info.interleave_pkg = ibridge_interleave_pkg; pvt->info.get_width = knl_get_width; - mci->ctl_name = kasprintf(GFP_KERNEL, - "Knights Landing Socket#%d", mci->mc_idx); rc = knl_mci_bind_devs(mci, sbridge_dev); if (unlikely(rc < 0)) goto fail0; + get_source_id(mci); + mci->ctl_name = kasprintf(GFP_KERNEL, "Knights Landing SrcID#%d_Ha#%d", + pvt->sbridge_dev->source_id, pvt->sbridge_dev->dom); break; } /* Get dimm basic config and the memory layout */ - get_dimm_config(mci); + rc = get_dimm_config(mci); + if (rc < 0) { + edac_dbg(0, "MC: failed to get_dimm_config()\n"); + goto fail; + } get_memory_layout(mci); /* record ptr to the generic device */ @@ -3327,13 +3272,14 @@ static int sbridge_register_mci(struct sbridge_dev *sbridge_dev, enum type type) if (unlikely(edac_mc_add_mc(mci))) { edac_dbg(0, "MC: failed edac_mc_add_mc()\n"); rc = -EINVAL; - goto fail0; + goto fail; } return 0; -fail0: +fail: kfree(mci->ctl_name); +fail0: edac_mc_free(mci); sbridge_dev->mci = NULL; return rc; diff --git a/drivers/edac/thunderx_edac.c b/drivers/edac/thunderx_edac.c index 86d585cb6d32..2d352b40ae1c 100644 --- a/drivers/edac/thunderx_edac.c +++ b/drivers/edac/thunderx_edac.c @@ -2080,7 +2080,7 @@ static int thunderx_l2c_probe(struct pci_dev *pdev, if (IS_ENABLED(CONFIG_EDAC_DEBUG)) { l2c->debugfs = edac_debugfs_create_dir(pdev->dev.kobj.name); - thunderx_create_debugfs_nodes(l2c->debugfs, l2c_devattr, + ret = thunderx_create_debugfs_nodes(l2c->debugfs, l2c_devattr, l2c, dfs_entries); if (ret != dfs_entries) { diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig index 2e78b0b96d74..394db40ed374 100644 --- a/drivers/firmware/efi/Kconfig +++ b/drivers/firmware/efi/Kconfig @@ -112,6 +112,15 @@ config EFI_CAPSULE_LOADER Most users should say N. +config EFI_CAPSULE_QUIRK_QUARK_CSH + boolean "Add support for Quark capsules with non-standard headers" + depends on X86 && !64BIT + select EFI_CAPSULE_LOADER + default y + help + Add support for processing Quark X1000 EFI capsules, whose header + layout deviates from the layout mandated by the UEFI specification. + config EFI_TEST tristate "EFI Runtime Service Tests Support" depends on EFI diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c index 974c5a31a005..1cc41c3d6315 100644 --- a/drivers/firmware/efi/arm-runtime.c +++ b/drivers/firmware/efi/arm-runtime.c @@ -11,6 +11,7 @@ * */ +#include <linux/dmi.h> #include <linux/efi.h> #include <linux/io.h> #include <linux/memblock.h> @@ -166,3 +167,18 @@ void efi_virtmap_unload(void) efi_set_pgd(current->active_mm); preempt_enable(); } + + +static int __init arm_dmi_init(void) +{ + /* + * On arm64/ARM, DMI depends on UEFI, and dmi_scan_machine() needs to + * be called early because dmi_id_init(), which is an arch_initcall + * itself, depends on dmi_scan_machine() having been called already. + */ + dmi_scan_machine(); + if (dmi_available) + dmi_set_dump_stack_arch_desc(); + return 0; +} +core_initcall(arm_dmi_init); diff --git a/drivers/firmware/efi/capsule-loader.c b/drivers/firmware/efi/capsule-loader.c index 9ae6c116c474..ec8ac5c4dd84 100644 --- a/drivers/firmware/efi/capsule-loader.c +++ b/drivers/firmware/efi/capsule-loader.c @@ -20,15 +20,9 @@ #define NO_FURTHER_WRITE_ACTION -1 -struct capsule_info { - bool header_obtained; - int reset_type; - long index; - size_t count; - size_t total_size; - struct page **pages; - size_t page_bytes_remain; -}; +#ifndef phys_to_page +#define phys_to_page(x) pfn_to_page((x) >> PAGE_SHIFT) +#endif /** * efi_free_all_buff_pages - free all previous allocated buffer pages @@ -41,65 +35,70 @@ struct capsule_info { static void efi_free_all_buff_pages(struct capsule_info *cap_info) { while (cap_info->index > 0) - __free_page(cap_info->pages[--cap_info->index]); + __free_page(phys_to_page(cap_info->pages[--cap_info->index])); cap_info->index = NO_FURTHER_WRITE_ACTION; } -/** - * efi_capsule_setup_info - obtain the efi capsule header in the binary and - * setup capsule_info structure - * @cap_info: pointer to current instance of capsule_info structure - * @kbuff: a mapped first page buffer pointer - * @hdr_bytes: the total received number of bytes for efi header - **/ -static ssize_t efi_capsule_setup_info(struct capsule_info *cap_info, - void *kbuff, size_t hdr_bytes) +int __efi_capsule_setup_info(struct capsule_info *cap_info) { - efi_capsule_header_t *cap_hdr; size_t pages_needed; int ret; void *temp_page; - /* Only process data block that is larger than efi header size */ - if (hdr_bytes < sizeof(efi_capsule_header_t)) - return 0; - - /* Reset back to the correct offset of header */ - cap_hdr = kbuff - cap_info->count; - pages_needed = ALIGN(cap_hdr->imagesize, PAGE_SIZE) >> PAGE_SHIFT; + pages_needed = ALIGN(cap_info->total_size, PAGE_SIZE) / PAGE_SIZE; if (pages_needed == 0) { - pr_err("%s: pages count invalid\n", __func__); + pr_err("invalid capsule size"); return -EINVAL; } /* Check if the capsule binary supported */ - ret = efi_capsule_supported(cap_hdr->guid, cap_hdr->flags, - cap_hdr->imagesize, + ret = efi_capsule_supported(cap_info->header.guid, + cap_info->header.flags, + cap_info->header.imagesize, &cap_info->reset_type); if (ret) { - pr_err("%s: efi_capsule_supported() failed\n", - __func__); + pr_err("capsule not supported\n"); return ret; } - cap_info->total_size = cap_hdr->imagesize; temp_page = krealloc(cap_info->pages, pages_needed * sizeof(void *), GFP_KERNEL | __GFP_ZERO); - if (!temp_page) { - pr_debug("%s: krealloc() failed\n", __func__); + if (!temp_page) return -ENOMEM; - } cap_info->pages = temp_page; - cap_info->header_obtained = true; return 0; } /** + * efi_capsule_setup_info - obtain the efi capsule header in the binary and + * setup capsule_info structure + * @cap_info: pointer to current instance of capsule_info structure + * @kbuff: a mapped first page buffer pointer + * @hdr_bytes: the total received number of bytes for efi header + * + * Platforms with non-standard capsule update mechanisms can override + * this __weak function so they can perform any required capsule + * image munging. See quark_quirk_function() for an example. + **/ +int __weak efi_capsule_setup_info(struct capsule_info *cap_info, void *kbuff, + size_t hdr_bytes) +{ + /* Only process data block that is larger than efi header size */ + if (hdr_bytes < sizeof(efi_capsule_header_t)) + return 0; + + memcpy(&cap_info->header, kbuff, sizeof(cap_info->header)); + cap_info->total_size = cap_info->header.imagesize; + + return __efi_capsule_setup_info(cap_info); +} + +/** * efi_capsule_submit_update - invoke the efi_capsule_update API once binary * upload done * @cap_info: pointer to current instance of capsule_info structure @@ -107,26 +106,17 @@ static ssize_t efi_capsule_setup_info(struct capsule_info *cap_info, static ssize_t efi_capsule_submit_update(struct capsule_info *cap_info) { int ret; - void *cap_hdr_temp; - - cap_hdr_temp = vmap(cap_info->pages, cap_info->index, - VM_MAP, PAGE_KERNEL); - if (!cap_hdr_temp) { - pr_debug("%s: vmap() failed\n", __func__); - return -EFAULT; - } - ret = efi_capsule_update(cap_hdr_temp, cap_info->pages); - vunmap(cap_hdr_temp); + ret = efi_capsule_update(&cap_info->header, cap_info->pages); if (ret) { - pr_err("%s: efi_capsule_update() failed\n", __func__); + pr_err("capsule update failed\n"); return ret; } /* Indicate capsule binary uploading is done */ cap_info->index = NO_FURTHER_WRITE_ACTION; - pr_info("%s: Successfully upload capsule file with reboot type '%s'\n", - __func__, !cap_info->reset_type ? "RESET_COLD" : + pr_info("Successfully upload capsule file with reboot type '%s'\n", + !cap_info->reset_type ? "RESET_COLD" : cap_info->reset_type == 1 ? "RESET_WARM" : "RESET_SHUTDOWN"); return 0; @@ -171,37 +161,30 @@ static ssize_t efi_capsule_write(struct file *file, const char __user *buff, if (!cap_info->page_bytes_remain) { page = alloc_page(GFP_KERNEL); if (!page) { - pr_debug("%s: alloc_page() failed\n", __func__); ret = -ENOMEM; goto failed; } - cap_info->pages[cap_info->index++] = page; + cap_info->pages[cap_info->index++] = page_to_phys(page); cap_info->page_bytes_remain = PAGE_SIZE; + } else { + page = phys_to_page(cap_info->pages[cap_info->index - 1]); } - page = cap_info->pages[cap_info->index - 1]; - kbuff = kmap(page); - if (!kbuff) { - pr_debug("%s: kmap() failed\n", __func__); - ret = -EFAULT; - goto failed; - } kbuff += PAGE_SIZE - cap_info->page_bytes_remain; /* Copy capsule binary data from user space to kernel space buffer */ write_byte = min_t(size_t, count, cap_info->page_bytes_remain); if (copy_from_user(kbuff, buff, write_byte)) { - pr_debug("%s: copy_from_user() failed\n", __func__); ret = -EFAULT; goto fail_unmap; } cap_info->page_bytes_remain -= write_byte; /* Setup capsule binary info structure */ - if (!cap_info->header_obtained) { - ret = efi_capsule_setup_info(cap_info, kbuff, + if (cap_info->header.headersize == 0) { + ret = efi_capsule_setup_info(cap_info, kbuff - cap_info->count, cap_info->count + write_byte); if (ret) goto fail_unmap; @@ -211,11 +194,10 @@ static ssize_t efi_capsule_write(struct file *file, const char __user *buff, kunmap(page); /* Submit the full binary to efi_capsule_update() API */ - if (cap_info->header_obtained && + if (cap_info->header.headersize > 0 && cap_info->count >= cap_info->total_size) { if (cap_info->count > cap_info->total_size) { - pr_err("%s: upload size exceeded header defined size\n", - __func__); + pr_err("capsule upload size exceeded header defined size\n"); ret = -EINVAL; goto failed; } @@ -249,7 +231,7 @@ static int efi_capsule_flush(struct file *file, fl_owner_t id) struct capsule_info *cap_info = file->private_data; if (cap_info->index > 0) { - pr_err("%s: capsule upload not complete\n", __func__); + pr_err("capsule upload not complete\n"); efi_free_all_buff_pages(cap_info); ret = -ECANCELED; } @@ -328,8 +310,7 @@ static int __init efi_capsule_loader_init(void) ret = misc_register(&efi_capsule_misc); if (ret) - pr_err("%s: Failed to register misc char file note\n", - __func__); + pr_err("Unable to register capsule loader device\n"); return ret; } diff --git a/drivers/firmware/efi/capsule.c b/drivers/firmware/efi/capsule.c index 6eedff45e6d7..901b9306bf94 100644 --- a/drivers/firmware/efi/capsule.c +++ b/drivers/firmware/efi/capsule.c @@ -214,7 +214,7 @@ efi_capsule_update_locked(efi_capsule_header_t *capsule, * * Return 0 on success, a converted EFI status code on failure. */ -int efi_capsule_update(efi_capsule_header_t *capsule, struct page **pages) +int efi_capsule_update(efi_capsule_header_t *capsule, phys_addr_t *pages) { u32 imagesize = capsule->imagesize; efi_guid_t guid = capsule->guid; @@ -247,16 +247,13 @@ int efi_capsule_update(efi_capsule_header_t *capsule, struct page **pages) efi_capsule_block_desc_t *sglist; sglist = kmap(sg_pages[i]); - if (!sglist) { - rv = -ENOMEM; - goto out; - } for (j = 0; j < SGLIST_PER_PAGE && count > 0; j++) { - u64 sz = min_t(u64, imagesize, PAGE_SIZE); + u64 sz = min_t(u64, imagesize, + PAGE_SIZE - (u64)*pages % PAGE_SIZE); sglist[j].length = sz; - sglist[j].data = page_to_phys(*pages++); + sglist[j].data = *pages++; imagesize -= sz; count--; diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index b372aad3b449..045d6d311bde 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -528,7 +528,8 @@ int __init efi_config_parse_tables(void *config_tables, int count, int sz, } } - efi_memattr_init(); + if (efi_enabled(EFI_MEMMAP)) + efi_memattr_init(); /* Parse the EFI Properties table if it exists */ if (efi.properties_table != EFI_INVALID_TABLE_ADDR) { diff --git a/drivers/firmware/efi/test/efi_test.c b/drivers/firmware/efi/test/efi_test.c index 8cd578f62059..08129b7b80ab 100644 --- a/drivers/firmware/efi/test/efi_test.c +++ b/drivers/firmware/efi/test/efi_test.c @@ -71,18 +71,13 @@ copy_ucs2_from_user_len(efi_char16_t **dst, efi_char16_t __user *src, if (!access_ok(VERIFY_READ, src, 1)) return -EFAULT; - buf = kmalloc(len, GFP_KERNEL); - if (!buf) { + buf = memdup_user(src, len); + if (IS_ERR(buf)) { *dst = NULL; - return -ENOMEM; + return PTR_ERR(buf); } *dst = buf; - if (copy_from_user(*dst, src, len)) { - kfree(buf); - return -EFAULT; - } - return 0; } diff --git a/drivers/gpio/gpio-mvebu.c b/drivers/gpio/gpio-mvebu.c index 5104b6398139..c83ea68be792 100644 --- a/drivers/gpio/gpio-mvebu.c +++ b/drivers/gpio/gpio-mvebu.c @@ -721,7 +721,7 @@ static int mvebu_pwm_probe(struct platform_device *pdev, u32 set; if (!of_device_is_compatible(mvchip->chip.of_node, - "marvell,armada-370-xp-gpio")) + "marvell,armada-370-gpio")) return 0; if (IS_ERR(mvchip->clk)) @@ -852,7 +852,7 @@ static const struct of_device_id mvebu_gpio_of_match[] = { .data = (void *) MVEBU_GPIO_SOC_VARIANT_ARMADAXP, }, { - .compatible = "marvell,armada-370-xp-gpio", + .compatible = "marvell,armada-370-gpio", .data = (void *) MVEBU_GPIO_SOC_VARIANT_ORION, }, { @@ -1128,7 +1128,7 @@ static int mvebu_gpio_probe(struct platform_device *pdev) mvchip); } - /* Armada 370/XP has simple PWM support for GPIO lines */ + /* Some MVEBU SoCs have simple PWM support for GPIO lines */ if (IS_ENABLED(CONFIG_PWM)) return mvebu_pwm_probe(pdev, mvchip, id); diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index 2185232da823..8fa5fcd00e9a 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -201,7 +201,7 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares, handler = acpi_gpio_irq_handler_evt; } if (!handler) - return AE_BAD_PARAMETER; + return AE_OK; pin = acpi_gpiochip_pin_to_gpio_offset(chip->gpiodev, pin); if (pin < 0) diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 5db44139cef8..a42a1eea5714 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -708,7 +708,8 @@ static irqreturn_t lineevent_irq_thread(int irq, void *p) ge.timestamp = ktime_get_real_ns(); - if (le->eflags & GPIOEVENT_REQUEST_BOTH_EDGES) { + if (le->eflags & GPIOEVENT_REQUEST_RISING_EDGE + && le->eflags & GPIOEVENT_REQUEST_FALLING_EDGE) { int level = gpiod_get_value_cansleep(le->desc); if (level) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c index 1cf78f4dd339..1e8e1123ddf4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c @@ -693,6 +693,10 @@ int amdgpu_atombios_get_clock_info(struct amdgpu_device *adev) DRM_INFO("Changing default dispclk from %dMhz to 600Mhz\n", adev->clock.default_dispclk / 100); adev->clock.default_dispclk = 60000; + } else if (adev->clock.default_dispclk <= 60000) { + DRM_INFO("Changing default dispclk from %dMhz to 625Mhz\n", + adev->clock.default_dispclk / 100); + adev->clock.default_dispclk = 62500; } adev->clock.dp_extclk = le16_to_cpu(firmware_info->info_21.usUniphyDPModeExtClkFreq); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index f2d705e6a75a..ab6b0d0febab 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -449,6 +449,7 @@ static const struct pci_device_id pciidlist[] = { {0x1002, 0x6986, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12}, {0x1002, 0x6987, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12}, {0x1002, 0x6995, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12}, + {0x1002, 0x6997, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12}, {0x1002, 0x699F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12}, /* Vega 10 */ {0x1002, 0x6860, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10|AMD_EXP_HW_SUPPORT}, diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_crtc.c b/drivers/gpu/drm/amd/amdgpu/atombios_crtc.c index 8c9bc75a9c2d..8a0818b23ea4 100644 --- a/drivers/gpu/drm/amd/amdgpu/atombios_crtc.c +++ b/drivers/gpu/drm/amd/amdgpu/atombios_crtc.c @@ -165,7 +165,7 @@ void amdgpu_atombios_crtc_powergate(struct drm_crtc *crtc, int state) struct drm_device *dev = crtc->dev; struct amdgpu_device *adev = dev->dev_private; int index = GetIndexIntoMasterTable(COMMAND, EnableDispPowerGating); - ENABLE_DISP_POWER_GATING_PARAMETERS_V2_1 args; + ENABLE_DISP_POWER_GATING_PS_ALLOCATION args; memset(&args, 0, sizeof(args)); @@ -178,7 +178,7 @@ void amdgpu_atombios_crtc_powergate(struct drm_crtc *crtc, int state) void amdgpu_atombios_crtc_powergate_init(struct amdgpu_device *adev) { int index = GetIndexIntoMasterTable(COMMAND, EnableDispPowerGating); - ENABLE_DISP_POWER_GATING_PARAMETERS_V2_1 args; + ENABLE_DISP_POWER_GATING_PS_ALLOCATION args; memset(&args, 0, sizeof(args)); diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c index 9f847615ac74..48ca2457df8c 100644 --- a/drivers/gpu/drm/drm_connector.c +++ b/drivers/gpu/drm/drm_connector.c @@ -1229,21 +1229,6 @@ int drm_mode_getconnector(struct drm_device *dev, void *data, if (!connector) return -ENOENT; - drm_modeset_lock(&dev->mode_config.connection_mutex, NULL); - encoder = drm_connector_get_encoder(connector); - if (encoder) - out_resp->encoder_id = encoder->base.id; - else - out_resp->encoder_id = 0; - - ret = drm_mode_object_get_properties(&connector->base, file_priv->atomic, - (uint32_t __user *)(unsigned long)(out_resp->props_ptr), - (uint64_t __user *)(unsigned long)(out_resp->prop_values_ptr), - &out_resp->count_props); - drm_modeset_unlock(&dev->mode_config.connection_mutex); - if (ret) - goto out_unref; - for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) if (connector->encoder_ids[i] != 0) encoders_count++; @@ -1256,7 +1241,7 @@ int drm_mode_getconnector(struct drm_device *dev, void *data, if (put_user(connector->encoder_ids[i], encoder_ptr + copied)) { ret = -EFAULT; - goto out_unref; + goto out; } copied++; } @@ -1300,15 +1285,32 @@ int drm_mode_getconnector(struct drm_device *dev, void *data, if (copy_to_user(mode_ptr + copied, &u_mode, sizeof(u_mode))) { ret = -EFAULT; + mutex_unlock(&dev->mode_config.mutex); + goto out; } copied++; } } out_resp->count_modes = mode_count; -out: mutex_unlock(&dev->mode_config.mutex); -out_unref: + + drm_modeset_lock(&dev->mode_config.connection_mutex, NULL); + encoder = drm_connector_get_encoder(connector); + if (encoder) + out_resp->encoder_id = encoder->base.id; + else + out_resp->encoder_id = 0; + + /* Only grab properties after probing, to make sure EDID and other + * properties reflect the latest status. */ + ret = drm_mode_object_get_properties(&connector->base, file_priv->atomic, + (uint32_t __user *)(unsigned long)(out_resp->props_ptr), + (uint64_t __user *)(unsigned long)(out_resp->prop_values_ptr), + &out_resp->count_props); + drm_modeset_unlock(&dev->mode_config.connection_mutex); + +out: drm_connector_put(connector); return ret; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.h b/drivers/gpu/drm/etnaviv/etnaviv_gem.h index c4a091e87426..e437fba1209d 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.h +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.h @@ -106,9 +106,10 @@ struct etnaviv_gem_submit { struct etnaviv_gpu *gpu; struct ww_acquire_ctx ticket; struct dma_fence *fence; + u32 flags; unsigned int nr_bos; struct etnaviv_gem_submit_bo bos[0]; - u32 flags; + /* No new members here, the previous one is variable-length! */ }; int etnaviv_gem_wait_bo(struct etnaviv_gpu *gpu, struct drm_gem_object *obj, diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c index de80ee1b71df..1013765274da 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c @@ -172,7 +172,7 @@ static int submit_fence_sync(const struct etnaviv_gem_submit *submit) for (i = 0; i < submit->nr_bos; i++) { struct etnaviv_gem_object *etnaviv_obj = submit->bos[i].obj; bool write = submit->bos[i].flags & ETNA_SUBMIT_BO_WRITE; - bool explicit = !(submit->flags & ETNA_SUBMIT_NO_IMPLICIT); + bool explicit = !!(submit->flags & ETNA_SUBMIT_NO_IMPLICIT); ret = etnaviv_gpu_fence_sync_obj(etnaviv_obj, context, write, explicit); diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index d689e511744e..4bd1467c17b1 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -292,6 +292,8 @@ static int per_file_stats(int id, void *ptr, void *data) struct file_stats *stats = data; struct i915_vma *vma; + lockdep_assert_held(&obj->base.dev->struct_mutex); + stats->count++; stats->total += obj->base.size; if (!obj->bind_count) @@ -476,6 +478,8 @@ static int i915_gem_object_info(struct seq_file *m, void *data) struct drm_i915_gem_request *request; struct task_struct *task; + mutex_lock(&dev->struct_mutex); + memset(&stats, 0, sizeof(stats)); stats.file_priv = file->driver_priv; spin_lock(&file->table_lock); @@ -487,7 +491,6 @@ static int i915_gem_object_info(struct seq_file *m, void *data) * still alive (e.g. get_pid(current) => fork() => exit()). * Therefore, we need to protect this ->comm access using RCU. */ - mutex_lock(&dev->struct_mutex); request = list_first_entry_or_null(&file_priv->mm.request_list, struct drm_i915_gem_request, client_link); @@ -497,6 +500,7 @@ static int i915_gem_object_info(struct seq_file *m, void *data) PIDTYPE_PID); print_file_stats(m, task ? task->comm : "<unknown>", stats); rcu_read_unlock(); + mutex_unlock(&dev->struct_mutex); } mutex_unlock(&dev->filelist_mutex); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 462031cbd77f..615f0a855222 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -2285,8 +2285,8 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj) struct page *page; unsigned long last_pfn = 0; /* suppress gcc warning */ unsigned int max_segment; + gfp_t noreclaim; int ret; - gfp_t gfp; /* Assert that the object is not currently in any GPU domain. As it * wasn't in the GTT, there shouldn't be any way it could have been in @@ -2315,22 +2315,31 @@ rebuild_st: * Fail silently without starting the shrinker */ mapping = obj->base.filp->f_mapping; - gfp = mapping_gfp_constraint(mapping, ~(__GFP_IO | __GFP_RECLAIM)); - gfp |= __GFP_NORETRY | __GFP_NOWARN; + noreclaim = mapping_gfp_constraint(mapping, + ~(__GFP_IO | __GFP_RECLAIM)); + noreclaim |= __GFP_NORETRY | __GFP_NOWARN; + sg = st->sgl; st->nents = 0; for (i = 0; i < page_count; i++) { - page = shmem_read_mapping_page_gfp(mapping, i, gfp); - if (unlikely(IS_ERR(page))) { - i915_gem_shrink(dev_priv, - page_count, - I915_SHRINK_BOUND | - I915_SHRINK_UNBOUND | - I915_SHRINK_PURGEABLE); + const unsigned int shrink[] = { + I915_SHRINK_BOUND | I915_SHRINK_UNBOUND | I915_SHRINK_PURGEABLE, + 0, + }, *s = shrink; + gfp_t gfp = noreclaim; + + do { page = shmem_read_mapping_page_gfp(mapping, i, gfp); - } - if (unlikely(IS_ERR(page))) { - gfp_t reclaim; + if (likely(!IS_ERR(page))) + break; + + if (!*s) { + ret = PTR_ERR(page); + goto err_sg; + } + + i915_gem_shrink(dev_priv, 2 * page_count, *s++); + cond_resched(); /* We've tried hard to allocate the memory by reaping * our own buffer, now let the real VM do its job and @@ -2340,15 +2349,26 @@ rebuild_st: * defer the oom here by reporting the ENOMEM back * to userspace. */ - reclaim = mapping_gfp_mask(mapping); - reclaim |= __GFP_NORETRY; /* reclaim, but no oom */ - - page = shmem_read_mapping_page_gfp(mapping, i, reclaim); - if (IS_ERR(page)) { - ret = PTR_ERR(page); - goto err_sg; + if (!*s) { + /* reclaim and warn, but no oom */ + gfp = mapping_gfp_mask(mapping); + + /* Our bo are always dirty and so we require + * kswapd to reclaim our pages (direct reclaim + * does not effectively begin pageout of our + * buffers on its own). However, direct reclaim + * only waits for kswapd when under allocation + * congestion. So as a result __GFP_RECLAIM is + * unreliable and fails to actually reclaim our + * dirty pages -- unless you try over and over + * again with !__GFP_NORETRY. However, we still + * want to fail this allocation rather than + * trigger the out-of-memory killer and for + * this we want the future __GFP_MAYFAIL. + */ } - } + } while (1); + if (!i || sg->length >= max_segment || page_to_pfn(page) != last_pfn + 1) { @@ -4222,6 +4242,7 @@ i915_gem_object_create(struct drm_i915_private *dev_priv, u64 size) mapping = obj->base.filp->f_mapping; mapping_set_gfp_mask(mapping, mask); + GEM_BUG_ON(!(mapping_gfp_mask(mapping) & __GFP_RECLAIM)); i915_gem_object_init(obj, &i915_gem_object_ops); diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index a3e59c8ef27b..9ad13eeed904 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -546,11 +546,12 @@ repeat: } static int -i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj, +i915_gem_execbuffer_relocate_entry(struct i915_vma *vma, struct eb_vmas *eb, struct drm_i915_gem_relocation_entry *reloc, struct reloc_cache *cache) { + struct drm_i915_gem_object *obj = vma->obj; struct drm_i915_private *dev_priv = to_i915(obj->base.dev); struct drm_gem_object *target_obj; struct drm_i915_gem_object *target_i915_obj; @@ -628,6 +629,16 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj, return -EINVAL; } + /* + * If we write into the object, we need to force the synchronisation + * barrier, either with an asynchronous clflush or if we executed the + * patching using the GPU (though that should be serialised by the + * timeline). To be completely sure, and since we are required to + * do relocations we are already stalling, disable the user's opt + * of our synchronisation. + */ + vma->exec_entry->flags &= ~EXEC_OBJECT_ASYNC; + ret = relocate_entry(obj, reloc, cache, target_offset); if (ret) return ret; @@ -678,7 +689,7 @@ i915_gem_execbuffer_relocate_vma(struct i915_vma *vma, do { u64 offset = r->presumed_offset; - ret = i915_gem_execbuffer_relocate_entry(vma->obj, eb, r, &cache); + ret = i915_gem_execbuffer_relocate_entry(vma, eb, r, &cache); if (ret) goto out; @@ -726,7 +737,7 @@ i915_gem_execbuffer_relocate_vma_slow(struct i915_vma *vma, reloc_cache_init(&cache, eb->i915); for (i = 0; i < entry->relocation_count; i++) { - ret = i915_gem_execbuffer_relocate_entry(vma->obj, eb, &relocs[i], &cache); + ret = i915_gem_execbuffer_relocate_entry(vma, eb, &relocs[i], &cache); if (ret) break; } diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c index 5ddbc9499775..a74d0ac737cb 100644 --- a/drivers/gpu/drm/i915/i915_gem_request.c +++ b/drivers/gpu/drm/i915/i915_gem_request.c @@ -623,7 +623,7 @@ i915_gem_request_alloc(struct intel_engine_cs *engine, * GPU processing the request, we never over-estimate the * position of the head. */ - req->head = req->ring->tail; + req->head = req->ring->emit; /* Check that we didn't interrupt ourselves with a new request */ GEM_BUG_ON(req->timeline->seqno != req->fence.seqno); diff --git a/drivers/gpu/drm/i915/i915_gem_request.h b/drivers/gpu/drm/i915/i915_gem_request.h index 129c58bb4805..a4a920c4c454 100644 --- a/drivers/gpu/drm/i915/i915_gem_request.h +++ b/drivers/gpu/drm/i915/i915_gem_request.h @@ -123,7 +123,7 @@ struct drm_i915_gem_request { * It is used by the driver to then queue the request for execution. */ struct i915_sw_fence submit; - wait_queue_t submitq; + wait_queue_entry_t submitq; wait_queue_head_t execute; /* A list of everyone we wait upon, and everyone who waits upon us. diff --git a/drivers/gpu/drm/i915/i915_guc_submission.c b/drivers/gpu/drm/i915/i915_guc_submission.c index 1642fff9cf13..ab5140ba108d 100644 --- a/drivers/gpu/drm/i915/i915_guc_submission.c +++ b/drivers/gpu/drm/i915/i915_guc_submission.c @@ -480,9 +480,7 @@ static void guc_wq_item_append(struct i915_guc_client *client, GEM_BUG_ON(freespace < wqi_size); /* The GuC firmware wants the tail index in QWords, not bytes */ - tail = rq->tail; - assert_ring_tail_valid(rq->ring, rq->tail); - tail >>= 3; + tail = intel_ring_set_tail(rq->ring, rq->tail) >> 3; GEM_BUG_ON(tail > WQ_RING_TAIL_MAX); /* For now workqueue item is 4 DWs; workqueue buffer is 2 pages. So we diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c index a277f8eb7beb..380de4360b8a 100644 --- a/drivers/gpu/drm/i915/i915_sw_fence.c +++ b/drivers/gpu/drm/i915/i915_sw_fence.c @@ -152,7 +152,7 @@ static void __i915_sw_fence_wake_up_all(struct i915_sw_fence *fence, struct list_head *continuation) { wait_queue_head_t *x = &fence->wait; - wait_queue_t *pos, *next; + wait_queue_entry_t *pos, *next; unsigned long flags; debug_fence_deactivate(fence); @@ -160,31 +160,30 @@ static void __i915_sw_fence_wake_up_all(struct i915_sw_fence *fence, /* * To prevent unbounded recursion as we traverse the graph of - * i915_sw_fences, we move the task_list from this, the next ready - * fence, to the tail of the original fence's task_list + * i915_sw_fences, we move the entry list from this, the next ready + * fence, to the tail of the original fence's entry list * (and so added to the list to be woken). */ spin_lock_irqsave_nested(&x->lock, flags, 1 + !!continuation); if (continuation) { - list_for_each_entry_safe(pos, next, &x->task_list, task_list) { + list_for_each_entry_safe(pos, next, &x->head, entry) { if (pos->func == autoremove_wake_function) pos->func(pos, TASK_NORMAL, 0, continuation); else - list_move_tail(&pos->task_list, continuation); + list_move_tail(&pos->entry, continuation); } } else { LIST_HEAD(extra); do { - list_for_each_entry_safe(pos, next, - &x->task_list, task_list) + list_for_each_entry_safe(pos, next, &x->head, entry) pos->func(pos, TASK_NORMAL, 0, &extra); if (list_empty(&extra)) break; - list_splice_tail_init(&extra, &x->task_list); + list_splice_tail_init(&extra, &x->head); } while (1); } spin_unlock_irqrestore(&x->lock, flags); @@ -254,9 +253,9 @@ void i915_sw_fence_commit(struct i915_sw_fence *fence) __i915_sw_fence_commit(fence); } -static int i915_sw_fence_wake(wait_queue_t *wq, unsigned mode, int flags, void *key) +static int i915_sw_fence_wake(wait_queue_entry_t *wq, unsigned mode, int flags, void *key) { - list_del(&wq->task_list); + list_del(&wq->entry); __i915_sw_fence_complete(wq->private, key); i915_sw_fence_put(wq->private); if (wq->flags & I915_SW_FENCE_FLAG_ALLOC) @@ -267,7 +266,7 @@ static int i915_sw_fence_wake(wait_queue_t *wq, unsigned mode, int flags, void * static bool __i915_sw_fence_check_if_after(struct i915_sw_fence *fence, const struct i915_sw_fence * const signaler) { - wait_queue_t *wq; + wait_queue_entry_t *wq; if (__test_and_set_bit(I915_SW_FENCE_CHECKED_BIT, &fence->flags)) return false; @@ -275,7 +274,7 @@ static bool __i915_sw_fence_check_if_after(struct i915_sw_fence *fence, if (fence == signaler) return true; - list_for_each_entry(wq, &fence->wait.task_list, task_list) { + list_for_each_entry(wq, &fence->wait.head, entry) { if (wq->func != i915_sw_fence_wake) continue; @@ -288,12 +287,12 @@ static bool __i915_sw_fence_check_if_after(struct i915_sw_fence *fence, static void __i915_sw_fence_clear_checked_bit(struct i915_sw_fence *fence) { - wait_queue_t *wq; + wait_queue_entry_t *wq; if (!__test_and_clear_bit(I915_SW_FENCE_CHECKED_BIT, &fence->flags)) return; - list_for_each_entry(wq, &fence->wait.task_list, task_list) { + list_for_each_entry(wq, &fence->wait.head, entry) { if (wq->func != i915_sw_fence_wake) continue; @@ -320,7 +319,7 @@ static bool i915_sw_fence_check_if_after(struct i915_sw_fence *fence, static int __i915_sw_fence_await_sw_fence(struct i915_sw_fence *fence, struct i915_sw_fence *signaler, - wait_queue_t *wq, gfp_t gfp) + wait_queue_entry_t *wq, gfp_t gfp) { unsigned long flags; int pending; @@ -350,7 +349,7 @@ static int __i915_sw_fence_await_sw_fence(struct i915_sw_fence *fence, pending |= I915_SW_FENCE_FLAG_ALLOC; } - INIT_LIST_HEAD(&wq->task_list); + INIT_LIST_HEAD(&wq->entry); wq->flags = pending; wq->func = i915_sw_fence_wake; wq->private = i915_sw_fence_get(fence); @@ -359,7 +358,7 @@ static int __i915_sw_fence_await_sw_fence(struct i915_sw_fence *fence, spin_lock_irqsave(&signaler->wait.lock, flags); if (likely(!i915_sw_fence_done(signaler))) { - __add_wait_queue_tail(&signaler->wait, wq); + __add_wait_queue_entry_tail(&signaler->wait, wq); pending = 1; } else { i915_sw_fence_wake(wq, 0, 0, NULL); @@ -372,7 +371,7 @@ static int __i915_sw_fence_await_sw_fence(struct i915_sw_fence *fence, int i915_sw_fence_await_sw_fence(struct i915_sw_fence *fence, struct i915_sw_fence *signaler, - wait_queue_t *wq) + wait_queue_entry_t *wq) { return __i915_sw_fence_await_sw_fence(fence, signaler, wq, 0); } diff --git a/drivers/gpu/drm/i915/i915_sw_fence.h b/drivers/gpu/drm/i915/i915_sw_fence.h index d31cefbbcc04..fd3c3bf6c8b7 100644 --- a/drivers/gpu/drm/i915/i915_sw_fence.h +++ b/drivers/gpu/drm/i915/i915_sw_fence.h @@ -66,7 +66,7 @@ void i915_sw_fence_commit(struct i915_sw_fence *fence); int i915_sw_fence_await_sw_fence(struct i915_sw_fence *fence, struct i915_sw_fence *after, - wait_queue_t *wq); + wait_queue_entry_t *wq); int i915_sw_fence_await_sw_fence_gfp(struct i915_sw_fence *fence, struct i915_sw_fence *after, gfp_t gfp); diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 1aba47024656..f066e2d785f5 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -650,6 +650,11 @@ int i915_vma_unbind(struct i915_vma *vma) break; } + if (!ret) { + ret = i915_gem_active_retire(&vma->last_fence, + &vma->vm->i915->drm.struct_mutex); + } + __i915_vma_unpin(vma); if (ret) return ret; diff --git a/drivers/gpu/drm/i915/intel_acpi.c b/drivers/gpu/drm/i915/intel_acpi.c index eb638a1e69d2..42fb436f6cdc 100644 --- a/drivers/gpu/drm/i915/intel_acpi.c +++ b/drivers/gpu/drm/i915/intel_acpi.c @@ -15,13 +15,9 @@ static struct intel_dsm_priv { acpi_handle dhandle; } intel_dsm_priv; -static const u8 intel_dsm_guid[] = { - 0xd3, 0x73, 0xd8, 0x7e, - 0xd0, 0xc2, - 0x4f, 0x4e, - 0xa8, 0x54, - 0x0f, 0x13, 0x17, 0xb0, 0x1c, 0x2c -}; +static const guid_t intel_dsm_guid = + GUID_INIT(0x7ed873d3, 0xc2d0, 0x4e4f, + 0xa8, 0x54, 0x0f, 0x13, 0x17, 0xb0, 0x1c, 0x2c); static char *intel_dsm_port_name(u8 id) { @@ -80,7 +76,7 @@ static void intel_dsm_platform_mux_info(void) int i; union acpi_object *pkg, *connector_count; - pkg = acpi_evaluate_dsm_typed(intel_dsm_priv.dhandle, intel_dsm_guid, + pkg = acpi_evaluate_dsm_typed(intel_dsm_priv.dhandle, &intel_dsm_guid, INTEL_DSM_REVISION_ID, INTEL_DSM_FN_PLATFORM_MUX_INFO, NULL, ACPI_TYPE_PACKAGE); if (!pkg) { @@ -118,7 +114,7 @@ static bool intel_dsm_pci_probe(struct pci_dev *pdev) if (!dhandle) return false; - if (!acpi_check_dsm(dhandle, intel_dsm_guid, INTEL_DSM_REVISION_ID, + if (!acpi_check_dsm(dhandle, &intel_dsm_guid, INTEL_DSM_REVISION_ID, 1 << INTEL_DSM_FN_PLATFORM_MUX_INFO)) { DRM_DEBUG_KMS("no _DSM method for intel device\n"); return false; diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 96b0b01677e2..9106ea32b048 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -120,7 +120,8 @@ static void intel_crtc_init_scalers(struct intel_crtc *crtc, static void skylake_pfit_enable(struct intel_crtc *crtc); static void ironlake_pfit_disable(struct intel_crtc *crtc, bool force); static void ironlake_pfit_enable(struct intel_crtc *crtc); -static void intel_modeset_setup_hw_state(struct drm_device *dev); +static void intel_modeset_setup_hw_state(struct drm_device *dev, + struct drm_modeset_acquire_ctx *ctx); static void intel_pre_disable_primary_noatomic(struct drm_crtc *crtc); struct intel_limit { @@ -3449,7 +3450,7 @@ __intel_display_resume(struct drm_device *dev, struct drm_crtc *crtc; int i, ret; - intel_modeset_setup_hw_state(dev); + intel_modeset_setup_hw_state(dev, ctx); i915_redisable_vga(to_i915(dev)); if (!state) @@ -5825,7 +5826,8 @@ static void i9xx_crtc_disable(struct intel_crtc_state *old_crtc_state, intel_update_watermarks(intel_crtc); } -static void intel_crtc_disable_noatomic(struct drm_crtc *crtc) +static void intel_crtc_disable_noatomic(struct drm_crtc *crtc, + struct drm_modeset_acquire_ctx *ctx) { struct intel_encoder *encoder; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); @@ -5855,7 +5857,7 @@ static void intel_crtc_disable_noatomic(struct drm_crtc *crtc) return; } - state->acquire_ctx = crtc->dev->mode_config.acquire_ctx; + state->acquire_ctx = ctx; /* Everything's already locked, -EDEADLK can't happen. */ crtc_state = intel_atomic_get_crtc_state(state, intel_crtc); @@ -15030,7 +15032,7 @@ int intel_modeset_init(struct drm_device *dev) intel_setup_outputs(dev_priv); drm_modeset_lock_all(dev); - intel_modeset_setup_hw_state(dev); + intel_modeset_setup_hw_state(dev, dev->mode_config.acquire_ctx); drm_modeset_unlock_all(dev); for_each_intel_crtc(dev, crtc) { @@ -15067,13 +15069,13 @@ int intel_modeset_init(struct drm_device *dev) return 0; } -static void intel_enable_pipe_a(struct drm_device *dev) +static void intel_enable_pipe_a(struct drm_device *dev, + struct drm_modeset_acquire_ctx *ctx) { struct intel_connector *connector; struct drm_connector_list_iter conn_iter; struct drm_connector *crt = NULL; struct intel_load_detect_pipe load_detect_temp; - struct drm_modeset_acquire_ctx *ctx = dev->mode_config.acquire_ctx; int ret; /* We can't just switch on the pipe A, we need to set things up with a @@ -15145,7 +15147,8 @@ static bool has_pch_trancoder(struct drm_i915_private *dev_priv, (HAS_PCH_LPT_H(dev_priv) && pch_transcoder == TRANSCODER_A); } -static void intel_sanitize_crtc(struct intel_crtc *crtc) +static void intel_sanitize_crtc(struct intel_crtc *crtc, + struct drm_modeset_acquire_ctx *ctx) { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = to_i915(dev); @@ -15191,7 +15194,7 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc) plane = crtc->plane; crtc->base.primary->state->visible = true; crtc->plane = !plane; - intel_crtc_disable_noatomic(&crtc->base); + intel_crtc_disable_noatomic(&crtc->base, ctx); crtc->plane = plane; } @@ -15201,13 +15204,13 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc) * resume. Force-enable the pipe to fix this, the update_dpms * call below we restore the pipe to the right state, but leave * the required bits on. */ - intel_enable_pipe_a(dev); + intel_enable_pipe_a(dev, ctx); } /* Adjust the state of the output pipe according to whether we * have active connectors/encoders. */ if (crtc->active && !intel_crtc_has_encoders(crtc)) - intel_crtc_disable_noatomic(&crtc->base); + intel_crtc_disable_noatomic(&crtc->base, ctx); if (crtc->active || HAS_GMCH_DISPLAY(dev_priv)) { /* @@ -15505,7 +15508,8 @@ get_encoder_power_domains(struct drm_i915_private *dev_priv) * and sanitizes it to the current state */ static void -intel_modeset_setup_hw_state(struct drm_device *dev) +intel_modeset_setup_hw_state(struct drm_device *dev, + struct drm_modeset_acquire_ctx *ctx) { struct drm_i915_private *dev_priv = to_i915(dev); enum pipe pipe; @@ -15525,7 +15529,7 @@ intel_modeset_setup_hw_state(struct drm_device *dev) for_each_pipe(dev_priv, pipe) { crtc = intel_get_crtc_for_pipe(dev_priv, pipe); - intel_sanitize_crtc(crtc); + intel_sanitize_crtc(crtc, ctx); intel_dump_pipe_config(crtc, crtc->config, "[setup_hw_state]"); } diff --git a/drivers/gpu/drm/i915/intel_dp_aux_backlight.c b/drivers/gpu/drm/i915/intel_dp_aux_backlight.c index 6532e226db29..40ba3134545e 100644 --- a/drivers/gpu/drm/i915/intel_dp_aux_backlight.c +++ b/drivers/gpu/drm/i915/intel_dp_aux_backlight.c @@ -119,8 +119,6 @@ static int intel_dp_aux_setup_backlight(struct intel_connector *connector, struct intel_dp *intel_dp = enc_to_intel_dp(&connector->encoder->base); struct intel_panel *panel = &connector->panel; - intel_dp_aux_enable_backlight(connector); - if (intel_dp->edp_dpcd[2] & DP_EDP_BACKLIGHT_BRIGHTNESS_BYTE_COUNT) panel->backlight.max = 0xFFFF; else diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index dac4e003c1f3..62f44d3e7c43 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -326,8 +326,7 @@ static u64 execlists_update_context(struct drm_i915_gem_request *rq) rq->ctx->ppgtt ?: rq->i915->mm.aliasing_ppgtt; u32 *reg_state = ce->lrc_reg_state; - assert_ring_tail_valid(rq->ring, rq->tail); - reg_state[CTX_RING_TAIL+1] = rq->tail; + reg_state[CTX_RING_TAIL+1] = intel_ring_set_tail(rq->ring, rq->tail); /* True 32b PPGTT with dynamic page allocation: update PDP * registers and point the unallocated PDPs to scratch page. @@ -2036,8 +2035,7 @@ void intel_lr_context_resume(struct drm_i915_private *dev_priv) ce->state->obj->mm.dirty = true; i915_gem_object_unpin_map(ce->state->obj); - ce->ring->head = ce->ring->tail = 0; - intel_ring_update_space(ce->ring); + intel_ring_reset(ce->ring, 0); } } } diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 66a2b8b83972..513a0f4b469b 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -49,7 +49,7 @@ static int __intel_ring_space(int head, int tail, int size) void intel_ring_update_space(struct intel_ring *ring) { - ring->space = __intel_ring_space(ring->head, ring->tail, ring->size); + ring->space = __intel_ring_space(ring->head, ring->emit, ring->size); } static int @@ -774,8 +774,8 @@ static void i9xx_submit_request(struct drm_i915_gem_request *request) i915_gem_request_submit(request); - assert_ring_tail_valid(request->ring, request->tail); - I915_WRITE_TAIL(request->engine, request->tail); + I915_WRITE_TAIL(request->engine, + intel_ring_set_tail(request->ring, request->tail)); } static void i9xx_emit_breadcrumb(struct drm_i915_gem_request *req, u32 *cs) @@ -1316,11 +1316,23 @@ err: return PTR_ERR(addr); } +void intel_ring_reset(struct intel_ring *ring, u32 tail) +{ + GEM_BUG_ON(!list_empty(&ring->request_list)); + ring->tail = tail; + ring->head = tail; + ring->emit = tail; + intel_ring_update_space(ring); +} + void intel_ring_unpin(struct intel_ring *ring) { GEM_BUG_ON(!ring->vma); GEM_BUG_ON(!ring->vaddr); + /* Discard any unused bytes beyond that submitted to hw. */ + intel_ring_reset(ring, ring->tail); + if (i915_vma_is_map_and_fenceable(ring->vma)) i915_vma_unpin_iomap(ring->vma); else @@ -1562,8 +1574,9 @@ void intel_legacy_submission_resume(struct drm_i915_private *dev_priv) struct intel_engine_cs *engine; enum intel_engine_id id; + /* Restart from the beginning of the rings for convenience */ for_each_engine(engine, dev_priv, id) - engine->buffer->head = engine->buffer->tail; + intel_ring_reset(engine->buffer, 0); } static int ring_request_alloc(struct drm_i915_gem_request *request) @@ -1616,7 +1629,7 @@ static int wait_for_space(struct drm_i915_gem_request *req, int bytes) unsigned space; /* Would completion of this request free enough space? */ - space = __intel_ring_space(target->postfix, ring->tail, + space = __intel_ring_space(target->postfix, ring->emit, ring->size); if (space >= bytes) break; @@ -1641,8 +1654,8 @@ static int wait_for_space(struct drm_i915_gem_request *req, int bytes) u32 *intel_ring_begin(struct drm_i915_gem_request *req, int num_dwords) { struct intel_ring *ring = req->ring; - int remain_actual = ring->size - ring->tail; - int remain_usable = ring->effective_size - ring->tail; + int remain_actual = ring->size - ring->emit; + int remain_usable = ring->effective_size - ring->emit; int bytes = num_dwords * sizeof(u32); int total_bytes, wait_bytes; bool need_wrap = false; @@ -1678,17 +1691,17 @@ u32 *intel_ring_begin(struct drm_i915_gem_request *req, int num_dwords) if (unlikely(need_wrap)) { GEM_BUG_ON(remain_actual > ring->space); - GEM_BUG_ON(ring->tail + remain_actual > ring->size); + GEM_BUG_ON(ring->emit + remain_actual > ring->size); /* Fill the tail with MI_NOOP */ - memset(ring->vaddr + ring->tail, 0, remain_actual); - ring->tail = 0; + memset(ring->vaddr + ring->emit, 0, remain_actual); + ring->emit = 0; ring->space -= remain_actual; } - GEM_BUG_ON(ring->tail > ring->size - bytes); - cs = ring->vaddr + ring->tail; - ring->tail += bytes; + GEM_BUG_ON(ring->emit > ring->size - bytes); + cs = ring->vaddr + ring->emit; + ring->emit += bytes; ring->space -= bytes; GEM_BUG_ON(ring->space < 0); @@ -1699,7 +1712,7 @@ u32 *intel_ring_begin(struct drm_i915_gem_request *req, int num_dwords) int intel_ring_cacheline_align(struct drm_i915_gem_request *req) { int num_dwords = - (req->ring->tail & (CACHELINE_BYTES - 1)) / sizeof(uint32_t); + (req->ring->emit & (CACHELINE_BYTES - 1)) / sizeof(uint32_t); u32 *cs; if (num_dwords == 0) diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index a82a0807f64d..f7144fe09613 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -145,6 +145,7 @@ struct intel_ring { u32 head; u32 tail; + u32 emit; int space; int size; @@ -488,6 +489,8 @@ intel_write_status_page(struct intel_engine_cs *engine, int reg, u32 value) struct intel_ring * intel_engine_create_ring(struct intel_engine_cs *engine, int size); int intel_ring_pin(struct intel_ring *ring, unsigned int offset_bias); +void intel_ring_reset(struct intel_ring *ring, u32 tail); +void intel_ring_update_space(struct intel_ring *ring); void intel_ring_unpin(struct intel_ring *ring); void intel_ring_free(struct intel_ring *ring); @@ -511,7 +514,7 @@ intel_ring_advance(struct drm_i915_gem_request *req, u32 *cs) * reserved for the command packet (i.e. the value passed to * intel_ring_begin()). */ - GEM_BUG_ON((req->ring->vaddr + req->ring->tail) != cs); + GEM_BUG_ON((req->ring->vaddr + req->ring->emit) != cs); } static inline u32 @@ -540,7 +543,19 @@ assert_ring_tail_valid(const struct intel_ring *ring, unsigned int tail) GEM_BUG_ON(tail >= ring->size); } -void intel_ring_update_space(struct intel_ring *ring); +static inline unsigned int +intel_ring_set_tail(struct intel_ring *ring, unsigned int tail) +{ + /* Whilst writes to the tail are strictly order, there is no + * serialisation between readers and the writers. The tail may be + * read by i915_gem_request_retire() just as it is being updated + * by execlists, as although the breadcrumb is complete, the context + * switch hasn't been seen. + */ + assert_ring_tail_valid(ring, tail); + ring->tail = tail; + return tail; +} void intel_engine_init_global_seqno(struct intel_engine_cs *engine, u32 seqno); diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c index 39468c218027..7459ef9943ec 100644 --- a/drivers/gpu/drm/nouveau/nouveau_acpi.c +++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c @@ -60,15 +60,13 @@ bool nouveau_is_v1_dsm(void) { } #ifdef CONFIG_VGA_SWITCHEROO -static const char nouveau_dsm_muid[] = { - 0xA0, 0xA0, 0x95, 0x9D, 0x60, 0x00, 0x48, 0x4D, - 0xB3, 0x4D, 0x7E, 0x5F, 0xEA, 0x12, 0x9F, 0xD4, -}; +static const guid_t nouveau_dsm_muid = + GUID_INIT(0x9D95A0A0, 0x0060, 0x4D48, + 0xB3, 0x4D, 0x7E, 0x5F, 0xEA, 0x12, 0x9F, 0xD4); -static const char nouveau_op_dsm_muid[] = { - 0xF8, 0xD8, 0x86, 0xA4, 0xDA, 0x0B, 0x1B, 0x47, - 0xA7, 0x2B, 0x60, 0x42, 0xA6, 0xB5, 0xBE, 0xE0, -}; +static const guid_t nouveau_op_dsm_muid = + GUID_INIT(0xA486D8F8, 0x0BDA, 0x471B, + 0xA7, 0x2B, 0x60, 0x42, 0xA6, 0xB5, 0xBE, 0xE0); static int nouveau_optimus_dsm(acpi_handle handle, int func, int arg, uint32_t *result) { @@ -86,7 +84,7 @@ static int nouveau_optimus_dsm(acpi_handle handle, int func, int arg, uint32_t * args_buff[i] = (arg >> i * 8) & 0xFF; *result = 0; - obj = acpi_evaluate_dsm_typed(handle, nouveau_op_dsm_muid, 0x00000100, + obj = acpi_evaluate_dsm_typed(handle, &nouveau_op_dsm_muid, 0x00000100, func, &argv4, ACPI_TYPE_BUFFER); if (!obj) { acpi_handle_info(handle, "failed to evaluate _DSM\n"); @@ -138,7 +136,7 @@ static int nouveau_dsm(acpi_handle handle, int func, int arg) .integer.value = arg, }; - obj = acpi_evaluate_dsm_typed(handle, nouveau_dsm_muid, 0x00000102, + obj = acpi_evaluate_dsm_typed(handle, &nouveau_dsm_muid, 0x00000102, func, &argv4, ACPI_TYPE_INTEGER); if (!obj) { acpi_handle_info(handle, "failed to evaluate _DSM\n"); @@ -259,7 +257,7 @@ static void nouveau_dsm_pci_probe(struct pci_dev *pdev, acpi_handle *dhandle_out if (!acpi_has_method(dhandle, "_DSM")) return; - supports_mux = acpi_check_dsm(dhandle, nouveau_dsm_muid, 0x00000102, + supports_mux = acpi_check_dsm(dhandle, &nouveau_dsm_muid, 0x00000102, 1 << NOUVEAU_DSM_POWER); optimus_funcs = nouveau_dsm_get_optimus_functions(dhandle); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mxm/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mxm/base.c index e3e2f5e83815..f44682d62f75 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/mxm/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mxm/base.c @@ -81,10 +81,9 @@ mxm_shadow_dsm(struct nvkm_mxm *mxm, u8 version) { struct nvkm_subdev *subdev = &mxm->subdev; struct nvkm_device *device = subdev->device; - static char muid[] = { - 0x00, 0xA4, 0x04, 0x40, 0x7D, 0x91, 0xF2, 0x4C, - 0xB8, 0x9C, 0x79, 0xB6, 0x2F, 0xD5, 0x56, 0x65 - }; + static guid_t muid = + GUID_INIT(0x4004A400, 0x917D, 0x4CF2, + 0xB8, 0x9C, 0x79, 0xB6, 0x2F, 0xD5, 0x56, 0x65); u32 mxms_args[] = { 0x00000000 }; union acpi_object argv4 = { .buffer.type = ACPI_TYPE_BUFFER, @@ -105,7 +104,7 @@ mxm_shadow_dsm(struct nvkm_mxm *mxm, u8 version) * unless you pass in exactly the version it supports.. */ rev = (version & 0xf0) << 4 | (version & 0x0f); - obj = acpi_evaluate_dsm(handle, muid, rev, 0x00000010, &argv4); + obj = acpi_evaluate_dsm(handle, &muid, rev, 0x00000010, &argv4); if (!obj) { nvkm_debug(subdev, "DSM MXMS failed\n"); return false; diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index c1c8e2208a21..e562a78510ff 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -375,7 +375,7 @@ struct radeon_fence { unsigned ring; bool is_vm_update; - wait_queue_t fence_wake; + wait_queue_entry_t fence_wake; }; int radeon_fence_driver_start_ring(struct radeon_device *rdev, int ring); diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c index 432480ff9d22..3178ba0c537c 100644 --- a/drivers/gpu/drm/radeon/radeon_combios.c +++ b/drivers/gpu/drm/radeon/radeon_combios.c @@ -3393,6 +3393,13 @@ void radeon_combios_asic_init(struct drm_device *dev) rdev->pdev->subsystem_vendor == 0x103c && rdev->pdev->subsystem_device == 0x280a) return; + /* quirk for rs4xx Toshiba Sattellite L20-183 latop to make it resume + * - it hangs on resume inside the dynclk 1 table. + */ + if (rdev->family == CHIP_RS400 && + rdev->pdev->subsystem_vendor == 0x1179 && + rdev->pdev->subsystem_device == 0xff31) + return; /* DYN CLK 1 */ table = combios_get_table_offset(dev, COMBIOS_DYN_CLK_1_TABLE); diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index 6ecf42783d4b..0a6444d72000 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -136,6 +136,10 @@ static struct radeon_px_quirk radeon_px_quirk_list[] = { * https://bugzilla.kernel.org/show_bug.cgi?id=51381 */ { PCI_VENDOR_ID_ATI, 0x6840, 0x1043, 0x2122, RADEON_PX_QUIRK_DISABLE_PX }, + /* Asus K53TK laptop with AMD A6-3420M APU and Radeon 7670m GPU + * https://bugs.freedesktop.org/show_bug.cgi?id=101491 + */ + { PCI_VENDOR_ID_ATI, 0x6741, 0x1043, 0x2122, RADEON_PX_QUIRK_DISABLE_PX }, /* macbook pro 8.2 */ { PCI_VENDOR_ID_ATI, 0x6741, PCI_VENDOR_ID_APPLE, 0x00e2, RADEON_PX_QUIRK_LONG_WAKEUP }, { 0, 0, 0, 0, 0 }, diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c index ef09f0a63754..e86f2bd38410 100644 --- a/drivers/gpu/drm/radeon/radeon_fence.c +++ b/drivers/gpu/drm/radeon/radeon_fence.c @@ -158,7 +158,7 @@ int radeon_fence_emit(struct radeon_device *rdev, * for the fence locking itself, so unlocked variants are used for * fence_signal, and remove_wait_queue. */ -static int radeon_fence_check_signaled(wait_queue_t *wait, unsigned mode, int flags, void *key) +static int radeon_fence_check_signaled(wait_queue_entry_t *wait, unsigned mode, int flags, void *key) { struct radeon_fence *fence; u64 seq; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c index 13db8a2851ed..1f013d45c9e9 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c @@ -321,6 +321,7 @@ void vmw_cmdbuf_res_man_destroy(struct vmw_cmdbuf_res_manager *man) list_for_each_entry_safe(entry, next, &man->list, head) vmw_cmdbuf_res_free(man, entry); + drm_ht_remove(&man->resources); kfree(man); } diff --git a/drivers/gpu/vga/vgaarb.c b/drivers/gpu/vga/vgaarb.c index 92f1452dad57..76875f6299b8 100644 --- a/drivers/gpu/vga/vgaarb.c +++ b/drivers/gpu/vga/vgaarb.c @@ -417,7 +417,7 @@ int vga_get(struct pci_dev *pdev, unsigned int rsrc, int interruptible) { struct vga_device *vgadev, *conflict; unsigned long flags; - wait_queue_t wait; + wait_queue_entry_t wait; int rc = 0; vga_check_first_use(); diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 8ca1e8ce0af2..4f9a3938189a 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -319,6 +319,9 @@ #define USB_VENDOR_ID_DELCOM 0x0fc5 #define USB_DEVICE_ID_DELCOM_VISUAL_IND 0xb080 +#define USB_VENDOR_ID_DELL 0x413c +#define USB_DEVICE_ID_DELL_PIXART_USB_OPTICAL_MOUSE 0x301a + #define USB_VENDOR_ID_DELORME 0x1163 #define USB_DEVICE_ID_DELORME_EARTHMATE 0x0100 #define USB_DEVICE_ID_DELORME_EM_LT20 0x0200 diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c index 1d6c997b3001..20b40ad26325 100644 --- a/drivers/hid/hid-magicmouse.c +++ b/drivers/hid/hid-magicmouse.c @@ -349,7 +349,6 @@ static int magicmouse_raw_event(struct hid_device *hdev, if (input->id.product == USB_DEVICE_ID_APPLE_MAGICMOUSE) { magicmouse_emit_buttons(msc, clicks & 3); - input_mt_report_pointer_emulation(input, true); input_report_rel(input, REL_X, x); input_report_rel(input, REL_Y, y); } else { /* USB_DEVICE_ID_APPLE_MAGICTRACKPAD */ @@ -389,16 +388,16 @@ static int magicmouse_setup_input(struct input_dev *input, struct hid_device *hd __clear_bit(BTN_RIGHT, input->keybit); __clear_bit(BTN_MIDDLE, input->keybit); __set_bit(BTN_MOUSE, input->keybit); + __set_bit(BTN_TOOL_FINGER, input->keybit); + __set_bit(BTN_TOOL_DOUBLETAP, input->keybit); + __set_bit(BTN_TOOL_TRIPLETAP, input->keybit); + __set_bit(BTN_TOOL_QUADTAP, input->keybit); + __set_bit(BTN_TOOL_QUINTTAP, input->keybit); + __set_bit(BTN_TOUCH, input->keybit); + __set_bit(INPUT_PROP_POINTER, input->propbit); __set_bit(INPUT_PROP_BUTTONPAD, input->propbit); } - __set_bit(BTN_TOOL_FINGER, input->keybit); - __set_bit(BTN_TOOL_DOUBLETAP, input->keybit); - __set_bit(BTN_TOOL_TRIPLETAP, input->keybit); - __set_bit(BTN_TOOL_QUADTAP, input->keybit); - __set_bit(BTN_TOOL_QUINTTAP, input->keybit); - __set_bit(BTN_TOUCH, input->keybit); - __set_bit(INPUT_PROP_POINTER, input->propbit); __set_bit(EV_ABS, input->evbit); diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c index fb55fb4c39fc..04015032a35a 100644 --- a/drivers/hid/i2c-hid/i2c-hid.c +++ b/drivers/hid/i2c-hid/i2c-hid.c @@ -872,10 +872,9 @@ static int i2c_hid_fetch_hid_descriptor(struct i2c_hid *ihid) static int i2c_hid_acpi_pdata(struct i2c_client *client, struct i2c_hid_platform_data *pdata) { - static u8 i2c_hid_guid[] = { - 0xF7, 0xF6, 0xDF, 0x3C, 0x67, 0x42, 0x55, 0x45, - 0xAD, 0x05, 0xB3, 0x0A, 0x3D, 0x89, 0x38, 0xDE, - }; + static guid_t i2c_hid_guid = + GUID_INIT(0x3CDFF6F7, 0x4267, 0x4555, + 0xAD, 0x05, 0xB3, 0x0A, 0x3D, 0x89, 0x38, 0xDE); union acpi_object *obj; struct acpi_device *adev; acpi_handle handle; @@ -884,7 +883,7 @@ static int i2c_hid_acpi_pdata(struct i2c_client *client, if (!handle || acpi_bus_get_device(handle, &adev)) return -ENODEV; - obj = acpi_evaluate_dsm_typed(handle, i2c_hid_guid, 1, 1, NULL, + obj = acpi_evaluate_dsm_typed(handle, &i2c_hid_guid, 1, 1, NULL, ACPI_TYPE_INTEGER); if (!obj) { dev_err(&client->dev, "device _DSM execution failed\n"); diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c index 6316498b7812..a88e7c7bea0a 100644 --- a/drivers/hid/usbhid/hid-quirks.c +++ b/drivers/hid/usbhid/hid-quirks.c @@ -85,6 +85,7 @@ static const struct hid_blacklist { { USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K65RGB_RAPIDFIRE, HID_QUIRK_NO_INIT_REPORTS | HID_QUIRK_ALWAYS_POLL }, { USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_SCIMITAR_PRO_RGB, HID_QUIRK_NO_INIT_REPORTS | HID_QUIRK_ALWAYS_POLL }, { USB_VENDOR_ID_CREATIVELABS, USB_DEVICE_ID_CREATIVE_SB_OMNI_SURROUND_51, HID_QUIRK_NOGET }, + { USB_VENDOR_ID_DELL, USB_DEVICE_ID_DELL_PIXART_USB_OPTICAL_MOUSE, HID_QUIRK_ALWAYS_POLL }, { USB_VENDOR_ID_DMI, USB_DEVICE_ID_DMI_ENC, HID_QUIRK_NOGET }, { USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_WIIU, HID_QUIRK_MULTI_INPUT }, { USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_PS3, HID_QUIRK_MULTI_INPUT }, diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index 95ed17183e73..54a47b40546f 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -734,9 +734,9 @@ static int i2c_imx_dma_read(struct imx_i2c_struct *i2c_imx, * the first read operation, otherwise the first read cost * one extra clock cycle. */ - temp = readb(i2c_imx->base + IMX_I2C_I2CR); + temp = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2CR); temp |= I2CR_MTX; - writeb(temp, i2c_imx->base + IMX_I2C_I2CR); + imx_i2c_write_reg(temp, i2c_imx, IMX_I2C_I2CR); } msgs->buf[msgs->len-1] = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2DR); @@ -857,9 +857,9 @@ static int i2c_imx_read(struct imx_i2c_struct *i2c_imx, struct i2c_msg *msgs, bo * the first read operation, otherwise the first read cost * one extra clock cycle. */ - temp = readb(i2c_imx->base + IMX_I2C_I2CR); + temp = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2CR); temp |= I2CR_MTX; - writeb(temp, i2c_imx->base + IMX_I2C_I2CR); + imx_i2c_write_reg(temp, i2c_imx, IMX_I2C_I2CR); } } else if (i == (msgs->len - 2)) { dev_dbg(&i2c_imx->adapter.dev, diff --git a/drivers/ide/ide-atapi.c b/drivers/ide/ide-atapi.c index 5901937284e7..14d1e7d9a1d6 100644 --- a/drivers/ide/ide-atapi.c +++ b/drivers/ide/ide-atapi.c @@ -93,7 +93,6 @@ int ide_queue_pc_tail(ide_drive_t *drive, struct gendisk *disk, int error; rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM); - scsi_req_init(rq); ide_req(rq)->type = ATA_PRIV_MISC; rq->special = (char *)pc; @@ -200,7 +199,7 @@ void ide_prep_sense(ide_drive_t *drive, struct request *rq) memset(sense, 0, sizeof(*sense)); blk_rq_init(rq->q, sense_rq); - scsi_req_init(sense_rq); + scsi_req_init(req); err = blk_rq_map_kern(drive->queue, sense_rq, sense, sense_len, GFP_NOIO); @@ -273,7 +272,7 @@ void ide_retry_pc(ide_drive_t *drive) ide_requeue_and_plug(drive, failed_rq); if (ide_queue_sense_rq(drive, pc)) { blk_start_request(failed_rq); - ide_complete_rq(drive, -EIO, blk_rq_bytes(failed_rq)); + ide_complete_rq(drive, BLK_STS_IOERR, blk_rq_bytes(failed_rq)); } } EXPORT_SYMBOL_GPL(ide_retry_pc); @@ -437,7 +436,8 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive) /* No more interrupts */ if ((stat & ATA_DRQ) == 0) { - int uptodate, error; + int uptodate; + blk_status_t error; debug_log("Packet command completed, %d bytes transferred\n", blk_rq_bytes(rq)); @@ -490,7 +490,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive) if (ata_misc_request(rq)) { scsi_req(rq)->result = 0; - error = 0; + error = BLK_STS_OK; } else { if (blk_rq_is_passthrough(rq) && uptodate <= 0) { @@ -498,7 +498,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive) scsi_req(rq)->result = -EIO; } - error = uptodate ? 0 : -EIO; + error = uptodate ? BLK_STS_OK : BLK_STS_IOERR; } ide_complete_rq(drive, error, blk_rq_bytes(rq)); diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c index 07e5ff3a64c3..81e18f9628d0 100644 --- a/drivers/ide/ide-cd.c +++ b/drivers/ide/ide-cd.c @@ -228,7 +228,7 @@ static void ide_cd_complete_failed_rq(ide_drive_t *drive, struct request *rq) scsi_req(failed)->sense_len = scsi_req(rq)->sense_len; cdrom_analyze_sense_data(drive, failed); - if (ide_end_rq(drive, failed, -EIO, blk_rq_bytes(failed))) + if (ide_end_rq(drive, failed, BLK_STS_IOERR, blk_rq_bytes(failed))) BUG(); } else cdrom_analyze_sense_data(drive, NULL); @@ -438,7 +438,6 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd, rq = blk_get_request(drive->queue, write ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, __GFP_RECLAIM); - scsi_req_init(rq); memcpy(scsi_req(rq)->cmd, cmd, BLK_MAX_CDB); ide_req(rq)->type = ATA_PRIV_PC; rq->rq_flags |= rq_flags; @@ -508,7 +507,7 @@ static bool ide_cd_error_cmd(ide_drive_t *drive, struct ide_cmd *cmd) nr_bytes -= cmd->last_xfer_len; if (nr_bytes > 0) { - ide_complete_rq(drive, 0, nr_bytes); + ide_complete_rq(drive, BLK_STS_OK, nr_bytes); return true; } @@ -674,7 +673,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive) out_end: if (blk_rq_is_scsi(rq) && rc == 0) { scsi_req(rq)->resid_len = 0; - blk_end_request_all(rq, 0); + blk_end_request_all(rq, BLK_STS_OK); hwif->rq = NULL; } else { if (sense && uptodate) @@ -699,7 +698,7 @@ out_end: scsi_req(rq)->resid_len += cmd->last_xfer_len; } - ide_complete_rq(drive, uptodate ? 0 : -EIO, blk_rq_bytes(rq)); + ide_complete_rq(drive, uptodate ? BLK_STS_OK : BLK_STS_IOERR, blk_rq_bytes(rq)); if (sense && rc == 2) ide_error(drive, "request sense failure", stat); @@ -844,7 +843,7 @@ out_end: if (nsectors == 0) nsectors = 1; - ide_complete_rq(drive, uptodate ? 0 : -EIO, nsectors << 9); + ide_complete_rq(drive, uptodate ? BLK_STS_OK : BLK_STS_IOERR, nsectors << 9); return ide_stopped; } diff --git a/drivers/ide/ide-cd_ioctl.c b/drivers/ide/ide-cd_ioctl.c index 55cd736c39c6..9d26c9737e21 100644 --- a/drivers/ide/ide-cd_ioctl.c +++ b/drivers/ide/ide-cd_ioctl.c @@ -304,7 +304,6 @@ int ide_cdrom_reset(struct cdrom_device_info *cdi) int ret; rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM); - scsi_req_init(rq); ide_req(rq)->type = ATA_PRIV_MISC; rq->rq_flags = RQF_QUIET; blk_execute_rq(drive->queue, cd->disk, rq, 0); diff --git a/drivers/ide/ide-devsets.c b/drivers/ide/ide-devsets.c index 9b69c32ee560..ef7c8c43a380 100644 --- a/drivers/ide/ide-devsets.c +++ b/drivers/ide/ide-devsets.c @@ -166,7 +166,6 @@ int ide_devset_execute(ide_drive_t *drive, const struct ide_devset *setting, return setting->set(drive, arg); rq = blk_get_request(q, REQ_OP_DRV_IN, __GFP_RECLAIM); - scsi_req_init(rq); ide_req(rq)->type = ATA_PRIV_MISC; scsi_req(rq)->cmd_len = 5; scsi_req(rq)->cmd[0] = REQ_DEVSET_EXEC; diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c index 7c06237f3479..241983da5fc4 100644 --- a/drivers/ide/ide-disk.c +++ b/drivers/ide/ide-disk.c @@ -478,7 +478,6 @@ static int set_multcount(ide_drive_t *drive, int arg) return -EBUSY; rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM); - scsi_req_init(rq); ide_req(rq)->type = ATA_PRIV_TASKFILE; drive->mult_req = arg; diff --git a/drivers/ide/ide-dma.c b/drivers/ide/ide-dma.c index 51c81223e56d..54d4d78ca46a 100644 --- a/drivers/ide/ide-dma.c +++ b/drivers/ide/ide-dma.c @@ -104,7 +104,7 @@ ide_startstop_t ide_dma_intr(ide_drive_t *drive) if ((cmd->tf_flags & IDE_TFLAG_FS) == 0) ide_finish_cmd(drive, cmd, stat); else - ide_complete_rq(drive, 0, + ide_complete_rq(drive, BLK_STS_OK, blk_rq_sectors(cmd->rq) << 9); return ide_stopped; } diff --git a/drivers/ide/ide-eh.c b/drivers/ide/ide-eh.c index 4b7ffd7d158d..47d5f3379748 100644 --- a/drivers/ide/ide-eh.c +++ b/drivers/ide/ide-eh.c @@ -135,7 +135,7 @@ ide_startstop_t ide_error(ide_drive_t *drive, const char *msg, u8 stat) return ide_stopped; } scsi_req(rq)->result = err; - ide_complete_rq(drive, err ? -EIO : 0, blk_rq_bytes(rq)); + ide_complete_rq(drive, err ? BLK_STS_IOERR : BLK_STS_OK, blk_rq_bytes(rq)); return ide_stopped; } @@ -143,7 +143,7 @@ ide_startstop_t ide_error(ide_drive_t *drive, const char *msg, u8 stat) } EXPORT_SYMBOL_GPL(ide_error); -static inline void ide_complete_drive_reset(ide_drive_t *drive, int err) +static inline void ide_complete_drive_reset(ide_drive_t *drive, blk_status_t err) { struct request *rq = drive->hwif->rq; @@ -151,7 +151,7 @@ static inline void ide_complete_drive_reset(ide_drive_t *drive, int err) scsi_req(rq)->cmd[0] == REQ_DRIVE_RESET) { if (err <= 0 && scsi_req(rq)->result == 0) scsi_req(rq)->result = -EIO; - ide_complete_rq(drive, err ? err : 0, blk_rq_bytes(rq)); + ide_complete_rq(drive, err, blk_rq_bytes(rq)); } } @@ -191,7 +191,7 @@ static ide_startstop_t atapi_reset_pollfunc(ide_drive_t *drive) } /* done polling */ hwif->polling = 0; - ide_complete_drive_reset(drive, 0); + ide_complete_drive_reset(drive, BLK_STS_OK); return ide_stopped; } @@ -225,7 +225,7 @@ static ide_startstop_t reset_pollfunc(ide_drive_t *drive) ide_hwif_t *hwif = drive->hwif; const struct ide_port_ops *port_ops = hwif->port_ops; u8 tmp; - int err = 0; + blk_status_t err = BLK_STS_OK; if (port_ops && port_ops->reset_poll) { err = port_ops->reset_poll(drive); @@ -247,7 +247,7 @@ static ide_startstop_t reset_pollfunc(ide_drive_t *drive) printk(KERN_ERR "%s: reset timed-out, status=0x%02x\n", hwif->name, tmp); drive->failures++; - err = -EIO; + err = BLK_STS_IOERR; } else { tmp = ide_read_error(drive); @@ -257,7 +257,7 @@ static ide_startstop_t reset_pollfunc(ide_drive_t *drive) } else { ide_reset_report_error(hwif, tmp); drive->failures++; - err = -EIO; + err = BLK_STS_IOERR; } } out: @@ -392,7 +392,7 @@ static ide_startstop_t do_reset1(ide_drive_t *drive, int do_not_try_atapi) if (io_ports->ctl_addr == 0) { spin_unlock_irqrestore(&hwif->lock, flags); - ide_complete_drive_reset(drive, -ENXIO); + ide_complete_drive_reset(drive, BLK_STS_IOERR); return ide_stopped; } diff --git a/drivers/ide/ide-floppy.c b/drivers/ide/ide-floppy.c index 8ac6048cd2df..627b1f62a749 100644 --- a/drivers/ide/ide-floppy.c +++ b/drivers/ide/ide-floppy.c @@ -143,7 +143,7 @@ static ide_startstop_t ide_floppy_issue_pc(ide_drive_t *drive, drive->failed_pc = NULL; drive->pc_callback(drive, 0); - ide_complete_rq(drive, -EIO, done); + ide_complete_rq(drive, BLK_STS_IOERR, done); return ide_stopped; } @@ -248,7 +248,7 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive, if (ata_misc_request(rq)) { scsi_req(rq)->result = 0; - ide_complete_rq(drive, 0, blk_rq_bytes(rq)); + ide_complete_rq(drive, BLK_STS_OK, blk_rq_bytes(rq)); return ide_stopped; } else goto out_end; @@ -303,7 +303,7 @@ out_end: drive->failed_pc = NULL; if (blk_rq_is_passthrough(rq) && scsi_req(rq)->result == 0) scsi_req(rq)->result = -EIO; - ide_complete_rq(drive, -EIO, blk_rq_bytes(rq)); + ide_complete_rq(drive, BLK_STS_IOERR, blk_rq_bytes(rq)); return ide_stopped; } diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c index 323af721f8cb..3a234701d92c 100644 --- a/drivers/ide/ide-io.c +++ b/drivers/ide/ide-io.c @@ -54,7 +54,7 @@ #include <linux/uaccess.h> #include <asm/io.h> -int ide_end_rq(ide_drive_t *drive, struct request *rq, int error, +int ide_end_rq(ide_drive_t *drive, struct request *rq, blk_status_t error, unsigned int nr_bytes) { /* @@ -112,7 +112,7 @@ void ide_complete_cmd(ide_drive_t *drive, struct ide_cmd *cmd, u8 stat, u8 err) } } -int ide_complete_rq(ide_drive_t *drive, int error, unsigned int nr_bytes) +int ide_complete_rq(ide_drive_t *drive, blk_status_t error, unsigned int nr_bytes) { ide_hwif_t *hwif = drive->hwif; struct request *rq = hwif->rq; @@ -122,7 +122,7 @@ int ide_complete_rq(ide_drive_t *drive, int error, unsigned int nr_bytes) * if failfast is set on a request, override number of sectors * and complete the whole request right now */ - if (blk_noretry_request(rq) && error <= 0) + if (blk_noretry_request(rq) && error) nr_bytes = blk_rq_sectors(rq) << 9; rc = ide_end_rq(drive, rq, error, nr_bytes); @@ -149,7 +149,7 @@ void ide_kill_rq(ide_drive_t *drive, struct request *rq) scsi_req(rq)->result = -EIO; } - ide_complete_rq(drive, -EIO, blk_rq_bytes(rq)); + ide_complete_rq(drive, BLK_STS_IOERR, blk_rq_bytes(rq)); } static void ide_tf_set_specify_cmd(ide_drive_t *drive, struct ide_taskfile *tf) @@ -272,7 +272,7 @@ static ide_startstop_t execute_drive_cmd (ide_drive_t *drive, printk("%s: DRIVE_CMD (null)\n", drive->name); #endif scsi_req(rq)->result = 0; - ide_complete_rq(drive, 0, blk_rq_bytes(rq)); + ide_complete_rq(drive, BLK_STS_OK, blk_rq_bytes(rq)); return ide_stopped; } diff --git a/drivers/ide/ide-ioctls.c b/drivers/ide/ide-ioctls.c index 8c0d17297a7a..3661abb16a5f 100644 --- a/drivers/ide/ide-ioctls.c +++ b/drivers/ide/ide-ioctls.c @@ -126,7 +126,6 @@ static int ide_cmd_ioctl(ide_drive_t *drive, unsigned long arg) struct request *rq; rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM); - scsi_req_init(rq); ide_req(rq)->type = ATA_PRIV_TASKFILE; blk_execute_rq(drive->queue, NULL, rq, 0); err = scsi_req(rq)->result ? -EIO : 0; @@ -224,7 +223,6 @@ static int generic_drive_reset(ide_drive_t *drive) int ret = 0; rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM); - scsi_req_init(rq); ide_req(rq)->type = ATA_PRIV_MISC; scsi_req(rq)->cmd_len = 1; scsi_req(rq)->cmd[0] = REQ_DRIVE_RESET; diff --git a/drivers/ide/ide-park.c b/drivers/ide/ide-park.c index 94e3107f59b9..1f264d5d3f3f 100644 --- a/drivers/ide/ide-park.c +++ b/drivers/ide/ide-park.c @@ -32,7 +32,6 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout) spin_unlock_irq(&hwif->lock); rq = blk_get_request(q, REQ_OP_DRV_IN, __GFP_RECLAIM); - scsi_req_init(rq); scsi_req(rq)->cmd[0] = REQ_PARK_HEADS; scsi_req(rq)->cmd_len = 1; ide_req(rq)->type = ATA_PRIV_MISC; @@ -48,7 +47,6 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout) * timeout has expired, so power management will be reenabled. */ rq = blk_get_request(q, REQ_OP_DRV_IN, GFP_NOWAIT); - scsi_req_init(rq); if (IS_ERR(rq)) goto out; diff --git a/drivers/ide/ide-pm.c b/drivers/ide/ide-pm.c index 0977fc1f40ce..544f02d673ca 100644 --- a/drivers/ide/ide-pm.c +++ b/drivers/ide/ide-pm.c @@ -19,7 +19,6 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg) memset(&rqpm, 0, sizeof(rqpm)); rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM); - scsi_req_init(rq); ide_req(rq)->type = ATA_PRIV_PM_SUSPEND; rq->special = &rqpm; rqpm.pm_step = IDE_PM_START_SUSPEND; @@ -40,7 +39,7 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg) return ret; } -static void ide_end_sync_rq(struct request *rq, int error) +static void ide_end_sync_rq(struct request *rq, blk_status_t error) { complete(rq->end_io_data); } @@ -57,7 +56,7 @@ static int ide_pm_execute_rq(struct request *rq) if (unlikely(blk_queue_dying(q))) { rq->rq_flags |= RQF_QUIET; scsi_req(rq)->result = -ENXIO; - __blk_end_request_all(rq, 0); + __blk_end_request_all(rq, BLK_STS_OK); spin_unlock_irq(q->queue_lock); return -ENXIO; } @@ -91,7 +90,6 @@ int generic_ide_resume(struct device *dev) memset(&rqpm, 0, sizeof(rqpm)); rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM); - scsi_req_init(rq); ide_req(rq)->type = ATA_PRIV_PM_RESUME; rq->rq_flags |= RQF_PREEMPT; rq->special = &rqpm; @@ -235,7 +233,7 @@ void ide_complete_pm_rq(ide_drive_t *drive, struct request *rq) drive->hwif->rq = NULL; - if (blk_end_request(rq, 0, 0)) + if (blk_end_request(rq, BLK_STS_OK, 0)) BUG(); } diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c index 023562565d11..01b2adfd8226 100644 --- a/drivers/ide/ide-probe.c +++ b/drivers/ide/ide-probe.c @@ -741,12 +741,12 @@ static void ide_port_tune_devices(ide_hwif_t *hwif) } } -static int ide_init_rq(struct request_queue *q, struct request *rq, gfp_t gfp) +static void ide_initialize_rq(struct request *rq) { struct ide_request *req = blk_mq_rq_to_pdu(rq); + scsi_req_init(&req->sreq); req->sreq.sense = req->sense; - return 0; } /* @@ -771,8 +771,9 @@ static int ide_init_queue(ide_drive_t *drive) return 1; q->request_fn = do_ide_request; - q->init_rq_fn = ide_init_rq; + q->initialize_rq_fn = ide_initialize_rq; q->cmd_size = sizeof(struct ide_request); + queue_flag_set_unlocked(QUEUE_FLAG_SCSI_PASSTHROUGH, q); if (blk_init_allocated_queue(q) < 0) { blk_cleanup_queue(q); return 1; diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c index a0651f948b76..fd57e8ccc47a 100644 --- a/drivers/ide/ide-tape.c +++ b/drivers/ide/ide-tape.c @@ -474,7 +474,7 @@ static ide_startstop_t ide_tape_issue_pc(ide_drive_t *drive, drive->failed_pc = NULL; drive->pc_callback(drive, 0); - ide_complete_rq(drive, -EIO, blk_rq_bytes(rq)); + ide_complete_rq(drive, BLK_STS_IOERR, blk_rq_bytes(rq)); return ide_stopped; } ide_debug_log(IDE_DBG_SENSE, "retry #%d, cmd: 0x%02x", pc->retries, @@ -855,7 +855,6 @@ static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int size) BUG_ON(size < 0 || size % tape->blk_size); rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM); - scsi_req_init(rq); ide_req(rq)->type = ATA_PRIV_MISC; scsi_req(rq)->cmd[13] = cmd; rq->rq_disk = tape->disk; diff --git a/drivers/ide/ide-taskfile.c b/drivers/ide/ide-taskfile.c index d71199d23c9e..4efe4c6e956c 100644 --- a/drivers/ide/ide-taskfile.c +++ b/drivers/ide/ide-taskfile.c @@ -318,7 +318,7 @@ static void ide_error_cmd(ide_drive_t *drive, struct ide_cmd *cmd) } if (nr_bytes > 0) - ide_complete_rq(drive, 0, nr_bytes); + ide_complete_rq(drive, BLK_STS_OK, nr_bytes); } } @@ -336,7 +336,7 @@ void ide_finish_cmd(ide_drive_t *drive, struct ide_cmd *cmd, u8 stat) ide_driveid_update(drive); } - ide_complete_rq(drive, err ? -EIO : 0, blk_rq_bytes(rq)); + ide_complete_rq(drive, err ? BLK_STS_IOERR : BLK_STS_OK, blk_rq_bytes(rq)); } /* @@ -394,7 +394,7 @@ out_end: if ((cmd->tf_flags & IDE_TFLAG_FS) == 0) ide_finish_cmd(drive, cmd, stat); else - ide_complete_rq(drive, 0, blk_rq_sectors(cmd->rq) << 9); + ide_complete_rq(drive, BLK_STS_OK, blk_rq_sectors(cmd->rq) << 9); return ide_stopped; out_err: ide_error_cmd(drive, cmd); @@ -433,7 +433,6 @@ int ide_raw_taskfile(ide_drive_t *drive, struct ide_cmd *cmd, u8 *buf, rq = blk_get_request(drive->queue, (cmd->tf_flags & IDE_TFLAG_WRITE) ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, __GFP_RECLAIM); - scsi_req_init(rq); ide_req(rq)->type = ATA_PRIV_TASKFILE; /* diff --git a/drivers/ide/siimage.c b/drivers/ide/siimage.c index 6a1849bb476c..57eea5a9047f 100644 --- a/drivers/ide/siimage.c +++ b/drivers/ide/siimage.c @@ -406,7 +406,7 @@ static int siimage_dma_test_irq(ide_drive_t *drive) * yet. */ -static int sil_sata_reset_poll(ide_drive_t *drive) +static blk_status_t sil_sata_reset_poll(ide_drive_t *drive) { ide_hwif_t *hwif = drive->hwif; void __iomem *sata_status_addr @@ -419,11 +419,11 @@ static int sil_sata_reset_poll(ide_drive_t *drive) if ((sata_stat & 0x03) != 0x03) { printk(KERN_WARNING "%s: reset phy dead, status=0x%08x\n", hwif->name, sata_stat); - return -ENXIO; + return BLK_STS_IOERR; } } - return 0; + return BLK_STS_OK; } /** diff --git a/drivers/infiniband/hw/i40iw/i40iw_main.c b/drivers/infiniband/hw/i40iw/i40iw_main.c index a3f18a22f5ed..e0f47cc2effc 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_main.c +++ b/drivers/infiniband/hw/i40iw/i40iw_main.c @@ -1939,7 +1939,7 @@ static int i40iw_virtchnl_receive(struct i40e_info *ldev, bool i40iw_vf_clear_to_send(struct i40iw_sc_dev *dev) { struct i40iw_device *iwdev; - wait_queue_t wait; + wait_queue_entry_t wait; iwdev = dev->back_dev; diff --git a/drivers/input/misc/soc_button_array.c b/drivers/input/misc/soc_button_array.c index e37d37273182..f600f3a7a3c6 100644 --- a/drivers/input/misc/soc_button_array.c +++ b/drivers/input/misc/soc_button_array.c @@ -248,7 +248,8 @@ static struct soc_button_info *soc_button_get_button_info(struct device *dev) if (!btns_desc) { dev_err(dev, "ACPI Button Descriptors not found\n"); - return ERR_PTR(-ENODEV); + button_info = ERR_PTR(-ENODEV); + goto out; } /* The first package describes the collection */ @@ -264,24 +265,31 @@ static struct soc_button_info *soc_button_get_button_info(struct device *dev) } if (collection_uid == -1) { dev_err(dev, "Invalid Button Collection Descriptor\n"); - return ERR_PTR(-ENODEV); + button_info = ERR_PTR(-ENODEV); + goto out; } /* There are package.count - 1 buttons + 1 terminating empty entry */ button_info = devm_kcalloc(dev, btns_desc->package.count, sizeof(*button_info), GFP_KERNEL); - if (!button_info) - return ERR_PTR(-ENOMEM); + if (!button_info) { + button_info = ERR_PTR(-ENOMEM); + goto out; + } /* Parse the button descriptors */ for (i = 1, btn = 0; i < btns_desc->package.count; i++, btn++) { if (soc_button_parse_btn_desc(dev, &btns_desc->package.elements[i], collection_uid, - &button_info[btn])) - return ERR_PTR(-ENODEV); + &button_info[btn])) { + button_info = ERR_PTR(-ENODEV); + goto out; + } } +out: + kfree(buf.pointer); return button_info; } diff --git a/drivers/input/rmi4/rmi_f54.c b/drivers/input/rmi4/rmi_f54.c index dea63e2db3e6..f5206e2c767e 100644 --- a/drivers/input/rmi4/rmi_f54.c +++ b/drivers/input/rmi4/rmi_f54.c @@ -31,9 +31,6 @@ #define F54_GET_REPORT 1 #define F54_FORCE_CAL 2 -/* Fixed sizes of reports */ -#define F54_QUERY_LEN 27 - /* F54 capabilities */ #define F54_CAP_BASELINE (1 << 2) #define F54_CAP_IMAGE8 (1 << 3) @@ -95,7 +92,6 @@ struct rmi_f54_reports { struct f54_data { struct rmi_function *fn; - u8 qry[F54_QUERY_LEN]; u8 num_rx_electrodes; u8 num_tx_electrodes; u8 capabilities; @@ -632,22 +628,23 @@ static int rmi_f54_detect(struct rmi_function *fn) { int error; struct f54_data *f54; + u8 buf[6]; f54 = dev_get_drvdata(&fn->dev); error = rmi_read_block(fn->rmi_dev, fn->fd.query_base_addr, - &f54->qry, sizeof(f54->qry)); + buf, sizeof(buf)); if (error) { dev_err(&fn->dev, "%s: Failed to query F54 properties\n", __func__); return error; } - f54->num_rx_electrodes = f54->qry[0]; - f54->num_tx_electrodes = f54->qry[1]; - f54->capabilities = f54->qry[2]; - f54->clock_rate = f54->qry[3] | (f54->qry[4] << 8); - f54->family = f54->qry[5]; + f54->num_rx_electrodes = buf[0]; + f54->num_tx_electrodes = buf[1]; + f54->capabilities = buf[2]; + f54->clock_rate = buf[3] | (buf[4] << 8); + f54->family = buf[5]; rmi_dbg(RMI_DEBUG_FN, &fn->dev, "F54 num_rx_electrodes: %d\n", f54->num_rx_electrodes); diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index 09720d950686..f932a83b4990 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -723,6 +723,13 @@ static const struct dmi_system_id __initconst i8042_dmi_notimeout_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK U574"), }, }, + { + /* Fujitsu UH554 laptop */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK UH544"), + }, + }, { } }; diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 63cacf5d6cf2..0f1219fa8561 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -3879,11 +3879,9 @@ static void irte_ga_prepare(void *entry, u8 vector, u32 dest_apicid, int devid) { struct irte_ga *irte = (struct irte_ga *) entry; - struct iommu_dev_data *dev_data = search_dev_data(devid); irte->lo.val = 0; irte->hi.val = 0; - irte->lo.fields_remap.guest_mode = dev_data ? dev_data->use_vapic : 0; irte->lo.fields_remap.int_type = delivery_mode; irte->lo.fields_remap.dm = dest_mode; irte->hi.fields.vector = vector; @@ -3939,10 +3937,10 @@ static void irte_ga_set_affinity(void *entry, u16 devid, u16 index, struct irte_ga *irte = (struct irte_ga *) entry; struct iommu_dev_data *dev_data = search_dev_data(devid); - if (!dev_data || !dev_data->use_vapic) { + if (!dev_data || !dev_data->use_vapic || + !irte->lo.fields_remap.guest_mode) { irte->hi.fields.vector = vector; irte->lo.fields_remap.destination = dest_apicid; - irte->lo.fields_remap.guest_mode = 0; modify_irte_ga(devid, index, irte, NULL); } } diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index cbf7763d8091..c8b0329c85d2 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -1808,10 +1808,9 @@ IOMMU_INIT_POST(detect_intel_iommu); * for Directed-IO Architecture Specifiction, Rev 2.2, Section 8.8 * "Remapping Hardware Unit Hot Plug". */ -static u8 dmar_hp_uuid[] = { - /* 0000 */ 0xA6, 0xA3, 0xC1, 0xD8, 0x9B, 0xBE, 0x9B, 0x4C, - /* 0008 */ 0x91, 0xBF, 0xC3, 0xCB, 0x81, 0xFC, 0x5D, 0xAF -}; +static guid_t dmar_hp_guid = + GUID_INIT(0xD8C1A3A6, 0xBE9B, 0x4C9B, + 0x91, 0xBF, 0xC3, 0xCB, 0x81, 0xFC, 0x5D, 0xAF); /* * Currently there's only one revision and BIOS will not check the revision id, @@ -1824,7 +1823,7 @@ static u8 dmar_hp_uuid[] = { static inline bool dmar_detect_dsm(acpi_handle handle, int func) { - return acpi_check_dsm(handle, dmar_hp_uuid, DMAR_DSM_REV_ID, 1 << func); + return acpi_check_dsm(handle, &dmar_hp_guid, DMAR_DSM_REV_ID, 1 << func); } static int dmar_walk_dsm_resource(acpi_handle handle, int func, @@ -1843,7 +1842,7 @@ static int dmar_walk_dsm_resource(acpi_handle handle, int func, if (!dmar_detect_dsm(handle, func)) return 0; - obj = acpi_evaluate_dsm_typed(handle, dmar_hp_uuid, DMAR_DSM_REV_ID, + obj = acpi_evaluate_dsm_typed(handle, &dmar_hp_guid, DMAR_DSM_REV_ID, func, NULL, ACPI_TYPE_BUFFER); if (!obj) return -ENODEV; diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index fc2765ccdb57..8500deda9175 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -4315,7 +4315,7 @@ int dmar_parse_one_atsr(struct acpi_dmar_header *hdr, void *arg) struct acpi_dmar_atsr *atsr; struct dmar_atsr_unit *atsru; - if (system_state != SYSTEM_BOOTING && !intel_iommu_enabled) + if (system_state >= SYSTEM_RUNNING && !intel_iommu_enabled) return 0; atsr = container_of(hdr, struct acpi_dmar_atsr, header); @@ -4565,7 +4565,7 @@ int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info) struct acpi_dmar_atsr *atsr; struct acpi_dmar_reserved_memory *rmrr; - if (!intel_iommu_enabled && system_state != SYSTEM_BOOTING) + if (!intel_iommu_enabled && system_state >= SYSTEM_RUNNING) return 0; list_for_each_entry(rmrru, &dmar_rmrr_units, list) { diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c index 19779b88a479..8cb60829a7a1 100644 --- a/drivers/iommu/of_iommu.c +++ b/drivers/iommu/of_iommu.c @@ -103,7 +103,7 @@ static bool of_iommu_driver_present(struct device_node *np) * it never will be. We don't want to defer indefinitely, nor attempt * to dereference __iommu_of_table after it's been freed. */ - if (system_state > SYSTEM_BOOTING) + if (system_state >= SYSTEM_RUNNING) return false; return of_match_node(&__iommu_of_table, np); diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index eb7fbe159963..929f8558bf1c 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -140,7 +140,7 @@ static inline void gic_map_to_vpe(unsigned int intr, unsigned int vpe) } #ifdef CONFIG_CLKSRC_MIPS_GIC -u64 gic_read_count(void) +u64 notrace gic_read_count(void) { unsigned int hi, hi2, lo; @@ -167,7 +167,7 @@ unsigned int gic_get_count_width(void) return bits; } -void gic_write_compare(u64 cnt) +void notrace gic_write_compare(u64 cnt) { if (mips_cm_is64) { gic_write(GIC_REG(VPE_LOCAL, GIC_VPE_COMPARE), cnt); @@ -179,7 +179,7 @@ void gic_write_compare(u64 cnt) } } -void gic_write_cpu_compare(u64 cnt, int cpu) +void notrace gic_write_cpu_compare(u64 cnt, int cpu) { unsigned long flags; diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c index 6a4aa608ad95..ddae430b6eae 100644 --- a/drivers/lightnvm/core.c +++ b/drivers/lightnvm/core.c @@ -252,8 +252,9 @@ static int nvm_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create) } mutex_unlock(&dev->mlock); - if (nvm_reserve_luns(dev, s->lun_begin, s->lun_end)) - return -ENOMEM; + ret = nvm_reserve_luns(dev, s->lun_begin, s->lun_end); + if (ret) + return ret; t = kmalloc(sizeof(struct nvm_target), GFP_KERNEL); if (!t) { @@ -640,6 +641,7 @@ EXPORT_SYMBOL(nvm_max_phys_sects); int nvm_submit_io(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd) { struct nvm_dev *dev = tgt_dev->parent; + int ret; if (!dev->ops->submit_io) return -ENODEV; @@ -647,7 +649,12 @@ int nvm_submit_io(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd) nvm_rq_tgt_to_dev(tgt_dev, rqd); rqd->dev = tgt_dev; - return dev->ops->submit_io(dev, rqd); + + /* In case of error, fail with right address format */ + ret = dev->ops->submit_io(dev, rqd); + if (ret) + nvm_rq_dev_to_tgt(tgt_dev, rqd); + return ret; } EXPORT_SYMBOL(nvm_submit_io); diff --git a/drivers/lightnvm/pblk-cache.c b/drivers/lightnvm/pblk-cache.c index 59bcea88db84..024a8fc93069 100644 --- a/drivers/lightnvm/pblk-cache.c +++ b/drivers/lightnvm/pblk-cache.c @@ -31,9 +31,13 @@ int pblk_write_to_cache(struct pblk *pblk, struct bio *bio, unsigned long flags) */ retry: ret = pblk_rb_may_write_user(&pblk->rwb, bio, nr_entries, &bpos); - if (ret == NVM_IO_REQUEUE) { + switch (ret) { + case NVM_IO_REQUEUE: io_schedule(); goto retry; + case NVM_IO_ERR: + pblk_pipeline_stop(pblk); + goto out; } if (unlikely(!bio_has_data(bio))) @@ -58,6 +62,8 @@ retry: atomic_long_add(nr_entries, &pblk->req_writes); #endif + pblk_rl_inserted(&pblk->rl, nr_entries); + out: pblk_write_should_kick(pblk); return ret; diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c index 5e44768ccffa..11fe0c5b2a9c 100644 --- a/drivers/lightnvm/pblk-core.c +++ b/drivers/lightnvm/pblk-core.c @@ -17,7 +17,6 @@ */ #include "pblk.h" -#include <linux/time.h> static void pblk_mark_bb(struct pblk *pblk, struct pblk_line *line, struct ppa_addr *ppa) @@ -34,7 +33,7 @@ static void pblk_mark_bb(struct pblk *pblk, struct pblk_line *line, pr_err("pblk: attempted to erase bb: line:%d, pos:%d\n", line->id, pos); - pblk_line_run_ws(pblk, NULL, ppa, pblk_line_mark_bb); + pblk_line_run_ws(pblk, NULL, ppa, pblk_line_mark_bb, pblk->bb_wq); } static void __pblk_end_io_erase(struct pblk *pblk, struct nvm_rq *rqd) @@ -54,6 +53,8 @@ static void __pblk_end_io_erase(struct pblk *pblk, struct nvm_rq *rqd) *ppa = rqd->ppa_addr; pblk_mark_bb(pblk, line, ppa); } + + atomic_dec(&pblk->inflight_io); } /* Erase completion assumes that only one block is erased at the time */ @@ -61,13 +62,12 @@ static void pblk_end_io_erase(struct nvm_rq *rqd) { struct pblk *pblk = rqd->private; - up(&pblk->erase_sem); __pblk_end_io_erase(pblk, rqd); - mempool_free(rqd, pblk->r_rq_pool); + mempool_free(rqd, pblk->g_rq_pool); } -static void __pblk_map_invalidate(struct pblk *pblk, struct pblk_line *line, - u64 paddr) +void __pblk_map_invalidate(struct pblk *pblk, struct pblk_line *line, + u64 paddr) { struct pblk_line_mgmt *l_mg = &pblk->l_mg; struct list_head *move_list = NULL; @@ -88,7 +88,7 @@ static void __pblk_map_invalidate(struct pblk *pblk, struct pblk_line *line, spin_unlock(&line->lock); return; } - line->vsc--; + le32_add_cpu(line->vsc, -1); if (line->state == PBLK_LINESTATE_CLOSED) move_list = pblk_line_gc_list(pblk, line); @@ -130,18 +130,6 @@ void pblk_map_invalidate(struct pblk *pblk, struct ppa_addr ppa) __pblk_map_invalidate(pblk, line, paddr); } -void pblk_map_pad_invalidate(struct pblk *pblk, struct pblk_line *line, - u64 paddr) -{ - __pblk_map_invalidate(pblk, line, paddr); - - pblk_rb_sync_init(&pblk->rwb, NULL); - line->left_ssecs--; - if (!line->left_ssecs) - pblk_line_run_ws(pblk, line, NULL, pblk_line_close_ws); - pblk_rb_sync_end(&pblk->rwb, NULL); -} - static void pblk_invalidate_range(struct pblk *pblk, sector_t slba, unsigned int nr_secs) { @@ -172,8 +160,8 @@ struct nvm_rq *pblk_alloc_rqd(struct pblk *pblk, int rw) pool = pblk->w_rq_pool; rq_size = pblk_w_rq_size; } else { - pool = pblk->r_rq_pool; - rq_size = pblk_r_rq_size; + pool = pblk->g_rq_pool; + rq_size = pblk_g_rq_size; } rqd = mempool_alloc(pool, GFP_KERNEL); @@ -189,7 +177,7 @@ void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int rw) if (rw == WRITE) pool = pblk->w_rq_pool; else - pool = pblk->r_rq_pool; + pool = pblk->g_rq_pool; mempool_free(rqd, pool); } @@ -271,35 +259,26 @@ void pblk_end_io_sync(struct nvm_rq *rqd) complete(waiting); } -void pblk_flush_writer(struct pblk *pblk) +void pblk_wait_for_meta(struct pblk *pblk) { - struct bio *bio; - int ret; - DECLARE_COMPLETION_ONSTACK(wait); - - bio = bio_alloc(GFP_KERNEL, 1); - if (!bio) - return; - - bio->bi_iter.bi_sector = 0; /* internal bio */ - bio_set_op_attrs(bio, REQ_OP_WRITE, REQ_OP_FLUSH); - bio->bi_private = &wait; - bio->bi_end_io = pblk_end_bio_sync; + do { + if (!atomic_read(&pblk->inflight_io)) + break; - ret = pblk_write_to_cache(pblk, bio, 0); - if (ret == NVM_IO_OK) { - if (!wait_for_completion_io_timeout(&wait, - msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) { - pr_err("pblk: flush cache timed out\n"); - } - } else if (ret != NVM_IO_DONE) { - pr_err("pblk: tear down bio failed\n"); - } + schedule(); + } while (1); +} - if (bio->bi_error) - pr_err("pblk: flush sync write failed (%u)\n", bio->bi_error); +static void pblk_flush_writer(struct pblk *pblk) +{ + pblk_rb_flush(&pblk->rwb); + do { + if (!pblk_rb_sync_count(&pblk->rwb)) + break; - bio_put(bio); + pblk_write_kick(pblk); + schedule(); + } while (1); } struct list_head *pblk_line_gc_list(struct pblk *pblk, struct pblk_line *line) @@ -307,28 +286,31 @@ struct list_head *pblk_line_gc_list(struct pblk *pblk, struct pblk_line *line) struct pblk_line_meta *lm = &pblk->lm; struct pblk_line_mgmt *l_mg = &pblk->l_mg; struct list_head *move_list = NULL; + int vsc = le32_to_cpu(*line->vsc); - if (!line->vsc) { + lockdep_assert_held(&line->lock); + + if (!vsc) { if (line->gc_group != PBLK_LINEGC_FULL) { line->gc_group = PBLK_LINEGC_FULL; move_list = &l_mg->gc_full_list; } - } else if (line->vsc < lm->mid_thrs) { + } else if (vsc < lm->high_thrs) { if (line->gc_group != PBLK_LINEGC_HIGH) { line->gc_group = PBLK_LINEGC_HIGH; move_list = &l_mg->gc_high_list; } - } else if (line->vsc < lm->high_thrs) { + } else if (vsc < lm->mid_thrs) { if (line->gc_group != PBLK_LINEGC_MID) { line->gc_group = PBLK_LINEGC_MID; move_list = &l_mg->gc_mid_list; } - } else if (line->vsc < line->sec_in_line) { + } else if (vsc < line->sec_in_line) { if (line->gc_group != PBLK_LINEGC_LOW) { line->gc_group = PBLK_LINEGC_LOW; move_list = &l_mg->gc_low_list; } - } else if (line->vsc == line->sec_in_line) { + } else if (vsc == line->sec_in_line) { if (line->gc_group != PBLK_LINEGC_EMPTY) { line->gc_group = PBLK_LINEGC_EMPTY; move_list = &l_mg->gc_empty_list; @@ -338,7 +320,7 @@ struct list_head *pblk_line_gc_list(struct pblk *pblk, struct pblk_line *line) line->gc_group = PBLK_LINEGC_NONE; move_list = &l_mg->corrupt_list; pr_err("pblk: corrupted vsc for line %d, vsc:%d (%d/%d/%d)\n", - line->id, line->vsc, + line->id, vsc, line->sec_in_line, lm->high_thrs, lm->mid_thrs); } @@ -397,6 +379,11 @@ void pblk_log_read_err(struct pblk *pblk, struct nvm_rq *rqd) #endif } +void pblk_set_sec_per_write(struct pblk *pblk, int sec_per_write) +{ + pblk->sec_per_write = sec_per_write; +} + int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd) { struct nvm_tgt_dev *dev = pblk->dev; @@ -431,21 +418,23 @@ int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd) } } #endif + + atomic_inc(&pblk->inflight_io); + return nvm_submit_io(dev, rqd); } struct bio *pblk_bio_map_addr(struct pblk *pblk, void *data, unsigned int nr_secs, unsigned int len, - gfp_t gfp_mask) + int alloc_type, gfp_t gfp_mask) { struct nvm_tgt_dev *dev = pblk->dev; - struct pblk_line_mgmt *l_mg = &pblk->l_mg; void *kaddr = data; struct page *page; struct bio *bio; int i, ret; - if (l_mg->emeta_alloc_type == PBLK_KMALLOC_META) + if (alloc_type == PBLK_KMALLOC_META) return bio_map_kern(dev->q, kaddr, len, gfp_mask); bio = bio_kmalloc(gfp_mask, nr_secs); @@ -478,7 +467,7 @@ out: int pblk_calc_secs(struct pblk *pblk, unsigned long secs_avail, unsigned long secs_to_flush) { - int max = pblk->max_write_pgs; + int max = pblk->sec_per_write; int min = pblk->min_write_pgs; int secs_to_sync = 0; @@ -492,12 +481,26 @@ int pblk_calc_secs(struct pblk *pblk, unsigned long secs_avail, return secs_to_sync; } -static u64 __pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, - int nr_secs) +void pblk_dealloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs) +{ + u64 addr; + int i; + + addr = find_next_zero_bit(line->map_bitmap, + pblk->lm.sec_per_line, line->cur_sec); + line->cur_sec = addr - nr_secs; + + for (i = 0; i < nr_secs; i++, line->cur_sec--) + WARN_ON(!test_and_clear_bit(line->cur_sec, line->map_bitmap)); +} + +u64 __pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs) { u64 addr; int i; + lockdep_assert_held(&line->lock); + /* logic error: ppa out-of-bounds. Prevent generating bad address */ if (line->cur_sec + nr_secs > pblk->lm.sec_per_line) { WARN(1, "pblk: page allocation out of bounds\n"); @@ -528,27 +531,38 @@ u64 pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs) return addr; } +u64 pblk_lookup_page(struct pblk *pblk, struct pblk_line *line) +{ + u64 paddr; + + spin_lock(&line->lock); + paddr = find_next_zero_bit(line->map_bitmap, + pblk->lm.sec_per_line, line->cur_sec); + spin_unlock(&line->lock); + + return paddr; +} + /* * Submit emeta to one LUN in the raid line at the time to avoid a deadlock when * taking the per LUN semaphore. */ static int pblk_line_submit_emeta_io(struct pblk *pblk, struct pblk_line *line, - u64 paddr, int dir) + void *emeta_buf, u64 paddr, int dir) { struct nvm_tgt_dev *dev = pblk->dev; struct nvm_geo *geo = &dev->geo; + struct pblk_line_mgmt *l_mg = &pblk->l_mg; struct pblk_line_meta *lm = &pblk->lm; + void *ppa_list, *meta_list; struct bio *bio; struct nvm_rq rqd; - struct ppa_addr *ppa_list; - dma_addr_t dma_ppa_list; - void *emeta = line->emeta; + dma_addr_t dma_ppa_list, dma_meta_list; int min = pblk->min_write_pgs; - int left_ppas = lm->emeta_sec; + int left_ppas = lm->emeta_sec[0]; int id = line->id; int rq_ppas, rq_len; int cmd_op, bio_op; - int flags; int i, j; int ret; DECLARE_COMPLETION_ONSTACK(wait); @@ -556,25 +570,28 @@ static int pblk_line_submit_emeta_io(struct pblk *pblk, struct pblk_line *line, if (dir == WRITE) { bio_op = REQ_OP_WRITE; cmd_op = NVM_OP_PWRITE; - flags = pblk_set_progr_mode(pblk, WRITE); } else if (dir == READ) { bio_op = REQ_OP_READ; cmd_op = NVM_OP_PREAD; - flags = pblk_set_read_mode(pblk); } else return -EINVAL; - ppa_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, &dma_ppa_list); - if (!ppa_list) + meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, + &dma_meta_list); + if (!meta_list) return -ENOMEM; + ppa_list = meta_list + pblk_dma_meta_size; + dma_ppa_list = dma_meta_list + pblk_dma_meta_size; + next_rq: memset(&rqd, 0, sizeof(struct nvm_rq)); rq_ppas = pblk_calc_secs(pblk, left_ppas, 0); rq_len = rq_ppas * geo->sec_size; - bio = pblk_bio_map_addr(pblk, emeta, rq_ppas, rq_len, GFP_KERNEL); + bio = pblk_bio_map_addr(pblk, emeta_buf, rq_ppas, rq_len, + l_mg->emeta_alloc_type, GFP_KERNEL); if (IS_ERR(bio)) { ret = PTR_ERR(bio); goto free_rqd_dma; @@ -584,27 +601,38 @@ next_rq: bio_set_op_attrs(bio, bio_op, 0); rqd.bio = bio; - rqd.opcode = cmd_op; - rqd.flags = flags; - rqd.nr_ppas = rq_ppas; + rqd.meta_list = meta_list; rqd.ppa_list = ppa_list; + rqd.dma_meta_list = dma_meta_list; rqd.dma_ppa_list = dma_ppa_list; + rqd.opcode = cmd_op; + rqd.nr_ppas = rq_ppas; rqd.end_io = pblk_end_io_sync; rqd.private = &wait; if (dir == WRITE) { + struct pblk_sec_meta *meta_list = rqd.meta_list; + + rqd.flags = pblk_set_progr_mode(pblk, WRITE); for (i = 0; i < rqd.nr_ppas; ) { spin_lock(&line->lock); paddr = __pblk_alloc_page(pblk, line, min); spin_unlock(&line->lock); - for (j = 0; j < min; j++, i++, paddr++) + for (j = 0; j < min; j++, i++, paddr++) { + meta_list[i].lba = cpu_to_le64(ADDR_EMPTY); rqd.ppa_list[i] = addr_to_gen_ppa(pblk, paddr, id); + } } } else { for (i = 0; i < rqd.nr_ppas; ) { struct ppa_addr ppa = addr_to_gen_ppa(pblk, paddr, id); int pos = pblk_dev_ppa_to_pos(geo, ppa); + int read_type = PBLK_READ_RANDOM; + + if (pblk_io_aligned(pblk, rq_ppas)) + read_type = PBLK_READ_SEQUENTIAL; + rqd.flags = pblk_set_read_mode(pblk, read_type); while (test_bit(pos, line->blk_bitmap)) { paddr += min; @@ -645,9 +673,11 @@ next_rq: msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) { pr_err("pblk: emeta I/O timed out\n"); } + atomic_dec(&pblk->inflight_io); reinit_completion(&wait); - bio_put(bio); + if (likely(pblk->l_mg.emeta_alloc_type == PBLK_VMALLOC_META)) + bio_put(bio); if (rqd.error) { if (dir == WRITE) @@ -656,12 +686,12 @@ next_rq: pblk_log_read_err(pblk, &rqd); } - emeta += rq_len; + emeta_buf += rq_len; left_ppas -= rq_ppas; if (left_ppas) goto next_rq; free_rqd_dma: - nvm_dev_dma_free(dev->parent, ppa_list, dma_ppa_list); + nvm_dev_dma_free(dev->parent, rqd.meta_list, rqd.dma_meta_list); return ret; } @@ -697,21 +727,24 @@ static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line, bio_op = REQ_OP_WRITE; cmd_op = NVM_OP_PWRITE; flags = pblk_set_progr_mode(pblk, WRITE); - lba_list = pblk_line_emeta_to_lbas(line->emeta); + lba_list = emeta_to_lbas(pblk, line->emeta->buf); } else if (dir == READ) { bio_op = REQ_OP_READ; cmd_op = NVM_OP_PREAD; - flags = pblk_set_read_mode(pblk); + flags = pblk_set_read_mode(pblk, PBLK_READ_SEQUENTIAL); } else return -EINVAL; memset(&rqd, 0, sizeof(struct nvm_rq)); - rqd.ppa_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, - &rqd.dma_ppa_list); - if (!rqd.ppa_list) + rqd.meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, + &rqd.dma_meta_list); + if (!rqd.meta_list) return -ENOMEM; + rqd.ppa_list = rqd.meta_list + pblk_dma_meta_size; + rqd.dma_ppa_list = rqd.dma_meta_list + pblk_dma_meta_size; + bio = bio_map_kern(dev->q, line->smeta, lm->smeta_len, GFP_KERNEL); if (IS_ERR(bio)) { ret = PTR_ERR(bio); @@ -729,9 +762,15 @@ static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line, rqd.private = &wait; for (i = 0; i < lm->smeta_sec; i++, paddr++) { + struct pblk_sec_meta *meta_list = rqd.meta_list; + rqd.ppa_list[i] = addr_to_gen_ppa(pblk, paddr, line->id); - if (dir == WRITE) - lba_list[paddr] = cpu_to_le64(ADDR_EMPTY); + + if (dir == WRITE) { + __le64 addr_empty = cpu_to_le64(ADDR_EMPTY); + + meta_list[i].lba = lba_list[paddr] = addr_empty; + } } /* @@ -750,6 +789,7 @@ static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line, msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) { pr_err("pblk: smeta I/O timed out\n"); } + atomic_dec(&pblk->inflight_io); if (rqd.error) { if (dir == WRITE) @@ -759,7 +799,7 @@ static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line, } free_ppa_list: - nvm_dev_dma_free(dev->parent, rqd.ppa_list, rqd.dma_ppa_list); + nvm_dev_dma_free(dev->parent, rqd.meta_list, rqd.dma_meta_list); return ret; } @@ -771,9 +811,11 @@ int pblk_line_read_smeta(struct pblk *pblk, struct pblk_line *line) return pblk_line_submit_smeta_io(pblk, line, bpaddr, READ); } -int pblk_line_read_emeta(struct pblk *pblk, struct pblk_line *line) +int pblk_line_read_emeta(struct pblk *pblk, struct pblk_line *line, + void *emeta_buf) { - return pblk_line_submit_emeta_io(pblk, line, line->emeta_ssec, READ); + return pblk_line_submit_emeta_io(pblk, line, emeta_buf, + line->emeta_ssec, READ); } static void pblk_setup_e_rq(struct pblk *pblk, struct nvm_rq *rqd, @@ -789,7 +831,7 @@ static void pblk_setup_e_rq(struct pblk *pblk, struct nvm_rq *rqd, static int pblk_blk_erase_sync(struct pblk *pblk, struct ppa_addr ppa) { struct nvm_rq rqd; - int ret; + int ret = 0; DECLARE_COMPLETION_ONSTACK(wait); memset(&rqd, 0, sizeof(struct nvm_rq)); @@ -824,14 +866,14 @@ out: rqd.private = pblk; __pblk_end_io_erase(pblk, &rqd); - return 0; + return ret; } int pblk_line_erase(struct pblk *pblk, struct pblk_line *line) { struct pblk_line_meta *lm = &pblk->lm; struct ppa_addr ppa; - int bit = -1; + int ret, bit = -1; /* Erase only good blocks, one at a time */ do { @@ -850,27 +892,59 @@ int pblk_line_erase(struct pblk *pblk, struct pblk_line *line) WARN_ON(test_and_set_bit(bit, line->erase_bitmap)); spin_unlock(&line->lock); - if (pblk_blk_erase_sync(pblk, ppa)) { + ret = pblk_blk_erase_sync(pblk, ppa); + if (ret) { pr_err("pblk: failed to erase line %d\n", line->id); - return -ENOMEM; + return ret; } } while (1); return 0; } +static void pblk_line_setup_metadata(struct pblk_line *line, + struct pblk_line_mgmt *l_mg, + struct pblk_line_meta *lm) +{ + int meta_line; + + lockdep_assert_held(&l_mg->free_lock); + +retry_meta: + meta_line = find_first_zero_bit(&l_mg->meta_bitmap, PBLK_DATA_LINES); + if (meta_line == PBLK_DATA_LINES) { + spin_unlock(&l_mg->free_lock); + io_schedule(); + spin_lock(&l_mg->free_lock); + goto retry_meta; + } + + set_bit(meta_line, &l_mg->meta_bitmap); + line->meta_line = meta_line; + + line->smeta = l_mg->sline_meta[meta_line]; + line->emeta = l_mg->eline_meta[meta_line]; + + memset(line->smeta, 0, lm->smeta_len); + memset(line->emeta->buf, 0, lm->emeta_len[0]); + + line->emeta->mem = 0; + atomic_set(&line->emeta->sync, 0); +} + /* For now lines are always assumed full lines. Thus, smeta former and current * lun bitmaps are omitted. */ -static int pblk_line_set_metadata(struct pblk *pblk, struct pblk_line *line, +static int pblk_line_init_metadata(struct pblk *pblk, struct pblk_line *line, struct pblk_line *cur) { struct nvm_tgt_dev *dev = pblk->dev; struct nvm_geo *geo = &dev->geo; struct pblk_line_meta *lm = &pblk->lm; struct pblk_line_mgmt *l_mg = &pblk->l_mg; - struct line_smeta *smeta = line->smeta; - struct line_emeta *emeta = line->emeta; + struct pblk_emeta *emeta = line->emeta; + struct line_emeta *emeta_buf = emeta->buf; + struct line_smeta *smeta_buf = (struct line_smeta *)line->smeta; int nr_blk_line; /* After erasing the line, new bad blocks might appear and we risk @@ -893,42 +967,44 @@ static int pblk_line_set_metadata(struct pblk *pblk, struct pblk_line *line, } /* Run-time metadata */ - line->lun_bitmap = ((void *)(smeta)) + sizeof(struct line_smeta); + line->lun_bitmap = ((void *)(smeta_buf)) + sizeof(struct line_smeta); /* Mark LUNs allocated in this line (all for now) */ bitmap_set(line->lun_bitmap, 0, lm->lun_bitmap_len); - smeta->header.identifier = cpu_to_le32(PBLK_MAGIC); - memcpy(smeta->header.uuid, pblk->instance_uuid, 16); - smeta->header.id = cpu_to_le32(line->id); - smeta->header.type = cpu_to_le16(line->type); - smeta->header.version = cpu_to_le16(1); + smeta_buf->header.identifier = cpu_to_le32(PBLK_MAGIC); + memcpy(smeta_buf->header.uuid, pblk->instance_uuid, 16); + smeta_buf->header.id = cpu_to_le32(line->id); + smeta_buf->header.type = cpu_to_le16(line->type); + smeta_buf->header.version = cpu_to_le16(1); /* Start metadata */ - smeta->seq_nr = cpu_to_le64(line->seq_nr); - smeta->window_wr_lun = cpu_to_le32(geo->nr_luns); + smeta_buf->seq_nr = cpu_to_le64(line->seq_nr); + smeta_buf->window_wr_lun = cpu_to_le32(geo->nr_luns); /* Fill metadata among lines */ if (cur) { memcpy(line->lun_bitmap, cur->lun_bitmap, lm->lun_bitmap_len); - smeta->prev_id = cpu_to_le32(cur->id); - cur->emeta->next_id = cpu_to_le32(line->id); + smeta_buf->prev_id = cpu_to_le32(cur->id); + cur->emeta->buf->next_id = cpu_to_le32(line->id); } else { - smeta->prev_id = cpu_to_le32(PBLK_LINE_EMPTY); + smeta_buf->prev_id = cpu_to_le32(PBLK_LINE_EMPTY); } /* All smeta must be set at this point */ - smeta->header.crc = cpu_to_le32(pblk_calc_meta_header_crc(pblk, smeta)); - smeta->crc = cpu_to_le32(pblk_calc_smeta_crc(pblk, smeta)); + smeta_buf->header.crc = cpu_to_le32( + pblk_calc_meta_header_crc(pblk, &smeta_buf->header)); + smeta_buf->crc = cpu_to_le32(pblk_calc_smeta_crc(pblk, smeta_buf)); /* End metadata */ - memcpy(&emeta->header, &smeta->header, sizeof(struct line_header)); - emeta->seq_nr = cpu_to_le64(line->seq_nr); - emeta->nr_lbas = cpu_to_le64(line->sec_in_line); - emeta->nr_valid_lbas = cpu_to_le64(0); - emeta->next_id = cpu_to_le32(PBLK_LINE_EMPTY); - emeta->crc = cpu_to_le32(0); - emeta->prev_id = smeta->prev_id; + memcpy(&emeta_buf->header, &smeta_buf->header, + sizeof(struct line_header)); + emeta_buf->seq_nr = cpu_to_le64(line->seq_nr); + emeta_buf->nr_lbas = cpu_to_le64(line->sec_in_line); + emeta_buf->nr_valid_lbas = cpu_to_le64(0); + emeta_buf->next_id = cpu_to_le32(PBLK_LINE_EMPTY); + emeta_buf->crc = cpu_to_le32(0); + emeta_buf->prev_id = smeta_buf->prev_id; return 1; } @@ -965,7 +1041,6 @@ static int pblk_line_init_bb(struct pblk *pblk, struct pblk_line *line, /* Mark smeta metadata sectors as bad sectors */ bit = find_first_zero_bit(line->blk_bitmap, lm->blk_per_line); off = bit * geo->sec_per_pl; -retry_smeta: bitmap_set(line->map_bitmap, off, lm->smeta_sec); line->sec_in_line -= lm->smeta_sec; line->smeta_ssec = off; @@ -973,8 +1048,7 @@ retry_smeta: if (init && pblk_line_submit_smeta_io(pblk, line, off, WRITE)) { pr_debug("pblk: line smeta I/O failed. Retry\n"); - off += geo->sec_per_pl; - goto retry_smeta; + return 1; } bitmap_copy(line->invalid_bitmap, line->map_bitmap, lm->sec_per_line); @@ -983,8 +1057,8 @@ retry_smeta: * blocks to make sure that there are enough sectors to store emeta */ bit = lm->sec_per_line; - off = lm->sec_per_line - lm->emeta_sec; - bitmap_set(line->invalid_bitmap, off, lm->emeta_sec); + off = lm->sec_per_line - lm->emeta_sec[0]; + bitmap_set(line->invalid_bitmap, off, lm->emeta_sec[0]); while (nr_bb) { off -= geo->sec_per_pl; if (!test_bit(off, line->invalid_bitmap)) { @@ -993,9 +1067,11 @@ retry_smeta: } } - line->sec_in_line -= lm->emeta_sec; + line->sec_in_line -= lm->emeta_sec[0]; line->emeta_ssec = off; - line->vsc = line->left_ssecs = line->left_msecs = line->sec_in_line; + line->nr_valid_lbas = 0; + line->left_msecs = line->sec_in_line; + *line->vsc = cpu_to_le32(line->sec_in_line); if (lm->sec_per_line - line->sec_in_line != bitmap_weight(line->invalid_bitmap, lm->sec_per_line)) { @@ -1034,14 +1110,20 @@ static int pblk_line_prepare(struct pblk *pblk, struct pblk_line *line) spin_lock(&line->lock); if (line->state != PBLK_LINESTATE_FREE) { + mempool_free(line->invalid_bitmap, pblk->line_meta_pool); + mempool_free(line->map_bitmap, pblk->line_meta_pool); spin_unlock(&line->lock); - WARN(1, "pblk: corrupted line state\n"); - return -EINTR; + WARN(1, "pblk: corrupted line %d, state %d\n", + line->id, line->state); + return -EAGAIN; } + line->state = PBLK_LINESTATE_OPEN; atomic_set(&line->left_eblks, blk_in_line); atomic_set(&line->left_seblks, blk_in_line); + + line->meta_distance = lm->meta_distance; spin_unlock(&line->lock); /* Bad blocks do not need to be erased */ @@ -1091,15 +1173,15 @@ struct pblk_line *pblk_line_get(struct pblk *pblk) { struct pblk_line_mgmt *l_mg = &pblk->l_mg; struct pblk_line_meta *lm = &pblk->lm; - struct pblk_line *line = NULL; - int bit; + struct pblk_line *line; + int ret, bit; lockdep_assert_held(&l_mg->free_lock); -retry_get: +retry: if (list_empty(&l_mg->free_list)) { pr_err("pblk: no free lines\n"); - goto out; + return NULL; } line = list_first_entry(&l_mg->free_list, struct pblk_line, list); @@ -1115,16 +1197,22 @@ retry_get: list_add_tail(&line->list, &l_mg->bad_list); pr_debug("pblk: line %d is bad\n", line->id); - goto retry_get; + goto retry; } - if (pblk_line_prepare(pblk, line)) { - pr_err("pblk: failed to prepare line %d\n", line->id); - list_add(&line->list, &l_mg->free_list); - return NULL; + ret = pblk_line_prepare(pblk, line); + if (ret) { + if (ret == -EAGAIN) { + list_add(&line->list, &l_mg->corrupt_list); + goto retry; + } else { + pr_err("pblk: failed to prepare line %d\n", line->id); + list_add(&line->list, &l_mg->free_list); + l_mg->nr_free_lines++; + return NULL; + } } -out: return line; } @@ -1134,6 +1222,7 @@ static struct pblk_line *pblk_line_retry(struct pblk *pblk, struct pblk_line_mgmt *l_mg = &pblk->l_mg; struct pblk_line *retry_line; +retry: spin_lock(&l_mg->free_lock); retry_line = pblk_line_get(pblk); if (!retry_line) { @@ -1150,23 +1239,25 @@ static struct pblk_line *pblk_line_retry(struct pblk *pblk, l_mg->data_line = retry_line; spin_unlock(&l_mg->free_lock); - if (pblk_line_erase(pblk, retry_line)) { - spin_lock(&l_mg->free_lock); - l_mg->data_line = NULL; - spin_unlock(&l_mg->free_lock); - return NULL; - } - pblk_rl_free_lines_dec(&pblk->rl, retry_line); + if (pblk_line_erase(pblk, retry_line)) + goto retry; + return retry_line; } +static void pblk_set_space_limit(struct pblk *pblk) +{ + struct pblk_rl *rl = &pblk->rl; + + atomic_set(&rl->rb_space, 0); +} + struct pblk_line *pblk_line_get_first_data(struct pblk *pblk) { struct pblk_line_mgmt *l_mg = &pblk->l_mg; struct pblk_line *line; - int meta_line; int is_next = 0; spin_lock(&l_mg->free_lock); @@ -1180,30 +1271,37 @@ struct pblk_line *pblk_line_get_first_data(struct pblk *pblk) line->type = PBLK_LINETYPE_DATA; l_mg->data_line = line; - meta_line = find_first_zero_bit(&l_mg->meta_bitmap, PBLK_DATA_LINES); - set_bit(meta_line, &l_mg->meta_bitmap); - line->smeta = l_mg->sline_meta[meta_line].meta; - line->emeta = l_mg->eline_meta[meta_line].meta; - line->meta_line = meta_line; + pblk_line_setup_metadata(line, l_mg, &pblk->lm); /* Allocate next line for preparation */ l_mg->data_next = pblk_line_get(pblk); - if (l_mg->data_next) { + if (!l_mg->data_next) { + /* If we cannot get a new line, we need to stop the pipeline. + * Only allow as many writes in as we can store safely and then + * fail gracefully + */ + pblk_set_space_limit(pblk); + + l_mg->data_next = NULL; + } else { l_mg->data_next->seq_nr = l_mg->d_seq_nr++; l_mg->data_next->type = PBLK_LINETYPE_DATA; is_next = 1; } spin_unlock(&l_mg->free_lock); + if (pblk_line_erase(pblk, line)) { + line = pblk_line_retry(pblk, line); + if (!line) + return NULL; + } + pblk_rl_free_lines_dec(&pblk->rl, line); if (is_next) pblk_rl_free_lines_dec(&pblk->rl, l_mg->data_next); - if (pblk_line_erase(pblk, line)) - return NULL; - retry_setup: - if (!pblk_line_set_metadata(pblk, line, NULL)) { + if (!pblk_line_init_metadata(pblk, line, NULL)) { line = pblk_line_retry(pblk, line); if (!line) return NULL; @@ -1222,69 +1320,89 @@ retry_setup: return line; } -struct pblk_line *pblk_line_replace_data(struct pblk *pblk) +static void pblk_stop_writes(struct pblk *pblk, struct pblk_line *line) +{ + lockdep_assert_held(&pblk->l_mg.free_lock); + + pblk_set_space_limit(pblk); + pblk->state = PBLK_STATE_STOPPING; +} + +void pblk_pipeline_stop(struct pblk *pblk) +{ + struct pblk_line_mgmt *l_mg = &pblk->l_mg; + int ret; + + spin_lock(&l_mg->free_lock); + if (pblk->state == PBLK_STATE_RECOVERING || + pblk->state == PBLK_STATE_STOPPED) { + spin_unlock(&l_mg->free_lock); + return; + } + pblk->state = PBLK_STATE_RECOVERING; + spin_unlock(&l_mg->free_lock); + + pblk_flush_writer(pblk); + pblk_wait_for_meta(pblk); + + ret = pblk_recov_pad(pblk); + if (ret) { + pr_err("pblk: could not close data on teardown(%d)\n", ret); + return; + } + + flush_workqueue(pblk->bb_wq); + pblk_line_close_meta_sync(pblk); + + spin_lock(&l_mg->free_lock); + pblk->state = PBLK_STATE_STOPPED; + l_mg->data_line = NULL; + l_mg->data_next = NULL; + spin_unlock(&l_mg->free_lock); +} + +void pblk_line_replace_data(struct pblk *pblk) { - struct pblk_line_meta *lm = &pblk->lm; struct pblk_line_mgmt *l_mg = &pblk->l_mg; struct pblk_line *cur, *new; unsigned int left_seblks; - int meta_line; int is_next = 0; cur = l_mg->data_line; new = l_mg->data_next; if (!new) - return NULL; + return; l_mg->data_line = new; -retry_line: + spin_lock(&l_mg->free_lock); + if (pblk->state != PBLK_STATE_RUNNING) { + l_mg->data_line = NULL; + l_mg->data_next = NULL; + spin_unlock(&l_mg->free_lock); + return; + } + + pblk_line_setup_metadata(new, l_mg, &pblk->lm); + spin_unlock(&l_mg->free_lock); + +retry_erase: left_seblks = atomic_read(&new->left_seblks); if (left_seblks) { /* If line is not fully erased, erase it */ if (atomic_read(&new->left_eblks)) { if (pblk_line_erase(pblk, new)) - return NULL; + return; } else { io_schedule(); } - goto retry_line; + goto retry_erase; } - spin_lock(&l_mg->free_lock); - /* Allocate next line for preparation */ - l_mg->data_next = pblk_line_get(pblk); - if (l_mg->data_next) { - l_mg->data_next->seq_nr = l_mg->d_seq_nr++; - l_mg->data_next->type = PBLK_LINETYPE_DATA; - is_next = 1; - } - -retry_meta: - meta_line = find_first_zero_bit(&l_mg->meta_bitmap, PBLK_DATA_LINES); - if (meta_line == PBLK_DATA_LINES) { - spin_unlock(&l_mg->free_lock); - io_schedule(); - spin_lock(&l_mg->free_lock); - goto retry_meta; - } - - set_bit(meta_line, &l_mg->meta_bitmap); - new->smeta = l_mg->sline_meta[meta_line].meta; - new->emeta = l_mg->eline_meta[meta_line].meta; - new->meta_line = meta_line; - - memset(new->smeta, 0, lm->smeta_len); - memset(new->emeta, 0, lm->emeta_len); - spin_unlock(&l_mg->free_lock); - - if (is_next) - pblk_rl_free_lines_dec(&pblk->rl, l_mg->data_next); - retry_setup: - if (!pblk_line_set_metadata(pblk, new, cur)) { + if (!pblk_line_init_metadata(pblk, new, cur)) { new = pblk_line_retry(pblk, new); if (!new) - return NULL; + return; goto retry_setup; } @@ -1292,12 +1410,30 @@ retry_setup: if (!pblk_line_init_bb(pblk, new, 1)) { new = pblk_line_retry(pblk, new); if (!new) - return NULL; + return; goto retry_setup; } - return new; + /* Allocate next line for preparation */ + spin_lock(&l_mg->free_lock); + l_mg->data_next = pblk_line_get(pblk); + if (!l_mg->data_next) { + /* If we cannot get a new line, we need to stop the pipeline. + * Only allow as many writes in as we can store safely and then + * fail gracefully + */ + pblk_stop_writes(pblk, new); + l_mg->data_next = NULL; + } else { + l_mg->data_next->seq_nr = l_mg->d_seq_nr++; + l_mg->data_next->type = PBLK_LINETYPE_DATA; + is_next = 1; + } + spin_unlock(&l_mg->free_lock); + + if (is_next) + pblk_rl_free_lines_dec(&pblk->rl, l_mg->data_next); } void pblk_line_free(struct pblk *pblk, struct pblk_line *line) @@ -1307,6 +1443,8 @@ void pblk_line_free(struct pblk *pblk, struct pblk_line *line) if (line->invalid_bitmap) mempool_free(line->invalid_bitmap, pblk->line_meta_pool); + *line->vsc = cpu_to_le32(EMPTY_ENTRY); + line->map_bitmap = NULL; line->invalid_bitmap = NULL; line->smeta = NULL; @@ -1339,8 +1477,8 @@ int pblk_blk_erase_async(struct pblk *pblk, struct ppa_addr ppa) struct nvm_rq *rqd; int err; - rqd = mempool_alloc(pblk->r_rq_pool, GFP_KERNEL); - memset(rqd, 0, pblk_r_rq_size); + rqd = mempool_alloc(pblk->g_rq_pool, GFP_KERNEL); + memset(rqd, 0, pblk_g_rq_size); pblk_setup_e_rq(pblk, rqd, ppa); @@ -1368,7 +1506,8 @@ struct pblk_line *pblk_line_get_data(struct pblk *pblk) return pblk->l_mg.data_line; } -struct pblk_line *pblk_line_get_data_next(struct pblk *pblk) +/* For now, always erase next line */ +struct pblk_line *pblk_line_get_erase(struct pblk *pblk) { return pblk->l_mg.data_next; } @@ -1378,18 +1517,58 @@ int pblk_line_is_full(struct pblk_line *line) return (line->left_msecs == 0); } +void pblk_line_close_meta_sync(struct pblk *pblk) +{ + struct pblk_line_mgmt *l_mg = &pblk->l_mg; + struct pblk_line_meta *lm = &pblk->lm; + struct pblk_line *line, *tline; + LIST_HEAD(list); + + spin_lock(&l_mg->close_lock); + if (list_empty(&l_mg->emeta_list)) { + spin_unlock(&l_mg->close_lock); + return; + } + + list_cut_position(&list, &l_mg->emeta_list, l_mg->emeta_list.prev); + spin_unlock(&l_mg->close_lock); + + list_for_each_entry_safe(line, tline, &list, list) { + struct pblk_emeta *emeta = line->emeta; + + while (emeta->mem < lm->emeta_len[0]) { + int ret; + + ret = pblk_submit_meta_io(pblk, line); + if (ret) { + pr_err("pblk: sync meta line %d failed (%d)\n", + line->id, ret); + return; + } + } + } + + pblk_wait_for_meta(pblk); + flush_workqueue(pblk->close_wq); +} + +static void pblk_line_should_sync_meta(struct pblk *pblk) +{ + if (pblk_rl_is_limit(&pblk->rl)) + pblk_line_close_meta_sync(pblk); +} + void pblk_line_close(struct pblk *pblk, struct pblk_line *line) { struct pblk_line_mgmt *l_mg = &pblk->l_mg; struct list_head *move_list; - line->emeta->crc = cpu_to_le32(pblk_calc_emeta_crc(pblk, line->emeta)); - - if (pblk_line_submit_emeta_io(pblk, line, line->cur_sec, WRITE)) - pr_err("pblk: line %d close I/O failed\n", line->id); +#ifdef CONFIG_NVM_DEBUG + struct pblk_line_meta *lm = &pblk->lm; - WARN(!bitmap_full(line->map_bitmap, line->sec_in_line), + WARN(!bitmap_full(line->map_bitmap, lm->sec_per_line), "pblk: corrupt closed line %d\n", line->id); +#endif spin_lock(&l_mg->free_lock); WARN_ON(!test_and_clear_bit(line->meta_line, &l_mg->meta_bitmap)); @@ -1410,6 +1589,31 @@ void pblk_line_close(struct pblk *pblk, struct pblk_line *line) spin_unlock(&line->lock); spin_unlock(&l_mg->gc_lock); + + pblk_gc_should_kick(pblk); +} + +void pblk_line_close_meta(struct pblk *pblk, struct pblk_line *line) +{ + struct pblk_line_mgmt *l_mg = &pblk->l_mg; + struct pblk_line_meta *lm = &pblk->lm; + struct pblk_emeta *emeta = line->emeta; + struct line_emeta *emeta_buf = emeta->buf; + + /* No need for exact vsc value; avoid a big line lock and take aprox. */ + memcpy(emeta_to_vsc(pblk, emeta_buf), l_mg->vsc_list, lm->vsc_list_len); + memcpy(emeta_to_bb(emeta_buf), line->blk_bitmap, lm->blk_bitmap_len); + + emeta_buf->nr_valid_lbas = cpu_to_le64(line->nr_valid_lbas); + emeta_buf->crc = cpu_to_le32(pblk_calc_emeta_crc(pblk, emeta_buf)); + + spin_lock(&l_mg->close_lock); + spin_lock(&line->lock); + list_add_tail(&line->list, &l_mg->emeta_list); + spin_unlock(&line->lock); + spin_unlock(&l_mg->close_lock); + + pblk_line_should_sync_meta(pblk); } void pblk_line_close_ws(struct work_struct *work) @@ -1449,7 +1653,8 @@ void pblk_line_mark_bb(struct work_struct *work) } void pblk_line_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv, - void (*work)(struct work_struct *)) + void (*work)(struct work_struct *), + struct workqueue_struct *wq) { struct pblk_line_ws *line_ws; @@ -1462,7 +1667,7 @@ void pblk_line_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv, line_ws->priv = priv; INIT_WORK(&line_ws->ws, work); - queue_work(pblk->kw_wq, &line_ws->ws); + queue_work(wq, &line_ws->ws); } void pblk_down_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas, @@ -1471,7 +1676,7 @@ void pblk_down_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas, struct nvm_tgt_dev *dev = pblk->dev; struct nvm_geo *geo = &dev->geo; struct pblk_lun *rlun; - int lun_id = ppa_list[0].g.ch * geo->luns_per_chnl + ppa_list[0].g.lun; + int pos = pblk_ppa_to_pos(geo, ppa_list[0]); int ret; /* @@ -1488,10 +1693,10 @@ void pblk_down_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas, /* If the LUN has been locked for this same request, do no attempt to * lock it again */ - if (test_and_set_bit(lun_id, lun_bitmap)) + if (test_and_set_bit(pos, lun_bitmap)) return; - rlun = &pblk->luns[lun_id]; + rlun = &pblk->luns[pos]; ret = down_timeout(&rlun->wr_sem, msecs_to_jiffies(5000)); if (ret) { switch (ret) { diff --git a/drivers/lightnvm/pblk-gc.c b/drivers/lightnvm/pblk-gc.c index eaf479c6b63c..6090d28f7995 100644 --- a/drivers/lightnvm/pblk-gc.c +++ b/drivers/lightnvm/pblk-gc.c @@ -20,8 +20,7 @@ static void pblk_gc_free_gc_rq(struct pblk_gc_rq *gc_rq) { - kfree(gc_rq->data); - kfree(gc_rq->lba_list); + vfree(gc_rq->data); kfree(gc_rq); } @@ -37,10 +36,8 @@ static int pblk_gc_write(struct pblk *pblk) return 1; } - list_for_each_entry_safe(gc_rq, tgc_rq, &gc->w_list, list) { - list_move_tail(&gc_rq->list, &w_list); - gc->w_entries--; - } + list_cut_position(&w_list, &gc->w_list, gc->w_list.prev); + gc->w_entries = 0; spin_unlock(&gc->w_lock); list_for_each_entry_safe(gc_rq, tgc_rq, &w_list, list) { @@ -48,9 +45,8 @@ static int pblk_gc_write(struct pblk *pblk) gc_rq->nr_secs, gc_rq->secs_to_gc, gc_rq->line, PBLK_IOTYPE_GC); - kref_put(&gc_rq->line->ref, pblk_line_put); - list_del(&gc_rq->list); + kref_put(&gc_rq->line->ref, pblk_line_put); pblk_gc_free_gc_rq(gc_rq); } @@ -66,52 +62,41 @@ static void pblk_gc_writer_kick(struct pblk_gc *gc) * Responsible for managing all memory related to a gc request. Also in case of * failure */ -static int pblk_gc_move_valid_secs(struct pblk *pblk, struct pblk_line *line, - u64 *lba_list, unsigned int nr_secs) +static int pblk_gc_move_valid_secs(struct pblk *pblk, struct pblk_gc_rq *gc_rq) { struct nvm_tgt_dev *dev = pblk->dev; struct nvm_geo *geo = &dev->geo; struct pblk_gc *gc = &pblk->gc; - struct pblk_gc_rq *gc_rq; + struct pblk_line *line = gc_rq->line; void *data; unsigned int secs_to_gc; - int ret = NVM_IO_OK; + int ret = 0; - data = kmalloc(nr_secs * geo->sec_size, GFP_KERNEL); + data = vmalloc(gc_rq->nr_secs * geo->sec_size); if (!data) { - ret = NVM_IO_ERR; - goto free_lba_list; + ret = -ENOMEM; + goto out; } /* Read from GC victim block */ - if (pblk_submit_read_gc(pblk, lba_list, data, nr_secs, + if (pblk_submit_read_gc(pblk, gc_rq->lba_list, data, gc_rq->nr_secs, &secs_to_gc, line)) { - ret = NVM_IO_ERR; + ret = -EFAULT; goto free_data; } if (!secs_to_gc) - goto free_data; - - gc_rq = kmalloc(sizeof(struct pblk_gc_rq), GFP_KERNEL); - if (!gc_rq) { - ret = NVM_IO_ERR; - goto free_data; - } + goto free_rq; - gc_rq->line = line; gc_rq->data = data; - gc_rq->lba_list = lba_list; - gc_rq->nr_secs = nr_secs; gc_rq->secs_to_gc = secs_to_gc; - kref_get(&line->ref); - retry: spin_lock(&gc->w_lock); - if (gc->w_entries > 256) { + if (gc->w_entries >= PBLK_GC_W_QD) { spin_unlock(&gc->w_lock); - usleep_range(256, 1024); + pblk_gc_writer_kick(&pblk->gc); + usleep_range(128, 256); goto retry; } gc->w_entries++; @@ -120,13 +105,14 @@ retry: pblk_gc_writer_kick(&pblk->gc); - return NVM_IO_OK; + return 0; +free_rq: + kfree(gc_rq); free_data: - kfree(data); -free_lba_list: - kfree(lba_list); - + vfree(data); +out: + kref_put(&line->ref, pblk_line_put); return ret; } @@ -150,140 +136,206 @@ static void pblk_put_line_back(struct pblk *pblk, struct pblk_line *line) static void pblk_gc_line_ws(struct work_struct *work) { + struct pblk_line_ws *line_rq_ws = container_of(work, + struct pblk_line_ws, ws); + struct pblk *pblk = line_rq_ws->pblk; + struct pblk_gc *gc = &pblk->gc; + struct pblk_line *line = line_rq_ws->line; + struct pblk_gc_rq *gc_rq = line_rq_ws->priv; + + up(&gc->gc_sem); + + if (pblk_gc_move_valid_secs(pblk, gc_rq)) { + pr_err("pblk: could not GC all sectors: line:%d (%d/%d)\n", + line->id, *line->vsc, + gc_rq->nr_secs); + } + + mempool_free(line_rq_ws, pblk->line_ws_pool); +} + +static void pblk_gc_line_prepare_ws(struct work_struct *work) +{ struct pblk_line_ws *line_ws = container_of(work, struct pblk_line_ws, ws); struct pblk *pblk = line_ws->pblk; - struct pblk_line_mgmt *l_mg = &pblk->l_mg; struct pblk_line *line = line_ws->line; + struct pblk_line_mgmt *l_mg = &pblk->l_mg; struct pblk_line_meta *lm = &pblk->lm; - __le64 *lba_list = line_ws->priv; - u64 *gc_list; - int sec_left; - int nr_ppas, bit; - int put_line = 1; + struct pblk_gc *gc = &pblk->gc; + struct line_emeta *emeta_buf; + struct pblk_line_ws *line_rq_ws; + struct pblk_gc_rq *gc_rq; + __le64 *lba_list; + int sec_left, nr_secs, bit; + int ret; - pr_debug("pblk: line '%d' being reclaimed for GC\n", line->id); + emeta_buf = pblk_malloc(lm->emeta_len[0], l_mg->emeta_alloc_type, + GFP_KERNEL); + if (!emeta_buf) { + pr_err("pblk: cannot use GC emeta\n"); + return; + } - spin_lock(&line->lock); - sec_left = line->vsc; - if (!sec_left) { - /* Lines are erased before being used (l_mg->data_/log_next) */ - spin_unlock(&line->lock); - goto out; + ret = pblk_line_read_emeta(pblk, line, emeta_buf); + if (ret) { + pr_err("pblk: line %d read emeta failed (%d)\n", line->id, ret); + goto fail_free_emeta; + } + + /* If this read fails, it means that emeta is corrupted. For now, leave + * the line untouched. TODO: Implement a recovery routine that scans and + * moves all sectors on the line. + */ + lba_list = pblk_recov_get_lba_list(pblk, emeta_buf); + if (!lba_list) { + pr_err("pblk: could not interpret emeta (line %d)\n", line->id); + goto fail_free_emeta; } - spin_unlock(&line->lock); + sec_left = pblk_line_vsc(line); if (sec_left < 0) { pr_err("pblk: corrupted GC line (%d)\n", line->id); - put_line = 0; - pblk_put_line_back(pblk, line); - goto out; + goto fail_free_emeta; } bit = -1; next_rq: - gc_list = kmalloc_array(pblk->max_write_pgs, sizeof(u64), GFP_KERNEL); - if (!gc_list) { - put_line = 0; - pblk_put_line_back(pblk, line); - goto out; - } + gc_rq = kmalloc(sizeof(struct pblk_gc_rq), GFP_KERNEL); + if (!gc_rq) + goto fail_free_emeta; - nr_ppas = 0; + nr_secs = 0; do { bit = find_next_zero_bit(line->invalid_bitmap, lm->sec_per_line, bit + 1); if (bit > line->emeta_ssec) break; - gc_list[nr_ppas++] = le64_to_cpu(lba_list[bit]); - } while (nr_ppas < pblk->max_write_pgs); + gc_rq->lba_list[nr_secs++] = le64_to_cpu(lba_list[bit]); + } while (nr_secs < pblk->max_write_pgs); - if (unlikely(!nr_ppas)) { - kfree(gc_list); + if (unlikely(!nr_secs)) { + kfree(gc_rq); goto out; } - if (pblk_gc_move_valid_secs(pblk, line, gc_list, nr_ppas)) { - pr_err("pblk: could not GC all sectors: line:%d (%d/%d/%d)\n", - line->id, line->vsc, - nr_ppas, nr_ppas); - put_line = 0; - pblk_put_line_back(pblk, line); - goto out; - } + gc_rq->nr_secs = nr_secs; + gc_rq->line = line; + + line_rq_ws = mempool_alloc(pblk->line_ws_pool, GFP_KERNEL); + if (!line_rq_ws) + goto fail_free_gc_rq; - sec_left -= nr_ppas; + line_rq_ws->pblk = pblk; + line_rq_ws->line = line; + line_rq_ws->priv = gc_rq; + + down(&gc->gc_sem); + kref_get(&line->ref); + + INIT_WORK(&line_rq_ws->ws, pblk_gc_line_ws); + queue_work(gc->gc_line_reader_wq, &line_rq_ws->ws); + + sec_left -= nr_secs; if (sec_left > 0) goto next_rq; out: - pblk_mfree(line->emeta, l_mg->emeta_alloc_type); + pblk_mfree(emeta_buf, l_mg->emeta_alloc_type); mempool_free(line_ws, pblk->line_ws_pool); - atomic_dec(&pblk->gc.inflight_gc); - if (put_line) - kref_put(&line->ref, pblk_line_put); + + kref_put(&line->ref, pblk_line_put); + atomic_dec(&gc->inflight_gc); + + return; + +fail_free_gc_rq: + kfree(gc_rq); +fail_free_emeta: + pblk_mfree(emeta_buf, l_mg->emeta_alloc_type); + pblk_put_line_back(pblk, line); + kref_put(&line->ref, pblk_line_put); + mempool_free(line_ws, pblk->line_ws_pool); + atomic_dec(&gc->inflight_gc); + + pr_err("pblk: Failed to GC line %d\n", line->id); } static int pblk_gc_line(struct pblk *pblk, struct pblk_line *line) { - struct pblk_line_mgmt *l_mg = &pblk->l_mg; - struct pblk_line_meta *lm = &pblk->lm; + struct pblk_gc *gc = &pblk->gc; struct pblk_line_ws *line_ws; - __le64 *lba_list; - int ret; - line_ws = mempool_alloc(pblk->line_ws_pool, GFP_KERNEL); - line->emeta = pblk_malloc(lm->emeta_len, l_mg->emeta_alloc_type, - GFP_KERNEL); - if (!line->emeta) { - pr_err("pblk: cannot use GC emeta\n"); - goto fail_free_ws; - } - - ret = pblk_line_read_emeta(pblk, line); - if (ret) { - pr_err("pblk: line %d read emeta failed (%d)\n", line->id, ret); - goto fail_free_emeta; - } + pr_debug("pblk: line '%d' being reclaimed for GC\n", line->id); - /* If this read fails, it means that emeta is corrupted. For now, leave - * the line untouched. TODO: Implement a recovery routine that scans and - * moves all sectors on the line. - */ - lba_list = pblk_recov_get_lba_list(pblk, line->emeta); - if (!lba_list) { - pr_err("pblk: could not interpret emeta (line %d)\n", line->id); - goto fail_free_emeta; - } + line_ws = mempool_alloc(pblk->line_ws_pool, GFP_KERNEL); + if (!line_ws) + return -ENOMEM; line_ws->pblk = pblk; line_ws->line = line; - line_ws->priv = lba_list; - INIT_WORK(&line_ws->ws, pblk_gc_line_ws); - queue_work(pblk->gc.gc_reader_wq, &line_ws->ws); + INIT_WORK(&line_ws->ws, pblk_gc_line_prepare_ws); + queue_work(gc->gc_reader_wq, &line_ws->ws); return 0; +} -fail_free_emeta: - pblk_mfree(line->emeta, l_mg->emeta_alloc_type); -fail_free_ws: - mempool_free(line_ws, pblk->line_ws_pool); - pblk_put_line_back(pblk, line); +static int pblk_gc_read(struct pblk *pblk) +{ + struct pblk_gc *gc = &pblk->gc; + struct pblk_line *line; + + spin_lock(&gc->r_lock); + if (list_empty(&gc->r_list)) { + spin_unlock(&gc->r_lock); + return 1; + } + + line = list_first_entry(&gc->r_list, struct pblk_line, list); + list_del(&line->list); + spin_unlock(&gc->r_lock); + + pblk_gc_kick(pblk); - return 1; + if (pblk_gc_line(pblk, line)) + pr_err("pblk: failed to GC line %d\n", line->id); + + return 0; } -static void pblk_gc_lines(struct pblk *pblk, struct list_head *gc_list) +static void pblk_gc_reader_kick(struct pblk_gc *gc) { - struct pblk_line *line, *tline; + wake_up_process(gc->gc_reader_ts); +} - list_for_each_entry_safe(line, tline, gc_list, list) { - if (pblk_gc_line(pblk, line)) - pr_err("pblk: failed to GC line %d\n", line->id); - list_del(&line->list); +static struct pblk_line *pblk_gc_get_victim_line(struct pblk *pblk, + struct list_head *group_list) +{ + struct pblk_line *line, *victim; + int line_vsc, victim_vsc; + + victim = list_first_entry(group_list, struct pblk_line, list); + list_for_each_entry(line, group_list, list) { + line_vsc = le32_to_cpu(*line->vsc); + victim_vsc = le32_to_cpu(*victim->vsc); + if (line_vsc < victim_vsc) + victim = line; } + + return victim; +} + +static bool pblk_gc_should_run(struct pblk_gc *gc, struct pblk_rl *rl) +{ + unsigned int nr_blocks_free, nr_blocks_need; + + nr_blocks_need = pblk_rl_high_thrs(rl); + nr_blocks_free = pblk_rl_nr_free_blks(rl); + + /* This is not critical, no need to take lock here */ + return ((gc->gc_active) && (nr_blocks_need > nr_blocks_free)); } /* @@ -296,71 +348,83 @@ static void pblk_gc_run(struct pblk *pblk) { struct pblk_line_mgmt *l_mg = &pblk->l_mg; struct pblk_gc *gc = &pblk->gc; - struct pblk_line *line, *tline; - unsigned int nr_blocks_free, nr_blocks_need; + struct pblk_line *line; struct list_head *group_list; - int run_gc, gc_group = 0; - int prev_gc = 0; - int inflight_gc = atomic_read(&gc->inflight_gc); - LIST_HEAD(gc_list); + bool run_gc; + int inflight_gc, gc_group = 0, prev_group = 0; + + do { + spin_lock(&l_mg->gc_lock); + if (list_empty(&l_mg->gc_full_list)) { + spin_unlock(&l_mg->gc_lock); + break; + } + + line = list_first_entry(&l_mg->gc_full_list, + struct pblk_line, list); - spin_lock(&l_mg->gc_lock); - list_for_each_entry_safe(line, tline, &l_mg->gc_full_list, list) { spin_lock(&line->lock); WARN_ON(line->state != PBLK_LINESTATE_CLOSED); line->state = PBLK_LINESTATE_GC; spin_unlock(&line->lock); list_del(&line->list); + spin_unlock(&l_mg->gc_lock); + kref_put(&line->ref, pblk_line_put); - } - spin_unlock(&l_mg->gc_lock); + } while (1); - nr_blocks_need = pblk_rl_gc_thrs(&pblk->rl); - nr_blocks_free = pblk_rl_nr_free_blks(&pblk->rl); - run_gc = (nr_blocks_need > nr_blocks_free || gc->gc_forced); + run_gc = pblk_gc_should_run(&pblk->gc, &pblk->rl); + if (!run_gc || (atomic_read(&gc->inflight_gc) >= PBLK_GC_L_QD)) + return; next_gc_group: group_list = l_mg->gc_lists[gc_group++]; - spin_lock(&l_mg->gc_lock); - while (run_gc && !list_empty(group_list)) { - /* No need to queue up more GC lines than we can handle */ - if (!run_gc || inflight_gc > gc->gc_jobs_active) { + + do { + spin_lock(&l_mg->gc_lock); + if (list_empty(group_list)) { spin_unlock(&l_mg->gc_lock); - pblk_gc_lines(pblk, &gc_list); - return; + break; } - line = list_first_entry(group_list, struct pblk_line, list); - nr_blocks_free += atomic_read(&line->blk_in_line); + line = pblk_gc_get_victim_line(pblk, group_list); spin_lock(&line->lock); WARN_ON(line->state != PBLK_LINESTATE_CLOSED); line->state = PBLK_LINESTATE_GC; - list_move_tail(&line->list, &gc_list); - atomic_inc(&gc->inflight_gc); - inflight_gc++; spin_unlock(&line->lock); - prev_gc = 1; - run_gc = (nr_blocks_need > nr_blocks_free || gc->gc_forced); - } - spin_unlock(&l_mg->gc_lock); + list_del(&line->list); + spin_unlock(&l_mg->gc_lock); + + spin_lock(&gc->r_lock); + list_add_tail(&line->list, &gc->r_list); + spin_unlock(&gc->r_lock); - pblk_gc_lines(pblk, &gc_list); + inflight_gc = atomic_inc_return(&gc->inflight_gc); + pblk_gc_reader_kick(gc); - if (!prev_gc && pblk->rl.rb_state > gc_group && - gc_group < PBLK_NR_GC_LISTS) + prev_group = 1; + + /* No need to queue up more GC lines than we can handle */ + run_gc = pblk_gc_should_run(&pblk->gc, &pblk->rl); + if (!run_gc || inflight_gc >= PBLK_GC_L_QD) + break; + } while (1); + + if (!prev_group && pblk->rl.rb_state > gc_group && + gc_group < PBLK_GC_NR_LISTS) goto next_gc_group; } - -static void pblk_gc_kick(struct pblk *pblk) +void pblk_gc_kick(struct pblk *pblk) { struct pblk_gc *gc = &pblk->gc; wake_up_process(gc->gc_ts); pblk_gc_writer_kick(gc); + pblk_gc_reader_kick(gc); mod_timer(&gc->gc_timer, jiffies + msecs_to_jiffies(GC_TIME_MSECS)); } @@ -398,42 +462,34 @@ static int pblk_gc_writer_ts(void *data) return 0; } -static void pblk_gc_start(struct pblk *pblk) +static int pblk_gc_reader_ts(void *data) { - pblk->gc.gc_active = 1; + struct pblk *pblk = data; - pr_debug("pblk: gc start\n"); + while (!kthread_should_stop()) { + if (!pblk_gc_read(pblk)) + continue; + set_current_state(TASK_INTERRUPTIBLE); + io_schedule(); + } + + return 0; } -int pblk_gc_status(struct pblk *pblk) +static void pblk_gc_start(struct pblk *pblk) { - struct pblk_gc *gc = &pblk->gc; - int ret; - - spin_lock(&gc->lock); - ret = gc->gc_active; - spin_unlock(&gc->lock); - - return ret; + pblk->gc.gc_active = 1; + pr_debug("pblk: gc start\n"); } -static void __pblk_gc_should_start(struct pblk *pblk) +void pblk_gc_should_start(struct pblk *pblk) { struct pblk_gc *gc = &pblk->gc; - lockdep_assert_held(&gc->lock); - if (gc->gc_enabled && !gc->gc_active) pblk_gc_start(pblk); -} -void pblk_gc_should_start(struct pblk *pblk) -{ - struct pblk_gc *gc = &pblk->gc; - - spin_lock(&gc->lock); - __pblk_gc_should_start(pblk); - spin_unlock(&gc->lock); + pblk_gc_kick(pblk); } /* @@ -442,10 +498,7 @@ void pblk_gc_should_start(struct pblk *pblk) */ static void pblk_gc_stop(struct pblk *pblk, int flush_wq) { - spin_lock(&pblk->gc.lock); pblk->gc.gc_active = 0; - spin_unlock(&pblk->gc.lock); - pr_debug("pblk: gc stop\n"); } @@ -468,20 +521,25 @@ void pblk_gc_sysfs_state_show(struct pblk *pblk, int *gc_enabled, spin_unlock(&gc->lock); } -void pblk_gc_sysfs_force(struct pblk *pblk, int force) +int pblk_gc_sysfs_force(struct pblk *pblk, int force) { struct pblk_gc *gc = &pblk->gc; - int rsv = 0; + + if (force < 0 || force > 1) + return -EINVAL; spin_lock(&gc->lock); - if (force) { - gc->gc_enabled = 1; - rsv = 64; - } - pblk_rl_set_gc_rsc(&pblk->rl, rsv); gc->gc_forced = force; - __pblk_gc_should_start(pblk); + + if (force) + gc->gc_enabled = 1; + else + gc->gc_enabled = 0; spin_unlock(&gc->lock); + + pblk_gc_should_start(pblk); + + return 0; } int pblk_gc_init(struct pblk *pblk) @@ -503,30 +561,58 @@ int pblk_gc_init(struct pblk *pblk) goto fail_free_main_kthread; } + gc->gc_reader_ts = kthread_create(pblk_gc_reader_ts, pblk, + "pblk-gc-reader-ts"); + if (IS_ERR(gc->gc_reader_ts)) { + pr_err("pblk: could not allocate GC reader kthread\n"); + ret = PTR_ERR(gc->gc_reader_ts); + goto fail_free_writer_kthread; + } + setup_timer(&gc->gc_timer, pblk_gc_timer, (unsigned long)pblk); mod_timer(&gc->gc_timer, jiffies + msecs_to_jiffies(GC_TIME_MSECS)); gc->gc_active = 0; gc->gc_forced = 0; gc->gc_enabled = 1; - gc->gc_jobs_active = 8; gc->w_entries = 0; atomic_set(&gc->inflight_gc, 0); - gc->gc_reader_wq = alloc_workqueue("pblk-gc-reader-wq", - WQ_MEM_RECLAIM | WQ_UNBOUND, gc->gc_jobs_active); + /* Workqueue that reads valid sectors from a line and submit them to the + * GC writer to be recycled. + */ + gc->gc_line_reader_wq = alloc_workqueue("pblk-gc-line-reader-wq", + WQ_MEM_RECLAIM | WQ_UNBOUND, PBLK_GC_MAX_READERS); + if (!gc->gc_line_reader_wq) { + pr_err("pblk: could not allocate GC line reader workqueue\n"); + ret = -ENOMEM; + goto fail_free_reader_kthread; + } + + /* Workqueue that prepare lines for GC */ + gc->gc_reader_wq = alloc_workqueue("pblk-gc-line_wq", + WQ_MEM_RECLAIM | WQ_UNBOUND, 1); if (!gc->gc_reader_wq) { pr_err("pblk: could not allocate GC reader workqueue\n"); ret = -ENOMEM; - goto fail_free_writer_kthread; + goto fail_free_reader_line_wq; } spin_lock_init(&gc->lock); spin_lock_init(&gc->w_lock); + spin_lock_init(&gc->r_lock); + + sema_init(&gc->gc_sem, 128); + INIT_LIST_HEAD(&gc->w_list); + INIT_LIST_HEAD(&gc->r_list); return 0; +fail_free_reader_line_wq: + destroy_workqueue(gc->gc_line_reader_wq); +fail_free_reader_kthread: + kthread_stop(gc->gc_reader_ts); fail_free_writer_kthread: kthread_stop(gc->gc_writer_ts); fail_free_main_kthread: @@ -540,6 +626,7 @@ void pblk_gc_exit(struct pblk *pblk) struct pblk_gc *gc = &pblk->gc; flush_workqueue(gc->gc_reader_wq); + flush_workqueue(gc->gc_line_reader_wq); del_timer(&gc->gc_timer); pblk_gc_stop(pblk, 1); @@ -547,9 +634,15 @@ void pblk_gc_exit(struct pblk *pblk) if (gc->gc_ts) kthread_stop(gc->gc_ts); - if (pblk->gc.gc_reader_wq) - destroy_workqueue(pblk->gc.gc_reader_wq); + if (gc->gc_reader_wq) + destroy_workqueue(gc->gc_reader_wq); + + if (gc->gc_line_reader_wq) + destroy_workqueue(gc->gc_line_reader_wq); if (gc->gc_writer_ts) kthread_stop(gc->gc_writer_ts); + + if (gc->gc_reader_ts) + kthread_stop(gc->gc_reader_ts); } diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c index ae8cd6d5af8b..1b0f61233c21 100644 --- a/drivers/lightnvm/pblk-init.c +++ b/drivers/lightnvm/pblk-init.c @@ -20,9 +20,10 @@ #include "pblk.h" -static struct kmem_cache *pblk_blk_ws_cache, *pblk_rec_cache, *pblk_r_rq_cache, - *pblk_w_rq_cache, *pblk_line_meta_cache; +static struct kmem_cache *pblk_blk_ws_cache, *pblk_rec_cache, *pblk_g_rq_cache, + *pblk_w_rq_cache, *pblk_line_meta_cache; static DECLARE_RWSEM(pblk_lock); +struct bio_set *pblk_bio_set; static int pblk_rw_io(struct request_queue *q, struct pblk *pblk, struct bio *bio) @@ -33,7 +34,7 @@ static int pblk_rw_io(struct request_queue *q, struct pblk *pblk, * constraint. Writes can be of arbitrary size. */ if (bio_data_dir(bio) == READ) { - blk_queue_split(q, &bio, q->bio_split); + blk_queue_split(q, &bio); ret = pblk_submit_read(pblk, bio); if (ret == NVM_IO_DONE && bio_flagged(bio, BIO_CLONED)) bio_put(bio); @@ -46,7 +47,7 @@ static int pblk_rw_io(struct request_queue *q, struct pblk *pblk, * available for user I/O. */ if (unlikely(pblk_get_secs(bio) >= pblk_rl_sysfs_rate_show(&pblk->rl))) - blk_queue_split(q, &bio, q->bio_split); + blk_queue_split(q, &bio); return pblk_write_to_cache(pblk, bio, PBLK_IOTYPE_USER); } @@ -199,9 +200,9 @@ static int pblk_init_global_caches(struct pblk *pblk) return -ENOMEM; } - pblk_r_rq_cache = kmem_cache_create("pblk_r_rq", pblk_r_rq_size, + pblk_g_rq_cache = kmem_cache_create("pblk_g_rq", pblk_g_rq_size, 0, 0, NULL); - if (!pblk_r_rq_cache) { + if (!pblk_g_rq_cache) { kmem_cache_destroy(pblk_blk_ws_cache); kmem_cache_destroy(pblk_rec_cache); up_write(&pblk_lock); @@ -213,7 +214,7 @@ static int pblk_init_global_caches(struct pblk *pblk) if (!pblk_w_rq_cache) { kmem_cache_destroy(pblk_blk_ws_cache); kmem_cache_destroy(pblk_rec_cache); - kmem_cache_destroy(pblk_r_rq_cache); + kmem_cache_destroy(pblk_g_rq_cache); up_write(&pblk_lock); return -ENOMEM; } @@ -225,7 +226,7 @@ static int pblk_init_global_caches(struct pblk *pblk) if (!pblk_line_meta_cache) { kmem_cache_destroy(pblk_blk_ws_cache); kmem_cache_destroy(pblk_rec_cache); - kmem_cache_destroy(pblk_r_rq_cache); + kmem_cache_destroy(pblk_g_rq_cache); kmem_cache_destroy(pblk_w_rq_cache); up_write(&pblk_lock); return -ENOMEM; @@ -239,27 +240,10 @@ static int pblk_core_init(struct pblk *pblk) { struct nvm_tgt_dev *dev = pblk->dev; struct nvm_geo *geo = &dev->geo; - int max_write_ppas; - int mod; - pblk->min_write_pgs = geo->sec_per_pl * (geo->sec_size / PAGE_SIZE); - max_write_ppas = pblk->min_write_pgs * geo->nr_luns; - pblk->max_write_pgs = (max_write_ppas < nvm_max_phys_sects(dev)) ? - max_write_ppas : nvm_max_phys_sects(dev); pblk->pgs_in_buffer = NVM_MEM_PAGE_WRITE * geo->sec_per_pg * geo->nr_planes * geo->nr_luns; - if (pblk->max_write_pgs > PBLK_MAX_REQ_ADDRS) { - pr_err("pblk: cannot support device max_phys_sect\n"); - return -EINVAL; - } - - div_u64_rem(geo->sec_per_blk, pblk->min_write_pgs, &mod); - if (mod) { - pr_err("pblk: bad configuration of sectors/pages\n"); - return -EINVAL; - } - if (pblk_init_global_caches(pblk)) return -ENOMEM; @@ -267,7 +251,7 @@ static int pblk_core_init(struct pblk *pblk) if (!pblk->page_pool) return -ENOMEM; - pblk->line_ws_pool = mempool_create_slab_pool(geo->nr_luns, + pblk->line_ws_pool = mempool_create_slab_pool(PBLK_WS_POOL_SIZE, pblk_blk_ws_cache); if (!pblk->line_ws_pool) goto free_page_pool; @@ -276,41 +260,51 @@ static int pblk_core_init(struct pblk *pblk) if (!pblk->rec_pool) goto free_blk_ws_pool; - pblk->r_rq_pool = mempool_create_slab_pool(64, pblk_r_rq_cache); - if (!pblk->r_rq_pool) + pblk->g_rq_pool = mempool_create_slab_pool(PBLK_READ_REQ_POOL_SIZE, + pblk_g_rq_cache); + if (!pblk->g_rq_pool) goto free_rec_pool; - pblk->w_rq_pool = mempool_create_slab_pool(64, pblk_w_rq_cache); + pblk->w_rq_pool = mempool_create_slab_pool(geo->nr_luns * 2, + pblk_w_rq_cache); if (!pblk->w_rq_pool) - goto free_r_rq_pool; + goto free_g_rq_pool; pblk->line_meta_pool = - mempool_create_slab_pool(16, pblk_line_meta_cache); + mempool_create_slab_pool(PBLK_META_POOL_SIZE, + pblk_line_meta_cache); if (!pblk->line_meta_pool) goto free_w_rq_pool; - pblk->kw_wq = alloc_workqueue("pblk-aux-wq", - WQ_MEM_RECLAIM | WQ_UNBOUND, 1); - if (!pblk->kw_wq) + pblk->close_wq = alloc_workqueue("pblk-close-wq", + WQ_MEM_RECLAIM | WQ_UNBOUND, PBLK_NR_CLOSE_JOBS); + if (!pblk->close_wq) goto free_line_meta_pool; + pblk->bb_wq = alloc_workqueue("pblk-bb-wq", + WQ_MEM_RECLAIM | WQ_UNBOUND, 0); + if (!pblk->bb_wq) + goto free_close_wq; + if (pblk_set_ppaf(pblk)) - goto free_kw_wq; + goto free_bb_wq; if (pblk_rwb_init(pblk)) - goto free_kw_wq; + goto free_bb_wq; INIT_LIST_HEAD(&pblk->compl_list); return 0; -free_kw_wq: - destroy_workqueue(pblk->kw_wq); +free_bb_wq: + destroy_workqueue(pblk->bb_wq); +free_close_wq: + destroy_workqueue(pblk->close_wq); free_line_meta_pool: mempool_destroy(pblk->line_meta_pool); free_w_rq_pool: mempool_destroy(pblk->w_rq_pool); -free_r_rq_pool: - mempool_destroy(pblk->r_rq_pool); +free_g_rq_pool: + mempool_destroy(pblk->g_rq_pool); free_rec_pool: mempool_destroy(pblk->rec_pool); free_blk_ws_pool: @@ -322,19 +316,22 @@ free_page_pool: static void pblk_core_free(struct pblk *pblk) { - if (pblk->kw_wq) - destroy_workqueue(pblk->kw_wq); + if (pblk->close_wq) + destroy_workqueue(pblk->close_wq); + + if (pblk->bb_wq) + destroy_workqueue(pblk->bb_wq); mempool_destroy(pblk->page_pool); mempool_destroy(pblk->line_ws_pool); mempool_destroy(pblk->rec_pool); - mempool_destroy(pblk->r_rq_pool); + mempool_destroy(pblk->g_rq_pool); mempool_destroy(pblk->w_rq_pool); mempool_destroy(pblk->line_meta_pool); kmem_cache_destroy(pblk_blk_ws_cache); kmem_cache_destroy(pblk_rec_cache); - kmem_cache_destroy(pblk_r_rq_cache); + kmem_cache_destroy(pblk_g_rq_cache); kmem_cache_destroy(pblk_w_rq_cache); kmem_cache_destroy(pblk_line_meta_cache); } @@ -344,6 +341,12 @@ static void pblk_luns_free(struct pblk *pblk) kfree(pblk->luns); } +static void pblk_free_line_bitmaps(struct pblk_line *line) +{ + kfree(line->blk_bitmap); + kfree(line->erase_bitmap); +} + static void pblk_lines_free(struct pblk *pblk) { struct pblk_line_mgmt *l_mg = &pblk->l_mg; @@ -355,8 +358,7 @@ static void pblk_lines_free(struct pblk *pblk) line = &pblk->lines[i]; pblk_line_free(pblk, line); - kfree(line->blk_bitmap); - kfree(line->erase_bitmap); + pblk_free_line_bitmaps(line); } spin_unlock(&l_mg->free_lock); } @@ -368,11 +370,15 @@ static void pblk_line_meta_free(struct pblk *pblk) kfree(l_mg->bb_template); kfree(l_mg->bb_aux); + kfree(l_mg->vsc_list); + spin_lock(&l_mg->free_lock); for (i = 0; i < PBLK_DATA_LINES; i++) { - pblk_mfree(l_mg->sline_meta[i].meta, l_mg->smeta_alloc_type); - pblk_mfree(l_mg->eline_meta[i].meta, l_mg->emeta_alloc_type); + kfree(l_mg->sline_meta[i]); + pblk_mfree(l_mg->eline_meta[i]->buf, l_mg->emeta_alloc_type); + kfree(l_mg->eline_meta[i]); } + spin_unlock(&l_mg->free_lock); kfree(pblk->lines); } @@ -411,13 +417,31 @@ out: return ret; } -static int pblk_bb_line(struct pblk *pblk, struct pblk_line *line) +static int pblk_bb_line(struct pblk *pblk, struct pblk_line *line, + int blk_per_line) { - struct pblk_line_meta *lm = &pblk->lm; + struct nvm_tgt_dev *dev = pblk->dev; + struct nvm_geo *geo = &dev->geo; struct pblk_lun *rlun; int bb_cnt = 0; int i; + for (i = 0; i < blk_per_line; i++) { + rlun = &pblk->luns[i]; + if (rlun->bb_list[line->id] == NVM_BLK_T_FREE) + continue; + + set_bit(pblk_ppa_to_pos(geo, rlun->bppa), line->blk_bitmap); + bb_cnt++; + } + + return bb_cnt; +} + +static int pblk_alloc_line_bitmaps(struct pblk *pblk, struct pblk_line *line) +{ + struct pblk_line_meta *lm = &pblk->lm; + line->blk_bitmap = kzalloc(lm->blk_bitmap_len, GFP_KERNEL); if (!line->blk_bitmap) return -ENOMEM; @@ -428,16 +452,7 @@ static int pblk_bb_line(struct pblk *pblk, struct pblk_line *line) return -ENOMEM; } - for (i = 0; i < lm->blk_per_line; i++) { - rlun = &pblk->luns[i]; - if (rlun->bb_list[line->id] == NVM_BLK_T_FREE) - continue; - - set_bit(i, line->blk_bitmap); - bb_cnt++; - } - - return bb_cnt; + return 0; } static int pblk_luns_init(struct pblk *pblk, struct ppa_addr *luns) @@ -505,12 +520,32 @@ static int pblk_lines_configure(struct pblk *pblk, int flags) } /* See comment over struct line_emeta definition */ -static unsigned int calc_emeta_len(struct pblk *pblk, struct pblk_line_meta *lm) +static unsigned int calc_emeta_len(struct pblk *pblk) { - return (sizeof(struct line_emeta) + - ((lm->sec_per_line - lm->emeta_sec) * sizeof(u64)) + - (pblk->l_mg.nr_lines * sizeof(u32)) + - lm->blk_bitmap_len); + struct pblk_line_meta *lm = &pblk->lm; + struct pblk_line_mgmt *l_mg = &pblk->l_mg; + struct nvm_tgt_dev *dev = pblk->dev; + struct nvm_geo *geo = &dev->geo; + + /* Round to sector size so that lba_list starts on its own sector */ + lm->emeta_sec[1] = DIV_ROUND_UP( + sizeof(struct line_emeta) + lm->blk_bitmap_len, + geo->sec_size); + lm->emeta_len[1] = lm->emeta_sec[1] * geo->sec_size; + + /* Round to sector size so that vsc_list starts on its own sector */ + lm->dsec_per_line = lm->sec_per_line - lm->emeta_sec[0]; + lm->emeta_sec[2] = DIV_ROUND_UP(lm->dsec_per_line * sizeof(u64), + geo->sec_size); + lm->emeta_len[2] = lm->emeta_sec[2] * geo->sec_size; + + lm->emeta_sec[3] = DIV_ROUND_UP(l_mg->nr_lines * sizeof(u32), + geo->sec_size); + lm->emeta_len[3] = lm->emeta_sec[3] * geo->sec_size; + + lm->vsc_list_len = l_mg->nr_lines * sizeof(u32); + + return (lm->emeta_len[1] + lm->emeta_len[2] + lm->emeta_len[3]); } static void pblk_set_provision(struct pblk *pblk, long nr_free_blks) @@ -534,6 +569,78 @@ static void pblk_set_provision(struct pblk *pblk, long nr_free_blks) atomic_set(&pblk->rl.free_blocks, nr_free_blks); } +static int pblk_lines_alloc_metadata(struct pblk *pblk) +{ + struct pblk_line_mgmt *l_mg = &pblk->l_mg; + struct pblk_line_meta *lm = &pblk->lm; + int i; + + /* smeta is always small enough to fit on a kmalloc memory allocation, + * emeta depends on the number of LUNs allocated to the pblk instance + */ + for (i = 0; i < PBLK_DATA_LINES; i++) { + l_mg->sline_meta[i] = kmalloc(lm->smeta_len, GFP_KERNEL); + if (!l_mg->sline_meta[i]) + goto fail_free_smeta; + } + + /* emeta allocates three different buffers for managing metadata with + * in-memory and in-media layouts + */ + for (i = 0; i < PBLK_DATA_LINES; i++) { + struct pblk_emeta *emeta; + + emeta = kmalloc(sizeof(struct pblk_emeta), GFP_KERNEL); + if (!emeta) + goto fail_free_emeta; + + if (lm->emeta_len[0] > KMALLOC_MAX_CACHE_SIZE) { + l_mg->emeta_alloc_type = PBLK_VMALLOC_META; + + emeta->buf = vmalloc(lm->emeta_len[0]); + if (!emeta->buf) { + kfree(emeta); + goto fail_free_emeta; + } + + emeta->nr_entries = lm->emeta_sec[0]; + l_mg->eline_meta[i] = emeta; + } else { + l_mg->emeta_alloc_type = PBLK_KMALLOC_META; + + emeta->buf = kmalloc(lm->emeta_len[0], GFP_KERNEL); + if (!emeta->buf) { + kfree(emeta); + goto fail_free_emeta; + } + + emeta->nr_entries = lm->emeta_sec[0]; + l_mg->eline_meta[i] = emeta; + } + } + + l_mg->vsc_list = kcalloc(l_mg->nr_lines, sizeof(__le32), GFP_KERNEL); + if (!l_mg->vsc_list) + goto fail_free_emeta; + + for (i = 0; i < l_mg->nr_lines; i++) + l_mg->vsc_list[i] = cpu_to_le32(EMPTY_ENTRY); + + return 0; + +fail_free_emeta: + while (--i >= 0) { + vfree(l_mg->eline_meta[i]->buf); + kfree(l_mg->eline_meta[i]); + } + +fail_free_smeta: + for (i = 0; i < PBLK_DATA_LINES; i++) + kfree(l_mg->sline_meta[i]); + + return -ENOMEM; +} + static int pblk_lines_init(struct pblk *pblk) { struct nvm_tgt_dev *dev = pblk->dev; @@ -542,10 +649,32 @@ static int pblk_lines_init(struct pblk *pblk) struct pblk_line_meta *lm = &pblk->lm; struct pblk_line *line; unsigned int smeta_len, emeta_len; - long nr_bad_blks, nr_meta_blks, nr_free_blks; - int bb_distance; - int i; - int ret; + long nr_bad_blks, nr_free_blks; + int bb_distance, max_write_ppas, mod; + int i, ret; + + pblk->min_write_pgs = geo->sec_per_pl * (geo->sec_size / PAGE_SIZE); + max_write_ppas = pblk->min_write_pgs * geo->nr_luns; + pblk->max_write_pgs = (max_write_ppas < nvm_max_phys_sects(dev)) ? + max_write_ppas : nvm_max_phys_sects(dev); + pblk_set_sec_per_write(pblk, pblk->min_write_pgs); + + if (pblk->max_write_pgs > PBLK_MAX_REQ_ADDRS) { + pr_err("pblk: cannot support device max_phys_sect\n"); + return -EINVAL; + } + + div_u64_rem(geo->sec_per_blk, pblk->min_write_pgs, &mod); + if (mod) { + pr_err("pblk: bad configuration of sectors/pages\n"); + return -EINVAL; + } + + l_mg->nr_lines = geo->blks_per_lun; + l_mg->log_line = l_mg->data_line = NULL; + l_mg->l_seq_nr = l_mg->d_seq_nr = 0; + l_mg->nr_free_lines = 0; + bitmap_zero(&l_mg->meta_bitmap, PBLK_DATA_LINES); lm->sec_per_line = geo->sec_per_blk * geo->nr_luns; lm->blk_per_line = geo->nr_luns; @@ -554,20 +683,17 @@ static int pblk_lines_init(struct pblk *pblk) lm->lun_bitmap_len = BITS_TO_LONGS(geo->nr_luns) * sizeof(long); lm->high_thrs = lm->sec_per_line / 2; lm->mid_thrs = lm->sec_per_line / 4; + lm->meta_distance = (geo->nr_luns / 2) * pblk->min_write_pgs; /* Calculate necessary pages for smeta. See comment over struct * line_smeta definition */ - lm->smeta_len = sizeof(struct line_smeta) + - PBLK_LINE_NR_LUN_BITMAP * lm->lun_bitmap_len; - i = 1; add_smeta_page: lm->smeta_sec = i * geo->sec_per_pl; lm->smeta_len = lm->smeta_sec * geo->sec_size; - smeta_len = sizeof(struct line_smeta) + - PBLK_LINE_NR_LUN_BITMAP * lm->lun_bitmap_len; + smeta_len = sizeof(struct line_smeta) + lm->lun_bitmap_len; if (smeta_len > lm->smeta_len) { i++; goto add_smeta_page; @@ -578,66 +704,28 @@ add_smeta_page: */ i = 1; add_emeta_page: - lm->emeta_sec = i * geo->sec_per_pl; - lm->emeta_len = lm->emeta_sec * geo->sec_size; + lm->emeta_sec[0] = i * geo->sec_per_pl; + lm->emeta_len[0] = lm->emeta_sec[0] * geo->sec_size; - emeta_len = calc_emeta_len(pblk, lm); - if (emeta_len > lm->emeta_len) { + emeta_len = calc_emeta_len(pblk); + if (emeta_len > lm->emeta_len[0]) { i++; goto add_emeta_page; } - lm->emeta_bb = geo->nr_luns - i; - - nr_meta_blks = (lm->smeta_sec + lm->emeta_sec + - (geo->sec_per_blk / 2)) / geo->sec_per_blk; - lm->min_blk_line = nr_meta_blks + 1; - - l_mg->nr_lines = geo->blks_per_lun; - l_mg->log_line = l_mg->data_line = NULL; - l_mg->l_seq_nr = l_mg->d_seq_nr = 0; - l_mg->nr_free_lines = 0; - bitmap_zero(&l_mg->meta_bitmap, PBLK_DATA_LINES); - /* smeta is always small enough to fit on a kmalloc memory allocation, - * emeta depends on the number of LUNs allocated to the pblk instance - */ - l_mg->smeta_alloc_type = PBLK_KMALLOC_META; - for (i = 0; i < PBLK_DATA_LINES; i++) { - l_mg->sline_meta[i].meta = kmalloc(lm->smeta_len, GFP_KERNEL); - if (!l_mg->sline_meta[i].meta) - while (--i >= 0) { - kfree(l_mg->sline_meta[i].meta); - ret = -ENOMEM; - goto fail; - } + lm->emeta_bb = geo->nr_luns - i; + lm->min_blk_line = 1 + DIV_ROUND_UP(lm->smeta_sec + lm->emeta_sec[0], + geo->sec_per_blk); + if (lm->min_blk_line > lm->blk_per_line) { + pr_err("pblk: config. not supported. Min. LUN in line:%d\n", + lm->blk_per_line); + ret = -EINVAL; + goto fail; } - if (lm->emeta_len > KMALLOC_MAX_CACHE_SIZE) { - l_mg->emeta_alloc_type = PBLK_VMALLOC_META; - - for (i = 0; i < PBLK_DATA_LINES; i++) { - l_mg->eline_meta[i].meta = vmalloc(lm->emeta_len); - if (!l_mg->eline_meta[i].meta) - while (--i >= 0) { - vfree(l_mg->eline_meta[i].meta); - ret = -ENOMEM; - goto fail; - } - } - } else { - l_mg->emeta_alloc_type = PBLK_KMALLOC_META; - - for (i = 0; i < PBLK_DATA_LINES; i++) { - l_mg->eline_meta[i].meta = - kmalloc(lm->emeta_len, GFP_KERNEL); - if (!l_mg->eline_meta[i].meta) - while (--i >= 0) { - kfree(l_mg->eline_meta[i].meta); - ret = -ENOMEM; - goto fail; - } - } - } + ret = pblk_lines_alloc_metadata(pblk); + if (ret) + goto fail; l_mg->bb_template = kzalloc(lm->sec_bitmap_len, GFP_KERNEL); if (!l_mg->bb_template) { @@ -664,11 +752,14 @@ add_emeta_page: INIT_LIST_HEAD(&l_mg->gc_low_list); INIT_LIST_HEAD(&l_mg->gc_empty_list); + INIT_LIST_HEAD(&l_mg->emeta_list); + l_mg->gc_lists[0] = &l_mg->gc_high_list; l_mg->gc_lists[1] = &l_mg->gc_mid_list; l_mg->gc_lists[2] = &l_mg->gc_low_list; spin_lock_init(&l_mg->free_lock); + spin_lock_init(&l_mg->close_lock); spin_lock_init(&l_mg->gc_lock); pblk->lines = kcalloc(l_mg->nr_lines, sizeof(struct pblk_line), @@ -689,10 +780,16 @@ add_emeta_page: line->type = PBLK_LINETYPE_FREE; line->state = PBLK_LINESTATE_FREE; line->gc_group = PBLK_LINEGC_NONE; + line->vsc = &l_mg->vsc_list[i]; spin_lock_init(&line->lock); - nr_bad_blks = pblk_bb_line(pblk, line); + ret = pblk_alloc_line_bitmaps(pblk, line); + if (ret) + goto fail_free_lines; + + nr_bad_blks = pblk_bb_line(pblk, line, lm->blk_per_line); if (nr_bad_blks < 0 || nr_bad_blks > lm->blk_per_line) { + pblk_free_line_bitmaps(line); ret = -EINVAL; goto fail_free_lines; } @@ -713,24 +810,20 @@ add_emeta_page: pblk_set_provision(pblk, nr_free_blks); - sema_init(&pblk->erase_sem, 1); - /* Cleanup per-LUN bad block lists - managed within lines on run-time */ for (i = 0; i < geo->nr_luns; i++) kfree(pblk->luns[i].bb_list); return 0; fail_free_lines: - kfree(pblk->lines); + while (--i >= 0) + pblk_free_line_bitmaps(&pblk->lines[i]); fail_free_bb_aux: kfree(l_mg->bb_aux); fail_free_bb_template: kfree(l_mg->bb_template); fail_free_meta: - for (i = 0; i < PBLK_DATA_LINES; i++) { - pblk_mfree(l_mg->sline_meta[i].meta, l_mg->smeta_alloc_type); - pblk_mfree(l_mg->eline_meta[i].meta, l_mg->emeta_alloc_type); - } + pblk_line_meta_free(pblk); fail: for (i = 0; i < geo->nr_luns; i++) kfree(pblk->luns[i].bb_list); @@ -754,6 +847,15 @@ static int pblk_writer_init(struct pblk *pblk) static void pblk_writer_stop(struct pblk *pblk) { + /* The pipeline must be stopped and the write buffer emptied before the + * write thread is stopped + */ + WARN(pblk_rb_read_count(&pblk->rwb), + "Stopping not fully persisted write buffer\n"); + + WARN(pblk_rb_sync_count(&pblk->rwb), + "Stopping not fully synced write buffer\n"); + if (pblk->writer_ts) kthread_stop(pblk->writer_ts); del_timer(&pblk->wtimer); @@ -772,10 +874,9 @@ static void pblk_free(struct pblk *pblk) static void pblk_tear_down(struct pblk *pblk) { - pblk_flush_writer(pblk); + pblk_pipeline_stop(pblk); pblk_writer_stop(pblk); pblk_rb_sync_l2p(&pblk->rwb); - pblk_recov_pad(pblk); pblk_rwb_free(pblk); pblk_rl_free(&pblk->rl); @@ -821,6 +922,7 @@ static void *pblk_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk, pblk->dev = dev; pblk->disk = tdisk; + pblk->state = PBLK_STATE_RUNNING; spin_lock_init(&pblk->trans_lock); spin_lock_init(&pblk->lock); @@ -836,8 +938,8 @@ static void *pblk_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk, atomic_long_set(&pblk->req_writes, 0); atomic_long_set(&pblk->sub_writes, 0); atomic_long_set(&pblk->sync_writes, 0); - atomic_long_set(&pblk->compl_writes, 0); atomic_long_set(&pblk->inflight_reads, 0); + atomic_long_set(&pblk->cache_reads, 0); atomic_long_set(&pblk->sync_reads, 0); atomic_long_set(&pblk->recov_writes, 0); atomic_long_set(&pblk->recov_writes, 0); @@ -946,11 +1048,20 @@ static struct nvm_tgt_type tt_pblk = { static int __init pblk_module_init(void) { - return nvm_register_tgt_type(&tt_pblk); + int ret; + + pblk_bio_set = bioset_create(BIO_POOL_SIZE, 0, 0); + if (!pblk_bio_set) + return -ENOMEM; + ret = nvm_register_tgt_type(&tt_pblk); + if (ret) + bioset_free(pblk_bio_set); + return ret; } static void pblk_module_exit(void) { + bioset_free(pblk_bio_set); nvm_unregister_tgt_type(&tt_pblk); } diff --git a/drivers/lightnvm/pblk-map.c b/drivers/lightnvm/pblk-map.c index 17c16955284d..fddb924f6dde 100644 --- a/drivers/lightnvm/pblk-map.c +++ b/drivers/lightnvm/pblk-map.c @@ -25,9 +25,9 @@ static void pblk_map_page_data(struct pblk *pblk, unsigned int sentry, unsigned int valid_secs) { struct pblk_line *line = pblk_line_get_data(pblk); - struct line_emeta *emeta = line->emeta; + struct pblk_emeta *emeta = line->emeta; struct pblk_w_ctx *w_ctx; - __le64 *lba_list = pblk_line_emeta_to_lbas(emeta); + __le64 *lba_list = emeta_to_lbas(pblk, emeta->buf); u64 paddr; int nr_secs = pblk->min_write_pgs; int i; @@ -51,18 +51,20 @@ static void pblk_map_page_data(struct pblk *pblk, unsigned int sentry, w_ctx->ppa = ppa_list[i]; meta_list[i].lba = cpu_to_le64(w_ctx->lba); lba_list[paddr] = cpu_to_le64(w_ctx->lba); - le64_add_cpu(&line->emeta->nr_valid_lbas, 1); + line->nr_valid_lbas++; } else { - meta_list[i].lba = cpu_to_le64(ADDR_EMPTY); - lba_list[paddr] = cpu_to_le64(ADDR_EMPTY); - pblk_map_pad_invalidate(pblk, line, paddr); + __le64 addr_empty = cpu_to_le64(ADDR_EMPTY); + + lba_list[paddr] = meta_list[i].lba = addr_empty; + __pblk_map_invalidate(pblk, line, paddr); } } if (pblk_line_is_full(line)) { - line = pblk_line_replace_data(pblk); - if (!line) - return; + struct pblk_line *prev_line = line; + + pblk_line_replace_data(pblk); + pblk_line_close_meta(pblk, prev_line); } pblk_down_rq(pblk, ppa_list, nr_secs, lun_bitmap); @@ -91,8 +93,9 @@ void pblk_map_erase_rq(struct pblk *pblk, struct nvm_rq *rqd, { struct nvm_tgt_dev *dev = pblk->dev; struct nvm_geo *geo = &dev->geo; - struct pblk_line *e_line = pblk_line_get_data_next(pblk); + struct pblk_line_meta *lm = &pblk->lm; struct pblk_sec_meta *meta_list = rqd->meta_list; + struct pblk_line *e_line, *d_line; unsigned int map_secs; int min = pblk->min_write_pgs; int i, erase_lun; @@ -102,35 +105,63 @@ void pblk_map_erase_rq(struct pblk *pblk, struct nvm_rq *rqd, pblk_map_page_data(pblk, sentry + i, &rqd->ppa_list[i], lun_bitmap, &meta_list[i], map_secs); - erase_lun = rqd->ppa_list[i].g.lun * geo->nr_chnls + - rqd->ppa_list[i].g.ch; + erase_lun = pblk_ppa_to_pos(geo, rqd->ppa_list[i]); - if (!test_bit(erase_lun, e_line->erase_bitmap)) { - if (down_trylock(&pblk->erase_sem)) - continue; + /* line can change after page map. We might also be writing the + * last line. + */ + e_line = pblk_line_get_erase(pblk); + if (!e_line) + return pblk_map_rq(pblk, rqd, sentry, lun_bitmap, + valid_secs, i + min); + spin_lock(&e_line->lock); + if (!test_bit(erase_lun, e_line->erase_bitmap)) { set_bit(erase_lun, e_line->erase_bitmap); atomic_dec(&e_line->left_eblks); + *erase_ppa = rqd->ppa_list[i]; erase_ppa->g.blk = e_line->id; + spin_unlock(&e_line->lock); + /* Avoid evaluating e_line->left_eblks */ return pblk_map_rq(pblk, rqd, sentry, lun_bitmap, valid_secs, i + min); } + spin_unlock(&e_line->lock); } - /* Erase blocks that are bad in this line but might not be in next */ - if (unlikely(ppa_empty(*erase_ppa))) { - struct pblk_line_meta *lm = &pblk->lm; + d_line = pblk_line_get_data(pblk); + + /* line can change after page map. We might also be writing the + * last line. + */ + e_line = pblk_line_get_erase(pblk); + if (!e_line) + return; - i = find_first_zero_bit(e_line->erase_bitmap, lm->blk_per_line); - if (i == lm->blk_per_line) + /* Erase blocks that are bad in this line but might not be in next */ + if (unlikely(ppa_empty(*erase_ppa)) && + bitmap_weight(d_line->blk_bitmap, lm->blk_per_line)) { + int bit = -1; + +retry: + bit = find_next_bit(d_line->blk_bitmap, + lm->blk_per_line, bit + 1); + if (bit >= lm->blk_per_line) return; - set_bit(i, e_line->erase_bitmap); + spin_lock(&e_line->lock); + if (test_bit(bit, e_line->erase_bitmap)) { + spin_unlock(&e_line->lock); + goto retry; + } + spin_unlock(&e_line->lock); + + set_bit(bit, e_line->erase_bitmap); atomic_dec(&e_line->left_eblks); - *erase_ppa = pblk->luns[i].bppa; /* set ch and lun */ + *erase_ppa = pblk->luns[bit].bppa; /* set ch and lun */ erase_ppa->g.blk = e_line->id; } } diff --git a/drivers/lightnvm/pblk-rb.c b/drivers/lightnvm/pblk-rb.c index 045384ddc1f9..5ecc154f6831 100644 --- a/drivers/lightnvm/pblk-rb.c +++ b/drivers/lightnvm/pblk-rb.c @@ -150,6 +150,7 @@ try: /* Release flags on context. Protect from writes and reads */ smp_store_release(&w_ctx->flags, PBLK_WRITABLE_ENTRY); pblk_ppa_set_empty(&w_ctx->ppa); + w_ctx->lba = ADDR_EMPTY; } #define pblk_rb_ring_count(head, tail, size) CIRC_CNT(head, tail, size) @@ -180,6 +181,14 @@ unsigned int pblk_rb_read_count(struct pblk_rb *rb) return pblk_rb_ring_count(mem, subm, rb->nr_entries); } +unsigned int pblk_rb_sync_count(struct pblk_rb *rb) +{ + unsigned int mem = READ_ONCE(rb->mem); + unsigned int sync = READ_ONCE(rb->sync); + + return pblk_rb_ring_count(mem, sync, rb->nr_entries); +} + unsigned int pblk_rb_read_commit(struct pblk_rb *rb, unsigned int nr_entries) { unsigned int subm; @@ -199,12 +208,22 @@ static int __pblk_rb_update_l2p(struct pblk_rb *rb, unsigned int *l2p_upd, struct pblk_line *line; struct pblk_rb_entry *entry; struct pblk_w_ctx *w_ctx; + unsigned int user_io = 0, gc_io = 0; unsigned int i; + int flags; for (i = 0; i < to_update; i++) { entry = &rb->entries[*l2p_upd]; w_ctx = &entry->w_ctx; + flags = READ_ONCE(entry->w_ctx.flags); + if (flags & PBLK_IOTYPE_USER) + user_io++; + else if (flags & PBLK_IOTYPE_GC) + gc_io++; + else + WARN(1, "pblk: unknown IO type\n"); + pblk_update_map_dev(pblk, w_ctx->lba, w_ctx->ppa, entry->cacheline); @@ -214,6 +233,8 @@ static int __pblk_rb_update_l2p(struct pblk_rb *rb, unsigned int *l2p_upd, *l2p_upd = (*l2p_upd + 1) & (rb->nr_entries - 1); } + pblk_rl_out(&pblk->rl, user_io, gc_io); + return 0; } @@ -357,6 +378,9 @@ static int pblk_rb_sync_point_set(struct pblk_rb *rb, struct bio *bio, /* Protect syncs */ smp_store_release(&rb->sync_point, sync_point); + if (!bio) + return 0; + spin_lock_irq(&rb->s_lock); bio_list_add(&entry->w_ctx.bios, bio); spin_unlock_irq(&rb->s_lock); @@ -395,6 +419,17 @@ static int pblk_rb_may_write(struct pblk_rb *rb, unsigned int nr_entries, return 1; } +void pblk_rb_flush(struct pblk_rb *rb) +{ + struct pblk *pblk = container_of(rb, struct pblk, rwb); + unsigned int mem = READ_ONCE(rb->mem); + + if (pblk_rb_sync_point_set(rb, NULL, mem)) + return; + + pblk_write_should_kick(pblk); +} + static int pblk_rb_may_write_flush(struct pblk_rb *rb, unsigned int nr_entries, unsigned int *pos, struct bio *bio, int *io_ret) @@ -431,15 +466,16 @@ int pblk_rb_may_write_user(struct pblk_rb *rb, struct bio *bio, unsigned int nr_entries, unsigned int *pos) { struct pblk *pblk = container_of(rb, struct pblk, rwb); - int flush_done; + int io_ret; spin_lock(&rb->w_lock); - if (!pblk_rl_user_may_insert(&pblk->rl, nr_entries)) { + io_ret = pblk_rl_user_may_insert(&pblk->rl, nr_entries); + if (io_ret) { spin_unlock(&rb->w_lock); - return NVM_IO_REQUEUE; + return io_ret; } - if (!pblk_rb_may_write_flush(rb, nr_entries, pos, bio, &flush_done)) { + if (!pblk_rb_may_write_flush(rb, nr_entries, pos, bio, &io_ret)) { spin_unlock(&rb->w_lock); return NVM_IO_REQUEUE; } @@ -447,7 +483,7 @@ int pblk_rb_may_write_user(struct pblk_rb *rb, struct bio *bio, pblk_rl_user_in(&pblk->rl, nr_entries); spin_unlock(&rb->w_lock); - return flush_done; + return io_ret; } /* @@ -521,20 +557,18 @@ out: * This function is used by the write thread to form the write bio that will * persist data on the write buffer to the media. */ -unsigned int pblk_rb_read_to_bio(struct pblk_rb *rb, struct bio *bio, - struct pblk_c_ctx *c_ctx, - unsigned int pos, - unsigned int nr_entries, - unsigned int count) +unsigned int pblk_rb_read_to_bio(struct pblk_rb *rb, struct nvm_rq *rqd, + struct bio *bio, unsigned int pos, + unsigned int nr_entries, unsigned int count) { struct pblk *pblk = container_of(rb, struct pblk, rwb); + struct request_queue *q = pblk->dev->q; + struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd); struct pblk_rb_entry *entry; struct page *page; - unsigned int pad = 0, read = 0, to_read = nr_entries; - unsigned int user_io = 0, gc_io = 0; + unsigned int pad = 0, to_read = nr_entries; unsigned int i; int flags; - int ret; if (count < nr_entries) { pad = nr_entries - count; @@ -553,15 +587,10 @@ unsigned int pblk_rb_read_to_bio(struct pblk_rb *rb, struct bio *bio, */ try: flags = READ_ONCE(entry->w_ctx.flags); - if (!(flags & PBLK_WRITTEN_DATA)) + if (!(flags & PBLK_WRITTEN_DATA)) { + io_schedule(); goto try; - - if (flags & PBLK_IOTYPE_USER) - user_io++; - else if (flags & PBLK_IOTYPE_GC) - gc_io++; - else - WARN(1, "pblk: unknown IO type\n"); + } page = virt_to_page(entry->data); if (!page) { @@ -570,17 +599,17 @@ try: flags |= PBLK_SUBMITTED_ENTRY; /* Release flags on context. Protect from writes */ smp_store_release(&entry->w_ctx.flags, flags); - goto out; + return NVM_IO_ERR; } - ret = bio_add_page(bio, page, rb->seg_size, 0); - if (ret != rb->seg_size) { + if (bio_add_pc_page(q, bio, page, rb->seg_size, 0) != + rb->seg_size) { pr_err("pblk: could not add page to write bio\n"); flags &= ~PBLK_WRITTEN_DATA; flags |= PBLK_SUBMITTED_ENTRY; /* Release flags on context. Protect from writes */ smp_store_release(&entry->w_ctx.flags, flags); - goto out; + return NVM_IO_ERR; } if (flags & PBLK_FLUSH_ENTRY) { @@ -607,14 +636,19 @@ try: pos = (pos + 1) & (rb->nr_entries - 1); } - read = to_read; - pblk_rl_out(&pblk->rl, user_io, gc_io); + if (pad) { + if (pblk_bio_add_pages(pblk, bio, GFP_KERNEL, pad)) { + pr_err("pblk: could not pad page in write bio\n"); + return NVM_IO_ERR; + } + } + #ifdef CONFIG_NVM_DEBUG atomic_long_add(pad, &((struct pblk *) (container_of(rb, struct pblk, rwb)))->padded_writes); #endif -out: - return read; + + return NVM_IO_OK; } /* @@ -623,15 +657,17 @@ out: * be directed to disk. */ int pblk_rb_copy_to_bio(struct pblk_rb *rb, struct bio *bio, sector_t lba, - u64 pos, int bio_iter) + struct ppa_addr ppa, int bio_iter) { + struct pblk *pblk = container_of(rb, struct pblk, rwb); struct pblk_rb_entry *entry; struct pblk_w_ctx *w_ctx; + struct ppa_addr l2p_ppa; + u64 pos = pblk_addr_to_cacheline(ppa); void *data; int flags; int ret = 1; - spin_lock(&rb->w_lock); #ifdef CONFIG_NVM_DEBUG /* Caller must ensure that the access will not cause an overflow */ @@ -641,8 +677,14 @@ int pblk_rb_copy_to_bio(struct pblk_rb *rb, struct bio *bio, sector_t lba, w_ctx = &entry->w_ctx; flags = READ_ONCE(w_ctx->flags); + spin_lock(&rb->w_lock); + spin_lock(&pblk->trans_lock); + l2p_ppa = pblk_trans_map_get(pblk, lba); + spin_unlock(&pblk->trans_lock); + /* Check if the entry has been overwritten or is scheduled to be */ - if (w_ctx->lba != lba || flags & PBLK_WRITABLE_ENTRY) { + if (!pblk_ppa_comp(l2p_ppa, ppa) || w_ctx->lba != lba || + flags & PBLK_WRITABLE_ENTRY) { ret = 0; goto out; } diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c index 4a12f14d78c6..4e5c48f3de62 100644 --- a/drivers/lightnvm/pblk-read.c +++ b/drivers/lightnvm/pblk-read.c @@ -34,8 +34,7 @@ static int pblk_read_from_cache(struct pblk *pblk, struct bio *bio, BUG_ON(!pblk_addr_in_cache(ppa)); #endif - return pblk_rb_copy_to_bio(&pblk->rwb, bio, lba, - pblk_addr_to_cacheline(ppa), bio_iter); + return pblk_rb_copy_to_bio(&pblk->rwb, bio, lba, ppa, bio_iter); } static void pblk_read_ppalist_rq(struct pblk *pblk, struct nvm_rq *rqd, @@ -76,6 +75,9 @@ retry: } WARN_ON(test_and_set_bit(i, read_bitmap)); advanced_bio = 1; +#ifdef CONFIG_NVM_DEBUG + atomic_long_inc(&pblk->cache_reads); +#endif } else { /* Read from media non-cached sectors */ rqd->ppa_list[j++] = p; @@ -85,6 +87,11 @@ retry: bio_advance(bio, PBLK_EXPOSED_PAGE_SIZE); } + if (pblk_io_aligned(pblk, nr_secs)) + rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_SEQUENTIAL); + else + rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM); + #ifdef CONFIG_NVM_DEBUG atomic_long_add(nr_secs, &pblk->inflight_reads); #endif @@ -94,8 +101,6 @@ static int pblk_submit_read_io(struct pblk *pblk, struct nvm_rq *rqd) { int err; - rqd->flags = pblk_set_read_mode(pblk); - err = pblk_submit_io(pblk, rqd); if (err) return NVM_IO_ERR; @@ -107,27 +112,27 @@ static void pblk_end_io_read(struct nvm_rq *rqd) { struct pblk *pblk = rqd->private; struct nvm_tgt_dev *dev = pblk->dev; - struct pblk_r_ctx *r_ctx = nvm_rq_to_pdu(rqd); + struct pblk_g_ctx *r_ctx = nvm_rq_to_pdu(rqd); struct bio *bio = rqd->bio; if (rqd->error) pblk_log_read_err(pblk, rqd); #ifdef CONFIG_NVM_DEBUG else - WARN_ONCE(bio->bi_error, "pblk: corrupted read error\n"); + WARN_ONCE(bio->bi_status, "pblk: corrupted read error\n"); #endif - if (rqd->nr_ppas > 1) - nvm_dev_dma_free(dev->parent, rqd->ppa_list, rqd->dma_ppa_list); + nvm_dev_dma_free(dev->parent, rqd->meta_list, rqd->dma_meta_list); bio_put(bio); - if (r_ctx->orig_bio) { + if (r_ctx->private) { + struct bio *orig_bio = r_ctx->private; + #ifdef CONFIG_NVM_DEBUG - WARN_ONCE(r_ctx->orig_bio->bi_error, - "pblk: corrupted read bio\n"); + WARN_ONCE(orig_bio->bi_status, "pblk: corrupted read bio\n"); #endif - bio_endio(r_ctx->orig_bio); - bio_put(r_ctx->orig_bio); + bio_endio(orig_bio); + bio_put(orig_bio); } #ifdef CONFIG_NVM_DEBUG @@ -136,6 +141,7 @@ static void pblk_end_io_read(struct nvm_rq *rqd) #endif pblk_free_rqd(pblk, rqd, READ); + atomic_dec(&pblk->inflight_io); } static int pblk_fill_partial_read_bio(struct pblk *pblk, struct nvm_rq *rqd, @@ -173,6 +179,7 @@ static int pblk_fill_partial_read_bio(struct pblk *pblk, struct nvm_rq *rqd, rqd->bio = new_bio; rqd->nr_ppas = nr_holes; + rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM); rqd->end_io = NULL; if (unlikely(nr_secs > 1 && nr_holes == 1)) { @@ -280,9 +287,14 @@ retry: goto retry; } WARN_ON(test_and_set_bit(0, read_bitmap)); +#ifdef CONFIG_NVM_DEBUG + atomic_long_inc(&pblk->cache_reads); +#endif } else { rqd->ppa_addr = ppa; } + + rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM); } int pblk_submit_read(struct pblk *pblk, struct bio *bio) @@ -316,13 +328,16 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio) */ bio_init_idx = pblk_get_bi_idx(bio); + rqd->meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, + &rqd->dma_meta_list); + if (!rqd->meta_list) { + pr_err("pblk: not able to allocate ppa list\n"); + goto fail_rqd_free; + } + if (nr_secs > 1) { - rqd->ppa_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, - &rqd->dma_ppa_list); - if (!rqd->ppa_list) { - pr_err("pblk: not able to allocate ppa list\n"); - goto fail_rqd_free; - } + rqd->ppa_list = rqd->meta_list + pblk_dma_meta_size; + rqd->dma_ppa_list = rqd->dma_meta_list + pblk_dma_meta_size; pblk_read_ppalist_rq(pblk, rqd, &read_bitmap); } else { @@ -332,6 +347,7 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio) bio_get(bio); if (bitmap_full(&read_bitmap, nr_secs)) { bio_endio(bio); + atomic_inc(&pblk->inflight_io); pblk_end_io_read(rqd); return NVM_IO_OK; } @@ -339,17 +355,17 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio) /* All sectors are to be read from the device */ if (bitmap_empty(&read_bitmap, rqd->nr_ppas)) { struct bio *int_bio = NULL; - struct pblk_r_ctx *r_ctx = nvm_rq_to_pdu(rqd); + struct pblk_g_ctx *r_ctx = nvm_rq_to_pdu(rqd); /* Clone read bio to deal with read errors internally */ - int_bio = bio_clone_bioset(bio, GFP_KERNEL, fs_bio_set); + int_bio = bio_clone_fast(bio, GFP_KERNEL, pblk_bio_set); if (!int_bio) { pr_err("pblk: could not clone read bio\n"); return NVM_IO_ERR; } rqd->bio = int_bio; - r_ctx->orig_bio = bio; + r_ctx->private = bio; ret = pblk_submit_read_io(pblk, rqd); if (ret) { @@ -445,7 +461,6 @@ int pblk_submit_read_gc(struct pblk *pblk, u64 *lba_list, void *data, { struct nvm_tgt_dev *dev = pblk->dev; struct nvm_geo *geo = &dev->geo; - struct request_queue *q = dev->q; struct bio *bio; struct nvm_rq rqd; int ret, data_len; @@ -453,22 +468,19 @@ int pblk_submit_read_gc(struct pblk *pblk, u64 *lba_list, void *data, memset(&rqd, 0, sizeof(struct nvm_rq)); + rqd.meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, + &rqd.dma_meta_list); + if (!rqd.meta_list) + return NVM_IO_ERR; + if (nr_secs > 1) { - rqd.ppa_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, - &rqd.dma_ppa_list); - if (!rqd.ppa_list) - return NVM_IO_ERR; + rqd.ppa_list = rqd.meta_list + pblk_dma_meta_size; + rqd.dma_ppa_list = rqd.dma_meta_list + pblk_dma_meta_size; *secs_to_gc = read_ppalist_rq_gc(pblk, &rqd, line, lba_list, nr_secs); - if (*secs_to_gc == 1) { - struct ppa_addr ppa; - - ppa = rqd.ppa_list[0]; - nvm_dev_dma_free(dev->parent, rqd.ppa_list, - rqd.dma_ppa_list); - rqd.ppa_addr = ppa; - } + if (*secs_to_gc == 1) + rqd.ppa_addr = rqd.ppa_list[0]; } else { *secs_to_gc = read_rq_gc(pblk, &rqd, line, lba_list[0]); } @@ -477,7 +489,8 @@ int pblk_submit_read_gc(struct pblk *pblk, u64 *lba_list, void *data, goto out; data_len = (*secs_to_gc) * geo->sec_size; - bio = bio_map_kern(q, data, data_len, GFP_KERNEL); + bio = pblk_bio_map_addr(pblk, data, *secs_to_gc, data_len, + PBLK_KMALLOC_META, GFP_KERNEL); if (IS_ERR(bio)) { pr_err("pblk: could not allocate GC bio (%lu)\n", PTR_ERR(bio)); goto err_free_dma; @@ -490,6 +503,7 @@ int pblk_submit_read_gc(struct pblk *pblk, u64 *lba_list, void *data, rqd.end_io = pblk_end_io_sync; rqd.private = &wait; rqd.nr_ppas = *secs_to_gc; + rqd.flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM); rqd.bio = bio; ret = pblk_submit_read_io(pblk, &rqd); @@ -503,6 +517,7 @@ int pblk_submit_read_gc(struct pblk *pblk, u64 *lba_list, void *data, msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) { pr_err("pblk: GC read I/O timed out\n"); } + atomic_dec(&pblk->inflight_io); if (rqd.error) { atomic_long_inc(&pblk->read_failed_gc); @@ -518,12 +533,10 @@ int pblk_submit_read_gc(struct pblk *pblk, u64 *lba_list, void *data, #endif out: - if (rqd.nr_ppas > 1) - nvm_dev_dma_free(dev->parent, rqd.ppa_list, rqd.dma_ppa_list); + nvm_dev_dma_free(dev->parent, rqd.meta_list, rqd.dma_meta_list); return NVM_IO_OK; err_free_dma: - if (rqd.nr_ppas > 1) - nvm_dev_dma_free(dev->parent, rqd.ppa_list, rqd.dma_ppa_list); + nvm_dev_dma_free(dev->parent, rqd.meta_list, rqd.dma_meta_list); return NVM_IO_ERR; } diff --git a/drivers/lightnvm/pblk-recovery.c b/drivers/lightnvm/pblk-recovery.c index f8f85087cd3c..0e48d3e4e143 100644 --- a/drivers/lightnvm/pblk-recovery.c +++ b/drivers/lightnvm/pblk-recovery.c @@ -120,18 +120,18 @@ int pblk_recov_setup_rq(struct pblk *pblk, struct pblk_c_ctx *c_ctx, return 0; } -__le64 *pblk_recov_get_lba_list(struct pblk *pblk, struct line_emeta *emeta) +__le64 *pblk_recov_get_lba_list(struct pblk *pblk, struct line_emeta *emeta_buf) { u32 crc; - crc = pblk_calc_emeta_crc(pblk, emeta); - if (le32_to_cpu(emeta->crc) != crc) + crc = pblk_calc_emeta_crc(pblk, emeta_buf); + if (le32_to_cpu(emeta_buf->crc) != crc) return NULL; - if (le32_to_cpu(emeta->header.identifier) != PBLK_MAGIC) + if (le32_to_cpu(emeta_buf->header.identifier) != PBLK_MAGIC) return NULL; - return pblk_line_emeta_to_lbas(emeta); + return emeta_to_lbas(pblk, emeta_buf); } static int pblk_recov_l2p_from_emeta(struct pblk *pblk, struct pblk_line *line) @@ -139,19 +139,20 @@ static int pblk_recov_l2p_from_emeta(struct pblk *pblk, struct pblk_line *line) struct nvm_tgt_dev *dev = pblk->dev; struct nvm_geo *geo = &dev->geo; struct pblk_line_meta *lm = &pblk->lm; - struct line_emeta *emeta = line->emeta; + struct pblk_emeta *emeta = line->emeta; + struct line_emeta *emeta_buf = emeta->buf; __le64 *lba_list; int data_start; int nr_data_lbas, nr_valid_lbas, nr_lbas = 0; int i; - lba_list = pblk_recov_get_lba_list(pblk, emeta); + lba_list = pblk_recov_get_lba_list(pblk, emeta_buf); if (!lba_list) return 1; data_start = pblk_line_smeta_start(pblk, line) + lm->smeta_sec; - nr_data_lbas = lm->sec_per_line - lm->emeta_sec; - nr_valid_lbas = le64_to_cpu(emeta->nr_valid_lbas); + nr_data_lbas = lm->sec_per_line - lm->emeta_sec[0]; + nr_valid_lbas = le64_to_cpu(emeta_buf->nr_valid_lbas); for (i = data_start; i < nr_data_lbas && nr_lbas < nr_valid_lbas; i++) { struct ppa_addr ppa; @@ -169,7 +170,7 @@ static int pblk_recov_l2p_from_emeta(struct pblk *pblk, struct pblk_line *line) if (test_and_set_bit(i, line->invalid_bitmap)) WARN_ONCE(1, "pblk: rec. double invalidate:\n"); else - line->vsc--; + le32_add_cpu(line->vsc, -1); spin_unlock(&line->lock); continue; @@ -181,7 +182,7 @@ static int pblk_recov_l2p_from_emeta(struct pblk *pblk, struct pblk_line *line) if (nr_valid_lbas != nr_lbas) pr_err("pblk: line %d - inconsistent lba list(%llu/%d)\n", - line->id, line->emeta->nr_valid_lbas, nr_lbas); + line->id, emeta_buf->nr_valid_lbas, nr_lbas); line->left_msecs = 0; @@ -195,7 +196,7 @@ static int pblk_calc_sec_in_line(struct pblk *pblk, struct pblk_line *line) struct pblk_line_meta *lm = &pblk->lm; int nr_bb = bitmap_weight(line->blk_bitmap, lm->blk_per_line); - return lm->sec_per_line - lm->smeta_sec - lm->emeta_sec - + return lm->sec_per_line - lm->smeta_sec - lm->emeta_sec[0] - nr_bb * geo->sec_per_blk; } @@ -240,7 +241,7 @@ static int pblk_recov_read_oob(struct pblk *pblk, struct pblk_line *line, r_ptr_int = r_ptr; next_read_rq: - memset(rqd, 0, pblk_r_rq_size); + memset(rqd, 0, pblk_g_rq_size); rq_ppas = pblk_calc_secs(pblk, left_ppas, 0); if (!rq_ppas) @@ -256,7 +257,6 @@ next_read_rq: rqd->bio = bio; rqd->opcode = NVM_OP_PREAD; - rqd->flags = pblk_set_read_mode(pblk); rqd->meta_list = meta_list; rqd->nr_ppas = rq_ppas; rqd->ppa_list = ppa_list; @@ -265,6 +265,11 @@ next_read_rq: rqd->end_io = pblk_end_io_sync; rqd->private = &wait; + if (pblk_io_aligned(pblk, rq_ppas)) + rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_SEQUENTIAL); + else + rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM); + for (i = 0; i < rqd->nr_ppas; ) { struct ppa_addr ppa; int pos; @@ -295,7 +300,7 @@ next_read_rq: pr_err("pblk: L2P recovery read timed out\n"); return -EINTR; } - + atomic_dec(&pblk->inflight_io); reinit_completion(&wait); /* At this point, the read should not fail. If it does, it is a problem @@ -322,47 +327,94 @@ next_read_rq: return 0; } +static void pblk_recov_complete(struct kref *ref) +{ + struct pblk_pad_rq *pad_rq = container_of(ref, struct pblk_pad_rq, ref); + + complete(&pad_rq->wait); +} + +static void pblk_end_io_recov(struct nvm_rq *rqd) +{ + struct pblk_pad_rq *pad_rq = rqd->private; + struct pblk *pblk = pad_rq->pblk; + struct nvm_tgt_dev *dev = pblk->dev; + + kref_put(&pad_rq->ref, pblk_recov_complete); + nvm_dev_dma_free(dev->parent, rqd->meta_list, rqd->dma_meta_list); + pblk_free_rqd(pblk, rqd, WRITE); +} + static int pblk_recov_pad_oob(struct pblk *pblk, struct pblk_line *line, - struct pblk_recov_alloc p, int left_ppas) + int left_ppas) { struct nvm_tgt_dev *dev = pblk->dev; struct nvm_geo *geo = &dev->geo; struct ppa_addr *ppa_list; struct pblk_sec_meta *meta_list; + struct pblk_pad_rq *pad_rq; struct nvm_rq *rqd; struct bio *bio; void *data; dma_addr_t dma_ppa_list, dma_meta_list; - __le64 *lba_list = pblk_line_emeta_to_lbas(line->emeta); + __le64 *lba_list = emeta_to_lbas(pblk, line->emeta->buf); u64 w_ptr = line->cur_sec; - int left_line_ppas = line->left_msecs; - int rq_ppas, rq_len; + int left_line_ppas, rq_ppas, rq_len; int i, j; int ret = 0; - DECLARE_COMPLETION_ONSTACK(wait); - ppa_list = p.ppa_list; - meta_list = p.meta_list; - rqd = p.rqd; - data = p.data; - dma_ppa_list = p.dma_ppa_list; - dma_meta_list = p.dma_meta_list; + spin_lock(&line->lock); + left_line_ppas = line->left_msecs; + spin_unlock(&line->lock); + + pad_rq = kmalloc(sizeof(struct pblk_pad_rq), GFP_KERNEL); + if (!pad_rq) + return -ENOMEM; + + data = vzalloc(pblk->max_write_pgs * geo->sec_size); + if (!data) { + ret = -ENOMEM; + goto free_rq; + } + + pad_rq->pblk = pblk; + init_completion(&pad_rq->wait); + kref_init(&pad_rq->ref); next_pad_rq: rq_ppas = pblk_calc_secs(pblk, left_ppas, 0); - if (!rq_ppas) - rq_ppas = pblk->min_write_pgs; + if (rq_ppas < pblk->min_write_pgs) { + pr_err("pblk: corrupted pad line %d\n", line->id); + goto free_rq; + } + rq_len = rq_ppas * geo->sec_size; + meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, &dma_meta_list); + if (!meta_list) { + ret = -ENOMEM; + goto free_data; + } + + ppa_list = (void *)(meta_list) + pblk_dma_meta_size; + dma_ppa_list = dma_meta_list + pblk_dma_meta_size; + + rqd = pblk_alloc_rqd(pblk, WRITE); + if (IS_ERR(rqd)) { + ret = PTR_ERR(rqd); + goto fail_free_meta; + } + memset(rqd, 0, pblk_w_rq_size); + bio = bio_map_kern(dev->q, data, rq_len, GFP_KERNEL); - if (IS_ERR(bio)) - return PTR_ERR(bio); + if (IS_ERR(bio)) { + ret = PTR_ERR(bio); + goto fail_free_rqd; + } bio->bi_iter.bi_sector = 0; /* internal bio */ bio_set_op_attrs(bio, REQ_OP_WRITE, 0); - memset(rqd, 0, pblk_r_rq_size); - rqd->bio = bio; rqd->opcode = NVM_OP_PWRITE; rqd->flags = pblk_set_progr_mode(pblk, WRITE); @@ -371,8 +423,8 @@ next_pad_rq: rqd->ppa_list = ppa_list; rqd->dma_ppa_list = dma_ppa_list; rqd->dma_meta_list = dma_meta_list; - rqd->end_io = pblk_end_io_sync; - rqd->private = &wait; + rqd->end_io = pblk_end_io_recov; + rqd->private = pad_rq; for (i = 0; i < rqd->nr_ppas; ) { struct ppa_addr ppa; @@ -390,34 +442,51 @@ next_pad_rq: for (j = 0; j < pblk->min_write_pgs; j++, i++, w_ptr++) { struct ppa_addr dev_ppa; + __le64 addr_empty = cpu_to_le64(ADDR_EMPTY); dev_ppa = addr_to_gen_ppa(pblk, w_ptr, line->id); pblk_map_invalidate(pblk, dev_ppa); - meta_list[i].lba = cpu_to_le64(ADDR_EMPTY); - lba_list[w_ptr] = cpu_to_le64(ADDR_EMPTY); + lba_list[w_ptr] = meta_list[i].lba = addr_empty; rqd->ppa_list[i] = dev_ppa; } } + kref_get(&pad_rq->ref); + ret = pblk_submit_io(pblk, rqd); if (ret) { pr_err("pblk: I/O submission failed: %d\n", ret); - return ret; + goto free_data; } - if (!wait_for_completion_io_timeout(&wait, - msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) { - pr_err("pblk: L2P recovery write timed out\n"); - } - reinit_completion(&wait); + atomic_dec(&pblk->inflight_io); left_line_ppas -= rq_ppas; left_ppas -= rq_ppas; - if (left_ppas > 0 && left_line_ppas) + if (left_ppas && left_line_ppas) goto next_pad_rq; - return 0; + kref_put(&pad_rq->ref, pblk_recov_complete); + + if (!wait_for_completion_io_timeout(&pad_rq->wait, + msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) { + pr_err("pblk: pad write timed out\n"); + ret = -ETIME; + } + +free_rq: + kfree(pad_rq); +free_data: + vfree(data); + return ret; + +fail_free_rqd: + pblk_free_rqd(pblk, rqd, WRITE); +fail_free_meta: + nvm_dev_dma_free(dev->parent, meta_list, dma_meta_list); + kfree(pad_rq); + return ret; } /* When this function is called, it means that not all upper pages have been @@ -456,7 +525,7 @@ static int pblk_recov_scan_all_oob(struct pblk *pblk, struct pblk_line *line, rec_round = 0; next_rq: - memset(rqd, 0, pblk_r_rq_size); + memset(rqd, 0, pblk_g_rq_size); rq_ppas = pblk_calc_secs(pblk, left_ppas, 0); if (!rq_ppas) @@ -472,7 +541,6 @@ next_rq: rqd->bio = bio; rqd->opcode = NVM_OP_PREAD; - rqd->flags = pblk_set_read_mode(pblk); rqd->meta_list = meta_list; rqd->nr_ppas = rq_ppas; rqd->ppa_list = ppa_list; @@ -481,6 +549,11 @@ next_rq: rqd->end_io = pblk_end_io_sync; rqd->private = &wait; + if (pblk_io_aligned(pblk, rq_ppas)) + rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_SEQUENTIAL); + else + rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM); + for (i = 0; i < rqd->nr_ppas; ) { struct ppa_addr ppa; int pos; @@ -510,6 +583,7 @@ next_rq: msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) { pr_err("pblk: L2P recovery read timed out\n"); } + atomic_dec(&pblk->inflight_io); reinit_completion(&wait); /* This should not happen since the read failed during normal recovery, @@ -544,7 +618,7 @@ next_rq: if (pad_secs > line->left_msecs) pad_secs = line->left_msecs; - ret = pblk_recov_pad_oob(pblk, line, p, pad_secs); + ret = pblk_recov_pad_oob(pblk, line, pad_secs); if (ret) pr_err("pblk: OOB padding failed (err:%d)\n", ret); @@ -552,7 +626,6 @@ next_rq: if (ret) pr_err("pblk: OOB read failed (err:%d)\n", ret); - line->left_ssecs = line->left_msecs; left_ppas = 0; } @@ -591,7 +664,7 @@ static int pblk_recov_scan_oob(struct pblk *pblk, struct pblk_line *line, *done = 1; next_rq: - memset(rqd, 0, pblk_r_rq_size); + memset(rqd, 0, pblk_g_rq_size); rq_ppas = pblk_calc_secs(pblk, left_ppas, 0); if (!rq_ppas) @@ -607,7 +680,6 @@ next_rq: rqd->bio = bio; rqd->opcode = NVM_OP_PREAD; - rqd->flags = pblk_set_read_mode(pblk); rqd->meta_list = meta_list; rqd->nr_ppas = rq_ppas; rqd->ppa_list = ppa_list; @@ -616,6 +688,11 @@ next_rq: rqd->end_io = pblk_end_io_sync; rqd->private = &wait; + if (pblk_io_aligned(pblk, rq_ppas)) + rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_SEQUENTIAL); + else + rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM); + for (i = 0; i < rqd->nr_ppas; ) { struct ppa_addr ppa; int pos; @@ -646,6 +723,7 @@ next_rq: msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) { pr_err("pblk: L2P recovery read timed out\n"); } + atomic_dec(&pblk->inflight_io); reinit_completion(&wait); /* Reached the end of the written line */ @@ -658,7 +736,6 @@ next_rq: /* Roll back failed sectors */ line->cur_sec -= nr_error_bits; line->left_msecs += nr_error_bits; - line->left_ssecs = line->left_msecs; bitmap_clear(line->map_bitmap, line->cur_sec, nr_error_bits); left_ppas = 0; @@ -770,8 +847,9 @@ struct pblk_line *pblk_recov_l2p(struct pblk *pblk) struct pblk_line_meta *lm = &pblk->lm; struct pblk_line_mgmt *l_mg = &pblk->l_mg; struct pblk_line *line, *tline, *data_line = NULL; - struct line_smeta *smeta; - struct line_emeta *emeta; + struct pblk_smeta *smeta; + struct pblk_emeta *emeta; + struct line_smeta *smeta_buf; int found_lines = 0, recovered_lines = 0, open_lines = 0; int is_next = 0; int meta_line; @@ -784,8 +862,9 @@ struct pblk_line *pblk_recov_l2p(struct pblk *pblk) spin_lock(&l_mg->free_lock); meta_line = find_first_zero_bit(&l_mg->meta_bitmap, PBLK_DATA_LINES); set_bit(meta_line, &l_mg->meta_bitmap); - smeta = l_mg->sline_meta[meta_line].meta; - emeta = l_mg->eline_meta[meta_line].meta; + smeta = l_mg->sline_meta[meta_line]; + emeta = l_mg->eline_meta[meta_line]; + smeta_buf = (struct line_smeta *)smeta; spin_unlock(&l_mg->free_lock); /* Order data lines using their sequence number */ @@ -796,33 +875,33 @@ struct pblk_line *pblk_recov_l2p(struct pblk *pblk) memset(smeta, 0, lm->smeta_len); line->smeta = smeta; - line->lun_bitmap = ((void *)(smeta)) + + line->lun_bitmap = ((void *)(smeta_buf)) + sizeof(struct line_smeta); /* Lines that cannot be read are assumed as not written here */ if (pblk_line_read_smeta(pblk, line)) continue; - crc = pblk_calc_smeta_crc(pblk, smeta); - if (le32_to_cpu(smeta->crc) != crc) + crc = pblk_calc_smeta_crc(pblk, smeta_buf); + if (le32_to_cpu(smeta_buf->crc) != crc) continue; - if (le32_to_cpu(smeta->header.identifier) != PBLK_MAGIC) + if (le32_to_cpu(smeta_buf->header.identifier) != PBLK_MAGIC) continue; - if (le16_to_cpu(smeta->header.version) != 1) { + if (le16_to_cpu(smeta_buf->header.version) != 1) { pr_err("pblk: found incompatible line version %u\n", - smeta->header.version); + smeta_buf->header.version); return ERR_PTR(-EINVAL); } /* The first valid instance uuid is used for initialization */ if (!valid_uuid) { - memcpy(pblk->instance_uuid, smeta->header.uuid, 16); + memcpy(pblk->instance_uuid, smeta_buf->header.uuid, 16); valid_uuid = 1; } - if (memcmp(pblk->instance_uuid, smeta->header.uuid, 16)) { + if (memcmp(pblk->instance_uuid, smeta_buf->header.uuid, 16)) { pr_debug("pblk: ignore line %u due to uuid mismatch\n", i); continue; @@ -830,9 +909,9 @@ struct pblk_line *pblk_recov_l2p(struct pblk *pblk) /* Update line metadata */ spin_lock(&line->lock); - line->id = le32_to_cpu(line->smeta->header.id); - line->type = le16_to_cpu(line->smeta->header.type); - line->seq_nr = le64_to_cpu(line->smeta->seq_nr); + line->id = le32_to_cpu(smeta_buf->header.id); + line->type = le16_to_cpu(smeta_buf->header.type); + line->seq_nr = le64_to_cpu(smeta_buf->seq_nr); spin_unlock(&line->lock); /* Update general metadata */ @@ -848,7 +927,7 @@ struct pblk_line *pblk_recov_l2p(struct pblk *pblk) pblk_recov_line_add_ordered(&recov_list, line); found_lines++; pr_debug("pblk: recovering data line %d, seq:%llu\n", - line->id, smeta->seq_nr); + line->id, smeta_buf->seq_nr); } if (!found_lines) { @@ -868,15 +947,15 @@ struct pblk_line *pblk_recov_l2p(struct pblk *pblk) recovered_lines++; /* Calculate where emeta starts based on the line bb */ - off = lm->sec_per_line - lm->emeta_sec; + off = lm->sec_per_line - lm->emeta_sec[0]; nr_bb = bitmap_weight(line->blk_bitmap, lm->blk_per_line); off -= nr_bb * geo->sec_per_pl; - memset(emeta, 0, lm->emeta_len); - line->emeta = emeta; line->emeta_ssec = off; + line->emeta = emeta; + memset(line->emeta->buf, 0, lm->emeta_len[0]); - if (pblk_line_read_emeta(pblk, line)) { + if (pblk_line_read_emeta(pblk, line, line->emeta->buf)) { pblk_recov_l2p_from_oob(pblk, line); goto next; } @@ -941,58 +1020,26 @@ out: } /* - * Pad until smeta can be read on current data line + * Pad current line */ -void pblk_recov_pad(struct pblk *pblk) +int pblk_recov_pad(struct pblk *pblk) { - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; struct pblk_line *line; struct pblk_line_mgmt *l_mg = &pblk->l_mg; - struct nvm_rq *rqd; - struct pblk_recov_alloc p; - struct ppa_addr *ppa_list; - struct pblk_sec_meta *meta_list; - void *data; - dma_addr_t dma_ppa_list, dma_meta_list; + int left_msecs; + int ret = 0; spin_lock(&l_mg->free_lock); line = l_mg->data_line; + left_msecs = line->left_msecs; spin_unlock(&l_mg->free_lock); - rqd = pblk_alloc_rqd(pblk, READ); - if (IS_ERR(rqd)) - return; - - meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, &dma_meta_list); - if (!meta_list) - goto free_rqd; - - ppa_list = (void *)(meta_list) + pblk_dma_meta_size; - dma_ppa_list = dma_meta_list + pblk_dma_meta_size; - - data = kcalloc(pblk->max_write_pgs, geo->sec_size, GFP_KERNEL); - if (!data) - goto free_meta_list; - - p.ppa_list = ppa_list; - p.meta_list = meta_list; - p.rqd = rqd; - p.data = data; - p.dma_ppa_list = dma_ppa_list; - p.dma_meta_list = dma_meta_list; - - if (pblk_recov_pad_oob(pblk, line, p, line->left_msecs)) { - pr_err("pblk: Tear down padding failed\n"); - goto free_data; + ret = pblk_recov_pad_oob(pblk, line, left_msecs); + if (ret) { + pr_err("pblk: Tear down padding failed (%d)\n", ret); + return ret; } - pblk_line_close(pblk, line); - -free_data: - kfree(data); -free_meta_list: - nvm_dev_dma_free(dev->parent, meta_list, dma_meta_list); -free_rqd: - pblk_free_rqd(pblk, rqd, READ); + pblk_line_close_meta(pblk, line); + return ret; } diff --git a/drivers/lightnvm/pblk-rl.c b/drivers/lightnvm/pblk-rl.c index ab7cbb144f3f..2e6a5361baf0 100644 --- a/drivers/lightnvm/pblk-rl.c +++ b/drivers/lightnvm/pblk-rl.c @@ -23,11 +23,35 @@ static void pblk_rl_kick_u_timer(struct pblk_rl *rl) mod_timer(&rl->u_timer, jiffies + msecs_to_jiffies(5000)); } +int pblk_rl_is_limit(struct pblk_rl *rl) +{ + int rb_space; + + rb_space = atomic_read(&rl->rb_space); + + return (rb_space == 0); +} + int pblk_rl_user_may_insert(struct pblk_rl *rl, int nr_entries) { int rb_user_cnt = atomic_read(&rl->rb_user_cnt); + int rb_space = atomic_read(&rl->rb_space); - return (!(rb_user_cnt + nr_entries > rl->rb_user_max)); + if (unlikely(rb_space >= 0) && (rb_space - nr_entries < 0)) + return NVM_IO_ERR; + + if (rb_user_cnt >= rl->rb_user_max) + return NVM_IO_REQUEUE; + + return NVM_IO_OK; +} + +void pblk_rl_inserted(struct pblk_rl *rl, int nr_entries) +{ + int rb_space = atomic_read(&rl->rb_space); + + if (unlikely(rb_space >= 0)) + atomic_sub(nr_entries, &rl->rb_space); } int pblk_rl_gc_may_insert(struct pblk_rl *rl, int nr_entries) @@ -37,7 +61,7 @@ int pblk_rl_gc_may_insert(struct pblk_rl *rl, int nr_entries) /* If there is no user I/O let GC take over space on the write buffer */ rb_user_active = READ_ONCE(rl->rb_user_active); - return (!(rb_gc_cnt + nr_entries > rl->rb_gc_max && rb_user_active)); + return (!(rb_gc_cnt >= rl->rb_gc_max && rb_user_active)); } void pblk_rl_user_in(struct pblk_rl *rl, int nr_entries) @@ -77,33 +101,32 @@ static int pblk_rl_update_rates(struct pblk_rl *rl, unsigned long max) unsigned long free_blocks = pblk_rl_nr_free_blks(rl); if (free_blocks >= rl->high) { - rl->rb_user_max = max - rl->rb_gc_rsv; - rl->rb_gc_max = rl->rb_gc_rsv; + rl->rb_user_max = max; + rl->rb_gc_max = 0; rl->rb_state = PBLK_RL_HIGH; } else if (free_blocks < rl->high) { int shift = rl->high_pw - rl->rb_windows_pw; int user_windows = free_blocks >> shift; int user_max = user_windows << PBLK_MAX_REQ_ADDRS_PW; - int gc_max; rl->rb_user_max = user_max; - gc_max = max - rl->rb_user_max; - rl->rb_gc_max = max(gc_max, rl->rb_gc_rsv); - - if (free_blocks > rl->low) - rl->rb_state = PBLK_RL_MID; - else - rl->rb_state = PBLK_RL_LOW; + rl->rb_gc_max = max - user_max; + + if (free_blocks <= rl->rsv_blocks) { + rl->rb_user_max = 0; + rl->rb_gc_max = max; + } + + /* In the worst case, we will need to GC lines in the low list + * (high valid sector count). If there are lines to GC on high + * or mid lists, these will be prioritized + */ + rl->rb_state = PBLK_RL_LOW; } return rl->rb_state; } -void pblk_rl_set_gc_rsc(struct pblk_rl *rl, int rsv) -{ - rl->rb_gc_rsv = rl->rb_gc_max = rsv; -} - void pblk_rl_free_lines_inc(struct pblk_rl *rl, struct pblk_line *line) { struct pblk *pblk = container_of(rl, struct pblk, rl); @@ -122,11 +145,15 @@ void pblk_rl_free_lines_inc(struct pblk_rl *rl, struct pblk_line *line) void pblk_rl_free_lines_dec(struct pblk_rl *rl, struct pblk_line *line) { - struct pblk *pblk = container_of(rl, struct pblk, rl); int blk_in_line = atomic_read(&line->blk_in_line); - int ret; atomic_sub(blk_in_line, &rl->free_blocks); +} + +void pblk_gc_should_kick(struct pblk *pblk) +{ + struct pblk_rl *rl = &pblk->rl; + int ret; /* Rates will not change that often - no need to lock update */ ret = pblk_rl_update_rates(rl, rl->rb_budget); @@ -136,11 +163,16 @@ void pblk_rl_free_lines_dec(struct pblk_rl *rl, struct pblk_line *line) pblk_gc_should_stop(pblk); } -int pblk_rl_gc_thrs(struct pblk_rl *rl) +int pblk_rl_high_thrs(struct pblk_rl *rl) { return rl->high; } +int pblk_rl_low_thrs(struct pblk_rl *rl) +{ + return rl->low; +} + int pblk_rl_sysfs_rate_show(struct pblk_rl *rl) { return rl->rb_user_max; @@ -161,24 +193,36 @@ void pblk_rl_free(struct pblk_rl *rl) void pblk_rl_init(struct pblk_rl *rl, int budget) { + struct pblk *pblk = container_of(rl, struct pblk, rl); + struct pblk_line_meta *lm = &pblk->lm; + int min_blocks = lm->blk_per_line * PBLK_GC_RSV_LINE; unsigned int rb_windows; rl->high = rl->total_blocks / PBLK_USER_HIGH_THRS; - rl->low = rl->total_blocks / PBLK_USER_LOW_THRS; rl->high_pw = get_count_order(rl->high); + rl->low = rl->total_blocks / PBLK_USER_LOW_THRS; + if (rl->low < min_blocks) + rl->low = min_blocks; + + rl->rsv_blocks = min_blocks; + /* This will always be a power-of-2 */ rb_windows = budget / PBLK_MAX_REQ_ADDRS; - rl->rb_windows_pw = get_count_order(rb_windows) + 1; + rl->rb_windows_pw = get_count_order(rb_windows); /* To start with, all buffer is available to user I/O writers */ rl->rb_budget = budget; rl->rb_user_max = budget; - atomic_set(&rl->rb_user_cnt, 0); rl->rb_gc_max = 0; rl->rb_state = PBLK_RL_HIGH; + + atomic_set(&rl->rb_user_cnt, 0); atomic_set(&rl->rb_gc_cnt, 0); + atomic_set(&rl->rb_space, -1); setup_timer(&rl->u_timer, pblk_rl_u_timer, (unsigned long)rl); + rl->rb_user_active = 0; + rl->rb_gc_active = 0; } diff --git a/drivers/lightnvm/pblk-sysfs.c b/drivers/lightnvm/pblk-sysfs.c index f0af1d1ceeff..95fb434e2f01 100644 --- a/drivers/lightnvm/pblk-sysfs.c +++ b/drivers/lightnvm/pblk-sysfs.c @@ -49,30 +49,26 @@ static ssize_t pblk_sysfs_luns_show(struct pblk *pblk, char *page) static ssize_t pblk_sysfs_rate_limiter(struct pblk *pblk, char *page) { - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; int free_blocks, total_blocks; int rb_user_max, rb_user_cnt; - int rb_gc_max, rb_gc_rsv, rb_gc_cnt, rb_budget, rb_state; + int rb_gc_max, rb_gc_cnt, rb_budget, rb_state; free_blocks = atomic_read(&pblk->rl.free_blocks); rb_user_max = pblk->rl.rb_user_max; rb_user_cnt = atomic_read(&pblk->rl.rb_user_cnt); rb_gc_max = pblk->rl.rb_gc_max; - rb_gc_rsv = pblk->rl.rb_gc_rsv; rb_gc_cnt = atomic_read(&pblk->rl.rb_gc_cnt); rb_budget = pblk->rl.rb_budget; rb_state = pblk->rl.rb_state; - total_blocks = geo->blks_per_lun * geo->nr_luns; + total_blocks = pblk->rl.total_blocks; return snprintf(page, PAGE_SIZE, - "u:%u/%u,gc:%u/%u/%u(%u/%u)(stop:<%u,full:>%u,free:%d/%d)-%d\n", + "u:%u/%u,gc:%u/%u(%u/%u)(stop:<%u,full:>%u,free:%d/%d)-%d\n", rb_user_cnt, rb_user_max, rb_gc_cnt, rb_gc_max, - rb_gc_rsv, rb_state, rb_budget, pblk->rl.low, @@ -150,11 +146,11 @@ static ssize_t pblk_sysfs_lines(struct pblk *pblk, char *page) ssize_t sz = 0; int nr_free_lines; int cur_data, cur_log; - int free_line_cnt = 0, closed_line_cnt = 0; + int free_line_cnt = 0, closed_line_cnt = 0, emeta_line_cnt = 0; int d_line_cnt = 0, l_line_cnt = 0; int gc_full = 0, gc_high = 0, gc_mid = 0, gc_low = 0, gc_empty = 0; - int free = 0, bad = 0, cor = 0; - int msecs = 0, ssecs = 0, cur_sec = 0, vsc = 0, sec_in_line = 0; + int bad = 0, cor = 0; + int msecs = 0, cur_sec = 0, vsc = 0, sec_in_line = 0; int map_weight = 0, meta_weight = 0; spin_lock(&l_mg->free_lock); @@ -166,6 +162,11 @@ static ssize_t pblk_sysfs_lines(struct pblk *pblk, char *page) free_line_cnt++; spin_unlock(&l_mg->free_lock); + spin_lock(&l_mg->close_lock); + list_for_each_entry(line, &l_mg->emeta_list, list) + emeta_line_cnt++; + spin_unlock(&l_mg->close_lock); + spin_lock(&l_mg->gc_lock); list_for_each_entry(line, &l_mg->gc_full_list, list) { if (line->type == PBLK_LINETYPE_DATA) @@ -212,8 +213,6 @@ static ssize_t pblk_sysfs_lines(struct pblk *pblk, char *page) gc_empty++; } - list_for_each_entry(line, &l_mg->free_list, list) - free++; list_for_each_entry(line, &l_mg->bad_list, list) bad++; list_for_each_entry(line, &l_mg->corrupt_list, list) @@ -224,8 +223,7 @@ static ssize_t pblk_sysfs_lines(struct pblk *pblk, char *page) if (l_mg->data_line) { cur_sec = l_mg->data_line->cur_sec; msecs = l_mg->data_line->left_msecs; - ssecs = l_mg->data_line->left_ssecs; - vsc = l_mg->data_line->vsc; + vsc = le32_to_cpu(*l_mg->data_line->vsc); sec_in_line = l_mg->data_line->sec_in_line; meta_weight = bitmap_weight(&l_mg->meta_bitmap, PBLK_DATA_LINES); @@ -235,17 +233,20 @@ static ssize_t pblk_sysfs_lines(struct pblk *pblk, char *page) spin_unlock(&l_mg->free_lock); if (nr_free_lines != free_line_cnt) - pr_err("pblk: corrupted free line list\n"); + pr_err("pblk: corrupted free line list:%d/%d\n", + nr_free_lines, free_line_cnt); sz = snprintf(page, PAGE_SIZE - sz, "line: nluns:%d, nblks:%d, nsecs:%d\n", geo->nr_luns, lm->blk_per_line, lm->sec_per_line); sz += snprintf(page + sz, PAGE_SIZE - sz, - "lines:d:%d,l:%d-f:%d(%d),b:%d,co:%d,c:%d(d:%d,l:%d)t:%d\n", + "lines:d:%d,l:%d-f:%d,m:%d/%d,c:%d,b:%d,co:%d(d:%d,l:%d)t:%d\n", cur_data, cur_log, - free, nr_free_lines, bad, cor, + nr_free_lines, + emeta_line_cnt, meta_weight, closed_line_cnt, + bad, cor, d_line_cnt, l_line_cnt, l_mg->nr_lines); @@ -255,9 +256,10 @@ static ssize_t pblk_sysfs_lines(struct pblk *pblk, char *page) atomic_read(&pblk->gc.inflight_gc)); sz += snprintf(page + sz, PAGE_SIZE - sz, - "data (%d) cur:%d, left:%d/%d, vsc:%d, s:%d, map:%d/%d (%d)\n", - cur_data, cur_sec, msecs, ssecs, vsc, sec_in_line, - map_weight, lm->sec_per_line, meta_weight); + "data (%d) cur:%d, left:%d, vsc:%d, s:%d, map:%d/%d (%d)\n", + cur_data, cur_sec, msecs, vsc, sec_in_line, + map_weight, lm->sec_per_line, + atomic_read(&pblk->inflight_io)); return sz; } @@ -274,7 +276,7 @@ static ssize_t pblk_sysfs_lines_info(struct pblk *pblk, char *page) lm->smeta_len, lm->smeta_sec); sz += snprintf(page + sz, PAGE_SIZE - sz, "emeta - len:%d, sec:%d, bb_start:%d\n", - lm->emeta_len, lm->emeta_sec, + lm->emeta_len[0], lm->emeta_sec[0], lm->emeta_bb); sz += snprintf(page + sz, PAGE_SIZE - sz, "bitmap lengths: sec:%d, blk:%d, lun:%d\n", @@ -290,6 +292,11 @@ static ssize_t pblk_sysfs_lines_info(struct pblk *pblk, char *page) return sz; } +static ssize_t pblk_sysfs_get_sec_per_write(struct pblk *pblk, char *page) +{ + return snprintf(page, PAGE_SIZE, "%d\n", pblk->sec_per_write); +} + #ifdef CONFIG_NVM_DEBUG static ssize_t pblk_sysfs_stats_debug(struct pblk *pblk, char *page) { @@ -303,52 +310,51 @@ static ssize_t pblk_sysfs_stats_debug(struct pblk *pblk, char *page) atomic_long_read(&pblk->padded_wb), atomic_long_read(&pblk->sub_writes), atomic_long_read(&pblk->sync_writes), - atomic_long_read(&pblk->compl_writes), atomic_long_read(&pblk->recov_writes), atomic_long_read(&pblk->recov_gc_writes), atomic_long_read(&pblk->recov_gc_reads), + atomic_long_read(&pblk->cache_reads), atomic_long_read(&pblk->sync_reads)); } #endif -static ssize_t pblk_sysfs_rate_store(struct pblk *pblk, const char *page, - size_t len) +static ssize_t pblk_sysfs_gc_force(struct pblk *pblk, const char *page, + size_t len) { - struct pblk_gc *gc = &pblk->gc; size_t c_len; - int value; + int force; c_len = strcspn(page, "\n"); if (c_len >= len) return -EINVAL; - if (kstrtouint(page, 0, &value)) + if (kstrtouint(page, 0, &force)) return -EINVAL; - spin_lock(&gc->lock); - pblk_rl_set_gc_rsc(&pblk->rl, value); - spin_unlock(&gc->lock); + pblk_gc_sysfs_force(pblk, force); return len; } -static ssize_t pblk_sysfs_gc_force(struct pblk *pblk, const char *page, - size_t len) +static ssize_t pblk_sysfs_set_sec_per_write(struct pblk *pblk, + const char *page, size_t len) { size_t c_len; - int force; + int sec_per_write; c_len = strcspn(page, "\n"); if (c_len >= len) return -EINVAL; - if (kstrtouint(page, 0, &force)) + if (kstrtouint(page, 0, &sec_per_write)) return -EINVAL; - if (force < 0 || force > 1) + if (sec_per_write < pblk->min_write_pgs + || sec_per_write > pblk->max_write_pgs + || sec_per_write % pblk->min_write_pgs != 0) return -EINVAL; - pblk_gc_sysfs_force(pblk, force); + pblk_set_sec_per_write(pblk, sec_per_write); return len; } @@ -398,9 +404,9 @@ static struct attribute sys_gc_force = { .mode = 0200, }; -static struct attribute sys_gc_rl_max = { - .name = "gc_rl_max", - .mode = 0200, +static struct attribute sys_max_sec_per_write = { + .name = "max_sec_per_write", + .mode = 0644, }; #ifdef CONFIG_NVM_DEBUG @@ -416,7 +422,7 @@ static struct attribute *pblk_attrs[] = { &sys_errors_attr, &sys_gc_state, &sys_gc_force, - &sys_gc_rl_max, + &sys_max_sec_per_write, &sys_rb_attr, &sys_stats_ppaf_attr, &sys_lines_attr, @@ -448,6 +454,8 @@ static ssize_t pblk_sysfs_show(struct kobject *kobj, struct attribute *attr, return pblk_sysfs_lines(pblk, buf); else if (strcmp(attr->name, "lines_info") == 0) return pblk_sysfs_lines_info(pblk, buf); + else if (strcmp(attr->name, "max_sec_per_write") == 0) + return pblk_sysfs_get_sec_per_write(pblk, buf); #ifdef CONFIG_NVM_DEBUG else if (strcmp(attr->name, "stats") == 0) return pblk_sysfs_stats_debug(pblk, buf); @@ -460,10 +468,10 @@ static ssize_t pblk_sysfs_store(struct kobject *kobj, struct attribute *attr, { struct pblk *pblk = container_of(kobj, struct pblk, kobj); - if (strcmp(attr->name, "gc_rl_max") == 0) - return pblk_sysfs_rate_store(pblk, buf, len); - else if (strcmp(attr->name, "gc_force") == 0) + if (strcmp(attr->name, "gc_force") == 0) return pblk_sysfs_gc_force(pblk, buf, len); + else if (strcmp(attr->name, "max_sec_per_write") == 0) + return pblk_sysfs_set_sec_per_write(pblk, buf, len); return 0; } diff --git a/drivers/lightnvm/pblk-write.c b/drivers/lightnvm/pblk-write.c index aef6fd7c4a0c..d62a8f4faaf4 100644 --- a/drivers/lightnvm/pblk-write.c +++ b/drivers/lightnvm/pblk-write.c @@ -17,18 +17,6 @@ #include "pblk.h" -static void pblk_sync_line(struct pblk *pblk, struct pblk_line *line) -{ -#ifdef CONFIG_NVM_DEBUG - atomic_long_inc(&pblk->sync_writes); -#endif - - /* Counter protected by rb sync lock */ - line->left_ssecs--; - if (!line->left_ssecs) - pblk_line_run_ws(pblk, line, NULL, pblk_line_close_ws); -} - static unsigned long pblk_end_w_bio(struct pblk *pblk, struct nvm_rq *rqd, struct pblk_c_ctx *c_ctx) { @@ -39,21 +27,14 @@ static unsigned long pblk_end_w_bio(struct pblk *pblk, struct nvm_rq *rqd, for (i = 0; i < c_ctx->nr_valid; i++) { struct pblk_w_ctx *w_ctx; - struct ppa_addr p; - struct pblk_line *line; w_ctx = pblk_rb_w_ctx(&pblk->rwb, c_ctx->sentry + i); - - p = rqd->ppa_list[i]; - line = &pblk->lines[pblk_dev_ppa_to_line(p)]; - pblk_sync_line(pblk, line); - while ((original_bio = bio_list_pop(&w_ctx->bios))) bio_endio(original_bio); } #ifdef CONFIG_NVM_DEBUG - atomic_long_add(c_ctx->nr_valid, &pblk->compl_writes); + atomic_long_add(c_ctx->nr_valid, &pblk->sync_writes); #endif ret = pblk_rb_sync_advance(&pblk->rwb, c_ctx->nr_valid); @@ -169,7 +150,7 @@ static void pblk_end_w_fail(struct pblk *pblk, struct nvm_rq *rqd) } INIT_WORK(&recovery->ws_rec, pblk_submit_rec); - queue_work(pblk->kw_wq, &recovery->ws_rec); + queue_work(pblk->close_wq, &recovery->ws_rec); out: pblk_complete_write(pblk, rqd, c_ctx); @@ -186,14 +167,50 @@ static void pblk_end_io_write(struct nvm_rq *rqd) } #ifdef CONFIG_NVM_DEBUG else - WARN_ONCE(rqd->bio->bi_error, "pblk: corrupted write error\n"); + WARN_ONCE(rqd->bio->bi_status, "pblk: corrupted write error\n"); #endif pblk_complete_write(pblk, rqd, c_ctx); + atomic_dec(&pblk->inflight_io); +} + +static void pblk_end_io_write_meta(struct nvm_rq *rqd) +{ + struct pblk *pblk = rqd->private; + struct nvm_tgt_dev *dev = pblk->dev; + struct nvm_geo *geo = &dev->geo; + struct pblk_g_ctx *m_ctx = nvm_rq_to_pdu(rqd); + struct pblk_line *line = m_ctx->private; + struct pblk_emeta *emeta = line->emeta; + int pos = pblk_ppa_to_pos(geo, rqd->ppa_list[0]); + struct pblk_lun *rlun = &pblk->luns[pos]; + int sync; + + up(&rlun->wr_sem); + + if (rqd->error) { + pblk_log_write_err(pblk, rqd); + pr_err("pblk: metadata I/O failed. Line %d\n", line->id); + } +#ifdef CONFIG_NVM_DEBUG + else + WARN_ONCE(rqd->bio->bi_status, "pblk: corrupted write error\n"); +#endif + + sync = atomic_add_return(rqd->nr_ppas, &emeta->sync); + if (sync == emeta->nr_entries) + pblk_line_run_ws(pblk, line, NULL, pblk_line_close_ws, + pblk->close_wq); + + bio_put(rqd->bio); + pblk_free_rqd(pblk, rqd, READ); + + atomic_dec(&pblk->inflight_io); } static int pblk_alloc_w_rq(struct pblk *pblk, struct nvm_rq *rqd, - unsigned int nr_secs) + unsigned int nr_secs, + nvm_end_io_fn(*end_io)) { struct nvm_tgt_dev *dev = pblk->dev; @@ -202,7 +219,7 @@ static int pblk_alloc_w_rq(struct pblk *pblk, struct nvm_rq *rqd, rqd->nr_ppas = nr_secs; rqd->flags = pblk_set_progr_mode(pblk, WRITE); rqd->private = pblk; - rqd->end_io = pblk_end_io_write; + rqd->end_io = end_io; rqd->meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, &rqd->dma_meta_list); @@ -219,11 +236,10 @@ static int pblk_alloc_w_rq(struct pblk *pblk, struct nvm_rq *rqd, } static int pblk_setup_w_rq(struct pblk *pblk, struct nvm_rq *rqd, - struct pblk_c_ctx *c_ctx) + struct pblk_c_ctx *c_ctx, struct ppa_addr *erase_ppa) { struct pblk_line_meta *lm = &pblk->lm; - struct pblk_line *e_line = pblk_line_get_data_next(pblk); - struct ppa_addr erase_ppa; + struct pblk_line *e_line = pblk_line_get_erase(pblk); unsigned int valid = c_ctx->nr_valid; unsigned int padded = c_ctx->nr_padded; unsigned int nr_secs = valid + padded; @@ -231,40 +247,23 @@ static int pblk_setup_w_rq(struct pblk *pblk, struct nvm_rq *rqd, int ret = 0; lun_bitmap = kzalloc(lm->lun_bitmap_len, GFP_KERNEL); - if (!lun_bitmap) { - ret = -ENOMEM; - goto out; - } + if (!lun_bitmap) + return -ENOMEM; c_ctx->lun_bitmap = lun_bitmap; - ret = pblk_alloc_w_rq(pblk, rqd, nr_secs); + ret = pblk_alloc_w_rq(pblk, rqd, nr_secs, pblk_end_io_write); if (ret) { kfree(lun_bitmap); - goto out; + return ret; } - ppa_set_empty(&erase_ppa); if (likely(!e_line || !atomic_read(&e_line->left_eblks))) pblk_map_rq(pblk, rqd, c_ctx->sentry, lun_bitmap, valid, 0); else pblk_map_erase_rq(pblk, rqd, c_ctx->sentry, lun_bitmap, - valid, &erase_ppa); - -out: - if (unlikely(e_line && !ppa_empty(erase_ppa))) { - if (pblk_blk_erase_async(pblk, erase_ppa)) { - struct nvm_tgt_dev *dev = pblk->dev; - struct nvm_geo *geo = &dev->geo; - int bit; - - atomic_inc(&e_line->left_eblks); - bit = erase_ppa.g.lun * geo->nr_chnls + erase_ppa.g.ch; - WARN_ON(!test_and_clear_bit(bit, e_line->erase_bitmap)); - up(&pblk->erase_sem); - } - } + valid, erase_ppa); - return ret; + return 0; } int pblk_setup_w_rec_rq(struct pblk *pblk, struct nvm_rq *rqd, @@ -280,7 +279,7 @@ int pblk_setup_w_rec_rq(struct pblk *pblk, struct nvm_rq *rqd, c_ctx->lun_bitmap = lun_bitmap; - ret = pblk_alloc_w_rq(pblk, rqd, rqd->nr_ppas); + ret = pblk_alloc_w_rq(pblk, rqd, rqd->nr_ppas, pblk_end_io_write); if (ret) return ret; @@ -311,16 +310,237 @@ static int pblk_calc_secs_to_sync(struct pblk *pblk, unsigned int secs_avail, return secs_to_sync; } +static inline int pblk_valid_meta_ppa(struct pblk *pblk, + struct pblk_line *meta_line, + struct ppa_addr *ppa_list, int nr_ppas) +{ + struct nvm_tgt_dev *dev = pblk->dev; + struct nvm_geo *geo = &dev->geo; + struct pblk_line *data_line; + struct ppa_addr ppa, ppa_opt; + u64 paddr; + int i; + + data_line = &pblk->lines[pblk_dev_ppa_to_line(ppa_list[0])]; + paddr = pblk_lookup_page(pblk, meta_line); + ppa = addr_to_gen_ppa(pblk, paddr, 0); + + if (test_bit(pblk_ppa_to_pos(geo, ppa), data_line->blk_bitmap)) + return 1; + + /* Schedule a metadata I/O that is half the distance from the data I/O + * with regards to the number of LUNs forming the pblk instance. This + * balances LUN conflicts across every I/O. + * + * When the LUN configuration changes (e.g., due to GC), this distance + * can align, which would result on a LUN deadlock. In this case, modify + * the distance to not be optimal, but allow metadata I/Os to succeed. + */ + ppa_opt = addr_to_gen_ppa(pblk, paddr + data_line->meta_distance, 0); + if (unlikely(ppa_opt.ppa == ppa.ppa)) { + data_line->meta_distance--; + return 0; + } + + for (i = 0; i < nr_ppas; i += pblk->min_write_pgs) + if (ppa_list[i].g.ch == ppa_opt.g.ch && + ppa_list[i].g.lun == ppa_opt.g.lun) + return 1; + + if (test_bit(pblk_ppa_to_pos(geo, ppa_opt), data_line->blk_bitmap)) { + for (i = 0; i < nr_ppas; i += pblk->min_write_pgs) + if (ppa_list[i].g.ch == ppa.g.ch && + ppa_list[i].g.lun == ppa.g.lun) + return 0; + + return 1; + } + + return 0; +} + +int pblk_submit_meta_io(struct pblk *pblk, struct pblk_line *meta_line) +{ + struct nvm_tgt_dev *dev = pblk->dev; + struct nvm_geo *geo = &dev->geo; + struct pblk_line_mgmt *l_mg = &pblk->l_mg; + struct pblk_line_meta *lm = &pblk->lm; + struct pblk_emeta *emeta = meta_line->emeta; + struct pblk_g_ctx *m_ctx; + struct pblk_lun *rlun; + struct bio *bio; + struct nvm_rq *rqd; + void *data; + u64 paddr; + int rq_ppas = pblk->min_write_pgs; + int id = meta_line->id; + int rq_len; + int i, j; + int ret; + + rqd = pblk_alloc_rqd(pblk, READ); + if (IS_ERR(rqd)) { + pr_err("pblk: cannot allocate write req.\n"); + return PTR_ERR(rqd); + } + m_ctx = nvm_rq_to_pdu(rqd); + m_ctx->private = meta_line; + + rq_len = rq_ppas * geo->sec_size; + data = ((void *)emeta->buf) + emeta->mem; + + bio = pblk_bio_map_addr(pblk, data, rq_ppas, rq_len, + l_mg->emeta_alloc_type, GFP_KERNEL); + if (IS_ERR(bio)) { + ret = PTR_ERR(bio); + goto fail_free_rqd; + } + bio->bi_iter.bi_sector = 0; /* internal bio */ + bio_set_op_attrs(bio, REQ_OP_WRITE, 0); + rqd->bio = bio; + + ret = pblk_alloc_w_rq(pblk, rqd, rq_ppas, pblk_end_io_write_meta); + if (ret) + goto fail_free_bio; + + for (i = 0; i < rqd->nr_ppas; ) { + spin_lock(&meta_line->lock); + paddr = __pblk_alloc_page(pblk, meta_line, rq_ppas); + spin_unlock(&meta_line->lock); + for (j = 0; j < rq_ppas; j++, i++, paddr++) + rqd->ppa_list[i] = addr_to_gen_ppa(pblk, paddr, id); + } + + rlun = &pblk->luns[pblk_ppa_to_pos(geo, rqd->ppa_list[0])]; + ret = down_timeout(&rlun->wr_sem, msecs_to_jiffies(5000)); + if (ret) { + pr_err("pblk: lun semaphore timed out (%d)\n", ret); + goto fail_free_bio; + } + + emeta->mem += rq_len; + if (emeta->mem >= lm->emeta_len[0]) { + spin_lock(&l_mg->close_lock); + list_del(&meta_line->list); + WARN(!bitmap_full(meta_line->map_bitmap, lm->sec_per_line), + "pblk: corrupt meta line %d\n", meta_line->id); + spin_unlock(&l_mg->close_lock); + } + + ret = pblk_submit_io(pblk, rqd); + if (ret) { + pr_err("pblk: emeta I/O submission failed: %d\n", ret); + goto fail_rollback; + } + + return NVM_IO_OK; + +fail_rollback: + spin_lock(&l_mg->close_lock); + pblk_dealloc_page(pblk, meta_line, rq_ppas); + list_add(&meta_line->list, &meta_line->list); + spin_unlock(&l_mg->close_lock); +fail_free_bio: + if (likely(l_mg->emeta_alloc_type == PBLK_VMALLOC_META)) + bio_put(bio); +fail_free_rqd: + pblk_free_rqd(pblk, rqd, READ); + return ret; +} + +static int pblk_sched_meta_io(struct pblk *pblk, struct ppa_addr *prev_list, + int prev_n) +{ + struct pblk_line_meta *lm = &pblk->lm; + struct pblk_line_mgmt *l_mg = &pblk->l_mg; + struct pblk_line *meta_line; + + spin_lock(&l_mg->close_lock); +retry: + if (list_empty(&l_mg->emeta_list)) { + spin_unlock(&l_mg->close_lock); + return 0; + } + meta_line = list_first_entry(&l_mg->emeta_list, struct pblk_line, list); + if (bitmap_full(meta_line->map_bitmap, lm->sec_per_line)) + goto retry; + spin_unlock(&l_mg->close_lock); + + if (!pblk_valid_meta_ppa(pblk, meta_line, prev_list, prev_n)) + return 0; + + return pblk_submit_meta_io(pblk, meta_line); +} + +static int pblk_submit_io_set(struct pblk *pblk, struct nvm_rq *rqd) +{ + struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd); + struct ppa_addr erase_ppa; + int err; + + ppa_set_empty(&erase_ppa); + + /* Assign lbas to ppas and populate request structure */ + err = pblk_setup_w_rq(pblk, rqd, c_ctx, &erase_ppa); + if (err) { + pr_err("pblk: could not setup write request: %d\n", err); + return NVM_IO_ERR; + } + + if (likely(ppa_empty(erase_ppa))) { + /* Submit metadata write for previous data line */ + err = pblk_sched_meta_io(pblk, rqd->ppa_list, rqd->nr_ppas); + if (err) { + pr_err("pblk: metadata I/O submission failed: %d", err); + return NVM_IO_ERR; + } + + /* Submit data write for current data line */ + err = pblk_submit_io(pblk, rqd); + if (err) { + pr_err("pblk: data I/O submission failed: %d\n", err); + return NVM_IO_ERR; + } + } else { + /* Submit data write for current data line */ + err = pblk_submit_io(pblk, rqd); + if (err) { + pr_err("pblk: data I/O submission failed: %d\n", err); + return NVM_IO_ERR; + } + + /* Submit available erase for next data line */ + if (pblk_blk_erase_async(pblk, erase_ppa)) { + struct pblk_line *e_line = pblk_line_get_erase(pblk); + struct nvm_tgt_dev *dev = pblk->dev; + struct nvm_geo *geo = &dev->geo; + int bit; + + atomic_inc(&e_line->left_eblks); + bit = pblk_ppa_to_pos(geo, erase_ppa); + WARN_ON(!test_and_clear_bit(bit, e_line->erase_bitmap)); + } + } + + return NVM_IO_OK; +} + +static void pblk_free_write_rqd(struct pblk *pblk, struct nvm_rq *rqd) +{ + struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd); + struct bio *bio = rqd->bio; + + if (c_ctx->nr_padded) + pblk_bio_free_pages(pblk, bio, rqd->nr_ppas, c_ctx->nr_padded); +} + static int pblk_submit_write(struct pblk *pblk) { struct bio *bio; struct nvm_rq *rqd; - struct pblk_c_ctx *c_ctx; - unsigned int pgs_read; unsigned int secs_avail, secs_to_sync, secs_to_com; unsigned int secs_to_flush; unsigned long pos; - int err; /* If there are no sectors in the cache, flushes (bios without data) * will be cleared on the cache threads @@ -338,7 +558,6 @@ static int pblk_submit_write(struct pblk *pblk) pr_err("pblk: cannot allocate write req.\n"); return 1; } - c_ctx = nvm_rq_to_pdu(rqd); bio = bio_alloc(GFP_KERNEL, pblk->max_write_pgs); if (!bio) { @@ -358,29 +577,14 @@ static int pblk_submit_write(struct pblk *pblk) secs_to_com = (secs_to_sync > secs_avail) ? secs_avail : secs_to_sync; pos = pblk_rb_read_commit(&pblk->rwb, secs_to_com); - pgs_read = pblk_rb_read_to_bio(&pblk->rwb, bio, c_ctx, pos, - secs_to_sync, secs_avail); - if (!pgs_read) { + if (pblk_rb_read_to_bio(&pblk->rwb, rqd, bio, pos, secs_to_sync, + secs_avail)) { pr_err("pblk: corrupted write bio\n"); goto fail_put_bio; } - if (c_ctx->nr_padded) - if (pblk_bio_add_pages(pblk, bio, GFP_KERNEL, c_ctx->nr_padded)) - goto fail_put_bio; - - /* Assign lbas to ppas and populate request structure */ - err = pblk_setup_w_rq(pblk, rqd, c_ctx); - if (err) { - pr_err("pblk: could not setup write request\n"); - goto fail_free_bio; - } - - err = pblk_submit_io(pblk, rqd); - if (err) { - pr_err("pblk: I/O submission failed: %d\n", err); + if (pblk_submit_io_set(pblk, rqd)) goto fail_free_bio; - } #ifdef CONFIG_NVM_DEBUG atomic_long_add(secs_to_sync, &pblk->sub_writes); @@ -389,8 +593,7 @@ static int pblk_submit_write(struct pblk *pblk) return 0; fail_free_bio: - if (c_ctx->nr_padded) - pblk_bio_free_pages(pblk, bio, secs_to_sync, c_ctx->nr_padded); + pblk_free_write_rqd(pblk, rqd); fail_put_bio: bio_put(bio); fail_free_rqd: diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h index 99f3186b5288..15931381348c 100644 --- a/drivers/lightnvm/pblk.h +++ b/drivers/lightnvm/pblk.h @@ -40,6 +40,12 @@ #define PBLK_MAX_REQ_ADDRS (64) #define PBLK_MAX_REQ_ADDRS_PW (6) +#define PBLK_WS_POOL_SIZE (128) +#define PBLK_META_POOL_SIZE (128) +#define PBLK_READ_REQ_POOL_SIZE (1024) + +#define PBLK_NR_CLOSE_JOBS (4) + #define PBLK_CACHE_NAME_LEN (DISK_NAME_LEN + 16) #define PBLK_COMMAND_TIMEOUT_MS 30000 @@ -72,11 +78,15 @@ enum { PBLK_BLK_ST_CLOSED = 0x2, }; +struct pblk_sec_meta { + u64 reserved; + __le64 lba; +}; + /* The number of GC lists and the rate-limiter states go together. This way the * rate-limiter can dictate how much GC is needed based on resource utilization. */ -#define PBLK_NR_GC_LISTS 3 -#define PBLK_MAX_GC_JOBS 32 +#define PBLK_GC_NR_LISTS 3 enum { PBLK_RL_HIGH = 1, @@ -84,14 +94,9 @@ enum { PBLK_RL_LOW = 3, }; -struct pblk_sec_meta { - u64 reserved; - __le64 lba; -}; - #define pblk_dma_meta_size (sizeof(struct pblk_sec_meta) * PBLK_MAX_REQ_ADDRS) -/* write completion context */ +/* write buffer completion context */ struct pblk_c_ctx { struct list_head list; /* Head for out-of-order completion */ @@ -101,9 +106,16 @@ struct pblk_c_ctx { unsigned int nr_padded; }; -/* Read context */ -struct pblk_r_ctx { - struct bio *orig_bio; +/* generic context */ +struct pblk_g_ctx { + void *private; +}; + +/* Pad context */ +struct pblk_pad_rq { + struct pblk *pblk; + struct completion wait; + struct kref ref; }; /* Recovery context */ @@ -195,29 +207,39 @@ struct pblk_lun { struct pblk_gc_rq { struct pblk_line *line; void *data; - u64 *lba_list; + u64 lba_list[PBLK_MAX_REQ_ADDRS]; int nr_secs; int secs_to_gc; struct list_head list; }; struct pblk_gc { + /* These states are not protected by a lock since (i) they are in the + * fast path, and (ii) they are not critical. + */ int gc_active; int gc_enabled; int gc_forced; - int gc_jobs_active; - atomic_t inflight_gc; struct task_struct *gc_ts; struct task_struct *gc_writer_ts; + struct task_struct *gc_reader_ts; + + struct workqueue_struct *gc_line_reader_wq; struct workqueue_struct *gc_reader_wq; + struct timer_list gc_timer; + struct semaphore gc_sem; + atomic_t inflight_gc; int w_entries; + struct list_head w_list; + struct list_head r_list; spinlock_t lock; spinlock_t w_lock; + spinlock_t r_lock; }; struct pblk_rl { @@ -229,10 +251,8 @@ struct pblk_rl { */ unsigned int high_pw; /* High rounded up as a power of 2 */ -#define PBLK_USER_HIGH_THRS 2 /* Begin write limit at 50 percent - * available blks - */ -#define PBLK_USER_LOW_THRS 20 /* Aggressive GC at 5% available blocks */ +#define PBLK_USER_HIGH_THRS 8 /* Begin write limit at 12% available blks */ +#define PBLK_USER_LOW_THRS 10 /* Aggressive GC at 10% available blocks */ int rb_windows_pw; /* Number of rate windows in the write buffer * given as a power-of-2. This guarantees that @@ -244,13 +264,19 @@ struct pblk_rl { */ int rb_budget; /* Total number of entries available for I/O */ int rb_user_max; /* Max buffer entries available for user I/O */ - atomic_t rb_user_cnt; /* User I/O buffer counter */ int rb_gc_max; /* Max buffer entries available for GC I/O */ int rb_gc_rsv; /* Reserved buffer entries for GC I/O */ int rb_state; /* Rate-limiter current state */ + + atomic_t rb_user_cnt; /* User I/O buffer counter */ atomic_t rb_gc_cnt; /* GC I/O buffer counter */ + atomic_t rb_space; /* Space limit in case of reaching capacity */ + + int rsv_blocks; /* Reserved blocks for GC */ int rb_user_active; + int rb_gc_active; + struct timer_list u_timer; unsigned long long nr_secs; @@ -258,8 +284,6 @@ struct pblk_rl { atomic_t free_blocks; }; -#define PBLK_LINE_NR_LUN_BITMAP 2 -#define PBLK_LINE_NR_SEC_BITMAP 2 #define PBLK_LINE_EMPTY (~0U) enum { @@ -310,16 +334,19 @@ struct line_smeta { __le32 window_wr_lun; /* Number of parallel LUNs to write */ __le32 rsvd[2]; + + __le64 lun_bitmap[]; }; /* - * Metadata Layout: - * 1. struct pblk_emeta - * 2. nr_lbas u64 forming lba list - * 3. nr_lines (all) u32 valid sector count (vsc) (~0U: non-alloc line) - * 4. nr_luns bits (u64 format) forming line bad block bitmap - * - * 3. and 4. will be part of FTL log + * Metadata layout in media: + * First sector: + * 1. struct line_emeta + * 2. bad block bitmap (u64 * window_wr_lun) + * Mid sectors (start at lbas_sector): + * 3. nr_lbas (u64) forming lba list + * Last sectors (start at vsc_sector): + * 4. u32 valid sector count (vsc) for all lines (~0U: free line) */ struct line_emeta { struct line_header header; @@ -339,6 +366,23 @@ struct line_emeta { __le32 next_id; /* Line id for next line */ __le64 nr_lbas; /* Number of lbas mapped in line */ __le64 nr_valid_lbas; /* Number of valid lbas mapped in line */ + __le64 bb_bitmap[]; /* Updated bad block bitmap for line */ +}; + +struct pblk_emeta { + struct line_emeta *buf; /* emeta buffer in media format */ + int mem; /* Write offset - points to next + * writable entry in memory + */ + atomic_t sync; /* Synced - backpointer that signals the + * last entry that has been successfully + * persisted to media + */ + unsigned int nr_entries; /* Number of emeta entries */ +}; + +struct pblk_smeta { + struct line_smeta *buf; /* smeta buffer in persistent format */ }; struct pblk_line { @@ -355,9 +399,12 @@ struct pblk_line { unsigned long *lun_bitmap; /* Bitmap for LUNs mapped in line */ - struct line_smeta *smeta; /* Start metadata */ - struct line_emeta *emeta; /* End metadata */ + struct pblk_smeta *smeta; /* Start metadata */ + struct pblk_emeta *emeta; /* End medatada */ + int meta_line; /* Metadata line id */ + int meta_distance; /* Distance between data and metadata */ + u64 smeta_ssec; /* Sector where smeta starts */ u64 emeta_ssec; /* Sector where emeta starts */ @@ -374,9 +421,10 @@ struct pblk_line { atomic_t left_seblks; /* Blocks left for sync erasing */ int left_msecs; /* Sectors left for mapping */ - int left_ssecs; /* Sectors left to sync */ unsigned int cur_sec; /* Sector map pointer */ - unsigned int vsc; /* Valid sector count in line */ + unsigned int nr_valid_lbas; /* Number of valid lbas in line */ + + __le32 *vsc; /* Valid sector count in line */ struct kref ref; /* Write buffer L2P references */ @@ -385,13 +433,15 @@ struct pblk_line { #define PBLK_DATA_LINES 4 -enum{ +enum { PBLK_KMALLOC_META = 1, PBLK_VMALLOC_META = 2, }; -struct pblk_line_metadata { - void *meta; +enum { + PBLK_EMETA_TYPE_HEADER = 1, /* struct line_emeta first sector */ + PBLK_EMETA_TYPE_LLBA = 2, /* lba list - type: __le64 */ + PBLK_EMETA_TYPE_VSC = 3, /* vsc list - type: __le32 */ }; struct pblk_line_mgmt { @@ -404,7 +454,7 @@ struct pblk_line_mgmt { struct list_head bad_list; /* Full lines bad */ /* GC lists - use gc_lock */ - struct list_head *gc_lists[PBLK_NR_GC_LISTS]; + struct list_head *gc_lists[PBLK_GC_NR_LISTS]; struct list_head gc_high_list; /* Full lines ready to GC, high isc */ struct list_head gc_mid_list; /* Full lines ready to GC, mid isc */ struct list_head gc_low_list; /* Full lines ready to GC, low isc */ @@ -417,13 +467,16 @@ struct pblk_line_mgmt { struct pblk_line *log_next; /* Next FTL log line */ struct pblk_line *data_next; /* Next data line */ + struct list_head emeta_list; /* Lines queued to schedule emeta */ + + __le32 *vsc_list; /* Valid sector counts for all lines */ + /* Metadata allocation type: VMALLOC | KMALLOC */ - int smeta_alloc_type; int emeta_alloc_type; /* Pre-allocated metadata for data lines */ - struct pblk_line_metadata sline_meta[PBLK_DATA_LINES]; - struct pblk_line_metadata eline_meta[PBLK_DATA_LINES]; + struct pblk_smeta *sline_meta[PBLK_DATA_LINES]; + struct pblk_emeta *eline_meta[PBLK_DATA_LINES]; unsigned long meta_bitmap; /* Helpers for fast bitmap calculations */ @@ -434,25 +487,40 @@ struct pblk_line_mgmt { unsigned long l_seq_nr; /* Log line unique sequence number */ spinlock_t free_lock; + spinlock_t close_lock; spinlock_t gc_lock; }; struct pblk_line_meta { unsigned int smeta_len; /* Total length for smeta */ - unsigned int smeta_sec; /* Sectors needed for smeta*/ - unsigned int emeta_len; /* Total length for emeta */ - unsigned int emeta_sec; /* Sectors needed for emeta*/ + unsigned int smeta_sec; /* Sectors needed for smeta */ + + unsigned int emeta_len[4]; /* Lengths for emeta: + * [0]: Total length + * [1]: struct line_emeta length + * [2]: L2P portion length + * [3]: vsc list length + */ + unsigned int emeta_sec[4]; /* Sectors needed for emeta. Same layout + * as emeta_len + */ + unsigned int emeta_bb; /* Boundary for bb that affects emeta */ + + unsigned int vsc_list_len; /* Length for vsc list */ unsigned int sec_bitmap_len; /* Length for sector bitmap in line */ unsigned int blk_bitmap_len; /* Length for block bitmap in line */ unsigned int lun_bitmap_len; /* Length for lun bitmap in line */ unsigned int blk_per_line; /* Number of blocks in a full line */ unsigned int sec_per_line; /* Number of sectors in a line */ + unsigned int dsec_per_line; /* Number of data sectors in a line */ unsigned int min_blk_line; /* Min. number of good blocks in line */ unsigned int mid_thrs; /* Threshold for GC mid list */ unsigned int high_thrs; /* Threshold for GC high list */ + + unsigned int meta_distance; /* Distance between data and metadata */ }; struct pblk_addr_format { @@ -470,6 +538,13 @@ struct pblk_addr_format { u8 sec_offset; }; +enum { + PBLK_STATE_RUNNING = 0, + PBLK_STATE_STOPPING = 1, + PBLK_STATE_RECOVERING = 2, + PBLK_STATE_STOPPED = 3, +}; + struct pblk { struct nvm_tgt_dev *dev; struct gendisk *disk; @@ -487,6 +562,8 @@ struct pblk { struct pblk_rb rwb; + int state; /* pblk line state */ + int min_write_pgs; /* Minimum amount of pages required by controller */ int max_write_pgs; /* Maximum amount of pages supported by controller */ int pgs_in_buffer; /* Number of pages that need to be held in buffer to @@ -499,7 +576,7 @@ struct pblk { /* pblk provisioning values. Used by rate limiter */ struct pblk_rl rl; - struct semaphore erase_sem; + int sec_per_write; unsigned char instance_uuid[16]; #ifdef CONFIG_NVM_DEBUG @@ -511,8 +588,8 @@ struct pblk { atomic_long_t req_writes; /* Sectors stored on write buffer */ atomic_long_t sub_writes; /* Sectors submitted from buffer */ atomic_long_t sync_writes; /* Sectors synced to media */ - atomic_long_t compl_writes; /* Sectors completed in write bio */ atomic_long_t inflight_reads; /* Inflight sector read requests */ + atomic_long_t cache_reads; /* Read requests that hit the cache */ atomic_long_t sync_reads; /* Completed sector read requests */ atomic_long_t recov_writes; /* Sectors submitted from recovery */ atomic_long_t recov_gc_writes; /* Sectors submitted from write GC */ @@ -528,6 +605,8 @@ struct pblk { atomic_long_t write_failed; atomic_long_t erase_failed; + atomic_t inflight_io; /* General inflight I/O counter */ + struct task_struct *writer_ts; /* Simple translation map of logical addresses to physical addresses. @@ -542,11 +621,13 @@ struct pblk { mempool_t *page_pool; mempool_t *line_ws_pool; mempool_t *rec_pool; - mempool_t *r_rq_pool; + mempool_t *g_rq_pool; mempool_t *w_rq_pool; mempool_t *line_meta_pool; - struct workqueue_struct *kw_wq; + struct workqueue_struct *close_wq; + struct workqueue_struct *bb_wq; + struct timer_list wtimer; struct pblk_gc gc; @@ -559,7 +640,7 @@ struct pblk_line_ws { struct work_struct ws; }; -#define pblk_r_rq_size (sizeof(struct nvm_rq) + sizeof(struct pblk_r_ctx)) +#define pblk_g_rq_size (sizeof(struct nvm_rq) + sizeof(struct pblk_g_ctx)) #define pblk_w_rq_size (sizeof(struct nvm_rq) + sizeof(struct pblk_c_ctx)) /* @@ -579,18 +660,17 @@ void pblk_rb_write_entry_gc(struct pblk_rb *rb, void *data, struct pblk_w_ctx w_ctx, struct pblk_line *gc_line, unsigned int pos); struct pblk_w_ctx *pblk_rb_w_ctx(struct pblk_rb *rb, unsigned int pos); +void pblk_rb_flush(struct pblk_rb *rb); void pblk_rb_sync_l2p(struct pblk_rb *rb); -unsigned int pblk_rb_read_to_bio(struct pblk_rb *rb, struct bio *bio, - struct pblk_c_ctx *c_ctx, - unsigned int pos, - unsigned int nr_entries, - unsigned int count); +unsigned int pblk_rb_read_to_bio(struct pblk_rb *rb, struct nvm_rq *rqd, + struct bio *bio, unsigned int pos, + unsigned int nr_entries, unsigned int count); unsigned int pblk_rb_read_to_bio_list(struct pblk_rb *rb, struct bio *bio, struct list_head *list, unsigned int max); int pblk_rb_copy_to_bio(struct pblk_rb *rb, struct bio *bio, sector_t lba, - u64 pos, int bio_iter); + struct ppa_addr ppa, int bio_iter); unsigned int pblk_rb_read_commit(struct pblk_rb *rb, unsigned int entries); unsigned int pblk_rb_sync_init(struct pblk_rb *rb, unsigned long *flags); @@ -601,6 +681,7 @@ void pblk_rb_sync_end(struct pblk_rb *rb, unsigned long *flags); unsigned int pblk_rb_sync_point_count(struct pblk_rb *rb); unsigned int pblk_rb_read_count(struct pblk_rb *rb); +unsigned int pblk_rb_sync_count(struct pblk_rb *rb); unsigned int pblk_rb_wrap_pos(struct pblk_rb *rb, unsigned int pos); int pblk_rb_tear_down_check(struct pblk_rb *rb); @@ -612,40 +693,50 @@ ssize_t pblk_rb_sysfs(struct pblk_rb *rb, char *buf); * pblk core */ struct nvm_rq *pblk_alloc_rqd(struct pblk *pblk, int rw); +void pblk_set_sec_per_write(struct pblk *pblk, int sec_per_write); int pblk_setup_w_rec_rq(struct pblk *pblk, struct nvm_rq *rqd, struct pblk_c_ctx *c_ctx); void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int rw); -void pblk_flush_writer(struct pblk *pblk); +void pblk_wait_for_meta(struct pblk *pblk); struct ppa_addr pblk_get_lba_map(struct pblk *pblk, sector_t lba); void pblk_discard(struct pblk *pblk, struct bio *bio); void pblk_log_write_err(struct pblk *pblk, struct nvm_rq *rqd); void pblk_log_read_err(struct pblk *pblk, struct nvm_rq *rqd); int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd); +int pblk_submit_meta_io(struct pblk *pblk, struct pblk_line *meta_line); struct bio *pblk_bio_map_addr(struct pblk *pblk, void *data, unsigned int nr_secs, unsigned int len, - gfp_t gfp_mask); + int alloc_type, gfp_t gfp_mask); struct pblk_line *pblk_line_get(struct pblk *pblk); struct pblk_line *pblk_line_get_first_data(struct pblk *pblk); -struct pblk_line *pblk_line_replace_data(struct pblk *pblk); +void pblk_line_replace_data(struct pblk *pblk); int pblk_line_recov_alloc(struct pblk *pblk, struct pblk_line *line); void pblk_line_recov_close(struct pblk *pblk, struct pblk_line *line); struct pblk_line *pblk_line_get_data(struct pblk *pblk); -struct pblk_line *pblk_line_get_data_next(struct pblk *pblk); +struct pblk_line *pblk_line_get_erase(struct pblk *pblk); int pblk_line_erase(struct pblk *pblk, struct pblk_line *line); int pblk_line_is_full(struct pblk_line *line); void pblk_line_free(struct pblk *pblk, struct pblk_line *line); -void pblk_line_close_ws(struct work_struct *work); +void pblk_line_close_meta(struct pblk *pblk, struct pblk_line *line); void pblk_line_close(struct pblk *pblk, struct pblk_line *line); +void pblk_line_close_meta_sync(struct pblk *pblk); +void pblk_line_close_ws(struct work_struct *work); +void pblk_pipeline_stop(struct pblk *pblk); void pblk_line_mark_bb(struct work_struct *work); void pblk_line_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv, - void (*work)(struct work_struct *)); + void (*work)(struct work_struct *), + struct workqueue_struct *wq); u64 pblk_line_smeta_start(struct pblk *pblk, struct pblk_line *line); int pblk_line_read_smeta(struct pblk *pblk, struct pblk_line *line); -int pblk_line_read_emeta(struct pblk *pblk, struct pblk_line *line); +int pblk_line_read_emeta(struct pblk *pblk, struct pblk_line *line, + void *emeta_buf); int pblk_blk_erase_async(struct pblk *pblk, struct ppa_addr erase_ppa); void pblk_line_put(struct kref *ref); struct list_head *pblk_line_gc_list(struct pblk *pblk, struct pblk_line *line); +u64 pblk_lookup_page(struct pblk *pblk, struct pblk_line *line); +void pblk_dealloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs); u64 pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs); +u64 __pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs); int pblk_calc_secs(struct pblk *pblk, unsigned long secs_avail, unsigned long secs_to_flush); void pblk_down_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas, @@ -656,11 +747,11 @@ void pblk_end_bio_sync(struct bio *bio); void pblk_end_io_sync(struct nvm_rq *rqd); int pblk_bio_add_pages(struct pblk *pblk, struct bio *bio, gfp_t flags, int nr_pages); -void pblk_map_pad_invalidate(struct pblk *pblk, struct pblk_line *line, - u64 paddr); void pblk_bio_free_pages(struct pblk *pblk, struct bio *bio, int off, int nr_pages); void pblk_map_invalidate(struct pblk *pblk, struct ppa_addr ppa); +void __pblk_map_invalidate(struct pblk *pblk, struct pblk_line *line, + u64 paddr); void pblk_update_map(struct pblk *pblk, sector_t lba, struct ppa_addr ppa); void pblk_update_map_cache(struct pblk *pblk, sector_t lba, struct ppa_addr ppa); @@ -702,6 +793,7 @@ void pblk_write_should_kick(struct pblk *pblk); /* * pblk read path */ +extern struct bio_set *pblk_bio_set; int pblk_submit_read(struct pblk *pblk, struct bio *bio); int pblk_submit_read_gc(struct pblk *pblk, u64 *lba_list, void *data, unsigned int nr_secs, unsigned int *secs_to_gc, @@ -711,7 +803,7 @@ int pblk_submit_read_gc(struct pblk *pblk, u64 *lba_list, void *data, */ void pblk_submit_rec(struct work_struct *work); struct pblk_line *pblk_recov_l2p(struct pblk *pblk); -void pblk_recov_pad(struct pblk *pblk); +int pblk_recov_pad(struct pblk *pblk); __le64 *pblk_recov_get_lba_list(struct pblk *pblk, struct line_emeta *emeta); int pblk_recov_setup_rq(struct pblk *pblk, struct pblk_c_ctx *c_ctx, struct pblk_rec_ctx *recovery, u64 *comp_bits, @@ -720,33 +812,40 @@ int pblk_recov_setup_rq(struct pblk *pblk, struct pblk_c_ctx *c_ctx, /* * pblk gc */ -#define PBLK_GC_TRIES 3 +#define PBLK_GC_MAX_READERS 8 /* Max number of outstanding GC reader jobs */ +#define PBLK_GC_W_QD 128 /* Queue depth for inflight GC write I/Os */ +#define PBLK_GC_L_QD 4 /* Queue depth for inflight GC lines */ +#define PBLK_GC_RSV_LINE 1 /* Reserved lines for GC */ int pblk_gc_init(struct pblk *pblk); void pblk_gc_exit(struct pblk *pblk); void pblk_gc_should_start(struct pblk *pblk); void pblk_gc_should_stop(struct pblk *pblk); -int pblk_gc_status(struct pblk *pblk); +void pblk_gc_should_kick(struct pblk *pblk); +void pblk_gc_kick(struct pblk *pblk); void pblk_gc_sysfs_state_show(struct pblk *pblk, int *gc_enabled, int *gc_active); -void pblk_gc_sysfs_force(struct pblk *pblk, int force); +int pblk_gc_sysfs_force(struct pblk *pblk, int force); /* * pblk rate limiter */ void pblk_rl_init(struct pblk_rl *rl, int budget); void pblk_rl_free(struct pblk_rl *rl); -int pblk_rl_gc_thrs(struct pblk_rl *rl); +int pblk_rl_high_thrs(struct pblk_rl *rl); +int pblk_rl_low_thrs(struct pblk_rl *rl); unsigned long pblk_rl_nr_free_blks(struct pblk_rl *rl); int pblk_rl_user_may_insert(struct pblk_rl *rl, int nr_entries); +void pblk_rl_inserted(struct pblk_rl *rl, int nr_entries); void pblk_rl_user_in(struct pblk_rl *rl, int nr_entries); int pblk_rl_gc_may_insert(struct pblk_rl *rl, int nr_entries); void pblk_rl_gc_in(struct pblk_rl *rl, int nr_entries); void pblk_rl_out(struct pblk_rl *rl, int nr_user, int nr_gc); -void pblk_rl_set_gc_rsc(struct pblk_rl *rl, int rsv); int pblk_rl_sysfs_rate_show(struct pblk_rl *rl); void pblk_rl_free_lines_inc(struct pblk_rl *rl, struct pblk_line *line); void pblk_rl_free_lines_dec(struct pblk_rl *rl, struct pblk_line *line); +void pblk_rl_set_space_limit(struct pblk_rl *rl, int entries_left); +int pblk_rl_is_limit(struct pblk_rl *rl); /* * pblk sysfs @@ -774,9 +873,30 @@ static inline struct nvm_rq *nvm_rq_from_c_ctx(void *c_ctx) return c_ctx - sizeof(struct nvm_rq); } -static inline void *pblk_line_emeta_to_lbas(struct line_emeta *emeta) +static inline void *emeta_to_bb(struct line_emeta *emeta) +{ + return emeta->bb_bitmap; +} + +static inline void *emeta_to_lbas(struct pblk *pblk, struct line_emeta *emeta) +{ + return ((void *)emeta + pblk->lm.emeta_len[1]); +} + +static inline void *emeta_to_vsc(struct pblk *pblk, struct line_emeta *emeta) { - return (emeta) + 1; + return (emeta_to_lbas(pblk, emeta) + pblk->lm.emeta_len[2]); +} + +static inline int pblk_line_vsc(struct pblk_line *line) +{ + int vsc; + + spin_lock(&line->lock); + vsc = le32_to_cpu(*line->vsc); + spin_unlock(&line->lock); + + return vsc; } #define NVM_MEM_PAGE_WRITE (8) @@ -917,6 +1037,14 @@ static inline void pblk_ppa_set_empty(struct ppa_addr *ppa_addr) ppa_addr->ppa = ADDR_EMPTY; } +static inline bool pblk_ppa_comp(struct ppa_addr lppa, struct ppa_addr rppa) +{ + if (lppa.ppa == rppa.ppa) + return true; + + return false; +} + static inline int pblk_addr_in_cache(struct ppa_addr ppa) { return (ppa.ppa != ADDR_EMPTY && ppa.c.is_cached); @@ -964,11 +1092,11 @@ static inline struct ppa_addr addr_to_pblk_ppa(struct pblk *pblk, u64 paddr, } static inline u32 pblk_calc_meta_header_crc(struct pblk *pblk, - struct line_smeta *smeta) + struct line_header *header) { u32 crc = ~(u32)0; - crc = crc32_le(crc, (unsigned char *)smeta + sizeof(crc), + crc = crc32_le(crc, (unsigned char *)header + sizeof(crc), sizeof(struct line_header) - sizeof(crc)); return crc; @@ -996,7 +1124,7 @@ static inline u32 pblk_calc_emeta_crc(struct pblk *pblk, crc = crc32_le(crc, (unsigned char *)emeta + sizeof(struct line_header) + sizeof(crc), - lm->emeta_len - + lm->emeta_len[0] - sizeof(struct line_header) - sizeof(crc)); return crc; @@ -1016,9 +1144,27 @@ static inline int pblk_set_progr_mode(struct pblk *pblk, int type) return flags; } -static inline int pblk_set_read_mode(struct pblk *pblk) +enum { + PBLK_READ_RANDOM = 0, + PBLK_READ_SEQUENTIAL = 1, +}; + +static inline int pblk_set_read_mode(struct pblk *pblk, int type) +{ + struct nvm_tgt_dev *dev = pblk->dev; + struct nvm_geo *geo = &dev->geo; + int flags; + + flags = NVM_IO_SUSPEND | NVM_IO_SCRAMBLE_ENABLE; + if (type == PBLK_READ_SEQUENTIAL) + flags |= geo->plane_mode >> 1; + + return flags; +} + +static inline int pblk_io_aligned(struct pblk *pblk, int nr_secs) { - return NVM_IO_SNGL_ACCESS | NVM_IO_SUSPEND | NVM_IO_SCRAMBLE_ENABLE; + return !(nr_secs % pblk->min_write_pgs); } #ifdef CONFIG_NVM_DEBUG diff --git a/drivers/lightnvm/rrpc.c b/drivers/lightnvm/rrpc.c index cf0e28a0ff61..267f01ae87e4 100644 --- a/drivers/lightnvm/rrpc.c +++ b/drivers/lightnvm/rrpc.c @@ -279,8 +279,8 @@ static void rrpc_end_sync_bio(struct bio *bio) { struct completion *waiting = bio->bi_private; - if (bio->bi_error) - pr_err("nvm: gc request failed (%u).\n", bio->bi_error); + if (bio->bi_status) + pr_err("nvm: gc request failed (%u).\n", bio->bi_status); complete(waiting); } @@ -359,7 +359,7 @@ try: goto finished; } wait_for_completion_io(&wait); - if (bio->bi_error) { + if (bio->bi_status) { rrpc_inflight_laddr_release(rrpc, rqd); goto finished; } @@ -385,7 +385,7 @@ try: wait_for_completion_io(&wait); rrpc_inflight_laddr_release(rrpc, rqd); - if (bio->bi_error) + if (bio->bi_status) goto finished; bio_reset(bio); @@ -994,7 +994,7 @@ static blk_qc_t rrpc_make_rq(struct request_queue *q, struct bio *bio) struct nvm_rq *rqd; int err; - blk_queue_split(q, &bio, q->bio_split); + blk_queue_split(q, &bio); if (bio_op(bio) == REQ_OP_DISCARD) { rrpc_discard(rrpc, bio); diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index c3ea03c9a1a8..dee542fff68e 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -849,10 +849,11 @@ static inline void wake_up_allocators(struct cache_set *c) /* Forward declarations */ -void bch_count_io_errors(struct cache *, int, const char *); +void bch_count_io_errors(struct cache *, blk_status_t, const char *); void bch_bbio_count_io_errors(struct cache_set *, struct bio *, - int, const char *); -void bch_bbio_endio(struct cache_set *, struct bio *, int, const char *); + blk_status_t, const char *); +void bch_bbio_endio(struct cache_set *, struct bio *, blk_status_t, + const char *); void bch_bbio_free(struct bio *, struct cache_set *); struct bio *bch_bbio_alloc(struct cache_set *); diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index 450d0e848ae4..866dcf78ff8e 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -307,7 +307,7 @@ static void bch_btree_node_read(struct btree *b) bch_submit_bbio(bio, b->c, &b->key, 0); closure_sync(&cl); - if (bio->bi_error) + if (bio->bi_status) set_btree_node_io_error(b); bch_bbio_free(bio, b->c); @@ -374,10 +374,10 @@ static void btree_node_write_endio(struct bio *bio) struct closure *cl = bio->bi_private; struct btree *b = container_of(cl, struct btree, io); - if (bio->bi_error) + if (bio->bi_status) set_btree_node_io_error(b); - bch_bbio_count_io_errors(b->c, bio, bio->bi_error, "writing btree"); + bch_bbio_count_io_errors(b->c, bio, bio->bi_status, "writing btree"); closure_put(cl); } diff --git a/drivers/md/bcache/btree.h b/drivers/md/bcache/btree.h index 9b80417cd547..73da1f5626cb 100644 --- a/drivers/md/bcache/btree.h +++ b/drivers/md/bcache/btree.h @@ -207,7 +207,7 @@ void bkey_put(struct cache_set *c, struct bkey *k); struct btree_op { /* for waiting on btree reserve in btree_split() */ - wait_queue_t wait; + wait_queue_entry_t wait; /* Btree level at which we start taking write locks */ short lock; diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c index 06f55056aaae..35a5a7210e51 100644 --- a/drivers/md/bcache/debug.c +++ b/drivers/md/bcache/debug.c @@ -110,7 +110,7 @@ void bch_data_verify(struct cached_dev *dc, struct bio *bio) struct bio_vec bv, cbv; struct bvec_iter iter, citer = { 0 }; - check = bio_clone(bio, GFP_NOIO); + check = bio_clone_kmalloc(bio, GFP_NOIO); if (!check) return; check->bi_opf = REQ_OP_READ; diff --git a/drivers/md/bcache/io.c b/drivers/md/bcache/io.c index db45a88c0ce9..6a9b85095e7b 100644 --- a/drivers/md/bcache/io.c +++ b/drivers/md/bcache/io.c @@ -50,7 +50,7 @@ void bch_submit_bbio(struct bio *bio, struct cache_set *c, /* IO errors */ -void bch_count_io_errors(struct cache *ca, int error, const char *m) +void bch_count_io_errors(struct cache *ca, blk_status_t error, const char *m) { /* * The halflife of an error is: @@ -103,7 +103,7 @@ void bch_count_io_errors(struct cache *ca, int error, const char *m) } void bch_bbio_count_io_errors(struct cache_set *c, struct bio *bio, - int error, const char *m) + blk_status_t error, const char *m) { struct bbio *b = container_of(bio, struct bbio, bio); struct cache *ca = PTR_CACHE(c, &b->key, 0); @@ -132,7 +132,7 @@ void bch_bbio_count_io_errors(struct cache_set *c, struct bio *bio, } void bch_bbio_endio(struct cache_set *c, struct bio *bio, - int error, const char *m) + blk_status_t error, const char *m) { struct closure *cl = bio->bi_private; diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c index 1198e53d5670..0352d05e495c 100644 --- a/drivers/md/bcache/journal.c +++ b/drivers/md/bcache/journal.c @@ -549,7 +549,7 @@ static void journal_write_endio(struct bio *bio) { struct journal_write *w = bio->bi_private; - cache_set_err_on(bio->bi_error, w->c, "journal io error"); + cache_set_err_on(bio->bi_status, w->c, "journal io error"); closure_put(&w->c->journal.io); } diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c index 13b8a907006d..f633b30c962e 100644 --- a/drivers/md/bcache/movinggc.c +++ b/drivers/md/bcache/movinggc.c @@ -63,14 +63,14 @@ static void read_moving_endio(struct bio *bio) struct moving_io *io = container_of(bio->bi_private, struct moving_io, cl); - if (bio->bi_error) - io->op.error = bio->bi_error; + if (bio->bi_status) + io->op.status = bio->bi_status; else if (!KEY_DIRTY(&b->key) && ptr_stale(io->op.c, &b->key, 0)) { - io->op.error = -EINTR; + io->op.status = BLK_STS_IOERR; } - bch_bbio_endio(io->op.c, bio, bio->bi_error, "reading data to move"); + bch_bbio_endio(io->op.c, bio, bio->bi_status, "reading data to move"); } static void moving_init(struct moving_io *io) @@ -92,7 +92,7 @@ static void write_moving(struct closure *cl) struct moving_io *io = container_of(cl, struct moving_io, cl); struct data_insert_op *op = &io->op; - if (!op->error) { + if (!op->status) { moving_init(io); io->bio.bio.bi_iter.bi_sector = KEY_START(&io->w->key); diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 709c9cc34369..019b3df9f1c6 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -81,7 +81,7 @@ static void bch_data_insert_keys(struct closure *cl) if (ret == -ESRCH) { op->replace_collision = true; } else if (ret) { - op->error = -ENOMEM; + op->status = BLK_STS_RESOURCE; op->insert_data_done = true; } @@ -178,17 +178,17 @@ static void bch_data_insert_endio(struct bio *bio) struct closure *cl = bio->bi_private; struct data_insert_op *op = container_of(cl, struct data_insert_op, cl); - if (bio->bi_error) { + if (bio->bi_status) { /* TODO: We could try to recover from this. */ if (op->writeback) - op->error = bio->bi_error; + op->status = bio->bi_status; else if (!op->replace) set_closure_fn(cl, bch_data_insert_error, op->wq); else set_closure_fn(cl, NULL, NULL); } - bch_bbio_endio(op->c, bio, bio->bi_error, "writing data to cache"); + bch_bbio_endio(op->c, bio, bio->bi_status, "writing data to cache"); } static void bch_data_insert_start(struct closure *cl) @@ -488,15 +488,15 @@ static void bch_cache_read_endio(struct bio *bio) * from the backing device. */ - if (bio->bi_error) - s->iop.error = bio->bi_error; + if (bio->bi_status) + s->iop.status = bio->bi_status; else if (!KEY_DIRTY(&b->key) && ptr_stale(s->iop.c, &b->key, 0)) { atomic_long_inc(&s->iop.c->cache_read_races); - s->iop.error = -EINTR; + s->iop.status = BLK_STS_IOERR; } - bch_bbio_endio(s->iop.c, bio, bio->bi_error, "reading from cache"); + bch_bbio_endio(s->iop.c, bio, bio->bi_status, "reading from cache"); } /* @@ -593,9 +593,9 @@ static void request_endio(struct bio *bio) { struct closure *cl = bio->bi_private; - if (bio->bi_error) { + if (bio->bi_status) { struct search *s = container_of(cl, struct search, cl); - s->iop.error = bio->bi_error; + s->iop.status = bio->bi_status; /* Only cache read errors are recoverable */ s->recoverable = false; } @@ -611,7 +611,7 @@ static void bio_complete(struct search *s) &s->d->disk->part0, s->start_time); trace_bcache_request_end(s->d, s->orig_bio); - s->orig_bio->bi_error = s->iop.error; + s->orig_bio->bi_status = s->iop.status; bio_endio(s->orig_bio); s->orig_bio = NULL; } @@ -664,7 +664,7 @@ static inline struct search *search_alloc(struct bio *bio, s->iop.inode = d->id; s->iop.write_point = hash_long((unsigned long) current, 16); s->iop.write_prio = 0; - s->iop.error = 0; + s->iop.status = 0; s->iop.flags = 0; s->iop.flush_journal = op_is_flush(bio->bi_opf); s->iop.wq = bcache_wq; @@ -707,7 +707,7 @@ static void cached_dev_read_error(struct closure *cl) /* Retry from the backing device: */ trace_bcache_read_retry(s->orig_bio); - s->iop.error = 0; + s->iop.status = 0; do_bio_hook(s, s->orig_bio); /* XXX: invalidate cache */ @@ -767,7 +767,7 @@ static void cached_dev_read_done_bh(struct closure *cl) !s->cache_miss, s->iop.bypass); trace_bcache_read(s->orig_bio, !s->cache_miss, s->iop.bypass); - if (s->iop.error) + if (s->iop.status) continue_at_nobarrier(cl, cached_dev_read_error, bcache_wq); else if (s->iop.bio || verify(dc, &s->bio.bio)) continue_at_nobarrier(cl, cached_dev_read_done, bcache_wq); diff --git a/drivers/md/bcache/request.h b/drivers/md/bcache/request.h index 1ff36875c2b3..7689176951ce 100644 --- a/drivers/md/bcache/request.h +++ b/drivers/md/bcache/request.h @@ -10,7 +10,7 @@ struct data_insert_op { unsigned inode; uint16_t write_point; uint16_t write_prio; - short error; + blk_status_t status; union { uint16_t flags; diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index e57353e39168..8352fad765f6 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -271,7 +271,7 @@ static void write_super_endio(struct bio *bio) { struct cache *ca = bio->bi_private; - bch_count_io_errors(ca, bio->bi_error, "writing superblock"); + bch_count_io_errors(ca, bio->bi_status, "writing superblock"); closure_put(&ca->set->sb_write); } @@ -321,7 +321,7 @@ static void uuid_endio(struct bio *bio) struct closure *cl = bio->bi_private; struct cache_set *c = container_of(cl, struct cache_set, uuid_write); - cache_set_err_on(bio->bi_error, c, "accessing uuids"); + cache_set_err_on(bio->bi_status, c, "accessing uuids"); bch_bbio_free(bio, c); closure_put(cl); } @@ -494,7 +494,7 @@ static void prio_endio(struct bio *bio) { struct cache *ca = bio->bi_private; - cache_set_err_on(bio->bi_error, ca->set, "accessing priorities"); + cache_set_err_on(bio->bi_status, ca->set, "accessing priorities"); bch_bbio_free(bio, ca->set); closure_put(&ca->prio); } @@ -782,7 +782,9 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size, minor *= BCACHE_MINORS; - if (!(d->bio_split = bioset_create(4, offsetof(struct bbio, bio))) || + if (!(d->bio_split = bioset_create(4, offsetof(struct bbio, bio), + BIOSET_NEED_BVECS | + BIOSET_NEED_RESCUER)) || !(d->disk = alloc_disk(BCACHE_MINORS))) { ida_simple_remove(&bcache_minor, minor); return -ENOMEM; @@ -1516,7 +1518,9 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb) sizeof(struct bbio) + sizeof(struct bio_vec) * bucket_pages(c))) || !(c->fill_iter = mempool_create_kmalloc_pool(1, iter_size)) || - !(c->bio_split = bioset_create(4, offsetof(struct bbio, bio))) || + !(c->bio_split = bioset_create(4, offsetof(struct bbio, bio), + BIOSET_NEED_BVECS | + BIOSET_NEED_RESCUER)) || !(c->uuids = alloc_bucket_pages(GFP_KERNEL, c)) || !(c->moving_gc_wq = alloc_workqueue("bcache_gc", WQ_MEM_RECLAIM, 0)) || diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index 6ac2e48b9235..42c66e76f05e 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -167,7 +167,7 @@ static void dirty_endio(struct bio *bio) struct keybuf_key *w = bio->bi_private; struct dirty_io *io = w->private; - if (bio->bi_error) + if (bio->bi_status) SET_KEY_DIRTY(&w->key, false); closure_put(&io->cl); @@ -195,7 +195,7 @@ static void read_dirty_endio(struct bio *bio) struct dirty_io *io = w->private; bch_count_io_errors(PTR_CACHE(io->dc->disk.c, &w->key, 0), - bio->bi_error, "reading dirty data from cache"); + bio->bi_status, "reading dirty data from cache"); dirty_endio(bio); } diff --git a/drivers/md/dm-bio-prison-v1.c b/drivers/md/dm-bio-prison-v1.c index ae7da2c30a57..82d27384d31f 100644 --- a/drivers/md/dm-bio-prison-v1.c +++ b/drivers/md/dm-bio-prison-v1.c @@ -229,7 +229,7 @@ void dm_cell_release_no_holder(struct dm_bio_prison *prison, EXPORT_SYMBOL_GPL(dm_cell_release_no_holder); void dm_cell_error(struct dm_bio_prison *prison, - struct dm_bio_prison_cell *cell, int error) + struct dm_bio_prison_cell *cell, blk_status_t error) { struct bio_list bios; struct bio *bio; @@ -238,7 +238,7 @@ void dm_cell_error(struct dm_bio_prison *prison, dm_cell_release(prison, cell, &bios); while ((bio = bio_list_pop(&bios))) { - bio->bi_error = error; + bio->bi_status = error; bio_endio(bio); } } diff --git a/drivers/md/dm-bio-prison-v1.h b/drivers/md/dm-bio-prison-v1.h index cddd4ac07e2c..cec52ac5e1ae 100644 --- a/drivers/md/dm-bio-prison-v1.h +++ b/drivers/md/dm-bio-prison-v1.h @@ -91,7 +91,7 @@ void dm_cell_release_no_holder(struct dm_bio_prison *prison, struct dm_bio_prison_cell *cell, struct bio_list *inmates); void dm_cell_error(struct dm_bio_prison *prison, - struct dm_bio_prison_cell *cell, int error); + struct dm_bio_prison_cell *cell, blk_status_t error); /* * Visits the cell and then releases. Guarantees no new inmates are diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 840c1496b2b1..850ff6c67994 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -145,8 +145,8 @@ struct dm_buffer { enum data_mode data_mode; unsigned char list_mode; /* LIST_* */ unsigned hold_count; - int read_error; - int write_error; + blk_status_t read_error; + blk_status_t write_error; unsigned long state; unsigned long last_accessed; struct dm_bufio_client *c; @@ -555,7 +555,7 @@ static void dmio_complete(unsigned long error, void *context) { struct dm_buffer *b = context; - b->bio.bi_error = error ? -EIO : 0; + b->bio.bi_status = error ? BLK_STS_IOERR : 0; b->bio.bi_end_io(&b->bio); } @@ -588,7 +588,7 @@ static void use_dmio(struct dm_buffer *b, int rw, sector_t sector, r = dm_io(&io_req, 1, ®ion, NULL); if (r) { - b->bio.bi_error = r; + b->bio.bi_status = errno_to_blk_status(r); end_io(&b->bio); } } @@ -596,7 +596,7 @@ static void use_dmio(struct dm_buffer *b, int rw, sector_t sector, static void inline_endio(struct bio *bio) { bio_end_io_t *end_fn = bio->bi_private; - int error = bio->bi_error; + blk_status_t status = bio->bi_status; /* * Reset the bio to free any attached resources @@ -604,7 +604,7 @@ static void inline_endio(struct bio *bio) */ bio_reset(bio); - bio->bi_error = error; + bio->bi_status = status; end_fn(bio); } @@ -685,11 +685,12 @@ static void write_endio(struct bio *bio) { struct dm_buffer *b = container_of(bio, struct dm_buffer, bio); - b->write_error = bio->bi_error; - if (unlikely(bio->bi_error)) { + b->write_error = bio->bi_status; + if (unlikely(bio->bi_status)) { struct dm_bufio_client *c = b->c; - int error = bio->bi_error; - (void)cmpxchg(&c->async_write_error, 0, error); + + (void)cmpxchg(&c->async_write_error, 0, + blk_status_to_errno(bio->bi_status)); } BUG_ON(!test_bit(B_WRITING, &b->state)); @@ -1063,7 +1064,7 @@ static void read_endio(struct bio *bio) { struct dm_buffer *b = container_of(bio, struct dm_buffer, bio); - b->read_error = bio->bi_error; + b->read_error = bio->bi_status; BUG_ON(!test_bit(B_READING, &b->state)); @@ -1107,7 +1108,7 @@ static void *new_read(struct dm_bufio_client *c, sector_t block, wait_on_bit_io(&b->state, B_READING, TASK_UNINTERRUPTIBLE); if (b->read_error) { - int error = b->read_error; + int error = blk_status_to_errno(b->read_error); dm_bufio_release(b); @@ -1257,7 +1258,8 @@ EXPORT_SYMBOL_GPL(dm_bufio_write_dirty_buffers_async); */ int dm_bufio_write_dirty_buffers(struct dm_bufio_client *c) { - int a, f; + blk_status_t a; + int f; unsigned long buffers_processed = 0; struct dm_buffer *b, *tmp; diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index d682a0511381..c5ea03fc7ee1 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -119,7 +119,7 @@ static void iot_io_end(struct io_tracker *iot, sector_t len) */ struct continuation { struct work_struct ws; - int input; + blk_status_t input; }; static inline void init_continuation(struct continuation *k, @@ -145,7 +145,7 @@ struct batcher { /* * The operation that everyone is waiting for. */ - int (*commit_op)(void *context); + blk_status_t (*commit_op)(void *context); void *commit_context; /* @@ -171,8 +171,7 @@ struct batcher { static void __commit(struct work_struct *_ws) { struct batcher *b = container_of(_ws, struct batcher, commit_work); - - int r; + blk_status_t r; unsigned long flags; struct list_head work_items; struct work_struct *ws, *tmp; @@ -205,7 +204,7 @@ static void __commit(struct work_struct *_ws) while ((bio = bio_list_pop(&bios))) { if (r) { - bio->bi_error = r; + bio->bi_status = r; bio_endio(bio); } else b->issue_op(bio, b->issue_context); @@ -213,7 +212,7 @@ static void __commit(struct work_struct *_ws) } static void batcher_init(struct batcher *b, - int (*commit_op)(void *), + blk_status_t (*commit_op)(void *), void *commit_context, void (*issue_op)(struct bio *bio, void *), void *issue_context, @@ -955,7 +954,7 @@ static void writethrough_endio(struct bio *bio) dm_unhook_bio(&pb->hook_info, bio); - if (bio->bi_error) { + if (bio->bi_status) { bio_endio(bio); return; } @@ -1220,7 +1219,7 @@ static void copy_complete(int read_err, unsigned long write_err, void *context) struct dm_cache_migration *mg = container_of(context, struct dm_cache_migration, k); if (read_err || write_err) - mg->k.input = -EIO; + mg->k.input = BLK_STS_IOERR; queue_continuation(mg->cache->wq, &mg->k); } @@ -1266,8 +1265,8 @@ static void overwrite_endio(struct bio *bio) dm_unhook_bio(&pb->hook_info, bio); - if (bio->bi_error) - mg->k.input = bio->bi_error; + if (bio->bi_status) + mg->k.input = bio->bi_status; queue_continuation(mg->cache->wq, &mg->k); } @@ -1323,8 +1322,10 @@ static void mg_complete(struct dm_cache_migration *mg, bool success) if (mg->overwrite_bio) { if (success) force_set_dirty(cache, cblock); + else if (mg->k.input) + mg->overwrite_bio->bi_status = mg->k.input; else - mg->overwrite_bio->bi_error = (mg->k.input ? : -EIO); + mg->overwrite_bio->bi_status = BLK_STS_IOERR; bio_endio(mg->overwrite_bio); } else { if (success) @@ -1504,7 +1505,7 @@ static void mg_copy(struct work_struct *ws) r = copy(mg, is_policy_promote); if (r) { DMERR_LIMIT("%s: migration copy failed", cache_device_name(cache)); - mg->k.input = -EIO; + mg->k.input = BLK_STS_IOERR; mg_complete(mg, false); } } @@ -1907,12 +1908,12 @@ static int commit(struct cache *cache, bool clean_shutdown) /* * Used by the batcher. */ -static int commit_op(void *context) +static blk_status_t commit_op(void *context) { struct cache *cache = context; if (dm_cache_changed_this_transaction(cache->cmd)) - return commit(cache, false); + return errno_to_blk_status(commit(cache, false)); return 0; } @@ -2018,7 +2019,7 @@ static void requeue_deferred_bios(struct cache *cache) bio_list_init(&cache->deferred_bios); while ((bio = bio_list_pop(&bios))) { - bio->bi_error = DM_ENDIO_REQUEUE; + bio->bi_status = BLK_STS_DM_REQUEUE; bio_endio(bio); } } @@ -2820,7 +2821,8 @@ static int cache_map(struct dm_target *ti, struct bio *bio) return r; } -static int cache_end_io(struct dm_target *ti, struct bio *bio, int error) +static int cache_end_io(struct dm_target *ti, struct bio *bio, + blk_status_t *error) { struct cache *cache = ti->private; unsigned long flags; @@ -2838,7 +2840,7 @@ static int cache_end_io(struct dm_target *ti, struct bio *bio, int error) bio_drop_shared_lock(cache, bio); accounted_complete(cache, bio); - return 0; + return DM_ENDIO_DONE; } static int write_dirty_bitset(struct cache *cache) diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index ebf9e72d479b..9e1b72e8f7ef 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -71,7 +71,7 @@ struct dm_crypt_io { struct convert_context ctx; atomic_t io_pending; - int error; + blk_status_t error; sector_t sector; struct rb_node rb_node; @@ -1292,7 +1292,7 @@ static void crypt_free_req(struct crypt_config *cc, void *req, struct bio *base_ /* * Encrypt / decrypt data from one bio to another one (can be the same one) */ -static int crypt_convert(struct crypt_config *cc, +static blk_status_t crypt_convert(struct crypt_config *cc, struct convert_context *ctx) { unsigned int tag_offset = 0; @@ -1343,13 +1343,13 @@ static int crypt_convert(struct crypt_config *cc, */ case -EBADMSG: atomic_dec(&ctx->cc_pending); - return -EILSEQ; + return BLK_STS_PROTECTION; /* * There was an error while processing the request. */ default: atomic_dec(&ctx->cc_pending); - return -EIO; + return BLK_STS_IOERR; } } @@ -1463,7 +1463,7 @@ static void crypt_dec_pending(struct dm_crypt_io *io) { struct crypt_config *cc = io->cc; struct bio *base_bio = io->base_bio; - int error = io->error; + blk_status_t error = io->error; if (!atomic_dec_and_test(&io->io_pending)) return; @@ -1476,7 +1476,7 @@ static void crypt_dec_pending(struct dm_crypt_io *io) else kfree(io->integrity_metadata); - base_bio->bi_error = error; + base_bio->bi_status = error; bio_endio(base_bio); } @@ -1502,7 +1502,7 @@ static void crypt_endio(struct bio *clone) struct dm_crypt_io *io = clone->bi_private; struct crypt_config *cc = io->cc; unsigned rw = bio_data_dir(clone); - int error; + blk_status_t error; /* * free the processed pages @@ -1510,7 +1510,7 @@ static void crypt_endio(struct bio *clone) if (rw == WRITE) crypt_free_buffer_pages(cc, clone); - error = clone->bi_error; + error = clone->bi_status; bio_put(clone); if (rw == READ && !error) { @@ -1570,7 +1570,7 @@ static void kcryptd_io_read_work(struct work_struct *work) crypt_inc_pending(io); if (kcryptd_io_read(io, GFP_NOIO)) - io->error = -ENOMEM; + io->error = BLK_STS_RESOURCE; crypt_dec_pending(io); } @@ -1656,7 +1656,7 @@ static void kcryptd_crypt_write_io_submit(struct dm_crypt_io *io, int async) sector_t sector; struct rb_node **rbp, *parent; - if (unlikely(io->error < 0)) { + if (unlikely(io->error)) { crypt_free_buffer_pages(cc, clone); bio_put(clone); crypt_dec_pending(io); @@ -1697,7 +1697,7 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io) struct bio *clone; int crypt_finished; sector_t sector = io->sector; - int r; + blk_status_t r; /* * Prevent io from disappearing until this function completes. @@ -1707,7 +1707,7 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io) clone = crypt_alloc_buffer(io, io->base_bio->bi_iter.bi_size); if (unlikely(!clone)) { - io->error = -EIO; + io->error = BLK_STS_IOERR; goto dec; } @@ -1718,7 +1718,7 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io) crypt_inc_pending(io); r = crypt_convert(cc, &io->ctx); - if (r < 0) + if (r) io->error = r; crypt_finished = atomic_dec_and_test(&io->ctx.cc_pending); @@ -1740,7 +1740,7 @@ static void kcryptd_crypt_read_done(struct dm_crypt_io *io) static void kcryptd_crypt_read_convert(struct dm_crypt_io *io) { struct crypt_config *cc = io->cc; - int r = 0; + blk_status_t r; crypt_inc_pending(io); @@ -1748,7 +1748,7 @@ static void kcryptd_crypt_read_convert(struct dm_crypt_io *io) io->sector); r = crypt_convert(cc, &io->ctx); - if (r < 0) + if (r) io->error = r; if (atomic_dec_and_test(&io->ctx.cc_pending)) @@ -1781,9 +1781,9 @@ static void kcryptd_async_done(struct crypto_async_request *async_req, if (error == -EBADMSG) { DMERR_LIMIT("INTEGRITY AEAD ERROR, sector %llu", (unsigned long long)le64_to_cpu(*org_sector_of_dmreq(cc, dmreq))); - io->error = -EILSEQ; + io->error = BLK_STS_PROTECTION; } else if (error < 0) - io->error = -EIO; + io->error = BLK_STS_IOERR; crypt_free_req(cc, req_of_dmreq(cc, dmreq), io->base_bio); @@ -2677,7 +2677,8 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto bad; } - cc->bs = bioset_create(MIN_IOS, 0); + cc->bs = bioset_create(MIN_IOS, 0, (BIOSET_NEED_BVECS | + BIOSET_NEED_RESCUER)); if (!cc->bs) { ti->error = "Cannot allocate crypt bioset"; goto bad; @@ -2795,10 +2796,10 @@ static int crypt_map(struct dm_target *ti, struct bio *bio) * and is aligned to this size as defined in IO hints. */ if (unlikely((bio->bi_iter.bi_sector & ((cc->sector_size >> SECTOR_SHIFT) - 1)) != 0)) - return -EIO; + return DM_MAPIO_KILL; if (unlikely(bio->bi_iter.bi_size & (cc->sector_size - 1))) - return -EIO; + return DM_MAPIO_KILL; io = dm_per_bio_data(bio, cc->per_bio_data_size); crypt_io_init(io, cc, bio, dm_target_offset(ti, bio->bi_iter.bi_sector)); diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c index 13305a182611..3d04d5ce19d9 100644 --- a/drivers/md/dm-flakey.c +++ b/drivers/md/dm-flakey.c @@ -321,7 +321,7 @@ static int flakey_map(struct dm_target *ti, struct bio *bio) if (bio_data_dir(bio) == READ) { if (!fc->corrupt_bio_byte && !test_bit(DROP_WRITES, &fc->flags) && !test_bit(ERROR_WRITES, &fc->flags)) - return -EIO; + return DM_MAPIO_KILL; goto map_bio; } @@ -349,7 +349,7 @@ static int flakey_map(struct dm_target *ti, struct bio *bio) /* * By default, error all I/O. */ - return -EIO; + return DM_MAPIO_KILL; } map_bio: @@ -358,12 +358,13 @@ map_bio: return DM_MAPIO_REMAPPED; } -static int flakey_end_io(struct dm_target *ti, struct bio *bio, int error) +static int flakey_end_io(struct dm_target *ti, struct bio *bio, + blk_status_t *error) { struct flakey_c *fc = ti->private; struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data)); - if (!error && pb->bio_submitted && (bio_data_dir(bio) == READ)) { + if (!*error && pb->bio_submitted && (bio_data_dir(bio) == READ)) { if (fc->corrupt_bio_byte && (fc->corrupt_bio_rw == READ) && all_corrupt_bio_flags_match(bio, fc)) { /* @@ -377,11 +378,11 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio, int error) * Error read during the down_interval if drop_writes * and error_writes were not configured. */ - return -EIO; + *error = BLK_STS_IOERR; } } - return error; + return DM_ENDIO_DONE; } static void flakey_status(struct dm_target *ti, status_type_t type, diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 7910bfe50da4..1b224aa9cf15 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -246,7 +246,7 @@ struct dm_integrity_io { unsigned metadata_offset; atomic_t in_flight; - int bi_error; + blk_status_t bi_status; struct completion *completion; @@ -1105,18 +1105,21 @@ static void schedule_autocommit(struct dm_integrity_c *ic) static void submit_flush_bio(struct dm_integrity_c *ic, struct dm_integrity_io *dio) { struct bio *bio; - spin_lock_irq(&ic->endio_wait.lock); + unsigned long flags; + + spin_lock_irqsave(&ic->endio_wait.lock, flags); bio = dm_bio_from_per_bio_data(dio, sizeof(struct dm_integrity_io)); bio_list_add(&ic->flush_bio_list, bio); - spin_unlock_irq(&ic->endio_wait.lock); + spin_unlock_irqrestore(&ic->endio_wait.lock, flags); + queue_work(ic->commit_wq, &ic->commit_work); } static void do_endio(struct dm_integrity_c *ic, struct bio *bio) { int r = dm_integrity_failed(ic); - if (unlikely(r) && !bio->bi_error) - bio->bi_error = r; + if (unlikely(r) && !bio->bi_status) + bio->bi_status = errno_to_blk_status(r); bio_endio(bio); } @@ -1124,7 +1127,7 @@ static void do_endio_flush(struct dm_integrity_c *ic, struct dm_integrity_io *di { struct bio *bio = dm_bio_from_per_bio_data(dio, sizeof(struct dm_integrity_io)); - if (unlikely(dio->fua) && likely(!bio->bi_error) && likely(!dm_integrity_failed(ic))) + if (unlikely(dio->fua) && likely(!bio->bi_status) && likely(!dm_integrity_failed(ic))) submit_flush_bio(ic, dio); else do_endio(ic, bio); @@ -1143,9 +1146,9 @@ static void dec_in_flight(struct dm_integrity_io *dio) bio = dm_bio_from_per_bio_data(dio, sizeof(struct dm_integrity_io)); - if (unlikely(dio->bi_error) && !bio->bi_error) - bio->bi_error = dio->bi_error; - if (likely(!bio->bi_error) && unlikely(bio_sectors(bio) != dio->range.n_sectors)) { + if (unlikely(dio->bi_status) && !bio->bi_status) + bio->bi_status = dio->bi_status; + if (likely(!bio->bi_status) && unlikely(bio_sectors(bio) != dio->range.n_sectors)) { dio->range.logical_sector += dio->range.n_sectors; bio_advance(bio, dio->range.n_sectors << SECTOR_SHIFT); INIT_WORK(&dio->work, integrity_bio_wait); @@ -1319,7 +1322,7 @@ skip_io: dec_in_flight(dio); return; error: - dio->bi_error = r; + dio->bi_status = errno_to_blk_status(r); dec_in_flight(dio); } @@ -1332,7 +1335,7 @@ static int dm_integrity_map(struct dm_target *ti, struct bio *bio) sector_t area, offset; dio->ic = ic; - dio->bi_error = 0; + dio->bi_status = 0; if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { submit_flush_bio(ic, dio); @@ -1353,13 +1356,13 @@ static int dm_integrity_map(struct dm_target *ti, struct bio *bio) DMERR("Too big sector number: 0x%llx + 0x%x > 0x%llx", (unsigned long long)dio->range.logical_sector, bio_sectors(bio), (unsigned long long)ic->provided_data_sectors); - return -EIO; + return DM_MAPIO_KILL; } if (unlikely((dio->range.logical_sector | bio_sectors(bio)) & (unsigned)(ic->sectors_per_block - 1))) { DMERR("Bio not aligned on %u sectors: 0x%llx, 0x%x", ic->sectors_per_block, (unsigned long long)dio->range.logical_sector, bio_sectors(bio)); - return -EIO; + return DM_MAPIO_KILL; } if (ic->sectors_per_block > 1) { @@ -1369,7 +1372,7 @@ static int dm_integrity_map(struct dm_target *ti, struct bio *bio) if (unlikely((bv.bv_offset | bv.bv_len) & ((ic->sectors_per_block << SECTOR_SHIFT) - 1))) { DMERR("Bio vector (%u,%u) is not aligned on %u-sector boundary", bv.bv_offset, bv.bv_len, ic->sectors_per_block); - return -EIO; + return DM_MAPIO_KILL; } } } @@ -1384,18 +1387,18 @@ static int dm_integrity_map(struct dm_target *ti, struct bio *bio) wanted_tag_size *= ic->tag_size; if (unlikely(wanted_tag_size != bip->bip_iter.bi_size)) { DMERR("Invalid integrity data size %u, expected %u", bip->bip_iter.bi_size, wanted_tag_size); - return -EIO; + return DM_MAPIO_KILL; } } } else { if (unlikely(bip != NULL)) { DMERR("Unexpected integrity data when using internal hash"); - return -EIO; + return DM_MAPIO_KILL; } } if (unlikely(ic->mode == 'R') && unlikely(dio->write)) - return -EIO; + return DM_MAPIO_KILL; get_area_and_offset(ic, dio->range.logical_sector, &area, &offset); dio->metadata_block = get_metadata_sector_and_offset(ic, area, offset, &dio->metadata_offset); @@ -3040,6 +3043,11 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv) ti->error = "The device is too small"; goto bad; } + if (ti->len > ic->provided_data_sectors) { + r = -EINVAL; + ti->error = "Not enough provided sectors for requested mapping size"; + goto bad; + } if (!buffer_sectors) buffer_sectors = 1; diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c index 3702e502466d..25039607f3cb 100644 --- a/drivers/md/dm-io.c +++ b/drivers/md/dm-io.c @@ -58,7 +58,8 @@ struct dm_io_client *dm_io_client_create(void) if (!client->pool) goto bad; - client->bios = bioset_create(min_ios, 0); + client->bios = bioset_create(min_ios, 0, (BIOSET_NEED_BVECS | + BIOSET_NEED_RESCUER)); if (!client->bios) goto bad; @@ -124,7 +125,7 @@ static void complete_io(struct io *io) fn(error_bits, context); } -static void dec_count(struct io *io, unsigned int region, int error) +static void dec_count(struct io *io, unsigned int region, blk_status_t error) { if (error) set_bit(region, &io->error_bits); @@ -137,9 +138,9 @@ static void endio(struct bio *bio) { struct io *io; unsigned region; - int error; + blk_status_t error; - if (bio->bi_error && bio_data_dir(bio) == READ) + if (bio->bi_status && bio_data_dir(bio) == READ) zero_fill_bio(bio); /* @@ -147,7 +148,7 @@ static void endio(struct bio *bio) */ retrieve_io_and_region_from_bio(bio, &io, ®ion); - error = bio->bi_error; + error = bio->bi_status; bio_put(bio); dec_count(io, region, error); @@ -317,9 +318,9 @@ static void do_region(int op, int op_flags, unsigned region, else if (op == REQ_OP_WRITE_SAME) special_cmd_max_sectors = q->limits.max_write_same_sectors; if ((op == REQ_OP_DISCARD || op == REQ_OP_WRITE_ZEROES || - op == REQ_OP_WRITE_SAME) && - special_cmd_max_sectors == 0) { - dec_count(io, region, -EOPNOTSUPP); + op == REQ_OP_WRITE_SAME) && special_cmd_max_sectors == 0) { + atomic_inc(&io->count); + dec_count(io, region, BLK_STS_NOTSUPP); return; } diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index 4dfe38655a49..a1da0eb58a93 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -150,10 +150,10 @@ static void log_end_io(struct bio *bio) { struct log_writes_c *lc = bio->bi_private; - if (bio->bi_error) { + if (bio->bi_status) { unsigned long flags; - DMERR("Error writing log block, error=%d", bio->bi_error); + DMERR("Error writing log block, error=%d", bio->bi_status); spin_lock_irqsave(&lc->blocks_lock, flags); lc->logging_enabled = false; spin_unlock_irqrestore(&lc->blocks_lock, flags); @@ -586,7 +586,7 @@ static int log_writes_map(struct dm_target *ti, struct bio *bio) spin_lock_irq(&lc->blocks_lock); lc->logging_enabled = false; spin_unlock_irq(&lc->blocks_lock); - return -ENOMEM; + return DM_MAPIO_KILL; } INIT_LIST_HEAD(&block->list); pb->block = block; @@ -639,7 +639,7 @@ static int log_writes_map(struct dm_target *ti, struct bio *bio) spin_lock_irq(&lc->blocks_lock); lc->logging_enabled = false; spin_unlock_irq(&lc->blocks_lock); - return -ENOMEM; + return DM_MAPIO_KILL; } src = kmap_atomic(bv.bv_page); @@ -664,7 +664,8 @@ map_bio: return DM_MAPIO_REMAPPED; } -static int normal_end_io(struct dm_target *ti, struct bio *bio, int error) +static int normal_end_io(struct dm_target *ti, struct bio *bio, + blk_status_t *error) { struct log_writes_c *lc = ti->private; struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data)); @@ -686,7 +687,7 @@ static int normal_end_io(struct dm_target *ti, struct bio *bio, int error) spin_unlock_irqrestore(&lc->blocks_lock, flags); } - return error; + return DM_ENDIO_DONE; } /* diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 3df056b73b66..0e8ab5bb3575 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -559,13 +559,13 @@ static int __multipath_map_bio(struct multipath *m, struct bio *bio, struct dm_m if (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) return DM_MAPIO_REQUEUE; dm_report_EIO(m); - return -EIO; + return DM_MAPIO_KILL; } mpio->pgpath = pgpath; mpio->nr_bytes = nr_bytes; - bio->bi_error = 0; + bio->bi_status = 0; bio->bi_bdev = pgpath->path.dev->bdev; bio->bi_opf |= REQ_FAILFAST_TRANSPORT; @@ -621,11 +621,19 @@ static void process_queued_bios(struct work_struct *work) blk_start_plug(&plug); while ((bio = bio_list_pop(&bios))) { r = __multipath_map_bio(m, bio, get_mpio_from_bio(bio)); - if (r < 0 || r == DM_MAPIO_REQUEUE) { - bio->bi_error = r; + switch (r) { + case DM_MAPIO_KILL: + bio->bi_status = BLK_STS_IOERR; + bio_endio(bio); + break; + case DM_MAPIO_REQUEUE: + bio->bi_status = BLK_STS_DM_REQUEUE; bio_endio(bio); - } else if (r == DM_MAPIO_REMAPPED) + break; + case DM_MAPIO_REMAPPED: generic_make_request(bio); + break; + } } blk_finish_plug(&plug); } @@ -1442,22 +1450,15 @@ static void activate_path_work(struct work_struct *work) activate_or_offline_path(pgpath); } -static int noretry_error(int error) +static int noretry_error(blk_status_t error) { switch (error) { - case -EBADE: - /* - * EBADE signals an reservation conflict. - * We shouldn't fail the path here as we can communicate with - * the target. We should failover to the next path, but in - * doing so we might be causing a ping-pong between paths. - * So just return the reservation conflict error. - */ - case -EOPNOTSUPP: - case -EREMOTEIO: - case -EILSEQ: - case -ENODATA: - case -ENOSPC: + case BLK_STS_NOTSUPP: + case BLK_STS_NOSPC: + case BLK_STS_TARGET: + case BLK_STS_NEXUS: + case BLK_STS_MEDIUM: + case BLK_STS_RESOURCE: return 1; } @@ -1466,7 +1467,7 @@ static int noretry_error(int error) } static int multipath_end_io(struct dm_target *ti, struct request *clone, - int error, union map_info *map_context) + blk_status_t error, union map_info *map_context) { struct dm_mpath_io *mpio = get_mpio(map_context); struct pgpath *pgpath = mpio->pgpath; @@ -1493,7 +1494,7 @@ static int multipath_end_io(struct dm_target *ti, struct request *clone, if (atomic_read(&m->nr_valid_paths) == 0 && !test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) { - if (error == -EIO) + if (error == BLK_STS_IOERR) dm_report_EIO(m); /* complete with the original error */ r = DM_ENDIO_DONE; @@ -1510,24 +1511,26 @@ static int multipath_end_io(struct dm_target *ti, struct request *clone, return r; } -static int do_end_io_bio(struct multipath *m, struct bio *clone, - int error, struct dm_mpath_io *mpio) +static int multipath_end_io_bio(struct dm_target *ti, struct bio *clone, + blk_status_t *error) { + struct multipath *m = ti->private; + struct dm_mpath_io *mpio = get_mpio_from_bio(clone); + struct pgpath *pgpath = mpio->pgpath; unsigned long flags; + int r = DM_ENDIO_DONE; - if (!error) - return 0; /* I/O complete */ - - if (noretry_error(error)) - return error; + if (!*error || noretry_error(*error)) + goto done; - if (mpio->pgpath) - fail_path(mpio->pgpath); + if (pgpath) + fail_path(pgpath); if (atomic_read(&m->nr_valid_paths) == 0 && !test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) { dm_report_EIO(m); - return -EIO; + *error = BLK_STS_IOERR; + goto done; } /* Queue for the daemon to resubmit */ @@ -1539,23 +1542,11 @@ static int do_end_io_bio(struct multipath *m, struct bio *clone, if (!test_bit(MPATHF_QUEUE_IO, &m->flags)) queue_work(kmultipathd, &m->process_queued_bios); - return DM_ENDIO_INCOMPLETE; -} - -static int multipath_end_io_bio(struct dm_target *ti, struct bio *clone, int error) -{ - struct multipath *m = ti->private; - struct dm_mpath_io *mpio = get_mpio_from_bio(clone); - struct pgpath *pgpath; - struct path_selector *ps; - int r; - - BUG_ON(!mpio); - - r = do_end_io_bio(m, clone, error, mpio); - pgpath = mpio->pgpath; + r = DM_ENDIO_INCOMPLETE; +done: if (pgpath) { - ps = &pgpath->pg->ps; + struct path_selector *ps = &pgpath->pg->ps; + if (ps->type->end_io) ps->type->end_io(ps, &pgpath->path, mpio->nr_bytes); } diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 7d893228c40f..b4b75dad816a 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -1927,7 +1927,7 @@ struct dm_raid_superblock { /******************************************************************** * BELOW FOLLOW V1.9.0 EXTENSIONS TO THE PRISTINE SUPERBLOCK FORMAT!!! * - * FEATURE_FLAG_SUPPORTS_V190 in the features member indicates that those exist + * FEATURE_FLAG_SUPPORTS_V190 in the compat_features member indicates that those exist */ __le32 flags; /* Flags defining array states for reshaping */ @@ -2092,6 +2092,11 @@ static void super_sync(struct mddev *mddev, struct md_rdev *rdev) sb->layout = cpu_to_le32(mddev->layout); sb->stripe_sectors = cpu_to_le32(mddev->chunk_sectors); + /******************************************************************** + * BELOW FOLLOW V1.9.0 EXTENSIONS TO THE PRISTINE SUPERBLOCK FORMAT!!! + * + * FEATURE_FLAG_SUPPORTS_V190 in the compat_features member indicates that those exist + */ sb->new_level = cpu_to_le32(mddev->new_level); sb->new_layout = cpu_to_le32(mddev->new_layout); sb->new_stripe_sectors = cpu_to_le32(mddev->new_chunk_sectors); @@ -2438,8 +2443,14 @@ static int super_validate(struct raid_set *rs, struct md_rdev *rdev) mddev->bitmap_info.default_offset = mddev->bitmap_info.offset; if (!test_and_clear_bit(FirstUse, &rdev->flags)) { - /* Retrieve device size stored in superblock to be prepared for shrink */ - rdev->sectors = le64_to_cpu(sb->sectors); + /* + * Retrieve rdev size stored in superblock to be prepared for shrink. + * Check extended superblock members are present otherwise the size + * will not be set! + */ + if (le32_to_cpu(sb->compat_features) & FEATURE_FLAG_SUPPORTS_V190) + rdev->sectors = le64_to_cpu(sb->sectors); + rdev->recovery_offset = le64_to_cpu(sb->disk_recovery_offset); if (rdev->recovery_offset == MaxSector) set_bit(In_sync, &rdev->flags); diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index e61c45047c25..a4fbd911d566 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -145,6 +145,7 @@ static void dispatch_bios(void *context, struct bio_list *bio_list) struct dm_raid1_bio_record { struct mirror *m; + /* if details->bi_bdev == NULL, details were not saved */ struct dm_bio_details details; region_t write_region; }; @@ -490,9 +491,9 @@ static void hold_bio(struct mirror_set *ms, struct bio *bio) * If device is suspended, complete the bio. */ if (dm_noflush_suspending(ms->ti)) - bio->bi_error = DM_ENDIO_REQUEUE; + bio->bi_status = BLK_STS_DM_REQUEUE; else - bio->bi_error = -EIO; + bio->bi_status = BLK_STS_IOERR; bio_endio(bio); return; @@ -626,7 +627,7 @@ static void write_callback(unsigned long error, void *context) * degrade the array. */ if (bio_op(bio) == REQ_OP_DISCARD) { - bio->bi_error = -EOPNOTSUPP; + bio->bi_status = BLK_STS_NOTSUPP; bio_endio(bio); return; } @@ -1198,6 +1199,8 @@ static int mirror_map(struct dm_target *ti, struct bio *bio) struct dm_raid1_bio_record *bio_record = dm_per_bio_data(bio, sizeof(struct dm_raid1_bio_record)); + bio_record->details.bi_bdev = NULL; + if (rw == WRITE) { /* Save region for mirror_end_io() handler */ bio_record->write_region = dm_rh_bio_to_region(ms->rh, bio); @@ -1207,14 +1210,14 @@ static int mirror_map(struct dm_target *ti, struct bio *bio) r = log->type->in_sync(log, dm_rh_bio_to_region(ms->rh, bio), 0); if (r < 0 && r != -EWOULDBLOCK) - return r; + return DM_MAPIO_KILL; /* * If region is not in-sync queue the bio. */ if (!r || (r == -EWOULDBLOCK)) { if (bio->bi_opf & REQ_RAHEAD) - return -EWOULDBLOCK; + return DM_MAPIO_KILL; queue_bio(ms, bio, rw); return DM_MAPIO_SUBMITTED; @@ -1226,7 +1229,7 @@ static int mirror_map(struct dm_target *ti, struct bio *bio) */ m = choose_mirror(ms, bio->bi_iter.bi_sector); if (unlikely(!m)) - return -EIO; + return DM_MAPIO_KILL; dm_bio_record(&bio_record->details, bio); bio_record->m = m; @@ -1236,7 +1239,8 @@ static int mirror_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_REMAPPED; } -static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error) +static int mirror_end_io(struct dm_target *ti, struct bio *bio, + blk_status_t *error) { int rw = bio_data_dir(bio); struct mirror_set *ms = (struct mirror_set *) ti->private; @@ -1252,16 +1256,26 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error) if (!(bio->bi_opf & REQ_PREFLUSH) && bio_op(bio) != REQ_OP_DISCARD) dm_rh_dec(ms->rh, bio_record->write_region); - return error; + return DM_ENDIO_DONE; } - if (error == -EOPNOTSUPP) - return error; + if (*error == BLK_STS_NOTSUPP) + goto out; + + if (bio->bi_opf & REQ_RAHEAD) + goto out; - if ((error == -EWOULDBLOCK) && (bio->bi_opf & REQ_RAHEAD)) - return error; + if (unlikely(*error)) { + if (!bio_record->details.bi_bdev) { + /* + * There wasn't enough memory to record necessary + * information for a retry or there was no other + * mirror in-sync. + */ + DMERR_LIMIT("Mirror read failed."); + return DM_ENDIO_DONE; + } - if (unlikely(error)) { m = bio_record->m; DMERR("Mirror read failed from %s. Trying alternative device.", @@ -1277,7 +1291,8 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error) bd = &bio_record->details; dm_bio_restore(bd, bio); - bio->bi_error = 0; + bio_record->details.bi_bdev = NULL; + bio->bi_status = 0; queue_bio(ms, bio, rw); return DM_ENDIO_INCOMPLETE; @@ -1285,7 +1300,10 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error) DMERR("All replicated volumes dead, failing I/O"); } - return error; +out: + bio_record->details.bi_bdev = NULL; + + return DM_ENDIO_DONE; } static void mirror_presuspend(struct dm_target *ti) diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index b639fa7246ee..c6ebc5b1e00e 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -71,7 +71,7 @@ static void dm_old_start_queue(struct request_queue *q) static void dm_mq_start_queue(struct request_queue *q) { - blk_mq_start_stopped_hw_queues(q, true); + blk_mq_unquiesce_queue(q); blk_mq_kick_requeue_list(q); } @@ -119,7 +119,7 @@ static void end_clone_bio(struct bio *clone) struct dm_rq_target_io *tio = info->tio; struct bio *bio = info->orig; unsigned int nr_bytes = info->orig->bi_iter.bi_size; - int error = clone->bi_error; + blk_status_t error = clone->bi_status; bio_put(clone); @@ -158,7 +158,7 @@ static void end_clone_bio(struct bio *clone) * Do not use blk_end_request() here, because it may complete * the original request before the clone, and break the ordering. */ - blk_update_request(tio->orig, 0, nr_bytes); + blk_update_request(tio->orig, BLK_STS_OK, nr_bytes); } static struct dm_rq_target_io *tio_from_request(struct request *rq) @@ -216,7 +216,7 @@ static void rq_completed(struct mapped_device *md, int rw, bool run_queue) * Must be called without clone's queue lock held, * see end_clone_request() for more details. */ -static void dm_end_request(struct request *clone, int error) +static void dm_end_request(struct request *clone, blk_status_t error) { int rw = rq_data_dir(clone); struct dm_rq_target_io *tio = clone->end_io_data; @@ -285,7 +285,7 @@ static void dm_requeue_original_request(struct dm_rq_target_io *tio, bool delay_ rq_completed(md, rw, false); } -static void dm_done(struct request *clone, int error, bool mapped) +static void dm_done(struct request *clone, blk_status_t error, bool mapped) { int r = DM_ENDIO_DONE; struct dm_rq_target_io *tio = clone->end_io_data; @@ -298,7 +298,7 @@ static void dm_done(struct request *clone, int error, bool mapped) r = rq_end_io(tio->ti, clone, error, &tio->info); } - if (unlikely(error == -EREMOTEIO)) { + if (unlikely(error == BLK_STS_TARGET)) { if (req_op(clone) == REQ_OP_WRITE_SAME && !clone->q->limits.max_write_same_sectors) disable_write_same(tio->md); @@ -358,7 +358,7 @@ static void dm_softirq_done(struct request *rq) * Complete the clone and the original request with the error status * through softirq context. */ -static void dm_complete_request(struct request *rq, int error) +static void dm_complete_request(struct request *rq, blk_status_t error) { struct dm_rq_target_io *tio = tio_from_request(rq); @@ -375,7 +375,7 @@ static void dm_complete_request(struct request *rq, int error) * Target's rq_end_io() function isn't called. * This may be used when the target's map_rq() or clone_and_map_rq() functions fail. */ -static void dm_kill_unmapped_request(struct request *rq, int error) +static void dm_kill_unmapped_request(struct request *rq, blk_status_t error) { rq->rq_flags |= RQF_FAILED; dm_complete_request(rq, error); @@ -384,7 +384,7 @@ static void dm_kill_unmapped_request(struct request *rq, int error) /* * Called with the clone's queue lock held (in the case of .request_fn) */ -static void end_clone_request(struct request *clone, int error) +static void end_clone_request(struct request *clone, blk_status_t error) { struct dm_rq_target_io *tio = clone->end_io_data; @@ -401,7 +401,7 @@ static void end_clone_request(struct request *clone, int error) static void dm_dispatch_clone_request(struct request *clone, struct request *rq) { - int r; + blk_status_t r; if (blk_queue_io_stat(clone->q)) clone->rq_flags |= RQF_IO_STAT; @@ -506,7 +506,7 @@ static int map_request(struct dm_rq_target_io *tio) break; case DM_MAPIO_KILL: /* The target wants to complete the I/O */ - dm_kill_unmapped_request(rq, -EIO); + dm_kill_unmapped_request(rq, BLK_STS_IOERR); break; default: DMWARN("unimplemented target map return value: %d", r); @@ -727,7 +727,7 @@ static int dm_mq_init_request(struct blk_mq_tag_set *set, struct request *rq, return __dm_rq_init_rq(set->driver_data, rq); } -static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx, +static blk_status_t dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { struct request *rq = bd->rq; @@ -744,7 +744,7 @@ static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx, } if (ti->type->busy && ti->type->busy(ti)) - return BLK_MQ_RQ_QUEUE_BUSY; + return BLK_STS_RESOURCE; dm_start_request(md, rq); @@ -762,10 +762,10 @@ static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx, rq_end_stats(md, rq); rq_completed(md, rq_data_dir(rq), false); blk_mq_delay_run_hw_queue(hctx, 100/*ms*/); - return BLK_MQ_RQ_QUEUE_BUSY; + return BLK_STS_RESOURCE; } - return BLK_MQ_RQ_QUEUE_OK; + return BLK_STS_OK; } static const struct blk_mq_ops dm_mq_ops = { diff --git a/drivers/md/dm-rq.h b/drivers/md/dm-rq.h index f0020d21b95f..9813922e4fe5 100644 --- a/drivers/md/dm-rq.h +++ b/drivers/md/dm-rq.h @@ -24,7 +24,7 @@ struct dm_rq_target_io { struct dm_target *ti; struct request *orig, *clone; struct kthread_work work; - int error; + blk_status_t error; union map_info info; struct dm_stats_aux stats_aux; unsigned long duration_jiffies; diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index e152d9817c81..1ba41048b438 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -1590,7 +1590,7 @@ static void full_bio_end_io(struct bio *bio) { void *callback_data = bio->bi_private; - dm_kcopyd_do_callback(callback_data, 0, bio->bi_error ? 1 : 0); + dm_kcopyd_do_callback(callback_data, 0, bio->bi_status ? 1 : 0); } static void start_full_bio(struct dm_snap_pending_exception *pe, @@ -1690,7 +1690,7 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio) /* Full snapshots are not usable */ /* To get here the table must be live so s->active is always set. */ if (!s->valid) - return -EIO; + return DM_MAPIO_KILL; /* FIXME: should only take write lock if we need * to copy an exception */ @@ -1698,7 +1698,7 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio) if (!s->valid || (unlikely(s->snapshot_overflowed) && bio_data_dir(bio) == WRITE)) { - r = -EIO; + r = DM_MAPIO_KILL; goto out_unlock; } @@ -1723,7 +1723,7 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio) if (!s->valid || s->snapshot_overflowed) { free_pending_exception(pe); - r = -EIO; + r = DM_MAPIO_KILL; goto out_unlock; } @@ -1741,7 +1741,7 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio) DMERR("Snapshot overflowed: Unable to allocate exception."); } else __invalidate_snapshot(s, -ENOMEM); - r = -EIO; + r = DM_MAPIO_KILL; goto out_unlock; } } @@ -1851,14 +1851,15 @@ out_unlock: return r; } -static int snapshot_end_io(struct dm_target *ti, struct bio *bio, int error) +static int snapshot_end_io(struct dm_target *ti, struct bio *bio, + blk_status_t *error) { struct dm_snapshot *s = ti->private; if (is_bio_tracked(bio)) stop_tracking_chunk(s, bio); - return 0; + return DM_ENDIO_DONE; } static void snapshot_merge_presuspend(struct dm_target *ti) diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index 75152482f3ad..11621a0af887 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -375,20 +375,21 @@ static void stripe_status(struct dm_target *ti, status_type_t type, } } -static int stripe_end_io(struct dm_target *ti, struct bio *bio, int error) +static int stripe_end_io(struct dm_target *ti, struct bio *bio, + blk_status_t *error) { unsigned i; char major_minor[16]; struct stripe_c *sc = ti->private; - if (!error) - return 0; /* I/O complete */ + if (!*error) + return DM_ENDIO_DONE; /* I/O complete */ - if ((error == -EWOULDBLOCK) && (bio->bi_opf & REQ_RAHEAD)) - return error; + if (bio->bi_opf & REQ_RAHEAD) + return DM_ENDIO_DONE; - if (error == -EOPNOTSUPP) - return error; + if (*error == BLK_STS_NOTSUPP) + return DM_ENDIO_DONE; memset(major_minor, 0, sizeof(major_minor)); sprintf(major_minor, "%d:%d", @@ -409,7 +410,7 @@ static int stripe_end_io(struct dm_target *ti, struct bio *bio, int error) schedule_work(&sc->trigger_event); } - return error; + return DM_ENDIO_DONE; } static int stripe_iterate_devices(struct dm_target *ti, diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c index b242b750542f..c0d7e60820c4 100644 --- a/drivers/md/dm-target.c +++ b/drivers/md/dm-target.c @@ -128,7 +128,7 @@ static void io_err_dtr(struct dm_target *tt) static int io_err_map(struct dm_target *tt, struct bio *bio) { - return -EIO; + return DM_MAPIO_KILL; } static int io_err_clone_and_map_rq(struct dm_target *ti, struct request *rq, diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 17ad50daed08..9dec2f8cc739 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -383,8 +383,8 @@ static void end_discard(struct discard_op *op, int r) * Even if r is set, there could be sub discards in flight that we * need to wait for. */ - if (r && !op->parent_bio->bi_error) - op->parent_bio->bi_error = r; + if (r && !op->parent_bio->bi_status) + op->parent_bio->bi_status = errno_to_blk_status(r); bio_endio(op->parent_bio); } @@ -450,22 +450,20 @@ static void cell_release_no_holder(struct pool *pool, } static void cell_error_with_code(struct pool *pool, - struct dm_bio_prison_cell *cell, int error_code) + struct dm_bio_prison_cell *cell, blk_status_t error_code) { dm_cell_error(pool->prison, cell, error_code); dm_bio_prison_free_cell(pool->prison, cell); } -static int get_pool_io_error_code(struct pool *pool) +static blk_status_t get_pool_io_error_code(struct pool *pool) { - return pool->out_of_data_space ? -ENOSPC : -EIO; + return pool->out_of_data_space ? BLK_STS_NOSPC : BLK_STS_IOERR; } static void cell_error(struct pool *pool, struct dm_bio_prison_cell *cell) { - int error = get_pool_io_error_code(pool); - - cell_error_with_code(pool, cell, error); + cell_error_with_code(pool, cell, get_pool_io_error_code(pool)); } static void cell_success(struct pool *pool, struct dm_bio_prison_cell *cell) @@ -475,7 +473,7 @@ static void cell_success(struct pool *pool, struct dm_bio_prison_cell *cell) static void cell_requeue(struct pool *pool, struct dm_bio_prison_cell *cell) { - cell_error_with_code(pool, cell, DM_ENDIO_REQUEUE); + cell_error_with_code(pool, cell, BLK_STS_DM_REQUEUE); } /*----------------------------------------------------------------*/ @@ -555,17 +553,18 @@ static void __merge_bio_list(struct bio_list *bios, struct bio_list *master) bio_list_init(master); } -static void error_bio_list(struct bio_list *bios, int error) +static void error_bio_list(struct bio_list *bios, blk_status_t error) { struct bio *bio; while ((bio = bio_list_pop(bios))) { - bio->bi_error = error; + bio->bi_status = error; bio_endio(bio); } } -static void error_thin_bio_list(struct thin_c *tc, struct bio_list *master, int error) +static void error_thin_bio_list(struct thin_c *tc, struct bio_list *master, + blk_status_t error) { struct bio_list bios; unsigned long flags; @@ -608,11 +607,11 @@ static void requeue_io(struct thin_c *tc) __merge_bio_list(&bios, &tc->retry_on_resume_list); spin_unlock_irqrestore(&tc->lock, flags); - error_bio_list(&bios, DM_ENDIO_REQUEUE); + error_bio_list(&bios, BLK_STS_DM_REQUEUE); requeue_deferred_cells(tc); } -static void error_retry_list_with_code(struct pool *pool, int error) +static void error_retry_list_with_code(struct pool *pool, blk_status_t error) { struct thin_c *tc; @@ -624,9 +623,7 @@ static void error_retry_list_with_code(struct pool *pool, int error) static void error_retry_list(struct pool *pool) { - int error = get_pool_io_error_code(pool); - - error_retry_list_with_code(pool, error); + error_retry_list_with_code(pool, get_pool_io_error_code(pool)); } /* @@ -774,7 +771,7 @@ struct dm_thin_new_mapping { */ atomic_t prepare_actions; - int err; + blk_status_t status; struct thin_c *tc; dm_block_t virt_begin, virt_end; dm_block_t data_block; @@ -814,7 +811,7 @@ static void copy_complete(int read_err, unsigned long write_err, void *context) { struct dm_thin_new_mapping *m = context; - m->err = read_err || write_err ? -EIO : 0; + m->status = read_err || write_err ? BLK_STS_IOERR : 0; complete_mapping_preparation(m); } @@ -825,7 +822,7 @@ static void overwrite_endio(struct bio *bio) bio->bi_end_io = m->saved_bi_end_io; - m->err = bio->bi_error; + m->status = bio->bi_status; complete_mapping_preparation(m); } @@ -925,7 +922,7 @@ static void process_prepared_mapping(struct dm_thin_new_mapping *m) struct bio *bio = m->bio; int r; - if (m->err) { + if (m->status) { cell_error(pool, m->cell); goto out; } @@ -1094,6 +1091,19 @@ static void process_prepared_discard_passdown_pt1(struct dm_thin_new_mapping *m) return; } + /* + * Increment the unmapped blocks. This prevents a race between the + * passdown io and reallocation of freed blocks. + */ + r = dm_pool_inc_data_range(pool->pmd, m->data_block, data_end); + if (r) { + metadata_operation_failed(pool, "dm_pool_inc_data_range", r); + bio_io_error(m->bio); + cell_defer_no_holder(tc, m->cell); + mempool_free(m, pool->mapping_pool); + return; + } + discard_parent = bio_alloc(GFP_NOIO, 1); if (!discard_parent) { DMWARN("%s: unable to allocate top level discard bio for passdown. Skipping passdown.", @@ -1114,19 +1124,6 @@ static void process_prepared_discard_passdown_pt1(struct dm_thin_new_mapping *m) end_discard(&op, r); } } - - /* - * Increment the unmapped blocks. This prevents a race between the - * passdown io and reallocation of freed blocks. - */ - r = dm_pool_inc_data_range(pool->pmd, m->data_block, data_end); - if (r) { - metadata_operation_failed(pool, "dm_pool_inc_data_range", r); - bio_io_error(m->bio); - cell_defer_no_holder(tc, m->cell); - mempool_free(m, pool->mapping_pool); - return; - } } static void process_prepared_discard_passdown_pt2(struct dm_thin_new_mapping *m) @@ -1495,7 +1492,7 @@ static void retry_on_resume(struct bio *bio) spin_unlock_irqrestore(&tc->lock, flags); } -static int should_error_unserviceable_bio(struct pool *pool) +static blk_status_t should_error_unserviceable_bio(struct pool *pool) { enum pool_mode m = get_pool_mode(pool); @@ -1503,27 +1500,27 @@ static int should_error_unserviceable_bio(struct pool *pool) case PM_WRITE: /* Shouldn't get here */ DMERR_LIMIT("bio unserviceable, yet pool is in PM_WRITE mode"); - return -EIO; + return BLK_STS_IOERR; case PM_OUT_OF_DATA_SPACE: - return pool->pf.error_if_no_space ? -ENOSPC : 0; + return pool->pf.error_if_no_space ? BLK_STS_NOSPC : 0; case PM_READ_ONLY: case PM_FAIL: - return -EIO; + return BLK_STS_IOERR; default: /* Shouldn't get here */ DMERR_LIMIT("bio unserviceable, yet pool has an unknown mode"); - return -EIO; + return BLK_STS_IOERR; } } static void handle_unserviceable_bio(struct pool *pool, struct bio *bio) { - int error = should_error_unserviceable_bio(pool); + blk_status_t error = should_error_unserviceable_bio(pool); if (error) { - bio->bi_error = error; + bio->bi_status = error; bio_endio(bio); } else retry_on_resume(bio); @@ -1533,7 +1530,7 @@ static void retry_bios_on_resume(struct pool *pool, struct dm_bio_prison_cell *c { struct bio *bio; struct bio_list bios; - int error; + blk_status_t error; error = should_error_unserviceable_bio(pool); if (error) { @@ -2071,7 +2068,8 @@ static void process_thin_deferred_bios(struct thin_c *tc) unsigned count = 0; if (tc->requeue_mode) { - error_thin_bio_list(tc, &tc->deferred_bio_list, DM_ENDIO_REQUEUE); + error_thin_bio_list(tc, &tc->deferred_bio_list, + BLK_STS_DM_REQUEUE); return; } @@ -2322,7 +2320,7 @@ static void do_no_space_timeout(struct work_struct *ws) if (get_pool_mode(pool) == PM_OUT_OF_DATA_SPACE && !pool->pf.error_if_no_space) { pool->pf.error_if_no_space = true; notify_of_pool_mode_change_to_oods(pool); - error_retry_list_with_code(pool, -ENOSPC); + error_retry_list_with_code(pool, BLK_STS_NOSPC); } } @@ -2624,7 +2622,7 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio) thin_hook_bio(tc, bio); if (tc->requeue_mode) { - bio->bi_error = DM_ENDIO_REQUEUE; + bio->bi_status = BLK_STS_DM_REQUEUE; bio_endio(bio); return DM_MAPIO_SUBMITTED; } @@ -4177,7 +4175,8 @@ static int thin_map(struct dm_target *ti, struct bio *bio) return thin_bio_map(ti, bio); } -static int thin_endio(struct dm_target *ti, struct bio *bio, int err) +static int thin_endio(struct dm_target *ti, struct bio *bio, + blk_status_t *err) { unsigned long flags; struct dm_thin_endio_hook *h = dm_per_bio_data(bio, sizeof(struct dm_thin_endio_hook)); @@ -4212,7 +4211,7 @@ static int thin_endio(struct dm_target *ti, struct bio *bio, int err) if (h->cell) cell_defer_no_holder(h->tc, h->cell); - return 0; + return DM_ENDIO_DONE; } static void thin_presuspend(struct dm_target *ti) diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 1ec9b2c51c07..b46705ebf01f 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -538,13 +538,13 @@ static int verity_verify_io(struct dm_verity_io *io) /* * End one "io" structure with a given error. */ -static void verity_finish_io(struct dm_verity_io *io, int error) +static void verity_finish_io(struct dm_verity_io *io, blk_status_t status) { struct dm_verity *v = io->v; struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_io_data_size); bio->bi_end_io = io->orig_bi_end_io; - bio->bi_error = error; + bio->bi_status = status; verity_fec_finish_io(io); @@ -555,15 +555,15 @@ static void verity_work(struct work_struct *w) { struct dm_verity_io *io = container_of(w, struct dm_verity_io, work); - verity_finish_io(io, verity_verify_io(io)); + verity_finish_io(io, errno_to_blk_status(verity_verify_io(io))); } static void verity_end_io(struct bio *bio) { struct dm_verity_io *io = bio->bi_private; - if (bio->bi_error && !verity_fec_is_enabled(io->v)) { - verity_finish_io(io, bio->bi_error); + if (bio->bi_status && !verity_fec_is_enabled(io->v)) { + verity_finish_io(io, bio->bi_status); return; } @@ -643,17 +643,17 @@ static int verity_map(struct dm_target *ti, struct bio *bio) if (((unsigned)bio->bi_iter.bi_sector | bio_sectors(bio)) & ((1 << (v->data_dev_block_bits - SECTOR_SHIFT)) - 1)) { DMERR_LIMIT("unaligned io"); - return -EIO; + return DM_MAPIO_KILL; } if (bio_end_sector(bio) >> (v->data_dev_block_bits - SECTOR_SHIFT) > v->data_blocks) { DMERR_LIMIT("io out of range"); - return -EIO; + return DM_MAPIO_KILL; } if (bio_data_dir(bio) == WRITE) - return -EIO; + return DM_MAPIO_KILL; io = dm_per_bio_data(bio, ti->per_io_data_size); io->v = v; diff --git a/drivers/md/dm-zero.c b/drivers/md/dm-zero.c index b616f11d8473..b65ca8dcfbdc 100644 --- a/drivers/md/dm-zero.c +++ b/drivers/md/dm-zero.c @@ -39,7 +39,7 @@ static int zero_map(struct dm_target *ti, struct bio *bio) case REQ_OP_READ: if (bio->bi_opf & REQ_RAHEAD) { /* readahead of null bytes only wastes buffer cache */ - return -EIO; + return DM_MAPIO_KILL; } zero_fill_bio(bio); break; @@ -47,7 +47,7 @@ static int zero_map(struct dm_target *ti, struct bio *bio) /* writes get silently dropped */ break; default: - return -EIO; + return DM_MAPIO_KILL; } bio_endio(bio); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 37ccd73c79ec..402946035308 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -63,7 +63,7 @@ static struct workqueue_struct *deferred_remove_workqueue; */ struct dm_io { struct mapped_device *md; - int error; + blk_status_t status; atomic_t io_count; struct bio *bio; unsigned long start_time; @@ -768,23 +768,24 @@ static int __noflush_suspending(struct mapped_device *md) * Decrements the number of outstanding ios that a bio has been * cloned into, completing the original io if necc. */ -static void dec_pending(struct dm_io *io, int error) +static void dec_pending(struct dm_io *io, blk_status_t error) { unsigned long flags; - int io_error; + blk_status_t io_error; struct bio *bio; struct mapped_device *md = io->md; /* Push-back supersedes any I/O errors */ if (unlikely(error)) { spin_lock_irqsave(&io->endio_lock, flags); - if (!(io->error > 0 && __noflush_suspending(md))) - io->error = error; + if (!(io->status == BLK_STS_DM_REQUEUE && + __noflush_suspending(md))) + io->status = error; spin_unlock_irqrestore(&io->endio_lock, flags); } if (atomic_dec_and_test(&io->io_count)) { - if (io->error == DM_ENDIO_REQUEUE) { + if (io->status == BLK_STS_DM_REQUEUE) { /* * Target requested pushing back the I/O. */ @@ -793,16 +794,16 @@ static void dec_pending(struct dm_io *io, int error) bio_list_add_head(&md->deferred, io->bio); else /* noflush suspend was interrupted. */ - io->error = -EIO; + io->status = BLK_STS_IOERR; spin_unlock_irqrestore(&md->deferred_lock, flags); } - io_error = io->error; + io_error = io->status; bio = io->bio; end_io_acct(io); free_io(md, io); - if (io_error == DM_ENDIO_REQUEUE) + if (io_error == BLK_STS_DM_REQUEUE) return; if ((bio->bi_opf & REQ_PREFLUSH) && bio->bi_iter.bi_size) { @@ -814,7 +815,7 @@ static void dec_pending(struct dm_io *io, int error) queue_io(md, bio); } else { /* done with normal IO or empty flush */ - bio->bi_error = io_error; + bio->bi_status = io_error; bio_endio(bio); } } @@ -838,31 +839,13 @@ void disable_write_zeroes(struct mapped_device *md) static void clone_endio(struct bio *bio) { - int error = bio->bi_error; - int r = error; + blk_status_t error = bio->bi_status; struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone); struct dm_io *io = tio->io; struct mapped_device *md = tio->io->md; dm_endio_fn endio = tio->ti->type->end_io; - if (endio) { - r = endio(tio->ti, bio, error); - if (r < 0 || r == DM_ENDIO_REQUEUE) - /* - * error and requeue request are handled - * in dec_pending(). - */ - error = r; - else if (r == DM_ENDIO_INCOMPLETE) - /* The target will handle the io */ - return; - else if (r) { - DMWARN("unimplemented target endio return value: %d", r); - BUG(); - } - } - - if (unlikely(r == -EREMOTEIO)) { + if (unlikely(error == BLK_STS_TARGET)) { if (bio_op(bio) == REQ_OP_WRITE_SAME && !bdev_get_queue(bio->bi_bdev)->limits.max_write_same_sectors) disable_write_same(md); @@ -871,6 +854,23 @@ static void clone_endio(struct bio *bio) disable_write_zeroes(md); } + if (endio) { + int r = endio(tio->ti, bio, &error); + switch (r) { + case DM_ENDIO_REQUEUE: + error = BLK_STS_DM_REQUEUE; + /*FALLTHRU*/ + case DM_ENDIO_DONE: + break; + case DM_ENDIO_INCOMPLETE: + /* The target will handle the io */ + return; + default: + DMWARN("unimplemented target endio return value: %d", r); + BUG(); + } + } + free_tio(tio); dec_pending(io, error); } @@ -1036,7 +1036,8 @@ static void flush_current_bio_list(struct blk_plug_cb *cb, bool from_schedule) while ((bio = bio_list_pop(&list))) { struct bio_set *bs = bio->bi_pool; - if (unlikely(!bs) || bs == fs_bio_set) { + if (unlikely(!bs) || bs == fs_bio_set || + !bs->rescue_workqueue) { bio_list_add(¤t->bio_list[i], bio); continue; } @@ -1084,18 +1085,24 @@ static void __map_bio(struct dm_target_io *tio) r = ti->type->map(ti, clone); dm_offload_end(&o); - if (r == DM_MAPIO_REMAPPED) { + switch (r) { + case DM_MAPIO_SUBMITTED: + break; + case DM_MAPIO_REMAPPED: /* the bio has been remapped so dispatch it */ - trace_block_bio_remap(bdev_get_queue(clone->bi_bdev), clone, tio->io->bio->bi_bdev->bd_dev, sector); - generic_make_request(clone); - } else if (r < 0 || r == DM_MAPIO_REQUEUE) { - /* error the io and bail out, or requeue it if needed */ - dec_pending(tio->io, r); + break; + case DM_MAPIO_KILL: + dec_pending(tio->io, BLK_STS_IOERR); + free_tio(tio); + break; + case DM_MAPIO_REQUEUE: + dec_pending(tio->io, BLK_STS_DM_REQUEUE); free_tio(tio); - } else if (r != DM_MAPIO_SUBMITTED) { + break; + default: DMWARN("unimplemented target map return value: %d", r); BUG(); } @@ -1360,7 +1367,7 @@ static void __split_and_process_bio(struct mapped_device *md, ci.map = map; ci.md = md; ci.io = alloc_io(md); - ci.io->error = 0; + ci.io->status = 0; atomic_set(&ci.io->io_count, 1); ci.io->bio = bio; ci.io->md = md; @@ -1527,7 +1534,6 @@ void dm_init_normal_md_queue(struct mapped_device *md) * Initialize aspects of queue that aren't relevant for blk-mq */ md->queue->backing_dev_info->congested_fn = dm_any_congested; - blk_queue_bounce_limit(md->queue, BLK_BOUNCE_ANY); } static void cleanup_mapped_device(struct mapped_device *md) @@ -2654,7 +2660,7 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, enum dm_qu BUG(); } - pools->bs = bioset_create_nobvec(pool_size, front_pad); + pools->bs = bioset_create(pool_size, front_pad, BIOSET_NEED_RESCUER); if (!pools->bs) goto out; diff --git a/drivers/md/md.c b/drivers/md/md.c index 87edc342ccb3..31bcbfb09fef 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -185,7 +185,7 @@ static int start_readonly; static bool create_on_open = true; /* bio_clone_mddev - * like bio_clone, but with a local bio set + * like bio_clone_bioset, but with a local bio set */ struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs, @@ -265,7 +265,7 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio) unsigned int sectors; int cpu; - blk_queue_split(q, &bio, q->bio_split); + blk_queue_split(q, &bio); if (mddev == NULL || mddev->pers == NULL) { bio_io_error(bio); @@ -273,7 +273,7 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio) } if (mddev->ro == 1 && unlikely(rw == WRITE)) { if (bio_sectors(bio) != 0) - bio->bi_error = -EROFS; + bio->bi_status = BLK_STS_IOERR; bio_endio(bio); return BLK_QC_T_NONE; } @@ -719,8 +719,8 @@ static void super_written(struct bio *bio) struct md_rdev *rdev = bio->bi_private; struct mddev *mddev = rdev->mddev; - if (bio->bi_error) { - pr_err("md: super_written gets error=%d\n", bio->bi_error); + if (bio->bi_status) { + pr_err("md: super_written gets error=%d\n", bio->bi_status); md_error(mddev, rdev); if (!test_bit(Faulty, &rdev->flags) && (bio->bi_opf & MD_FAILFAST)) { @@ -801,7 +801,7 @@ int sync_page_io(struct md_rdev *rdev, sector_t sector, int size, submit_bio_wait(bio); - ret = !bio->bi_error; + ret = !bio->bi_status; bio_put(bio); return ret; } @@ -825,7 +825,7 @@ fail: return -EINVAL; } -static int uuid_equal(mdp_super_t *sb1, mdp_super_t *sb2) +static int md_uuid_equal(mdp_super_t *sb1, mdp_super_t *sb2) { return sb1->set_uuid0 == sb2->set_uuid0 && sb1->set_uuid1 == sb2->set_uuid1 && @@ -833,7 +833,7 @@ static int uuid_equal(mdp_super_t *sb1, mdp_super_t *sb2) sb1->set_uuid3 == sb2->set_uuid3; } -static int sb_equal(mdp_super_t *sb1, mdp_super_t *sb2) +static int md_sb_equal(mdp_super_t *sb1, mdp_super_t *sb2) { int ret; mdp_super_t *tmp1, *tmp2; @@ -1025,12 +1025,12 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor } else { __u64 ev1, ev2; mdp_super_t *refsb = page_address(refdev->sb_page); - if (!uuid_equal(refsb, sb)) { + if (!md_uuid_equal(refsb, sb)) { pr_warn("md: %s has different UUID to %s\n", b, bdevname(refdev->bdev,b2)); goto abort; } - if (!sb_equal(refsb, sb)) { + if (!md_sb_equal(refsb, sb)) { pr_warn("md: %s has same UUID but different superblock to %s\n", b, bdevname(refdev->bdev, b2)); goto abort; @@ -5428,7 +5428,7 @@ int md_run(struct mddev *mddev) } if (mddev->bio_set == NULL) { - mddev->bio_set = bioset_create(BIO_POOL_SIZE, 0); + mddev->bio_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); if (!mddev->bio_set) return -ENOMEM; } diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c index e95d521d93e9..68d036e64041 100644 --- a/drivers/md/multipath.c +++ b/drivers/md/multipath.c @@ -73,12 +73,12 @@ static void multipath_reschedule_retry (struct multipath_bh *mp_bh) * operation and are ready to return a success/failure code to the buffer * cache layer. */ -static void multipath_end_bh_io (struct multipath_bh *mp_bh, int err) +static void multipath_end_bh_io(struct multipath_bh *mp_bh, blk_status_t status) { struct bio *bio = mp_bh->master_bio; struct mpconf *conf = mp_bh->mddev->private; - bio->bi_error = err; + bio->bi_status = status; bio_endio(bio); mempool_free(mp_bh, conf->pool); } @@ -89,7 +89,7 @@ static void multipath_end_request(struct bio *bio) struct mpconf *conf = mp_bh->mddev->private; struct md_rdev *rdev = conf->multipaths[mp_bh->path].rdev; - if (!bio->bi_error) + if (!bio->bi_status) multipath_end_bh_io(mp_bh, 0); else if (!(bio->bi_opf & REQ_RAHEAD)) { /* @@ -102,7 +102,7 @@ static void multipath_end_request(struct bio *bio) (unsigned long long)bio->bi_iter.bi_sector); multipath_reschedule_retry(mp_bh); } else - multipath_end_bh_io(mp_bh, bio->bi_error); + multipath_end_bh_io(mp_bh, bio->bi_status); rdev_dec_pending(rdev, conf->mddev); } @@ -347,7 +347,7 @@ static void multipathd(struct md_thread *thread) pr_err("multipath: %s: unrecoverable IO read error for block %llu\n", bdevname(bio->bi_bdev,b), (unsigned long long)bio->bi_iter.bi_sector); - multipath_end_bh_io(mp_bh, -EIO); + multipath_end_bh_io(mp_bh, BLK_STS_IOERR); } else { pr_err("multipath: %s: redirecting sector %llu to another IO path\n", bdevname(bio->bi_bdev,b), diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index e1a7e3d4c5e4..98ca2c1d3226 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -277,7 +277,7 @@ static void call_bio_endio(struct r1bio *r1_bio) struct r1conf *conf = r1_bio->mddev->private; if (!test_bit(R1BIO_Uptodate, &r1_bio->state)) - bio->bi_error = -EIO; + bio->bi_status = BLK_STS_IOERR; bio_endio(bio); /* @@ -335,7 +335,7 @@ static int find_bio_disk(struct r1bio *r1_bio, struct bio *bio) static void raid1_end_read_request(struct bio *bio) { - int uptodate = !bio->bi_error; + int uptodate = !bio->bi_status; struct r1bio *r1_bio = bio->bi_private; struct r1conf *conf = r1_bio->mddev->private; struct md_rdev *rdev = conf->mirrors[r1_bio->read_disk].rdev; @@ -426,12 +426,12 @@ static void raid1_end_write_request(struct bio *bio) struct md_rdev *rdev = conf->mirrors[mirror].rdev; bool discard_error; - discard_error = bio->bi_error && bio_op(bio) == REQ_OP_DISCARD; + discard_error = bio->bi_status && bio_op(bio) == REQ_OP_DISCARD; /* * 'one mirror IO has finished' event handler: */ - if (bio->bi_error && !discard_error) { + if (bio->bi_status && !discard_error) { set_bit(WriteErrorSeen, &rdev->flags); if (!test_and_set_bit(WantReplacement, &rdev->flags)) set_bit(MD_RECOVERY_NEEDED, & @@ -802,7 +802,7 @@ static void flush_bio_list(struct r1conf *conf, struct bio *bio) bio->bi_next = NULL; bio->bi_bdev = rdev->bdev; if (test_bit(Faulty, &rdev->flags)) { - bio->bi_error = -EIO; + bio->bi_status = BLK_STS_IOERR; bio_endio(bio); } else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) && !blk_queue_discard(bdev_get_queue(bio->bi_bdev)))) @@ -1856,7 +1856,7 @@ static void end_sync_read(struct bio *bio) * or re-read if the read failed. * We don't do much here, just schedule handling by raid1d */ - if (!bio->bi_error) + if (!bio->bi_status) set_bit(R1BIO_Uptodate, &r1_bio->state); if (atomic_dec_and_test(&r1_bio->remaining)) @@ -1865,7 +1865,7 @@ static void end_sync_read(struct bio *bio) static void end_sync_write(struct bio *bio) { - int uptodate = !bio->bi_error; + int uptodate = !bio->bi_status; struct r1bio *r1_bio = get_resync_r1bio(bio); struct mddev *mddev = r1_bio->mddev; struct r1conf *conf = mddev->private; @@ -2058,7 +2058,7 @@ static int fix_sync_read_error(struct r1bio *r1_bio) idx ++; } set_bit(R1BIO_Uptodate, &r1_bio->state); - bio->bi_error = 0; + bio->bi_status = 0; return 1; } @@ -2082,16 +2082,16 @@ static void process_checks(struct r1bio *r1_bio) for (i = 0; i < conf->raid_disks * 2; i++) { int j; int size; - int error; + blk_status_t status; struct bio_vec *bi; struct bio *b = r1_bio->bios[i]; struct resync_pages *rp = get_resync_pages(b); if (b->bi_end_io != end_sync_read) continue; /* fixup the bio for reuse, but preserve errno */ - error = b->bi_error; + status = b->bi_status; bio_reset(b); - b->bi_error = error; + b->bi_status = status; b->bi_vcnt = vcnt; b->bi_iter.bi_size = r1_bio->sectors << 9; b->bi_iter.bi_sector = r1_bio->sector + @@ -2113,7 +2113,7 @@ static void process_checks(struct r1bio *r1_bio) } for (primary = 0; primary < conf->raid_disks * 2; primary++) if (r1_bio->bios[primary]->bi_end_io == end_sync_read && - !r1_bio->bios[primary]->bi_error) { + !r1_bio->bios[primary]->bi_status) { r1_bio->bios[primary]->bi_end_io = NULL; rdev_dec_pending(conf->mirrors[primary].rdev, mddev); break; @@ -2123,7 +2123,7 @@ static void process_checks(struct r1bio *r1_bio) int j; struct bio *pbio = r1_bio->bios[primary]; struct bio *sbio = r1_bio->bios[i]; - int error = sbio->bi_error; + blk_status_t status = sbio->bi_status; struct page **ppages = get_resync_pages(pbio)->pages; struct page **spages = get_resync_pages(sbio)->pages; struct bio_vec *bi; @@ -2132,12 +2132,12 @@ static void process_checks(struct r1bio *r1_bio) if (sbio->bi_end_io != end_sync_read) continue; /* Now we can 'fixup' the error value */ - sbio->bi_error = 0; + sbio->bi_status = 0; bio_for_each_segment_all(bi, sbio, j) page_len[j] = bi->bv_len; - if (!error) { + if (!status) { for (j = vcnt; j-- ; ) { if (memcmp(page_address(ppages[j]), page_address(spages[j]), @@ -2149,7 +2149,7 @@ static void process_checks(struct r1bio *r1_bio) if (j >= 0) atomic64_add(r1_bio->sectors, &mddev->resync_mismatches); if (j < 0 || (test_bit(MD_RECOVERY_CHECK, &mddev->recovery) - && !error)) { + && !status)) { /* No need to write to this device. */ sbio->bi_end_io = NULL; rdev_dec_pending(conf->mirrors[i].rdev, mddev); @@ -2400,11 +2400,11 @@ static void handle_sync_write_finished(struct r1conf *conf, struct r1bio *r1_bio struct bio *bio = r1_bio->bios[m]; if (bio->bi_end_io == NULL) continue; - if (!bio->bi_error && + if (!bio->bi_status && test_bit(R1BIO_MadeGood, &r1_bio->state)) { rdev_clear_badblocks(rdev, r1_bio->sector, s, 0); } - if (bio->bi_error && + if (bio->bi_status && test_bit(R1BIO_WriteError, &r1_bio->state)) { if (!rdev_set_badblocks(rdev, r1_bio->sector, s, 0)) md_error(conf->mddev, rdev); @@ -2955,7 +2955,7 @@ static struct r1conf *setup_conf(struct mddev *mddev) if (!conf->r1bio_pool) goto abort; - conf->bio_split = bioset_create(BIO_POOL_SIZE, 0); + conf->bio_split = bioset_create(BIO_POOL_SIZE, 0, 0); if (!conf->bio_split) goto abort; diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 797ed60abd5e..57a250fdbbcc 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -336,7 +336,7 @@ static void raid_end_bio_io(struct r10bio *r10_bio) struct r10conf *conf = r10_bio->mddev->private; if (!test_bit(R10BIO_Uptodate, &r10_bio->state)) - bio->bi_error = -EIO; + bio->bi_status = BLK_STS_IOERR; bio_endio(bio); /* @@ -389,7 +389,7 @@ static int find_bio_disk(struct r10conf *conf, struct r10bio *r10_bio, static void raid10_end_read_request(struct bio *bio) { - int uptodate = !bio->bi_error; + int uptodate = !bio->bi_status; struct r10bio *r10_bio = bio->bi_private; int slot, dev; struct md_rdev *rdev; @@ -477,7 +477,7 @@ static void raid10_end_write_request(struct bio *bio) struct bio *to_put = NULL; bool discard_error; - discard_error = bio->bi_error && bio_op(bio) == REQ_OP_DISCARD; + discard_error = bio->bi_status && bio_op(bio) == REQ_OP_DISCARD; dev = find_bio_disk(conf, r10_bio, bio, &slot, &repl); @@ -491,7 +491,7 @@ static void raid10_end_write_request(struct bio *bio) /* * this branch is our 'one mirror IO has finished' event handler: */ - if (bio->bi_error && !discard_error) { + if (bio->bi_status && !discard_error) { if (repl) /* Never record new bad blocks to replacement, * just fail it. @@ -913,7 +913,7 @@ static void flush_pending_writes(struct r10conf *conf) bio->bi_next = NULL; bio->bi_bdev = rdev->bdev; if (test_bit(Faulty, &rdev->flags)) { - bio->bi_error = -EIO; + bio->bi_status = BLK_STS_IOERR; bio_endio(bio); } else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) && !blk_queue_discard(bdev_get_queue(bio->bi_bdev)))) @@ -1098,7 +1098,7 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule) bio->bi_next = NULL; bio->bi_bdev = rdev->bdev; if (test_bit(Faulty, &rdev->flags)) { - bio->bi_error = -EIO; + bio->bi_status = BLK_STS_IOERR; bio_endio(bio); } else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) && !blk_queue_discard(bdev_get_queue(bio->bi_bdev)))) @@ -1888,7 +1888,7 @@ static void __end_sync_read(struct r10bio *r10_bio, struct bio *bio, int d) { struct r10conf *conf = r10_bio->mddev->private; - if (!bio->bi_error) + if (!bio->bi_status) set_bit(R10BIO_Uptodate, &r10_bio->state); else /* The write handler will notice the lack of @@ -1972,7 +1972,7 @@ static void end_sync_write(struct bio *bio) else rdev = conf->mirrors[d].rdev; - if (bio->bi_error) { + if (bio->bi_status) { if (repl) md_error(mddev, rdev); else { @@ -2021,7 +2021,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio) /* find the first device with a block */ for (i=0; i<conf->copies; i++) - if (!r10_bio->devs[i].bio->bi_error) + if (!r10_bio->devs[i].bio->bi_status) break; if (i == conf->copies) @@ -2050,7 +2050,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio) tpages = get_resync_pages(tbio)->pages; d = r10_bio->devs[i].devnum; rdev = conf->mirrors[d].rdev; - if (!r10_bio->devs[i].bio->bi_error) { + if (!r10_bio->devs[i].bio->bi_status) { /* We know that the bi_io_vec layout is the same for * both 'first' and 'i', so we just compare them. * All vec entries are PAGE_SIZE; @@ -2633,7 +2633,7 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio) rdev = conf->mirrors[dev].rdev; if (r10_bio->devs[m].bio == NULL) continue; - if (!r10_bio->devs[m].bio->bi_error) { + if (!r10_bio->devs[m].bio->bi_status) { rdev_clear_badblocks( rdev, r10_bio->devs[m].addr, @@ -2649,7 +2649,7 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio) if (r10_bio->devs[m].repl_bio == NULL) continue; - if (!r10_bio->devs[m].repl_bio->bi_error) { + if (!r10_bio->devs[m].repl_bio->bi_status) { rdev_clear_badblocks( rdev, r10_bio->devs[m].addr, @@ -2675,7 +2675,7 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio) r10_bio->devs[m].addr, r10_bio->sectors, 0); rdev_dec_pending(rdev, conf->mddev); - } else if (bio != NULL && bio->bi_error) { + } else if (bio != NULL && bio->bi_status) { fail = true; if (!narrow_write_error(r10_bio, m)) { md_error(conf->mddev, rdev); @@ -3267,7 +3267,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, r10_bio->devs[i].repl_bio->bi_end_io = NULL; bio = r10_bio->devs[i].bio; - bio->bi_error = -EIO; + bio->bi_status = BLK_STS_IOERR; rcu_read_lock(); rdev = rcu_dereference(conf->mirrors[d].rdev); if (rdev == NULL || test_bit(Faulty, &rdev->flags)) { @@ -3309,7 +3309,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, /* Need to set up for writing to the replacement */ bio = r10_bio->devs[i].repl_bio; - bio->bi_error = -EIO; + bio->bi_status = BLK_STS_IOERR; sector = r10_bio->devs[i].addr; bio->bi_next = biolist; @@ -3375,7 +3375,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, if (bio->bi_end_io == end_sync_read) { md_sync_acct(bio->bi_bdev, nr_sectors); - bio->bi_error = 0; + bio->bi_status = 0; generic_make_request(bio); } } @@ -3552,7 +3552,7 @@ static struct r10conf *setup_conf(struct mddev *mddev) if (!conf->r10bio_pool) goto out; - conf->bio_split = bioset_create(BIO_POOL_SIZE, 0); + conf->bio_split = bioset_create(BIO_POOL_SIZE, 0, 0); if (!conf->bio_split) goto out; @@ -4397,7 +4397,7 @@ read_more: read_bio->bi_end_io = end_reshape_read; bio_set_op_attrs(read_bio, REQ_OP_READ, 0); read_bio->bi_flags &= (~0UL << BIO_RESET_BITS); - read_bio->bi_error = 0; + read_bio->bi_status = 0; read_bio->bi_vcnt = 0; read_bio->bi_iter.bi_size = 0; r10_bio->master_bio = read_bio; @@ -4641,7 +4641,7 @@ static void end_reshape_write(struct bio *bio) rdev = conf->mirrors[d].rdev; } - if (bio->bi_error) { + if (bio->bi_status) { /* FIXME should record badblock */ md_error(mddev, rdev); } diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index 0a7af8b0a80a..bfa1e907c472 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -572,7 +572,7 @@ static void r5l_log_endio(struct bio *bio) struct r5l_log *log = io->log; unsigned long flags; - if (bio->bi_error) + if (bio->bi_status) md_error(log->rdev->mddev, log->rdev); bio_put(bio); @@ -1247,7 +1247,7 @@ static void r5l_log_flush_endio(struct bio *bio) unsigned long flags; struct r5l_io_unit *io; - if (bio->bi_error) + if (bio->bi_status) md_error(log->rdev->mddev, log->rdev); spin_lock_irqsave(&log->io_list_lock, flags); @@ -3063,7 +3063,7 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev) if (!log->io_pool) goto io_pool; - log->bs = bioset_create(R5L_POOL_SIZE, 0); + log->bs = bioset_create(R5L_POOL_SIZE, 0, BIOSET_NEED_BVECS); if (!log->bs) goto io_bs; diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c index ccce92e68d7f..77cce3573aa8 100644 --- a/drivers/md/raid5-ppl.c +++ b/drivers/md/raid5-ppl.c @@ -397,7 +397,7 @@ static void ppl_log_endio(struct bio *bio) pr_debug("%s: seq: %llu\n", __func__, io->seq); - if (bio->bi_error) + if (bio->bi_status) md_error(ppl_conf->mddev, log->rdev); list_for_each_entry_safe(sh, next, &io->stripe_list, log_list) { @@ -1150,7 +1150,7 @@ int ppl_init_log(struct r5conf *conf) goto err; } - ppl_conf->bs = bioset_create(conf->raid_disks, 0); + ppl_conf->bs = bioset_create(conf->raid_disks, 0, 0); if (!ppl_conf->bs) { ret = -ENOMEM; goto err; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index ec0f951ae19f..62c965be97e1 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -2476,7 +2476,7 @@ static void raid5_end_read_request(struct bio * bi) pr_debug("end_read_request %llu/%d, count: %d, error %d.\n", (unsigned long long)sh->sector, i, atomic_read(&sh->count), - bi->bi_error); + bi->bi_status); if (i == disks) { bio_reset(bi); BUG(); @@ -2496,7 +2496,7 @@ static void raid5_end_read_request(struct bio * bi) s = sh->sector + rdev->new_data_offset; else s = sh->sector + rdev->data_offset; - if (!bi->bi_error) { + if (!bi->bi_status) { set_bit(R5_UPTODATE, &sh->dev[i].flags); if (test_bit(R5_ReadError, &sh->dev[i].flags)) { /* Note that this cannot happen on a @@ -2613,7 +2613,7 @@ static void raid5_end_write_request(struct bio *bi) } pr_debug("end_write_request %llu/%d, count %d, error: %d.\n", (unsigned long long)sh->sector, i, atomic_read(&sh->count), - bi->bi_error); + bi->bi_status); if (i == disks) { bio_reset(bi); BUG(); @@ -2621,14 +2621,14 @@ static void raid5_end_write_request(struct bio *bi) } if (replacement) { - if (bi->bi_error) + if (bi->bi_status) md_error(conf->mddev, rdev); else if (is_badblock(rdev, sh->sector, STRIPE_SECTORS, &first_bad, &bad_sectors)) set_bit(R5_MadeGoodRepl, &sh->dev[i].flags); } else { - if (bi->bi_error) { + if (bi->bi_status) { set_bit(STRIPE_DEGRADED, &sh->state); set_bit(WriteErrorSeen, &rdev->flags); set_bit(R5_WriteError, &sh->dev[i].flags); @@ -2649,7 +2649,7 @@ static void raid5_end_write_request(struct bio *bi) } rdev_dec_pending(rdev, conf->mddev); - if (sh->batch_head && bi->bi_error && !replacement) + if (sh->batch_head && bi->bi_status && !replacement) set_bit(STRIPE_BATCH_ERR, &sh->batch_head->state); bio_reset(bi); @@ -3381,7 +3381,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, sh->dev[i].sector + STRIPE_SECTORS) { struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector); - bi->bi_error = -EIO; + bi->bi_status = BLK_STS_IOERR; md_write_end(conf->mddev); bio_endio(bi); bi = nextbi; @@ -3403,7 +3403,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, sh->dev[i].sector + STRIPE_SECTORS) { struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector); - bi->bi_error = -EIO; + bi->bi_status = BLK_STS_IOERR; md_write_end(conf->mddev); bio_endio(bi); bi = bi2; @@ -3429,7 +3429,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector); - bi->bi_error = -EIO; + bi->bi_status = BLK_STS_IOERR; bio_endio(bi); bi = nextbi; } @@ -5154,7 +5154,7 @@ static void raid5_align_endio(struct bio *bi) struct mddev *mddev; struct r5conf *conf; struct md_rdev *rdev; - int error = bi->bi_error; + blk_status_t error = bi->bi_status; bio_put(bi); @@ -5731,7 +5731,7 @@ static void raid5_make_request(struct mddev *mddev, struct bio * bi) release_stripe_plug(mddev, sh); } else { /* cannot get stripe for read-ahead, just give-up */ - bi->bi_error = -EIO; + bi->bi_status = BLK_STS_IOERR; break; } } @@ -6943,7 +6943,7 @@ static struct r5conf *setup_conf(struct mddev *mddev) goto abort; } - conf->bio_split = bioset_create(BIO_POOL_SIZE, 0); + conf->bio_split = bioset_create(BIO_POOL_SIZE, 0, 0); if (!conf->bio_split) goto abort; conf->mddev = mddev; diff --git a/drivers/memstick/core/ms_block.c b/drivers/memstick/core/ms_block.c index 99e651c27fb7..22de7f5ed032 100644 --- a/drivers/memstick/core/ms_block.c +++ b/drivers/memstick/core/ms_block.c @@ -1921,12 +1921,13 @@ static void msb_io_work(struct work_struct *work) spin_lock_irqsave(&msb->q_lock, flags); if (len) - if (!__blk_end_request(msb->req, 0, len)) + if (!__blk_end_request(msb->req, BLK_STS_OK, len)) msb->req = NULL; if (error && msb->req) { + blk_status_t ret = errno_to_blk_status(error); dbg_verbose("IO: ending one sector of the request with error"); - if (!__blk_end_request(msb->req, error, msb->page_size)) + if (!__blk_end_request(msb->req, ret, msb->page_size)) msb->req = NULL; } @@ -2014,7 +2015,7 @@ static void msb_submit_req(struct request_queue *q) WARN_ON(!msb->io_queue_stopped); while ((req = blk_fetch_request(q)) != NULL) - __blk_end_request_all(req, -ENODEV); + __blk_end_request_all(req, BLK_STS_IOERR); return; } diff --git a/drivers/memstick/core/mspro_block.c b/drivers/memstick/core/mspro_block.c index c00d8a266878..8897962781bb 100644 --- a/drivers/memstick/core/mspro_block.c +++ b/drivers/memstick/core/mspro_block.c @@ -709,7 +709,8 @@ try_again: msb->req_sg); if (!msb->seg_count) { - chunk = __blk_end_request_cur(msb->block_req, -ENOMEM); + chunk = __blk_end_request_cur(msb->block_req, + BLK_STS_RESOURCE); continue; } @@ -776,7 +777,8 @@ static int mspro_block_complete_req(struct memstick_dev *card, int error) if (error && !t_len) t_len = blk_rq_cur_bytes(msb->block_req); - chunk = __blk_end_request(msb->block_req, error, t_len); + chunk = __blk_end_request(msb->block_req, + errno_to_blk_status(error), t_len); error = mspro_block_issue_req(card, chunk); @@ -838,7 +840,7 @@ static void mspro_block_submit_req(struct request_queue *q) if (msb->eject) { while ((req = blk_fetch_request(q)) != NULL) - __blk_end_request_all(req, -ENODEV); + __blk_end_request_all(req, BLK_STS_IOERR); return; } diff --git a/drivers/mfd/arizona-core.c b/drivers/mfd/arizona-core.c index 75488e65cd96..8d46e3ad9529 100644 --- a/drivers/mfd/arizona-core.c +++ b/drivers/mfd/arizona-core.c @@ -245,8 +245,7 @@ static int arizona_poll_reg(struct arizona *arizona, int ret; ret = regmap_read_poll_timeout(arizona->regmap, - ARIZONA_INTERRUPT_RAW_STATUS_5, val, - ((val & mask) == target), + reg, val, ((val & mask) == target), ARIZONA_REG_POLL_DELAY_US, timeout_ms * 1000); if (ret) diff --git a/drivers/misc/cxl/context.c b/drivers/misc/cxl/context.c index 4472ce11f98d..8c32040b9c09 100644 --- a/drivers/misc/cxl/context.c +++ b/drivers/misc/cxl/context.c @@ -45,7 +45,7 @@ int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master) mutex_init(&ctx->mapping_lock); ctx->mapping = NULL; - if (cxl_is_psl8(afu)) { + if (cxl_is_power8()) { spin_lock_init(&ctx->sste_lock); /* @@ -189,7 +189,7 @@ int cxl_context_iomap(struct cxl_context *ctx, struct vm_area_struct *vma) if (start + len > ctx->afu->adapter->ps_size) return -EINVAL; - if (cxl_is_psl9(ctx->afu)) { + if (cxl_is_power9()) { /* * Make sure there is a valid problem state * area space for this AFU. @@ -324,7 +324,7 @@ static void reclaim_ctx(struct rcu_head *rcu) { struct cxl_context *ctx = container_of(rcu, struct cxl_context, rcu); - if (cxl_is_psl8(ctx->afu)) + if (cxl_is_power8()) free_page((u64)ctx->sstp); if (ctx->ff_page) __free_page(ctx->ff_page); diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h index c8568ea7c518..a03f8e7535e5 100644 --- a/drivers/misc/cxl/cxl.h +++ b/drivers/misc/cxl/cxl.h @@ -357,6 +357,7 @@ static const cxl_p2n_reg_t CXL_PSL_WED_An = {0x0A0}; #define CXL_PSL9_DSISR_An_PF_RGP 0x0000000000000090ULL /* PTE not found (Radix Guest (parent)) 0b10010000 */ #define CXL_PSL9_DSISR_An_PF_HRH 0x0000000000000094ULL /* PTE not found (HPT/Radix Host) 0b10010100 */ #define CXL_PSL9_DSISR_An_PF_STEG 0x000000000000009CULL /* PTE not found (STEG VA) 0b10011100 */ +#define CXL_PSL9_DSISR_An_URTCH 0x00000000000000B4ULL /* Unsupported Radix Tree Configuration 0b10110100 */ /****** CXL_PSL_TFC_An ******************************************************/ #define CXL_PSL_TFC_An_A (1ull << (63-28)) /* Acknowledge non-translation fault */ @@ -844,24 +845,15 @@ static inline bool cxl_is_power8(void) static inline bool cxl_is_power9(void) { - /* intermediate solution */ - if (!cxl_is_power8() && - (cpu_has_feature(CPU_FTRS_POWER9) || - cpu_has_feature(CPU_FTR_POWER9_DD1))) + if (pvr_version_is(PVR_POWER9)) return true; return false; } -static inline bool cxl_is_psl8(struct cxl_afu *afu) +static inline bool cxl_is_power9_dd1(void) { - if (afu->adapter->caia_major == 1) - return true; - return false; -} - -static inline bool cxl_is_psl9(struct cxl_afu *afu) -{ - if (afu->adapter->caia_major == 2) + if ((pvr_version_is(PVR_POWER9)) && + cpu_has_feature(CPU_FTR_POWER9_DD1)) return true; return false; } diff --git a/drivers/misc/cxl/fault.c b/drivers/misc/cxl/fault.c index 5344448f514e..c79e39bad7a4 100644 --- a/drivers/misc/cxl/fault.c +++ b/drivers/misc/cxl/fault.c @@ -187,7 +187,7 @@ static struct mm_struct *get_mem_context(struct cxl_context *ctx) static bool cxl_is_segment_miss(struct cxl_context *ctx, u64 dsisr) { - if ((cxl_is_psl8(ctx->afu)) && (dsisr & CXL_PSL_DSISR_An_DS)) + if ((cxl_is_power8() && (dsisr & CXL_PSL_DSISR_An_DS))) return true; return false; @@ -195,16 +195,23 @@ static bool cxl_is_segment_miss(struct cxl_context *ctx, u64 dsisr) static bool cxl_is_page_fault(struct cxl_context *ctx, u64 dsisr) { - if ((cxl_is_psl8(ctx->afu)) && (dsisr & CXL_PSL_DSISR_An_DM)) - return true; + u64 crs; /* Translation Checkout Response Status */ - if ((cxl_is_psl9(ctx->afu)) && - ((dsisr & CXL_PSL9_DSISR_An_CO_MASK) & - (CXL_PSL9_DSISR_An_PF_SLR | CXL_PSL9_DSISR_An_PF_RGC | - CXL_PSL9_DSISR_An_PF_RGP | CXL_PSL9_DSISR_An_PF_HRH | - CXL_PSL9_DSISR_An_PF_STEG))) + if ((cxl_is_power8()) && (dsisr & CXL_PSL_DSISR_An_DM)) return true; + if (cxl_is_power9()) { + crs = (dsisr & CXL_PSL9_DSISR_An_CO_MASK); + if ((crs == CXL_PSL9_DSISR_An_PF_SLR) || + (crs == CXL_PSL9_DSISR_An_PF_RGC) || + (crs == CXL_PSL9_DSISR_An_PF_RGP) || + (crs == CXL_PSL9_DSISR_An_PF_HRH) || + (crs == CXL_PSL9_DSISR_An_PF_STEG) || + (crs == CXL_PSL9_DSISR_An_URTCH)) { + return true; + } + } + return false; } diff --git a/drivers/misc/cxl/main.c b/drivers/misc/cxl/main.c index 1703655072b1..c1ba0d42cbc8 100644 --- a/drivers/misc/cxl/main.c +++ b/drivers/misc/cxl/main.c @@ -329,8 +329,15 @@ static int __init init_cxl(void) cxl_debugfs_init(); - if ((rc = register_cxl_calls(&cxl_calls))) - goto err; + /* + * we don't register the callback on P9. slb callack is only + * used for the PSL8 MMU and CX4. + */ + if (cxl_is_power8()) { + rc = register_cxl_calls(&cxl_calls); + if (rc) + goto err; + } if (cpu_has_feature(CPU_FTR_HVMODE)) { cxl_ops = &cxl_native_ops; @@ -347,7 +354,8 @@ static int __init init_cxl(void) return 0; err1: - unregister_cxl_calls(&cxl_calls); + if (cxl_is_power8()) + unregister_cxl_calls(&cxl_calls); err: cxl_debugfs_exit(); cxl_file_exit(); @@ -366,7 +374,8 @@ static void exit_cxl(void) cxl_debugfs_exit(); cxl_file_exit(); - unregister_cxl_calls(&cxl_calls); + if (cxl_is_power8()) + unregister_cxl_calls(&cxl_calls); idr_destroy(&cxl_adapter_idr); } diff --git a/drivers/misc/cxl/native.c b/drivers/misc/cxl/native.c index 8d6ea9712dbd..2b2f8894149d 100644 --- a/drivers/misc/cxl/native.c +++ b/drivers/misc/cxl/native.c @@ -105,11 +105,16 @@ static int native_afu_reset(struct cxl_afu *afu) CXL_AFU_Cntl_An_RS_MASK | CXL_AFU_Cntl_An_ES_MASK, false); - /* Re-enable any masked interrupts */ - serr = cxl_p1n_read(afu, CXL_PSL_SERR_An); - serr &= ~CXL_PSL_SERR_An_IRQ_MASKS; - cxl_p1n_write(afu, CXL_PSL_SERR_An, serr); - + /* + * Re-enable any masked interrupts when the AFU is not + * activated to avoid side effects after attaching a process + * in dedicated mode. + */ + if (afu->current_mode == 0) { + serr = cxl_p1n_read(afu, CXL_PSL_SERR_An); + serr &= ~CXL_PSL_SERR_An_IRQ_MASKS; + cxl_p1n_write(afu, CXL_PSL_SERR_An, serr); + } return rc; } @@ -139,9 +144,9 @@ int cxl_psl_purge(struct cxl_afu *afu) pr_devel("PSL purge request\n"); - if (cxl_is_psl8(afu)) + if (cxl_is_power8()) trans_fault = CXL_PSL_DSISR_TRANS; - if (cxl_is_psl9(afu)) + if (cxl_is_power9()) trans_fault = CXL_PSL9_DSISR_An_TF; if (!cxl_ops->link_ok(afu->adapter, afu)) { @@ -603,7 +608,7 @@ static u64 calculate_sr(struct cxl_context *ctx) if (!test_tsk_thread_flag(current, TIF_32BIT)) sr |= CXL_PSL_SR_An_SF; } - if (cxl_is_psl9(ctx->afu)) { + if (cxl_is_power9()) { if (radix_enabled()) sr |= CXL_PSL_SR_An_XLAT_ror; else @@ -1117,10 +1122,10 @@ static irqreturn_t native_handle_psl_slice_error(struct cxl_context *ctx, static bool cxl_is_translation_fault(struct cxl_afu *afu, u64 dsisr) { - if ((cxl_is_psl8(afu)) && (dsisr & CXL_PSL_DSISR_TRANS)) + if ((cxl_is_power8()) && (dsisr & CXL_PSL_DSISR_TRANS)) return true; - if ((cxl_is_psl9(afu)) && (dsisr & CXL_PSL9_DSISR_An_TF)) + if ((cxl_is_power9()) && (dsisr & CXL_PSL9_DSISR_An_TF)) return true; return false; @@ -1194,10 +1199,10 @@ static void native_irq_wait(struct cxl_context *ctx) if (ph != ctx->pe) return; dsisr = cxl_p2n_read(ctx->afu, CXL_PSL_DSISR_An); - if (cxl_is_psl8(ctx->afu) && + if (cxl_is_power8() && ((dsisr & CXL_PSL_DSISR_PENDING) == 0)) return; - if (cxl_is_psl9(ctx->afu) && + if (cxl_is_power9() && ((dsisr & CXL_PSL9_DSISR_PENDING) == 0)) return; /* diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c index 6dc1ee5b92c9..1eb9859809bf 100644 --- a/drivers/misc/cxl/pci.c +++ b/drivers/misc/cxl/pci.c @@ -436,7 +436,7 @@ static int init_implementation_adapter_regs_psl9(struct cxl *adapter, struct pci /* nMMU_ID Defaults to: b’000001001’*/ xsl_dsnctl |= ((u64)0x09 << (63-28)); - if (cxl_is_power9() && !cpu_has_feature(CPU_FTR_POWER9_DD1)) { + if (!(cxl_is_power9_dd1())) { /* * Used to identify CAPI packets which should be sorted into * the Non-Blocking queues by the PHB. This field should match @@ -491,7 +491,7 @@ static int init_implementation_adapter_regs_psl9(struct cxl *adapter, struct pci cxl_p1_write(adapter, CXL_PSL9_APCDEDTYPE, 0x40000003FFFF0000ULL); /* Disable vc dd1 fix */ - if ((cxl_is_power9() && cpu_has_feature(CPU_FTR_POWER9_DD1))) + if (cxl_is_power9_dd1()) cxl_p1_write(adapter, CXL_PSL9_GP_CT, 0x0400000000000001ULL); return 0; @@ -1439,8 +1439,7 @@ int cxl_pci_reset(struct cxl *adapter) * The adapter is about to be reset, so ignore errors. * Not supported on P9 DD1 */ - if ((cxl_is_power8()) || - ((cxl_is_power9() && !cpu_has_feature(CPU_FTR_POWER9_DD1)))) + if ((cxl_is_power8()) || (!(cxl_is_power9_dd1()))) cxl_data_cache_flush(adapter); /* pcie_warm_reset requests a fundamental pci reset which includes a @@ -1750,7 +1749,6 @@ static const struct cxl_service_layer_ops psl9_ops = { .debugfs_add_adapter_regs = cxl_debugfs_add_adapter_regs_psl9, .debugfs_add_afu_regs = cxl_debugfs_add_afu_regs_psl9, .psl_irq_dump_registers = cxl_native_irq_dump_regs_psl9, - .err_irq_dump_registers = cxl_native_err_irq_dump_regs, .debugfs_stop_trace = cxl_stop_trace_psl9, .write_timebase_ctrl = write_timebase_ctrl_psl9, .timebase_read = timebase_read_psl9, @@ -1889,8 +1887,7 @@ static void cxl_pci_remove_adapter(struct cxl *adapter) * Flush adapter datacache as its about to be removed. * Not supported on P9 DD1. */ - if ((cxl_is_power8()) || - ((cxl_is_power9() && !cpu_has_feature(CPU_FTR_POWER9_DD1)))) + if ((cxl_is_power8()) || (!(cxl_is_power9_dd1()))) cxl_data_cache_flush(adapter); cxl_deconfigure_adapter(adapter); diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 8273b078686d..6ff94a948a4b 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -1184,9 +1184,10 @@ static void mmc_blk_issue_discard_rq(struct mmc_queue *mq, struct request *req) struct mmc_card *card = md->queue.card; unsigned int from, nr, arg; int err = 0, type = MMC_BLK_DISCARD; + blk_status_t status = BLK_STS_OK; if (!mmc_can_erase(card)) { - err = -EOPNOTSUPP; + status = BLK_STS_NOTSUPP; goto fail; } @@ -1212,10 +1213,12 @@ static void mmc_blk_issue_discard_rq(struct mmc_queue *mq, struct request *req) if (!err) err = mmc_erase(card, from, nr, arg); } while (err == -EIO && !mmc_blk_reset(md, card->host, type)); - if (!err) + if (err) + status = BLK_STS_IOERR; + else mmc_blk_reset_success(md, type); fail: - blk_end_request(req, err, blk_rq_bytes(req)); + blk_end_request(req, status, blk_rq_bytes(req)); } static void mmc_blk_issue_secdiscard_rq(struct mmc_queue *mq, @@ -1225,9 +1228,10 @@ static void mmc_blk_issue_secdiscard_rq(struct mmc_queue *mq, struct mmc_card *card = md->queue.card; unsigned int from, nr, arg; int err = 0, type = MMC_BLK_SECDISCARD; + blk_status_t status = BLK_STS_OK; if (!(mmc_can_secure_erase_trim(card))) { - err = -EOPNOTSUPP; + status = BLK_STS_NOTSUPP; goto out; } @@ -1254,8 +1258,10 @@ retry: err = mmc_erase(card, from, nr, arg); if (err == -EIO) goto out_retry; - if (err) + if (err) { + status = BLK_STS_IOERR; goto out; + } if (arg == MMC_SECURE_TRIM1_ARG) { if (card->quirks & MMC_QUIRK_INAND_CMD38) { @@ -1270,8 +1276,10 @@ retry: err = mmc_erase(card, from, nr, MMC_SECURE_TRIM2_ARG); if (err == -EIO) goto out_retry; - if (err) + if (err) { + status = BLK_STS_IOERR; goto out; + } } out_retry: @@ -1280,7 +1288,7 @@ out_retry: if (!err) mmc_blk_reset_success(md, type); out: - blk_end_request(req, err, blk_rq_bytes(req)); + blk_end_request(req, status, blk_rq_bytes(req)); } static void mmc_blk_issue_flush(struct mmc_queue *mq, struct request *req) @@ -1290,10 +1298,7 @@ static void mmc_blk_issue_flush(struct mmc_queue *mq, struct request *req) int ret = 0; ret = mmc_flush_cache(card); - if (ret) - ret = -EIO; - - blk_end_request_all(req, ret); + blk_end_request_all(req, ret ? BLK_STS_IOERR : BLK_STS_OK); } /* @@ -1641,7 +1646,7 @@ static void mmc_blk_rw_cmd_abort(struct mmc_queue *mq, struct mmc_card *card, { if (mmc_card_removed(card)) req->rq_flags |= RQF_QUIET; - while (blk_end_request(req, -EIO, blk_rq_cur_bytes(req))); + while (blk_end_request(req, BLK_STS_IOERR, blk_rq_cur_bytes(req))); mmc_queue_req_free(mq, mqrq); } @@ -1661,7 +1666,7 @@ static void mmc_blk_rw_try_restart(struct mmc_queue *mq, struct request *req, */ if (mmc_card_removed(mq->card)) { req->rq_flags |= RQF_QUIET; - blk_end_request_all(req, -EIO); + blk_end_request_all(req, BLK_STS_IOERR); mmc_queue_req_free(mq, mqrq); return; } @@ -1743,7 +1748,7 @@ static void mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *new_req) */ mmc_blk_reset_success(md, type); - req_pending = blk_end_request(old_req, 0, + req_pending = blk_end_request(old_req, BLK_STS_OK, brq->data.bytes_xfered); /* * If the blk_end_request function returns non-zero even @@ -1811,7 +1816,7 @@ static void mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *new_req) * time, so we only reach here after trying to * read a single sector. */ - req_pending = blk_end_request(old_req, -EIO, + req_pending = blk_end_request(old_req, BLK_STS_IOERR, brq->data.blksz); if (!req_pending) { mmc_queue_req_free(mq, mq_rq); @@ -1860,7 +1865,7 @@ void mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req) ret = mmc_blk_part_switch(card, md); if (ret) { if (req) { - blk_end_request_all(req, -EIO); + blk_end_request_all(req, BLK_STS_IOERR); } goto out; } diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c index 5c37b6be3e7b..b659a28c8018 100644 --- a/drivers/mmc/core/queue.c +++ b/drivers/mmc/core/queue.c @@ -133,7 +133,7 @@ static void mmc_request_fn(struct request_queue *q) if (!mq) { while ((req = blk_fetch_request(q)) != NULL) { req->rq_flags |= RQF_QUIET; - __blk_end_request_all(req, -EIO); + __blk_end_request_all(req, BLK_STS_IOERR); } return; } @@ -388,7 +388,6 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, mmc_queue_setup_discard(mq->queue, card); if (card->bouncesz) { - blk_queue_bounce_limit(mq->queue, BLK_BOUNCE_ANY); blk_queue_max_hw_sectors(mq->queue, card->bouncesz / 512); blk_queue_max_segments(mq->queue, card->bouncesz / 512); blk_queue_max_segment_size(mq->queue, card->bouncesz); diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c index 92fc3f7c538d..18957fea82ff 100644 --- a/drivers/mmc/host/sdhci-pci-core.c +++ b/drivers/mmc/host/sdhci-pci-core.c @@ -404,10 +404,9 @@ struct intel_host { bool d3_retune; }; -const u8 intel_dsm_uuid[] = { - 0xA5, 0x3E, 0xC1, 0xF6, 0xCD, 0x65, 0x1F, 0x46, - 0xAB, 0x7A, 0x29, 0xF7, 0xE8, 0xD5, 0xBD, 0x61, -}; +static const guid_t intel_dsm_guid = + GUID_INIT(0xF6C13EA5, 0x65CD, 0x461F, + 0xAB, 0x7A, 0x29, 0xF7, 0xE8, 0xD5, 0xBD, 0x61); static int __intel_dsm(struct intel_host *intel_host, struct device *dev, unsigned int fn, u32 *result) @@ -416,7 +415,7 @@ static int __intel_dsm(struct intel_host *intel_host, struct device *dev, int err = 0; size_t len; - obj = acpi_evaluate_dsm(ACPI_HANDLE(dev), intel_dsm_uuid, 0, fn, NULL); + obj = acpi_evaluate_dsm(ACPI_HANDLE(dev), &intel_dsm_guid, 0, fn, NULL); if (!obj) return -EOPNOTSUPP; diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index 6b8d5cd7dbf6..f336a9b85576 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -73,7 +73,7 @@ static void blktrans_dev_put(struct mtd_blktrans_dev *dev) } -static int do_blktrans_request(struct mtd_blktrans_ops *tr, +static blk_status_t do_blktrans_request(struct mtd_blktrans_ops *tr, struct mtd_blktrans_dev *dev, struct request *req) { @@ -84,33 +84,37 @@ static int do_blktrans_request(struct mtd_blktrans_ops *tr, nsect = blk_rq_cur_bytes(req) >> tr->blkshift; buf = bio_data(req->bio); - if (req_op(req) == REQ_OP_FLUSH) - return tr->flush(dev); + if (req_op(req) == REQ_OP_FLUSH) { + if (tr->flush(dev)) + return BLK_STS_IOERR; + return BLK_STS_OK; + } if (blk_rq_pos(req) + blk_rq_cur_sectors(req) > get_capacity(req->rq_disk)) - return -EIO; + return BLK_STS_IOERR; switch (req_op(req)) { case REQ_OP_DISCARD: - return tr->discard(dev, block, nsect); + if (tr->discard(dev, block, nsect)) + return BLK_STS_IOERR; + return BLK_STS_OK; case REQ_OP_READ: for (; nsect > 0; nsect--, block++, buf += tr->blksize) if (tr->readsect(dev, block, buf)) - return -EIO; + return BLK_STS_IOERR; rq_flush_dcache_pages(req); - return 0; + return BLK_STS_OK; case REQ_OP_WRITE: if (!tr->writesect) - return -EIO; + return BLK_STS_IOERR; rq_flush_dcache_pages(req); for (; nsect > 0; nsect--, block++, buf += tr->blksize) if (tr->writesect(dev, block, buf)) - return -EIO; - return 0; + return BLK_STS_IOERR; default: - return -EIO; + return BLK_STS_IOERR; } } @@ -132,7 +136,7 @@ static void mtd_blktrans_work(struct work_struct *work) spin_lock_irq(rq->queue_lock); while (1) { - int res; + blk_status_t res; dev->bg_stop = false; if (!req && !(req = blk_fetch_request(rq))) { @@ -178,7 +182,7 @@ static void mtd_blktrans_request(struct request_queue *rq) if (!dev) while ((req = blk_fetch_request(rq)) != NULL) - __blk_end_request_all(req, -ENODEV); + __blk_end_request_all(req, BLK_STS_IOERR); else queue_work(dev->wq, &dev->work); } @@ -413,6 +417,7 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new) new->rq->queuedata = new; blk_queue_logical_block_size(new->rq, tr->blksize); + blk_queue_bounce_limit(new->rq, BLK_BOUNCE_HIGH); queue_flag_set_unlocked(QUEUE_FLAG_NONROT, new->rq); queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, new->rq); diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c index 5497e65439df..c3963f880448 100644 --- a/drivers/mtd/ubi/block.c +++ b/drivers/mtd/ubi/block.c @@ -313,10 +313,10 @@ static void ubiblock_do_work(struct work_struct *work) ret = ubiblock_read(pdu); rq_flush_dcache_pages(req); - blk_mq_end_request(req, ret); + blk_mq_end_request(req, errno_to_blk_status(ret)); } -static int ubiblock_queue_rq(struct blk_mq_hw_ctx *hctx, +static blk_status_t ubiblock_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { struct request *req = bd->rq; @@ -327,9 +327,9 @@ static int ubiblock_queue_rq(struct blk_mq_hw_ctx *hctx, case REQ_OP_READ: ubi_sgl_init(&pdu->usgl); queue_work(dev->wq, &pdu->work); - return BLK_MQ_RQ_QUEUE_OK; + return BLK_STS_OK; default: - return BLK_MQ_RQ_QUEUE_ERROR; + return BLK_STS_IOERR; } } diff --git a/drivers/net/arcnet/arcnet.c b/drivers/net/arcnet/arcnet.c index 62ee439d5882..53a1cb551def 100644 --- a/drivers/net/arcnet/arcnet.c +++ b/drivers/net/arcnet/arcnet.c @@ -756,6 +756,7 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) struct net_device *dev = dev_id; struct arcnet_local *lp; int recbuf, status, diagstatus, didsomething, boguscount; + unsigned long flags; int retval = IRQ_NONE; arc_printk(D_DURING, dev, "\n"); @@ -765,7 +766,7 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) lp = netdev_priv(dev); BUG_ON(!lp); - spin_lock(&lp->lock); + spin_lock_irqsave(&lp->lock, flags); /* RESET flag was enabled - if device is not running, we must * clear it right away (but nothing else). @@ -774,7 +775,7 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) if (lp->hw.status(dev) & RESETflag) lp->hw.command(dev, CFLAGScmd | RESETclear); lp->hw.intmask(dev, 0); - spin_unlock(&lp->lock); + spin_unlock_irqrestore(&lp->lock, flags); return retval; } @@ -998,7 +999,7 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) udelay(1); lp->hw.intmask(dev, lp->intmask); - spin_unlock(&lp->lock); + spin_unlock_irqrestore(&lp->lock, flags); return retval; } EXPORT_SYMBOL(arcnet_interrupt); diff --git a/drivers/net/arcnet/capmode.c b/drivers/net/arcnet/capmode.c index 2056878fb087..4fa2e46b48d3 100644 --- a/drivers/net/arcnet/capmode.c +++ b/drivers/net/arcnet/capmode.c @@ -212,7 +212,7 @@ static int ack_tx(struct net_device *dev, int acked) ackpkt->soft.cap.proto = 0; /* using protocol 0 for acknowledge */ ackpkt->soft.cap.mes.ack = acked; - arc_printk(D_PROTO, dev, "Ackknowledge for cap packet %x.\n", + arc_printk(D_PROTO, dev, "Acknowledge for cap packet %x.\n", *((int *)&ackpkt->soft.cap.cookie[0])); ackskb->protocol = cpu_to_be16(ETH_P_ARCNET); diff --git a/drivers/net/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c index 239de38fbd6a..47f80b83dcf4 100644 --- a/drivers/net/arcnet/com20020-pci.c +++ b/drivers/net/arcnet/com20020-pci.c @@ -135,6 +135,7 @@ static int com20020pci_probe(struct pci_dev *pdev, for (i = 0; i < ci->devcount; i++) { struct com20020_pci_channel_map *cm = &ci->chan_map_tbl[i]; struct com20020_dev *card; + int dev_id_mask = 0xf; dev = alloc_arcdev(device); if (!dev) { @@ -166,6 +167,7 @@ static int com20020pci_probe(struct pci_dev *pdev, arcnet_outb(0x00, ioaddr, COM20020_REG_W_COMMAND); arcnet_inb(ioaddr, COM20020_REG_R_DIAGSTAT); + SET_NETDEV_DEV(dev, &pdev->dev); dev->base_addr = ioaddr; dev->dev_addr[0] = node; dev->irq = pdev->irq; @@ -179,8 +181,8 @@ static int com20020pci_probe(struct pci_dev *pdev, /* Get the dev_id from the PLX rotary coder */ if (!strncmp(ci->name, "EAE PLX-PCI MA1", 15)) - dev->dev_id = 0xc; - dev->dev_id ^= inb(priv->misc + ci->rotary) >> 4; + dev_id_mask = 0x3; + dev->dev_id = (inb(priv->misc + ci->rotary) >> 4) & dev_id_mask; snprintf(dev->name, sizeof(dev->name), "arc%d-%d", dev->dev_id, i); diff --git a/drivers/net/arcnet/com20020.c b/drivers/net/arcnet/com20020.c index 13d9ad4b3f5c..78043a9c5981 100644 --- a/drivers/net/arcnet/com20020.c +++ b/drivers/net/arcnet/com20020.c @@ -246,8 +246,6 @@ int com20020_found(struct net_device *dev, int shared) return -ENODEV; } - dev->base_addr = ioaddr; - arc_printk(D_NORMAL, dev, "%s: station %02Xh found at %03lXh, IRQ %d.\n", lp->card_name, dev->dev_addr[0], dev->base_addr, dev->irq); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index a851f95c307a..349a46593abf 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -12729,7 +12729,7 @@ static int bnx2x_set_mc_list(struct bnx2x *bp) } else { /* If no mc addresses are required, flush the configuration */ rc = bnx2x_config_mcast(bp, &rparam, BNX2X_MCAST_CMD_DEL); - if (rc) + if (rc < 0) BNX2X_ERR("Failed to clear multicast configuration %d\n", rc); } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 03f55daecb20..74e8e215524d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1301,10 +1301,11 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, cp_cons = NEXT_CMP(cp_cons); } - if (unlikely(agg_bufs > MAX_SKB_FRAGS)) { + if (unlikely(agg_bufs > MAX_SKB_FRAGS || TPA_END_ERRORS(tpa_end1))) { bnxt_abort_tpa(bp, bnapi, cp_cons, agg_bufs); - netdev_warn(bp->dev, "TPA frags %d exceeded MAX_SKB_FRAGS %d\n", - agg_bufs, (int)MAX_SKB_FRAGS); + if (agg_bufs > MAX_SKB_FRAGS) + netdev_warn(bp->dev, "TPA frags %d exceeded MAX_SKB_FRAGS %d\n", + agg_bufs, (int)MAX_SKB_FRAGS); return NULL; } @@ -1562,6 +1563,45 @@ next_rx_no_prod: return rc; } +/* In netpoll mode, if we are using a combined completion ring, we need to + * discard the rx packets and recycle the buffers. + */ +static int bnxt_force_rx_discard(struct bnxt *bp, struct bnxt_napi *bnapi, + u32 *raw_cons, u8 *event) +{ + struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring; + u32 tmp_raw_cons = *raw_cons; + struct rx_cmp_ext *rxcmp1; + struct rx_cmp *rxcmp; + u16 cp_cons; + u8 cmp_type; + + cp_cons = RING_CMP(tmp_raw_cons); + rxcmp = (struct rx_cmp *) + &cpr->cp_desc_ring[CP_RING(cp_cons)][CP_IDX(cp_cons)]; + + tmp_raw_cons = NEXT_RAW_CMP(tmp_raw_cons); + cp_cons = RING_CMP(tmp_raw_cons); + rxcmp1 = (struct rx_cmp_ext *) + &cpr->cp_desc_ring[CP_RING(cp_cons)][CP_IDX(cp_cons)]; + + if (!RX_CMP_VALID(rxcmp1, tmp_raw_cons)) + return -EBUSY; + + cmp_type = RX_CMP_TYPE(rxcmp); + if (cmp_type == CMP_TYPE_RX_L2_CMP) { + rxcmp1->rx_cmp_cfa_code_errors_v2 |= + cpu_to_le32(RX_CMPL_ERRORS_CRC_ERROR); + } else if (cmp_type == CMP_TYPE_RX_L2_TPA_END_CMP) { + struct rx_tpa_end_cmp_ext *tpa_end1; + + tpa_end1 = (struct rx_tpa_end_cmp_ext *)rxcmp1; + tpa_end1->rx_tpa_end_cmp_errors_v2 |= + cpu_to_le32(RX_TPA_END_CMP_ERRORS); + } + return bnxt_rx_pkt(bp, bnapi, raw_cons, event); +} + #define BNXT_GET_EVENT_PORT(data) \ ((data) & \ ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_PORT_ID_MASK) @@ -1744,7 +1784,11 @@ static int bnxt_poll_work(struct bnxt *bp, struct bnxt_napi *bnapi, int budget) if (unlikely(tx_pkts > bp->tx_wake_thresh)) rx_pkts = budget; } else if ((TX_CMP_TYPE(txcmp) & 0x30) == 0x10) { - rc = bnxt_rx_pkt(bp, bnapi, &raw_cons, &event); + if (likely(budget)) + rc = bnxt_rx_pkt(bp, bnapi, &raw_cons, &event); + else + rc = bnxt_force_rx_discard(bp, bnapi, &raw_cons, + &event); if (likely(rc >= 0)) rx_pkts += rc; else if (rc == -EBUSY) /* partial completion */ @@ -6663,12 +6707,11 @@ static void bnxt_poll_controller(struct net_device *dev) struct bnxt *bp = netdev_priv(dev); int i; - for (i = 0; i < bp->cp_nr_rings; i++) { - struct bnxt_irq *irq = &bp->irq_tbl[i]; + /* Only process tx rings/combined rings in netpoll mode. */ + for (i = 0; i < bp->tx_nr_rings; i++) { + struct bnxt_tx_ring_info *txr = &bp->tx_ring[i]; - disable_irq(irq->vector); - irq->handler(irq->vector, bp->bnapi[i]); - enable_irq(irq->vector); + napi_schedule(&txr->bnapi->napi); } } #endif diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 3ef42dbc6327..d46a85041083 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -374,12 +374,16 @@ struct rx_tpa_end_cmp_ext { __le32 rx_tpa_end_cmp_errors_v2; #define RX_TPA_END_CMP_V2 (0x1 << 0) - #define RX_TPA_END_CMP_ERRORS (0x7fff << 1) + #define RX_TPA_END_CMP_ERRORS (0x3 << 1) #define RX_TPA_END_CMPL_ERRORS_SHIFT 1 u32 rx_tpa_end_cmp_start_opaque; }; +#define TPA_END_ERRORS(rx_tpa_end_ext) \ + ((rx_tpa_end_ext)->rx_tpa_end_cmp_errors_v2 & \ + cpu_to_le32(RX_TPA_END_CMP_ERRORS)) + #define DB_IDX_MASK 0xffffff #define DB_IDX_VALID (0x1 << 26) #define DB_IRQ_DIS (0x1 << 27) diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_main.h b/drivers/net/ethernet/cavium/liquidio/octeon_main.h index bed9ef17bc26..7ccffbb0019e 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_main.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_main.h @@ -144,7 +144,7 @@ static inline int sleep_cond(wait_queue_head_t *wait_queue, int *condition) { int errno = 0; - wait_queue_t we; + wait_queue_entry_t we; init_waitqueue_entry(&we, current); add_wait_queue(wait_queue, &we); @@ -171,7 +171,7 @@ sleep_timeout_cond(wait_queue_head_t *wait_queue, int *condition, int timeout) { - wait_queue_t we; + wait_queue_entry_t we; init_waitqueue_entry(&we, current); add_wait_queue(wait_queue, &we); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index ea1bfcf1870a..53309f659951 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -2171,9 +2171,10 @@ static int cxgb_up(struct adapter *adap) { int err; + mutex_lock(&uld_mutex); err = setup_sge_queues(adap); if (err) - goto out; + goto rel_lock; err = setup_rss(adap); if (err) goto freeq; @@ -2197,7 +2198,6 @@ static int cxgb_up(struct adapter *adap) goto irq_err; } - mutex_lock(&uld_mutex); enable_rx(adap); t4_sge_start(adap); t4_intr_enable(adap); @@ -2210,13 +2210,15 @@ static int cxgb_up(struct adapter *adap) #endif /* Initialize hash mac addr list*/ INIT_LIST_HEAD(&adap->mac_hlist); - out: return err; + irq_err: dev_err(adap->pdev_dev, "request_irq failed, err %d\n", err); freeq: t4_free_sge_resources(adap); - goto out; + rel_lock: + mutex_unlock(&uld_mutex); + return err; } static void cxgb_down(struct adapter *adapter) diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 9a520e4f0df9..290ad0563320 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -2647,7 +2647,7 @@ static int dpaa_eth_probe(struct platform_device *pdev) priv->buf_layout[TX].priv_data_size = DPAA_TX_PRIV_DATA_SIZE; /* Tx */ /* device used for DMA mapping */ - arch_setup_dma_ops(dev, 0, 0, NULL, false); + set_dma_ops(dev, get_dma_ops(&pdev->dev)); err = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(40)); if (err) { dev_err(dev, "dma_coerce_mask_and_coherent() failed\n"); diff --git a/drivers/net/ethernet/freescale/fman/Kconfig b/drivers/net/ethernet/freescale/fman/Kconfig index dc0850b3b517..8870a9a798ca 100644 --- a/drivers/net/ethernet/freescale/fman/Kconfig +++ b/drivers/net/ethernet/freescale/fman/Kconfig @@ -2,6 +2,7 @@ config FSL_FMAN tristate "FMan support" depends on FSL_SOC || ARCH_LAYERSCAPE || COMPILE_TEST select GENERIC_ALLOCATOR + depends on HAS_DMA select PHYLIB default n help diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c index 0b31f8502ada..6e67d22fd0d5 100644 --- a/drivers/net/ethernet/freescale/fman/mac.c +++ b/drivers/net/ethernet/freescale/fman/mac.c @@ -623,6 +623,8 @@ static struct platform_device *dpaa_eth_add_device(int fman_id, goto no_mem; } + set_dma_ops(&pdev->dev, get_dma_ops(priv->dev)); + ret = platform_device_add_data(pdev, &data, sizeof(data)); if (ret) goto err; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c index e13aa064a8e9..7a8addda726e 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c @@ -29,10 +29,9 @@ enum _dsm_rst_type { HNS_ROCE_RESET_FUNC = 0x7, }; -const u8 hns_dsaf_acpi_dsm_uuid[] = { - 0x1A, 0xAA, 0x85, 0x1A, 0x93, 0xE2, 0x5E, 0x41, - 0x8E, 0x28, 0x8D, 0x69, 0x0A, 0x0F, 0x82, 0x0A -}; +static const guid_t hns_dsaf_acpi_dsm_guid = + GUID_INIT(0x1A85AA1A, 0xE293, 0x415E, + 0x8E, 0x28, 0x8D, 0x69, 0x0A, 0x0F, 0x82, 0x0A); static void dsaf_write_sub(struct dsaf_device *dsaf_dev, u32 reg, u32 val) { @@ -151,7 +150,7 @@ static void hns_dsaf_acpi_srst_by_port(struct dsaf_device *dsaf_dev, u8 op_type, argv4.package.elements = obj_args; obj = acpi_evaluate_dsm(ACPI_HANDLE(dsaf_dev->dev), - hns_dsaf_acpi_dsm_uuid, 0, op_type, &argv4); + &hns_dsaf_acpi_dsm_guid, 0, op_type, &argv4); if (!obj) { dev_warn(dsaf_dev->dev, "reset port_type%d port%d fail!", port_type, port); @@ -434,7 +433,7 @@ static phy_interface_t hns_mac_get_phy_if_acpi(struct hns_mac_cb *mac_cb) argv4.package.elements = &obj_args, obj = acpi_evaluate_dsm(ACPI_HANDLE(mac_cb->dev), - hns_dsaf_acpi_dsm_uuid, 0, + &hns_dsaf_acpi_dsm_guid, 0, HNS_OP_GET_PORT_TYPE_FUNC, &argv4); if (!obj || obj->type != ACPI_TYPE_INTEGER) @@ -474,7 +473,7 @@ int hns_mac_get_sfp_prsnt_acpi(struct hns_mac_cb *mac_cb, int *sfp_prsnt) argv4.package.elements = &obj_args, obj = acpi_evaluate_dsm(ACPI_HANDLE(mac_cb->dev), - hns_dsaf_acpi_dsm_uuid, 0, + &hns_dsaf_acpi_dsm_guid, 0, HNS_OP_GET_SFP_STAT_FUNC, &argv4); if (!obj || obj->type != ACPI_TYPE_INTEGER) @@ -565,7 +564,7 @@ hns_mac_config_sds_loopback_acpi(struct hns_mac_cb *mac_cb, bool en) argv4.package.elements = obj_args; obj = acpi_evaluate_dsm(ACPI_HANDLE(mac_cb->dsaf_dev->dev), - hns_dsaf_acpi_dsm_uuid, 0, + &hns_dsaf_acpi_dsm_guid, 0, HNS_OP_SERDES_LP_FUNC, &argv4); if (!obj) { dev_warn(mac_cb->dsaf_dev->dev, "set port%d serdes lp fail!", diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c index b8fab149690f..e95795b3c841 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -288,9 +288,15 @@ static int hns_nic_config_phy_loopback(struct phy_device *phy_dev, u8 en) /* Force 1000M Link, Default is 0x0200 */ phy_write(phy_dev, 7, 0x20C); - phy_write(phy_dev, HNS_PHY_PAGE_REG, 0); - /* Enable PHY loop-back */ + /* Powerup Fiber */ + phy_write(phy_dev, HNS_PHY_PAGE_REG, 1); + val = phy_read(phy_dev, COPPER_CONTROL_REG); + val &= ~PHY_POWER_DOWN; + phy_write(phy_dev, COPPER_CONTROL_REG, val); + + /* Enable Phy Loopback */ + phy_write(phy_dev, HNS_PHY_PAGE_REG, 0); val = phy_read(phy_dev, COPPER_CONTROL_REG); val |= PHY_LOOP_BACK; val &= ~PHY_POWER_DOWN; @@ -299,6 +305,12 @@ static int hns_nic_config_phy_loopback(struct phy_device *phy_dev, u8 en) phy_write(phy_dev, HNS_PHY_PAGE_REG, 0xFA); phy_write(phy_dev, 1, 0x400); phy_write(phy_dev, 7, 0x200); + + phy_write(phy_dev, HNS_PHY_PAGE_REG, 1); + val = phy_read(phy_dev, COPPER_CONTROL_REG); + val |= PHY_POWER_DOWN; + phy_write(phy_dev, COPPER_CONTROL_REG, val); + phy_write(phy_dev, HNS_PHY_PAGE_REG, 0); phy_write(phy_dev, 9, 0xF00); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 8209affa75c3..16486dff1493 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1242,11 +1242,11 @@ static int mlx5e_get_ts_info(struct net_device *dev, SOF_TIMESTAMPING_RX_HARDWARE | SOF_TIMESTAMPING_RAW_HARDWARE; - info->tx_types = (BIT(1) << HWTSTAMP_TX_OFF) | - (BIT(1) << HWTSTAMP_TX_ON); + info->tx_types = BIT(HWTSTAMP_TX_OFF) | + BIT(HWTSTAMP_TX_ON); - info->rx_filters = (BIT(1) << HWTSTAMP_FILTER_NONE) | - (BIT(1) << HWTSTAMP_FILTER_ALL); + info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | + BIT(HWTSTAMP_FILTER_ALL); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 41cd22a223dc..277f4de30375 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4241,7 +4241,8 @@ struct net_device *mlx5e_create_netdev(struct mlx5_core_dev *mdev, return netdev; err_cleanup_nic: - profile->cleanup(priv); + if (profile->cleanup) + profile->cleanup(priv); free_netdev(netdev); return NULL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 79462c0368a0..46984a52a94b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -791,6 +791,8 @@ static void mlx5e_build_rep_params(struct mlx5_core_dev *mdev, params->tx_max_inline = mlx5e_get_max_inline_cap(mdev); params->num_tc = 1; params->lro_wqe_sz = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ; + + mlx5_query_min_inline(mdev, ¶ms->tx_min_inline_mode); } static void mlx5e_build_rep_netdev(struct net_device *netdev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index ec63158ab643..9df9fc0d26f5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -895,7 +895,6 @@ static struct mlx5_fields fields[] = { {MLX5_ACTION_IN_FIELD_OUT_SMAC_15_0, 2, offsetof(struct pedit_headers, eth.h_source[4])}, {MLX5_ACTION_IN_FIELD_OUT_ETHERTYPE, 2, offsetof(struct pedit_headers, eth.h_proto)}, - {MLX5_ACTION_IN_FIELD_OUT_IP_DSCP, 1, offsetof(struct pedit_headers, ip4.tos)}, {MLX5_ACTION_IN_FIELD_OUT_IP_TTL, 1, offsetof(struct pedit_headers, ip4.ttl)}, {MLX5_ACTION_IN_FIELD_OUT_SIPV4, 4, offsetof(struct pedit_headers, ip4.saddr)}, {MLX5_ACTION_IN_FIELD_OUT_DIPV4, 4, offsetof(struct pedit_headers, ip4.daddr)}, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index f991f669047e..a53e982a6863 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -906,21 +906,34 @@ static int esw_inline_mode_to_devlink(u8 mlx5_mode, u8 *mode) return 0; } -int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode) +static int mlx5_devlink_eswitch_check(struct devlink *devlink) { - struct mlx5_core_dev *dev; - u16 cur_mlx5_mode, mlx5_mode = 0; + struct mlx5_core_dev *dev = devlink_priv(devlink); - dev = devlink_priv(devlink); + if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH) + return -EOPNOTSUPP; if (!MLX5_CAP_GEN(dev, vport_group_manager)) return -EOPNOTSUPP; - cur_mlx5_mode = dev->priv.eswitch->mode; - - if (cur_mlx5_mode == SRIOV_NONE) + if (dev->priv.eswitch->mode == SRIOV_NONE) return -EOPNOTSUPP; + return 0; +} + +int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + u16 cur_mlx5_mode, mlx5_mode = 0; + int err; + + err = mlx5_devlink_eswitch_check(devlink); + if (err) + return err; + + cur_mlx5_mode = dev->priv.eswitch->mode; + if (esw_mode_from_devlink(mode, &mlx5_mode)) return -EINVAL; @@ -937,15 +950,12 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode) int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode) { - struct mlx5_core_dev *dev; - - dev = devlink_priv(devlink); - - if (!MLX5_CAP_GEN(dev, vport_group_manager)) - return -EOPNOTSUPP; + struct mlx5_core_dev *dev = devlink_priv(devlink); + int err; - if (dev->priv.eswitch->mode == SRIOV_NONE) - return -EOPNOTSUPP; + err = mlx5_devlink_eswitch_check(devlink); + if (err) + return err; return esw_mode_to_devlink(dev->priv.eswitch->mode, mode); } @@ -954,15 +964,12 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode) { struct mlx5_core_dev *dev = devlink_priv(devlink); struct mlx5_eswitch *esw = dev->priv.eswitch; - int num_vports = esw->enabled_vports; int err, vport; u8 mlx5_mode; - if (!MLX5_CAP_GEN(dev, vport_group_manager)) - return -EOPNOTSUPP; - - if (esw->mode == SRIOV_NONE) - return -EOPNOTSUPP; + err = mlx5_devlink_eswitch_check(devlink); + if (err) + return err; switch (MLX5_CAP_ETH(dev, wqe_inline_mode)) { case MLX5_CAP_INLINE_MODE_NOT_REQUIRED: @@ -985,7 +992,7 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode) if (err) goto out; - for (vport = 1; vport < num_vports; vport++) { + for (vport = 1; vport < esw->enabled_vports; vport++) { err = mlx5_modify_nic_vport_min_inline(dev, vport, mlx5_mode); if (err) { esw_warn(dev, "Failed to set min inline on vport %d\n", @@ -1010,12 +1017,11 @@ int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode) { struct mlx5_core_dev *dev = devlink_priv(devlink); struct mlx5_eswitch *esw = dev->priv.eswitch; + int err; - if (!MLX5_CAP_GEN(dev, vport_group_manager)) - return -EOPNOTSUPP; - - if (esw->mode == SRIOV_NONE) - return -EOPNOTSUPP; + err = mlx5_devlink_eswitch_check(devlink); + if (err) + return err; return esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode); } @@ -1062,11 +1068,9 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, u8 encap) struct mlx5_eswitch *esw = dev->priv.eswitch; int err; - if (!MLX5_CAP_GEN(dev, vport_group_manager)) - return -EOPNOTSUPP; - - if (esw->mode == SRIOV_NONE) - return -EOPNOTSUPP; + err = mlx5_devlink_eswitch_check(devlink); + if (err) + return err; if (encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE && (!MLX5_CAP_ESW_FLOWTABLE_FDB(dev, encap) || @@ -1105,12 +1109,11 @@ int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, u8 *encap) { struct mlx5_core_dev *dev = devlink_priv(devlink); struct mlx5_eswitch *esw = dev->priv.eswitch; + int err; - if (!MLX5_CAP_GEN(dev, vport_group_manager)) - return -EOPNOTSUPP; - - if (esw->mode == SRIOV_NONE) - return -EOPNOTSUPP; + err = mlx5_devlink_eswitch_check(devlink); + if (err) + return err; *encap = esw->offloads.encap; return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 4f577a5abf88..13be264587f1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -175,8 +175,9 @@ static struct mlx5_profile profile[] = { }, }; -#define FW_INIT_TIMEOUT_MILI 2000 -#define FW_INIT_WAIT_MS 2 +#define FW_INIT_TIMEOUT_MILI 2000 +#define FW_INIT_WAIT_MS 2 +#define FW_PRE_INIT_TIMEOUT_MILI 10000 static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili) { @@ -1013,6 +1014,15 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, */ dev->state = MLX5_DEVICE_STATE_UP; + /* wait for firmware to accept initialization segments configurations + */ + err = wait_fw_init(dev, FW_PRE_INIT_TIMEOUT_MILI); + if (err) { + dev_err(&dev->pdev->dev, "Firmware over %d MS in pre-initializing state, aborting\n", + FW_PRE_INIT_TIMEOUT_MILI); + goto out; + } + err = mlx5_cmd_init(dev); if (err) { dev_err(&pdev->dev, "Failed initializing command interface, aborting\n"); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 9f89c4137d21..0744452a0b18 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -3334,6 +3334,9 @@ static int mlxsw_sp_inetaddr_vlan_event(struct net_device *vlan_dev, struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(vlan_dev); u16 vid = vlan_dev_vlan_id(vlan_dev); + if (netif_is_bridge_port(vlan_dev)) + return 0; + if (mlxsw_sp_port_dev_check(real_dev)) return mlxsw_sp_inetaddr_vport_event(vlan_dev, real_dev, event, vid); diff --git a/drivers/net/ethernet/rocker/rocker_ofdpa.c b/drivers/net/ethernet/rocker/rocker_ofdpa.c index 2ae852454780..a9ce82d3e9cf 100644 --- a/drivers/net/ethernet/rocker/rocker_ofdpa.c +++ b/drivers/net/ethernet/rocker/rocker_ofdpa.c @@ -1505,8 +1505,8 @@ static int ofdpa_port_ipv4_nh(struct ofdpa_port *ofdpa_port, *index = entry->index; resolved = false; } else if (removing) { - ofdpa_neigh_del(trans, found); *index = found->index; + ofdpa_neigh_del(trans, found); } else if (updating) { ofdpa_neigh_update(found, trans, NULL, false); resolved = !is_zero_ether_addr(found->eth_dst); diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 78efb2822b86..78f9e43420e0 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -4172,7 +4172,7 @@ found: * recipients */ if (is_mc_recip) { - MCDI_DECLARE_BUF(inbuf, MC_CMD_FILTER_OP_IN_LEN); + MCDI_DECLARE_BUF(inbuf, MC_CMD_FILTER_OP_EXT_IN_LEN); unsigned int depth, i; memset(inbuf, 0, sizeof(inbuf)); @@ -4320,7 +4320,7 @@ static int efx_ef10_filter_remove_internal(struct efx_nic *efx, efx_ef10_filter_set_entry(table, filter_idx, NULL, 0); } else { efx_mcdi_display_error(efx, MC_CMD_FILTER_OP, - MC_CMD_FILTER_OP_IN_LEN, + MC_CMD_FILTER_OP_EXT_IN_LEN, NULL, 0, rc); } } @@ -4453,7 +4453,7 @@ static s32 efx_ef10_filter_rfs_insert(struct efx_nic *efx, struct efx_filter_spec *spec) { struct efx_ef10_filter_table *table = efx->filter_state; - MCDI_DECLARE_BUF(inbuf, MC_CMD_FILTER_OP_IN_LEN); + MCDI_DECLARE_BUF(inbuf, MC_CMD_FILTER_OP_EXT_IN_LEN); struct efx_filter_spec *saved_spec; unsigned int hash, i, depth = 1; bool replacing = false; @@ -4940,7 +4940,7 @@ not_restored: static void efx_ef10_filter_table_remove(struct efx_nic *efx) { struct efx_ef10_filter_table *table = efx->filter_state; - MCDI_DECLARE_BUF(inbuf, MC_CMD_FILTER_OP_IN_LEN); + MCDI_DECLARE_BUF(inbuf, MC_CMD_FILTER_OP_EXT_IN_LEN); struct efx_filter_spec *spec; unsigned int filter_idx; int rc; @@ -5105,6 +5105,7 @@ static int efx_ef10_filter_insert_addr_list(struct efx_nic *efx, /* Insert/renew filters */ for (i = 0; i < addr_count; i++) { + EFX_WARN_ON_PARANOID(ids[i] != EFX_EF10_FILTER_ID_INVALID); efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, filter_flags, 0); efx_filter_set_eth_local(&spec, vlan->vid, addr_list[i].addr); rc = efx_ef10_filter_insert(efx, &spec, true); @@ -5122,11 +5123,11 @@ static int efx_ef10_filter_insert_addr_list(struct efx_nic *efx, } return rc; } else { - /* mark as not inserted, and carry on */ - rc = EFX_EF10_FILTER_ID_INVALID; + /* keep invalid ID, and carry on */ } + } else { + ids[i] = efx_ef10_filter_get_unsafe_id(rc); } - ids[i] = efx_ef10_filter_get_unsafe_id(rc); } if (multicast && rollback) { diff --git a/drivers/net/ethernet/sfc/ef10_sriov.c b/drivers/net/ethernet/sfc/ef10_sriov.c index b7e4345c990d..019cef1d3cf7 100644 --- a/drivers/net/ethernet/sfc/ef10_sriov.c +++ b/drivers/net/ethernet/sfc/ef10_sriov.c @@ -661,8 +661,6 @@ restore_filters: up_write(&vf->efx->filter_sem); mutex_unlock(&vf->efx->mac_lock); - up_write(&vf->efx->filter_sem); - rc2 = efx_net_open(vf->efx->net_dev); if (rc2) goto reset_nic; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index d16d11bfc046..6e4cbc6ce0ef 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2831,7 +2831,6 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) tx_q->tx_skbuff_dma[first_entry].buf = des; tx_q->tx_skbuff_dma[first_entry].len = skb_headlen(skb); - tx_q->tx_skbuff[first_entry] = skb; first->des0 = cpu_to_le32(des); @@ -2865,6 +2864,14 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) tx_q->tx_skbuff_dma[tx_q->cur_tx].last_segment = true; + /* Only the last descriptor gets to point to the skb. */ + tx_q->tx_skbuff[tx_q->cur_tx] = skb; + + /* We've used all descriptors we need for this skb, however, + * advance cur_tx so that it references a fresh descriptor. + * ndo_start_xmit will fill this descriptor the next time it's + * called and stmmac_tx_clean may clean up to this descriptor. + */ tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, DMA_TX_SIZE); if (unlikely(stmmac_tx_avail(priv, queue) <= (MAX_SKB_FRAGS + 1))) { @@ -2998,8 +3005,6 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) first = desc; - tx_q->tx_skbuff[first_entry] = skb; - enh_desc = priv->plat->enh_desc; /* To program the descriptors according to the size of the frame */ if (enh_desc) @@ -3047,8 +3052,15 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) skb->len); } - entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE); + /* Only the last descriptor gets to point to the skb. */ + tx_q->tx_skbuff[entry] = skb; + /* We've used all descriptors we need for this skb, however, + * advance cur_tx so that it references a fresh descriptor. + * ndo_start_xmit will fill this descriptor the next time it's + * called and stmmac_tx_clean may clean up to this descriptor. + */ + entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE); tx_q->cur_tx = entry; if (netif_msg_pktdata(priv)) { diff --git a/drivers/net/ethernet/ti/cpsw-common.c b/drivers/net/ethernet/ti/cpsw-common.c index 1562ab4151e1..56ba411421f0 100644 --- a/drivers/net/ethernet/ti/cpsw-common.c +++ b/drivers/net/ethernet/ti/cpsw-common.c @@ -90,7 +90,7 @@ int ti_cm_get_macid(struct device *dev, int slave, u8 *mac_addr) if (of_device_is_compatible(dev->of_node, "ti,dm816-emac")) return cpsw_am33xx_cm_get_macid(dev, 0x30, slave, mac_addr); - if (of_machine_is_compatible("ti,am4372")) + if (of_machine_is_compatible("ti,am43")) return cpsw_am33xx_cm_get_macid(dev, 0x630, slave, mac_addr); if (of_machine_is_compatible("ti,dra7")) diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 82d6c022ca85..643c539a08ba 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -776,7 +776,7 @@ static int netvsc_set_channels(struct net_device *net, channels->rx_count || channels->tx_count || channels->other_count) return -EINVAL; - if (count > net->num_tx_queues || count > net->num_rx_queues) + if (count > net->num_tx_queues || count > VRSS_CHANNEL_MAX) return -EINVAL; if (!nvdev || nvdev->destroy) @@ -1203,7 +1203,7 @@ static int netvsc_set_rxfh(struct net_device *dev, const u32 *indir, rndis_dev = ndev->extension; if (indir) { for (i = 0; i < ITAB_NUM; i++) - if (indir[i] >= dev->num_rx_queues) + if (indir[i] >= VRSS_CHANNEL_MAX) return -EINVAL; for (i = 0; i < ITAB_NUM; i++) diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 67bf7ebae5c6..72b801803aa4 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -39,16 +39,20 @@ #define MACVLAN_HASH_SIZE (1<<MACVLAN_HASH_BITS) #define MACVLAN_BC_QUEUE_LEN 1000 +#define MACVLAN_F_PASSTHRU 1 +#define MACVLAN_F_ADDRCHANGE 2 + struct macvlan_port { struct net_device *dev; struct hlist_head vlan_hash[MACVLAN_HASH_SIZE]; struct list_head vlans; struct sk_buff_head bc_queue; struct work_struct bc_work; - bool passthru; + u32 flags; int count; struct hlist_head vlan_source_hash[MACVLAN_HASH_SIZE]; DECLARE_BITMAP(mc_filter, MACVLAN_MC_FILTER_SZ); + unsigned char perm_addr[ETH_ALEN]; }; struct macvlan_source_entry { @@ -66,6 +70,31 @@ struct macvlan_skb_cb { static void macvlan_port_destroy(struct net_device *dev); +static inline bool macvlan_passthru(const struct macvlan_port *port) +{ + return port->flags & MACVLAN_F_PASSTHRU; +} + +static inline void macvlan_set_passthru(struct macvlan_port *port) +{ + port->flags |= MACVLAN_F_PASSTHRU; +} + +static inline bool macvlan_addr_change(const struct macvlan_port *port) +{ + return port->flags & MACVLAN_F_ADDRCHANGE; +} + +static inline void macvlan_set_addr_change(struct macvlan_port *port) +{ + port->flags |= MACVLAN_F_ADDRCHANGE; +} + +static inline void macvlan_clear_addr_change(struct macvlan_port *port) +{ + port->flags &= ~MACVLAN_F_ADDRCHANGE; +} + /* Hash Ethernet address */ static u32 macvlan_eth_hash(const unsigned char *addr) { @@ -181,11 +210,12 @@ static void macvlan_hash_change_addr(struct macvlan_dev *vlan, static bool macvlan_addr_busy(const struct macvlan_port *port, const unsigned char *addr) { - /* Test to see if the specified multicast address is + /* Test to see if the specified address is * currently in use by the underlying device or * another macvlan. */ - if (ether_addr_equal_64bits(port->dev->dev_addr, addr)) + if (!macvlan_passthru(port) && !macvlan_addr_change(port) && + ether_addr_equal_64bits(port->dev->dev_addr, addr)) return true; if (macvlan_hash_lookup(port, addr)) @@ -445,7 +475,7 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb) } macvlan_forward_source(skb, port, eth->h_source); - if (port->passthru) + if (macvlan_passthru(port)) vlan = list_first_or_null_rcu(&port->vlans, struct macvlan_dev, list); else @@ -574,7 +604,7 @@ static int macvlan_open(struct net_device *dev) struct net_device *lowerdev = vlan->lowerdev; int err; - if (vlan->port->passthru) { + if (macvlan_passthru(vlan->port)) { if (!(vlan->flags & MACVLAN_FLAG_NOPROMISC)) { err = dev_set_promiscuity(lowerdev, 1); if (err < 0) @@ -649,7 +679,7 @@ static int macvlan_stop(struct net_device *dev) dev_uc_unsync(lowerdev, dev); dev_mc_unsync(lowerdev, dev); - if (vlan->port->passthru) { + if (macvlan_passthru(vlan->port)) { if (!(vlan->flags & MACVLAN_FLAG_NOPROMISC)) dev_set_promiscuity(lowerdev, -1); goto hash_del; @@ -672,6 +702,7 @@ static int macvlan_sync_address(struct net_device *dev, unsigned char *addr) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; + struct macvlan_port *port = vlan->port; int err; if (!(dev->flags & IFF_UP)) { @@ -682,7 +713,7 @@ static int macvlan_sync_address(struct net_device *dev, unsigned char *addr) if (macvlan_addr_busy(vlan->port, addr)) return -EBUSY; - if (!vlan->port->passthru) { + if (!macvlan_passthru(port)) { err = dev_uc_add(lowerdev, addr); if (err) return err; @@ -692,6 +723,15 @@ static int macvlan_sync_address(struct net_device *dev, unsigned char *addr) macvlan_hash_change_addr(vlan, addr); } + if (macvlan_passthru(port) && !macvlan_addr_change(port)) { + /* Since addr_change isn't set, we are here due to lower + * device change. Save the lower-dev address so we can + * restore it later. + */ + ether_addr_copy(vlan->port->perm_addr, + lowerdev->dev_addr); + } + macvlan_clear_addr_change(port); return 0; } @@ -703,7 +743,12 @@ static int macvlan_set_mac_address(struct net_device *dev, void *p) if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; + /* If the addresses are the same, this is a no-op */ + if (ether_addr_equal(dev->dev_addr, addr->sa_data)) + return 0; + if (vlan->mode == MACVLAN_MODE_PASSTHRU) { + macvlan_set_addr_change(vlan->port); dev_set_mac_address(vlan->lowerdev, addr); return 0; } @@ -928,7 +973,7 @@ static int macvlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], /* Support unicast filter only on passthru devices. * Multicast filter should be allowed on all devices. */ - if (!vlan->port->passthru && is_unicast_ether_addr(addr)) + if (!macvlan_passthru(vlan->port) && is_unicast_ether_addr(addr)) return -EOPNOTSUPP; if (flags & NLM_F_REPLACE) @@ -952,7 +997,7 @@ static int macvlan_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], /* Support unicast filter only on passthru devices. * Multicast filter should be allowed on all devices. */ - if (!vlan->port->passthru && is_unicast_ether_addr(addr)) + if (!macvlan_passthru(vlan->port) && is_unicast_ether_addr(addr)) return -EOPNOTSUPP; if (is_unicast_ether_addr(addr)) @@ -1120,8 +1165,8 @@ static int macvlan_port_create(struct net_device *dev) if (port == NULL) return -ENOMEM; - port->passthru = false; port->dev = dev; + ether_addr_copy(port->perm_addr, dev->dev_addr); INIT_LIST_HEAD(&port->vlans); for (i = 0; i < MACVLAN_HASH_SIZE; i++) INIT_HLIST_HEAD(&port->vlan_hash[i]); @@ -1161,6 +1206,18 @@ static void macvlan_port_destroy(struct net_device *dev) kfree_skb(skb); } + /* If the lower device address has been changed by passthru + * macvlan, put it back. + */ + if (macvlan_passthru(port) && + !ether_addr_equal(port->dev->dev_addr, port->perm_addr)) { + struct sockaddr sa; + + sa.sa_family = port->dev->type; + memcpy(&sa.sa_data, port->perm_addr, port->dev->addr_len); + dev_set_mac_address(port->dev, &sa); + } + kfree(port); } @@ -1326,7 +1383,7 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev, port = macvlan_port_get_rtnl(lowerdev); /* Only 1 macvlan device can be created in passthru mode */ - if (port->passthru) { + if (macvlan_passthru(port)) { /* The macvlan port must be not created this time, * still goto destroy_macvlan_port for readability. */ @@ -1352,7 +1409,7 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev, err = -EINVAL; goto destroy_macvlan_port; } - port->passthru = true; + macvlan_set_passthru(port); eth_hw_addr_inherit(dev, lowerdev); } @@ -1434,7 +1491,7 @@ static int macvlan_changelink(struct net_device *dev, if (data && data[IFLA_MACVLAN_FLAGS]) { __u16 flags = nla_get_u16(data[IFLA_MACVLAN_FLAGS]); bool promisc = (flags ^ vlan->flags) & MACVLAN_FLAG_NOPROMISC; - if (vlan->port->passthru && promisc) { + if (macvlan_passthru(vlan->port) && promisc) { int err; if (flags & MACVLAN_FLAG_NOPROMISC) @@ -1597,7 +1654,7 @@ static int macvlan_device_event(struct notifier_block *unused, } break; case NETDEV_CHANGEADDR: - if (!port->passthru) + if (!macvlan_passthru(port)) return NOTIFY_DONE; vlan = list_first_entry_or_null(&port->vlans, diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index ed0d10f54f26..c3065236ffcc 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -908,7 +908,7 @@ static void decode_txts(struct dp83640_private *dp83640, if (overflow) { pr_debug("tx timestamp queue overflow, count %d\n", overflow); while (skb) { - skb_complete_tx_timestamp(skb, NULL); + kfree_skb(skb); skb = skb_dequeue(&dp83640->tx_queue); } return; diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index b9252b8d81ff..8b2038844ba9 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -619,6 +619,8 @@ static int ksz9031_read_status(struct phy_device *phydev) if ((regval & 0xFF) == 0xFF) { phy_init_hw(phydev); phydev->link = 0; + if (phydev->drv->config_intr && phy_interrupt_is_valid(phydev)) + phydev->drv->config_intr(phydev); } return 0; diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index 51cf60092a18..4037ab27734a 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -1722,6 +1722,18 @@ static const struct driver_info lenovo_info = { .tx_fixup = ax88179_tx_fixup, }; +static const struct driver_info belkin_info = { + .description = "Belkin USB Ethernet Adapter", + .bind = ax88179_bind, + .unbind = ax88179_unbind, + .status = ax88179_status, + .link_reset = ax88179_link_reset, + .reset = ax88179_reset, + .flags = FLAG_ETHER | FLAG_FRAMING_AX, + .rx_fixup = ax88179_rx_fixup, + .tx_fixup = ax88179_tx_fixup, +}; + static const struct usb_device_id products[] = { { /* ASIX AX88179 10/100/1000 */ @@ -1751,6 +1763,10 @@ static const struct usb_device_id products[] = { /* Lenovo OneLinkDock Gigabit LAN */ USB_DEVICE(0x17ef, 0x304b), .driver_info = (unsigned long)&lenovo_info, +}, { + /* Belkin B2B128 USB 3.0 Hub + Gigabit Ethernet Adapter */ + USB_DEVICE(0x050d, 0x0128), + .driver_info = (unsigned long)&belkin_info, }, { }, }; diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 0156fe8cac17..364fa9d11d1a 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -383,7 +383,7 @@ static int veth_newlink(struct net *src_net, struct net_device *dev, tbp = tb; } - if (tbp[IFLA_IFNAME]) { + if (ifmp && tbp[IFLA_IFNAME]) { nla_strlcpy(ifname, tbp[IFLA_IFNAME], IFNAMSIZ); name_assign_type = NET_NAME_USER; } else { @@ -402,7 +402,7 @@ static int veth_newlink(struct net *src_net, struct net_device *dev, return PTR_ERR(peer); } - if (tbp[IFLA_ADDRESS] == NULL) + if (!ifmp || !tbp[IFLA_ADDRESS]) eth_hw_addr_random(peer); if (ifmp && (dev->ifindex != 0)) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index a871f45ecc79..143d8a95a60d 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1797,6 +1797,7 @@ static void virtnet_freeze_down(struct virtio_device *vdev) flush_work(&vi->config_work); netif_device_detach(vi->dev); + netif_tx_disable(vi->dev); cancel_delayed_work_sync(&vi->refill); if (netif_running(vi->dev)) { diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c index c7c1e9906500..d231042f19d6 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c @@ -442,7 +442,7 @@ struct brcmf_fw { const char *nvram_name; u16 domain_nr; u16 bus_nr; - void (*done)(struct device *dev, const struct firmware *fw, + void (*done)(struct device *dev, int err, const struct firmware *fw, void *nvram_image, u32 nvram_len); }; @@ -477,52 +477,51 @@ static void brcmf_fw_request_nvram_done(const struct firmware *fw, void *ctx) if (!nvram && !(fwctx->flags & BRCMF_FW_REQ_NV_OPTIONAL)) goto fail; - fwctx->done(fwctx->dev, fwctx->code, nvram, nvram_length); + fwctx->done(fwctx->dev, 0, fwctx->code, nvram, nvram_length); kfree(fwctx); return; fail: brcmf_dbg(TRACE, "failed: dev=%s\n", dev_name(fwctx->dev)); release_firmware(fwctx->code); - device_release_driver(fwctx->dev); + fwctx->done(fwctx->dev, -ENOENT, NULL, NULL, 0); kfree(fwctx); } static void brcmf_fw_request_code_done(const struct firmware *fw, void *ctx) { struct brcmf_fw *fwctx = ctx; - int ret; + int ret = 0; brcmf_dbg(TRACE, "enter: dev=%s\n", dev_name(fwctx->dev)); - if (!fw) + if (!fw) { + ret = -ENOENT; goto fail; - - /* only requested code so done here */ - if (!(fwctx->flags & BRCMF_FW_REQUEST_NVRAM)) { - fwctx->done(fwctx->dev, fw, NULL, 0); - kfree(fwctx); - return; } + /* only requested code so done here */ + if (!(fwctx->flags & BRCMF_FW_REQUEST_NVRAM)) + goto done; + fwctx->code = fw; ret = request_firmware_nowait(THIS_MODULE, true, fwctx->nvram_name, fwctx->dev, GFP_KERNEL, fwctx, brcmf_fw_request_nvram_done); - if (!ret) - return; - - brcmf_fw_request_nvram_done(NULL, fwctx); + /* pass NULL to nvram callback for bcm47xx fallback */ + if (ret) + brcmf_fw_request_nvram_done(NULL, fwctx); return; fail: brcmf_dbg(TRACE, "failed: dev=%s\n", dev_name(fwctx->dev)); - device_release_driver(fwctx->dev); +done: + fwctx->done(fwctx->dev, ret, fw, NULL, 0); kfree(fwctx); } int brcmf_fw_get_firmwares_pcie(struct device *dev, u16 flags, const char *code, const char *nvram, - void (*fw_cb)(struct device *dev, + void (*fw_cb)(struct device *dev, int err, const struct firmware *fw, void *nvram_image, u32 nvram_len), u16 domain_nr, u16 bus_nr) @@ -555,7 +554,7 @@ int brcmf_fw_get_firmwares_pcie(struct device *dev, u16 flags, int brcmf_fw_get_firmwares(struct device *dev, u16 flags, const char *code, const char *nvram, - void (*fw_cb)(struct device *dev, + void (*fw_cb)(struct device *dev, int err, const struct firmware *fw, void *nvram_image, u32 nvram_len)) { diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.h index d3c9f0d52ae3..8fa4b7e1ab3d 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.h @@ -73,13 +73,13 @@ void brcmf_fw_nvram_free(void *nvram); */ int brcmf_fw_get_firmwares_pcie(struct device *dev, u16 flags, const char *code, const char *nvram, - void (*fw_cb)(struct device *dev, + void (*fw_cb)(struct device *dev, int err, const struct firmware *fw, void *nvram_image, u32 nvram_len), u16 domain_nr, u16 bus_nr); int brcmf_fw_get_firmwares(struct device *dev, u16 flags, const char *code, const char *nvram, - void (*fw_cb)(struct device *dev, + void (*fw_cb)(struct device *dev, int err, const struct firmware *fw, void *nvram_image, u32 nvram_len)); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c index 72373e59308e..f59642b2c935 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c @@ -2145,7 +2145,7 @@ void brcmf_fws_add_interface(struct brcmf_if *ifp) struct brcmf_fws_info *fws = drvr_to_fws(ifp->drvr); struct brcmf_fws_mac_descriptor *entry; - if (!ifp->ndev || fws->fcmode == BRCMF_FWS_FCMODE_NONE) + if (!ifp->ndev || !brcmf_fws_queue_skbs(fws)) return; entry = &fws->desc.iface[ifp->ifidx]; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c index f36b96dc6acd..f878706613e6 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c @@ -1650,16 +1650,23 @@ static const struct brcmf_buscore_ops brcmf_pcie_buscore_ops = { .write32 = brcmf_pcie_buscore_write32, }; -static void brcmf_pcie_setup(struct device *dev, const struct firmware *fw, +static void brcmf_pcie_setup(struct device *dev, int ret, + const struct firmware *fw, void *nvram, u32 nvram_len) { - struct brcmf_bus *bus = dev_get_drvdata(dev); - struct brcmf_pciedev *pcie_bus_dev = bus->bus_priv.pcie; - struct brcmf_pciedev_info *devinfo = pcie_bus_dev->devinfo; + struct brcmf_bus *bus; + struct brcmf_pciedev *pcie_bus_dev; + struct brcmf_pciedev_info *devinfo; struct brcmf_commonring **flowrings; - int ret; u32 i; + /* check firmware loading result */ + if (ret) + goto fail; + + bus = dev_get_drvdata(dev); + pcie_bus_dev = bus->bus_priv.pcie; + devinfo = pcie_bus_dev->devinfo; brcmf_pcie_attach(devinfo); /* Some of the firmwares have the size of the memory of the device diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c index e03450059b06..5653d6dd38f6 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c @@ -3982,21 +3982,26 @@ static const struct brcmf_bus_ops brcmf_sdio_bus_ops = { .get_memdump = brcmf_sdio_bus_get_memdump, }; -static void brcmf_sdio_firmware_callback(struct device *dev, +static void brcmf_sdio_firmware_callback(struct device *dev, int err, const struct firmware *code, void *nvram, u32 nvram_len) { - struct brcmf_bus *bus_if = dev_get_drvdata(dev); - struct brcmf_sdio_dev *sdiodev = bus_if->bus_priv.sdio; - struct brcmf_sdio *bus = sdiodev->bus; - int err = 0; + struct brcmf_bus *bus_if; + struct brcmf_sdio_dev *sdiodev; + struct brcmf_sdio *bus; u8 saveclk; - brcmf_dbg(TRACE, "Enter: dev=%s\n", dev_name(dev)); + brcmf_dbg(TRACE, "Enter: dev=%s, err=%d\n", dev_name(dev), err); + bus_if = dev_get_drvdata(dev); + sdiodev = bus_if->bus_priv.sdio; + if (err) + goto fail; if (!bus_if->drvr) return; + bus = sdiodev->bus; + /* try to download image and nvram to the dongle */ bus->alp_only = true; err = brcmf_sdio_download_firmware(bus, code, nvram, nvram_len); @@ -4083,6 +4088,7 @@ release: fail: brcmf_dbg(TRACE, "failed: dev=%s, err=%d\n", dev_name(dev), err); device_release_driver(dev); + device_release_driver(&sdiodev->func[2]->dev); } struct brcmf_sdio *brcmf_sdio_probe(struct brcmf_sdio_dev *sdiodev) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c index e4d545f9edee..0eea48e73331 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c @@ -1159,17 +1159,18 @@ fail: return ret; } -static void brcmf_usb_probe_phase2(struct device *dev, +static void brcmf_usb_probe_phase2(struct device *dev, int ret, const struct firmware *fw, void *nvram, u32 nvlen) { struct brcmf_bus *bus = dev_get_drvdata(dev); - struct brcmf_usbdev_info *devinfo; - int ret; + struct brcmf_usbdev_info *devinfo = bus->bus_priv.usb->devinfo; + + if (ret) + goto error; brcmf_dbg(USB, "Start fw downloading\n"); - devinfo = bus->bus_priv.usb->devinfo; ret = check_file(fw->data); if (ret < 0) { brcmf_err("invalid firmware\n"); diff --git a/drivers/net/wireless/cisco/airo.c b/drivers/net/wireless/cisco/airo.c index 1b7e125a28e2..6a13303af2b7 100644 --- a/drivers/net/wireless/cisco/airo.c +++ b/drivers/net/wireless/cisco/airo.c @@ -3066,7 +3066,7 @@ static int airo_thread(void *data) { if (ai->jobs) { locked = down_interruptible(&ai->sem); } else { - wait_queue_t wait; + wait_queue_entry_t wait; init_waitqueue_entry(&wait, current); add_wait_queue(&ai->thr_wait, &wait); diff --git a/drivers/net/wireless/intersil/hostap/hostap_ioctl.c b/drivers/net/wireless/intersil/hostap/hostap_ioctl.c index b2c6b065b542..ff153ce29539 100644 --- a/drivers/net/wireless/intersil/hostap/hostap_ioctl.c +++ b/drivers/net/wireless/intersil/hostap/hostap_ioctl.c @@ -2544,7 +2544,7 @@ static int prism2_ioctl_priv_prism2_param(struct net_device *dev, ret = -EINVAL; } if (local->iw_mode == IW_MODE_MASTER) { - wait_queue_t __wait; + wait_queue_entry_t __wait; init_waitqueue_entry(&__wait, current); add_wait_queue(&local->hostscan_wq, &__wait); set_current_state(TASK_INTERRUPTIBLE); diff --git a/drivers/net/wireless/marvell/libertas/main.c b/drivers/net/wireless/marvell/libertas/main.c index e3500203715c..dde065d0d5c1 100644 --- a/drivers/net/wireless/marvell/libertas/main.c +++ b/drivers/net/wireless/marvell/libertas/main.c @@ -453,7 +453,7 @@ static int lbs_thread(void *data) { struct net_device *dev = data; struct lbs_private *priv = dev->ml_priv; - wait_queue_t wait; + wait_queue_entry_t wait; lbs_deb_enter(LBS_DEB_THREAD); diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h index 530586be05b4..5b1d2e8402d9 100644 --- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -199,6 +199,7 @@ struct xenvif_queue { /* Per-queue data for xenvif */ unsigned long remaining_credit; struct timer_list credit_timeout; u64 credit_window_start; + bool rate_limited; /* Statistics */ struct xenvif_stats stats; diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 8397f6c92451..e322a862ddfe 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -106,7 +106,11 @@ static int xenvif_poll(struct napi_struct *napi, int budget) if (work_done < budget) { napi_complete_done(napi, work_done); - xenvif_napi_schedule_or_enable_events(queue); + /* If the queue is rate-limited, it shall be + * rescheduled in the timer callback. + */ + if (likely(!queue->rate_limited)) + xenvif_napi_schedule_or_enable_events(queue); } return work_done; diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 602d408fa25e..5042ff8d449a 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -180,6 +180,7 @@ static void tx_add_credit(struct xenvif_queue *queue) max_credit = ULONG_MAX; /* wrapped: clamp to ULONG_MAX */ queue->remaining_credit = min(max_credit, max_burst); + queue->rate_limited = false; } void xenvif_tx_credit_callback(unsigned long data) @@ -686,8 +687,10 @@ static bool tx_credit_exceeded(struct xenvif_queue *queue, unsigned size) msecs_to_jiffies(queue->credit_usec / 1000); /* Timer could already be pending in rare cases. */ - if (timer_pending(&queue->credit_timeout)) + if (timer_pending(&queue->credit_timeout)) { + queue->rate_limited = true; return true; + } /* Passed the point where we can replenish credit? */ if (time_after_eq64(now, next_credit)) { @@ -702,6 +705,7 @@ static bool tx_credit_exceeded(struct xenvif_queue *queue, unsigned size) mod_timer(&queue->credit_timeout, next_credit); queue->credit_window_start = next_credit; + queue->rate_limited = true; return true; } diff --git a/drivers/ntb/hw/intel/ntb_hw_intel.c b/drivers/ntb/hw/intel/ntb_hw_intel.c index c00238491673..7b3b6fd63d7d 100644 --- a/drivers/ntb/hw/intel/ntb_hw_intel.c +++ b/drivers/ntb/hw/intel/ntb_hw_intel.c @@ -2878,7 +2878,7 @@ static const struct intel_ntb_reg skx_reg = { .link_is_up = xeon_link_is_up, .db_ioread = skx_db_ioread, .db_iowrite = skx_db_iowrite, - .db_size = sizeof(u64), + .db_size = sizeof(u32), .ntb_ctl = SKX_NTBCNTL_OFFSET, .mw_bar = {2, 4}, }; diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c index 02ca45fdd892..10e5bf460139 100644 --- a/drivers/ntb/ntb_transport.c +++ b/drivers/ntb/ntb_transport.c @@ -177,14 +177,12 @@ struct ntb_transport_qp { u64 rx_err_ver; u64 rx_memcpy; u64 rx_async; - u64 dma_rx_prep_err; u64 tx_bytes; u64 tx_pkts; u64 tx_ring_full; u64 tx_err_no_buf; u64 tx_memcpy; u64 tx_async; - u64 dma_tx_prep_err; }; struct ntb_transport_mw { @@ -254,8 +252,6 @@ enum { #define QP_TO_MW(nt, qp) ((qp) % nt->mw_count) #define NTB_QP_DEF_NUM_ENTRIES 100 #define NTB_LINK_DOWN_TIMEOUT 10 -#define DMA_RETRIES 20 -#define DMA_OUT_RESOURCE_TO msecs_to_jiffies(50) static void ntb_transport_rxc_db(unsigned long data); static const struct ntb_ctx_ops ntb_transport_ops; @@ -516,12 +512,6 @@ static ssize_t debugfs_read(struct file *filp, char __user *ubuf, size_t count, out_offset += snprintf(buf + out_offset, out_count - out_offset, "free tx - \t%u\n", ntb_transport_tx_free_entry(qp)); - out_offset += snprintf(buf + out_offset, out_count - out_offset, - "DMA tx prep err - \t%llu\n", - qp->dma_tx_prep_err); - out_offset += snprintf(buf + out_offset, out_count - out_offset, - "DMA rx prep err - \t%llu\n", - qp->dma_rx_prep_err); out_offset += snprintf(buf + out_offset, out_count - out_offset, "\n"); @@ -623,7 +613,7 @@ static int ntb_transport_setup_qp_mw(struct ntb_transport_ctx *nt, if (!mw->virt_addr) return -ENOMEM; - if (qp_count % mw_count && mw_num + 1 < qp_count / mw_count) + if (mw_num < qp_count % mw_count) num_qps_mw = qp_count / mw_count + 1; else num_qps_mw = qp_count / mw_count; @@ -768,8 +758,6 @@ static void ntb_qp_link_down_reset(struct ntb_transport_qp *qp) qp->tx_err_no_buf = 0; qp->tx_memcpy = 0; qp->tx_async = 0; - qp->dma_tx_prep_err = 0; - qp->dma_rx_prep_err = 0; } static void ntb_qp_link_cleanup(struct ntb_transport_qp *qp) @@ -1000,7 +988,7 @@ static int ntb_transport_init_queue(struct ntb_transport_ctx *nt, qp->event_handler = NULL; ntb_qp_link_down_reset(qp); - if (qp_count % mw_count && mw_num + 1 < qp_count / mw_count) + if (mw_num < qp_count % mw_count) num_qps_mw = qp_count / mw_count + 1; else num_qps_mw = qp_count / mw_count; @@ -1128,8 +1116,8 @@ static int ntb_transport_probe(struct ntb_client *self, struct ntb_dev *ndev) qp_count = ilog2(qp_bitmap); if (max_num_clients && max_num_clients < qp_count) qp_count = max_num_clients; - else if (mw_count < qp_count) - qp_count = mw_count; + else if (nt->mw_count < qp_count) + qp_count = nt->mw_count; qp_bitmap &= BIT_ULL(qp_count) - 1; @@ -1317,7 +1305,6 @@ static int ntb_async_rx_submit(struct ntb_queue_entry *entry, void *offset) struct dmaengine_unmap_data *unmap; dma_cookie_t cookie; void *buf = entry->buf; - int retries = 0; len = entry->len; device = chan->device; @@ -1346,22 +1333,11 @@ static int ntb_async_rx_submit(struct ntb_queue_entry *entry, void *offset) unmap->from_cnt = 1; - for (retries = 0; retries < DMA_RETRIES; retries++) { - txd = device->device_prep_dma_memcpy(chan, - unmap->addr[1], - unmap->addr[0], len, - DMA_PREP_INTERRUPT); - if (txd) - break; - - set_current_state(TASK_INTERRUPTIBLE); - schedule_timeout(DMA_OUT_RESOURCE_TO); - } - - if (!txd) { - qp->dma_rx_prep_err++; + txd = device->device_prep_dma_memcpy(chan, unmap->addr[1], + unmap->addr[0], len, + DMA_PREP_INTERRUPT); + if (!txd) goto err_get_unmap; - } txd->callback_result = ntb_rx_copy_callback; txd->callback_param = entry; @@ -1606,7 +1582,6 @@ static int ntb_async_tx_submit(struct ntb_transport_qp *qp, struct dmaengine_unmap_data *unmap; dma_addr_t dest; dma_cookie_t cookie; - int retries = 0; device = chan->device; dest = qp->tx_mw_phys + qp->tx_max_frame * entry->tx_index; @@ -1628,21 +1603,10 @@ static int ntb_async_tx_submit(struct ntb_transport_qp *qp, unmap->to_cnt = 1; - for (retries = 0; retries < DMA_RETRIES; retries++) { - txd = device->device_prep_dma_memcpy(chan, dest, - unmap->addr[0], len, - DMA_PREP_INTERRUPT); - if (txd) - break; - - set_current_state(TASK_INTERRUPTIBLE); - schedule_timeout(DMA_OUT_RESOURCE_TO); - } - - if (!txd) { - qp->dma_tx_prep_err++; + txd = device->device_prep_dma_memcpy(chan, dest, unmap->addr[0], len, + DMA_PREP_INTERRUPT); + if (!txd) goto err_get_unmap; - } txd->callback_result = ntb_tx_copy_callback; txd->callback_param = entry; diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c index 434e1d474f33..5cab2831ce99 100644 --- a/drivers/ntb/test/ntb_perf.c +++ b/drivers/ntb/test/ntb_perf.c @@ -90,11 +90,11 @@ MODULE_PARM_DESC(max_mw_size, "Limit size of large memory windows"); static unsigned int seg_order = 19; /* 512K */ module_param(seg_order, uint, 0644); -MODULE_PARM_DESC(seg_order, "size order [n^2] of buffer segment for testing"); +MODULE_PARM_DESC(seg_order, "size order [2^n] of buffer segment for testing"); static unsigned int run_order = 32; /* 4G */ module_param(run_order, uint, 0644); -MODULE_PARM_DESC(run_order, "size order [n^2] of total data to transfer"); +MODULE_PARM_DESC(run_order, "size order [2^n] of total data to transfer"); static bool use_dma; /* default to 0 */ module_param(use_dma, bool, 0644); diff --git a/drivers/nubus/nubus.c b/drivers/nubus/nubus.c index 77a48a5164ff..df431e8a0631 100644 --- a/drivers/nubus/nubus.c +++ b/drivers/nubus/nubus.c @@ -13,7 +13,6 @@ #include <linux/nubus.h> #include <linux/errno.h> #include <linux/init.h> -#include <linux/delay.h> #include <linux/module.h> #include <linux/slab.h> #include <asm/setup.h> @@ -34,14 +33,6 @@ extern void oss_nubus_init(void); #define NUBUS_TEST_PATTERN 0x5A932BC7 -/* Define this if you like to live dangerously - it is known not to - work on pretty much every machine except the Quadra 630 and the LC - III. */ -#undef I_WANT_TO_PROBE_SLOT_ZERO - -/* This sometimes helps combat failure to boot */ -#undef TRY_TO_DODGE_WSOD - /* Globals */ struct nubus_dev *nubus_devices; @@ -101,9 +92,6 @@ static void nubus_rewind(unsigned char **ptr, int len, int map) { unsigned char *p = *ptr; - /* Sanity check */ - if (len > 65536) - pr_err("rewind of 0x%08x!\n", len); while (len) { do { p--; @@ -117,8 +105,6 @@ static void nubus_advance(unsigned char **ptr, int len, int map) { unsigned char *p = *ptr; - if (len > 65536) - pr_err("advance of 0x%08x!\n", len); while (len) { while (not_useful(p, map)) p++; @@ -130,10 +116,15 @@ static void nubus_advance(unsigned char **ptr, int len, int map) static void nubus_move(unsigned char **ptr, int len, int map) { + unsigned long slot_space = (unsigned long)*ptr & 0xFF000000; + if (len > 0) nubus_advance(ptr, len, map); else if (len < 0) nubus_rewind(ptr, -len, map); + + if (((unsigned long)*ptr & 0xFF000000) != slot_space) + pr_err("%s: moved out of slot address space!\n", __func__); } /* Now, functions to read the sResource tree */ @@ -454,10 +445,6 @@ nubus_get_functional_resource(struct nubus_board *board, int slot, pr_info(" Function 0x%02x:\n", parent->type); nubus_get_subdir(parent, &dir); - /* Apple seems to have botched the ROM on the IIx */ - if (slot == 0 && (unsigned long)dir.base % 2) - dir.base += 1; - pr_debug("%s: parent is 0x%p, dir is 0x%p\n", __func__, parent->base, dir.base); @@ -691,83 +678,6 @@ static int __init nubus_get_board_resource(struct nubus_board *board, int slot, return 0; } -/* Attempt to bypass the somewhat non-obvious arrangement of - sResources in the motherboard ROM */ -static void __init nubus_find_rom_dir(struct nubus_board* board) -{ - unsigned char *rp; - unsigned char *romdir; - struct nubus_dir dir; - struct nubus_dirent ent; - - /* Check for the extra directory just under the format block */ - rp = board->fblock; - nubus_rewind(&rp, 4, board->lanes); - if (nubus_get_rom(&rp, 4, board->lanes) != NUBUS_TEST_PATTERN) { - /* OK, the ROM was telling the truth */ - board->directory = board->fblock; - nubus_move(&board->directory, - nubus_expand32(board->doffset), - board->lanes); - return; - } - - /* On "slot zero", you have to walk down a few more - directories to get to the equivalent of a real card's root - directory. We don't know what they were smoking when they - came up with this. */ - romdir = nubus_rom_addr(board->slot); - nubus_rewind(&romdir, ROM_DIR_OFFSET, board->lanes); - dir.base = dir.ptr = romdir; - dir.done = 0; - dir.mask = board->lanes; - - /* This one points to an "Unknown Macintosh" directory */ - if (nubus_readdir(&dir, &ent) == -1) - goto badrom; - - if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG) - printk(KERN_INFO "nubus_get_rom_dir: entry %02x %06x\n", ent.type, ent.data); - /* This one takes us to where we want to go. */ - if (nubus_readdir(&dir, &ent) == -1) - goto badrom; - if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG) - printk(KERN_DEBUG "nubus_get_rom_dir: entry %02x %06x\n", ent.type, ent.data); - nubus_get_subdir(&ent, &dir); - - /* Resource ID 01, also an "Unknown Macintosh" */ - if (nubus_readdir(&dir, &ent) == -1) - goto badrom; - if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG) - printk(KERN_DEBUG "nubus_get_rom_dir: entry %02x %06x\n", ent.type, ent.data); - - /* FIXME: the first one is *not* always the right one. We - suspect this has something to do with the ROM revision. - "The HORROR ROM" (LC-series) uses 0x7e, while "The HORROR - Continues" (Q630) uses 0x7b. The DAFB Macs evidently use - something else. Please run "Slots" on your Mac (see - include/linux/nubus.h for where to get this program) and - tell us where the 'SiDirPtr' for Slot 0 is. If you feel - brave, you should also use MacsBug to walk down the ROM - directories like this function does and try to find the - path to that address... */ - if (nubus_readdir(&dir, &ent) == -1) - goto badrom; - if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG) - printk(KERN_DEBUG "nubus_get_rom_dir: entry %02x %06x\n", ent.type, ent.data); - - /* Bwahahahaha... */ - nubus_get_subdir(&ent, &dir); - board->directory = dir.base; - return; - - /* Even more evil laughter... */ - badrom: - board->directory = board->fblock; - nubus_move(&board->directory, nubus_expand32(board->doffset), board->lanes); - printk(KERN_ERR "nubus_get_rom_dir: ROM weirdness! Notify the developers...\n"); -} - /* Add a board (might be many devices) to the list */ static struct nubus_board * __init nubus_add_board(int slot, int bytelanes) { @@ -828,8 +738,11 @@ static struct nubus_board * __init nubus_add_board(int slot, int bytelanes) * since the initial Macintosh ROM releases skipped the check. */ - /* Attempt to work around slot zero weirdness */ - nubus_find_rom_dir(board); + /* Set up the directory pointer */ + board->directory = board->fblock; + nubus_move(&board->directory, nubus_expand32(board->doffset), + board->lanes); + nubus_get_root_dir(board, &dir); /* We're ready to rock */ @@ -849,9 +762,6 @@ static struct nubus_board * __init nubus_add_board(int slot, int bytelanes) nubus_get_board_resource(board, slot, &ent); } - /* Aaaarrrrgghh! The LC III motherboard has *two* board - resources. I have no idea WTF to do about this. */ - while (nubus_readdir(&dir, &ent) != -1) { struct nubus_dev *dev; struct nubus_dev **devp; @@ -898,8 +808,6 @@ void __init nubus_probe_slot(int slot) continue; dp = *rp; - if(dp == 0) - continue; /* The last byte of the format block consists of two nybbles which are "mirror images" of each other. @@ -908,7 +816,7 @@ void __init nubus_probe_slot(int slot) continue; /* Check that this value is actually *on* one of the bytelanes it claims are valid! */ - if ((dp & 0x0F) >= (1 << i)) + if (not_useful(rp, dp)) continue; /* Looks promising. Let's put it on the list. */ @@ -922,10 +830,6 @@ void __init nubus_scan_bus(void) { int slot; - /* This might not work on your machine */ -#ifdef I_WANT_TO_PROBE_SLOT_ZERO - nubus_probe_slot(0); -#endif for (slot = 9; slot < 15; slot++) { nubus_probe_slot(slot); } @@ -943,13 +847,6 @@ static int __init nubus_init(void) via_nubus_init(); } -#ifdef TRY_TO_DODGE_WSOD - /* Rogue Ethernet interrupts can kill the machine if we don't - do this. Obviously this is bogus. Hopefully the local VIA - gurus can fix the real cause of the problem. */ - mdelay(1000); -#endif - /* And probe */ pr_info("NuBus: Scanning NuBus slots.\n"); nubus_devices = NULL; diff --git a/drivers/nvdimm/blk.c b/drivers/nvdimm/blk.c index 822198a75e96..f12d23c49771 100644 --- a/drivers/nvdimm/blk.c +++ b/drivers/nvdimm/blk.c @@ -186,7 +186,7 @@ static blk_qc_t nd_blk_make_request(struct request_queue *q, struct bio *bio) * another kernel subsystem, and we just pass it through. */ if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) { - bio->bi_error = -EIO; + bio->bi_status = BLK_STS_IOERR; goto out; } @@ -205,7 +205,7 @@ static blk_qc_t nd_blk_make_request(struct request_queue *q, struct bio *bio) "io error in %s sector %lld, len %d,\n", (rw == READ) ? "READ" : "WRITE", (unsigned long long) iter.bi_sector, len); - bio->bi_error = err; + bio->bi_status = errno_to_blk_status(err); break; } } @@ -273,7 +273,6 @@ static int nsblk_attach_disk(struct nd_namespace_blk *nsblk) blk_queue_make_request(q, nd_blk_make_request); blk_queue_max_hw_sectors(q, UINT_MAX); - blk_queue_bounce_limit(q, BLK_BOUNCE_ANY); blk_queue_logical_block_size(q, nsblk_sector_size(nsblk)); queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q); q->queuedata = nsblk; diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c index 983718b8fd9b..b6ba0618ea46 100644 --- a/drivers/nvdimm/btt.c +++ b/drivers/nvdimm/btt.c @@ -1210,7 +1210,7 @@ static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio) * another kernel subsystem, and we just pass it through. */ if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) { - bio->bi_error = -EIO; + bio->bi_status = BLK_STS_IOERR; goto out; } @@ -1232,7 +1232,7 @@ static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio) (op_is_write(bio_op(bio))) ? "WRITE" : "READ", (unsigned long long) iter.bi_sector, len); - bio->bi_error = err; + bio->bi_status = errno_to_blk_status(err); break; } } @@ -1297,7 +1297,6 @@ static int btt_blk_init(struct btt *btt) blk_queue_make_request(btt->btt_queue, btt_make_request); blk_queue_logical_block_size(btt->btt_queue, btt->sector_size); blk_queue_max_hw_sectors(btt->btt_queue, UINT_MAX); - blk_queue_bounce_limit(btt->btt_queue, BLK_BOUNCE_ANY); queue_flag_set_unlocked(QUEUE_FLAG_NONROT, btt->btt_queue); btt->btt_queue->queuedata = btt; diff --git a/drivers/nvdimm/btt_devs.c b/drivers/nvdimm/btt_devs.c index ae00dc0d9791..4c989bb9a8a0 100644 --- a/drivers/nvdimm/btt_devs.c +++ b/drivers/nvdimm/btt_devs.c @@ -222,13 +222,6 @@ struct device *nd_btt_create(struct nd_region *nd_region) return dev; } -static bool uuid_is_null(u8 *uuid) -{ - static const u8 null_uuid[16]; - - return (memcmp(uuid, null_uuid, 16) == 0); -} - /** * nd_btt_arena_is_valid - check if the metadata layout is valid * @nd_btt: device with BTT geometry and backing device info @@ -249,7 +242,7 @@ bool nd_btt_arena_is_valid(struct nd_btt *nd_btt, struct btt_sb *super) if (memcmp(super->signature, BTT_SIG, BTT_SIG_LEN) != 0) return false; - if (!uuid_is_null(super->parent_uuid)) + if (!guid_is_null((guid_t *)&super->parent_uuid)) if (memcmp(super->parent_uuid, parent_uuid, 16) != 0) return false; diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index c544d466ea51..6b577afb1d44 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -49,19 +49,19 @@ static struct nd_region *to_region(struct pmem_device *pmem) return to_nd_region(to_dev(pmem)->parent); } -static int pmem_clear_poison(struct pmem_device *pmem, phys_addr_t offset, - unsigned int len) +static blk_status_t pmem_clear_poison(struct pmem_device *pmem, + phys_addr_t offset, unsigned int len) { struct device *dev = to_dev(pmem); sector_t sector; long cleared; - int rc = 0; + blk_status_t rc = BLK_STS_OK; sector = (offset - pmem->data_offset) / 512; cleared = nvdimm_clear_poison(dev, pmem->phys_addr + offset, len); if (cleared < len) - rc = -EIO; + rc = BLK_STS_IOERR; if (cleared > 0 && cleared / 512) { cleared /= 512; dev_dbg(dev, "%s: %#llx clear %ld sector%s\n", __func__, @@ -84,7 +84,7 @@ static void write_pmem(void *pmem_addr, struct page *page, kunmap_atomic(mem); } -static int read_pmem(struct page *page, unsigned int off, +static blk_status_t read_pmem(struct page *page, unsigned int off, void *pmem_addr, unsigned int len) { int rc; @@ -93,15 +93,15 @@ static int read_pmem(struct page *page, unsigned int off, rc = memcpy_mcsafe(mem + off, pmem_addr, len); kunmap_atomic(mem); if (rc) - return -EIO; - return 0; + return BLK_STS_IOERR; + return BLK_STS_OK; } -static int pmem_do_bvec(struct pmem_device *pmem, struct page *page, +static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page, unsigned int len, unsigned int off, bool is_write, sector_t sector) { - int rc = 0; + blk_status_t rc = BLK_STS_OK; bool bad_pmem = false; phys_addr_t pmem_off = sector * 512 + pmem->data_offset; void *pmem_addr = pmem->virt_addr + pmem_off; @@ -111,7 +111,7 @@ static int pmem_do_bvec(struct pmem_device *pmem, struct page *page, if (!is_write) { if (unlikely(bad_pmem)) - rc = -EIO; + rc = BLK_STS_IOERR; else { rc = read_pmem(page, off, pmem_addr, len); flush_dcache_page(page); @@ -149,7 +149,7 @@ static int pmem_do_bvec(struct pmem_device *pmem, struct page *page, static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio) { - int rc = 0; + blk_status_t rc = 0; bool do_acct; unsigned long start; struct bio_vec bvec; @@ -166,7 +166,7 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio) bvec.bv_offset, op_is_write(bio_op(bio)), iter.bi_sector); if (rc) { - bio->bi_error = rc; + bio->bi_status = rc; break; } } @@ -184,7 +184,7 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector, struct page *page, bool is_write) { struct pmem_device *pmem = bdev->bd_queue->queuedata; - int rc; + blk_status_t rc; rc = pmem_do_bvec(pmem, page, PAGE_SIZE, 0, is_write, sector); @@ -197,7 +197,7 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector, if (rc == 0) page_endio(page, is_write, 0); - return rc; + return blk_status_to_errno(rc); } /* see "strong" declaration in tools/testing/nvdimm/pmem-dax.c */ @@ -343,7 +343,6 @@ static int pmem_attach_disk(struct device *dev, blk_queue_make_request(q, pmem_make_request); blk_queue_physical_block_size(q, PAGE_SIZE); blk_queue_max_hw_sectors(q, UINT_MAX); - blk_queue_bounce_limit(q, BLK_BOUNCE_ANY); queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q); queue_flag_set_unlocked(QUEUE_FLAG_DAX, q); q->queuedata = pmem; diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig index 90745a616df7..46d6cb1e03bd 100644 --- a/drivers/nvme/host/Kconfig +++ b/drivers/nvme/host/Kconfig @@ -13,18 +13,6 @@ config BLK_DEV_NVME To compile this driver as a module, choose M here: the module will be called nvme. -config BLK_DEV_NVME_SCSI - bool "SCSI emulation for NVMe device nodes" - depends on NVME_CORE - ---help--- - This adds support for the SG_IO ioctl on the NVMe character - and block devices nodes, as well as a translation for a small - number of selected SCSI commands to NVMe commands to the NVMe - driver. If you don't know what this means you probably want - to say N here, unless you run a distro that abuses the SCSI - emulation to provide stable device names for mount by id, like - some OpenSuSE and SLES versions. - config NVME_FABRICS tristate diff --git a/drivers/nvme/host/Makefile b/drivers/nvme/host/Makefile index f1a7d945fbb6..cc0aacb4c8b4 100644 --- a/drivers/nvme/host/Makefile +++ b/drivers/nvme/host/Makefile @@ -5,7 +5,6 @@ obj-$(CONFIG_NVME_RDMA) += nvme-rdma.o obj-$(CONFIG_NVME_FC) += nvme-fc.o nvme-core-y := core.o -nvme-core-$(CONFIG_BLK_DEV_NVME_SCSI) += scsi.o nvme-core-$(CONFIG_NVM) += lightnvm.o nvme-y += pci.o diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 903d5813023a..d70df1d0072d 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -27,7 +27,6 @@ #include <linux/nvme_ioctl.h> #include <linux/t10-pi.h> #include <linux/pm_qos.h> -#include <scsi/sg.h> #include <asm/unaligned.h> #include "nvme.h" @@ -45,7 +44,7 @@ module_param_named(io_timeout, nvme_io_timeout, byte, 0644); MODULE_PARM_DESC(io_timeout, "timeout in seconds for I/O"); EXPORT_SYMBOL_GPL(nvme_io_timeout); -unsigned char shutdown_timeout = 5; +static unsigned char shutdown_timeout = 5; module_param(shutdown_timeout, byte, 0644); MODULE_PARM_DESC(shutdown_timeout, "timeout in seconds for controller shutdown"); @@ -65,34 +64,53 @@ static bool force_apst; module_param(force_apst, bool, 0644); MODULE_PARM_DESC(force_apst, "allow APST for newly enumerated devices even if quirked off"); +static bool streams; +module_param(streams, bool, 0644); +MODULE_PARM_DESC(streams, "turn on support for Streams write directives"); + +struct workqueue_struct *nvme_wq; +EXPORT_SYMBOL_GPL(nvme_wq); + static LIST_HEAD(nvme_ctrl_list); static DEFINE_SPINLOCK(dev_list_lock); static struct class *nvme_class; -static int nvme_error_status(struct request *req) +int nvme_reset_ctrl(struct nvme_ctrl *ctrl) +{ + if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) + return -EBUSY; + if (!queue_work(nvme_wq, &ctrl->reset_work)) + return -EBUSY; + return 0; +} +EXPORT_SYMBOL_GPL(nvme_reset_ctrl); + +static int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl) +{ + int ret; + + ret = nvme_reset_ctrl(ctrl); + if (!ret) + flush_work(&ctrl->reset_work); + return ret; +} + +static blk_status_t nvme_error_status(struct request *req) { switch (nvme_req(req)->status & 0x7ff) { case NVME_SC_SUCCESS: - return 0; + return BLK_STS_OK; case NVME_SC_CAP_EXCEEDED: - return -ENOSPC; - default: - return -EIO; - - /* - * XXX: these errors are a nasty side-band protocol to - * drivers/md/dm-mpath.c:noretry_error() that aren't documented - * anywhere.. - */ - case NVME_SC_CMD_SEQ_ERROR: - return -EILSEQ; + return BLK_STS_NOSPC; case NVME_SC_ONCS_NOT_SUPPORTED: - return -EOPNOTSUPP; + return BLK_STS_NOTSUPP; case NVME_SC_WRITE_FAULT: case NVME_SC_READ_ERROR: case NVME_SC_UNWRITTEN_BLOCK: - return -ENODATA; + return BLK_STS_MEDIUM; + default: + return BLK_STS_IOERR; } } @@ -165,7 +183,6 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, switch (old_state) { case NVME_CTRL_NEW: case NVME_CTRL_LIVE: - case NVME_CTRL_RECONNECTING: changed = true; /* FALLTHRU */ default: @@ -283,6 +300,105 @@ struct request *nvme_alloc_request(struct request_queue *q, } EXPORT_SYMBOL_GPL(nvme_alloc_request); +static int nvme_toggle_streams(struct nvme_ctrl *ctrl, bool enable) +{ + struct nvme_command c; + + memset(&c, 0, sizeof(c)); + + c.directive.opcode = nvme_admin_directive_send; + c.directive.nsid = cpu_to_le32(0xffffffff); + c.directive.doper = NVME_DIR_SND_ID_OP_ENABLE; + c.directive.dtype = NVME_DIR_IDENTIFY; + c.directive.tdtype = NVME_DIR_STREAMS; + c.directive.endir = enable ? NVME_DIR_ENDIR : 0; + + return nvme_submit_sync_cmd(ctrl->admin_q, &c, NULL, 0); +} + +static int nvme_disable_streams(struct nvme_ctrl *ctrl) +{ + return nvme_toggle_streams(ctrl, false); +} + +static int nvme_enable_streams(struct nvme_ctrl *ctrl) +{ + return nvme_toggle_streams(ctrl, true); +} + +static int nvme_get_stream_params(struct nvme_ctrl *ctrl, + struct streams_directive_params *s, u32 nsid) +{ + struct nvme_command c; + + memset(&c, 0, sizeof(c)); + memset(s, 0, sizeof(*s)); + + c.directive.opcode = nvme_admin_directive_recv; + c.directive.nsid = cpu_to_le32(nsid); + c.directive.numd = sizeof(*s); + c.directive.doper = NVME_DIR_RCV_ST_OP_PARAM; + c.directive.dtype = NVME_DIR_STREAMS; + + return nvme_submit_sync_cmd(ctrl->admin_q, &c, s, sizeof(*s)); +} + +static int nvme_configure_directives(struct nvme_ctrl *ctrl) +{ + struct streams_directive_params s; + int ret; + + if (!(ctrl->oacs & NVME_CTRL_OACS_DIRECTIVES)) + return 0; + if (!streams) + return 0; + + ret = nvme_enable_streams(ctrl); + if (ret) + return ret; + + ret = nvme_get_stream_params(ctrl, &s, 0xffffffff); + if (ret) + return ret; + + ctrl->nssa = le16_to_cpu(s.nssa); + if (ctrl->nssa < BLK_MAX_WRITE_HINTS - 1) { + dev_info(ctrl->device, "too few streams (%u) available\n", + ctrl->nssa); + nvme_disable_streams(ctrl); + return 0; + } + + ctrl->nr_streams = min_t(unsigned, ctrl->nssa, BLK_MAX_WRITE_HINTS - 1); + dev_info(ctrl->device, "Using %u streams\n", ctrl->nr_streams); + return 0; +} + +/* + * Check if 'req' has a write hint associated with it. If it does, assign + * a valid namespace stream to the write. + */ +static void nvme_assign_write_stream(struct nvme_ctrl *ctrl, + struct request *req, u16 *control, + u32 *dsmgmt) +{ + enum rw_hint streamid = req->write_hint; + + if (streamid == WRITE_LIFE_NOT_SET || streamid == WRITE_LIFE_NONE) + streamid = 0; + else { + streamid--; + if (WARN_ON_ONCE(streamid > ctrl->nr_streams)) + return; + + *control |= NVME_RW_DTYPE_STREAMS; + *dsmgmt |= streamid << 16; + } + + if (streamid < ARRAY_SIZE(req->q->write_hints)) + req->q->write_hints[streamid] += blk_rq_bytes(req) >> 9; +} + static inline void nvme_setup_flush(struct nvme_ns *ns, struct nvme_command *cmnd) { @@ -291,7 +407,7 @@ static inline void nvme_setup_flush(struct nvme_ns *ns, cmnd->common.nsid = cpu_to_le32(ns->ns_id); } -static inline int nvme_setup_discard(struct nvme_ns *ns, struct request *req, +static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req, struct nvme_command *cmnd) { unsigned short segments = blk_rq_nr_discard_segments(req), n = 0; @@ -300,7 +416,7 @@ static inline int nvme_setup_discard(struct nvme_ns *ns, struct request *req, range = kmalloc_array(segments, sizeof(*range), GFP_ATOMIC); if (!range) - return BLK_MQ_RQ_QUEUE_BUSY; + return BLK_STS_RESOURCE; __rq_for_each_bio(bio, req) { u64 slba = nvme_block_nr(ns, bio->bi_iter.bi_sector); @@ -314,7 +430,7 @@ static inline int nvme_setup_discard(struct nvme_ns *ns, struct request *req, if (WARN_ON_ONCE(n != segments)) { kfree(range); - return BLK_MQ_RQ_QUEUE_ERROR; + return BLK_STS_IOERR; } memset(cmnd, 0, sizeof(*cmnd)); @@ -328,15 +444,26 @@ static inline int nvme_setup_discard(struct nvme_ns *ns, struct request *req, req->special_vec.bv_len = sizeof(*range) * segments; req->rq_flags |= RQF_SPECIAL_PAYLOAD; - return BLK_MQ_RQ_QUEUE_OK; + return BLK_STS_OK; } -static inline void nvme_setup_rw(struct nvme_ns *ns, struct request *req, - struct nvme_command *cmnd) +static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns, + struct request *req, struct nvme_command *cmnd) { + struct nvme_ctrl *ctrl = ns->ctrl; u16 control = 0; u32 dsmgmt = 0; + /* + * If formated with metadata, require the block layer provide a buffer + * unless this namespace is formated such that the metadata can be + * stripped/generated by the controller with PRACT=1. + */ + if (ns && ns->ms && + (!ns->pi_type || ns->ms != sizeof(struct t10_pi_tuple)) && + !blk_integrity_rq(req) && !blk_rq_is_passthrough(req)) + return BLK_STS_NOTSUPP; + if (req->cmd_flags & REQ_FUA) control |= NVME_RW_FUA; if (req->cmd_flags & (REQ_FAILFAST_DEV | REQ_RAHEAD)) @@ -351,6 +478,9 @@ static inline void nvme_setup_rw(struct nvme_ns *ns, struct request *req, cmnd->rw.slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req))); cmnd->rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1); + if (req_op(req) == REQ_OP_WRITE && ctrl->nr_streams) + nvme_assign_write_stream(ctrl, req, &control, &dsmgmt); + if (ns->ms) { switch (ns->pi_type) { case NVME_NS_DPS_PI_TYPE3: @@ -370,12 +500,13 @@ static inline void nvme_setup_rw(struct nvme_ns *ns, struct request *req, cmnd->rw.control = cpu_to_le16(control); cmnd->rw.dsmgmt = cpu_to_le32(dsmgmt); + return 0; } -int nvme_setup_cmd(struct nvme_ns *ns, struct request *req, +blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req, struct nvme_command *cmd) { - int ret = BLK_MQ_RQ_QUEUE_OK; + blk_status_t ret = BLK_STS_OK; if (!(req->rq_flags & RQF_DONTPREP)) { nvme_req(req)->retries = 0; @@ -398,11 +529,11 @@ int nvme_setup_cmd(struct nvme_ns *ns, struct request *req, break; case REQ_OP_READ: case REQ_OP_WRITE: - nvme_setup_rw(ns, req, cmd); + ret = nvme_setup_rw(ns, req, cmd); break; default: WARN_ON_ONCE(1); - return BLK_MQ_RQ_QUEUE_ERROR; + return BLK_STS_IOERR; } cmd->common.command_id = req->tag; @@ -555,15 +686,16 @@ int nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd, result, timeout); } -static void nvme_keep_alive_end_io(struct request *rq, int error) +static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status) { struct nvme_ctrl *ctrl = rq->end_io_data; blk_mq_free_request(rq); - if (error) { + if (status) { dev_err(ctrl->device, - "failed nvme_keep_alive_end_io error=%d\n", error); + "failed nvme_keep_alive_end_io error=%d\n", + status); return; } @@ -599,7 +731,7 @@ static void nvme_keep_alive_work(struct work_struct *work) if (nvme_keep_alive(ctrl)) { /* allocation failure, reset the controller */ dev_err(ctrl->device, "keep-alive failed\n"); - ctrl->ops->reset_ctrl(ctrl); + nvme_reset_ctrl(ctrl); return; } } @@ -623,7 +755,7 @@ void nvme_stop_keep_alive(struct nvme_ctrl *ctrl) } EXPORT_SYMBOL_GPL(nvme_stop_keep_alive); -int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id) +static int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id) { struct nvme_command c = { }; int error; @@ -643,6 +775,77 @@ int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id) return error; } +static int nvme_identify_ns_descs(struct nvme_ns *ns, unsigned nsid) +{ + struct nvme_command c = { }; + int status; + void *data; + int pos; + int len; + + c.identify.opcode = nvme_admin_identify; + c.identify.nsid = cpu_to_le32(nsid); + c.identify.cns = NVME_ID_CNS_NS_DESC_LIST; + + data = kzalloc(NVME_IDENTIFY_DATA_SIZE, GFP_KERNEL); + if (!data) + return -ENOMEM; + + status = nvme_submit_sync_cmd(ns->ctrl->admin_q, &c, data, + NVME_IDENTIFY_DATA_SIZE); + if (status) + goto free_data; + + for (pos = 0; pos < NVME_IDENTIFY_DATA_SIZE; pos += len) { + struct nvme_ns_id_desc *cur = data + pos; + + if (cur->nidl == 0) + break; + + switch (cur->nidt) { + case NVME_NIDT_EUI64: + if (cur->nidl != NVME_NIDT_EUI64_LEN) { + dev_warn(ns->ctrl->device, + "ctrl returned bogus length: %d for NVME_NIDT_EUI64\n", + cur->nidl); + goto free_data; + } + len = NVME_NIDT_EUI64_LEN; + memcpy(ns->eui, data + pos + sizeof(*cur), len); + break; + case NVME_NIDT_NGUID: + if (cur->nidl != NVME_NIDT_NGUID_LEN) { + dev_warn(ns->ctrl->device, + "ctrl returned bogus length: %d for NVME_NIDT_NGUID\n", + cur->nidl); + goto free_data; + } + len = NVME_NIDT_NGUID_LEN; + memcpy(ns->nguid, data + pos + sizeof(*cur), len); + break; + case NVME_NIDT_UUID: + if (cur->nidl != NVME_NIDT_UUID_LEN) { + dev_warn(ns->ctrl->device, + "ctrl returned bogus length: %d for NVME_NIDT_UUID\n", + cur->nidl); + goto free_data; + } + len = NVME_NIDT_UUID_LEN; + uuid_copy(&ns->uuid, data + pos + sizeof(*cur)); + break; + default: + /* Skip unnkown types */ + len = cur->nidl; + break; + } + + len += sizeof(*cur); + } +free_data: + kfree(data); + return status; +} + static int nvme_identify_ns_list(struct nvme_ctrl *dev, unsigned nsid, __le32 *ns_list) { struct nvme_command c = { }; @@ -653,7 +856,7 @@ static int nvme_identify_ns_list(struct nvme_ctrl *dev, unsigned nsid, __le32 *n return nvme_submit_sync_cmd(dev->admin_q, &c, ns_list, 0x1000); } -int nvme_identify_ns(struct nvme_ctrl *dev, unsigned nsid, +static int nvme_identify_ns(struct nvme_ctrl *dev, unsigned nsid, struct nvme_id_ns **id) { struct nvme_command c = { }; @@ -675,26 +878,7 @@ int nvme_identify_ns(struct nvme_ctrl *dev, unsigned nsid, return error; } -int nvme_get_features(struct nvme_ctrl *dev, unsigned fid, unsigned nsid, - void *buffer, size_t buflen, u32 *result) -{ - struct nvme_command c; - union nvme_result res; - int ret; - - memset(&c, 0, sizeof(c)); - c.features.opcode = nvme_admin_get_features; - c.features.nsid = cpu_to_le32(nsid); - c.features.fid = cpu_to_le32(fid); - - ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &res, buffer, buflen, 0, - NVME_QID_ANY, 0, 0); - if (ret >= 0 && result) - *result = le32_to_cpu(res.u32); - return ret; -} - -int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11, +static int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11, void *buffer, size_t buflen, u32 *result) { struct nvme_command c; @@ -713,28 +897,6 @@ int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11, return ret; } -int nvme_get_log_page(struct nvme_ctrl *dev, struct nvme_smart_log **log) -{ - struct nvme_command c = { }; - int error; - - c.common.opcode = nvme_admin_get_log_page, - c.common.nsid = cpu_to_le32(0xFFFFFFFF), - c.common.cdw10[0] = cpu_to_le32( - (((sizeof(struct nvme_smart_log) / 4) - 1) << 16) | - NVME_LOG_SMART), - - *log = kmalloc(sizeof(struct nvme_smart_log), GFP_KERNEL); - if (!*log) - return -ENOMEM; - - error = nvme_submit_sync_cmd(dev->admin_q, &c, *log, - sizeof(struct nvme_smart_log)); - if (error) - kfree(*log); - return error; -} - int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count) { u32 q_count = (*count - 1) | ((*count - 1) << 16); @@ -752,7 +914,7 @@ int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count) * access to the admin queue, as that might be only way to fix them up. */ if (status > 0) { - dev_err(ctrl->dev, "Could not set queue count (%d)\n", status); + dev_err(ctrl->device, "Could not set queue count (%d)\n", status); *count = 0; } else { nr_io_queues = min(result & 0xffff, result >> 16) + 1; @@ -870,12 +1032,6 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode, return nvme_user_cmd(ns->ctrl, ns, (void __user *)arg); case NVME_IOCTL_SUBMIT_IO: return nvme_submit_io(ns, (void __user *)arg); -#ifdef CONFIG_BLK_DEV_NVME_SCSI - case SG_GET_VERSION_NUM: - return nvme_sg_get_version_num((void __user *)arg); - case SG_IO: - return nvme_sg_io(ns, (void __user *)arg); -#endif default: #ifdef CONFIG_NVM if (ns->ndev) @@ -892,10 +1048,6 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode, static int nvme_compat_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { - switch (cmd) { - case SG_IO: - return -ENOIOCTLCMD; - } return nvme_ioctl(bdev, mode, cmd, arg); } #else @@ -983,6 +1135,12 @@ static void nvme_init_integrity(struct nvme_ns *ns) } #endif /* CONFIG_BLK_DEV_INTEGRITY */ +static void nvme_set_chunk_size(struct nvme_ns *ns) +{ + u32 chunk_size = (((u32)ns->noiob) << (ns->lba_shift - 9)); + blk_queue_chunk_sectors(ns->queue, rounddown_pow_of_two(chunk_size)); +} + static void nvme_config_discard(struct nvme_ns *ns) { struct nvme_ctrl *ctrl = ns->ctrl; @@ -991,8 +1149,15 @@ static void nvme_config_discard(struct nvme_ns *ns) BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) < NVME_DSM_MAX_RANGES); - ns->queue->limits.discard_alignment = logical_block_size; - ns->queue->limits.discard_granularity = logical_block_size; + if (ctrl->nr_streams && ns->sws && ns->sgs) { + unsigned int sz = logical_block_size * ns->sws * ns->sgs; + + ns->queue->limits.discard_alignment = sz; + ns->queue->limits.discard_granularity = sz; + } else { + ns->queue->limits.discard_alignment = logical_block_size; + ns->queue->limits.discard_granularity = logical_block_size; + } blk_queue_max_discard_sectors(ns->queue, UINT_MAX); blk_queue_max_discard_segments(ns->queue, NVME_DSM_MAX_RANGES); queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, ns->queue); @@ -1016,7 +1181,15 @@ static int nvme_revalidate_ns(struct nvme_ns *ns, struct nvme_id_ns **id) if (ns->ctrl->vs >= NVME_VS(1, 1, 0)) memcpy(ns->eui, (*id)->eui64, sizeof(ns->eui)); if (ns->ctrl->vs >= NVME_VS(1, 2, 0)) - memcpy(ns->uuid, (*id)->nguid, sizeof(ns->uuid)); + memcpy(ns->nguid, (*id)->nguid, sizeof(ns->nguid)); + if (ns->ctrl->vs >= NVME_VS(1, 3, 0)) { + /* Don't treat error as fatal we potentially + * already have a NGUID or EUI-64 + */ + if (nvme_identify_ns_descs(ns, ns->ns_id)) + dev_warn(ns->ctrl->device, + "%s: Identify Descriptors failed\n", __func__); + } return 0; } @@ -1024,6 +1197,7 @@ static int nvme_revalidate_ns(struct nvme_ns *ns, struct nvme_id_ns **id) static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id) { struct nvme_ns *ns = disk->private_data; + struct nvme_ctrl *ctrl = ns->ctrl; u16 bs; /* @@ -1034,12 +1208,15 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id) if (ns->lba_shift == 0) ns->lba_shift = 9; bs = 1 << ns->lba_shift; + ns->noiob = le16_to_cpu(id->noiob); blk_mq_freeze_queue(disk->queue); - if (ns->ctrl->ops->flags & NVME_F_METADATA_SUPPORTED) + if (ctrl->ops->flags & NVME_F_METADATA_SUPPORTED) nvme_prep_integrity(disk, id, bs); blk_queue_logical_block_size(ns->queue, bs); + if (ns->noiob) + nvme_set_chunk_size(ns); if (ns->ms && !blk_get_integrity(disk) && !ns->ext) nvme_init_integrity(ns); if (ns->ms && !(ns->ms == 8 && ns->pi_type) && !blk_get_integrity(disk)) @@ -1047,7 +1224,7 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id) else set_capacity(disk, le64_to_cpup(&id->nsze) << (ns->lba_shift - 9)); - if (ns->ctrl->oncs & NVME_CTRL_ONCS_DSM) + if (ctrl->oncs & NVME_CTRL_ONCS_DSM) nvme_config_discard(ns); blk_mq_unfreeze_queue(disk->queue); } @@ -1283,7 +1460,7 @@ EXPORT_SYMBOL_GPL(nvme_enable_ctrl); int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl) { - unsigned long timeout = SHUTDOWN_TIMEOUT + jiffies; + unsigned long timeout = jiffies + (shutdown_timeout * HZ); u32 csts; int ret; @@ -1372,7 +1549,7 @@ static void nvme_configure_apst(struct nvme_ctrl *ctrl) if (!table) return; - if (ctrl->ps_max_latency_us == 0) { + if (!ctrl->apst_enabled || ctrl->ps_max_latency_us == 0) { /* Turn off APST. */ apste = 0; dev_dbg(ctrl->device, "APST disabled\n"); @@ -1528,6 +1705,31 @@ static bool quirk_matches(const struct nvme_id_ctrl *id, string_matches(id->fr, q->fr, sizeof(id->fr)); } +static void nvme_init_subnqn(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) +{ + size_t nqnlen; + int off; + + nqnlen = strnlen(id->subnqn, NVMF_NQN_SIZE); + if (nqnlen > 0 && nqnlen < NVMF_NQN_SIZE) { + strcpy(ctrl->subnqn, id->subnqn); + return; + } + + if (ctrl->vs >= NVME_VS(1, 2, 1)) + dev_warn(ctrl->device, "missing or invalid SUBNQN field.\n"); + + /* Generate a "fake" NQN per Figure 254 in NVMe 1.3 + ECN 001 */ + off = snprintf(ctrl->subnqn, NVMF_NQN_SIZE, + "nqn.2014.08.org.nvmexpress:%4x%4x", + le16_to_cpu(id->vid), le16_to_cpu(id->ssvid)); + memcpy(ctrl->subnqn + off, id->sn, sizeof(id->sn)); + off += sizeof(id->sn); + memcpy(ctrl->subnqn + off, id->mn, sizeof(id->mn)); + off += sizeof(id->mn); + memset(ctrl->subnqn + off, 0, sizeof(ctrl->subnqn) - off); +} + /* * Initialize the cached copies of the Identify data and various controller * register in our nvme_ctrl structure. This should be called as soon as @@ -1539,7 +1741,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) u64 cap; int ret, page_shift; u32 max_hw_sectors; - u8 prev_apsta; + bool prev_apst_enabled; ret = ctrl->ops->reg_read32(ctrl, NVME_REG_VS, &ctrl->vs); if (ret) { @@ -1563,6 +1765,8 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) return -EIO; } + nvme_init_subnqn(ctrl, id); + if (!ctrl->identified) { /* * Check for quirks. Quirk can depend on firmware version, @@ -1582,7 +1786,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) } if (force_apst && (ctrl->quirks & NVME_QUIRK_NO_DEEPEST_PS)) { - dev_warn(ctrl->dev, "forcibly allowing all power states due to nvme_core.force_apst -- use at your own risk\n"); + dev_warn(ctrl->device, "forcibly allowing all power states due to nvme_core.force_apst -- use at your own risk\n"); ctrl->quirks &= ~NVME_QUIRK_NO_DEEPEST_PS; } @@ -1607,16 +1811,17 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) ctrl->kas = le16_to_cpu(id->kas); ctrl->npss = id->npss; - prev_apsta = ctrl->apsta; + ctrl->apsta = id->apsta; + prev_apst_enabled = ctrl->apst_enabled; if (ctrl->quirks & NVME_QUIRK_NO_APST) { if (force_apst && id->apsta) { - dev_warn(ctrl->dev, "forcibly allowing APST due to nvme_core.force_apst -- use at your own risk\n"); - ctrl->apsta = 1; + dev_warn(ctrl->device, "forcibly allowing APST due to nvme_core.force_apst -- use at your own risk\n"); + ctrl->apst_enabled = true; } else { - ctrl->apsta = 0; + ctrl->apst_enabled = false; } } else { - ctrl->apsta = id->apsta; + ctrl->apst_enabled = id->apsta; } memcpy(ctrl->psd, id->psd, sizeof(ctrl->psd)); @@ -1634,22 +1839,25 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) ret = -EINVAL; if (!ctrl->opts->discovery_nqn && !ctrl->kas) { - dev_err(ctrl->dev, + dev_err(ctrl->device, "keep-alive support is mandatory for fabrics\n"); ret = -EINVAL; } } else { ctrl->cntlid = le16_to_cpu(id->cntlid); + ctrl->hmpre = le32_to_cpu(id->hmpre); + ctrl->hmmin = le32_to_cpu(id->hmmin); } kfree(id); - if (ctrl->apsta && !prev_apsta) + if (ctrl->apst_enabled && !prev_apst_enabled) dev_pm_qos_expose_latency_tolerance(ctrl->device); - else if (!ctrl->apsta && prev_apsta) + else if (!ctrl->apst_enabled && prev_apst_enabled) dev_pm_qos_hide_latency_tolerance(ctrl->device); nvme_configure_apst(ctrl); + nvme_configure_directives(ctrl); ctrl->identified = true; @@ -1735,7 +1943,7 @@ static long nvme_dev_ioctl(struct file *file, unsigned int cmd, return nvme_dev_user_cmd(ctrl, argp); case NVME_IOCTL_RESET: dev_warn(ctrl->device, "resetting controller\n"); - return ctrl->ops->reset_ctrl(ctrl); + return nvme_reset_ctrl_sync(ctrl); case NVME_IOCTL_SUBSYS_RESET: return nvme_reset_subsystem(ctrl); case NVME_IOCTL_RESCAN: @@ -1761,7 +1969,7 @@ static ssize_t nvme_sysfs_reset(struct device *dev, struct nvme_ctrl *ctrl = dev_get_drvdata(dev); int ret; - ret = ctrl->ops->reset_ctrl(ctrl); + ret = nvme_reset_ctrl_sync(ctrl); if (ret < 0) return ret; return count; @@ -1787,8 +1995,8 @@ static ssize_t wwid_show(struct device *dev, struct device_attribute *attr, int serial_len = sizeof(ctrl->serial); int model_len = sizeof(ctrl->model); - if (memchr_inv(ns->uuid, 0, sizeof(ns->uuid))) - return sprintf(buf, "eui.%16phN\n", ns->uuid); + if (memchr_inv(ns->nguid, 0, sizeof(ns->nguid))) + return sprintf(buf, "eui.%16phN\n", ns->nguid); if (memchr_inv(ns->eui, 0, sizeof(ns->eui))) return sprintf(buf, "eui.%8phN\n", ns->eui); @@ -1803,11 +2011,28 @@ static ssize_t wwid_show(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR(wwid, S_IRUGO, wwid_show, NULL); +static ssize_t nguid_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct nvme_ns *ns = nvme_get_ns_from_dev(dev); + return sprintf(buf, "%pU\n", ns->nguid); +} +static DEVICE_ATTR(nguid, S_IRUGO, nguid_show, NULL); + static ssize_t uuid_show(struct device *dev, struct device_attribute *attr, char *buf) { struct nvme_ns *ns = nvme_get_ns_from_dev(dev); - return sprintf(buf, "%pU\n", ns->uuid); + + /* For backward compatibility expose the NGUID to userspace if + * we have no UUID set + */ + if (uuid_is_null(&ns->uuid)) { + printk_ratelimited(KERN_WARNING + "No UUID available providing old NGUID\n"); + return sprintf(buf, "%pU\n", ns->nguid); + } + return sprintf(buf, "%pU\n", &ns->uuid); } static DEVICE_ATTR(uuid, S_IRUGO, uuid_show, NULL); @@ -1830,6 +2055,7 @@ static DEVICE_ATTR(nsid, S_IRUGO, nsid_show, NULL); static struct attribute *nvme_ns_attrs[] = { &dev_attr_wwid.attr, &dev_attr_uuid.attr, + &dev_attr_nguid.attr, &dev_attr_eui.attr, &dev_attr_nsid.attr, NULL, @@ -1842,7 +2068,12 @@ static umode_t nvme_ns_attrs_are_visible(struct kobject *kobj, struct nvme_ns *ns = nvme_get_ns_from_dev(dev); if (a == &dev_attr_uuid.attr) { - if (!memchr_inv(ns->uuid, 0, sizeof(ns->uuid))) + if (uuid_is_null(&ns->uuid) || + !memchr_inv(ns->nguid, 0, sizeof(ns->nguid))) + return 0; + } + if (a == &dev_attr_nguid.attr) { + if (!memchr_inv(ns->nguid, 0, sizeof(ns->nguid))) return 0; } if (a == &dev_attr_eui.attr) { @@ -1931,8 +2162,7 @@ static ssize_t nvme_sysfs_show_subsysnqn(struct device *dev, { struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - return snprintf(buf, PAGE_SIZE, "%s\n", - ctrl->ops->get_subsysnqn(ctrl)); + return snprintf(buf, PAGE_SIZE, "%s\n", ctrl->subnqn); } static DEVICE_ATTR(subsysnqn, S_IRUGO, nvme_sysfs_show_subsysnqn, NULL); @@ -1961,24 +2191,16 @@ static struct attribute *nvme_dev_attrs[] = { NULL }; -#define CHECK_ATTR(ctrl, a, name) \ - if ((a) == &dev_attr_##name.attr && \ - !(ctrl)->ops->get_##name) \ - return 0 - static umode_t nvme_dev_attrs_are_visible(struct kobject *kobj, struct attribute *a, int n) { struct device *dev = container_of(kobj, struct device, kobj); struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - if (a == &dev_attr_delete_controller.attr) { - if (!ctrl->ops->delete_ctrl) - return 0; - } - - CHECK_ATTR(ctrl, a, subsysnqn); - CHECK_ATTR(ctrl, a, address); + if (a == &dev_attr_delete_controller.attr && !ctrl->ops->delete_ctrl) + return 0; + if (a == &dev_attr_address.attr && !ctrl->ops->get_address) + return 0; return a->mode; } @@ -2019,6 +2241,32 @@ static struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid) return ret; } +static int nvme_setup_streams_ns(struct nvme_ctrl *ctrl, struct nvme_ns *ns) +{ + struct streams_directive_params s; + int ret; + + if (!ctrl->nr_streams) + return 0; + + ret = nvme_get_stream_params(ctrl, &s, ns->ns_id); + if (ret) + return ret; + + ns->sws = le32_to_cpu(s.sws); + ns->sgs = le16_to_cpu(s.sgs); + + if (ns->sws) { + unsigned int bs = 1 << ns->lba_shift; + + blk_queue_io_min(ns->queue, bs * ns->sws); + if (ns->sgs) + blk_queue_io_opt(ns->queue, bs * ns->sws * ns->sgs); + } + + return 0; +} + static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) { struct nvme_ns *ns; @@ -2048,6 +2296,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift); nvme_set_queue_limits(ctrl, ns->queue); + nvme_setup_streams_ns(ctrl, ns); sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->instance); @@ -2056,7 +2305,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) if (nvme_nvm_ns_supported(ns, id) && nvme_nvm_register(ns, disk_name, node)) { - dev_warn(ctrl->dev, "%s: LightNVM init failure\n", __func__); + dev_warn(ctrl->device, "%s: LightNVM init failure\n", __func__); goto out_free_id; } @@ -2231,7 +2480,7 @@ void nvme_queue_scan(struct nvme_ctrl *ctrl) * removal. */ if (ctrl->state == NVME_CTRL_LIVE) - schedule_work(&ctrl->scan_work); + queue_work(nvme_wq, &ctrl->scan_work); } EXPORT_SYMBOL_GPL(nvme_queue_scan); @@ -2286,7 +2535,7 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status, /*FALLTHRU*/ case NVME_SC_ABORT_REQ: ++ctrl->event_limit; - schedule_work(&ctrl->async_event_work); + queue_work(nvme_wq, &ctrl->async_event_work); break; default: break; @@ -2309,7 +2558,7 @@ EXPORT_SYMBOL_GPL(nvme_complete_async_event); void nvme_queue_async_events(struct nvme_ctrl *ctrl) { ctrl->event_limit = NVME_NR_AERS; - schedule_work(&ctrl->async_event_work); + queue_work(nvme_wq, &ctrl->async_event_work); } EXPORT_SYMBOL_GPL(nvme_queue_async_events); @@ -2442,6 +2691,9 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl) mutex_lock(&ctrl->namespaces_mutex); + /* Forcibly unquiesce queues to avoid blocking dispatch */ + blk_mq_unquiesce_queue(ctrl->admin_q); + /* Forcibly start all queues to avoid having stuck requests */ blk_mq_start_hw_queues(ctrl->admin_q); @@ -2455,6 +2707,9 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl) revalidate_disk(ns->disk); blk_set_queue_dying(ns->queue); + /* Forcibly unquiesce queues to avoid blocking dispatch */ + blk_mq_unquiesce_queue(ns->queue); + /* * Forcibly start all queues to avoid having stuck requests. * Note that we must ensure the queues are not stopped @@ -2533,7 +2788,7 @@ void nvme_start_queues(struct nvme_ctrl *ctrl) mutex_lock(&ctrl->namespaces_mutex); list_for_each_entry(ns, &ctrl->namespaces, list) { - blk_mq_start_stopped_hw_queues(ns->queue, true); + blk_mq_unquiesce_queue(ns->queue); blk_mq_kick_requeue_list(ns->queue); } mutex_unlock(&ctrl->namespaces_mutex); @@ -2544,10 +2799,15 @@ int __init nvme_core_init(void) { int result; + nvme_wq = alloc_workqueue("nvme-wq", + WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0); + if (!nvme_wq) + return -ENOMEM; + result = __register_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme", &nvme_dev_fops); if (result < 0) - return result; + goto destroy_wq; else if (result > 0) nvme_char_major = result; @@ -2559,8 +2819,10 @@ int __init nvme_core_init(void) return 0; - unregister_chrdev: +unregister_chrdev: __unregister_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme"); +destroy_wq: + destroy_workqueue(nvme_wq); return result; } @@ -2568,6 +2830,7 @@ void nvme_core_exit(void) { class_destroy(nvme_class); __unregister_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme"); + destroy_workqueue(nvme_wq); } MODULE_LICENSE("GPL"); diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 990e6fb32a63..2e582a240943 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -58,7 +58,6 @@ static struct nvmf_host *nvmf_host_add(const char *hostnqn) kref_init(&host->ref); memcpy(host->nqn, hostnqn, NVMF_NQN_SIZE); - uuid_be_gen(&host->id); list_add_tail(&host->list, &nvmf_hosts); out_unlock: @@ -75,7 +74,6 @@ static struct nvmf_host *nvmf_host_default(void) return NULL; kref_init(&host->ref); - uuid_be_gen(&host->id); snprintf(host->nqn, NVMF_NQN_SIZE, "nqn.2014-08.org.nvmexpress:NVMf:uuid:%pUb", &host->id); @@ -128,16 +126,6 @@ int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size) EXPORT_SYMBOL_GPL(nvmf_get_address); /** - * nvmf_get_subsysnqn() - Get subsystem NQN - * @ctrl: Host NVMe controller instance which we got the NQN - */ -const char *nvmf_get_subsysnqn(struct nvme_ctrl *ctrl) -{ - return ctrl->opts->subsysnqn; -} -EXPORT_SYMBOL_GPL(nvmf_get_subsysnqn); - -/** * nvmf_reg_read32() - NVMe Fabrics "Property Get" API function. * @ctrl: Host NVMe controller instance maintaining the admin * queue used to submit the property read command to @@ -337,6 +325,24 @@ static void nvmf_log_connect_error(struct nvme_ctrl *ctrl, } } break; + + case NVME_SC_CONNECT_INVALID_HOST: + dev_err(ctrl->device, + "Connect for subsystem %s is not allowed, hostnqn: %s\n", + data->subsysnqn, data->hostnqn); + break; + + case NVME_SC_CONNECT_CTRL_BUSY: + dev_err(ctrl->device, + "Connect command failed: controller is busy or not available\n"); + break; + + case NVME_SC_CONNECT_FORMAT: + dev_err(ctrl->device, + "Connect incompatible format: %d", + cmd->connect.recfmt); + break; + default: dev_err(ctrl->device, "Connect command failed, error wo/DNR bit: %d\n", @@ -376,13 +382,7 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl) cmd.connect.opcode = nvme_fabrics_command; cmd.connect.fctype = nvme_fabrics_type_connect; cmd.connect.qid = 0; - - /* - * fabrics spec sets a minimum of depth 32 for admin queue, - * so set the queue with this depth always until - * justification otherwise. - */ - cmd.connect.sqsize = cpu_to_le16(NVMF_AQ_DEPTH - 1); + cmd.connect.sqsize = cpu_to_le16(NVME_AQ_DEPTH - 1); /* * Set keep-alive timeout in seconds granularity (ms * 1000) @@ -395,7 +395,7 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl) if (!data) return -ENOMEM; - memcpy(&data->hostid, &ctrl->opts->host->id, sizeof(uuid_be)); + uuid_copy(&data->hostid, &ctrl->opts->host->id); data->cntlid = cpu_to_le16(0xffff); strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE); strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE); @@ -454,7 +454,7 @@ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid) if (!data) return -ENOMEM; - memcpy(&data->hostid, &ctrl->opts->host->id, sizeof(uuid_be)); + uuid_copy(&data->hostid, &ctrl->opts->host->id); data->cntlid = cpu_to_le16(ctrl->cntlid); strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE); strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE); @@ -474,7 +474,7 @@ EXPORT_SYMBOL_GPL(nvmf_connect_io_queue); bool nvmf_should_reconnect(struct nvme_ctrl *ctrl) { if (ctrl->opts->max_reconnects != -1 && - ctrl->opts->nr_reconnects < ctrl->opts->max_reconnects) + ctrl->nr_reconnects < ctrl->opts->max_reconnects) return true; return false; @@ -547,6 +547,7 @@ static const match_table_t opt_tokens = { { NVMF_OPT_KATO, "keep_alive_tmo=%d" }, { NVMF_OPT_HOSTNQN, "hostnqn=%s" }, { NVMF_OPT_HOST_TRADDR, "host_traddr=%s" }, + { NVMF_OPT_HOST_ID, "hostid=%s" }, { NVMF_OPT_ERR, NULL } }; @@ -558,6 +559,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, int token, ret = 0; size_t nqnlen = 0; int ctrl_loss_tmo = NVMF_DEF_CTRL_LOSS_TMO; + uuid_t hostid; /* Set defaults */ opts->queue_size = NVMF_DEF_QUEUE_SIZE; @@ -568,6 +570,8 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, if (!options) return -ENOMEM; + uuid_gen(&hostid); + while ((p = strsep(&o, ",\n")) != NULL) { if (!*p) continue; @@ -724,6 +728,17 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, } opts->host_traddr = p; break; + case NVMF_OPT_HOST_ID: + p = match_strdup(args); + if (!p) { + ret = -ENOMEM; + goto out; + } + if (uuid_parse(p, &hostid)) { + ret = -EINVAL; + goto out; + } + break; default: pr_warn("unknown parameter or missing value '%s' in ctrl creation request\n", p); @@ -743,6 +758,8 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, opts->host = nvmf_default_host; } + uuid_copy(&opts->host->id, &hostid); + out: if (!opts->discovery_nqn && !opts->kato) opts->kato = NVME_DEFAULT_KATO; @@ -803,7 +820,8 @@ EXPORT_SYMBOL_GPL(nvmf_free_options); #define NVMF_REQUIRED_OPTS (NVMF_OPT_TRANSPORT | NVMF_OPT_NQN) #define NVMF_ALLOWED_OPTS (NVMF_OPT_QUEUE_SIZE | NVMF_OPT_NR_IO_QUEUES | \ - NVMF_OPT_KATO | NVMF_OPT_HOSTNQN) + NVMF_OPT_KATO | NVMF_OPT_HOSTNQN | \ + NVMF_OPT_HOST_ID) static struct nvme_ctrl * nvmf_create_ctrl(struct device *dev, const char *buf, size_t count) @@ -854,6 +872,15 @@ nvmf_create_ctrl(struct device *dev, const char *buf, size_t count) goto out_unlock; } + if (strcmp(ctrl->subnqn, opts->subsysnqn)) { + dev_warn(ctrl->device, + "controller returned incorrect NQN: \"%s\".\n", + ctrl->subnqn); + mutex_unlock(&nvmf_transports_mutex); + ctrl->ops->delete_ctrl(ctrl); + return ERR_PTR(-EINVAL); + } + mutex_unlock(&nvmf_transports_mutex); return ctrl; diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index f5a9c1fb186f..bf33663218cd 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -36,7 +36,7 @@ struct nvmf_host { struct kref ref; struct list_head list; char nqn[NVMF_NQN_SIZE]; - uuid_be id; + uuid_t id; }; /** @@ -56,6 +56,7 @@ enum { NVMF_OPT_RECONNECT_DELAY = 1 << 9, NVMF_OPT_HOST_TRADDR = 1 << 10, NVMF_OPT_CTRL_LOSS_TMO = 1 << 11, + NVMF_OPT_HOST_ID = 1 << 12, }; /** @@ -80,7 +81,6 @@ enum { * @discovery_nqn: indicates if the subsysnqn is the well-known discovery NQN. * @kato: Keep-alive timeout. * @host: Virtual NVMe host, contains the NQN and Host ID. - * @nr_reconnects: number of reconnect attempted since the last ctrl failure * @max_reconnects: maximum number of allowed reconnect attempts before removing * the controller, (-1) means reconnect forever, zero means remove * immediately; @@ -98,7 +98,6 @@ struct nvmf_ctrl_options { bool discovery_nqn; unsigned int kato; struct nvmf_host *host; - int nr_reconnects; int max_reconnects; }; @@ -140,7 +139,6 @@ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid); int nvmf_register_transport(struct nvmf_transport_ops *ops); void nvmf_unregister_transport(struct nvmf_transport_ops *ops); void nvmf_free_options(struct nvmf_ctrl_options *opts); -const char *nvmf_get_subsysnqn(struct nvme_ctrl *ctrl); int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size); bool nvmf_should_reconnect(struct nvme_ctrl *ctrl); diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 92964cef0f4b..ed87214fdc0e 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -36,7 +36,7 @@ */ #define NVME_FC_NR_AEN_COMMANDS 1 #define NVME_FC_AQ_BLKMQ_DEPTH \ - (NVMF_AQ_DEPTH - NVME_FC_NR_AEN_COMMANDS) + (NVME_AQ_DEPTH - NVME_FC_NR_AEN_COMMANDS) #define AEN_CMDID_BASE (NVME_FC_AQ_BLKMQ_DEPTH + 1) enum nvme_fc_queue_flags { @@ -161,12 +161,12 @@ struct nvme_fc_ctrl { struct blk_mq_tag_set tag_set; struct work_struct delete_work; - struct work_struct reset_work; struct delayed_work connect_work; struct kref ref; u32 flags; u32 iocnt; + wait_queue_head_t ioabort_wait; struct nvme_fc_fcp_op aen_ops[NVME_FC_NR_AEN_COMMANDS]; @@ -214,7 +214,6 @@ static LIST_HEAD(nvme_fc_lport_list); static DEFINE_IDA(nvme_fc_local_port_cnt); static DEFINE_IDA(nvme_fc_ctrl_cnt); -static struct workqueue_struct *nvme_fc_wq; @@ -878,8 +877,7 @@ nvme_fc_connect_admin_queue(struct nvme_fc_ctrl *ctrl, assoc_rqst->assoc_cmd.sqsize = cpu_to_be16(qsize); /* Linux supports only Dynamic controllers */ assoc_rqst->assoc_cmd.cntlid = cpu_to_be16(0xffff); - memcpy(&assoc_rqst->assoc_cmd.hostid, &ctrl->ctrl.opts->host->id, - min_t(size_t, FCNVME_ASSOC_HOSTID_LEN, sizeof(uuid_be))); + uuid_copy(&assoc_rqst->assoc_cmd.hostid, &ctrl->ctrl.opts->host->id); strncpy(assoc_rqst->assoc_cmd.hostnqn, ctrl->ctrl.opts->host->nqn, min(FCNVME_ASSOC_HOSTNQN_LEN, NVMF_NQN_SIZE)); strncpy(assoc_rqst->assoc_cmd.subnqn, ctrl->ctrl.opts->subsysnqn, @@ -1242,8 +1240,10 @@ __nvme_fc_fcpop_chk_teardowns(struct nvme_fc_ctrl *ctrl, spin_lock_irqsave(&ctrl->lock, flags); if (unlikely(op->flags & FCOP_FLAGS_TERMIO)) { - if (ctrl->flags & FCCTRL_TERMIO) - ctrl->iocnt--; + if (ctrl->flags & FCCTRL_TERMIO) { + if (!--ctrl->iocnt) + wake_up(&ctrl->ioabort_wait); + } } if (op->flags & FCOP_FLAGS_RELEASED) complete_rq = true; @@ -1450,18 +1450,8 @@ nvme_fc_init_request(struct blk_mq_tag_set *set, struct request *rq, { struct nvme_fc_ctrl *ctrl = set->driver_data; struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(rq); - struct nvme_fc_queue *queue = &ctrl->queues[hctx_idx+1]; - - return __nvme_fc_init_request(ctrl, queue, op, rq, queue->rqcnt++); -} - -static int -nvme_fc_init_admin_request(struct blk_mq_tag_set *set, struct request *rq, - unsigned int hctx_idx, unsigned int numa_node) -{ - struct nvme_fc_ctrl *ctrl = set->driver_data; - struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(rq); - struct nvme_fc_queue *queue = &ctrl->queues[0]; + int queue_idx = (set == &ctrl->tag_set) ? hctx_idx + 1 : 0; + struct nvme_fc_queue *queue = &ctrl->queues[queue_idx]; return __nvme_fc_init_request(ctrl, queue, op, rq, queue->rqcnt++); } @@ -1759,16 +1749,16 @@ nvme_fc_nvme_ctrl_freed(struct nvme_ctrl *nctrl) static void nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg) { + /* only proceed if in LIVE state - e.g. on first error */ + if (ctrl->ctrl.state != NVME_CTRL_LIVE) + return; + dev_warn(ctrl->ctrl.device, "NVME-FC{%d}: transport association error detected: %s\n", ctrl->cnum, errmsg); dev_warn(ctrl->ctrl.device, "NVME-FC{%d}: resetting controller\n", ctrl->cnum); - /* stop the queues on error, cleanup is in reset thread */ - if (ctrl->queue_count > 1) - nvme_stop_queues(&ctrl->ctrl); - if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RECONNECTING)) { dev_err(ctrl->ctrl.device, "NVME-FC{%d}: error_recovery: Couldn't change state " @@ -1776,10 +1766,7 @@ nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg) return; } - if (!queue_work(nvme_fc_wq, &ctrl->reset_work)) - dev_err(ctrl->ctrl.device, - "NVME-FC{%d}: error_recovery: Failed to schedule " - "reset work\n", ctrl->cnum); + nvme_reset_ctrl(&ctrl->ctrl); } static enum blk_eh_timer_return @@ -1888,7 +1875,7 @@ nvme_fc_unmap_data(struct nvme_fc_ctrl *ctrl, struct request *rq, * level FC exchange resource that is also outstanding. This must be * considered in all cleanup operations. */ -static int +static blk_status_t nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue, struct nvme_fc_fcp_op *op, u32 data_len, enum nvmefc_fcp_datadir io_dir) @@ -1903,10 +1890,10 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue, * the target device is present */ if (ctrl->rport->remoteport.port_state != FC_OBJSTATE_ONLINE) - return BLK_MQ_RQ_QUEUE_ERROR; + return BLK_STS_IOERR; if (!nvme_fc_ctrl_get(ctrl)) - return BLK_MQ_RQ_QUEUE_ERROR; + return BLK_STS_IOERR; /* format the FC-NVME CMD IU and fcp_req */ cmdiu->connection_id = cpu_to_be64(queue->connection_id); @@ -1954,8 +1941,9 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue, if (ret < 0) { nvme_cleanup_cmd(op->rq); nvme_fc_ctrl_put(ctrl); - return (ret == -ENOMEM || ret == -EAGAIN) ? - BLK_MQ_RQ_QUEUE_BUSY : BLK_MQ_RQ_QUEUE_ERROR; + if (ret == -ENOMEM || ret == -EAGAIN) + return BLK_STS_RESOURCE; + return BLK_STS_IOERR; } } @@ -1972,28 +1960,26 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue, queue->lldd_handle, &op->fcp_req); if (ret) { - if (op->rq) { /* normal request */ + if (op->rq) /* normal request */ nvme_fc_unmap_data(ctrl, op->rq, op); - nvme_cleanup_cmd(op->rq); - } /* else - aen. no cleanup needed */ nvme_fc_ctrl_put(ctrl); if (ret != -EBUSY) - return BLK_MQ_RQ_QUEUE_ERROR; + return BLK_STS_IOERR; if (op->rq) { blk_mq_stop_hw_queues(op->rq->q); blk_mq_delay_queue(queue->hctx, NVMEFC_QUEUE_DELAY); } - return BLK_MQ_RQ_QUEUE_BUSY; + return BLK_STS_RESOURCE; } - return BLK_MQ_RQ_QUEUE_OK; + return BLK_STS_OK; } -static int +static blk_status_t nvme_fc_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { @@ -2006,7 +1992,7 @@ nvme_fc_queue_rq(struct blk_mq_hw_ctx *hctx, struct nvme_command *sqe = &cmdiu->sqe; enum nvmefc_fcp_datadir io_dir; u32 data_len; - int ret; + blk_status_t ret; ret = nvme_setup_cmd(ns, rq, sqe); if (ret) @@ -2061,7 +2047,7 @@ nvme_fc_submit_async_event(struct nvme_ctrl *arg, int aer_idx) struct nvme_fc_fcp_op *aen_op; unsigned long flags; bool terminating = false; - int ret; + blk_status_t ret; if (aer_idx > NVME_FC_NR_AEN_COMMANDS) return; @@ -2093,7 +2079,6 @@ __nvme_fc_final_op_cleanup(struct request *rq) op->flags &= ~(FCOP_FLAGS_TERMIO | FCOP_FLAGS_RELEASED | FCOP_FLAGS_COMPLETE); - nvme_cleanup_cmd(rq); nvme_fc_unmap_data(ctrl, rq, op); nvme_complete_rq(rq); nvme_fc_ctrl_put(ctrl); @@ -2311,7 +2296,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) int ret; bool changed; - ++ctrl->ctrl.opts->nr_reconnects; + ++ctrl->ctrl.nr_reconnects; /* * Create the admin queue @@ -2408,7 +2393,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE); WARN_ON_ONCE(!changed); - ctrl->ctrl.opts->nr_reconnects = 0; + ctrl->ctrl.nr_reconnects = 0; if (ctrl->queue_count > 1) { nvme_start_queues(&ctrl->ctrl); @@ -2494,11 +2479,7 @@ nvme_fc_delete_association(struct nvme_fc_ctrl *ctrl) /* wait for all io that had to be aborted */ spin_lock_irqsave(&ctrl->lock, flags); - while (ctrl->iocnt) { - spin_unlock_irqrestore(&ctrl->lock, flags); - msleep(1000); - spin_lock_irqsave(&ctrl->lock, flags); - } + wait_event_lock_irq(ctrl->ioabort_wait, ctrl->iocnt == 0, ctrl->lock); ctrl->flags &= ~FCCTRL_TERMIO; spin_unlock_irqrestore(&ctrl->lock, flags); @@ -2528,7 +2509,7 @@ nvme_fc_delete_ctrl_work(struct work_struct *work) struct nvme_fc_ctrl *ctrl = container_of(work, struct nvme_fc_ctrl, delete_work); - cancel_work_sync(&ctrl->reset_work); + cancel_work_sync(&ctrl->ctrl.reset_work); cancel_delayed_work_sync(&ctrl->connect_work); /* @@ -2555,7 +2536,7 @@ __nvme_fc_schedule_delete_work(struct nvme_fc_ctrl *ctrl) if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING)) return true; - if (!queue_work(nvme_fc_wq, &ctrl->delete_work)) + if (!queue_work(nvme_wq, &ctrl->delete_work)) return true; return false; @@ -2582,7 +2563,7 @@ nvme_fc_del_nvme_ctrl(struct nvme_ctrl *nctrl) ret = __nvme_fc_del_ctrl(ctrl); if (!ret) - flush_workqueue(nvme_fc_wq); + flush_workqueue(nvme_wq); nvme_put_ctrl(&ctrl->ctrl); @@ -2607,13 +2588,13 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status) dev_info(ctrl->ctrl.device, "NVME-FC{%d}: Reconnect attempt in %d seconds.\n", ctrl->cnum, ctrl->ctrl.opts->reconnect_delay); - queue_delayed_work(nvme_fc_wq, &ctrl->connect_work, + queue_delayed_work(nvme_wq, &ctrl->connect_work, ctrl->ctrl.opts->reconnect_delay * HZ); } else { dev_warn(ctrl->ctrl.device, "NVME-FC{%d}: Max reconnect attempts (%d) " "reached. Removing controller\n", - ctrl->cnum, ctrl->ctrl.opts->nr_reconnects); + ctrl->cnum, ctrl->ctrl.nr_reconnects); WARN_ON(__nvme_fc_schedule_delete_work(ctrl)); } } @@ -2622,7 +2603,7 @@ static void nvme_fc_reset_ctrl_work(struct work_struct *work) { struct nvme_fc_ctrl *ctrl = - container_of(work, struct nvme_fc_ctrl, reset_work); + container_of(work, struct nvme_fc_ctrl, ctrl.reset_work); int ret; /* will block will waiting for io to terminate */ @@ -2636,29 +2617,6 @@ nvme_fc_reset_ctrl_work(struct work_struct *work) "NVME-FC{%d}: controller reset complete\n", ctrl->cnum); } -/* - * called by the nvme core layer, for sysfs interface that requests - * a reset of the nvme controller - */ -static int -nvme_fc_reset_nvme_ctrl(struct nvme_ctrl *nctrl) -{ - struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl); - - dev_info(ctrl->ctrl.device, - "NVME-FC{%d}: admin requested controller reset\n", ctrl->cnum); - - if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING)) - return -EBUSY; - - if (!queue_work(nvme_fc_wq, &ctrl->reset_work)) - return -EBUSY; - - flush_work(&ctrl->reset_work); - - return 0; -} - static const struct nvme_ctrl_ops nvme_fc_ctrl_ops = { .name = "fc", .module = THIS_MODULE, @@ -2666,11 +2624,9 @@ static const struct nvme_ctrl_ops nvme_fc_ctrl_ops = { .reg_read32 = nvmf_reg_read32, .reg_read64 = nvmf_reg_read64, .reg_write32 = nvmf_reg_write32, - .reset_ctrl = nvme_fc_reset_nvme_ctrl, .free_ctrl = nvme_fc_nvme_ctrl_freed, .submit_async_event = nvme_fc_submit_async_event, .delete_ctrl = nvme_fc_del_nvme_ctrl, - .get_subsysnqn = nvmf_get_subsysnqn, .get_address = nvmf_get_address, }; @@ -2696,7 +2652,7 @@ nvme_fc_connect_ctrl_work(struct work_struct *work) static const struct blk_mq_ops nvme_fc_admin_mq_ops = { .queue_rq = nvme_fc_queue_rq, .complete = nvme_fc_complete_rq, - .init_request = nvme_fc_init_admin_request, + .init_request = nvme_fc_init_request, .exit_request = nvme_fc_exit_request, .reinit_request = nvme_fc_reinit_request, .init_hctx = nvme_fc_init_admin_hctx, @@ -2741,7 +2697,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, kref_init(&ctrl->ref); INIT_WORK(&ctrl->delete_work, nvme_fc_delete_ctrl_work); - INIT_WORK(&ctrl->reset_work, nvme_fc_reset_ctrl_work); + INIT_WORK(&ctrl->ctrl.reset_work, nvme_fc_reset_ctrl_work); INIT_DELAYED_WORK(&ctrl->connect_work, nvme_fc_connect_ctrl_work); spin_lock_init(&ctrl->lock); @@ -2808,6 +2764,9 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, nvme_uninit_ctrl(&ctrl->ctrl); nvme_put_ctrl(&ctrl->ctrl); + /* Remove core ctrl ref. */ + nvme_put_ctrl(&ctrl->ctrl); + /* as we're past the point where we transition to the ref * counting teardown path, if we return a bad pointer here, * the calling routine, thinking it's prior to the @@ -2966,20 +2925,7 @@ static struct nvmf_transport_ops nvme_fc_transport = { static int __init nvme_fc_init_module(void) { - int ret; - - nvme_fc_wq = create_workqueue("nvme_fc_wq"); - if (!nvme_fc_wq) - return -ENOMEM; - - ret = nvmf_register_transport(&nvme_fc_transport); - if (ret) - goto err; - - return 0; -err: - destroy_workqueue(nvme_fc_wq); - return ret; + return nvmf_register_transport(&nvme_fc_transport); } static void __exit nvme_fc_exit_module(void) @@ -2990,8 +2936,6 @@ static void __exit nvme_fc_exit_module(void) nvmf_unregister_transport(&nvme_fc_transport); - destroy_workqueue(nvme_fc_wq); - ida_destroy(&nvme_fc_local_port_cnt); ida_destroy(&nvme_fc_ctrl_cnt); } diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c index f5df78ed1e10..be8541335e31 100644 --- a/drivers/nvme/host/lightnvm.c +++ b/drivers/nvme/host/lightnvm.c @@ -242,7 +242,7 @@ static inline void _nvme_nvm_check_size(void) BUILD_BUG_ON(sizeof(struct nvme_nvm_erase_blk) != 64); BUILD_BUG_ON(sizeof(struct nvme_nvm_id_group) != 960); BUILD_BUG_ON(sizeof(struct nvme_nvm_addr_format) != 16); - BUILD_BUG_ON(sizeof(struct nvme_nvm_id) != 4096); + BUILD_BUG_ON(sizeof(struct nvme_nvm_id) != NVME_IDENTIFY_DATA_SIZE); BUILD_BUG_ON(sizeof(struct nvme_nvm_bb_tbl) != 64); } @@ -480,7 +480,7 @@ static inline void nvme_nvm_rqtocmd(struct nvm_rq *rqd, struct nvme_ns *ns, rqd->bio->bi_iter.bi_sector)); } -static void nvme_nvm_end_io(struct request *rq, int error) +static void nvme_nvm_end_io(struct request *rq, blk_status_t status) { struct nvm_rq *rqd = rq->end_io_data; @@ -509,7 +509,7 @@ static int nvme_nvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd) rq = nvme_alloc_request(q, (struct nvme_command *)cmd, 0, NVME_QID_ANY); if (IS_ERR(rq)) { kfree(cmd); - return -ENOMEM; + return PTR_ERR(rq); } rq->cmd_flags &= ~REQ_FAILFAST_DRIVER; @@ -571,13 +571,6 @@ static struct nvm_dev_ops nvme_nvm_dev_ops = { .max_phys_sect = 64, }; -static void nvme_nvm_end_user_vio(struct request *rq, int error) -{ - struct completion *waiting = rq->end_io_data; - - complete(waiting); -} - static int nvme_nvm_submit_user_cmd(struct request_queue *q, struct nvme_ns *ns, struct nvme_nvm_command *vcmd, @@ -608,7 +601,6 @@ static int nvme_nvm_submit_user_cmd(struct request_queue *q, rq->timeout = timeout ? timeout : ADMIN_TIMEOUT; rq->cmd_flags &= ~REQ_FAILFAST_DRIVER; - rq->end_io_data = &wait; if (ppa_buf && ppa_len) { ppa_list = dma_pool_alloc(dev->dma_pool, GFP_KERNEL, &ppa_dma); @@ -662,9 +654,7 @@ static int nvme_nvm_submit_user_cmd(struct request_queue *q, } submit: - blk_execute_rq_nowait(q, NULL, rq, 0, nvme_nvm_end_user_vio); - - wait_for_completion_io(&wait); + blk_execute_rq(q, NULL, rq, 0); if (nvme_req(rq)->flags & NVME_REQ_CANCELLED) ret = -EINTR; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 9d6a070d4391..d70ff0fdd36b 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -27,12 +27,11 @@ extern unsigned char nvme_io_timeout; extern unsigned char admin_timeout; #define ADMIN_TIMEOUT (admin_timeout * HZ) -extern unsigned char shutdown_timeout; -#define SHUTDOWN_TIMEOUT (shutdown_timeout * HZ) - #define NVME_DEFAULT_KATO 5 #define NVME_KATO_GRACE 10 +extern struct workqueue_struct *nvme_wq; + enum { NVME_NS_LBA = 0, NVME_NS_LIGHTNVM = 1, @@ -131,6 +130,7 @@ struct nvme_ctrl { struct device *device; /* char device */ struct list_head node; struct ida ns_ida; + struct work_struct reset_work; struct opal_dev *opal_dev; @@ -138,6 +138,7 @@ struct nvme_ctrl { char serial[20]; char model[40]; char firmware_rev[8]; + char subnqn[NVMF_NQN_SIZE]; u16 cntlid; u32 ctrl_config; @@ -147,6 +148,8 @@ struct nvme_ctrl { u16 oncs; u16 vid; u16 oacs; + u16 nssa; + u16 nr_streams; atomic_t abort_limit; u8 event_limit; u8 vwc; @@ -165,6 +168,10 @@ struct nvme_ctrl { /* Power saving configuration */ u64 ps_max_latency_us; + bool apst_enabled; + + u32 hmpre; + u32 hmmin; /* Fabrics only */ u16 sqsize; @@ -172,12 +179,10 @@ struct nvme_ctrl { u32 iorcsz; u16 icdoff; u16 maxcmd; + int nr_reconnects; struct nvmf_ctrl_options *opts; }; -/* - * An NVM Express namespace is equivalent to a SCSI LUN - */ struct nvme_ns { struct list_head list; @@ -189,14 +194,18 @@ struct nvme_ns { int instance; u8 eui[8]; - u8 uuid[16]; + u8 nguid[16]; + uuid_t uuid; unsigned ns_id; int lba_shift; u16 ms; + u16 sgs; + u32 sws; bool ext; u8 pi_type; unsigned long flags; + u16 noiob; #define NVME_NS_REMOVING 0 #define NVME_NS_DEAD 1 @@ -214,11 +223,9 @@ struct nvme_ctrl_ops { int (*reg_read32)(struct nvme_ctrl *ctrl, u32 off, u32 *val); int (*reg_write32)(struct nvme_ctrl *ctrl, u32 off, u32 val); int (*reg_read64)(struct nvme_ctrl *ctrl, u32 off, u64 *val); - int (*reset_ctrl)(struct nvme_ctrl *ctrl); void (*free_ctrl)(struct nvme_ctrl *ctrl); void (*submit_async_event)(struct nvme_ctrl *ctrl, int aer_idx); int (*delete_ctrl)(struct nvme_ctrl *ctrl); - const char *(*get_subsysnqn)(struct nvme_ctrl *ctrl); int (*get_address)(struct nvme_ctrl *ctrl, char *buf, int size); }; @@ -296,7 +303,7 @@ void nvme_start_freeze(struct nvme_ctrl *ctrl); #define NVME_QID_ANY -1 struct request *nvme_alloc_request(struct request_queue *q, struct nvme_command *cmd, unsigned int flags, int qid); -int nvme_setup_cmd(struct nvme_ns *ns, struct request *req, +blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req, struct nvme_command *cmd); int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, void *buf, unsigned bufflen); @@ -310,23 +317,10 @@ int __nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd, void __user *ubuffer, unsigned bufflen, void __user *meta_buffer, unsigned meta_len, u32 meta_seed, u32 *result, unsigned timeout); -int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id); -int nvme_identify_ns(struct nvme_ctrl *dev, unsigned nsid, - struct nvme_id_ns **id); -int nvme_get_log_page(struct nvme_ctrl *dev, struct nvme_smart_log **log); -int nvme_get_features(struct nvme_ctrl *dev, unsigned fid, unsigned nsid, - void *buffer, size_t buflen, u32 *result); -int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11, - void *buffer, size_t buflen, u32 *result); int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count); void nvme_start_keep_alive(struct nvme_ctrl *ctrl); void nvme_stop_keep_alive(struct nvme_ctrl *ctrl); - -struct sg_io_hdr; - -int nvme_sg_io(struct nvme_ns *ns, struct sg_io_hdr __user *u_hdr); -int nvme_sg_io32(struct nvme_ns *ns, unsigned long arg); -int nvme_sg_get_version_num(int __user *ip); +int nvme_reset_ctrl(struct nvme_ctrl *ctrl); #ifdef CONFIG_NVM int nvme_nvm_ns_supported(struct nvme_ns *ns, struct nvme_id_ns *id); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 951042a375d6..33c3b9db7d36 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -17,28 +17,15 @@ #include <linux/blkdev.h> #include <linux/blk-mq.h> #include <linux/blk-mq-pci.h> -#include <linux/cpu.h> -#include <linux/delay.h> #include <linux/dmi.h> -#include <linux/errno.h> -#include <linux/fs.h> -#include <linux/genhd.h> -#include <linux/hdreg.h> -#include <linux/idr.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/io.h> -#include <linux/kdev_t.h> -#include <linux/kernel.h> #include <linux/mm.h> #include <linux/module.h> -#include <linux/moduleparam.h> #include <linux/mutex.h> #include <linux/pci.h> #include <linux/poison.h> -#include <linux/ptrace.h> -#include <linux/sched.h> -#include <linux/slab.h> #include <linux/t10-pi.h> #include <linux/timer.h> #include <linux/types.h> @@ -49,7 +36,6 @@ #include "nvme.h" #define NVME_Q_DEPTH 1024 -#define NVME_AQ_DEPTH 256 #define SQ_SIZE(depth) (depth * sizeof(struct nvme_command)) #define CQ_SIZE(depth) (depth * sizeof(struct nvme_completion)) @@ -66,12 +52,14 @@ static bool use_cmb_sqes = true; module_param(use_cmb_sqes, bool, 0644); MODULE_PARM_DESC(use_cmb_sqes, "use controller's memory buffer for I/O SQes"); -static struct workqueue_struct *nvme_workq; +static unsigned int max_host_mem_size_mb = 128; +module_param(max_host_mem_size_mb, uint, 0444); +MODULE_PARM_DESC(max_host_mem_size_mb, + "Maximum Host Memory Buffer (HMB) size per controller (in MiB)"); struct nvme_dev; struct nvme_queue; -static int nvme_reset(struct nvme_dev *dev); static void nvme_process_cq(struct nvme_queue *nvmeq); static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown); @@ -92,9 +80,8 @@ struct nvme_dev { int q_depth; u32 db_stride; void __iomem *bar; - struct work_struct reset_work; + unsigned long bar_mapped_size; struct work_struct remove_work; - struct timer_list watchdog_timer; struct mutex shutdown_lock; bool subsystem; void __iomem *cmb; @@ -104,10 +91,18 @@ struct nvme_dev { u32 cmbloc; struct nvme_ctrl ctrl; struct completion ioq_wait; + + /* shadow doorbell buffer support: */ u32 *dbbuf_dbs; dma_addr_t dbbuf_dbs_dma_addr; u32 *dbbuf_eis; dma_addr_t dbbuf_eis_dma_addr; + + /* host memory buffer support: */ + u64 host_mem_size; + u32 nr_host_mem_descs; + struct nvme_host_mem_buf_desc *host_mem_descs; + void **host_mem_desc_bufs; }; static inline unsigned int sq_idx(unsigned int qid, u32 stride) @@ -185,8 +180,8 @@ static inline void _nvme_check_size(void) BUILD_BUG_ON(sizeof(struct nvme_format_cmd) != 64); BUILD_BUG_ON(sizeof(struct nvme_abort_cmd) != 64); BUILD_BUG_ON(sizeof(struct nvme_command) != 64); - BUILD_BUG_ON(sizeof(struct nvme_id_ctrl) != 4096); - BUILD_BUG_ON(sizeof(struct nvme_id_ns) != 4096); + BUILD_BUG_ON(sizeof(struct nvme_id_ctrl) != NVME_IDENTIFY_DATA_SIZE); + BUILD_BUG_ON(sizeof(struct nvme_id_ns) != NVME_IDENTIFY_DATA_SIZE); BUILD_BUG_ON(sizeof(struct nvme_lba_range_type) != 64); BUILD_BUG_ON(sizeof(struct nvme_smart_log) != 512); BUILD_BUG_ON(sizeof(struct nvme_dbbuf) != 64); @@ -350,19 +345,6 @@ static void nvme_admin_exit_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_i nvmeq->tags = NULL; } -static int nvme_admin_init_request(struct blk_mq_tag_set *set, - struct request *req, unsigned int hctx_idx, - unsigned int numa_node) -{ - struct nvme_dev *dev = set->driver_data; - struct nvme_iod *iod = blk_mq_rq_to_pdu(req); - struct nvme_queue *nvmeq = dev->queues[0]; - - BUG_ON(!nvmeq); - iod->nvmeq = nvmeq; - return 0; -} - static int nvme_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, unsigned int hctx_idx) { @@ -382,7 +364,8 @@ static int nvme_init_request(struct blk_mq_tag_set *set, struct request *req, { struct nvme_dev *dev = set->driver_data; struct nvme_iod *iod = blk_mq_rq_to_pdu(req); - struct nvme_queue *nvmeq = dev->queues[hctx_idx + 1]; + int queue_idx = (set == &dev->tagset) ? hctx_idx + 1 : 0; + struct nvme_queue *nvmeq = dev->queues[queue_idx]; BUG_ON(!nvmeq); iod->nvmeq = nvmeq; @@ -427,7 +410,7 @@ static __le64 **iod_list(struct request *req) return (__le64 **)(iod->sg + blk_rq_nr_phys_segments(req)); } -static int nvme_init_iod(struct request *rq, struct nvme_dev *dev) +static blk_status_t nvme_init_iod(struct request *rq, struct nvme_dev *dev) { struct nvme_iod *iod = blk_mq_rq_to_pdu(rq); int nseg = blk_rq_nr_phys_segments(rq); @@ -436,7 +419,7 @@ static int nvme_init_iod(struct request *rq, struct nvme_dev *dev) if (nseg > NVME_INT_PAGES || size > NVME_INT_BYTES(dev)) { iod->sg = kmalloc(nvme_iod_alloc_size(dev, size, nseg), GFP_ATOMIC); if (!iod->sg) - return BLK_MQ_RQ_QUEUE_BUSY; + return BLK_STS_RESOURCE; } else { iod->sg = iod->inline_sg; } @@ -446,7 +429,7 @@ static int nvme_init_iod(struct request *rq, struct nvme_dev *dev) iod->nents = 0; iod->length = size; - return BLK_MQ_RQ_QUEUE_OK; + return BLK_STS_OK; } static void nvme_free_iod(struct nvme_dev *dev, struct request *req) @@ -616,21 +599,21 @@ static bool nvme_setup_prps(struct nvme_dev *dev, struct request *req) return true; } -static int nvme_map_data(struct nvme_dev *dev, struct request *req, +static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req, struct nvme_command *cmnd) { struct nvme_iod *iod = blk_mq_rq_to_pdu(req); struct request_queue *q = req->q; enum dma_data_direction dma_dir = rq_data_dir(req) ? DMA_TO_DEVICE : DMA_FROM_DEVICE; - int ret = BLK_MQ_RQ_QUEUE_ERROR; + blk_status_t ret = BLK_STS_IOERR; sg_init_table(iod->sg, blk_rq_nr_phys_segments(req)); iod->nents = blk_rq_map_sg(q, req, iod->sg); if (!iod->nents) goto out; - ret = BLK_MQ_RQ_QUEUE_BUSY; + ret = BLK_STS_RESOURCE; if (!dma_map_sg_attrs(dev->dev, iod->sg, iod->nents, dma_dir, DMA_ATTR_NO_WARN)) goto out; @@ -638,7 +621,7 @@ static int nvme_map_data(struct nvme_dev *dev, struct request *req, if (!nvme_setup_prps(dev, req)) goto out_unmap; - ret = BLK_MQ_RQ_QUEUE_ERROR; + ret = BLK_STS_IOERR; if (blk_integrity_rq(req)) { if (blk_rq_count_integrity_sg(q, req->bio) != 1) goto out_unmap; @@ -658,7 +641,7 @@ static int nvme_map_data(struct nvme_dev *dev, struct request *req, cmnd->rw.dptr.prp2 = cpu_to_le64(iod->first_dma); if (blk_integrity_rq(req)) cmnd->rw.metadata = cpu_to_le64(sg_dma_address(&iod->meta_sg)); - return BLK_MQ_RQ_QUEUE_OK; + return BLK_STS_OK; out_unmap: dma_unmap_sg(dev->dev, iod->sg, iod->nents, dma_dir); @@ -688,7 +671,7 @@ static void nvme_unmap_data(struct nvme_dev *dev, struct request *req) /* * NOTE: ns is NULL when called on the admin queue. */ -static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx, +static blk_status_t nvme_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { struct nvme_ns *ns = hctx->queue->queuedata; @@ -696,47 +679,34 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx, struct nvme_dev *dev = nvmeq->dev; struct request *req = bd->rq; struct nvme_command cmnd; - int ret = BLK_MQ_RQ_QUEUE_OK; - - /* - * If formated with metadata, require the block layer provide a buffer - * unless this namespace is formated such that the metadata can be - * stripped/generated by the controller with PRACT=1. - */ - if (ns && ns->ms && !blk_integrity_rq(req)) { - if (!(ns->pi_type && ns->ms == 8) && - !blk_rq_is_passthrough(req)) { - blk_mq_end_request(req, -EFAULT); - return BLK_MQ_RQ_QUEUE_OK; - } - } + blk_status_t ret; ret = nvme_setup_cmd(ns, req, &cmnd); - if (ret != BLK_MQ_RQ_QUEUE_OK) + if (ret) return ret; ret = nvme_init_iod(req, dev); - if (ret != BLK_MQ_RQ_QUEUE_OK) + if (ret) goto out_free_cmd; - if (blk_rq_nr_phys_segments(req)) + if (blk_rq_nr_phys_segments(req)) { ret = nvme_map_data(dev, req, &cmnd); - - if (ret != BLK_MQ_RQ_QUEUE_OK) - goto out_cleanup_iod; + if (ret) + goto out_cleanup_iod; + } blk_mq_start_request(req); spin_lock_irq(&nvmeq->q_lock); if (unlikely(nvmeq->cq_vector < 0)) { - ret = BLK_MQ_RQ_QUEUE_ERROR; + ret = BLK_STS_IOERR; spin_unlock_irq(&nvmeq->q_lock); goto out_cleanup_iod; } __nvme_submit_cmd(nvmeq, &cmnd); nvme_process_cq(nvmeq); spin_unlock_irq(&nvmeq->q_lock); - return BLK_MQ_RQ_QUEUE_OK; + return BLK_STS_OK; out_cleanup_iod: nvme_free_iod(dev, req); out_free_cmd: @@ -759,65 +729,75 @@ static inline bool nvme_cqe_valid(struct nvme_queue *nvmeq, u16 head, return (le16_to_cpu(nvmeq->cqes[head].status) & 1) == phase; } -static void __nvme_process_cq(struct nvme_queue *nvmeq, unsigned int *tag) +static inline void nvme_ring_cq_doorbell(struct nvme_queue *nvmeq) { - u16 head, phase; - - head = nvmeq->cq_head; - phase = nvmeq->cq_phase; - - while (nvme_cqe_valid(nvmeq, head, phase)) { - struct nvme_completion cqe = nvmeq->cqes[head]; - struct request *req; - - if (++head == nvmeq->q_depth) { - head = 0; - phase = !phase; - } - - if (tag && *tag == cqe.command_id) - *tag = -1; + u16 head = nvmeq->cq_head; - if (unlikely(cqe.command_id >= nvmeq->q_depth)) { - dev_warn(nvmeq->dev->ctrl.device, - "invalid id %d completed on queue %d\n", - cqe.command_id, le16_to_cpu(cqe.sq_id)); - continue; - } + if (likely(nvmeq->cq_vector >= 0)) { + if (nvme_dbbuf_update_and_check_event(head, nvmeq->dbbuf_cq_db, + nvmeq->dbbuf_cq_ei)) + writel(head, nvmeq->q_db + nvmeq->dev->db_stride); + } +} - /* - * AEN requests are special as they don't time out and can - * survive any kind of queue freeze and often don't respond to - * aborts. We don't even bother to allocate a struct request - * for them but rather special case them here. - */ - if (unlikely(nvmeq->qid == 0 && - cqe.command_id >= NVME_AQ_BLKMQ_DEPTH)) { - nvme_complete_async_event(&nvmeq->dev->ctrl, - cqe.status, &cqe.result); - continue; - } +static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, + struct nvme_completion *cqe) +{ + struct request *req; - req = blk_mq_tag_to_rq(*nvmeq->tags, cqe.command_id); - nvme_end_request(req, cqe.status, cqe.result); + if (unlikely(cqe->command_id >= nvmeq->q_depth)) { + dev_warn(nvmeq->dev->ctrl.device, + "invalid id %d completed on queue %d\n", + cqe->command_id, le16_to_cpu(cqe->sq_id)); + return; } - if (head == nvmeq->cq_head && phase == nvmeq->cq_phase) + /* + * AEN requests are special as they don't time out and can + * survive any kind of queue freeze and often don't respond to + * aborts. We don't even bother to allocate a struct request + * for them but rather special case them here. + */ + if (unlikely(nvmeq->qid == 0 && + cqe->command_id >= NVME_AQ_BLKMQ_DEPTH)) { + nvme_complete_async_event(&nvmeq->dev->ctrl, + cqe->status, &cqe->result); return; + } - if (likely(nvmeq->cq_vector >= 0)) - if (nvme_dbbuf_update_and_check_event(head, nvmeq->dbbuf_cq_db, - nvmeq->dbbuf_cq_ei)) - writel(head, nvmeq->q_db + nvmeq->dev->db_stride); - nvmeq->cq_head = head; - nvmeq->cq_phase = phase; + req = blk_mq_tag_to_rq(*nvmeq->tags, cqe->command_id); + nvme_end_request(req, cqe->status, cqe->result); +} - nvmeq->cqe_seen = 1; +static inline bool nvme_read_cqe(struct nvme_queue *nvmeq, + struct nvme_completion *cqe) +{ + if (nvme_cqe_valid(nvmeq, nvmeq->cq_head, nvmeq->cq_phase)) { + *cqe = nvmeq->cqes[nvmeq->cq_head]; + + if (++nvmeq->cq_head == nvmeq->q_depth) { + nvmeq->cq_head = 0; + nvmeq->cq_phase = !nvmeq->cq_phase; + } + return true; + } + return false; } static void nvme_process_cq(struct nvme_queue *nvmeq) { - __nvme_process_cq(nvmeq, NULL); + struct nvme_completion cqe; + int consumed = 0; + + while (nvme_read_cqe(nvmeq, &cqe)) { + nvme_handle_cqe(nvmeq, &cqe); + consumed++; + } + + if (consumed) { + nvme_ring_cq_doorbell(nvmeq); + nvmeq->cqe_seen = 1; + } } static irqreturn_t nvme_irq(int irq, void *data) @@ -842,16 +822,28 @@ static irqreturn_t nvme_irq_check(int irq, void *data) static int __nvme_poll(struct nvme_queue *nvmeq, unsigned int tag) { - if (nvme_cqe_valid(nvmeq, nvmeq->cq_head, nvmeq->cq_phase)) { - spin_lock_irq(&nvmeq->q_lock); - __nvme_process_cq(nvmeq, &tag); - spin_unlock_irq(&nvmeq->q_lock); + struct nvme_completion cqe; + int found = 0, consumed = 0; - if (tag == -1) - return 1; - } + if (!nvme_cqe_valid(nvmeq, nvmeq->cq_head, nvmeq->cq_phase)) + return 0; - return 0; + spin_lock_irq(&nvmeq->q_lock); + while (nvme_read_cqe(nvmeq, &cqe)) { + nvme_handle_cqe(nvmeq, &cqe); + consumed++; + + if (tag == cqe.command_id) { + found = 1; + break; + } + } + + if (consumed) + nvme_ring_cq_doorbell(nvmeq); + spin_unlock_irq(&nvmeq->q_lock); + + return found; } static int nvme_poll(struct blk_mq_hw_ctx *hctx, unsigned int tag) @@ -939,7 +931,7 @@ static int adapter_delete_sq(struct nvme_dev *dev, u16 sqid) return adapter_delete_queue(dev, nvme_admin_delete_sq, sqid); } -static void abort_endio(struct request *req, int error) +static void abort_endio(struct request *req, blk_status_t error) { struct nvme_iod *iod = blk_mq_rq_to_pdu(req); struct nvme_queue *nvmeq = iod->nvmeq; @@ -950,6 +942,51 @@ static void abort_endio(struct request *req, int error) blk_mq_free_request(req); } +static bool nvme_should_reset(struct nvme_dev *dev, u32 csts) +{ + + /* If true, indicates loss of adapter communication, possibly by a + * NVMe Subsystem reset. + */ + bool nssro = dev->subsystem && (csts & NVME_CSTS_NSSRO); + + /* If there is a reset ongoing, we shouldn't reset again. */ + if (dev->ctrl.state == NVME_CTRL_RESETTING) + return false; + + /* We shouldn't reset unless the controller is on fatal error state + * _or_ if we lost the communication with it. + */ + if (!(csts & NVME_CSTS_CFS) && !nssro) + return false; + + /* If PCI error recovery process is happening, we cannot reset or + * the recovery mechanism will surely fail. + */ + if (pci_channel_offline(to_pci_dev(dev->dev))) + return false; + + return true; +} + +static void nvme_warn_reset(struct nvme_dev *dev, u32 csts) +{ + /* Read a config register to help see what died. */ + u16 pci_status; + int result; + + result = pci_read_config_word(to_pci_dev(dev->dev), PCI_STATUS, + &pci_status); + if (result == PCIBIOS_SUCCESSFUL) + dev_warn(dev->ctrl.device, + "controller is down; will reset: CSTS=0x%x, PCI_STATUS=0x%hx\n", + csts, pci_status); + else + dev_warn(dev->ctrl.device, + "controller is down; will reset: CSTS=0x%x, PCI_STATUS read failed (%d)\n", + csts, result); +} + static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved) { struct nvme_iod *iod = blk_mq_rq_to_pdu(req); @@ -957,6 +994,17 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved) struct nvme_dev *dev = nvmeq->dev; struct request *abort_req; struct nvme_command cmd; + u32 csts = readl(dev->bar + NVME_REG_CSTS); + + /* + * Reset immediately if the controller is failed + */ + if (nvme_should_reset(dev, csts)) { + nvme_warn_reset(dev, csts); + nvme_dev_disable(dev, false); + nvme_reset_ctrl(&dev->ctrl); + return BLK_EH_HANDLED; + } /* * Did we miss an interrupt? @@ -993,7 +1041,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved) "I/O %d QID %d timeout, reset controller\n", req->tag, nvmeq->qid); nvme_dev_disable(dev, false); - nvme_reset(dev); + nvme_reset_ctrl(&dev->ctrl); /* * Mark the request as handled, since the inline shutdown @@ -1247,7 +1295,7 @@ static const struct blk_mq_ops nvme_mq_admin_ops = { .complete = nvme_pci_complete_rq, .init_hctx = nvme_admin_init_hctx, .exit_hctx = nvme_admin_exit_hctx, - .init_request = nvme_admin_init_request, + .init_request = nvme_init_request, .timeout = nvme_timeout, }; @@ -1311,6 +1359,32 @@ static int nvme_alloc_admin_tags(struct nvme_dev *dev) return 0; } +static unsigned long db_bar_size(struct nvme_dev *dev, unsigned nr_io_queues) +{ + return NVME_REG_DBS + ((nr_io_queues + 1) * 8 * dev->db_stride); +} + +static int nvme_remap_bar(struct nvme_dev *dev, unsigned long size) +{ + struct pci_dev *pdev = to_pci_dev(dev->dev); + + if (size <= dev->bar_mapped_size) + return 0; + if (size > pci_resource_len(pdev, 0)) + return -ENOMEM; + if (dev->bar) + iounmap(dev->bar); + dev->bar = ioremap(pci_resource_start(pdev, 0), size); + if (!dev->bar) { + dev->bar_mapped_size = 0; + return -ENOMEM; + } + dev->bar_mapped_size = size; + dev->dbs = dev->bar + NVME_REG_DBS; + + return 0; +} + static int nvme_configure_admin_queue(struct nvme_dev *dev) { int result; @@ -1318,6 +1392,10 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev) u64 cap = lo_hi_readq(dev->bar + NVME_REG_CAP); struct nvme_queue *nvmeq; + result = nvme_remap_bar(dev, db_bar_size(dev, 0)); + if (result < 0) + return result; + dev->subsystem = readl(dev->bar + NVME_REG_VS) >= NVME_VS(1, 1, 0) ? NVME_CAP_NSSRC(cap) : 0; @@ -1358,66 +1436,6 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev) return result; } -static bool nvme_should_reset(struct nvme_dev *dev, u32 csts) -{ - - /* If true, indicates loss of adapter communication, possibly by a - * NVMe Subsystem reset. - */ - bool nssro = dev->subsystem && (csts & NVME_CSTS_NSSRO); - - /* If there is a reset ongoing, we shouldn't reset again. */ - if (dev->ctrl.state == NVME_CTRL_RESETTING) - return false; - - /* We shouldn't reset unless the controller is on fatal error state - * _or_ if we lost the communication with it. - */ - if (!(csts & NVME_CSTS_CFS) && !nssro) - return false; - - /* If PCI error recovery process is happening, we cannot reset or - * the recovery mechanism will surely fail. - */ - if (pci_channel_offline(to_pci_dev(dev->dev))) - return false; - - return true; -} - -static void nvme_warn_reset(struct nvme_dev *dev, u32 csts) -{ - /* Read a config register to help see what died. */ - u16 pci_status; - int result; - - result = pci_read_config_word(to_pci_dev(dev->dev), PCI_STATUS, - &pci_status); - if (result == PCIBIOS_SUCCESSFUL) - dev_warn(dev->ctrl.device, - "controller is down; will reset: CSTS=0x%x, PCI_STATUS=0x%hx\n", - csts, pci_status); - else - dev_warn(dev->ctrl.device, - "controller is down; will reset: CSTS=0x%x, PCI_STATUS read failed (%d)\n", - csts, result); -} - -static void nvme_watchdog_timer(unsigned long data) -{ - struct nvme_dev *dev = (struct nvme_dev *)data; - u32 csts = readl(dev->bar + NVME_REG_CSTS); - - /* Skip controllers under certain specific conditions. */ - if (nvme_should_reset(dev, csts)) { - if (!nvme_reset(dev)) - nvme_warn_reset(dev, csts); - return; - } - - mod_timer(&dev->watchdog_timer, round_jiffies(jiffies + HZ)); -} - static int nvme_create_io_queues(struct nvme_dev *dev) { unsigned i, max; @@ -1514,16 +1532,168 @@ static inline void nvme_release_cmb(struct nvme_dev *dev) } } -static size_t db_bar_size(struct nvme_dev *dev, unsigned nr_io_queues) +static int nvme_set_host_mem(struct nvme_dev *dev, u32 bits) +{ + size_t len = dev->nr_host_mem_descs * sizeof(*dev->host_mem_descs); + struct nvme_command c; + u64 dma_addr; + int ret; + + dma_addr = dma_map_single(dev->dev, dev->host_mem_descs, len, + DMA_TO_DEVICE); + if (dma_mapping_error(dev->dev, dma_addr)) + return -ENOMEM; + + memset(&c, 0, sizeof(c)); + c.features.opcode = nvme_admin_set_features; + c.features.fid = cpu_to_le32(NVME_FEAT_HOST_MEM_BUF); + c.features.dword11 = cpu_to_le32(bits); + c.features.dword12 = cpu_to_le32(dev->host_mem_size >> + ilog2(dev->ctrl.page_size)); + c.features.dword13 = cpu_to_le32(lower_32_bits(dma_addr)); + c.features.dword14 = cpu_to_le32(upper_32_bits(dma_addr)); + c.features.dword15 = cpu_to_le32(dev->nr_host_mem_descs); + + ret = nvme_submit_sync_cmd(dev->ctrl.admin_q, &c, NULL, 0); + if (ret) { + dev_warn(dev->ctrl.device, + "failed to set host mem (err %d, flags %#x).\n", + ret, bits); + } + dma_unmap_single(dev->dev, dma_addr, len, DMA_TO_DEVICE); + return ret; +} + +static void nvme_free_host_mem(struct nvme_dev *dev) +{ + int i; + + for (i = 0; i < dev->nr_host_mem_descs; i++) { + struct nvme_host_mem_buf_desc *desc = &dev->host_mem_descs[i]; + size_t size = le32_to_cpu(desc->size) * dev->ctrl.page_size; + + dma_free_coherent(dev->dev, size, dev->host_mem_desc_bufs[i], + le64_to_cpu(desc->addr)); + } + + kfree(dev->host_mem_desc_bufs); + dev->host_mem_desc_bufs = NULL; + kfree(dev->host_mem_descs); + dev->host_mem_descs = NULL; +} + +static int nvme_alloc_host_mem(struct nvme_dev *dev, u64 min, u64 preferred) { - return 4096 + ((nr_io_queues + 1) * 8 * dev->db_stride); + struct nvme_host_mem_buf_desc *descs; + u32 chunk_size, max_entries, i = 0; + void **bufs; + u64 size, tmp; + + /* start big and work our way down */ + chunk_size = min(preferred, (u64)PAGE_SIZE << MAX_ORDER); +retry: + tmp = (preferred + chunk_size - 1); + do_div(tmp, chunk_size); + max_entries = tmp; + descs = kcalloc(max_entries, sizeof(*descs), GFP_KERNEL); + if (!descs) + goto out; + + bufs = kcalloc(max_entries, sizeof(*bufs), GFP_KERNEL); + if (!bufs) + goto out_free_descs; + + for (size = 0; size < preferred; size += chunk_size) { + u32 len = min_t(u64, chunk_size, preferred - size); + dma_addr_t dma_addr; + + bufs[i] = dma_alloc_attrs(dev->dev, len, &dma_addr, GFP_KERNEL, + DMA_ATTR_NO_KERNEL_MAPPING | DMA_ATTR_NO_WARN); + if (!bufs[i]) + break; + + descs[i].addr = cpu_to_le64(dma_addr); + descs[i].size = cpu_to_le32(len / dev->ctrl.page_size); + i++; + } + + if (!size || (min && size < min)) { + dev_warn(dev->ctrl.device, + "failed to allocate host memory buffer.\n"); + goto out_free_bufs; + } + + dev_info(dev->ctrl.device, + "allocated %lld MiB host memory buffer.\n", + size >> ilog2(SZ_1M)); + dev->nr_host_mem_descs = i; + dev->host_mem_size = size; + dev->host_mem_descs = descs; + dev->host_mem_desc_bufs = bufs; + return 0; + +out_free_bufs: + while (--i >= 0) { + size_t size = le32_to_cpu(descs[i].size) * dev->ctrl.page_size; + + dma_free_coherent(dev->dev, size, bufs[i], + le64_to_cpu(descs[i].addr)); + } + + kfree(bufs); +out_free_descs: + kfree(descs); +out: + /* try a smaller chunk size if we failed early */ + if (chunk_size >= PAGE_SIZE * 2 && (i == 0 || size < min)) { + chunk_size /= 2; + goto retry; + } + dev->host_mem_descs = NULL; + return -ENOMEM; +} + +static void nvme_setup_host_mem(struct nvme_dev *dev) +{ + u64 max = (u64)max_host_mem_size_mb * SZ_1M; + u64 preferred = (u64)dev->ctrl.hmpre * 4096; + u64 min = (u64)dev->ctrl.hmmin * 4096; + u32 enable_bits = NVME_HOST_MEM_ENABLE; + + preferred = min(preferred, max); + if (min > max) { + dev_warn(dev->ctrl.device, + "min host memory (%lld MiB) above limit (%d MiB).\n", + min >> ilog2(SZ_1M), max_host_mem_size_mb); + nvme_free_host_mem(dev); + return; + } + + /* + * If we already have a buffer allocated check if we can reuse it. + */ + if (dev->host_mem_descs) { + if (dev->host_mem_size >= min) + enable_bits |= NVME_HOST_MEM_RETURN; + else + nvme_free_host_mem(dev); + } + + if (!dev->host_mem_descs) { + if (nvme_alloc_host_mem(dev, min, preferred)) + return; + } + + if (nvme_set_host_mem(dev, enable_bits)) + nvme_free_host_mem(dev); } static int nvme_setup_io_queues(struct nvme_dev *dev) { struct nvme_queue *adminq = dev->queues[0]; struct pci_dev *pdev = to_pci_dev(dev->dev); - int result, nr_io_queues, size; + int result, nr_io_queues; + unsigned long size; nr_io_queues = num_online_cpus(); result = nvme_set_queue_count(&dev->ctrl, &nr_io_queues); @@ -1542,20 +1712,15 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) nvme_release_cmb(dev); } - size = db_bar_size(dev, nr_io_queues); - if (size > 8192) { - iounmap(dev->bar); - do { - dev->bar = ioremap(pci_resource_start(pdev, 0), size); - if (dev->bar) - break; - if (!--nr_io_queues) - return -ENOMEM; - size = db_bar_size(dev, nr_io_queues); - } while (1); - dev->dbs = dev->bar + 4096; - adminq->q_db = dev->dbs; - } + do { + size = db_bar_size(dev, nr_io_queues); + result = nvme_remap_bar(dev, size); + if (!result) + break; + if (!--nr_io_queues) + return -ENOMEM; + } while (1); + adminq->q_db = dev->dbs; /* Deregister the admin queue's interrupt */ pci_free_irq(pdev, 0, adminq); @@ -1586,7 +1751,7 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) return nvme_create_io_queues(dev); } -static void nvme_del_queue_end(struct request *req, int error) +static void nvme_del_queue_end(struct request *req, blk_status_t error) { struct nvme_queue *nvmeq = req->end_io_data; @@ -1594,7 +1759,7 @@ static void nvme_del_queue_end(struct request *req, int error) complete(&nvmeq->dev->ioq_wait); } -static void nvme_del_cq_end(struct request *req, int error) +static void nvme_del_cq_end(struct request *req, blk_status_t error) { struct nvme_queue *nvmeq = req->end_io_data; @@ -1799,13 +1964,12 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) bool dead = true; struct pci_dev *pdev = to_pci_dev(dev->dev); - del_timer_sync(&dev->watchdog_timer); - mutex_lock(&dev->shutdown_lock); if (pci_is_enabled(pdev)) { u32 csts = readl(dev->bar + NVME_REG_CSTS); - if (dev->ctrl.state == NVME_CTRL_LIVE) + if (dev->ctrl.state == NVME_CTRL_LIVE || + dev->ctrl.state == NVME_CTRL_RESETTING) nvme_start_freeze(&dev->ctrl); dead = !!((csts & NVME_CSTS_CFS) || !(csts & NVME_CSTS_RDY) || pdev->error_state != pci_channel_io_normal); @@ -1815,8 +1979,20 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) * Give the controller a chance to complete all entered requests if * doing a safe shutdown. */ - if (!dead && shutdown) - nvme_wait_freeze_timeout(&dev->ctrl, NVME_IO_TIMEOUT); + if (!dead) { + if (shutdown) + nvme_wait_freeze_timeout(&dev->ctrl, NVME_IO_TIMEOUT); + + /* + * If the controller is still alive tell it to stop using the + * host memory buffer. In theory the shutdown / reset should + * make sure that it doesn't access the host memoery anymore, + * but I'd rather be safe than sorry.. + */ + if (dev->host_mem_descs) + nvme_set_host_mem(dev, 0); + + } nvme_stop_queues(&dev->ctrl); queues = dev->online_queues - 1; @@ -1899,7 +2075,8 @@ static void nvme_remove_dead_ctrl(struct nvme_dev *dev, int status) static void nvme_reset_work(struct work_struct *work) { - struct nvme_dev *dev = container_of(work, struct nvme_dev, reset_work); + struct nvme_dev *dev = + container_of(work, struct nvme_dev, ctrl.reset_work); bool was_suspend = !!(dev->ctrl.ctrl_config & NVME_CC_SHN_NORMAL); int result = -ENODEV; @@ -1948,6 +2125,9 @@ static void nvme_reset_work(struct work_struct *work) "unable to allocate dma for dbbuf\n"); } + if (dev->ctrl.hmpre) + nvme_setup_host_mem(dev); + result = nvme_setup_io_queues(dev); if (result) goto out; @@ -1961,8 +2141,6 @@ static void nvme_reset_work(struct work_struct *work) if (dev->online_queues > 1) nvme_queue_async_events(&dev->ctrl); - mod_timer(&dev->watchdog_timer, round_jiffies(jiffies + HZ)); - /* * Keep the controller around but remove all namespaces if we don't have * any working I/O queue. @@ -2002,17 +2180,6 @@ static void nvme_remove_dead_ctrl_work(struct work_struct *work) nvme_put_ctrl(&dev->ctrl); } -static int nvme_reset(struct nvme_dev *dev) -{ - if (!dev->ctrl.admin_q || blk_queue_dying(dev->ctrl.admin_q)) - return -ENODEV; - if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RESETTING)) - return -EBUSY; - if (!queue_work(nvme_workq, &dev->reset_work)) - return -EBUSY; - return 0; -} - static int nvme_pci_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val) { *val = readl(to_nvme_dev(ctrl)->bar + off); @@ -2031,16 +2198,6 @@ static int nvme_pci_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val) return 0; } -static int nvme_pci_reset_ctrl(struct nvme_ctrl *ctrl) -{ - struct nvme_dev *dev = to_nvme_dev(ctrl); - int ret = nvme_reset(dev); - - if (!ret) - flush_work(&dev->reset_work); - return ret; -} - static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = { .name = "pcie", .module = THIS_MODULE, @@ -2048,7 +2205,6 @@ static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = { .reg_read32 = nvme_pci_reg_read32, .reg_write32 = nvme_pci_reg_write32, .reg_read64 = nvme_pci_reg_read64, - .reset_ctrl = nvme_pci_reset_ctrl, .free_ctrl = nvme_pci_free_ctrl, .submit_async_event = nvme_pci_submit_async_event, }; @@ -2060,8 +2216,7 @@ static int nvme_dev_map(struct nvme_dev *dev) if (pci_request_mem_regions(pdev, "nvme")) return -ENODEV; - dev->bar = ioremap(pci_resource_start(pdev, 0), 8192); - if (!dev->bar) + if (nvme_remap_bar(dev, NVME_REG_DBS + 4096)) goto release; return 0; @@ -2115,10 +2270,8 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (result) goto free; - INIT_WORK(&dev->reset_work, nvme_reset_work); + INIT_WORK(&dev->ctrl.reset_work, nvme_reset_work); INIT_WORK(&dev->remove_work, nvme_remove_dead_ctrl_work); - setup_timer(&dev->watchdog_timer, nvme_watchdog_timer, - (unsigned long)dev); mutex_init(&dev->shutdown_lock); init_completion(&dev->ioq_wait); @@ -2136,7 +2289,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RESETTING); dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev)); - queue_work(nvme_workq, &dev->reset_work); + queue_work(nvme_wq, &dev->ctrl.reset_work); return 0; release_pools: @@ -2157,7 +2310,7 @@ static void nvme_reset_notify(struct pci_dev *pdev, bool prepare) if (prepare) nvme_dev_disable(dev, false); else - nvme_reset(dev); + nvme_reset_ctrl(&dev->ctrl); } static void nvme_shutdown(struct pci_dev *pdev) @@ -2177,7 +2330,7 @@ static void nvme_remove(struct pci_dev *pdev) nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING); - cancel_work_sync(&dev->reset_work); + cancel_work_sync(&dev->ctrl.reset_work); pci_set_drvdata(pdev, NULL); if (!pci_device_is_present(pdev)) { @@ -2185,9 +2338,10 @@ static void nvme_remove(struct pci_dev *pdev) nvme_dev_disable(dev, false); } - flush_work(&dev->reset_work); + flush_work(&dev->ctrl.reset_work); nvme_uninit_ctrl(&dev->ctrl); nvme_dev_disable(dev, true); + nvme_free_host_mem(dev); nvme_dev_remove_admin(dev); nvme_free_queues(dev, 0); nvme_release_prp_pools(dev); @@ -2228,7 +2382,7 @@ static int nvme_resume(struct device *dev) struct pci_dev *pdev = to_pci_dev(dev); struct nvme_dev *ndev = pci_get_drvdata(pdev); - nvme_reset(ndev); + nvme_reset_ctrl(&ndev->ctrl); return 0; } #endif @@ -2267,7 +2421,7 @@ static pci_ers_result_t nvme_slot_reset(struct pci_dev *pdev) dev_info(dev->ctrl.device, "restart after slot reset\n"); pci_restore_state(pdev); - nvme_reset(dev); + nvme_reset_ctrl(&dev->ctrl); return PCI_ERS_RESULT_RECOVERED; } @@ -2323,22 +2477,12 @@ static struct pci_driver nvme_driver = { static int __init nvme_init(void) { - int result; - - nvme_workq = alloc_workqueue("nvme", WQ_UNBOUND | WQ_MEM_RECLAIM, 0); - if (!nvme_workq) - return -ENOMEM; - - result = pci_register_driver(&nvme_driver); - if (result) - destroy_workqueue(nvme_workq); - return result; + return pci_register_driver(&nvme_driver); } static void __exit nvme_exit(void) { pci_unregister_driver(&nvme_driver); - destroy_workqueue(nvme_workq); _nvme_check_size(); } diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 24397d306d53..6d4119dfbdaa 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -48,7 +48,7 @@ */ #define NVME_RDMA_NR_AEN_COMMANDS 1 #define NVME_RDMA_AQ_BLKMQ_DEPTH \ - (NVMF_AQ_DEPTH - NVME_RDMA_NR_AEN_COMMANDS) + (NVME_AQ_DEPTH - NVME_RDMA_NR_AEN_COMMANDS) struct nvme_rdma_device { struct ib_device *dev; @@ -80,10 +80,8 @@ struct nvme_rdma_request { }; enum nvme_rdma_queue_flags { - NVME_RDMA_Q_CONNECTED = (1 << 0), - NVME_RDMA_IB_QUEUE_ALLOCATED = (1 << 1), - NVME_RDMA_Q_DELETING = (1 << 2), - NVME_RDMA_Q_LIVE = (1 << 3), + NVME_RDMA_Q_LIVE = 0, + NVME_RDMA_Q_DELETING = 1, }; struct nvme_rdma_queue { @@ -103,9 +101,6 @@ struct nvme_rdma_queue { }; struct nvme_rdma_ctrl { - /* read and written in the hot path */ - spinlock_t lock; - /* read only in the hot path */ struct nvme_rdma_queue *queues; u32 queue_count; @@ -113,7 +108,6 @@ struct nvme_rdma_ctrl { /* other member variables */ struct blk_mq_tag_set tag_set; struct work_struct delete_work; - struct work_struct reset_work; struct work_struct err_work; struct nvme_rdma_qe async_event_sqe; @@ -145,8 +139,6 @@ static DEFINE_MUTEX(device_list_mutex); static LIST_HEAD(nvme_rdma_ctrl_list); static DEFINE_MUTEX(nvme_rdma_ctrl_mutex); -static struct workqueue_struct *nvme_rdma_wq; - /* * Disabling this option makes small I/O goes faster, but is fundamentally * unsafe. With it turned off we will have to register a global rkey that @@ -301,10 +293,12 @@ out: return ret; } -static void __nvme_rdma_exit_request(struct nvme_rdma_ctrl *ctrl, - struct request *rq, unsigned int queue_idx) +static void nvme_rdma_exit_request(struct blk_mq_tag_set *set, + struct request *rq, unsigned int hctx_idx) { + struct nvme_rdma_ctrl *ctrl = set->driver_data; struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq); + int queue_idx = (set == &ctrl->tag_set) ? hctx_idx + 1 : 0; struct nvme_rdma_queue *queue = &ctrl->queues[queue_idx]; struct nvme_rdma_device *dev = queue->device; @@ -315,22 +309,13 @@ static void __nvme_rdma_exit_request(struct nvme_rdma_ctrl *ctrl, DMA_TO_DEVICE); } -static void nvme_rdma_exit_request(struct blk_mq_tag_set *set, - struct request *rq, unsigned int hctx_idx) -{ - return __nvme_rdma_exit_request(set->driver_data, rq, hctx_idx + 1); -} - -static void nvme_rdma_exit_admin_request(struct blk_mq_tag_set *set, - struct request *rq, unsigned int hctx_idx) -{ - return __nvme_rdma_exit_request(set->driver_data, rq, 0); -} - -static int __nvme_rdma_init_request(struct nvme_rdma_ctrl *ctrl, - struct request *rq, unsigned int queue_idx) +static int nvme_rdma_init_request(struct blk_mq_tag_set *set, + struct request *rq, unsigned int hctx_idx, + unsigned int numa_node) { + struct nvme_rdma_ctrl *ctrl = set->driver_data; struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq); + int queue_idx = (set == &ctrl->tag_set) ? hctx_idx + 1 : 0; struct nvme_rdma_queue *queue = &ctrl->queues[queue_idx]; struct nvme_rdma_device *dev = queue->device; struct ib_device *ibdev = dev->dev; @@ -358,20 +343,6 @@ out_free_qe: return -ENOMEM; } -static int nvme_rdma_init_request(struct blk_mq_tag_set *set, - struct request *rq, unsigned int hctx_idx, - unsigned int numa_node) -{ - return __nvme_rdma_init_request(set->driver_data, rq, hctx_idx + 1); -} - -static int nvme_rdma_init_admin_request(struct blk_mq_tag_set *set, - struct request *rq, unsigned int hctx_idx, - unsigned int numa_node) -{ - return __nvme_rdma_init_request(set->driver_data, rq, 0); -} - static int nvme_rdma_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, unsigned int hctx_idx) { @@ -469,9 +440,6 @@ static void nvme_rdma_destroy_queue_ib(struct nvme_rdma_queue *queue) struct nvme_rdma_device *dev; struct ib_device *ibdev; - if (!test_and_clear_bit(NVME_RDMA_IB_QUEUE_ALLOCATED, &queue->flags)) - return; - dev = queue->device; ibdev = dev->dev; rdma_destroy_qp(queue->cm_id); @@ -483,17 +451,21 @@ static void nvme_rdma_destroy_queue_ib(struct nvme_rdma_queue *queue) nvme_rdma_dev_put(dev); } -static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue, - struct nvme_rdma_device *dev) +static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue) { - struct ib_device *ibdev = dev->dev; + struct ib_device *ibdev; const int send_wr_factor = 3; /* MR, SEND, INV */ const int cq_factor = send_wr_factor + 1; /* + RECV */ int comp_vector, idx = nvme_rdma_queue_idx(queue); - int ret; - queue->device = dev; + queue->device = nvme_rdma_find_get_device(queue->cm_id); + if (!queue->device) { + dev_err(queue->cm_id->device->dev.parent, + "no client data found!\n"); + return -ECONNREFUSED; + } + ibdev = queue->device->dev; /* * The admin queue is barely used once the controller is live, so don't @@ -506,12 +478,12 @@ static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue, /* +1 for ib_stop_cq */ - queue->ib_cq = ib_alloc_cq(dev->dev, queue, - cq_factor * queue->queue_size + 1, comp_vector, - IB_POLL_SOFTIRQ); + queue->ib_cq = ib_alloc_cq(ibdev, queue, + cq_factor * queue->queue_size + 1, + comp_vector, IB_POLL_SOFTIRQ); if (IS_ERR(queue->ib_cq)) { ret = PTR_ERR(queue->ib_cq); - goto out; + goto out_put_dev; } ret = nvme_rdma_create_qp(queue, send_wr_factor); @@ -524,7 +496,6 @@ static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue, ret = -ENOMEM; goto out_destroy_qp; } - set_bit(NVME_RDMA_IB_QUEUE_ALLOCATED, &queue->flags); return 0; @@ -532,7 +503,8 @@ out_destroy_qp: ib_destroy_qp(queue->qp); out_destroy_ib_cq: ib_free_cq(queue->ib_cq); -out: +out_put_dev: + nvme_rdma_dev_put(queue->device); return ret; } @@ -583,12 +555,10 @@ static int nvme_rdma_init_queue(struct nvme_rdma_ctrl *ctrl, } clear_bit(NVME_RDMA_Q_DELETING, &queue->flags); - set_bit(NVME_RDMA_Q_CONNECTED, &queue->flags); return 0; out_destroy_cm_id: - nvme_rdma_destroy_queue_ib(queue); rdma_destroy_id(queue->cm_id); return ret; } @@ -718,11 +688,11 @@ static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl) if (nvmf_should_reconnect(&ctrl->ctrl)) { dev_info(ctrl->ctrl.device, "Reconnecting in %d seconds...\n", ctrl->ctrl.opts->reconnect_delay); - queue_delayed_work(nvme_rdma_wq, &ctrl->reconnect_work, + queue_delayed_work(nvme_wq, &ctrl->reconnect_work, ctrl->ctrl.opts->reconnect_delay * HZ); } else { dev_info(ctrl->ctrl.device, "Removing controller...\n"); - queue_work(nvme_rdma_wq, &ctrl->delete_work); + queue_work(nvme_wq, &ctrl->delete_work); } } @@ -733,7 +703,7 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work) bool changed; int ret; - ++ctrl->ctrl.opts->nr_reconnects; + ++ctrl->ctrl.nr_reconnects; if (ctrl->queue_count > 1) { nvme_rdma_free_io_queues(ctrl); @@ -749,7 +719,7 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work) if (ret) goto requeue; - ret = nvme_rdma_init_queue(ctrl, 0, NVMF_AQ_DEPTH); + ret = nvme_rdma_init_queue(ctrl, 0, NVME_AQ_DEPTH); if (ret) goto requeue; @@ -777,7 +747,7 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work) changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE); WARN_ON_ONCE(!changed); - ctrl->ctrl.opts->nr_reconnects = 0; + ctrl->ctrl.nr_reconnects = 0; if (ctrl->queue_count > 1) { nvme_queue_scan(&ctrl->ctrl); @@ -790,7 +760,7 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work) requeue: dev_info(ctrl->ctrl.device, "Failed reconnect attempt %d\n", - ctrl->ctrl.opts->nr_reconnects); + ctrl->ctrl.nr_reconnects); nvme_rdma_reconnect_or_remove(ctrl); } @@ -802,10 +772,8 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work) nvme_stop_keep_alive(&ctrl->ctrl); - for (i = 0; i < ctrl->queue_count; i++) { - clear_bit(NVME_RDMA_Q_CONNECTED, &ctrl->queues[i].flags); + for (i = 0; i < ctrl->queue_count; i++) clear_bit(NVME_RDMA_Q_LIVE, &ctrl->queues[i].flags); - } if (ctrl->queue_count > 1) nvme_stop_queues(&ctrl->ctrl); @@ -833,7 +801,7 @@ static void nvme_rdma_error_recovery(struct nvme_rdma_ctrl *ctrl) if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RECONNECTING)) return; - queue_work(nvme_rdma_wq, &ctrl->err_work); + queue_work(nvme_wq, &ctrl->err_work); } static void nvme_rdma_wr_error(struct ib_cq *cq, struct ib_wc *wc, @@ -1278,21 +1246,11 @@ static int nvme_rdma_conn_rejected(struct nvme_rdma_queue *queue, static int nvme_rdma_addr_resolved(struct nvme_rdma_queue *queue) { - struct nvme_rdma_device *dev; int ret; - dev = nvme_rdma_find_get_device(queue->cm_id); - if (!dev) { - dev_err(queue->cm_id->device->dev.parent, - "no client data found!\n"); - return -ECONNREFUSED; - } - - ret = nvme_rdma_create_queue_ib(queue, dev); - if (ret) { - nvme_rdma_dev_put(dev); - goto out; - } + ret = nvme_rdma_create_queue_ib(queue); + if (ret) + return ret; ret = rdma_resolve_route(queue->cm_id, NVME_RDMA_CONNECT_TIMEOUT_MS); if (ret) { @@ -1306,7 +1264,6 @@ static int nvme_rdma_addr_resolved(struct nvme_rdma_queue *queue) out_destroy_queue: nvme_rdma_destroy_queue_ib(queue); -out: return ret; } @@ -1334,8 +1291,8 @@ static int nvme_rdma_route_resolved(struct nvme_rdma_queue *queue) * specified by the Fabrics standard. */ if (priv.qid == 0) { - priv.hrqsize = cpu_to_le16(NVMF_AQ_DEPTH); - priv.hsqsize = cpu_to_le16(NVMF_AQ_DEPTH - 1); + priv.hrqsize = cpu_to_le16(NVME_AQ_DEPTH); + priv.hsqsize = cpu_to_le16(NVME_AQ_DEPTH - 1); } else { /* * current interpretation of the fabrics spec @@ -1383,12 +1340,14 @@ static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id, complete(&queue->cm_done); return 0; case RDMA_CM_EVENT_REJECTED: + nvme_rdma_destroy_queue_ib(queue); cm_error = nvme_rdma_conn_rejected(queue, ev); break; - case RDMA_CM_EVENT_ADDR_ERROR: case RDMA_CM_EVENT_ROUTE_ERROR: case RDMA_CM_EVENT_CONNECT_ERROR: case RDMA_CM_EVENT_UNREACHABLE: + nvme_rdma_destroy_queue_ib(queue); + case RDMA_CM_EVENT_ADDR_ERROR: dev_dbg(queue->ctrl->ctrl.device, "CM error event %d\n", ev->event); cm_error = -ECONNRESET; @@ -1435,8 +1394,8 @@ nvme_rdma_timeout(struct request *rq, bool reserved) /* * We cannot accept any other command until the Connect command has completed. */ -static inline int nvme_rdma_queue_is_ready(struct nvme_rdma_queue *queue, - struct request *rq) +static inline blk_status_t +nvme_rdma_queue_is_ready(struct nvme_rdma_queue *queue, struct request *rq) { if (unlikely(!test_bit(NVME_RDMA_Q_LIVE, &queue->flags))) { struct nvme_command *cmd = nvme_req(rq)->cmd; @@ -1452,16 +1411,15 @@ static inline int nvme_rdma_queue_is_ready(struct nvme_rdma_queue *queue, * failover. */ if (queue->ctrl->ctrl.state == NVME_CTRL_RECONNECTING) - return -EIO; - else - return -EAGAIN; + return BLK_STS_IOERR; + return BLK_STS_RESOURCE; /* try again later */ } } return 0; } -static int nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, +static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { struct nvme_ns *ns = hctx->queue->queuedata; @@ -1472,28 +1430,29 @@ static int nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, struct nvme_command *c = sqe->data; bool flush = false; struct ib_device *dev; - int ret; + blk_status_t ret; + int err; WARN_ON_ONCE(rq->tag < 0); ret = nvme_rdma_queue_is_ready(queue, rq); if (unlikely(ret)) - goto err; + return ret; dev = queue->device->dev; ib_dma_sync_single_for_cpu(dev, sqe->dma, sizeof(struct nvme_command), DMA_TO_DEVICE); ret = nvme_setup_cmd(ns, rq, c); - if (ret != BLK_MQ_RQ_QUEUE_OK) + if (ret) return ret; blk_mq_start_request(rq); - ret = nvme_rdma_map_data(queue, rq, c); - if (ret < 0) { + err = nvme_rdma_map_data(queue, rq, c); + if (err < 0) { dev_err(queue->ctrl->ctrl.device, - "Failed to map data (%d)\n", ret); + "Failed to map data (%d)\n", err); nvme_cleanup_cmd(rq); goto err; } @@ -1503,17 +1462,18 @@ static int nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, if (req_op(rq) == REQ_OP_FLUSH) flush = true; - ret = nvme_rdma_post_send(queue, sqe, req->sge, req->num_sge, + err = nvme_rdma_post_send(queue, sqe, req->sge, req->num_sge, req->mr->need_inval ? &req->reg_wr.wr : NULL, flush); - if (ret) { + if (err) { nvme_rdma_unmap_data(queue, rq); goto err; } - return BLK_MQ_RQ_QUEUE_OK; + return BLK_STS_OK; err: - return (ret == -ENOMEM || ret == -EAGAIN) ? - BLK_MQ_RQ_QUEUE_BUSY : BLK_MQ_RQ_QUEUE_ERROR; + if (err == -ENOMEM || err == -EAGAIN) + return BLK_STS_RESOURCE; + return BLK_STS_IOERR; } static int nvme_rdma_poll(struct blk_mq_hw_ctx *hctx, unsigned int tag) @@ -1523,7 +1483,6 @@ static int nvme_rdma_poll(struct blk_mq_hw_ctx *hctx, unsigned int tag) struct ib_wc wc; int found = 0; - ib_req_notify_cq(cq, IB_CQ_NEXT_COMP); while (ib_poll_cq(cq, 1, &wc) > 0) { struct ib_cqe *cqe = wc.wr_cqe; @@ -1560,8 +1519,8 @@ static const struct blk_mq_ops nvme_rdma_mq_ops = { static const struct blk_mq_ops nvme_rdma_admin_mq_ops = { .queue_rq = nvme_rdma_queue_rq, .complete = nvme_rdma_complete_rq, - .init_request = nvme_rdma_init_admin_request, - .exit_request = nvme_rdma_exit_admin_request, + .init_request = nvme_rdma_init_request, + .exit_request = nvme_rdma_exit_request, .reinit_request = nvme_rdma_reinit_request, .init_hctx = nvme_rdma_init_admin_hctx, .timeout = nvme_rdma_timeout, @@ -1571,7 +1530,7 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl) { int error; - error = nvme_rdma_init_queue(ctrl, 0, NVMF_AQ_DEPTH); + error = nvme_rdma_init_queue(ctrl, 0, NVME_AQ_DEPTH); if (error) return error; @@ -1672,7 +1631,7 @@ static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl) nvme_rdma_free_io_queues(ctrl); } - if (test_bit(NVME_RDMA_Q_CONNECTED, &ctrl->queues[0].flags)) + if (test_bit(NVME_RDMA_Q_LIVE, &ctrl->queues[0].flags)) nvme_shutdown_ctrl(&ctrl->ctrl); blk_mq_stop_hw_queues(ctrl->ctrl.admin_q); @@ -1709,7 +1668,7 @@ static int __nvme_rdma_del_ctrl(struct nvme_rdma_ctrl *ctrl) if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING)) return -EBUSY; - if (!queue_work(nvme_rdma_wq, &ctrl->delete_work)) + if (!queue_work(nvme_wq, &ctrl->delete_work)) return -EBUSY; return 0; @@ -1743,8 +1702,8 @@ static void nvme_rdma_remove_ctrl_work(struct work_struct *work) static void nvme_rdma_reset_ctrl_work(struct work_struct *work) { - struct nvme_rdma_ctrl *ctrl = container_of(work, - struct nvme_rdma_ctrl, reset_work); + struct nvme_rdma_ctrl *ctrl = + container_of(work, struct nvme_rdma_ctrl, ctrl.reset_work); int ret; bool changed; @@ -1785,22 +1744,7 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work) del_dead_ctrl: /* Deleting this dead controller... */ dev_warn(ctrl->ctrl.device, "Removing after reset failure\n"); - WARN_ON(!queue_work(nvme_rdma_wq, &ctrl->delete_work)); -} - -static int nvme_rdma_reset_ctrl(struct nvme_ctrl *nctrl) -{ - struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl); - - if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING)) - return -EBUSY; - - if (!queue_work(nvme_rdma_wq, &ctrl->reset_work)) - return -EBUSY; - - flush_work(&ctrl->reset_work); - - return 0; + WARN_ON(!queue_work(nvme_wq, &ctrl->delete_work)); } static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = { @@ -1810,11 +1754,9 @@ static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = { .reg_read32 = nvmf_reg_read32, .reg_read64 = nvmf_reg_read64, .reg_write32 = nvmf_reg_write32, - .reset_ctrl = nvme_rdma_reset_ctrl, .free_ctrl = nvme_rdma_free_ctrl, .submit_async_event = nvme_rdma_submit_async_event, .delete_ctrl = nvme_rdma_del_ctrl, - .get_subsysnqn = nvmf_get_subsysnqn, .get_address = nvmf_get_address, }; @@ -1919,8 +1861,7 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev, nvme_rdma_reconnect_ctrl_work); INIT_WORK(&ctrl->err_work, nvme_rdma_error_recovery_work); INIT_WORK(&ctrl->delete_work, nvme_rdma_del_ctrl_work); - INIT_WORK(&ctrl->reset_work, nvme_rdma_reset_ctrl_work); - spin_lock_init(&ctrl->lock); + INIT_WORK(&ctrl->ctrl.reset_work, nvme_rdma_reset_ctrl_work); ctrl->queue_count = opts->nr_io_queues + 1; /* +1 for admin queue */ ctrl->ctrl.sqsize = opts->queue_size - 1; @@ -1939,12 +1880,14 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev, /* sanity check icdoff */ if (ctrl->ctrl.icdoff) { dev_err(ctrl->ctrl.device, "icdoff is not supported!\n"); + ret = -EINVAL; goto out_remove_admin_queue; } /* sanity check keyed sgls */ if (!(ctrl->ctrl.sgls & (1 << 20))) { dev_err(ctrl->ctrl.device, "Mandatory keyed sgls are not support\n"); + ret = -EINVAL; goto out_remove_admin_queue; } @@ -2033,7 +1976,7 @@ static void nvme_rdma_remove_one(struct ib_device *ib_device, void *client_data) } mutex_unlock(&nvme_rdma_ctrl_mutex); - flush_workqueue(nvme_rdma_wq); + flush_workqueue(nvme_wq); } static struct ib_client nvme_rdma_ib_client = { @@ -2046,13 +1989,9 @@ static int __init nvme_rdma_init_module(void) { int ret; - nvme_rdma_wq = create_workqueue("nvme_rdma_wq"); - if (!nvme_rdma_wq) - return -ENOMEM; - ret = ib_register_client(&nvme_rdma_ib_client); if (ret) - goto err_destroy_wq; + return ret; ret = nvmf_register_transport(&nvme_rdma_transport); if (ret) @@ -2062,8 +2001,6 @@ static int __init nvme_rdma_init_module(void) err_unreg_client: ib_unregister_client(&nvme_rdma_ib_client); -err_destroy_wq: - destroy_workqueue(nvme_rdma_wq); return ret; } @@ -2071,7 +2008,6 @@ static void __exit nvme_rdma_cleanup_module(void) { nvmf_unregister_transport(&nvme_rdma_transport); ib_unregister_client(&nvme_rdma_ib_client); - destroy_workqueue(nvme_rdma_wq); } module_init(nvme_rdma_init_module); diff --git a/drivers/nvme/host/scsi.c b/drivers/nvme/host/scsi.c deleted file mode 100644 index 1f7671e631dd..000000000000 --- a/drivers/nvme/host/scsi.c +++ /dev/null @@ -1,2460 +0,0 @@ -/* - * NVM Express device driver - * Copyright (c) 2011-2014, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope 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. - */ - -/* - * Refer to the SCSI-NVMe Translation spec for details on how - * each command is translated. - */ - -#include <linux/bio.h> -#include <linux/bitops.h> -#include <linux/blkdev.h> -#include <linux/compat.h> -#include <linux/delay.h> -#include <linux/errno.h> -#include <linux/fs.h> -#include <linux/genhd.h> -#include <linux/idr.h> -#include <linux/init.h> -#include <linux/interrupt.h> -#include <linux/io.h> -#include <linux/kdev_t.h> -#include <linux/kthread.h> -#include <linux/kernel.h> -#include <linux/mm.h> -#include <linux/module.h> -#include <linux/moduleparam.h> -#include <linux/pci.h> -#include <linux/poison.h> -#include <linux/sched.h> -#include <linux/slab.h> -#include <linux/types.h> -#include <asm/unaligned.h> -#include <scsi/sg.h> -#include <scsi/scsi.h> -#include <scsi/scsi_request.h> - -#include "nvme.h" - -static int sg_version_num = 30534; /* 2 digits for each component */ - -/* VPD Page Codes */ -#define VPD_SUPPORTED_PAGES 0x00 -#define VPD_SERIAL_NUMBER 0x80 -#define VPD_DEVICE_IDENTIFIERS 0x83 -#define VPD_EXTENDED_INQUIRY 0x86 -#define VPD_BLOCK_LIMITS 0xB0 -#define VPD_BLOCK_DEV_CHARACTERISTICS 0xB1 - -/* format unit paramter list offsets */ -#define FORMAT_UNIT_SHORT_PARM_LIST_LEN 4 -#define FORMAT_UNIT_LONG_PARM_LIST_LEN 8 -#define FORMAT_UNIT_PROT_INT_OFFSET 3 -#define FORMAT_UNIT_PROT_FIELD_USAGE_OFFSET 0 -#define FORMAT_UNIT_PROT_FIELD_USAGE_MASK 0x07 - -/* Misc. defines */ -#define FIXED_SENSE_DATA 0x70 -#define DESC_FORMAT_SENSE_DATA 0x72 -#define FIXED_SENSE_DATA_ADD_LENGTH 10 -#define LUN_ENTRY_SIZE 8 -#define LUN_DATA_HEADER_SIZE 8 -#define ALL_LUNS_RETURNED 0x02 -#define ALL_WELL_KNOWN_LUNS_RETURNED 0x01 -#define RESTRICTED_LUNS_RETURNED 0x00 -#define DOWNLOAD_SAVE_ACTIVATE 0x05 -#define DOWNLOAD_SAVE_DEFER_ACTIVATE 0x0E -#define ACTIVATE_DEFERRED_MICROCODE 0x0F -#define FORMAT_UNIT_IMMED_MASK 0x2 -#define FORMAT_UNIT_IMMED_OFFSET 1 -#define KELVIN_TEMP_FACTOR 273 -#define FIXED_FMT_SENSE_DATA_SIZE 18 -#define DESC_FMT_SENSE_DATA_SIZE 8 - -/* SCSI/NVMe defines and bit masks */ -#define INQ_STANDARD_INQUIRY_PAGE 0x00 -#define INQ_SUPPORTED_VPD_PAGES_PAGE 0x00 -#define INQ_UNIT_SERIAL_NUMBER_PAGE 0x80 -#define INQ_DEVICE_IDENTIFICATION_PAGE 0x83 -#define INQ_EXTENDED_INQUIRY_DATA_PAGE 0x86 -#define INQ_BDEV_LIMITS_PAGE 0xB0 -#define INQ_BDEV_CHARACTERISTICS_PAGE 0xB1 -#define INQ_SERIAL_NUMBER_LENGTH 0x14 -#define INQ_NUM_SUPPORTED_VPD_PAGES 6 -#define VERSION_SPC_4 0x06 -#define ACA_UNSUPPORTED 0 -#define STANDARD_INQUIRY_LENGTH 36 -#define ADDITIONAL_STD_INQ_LENGTH 31 -#define EXTENDED_INQUIRY_DATA_PAGE_LENGTH 0x3C -#define RESERVED_FIELD 0 - -/* Mode Sense/Select defines */ -#define MODE_PAGE_INFO_EXCEP 0x1C -#define MODE_PAGE_CACHING 0x08 -#define MODE_PAGE_CONTROL 0x0A -#define MODE_PAGE_POWER_CONDITION 0x1A -#define MODE_PAGE_RETURN_ALL 0x3F -#define MODE_PAGE_BLK_DES_LEN 0x08 -#define MODE_PAGE_LLBAA_BLK_DES_LEN 0x10 -#define MODE_PAGE_CACHING_LEN 0x14 -#define MODE_PAGE_CONTROL_LEN 0x0C -#define MODE_PAGE_POW_CND_LEN 0x28 -#define MODE_PAGE_INF_EXC_LEN 0x0C -#define MODE_PAGE_ALL_LEN 0x54 -#define MODE_SENSE6_MPH_SIZE 4 -#define MODE_SENSE_PAGE_CONTROL_MASK 0xC0 -#define MODE_SENSE_PAGE_CODE_OFFSET 2 -#define MODE_SENSE_PAGE_CODE_MASK 0x3F -#define MODE_SENSE_LLBAA_MASK 0x10 -#define MODE_SENSE_LLBAA_SHIFT 4 -#define MODE_SENSE_DBD_MASK 8 -#define MODE_SENSE_DBD_SHIFT 3 -#define MODE_SENSE10_MPH_SIZE 8 -#define MODE_SELECT_CDB_PAGE_FORMAT_MASK 0x10 -#define MODE_SELECT_CDB_SAVE_PAGES_MASK 0x1 -#define MODE_SELECT_6_BD_OFFSET 3 -#define MODE_SELECT_10_BD_OFFSET 6 -#define MODE_SELECT_10_LLBAA_OFFSET 4 -#define MODE_SELECT_10_LLBAA_MASK 1 -#define MODE_SELECT_6_MPH_SIZE 4 -#define MODE_SELECT_10_MPH_SIZE 8 -#define CACHING_MODE_PAGE_WCE_MASK 0x04 -#define MODE_SENSE_BLK_DESC_ENABLED 0 -#define MODE_SENSE_BLK_DESC_COUNT 1 -#define MODE_SELECT_PAGE_CODE_MASK 0x3F -#define SHORT_DESC_BLOCK 8 -#define LONG_DESC_BLOCK 16 -#define MODE_PAGE_POW_CND_LEN_FIELD 0x26 -#define MODE_PAGE_INF_EXC_LEN_FIELD 0x0A -#define MODE_PAGE_CACHING_LEN_FIELD 0x12 -#define MODE_PAGE_CONTROL_LEN_FIELD 0x0A -#define MODE_SENSE_PC_CURRENT_VALUES 0 - -/* Log Sense defines */ -#define LOG_PAGE_SUPPORTED_LOG_PAGES_PAGE 0x00 -#define LOG_PAGE_SUPPORTED_LOG_PAGES_LENGTH 0x07 -#define LOG_PAGE_INFORMATIONAL_EXCEPTIONS_PAGE 0x2F -#define LOG_PAGE_TEMPERATURE_PAGE 0x0D -#define LOG_SENSE_CDB_SP_NOT_ENABLED 0 -#define LOG_SENSE_CDB_PC_MASK 0xC0 -#define LOG_SENSE_CDB_PC_SHIFT 6 -#define LOG_SENSE_CDB_PC_CUMULATIVE_VALUES 1 -#define LOG_SENSE_CDB_PAGE_CODE_MASK 0x3F -#define REMAINING_INFO_EXCP_PAGE_LENGTH 0x8 -#define LOG_INFO_EXCP_PAGE_LENGTH 0xC -#define REMAINING_TEMP_PAGE_LENGTH 0xC -#define LOG_TEMP_PAGE_LENGTH 0x10 -#define LOG_TEMP_UNKNOWN 0xFF -#define SUPPORTED_LOG_PAGES_PAGE_LENGTH 0x3 - -/* Read Capacity defines */ -#define READ_CAP_10_RESP_SIZE 8 -#define READ_CAP_16_RESP_SIZE 32 - -/* NVMe Namespace and Command Defines */ -#define BYTES_TO_DWORDS 4 -#define NVME_MAX_FIRMWARE_SLOT 7 - -/* Report LUNs defines */ -#define REPORT_LUNS_FIRST_LUN_OFFSET 8 - -/* SCSI ADDITIONAL SENSE Codes */ - -#define SCSI_ASC_NO_SENSE 0x00 -#define SCSI_ASC_PERIPHERAL_DEV_WRITE_FAULT 0x03 -#define SCSI_ASC_LUN_NOT_READY 0x04 -#define SCSI_ASC_WARNING 0x0B -#define SCSI_ASC_LOG_BLOCK_GUARD_CHECK_FAILED 0x10 -#define SCSI_ASC_LOG_BLOCK_APPTAG_CHECK_FAILED 0x10 -#define SCSI_ASC_LOG_BLOCK_REFTAG_CHECK_FAILED 0x10 -#define SCSI_ASC_UNRECOVERED_READ_ERROR 0x11 -#define SCSI_ASC_MISCOMPARE_DURING_VERIFY 0x1D -#define SCSI_ASC_ACCESS_DENIED_INVALID_LUN_ID 0x20 -#define SCSI_ASC_ILLEGAL_COMMAND 0x20 -#define SCSI_ASC_ILLEGAL_BLOCK 0x21 -#define SCSI_ASC_INVALID_CDB 0x24 -#define SCSI_ASC_INVALID_LUN 0x25 -#define SCSI_ASC_INVALID_PARAMETER 0x26 -#define SCSI_ASC_FORMAT_COMMAND_FAILED 0x31 -#define SCSI_ASC_INTERNAL_TARGET_FAILURE 0x44 - -/* SCSI ADDITIONAL SENSE Code Qualifiers */ - -#define SCSI_ASCQ_CAUSE_NOT_REPORTABLE 0x00 -#define SCSI_ASCQ_FORMAT_COMMAND_FAILED 0x01 -#define SCSI_ASCQ_LOG_BLOCK_GUARD_CHECK_FAILED 0x01 -#define SCSI_ASCQ_LOG_BLOCK_APPTAG_CHECK_FAILED 0x02 -#define SCSI_ASCQ_LOG_BLOCK_REFTAG_CHECK_FAILED 0x03 -#define SCSI_ASCQ_FORMAT_IN_PROGRESS 0x04 -#define SCSI_ASCQ_POWER_LOSS_EXPECTED 0x08 -#define SCSI_ASCQ_INVALID_LUN_ID 0x09 - -/* copied from drivers/usb/gadget/function/storage_common.h */ -static inline u32 get_unaligned_be24(u8 *buf) -{ - return 0xffffff & (u32) get_unaligned_be32(buf - 1); -} - -/* Struct to gather data that needs to be extracted from a SCSI CDB. - Not conforming to any particular CDB variant, but compatible with all. */ - -struct nvme_trans_io_cdb { - u8 fua; - u8 prot_info; - u64 lba; - u32 xfer_len; -}; - - -/* Internal Helper Functions */ - - -/* Copy data to userspace memory */ - -static int nvme_trans_copy_to_user(struct sg_io_hdr *hdr, void *from, - unsigned long n) -{ - int i; - void *index = from; - size_t remaining = n; - size_t xfer_len; - - if (hdr->iovec_count > 0) { - struct sg_iovec sgl; - - for (i = 0; i < hdr->iovec_count; i++) { - if (copy_from_user(&sgl, hdr->dxferp + - i * sizeof(struct sg_iovec), - sizeof(struct sg_iovec))) - return -EFAULT; - xfer_len = min(remaining, sgl.iov_len); - if (copy_to_user(sgl.iov_base, index, xfer_len)) - return -EFAULT; - - index += xfer_len; - remaining -= xfer_len; - if (remaining == 0) - break; - } - return 0; - } - - if (copy_to_user(hdr->dxferp, from, n)) - return -EFAULT; - return 0; -} - -/* Copy data from userspace memory */ - -static int nvme_trans_copy_from_user(struct sg_io_hdr *hdr, void *to, - unsigned long n) -{ - int i; - void *index = to; - size_t remaining = n; - size_t xfer_len; - - if (hdr->iovec_count > 0) { - struct sg_iovec sgl; - - for (i = 0; i < hdr->iovec_count; i++) { - if (copy_from_user(&sgl, hdr->dxferp + - i * sizeof(struct sg_iovec), - sizeof(struct sg_iovec))) - return -EFAULT; - xfer_len = min(remaining, sgl.iov_len); - if (copy_from_user(index, sgl.iov_base, xfer_len)) - return -EFAULT; - index += xfer_len; - remaining -= xfer_len; - if (remaining == 0) - break; - } - return 0; - } - - if (copy_from_user(to, hdr->dxferp, n)) - return -EFAULT; - return 0; -} - -/* Status/Sense Buffer Writeback */ - -static int nvme_trans_completion(struct sg_io_hdr *hdr, u8 status, u8 sense_key, - u8 asc, u8 ascq) -{ - u8 xfer_len; - u8 resp[DESC_FMT_SENSE_DATA_SIZE]; - - if (scsi_status_is_good(status)) { - hdr->status = SAM_STAT_GOOD; - hdr->masked_status = GOOD; - hdr->host_status = DID_OK; - hdr->driver_status = DRIVER_OK; - hdr->sb_len_wr = 0; - } else { - hdr->status = status; - hdr->masked_status = status >> 1; - hdr->host_status = DID_OK; - hdr->driver_status = DRIVER_OK; - - memset(resp, 0, DESC_FMT_SENSE_DATA_SIZE); - resp[0] = DESC_FORMAT_SENSE_DATA; - resp[1] = sense_key; - resp[2] = asc; - resp[3] = ascq; - - xfer_len = min_t(u8, hdr->mx_sb_len, DESC_FMT_SENSE_DATA_SIZE); - hdr->sb_len_wr = xfer_len; - if (copy_to_user(hdr->sbp, resp, xfer_len) > 0) - return -EFAULT; - } - - return 0; -} - -/* - * Take a status code from a lowlevel routine, and if it was a positive NVMe - * error code update the sense data based on it. In either case the passed - * in value is returned again, unless an -EFAULT from copy_to_user overrides - * it. - */ -static int nvme_trans_status_code(struct sg_io_hdr *hdr, int nvme_sc) -{ - u8 status, sense_key, asc, ascq; - int res; - - /* For non-nvme (Linux) errors, simply return the error code */ - if (nvme_sc < 0) - return nvme_sc; - - /* Mask DNR, More, and reserved fields */ - switch (nvme_sc & 0x7FF) { - /* Generic Command Status */ - case NVME_SC_SUCCESS: - status = SAM_STAT_GOOD; - sense_key = NO_SENSE; - asc = SCSI_ASC_NO_SENSE; - ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE; - break; - case NVME_SC_INVALID_OPCODE: - status = SAM_STAT_CHECK_CONDITION; - sense_key = ILLEGAL_REQUEST; - asc = SCSI_ASC_ILLEGAL_COMMAND; - ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE; - break; - case NVME_SC_INVALID_FIELD: - status = SAM_STAT_CHECK_CONDITION; - sense_key = ILLEGAL_REQUEST; - asc = SCSI_ASC_INVALID_CDB; - ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE; - break; - case NVME_SC_DATA_XFER_ERROR: - status = SAM_STAT_CHECK_CONDITION; - sense_key = MEDIUM_ERROR; - asc = SCSI_ASC_NO_SENSE; - ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE; - break; - case NVME_SC_POWER_LOSS: - status = SAM_STAT_TASK_ABORTED; - sense_key = ABORTED_COMMAND; - asc = SCSI_ASC_WARNING; - ascq = SCSI_ASCQ_POWER_LOSS_EXPECTED; - break; - case NVME_SC_INTERNAL: - status = SAM_STAT_CHECK_CONDITION; - sense_key = HARDWARE_ERROR; - asc = SCSI_ASC_INTERNAL_TARGET_FAILURE; - ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE; - break; - case NVME_SC_ABORT_REQ: - status = SAM_STAT_TASK_ABORTED; - sense_key = ABORTED_COMMAND; - asc = SCSI_ASC_NO_SENSE; - ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE; - break; - case NVME_SC_ABORT_QUEUE: - status = SAM_STAT_TASK_ABORTED; - sense_key = ABORTED_COMMAND; - asc = SCSI_ASC_NO_SENSE; - ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE; - break; - case NVME_SC_FUSED_FAIL: - status = SAM_STAT_TASK_ABORTED; - sense_key = ABORTED_COMMAND; - asc = SCSI_ASC_NO_SENSE; - ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE; - break; - case NVME_SC_FUSED_MISSING: - status = SAM_STAT_TASK_ABORTED; - sense_key = ABORTED_COMMAND; - asc = SCSI_ASC_NO_SENSE; - ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE; - break; - case NVME_SC_INVALID_NS: - status = SAM_STAT_CHECK_CONDITION; - sense_key = ILLEGAL_REQUEST; - asc = SCSI_ASC_ACCESS_DENIED_INVALID_LUN_ID; - ascq = SCSI_ASCQ_INVALID_LUN_ID; - break; - case NVME_SC_LBA_RANGE: - status = SAM_STAT_CHECK_CONDITION; - sense_key = ILLEGAL_REQUEST; - asc = SCSI_ASC_ILLEGAL_BLOCK; - ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE; - break; - case NVME_SC_CAP_EXCEEDED: - status = SAM_STAT_CHECK_CONDITION; - sense_key = MEDIUM_ERROR; - asc = SCSI_ASC_NO_SENSE; - ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE; - break; - case NVME_SC_NS_NOT_READY: - status = SAM_STAT_CHECK_CONDITION; - sense_key = NOT_READY; - asc = SCSI_ASC_LUN_NOT_READY; - ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE; - break; - - /* Command Specific Status */ - case NVME_SC_INVALID_FORMAT: - status = SAM_STAT_CHECK_CONDITION; - sense_key = ILLEGAL_REQUEST; - asc = SCSI_ASC_FORMAT_COMMAND_FAILED; - ascq = SCSI_ASCQ_FORMAT_COMMAND_FAILED; - break; - case NVME_SC_BAD_ATTRIBUTES: - status = SAM_STAT_CHECK_CONDITION; - sense_key = ILLEGAL_REQUEST; - asc = SCSI_ASC_INVALID_CDB; - ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE; - break; - - /* Media Errors */ - case NVME_SC_WRITE_FAULT: - status = SAM_STAT_CHECK_CONDITION; - sense_key = MEDIUM_ERROR; - asc = SCSI_ASC_PERIPHERAL_DEV_WRITE_FAULT; - ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE; - break; - case NVME_SC_READ_ERROR: - status = SAM_STAT_CHECK_CONDITION; - sense_key = MEDIUM_ERROR; - asc = SCSI_ASC_UNRECOVERED_READ_ERROR; - ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE; - break; - case NVME_SC_GUARD_CHECK: - status = SAM_STAT_CHECK_CONDITION; - sense_key = MEDIUM_ERROR; - asc = SCSI_ASC_LOG_BLOCK_GUARD_CHECK_FAILED; - ascq = SCSI_ASCQ_LOG_BLOCK_GUARD_CHECK_FAILED; - break; - case NVME_SC_APPTAG_CHECK: - status = SAM_STAT_CHECK_CONDITION; - sense_key = MEDIUM_ERROR; - asc = SCSI_ASC_LOG_BLOCK_APPTAG_CHECK_FAILED; - ascq = SCSI_ASCQ_LOG_BLOCK_APPTAG_CHECK_FAILED; - break; - case NVME_SC_REFTAG_CHECK: - status = SAM_STAT_CHECK_CONDITION; - sense_key = MEDIUM_ERROR; - asc = SCSI_ASC_LOG_BLOCK_REFTAG_CHECK_FAILED; - ascq = SCSI_ASCQ_LOG_BLOCK_REFTAG_CHECK_FAILED; - break; - case NVME_SC_COMPARE_FAILED: - status = SAM_STAT_CHECK_CONDITION; - sense_key = MISCOMPARE; - asc = SCSI_ASC_MISCOMPARE_DURING_VERIFY; - ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE; - break; - case NVME_SC_ACCESS_DENIED: - status = SAM_STAT_CHECK_CONDITION; - sense_key = ILLEGAL_REQUEST; - asc = SCSI_ASC_ACCESS_DENIED_INVALID_LUN_ID; - ascq = SCSI_ASCQ_INVALID_LUN_ID; - break; - - /* Unspecified/Default */ - case NVME_SC_CMDID_CONFLICT: - case NVME_SC_CMD_SEQ_ERROR: - case NVME_SC_CQ_INVALID: - case NVME_SC_QID_INVALID: - case NVME_SC_QUEUE_SIZE: - case NVME_SC_ABORT_LIMIT: - case NVME_SC_ABORT_MISSING: - case NVME_SC_ASYNC_LIMIT: - case NVME_SC_FIRMWARE_SLOT: - case NVME_SC_FIRMWARE_IMAGE: - case NVME_SC_INVALID_VECTOR: - case NVME_SC_INVALID_LOG_PAGE: - default: - status = SAM_STAT_CHECK_CONDITION; - sense_key = ILLEGAL_REQUEST; - asc = SCSI_ASC_NO_SENSE; - ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE; - break; - } - - res = nvme_trans_completion(hdr, status, sense_key, asc, ascq); - return res ? res : nvme_sc; -} - -/* INQUIRY Helper Functions */ - -static int nvme_trans_standard_inquiry_page(struct nvme_ns *ns, - struct sg_io_hdr *hdr, u8 *inq_response, - int alloc_len) -{ - struct nvme_ctrl *ctrl = ns->ctrl; - struct nvme_id_ns *id_ns; - int res; - int nvme_sc; - int xfer_len; - u8 resp_data_format = 0x02; - u8 protect; - u8 cmdque = 0x01 << 1; - u8 fw_offset = sizeof(ctrl->firmware_rev); - - /* nvme ns identify - use DPS value for PROTECT field */ - nvme_sc = nvme_identify_ns(ctrl, ns->ns_id, &id_ns); - res = nvme_trans_status_code(hdr, nvme_sc); - if (res) - return res; - - if (id_ns->dps) - protect = 0x01; - else - protect = 0; - kfree(id_ns); - - memset(inq_response, 0, STANDARD_INQUIRY_LENGTH); - inq_response[2] = VERSION_SPC_4; - inq_response[3] = resp_data_format; /*normaca=0 | hisup=0 */ - inq_response[4] = ADDITIONAL_STD_INQ_LENGTH; - inq_response[5] = protect; /* sccs=0 | acc=0 | tpgs=0 | pc3=0 */ - inq_response[7] = cmdque; /* wbus16=0 | sync=0 | vs=0 */ - strncpy(&inq_response[8], "NVMe ", 8); - strncpy(&inq_response[16], ctrl->model, 16); - - while (ctrl->firmware_rev[fw_offset - 1] == ' ' && fw_offset > 4) - fw_offset--; - fw_offset -= 4; - strncpy(&inq_response[32], ctrl->firmware_rev + fw_offset, 4); - - xfer_len = min(alloc_len, STANDARD_INQUIRY_LENGTH); - return nvme_trans_copy_to_user(hdr, inq_response, xfer_len); -} - -static int nvme_trans_supported_vpd_pages(struct nvme_ns *ns, - struct sg_io_hdr *hdr, u8 *inq_response, - int alloc_len) -{ - int xfer_len; - - memset(inq_response, 0, STANDARD_INQUIRY_LENGTH); - inq_response[1] = INQ_SUPPORTED_VPD_PAGES_PAGE; /* Page Code */ - inq_response[3] = INQ_NUM_SUPPORTED_VPD_PAGES; /* Page Length */ - inq_response[4] = INQ_SUPPORTED_VPD_PAGES_PAGE; - inq_response[5] = INQ_UNIT_SERIAL_NUMBER_PAGE; - inq_response[6] = INQ_DEVICE_IDENTIFICATION_PAGE; - inq_response[7] = INQ_EXTENDED_INQUIRY_DATA_PAGE; - inq_response[8] = INQ_BDEV_CHARACTERISTICS_PAGE; - inq_response[9] = INQ_BDEV_LIMITS_PAGE; - - xfer_len = min(alloc_len, STANDARD_INQUIRY_LENGTH); - return nvme_trans_copy_to_user(hdr, inq_response, xfer_len); -} - -static int nvme_trans_unit_serial_page(struct nvme_ns *ns, - struct sg_io_hdr *hdr, u8 *inq_response, - int alloc_len) -{ - int xfer_len; - - memset(inq_response, 0, STANDARD_INQUIRY_LENGTH); - inq_response[1] = INQ_UNIT_SERIAL_NUMBER_PAGE; /* Page Code */ - inq_response[3] = INQ_SERIAL_NUMBER_LENGTH; /* Page Length */ - strncpy(&inq_response[4], ns->ctrl->serial, INQ_SERIAL_NUMBER_LENGTH); - - xfer_len = min(alloc_len, STANDARD_INQUIRY_LENGTH); - return nvme_trans_copy_to_user(hdr, inq_response, xfer_len); -} - -static int nvme_fill_device_id_eui64(struct nvme_ns *ns, struct sg_io_hdr *hdr, - u8 *inq_response, int alloc_len) -{ - struct nvme_id_ns *id_ns; - int nvme_sc, res; - size_t len; - void *eui; - - nvme_sc = nvme_identify_ns(ns->ctrl, ns->ns_id, &id_ns); - res = nvme_trans_status_code(hdr, nvme_sc); - if (res) - return res; - - eui = id_ns->eui64; - len = sizeof(id_ns->eui64); - - if (ns->ctrl->vs >= NVME_VS(1, 2, 0)) { - if (bitmap_empty(eui, len * 8)) { - eui = id_ns->nguid; - len = sizeof(id_ns->nguid); - } - } - - if (bitmap_empty(eui, len * 8)) { - res = -EOPNOTSUPP; - goto out_free_id; - } - - memset(inq_response, 0, alloc_len); - inq_response[1] = INQ_DEVICE_IDENTIFICATION_PAGE; - inq_response[3] = 4 + len; /* Page Length */ - - /* Designation Descriptor start */ - inq_response[4] = 0x01; /* Proto ID=0h | Code set=1h */ - inq_response[5] = 0x02; /* PIV=0b | Asso=00b | Designator Type=2h */ - inq_response[6] = 0x00; /* Rsvd */ - inq_response[7] = len; /* Designator Length */ - memcpy(&inq_response[8], eui, len); - - res = nvme_trans_copy_to_user(hdr, inq_response, alloc_len); -out_free_id: - kfree(id_ns); - return res; -} - -static int nvme_fill_device_id_scsi_string(struct nvme_ns *ns, - struct sg_io_hdr *hdr, u8 *inq_response, int alloc_len) -{ - struct nvme_ctrl *ctrl = ns->ctrl; - struct nvme_id_ctrl *id_ctrl; - int nvme_sc, res; - - if (alloc_len < 72) { - return nvme_trans_completion(hdr, - SAM_STAT_CHECK_CONDITION, - ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB, - SCSI_ASCQ_CAUSE_NOT_REPORTABLE); - } - - nvme_sc = nvme_identify_ctrl(ctrl, &id_ctrl); - res = nvme_trans_status_code(hdr, nvme_sc); - if (res) - return res; - - memset(inq_response, 0, alloc_len); - inq_response[1] = INQ_DEVICE_IDENTIFICATION_PAGE; - inq_response[3] = 0x48; /* Page Length */ - - /* Designation Descriptor start */ - inq_response[4] = 0x03; /* Proto ID=0h | Code set=3h */ - inq_response[5] = 0x08; /* PIV=0b | Asso=00b | Designator Type=8h */ - inq_response[6] = 0x00; /* Rsvd */ - inq_response[7] = 0x44; /* Designator Length */ - - sprintf(&inq_response[8], "%04x", le16_to_cpu(id_ctrl->vid)); - memcpy(&inq_response[12], ctrl->model, sizeof(ctrl->model)); - sprintf(&inq_response[52], "%04x", cpu_to_be32(ns->ns_id)); - memcpy(&inq_response[56], ctrl->serial, sizeof(ctrl->serial)); - - res = nvme_trans_copy_to_user(hdr, inq_response, alloc_len); - kfree(id_ctrl); - return res; -} - -static int nvme_trans_device_id_page(struct nvme_ns *ns, struct sg_io_hdr *hdr, - u8 *resp, int alloc_len) -{ - int res; - - if (ns->ctrl->vs >= NVME_VS(1, 1, 0)) { - res = nvme_fill_device_id_eui64(ns, hdr, resp, alloc_len); - if (res != -EOPNOTSUPP) - return res; - } - - return nvme_fill_device_id_scsi_string(ns, hdr, resp, alloc_len); -} - -static int nvme_trans_ext_inq_page(struct nvme_ns *ns, struct sg_io_hdr *hdr, - int alloc_len) -{ - u8 *inq_response; - int res; - int nvme_sc; - struct nvme_ctrl *ctrl = ns->ctrl; - struct nvme_id_ctrl *id_ctrl; - struct nvme_id_ns *id_ns; - int xfer_len; - u8 microcode = 0x80; - u8 spt; - u8 spt_lut[8] = {0, 0, 2, 1, 4, 6, 5, 7}; - u8 grd_chk, app_chk, ref_chk, protect; - u8 uask_sup = 0x20; - u8 v_sup; - u8 luiclr = 0x01; - - inq_response = kmalloc(EXTENDED_INQUIRY_DATA_PAGE_LENGTH, GFP_KERNEL); - if (inq_response == NULL) - return -ENOMEM; - - nvme_sc = nvme_identify_ns(ctrl, ns->ns_id, &id_ns); - res = nvme_trans_status_code(hdr, nvme_sc); - if (res) - goto out_free_inq; - - spt = spt_lut[id_ns->dpc & 0x07] << 3; - if (id_ns->dps) - protect = 0x01; - else - protect = 0; - kfree(id_ns); - - grd_chk = protect << 2; - app_chk = protect << 1; - ref_chk = protect; - - nvme_sc = nvme_identify_ctrl(ctrl, &id_ctrl); - res = nvme_trans_status_code(hdr, nvme_sc); - if (res) - goto out_free_inq; - - v_sup = id_ctrl->vwc; - kfree(id_ctrl); - - memset(inq_response, 0, EXTENDED_INQUIRY_DATA_PAGE_LENGTH); - inq_response[1] = INQ_EXTENDED_INQUIRY_DATA_PAGE; /* Page Code */ - inq_response[2] = 0x00; /* Page Length MSB */ - inq_response[3] = 0x3C; /* Page Length LSB */ - inq_response[4] = microcode | spt | grd_chk | app_chk | ref_chk; - inq_response[5] = uask_sup; - inq_response[6] = v_sup; - inq_response[7] = luiclr; - inq_response[8] = 0; - inq_response[9] = 0; - - xfer_len = min(alloc_len, EXTENDED_INQUIRY_DATA_PAGE_LENGTH); - res = nvme_trans_copy_to_user(hdr, inq_response, xfer_len); - - out_free_inq: - kfree(inq_response); - return res; -} - -static int nvme_trans_bdev_limits_page(struct nvme_ns *ns, struct sg_io_hdr *hdr, - u8 *inq_response, int alloc_len) -{ - __be32 max_sectors = cpu_to_be32( - nvme_block_nr(ns, queue_max_hw_sectors(ns->queue))); - __be32 max_discard = cpu_to_be32(ns->queue->limits.max_discard_sectors); - __be32 discard_desc_count = cpu_to_be32(0x100); - - memset(inq_response, 0, STANDARD_INQUIRY_LENGTH); - inq_response[1] = VPD_BLOCK_LIMITS; - inq_response[3] = 0x3c; /* Page Length */ - memcpy(&inq_response[8], &max_sectors, sizeof(u32)); - memcpy(&inq_response[20], &max_discard, sizeof(u32)); - - if (max_discard) - memcpy(&inq_response[24], &discard_desc_count, sizeof(u32)); - - return nvme_trans_copy_to_user(hdr, inq_response, 0x3c); -} - -static int nvme_trans_bdev_char_page(struct nvme_ns *ns, struct sg_io_hdr *hdr, - int alloc_len) -{ - u8 *inq_response; - int res; - int xfer_len; - - inq_response = kzalloc(EXTENDED_INQUIRY_DATA_PAGE_LENGTH, GFP_KERNEL); - if (inq_response == NULL) { - res = -ENOMEM; - goto out_mem; - } - - inq_response[1] = INQ_BDEV_CHARACTERISTICS_PAGE; /* Page Code */ - inq_response[2] = 0x00; /* Page Length MSB */ - inq_response[3] = 0x3C; /* Page Length LSB */ - inq_response[4] = 0x00; /* Medium Rotation Rate MSB */ - inq_response[5] = 0x01; /* Medium Rotation Rate LSB */ - inq_response[6] = 0x00; /* Form Factor */ - - xfer_len = min(alloc_len, EXTENDED_INQUIRY_DATA_PAGE_LENGTH); - res = nvme_trans_copy_to_user(hdr, inq_response, xfer_len); - - kfree(inq_response); - out_mem: - return res; -} - -/* LOG SENSE Helper Functions */ - -static int nvme_trans_log_supp_pages(struct nvme_ns *ns, struct sg_io_hdr *hdr, - int alloc_len) -{ - int res; - int xfer_len; - u8 *log_response; - - log_response = kzalloc(LOG_PAGE_SUPPORTED_LOG_PAGES_LENGTH, GFP_KERNEL); - if (log_response == NULL) { - res = -ENOMEM; - goto out_mem; - } - - log_response[0] = LOG_PAGE_SUPPORTED_LOG_PAGES_PAGE; - /* Subpage=0x00, Page Length MSB=0 */ - log_response[3] = SUPPORTED_LOG_PAGES_PAGE_LENGTH; - log_response[4] = LOG_PAGE_SUPPORTED_LOG_PAGES_PAGE; - log_response[5] = LOG_PAGE_INFORMATIONAL_EXCEPTIONS_PAGE; - log_response[6] = LOG_PAGE_TEMPERATURE_PAGE; - - xfer_len = min(alloc_len, LOG_PAGE_SUPPORTED_LOG_PAGES_LENGTH); - res = nvme_trans_copy_to_user(hdr, log_response, xfer_len); - - kfree(log_response); - out_mem: - return res; -} - -static int nvme_trans_log_info_exceptions(struct nvme_ns *ns, - struct sg_io_hdr *hdr, int alloc_len) -{ - int res; - int xfer_len; - u8 *log_response; - struct nvme_smart_log *smart_log; - u8 temp_c; - u16 temp_k; - - log_response = kzalloc(LOG_INFO_EXCP_PAGE_LENGTH, GFP_KERNEL); - if (log_response == NULL) - return -ENOMEM; - - res = nvme_get_log_page(ns->ctrl, &smart_log); - if (res < 0) - goto out_free_response; - - if (res != NVME_SC_SUCCESS) { - temp_c = LOG_TEMP_UNKNOWN; - } else { - temp_k = (smart_log->temperature[1] << 8) + - (smart_log->temperature[0]); - temp_c = temp_k - KELVIN_TEMP_FACTOR; - } - kfree(smart_log); - - log_response[0] = LOG_PAGE_INFORMATIONAL_EXCEPTIONS_PAGE; - /* Subpage=0x00, Page Length MSB=0 */ - log_response[3] = REMAINING_INFO_EXCP_PAGE_LENGTH; - /* Informational Exceptions Log Parameter 1 Start */ - /* Parameter Code=0x0000 bytes 4,5 */ - log_response[6] = 0x23; /* DU=0, TSD=1, ETC=0, TMC=0, FMT_AND_LNK=11b */ - log_response[7] = 0x04; /* PARAMETER LENGTH */ - /* Add sense Code and qualifier = 0x00 each */ - /* Use Temperature from NVMe Get Log Page, convert to C from K */ - log_response[10] = temp_c; - - xfer_len = min(alloc_len, LOG_INFO_EXCP_PAGE_LENGTH); - res = nvme_trans_copy_to_user(hdr, log_response, xfer_len); - - out_free_response: - kfree(log_response); - return res; -} - -static int nvme_trans_log_temperature(struct nvme_ns *ns, struct sg_io_hdr *hdr, - int alloc_len) -{ - int res; - int xfer_len; - u8 *log_response; - struct nvme_smart_log *smart_log; - u32 feature_resp; - u8 temp_c_cur, temp_c_thresh; - u16 temp_k; - - log_response = kzalloc(LOG_TEMP_PAGE_LENGTH, GFP_KERNEL); - if (log_response == NULL) - return -ENOMEM; - - res = nvme_get_log_page(ns->ctrl, &smart_log); - if (res < 0) - goto out_free_response; - - if (res != NVME_SC_SUCCESS) { - temp_c_cur = LOG_TEMP_UNKNOWN; - } else { - temp_k = (smart_log->temperature[1] << 8) + - (smart_log->temperature[0]); - temp_c_cur = temp_k - KELVIN_TEMP_FACTOR; - } - kfree(smart_log); - - /* Get Features for Temp Threshold */ - res = nvme_get_features(ns->ctrl, NVME_FEAT_TEMP_THRESH, 0, NULL, 0, - &feature_resp); - if (res != NVME_SC_SUCCESS) - temp_c_thresh = LOG_TEMP_UNKNOWN; - else - temp_c_thresh = (feature_resp & 0xFFFF) - KELVIN_TEMP_FACTOR; - - log_response[0] = LOG_PAGE_TEMPERATURE_PAGE; - /* Subpage=0x00, Page Length MSB=0 */ - log_response[3] = REMAINING_TEMP_PAGE_LENGTH; - /* Temperature Log Parameter 1 (Temperature) Start */ - /* Parameter Code = 0x0000 */ - log_response[6] = 0x01; /* Format and Linking = 01b */ - log_response[7] = 0x02; /* Parameter Length */ - /* Use Temperature from NVMe Get Log Page, convert to C from K */ - log_response[9] = temp_c_cur; - /* Temperature Log Parameter 2 (Reference Temperature) Start */ - log_response[11] = 0x01; /* Parameter Code = 0x0001 */ - log_response[12] = 0x01; /* Format and Linking = 01b */ - log_response[13] = 0x02; /* Parameter Length */ - /* Use Temperature Thresh from NVMe Get Log Page, convert to C from K */ - log_response[15] = temp_c_thresh; - - xfer_len = min(alloc_len, LOG_TEMP_PAGE_LENGTH); - res = nvme_trans_copy_to_user(hdr, log_response, xfer_len); - - out_free_response: - kfree(log_response); - return res; -} - -/* MODE SENSE Helper Functions */ - -static int nvme_trans_fill_mode_parm_hdr(u8 *resp, int len, u8 cdb10, u8 llbaa, - u16 mode_data_length, u16 blk_desc_len) -{ - /* Quick check to make sure I don't stomp on my own memory... */ - if ((cdb10 && len < 8) || (!cdb10 && len < 4)) - return -EINVAL; - - if (cdb10) { - resp[0] = (mode_data_length & 0xFF00) >> 8; - resp[1] = (mode_data_length & 0x00FF); - resp[3] = 0x10 /* DPOFUA */; - resp[4] = llbaa; - resp[5] = RESERVED_FIELD; - resp[6] = (blk_desc_len & 0xFF00) >> 8; - resp[7] = (blk_desc_len & 0x00FF); - } else { - resp[0] = (mode_data_length & 0x00FF); - resp[2] = 0x10 /* DPOFUA */; - resp[3] = (blk_desc_len & 0x00FF); - } - - return 0; -} - -static int nvme_trans_fill_blk_desc(struct nvme_ns *ns, struct sg_io_hdr *hdr, - u8 *resp, int len, u8 llbaa) -{ - int res; - int nvme_sc; - struct nvme_id_ns *id_ns; - u8 flbas; - u32 lba_length; - - if (llbaa == 0 && len < MODE_PAGE_BLK_DES_LEN) - return -EINVAL; - else if (llbaa > 0 && len < MODE_PAGE_LLBAA_BLK_DES_LEN) - return -EINVAL; - - nvme_sc = nvme_identify_ns(ns->ctrl, ns->ns_id, &id_ns); - res = nvme_trans_status_code(hdr, nvme_sc); - if (res) - return res; - - flbas = (id_ns->flbas) & 0x0F; - lba_length = (1 << (id_ns->lbaf[flbas].ds)); - - if (llbaa == 0) { - __be32 tmp_cap = cpu_to_be32(le64_to_cpu(id_ns->ncap)); - /* Byte 4 is reserved */ - __be32 tmp_len = cpu_to_be32(lba_length & 0x00FFFFFF); - - memcpy(resp, &tmp_cap, sizeof(u32)); - memcpy(&resp[4], &tmp_len, sizeof(u32)); - } else { - __be64 tmp_cap = cpu_to_be64(le64_to_cpu(id_ns->ncap)); - __be32 tmp_len = cpu_to_be32(lba_length); - - memcpy(resp, &tmp_cap, sizeof(u64)); - /* Bytes 8, 9, 10, 11 are reserved */ - memcpy(&resp[12], &tmp_len, sizeof(u32)); - } - - kfree(id_ns); - return res; -} - -static int nvme_trans_fill_control_page(struct nvme_ns *ns, - struct sg_io_hdr *hdr, u8 *resp, - int len) -{ - if (len < MODE_PAGE_CONTROL_LEN) - return -EINVAL; - - resp[0] = MODE_PAGE_CONTROL; - resp[1] = MODE_PAGE_CONTROL_LEN_FIELD; - resp[2] = 0x0E; /* TST=000b, TMF_ONLY=0, DPICZ=1, - * D_SENSE=1, GLTSD=1, RLEC=0 */ - resp[3] = 0x12; /* Q_ALGO_MODIFIER=1h, NUAR=0, QERR=01b */ - /* Byte 4: VS=0, RAC=0, UA_INT=0, SWP=0 */ - resp[5] = 0x40; /* ATO=0, TAS=1, ATMPE=0, RWWP=0, AUTOLOAD=0 */ - /* resp[6] and [7] are obsolete, thus zero */ - resp[8] = 0xFF; /* Busy timeout period = 0xffff */ - resp[9] = 0xFF; - /* Bytes 10,11: Extended selftest completion time = 0x0000 */ - - return 0; -} - -static int nvme_trans_fill_caching_page(struct nvme_ns *ns, - struct sg_io_hdr *hdr, - u8 *resp, int len) -{ - int res = 0; - int nvme_sc; - u32 feature_resp; - u8 vwc; - - if (len < MODE_PAGE_CACHING_LEN) - return -EINVAL; - - nvme_sc = nvme_get_features(ns->ctrl, NVME_FEAT_VOLATILE_WC, 0, NULL, 0, - &feature_resp); - res = nvme_trans_status_code(hdr, nvme_sc); - if (res) - return res; - - vwc = feature_resp & 0x00000001; - - resp[0] = MODE_PAGE_CACHING; - resp[1] = MODE_PAGE_CACHING_LEN_FIELD; - resp[2] = vwc << 2; - return 0; -} - -static int nvme_trans_fill_pow_cnd_page(struct nvme_ns *ns, - struct sg_io_hdr *hdr, u8 *resp, - int len) -{ - if (len < MODE_PAGE_POW_CND_LEN) - return -EINVAL; - - resp[0] = MODE_PAGE_POWER_CONDITION; - resp[1] = MODE_PAGE_POW_CND_LEN_FIELD; - /* All other bytes are zero */ - - return 0; -} - -static int nvme_trans_fill_inf_exc_page(struct nvme_ns *ns, - struct sg_io_hdr *hdr, u8 *resp, - int len) -{ - if (len < MODE_PAGE_INF_EXC_LEN) - return -EINVAL; - - resp[0] = MODE_PAGE_INFO_EXCEP; - resp[1] = MODE_PAGE_INF_EXC_LEN_FIELD; - resp[2] = 0x88; - /* All other bytes are zero */ - - return 0; -} - -static int nvme_trans_fill_all_pages(struct nvme_ns *ns, struct sg_io_hdr *hdr, - u8 *resp, int len) -{ - int res; - u16 mode_pages_offset_1 = 0; - u16 mode_pages_offset_2, mode_pages_offset_3, mode_pages_offset_4; - - mode_pages_offset_2 = mode_pages_offset_1 + MODE_PAGE_CACHING_LEN; - mode_pages_offset_3 = mode_pages_offset_2 + MODE_PAGE_CONTROL_LEN; - mode_pages_offset_4 = mode_pages_offset_3 + MODE_PAGE_POW_CND_LEN; - - res = nvme_trans_fill_caching_page(ns, hdr, &resp[mode_pages_offset_1], - MODE_PAGE_CACHING_LEN); - if (res) - return res; - res = nvme_trans_fill_control_page(ns, hdr, &resp[mode_pages_offset_2], - MODE_PAGE_CONTROL_LEN); - if (res) - return res; - res = nvme_trans_fill_pow_cnd_page(ns, hdr, &resp[mode_pages_offset_3], - MODE_PAGE_POW_CND_LEN); - if (res) - return res; - return nvme_trans_fill_inf_exc_page(ns, hdr, &resp[mode_pages_offset_4], - MODE_PAGE_INF_EXC_LEN); -} - -static inline int nvme_trans_get_blk_desc_len(u8 dbd, u8 llbaa) -{ - if (dbd == MODE_SENSE_BLK_DESC_ENABLED) { - /* SPC-4: len = 8 x Num_of_descriptors if llbaa = 0, 16x if 1 */ - return 8 * (llbaa + 1) * MODE_SENSE_BLK_DESC_COUNT; - } else { - return 0; - } -} - -static int nvme_trans_mode_page_create(struct nvme_ns *ns, - struct sg_io_hdr *hdr, u8 *cmd, - u16 alloc_len, u8 cdb10, - int (*mode_page_fill_func) - (struct nvme_ns *, - struct sg_io_hdr *hdr, u8 *, int), - u16 mode_pages_tot_len) -{ - int res; - int xfer_len; - u8 *response; - u8 dbd, llbaa; - u16 resp_size; - int mph_size; - u16 mode_pages_offset_1; - u16 blk_desc_len, blk_desc_offset, mode_data_length; - - dbd = (cmd[1] & MODE_SENSE_DBD_MASK) >> MODE_SENSE_DBD_SHIFT; - llbaa = (cmd[1] & MODE_SENSE_LLBAA_MASK) >> MODE_SENSE_LLBAA_SHIFT; - mph_size = cdb10 ? MODE_SENSE10_MPH_SIZE : MODE_SENSE6_MPH_SIZE; - - blk_desc_len = nvme_trans_get_blk_desc_len(dbd, llbaa); - - resp_size = mph_size + blk_desc_len + mode_pages_tot_len; - /* Refer spc4r34 Table 440 for calculation of Mode data Length field */ - mode_data_length = 3 + (3 * cdb10) + blk_desc_len + mode_pages_tot_len; - - blk_desc_offset = mph_size; - mode_pages_offset_1 = blk_desc_offset + blk_desc_len; - - response = kzalloc(resp_size, GFP_KERNEL); - if (response == NULL) { - res = -ENOMEM; - goto out_mem; - } - - res = nvme_trans_fill_mode_parm_hdr(&response[0], mph_size, cdb10, - llbaa, mode_data_length, blk_desc_len); - if (res) - goto out_free; - if (blk_desc_len > 0) { - res = nvme_trans_fill_blk_desc(ns, hdr, - &response[blk_desc_offset], - blk_desc_len, llbaa); - if (res) - goto out_free; - } - res = mode_page_fill_func(ns, hdr, &response[mode_pages_offset_1], - mode_pages_tot_len); - if (res) - goto out_free; - - xfer_len = min(alloc_len, resp_size); - res = nvme_trans_copy_to_user(hdr, response, xfer_len); - - out_free: - kfree(response); - out_mem: - return res; -} - -/* Read Capacity Helper Functions */ - -static void nvme_trans_fill_read_cap(u8 *response, struct nvme_id_ns *id_ns, - u8 cdb16) -{ - u8 flbas; - u32 lba_length; - u64 rlba; - u8 prot_en; - u8 p_type_lut[4] = {0, 0, 1, 2}; - __be64 tmp_rlba; - __be32 tmp_rlba_32; - __be32 tmp_len; - - flbas = (id_ns->flbas) & 0x0F; - lba_length = (1 << (id_ns->lbaf[flbas].ds)); - rlba = le64_to_cpup(&id_ns->nsze) - 1; - (id_ns->dps) ? (prot_en = 0x01) : (prot_en = 0); - - if (!cdb16) { - if (rlba > 0xFFFFFFFF) - rlba = 0xFFFFFFFF; - tmp_rlba_32 = cpu_to_be32(rlba); - tmp_len = cpu_to_be32(lba_length); - memcpy(response, &tmp_rlba_32, sizeof(u32)); - memcpy(&response[4], &tmp_len, sizeof(u32)); - } else { - tmp_rlba = cpu_to_be64(rlba); - tmp_len = cpu_to_be32(lba_length); - memcpy(response, &tmp_rlba, sizeof(u64)); - memcpy(&response[8], &tmp_len, sizeof(u32)); - response[12] = (p_type_lut[id_ns->dps & 0x3] << 1) | prot_en; - /* P_I_Exponent = 0x0 | LBPPBE = 0x0 */ - /* LBPME = 0 | LBPRZ = 0 | LALBA = 0x00 */ - /* Bytes 16-31 - Reserved */ - } -} - -/* Start Stop Unit Helper Functions */ - -static int nvme_trans_send_activate_fw_cmd(struct nvme_ns *ns, struct sg_io_hdr *hdr, - u8 buffer_id) -{ - struct nvme_command c; - int nvme_sc; - - memset(&c, 0, sizeof(c)); - c.common.opcode = nvme_admin_activate_fw; - c.common.cdw10[0] = cpu_to_le32(buffer_id | NVME_FWACT_REPL_ACTV); - - nvme_sc = nvme_submit_sync_cmd(ns->queue, &c, NULL, 0); - return nvme_trans_status_code(hdr, nvme_sc); -} - -static int nvme_trans_send_download_fw_cmd(struct nvme_ns *ns, struct sg_io_hdr *hdr, - u8 opcode, u32 tot_len, u32 offset, - u8 buffer_id) -{ - int nvme_sc; - struct nvme_command c; - - if (hdr->iovec_count > 0) { - /* Assuming SGL is not allowed for this command */ - return nvme_trans_completion(hdr, - SAM_STAT_CHECK_CONDITION, - ILLEGAL_REQUEST, - SCSI_ASC_INVALID_CDB, - SCSI_ASCQ_CAUSE_NOT_REPORTABLE); - } - - memset(&c, 0, sizeof(c)); - c.common.opcode = nvme_admin_download_fw; - c.dlfw.numd = cpu_to_le32((tot_len/BYTES_TO_DWORDS) - 1); - c.dlfw.offset = cpu_to_le32(offset/BYTES_TO_DWORDS); - - nvme_sc = nvme_submit_user_cmd(ns->ctrl->admin_q, &c, - hdr->dxferp, tot_len, NULL, 0); - return nvme_trans_status_code(hdr, nvme_sc); -} - -/* Mode Select Helper Functions */ - -static inline void nvme_trans_modesel_get_bd_len(u8 *parm_list, u8 cdb10, - u16 *bd_len, u8 *llbaa) -{ - if (cdb10) { - /* 10 Byte CDB */ - *bd_len = (parm_list[MODE_SELECT_10_BD_OFFSET] << 8) + - parm_list[MODE_SELECT_10_BD_OFFSET + 1]; - *llbaa = parm_list[MODE_SELECT_10_LLBAA_OFFSET] & - MODE_SELECT_10_LLBAA_MASK; - } else { - /* 6 Byte CDB */ - *bd_len = parm_list[MODE_SELECT_6_BD_OFFSET]; - } -} - -static void nvme_trans_modesel_save_bd(struct nvme_ns *ns, u8 *parm_list, - u16 idx, u16 bd_len, u8 llbaa) -{ - /* Store block descriptor info if a FORMAT UNIT comes later */ - /* TODO Saving 1st BD info; what to do if multiple BD received? */ - if (llbaa == 0) { - /* Standard Block Descriptor - spc4r34 7.5.5.1 */ - ns->mode_select_num_blocks = - (parm_list[idx + 1] << 16) + - (parm_list[idx + 2] << 8) + - (parm_list[idx + 3]); - - ns->mode_select_block_len = - (parm_list[idx + 5] << 16) + - (parm_list[idx + 6] << 8) + - (parm_list[idx + 7]); - } else { - /* Long LBA Block Descriptor - sbc3r27 6.4.2.3 */ - ns->mode_select_num_blocks = - (((u64)parm_list[idx + 0]) << 56) + - (((u64)parm_list[idx + 1]) << 48) + - (((u64)parm_list[idx + 2]) << 40) + - (((u64)parm_list[idx + 3]) << 32) + - (((u64)parm_list[idx + 4]) << 24) + - (((u64)parm_list[idx + 5]) << 16) + - (((u64)parm_list[idx + 6]) << 8) + - ((u64)parm_list[idx + 7]); - - ns->mode_select_block_len = - (parm_list[idx + 12] << 24) + - (parm_list[idx + 13] << 16) + - (parm_list[idx + 14] << 8) + - (parm_list[idx + 15]); - } -} - -static int nvme_trans_modesel_get_mp(struct nvme_ns *ns, struct sg_io_hdr *hdr, - u8 *mode_page, u8 page_code) -{ - int res = 0; - int nvme_sc; - unsigned dword11; - - switch (page_code) { - case MODE_PAGE_CACHING: - dword11 = ((mode_page[2] & CACHING_MODE_PAGE_WCE_MASK) ? 1 : 0); - nvme_sc = nvme_set_features(ns->ctrl, NVME_FEAT_VOLATILE_WC, - dword11, NULL, 0, NULL); - res = nvme_trans_status_code(hdr, nvme_sc); - break; - case MODE_PAGE_CONTROL: - break; - case MODE_PAGE_POWER_CONDITION: - /* Verify the OS is not trying to set timers */ - if ((mode_page[2] & 0x01) != 0 || (mode_page[3] & 0x0F) != 0) { - res = nvme_trans_completion(hdr, - SAM_STAT_CHECK_CONDITION, - ILLEGAL_REQUEST, - SCSI_ASC_INVALID_PARAMETER, - SCSI_ASCQ_CAUSE_NOT_REPORTABLE); - break; - } - break; - default: - res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION, - ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB, - SCSI_ASCQ_CAUSE_NOT_REPORTABLE); - break; - } - - return res; -} - -static int nvme_trans_modesel_data(struct nvme_ns *ns, struct sg_io_hdr *hdr, - u8 *cmd, u16 parm_list_len, u8 pf, - u8 sp, u8 cdb10) -{ - int res; - u8 *parm_list; - u16 bd_len; - u8 llbaa = 0; - u16 index, saved_index; - u8 page_code; - u16 mp_size; - - /* Get parm list from data-in/out buffer */ - parm_list = kmalloc(parm_list_len, GFP_KERNEL); - if (parm_list == NULL) { - res = -ENOMEM; - goto out; - } - - res = nvme_trans_copy_from_user(hdr, parm_list, parm_list_len); - if (res) - goto out_mem; - - nvme_trans_modesel_get_bd_len(parm_list, cdb10, &bd_len, &llbaa); - index = (cdb10) ? (MODE_SELECT_10_MPH_SIZE) : (MODE_SELECT_6_MPH_SIZE); - - if (bd_len != 0) { - /* Block Descriptors present, parse */ - nvme_trans_modesel_save_bd(ns, parm_list, index, bd_len, llbaa); - index += bd_len; - } - saved_index = index; - - /* Multiple mode pages may be present; iterate through all */ - /* In 1st Iteration, don't do NVME Command, only check for CDB errors */ - do { - page_code = parm_list[index] & MODE_SELECT_PAGE_CODE_MASK; - mp_size = parm_list[index + 1] + 2; - if ((page_code != MODE_PAGE_CACHING) && - (page_code != MODE_PAGE_CONTROL) && - (page_code != MODE_PAGE_POWER_CONDITION)) { - res = nvme_trans_completion(hdr, - SAM_STAT_CHECK_CONDITION, - ILLEGAL_REQUEST, - SCSI_ASC_INVALID_CDB, - SCSI_ASCQ_CAUSE_NOT_REPORTABLE); - goto out_mem; - } - index += mp_size; - } while (index < parm_list_len); - - /* In 2nd Iteration, do the NVME Commands */ - index = saved_index; - do { - page_code = parm_list[index] & MODE_SELECT_PAGE_CODE_MASK; - mp_size = parm_list[index + 1] + 2; - res = nvme_trans_modesel_get_mp(ns, hdr, &parm_list[index], - page_code); - if (res) - break; - index += mp_size; - } while (index < parm_list_len); - - out_mem: - kfree(parm_list); - out: - return res; -} - -/* Format Unit Helper Functions */ - -static int nvme_trans_fmt_set_blk_size_count(struct nvme_ns *ns, - struct sg_io_hdr *hdr) -{ - int res = 0; - int nvme_sc; - u8 flbas; - - /* - * SCSI Expects a MODE SELECT would have been issued prior to - * a FORMAT UNIT, and the block size and number would be used - * from the block descriptor in it. If a MODE SELECT had not - * been issued, FORMAT shall use the current values for both. - */ - - if (ns->mode_select_num_blocks == 0 || ns->mode_select_block_len == 0) { - struct nvme_id_ns *id_ns; - - nvme_sc = nvme_identify_ns(ns->ctrl, ns->ns_id, &id_ns); - res = nvme_trans_status_code(hdr, nvme_sc); - if (res) - return res; - - if (ns->mode_select_num_blocks == 0) - ns->mode_select_num_blocks = le64_to_cpu(id_ns->ncap); - if (ns->mode_select_block_len == 0) { - flbas = (id_ns->flbas) & 0x0F; - ns->mode_select_block_len = - (1 << (id_ns->lbaf[flbas].ds)); - } - - kfree(id_ns); - } - - return 0; -} - -static int nvme_trans_fmt_get_parm_header(struct sg_io_hdr *hdr, u8 len, - u8 format_prot_info, u8 *nvme_pf_code) -{ - int res; - u8 *parm_list; - u8 pf_usage, pf_code; - - parm_list = kmalloc(len, GFP_KERNEL); - if (parm_list == NULL) { - res = -ENOMEM; - goto out; - } - res = nvme_trans_copy_from_user(hdr, parm_list, len); - if (res) - goto out_mem; - - if ((parm_list[FORMAT_UNIT_IMMED_OFFSET] & - FORMAT_UNIT_IMMED_MASK) != 0) { - res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION, - ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB, - SCSI_ASCQ_CAUSE_NOT_REPORTABLE); - goto out_mem; - } - - if (len == FORMAT_UNIT_LONG_PARM_LIST_LEN && - (parm_list[FORMAT_UNIT_PROT_INT_OFFSET] & 0x0F) != 0) { - res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION, - ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB, - SCSI_ASCQ_CAUSE_NOT_REPORTABLE); - goto out_mem; - } - pf_usage = parm_list[FORMAT_UNIT_PROT_FIELD_USAGE_OFFSET] & - FORMAT_UNIT_PROT_FIELD_USAGE_MASK; - pf_code = (pf_usage << 2) | format_prot_info; - switch (pf_code) { - case 0: - *nvme_pf_code = 0; - break; - case 2: - *nvme_pf_code = 1; - break; - case 3: - *nvme_pf_code = 2; - break; - case 7: - *nvme_pf_code = 3; - break; - default: - res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION, - ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB, - SCSI_ASCQ_CAUSE_NOT_REPORTABLE); - break; - } - - out_mem: - kfree(parm_list); - out: - return res; -} - -static int nvme_trans_fmt_send_cmd(struct nvme_ns *ns, struct sg_io_hdr *hdr, - u8 prot_info) -{ - int res; - int nvme_sc; - struct nvme_id_ns *id_ns; - u8 i; - u8 nlbaf; - u8 selected_lbaf = 0xFF; - u32 cdw10 = 0; - struct nvme_command c; - - /* Loop thru LBAF's in id_ns to match reqd lbaf, put in cdw10 */ - nvme_sc = nvme_identify_ns(ns->ctrl, ns->ns_id, &id_ns); - res = nvme_trans_status_code(hdr, nvme_sc); - if (res) - return res; - - nlbaf = id_ns->nlbaf; - - for (i = 0; i < nlbaf; i++) { - if (ns->mode_select_block_len == (1 << (id_ns->lbaf[i].ds))) { - selected_lbaf = i; - break; - } - } - if (selected_lbaf > 0x0F) { - res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION, - ILLEGAL_REQUEST, SCSI_ASC_INVALID_PARAMETER, - SCSI_ASCQ_CAUSE_NOT_REPORTABLE); - } - if (ns->mode_select_num_blocks != le64_to_cpu(id_ns->ncap)) { - res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION, - ILLEGAL_REQUEST, SCSI_ASC_INVALID_PARAMETER, - SCSI_ASCQ_CAUSE_NOT_REPORTABLE); - } - - cdw10 |= prot_info << 5; - cdw10 |= selected_lbaf & 0x0F; - memset(&c, 0, sizeof(c)); - c.format.opcode = nvme_admin_format_nvm; - c.format.nsid = cpu_to_le32(ns->ns_id); - c.format.cdw10 = cpu_to_le32(cdw10); - - nvme_sc = nvme_submit_sync_cmd(ns->ctrl->admin_q, &c, NULL, 0); - res = nvme_trans_status_code(hdr, nvme_sc); - - kfree(id_ns); - return res; -} - -static inline u32 nvme_trans_io_get_num_cmds(struct sg_io_hdr *hdr, - struct nvme_trans_io_cdb *cdb_info, - u32 max_blocks) -{ - /* If using iovecs, send one nvme command per vector */ - if (hdr->iovec_count > 0) - return hdr->iovec_count; - else if (cdb_info->xfer_len > max_blocks) - return ((cdb_info->xfer_len - 1) / max_blocks) + 1; - else - return 1; -} - -static u16 nvme_trans_io_get_control(struct nvme_ns *ns, - struct nvme_trans_io_cdb *cdb_info) -{ - u16 control = 0; - - /* When Protection information support is added, implement here */ - - if (cdb_info->fua > 0) - control |= NVME_RW_FUA; - - return control; -} - -static int nvme_trans_do_nvme_io(struct nvme_ns *ns, struct sg_io_hdr *hdr, - struct nvme_trans_io_cdb *cdb_info, u8 is_write) -{ - int nvme_sc = NVME_SC_SUCCESS; - u32 num_cmds; - u64 unit_len; - u64 unit_num_blocks; /* Number of blocks to xfer in each nvme cmd */ - u32 retcode; - u32 i = 0; - u64 nvme_offset = 0; - void __user *next_mapping_addr; - struct nvme_command c; - u8 opcode = (is_write ? nvme_cmd_write : nvme_cmd_read); - u16 control; - u32 max_blocks = queue_max_hw_sectors(ns->queue) >> (ns->lba_shift - 9); - - num_cmds = nvme_trans_io_get_num_cmds(hdr, cdb_info, max_blocks); - - /* - * This loop handles two cases. - * First, when an SGL is used in the form of an iovec list: - * - Use iov_base as the next mapping address for the nvme command_id - * - Use iov_len as the data transfer length for the command. - * Second, when we have a single buffer - * - If larger than max_blocks, split into chunks, offset - * each nvme command accordingly. - */ - for (i = 0; i < num_cmds; i++) { - memset(&c, 0, sizeof(c)); - if (hdr->iovec_count > 0) { - struct sg_iovec sgl; - - retcode = copy_from_user(&sgl, hdr->dxferp + - i * sizeof(struct sg_iovec), - sizeof(struct sg_iovec)); - if (retcode) - return -EFAULT; - unit_len = sgl.iov_len; - unit_num_blocks = unit_len >> ns->lba_shift; - next_mapping_addr = sgl.iov_base; - } else { - unit_num_blocks = min((u64)max_blocks, - (cdb_info->xfer_len - nvme_offset)); - unit_len = unit_num_blocks << ns->lba_shift; - next_mapping_addr = hdr->dxferp + - ((1 << ns->lba_shift) * nvme_offset); - } - - c.rw.opcode = opcode; - c.rw.nsid = cpu_to_le32(ns->ns_id); - c.rw.slba = cpu_to_le64(cdb_info->lba + nvme_offset); - c.rw.length = cpu_to_le16(unit_num_blocks - 1); - control = nvme_trans_io_get_control(ns, cdb_info); - c.rw.control = cpu_to_le16(control); - - if (get_capacity(ns->disk) - unit_num_blocks < - cdb_info->lba + nvme_offset) { - nvme_sc = NVME_SC_LBA_RANGE; - break; - } - nvme_sc = nvme_submit_user_cmd(ns->queue, &c, - next_mapping_addr, unit_len, NULL, 0); - if (nvme_sc) - break; - - nvme_offset += unit_num_blocks; - } - - return nvme_trans_status_code(hdr, nvme_sc); -} - - -/* SCSI Command Translation Functions */ - -static int nvme_trans_io(struct nvme_ns *ns, struct sg_io_hdr *hdr, u8 is_write, - u8 *cmd) -{ - int res = 0; - struct nvme_trans_io_cdb cdb_info = { 0, }; - u8 opcode = cmd[0]; - u64 xfer_bytes; - u64 sum_iov_len = 0; - struct sg_iovec sgl; - int i; - size_t not_copied; - - /* - * The FUA and WPROTECT fields are not supported in 6-byte CDBs, - * but always in the same place for all others. - */ - switch (opcode) { - case WRITE_6: - case READ_6: - break; - default: - cdb_info.fua = cmd[1] & 0x8; - cdb_info.prot_info = (cmd[1] & 0xe0) >> 5; - if (cdb_info.prot_info && !ns->pi_type) { - return nvme_trans_completion(hdr, - SAM_STAT_CHECK_CONDITION, - ILLEGAL_REQUEST, - SCSI_ASC_INVALID_CDB, - SCSI_ASCQ_CAUSE_NOT_REPORTABLE); - } - } - - switch (opcode) { - case WRITE_6: - case READ_6: - cdb_info.lba = get_unaligned_be24(&cmd[1]); - cdb_info.xfer_len = cmd[4]; - if (cdb_info.xfer_len == 0) - cdb_info.xfer_len = 256; - break; - case WRITE_10: - case READ_10: - cdb_info.lba = get_unaligned_be32(&cmd[2]); - cdb_info.xfer_len = get_unaligned_be16(&cmd[7]); - break; - case WRITE_12: - case READ_12: - cdb_info.lba = get_unaligned_be32(&cmd[2]); - cdb_info.xfer_len = get_unaligned_be32(&cmd[6]); - break; - case WRITE_16: - case READ_16: - cdb_info.lba = get_unaligned_be64(&cmd[2]); - cdb_info.xfer_len = get_unaligned_be32(&cmd[10]); - break; - default: - /* Will never really reach here */ - res = -EIO; - goto out; - } - - /* Calculate total length of transfer (in bytes) */ - if (hdr->iovec_count > 0) { - for (i = 0; i < hdr->iovec_count; i++) { - not_copied = copy_from_user(&sgl, hdr->dxferp + - i * sizeof(struct sg_iovec), - sizeof(struct sg_iovec)); - if (not_copied) - return -EFAULT; - sum_iov_len += sgl.iov_len; - /* IO vector sizes should be multiples of block size */ - if (sgl.iov_len % (1 << ns->lba_shift) != 0) { - res = nvme_trans_completion(hdr, - SAM_STAT_CHECK_CONDITION, - ILLEGAL_REQUEST, - SCSI_ASC_INVALID_PARAMETER, - SCSI_ASCQ_CAUSE_NOT_REPORTABLE); - goto out; - } - } - } else { - sum_iov_len = hdr->dxfer_len; - } - - /* As Per sg ioctl howto, if the lengths differ, use the lower one */ - xfer_bytes = min(((u64)hdr->dxfer_len), sum_iov_len); - - /* If block count and actual data buffer size dont match, error out */ - if (xfer_bytes != (cdb_info.xfer_len << ns->lba_shift)) { - res = -EINVAL; - goto out; - } - - /* Check for 0 length transfer - it is not illegal */ - if (cdb_info.xfer_len == 0) - goto out; - - /* Send NVMe IO Command(s) */ - res = nvme_trans_do_nvme_io(ns, hdr, &cdb_info, is_write); - if (res) - goto out; - - out: - return res; -} - -static int nvme_trans_inquiry(struct nvme_ns *ns, struct sg_io_hdr *hdr, - u8 *cmd) -{ - int res = 0; - u8 evpd; - u8 page_code; - int alloc_len; - u8 *inq_response; - - evpd = cmd[1] & 0x01; - page_code = cmd[2]; - alloc_len = get_unaligned_be16(&cmd[3]); - - inq_response = kmalloc(max(alloc_len, STANDARD_INQUIRY_LENGTH), - GFP_KERNEL); - if (inq_response == NULL) { - res = -ENOMEM; - goto out_mem; - } - - if (evpd == 0) { - if (page_code == INQ_STANDARD_INQUIRY_PAGE) { - res = nvme_trans_standard_inquiry_page(ns, hdr, - inq_response, alloc_len); - } else { - res = nvme_trans_completion(hdr, - SAM_STAT_CHECK_CONDITION, - ILLEGAL_REQUEST, - SCSI_ASC_INVALID_CDB, - SCSI_ASCQ_CAUSE_NOT_REPORTABLE); - } - } else { - switch (page_code) { - case VPD_SUPPORTED_PAGES: - res = nvme_trans_supported_vpd_pages(ns, hdr, - inq_response, alloc_len); - break; - case VPD_SERIAL_NUMBER: - res = nvme_trans_unit_serial_page(ns, hdr, inq_response, - alloc_len); - break; - case VPD_DEVICE_IDENTIFIERS: - res = nvme_trans_device_id_page(ns, hdr, inq_response, - alloc_len); - break; - case VPD_EXTENDED_INQUIRY: - res = nvme_trans_ext_inq_page(ns, hdr, alloc_len); - break; - case VPD_BLOCK_LIMITS: - res = nvme_trans_bdev_limits_page(ns, hdr, inq_response, - alloc_len); - break; - case VPD_BLOCK_DEV_CHARACTERISTICS: - res = nvme_trans_bdev_char_page(ns, hdr, alloc_len); - break; - default: - res = nvme_trans_completion(hdr, - SAM_STAT_CHECK_CONDITION, - ILLEGAL_REQUEST, - SCSI_ASC_INVALID_CDB, - SCSI_ASCQ_CAUSE_NOT_REPORTABLE); - break; - } - } - kfree(inq_response); - out_mem: - return res; -} - -static int nvme_trans_log_sense(struct nvme_ns *ns, struct sg_io_hdr *hdr, - u8 *cmd) -{ - int res; - u16 alloc_len; - u8 pc; - u8 page_code; - - if (cmd[1] != LOG_SENSE_CDB_SP_NOT_ENABLED) { - res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION, - ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB, - SCSI_ASCQ_CAUSE_NOT_REPORTABLE); - goto out; - } - - page_code = cmd[2] & LOG_SENSE_CDB_PAGE_CODE_MASK; - pc = (cmd[2] & LOG_SENSE_CDB_PC_MASK) >> LOG_SENSE_CDB_PC_SHIFT; - if (pc != LOG_SENSE_CDB_PC_CUMULATIVE_VALUES) { - res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION, - ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB, - SCSI_ASCQ_CAUSE_NOT_REPORTABLE); - goto out; - } - alloc_len = get_unaligned_be16(&cmd[7]); - switch (page_code) { - case LOG_PAGE_SUPPORTED_LOG_PAGES_PAGE: - res = nvme_trans_log_supp_pages(ns, hdr, alloc_len); - break; - case LOG_PAGE_INFORMATIONAL_EXCEPTIONS_PAGE: - res = nvme_trans_log_info_exceptions(ns, hdr, alloc_len); - break; - case LOG_PAGE_TEMPERATURE_PAGE: - res = nvme_trans_log_temperature(ns, hdr, alloc_len); - break; - default: - res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION, - ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB, - SCSI_ASCQ_CAUSE_NOT_REPORTABLE); - break; - } - - out: - return res; -} - -static int nvme_trans_mode_select(struct nvme_ns *ns, struct sg_io_hdr *hdr, - u8 *cmd) -{ - u8 cdb10 = 0; - u16 parm_list_len; - u8 page_format; - u8 save_pages; - - page_format = cmd[1] & MODE_SELECT_CDB_PAGE_FORMAT_MASK; - save_pages = cmd[1] & MODE_SELECT_CDB_SAVE_PAGES_MASK; - - if (cmd[0] == MODE_SELECT) { - parm_list_len = cmd[4]; - } else { - parm_list_len = cmd[7]; - cdb10 = 1; - } - - if (parm_list_len != 0) { - /* - * According to SPC-4 r24, a paramter list length field of 0 - * shall not be considered an error - */ - return nvme_trans_modesel_data(ns, hdr, cmd, parm_list_len, - page_format, save_pages, cdb10); - } - - return 0; -} - -static int nvme_trans_mode_sense(struct nvme_ns *ns, struct sg_io_hdr *hdr, - u8 *cmd) -{ - int res = 0; - u16 alloc_len; - u8 cdb10 = 0; - - if (cmd[0] == MODE_SENSE) { - alloc_len = cmd[4]; - } else { - alloc_len = get_unaligned_be16(&cmd[7]); - cdb10 = 1; - } - - if ((cmd[2] & MODE_SENSE_PAGE_CONTROL_MASK) != - MODE_SENSE_PC_CURRENT_VALUES) { - res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION, - ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB, - SCSI_ASCQ_CAUSE_NOT_REPORTABLE); - goto out; - } - - switch (cmd[2] & MODE_SENSE_PAGE_CODE_MASK) { - case MODE_PAGE_CACHING: - res = nvme_trans_mode_page_create(ns, hdr, cmd, alloc_len, - cdb10, - &nvme_trans_fill_caching_page, - MODE_PAGE_CACHING_LEN); - break; - case MODE_PAGE_CONTROL: - res = nvme_trans_mode_page_create(ns, hdr, cmd, alloc_len, - cdb10, - &nvme_trans_fill_control_page, - MODE_PAGE_CONTROL_LEN); - break; - case MODE_PAGE_POWER_CONDITION: - res = nvme_trans_mode_page_create(ns, hdr, cmd, alloc_len, - cdb10, - &nvme_trans_fill_pow_cnd_page, - MODE_PAGE_POW_CND_LEN); - break; - case MODE_PAGE_INFO_EXCEP: - res = nvme_trans_mode_page_create(ns, hdr, cmd, alloc_len, - cdb10, - &nvme_trans_fill_inf_exc_page, - MODE_PAGE_INF_EXC_LEN); - break; - case MODE_PAGE_RETURN_ALL: - res = nvme_trans_mode_page_create(ns, hdr, cmd, alloc_len, - cdb10, - &nvme_trans_fill_all_pages, - MODE_PAGE_ALL_LEN); - break; - default: - res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION, - ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB, - SCSI_ASCQ_CAUSE_NOT_REPORTABLE); - break; - } - - out: - return res; -} - -static int nvme_trans_read_capacity(struct nvme_ns *ns, struct sg_io_hdr *hdr, - u8 *cmd, u8 cdb16) -{ - int res; - int nvme_sc; - u32 alloc_len; - u32 resp_size; - u32 xfer_len; - struct nvme_id_ns *id_ns; - u8 *response; - - if (cdb16) { - alloc_len = get_unaligned_be32(&cmd[10]); - resp_size = READ_CAP_16_RESP_SIZE; - } else { - alloc_len = READ_CAP_10_RESP_SIZE; - resp_size = READ_CAP_10_RESP_SIZE; - } - - nvme_sc = nvme_identify_ns(ns->ctrl, ns->ns_id, &id_ns); - res = nvme_trans_status_code(hdr, nvme_sc); - if (res) - return res; - - response = kzalloc(resp_size, GFP_KERNEL); - if (response == NULL) { - res = -ENOMEM; - goto out_free_id; - } - nvme_trans_fill_read_cap(response, id_ns, cdb16); - - xfer_len = min(alloc_len, resp_size); - res = nvme_trans_copy_to_user(hdr, response, xfer_len); - - kfree(response); - out_free_id: - kfree(id_ns); - return res; -} - -static int nvme_trans_report_luns(struct nvme_ns *ns, struct sg_io_hdr *hdr, - u8 *cmd) -{ - int res; - int nvme_sc; - u32 alloc_len, xfer_len, resp_size; - u8 *response; - struct nvme_id_ctrl *id_ctrl; - u32 ll_length, lun_id; - u8 lun_id_offset = REPORT_LUNS_FIRST_LUN_OFFSET; - __be32 tmp_len; - - switch (cmd[2]) { - default: - return nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION, - ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB, - SCSI_ASCQ_CAUSE_NOT_REPORTABLE); - case ALL_LUNS_RETURNED: - case ALL_WELL_KNOWN_LUNS_RETURNED: - case RESTRICTED_LUNS_RETURNED: - nvme_sc = nvme_identify_ctrl(ns->ctrl, &id_ctrl); - res = nvme_trans_status_code(hdr, nvme_sc); - if (res) - return res; - - ll_length = le32_to_cpu(id_ctrl->nn) * LUN_ENTRY_SIZE; - resp_size = ll_length + LUN_DATA_HEADER_SIZE; - - alloc_len = get_unaligned_be32(&cmd[6]); - if (alloc_len < resp_size) { - res = nvme_trans_completion(hdr, - SAM_STAT_CHECK_CONDITION, - ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB, - SCSI_ASCQ_CAUSE_NOT_REPORTABLE); - goto out_free_id; - } - - response = kzalloc(resp_size, GFP_KERNEL); - if (response == NULL) { - res = -ENOMEM; - goto out_free_id; - } - - /* The first LUN ID will always be 0 per the SAM spec */ - for (lun_id = 0; lun_id < le32_to_cpu(id_ctrl->nn); lun_id++) { - /* - * Set the LUN Id and then increment to the next LUN - * location in the parameter data. - */ - __be64 tmp_id = cpu_to_be64(lun_id); - memcpy(&response[lun_id_offset], &tmp_id, sizeof(u64)); - lun_id_offset += LUN_ENTRY_SIZE; - } - tmp_len = cpu_to_be32(ll_length); - memcpy(response, &tmp_len, sizeof(u32)); - } - - xfer_len = min(alloc_len, resp_size); - res = nvme_trans_copy_to_user(hdr, response, xfer_len); - - kfree(response); - out_free_id: - kfree(id_ctrl); - return res; -} - -static int nvme_trans_request_sense(struct nvme_ns *ns, struct sg_io_hdr *hdr, - u8 *cmd) -{ - int res; - u8 alloc_len, xfer_len, resp_size; - u8 desc_format; - u8 *response; - - desc_format = cmd[1] & 0x01; - alloc_len = cmd[4]; - - resp_size = ((desc_format) ? (DESC_FMT_SENSE_DATA_SIZE) : - (FIXED_FMT_SENSE_DATA_SIZE)); - response = kzalloc(resp_size, GFP_KERNEL); - if (response == NULL) { - res = -ENOMEM; - goto out; - } - - if (desc_format) { - /* Descriptor Format Sense Data */ - response[0] = DESC_FORMAT_SENSE_DATA; - response[1] = NO_SENSE; - /* TODO How is LOW POWER CONDITION ON handled? (byte 2) */ - response[2] = SCSI_ASC_NO_SENSE; - response[3] = SCSI_ASCQ_CAUSE_NOT_REPORTABLE; - /* SDAT_OVFL = 0 | Additional Sense Length = 0 */ - } else { - /* Fixed Format Sense Data */ - response[0] = FIXED_SENSE_DATA; - /* Byte 1 = Obsolete */ - response[2] = NO_SENSE; /* FM, EOM, ILI, SDAT_OVFL = 0 */ - /* Bytes 3-6 - Information - set to zero */ - response[7] = FIXED_SENSE_DATA_ADD_LENGTH; - /* Bytes 8-11 - Cmd Specific Information - set to zero */ - response[12] = SCSI_ASC_NO_SENSE; - response[13] = SCSI_ASCQ_CAUSE_NOT_REPORTABLE; - /* Byte 14 = Field Replaceable Unit Code = 0 */ - /* Bytes 15-17 - SKSV=0; Sense Key Specific = 0 */ - } - - xfer_len = min(alloc_len, resp_size); - res = nvme_trans_copy_to_user(hdr, response, xfer_len); - - kfree(response); - out: - return res; -} - -static int nvme_trans_synchronize_cache(struct nvme_ns *ns, - struct sg_io_hdr *hdr) -{ - int nvme_sc; - struct nvme_command c; - - memset(&c, 0, sizeof(c)); - c.common.opcode = nvme_cmd_flush; - c.common.nsid = cpu_to_le32(ns->ns_id); - - nvme_sc = nvme_submit_sync_cmd(ns->queue, &c, NULL, 0); - return nvme_trans_status_code(hdr, nvme_sc); -} - -static int nvme_trans_format_unit(struct nvme_ns *ns, struct sg_io_hdr *hdr, - u8 *cmd) -{ - int res; - u8 parm_hdr_len = 0; - u8 nvme_pf_code = 0; - u8 format_prot_info, long_list, format_data; - - format_prot_info = (cmd[1] & 0xc0) >> 6; - long_list = cmd[1] & 0x20; - format_data = cmd[1] & 0x10; - - if (format_data != 0) { - if (format_prot_info != 0) { - if (long_list == 0) - parm_hdr_len = FORMAT_UNIT_SHORT_PARM_LIST_LEN; - else - parm_hdr_len = FORMAT_UNIT_LONG_PARM_LIST_LEN; - } - } else if (format_data == 0 && format_prot_info != 0) { - res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION, - ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB, - SCSI_ASCQ_CAUSE_NOT_REPORTABLE); - goto out; - } - - /* Get parm header from data-in/out buffer */ - /* - * According to the translation spec, the only fields in the parameter - * list we are concerned with are in the header. So allocate only that. - */ - if (parm_hdr_len > 0) { - res = nvme_trans_fmt_get_parm_header(hdr, parm_hdr_len, - format_prot_info, &nvme_pf_code); - if (res) - goto out; - } - - /* Attempt to activate any previously downloaded firmware image */ - res = nvme_trans_send_activate_fw_cmd(ns, hdr, 0); - - /* Determine Block size and count and send format command */ - res = nvme_trans_fmt_set_blk_size_count(ns, hdr); - if (res) - goto out; - - res = nvme_trans_fmt_send_cmd(ns, hdr, nvme_pf_code); - - out: - return res; -} - -static int nvme_trans_test_unit_ready(struct nvme_ns *ns, - struct sg_io_hdr *hdr, - u8 *cmd) -{ - if (nvme_ctrl_ready(ns->ctrl)) - return nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION, - NOT_READY, SCSI_ASC_LUN_NOT_READY, - SCSI_ASCQ_CAUSE_NOT_REPORTABLE); - else - return nvme_trans_completion(hdr, SAM_STAT_GOOD, NO_SENSE, 0, 0); -} - -static int nvme_trans_write_buffer(struct nvme_ns *ns, struct sg_io_hdr *hdr, - u8 *cmd) -{ - int res = 0; - u32 buffer_offset, parm_list_length; - u8 buffer_id, mode; - - parm_list_length = get_unaligned_be24(&cmd[6]); - if (parm_list_length % BYTES_TO_DWORDS != 0) { - /* NVMe expects Firmware file to be a whole number of DWORDS */ - res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION, - ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB, - SCSI_ASCQ_CAUSE_NOT_REPORTABLE); - goto out; - } - buffer_id = cmd[2]; - if (buffer_id > NVME_MAX_FIRMWARE_SLOT) { - res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION, - ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB, - SCSI_ASCQ_CAUSE_NOT_REPORTABLE); - goto out; - } - mode = cmd[1] & 0x1f; - buffer_offset = get_unaligned_be24(&cmd[3]); - - switch (mode) { - case DOWNLOAD_SAVE_ACTIVATE: - res = nvme_trans_send_download_fw_cmd(ns, hdr, nvme_admin_download_fw, - parm_list_length, buffer_offset, - buffer_id); - if (res) - goto out; - res = nvme_trans_send_activate_fw_cmd(ns, hdr, buffer_id); - break; - case DOWNLOAD_SAVE_DEFER_ACTIVATE: - res = nvme_trans_send_download_fw_cmd(ns, hdr, nvme_admin_download_fw, - parm_list_length, buffer_offset, - buffer_id); - break; - case ACTIVATE_DEFERRED_MICROCODE: - res = nvme_trans_send_activate_fw_cmd(ns, hdr, buffer_id); - break; - default: - res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION, - ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB, - SCSI_ASCQ_CAUSE_NOT_REPORTABLE); - break; - } - - out: - return res; -} - -struct scsi_unmap_blk_desc { - __be64 slba; - __be32 nlb; - u32 resv; -}; - -struct scsi_unmap_parm_list { - __be16 unmap_data_len; - __be16 unmap_blk_desc_data_len; - u32 resv; - struct scsi_unmap_blk_desc desc[0]; -}; - -static int nvme_trans_unmap(struct nvme_ns *ns, struct sg_io_hdr *hdr, - u8 *cmd) -{ - struct scsi_unmap_parm_list *plist; - struct nvme_dsm_range *range; - struct nvme_command c; - int i, nvme_sc, res; - u16 ndesc, list_len; - - list_len = get_unaligned_be16(&cmd[7]); - if (!list_len) - return -EINVAL; - - plist = kmalloc(list_len, GFP_KERNEL); - if (!plist) - return -ENOMEM; - - res = nvme_trans_copy_from_user(hdr, plist, list_len); - if (res) - goto out; - - ndesc = be16_to_cpu(plist->unmap_blk_desc_data_len) >> 4; - if (!ndesc || ndesc > 256) { - res = -EINVAL; - goto out; - } - - range = kcalloc(ndesc, sizeof(*range), GFP_KERNEL); - if (!range) { - res = -ENOMEM; - goto out; - } - - for (i = 0; i < ndesc; i++) { - range[i].nlb = cpu_to_le32(be32_to_cpu(plist->desc[i].nlb)); - range[i].slba = cpu_to_le64(be64_to_cpu(plist->desc[i].slba)); - range[i].cattr = 0; - } - - memset(&c, 0, sizeof(c)); - c.dsm.opcode = nvme_cmd_dsm; - c.dsm.nsid = cpu_to_le32(ns->ns_id); - c.dsm.nr = cpu_to_le32(ndesc - 1); - c.dsm.attributes = cpu_to_le32(NVME_DSMGMT_AD); - - nvme_sc = nvme_submit_sync_cmd(ns->queue, &c, range, - ndesc * sizeof(*range)); - res = nvme_trans_status_code(hdr, nvme_sc); - - kfree(range); - out: - kfree(plist); - return res; -} - -static int nvme_scsi_translate(struct nvme_ns *ns, struct sg_io_hdr *hdr) -{ - u8 cmd[16]; - int retcode; - unsigned int opcode; - - if (hdr->cmdp == NULL) - return -EMSGSIZE; - if (hdr->cmd_len > sizeof(cmd)) - return -EINVAL; - if (copy_from_user(cmd, hdr->cmdp, hdr->cmd_len)) - return -EFAULT; - - /* - * Prime the hdr with good status for scsi commands that don't require - * an nvme command for translation. - */ - retcode = nvme_trans_status_code(hdr, NVME_SC_SUCCESS); - if (retcode) - return retcode; - - opcode = cmd[0]; - - switch (opcode) { - case READ_6: - case READ_10: - case READ_12: - case READ_16: - retcode = nvme_trans_io(ns, hdr, 0, cmd); - break; - case WRITE_6: - case WRITE_10: - case WRITE_12: - case WRITE_16: - retcode = nvme_trans_io(ns, hdr, 1, cmd); - break; - case INQUIRY: - retcode = nvme_trans_inquiry(ns, hdr, cmd); - break; - case LOG_SENSE: - retcode = nvme_trans_log_sense(ns, hdr, cmd); - break; - case MODE_SELECT: - case MODE_SELECT_10: - retcode = nvme_trans_mode_select(ns, hdr, cmd); - break; - case MODE_SENSE: - case MODE_SENSE_10: - retcode = nvme_trans_mode_sense(ns, hdr, cmd); - break; - case READ_CAPACITY: - retcode = nvme_trans_read_capacity(ns, hdr, cmd, 0); - break; - case SERVICE_ACTION_IN_16: - switch (cmd[1]) { - case SAI_READ_CAPACITY_16: - retcode = nvme_trans_read_capacity(ns, hdr, cmd, 1); - break; - default: - goto out; - } - break; - case REPORT_LUNS: - retcode = nvme_trans_report_luns(ns, hdr, cmd); - break; - case REQUEST_SENSE: - retcode = nvme_trans_request_sense(ns, hdr, cmd); - break; - case SYNCHRONIZE_CACHE: - retcode = nvme_trans_synchronize_cache(ns, hdr); - break; - case FORMAT_UNIT: - retcode = nvme_trans_format_unit(ns, hdr, cmd); - break; - case TEST_UNIT_READY: - retcode = nvme_trans_test_unit_ready(ns, hdr, cmd); - break; - case WRITE_BUFFER: - retcode = nvme_trans_write_buffer(ns, hdr, cmd); - break; - case UNMAP: - retcode = nvme_trans_unmap(ns, hdr, cmd); - break; - default: - out: - retcode = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION, - ILLEGAL_REQUEST, SCSI_ASC_ILLEGAL_COMMAND, - SCSI_ASCQ_CAUSE_NOT_REPORTABLE); - break; - } - return retcode; -} - -int nvme_sg_io(struct nvme_ns *ns, struct sg_io_hdr __user *u_hdr) -{ - struct sg_io_hdr hdr; - int retcode; - - if (!capable(CAP_SYS_ADMIN)) - return -EACCES; - if (copy_from_user(&hdr, u_hdr, sizeof(hdr))) - return -EFAULT; - if (hdr.interface_id != 'S') - return -EINVAL; - - /* - * A positive return code means a NVMe status, which has been - * translated to sense data. - */ - retcode = nvme_scsi_translate(ns, &hdr); - if (retcode < 0) - return retcode; - if (copy_to_user(u_hdr, &hdr, sizeof(sg_io_hdr_t)) > 0) - return -EFAULT; - return 0; -} - -int nvme_sg_get_version_num(int __user *ip) -{ - return put_user(sg_version_num, ip); -} diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index ff1f97006322..35f930db3c02 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -336,7 +336,7 @@ out: static void nvmet_execute_identify_nslist(struct nvmet_req *req) { - static const int buf_size = 4096; + static const int buf_size = NVME_IDENTIFY_DATA_SIZE; struct nvmet_ctrl *ctrl = req->sq->ctrl; struct nvmet_ns *ns; u32 min_nsid = le32_to_cpu(req->cmd->identify.nsid); @@ -367,6 +367,64 @@ out: nvmet_req_complete(req, status); } +static u16 nvmet_copy_ns_identifier(struct nvmet_req *req, u8 type, u8 len, + void *id, off_t *off) +{ + struct nvme_ns_id_desc desc = { + .nidt = type, + .nidl = len, + }; + u16 status; + + status = nvmet_copy_to_sgl(req, *off, &desc, sizeof(desc)); + if (status) + return status; + *off += sizeof(desc); + + status = nvmet_copy_to_sgl(req, *off, id, len); + if (status) + return status; + *off += len; + + return 0; +} + +static void nvmet_execute_identify_desclist(struct nvmet_req *req) +{ + struct nvmet_ns *ns; + u16 status = 0; + off_t off = 0; + + ns = nvmet_find_namespace(req->sq->ctrl, req->cmd->identify.nsid); + if (!ns) { + status = NVME_SC_INVALID_NS | NVME_SC_DNR; + goto out; + } + + if (memchr_inv(&ns->uuid, 0, sizeof(ns->uuid))) { + status = nvmet_copy_ns_identifier(req, NVME_NIDT_UUID, + NVME_NIDT_UUID_LEN, + &ns->uuid, &off); + if (status) + goto out_put_ns; + } + if (memchr_inv(ns->nguid, 0, sizeof(ns->nguid))) { + status = nvmet_copy_ns_identifier(req, NVME_NIDT_NGUID, + NVME_NIDT_NGUID_LEN, + &ns->nguid, &off); + if (status) + goto out_put_ns; + } + + if (sg_zero_buffer(req->sg, req->sg_cnt, NVME_IDENTIFY_DATA_SIZE - off, + off) != NVME_IDENTIFY_DATA_SIZE - off) + status = NVME_SC_INTERNAL | NVME_SC_DNR; +out_put_ns: + nvmet_put_namespace(ns); +out: + nvmet_req_complete(req, status); +} + /* * A "mimimum viable" abort implementation: the command is mandatory in the * spec, but we are not required to do any useful work. We couldn't really @@ -504,7 +562,7 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req) } break; case nvme_admin_identify: - req->data_len = 4096; + req->data_len = NVME_IDENTIFY_DATA_SIZE; switch (cmd->identify.cns) { case NVME_ID_CNS_NS: req->execute = nvmet_execute_identify_ns; @@ -515,6 +573,9 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req) case NVME_ID_CNS_NS_ACTIVE_LIST: req->execute = nvmet_execute_identify_nslist; return 0; + case NVME_ID_CNS_NS_DESC_LIST: + req->execute = nvmet_execute_identify_desclist; + return 0; } break; case nvme_admin_abort_cmd: diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index be8c800078e2..a358ecd93e11 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -305,11 +305,41 @@ out_unlock: CONFIGFS_ATTR(nvmet_ns_, device_path); +static ssize_t nvmet_ns_device_uuid_show(struct config_item *item, char *page) +{ + return sprintf(page, "%pUb\n", &to_nvmet_ns(item)->uuid); +} + +static ssize_t nvmet_ns_device_uuid_store(struct config_item *item, + const char *page, size_t count) +{ + struct nvmet_ns *ns = to_nvmet_ns(item); + struct nvmet_subsys *subsys = ns->subsys; + int ret = 0; + + + mutex_lock(&subsys->lock); + if (ns->enabled) { + ret = -EBUSY; + goto out_unlock; + } + + + if (uuid_parse(page, &ns->uuid)) + ret = -EINVAL; + +out_unlock: + mutex_unlock(&subsys->lock); + return ret ? ret : count; +} + static ssize_t nvmet_ns_device_nguid_show(struct config_item *item, char *page) { return sprintf(page, "%pUb\n", &to_nvmet_ns(item)->nguid); } +CONFIGFS_ATTR(nvmet_ns_, device_uuid); + static ssize_t nvmet_ns_device_nguid_store(struct config_item *item, const char *page, size_t count) { @@ -379,6 +409,7 @@ CONFIGFS_ATTR(nvmet_ns_, enable); static struct configfs_attribute *nvmet_ns_attrs[] = { &nvmet_ns_attr_device_path, &nvmet_ns_attr_device_nguid, + &nvmet_ns_attr_device_uuid, &nvmet_ns_attr_enable, NULL, }; @@ -619,8 +650,45 @@ out_unlock: CONFIGFS_ATTR(nvmet_subsys_, attr_allow_any_host); +static ssize_t nvmet_subsys_version_show(struct config_item *item, + char *page) +{ + struct nvmet_subsys *subsys = to_subsys(item); + + if (NVME_TERTIARY(subsys->ver)) + return snprintf(page, PAGE_SIZE, "%d.%d.%d\n", + (int)NVME_MAJOR(subsys->ver), + (int)NVME_MINOR(subsys->ver), + (int)NVME_TERTIARY(subsys->ver)); + else + return snprintf(page, PAGE_SIZE, "%d.%d\n", + (int)NVME_MAJOR(subsys->ver), + (int)NVME_MINOR(subsys->ver)); +} + +static ssize_t nvmet_subsys_version_store(struct config_item *item, + const char *page, size_t count) +{ + struct nvmet_subsys *subsys = to_subsys(item); + int major, minor, tertiary = 0; + int ret; + + + ret = sscanf(page, "%d.%d.%d\n", &major, &minor, &tertiary); + if (ret != 2 && ret != 3) + return -EINVAL; + + down_write(&nvmet_config_sem); + subsys->ver = NVME_VS(major, minor, tertiary); + up_write(&nvmet_config_sem); + + return count; +} +CONFIGFS_ATTR(nvmet_subsys_, version); + static struct configfs_attribute *nvmet_subsys_attrs[] = { &nvmet_subsys_attr_attr_allow_any_host, + &nvmet_subsys_attr_version, NULL, }; diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index eb9399ac97cf..b5b4ac103748 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -380,6 +380,7 @@ struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid) ns->nsid = nsid; ns->subsys = subsys; + uuid_gen(&ns->uuid); return ns; } @@ -926,7 +927,7 @@ struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn, if (!subsys) return NULL; - subsys->ver = NVME_VS(1, 2, 1); /* NVMe 1.2.1 */ + subsys->ver = NVME_VS(1, 3, 0); /* NVMe 1.3.0 */ switch (type) { case NVME_NQN_NVME: diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c index 1aaf597e81fc..8f3b57b4c97b 100644 --- a/drivers/nvme/target/discovery.c +++ b/drivers/nvme/target/discovery.c @@ -53,7 +53,7 @@ static void nvmet_format_discovery_entry(struct nvmf_disc_rsp_page_hdr *hdr, e->portid = port->disc_addr.portid; /* we support only dynamic controllers */ e->cntlid = cpu_to_le16(NVME_CNTLID_DYNAMIC); - e->asqsz = cpu_to_le16(NVMF_AQ_DEPTH); + e->asqsz = cpu_to_le16(NVME_AQ_DEPTH); e->subtype = type; memcpy(e->trsvcid, port->disc_addr.trsvcid, NVMF_TRSVCID_SIZE); memcpy(e->traddr, port->disc_addr.traddr, NVMF_TRADDR_SIZE); @@ -185,7 +185,7 @@ u16 nvmet_parse_discovery_cmd(struct nvmet_req *req) return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; } case nvme_admin_identify: - req->data_len = 4096; + req->data_len = NVME_IDENTIFY_DATA_SIZE; switch (cmd->identify.cns) { case NVME_ID_CNS_CTRL: req->execute = diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index 2006fae61980..7692a96c9065 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -2096,20 +2096,22 @@ nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport, /* clear any response payload */ memset(&fod->rspiubuf, 0, sizeof(fod->rspiubuf)); + fod->data_sg = NULL; + fod->data_sg_cnt = 0; + ret = nvmet_req_init(&fod->req, &fod->queue->nvme_cq, &fod->queue->nvme_sq, &nvmet_fc_tgt_fcp_ops); - if (!ret) { /* bad SQE content or invalid ctrl state */ - nvmet_fc_abort_op(tgtport, fod); + if (!ret) { + /* bad SQE content or invalid ctrl state */ + /* nvmet layer has already called op done to send rsp. */ return; } /* keep a running counter of tail position */ atomic_inc(&fod->queue->sqtail); - fod->data_sg = NULL; - fod->data_sg_cnt = 0; if (fod->total_length) { ret = nvmet_fc_alloc_tgt_pgs(fod); if (ret) { diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index 294a6611fb24..1bb9d5b311b1 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -569,7 +569,6 @@ fcloop_tgt_fcp_abort(struct nvmet_fc_target_port *tgtport, struct nvmefc_tgt_fcp_req *tgt_fcpreq) { struct fcloop_fcpreq *tfcp_req = tgt_fcp_req_to_fcpreq(tgt_fcpreq); - int active; /* * mark aborted only in case there were 2 threads in transport @@ -577,7 +576,6 @@ fcloop_tgt_fcp_abort(struct nvmet_fc_target_port *tgtport, * after the abort request */ spin_lock(&tfcp_req->reqlock); - active = tfcp_req->active; tfcp_req->aborted = true; spin_unlock(&tfcp_req->reqlock); diff --git a/drivers/nvme/target/io-cmd.c b/drivers/nvme/target/io-cmd.c index c77940d80fc8..40128793e613 100644 --- a/drivers/nvme/target/io-cmd.c +++ b/drivers/nvme/target/io-cmd.c @@ -21,7 +21,7 @@ static void nvmet_bio_done(struct bio *bio) struct nvmet_req *req = bio->bi_private; nvmet_req_complete(req, - bio->bi_error ? NVME_SC_INTERNAL | NVME_SC_DNR : 0); + bio->bi_status ? NVME_SC_INTERNAL | NVME_SC_DNR : 0); if (bio != &req->inline_bio) bio_put(bio); @@ -145,7 +145,7 @@ static void nvmet_execute_discard(struct nvmet_req *req) bio->bi_private = req; bio->bi_end_io = nvmet_bio_done; if (status) { - bio->bi_error = -EIO; + bio->bi_status = BLK_STS_IOERR; bio_endio(bio); } else { submit_bio(bio); diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index e503cfff0337..5f55c683b338 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -21,8 +21,6 @@ #include "../host/nvme.h" #include "../host/fabrics.h" -#define NVME_LOOP_AQ_DEPTH 256 - #define NVME_LOOP_MAX_SEGMENTS 256 /* @@ -31,7 +29,7 @@ */ #define NVME_LOOP_NR_AEN_COMMANDS 1 #define NVME_LOOP_AQ_BLKMQ_DEPTH \ - (NVME_LOOP_AQ_DEPTH - NVME_LOOP_NR_AEN_COMMANDS) + (NVME_AQ_DEPTH - NVME_LOOP_NR_AEN_COMMANDS) struct nvme_loop_iod { struct nvme_request nvme_req; @@ -45,7 +43,6 @@ struct nvme_loop_iod { }; struct nvme_loop_ctrl { - spinlock_t lock; struct nvme_loop_queue *queues; u32 queue_count; @@ -59,7 +56,6 @@ struct nvme_loop_ctrl { struct nvmet_ctrl *target_ctrl; struct work_struct delete_work; - struct work_struct reset_work; }; static inline struct nvme_loop_ctrl *to_loop_ctrl(struct nvme_ctrl *ctrl) @@ -151,7 +147,7 @@ nvme_loop_timeout(struct request *rq, bool reserved) struct nvme_loop_iod *iod = blk_mq_rq_to_pdu(rq); /* queue error recovery */ - schedule_work(&iod->queue->ctrl->reset_work); + nvme_reset_ctrl(&iod->queue->ctrl->ctrl); /* fail with DNR on admin cmd timeout */ nvme_req(rq)->status = NVME_SC_ABORT_REQ | NVME_SC_DNR; @@ -159,17 +155,17 @@ nvme_loop_timeout(struct request *rq, bool reserved) return BLK_EH_HANDLED; } -static int nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx, +static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { struct nvme_ns *ns = hctx->queue->queuedata; struct nvme_loop_queue *queue = hctx->driver_data; struct request *req = bd->rq; struct nvme_loop_iod *iod = blk_mq_rq_to_pdu(req); - int ret; + blk_status_t ret; ret = nvme_setup_cmd(ns, req, &iod->cmd); - if (ret != BLK_MQ_RQ_QUEUE_OK) + if (ret) return ret; iod->cmd.common.flags |= NVME_CMD_SGL_METABUF; @@ -179,16 +175,15 @@ static int nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx, nvme_cleanup_cmd(req); blk_mq_start_request(req); nvme_loop_queue_response(&iod->req); - return BLK_MQ_RQ_QUEUE_OK; + return BLK_STS_OK; } if (blk_rq_bytes(req)) { iod->sg_table.sgl = iod->first_sgl; - ret = sg_alloc_table_chained(&iod->sg_table, + if (sg_alloc_table_chained(&iod->sg_table, blk_rq_nr_phys_segments(req), - iod->sg_table.sgl); - if (ret) - return BLK_MQ_RQ_QUEUE_BUSY; + iod->sg_table.sgl)) + return BLK_STS_RESOURCE; iod->req.sg = iod->sg_table.sgl; iod->req.sg_cnt = blk_rq_map_sg(req->q, req, iod->sg_table.sgl); @@ -197,7 +192,7 @@ static int nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx, blk_mq_start_request(req); schedule_work(&iod->work); - return BLK_MQ_RQ_QUEUE_OK; + return BLK_STS_OK; } static void nvme_loop_submit_async_event(struct nvme_ctrl *arg, int aer_idx) @@ -234,15 +229,10 @@ static int nvme_loop_init_request(struct blk_mq_tag_set *set, struct request *req, unsigned int hctx_idx, unsigned int numa_node) { - return nvme_loop_init_iod(set->driver_data, blk_mq_rq_to_pdu(req), - hctx_idx + 1); -} + struct nvme_loop_ctrl *ctrl = set->driver_data; -static int nvme_loop_init_admin_request(struct blk_mq_tag_set *set, - struct request *req, unsigned int hctx_idx, - unsigned int numa_node) -{ - return nvme_loop_init_iod(set->driver_data, blk_mq_rq_to_pdu(req), 0); + return nvme_loop_init_iod(ctrl, blk_mq_rq_to_pdu(req), + (set == &ctrl->tag_set) ? hctx_idx + 1 : 0); } static int nvme_loop_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, @@ -280,7 +270,7 @@ static const struct blk_mq_ops nvme_loop_mq_ops = { static const struct blk_mq_ops nvme_loop_admin_mq_ops = { .queue_rq = nvme_loop_queue_rq, .complete = nvme_loop_complete_rq, - .init_request = nvme_loop_init_admin_request, + .init_request = nvme_loop_init_request, .init_hctx = nvme_loop_init_admin_hctx, .timeout = nvme_loop_timeout, }; @@ -467,7 +457,7 @@ static int __nvme_loop_del_ctrl(struct nvme_loop_ctrl *ctrl) if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING)) return -EBUSY; - if (!schedule_work(&ctrl->delete_work)) + if (!queue_work(nvme_wq, &ctrl->delete_work)) return -EBUSY; return 0; @@ -501,8 +491,8 @@ static void nvme_loop_delete_ctrl(struct nvmet_ctrl *nctrl) static void nvme_loop_reset_ctrl_work(struct work_struct *work) { - struct nvme_loop_ctrl *ctrl = container_of(work, - struct nvme_loop_ctrl, reset_work); + struct nvme_loop_ctrl *ctrl = + container_of(work, struct nvme_loop_ctrl, ctrl.reset_work); bool changed; int ret; @@ -540,21 +530,6 @@ out_disable: nvme_put_ctrl(&ctrl->ctrl); } -static int nvme_loop_reset_ctrl(struct nvme_ctrl *nctrl) -{ - struct nvme_loop_ctrl *ctrl = to_loop_ctrl(nctrl); - - if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING)) - return -EBUSY; - - if (!schedule_work(&ctrl->reset_work)) - return -EBUSY; - - flush_work(&ctrl->reset_work); - - return 0; -} - static const struct nvme_ctrl_ops nvme_loop_ctrl_ops = { .name = "loop", .module = THIS_MODULE, @@ -562,11 +537,9 @@ static const struct nvme_ctrl_ops nvme_loop_ctrl_ops = { .reg_read32 = nvmf_reg_read32, .reg_read64 = nvmf_reg_read64, .reg_write32 = nvmf_reg_write32, - .reset_ctrl = nvme_loop_reset_ctrl, .free_ctrl = nvme_loop_free_ctrl, .submit_async_event = nvme_loop_submit_async_event, .delete_ctrl = nvme_loop_del_ctrl, - .get_subsysnqn = nvmf_get_subsysnqn, }; static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl) @@ -629,15 +602,13 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev, INIT_LIST_HEAD(&ctrl->list); INIT_WORK(&ctrl->delete_work, nvme_loop_del_ctrl_work); - INIT_WORK(&ctrl->reset_work, nvme_loop_reset_ctrl_work); + INIT_WORK(&ctrl->ctrl.reset_work, nvme_loop_reset_ctrl_work); ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_loop_ctrl_ops, 0 /* no quirks, we're perfect! */); if (ret) goto out_put_ctrl; - spin_lock_init(&ctrl->lock); - ret = -ENOMEM; ctrl->ctrl.sqsize = opts->queue_size - 1; @@ -766,7 +737,7 @@ static void __exit nvme_loop_cleanup_module(void) __nvme_loop_del_ctrl(ctrl); mutex_unlock(&nvme_loop_ctrl_mutex); - flush_scheduled_work(); + flush_workqueue(nvme_wq); } module_init(nvme_loop_init_module); diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index cfc5c7fb0ab7..747bbdb4f9c6 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -21,6 +21,7 @@ #include <linux/percpu-refcount.h> #include <linux/list.h> #include <linux/mutex.h> +#include <linux/uuid.h> #include <linux/nvme.h> #include <linux/configfs.h> #include <linux/rcupdate.h> @@ -46,6 +47,7 @@ struct nvmet_ns { u32 blksize_shift; loff_t size; u8 nguid[16]; + uuid_t uuid; bool enabled; struct nvmet_subsys *subsys; diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 9e45cde63376..56a4cba690b5 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -1027,7 +1027,7 @@ nvmet_rdma_parse_cm_connect_req(struct rdma_conn_param *conn, queue->recv_queue_size = le16_to_cpu(req->hsqsize) + 1; queue->send_queue_size = le16_to_cpu(req->hrqsize); - if (!queue->host_qid && queue->recv_queue_size > NVMF_AQ_DEPTH) + if (!queue->host_qid && queue->recv_queue_size > NVME_AQ_DEPTH) return NVME_RDMA_CM_INVALID_HSQSIZE; /* XXX: Should we enforce some kind of max for IO queues? */ @@ -1307,53 +1307,44 @@ static void nvmet_rdma_queue_connect_fail(struct rdma_cm_id *cm_id, /** * nvme_rdma_device_removal() - Handle RDMA device removal + * @cm_id: rdma_cm id, used for nvmet port * @queue: nvmet rdma queue (cm id qp_context) - * @addr: nvmet address (cm_id context) * * DEVICE_REMOVAL event notifies us that the RDMA device is about - * to unplug so we should take care of destroying our RDMA resources. - * This event will be generated for each allocated cm_id. + * to unplug. Note that this event can be generated on a normal + * queue cm_id and/or a device bound listener cm_id (where in this + * case queue will be null). * - * Note that this event can be generated on a normal queue cm_id - * and/or a device bound listener cm_id (where in this case - * queue will be null). - * - * we claim ownership on destroying the cm_id. For queues we move - * the queue state to NVMET_RDMA_IN_DEVICE_REMOVAL and for port + * We registered an ib_client to handle device removal for queues, + * so we only need to handle the listening port cm_ids. In this case * we nullify the priv to prevent double cm_id destruction and destroying * the cm_id implicitely by returning a non-zero rc to the callout. */ static int nvmet_rdma_device_removal(struct rdma_cm_id *cm_id, struct nvmet_rdma_queue *queue) { - unsigned long flags; - - if (!queue) { - struct nvmet_port *port = cm_id->context; + struct nvmet_port *port; + if (queue) { /* - * This is a listener cm_id. Make sure that - * future remove_port won't invoke a double - * cm_id destroy. use atomic xchg to make sure - * we don't compete with remove_port. - */ - if (xchg(&port->priv, NULL) != cm_id) - return 0; - } else { - /* - * This is a queue cm_id. Make sure that - * release queue will not destroy the cm_id - * and schedule all ctrl queues removal (only - * if the queue is not disconnecting already). + * This is a queue cm_id. we have registered + * an ib_client to handle queues removal + * so don't interfear and just return. */ - spin_lock_irqsave(&queue->state_lock, flags); - if (queue->state != NVMET_RDMA_Q_DISCONNECTING) - queue->state = NVMET_RDMA_IN_DEVICE_REMOVAL; - spin_unlock_irqrestore(&queue->state_lock, flags); - nvmet_rdma_queue_disconnect(queue); - flush_scheduled_work(); + return 0; } + port = cm_id->context; + + /* + * This is a listener cm_id. Make sure that + * future remove_port won't invoke a double + * cm_id destroy. use atomic xchg to make sure + * we don't compete with remove_port. + */ + if (xchg(&port->priv, NULL) != cm_id) + return 0; + /* * We need to return 1 so that the core will destroy * it's own ID. What a great API design.. @@ -1519,9 +1510,51 @@ static struct nvmet_fabrics_ops nvmet_rdma_ops = { .delete_ctrl = nvmet_rdma_delete_ctrl, }; +static void nvmet_rdma_add_one(struct ib_device *ib_device) +{ +} + +static void nvmet_rdma_remove_one(struct ib_device *ib_device, void *client_data) +{ + struct nvmet_rdma_queue *queue; + + /* Device is being removed, delete all queues using this device */ + mutex_lock(&nvmet_rdma_queue_mutex); + list_for_each_entry(queue, &nvmet_rdma_queue_list, queue_list) { + if (queue->dev->device != ib_device) + continue; + + pr_info("Removing queue %d\n", queue->idx); + __nvmet_rdma_queue_disconnect(queue); + } + mutex_unlock(&nvmet_rdma_queue_mutex); + + flush_scheduled_work(); +} + +static struct ib_client nvmet_rdma_ib_client = { + .name = "nvmet_rdma", + .add = nvmet_rdma_add_one, + .remove = nvmet_rdma_remove_one +}; + static int __init nvmet_rdma_init(void) { - return nvmet_register_transport(&nvmet_rdma_ops); + int ret; + + ret = ib_register_client(&nvmet_rdma_ib_client); + if (ret) + return ret; + + ret = nvmet_register_transport(&nvmet_rdma_ops); + if (ret) + goto err_ib_client; + + return 0; + +err_ib_client: + ib_unregister_client(&nvmet_rdma_ib_client); + return ret; } static void __exit nvmet_rdma_exit(void) @@ -1544,6 +1577,7 @@ static void __exit nvmet_rdma_exit(void) mutex_unlock(&nvmet_rdma_queue_mutex); flush_scheduled_work(); + ib_unregister_client(&nvmet_rdma_ib_client); ida_destroy(&nvmet_rdma_queue_ida); } diff --git a/drivers/parisc/ccio-dma.c b/drivers/parisc/ccio-dma.c index e32ca2ef9e54..56c93f096de9 100644 --- a/drivers/parisc/ccio-dma.c +++ b/drivers/parisc/ccio-dma.c @@ -741,6 +741,8 @@ ccio_map_single(struct device *dev, void *addr, size_t size, BUG_ON(!dev); ioc = GET_IOC(dev); + if (!ioc) + return DMA_ERROR_CODE; BUG_ON(size <= 0); @@ -814,6 +816,10 @@ ccio_unmap_page(struct device *dev, dma_addr_t iova, size_t size, BUG_ON(!dev); ioc = GET_IOC(dev); + if (!ioc) { + WARN_ON(!ioc); + return; + } DBG_RUN("%s() iovp 0x%lx/%x\n", __func__, (long)iova, size); @@ -918,6 +924,8 @@ ccio_map_sg(struct device *dev, struct scatterlist *sglist, int nents, BUG_ON(!dev); ioc = GET_IOC(dev); + if (!ioc) + return 0; DBG_RUN_SG("%s() START %d entries\n", __func__, nents); @@ -990,6 +998,10 @@ ccio_unmap_sg(struct device *dev, struct scatterlist *sglist, int nents, BUG_ON(!dev); ioc = GET_IOC(dev); + if (!ioc) { + WARN_ON(!ioc); + return; + } DBG_RUN_SG("%s() START %d entries, %p,%x\n", __func__, nents, sg_virt(sglist), sglist->length); diff --git a/drivers/parisc/dino.c b/drivers/parisc/dino.c index 1133b5cc88ca..5c63b920b471 100644 --- a/drivers/parisc/dino.c +++ b/drivers/parisc/dino.c @@ -154,7 +154,10 @@ struct dino_device }; /* Looks nice and keeps the compiler happy */ -#define DINO_DEV(d) ((struct dino_device *) d) +#define DINO_DEV(d) ({ \ + void *__pdata = d; \ + BUG_ON(!__pdata); \ + (struct dino_device *)__pdata; }) /* diff --git a/drivers/parisc/lba_pci.c b/drivers/parisc/lba_pci.c index 2ec2aef4d211..bc286cbbbc9b 100644 --- a/drivers/parisc/lba_pci.c +++ b/drivers/parisc/lba_pci.c @@ -111,8 +111,10 @@ static u32 lba_t32; /* Looks nice and keeps the compiler happy */ -#define LBA_DEV(d) ((struct lba_device *) (d)) - +#define LBA_DEV(d) ({ \ + void *__pdata = d; \ + BUG_ON(!__pdata); \ + (struct lba_device *)__pdata; }) /* ** Only allow 8 subsidiary busses per LBA diff --git a/drivers/parisc/sba_iommu.c b/drivers/parisc/sba_iommu.c index 33385e574433..87ad5fd6a7a2 100644 --- a/drivers/parisc/sba_iommu.c +++ b/drivers/parisc/sba_iommu.c @@ -691,6 +691,8 @@ static int sba_dma_supported( struct device *dev, u64 mask) return 0; ioc = GET_IOC(dev); + if (!ioc) + return 0; /* * check if mask is >= than the current max IO Virt Address @@ -722,6 +724,8 @@ sba_map_single(struct device *dev, void *addr, size_t size, int pide; ioc = GET_IOC(dev); + if (!ioc) + return DMA_ERROR_CODE; /* save offset bits */ offset = ((dma_addr_t) (long) addr) & ~IOVP_MASK; @@ -813,6 +817,10 @@ sba_unmap_page(struct device *dev, dma_addr_t iova, size_t size, DBG_RUN("%s() iovp 0x%lx/%x\n", __func__, (long) iova, size); ioc = GET_IOC(dev); + if (!ioc) { + WARN_ON(!ioc); + return; + } offset = iova & ~IOVP_MASK; iova ^= offset; /* clear offset bits */ size += offset; @@ -952,6 +960,8 @@ sba_map_sg(struct device *dev, struct scatterlist *sglist, int nents, DBG_RUN_SG("%s() START %d entries\n", __func__, nents); ioc = GET_IOC(dev); + if (!ioc) + return 0; /* Fast path single entry scatterlists. */ if (nents == 1) { @@ -1037,6 +1047,10 @@ sba_unmap_sg(struct device *dev, struct scatterlist *sglist, int nents, __func__, nents, sg_virt(sglist), sglist->length); ioc = GET_IOC(dev); + if (!ioc) { + WARN_ON(!ioc); + return; + } #ifdef SBA_COLLECT_STATS ioc->usg_calls++; diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index 001860361434..47070cff508c 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -21,13 +21,12 @@ #include "pci.h" /* - * The UUID is defined in the PCI Firmware Specification available here: + * The GUID is defined in the PCI Firmware Specification available here: * https://www.pcisig.com/members/downloads/pcifw_r3_1_13Dec10.pdf */ -const u8 pci_acpi_dsm_uuid[] = { - 0xd0, 0x37, 0xc9, 0xe5, 0x53, 0x35, 0x7a, 0x4d, - 0x91, 0x17, 0xea, 0x4d, 0x19, 0xc3, 0x43, 0x4d -}; +const guid_t pci_acpi_dsm_guid = + GUID_INIT(0xe5c937d0, 0x3553, 0x4d7a, + 0x91, 0x17, 0xea, 0x4d, 0x19, 0xc3, 0x43, 0x4d); #if defined(CONFIG_PCI_QUIRKS) && defined(CONFIG_ARM64) static int acpi_get_rc_addr(struct acpi_device *adev, struct resource *res) @@ -680,7 +679,7 @@ void acpi_pci_add_bus(struct pci_bus *bus) if (!pci_is_root_bus(bus)) return; - obj = acpi_evaluate_dsm(ACPI_HANDLE(bus->bridge), pci_acpi_dsm_uuid, 3, + obj = acpi_evaluate_dsm(ACPI_HANDLE(bus->bridge), &pci_acpi_dsm_guid, 3, RESET_DELAY_DSM, NULL); if (!obj) return; @@ -745,7 +744,7 @@ static void pci_acpi_optimize_delay(struct pci_dev *pdev, if (bridge->ignore_reset_delay) pdev->d3cold_delay = 0; - obj = acpi_evaluate_dsm(handle, pci_acpi_dsm_uuid, 3, + obj = acpi_evaluate_dsm(handle, &pci_acpi_dsm_guid, 3, FUNCTION_DELAY_DSM, NULL); if (!obj) return; diff --git a/drivers/pci/pci-label.c b/drivers/pci/pci-label.c index 51357377efbc..2d8db3ead6e8 100644 --- a/drivers/pci/pci-label.c +++ b/drivers/pci/pci-label.c @@ -172,7 +172,7 @@ static int dsm_get_label(struct device *dev, char *buf, if (!handle) return -1; - obj = acpi_evaluate_dsm(handle, pci_acpi_dsm_uuid, 0x2, + obj = acpi_evaluate_dsm(handle, &pci_acpi_dsm_guid, 0x2, DEVICE_LABEL_DSM, NULL); if (!obj) return -1; @@ -212,7 +212,7 @@ static bool device_has_dsm(struct device *dev) if (!handle) return false; - return !!acpi_check_dsm(handle, pci_acpi_dsm_uuid, 0x2, + return !!acpi_check_dsm(handle, &pci_acpi_dsm_guid, 0x2, 1 << DEVICE_LABEL_DSM); } diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 1482d132fbb8..e432ec887479 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -495,64 +495,54 @@ static struct irq_chip amd_gpio_irqchip = { .flags = IRQCHIP_SKIP_SET_WAKE, }; -static void amd_gpio_irq_handler(struct irq_desc *desc) +#define PIN_IRQ_PENDING (BIT(INTERRUPT_STS_OFF) | BIT(WAKE_STS_OFF)) + +static irqreturn_t amd_gpio_irq_handler(int irq, void *dev_id) { - u32 i; - u32 off; - u32 reg; - u32 pin_reg; - u64 reg64; - int handled = 0; - unsigned int irq; + struct amd_gpio *gpio_dev = dev_id; + struct gpio_chip *gc = &gpio_dev->gc; + irqreturn_t ret = IRQ_NONE; + unsigned int i, irqnr; unsigned long flags; - struct irq_chip *chip = irq_desc_get_chip(desc); - struct gpio_chip *gc = irq_desc_get_handler_data(desc); - struct amd_gpio *gpio_dev = gpiochip_get_data(gc); + u32 *regs, regval; + u64 status, mask; - chained_irq_enter(chip, desc); - /*enable GPIO interrupt again*/ + /* Read the wake status */ raw_spin_lock_irqsave(&gpio_dev->lock, flags); - reg = readl(gpio_dev->base + WAKE_INT_STATUS_REG1); - reg64 = reg; - reg64 = reg64 << 32; - - reg = readl(gpio_dev->base + WAKE_INT_STATUS_REG0); - reg64 |= reg; + status = readl(gpio_dev->base + WAKE_INT_STATUS_REG1); + status <<= 32; + status |= readl(gpio_dev->base + WAKE_INT_STATUS_REG0); raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); - /* - * first 46 bits indicates interrupt status. - * one bit represents four interrupt sources. - */ - for (off = 0; off < 46 ; off++) { - if (reg64 & BIT(off)) { - for (i = 0; i < 4; i++) { - pin_reg = readl(gpio_dev->base + - (off * 4 + i) * 4); - if ((pin_reg & BIT(INTERRUPT_STS_OFF)) || - (pin_reg & BIT(WAKE_STS_OFF))) { - irq = irq_find_mapping(gc->irqdomain, - off * 4 + i); - generic_handle_irq(irq); - writel(pin_reg, - gpio_dev->base - + (off * 4 + i) * 4); - handled++; - } - } + /* Bit 0-45 contain the relevant status bits */ + status &= (1ULL << 46) - 1; + regs = gpio_dev->base; + for (mask = 1, irqnr = 0; status; mask <<= 1, regs += 4, irqnr += 4) { + if (!(status & mask)) + continue; + status &= ~mask; + + /* Each status bit covers four pins */ + for (i = 0; i < 4; i++) { + regval = readl(regs + i); + if (!(regval & PIN_IRQ_PENDING)) + continue; + irq = irq_find_mapping(gc->irqdomain, irqnr + i); + generic_handle_irq(irq); + /* Clear interrupt */ + writel(regval, regs + i); + ret = IRQ_HANDLED; } } - if (handled == 0) - handle_bad_irq(desc); - + /* Signal EOI to the GPIO unit */ raw_spin_lock_irqsave(&gpio_dev->lock, flags); - reg = readl(gpio_dev->base + WAKE_INT_MASTER_REG); - reg |= EOI_MASK; - writel(reg, gpio_dev->base + WAKE_INT_MASTER_REG); + regval = readl(gpio_dev->base + WAKE_INT_MASTER_REG); + regval |= EOI_MASK; + writel(regval, gpio_dev->base + WAKE_INT_MASTER_REG); raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); - chained_irq_exit(chip, desc); + return ret; } static int amd_get_groups_count(struct pinctrl_dev *pctldev) @@ -821,10 +811,11 @@ static int amd_gpio_probe(struct platform_device *pdev) goto out2; } - gpiochip_set_chained_irqchip(&gpio_dev->gc, - &amd_gpio_irqchip, - irq_base, - amd_gpio_irq_handler); + ret = devm_request_irq(&pdev->dev, irq_base, amd_gpio_irq_handler, 0, + KBUILD_MODNAME, gpio_dev); + if (ret) + goto out2; + platform_set_drvdata(pdev, gpio_dev); dev_dbg(&pdev->dev, "amd gpio driver loaded\n"); diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c index f141aa0430b1..9dd981ddbb17 100644 --- a/drivers/pinctrl/pinctrl-rockchip.c +++ b/drivers/pinctrl/pinctrl-rockchip.c @@ -143,9 +143,6 @@ struct rockchip_drv { * @gpio_chip: gpiolib chip * @grange: gpio range * @slock: spinlock for the gpio bank - * @irq_lock: bus lock for irq chip - * @new_irqs: newly configured irqs which must be muxed as GPIOs in - * irq_bus_sync_unlock() */ struct rockchip_pin_bank { void __iomem *reg_base; @@ -168,8 +165,6 @@ struct rockchip_pin_bank { struct pinctrl_gpio_range grange; raw_spinlock_t slock; u32 toggle_edge_mode; - struct mutex irq_lock; - u32 new_irqs; }; #define PIN_BANK(id, pins, label) \ @@ -2134,12 +2129,11 @@ static int rockchip_irq_set_type(struct irq_data *d, unsigned int type) int ret; /* make sure the pin is configured as gpio input */ - ret = rockchip_verify_mux(bank, d->hwirq, RK_FUNC_GPIO); + ret = rockchip_set_mux(bank, d->hwirq, RK_FUNC_GPIO); if (ret < 0) return ret; - bank->new_irqs |= mask; - + clk_enable(bank->clk); raw_spin_lock_irqsave(&bank->slock, flags); data = readl_relaxed(bank->reg_base + GPIO_SWPORT_DDR); @@ -2197,6 +2191,7 @@ static int rockchip_irq_set_type(struct irq_data *d, unsigned int type) default: irq_gc_unlock(gc); raw_spin_unlock_irqrestore(&bank->slock, flags); + clk_disable(bank->clk); return -EINVAL; } @@ -2205,6 +2200,7 @@ static int rockchip_irq_set_type(struct irq_data *d, unsigned int type) irq_gc_unlock(gc); raw_spin_unlock_irqrestore(&bank->slock, flags); + clk_disable(bank->clk); return 0; } @@ -2248,34 +2244,6 @@ static void rockchip_irq_disable(struct irq_data *d) clk_disable(bank->clk); } -static void rockchip_irq_bus_lock(struct irq_data *d) -{ - struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); - struct rockchip_pin_bank *bank = gc->private; - - clk_enable(bank->clk); - mutex_lock(&bank->irq_lock); -} - -static void rockchip_irq_bus_sync_unlock(struct irq_data *d) -{ - struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); - struct rockchip_pin_bank *bank = gc->private; - - while (bank->new_irqs) { - unsigned int irq = __ffs(bank->new_irqs); - int ret; - - ret = rockchip_set_mux(bank, irq, RK_FUNC_GPIO); - WARN_ON(ret < 0); - - bank->new_irqs &= ~BIT(irq); - } - - mutex_unlock(&bank->irq_lock); - clk_disable(bank->clk); -} - static int rockchip_interrupts_register(struct platform_device *pdev, struct rockchip_pinctrl *info) { @@ -2342,9 +2310,6 @@ static int rockchip_interrupts_register(struct platform_device *pdev, gc->chip_types[0].chip.irq_suspend = rockchip_irq_suspend; gc->chip_types[0].chip.irq_resume = rockchip_irq_resume; gc->chip_types[0].chip.irq_set_type = rockchip_irq_set_type; - gc->chip_types[0].chip.irq_bus_lock = rockchip_irq_bus_lock; - gc->chip_types[0].chip.irq_bus_sync_unlock = - rockchip_irq_bus_sync_unlock; gc->wake_enabled = IRQ_MSK(bank->nr_pins); irq_set_chained_handler_and_data(bank->irq, @@ -2518,7 +2483,6 @@ static struct rockchip_pin_ctrl *rockchip_pinctrl_get_soc_data( int bank_pins = 0; raw_spin_lock_init(&bank->slock); - mutex_init(&bank->irq_lock); bank->drvdata = d; bank->pin_base = ctrl->nr_pins; ctrl->nr_pins += bank->nr_pins; diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c index d3c5f5dfbbd7..222b6685b09f 100644 --- a/drivers/pinctrl/stm32/pinctrl-stm32.c +++ b/drivers/pinctrl/stm32/pinctrl-stm32.c @@ -798,7 +798,7 @@ static int stm32_pconf_parse_conf(struct pinctrl_dev *pctldev, break; case PIN_CONFIG_OUTPUT: __stm32_gpio_set(bank, offset, arg); - ret = stm32_pmx_gpio_set_direction(pctldev, NULL, pin, false); + ret = stm32_pmx_gpio_set_direction(pctldev, range, pin, false); break; default: ret = -EINVAL; diff --git a/drivers/rtc/rtc-imxdi.c b/drivers/rtc/rtc-imxdi.c index 6b54f6c24c5f..80931114c899 100644 --- a/drivers/rtc/rtc-imxdi.c +++ b/drivers/rtc/rtc-imxdi.c @@ -709,7 +709,7 @@ static irqreturn_t dryice_irq(int irq, void *dev_id) /*If the write wait queue is empty then there is no pending operations. It means the interrupt is for DryIce -Security. IRQ must be returned as none.*/ - if (list_empty_careful(&imxdi->write_wait.task_list)) + if (list_empty_careful(&imxdi->write_wait.head)) return rc; /* DSR_WCF clears itself on DSR read */ diff --git a/drivers/s390/block/Kconfig b/drivers/s390/block/Kconfig index 0acb8c2f9475..31f014b57bfc 100644 --- a/drivers/s390/block/Kconfig +++ b/drivers/s390/block/Kconfig @@ -82,10 +82,3 @@ config SCM_BLOCK To compile this driver as a module, choose M here: the module will be called scm_block. - -config SCM_BLOCK_CLUSTER_WRITE - def_bool y - prompt "SCM force cluster writes" - depends on SCM_BLOCK - help - Force writes to Storage Class Memory (SCM) to be in done in clusters. diff --git a/drivers/s390/block/Makefile b/drivers/s390/block/Makefile index c2f4e673e031..b64e2b32c753 100644 --- a/drivers/s390/block/Makefile +++ b/drivers/s390/block/Makefile @@ -19,7 +19,4 @@ obj-$(CONFIG_BLK_DEV_XPRAM) += xpram.o obj-$(CONFIG_DCSSBLK) += dcssblk.o scm_block-objs := scm_drv.o scm_blk.o -ifdef CONFIG_SCM_BLOCK_CLUSTER_WRITE -scm_block-objs += scm_blk_cluster.o -endif obj-$(CONFIG_SCM_BLOCK) += scm_block.o diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 6fb3fd5efc11..0f1fe4ff7f51 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -1965,8 +1965,12 @@ static int __dasd_device_is_unusable(struct dasd_device *device, { int mask = ~(DASD_STOPPED_DC_WAIT | DASD_UNRESUMED_PM); - if (test_bit(DASD_FLAG_OFFLINE, &device->flags)) { - /* dasd is being set offline. */ + if (test_bit(DASD_FLAG_OFFLINE, &device->flags) && + !test_bit(DASD_FLAG_SAFE_OFFLINE_RUNNING, &device->flags)) { + /* + * dasd is being set offline + * but it is no safe offline where we have to allow I/O + */ return 1; } if (device->stopped) { @@ -2672,7 +2676,7 @@ static void __dasd_process_request_queue(struct dasd_block *block) */ if (basedev->state < DASD_STATE_READY) { while ((req = blk_fetch_request(block->request_queue))) - __blk_end_request_all(req, -EIO); + __blk_end_request_all(req, BLK_STS_IOERR); return; } @@ -2692,7 +2696,7 @@ static void __dasd_process_request_queue(struct dasd_block *block) "Rejecting write request %p", req); blk_start_request(req); - __blk_end_request_all(req, -EIO); + __blk_end_request_all(req, BLK_STS_IOERR); continue; } if (test_bit(DASD_FLAG_ABORTALL, &basedev->flags) && @@ -2702,7 +2706,7 @@ static void __dasd_process_request_queue(struct dasd_block *block) "Rejecting failfast request %p", req); blk_start_request(req); - __blk_end_request_all(req, -ETIMEDOUT); + __blk_end_request_all(req, BLK_STS_TIMEOUT); continue; } cqr = basedev->discipline->build_cp(basedev, block, req); @@ -2734,7 +2738,7 @@ static void __dasd_process_request_queue(struct dasd_block *block) "on request %p", PTR_ERR(cqr), req); blk_start_request(req); - __blk_end_request_all(req, -EIO); + __blk_end_request_all(req, BLK_STS_IOERR); continue; } /* @@ -2755,21 +2759,29 @@ static void __dasd_cleanup_cqr(struct dasd_ccw_req *cqr) { struct request *req; int status; - int error = 0; + blk_status_t error = BLK_STS_OK; req = (struct request *) cqr->callback_data; dasd_profile_end(cqr->block, cqr, req); + status = cqr->block->base->discipline->free_cp(cqr, req); if (status < 0) - error = status; + error = errno_to_blk_status(status); else if (status == 0) { - if (cqr->intrc == -EPERM) - error = -EBADE; - else if (cqr->intrc == -ENOLINK || - cqr->intrc == -ETIMEDOUT) - error = cqr->intrc; - else - error = -EIO; + switch (cqr->intrc) { + case -EPERM: + error = BLK_STS_NEXUS; + break; + case -ENOLINK: + error = BLK_STS_TRANSPORT; + break; + case -ETIMEDOUT: + error = BLK_STS_TIMEOUT; + break; + default: + error = BLK_STS_IOERR; + break; + } } __blk_end_request_all(req, error); } @@ -3190,7 +3202,7 @@ static void dasd_flush_request_queue(struct dasd_block *block) spin_lock_irq(&block->request_queue_lock); while ((req = blk_fetch_request(block->request_queue))) - __blk_end_request_all(req, -EIO); + __blk_end_request_all(req, BLK_STS_IOERR); spin_unlock_irq(&block->request_queue_lock); } @@ -3562,57 +3574,69 @@ int dasd_generic_set_offline(struct ccw_device *cdev) else pr_warn("%s: The DASD cannot be set offline while it is in use\n", dev_name(&cdev->dev)); - clear_bit(DASD_FLAG_OFFLINE, &device->flags); - goto out_busy; + rc = -EBUSY; + goto out_err; } } - if (test_bit(DASD_FLAG_SAFE_OFFLINE_RUNNING, &device->flags)) { - /* - * safe offline already running - * could only be called by normal offline so safe_offline flag - * needs to be removed to run normal offline and kill all I/O - */ - if (test_and_set_bit(DASD_FLAG_OFFLINE, &device->flags)) - /* Already doing normal offline processing */ - goto out_busy; - else - clear_bit(DASD_FLAG_SAFE_OFFLINE, &device->flags); - } else { - if (test_bit(DASD_FLAG_OFFLINE, &device->flags)) - /* Already doing offline processing */ - goto out_busy; + /* + * Test if the offline processing is already running and exit if so. + * If a safe offline is being processed this could only be a normal + * offline that should be able to overtake the safe offline and + * cancel any I/O we do not want to wait for any longer + */ + if (test_bit(DASD_FLAG_OFFLINE, &device->flags)) { + if (test_bit(DASD_FLAG_SAFE_OFFLINE_RUNNING, &device->flags)) { + clear_bit(DASD_FLAG_SAFE_OFFLINE_RUNNING, + &device->flags); + } else { + rc = -EBUSY; + goto out_err; + } } - set_bit(DASD_FLAG_OFFLINE, &device->flags); - spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags); /* - * if safe_offline called set safe_offline_running flag and + * if safe_offline is called set safe_offline_running flag and * clear safe_offline so that a call to normal offline * can overrun safe_offline processing */ if (test_and_clear_bit(DASD_FLAG_SAFE_OFFLINE, &device->flags) && !test_and_set_bit(DASD_FLAG_SAFE_OFFLINE_RUNNING, &device->flags)) { + /* need to unlock here to wait for outstanding I/O */ + spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags); /* * If we want to set the device safe offline all IO operations * should be finished before continuing the offline process * so sync bdev first and then wait for our queues to become * empty */ - /* sync blockdev and partitions */ if (device->block) { rc = fsync_bdev(device->block->bdev); if (rc != 0) goto interrupted; } - /* schedule device tasklet and wait for completion */ dasd_schedule_device_bh(device); rc = wait_event_interruptible(shutdown_waitq, _wait_for_empty_queues(device)); if (rc != 0) goto interrupted; + + /* + * check if a normal offline process overtook the offline + * processing in this case simply do nothing beside returning + * that we got interrupted + * otherwise mark safe offline as not running any longer and + * continue with normal offline + */ + spin_lock_irqsave(get_ccwdev_lock(cdev), flags); + if (!test_bit(DASD_FLAG_SAFE_OFFLINE_RUNNING, &device->flags)) { + rc = -ERESTARTSYS; + goto out_err; + } + clear_bit(DASD_FLAG_SAFE_OFFLINE_RUNNING, &device->flags); } + spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags); dasd_set_target_state(device, DASD_STATE_NEW); /* dasd_delete_device destroys the device reference. */ @@ -3624,22 +3648,18 @@ int dasd_generic_set_offline(struct ccw_device *cdev) */ if (block) dasd_free_block(block); + return 0; interrupted: /* interrupted by signal */ - clear_bit(DASD_FLAG_SAFE_OFFLINE, &device->flags); + spin_lock_irqsave(get_ccwdev_lock(cdev), flags); clear_bit(DASD_FLAG_SAFE_OFFLINE_RUNNING, &device->flags); clear_bit(DASD_FLAG_OFFLINE, &device->flags); - dasd_put_device(device); - - return rc; - -out_busy: +out_err: dasd_put_device(device); spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags); - - return -EBUSY; + return rc; } EXPORT_SYMBOL_GPL(dasd_generic_set_offline); diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c index 1164b51d09f3..7c7351276d2e 100644 --- a/drivers/s390/block/dasd_devmap.c +++ b/drivers/s390/block/dasd_devmap.c @@ -315,45 +315,58 @@ static int __init dasd_parse_range(const char *range) char *features_str = NULL; char *from_str = NULL; char *to_str = NULL; - size_t len = strlen(range) + 1; - char tmp[len]; + int rc = 0; + char *tmp; - strlcpy(tmp, range, len); + tmp = kstrdup(range, GFP_KERNEL); + if (!tmp) + return -ENOMEM; - if (dasd_evaluate_range_param(tmp, &from_str, &to_str, &features_str)) - goto out_err; + if (dasd_evaluate_range_param(tmp, &from_str, &to_str, &features_str)) { + rc = -EINVAL; + goto out; + } - if (dasd_busid(from_str, &from_id0, &from_id1, &from)) - goto out_err; + if (dasd_busid(from_str, &from_id0, &from_id1, &from)) { + rc = -EINVAL; + goto out; + } to = from; to_id0 = from_id0; to_id1 = from_id1; if (to_str) { - if (dasd_busid(to_str, &to_id0, &to_id1, &to)) - goto out_err; + if (dasd_busid(to_str, &to_id0, &to_id1, &to)) { + rc = -EINVAL; + goto out; + } if (from_id0 != to_id0 || from_id1 != to_id1 || from > to) { pr_err("%s is not a valid device range\n", range); - goto out_err; + rc = -EINVAL; + goto out; } } features = dasd_feature_list(features_str); - if (features < 0) - goto out_err; + if (features < 0) { + rc = -EINVAL; + goto out; + } /* each device in dasd= parameter should be set initially online */ features |= DASD_FEATURE_INITIAL_ONLINE; while (from <= to) { sprintf(bus_id, "%01x.%01x.%04x", from_id0, from_id1, from++); devmap = dasd_add_busid(bus_id, features); - if (IS_ERR(devmap)) - return PTR_ERR(devmap); + if (IS_ERR(devmap)) { + rc = PTR_ERR(devmap); + goto out; + } } - return 0; +out: + kfree(tmp); -out_err: - return -EINVAL; + return rc; } /* @@ -735,13 +748,22 @@ static ssize_t dasd_ro_show(struct device *dev, struct device_attribute *attr, char *buf) { struct dasd_devmap *devmap; - int ro_flag; + struct dasd_device *device; + int ro_flag = 0; devmap = dasd_find_busid(dev_name(dev)); - if (!IS_ERR(devmap)) - ro_flag = (devmap->features & DASD_FEATURE_READONLY) != 0; - else - ro_flag = (DASD_FEATURE_DEFAULT & DASD_FEATURE_READONLY) != 0; + if (IS_ERR(devmap)) + goto out; + + ro_flag = !!(devmap->features & DASD_FEATURE_READONLY); + + spin_lock(&dasd_devmap_lock); + device = devmap->device; + if (device) + ro_flag |= test_bit(DASD_FLAG_DEVICE_RO, &device->flags); + spin_unlock(&dasd_devmap_lock); + +out: return snprintf(buf, PAGE_SIZE, ro_flag ? "1\n" : "0\n"); } @@ -764,7 +786,7 @@ dasd_ro_store(struct device *dev, struct device_attribute *attr, device = dasd_device_from_cdev(cdev); if (IS_ERR(device)) - return PTR_ERR(device); + return count; spin_lock_irqsave(get_ccwdev_lock(cdev), flags); val = val || test_bit(DASD_FLAG_DEVICE_RO, &device->flags); @@ -928,11 +950,14 @@ dasd_safe_offline_store(struct device *dev, struct device_attribute *attr, { struct ccw_device *cdev = to_ccwdev(dev); struct dasd_device *device; + unsigned long flags; int rc; - device = dasd_device_from_cdev(cdev); + spin_lock_irqsave(get_ccwdev_lock(cdev), flags); + device = dasd_device_from_cdev_locked(cdev); if (IS_ERR(device)) { rc = PTR_ERR(device); + spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags); goto out; } @@ -940,12 +965,14 @@ dasd_safe_offline_store(struct device *dev, struct device_attribute *attr, test_bit(DASD_FLAG_SAFE_OFFLINE_RUNNING, &device->flags)) { /* Already doing offline processing */ dasd_put_device(device); + spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags); rc = -EBUSY; goto out; } set_bit(DASD_FLAG_SAFE_OFFLINE, &device->flags); dasd_put_device(device); + spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags); rc = ccw_device_set_offline(cdev); diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index 36e5280af3e4..06eb1de52d1c 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -845,7 +845,7 @@ dcssblk_make_request(struct request_queue *q, struct bio *bio) unsigned long source_addr; unsigned long bytes_done; - blk_queue_split(q, &bio, q->bio_split); + blk_queue_split(q, &bio); bytes_done = 0; dev_info = bio->bi_bdev->bd_disk->private_data; diff --git a/drivers/s390/block/scm_blk.c b/drivers/s390/block/scm_blk.c index 152de6817875..42018a20f2b7 100644 --- a/drivers/s390/block/scm_blk.c +++ b/drivers/s390/block/scm_blk.c @@ -13,6 +13,7 @@ #include <linux/mempool.h> #include <linux/module.h> #include <linux/blkdev.h> +#include <linux/blk-mq.h> #include <linux/genhd.h> #include <linux/slab.h> #include <linux/list.h> @@ -42,7 +43,6 @@ static void __scm_free_rq(struct scm_request *scmrq) struct aob_rq_header *aobrq = to_aobrq(scmrq); free_page((unsigned long) scmrq->aob); - __scm_free_rq_cluster(scmrq); kfree(scmrq->request); kfree(aobrq); } @@ -82,9 +82,6 @@ static int __scm_alloc_rq(void) if (!scmrq->request) goto free; - if (__scm_alloc_rq_cluster(scmrq)) - goto free; - INIT_LIST_HEAD(&scmrq->list); spin_lock_irq(&list_lock); list_add(&scmrq->list, &inactive_requests); @@ -114,13 +111,13 @@ static struct scm_request *scm_request_fetch(void) { struct scm_request *scmrq = NULL; - spin_lock(&list_lock); + spin_lock_irq(&list_lock); if (list_empty(&inactive_requests)) goto out; scmrq = list_first_entry(&inactive_requests, struct scm_request, list); list_del(&scmrq->list); out: - spin_unlock(&list_lock); + spin_unlock_irq(&list_lock); return scmrq; } @@ -231,140 +228,133 @@ static inline void scm_request_init(struct scm_blk_dev *bdev, aob->request.data = (u64) aobrq; scmrq->bdev = bdev; scmrq->retries = 4; - scmrq->error = 0; + scmrq->error = BLK_STS_OK; /* We don't use all msbs - place aidaws at the end of the aob page. */ scmrq->next_aidaw = (void *) &aob->msb[nr_requests_per_io]; - scm_request_cluster_init(scmrq); } -static void scm_ensure_queue_restart(struct scm_blk_dev *bdev) -{ - if (atomic_read(&bdev->queued_reqs)) { - /* Queue restart is triggered by the next interrupt. */ - return; - } - blk_delay_queue(bdev->rq, SCM_QUEUE_DELAY); -} - -void scm_request_requeue(struct scm_request *scmrq) +static void scm_request_requeue(struct scm_request *scmrq) { struct scm_blk_dev *bdev = scmrq->bdev; int i; - scm_release_cluster(scmrq); for (i = 0; i < nr_requests_per_io && scmrq->request[i]; i++) - blk_requeue_request(bdev->rq, scmrq->request[i]); + blk_mq_requeue_request(scmrq->request[i], false); atomic_dec(&bdev->queued_reqs); scm_request_done(scmrq); - scm_ensure_queue_restart(bdev); + blk_mq_kick_requeue_list(bdev->rq); } -void scm_request_finish(struct scm_request *scmrq) +static void scm_request_finish(struct scm_request *scmrq) { struct scm_blk_dev *bdev = scmrq->bdev; int i; - scm_release_cluster(scmrq); - for (i = 0; i < nr_requests_per_io && scmrq->request[i]; i++) - blk_end_request_all(scmrq->request[i], scmrq->error); + for (i = 0; i < nr_requests_per_io && scmrq->request[i]; i++) { + if (scmrq->error) + blk_mq_end_request(scmrq->request[i], scmrq->error); + else + blk_mq_complete_request(scmrq->request[i]); + } atomic_dec(&bdev->queued_reqs); scm_request_done(scmrq); } -static int scm_request_start(struct scm_request *scmrq) +static void scm_request_start(struct scm_request *scmrq) { struct scm_blk_dev *bdev = scmrq->bdev; - int ret; atomic_inc(&bdev->queued_reqs); - if (!scmrq->aob->request.msb_count) { - scm_request_requeue(scmrq); - return -EINVAL; - } - - ret = eadm_start_aob(scmrq->aob); - if (ret) { + if (eadm_start_aob(scmrq->aob)) { SCM_LOG(5, "no subchannel"); scm_request_requeue(scmrq); } - return ret; } -static void scm_blk_request(struct request_queue *rq) +struct scm_queue { + struct scm_request *scmrq; + spinlock_t lock; +}; + +static int scm_blk_request(struct blk_mq_hw_ctx *hctx, + const struct blk_mq_queue_data *qd) { - struct scm_device *scmdev = rq->queuedata; + struct scm_device *scmdev = hctx->queue->queuedata; struct scm_blk_dev *bdev = dev_get_drvdata(&scmdev->dev); - struct scm_request *scmrq = NULL; - struct request *req; + struct scm_queue *sq = hctx->driver_data; + struct request *req = qd->rq; + struct scm_request *scmrq; - while ((req = blk_peek_request(rq))) { - if (!scm_permit_request(bdev, req)) - goto out; + spin_lock(&sq->lock); + if (!scm_permit_request(bdev, req)) { + spin_unlock(&sq->lock); + return BLK_MQ_RQ_QUEUE_BUSY; + } + scmrq = sq->scmrq; + if (!scmrq) { + scmrq = scm_request_fetch(); if (!scmrq) { - scmrq = scm_request_fetch(); - if (!scmrq) { - SCM_LOG(5, "no request"); - goto out; - } - scm_request_init(bdev, scmrq); + SCM_LOG(5, "no request"); + spin_unlock(&sq->lock); + return BLK_MQ_RQ_QUEUE_BUSY; } - scm_request_set(scmrq, req); + scm_request_init(bdev, scmrq); + sq->scmrq = scmrq; + } + scm_request_set(scmrq, req); - if (!scm_reserve_cluster(scmrq)) { - SCM_LOG(5, "cluster busy"); - scm_request_set(scmrq, NULL); - if (scmrq->aob->request.msb_count) - goto out; + if (scm_request_prepare(scmrq)) { + SCM_LOG(5, "aidaw alloc failed"); + scm_request_set(scmrq, NULL); - scm_request_done(scmrq); - return; - } + if (scmrq->aob->request.msb_count) + scm_request_start(scmrq); - if (scm_need_cluster_request(scmrq)) { - if (scmrq->aob->request.msb_count) { - /* Start cluster requests separately. */ - scm_request_set(scmrq, NULL); - if (scm_request_start(scmrq)) - return; - } else { - atomic_inc(&bdev->queued_reqs); - blk_start_request(req); - scm_initiate_cluster_request(scmrq); - } - scmrq = NULL; - continue; - } + sq->scmrq = NULL; + spin_unlock(&sq->lock); + return BLK_MQ_RQ_QUEUE_BUSY; + } + blk_mq_start_request(req); - if (scm_request_prepare(scmrq)) { - SCM_LOG(5, "aidaw alloc failed"); - scm_request_set(scmrq, NULL); - goto out; - } - blk_start_request(req); + if (qd->last || scmrq->aob->request.msb_count == nr_requests_per_io) { + scm_request_start(scmrq); + sq->scmrq = NULL; + } + spin_unlock(&sq->lock); + return BLK_MQ_RQ_QUEUE_OK; +} - if (scmrq->aob->request.msb_count < nr_requests_per_io) - continue; +static int scm_blk_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, + unsigned int idx) +{ + struct scm_queue *qd = kzalloc(sizeof(*qd), GFP_KERNEL); - if (scm_request_start(scmrq)) - return; + if (!qd) + return -ENOMEM; - scmrq = NULL; - } -out: - if (scmrq) - scm_request_start(scmrq); - else - scm_ensure_queue_restart(bdev); + spin_lock_init(&qd->lock); + hctx->driver_data = qd; + + return 0; +} + +static void scm_blk_exit_hctx(struct blk_mq_hw_ctx *hctx, unsigned int idx) +{ + struct scm_queue *qd = hctx->driver_data; + + WARN_ON(qd->scmrq); + kfree(hctx->driver_data); + hctx->driver_data = NULL; } static void __scmrq_log_error(struct scm_request *scmrq) { struct aob *aob = scmrq->aob; - if (scmrq->error == -ETIMEDOUT) + if (scmrq->error == BLK_STS_TIMEOUT) SCM_LOG(1, "Request timeout"); else { SCM_LOG(1, "Request error"); @@ -377,27 +367,12 @@ static void __scmrq_log_error(struct scm_request *scmrq) scmrq->error); } -void scm_blk_irq(struct scm_device *scmdev, void *data, int error) -{ - struct scm_request *scmrq = data; - struct scm_blk_dev *bdev = scmrq->bdev; - - scmrq->error = error; - if (error) - __scmrq_log_error(scmrq); - - spin_lock(&bdev->lock); - list_add_tail(&scmrq->list, &bdev->finished_requests); - spin_unlock(&bdev->lock); - tasklet_hi_schedule(&bdev->tasklet); -} - static void scm_blk_handle_error(struct scm_request *scmrq) { struct scm_blk_dev *bdev = scmrq->bdev; unsigned long flags; - if (scmrq->error != -EIO) + if (scmrq->error != BLK_STS_IOERR) goto restart; /* For -EIO the response block is valid. */ @@ -419,54 +394,46 @@ restart: return; requeue: - spin_lock_irqsave(&bdev->rq_lock, flags); scm_request_requeue(scmrq); - spin_unlock_irqrestore(&bdev->rq_lock, flags); } -static void scm_blk_tasklet(struct scm_blk_dev *bdev) +void scm_blk_irq(struct scm_device *scmdev, void *data, blk_status_t error) { - struct scm_request *scmrq; - unsigned long flags; - - spin_lock_irqsave(&bdev->lock, flags); - while (!list_empty(&bdev->finished_requests)) { - scmrq = list_first_entry(&bdev->finished_requests, - struct scm_request, list); - list_del(&scmrq->list); - spin_unlock_irqrestore(&bdev->lock, flags); + struct scm_request *scmrq = data; - if (scmrq->error && scmrq->retries-- > 0) { + scmrq->error = error; + if (error) { + __scmrq_log_error(scmrq); + if (scmrq->retries-- > 0) { scm_blk_handle_error(scmrq); - - /* Request restarted or requeued, handle next. */ - spin_lock_irqsave(&bdev->lock, flags); - continue; + return; } + } - if (scm_test_cluster_request(scmrq)) { - scm_cluster_request_irq(scmrq); - spin_lock_irqsave(&bdev->lock, flags); - continue; - } + scm_request_finish(scmrq); +} - scm_request_finish(scmrq); - spin_lock_irqsave(&bdev->lock, flags); - } - spin_unlock_irqrestore(&bdev->lock, flags); - /* Look out for more requests. */ - blk_run_queue(bdev->rq); +static void scm_blk_request_done(struct request *req) +{ + blk_mq_end_request(req, 0); } static const struct block_device_operations scm_blk_devops = { .owner = THIS_MODULE, }; +static const struct blk_mq_ops scm_mq_ops = { + .queue_rq = scm_blk_request, + .complete = scm_blk_request_done, + .init_hctx = scm_blk_init_hctx, + .exit_hctx = scm_blk_exit_hctx, +}; + int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev) { - struct request_queue *rq; - int len, ret = -ENOMEM; unsigned int devindex, nr_max_blk; + struct request_queue *rq; + int len, ret; devindex = atomic_inc_return(&nr_devices) - 1; /* scma..scmz + scmaa..scmzz */ @@ -477,18 +444,23 @@ int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev) bdev->scmdev = scmdev; bdev->state = SCM_OPER; - spin_lock_init(&bdev->rq_lock); spin_lock_init(&bdev->lock); - INIT_LIST_HEAD(&bdev->finished_requests); atomic_set(&bdev->queued_reqs, 0); - tasklet_init(&bdev->tasklet, - (void (*)(unsigned long)) scm_blk_tasklet, - (unsigned long) bdev); - rq = blk_init_queue(scm_blk_request, &bdev->rq_lock); - if (!rq) + bdev->tag_set.ops = &scm_mq_ops; + bdev->tag_set.nr_hw_queues = nr_requests; + bdev->tag_set.queue_depth = nr_requests_per_io * nr_requests; + bdev->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; + + ret = blk_mq_alloc_tag_set(&bdev->tag_set); + if (ret) goto out; + rq = blk_mq_init_queue(&bdev->tag_set); + if (IS_ERR(rq)) { + ret = PTR_ERR(rq); + goto out_tag; + } bdev->rq = rq; nr_max_blk = min(scmdev->nr_max_block, (unsigned int) (PAGE_SIZE / sizeof(struct aidaw))); @@ -498,12 +470,12 @@ int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev) blk_queue_max_segments(rq, nr_max_blk); queue_flag_set_unlocked(QUEUE_FLAG_NONROT, rq); queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, rq); - scm_blk_dev_cluster_setup(bdev); bdev->gendisk = alloc_disk(SCM_NR_PARTS); - if (!bdev->gendisk) + if (!bdev->gendisk) { + ret = -ENOMEM; goto out_queue; - + } rq->queuedata = scmdev; bdev->gendisk->private_data = scmdev; bdev->gendisk->fops = &scm_blk_devops; @@ -528,6 +500,8 @@ int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev) out_queue: blk_cleanup_queue(rq); +out_tag: + blk_mq_free_tag_set(&bdev->tag_set); out: atomic_dec(&nr_devices); return ret; @@ -535,9 +509,9 @@ out: void scm_blk_dev_cleanup(struct scm_blk_dev *bdev) { - tasklet_kill(&bdev->tasklet); del_gendisk(bdev->gendisk); blk_cleanup_queue(bdev->gendisk->queue); + blk_mq_free_tag_set(&bdev->tag_set); put_disk(bdev->gendisk); } @@ -558,7 +532,7 @@ static bool __init scm_blk_params_valid(void) if (!nr_requests_per_io || nr_requests_per_io > 64) return false; - return scm_cluster_size_valid(); + return true; } static int __init scm_blk_init(void) diff --git a/drivers/s390/block/scm_blk.h b/drivers/s390/block/scm_blk.h index 09218cdc5129..71288dd9dd7f 100644 --- a/drivers/s390/block/scm_blk.h +++ b/drivers/s390/block/scm_blk.h @@ -4,6 +4,7 @@ #include <linux/interrupt.h> #include <linux/spinlock.h> #include <linux/blkdev.h> +#include <linux/blk-mq.h> #include <linux/genhd.h> #include <linux/list.h> @@ -14,18 +15,14 @@ #define SCM_QUEUE_DELAY 5 struct scm_blk_dev { - struct tasklet_struct tasklet; struct request_queue *rq; struct gendisk *gendisk; + struct blk_mq_tag_set tag_set; struct scm_device *scmdev; - spinlock_t rq_lock; /* guard the request queue */ - spinlock_t lock; /* guard the rest of the blockdev */ + spinlock_t lock; atomic_t queued_reqs; enum {SCM_OPER, SCM_WR_PROHIBIT} state; struct list_head finished_requests; -#ifdef CONFIG_SCM_BLOCK_CLUSTER_WRITE - struct list_head cluster_list; -#endif }; struct scm_request { @@ -35,14 +32,7 @@ struct scm_request { struct aob *aob; struct list_head list; u8 retries; - int error; -#ifdef CONFIG_SCM_BLOCK_CLUSTER_WRITE - struct { - enum {CLUSTER_NONE, CLUSTER_READ, CLUSTER_WRITE} state; - struct list_head list; - void **buf; - } cluster; -#endif + blk_status_t error; }; #define to_aobrq(rq) container_of((void *) rq, struct aob_rq_header, data) @@ -50,57 +40,13 @@ struct scm_request { int scm_blk_dev_setup(struct scm_blk_dev *, struct scm_device *); void scm_blk_dev_cleanup(struct scm_blk_dev *); void scm_blk_set_available(struct scm_blk_dev *); -void scm_blk_irq(struct scm_device *, void *, int); - -void scm_request_finish(struct scm_request *); -void scm_request_requeue(struct scm_request *); +void scm_blk_irq(struct scm_device *, void *, blk_status_t); struct aidaw *scm_aidaw_fetch(struct scm_request *scmrq, unsigned int bytes); int scm_drv_init(void); void scm_drv_cleanup(void); -#ifdef CONFIG_SCM_BLOCK_CLUSTER_WRITE -void __scm_free_rq_cluster(struct scm_request *); -int __scm_alloc_rq_cluster(struct scm_request *); -void scm_request_cluster_init(struct scm_request *); -bool scm_reserve_cluster(struct scm_request *); -void scm_release_cluster(struct scm_request *); -void scm_blk_dev_cluster_setup(struct scm_blk_dev *); -bool scm_need_cluster_request(struct scm_request *); -void scm_initiate_cluster_request(struct scm_request *); -void scm_cluster_request_irq(struct scm_request *); -bool scm_test_cluster_request(struct scm_request *); -bool scm_cluster_size_valid(void); -#else /* CONFIG_SCM_BLOCK_CLUSTER_WRITE */ -static inline void __scm_free_rq_cluster(struct scm_request *scmrq) {} -static inline int __scm_alloc_rq_cluster(struct scm_request *scmrq) -{ - return 0; -} -static inline void scm_request_cluster_init(struct scm_request *scmrq) {} -static inline bool scm_reserve_cluster(struct scm_request *scmrq) -{ - return true; -} -static inline void scm_release_cluster(struct scm_request *scmrq) {} -static inline void scm_blk_dev_cluster_setup(struct scm_blk_dev *bdev) {} -static inline bool scm_need_cluster_request(struct scm_request *scmrq) -{ - return false; -} -static inline void scm_initiate_cluster_request(struct scm_request *scmrq) {} -static inline void scm_cluster_request_irq(struct scm_request *scmrq) {} -static inline bool scm_test_cluster_request(struct scm_request *scmrq) -{ - return false; -} -static inline bool scm_cluster_size_valid(void) -{ - return true; -} -#endif /* CONFIG_SCM_BLOCK_CLUSTER_WRITE */ - extern debug_info_t *scm_debug; #define SCM_LOG(imp, txt) do { \ diff --git a/drivers/s390/block/scm_blk_cluster.c b/drivers/s390/block/scm_blk_cluster.c deleted file mode 100644 index 7497ddde2dd6..000000000000 --- a/drivers/s390/block/scm_blk_cluster.c +++ /dev/null @@ -1,255 +0,0 @@ -/* - * Block driver for s390 storage class memory. - * - * Copyright IBM Corp. 2012 - * Author(s): Sebastian Ott <sebott@linux.vnet.ibm.com> - */ - -#include <linux/spinlock.h> -#include <linux/module.h> -#include <linux/blkdev.h> -#include <linux/genhd.h> -#include <linux/slab.h> -#include <linux/list.h> -#include <asm/eadm.h> -#include "scm_blk.h" - -static unsigned int write_cluster_size = 64; -module_param(write_cluster_size, uint, S_IRUGO); -MODULE_PARM_DESC(write_cluster_size, - "Number of pages used for contiguous writes."); - -#define CLUSTER_SIZE (write_cluster_size * PAGE_SIZE) - -void __scm_free_rq_cluster(struct scm_request *scmrq) -{ - int i; - - if (!scmrq->cluster.buf) - return; - - for (i = 0; i < 2 * write_cluster_size; i++) - free_page((unsigned long) scmrq->cluster.buf[i]); - - kfree(scmrq->cluster.buf); -} - -int __scm_alloc_rq_cluster(struct scm_request *scmrq) -{ - int i; - - scmrq->cluster.buf = kzalloc(sizeof(void *) * 2 * write_cluster_size, - GFP_KERNEL); - if (!scmrq->cluster.buf) - return -ENOMEM; - - for (i = 0; i < 2 * write_cluster_size; i++) { - scmrq->cluster.buf[i] = (void *) get_zeroed_page(GFP_DMA); - if (!scmrq->cluster.buf[i]) - return -ENOMEM; - } - INIT_LIST_HEAD(&scmrq->cluster.list); - return 0; -} - -void scm_request_cluster_init(struct scm_request *scmrq) -{ - scmrq->cluster.state = CLUSTER_NONE; -} - -static bool clusters_intersect(struct request *A, struct request *B) -{ - unsigned long firstA, lastA, firstB, lastB; - - firstA = ((u64) blk_rq_pos(A) << 9) / CLUSTER_SIZE; - lastA = (((u64) blk_rq_pos(A) << 9) + - blk_rq_bytes(A) - 1) / CLUSTER_SIZE; - - firstB = ((u64) blk_rq_pos(B) << 9) / CLUSTER_SIZE; - lastB = (((u64) blk_rq_pos(B) << 9) + - blk_rq_bytes(B) - 1) / CLUSTER_SIZE; - - return (firstB <= lastA && firstA <= lastB); -} - -bool scm_reserve_cluster(struct scm_request *scmrq) -{ - struct request *req = scmrq->request[scmrq->aob->request.msb_count]; - struct scm_blk_dev *bdev = scmrq->bdev; - struct scm_request *iter; - int pos, add = 1; - - if (write_cluster_size == 0) - return true; - - spin_lock(&bdev->lock); - list_for_each_entry(iter, &bdev->cluster_list, cluster.list) { - if (iter == scmrq) { - /* - * We don't have to use clusters_intersect here, since - * cluster requests are always started separately. - */ - add = 0; - continue; - } - for (pos = 0; pos < iter->aob->request.msb_count; pos++) { - if (clusters_intersect(req, iter->request[pos]) && - (rq_data_dir(req) == WRITE || - rq_data_dir(iter->request[pos]) == WRITE)) { - spin_unlock(&bdev->lock); - return false; - } - } - } - if (add) - list_add(&scmrq->cluster.list, &bdev->cluster_list); - spin_unlock(&bdev->lock); - - return true; -} - -void scm_release_cluster(struct scm_request *scmrq) -{ - struct scm_blk_dev *bdev = scmrq->bdev; - unsigned long flags; - - if (write_cluster_size == 0) - return; - - spin_lock_irqsave(&bdev->lock, flags); - list_del(&scmrq->cluster.list); - spin_unlock_irqrestore(&bdev->lock, flags); -} - -void scm_blk_dev_cluster_setup(struct scm_blk_dev *bdev) -{ - INIT_LIST_HEAD(&bdev->cluster_list); - blk_queue_io_opt(bdev->rq, CLUSTER_SIZE); -} - -static int scm_prepare_cluster_request(struct scm_request *scmrq) -{ - struct scm_blk_dev *bdev = scmrq->bdev; - struct scm_device *scmdev = bdev->gendisk->private_data; - struct request *req = scmrq->request[0]; - struct msb *msb = &scmrq->aob->msb[0]; - struct req_iterator iter; - struct aidaw *aidaw; - struct bio_vec bv; - int i = 0; - u64 addr; - - switch (scmrq->cluster.state) { - case CLUSTER_NONE: - scmrq->cluster.state = CLUSTER_READ; - /* fall through */ - case CLUSTER_READ: - msb->bs = MSB_BS_4K; - msb->oc = MSB_OC_READ; - msb->flags = MSB_FLAG_IDA; - msb->blk_count = write_cluster_size; - - addr = scmdev->address + ((u64) blk_rq_pos(req) << 9); - msb->scm_addr = round_down(addr, CLUSTER_SIZE); - - if (msb->scm_addr != - round_down(addr + (u64) blk_rq_bytes(req) - 1, - CLUSTER_SIZE)) - msb->blk_count = 2 * write_cluster_size; - - aidaw = scm_aidaw_fetch(scmrq, msb->blk_count * PAGE_SIZE); - if (!aidaw) - return -ENOMEM; - - scmrq->aob->request.msb_count = 1; - msb->data_addr = (u64) aidaw; - for (i = 0; i < msb->blk_count; i++) { - aidaw->data_addr = (u64) scmrq->cluster.buf[i]; - aidaw++; - } - - break; - case CLUSTER_WRITE: - aidaw = (void *) msb->data_addr; - msb->oc = MSB_OC_WRITE; - - for (addr = msb->scm_addr; - addr < scmdev->address + ((u64) blk_rq_pos(req) << 9); - addr += PAGE_SIZE) { - aidaw->data_addr = (u64) scmrq->cluster.buf[i]; - aidaw++; - i++; - } - rq_for_each_segment(bv, req, iter) { - aidaw->data_addr = (u64) page_address(bv.bv_page); - aidaw++; - i++; - } - for (; i < msb->blk_count; i++) { - aidaw->data_addr = (u64) scmrq->cluster.buf[i]; - aidaw++; - } - break; - } - return 0; -} - -bool scm_need_cluster_request(struct scm_request *scmrq) -{ - int pos = scmrq->aob->request.msb_count; - - if (rq_data_dir(scmrq->request[pos]) == READ) - return false; - - return blk_rq_bytes(scmrq->request[pos]) < CLUSTER_SIZE; -} - -/* Called with queue lock held. */ -void scm_initiate_cluster_request(struct scm_request *scmrq) -{ - if (scm_prepare_cluster_request(scmrq)) - goto requeue; - if (eadm_start_aob(scmrq->aob)) - goto requeue; - return; -requeue: - scm_request_requeue(scmrq); -} - -bool scm_test_cluster_request(struct scm_request *scmrq) -{ - return scmrq->cluster.state != CLUSTER_NONE; -} - -void scm_cluster_request_irq(struct scm_request *scmrq) -{ - struct scm_blk_dev *bdev = scmrq->bdev; - unsigned long flags; - - switch (scmrq->cluster.state) { - case CLUSTER_NONE: - BUG(); - break; - case CLUSTER_READ: - if (scmrq->error) { - scm_request_finish(scmrq); - break; - } - scmrq->cluster.state = CLUSTER_WRITE; - spin_lock_irqsave(&bdev->rq_lock, flags); - scm_initiate_cluster_request(scmrq); - spin_unlock_irqrestore(&bdev->rq_lock, flags); - break; - case CLUSTER_WRITE: - scm_request_finish(scmrq); - break; - } -} - -bool scm_cluster_size_valid(void) -{ - if (write_cluster_size == 1 || write_cluster_size > 128) - return false; - - return !(write_cluster_size & (write_cluster_size - 1)); -} diff --git a/drivers/s390/block/xpram.c b/drivers/s390/block/xpram.c index b9d7e755c8a3..a48f0d40c1d2 100644 --- a/drivers/s390/block/xpram.c +++ b/drivers/s390/block/xpram.c @@ -190,7 +190,7 @@ static blk_qc_t xpram_make_request(struct request_queue *q, struct bio *bio) unsigned long page_addr; unsigned long bytes; - blk_queue_split(q, &bio, q->bio_split); + blk_queue_split(q, &bio); if ((bio->bi_iter.bi_sector & 7) != 0 || (bio->bi_iter.bi_size & 4095) != 0) diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c index e2aa944eb566..d3e504c3c362 100644 --- a/drivers/s390/cio/css.c +++ b/drivers/s390/cio/css.c @@ -296,6 +296,51 @@ static const struct attribute_group *default_subch_attr_groups[] = { NULL, }; +static ssize_t chpids_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct subchannel *sch = to_subchannel(dev); + struct chsc_ssd_info *ssd = &sch->ssd_info; + ssize_t ret = 0; + int mask; + int chp; + + for (chp = 0; chp < 8; chp++) { + mask = 0x80 >> chp; + if (ssd->path_mask & mask) + ret += sprintf(buf + ret, "%02x ", ssd->chpid[chp].id); + else + ret += sprintf(buf + ret, "00 "); + } + ret += sprintf(buf + ret, "\n"); + return ret; +} +static DEVICE_ATTR(chpids, 0444, chpids_show, NULL); + +static ssize_t pimpampom_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct subchannel *sch = to_subchannel(dev); + struct pmcw *pmcw = &sch->schib.pmcw; + + return sprintf(buf, "%02x %02x %02x\n", + pmcw->pim, pmcw->pam, pmcw->pom); +} +static DEVICE_ATTR(pimpampom, 0444, pimpampom_show, NULL); + +static struct attribute *io_subchannel_type_attrs[] = { + &dev_attr_chpids.attr, + &dev_attr_pimpampom.attr, + NULL, +}; +ATTRIBUTE_GROUPS(io_subchannel_type); + +static const struct device_type io_subchannel_type = { + .groups = io_subchannel_type_groups, +}; + int css_register_subchannel(struct subchannel *sch) { int ret; @@ -304,6 +349,10 @@ int css_register_subchannel(struct subchannel *sch) sch->dev.parent = &channel_subsystems[0]->device; sch->dev.bus = &css_bus_type; sch->dev.groups = default_subch_attr_groups; + + if (sch->st == SUBCHANNEL_TYPE_IO) + sch->dev.type = &io_subchannel_type; + /* * We don't want to generate uevents for I/O subchannels that don't * have a working ccw device behind them since they will be diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c index b8006ea9099c..7be01a58b44f 100644 --- a/drivers/s390/cio/device.c +++ b/drivers/s390/cio/device.c @@ -208,44 +208,6 @@ int __init io_subchannel_init(void) /************************ device handling **************************/ -/* - * A ccw_device has some interfaces in sysfs in addition to the - * standard ones. - * The following entries are designed to export the information which - * resided in 2.4 in /proc/subchannels. Subchannel and device number - * are obvious, so they don't have an entry :) - * TODO: Split chpids and pimpampom up? Where is "in use" in the tree? - */ -static ssize_t -chpids_show (struct device * dev, struct device_attribute *attr, char * buf) -{ - struct subchannel *sch = to_subchannel(dev); - struct chsc_ssd_info *ssd = &sch->ssd_info; - ssize_t ret = 0; - int chp; - int mask; - - for (chp = 0; chp < 8; chp++) { - mask = 0x80 >> chp; - if (ssd->path_mask & mask) - ret += sprintf(buf + ret, "%02x ", ssd->chpid[chp].id); - else - ret += sprintf(buf + ret, "00 "); - } - ret += sprintf (buf+ret, "\n"); - return min((ssize_t)PAGE_SIZE, ret); -} - -static ssize_t -pimpampom_show (struct device * dev, struct device_attribute *attr, char * buf) -{ - struct subchannel *sch = to_subchannel(dev); - struct pmcw *pmcw = &sch->schib.pmcw; - - return sprintf (buf, "%02x %02x %02x\n", - pmcw->pim, pmcw->pam, pmcw->pom); -} - static ssize_t devtype_show (struct device *dev, struct device_attribute *attr, char *buf) { @@ -636,8 +598,6 @@ static ssize_t vpm_show(struct device *dev, struct device_attribute *attr, return sprintf(buf, "%02x\n", sch->vpm); } -static DEVICE_ATTR(chpids, 0444, chpids_show, NULL); -static DEVICE_ATTR(pimpampom, 0444, pimpampom_show, NULL); static DEVICE_ATTR(devtype, 0444, devtype_show, NULL); static DEVICE_ATTR(cutype, 0444, cutype_show, NULL); static DEVICE_ATTR(modalias, 0444, modalias_show, NULL); @@ -647,8 +607,6 @@ static DEVICE_ATTR(logging, 0200, NULL, initiate_logging); static DEVICE_ATTR(vpm, 0444, vpm_show, NULL); static struct attribute *io_subchannel_attrs[] = { - &dev_attr_chpids.attr, - &dev_attr_pimpampom.attr, &dev_attr_logging.attr, &dev_attr_vpm.attr, NULL, diff --git a/drivers/s390/cio/eadm_sch.c b/drivers/s390/cio/eadm_sch.c index b3f44bc7f644..0f11f3bcac82 100644 --- a/drivers/s390/cio/eadm_sch.c +++ b/drivers/s390/cio/eadm_sch.c @@ -135,7 +135,7 @@ static void eadm_subchannel_irq(struct subchannel *sch) struct eadm_private *private = get_eadm_private(sch); struct eadm_scsw *scsw = &sch->schib.scsw.eadm; struct irb *irb = this_cpu_ptr(&cio_irb); - int error = 0; + blk_status_t error = BLK_STS_OK; EADM_LOG(6, "irq"); EADM_LOG_HEX(6, irb, sizeof(*irb)); @@ -144,10 +144,10 @@ static void eadm_subchannel_irq(struct subchannel *sch) if ((scsw->stctl & (SCSW_STCTL_ALERT_STATUS | SCSW_STCTL_STATUS_PEND)) && scsw->eswf == 1 && irb->esw.eadm.erw.r) - error = -EIO; + error = BLK_STS_IOERR; if (scsw->fctl & SCSW_FCTL_CLEAR_FUNC) - error = -ETIMEDOUT; + error = BLK_STS_TIMEOUT; eadm_subchannel_set_timeout(sch, 0); diff --git a/drivers/s390/cio/scm.c b/drivers/s390/cio/scm.c index 15268edc54ae..1fa53ecdc2aa 100644 --- a/drivers/s390/cio/scm.c +++ b/drivers/s390/cio/scm.c @@ -71,7 +71,7 @@ void scm_driver_unregister(struct scm_driver *scmdrv) } EXPORT_SYMBOL_GPL(scm_driver_unregister); -void scm_irq_handler(struct aob *aob, int error) +void scm_irq_handler(struct aob *aob, blk_status_t error) { struct aob_rq_header *aobrq = (void *) aob->request.data; struct scm_device *scmdev = aobrq->scmdev; diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c index e90dd43d2a55..a25367ebaa89 100644 --- a/drivers/s390/cio/vfio_ccw_drv.c +++ b/drivers/s390/cio/vfio_ccw_drv.c @@ -90,54 +90,6 @@ static void vfio_ccw_sch_io_todo(struct work_struct *work) } /* - * Sysfs interfaces - */ -static ssize_t chpids_show(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct subchannel *sch = to_subchannel(dev); - struct chsc_ssd_info *ssd = &sch->ssd_info; - ssize_t ret = 0; - int chp; - int mask; - - for (chp = 0; chp < 8; chp++) { - mask = 0x80 >> chp; - if (ssd->path_mask & mask) - ret += sprintf(buf + ret, "%02x ", ssd->chpid[chp].id); - else - ret += sprintf(buf + ret, "00 "); - } - ret += sprintf(buf+ret, "\n"); - return ret; -} - -static ssize_t pimpampom_show(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct subchannel *sch = to_subchannel(dev); - struct pmcw *pmcw = &sch->schib.pmcw; - - return sprintf(buf, "%02x %02x %02x\n", - pmcw->pim, pmcw->pam, pmcw->pom); -} - -static DEVICE_ATTR(chpids, 0444, chpids_show, NULL); -static DEVICE_ATTR(pimpampom, 0444, pimpampom_show, NULL); - -static struct attribute *vfio_subchannel_attrs[] = { - &dev_attr_chpids.attr, - &dev_attr_pimpampom.attr, - NULL, -}; - -static struct attribute_group vfio_subchannel_attr_group = { - .attrs = vfio_subchannel_attrs, -}; - -/* * Css driver callbacks */ static void vfio_ccw_sch_irq(struct subchannel *sch) @@ -174,13 +126,9 @@ static int vfio_ccw_sch_probe(struct subchannel *sch) if (ret) goto out_free; - ret = sysfs_create_group(&sch->dev.kobj, &vfio_subchannel_attr_group); - if (ret) - goto out_disable; - ret = vfio_ccw_mdev_reg(sch); if (ret) - goto out_rm_group; + goto out_disable; INIT_WORK(&private->io_work, vfio_ccw_sch_io_todo); atomic_set(&private->avail, 1); @@ -188,8 +136,6 @@ static int vfio_ccw_sch_probe(struct subchannel *sch) return 0; -out_rm_group: - sysfs_remove_group(&sch->dev.kobj, &vfio_subchannel_attr_group); out_disable: cio_disable_subchannel(sch); out_free: @@ -206,8 +152,6 @@ static int vfio_ccw_sch_remove(struct subchannel *sch) vfio_ccw_mdev_unreg(sch); - sysfs_remove_group(&sch->dev.kobj, &vfio_subchannel_attr_group); - dev_set_drvdata(&sch->dev, NULL); kfree(private); diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index ea099910b4e9..6dee598979e7 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -766,7 +766,7 @@ static ssize_t ap_domain_store(struct bus_type *bus, ap_domain_index = domain; spin_unlock_bh(&ap_domain_lock); - AP_DBF(DBF_DEBUG, "store new default domain=%d\n", domain); + AP_DBF(DBF_DEBUG, "stored new default domain=%d\n", domain); return count; } @@ -952,6 +952,7 @@ static int ap_select_domain(void) } if (best_domain >= 0){ ap_domain_index = best_domain; + AP_DBF(DBF_DEBUG, "new ap_domain_index=%d\n", ap_domain_index); spin_unlock_bh(&ap_domain_lock); return 0; } @@ -988,7 +989,7 @@ static void ap_scan_bus(struct work_struct *unused) ap_qid_t qid; int depth = 0, type = 0; unsigned int functions = 0; - int rc, id, dom, borked, domains; + int rc, id, dom, borked, domains, defdomdevs = 0; AP_DBF(DBF_DEBUG, "ap_scan_bus running\n"); @@ -1052,6 +1053,8 @@ static void ap_scan_bus(struct work_struct *unused) put_device(dev); if (!borked) { domains++; + if (dom == ap_domain_index) + defdomdevs++; continue; } } @@ -1098,6 +1101,8 @@ static void ap_scan_bus(struct work_struct *unused) continue; } domains++; + if (dom == ap_domain_index) + defdomdevs++; } /* end domain loop */ if (ac) { /* remove card dev if there are no queue devices */ @@ -1106,6 +1111,11 @@ static void ap_scan_bus(struct work_struct *unused) put_device(&ac->ap_dev.device); } } /* end device loop */ + + if (defdomdevs < 1) + AP_DBF(DBF_INFO, "no queue device with default domain %d available\n", + ap_domain_index); + out: mod_timer(&ap_config_timer, jiffies + ap_config_time * HZ); } @@ -1174,14 +1184,14 @@ int __init ap_module_init(void) ap_init_configuration(); if (ap_configuration) - max_domain_id = ap_max_domain_id ? : (AP_DOMAINS - 1); + max_domain_id = + ap_max_domain_id ? ap_max_domain_id : AP_DOMAINS - 1; else max_domain_id = 15; if (ap_domain_index < -1 || ap_domain_index > max_domain_id) { pr_warn("%d is not a valid cryptographic domain\n", ap_domain_index); - rc = -EINVAL; - goto out_free; + ap_domain_index = -1; } /* In resume callback we need to know if the user had set the domain. * If so, we can not just reset it. @@ -1254,7 +1264,6 @@ out: unregister_reset_call(&ap_reset_call); if (ap_using_interrupts()) unregister_adapter_interrupt(&ap_airq); -out_free: kfree(ap_configuration); return rc; } diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c index ea86da8c75f9..f61fa47135a6 100644 --- a/drivers/s390/crypto/pkey_api.c +++ b/drivers/s390/crypto/pkey_api.c @@ -178,9 +178,9 @@ static inline void prep_xcrb(struct ica_xcRB *pxcrb, pxcrb->user_defined = (cardnr == 0xFFFF ? AUTOSELECT : cardnr); pxcrb->request_control_blk_length = preqcblk->cprb_len + preqcblk->req_parml; - pxcrb->request_control_blk_addr = (void *) preqcblk; + pxcrb->request_control_blk_addr = (void __user *) preqcblk; pxcrb->reply_control_blk_length = preqcblk->rpl_msgbl; - pxcrb->reply_control_blk_addr = (void *) prepcblk; + pxcrb->reply_control_blk_addr = (void __user *) prepcblk; } /* @@ -1194,7 +1194,7 @@ static struct miscdevice pkey_dev = { /* * Module init */ -int __init pkey_init(void) +static int __init pkey_init(void) { cpacf_mask_t pckmo_functions; diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index 93015f85d4a6..b1c27e28859b 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -821,8 +821,10 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd, do { rc = zcrypt_rsa_modexpo(&mex); } while (rc == -EAGAIN); - if (rc) + if (rc) { + ZCRYPT_DBF(DBF_DEBUG, "ioctl ICARSAMODEXPO rc=%d", rc); return rc; + } return put_user(mex.outputdatalength, &umex->outputdatalength); } case ICARSACRT: { @@ -838,8 +840,10 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd, do { rc = zcrypt_rsa_crt(&crt); } while (rc == -EAGAIN); - if (rc) + if (rc) { + ZCRYPT_DBF(DBF_DEBUG, "ioctl ICARSACRT rc=%d", rc); return rc; + } return put_user(crt.outputdatalength, &ucrt->outputdatalength); } case ZSECSENDCPRB: { @@ -855,6 +859,8 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd, do { rc = zcrypt_send_cprb(&xcRB); } while (rc == -EAGAIN); + if (rc) + ZCRYPT_DBF(DBF_DEBUG, "ioctl ZSENDCPRB rc=%d", rc); if (copy_to_user(uxcRB, &xcRB, sizeof(xcRB))) return -EFAULT; return rc; @@ -872,6 +878,8 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd, do { rc = zcrypt_send_ep11_cprb(&xcrb); } while (rc == -EAGAIN); + if (rc) + ZCRYPT_DBF(DBF_DEBUG, "ioctl ZSENDEP11CPRB rc=%d", rc); if (copy_to_user(uxcrb, &xcrb, sizeof(xcrb))) return -EFAULT; return rc; diff --git a/drivers/s390/crypto/zcrypt_cca_key.h b/drivers/s390/crypto/zcrypt_cca_key.h index ca0cdbe46368..12cff6262566 100644 --- a/drivers/s390/crypto/zcrypt_cca_key.h +++ b/drivers/s390/crypto/zcrypt_cca_key.h @@ -48,26 +48,6 @@ struct cca_token_hdr { #define CCA_TKN_HDR_ID_EXT 0x1E -/** - * mapping for the cca private ME section - */ -struct cca_private_ext_ME_sec { - unsigned char section_identifier; - unsigned char version; - unsigned short section_length; - unsigned char private_key_hash[20]; - unsigned char reserved1[4]; - unsigned char key_format; - unsigned char reserved2; - unsigned char key_name_hash[20]; - unsigned char key_use_flags[4]; - unsigned char reserved3[6]; - unsigned char reserved4[24]; - unsigned char confounder[24]; - unsigned char exponent[128]; - unsigned char modulus[128]; -} __attribute__((packed)); - #define CCA_PVT_USAGE_ALL 0x80 /** @@ -124,77 +104,6 @@ struct cca_pvt_ext_CRT_sec { #define CCA_PVT_EXT_CRT_SEC_FMT_CL 0x40 /** - * Set up private key fields of a type6 MEX message. - * Note that all numerics in the key token are big-endian, - * while the entries in the key block header are little-endian. - * - * @mex: pointer to user input data - * @p: pointer to memory area for the key - * - * Returns the size of the key area or -EFAULT - */ -static inline int zcrypt_type6_mex_key_de(struct ica_rsa_modexpo *mex, - void *p, int big_endian) -{ - static struct cca_token_hdr static_pvt_me_hdr = { - .token_identifier = 0x1E, - .token_length = 0x0183, - }; - static struct cca_private_ext_ME_sec static_pvt_me_sec = { - .section_identifier = 0x02, - .section_length = 0x016C, - .key_use_flags = {0x80,0x00,0x00,0x00}, - }; - static struct cca_public_sec static_pub_me_sec = { - .section_identifier = 0x04, - .section_length = 0x000F, - .exponent_len = 0x0003, - }; - static char pk_exponent[3] = { 0x01, 0x00, 0x01 }; - struct { - struct T6_keyBlock_hdr t6_hdr; - struct cca_token_hdr pvtMeHdr; - struct cca_private_ext_ME_sec pvtMeSec; - struct cca_public_sec pubMeSec; - char exponent[3]; - } __attribute__((packed)) *key = p; - unsigned char *temp; - - memset(key, 0, sizeof(*key)); - - if (big_endian) { - key->t6_hdr.blen = cpu_to_be16(0x189); - key->t6_hdr.ulen = cpu_to_be16(0x189 - 2); - } else { - key->t6_hdr.blen = cpu_to_le16(0x189); - key->t6_hdr.ulen = cpu_to_le16(0x189 - 2); - } - key->pvtMeHdr = static_pvt_me_hdr; - key->pvtMeSec = static_pvt_me_sec; - key->pubMeSec = static_pub_me_sec; - /* - * In a private key, the modulus doesn't appear in the public - * section. So, an arbitrary public exponent of 0x010001 will be - * used. - */ - memcpy(key->exponent, pk_exponent, 3); - - /* key parameter block */ - temp = key->pvtMeSec.exponent + - sizeof(key->pvtMeSec.exponent) - mex->inputdatalength; - if (copy_from_user(temp, mex->b_key, mex->inputdatalength)) - return -EFAULT; - - /* modulus */ - temp = key->pvtMeSec.modulus + - sizeof(key->pvtMeSec.modulus) - mex->inputdatalength; - if (copy_from_user(temp, mex->n_modulus, mex->inputdatalength)) - return -EFAULT; - key->pubMeSec.modulus_bit_len = 8 * mex->inputdatalength; - return sizeof(*key); -} - -/** * Set up private key fields of a type6 MEX message. The _pad variant * strips leading zeroes from the b_key. * Note that all numerics in the key token are big-endian, @@ -205,8 +114,7 @@ static inline int zcrypt_type6_mex_key_de(struct ica_rsa_modexpo *mex, * * Returns the size of the key area or -EFAULT */ -static inline int zcrypt_type6_mex_key_en(struct ica_rsa_modexpo *mex, - void *p, int big_endian) +static inline int zcrypt_type6_mex_key_en(struct ica_rsa_modexpo *mex, void *p) { static struct cca_token_hdr static_pub_hdr = { .token_identifier = 0x1E, @@ -251,13 +159,8 @@ static inline int zcrypt_type6_mex_key_en(struct ica_rsa_modexpo *mex, 2*mex->inputdatalength - i; key->pubHdr.token_length = key->pubSec.section_length + sizeof(key->pubHdr); - if (big_endian) { - key->t6_hdr.ulen = cpu_to_be16(key->pubHdr.token_length + 4); - key->t6_hdr.blen = cpu_to_be16(key->pubHdr.token_length + 6); - } else { - key->t6_hdr.ulen = cpu_to_le16(key->pubHdr.token_length + 4); - key->t6_hdr.blen = cpu_to_le16(key->pubHdr.token_length + 6); - } + key->t6_hdr.ulen = key->pubHdr.token_length + 4; + key->t6_hdr.blen = key->pubHdr.token_length + 6; return sizeof(*key) + 2*mex->inputdatalength - i; } @@ -271,8 +174,7 @@ static inline int zcrypt_type6_mex_key_en(struct ica_rsa_modexpo *mex, * * Returns the size of the key area or -EFAULT */ -static inline int zcrypt_type6_crt_key(struct ica_rsa_modexpo_crt *crt, - void *p, int big_endian) +static inline int zcrypt_type6_crt_key(struct ica_rsa_modexpo_crt *crt, void *p) { static struct cca_public_sec static_cca_pub_sec = { .section_identifier = 4, @@ -298,13 +200,8 @@ static inline int zcrypt_type6_crt_key(struct ica_rsa_modexpo_crt *crt, size = sizeof(*key) + key_len + sizeof(*pub) + 3; /* parameter block.key block */ - if (big_endian) { - key->t6_hdr.blen = cpu_to_be16(size); - key->t6_hdr.ulen = cpu_to_be16(size - 2); - } else { - key->t6_hdr.blen = cpu_to_le16(size); - key->t6_hdr.ulen = cpu_to_le16(size - 2); - } + key->t6_hdr.blen = size; + key->t6_hdr.ulen = size - 2; /* key token header */ key->token.token_identifier = CCA_TKN_HDR_ID_EXT; diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c index e5563ffeb839..4fddb4319481 100644 --- a/drivers/s390/crypto/zcrypt_msgtype6.c +++ b/drivers/s390/crypto/zcrypt_msgtype6.c @@ -291,7 +291,7 @@ static int ICAMEX_msg_to_type6MEX_msgX(struct zcrypt_queue *zq, return -EFAULT; /* Set up key which is located after the variable length text. */ - size = zcrypt_type6_mex_key_en(mex, msg->text+mex->inputdatalength, 1); + size = zcrypt_type6_mex_key_en(mex, msg->text+mex->inputdatalength); if (size < 0) return size; size += sizeof(*msg) + mex->inputdatalength; @@ -353,7 +353,7 @@ static int ICACRT_msg_to_type6CRT_msgX(struct zcrypt_queue *zq, return -EFAULT; /* Set up key which is located after the variable length text. */ - size = zcrypt_type6_crt_key(crt, msg->text + crt->inputdatalength, 1); + size = zcrypt_type6_crt_key(crt, msg->text + crt->inputdatalength); if (size < 0) return size; size += sizeof(*msg) + crt->inputdatalength; /* total size of msg */ diff --git a/drivers/sbus/char/jsflash.c b/drivers/sbus/char/jsflash.c index 62fed9dc893e..14f377ac1280 100644 --- a/drivers/sbus/char/jsflash.c +++ b/drivers/sbus/char/jsflash.c @@ -214,7 +214,7 @@ static void jsfd_request(void) struct jsfd_part *jdp = req->rq_disk->private_data; unsigned long offset = blk_rq_pos(req) << 9; size_t len = blk_rq_cur_bytes(req); - int err = -EIO; + blk_status_t err = BLK_STS_IOERR; if ((offset + len) > jdp->dsize) goto end; @@ -230,7 +230,7 @@ static void jsfd_request(void) } jsfd_read(bio_data(req->bio), jdp->dbase + offset, len); - err = 0; + err = BLK_STS_OK; end: if (!__blk_end_request_cur(req, err)) req = jsfd_next_request(); @@ -592,6 +592,7 @@ static int jsfd_init(void) put_disk(disk); goto out; } + blk_queue_bounce_limit(disk->queue, BLK_BOUNCE_HIGH); jsfd_disk[i] = disk; } diff --git a/drivers/scsi/dpt/dpti_i2o.h b/drivers/scsi/dpt/dpti_i2o.h index bd9e31e16249..16fc380b5512 100644 --- a/drivers/scsi/dpt/dpti_i2o.h +++ b/drivers/scsi/dpt/dpti_i2o.h @@ -48,7 +48,7 @@ #include <linux/wait.h> typedef wait_queue_head_t adpt_wait_queue_head_t; #define ADPT_DECLARE_WAIT_QUEUE_HEAD(wait) DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wait) -typedef wait_queue_t adpt_wait_queue_t; +typedef wait_queue_entry_t adpt_wait_queue_entry_t; /* * message structures diff --git a/drivers/scsi/ips.c b/drivers/scsi/ips.c index 3419e1bcdff6..67621308eb9c 100644 --- a/drivers/scsi/ips.c +++ b/drivers/scsi/ips.c @@ -301,13 +301,13 @@ static uint32_t ips_statupd_copperhead_memio(ips_ha_t *); static uint32_t ips_statupd_morpheus(ips_ha_t *); static ips_scb_t *ips_getscb(ips_ha_t *); static void ips_putq_scb_head(ips_scb_queue_t *, ips_scb_t *); -static void ips_putq_wait_tail(ips_wait_queue_t *, struct scsi_cmnd *); +static void ips_putq_wait_tail(ips_wait_queue_entry_t *, struct scsi_cmnd *); static void ips_putq_copp_tail(ips_copp_queue_t *, ips_copp_wait_item_t *); static ips_scb_t *ips_removeq_scb_head(ips_scb_queue_t *); static ips_scb_t *ips_removeq_scb(ips_scb_queue_t *, ips_scb_t *); -static struct scsi_cmnd *ips_removeq_wait_head(ips_wait_queue_t *); -static struct scsi_cmnd *ips_removeq_wait(ips_wait_queue_t *, +static struct scsi_cmnd *ips_removeq_wait_head(ips_wait_queue_entry_t *); +static struct scsi_cmnd *ips_removeq_wait(ips_wait_queue_entry_t *, struct scsi_cmnd *); static ips_copp_wait_item_t *ips_removeq_copp(ips_copp_queue_t *, ips_copp_wait_item_t *); @@ -2871,7 +2871,7 @@ ips_removeq_scb(ips_scb_queue_t * queue, ips_scb_t * item) /* ASSUMED to be called from within the HA lock */ /* */ /****************************************************************************/ -static void ips_putq_wait_tail(ips_wait_queue_t *queue, struct scsi_cmnd *item) +static void ips_putq_wait_tail(ips_wait_queue_entry_t *queue, struct scsi_cmnd *item) { METHOD_TRACE("ips_putq_wait_tail", 1); @@ -2902,7 +2902,7 @@ static void ips_putq_wait_tail(ips_wait_queue_t *queue, struct scsi_cmnd *item) /* ASSUMED to be called from within the HA lock */ /* */ /****************************************************************************/ -static struct scsi_cmnd *ips_removeq_wait_head(ips_wait_queue_t *queue) +static struct scsi_cmnd *ips_removeq_wait_head(ips_wait_queue_entry_t *queue) { struct scsi_cmnd *item; @@ -2936,7 +2936,7 @@ static struct scsi_cmnd *ips_removeq_wait_head(ips_wait_queue_t *queue) /* ASSUMED to be called from within the HA lock */ /* */ /****************************************************************************/ -static struct scsi_cmnd *ips_removeq_wait(ips_wait_queue_t *queue, +static struct scsi_cmnd *ips_removeq_wait(ips_wait_queue_entry_t *queue, struct scsi_cmnd *item) { struct scsi_cmnd *p; diff --git a/drivers/scsi/ips.h b/drivers/scsi/ips.h index b782bb60baf0..366be3b2f9b4 100644 --- a/drivers/scsi/ips.h +++ b/drivers/scsi/ips.h @@ -989,7 +989,7 @@ typedef struct ips_wait_queue { struct scsi_cmnd *head; struct scsi_cmnd *tail; int count; -} ips_wait_queue_t; +} ips_wait_queue_entry_t; typedef struct ips_copp_wait_item { struct scsi_cmnd *scsi_cmd; @@ -1035,7 +1035,7 @@ typedef struct ips_ha { ips_stat_t sp; /* Status packer pointer */ struct ips_scb *scbs; /* Array of all CCBS */ struct ips_scb *scb_freelist; /* SCB free list */ - ips_wait_queue_t scb_waitlist; /* Pending SCB list */ + ips_wait_queue_entry_t scb_waitlist; /* Pending SCB list */ ips_copp_queue_t copp_waitlist; /* Pending PT list */ ips_scb_queue_t scb_activelist; /* Active SCB list */ IPS_IO_CMD *dummy; /* dummy command */ diff --git a/drivers/scsi/osd/osd_initiator.c b/drivers/scsi/osd/osd_initiator.c index 8a1b94816419..a4f28b7e4c65 100644 --- a/drivers/scsi/osd/osd_initiator.c +++ b/drivers/scsi/osd/osd_initiator.c @@ -446,7 +446,7 @@ static void _put_request(struct request *rq) * code paths. */ if (unlikely(rq->bio)) - blk_end_request(rq, -ENOMEM, blk_rq_bytes(rq)); + blk_end_request(rq, BLK_STS_IOERR, blk_rq_bytes(rq)); else blk_put_request(rq); } @@ -474,10 +474,10 @@ void osd_end_request(struct osd_request *or) EXPORT_SYMBOL(osd_end_request); static void _set_error_resid(struct osd_request *or, struct request *req, - int error) + blk_status_t error) { or->async_error = error; - or->req_errors = scsi_req(req)->result ? : error; + or->req_errors = scsi_req(req)->result; or->sense_len = scsi_req(req)->sense_len; if (or->sense_len) memcpy(or->sense, scsi_req(req)->sense, or->sense_len); @@ -489,17 +489,19 @@ static void _set_error_resid(struct osd_request *or, struct request *req, int osd_execute_request(struct osd_request *or) { - int error; - blk_execute_rq(or->request->q, NULL, or->request, 0); - error = scsi_req(or->request)->result ? -EIO : 0; - _set_error_resid(or, or->request, error); - return error; + if (scsi_req(or->request)->result) { + _set_error_resid(or, or->request, BLK_STS_IOERR); + return -EIO; + } + + _set_error_resid(or, or->request, BLK_STS_OK); + return 0; } EXPORT_SYMBOL(osd_execute_request); -static void osd_request_async_done(struct request *req, int error) +static void osd_request_async_done(struct request *req, blk_status_t error) { struct osd_request *or = req->end_io_data; @@ -1572,13 +1574,9 @@ static struct request *_make_request(struct request_queue *q, bool has_write, flags); if (IS_ERR(req)) return req; - scsi_req_init(req); for_each_bio(bio) { - struct bio *bounce_bio = bio; - - blk_queue_bounce(req->q, &bounce_bio); - ret = blk_rq_append_bio(req, bounce_bio); + ret = blk_rq_append_bio(req, bio); if (ret) return ERR_PTR(ret); } @@ -1617,7 +1615,6 @@ static int _init_blk_request(struct osd_request *or, ret = PTR_ERR(req); goto out; } - scsi_req_init(req); or->in.req = or->request->next_rq = req; } } else if (has_in) @@ -1914,7 +1911,7 @@ analyze: /* scsi sense is Empty, the request was never issued to target * linux return code might tell us what happened. */ - if (or->async_error == -ENOMEM) + if (or->async_error == BLK_STS_RESOURCE) osi->osd_err_pri = OSD_ERR_PRI_RESOURCE; else osi->osd_err_pri = OSD_ERR_PRI_UNREACHABLE; diff --git a/drivers/scsi/osst.c b/drivers/scsi/osst.c index 67cbed92f07d..929ee7e88120 100644 --- a/drivers/scsi/osst.c +++ b/drivers/scsi/osst.c @@ -320,7 +320,7 @@ static int osst_chk_result(struct osst_tape * STp, struct osst_request * SRpnt) /* Wakeup from interrupt */ -static void osst_end_async(struct request *req, int update) +static void osst_end_async(struct request *req, blk_status_t status) { struct scsi_request *rq = scsi_req(req); struct osst_request *SRpnt = req->end_io_data; @@ -373,7 +373,6 @@ static int osst_execute(struct osst_request *SRpnt, const unsigned char *cmd, return DRIVER_ERROR << 24; rq = scsi_req(req); - scsi_req_init(req); req->rq_flags |= RQF_QUIET; SRpnt->bio = NULL; diff --git a/drivers/scsi/qedi/qedi_fw.c b/drivers/scsi/qedi/qedi_fw.c index 8bc7ee1a8ca8..507512cc478b 100644 --- a/drivers/scsi/qedi/qedi_fw.c +++ b/drivers/scsi/qedi/qedi_fw.c @@ -870,7 +870,6 @@ static void qedi_process_cmd_cleanup_resp(struct qedi_ctx *qedi, QEDI_ERR(&qedi->dbg_ctx, "Delayed or untracked cleanup response, itt=0x%x, tid=0x%x, cid=0x%x, task=%p\n", protoitt, cqe->itid, qedi_conn->iscsi_conn_id, task); - WARN_ON(1); } } diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index 09a294634bc7..879d3b7462f9 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -1499,11 +1499,9 @@ err_idx: void qedi_clear_task_idx(struct qedi_ctx *qedi, int idx) { - if (!test_and_clear_bit(idx, qedi->task_idx_map)) { + if (!test_and_clear_bit(idx, qedi->task_idx_map)) QEDI_ERR(&qedi->dbg_ctx, "FW task context, already cleared, tid=0x%x\n", idx); - WARN_ON(1); - } } void qedi_update_itt_map(struct qedi_ctx *qedi, u32 tid, u32 proto_itt, diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index dc095a292c61..3be980d47268 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -245,7 +245,7 @@ struct sdebug_dev_info { unsigned int channel; unsigned int target; u64 lun; - uuid_be lu_name; + uuid_t lu_name; struct sdebug_host_info *sdbg_host; unsigned long uas_bm[1]; atomic_t num_in_q; @@ -965,7 +965,7 @@ static const u64 naa3_comp_c = 0x3111111000000000ULL; static int inquiry_vpd_83(unsigned char *arr, int port_group_id, int target_dev_id, int dev_id_num, const char *dev_id_str, int dev_id_str_len, - const uuid_be *lu_name) + const uuid_t *lu_name) { int num, port_a; char b[32]; @@ -3568,7 +3568,7 @@ static void sdebug_q_cmd_wq_complete(struct work_struct *work) } static bool got_shared_uuid; -static uuid_be shared_uuid; +static uuid_t shared_uuid; static struct sdebug_dev_info *sdebug_device_create( struct sdebug_host_info *sdbg_host, gfp_t flags) @@ -3578,12 +3578,12 @@ static struct sdebug_dev_info *sdebug_device_create( devip = kzalloc(sizeof(*devip), flags); if (devip) { if (sdebug_uuid_ctl == 1) - uuid_be_gen(&devip->lu_name); + uuid_gen(&devip->lu_name); else if (sdebug_uuid_ctl == 2) { if (got_shared_uuid) devip->lu_name = shared_uuid; else { - uuid_be_gen(&shared_uuid); + uuid_gen(&shared_uuid); got_shared_uuid = true; devip->lu_name = shared_uuid; } diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index ecc07dab893d..304a7158540f 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -1874,7 +1874,7 @@ int scsi_decide_disposition(struct scsi_cmnd *scmd) } } -static void eh_lock_door_done(struct request *req, int uptodate) +static void eh_lock_door_done(struct request *req, blk_status_t status) { __blk_put_request(req->q, req); } @@ -1903,7 +1903,6 @@ static void scsi_eh_lock_door(struct scsi_device *sdev) if (IS_ERR(req)) return; rq = scsi_req(req); - scsi_req_init(req); rq->cmd[0] = ALLOW_MEDIUM_REMOVAL; rq->cmd[1] = 0; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 99e16ac479e3..550e29f903b7 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -250,7 +250,6 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd, if (IS_ERR(req)) return ret; rq = scsi_req(req); - scsi_req_init(req); if (bufflen && blk_rq_map_kern(sdev->request_queue, req, buffer, bufflen, __GFP_RECLAIM)) @@ -635,7 +634,7 @@ static void scsi_release_bidi_buffers(struct scsi_cmnd *cmd) cmd->request->next_rq->special = NULL; } -static bool scsi_end_request(struct request *req, int error, +static bool scsi_end_request(struct request *req, blk_status_t error, unsigned int bytes, unsigned int bidi_bytes) { struct scsi_cmnd *cmd = req->special; @@ -694,45 +693,28 @@ static bool scsi_end_request(struct request *req, int error, * @cmd: SCSI command (unused) * @result: scsi error code * - * Translate SCSI error code into standard UNIX errno. - * Return values: - * -ENOLINK temporary transport failure - * -EREMOTEIO permanent target failure, do not retry - * -EBADE permanent nexus failure, retry on other path - * -ENOSPC No write space available - * -ENODATA Medium error - * -EIO unspecified I/O error + * Translate SCSI error code into block errors. */ -static int __scsi_error_from_host_byte(struct scsi_cmnd *cmd, int result) +static blk_status_t __scsi_error_from_host_byte(struct scsi_cmnd *cmd, + int result) { - int error = 0; - - switch(host_byte(result)) { + switch (host_byte(result)) { case DID_TRANSPORT_FAILFAST: - error = -ENOLINK; - break; + return BLK_STS_TRANSPORT; case DID_TARGET_FAILURE: set_host_byte(cmd, DID_OK); - error = -EREMOTEIO; - break; + return BLK_STS_TARGET; case DID_NEXUS_FAILURE: - set_host_byte(cmd, DID_OK); - error = -EBADE; - break; + return BLK_STS_NEXUS; case DID_ALLOC_FAILURE: set_host_byte(cmd, DID_OK); - error = -ENOSPC; - break; + return BLK_STS_NOSPC; case DID_MEDIUM_ERROR: set_host_byte(cmd, DID_OK); - error = -ENODATA; - break; + return BLK_STS_MEDIUM; default: - error = -EIO; - break; + return BLK_STS_IOERR; } - - return error; } /* @@ -769,7 +751,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) int result = cmd->result; struct request_queue *q = cmd->device->request_queue; struct request *req = cmd->request; - int error = 0; + blk_status_t error = BLK_STS_OK; struct scsi_sense_hdr sshdr; bool sense_valid = false; int sense_deferred = 0, level = 0; @@ -808,7 +790,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) * both sides at once. */ scsi_req(req->next_rq)->resid_len = scsi_in(cmd)->resid; - if (scsi_end_request(req, 0, blk_rq_bytes(req), + if (scsi_end_request(req, BLK_STS_OK, blk_rq_bytes(req), blk_rq_bytes(req->next_rq))) BUG(); return; @@ -850,7 +832,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) scsi_print_sense(cmd); result = 0; /* for passthrough error may be set */ - error = 0; + error = BLK_STS_OK; } /* @@ -922,18 +904,18 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) action = ACTION_REPREP; } else if (sshdr.asc == 0x10) /* DIX */ { action = ACTION_FAIL; - error = -EILSEQ; + error = BLK_STS_PROTECTION; /* INVALID COMMAND OPCODE or INVALID FIELD IN CDB */ } else if (sshdr.asc == 0x20 || sshdr.asc == 0x24) { action = ACTION_FAIL; - error = -EREMOTEIO; + error = BLK_STS_TARGET; } else action = ACTION_FAIL; break; case ABORTED_COMMAND: action = ACTION_FAIL; if (sshdr.asc == 0x10) /* DIF */ - error = -EILSEQ; + error = BLK_STS_PROTECTION; break; case NOT_READY: /* If the device is in the process of becoming @@ -1134,6 +1116,20 @@ err_exit: } EXPORT_SYMBOL(scsi_init_io); +/** + * scsi_initialize_rq - initialize struct scsi_cmnd.req + * + * Called from inside blk_get_request(). + */ +void scsi_initialize_rq(struct request *rq) +{ + struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq); + + scsi_req_init(&cmd->req); +} +EXPORT_SYMBOL(scsi_initialize_rq); + +/* Called after a request has been started. */ void scsi_init_command(struct scsi_device *dev, struct scsi_cmnd *cmd) { void *buf = cmd->sense_buffer; @@ -1829,15 +1825,15 @@ out_delay: blk_delay_queue(q, SCSI_QUEUE_DELAY); } -static inline int prep_to_mq(int ret) +static inline blk_status_t prep_to_mq(int ret) { switch (ret) { case BLKPREP_OK: - return BLK_MQ_RQ_QUEUE_OK; + return BLK_STS_OK; case BLKPREP_DEFER: - return BLK_MQ_RQ_QUEUE_BUSY; + return BLK_STS_RESOURCE; default: - return BLK_MQ_RQ_QUEUE_ERROR; + return BLK_STS_IOERR; } } @@ -1909,7 +1905,7 @@ static void scsi_mq_done(struct scsi_cmnd *cmd) blk_mq_complete_request(cmd->request); } -static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx, +static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { struct request *req = bd->rq; @@ -1917,14 +1913,14 @@ static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx, struct scsi_device *sdev = q->queuedata; struct Scsi_Host *shost = sdev->host; struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(req); - int ret; + blk_status_t ret; int reason; ret = prep_to_mq(scsi_prep_state_check(sdev, req)); - if (ret != BLK_MQ_RQ_QUEUE_OK) + if (ret != BLK_STS_OK) goto out; - ret = BLK_MQ_RQ_QUEUE_BUSY; + ret = BLK_STS_RESOURCE; if (!get_device(&sdev->sdev_gendev)) goto out; @@ -1937,7 +1933,7 @@ static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx, if (!(req->rq_flags & RQF_DONTPREP)) { ret = prep_to_mq(scsi_mq_prep_fn(req)); - if (ret != BLK_MQ_RQ_QUEUE_OK) + if (ret != BLK_STS_OK) goto out_dec_host_busy; req->rq_flags |= RQF_DONTPREP; } else { @@ -1955,11 +1951,11 @@ static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx, reason = scsi_dispatch_cmd(cmd); if (reason) { scsi_set_blocked(cmd, reason); - ret = BLK_MQ_RQ_QUEUE_BUSY; + ret = BLK_STS_RESOURCE; goto out_dec_host_busy; } - return BLK_MQ_RQ_QUEUE_OK; + return BLK_STS_OK; out_dec_host_busy: atomic_dec(&shost->host_busy); @@ -1972,12 +1968,14 @@ out_put_device: put_device(&sdev->sdev_gendev); out: switch (ret) { - case BLK_MQ_RQ_QUEUE_BUSY: + case BLK_STS_OK: + break; + case BLK_STS_RESOURCE: if (atomic_read(&sdev->device_busy) == 0 && !scsi_device_blocked(sdev)) blk_mq_delay_run_hw_queue(hctx, SCSI_QUEUE_DELAY); break; - case BLK_MQ_RQ_QUEUE_ERROR: + default: /* * Make sure to release all allocated ressources when * we hit an error, as we will never see this command @@ -1986,8 +1984,6 @@ out: if (req->rq_flags & RQF_DONTPREP) scsi_mq_uninit_cmd(cmd); break; - default: - break; } return ret; } @@ -2057,6 +2053,8 @@ void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q) { struct device *dev = shost->dma_dev; + queue_flag_set_unlocked(QUEUE_FLAG_SCSI_PASSTHROUGH, q); + /* * this limit is imposed by hardware restrictions */ @@ -2139,6 +2137,7 @@ struct request_queue *scsi_alloc_queue(struct scsi_device *sdev) q->request_fn = scsi_request_fn; q->init_rq_fn = scsi_init_rq; q->exit_rq_fn = scsi_exit_rq; + q->initialize_rq_fn = scsi_initialize_rq; if (blk_init_allocated_queue(q) < 0) { blk_cleanup_queue(q); @@ -2163,6 +2162,7 @@ static const struct blk_mq_ops scsi_mq_ops = { #endif .init_request = scsi_init_request, .exit_request = scsi_exit_request, + .initialize_rq_fn = scsi_initialize_rq, .map_queues = scsi_map_queues, }; @@ -2977,7 +2977,7 @@ scsi_internal_device_block(struct scsi_device *sdev, bool wait) if (wait) blk_mq_quiesce_queue(q); else - blk_mq_stop_hw_queues(q); + blk_mq_quiesce_queue_nowait(q); } else { spin_lock_irqsave(q->queue_lock, flags); blk_stop_queue(q); @@ -3031,7 +3031,7 @@ scsi_internal_device_unblock(struct scsi_device *sdev, return -EINVAL; if (q->mq_ops) { - blk_mq_start_stopped_hw_queues(q, false); + blk_mq_unquiesce_queue(q); } else { spin_lock_irqsave(q->queue_lock, flags); blk_start_queue(q); diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c index 0ebe2f1bb908..5006a656e16a 100644 --- a/drivers/scsi/scsi_transport_sas.c +++ b/drivers/scsi/scsi_transport_sas.c @@ -33,6 +33,7 @@ #include <linux/bsg.h> #include <scsi/scsi.h> +#include <scsi/scsi_cmnd.h> #include <scsi/scsi_request.h> #include <scsi/scsi_device.h> #include <scsi/scsi_host.h> @@ -172,7 +173,7 @@ static void sas_smp_request(struct request_queue *q, struct Scsi_Host *shost, struct sas_rphy *rphy) { struct request *req; - int ret; + blk_status_t ret; int (*handler)(struct Scsi_Host *, struct sas_rphy *, struct request *); while ((req = blk_fetch_request(q)) != NULL) { @@ -230,6 +231,7 @@ static int sas_bsg_initialize(struct Scsi_Host *shost, struct sas_rphy *rphy) q = blk_alloc_queue(GFP_KERNEL); if (!q) return -ENOMEM; + q->initialize_rq_fn = scsi_initialize_rq; q->cmd_size = sizeof(struct scsi_request); if (rphy) { @@ -249,6 +251,11 @@ static int sas_bsg_initialize(struct Scsi_Host *shost, struct sas_rphy *rphy) if (error) goto out_cleanup_queue; + /* + * by default assume old behaviour and bounce for any highmem page + */ + blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH); + error = bsg_register_queue(q, dev, name, release); if (error) goto out_cleanup_queue; @@ -264,6 +271,7 @@ static int sas_bsg_initialize(struct Scsi_Host *shost, struct sas_rphy *rphy) q->queuedata = shost; queue_flag_set_unlocked(QUEUE_FLAG_BIDI, q); + queue_flag_set_unlocked(QUEUE_FLAG_SCSI_PASSTHROUGH, q); return 0; out_cleanup_queue: diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 82c33a6edbea..21225d62b0c1 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -177,7 +177,7 @@ typedef struct sg_device { /* holds the state of each scsi generic device */ } Sg_device; /* tasklet or soft irq callback */ -static void sg_rq_end_io(struct request *rq, int uptodate); +static void sg_rq_end_io(struct request *rq, blk_status_t status); static int sg_start_req(Sg_request *srp, unsigned char *cmd); static int sg_finish_rem_req(Sg_request * srp); static int sg_build_indirect(Sg_scatter_hold * schp, Sg_fd * sfp, int buff_size); @@ -808,7 +808,7 @@ sg_common_write(Sg_fd * sfp, Sg_request * srp, if (atomic_read(&sdp->detaching)) { if (srp->bio) { scsi_req_free_cmd(scsi_req(srp->rq)); - blk_end_request_all(srp->rq, -EIO); + blk_end_request_all(srp->rq, BLK_STS_IOERR); srp->rq = NULL; } @@ -1300,7 +1300,7 @@ sg_rq_end_io_usercontext(struct work_struct *work) * level when a command is completed (or has failed). */ static void -sg_rq_end_io(struct request *rq, int uptodate) +sg_rq_end_io(struct request *rq, blk_status_t status) { struct sg_request *srp = rq->end_io_data; struct scsi_request *req = scsi_req(rq); @@ -1732,8 +1732,6 @@ sg_start_req(Sg_request *srp, unsigned char *cmd) } req = scsi_req(rq); - scsi_req_init(rq); - if (hp->cmd_len > BLK_MAX_CDB) req->cmd = long_cmdp; memcpy(req->cmd, cmd, hp->cmd_len); diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c index 1ea34d6f5437..8e5013d9cad4 100644 --- a/drivers/scsi/st.c +++ b/drivers/scsi/st.c @@ -511,7 +511,7 @@ static void st_do_stats(struct scsi_tape *STp, struct request *req) atomic64_dec(&STp->stats->in_flight); } -static void st_scsi_execute_end(struct request *req, int uptodate) +static void st_scsi_execute_end(struct request *req, blk_status_t status) { struct st_request *SRpnt = req->end_io_data; struct scsi_request *rq = scsi_req(req); @@ -549,7 +549,6 @@ static int st_scsi_execute(struct st_request *SRpnt, const unsigned char *cmd, if (IS_ERR(req)) return DRIVER_ERROR << 24; rq = scsi_req(req); - scsi_req_init(req); req->rq_flags |= RQF_QUIET; mdata->null_mapped = 1; diff --git a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c index 0db662d6abdd..85b242ec5f9b 100644 --- a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c +++ b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c @@ -3267,7 +3267,7 @@ int kiblnd_connd(void *arg) { spinlock_t *lock = &kiblnd_data.kib_connd_lock; - wait_queue_t wait; + wait_queue_entry_t wait; unsigned long flags; struct kib_conn *conn; int timeout; @@ -3521,7 +3521,7 @@ kiblnd_scheduler(void *arg) long id = (long)arg; struct kib_sched_info *sched; struct kib_conn *conn; - wait_queue_t wait; + wait_queue_entry_t wait; unsigned long flags; struct ib_wc wc; int did_something; @@ -3656,7 +3656,7 @@ kiblnd_failover_thread(void *arg) { rwlock_t *glock = &kiblnd_data.kib_global_lock; struct kib_dev *dev; - wait_queue_t wait; + wait_queue_entry_t wait; unsigned long flags; int rc; diff --git a/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_cb.c b/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_cb.c index 3ed3b08c122c..6b38d5a8fe92 100644 --- a/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_cb.c +++ b/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_cb.c @@ -2166,7 +2166,7 @@ ksocknal_connd(void *arg) { spinlock_t *connd_lock = &ksocknal_data.ksnd_connd_lock; struct ksock_connreq *cr; - wait_queue_t wait; + wait_queue_entry_t wait; int nloops = 0; int cons_retry = 0; @@ -2554,7 +2554,7 @@ ksocknal_check_peer_timeouts(int idx) int ksocknal_reaper(void *arg) { - wait_queue_t wait; + wait_queue_entry_t wait; struct ksock_conn *conn; struct ksock_sched *sched; struct list_head enomem_conns; diff --git a/drivers/staging/lustre/lnet/libcfs/debug.c b/drivers/staging/lustre/lnet/libcfs/debug.c index c56e9922cd5b..49deb448b044 100644 --- a/drivers/staging/lustre/lnet/libcfs/debug.c +++ b/drivers/staging/lustre/lnet/libcfs/debug.c @@ -361,7 +361,7 @@ static int libcfs_debug_dumplog_thread(void *arg) void libcfs_debug_dumplog(void) { - wait_queue_t wait; + wait_queue_entry_t wait; struct task_struct *dumper; /* we're being careful to ensure that the kernel thread is diff --git a/drivers/staging/lustre/lnet/libcfs/tracefile.c b/drivers/staging/lustre/lnet/libcfs/tracefile.c index 9599b7441feb..27082d2f7938 100644 --- a/drivers/staging/lustre/lnet/libcfs/tracefile.c +++ b/drivers/staging/lustre/lnet/libcfs/tracefile.c @@ -990,7 +990,7 @@ static int tracefiled(void *arg) complete(&tctl->tctl_start); while (1) { - wait_queue_t __wait; + wait_queue_entry_t __wait; pc.pc_want_daemon_pages = 0; collect_pages(&pc); diff --git a/drivers/staging/lustre/lnet/lnet/lib-eq.c b/drivers/staging/lustre/lnet/lnet/lib-eq.c index ce4b83584e17..9ebba4ef5f90 100644 --- a/drivers/staging/lustre/lnet/lnet/lib-eq.c +++ b/drivers/staging/lustre/lnet/lnet/lib-eq.c @@ -312,7 +312,7 @@ __must_hold(&the_lnet.ln_eq_wait_lock) { int tms = *timeout_ms; int wait; - wait_queue_t wl; + wait_queue_entry_t wl; unsigned long now; if (!tms) diff --git a/drivers/staging/lustre/lnet/lnet/lib-socket.c b/drivers/staging/lustre/lnet/lnet/lib-socket.c index 9fca8d225ee0..f075706bba6d 100644 --- a/drivers/staging/lustre/lnet/lnet/lib-socket.c +++ b/drivers/staging/lustre/lnet/lnet/lib-socket.c @@ -516,7 +516,7 @@ lnet_sock_listen(struct socket **sockp, __u32 local_ip, int local_port, int lnet_sock_accept(struct socket **newsockp, struct socket *sock) { - wait_queue_t wait; + wait_queue_entry_t wait; struct socket *newsock; int rc; diff --git a/drivers/staging/lustre/lustre/fid/fid_request.c b/drivers/staging/lustre/lustre/fid/fid_request.c index 999f250ceed0..bf31bc200d27 100644 --- a/drivers/staging/lustre/lustre/fid/fid_request.c +++ b/drivers/staging/lustre/lustre/fid/fid_request.c @@ -192,7 +192,7 @@ static int seq_client_alloc_seq(const struct lu_env *env, } static int seq_fid_alloc_prep(struct lu_client_seq *seq, - wait_queue_t *link) + wait_queue_entry_t *link) { if (seq->lcs_update) { add_wait_queue(&seq->lcs_waitq, link); @@ -223,7 +223,7 @@ static void seq_fid_alloc_fini(struct lu_client_seq *seq) int seq_client_alloc_fid(const struct lu_env *env, struct lu_client_seq *seq, struct lu_fid *fid) { - wait_queue_t link; + wait_queue_entry_t link; int rc; LASSERT(seq); @@ -290,7 +290,7 @@ EXPORT_SYMBOL(seq_client_alloc_fid); */ void seq_client_flush(struct lu_client_seq *seq) { - wait_queue_t link; + wait_queue_entry_t link; LASSERT(seq); init_waitqueue_entry(&link, current); diff --git a/drivers/staging/lustre/lustre/include/lustre_lib.h b/drivers/staging/lustre/lustre/include/lustre_lib.h index b04d613846ee..f24970da8323 100644 --- a/drivers/staging/lustre/lustre/include/lustre_lib.h +++ b/drivers/staging/lustre/lustre/include/lustre_lib.h @@ -201,7 +201,7 @@ struct l_wait_info { sigmask(SIGALRM)) /** - * wait_queue_t of Linux (version < 2.6.34) is a FIFO list for exclusively + * wait_queue_entry_t of Linux (version < 2.6.34) is a FIFO list for exclusively * waiting threads, which is not always desirable because all threads will * be waken up again and again, even user only needs a few of them to be * active most time. This is not good for performance because cache can @@ -228,7 +228,7 @@ struct l_wait_info { */ #define __l_wait_event(wq, condition, info, ret, l_add_wait) \ do { \ - wait_queue_t __wait; \ + wait_queue_entry_t __wait; \ long __timeout = info->lwi_timeout; \ sigset_t __blocked; \ int __allow_intr = info->lwi_allow_intr; \ diff --git a/drivers/staging/lustre/lustre/llite/lcommon_cl.c b/drivers/staging/lustre/lustre/llite/lcommon_cl.c index 8af611033e12..96515b839436 100644 --- a/drivers/staging/lustre/lustre/llite/lcommon_cl.c +++ b/drivers/staging/lustre/lustre/llite/lcommon_cl.c @@ -207,7 +207,7 @@ int cl_file_inode_init(struct inode *inode, struct lustre_md *md) static void cl_object_put_last(struct lu_env *env, struct cl_object *obj) { struct lu_object_header *header = obj->co_lu.lo_header; - wait_queue_t waiter; + wait_queue_entry_t waiter; if (unlikely(atomic_read(&header->loh_ref) != 1)) { struct lu_site *site = obj->co_lu.lo_dev->ld_site; diff --git a/drivers/staging/lustre/lustre/lov/lov_cl_internal.h b/drivers/staging/lustre/lustre/lov/lov_cl_internal.h index 391c632365ae..e889d3a7de9c 100644 --- a/drivers/staging/lustre/lustre/lov/lov_cl_internal.h +++ b/drivers/staging/lustre/lustre/lov/lov_cl_internal.h @@ -370,7 +370,7 @@ struct lov_thread_info { struct ost_lvb lti_lvb; struct cl_2queue lti_cl2q; struct cl_page_list lti_plist; - wait_queue_t lti_waiter; + wait_queue_entry_t lti_waiter; struct cl_attr lti_attr; }; diff --git a/drivers/staging/lustre/lustre/lov/lov_object.c b/drivers/staging/lustre/lustre/lov/lov_object.c index ab3ecfeeadc8..eddabbe31e5c 100644 --- a/drivers/staging/lustre/lustre/lov/lov_object.c +++ b/drivers/staging/lustre/lustre/lov/lov_object.c @@ -371,7 +371,7 @@ static void lov_subobject_kill(const struct lu_env *env, struct lov_object *lov, struct lov_layout_raid0 *r0; struct lu_site *site; struct lu_site_bkt_data *bkt; - wait_queue_t *waiter; + wait_queue_entry_t *waiter; r0 = &lov->u.raid0; LASSERT(r0->lo_sub[idx] == los); diff --git a/drivers/staging/lustre/lustre/obdclass/lu_object.c b/drivers/staging/lustre/lustre/obdclass/lu_object.c index abcf951208d2..76ae600ae2c8 100644 --- a/drivers/staging/lustre/lustre/obdclass/lu_object.c +++ b/drivers/staging/lustre/lustre/obdclass/lu_object.c @@ -556,7 +556,7 @@ EXPORT_SYMBOL(lu_object_print); static struct lu_object *htable_lookup(struct lu_site *s, struct cfs_hash_bd *bd, const struct lu_fid *f, - wait_queue_t *waiter, + wait_queue_entry_t *waiter, __u64 *version) { struct lu_site_bkt_data *bkt; @@ -670,7 +670,7 @@ static struct lu_object *lu_object_find_try(const struct lu_env *env, struct lu_device *dev, const struct lu_fid *f, const struct lu_object_conf *conf, - wait_queue_t *waiter) + wait_queue_entry_t *waiter) { struct lu_object *o; struct lu_object *shadow; @@ -750,7 +750,7 @@ struct lu_object *lu_object_find_at(const struct lu_env *env, { struct lu_site_bkt_data *bkt; struct lu_object *obj; - wait_queue_t wait; + wait_queue_entry_t wait; while (1) { obj = lu_object_find_try(env, dev, f, conf, &wait); diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 0d8f81591bed..3fdca2cdd8da 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -1279,6 +1279,18 @@ iscsit_get_immediate_data(struct iscsi_cmd *cmd, struct iscsi_scsi_req *hdr, */ if (dump_payload) goto after_immediate_data; + /* + * Check for underflow case where both EDTL and immediate data payload + * exceeds what is presented by CDB's TRANSFER LENGTH, and what has + * already been set in target_cmd_size_check() as se_cmd->data_length. + * + * For this special case, fail the command and dump the immediate data + * payload. + */ + if (cmd->first_burst_len > cmd->se_cmd.data_length) { + cmd->sense_reason = TCM_INVALID_CDB_FIELD; + goto after_immediate_data; + } immed_ret = iscsit_handle_immediate_data(cmd, hdr, cmd->first_burst_len); @@ -4423,8 +4435,11 @@ static void iscsit_logout_post_handler_closesession( * always sleep waiting for RX/TX thread shutdown to complete * within iscsit_close_connection(). */ - if (!conn->conn_transport->rdma_shutdown) + if (!conn->conn_transport->rdma_shutdown) { sleep = cmpxchg(&conn->tx_thread_active, true, false); + if (!sleep) + return; + } atomic_set(&conn->conn_logout_remove, 0); complete(&conn->conn_logout_comp); @@ -4440,8 +4455,11 @@ static void iscsit_logout_post_handler_samecid( { int sleep = 1; - if (!conn->conn_transport->rdma_shutdown) + if (!conn->conn_transport->rdma_shutdown) { sleep = cmpxchg(&conn->tx_thread_active, true, false); + if (!sleep) + return; + } atomic_set(&conn->conn_logout_remove, 0); complete(&conn->conn_logout_comp); diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index bb069ebe4aa6..c05d38016556 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -93,7 +93,7 @@ static int iblock_configure_device(struct se_device *dev) return -EINVAL; } - ib_dev->ibd_bio_set = bioset_create(IBLOCK_BIO_POOL_SIZE, 0); + ib_dev->ibd_bio_set = bioset_create(IBLOCK_BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); if (!ib_dev->ibd_bio_set) { pr_err("IBLOCK: Unable to create bioset\n"); goto out; @@ -296,8 +296,8 @@ static void iblock_bio_done(struct bio *bio) struct se_cmd *cmd = bio->bi_private; struct iblock_req *ibr = cmd->priv; - if (bio->bi_error) { - pr_err("bio error: %p, err: %d\n", bio, bio->bi_error); + if (bio->bi_status) { + pr_err("bio error: %p, err: %d\n", bio, bio->bi_status); /* * Bump the ib_bio_err_cnt and release bio. */ @@ -354,11 +354,11 @@ static void iblock_end_io_flush(struct bio *bio) { struct se_cmd *cmd = bio->bi_private; - if (bio->bi_error) - pr_err("IBLOCK: cache flush failed: %d\n", bio->bi_error); + if (bio->bi_status) + pr_err("IBLOCK: cache flush failed: %d\n", bio->bi_status); if (cmd) { - if (bio->bi_error) + if (bio->bi_status) target_complete_cmd(cmd, SAM_STAT_CHECK_CONDITION); else target_complete_cmd(cmd, SAM_STAT_GOOD); diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h index 9ab7090f7c83..0912de7c0cf8 100644 --- a/drivers/target/target_core_internal.h +++ b/drivers/target/target_core_internal.h @@ -136,7 +136,7 @@ int init_se_kmem_caches(void); void release_se_kmem_caches(void); u32 scsi_get_new_index(scsi_index_t); void transport_subsystem_check_init(void); -void transport_cmd_finish_abort(struct se_cmd *, int); +int transport_cmd_finish_abort(struct se_cmd *, int); unsigned char *transport_dump_cmd_direction(struct se_cmd *); void transport_dump_dev_state(struct se_device *, char *, int *); void transport_dump_dev_info(struct se_device *, struct se_lun *, diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index 3e4abb13f8ea..ceec0211e84e 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -55,7 +55,7 @@ static inline struct pscsi_dev_virt *PSCSI_DEV(struct se_device *dev) } static sense_reason_t pscsi_execute_cmd(struct se_cmd *cmd); -static void pscsi_req_done(struct request *, int); +static void pscsi_req_done(struct request *, blk_status_t); /* pscsi_attach_hba(): * @@ -992,8 +992,6 @@ pscsi_execute_cmd(struct se_cmd *cmd) goto fail; } - scsi_req_init(req); - if (sgl) { ret = pscsi_map_sg(cmd, sgl, sgl_nents, req); if (ret) @@ -1045,7 +1043,7 @@ static sector_t pscsi_get_blocks(struct se_device *dev) return 0; } -static void pscsi_req_done(struct request *req, int uptodate) +static void pscsi_req_done(struct request *req, blk_status_t status) { struct se_cmd *cmd = req->end_io_data; struct pscsi_plugin_task *pt = cmd->priv; diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c index dce1e1b47316..13f47bf4d16b 100644 --- a/drivers/target/target_core_tmr.c +++ b/drivers/target/target_core_tmr.c @@ -75,7 +75,7 @@ void core_tmr_release_req(struct se_tmr_req *tmr) kfree(tmr); } -static void core_tmr_handle_tas_abort(struct se_cmd *cmd, int tas) +static int core_tmr_handle_tas_abort(struct se_cmd *cmd, int tas) { unsigned long flags; bool remove = true, send_tas; @@ -91,7 +91,7 @@ static void core_tmr_handle_tas_abort(struct se_cmd *cmd, int tas) transport_send_task_abort(cmd); } - transport_cmd_finish_abort(cmd, remove); + return transport_cmd_finish_abort(cmd, remove); } static int target_check_cdb_and_preempt(struct list_head *list, @@ -184,8 +184,8 @@ void core_tmr_abort_task( cancel_work_sync(&se_cmd->work); transport_wait_for_tasks(se_cmd); - transport_cmd_finish_abort(se_cmd, true); - target_put_sess_cmd(se_cmd); + if (!transport_cmd_finish_abort(se_cmd, true)) + target_put_sess_cmd(se_cmd); printk("ABORT_TASK: Sending TMR_FUNCTION_COMPLETE for" " ref_tag: %llu\n", ref_tag); @@ -281,8 +281,8 @@ static void core_tmr_drain_tmr_list( cancel_work_sync(&cmd->work); transport_wait_for_tasks(cmd); - transport_cmd_finish_abort(cmd, 1); - target_put_sess_cmd(cmd); + if (!transport_cmd_finish_abort(cmd, 1)) + target_put_sess_cmd(cmd); } } @@ -380,8 +380,8 @@ static void core_tmr_drain_state_list( cancel_work_sync(&cmd->work); transport_wait_for_tasks(cmd); - core_tmr_handle_tas_abort(cmd, tas); - target_put_sess_cmd(cmd); + if (!core_tmr_handle_tas_abort(cmd, tas)) + target_put_sess_cmd(cmd); } } diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 6025935036c9..f1b3a46bdcaf 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -651,9 +651,10 @@ static void transport_lun_remove_cmd(struct se_cmd *cmd) percpu_ref_put(&lun->lun_ref); } -void transport_cmd_finish_abort(struct se_cmd *cmd, int remove) +int transport_cmd_finish_abort(struct se_cmd *cmd, int remove) { bool ack_kref = (cmd->se_cmd_flags & SCF_ACK_KREF); + int ret = 0; if (cmd->se_cmd_flags & SCF_SE_LUN_CMD) transport_lun_remove_cmd(cmd); @@ -665,9 +666,11 @@ void transport_cmd_finish_abort(struct se_cmd *cmd, int remove) cmd->se_tfo->aborted_task(cmd); if (transport_cmd_check_stop_to_fabric(cmd)) - return; + return 1; if (remove && ack_kref) - transport_put_cmd(cmd); + ret = transport_put_cmd(cmd); + + return ret; } static void target_complete_failure_work(struct work_struct *work) diff --git a/drivers/thermal/int340x_thermal/int3400_thermal.c b/drivers/thermal/int340x_thermal/int3400_thermal.c index 9413c4abf0b9..a9ec94ed7a42 100644 --- a/drivers/thermal/int340x_thermal/int3400_thermal.c +++ b/drivers/thermal/int340x_thermal/int3400_thermal.c @@ -23,7 +23,7 @@ enum int3400_thermal_uuid { INT3400_THERMAL_MAXIMUM_UUID, }; -static u8 *int3400_thermal_uuids[INT3400_THERMAL_MAXIMUM_UUID] = { +static char *int3400_thermal_uuids[INT3400_THERMAL_MAXIMUM_UUID] = { "42A441D6-AE6A-462b-A84B-4A8CE79027D3", "3A95C389-E4B8-4629-A526-C52C88626BAE", "97C68AE7-15FA-499c-B8C9-5DA81D606E0A", @@ -141,10 +141,10 @@ static int int3400_thermal_get_uuids(struct int3400_thermal_priv *priv) } for (j = 0; j < INT3400_THERMAL_MAXIMUM_UUID; j++) { - u8 uuid[16]; + guid_t guid; - acpi_str_to_uuid(int3400_thermal_uuids[j], uuid); - if (!strncmp(uuid, objb->buffer.pointer, 16)) { + guid_parse(int3400_thermal_uuids[j], &guid); + if (guid_equal((guid_t *)objb->buffer.pointer, &guid)) { priv->uuid_bitmap |= (1 << j); break; } diff --git a/drivers/tty/hvc/Kconfig b/drivers/tty/hvc/Kconfig index 574da15fe618..b8d5ea0ae26b 100644 --- a/drivers/tty/hvc/Kconfig +++ b/drivers/tty/hvc/Kconfig @@ -44,7 +44,7 @@ config HVC_RTAS config HVC_IUCV bool "z/VM IUCV Hypervisor console support (VM only)" - depends on S390 + depends on S390 && NET select HVC_DRIVER select IUCV default y diff --git a/drivers/tty/synclink_gt.c b/drivers/tty/synclink_gt.c index 31885f20fc15..cc047de72e2a 100644 --- a/drivers/tty/synclink_gt.c +++ b/drivers/tty/synclink_gt.c @@ -184,7 +184,7 @@ static void hdlcdev_exit(struct slgt_info *info); struct cond_wait { struct cond_wait *next; wait_queue_head_t q; - wait_queue_t wait; + wait_queue_entry_t wait; unsigned int data; }; static void init_cond_wait(struct cond_wait *w, unsigned int data); diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index 84a2cebfc712..fe851544d7fb 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -42,7 +42,7 @@ #define PCI_DEVICE_ID_INTEL_CNPLP 0x9dee #define PCI_DEVICE_ID_INTEL_CNPH 0xa36e -#define PCI_INTEL_BXT_DSM_UUID "732b85d5-b7a7-4a1b-9ba0-4bbd00ffd511" +#define PCI_INTEL_BXT_DSM_GUID "732b85d5-b7a7-4a1b-9ba0-4bbd00ffd511" #define PCI_INTEL_BXT_FUNC_PMU_PWR 4 #define PCI_INTEL_BXT_STATE_D0 0 #define PCI_INTEL_BXT_STATE_D3 3 @@ -51,14 +51,14 @@ * struct dwc3_pci - Driver private structure * @dwc3: child dwc3 platform_device * @pci: our link to PCI bus - * @uuid: _DSM UUID + * @guid: _DSM GUID * @has_dsm_for_pm: true for devices which need to run _DSM on runtime PM */ struct dwc3_pci { struct platform_device *dwc3; struct pci_dev *pci; - u8 uuid[16]; + guid_t guid; unsigned int has_dsm_for_pm:1; }; @@ -120,7 +120,7 @@ static int dwc3_pci_quirks(struct dwc3_pci *dwc) if (pdev->device == PCI_DEVICE_ID_INTEL_BXT || pdev->device == PCI_DEVICE_ID_INTEL_BXT_M) { - acpi_str_to_uuid(PCI_INTEL_BXT_DSM_UUID, dwc->uuid); + guid_parse(PCI_INTEL_BXT_DSM_GUID, &dwc->guid); dwc->has_dsm_for_pm = true; } @@ -292,7 +292,7 @@ static int dwc3_pci_dsm(struct dwc3_pci *dwc, int param) tmp.type = ACPI_TYPE_INTEGER; tmp.integer.value = param; - obj = acpi_evaluate_dsm(ACPI_HANDLE(&dwc->pci->dev), dwc->uuid, + obj = acpi_evaluate_dsm(ACPI_HANDLE(&dwc->pci->dev), &dwc->guid, 1, PCI_INTEL_BXT_FUNC_PMU_PWR, &argv4); if (!obj) { dev_err(&dwc->pci->dev, "failed to evaluate _DSM\n"); diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 1bcf971141c0..783e6687bf4a 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -216,13 +216,12 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) #ifdef CONFIG_ACPI static void xhci_pme_acpi_rtd3_enable(struct pci_dev *dev) { - static const u8 intel_dsm_uuid[] = { - 0xb7, 0x0c, 0x34, 0xac, 0x01, 0xe9, 0xbf, 0x45, - 0xb7, 0xe6, 0x2b, 0x34, 0xec, 0x93, 0x1e, 0x23, - }; + static const guid_t intel_dsm_guid = + GUID_INIT(0xac340cb7, 0xe901, 0x45bf, + 0xb7, 0xe6, 0x2b, 0x34, 0xec, 0x93, 0x1e, 0x23); union acpi_object *obj; - obj = acpi_evaluate_dsm(ACPI_HANDLE(&dev->dev), intel_dsm_uuid, 3, 1, + obj = acpi_evaluate_dsm(ACPI_HANDLE(&dev->dev), &intel_dsm_guid, 3, 1, NULL); ACPI_FREE(obj); } diff --git a/drivers/usb/misc/ucsi.c b/drivers/usb/misc/ucsi.c index 07397bddefa3..81251aaa20f9 100644 --- a/drivers/usb/misc/ucsi.c +++ b/drivers/usb/misc/ucsi.c @@ -55,13 +55,13 @@ struct ucsi { static int ucsi_acpi_cmd(struct ucsi *ucsi, struct ucsi_control *ctrl) { - uuid_le uuid = UUID_LE(0x6f8398c2, 0x7ca4, 0x11e4, - 0xad, 0x36, 0x63, 0x10, 0x42, 0xb5, 0x00, 0x8f); + guid_t guid = GUID_INIT(0x6f8398c2, 0x7ca4, 0x11e4, + 0xad, 0x36, 0x63, 0x10, 0x42, 0xb5, 0x00, 0x8f); union acpi_object *obj; ucsi->data->ctrl.raw_cmd = ctrl->raw_cmd; - obj = acpi_evaluate_dsm(ACPI_HANDLE(ucsi->dev), uuid.b, 1, 1, NULL); + obj = acpi_evaluate_dsm(ACPI_HANDLE(ucsi->dev), &guid, 1, 1, NULL); if (!obj) { dev_err(ucsi->dev, "%s: failed to evaluate _DSM\n", __func__); return -EIO; diff --git a/drivers/usb/typec/typec_wcove.c b/drivers/usb/typec/typec_wcove.c index d5a7b21fa3f1..c2ce25289027 100644 --- a/drivers/usb/typec/typec_wcove.c +++ b/drivers/usb/typec/typec_wcove.c @@ -105,8 +105,8 @@ enum wcove_typec_role { WCOVE_ROLE_DEVICE, }; -static uuid_le uuid = UUID_LE(0x482383f0, 0x2876, 0x4e49, - 0x86, 0x85, 0xdb, 0x66, 0x21, 0x1a, 0xf0, 0x37); +static guid_t guid = GUID_INIT(0x482383f0, 0x2876, 0x4e49, + 0x86, 0x85, 0xdb, 0x66, 0x21, 0x1a, 0xf0, 0x37); static int wcove_typec_func(struct wcove_typec *wcove, enum wcove_typec_func func, int param) @@ -118,7 +118,7 @@ static int wcove_typec_func(struct wcove_typec *wcove, tmp.type = ACPI_TYPE_INTEGER; tmp.integer.value = param; - obj = acpi_evaluate_dsm(ACPI_HANDLE(wcove->dev), uuid.b, 1, func, + obj = acpi_evaluate_dsm(ACPI_HANDLE(wcove->dev), &guid, 1, func, &argv4); if (!obj) { dev_err(wcove->dev, "%s: failed to evaluate _DSM\n", __func__); @@ -314,7 +314,7 @@ static int wcove_typec_probe(struct platform_device *pdev) if (ret) return ret; - if (!acpi_check_dsm(ACPI_HANDLE(&pdev->dev), uuid.b, 0, 0x1f)) { + if (!acpi_check_dsm(ACPI_HANDLE(&pdev->dev), &guid, 0, 0x1f)) { dev_err(&pdev->dev, "Missing _DSM functions\n"); return -ENODEV; } diff --git a/drivers/vfio/virqfd.c b/drivers/vfio/virqfd.c index 27c89cd5d70b..4797217e5e72 100644 --- a/drivers/vfio/virqfd.c +++ b/drivers/vfio/virqfd.c @@ -43,7 +43,7 @@ static void virqfd_deactivate(struct virqfd *virqfd) queue_work(vfio_irqfd_cleanup_wq, &virqfd->shutdown); } -static int virqfd_wakeup(wait_queue_t *wait, unsigned mode, int sync, void *key) +static int virqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct virqfd *virqfd = container_of(wait, struct virqfd, wait); unsigned long flags = (unsigned long)key; diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 042030e5a035..e4613a3c362d 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -165,7 +165,7 @@ static void vhost_poll_func(struct file *file, wait_queue_head_t *wqh, add_wait_queue(wqh, &poll->wait); } -static int vhost_poll_wakeup(wait_queue_t *wait, unsigned mode, int sync, +static int vhost_poll_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct vhost_poll *poll = container_of(wait, struct vhost_poll, wait); diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index f55671d53f28..f72095868b93 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -31,7 +31,7 @@ struct vhost_work { struct vhost_poll { poll_table table; wait_queue_head_t *wqh; - wait_queue_t wait; + wait_queue_entry_t wait; struct vhost_work work; unsigned long mask; struct vhost_dev *dev; diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c index c1ec8ee80924..9e35032351a0 100644 --- a/drivers/xen/manage.c +++ b/drivers/xen/manage.c @@ -190,6 +190,7 @@ static void do_poweroff(void) { switch (system_state) { case SYSTEM_BOOTING: + case SYSTEM_SCHEDULING: orderly_poweroff(true); break; case SYSTEM_RUNNING: diff --git a/drivers/xen/tmem.c b/drivers/xen/tmem.c index 4ac2ca8a7656..bf13d1ec51f3 100644 --- a/drivers/xen/tmem.c +++ b/drivers/xen/tmem.c @@ -233,12 +233,12 @@ static int tmem_cleancache_init_fs(size_t pagesize) return xen_tmem_new_pool(uuid_private, 0, pagesize); } -static int tmem_cleancache_init_shared_fs(char *uuid, size_t pagesize) +static int tmem_cleancache_init_shared_fs(uuid_t *uuid, size_t pagesize) { struct tmem_pool_uuid shared_uuid; - shared_uuid.uuid_lo = *(u64 *)uuid; - shared_uuid.uuid_hi = *(u64 *)(&uuid[8]); + shared_uuid.uuid_lo = *(u64 *)&uuid->b[0]; + shared_uuid.uuid_hi = *(u64 *)&uuid->b[8]; return xen_tmem_new_pool(shared_uuid, TMEM_POOL_SHARED, pagesize); } diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c index 3062cceb5c2a..782d4d05a53b 100644 --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@ -350,7 +350,7 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call) { struct sockaddr_rxrpc srx; struct afs_server *server; - struct uuid_v1 *r; + struct afs_uuid *r; unsigned loop; __be32 *b; int ret; @@ -380,7 +380,7 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call) } _debug("unmarshall UUID"); - call->request = kmalloc(sizeof(struct uuid_v1), GFP_KERNEL); + call->request = kmalloc(sizeof(struct afs_uuid), GFP_KERNEL); if (!call->request) return -ENOMEM; @@ -453,7 +453,7 @@ static int afs_deliver_cb_probe(struct afs_call *call) static void SRXAFSCB_ProbeUuid(struct work_struct *work) { struct afs_call *call = container_of(work, struct afs_call, work); - struct uuid_v1 *r = call->request; + struct afs_uuid *r = call->request; struct { __be32 match; @@ -476,7 +476,7 @@ static void SRXAFSCB_ProbeUuid(struct work_struct *work) */ static int afs_deliver_cb_probe_uuid(struct afs_call *call) { - struct uuid_v1 *r; + struct afs_uuid *r; unsigned loop; __be32 *b; int ret; @@ -502,15 +502,15 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call) } _debug("unmarshall UUID"); - call->request = kmalloc(sizeof(struct uuid_v1), GFP_KERNEL); + call->request = kmalloc(sizeof(struct afs_uuid), GFP_KERNEL); if (!call->request) return -ENOMEM; b = call->buffer; r = call->request; - r->time_low = b[0]; - r->time_mid = htons(ntohl(b[1])); - r->time_hi_and_version = htons(ntohl(b[2])); + r->time_low = ntohl(b[0]); + r->time_mid = ntohl(b[1]); + r->time_hi_and_version = ntohl(b[2]); r->clock_seq_hi_and_reserved = ntohl(b[3]); r->clock_seq_low = ntohl(b[4]); diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 393672997cc2..4e2556606623 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -410,6 +410,15 @@ struct afs_interface { unsigned mtu; /* MTU of interface */ }; +struct afs_uuid { + __be32 time_low; /* low part of timestamp */ + __be16 time_mid; /* mid part of timestamp */ + __be16 time_hi_and_version; /* high part of timestamp and version */ + __u8 clock_seq_hi_and_reserved; /* clock seq hi and variant */ + __u8 clock_seq_low; /* clock seq low */ + __u8 node[6]; /* spatially unique node ID (MAC addr) */ +}; + /*****************************************************************************/ /* * cache.c @@ -544,7 +553,7 @@ extern int afs_drop_inode(struct inode *); * main.c */ extern struct workqueue_struct *afs_wq; -extern struct uuid_v1 afs_uuid; +extern struct afs_uuid afs_uuid; /* * misc.c diff --git a/fs/afs/main.c b/fs/afs/main.c index 51d7d17bca57..9944770849da 100644 --- a/fs/afs/main.c +++ b/fs/afs/main.c @@ -31,7 +31,7 @@ static char *rootcell; module_param(rootcell, charp, 0); MODULE_PARM_DESC(rootcell, "root AFS cell name and VL server IP addr list"); -struct uuid_v1 afs_uuid; +struct afs_uuid afs_uuid; struct workqueue_struct *afs_wq; /* @@ -1541,7 +1541,7 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, ssize_t ret; /* enforce forwards compatibility on users */ - if (unlikely(iocb->aio_reserved1 || iocb->aio_reserved2)) { + if (unlikely(iocb->aio_reserved2)) { pr_debug("EINVAL: reserve field set\n"); return -EINVAL; } @@ -1568,6 +1568,7 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, req->common.ki_pos = iocb->aio_offset; req->common.ki_complete = aio_complete; req->common.ki_flags = iocb_flags(req->common.ki_filp); + req->common.ki_hint = file_write_hint(file); if (iocb->aio_flags & IOCB_FLAG_RESFD) { /* @@ -1586,6 +1587,18 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, req->common.ki_flags |= IOCB_EVENTFD; } + ret = kiocb_set_rw_flags(&req->common, iocb->aio_rw_flags); + if (unlikely(ret)) { + pr_debug("EINVAL: aio_rw_flags\n"); + goto out_put_req; + } + + if ((req->common.ki_flags & IOCB_NOWAIT) && + !(req->common.ki_flags & IOCB_DIRECT)) { + ret = -EOPNOTSUPP; + goto out_put_req; + } + ret = put_user(KIOCB_KEY, &user_iocb->aio_key); if (unlikely(ret)) { pr_debug("EFAULT: aio_key\n"); diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h index beef981aa54f..974f5346458a 100644 --- a/fs/autofs4/autofs_i.h +++ b/fs/autofs4/autofs_i.h @@ -83,7 +83,7 @@ struct autofs_info { struct autofs_wait_queue { wait_queue_head_t queue; struct autofs_wait_queue *next; - autofs_wqt_t wait_queue_token; + autofs_wqt_t wait_queue_entry_token; /* We use the following to see what we are waiting for */ struct qstr name; u32 dev; diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c index 734cbf8d9676..dd9f1bebb5a3 100644 --- a/fs/autofs4/dev-ioctl.c +++ b/fs/autofs4/dev-ioctl.c @@ -344,7 +344,7 @@ static int autofs_dev_ioctl_fail(struct file *fp, int status; token = (autofs_wqt_t) param->fail.token; - status = param->fail.status ? param->fail.status : -ENOENT; + status = param->fail.status < 0 ? param->fail.status : -ENOENT; return autofs4_wait_release(sbi, token, status); } diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c index 24a58bf9ca72..7071895b0678 100644 --- a/fs/autofs4/waitq.c +++ b/fs/autofs4/waitq.c @@ -104,7 +104,7 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi, size_t pktsz; pr_debug("wait id = 0x%08lx, name = %.*s, type=%d\n", - (unsigned long) wq->wait_queue_token, + (unsigned long) wq->wait_queue_entry_token, wq->name.len, wq->name.name, type); memset(&pkt, 0, sizeof(pkt)); /* For security reasons */ @@ -120,7 +120,7 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi, pktsz = sizeof(*mp); - mp->wait_queue_token = wq->wait_queue_token; + mp->wait_queue_entry_token = wq->wait_queue_entry_token; mp->len = wq->name.len; memcpy(mp->name, wq->name.name, wq->name.len); mp->name[wq->name.len] = '\0'; @@ -133,7 +133,7 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi, pktsz = sizeof(*ep); - ep->wait_queue_token = wq->wait_queue_token; + ep->wait_queue_entry_token = wq->wait_queue_entry_token; ep->len = wq->name.len; memcpy(ep->name, wq->name.name, wq->name.len); ep->name[wq->name.len] = '\0'; @@ -153,7 +153,7 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi, pktsz = sizeof(*packet); - packet->wait_queue_token = wq->wait_queue_token; + packet->wait_queue_entry_token = wq->wait_queue_entry_token; packet->len = wq->name.len; memcpy(packet->name, wq->name.name, wq->name.len); packet->name[wq->name.len] = '\0'; @@ -428,7 +428,7 @@ int autofs4_wait(struct autofs_sb_info *sbi, return -ENOMEM; } - wq->wait_queue_token = autofs4_next_wait_queue; + wq->wait_queue_entry_token = autofs4_next_wait_queue; if (++autofs4_next_wait_queue == 0) autofs4_next_wait_queue = 1; wq->next = sbi->queues; @@ -461,7 +461,7 @@ int autofs4_wait(struct autofs_sb_info *sbi, } pr_debug("new wait id = 0x%08lx, name = %.*s, nfy=%d\n", - (unsigned long) wq->wait_queue_token, wq->name.len, + (unsigned long) wq->wait_queue_entry_token, wq->name.len, wq->name.name, notify); /* @@ -471,7 +471,7 @@ int autofs4_wait(struct autofs_sb_info *sbi, } else { wq->wait_ctr++; pr_debug("existing wait id = 0x%08lx, name = %.*s, nfy=%d\n", - (unsigned long) wq->wait_queue_token, wq->name.len, + (unsigned long) wq->wait_queue_entry_token, wq->name.len, wq->name.name, notify); mutex_unlock(&sbi->wq_mutex); kfree(qstr.name); @@ -550,13 +550,13 @@ int autofs4_wait(struct autofs_sb_info *sbi, } -int autofs4_wait_release(struct autofs_sb_info *sbi, autofs_wqt_t wait_queue_token, int status) +int autofs4_wait_release(struct autofs_sb_info *sbi, autofs_wqt_t wait_queue_entry_token, int status) { struct autofs_wait_queue *wq, **wql; mutex_lock(&sbi->wq_mutex); for (wql = &sbi->queues; (wq = *wql) != NULL; wql = &wq->next) { - if (wq->wait_queue_token == wait_queue_token) + if (wq->wait_queue_entry_token == wait_queue_entry_token) break; } diff --git a/fs/block_dev.c b/fs/block_dev.c index 519599dddd36..a7df151f8aba 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -225,6 +225,7 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, bio_init(&bio, vecs, nr_pages); bio.bi_bdev = bdev; bio.bi_iter.bi_sector = pos >> 9; + bio.bi_write_hint = iocb->ki_hint; bio.bi_private = current; bio.bi_end_io = blkdev_bio_end_io_simple; @@ -262,8 +263,11 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, if (vecs != inline_vecs) kfree(vecs); - if (unlikely(bio.bi_error)) - return bio.bi_error; + if (unlikely(bio.bi_status)) + ret = blk_status_to_errno(bio.bi_status); + + bio_uninit(&bio); + return ret; } @@ -288,16 +292,18 @@ static void blkdev_bio_end_io(struct bio *bio) bool should_dirty = dio->should_dirty; if (dio->multi_bio && !atomic_dec_and_test(&dio->ref)) { - if (bio->bi_error && !dio->bio.bi_error) - dio->bio.bi_error = bio->bi_error; + if (bio->bi_status && !dio->bio.bi_status) + dio->bio.bi_status = bio->bi_status; } else { if (!dio->is_sync) { struct kiocb *iocb = dio->iocb; - ssize_t ret = dio->bio.bi_error; + ssize_t ret; - if (likely(!ret)) { + if (likely(!dio->bio.bi_status)) { ret = dio->size; iocb->ki_pos += ret; + } else { + ret = blk_status_to_errno(dio->bio.bi_status); } dio->iocb->ki_complete(iocb, ret, 0); @@ -334,7 +340,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) bool is_read = (iov_iter_rw(iter) == READ), is_sync; loff_t pos = iocb->ki_pos; blk_qc_t qc = BLK_QC_T_NONE; - int ret; + int ret = 0; if ((pos | iov_iter_alignment(iter)) & (bdev_logical_block_size(bdev) - 1)) @@ -358,12 +364,13 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) for (;;) { bio->bi_bdev = bdev; bio->bi_iter.bi_sector = pos >> 9; + bio->bi_write_hint = iocb->ki_hint; bio->bi_private = dio; bio->bi_end_io = blkdev_bio_end_io; ret = bio_iov_iter_get_pages(bio, iter); if (unlikely(ret)) { - bio->bi_error = ret; + bio->bi_status = BLK_STS_IOERR; bio_endio(bio); break; } @@ -412,7 +419,8 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) } __set_current_state(TASK_RUNNING); - ret = dio->bio.bi_error; + if (!ret) + ret = blk_status_to_errno(dio->bio.bi_status); if (likely(!ret)) ret = dio->size; @@ -436,7 +444,7 @@ blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter) static __init int blkdev_init(void) { - blkdev_dio_pool = bioset_create(4, offsetof(struct blkdev_dio, bio)); + blkdev_dio_pool = bioset_create(4, offsetof(struct blkdev_dio, bio), BIOSET_NEED_BVECS); if (!blkdev_dio_pool) return -ENOMEM; return 0; diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index b8622e4d1744..d87ac27a5f2b 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -310,7 +310,8 @@ struct btrfs_dio_private { * The original bio may be split to several sub-bios, this is * done during endio of sub-bios */ - int (*subio_endio)(struct inode *, struct btrfs_io_bio *, int); + blk_status_t (*subio_endio)(struct inode *, struct btrfs_io_bio *, + blk_status_t); }; /* diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c index ab14c2e635ca..4ded1c3f92b8 100644 --- a/fs/btrfs/check-integrity.c +++ b/fs/btrfs/check-integrity.c @@ -2129,7 +2129,7 @@ static void btrfsic_bio_end_io(struct bio *bp) /* mutex is not held! This is not save if IO is not yet completed * on umount */ iodone_w_error = 0; - if (bp->bi_error) + if (bp->bi_status) iodone_w_error = 1; BUG_ON(NULL == block); @@ -2143,7 +2143,7 @@ static void btrfsic_bio_end_io(struct bio *bp) if ((dev_state->state->print_mask & BTRFSIC_PRINT_MASK_END_IO_BIO_BH)) pr_info("bio_end_io(err=%d) for %c @%llu (%s/%llu/%d)\n", - bp->bi_error, + bp->bi_status, btrfsic_get_block_type(dev_state->state, block), block->logical_bytenr, dev_state->name, block->dev_bytenr, block->mirror_num); diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index 10e6b282d09d..a2fad39f79ba 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -155,7 +155,7 @@ static void end_compressed_bio_read(struct bio *bio) unsigned long index; int ret; - if (bio->bi_error) + if (bio->bi_status) cb->errors = 1; /* if there are more bios still pending for this compressed @@ -268,7 +268,7 @@ static void end_compressed_bio_write(struct bio *bio) struct page *page; unsigned long index; - if (bio->bi_error) + if (bio->bi_status) cb->errors = 1; /* if there are more bios still pending for this compressed @@ -287,7 +287,7 @@ static void end_compressed_bio_write(struct bio *bio) cb->start, cb->start + cb->len - 1, NULL, - bio->bi_error ? 0 : 1); + bio->bi_status ? 0 : 1); cb->compressed_pages[0]->mapping = NULL; end_compressed_writeback(inode, cb); @@ -320,7 +320,7 @@ out: * This also checksums the file bytes and gets things ready for * the end io hooks. */ -int btrfs_submit_compressed_write(struct inode *inode, u64 start, +blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start, unsigned long len, u64 disk_start, unsigned long compressed_len, struct page **compressed_pages, @@ -335,13 +335,13 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start, struct page *page; u64 first_byte = disk_start; struct block_device *bdev; - int ret; + blk_status_t ret; int skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM; WARN_ON(start & ((u64)PAGE_SIZE - 1)); cb = kmalloc(compressed_bio_size(fs_info, compressed_len), GFP_NOFS); if (!cb) - return -ENOMEM; + return BLK_STS_RESOURCE; refcount_set(&cb->pending_bios, 0); cb->errors = 0; cb->inode = inode; @@ -358,7 +358,7 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start, bio = compressed_bio_alloc(bdev, first_byte, GFP_NOFS); if (!bio) { kfree(cb); - return -ENOMEM; + return BLK_STS_RESOURCE; } bio_set_op_attrs(bio, REQ_OP_WRITE, 0); bio->bi_private = cb; @@ -368,17 +368,17 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start, /* create and submit bios for the compressed pages */ bytes_left = compressed_len; for (pg_index = 0; pg_index < cb->nr_pages; pg_index++) { + int submit = 0; + page = compressed_pages[pg_index]; page->mapping = inode->i_mapping; if (bio->bi_iter.bi_size) - ret = io_tree->ops->merge_bio_hook(page, 0, + submit = io_tree->ops->merge_bio_hook(page, 0, PAGE_SIZE, bio, 0); - else - ret = 0; page->mapping = NULL; - if (ret || bio_add_page(bio, page, PAGE_SIZE, 0) < + if (submit || bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) { bio_get(bio); @@ -400,7 +400,7 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start, ret = btrfs_map_bio(fs_info, bio, 0, 1); if (ret) { - bio->bi_error = ret; + bio->bi_status = ret; bio_endio(bio); } @@ -434,7 +434,7 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start, ret = btrfs_map_bio(fs_info, bio, 0, 1); if (ret) { - bio->bi_error = ret; + bio->bi_status = ret; bio_endio(bio); } @@ -569,7 +569,7 @@ next: * After the compressed pages are read, we copy the bytes into the * bio we were passed and then call the bio end_io calls */ -int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, +blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, int mirror_num, unsigned long bio_flags) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); @@ -586,7 +586,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, u64 em_len; u64 em_start; struct extent_map *em; - int ret = -ENOMEM; + blk_status_t ret = BLK_STS_RESOURCE; int faili = 0; u32 *sums; @@ -600,7 +600,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, PAGE_SIZE); read_unlock(&em_tree->lock); if (!em) - return -EIO; + return BLK_STS_IOERR; compressed_len = em->block_len; cb = kmalloc(compressed_bio_size(fs_info, compressed_len), GFP_NOFS); @@ -638,7 +638,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, __GFP_HIGHMEM); if (!cb->compressed_pages[pg_index]) { faili = pg_index - 1; - ret = -ENOMEM; + ret = BLK_STS_RESOURCE; goto fail2; } } @@ -659,19 +659,19 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, refcount_set(&cb->pending_bios, 1); for (pg_index = 0; pg_index < nr_pages; pg_index++) { + int submit = 0; + page = cb->compressed_pages[pg_index]; page->mapping = inode->i_mapping; page->index = em_start >> PAGE_SHIFT; if (comp_bio->bi_iter.bi_size) - ret = tree->ops->merge_bio_hook(page, 0, + submit = tree->ops->merge_bio_hook(page, 0, PAGE_SIZE, comp_bio, 0); - else - ret = 0; page->mapping = NULL; - if (ret || bio_add_page(comp_bio, page, PAGE_SIZE, 0) < + if (submit || bio_add_page(comp_bio, page, PAGE_SIZE, 0) < PAGE_SIZE) { bio_get(comp_bio); @@ -697,7 +697,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, ret = btrfs_map_bio(fs_info, comp_bio, mirror_num, 0); if (ret) { - comp_bio->bi_error = ret; + comp_bio->bi_status = ret; bio_endio(comp_bio); } @@ -726,7 +726,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, ret = btrfs_map_bio(fs_info, comp_bio, mirror_num, 0); if (ret) { - comp_bio->bi_error = ret; + comp_bio->bi_status = ret; bio_endio(comp_bio); } diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h index 39ec43ab8df1..680d4265d601 100644 --- a/fs/btrfs/compression.h +++ b/fs/btrfs/compression.h @@ -48,12 +48,12 @@ int btrfs_decompress_buf2page(const char *buf, unsigned long buf_start, unsigned long total_out, u64 disk_start, struct bio *bio); -int btrfs_submit_compressed_write(struct inode *inode, u64 start, +blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start, unsigned long len, u64 disk_start, unsigned long compressed_len, struct page **compressed_pages, unsigned long nr_pages); -int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, +blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, int mirror_num, unsigned long bio_flags); enum btrfs_compression_type { diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 4f8f75d9e839..a0d0c79d95ed 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3078,8 +3078,8 @@ int btrfs_find_name_in_ext_backref(struct btrfs_path *path, struct btrfs_dio_private; int btrfs_del_csums(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 bytenr, u64 len); -int btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u32 *dst); -int btrfs_lookup_bio_sums_dio(struct inode *inode, struct bio *bio, +blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u32 *dst); +blk_status_t btrfs_lookup_bio_sums_dio(struct inode *inode, struct bio *bio, u64 logical_offset); int btrfs_insert_file_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, @@ -3094,7 +3094,7 @@ int btrfs_lookup_file_extent(struct btrfs_trans_handle *trans, int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_ordered_sum *sums); -int btrfs_csum_one_bio(struct inode *inode, struct bio *bio, +blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio, u64 file_start, int contig); int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end, struct list_head *list, int search_commit); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 5f678dcb20e6..6036d15b47b8 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -87,7 +87,7 @@ struct btrfs_end_io_wq { bio_end_io_t *end_io; void *private; struct btrfs_fs_info *info; - int error; + blk_status_t status; enum btrfs_wq_endio_type metadata; struct list_head list; struct btrfs_work work; @@ -131,7 +131,7 @@ struct async_submit_bio { */ u64 bio_offset; struct btrfs_work work; - int error; + blk_status_t status; }; /* @@ -799,7 +799,7 @@ static void end_workqueue_bio(struct bio *bio) btrfs_work_func_t func; fs_info = end_io_wq->info; - end_io_wq->error = bio->bi_error; + end_io_wq->status = bio->bi_status; if (bio_op(bio) == REQ_OP_WRITE) { if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA) { @@ -836,19 +836,19 @@ static void end_workqueue_bio(struct bio *bio) btrfs_queue_work(wq, &end_io_wq->work); } -int btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio, +blk_status_t btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio, enum btrfs_wq_endio_type metadata) { struct btrfs_end_io_wq *end_io_wq; end_io_wq = kmem_cache_alloc(btrfs_end_io_wq_cache, GFP_NOFS); if (!end_io_wq) - return -ENOMEM; + return BLK_STS_RESOURCE; end_io_wq->private = bio->bi_private; end_io_wq->end_io = bio->bi_end_io; end_io_wq->info = info; - end_io_wq->error = 0; + end_io_wq->status = 0; end_io_wq->bio = bio; end_io_wq->metadata = metadata; @@ -868,14 +868,14 @@ unsigned long btrfs_async_submit_limit(struct btrfs_fs_info *info) static void run_one_async_start(struct btrfs_work *work) { struct async_submit_bio *async; - int ret; + blk_status_t ret; async = container_of(work, struct async_submit_bio, work); ret = async->submit_bio_start(async->inode, async->bio, async->mirror_num, async->bio_flags, async->bio_offset); if (ret) - async->error = ret; + async->status = ret; } static void run_one_async_done(struct btrfs_work *work) @@ -898,8 +898,8 @@ static void run_one_async_done(struct btrfs_work *work) wake_up(&fs_info->async_submit_wait); /* If an error occurred we just want to clean up the bio and move on */ - if (async->error) { - async->bio->bi_error = async->error; + if (async->status) { + async->bio->bi_status = async->status; bio_endio(async->bio); return; } @@ -916,18 +916,17 @@ static void run_one_async_free(struct btrfs_work *work) kfree(async); } -int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode, - struct bio *bio, int mirror_num, - unsigned long bio_flags, - u64 bio_offset, - extent_submit_bio_hook_t *submit_bio_start, - extent_submit_bio_hook_t *submit_bio_done) +blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, + struct inode *inode, struct bio *bio, int mirror_num, + unsigned long bio_flags, u64 bio_offset, + extent_submit_bio_hook_t *submit_bio_start, + extent_submit_bio_hook_t *submit_bio_done) { struct async_submit_bio *async; async = kmalloc(sizeof(*async), GFP_NOFS); if (!async) - return -ENOMEM; + return BLK_STS_RESOURCE; async->inode = inode; async->bio = bio; @@ -941,7 +940,7 @@ int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode, async->bio_flags = bio_flags; async->bio_offset = bio_offset; - async->error = 0; + async->status = 0; atomic_inc(&fs_info->nr_async_submits); @@ -959,7 +958,7 @@ int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode, return 0; } -static int btree_csum_one_bio(struct bio *bio) +static blk_status_t btree_csum_one_bio(struct bio *bio) { struct bio_vec *bvec; struct btrfs_root *root; @@ -972,12 +971,12 @@ static int btree_csum_one_bio(struct bio *bio) break; } - return ret; + return errno_to_blk_status(ret); } -static int __btree_submit_bio_start(struct inode *inode, struct bio *bio, - int mirror_num, unsigned long bio_flags, - u64 bio_offset) +static blk_status_t __btree_submit_bio_start(struct inode *inode, + struct bio *bio, int mirror_num, unsigned long bio_flags, + u64 bio_offset) { /* * when we're called for a write, we're already in the async @@ -986,11 +985,11 @@ static int __btree_submit_bio_start(struct inode *inode, struct bio *bio, return btree_csum_one_bio(bio); } -static int __btree_submit_bio_done(struct inode *inode, struct bio *bio, - int mirror_num, unsigned long bio_flags, - u64 bio_offset) +static blk_status_t __btree_submit_bio_done(struct inode *inode, + struct bio *bio, int mirror_num, unsigned long bio_flags, + u64 bio_offset) { - int ret; + blk_status_t ret; /* * when we're called for a write, we're already in the async @@ -998,7 +997,7 @@ static int __btree_submit_bio_done(struct inode *inode, struct bio *bio, */ ret = btrfs_map_bio(btrfs_sb(inode->i_sb), bio, mirror_num, 1); if (ret) { - bio->bi_error = ret; + bio->bi_status = ret; bio_endio(bio); } return ret; @@ -1015,13 +1014,13 @@ static int check_async_write(unsigned long bio_flags) return 1; } -static int btree_submit_bio_hook(struct inode *inode, struct bio *bio, +static blk_status_t btree_submit_bio_hook(struct inode *inode, struct bio *bio, int mirror_num, unsigned long bio_flags, u64 bio_offset) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); int async = check_async_write(bio_flags); - int ret; + blk_status_t ret; if (bio_op(bio) != REQ_OP_WRITE) { /* @@ -1054,7 +1053,7 @@ static int btree_submit_bio_hook(struct inode *inode, struct bio *bio, return 0; out_w_error: - bio->bi_error = ret; + bio->bi_status = ret; bio_endio(bio); return ret; } @@ -1820,7 +1819,7 @@ static void end_workqueue_fn(struct btrfs_work *work) end_io_wq = container_of(work, struct btrfs_end_io_wq, work); bio = end_io_wq->bio; - bio->bi_error = end_io_wq->error; + bio->bi_status = end_io_wq->status; bio->bi_private = end_io_wq->private; bio->bi_end_io = end_io_wq->end_io; kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq); @@ -3497,11 +3496,11 @@ static void btrfs_end_empty_barrier(struct bio *bio) * any device where the flush fails with eopnotsupp are flagged as not-barrier * capable */ -static int write_dev_flush(struct btrfs_device *device, int wait) +static blk_status_t write_dev_flush(struct btrfs_device *device, int wait) { struct request_queue *q = bdev_get_queue(device->bdev); struct bio *bio; - int ret = 0; + blk_status_t ret = 0; if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags)) return 0; @@ -3513,8 +3512,8 @@ static int write_dev_flush(struct btrfs_device *device, int wait) wait_for_completion(&device->flush_wait); - if (bio->bi_error) { - ret = bio->bi_error; + if (bio->bi_status) { + ret = bio->bi_status; btrfs_dev_stat_inc_and_print(device, BTRFS_DEV_STAT_FLUSH_ERRS); } @@ -3533,7 +3532,7 @@ static int write_dev_flush(struct btrfs_device *device, int wait) device->flush_bio = NULL; bio = btrfs_io_bio_alloc(GFP_NOFS, 0); if (!bio) - return -ENOMEM; + return BLK_STS_RESOURCE; bio->bi_end_io = btrfs_end_empty_barrier; bio->bi_bdev = device->bdev; @@ -3558,7 +3557,7 @@ static int barrier_all_devices(struct btrfs_fs_info *info) struct btrfs_device *dev; int errors_send = 0; int errors_wait = 0; - int ret; + blk_status_t ret; /* send down all the barriers */ head = &info->fs_devices->devices; diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index 21f1ceb85b76..c581927555f3 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -118,13 +118,13 @@ int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid, int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid); u32 btrfs_csum_data(const char *data, u32 seed, size_t len); void btrfs_csum_final(u32 crc, u8 *result); -int btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio, +blk_status_t btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio, enum btrfs_wq_endio_type metadata); -int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode, - struct bio *bio, int mirror_num, - unsigned long bio_flags, u64 bio_offset, - extent_submit_bio_hook_t *submit_bio_start, - extent_submit_bio_hook_t *submit_bio_done); +blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, + struct inode *inode, struct bio *bio, int mirror_num, + unsigned long bio_flags, u64 bio_offset, + extent_submit_bio_hook_t *submit_bio_start, + extent_submit_bio_hook_t *submit_bio_done); unsigned long btrfs_async_submit_limit(struct btrfs_fs_info *info); int btrfs_write_tree_block(struct extent_buffer *buf); int btrfs_wait_tree_block_writeback(struct extent_buffer *buf); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index d3619e010005..d1cd60140817 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -174,7 +174,8 @@ int __init extent_io_init(void) goto free_state_cache; btrfs_bioset = bioset_create(BIO_POOL_SIZE, - offsetof(struct btrfs_io_bio, bio)); + offsetof(struct btrfs_io_bio, bio), + BIOSET_NEED_BVECS); if (!btrfs_bioset) goto free_buffer_cache; @@ -2399,6 +2400,7 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset, struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree; struct bio *bio; int read_mode = 0; + blk_status_t status; int ret; BUG_ON(bio_op(failed_bio) == REQ_OP_WRITE); @@ -2431,11 +2433,12 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset, "Repair Read Error: submitting new read[%#x] to this_mirror=%d, in_validation=%d", read_mode, failrec->this_mirror, failrec->in_validation); - ret = tree->ops->submit_bio_hook(inode, bio, failrec->this_mirror, + status = tree->ops->submit_bio_hook(inode, bio, failrec->this_mirror, failrec->bio_flags, 0); - if (ret) { + if (status) { free_io_failure(BTRFS_I(inode), failrec); bio_put(bio); + ret = blk_status_to_errno(status); } return ret; @@ -2474,6 +2477,7 @@ void end_extent_writepage(struct page *page, int err, u64 start, u64 end) */ static void end_bio_extent_writepage(struct bio *bio) { + int error = blk_status_to_errno(bio->bi_status); struct bio_vec *bvec; u64 start; u64 end; @@ -2503,7 +2507,7 @@ static void end_bio_extent_writepage(struct bio *bio) start = page_offset(page); end = start + bvec->bv_offset + bvec->bv_len - 1; - end_extent_writepage(page, bio->bi_error, start, end); + end_extent_writepage(page, error, start, end); end_page_writeback(page); } @@ -2536,7 +2540,7 @@ endio_readpage_release_extent(struct extent_io_tree *tree, u64 start, u64 len, static void end_bio_extent_readpage(struct bio *bio) { struct bio_vec *bvec; - int uptodate = !bio->bi_error; + int uptodate = !bio->bi_status; struct btrfs_io_bio *io_bio = btrfs_io_bio(bio); struct extent_io_tree *tree; u64 offset = 0; @@ -2556,7 +2560,7 @@ static void end_bio_extent_readpage(struct bio *bio) btrfs_debug(fs_info, "end_bio_extent_readpage: bi_sector=%llu, err=%d, mirror=%u", - (u64)bio->bi_iter.bi_sector, bio->bi_error, + (u64)bio->bi_iter.bi_sector, bio->bi_status, io_bio->mirror_num); tree = &BTRFS_I(inode)->io_tree; @@ -2615,7 +2619,7 @@ static void end_bio_extent_readpage(struct bio *bio) ret = bio_readpage_error(bio, offset, page, start, end, mirror); if (ret == 0) { - uptodate = !bio->bi_error; + uptodate = !bio->bi_status; offset += len; continue; } @@ -2673,7 +2677,7 @@ readpage_ok: endio_readpage_release_extent(tree, extent_start, extent_len, uptodate); if (io_bio->end_io) - io_bio->end_io(io_bio, bio->bi_error); + io_bio->end_io(io_bio, blk_status_to_errno(bio->bi_status)); bio_put(bio); } @@ -2743,7 +2747,7 @@ struct bio *btrfs_io_bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs) static int __must_check submit_one_bio(struct bio *bio, int mirror_num, unsigned long bio_flags) { - int ret = 0; + blk_status_t ret = 0; struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1; struct page *page = bvec->bv_page; struct extent_io_tree *tree = bio->bi_private; @@ -2761,7 +2765,7 @@ static int __must_check submit_one_bio(struct bio *bio, int mirror_num, btrfsic_submit_bio(bio); bio_put(bio); - return ret; + return blk_status_to_errno(ret); } static int merge_bio(struct extent_io_tree *tree, struct page *page, @@ -2826,6 +2830,7 @@ static int submit_extent_page(int op, int op_flags, struct extent_io_tree *tree, bio_add_page(bio, page, page_size, offset); bio->bi_end_io = end_io_func; bio->bi_private = tree; + bio->bi_write_hint = page->mapping->host->i_write_hint; bio_set_op_attrs(bio, op, op_flags); if (wbc) { wbc_init_bio(wbc, bio); @@ -3707,7 +3712,7 @@ static void end_bio_extent_buffer_writepage(struct bio *bio) BUG_ON(!eb); done = atomic_dec_and_test(&eb->io_pages); - if (bio->bi_error || + if (bio->bi_status || test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags)) { ClearPageUptodate(page); set_btree_ioerr(page); diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 1eafa2f0ede3..487ca0207cb6 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -92,9 +92,9 @@ struct btrfs_inode; struct btrfs_io_bio; struct io_failure_record; -typedef int (extent_submit_bio_hook_t)(struct inode *inode, struct bio *bio, - int mirror_num, unsigned long bio_flags, - u64 bio_offset); +typedef blk_status_t (extent_submit_bio_hook_t)(struct inode *inode, + struct bio *bio, int mirror_num, unsigned long bio_flags, + u64 bio_offset); struct extent_io_ops { /* * The following callbacks must be allways defined, the function diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 64fcb31d7163..5b1c7090e546 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -160,7 +160,7 @@ static void btrfs_io_bio_endio_readpage(struct btrfs_io_bio *bio, int err) kfree(bio->csum_allocated); } -static int __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, +static blk_status_t __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u64 logical_offset, u32 *dst, int dio) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); @@ -182,7 +182,7 @@ static int __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, path = btrfs_alloc_path(); if (!path) - return -ENOMEM; + return BLK_STS_RESOURCE; nblocks = bio->bi_iter.bi_size >> inode->i_sb->s_blocksize_bits; if (!dst) { @@ -191,7 +191,7 @@ static int __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, csum_size, GFP_NOFS); if (!btrfs_bio->csum_allocated) { btrfs_free_path(path); - return -ENOMEM; + return BLK_STS_RESOURCE; } btrfs_bio->csum = btrfs_bio->csum_allocated; btrfs_bio->end_io = btrfs_io_bio_endio_readpage; @@ -303,12 +303,12 @@ next: return 0; } -int btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u32 *dst) +blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u32 *dst) { return __btrfs_lookup_bio_sums(inode, bio, 0, dst, 0); } -int btrfs_lookup_bio_sums_dio(struct inode *inode, struct bio *bio, u64 offset) +blk_status_t btrfs_lookup_bio_sums_dio(struct inode *inode, struct bio *bio, u64 offset) { return __btrfs_lookup_bio_sums(inode, bio, offset, NULL, 1); } @@ -433,7 +433,7 @@ fail: return ret; } -int btrfs_csum_one_bio(struct inode *inode, struct bio *bio, +blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio, u64 file_start, int contig) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); @@ -452,7 +452,7 @@ int btrfs_csum_one_bio(struct inode *inode, struct bio *bio, sums = kzalloc(btrfs_ordered_sum_size(fs_info, bio->bi_iter.bi_size), GFP_NOFS); if (!sums) - return -ENOMEM; + return BLK_STS_RESOURCE; sums->len = bio->bi_iter.bi_size; INIT_LIST_HEAD(&sums->list); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index da1096eb1a40..59e2dccdf75b 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1875,12 +1875,29 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, ssize_t num_written = 0; bool sync = (file->f_flags & O_DSYNC) || IS_SYNC(file->f_mapping->host); ssize_t err; - loff_t pos; - size_t count; + loff_t pos = iocb->ki_pos; + size_t count = iov_iter_count(from); loff_t oldsize; int clean_page = 0; - inode_lock(inode); + if ((iocb->ki_flags & IOCB_NOWAIT) && + (iocb->ki_flags & IOCB_DIRECT)) { + /* Don't sleep on inode rwsem */ + if (!inode_trylock(inode)) + return -EAGAIN; + /* + * We will allocate space in case nodatacow is not set, + * so bail + */ + if (!(BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | + BTRFS_INODE_PREALLOC)) || + check_can_nocow(BTRFS_I(inode), pos, &count) <= 0) { + inode_unlock(inode); + return -EAGAIN; + } + } else + inode_lock(inode); + err = generic_write_checks(iocb, from); if (err <= 0) { inode_unlock(inode); @@ -1914,8 +1931,6 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, */ update_time_for_write(inode); - pos = iocb->ki_pos; - count = iov_iter_count(from); start_pos = round_down(pos, fs_info->sectorsize); oldsize = i_size_read(inode); if (start_pos > oldsize) { @@ -3071,13 +3086,19 @@ out: return offset; } +static int btrfs_file_open(struct inode *inode, struct file *filp) +{ + filp->f_mode |= FMODE_AIO_NOWAIT; + return generic_file_open(inode, filp); +} + const struct file_operations btrfs_file_operations = { .llseek = btrfs_file_llseek, .read_iter = generic_file_read_iter, .splice_read = generic_file_splice_read, .write_iter = btrfs_file_write_iter, .mmap = btrfs_file_mmap, - .open = generic_file_open, + .open = btrfs_file_open, .release = btrfs_release_file, .fsync = btrfs_sync_file, .fallocate = btrfs_fallocate, diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index ef3c98c527c1..556c93060606 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -842,13 +842,12 @@ retry: NULL, EXTENT_LOCKED | EXTENT_DELALLOC, PAGE_UNLOCK | PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK); - ret = btrfs_submit_compressed_write(inode, + if (btrfs_submit_compressed_write(inode, async_extent->start, async_extent->ram_size, ins.objectid, ins.offset, async_extent->pages, - async_extent->nr_pages); - if (ret) { + async_extent->nr_pages)) { struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree; struct page *p = async_extent->pages[0]; const u64 start = async_extent->start; @@ -1901,11 +1900,11 @@ int btrfs_merge_bio_hook(struct page *page, unsigned long offset, * At IO completion time the cums attached on the ordered extent record * are inserted into the btree */ -static int __btrfs_submit_bio_start(struct inode *inode, struct bio *bio, - int mirror_num, unsigned long bio_flags, - u64 bio_offset) +static blk_status_t __btrfs_submit_bio_start(struct inode *inode, + struct bio *bio, int mirror_num, unsigned long bio_flags, + u64 bio_offset) { - int ret = 0; + blk_status_t ret = 0; ret = btrfs_csum_one_bio(inode, bio, 0, 0); BUG_ON(ret); /* -ENOMEM */ @@ -1920,16 +1919,16 @@ static int __btrfs_submit_bio_start(struct inode *inode, struct bio *bio, * At IO completion time the cums attached on the ordered extent record * are inserted into the btree */ -static int __btrfs_submit_bio_done(struct inode *inode, struct bio *bio, - int mirror_num, unsigned long bio_flags, - u64 bio_offset) +static blk_status_t __btrfs_submit_bio_done(struct inode *inode, + struct bio *bio, int mirror_num, unsigned long bio_flags, + u64 bio_offset) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - int ret; + blk_status_t ret; ret = btrfs_map_bio(fs_info, bio, mirror_num, 1); if (ret) { - bio->bi_error = ret; + bio->bi_status = ret; bio_endio(bio); } return ret; @@ -1939,14 +1938,14 @@ static int __btrfs_submit_bio_done(struct inode *inode, struct bio *bio, * extent_io.c submission hook. This does the right thing for csum calculation * on write, or reading the csums from the tree before a read */ -static int btrfs_submit_bio_hook(struct inode *inode, struct bio *bio, +static blk_status_t btrfs_submit_bio_hook(struct inode *inode, struct bio *bio, int mirror_num, unsigned long bio_flags, u64 bio_offset) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_root *root = BTRFS_I(inode)->root; enum btrfs_wq_endio_type metadata = BTRFS_WQ_ENDIO_DATA; - int ret = 0; + blk_status_t ret = 0; int skip_sum; int async = !atomic_read(&BTRFS_I(inode)->sync_writers); @@ -1991,8 +1990,8 @@ mapit: ret = btrfs_map_bio(fs_info, bio, mirror_num, 0); out: - if (ret < 0) { - bio->bi_error = ret; + if (ret) { + bio->bi_status = ret; bio_endio(bio); } return ret; @@ -8037,7 +8036,7 @@ static void btrfs_retry_endio_nocsum(struct bio *bio) struct bio_vec *bvec; int i; - if (bio->bi_error) + if (bio->bi_status) goto end; ASSERT(bio->bi_vcnt == 1); @@ -8116,7 +8115,7 @@ static void btrfs_retry_endio(struct bio *bio) int ret; int i; - if (bio->bi_error) + if (bio->bi_status) goto end; uptodate = 1; @@ -8141,8 +8140,8 @@ end: bio_put(bio); } -static int __btrfs_subio_endio_read(struct inode *inode, - struct btrfs_io_bio *io_bio, int err) +static blk_status_t __btrfs_subio_endio_read(struct inode *inode, + struct btrfs_io_bio *io_bio, blk_status_t err) { struct btrfs_fs_info *fs_info; struct bio_vec *bvec; @@ -8184,7 +8183,7 @@ try_again: io_bio->mirror_num, btrfs_retry_endio, &done); if (ret) { - err = ret; + err = errno_to_blk_status(ret); goto next; } @@ -8211,8 +8210,8 @@ next: return err; } -static int btrfs_subio_endio_read(struct inode *inode, - struct btrfs_io_bio *io_bio, int err) +static blk_status_t btrfs_subio_endio_read(struct inode *inode, + struct btrfs_io_bio *io_bio, blk_status_t err) { bool skip_csum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM; @@ -8232,7 +8231,7 @@ static void btrfs_endio_direct_read(struct bio *bio) struct inode *inode = dip->inode; struct bio *dio_bio; struct btrfs_io_bio *io_bio = btrfs_io_bio(bio); - int err = bio->bi_error; + blk_status_t err = bio->bi_status; if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED) err = btrfs_subio_endio_read(inode, io_bio, err); @@ -8243,11 +8242,11 @@ static void btrfs_endio_direct_read(struct bio *bio) kfree(dip); - dio_bio->bi_error = bio->bi_error; - dio_end_io(dio_bio, bio->bi_error); + dio_bio->bi_status = bio->bi_status; + dio_end_io(dio_bio); if (io_bio->end_io) - io_bio->end_io(io_bio, err); + io_bio->end_io(io_bio, blk_status_to_errno(err)); bio_put(bio); } @@ -8299,20 +8298,20 @@ static void btrfs_endio_direct_write(struct bio *bio) struct bio *dio_bio = dip->dio_bio; __endio_write_update_ordered(dip->inode, dip->logical_offset, - dip->bytes, !bio->bi_error); + dip->bytes, !bio->bi_status); kfree(dip); - dio_bio->bi_error = bio->bi_error; - dio_end_io(dio_bio, bio->bi_error); + dio_bio->bi_status = bio->bi_status; + dio_end_io(dio_bio); bio_put(bio); } -static int __btrfs_submit_bio_start_direct_io(struct inode *inode, +static blk_status_t __btrfs_submit_bio_start_direct_io(struct inode *inode, struct bio *bio, int mirror_num, unsigned long bio_flags, u64 offset) { - int ret; + blk_status_t ret; ret = btrfs_csum_one_bio(inode, bio, offset, 1); BUG_ON(ret); /* -ENOMEM */ return 0; @@ -8321,7 +8320,7 @@ static int __btrfs_submit_bio_start_direct_io(struct inode *inode, static void btrfs_end_dio_bio(struct bio *bio) { struct btrfs_dio_private *dip = bio->bi_private; - int err = bio->bi_error; + blk_status_t err = bio->bi_status; if (err) btrfs_warn(BTRFS_I(dip->inode)->root->fs_info, @@ -8351,7 +8350,7 @@ static void btrfs_end_dio_bio(struct bio *bio) if (dip->errors) { bio_io_error(dip->orig_bio); } else { - dip->dio_bio->bi_error = 0; + dip->dio_bio->bi_status = 0; bio_endio(dip->orig_bio); } out: @@ -8368,14 +8367,14 @@ static struct bio *btrfs_dio_bio_alloc(struct block_device *bdev, return bio; } -static inline int btrfs_lookup_and_bind_dio_csum(struct inode *inode, +static inline blk_status_t btrfs_lookup_and_bind_dio_csum(struct inode *inode, struct btrfs_dio_private *dip, struct bio *bio, u64 file_offset) { struct btrfs_io_bio *io_bio = btrfs_io_bio(bio); struct btrfs_io_bio *orig_io_bio = btrfs_io_bio(dip->orig_bio); - int ret; + blk_status_t ret; /* * We load all the csum data we need when we submit @@ -8406,7 +8405,7 @@ static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode, struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_dio_private *dip = bio->bi_private; bool write = bio_op(bio) == REQ_OP_WRITE; - int ret; + blk_status_t ret; if (async_submit) async_submit = !atomic_read(&BTRFS_I(inode)->sync_writers); @@ -8649,7 +8648,7 @@ free_ordered: * callbacks - they require an allocated dip and a clone of dio_bio. */ if (io_bio && dip) { - io_bio->bi_error = -EIO; + io_bio->bi_status = BLK_STS_IOERR; bio_endio(io_bio); /* * The end io callbacks free our dip, do the final put on io_bio @@ -8668,12 +8667,12 @@ free_ordered: unlock_extent(&BTRFS_I(inode)->io_tree, file_offset, file_offset + dio_bio->bi_iter.bi_size - 1); - dio_bio->bi_error = -EIO; + dio_bio->bi_status = BLK_STS_IOERR; /* * Releases and cleans up our dio_bio, no need to bio_put() * nor bio_endio()/bio_io_error() against dio_bio. */ - dio_end_io(dio_bio, ret); + dio_end_io(dio_bio); } if (io_bio) bio_put(io_bio); @@ -8755,6 +8754,9 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) dio_data.overwrite = 1; inode_unlock(inode); relock = true; + } else if (iocb->ki_flags & IOCB_NOWAIT) { + ret = -EAGAIN; + goto out; } ret = btrfs_delalloc_reserve_space(inode, offset, count); if (ret) diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index d8ea0eb76325..f3d30d9ea8f9 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -871,7 +871,7 @@ static void free_raid_bio(struct btrfs_raid_bio *rbio) * this frees the rbio and runs through all the bios in the * bio_list and calls end_io on them */ -static void rbio_orig_end_io(struct btrfs_raid_bio *rbio, int err) +static void rbio_orig_end_io(struct btrfs_raid_bio *rbio, blk_status_t err) { struct bio *cur = bio_list_get(&rbio->bio_list); struct bio *next; @@ -884,7 +884,7 @@ static void rbio_orig_end_io(struct btrfs_raid_bio *rbio, int err) while (cur) { next = cur->bi_next; cur->bi_next = NULL; - cur->bi_error = err; + cur->bi_status = err; bio_endio(cur); cur = next; } @@ -897,7 +897,7 @@ static void rbio_orig_end_io(struct btrfs_raid_bio *rbio, int err) static void raid_write_end_io(struct bio *bio) { struct btrfs_raid_bio *rbio = bio->bi_private; - int err = bio->bi_error; + blk_status_t err = bio->bi_status; int max_errors; if (err) @@ -914,7 +914,7 @@ static void raid_write_end_io(struct bio *bio) max_errors = (rbio->operation == BTRFS_RBIO_PARITY_SCRUB) ? 0 : rbio->bbio->max_errors; if (atomic_read(&rbio->error) > max_errors) - err = -EIO; + err = BLK_STS_IOERR; rbio_orig_end_io(rbio, err); } @@ -1092,7 +1092,7 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio, * devices or if they are not contiguous */ if (last_end == disk_start && stripe->dev->bdev && - !last->bi_error && + !last->bi_status && last->bi_bdev == stripe->dev->bdev) { ret = bio_add_page(last, page, PAGE_SIZE, 0); if (ret == PAGE_SIZE) @@ -1448,7 +1448,7 @@ static void raid_rmw_end_io(struct bio *bio) { struct btrfs_raid_bio *rbio = bio->bi_private; - if (bio->bi_error) + if (bio->bi_status) fail_bio_stripe(rbio, bio); else set_bio_pages_uptodate(bio); @@ -1991,7 +1991,7 @@ static void raid_recover_end_io(struct bio *bio) * we only read stripe pages off the disk, set them * up to date if there were no errors */ - if (bio->bi_error) + if (bio->bi_status) fail_bio_stripe(rbio, bio); else set_bio_pages_uptodate(bio); @@ -2530,7 +2530,7 @@ static void raid56_parity_scrub_end_io(struct bio *bio) { struct btrfs_raid_bio *rbio = bio->bi_private; - if (bio->bi_error) + if (bio->bi_status) fail_bio_stripe(rbio, bio); else set_bio_pages_uptodate(bio); diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index c7b45eb2403d..ba5595d19de1 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -95,7 +95,7 @@ struct scrub_bio { struct scrub_ctx *sctx; struct btrfs_device *dev; struct bio *bio; - int err; + blk_status_t status; u64 logical; u64 physical; #if SCRUB_PAGES_PER_WR_BIO >= SCRUB_PAGES_PER_RD_BIO @@ -1668,14 +1668,14 @@ leave_nomem: struct scrub_bio_ret { struct completion event; - int error; + blk_status_t status; }; static void scrub_bio_wait_endio(struct bio *bio) { struct scrub_bio_ret *ret = bio->bi_private; - ret->error = bio->bi_error; + ret->status = bio->bi_status; complete(&ret->event); } @@ -1693,7 +1693,7 @@ static int scrub_submit_raid56_bio_wait(struct btrfs_fs_info *fs_info, int ret; init_completion(&done.event); - done.error = 0; + done.status = 0; bio->bi_iter.bi_sector = page->logical >> 9; bio->bi_private = &done; bio->bi_end_io = scrub_bio_wait_endio; @@ -1705,7 +1705,7 @@ static int scrub_submit_raid56_bio_wait(struct btrfs_fs_info *fs_info, return ret; wait_for_completion(&done.event); - if (done.error) + if (done.status) return -EIO; return 0; @@ -1937,7 +1937,7 @@ again: bio->bi_bdev = sbio->dev->bdev; bio->bi_iter.bi_sector = sbio->physical >> 9; bio_set_op_attrs(bio, REQ_OP_WRITE, 0); - sbio->err = 0; + sbio->status = 0; } else if (sbio->physical + sbio->page_count * PAGE_SIZE != spage->physical_for_dev_replace || sbio->logical + sbio->page_count * PAGE_SIZE != @@ -1992,7 +1992,7 @@ static void scrub_wr_bio_end_io(struct bio *bio) struct scrub_bio *sbio = bio->bi_private; struct btrfs_fs_info *fs_info = sbio->dev->fs_info; - sbio->err = bio->bi_error; + sbio->status = bio->bi_status; sbio->bio = bio; btrfs_init_work(&sbio->work, btrfs_scrubwrc_helper, @@ -2007,7 +2007,7 @@ static void scrub_wr_bio_end_io_worker(struct btrfs_work *work) int i; WARN_ON(sbio->page_count > SCRUB_PAGES_PER_WR_BIO); - if (sbio->err) { + if (sbio->status) { struct btrfs_dev_replace *dev_replace = &sbio->sctx->fs_info->dev_replace; @@ -2341,7 +2341,7 @@ again: bio->bi_bdev = sbio->dev->bdev; bio->bi_iter.bi_sector = sbio->physical >> 9; bio_set_op_attrs(bio, REQ_OP_READ, 0); - sbio->err = 0; + sbio->status = 0; } else if (sbio->physical + sbio->page_count * PAGE_SIZE != spage->physical || sbio->logical + sbio->page_count * PAGE_SIZE != @@ -2377,7 +2377,7 @@ static void scrub_missing_raid56_end_io(struct bio *bio) struct scrub_block *sblock = bio->bi_private; struct btrfs_fs_info *fs_info = sblock->sctx->fs_info; - if (bio->bi_error) + if (bio->bi_status) sblock->no_io_error_seen = 0; bio_put(bio); @@ -2588,7 +2588,7 @@ static void scrub_bio_end_io(struct bio *bio) struct scrub_bio *sbio = bio->bi_private; struct btrfs_fs_info *fs_info = sbio->dev->fs_info; - sbio->err = bio->bi_error; + sbio->status = bio->bi_status; sbio->bio = bio; btrfs_queue_work(fs_info->scrub_workers, &sbio->work); @@ -2601,7 +2601,7 @@ static void scrub_bio_end_io_worker(struct btrfs_work *work) int i; BUG_ON(sbio->page_count > SCRUB_PAGES_PER_RD_BIO); - if (sbio->err) { + if (sbio->status) { for (i = 0; i < sbio->page_count; i++) { struct scrub_page *spage = sbio->pagev[i]; @@ -3004,7 +3004,7 @@ static void scrub_parity_bio_endio(struct bio *bio) struct scrub_parity *sparity = (struct scrub_parity *)bio->bi_private; struct btrfs_fs_info *fs_info = sparity->sctx->fs_info; - if (bio->bi_error) + if (bio->bi_status) bitmap_or(sparity->ebitmap, sparity->ebitmap, sparity->dbitmap, sparity->nsectors); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 017b67daa3bb..84a495967e0a 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -6042,9 +6042,10 @@ static void btrfs_end_bio(struct bio *bio) struct btrfs_bio *bbio = bio->bi_private; int is_orig_bio = 0; - if (bio->bi_error) { + if (bio->bi_status) { atomic_inc(&bbio->error); - if (bio->bi_error == -EIO || bio->bi_error == -EREMOTEIO) { + if (bio->bi_status == BLK_STS_IOERR || + bio->bi_status == BLK_STS_TARGET) { unsigned int stripe_index = btrfs_io_bio(bio)->stripe_index; struct btrfs_device *dev; @@ -6082,13 +6083,13 @@ static void btrfs_end_bio(struct bio *bio) * beyond the tolerance of the btrfs bio */ if (atomic_read(&bbio->error) > bbio->max_errors) { - bio->bi_error = -EIO; + bio->bi_status = BLK_STS_IOERR; } else { /* * this bio is actually up to date, we didn't * go over the max number of errors */ - bio->bi_error = 0; + bio->bi_status = 0; } btrfs_end_bbio(bbio, bio); @@ -6199,7 +6200,7 @@ static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical) btrfs_io_bio(bio)->mirror_num = bbio->mirror_num; bio->bi_iter.bi_sector = logical >> 9; - bio->bi_error = -EIO; + bio->bi_status = BLK_STS_IOERR; btrfs_end_bbio(bbio, bio); } } diff --git a/fs/buffer.c b/fs/buffer.c index 161be58c5cb0..5c2cba8d2387 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -49,7 +49,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list); static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, - struct writeback_control *wbc); + enum rw_hint hint, struct writeback_control *wbc); #define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers) @@ -1829,7 +1829,8 @@ int __block_write_full_page(struct inode *inode, struct page *page, do { struct buffer_head *next = bh->b_this_page; if (buffer_async_write(bh)) { - submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, wbc); + submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, + inode->i_write_hint, wbc); nr_underway++; } bh = next; @@ -1883,7 +1884,8 @@ recover: struct buffer_head *next = bh->b_this_page; if (buffer_async_write(bh)) { clear_buffer_dirty(bh); - submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, wbc); + submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, + inode->i_write_hint, wbc); nr_underway++; } bh = next; @@ -3038,7 +3040,7 @@ static void end_bio_bh_io_sync(struct bio *bio) if (unlikely(bio_flagged(bio, BIO_QUIET))) set_bit(BH_Quiet, &bh->b_state); - bh->b_end_io(bh, !bio->bi_error); + bh->b_end_io(bh, !bio->bi_status); bio_put(bio); } @@ -3091,7 +3093,7 @@ void guard_bio_eod(int op, struct bio *bio) } static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, - struct writeback_control *wbc) + enum rw_hint write_hint, struct writeback_control *wbc) { struct bio *bio; @@ -3120,6 +3122,7 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); bio->bi_bdev = bh->b_bdev; + bio->bi_write_hint = write_hint; bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh)); BUG_ON(bio->bi_iter.bi_size != bh->b_size); @@ -3142,7 +3145,7 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, int submit_bh(int op, int op_flags, struct buffer_head *bh) { - return submit_bh_wbc(op, op_flags, bh, NULL); + return submit_bh_wbc(op, op_flags, bh, 0, NULL); } EXPORT_SYMBOL(submit_bh); diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index 9bf90bcc56ac..bb3a02ca9da4 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -18,7 +18,7 @@ #include <linux/fscache-cache.h> #include <linux/timer.h> -#include <linux/wait.h> +#include <linux/wait_bit.h> #include <linux/cred.h> #include <linux/workqueue.h> #include <linux/security.h> @@ -97,7 +97,7 @@ struct cachefiles_cache { * backing file read tracking */ struct cachefiles_one_read { - wait_queue_t monitor; /* link into monitored waitqueue */ + wait_queue_entry_t monitor; /* link into monitored waitqueue */ struct page *back_page; /* backing file page we're waiting for */ struct page *netfs_page; /* netfs page we're going to fill */ struct fscache_retrieval *op; /* retrieval op covering this */ diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index 41df8a27d7eb..3978b324cbca 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -204,7 +204,7 @@ wait_for_old_object: wait_queue_head_t *wq; signed long timeout = 60 * HZ; - wait_queue_t wait; + wait_queue_entry_t wait; bool requeue; /* if the object we're waiting for is queued for processing, diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index afbdc418966d..18d7aa61ef0f 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -21,7 +21,7 @@ * - we use this to detect read completion of backing pages * - the caller holds the waitqueue lock */ -static int cachefiles_read_waiter(wait_queue_t *wait, unsigned mode, +static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode, int sync, void *_key) { struct cachefiles_one_read *monitor = @@ -48,7 +48,7 @@ static int cachefiles_read_waiter(wait_queue_t *wait, unsigned mode, } /* remove from the waitqueue */ - list_del(&wait->task_list); + list_del(&wait->entry); /* move onto the action list and queue for FS-Cache thread pool */ ASSERT(monitor->op); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 0fd081bd2a2f..fcef70602b27 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -3271,7 +3271,7 @@ ssize_t cifs_user_readv(struct kiocb *iocb, struct iov_iter *to) if (!is_sync_kiocb(iocb)) ctx->iocb = iocb; - if (to->type & ITER_IOVEC) + if (to->type == ITER_IOVEC) ctx->should_dirty = true; rc = setup_aio_ctx_iter(ctx, to, READ); diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 4d1fcd76d022..a8693632235f 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -24,6 +24,7 @@ #include <linux/pagemap.h> #include <linux/freezer.h> #include <linux/sched/signal.h> +#include <linux/wait_bit.h> #include <asm/div64.h> #include "cifsfs.h" diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index b08531977daa..3b147dc6af63 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -810,7 +810,7 @@ setup_aio_ctx_iter(struct cifs_aio_ctx *ctx, struct iov_iter *iter, int rw) if (!pages) { pages = vmalloc(max_pages * sizeof(struct page *)); - if (!bv) { + if (!pages) { kvfree(bv); return -ENOMEM; } diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index 27bc360c7ffd..a723df3e0197 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -849,8 +849,13 @@ cifs_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *fid, __u16 search_flags, struct cifs_search_info *srch_inf) { - return CIFSFindFirst(xid, tcon, path, cifs_sb, - &fid->netfid, search_flags, srch_inf, true); + int rc; + + rc = CIFSFindFirst(xid, tcon, path, cifs_sb, + &fid->netfid, search_flags, srch_inf, true); + if (rc) + cifs_dbg(FYI, "find first failed=%d\n", rc); + return rc; } static int diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index c58691834eb2..7e48561abd29 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -982,7 +982,7 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon, rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL); kfree(utf16_path); if (rc) { - cifs_dbg(VFS, "open dir failed\n"); + cifs_dbg(FYI, "open dir failed rc=%d\n", rc); return rc; } @@ -992,7 +992,7 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon, rc = SMB2_query_directory(xid, tcon, fid->persistent_fid, fid->volatile_fid, 0, srch_inf); if (rc) { - cifs_dbg(VFS, "query directory failed\n"); + cifs_dbg(FYI, "query directory failed rc=%d\n", rc); SMB2_close(xid, tcon, fid->persistent_fid, fid->volatile_fid); } return rc; @@ -1809,7 +1809,8 @@ crypt_message(struct TCP_Server_Info *server, struct smb_rqst *rqst, int enc) sg = init_sg(rqst, sign); if (!sg) { - cifs_dbg(VFS, "%s: Failed to init sg %d", __func__, rc); + cifs_dbg(VFS, "%s: Failed to init sg", __func__); + rc = -ENOMEM; goto free_req; } @@ -1817,6 +1818,7 @@ crypt_message(struct TCP_Server_Info *server, struct smb_rqst *rqst, int enc) iv = kzalloc(iv_len, GFP_KERNEL); if (!iv) { cifs_dbg(VFS, "%s: Failed to alloc IV", __func__); + rc = -ENOMEM; goto free_sg; } iv[0] = 3; diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c index 3cb5c9e2d4e7..de50e749ff05 100644 --- a/fs/cifs/xattr.c +++ b/fs/cifs/xattr.c @@ -188,8 +188,6 @@ static int cifs_creation_time_get(struct dentry *dentry, struct inode *inode, pcreatetime = (__u64 *)value; *pcreatetime = CIFS_I(inode)->createtime; return sizeof(__u64); - - return rc; } diff --git a/fs/crypto/bio.c b/fs/crypto/bio.c index a409a84f1bca..6181e9526860 100644 --- a/fs/crypto/bio.c +++ b/fs/crypto/bio.c @@ -129,7 +129,7 @@ int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, goto errout; } err = submit_bio_wait(bio); - if ((err == 0) && bio->bi_error) + if (err == 0 && bio->bi_status) err = -EIO; bio_put(bio); if (err) @@ -84,7 +84,7 @@ struct exceptional_entry_key { }; struct wait_exceptional_entry_queue { - wait_queue_t wait; + wait_queue_entry_t wait; struct exceptional_entry_key key; }; @@ -108,7 +108,7 @@ static wait_queue_head_t *dax_entry_waitqueue(struct address_space *mapping, return wait_table + hash; } -static int wake_exceptional_entry_func(wait_queue_t *wait, unsigned int mode, +static int wake_exceptional_entry_func(wait_queue_entry_t *wait, unsigned int mode, int sync, void *keyp) { struct exceptional_entry_key *key = keyp; @@ -859,6 +859,7 @@ int dax_writeback_mapping_range(struct address_space *mapping, if (ret < 0) goto out; } + start_index = indices[pvec.nr - 1] + 1; } out: put_dax(dax_dev); diff --git a/fs/direct-io.c b/fs/direct-io.c index a04ebea77de8..08cf27811e5a 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -294,7 +294,7 @@ static void dio_aio_complete_work(struct work_struct *work) dio_complete(dio, 0, true); } -static int dio_bio_complete(struct dio *dio, struct bio *bio); +static blk_status_t dio_bio_complete(struct dio *dio, struct bio *bio); /* * Asynchronous IO callback. @@ -348,13 +348,12 @@ static void dio_bio_end_io(struct bio *bio) /** * dio_end_io - handle the end io action for the given bio * @bio: The direct io bio thats being completed - * @error: Error if there was one * * This is meant to be called by any filesystem that uses their own dio_submit_t * so that the DIO specific endio actions are dealt with after the filesystem * has done it's completion work. */ -void dio_end_io(struct bio *bio, int error) +void dio_end_io(struct bio *bio) { struct dio *dio = bio->bi_private; @@ -386,6 +385,8 @@ dio_bio_alloc(struct dio *dio, struct dio_submit *sdio, else bio->bi_end_io = dio_bio_end_io; + bio->bi_write_hint = dio->iocb->ki_hint; + sdio->bio = bio; sdio->logical_offset_in_bio = sdio->cur_page_fs_offset; } @@ -474,17 +475,20 @@ static struct bio *dio_await_one(struct dio *dio) /* * Process one completed BIO. No locks are held. */ -static int dio_bio_complete(struct dio *dio, struct bio *bio) +static blk_status_t dio_bio_complete(struct dio *dio, struct bio *bio) { struct bio_vec *bvec; unsigned i; - int err; + blk_status_t err = bio->bi_status; - if (bio->bi_error) - dio->io_error = -EIO; + if (err) { + if (err == BLK_STS_AGAIN && (bio->bi_opf & REQ_NOWAIT)) + dio->io_error = -EAGAIN; + else + dio->io_error = -EIO; + } if (dio->is_async && dio->op == REQ_OP_READ && dio->should_dirty) { - err = bio->bi_error; bio_check_pages_dirty(bio); /* transfers ownership */ } else { bio_for_each_segment_all(bvec, bio, i) { @@ -495,7 +499,6 @@ static int dio_bio_complete(struct dio *dio, struct bio *bio) set_page_dirty_lock(page); put_page(page); } - err = bio->bi_error; bio_put(bio); } return err; @@ -539,7 +542,7 @@ static inline int dio_bio_reap(struct dio *dio, struct dio_submit *sdio) bio = dio->bio_list; dio->bio_list = bio->bi_private; spin_unlock_irqrestore(&dio->bio_lock, flags); - ret2 = dio_bio_complete(dio, bio); + ret2 = blk_status_to_errno(dio_bio_complete(dio, bio)); if (ret == 0) ret = ret2; } @@ -1197,6 +1200,8 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, if (iov_iter_rw(iter) == WRITE) { dio->op = REQ_OP_WRITE; dio->op_flags = REQ_SYNC | REQ_IDLE; + if (iocb->ki_flags & IOCB_NOWAIT) + dio->op_flags |= REQ_NOWAIT; } else { dio->op = REQ_OP_READ; } diff --git a/fs/eventfd.c b/fs/eventfd.c index 68b9fffcb2c8..9736df2ce89d 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -191,7 +191,7 @@ static void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt) * This is used to atomically remove a wait queue entry from the eventfd wait * queue head, and read/reset the counter value. */ -int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_t *wait, +int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait, __u64 *cnt) { unsigned long flags; diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 5420767c9b68..b1c8e23ddf65 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -244,7 +244,7 @@ struct eppoll_entry { * Wait queue item that will be linked to the target file wait * queue head. */ - wait_queue_t wait; + wait_queue_entry_t wait; /* The wait queue head that linked the "wait" wait queue item */ wait_queue_head_t *whead; @@ -347,13 +347,13 @@ static inline int ep_is_linked(struct list_head *p) return !list_empty(p); } -static inline struct eppoll_entry *ep_pwq_from_wait(wait_queue_t *p) +static inline struct eppoll_entry *ep_pwq_from_wait(wait_queue_entry_t *p) { return container_of(p, struct eppoll_entry, wait); } /* Get the "struct epitem" from a wait queue pointer */ -static inline struct epitem *ep_item_from_wait(wait_queue_t *p) +static inline struct epitem *ep_item_from_wait(wait_queue_entry_t *p) { return container_of(p, struct eppoll_entry, wait)->base; } @@ -1078,7 +1078,7 @@ static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd) * mechanism. It is called by the stored file descriptors when they * have events to report. */ -static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *key) +static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { int pwake = 0; unsigned long flags; @@ -1094,7 +1094,7 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k * can't use __remove_wait_queue(). whead->lock is held by * the caller. */ - list_del_init(&wait->task_list); + list_del_init(&wait->entry); } spin_lock_irqsave(&ep->lock, flags); @@ -1699,7 +1699,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, int res = 0, eavail, timed_out = 0; unsigned long flags; u64 slack = 0; - wait_queue_t wait; + wait_queue_entry_t wait; ktime_t expires, *to = NULL; if (timeout > 0) { diff --git a/fs/exec.c b/fs/exec.c index 72934df68471..904199086490 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -220,8 +220,26 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, if (write) { unsigned long size = bprm->vma->vm_end - bprm->vma->vm_start; + unsigned long ptr_size; struct rlimit *rlim; + /* + * Since the stack will hold pointers to the strings, we + * must account for them as well. + * + * The size calculation is the entire vma while each arg page is + * built, so each time we get here it's calculating how far it + * is currently (rather than each call being just the newly + * added size from the arg page). As a result, we need to + * always add the entire size of the pointers, so that on the + * last call to get_arg_page() we'll actually have the entire + * correct size. + */ + ptr_size = (bprm->argc + bprm->envc) * sizeof(void *); + if (ptr_size > ULONG_MAX - size) + goto fail; + size += ptr_size; + acct_arg_size(bprm, size / PAGE_SIZE); /* @@ -239,13 +257,15 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, * to work from. */ rlim = current->signal->rlim; - if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur) / 4) { - put_page(page); - return NULL; - } + if (size > READ_ONCE(rlim[RLIMIT_STACK].rlim_cur) / 4) + goto fail; } return page; + +fail: + put_page(page); + return NULL; } static void put_arg_page(struct page *page) diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 02ce7e7bbdf5..58e2eeaa0bc4 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -37,7 +37,11 @@ static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to) struct inode *inode = file_inode(iocb->ki_filp); ssize_t ret; - inode_lock_shared(inode); + if (!inode_trylock_shared(inode)) { + if (iocb->ki_flags & IOCB_NOWAIT) + return -EAGAIN; + inode_lock_shared(inode); + } /* * Recheck under inode lock - at this point we are sure it cannot * change anymore @@ -179,7 +183,11 @@ ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from) struct inode *inode = file_inode(iocb->ki_filp); ssize_t ret; - inode_lock(inode); + if (!inode_trylock(inode)) { + if (iocb->ki_flags & IOCB_NOWAIT) + return -EAGAIN; + inode_lock(inode); + } ret = ext4_write_checks(iocb, from); if (ret <= 0) goto out; @@ -216,7 +224,12 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from) return ext4_dax_write_iter(iocb, from); #endif - inode_lock(inode); + if (!inode_trylock(inode)) { + if (iocb->ki_flags & IOCB_NOWAIT) + return -EAGAIN; + inode_lock(inode); + } + ret = ext4_write_checks(iocb, from); if (ret <= 0) goto out; @@ -235,9 +248,15 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from) iocb->private = &overwrite; /* Check whether we do a DIO overwrite or not */ - if (o_direct && ext4_should_dioread_nolock(inode) && !unaligned_aio && - ext4_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from))) - overwrite = 1; + if (o_direct && !unaligned_aio) { + if (ext4_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from))) { + if (ext4_should_dioread_nolock(inode)) + overwrite = 1; + } else if (iocb->ki_flags & IOCB_NOWAIT) { + ret = -EAGAIN; + goto out; + } + } ret = __generic_file_write_iter(iocb, from); inode_unlock(inode); @@ -435,6 +454,10 @@ static int ext4_file_open(struct inode * inode, struct file * filp) if (ret < 0) return ret; } + + /* Set the flags to support nowait AIO */ + filp->f_mode |= FMODE_AIO_NOWAIT; + return dquot_file_open(inode, filp); } diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 1a82138ba739..c2fce4478cca 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -85,7 +85,7 @@ static void ext4_finish_bio(struct bio *bio) } #endif - if (bio->bi_error) { + if (bio->bi_status) { SetPageError(page); mapping_set_error(page->mapping, -EIO); } @@ -104,7 +104,7 @@ static void ext4_finish_bio(struct bio *bio) continue; } clear_buffer_async_write(bh); - if (bio->bi_error) + if (bio->bi_status) buffer_io_error(bh); } while ((bh = bh->b_this_page) != head); bit_spin_unlock(BH_Uptodate_Lock, &head->b_state); @@ -303,24 +303,25 @@ static void ext4_end_bio(struct bio *bio) bdevname(bio->bi_bdev, b), (long long) bio->bi_iter.bi_sector, (unsigned) bio_sectors(bio), - bio->bi_error)) { + bio->bi_status)) { ext4_finish_bio(bio); bio_put(bio); return; } bio->bi_end_io = NULL; - if (bio->bi_error) { + if (bio->bi_status) { struct inode *inode = io_end->inode; ext4_warning(inode->i_sb, "I/O error %d writing to inode %lu " "(offset %llu size %ld starting block %llu)", - bio->bi_error, inode->i_ino, + bio->bi_status, inode->i_ino, (unsigned long long) io_end->offset, (long) io_end->size, (unsigned long long) bi_sector >> (inode->i_blkbits - 9)); - mapping_set_error(inode->i_mapping, bio->bi_error); + mapping_set_error(inode->i_mapping, + blk_status_to_errno(bio->bi_status)); } if (io_end->flag & EXT4_IO_END_UNWRITTEN) { @@ -349,6 +350,7 @@ void ext4_io_submit(struct ext4_io_submit *io) if (bio) { int io_op_flags = io->io_wbc->sync_mode == WB_SYNC_ALL ? REQ_SYNC : 0; + io->io_bio->bi_write_hint = io->io_end->inode->i_write_hint; bio_set_op_attrs(io->io_bio, REQ_OP_WRITE, io_op_flags); submit_bio(io->io_bio); } @@ -396,6 +398,7 @@ submit_and_retry: ret = io_submit_init_bio(io, bh); if (ret) return ret; + io->io_bio->bi_write_hint = inode->i_write_hint; } ret = bio_add_page(io->io_bio, page, bh->b_size, bh_offset(bh)); if (ret != bh->b_size) diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index a81b829d56de..40a5497b0f60 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -73,7 +73,7 @@ static void mpage_end_io(struct bio *bio) int i; if (ext4_bio_encrypted(bio)) { - if (bio->bi_error) { + if (bio->bi_status) { fscrypt_release_ctx(bio->bi_private); } else { fscrypt_decrypt_bio_pages(bio->bi_private, bio); @@ -83,7 +83,7 @@ static void mpage_end_io(struct bio *bio) bio_for_each_segment_all(bv, bio, i) { struct page *page = bv->bv_page; - if (!bio->bi_error) { + if (!bio->bi_status) { SetPageUptodate(page); } else { ClearPageUptodate(page); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index d37c81f327e7..9006cb5857b8 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3950,7 +3950,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sb->s_qcop = &ext4_qctl_operations; sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP | QTYPE_MASK_PRJ; #endif - memcpy(sb->s_uuid, es->s_uuid, sizeof(es->s_uuid)); + memcpy(&sb->s_uuid, es->s_uuid, sizeof(es->s_uuid)); INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */ mutex_init(&sbi->s_orphan_lock); diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 7c0f6bdf817d..36fe82012a33 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -58,12 +58,12 @@ static void f2fs_read_end_io(struct bio *bio) #ifdef CONFIG_F2FS_FAULT_INJECTION if (time_to_inject(F2FS_P_SB(bio->bi_io_vec->bv_page), FAULT_IO)) { f2fs_show_injection_info(FAULT_IO); - bio->bi_error = -EIO; + bio->bi_status = BLK_STS_IOERR; } #endif if (f2fs_bio_encrypted(bio)) { - if (bio->bi_error) { + if (bio->bi_status) { fscrypt_release_ctx(bio->bi_private); } else { fscrypt_decrypt_bio_pages(bio->bi_private, bio); @@ -74,7 +74,7 @@ static void f2fs_read_end_io(struct bio *bio) bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; - if (!bio->bi_error) { + if (!bio->bi_status) { if (!PageUptodate(page)) SetPageUptodate(page); } else { @@ -102,14 +102,14 @@ static void f2fs_write_end_io(struct bio *bio) unlock_page(page); mempool_free(page, sbi->write_io_dummy); - if (unlikely(bio->bi_error)) + if (unlikely(bio->bi_status)) f2fs_stop_checkpoint(sbi, true); continue; } fscrypt_pullback_bio_page(&page, true); - if (unlikely(bio->bi_error)) { + if (unlikely(bio->bi_status)) { mapping_set_error(page->mapping, -EIO); f2fs_stop_checkpoint(sbi, true); } diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 96845854e7ee..ea9f455d94ba 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -749,7 +749,7 @@ static void f2fs_submit_discard_endio(struct bio *bio) { struct discard_cmd *dc = (struct discard_cmd *)bio->bi_private; - dc->error = bio->bi_error; + dc->error = blk_status_to_errno(bio->bi_status); dc->state = D_DONE; complete(&dc->wait); bio_put(bio); diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 83355ec4a92c..0b89b0b7b9f7 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1937,7 +1937,7 @@ try_onemore: sb->s_time_gran = 1; sb->s_flags = (sb->s_flags & ~MS_POSIXACL) | (test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0); - memcpy(sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid)); + memcpy(&sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid)); /* init f2fs-specific super block info */ sbi->valid_super_block = valid_super_block; diff --git a/fs/fcntl.c b/fs/fcntl.c index f4e7267d117f..ed051f825bad 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -243,6 +243,67 @@ static int f_getowner_uids(struct file *filp, unsigned long arg) } #endif +static bool rw_hint_valid(enum rw_hint hint) +{ + switch (hint) { + case RWF_WRITE_LIFE_NOT_SET: + case RWH_WRITE_LIFE_NONE: + case RWH_WRITE_LIFE_SHORT: + case RWH_WRITE_LIFE_MEDIUM: + case RWH_WRITE_LIFE_LONG: + case RWH_WRITE_LIFE_EXTREME: + return true; + default: + return false; + } +} + +static long fcntl_rw_hint(struct file *file, unsigned int cmd, + unsigned long arg) +{ + struct inode *inode = file_inode(file); + u64 *argp = (u64 __user *)arg; + enum rw_hint hint; + u64 h; + + switch (cmd) { + case F_GET_FILE_RW_HINT: + h = file_write_hint(file); + if (copy_to_user(argp, &h, sizeof(*argp))) + return -EFAULT; + return 0; + case F_SET_FILE_RW_HINT: + if (copy_from_user(&h, argp, sizeof(h))) + return -EFAULT; + hint = (enum rw_hint) h; + if (!rw_hint_valid(hint)) + return -EINVAL; + + spin_lock(&file->f_lock); + file->f_write_hint = hint; + spin_unlock(&file->f_lock); + return 0; + case F_GET_RW_HINT: + h = inode->i_write_hint; + if (copy_to_user(argp, &h, sizeof(*argp))) + return -EFAULT; + return 0; + case F_SET_RW_HINT: + if (copy_from_user(&h, argp, sizeof(h))) + return -EFAULT; + hint = (enum rw_hint) h; + if (!rw_hint_valid(hint)) + return -EINVAL; + + inode_lock(inode); + inode->i_write_hint = hint; + inode_unlock(inode); + return 0; + default: + return -EINVAL; + } +} + static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, struct file *filp) { @@ -337,6 +398,12 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, case F_GET_SEALS: err = shmem_fcntl(filp, cmd, arg); break; + case F_GET_RW_HINT: + case F_SET_RW_HINT: + case F_GET_FILE_RW_HINT: + case F_SET_FILE_RW_HINT: + err = fcntl_rw_hint(filp, cmd, arg); + break; default: break; } diff --git a/fs/fs_pin.c b/fs/fs_pin.c index 611b5408f6ec..e747b3d720ee 100644 --- a/fs/fs_pin.c +++ b/fs/fs_pin.c @@ -34,7 +34,7 @@ void pin_insert(struct fs_pin *pin, struct vfsmount *m) void pin_kill(struct fs_pin *p) { - wait_queue_t wait; + wait_queue_entry_t wait; if (!p) { rcu_read_unlock(); @@ -61,7 +61,7 @@ void pin_kill(struct fs_pin *p) rcu_read_unlock(); schedule(); rcu_read_lock(); - if (likely(list_empty(&wait.task_list))) + if (likely(list_empty(&wait.entry))) break; /* OK, we know p couldn't have been freed yet */ spin_lock_irq(&p->wait.lock); diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index b7cf65d13561..aa3d44527fa2 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -815,7 +815,6 @@ struct gfs2_sbd { atomic_t sd_log_in_flight; struct bio *sd_log_bio; wait_queue_head_t sd_log_flush_wait; - int sd_log_error; atomic_t sd_reserving_log; wait_queue_head_t sd_reserving_log_wait; diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index b1f9144b42c7..885d36e7a29f 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -170,7 +170,7 @@ static u64 gfs2_log_bmap(struct gfs2_sbd *sdp) */ static void gfs2_end_log_write_bh(struct gfs2_sbd *sdp, struct bio_vec *bvec, - int error) + blk_status_t error) { struct buffer_head *bh, *next; struct page *page = bvec->bv_page; @@ -209,15 +209,13 @@ static void gfs2_end_log_write(struct bio *bio) struct page *page; int i; - if (bio->bi_error) { - sdp->sd_log_error = bio->bi_error; - fs_err(sdp, "Error %d writing to log\n", bio->bi_error); - } + if (bio->bi_status) + fs_err(sdp, "Error %d writing to log\n", bio->bi_status); bio_for_each_segment_all(bvec, bio, i) { page = bvec->bv_page; if (page_has_buffers(page)) - gfs2_end_log_write_bh(sdp, bvec, bio->bi_error); + gfs2_end_log_write_bh(sdp, bvec, bio->bi_status); else mempool_free(page, gfs2_page_pool); } diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 663ffc135ef3..fabe1614f879 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -201,7 +201,7 @@ static void gfs2_meta_read_endio(struct bio *bio) do { struct buffer_head *next = bh->b_this_page; len -= bh->b_size; - bh->b_end_io(bh, !bio->bi_error); + bh->b_end_io(bh, !bio->bi_status); bh = next; } while (bh && len); } diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index ed67548b286c..e76058d34b74 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -176,10 +176,10 @@ static void end_bio_io_page(struct bio *bio) { struct page *page = bio->bi_private; - if (!bio->bi_error) + if (!bio->bi_status) SetPageUptodate(page); else - pr_warn("error %d reading superblock\n", bio->bi_error); + pr_warn("error %d reading superblock\n", bio->bi_status); unlock_page(page); } @@ -203,7 +203,7 @@ static void gfs2_sb_in(struct gfs2_sbd *sdp, const void *buf) memcpy(sb->sb_lockproto, str->sb_lockproto, GFS2_LOCKNAME_LEN); memcpy(sb->sb_locktable, str->sb_locktable, GFS2_LOCKNAME_LEN); - memcpy(s->s_uuid, str->sb_uuid, 16); + memcpy(&s->s_uuid, str->sb_uuid, 16); } /** diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index 7a515345610c..e77bc52b468f 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -71,25 +71,14 @@ static ssize_t fsname_show(struct gfs2_sbd *sdp, char *buf) return snprintf(buf, PAGE_SIZE, "%s\n", sdp->sd_fsname); } -static int gfs2_uuid_valid(const u8 *uuid) -{ - int i; - - for (i = 0; i < 16; i++) { - if (uuid[i]) - return 1; - } - return 0; -} - static ssize_t uuid_show(struct gfs2_sbd *sdp, char *buf) { struct super_block *s = sdp->sd_vfs; - const u8 *uuid = s->s_uuid; + buf[0] = '\0'; - if (!gfs2_uuid_valid(uuid)) + if (uuid_is_null(&s->s_uuid)) return 0; - return snprintf(buf, PAGE_SIZE, "%pUB\n", uuid); + return snprintf(buf, PAGE_SIZE, "%pUB\n", &s->s_uuid); } static ssize_t freeze_show(struct gfs2_sbd *sdp, char *buf) @@ -712,14 +701,13 @@ static int gfs2_uevent(struct kset *kset, struct kobject *kobj, { struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj); struct super_block *s = sdp->sd_vfs; - const u8 *uuid = s->s_uuid; add_uevent_var(env, "LOCKTABLE=%s", sdp->sd_table_name); add_uevent_var(env, "LOCKPROTO=%s", sdp->sd_proto_name); if (!test_bit(SDF_NOJOURNALID, &sdp->sd_flags)) add_uevent_var(env, "JOURNALID=%d", sdp->sd_lockstruct.ls_jid); - if (gfs2_uuid_valid(uuid)) - add_uevent_var(env, "UUID=%pUB", uuid); + if (!uuid_is_null(&s->s_uuid)) + add_uevent_var(env, "UUID=%pUB", &s->s_uuid); return 0; } diff --git a/fs/inode.c b/fs/inode.c index db5914783a71..ab3b9a795c0b 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -146,6 +146,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode) i_gid_write(inode, 0); atomic_set(&inode->i_writecount, 0); inode->i_size = 0; + inode->i_write_hint = WRITE_LIFE_NOT_SET; inode->i_blocks = 0; inode->i_bytes = 0; inode->i_generation = 0; @@ -1891,11 +1892,11 @@ static void __wait_on_freeing_inode(struct inode *inode) wait_queue_head_t *wq; DEFINE_WAIT_BIT(wait, &inode->i_state, __I_NEW); wq = bit_waitqueue(&inode->i_state, __I_NEW); - prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE); + prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); schedule(); - finish_wait(wq, &wait.wait); + finish_wait(wq, &wait.wq_entry); spin_lock(&inode_hash_lock); } @@ -2038,11 +2039,11 @@ static void __inode_dio_wait(struct inode *inode) DEFINE_WAIT_BIT(q, &inode->i_state, __I_DIO_WAKEUP); do { - prepare_to_wait(wq, &q.wait, TASK_UNINTERRUPTIBLE); + prepare_to_wait(wq, &q.wq_entry, TASK_UNINTERRUPTIBLE); if (atomic_read(&inode->i_dio_count)) schedule(); } while (atomic_read(&inode->i_dio_count)); - finish_wait(wq, &q.wait); + finish_wait(wq, &q.wq_entry); } /** diff --git a/fs/iomap.c b/fs/iomap.c index 4b10892967a5..fa6cd5b3f578 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -672,8 +672,8 @@ static void iomap_dio_bio_end_io(struct bio *bio) struct iomap_dio *dio = bio->bi_private; bool should_dirty = (dio->flags & IOMAP_DIO_DIRTY); - if (bio->bi_error) - iomap_dio_set_error(dio, bio->bi_error); + if (bio->bi_status) + iomap_dio_set_error(dio, blk_status_to_errno(bio->bi_status)); if (atomic_dec_and_test(&dio->ref)) { if (is_sync_kiocb(dio->iocb)) { @@ -793,6 +793,7 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length, bio->bi_bdev = iomap->bdev; bio->bi_iter.bi_sector = iomap->blkno + ((pos - iomap->offset) >> 9); + bio->bi_write_hint = dio->iocb->ki_hint; bio->bi_private = dio; bio->bi_end_io = iomap_dio_bio_end_io; @@ -881,6 +882,14 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, flags |= IOMAP_WRITE; } + if (iocb->ki_flags & IOCB_NOWAIT) { + if (filemap_range_has_page(mapping, start, end)) { + ret = -EAGAIN; + goto out_free_dio; + } + flags |= IOMAP_NOWAIT; + } + ret = filemap_write_and_wait_range(mapping, start, end); if (ret) goto out_free_dio; diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index ebad34266bcf..7d5ef3bf3f3e 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -2579,10 +2579,10 @@ restart: wait_queue_head_t *wq; DEFINE_WAIT_BIT(wait, &jinode->i_flags, __JI_COMMIT_RUNNING); wq = bit_waitqueue(&jinode->i_flags, __JI_COMMIT_RUNNING); - prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE); + prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); spin_unlock(&journal->j_list_lock); schedule(); - finish_wait(wq, &wait.wait); + finish_wait(wq, &wait.wq_entry); goto restart; } diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c index bb1da1feafeb..a21f0e9eecd4 100644 --- a/fs/jfs/jfs_logmgr.c +++ b/fs/jfs/jfs_logmgr.c @@ -2205,7 +2205,7 @@ static void lbmIODone(struct bio *bio) bp->l_flag |= lbmDONE; - if (bio->bi_error) { + if (bio->bi_status) { bp->l_flag |= lbmERROR; jfs_err("lbmIODone: I/O error in JFS log"); diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c index 489aaa1403e5..ce93db3aef3c 100644 --- a/fs/jfs/jfs_metapage.c +++ b/fs/jfs/jfs_metapage.c @@ -280,7 +280,7 @@ static void metapage_read_end_io(struct bio *bio) { struct page *page = bio->bi_private; - if (bio->bi_error) { + if (bio->bi_status) { printk(KERN_ERR "metapage_read_end_io: I/O error\n"); SetPageError(page); } @@ -337,7 +337,7 @@ static void metapage_write_end_io(struct bio *bio) BUG_ON(!PagePrivate(page)); - if (bio->bi_error) { + if (bio->bi_status) { printk(KERN_ERR "metapage_write_end_io: I/O error\n"); SetPageError(page); } diff --git a/fs/mpage.c b/fs/mpage.c index baff8f820c29..d6d1486d6f99 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -50,7 +50,8 @@ static void mpage_end_io(struct bio *bio) bio_for_each_segment_all(bv, bio, i) { struct page *page = bv->bv_page; - page_endio(page, op_is_write(bio_op(bio)), bio->bi_error); + page_endio(page, op_is_write(bio_op(bio)), + blk_status_to_errno(bio->bi_status)); } bio_put(bio); @@ -614,6 +615,7 @@ alloc_new: goto confused; wbc_init_bio(wbc, bio); + bio->bi_write_hint = inode->i_write_hint; } /* diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 0ca370d23ddb..d8863a804b15 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -188,7 +188,7 @@ static void bl_end_io_read(struct bio *bio) { struct parallel_io *par = bio->bi_private; - if (bio->bi_error) { + if (bio->bi_status) { struct nfs_pgio_header *header = par->data; if (!header->pnfs_error) @@ -319,7 +319,7 @@ static void bl_end_io_write(struct bio *bio) struct parallel_io *par = bio->bi_private; struct nfs_pgio_header *header = par->data; - if (bio->bi_error) { + if (bio->bi_status) { if (!header->pnfs_error) header->pnfs_error = -EIO; pnfs_set_lo_fail(header->lseg); diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index c14758e08d73..390ac9c39c59 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -753,7 +753,6 @@ static void nfs4_callback_free_slot(struct nfs4_session *session, * A single slot, so highest used slotid is either 0 or -1 */ nfs4_free_slot(tbl, slot); - nfs4_slot_tbl_drain_complete(tbl); spin_unlock(&tbl->slot_tbl_lock); } diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 32ccd7754f8a..2ac00bf4ecf1 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1946,29 +1946,6 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) } EXPORT_SYMBOL_GPL(nfs_link); -static void -nfs_complete_rename(struct rpc_task *task, struct nfs_renamedata *data) -{ - struct dentry *old_dentry = data->old_dentry; - struct dentry *new_dentry = data->new_dentry; - struct inode *old_inode = d_inode(old_dentry); - struct inode *new_inode = d_inode(new_dentry); - - nfs_mark_for_revalidate(old_inode); - - switch (task->tk_status) { - case 0: - if (new_inode != NULL) - nfs_drop_nlink(new_inode); - d_move(old_dentry, new_dentry); - nfs_set_verifier(new_dentry, - nfs_save_change_attribute(data->new_dir)); - break; - case -ENOENT: - nfs_dentry_handle_enoent(old_dentry); - } -} - /* * RENAME * FIXME: Some nfsds, like the Linux user space nfsd, may generate a @@ -1999,7 +1976,7 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry, { struct inode *old_inode = d_inode(old_dentry); struct inode *new_inode = d_inode(new_dentry); - struct dentry *dentry = NULL; + struct dentry *dentry = NULL, *rehash = NULL; struct rpc_task *task; int error = -EBUSY; @@ -2022,8 +1999,10 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry, * To prevent any new references to the target during the * rename, we unhash the dentry in advance. */ - if (!d_unhashed(new_dentry)) + if (!d_unhashed(new_dentry)) { d_drop(new_dentry); + rehash = new_dentry; + } if (d_count(new_dentry) > 2) { int err; @@ -2040,6 +2019,7 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry, goto out; new_dentry = dentry; + rehash = NULL; new_inode = NULL; } } @@ -2048,8 +2028,7 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (new_inode != NULL) NFS_PROTO(new_inode)->return_delegation(new_inode); - task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry, - nfs_complete_rename); + task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry, NULL); if (IS_ERR(task)) { error = PTR_ERR(task); goto out; @@ -2059,9 +2038,27 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (error == 0) error = task->tk_status; rpc_put_task(task); + nfs_mark_for_revalidate(old_inode); out: + if (rehash) + d_rehash(rehash); trace_nfs_rename_exit(old_dir, old_dentry, new_dir, new_dentry, error); + if (!error) { + if (new_inode != NULL) + nfs_drop_nlink(new_inode); + /* + * The d_move() should be here instead of in an async RPC completion + * handler because we need the proper locks to move the dentry. If + * we're interrupted by a signal, the async RPC completion handler + * should mark the directories for revalidation. + */ + d_move(old_dentry, new_dentry); + nfs_set_verifier(new_dentry, + nfs_save_change_attribute(new_dir)); + } else if (error == -ENOENT) + nfs_dentry_handle_enoent(old_dentry); + /* new dentry created? */ if (dentry) dput(dentry); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 3e24392f2caa..8701d7617964 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -7,6 +7,7 @@ #include <linux/security.h> #include <linux/crc32.h> #include <linux/nfs_page.h> +#include <linux/wait_bit.h> #define NFS_MS_MASK (MS_RDONLY|MS_NOSUID|MS_NODEV|MS_NOEXEC|MS_SYNCHRONOUS) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index c08c46a3b8cd..98b0b662af09 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2589,7 +2589,8 @@ static inline void nfs4_exclusive_attrset(struct nfs4_opendata *opendata, /* Except MODE, it seems harmless of setting twice. */ if (opendata->o_arg.createmode != NFS4_CREATE_EXCLUSIVE && - attrset[1] & FATTR4_WORD1_MODE) + (attrset[1] & FATTR4_WORD1_MODE || + attrset[2] & FATTR4_WORD2_MODE_UMASK)) sattr->ia_valid &= ~ATTR_MODE; if (attrset[2] & FATTR4_WORD2_SECURITY_LABEL) @@ -6372,7 +6373,7 @@ struct nfs4_lock_waiter { }; static int -nfs4_wake_lock_waiter(wait_queue_t *wait, unsigned int mode, int flags, void *key) +nfs4_wake_lock_waiter(wait_queue_entry_t *wait, unsigned int mode, int flags, void *key) { int ret; struct cb_notify_lock_args *cbnl = key; @@ -6415,7 +6416,7 @@ nfs4_retry_setlk(struct nfs4_state *state, int cmd, struct file_lock *request) .inode = state->inode, .owner = &owner, .notified = false }; - wait_queue_t wait; + wait_queue_entry_t wait; /* Don't bother with waitqueue if we don't expect a callback */ if (!test_bit(NFS_STATE_MAY_NOTIFY_LOCK, &state->flags)) @@ -8416,6 +8417,7 @@ static void nfs4_layoutget_release(void *calldata) size_t max_pages = max_response_pages(server); dprintk("--> %s\n", __func__); + nfs4_sequence_free_slot(&lgp->res.seq_res); nfs4_free_pages(lgp->args.layout.pages, max_pages); pnfs_put_layout_hdr(NFS_I(inode)->layout); put_nfs_open_context(lgp->args.ctx); @@ -8490,7 +8492,6 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout, gfp_t gfp_flags) /* if layoutp->len is 0, nfs4_layoutget_prepare called rpc_exit */ if (status == 0 && lgp->res.layoutp->len) lseg = pnfs_layout_process(lgp); - nfs4_sequence_free_slot(&lgp->res.seq_res); rpc_put_task(task); dprintk("<-- %s status=%d\n", __func__, status); if (status) diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index b34de036501b..cbf82b0d4467 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -2134,6 +2134,8 @@ again: put_rpccred(cred); switch (status) { case 0: + case -EINTR: + case -ERESTARTSYS: break; case -ETIMEDOUT: if (clnt->cl_softrtry) diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index fb5213afc854..c862c2489df0 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -219,6 +219,9 @@ static int nfsd4_scsi_identify_device(struct block_device *bdev, u8 *buf, *d, type, assoc; int error; + if (WARN_ON_ONCE(!blk_queue_scsi_passthrough(q))) + return -EINVAL; + buf = kzalloc(bufflen, GFP_KERNEL); if (!buf) return -ENOMEM; @@ -229,7 +232,6 @@ static int nfsd4_scsi_identify_device(struct block_device *bdev, goto out_free_buf; } req = scsi_req(rq); - scsi_req_init(rq); error = blk_rq_map_kern(q, rq, buf, bufflen, GFP_KERNEL); if (error) diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index e71f11b1a180..3bc08c394a3f 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -486,7 +486,7 @@ secinfo_parse(char **mesg, char *buf, struct svc_export *exp) { return 0; } #endif static inline int -uuid_parse(char **mesg, char *buf, unsigned char **puuid) +nfsd_uuid_parse(char **mesg, char *buf, unsigned char **puuid) { int len; @@ -586,7 +586,7 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) if (strcmp(buf, "fsloc") == 0) err = fsloc_parse(&mesg, buf, &exp.ex_fslocs); else if (strcmp(buf, "uuid") == 0) - err = uuid_parse(&mesg, buf, &exp.ex_uuid); + err = nfsd_uuid_parse(&mesg, buf, &exp.ex_uuid); else if (strcmp(buf, "secinfo") == 0) err = secinfo_parse(&mesg, buf, &exp); else diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c index 6f87b2ac1aeb..e73c86d9855c 100644 --- a/fs/nilfs2/segbuf.c +++ b/fs/nilfs2/segbuf.c @@ -338,7 +338,7 @@ static void nilfs_end_bio_write(struct bio *bio) { struct nilfs_segment_buffer *segbuf = bio->bi_private; - if (bio->bi_error) + if (bio->bi_status) atomic_inc(&segbuf->sb_err); bio_put(bio); diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index febed1217b3f..70ded52dc1dd 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -2161,7 +2161,7 @@ void nilfs_flush_segment(struct super_block *sb, ino_t ino) } struct nilfs_segctor_wait_request { - wait_queue_t wq; + wait_queue_entry_t wq; __u32 seq; int err; atomic_t done; @@ -2206,8 +2206,7 @@ static void nilfs_segctor_wakeup(struct nilfs_sc_info *sci, int err) unsigned long flags; spin_lock_irqsave(&sci->sc_wait_request.lock, flags); - list_for_each_entry_safe(wrq, n, &sci->sc_wait_request.task_list, - wq.task_list) { + list_for_each_entry_safe(wrq, n, &sci->sc_wait_request.head, wq.entry) { if (!atomic_read(&wrq->done) && nilfs_cnt32_ge(sci->sc_seq_done, wrq->seq)) { wrq->err = err; diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 0da0332725aa..ffe003982d95 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -516,9 +516,9 @@ static void o2hb_bio_end_io(struct bio *bio) { struct o2hb_bio_wait_ctxt *wc = bio->bi_private; - if (bio->bi_error) { - mlog(ML_ERROR, "IO Error %d\n", bio->bi_error); - wc->wc_error = bio->bi_error; + if (bio->bi_status) { + mlog(ML_ERROR, "IO Error %d\n", bio->bi_status); + wc->wc_error = blk_status_to_errno(bio->bi_status); } o2hb_bio_wait_dec(wc, 1); diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 3b7c937a36b5..4689940a953c 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -2591,6 +2591,10 @@ void ocfs2_inode_unlock_tracker(struct inode *inode, struct ocfs2_lock_res *lockres; lockres = &OCFS2_I(inode)->ip_inode_lockres; + /* had_lock means that the currect process already takes the cluster + * lock previously. If had_lock is 1, we have nothing to do here, and + * it will get unlocked where we got the lock. + */ if (!had_lock) { ocfs2_remove_holder(lockres, oh); ocfs2_inode_unlock(inode, ex); diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index ca1646fbcaef..83005f486451 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -2062,7 +2062,7 @@ static int ocfs2_initialize_super(struct super_block *sb, cbits = le32_to_cpu(di->id2.i_super.s_clustersize_bits); bbits = le32_to_cpu(di->id2.i_super.s_blocksize_bits); sb->s_maxbytes = ocfs2_max_file_offset(bbits, cbits); - memcpy(sb->s_uuid, di->id2.i_super.s_uuid, + memcpy(&sb->s_uuid, di->id2.i_super.s_uuid, sizeof(di->id2.i_super.s_uuid)); osb->osb_dx_mask = (1 << (cbits - bbits)) - 1; diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 3c5384d9b3a5..f70c3778d600 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -1328,20 +1328,21 @@ static int ocfs2_xattr_get(struct inode *inode, void *buffer, size_t buffer_size) { - int ret; + int ret, had_lock; struct buffer_head *di_bh = NULL; + struct ocfs2_lock_holder oh; - ret = ocfs2_inode_lock(inode, &di_bh, 0); - if (ret < 0) { - mlog_errno(ret); - return ret; + had_lock = ocfs2_inode_lock_tracker(inode, &di_bh, 0, &oh); + if (had_lock < 0) { + mlog_errno(had_lock); + return had_lock; } down_read(&OCFS2_I(inode)->ip_xattr_sem); ret = ocfs2_xattr_get_nolock(inode, di_bh, name_index, name, buffer, buffer_size); up_read(&OCFS2_I(inode)->ip_xattr_sem); - ocfs2_inode_unlock(inode, 0); + ocfs2_inode_unlock_tracker(inode, 0, &oh, had_lock); brelse(di_bh); @@ -3537,11 +3538,12 @@ int ocfs2_xattr_set(struct inode *inode, { struct buffer_head *di_bh = NULL; struct ocfs2_dinode *di; - int ret, credits, ref_meta = 0, ref_credits = 0; + int ret, credits, had_lock, ref_meta = 0, ref_credits = 0; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct inode *tl_inode = osb->osb_tl_inode; struct ocfs2_xattr_set_ctxt ctxt = { NULL, NULL, NULL, }; struct ocfs2_refcount_tree *ref_tree = NULL; + struct ocfs2_lock_holder oh; struct ocfs2_xattr_info xi = { .xi_name_index = name_index, @@ -3572,8 +3574,9 @@ int ocfs2_xattr_set(struct inode *inode, return -ENOMEM; } - ret = ocfs2_inode_lock(inode, &di_bh, 1); - if (ret < 0) { + had_lock = ocfs2_inode_lock_tracker(inode, &di_bh, 1, &oh); + if (had_lock < 0) { + ret = had_lock; mlog_errno(ret); goto cleanup_nolock; } @@ -3670,7 +3673,7 @@ cleanup: if (ret) mlog_errno(ret); } - ocfs2_inode_unlock(inode, 1); + ocfs2_inode_unlock_tracker(inode, 1, &oh, had_lock); cleanup_nolock: brelse(di_bh); brelse(xbs.xattr_bh); diff --git a/fs/open.c b/fs/open.c index cd0c5be8d012..3fe0c4aa7d27 100644 --- a/fs/open.c +++ b/fs/open.c @@ -759,6 +759,7 @@ static int do_dentry_open(struct file *f, likely(f->f_op->write || f->f_op->write_iter)) f->f_mode |= FMODE_CAN_WRITE; + f->f_write_hint = WRITE_LIFE_NOT_SET; f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC); file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping); diff --git a/fs/orangefs/orangefs-bufmap.c b/fs/orangefs/orangefs-bufmap.c index 83b506020718..038d67545d9f 100644 --- a/fs/orangefs/orangefs-bufmap.c +++ b/fs/orangefs/orangefs-bufmap.c @@ -46,8 +46,8 @@ static void run_down(struct slot_map *m) spin_lock(&m->q.lock); if (m->c != -1) { for (;;) { - if (likely(list_empty(&wait.task_list))) - __add_wait_queue_tail(&m->q, &wait); + if (likely(list_empty(&wait.entry))) + __add_wait_queue_entry_tail(&m->q, &wait); set_current_state(TASK_UNINTERRUPTIBLE); if (m->c == -1) @@ -84,8 +84,8 @@ static int wait_for_free(struct slot_map *m) do { long n = left, t; - if (likely(list_empty(&wait.task_list))) - __add_wait_queue_tail_exclusive(&m->q, &wait); + if (likely(list_empty(&wait.entry))) + __add_wait_queue_entry_tail_exclusive(&m->q, &wait); set_current_state(TASK_INTERRUPTIBLE); if (m->c > 0) @@ -108,8 +108,8 @@ static int wait_for_free(struct slot_map *m) left = -EINTR; } while (left > 0); - if (!list_empty(&wait.task_list)) - list_del(&wait.task_list); + if (!list_empty(&wait.entry)) + list_del(&wait.entry); else if (left <= 0 && waitqueue_active(&m->q)) __wake_up_locked_key(&m->q, TASK_INTERRUPTIBLE, NULL); __set_current_state(TASK_RUNNING); diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 7a44533f4bbf..e5869f91b3ab 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -233,7 +233,7 @@ int ovl_set_attr(struct dentry *upperdentry, struct kstat *stat) return err; } -static struct ovl_fh *ovl_encode_fh(struct dentry *lower, uuid_be *uuid) +static struct ovl_fh *ovl_encode_fh(struct dentry *lower, uuid_t *uuid) { struct ovl_fh *fh; int fh_type, fh_len, dwords; @@ -284,7 +284,6 @@ static int ovl_set_origin(struct dentry *dentry, struct dentry *lower, struct dentry *upper) { struct super_block *sb = lower->d_sb; - uuid_be *uuid = (uuid_be *) &sb->s_uuid; const struct ovl_fh *fh = NULL; int err; @@ -294,8 +293,8 @@ static int ovl_set_origin(struct dentry *dentry, struct dentry *lower, * up and a pure upper inode. */ if (sb->s_export_op && sb->s_export_op->fh_to_dentry && - uuid_be_cmp(*uuid, NULL_UUID_BE)) { - fh = ovl_encode_fh(lower, uuid); + !uuid_is_null(&sb->s_uuid)) { + fh = ovl_encode_fh(lower, &sb->s_uuid); if (IS_ERR(fh)) return PTR_ERR(fh); } @@ -330,15 +329,9 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir, .link = link }; - upper = lookup_one_len(dentry->d_name.name, upperdir, - dentry->d_name.len); - err = PTR_ERR(upper); - if (IS_ERR(upper)) - goto out; - err = security_inode_copy_up(dentry, &new_creds); if (err < 0) - goto out1; + goto out; if (new_creds) old_creds = override_creds(new_creds); @@ -362,7 +355,7 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir, } if (err) - goto out2; + goto out; if (S_ISREG(stat->mode)) { struct path upperpath; @@ -398,10 +391,23 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir, /* * Store identifier of lower inode in upper inode xattr to * allow lookup of the copy up origin inode. + * + * Don't set origin when we are breaking the association with a lower + * hard link. */ - err = ovl_set_origin(dentry, lowerpath->dentry, temp); - if (err) + if (S_ISDIR(stat->mode) || stat->nlink == 1) { + err = ovl_set_origin(dentry, lowerpath->dentry, temp); + if (err) + goto out_cleanup; + } + + upper = lookup_one_len(dentry->d_name.name, upperdir, + dentry->d_name.len); + if (IS_ERR(upper)) { + err = PTR_ERR(upper); + upper = NULL; goto out_cleanup; + } if (tmpfile) err = ovl_do_link(temp, udir, upper, true); @@ -416,17 +422,15 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir, /* Restore timestamps on parent (best effort) */ ovl_set_timestamps(upperdir, pstat); -out2: +out: dput(temp); -out1: dput(upper); -out: return err; out_cleanup: if (!tmpfile) ovl_cleanup(wdir, temp); - goto out2; + goto out; } /* diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index f3136c31e72a..de0d4f742f36 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -135,7 +135,7 @@ static struct dentry *ovl_get_origin(struct dentry *dentry, * Make sure that the stored uuid matches the uuid of the lower * layer where file handle will be decoded. */ - if (uuid_be_cmp(fh->uuid, *(uuid_be *) &mnt->mnt_sb->s_uuid)) + if (!uuid_equal(&fh->uuid, &mnt->mnt_sb->s_uuid)) goto out; origin = exportfs_decode_fh(mnt, (struct fid *)fh->fid, diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 0623cebeefff..10863b4105fa 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -56,7 +56,7 @@ struct ovl_fh { u8 len; /* size of this header + size of fid */ u8 flags; /* OVL_FH_FLAG_* */ u8 type; /* fid_type of fid */ - uuid_be uuid; /* uuid of filesystem */ + uuid_t uuid; /* uuid of filesystem */ u8 fid[0]; /* file identifier */ } __packed; diff --git a/fs/read_write.c b/fs/read_write.c index 19d4d88fa285..d591eeed061f 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -678,16 +678,10 @@ static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, struct kiocb kiocb; ssize_t ret; - if (flags & ~(RWF_HIPRI | RWF_DSYNC | RWF_SYNC)) - return -EOPNOTSUPP; - init_sync_kiocb(&kiocb, filp); - if (flags & RWF_HIPRI) - kiocb.ki_flags |= IOCB_HIPRI; - if (flags & RWF_DSYNC) - kiocb.ki_flags |= IOCB_DSYNC; - if (flags & RWF_SYNC) - kiocb.ki_flags |= (IOCB_DSYNC | IOCB_SYNC); + ret = kiocb_set_rw_flags(&kiocb, flags); + if (ret) + return ret; kiocb.ki_pos = *ppos; if (type == READ) diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index 39bb1e838d8d..a11d773e5ff3 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -2956,7 +2956,7 @@ void reiserfs_wait_on_write_block(struct super_block *s) static void queue_log_writer(struct super_block *s) { - wait_queue_t wait; + wait_queue_entry_t wait; struct reiserfs_journal *journal = SB_JOURNAL(s); set_bit(J_WRITERS_QUEUED, &journal->j_state); diff --git a/fs/select.c b/fs/select.c index d6c652a31e99..5b524a977d91 100644 --- a/fs/select.c +++ b/fs/select.c @@ -180,7 +180,7 @@ static struct poll_table_entry *poll_get_entry(struct poll_wqueues *p) return table->entry++; } -static int __pollwake(wait_queue_t *wait, unsigned mode, int sync, void *key) +static int __pollwake(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct poll_wqueues *pwq = wait->private; DECLARE_WAITQUEUE(dummy_wait, pwq->polling_task); @@ -206,7 +206,7 @@ static int __pollwake(wait_queue_t *wait, unsigned mode, int sync, void *key) return default_wake_function(&dummy_wait, mode, sync, key); } -static int pollwake(wait_queue_t *wait, unsigned mode, int sync, void *key) +static int pollwake(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct poll_table_entry *entry; diff --git a/fs/signalfd.c b/fs/signalfd.c index 7e3d71109f51..593b022ac11b 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -43,7 +43,7 @@ void signalfd_cleanup(struct sighand_struct *sighand) if (likely(!waitqueue_active(wqh))) return; - /* wait_queue_t->func(POLLFREE) should do remove_wait_queue() */ + /* wait_queue_entry_t->func(POLLFREE) should do remove_wait_queue() */ wake_up_poll(wqh, POLLHUP | POLLFREE); } diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c index 0315fea1d589..f80be4c5df9d 100644 --- a/fs/ufs/balloc.c +++ b/fs/ufs/balloc.c @@ -455,24 +455,14 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment, /* * allocate new block and move data */ - switch (fs32_to_cpu(sb, usb1->fs_optim)) { - case UFS_OPTSPACE: + if (fs32_to_cpu(sb, usb1->fs_optim) == UFS_OPTSPACE) { request = newcount; - if (uspi->s_minfree < 5 || uspi->cs_total.cs_nffree - > uspi->s_dsize * uspi->s_minfree / (2 * 100)) - break; - usb1->fs_optim = cpu_to_fs32(sb, UFS_OPTTIME); - break; - default: - usb1->fs_optim = cpu_to_fs32(sb, UFS_OPTTIME); - - case UFS_OPTTIME: + if (uspi->cs_total.cs_nffree < uspi->s_space_to_time) + usb1->fs_optim = cpu_to_fs32(sb, UFS_OPTTIME); + } else { request = uspi->s_fpb; - if (uspi->cs_total.cs_nffree < uspi->s_dsize * - (uspi->s_minfree - 2) / 100) - break; - usb1->fs_optim = cpu_to_fs32(sb, UFS_OPTTIME); - break; + if (uspi->cs_total.cs_nffree > uspi->s_time_to_space) + usb1->fs_optim = cpu_to_fs32(sb, UFS_OPTSPACE); } result = ufs_alloc_fragments (inode, cgno, goal, request, err); if (result) { diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index 9f4590261134..f36d6a53687d 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -566,10 +566,8 @@ static int ufs1_read_inode(struct inode *inode, struct ufs_inode *ufs_inode) */ inode->i_mode = mode = fs16_to_cpu(sb, ufs_inode->ui_mode); set_nlink(inode, fs16_to_cpu(sb, ufs_inode->ui_nlink)); - if (inode->i_nlink == 0) { - ufs_error (sb, "ufs_read_inode", "inode %lu has zero nlink\n", inode->i_ino); - return -1; - } + if (inode->i_nlink == 0) + return -ESTALE; /* * Linux now has 32-bit uid and gid, so we can support EFT. @@ -578,9 +576,9 @@ static int ufs1_read_inode(struct inode *inode, struct ufs_inode *ufs_inode) i_gid_write(inode, ufs_get_inode_gid(sb, ufs_inode)); inode->i_size = fs64_to_cpu(sb, ufs_inode->ui_size); - inode->i_atime.tv_sec = fs32_to_cpu(sb, ufs_inode->ui_atime.tv_sec); - inode->i_ctime.tv_sec = fs32_to_cpu(sb, ufs_inode->ui_ctime.tv_sec); - inode->i_mtime.tv_sec = fs32_to_cpu(sb, ufs_inode->ui_mtime.tv_sec); + inode->i_atime.tv_sec = (signed)fs32_to_cpu(sb, ufs_inode->ui_atime.tv_sec); + inode->i_ctime.tv_sec = (signed)fs32_to_cpu(sb, ufs_inode->ui_ctime.tv_sec); + inode->i_mtime.tv_sec = (signed)fs32_to_cpu(sb, ufs_inode->ui_mtime.tv_sec); inode->i_mtime.tv_nsec = 0; inode->i_atime.tv_nsec = 0; inode->i_ctime.tv_nsec = 0; @@ -614,10 +612,8 @@ static int ufs2_read_inode(struct inode *inode, struct ufs2_inode *ufs2_inode) */ inode->i_mode = mode = fs16_to_cpu(sb, ufs2_inode->ui_mode); set_nlink(inode, fs16_to_cpu(sb, ufs2_inode->ui_nlink)); - if (inode->i_nlink == 0) { - ufs_error (sb, "ufs_read_inode", "inode %lu has zero nlink\n", inode->i_ino); - return -1; - } + if (inode->i_nlink == 0) + return -ESTALE; /* * Linux now has 32-bit uid and gid, so we can support EFT. @@ -657,7 +653,7 @@ struct inode *ufs_iget(struct super_block *sb, unsigned long ino) struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi; struct buffer_head * bh; struct inode *inode; - int err; + int err = -EIO; UFSD("ENTER, ino %lu\n", ino); @@ -692,9 +688,10 @@ struct inode *ufs_iget(struct super_block *sb, unsigned long ino) err = ufs1_read_inode(inode, ufs_inode + ufs_inotofsbo(inode->i_ino)); } - + brelse(bh); if (err) goto bad_inode; + inode->i_version++; ufsi->i_lastfrag = (inode->i_size + uspi->s_fsize - 1) >> uspi->s_fshift; @@ -703,15 +700,13 @@ struct inode *ufs_iget(struct super_block *sb, unsigned long ino) ufs_set_inode_ops(inode); - brelse(bh); - UFSD("EXIT\n"); unlock_new_inode(inode); return inode; bad_inode: iget_failed(inode); - return ERR_PTR(-EIO); + return ERR_PTR(err); } static void ufs1_update_inode(struct inode *inode, struct ufs_inode *ufs_inode) diff --git a/fs/ufs/super.c b/fs/ufs/super.c index d5300adbfd79..0a4f58a5073c 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -1210,6 +1210,15 @@ magic_found: uspi->s_root_blocks = mul_u64_u32_div(uspi->s_dsize, uspi->s_minfree, 100); + if (uspi->s_minfree <= 5) { + uspi->s_time_to_space = ~0ULL; + uspi->s_space_to_time = 0; + usb1->fs_optim = cpu_to_fs32(sb, UFS_OPTSPACE); + } else { + uspi->s_time_to_space = (uspi->s_root_blocks / 2) + 1; + uspi->s_space_to_time = mul_u64_u32_div(uspi->s_dsize, + uspi->s_minfree - 2, 100) - 1; + } /* * Compute another frequently used values diff --git a/fs/ufs/ufs_fs.h b/fs/ufs/ufs_fs.h index 823d55a37586..150eef6f1233 100644 --- a/fs/ufs/ufs_fs.h +++ b/fs/ufs/ufs_fs.h @@ -792,6 +792,8 @@ struct ufs_sb_private_info { __s32 fs_magic; /* filesystem magic */ unsigned int s_dirblksize; __u64 s_root_blocks; + __u64 s_time_to_space; + __u64 s_space_to_time; }; /* diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 1d622f276e3a..6148ccd6cccf 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -81,7 +81,7 @@ struct userfaultfd_unmap_ctx { struct userfaultfd_wait_queue { struct uffd_msg msg; - wait_queue_t wq; + wait_queue_entry_t wq; struct userfaultfd_ctx *ctx; bool waken; }; @@ -91,7 +91,7 @@ struct userfaultfd_wake_range { unsigned long len; }; -static int userfaultfd_wake_function(wait_queue_t *wq, unsigned mode, +static int userfaultfd_wake_function(wait_queue_entry_t *wq, unsigned mode, int wake_flags, void *key) { struct userfaultfd_wake_range *range = key; @@ -129,7 +129,7 @@ static int userfaultfd_wake_function(wait_queue_t *wq, unsigned mode, * wouldn't be enough, the smp_mb__before_spinlock is * enough to avoid an explicit smp_mb() here. */ - list_del_init(&wq->task_list); + list_del_init(&wq->entry); out: return ret; } @@ -522,13 +522,13 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason) * and it's fine not to block on the spinlock. The uwq on this * kernel stack can be released after the list_del_init. */ - if (!list_empty_careful(&uwq.wq.task_list)) { + if (!list_empty_careful(&uwq.wq.entry)) { spin_lock(&ctx->fault_pending_wqh.lock); /* * No need of list_del_init(), the uwq on the stack * will be freed shortly anyway. */ - list_del(&uwq.wq.task_list); + list_del(&uwq.wq.entry); spin_unlock(&ctx->fault_pending_wqh.lock); } @@ -860,7 +860,7 @@ wakeup: static inline struct userfaultfd_wait_queue *find_userfault_in( wait_queue_head_t *wqh) { - wait_queue_t *wq; + wait_queue_entry_t *wq; struct userfaultfd_wait_queue *uwq; VM_BUG_ON(!spin_is_locked(&wqh->lock)); @@ -869,7 +869,7 @@ static inline struct userfaultfd_wait_queue *find_userfault_in( if (!waitqueue_active(wqh)) goto out; /* walk in reverse to provide FIFO behavior to read userfaults */ - wq = list_last_entry(&wqh->task_list, typeof(*wq), task_list); + wq = list_last_entry(&wqh->head, typeof(*wq), entry); uwq = container_of(wq, struct userfaultfd_wait_queue, wq); out: return uwq; @@ -1003,14 +1003,14 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, * changes __remove_wait_queue() to use * list_del_init() in turn breaking the * !list_empty_careful() check in - * handle_userfault(). The uwq->wq.task_list + * handle_userfault(). The uwq->wq.head list * must never be empty at any time during the * refile, or the waitqueue could disappear * from under us. The "wait_queue_head_t" * parameter of __remove_wait_queue() is unused * anyway. */ - list_del(&uwq->wq.task_list); + list_del(&uwq->wq.entry); __add_wait_queue(&ctx->fault_wqh, &uwq->wq); write_seqcount_end(&ctx->refile_seq); @@ -1032,7 +1032,7 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, fork_nctx = (struct userfaultfd_ctx *) (unsigned long) uwq->msg.arg.reserved.reserved1; - list_move(&uwq->wq.task_list, &fork_event); + list_move(&uwq->wq.entry, &fork_event); spin_unlock(&ctx->event_wqh.lock); ret = 0; break; @@ -1069,8 +1069,8 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, if (!list_empty(&fork_event)) { uwq = list_first_entry(&fork_event, typeof(*uwq), - wq.task_list); - list_del(&uwq->wq.task_list); + wq.entry); + list_del(&uwq->wq.entry); __add_wait_queue(&ctx->event_wqh, &uwq->wq); userfaultfd_event_complete(ctx, uwq); } @@ -1747,17 +1747,17 @@ static long userfaultfd_ioctl(struct file *file, unsigned cmd, static void userfaultfd_show_fdinfo(struct seq_file *m, struct file *f) { struct userfaultfd_ctx *ctx = f->private_data; - wait_queue_t *wq; + wait_queue_entry_t *wq; struct userfaultfd_wait_queue *uwq; unsigned long pending = 0, total = 0; spin_lock(&ctx->fault_pending_wqh.lock); - list_for_each_entry(wq, &ctx->fault_pending_wqh.task_list, task_list) { + list_for_each_entry(wq, &ctx->fault_pending_wqh.head, entry) { uwq = container_of(wq, struct userfaultfd_wait_queue, wq); pending++; total++; } - list_for_each_entry(wq, &ctx->fault_wqh.task_list, task_list) { + list_for_each_entry(wq, &ctx->fault_wqh.head, entry) { uwq = container_of(wq, struct userfaultfd_wait_queue, wq); total++; } diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile index 5c90f82b8f6b..a6e955bfead8 100644 --- a/fs/xfs/Makefile +++ b/fs/xfs/Makefile @@ -98,8 +98,7 @@ xfs-y += xfs_aops.o \ xfs_sysfs.o \ xfs_trans.o \ xfs_xattr.o \ - kmem.o \ - uuid.o + kmem.o # low-level transaction/log code xfs-y += xfs_log.o \ diff --git a/fs/xfs/uuid.c b/fs/xfs/uuid.c deleted file mode 100644 index b83f76b6d410..000000000000 --- a/fs/xfs/uuid.c +++ /dev/null @@ -1,63 +0,0 @@ -/* - * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc. - * All Rights Reserved. - * - * 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. - * - * This program is distributed in the hope that it would 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 the Free Software Foundation, - * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - */ -#include <xfs.h> - -/* IRIX interpretation of an uuid_t */ -typedef struct { - __be32 uu_timelow; - __be16 uu_timemid; - __be16 uu_timehi; - __be16 uu_clockseq; - __be16 uu_node[3]; -} xfs_uu_t; - -/* - * uuid_getnodeuniq - obtain the node unique fields of a UUID. - * - * This is not in any way a standard or condoned UUID function; - * it just something that's needed for user-level file handles. - */ -void -uuid_getnodeuniq(uuid_t *uuid, int fsid [2]) -{ - xfs_uu_t *uup = (xfs_uu_t *)uuid; - - fsid[0] = (be16_to_cpu(uup->uu_clockseq) << 16) | - be16_to_cpu(uup->uu_timemid); - fsid[1] = be32_to_cpu(uup->uu_timelow); -} - -int -uuid_is_nil(uuid_t *uuid) -{ - int i; - char *cp = (char *)uuid; - - if (uuid == NULL) - return 0; - /* implied check of version number here... */ - for (i = 0; i < sizeof *uuid; i++) - if (*cp++) return 0; /* not nil */ - return 1; /* is nil */ -} - -int -uuid_equal(uuid_t *uuid1, uuid_t *uuid2) -{ - return memcmp(uuid1, uuid2, sizeof(uuid_t)) ? 0 : 1; -} diff --git a/fs/xfs/uuid.h b/fs/xfs/uuid.h deleted file mode 100644 index 104db0f3bed6..000000000000 --- a/fs/xfs/uuid.h +++ /dev/null @@ -1,35 +0,0 @@ -/* - * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc. - * All Rights Reserved. - * - * 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. - * - * This program is distributed in the hope that it would 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 the Free Software Foundation, - * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - */ -#ifndef __XFS_SUPPORT_UUID_H__ -#define __XFS_SUPPORT_UUID_H__ - -typedef struct { - unsigned char __u_bits[16]; -} uuid_t; - -extern int uuid_is_nil(uuid_t *uuid); -extern int uuid_equal(uuid_t *uuid1, uuid_t *uuid2); -extern void uuid_getnodeuniq(uuid_t *uuid, int fsid [2]); - -static inline void -uuid_copy(uuid_t *dst, uuid_t *src) -{ - memcpy(dst, src, sizeof(uuid_t)); -} - -#endif /* __XFS_SUPPORT_UUID_H__ */ diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 09af0f7cd55e..d20c29b9c95b 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -276,7 +276,7 @@ xfs_end_io( struct xfs_inode *ip = XFS_I(ioend->io_inode); xfs_off_t offset = ioend->io_offset; size_t size = ioend->io_size; - int error = ioend->io_bio->bi_error; + int error; /* * Just clean up the in-memory strutures if the fs has been shut down. @@ -289,6 +289,7 @@ xfs_end_io( /* * Clean up any COW blocks on an I/O error. */ + error = blk_status_to_errno(ioend->io_bio->bi_status); if (unlikely(error)) { switch (ioend->io_type) { case XFS_IO_COW: @@ -332,7 +333,7 @@ xfs_end_bio( else if (ioend->io_append_trans) queue_work(mp->m_data_workqueue, &ioend->io_work); else - xfs_destroy_ioend(ioend, bio->bi_error); + xfs_destroy_ioend(ioend, blk_status_to_errno(bio->bi_status)); } STATIC int @@ -500,11 +501,12 @@ xfs_submit_ioend( * time. */ if (status) { - ioend->io_bio->bi_error = status; + ioend->io_bio->bi_status = errno_to_blk_status(status); bio_endio(ioend->io_bio); return status; } + ioend->io_bio->bi_write_hint = ioend->io_inode->i_write_hint; submit_bio(ioend->io_bio); return 0; } @@ -564,6 +566,7 @@ xfs_chain_bio( bio_chain(ioend->io_bio, new); bio_get(ioend->io_bio); /* for xfs_destroy_ioend */ ioend->io_bio->bi_opf = REQ_OP_WRITE | wbc_to_write_flags(wbc); + ioend->io_bio->bi_write_hint = ioend->io_inode->i_write_hint; submit_bio(ioend->io_bio); ioend->io_bio = new; } @@ -1316,9 +1319,12 @@ xfs_vm_bmap( * The swap code (ab-)uses ->bmap to get a block mapping and then * bypasseÑ• the file system for actual I/O. We really can't allow * that on reflinks inodes, so we have to skip out here. And yes, - * 0 is the magic code for a bmap error.. + * 0 is the magic code for a bmap error. + * + * Since we don't pass back blockdev info, we can't return bmap + * information for rt files either. */ - if (xfs_is_reflink_inode(ip)) + if (xfs_is_reflink_inode(ip) || XFS_IS_REALTIME_INODE(ip)) return 0; filemap_write_and_wait(mapping); diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 16d6a578fc16..438505f395e7 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1227,8 +1227,11 @@ xfs_buf_bio_end_io( * don't overwrite existing errors - otherwise we can lose errors on * buffers that require multiple bios to complete. */ - if (bio->bi_error) - cmpxchg(&bp->b_io_error, 0, bio->bi_error); + if (bio->bi_status) { + int error = blk_status_to_errno(bio->bi_status); + + cmpxchg(&bp->b_io_error, 0, error); + } if (!bp->b_error && xfs_buf_is_vmapped(bp) && (bp->b_flags & XBF_READ)) invalidate_kernel_vmap_range(bp->b_addr, xfs_buf_vmap_len(bp)); diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 5fb5a0958a14..17f27a2fb5e2 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -237,7 +237,11 @@ xfs_file_dax_read( if (!count) return 0; /* skip atime */ - xfs_ilock(ip, XFS_IOLOCK_SHARED); + if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED)) { + if (iocb->ki_flags & IOCB_NOWAIT) + return -EAGAIN; + xfs_ilock(ip, XFS_IOLOCK_SHARED); + } ret = dax_iomap_rw(iocb, to, &xfs_iomap_ops); xfs_iunlock(ip, XFS_IOLOCK_SHARED); @@ -541,7 +545,11 @@ xfs_file_dio_aio_write( iolock = XFS_IOLOCK_SHARED; } - xfs_ilock(ip, iolock); + if (!xfs_ilock_nowait(ip, iolock)) { + if (iocb->ki_flags & IOCB_NOWAIT) + return -EAGAIN; + xfs_ilock(ip, iolock); + } ret = xfs_file_aio_write_checks(iocb, from, &iolock); if (ret) @@ -553,9 +561,15 @@ xfs_file_dio_aio_write( * otherwise demote the lock if we had to take the exclusive lock * for other reasons in xfs_file_aio_write_checks. */ - if (unaligned_io) - inode_dio_wait(inode); - else if (iolock == XFS_IOLOCK_EXCL) { + if (unaligned_io) { + /* If we are going to wait for other DIO to finish, bail */ + if (iocb->ki_flags & IOCB_NOWAIT) { + if (atomic_read(&inode->i_dio_count)) + return -EAGAIN; + } else { + inode_dio_wait(inode); + } + } else if (iolock == XFS_IOLOCK_EXCL) { xfs_ilock_demote(ip, XFS_IOLOCK_EXCL); iolock = XFS_IOLOCK_SHARED; } @@ -585,7 +599,12 @@ xfs_file_dax_write( size_t count; loff_t pos; - xfs_ilock(ip, iolock); + if (!xfs_ilock_nowait(ip, iolock)) { + if (iocb->ki_flags & IOCB_NOWAIT) + return -EAGAIN; + xfs_ilock(ip, iolock); + } + ret = xfs_file_aio_write_checks(iocb, from, &iolock); if (ret) goto out; @@ -892,6 +911,7 @@ xfs_file_open( return -EFBIG; if (XFS_FORCED_SHUTDOWN(XFS_M(inode->i_sb))) return -EIO; + file->f_mode |= FMODE_AIO_NOWAIT; return 0; } diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 990210fcb9c3..b9c12e1cc23a 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -269,12 +269,12 @@ xfs_inew_wait( DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_INEW_BIT); do { - prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE); + prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); if (!xfs_iflags_test(ip, XFS_INEW)) break; schedule(); } while (true); - finish_wait(wq, &wait.wait); + finish_wait(wq, &wait.wq_entry); } /* diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index ec9826c56500..c0a1e840a588 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -622,12 +622,12 @@ __xfs_iflock( DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_IFLOCK_BIT); do { - prepare_to_wait_exclusive(wq, &wait.wait, TASK_UNINTERRUPTIBLE); + prepare_to_wait_exclusive(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); if (xfs_isiflocked(ip)) io_schedule(); } while (!xfs_iflock_nowait(ip)); - finish_wait(wq, &wait.wait); + finish_wait(wq, &wait.wq_entry); } STATIC uint @@ -2486,11 +2486,11 @@ __xfs_iunpin_wait( xfs_iunpin(ip); do { - prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE); + prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); if (xfs_ipincount(ip)) io_schedule(); } while (xfs_ipincount(ip)); - finish_wait(wq, &wait.wait); + finish_wait(wq, &wait.wq_entry); } void diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 08cb7d1a4a3a..013cc78d7daf 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -834,9 +834,7 @@ xfs_inode_item_format_convert( in_f->ilf_dsize = in_f32->ilf_dsize; in_f->ilf_ino = in_f32->ilf_ino; /* copy biggest field of ilf_u */ - memcpy(in_f->ilf_u.ilfu_uuid.__u_bits, - in_f32->ilf_u.ilfu_uuid.__u_bits, - sizeof(uuid_t)); + uuid_copy(&in_f->ilf_u.ilfu_uuid, &in_f32->ilf_u.ilfu_uuid); in_f->ilf_blkno = in_f32->ilf_blkno; in_f->ilf_len = in_f32->ilf_len; in_f->ilf_boffset = in_f32->ilf_boffset; @@ -851,9 +849,7 @@ xfs_inode_item_format_convert( in_f->ilf_dsize = in_f64->ilf_dsize; in_f->ilf_ino = in_f64->ilf_ino; /* copy biggest field of ilf_u */ - memcpy(in_f->ilf_u.ilfu_uuid.__u_bits, - in_f64->ilf_u.ilfu_uuid.__u_bits, - sizeof(uuid_t)); + uuid_copy(&in_f->ilf_u.ilfu_uuid, &in_f64->ilf_u.ilfu_uuid); in_f->ilf_blkno = in_f64->ilf_blkno; in_f->ilf_len = in_f64->ilf_len; in_f->ilf_boffset = in_f64->ilf_boffset; diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 94e5bdf7304c..05dc87e8c1f5 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -995,6 +995,11 @@ xfs_file_iomap_begin( lockmode = xfs_ilock_data_map_shared(ip); } + if ((flags & IOMAP_NOWAIT) && !(ip->i_df.if_flags & XFS_IFEXTENTS)) { + error = -EAGAIN; + goto out_unlock; + } + ASSERT(offset <= mp->m_super->s_maxbytes); if ((xfs_fsize_t)offset + length > mp->m_super->s_maxbytes) length = mp->m_super->s_maxbytes - offset; @@ -1016,6 +1021,15 @@ xfs_file_iomap_begin( if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) { if (flags & IOMAP_DIRECT) { + /* + * A reflinked inode will result in CoW alloc. + * FIXME: It could still overwrite on unshared extents + * and not need allocation. + */ + if (flags & IOMAP_NOWAIT) { + error = -EAGAIN; + goto out_unlock; + } /* may drop and re-acquire the ilock */ error = xfs_reflink_allocate_cow(ip, &imap, &shared, &lockmode); @@ -1033,6 +1047,14 @@ xfs_file_iomap_begin( if ((flags & IOMAP_WRITE) && imap_needs_alloc(inode, &imap, nimaps)) { /* + * If nowait is set bail since we are going to make + * allocations. + */ + if (flags & IOMAP_NOWAIT) { + error = -EAGAIN; + goto out_unlock; + } + /* * We cap the maximum length we map here to MAX_WRITEBACK_PAGES * pages to keep the chunks of work done where somewhat symmetric * with the work writeback does. This is a completely arbitrary diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h index 044fb0e15390..2d167fe643ec 100644 --- a/fs/xfs/xfs_linux.h +++ b/fs/xfs/xfs_linux.h @@ -19,6 +19,7 @@ #define __XFS_LINUX__ #include <linux/types.h> +#include <linux/uuid.h> /* * Kernel specific type declarations for XFS @@ -42,7 +43,6 @@ typedef __u32 xfs_nlink_t; #include "kmem.h" #include "mrlock.h" -#include "uuid.h" #include <linux/semaphore.h> #include <linux/mm.h> diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index cd0b077deb35..8cec1e5505a4 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -352,13 +352,13 @@ xlog_header_check_mount( { ASSERT(head->h_magicno == cpu_to_be32(XLOG_HEADER_MAGIC_NUM)); - if (uuid_is_nil(&head->h_fs_uuid)) { + if (uuid_is_null(&head->h_fs_uuid)) { /* * IRIX doesn't write the h_fs_uuid or h_fmt fields. If - * h_fs_uuid is nil, we assume this log was last mounted + * h_fs_uuid is null, we assume this log was last mounted * by IRIX and continue. */ - xfs_warn(mp, "nil uuid in log - IRIX style log"); + xfs_warn(mp, "null uuid in log - IRIX style log"); } else if (unlikely(!uuid_equal(&mp->m_sb.sb_uuid, &head->h_fs_uuid))) { xfs_warn(mp, "log has mismatched uuid - can't recover"); xlog_header_check_dump(mp, head); diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 2eaf81859166..d249546da15e 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -74,20 +74,19 @@ xfs_uuid_mount( int hole, i; /* Publish UUID in struct super_block */ - BUILD_BUG_ON(sizeof(mp->m_super->s_uuid) != sizeof(uuid_t)); - memcpy(&mp->m_super->s_uuid, uuid, sizeof(uuid_t)); + uuid_copy(&mp->m_super->s_uuid, uuid); if (mp->m_flags & XFS_MOUNT_NOUUID) return 0; - if (uuid_is_nil(uuid)) { - xfs_warn(mp, "Filesystem has nil UUID - can't mount"); + if (uuid_is_null(uuid)) { + xfs_warn(mp, "Filesystem has null UUID - can't mount"); return -EINVAL; } mutex_lock(&xfs_uuid_table_mutex); for (i = 0, hole = -1; i < xfs_uuid_table_size; i++) { - if (uuid_is_nil(&xfs_uuid_table[i])) { + if (uuid_is_null(&xfs_uuid_table[i])) { hole = i; continue; } @@ -124,7 +123,7 @@ xfs_uuid_unmount( mutex_lock(&xfs_uuid_table_mutex); for (i = 0; i < xfs_uuid_table_size; i++) { - if (uuid_is_nil(&xfs_uuid_table[i])) + if (uuid_is_null(&xfs_uuid_table[i])) continue; if (!uuid_equal(uuid, &xfs_uuid_table[i])) continue; @@ -793,7 +792,10 @@ xfs_mountfs( * Copies the low order bits of the timestamp and the randomly * set "sequence" number out of a UUID. */ - uuid_getnodeuniq(&sbp->sb_uuid, mp->m_fixedfsid); + mp->m_fixedfsid[0] = + (get_unaligned_be16(&sbp->sb_uuid.b[8]) << 16) | + get_unaligned_be16(&sbp->sb_uuid.b[4]); + mp->m_fixedfsid[1] = get_unaligned_be32(&sbp->sb_uuid.b[0]); mp->m_dmevmask = 0; /* not persistent; set after each mount */ diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 455a575f101d..97df4db13b2e 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1766,7 +1766,8 @@ STATIC int __init xfs_init_zones(void) { xfs_ioend_bioset = bioset_create(4 * MAX_BUF_PER_PAGE, - offsetof(struct xfs_ioend, io_inline_bio)); + offsetof(struct xfs_ioend, io_inline_bio), + BIOSET_NEED_BVECS); if (!xfs_ioend_bioset) goto out; diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 197f3fffc9a7..c1b163cb68b1 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -61,17 +61,18 @@ bool acpi_ata_match(acpi_handle handle); bool acpi_bay_match(acpi_handle handle); bool acpi_dock_match(acpi_handle handle); -bool acpi_check_dsm(acpi_handle handle, const u8 *uuid, u64 rev, u64 funcs); -union acpi_object *acpi_evaluate_dsm(acpi_handle handle, const u8 *uuid, +bool acpi_check_dsm(acpi_handle handle, const guid_t *guid, u64 rev, u64 funcs); +union acpi_object *acpi_evaluate_dsm(acpi_handle handle, const guid_t *guid, u64 rev, u64 func, union acpi_object *argv4); static inline union acpi_object * -acpi_evaluate_dsm_typed(acpi_handle handle, const u8 *uuid, u64 rev, u64 func, - union acpi_object *argv4, acpi_object_type type) +acpi_evaluate_dsm_typed(acpi_handle handle, const guid_t *guid, u64 rev, + u64 func, union acpi_object *argv4, + acpi_object_type type) { union acpi_object *obj; - obj = acpi_evaluate_dsm(handle, uuid, rev, func, argv4); + obj = acpi_evaluate_dsm(handle, guid, rev, func, argv4); if (obj && obj->type != type) { ACPI_FREE(obj); obj = NULL; @@ -210,7 +211,8 @@ struct acpi_device_flags { u32 of_compatible_ok:1; u32 coherent_dma:1; u32 cca_seen:1; - u32 reserved:20; + u32 spi_i2c_slave:1; + u32 reserved:19; }; /* File System */ diff --git a/include/dt-bindings/clock/sun50i-a64-ccu.h b/include/dt-bindings/clock/sun50i-a64-ccu.h index 370c0a0473fc..d66432c6e675 100644 --- a/include/dt-bindings/clock/sun50i-a64-ccu.h +++ b/include/dt-bindings/clock/sun50i-a64-ccu.h @@ -43,6 +43,8 @@ #ifndef _DT_BINDINGS_CLK_SUN50I_A64_H_ #define _DT_BINDINGS_CLK_SUN50I_A64_H_ +#define CLK_PLL_PERIPH0 11 + #define CLK_BUS_MIPI_DSI 28 #define CLK_BUS_CE 29 #define CLK_BUS_DMA 30 diff --git a/include/dt-bindings/clock/sun8i-h3-ccu.h b/include/dt-bindings/clock/sun8i-h3-ccu.h index c2afc41d6964..e139fe5c62ec 100644 --- a/include/dt-bindings/clock/sun8i-h3-ccu.h +++ b/include/dt-bindings/clock/sun8i-h3-ccu.h @@ -43,6 +43,8 @@ #ifndef _DT_BINDINGS_CLK_SUN8I_H3_H_ #define _DT_BINDINGS_CLK_SUN8I_H3_H_ +#define CLK_PLL_PERIPH0 9 + #define CLK_CPUX 14 #define CLK_BUS_CE 20 diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 137e4a3d89c5..cafdfb84ca28 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -26,6 +26,7 @@ #include <linux/resource_ext.h> #include <linux/device.h> #include <linux/property.h> +#include <linux/uuid.h> #ifndef _LINUX #define _LINUX @@ -457,7 +458,6 @@ struct acpi_osc_context { struct acpi_buffer ret; /* free by caller if success */ }; -acpi_status acpi_str_to_uuid(char *str, u8 *uuid); acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); /* Indexes into _OSC Capabilities Buffer (DWORDs 2 & 3 are device-specific) */ @@ -741,7 +741,7 @@ static inline bool acpi_driver_match_device(struct device *dev, } static inline union acpi_object *acpi_evaluate_dsm(acpi_handle handle, - const u8 *uuid, + const guid_t *guid, int rev, int func, union acpi_object *argv4) { diff --git a/include/linux/bcm47xx_nvram.h b/include/linux/bcm47xx_nvram.h index 2793652fbf66..a414a2b53e41 100644 --- a/include/linux/bcm47xx_nvram.h +++ b/include/linux/bcm47xx_nvram.h @@ -8,6 +8,7 @@ #ifndef __BCM47XX_NVRAM_H #define __BCM47XX_NVRAM_H +#include <linux/errno.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/vmalloc.h> diff --git a/include/linux/bio.h b/include/linux/bio.h index d1b04b0e99cf..664a27da276d 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -118,7 +118,6 @@ static inline void *bio_data(struct bio *bio) /* * will die */ -#define bio_to_phys(bio) (page_to_phys(bio_page((bio))) + (unsigned long) bio_offset((bio))) #define bvec_to_phys(bv) (page_to_phys((bv)->bv_page) + (unsigned long) (bv)->bv_offset) /* @@ -373,8 +372,11 @@ static inline struct bio *bio_next_split(struct bio *bio, int sectors, return bio_split(bio, sectors, gfp, bs); } -extern struct bio_set *bioset_create(unsigned int, unsigned int); -extern struct bio_set *bioset_create_nobvec(unsigned int, unsigned int); +extern struct bio_set *bioset_create(unsigned int, unsigned int, int flags); +enum { + BIOSET_NEED_BVECS = BIT(0), + BIOSET_NEED_RESCUER = BIT(1), +}; extern void bioset_free(struct bio_set *); extern mempool_t *biovec_create_pool(int pool_entries); @@ -392,11 +394,6 @@ static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs) return bio_alloc_bioset(gfp_mask, nr_iovecs, fs_bio_set); } -static inline struct bio *bio_clone(struct bio *bio, gfp_t gfp_mask) -{ - return bio_clone_bioset(bio, gfp_mask, fs_bio_set); -} - static inline struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned int nr_iovecs) { return bio_alloc_bioset(gfp_mask, nr_iovecs, NULL); @@ -414,7 +411,13 @@ extern void bio_endio(struct bio *); static inline void bio_io_error(struct bio *bio) { - bio->bi_error = -EIO; + bio->bi_status = BLK_STS_IOERR; + bio_endio(bio); +} + +static inline void bio_wouldblock_error(struct bio *bio) +{ + bio->bi_status = BLK_STS_AGAIN; bio_endio(bio); } @@ -426,6 +429,7 @@ extern void bio_advance(struct bio *, unsigned); extern void bio_init(struct bio *bio, struct bio_vec *table, unsigned short max_vecs); +extern void bio_uninit(struct bio *); extern void bio_reset(struct bio *); void bio_chain(struct bio *, struct bio *); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index fcd641032f8d..14542308d25b 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -33,14 +33,12 @@ struct blk_mq_hw_ctx { struct blk_mq_ctx **ctxs; unsigned int nr_ctx; - wait_queue_t dispatch_wait; + wait_queue_entry_t dispatch_wait; atomic_t wait_index; struct blk_mq_tags *tags; struct blk_mq_tags *sched_tags; - struct srcu_struct queue_rq_srcu; - unsigned long queued; unsigned long run; #define BLK_MQ_MAX_DISPATCH_ORDER 7 @@ -62,6 +60,9 @@ struct blk_mq_hw_ctx { struct dentry *debugfs_dir; struct dentry *sched_debugfs_dir; #endif + + /* Must be the last member - see also blk_mq_hw_ctx_size(). */ + struct srcu_struct queue_rq_srcu[0]; }; struct blk_mq_tag_set { @@ -87,7 +88,8 @@ struct blk_mq_queue_data { bool last; }; -typedef int (queue_rq_fn)(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *); +typedef blk_status_t (queue_rq_fn)(struct blk_mq_hw_ctx *, + const struct blk_mq_queue_data *); typedef enum blk_eh_timer_return (timeout_fn)(struct request *, bool); typedef int (init_hctx_fn)(struct blk_mq_hw_ctx *, void *, unsigned int); typedef void (exit_hctx_fn)(struct blk_mq_hw_ctx *, unsigned int); @@ -142,6 +144,8 @@ struct blk_mq_ops { init_request_fn *init_request; exit_request_fn *exit_request; reinit_request_fn *reinit_request; + /* Called from inside blk_get_request() */ + void (*initialize_rq_fn)(struct request *rq); map_queues_fn *map_queues; @@ -155,10 +159,6 @@ struct blk_mq_ops { }; enum { - BLK_MQ_RQ_QUEUE_OK = 0, /* queued fine */ - BLK_MQ_RQ_QUEUE_BUSY = 1, /* requeue IO for later */ - BLK_MQ_RQ_QUEUE_ERROR = 2, /* end IO with error */ - BLK_MQ_F_SHOULD_MERGE = 1 << 0, BLK_MQ_F_TAG_SHARED = 1 << 1, BLK_MQ_F_SG_MERGE = 1 << 2, @@ -204,10 +204,10 @@ enum { BLK_MQ_REQ_INTERNAL = (1 << 2), /* allocate internal/sched tag */ }; -struct request *blk_mq_alloc_request(struct request_queue *q, int rw, +struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op, unsigned int flags); -struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int op, - unsigned int flags, unsigned int hctx_idx); +struct request *blk_mq_alloc_request_hctx(struct request_queue *q, + unsigned int op, unsigned int flags, unsigned int hctx_idx); struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag); enum { @@ -230,8 +230,8 @@ static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag) int blk_mq_request_started(struct request *rq); void blk_mq_start_request(struct request *rq); -void blk_mq_end_request(struct request *rq, int error); -void __blk_mq_end_request(struct request *rq, int error); +void blk_mq_end_request(struct request *rq, blk_status_t error); +void __blk_mq_end_request(struct request *rq, blk_status_t error); void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list); void blk_mq_add_to_requeue_list(struct request *rq, bool at_head, @@ -247,6 +247,8 @@ void blk_mq_stop_hw_queues(struct request_queue *q); void blk_mq_start_hw_queues(struct request_queue *q); void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async); +void blk_mq_quiesce_queue(struct request_queue *q); +void blk_mq_unquiesce_queue(struct request_queue *q); void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_run_hw_queues(struct request_queue *q, bool async); @@ -264,6 +266,8 @@ int blk_mq_reinit_tagset(struct blk_mq_tag_set *set); int blk_mq_map_queues(struct blk_mq_tag_set *set); void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues); +void blk_mq_quiesce_queue_nowait(struct request_queue *q); + /* * Driver command data is immediately after the request. So subtract request * size to get back to the original request, add request size to get the PDU. diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 61339bc44400..d2eb87c84d82 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -17,6 +17,27 @@ struct io_context; struct cgroup_subsys_state; typedef void (bio_end_io_t) (struct bio *); +/* + * Block error status values. See block/blk-core:blk_errors for the details. + */ +typedef u8 __bitwise blk_status_t; +#define BLK_STS_OK 0 +#define BLK_STS_NOTSUPP ((__force blk_status_t)1) +#define BLK_STS_TIMEOUT ((__force blk_status_t)2) +#define BLK_STS_NOSPC ((__force blk_status_t)3) +#define BLK_STS_TRANSPORT ((__force blk_status_t)4) +#define BLK_STS_TARGET ((__force blk_status_t)5) +#define BLK_STS_NEXUS ((__force blk_status_t)6) +#define BLK_STS_MEDIUM ((__force blk_status_t)7) +#define BLK_STS_PROTECTION ((__force blk_status_t)8) +#define BLK_STS_RESOURCE ((__force blk_status_t)9) +#define BLK_STS_IOERR ((__force blk_status_t)10) + +/* hack for device mapper, don't use elsewhere: */ +#define BLK_STS_DM_REQUEUE ((__force blk_status_t)11) + +#define BLK_STS_AGAIN ((__force blk_status_t)12) + struct blk_issue_stat { u64 stat; }; @@ -28,13 +49,14 @@ struct blk_issue_stat { struct bio { struct bio *bi_next; /* request queue link */ struct block_device *bi_bdev; - int bi_error; + blk_status_t bi_status; unsigned int bi_opf; /* bottom bits req flags, * top bits REQ_OP. Use * accessors. */ unsigned short bi_flags; /* status, etc and bvec pool number */ unsigned short bi_ioprio; + unsigned short bi_write_hint; struct bvec_iter bi_iter; @@ -205,6 +227,7 @@ enum req_flag_bits { /* command specific flags for REQ_OP_WRITE_ZEROES: */ __REQ_NOUNMAP, /* do not free blocks when zeroing */ + __REQ_NOWAIT, /* Don't wait if request will block */ __REQ_NR_BITS, /* stops here */ }; @@ -223,6 +246,7 @@ enum req_flag_bits { #define REQ_BACKGROUND (1ULL << __REQ_BACKGROUND) #define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP) +#define REQ_NOWAIT (1ULL << __REQ_NOWAIT) #define REQ_FAILFAST_MASK \ (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index b74a3edcb3da..25f6a0cb27d3 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -55,7 +55,7 @@ struct blk_stat_callback; */ #define BLKCG_MAX_POLS 3 -typedef void (rq_end_io_fn)(struct request *, int); +typedef void (rq_end_io_fn)(struct request *, blk_status_t); #define BLK_RL_SYNCFULL (1U << 0) #define BLK_RL_ASYNCFULL (1U << 1) @@ -225,6 +225,8 @@ struct request { unsigned int extra_len; /* length of alignment and padding */ + unsigned short write_hint; + unsigned long deadline; struct list_head timeout_list; @@ -391,6 +393,8 @@ struct request_queue { int nr_rqs[2]; /* # allocated [a]sync rqs */ int nr_rqs_elvpriv; /* # allocated rqs w/ elvpriv */ + atomic_t shared_hctx_restart; + struct blk_queue_stats *stats; struct rq_wb *rq_wb; @@ -410,8 +414,12 @@ struct request_queue { rq_timed_out_fn *rq_timed_out_fn; dma_drain_needed_fn *dma_drain_needed; lld_busy_fn *lld_busy_fn; + /* Called just after a request is allocated */ init_rq_fn *init_rq_fn; + /* Called just before a request is freed */ exit_rq_fn *exit_rq_fn; + /* Called from inside blk_get_request() */ + void (*initialize_rq_fn)(struct request *rq); const struct blk_mq_ops *mq_ops; @@ -588,6 +596,9 @@ struct request_queue { void *rq_alloc_data; struct work_struct release_work; + +#define BLK_MAX_WRITE_HINTS 5 + u64 write_hints[BLK_MAX_WRITE_HINTS]; }; #define QUEUE_FLAG_QUEUED 1 /* uses generic tag queueing */ @@ -620,6 +631,8 @@ struct request_queue { #define QUEUE_FLAG_STATS 27 /* track rq completion times */ #define QUEUE_FLAG_POLL_STATS 28 /* collecting stats for hybrid polling */ #define QUEUE_FLAG_REGISTERED 29 /* queue has been registered to a disk */ +#define QUEUE_FLAG_SCSI_PASSTHROUGH 30 /* queue supports SCSI commands */ +#define QUEUE_FLAG_QUIESCED 31 /* queue has been quiesced */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_STACKABLE) | \ @@ -631,6 +644,13 @@ struct request_queue { (1 << QUEUE_FLAG_SAME_COMP) | \ (1 << QUEUE_FLAG_POLL)) +/* + * @q->queue_lock is set while a queue is being initialized. Since we know + * that no other threads access the queue object before @q->queue_lock has + * been set, it is safe to manipulate queue flags without holding the + * queue_lock if @q->queue_lock == NULL. See also blk_alloc_queue_node() and + * blk_init_allocated_queue(). + */ static inline void queue_lockdep_assert_held(struct request_queue *q) { if (q->queue_lock) @@ -710,10 +730,13 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) #define blk_queue_secure_erase(q) \ (test_bit(QUEUE_FLAG_SECERASE, &(q)->queue_flags)) #define blk_queue_dax(q) test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags) +#define blk_queue_scsi_passthrough(q) \ + test_bit(QUEUE_FLAG_SCSI_PASSTHROUGH, &(q)->queue_flags) #define blk_noretry_request(rq) \ ((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \ REQ_FAILFAST_DRIVER)) +#define blk_queue_quiesced(q) test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags) static inline bool blk_account_rq(struct request *rq) { @@ -812,7 +835,8 @@ static inline bool rq_mergeable(struct request *rq) static inline bool blk_write_same_mergeable(struct bio *a, struct bio *b) { - if (bio_data(a) == bio_data(b)) + if (bio_page(a) == bio_page(b) && + bio_offset(a) == bio_offset(b)) return true; return false; @@ -860,19 +884,6 @@ extern unsigned long blk_max_low_pfn, blk_max_pfn; #define BLK_DEFAULT_SG_TIMEOUT (60 * HZ) #define BLK_MIN_SG_TIMEOUT (7 * HZ) -#ifdef CONFIG_BOUNCE -extern int init_emergency_isa_pool(void); -extern void blk_queue_bounce(struct request_queue *q, struct bio **bio); -#else -static inline int init_emergency_isa_pool(void) -{ - return 0; -} -static inline void blk_queue_bounce(struct request_queue *q, struct bio **bio) -{ -} -#endif /* CONFIG_MMU */ - struct rq_map_data { struct page **pages; int page_order; @@ -931,7 +942,8 @@ extern void blk_rq_init(struct request_queue *q, struct request *rq); extern void blk_init_request_from_bio(struct request *req, struct bio *bio); extern void blk_put_request(struct request *); extern void __blk_put_request(struct request_queue *, struct request *); -extern struct request *blk_get_request(struct request_queue *, int, gfp_t); +extern struct request *blk_get_request(struct request_queue *, unsigned int op, + gfp_t gfp_mask); extern void blk_requeue_request(struct request_queue *, struct request *); extern int blk_lld_busy(struct request_queue *q); extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src, @@ -939,12 +951,11 @@ extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src, int (*bio_ctr)(struct bio *, struct bio *, void *), void *data); extern void blk_rq_unprep_clone(struct request *rq); -extern int blk_insert_cloned_request(struct request_queue *q, +extern blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq); extern int blk_rq_append_bio(struct request *rq, struct bio *bio); extern void blk_delay_queue(struct request_queue *, unsigned long); -extern void blk_queue_split(struct request_queue *, struct bio **, - struct bio_set *); +extern void blk_queue_split(struct request_queue *, struct bio **); extern void blk_recount_segments(struct request_queue *, struct bio *); extern int scsi_verify_blk_ioctl(struct block_device *, unsigned int); extern int scsi_cmd_blk_ioctl(struct block_device *, fmode_t, @@ -965,7 +976,6 @@ extern void __blk_run_queue(struct request_queue *q); extern void __blk_run_queue_uncond(struct request_queue *q); extern void blk_run_queue(struct request_queue *); extern void blk_run_queue_async(struct request_queue *q); -extern void blk_mq_quiesce_queue(struct request_queue *q); extern int blk_rq_map_user(struct request_queue *, struct request *, struct rq_map_data *, void __user *, unsigned long, gfp_t); @@ -979,6 +989,9 @@ extern void blk_execute_rq(struct request_queue *, struct gendisk *, extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *, struct request *, int, rq_end_io_fn *); +int blk_status_to_errno(blk_status_t status); +blk_status_t errno_to_blk_status(int errno); + bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie); static inline struct request_queue *bdev_get_queue(struct block_device *bdev) @@ -1111,16 +1124,16 @@ extern struct request *blk_fetch_request(struct request_queue *q); * blk_end_request() for parts of the original function. * This prevents code duplication in drivers. */ -extern bool blk_update_request(struct request *rq, int error, +extern bool blk_update_request(struct request *rq, blk_status_t error, unsigned int nr_bytes); -extern void blk_finish_request(struct request *rq, int error); -extern bool blk_end_request(struct request *rq, int error, +extern void blk_finish_request(struct request *rq, blk_status_t error); +extern bool blk_end_request(struct request *rq, blk_status_t error, unsigned int nr_bytes); -extern void blk_end_request_all(struct request *rq, int error); -extern bool __blk_end_request(struct request *rq, int error, +extern void blk_end_request_all(struct request *rq, blk_status_t error); +extern bool __blk_end_request(struct request *rq, blk_status_t error, unsigned int nr_bytes); -extern void __blk_end_request_all(struct request *rq, int error); -extern bool __blk_end_request_cur(struct request *rq, int error); +extern void __blk_end_request_all(struct request *rq, blk_status_t error); +extern bool __blk_end_request_cur(struct request *rq, blk_status_t error); extern void blk_complete_request(struct request *); extern void __blk_complete_request(struct request *); @@ -1372,11 +1385,6 @@ enum blk_default_limits { #define blkdev_entry_to_request(entry) list_entry((entry), struct request, queuelist) -static inline unsigned long queue_bounce_pfn(struct request_queue *q) -{ - return q->limits.bounce_pfn; -} - static inline unsigned long queue_segment_boundary(struct request_queue *q) { return q->limits.seg_boundary_mask; @@ -1778,7 +1786,7 @@ struct blk_integrity_iter { const char *disk_name; }; -typedef int (integrity_processing_fn) (struct blk_integrity_iter *); +typedef blk_status_t (integrity_processing_fn) (struct blk_integrity_iter *); struct blk_integrity_profile { integrity_processing_fn *generate_fn; diff --git a/include/linux/cleancache.h b/include/linux/cleancache.h index fccf7f44139d..bbb3712dd892 100644 --- a/include/linux/cleancache.h +++ b/include/linux/cleancache.h @@ -27,7 +27,7 @@ struct cleancache_filekey { struct cleancache_ops { int (*init_fs)(size_t); - int (*init_shared_fs)(char *uuid, size_t); + int (*init_shared_fs)(uuid_t *uuid, size_t); int (*get_page)(int, struct cleancache_filekey, pgoff_t, struct page *); void (*put_page)(int, struct cleancache_filekey, diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index d92bd83eed9f..a78cb1848e65 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -96,6 +96,7 @@ struct clocksource { void (*suspend)(struct clocksource *cs); void (*resume)(struct clocksource *cs); void (*mark_unstable)(struct clocksource *cs); + void (*tick_stable)(struct clocksource *cs); /* private: */ #ifdef CONFIG_CLOCKSOURCE_WATCHDOG diff --git a/include/linux/compiler.h b/include/linux/compiler.h index f8110051188f..707242fdbb89 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -17,11 +17,7 @@ # define __release(x) __context__(x,-1) # define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0) # define __percpu __attribute__((noderef, address_space(3))) -#ifdef CONFIG_SPARSE_RCU_POINTER # define __rcu __attribute__((noderef, address_space(4))) -#else /* CONFIG_SPARSE_RCU_POINTER */ -# define __rcu -#endif /* CONFIG_SPARSE_RCU_POINTER */ # define __private __attribute__((noderef)) extern void __chk_user_ptr(const volatile void __user *); extern void __chk_io_ptr(const volatile void __iomem *); diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 2404ad238c0b..4bf4479a3a80 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -236,6 +236,23 @@ unsigned int cpumask_local_spread(unsigned int i, int node); (cpu) = cpumask_next_zero((cpu), (mask)), \ (cpu) < nr_cpu_ids;) +extern int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap); + +/** + * for_each_cpu_wrap - iterate over every cpu in a mask, starting at a specified location + * @cpu: the (optionally unsigned) integer iterator + * @mask: the cpumask poiter + * @start: the start location + * + * The implementation does not assume any bit in @mask is set (including @start). + * + * After the loop, cpu is >= nr_cpu_ids. + */ +#define for_each_cpu_wrap(cpu, mask, start) \ + for ((cpu) = cpumask_next_wrap((start)-1, (mask), (start), false); \ + (cpu) < nr_cpumask_bits; \ + (cpu) = cpumask_next_wrap((cpu), (mask), (start), true)) + /** * for_each_cpu_and - iterate over every cpu in both masks * @cpu: the (optionally unsigned) integer iterator @@ -276,6 +293,12 @@ static inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } +static inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) +{ + __set_bit(cpumask_check(cpu), cpumask_bits(dstp)); +} + + /** * cpumask_clear_cpu - clear a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) @@ -286,6 +309,11 @@ static inline void cpumask_clear_cpu(int cpu, struct cpumask *dstp) clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); } +static inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp) +{ + __clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); +} + /** * cpumask_test_cpu - test for a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index f4c639c0c362..456da5017b32 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -72,9 +72,9 @@ typedef void (*dm_release_clone_request_fn) (struct request *clone); * 2 : The target wants to push back the io */ typedef int (*dm_endio_fn) (struct dm_target *ti, - struct bio *bio, int error); + struct bio *bio, blk_status_t *error); typedef int (*dm_request_endio_fn) (struct dm_target *ti, - struct request *clone, int error, + struct request *clone, blk_status_t error, union map_info *map_context); typedef void (*dm_presuspend_fn) (struct dm_target *ti); diff --git a/include/linux/efi.h b/include/linux/efi.h index ec36f42a2add..8269bcb8ccf7 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -137,6 +137,18 @@ struct efi_boot_memmap { #define EFI_CAPSULE_POPULATE_SYSTEM_TABLE 0x00020000 #define EFI_CAPSULE_INITIATE_RESET 0x00040000 +struct capsule_info { + efi_capsule_header_t header; + int reset_type; + long index; + size_t count; + size_t total_size; + phys_addr_t *pages; + size_t page_bytes_remain; +}; + +int __efi_capsule_setup_info(struct capsule_info *cap_info); + /* * Allocation types for calls to boottime->allocate_pages. */ @@ -1403,7 +1415,7 @@ extern int efi_capsule_supported(efi_guid_t guid, u32 flags, size_t size, int *reset); extern int efi_capsule_update(efi_capsule_header_t *capsule, - struct page **pages); + phys_addr_t *pages); #ifdef CONFIG_EFI_RUNTIME_MAP int efi_runtime_map_init(struct kobject *); diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 0e306c5a86d6..5bc8f8682a3e 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -104,8 +104,9 @@ struct elevator_mq_ops { int (*request_merge)(struct request_queue *q, struct request **, struct bio *); void (*request_merged)(struct request_queue *, struct request *, enum elv_merge); void (*requests_merged)(struct request_queue *, struct request *, struct request *); - struct request *(*get_request)(struct request_queue *, unsigned int, struct blk_mq_alloc_data *); - void (*put_request)(struct request *); + void (*limit_depth)(unsigned int, struct blk_mq_alloc_data *); + void (*prepare_request)(struct request *, struct bio *bio); + void (*finish_request)(struct request *); void (*insert_requests)(struct blk_mq_hw_ctx *, struct list_head *, bool); struct request *(*dispatch_request)(struct blk_mq_hw_ctx *); bool (*has_work)(struct blk_mq_hw_ctx *); @@ -114,8 +115,6 @@ struct elevator_mq_ops { void (*requeue_request)(struct request *); struct request *(*former_request)(struct request_queue *, struct request *); struct request *(*next_request)(struct request_queue *, struct request *); - int (*get_rq_priv)(struct request_queue *, struct request *, struct bio *); - void (*put_rq_priv)(struct request_queue *, struct request *); void (*init_icq)(struct io_cq *); void (*exit_icq)(struct io_cq *); }; diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index ff0b981f078e..9e4befd95bc7 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -37,7 +37,7 @@ struct eventfd_ctx *eventfd_ctx_fdget(int fd); struct eventfd_ctx *eventfd_ctx_fileget(struct file *file); __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n); ssize_t eventfd_ctx_read(struct eventfd_ctx *ctx, int no_wait, __u64 *cnt); -int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_t *wait, +int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait, __u64 *cnt); #else /* CONFIG_EVENTFD */ @@ -73,7 +73,7 @@ static inline ssize_t eventfd_ctx_read(struct eventfd_ctx *ctx, int no_wait, } static inline int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, - wait_queue_t *wait, __u64 *cnt) + wait_queue_entry_t *wait, __u64 *cnt) { return -ENOSYS; } diff --git a/include/linux/fs.h b/include/linux/fs.h index 803e5a9b2654..771fe1131467 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2,7 +2,7 @@ #define _LINUX_FS_H #include <linux/linkage.h> -#include <linux/wait.h> +#include <linux/wait_bit.h> #include <linux/kdev_t.h> #include <linux/dcache.h> #include <linux/path.h> @@ -20,6 +20,7 @@ #include <linux/rwsem.h> #include <linux/capability.h> #include <linux/semaphore.h> +#include <linux/fcntl.h> #include <linux/fiemap.h> #include <linux/rculist_bl.h> #include <linux/atomic.h> @@ -30,6 +31,7 @@ #include <linux/percpu-rwsem.h> #include <linux/workqueue.h> #include <linux/delayed_call.h> +#include <linux/uuid.h> #include <asm/byteorder.h> #include <uapi/linux/fs.h> @@ -142,6 +144,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)0x4000000) +/* File is capable of returning -EAGAIN if AIO will block */ +#define FMODE_AIO_NOWAIT ((__force fmode_t)0x8000000) + /* * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector * that indicates that they should check the contents of the iovec are @@ -261,6 +266,18 @@ struct page; struct address_space; struct writeback_control; +/* + * Write life time hint values. + */ +enum rw_hint { + WRITE_LIFE_NOT_SET = 0, + WRITE_LIFE_NONE = RWH_WRITE_LIFE_NONE, + WRITE_LIFE_SHORT = RWH_WRITE_LIFE_SHORT, + WRITE_LIFE_MEDIUM = RWH_WRITE_LIFE_MEDIUM, + WRITE_LIFE_LONG = RWH_WRITE_LIFE_LONG, + WRITE_LIFE_EXTREME = RWH_WRITE_LIFE_EXTREME, +}; + #define IOCB_EVENTFD (1 << 0) #define IOCB_APPEND (1 << 1) #define IOCB_DIRECT (1 << 2) @@ -268,6 +285,7 @@ struct writeback_control; #define IOCB_DSYNC (1 << 4) #define IOCB_SYNC (1 << 5) #define IOCB_WRITE (1 << 6) +#define IOCB_NOWAIT (1 << 7) struct kiocb { struct file *ki_filp; @@ -275,6 +293,7 @@ struct kiocb { void (*ki_complete)(struct kiocb *iocb, long ret, long ret2); void *private; int ki_flags; + enum rw_hint ki_hint; }; static inline bool is_sync_kiocb(struct kiocb *kiocb) @@ -282,16 +301,6 @@ static inline bool is_sync_kiocb(struct kiocb *kiocb) return kiocb->ki_complete == NULL; } -static inline int iocb_flags(struct file *file); - -static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) -{ - *kiocb = (struct kiocb) { - .ki_filp = filp, - .ki_flags = iocb_flags(filp), - }; -} - /* * "descriptor" for what we're up to with a read. * This allows us to use the same read code yet @@ -592,6 +601,7 @@ struct inode { spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ unsigned short i_bytes; unsigned int i_blkbits; + enum rw_hint i_write_hint; blkcnt_t i_blocks; #ifdef __NEED_I_SIZE_ORDERED @@ -846,6 +856,7 @@ struct file { * Must not be taken from IRQ context. */ spinlock_t f_lock; + enum rw_hint f_write_hint; atomic_long_t f_count; unsigned int f_flags; fmode_t f_mode; @@ -1021,8 +1032,6 @@ struct file_lock_context { #define OFFT_OFFSET_MAX INT_LIMIT(off_t) #endif -#include <linux/fcntl.h> - extern void send_sigio(struct fown_struct *fown, int fd, int band); /* @@ -1328,8 +1337,8 @@ struct super_block { struct sb_writers s_writers; - char s_id[32]; /* Informational name */ - u8 s_uuid[16]; /* UUID */ + char s_id[32]; /* Informational name */ + uuid_t s_uuid; /* UUID */ void *s_fs_info; /* Filesystem private info */ unsigned int s_max_links; @@ -1873,6 +1882,25 @@ static inline bool HAS_UNMAPPED_ID(struct inode *inode) return !uid_valid(inode->i_uid) || !gid_valid(inode->i_gid); } +static inline enum rw_hint file_write_hint(struct file *file) +{ + if (file->f_write_hint != WRITE_LIFE_NOT_SET) + return file->f_write_hint; + + return file_inode(file)->i_write_hint; +} + +static inline int iocb_flags(struct file *file); + +static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) +{ + *kiocb = (struct kiocb) { + .ki_filp = filp, + .ki_flags = iocb_flags(filp), + .ki_hint = file_write_hint(filp), + }; +} + /* * Inode state bits. Protected by inode->i_lock * @@ -2517,6 +2545,8 @@ extern int filemap_fdatawait(struct address_space *); extern void filemap_fdatawait_keep_errors(struct address_space *); extern int filemap_fdatawait_range(struct address_space *, loff_t lstart, loff_t lend); +extern bool filemap_range_has_page(struct address_space *, loff_t lstart, + loff_t lend); extern int filemap_write_and_wait(struct address_space *mapping); extern int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend); @@ -2843,7 +2873,7 @@ enum { DIO_SKIP_DIO_COUNT = 0x08, }; -void dio_end_io(struct bio *bio, int error); +void dio_end_io(struct bio *bio); ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, @@ -3056,6 +3086,25 @@ static inline int iocb_flags(struct file *file) return res; } +static inline int kiocb_set_rw_flags(struct kiocb *ki, int flags) +{ + if (unlikely(flags & ~RWF_SUPPORTED)) + return -EOPNOTSUPP; + + if (flags & RWF_NOWAIT) { + if (!(ki->ki_filp->f_mode & FMODE_AIO_NOWAIT)) + return -EOPNOTSUPP; + ki->ki_flags |= IOCB_NOWAIT; + } + if (flags & RWF_HIPRI) + ki->ki_flags |= IOCB_HIPRI; + if (flags & RWF_DSYNC) + ki->ki_flags |= IOCB_DSYNC; + if (flags & RWF_SYNC) + ki->ki_flags |= (IOCB_DSYNC | IOCB_SYNC); + return 0; +} + static inline ino_t parent_ino(struct dentry *dentry) { ino_t res; diff --git a/include/linux/genhd.h b/include/linux/genhd.h index acff9437e5c3..e619fae2f037 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -219,12 +219,6 @@ static inline struct gendisk *part_to_disk(struct hd_struct *part) return NULL; } -static inline int blk_part_pack_uuid(const u8 *uuid_str, u8 *to) -{ - uuid_be_to_bin(uuid_str, (uuid_be *)to); - return 0; -} - static inline int disk_max_parts(struct gendisk *disk) { if (disk->flags & GENHD_FL_EXT_DEVT) @@ -736,11 +730,6 @@ static inline dev_t blk_lookup_devt(const char *name, int partno) dev_t devt = MKDEV(0, 0); return devt; } - -static inline int blk_part_pack_uuid(const u8 *uuid_str, u8 *to) -{ - return -EINVAL; -} #endif /* CONFIG_BLOCK */ #endif /* _LINUX_GENHD_H */ diff --git a/include/linux/hashtable.h b/include/linux/hashtable.h index 661e5c2a8e2a..082dc1bd0801 100644 --- a/include/linux/hashtable.h +++ b/include/linux/hashtable.h @@ -167,7 +167,6 @@ static inline void hash_del_rcu(struct hlist_node *node) /** * hash_for_each_possible_rcu - iterate over all possible objects hashing to the * same bucket in an rcu enabled hashtable - * in a rcu enabled hashtable * @name: hashtable to iterate * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct diff --git a/include/linux/ide.h b/include/linux/ide.h index 6980ca322074..dc152e4b7f73 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -671,7 +671,7 @@ struct ide_port_ops { void (*init_dev)(ide_drive_t *); void (*set_pio_mode)(struct hwif_s *, ide_drive_t *); void (*set_dma_mode)(struct hwif_s *, ide_drive_t *); - int (*reset_poll)(ide_drive_t *); + blk_status_t (*reset_poll)(ide_drive_t *); void (*pre_reset)(ide_drive_t *); void (*resetproc)(ide_drive_t *); void (*maskproc)(ide_drive_t *, int); @@ -1092,7 +1092,7 @@ int generic_ide_ioctl(ide_drive_t *, struct block_device *, unsigned, unsigned l extern int ide_vlb_clk; extern int ide_pci_clk; -int ide_end_rq(ide_drive_t *, struct request *, int, unsigned int); +int ide_end_rq(ide_drive_t *, struct request *, blk_status_t, unsigned int); void ide_kill_rq(ide_drive_t *, struct request *); void __ide_set_handler(ide_drive_t *, ide_handler_t *, unsigned int); @@ -1123,7 +1123,7 @@ extern int ide_devset_execute(ide_drive_t *drive, const struct ide_devset *setting, int arg); void ide_complete_cmd(ide_drive_t *, struct ide_cmd *, u8, u8); -int ide_complete_rq(ide_drive_t *, int, unsigned int); +int ide_complete_rq(ide_drive_t *, blk_status_t, unsigned int); void ide_tf_readback(ide_drive_t *drive, struct ide_cmd *cmd); void ide_tf_dump(const char *, struct ide_cmd *); diff --git a/include/linux/iomap.h b/include/linux/iomap.h index f753e788da31..69f4e9470084 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -52,6 +52,7 @@ struct iomap { #define IOMAP_REPORT (1 << 2) /* report extent status, e.g. FIEMAP */ #define IOMAP_FAULT (1 << 3) /* mapping for page fault */ #define IOMAP_DIRECT (1 << 4) /* direct I/O */ +#define IOMAP_NOWAIT (1 << 5) /* Don't wait for writeback */ struct iomap_ops { /* diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 13bc08aba704..1c91f26e2996 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -490,9 +490,13 @@ extern int root_mountflags; extern bool early_boot_irqs_disabled; -/* Values used for system_state */ +/* + * Values used for system_state. Ordering of the states must not be changed + * as code checks for <, <=, >, >= STATE. + */ extern enum system_states { SYSTEM_BOOTING, + SYSTEM_SCHEDULING, SYSTEM_RUNNING, SYSTEM_HALT, SYSTEM_POWER_OFF, diff --git a/include/linux/kvm_irqfd.h b/include/linux/kvm_irqfd.h index 0c1de05098c8..76c2fbc59f35 100644 --- a/include/linux/kvm_irqfd.h +++ b/include/linux/kvm_irqfd.h @@ -46,7 +46,7 @@ struct kvm_kernel_irqfd_resampler { struct kvm_kernel_irqfd { /* Used for MSI fast-path */ struct kvm *kvm; - wait_queue_t wait; + wait_queue_entry_t wait; /* Update side is protected by irqfds.lock */ struct kvm_kernel_irq_routing_entry irq_entry; seqcount_t irq_entry_sc; diff --git a/include/linux/llist.h b/include/linux/llist.h index 171baa90f6f6..d11738110a7a 100644 --- a/include/linux/llist.h +++ b/include/linux/llist.h @@ -110,6 +110,25 @@ static inline void init_llist_head(struct llist_head *list) for ((pos) = (node); pos; (pos) = (pos)->next) /** + * llist_for_each_safe - iterate over some deleted entries of a lock-less list + * safe against removal of list entry + * @pos: the &struct llist_node to use as a loop cursor + * @n: another &struct llist_node to use as temporary storage + * @node: the first entry of deleted list entries + * + * In general, some entries of the lock-less list can be traversed + * safely only after being deleted from list, so start with an entry + * instead of list head. + * + * If being used on entries deleted from lock-less list directly, the + * traverse order is from the newest to the oldest added entry. If + * you want to traverse from the oldest to the newest, you must + * reverse the order by yourself before traversing. + */ +#define llist_for_each_safe(pos, n, node) \ + for ((pos) = (node); (pos) && ((n) = (pos)->next, true); (pos) = (n)) + +/** * llist_for_each_entry - iterate over some deleted entries of lock-less list of given type * @pos: the type * to use as a loop cursor. * @node: the fist entry of deleted list entries. diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h index 136dfdf63ba1..fc412fbd80bd 100644 --- a/include/linux/mm_types_task.h +++ b/include/linux/mm_types_task.h @@ -14,6 +14,10 @@ #include <asm/page.h> +#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH +#include <asm/tlbbatch.h> +#endif + #define USE_SPLIT_PTE_PTLOCKS (NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS) #define USE_SPLIT_PMD_PTLOCKS (USE_SPLIT_PTE_PTLOCKS && \ IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK)) @@ -67,12 +71,15 @@ struct page_frag { struct tlbflush_unmap_batch { #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* - * Each bit set is a CPU that potentially has a TLB entry for one of - * the PFNs being flushed. See set_tlb_ubc_flush_pending(). + * The arch code makes the following promise: generic code can modify a + * PTE, then call arch_tlbbatch_add_mm() (which internally provides all + * needed barriers), then call arch_tlbbatch_flush(), and the entries + * will be flushed on all CPUs by the time that arch_tlbbatch_flush() + * returns. */ - struct cpumask cpumask; + struct arch_tlbflush_unmap_batch arch; - /* True if any bit in cpumask is set */ + /* True if a flush is needed. */ bool flush_required; /* diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index 6be1949ebcdf..1ee7b30dafec 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -457,7 +457,7 @@ enum hwparam_type { hwparam_ioport, /* Module parameter configures an I/O port */ hwparam_iomem, /* Module parameter configures an I/O mem address */ hwparam_ioport_or_iomem, /* Module parameter could be either, depending on other option */ - hwparam_irq, /* Module parameter configures an I/O port */ + hwparam_irq, /* Module parameter configures an IRQ */ hwparam_dma, /* Module parameter configures a DMA channel */ hwparam_dma_addr, /* Module parameter configures a DMA buffer address */ hwparam_other, /* Module parameter configures some other value */ diff --git a/include/linux/nvme-fc.h b/include/linux/nvme-fc.h index e997c4a49a88..bc711a10be05 100644 --- a/include/linux/nvme-fc.h +++ b/include/linux/nvme-fc.h @@ -177,7 +177,6 @@ struct fcnvme_lsdesc_rjt { }; -#define FCNVME_ASSOC_HOSTID_LEN 16 #define FCNVME_ASSOC_HOSTNQN_LEN 256 #define FCNVME_ASSOC_SUBNQN_LEN 256 @@ -191,7 +190,7 @@ struct fcnvme_lsdesc_cr_assoc_cmd { __be16 cntlid; __be16 sqsize; __be32 rsvd52; - u8 hostid[FCNVME_ASSOC_HOSTID_LEN]; + uuid_t hostid; u8 hostnqn[FCNVME_ASSOC_HOSTNQN_LEN]; u8 subnqn[FCNVME_ASSOC_SUBNQN_LEN]; u8 rsvd632[384]; diff --git a/include/linux/nvme.h b/include/linux/nvme.h index b625bacf37ef..6b8ee9e628e1 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -16,6 +16,7 @@ #define _LINUX_NVME_H #include <linux/types.h> +#include <linux/uuid.h> /* NQN names in commands fields specified one size */ #define NVMF_NQN_FIELD_LEN 256 @@ -86,7 +87,7 @@ enum { NVMF_RDMA_CMS_RDMA_CM = 1, /* Sockets based endpoint addressing */ }; -#define NVMF_AQ_DEPTH 32 +#define NVME_AQ_DEPTH 32 enum { NVME_REG_CAP = 0x0000, /* Controller Capabilities */ @@ -101,6 +102,7 @@ enum { NVME_REG_ACQ = 0x0030, /* Admin CQ Base Address */ NVME_REG_CMBLOC = 0x0038, /* Controller Memory Buffer Location */ NVME_REG_CMBSZ = 0x003c, /* Controller Memory Buffer Size */ + NVME_REG_DBS = 0x1000, /* SQ 0 Tail Doorbell */ }; #define NVME_CAP_MQES(cap) ((cap) & 0xffff) @@ -207,9 +209,15 @@ struct nvme_id_ctrl { __u8 tnvmcap[16]; __u8 unvmcap[16]; __le32 rpmbs; - __u8 rsvd316[4]; + __le16 edstt; + __u8 dsto; + __u8 fwug; __le16 kas; - __u8 rsvd322[190]; + __le16 hctma; + __le16 mntmt; + __le16 mxtmt; + __le32 sanicap; + __u8 rsvd332[180]; __u8 sqes; __u8 cqes; __le16 maxcmd; @@ -245,6 +253,7 @@ enum { NVME_CTRL_ONCS_WRITE_ZEROES = 1 << 3, NVME_CTRL_VWC_PRESENT = 1 << 0, NVME_CTRL_OACS_SEC_SUPP = 1 << 0, + NVME_CTRL_OACS_DIRECTIVES = 1 << 5, NVME_CTRL_OACS_DBBUF_SUPP = 1 << 7, }; @@ -274,7 +283,7 @@ struct nvme_id_ns { __le16 nabsn; __le16 nabo; __le16 nabspf; - __u16 rsvd46; + __le16 noiob; __u8 nvmcap[16]; __u8 rsvd64[40]; __u8 nguid[16]; @@ -288,6 +297,7 @@ enum { NVME_ID_CNS_NS = 0x00, NVME_ID_CNS_CTRL = 0x01, NVME_ID_CNS_NS_ACTIVE_LIST = 0x02, + NVME_ID_CNS_NS_DESC_LIST = 0x03, NVME_ID_CNS_NS_PRESENT_LIST = 0x10, NVME_ID_CNS_NS_PRESENT = 0x11, NVME_ID_CNS_CTRL_NS_LIST = 0x12, @@ -295,6 +305,19 @@ enum { }; enum { + NVME_DIR_IDENTIFY = 0x00, + NVME_DIR_STREAMS = 0x01, + NVME_DIR_SND_ID_OP_ENABLE = 0x01, + NVME_DIR_SND_ST_OP_REL_ID = 0x01, + NVME_DIR_SND_ST_OP_REL_RSC = 0x02, + NVME_DIR_RCV_ID_OP_PARAM = 0x01, + NVME_DIR_RCV_ST_OP_PARAM = 0x01, + NVME_DIR_RCV_ST_OP_STATUS = 0x02, + NVME_DIR_RCV_ST_OP_RESOURCE = 0x03, + NVME_DIR_ENDIR = 0x01, +}; + +enum { NVME_NS_FEAT_THIN = 1 << 0, NVME_NS_FLBAS_LBA_MASK = 0xf, NVME_NS_FLBAS_META_EXT = 0x10, @@ -314,6 +337,22 @@ enum { NVME_NS_DPS_PI_TYPE3 = 3, }; +struct nvme_ns_id_desc { + __u8 nidt; + __u8 nidl; + __le16 reserved; +}; + +#define NVME_NIDT_EUI64_LEN 8 +#define NVME_NIDT_NGUID_LEN 16 +#define NVME_NIDT_UUID_LEN 16 + +enum { + NVME_NIDT_EUI64 = 0x01, + NVME_NIDT_NGUID = 0x02, + NVME_NIDT_UUID = 0x03, +}; + struct nvme_smart_log { __u8 critical_warning; __u8 temperature[2]; @@ -535,6 +574,7 @@ enum { NVME_RW_PRINFO_PRCHK_APP = 1 << 11, NVME_RW_PRINFO_PRCHK_GUARD = 1 << 12, NVME_RW_PRINFO_PRACT = 1 << 13, + NVME_RW_DTYPE_STREAMS = 1 << 4, }; struct nvme_dsm_cmd { @@ -586,6 +626,11 @@ struct nvme_feat_auto_pst { __le64 entries[32]; }; +enum { + NVME_HOST_MEM_ENABLE = (1 << 0), + NVME_HOST_MEM_RETURN = (1 << 1), +}; + /* Admin commands */ enum nvme_admin_opcode { @@ -604,6 +649,8 @@ enum nvme_admin_opcode { nvme_admin_download_fw = 0x11, nvme_admin_ns_attach = 0x15, nvme_admin_keep_alive = 0x18, + nvme_admin_directive_send = 0x19, + nvme_admin_directive_recv = 0x1a, nvme_admin_dbbuf = 0x7C, nvme_admin_format_nvm = 0x80, nvme_admin_security_send = 0x81, @@ -658,6 +705,8 @@ struct nvme_identify { __u32 rsvd11[5]; }; +#define NVME_IDENTIFY_DATA_SIZE 4096 + struct nvme_features { __u8 opcode; __u8 flags; @@ -667,7 +716,16 @@ struct nvme_features { union nvme_data_ptr dptr; __le32 fid; __le32 dword11; - __u32 rsvd12[4]; + __le32 dword12; + __le32 dword13; + __le32 dword14; + __le32 dword15; +}; + +struct nvme_host_mem_buf_desc { + __le64 addr; + __le32 size; + __u32 rsvd; }; struct nvme_create_cq { @@ -756,6 +814,24 @@ struct nvme_get_log_page_command { __u32 rsvd14[2]; }; +struct nvme_directive_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __u64 rsvd2[2]; + union nvme_data_ptr dptr; + __le32 numd; + __u8 doper; + __u8 dtype; + __le16 dspec; + __u8 endir; + __u8 tdtype; + __u16 rsvd15; + + __u32 rsvd16[3]; +}; + /* * Fabrics subcommands. */ @@ -843,7 +919,7 @@ struct nvmf_connect_command { }; struct nvmf_connect_data { - __u8 hostid[16]; + uuid_t hostid; __le16 cntlid; char resv4[238]; char subsysnqn[NVMF_NQN_FIELD_LEN]; @@ -886,6 +962,18 @@ struct nvme_dbbuf { __u32 rsvd12[6]; }; +struct streams_directive_params { + __u16 msl; + __u16 nssa; + __u16 nsso; + __u8 rsvd[10]; + __u32 sws; + __u16 sgs; + __u16 nsa; + __u16 nso; + __u8 rsvd2[6]; +}; + struct nvme_command { union { struct nvme_common_command common; @@ -906,6 +994,7 @@ struct nvme_command { struct nvmf_property_set_command prop_set; struct nvmf_property_get_command prop_get; struct nvme_dbbuf dbbuf; + struct nvme_directive_cmd directive; }; }; @@ -1050,4 +1139,8 @@ struct nvme_completion { #define NVME_VS(major, minor, tertiary) \ (((major) << 16) | ((minor) << 8) | (tertiary)) +#define NVME_MAJOR(ver) ((ver) >> 16) +#define NVME_MINOR(ver) (((ver) >> 8) & 0xff) +#define NVME_TERTIARY(ver) ((ver) & 0xff) + #endif /* _LINUX_NVME_H */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 316a19f6b635..e7bbd9d4dc6c 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -524,7 +524,7 @@ void page_endio(struct page *page, bool is_write, int err); /* * Add an arbitrary waiter to a page's wait queue */ -extern void add_page_wait_queue(struct page *page, wait_queue_t *waiter); +extern void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter); /* * Fault everything in given userspace address range in. diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h index 7a4e83a8c89c..dd86c97f2454 100644 --- a/include/linux/pci-acpi.h +++ b/include/linux/pci-acpi.h @@ -105,7 +105,7 @@ static inline void acpiphp_remove_slots(struct pci_bus *bus) { } static inline void acpiphp_check_host_bridge(struct acpi_device *adev) { } #endif -extern const u8 pci_acpi_dsm_uuid[]; +extern const guid_t pci_acpi_dsm_guid; #define DEVICE_LABEL_DSM 0x07 #define RESET_DELAY_DSM 0x08 #define FUNCTION_DELAY_DSM 0x09 diff --git a/include/linux/poll.h b/include/linux/poll.h index 75ffc5729e4c..2889f09a1c60 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -75,7 +75,7 @@ static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc qproc) struct poll_table_entry { struct file *filp; unsigned long key; - wait_queue_t wait; + wait_queue_entry_t wait; wait_queue_head_t *wait_address; }; diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index ef3eb8bbfee4..0e5fcc11b1b8 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -391,10 +391,6 @@ static inline void user_single_step_siginfo(struct task_struct *tsk, #define current_pt_regs() task_pt_regs(current) #endif -#ifndef ptrace_signal_deliver -#define ptrace_signal_deliver() ((void)0) -#endif - /* * unlike current_pt_regs(), this one is equal to task_pt_regs(current) * on *all* architectures; the only reason to have a per-arch definition diff --git a/include/linux/rcu_node_tree.h b/include/linux/rcu_node_tree.h index 4b766b61e1a0..426cee67f0e2 100644 --- a/include/linux/rcu_node_tree.h +++ b/include/linux/rcu_node_tree.h @@ -7,6 +7,10 @@ * unlimited scalability while maintaining a constant level of contention * on the root node. * + * This seemingly RCU-private file must be available to SRCU users + * because the size of the TREE SRCU srcu_struct structure depends + * on these definitions. + * * 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 diff --git a/include/linux/rcu_segcblist.h b/include/linux/rcu_segcblist.h index ba4d2621d9ca..c3ad00e63556 100644 --- a/include/linux/rcu_segcblist.h +++ b/include/linux/rcu_segcblist.h @@ -1,6 +1,10 @@ /* * RCU segmented callback lists * + * This seemingly RCU-private file must be available to SRCU users + * because the size of the TREE SRCU srcu_struct structure depends + * on these definitions. + * * 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 diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index e1e5d002fdb9..f816fc72b51e 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -34,104 +34,15 @@ #define __LINUX_RCUPDATE_H #include <linux/types.h> -#include <linux/cache.h> -#include <linux/spinlock.h> -#include <linux/threads.h> -#include <linux/cpumask.h> -#include <linux/seqlock.h> -#include <linux/lockdep.h> -#include <linux/debugobjects.h> -#include <linux/bug.h> #include <linux/compiler.h> -#include <linux/ktime.h> +#include <linux/atomic.h> #include <linux/irqflags.h> +#include <linux/preempt.h> +#include <linux/bottom_half.h> +#include <linux/lockdep.h> +#include <asm/processor.h> +#include <linux/cpumask.h> -#include <asm/barrier.h> - -#ifndef CONFIG_TINY_RCU -extern int rcu_expedited; /* for sysctl */ -extern int rcu_normal; /* also for sysctl */ -#endif /* #ifndef CONFIG_TINY_RCU */ - -#ifdef CONFIG_TINY_RCU -/* Tiny RCU doesn't expedite, as its purpose in life is instead to be tiny. */ -static inline bool rcu_gp_is_normal(void) /* Internal RCU use. */ -{ - return true; -} -static inline bool rcu_gp_is_expedited(void) /* Internal RCU use. */ -{ - return false; -} - -static inline void rcu_expedite_gp(void) -{ -} - -static inline void rcu_unexpedite_gp(void) -{ -} -#else /* #ifdef CONFIG_TINY_RCU */ -bool rcu_gp_is_normal(void); /* Internal RCU use. */ -bool rcu_gp_is_expedited(void); /* Internal RCU use. */ -void rcu_expedite_gp(void); -void rcu_unexpedite_gp(void); -#endif /* #else #ifdef CONFIG_TINY_RCU */ - -enum rcutorture_type { - RCU_FLAVOR, - RCU_BH_FLAVOR, - RCU_SCHED_FLAVOR, - RCU_TASKS_FLAVOR, - SRCU_FLAVOR, - INVALID_RCU_FLAVOR -}; - -#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU) -void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, - unsigned long *gpnum, unsigned long *completed); -void rcutorture_record_test_transition(void); -void rcutorture_record_progress(unsigned long vernum); -void do_trace_rcu_torture_read(const char *rcutorturename, - struct rcu_head *rhp, - unsigned long secs, - unsigned long c_old, - unsigned long c); -bool rcu_irq_enter_disabled(void); -#else -static inline void rcutorture_get_gp_data(enum rcutorture_type test_type, - int *flags, - unsigned long *gpnum, - unsigned long *completed) -{ - *flags = 0; - *gpnum = 0; - *completed = 0; -} -static inline void rcutorture_record_test_transition(void) -{ -} -static inline void rcutorture_record_progress(unsigned long vernum) -{ -} -static inline bool rcu_irq_enter_disabled(void) -{ - return false; -} -#ifdef CONFIG_RCU_TRACE -void do_trace_rcu_torture_read(const char *rcutorturename, - struct rcu_head *rhp, - unsigned long secs, - unsigned long c_old, - unsigned long c); -#else -#define do_trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \ - do { } while (0) -#endif -#endif - -#define UINT_CMP_GE(a, b) (UINT_MAX / 2 >= (a) - (b)) -#define UINT_CMP_LT(a, b) (UINT_MAX / 2 < (a) - (b)) #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) #define ulong2long(a) (*(long *)(&(a))) @@ -139,115 +50,14 @@ void do_trace_rcu_torture_read(const char *rcutorturename, /* Exported common interfaces */ #ifdef CONFIG_PREEMPT_RCU - -/** - * call_rcu() - Queue an RCU callback for invocation after a grace period. - * @head: structure to be used for queueing the RCU updates. - * @func: actual callback function to be invoked after the grace period - * - * The callback function will be invoked some time after a full grace - * period elapses, in other words after all pre-existing RCU read-side - * critical sections have completed. However, the callback function - * might well execute concurrently with RCU read-side critical sections - * that started after call_rcu() was invoked. RCU read-side critical - * sections are delimited by rcu_read_lock() and rcu_read_unlock(), - * and may be nested. - * - * Note that all CPUs must agree that the grace period extended beyond - * all pre-existing RCU read-side critical section. On systems with more - * than one CPU, this means that when "func()" is invoked, each CPU is - * guaranteed to have executed a full memory barrier since the end of its - * last RCU read-side critical section whose beginning preceded the call - * to call_rcu(). It also means that each CPU executing an RCU read-side - * critical section that continues beyond the start of "func()" must have - * executed a memory barrier after the call_rcu() but before the beginning - * of that RCU read-side critical section. Note that these guarantees - * include CPUs that are offline, idle, or executing in user mode, as - * well as CPUs that are executing in the kernel. - * - * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the - * resulting RCU callback function "func()", then both CPU A and CPU B are - * guaranteed to execute a full memory barrier during the time interval - * between the call to call_rcu() and the invocation of "func()" -- even - * if CPU A and CPU B are the same CPU (but again only if the system has - * more than one CPU). - */ -void call_rcu(struct rcu_head *head, - rcu_callback_t func); - +void call_rcu(struct rcu_head *head, rcu_callback_t func); #else /* #ifdef CONFIG_PREEMPT_RCU */ - -/* In classic RCU, call_rcu() is just call_rcu_sched(). */ #define call_rcu call_rcu_sched - #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ -/** - * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period. - * @head: structure to be used for queueing the RCU updates. - * @func: actual callback function to be invoked after the grace period - * - * The callback function will be invoked some time after a full grace - * period elapses, in other words after all currently executing RCU - * read-side critical sections have completed. call_rcu_bh() assumes - * that the read-side critical sections end on completion of a softirq - * handler. This means that read-side critical sections in process - * context must not be interrupted by softirqs. This interface is to be - * used when most of the read-side critical sections are in softirq context. - * RCU read-side critical sections are delimited by : - * - rcu_read_lock() and rcu_read_unlock(), if in interrupt context. - * OR - * - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context. - * These may be nested. - * - * See the description of call_rcu() for more detailed information on - * memory ordering guarantees. - */ -void call_rcu_bh(struct rcu_head *head, - rcu_callback_t func); - -/** - * call_rcu_sched() - Queue an RCU for invocation after sched grace period. - * @head: structure to be used for queueing the RCU updates. - * @func: actual callback function to be invoked after the grace period - * - * The callback function will be invoked some time after a full grace - * period elapses, in other words after all currently executing RCU - * read-side critical sections have completed. call_rcu_sched() assumes - * that the read-side critical sections end on enabling of preemption - * or on voluntary preemption. - * RCU read-side critical sections are delimited by : - * - rcu_read_lock_sched() and rcu_read_unlock_sched(), - * OR - * anything that disables preemption. - * These may be nested. - * - * See the description of call_rcu() for more detailed information on - * memory ordering guarantees. - */ -void call_rcu_sched(struct rcu_head *head, - rcu_callback_t func); - +void call_rcu_bh(struct rcu_head *head, rcu_callback_t func); +void call_rcu_sched(struct rcu_head *head, rcu_callback_t func); void synchronize_sched(void); - -/** - * call_rcu_tasks() - Queue an RCU for invocation task-based grace period - * @head: structure to be used for queueing the RCU updates. - * @func: actual callback function to be invoked after the grace period - * - * The callback function will be invoked some time after a full grace - * period elapses, in other words after all currently executing RCU - * read-side critical sections have completed. call_rcu_tasks() assumes - * that the read-side critical sections end at a voluntary context - * switch (not a preemption!), entry into idle, or transition to usermode - * execution. As such, there are no read-side primitives analogous to - * rcu_read_lock() and rcu_read_unlock() because this primitive is intended - * to determine that all tasks have passed through a safe state, not so - * much for data-strcuture synchronization. - * - * See the description of call_rcu() for more detailed information on - * memory ordering guarantees. - */ void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks(void); void rcu_barrier_tasks(void); @@ -301,22 +111,12 @@ void rcu_check_callbacks(int user); void rcu_report_dead(unsigned int cpu); void rcu_cpu_starting(unsigned int cpu); -#ifndef CONFIG_TINY_RCU -void rcu_end_inkernel_boot(void); -#else /* #ifndef CONFIG_TINY_RCU */ -static inline void rcu_end_inkernel_boot(void) { } -#endif /* #ifndef CONFIG_TINY_RCU */ - #ifdef CONFIG_RCU_STALL_COMMON void rcu_sysrq_start(void); void rcu_sysrq_end(void); #else /* #ifdef CONFIG_RCU_STALL_COMMON */ -static inline void rcu_sysrq_start(void) -{ -} -static inline void rcu_sysrq_end(void) -{ -} +static inline void rcu_sysrq_start(void) { } +static inline void rcu_sysrq_end(void) { } #endif /* #else #ifdef CONFIG_RCU_STALL_COMMON */ #ifdef CONFIG_NO_HZ_FULL @@ -330,9 +130,7 @@ static inline void rcu_user_exit(void) { } #ifdef CONFIG_RCU_NOCB_CPU void rcu_init_nohz(void); #else /* #ifdef CONFIG_RCU_NOCB_CPU */ -static inline void rcu_init_nohz(void) -{ -} +static inline void rcu_init_nohz(void) { } #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ /** @@ -397,10 +195,6 @@ do { \ rcu_note_voluntary_context_switch(current); \ } while (0) -#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP) -bool __rcu_is_watching(void); -#endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP) */ - /* * Infrastructure to implement the synchronize_() primitives in * TREE_RCU and rcu_barrier_() primitives in TINY_RCU. @@ -414,10 +208,6 @@ bool __rcu_is_watching(void); #error "Unknown RCU implementation specified to kernel configuration" #endif -#define RCU_SCHEDULER_INACTIVE 0 -#define RCU_SCHEDULER_INIT 1 -#define RCU_SCHEDULER_RUNNING 2 - /* * init_rcu_head_on_stack()/destroy_rcu_head_on_stack() are needed for dynamic * initialization and destruction of rcu_head on the stack. rcu_head structures @@ -430,30 +220,16 @@ void destroy_rcu_head(struct rcu_head *head); void init_rcu_head_on_stack(struct rcu_head *head); void destroy_rcu_head_on_stack(struct rcu_head *head); #else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ -static inline void init_rcu_head(struct rcu_head *head) -{ -} - -static inline void destroy_rcu_head(struct rcu_head *head) -{ -} - -static inline void init_rcu_head_on_stack(struct rcu_head *head) -{ -} - -static inline void destroy_rcu_head_on_stack(struct rcu_head *head) -{ -} +static inline void init_rcu_head(struct rcu_head *head) { } +static inline void destroy_rcu_head(struct rcu_head *head) { } +static inline void init_rcu_head_on_stack(struct rcu_head *head) { } +static inline void destroy_rcu_head_on_stack(struct rcu_head *head) { } #endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) bool rcu_lockdep_current_cpu_online(void); #else /* #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ -static inline bool rcu_lockdep_current_cpu_online(void) -{ - return true; -} +static inline bool rcu_lockdep_current_cpu_online(void) { return true; } #endif /* #else #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ #ifdef CONFIG_DEBUG_LOCK_ALLOC @@ -473,18 +249,8 @@ extern struct lockdep_map rcu_bh_lock_map; extern struct lockdep_map rcu_sched_lock_map; extern struct lockdep_map rcu_callback_map; int debug_lockdep_rcu_enabled(void); - int rcu_read_lock_held(void); int rcu_read_lock_bh_held(void); - -/** - * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section? - * - * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an - * RCU-sched read-side critical section. In absence of - * CONFIG_DEBUG_LOCK_ALLOC, this assumes we are in an RCU-sched read-side - * critical section unless it can prove otherwise. - */ int rcu_read_lock_sched_held(void); #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ @@ -531,9 +297,7 @@ static inline void rcu_preempt_sleep_check(void) "Illegal context switch in RCU read-side critical section"); } #else /* #ifdef CONFIG_PROVE_RCU */ -static inline void rcu_preempt_sleep_check(void) -{ -} +static inline void rcu_preempt_sleep_check(void) { } #endif /* #else #ifdef CONFIG_PROVE_RCU */ #define rcu_sleep_check() \ @@ -1084,52 +848,6 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) #define kfree_rcu(ptr, rcu_head) \ __kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head)) -#ifdef CONFIG_TINY_RCU -static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt) -{ - *nextevt = KTIME_MAX; - return 0; -} -#endif /* #ifdef CONFIG_TINY_RCU */ - -#if defined(CONFIG_RCU_NOCB_CPU_ALL) -static inline bool rcu_is_nocb_cpu(int cpu) { return true; } -#elif defined(CONFIG_RCU_NOCB_CPU) -bool rcu_is_nocb_cpu(int cpu); -#else -static inline bool rcu_is_nocb_cpu(int cpu) { return false; } -#endif - - -/* Only for use by adaptive-ticks code. */ -#ifdef CONFIG_NO_HZ_FULL_SYSIDLE -bool rcu_sys_is_idle(void); -void rcu_sysidle_force_exit(void); -#else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ - -static inline bool rcu_sys_is_idle(void) -{ - return false; -} - -static inline void rcu_sysidle_force_exit(void) -{ -} - -#endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ - - -/* - * Dump the ftrace buffer, but only one time per callsite per boot. - */ -#define rcu_ftrace_dump(oops_dump_mode) \ -do { \ - static atomic_t ___rfd_beenhere = ATOMIC_INIT(0); \ - \ - if (!atomic_read(&___rfd_beenhere) && \ - !atomic_xchg(&___rfd_beenhere, 1)) \ - ftrace_dump(oops_dump_mode); \ -} while (0) /* * Place this after a lock-acquisition primitive to guarantee that diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 74d9c3a1feee..5becbbccb998 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -25,7 +25,7 @@ #ifndef __LINUX_TINY_H #define __LINUX_TINY_H -#include <linux/cache.h> +#include <linux/ktime.h> struct rcu_dynticks; static inline int rcu_dynticks_snap(struct rcu_dynticks *rdtp) @@ -33,10 +33,8 @@ static inline int rcu_dynticks_snap(struct rcu_dynticks *rdtp) return 0; } -static inline bool rcu_eqs_special_set(int cpu) -{ - return false; /* Never flag non-existent other CPUs! */ -} +/* Never flag non-existent other CPUs! */ +static inline bool rcu_eqs_special_set(int cpu) { return false; } static inline unsigned long get_state_synchronize_rcu(void) { @@ -98,159 +96,38 @@ static inline void kfree_call_rcu(struct rcu_head *head, rcu_note_voluntary_context_switch_lite(current); \ } while (0) -/* - * Take advantage of the fact that there is only one CPU, which - * allows us to ignore virtualization-based context switches. - */ -static inline void rcu_virt_note_context_switch(int cpu) -{ -} - -/* - * Return the number of grace periods started. - */ -static inline unsigned long rcu_batches_started(void) -{ - return 0; -} - -/* - * Return the number of bottom-half grace periods started. - */ -static inline unsigned long rcu_batches_started_bh(void) -{ - return 0; -} - -/* - * Return the number of sched grace periods started. - */ -static inline unsigned long rcu_batches_started_sched(void) -{ - return 0; -} - -/* - * Return the number of grace periods completed. - */ -static inline unsigned long rcu_batches_completed(void) -{ - return 0; -} - -/* - * Return the number of bottom-half grace periods completed. - */ -static inline unsigned long rcu_batches_completed_bh(void) -{ - return 0; -} - -/* - * Return the number of sched grace periods completed. - */ -static inline unsigned long rcu_batches_completed_sched(void) +static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt) { + *nextevt = KTIME_MAX; return 0; } /* - * Return the number of expedited grace periods completed. - */ -static inline unsigned long rcu_exp_batches_completed(void) -{ - return 0; -} - -/* - * Return the number of expedited sched grace periods completed. + * Take advantage of the fact that there is only one CPU, which + * allows us to ignore virtualization-based context switches. */ -static inline unsigned long rcu_exp_batches_completed_sched(void) -{ - return 0; -} - -static inline void rcu_force_quiescent_state(void) -{ -} - -static inline void rcu_bh_force_quiescent_state(void) -{ -} - -static inline void rcu_sched_force_quiescent_state(void) -{ -} - -static inline void show_rcu_gp_kthreads(void) -{ -} - -static inline void rcu_cpu_stall_reset(void) -{ -} - -static inline void rcu_idle_enter(void) -{ -} - -static inline void rcu_idle_exit(void) -{ -} - -static inline void rcu_irq_enter(void) -{ -} - -static inline void rcu_irq_exit_irqson(void) -{ -} - -static inline void rcu_irq_enter_irqson(void) -{ -} - -static inline void rcu_irq_exit(void) -{ -} - -static inline void exit_rcu(void) -{ -} +static inline void rcu_virt_note_context_switch(int cpu) { } +static inline void rcu_cpu_stall_reset(void) { } +static inline void rcu_idle_enter(void) { } +static inline void rcu_idle_exit(void) { } +static inline void rcu_irq_enter(void) { } +static inline bool rcu_irq_enter_disabled(void) { return false; } +static inline void rcu_irq_exit_irqson(void) { } +static inline void rcu_irq_enter_irqson(void) { } +static inline void rcu_irq_exit(void) { } +static inline void exit_rcu(void) { } #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) extern int rcu_scheduler_active __read_mostly; void rcu_scheduler_starting(void); #else /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) */ -static inline void rcu_scheduler_starting(void) -{ -} +static inline void rcu_scheduler_starting(void) { } #endif /* #else #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) */ +static inline void rcu_end_inkernel_boot(void) { } +static inline bool rcu_is_watching(void) { return true; } -#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) - -static inline bool rcu_is_watching(void) -{ - return __rcu_is_watching(); -} - -#else /* defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */ - -static inline bool rcu_is_watching(void) -{ - return true; -} - -#endif /* #else defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */ - -static inline void rcu_request_urgent_qs_task(struct task_struct *t) -{ -} - -static inline void rcu_all_qs(void) -{ - barrier(); /* Avoid RCU read-side critical sections leaking across. */ -} +/* Avoid RCU read-side critical sections leaking across. */ +static inline void rcu_all_qs(void) { barrier(); } /* RCUtree hotplug events */ #define rcutree_prepare_cpu NULL diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 0bacb6b2af69..37d6fd3b7ff8 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -79,37 +79,20 @@ void cond_synchronize_rcu(unsigned long oldstate); unsigned long get_state_synchronize_sched(void); void cond_synchronize_sched(unsigned long oldstate); -extern unsigned long rcutorture_testseq; -extern unsigned long rcutorture_vernum; -unsigned long rcu_batches_started(void); -unsigned long rcu_batches_started_bh(void); -unsigned long rcu_batches_started_sched(void); -unsigned long rcu_batches_completed(void); -unsigned long rcu_batches_completed_bh(void); -unsigned long rcu_batches_completed_sched(void); -unsigned long rcu_exp_batches_completed(void); -unsigned long rcu_exp_batches_completed_sched(void); -void show_rcu_gp_kthreads(void); - -void rcu_force_quiescent_state(void); -void rcu_bh_force_quiescent_state(void); -void rcu_sched_force_quiescent_state(void); - void rcu_idle_enter(void); void rcu_idle_exit(void); void rcu_irq_enter(void); void rcu_irq_exit(void); void rcu_irq_enter_irqson(void); void rcu_irq_exit_irqson(void); +bool rcu_irq_enter_disabled(void); void exit_rcu(void); void rcu_scheduler_starting(void); extern int rcu_scheduler_active __read_mostly; - +void rcu_end_inkernel_boot(void); bool rcu_is_watching(void); -void rcu_request_urgent_qs_task(struct task_struct *t); - void rcu_all_qs(void); /* RCUtree hotplug events */ diff --git a/include/linux/refcount.h b/include/linux/refcount.h index b34aa649d204..591792c8e5b0 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -41,6 +41,7 @@ static inline unsigned int refcount_read(const refcount_t *r) return atomic_read(&r->refs); } +#ifdef CONFIG_REFCOUNT_FULL extern __must_check bool refcount_add_not_zero(unsigned int i, refcount_t *r); extern void refcount_add(unsigned int i, refcount_t *r); @@ -48,10 +49,45 @@ extern __must_check bool refcount_inc_not_zero(refcount_t *r); extern void refcount_inc(refcount_t *r); extern __must_check bool refcount_sub_and_test(unsigned int i, refcount_t *r); -extern void refcount_sub(unsigned int i, refcount_t *r); extern __must_check bool refcount_dec_and_test(refcount_t *r); extern void refcount_dec(refcount_t *r); +#else +static inline __must_check bool refcount_add_not_zero(unsigned int i, refcount_t *r) +{ + return atomic_add_unless(&r->refs, i, 0); +} + +static inline void refcount_add(unsigned int i, refcount_t *r) +{ + atomic_add(i, &r->refs); +} + +static inline __must_check bool refcount_inc_not_zero(refcount_t *r) +{ + return atomic_add_unless(&r->refs, 1, 0); +} + +static inline void refcount_inc(refcount_t *r) +{ + atomic_inc(&r->refs); +} + +static inline __must_check bool refcount_sub_and_test(unsigned int i, refcount_t *r) +{ + return atomic_sub_and_test(i, &r->refs); +} + +static inline __must_check bool refcount_dec_and_test(refcount_t *r) +{ + return atomic_dec_and_test(&r->refs); +} + +static inline void refcount_dec(refcount_t *r) +{ + atomic_dec(&r->refs); +} +#endif /* CONFIG_REFCOUNT_FULL */ extern __must_check bool refcount_dec_if_one(refcount_t *r); extern __must_check bool refcount_dec_not_one(refcount_t *r); diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h index 1abba5ce2a2f..44fd002f7cd5 100644 --- a/include/linux/rtmutex.h +++ b/include/linux/rtmutex.h @@ -37,6 +37,9 @@ struct rt_mutex { int line; void *magic; #endif +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif }; struct rt_mutex_waiter; @@ -58,19 +61,33 @@ struct hrtimer_sleeper; #ifdef CONFIG_DEBUG_RT_MUTEXES # define __DEBUG_RT_MUTEX_INITIALIZER(mutexname) \ , .name = #mutexname, .file = __FILE__, .line = __LINE__ -# define rt_mutex_init(mutex) __rt_mutex_init(mutex, __func__) + +# define rt_mutex_init(mutex) \ +do { \ + static struct lock_class_key __key; \ + __rt_mutex_init(mutex, __func__, &__key); \ +} while (0) + extern void rt_mutex_debug_task_free(struct task_struct *tsk); #else # define __DEBUG_RT_MUTEX_INITIALIZER(mutexname) -# define rt_mutex_init(mutex) __rt_mutex_init(mutex, NULL) +# define rt_mutex_init(mutex) __rt_mutex_init(mutex, NULL, NULL) # define rt_mutex_debug_task_free(t) do { } while (0) #endif +#ifdef CONFIG_DEBUG_LOCK_ALLOC +#define __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname) \ + , .dep_map = { .name = #mutexname } +#else +#define __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname) +#endif + #define __RT_MUTEX_INITIALIZER(mutexname) \ { .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \ , .waiters = RB_ROOT \ , .owner = NULL \ - __DEBUG_RT_MUTEX_INITIALIZER(mutexname)} + __DEBUG_RT_MUTEX_INITIALIZER(mutexname) \ + __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname)} #define DEFINE_RT_MUTEX(mutexname) \ struct rt_mutex mutexname = __RT_MUTEX_INITIALIZER(mutexname) @@ -86,7 +103,7 @@ static inline int rt_mutex_is_locked(struct rt_mutex *lock) return lock->owner != NULL; } -extern void __rt_mutex_init(struct rt_mutex *lock, const char *name); +extern void __rt_mutex_init(struct rt_mutex *lock, const char *name, struct lock_class_key *key); extern void rt_mutex_destroy(struct rt_mutex *lock); extern void rt_mutex_lock(struct rt_mutex *lock); diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index cb3c8fe6acd7..4b3286ac60c8 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -278,6 +278,8 @@ size_t sg_pcopy_from_buffer(struct scatterlist *sgl, unsigned int nents, const void *buf, size_t buflen, off_t skip); size_t sg_pcopy_to_buffer(struct scatterlist *sgl, unsigned int nents, void *buf, size_t buflen, off_t skip); +size_t sg_zero_buffer(struct scatterlist *sgl, unsigned int nents, + size_t buflen, off_t skip); /* * Maximum number of entries that will be allocated in one piece, if diff --git a/include/linux/sched.h b/include/linux/sched.h index 2b69fc650201..1f0f427e0292 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -421,7 +421,8 @@ struct sched_dl_entity { u64 dl_runtime; /* Maximum runtime for each instance */ u64 dl_deadline; /* Relative deadline of each instance */ u64 dl_period; /* Separation of two instances (period) */ - u64 dl_bw; /* dl_runtime / dl_deadline */ + u64 dl_bw; /* dl_runtime / dl_period */ + u64 dl_density; /* dl_runtime / dl_deadline */ /* * Actual scheduling parameters. Initialized with the values above, @@ -445,16 +446,33 @@ struct sched_dl_entity { * * @dl_yielded tells if task gave up the CPU before consuming * all its available runtime during the last job. + * + * @dl_non_contending tells if the task is inactive while still + * contributing to the active utilization. In other words, it + * indicates if the inactive timer has been armed and its handler + * has not been executed yet. This flag is useful to avoid race + * conditions between the inactive timer handler and the wakeup + * code. */ int dl_throttled; int dl_boosted; int dl_yielded; + int dl_non_contending; /* * Bandwidth enforcement timer. Each -deadline task has its * own bandwidth to be enforced, thus we need one timer per task. */ struct hrtimer dl_timer; + + /* + * Inactive timer, responsible for decreasing the active utilization + * at the "0-lag time". When a -deadline task blocks, it contributes + * to GRUB's active utilization until the "0-lag time", hence a + * timer is needed to decrease the active utilization at the correct + * time. + */ + struct hrtimer inactive_timer; }; union rcu_special { @@ -1096,8 +1114,6 @@ static inline struct pid *task_session(struct task_struct *task) * current. * task_xid_nr_ns() : id seen from the ns specified; * - * set_task_vxid() : assigns a virtual id to a task; - * * see also pid_nr() etc in include/linux/pid.h */ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns); diff --git a/include/linux/sched/clock.h b/include/linux/sched/clock.h index 34fe92ce1ebd..a55600ffdf4b 100644 --- a/include/linux/sched/clock.h +++ b/include/linux/sched/clock.h @@ -23,10 +23,6 @@ extern u64 sched_clock_cpu(int cpu); extern void sched_clock_init(void); #ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK -static inline void sched_clock_init_late(void) -{ -} - static inline void sched_clock_tick(void) { } @@ -39,7 +35,7 @@ static inline void sched_clock_idle_sleep_event(void) { } -static inline void sched_clock_idle_wakeup_event(u64 delta_ns) +static inline void sched_clock_idle_wakeup_event(void) { } @@ -53,7 +49,6 @@ static inline u64 local_clock(void) return sched_clock(); } #else -extern void sched_clock_init_late(void); extern int sched_clock_stable(void); extern void clear_sched_clock_stable(void); @@ -63,10 +58,10 @@ extern void clear_sched_clock_stable(void); */ extern u64 __sched_clock_offset; - extern void sched_clock_tick(void); +extern void sched_clock_tick_stable(void); extern void sched_clock_idle_sleep_event(void); -extern void sched_clock_idle_wakeup_event(u64 delta_ns); +extern void sched_clock_idle_wakeup_event(void); /* * As outlined in clock.c, provides a fast, high resolution, nanosecond diff --git a/include/linux/sched/nohz.h b/include/linux/sched/nohz.h index 4995b717500b..7d3f75db23e5 100644 --- a/include/linux/sched/nohz.h +++ b/include/linux/sched/nohz.h @@ -23,11 +23,11 @@ static inline void set_cpu_sd_state_idle(void) { } #endif #ifdef CONFIG_NO_HZ_COMMON -void calc_load_enter_idle(void); -void calc_load_exit_idle(void); +void calc_load_nohz_start(void); +void calc_load_nohz_stop(void); #else -static inline void calc_load_enter_idle(void) { } -static inline void calc_load_exit_idle(void) { } +static inline void calc_load_nohz_start(void) { } +static inline void calc_load_nohz_stop(void) { } #endif /* CONFIG_NO_HZ_COMMON */ #if defined(CONFIG_NO_HZ_COMMON) && defined(CONFIG_SMP) diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index a978d7189cfd..f0f065c5afcf 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -95,8 +95,6 @@ static inline void put_task_struct(struct task_struct *t) } struct task_struct *task_rcu_dereference(struct task_struct **ptask); -struct task_struct *try_get_task_struct(struct task_struct **ptask); - #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT extern int arch_task_struct_size __read_mostly; diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 07ef550c6627..93315d6b21a8 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -84,6 +84,7 @@ struct kmem_cache { int red_left_pad; /* Left redzone padding size */ #ifdef CONFIG_SYSFS struct kobject kobj; /* For sysfs */ + struct work_struct kobj_remove_work; #endif #ifdef CONFIG_MEMCG struct memcg_cache_params memcg_params; diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 59248dcc6ef3..d9510e8522d4 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -369,6 +369,26 @@ static __always_inline int spin_trylock_irq(spinlock_t *lock) raw_spin_trylock_irqsave(spinlock_check(lock), flags); \ }) +/** + * spin_unlock_wait - Interpose between successive critical sections + * @lock: the spinlock whose critical sections are to be interposed. + * + * Semantically this is equivalent to a spin_lock() immediately + * followed by a spin_unlock(). However, most architectures have + * more efficient implementations in which the spin_unlock_wait() + * cannot block concurrent lock acquisition, and in some cases + * where spin_unlock_wait() does not write to the lock variable. + * Nevertheless, spin_unlock_wait() can have high overhead, so if + * you feel the need to use it, please check to see if there is + * a better way to get your job done. + * + * The ordering guarantees provided by spin_unlock_wait() are: + * + * 1. All accesses preceding the spin_unlock_wait() happen before + * any accesses in later critical sections for this same lock. + * 2. All accesses following the spin_unlock_wait() happen after + * any accesses in earlier critical sections for this same lock. + */ static __always_inline void spin_unlock_wait(spinlock_t *lock) { raw_spin_unlock_wait(&lock->rlock); diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 4c1d5f7e62c4..39af9bc0f653 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -60,32 +60,15 @@ int init_srcu_struct(struct srcu_struct *sp); #include <linux/srcutiny.h> #elif defined(CONFIG_TREE_SRCU) #include <linux/srcutree.h> -#elif defined(CONFIG_CLASSIC_SRCU) -#include <linux/srcuclassic.h> -#else +#elif defined(CONFIG_SRCU) #error "Unknown SRCU implementation specified to kernel configuration" +#else +/* Dummy definition for things like notifiers. Actual use gets link error. */ +struct srcu_struct { }; #endif -/** - * call_srcu() - Queue a callback for invocation after an SRCU grace period - * @sp: srcu_struct in queue the callback - * @head: structure to be used for queueing the SRCU callback. - * @func: function to be invoked after the SRCU grace period - * - * The callback function will be invoked some time after a full SRCU - * grace period elapses, in other words after all pre-existing SRCU - * read-side critical sections have completed. However, the callback - * function might well execute concurrently with other SRCU read-side - * critical sections that started after call_srcu() was invoked. SRCU - * read-side critical sections are delimited by srcu_read_lock() and - * srcu_read_unlock(), and may be nested. - * - * The callback will be invoked from process context, but must nevertheless - * be fast and must not block. - */ void call_srcu(struct srcu_struct *sp, struct rcu_head *head, void (*func)(struct rcu_head *head)); - 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); diff --git a/include/linux/srcuclassic.h b/include/linux/srcuclassic.h deleted file mode 100644 index 5753f7322262..000000000000 --- a/include/linux/srcuclassic.h +++ /dev/null @@ -1,115 +0,0 @@ -/* - * Sleepable Read-Copy Update mechanism for mutual exclusion, - * classic v4.11 variant. - * - * 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, you can access it online at - * http://www.gnu.org/licenses/gpl-2.0.html. - * - * Copyright (C) IBM Corporation, 2017 - * - * Author: Paul McKenney <paulmck@us.ibm.com> - */ - -#ifndef _LINUX_SRCU_CLASSIC_H -#define _LINUX_SRCU_CLASSIC_H - -struct srcu_array { - unsigned long lock_count[2]; - unsigned long unlock_count[2]; -}; - -struct rcu_batch { - struct rcu_head *head, **tail; -}; - -#define RCU_BATCH_INIT(name) { NULL, &(name.head) } - -struct srcu_struct { - unsigned long completed; - struct srcu_array __percpu *per_cpu_ref; - spinlock_t queue_lock; /* protect ->batch_queue, ->running */ - bool running; - /* callbacks just queued */ - struct rcu_batch batch_queue; - /* callbacks try to do the first check_zero */ - struct rcu_batch batch_check0; - /* callbacks done with the first check_zero and the flip */ - struct rcu_batch batch_check1; - struct rcu_batch batch_done; - struct delayed_work work; -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map dep_map; -#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ -}; - -void process_srcu(struct work_struct *work); - -#define __SRCU_STRUCT_INIT(name) \ - { \ - .completed = -300, \ - .per_cpu_ref = &name##_srcu_array, \ - .queue_lock = __SPIN_LOCK_UNLOCKED(name.queue_lock), \ - .running = false, \ - .batch_queue = RCU_BATCH_INIT(name.batch_queue), \ - .batch_check0 = RCU_BATCH_INIT(name.batch_check0), \ - .batch_check1 = RCU_BATCH_INIT(name.batch_check1), \ - .batch_done = RCU_BATCH_INIT(name.batch_done), \ - .work = __DELAYED_WORK_INITIALIZER(name.work, process_srcu, 0),\ - __SRCU_DEP_MAP_INIT(name) \ - } - -/* - * Define and initialize a srcu struct at build time. - * Do -not- call init_srcu_struct() nor cleanup_srcu_struct() on it. - * - * Note that although DEFINE_STATIC_SRCU() hides the name from other - * files, the per-CPU variable rules nevertheless require that the - * chosen name be globally unique. These rules also prohibit use of - * DEFINE_STATIC_SRCU() within a function. If these rules are too - * restrictive, declare the srcu_struct manually. For example, in - * each file: - * - * static struct srcu_struct my_srcu; - * - * Then, before the first use of each my_srcu, manually initialize it: - * - * init_srcu_struct(&my_srcu); - * - * See include/linux/percpu-defs.h for the rules on per-CPU variables. - */ -#define __DEFINE_SRCU(name, is_static) \ - static DEFINE_PER_CPU(struct srcu_array, name##_srcu_array);\ - is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name) -#define DEFINE_SRCU(name) __DEFINE_SRCU(name, /* not static */) -#define DEFINE_STATIC_SRCU(name) __DEFINE_SRCU(name, static) - -void synchronize_srcu_expedited(struct srcu_struct *sp); -void srcu_barrier(struct srcu_struct *sp); -unsigned long srcu_batches_completed(struct srcu_struct *sp); - -static inline void srcutorture_get_gp_data(enum rcutorture_type test_type, - struct srcu_struct *sp, int *flags, - unsigned long *gpnum, - unsigned long *completed) -{ - if (test_type != SRCU_FLAVOR) - return; - *flags = 0; - *completed = sp->completed; - *gpnum = *completed; - if (sp->batch_queue.head || sp->batch_check0.head || sp->batch_check0.head) - (*gpnum)++; -} - -#endif diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h index 42311ee0334f..cfbfc540cafc 100644 --- a/include/linux/srcutiny.h +++ b/include/linux/srcutiny.h @@ -27,15 +27,14 @@ #include <linux/swait.h> struct srcu_struct { - int srcu_lock_nesting[2]; /* srcu_read_lock() nesting depth. */ + short srcu_lock_nesting[2]; /* srcu_read_lock() nesting depth. */ + short srcu_idx; /* Current reader array element. */ + u8 srcu_gp_running; /* GP workqueue running? */ + u8 srcu_gp_waiting; /* GP waiting for readers? */ struct swait_queue_head srcu_wq; /* Last srcu_read_unlock() wakes GP. */ - unsigned long srcu_gp_seq; /* GP seq # for callback tagging. */ - struct rcu_segcblist srcu_cblist; - /* Pending SRCU callbacks. */ - int srcu_idx; /* Current reader array element. */ - bool srcu_gp_running; /* GP workqueue running? */ - bool srcu_gp_waiting; /* GP waiting for readers? */ + struct rcu_head *srcu_cb_head; /* Pending callbacks: Head. */ + struct rcu_head **srcu_cb_tail; /* Pending callbacks: Tail. */ struct work_struct srcu_work; /* For driving grace periods. */ #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; @@ -47,7 +46,7 @@ void srcu_drive_gp(struct work_struct *wp); #define __SRCU_STRUCT_INIT(name) \ { \ .srcu_wq = __SWAIT_QUEUE_HEAD_INITIALIZER(name.srcu_wq), \ - .srcu_cblist = RCU_SEGCBLIST_INITIALIZER(name.srcu_cblist), \ + .srcu_cb_tail = &name.srcu_cb_head, \ .srcu_work = __WORK_INITIALIZER(name.srcu_work, srcu_drive_gp), \ __SRCU_DEP_MAP_INIT(name) \ } @@ -63,31 +62,29 @@ void srcu_drive_gp(struct work_struct *wp); void synchronize_srcu(struct srcu_struct *sp); -static inline void synchronize_srcu_expedited(struct srcu_struct *sp) +/* + * Counts the new reader in the appropriate per-CPU element of the + * srcu_struct. Can be invoked from irq/bh handlers, but the matching + * __srcu_read_unlock() must be in the same handler instance. Returns an + * index that must be passed to the matching srcu_read_unlock(). + */ +static inline int __srcu_read_lock(struct srcu_struct *sp) { - synchronize_srcu(sp); -} + int idx; -static inline void srcu_barrier(struct srcu_struct *sp) -{ - synchronize_srcu(sp); + idx = READ_ONCE(sp->srcu_idx); + WRITE_ONCE(sp->srcu_lock_nesting[idx], sp->srcu_lock_nesting[idx] + 1); + return idx; } -static inline unsigned long srcu_batches_completed(struct srcu_struct *sp) +static inline void synchronize_srcu_expedited(struct srcu_struct *sp) { - return 0; + synchronize_srcu(sp); } -static inline void srcutorture_get_gp_data(enum rcutorture_type test_type, - struct srcu_struct *sp, int *flags, - unsigned long *gpnum, - unsigned long *completed) +static inline void srcu_barrier(struct srcu_struct *sp) { - if (test_type != SRCU_FLAVOR) - return; - *flags = 0; - *completed = sp->srcu_gp_seq; - *gpnum = *completed; + synchronize_srcu(sp); } #endif diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 32e86d85fd11..42973f787e7e 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -40,7 +40,7 @@ struct srcu_data { unsigned long srcu_unlock_count[2]; /* Unlocks per CPU. */ /* Update-side state. */ - spinlock_t lock ____cacheline_internodealigned_in_smp; + raw_spinlock_t __private lock ____cacheline_internodealigned_in_smp; struct rcu_segcblist srcu_cblist; /* List of callbacks.*/ unsigned long srcu_gp_seq_needed; /* Furthest future GP needed. */ unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ @@ -58,7 +58,7 @@ struct srcu_data { * Node in SRCU combining tree, similar in function to rcu_data. */ struct srcu_node { - spinlock_t lock; + raw_spinlock_t __private lock; unsigned long srcu_have_cbs[4]; /* GP seq for children */ /* having CBs, but only */ /* is > ->srcu_gq_seq. */ @@ -78,7 +78,7 @@ struct srcu_struct { struct srcu_node *level[RCU_NUM_LVLS + 1]; /* First node at each level. */ struct mutex srcu_cb_mutex; /* Serialize CB preparation. */ - spinlock_t gp_lock; /* protect ->srcu_cblist */ + raw_spinlock_t __private lock; /* Protect counters */ struct mutex srcu_gp_mutex; /* Serialize GP work. */ unsigned int srcu_idx; /* Current rdr array element. */ unsigned long srcu_gp_seq; /* Grace-period seq #. */ @@ -109,7 +109,7 @@ void process_srcu(struct work_struct *work); #define __SRCU_STRUCT_INIT(name) \ { \ .sda = &name##_srcu_data, \ - .gp_lock = __SPIN_LOCK_UNLOCKED(name.gp_lock), \ + .lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock), \ .srcu_gp_seq_needed = 0 - 1, \ __SRCU_DEP_MAP_INIT(name) \ } @@ -141,10 +141,5 @@ void process_srcu(struct work_struct *work); void synchronize_srcu_expedited(struct srcu_struct *sp); void srcu_barrier(struct srcu_struct *sp); -unsigned long srcu_batches_completed(struct srcu_struct *sp); - -void srcutorture_get_gp_data(enum rcutorture_type test_type, - struct srcu_struct *sp, int *flags, - unsigned long *gpnum, unsigned long *completed); #endif diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 7ba040c797ec..9d7529ffc4ce 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -13,7 +13,7 @@ #include <linux/ktime.h> #include <linux/sunrpc/types.h> #include <linux/spinlock.h> -#include <linux/wait.h> +#include <linux/wait_bit.h> #include <linux/workqueue.h> #include <linux/sunrpc/xdr.h> diff --git a/include/linux/uuid.h b/include/linux/uuid.h index 4dff73a89758..d1defe4ab167 100644 --- a/include/linux/uuid.h +++ b/include/linux/uuid.h @@ -18,29 +18,16 @@ #include <uapi/linux/uuid.h> -/* - * V1 (time-based) UUID definition [RFC 4122]. - * - the timestamp is a 60-bit value, split 32/16/12, and goes in 100ns - * increments since midnight 15th October 1582 - * - add AFS_UUID_TO_UNIX_TIME to convert unix time in 100ns units to UUID - * time - * - the clock sequence is a 14-bit counter to avoid duplicate times - */ -struct uuid_v1 { - __be32 time_low; /* low part of timestamp */ - __be16 time_mid; /* mid part of timestamp */ - __be16 time_hi_and_version; /* high part of timestamp and version */ -#define UUID_TO_UNIX_TIME 0x01b21dd213814000ULL -#define UUID_TIMEHI_MASK 0x0fff -#define UUID_VERSION_TIME 0x1000 /* time-based UUID */ -#define UUID_VERSION_NAME 0x3000 /* name-based UUID */ -#define UUID_VERSION_RANDOM 0x4000 /* (pseudo-)random generated UUID */ - u8 clock_seq_hi_and_reserved; /* clock seq hi and variant */ -#define UUID_CLOCKHI_MASK 0x3f -#define UUID_VARIANT_STD 0x80 - u8 clock_seq_low; /* clock seq low */ - u8 node[6]; /* spatially unique node ID (MAC addr) */ -}; +typedef struct { + __u8 b[16]; +} uuid_t; + +#define UUID_INIT(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) \ +((uuid_t) \ +{{ ((a) >> 24) & 0xff, ((a) >> 16) & 0xff, ((a) >> 8) & 0xff, (a) & 0xff, \ + ((b) >> 8) & 0xff, (b) & 0xff, \ + ((c) >> 8) & 0xff, (c) & 0xff, \ + (d0), (d1), (d2), (d3), (d4), (d5), (d6), (d7) }}) /* * The length of a UUID string ("aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee") @@ -48,27 +35,73 @@ struct uuid_v1 { */ #define UUID_STRING_LEN 36 -static inline int uuid_le_cmp(const uuid_le u1, const uuid_le u2) +extern const guid_t guid_null; +extern const uuid_t uuid_null; + +static inline bool guid_equal(const guid_t *u1, const guid_t *u2) +{ + return memcmp(u1, u2, sizeof(guid_t)) == 0; +} + +static inline void guid_copy(guid_t *dst, const guid_t *src) +{ + memcpy(dst, src, sizeof(guid_t)); +} + +static inline bool guid_is_null(const guid_t *guid) +{ + return guid_equal(guid, &guid_null); +} + +static inline bool uuid_equal(const uuid_t *u1, const uuid_t *u2) +{ + return memcmp(u1, u2, sizeof(uuid_t)) == 0; +} + +static inline void uuid_copy(uuid_t *dst, const uuid_t *src) { - return memcmp(&u1, &u2, sizeof(uuid_le)); + memcpy(dst, src, sizeof(uuid_t)); } -static inline int uuid_be_cmp(const uuid_be u1, const uuid_be u2) +static inline bool uuid_is_null(const uuid_t *uuid) { - return memcmp(&u1, &u2, sizeof(uuid_be)); + return uuid_equal(uuid, &uuid_null); } void generate_random_uuid(unsigned char uuid[16]); -extern void uuid_le_gen(uuid_le *u); -extern void uuid_be_gen(uuid_be *u); +extern void guid_gen(guid_t *u); +extern void uuid_gen(uuid_t *u); bool __must_check uuid_is_valid(const char *uuid); -extern const u8 uuid_le_index[16]; -extern const u8 uuid_be_index[16]; +extern const u8 guid_index[16]; +extern const u8 uuid_index[16]; + +int guid_parse(const char *uuid, guid_t *u); +int uuid_parse(const char *uuid, uuid_t *u); + +/* backwards compatibility, don't use in new code */ +typedef uuid_t uuid_be; +#define UUID_BE(a, _b, c, d0, d1, d2, d3, d4, d5, d6, d7) \ + UUID_INIT(a, _b, c, d0, d1, d2, d3, d4, d5, d6, d7) +#define NULL_UUID_BE \ + UUID_BE(0x00000000, 0x0000, 0x0000, 0x00, 0x00, 0x00, 0x00, \ + 0x00, 0x00, 0x00, 0x00) -int uuid_le_to_bin(const char *uuid, uuid_le *u); -int uuid_be_to_bin(const char *uuid, uuid_be *u); +#define uuid_le_gen(u) guid_gen(u) +#define uuid_be_gen(u) uuid_gen(u) +#define uuid_le_to_bin(guid, u) guid_parse(guid, u) +#define uuid_be_to_bin(uuid, u) uuid_parse(uuid, u) + +static inline int uuid_le_cmp(const guid_t u1, const guid_t u2) +{ + return memcmp(&u1, &u2, sizeof(guid_t)); +} + +static inline int uuid_be_cmp(const uuid_t u1, const uuid_t u2) +{ + return memcmp(&u1, &u2, sizeof(uuid_t)); +} #endif diff --git a/include/linux/vfio.h b/include/linux/vfio.h index edf9b2cad277..f57076b958b7 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -183,7 +183,7 @@ struct virqfd { void (*thread)(void *, void *); void *data; struct work_struct inject; - wait_queue_t wait; + wait_queue_entry_t wait; poll_table pt; struct work_struct shutdown; struct virqfd **pvirqfd; diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index d84ae90ccd5c..be3ab2d13adf 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -93,10 +93,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #endif #endif #ifdef CONFIG_DEBUG_TLBFLUSH -#ifdef CONFIG_SMP NR_TLB_REMOTE_FLUSH, /* cpu tried to flush others' tlbs */ NR_TLB_REMOTE_FLUSH_RECEIVED,/* cpu received ipi for flush */ -#endif /* CONFIG_SMP */ NR_TLB_LOCAL_FLUSH_ALL, NR_TLB_LOCAL_FLUSH_ONE, #endif /* CONFIG_DEBUG_TLBFLUSH */ diff --git a/include/linux/wait.h b/include/linux/wait.h index db076ca7f11d..b289c96151ee 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -10,38 +10,30 @@ #include <asm/current.h> #include <uapi/linux/wait.h> -typedef struct __wait_queue wait_queue_t; -typedef int (*wait_queue_func_t)(wait_queue_t *wait, unsigned mode, int flags, void *key); -int default_wake_function(wait_queue_t *wait, unsigned mode, int flags, void *key); +typedef struct wait_queue_entry wait_queue_entry_t; -/* __wait_queue::flags */ +typedef int (*wait_queue_func_t)(struct wait_queue_entry *wq_entry, unsigned mode, int flags, void *key); +int default_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int flags, void *key); + +/* wait_queue_entry::flags */ #define WQ_FLAG_EXCLUSIVE 0x01 #define WQ_FLAG_WOKEN 0x02 -struct __wait_queue { +/* + * A single wait-queue entry structure: + */ +struct wait_queue_entry { unsigned int flags; void *private; wait_queue_func_t func; - struct list_head task_list; -}; - -struct wait_bit_key { - void *flags; - int bit_nr; -#define WAIT_ATOMIC_T_BIT_NR -1 - unsigned long timeout; + struct list_head entry; }; -struct wait_bit_queue { - struct wait_bit_key key; - wait_queue_t wait; -}; - -struct __wait_queue_head { +struct wait_queue_head { spinlock_t lock; - struct list_head task_list; + struct list_head head; }; -typedef struct __wait_queue_head wait_queue_head_t; +typedef struct wait_queue_head wait_queue_head_t; struct task_struct; @@ -49,82 +41,76 @@ struct task_struct; * Macros for declaration and initialisaton of the datatypes */ -#define __WAITQUEUE_INITIALIZER(name, tsk) { \ - .private = tsk, \ - .func = default_wake_function, \ - .task_list = { NULL, NULL } } +#define __WAITQUEUE_INITIALIZER(name, tsk) { \ + .private = tsk, \ + .func = default_wake_function, \ + .entry = { NULL, NULL } } -#define DECLARE_WAITQUEUE(name, tsk) \ - wait_queue_t name = __WAITQUEUE_INITIALIZER(name, tsk) +#define DECLARE_WAITQUEUE(name, tsk) \ + struct wait_queue_entry name = __WAITQUEUE_INITIALIZER(name, tsk) -#define __WAIT_QUEUE_HEAD_INITIALIZER(name) { \ - .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ - .task_list = { &(name).task_list, &(name).task_list } } +#define __WAIT_QUEUE_HEAD_INITIALIZER(name) { \ + .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ + .head = { &(name).head, &(name).head } } #define DECLARE_WAIT_QUEUE_HEAD(name) \ - wait_queue_head_t name = __WAIT_QUEUE_HEAD_INITIALIZER(name) - -#define __WAIT_BIT_KEY_INITIALIZER(word, bit) \ - { .flags = word, .bit_nr = bit, } + struct wait_queue_head name = __WAIT_QUEUE_HEAD_INITIALIZER(name) -#define __WAIT_ATOMIC_T_KEY_INITIALIZER(p) \ - { .flags = p, .bit_nr = WAIT_ATOMIC_T_BIT_NR, } +extern void __init_waitqueue_head(struct wait_queue_head *wq_head, const char *name, struct lock_class_key *); -extern void __init_waitqueue_head(wait_queue_head_t *q, const char *name, struct lock_class_key *); - -#define init_waitqueue_head(q) \ - do { \ - static struct lock_class_key __key; \ - \ - __init_waitqueue_head((q), #q, &__key); \ +#define init_waitqueue_head(wq_head) \ + do { \ + static struct lock_class_key __key; \ + \ + __init_waitqueue_head((wq_head), #wq_head, &__key); \ } while (0) #ifdef CONFIG_LOCKDEP # define __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) \ ({ init_waitqueue_head(&name); name; }) # define DECLARE_WAIT_QUEUE_HEAD_ONSTACK(name) \ - wait_queue_head_t name = __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) + struct wait_queue_head name = __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) #else # define DECLARE_WAIT_QUEUE_HEAD_ONSTACK(name) DECLARE_WAIT_QUEUE_HEAD(name) #endif -static inline void init_waitqueue_entry(wait_queue_t *q, struct task_struct *p) +static inline void init_waitqueue_entry(struct wait_queue_entry *wq_entry, struct task_struct *p) { - q->flags = 0; - q->private = p; - q->func = default_wake_function; + wq_entry->flags = 0; + wq_entry->private = p; + wq_entry->func = default_wake_function; } static inline void -init_waitqueue_func_entry(wait_queue_t *q, wait_queue_func_t func) +init_waitqueue_func_entry(struct wait_queue_entry *wq_entry, wait_queue_func_t func) { - q->flags = 0; - q->private = NULL; - q->func = func; + wq_entry->flags = 0; + wq_entry->private = NULL; + wq_entry->func = func; } /** * waitqueue_active -- locklessly test for waiters on the queue - * @q: the waitqueue to test for waiters + * @wq_head: the waitqueue to test for waiters * * returns true if the wait list is not empty * * NOTE: this function is lockless and requires care, incorrect usage _will_ * lead to sporadic and non-obvious failure. * - * Use either while holding wait_queue_head_t::lock or when used for wakeups + * Use either while holding wait_queue_head::lock or when used for wakeups * with an extra smp_mb() like: * * CPU0 - waker CPU1 - waiter * * for (;;) { - * @cond = true; prepare_to_wait(&wq, &wait, state); + * @cond = true; prepare_to_wait(&wq_head, &wait, state); * smp_mb(); // smp_mb() from set_current_state() - * if (waitqueue_active(wq)) if (@cond) - * wake_up(wq); break; + * if (waitqueue_active(wq_head)) if (@cond) + * wake_up(wq_head); break; * schedule(); * } - * finish_wait(&wq, &wait); + * finish_wait(&wq_head, &wait); * * Because without the explicit smp_mb() it's possible for the * waitqueue_active() load to get hoisted over the @cond store such that we'll @@ -133,20 +119,20 @@ init_waitqueue_func_entry(wait_queue_t *q, wait_queue_func_t func) * Also note that this 'optimization' trades a spin_lock() for an smp_mb(), * which (when the lock is uncontended) are of roughly equal cost. */ -static inline int waitqueue_active(wait_queue_head_t *q) +static inline int waitqueue_active(struct wait_queue_head *wq_head) { - return !list_empty(&q->task_list); + return !list_empty(&wq_head->head); } /** * wq_has_sleeper - check if there are any waiting processes - * @wq: wait queue head + * @wq_head: wait queue head * - * Returns true if wq has waiting processes + * Returns true if wq_head has waiting processes * * Please refer to the comment for waitqueue_active. */ -static inline bool wq_has_sleeper(wait_queue_head_t *wq) +static inline bool wq_has_sleeper(struct wait_queue_head *wq_head) { /* * We need to be sure we are in sync with the @@ -156,63 +142,51 @@ static inline bool wq_has_sleeper(wait_queue_head_t *wq) * waiting side. */ smp_mb(); - return waitqueue_active(wq); + return waitqueue_active(wq_head); } -extern void add_wait_queue(wait_queue_head_t *q, wait_queue_t *wait); -extern void add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t *wait); -extern void remove_wait_queue(wait_queue_head_t *q, wait_queue_t *wait); +extern void add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); +extern void add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); +extern void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); -static inline void __add_wait_queue(wait_queue_head_t *head, wait_queue_t *new) +static inline void __add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { - list_add(&new->task_list, &head->task_list); + list_add(&wq_entry->entry, &wq_head->head); } /* * Used for wake-one threads: */ static inline void -__add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t *wait) +__add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { - wait->flags |= WQ_FLAG_EXCLUSIVE; - __add_wait_queue(q, wait); + wq_entry->flags |= WQ_FLAG_EXCLUSIVE; + __add_wait_queue(wq_head, wq_entry); } -static inline void __add_wait_queue_tail(wait_queue_head_t *head, - wait_queue_t *new) +static inline void __add_wait_queue_entry_tail(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { - list_add_tail(&new->task_list, &head->task_list); + list_add_tail(&wq_entry->entry, &wq_head->head); } static inline void -__add_wait_queue_tail_exclusive(wait_queue_head_t *q, wait_queue_t *wait) +__add_wait_queue_entry_tail_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { - wait->flags |= WQ_FLAG_EXCLUSIVE; - __add_wait_queue_tail(q, wait); + wq_entry->flags |= WQ_FLAG_EXCLUSIVE; + __add_wait_queue_entry_tail(wq_head, wq_entry); } static inline void -__remove_wait_queue(wait_queue_head_t *head, wait_queue_t *old) +__remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { - list_del(&old->task_list); + list_del(&wq_entry->entry); } -typedef int wait_bit_action_f(struct wait_bit_key *, int mode); -void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key); -void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key); -void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key); -void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr); -void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr); -void __wake_up_bit(wait_queue_head_t *, void *, int); -int __wait_on_bit(wait_queue_head_t *, struct wait_bit_queue *, wait_bit_action_f *, unsigned); -int __wait_on_bit_lock(wait_queue_head_t *, struct wait_bit_queue *, wait_bit_action_f *, unsigned); -void wake_up_bit(void *, int); -void wake_up_atomic_t(atomic_t *); -int out_of_line_wait_on_bit(void *, int, wait_bit_action_f *, unsigned); -int out_of_line_wait_on_bit_timeout(void *, int, wait_bit_action_f *, unsigned, unsigned long); -int out_of_line_wait_on_bit_lock(void *, int, wait_bit_action_f *, unsigned); -int out_of_line_wait_on_atomic_t(atomic_t *, int (*)(atomic_t *), unsigned); -wait_queue_head_t *bit_waitqueue(void *, int); +void __wake_up(struct wait_queue_head *wq_head, unsigned int mode, int nr, void *key); +void __wake_up_locked_key(struct wait_queue_head *wq_head, unsigned int mode, void *key); +void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, int nr, void *key); +void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr); +void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode, int nr); #define wake_up(x) __wake_up(x, TASK_NORMAL, 1, NULL) #define wake_up_nr(x, nr) __wake_up(x, TASK_NORMAL, nr, NULL) @@ -228,28 +202,28 @@ wait_queue_head_t *bit_waitqueue(void *, int); /* * Wakeup macros to be used to report events to the targets. */ -#define wake_up_poll(x, m) \ +#define wake_up_poll(x, m) \ __wake_up(x, TASK_NORMAL, 1, (void *) (m)) -#define wake_up_locked_poll(x, m) \ +#define wake_up_locked_poll(x, m) \ __wake_up_locked_key((x), TASK_NORMAL, (void *) (m)) -#define wake_up_interruptible_poll(x, m) \ +#define wake_up_interruptible_poll(x, m) \ __wake_up(x, TASK_INTERRUPTIBLE, 1, (void *) (m)) -#define wake_up_interruptible_sync_poll(x, m) \ +#define wake_up_interruptible_sync_poll(x, m) \ __wake_up_sync_key((x), TASK_INTERRUPTIBLE, 1, (void *) (m)) -#define ___wait_cond_timeout(condition) \ -({ \ - bool __cond = (condition); \ - if (__cond && !__ret) \ - __ret = 1; \ - __cond || !__ret; \ +#define ___wait_cond_timeout(condition) \ +({ \ + bool __cond = (condition); \ + if (__cond && !__ret) \ + __ret = 1; \ + __cond || !__ret; \ }) -#define ___wait_is_interruptible(state) \ - (!__builtin_constant_p(state) || \ - state == TASK_INTERRUPTIBLE || state == TASK_KILLABLE) \ +#define ___wait_is_interruptible(state) \ + (!__builtin_constant_p(state) || \ + state == TASK_INTERRUPTIBLE || state == TASK_KILLABLE) \ -extern void init_wait_entry(wait_queue_t *__wait, int flags); +extern void init_wait_entry(struct wait_queue_entry *wq_entry, int flags); /* * The below macro ___wait_event() has an explicit shadow of the __ret @@ -263,108 +237,108 @@ extern void init_wait_entry(wait_queue_t *__wait, int flags); * otherwise. */ -#define ___wait_event(wq, condition, state, exclusive, ret, cmd) \ -({ \ - __label__ __out; \ - wait_queue_t __wait; \ - long __ret = ret; /* explicit shadow */ \ - \ - init_wait_entry(&__wait, exclusive ? WQ_FLAG_EXCLUSIVE : 0); \ - for (;;) { \ - long __int = prepare_to_wait_event(&wq, &__wait, state);\ - \ - if (condition) \ - break; \ - \ - if (___wait_is_interruptible(state) && __int) { \ - __ret = __int; \ - goto __out; \ - } \ - \ - cmd; \ - } \ - finish_wait(&wq, &__wait); \ -__out: __ret; \ +#define ___wait_event(wq_head, condition, state, exclusive, ret, cmd) \ +({ \ + __label__ __out; \ + struct wait_queue_entry __wq_entry; \ + long __ret = ret; /* explicit shadow */ \ + \ + init_wait_entry(&__wq_entry, exclusive ? WQ_FLAG_EXCLUSIVE : 0); \ + for (;;) { \ + long __int = prepare_to_wait_event(&wq_head, &__wq_entry, state);\ + \ + if (condition) \ + break; \ + \ + if (___wait_is_interruptible(state) && __int) { \ + __ret = __int; \ + goto __out; \ + } \ + \ + cmd; \ + } \ + finish_wait(&wq_head, &__wq_entry); \ +__out: __ret; \ }) -#define __wait_event(wq, condition) \ - (void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ +#define __wait_event(wq_head, condition) \ + (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ schedule()) /** * wait_event - sleep until a condition gets true - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time - * the waitqueue @wq is woken up. + * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. */ -#define wait_event(wq, condition) \ -do { \ - might_sleep(); \ - if (condition) \ - break; \ - __wait_event(wq, condition); \ +#define wait_event(wq_head, condition) \ +do { \ + might_sleep(); \ + if (condition) \ + break; \ + __wait_event(wq_head, condition); \ } while (0) -#define __io_wait_event(wq, condition) \ - (void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ +#define __io_wait_event(wq_head, condition) \ + (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ io_schedule()) /* * io_wait_event() -- like wait_event() but with io_schedule() */ -#define io_wait_event(wq, condition) \ -do { \ - might_sleep(); \ - if (condition) \ - break; \ - __io_wait_event(wq, condition); \ +#define io_wait_event(wq_head, condition) \ +do { \ + might_sleep(); \ + if (condition) \ + break; \ + __io_wait_event(wq_head, condition); \ } while (0) -#define __wait_event_freezable(wq, condition) \ - ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, 0, \ +#define __wait_event_freezable(wq_head, condition) \ + ___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0, \ schedule(); try_to_freeze()) /** * wait_event_freezable - sleep (or freeze) until a condition gets true - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE -- so as not to contribute * to system load) until the @condition evaluates to true. The - * @condition is checked each time the waitqueue @wq is woken up. + * @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. */ -#define wait_event_freezable(wq, condition) \ -({ \ - int __ret = 0; \ - might_sleep(); \ - if (!(condition)) \ - __ret = __wait_event_freezable(wq, condition); \ - __ret; \ +#define wait_event_freezable(wq_head, condition) \ +({ \ + int __ret = 0; \ + might_sleep(); \ + if (!(condition)) \ + __ret = __wait_event_freezable(wq_head, condition); \ + __ret; \ }) -#define __wait_event_timeout(wq, condition, timeout) \ - ___wait_event(wq, ___wait_cond_timeout(condition), \ - TASK_UNINTERRUPTIBLE, 0, timeout, \ +#define __wait_event_timeout(wq_head, condition, timeout) \ + ___wait_event(wq_head, ___wait_cond_timeout(condition), \ + TASK_UNINTERRUPTIBLE, 0, timeout, \ __ret = schedule_timeout(__ret)) /** * wait_event_timeout - sleep until a condition gets true or a timeout elapses - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time - * the waitqueue @wq is woken up. + * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. @@ -375,83 +349,83 @@ do { \ * or the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed. */ -#define wait_event_timeout(wq, condition, timeout) \ -({ \ - long __ret = timeout; \ - might_sleep(); \ - if (!___wait_cond_timeout(condition)) \ - __ret = __wait_event_timeout(wq, condition, timeout); \ - __ret; \ +#define wait_event_timeout(wq_head, condition, timeout) \ +({ \ + long __ret = timeout; \ + might_sleep(); \ + if (!___wait_cond_timeout(condition)) \ + __ret = __wait_event_timeout(wq_head, condition, timeout); \ + __ret; \ }) -#define __wait_event_freezable_timeout(wq, condition, timeout) \ - ___wait_event(wq, ___wait_cond_timeout(condition), \ - TASK_INTERRUPTIBLE, 0, timeout, \ +#define __wait_event_freezable_timeout(wq_head, condition, timeout) \ + ___wait_event(wq_head, ___wait_cond_timeout(condition), \ + TASK_INTERRUPTIBLE, 0, timeout, \ __ret = schedule_timeout(__ret); try_to_freeze()) /* * like wait_event_timeout() -- except it uses TASK_INTERRUPTIBLE to avoid * increasing load and is freezable. */ -#define wait_event_freezable_timeout(wq, condition, timeout) \ -({ \ - long __ret = timeout; \ - might_sleep(); \ - if (!___wait_cond_timeout(condition)) \ - __ret = __wait_event_freezable_timeout(wq, condition, timeout); \ - __ret; \ +#define wait_event_freezable_timeout(wq_head, condition, timeout) \ +({ \ + long __ret = timeout; \ + might_sleep(); \ + if (!___wait_cond_timeout(condition)) \ + __ret = __wait_event_freezable_timeout(wq_head, condition, timeout); \ + __ret; \ }) -#define __wait_event_exclusive_cmd(wq, condition, cmd1, cmd2) \ - (void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 1, 0, \ +#define __wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2) \ + (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 1, 0, \ cmd1; schedule(); cmd2) /* * Just like wait_event_cmd(), except it sets exclusive flag */ -#define wait_event_exclusive_cmd(wq, condition, cmd1, cmd2) \ -do { \ - if (condition) \ - break; \ - __wait_event_exclusive_cmd(wq, condition, cmd1, cmd2); \ +#define wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2) \ +do { \ + if (condition) \ + break; \ + __wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2); \ } while (0) -#define __wait_event_cmd(wq, condition, cmd1, cmd2) \ - (void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ +#define __wait_event_cmd(wq_head, condition, cmd1, cmd2) \ + (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ cmd1; schedule(); cmd2) /** * wait_event_cmd - sleep until a condition gets true - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @cmd1: the command will be executed before sleep * @cmd2: the command will be executed after sleep * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time - * the waitqueue @wq is woken up. + * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. */ -#define wait_event_cmd(wq, condition, cmd1, cmd2) \ -do { \ - if (condition) \ - break; \ - __wait_event_cmd(wq, condition, cmd1, cmd2); \ +#define wait_event_cmd(wq_head, condition, cmd1, cmd2) \ +do { \ + if (condition) \ + break; \ + __wait_event_cmd(wq_head, condition, cmd1, cmd2); \ } while (0) -#define __wait_event_interruptible(wq, condition) \ - ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, 0, \ +#define __wait_event_interruptible(wq_head, condition) \ + ___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0, \ schedule()) /** * wait_event_interruptible - sleep until a condition gets true - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. - * The @condition is checked each time the waitqueue @wq is woken up. + * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. @@ -459,29 +433,29 @@ do { \ * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ -#define wait_event_interruptible(wq, condition) \ -({ \ - int __ret = 0; \ - might_sleep(); \ - if (!(condition)) \ - __ret = __wait_event_interruptible(wq, condition); \ - __ret; \ +#define wait_event_interruptible(wq_head, condition) \ +({ \ + int __ret = 0; \ + might_sleep(); \ + if (!(condition)) \ + __ret = __wait_event_interruptible(wq_head, condition); \ + __ret; \ }) -#define __wait_event_interruptible_timeout(wq, condition, timeout) \ - ___wait_event(wq, ___wait_cond_timeout(condition), \ - TASK_INTERRUPTIBLE, 0, timeout, \ +#define __wait_event_interruptible_timeout(wq_head, condition, timeout) \ + ___wait_event(wq_head, ___wait_cond_timeout(condition), \ + TASK_INTERRUPTIBLE, 0, timeout, \ __ret = schedule_timeout(__ret)) /** * wait_event_interruptible_timeout - sleep until a condition gets true or a timeout elapses - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. - * The @condition is checked each time the waitqueue @wq is woken up. + * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. @@ -493,50 +467,49 @@ do { \ * to %true before the @timeout elapsed, or -%ERESTARTSYS if it was * interrupted by a signal. */ -#define wait_event_interruptible_timeout(wq, condition, timeout) \ -({ \ - long __ret = timeout; \ - might_sleep(); \ - if (!___wait_cond_timeout(condition)) \ - __ret = __wait_event_interruptible_timeout(wq, \ - condition, timeout); \ - __ret; \ +#define wait_event_interruptible_timeout(wq_head, condition, timeout) \ +({ \ + long __ret = timeout; \ + might_sleep(); \ + if (!___wait_cond_timeout(condition)) \ + __ret = __wait_event_interruptible_timeout(wq_head, \ + condition, timeout); \ + __ret; \ }) -#define __wait_event_hrtimeout(wq, condition, timeout, state) \ -({ \ - int __ret = 0; \ - struct hrtimer_sleeper __t; \ - \ - hrtimer_init_on_stack(&__t.timer, CLOCK_MONOTONIC, \ - HRTIMER_MODE_REL); \ - hrtimer_init_sleeper(&__t, current); \ - if ((timeout) != KTIME_MAX) \ - hrtimer_start_range_ns(&__t.timer, timeout, \ - current->timer_slack_ns, \ - HRTIMER_MODE_REL); \ - \ - __ret = ___wait_event(wq, condition, state, 0, 0, \ - if (!__t.task) { \ - __ret = -ETIME; \ - break; \ - } \ - schedule()); \ - \ - hrtimer_cancel(&__t.timer); \ - destroy_hrtimer_on_stack(&__t.timer); \ - __ret; \ +#define __wait_event_hrtimeout(wq_head, condition, timeout, state) \ +({ \ + int __ret = 0; \ + struct hrtimer_sleeper __t; \ + \ + hrtimer_init_on_stack(&__t.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); \ + hrtimer_init_sleeper(&__t, current); \ + if ((timeout) != KTIME_MAX) \ + hrtimer_start_range_ns(&__t.timer, timeout, \ + current->timer_slack_ns, \ + HRTIMER_MODE_REL); \ + \ + __ret = ___wait_event(wq_head, condition, state, 0, 0, \ + if (!__t.task) { \ + __ret = -ETIME; \ + break; \ + } \ + schedule()); \ + \ + hrtimer_cancel(&__t.timer); \ + destroy_hrtimer_on_stack(&__t.timer); \ + __ret; \ }) /** * wait_event_hrtimeout - sleep until a condition gets true or a timeout elapses - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, as a ktime_t * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. - * The @condition is checked each time the waitqueue @wq is woken up. + * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. @@ -544,25 +517,25 @@ do { \ * The function returns 0 if @condition became true, or -ETIME if the timeout * elapsed. */ -#define wait_event_hrtimeout(wq, condition, timeout) \ -({ \ - int __ret = 0; \ - might_sleep(); \ - if (!(condition)) \ - __ret = __wait_event_hrtimeout(wq, condition, timeout, \ - TASK_UNINTERRUPTIBLE); \ - __ret; \ +#define wait_event_hrtimeout(wq_head, condition, timeout) \ +({ \ + int __ret = 0; \ + might_sleep(); \ + if (!(condition)) \ + __ret = __wait_event_hrtimeout(wq_head, condition, timeout, \ + TASK_UNINTERRUPTIBLE); \ + __ret; \ }) /** * wait_event_interruptible_hrtimeout - sleep until a condition gets true or a timeout elapses - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, as a ktime_t * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. - * The @condition is checked each time the waitqueue @wq is woken up. + * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. @@ -570,73 +543,73 @@ do { \ * The function returns 0 if @condition became true, -ERESTARTSYS if it was * interrupted by a signal, or -ETIME if the timeout elapsed. */ -#define wait_event_interruptible_hrtimeout(wq, condition, timeout) \ -({ \ - long __ret = 0; \ - might_sleep(); \ - if (!(condition)) \ - __ret = __wait_event_hrtimeout(wq, condition, timeout, \ - TASK_INTERRUPTIBLE); \ - __ret; \ +#define wait_event_interruptible_hrtimeout(wq, condition, timeout) \ +({ \ + long __ret = 0; \ + might_sleep(); \ + if (!(condition)) \ + __ret = __wait_event_hrtimeout(wq, condition, timeout, \ + TASK_INTERRUPTIBLE); \ + __ret; \ }) -#define __wait_event_interruptible_exclusive(wq, condition) \ - ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0, \ +#define __wait_event_interruptible_exclusive(wq, condition) \ + ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0, \ schedule()) -#define wait_event_interruptible_exclusive(wq, condition) \ -({ \ - int __ret = 0; \ - might_sleep(); \ - if (!(condition)) \ - __ret = __wait_event_interruptible_exclusive(wq, condition);\ - __ret; \ +#define wait_event_interruptible_exclusive(wq, condition) \ +({ \ + int __ret = 0; \ + might_sleep(); \ + if (!(condition)) \ + __ret = __wait_event_interruptible_exclusive(wq, condition); \ + __ret; \ }) -#define __wait_event_killable_exclusive(wq, condition) \ - ___wait_event(wq, condition, TASK_KILLABLE, 1, 0, \ +#define __wait_event_killable_exclusive(wq, condition) \ + ___wait_event(wq, condition, TASK_KILLABLE, 1, 0, \ schedule()) -#define wait_event_killable_exclusive(wq, condition) \ -({ \ - int __ret = 0; \ - might_sleep(); \ - if (!(condition)) \ - __ret = __wait_event_killable_exclusive(wq, condition); \ - __ret; \ +#define wait_event_killable_exclusive(wq, condition) \ +({ \ + int __ret = 0; \ + might_sleep(); \ + if (!(condition)) \ + __ret = __wait_event_killable_exclusive(wq, condition); \ + __ret; \ }) -#define __wait_event_freezable_exclusive(wq, condition) \ - ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0, \ +#define __wait_event_freezable_exclusive(wq, condition) \ + ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0, \ schedule(); try_to_freeze()) -#define wait_event_freezable_exclusive(wq, condition) \ -({ \ - int __ret = 0; \ - might_sleep(); \ - if (!(condition)) \ - __ret = __wait_event_freezable_exclusive(wq, condition);\ - __ret; \ +#define wait_event_freezable_exclusive(wq, condition) \ +({ \ + int __ret = 0; \ + might_sleep(); \ + if (!(condition)) \ + __ret = __wait_event_freezable_exclusive(wq, condition); \ + __ret; \ }) -extern int do_wait_intr(wait_queue_head_t *, wait_queue_t *); -extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *); - -#define __wait_event_interruptible_locked(wq, condition, exclusive, fn) \ -({ \ - int __ret; \ - DEFINE_WAIT(__wait); \ - if (exclusive) \ - __wait.flags |= WQ_FLAG_EXCLUSIVE; \ - do { \ - __ret = fn(&(wq), &__wait); \ - if (__ret) \ - break; \ - } while (!(condition)); \ - __remove_wait_queue(&(wq), &__wait); \ - __set_current_state(TASK_RUNNING); \ - __ret; \ +extern int do_wait_intr(wait_queue_head_t *, wait_queue_entry_t *); +extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_entry_t *); + +#define __wait_event_interruptible_locked(wq, condition, exclusive, fn) \ +({ \ + int __ret; \ + DEFINE_WAIT(__wait); \ + if (exclusive) \ + __wait.flags |= WQ_FLAG_EXCLUSIVE; \ + do { \ + __ret = fn(&(wq), &__wait); \ + if (__ret) \ + break; \ + } while (!(condition)); \ + __remove_wait_queue(&(wq), &__wait); \ + __set_current_state(TASK_RUNNING); \ + __ret; \ }) @@ -663,8 +636,8 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *); * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ -#define wait_event_interruptible_locked(wq, condition) \ - ((condition) \ +#define wait_event_interruptible_locked(wq, condition) \ + ((condition) \ ? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr)) /** @@ -690,8 +663,8 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *); * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ -#define wait_event_interruptible_locked_irq(wq, condition) \ - ((condition) \ +#define wait_event_interruptible_locked_irq(wq, condition) \ + ((condition) \ ? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr_irq)) /** @@ -721,8 +694,8 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *); * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ -#define wait_event_interruptible_exclusive_locked(wq, condition) \ - ((condition) \ +#define wait_event_interruptible_exclusive_locked(wq, condition) \ + ((condition) \ ? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr)) /** @@ -752,12 +725,12 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *); * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ -#define wait_event_interruptible_exclusive_locked_irq(wq, condition) \ - ((condition) \ +#define wait_event_interruptible_exclusive_locked_irq(wq, condition) \ + ((condition) \ ? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr_irq)) -#define __wait_event_killable(wq, condition) \ +#define __wait_event_killable(wq, condition) \ ___wait_event(wq, condition, TASK_KILLABLE, 0, 0, schedule()) /** @@ -775,21 +748,21 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *); * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ -#define wait_event_killable(wq, condition) \ -({ \ - int __ret = 0; \ - might_sleep(); \ - if (!(condition)) \ - __ret = __wait_event_killable(wq, condition); \ - __ret; \ +#define wait_event_killable(wq_head, condition) \ +({ \ + int __ret = 0; \ + might_sleep(); \ + if (!(condition)) \ + __ret = __wait_event_killable(wq_head, condition); \ + __ret; \ }) -#define __wait_event_lock_irq(wq, condition, lock, cmd) \ - (void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ - spin_unlock_irq(&lock); \ - cmd; \ - schedule(); \ +#define __wait_event_lock_irq(wq_head, condition, lock, cmd) \ + (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ + spin_unlock_irq(&lock); \ + cmd; \ + schedule(); \ spin_lock_irq(&lock)) /** @@ -797,7 +770,7 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *); * condition is checked under the lock. This * is expected to be called with the lock * taken. - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before cmd * and schedule() and reacquired afterwards. @@ -806,7 +779,7 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *); * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time - * the waitqueue @wq is woken up. + * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. @@ -815,11 +788,11 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *); * dropped before invoking the cmd and going to sleep and is reacquired * afterwards. */ -#define wait_event_lock_irq_cmd(wq, condition, lock, cmd) \ -do { \ - if (condition) \ - break; \ - __wait_event_lock_irq(wq, condition, lock, cmd); \ +#define wait_event_lock_irq_cmd(wq_head, condition, lock, cmd) \ +do { \ + if (condition) \ + break; \ + __wait_event_lock_irq(wq_head, condition, lock, cmd); \ } while (0) /** @@ -827,14 +800,14 @@ do { \ * condition is checked under the lock. This * is expected to be called with the lock * taken. - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before schedule() * and reacquired afterwards. * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time - * the waitqueue @wq is woken up. + * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. @@ -842,26 +815,26 @@ do { \ * This is supposed to be called while holding the lock. The lock is * dropped before going to sleep and is reacquired afterwards. */ -#define wait_event_lock_irq(wq, condition, lock) \ -do { \ - if (condition) \ - break; \ - __wait_event_lock_irq(wq, condition, lock, ); \ +#define wait_event_lock_irq(wq_head, condition, lock) \ +do { \ + if (condition) \ + break; \ + __wait_event_lock_irq(wq_head, condition, lock, ); \ } while (0) -#define __wait_event_interruptible_lock_irq(wq, condition, lock, cmd) \ - ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, 0, \ - spin_unlock_irq(&lock); \ - cmd; \ - schedule(); \ +#define __wait_event_interruptible_lock_irq(wq_head, condition, lock, cmd) \ + ___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0, \ + spin_unlock_irq(&lock); \ + cmd; \ + schedule(); \ spin_lock_irq(&lock)) /** * wait_event_interruptible_lock_irq_cmd - sleep until a condition gets true. * The condition is checked under the lock. This is expected to * be called with the lock taken. - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before cmd and * schedule() and reacquired afterwards. @@ -870,7 +843,7 @@ do { \ * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. The @condition is - * checked each time the waitqueue @wq is woken up. + * checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. @@ -882,27 +855,27 @@ do { \ * The macro will return -ERESTARTSYS if it was interrupted by a signal * and 0 if @condition evaluated to true. */ -#define wait_event_interruptible_lock_irq_cmd(wq, condition, lock, cmd) \ -({ \ - int __ret = 0; \ - if (!(condition)) \ - __ret = __wait_event_interruptible_lock_irq(wq, \ - condition, lock, cmd); \ - __ret; \ +#define wait_event_interruptible_lock_irq_cmd(wq_head, condition, lock, cmd) \ +({ \ + int __ret = 0; \ + if (!(condition)) \ + __ret = __wait_event_interruptible_lock_irq(wq_head, \ + condition, lock, cmd); \ + __ret; \ }) /** * wait_event_interruptible_lock_irq - sleep until a condition gets true. * The condition is checked under the lock. This is expected * to be called with the lock taken. - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before schedule() * and reacquired afterwards. * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or signal is received. The @condition is - * checked each time the waitqueue @wq is woken up. + * checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. @@ -913,28 +886,28 @@ do { \ * The macro will return -ERESTARTSYS if it was interrupted by a signal * and 0 if @condition evaluated to true. */ -#define wait_event_interruptible_lock_irq(wq, condition, lock) \ -({ \ - int __ret = 0; \ - if (!(condition)) \ - __ret = __wait_event_interruptible_lock_irq(wq, \ - condition, lock,); \ - __ret; \ +#define wait_event_interruptible_lock_irq(wq_head, condition, lock) \ +({ \ + int __ret = 0; \ + if (!(condition)) \ + __ret = __wait_event_interruptible_lock_irq(wq_head, \ + condition, lock,); \ + __ret; \ }) -#define __wait_event_interruptible_lock_irq_timeout(wq, condition, \ - lock, timeout) \ - ___wait_event(wq, ___wait_cond_timeout(condition), \ - TASK_INTERRUPTIBLE, 0, timeout, \ - spin_unlock_irq(&lock); \ - __ret = schedule_timeout(__ret); \ +#define __wait_event_interruptible_lock_irq_timeout(wq_head, condition, \ + lock, timeout) \ + ___wait_event(wq_head, ___wait_cond_timeout(condition), \ + TASK_INTERRUPTIBLE, 0, timeout, \ + spin_unlock_irq(&lock); \ + __ret = schedule_timeout(__ret); \ spin_lock_irq(&lock)); /** * wait_event_interruptible_lock_irq_timeout - sleep until a condition gets * true or a timeout elapses. The condition is checked under * the lock. This is expected to be called with the lock taken. - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before schedule() * and reacquired afterwards. @@ -942,7 +915,7 @@ do { \ * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or signal is received. The @condition is - * checked each time the waitqueue @wq is woken up. + * checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. @@ -954,263 +927,42 @@ do { \ * was interrupted by a signal, and the remaining jiffies otherwise * if the condition evaluated to true before the timeout elapsed. */ -#define wait_event_interruptible_lock_irq_timeout(wq, condition, lock, \ - timeout) \ -({ \ - long __ret = timeout; \ - if (!___wait_cond_timeout(condition)) \ - __ret = __wait_event_interruptible_lock_irq_timeout( \ - wq, condition, lock, timeout); \ - __ret; \ +#define wait_event_interruptible_lock_irq_timeout(wq_head, condition, lock, \ + timeout) \ +({ \ + long __ret = timeout; \ + if (!___wait_cond_timeout(condition)) \ + __ret = __wait_event_interruptible_lock_irq_timeout( \ + wq_head, condition, lock, timeout); \ + __ret; \ }) /* * Waitqueues which are removed from the waitqueue_head at wakeup time */ -void prepare_to_wait(wait_queue_head_t *q, wait_queue_t *wait, int state); -void prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state); -long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state); -void finish_wait(wait_queue_head_t *q, wait_queue_t *wait); -long wait_woken(wait_queue_t *wait, unsigned mode, long timeout); -int woken_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key); -int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key); -int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key); - -#define DEFINE_WAIT_FUNC(name, function) \ - wait_queue_t name = { \ - .private = current, \ - .func = function, \ - .task_list = LIST_HEAD_INIT((name).task_list), \ +void prepare_to_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); +void prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); +long prepare_to_wait_event(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); +void finish_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); +long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout); +int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key); +int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key); + +#define DEFINE_WAIT_FUNC(name, function) \ + struct wait_queue_entry name = { \ + .private = current, \ + .func = function, \ + .entry = LIST_HEAD_INIT((name).entry), \ } #define DEFINE_WAIT(name) DEFINE_WAIT_FUNC(name, autoremove_wake_function) -#define DEFINE_WAIT_BIT(name, word, bit) \ - struct wait_bit_queue name = { \ - .key = __WAIT_BIT_KEY_INITIALIZER(word, bit), \ - .wait = { \ - .private = current, \ - .func = wake_bit_function, \ - .task_list = \ - LIST_HEAD_INIT((name).wait.task_list), \ - }, \ - } - -#define init_wait(wait) \ - do { \ - (wait)->private = current; \ - (wait)->func = autoremove_wake_function; \ - INIT_LIST_HEAD(&(wait)->task_list); \ - (wait)->flags = 0; \ +#define init_wait(wait) \ + do { \ + (wait)->private = current; \ + (wait)->func = autoremove_wake_function; \ + INIT_LIST_HEAD(&(wait)->entry); \ + (wait)->flags = 0; \ } while (0) - -extern int bit_wait(struct wait_bit_key *, int); -extern int bit_wait_io(struct wait_bit_key *, int); -extern int bit_wait_timeout(struct wait_bit_key *, int); -extern int bit_wait_io_timeout(struct wait_bit_key *, int); - -/** - * wait_on_bit - wait for a bit to be cleared - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on - * @mode: the task state to sleep in - * - * There is a standard hashed waitqueue table for generic use. This - * is the part of the hashtable's accessor API that waits on a bit. - * For instance, if one were to have waiters on a bitflag, one would - * call wait_on_bit() in threads waiting for the bit to clear. - * One uses wait_on_bit() where one is waiting for the bit to clear, - * but has no intention of setting it. - * Returned value will be zero if the bit was cleared, or non-zero - * if the process received a signal and the mode permitted wakeup - * on that signal. - */ -static inline int -wait_on_bit(unsigned long *word, int bit, unsigned mode) -{ - might_sleep(); - if (!test_bit(bit, word)) - return 0; - return out_of_line_wait_on_bit(word, bit, - bit_wait, - mode); -} - -/** - * wait_on_bit_io - wait for a bit to be cleared - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on - * @mode: the task state to sleep in - * - * Use the standard hashed waitqueue table to wait for a bit - * to be cleared. This is similar to wait_on_bit(), but calls - * io_schedule() instead of schedule() for the actual waiting. - * - * Returned value will be zero if the bit was cleared, or non-zero - * if the process received a signal and the mode permitted wakeup - * on that signal. - */ -static inline int -wait_on_bit_io(unsigned long *word, int bit, unsigned mode) -{ - might_sleep(); - if (!test_bit(bit, word)) - return 0; - return out_of_line_wait_on_bit(word, bit, - bit_wait_io, - mode); -} - -/** - * wait_on_bit_timeout - wait for a bit to be cleared or a timeout elapses - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on - * @mode: the task state to sleep in - * @timeout: timeout, in jiffies - * - * Use the standard hashed waitqueue table to wait for a bit - * to be cleared. This is similar to wait_on_bit(), except also takes a - * timeout parameter. - * - * Returned value will be zero if the bit was cleared before the - * @timeout elapsed, or non-zero if the @timeout elapsed or process - * received a signal and the mode permitted wakeup on that signal. - */ -static inline int -wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode, - unsigned long timeout) -{ - might_sleep(); - if (!test_bit(bit, word)) - return 0; - return out_of_line_wait_on_bit_timeout(word, bit, - bit_wait_timeout, - mode, timeout); -} - -/** - * wait_on_bit_action - wait for a bit to be cleared - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on - * @action: the function used to sleep, which may take special actions - * @mode: the task state to sleep in - * - * Use the standard hashed waitqueue table to wait for a bit - * to be cleared, and allow the waiting action to be specified. - * This is like wait_on_bit() but allows fine control of how the waiting - * is done. - * - * Returned value will be zero if the bit was cleared, or non-zero - * if the process received a signal and the mode permitted wakeup - * on that signal. - */ -static inline int -wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action, - unsigned mode) -{ - might_sleep(); - if (!test_bit(bit, word)) - return 0; - return out_of_line_wait_on_bit(word, bit, action, mode); -} - -/** - * wait_on_bit_lock - wait for a bit to be cleared, when wanting to set it - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on - * @mode: the task state to sleep in - * - * There is a standard hashed waitqueue table for generic use. This - * is the part of the hashtable's accessor API that waits on a bit - * when one intends to set it, for instance, trying to lock bitflags. - * For instance, if one were to have waiters trying to set bitflag - * and waiting for it to clear before setting it, one would call - * wait_on_bit() in threads waiting to be able to set the bit. - * One uses wait_on_bit_lock() where one is waiting for the bit to - * clear with the intention of setting it, and when done, clearing it. - * - * Returns zero if the bit was (eventually) found to be clear and was - * set. Returns non-zero if a signal was delivered to the process and - * the @mode allows that signal to wake the process. - */ -static inline int -wait_on_bit_lock(unsigned long *word, int bit, unsigned mode) -{ - might_sleep(); - if (!test_and_set_bit(bit, word)) - return 0; - return out_of_line_wait_on_bit_lock(word, bit, bit_wait, mode); -} - -/** - * wait_on_bit_lock_io - wait for a bit to be cleared, when wanting to set it - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on - * @mode: the task state to sleep in - * - * Use the standard hashed waitqueue table to wait for a bit - * to be cleared and then to atomically set it. This is similar - * to wait_on_bit(), but calls io_schedule() instead of schedule() - * for the actual waiting. - * - * Returns zero if the bit was (eventually) found to be clear and was - * set. Returns non-zero if a signal was delivered to the process and - * the @mode allows that signal to wake the process. - */ -static inline int -wait_on_bit_lock_io(unsigned long *word, int bit, unsigned mode) -{ - might_sleep(); - if (!test_and_set_bit(bit, word)) - return 0; - return out_of_line_wait_on_bit_lock(word, bit, bit_wait_io, mode); -} - -/** - * wait_on_bit_lock_action - wait for a bit to be cleared, when wanting to set it - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on - * @action: the function used to sleep, which may take special actions - * @mode: the task state to sleep in - * - * Use the standard hashed waitqueue table to wait for a bit - * to be cleared and then to set it, and allow the waiting action - * to be specified. - * This is like wait_on_bit() but allows fine control of how the waiting - * is done. - * - * Returns zero if the bit was (eventually) found to be clear and was - * set. Returns non-zero if a signal was delivered to the process and - * the @mode allows that signal to wake the process. - */ -static inline int -wait_on_bit_lock_action(unsigned long *word, int bit, wait_bit_action_f *action, - unsigned mode) -{ - might_sleep(); - if (!test_and_set_bit(bit, word)) - return 0; - return out_of_line_wait_on_bit_lock(word, bit, action, mode); -} - -/** - * wait_on_atomic_t - Wait for an atomic_t to become 0 - * @val: The atomic value being waited on, a kernel virtual address - * @action: the function used to sleep, which may take special actions - * @mode: the task state to sleep in - * - * Wait for an atomic_t to become 0. We abuse the bit-wait waitqueue table for - * the purpose of getting a waitqueue, but we set the key to a bit number - * outside of the target 'word'. - */ -static inline -int wait_on_atomic_t(atomic_t *val, int (*action)(atomic_t *), unsigned mode) -{ - might_sleep(); - if (atomic_read(val) == 0) - return 0; - return out_of_line_wait_on_atomic_t(val, action, mode); -} - #endif /* _LINUX_WAIT_H */ diff --git a/include/linux/wait_bit.h b/include/linux/wait_bit.h new file mode 100644 index 000000000000..12b26660d7e9 --- /dev/null +++ b/include/linux/wait_bit.h @@ -0,0 +1,261 @@ +#ifndef _LINUX_WAIT_BIT_H +#define _LINUX_WAIT_BIT_H + +/* + * Linux wait-bit related types and methods: + */ +#include <linux/wait.h> + +struct wait_bit_key { + void *flags; + int bit_nr; +#define WAIT_ATOMIC_T_BIT_NR -1 + unsigned long timeout; +}; + +struct wait_bit_queue_entry { + struct wait_bit_key key; + struct wait_queue_entry wq_entry; +}; + +#define __WAIT_BIT_KEY_INITIALIZER(word, bit) \ + { .flags = word, .bit_nr = bit, } + +#define __WAIT_ATOMIC_T_KEY_INITIALIZER(p) \ + { .flags = p, .bit_nr = WAIT_ATOMIC_T_BIT_NR, } + +typedef int wait_bit_action_f(struct wait_bit_key *key, int mode); +void __wake_up_bit(struct wait_queue_head *wq_head, void *word, int bit); +int __wait_on_bit(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, wait_bit_action_f *action, unsigned int mode); +int __wait_on_bit_lock(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, wait_bit_action_f *action, unsigned int mode); +void wake_up_bit(void *word, int bit); +void wake_up_atomic_t(atomic_t *p); +int out_of_line_wait_on_bit(void *word, int, wait_bit_action_f *action, unsigned int mode); +int out_of_line_wait_on_bit_timeout(void *word, int, wait_bit_action_f *action, unsigned int mode, unsigned long timeout); +int out_of_line_wait_on_bit_lock(void *word, int, wait_bit_action_f *action, unsigned int mode); +int out_of_line_wait_on_atomic_t(atomic_t *p, int (*)(atomic_t *), unsigned int mode); +struct wait_queue_head *bit_waitqueue(void *word, int bit); +extern void __init wait_bit_init(void); + +int wake_bit_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key); + +#define DEFINE_WAIT_BIT(name, word, bit) \ + struct wait_bit_queue_entry name = { \ + .key = __WAIT_BIT_KEY_INITIALIZER(word, bit), \ + .wq_entry = { \ + .private = current, \ + .func = wake_bit_function, \ + .entry = \ + LIST_HEAD_INIT((name).wq_entry.entry), \ + }, \ + } + +extern int bit_wait(struct wait_bit_key *key, int bit); +extern int bit_wait_io(struct wait_bit_key *key, int bit); +extern int bit_wait_timeout(struct wait_bit_key *key, int bit); +extern int bit_wait_io_timeout(struct wait_bit_key *key, int bit); + +/** + * wait_on_bit - wait for a bit to be cleared + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @mode: the task state to sleep in + * + * There is a standard hashed waitqueue table for generic use. This + * is the part of the hashtable's accessor API that waits on a bit. + * For instance, if one were to have waiters on a bitflag, one would + * call wait_on_bit() in threads waiting for the bit to clear. + * One uses wait_on_bit() where one is waiting for the bit to clear, + * but has no intention of setting it. + * Returned value will be zero if the bit was cleared, or non-zero + * if the process received a signal and the mode permitted wakeup + * on that signal. + */ +static inline int +wait_on_bit(unsigned long *word, int bit, unsigned mode) +{ + might_sleep(); + if (!test_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit(word, bit, + bit_wait, + mode); +} + +/** + * wait_on_bit_io - wait for a bit to be cleared + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @mode: the task state to sleep in + * + * Use the standard hashed waitqueue table to wait for a bit + * to be cleared. This is similar to wait_on_bit(), but calls + * io_schedule() instead of schedule() for the actual waiting. + * + * Returned value will be zero if the bit was cleared, or non-zero + * if the process received a signal and the mode permitted wakeup + * on that signal. + */ +static inline int +wait_on_bit_io(unsigned long *word, int bit, unsigned mode) +{ + might_sleep(); + if (!test_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit(word, bit, + bit_wait_io, + mode); +} + +/** + * wait_on_bit_timeout - wait for a bit to be cleared or a timeout elapses + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @mode: the task state to sleep in + * @timeout: timeout, in jiffies + * + * Use the standard hashed waitqueue table to wait for a bit + * to be cleared. This is similar to wait_on_bit(), except also takes a + * timeout parameter. + * + * Returned value will be zero if the bit was cleared before the + * @timeout elapsed, or non-zero if the @timeout elapsed or process + * received a signal and the mode permitted wakeup on that signal. + */ +static inline int +wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode, + unsigned long timeout) +{ + might_sleep(); + if (!test_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit_timeout(word, bit, + bit_wait_timeout, + mode, timeout); +} + +/** + * wait_on_bit_action - wait for a bit to be cleared + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @action: the function used to sleep, which may take special actions + * @mode: the task state to sleep in + * + * Use the standard hashed waitqueue table to wait for a bit + * to be cleared, and allow the waiting action to be specified. + * This is like wait_on_bit() but allows fine control of how the waiting + * is done. + * + * Returned value will be zero if the bit was cleared, or non-zero + * if the process received a signal and the mode permitted wakeup + * on that signal. + */ +static inline int +wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action, + unsigned mode) +{ + might_sleep(); + if (!test_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit(word, bit, action, mode); +} + +/** + * wait_on_bit_lock - wait for a bit to be cleared, when wanting to set it + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @mode: the task state to sleep in + * + * There is a standard hashed waitqueue table for generic use. This + * is the part of the hashtable's accessor API that waits on a bit + * when one intends to set it, for instance, trying to lock bitflags. + * For instance, if one were to have waiters trying to set bitflag + * and waiting for it to clear before setting it, one would call + * wait_on_bit() in threads waiting to be able to set the bit. + * One uses wait_on_bit_lock() where one is waiting for the bit to + * clear with the intention of setting it, and when done, clearing it. + * + * Returns zero if the bit was (eventually) found to be clear and was + * set. Returns non-zero if a signal was delivered to the process and + * the @mode allows that signal to wake the process. + */ +static inline int +wait_on_bit_lock(unsigned long *word, int bit, unsigned mode) +{ + might_sleep(); + if (!test_and_set_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit_lock(word, bit, bit_wait, mode); +} + +/** + * wait_on_bit_lock_io - wait for a bit to be cleared, when wanting to set it + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @mode: the task state to sleep in + * + * Use the standard hashed waitqueue table to wait for a bit + * to be cleared and then to atomically set it. This is similar + * to wait_on_bit(), but calls io_schedule() instead of schedule() + * for the actual waiting. + * + * Returns zero if the bit was (eventually) found to be clear and was + * set. Returns non-zero if a signal was delivered to the process and + * the @mode allows that signal to wake the process. + */ +static inline int +wait_on_bit_lock_io(unsigned long *word, int bit, unsigned mode) +{ + might_sleep(); + if (!test_and_set_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit_lock(word, bit, bit_wait_io, mode); +} + +/** + * wait_on_bit_lock_action - wait for a bit to be cleared, when wanting to set it + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @action: the function used to sleep, which may take special actions + * @mode: the task state to sleep in + * + * Use the standard hashed waitqueue table to wait for a bit + * to be cleared and then to set it, and allow the waiting action + * to be specified. + * This is like wait_on_bit() but allows fine control of how the waiting + * is done. + * + * Returns zero if the bit was (eventually) found to be clear and was + * set. Returns non-zero if a signal was delivered to the process and + * the @mode allows that signal to wake the process. + */ +static inline int +wait_on_bit_lock_action(unsigned long *word, int bit, wait_bit_action_f *action, + unsigned mode) +{ + might_sleep(); + if (!test_and_set_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit_lock(word, bit, action, mode); +} + +/** + * wait_on_atomic_t - Wait for an atomic_t to become 0 + * @val: The atomic value being waited on, a kernel virtual address + * @action: the function used to sleep, which may take special actions + * @mode: the task state to sleep in + * + * Wait for an atomic_t to become 0. We abuse the bit-wait waitqueue table for + * the purpose of getting a waitqueue, but we set the key to a bit number + * outside of the target 'word'. + */ +static inline +int wait_on_atomic_t(atomic_t *val, int (*action)(atomic_t *), unsigned mode) +{ + might_sleep(); + if (atomic_read(val) == 0) + return 0; + return out_of_line_wait_on_atomic_t(val, action, mode); +} + +#endif /* _LINUX_WAIT_BIT_H */ diff --git a/include/net/af_unix.h b/include/net/af_unix.h index fd60eccb59a6..75e612a45824 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -62,7 +62,7 @@ struct unix_sock { #define UNIX_GC_CANDIDATE 0 #define UNIX_GC_MAYBE_CYCLE 1 struct socket_wq peer_wq; - wait_queue_t peer_wake; + wait_queue_entry_t peer_wake; }; static inline struct unix_sock *unix_sk(const struct sock *sk) diff --git a/include/net/wext.h b/include/net/wext.h index 345911965dbb..454ff763eeba 100644 --- a/include/net/wext.h +++ b/include/net/wext.h @@ -6,7 +6,7 @@ struct net; #ifdef CONFIG_WEXT_CORE -int wext_handle_ioctl(struct net *net, struct ifreq *ifr, unsigned int cmd, +int wext_handle_ioctl(struct net *net, struct iwreq *iwr, unsigned int cmd, void __user *arg); int compat_wext_handle_ioctl(struct net *net, unsigned int cmd, unsigned long arg); @@ -14,7 +14,7 @@ int compat_wext_handle_ioctl(struct net *net, unsigned int cmd, struct iw_statistics *get_wireless_stats(struct net_device *dev); int call_commit_handler(struct net_device *dev); #else -static inline int wext_handle_ioctl(struct net *net, struct ifreq *ifr, unsigned int cmd, +static inline int wext_handle_ioctl(struct net *net, struct iwreq *iwr, unsigned int cmd, void __user *arg) { return -EINVAL; diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 7e7e2b0d2915..62f5a259e597 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1850,8 +1850,9 @@ static inline struct xfrm_offload *xfrm_offload(struct sk_buff *skb) } #endif -#ifdef CONFIG_XFRM_OFFLOAD void __net_init xfrm_dev_init(void); + +#ifdef CONFIG_XFRM_OFFLOAD int validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features); int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, struct xfrm_user_offload *xuo); @@ -1877,10 +1878,6 @@ static inline void xfrm_dev_state_free(struct xfrm_state *x) } } #else -static inline void __net_init xfrm_dev_init(void) -{ -} - static inline int validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features) { return 0; diff --git a/include/scsi/osd_initiator.h b/include/scsi/osd_initiator.h index a09cca829082..a29d3086eb56 100644 --- a/include/scsi/osd_initiator.h +++ b/include/scsi/osd_initiator.h @@ -157,7 +157,7 @@ struct osd_request { osd_req_done_fn *async_done; void *async_private; - int async_error; + blk_status_t async_error; int req_errors; }; diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index b379f93a2c48..da9bf2bcdf1a 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -166,6 +166,7 @@ extern void *scsi_kmap_atomic_sg(struct scatterlist *sg, int sg_count, extern void scsi_kunmap_atomic_sg(void *virt); extern int scsi_init_io(struct scsi_cmnd *cmd); +extern void scsi_initialize_rq(struct request *rq); extern int scsi_dma_map(struct scsi_cmnd *cmd); extern void scsi_dma_unmap(struct scsi_cmnd *cmd); diff --git a/include/scsi/scsi_request.h b/include/scsi/scsi_request.h index f0c76f9dc285..e0afa445ee4e 100644 --- a/include/scsi/scsi_request.h +++ b/include/scsi/scsi_request.h @@ -27,6 +27,6 @@ static inline void scsi_req_free_cmd(struct scsi_request *req) kfree(req->cmd); } -void scsi_req_init(struct request *); +void scsi_req_init(struct scsi_request *req); #endif /* _SCSI_SCSI_REQUEST_H */ diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index e3facb356838..91dc089d65b7 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -742,6 +742,7 @@ TRACE_EVENT(rcu_torture_read, * "OnlineQ": _rcu_barrier() found online CPU with callbacks. * "OnlineNQ": _rcu_barrier() found online CPU, no callbacks. * "IRQ": An rcu_barrier_callback() callback posted on remote CPU. + * "IRQNQ": An rcu_barrier_callback() callback found no callbacks. * "CB": An rcu_barrier_callback() invoked a callback, not the last. * "LastCB": An rcu_barrier_callback() invoked the last callback. * "Inc2": _rcu_barrier() piggyback check counter incremented. diff --git a/include/uapi/linux/a.out.h b/include/uapi/linux/a.out.h index 7caf44c7fa51..295cd3ef6330 100644 --- a/include/uapi/linux/a.out.h +++ b/include/uapi/linux/a.out.h @@ -112,24 +112,7 @@ enum machine_type { #define N_TXTADDR(x) (N_MAGIC(x) == QMAGIC ? PAGE_SIZE : 0) #endif -/* Address of data segment in memory after it is loaded. - Note that it is up to you to define SEGMENT_SIZE - on machines not listed here. */ -#if defined(vax) || defined(hp300) || defined(pyr) -#define SEGMENT_SIZE page_size -#endif -#ifdef sony -#define SEGMENT_SIZE 0x2000 -#endif /* Sony. */ -#ifdef is68k -#define SEGMENT_SIZE 0x20000 -#endif -#if defined(m68k) && defined(PORTAR) -#define PAGE_SIZE 0x400 -#define SEGMENT_SIZE PAGE_SIZE -#endif - -#ifdef linux +/* Address of data segment in memory after it is loaded. */ #ifndef __KERNEL__ #include <unistd.h> #endif @@ -142,7 +125,6 @@ enum machine_type { #endif #endif #endif -#endif #define _N_SEGMENT_ROUND(x) ALIGN(x, SEGMENT_SIZE) @@ -260,13 +242,7 @@ struct relocation_info unsigned int r_extern:1; /* Four bits that aren't used, but when writing an object file it is desirable to clear them. */ -#ifdef NS32K - unsigned r_bsr:1; - unsigned r_disp:1; - unsigned r_pad:2; -#else unsigned int r_pad:4; -#endif }; #endif /* no N_RELOCATION_INFO_DECLARED. */ diff --git a/include/uapi/linux/aio_abi.h b/include/uapi/linux/aio_abi.h index bb2554f7fbd1..a2d4a8ac94ca 100644 --- a/include/uapi/linux/aio_abi.h +++ b/include/uapi/linux/aio_abi.h @@ -79,7 +79,7 @@ struct io_event { struct iocb { /* these are internal to the kernel/libc. */ __u64 aio_data; /* data to be returned in event's data */ - __u32 PADDED(aio_key, aio_reserved1); + __u32 PADDED(aio_key, aio_rw_flags); /* the kernel sets aio_key to the req # */ /* common fields */ diff --git a/include/uapi/linux/auto_fs.h b/include/uapi/linux/auto_fs.h index aa63451ef20a..1953f8d6063b 100644 --- a/include/uapi/linux/auto_fs.h +++ b/include/uapi/linux/auto_fs.h @@ -26,7 +26,7 @@ #define AUTOFS_MIN_PROTO_VERSION AUTOFS_PROTO_VERSION /* - * The wait_queue_token (autofs_wqt_t) is part of a structure which is passed + * The wait_queue_entry_token (autofs_wqt_t) is part of a structure which is passed * back to the kernel via ioctl from userspace. On architectures where 32- and * 64-bit userspace binaries can be executed it's important that the size of * autofs_wqt_t stays constant between 32- and 64-bit Linux kernels so that we @@ -49,7 +49,7 @@ struct autofs_packet_hdr { struct autofs_packet_missing { struct autofs_packet_hdr hdr; - autofs_wqt_t wait_queue_token; + autofs_wqt_t wait_queue_entry_token; int len; char name[NAME_MAX+1]; }; diff --git a/include/uapi/linux/auto_fs4.h b/include/uapi/linux/auto_fs4.h index 7c6da423d54e..65b72d0222e7 100644 --- a/include/uapi/linux/auto_fs4.h +++ b/include/uapi/linux/auto_fs4.h @@ -108,7 +108,7 @@ enum autofs_notify { /* v4 multi expire (via pipe) */ struct autofs_packet_expire_multi { struct autofs_packet_hdr hdr; - autofs_wqt_t wait_queue_token; + autofs_wqt_t wait_queue_entry_token; int len; char name[NAME_MAX+1]; }; @@ -123,7 +123,7 @@ union autofs_packet_union { /* autofs v5 common packet struct */ struct autofs_v5_packet { struct autofs_packet_hdr hdr; - autofs_wqt_t wait_queue_token; + autofs_wqt_t wait_queue_entry_token; __u32 dev; __u64 ino; __u32 uid; diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h index 4bf9f1eabffc..2f6c77aebe1a 100644 --- a/include/uapi/linux/dm-ioctl.h +++ b/include/uapi/linux/dm-ioctl.h @@ -267,9 +267,9 @@ enum { #define DM_DEV_SET_GEOMETRY _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl) #define DM_VERSION_MAJOR 4 -#define DM_VERSION_MINOR 35 +#define DM_VERSION_MINOR 36 #define DM_VERSION_PATCHLEVEL 0 -#define DM_VERSION_EXTRA "-ioctl (2016-06-23)" +#define DM_VERSION_EXTRA "-ioctl (2017-06-09)" /* Status bits */ #define DM_READONLY_FLAG (1 << 0) /* In/Out */ diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h index 813afd6eee71..ec69d55bcec7 100644 --- a/include/uapi/linux/fcntl.h +++ b/include/uapi/linux/fcntl.h @@ -43,6 +43,27 @@ /* (1U << 31) is reserved for signed error codes */ /* + * Set/Get write life time hints. {GET,SET}_RW_HINT operate on the + * underlying inode, while {GET,SET}_FILE_RW_HINT operate only on + * the specific file. + */ +#define F_GET_RW_HINT (F_LINUX_SPECIFIC_BASE + 11) +#define F_SET_RW_HINT (F_LINUX_SPECIFIC_BASE + 12) +#define F_GET_FILE_RW_HINT (F_LINUX_SPECIFIC_BASE + 13) +#define F_SET_FILE_RW_HINT (F_LINUX_SPECIFIC_BASE + 14) + +/* + * Valid hint values for F_{GET,SET}_RW_HINT. 0 is "not set", or can be + * used to clear any hints previously set. + */ +#define RWF_WRITE_LIFE_NOT_SET 0 +#define RWH_WRITE_LIFE_NONE 1 +#define RWH_WRITE_LIFE_SHORT 2 +#define RWH_WRITE_LIFE_MEDIUM 3 +#define RWH_WRITE_LIFE_LONG 4 +#define RWH_WRITE_LIFE_EXTREME 5 + +/* * Types of directory notifications that may be requested. */ #define DN_ACCESS 0x00000001 /* File accessed */ diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 24e61a54feaa..27d8c36c04af 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -360,5 +360,9 @@ struct fscrypt_key { #define RWF_HIPRI 0x00000001 /* high priority request, poll if possible */ #define RWF_DSYNC 0x00000002 /* per-IO O_DSYNC */ #define RWF_SYNC 0x00000004 /* per-IO O_SYNC */ +#define RWF_NOWAIT 0x00000008 /* per-IO, return -EAGAIN if operation would block */ + +#define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC |\ + RWF_NOWAIT) #endif /* _UAPI_LINUX_FS_H */ diff --git a/include/uapi/linux/loop.h b/include/uapi/linux/loop.h index c8125ec1f4f2..a3960f98679c 100644 --- a/include/uapi/linux/loop.h +++ b/include/uapi/linux/loop.h @@ -22,6 +22,7 @@ enum { LO_FLAGS_AUTOCLEAR = 4, LO_FLAGS_PARTSCAN = 8, LO_FLAGS_DIRECT_IO = 16, + LO_FLAGS_BLOCKSIZE = 32, }; #include <asm/posix_types.h> /* for __kernel_old_dev_t */ @@ -59,6 +60,8 @@ struct loop_info64 { __u64 lo_init[2]; }; +#define LO_INFO_BLOCKSIZE(l) (l)->lo_init[0] + /* * Loop filter types */ diff --git a/include/uapi/linux/nbd.h b/include/uapi/linux/nbd.h index 155e33f81913..a50527ebf671 100644 --- a/include/uapi/linux/nbd.h +++ b/include/uapi/linux/nbd.h @@ -41,10 +41,14 @@ enum { #define NBD_FLAG_HAS_FLAGS (1 << 0) /* nbd-server supports flags */ #define NBD_FLAG_READ_ONLY (1 << 1) /* device is read-only */ #define NBD_FLAG_SEND_FLUSH (1 << 2) /* can flush writeback cache */ +#define NBD_FLAG_SEND_FUA (1 << 3) /* send FUA (forced unit access) */ /* there is a gap here to match userspace */ #define NBD_FLAG_SEND_TRIM (1 << 5) /* send trim/discard */ #define NBD_FLAG_CAN_MULTI_CONN (1 << 8) /* Server supports multiple connections per export. */ +/* values for cmd flags in the upper 16 bits of request type */ +#define NBD_CMD_FLAG_FUA (1 << 16) /* FUA (forced unit access) op */ + /* These are client behavior specific flags. */ #define NBD_CFLAG_DESTROY_ON_DISCONNECT (1 << 0) /* delete the nbd device on disconnect. */ diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h index 5f0fe019a720..e2a6c7b3510b 100644 --- a/include/uapi/linux/sched.h +++ b/include/uapi/linux/sched.h @@ -47,5 +47,6 @@ * For the sched_{set,get}attr() calls */ #define SCHED_FLAG_RESET_ON_FORK 0x01 +#define SCHED_FLAG_RECLAIM 0x02 #endif /* _UAPI_LINUX_SCHED_H */ diff --git a/include/uapi/linux/uuid.h b/include/uapi/linux/uuid.h index 3738e5fb6a4d..8ef82f433877 100644 --- a/include/uapi/linux/uuid.h +++ b/include/uapi/linux/uuid.h @@ -22,33 +22,21 @@ typedef struct { __u8 b[16]; -} uuid_le; +} guid_t; -typedef struct { - __u8 b[16]; -} uuid_be; - -#define UUID_LE(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) \ -((uuid_le) \ +#define GUID_INIT(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) \ +((guid_t) \ {{ (a) & 0xff, ((a) >> 8) & 0xff, ((a) >> 16) & 0xff, ((a) >> 24) & 0xff, \ (b) & 0xff, ((b) >> 8) & 0xff, \ (c) & 0xff, ((c) >> 8) & 0xff, \ (d0), (d1), (d2), (d3), (d4), (d5), (d6), (d7) }}) -#define UUID_BE(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) \ -((uuid_be) \ -{{ ((a) >> 24) & 0xff, ((a) >> 16) & 0xff, ((a) >> 8) & 0xff, (a) & 0xff, \ - ((b) >> 8) & 0xff, (b) & 0xff, \ - ((c) >> 8) & 0xff, (c) & 0xff, \ - (d0), (d1), (d2), (d3), (d4), (d5), (d6), (d7) }}) - +/* backwards compatibility, don't use in new code */ +typedef guid_t uuid_le; +#define UUID_LE(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) \ + GUID_INIT(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) #define NULL_UUID_LE \ UUID_LE(0x00000000, 0x0000, 0x0000, 0x00, 0x00, 0x00, 0x00, \ - 0x00, 0x00, 0x00, 0x00) - -#define NULL_UUID_BE \ - UUID_BE(0x00000000, 0x0000, 0x0000, 0x00, 0x00, 0x00, 0x00, \ - 0x00, 0x00, 0x00, 0x00) - + 0x00, 0x00, 0x00, 0x00) #endif /* _UAPI_LINUX_UUID_H_ */ diff --git a/init/Kconfig b/init/Kconfig index 1d3475fc9496..ee0f03b69d11 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -472,354 +472,7 @@ config TASK_IO_ACCOUNTING endmenu # "CPU/Task time and stats accounting" -menu "RCU Subsystem" - -config TREE_RCU - bool - default y if !PREEMPT && SMP - help - This option selects the RCU implementation that is - designed for very large SMP system with hundreds or - thousands of CPUs. It also scales down nicely to - smaller systems. - -config PREEMPT_RCU - bool - default y if PREEMPT - help - This option selects the RCU implementation that is - designed for very large SMP systems with hundreds or - thousands of CPUs, but for which real-time response - is also required. It also scales down nicely to - smaller systems. - - Select this option if you are unsure. - -config TINY_RCU - bool - default y if !PREEMPT && !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. - -config RCU_EXPERT - bool "Make expert-level adjustments to RCU configuration" - default n - help - This option needs to be enabled if you wish to make - expert-level adjustments to RCU configuration. By default, - no such adjustments can be made, which has the often-beneficial - side-effect of preventing "make oldconfig" from asking you all - sorts of detailed questions about how you would like numerous - obscure RCU options to be set up. - - Say Y if you need to make expert-level adjustments to RCU. - - Say N if you are unsure. - -config SRCU - bool - default y - help - This option selects the sleepable version of RCU. This version - permits arbitrary sleeping or blocking within RCU read-side critical - sections. - -config CLASSIC_SRCU - bool "Use v4.11 classic SRCU implementation" - default n - depends on RCU_EXPERT && SRCU - help - This option selects the traditional well-tested classic SRCU - implementation from v4.11, as might be desired for enterprise - Linux distributions. Without this option, the shiny new - Tiny SRCU and Tree SRCU implementations are used instead. - At some point, it is hoped that Tiny SRCU and Tree SRCU - will accumulate enough test time and confidence to allow - Classic SRCU to be dropped entirely. - - Say Y if you need a rock-solid SRCU. - - Say N if you would like help test Tree SRCU. - -config TINY_SRCU - bool - default y if SRCU && TINY_RCU && !CLASSIC_SRCU - help - This option selects the single-CPU non-preemptible version of SRCU. - -config TREE_SRCU - bool - default y if SRCU && !TINY_RCU && !CLASSIC_SRCU - help - This option selects the full-fledged version of SRCU. - -config TASKS_RCU - bool - default n - select SRCU - help - This option enables a task-based RCU implementation that uses - only voluntary context switch (not preemption!), idle, and - user-mode execution as quiescent states. - -config RCU_STALL_COMMON - def_bool ( TREE_RCU || PREEMPT_RCU || RCU_TRACE ) - help - This option enables RCU CPU stall code that is common between - the TINY and TREE variants of RCU. The purpose is to allow - the tiny variants to disable RCU CPU stall warnings, while - making these warnings mandatory for the tree variants. - -config RCU_NEED_SEGCBLIST - def_bool ( TREE_RCU || PREEMPT_RCU || TINY_SRCU || TREE_SRCU ) - -config CONTEXT_TRACKING - bool - -config CONTEXT_TRACKING_FORCE - bool "Force context tracking" - depends on CONTEXT_TRACKING - default y if !NO_HZ_FULL - help - The major pre-requirement for full dynticks to work is to - support the context tracking subsystem. But there are also - other dependencies to provide in order to make the full - dynticks working. - - This option stands for testing when an arch implements the - context tracking backend but doesn't yet fullfill all the - requirements to make the full dynticks feature working. - Without the full dynticks, there is no way to test the support - for context tracking and the subsystems that rely on it: RCU - userspace extended quiescent state and tickless cputime - accounting. This option copes with the absence of the full - dynticks subsystem by forcing the context tracking on all - CPUs in the system. - - Say Y only if you're working on the development of an - architecture backend for the context tracking. - - Say N otherwise, this option brings an overhead that you - don't want in production. - - -config RCU_FANOUT - int "Tree-based hierarchical RCU fanout value" - range 2 64 if 64BIT - range 2 32 if !64BIT - depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT - default 64 if 64BIT - default 32 if !64BIT - help - This option controls the fanout of hierarchical implementations - of RCU, allowing RCU to work efficiently on machines with - large numbers of CPUs. This value must be at least the fourth - root of NR_CPUS, which allows NR_CPUS to be insanely large. - The default value of RCU_FANOUT should be used for production - systems, but if you are stress-testing the RCU implementation - itself, small RCU_FANOUT values allow you to test large-system - code paths on small(er) systems. - - Select a specific number if testing RCU itself. - Take the default if unsure. - -config RCU_FANOUT_LEAF - int "Tree-based hierarchical RCU leaf-level fanout value" - range 2 64 if 64BIT - range 2 32 if !64BIT - depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT - default 16 - help - This option controls the leaf-level fanout of hierarchical - implementations of RCU, and allows trading off cache misses - against lock contention. Systems that synchronize their - scheduling-clock interrupts for energy-efficiency reasons will - want the default because the smaller leaf-level fanout keeps - lock contention levels acceptably low. Very large systems - (hundreds or thousands of CPUs) will instead want to set this - value to the maximum value possible in order to reduce the - number of cache misses incurred during RCU's grace-period - initialization. These systems tend to run CPU-bound, and thus - are not helped by synchronized interrupts, and thus tend to - skew them, which reduces lock contention enough that large - leaf-level fanouts work well. That said, setting leaf-level - fanout to a large number will likely cause problematic - lock contention on the leaf-level rcu_node structures unless - you boot with the skew_tick kernel parameter. - - Select a specific number if testing RCU itself. - - Select the maximum permissible value for large systems, but - please understand that you may also need to set the skew_tick - kernel boot parameter to avoid contention on the rcu_node - structure's locks. - - Take the default if unsure. - -config RCU_FAST_NO_HZ - bool "Accelerate last non-dyntick-idle CPU's grace periods" - depends on NO_HZ_COMMON && SMP && RCU_EXPERT - default n - help - This option permits CPUs to enter dynticks-idle state even if - they have RCU callbacks queued, and prevents RCU from waking - these CPUs up more than roughly once every four jiffies (by - default, you can adjust this using the rcutree.rcu_idle_gp_delay - parameter), thus improving energy efficiency. On the other - hand, this option increases the duration of RCU grace periods, - for example, slowing down synchronize_rcu(). - - Say Y if energy efficiency is critically important, and you - don't care about increased grace-period durations. - - Say N if you are unsure. - -config TREE_RCU_TRACE - def_bool RCU_TRACE && ( TREE_RCU || PREEMPT_RCU ) - select DEBUG_FS - help - This option provides tracing for the TREE_RCU and - PREEMPT_RCU implementations, permitting Makefile to - trivially select kernel/rcutree_trace.c. - -config RCU_BOOST - bool "Enable RCU priority boosting" - depends on RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT - default n - help - This option boosts the priority of preempted RCU readers that - block the current preemptible RCU grace period for too long. - This option also prevents heavy loads from blocking RCU - callback invocation for all flavors of RCU. - - Say Y here if you are working with real-time apps or heavy loads - Say N here if you are unsure. - -config RCU_KTHREAD_PRIO - int "Real-time priority to use for RCU worker threads" - range 1 99 if RCU_BOOST - range 0 99 if !RCU_BOOST - default 1 if RCU_BOOST - default 0 if !RCU_BOOST - depends on RCU_EXPERT - help - This option specifies the SCHED_FIFO priority value that will be - assigned to the rcuc/n and rcub/n threads and is also the value - used for RCU_BOOST (if enabled). If you are working with a - real-time application that has one or more CPU-bound threads - running at a real-time priority level, you should set - RCU_KTHREAD_PRIO to a priority higher than the highest-priority - real-time CPU-bound application thread. The default RCU_KTHREAD_PRIO - value of 1 is appropriate in the common case, which is real-time - applications that do not have any CPU-bound threads. - - Some real-time applications might not have a single real-time - thread that saturates a given CPU, but instead might have - multiple real-time threads that, taken together, fully utilize - that CPU. In this case, you should set RCU_KTHREAD_PRIO to - a priority higher than the lowest-priority thread that is - conspiring to prevent the CPU from running any non-real-time - tasks. For example, if one thread at priority 10 and another - thread at priority 5 are between themselves fully consuming - the CPU time on a given CPU, then RCU_KTHREAD_PRIO should be - set to priority 6 or higher. - - Specify the real-time priority, or take the default if unsure. - -config RCU_BOOST_DELAY - int "Milliseconds to delay boosting after RCU grace-period start" - range 0 3000 - depends on RCU_BOOST - default 500 - help - This option specifies the time to wait after the beginning of - a given grace period before priority-boosting preempted RCU - readers blocking that grace period. Note that any RCU reader - blocking an expedited RCU grace period is boosted immediately. - - Accept the default if unsure. - -config RCU_NOCB_CPU - bool "Offload RCU callback processing from boot-selected CPUs" - depends on TREE_RCU || PREEMPT_RCU - depends on RCU_EXPERT || NO_HZ_FULL - default n - help - Use this option to reduce OS jitter for aggressive HPC or - real-time workloads. It can also be used to offload RCU - callback invocation to energy-efficient CPUs in battery-powered - asymmetric multiprocessors. - - This option offloads callback invocation from the set of - CPUs specified at boot time by the rcu_nocbs parameter. - For each such CPU, a kthread ("rcuox/N") will be created to - invoke callbacks, where the "N" is the CPU being offloaded, - and where the "x" is "b" for RCU-bh, "p" for RCU-preempt, and - "s" for RCU-sched. Nothing prevents this kthread from running - on the specified CPUs, but (1) the kthreads may be preempted - between each callback, and (2) affinity or cgroups can be used - to force the kthreads to run on whatever set of CPUs is desired. - - Say Y here if you want to help to debug reduced OS jitter. - Say N here if you are unsure. - -choice - prompt "Build-forced no-CBs CPUs" - default RCU_NOCB_CPU_NONE - depends on RCU_NOCB_CPU - help - This option allows no-CBs CPUs (whose RCU callbacks are invoked - from kthreads rather than from softirq context) to be specified - at build time. Additional no-CBs CPUs may be specified by - the rcu_nocbs= boot parameter. - -config RCU_NOCB_CPU_NONE - bool "No build_forced no-CBs CPUs" - help - This option does not force any of the CPUs to be no-CBs CPUs. - Only CPUs designated by the rcu_nocbs= boot parameter will be - no-CBs CPUs, whose RCU callbacks will be invoked by per-CPU - kthreads whose names begin with "rcuo". All other CPUs will - invoke their own RCU callbacks in softirq context. - - Select this option if you want to choose no-CBs CPUs at - boot time, for example, to allow testing of different no-CBs - configurations without having to rebuild the kernel each time. - -config RCU_NOCB_CPU_ZERO - bool "CPU 0 is a build_forced no-CBs CPU" - help - This option forces CPU 0 to be a no-CBs CPU, so that its RCU - callbacks are invoked by a per-CPU kthread whose name begins - with "rcuo". Additional CPUs may be designated as no-CBs - CPUs using the rcu_nocbs= boot parameter will be no-CBs CPUs. - All other CPUs will invoke their own RCU callbacks in softirq - context. - - Select this if CPU 0 needs to be a no-CBs CPU for real-time - or energy-efficiency reasons, but the real reason it exists - is to ensure that randconfig testing covers mixed systems. - -config RCU_NOCB_CPU_ALL - bool "All CPUs are build_forced no-CBs CPUs" - help - This option forces all CPUs to be no-CBs CPUs. The rcu_nocbs= - boot parameter will be ignored. All CPUs' RCU callbacks will - be executed in the context of per-CPU rcuo kthreads created for - this purpose. Assuming that the kthreads whose names start with - "rcuo" are bound to "housekeeping" CPUs, this reduces OS jitter - on the remaining CPUs, but might decrease memory locality during - RCU-callback invocation, thus potentially degrading throughput. - - Select this if all CPUs need to be no-CBs CPUs for real-time - or energy-efficiency reasons. - -endchoice - -endmenu # "RCU Subsystem" +source "kernel/rcu/Kconfig" config BUILD_BIN2C bool @@ -1156,6 +809,7 @@ config CGROUP_HUGETLB config CPUSETS bool "Cpuset controller" + depends on SMP help This option will let you create and manage CPUSETs which allow dynamically partitioning a system into sets of CPUs and diff --git a/init/main.c b/init/main.c index f866510472d7..df58a416dd1d 100644 --- a/init/main.c +++ b/init/main.c @@ -389,6 +389,7 @@ static __initdata DECLARE_COMPLETION(kthreadd_done); static noinline void __ref rest_init(void) { + struct task_struct *tsk; int pid; rcu_scheduler_starting(); @@ -397,12 +398,32 @@ static noinline void __ref rest_init(void) * the init task will end up wanting to create kthreads, which, if * we schedule it before we create kthreadd, will OOPS. */ - kernel_thread(kernel_init, NULL, CLONE_FS); + pid = kernel_thread(kernel_init, NULL, CLONE_FS); + /* + * Pin init on the boot CPU. Task migration is not properly working + * until sched_init_smp() has been run. It will set the allowed + * CPUs for init to the non isolated CPUs. + */ + rcu_read_lock(); + tsk = find_task_by_pid_ns(pid, &init_pid_ns); + set_cpus_allowed_ptr(tsk, cpumask_of(smp_processor_id())); + rcu_read_unlock(); + numa_default_policy(); pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES); rcu_read_lock(); kthreadd_task = find_task_by_pid_ns(pid, &init_pid_ns); rcu_read_unlock(); + + /* + * Enable might_sleep() and smp_processor_id() checks. + * They cannot be enabled earlier because with CONFIG_PRREMPT=y + * kernel_thread() would trigger might_sleep() splats. With + * CONFIG_PREEMPT_VOLUNTARY=y the init task might have scheduled + * already, but it's stuck on the kthreadd_done completion. + */ + system_state = SYSTEM_SCHEDULING; + complete(&kthreadd_done); /* @@ -1015,10 +1036,6 @@ static noinline void __init kernel_init_freeable(void) * init can allocate pages on any node */ set_mems_allowed(node_states[N_MEMORY]); - /* - * init can run on any cpu. - */ - set_cpus_allowed_ptr(current, cpu_all_mask); cad_pid = task_pid(current); diff --git a/kernel/async.c b/kernel/async.c index d2edd6efec56..2cbd3dd5940d 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -114,14 +114,14 @@ static void async_run_entry_fn(struct work_struct *work) ktime_t uninitialized_var(calltime), delta, rettime; /* 1) run (and print duration) */ - if (initcall_debug && system_state == SYSTEM_BOOTING) { + if (initcall_debug && system_state < SYSTEM_RUNNING) { pr_debug("calling %lli_%pF @ %i\n", (long long)entry->cookie, entry->func, task_pid_nr(current)); calltime = ktime_get(); } entry->func(entry->data, entry->cookie); - if (initcall_debug && system_state == SYSTEM_BOOTING) { + if (initcall_debug && system_state < SYSTEM_RUNNING) { rettime = ktime_get(); delta = ktime_sub(rettime, calltime); pr_debug("initcall %lli_%pF returned 0 after %lld usecs\n", @@ -284,14 +284,14 @@ void async_synchronize_cookie_domain(async_cookie_t cookie, struct async_domain { ktime_t uninitialized_var(starttime), delta, endtime; - if (initcall_debug && system_state == SYSTEM_BOOTING) { + if (initcall_debug && system_state < SYSTEM_RUNNING) { pr_debug("async_waiting @ %i\n", task_pid_nr(current)); starttime = ktime_get(); } wait_event(async_done, lowest_in_progress(domain) >= cookie); - if (initcall_debug && system_state == SYSTEM_BOOTING) { + if (initcall_debug && system_state < SYSTEM_RUNNING) { endtime = ktime_get(); delta = ktime_sub(endtime, starttime); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 339c8a1371de..a8a725697bed 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -989,6 +989,11 @@ static int check_xadd(struct bpf_verifier_env *env, struct bpf_insn *insn) if (err) return err; + if (is_pointer_value(env, insn->src_reg)) { + verbose("R%d leaks addr into mem\n", insn->src_reg); + return -EACCES; + } + /* check whether atomic_add can read the memory */ err = check_mem_access(env, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_READ, -1); diff --git a/kernel/events/core.c b/kernel/events/core.c index 6c4e523dc1e2..bc63f8db1b0d 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -925,11 +925,6 @@ static inline int is_cgroup_event(struct perf_event *event) return 0; } -static inline u64 perf_cgroup_event_cgrp_time(struct perf_event *event) -{ - return 0; -} - static inline void update_cgrp_time_from_event(struct perf_event *event) { } @@ -5729,9 +5724,6 @@ static void perf_output_read_one(struct perf_output_handle *handle, __output_copy(handle, values, n * sizeof(u64)); } -/* - * XXX PERF_FORMAT_GROUP vs inherited events seems difficult. - */ static void perf_output_read_group(struct perf_output_handle *handle, struct perf_event *event, u64 enabled, u64 running) @@ -5776,6 +5768,13 @@ static void perf_output_read_group(struct perf_output_handle *handle, #define PERF_FORMAT_TOTAL_TIMES (PERF_FORMAT_TOTAL_TIME_ENABLED|\ PERF_FORMAT_TOTAL_TIME_RUNNING) +/* + * XXX PERF_SAMPLE_READ vs inherited events seems difficult. + * + * The problem is that its both hard and excessively expensive to iterate the + * child list, not to mention that its impossible to IPI the children running + * on another CPU, from interrupt/NMI context. + */ static void perf_output_read(struct perf_output_handle *handle, struct perf_event *event) { @@ -9193,7 +9192,7 @@ static int perf_try_init_event(struct pmu *pmu, struct perf_event *event) static struct pmu *perf_init_event(struct perf_event *event) { - struct pmu *pmu = NULL; + struct pmu *pmu; int idx; int ret; @@ -9462,9 +9461,10 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, local64_set(&hwc->period_left, hwc->sample_period); /* - * we currently do not support PERF_FORMAT_GROUP on inherited events + * We currently do not support PERF_SAMPLE_READ on inherited events. + * See perf_output_read(). */ - if (attr->inherit && (attr->read_format & PERF_FORMAT_GROUP)) + if (attr->inherit && (attr->sample_type & PERF_SAMPLE_READ)) goto err_ns; if (!has_branch_stack(event)) @@ -9477,9 +9477,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, } pmu = perf_init_event(event); - if (!pmu) - goto err_ns; - else if (IS_ERR(pmu)) { + if (IS_ERR(pmu)) { err = PTR_ERR(pmu); goto err_ns; } @@ -9492,8 +9490,10 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, event->addr_filters_offs = kcalloc(pmu->nr_addr_filters, sizeof(unsigned long), GFP_KERNEL); - if (!event->addr_filters_offs) + if (!event->addr_filters_offs) { + err = -ENOMEM; goto err_per_task; + } /* force hw sync on the address filters */ event->addr_filters_gen = 1; diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 2831480c63a2..ee97196bb151 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -580,7 +580,7 @@ int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event, int ret = -ENOMEM, max_order = 0; if (!has_aux(event)) - return -ENOTSUPP; + return -EOPNOTSUPP; if (event->pmu->capabilities & PERF_PMU_CAP_AUX_NO_SG) { /* diff --git a/kernel/exit.c b/kernel/exit.c index 516acdb0e0ec..c63226283aef 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -318,19 +318,6 @@ void rcuwait_wake_up(struct rcuwait *w) rcu_read_unlock(); } -struct task_struct *try_get_task_struct(struct task_struct **ptask) -{ - struct task_struct *task; - - rcu_read_lock(); - task = task_rcu_dereference(ptask); - if (task) - get_task_struct(task); - rcu_read_unlock(); - - return task; -} - /* * Determine if a process group is "orphaned", according to the POSIX * definition in 2.2.2.52. Orphaned process groups are not to be affected @@ -1004,7 +991,7 @@ struct wait_opts { int __user *wo_stat; struct rusage __user *wo_rusage; - wait_queue_t child_wait; + wait_queue_entry_t child_wait; int notask_error; }; @@ -1541,7 +1528,7 @@ static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk) return 0; } -static int child_wait_callback(wait_queue_t *wait, unsigned mode, +static int child_wait_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct wait_opts *wo = container_of(wait, struct wait_opts, diff --git a/kernel/extable.c b/kernel/extable.c index 2676d7f8baf6..0fbdd8582f08 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -75,7 +75,7 @@ int core_kernel_text(unsigned long addr) addr < (unsigned long)_etext) return 1; - if (system_state == SYSTEM_BOOTING && + if (system_state < SYSTEM_RUNNING && init_kernel_text(addr)) return 1; return 0; diff --git a/kernel/futex.c b/kernel/futex.c index 357348a6cf6b..d6cf71d08f21 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -225,7 +225,7 @@ struct futex_pi_state { * @requeue_pi_key: the requeue_pi target futex key * @bitset: bitset for the optional bitmasked wakeup * - * We use this hashed waitqueue, instead of a normal wait_queue_t, so + * We use this hashed waitqueue, instead of a normal wait_queue_entry_t, so * we can wake only the relevant ones (hashed queues may be shared). * * A futex_q has a woken state, just like tasks have TASK_RUNNING. diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index ae1a3ba24df5..154ffb489b93 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -38,6 +38,7 @@ #include <linux/syscore_ops.h> #include <linux/compiler.h> #include <linux/hugetlb.h> +#include <linux/frame.h> #include <asm/page.h> #include <asm/sections.h> @@ -874,7 +875,7 @@ int kexec_load_disabled; * only when panic_cpu holds the current CPU number; this is the only CPU * which processes crash_kexec routines. */ -void __crash_kexec(struct pt_regs *regs) +void __noclone __crash_kexec(struct pt_regs *regs) { /* Take the kexec_mutex here to prevent sys_kexec_load * running on one cpu from replacing the crash kernel @@ -896,6 +897,7 @@ void __crash_kexec(struct pt_regs *regs) mutex_unlock(&kexec_mutex); } } +STACK_FRAME_NON_STANDARD(__crash_kexec); void crash_kexec(struct pt_regs *regs) { diff --git a/kernel/livepatch/patch.c b/kernel/livepatch/patch.c index f8269036bf0b..52c4e907c14b 100644 --- a/kernel/livepatch/patch.c +++ b/kernel/livepatch/patch.c @@ -59,7 +59,11 @@ static void notrace klp_ftrace_handler(unsigned long ip, ops = container_of(fops, struct klp_ops, fops); - rcu_read_lock(); + /* + * A variant of synchronize_sched() is used to allow patching functions + * where RCU is not watching, see klp_synchronize_transition(). + */ + preempt_disable_notrace(); func = list_first_or_null_rcu(&ops->func_stack, struct klp_func, stack_node); @@ -115,7 +119,7 @@ static void notrace klp_ftrace_handler(unsigned long ip, klp_arch_set_pc(regs, (unsigned long)func->new_func); unlock: - rcu_read_unlock(); + preempt_enable_notrace(); } /* diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c index adc0cc64aa4b..b004a1fb6032 100644 --- a/kernel/livepatch/transition.c +++ b/kernel/livepatch/transition.c @@ -49,6 +49,28 @@ static void klp_transition_work_fn(struct work_struct *work) static DECLARE_DELAYED_WORK(klp_transition_work, klp_transition_work_fn); /* + * This function is just a stub to implement a hard force + * of synchronize_sched(). This requires synchronizing + * tasks even in userspace and idle. + */ +static void klp_sync(struct work_struct *work) +{ +} + +/* + * We allow to patch also functions where RCU is not watching, + * e.g. before user_exit(). We can not rely on the RCU infrastructure + * to do the synchronization. Instead hard force the sched synchronization. + * + * This approach allows to use RCU functions for manipulating func_stack + * safely. + */ +static void klp_synchronize_transition(void) +{ + schedule_on_each_cpu(klp_sync); +} + +/* * The transition to the target patch state is complete. Clean up the data * structures. */ @@ -73,7 +95,7 @@ static void klp_complete_transition(void) * func->transition gets cleared, the handler may choose a * removed function. */ - synchronize_rcu(); + klp_synchronize_transition(); } if (klp_transition_patch->immediate) @@ -92,7 +114,7 @@ static void klp_complete_transition(void) /* Prevent klp_ftrace_handler() from seeing KLP_UNDEFINED state */ if (klp_target_state == KLP_PATCHED) - synchronize_rcu(); + klp_synchronize_transition(); read_lock(&tasklist_lock); for_each_process_thread(g, task) { @@ -136,7 +158,11 @@ void klp_cancel_transition(void) */ void klp_update_patch_state(struct task_struct *task) { - rcu_read_lock(); + /* + * A variant of synchronize_sched() is used to allow patching functions + * where RCU is not watching, see klp_synchronize_transition(). + */ + preempt_disable_notrace(); /* * This test_and_clear_tsk_thread_flag() call also serves as a read @@ -153,7 +179,7 @@ void klp_update_patch_state(struct task_struct *task) if (test_and_clear_tsk_thread_flag(task, TIF_PATCH_PENDING)) task->patch_state = READ_ONCE(klp_target_state); - rcu_read_unlock(); + preempt_enable_notrace(); } /* @@ -539,7 +565,7 @@ void klp_reverse_transition(void) clear_tsk_thread_flag(idle_task(cpu), TIF_PATCH_PENDING); /* Let any remaining calls to klp_update_patch_state() complete */ - synchronize_rcu(); + klp_synchronize_transition(); klp_start_transition(); } diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index c0e31bfee25c..7d2499bec5fe 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -1157,18 +1157,18 @@ print_circular_bug_header(struct lock_list *entry, unsigned int depth, if (debug_locks_silent) return 0; - printk("\n"); + pr_warn("\n"); pr_warn("======================================================\n"); pr_warn("WARNING: possible circular locking dependency detected\n"); print_kernel_ident(); pr_warn("------------------------------------------------------\n"); - printk("%s/%d is trying to acquire lock:\n", + pr_warn("%s/%d is trying to acquire lock:\n", curr->comm, task_pid_nr(curr)); print_lock(check_src); - printk("\nbut task is already holding lock:\n"); + pr_warn("\nbut task is already holding lock:\n"); print_lock(check_tgt); - printk("\nwhich lock already depends on the new lock.\n\n"); - printk("\nthe existing dependency chain (in reverse order) is:\n"); + pr_warn("\nwhich lock already depends on the new lock.\n\n"); + pr_warn("\nthe existing dependency chain (in reverse order) is:\n"); print_circular_bug_entry(entry, depth); @@ -1495,13 +1495,13 @@ print_bad_irq_dependency(struct task_struct *curr, if (!debug_locks_off_graph_unlock() || debug_locks_silent) return 0; - printk("\n"); + pr_warn("\n"); pr_warn("=====================================================\n"); pr_warn("WARNING: %s-safe -> %s-unsafe lock order detected\n", irqclass, irqclass); print_kernel_ident(); pr_warn("-----------------------------------------------------\n"); - printk("%s/%d [HC%u[%lu]:SC%u[%lu]:HE%u:SE%u] is trying to acquire:\n", + pr_warn("%s/%d [HC%u[%lu]:SC%u[%lu]:HE%u:SE%u] is trying to acquire:\n", curr->comm, task_pid_nr(curr), curr->hardirq_context, hardirq_count() >> HARDIRQ_SHIFT, curr->softirq_context, softirq_count() >> SOFTIRQ_SHIFT, @@ -1509,46 +1509,46 @@ print_bad_irq_dependency(struct task_struct *curr, curr->softirqs_enabled); print_lock(next); - printk("\nand this task is already holding:\n"); + pr_warn("\nand this task is already holding:\n"); print_lock(prev); - printk("which would create a new lock dependency:\n"); + pr_warn("which would create a new lock dependency:\n"); print_lock_name(hlock_class(prev)); - printk(KERN_CONT " ->"); + pr_cont(" ->"); print_lock_name(hlock_class(next)); - printk(KERN_CONT "\n"); + pr_cont("\n"); - printk("\nbut this new dependency connects a %s-irq-safe lock:\n", + pr_warn("\nbut this new dependency connects a %s-irq-safe lock:\n", irqclass); print_lock_name(backwards_entry->class); - printk("\n... which became %s-irq-safe at:\n", irqclass); + pr_warn("\n... which became %s-irq-safe at:\n", irqclass); print_stack_trace(backwards_entry->class->usage_traces + bit1, 1); - printk("\nto a %s-irq-unsafe lock:\n", irqclass); + pr_warn("\nto a %s-irq-unsafe lock:\n", irqclass); print_lock_name(forwards_entry->class); - printk("\n... which became %s-irq-unsafe at:\n", irqclass); - printk("..."); + pr_warn("\n... which became %s-irq-unsafe at:\n", irqclass); + pr_warn("..."); print_stack_trace(forwards_entry->class->usage_traces + bit2, 1); - printk("\nother info that might help us debug this:\n\n"); + pr_warn("\nother info that might help us debug this:\n\n"); print_irq_lock_scenario(backwards_entry, forwards_entry, hlock_class(prev), hlock_class(next)); lockdep_print_held_locks(curr); - printk("\nthe dependencies between %s-irq-safe lock and the holding lock:\n", irqclass); + pr_warn("\nthe dependencies between %s-irq-safe lock and the holding lock:\n", irqclass); if (!save_trace(&prev_root->trace)) return 0; print_shortest_lock_dependencies(backwards_entry, prev_root); - printk("\nthe dependencies between the lock to be acquired"); - printk(" and %s-irq-unsafe lock:\n", irqclass); + pr_warn("\nthe dependencies between the lock to be acquired"); + pr_warn(" and %s-irq-unsafe lock:\n", irqclass); if (!save_trace(&next_root->trace)) return 0; print_shortest_lock_dependencies(forwards_entry, next_root); - printk("\nstack backtrace:\n"); + pr_warn("\nstack backtrace:\n"); dump_stack(); return 0; @@ -1724,22 +1724,22 @@ print_deadlock_bug(struct task_struct *curr, struct held_lock *prev, if (!debug_locks_off_graph_unlock() || debug_locks_silent) return 0; - printk("\n"); + pr_warn("\n"); pr_warn("============================================\n"); pr_warn("WARNING: possible recursive locking detected\n"); print_kernel_ident(); pr_warn("--------------------------------------------\n"); - printk("%s/%d is trying to acquire lock:\n", + pr_warn("%s/%d is trying to acquire lock:\n", curr->comm, task_pid_nr(curr)); print_lock(next); - printk("\nbut task is already holding lock:\n"); + pr_warn("\nbut task is already holding lock:\n"); print_lock(prev); - printk("\nother info that might help us debug this:\n"); + pr_warn("\nother info that might help us debug this:\n"); print_deadlock_scenario(next, prev); lockdep_print_held_locks(curr); - printk("\nstack backtrace:\n"); + pr_warn("\nstack backtrace:\n"); dump_stack(); return 0; @@ -2074,21 +2074,21 @@ static void print_collision(struct task_struct *curr, struct held_lock *hlock_next, struct lock_chain *chain) { - printk("\n"); + pr_warn("\n"); pr_warn("============================\n"); pr_warn("WARNING: chain_key collision\n"); print_kernel_ident(); pr_warn("----------------------------\n"); - printk("%s/%d: ", current->comm, task_pid_nr(current)); - printk("Hash chain already cached but the contents don't match!\n"); + pr_warn("%s/%d: ", current->comm, task_pid_nr(current)); + pr_warn("Hash chain already cached but the contents don't match!\n"); - printk("Held locks:"); + pr_warn("Held locks:"); print_chain_keys_held_locks(curr, hlock_next); - printk("Locks in cached chain:"); + pr_warn("Locks in cached chain:"); print_chain_keys_chain(chain); - printk("\nstack backtrace:\n"); + pr_warn("\nstack backtrace:\n"); dump_stack(); } #endif @@ -2373,16 +2373,16 @@ print_usage_bug(struct task_struct *curr, struct held_lock *this, if (!debug_locks_off_graph_unlock() || debug_locks_silent) return 0; - printk("\n"); + pr_warn("\n"); pr_warn("================================\n"); pr_warn("WARNING: inconsistent lock state\n"); print_kernel_ident(); pr_warn("--------------------------------\n"); - printk("inconsistent {%s} -> {%s} usage.\n", + pr_warn("inconsistent {%s} -> {%s} usage.\n", usage_str[prev_bit], usage_str[new_bit]); - printk("%s/%d [HC%u[%lu]:SC%u[%lu]:HE%u:SE%u] takes:\n", + pr_warn("%s/%d [HC%u[%lu]:SC%u[%lu]:HE%u:SE%u] takes:\n", curr->comm, task_pid_nr(curr), trace_hardirq_context(curr), hardirq_count() >> HARDIRQ_SHIFT, trace_softirq_context(curr), softirq_count() >> SOFTIRQ_SHIFT, @@ -2390,16 +2390,16 @@ print_usage_bug(struct task_struct *curr, struct held_lock *this, trace_softirqs_enabled(curr)); print_lock(this); - printk("{%s} state was registered at:\n", usage_str[prev_bit]); + pr_warn("{%s} state was registered at:\n", usage_str[prev_bit]); print_stack_trace(hlock_class(this)->usage_traces + prev_bit, 1); print_irqtrace_events(curr); - printk("\nother info that might help us debug this:\n"); + pr_warn("\nother info that might help us debug this:\n"); print_usage_bug_scenario(this); lockdep_print_held_locks(curr); - printk("\nstack backtrace:\n"); + pr_warn("\nstack backtrace:\n"); dump_stack(); return 0; @@ -2438,28 +2438,28 @@ print_irq_inversion_bug(struct task_struct *curr, if (!debug_locks_off_graph_unlock() || debug_locks_silent) return 0; - printk("\n"); + pr_warn("\n"); pr_warn("========================================================\n"); pr_warn("WARNING: possible irq lock inversion dependency detected\n"); print_kernel_ident(); pr_warn("--------------------------------------------------------\n"); - printk("%s/%d just changed the state of lock:\n", + pr_warn("%s/%d just changed the state of lock:\n", curr->comm, task_pid_nr(curr)); print_lock(this); if (forwards) - printk("but this lock took another, %s-unsafe lock in the past:\n", irqclass); + pr_warn("but this lock took another, %s-unsafe lock in the past:\n", irqclass); else - printk("but this lock was taken by another, %s-safe lock in the past:\n", irqclass); + pr_warn("but this lock was taken by another, %s-safe lock in the past:\n", irqclass); print_lock_name(other->class); - printk("\n\nand interrupts could create inverse lock ordering between them.\n\n"); + pr_warn("\n\nand interrupts could create inverse lock ordering between them.\n\n"); - printk("\nother info that might help us debug this:\n"); + pr_warn("\nother info that might help us debug this:\n"); /* Find a middle lock (if one exists) */ depth = get_lock_depth(other); do { if (depth == 0 && (entry != root)) { - printk("lockdep:%s bad path found in chain graph\n", __func__); + pr_warn("lockdep:%s bad path found in chain graph\n", __func__); break; } middle = entry; @@ -2475,12 +2475,12 @@ print_irq_inversion_bug(struct task_struct *curr, lockdep_print_held_locks(curr); - printk("\nthe shortest dependencies between 2nd lock and 1st lock:\n"); + pr_warn("\nthe shortest dependencies between 2nd lock and 1st lock:\n"); if (!save_trace(&root->trace)) return 0; print_shortest_lock_dependencies(other, root); - printk("\nstack backtrace:\n"); + pr_warn("\nstack backtrace:\n"); dump_stack(); return 0; @@ -3189,25 +3189,25 @@ print_lock_nested_lock_not_held(struct task_struct *curr, if (debug_locks_silent) return 0; - printk("\n"); + pr_warn("\n"); pr_warn("==================================\n"); pr_warn("WARNING: Nested lock was not taken\n"); print_kernel_ident(); pr_warn("----------------------------------\n"); - printk("%s/%d is trying to lock:\n", curr->comm, task_pid_nr(curr)); + pr_warn("%s/%d is trying to lock:\n", curr->comm, task_pid_nr(curr)); print_lock(hlock); - printk("\nbut this task is not holding:\n"); - printk("%s\n", hlock->nest_lock->name); + pr_warn("\nbut this task is not holding:\n"); + pr_warn("%s\n", hlock->nest_lock->name); - printk("\nstack backtrace:\n"); + pr_warn("\nstack backtrace:\n"); dump_stack(); - printk("\nother info that might help us debug this:\n"); + pr_warn("\nother info that might help us debug this:\n"); lockdep_print_held_locks(curr); - printk("\nstack backtrace:\n"); + pr_warn("\nstack backtrace:\n"); dump_stack(); return 0; @@ -3402,21 +3402,21 @@ print_unlock_imbalance_bug(struct task_struct *curr, struct lockdep_map *lock, if (debug_locks_silent) return 0; - printk("\n"); + pr_warn("\n"); pr_warn("=====================================\n"); pr_warn("WARNING: bad unlock balance detected!\n"); print_kernel_ident(); pr_warn("-------------------------------------\n"); - printk("%s/%d is trying to release lock (", + pr_warn("%s/%d is trying to release lock (", curr->comm, task_pid_nr(curr)); print_lockdep_cache(lock); - printk(KERN_CONT ") at:\n"); + pr_cont(") at:\n"); print_ip_sym(ip); - printk("but there are no more locks to release!\n"); - printk("\nother info that might help us debug this:\n"); + pr_warn("but there are no more locks to release!\n"); + pr_warn("\nother info that might help us debug this:\n"); lockdep_print_held_locks(curr); - printk("\nstack backtrace:\n"); + pr_warn("\nstack backtrace:\n"); dump_stack(); return 0; @@ -3974,21 +3974,21 @@ print_lock_contention_bug(struct task_struct *curr, struct lockdep_map *lock, if (debug_locks_silent) return 0; - printk("\n"); + pr_warn("\n"); pr_warn("=================================\n"); pr_warn("WARNING: bad contention detected!\n"); print_kernel_ident(); pr_warn("---------------------------------\n"); - printk("%s/%d is trying to contend lock (", + pr_warn("%s/%d is trying to contend lock (", curr->comm, task_pid_nr(curr)); print_lockdep_cache(lock); - printk(KERN_CONT ") at:\n"); + pr_cont(") at:\n"); print_ip_sym(ip); - printk("but there are no locks held!\n"); - printk("\nother info that might help us debug this:\n"); + pr_warn("but there are no locks held!\n"); + pr_warn("\nother info that might help us debug this:\n"); lockdep_print_held_locks(curr); - printk("\nstack backtrace:\n"); + pr_warn("\nstack backtrace:\n"); dump_stack(); return 0; @@ -4318,17 +4318,17 @@ print_freed_lock_bug(struct task_struct *curr, const void *mem_from, if (debug_locks_silent) return; - printk("\n"); + pr_warn("\n"); pr_warn("=========================\n"); pr_warn("WARNING: held lock freed!\n"); print_kernel_ident(); pr_warn("-------------------------\n"); - printk("%s/%d is freeing memory %p-%p, with a lock still held there!\n", + pr_warn("%s/%d is freeing memory %p-%p, with a lock still held there!\n", curr->comm, task_pid_nr(curr), mem_from, mem_to-1); print_lock(hlock); lockdep_print_held_locks(curr); - printk("\nstack backtrace:\n"); + pr_warn("\nstack backtrace:\n"); dump_stack(); } @@ -4376,14 +4376,14 @@ static void print_held_locks_bug(void) if (debug_locks_silent) return; - printk("\n"); + pr_warn("\n"); pr_warn("====================================\n"); pr_warn("WARNING: %s/%d still has locks held!\n", current->comm, task_pid_nr(current)); print_kernel_ident(); pr_warn("------------------------------------\n"); lockdep_print_held_locks(current); - printk("\nstack backtrace:\n"); + pr_warn("\nstack backtrace:\n"); dump_stack(); } @@ -4402,10 +4402,10 @@ void debug_show_all_locks(void) int unlock = 1; if (unlikely(!debug_locks)) { - printk("INFO: lockdep is turned off.\n"); + pr_warn("INFO: lockdep is turned off.\n"); return; } - printk("\nShowing all locks held in the system:\n"); + pr_warn("\nShowing all locks held in the system:\n"); /* * Here we try to get the tasklist_lock as hard as possible, @@ -4416,18 +4416,18 @@ void debug_show_all_locks(void) retry: if (!read_trylock(&tasklist_lock)) { if (count == 10) - printk("hm, tasklist_lock locked, retrying... "); + pr_warn("hm, tasklist_lock locked, retrying... "); if (count) { count--; - printk(" #%d", 10-count); + pr_cont(" #%d", 10-count); mdelay(200); goto retry; } - printk(" ignoring it.\n"); + pr_cont(" ignoring it.\n"); unlock = 0; } else { if (count != 10) - printk(KERN_CONT " locked it.\n"); + pr_cont(" locked it.\n"); } do_each_thread(g, p) { @@ -4445,7 +4445,7 @@ retry: unlock = 1; } while_each_thread(g, p); - printk("\n"); + pr_warn("\n"); pr_warn("=============================================\n\n"); if (unlock) @@ -4475,12 +4475,12 @@ asmlinkage __visible void lockdep_sys_exit(void) if (unlikely(curr->lockdep_depth)) { if (!debug_locks_off()) return; - printk("\n"); + pr_warn("\n"); pr_warn("================================================\n"); pr_warn("WARNING: lock held when returning to user space!\n"); print_kernel_ident(); pr_warn("------------------------------------------------\n"); - printk("%s/%d is leaving the kernel with locks still held!\n", + pr_warn("%s/%d is leaving the kernel with locks still held!\n", curr->comm, curr->pid); lockdep_print_held_locks(curr); } @@ -4490,19 +4490,15 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s) { struct task_struct *curr = current; -#ifndef CONFIG_PROVE_RCU_REPEATEDLY - if (!debug_locks_off()) - return; -#endif /* #ifdef CONFIG_PROVE_RCU_REPEATEDLY */ /* Note: the following can be executed concurrently, so be careful. */ - printk("\n"); + pr_warn("\n"); pr_warn("=============================\n"); pr_warn("WARNING: suspicious RCU usage\n"); print_kernel_ident(); pr_warn("-----------------------------\n"); - printk("%s:%d %s!\n", file, line, s); - printk("\nother info that might help us debug this:\n\n"); - printk("\n%srcu_scheduler_active = %d, debug_locks = %d\n", + pr_warn("%s:%d %s!\n", file, line, s); + pr_warn("\nother info that might help us debug this:\n\n"); + pr_warn("\n%srcu_scheduler_active = %d, debug_locks = %d\n", !rcu_lockdep_current_cpu_online() ? "RCU used illegally from offline CPU!\n" : !rcu_is_watching() @@ -4529,10 +4525,10 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s) * rcu_read_lock_bh() and so on from extended quiescent states. */ if (!rcu_is_watching()) - printk("RCU used illegally from extended quiescent state!\n"); + pr_warn("RCU used illegally from extended quiescent state!\n"); lockdep_print_held_locks(curr); - printk("\nstack backtrace:\n"); + pr_warn("\nstack backtrace:\n"); dump_stack(); } EXPORT_SYMBOL_GPL(lockdep_rcu_suspicious); diff --git a/kernel/locking/rtmutex-debug.c b/kernel/locking/rtmutex-debug.c index 58e366ad36f4..ac35e648b0e5 100644 --- a/kernel/locking/rtmutex-debug.c +++ b/kernel/locking/rtmutex-debug.c @@ -166,12 +166,16 @@ void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter) memset(waiter, 0x22, sizeof(*waiter)); } -void debug_rt_mutex_init(struct rt_mutex *lock, const char *name) +void debug_rt_mutex_init(struct rt_mutex *lock, const char *name, struct lock_class_key *key) { /* * Make sure we are not reinitializing a held lock: */ debug_check_no_locks_freed((void *)lock, sizeof(*lock)); lock->name = name; + +#ifdef CONFIG_DEBUG_LOCK_ALLOC + lockdep_init_map(&lock->dep_map, name, key, 0); +#endif } diff --git a/kernel/locking/rtmutex-debug.h b/kernel/locking/rtmutex-debug.h index b585af9a1b50..5078c6ddf4a5 100644 --- a/kernel/locking/rtmutex-debug.h +++ b/kernel/locking/rtmutex-debug.h @@ -11,7 +11,7 @@ extern void debug_rt_mutex_init_waiter(struct rt_mutex_waiter *waiter); extern void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter); -extern void debug_rt_mutex_init(struct rt_mutex *lock, const char *name); +extern void debug_rt_mutex_init(struct rt_mutex *lock, const char *name, struct lock_class_key *key); extern void debug_rt_mutex_lock(struct rt_mutex *lock); extern void debug_rt_mutex_unlock(struct rt_mutex *lock); extern void debug_rt_mutex_proxy_lock(struct rt_mutex *lock, diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 28cd09e635ed..78069895032a 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1481,6 +1481,7 @@ void __sched rt_mutex_lock(struct rt_mutex *lock) { might_sleep(); + mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock); } EXPORT_SYMBOL_GPL(rt_mutex_lock); @@ -1496,9 +1497,16 @@ EXPORT_SYMBOL_GPL(rt_mutex_lock); */ int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock) { + int ret; + might_sleep(); - return rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, rt_mutex_slowlock); + mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); + ret = rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, rt_mutex_slowlock); + if (ret) + mutex_release(&lock->dep_map, 1, _RET_IP_); + + return ret; } EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible); @@ -1526,11 +1534,18 @@ int __sched rt_mutex_futex_trylock(struct rt_mutex *lock) int rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout) { + int ret; + might_sleep(); - return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout, + mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); + ret = rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout, RT_MUTEX_MIN_CHAINWALK, rt_mutex_slowlock); + if (ret) + mutex_release(&lock->dep_map, 1, _RET_IP_); + + return ret; } EXPORT_SYMBOL_GPL(rt_mutex_timed_lock); @@ -1547,10 +1562,16 @@ EXPORT_SYMBOL_GPL(rt_mutex_timed_lock); */ int __sched rt_mutex_trylock(struct rt_mutex *lock) { + int ret; + if (WARN_ON_ONCE(in_irq() || in_nmi() || in_serving_softirq())) return 0; - return rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock); + ret = rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock); + if (ret) + mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); + + return ret; } EXPORT_SYMBOL_GPL(rt_mutex_trylock); @@ -1561,6 +1582,7 @@ EXPORT_SYMBOL_GPL(rt_mutex_trylock); */ void __sched rt_mutex_unlock(struct rt_mutex *lock) { + mutex_release(&lock->dep_map, 1, _RET_IP_); rt_mutex_fastunlock(lock, rt_mutex_slowunlock); } EXPORT_SYMBOL_GPL(rt_mutex_unlock); @@ -1620,7 +1642,6 @@ void rt_mutex_destroy(struct rt_mutex *lock) lock->magic = NULL; #endif } - EXPORT_SYMBOL_GPL(rt_mutex_destroy); /** @@ -1632,14 +1653,16 @@ EXPORT_SYMBOL_GPL(rt_mutex_destroy); * * Initializing of a locked rt lock is not allowed */ -void __rt_mutex_init(struct rt_mutex *lock, const char *name) +void __rt_mutex_init(struct rt_mutex *lock, const char *name, + struct lock_class_key *key) { lock->owner = NULL; raw_spin_lock_init(&lock->wait_lock); lock->waiters = RB_ROOT; lock->waiters_leftmost = NULL; - debug_rt_mutex_init(lock, name); + if (name && key) + debug_rt_mutex_init(lock, name, key); } EXPORT_SYMBOL_GPL(__rt_mutex_init); @@ -1660,7 +1683,7 @@ EXPORT_SYMBOL_GPL(__rt_mutex_init); void rt_mutex_init_proxy_locked(struct rt_mutex *lock, struct task_struct *proxy_owner) { - __rt_mutex_init(lock, NULL); + __rt_mutex_init(lock, NULL, NULL); debug_rt_mutex_proxy_lock(lock, proxy_owner); rt_mutex_set_owner(lock, proxy_owner); } diff --git a/kernel/locking/rtmutex.h b/kernel/locking/rtmutex.h index 6607802efa8b..5c253caffe91 100644 --- a/kernel/locking/rtmutex.h +++ b/kernel/locking/rtmutex.h @@ -17,7 +17,7 @@ #define debug_rt_mutex_proxy_lock(l,p) do { } while (0) #define debug_rt_mutex_proxy_unlock(l) do { } while (0) #define debug_rt_mutex_unlock(l) do { } while (0) -#define debug_rt_mutex_init(m, n) do { } while (0) +#define debug_rt_mutex_init(m, n, k) do { } while (0) #define debug_rt_mutex_deadlock(d, a ,l) do { } while (0) #define debug_rt_mutex_print_deadlock(w) do { } while (0) #define debug_rt_mutex_reset_waiter(w) do { } while (0) diff --git a/kernel/power/swap.c b/kernel/power/swap.c index f80fd33639e0..57d22571f306 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -225,14 +225,14 @@ static struct block_device *hib_resume_bdev; struct hib_bio_batch { atomic_t count; wait_queue_head_t wait; - int error; + blk_status_t error; }; static void hib_init_batch(struct hib_bio_batch *hb) { atomic_set(&hb->count, 0); init_waitqueue_head(&hb->wait); - hb->error = 0; + hb->error = BLK_STS_OK; } static void hib_end_io(struct bio *bio) @@ -240,7 +240,7 @@ static void hib_end_io(struct bio *bio) struct hib_bio_batch *hb = bio->bi_private; struct page *page = bio->bi_io_vec[0].bv_page; - if (bio->bi_error) { + if (bio->bi_status) { printk(KERN_ALERT "Read-error on swap-device (%u:%u:%Lu)\n", imajor(bio->bi_bdev->bd_inode), iminor(bio->bi_bdev->bd_inode), @@ -253,8 +253,8 @@ static void hib_end_io(struct bio *bio) flush_icache_range((unsigned long)page_address(page), (unsigned long)page_address(page) + PAGE_SIZE); - if (bio->bi_error && !hb->error) - hb->error = bio->bi_error; + if (bio->bi_status && !hb->error) + hb->error = bio->bi_status; if (atomic_dec_and_test(&hb->count)) wake_up(&hb->wait); @@ -293,10 +293,10 @@ static int hib_submit_io(int op, int op_flags, pgoff_t page_off, void *addr, return error; } -static int hib_wait_io(struct hib_bio_batch *hb) +static blk_status_t hib_wait_io(struct hib_bio_batch *hb) { wait_event(hb->wait, atomic_read(&hb->count) == 0); - return hb->error; + return blk_status_to_errno(hb->error); } /* diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index a1db38abac5b..bd53ea579dc8 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1175,7 +1175,7 @@ static void boot_delay_msec(int level) unsigned long long k; unsigned long timeout; - if ((boot_delay == 0 || system_state != SYSTEM_BOOTING) + if ((boot_delay == 0 || system_state >= SYSTEM_RUNNING) || suppress_message_printing(level)) { return; } diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig new file mode 100644 index 000000000000..be90c945063f --- /dev/null +++ b/kernel/rcu/Kconfig @@ -0,0 +1,242 @@ +# +# RCU-related configuration options +# + +menu "RCU Subsystem" + +config TREE_RCU + bool + default y if !PREEMPT && SMP + help + This option selects the RCU implementation that is + designed for very large SMP system with hundreds or + thousands of CPUs. It also scales down nicely to + smaller systems. + +config PREEMPT_RCU + bool + default y if PREEMPT + help + This option selects the RCU implementation that is + designed for very large SMP systems with hundreds or + thousands of CPUs, but for which real-time response + is also required. It also scales down nicely to + smaller systems. + + Select this option if you are unsure. + +config TINY_RCU + bool + default y if !PREEMPT && !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. + +config RCU_EXPERT + bool "Make expert-level adjustments to RCU configuration" + default n + help + This option needs to be enabled if you wish to make + expert-level adjustments to RCU configuration. By default, + no such adjustments can be made, which has the often-beneficial + side-effect of preventing "make oldconfig" from asking you all + sorts of detailed questions about how you would like numerous + obscure RCU options to be set up. + + Say Y if you need to make expert-level adjustments to RCU. + + Say N if you are unsure. + +config SRCU + bool + help + This option selects the sleepable version of RCU. This version + permits arbitrary sleeping or blocking within RCU read-side critical + sections. + +config TINY_SRCU + bool + default y if SRCU && TINY_RCU + help + This option selects the single-CPU non-preemptible version of SRCU. + +config TREE_SRCU + bool + default y if SRCU && !TINY_RCU + help + This option selects the full-fledged version of SRCU. + +config TASKS_RCU + bool + default n + select SRCU + help + This option enables a task-based RCU implementation that uses + only voluntary context switch (not preemption!), idle, and + user-mode execution as quiescent states. + +config RCU_STALL_COMMON + def_bool ( TREE_RCU || PREEMPT_RCU ) + help + This option enables RCU CPU stall code that is common between + the TINY and TREE variants of RCU. The purpose is to allow + the tiny variants to disable RCU CPU stall warnings, while + making these warnings mandatory for the tree variants. + +config RCU_NEED_SEGCBLIST + def_bool ( TREE_RCU || PREEMPT_RCU || TREE_SRCU ) + +config CONTEXT_TRACKING + bool + +config CONTEXT_TRACKING_FORCE + bool "Force context tracking" + depends on CONTEXT_TRACKING + default y if !NO_HZ_FULL + help + The major pre-requirement for full dynticks to work is to + support the context tracking subsystem. But there are also + other dependencies to provide in order to make the full + dynticks working. + + This option stands for testing when an arch implements the + context tracking backend but doesn't yet fullfill all the + requirements to make the full dynticks feature working. + Without the full dynticks, there is no way to test the support + for context tracking and the subsystems that rely on it: RCU + userspace extended quiescent state and tickless cputime + accounting. This option copes with the absence of the full + dynticks subsystem by forcing the context tracking on all + CPUs in the system. + + Say Y only if you're working on the development of an + architecture backend for the context tracking. + + Say N otherwise, this option brings an overhead that you + don't want in production. + + +config RCU_FANOUT + int "Tree-based hierarchical RCU fanout value" + range 2 64 if 64BIT + range 2 32 if !64BIT + depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT + default 64 if 64BIT + default 32 if !64BIT + help + This option controls the fanout of hierarchical implementations + of RCU, allowing RCU to work efficiently on machines with + large numbers of CPUs. This value must be at least the fourth + root of NR_CPUS, which allows NR_CPUS to be insanely large. + The default value of RCU_FANOUT should be used for production + systems, but if you are stress-testing the RCU implementation + itself, small RCU_FANOUT values allow you to test large-system + code paths on small(er) systems. + + Select a specific number if testing RCU itself. + Take the default if unsure. + +config RCU_FANOUT_LEAF + int "Tree-based hierarchical RCU leaf-level fanout value" + range 2 64 if 64BIT + range 2 32 if !64BIT + depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT + default 16 + help + This option controls the leaf-level fanout of hierarchical + implementations of RCU, and allows trading off cache misses + against lock contention. Systems that synchronize their + scheduling-clock interrupts for energy-efficiency reasons will + want the default because the smaller leaf-level fanout keeps + lock contention levels acceptably low. Very large systems + (hundreds or thousands of CPUs) will instead want to set this + value to the maximum value possible in order to reduce the + number of cache misses incurred during RCU's grace-period + initialization. These systems tend to run CPU-bound, and thus + are not helped by synchronized interrupts, and thus tend to + skew them, which reduces lock contention enough that large + leaf-level fanouts work well. That said, setting leaf-level + fanout to a large number will likely cause problematic + lock contention on the leaf-level rcu_node structures unless + you boot with the skew_tick kernel parameter. + + Select a specific number if testing RCU itself. + + Select the maximum permissible value for large systems, but + please understand that you may also need to set the skew_tick + kernel boot parameter to avoid contention on the rcu_node + structure's locks. + + Take the default if unsure. + +config RCU_FAST_NO_HZ + bool "Accelerate last non-dyntick-idle CPU's grace periods" + depends on NO_HZ_COMMON && SMP && RCU_EXPERT + default n + help + This option permits CPUs to enter dynticks-idle state even if + they have RCU callbacks queued, and prevents RCU from waking + these CPUs up more than roughly once every four jiffies (by + default, you can adjust this using the rcutree.rcu_idle_gp_delay + parameter), thus improving energy efficiency. On the other + hand, this option increases the duration of RCU grace periods, + for example, slowing down synchronize_rcu(). + + Say Y if energy efficiency is critically important, and you + don't care about increased grace-period durations. + + Say N if you are unsure. + +config RCU_BOOST + bool "Enable RCU priority boosting" + depends on RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT + default n + help + This option boosts the priority of preempted RCU readers that + block the current preemptible RCU grace period for too long. + This option also prevents heavy loads from blocking RCU + callback invocation for all flavors of RCU. + + Say Y here if you are working with real-time apps or heavy loads + Say N here if you are unsure. + +config RCU_BOOST_DELAY + int "Milliseconds to delay boosting after RCU grace-period start" + range 0 3000 + depends on RCU_BOOST + default 500 + help + This option specifies the time to wait after the beginning of + a given grace period before priority-boosting preempted RCU + readers blocking that grace period. Note that any RCU reader + blocking an expedited RCU grace period is boosted immediately. + + Accept the default if unsure. + +config RCU_NOCB_CPU + bool "Offload RCU callback processing from boot-selected CPUs" + depends on TREE_RCU || PREEMPT_RCU + depends on RCU_EXPERT || NO_HZ_FULL + default n + help + Use this option to reduce OS jitter for aggressive HPC or + real-time workloads. It can also be used to offload RCU + callback invocation to energy-efficient CPUs in battery-powered + asymmetric multiprocessors. + + This option offloads callback invocation from the set of + CPUs specified at boot time by the rcu_nocbs parameter. + For each such CPU, a kthread ("rcuox/N") will be created to + invoke callbacks, where the "N" is the CPU being offloaded, + and where the "x" is "b" for RCU-bh, "p" for RCU-preempt, and + "s" for RCU-sched. Nothing prevents this kthread from running + on the specified CPUs, but (1) the kthreads may be preempted + between each callback, and (2) affinity or cgroups can be used + to force the kthreads to run on whatever set of CPUs is desired. + + Say Y here if you want to help to debug reduced OS jitter. + Say N here if you are unsure. + +endmenu # "RCU Subsystem" diff --git a/kernel/rcu/Kconfig.debug b/kernel/rcu/Kconfig.debug new file mode 100644 index 000000000000..0ec7d1d33a14 --- /dev/null +++ b/kernel/rcu/Kconfig.debug @@ -0,0 +1,82 @@ +# +# RCU-related debugging configuration options +# + +menu "RCU Debugging" + +config PROVE_RCU + def_bool PROVE_LOCKING + +config TORTURE_TEST + tristate + default n + +config RCU_PERF_TEST + tristate "performance tests for RCU" + depends on DEBUG_KERNEL + select TORTURE_TEST + select SRCU + select TASKS_RCU + default n + help + This option provides a kernel module that runs performance + tests on the RCU infrastructure. The kernel module may be built + after the fact on the running kernel to be tested, if desired. + + Say Y here if you want RCU performance tests to be built into + the kernel. + Say M if you want the RCU performance tests to build as a module. + Say N if you are unsure. + +config RCU_TORTURE_TEST + tristate "torture tests for RCU" + depends on DEBUG_KERNEL + select TORTURE_TEST + select SRCU + select TASKS_RCU + default n + help + This option provides a kernel module that runs torture tests + on the RCU infrastructure. The kernel module may be built + after the fact on the running kernel to be tested, if desired. + + Say Y here if you want RCU torture tests to be built into + the kernel. + Say M if you want the RCU torture tests to build as a module. + Say N if you are unsure. + +config RCU_CPU_STALL_TIMEOUT + int "RCU CPU stall timeout in seconds" + depends on RCU_STALL_COMMON + range 3 300 + default 21 + help + If a given RCU grace period extends more than the specified + number of seconds, a CPU stall warning is printed. If the + RCU grace period persists, additional CPU stall warnings are + printed at more widely spaced intervals. + +config RCU_TRACE + bool "Enable tracing for RCU" + depends on DEBUG_KERNEL + default y if TREE_RCU + select TRACE_CLOCK + help + This option enables additional tracepoints for ftrace-style + event tracing. + + Say Y here if you want to enable RCU tracing + Say N if you are unsure. + +config RCU_EQS_DEBUG + bool "Provide debugging asserts for adding NO_HZ support to an arch" + depends on DEBUG_KERNEL + help + This option provides consistency checks in RCU's handling of + NO_HZ. These checks have proven quite helpful in detecting + bugs in arch-specific NO_HZ code. + + Say N here if you need ultimate kernel/user switch latencies + Say Y if you are unsure + +endmenu # "RCU Debugging" diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile index 23803c7d5180..13c0fc852767 100644 --- a/kernel/rcu/Makefile +++ b/kernel/rcu/Makefile @@ -3,13 +3,11 @@ KCOV_INSTRUMENT := n obj-y += update.o sync.o -obj-$(CONFIG_CLASSIC_SRCU) += srcu.o obj-$(CONFIG_TREE_SRCU) += srcutree.o obj-$(CONFIG_TINY_SRCU) += srcutiny.o obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o obj-$(CONFIG_RCU_PERF_TEST) += rcuperf.o obj-$(CONFIG_TREE_RCU) += tree.o obj-$(CONFIG_PREEMPT_RCU) += tree.o -obj-$(CONFIG_TREE_RCU_TRACE) += tree_trace.o obj-$(CONFIG_TINY_RCU) += tiny.o obj-$(CONFIG_RCU_NEED_SEGCBLIST) += rcu_segcblist.o diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index 73e16ec4054b..808b8c85f626 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -212,6 +212,18 @@ int rcu_jiffies_till_stall_check(void); */ #define TPS(x) tracepoint_string(x) +/* + * Dump the ftrace buffer, but only one time per callsite per boot. + */ +#define rcu_ftrace_dump(oops_dump_mode) \ +do { \ + static atomic_t ___rfd_beenhere = ATOMIC_INIT(0); \ + \ + if (!atomic_read(&___rfd_beenhere) && \ + !atomic_xchg(&___rfd_beenhere, 1)) \ + ftrace_dump(oops_dump_mode); \ +} while (0) + void rcu_early_boot_tests(void); void rcu_test_sync_prims(void); @@ -291,6 +303,271 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt) cpu <= rnp->grphi; \ cpu = cpumask_next((cpu), cpu_possible_mask)) +/* + * Wrappers for the rcu_node::lock acquire and release. + * + * Because the rcu_nodes form a tree, the tree traversal locking will observe + * different lock values, this in turn means that an UNLOCK of one level + * followed by a LOCK of another level does not imply a full memory barrier; + * and most importantly transitivity is lost. + * + * In order to restore full ordering between tree levels, augment the regular + * lock acquire functions with smp_mb__after_unlock_lock(). + * + * As ->lock of struct rcu_node is a __private field, therefore one should use + * these wrappers rather than directly call raw_spin_{lock,unlock}* on ->lock. + */ +#define raw_spin_lock_rcu_node(p) \ +do { \ + raw_spin_lock(&ACCESS_PRIVATE(p, lock)); \ + smp_mb__after_unlock_lock(); \ +} while (0) + +#define raw_spin_unlock_rcu_node(p) raw_spin_unlock(&ACCESS_PRIVATE(p, lock)) + +#define raw_spin_lock_irq_rcu_node(p) \ +do { \ + raw_spin_lock_irq(&ACCESS_PRIVATE(p, lock)); \ + smp_mb__after_unlock_lock(); \ +} while (0) + +#define raw_spin_unlock_irq_rcu_node(p) \ + raw_spin_unlock_irq(&ACCESS_PRIVATE(p, lock)) + +#define raw_spin_lock_irqsave_rcu_node(p, flags) \ +do { \ + raw_spin_lock_irqsave(&ACCESS_PRIVATE(p, lock), flags); \ + smp_mb__after_unlock_lock(); \ +} while (0) + +#define raw_spin_unlock_irqrestore_rcu_node(p, flags) \ + raw_spin_unlock_irqrestore(&ACCESS_PRIVATE(p, lock), flags) \ + +#define raw_spin_trylock_rcu_node(p) \ +({ \ + bool ___locked = raw_spin_trylock(&ACCESS_PRIVATE(p, lock)); \ + \ + if (___locked) \ + smp_mb__after_unlock_lock(); \ + ___locked; \ +}) + #endif /* #if defined(SRCU) || !defined(TINY_RCU) */ +#ifdef CONFIG_TINY_RCU +/* Tiny RCU doesn't expedite, as its purpose in life is instead to be tiny. */ +static inline bool rcu_gp_is_normal(void) /* Internal RCU use. */ +{ + return true; +} +static inline bool rcu_gp_is_expedited(void) /* Internal RCU use. */ +{ + return false; +} + +static inline void rcu_expedite_gp(void) +{ +} + +static inline void rcu_unexpedite_gp(void) +{ +} +#else /* #ifdef CONFIG_TINY_RCU */ +bool rcu_gp_is_normal(void); /* Internal RCU use. */ +bool rcu_gp_is_expedited(void); /* Internal RCU use. */ +void rcu_expedite_gp(void); +void rcu_unexpedite_gp(void); +void rcupdate_announce_bootup_oddness(void); +#endif /* #else #ifdef CONFIG_TINY_RCU */ + +#define RCU_SCHEDULER_INACTIVE 0 +#define RCU_SCHEDULER_INIT 1 +#define RCU_SCHEDULER_RUNNING 2 + +#ifdef CONFIG_TINY_RCU +static inline void rcu_request_urgent_qs_task(struct task_struct *t) { } +#else /* #ifdef CONFIG_TINY_RCU */ +void rcu_request_urgent_qs_task(struct task_struct *t); +#endif /* #else #ifdef CONFIG_TINY_RCU */ + +enum rcutorture_type { + RCU_FLAVOR, + RCU_BH_FLAVOR, + RCU_SCHED_FLAVOR, + RCU_TASKS_FLAVOR, + SRCU_FLAVOR, + INVALID_RCU_FLAVOR +}; + +#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU) +void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, + unsigned long *gpnum, unsigned long *completed); +void rcutorture_record_test_transition(void); +void rcutorture_record_progress(unsigned long vernum); +void do_trace_rcu_torture_read(const char *rcutorturename, + struct rcu_head *rhp, + unsigned long secs, + unsigned long c_old, + unsigned long c); +#else +static inline void rcutorture_get_gp_data(enum rcutorture_type test_type, + int *flags, + unsigned long *gpnum, + unsigned long *completed) +{ + *flags = 0; + *gpnum = 0; + *completed = 0; +} +static inline void rcutorture_record_test_transition(void) +{ +} +static inline void rcutorture_record_progress(unsigned long vernum) +{ +} +#ifdef CONFIG_RCU_TRACE +void do_trace_rcu_torture_read(const char *rcutorturename, + struct rcu_head *rhp, + unsigned long secs, + unsigned long c_old, + unsigned long c); +#else +#define do_trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \ + do { } while (0) +#endif +#endif + +#ifdef CONFIG_TINY_SRCU + +static inline void srcutorture_get_gp_data(enum rcutorture_type test_type, + struct srcu_struct *sp, int *flags, + unsigned long *gpnum, + unsigned long *completed) +{ + if (test_type != SRCU_FLAVOR) + return; + *flags = 0; + *completed = sp->srcu_idx; + *gpnum = *completed; +} + +#elif defined(CONFIG_TREE_SRCU) + +void srcutorture_get_gp_data(enum rcutorture_type test_type, + struct srcu_struct *sp, int *flags, + unsigned long *gpnum, unsigned long *completed); + +#endif + +#ifdef CONFIG_TINY_RCU + +/* + * Return the number of grace periods started. + */ +static inline unsigned long rcu_batches_started(void) +{ + return 0; +} + +/* + * Return the number of bottom-half grace periods started. + */ +static inline unsigned long rcu_batches_started_bh(void) +{ + return 0; +} + +/* + * Return the number of sched grace periods started. + */ +static inline unsigned long rcu_batches_started_sched(void) +{ + return 0; +} + +/* + * Return the number of grace periods completed. + */ +static inline unsigned long rcu_batches_completed(void) +{ + return 0; +} + +/* + * Return the number of bottom-half grace periods completed. + */ +static inline unsigned long rcu_batches_completed_bh(void) +{ + return 0; +} + +/* + * Return the number of sched grace periods completed. + */ +static inline unsigned long rcu_batches_completed_sched(void) +{ + return 0; +} + +/* + * Return the number of expedited grace periods completed. + */ +static inline unsigned long rcu_exp_batches_completed(void) +{ + return 0; +} + +/* + * Return the number of expedited sched grace periods completed. + */ +static inline unsigned long rcu_exp_batches_completed_sched(void) +{ + return 0; +} + +static inline unsigned long srcu_batches_completed(struct srcu_struct *sp) +{ + return 0; +} + +static inline void rcu_force_quiescent_state(void) +{ +} + +static inline void rcu_bh_force_quiescent_state(void) +{ +} + +static inline void rcu_sched_force_quiescent_state(void) +{ +} + +static inline void show_rcu_gp_kthreads(void) +{ +} + +#else /* #ifdef CONFIG_TINY_RCU */ +extern unsigned long rcutorture_testseq; +extern unsigned long rcutorture_vernum; +unsigned long rcu_batches_started(void); +unsigned long rcu_batches_started_bh(void); +unsigned long rcu_batches_started_sched(void); +unsigned long rcu_batches_completed(void); +unsigned long rcu_batches_completed_bh(void); +unsigned long rcu_batches_completed_sched(void); +unsigned long rcu_exp_batches_completed(void); +unsigned long rcu_exp_batches_completed_sched(void); +unsigned long srcu_batches_completed(struct srcu_struct *sp); +void show_rcu_gp_kthreads(void); +void rcu_force_quiescent_state(void); +void rcu_bh_force_quiescent_state(void); +void rcu_sched_force_quiescent_state(void); +#endif /* #else #ifdef CONFIG_TINY_RCU */ + +#ifdef CONFIG_RCU_NOCB_CPU +bool rcu_is_nocb_cpu(int cpu); +#else +static inline bool rcu_is_nocb_cpu(int cpu) { return false; } +#endif + #endif /* __LINUX_RCU_H */ diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c index a4a86fb47e4a..3cc18110b612 100644 --- a/kernel/rcu/rcuperf.c +++ b/kernel/rcu/rcuperf.c @@ -48,6 +48,8 @@ #include <linux/torture.h> #include <linux/vmalloc.h> +#include "rcu.h" + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.vnet.ibm.com>"); @@ -59,12 +61,16 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.vnet.ibm.com>"); #define VERBOSE_PERFOUT_ERRSTRING(s) \ do { if (verbose) pr_alert("%s" PERF_FLAG "!!! %s\n", perf_type, s); } while (0) +torture_param(bool, gp_async, false, "Use asynchronous GP wait primitives"); +torture_param(int, gp_async_max, 1000, "Max # outstanding waits per reader"); torture_param(bool, gp_exp, false, "Use expedited GP wait primitives"); torture_param(int, holdoff, 10, "Holdoff time before test start (s)"); -torture_param(int, nreaders, -1, "Number of RCU reader threads"); +torture_param(int, nreaders, 0, "Number of RCU reader threads"); torture_param(int, nwriters, -1, "Number of RCU updater threads"); -torture_param(bool, shutdown, false, "Shutdown at end of performance tests."); +torture_param(bool, shutdown, !IS_ENABLED(MODULE), + "Shutdown at end of performance tests."); torture_param(bool, verbose, true, "Enable verbose debugging printk()s"); +torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable"); static char *perf_type = "rcu"; module_param(perf_type, charp, 0444); @@ -86,13 +92,16 @@ static u64 t_rcu_perf_writer_started; static u64 t_rcu_perf_writer_finished; static unsigned long b_rcu_perf_writer_started; static unsigned long b_rcu_perf_writer_finished; +static DEFINE_PER_CPU(atomic_t, n_async_inflight); static int rcu_perf_writer_state; #define RTWS_INIT 0 -#define RTWS_EXP_SYNC 1 -#define RTWS_SYNC 2 -#define RTWS_IDLE 2 -#define RTWS_STOPPING 3 +#define RTWS_ASYNC 1 +#define RTWS_BARRIER 2 +#define RTWS_EXP_SYNC 3 +#define RTWS_SYNC 4 +#define RTWS_IDLE 5 +#define RTWS_STOPPING 6 #define MAX_MEAS 10000 #define MIN_MEAS 100 @@ -114,6 +123,8 @@ struct rcu_perf_ops { unsigned long (*started)(void); unsigned long (*completed)(void); unsigned long (*exp_completed)(void); + void (*async)(struct rcu_head *head, rcu_callback_t func); + void (*gp_barrier)(void); void (*sync)(void); void (*exp_sync)(void); const char *name; @@ -153,6 +164,8 @@ static struct rcu_perf_ops rcu_ops = { .started = rcu_batches_started, .completed = rcu_batches_completed, .exp_completed = rcu_exp_batches_completed, + .async = call_rcu, + .gp_barrier = rcu_barrier, .sync = synchronize_rcu, .exp_sync = synchronize_rcu_expedited, .name = "rcu" @@ -181,6 +194,8 @@ static struct rcu_perf_ops rcu_bh_ops = { .started = rcu_batches_started_bh, .completed = rcu_batches_completed_bh, .exp_completed = rcu_exp_batches_completed_sched, + .async = call_rcu_bh, + .gp_barrier = rcu_barrier_bh, .sync = synchronize_rcu_bh, .exp_sync = synchronize_rcu_bh_expedited, .name = "rcu_bh" @@ -208,6 +223,16 @@ static unsigned long srcu_perf_completed(void) return srcu_batches_completed(srcu_ctlp); } +static void srcu_call_rcu(struct rcu_head *head, rcu_callback_t func) +{ + call_srcu(srcu_ctlp, head, func); +} + +static void srcu_rcu_barrier(void) +{ + srcu_barrier(srcu_ctlp); +} + static void srcu_perf_synchronize(void) { synchronize_srcu(srcu_ctlp); @@ -226,11 +251,42 @@ static struct rcu_perf_ops srcu_ops = { .started = NULL, .completed = srcu_perf_completed, .exp_completed = srcu_perf_completed, + .async = srcu_call_rcu, + .gp_barrier = srcu_rcu_barrier, .sync = srcu_perf_synchronize, .exp_sync = srcu_perf_synchronize_expedited, .name = "srcu" }; +static struct srcu_struct srcud; + +static void srcu_sync_perf_init(void) +{ + srcu_ctlp = &srcud; + init_srcu_struct(srcu_ctlp); +} + +static void srcu_sync_perf_cleanup(void) +{ + cleanup_srcu_struct(srcu_ctlp); +} + +static struct rcu_perf_ops srcud_ops = { + .ptype = SRCU_FLAVOR, + .init = srcu_sync_perf_init, + .cleanup = srcu_sync_perf_cleanup, + .readlock = srcu_perf_read_lock, + .readunlock = srcu_perf_read_unlock, + .started = NULL, + .completed = srcu_perf_completed, + .exp_completed = srcu_perf_completed, + .async = srcu_call_rcu, + .gp_barrier = srcu_rcu_barrier, + .sync = srcu_perf_synchronize, + .exp_sync = srcu_perf_synchronize_expedited, + .name = "srcud" +}; + /* * Definitions for sched perf testing. */ @@ -254,6 +310,8 @@ static struct rcu_perf_ops sched_ops = { .started = rcu_batches_started_sched, .completed = rcu_batches_completed_sched, .exp_completed = rcu_exp_batches_completed_sched, + .async = call_rcu_sched, + .gp_barrier = rcu_barrier_sched, .sync = synchronize_sched, .exp_sync = synchronize_sched_expedited, .name = "sched" @@ -281,6 +339,8 @@ static struct rcu_perf_ops tasks_ops = { .readunlock = tasks_perf_read_unlock, .started = rcu_no_completed, .completed = rcu_no_completed, + .async = call_rcu_tasks, + .gp_barrier = rcu_barrier_tasks, .sync = synchronize_rcu_tasks, .exp_sync = synchronize_rcu_tasks, .name = "tasks" @@ -344,6 +404,15 @@ rcu_perf_reader(void *arg) } /* + * Callback function for asynchronous grace periods from rcu_perf_writer(). + */ +static void rcu_perf_async_cb(struct rcu_head *rhp) +{ + atomic_dec(this_cpu_ptr(&n_async_inflight)); + kfree(rhp); +} + +/* * RCU perf writer kthread. Repeatedly does a grace period. */ static int @@ -352,6 +421,7 @@ rcu_perf_writer(void *arg) int i = 0; int i_max; long me = (long)arg; + struct rcu_head *rhp = NULL; struct sched_param sp; bool started = false, done = false, alldone = false; u64 t; @@ -380,9 +450,27 @@ rcu_perf_writer(void *arg) } do { + if (writer_holdoff) + udelay(writer_holdoff); wdp = &wdpp[i]; *wdp = ktime_get_mono_fast_ns(); - if (gp_exp) { + if (gp_async) { +retry: + if (!rhp) + rhp = kmalloc(sizeof(*rhp), GFP_KERNEL); + if (rhp && atomic_read(this_cpu_ptr(&n_async_inflight)) < gp_async_max) { + rcu_perf_writer_state = RTWS_ASYNC; + atomic_inc(this_cpu_ptr(&n_async_inflight)); + cur_ops->async(rhp, rcu_perf_async_cb); + rhp = NULL; + } else if (!kthread_should_stop()) { + rcu_perf_writer_state = RTWS_BARRIER; + cur_ops->gp_barrier(); + goto retry; + } else { + kfree(rhp); /* Because we are stopping. */ + } + } else if (gp_exp) { rcu_perf_writer_state = RTWS_EXP_SYNC; cur_ops->exp_sync(); } else { @@ -429,6 +517,10 @@ rcu_perf_writer(void *arg) i++; rcu_perf_wait_shutdown(); } while (!torture_must_stop()); + if (gp_async) { + rcu_perf_writer_state = RTWS_BARRIER; + cur_ops->gp_barrier(); + } rcu_perf_writer_state = RTWS_STOPPING; writer_n_durations[me] = i_max; torture_kthread_stopping("rcu_perf_writer"); @@ -452,6 +544,17 @@ rcu_perf_cleanup(void) u64 *wdp; u64 *wdpp; + /* + * Would like warning at start, but everything is expedited + * during the mid-boot phase, so have to wait till the end. + */ + if (rcu_gp_is_expedited() && !rcu_gp_is_normal() && !gp_exp) + VERBOSE_PERFOUT_ERRSTRING("All grace periods expedited, no normal ones to measure!"); + if (rcu_gp_is_normal() && gp_exp) + VERBOSE_PERFOUT_ERRSTRING("All grace periods normal, no expedited ones to measure!"); + if (gp_exp && gp_async) + VERBOSE_PERFOUT_ERRSTRING("No expedited async GPs, so went with async!"); + if (torture_cleanup_begin()) return; @@ -554,7 +657,7 @@ rcu_perf_init(void) long i; int firsterr = 0; static struct rcu_perf_ops *perf_ops[] = { - &rcu_ops, &rcu_bh_ops, &srcu_ops, &sched_ops, + &rcu_ops, &rcu_bh_ops, &srcu_ops, &srcud_ops, &sched_ops, RCUPERF_TASKS_OPS }; @@ -624,16 +727,6 @@ rcu_perf_init(void) firsterr = -ENOMEM; goto unwind; } - if (rcu_gp_is_expedited() && !rcu_gp_is_normal() && !gp_exp) { - VERBOSE_PERFOUT_ERRSTRING("All grace periods expedited, no normal ones to measure!"); - firsterr = -EINVAL; - goto unwind; - } - if (rcu_gp_is_normal() && gp_exp) { - VERBOSE_PERFOUT_ERRSTRING("All grace periods normal, no expedited ones to measure!"); - firsterr = -EINVAL; - goto unwind; - } for (i = 0; i < nrealwriters; i++) { writer_durations[i] = kcalloc(MAX_MEAS, sizeof(*writer_durations[i]), diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index ae6e574d4cf5..b8f7f8ce8575 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -52,6 +52,8 @@ #include <linux/torture.h> #include <linux/vmalloc.h> +#include "rcu.h" + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@joshtriplett.org>"); @@ -562,31 +564,19 @@ static void srcu_torture_stats(void) int __maybe_unused cpu; int idx; -#if defined(CONFIG_TREE_SRCU) || defined(CONFIG_CLASSIC_SRCU) #ifdef CONFIG_TREE_SRCU idx = srcu_ctlp->srcu_idx & 0x1; -#else /* #ifdef CONFIG_TREE_SRCU */ - idx = srcu_ctlp->completed & 0x1; -#endif /* #else #ifdef CONFIG_TREE_SRCU */ pr_alert("%s%s Tree SRCU per-CPU(idx=%d):", torture_type, TORTURE_FLAG, idx); for_each_possible_cpu(cpu) { unsigned long l0, l1; unsigned long u0, u1; long c0, c1; -#ifdef CONFIG_TREE_SRCU struct srcu_data *counts; counts = per_cpu_ptr(srcu_ctlp->sda, cpu); u0 = counts->srcu_unlock_count[!idx]; u1 = counts->srcu_unlock_count[idx]; -#else /* #ifdef CONFIG_TREE_SRCU */ - struct srcu_array *counts; - - counts = per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu); - u0 = counts->unlock_count[!idx]; - u1 = counts->unlock_count[idx]; -#endif /* #else #ifdef CONFIG_TREE_SRCU */ /* * Make sure that a lock is always counted if the corresponding @@ -594,13 +584,8 @@ static void srcu_torture_stats(void) */ smp_rmb(); -#ifdef CONFIG_TREE_SRCU l0 = counts->srcu_lock_count[!idx]; l1 = counts->srcu_lock_count[idx]; -#else /* #ifdef CONFIG_TREE_SRCU */ - l0 = counts->lock_count[!idx]; - l1 = counts->lock_count[idx]; -#endif /* #else #ifdef CONFIG_TREE_SRCU */ c0 = l0 - u0; c1 = l1 - u1; @@ -609,7 +594,7 @@ static void srcu_torture_stats(void) pr_cont("\n"); #elif defined(CONFIG_TINY_SRCU) idx = READ_ONCE(srcu_ctlp->srcu_idx) & 0x1; - pr_alert("%s%s Tiny SRCU per-CPU(idx=%d): (%d,%d)\n", + pr_alert("%s%s Tiny SRCU per-CPU(idx=%d): (%hd,%hd)\n", torture_type, TORTURE_FLAG, idx, READ_ONCE(srcu_ctlp->srcu_lock_nesting[!idx]), READ_ONCE(srcu_ctlp->srcu_lock_nesting[idx])); diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c deleted file mode 100644 index dea03614263f..000000000000 --- a/kernel/rcu/srcu.c +++ /dev/null @@ -1,661 +0,0 @@ -/* - * Sleepable Read-Copy Update mechanism for mutual exclusion. - * - * 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, you can access it online at - * http://www.gnu.org/licenses/gpl-2.0.html. - * - * Copyright (C) IBM Corporation, 2006 - * Copyright (C) Fujitsu, 2012 - * - * Author: Paul McKenney <paulmck@us.ibm.com> - * Lai Jiangshan <laijs@cn.fujitsu.com> - * - * For detailed explanation of Read-Copy Update mechanism see - - * Documentation/RCU/ *.txt - * - */ - -#include <linux/export.h> -#include <linux/mutex.h> -#include <linux/percpu.h> -#include <linux/preempt.h> -#include <linux/rcupdate_wait.h> -#include <linux/sched.h> -#include <linux/smp.h> -#include <linux/delay.h> -#include <linux/srcu.h> - -#include "rcu.h" - -/* - * Initialize an rcu_batch structure to empty. - */ -static inline void rcu_batch_init(struct rcu_batch *b) -{ - b->head = NULL; - b->tail = &b->head; -} - -/* - * Enqueue a callback onto the tail of the specified rcu_batch structure. - */ -static inline void rcu_batch_queue(struct rcu_batch *b, struct rcu_head *head) -{ - *b->tail = head; - b->tail = &head->next; -} - -/* - * Is the specified rcu_batch structure empty? - */ -static inline bool rcu_batch_empty(struct rcu_batch *b) -{ - return b->tail == &b->head; -} - -/* - * Remove the callback at the head of the specified rcu_batch structure - * and return a pointer to it, or return NULL if the structure is empty. - */ -static inline struct rcu_head *rcu_batch_dequeue(struct rcu_batch *b) -{ - struct rcu_head *head; - - if (rcu_batch_empty(b)) - return NULL; - - head = b->head; - b->head = head->next; - if (b->tail == &head->next) - rcu_batch_init(b); - - return head; -} - -/* - * Move all callbacks from the rcu_batch structure specified by "from" to - * the structure specified by "to". - */ -static inline void rcu_batch_move(struct rcu_batch *to, struct rcu_batch *from) -{ - if (!rcu_batch_empty(from)) { - *to->tail = from->head; - to->tail = from->tail; - rcu_batch_init(from); - } -} - -static int init_srcu_struct_fields(struct srcu_struct *sp) -{ - sp->completed = 0; - spin_lock_init(&sp->queue_lock); - sp->running = false; - rcu_batch_init(&sp->batch_queue); - rcu_batch_init(&sp->batch_check0); - rcu_batch_init(&sp->batch_check1); - rcu_batch_init(&sp->batch_done); - INIT_DELAYED_WORK(&sp->work, process_srcu); - sp->per_cpu_ref = alloc_percpu(struct srcu_array); - return sp->per_cpu_ref ? 0 : -ENOMEM; -} - -#ifdef CONFIG_DEBUG_LOCK_ALLOC - -int __init_srcu_struct(struct srcu_struct *sp, const char *name, - struct lock_class_key *key) -{ - /* Don't re-initialize a lock while it is held. */ - debug_check_no_locks_freed((void *)sp, sizeof(*sp)); - lockdep_init_map(&sp->dep_map, name, key, 0); - return init_srcu_struct_fields(sp); -} -EXPORT_SYMBOL_GPL(__init_srcu_struct); - -#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ - -/** - * init_srcu_struct - initialize a sleep-RCU structure - * @sp: structure to initialize. - * - * Must invoke this on a given srcu_struct before passing that srcu_struct - * to any other function. Each srcu_struct represents a separate domain - * of SRCU protection. - */ -int init_srcu_struct(struct srcu_struct *sp) -{ - return init_srcu_struct_fields(sp); -} -EXPORT_SYMBOL_GPL(init_srcu_struct); - -#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ - -/* - * Returns approximate total of the readers' ->lock_count[] values for the - * rank of per-CPU counters specified by idx. - */ -static unsigned long srcu_readers_lock_idx(struct srcu_struct *sp, int idx) -{ - int cpu; - unsigned long sum = 0; - - for_each_possible_cpu(cpu) { - struct srcu_array *cpuc = per_cpu_ptr(sp->per_cpu_ref, cpu); - - sum += READ_ONCE(cpuc->lock_count[idx]); - } - return sum; -} - -/* - * Returns approximate total of the readers' ->unlock_count[] values for the - * rank of per-CPU counters specified by idx. - */ -static unsigned long srcu_readers_unlock_idx(struct srcu_struct *sp, int idx) -{ - int cpu; - unsigned long sum = 0; - - for_each_possible_cpu(cpu) { - struct srcu_array *cpuc = per_cpu_ptr(sp->per_cpu_ref, cpu); - - sum += READ_ONCE(cpuc->unlock_count[idx]); - } - return sum; -} - -/* - * Return true if the number of pre-existing readers is determined to - * be zero. - */ -static bool srcu_readers_active_idx_check(struct srcu_struct *sp, int idx) -{ - unsigned long unlocks; - - unlocks = srcu_readers_unlock_idx(sp, idx); - - /* - * Make sure that a lock is always counted if the corresponding unlock - * is counted. Needs to be a smp_mb() as the read side may contain a - * read from a variable that is written to before the synchronize_srcu() - * in the write side. In this case smp_mb()s A and B act like the store - * buffering pattern. - * - * This smp_mb() also pairs with smp_mb() C to prevent accesses after the - * synchronize_srcu() from being executed before the grace period ends. - */ - smp_mb(); /* A */ - - /* - * If the locks are the same as the unlocks, then there must have - * been no readers on this index at some time in between. This does not - * mean that there are no more readers, as one could have read the - * current index but not have incremented the lock counter yet. - * - * Possible bug: There is no guarantee that there haven't been ULONG_MAX - * increments of ->lock_count[] since the unlocks were counted, meaning - * that this could return true even if there are still active readers. - * Since there are no memory barriers around srcu_flip(), the CPU is not - * required to increment ->completed before running - * srcu_readers_unlock_idx(), which means that there could be an - * arbitrarily large number of critical sections that execute after - * srcu_readers_unlock_idx() but use the old value of ->completed. - */ - return srcu_readers_lock_idx(sp, idx) == unlocks; -} - -/** - * srcu_readers_active - returns true if there are readers. and false - * otherwise - * @sp: which srcu_struct to count active readers (holding srcu_read_lock). - * - * Note that this is not an atomic primitive, and can therefore suffer - * severe errors when invoked on an active srcu_struct. That said, it - * can be useful as an error check at cleanup time. - */ -static bool srcu_readers_active(struct srcu_struct *sp) -{ - int cpu; - unsigned long sum = 0; - - for_each_possible_cpu(cpu) { - struct srcu_array *cpuc = per_cpu_ptr(sp->per_cpu_ref, cpu); - - sum += READ_ONCE(cpuc->lock_count[0]); - sum += READ_ONCE(cpuc->lock_count[1]); - sum -= READ_ONCE(cpuc->unlock_count[0]); - sum -= READ_ONCE(cpuc->unlock_count[1]); - } - return sum; -} - -/** - * cleanup_srcu_struct - deconstruct a sleep-RCU structure - * @sp: structure to clean up. - * - * Must invoke this only after you are finished using a given srcu_struct - * that was initialized via init_srcu_struct(). This code does some - * probabalistic checking, spotting late uses of srcu_read_lock(), - * synchronize_srcu(), synchronize_srcu_expedited(), and call_srcu(). - * If any such late uses are detected, the per-CPU memory associated with - * the srcu_struct is simply leaked and WARN_ON() is invoked. If the - * caller frees the srcu_struct itself, a use-after-free crash will likely - * ensue, but at least there will be a warning printed. - */ -void cleanup_srcu_struct(struct srcu_struct *sp) -{ - if (WARN_ON(srcu_readers_active(sp))) - return; /* Leakage unless caller handles error. */ - free_percpu(sp->per_cpu_ref); - sp->per_cpu_ref = NULL; -} -EXPORT_SYMBOL_GPL(cleanup_srcu_struct); - -/* - * Counts the new reader in the appropriate per-CPU element of the - * srcu_struct. - * Returns an index that must be passed to the matching srcu_read_unlock(). - */ -int __srcu_read_lock(struct srcu_struct *sp) -{ - int idx; - - idx = READ_ONCE(sp->completed) & 0x1; - this_cpu_inc(sp->per_cpu_ref->lock_count[idx]); - smp_mb(); /* B */ /* Avoid leaking the critical section. */ - return idx; -} -EXPORT_SYMBOL_GPL(__srcu_read_lock); - -/* - * Removes the count for the old reader from the appropriate per-CPU - * element of the srcu_struct. Note that this may well be a different - * CPU than that which was incremented by the corresponding srcu_read_lock(). - */ -void __srcu_read_unlock(struct srcu_struct *sp, int idx) -{ - smp_mb(); /* C */ /* Avoid leaking the critical section. */ - this_cpu_inc(sp->per_cpu_ref->unlock_count[idx]); -} -EXPORT_SYMBOL_GPL(__srcu_read_unlock); - -/* - * We use an adaptive strategy for synchronize_srcu() and especially for - * synchronize_srcu_expedited(). We spin for a fixed time period - * (defined below) to allow SRCU readers to exit their read-side critical - * sections. If there are still some readers after 10 microseconds, - * we repeatedly block for 1-millisecond time periods. This approach - * has done well in testing, so there is no need for a config parameter. - */ -#define SRCU_RETRY_CHECK_DELAY 5 -#define SYNCHRONIZE_SRCU_TRYCOUNT 2 -#define SYNCHRONIZE_SRCU_EXP_TRYCOUNT 12 - -/* - * @@@ Wait until all pre-existing readers complete. Such readers - * will have used the index specified by "idx". - * the caller should ensures the ->completed is not changed while checking - * and idx = (->completed & 1) ^ 1 - */ -static bool try_check_zero(struct srcu_struct *sp, int idx, int trycount) -{ - for (;;) { - if (srcu_readers_active_idx_check(sp, idx)) - return true; - if (--trycount <= 0) - return false; - udelay(SRCU_RETRY_CHECK_DELAY); - } -} - -/* - * Increment the ->completed counter so that future SRCU readers will - * use the other rank of the ->(un)lock_count[] arrays. This allows - * us to wait for pre-existing readers in a starvation-free manner. - */ -static void srcu_flip(struct srcu_struct *sp) -{ - WRITE_ONCE(sp->completed, sp->completed + 1); - - /* - * Ensure that if the updater misses an __srcu_read_unlock() - * increment, that task's next __srcu_read_lock() will see the - * above counter update. Note that both this memory barrier - * and the one in srcu_readers_active_idx_check() provide the - * guarantee for __srcu_read_lock(). - */ - smp_mb(); /* D */ /* Pairs with C. */ -} - -/* - * Enqueue an SRCU callback on the specified srcu_struct structure, - * initiating grace-period processing if it is not already running. - * - * Note that all CPUs must agree that the grace period extended beyond - * all pre-existing SRCU read-side critical section. On systems with - * more than one CPU, this means that when "func()" is invoked, each CPU - * is guaranteed to have executed a full memory barrier since the end of - * its last corresponding SRCU read-side critical section whose beginning - * preceded the call to call_rcu(). It also means that each CPU executing - * an SRCU read-side critical section that continues beyond the start of - * "func()" must have executed a memory barrier after the call_rcu() - * but before the beginning of that SRCU read-side critical section. - * Note that these guarantees include CPUs that are offline, idle, or - * executing in user mode, as well as CPUs that are executing in the kernel. - * - * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the - * resulting SRCU callback function "func()", then both CPU A and CPU - * B are guaranteed to execute a full memory barrier during the time - * interval between the call to call_rcu() and the invocation of "func()". - * This guarantee applies even if CPU A and CPU B are the same CPU (but - * again only if the system has more than one CPU). - * - * Of course, these guarantees apply only for invocations of call_srcu(), - * srcu_read_lock(), and srcu_read_unlock() that are all passed the same - * srcu_struct structure. - */ -void call_srcu(struct srcu_struct *sp, struct rcu_head *head, - rcu_callback_t func) -{ - unsigned long flags; - - head->next = NULL; - head->func = func; - spin_lock_irqsave(&sp->queue_lock, flags); - smp_mb__after_unlock_lock(); /* Caller's prior accesses before GP. */ - rcu_batch_queue(&sp->batch_queue, head); - if (!sp->running) { - sp->running = true; - queue_delayed_work(system_power_efficient_wq, &sp->work, 0); - } - spin_unlock_irqrestore(&sp->queue_lock, flags); -} -EXPORT_SYMBOL_GPL(call_srcu); - -static void srcu_advance_batches(struct srcu_struct *sp, int trycount); -static void srcu_reschedule(struct srcu_struct *sp); - -/* - * Helper function for synchronize_srcu() and synchronize_srcu_expedited(). - */ -static void __synchronize_srcu(struct srcu_struct *sp, int trycount) -{ - struct rcu_synchronize rcu; - struct rcu_head *head = &rcu.head; - bool done = false; - - RCU_LOCKDEP_WARN(lock_is_held(&sp->dep_map) || - lock_is_held(&rcu_bh_lock_map) || - lock_is_held(&rcu_lock_map) || - lock_is_held(&rcu_sched_lock_map), - "Illegal synchronize_srcu() in same-type SRCU (or in RCU) read-side critical section"); - - might_sleep(); - init_completion(&rcu.completion); - - head->next = NULL; - head->func = wakeme_after_rcu; - spin_lock_irq(&sp->queue_lock); - smp_mb__after_unlock_lock(); /* Caller's prior accesses before GP. */ - if (!sp->running) { - /* steal the processing owner */ - sp->running = true; - rcu_batch_queue(&sp->batch_check0, head); - spin_unlock_irq(&sp->queue_lock); - - srcu_advance_batches(sp, trycount); - if (!rcu_batch_empty(&sp->batch_done)) { - BUG_ON(sp->batch_done.head != head); - rcu_batch_dequeue(&sp->batch_done); - done = true; - } - /* give the processing owner to work_struct */ - srcu_reschedule(sp); - } else { - rcu_batch_queue(&sp->batch_queue, head); - spin_unlock_irq(&sp->queue_lock); - } - - if (!done) { - wait_for_completion(&rcu.completion); - smp_mb(); /* Caller's later accesses after GP. */ - } - -} - -/** - * synchronize_srcu - wait for prior SRCU read-side critical-section completion - * @sp: srcu_struct with which to synchronize. - * - * Wait for the count to drain to zero of both indexes. To avoid the - * possible starvation of synchronize_srcu(), it waits for the count of - * the index=((->completed & 1) ^ 1) to drain to zero at first, - * and then flip the completed and wait for the count of the other index. - * - * 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, - * as long as the resulting graph of srcu_structs is acyclic. - * - * There are memory-ordering constraints implied by synchronize_srcu(). - * On systems with more than one CPU, when synchronize_srcu() returns, - * each CPU is guaranteed to have executed a full memory barrier since - * the end of its last corresponding SRCU-sched read-side critical section - * whose beginning preceded the call to synchronize_srcu(). In addition, - * each CPU having an SRCU read-side critical section that extends beyond - * the return from synchronize_srcu() is guaranteed to have executed a - * full memory barrier after the beginning of synchronize_srcu() and before - * the beginning of that SRCU read-side critical section. Note that these - * guarantees include CPUs that are offline, idle, or executing in user mode, - * as well as CPUs that are executing in the kernel. - * - * Furthermore, if CPU A invoked synchronize_srcu(), which returned - * to its caller on CPU B, then both CPU A and CPU B are guaranteed - * to have executed a full memory barrier during the execution of - * synchronize_srcu(). This guarantee applies even if CPU A and CPU B - * are the same CPU, but again only if the system has more than one CPU. - * - * Of course, these memory-ordering guarantees apply only when - * synchronize_srcu(), srcu_read_lock(), and srcu_read_unlock() are - * passed the same srcu_struct structure. - */ -void synchronize_srcu(struct srcu_struct *sp) -{ - __synchronize_srcu(sp, (rcu_gp_is_expedited() && !rcu_gp_is_normal()) - ? SYNCHRONIZE_SRCU_EXP_TRYCOUNT - : SYNCHRONIZE_SRCU_TRYCOUNT); -} -EXPORT_SYMBOL_GPL(synchronize_srcu); - -/** - * synchronize_srcu_expedited - Brute-force SRCU grace period - * @sp: srcu_struct with which to synchronize. - * - * Wait for an SRCU grace period to elapse, but be more aggressive about - * spinning rather than blocking when waiting. - * - * Note that synchronize_srcu_expedited() has the same deadlock and - * memory-ordering properties as does synchronize_srcu(). - */ -void synchronize_srcu_expedited(struct srcu_struct *sp) -{ - __synchronize_srcu(sp, SYNCHRONIZE_SRCU_EXP_TRYCOUNT); -} -EXPORT_SYMBOL_GPL(synchronize_srcu_expedited); - -/** - * srcu_barrier - Wait until all in-flight call_srcu() callbacks complete. - * @sp: srcu_struct on which to wait for in-flight callbacks. - */ -void srcu_barrier(struct srcu_struct *sp) -{ - synchronize_srcu(sp); -} -EXPORT_SYMBOL_GPL(srcu_barrier); - -/** - * srcu_batches_completed - return batches completed. - * @sp: srcu_struct on which to report batch completion. - * - * Report the number of batches, correlated with, but not necessarily - * precisely the same as, the number of grace periods that have elapsed. - */ -unsigned long srcu_batches_completed(struct srcu_struct *sp) -{ - return sp->completed; -} -EXPORT_SYMBOL_GPL(srcu_batches_completed); - -#define SRCU_CALLBACK_BATCH 10 -#define SRCU_INTERVAL 1 - -/* - * Move any new SRCU callbacks to the first stage of the SRCU grace - * period pipeline. - */ -static void srcu_collect_new(struct srcu_struct *sp) -{ - if (!rcu_batch_empty(&sp->batch_queue)) { - spin_lock_irq(&sp->queue_lock); - rcu_batch_move(&sp->batch_check0, &sp->batch_queue); - spin_unlock_irq(&sp->queue_lock); - } -} - -/* - * Core SRCU state machine. Advance callbacks from ->batch_check0 to - * ->batch_check1 and then to ->batch_done as readers drain. - */ -static void srcu_advance_batches(struct srcu_struct *sp, int trycount) -{ - int idx = 1 ^ (sp->completed & 1); - - /* - * Because readers might be delayed for an extended period after - * fetching ->completed for their index, at any point in time there - * might well be readers using both idx=0 and idx=1. We therefore - * need to wait for readers to clear from both index values before - * invoking a callback. - */ - - if (rcu_batch_empty(&sp->batch_check0) && - rcu_batch_empty(&sp->batch_check1)) - return; /* no callbacks need to be advanced */ - - if (!try_check_zero(sp, idx, trycount)) - return; /* failed to advance, will try after SRCU_INTERVAL */ - - /* - * The callbacks in ->batch_check1 have already done with their - * first zero check and flip back when they were enqueued on - * ->batch_check0 in a previous invocation of srcu_advance_batches(). - * (Presumably try_check_zero() returned false during that - * invocation, leaving the callbacks stranded on ->batch_check1.) - * They are therefore ready to invoke, so move them to ->batch_done. - */ - rcu_batch_move(&sp->batch_done, &sp->batch_check1); - - if (rcu_batch_empty(&sp->batch_check0)) - return; /* no callbacks need to be advanced */ - srcu_flip(sp); - - /* - * The callbacks in ->batch_check0 just finished their - * first check zero and flip, so move them to ->batch_check1 - * for future checking on the other idx. - */ - rcu_batch_move(&sp->batch_check1, &sp->batch_check0); - - /* - * SRCU read-side critical sections are normally short, so check - * at least twice in quick succession after a flip. - */ - trycount = trycount < 2 ? 2 : trycount; - if (!try_check_zero(sp, idx^1, trycount)) - return; /* failed to advance, will try after SRCU_INTERVAL */ - - /* - * The callbacks in ->batch_check1 have now waited for all - * pre-existing readers using both idx values. They are therefore - * ready to invoke, so move them to ->batch_done. - */ - rcu_batch_move(&sp->batch_done, &sp->batch_check1); -} - -/* - * Invoke a limited number of SRCU callbacks that have passed through - * their grace period. If there are more to do, SRCU will reschedule - * the workqueue. Note that needed memory barriers have been executed - * in this task's context by srcu_readers_active_idx_check(). - */ -static void srcu_invoke_callbacks(struct srcu_struct *sp) -{ - int i; - struct rcu_head *head; - - for (i = 0; i < SRCU_CALLBACK_BATCH; i++) { - head = rcu_batch_dequeue(&sp->batch_done); - if (!head) - break; - local_bh_disable(); - head->func(head); - local_bh_enable(); - } -} - -/* - * Finished one round of SRCU grace period. Start another if there are - * more SRCU callbacks queued, otherwise put SRCU into not-running state. - */ -static void srcu_reschedule(struct srcu_struct *sp) -{ - bool pending = true; - - if (rcu_batch_empty(&sp->batch_done) && - rcu_batch_empty(&sp->batch_check1) && - rcu_batch_empty(&sp->batch_check0) && - rcu_batch_empty(&sp->batch_queue)) { - spin_lock_irq(&sp->queue_lock); - if (rcu_batch_empty(&sp->batch_done) && - rcu_batch_empty(&sp->batch_check1) && - rcu_batch_empty(&sp->batch_check0) && - rcu_batch_empty(&sp->batch_queue)) { - sp->running = false; - pending = false; - } - spin_unlock_irq(&sp->queue_lock); - } - - if (pending) - queue_delayed_work(system_power_efficient_wq, - &sp->work, SRCU_INTERVAL); -} - -/* - * This is the work-queue function that handles SRCU grace periods. - */ -void process_srcu(struct work_struct *work) -{ - struct srcu_struct *sp; - - sp = container_of(work, struct srcu_struct, work.work); - - srcu_collect_new(sp); - srcu_advance_batches(sp, 1); - srcu_invoke_callbacks(sp); - srcu_reschedule(sp); -} -EXPORT_SYMBOL_GPL(process_srcu); diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c index 32798eb14853..1a1c1047d2ed 100644 --- a/kernel/rcu/srcutiny.c +++ b/kernel/rcu/srcutiny.c @@ -38,8 +38,8 @@ static int init_srcu_struct_fields(struct srcu_struct *sp) sp->srcu_lock_nesting[0] = 0; sp->srcu_lock_nesting[1] = 0; init_swait_queue_head(&sp->srcu_wq); - sp->srcu_gp_seq = 0; - rcu_segcblist_init(&sp->srcu_cblist); + sp->srcu_cb_head = NULL; + sp->srcu_cb_tail = &sp->srcu_cb_head; sp->srcu_gp_running = false; sp->srcu_gp_waiting = false; sp->srcu_idx = 0; @@ -88,30 +88,14 @@ void cleanup_srcu_struct(struct srcu_struct *sp) { WARN_ON(sp->srcu_lock_nesting[0] || sp->srcu_lock_nesting[1]); flush_work(&sp->srcu_work); - WARN_ON(rcu_seq_state(sp->srcu_gp_seq)); WARN_ON(sp->srcu_gp_running); WARN_ON(sp->srcu_gp_waiting); - WARN_ON(!rcu_segcblist_empty(&sp->srcu_cblist)); + WARN_ON(sp->srcu_cb_head); + WARN_ON(&sp->srcu_cb_head != sp->srcu_cb_tail); } EXPORT_SYMBOL_GPL(cleanup_srcu_struct); /* - * Counts the new reader in the appropriate per-CPU element of the - * srcu_struct. Can be invoked from irq/bh handlers, but the matching - * __srcu_read_unlock() must be in the same handler instance. Returns an - * index that must be passed to the matching srcu_read_unlock(). - */ -int __srcu_read_lock(struct srcu_struct *sp) -{ - int idx; - - idx = READ_ONCE(sp->srcu_idx); - WRITE_ONCE(sp->srcu_lock_nesting[idx], sp->srcu_lock_nesting[idx] + 1); - return idx; -} -EXPORT_SYMBOL_GPL(__srcu_read_lock); - -/* * Removes the count for the old reader from the appropriate element of * the srcu_struct. */ @@ -133,52 +117,44 @@ EXPORT_SYMBOL_GPL(__srcu_read_unlock); void srcu_drive_gp(struct work_struct *wp) { int idx; - struct rcu_cblist ready_cbs; - struct srcu_struct *sp; + struct rcu_head *lh; struct rcu_head *rhp; + struct srcu_struct *sp; sp = container_of(wp, struct srcu_struct, srcu_work); - if (sp->srcu_gp_running || rcu_segcblist_empty(&sp->srcu_cblist)) + if (sp->srcu_gp_running || !READ_ONCE(sp->srcu_cb_head)) return; /* Already running or nothing to do. */ - /* Tag recently arrived callbacks and wait for readers. */ + /* Remove recently arrived callbacks and wait for readers. */ WRITE_ONCE(sp->srcu_gp_running, true); - rcu_segcblist_accelerate(&sp->srcu_cblist, - rcu_seq_snap(&sp->srcu_gp_seq)); - rcu_seq_start(&sp->srcu_gp_seq); + local_irq_disable(); + lh = sp->srcu_cb_head; + sp->srcu_cb_head = NULL; + sp->srcu_cb_tail = &sp->srcu_cb_head; + local_irq_enable(); idx = sp->srcu_idx; WRITE_ONCE(sp->srcu_idx, !sp->srcu_idx); WRITE_ONCE(sp->srcu_gp_waiting, true); /* srcu_read_unlock() wakes! */ swait_event(sp->srcu_wq, !READ_ONCE(sp->srcu_lock_nesting[idx])); WRITE_ONCE(sp->srcu_gp_waiting, false); /* srcu_read_unlock() cheap. */ - rcu_seq_end(&sp->srcu_gp_seq); - - /* Update callback list based on GP, and invoke ready callbacks. */ - rcu_segcblist_advance(&sp->srcu_cblist, - rcu_seq_current(&sp->srcu_gp_seq)); - if (rcu_segcblist_ready_cbs(&sp->srcu_cblist)) { - rcu_cblist_init(&ready_cbs); - local_irq_disable(); - rcu_segcblist_extract_done_cbs(&sp->srcu_cblist, &ready_cbs); - local_irq_enable(); - rhp = rcu_cblist_dequeue(&ready_cbs); - for (; rhp != NULL; rhp = rcu_cblist_dequeue(&ready_cbs)) { - local_bh_disable(); - rhp->func(rhp); - local_bh_enable(); - } - local_irq_disable(); - rcu_segcblist_insert_count(&sp->srcu_cblist, &ready_cbs); - local_irq_enable(); + + /* Invoke the callbacks we removed above. */ + while (lh) { + rhp = lh; + lh = lh->next; + local_bh_disable(); + rhp->func(rhp); + local_bh_enable(); } - WRITE_ONCE(sp->srcu_gp_running, false); /* - * If more callbacks, reschedule ourselves. This can race with - * a call_srcu() at interrupt level, but the ->srcu_gp_running - * checks will straighten that out. + * Enable rescheduling, and if there are more callbacks, + * reschedule ourselves. This can race with a call_srcu() + * at interrupt level, but the ->srcu_gp_running checks will + * straighten that out. */ - if (!rcu_segcblist_empty(&sp->srcu_cblist)) + WRITE_ONCE(sp->srcu_gp_running, false); + if (READ_ONCE(sp->srcu_cb_head)) schedule_work(&sp->srcu_work); } EXPORT_SYMBOL_GPL(srcu_drive_gp); @@ -187,14 +163,16 @@ EXPORT_SYMBOL_GPL(srcu_drive_gp); * Enqueue an SRCU callback on the specified srcu_struct structure, * initiating grace-period processing if it is not already running. */ -void call_srcu(struct srcu_struct *sp, struct rcu_head *head, +void call_srcu(struct srcu_struct *sp, struct rcu_head *rhp, rcu_callback_t func) { unsigned long flags; - head->func = func; + rhp->func = func; + rhp->next = NULL; local_irq_save(flags); - rcu_segcblist_enqueue(&sp->srcu_cblist, head, false); + *sp->srcu_cb_tail = rhp; + sp->srcu_cb_tail = &rhp->next; local_irq_restore(flags); if (!READ_ONCE(sp->srcu_gp_running)) schedule_work(&sp->srcu_work); diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index 157654fa436a..d0ca524bf042 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -40,9 +40,15 @@ #include "rcu.h" #include "rcu_segcblist.h" -ulong exp_holdoff = 25 * 1000; /* Holdoff (ns) for auto-expediting. */ +/* Holdoff in nanoseconds for auto-expediting. */ +#define DEFAULT_SRCU_EXP_HOLDOFF (25 * 1000) +static ulong exp_holdoff = DEFAULT_SRCU_EXP_HOLDOFF; module_param(exp_holdoff, ulong, 0444); +/* Overflow-check frequency. N bits roughly says every 2**N grace periods. */ +static ulong counter_wrap_check = (ULONG_MAX >> 2); +module_param(counter_wrap_check, ulong, 0444); + static void srcu_invoke_callbacks(struct work_struct *work); static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay); @@ -70,7 +76,7 @@ static void init_srcu_struct_nodes(struct srcu_struct *sp, bool is_static) /* Each pass through this loop initializes one srcu_node structure. */ rcu_for_each_node_breadth_first(sp, snp) { - spin_lock_init(&snp->lock); + raw_spin_lock_init(&ACCESS_PRIVATE(snp, lock)); WARN_ON_ONCE(ARRAY_SIZE(snp->srcu_have_cbs) != ARRAY_SIZE(snp->srcu_data_have_cbs)); for (i = 0; i < ARRAY_SIZE(snp->srcu_have_cbs); i++) { @@ -104,7 +110,7 @@ static void init_srcu_struct_nodes(struct srcu_struct *sp, bool is_static) snp_first = sp->level[level]; for_each_possible_cpu(cpu) { sdp = per_cpu_ptr(sp->sda, cpu); - spin_lock_init(&sdp->lock); + raw_spin_lock_init(&ACCESS_PRIVATE(sdp, lock)); rcu_segcblist_init(&sdp->srcu_cblist); sdp->srcu_cblist_invoking = false; sdp->srcu_gp_seq_needed = sp->srcu_gp_seq; @@ -163,7 +169,7 @@ int __init_srcu_struct(struct srcu_struct *sp, const char *name, /* Don't re-initialize a lock while it is held. */ debug_check_no_locks_freed((void *)sp, sizeof(*sp)); lockdep_init_map(&sp->dep_map, name, key, 0); - spin_lock_init(&sp->gp_lock); + raw_spin_lock_init(&ACCESS_PRIVATE(sp, lock)); return init_srcu_struct_fields(sp, false); } EXPORT_SYMBOL_GPL(__init_srcu_struct); @@ -180,7 +186,7 @@ EXPORT_SYMBOL_GPL(__init_srcu_struct); */ int init_srcu_struct(struct srcu_struct *sp) { - spin_lock_init(&sp->gp_lock); + raw_spin_lock_init(&ACCESS_PRIVATE(sp, lock)); return init_srcu_struct_fields(sp, false); } EXPORT_SYMBOL_GPL(init_srcu_struct); @@ -191,7 +197,7 @@ EXPORT_SYMBOL_GPL(init_srcu_struct); * First-use initialization of statically allocated srcu_struct * structure. Wiring up the combining tree is more than can be * done with compile-time initialization, so this check is added - * to each update-side SRCU primitive. Use ->gp_lock, which -is- + * to each update-side SRCU primitive. Use sp->lock, which -is- * compile-time initialized, to resolve races involving multiple * CPUs trying to garner first-use privileges. */ @@ -203,13 +209,13 @@ static void check_init_srcu_struct(struct srcu_struct *sp) /* The smp_load_acquire() pairs with the smp_store_release(). */ if (!rcu_seq_state(smp_load_acquire(&sp->srcu_gp_seq_needed))) /*^^^*/ return; /* Already initialized. */ - spin_lock_irqsave(&sp->gp_lock, flags); + raw_spin_lock_irqsave_rcu_node(sp, flags); if (!rcu_seq_state(sp->srcu_gp_seq_needed)) { - spin_unlock_irqrestore(&sp->gp_lock, flags); + raw_spin_unlock_irqrestore_rcu_node(sp, flags); return; } init_srcu_struct_fields(sp, true); - spin_unlock_irqrestore(&sp->gp_lock, flags); + raw_spin_unlock_irqrestore_rcu_node(sp, flags); } /* @@ -275,15 +281,20 @@ static bool srcu_readers_active_idx_check(struct srcu_struct *sp, int idx) * not mean that there are no more readers, as one could have read * the current index but not have incremented the lock counter yet. * - * Possible bug: There is no guarantee that there haven't been - * ULONG_MAX increments of ->srcu_lock_count[] since the unlocks were - * counted, meaning that this could return true even if there are - * still active readers. Since there are no memory barriers around - * srcu_flip(), the CPU is not required to increment ->srcu_idx - * before running srcu_readers_unlock_idx(), which means that there - * could be an arbitrarily large number of critical sections that - * execute after srcu_readers_unlock_idx() but use the old value - * of ->srcu_idx. + * So suppose that the updater is preempted here for so long + * that more than ULONG_MAX non-nested readers come and go in + * the meantime. It turns out that this cannot result in overflow + * because if a reader modifies its unlock count after we read it + * above, then that reader's next load of ->srcu_idx is guaranteed + * to get the new value, which will cause it to operate on the + * other bank of counters, where it cannot contribute to the + * overflow of these counters. This means that there is a maximum + * of 2*NR_CPUS increments, which cannot overflow given current + * systems, especially not on 64-bit systems. + * + * OK, how about nesting? This does impose a limit on nesting + * of floor(ULONG_MAX/NR_CPUS/2), which should be sufficient, + * especially on 64-bit systems. */ return srcu_readers_lock_idx(sp, idx) == unlocks; } @@ -400,8 +411,7 @@ static void srcu_gp_start(struct srcu_struct *sp) struct srcu_data *sdp = this_cpu_ptr(sp->sda); int state; - RCU_LOCKDEP_WARN(!lockdep_is_held(&sp->gp_lock), - "Invoked srcu_gp_start() without ->gp_lock!"); + lockdep_assert_held(&sp->lock); WARN_ON_ONCE(ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed)); rcu_segcblist_advance(&sdp->srcu_cblist, rcu_seq_current(&sp->srcu_gp_seq)); @@ -489,17 +499,20 @@ static void srcu_gp_end(struct srcu_struct *sp) { unsigned long cbdelay; bool cbs; + int cpu; + unsigned long flags; unsigned long gpseq; int idx; int idxnext; unsigned long mask; + struct srcu_data *sdp; struct srcu_node *snp; /* Prevent more than one additional grace period. */ mutex_lock(&sp->srcu_cb_mutex); /* End the current grace period. */ - spin_lock_irq(&sp->gp_lock); + raw_spin_lock_irq_rcu_node(sp); idx = rcu_seq_state(sp->srcu_gp_seq); WARN_ON_ONCE(idx != SRCU_STATE_SCAN2); cbdelay = srcu_get_delay(sp); @@ -508,7 +521,7 @@ static void srcu_gp_end(struct srcu_struct *sp) gpseq = rcu_seq_current(&sp->srcu_gp_seq); if (ULONG_CMP_LT(sp->srcu_gp_seq_needed_exp, gpseq)) sp->srcu_gp_seq_needed_exp = gpseq; - spin_unlock_irq(&sp->gp_lock); + raw_spin_unlock_irq_rcu_node(sp); mutex_unlock(&sp->srcu_gp_mutex); /* A new grace period can start at this point. But only one. */ @@ -516,7 +529,7 @@ static void srcu_gp_end(struct srcu_struct *sp) idx = rcu_seq_ctr(gpseq) % ARRAY_SIZE(snp->srcu_have_cbs); idxnext = (idx + 1) % ARRAY_SIZE(snp->srcu_have_cbs); rcu_for_each_node_breadth_first(sp, snp) { - spin_lock_irq(&snp->lock); + raw_spin_lock_irq_rcu_node(snp); cbs = false; if (snp >= sp->level[rcu_num_lvls - 1]) cbs = snp->srcu_have_cbs[idx] == gpseq; @@ -526,28 +539,37 @@ static void srcu_gp_end(struct srcu_struct *sp) snp->srcu_gp_seq_needed_exp = gpseq; mask = snp->srcu_data_have_cbs[idx]; snp->srcu_data_have_cbs[idx] = 0; - spin_unlock_irq(&snp->lock); - if (cbs) { - smp_mb(); /* GP end before CB invocation. */ + raw_spin_unlock_irq_rcu_node(snp); + if (cbs) srcu_schedule_cbs_snp(sp, snp, mask, cbdelay); - } + + /* Occasionally prevent srcu_data counter wrap. */ + if (!(gpseq & counter_wrap_check)) + for (cpu = snp->grplo; cpu <= snp->grphi; cpu++) { + sdp = per_cpu_ptr(sp->sda, cpu); + raw_spin_lock_irqsave_rcu_node(sdp, flags); + if (ULONG_CMP_GE(gpseq, + sdp->srcu_gp_seq_needed + 100)) + sdp->srcu_gp_seq_needed = gpseq; + raw_spin_unlock_irqrestore_rcu_node(sdp, flags); + } } /* Callback initiation done, allow grace periods after next. */ mutex_unlock(&sp->srcu_cb_mutex); /* Start a new grace period if needed. */ - spin_lock_irq(&sp->gp_lock); + raw_spin_lock_irq_rcu_node(sp); gpseq = rcu_seq_current(&sp->srcu_gp_seq); if (!rcu_seq_state(gpseq) && ULONG_CMP_LT(gpseq, sp->srcu_gp_seq_needed)) { srcu_gp_start(sp); - spin_unlock_irq(&sp->gp_lock); + raw_spin_unlock_irq_rcu_node(sp); /* Throttle expedited grace periods: Should be rare! */ srcu_reschedule(sp, rcu_seq_ctr(gpseq) & 0x3ff ? 0 : SRCU_INTERVAL); } else { - spin_unlock_irq(&sp->gp_lock); + raw_spin_unlock_irq_rcu_node(sp); } } @@ -567,18 +589,18 @@ static void srcu_funnel_exp_start(struct srcu_struct *sp, struct srcu_node *snp, if (rcu_seq_done(&sp->srcu_gp_seq, s) || ULONG_CMP_GE(READ_ONCE(snp->srcu_gp_seq_needed_exp), s)) return; - spin_lock_irqsave(&snp->lock, flags); + raw_spin_lock_irqsave_rcu_node(snp, flags); if (ULONG_CMP_GE(snp->srcu_gp_seq_needed_exp, s)) { - spin_unlock_irqrestore(&snp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(snp, flags); return; } WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s); - spin_unlock_irqrestore(&snp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(snp, flags); } - spin_lock_irqsave(&sp->gp_lock, flags); + raw_spin_lock_irqsave_rcu_node(sp, flags); if (!ULONG_CMP_LT(sp->srcu_gp_seq_needed_exp, s)) sp->srcu_gp_seq_needed_exp = s; - spin_unlock_irqrestore(&sp->gp_lock, flags); + raw_spin_unlock_irqrestore_rcu_node(sp, flags); } /* @@ -600,14 +622,13 @@ static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp, for (; snp != NULL; snp = snp->srcu_parent) { if (rcu_seq_done(&sp->srcu_gp_seq, s) && snp != sdp->mynode) return; /* GP already done and CBs recorded. */ - spin_lock_irqsave(&snp->lock, flags); + raw_spin_lock_irqsave_rcu_node(snp, flags); if (ULONG_CMP_GE(snp->srcu_have_cbs[idx], s)) { snp_seq = snp->srcu_have_cbs[idx]; if (snp == sdp->mynode && snp_seq == s) snp->srcu_data_have_cbs[idx] |= sdp->grpmask; - spin_unlock_irqrestore(&snp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(snp, flags); if (snp == sdp->mynode && snp_seq != s) { - smp_mb(); /* CBs after GP! */ srcu_schedule_cbs_sdp(sdp, do_norm ? SRCU_INTERVAL : 0); @@ -622,11 +643,11 @@ static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp, snp->srcu_data_have_cbs[idx] |= sdp->grpmask; if (!do_norm && ULONG_CMP_LT(snp->srcu_gp_seq_needed_exp, s)) snp->srcu_gp_seq_needed_exp = s; - spin_unlock_irqrestore(&snp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(snp, flags); } /* Top of tree, must ensure the grace period will be started. */ - spin_lock_irqsave(&sp->gp_lock, flags); + raw_spin_lock_irqsave_rcu_node(sp, flags); if (ULONG_CMP_LT(sp->srcu_gp_seq_needed, s)) { /* * Record need for grace period s. Pair with load @@ -645,7 +666,7 @@ static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp, queue_delayed_work(system_power_efficient_wq, &sp->work, srcu_get_delay(sp)); } - spin_unlock_irqrestore(&sp->gp_lock, flags); + raw_spin_unlock_irqrestore_rcu_node(sp, flags); } /* @@ -671,6 +692,16 @@ static bool try_check_zero(struct srcu_struct *sp, int idx, int trycount) */ static void srcu_flip(struct srcu_struct *sp) { + /* + * Ensure that if this updater saw a given reader's increment + * from __srcu_read_lock(), that reader was using an old value + * of ->srcu_idx. Also ensure that if a given reader sees the + * new value of ->srcu_idx, this updater's earlier scans cannot + * have seen that reader's increments (which is OK, because this + * grace period need not wait on that reader). + */ + smp_mb(); /* E */ /* Pairs with B and C. */ + WRITE_ONCE(sp->srcu_idx, sp->srcu_idx + 1); /* @@ -745,6 +776,13 @@ static bool srcu_might_be_idle(struct srcu_struct *sp) } /* + * SRCU callback function to leak a callback. + */ +static void srcu_leak_callback(struct rcu_head *rhp) +{ +} + +/* * Enqueue an SRCU callback on the srcu_data structure associated with * the current CPU and the specified srcu_struct structure, initiating * grace-period processing if it is not already running. @@ -782,10 +820,16 @@ void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp, struct srcu_data *sdp; check_init_srcu_struct(sp); + if (debug_rcu_head_queue(rhp)) { + /* Probable double call_srcu(), so leak the callback. */ + WRITE_ONCE(rhp->func, srcu_leak_callback); + WARN_ONCE(1, "call_srcu(): Leaked duplicate callback\n"); + return; + } rhp->func = func; local_irq_save(flags); sdp = this_cpu_ptr(sp->sda); - spin_lock(&sdp->lock); + raw_spin_lock_rcu_node(sdp); rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp, false); rcu_segcblist_advance(&sdp->srcu_cblist, rcu_seq_current(&sp->srcu_gp_seq)); @@ -799,13 +843,30 @@ void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp, sdp->srcu_gp_seq_needed_exp = s; needexp = true; } - spin_unlock_irqrestore(&sdp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(sdp, flags); if (needgp) srcu_funnel_gp_start(sp, sdp, s, do_norm); else if (needexp) srcu_funnel_exp_start(sp, sdp->mynode, s); } +/** + * call_srcu() - Queue a callback for invocation after an SRCU grace period + * @sp: srcu_struct in queue the callback + * @head: structure to be used for queueing the SRCU callback. + * @func: function to be invoked after the SRCU grace period + * + * The callback function will be invoked some time after a full SRCU + * grace period elapses, in other words after all pre-existing SRCU + * read-side critical sections have completed. However, the callback + * function might well execute concurrently with other SRCU read-side + * critical sections that started after call_srcu() was invoked. SRCU + * read-side critical sections are delimited by srcu_read_lock() and + * srcu_read_unlock(), and may be nested. + * + * The callback will be invoked from process context, but must nevertheless + * be fast and must not block. + */ void call_srcu(struct srcu_struct *sp, struct rcu_head *rhp, rcu_callback_t func) { @@ -953,13 +1014,16 @@ void srcu_barrier(struct srcu_struct *sp) */ for_each_possible_cpu(cpu) { sdp = per_cpu_ptr(sp->sda, cpu); - spin_lock_irq(&sdp->lock); + raw_spin_lock_irq_rcu_node(sdp); atomic_inc(&sp->srcu_barrier_cpu_cnt); sdp->srcu_barrier_head.func = srcu_barrier_cb; + debug_rcu_head_queue(&sdp->srcu_barrier_head); if (!rcu_segcblist_entrain(&sdp->srcu_cblist, - &sdp->srcu_barrier_head, 0)) + &sdp->srcu_barrier_head, 0)) { + debug_rcu_head_unqueue(&sdp->srcu_barrier_head); atomic_dec(&sp->srcu_barrier_cpu_cnt); - spin_unlock_irq(&sdp->lock); + } + raw_spin_unlock_irq_rcu_node(sdp); } /* Remove the initial count, at which point reaching zero can happen. */ @@ -1008,17 +1072,17 @@ static void srcu_advance_state(struct srcu_struct *sp) */ idx = rcu_seq_state(smp_load_acquire(&sp->srcu_gp_seq)); /* ^^^ */ if (idx == SRCU_STATE_IDLE) { - spin_lock_irq(&sp->gp_lock); + raw_spin_lock_irq_rcu_node(sp); if (ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed)) { WARN_ON_ONCE(rcu_seq_state(sp->srcu_gp_seq)); - spin_unlock_irq(&sp->gp_lock); + raw_spin_unlock_irq_rcu_node(sp); mutex_unlock(&sp->srcu_gp_mutex); return; } idx = rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)); if (idx == SRCU_STATE_IDLE) srcu_gp_start(sp); - spin_unlock_irq(&sp->gp_lock); + raw_spin_unlock_irq_rcu_node(sp); if (idx != SRCU_STATE_IDLE) { mutex_unlock(&sp->srcu_gp_mutex); return; /* Someone else started the grace period. */ @@ -1067,22 +1131,22 @@ static void srcu_invoke_callbacks(struct work_struct *work) sdp = container_of(work, struct srcu_data, work.work); sp = sdp->sp; rcu_cblist_init(&ready_cbs); - spin_lock_irq(&sdp->lock); - smp_mb(); /* Old grace periods before callback invocation! */ + raw_spin_lock_irq_rcu_node(sdp); rcu_segcblist_advance(&sdp->srcu_cblist, rcu_seq_current(&sp->srcu_gp_seq)); if (sdp->srcu_cblist_invoking || !rcu_segcblist_ready_cbs(&sdp->srcu_cblist)) { - spin_unlock_irq(&sdp->lock); + raw_spin_unlock_irq_rcu_node(sdp); return; /* Someone else on the job or nothing to do. */ } /* We are on the job! Extract and invoke ready callbacks. */ sdp->srcu_cblist_invoking = true; rcu_segcblist_extract_done_cbs(&sdp->srcu_cblist, &ready_cbs); - spin_unlock_irq(&sdp->lock); + raw_spin_unlock_irq_rcu_node(sdp); rhp = rcu_cblist_dequeue(&ready_cbs); for (; rhp != NULL; rhp = rcu_cblist_dequeue(&ready_cbs)) { + debug_rcu_head_unqueue(rhp); local_bh_disable(); rhp->func(rhp); local_bh_enable(); @@ -1092,13 +1156,13 @@ static void srcu_invoke_callbacks(struct work_struct *work) * Update counts, accelerate new callbacks, and if needed, * schedule another round of callback invocation. */ - spin_lock_irq(&sdp->lock); + raw_spin_lock_irq_rcu_node(sdp); rcu_segcblist_insert_count(&sdp->srcu_cblist, &ready_cbs); (void)rcu_segcblist_accelerate(&sdp->srcu_cblist, rcu_seq_snap(&sp->srcu_gp_seq)); sdp->srcu_cblist_invoking = false; more = rcu_segcblist_ready_cbs(&sdp->srcu_cblist); - spin_unlock_irq(&sdp->lock); + raw_spin_unlock_irq_rcu_node(sdp); if (more) srcu_schedule_cbs_sdp(sdp, 0); } @@ -1111,7 +1175,7 @@ static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay) { bool pushgp = true; - spin_lock_irq(&sp->gp_lock); + raw_spin_lock_irq_rcu_node(sp); if (ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed)) { if (!WARN_ON_ONCE(rcu_seq_state(sp->srcu_gp_seq))) { /* All requests fulfilled, time to go idle. */ @@ -1121,7 +1185,7 @@ static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay) /* Outstanding request and no GP. Start one. */ srcu_gp_start(sp); } - spin_unlock_irq(&sp->gp_lock); + raw_spin_unlock_irq_rcu_node(sp); if (pushgp) queue_delayed_work(system_power_efficient_wq, &sp->work, delay); @@ -1152,3 +1216,12 @@ void srcutorture_get_gp_data(enum rcutorture_type test_type, *gpnum = rcu_seq_ctr(sp->srcu_gp_seq_needed); } EXPORT_SYMBOL_GPL(srcutorture_get_gp_data); + +static int __init srcu_bootup_announce(void) +{ + pr_info("Hierarchical SRCU implementation.\n"); + if (exp_holdoff != DEFAULT_SRCU_EXP_HOLDOFF) + pr_info("\tNon-default auto-expedite holdoff of %lu ns.\n", exp_holdoff); + return 0; +} +early_initcall(srcu_bootup_announce); diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index e5385731e391..f8488965250f 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -35,15 +35,26 @@ #include <linux/time.h> #include <linux/cpu.h> #include <linux/prefetch.h> -#include <linux/trace_events.h> #include "rcu.h" -/* Forward declarations for tiny_plugin.h. */ -struct rcu_ctrlblk; -static void __call_rcu(struct rcu_head *head, - rcu_callback_t func, - struct rcu_ctrlblk *rcp); +/* 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_sched_ctrlblk = { + .donetail = &rcu_sched_ctrlblk.rcucblist, + .curtail = &rcu_sched_ctrlblk.rcucblist, +}; + +static struct rcu_ctrlblk rcu_bh_ctrlblk = { + .donetail = &rcu_bh_ctrlblk.rcucblist, + .curtail = &rcu_bh_ctrlblk.rcucblist, +}; #include "tiny_plugin.h" @@ -59,19 +70,6 @@ void rcu_barrier_sched(void) } EXPORT_SYMBOL(rcu_barrier_sched); -#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) - -/* - * Test whether RCU thinks that the current CPU is idle. - */ -bool notrace __rcu_is_watching(void) -{ - return true; -} -EXPORT_SYMBOL(__rcu_is_watching); - -#endif /* defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */ - /* * Helper function for rcu_sched_qs() and rcu_bh_qs(). * Also irqs are disabled to avoid confusion due to interrupt handlers @@ -79,7 +77,6 @@ EXPORT_SYMBOL(__rcu_is_watching); */ static int rcu_qsctr_help(struct rcu_ctrlblk *rcp) { - RCU_TRACE(reset_cpu_stall_ticks(rcp);) if (rcp->donetail != rcp->curtail) { rcp->donetail = rcp->curtail; return 1; @@ -125,7 +122,6 @@ void rcu_bh_qs(void) */ void rcu_check_callbacks(int user) { - RCU_TRACE(check_cpu_stalls();) if (user) rcu_sched_qs(); else if (!in_softirq()) @@ -140,10 +136,8 @@ void rcu_check_callbacks(int user) */ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp) { - const char *rn = NULL; struct rcu_head *next, *list; unsigned long flags; - RCU_TRACE(int cb_count = 0;) /* Move the ready-to-invoke callbacks to a local list. */ local_irq_save(flags); @@ -152,7 +146,6 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp) local_irq_restore(flags); return; } - RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, rcp->qlen, -1);) list = rcp->rcucblist; rcp->rcucblist = *rcp->donetail; *rcp->donetail = NULL; @@ -162,22 +155,15 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp) local_irq_restore(flags); /* Invoke the callbacks on the local list. */ - RCU_TRACE(rn = rcp->name;) while (list) { next = list->next; prefetch(next); debug_rcu_head_unqueue(list); local_bh_disable(); - __rcu_reclaim(rn, list); + __rcu_reclaim("", list); local_bh_enable(); list = next; - RCU_TRACE(cb_count++;) } - RCU_TRACE(rcu_trace_sub_qlen(rcp, cb_count);) - RCU_TRACE(trace_rcu_batch_end(rcp->name, - cb_count, 0, need_resched(), - is_idle_task(current), - false)); } static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused) @@ -221,7 +207,6 @@ static void __call_rcu(struct rcu_head *head, local_irq_save(flags); *rcp->curtail = head; rcp->curtail = &head->next; - RCU_TRACE(rcp->qlen++;) local_irq_restore(flags); if (unlikely(is_idle_task(current))) { @@ -254,8 +239,5 @@ EXPORT_SYMBOL_GPL(call_rcu_bh); void __init rcu_init(void) { open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); - RCU_TRACE(reset_cpu_stall_ticks(&rcu_sched_ctrlblk);) - RCU_TRACE(reset_cpu_stall_ticks(&rcu_bh_ctrlblk);) - rcu_early_boot_tests(); } diff --git a/kernel/rcu/tiny_plugin.h b/kernel/rcu/tiny_plugin.h index 371034e77f87..f0a01b2a3062 100644 --- a/kernel/rcu/tiny_plugin.h +++ b/kernel/rcu/tiny_plugin.h @@ -22,36 +22,6 @@ * Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com> */ -#include <linux/kthread.h> -#include <linux/init.h> -#include <linux/debugfs.h> -#include <linux/seq_file.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. */ - RCU_TRACE(long qlen); /* Number of pending CBs. */ - RCU_TRACE(unsigned long gp_start); /* Start time for stalls. */ - RCU_TRACE(unsigned long ticks_this_gp); /* Statistic for stalls. */ - RCU_TRACE(unsigned long jiffies_stall); /* Jiffies at next stall. */ - RCU_TRACE(const char *name); /* Name of RCU type. */ -}; - -/* Definition for rcupdate control block. */ -static struct rcu_ctrlblk rcu_sched_ctrlblk = { - .donetail = &rcu_sched_ctrlblk.rcucblist, - .curtail = &rcu_sched_ctrlblk.rcucblist, - RCU_TRACE(.name = "rcu_sched") -}; - -static struct rcu_ctrlblk rcu_bh_ctrlblk = { - .donetail = &rcu_bh_ctrlblk.rcucblist, - .curtail = &rcu_bh_ctrlblk.rcucblist, - RCU_TRACE(.name = "rcu_bh") -}; - #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) #include <linux/kernel_stat.h> @@ -75,96 +45,3 @@ void __init rcu_scheduler_starting(void) } #endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) */ - -#ifdef CONFIG_RCU_TRACE - -static void rcu_trace_sub_qlen(struct rcu_ctrlblk *rcp, int n) -{ - unsigned long flags; - - local_irq_save(flags); - rcp->qlen -= n; - local_irq_restore(flags); -} - -/* - * Dump statistics for TINY_RCU, such as they are. - */ -static int show_tiny_stats(struct seq_file *m, void *unused) -{ - seq_printf(m, "rcu_sched: qlen: %ld\n", rcu_sched_ctrlblk.qlen); - seq_printf(m, "rcu_bh: qlen: %ld\n", rcu_bh_ctrlblk.qlen); - return 0; -} - -static int show_tiny_stats_open(struct inode *inode, struct file *file) -{ - return single_open(file, show_tiny_stats, NULL); -} - -static const struct file_operations show_tiny_stats_fops = { - .owner = THIS_MODULE, - .open = show_tiny_stats_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -static struct dentry *rcudir; - -static int __init rcutiny_trace_init(void) -{ - struct dentry *retval; - - rcudir = debugfs_create_dir("rcu", NULL); - if (!rcudir) - goto free_out; - retval = debugfs_create_file("rcudata", 0444, rcudir, - NULL, &show_tiny_stats_fops); - if (!retval) - goto free_out; - return 0; -free_out: - debugfs_remove_recursive(rcudir); - return 1; -} -device_initcall(rcutiny_trace_init); - -static void check_cpu_stall(struct rcu_ctrlblk *rcp) -{ - unsigned long j; - unsigned long js; - - if (rcu_cpu_stall_suppress) - return; - rcp->ticks_this_gp++; - j = jiffies; - js = READ_ONCE(rcp->jiffies_stall); - if (rcp->rcucblist && ULONG_CMP_GE(j, js)) { - pr_err("INFO: %s stall on CPU (%lu ticks this GP) idle=%llx (t=%lu jiffies q=%ld)\n", - rcp->name, rcp->ticks_this_gp, DYNTICK_TASK_EXIT_IDLE, - jiffies - rcp->gp_start, rcp->qlen); - dump_stack(); - WRITE_ONCE(rcp->jiffies_stall, - jiffies + 3 * rcu_jiffies_till_stall_check() + 3); - } else if (ULONG_CMP_GE(j, js)) { - WRITE_ONCE(rcp->jiffies_stall, - jiffies + rcu_jiffies_till_stall_check()); - } -} - -static void reset_cpu_stall_ticks(struct rcu_ctrlblk *rcp) -{ - rcp->ticks_this_gp = 0; - rcp->gp_start = jiffies; - WRITE_ONCE(rcp->jiffies_stall, - jiffies + rcu_jiffies_till_stall_check()); -} - -static void check_cpu_stalls(void) -{ - RCU_TRACE(check_cpu_stall(&rcu_bh_ctrlblk);) - RCU_TRACE(check_cpu_stall(&rcu_sched_ctrlblk);) -} - -#endif /* #ifdef CONFIG_RCU_TRACE */ diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index e354e475e645..51d4c3acf32d 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -168,35 +168,17 @@ static void rcu_report_exp_rdp(struct rcu_state *rsp, static void sync_sched_exp_online_cleanup(int cpu); /* rcuc/rcub kthread realtime priority */ -#ifdef CONFIG_RCU_KTHREAD_PRIO -static int kthread_prio = CONFIG_RCU_KTHREAD_PRIO; -#else /* #ifdef CONFIG_RCU_KTHREAD_PRIO */ static int kthread_prio = IS_ENABLED(CONFIG_RCU_BOOST) ? 1 : 0; -#endif /* #else #ifdef CONFIG_RCU_KTHREAD_PRIO */ module_param(kthread_prio, int, 0644); /* Delay in jiffies for grace-period initialization delays, debug only. */ -#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT -static int gp_preinit_delay = CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT_DELAY; -module_param(gp_preinit_delay, int, 0644); -#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT */ -static const int gp_preinit_delay; -#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT */ - -#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT -static int gp_init_delay = CONFIG_RCU_TORTURE_TEST_SLOW_INIT_DELAY; -module_param(gp_init_delay, int, 0644); -#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT */ -static const int gp_init_delay; -#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT */ - -#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP -static int gp_cleanup_delay = CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP_DELAY; -module_param(gp_cleanup_delay, int, 0644); -#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP */ -static const int gp_cleanup_delay; -#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP */ +static int gp_preinit_delay; +module_param(gp_preinit_delay, int, 0444); +static int gp_init_delay; +module_param(gp_init_delay, int, 0444); +static int gp_cleanup_delay; +module_param(gp_cleanup_delay, int, 0444); /* * Number of grace periods between delays, normalized by the duration of @@ -250,6 +232,7 @@ static int rcu_gp_in_progress(struct rcu_state *rsp) */ void rcu_sched_qs(void) { + RCU_LOCKDEP_WARN(preemptible(), "rcu_sched_qs() invoked with preemption enabled!!!"); if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.s)) return; trace_rcu_grace_period(TPS("rcu_sched"), @@ -265,6 +248,7 @@ void rcu_sched_qs(void) void rcu_bh_qs(void) { + RCU_LOCKDEP_WARN(preemptible(), "rcu_bh_qs() invoked with preemption enabled!!!"); if (__this_cpu_read(rcu_bh_data.cpu_no_qs.s)) { trace_rcu_grace_period(TPS("rcu_bh"), __this_cpu_read(rcu_bh_data.gpnum), @@ -286,10 +270,6 @@ void rcu_bh_qs(void) static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = { .dynticks_nesting = DYNTICK_TASK_EXIT_IDLE, .dynticks = ATOMIC_INIT(RCU_DYNTICK_CTRL_CTR), -#ifdef CONFIG_NO_HZ_FULL_SYSIDLE - .dynticks_idle_nesting = DYNTICK_TASK_NEST_VALUE, - .dynticks_idle = ATOMIC_INIT(1), -#endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ }; /* @@ -478,7 +458,7 @@ void rcu_note_context_switch(bool preempt) barrier(); /* Avoid RCU read-side critical sections leaking down. */ trace_rcu_utilization(TPS("Start context switch")); rcu_sched_qs(); - rcu_preempt_note_context_switch(); + rcu_preempt_note_context_switch(preempt); /* Load rcu_urgent_qs before other flags. */ if (!smp_load_acquire(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs))) goto out; @@ -534,9 +514,12 @@ void rcu_all_qs(void) } EXPORT_SYMBOL_GPL(rcu_all_qs); -static long blimit = 10; /* Maximum callbacks per rcu_do_batch. */ -static long qhimark = 10000; /* If this many pending, ignore blimit. */ -static long qlowmark = 100; /* Once only this many pending, use blimit. */ +#define DEFAULT_RCU_BLIMIT 10 /* Maximum callbacks per rcu_do_batch. */ +static long blimit = DEFAULT_RCU_BLIMIT; +#define DEFAULT_RCU_QHIMARK 10000 /* If this many pending, ignore blimit. */ +static long qhimark = DEFAULT_RCU_QHIMARK; +#define DEFAULT_RCU_QLOMARK 100 /* Once only this many pending, use blimit. */ +static long qlowmark = DEFAULT_RCU_QLOMARK; module_param(blimit, long, 0444); module_param(qhimark, long, 0444); @@ -559,10 +542,7 @@ module_param(jiffies_till_sched_qs, ulong, 0644); static bool rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp); -static void force_qs_rnp(struct rcu_state *rsp, - int (*f)(struct rcu_data *rsp, bool *isidle, - unsigned long *maxj), - bool *isidle, unsigned long *maxj); +static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp)); static void force_quiescent_state(struct rcu_state *rsp); static int rcu_pending(void); @@ -757,6 +737,7 @@ static int rcu_future_needs_gp(struct rcu_state *rsp) int idx = (READ_ONCE(rnp->completed) + 1) & 0x1; int *fp = &rnp->need_future_gp[idx]; + RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_future_needs_gp() invoked with irqs enabled!!!"); return READ_ONCE(*fp); } @@ -768,6 +749,7 @@ static int rcu_future_needs_gp(struct rcu_state *rsp) static bool cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp) { + RCU_LOCKDEP_WARN(!irqs_disabled(), "cpu_needs_another_gp() invoked with irqs enabled!!!"); if (rcu_gp_in_progress(rsp)) return false; /* No, a grace period is already in progress. */ if (rcu_future_needs_gp(rsp)) @@ -794,6 +776,7 @@ static void rcu_eqs_enter_common(bool user) struct rcu_data *rdp; struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_eqs_enter_common() invoked with irqs enabled!!!"); trace_rcu_dyntick(TPS("Start"), rdtp->dynticks_nesting, 0); if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current)) { @@ -864,7 +847,6 @@ void rcu_idle_enter(void) local_irq_save(flags); rcu_eqs_enter(false); - rcu_sysidle_enter(0); local_irq_restore(flags); } EXPORT_SYMBOL_GPL(rcu_idle_enter); @@ -914,7 +896,6 @@ void rcu_irq_exit(void) trace_rcu_dyntick(TPS("--="), rdtp->dynticks_nesting, rdtp->dynticks_nesting - 1); rdtp->dynticks_nesting--; } - rcu_sysidle_enter(1); } /* @@ -967,6 +948,7 @@ static void rcu_eqs_exit(bool user) struct rcu_dynticks *rdtp; long long oldval; + RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_eqs_exit() invoked with irqs enabled!!!"); rdtp = this_cpu_ptr(&rcu_dynticks); oldval = rdtp->dynticks_nesting; WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && oldval < 0); @@ -995,7 +977,6 @@ void rcu_idle_exit(void) local_irq_save(flags); rcu_eqs_exit(false); - rcu_sysidle_exit(0); local_irq_restore(flags); } EXPORT_SYMBOL_GPL(rcu_idle_exit); @@ -1047,7 +1028,6 @@ void rcu_irq_enter(void) trace_rcu_dyntick(TPS("++="), oldval, rdtp->dynticks_nesting); else rcu_eqs_exit_common(oldval, true); - rcu_sysidle_exit(1); } /* @@ -1130,22 +1110,11 @@ void rcu_nmi_exit(void) } /** - * __rcu_is_watching - are RCU read-side critical sections safe? - * - * Return true if RCU is watching the running CPU, which means that - * this CPU can safely enter RCU read-side critical sections. Unlike - * rcu_is_watching(), the caller of __rcu_is_watching() must have at - * least disabled preemption. - */ -bool notrace __rcu_is_watching(void) -{ - return !rcu_dynticks_curr_cpu_in_eqs(); -} - -/** * rcu_is_watching - see if RCU thinks that the current CPU is idle * - * If the current CPU is in its idle loop and is neither in an interrupt + * Return true if RCU is watching the running CPU, which means that this + * CPU can safely enter RCU read-side critical sections. In other words, + * if the current CPU is in its idle loop and is neither in an interrupt * or NMI handler, return true. */ bool notrace rcu_is_watching(void) @@ -1153,7 +1122,7 @@ bool notrace rcu_is_watching(void) bool ret; preempt_disable_notrace(); - ret = __rcu_is_watching(); + ret = !rcu_dynticks_curr_cpu_in_eqs(); preempt_enable_notrace(); return ret; } @@ -1237,11 +1206,9 @@ static int rcu_is_cpu_rrupt_from_idle(void) * credit them with an implicit quiescent state. Return 1 if this CPU * is in dynticks idle mode, which is an extended quiescent state. */ -static int dyntick_save_progress_counter(struct rcu_data *rdp, - bool *isidle, unsigned long *maxj) +static int dyntick_save_progress_counter(struct rcu_data *rdp) { rdp->dynticks_snap = rcu_dynticks_snap(rdp->dynticks); - rcu_sysidle_check_cpu(rdp, isidle, maxj); if (rcu_dynticks_in_eqs(rdp->dynticks_snap)) { trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti")); if (ULONG_CMP_LT(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4, @@ -1258,8 +1225,7 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp, * idle state since the last call to dyntick_save_progress_counter() * for this same CPU, or by virtue of having been offline. */ -static int rcu_implicit_dynticks_qs(struct rcu_data *rdp, - bool *isidle, unsigned long *maxj) +static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) { unsigned long jtsq; bool *rnhqp; @@ -1674,6 +1640,8 @@ void rcu_cpu_stall_reset(void) static unsigned long rcu_cbs_completed(struct rcu_state *rsp, struct rcu_node *rnp) { + lockdep_assert_held(&rnp->lock); + /* * If RCU is idle, we just wait for the next grace period. * But we can only be sure that RCU is idle if we are looking @@ -1719,6 +1687,8 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp, bool ret = false; struct rcu_node *rnp_root = rcu_get_root(rdp->rsp); + lockdep_assert_held(&rnp->lock); + /* * Pick up grace-period number for new callbacks. If this * grace period is already marked as needed, return to the caller. @@ -1845,6 +1815,8 @@ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, { bool ret = false; + lockdep_assert_held(&rnp->lock); + /* If no pending (not yet ready to invoke) callbacks, nothing to do. */ if (!rcu_segcblist_pend_cbs(&rdp->cblist)) return false; @@ -1883,6 +1855,8 @@ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, static bool rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) { + lockdep_assert_held(&rnp->lock); + /* If no pending (not yet ready to invoke) callbacks, nothing to do. */ if (!rcu_segcblist_pend_cbs(&rdp->cblist)) return false; @@ -1909,6 +1883,8 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, bool ret; bool need_gp; + lockdep_assert_held(&rnp->lock); + /* Handle the ends of any preceding grace periods first. */ if (rdp->completed == rnp->completed && !unlikely(READ_ONCE(rdp->gpwrap))) { @@ -2115,25 +2091,16 @@ static bool rcu_gp_fqs_check_wake(struct rcu_state *rsp, int *gfp) */ static void rcu_gp_fqs(struct rcu_state *rsp, bool first_time) { - bool isidle = false; - unsigned long maxj; struct rcu_node *rnp = rcu_get_root(rsp); WRITE_ONCE(rsp->gp_activity, jiffies); rsp->n_force_qs++; if (first_time) { /* Collect dyntick-idle snapshots. */ - if (is_sysidle_rcu_state(rsp)) { - isidle = true; - maxj = jiffies - ULONG_MAX / 4; - } - force_qs_rnp(rsp, dyntick_save_progress_counter, - &isidle, &maxj); - rcu_sysidle_report_gp(rsp, isidle, maxj); + force_qs_rnp(rsp, dyntick_save_progress_counter); } else { /* Handle dyntick-idle and offline CPUs. */ - isidle = true; - force_qs_rnp(rsp, rcu_implicit_dynticks_qs, &isidle, &maxj); + force_qs_rnp(rsp, rcu_implicit_dynticks_qs); } /* Clear flag to prevent immediate re-entry. */ if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) { @@ -2341,6 +2308,7 @@ static bool rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) { + lockdep_assert_held(&rnp->lock); if (!rsp->gp_kthread || !cpu_needs_another_gp(rsp, rdp)) { /* * Either we have not yet spawned the grace-period @@ -2402,6 +2370,7 @@ static bool rcu_start_gp(struct rcu_state *rsp) static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) __releases(rcu_get_root(rsp)->lock) { + lockdep_assert_held(&rcu_get_root(rsp)->lock); WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS); raw_spin_unlock_irqrestore_rcu_node(rcu_get_root(rsp), flags); @@ -2426,6 +2395,8 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, unsigned long oldmask = 0; struct rcu_node *rnp_c; + lockdep_assert_held(&rnp->lock); + /* Walk up the rcu_node hierarchy. */ for (;;) { if (!(rnp->qsmask & mask) || rnp->gpnum != gps) { @@ -2486,6 +2457,7 @@ static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp, unsigned long mask; struct rcu_node *rnp_p; + lockdep_assert_held(&rnp->lock); if (rcu_state_p == &rcu_sched_state || rsp != rcu_state_p || rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) { raw_spin_unlock_irqrestore_rcu_node(rnp, flags); @@ -2599,6 +2571,8 @@ static void rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) { + lockdep_assert_held(&rsp->orphan_lock); + /* No-CBs CPUs do not have orphanable callbacks. */ if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) || rcu_is_nocb_cpu(rdp->cpu)) return; @@ -2639,6 +2613,8 @@ static void rcu_adopt_orphan_cbs(struct rcu_state *rsp, unsigned long flags) { struct rcu_data *rdp = raw_cpu_ptr(rsp->rda); + lockdep_assert_held(&rsp->orphan_lock); + /* No-CBs CPUs are handled specially. */ if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) || rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags)) @@ -2705,6 +2681,7 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf) long mask; struct rcu_node *rnp = rnp_leaf; + lockdep_assert_held(&rnp->lock); if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) || rnp->qsmaskinit || rcu_preempt_has_tasks(rnp)) return; @@ -2895,10 +2872,7 @@ void rcu_check_callbacks(int user) * * The caller must have suppressed start of new grace periods. */ -static void force_qs_rnp(struct rcu_state *rsp, - int (*f)(struct rcu_data *rsp, bool *isidle, - unsigned long *maxj), - bool *isidle, unsigned long *maxj) +static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp)) { int cpu; unsigned long flags; @@ -2937,7 +2911,7 @@ static void force_qs_rnp(struct rcu_state *rsp, for_each_leaf_node_possible_cpu(rnp, cpu) { unsigned long bit = leaf_node_cpu_bit(rnp, cpu); if ((rnp->qsmask & bit) != 0) { - if (f(per_cpu_ptr(rsp->rda, cpu), isidle, maxj)) + if (f(per_cpu_ptr(rsp->rda, cpu))) mask |= bit; } } @@ -3143,9 +3117,14 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func, WARN_ON_ONCE((unsigned long)head & (sizeof(void *) - 1)); if (debug_rcu_head_queue(head)) { - /* Probable double call_rcu(), so leak the callback. */ + /* + * Probable double call_rcu(), so leak the callback. + * Use rcu:rcu_callback trace event to find the previous + * time callback was passed to __call_rcu(). + */ + WARN_ONCE(1, "__call_rcu(): Double-freed CB %p->%pF()!!!\n", + head, head->func); WRITE_ONCE(head->func, rcu_leak_callback); - WARN_ONCE(1, "__call_rcu(): Leaked duplicate callback\n"); return; } head->func = func; @@ -3194,8 +3173,24 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func, local_irq_restore(flags); } -/* - * Queue an RCU-sched callback for invocation after a grace period. +/** + * call_rcu_sched() - Queue an RCU for invocation after sched grace period. + * @head: structure to be used for queueing the RCU updates. + * @func: actual callback function to be invoked after the grace period + * + * The callback function will be invoked some time after a full grace + * period elapses, in other words after all currently executing RCU + * read-side critical sections have completed. call_rcu_sched() assumes + * that the read-side critical sections end on enabling of preemption + * or on voluntary preemption. + * RCU read-side critical sections are delimited by : + * - rcu_read_lock_sched() and rcu_read_unlock_sched(), OR + * - anything that disables preemption. + * + * These may be nested. + * + * See the description of call_rcu() for more detailed information on + * memory ordering guarantees. */ void call_rcu_sched(struct rcu_head *head, rcu_callback_t func) { @@ -3203,8 +3198,26 @@ void call_rcu_sched(struct rcu_head *head, rcu_callback_t func) } EXPORT_SYMBOL_GPL(call_rcu_sched); -/* - * Queue an RCU callback for invocation after a quicker grace period. +/** + * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period. + * @head: structure to be used for queueing the RCU updates. + * @func: actual callback function to be invoked after the grace period + * + * The callback function will be invoked some time after a full grace + * period elapses, in other words after all currently executing RCU + * read-side critical sections have completed. call_rcu_bh() assumes + * that the read-side critical sections end on completion of a softirq + * handler. This means that read-side critical sections in process + * context must not be interrupted by softirqs. This interface is to be + * used when most of the read-side critical sections are in softirq context. + * RCU read-side critical sections are delimited by : + * - rcu_read_lock() and rcu_read_unlock(), if in interrupt context. + * OR + * - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context. + * These may be nested. + * + * See the description of call_rcu() for more detailed information on + * memory ordering guarantees. */ void call_rcu_bh(struct rcu_head *head, rcu_callback_t func) { @@ -3280,12 +3293,6 @@ static inline int rcu_blocking_is_gp(void) * to have executed a full memory barrier during the execution of * synchronize_sched() -- even if CPU A and CPU B are the same CPU (but * again only if the system has more than one CPU). - * - * 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) { @@ -3578,8 +3585,14 @@ static void rcu_barrier_func(void *type) struct rcu_data *rdp = raw_cpu_ptr(rsp->rda); _rcu_barrier_trace(rsp, "IRQ", -1, rsp->barrier_sequence); - atomic_inc(&rsp->barrier_cpu_count); - rsp->call(&rdp->barrier_head, rcu_barrier_callback); + rdp->barrier_head.func = rcu_barrier_callback; + debug_rcu_head_queue(&rdp->barrier_head); + if (rcu_segcblist_entrain(&rdp->cblist, &rdp->barrier_head, 0)) { + atomic_inc(&rsp->barrier_cpu_count); + } else { + debug_rcu_head_unqueue(&rdp->barrier_head); + _rcu_barrier_trace(rsp, "IRQNQ", -1, rsp->barrier_sequence); + } } /* @@ -3698,6 +3711,7 @@ static void rcu_init_new_rnp(struct rcu_node *rnp_leaf) long mask; struct rcu_node *rnp = rnp_leaf; + lockdep_assert_held(&rnp->lock); for (;;) { mask = rnp->grpmask; rnp = rnp->parent; @@ -3753,7 +3767,6 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) !init_nocb_callback_list(rdp)) rcu_segcblist_init(&rdp->cblist); /* Re-enable callbacks. */ rdp->dynticks->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; - rcu_sysidle_init_percpu_data(rdp->dynticks); rcu_dynticks_eqs_online(); raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index ba38262c3554..9af0f31d6847 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -45,14 +45,6 @@ struct rcu_dynticks { bool rcu_need_heavy_qs; /* GP old, need heavy quiescent state. */ unsigned long rcu_qs_ctr; /* Light universal quiescent state ctr. */ bool rcu_urgent_qs; /* GP old need light quiescent state. */ -#ifdef CONFIG_NO_HZ_FULL_SYSIDLE - long long dynticks_idle_nesting; - /* irq/process nesting level from idle. */ - atomic_t dynticks_idle; /* Even value for idle, else odd. */ - /* "Idle" excludes userspace execution. */ - unsigned long dynticks_idle_jiffies; - /* End of last non-NMI non-idle period. */ -#endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ #ifdef CONFIG_RCU_FAST_NO_HZ bool all_lazy; /* Are all CPU's CBs lazy? */ unsigned long nonlazy_posted; @@ -160,19 +152,6 @@ struct rcu_node { /* Number of tasks boosted for expedited GP. */ unsigned long n_normal_boosts; /* Number of tasks boosted for normal GP. */ - unsigned long n_balk_blkd_tasks; - /* Refused to boost: no blocked tasks. */ - unsigned long n_balk_exp_gp_tasks; - /* Refused to boost: nothing blocking GP. */ - unsigned long n_balk_boost_tasks; - /* Refused to boost: already boosting. */ - unsigned long n_balk_notblocked; - /* Refused to boost: RCU RS CS still running. */ - unsigned long n_balk_notyet; - /* Refused to boost: not yet time. */ - unsigned long n_balk_nos; - /* Refused to boost: not sure why, though. */ - /* This can happen due to race conditions. */ #ifdef CONFIG_RCU_NOCB_CPU struct swait_queue_head nocb_gp_wq[2]; /* Place for rcu_nocb_kthread() to wait GP. */ @@ -312,9 +291,9 @@ struct rcu_data { }; /* Values for nocb_defer_wakeup field in struct rcu_data. */ -#define RCU_NOGP_WAKE_NOT 0 -#define RCU_NOGP_WAKE 1 -#define RCU_NOGP_WAKE_FORCE 2 +#define RCU_NOCB_WAKE_NOT 0 +#define RCU_NOCB_WAKE 1 +#define RCU_NOCB_WAKE_FORCE 2 #define RCU_JIFFIES_TILL_FORCE_QS (1 + (HZ > 250) + (HZ > 500)) /* For jiffies_till_first_fqs and */ @@ -477,7 +456,7 @@ DECLARE_PER_CPU(char, rcu_cpu_has_work); /* Forward declarations for rcutree_plugin.h */ static void rcu_bootup_announce(void); -static void rcu_preempt_note_context_switch(void); +static void rcu_preempt_note_context_switch(bool preempt); static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp); #ifdef CONFIG_HOTPLUG_CPU static bool rcu_preempt_has_tasks(struct rcu_node *rnp); @@ -529,15 +508,7 @@ static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp); #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ static void __maybe_unused rcu_kick_nohz_cpu(int cpu); static bool init_nocb_callback_list(struct rcu_data *rdp); -static void rcu_sysidle_enter(int irq); -static void rcu_sysidle_exit(int irq); -static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle, - unsigned long *maxj); -static bool is_sysidle_rcu_state(struct rcu_state *rsp); -static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle, - unsigned long maxj); static void rcu_bind_gp_kthread(void); -static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp); static bool rcu_nohz_full_cpu(struct rcu_state *rsp); static void rcu_dynticks_task_enter(void); static void rcu_dynticks_task_exit(void); @@ -551,75 +522,3 @@ void srcu_offline_cpu(unsigned int cpu) { } #endif /* #else #ifdef CONFIG_SRCU */ #endif /* #ifndef RCU_TREE_NONCORE */ - -#ifdef CONFIG_RCU_TRACE -/* Read out queue lengths for tracing. */ -static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll) -{ -#ifdef CONFIG_RCU_NOCB_CPU - *ql = atomic_long_read(&rdp->nocb_q_count); - *qll = atomic_long_read(&rdp->nocb_q_count_lazy); -#else /* #ifdef CONFIG_RCU_NOCB_CPU */ - *ql = 0; - *qll = 0; -#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ -} -#endif /* #ifdef CONFIG_RCU_TRACE */ - -/* - * Wrappers for the rcu_node::lock acquire and release. - * - * Because the rcu_nodes form a tree, the tree traversal locking will observe - * different lock values, this in turn means that an UNLOCK of one level - * followed by a LOCK of another level does not imply a full memory barrier; - * and most importantly transitivity is lost. - * - * In order to restore full ordering between tree levels, augment the regular - * lock acquire functions with smp_mb__after_unlock_lock(). - * - * As ->lock of struct rcu_node is a __private field, therefore one should use - * these wrappers rather than directly call raw_spin_{lock,unlock}* on ->lock. - */ -static inline void raw_spin_lock_rcu_node(struct rcu_node *rnp) -{ - raw_spin_lock(&ACCESS_PRIVATE(rnp, lock)); - smp_mb__after_unlock_lock(); -} - -static inline void raw_spin_unlock_rcu_node(struct rcu_node *rnp) -{ - raw_spin_unlock(&ACCESS_PRIVATE(rnp, lock)); -} - -static inline void raw_spin_lock_irq_rcu_node(struct rcu_node *rnp) -{ - raw_spin_lock_irq(&ACCESS_PRIVATE(rnp, lock)); - smp_mb__after_unlock_lock(); -} - -static inline void raw_spin_unlock_irq_rcu_node(struct rcu_node *rnp) -{ - raw_spin_unlock_irq(&ACCESS_PRIVATE(rnp, lock)); -} - -#define raw_spin_lock_irqsave_rcu_node(rnp, flags) \ -do { \ - typecheck(unsigned long, flags); \ - raw_spin_lock_irqsave(&ACCESS_PRIVATE(rnp, lock), flags); \ - smp_mb__after_unlock_lock(); \ -} while (0) - -#define raw_spin_unlock_irqrestore_rcu_node(rnp, flags) \ -do { \ - typecheck(unsigned long, flags); \ - raw_spin_unlock_irqrestore(&ACCESS_PRIVATE(rnp, lock), flags); \ -} while (0) - -static inline bool raw_spin_trylock_rcu_node(struct rcu_node *rnp) -{ - bool locked = raw_spin_trylock(&ACCESS_PRIVATE(rnp, lock)); - - if (locked) - smp_mb__after_unlock_lock(); - return locked; -} diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index e513b4ab1197..dd21ca47e4b4 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -147,7 +147,7 @@ static void __maybe_unused sync_exp_reset_tree(struct rcu_state *rsp) * * Caller must hold the rcu_state's exp_mutex. */ -static int sync_rcu_preempt_exp_done(struct rcu_node *rnp) +static bool sync_rcu_preempt_exp_done(struct rcu_node *rnp) { return rnp->exp_tasks == NULL && READ_ONCE(rnp->expmask) == 0; diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index c9a48657512a..908b309d60d7 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -70,7 +70,7 @@ static bool __read_mostly rcu_nocb_poll; /* Offload kthread are to poll. */ static void __init rcu_bootup_announce_oddness(void) { if (IS_ENABLED(CONFIG_RCU_TRACE)) - pr_info("\tRCU debugfs-based tracing is enabled.\n"); + pr_info("\tRCU event tracing is enabled.\n"); if ((IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 64) || (!IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 32)) pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d\n", @@ -90,8 +90,32 @@ static void __init rcu_bootup_announce_oddness(void) pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf); if (nr_cpu_ids != NR_CPUS) pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids); - if (IS_ENABLED(CONFIG_RCU_BOOST)) - pr_info("\tRCU kthread priority: %d.\n", kthread_prio); +#ifdef CONFIG_RCU_BOOST + pr_info("\tRCU priority boosting: priority %d delay %d ms.\n", kthread_prio, CONFIG_RCU_BOOST_DELAY); +#endif + if (blimit != DEFAULT_RCU_BLIMIT) + pr_info("\tBoot-time adjustment of callback invocation limit to %ld.\n", blimit); + if (qhimark != DEFAULT_RCU_QHIMARK) + pr_info("\tBoot-time adjustment of callback high-water mark to %ld.\n", qhimark); + if (qlowmark != DEFAULT_RCU_QLOMARK) + pr_info("\tBoot-time adjustment of callback low-water mark to %ld.\n", qlowmark); + if (jiffies_till_first_fqs != ULONG_MAX) + pr_info("\tBoot-time adjustment of first FQS scan delay to %ld jiffies.\n", jiffies_till_first_fqs); + if (jiffies_till_next_fqs != ULONG_MAX) + pr_info("\tBoot-time adjustment of subsequent FQS scan delay to %ld jiffies.\n", jiffies_till_next_fqs); + if (rcu_kick_kthreads) + pr_info("\tKick kthreads if too-long grace period.\n"); + if (IS_ENABLED(CONFIG_DEBUG_OBJECTS_RCU_HEAD)) + pr_info("\tRCU callback double-/use-after-free debug enabled.\n"); + if (gp_preinit_delay) + pr_info("\tRCU debug GP pre-init slowdown %d jiffies.\n", gp_preinit_delay); + if (gp_init_delay) + pr_info("\tRCU debug GP init slowdown %d jiffies.\n", gp_init_delay); + if (gp_cleanup_delay) + pr_info("\tRCU debug GP init slowdown %d jiffies.\n", gp_cleanup_delay); + if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG)) + pr_info("\tRCU debug extended QS entry/exit.\n"); + rcupdate_announce_bootup_oddness(); } #ifdef CONFIG_PREEMPT_RCU @@ -155,6 +179,8 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) (rnp->expmask & rdp->grpmask ? RCU_EXP_BLKD : 0); struct task_struct *t = current; + lockdep_assert_held(&rnp->lock); + /* * Decide where to queue the newly blocked task. In theory, * this could be an if-statement. In practice, when I tried @@ -263,6 +289,7 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) */ static void rcu_preempt_qs(void) { + RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_qs() invoked with preemption enabled!!!\n"); if (__this_cpu_read(rcu_data_p->cpu_no_qs.s)) { trace_rcu_grace_period(TPS("rcu_preempt"), __this_cpu_read(rcu_data_p->gpnum), @@ -286,12 +313,14 @@ static void rcu_preempt_qs(void) * * Caller must disable interrupts. */ -static void rcu_preempt_note_context_switch(void) +static void rcu_preempt_note_context_switch(bool preempt) { struct task_struct *t = current; struct rcu_data *rdp; struct rcu_node *rnp; + RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_preempt_note_context_switch() invoked with interrupts enabled!!!\n"); + WARN_ON_ONCE(!preempt && t->rcu_read_lock_nesting > 0); if (t->rcu_read_lock_nesting > 0 && !t->rcu_read_unlock_special.b.blocked) { @@ -607,6 +636,7 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp) */ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) { + RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_check_blocked_tasks() invoked with preemption enabled!!!\n"); WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)); if (rcu_preempt_has_tasks(rnp)) rnp->gp_tasks = rnp->blkd_tasks.next; @@ -643,8 +673,37 @@ static void rcu_preempt_do_callbacks(void) #endif /* #ifdef CONFIG_RCU_BOOST */ -/* - * Queue a preemptible-RCU callback for invocation after a grace period. +/** + * call_rcu() - Queue an RCU callback for invocation after a grace period. + * @head: structure to be used for queueing the RCU updates. + * @func: actual callback function to be invoked after the grace period + * + * The callback function will be invoked some time after a full grace + * period elapses, in other words after all pre-existing RCU read-side + * critical sections have completed. However, the callback function + * might well execute concurrently with RCU read-side critical sections + * that started after call_rcu() was invoked. RCU read-side critical + * sections are delimited by rcu_read_lock() and rcu_read_unlock(), + * and may be nested. + * + * Note that all CPUs must agree that the grace period extended beyond + * all pre-existing RCU read-side critical section. On systems with more + * than one CPU, this means that when "func()" is invoked, each CPU is + * guaranteed to have executed a full memory barrier since the end of its + * last RCU read-side critical section whose beginning preceded the call + * to call_rcu(). It also means that each CPU executing an RCU read-side + * critical section that continues beyond the start of "func()" must have + * executed a memory barrier after the call_rcu() but before the beginning + * of that RCU read-side critical section. Note that these guarantees + * include CPUs that are offline, idle, or executing in user mode, as + * well as CPUs that are executing in the kernel. + * + * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the + * resulting RCU callback function "func()", then both CPU A and CPU B are + * guaranteed to execute a full memory barrier during the time interval + * between the call to call_rcu() and the invocation of "func()" -- even + * if CPU A and CPU B are the same CPU (but again only if the system has + * more than one CPU). */ void call_rcu(struct rcu_head *head, rcu_callback_t func) { @@ -663,8 +722,13 @@ EXPORT_SYMBOL_GPL(call_rcu); * synchronize_rcu() was waiting. RCU read-side critical sections are * delimited by rcu_read_lock() and rcu_read_unlock(), and may be nested. * - * See the description of synchronize_sched() for more detailed information - * on memory ordering guarantees. + * See the description of synchronize_sched() for more detailed + * information on memory-ordering guarantees. However, please note + * that -only- the memory-ordering guarantees apply. For example, + * synchronize_rcu() is -not- guaranteed to wait on things like code + * protected by preempt_disable(), instead, synchronize_rcu() is -only- + * guaranteed to wait on RCU read-side critical sections, that is, sections + * of code protected by rcu_read_lock(). */ void synchronize_rcu(void) { @@ -738,7 +802,7 @@ static void __init rcu_bootup_announce(void) * Because preemptible RCU does not exist, we never have to check for * CPUs being in quiescent states. */ -static void rcu_preempt_note_context_switch(void) +static void rcu_preempt_note_context_switch(bool preempt) { } @@ -835,33 +899,6 @@ void exit_rcu(void) #include "../locking/rtmutex_common.h" -#ifdef CONFIG_RCU_TRACE - -static void rcu_initiate_boost_trace(struct rcu_node *rnp) -{ - if (!rcu_preempt_has_tasks(rnp)) - rnp->n_balk_blkd_tasks++; - else if (rnp->exp_tasks == NULL && rnp->gp_tasks == NULL) - rnp->n_balk_exp_gp_tasks++; - else if (rnp->gp_tasks != NULL && rnp->boost_tasks != NULL) - rnp->n_balk_boost_tasks++; - else if (rnp->gp_tasks != NULL && rnp->qsmask != 0) - rnp->n_balk_notblocked++; - else if (rnp->gp_tasks != NULL && - ULONG_CMP_LT(jiffies, rnp->boost_time)) - rnp->n_balk_notyet++; - else - rnp->n_balk_nos++; -} - -#else /* #ifdef CONFIG_RCU_TRACE */ - -static void rcu_initiate_boost_trace(struct rcu_node *rnp) -{ -} - -#endif /* #else #ifdef CONFIG_RCU_TRACE */ - static void rcu_wake_cond(struct task_struct *t, int status) { /* @@ -992,8 +1029,8 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) { struct task_struct *t; + lockdep_assert_held(&rnp->lock); if (!rcu_preempt_blocked_readers_cgp(rnp) && rnp->exp_tasks == NULL) { - rnp->n_balk_exp_gp_tasks++; raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; } @@ -1009,7 +1046,6 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) if (t) rcu_wake_cond(t, rnp->boost_kthread_status); } else { - rcu_initiate_boost_trace(rnp); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } } @@ -1260,8 +1296,7 @@ static void rcu_prepare_kthreads(int cpu) int rcu_needs_cpu(u64 basemono, u64 *nextevt) { *nextevt = KTIME_MAX; - return IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL) - ? 0 : rcu_cpu_has_callbacks(NULL); + return rcu_cpu_has_callbacks(NULL); } /* @@ -1372,10 +1407,7 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt) struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); unsigned long dj; - if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL)) { - *nextevt = KTIME_MAX; - return 0; - } + RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_needs_cpu() invoked with irqs enabled!!!"); /* Snapshot to detect later posting of non-lazy callback. */ rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted; @@ -1424,8 +1456,8 @@ static void rcu_prepare_for_idle(void) struct rcu_state *rsp; int tne; - if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL) || - rcu_is_nocb_cpu(smp_processor_id())) + RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_prepare_for_idle() invoked with irqs enabled!!!"); + if (rcu_is_nocb_cpu(smp_processor_id())) return; /* Handle nohz enablement switches conservatively. */ @@ -1479,8 +1511,8 @@ static void rcu_prepare_for_idle(void) */ static void rcu_cleanup_after_idle(void) { - if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL) || - rcu_is_nocb_cpu(smp_processor_id())) + RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_cleanup_after_idle() invoked with irqs enabled!!!"); + if (rcu_is_nocb_cpu(smp_processor_id())) return; if (rcu_try_advance_all_cbs()) invoke_rcu_core(); @@ -1747,7 +1779,6 @@ static void rcu_init_one_nocb(struct rcu_node *rnp) init_swait_queue_head(&rnp->nocb_gp_wq[1]); } -#ifndef CONFIG_RCU_NOCB_CPU_ALL /* Is the specified CPU a no-CBs CPU? */ bool rcu_is_nocb_cpu(int cpu) { @@ -1755,7 +1786,6 @@ bool rcu_is_nocb_cpu(int cpu) return cpumask_test_cpu(cpu, rcu_nocb_mask); return false; } -#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */ /* * Kick the leader kthread for this NOCB group. @@ -1769,6 +1799,7 @@ static void wake_nocb_leader(struct rcu_data *rdp, bool force) if (READ_ONCE(rdp_leader->nocb_leader_sleep) || force) { /* Prior smp_mb__after_atomic() orders against prior enqueue. */ WRITE_ONCE(rdp_leader->nocb_leader_sleep, false); + smp_mb(); /* ->nocb_leader_sleep before swake_up(). */ swake_up(&rdp_leader->nocb_wq); } } @@ -1860,7 +1891,7 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp, trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeEmpty")); } else { - WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOGP_WAKE); + WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOCB_WAKE); /* Store ->nocb_defer_wakeup before ->rcu_urgent_qs. */ smp_store_release(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs), true); trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, @@ -1874,7 +1905,7 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp, trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeOvf")); } else { - WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOGP_WAKE_FORCE); + WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOCB_WAKE_FORCE); /* Store ->nocb_defer_wakeup before ->rcu_urgent_qs. */ smp_store_release(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs), true); trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, @@ -2023,6 +2054,7 @@ wait_again: * nocb_gp_head, where they await a grace period. */ gotcbs = false; + smp_mb(); /* wakeup before ->nocb_head reads. */ for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) { rdp->nocb_gp_head = READ_ONCE(rdp->nocb_head); if (!rdp->nocb_gp_head) @@ -2201,8 +2233,8 @@ static void do_nocb_deferred_wakeup(struct rcu_data *rdp) if (!rcu_nocb_need_deferred_wakeup(rdp)) return; ndw = READ_ONCE(rdp->nocb_defer_wakeup); - WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOGP_WAKE_NOT); - wake_nocb_leader(rdp, ndw == RCU_NOGP_WAKE_FORCE); + WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOCB_WAKE_NOT); + wake_nocb_leader(rdp, ndw == RCU_NOCB_WAKE_FORCE); trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWake")); } @@ -2212,10 +2244,6 @@ void __init rcu_init_nohz(void) bool need_rcu_nocb_mask = true; struct rcu_state *rsp; -#ifdef CONFIG_RCU_NOCB_CPU_NONE - need_rcu_nocb_mask = false; -#endif /* #ifndef CONFIG_RCU_NOCB_CPU_NONE */ - #if defined(CONFIG_NO_HZ_FULL) if (tick_nohz_full_running && cpumask_weight(tick_nohz_full_mask)) need_rcu_nocb_mask = true; @@ -2231,14 +2259,6 @@ void __init rcu_init_nohz(void) if (!have_rcu_nocb_mask) return; -#ifdef CONFIG_RCU_NOCB_CPU_ZERO - pr_info("\tOffload RCU callbacks from CPU 0\n"); - cpumask_set_cpu(0, rcu_nocb_mask); -#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ZERO */ -#ifdef CONFIG_RCU_NOCB_CPU_ALL - pr_info("\tOffload RCU callbacks from all CPUs\n"); - cpumask_copy(rcu_nocb_mask, cpu_possible_mask); -#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ALL */ #if defined(CONFIG_NO_HZ_FULL) if (tick_nohz_full_running) cpumask_or(rcu_nocb_mask, rcu_nocb_mask, tick_nohz_full_mask); @@ -2491,421 +2511,6 @@ static void __maybe_unused rcu_kick_nohz_cpu(int cpu) #endif /* #ifdef CONFIG_NO_HZ_FULL */ } - -#ifdef CONFIG_NO_HZ_FULL_SYSIDLE - -static int full_sysidle_state; /* Current system-idle state. */ -#define RCU_SYSIDLE_NOT 0 /* Some CPU is not idle. */ -#define RCU_SYSIDLE_SHORT 1 /* All CPUs idle for brief period. */ -#define RCU_SYSIDLE_LONG 2 /* All CPUs idle for long enough. */ -#define RCU_SYSIDLE_FULL 3 /* All CPUs idle, ready for sysidle. */ -#define RCU_SYSIDLE_FULL_NOTED 4 /* Actually entered sysidle state. */ - -/* - * Invoked to note exit from irq or task transition to idle. Note that - * usermode execution does -not- count as idle here! After all, we want - * to detect full-system idle states, not RCU quiescent states and grace - * periods. The caller must have disabled interrupts. - */ -static void rcu_sysidle_enter(int irq) -{ - unsigned long j; - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); - - /* If there are no nohz_full= CPUs, no need to track this. */ - if (!tick_nohz_full_enabled()) - return; - - /* Adjust nesting, check for fully idle. */ - if (irq) { - rdtp->dynticks_idle_nesting--; - WARN_ON_ONCE(rdtp->dynticks_idle_nesting < 0); - if (rdtp->dynticks_idle_nesting != 0) - return; /* Still not fully idle. */ - } else { - if ((rdtp->dynticks_idle_nesting & DYNTICK_TASK_NEST_MASK) == - DYNTICK_TASK_NEST_VALUE) { - rdtp->dynticks_idle_nesting = 0; - } else { - rdtp->dynticks_idle_nesting -= DYNTICK_TASK_NEST_VALUE; - WARN_ON_ONCE(rdtp->dynticks_idle_nesting < 0); - return; /* Still not fully idle. */ - } - } - - /* Record start of fully idle period. */ - j = jiffies; - WRITE_ONCE(rdtp->dynticks_idle_jiffies, j); - smp_mb__before_atomic(); - atomic_inc(&rdtp->dynticks_idle); - smp_mb__after_atomic(); - WARN_ON_ONCE(atomic_read(&rdtp->dynticks_idle) & 0x1); -} - -/* - * Unconditionally force exit from full system-idle state. This is - * invoked when a normal CPU exits idle, but must be called separately - * for the timekeeping CPU (tick_do_timer_cpu). The reason for this - * is that the timekeeping CPU is permitted to take scheduling-clock - * interrupts while the system is in system-idle state, and of course - * rcu_sysidle_exit() has no way of distinguishing a scheduling-clock - * interrupt from any other type of interrupt. - */ -void rcu_sysidle_force_exit(void) -{ - int oldstate = READ_ONCE(full_sysidle_state); - int newoldstate; - - /* - * Each pass through the following loop attempts to exit full - * system-idle state. If contention proves to be a problem, - * a trylock-based contention tree could be used here. - */ - while (oldstate > RCU_SYSIDLE_SHORT) { - newoldstate = cmpxchg(&full_sysidle_state, - oldstate, RCU_SYSIDLE_NOT); - if (oldstate == newoldstate && - oldstate == RCU_SYSIDLE_FULL_NOTED) { - rcu_kick_nohz_cpu(tick_do_timer_cpu); - return; /* We cleared it, done! */ - } - oldstate = newoldstate; - } - smp_mb(); /* Order initial oldstate fetch vs. later non-idle work. */ -} - -/* - * Invoked to note entry to irq or task transition from idle. Note that - * usermode execution does -not- count as idle here! The caller must - * have disabled interrupts. - */ -static void rcu_sysidle_exit(int irq) -{ - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); - - /* If there are no nohz_full= CPUs, no need to track this. */ - if (!tick_nohz_full_enabled()) - return; - - /* Adjust nesting, check for already non-idle. */ - if (irq) { - rdtp->dynticks_idle_nesting++; - WARN_ON_ONCE(rdtp->dynticks_idle_nesting <= 0); - if (rdtp->dynticks_idle_nesting != 1) - return; /* Already non-idle. */ - } else { - /* - * Allow for irq misnesting. Yes, it really is possible - * to enter an irq handler then never leave it, and maybe - * also vice versa. Handle both possibilities. - */ - if (rdtp->dynticks_idle_nesting & DYNTICK_TASK_NEST_MASK) { - rdtp->dynticks_idle_nesting += DYNTICK_TASK_NEST_VALUE; - WARN_ON_ONCE(rdtp->dynticks_idle_nesting <= 0); - return; /* Already non-idle. */ - } else { - rdtp->dynticks_idle_nesting = DYNTICK_TASK_EXIT_IDLE; - } - } - - /* Record end of idle period. */ - smp_mb__before_atomic(); - atomic_inc(&rdtp->dynticks_idle); - smp_mb__after_atomic(); - WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks_idle) & 0x1)); - - /* - * If we are the timekeeping CPU, we are permitted to be non-idle - * during a system-idle state. This must be the case, because - * the timekeeping CPU has to take scheduling-clock interrupts - * during the time that the system is transitioning to full - * system-idle state. This means that the timekeeping CPU must - * invoke rcu_sysidle_force_exit() directly if it does anything - * more than take a scheduling-clock interrupt. - */ - if (smp_processor_id() == tick_do_timer_cpu) - return; - - /* Update system-idle state: We are clearly no longer fully idle! */ - rcu_sysidle_force_exit(); -} - -/* - * Check to see if the current CPU is idle. Note that usermode execution - * does not count as idle. The caller must have disabled interrupts, - * and must be running on tick_do_timer_cpu. - */ -static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle, - unsigned long *maxj) -{ - int cur; - unsigned long j; - struct rcu_dynticks *rdtp = rdp->dynticks; - - /* If there are no nohz_full= CPUs, don't check system-wide idleness. */ - if (!tick_nohz_full_enabled()) - return; - - /* - * If some other CPU has already reported non-idle, if this is - * not the flavor of RCU that tracks sysidle state, or if this - * is an offline or the timekeeping CPU, nothing to do. - */ - if (!*isidle || rdp->rsp != rcu_state_p || - cpu_is_offline(rdp->cpu) || rdp->cpu == tick_do_timer_cpu) - return; - /* Verify affinity of current kthread. */ - WARN_ON_ONCE(smp_processor_id() != tick_do_timer_cpu); - - /* Pick up current idle and NMI-nesting counter and check. */ - cur = atomic_read(&rdtp->dynticks_idle); - if (cur & 0x1) { - *isidle = false; /* We are not idle! */ - return; - } - smp_mb(); /* Read counters before timestamps. */ - - /* Pick up timestamps. */ - j = READ_ONCE(rdtp->dynticks_idle_jiffies); - /* If this CPU entered idle more recently, update maxj timestamp. */ - if (ULONG_CMP_LT(*maxj, j)) - *maxj = j; -} - -/* - * Is this the flavor of RCU that is handling full-system idle? - */ -static bool is_sysidle_rcu_state(struct rcu_state *rsp) -{ - return rsp == rcu_state_p; -} - -/* - * Return a delay in jiffies based on the number of CPUs, rcu_node - * leaf fanout, and jiffies tick rate. The idea is to allow larger - * systems more time to transition to full-idle state in order to - * avoid the cache thrashing that otherwise occur on the state variable. - * Really small systems (less than a couple of tens of CPUs) should - * instead use a single global atomically incremented counter, and later - * versions of this will automatically reconfigure themselves accordingly. - */ -static unsigned long rcu_sysidle_delay(void) -{ - if (nr_cpu_ids <= CONFIG_NO_HZ_FULL_SYSIDLE_SMALL) - return 0; - return DIV_ROUND_UP(nr_cpu_ids * HZ, rcu_fanout_leaf * 1000); -} - -/* - * Advance the full-system-idle state. This is invoked when all of - * the non-timekeeping CPUs are idle. - */ -static void rcu_sysidle(unsigned long j) -{ - /* Check the current state. */ - switch (READ_ONCE(full_sysidle_state)) { - case RCU_SYSIDLE_NOT: - - /* First time all are idle, so note a short idle period. */ - WRITE_ONCE(full_sysidle_state, RCU_SYSIDLE_SHORT); - break; - - case RCU_SYSIDLE_SHORT: - - /* - * Idle for a bit, time to advance to next state? - * cmpxchg failure means race with non-idle, let them win. - */ - if (ULONG_CMP_GE(jiffies, j + rcu_sysidle_delay())) - (void)cmpxchg(&full_sysidle_state, - RCU_SYSIDLE_SHORT, RCU_SYSIDLE_LONG); - break; - - case RCU_SYSIDLE_LONG: - - /* - * Do an additional check pass before advancing to full. - * cmpxchg failure means race with non-idle, let them win. - */ - if (ULONG_CMP_GE(jiffies, j + rcu_sysidle_delay())) - (void)cmpxchg(&full_sysidle_state, - RCU_SYSIDLE_LONG, RCU_SYSIDLE_FULL); - break; - - default: - break; - } -} - -/* - * Found a non-idle non-timekeeping CPU, so kick the system-idle state - * back to the beginning. - */ -static void rcu_sysidle_cancel(void) -{ - smp_mb(); - if (full_sysidle_state > RCU_SYSIDLE_SHORT) - WRITE_ONCE(full_sysidle_state, RCU_SYSIDLE_NOT); -} - -/* - * Update the sysidle state based on the results of a force-quiescent-state - * scan of the CPUs' dyntick-idle state. - */ -static void rcu_sysidle_report(struct rcu_state *rsp, int isidle, - unsigned long maxj, bool gpkt) -{ - if (rsp != rcu_state_p) - return; /* Wrong flavor, ignore. */ - if (gpkt && nr_cpu_ids <= CONFIG_NO_HZ_FULL_SYSIDLE_SMALL) - return; /* Running state machine from timekeeping CPU. */ - if (isidle) - rcu_sysidle(maxj); /* More idle! */ - else - rcu_sysidle_cancel(); /* Idle is over. */ -} - -/* - * Wrapper for rcu_sysidle_report() when called from the grace-period - * kthread's context. - */ -static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle, - unsigned long maxj) -{ - /* If there are no nohz_full= CPUs, no need to track this. */ - if (!tick_nohz_full_enabled()) - return; - - rcu_sysidle_report(rsp, isidle, maxj, true); -} - -/* Callback and function for forcing an RCU grace period. */ -struct rcu_sysidle_head { - struct rcu_head rh; - int inuse; -}; - -static void rcu_sysidle_cb(struct rcu_head *rhp) -{ - struct rcu_sysidle_head *rshp; - - /* - * The following memory barrier is needed to replace the - * memory barriers that would normally be in the memory - * allocator. - */ - smp_mb(); /* grace period precedes setting inuse. */ - - rshp = container_of(rhp, struct rcu_sysidle_head, rh); - WRITE_ONCE(rshp->inuse, 0); -} - -/* - * Check to see if the system is fully idle, other than the timekeeping CPU. - * The caller must have disabled interrupts. This is not intended to be - * called unless tick_nohz_full_enabled(). - */ -bool rcu_sys_is_idle(void) -{ - static struct rcu_sysidle_head rsh; - int rss = READ_ONCE(full_sysidle_state); - - if (WARN_ON_ONCE(smp_processor_id() != tick_do_timer_cpu)) - return false; - - /* Handle small-system case by doing a full scan of CPUs. */ - if (nr_cpu_ids <= CONFIG_NO_HZ_FULL_SYSIDLE_SMALL) { - int oldrss = rss - 1; - - /* - * One pass to advance to each state up to _FULL. - * Give up if any pass fails to advance the state. - */ - while (rss < RCU_SYSIDLE_FULL && oldrss < rss) { - int cpu; - bool isidle = true; - unsigned long maxj = jiffies - ULONG_MAX / 4; - struct rcu_data *rdp; - - /* Scan all the CPUs looking for nonidle CPUs. */ - for_each_possible_cpu(cpu) { - rdp = per_cpu_ptr(rcu_state_p->rda, cpu); - rcu_sysidle_check_cpu(rdp, &isidle, &maxj); - if (!isidle) - break; - } - rcu_sysidle_report(rcu_state_p, isidle, maxj, false); - oldrss = rss; - rss = READ_ONCE(full_sysidle_state); - } - } - - /* If this is the first observation of an idle period, record it. */ - if (rss == RCU_SYSIDLE_FULL) { - rss = cmpxchg(&full_sysidle_state, - RCU_SYSIDLE_FULL, RCU_SYSIDLE_FULL_NOTED); - return rss == RCU_SYSIDLE_FULL; - } - - smp_mb(); /* ensure rss load happens before later caller actions. */ - - /* If already fully idle, tell the caller (in case of races). */ - if (rss == RCU_SYSIDLE_FULL_NOTED) - return true; - - /* - * If we aren't there yet, and a grace period is not in flight, - * initiate a grace period. Either way, tell the caller that - * we are not there yet. We use an xchg() rather than an assignment - * to make up for the memory barriers that would otherwise be - * provided by the memory allocator. - */ - if (nr_cpu_ids > CONFIG_NO_HZ_FULL_SYSIDLE_SMALL && - !rcu_gp_in_progress(rcu_state_p) && - !rsh.inuse && xchg(&rsh.inuse, 1) == 0) - call_rcu(&rsh.rh, rcu_sysidle_cb); - return false; -} - -/* - * Initialize dynticks sysidle state for CPUs coming online. - */ -static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp) -{ - rdtp->dynticks_idle_nesting = DYNTICK_TASK_NEST_VALUE; -} - -#else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ - -static void rcu_sysidle_enter(int irq) -{ -} - -static void rcu_sysidle_exit(int irq) -{ -} - -static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle, - unsigned long *maxj) -{ -} - -static bool is_sysidle_rcu_state(struct rcu_state *rsp) -{ - return false; -} - -static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle, - unsigned long maxj) -{ -} - -static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp) -{ -} - -#endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ - /* * Is this CPU a NO_HZ_FULL CPU that should ignore RCU so that the * grace-period kthread will do force_quiescent_state() processing? @@ -2936,13 +2541,7 @@ static void rcu_bind_gp_kthread(void) if (!tick_nohz_full_enabled()) return; -#ifdef CONFIG_NO_HZ_FULL_SYSIDLE - cpu = tick_do_timer_cpu; - if (cpu >= 0 && cpu < nr_cpu_ids) - set_cpus_allowed_ptr(current, cpumask_of(cpu)); -#else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ housekeeping_affine(current); -#endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ } /* Record the current task on dyntick-idle entry. */ diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c deleted file mode 100644 index 6cea17a1ea30..000000000000 --- a/kernel/rcu/tree_trace.c +++ /dev/null @@ -1,494 +0,0 @@ -/* - * Read-Copy Update tracing for hierarchical implementation. - * - * 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, you can access it online at - * http://www.gnu.org/licenses/gpl-2.0.html. - * - * Copyright IBM Corporation, 2008 - * Author: Paul E. McKenney - * - * Papers: http://www.rdrop.com/users/paulmck/RCU - * - * For detailed explanation of Read-Copy Update mechanism see - - * Documentation/RCU - * - */ -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/spinlock.h> -#include <linux/smp.h> -#include <linux/rcupdate.h> -#include <linux/interrupt.h> -#include <linux/sched.h> -#include <linux/atomic.h> -#include <linux/bitops.h> -#include <linux/completion.h> -#include <linux/percpu.h> -#include <linux/notifier.h> -#include <linux/cpu.h> -#include <linux/mutex.h> -#include <linux/debugfs.h> -#include <linux/seq_file.h> -#include <linux/prefetch.h> - -#define RCU_TREE_NONCORE -#include "tree.h" -#include "rcu.h" - -static int r_open(struct inode *inode, struct file *file, - const struct seq_operations *op) -{ - int ret = seq_open(file, op); - if (!ret) { - struct seq_file *m = (struct seq_file *)file->private_data; - m->private = inode->i_private; - } - return ret; -} - -static void *r_start(struct seq_file *m, loff_t *pos) -{ - struct rcu_state *rsp = (struct rcu_state *)m->private; - *pos = cpumask_next(*pos - 1, cpu_possible_mask); - if ((*pos) < nr_cpu_ids) - return per_cpu_ptr(rsp->rda, *pos); - return NULL; -} - -static void *r_next(struct seq_file *m, void *v, loff_t *pos) -{ - (*pos)++; - return r_start(m, pos); -} - -static void r_stop(struct seq_file *m, void *v) -{ -} - -static int show_rcubarrier(struct seq_file *m, void *v) -{ - struct rcu_state *rsp = (struct rcu_state *)m->private; - seq_printf(m, "bcc: %d bseq: %lu\n", - atomic_read(&rsp->barrier_cpu_count), - rsp->barrier_sequence); - return 0; -} - -static int rcubarrier_open(struct inode *inode, struct file *file) -{ - return single_open(file, show_rcubarrier, inode->i_private); -} - -static const struct file_operations rcubarrier_fops = { - .owner = THIS_MODULE, - .open = rcubarrier_open, - .read = seq_read, - .llseek = no_llseek, - .release = single_release, -}; - -#ifdef CONFIG_RCU_BOOST - -static char convert_kthread_status(unsigned int kthread_status) -{ - if (kthread_status > RCU_KTHREAD_MAX) - return '?'; - return "SRWOY"[kthread_status]; -} - -#endif /* #ifdef CONFIG_RCU_BOOST */ - -static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) -{ - long ql, qll; - - if (!rdp->beenonline) - return; - seq_printf(m, "%3d%cc=%ld g=%ld cnq=%d/%d:%d", - rdp->cpu, - cpu_is_offline(rdp->cpu) ? '!' : ' ', - ulong2long(rdp->completed), ulong2long(rdp->gpnum), - rdp->cpu_no_qs.b.norm, - rdp->rcu_qs_ctr_snap == per_cpu(rdp->dynticks->rcu_qs_ctr, rdp->cpu), - rdp->core_needs_qs); - seq_printf(m, " dt=%d/%llx/%d df=%lu", - rcu_dynticks_snap(rdp->dynticks), - rdp->dynticks->dynticks_nesting, - rdp->dynticks->dynticks_nmi_nesting, - rdp->dynticks_fqs); - seq_printf(m, " of=%lu", rdp->offline_fqs); - rcu_nocb_q_lengths(rdp, &ql, &qll); - qll += rcu_segcblist_n_lazy_cbs(&rdp->cblist); - ql += rcu_segcblist_n_cbs(&rdp->cblist); - seq_printf(m, " ql=%ld/%ld qs=%c%c%c%c", - qll, ql, - ".N"[!rcu_segcblist_segempty(&rdp->cblist, RCU_NEXT_TAIL)], - ".R"[!rcu_segcblist_segempty(&rdp->cblist, - RCU_NEXT_READY_TAIL)], - ".W"[!rcu_segcblist_segempty(&rdp->cblist, RCU_WAIT_TAIL)], - ".D"[!rcu_segcblist_segempty(&rdp->cblist, RCU_DONE_TAIL)]); -#ifdef CONFIG_RCU_BOOST - seq_printf(m, " kt=%d/%c ktl=%x", - per_cpu(rcu_cpu_has_work, rdp->cpu), - convert_kthread_status(per_cpu(rcu_cpu_kthread_status, - rdp->cpu)), - per_cpu(rcu_cpu_kthread_loops, rdp->cpu) & 0xffff); -#endif /* #ifdef CONFIG_RCU_BOOST */ - seq_printf(m, " b=%ld", rdp->blimit); - seq_printf(m, " ci=%lu nci=%lu co=%lu ca=%lu\n", - rdp->n_cbs_invoked, rdp->n_nocbs_invoked, - rdp->n_cbs_orphaned, rdp->n_cbs_adopted); -} - -static int show_rcudata(struct seq_file *m, void *v) -{ - print_one_rcu_data(m, (struct rcu_data *)v); - return 0; -} - -static const struct seq_operations rcudate_op = { - .start = r_start, - .next = r_next, - .stop = r_stop, - .show = show_rcudata, -}; - -static int rcudata_open(struct inode *inode, struct file *file) -{ - return r_open(inode, file, &rcudate_op); -} - -static const struct file_operations rcudata_fops = { - .owner = THIS_MODULE, - .open = rcudata_open, - .read = seq_read, - .llseek = no_llseek, - .release = seq_release, -}; - -static int show_rcuexp(struct seq_file *m, void *v) -{ - int cpu; - struct rcu_state *rsp = (struct rcu_state *)m->private; - struct rcu_data *rdp; - unsigned long s0 = 0, s1 = 0, s2 = 0, s3 = 0; - - for_each_possible_cpu(cpu) { - rdp = per_cpu_ptr(rsp->rda, cpu); - s0 += atomic_long_read(&rdp->exp_workdone0); - s1 += atomic_long_read(&rdp->exp_workdone1); - s2 += atomic_long_read(&rdp->exp_workdone2); - s3 += atomic_long_read(&rdp->exp_workdone3); - } - seq_printf(m, "s=%lu wd0=%lu wd1=%lu wd2=%lu wd3=%lu enq=%d sc=%lu\n", - rsp->expedited_sequence, s0, s1, s2, s3, - atomic_read(&rsp->expedited_need_qs), - rsp->expedited_sequence / 2); - return 0; -} - -static int rcuexp_open(struct inode *inode, struct file *file) -{ - return single_open(file, show_rcuexp, inode->i_private); -} - -static const struct file_operations rcuexp_fops = { - .owner = THIS_MODULE, - .open = rcuexp_open, - .read = seq_read, - .llseek = no_llseek, - .release = single_release, -}; - -#ifdef CONFIG_RCU_BOOST - -static void print_one_rcu_node_boost(struct seq_file *m, struct rcu_node *rnp) -{ - seq_printf(m, "%d:%d tasks=%c%c%c%c kt=%c ntb=%lu neb=%lu nnb=%lu ", - rnp->grplo, rnp->grphi, - "T."[list_empty(&rnp->blkd_tasks)], - "N."[!rnp->gp_tasks], - "E."[!rnp->exp_tasks], - "B."[!rnp->boost_tasks], - convert_kthread_status(rnp->boost_kthread_status), - rnp->n_tasks_boosted, rnp->n_exp_boosts, - rnp->n_normal_boosts); - seq_printf(m, "j=%04x bt=%04x\n", - (int)(jiffies & 0xffff), - (int)(rnp->boost_time & 0xffff)); - seq_printf(m, " balk: nt=%lu egt=%lu bt=%lu nb=%lu ny=%lu nos=%lu\n", - rnp->n_balk_blkd_tasks, - rnp->n_balk_exp_gp_tasks, - rnp->n_balk_boost_tasks, - rnp->n_balk_notblocked, - rnp->n_balk_notyet, - rnp->n_balk_nos); -} - -static int show_rcu_node_boost(struct seq_file *m, void *unused) -{ - struct rcu_node *rnp; - - rcu_for_each_leaf_node(&rcu_preempt_state, rnp) - print_one_rcu_node_boost(m, rnp); - return 0; -} - -static int rcu_node_boost_open(struct inode *inode, struct file *file) -{ - return single_open(file, show_rcu_node_boost, NULL); -} - -static const struct file_operations rcu_node_boost_fops = { - .owner = THIS_MODULE, - .open = rcu_node_boost_open, - .read = seq_read, - .llseek = no_llseek, - .release = single_release, -}; - -#endif /* #ifdef CONFIG_RCU_BOOST */ - -static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp) -{ - unsigned long gpnum; - int level = 0; - struct rcu_node *rnp; - - gpnum = rsp->gpnum; - seq_printf(m, "c=%ld g=%ld s=%d jfq=%ld j=%x ", - ulong2long(rsp->completed), ulong2long(gpnum), - rsp->gp_state, - (long)(rsp->jiffies_force_qs - jiffies), - (int)(jiffies & 0xffff)); - seq_printf(m, "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld/%ld\n", - rsp->n_force_qs, rsp->n_force_qs_ngp, - rsp->n_force_qs - rsp->n_force_qs_ngp, - READ_ONCE(rsp->n_force_qs_lh), - rsp->orphan_done.len_lazy, - rsp->orphan_done.len); - for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < rcu_num_nodes; rnp++) { - if (rnp->level != level) { - seq_puts(m, "\n"); - level = rnp->level; - } - seq_printf(m, "%lx/%lx->%lx %c%c>%c %d:%d ^%d ", - rnp->qsmask, rnp->qsmaskinit, rnp->qsmaskinitnext, - ".G"[rnp->gp_tasks != NULL], - ".E"[rnp->exp_tasks != NULL], - ".T"[!list_empty(&rnp->blkd_tasks)], - rnp->grplo, rnp->grphi, rnp->grpnum); - } - seq_puts(m, "\n"); -} - -static int show_rcuhier(struct seq_file *m, void *v) -{ - struct rcu_state *rsp = (struct rcu_state *)m->private; - print_one_rcu_state(m, rsp); - return 0; -} - -static int rcuhier_open(struct inode *inode, struct file *file) -{ - return single_open(file, show_rcuhier, inode->i_private); -} - -static const struct file_operations rcuhier_fops = { - .owner = THIS_MODULE, - .open = rcuhier_open, - .read = seq_read, - .llseek = no_llseek, - .release = single_release, -}; - -static void show_one_rcugp(struct seq_file *m, struct rcu_state *rsp) -{ - unsigned long flags; - unsigned long completed; - unsigned long gpnum; - unsigned long gpage; - unsigned long gpmax; - struct rcu_node *rnp = &rsp->node[0]; - - raw_spin_lock_irqsave_rcu_node(rnp, flags); - completed = READ_ONCE(rsp->completed); - gpnum = READ_ONCE(rsp->gpnum); - if (completed == gpnum) - gpage = 0; - else - gpage = jiffies - rsp->gp_start; - gpmax = rsp->gp_max; - raw_spin_unlock_irqrestore(&rnp->lock, flags); - seq_printf(m, "completed=%ld gpnum=%ld age=%ld max=%ld\n", - ulong2long(completed), ulong2long(gpnum), gpage, gpmax); -} - -static int show_rcugp(struct seq_file *m, void *v) -{ - struct rcu_state *rsp = (struct rcu_state *)m->private; - show_one_rcugp(m, rsp); - return 0; -} - -static int rcugp_open(struct inode *inode, struct file *file) -{ - return single_open(file, show_rcugp, inode->i_private); -} - -static const struct file_operations rcugp_fops = { - .owner = THIS_MODULE, - .open = rcugp_open, - .read = seq_read, - .llseek = no_llseek, - .release = single_release, -}; - -static void print_one_rcu_pending(struct seq_file *m, struct rcu_data *rdp) -{ - if (!rdp->beenonline) - return; - seq_printf(m, "%3d%cnp=%ld ", - rdp->cpu, - cpu_is_offline(rdp->cpu) ? '!' : ' ', - rdp->n_rcu_pending); - seq_printf(m, "qsp=%ld rpq=%ld cbr=%ld cng=%ld ", - rdp->n_rp_core_needs_qs, - rdp->n_rp_report_qs, - rdp->n_rp_cb_ready, - rdp->n_rp_cpu_needs_gp); - seq_printf(m, "gpc=%ld gps=%ld nn=%ld ndw%ld\n", - rdp->n_rp_gp_completed, - rdp->n_rp_gp_started, - rdp->n_rp_nocb_defer_wakeup, - rdp->n_rp_need_nothing); -} - -static int show_rcu_pending(struct seq_file *m, void *v) -{ - print_one_rcu_pending(m, (struct rcu_data *)v); - return 0; -} - -static const struct seq_operations rcu_pending_op = { - .start = r_start, - .next = r_next, - .stop = r_stop, - .show = show_rcu_pending, -}; - -static int rcu_pending_open(struct inode *inode, struct file *file) -{ - return r_open(inode, file, &rcu_pending_op); -} - -static const struct file_operations rcu_pending_fops = { - .owner = THIS_MODULE, - .open = rcu_pending_open, - .read = seq_read, - .llseek = no_llseek, - .release = seq_release, -}; - -static int show_rcutorture(struct seq_file *m, void *unused) -{ - seq_printf(m, "rcutorture test sequence: %lu %s\n", - rcutorture_testseq >> 1, - (rcutorture_testseq & 0x1) ? "(test in progress)" : ""); - seq_printf(m, "rcutorture update version number: %lu\n", - rcutorture_vernum); - return 0; -} - -static int rcutorture_open(struct inode *inode, struct file *file) -{ - return single_open(file, show_rcutorture, NULL); -} - -static const struct file_operations rcutorture_fops = { - .owner = THIS_MODULE, - .open = rcutorture_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -static struct dentry *rcudir; - -static int __init rcutree_trace_init(void) -{ - struct rcu_state *rsp; - struct dentry *retval; - struct dentry *rspdir; - - rcudir = debugfs_create_dir("rcu", NULL); - if (!rcudir) - goto free_out; - - for_each_rcu_flavor(rsp) { - rspdir = debugfs_create_dir(rsp->name, rcudir); - if (!rspdir) - goto free_out; - - retval = debugfs_create_file("rcudata", 0444, - rspdir, rsp, &rcudata_fops); - if (!retval) - goto free_out; - - retval = debugfs_create_file("rcuexp", 0444, - rspdir, rsp, &rcuexp_fops); - if (!retval) - goto free_out; - - retval = debugfs_create_file("rcu_pending", 0444, - rspdir, rsp, &rcu_pending_fops); - if (!retval) - goto free_out; - - retval = debugfs_create_file("rcubarrier", 0444, - rspdir, rsp, &rcubarrier_fops); - if (!retval) - goto free_out; - -#ifdef CONFIG_RCU_BOOST - if (rsp == &rcu_preempt_state) { - retval = debugfs_create_file("rcuboost", 0444, - rspdir, NULL, &rcu_node_boost_fops); - if (!retval) - goto free_out; - } -#endif - - retval = debugfs_create_file("rcugp", 0444, - rspdir, rsp, &rcugp_fops); - if (!retval) - goto free_out; - - retval = debugfs_create_file("rcuhier", 0444, - rspdir, rsp, &rcuhier_fops); - if (!retval) - goto free_out; - } - - retval = debugfs_create_file("rcutorture", 0444, rcudir, - NULL, &rcutorture_fops); - if (!retval) - goto free_out; - return 0; -free_out: - debugfs_remove_recursive(rcudir); - return 1; -} -device_initcall(rcutree_trace_init); diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 273e869ca21d..00e77c470017 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -62,7 +62,9 @@ #define MODULE_PARAM_PREFIX "rcupdate." #ifndef CONFIG_TINY_RCU +extern int rcu_expedited; /* from sysctl */ module_param(rcu_expedited, int, 0); +extern int rcu_normal; /* from sysctl */ module_param(rcu_normal, int, 0); static int rcu_normal_after_boot; module_param(rcu_normal_after_boot, int, 0); @@ -379,6 +381,7 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array, struct rcu_synchronize *rs_array) { int i; + int j; /* Initialize and register callbacks for each flavor specified. */ for (i = 0; i < n; i++) { @@ -390,7 +393,11 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array, } init_rcu_head_on_stack(&rs_array[i].head); init_completion(&rs_array[i].completion); - (crcu_array[i])(&rs_array[i].head, wakeme_after_rcu); + for (j = 0; j < i; j++) + if (crcu_array[j] == crcu_array[i]) + break; + if (j == i) + (crcu_array[i])(&rs_array[i].head, wakeme_after_rcu); } /* Wait for all callbacks to be invoked. */ @@ -399,7 +406,11 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array, (crcu_array[i] == call_rcu || crcu_array[i] == call_rcu_bh)) continue; - wait_for_completion(&rs_array[i].completion); + for (j = 0; j < i; j++) + if (crcu_array[j] == crcu_array[i]) + break; + if (j == i) + wait_for_completion(&rs_array[i].completion); destroy_rcu_head_on_stack(&rs_array[i].head); } } @@ -560,15 +571,30 @@ static DEFINE_RAW_SPINLOCK(rcu_tasks_cbs_lock); DEFINE_SRCU(tasks_rcu_exit_srcu); /* Control stall timeouts. Disable with <= 0, otherwise jiffies till stall. */ -static int rcu_task_stall_timeout __read_mostly = HZ * 60 * 10; +#define RCU_TASK_STALL_TIMEOUT (HZ * 60 * 10) +static int rcu_task_stall_timeout __read_mostly = RCU_TASK_STALL_TIMEOUT; module_param(rcu_task_stall_timeout, int, 0644); static void rcu_spawn_tasks_kthread(void); static struct task_struct *rcu_tasks_kthread_ptr; -/* - * Post an RCU-tasks callback. First call must be from process context - * after the scheduler if fully operational. +/** + * call_rcu_tasks() - Queue an RCU for invocation task-based grace period + * @rhp: structure to be used for queueing the RCU updates. + * @func: actual callback function to be invoked after the grace period + * + * The callback function will be invoked some time after a full grace + * period elapses, in other words after all currently executing RCU + * read-side critical sections have completed. call_rcu_tasks() assumes + * that the read-side critical sections end at a voluntary context + * switch (not a preemption!), entry into idle, or transition to usermode + * execution. As such, there are no read-side primitives analogous to + * rcu_read_lock() and rcu_read_unlock() because this primitive is intended + * to determine that all tasks have passed through a safe state, not so + * much for data-strcuture synchronization. + * + * See the description of call_rcu() for more detailed information on + * memory ordering guarantees. */ void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func) { @@ -851,6 +877,23 @@ static void rcu_spawn_tasks_kthread(void) #endif /* #ifdef CONFIG_TASKS_RCU */ +#ifndef CONFIG_TINY_RCU + +/* + * Print any non-default Tasks RCU settings. + */ +static void __init rcu_tasks_bootup_oddness(void) +{ +#ifdef CONFIG_TASKS_RCU + if (rcu_task_stall_timeout != RCU_TASK_STALL_TIMEOUT) + pr_info("\tTasks-RCU CPU stall warnings timeout set to %d (rcu_task_stall_timeout).\n", rcu_task_stall_timeout); + else + pr_info("\tTasks RCU enabled.\n"); +#endif /* #ifdef CONFIG_TASKS_RCU */ +} + +#endif /* #ifndef CONFIG_TINY_RCU */ + #ifdef CONFIG_PROVE_RCU /* @@ -935,3 +978,25 @@ late_initcall(rcu_verify_early_boot_tests); #else void rcu_early_boot_tests(void) {} #endif /* CONFIG_PROVE_RCU */ + +#ifndef CONFIG_TINY_RCU + +/* + * Print any significant non-default boot-time settings. + */ +void __init rcupdate_announce_bootup_oddness(void) +{ + if (rcu_normal) + pr_info("\tNo expedited grace period (rcu_normal).\n"); + else if (rcu_normal_after_boot) + pr_info("\tNo expedited grace period (rcu_normal_after_boot).\n"); + else if (rcu_expedited) + pr_info("\tAll grace periods are expedited (rcu_expedited).\n"); + if (rcu_cpu_stall_suppress) + pr_info("\tRCU CPU stall warnings suppressed (rcu_cpu_stall_suppress).\n"); + if (rcu_cpu_stall_timeout != CONFIG_RCU_CPU_STALL_TIMEOUT) + pr_info("\tRCU CPU stall warnings timeout set to %d (rcu_cpu_stall_timeout).\n", rcu_cpu_stall_timeout); + rcu_tasks_bootup_oddness(); +} + +#endif /* #ifndef CONFIG_TINY_RCU */ diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 89ab6758667b..53f0164ed362 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -16,9 +16,9 @@ CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer endif obj-y += core.o loadavg.o clock.o cputime.o -obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o -obj-y += wait.o swait.o completion.o idle.o -obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o +obj-y += idle_task.o fair.o rt.o deadline.o +obj-y += wait.o wait_bit.o swait.o completion.o idle.o +obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o obj-$(CONFIG_SCHEDSTATS) += stats.o obj-$(CONFIG_SCHED_DEBUG) += debug.o diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index 00a45c45beca..ca0f8fc945c6 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -64,6 +64,7 @@ #include <linux/workqueue.h> #include <linux/compiler.h> #include <linux/tick.h> +#include <linux/init.h> /* * Scheduler clock - returns current time in nanosec units. @@ -124,14 +125,27 @@ int sched_clock_stable(void) return static_branch_likely(&__sched_clock_stable); } +static void __scd_stamp(struct sched_clock_data *scd) +{ + scd->tick_gtod = ktime_get_ns(); + scd->tick_raw = sched_clock(); +} + static void __set_sched_clock_stable(void) { - struct sched_clock_data *scd = this_scd(); + struct sched_clock_data *scd; /* + * Since we're still unstable and the tick is already running, we have + * to disable IRQs in order to get a consistent scd->tick* reading. + */ + local_irq_disable(); + scd = this_scd(); + /* * Attempt to make the (initial) unstable->stable transition continuous. */ __sched_clock_offset = (scd->tick_gtod + __gtod_offset) - (scd->tick_raw); + local_irq_enable(); printk(KERN_INFO "sched_clock: Marking stable (%lld, %lld)->(%lld, %lld)\n", scd->tick_gtod, __gtod_offset, @@ -141,8 +155,38 @@ static void __set_sched_clock_stable(void) tick_dep_clear(TICK_DEP_BIT_CLOCK_UNSTABLE); } +/* + * If we ever get here, we're screwed, because we found out -- typically after + * the fact -- that TSC wasn't good. This means all our clocksources (including + * ktime) could have reported wrong values. + * + * What we do here is an attempt to fix up and continue sort of where we left + * off in a coherent manner. + * + * The only way to fully avoid random clock jumps is to boot with: + * "tsc=unstable". + */ static void __sched_clock_work(struct work_struct *work) { + struct sched_clock_data *scd; + int cpu; + + /* take a current timestamp and set 'now' */ + preempt_disable(); + scd = this_scd(); + __scd_stamp(scd); + scd->clock = scd->tick_gtod + __gtod_offset; + preempt_enable(); + + /* clone to all CPUs */ + for_each_possible_cpu(cpu) + per_cpu(sched_clock_data, cpu) = *scd; + + printk(KERN_WARNING "TSC found unstable after boot, most likely due to broken BIOS. Use 'tsc=unstable'.\n"); + printk(KERN_INFO "sched_clock: Marking unstable (%lld, %lld)<-(%lld, %lld)\n", + scd->tick_gtod, __gtod_offset, + scd->tick_raw, __sched_clock_offset); + static_branch_disable(&__sched_clock_stable); } @@ -150,27 +194,11 @@ static DECLARE_WORK(sched_clock_work, __sched_clock_work); static void __clear_sched_clock_stable(void) { - struct sched_clock_data *scd = this_scd(); - - /* - * Attempt to make the stable->unstable transition continuous. - * - * Trouble is, this is typically called from the TSC watchdog - * timer, which is late per definition. This means the tick - * values can already be screwy. - * - * Still do what we can. - */ - __gtod_offset = (scd->tick_raw + __sched_clock_offset) - (scd->tick_gtod); - - printk(KERN_INFO "sched_clock: Marking unstable (%lld, %lld)<-(%lld, %lld)\n", - scd->tick_gtod, __gtod_offset, - scd->tick_raw, __sched_clock_offset); + if (!sched_clock_stable()) + return; tick_dep_set(TICK_DEP_BIT_CLOCK_UNSTABLE); - - if (sched_clock_stable()) - schedule_work(&sched_clock_work); + schedule_work(&sched_clock_work); } void clear_sched_clock_stable(void) @@ -183,7 +211,11 @@ void clear_sched_clock_stable(void) __clear_sched_clock_stable(); } -void sched_clock_init_late(void) +/* + * We run this as late_initcall() such that it runs after all built-in drivers, + * notably: acpi_processor and intel_idle, which can mark the TSC as unstable. + */ +static int __init sched_clock_init_late(void) { sched_clock_running = 2; /* @@ -197,7 +229,10 @@ void sched_clock_init_late(void) if (__sched_clock_stable_early) __set_sched_clock_stable(); + + return 0; } +late_initcall(sched_clock_init_late); /* * min, max except they take wrapping into account @@ -347,21 +382,38 @@ void sched_clock_tick(void) { struct sched_clock_data *scd; + if (sched_clock_stable()) + return; + + if (unlikely(!sched_clock_running)) + return; + WARN_ON_ONCE(!irqs_disabled()); + scd = this_scd(); + __scd_stamp(scd); + sched_clock_local(scd); +} + +void sched_clock_tick_stable(void) +{ + u64 gtod, clock; + + if (!sched_clock_stable()) + return; + /* - * Update these values even if sched_clock_stable(), because it can - * become unstable at any point in time at which point we need some - * values to fall back on. + * Called under watchdog_lock. * - * XXX arguably we can skip this if we expose tsc_clocksource_reliable + * The watchdog just found this TSC to (still) be stable, so now is a + * good moment to update our __gtod_offset. Because once we find the + * TSC to be unstable, any computation will be computing crap. */ - scd = this_scd(); - scd->tick_raw = sched_clock(); - scd->tick_gtod = ktime_get_ns(); - - if (!sched_clock_stable() && likely(sched_clock_running)) - sched_clock_local(scd); + local_irq_disable(); + gtod = ktime_get_ns(); + clock = sched_clock(); + __gtod_offset = (clock + __sched_clock_offset) - gtod; + local_irq_enable(); } /* @@ -374,15 +426,21 @@ void sched_clock_idle_sleep_event(void) EXPORT_SYMBOL_GPL(sched_clock_idle_sleep_event); /* - * We just idled delta nanoseconds (called with irqs disabled): + * We just idled; resync with ktime. */ -void sched_clock_idle_wakeup_event(u64 delta_ns) +void sched_clock_idle_wakeup_event(void) { - if (timekeeping_suspended) + unsigned long flags; + + if (sched_clock_stable()) + return; + + if (unlikely(timekeeping_suspended)) return; + local_irq_save(flags); sched_clock_tick(); - touch_softlockup_watchdog_sched(); + local_irq_restore(flags); } EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event); diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c index 53f9558fa925..13fc5ae9bf2f 100644 --- a/kernel/sched/completion.c +++ b/kernel/sched/completion.c @@ -66,7 +66,7 @@ do_wait_for_common(struct completion *x, if (!x->done) { DECLARE_WAITQUEUE(wait, current); - __add_wait_queue_tail_exclusive(&x->wait, &wait); + __add_wait_queue_entry_tail_exclusive(&x->wait, &wait); do { if (signal_pending_state(state, current)) { timeout = -ERESTARTSYS; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 326d4f88e2b1..17c667b427b4 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -10,6 +10,7 @@ #include <uapi/linux/sched/types.h> #include <linux/sched/loadavg.h> #include <linux/sched/hotplug.h> +#include <linux/wait_bit.h> #include <linux/cpuset.h> #include <linux/delayacct.h> #include <linux/init_task.h> @@ -788,36 +789,6 @@ void deactivate_task(struct rq *rq, struct task_struct *p, int flags) dequeue_task(rq, p, flags); } -void sched_set_stop_task(int cpu, struct task_struct *stop) -{ - struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 }; - struct task_struct *old_stop = cpu_rq(cpu)->stop; - - if (stop) { - /* - * Make it appear like a SCHED_FIFO task, its something - * userspace knows about and won't get confused about. - * - * Also, it will make PI more or less work without too - * much confusion -- but then, stop work should not - * rely on PI working anyway. - */ - sched_setscheduler_nocheck(stop, SCHED_FIFO, ¶m); - - stop->sched_class = &stop_sched_class; - } - - cpu_rq(cpu)->stop = stop; - - if (old_stop) { - /* - * Reset it back to a normal scheduling class so that - * it can die in pieces. - */ - old_stop->sched_class = &rt_sched_class; - } -} - /* * __normal_prio - return the priority that is based on the static prio */ @@ -1588,6 +1559,36 @@ static void update_avg(u64 *avg, u64 sample) *avg += diff >> 3; } +void sched_set_stop_task(int cpu, struct task_struct *stop) +{ + struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 }; + struct task_struct *old_stop = cpu_rq(cpu)->stop; + + if (stop) { + /* + * Make it appear like a SCHED_FIFO task, its something + * userspace knows about and won't get confused about. + * + * Also, it will make PI more or less work without too + * much confusion -- but then, stop work should not + * rely on PI working anyway. + */ + sched_setscheduler_nocheck(stop, SCHED_FIFO, ¶m); + + stop->sched_class = &stop_sched_class; + } + + cpu_rq(cpu)->stop = stop; + + if (old_stop) { + /* + * Reset it back to a normal scheduling class so that + * it can die in pieces. + */ + old_stop->sched_class = &rt_sched_class; + } +} + #else static inline int __set_cpus_allowed_ptr(struct task_struct *p, @@ -1731,7 +1732,7 @@ void sched_ttwu_pending(void) { struct rq *rq = this_rq(); struct llist_node *llist = llist_del_all(&rq->wake_list); - struct task_struct *p; + struct task_struct *p, *t; struct rq_flags rf; if (!llist) @@ -1740,17 +1741,8 @@ void sched_ttwu_pending(void) rq_lock_irqsave(rq, &rf); update_rq_clock(rq); - while (llist) { - int wake_flags = 0; - - p = llist_entry(llist, struct task_struct, wake_entry); - llist = llist_next(llist); - - if (p->sched_remote_wakeup) - wake_flags = WF_MIGRATED; - - ttwu_do_activate(rq, p, wake_flags, &rf); - } + llist_for_each_entry_safe(p, t, llist, wake_entry) + ttwu_do_activate(rq, p, p->sched_remote_wakeup ? WF_MIGRATED : 0, &rf); rq_unlock_irqrestore(rq, &rf); } @@ -2148,23 +2140,6 @@ int wake_up_state(struct task_struct *p, unsigned int state) } /* - * This function clears the sched_dl_entity static params. - */ -void __dl_clear_params(struct task_struct *p) -{ - struct sched_dl_entity *dl_se = &p->dl; - - dl_se->dl_runtime = 0; - dl_se->dl_deadline = 0; - dl_se->dl_period = 0; - dl_se->flags = 0; - dl_se->dl_bw = 0; - - dl_se->dl_throttled = 0; - dl_se->dl_yielded = 0; -} - -/* * Perform scheduler related setup for a newly forked process p. * p is forked by current. * @@ -2193,6 +2168,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) RB_CLEAR_NODE(&p->dl.rb_node); init_dl_task_timer(&p->dl); + init_dl_inactive_task_timer(&p->dl); __dl_clear_params(p); INIT_LIST_HEAD(&p->rt.run_list); @@ -2430,7 +2406,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) unsigned long to_ratio(u64 period, u64 runtime) { if (runtime == RUNTIME_INF) - return 1ULL << 20; + return BW_UNIT; /* * Doing this here saves a lot of checks in all @@ -2440,93 +2416,9 @@ unsigned long to_ratio(u64 period, u64 runtime) if (period == 0) return 0; - return div64_u64(runtime << 20, period); -} - -#ifdef CONFIG_SMP -inline struct dl_bw *dl_bw_of(int i) -{ - RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(), - "sched RCU must be held"); - return &cpu_rq(i)->rd->dl_bw; -} - -static inline int dl_bw_cpus(int i) -{ - struct root_domain *rd = cpu_rq(i)->rd; - int cpus = 0; - - RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(), - "sched RCU must be held"); - for_each_cpu_and(i, rd->span, cpu_active_mask) - cpus++; - - return cpus; -} -#else -inline struct dl_bw *dl_bw_of(int i) -{ - return &cpu_rq(i)->dl.dl_bw; -} - -static inline int dl_bw_cpus(int i) -{ - return 1; -} -#endif - -/* - * We must be sure that accepting a new task (or allowing changing the - * parameters of an existing one) is consistent with the bandwidth - * constraints. If yes, this function also accordingly updates the currently - * allocated bandwidth to reflect the new situation. - * - * This function is called while holding p's rq->lock. - * - * XXX we should delay bw change until the task's 0-lag point, see - * __setparam_dl(). - */ -static int dl_overflow(struct task_struct *p, int policy, - const struct sched_attr *attr) -{ - - struct dl_bw *dl_b = dl_bw_of(task_cpu(p)); - u64 period = attr->sched_period ?: attr->sched_deadline; - u64 runtime = attr->sched_runtime; - u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0; - int cpus, err = -1; - - /* !deadline task may carry old deadline bandwidth */ - if (new_bw == p->dl.dl_bw && task_has_dl_policy(p)) - return 0; - - /* - * Either if a task, enters, leave, or stays -deadline but changes - * its parameters, we may need to update accordingly the total - * allocated bandwidth of the container. - */ - raw_spin_lock(&dl_b->lock); - cpus = dl_bw_cpus(task_cpu(p)); - if (dl_policy(policy) && !task_has_dl_policy(p) && - !__dl_overflow(dl_b, cpus, 0, new_bw)) { - __dl_add(dl_b, new_bw); - err = 0; - } else if (dl_policy(policy) && task_has_dl_policy(p) && - !__dl_overflow(dl_b, cpus, p->dl.dl_bw, new_bw)) { - __dl_clear(dl_b, p->dl.dl_bw); - __dl_add(dl_b, new_bw); - err = 0; - } else if (!dl_policy(policy) && task_has_dl_policy(p)) { - __dl_clear(dl_b, p->dl.dl_bw); - err = 0; - } - raw_spin_unlock(&dl_b->lock); - - return err; + return div64_u64(runtime << BW_SHIFT, period); } -extern void init_dl_bw(struct dl_bw *dl_b); - /* * wake_up_new_task - wake up a newly created task for the first time. * @@ -3687,7 +3579,7 @@ asmlinkage __visible void __sched preempt_schedule_irq(void) exception_exit(prev_state); } -int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags, +int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flags, void *key) { return try_to_wake_up(curr->private, mode, wake_flags); @@ -4009,46 +3901,6 @@ static struct task_struct *find_process_by_pid(pid_t pid) } /* - * This function initializes the sched_dl_entity of a newly becoming - * SCHED_DEADLINE task. - * - * Only the static values are considered here, the actual runtime and the - * absolute deadline will be properly calculated when the task is enqueued - * for the first time with its new policy. - */ -static void -__setparam_dl(struct task_struct *p, const struct sched_attr *attr) -{ - struct sched_dl_entity *dl_se = &p->dl; - - dl_se->dl_runtime = attr->sched_runtime; - dl_se->dl_deadline = attr->sched_deadline; - dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline; - dl_se->flags = attr->sched_flags; - dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime); - - /* - * Changing the parameters of a task is 'tricky' and we're not doing - * the correct thing -- also see task_dead_dl() and switched_from_dl(). - * - * What we SHOULD do is delay the bandwidth release until the 0-lag - * point. This would include retaining the task_struct until that time - * and change dl_overflow() to not immediately decrement the current - * amount. - * - * Instead we retain the current runtime/deadline and let the new - * parameters take effect after the current reservation period lapses. - * This is safe (albeit pessimistic) because the 0-lag point is always - * before the current scheduling deadline. - * - * We can still have temporary overloads because we do not delay the - * change in bandwidth until that time; so admission control is - * not on the safe side. It does however guarantee tasks will never - * consume more than promised. - */ -} - -/* * sched_setparam() passes in -1 for its policy, to let the functions * it calls know not to change it. */ @@ -4101,59 +3953,6 @@ static void __setscheduler(struct rq *rq, struct task_struct *p, p->sched_class = &fair_sched_class; } -static void -__getparam_dl(struct task_struct *p, struct sched_attr *attr) -{ - struct sched_dl_entity *dl_se = &p->dl; - - attr->sched_priority = p->rt_priority; - attr->sched_runtime = dl_se->dl_runtime; - attr->sched_deadline = dl_se->dl_deadline; - attr->sched_period = dl_se->dl_period; - attr->sched_flags = dl_se->flags; -} - -/* - * This function validates the new parameters of a -deadline task. - * We ask for the deadline not being zero, and greater or equal - * than the runtime, as well as the period of being zero or - * greater than deadline. Furthermore, we have to be sure that - * user parameters are above the internal resolution of 1us (we - * check sched_runtime only since it is always the smaller one) and - * below 2^63 ns (we have to check both sched_deadline and - * sched_period, as the latter can be zero). - */ -static bool -__checkparam_dl(const struct sched_attr *attr) -{ - /* deadline != 0 */ - if (attr->sched_deadline == 0) - return false; - - /* - * Since we truncate DL_SCALE bits, make sure we're at least - * that big. - */ - if (attr->sched_runtime < (1ULL << DL_SCALE)) - return false; - - /* - * Since we use the MSB for wrap-around and sign issues, make - * sure it's not set (mind that period can be equal to zero). - */ - if (attr->sched_deadline & (1ULL << 63) || - attr->sched_period & (1ULL << 63)) - return false; - - /* runtime <= deadline <= period (if period != 0) */ - if ((attr->sched_period != 0 && - attr->sched_period < attr->sched_deadline) || - attr->sched_deadline < attr->sched_runtime) - return false; - - return true; -} - /* * Check the target process has a UID that matches the current process's: */ @@ -4170,19 +3969,6 @@ static bool check_same_owner(struct task_struct *p) return match; } -static bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr) -{ - struct sched_dl_entity *dl_se = &p->dl; - - if (dl_se->dl_runtime != attr->sched_runtime || - dl_se->dl_deadline != attr->sched_deadline || - dl_se->dl_period != attr->sched_period || - dl_se->flags != attr->sched_flags) - return true; - - return false; -} - static int __sched_setscheduler(struct task_struct *p, const struct sched_attr *attr, bool user, bool pi) @@ -4197,8 +3983,8 @@ static int __sched_setscheduler(struct task_struct *p, int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK; struct rq *rq; - /* May grab non-irq protected spin_locks: */ - BUG_ON(in_interrupt()); + /* The pi code expects interrupts enabled */ + BUG_ON(pi && in_interrupt()); recheck: /* Double check policy once rq lock held: */ if (policy < 0) { @@ -4211,7 +3997,8 @@ recheck: return -EINVAL; } - if (attr->sched_flags & ~(SCHED_FLAG_RESET_ON_FORK)) + if (attr->sched_flags & + ~(SCHED_FLAG_RESET_ON_FORK | SCHED_FLAG_RECLAIM)) return -EINVAL; /* @@ -4362,7 +4149,7 @@ change: * of a SCHED_DEADLINE task) we need to check if enough bandwidth * is available. */ - if ((dl_policy(policy) || dl_task(p)) && dl_overflow(p, policy, attr)) { + if ((dl_policy(policy) || dl_task(p)) && sched_dl_overflow(p, policy, attr)) { task_rq_unlock(rq, p, &rf); return -EBUSY; } @@ -5463,26 +5250,17 @@ void init_idle(struct task_struct *idle, int cpu) #endif } +#ifdef CONFIG_SMP + int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial) { - int ret = 1, trial_cpus; - struct dl_bw *cur_dl_b; - unsigned long flags; + int ret = 1; if (!cpumask_weight(cur)) return ret; - rcu_read_lock_sched(); - cur_dl_b = dl_bw_of(cpumask_any(cur)); - trial_cpus = cpumask_weight(trial); - - raw_spin_lock_irqsave(&cur_dl_b->lock, flags); - if (cur_dl_b->bw != -1 && - cur_dl_b->bw * trial_cpus < cur_dl_b->total_bw) - ret = 0; - raw_spin_unlock_irqrestore(&cur_dl_b->lock, flags); - rcu_read_unlock_sched(); + ret = dl_cpuset_cpumask_can_shrink(cur, trial); return ret; } @@ -5506,43 +5284,14 @@ int task_can_attach(struct task_struct *p, goto out; } -#ifdef CONFIG_SMP if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span, - cs_cpus_allowed)) { - unsigned int dest_cpu = cpumask_any_and(cpu_active_mask, - cs_cpus_allowed); - struct dl_bw *dl_b; - bool overflow; - int cpus; - unsigned long flags; - - rcu_read_lock_sched(); - dl_b = dl_bw_of(dest_cpu); - raw_spin_lock_irqsave(&dl_b->lock, flags); - cpus = dl_bw_cpus(dest_cpu); - overflow = __dl_overflow(dl_b, cpus, 0, p->dl.dl_bw); - if (overflow) - ret = -EBUSY; - else { - /* - * We reserve space for this task in the destination - * root_domain, as we can't fail after this point. - * We will free resources in the source root_domain - * later on (see set_cpus_allowed_dl()). - */ - __dl_add(dl_b, p->dl.dl_bw); - } - raw_spin_unlock_irqrestore(&dl_b->lock, flags); - rcu_read_unlock_sched(); + cs_cpus_allowed)) + ret = dl_task_can_attach(p, cs_cpus_allowed); - } -#endif out: return ret; } -#ifdef CONFIG_SMP - bool sched_smp_initialized __read_mostly; #ifdef CONFIG_NUMA_BALANCING @@ -5805,23 +5554,8 @@ static void cpuset_cpu_active(void) static int cpuset_cpu_inactive(unsigned int cpu) { - unsigned long flags; - struct dl_bw *dl_b; - bool overflow; - int cpus; - if (!cpuhp_tasks_frozen) { - rcu_read_lock_sched(); - dl_b = dl_bw_of(cpu); - - raw_spin_lock_irqsave(&dl_b->lock, flags); - cpus = dl_bw_cpus(cpu); - overflow = __dl_overflow(dl_b, cpus, 0, 0); - raw_spin_unlock_irqrestore(&dl_b->lock, flags); - - rcu_read_unlock_sched(); - - if (overflow) + if (dl_cpu_busy(cpu)) return -EBUSY; cpuset_update_active_cpus(); } else { @@ -5874,15 +5608,9 @@ int sched_cpu_deactivate(unsigned int cpu) * users of this state to go away such that all new such users will * observe it. * - * For CONFIG_PREEMPT we have preemptible RCU and its sync_rcu() might - * not imply sync_sched(), so wait for both. - * * Do sync before park smpboot threads to take care the rcu boost case. */ - if (IS_ENABLED(CONFIG_PREEMPT)) - synchronize_rcu_mult(call_rcu, call_rcu_sched); - else - synchronize_rcu(); + synchronize_rcu_mult(call_rcu, call_rcu_sched); if (!sched_smp_initialized) return 0; @@ -5958,7 +5686,6 @@ void __init sched_init_smp(void) cpumask_var_t non_isolated_cpus; alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL); - alloc_cpumask_var(&fallback_doms, GFP_KERNEL); sched_init_numa(); @@ -5968,7 +5695,7 @@ void __init sched_init_smp(void) * happen. */ mutex_lock(&sched_domains_mutex); - init_sched_domains(cpu_active_mask); + sched_init_domains(cpu_active_mask); cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map); if (cpumask_empty(non_isolated_cpus)) cpumask_set_cpu(smp_processor_id(), non_isolated_cpus); @@ -5984,7 +5711,6 @@ void __init sched_init_smp(void) init_sched_dl_class(); sched_init_smt(); - sched_clock_init_late(); sched_smp_initialized = true; } @@ -6000,7 +5726,6 @@ early_initcall(migration_init); void __init sched_init_smp(void) { sched_init_granularity(); - sched_clock_init_late(); } #endif /* CONFIG_SMP */ @@ -6026,28 +5751,13 @@ static struct kmem_cache *task_group_cache __read_mostly; DECLARE_PER_CPU(cpumask_var_t, load_balance_mask); DECLARE_PER_CPU(cpumask_var_t, select_idle_mask); -#define WAIT_TABLE_BITS 8 -#define WAIT_TABLE_SIZE (1 << WAIT_TABLE_BITS) -static wait_queue_head_t bit_wait_table[WAIT_TABLE_SIZE] __cacheline_aligned; - -wait_queue_head_t *bit_waitqueue(void *word, int bit) -{ - const int shift = BITS_PER_LONG == 32 ? 5 : 6; - unsigned long val = (unsigned long)word << shift | bit; - - return bit_wait_table + hash_long(val, WAIT_TABLE_BITS); -} -EXPORT_SYMBOL(bit_waitqueue); - void __init sched_init(void) { int i, j; unsigned long alloc_size = 0, ptr; sched_clock_init(); - - for (i = 0; i < WAIT_TABLE_SIZE; i++) - init_waitqueue_head(bit_wait_table + i); + wait_bit_init(); #ifdef CONFIG_FAIR_GROUP_SCHED alloc_size += 2 * nr_cpu_ids * sizeof(void **); @@ -6199,7 +5909,6 @@ void __init sched_init(void) calc_load_update = jiffies + LOAD_FREQ; #ifdef CONFIG_SMP - zalloc_cpumask_var(&sched_domains_tmpmask, GFP_NOWAIT); /* May be allocated at isolcpus cmdline parse time */ if (cpu_isolated_map == NULL) zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT); @@ -6251,8 +5960,10 @@ void ___might_sleep(const char *file, int line, int preempt_offset) if ((preempt_count_equals(preempt_offset) && !irqs_disabled() && !is_idle_task(current)) || - system_state != SYSTEM_RUNNING || oops_in_progress) + system_state == SYSTEM_BOOTING || system_state > SYSTEM_RUNNING || + oops_in_progress) return; + if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy) return; prev_jiffy = jiffies; @@ -6507,385 +6218,6 @@ void sched_move_task(struct task_struct *tsk) task_rq_unlock(rq, tsk, &rf); } -#endif /* CONFIG_CGROUP_SCHED */ - -#ifdef CONFIG_RT_GROUP_SCHED -/* - * Ensure that the real time constraints are schedulable. - */ -static DEFINE_MUTEX(rt_constraints_mutex); - -/* Must be called with tasklist_lock held */ -static inline int tg_has_rt_tasks(struct task_group *tg) -{ - struct task_struct *g, *p; - - /* - * Autogroups do not have RT tasks; see autogroup_create(). - */ - if (task_group_is_autogroup(tg)) - return 0; - - for_each_process_thread(g, p) { - if (rt_task(p) && task_group(p) == tg) - return 1; - } - - return 0; -} - -struct rt_schedulable_data { - struct task_group *tg; - u64 rt_period; - u64 rt_runtime; -}; - -static int tg_rt_schedulable(struct task_group *tg, void *data) -{ - struct rt_schedulable_data *d = data; - struct task_group *child; - unsigned long total, sum = 0; - u64 period, runtime; - - period = ktime_to_ns(tg->rt_bandwidth.rt_period); - runtime = tg->rt_bandwidth.rt_runtime; - - if (tg == d->tg) { - period = d->rt_period; - runtime = d->rt_runtime; - } - - /* - * Cannot have more runtime than the period. - */ - if (runtime > period && runtime != RUNTIME_INF) - return -EINVAL; - - /* - * Ensure we don't starve existing RT tasks. - */ - if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg)) - return -EBUSY; - - total = to_ratio(period, runtime); - - /* - * Nobody can have more than the global setting allows. - */ - if (total > to_ratio(global_rt_period(), global_rt_runtime())) - return -EINVAL; - - /* - * The sum of our children's runtime should not exceed our own. - */ - list_for_each_entry_rcu(child, &tg->children, siblings) { - period = ktime_to_ns(child->rt_bandwidth.rt_period); - runtime = child->rt_bandwidth.rt_runtime; - - if (child == d->tg) { - period = d->rt_period; - runtime = d->rt_runtime; - } - - sum += to_ratio(period, runtime); - } - - if (sum > total) - return -EINVAL; - - return 0; -} - -static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime) -{ - int ret; - - struct rt_schedulable_data data = { - .tg = tg, - .rt_period = period, - .rt_runtime = runtime, - }; - - rcu_read_lock(); - ret = walk_tg_tree(tg_rt_schedulable, tg_nop, &data); - rcu_read_unlock(); - - return ret; -} - -static int tg_set_rt_bandwidth(struct task_group *tg, - u64 rt_period, u64 rt_runtime) -{ - int i, err = 0; - - /* - * Disallowing the root group RT runtime is BAD, it would disallow the - * kernel creating (and or operating) RT threads. - */ - if (tg == &root_task_group && rt_runtime == 0) - return -EINVAL; - - /* No period doesn't make any sense. */ - if (rt_period == 0) - return -EINVAL; - - mutex_lock(&rt_constraints_mutex); - read_lock(&tasklist_lock); - err = __rt_schedulable(tg, rt_period, rt_runtime); - if (err) - goto unlock; - - raw_spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock); - tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period); - tg->rt_bandwidth.rt_runtime = rt_runtime; - - for_each_possible_cpu(i) { - struct rt_rq *rt_rq = tg->rt_rq[i]; - - raw_spin_lock(&rt_rq->rt_runtime_lock); - rt_rq->rt_runtime = rt_runtime; - raw_spin_unlock(&rt_rq->rt_runtime_lock); - } - raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock); -unlock: - read_unlock(&tasklist_lock); - mutex_unlock(&rt_constraints_mutex); - - return err; -} - -static int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us) -{ - u64 rt_runtime, rt_period; - - rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period); - rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC; - if (rt_runtime_us < 0) - rt_runtime = RUNTIME_INF; - - return tg_set_rt_bandwidth(tg, rt_period, rt_runtime); -} - -static long sched_group_rt_runtime(struct task_group *tg) -{ - u64 rt_runtime_us; - - if (tg->rt_bandwidth.rt_runtime == RUNTIME_INF) - return -1; - - rt_runtime_us = tg->rt_bandwidth.rt_runtime; - do_div(rt_runtime_us, NSEC_PER_USEC); - return rt_runtime_us; -} - -static int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us) -{ - u64 rt_runtime, rt_period; - - rt_period = rt_period_us * NSEC_PER_USEC; - rt_runtime = tg->rt_bandwidth.rt_runtime; - - return tg_set_rt_bandwidth(tg, rt_period, rt_runtime); -} - -static long sched_group_rt_period(struct task_group *tg) -{ - u64 rt_period_us; - - rt_period_us = ktime_to_ns(tg->rt_bandwidth.rt_period); - do_div(rt_period_us, NSEC_PER_USEC); - return rt_period_us; -} -#endif /* CONFIG_RT_GROUP_SCHED */ - -#ifdef CONFIG_RT_GROUP_SCHED -static int sched_rt_global_constraints(void) -{ - int ret = 0; - - mutex_lock(&rt_constraints_mutex); - read_lock(&tasklist_lock); - ret = __rt_schedulable(NULL, 0, 0); - read_unlock(&tasklist_lock); - mutex_unlock(&rt_constraints_mutex); - - return ret; -} - -static int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk) -{ - /* Don't accept realtime tasks when there is no way for them to run */ - if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0) - return 0; - - return 1; -} - -#else /* !CONFIG_RT_GROUP_SCHED */ -static int sched_rt_global_constraints(void) -{ - unsigned long flags; - int i; - - raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags); - for_each_possible_cpu(i) { - struct rt_rq *rt_rq = &cpu_rq(i)->rt; - - raw_spin_lock(&rt_rq->rt_runtime_lock); - rt_rq->rt_runtime = global_rt_runtime(); - raw_spin_unlock(&rt_rq->rt_runtime_lock); - } - raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags); - - return 0; -} -#endif /* CONFIG_RT_GROUP_SCHED */ - -static int sched_dl_global_validate(void) -{ - u64 runtime = global_rt_runtime(); - u64 period = global_rt_period(); - u64 new_bw = to_ratio(period, runtime); - struct dl_bw *dl_b; - int cpu, ret = 0; - unsigned long flags; - - /* - * Here we want to check the bandwidth not being set to some - * value smaller than the currently allocated bandwidth in - * any of the root_domains. - * - * FIXME: Cycling on all the CPUs is overdoing, but simpler than - * cycling on root_domains... Discussion on different/better - * solutions is welcome! - */ - for_each_possible_cpu(cpu) { - rcu_read_lock_sched(); - dl_b = dl_bw_of(cpu); - - raw_spin_lock_irqsave(&dl_b->lock, flags); - if (new_bw < dl_b->total_bw) - ret = -EBUSY; - raw_spin_unlock_irqrestore(&dl_b->lock, flags); - - rcu_read_unlock_sched(); - - if (ret) - break; - } - - return ret; -} - -static void sched_dl_do_global(void) -{ - u64 new_bw = -1; - struct dl_bw *dl_b; - int cpu; - unsigned long flags; - - def_dl_bandwidth.dl_period = global_rt_period(); - def_dl_bandwidth.dl_runtime = global_rt_runtime(); - - if (global_rt_runtime() != RUNTIME_INF) - new_bw = to_ratio(global_rt_period(), global_rt_runtime()); - - /* - * FIXME: As above... - */ - for_each_possible_cpu(cpu) { - rcu_read_lock_sched(); - dl_b = dl_bw_of(cpu); - - raw_spin_lock_irqsave(&dl_b->lock, flags); - dl_b->bw = new_bw; - raw_spin_unlock_irqrestore(&dl_b->lock, flags); - - rcu_read_unlock_sched(); - } -} - -static int sched_rt_global_validate(void) -{ - if (sysctl_sched_rt_period <= 0) - return -EINVAL; - - if ((sysctl_sched_rt_runtime != RUNTIME_INF) && - (sysctl_sched_rt_runtime > sysctl_sched_rt_period)) - return -EINVAL; - - return 0; -} - -static void sched_rt_do_global(void) -{ - def_rt_bandwidth.rt_runtime = global_rt_runtime(); - def_rt_bandwidth.rt_period = ns_to_ktime(global_rt_period()); -} - -int sched_rt_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos) -{ - int old_period, old_runtime; - static DEFINE_MUTEX(mutex); - int ret; - - mutex_lock(&mutex); - old_period = sysctl_sched_rt_period; - old_runtime = sysctl_sched_rt_runtime; - - ret = proc_dointvec(table, write, buffer, lenp, ppos); - - if (!ret && write) { - ret = sched_rt_global_validate(); - if (ret) - goto undo; - - ret = sched_dl_global_validate(); - if (ret) - goto undo; - - ret = sched_rt_global_constraints(); - if (ret) - goto undo; - - sched_rt_do_global(); - sched_dl_do_global(); - } - if (0) { -undo: - sysctl_sched_rt_period = old_period; - sysctl_sched_rt_runtime = old_runtime; - } - mutex_unlock(&mutex); - - return ret; -} - -int sched_rr_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos) -{ - int ret; - static DEFINE_MUTEX(mutex); - - mutex_lock(&mutex); - ret = proc_dointvec(table, write, buffer, lenp, ppos); - /* - * Make sure that internally we keep jiffies. - * Also, writing zero resets the timeslice to default: - */ - if (!ret && write) { - sched_rr_timeslice = - sysctl_sched_rr_timeslice <= 0 ? RR_TIMESLICE : - msecs_to_jiffies(sysctl_sched_rr_timeslice); - } - mutex_unlock(&mutex); - return ret; -} - -#ifdef CONFIG_CGROUP_SCHED static inline struct task_group *css_tg(struct cgroup_subsys_state *css) { diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index aea3135c5d90..67c70e287647 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -615,19 +615,13 @@ static void cputime_adjust(struct task_cputime *curr, * userspace. Once a task gets some ticks, the monotonicy code at * 'update' will ensure things converge to the observed ratio. */ - if (stime == 0) { - utime = rtime; - goto update; + if (stime != 0) { + if (utime == 0) + stime = rtime; + else + stime = scale_stime(stime, rtime, stime + utime); } - if (utime == 0) { - stime = rtime; - goto update; - } - - stime = scale_stime(stime, rtime, stime + utime); - -update: /* * Make sure stime doesn't go backwards; this preserves monotonicity * for utime because rtime is monotonic. diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index a2ce59015642..a84299f44b5d 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -17,6 +17,7 @@ #include "sched.h" #include <linux/slab.h> +#include <uapi/linux/sched/types.h> struct dl_bandwidth def_dl_bandwidth; @@ -43,6 +44,254 @@ static inline int on_dl_rq(struct sched_dl_entity *dl_se) return !RB_EMPTY_NODE(&dl_se->rb_node); } +#ifdef CONFIG_SMP +static inline struct dl_bw *dl_bw_of(int i) +{ + RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(), + "sched RCU must be held"); + return &cpu_rq(i)->rd->dl_bw; +} + +static inline int dl_bw_cpus(int i) +{ + struct root_domain *rd = cpu_rq(i)->rd; + int cpus = 0; + + RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(), + "sched RCU must be held"); + for_each_cpu_and(i, rd->span, cpu_active_mask) + cpus++; + + return cpus; +} +#else +static inline struct dl_bw *dl_bw_of(int i) +{ + return &cpu_rq(i)->dl.dl_bw; +} + +static inline int dl_bw_cpus(int i) +{ + return 1; +} +#endif + +static inline +void add_running_bw(u64 dl_bw, struct dl_rq *dl_rq) +{ + u64 old = dl_rq->running_bw; + + lockdep_assert_held(&(rq_of_dl_rq(dl_rq))->lock); + dl_rq->running_bw += dl_bw; + SCHED_WARN_ON(dl_rq->running_bw < old); /* overflow */ + SCHED_WARN_ON(dl_rq->running_bw > dl_rq->this_bw); +} + +static inline +void sub_running_bw(u64 dl_bw, struct dl_rq *dl_rq) +{ + u64 old = dl_rq->running_bw; + + lockdep_assert_held(&(rq_of_dl_rq(dl_rq))->lock); + dl_rq->running_bw -= dl_bw; + SCHED_WARN_ON(dl_rq->running_bw > old); /* underflow */ + if (dl_rq->running_bw > old) + dl_rq->running_bw = 0; +} + +static inline +void add_rq_bw(u64 dl_bw, struct dl_rq *dl_rq) +{ + u64 old = dl_rq->this_bw; + + lockdep_assert_held(&(rq_of_dl_rq(dl_rq))->lock); + dl_rq->this_bw += dl_bw; + SCHED_WARN_ON(dl_rq->this_bw < old); /* overflow */ +} + +static inline +void sub_rq_bw(u64 dl_bw, struct dl_rq *dl_rq) +{ + u64 old = dl_rq->this_bw; + + lockdep_assert_held(&(rq_of_dl_rq(dl_rq))->lock); + dl_rq->this_bw -= dl_bw; + SCHED_WARN_ON(dl_rq->this_bw > old); /* underflow */ + if (dl_rq->this_bw > old) + dl_rq->this_bw = 0; + SCHED_WARN_ON(dl_rq->running_bw > dl_rq->this_bw); +} + +void dl_change_utilization(struct task_struct *p, u64 new_bw) +{ + struct rq *rq; + + if (task_on_rq_queued(p)) + return; + + rq = task_rq(p); + if (p->dl.dl_non_contending) { + sub_running_bw(p->dl.dl_bw, &rq->dl); + p->dl.dl_non_contending = 0; + /* + * If the timer handler is currently running and the + * timer cannot be cancelled, inactive_task_timer() + * will see that dl_not_contending is not set, and + * will not touch the rq's active utilization, + * so we are still safe. + */ + if (hrtimer_try_to_cancel(&p->dl.inactive_timer) == 1) + put_task_struct(p); + } + sub_rq_bw(p->dl.dl_bw, &rq->dl); + add_rq_bw(new_bw, &rq->dl); +} + +/* + * The utilization of a task cannot be immediately removed from + * the rq active utilization (running_bw) when the task blocks. + * Instead, we have to wait for the so called "0-lag time". + * + * If a task blocks before the "0-lag time", a timer (the inactive + * timer) is armed, and running_bw is decreased when the timer + * fires. + * + * If the task wakes up again before the inactive timer fires, + * the timer is cancelled, whereas if the task wakes up after the + * inactive timer fired (and running_bw has been decreased) the + * task's utilization has to be added to running_bw again. + * A flag in the deadline scheduling entity (dl_non_contending) + * is used to avoid race conditions between the inactive timer handler + * and task wakeups. + * + * The following diagram shows how running_bw is updated. A task is + * "ACTIVE" when its utilization contributes to running_bw; an + * "ACTIVE contending" task is in the TASK_RUNNING state, while an + * "ACTIVE non contending" task is a blocked task for which the "0-lag time" + * has not passed yet. An "INACTIVE" task is a task for which the "0-lag" + * time already passed, which does not contribute to running_bw anymore. + * +------------------+ + * wakeup | ACTIVE | + * +------------------>+ contending | + * | add_running_bw | | + * | +----+------+------+ + * | | ^ + * | dequeue | | + * +--------+-------+ | | + * | | t >= 0-lag | | wakeup + * | INACTIVE |<---------------+ | + * | | sub_running_bw | | + * +--------+-------+ | | + * ^ | | + * | t < 0-lag | | + * | | | + * | V | + * | +----+------+------+ + * | sub_running_bw | ACTIVE | + * +-------------------+ | + * inactive timer | non contending | + * fired +------------------+ + * + * The task_non_contending() function is invoked when a task + * blocks, and checks if the 0-lag time already passed or + * not (in the first case, it directly updates running_bw; + * in the second case, it arms the inactive timer). + * + * The task_contending() function is invoked when a task wakes + * up, and checks if the task is still in the "ACTIVE non contending" + * state or not (in the second case, it updates running_bw). + */ +static void task_non_contending(struct task_struct *p) +{ + struct sched_dl_entity *dl_se = &p->dl; + struct hrtimer *timer = &dl_se->inactive_timer; + struct dl_rq *dl_rq = dl_rq_of_se(dl_se); + struct rq *rq = rq_of_dl_rq(dl_rq); + s64 zerolag_time; + + /* + * If this is a non-deadline task that has been boosted, + * do nothing + */ + if (dl_se->dl_runtime == 0) + return; + + WARN_ON(hrtimer_active(&dl_se->inactive_timer)); + WARN_ON(dl_se->dl_non_contending); + + zerolag_time = dl_se->deadline - + div64_long((dl_se->runtime * dl_se->dl_period), + dl_se->dl_runtime); + + /* + * Using relative times instead of the absolute "0-lag time" + * allows to simplify the code + */ + zerolag_time -= rq_clock(rq); + + /* + * If the "0-lag time" already passed, decrease the active + * utilization now, instead of starting a timer + */ + if (zerolag_time < 0) { + if (dl_task(p)) + sub_running_bw(dl_se->dl_bw, dl_rq); + if (!dl_task(p) || p->state == TASK_DEAD) { + struct dl_bw *dl_b = dl_bw_of(task_cpu(p)); + + if (p->state == TASK_DEAD) + sub_rq_bw(p->dl.dl_bw, &rq->dl); + raw_spin_lock(&dl_b->lock); + __dl_clear(dl_b, p->dl.dl_bw, dl_bw_cpus(task_cpu(p))); + __dl_clear_params(p); + raw_spin_unlock(&dl_b->lock); + } + + return; + } + + dl_se->dl_non_contending = 1; + get_task_struct(p); + hrtimer_start(timer, ns_to_ktime(zerolag_time), HRTIMER_MODE_REL); +} + +static void task_contending(struct sched_dl_entity *dl_se, int flags) +{ + struct dl_rq *dl_rq = dl_rq_of_se(dl_se); + + /* + * If this is a non-deadline task that has been boosted, + * do nothing + */ + if (dl_se->dl_runtime == 0) + return; + + if (flags & ENQUEUE_MIGRATED) + add_rq_bw(dl_se->dl_bw, dl_rq); + + if (dl_se->dl_non_contending) { + dl_se->dl_non_contending = 0; + /* + * If the timer handler is currently running and the + * timer cannot be cancelled, inactive_task_timer() + * will see that dl_not_contending is not set, and + * will not touch the rq's active utilization, + * so we are still safe. + */ + if (hrtimer_try_to_cancel(&dl_se->inactive_timer) == 1) + put_task_struct(dl_task_of(dl_se)); + } else { + /* + * Since "dl_non_contending" is not set, the + * task's utilization has already been removed from + * active utilization (either when the task blocked, + * when the "inactive timer" fired). + * So, add it back. + */ + add_running_bw(dl_se->dl_bw, dl_rq); + } +} + static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq) { struct sched_dl_entity *dl_se = &p->dl; @@ -83,6 +332,10 @@ void init_dl_rq(struct dl_rq *dl_rq) #else init_dl_bw(&dl_rq->dl_bw); #endif + + dl_rq->running_bw = 0; + dl_rq->this_bw = 0; + init_dl_rq_bw_ratio(dl_rq); } #ifdef CONFIG_SMP @@ -484,13 +737,84 @@ static bool dl_entity_overflow(struct sched_dl_entity *dl_se, } /* - * When a -deadline entity is queued back on the runqueue, its runtime and - * deadline might need updating. + * Revised wakeup rule [1]: For self-suspending tasks, rather then + * re-initializing task's runtime and deadline, the revised wakeup + * rule adjusts the task's runtime to avoid the task to overrun its + * density. + * + * Reasoning: a task may overrun the density if: + * runtime / (deadline - t) > dl_runtime / dl_deadline + * + * Therefore, runtime can be adjusted to: + * runtime = (dl_runtime / dl_deadline) * (deadline - t) + * + * In such way that runtime will be equal to the maximum density + * the task can use without breaking any rule. + * + * [1] Luca Abeni, Giuseppe Lipari, and Juri Lelli. 2015. Constant + * bandwidth server revisited. SIGBED Rev. 11, 4 (January 2015), 19-24. + */ +static void +update_dl_revised_wakeup(struct sched_dl_entity *dl_se, struct rq *rq) +{ + u64 laxity = dl_se->deadline - rq_clock(rq); + + /* + * If the task has deadline < period, and the deadline is in the past, + * it should already be throttled before this check. + * + * See update_dl_entity() comments for further details. + */ + WARN_ON(dl_time_before(dl_se->deadline, rq_clock(rq))); + + dl_se->runtime = (dl_se->dl_density * laxity) >> BW_SHIFT; +} + +/* + * Regarding the deadline, a task with implicit deadline has a relative + * deadline == relative period. A task with constrained deadline has a + * relative deadline <= relative period. + * + * We support constrained deadline tasks. However, there are some restrictions + * applied only for tasks which do not have an implicit deadline. See + * update_dl_entity() to know more about such restrictions. + * + * The dl_is_implicit() returns true if the task has an implicit deadline. + */ +static inline bool dl_is_implicit(struct sched_dl_entity *dl_se) +{ + return dl_se->dl_deadline == dl_se->dl_period; +} + +/* + * When a deadline entity is placed in the runqueue, its runtime and deadline + * might need to be updated. This is done by a CBS wake up rule. There are two + * different rules: 1) the original CBS; and 2) the Revisited CBS. + * + * When the task is starting a new period, the Original CBS is used. In this + * case, the runtime is replenished and a new absolute deadline is set. + * + * When a task is queued before the begin of the next period, using the + * remaining runtime and deadline could make the entity to overflow, see + * dl_entity_overflow() to find more about runtime overflow. When such case + * is detected, the runtime and deadline need to be updated. + * + * If the task has an implicit deadline, i.e., deadline == period, the Original + * CBS is applied. the runtime is replenished and a new absolute deadline is + * set, as in the previous cases. + * + * However, the Original CBS does not work properly for tasks with + * deadline < period, which are said to have a constrained deadline. By + * applying the Original CBS, a constrained deadline task would be able to run + * runtime/deadline in a period. With deadline < period, the task would + * overrun the runtime/period allowed bandwidth, breaking the admission test. * - * The policy here is that we update the deadline of the entity only if: - * - the current deadline is in the past, - * - using the remaining runtime with the current deadline would make - * the entity exceed its bandwidth. + * In order to prevent this misbehave, the Revisited CBS is used for + * constrained deadline tasks when a runtime overflow is detected. In the + * Revisited CBS, rather than replenishing & setting a new absolute deadline, + * the remaining runtime of the task is reduced to avoid runtime overflow. + * Please refer to the comments update_dl_revised_wakeup() function to find + * more about the Revised CBS rule. */ static void update_dl_entity(struct sched_dl_entity *dl_se, struct sched_dl_entity *pi_se) @@ -500,6 +824,14 @@ static void update_dl_entity(struct sched_dl_entity *dl_se, if (dl_time_before(dl_se->deadline, rq_clock(rq)) || dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) { + + if (unlikely(!dl_is_implicit(dl_se) && + !dl_time_before(dl_se->deadline, rq_clock(rq)) && + !dl_se->dl_boosted)){ + update_dl_revised_wakeup(dl_se, rq); + return; + } + dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; dl_se->runtime = pi_se->dl_runtime; } @@ -593,10 +925,8 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) * The task might have changed its scheduling policy to something * different than SCHED_DEADLINE (through switched_from_dl()). */ - if (!dl_task(p)) { - __dl_clear_params(p); + if (!dl_task(p)) goto unlock; - } /* * The task might have been boosted by someone else and might be in the @@ -723,6 +1053,8 @@ static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se) if (unlikely(dl_se->dl_boosted || !start_dl_timer(p))) return; dl_se->dl_throttled = 1; + if (dl_se->runtime > 0) + dl_se->runtime = 0; } } @@ -735,6 +1067,47 @@ int dl_runtime_exceeded(struct sched_dl_entity *dl_se) extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq); /* + * This function implements the GRUB accounting rule: + * according to the GRUB reclaiming algorithm, the runtime is + * not decreased as "dq = -dt", but as + * "dq = -max{u / Umax, (1 - Uinact - Uextra)} dt", + * where u is the utilization of the task, Umax is the maximum reclaimable + * utilization, Uinact is the (per-runqueue) inactive utilization, computed + * as the difference between the "total runqueue utilization" and the + * runqueue active utilization, and Uextra is the (per runqueue) extra + * reclaimable utilization. + * Since rq->dl.running_bw and rq->dl.this_bw contain utilizations + * multiplied by 2^BW_SHIFT, the result has to be shifted right by + * BW_SHIFT. + * Since rq->dl.bw_ratio contains 1 / Umax multipled by 2^RATIO_SHIFT, + * dl_bw is multiped by rq->dl.bw_ratio and shifted right by RATIO_SHIFT. + * Since delta is a 64 bit variable, to have an overflow its value + * should be larger than 2^(64 - 20 - 8), which is more than 64 seconds. + * So, overflow is not an issue here. + */ +u64 grub_reclaim(u64 delta, struct rq *rq, struct sched_dl_entity *dl_se) +{ + u64 u_inact = rq->dl.this_bw - rq->dl.running_bw; /* Utot - Uact */ + u64 u_act; + u64 u_act_min = (dl_se->dl_bw * rq->dl.bw_ratio) >> RATIO_SHIFT; + + /* + * Instead of computing max{u * bw_ratio, (1 - u_inact - u_extra)}, + * we compare u_inact + rq->dl.extra_bw with + * 1 - (u * rq->dl.bw_ratio >> RATIO_SHIFT), because + * u_inact + rq->dl.extra_bw can be larger than + * 1 * (so, 1 - u_inact - rq->dl.extra_bw would be negative + * leading to wrong results) + */ + if (u_inact + rq->dl.extra_bw > BW_UNIT - u_act_min) + u_act = u_act_min; + else + u_act = BW_UNIT - u_inact - rq->dl.extra_bw; + + return (delta * u_act) >> BW_SHIFT; +} + +/* * Update the current task's runtime statistics (provided it is still * a -deadline task and has not been removed from the dl_rq). */ @@ -776,6 +1149,8 @@ static void update_curr_dl(struct rq *rq) sched_rt_avg_update(rq, delta_exec); + if (unlikely(dl_se->flags & SCHED_FLAG_RECLAIM)) + delta_exec = grub_reclaim(delta_exec, rq, &curr->dl); dl_se->runtime -= delta_exec; throttle: @@ -815,6 +1190,56 @@ throttle: } } +static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer) +{ + struct sched_dl_entity *dl_se = container_of(timer, + struct sched_dl_entity, + inactive_timer); + struct task_struct *p = dl_task_of(dl_se); + struct rq_flags rf; + struct rq *rq; + + rq = task_rq_lock(p, &rf); + + if (!dl_task(p) || p->state == TASK_DEAD) { + struct dl_bw *dl_b = dl_bw_of(task_cpu(p)); + + if (p->state == TASK_DEAD && dl_se->dl_non_contending) { + sub_running_bw(p->dl.dl_bw, dl_rq_of_se(&p->dl)); + sub_rq_bw(p->dl.dl_bw, dl_rq_of_se(&p->dl)); + dl_se->dl_non_contending = 0; + } + + raw_spin_lock(&dl_b->lock); + __dl_clear(dl_b, p->dl.dl_bw, dl_bw_cpus(task_cpu(p))); + raw_spin_unlock(&dl_b->lock); + __dl_clear_params(p); + + goto unlock; + } + if (dl_se->dl_non_contending == 0) + goto unlock; + + sched_clock_tick(); + update_rq_clock(rq); + + sub_running_bw(dl_se->dl_bw, &rq->dl); + dl_se->dl_non_contending = 0; +unlock: + task_rq_unlock(rq, p, &rf); + put_task_struct(p); + + return HRTIMER_NORESTART; +} + +void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se) +{ + struct hrtimer *timer = &dl_se->inactive_timer; + + hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + timer->function = inactive_task_timer; +} + #ifdef CONFIG_SMP static void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline) @@ -946,10 +1371,12 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, * parameters of the task might need updating. Otherwise, * we want a replenishment of its runtime. */ - if (flags & ENQUEUE_WAKEUP) + if (flags & ENQUEUE_WAKEUP) { + task_contending(dl_se, flags); update_dl_entity(dl_se, pi_se); - else if (flags & ENQUEUE_REPLENISH) + } else if (flags & ENQUEUE_REPLENISH) { replenish_dl_entity(dl_se, pi_se); + } __enqueue_dl_entity(dl_se); } @@ -959,11 +1386,6 @@ static void dequeue_dl_entity(struct sched_dl_entity *dl_se) __dequeue_dl_entity(dl_se); } -static inline bool dl_is_constrained(struct sched_dl_entity *dl_se) -{ - return dl_se->dl_deadline < dl_se->dl_period; -} - static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) { struct task_struct *pi_task = rt_mutex_get_top_task(p); @@ -995,17 +1417,32 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) * If that is the case, the task will be throttled and * the replenishment timer will be set to the next period. */ - if (!p->dl.dl_throttled && dl_is_constrained(&p->dl)) + if (!p->dl.dl_throttled && !dl_is_implicit(&p->dl)) dl_check_constrained_dl(&p->dl); + if (p->on_rq == TASK_ON_RQ_MIGRATING || flags & ENQUEUE_RESTORE) { + add_rq_bw(p->dl.dl_bw, &rq->dl); + add_running_bw(p->dl.dl_bw, &rq->dl); + } + /* - * If p is throttled, we do nothing. In fact, if it exhausted + * If p is throttled, we do not enqueue it. In fact, if it exhausted * its budget it needs a replenishment and, since it now is on * its rq, the bandwidth timer callback (which clearly has not * run yet) will take care of this. + * However, the active utilization does not depend on the fact + * that the task is on the runqueue or not (but depends on the + * task's state - in GRUB parlance, "inactive" vs "active contending"). + * In other words, even if a task is throttled its utilization must + * be counted in the active utilization; hence, we need to call + * add_running_bw(). */ - if (p->dl.dl_throttled && !(flags & ENQUEUE_REPLENISH)) + if (p->dl.dl_throttled && !(flags & ENQUEUE_REPLENISH)) { + if (flags & ENQUEUE_WAKEUP) + task_contending(&p->dl, flags); + return; + } enqueue_dl_entity(&p->dl, pi_se, flags); @@ -1023,6 +1460,23 @@ static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags) { update_curr_dl(rq); __dequeue_task_dl(rq, p, flags); + + if (p->on_rq == TASK_ON_RQ_MIGRATING || flags & DEQUEUE_SAVE) { + sub_running_bw(p->dl.dl_bw, &rq->dl); + sub_rq_bw(p->dl.dl_bw, &rq->dl); + } + + /* + * This check allows to start the inactive timer (or to immediately + * decrease the active utilization, if needed) in two cases: + * when the task blocks and when it is terminating + * (p->state == TASK_DEAD). We can handle the two cases in the same + * way, because from GRUB's point of view the same thing is happening + * (the task moves from "active contending" to "active non contending" + * or "inactive") + */ + if (flags & DEQUEUE_SLEEP) + task_non_contending(p); } /* @@ -1100,6 +1554,37 @@ out: return cpu; } +static void migrate_task_rq_dl(struct task_struct *p) +{ + struct rq *rq; + + if (p->state != TASK_WAKING) + return; + + rq = task_rq(p); + /* + * Since p->state == TASK_WAKING, set_task_cpu() has been called + * from try_to_wake_up(). Hence, p->pi_lock is locked, but + * rq->lock is not... So, lock it + */ + raw_spin_lock(&rq->lock); + if (p->dl.dl_non_contending) { + sub_running_bw(p->dl.dl_bw, &rq->dl); + p->dl.dl_non_contending = 0; + /* + * If the timer handler is currently running and the + * timer cannot be cancelled, inactive_task_timer() + * will see that dl_not_contending is not set, and + * will not touch the rq's active utilization, + * so we are still safe. + */ + if (hrtimer_try_to_cancel(&p->dl.inactive_timer) == 1) + put_task_struct(p); + } + sub_rq_bw(p->dl.dl_bw, &rq->dl); + raw_spin_unlock(&rq->lock); +} + static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p) { /* @@ -1255,19 +1740,6 @@ static void task_fork_dl(struct task_struct *p) */ } -static void task_dead_dl(struct task_struct *p) -{ - struct dl_bw *dl_b = dl_bw_of(task_cpu(p)); - - /* - * Since we are TASK_DEAD we won't slip out of the domain! - */ - raw_spin_lock_irq(&dl_b->lock); - /* XXX we should retain the bw until 0-lag */ - dl_b->total_bw -= p->dl.dl_bw; - raw_spin_unlock_irq(&dl_b->lock); -} - static void set_curr_task_dl(struct rq *rq) { struct task_struct *p = rq->curr; @@ -1533,7 +2005,7 @@ retry: * then possible that next_task has migrated. */ task = pick_next_pushable_dl_task(rq); - if (task_cpu(next_task) == rq->cpu && task == next_task) { + if (task == next_task) { /* * The task is still there. We don't try * again, some other cpu will pull it when ready. @@ -1551,7 +2023,11 @@ retry: } deactivate_task(rq, next_task, 0); + sub_running_bw(next_task->dl.dl_bw, &rq->dl); + sub_rq_bw(next_task->dl.dl_bw, &rq->dl); set_task_cpu(next_task, later_rq->cpu); + add_rq_bw(next_task->dl.dl_bw, &later_rq->dl); + add_running_bw(next_task->dl.dl_bw, &later_rq->dl); activate_task(later_rq, next_task, 0); ret = 1; @@ -1639,7 +2115,11 @@ static void pull_dl_task(struct rq *this_rq) resched = true; deactivate_task(src_rq, p, 0); + sub_running_bw(p->dl.dl_bw, &src_rq->dl); + sub_rq_bw(p->dl.dl_bw, &src_rq->dl); set_task_cpu(p, this_cpu); + add_rq_bw(p->dl.dl_bw, &this_rq->dl); + add_running_bw(p->dl.dl_bw, &this_rq->dl); activate_task(this_rq, p, 0); dmin = p->dl.deadline; @@ -1695,7 +2175,7 @@ static void set_cpus_allowed_dl(struct task_struct *p, * until we complete the update. */ raw_spin_lock(&src_dl_b->lock); - __dl_clear(src_dl_b, p->dl.dl_bw); + __dl_clear(src_dl_b, p->dl.dl_bw, dl_bw_cpus(task_cpu(p))); raw_spin_unlock(&src_dl_b->lock); } @@ -1737,13 +2217,26 @@ void __init init_sched_dl_class(void) static void switched_from_dl(struct rq *rq, struct task_struct *p) { /* - * Start the deadline timer; if we switch back to dl before this we'll - * continue consuming our current CBS slice. If we stay outside of - * SCHED_DEADLINE until the deadline passes, the timer will reset the - * task. + * task_non_contending() can start the "inactive timer" (if the 0-lag + * time is in the future). If the task switches back to dl before + * the "inactive timer" fires, it can continue to consume its current + * runtime using its current deadline. If it stays outside of + * SCHED_DEADLINE until the 0-lag time passes, inactive_task_timer() + * will reset the task parameters. */ - if (!start_dl_timer(p)) - __dl_clear_params(p); + if (task_on_rq_queued(p) && p->dl.dl_runtime) + task_non_contending(p); + + if (!task_on_rq_queued(p)) + sub_rq_bw(p->dl.dl_bw, &rq->dl); + + /* + * We cannot use inactive_task_timer() to invoke sub_running_bw() + * at the 0-lag time, because the task could have been migrated + * while SCHED_OTHER in the meanwhile. + */ + if (p->dl.dl_non_contending) + p->dl.dl_non_contending = 0; /* * Since this might be the only -deadline task on the rq, @@ -1762,11 +2255,15 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p) */ static void switched_to_dl(struct rq *rq, struct task_struct *p) { + if (hrtimer_try_to_cancel(&p->dl.inactive_timer) == 1) + put_task_struct(p); /* If p is not queued we will update its parameters at next wakeup. */ - if (!task_on_rq_queued(p)) - return; + if (!task_on_rq_queued(p)) { + add_rq_bw(p->dl.dl_bw, &rq->dl); + return; + } /* * If p is boosted we already updated its params in * rt_mutex_setprio()->enqueue_task(..., ENQUEUE_REPLENISH), @@ -1836,6 +2333,7 @@ const struct sched_class dl_sched_class = { #ifdef CONFIG_SMP .select_task_rq = select_task_rq_dl, + .migrate_task_rq = migrate_task_rq_dl, .set_cpus_allowed = set_cpus_allowed_dl, .rq_online = rq_online_dl, .rq_offline = rq_offline_dl, @@ -1845,7 +2343,6 @@ const struct sched_class dl_sched_class = { .set_curr_task = set_curr_task_dl, .task_tick = task_tick_dl, .task_fork = task_fork_dl, - .task_dead = task_dead_dl, .prio_changed = prio_changed_dl, .switched_from = switched_from_dl, @@ -1854,6 +2351,317 @@ const struct sched_class dl_sched_class = { .update_curr = update_curr_dl, }; +int sched_dl_global_validate(void) +{ + u64 runtime = global_rt_runtime(); + u64 period = global_rt_period(); + u64 new_bw = to_ratio(period, runtime); + struct dl_bw *dl_b; + int cpu, ret = 0; + unsigned long flags; + + /* + * Here we want to check the bandwidth not being set to some + * value smaller than the currently allocated bandwidth in + * any of the root_domains. + * + * FIXME: Cycling on all the CPUs is overdoing, but simpler than + * cycling on root_domains... Discussion on different/better + * solutions is welcome! + */ + for_each_possible_cpu(cpu) { + rcu_read_lock_sched(); + dl_b = dl_bw_of(cpu); + + raw_spin_lock_irqsave(&dl_b->lock, flags); + if (new_bw < dl_b->total_bw) + ret = -EBUSY; + raw_spin_unlock_irqrestore(&dl_b->lock, flags); + + rcu_read_unlock_sched(); + + if (ret) + break; + } + + return ret; +} + +void init_dl_rq_bw_ratio(struct dl_rq *dl_rq) +{ + if (global_rt_runtime() == RUNTIME_INF) { + dl_rq->bw_ratio = 1 << RATIO_SHIFT; + dl_rq->extra_bw = 1 << BW_SHIFT; + } else { + dl_rq->bw_ratio = to_ratio(global_rt_runtime(), + global_rt_period()) >> (BW_SHIFT - RATIO_SHIFT); + dl_rq->extra_bw = to_ratio(global_rt_period(), + global_rt_runtime()); + } +} + +void sched_dl_do_global(void) +{ + u64 new_bw = -1; + struct dl_bw *dl_b; + int cpu; + unsigned long flags; + + def_dl_bandwidth.dl_period = global_rt_period(); + def_dl_bandwidth.dl_runtime = global_rt_runtime(); + + if (global_rt_runtime() != RUNTIME_INF) + new_bw = to_ratio(global_rt_period(), global_rt_runtime()); + + /* + * FIXME: As above... + */ + for_each_possible_cpu(cpu) { + rcu_read_lock_sched(); + dl_b = dl_bw_of(cpu); + + raw_spin_lock_irqsave(&dl_b->lock, flags); + dl_b->bw = new_bw; + raw_spin_unlock_irqrestore(&dl_b->lock, flags); + + rcu_read_unlock_sched(); + init_dl_rq_bw_ratio(&cpu_rq(cpu)->dl); + } +} + +/* + * We must be sure that accepting a new task (or allowing changing the + * parameters of an existing one) is consistent with the bandwidth + * constraints. If yes, this function also accordingly updates the currently + * allocated bandwidth to reflect the new situation. + * + * This function is called while holding p's rq->lock. + */ +int sched_dl_overflow(struct task_struct *p, int policy, + const struct sched_attr *attr) +{ + struct dl_bw *dl_b = dl_bw_of(task_cpu(p)); + u64 period = attr->sched_period ?: attr->sched_deadline; + u64 runtime = attr->sched_runtime; + u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0; + int cpus, err = -1; + + /* !deadline task may carry old deadline bandwidth */ + if (new_bw == p->dl.dl_bw && task_has_dl_policy(p)) + return 0; + + /* + * Either if a task, enters, leave, or stays -deadline but changes + * its parameters, we may need to update accordingly the total + * allocated bandwidth of the container. + */ + raw_spin_lock(&dl_b->lock); + cpus = dl_bw_cpus(task_cpu(p)); + if (dl_policy(policy) && !task_has_dl_policy(p) && + !__dl_overflow(dl_b, cpus, 0, new_bw)) { + if (hrtimer_active(&p->dl.inactive_timer)) + __dl_clear(dl_b, p->dl.dl_bw, cpus); + __dl_add(dl_b, new_bw, cpus); + err = 0; + } else if (dl_policy(policy) && task_has_dl_policy(p) && + !__dl_overflow(dl_b, cpus, p->dl.dl_bw, new_bw)) { + /* + * XXX this is slightly incorrect: when the task + * utilization decreases, we should delay the total + * utilization change until the task's 0-lag point. + * But this would require to set the task's "inactive + * timer" when the task is not inactive. + */ + __dl_clear(dl_b, p->dl.dl_bw, cpus); + __dl_add(dl_b, new_bw, cpus); + dl_change_utilization(p, new_bw); + err = 0; + } else if (!dl_policy(policy) && task_has_dl_policy(p)) { + /* + * Do not decrease the total deadline utilization here, + * switched_from_dl() will take care to do it at the correct + * (0-lag) time. + */ + err = 0; + } + raw_spin_unlock(&dl_b->lock); + + return err; +} + +/* + * This function initializes the sched_dl_entity of a newly becoming + * SCHED_DEADLINE task. + * + * Only the static values are considered here, the actual runtime and the + * absolute deadline will be properly calculated when the task is enqueued + * for the first time with its new policy. + */ +void __setparam_dl(struct task_struct *p, const struct sched_attr *attr) +{ + struct sched_dl_entity *dl_se = &p->dl; + + dl_se->dl_runtime = attr->sched_runtime; + dl_se->dl_deadline = attr->sched_deadline; + dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline; + dl_se->flags = attr->sched_flags; + dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime); + dl_se->dl_density = to_ratio(dl_se->dl_deadline, dl_se->dl_runtime); +} + +void __getparam_dl(struct task_struct *p, struct sched_attr *attr) +{ + struct sched_dl_entity *dl_se = &p->dl; + + attr->sched_priority = p->rt_priority; + attr->sched_runtime = dl_se->dl_runtime; + attr->sched_deadline = dl_se->dl_deadline; + attr->sched_period = dl_se->dl_period; + attr->sched_flags = dl_se->flags; +} + +/* + * This function validates the new parameters of a -deadline task. + * We ask for the deadline not being zero, and greater or equal + * than the runtime, as well as the period of being zero or + * greater than deadline. Furthermore, we have to be sure that + * user parameters are above the internal resolution of 1us (we + * check sched_runtime only since it is always the smaller one) and + * below 2^63 ns (we have to check both sched_deadline and + * sched_period, as the latter can be zero). + */ +bool __checkparam_dl(const struct sched_attr *attr) +{ + /* deadline != 0 */ + if (attr->sched_deadline == 0) + return false; + + /* + * Since we truncate DL_SCALE bits, make sure we're at least + * that big. + */ + if (attr->sched_runtime < (1ULL << DL_SCALE)) + return false; + + /* + * Since we use the MSB for wrap-around and sign issues, make + * sure it's not set (mind that period can be equal to zero). + */ + if (attr->sched_deadline & (1ULL << 63) || + attr->sched_period & (1ULL << 63)) + return false; + + /* runtime <= deadline <= period (if period != 0) */ + if ((attr->sched_period != 0 && + attr->sched_period < attr->sched_deadline) || + attr->sched_deadline < attr->sched_runtime) + return false; + + return true; +} + +/* + * This function clears the sched_dl_entity static params. + */ +void __dl_clear_params(struct task_struct *p) +{ + struct sched_dl_entity *dl_se = &p->dl; + + dl_se->dl_runtime = 0; + dl_se->dl_deadline = 0; + dl_se->dl_period = 0; + dl_se->flags = 0; + dl_se->dl_bw = 0; + dl_se->dl_density = 0; + + dl_se->dl_throttled = 0; + dl_se->dl_yielded = 0; + dl_se->dl_non_contending = 0; +} + +bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr) +{ + struct sched_dl_entity *dl_se = &p->dl; + + if (dl_se->dl_runtime != attr->sched_runtime || + dl_se->dl_deadline != attr->sched_deadline || + dl_se->dl_period != attr->sched_period || + dl_se->flags != attr->sched_flags) + return true; + + return false; +} + +#ifdef CONFIG_SMP +int dl_task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed) +{ + unsigned int dest_cpu = cpumask_any_and(cpu_active_mask, + cs_cpus_allowed); + struct dl_bw *dl_b; + bool overflow; + int cpus, ret; + unsigned long flags; + + rcu_read_lock_sched(); + dl_b = dl_bw_of(dest_cpu); + raw_spin_lock_irqsave(&dl_b->lock, flags); + cpus = dl_bw_cpus(dest_cpu); + overflow = __dl_overflow(dl_b, cpus, 0, p->dl.dl_bw); + if (overflow) + ret = -EBUSY; + else { + /* + * We reserve space for this task in the destination + * root_domain, as we can't fail after this point. + * We will free resources in the source root_domain + * later on (see set_cpus_allowed_dl()). + */ + __dl_add(dl_b, p->dl.dl_bw, cpus); + ret = 0; + } + raw_spin_unlock_irqrestore(&dl_b->lock, flags); + rcu_read_unlock_sched(); + return ret; +} + +int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, + const struct cpumask *trial) +{ + int ret = 1, trial_cpus; + struct dl_bw *cur_dl_b; + unsigned long flags; + + rcu_read_lock_sched(); + cur_dl_b = dl_bw_of(cpumask_any(cur)); + trial_cpus = cpumask_weight(trial); + + raw_spin_lock_irqsave(&cur_dl_b->lock, flags); + if (cur_dl_b->bw != -1 && + cur_dl_b->bw * trial_cpus < cur_dl_b->total_bw) + ret = 0; + raw_spin_unlock_irqrestore(&cur_dl_b->lock, flags); + rcu_read_unlock_sched(); + return ret; +} + +bool dl_cpu_busy(unsigned int cpu) +{ + unsigned long flags; + struct dl_bw *dl_b; + bool overflow; + int cpus; + + rcu_read_lock_sched(); + dl_b = dl_bw_of(cpu); + raw_spin_lock_irqsave(&dl_b->lock, flags); + cpus = dl_bw_cpus(cpu); + overflow = __dl_overflow(dl_b, cpus, 0, 0); + raw_spin_unlock_irqrestore(&dl_b->lock, flags); + rcu_read_unlock_sched(); + return overflow; +} +#endif + #ifdef CONFIG_SCHED_DEBUG extern void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq); diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 38f019324f1a..4fa66de52bd6 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -552,15 +552,21 @@ void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq) #define P(x) \ SEQ_printf(m, " .%-30s: %Ld\n", #x, (long long)(rt_rq->x)) +#define PU(x) \ + SEQ_printf(m, " .%-30s: %lu\n", #x, (unsigned long)(rt_rq->x)) #define PN(x) \ SEQ_printf(m, " .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rt_rq->x)) - P(rt_nr_running); + PU(rt_nr_running); +#ifdef CONFIG_SMP + PU(rt_nr_migratory); +#endif P(rt_throttled); PN(rt_time); PN(rt_runtime); #undef PN +#undef PU #undef P } @@ -569,14 +575,21 @@ void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq) struct dl_bw *dl_bw; SEQ_printf(m, "\ndl_rq[%d]:\n", cpu); - SEQ_printf(m, " .%-30s: %ld\n", "dl_nr_running", dl_rq->dl_nr_running); + +#define PU(x) \ + SEQ_printf(m, " .%-30s: %lu\n", #x, (unsigned long)(dl_rq->x)) + + PU(dl_nr_running); #ifdef CONFIG_SMP + PU(dl_nr_migratory); dl_bw = &cpu_rq(cpu)->rd->dl_bw; #else dl_bw = &dl_rq->dl_bw; #endif SEQ_printf(m, " .%-30s: %lld\n", "dl_bw->bw", dl_bw->bw); SEQ_printf(m, " .%-30s: %lld\n", "dl_bw->total_bw", dl_bw->total_bw); + +#undef PU } extern __read_mostly int sched_clock_running; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index c77e4b1d51c0..008c514dc241 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -369,8 +369,9 @@ static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq) } /* Iterate thr' all leaf cfs_rq's on a runqueue */ -#define for_each_leaf_cfs_rq(rq, cfs_rq) \ - list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list) +#define for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos) \ + list_for_each_entry_safe(cfs_rq, pos, &rq->leaf_cfs_rq_list, \ + leaf_cfs_rq_list) /* Do the two (enqueued) entities belong to the same group ? */ static inline struct cfs_rq * @@ -463,8 +464,8 @@ static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq) { } -#define for_each_leaf_cfs_rq(rq, cfs_rq) \ - for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL) +#define for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos) \ + for (cfs_rq = &rq->cfs, pos = NULL; cfs_rq; cfs_rq = pos) static inline struct sched_entity *parent_entity(struct sched_entity *se) { @@ -1381,7 +1382,6 @@ static unsigned long weighted_cpuload(const int cpu); static unsigned long source_load(int cpu, int type); static unsigned long target_load(int cpu, int type); static unsigned long capacity_of(int cpu); -static long effective_load(struct task_group *tg, int cpu, long wl, long wg); /* Cached statistics for all CPUs within a node */ struct numa_stats { @@ -2469,7 +2469,8 @@ void task_numa_work(struct callback_head *work) return; - down_read(&mm->mmap_sem); + if (!down_read_trylock(&mm->mmap_sem)) + return; vma = find_vma(mm, start); if (!vma) { reset_ptenuma_scan(p); @@ -2584,6 +2585,60 @@ void task_tick_numa(struct rq *rq, struct task_struct *curr) } } } + +/* + * Can a task be moved from prev_cpu to this_cpu without causing a load + * imbalance that would trigger the load balancer? + */ +static inline bool numa_wake_affine(struct sched_domain *sd, + struct task_struct *p, int this_cpu, + int prev_cpu, int sync) +{ + struct numa_stats prev_load, this_load; + s64 this_eff_load, prev_eff_load; + + update_numa_stats(&prev_load, cpu_to_node(prev_cpu)); + update_numa_stats(&this_load, cpu_to_node(this_cpu)); + + /* + * If sync wakeup then subtract the (maximum possible) + * effect of the currently running task from the load + * of the current CPU: + */ + if (sync) { + unsigned long current_load = task_h_load(current); + + if (this_load.load > current_load) + this_load.load -= current_load; + else + this_load.load = 0; + } + + /* + * In low-load situations, where this_cpu's node is idle due to the + * sync cause above having dropped this_load.load to 0, move the task. + * Moving to an idle socket will not create a bad imbalance. + * + * Otherwise check if the nodes are near enough in load to allow this + * task to be woken on this_cpu's node. + */ + if (this_load.load > 0) { + unsigned long task_load = task_h_load(p); + + this_eff_load = 100; + this_eff_load *= prev_load.compute_capacity; + + prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2; + prev_eff_load *= this_load.compute_capacity; + + this_eff_load *= this_load.load + task_load; + prev_eff_load *= prev_load.load - task_load; + + return this_eff_load <= prev_eff_load; + } + + return true; +} #else static void task_tick_numa(struct rq *rq, struct task_struct *curr) { @@ -2596,6 +2651,15 @@ static inline void account_numa_enqueue(struct rq *rq, struct task_struct *p) static inline void account_numa_dequeue(struct rq *rq, struct task_struct *p) { } + +#ifdef CONFIG_SMP +static inline bool numa_wake_affine(struct sched_domain *sd, + struct task_struct *p, int this_cpu, + int prev_cpu, int sync) +{ + return true; +} +#endif /* !SMP */ #endif /* CONFIG_NUMA_BALANCING */ static void @@ -2916,12 +2980,12 @@ ___update_load_avg(u64 now, int cpu, struct sched_avg *sa, /* * Step 2: update *_avg. */ - sa->load_avg = div_u64(sa->load_sum, LOAD_AVG_MAX); + sa->load_avg = div_u64(sa->load_sum, LOAD_AVG_MAX - 1024 + sa->period_contrib); if (cfs_rq) { cfs_rq->runnable_load_avg = - div_u64(cfs_rq->runnable_load_sum, LOAD_AVG_MAX); + div_u64(cfs_rq->runnable_load_sum, LOAD_AVG_MAX - 1024 + sa->period_contrib); } - sa->util_avg = sa->util_sum / LOAD_AVG_MAX; + sa->util_avg = sa->util_sum / (LOAD_AVG_MAX - 1024 + sa->period_contrib); return 1; } @@ -2982,8 +3046,7 @@ __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq) * differential update where we store the last value we propagated. This in * turn allows skipping updates if the differential is 'small'. * - * Updating tg's load_avg is necessary before update_cfs_share() (which is - * done) and effective_load() (which is not done because it is too costly). + * Updating tg's load_avg is necessary before update_cfs_share(). */ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) { @@ -4642,24 +4705,43 @@ static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) hrtimer_cancel(&cfs_b->slack_timer); } +/* + * Both these cpu hotplug callbacks race against unregister_fair_sched_group() + * + * The race is harmless, since modifying bandwidth settings of unhooked group + * bits doesn't do much. + */ + +/* cpu online calback */ static void __maybe_unused update_runtime_enabled(struct rq *rq) { - struct cfs_rq *cfs_rq; + struct task_group *tg; - for_each_leaf_cfs_rq(rq, cfs_rq) { - struct cfs_bandwidth *cfs_b = &cfs_rq->tg->cfs_bandwidth; + lockdep_assert_held(&rq->lock); + + rcu_read_lock(); + list_for_each_entry_rcu(tg, &task_groups, list) { + struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth; + struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)]; raw_spin_lock(&cfs_b->lock); cfs_rq->runtime_enabled = cfs_b->quota != RUNTIME_INF; raw_spin_unlock(&cfs_b->lock); } + rcu_read_unlock(); } +/* cpu offline callback */ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq) { - struct cfs_rq *cfs_rq; + struct task_group *tg; + + lockdep_assert_held(&rq->lock); + + rcu_read_lock(); + list_for_each_entry_rcu(tg, &task_groups, list) { + struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)]; - for_each_leaf_cfs_rq(rq, cfs_rq) { if (!cfs_rq->runtime_enabled) continue; @@ -4677,6 +4759,7 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq) if (cfs_rq_throttled(cfs_rq)) unthrottle_cfs_rq(cfs_rq); } + rcu_read_unlock(); } #else /* CONFIG_CFS_BANDWIDTH */ @@ -5215,126 +5298,6 @@ static unsigned long cpu_avg_load_per_task(int cpu) return 0; } -#ifdef CONFIG_FAIR_GROUP_SCHED -/* - * effective_load() calculates the load change as seen from the root_task_group - * - * Adding load to a group doesn't make a group heavier, but can cause movement - * of group shares between cpus. Assuming the shares were perfectly aligned one - * can calculate the shift in shares. - * - * Calculate the effective load difference if @wl is added (subtracted) to @tg - * on this @cpu and results in a total addition (subtraction) of @wg to the - * total group weight. - * - * Given a runqueue weight distribution (rw_i) we can compute a shares - * distribution (s_i) using: - * - * s_i = rw_i / \Sum rw_j (1) - * - * Suppose we have 4 CPUs and our @tg is a direct child of the root group and - * has 7 equal weight tasks, distributed as below (rw_i), with the resulting - * shares distribution (s_i): - * - * rw_i = { 2, 4, 1, 0 } - * s_i = { 2/7, 4/7, 1/7, 0 } - * - * As per wake_affine() we're interested in the load of two CPUs (the CPU the - * task used to run on and the CPU the waker is running on), we need to - * compute the effect of waking a task on either CPU and, in case of a sync - * wakeup, compute the effect of the current task going to sleep. - * - * So for a change of @wl to the local @cpu with an overall group weight change - * of @wl we can compute the new shares distribution (s'_i) using: - * - * s'_i = (rw_i + @wl) / (@wg + \Sum rw_j) (2) - * - * Suppose we're interested in CPUs 0 and 1, and want to compute the load - * differences in waking a task to CPU 0. The additional task changes the - * weight and shares distributions like: - * - * rw'_i = { 3, 4, 1, 0 } - * s'_i = { 3/8, 4/8, 1/8, 0 } - * - * We can then compute the difference in effective weight by using: - * - * dw_i = S * (s'_i - s_i) (3) - * - * Where 'S' is the group weight as seen by its parent. - * - * Therefore the effective change in loads on CPU 0 would be 5/56 (3/8 - 2/7) - * times the weight of the group. The effect on CPU 1 would be -4/56 (4/8 - - * 4/7) times the weight of the group. - */ -static long effective_load(struct task_group *tg, int cpu, long wl, long wg) -{ - struct sched_entity *se = tg->se[cpu]; - - if (!tg->parent) /* the trivial, non-cgroup case */ - return wl; - - for_each_sched_entity(se) { - struct cfs_rq *cfs_rq = se->my_q; - long W, w = cfs_rq_load_avg(cfs_rq); - - tg = cfs_rq->tg; - - /* - * W = @wg + \Sum rw_j - */ - W = wg + atomic_long_read(&tg->load_avg); - - /* Ensure \Sum rw_j >= rw_i */ - W -= cfs_rq->tg_load_avg_contrib; - W += w; - - /* - * w = rw_i + @wl - */ - w += wl; - - /* - * wl = S * s'_i; see (2) - */ - if (W > 0 && w < W) - wl = (w * (long)scale_load_down(tg->shares)) / W; - else - wl = scale_load_down(tg->shares); - - /* - * Per the above, wl is the new se->load.weight value; since - * those are clipped to [MIN_SHARES, ...) do so now. See - * calc_cfs_shares(). - */ - if (wl < MIN_SHARES) - wl = MIN_SHARES; - - /* - * wl = dw_i = S * (s'_i - s_i); see (3) - */ - wl -= se->avg.load_avg; - - /* - * Recursively apply this logic to all parent groups to compute - * the final effective load change on the root group. Since - * only the @tg group gets extra weight, all parent groups can - * only redistribute existing shares. @wl is the shift in shares - * resulting from this level per the above. - */ - wg = 0; - } - - return wl; -} -#else - -static long effective_load(struct task_group *tg, int cpu, long wl, long wg) -{ - return wl; -} - -#endif - static void record_wakee(struct task_struct *p) { /* @@ -5385,67 +5348,25 @@ static int wake_wide(struct task_struct *p) static int wake_affine(struct sched_domain *sd, struct task_struct *p, int prev_cpu, int sync) { - s64 this_load, load; - s64 this_eff_load, prev_eff_load; - int idx, this_cpu; - struct task_group *tg; - unsigned long weight; - int balanced; - - idx = sd->wake_idx; - this_cpu = smp_processor_id(); - load = source_load(prev_cpu, idx); - this_load = target_load(this_cpu, idx); - - /* - * If sync wakeup then subtract the (maximum possible) - * effect of the currently running task from the load - * of the current CPU: - */ - if (sync) { - tg = task_group(current); - weight = current->se.avg.load_avg; - - this_load += effective_load(tg, this_cpu, -weight, -weight); - load += effective_load(tg, prev_cpu, 0, -weight); - } - - tg = task_group(p); - weight = p->se.avg.load_avg; + int this_cpu = smp_processor_id(); + bool affine = false; /* - * In low-load situations, where prev_cpu is idle and this_cpu is idle - * due to the sync cause above having dropped this_load to 0, we'll - * always have an imbalance, but there's really nothing you can do - * about that, so that's good too. - * - * Otherwise check if either cpus are near enough in load to allow this - * task to be woken on this_cpu. + * Common case: CPUs are in the same socket, and select_idle_sibling() + * will do its thing regardless of what we return: */ - this_eff_load = 100; - this_eff_load *= capacity_of(prev_cpu); - - prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2; - prev_eff_load *= capacity_of(this_cpu); - - if (this_load > 0) { - this_eff_load *= this_load + - effective_load(tg, this_cpu, weight, weight); - - prev_eff_load *= load + effective_load(tg, prev_cpu, 0, weight); - } - - balanced = this_eff_load <= prev_eff_load; + if (cpus_share_cache(prev_cpu, this_cpu)) + affine = true; + else + affine = numa_wake_affine(sd, p, this_cpu, prev_cpu, sync); schedstat_inc(p->se.statistics.nr_wakeups_affine_attempts); + if (affine) { + schedstat_inc(sd->ttwu_move_affine); + schedstat_inc(p->se.statistics.nr_wakeups_affine); + } - if (!balanced) - return 0; - - schedstat_inc(sd->ttwu_move_affine); - schedstat_inc(p->se.statistics.nr_wakeups_affine); - - return 1; + return affine; } static inline int task_util(struct task_struct *p); @@ -5484,12 +5405,12 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int i; /* Skip over this group if it has no CPUs allowed */ - if (!cpumask_intersects(sched_group_cpus(group), + if (!cpumask_intersects(sched_group_span(group), &p->cpus_allowed)) continue; local_group = cpumask_test_cpu(this_cpu, - sched_group_cpus(group)); + sched_group_span(group)); /* * Tally up the load of all CPUs in the group and find @@ -5499,7 +5420,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, runnable_load = 0; max_spare_cap = 0; - for_each_cpu(i, sched_group_cpus(group)) { + for_each_cpu(i, sched_group_span(group)) { /* Bias balancing toward cpus of our domain */ if (local_group) load = source_load(i, load_idx); @@ -5602,10 +5523,10 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu) /* Check if we have any choice: */ if (group->group_weight == 1) - return cpumask_first(sched_group_cpus(group)); + return cpumask_first(sched_group_span(group)); /* Traverse only the allowed CPUs */ - for_each_cpu_and(i, sched_group_cpus(group), &p->cpus_allowed) { + for_each_cpu_and(i, sched_group_span(group), &p->cpus_allowed) { if (idle_cpu(i)) { struct rq *rq = cpu_rq(i); struct cpuidle_state *idle = idle_get_state(rq); @@ -5640,43 +5561,6 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu) return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu; } -/* - * Implement a for_each_cpu() variant that starts the scan at a given cpu - * (@start), and wraps around. - * - * This is used to scan for idle CPUs; such that not all CPUs looking for an - * idle CPU find the same CPU. The down-side is that tasks tend to cycle - * through the LLC domain. - * - * Especially tbench is found sensitive to this. - */ - -static int cpumask_next_wrap(int n, const struct cpumask *mask, int start, int *wrapped) -{ - int next; - -again: - next = find_next_bit(cpumask_bits(mask), nr_cpumask_bits, n+1); - - if (*wrapped) { - if (next >= start) - return nr_cpumask_bits; - } else { - if (next >= nr_cpumask_bits) { - *wrapped = 1; - n = -1; - goto again; - } - } - - return next; -} - -#define for_each_cpu_wrap(cpu, mask, start, wrap) \ - for ((wrap) = 0, (cpu) = (start)-1; \ - (cpu) = cpumask_next_wrap((cpu), (mask), (start), &(wrap)), \ - (cpu) < nr_cpumask_bits; ) - #ifdef CONFIG_SCHED_SMT static inline void set_idle_cores(int cpu, int val) @@ -5736,7 +5620,7 @@ unlock: static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int target) { struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask); - int core, cpu, wrap; + int core, cpu; if (!static_branch_likely(&sched_smt_present)) return -1; @@ -5746,7 +5630,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int cpumask_and(cpus, sched_domain_span(sd), &p->cpus_allowed); - for_each_cpu_wrap(core, cpus, target, wrap) { + for_each_cpu_wrap(core, cpus, target) { bool idle = true; for_each_cpu(cpu, cpu_smt_mask(core)) { @@ -5809,27 +5693,38 @@ static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int target) { struct sched_domain *this_sd; - u64 avg_cost, avg_idle = this_rq()->avg_idle; + u64 avg_cost, avg_idle; u64 time, cost; s64 delta; - int cpu, wrap; + int cpu, nr = INT_MAX; this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc)); if (!this_sd) return -1; - avg_cost = this_sd->avg_scan_cost; - /* * Due to large variance we need a large fuzz factor; hackbench in * particularly is sensitive here. */ - if (sched_feat(SIS_AVG_CPU) && (avg_idle / 512) < avg_cost) + avg_idle = this_rq()->avg_idle / 512; + avg_cost = this_sd->avg_scan_cost + 1; + + if (sched_feat(SIS_AVG_CPU) && avg_idle < avg_cost) return -1; + if (sched_feat(SIS_PROP)) { + u64 span_avg = sd->span_weight * avg_idle; + if (span_avg > 4*avg_cost) + nr = div_u64(span_avg, avg_cost); + else + nr = 4; + } + time = local_clock(); - for_each_cpu_wrap(cpu, sched_domain_span(sd), target, wrap) { + for_each_cpu_wrap(cpu, sched_domain_span(sd), target) { + if (!--nr) + return -1; if (!cpumask_test_cpu(cpu, &p->cpus_allowed)) continue; if (idle_cpu(cpu)) @@ -6011,11 +5906,15 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f if (affine_sd) { sd = NULL; /* Prefer wake_affine over balance flags */ - if (cpu != prev_cpu && wake_affine(affine_sd, p, prev_cpu, sync)) + if (cpu == prev_cpu) + goto pick_cpu; + + if (wake_affine(affine_sd, p, prev_cpu, sync)) new_cpu = cpu; } if (!sd) { + pick_cpu: if (sd_flag & SD_BALANCE_WAKE) /* XXX always ? */ new_cpu = select_idle_sibling(p, prev_cpu, new_cpu); @@ -6168,8 +6067,11 @@ static void set_last_buddy(struct sched_entity *se) if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE)) return; - for_each_sched_entity(se) + for_each_sched_entity(se) { + if (SCHED_WARN_ON(!se->on_rq)) + return; cfs_rq_of(se)->last = se; + } } static void set_next_buddy(struct sched_entity *se) @@ -6177,8 +6079,11 @@ static void set_next_buddy(struct sched_entity *se) if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE)) return; - for_each_sched_entity(se) + for_each_sched_entity(se) { + if (SCHED_WARN_ON(!se->on_rq)) + return; cfs_rq_of(se)->next = se; + } } static void set_skip_buddy(struct sched_entity *se) @@ -6686,6 +6591,10 @@ static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env) if (dst_nid == p->numa_preferred_nid) return 0; + /* Leaving a core idle is often worse than degrading locality. */ + if (env->idle != CPU_NOT_IDLE) + return -1; + if (numa_group) { src_faults = group_faults(p, src_nid); dst_faults = group_faults(p, dst_nid); @@ -6970,10 +6879,28 @@ static void attach_tasks(struct lb_env *env) } #ifdef CONFIG_FAIR_GROUP_SCHED + +static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq) +{ + if (cfs_rq->load.weight) + return false; + + if (cfs_rq->avg.load_sum) + return false; + + if (cfs_rq->avg.util_sum) + return false; + + if (cfs_rq->runnable_load_sum) + return false; + + return true; +} + static void update_blocked_averages(int cpu) { struct rq *rq = cpu_rq(cpu); - struct cfs_rq *cfs_rq; + struct cfs_rq *cfs_rq, *pos; struct rq_flags rf; rq_lock_irqsave(rq, &rf); @@ -6983,7 +6910,7 @@ static void update_blocked_averages(int cpu) * Iterates the task_group tree in a bottom up fashion, see * list_add_leaf_cfs_rq() for details. */ - for_each_leaf_cfs_rq(rq, cfs_rq) { + for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos) { struct sched_entity *se; /* throttled entities do not contribute to load */ @@ -6997,6 +6924,13 @@ static void update_blocked_averages(int cpu) se = cfs_rq->tg->se[cpu]; if (se && !skip_blocked_update(se)) update_load_avg(se, 0); + + /* + * There can be a lot of idle CPU cgroups. Don't let fully + * decayed cfs_rqs linger on the list. + */ + if (cfs_rq_is_decayed(cfs_rq)) + list_del_leaf_cfs_rq(cfs_rq); } rq_unlock_irqrestore(rq, &rf); } @@ -7229,7 +7163,7 @@ void update_group_capacity(struct sched_domain *sd, int cpu) * span the current group. */ - for_each_cpu(cpu, sched_group_cpus(sdg)) { + for_each_cpu(cpu, sched_group_span(sdg)) { struct sched_group_capacity *sgc; struct rq *rq = cpu_rq(cpu); @@ -7408,7 +7342,7 @@ static inline void update_sg_lb_stats(struct lb_env *env, memset(sgs, 0, sizeof(*sgs)); - for_each_cpu_and(i, sched_group_cpus(group), env->cpus) { + for_each_cpu_and(i, sched_group_span(group), env->cpus) { struct rq *rq = cpu_rq(i); /* Bias balancing toward cpus of our domain */ @@ -7572,7 +7506,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd struct sg_lb_stats *sgs = &tmp_sgs; int local_group; - local_group = cpumask_test_cpu(env->dst_cpu, sched_group_cpus(sg)); + local_group = cpumask_test_cpu(env->dst_cpu, sched_group_span(sg)); if (local_group) { sds->local = sg; sgs = local; @@ -7927,7 +7861,7 @@ static struct rq *find_busiest_queue(struct lb_env *env, unsigned long busiest_load = 0, busiest_capacity = 1; int i; - for_each_cpu_and(i, sched_group_cpus(group), env->cpus) { + for_each_cpu_and(i, sched_group_span(group), env->cpus) { unsigned long capacity, wl; enum fbq_type rt; @@ -8033,7 +7967,6 @@ static int active_load_balance_cpu_stop(void *data); static int should_we_balance(struct lb_env *env) { struct sched_group *sg = env->sd->groups; - struct cpumask *sg_cpus, *sg_mask; int cpu, balance_cpu = -1; /* @@ -8043,11 +7976,9 @@ static int should_we_balance(struct lb_env *env) if (env->idle == CPU_NEWLY_IDLE) return 1; - sg_cpus = sched_group_cpus(sg); - sg_mask = sched_group_mask(sg); /* Try to find first idle cpu */ - for_each_cpu_and(cpu, sg_cpus, env->cpus) { - if (!cpumask_test_cpu(cpu, sg_mask) || !idle_cpu(cpu)) + for_each_cpu_and(cpu, group_balance_mask(sg), env->cpus) { + if (!idle_cpu(cpu)) continue; balance_cpu = cpu; @@ -8083,7 +8014,7 @@ static int load_balance(int this_cpu, struct rq *this_rq, .sd = sd, .dst_cpu = this_cpu, .dst_rq = this_rq, - .dst_grpmask = sched_group_cpus(sd->groups), + .dst_grpmask = sched_group_span(sd->groups), .idle = idle, .loop_break = sched_nr_migrate_break, .cpus = cpus, @@ -8659,6 +8590,10 @@ void nohz_balance_enter_idle(int cpu) if (!cpu_active(cpu)) return; + /* Spare idle load balancing on CPUs that don't want to be disturbed: */ + if (!is_housekeeping_cpu(cpu)) + return; + if (test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu))) return; @@ -9523,10 +9458,10 @@ const struct sched_class fair_sched_class = { #ifdef CONFIG_SCHED_DEBUG void print_cfs_stats(struct seq_file *m, int cpu) { - struct cfs_rq *cfs_rq; + struct cfs_rq *cfs_rq, *pos; rcu_read_lock(); - for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq) + for_each_leaf_cfs_rq_safe(cpu_rq(cpu), cfs_rq, pos) print_cfs_rq(m, cpu, cfs_rq); rcu_read_unlock(); } diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 11192e0cb122..d3fb15555291 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -55,6 +55,7 @@ SCHED_FEAT(TTWU_QUEUE, true) * When doing wakeups, attempt to limit superfluous scans of the LLC domain. */ SCHED_FEAT(SIS_AVG_CPU, false) +SCHED_FEAT(SIS_PROP, true) /* * Issue a WARN when we do multiple update_rq_clock() calls @@ -76,7 +77,6 @@ SCHED_FEAT(WARN_DOUBLE_CLOCK, false) SCHED_FEAT(RT_PUSH_IPI, true) #endif -SCHED_FEAT(FORCE_SD_OVERLAP, false) SCHED_FEAT(RT_RUNTIME_SHARE, true) SCHED_FEAT(LB_MIN, false) SCHED_FEAT(ATTACH_AGE_LOAD, true) diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index ef63adce0c9c..6c23e30c0e5c 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -219,6 +219,7 @@ static void do_idle(void) */ __current_set_polling(); + quiet_vmstat(); tick_nohz_idle_enter(); while (!need_resched()) { diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index f15fb2bdbc0d..f14716a3522f 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -117,7 +117,7 @@ calc_load(unsigned long load, unsigned long exp, unsigned long active) * load-average relies on per-cpu sampling from the tick, it is affected by * NO_HZ. * - * The basic idea is to fold the nr_active delta into a global idle-delta upon + * The basic idea is to fold the nr_active delta into a global NO_HZ-delta upon * entering NO_HZ state such that we can include this as an 'extra' cpu delta * when we read the global state. * @@ -126,7 +126,7 @@ calc_load(unsigned long load, unsigned long exp, unsigned long active) * - When we go NO_HZ idle during the window, we can negate our sample * contribution, causing under-accounting. * - * We avoid this by keeping two idle-delta counters and flipping them + * We avoid this by keeping two NO_HZ-delta counters and flipping them * when the window starts, thus separating old and new NO_HZ load. * * The only trick is the slight shift in index flip for read vs write. @@ -137,22 +137,22 @@ calc_load(unsigned long load, unsigned long exp, unsigned long active) * r:0 0 1 1 0 0 1 1 0 * w:0 1 1 0 0 1 1 0 0 * - * This ensures we'll fold the old idle contribution in this window while + * This ensures we'll fold the old NO_HZ contribution in this window while * accumlating the new one. * - * - When we wake up from NO_HZ idle during the window, we push up our + * - When we wake up from NO_HZ during the window, we push up our * contribution, since we effectively move our sample point to a known * busy state. * * This is solved by pushing the window forward, and thus skipping the - * sample, for this cpu (effectively using the idle-delta for this cpu which + * sample, for this cpu (effectively using the NO_HZ-delta for this cpu which * was in effect at the time the window opened). This also solves the issue - * of having to deal with a cpu having been in NOHZ idle for multiple - * LOAD_FREQ intervals. + * of having to deal with a cpu having been in NO_HZ for multiple LOAD_FREQ + * intervals. * * When making the ILB scale, we should try to pull this in as well. */ -static atomic_long_t calc_load_idle[2]; +static atomic_long_t calc_load_nohz[2]; static int calc_load_idx; static inline int calc_load_write_idx(void) @@ -167,7 +167,7 @@ static inline int calc_load_write_idx(void) /* * If the folding window started, make sure we start writing in the - * next idle-delta. + * next NO_HZ-delta. */ if (!time_before(jiffies, READ_ONCE(calc_load_update))) idx++; @@ -180,24 +180,24 @@ static inline int calc_load_read_idx(void) return calc_load_idx & 1; } -void calc_load_enter_idle(void) +void calc_load_nohz_start(void) { struct rq *this_rq = this_rq(); long delta; /* - * We're going into NOHZ mode, if there's any pending delta, fold it - * into the pending idle delta. + * We're going into NO_HZ mode, if there's any pending delta, fold it + * into the pending NO_HZ delta. */ delta = calc_load_fold_active(this_rq, 0); if (delta) { int idx = calc_load_write_idx(); - atomic_long_add(delta, &calc_load_idle[idx]); + atomic_long_add(delta, &calc_load_nohz[idx]); } } -void calc_load_exit_idle(void) +void calc_load_nohz_stop(void) { struct rq *this_rq = this_rq(); @@ -217,13 +217,13 @@ void calc_load_exit_idle(void) this_rq->calc_load_update += LOAD_FREQ; } -static long calc_load_fold_idle(void) +static long calc_load_nohz_fold(void) { int idx = calc_load_read_idx(); long delta = 0; - if (atomic_long_read(&calc_load_idle[idx])) - delta = atomic_long_xchg(&calc_load_idle[idx], 0); + if (atomic_long_read(&calc_load_nohz[idx])) + delta = atomic_long_xchg(&calc_load_nohz[idx], 0); return delta; } @@ -299,9 +299,9 @@ calc_load_n(unsigned long load, unsigned long exp, /* * NO_HZ can leave us missing all per-cpu ticks calling - * calc_load_account_active(), but since an idle CPU folds its delta into - * calc_load_tasks_idle per calc_load_account_idle(), all we need to do is fold - * in the pending idle delta if our idle period crossed a load cycle boundary. + * calc_load_fold_active(), but since a NO_HZ CPU folds its delta into + * calc_load_nohz per calc_load_nohz_start(), all we need to do is fold + * in the pending NO_HZ delta if our NO_HZ period crossed a load cycle boundary. * * Once we've updated the global active value, we need to apply the exponential * weights adjusted to the number of cycles missed. @@ -330,7 +330,7 @@ static void calc_global_nohz(void) } /* - * Flip the idle index... + * Flip the NO_HZ index... * * Make sure we first write the new time then flip the index, so that * calc_load_write_idx() will see the new time when it reads the new @@ -341,7 +341,7 @@ static void calc_global_nohz(void) } #else /* !CONFIG_NO_HZ_COMMON */ -static inline long calc_load_fold_idle(void) { return 0; } +static inline long calc_load_nohz_fold(void) { return 0; } static inline void calc_global_nohz(void) { } #endif /* CONFIG_NO_HZ_COMMON */ @@ -362,9 +362,9 @@ void calc_global_load(unsigned long ticks) return; /* - * Fold the 'old' idle-delta to include all NO_HZ cpus. + * Fold the 'old' NO_HZ-delta to include all NO_HZ cpus. */ - delta = calc_load_fold_idle(); + delta = calc_load_nohz_fold(); if (delta) atomic_long_add(delta, &calc_load_tasks); @@ -378,7 +378,8 @@ void calc_global_load(unsigned long ticks) WRITE_ONCE(calc_load_update, sample_window + LOAD_FREQ); /* - * In case we idled for multiple LOAD_FREQ intervals, catch up in bulk. + * In case we went to NO_HZ for multiple LOAD_FREQ intervals + * catch up in bulk. */ calc_global_nohz(); } diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 979b7341008a..45caf937ef90 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -840,6 +840,17 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) int enqueue = 0; struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i); struct rq *rq = rq_of_rt_rq(rt_rq); + int skip; + + /* + * When span == cpu_online_mask, taking each rq->lock + * can be time-consuming. Try to avoid it when possible. + */ + raw_spin_lock(&rt_rq->rt_runtime_lock); + skip = !rt_rq->rt_time && !rt_rq->rt_nr_running; + raw_spin_unlock(&rt_rq->rt_runtime_lock); + if (skip) + continue; raw_spin_lock(&rq->lock); if (rt_rq->rt_time) { @@ -1819,7 +1830,7 @@ retry: * pushing. */ task = pick_next_pushable_task(rq); - if (task_cpu(next_task) == rq->cpu && task == next_task) { + if (task == next_task) { /* * The task hasn't migrated, and is still the next * eligible task, but we failed to find a run-queue @@ -2438,6 +2449,316 @@ const struct sched_class rt_sched_class = { .update_curr = update_curr_rt, }; +#ifdef CONFIG_RT_GROUP_SCHED +/* + * Ensure that the real time constraints are schedulable. + */ +static DEFINE_MUTEX(rt_constraints_mutex); + +/* Must be called with tasklist_lock held */ +static inline int tg_has_rt_tasks(struct task_group *tg) +{ + struct task_struct *g, *p; + + /* + * Autogroups do not have RT tasks; see autogroup_create(). + */ + if (task_group_is_autogroup(tg)) + return 0; + + for_each_process_thread(g, p) { + if (rt_task(p) && task_group(p) == tg) + return 1; + } + + return 0; +} + +struct rt_schedulable_data { + struct task_group *tg; + u64 rt_period; + u64 rt_runtime; +}; + +static int tg_rt_schedulable(struct task_group *tg, void *data) +{ + struct rt_schedulable_data *d = data; + struct task_group *child; + unsigned long total, sum = 0; + u64 period, runtime; + + period = ktime_to_ns(tg->rt_bandwidth.rt_period); + runtime = tg->rt_bandwidth.rt_runtime; + + if (tg == d->tg) { + period = d->rt_period; + runtime = d->rt_runtime; + } + + /* + * Cannot have more runtime than the period. + */ + if (runtime > period && runtime != RUNTIME_INF) + return -EINVAL; + + /* + * Ensure we don't starve existing RT tasks. + */ + if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg)) + return -EBUSY; + + total = to_ratio(period, runtime); + + /* + * Nobody can have more than the global setting allows. + */ + if (total > to_ratio(global_rt_period(), global_rt_runtime())) + return -EINVAL; + + /* + * The sum of our children's runtime should not exceed our own. + */ + list_for_each_entry_rcu(child, &tg->children, siblings) { + period = ktime_to_ns(child->rt_bandwidth.rt_period); + runtime = child->rt_bandwidth.rt_runtime; + + if (child == d->tg) { + period = d->rt_period; + runtime = d->rt_runtime; + } + + sum += to_ratio(period, runtime); + } + + if (sum > total) + return -EINVAL; + + return 0; +} + +static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime) +{ + int ret; + + struct rt_schedulable_data data = { + .tg = tg, + .rt_period = period, + .rt_runtime = runtime, + }; + + rcu_read_lock(); + ret = walk_tg_tree(tg_rt_schedulable, tg_nop, &data); + rcu_read_unlock(); + + return ret; +} + +static int tg_set_rt_bandwidth(struct task_group *tg, + u64 rt_period, u64 rt_runtime) +{ + int i, err = 0; + + /* + * Disallowing the root group RT runtime is BAD, it would disallow the + * kernel creating (and or operating) RT threads. + */ + if (tg == &root_task_group && rt_runtime == 0) + return -EINVAL; + + /* No period doesn't make any sense. */ + if (rt_period == 0) + return -EINVAL; + + mutex_lock(&rt_constraints_mutex); + read_lock(&tasklist_lock); + err = __rt_schedulable(tg, rt_period, rt_runtime); + if (err) + goto unlock; + + raw_spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock); + tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period); + tg->rt_bandwidth.rt_runtime = rt_runtime; + + for_each_possible_cpu(i) { + struct rt_rq *rt_rq = tg->rt_rq[i]; + + raw_spin_lock(&rt_rq->rt_runtime_lock); + rt_rq->rt_runtime = rt_runtime; + raw_spin_unlock(&rt_rq->rt_runtime_lock); + } + raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock); +unlock: + read_unlock(&tasklist_lock); + mutex_unlock(&rt_constraints_mutex); + + return err; +} + +int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us) +{ + u64 rt_runtime, rt_period; + + rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period); + rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC; + if (rt_runtime_us < 0) + rt_runtime = RUNTIME_INF; + + return tg_set_rt_bandwidth(tg, rt_period, rt_runtime); +} + +long sched_group_rt_runtime(struct task_group *tg) +{ + u64 rt_runtime_us; + + if (tg->rt_bandwidth.rt_runtime == RUNTIME_INF) + return -1; + + rt_runtime_us = tg->rt_bandwidth.rt_runtime; + do_div(rt_runtime_us, NSEC_PER_USEC); + return rt_runtime_us; +} + +int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us) +{ + u64 rt_runtime, rt_period; + + rt_period = rt_period_us * NSEC_PER_USEC; + rt_runtime = tg->rt_bandwidth.rt_runtime; + + return tg_set_rt_bandwidth(tg, rt_period, rt_runtime); +} + +long sched_group_rt_period(struct task_group *tg) +{ + u64 rt_period_us; + + rt_period_us = ktime_to_ns(tg->rt_bandwidth.rt_period); + do_div(rt_period_us, NSEC_PER_USEC); + return rt_period_us; +} + +static int sched_rt_global_constraints(void) +{ + int ret = 0; + + mutex_lock(&rt_constraints_mutex); + read_lock(&tasklist_lock); + ret = __rt_schedulable(NULL, 0, 0); + read_unlock(&tasklist_lock); + mutex_unlock(&rt_constraints_mutex); + + return ret; +} + +int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk) +{ + /* Don't accept realtime tasks when there is no way for them to run */ + if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0) + return 0; + + return 1; +} + +#else /* !CONFIG_RT_GROUP_SCHED */ +static int sched_rt_global_constraints(void) +{ + unsigned long flags; + int i; + + raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags); + for_each_possible_cpu(i) { + struct rt_rq *rt_rq = &cpu_rq(i)->rt; + + raw_spin_lock(&rt_rq->rt_runtime_lock); + rt_rq->rt_runtime = global_rt_runtime(); + raw_spin_unlock(&rt_rq->rt_runtime_lock); + } + raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags); + + return 0; +} +#endif /* CONFIG_RT_GROUP_SCHED */ + +static int sched_rt_global_validate(void) +{ + if (sysctl_sched_rt_period <= 0) + return -EINVAL; + + if ((sysctl_sched_rt_runtime != RUNTIME_INF) && + (sysctl_sched_rt_runtime > sysctl_sched_rt_period)) + return -EINVAL; + + return 0; +} + +static void sched_rt_do_global(void) +{ + def_rt_bandwidth.rt_runtime = global_rt_runtime(); + def_rt_bandwidth.rt_period = ns_to_ktime(global_rt_period()); +} + +int sched_rt_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int old_period, old_runtime; + static DEFINE_MUTEX(mutex); + int ret; + + mutex_lock(&mutex); + old_period = sysctl_sched_rt_period; + old_runtime = sysctl_sched_rt_runtime; + + ret = proc_dointvec(table, write, buffer, lenp, ppos); + + if (!ret && write) { + ret = sched_rt_global_validate(); + if (ret) + goto undo; + + ret = sched_dl_global_validate(); + if (ret) + goto undo; + + ret = sched_rt_global_constraints(); + if (ret) + goto undo; + + sched_rt_do_global(); + sched_dl_do_global(); + } + if (0) { +undo: + sysctl_sched_rt_period = old_period; + sysctl_sched_rt_runtime = old_runtime; + } + mutex_unlock(&mutex); + + return ret; +} + +int sched_rr_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret; + static DEFINE_MUTEX(mutex); + + mutex_lock(&mutex); + ret = proc_dointvec(table, write, buffer, lenp, ppos); + /* + * Make sure that internally we keep jiffies. + * Also, writing zero resets the timeslice to default: + */ + if (!ret && write) { + sched_rr_timeslice = + sysctl_sched_rr_timeslice <= 0 ? RR_TIMESLICE : + msecs_to_jiffies(sysctl_sched_rr_timeslice); + } + mutex_unlock(&mutex); + return ret; +} + #ifdef CONFIG_SCHED_DEBUG extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 6dda2aab731e..eeef1a3086d1 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -39,9 +39,9 @@ #include "cpuacct.h" #ifdef CONFIG_SCHED_DEBUG -#define SCHED_WARN_ON(x) WARN_ONCE(x, #x) +# define SCHED_WARN_ON(x) WARN_ONCE(x, #x) #else -#define SCHED_WARN_ON(x) ((void)(x)) +# define SCHED_WARN_ON(x) ({ (void)(x), 0; }) #endif struct rq; @@ -218,23 +218,25 @@ static inline int dl_bandwidth_enabled(void) return sysctl_sched_rt_runtime >= 0; } -extern struct dl_bw *dl_bw_of(int i); - struct dl_bw { raw_spinlock_t lock; u64 bw, total_bw; }; +static inline void __dl_update(struct dl_bw *dl_b, s64 bw); + static inline -void __dl_clear(struct dl_bw *dl_b, u64 tsk_bw) +void __dl_clear(struct dl_bw *dl_b, u64 tsk_bw, int cpus) { dl_b->total_bw -= tsk_bw; + __dl_update(dl_b, (s32)tsk_bw / cpus); } static inline -void __dl_add(struct dl_bw *dl_b, u64 tsk_bw) +void __dl_add(struct dl_bw *dl_b, u64 tsk_bw, int cpus) { dl_b->total_bw += tsk_bw; + __dl_update(dl_b, -((s32)tsk_bw / cpus)); } static inline @@ -244,7 +246,22 @@ bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw) dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw; } +void dl_change_utilization(struct task_struct *p, u64 new_bw); extern void init_dl_bw(struct dl_bw *dl_b); +extern int sched_dl_global_validate(void); +extern void sched_dl_do_global(void); +extern int sched_dl_overflow(struct task_struct *p, int policy, + const struct sched_attr *attr); +extern void __setparam_dl(struct task_struct *p, const struct sched_attr *attr); +extern void __getparam_dl(struct task_struct *p, struct sched_attr *attr); +extern bool __checkparam_dl(const struct sched_attr *attr); +extern void __dl_clear_params(struct task_struct *p); +extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr); +extern int dl_task_can_attach(struct task_struct *p, + const struct cpumask *cs_cpus_allowed); +extern int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, + const struct cpumask *trial); +extern bool dl_cpu_busy(unsigned int cpu); #ifdef CONFIG_CGROUP_SCHED @@ -366,6 +383,11 @@ extern int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent extern void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq, struct sched_rt_entity *rt_se, int cpu, struct sched_rt_entity *parent); +extern int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us); +extern int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us); +extern long sched_group_rt_runtime(struct task_group *tg); +extern long sched_group_rt_period(struct task_group *tg); +extern int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk); extern struct task_group *sched_create_group(struct task_group *parent); extern void sched_online_group(struct task_group *tg, @@ -558,6 +580,30 @@ struct dl_rq { #else struct dl_bw dl_bw; #endif + /* + * "Active utilization" for this runqueue: increased when a + * task wakes up (becomes TASK_RUNNING) and decreased when a + * task blocks + */ + u64 running_bw; + + /* + * Utilization of the tasks "assigned" to this runqueue (including + * the tasks that are in runqueue and the tasks that executed on this + * CPU and blocked). Increased when a task moves to this runqueue, and + * decreased when the task moves away (migrates, changes scheduling + * policy, or terminates). + * This is needed to compute the "inactive utilization" for the + * runqueue (inactive utilization = this_bw - running_bw). + */ + u64 this_bw; + u64 extra_bw; + + /* + * Inverse of the fraction of CPU utilization that can be reclaimed + * by the GRUB algorithm. + */ + u64 bw_ratio; }; #ifdef CONFIG_SMP @@ -606,11 +652,9 @@ struct root_domain { extern struct root_domain def_root_domain; extern struct mutex sched_domains_mutex; -extern cpumask_var_t fallback_doms; -extern cpumask_var_t sched_domains_tmpmask; extern void init_defrootdomain(void); -extern int init_sched_domains(const struct cpumask *cpu_map); +extern int sched_init_domains(const struct cpumask *cpu_map); extern void rq_attach_root(struct rq *rq, struct root_domain *rd); #endif /* CONFIG_SMP */ @@ -1025,7 +1069,11 @@ struct sched_group_capacity { unsigned long next_update; int imbalance; /* XXX unrelated to capacity but shared group state */ - unsigned long cpumask[0]; /* iteration mask */ +#ifdef CONFIG_SCHED_DEBUG + int id; +#endif + + unsigned long cpumask[0]; /* balance mask */ }; struct sched_group { @@ -1046,16 +1094,15 @@ struct sched_group { unsigned long cpumask[0]; }; -static inline struct cpumask *sched_group_cpus(struct sched_group *sg) +static inline struct cpumask *sched_group_span(struct sched_group *sg) { return to_cpumask(sg->cpumask); } /* - * cpumask masking which cpus in the group are allowed to iterate up the domain - * tree. + * See build_balance_mask(). */ -static inline struct cpumask *sched_group_mask(struct sched_group *sg) +static inline struct cpumask *group_balance_mask(struct sched_group *sg) { return to_cpumask(sg->sgc->cpumask); } @@ -1066,7 +1113,7 @@ static inline struct cpumask *sched_group_mask(struct sched_group *sg) */ static inline unsigned int group_first_cpu(struct sched_group *group) { - return cpumask_first(sched_group_cpus(group)); + return cpumask_first(sched_group_span(group)); } extern int group_balance_cpu(struct sched_group *sg); @@ -1422,7 +1469,11 @@ static inline void set_curr_task(struct rq *rq, struct task_struct *curr) curr->sched_class->set_curr_task(rq); } +#ifdef CONFIG_SMP #define sched_class_highest (&stop_sched_class) +#else +#define sched_class_highest (&dl_sched_class) +#endif #define for_each_class(class) \ for (class = sched_class_highest; class; class = class->next) @@ -1486,7 +1537,12 @@ extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime extern struct dl_bandwidth def_dl_bandwidth; extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime); extern void init_dl_task_timer(struct sched_dl_entity *dl_se); +extern void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se); +extern void init_dl_rq_bw_ratio(struct dl_rq *dl_rq); +#define BW_SHIFT 20 +#define BW_UNIT (1 << BW_SHIFT) +#define RATIO_SHIFT 8 unsigned long to_ratio(u64 period, u64 runtime); extern void init_entity_runnable_average(struct sched_entity *se); @@ -1928,6 +1984,33 @@ extern void nohz_balance_exit_idle(unsigned int cpu); static inline void nohz_balance_exit_idle(unsigned int cpu) { } #endif + +#ifdef CONFIG_SMP +static inline +void __dl_update(struct dl_bw *dl_b, s64 bw) +{ + struct root_domain *rd = container_of(dl_b, struct root_domain, dl_bw); + int i; + + RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(), + "sched RCU must be held"); + for_each_cpu_and(i, rd->span, cpu_active_mask) { + struct rq *rq = cpu_rq(i); + + rq->dl.extra_bw += bw; + } +} +#else +static inline +void __dl_update(struct dl_bw *dl_b, s64 bw) +{ + struct dl_rq *dl = container_of(dl_b, struct dl_rq, dl_bw); + + dl->extra_bw += bw; +} +#endif + + #ifdef CONFIG_IRQ_TIME_ACCOUNTING struct irqtime { u64 total; diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 1b0b4fb12837..79895aec281e 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -10,6 +10,7 @@ DEFINE_MUTEX(sched_domains_mutex); /* Protected by sched_domains_mutex: */ cpumask_var_t sched_domains_tmpmask; +cpumask_var_t sched_domains_tmpmask2; #ifdef CONFIG_SCHED_DEBUG @@ -35,7 +36,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, cpumask_clear(groupmask); - printk(KERN_DEBUG "%*s domain %d: ", level, "", level); + printk(KERN_DEBUG "%*s domain-%d: ", level, "", level); if (!(sd->flags & SD_LOAD_BALANCE)) { printk("does not load-balance\n"); @@ -45,14 +46,14 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, return -1; } - printk(KERN_CONT "span %*pbl level %s\n", + printk(KERN_CONT "span=%*pbl level=%s\n", cpumask_pr_args(sched_domain_span(sd)), sd->name); if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) { printk(KERN_ERR "ERROR: domain->span does not contain " "CPU%d\n", cpu); } - if (!cpumask_test_cpu(cpu, sched_group_cpus(group))) { + if (!cpumask_test_cpu(cpu, sched_group_span(group))) { printk(KERN_ERR "ERROR: domain->groups does not contain" " CPU%d\n", cpu); } @@ -65,29 +66,47 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, break; } - if (!cpumask_weight(sched_group_cpus(group))) { + if (!cpumask_weight(sched_group_span(group))) { printk(KERN_CONT "\n"); printk(KERN_ERR "ERROR: empty group\n"); break; } if (!(sd->flags & SD_OVERLAP) && - cpumask_intersects(groupmask, sched_group_cpus(group))) { + cpumask_intersects(groupmask, sched_group_span(group))) { printk(KERN_CONT "\n"); printk(KERN_ERR "ERROR: repeated CPUs\n"); break; } - cpumask_or(groupmask, groupmask, sched_group_cpus(group)); + cpumask_or(groupmask, groupmask, sched_group_span(group)); - printk(KERN_CONT " %*pbl", - cpumask_pr_args(sched_group_cpus(group))); - if (group->sgc->capacity != SCHED_CAPACITY_SCALE) { - printk(KERN_CONT " (cpu_capacity = %lu)", - group->sgc->capacity); + printk(KERN_CONT " %d:{ span=%*pbl", + group->sgc->id, + cpumask_pr_args(sched_group_span(group))); + + if ((sd->flags & SD_OVERLAP) && + !cpumask_equal(group_balance_mask(group), sched_group_span(group))) { + printk(KERN_CONT " mask=%*pbl", + cpumask_pr_args(group_balance_mask(group))); + } + + if (group->sgc->capacity != SCHED_CAPACITY_SCALE) + printk(KERN_CONT " cap=%lu", group->sgc->capacity); + + if (group == sd->groups && sd->child && + !cpumask_equal(sched_domain_span(sd->child), + sched_group_span(group))) { + printk(KERN_ERR "ERROR: domain->groups does not match domain->child\n"); } + printk(KERN_CONT " }"); + group = group->next; + + if (group != sd->groups) + printk(KERN_CONT ","); + } while (group != sd->groups); printk(KERN_CONT "\n"); @@ -113,7 +132,7 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu) return; } - printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu); + printk(KERN_DEBUG "CPU%d attaching sched-domain(s):\n", cpu); for (;;) { if (sched_domain_debug_one(sd, cpu, level, sched_domains_tmpmask)) @@ -477,46 +496,214 @@ enum s_alloc { }; /* - * Build an iteration mask that can exclude certain CPUs from the upwards - * domain traversal. + * Return the canonical balance CPU for this group, this is the first CPU + * of this group that's also in the balance mask. * - * Asymmetric node setups can result in situations where the domain tree is of - * unequal depth, make sure to skip domains that already cover the entire - * range. + * The balance mask are all those CPUs that could actually end up at this + * group. See build_balance_mask(). * - * In that case build_sched_domains() will have terminated the iteration early - * and our sibling sd spans will be empty. Domains should always include the - * CPU they're built on, so check that. + * Also see should_we_balance(). */ -static void build_group_mask(struct sched_domain *sd, struct sched_group *sg) +int group_balance_cpu(struct sched_group *sg) { - const struct cpumask *span = sched_domain_span(sd); + return cpumask_first(group_balance_mask(sg)); +} + + +/* + * NUMA topology (first read the regular topology blurb below) + * + * Given a node-distance table, for example: + * + * node 0 1 2 3 + * 0: 10 20 30 20 + * 1: 20 10 20 30 + * 2: 30 20 10 20 + * 3: 20 30 20 10 + * + * which represents a 4 node ring topology like: + * + * 0 ----- 1 + * | | + * | | + * | | + * 3 ----- 2 + * + * We want to construct domains and groups to represent this. The way we go + * about doing this is to build the domains on 'hops'. For each NUMA level we + * construct the mask of all nodes reachable in @level hops. + * + * For the above NUMA topology that gives 3 levels: + * + * NUMA-2 0-3 0-3 0-3 0-3 + * groups: {0-1,3},{1-3} {0-2},{0,2-3} {1-3},{0-1,3} {0,2-3},{0-2} + * + * NUMA-1 0-1,3 0-2 1-3 0,2-3 + * groups: {0},{1},{3} {0},{1},{2} {1},{2},{3} {0},{2},{3} + * + * NUMA-0 0 1 2 3 + * + * + * As can be seen; things don't nicely line up as with the regular topology. + * When we iterate a domain in child domain chunks some nodes can be + * represented multiple times -- hence the "overlap" naming for this part of + * the topology. + * + * In order to minimize this overlap, we only build enough groups to cover the + * domain. For instance Node-0 NUMA-2 would only get groups: 0-1,3 and 1-3. + * + * Because: + * + * - the first group of each domain is its child domain; this + * gets us the first 0-1,3 + * - the only uncovered node is 2, who's child domain is 1-3. + * + * However, because of the overlap, computing a unique CPU for each group is + * more complicated. Consider for instance the groups of NODE-1 NUMA-2, both + * groups include the CPUs of Node-0, while those CPUs would not in fact ever + * end up at those groups (they would end up in group: 0-1,3). + * + * To correct this we have to introduce the group balance mask. This mask + * will contain those CPUs in the group that can reach this group given the + * (child) domain tree. + * + * With this we can once again compute balance_cpu and sched_group_capacity + * relations. + * + * XXX include words on how balance_cpu is unique and therefore can be + * used for sched_group_capacity links. + * + * + * Another 'interesting' topology is: + * + * node 0 1 2 3 + * 0: 10 20 20 30 + * 1: 20 10 20 20 + * 2: 20 20 10 20 + * 3: 30 20 20 10 + * + * Which looks a little like: + * + * 0 ----- 1 + * | / | + * | / | + * | / | + * 2 ----- 3 + * + * This topology is asymmetric, nodes 1,2 are fully connected, but nodes 0,3 + * are not. + * + * This leads to a few particularly weird cases where the sched_domain's are + * not of the same number for each cpu. Consider: + * + * NUMA-2 0-3 0-3 + * groups: {0-2},{1-3} {1-3},{0-2} + * + * NUMA-1 0-2 0-3 0-3 1-3 + * + * NUMA-0 0 1 2 3 + * + */ + + +/* + * Build the balance mask; it contains only those CPUs that can arrive at this + * group and should be considered to continue balancing. + * + * We do this during the group creation pass, therefore the group information + * isn't complete yet, however since each group represents a (child) domain we + * can fully construct this using the sched_domain bits (which are already + * complete). + */ +static void +build_balance_mask(struct sched_domain *sd, struct sched_group *sg, struct cpumask *mask) +{ + const struct cpumask *sg_span = sched_group_span(sg); struct sd_data *sdd = sd->private; struct sched_domain *sibling; int i; - for_each_cpu(i, span) { + cpumask_clear(mask); + + for_each_cpu(i, sg_span) { sibling = *per_cpu_ptr(sdd->sd, i); - if (!cpumask_test_cpu(i, sched_domain_span(sibling))) + + /* + * Can happen in the asymmetric case, where these siblings are + * unused. The mask will not be empty because those CPUs that + * do have the top domain _should_ span the domain. + */ + if (!sibling->child) continue; - cpumask_set_cpu(i, sched_group_mask(sg)); + /* If we would not end up here, we can't continue from here */ + if (!cpumask_equal(sg_span, sched_domain_span(sibling->child))) + continue; + + cpumask_set_cpu(i, mask); } + + /* We must not have empty masks here */ + WARN_ON_ONCE(cpumask_empty(mask)); } /* - * Return the canonical balance CPU for this group, this is the first CPU - * of this group that's also in the iteration mask. + * XXX: This creates per-node group entries; since the load-balancer will + * immediately access remote memory to construct this group's load-balance + * statistics having the groups node local is of dubious benefit. */ -int group_balance_cpu(struct sched_group *sg) +static struct sched_group * +build_group_from_child_sched_domain(struct sched_domain *sd, int cpu) { - return cpumask_first_and(sched_group_cpus(sg), sched_group_mask(sg)); + struct sched_group *sg; + struct cpumask *sg_span; + + sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(), + GFP_KERNEL, cpu_to_node(cpu)); + + if (!sg) + return NULL; + + sg_span = sched_group_span(sg); + if (sd->child) + cpumask_copy(sg_span, sched_domain_span(sd->child)); + else + cpumask_copy(sg_span, sched_domain_span(sd)); + + return sg; +} + +static void init_overlap_sched_group(struct sched_domain *sd, + struct sched_group *sg) +{ + struct cpumask *mask = sched_domains_tmpmask2; + struct sd_data *sdd = sd->private; + struct cpumask *sg_span; + int cpu; + + build_balance_mask(sd, sg, mask); + cpu = cpumask_first_and(sched_group_span(sg), mask); + + sg->sgc = *per_cpu_ptr(sdd->sgc, cpu); + if (atomic_inc_return(&sg->sgc->ref) == 1) + cpumask_copy(group_balance_mask(sg), mask); + else + WARN_ON_ONCE(!cpumask_equal(group_balance_mask(sg), mask)); + + /* + * Initialize sgc->capacity such that even if we mess up the + * domains and no possible iteration will get us here, we won't + * die on a /0 trap. + */ + sg_span = sched_group_span(sg); + sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span); + sg->sgc->min_capacity = SCHED_CAPACITY_SCALE; } static int build_overlap_sched_groups(struct sched_domain *sd, int cpu) { - struct sched_group *first = NULL, *last = NULL, *groups = NULL, *sg; + struct sched_group *first = NULL, *last = NULL, *sg; const struct cpumask *span = sched_domain_span(sd); struct cpumask *covered = sched_domains_tmpmask; struct sd_data *sdd = sd->private; @@ -525,7 +712,7 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu) cpumask_clear(covered); - for_each_cpu(i, span) { + for_each_cpu_wrap(i, span, cpu) { struct cpumask *sg_span; if (cpumask_test_cpu(i, covered)) @@ -533,44 +720,27 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu) sibling = *per_cpu_ptr(sdd->sd, i); - /* See the comment near build_group_mask(). */ + /* + * Asymmetric node setups can result in situations where the + * domain tree is of unequal depth, make sure to skip domains + * that already cover the entire range. + * + * In that case build_sched_domains() will have terminated the + * iteration early and our sibling sd spans will be empty. + * Domains should always include the CPU they're built on, so + * check that. + */ if (!cpumask_test_cpu(i, sched_domain_span(sibling))) continue; - sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(), - GFP_KERNEL, cpu_to_node(cpu)); - + sg = build_group_from_child_sched_domain(sibling, cpu); if (!sg) goto fail; - sg_span = sched_group_cpus(sg); - if (sibling->child) - cpumask_copy(sg_span, sched_domain_span(sibling->child)); - else - cpumask_set_cpu(i, sg_span); - + sg_span = sched_group_span(sg); cpumask_or(covered, covered, sg_span); - sg->sgc = *per_cpu_ptr(sdd->sgc, i); - if (atomic_inc_return(&sg->sgc->ref) == 1) - build_group_mask(sd, sg); - - /* - * Initialize sgc->capacity such that even if we mess up the - * domains and no possible iteration will get us here, we won't - * die on a /0 trap. - */ - sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span); - sg->sgc->min_capacity = SCHED_CAPACITY_SCALE; - - /* - * Make sure the first group of this domain contains the - * canonical balance CPU. Otherwise the sched_domain iteration - * breaks. See update_sg_lb_stats(). - */ - if ((!groups && cpumask_test_cpu(cpu, sg_span)) || - group_balance_cpu(sg) == cpu) - groups = sg; + init_overlap_sched_group(sd, sg); if (!first) first = sg; @@ -579,7 +749,7 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu) last = sg; last->next = first; } - sd->groups = groups; + sd->groups = first; return 0; @@ -589,23 +759,106 @@ fail: return -ENOMEM; } -static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg) + +/* + * Package topology (also see the load-balance blurb in fair.c) + * + * The scheduler builds a tree structure to represent a number of important + * topology features. By default (default_topology[]) these include: + * + * - Simultaneous multithreading (SMT) + * - Multi-Core Cache (MC) + * - Package (DIE) + * + * Where the last one more or less denotes everything up to a NUMA node. + * + * The tree consists of 3 primary data structures: + * + * sched_domain -> sched_group -> sched_group_capacity + * ^ ^ ^ ^ + * `-' `-' + * + * The sched_domains are per-cpu and have a two way link (parent & child) and + * denote the ever growing mask of CPUs belonging to that level of topology. + * + * Each sched_domain has a circular (double) linked list of sched_group's, each + * denoting the domains of the level below (or individual CPUs in case of the + * first domain level). The sched_group linked by a sched_domain includes the + * CPU of that sched_domain [*]. + * + * Take for instance a 2 threaded, 2 core, 2 cache cluster part: + * + * CPU 0 1 2 3 4 5 6 7 + * + * DIE [ ] + * MC [ ] [ ] + * SMT [ ] [ ] [ ] [ ] + * + * - or - + * + * DIE 0-7 0-7 0-7 0-7 0-7 0-7 0-7 0-7 + * MC 0-3 0-3 0-3 0-3 4-7 4-7 4-7 4-7 + * SMT 0-1 0-1 2-3 2-3 4-5 4-5 6-7 6-7 + * + * CPU 0 1 2 3 4 5 6 7 + * + * One way to think about it is: sched_domain moves you up and down among these + * topology levels, while sched_group moves you sideways through it, at child + * domain granularity. + * + * sched_group_capacity ensures each unique sched_group has shared storage. + * + * There are two related construction problems, both require a CPU that + * uniquely identify each group (for a given domain): + * + * - The first is the balance_cpu (see should_we_balance() and the + * load-balance blub in fair.c); for each group we only want 1 CPU to + * continue balancing at a higher domain. + * + * - The second is the sched_group_capacity; we want all identical groups + * to share a single sched_group_capacity. + * + * Since these topologies are exclusive by construction. That is, its + * impossible for an SMT thread to belong to multiple cores, and cores to + * be part of multiple caches. There is a very clear and unique location + * for each CPU in the hierarchy. + * + * Therefore computing a unique CPU for each group is trivial (the iteration + * mask is redundant and set all 1s; all CPUs in a group will end up at _that_ + * group), we can simply pick the first CPU in each group. + * + * + * [*] in other words, the first group of each domain is its child domain. + */ + +static struct sched_group *get_group(int cpu, struct sd_data *sdd) { struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu); struct sched_domain *child = sd->child; + struct sched_group *sg; if (child) cpu = cpumask_first(sched_domain_span(child)); - if (sg) { - *sg = *per_cpu_ptr(sdd->sg, cpu); - (*sg)->sgc = *per_cpu_ptr(sdd->sgc, cpu); + sg = *per_cpu_ptr(sdd->sg, cpu); + sg->sgc = *per_cpu_ptr(sdd->sgc, cpu); + + /* For claim_allocations: */ + atomic_inc(&sg->ref); + atomic_inc(&sg->sgc->ref); - /* For claim_allocations: */ - atomic_set(&(*sg)->sgc->ref, 1); + if (child) { + cpumask_copy(sched_group_span(sg), sched_domain_span(child)); + cpumask_copy(group_balance_mask(sg), sched_group_span(sg)); + } else { + cpumask_set_cpu(cpu, sched_group_span(sg)); + cpumask_set_cpu(cpu, group_balance_mask(sg)); } - return cpu; + sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sched_group_span(sg)); + sg->sgc->min_capacity = SCHED_CAPACITY_SCALE; + + return sg; } /* @@ -624,34 +877,20 @@ build_sched_groups(struct sched_domain *sd, int cpu) struct cpumask *covered; int i; - get_group(cpu, sdd, &sd->groups); - atomic_inc(&sd->groups->ref); - - if (cpu != cpumask_first(span)) - return 0; - lockdep_assert_held(&sched_domains_mutex); covered = sched_domains_tmpmask; cpumask_clear(covered); - for_each_cpu(i, span) { + for_each_cpu_wrap(i, span, cpu) { struct sched_group *sg; - int group, j; if (cpumask_test_cpu(i, covered)) continue; - group = get_group(i, sdd, &sg); - cpumask_setall(sched_group_mask(sg)); + sg = get_group(i, sdd); - for_each_cpu(j, span) { - if (get_group(j, sdd, NULL) != group) - continue; - - cpumask_set_cpu(j, covered); - cpumask_set_cpu(j, sched_group_cpus(sg)); - } + cpumask_or(covered, covered, sched_group_span(sg)); if (!first) first = sg; @@ -660,6 +899,7 @@ build_sched_groups(struct sched_domain *sd, int cpu) last = sg; } last->next = first; + sd->groups = first; return 0; } @@ -683,12 +923,12 @@ static void init_sched_groups_capacity(int cpu, struct sched_domain *sd) do { int cpu, max_cpu = -1; - sg->group_weight = cpumask_weight(sched_group_cpus(sg)); + sg->group_weight = cpumask_weight(sched_group_span(sg)); if (!(sd->flags & SD_ASYM_PACKING)) goto next; - for_each_cpu(cpu, sched_group_cpus(sg)) { + for_each_cpu(cpu, sched_group_span(sg)) { if (max_cpu < 0) max_cpu = cpu; else if (sched_asym_prefer(cpu, max_cpu)) @@ -1308,6 +1548,10 @@ static int __sdt_alloc(const struct cpumask *cpu_map) if (!sgc) return -ENOMEM; +#ifdef CONFIG_SCHED_DEBUG + sgc->id = j; +#endif + *per_cpu_ptr(sdd->sgc, j) = sgc; } } @@ -1407,7 +1651,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att sd = build_sched_domain(tl, cpu_map, attr, sd, i); if (tl == sched_domain_topology) *per_cpu_ptr(d.sd, i) = sd; - if (tl->flags & SDTL_OVERLAP || sched_feat(FORCE_SD_OVERLAP)) + if (tl->flags & SDTL_OVERLAP) sd->flags |= SD_OVERLAP; if (cpumask_equal(cpu_map, sched_domain_span(sd))) break; @@ -1478,7 +1722,7 @@ static struct sched_domain_attr *dattr_cur; * cpumask) fails, then fallback to a single sched domain, * as determined by the single cpumask fallback_doms. */ -cpumask_var_t fallback_doms; +static cpumask_var_t fallback_doms; /* * arch_update_cpu_topology lets virtualized architectures update the @@ -1520,10 +1764,14 @@ void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms) * For now this just excludes isolated CPUs, but could be used to * exclude other special cases in the future. */ -int init_sched_domains(const struct cpumask *cpu_map) +int sched_init_domains(const struct cpumask *cpu_map) { int err; + zalloc_cpumask_var(&sched_domains_tmpmask, GFP_KERNEL); + zalloc_cpumask_var(&sched_domains_tmpmask2, GFP_KERNEL); + zalloc_cpumask_var(&fallback_doms, GFP_KERNEL); + arch_update_cpu_topology(); ndoms_cur = 1; doms_cur = alloc_sched_domains(ndoms_cur); diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index b8c84c6dee64..17f11c6b0a9f 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -12,44 +12,44 @@ #include <linux/hash.h> #include <linux/kthread.h> -void __init_waitqueue_head(wait_queue_head_t *q, const char *name, struct lock_class_key *key) +void __init_waitqueue_head(struct wait_queue_head *wq_head, const char *name, struct lock_class_key *key) { - spin_lock_init(&q->lock); - lockdep_set_class_and_name(&q->lock, key, name); - INIT_LIST_HEAD(&q->task_list); + spin_lock_init(&wq_head->lock); + lockdep_set_class_and_name(&wq_head->lock, key, name); + INIT_LIST_HEAD(&wq_head->head); } EXPORT_SYMBOL(__init_waitqueue_head); -void add_wait_queue(wait_queue_head_t *q, wait_queue_t *wait) +void add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { unsigned long flags; - wait->flags &= ~WQ_FLAG_EXCLUSIVE; - spin_lock_irqsave(&q->lock, flags); - __add_wait_queue(q, wait); - spin_unlock_irqrestore(&q->lock, flags); + wq_entry->flags &= ~WQ_FLAG_EXCLUSIVE; + spin_lock_irqsave(&wq_head->lock, flags); + __add_wait_queue_entry_tail(wq_head, wq_entry); + spin_unlock_irqrestore(&wq_head->lock, flags); } EXPORT_SYMBOL(add_wait_queue); -void add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t *wait) +void add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { unsigned long flags; - wait->flags |= WQ_FLAG_EXCLUSIVE; - spin_lock_irqsave(&q->lock, flags); - __add_wait_queue_tail(q, wait); - spin_unlock_irqrestore(&q->lock, flags); + wq_entry->flags |= WQ_FLAG_EXCLUSIVE; + spin_lock_irqsave(&wq_head->lock, flags); + __add_wait_queue_entry_tail(wq_head, wq_entry); + spin_unlock_irqrestore(&wq_head->lock, flags); } EXPORT_SYMBOL(add_wait_queue_exclusive); -void remove_wait_queue(wait_queue_head_t *q, wait_queue_t *wait) +void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { unsigned long flags; - spin_lock_irqsave(&q->lock, flags); - __remove_wait_queue(q, wait); - spin_unlock_irqrestore(&q->lock, flags); + spin_lock_irqsave(&wq_head->lock, flags); + __remove_wait_queue(wq_head, wq_entry); + spin_unlock_irqrestore(&wq_head->lock, flags); } EXPORT_SYMBOL(remove_wait_queue); @@ -63,12 +63,12 @@ EXPORT_SYMBOL(remove_wait_queue); * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns * zero in this (rare) case, and we handle it by continuing to scan the queue. */ -static void __wake_up_common(wait_queue_head_t *q, unsigned int mode, +static void __wake_up_common(struct wait_queue_head *wq_head, unsigned int mode, int nr_exclusive, int wake_flags, void *key) { - wait_queue_t *curr, *next; + wait_queue_entry_t *curr, *next; - list_for_each_entry_safe(curr, next, &q->task_list, task_list) { + list_for_each_entry_safe(curr, next, &wq_head->head, entry) { unsigned flags = curr->flags; if (curr->func(curr, mode, wake_flags, key) && @@ -79,7 +79,7 @@ static void __wake_up_common(wait_queue_head_t *q, unsigned int mode, /** * __wake_up - wake up threads blocked on a waitqueue. - * @q: the waitqueue + * @wq_head: the waitqueue * @mode: which threads * @nr_exclusive: how many wake-one or wake-many threads to wake up * @key: is directly passed to the wakeup function @@ -87,35 +87,35 @@ static void __wake_up_common(wait_queue_head_t *q, unsigned int mode, * It may be assumed that this function implies a write memory barrier before * changing the task state if and only if any tasks are woken up. */ -void __wake_up(wait_queue_head_t *q, unsigned int mode, +void __wake_up(struct wait_queue_head *wq_head, unsigned int mode, int nr_exclusive, void *key) { unsigned long flags; - spin_lock_irqsave(&q->lock, flags); - __wake_up_common(q, mode, nr_exclusive, 0, key); - spin_unlock_irqrestore(&q->lock, flags); + spin_lock_irqsave(&wq_head->lock, flags); + __wake_up_common(wq_head, mode, nr_exclusive, 0, key); + spin_unlock_irqrestore(&wq_head->lock, flags); } EXPORT_SYMBOL(__wake_up); /* * Same as __wake_up but called with the spinlock in wait_queue_head_t held. */ -void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr) +void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr) { - __wake_up_common(q, mode, nr, 0, NULL); + __wake_up_common(wq_head, mode, nr, 0, NULL); } EXPORT_SYMBOL_GPL(__wake_up_locked); -void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key) +void __wake_up_locked_key(struct wait_queue_head *wq_head, unsigned int mode, void *key) { - __wake_up_common(q, mode, 1, 0, key); + __wake_up_common(wq_head, mode, 1, 0, key); } EXPORT_SYMBOL_GPL(__wake_up_locked_key); /** * __wake_up_sync_key - wake up threads blocked on a waitqueue. - * @q: the waitqueue + * @wq_head: the waitqueue * @mode: which threads * @nr_exclusive: how many wake-one or wake-many threads to wake up * @key: opaque value to be passed to wakeup targets @@ -130,30 +130,30 @@ EXPORT_SYMBOL_GPL(__wake_up_locked_key); * It may be assumed that this function implies a write memory barrier before * changing the task state if and only if any tasks are woken up. */ -void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, +void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, int nr_exclusive, void *key) { unsigned long flags; int wake_flags = 1; /* XXX WF_SYNC */ - if (unlikely(!q)) + if (unlikely(!wq_head)) return; if (unlikely(nr_exclusive != 1)) wake_flags = 0; - spin_lock_irqsave(&q->lock, flags); - __wake_up_common(q, mode, nr_exclusive, wake_flags, key); - spin_unlock_irqrestore(&q->lock, flags); + spin_lock_irqsave(&wq_head->lock, flags); + __wake_up_common(wq_head, mode, nr_exclusive, wake_flags, key); + spin_unlock_irqrestore(&wq_head->lock, flags); } EXPORT_SYMBOL_GPL(__wake_up_sync_key); /* * __wake_up_sync - see __wake_up_sync_key() */ -void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive) +void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode, int nr_exclusive) { - __wake_up_sync_key(q, mode, nr_exclusive, NULL); + __wake_up_sync_key(wq_head, mode, nr_exclusive, NULL); } EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */ @@ -170,48 +170,48 @@ EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */ * loads to move into the critical region). */ void -prepare_to_wait(wait_queue_head_t *q, wait_queue_t *wait, int state) +prepare_to_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state) { unsigned long flags; - wait->flags &= ~WQ_FLAG_EXCLUSIVE; - spin_lock_irqsave(&q->lock, flags); - if (list_empty(&wait->task_list)) - __add_wait_queue(q, wait); + wq_entry->flags &= ~WQ_FLAG_EXCLUSIVE; + spin_lock_irqsave(&wq_head->lock, flags); + if (list_empty(&wq_entry->entry)) + __add_wait_queue(wq_head, wq_entry); set_current_state(state); - spin_unlock_irqrestore(&q->lock, flags); + spin_unlock_irqrestore(&wq_head->lock, flags); } EXPORT_SYMBOL(prepare_to_wait); void -prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state) +prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state) { unsigned long flags; - wait->flags |= WQ_FLAG_EXCLUSIVE; - spin_lock_irqsave(&q->lock, flags); - if (list_empty(&wait->task_list)) - __add_wait_queue_tail(q, wait); + wq_entry->flags |= WQ_FLAG_EXCLUSIVE; + spin_lock_irqsave(&wq_head->lock, flags); + if (list_empty(&wq_entry->entry)) + __add_wait_queue_entry_tail(wq_head, wq_entry); set_current_state(state); - spin_unlock_irqrestore(&q->lock, flags); + spin_unlock_irqrestore(&wq_head->lock, flags); } EXPORT_SYMBOL(prepare_to_wait_exclusive); -void init_wait_entry(wait_queue_t *wait, int flags) +void init_wait_entry(struct wait_queue_entry *wq_entry, int flags) { - wait->flags = flags; - wait->private = current; - wait->func = autoremove_wake_function; - INIT_LIST_HEAD(&wait->task_list); + wq_entry->flags = flags; + wq_entry->private = current; + wq_entry->func = autoremove_wake_function; + INIT_LIST_HEAD(&wq_entry->entry); } EXPORT_SYMBOL(init_wait_entry); -long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state) +long prepare_to_wait_event(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state) { unsigned long flags; long ret = 0; - spin_lock_irqsave(&q->lock, flags); + spin_lock_irqsave(&wq_head->lock, flags); if (unlikely(signal_pending_state(state, current))) { /* * Exclusive waiter must not fail if it was selected by wakeup, @@ -219,24 +219,24 @@ long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state) * * The caller will recheck the condition and return success if * we were already woken up, we can not miss the event because - * wakeup locks/unlocks the same q->lock. + * wakeup locks/unlocks the same wq_head->lock. * * But we need to ensure that set-condition + wakeup after that * can't see us, it should wake up another exclusive waiter if * we fail. */ - list_del_init(&wait->task_list); + list_del_init(&wq_entry->entry); ret = -ERESTARTSYS; } else { - if (list_empty(&wait->task_list)) { - if (wait->flags & WQ_FLAG_EXCLUSIVE) - __add_wait_queue_tail(q, wait); + if (list_empty(&wq_entry->entry)) { + if (wq_entry->flags & WQ_FLAG_EXCLUSIVE) + __add_wait_queue_entry_tail(wq_head, wq_entry); else - __add_wait_queue(q, wait); + __add_wait_queue(wq_head, wq_entry); } set_current_state(state); } - spin_unlock_irqrestore(&q->lock, flags); + spin_unlock_irqrestore(&wq_head->lock, flags); return ret; } @@ -249,10 +249,10 @@ EXPORT_SYMBOL(prepare_to_wait_event); * condition in the caller before they add the wait * entry to the wake queue. */ -int do_wait_intr(wait_queue_head_t *wq, wait_queue_t *wait) +int do_wait_intr(wait_queue_head_t *wq, wait_queue_entry_t *wait) { - if (likely(list_empty(&wait->task_list))) - __add_wait_queue_tail(wq, wait); + if (likely(list_empty(&wait->entry))) + __add_wait_queue_entry_tail(wq, wait); set_current_state(TASK_INTERRUPTIBLE); if (signal_pending(current)) @@ -265,10 +265,10 @@ int do_wait_intr(wait_queue_head_t *wq, wait_queue_t *wait) } EXPORT_SYMBOL(do_wait_intr); -int do_wait_intr_irq(wait_queue_head_t *wq, wait_queue_t *wait) +int do_wait_intr_irq(wait_queue_head_t *wq, wait_queue_entry_t *wait) { - if (likely(list_empty(&wait->task_list))) - __add_wait_queue_tail(wq, wait); + if (likely(list_empty(&wait->entry))) + __add_wait_queue_entry_tail(wq, wait); set_current_state(TASK_INTERRUPTIBLE); if (signal_pending(current)) @@ -283,14 +283,14 @@ EXPORT_SYMBOL(do_wait_intr_irq); /** * finish_wait - clean up after waiting in a queue - * @q: waitqueue waited on - * @wait: wait descriptor + * @wq_head: waitqueue waited on + * @wq_entry: wait descriptor * * Sets current thread back to running state and removes * the wait descriptor from the given waitqueue if still * queued. */ -void finish_wait(wait_queue_head_t *q, wait_queue_t *wait) +void finish_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { unsigned long flags; @@ -308,20 +308,20 @@ void finish_wait(wait_queue_head_t *q, wait_queue_t *wait) * have _one_ other CPU that looks at or modifies * the list). */ - if (!list_empty_careful(&wait->task_list)) { - spin_lock_irqsave(&q->lock, flags); - list_del_init(&wait->task_list); - spin_unlock_irqrestore(&q->lock, flags); + if (!list_empty_careful(&wq_entry->entry)) { + spin_lock_irqsave(&wq_head->lock, flags); + list_del_init(&wq_entry->entry); + spin_unlock_irqrestore(&wq_head->lock, flags); } } EXPORT_SYMBOL(finish_wait); -int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key) +int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key) { - int ret = default_wake_function(wait, mode, sync, key); + int ret = default_wake_function(wq_entry, mode, sync, key); if (ret) - list_del_init(&wait->task_list); + list_del_init(&wq_entry->entry); return ret; } EXPORT_SYMBOL(autoremove_wake_function); @@ -334,24 +334,24 @@ static inline bool is_kthread_should_stop(void) /* * DEFINE_WAIT_FUNC(wait, woken_wake_func); * - * add_wait_queue(&wq, &wait); + * add_wait_queue(&wq_head, &wait); * for (;;) { * if (condition) * break; * * p->state = mode; condition = true; * smp_mb(); // A smp_wmb(); // C - * if (!wait->flags & WQ_FLAG_WOKEN) wait->flags |= WQ_FLAG_WOKEN; + * if (!wq_entry->flags & WQ_FLAG_WOKEN) wq_entry->flags |= WQ_FLAG_WOKEN; * schedule() try_to_wake_up(); * p->state = TASK_RUNNING; ~~~~~~~~~~~~~~~~~~ - * wait->flags &= ~WQ_FLAG_WOKEN; condition = true; + * wq_entry->flags &= ~WQ_FLAG_WOKEN; condition = true; * smp_mb() // B smp_wmb(); // C - * wait->flags |= WQ_FLAG_WOKEN; + * wq_entry->flags |= WQ_FLAG_WOKEN; * } - * remove_wait_queue(&wq, &wait); + * remove_wait_queue(&wq_head, &wait); * */ -long wait_woken(wait_queue_t *wait, unsigned mode, long timeout) +long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout) { set_current_state(mode); /* A */ /* @@ -359,7 +359,7 @@ long wait_woken(wait_queue_t *wait, unsigned mode, long timeout) * woken_wake_function() such that if we observe WQ_FLAG_WOKEN we must * also observe all state before the wakeup. */ - if (!(wait->flags & WQ_FLAG_WOKEN) && !is_kthread_should_stop()) + if (!(wq_entry->flags & WQ_FLAG_WOKEN) && !is_kthread_should_stop()) timeout = schedule_timeout(timeout); __set_current_state(TASK_RUNNING); @@ -369,13 +369,13 @@ long wait_woken(wait_queue_t *wait, unsigned mode, long timeout) * condition being true _OR_ WQ_FLAG_WOKEN such that we will not miss * an event. */ - smp_store_mb(wait->flags, wait->flags & ~WQ_FLAG_WOKEN); /* B */ + smp_store_mb(wq_entry->flags, wq_entry->flags & ~WQ_FLAG_WOKEN); /* B */ return timeout; } EXPORT_SYMBOL(wait_woken); -int woken_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key) +int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key) { /* * Although this function is called under waitqueue lock, LOCK @@ -385,267 +385,8 @@ int woken_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key) * and is paired with smp_store_mb() in wait_woken(). */ smp_wmb(); /* C */ - wait->flags |= WQ_FLAG_WOKEN; + wq_entry->flags |= WQ_FLAG_WOKEN; - return default_wake_function(wait, mode, sync, key); + return default_wake_function(wq_entry, mode, sync, key); } EXPORT_SYMBOL(woken_wake_function); - -int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *arg) -{ - struct wait_bit_key *key = arg; - struct wait_bit_queue *wait_bit - = container_of(wait, struct wait_bit_queue, wait); - - if (wait_bit->key.flags != key->flags || - wait_bit->key.bit_nr != key->bit_nr || - test_bit(key->bit_nr, key->flags)) - return 0; - else - return autoremove_wake_function(wait, mode, sync, key); -} -EXPORT_SYMBOL(wake_bit_function); - -/* - * To allow interruptible waiting and asynchronous (i.e. nonblocking) - * waiting, the actions of __wait_on_bit() and __wait_on_bit_lock() are - * permitted return codes. Nonzero return codes halt waiting and return. - */ -int __sched -__wait_on_bit(wait_queue_head_t *wq, struct wait_bit_queue *q, - wait_bit_action_f *action, unsigned mode) -{ - int ret = 0; - - do { - prepare_to_wait(wq, &q->wait, mode); - if (test_bit(q->key.bit_nr, q->key.flags)) - ret = (*action)(&q->key, mode); - } while (test_bit(q->key.bit_nr, q->key.flags) && !ret); - finish_wait(wq, &q->wait); - return ret; -} -EXPORT_SYMBOL(__wait_on_bit); - -int __sched out_of_line_wait_on_bit(void *word, int bit, - wait_bit_action_f *action, unsigned mode) -{ - wait_queue_head_t *wq = bit_waitqueue(word, bit); - DEFINE_WAIT_BIT(wait, word, bit); - - return __wait_on_bit(wq, &wait, action, mode); -} -EXPORT_SYMBOL(out_of_line_wait_on_bit); - -int __sched out_of_line_wait_on_bit_timeout( - void *word, int bit, wait_bit_action_f *action, - unsigned mode, unsigned long timeout) -{ - wait_queue_head_t *wq = bit_waitqueue(word, bit); - DEFINE_WAIT_BIT(wait, word, bit); - - wait.key.timeout = jiffies + timeout; - return __wait_on_bit(wq, &wait, action, mode); -} -EXPORT_SYMBOL_GPL(out_of_line_wait_on_bit_timeout); - -int __sched -__wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q, - wait_bit_action_f *action, unsigned mode) -{ - int ret = 0; - - for (;;) { - prepare_to_wait_exclusive(wq, &q->wait, mode); - if (test_bit(q->key.bit_nr, q->key.flags)) { - ret = action(&q->key, mode); - /* - * See the comment in prepare_to_wait_event(). - * finish_wait() does not necessarily takes wq->lock, - * but test_and_set_bit() implies mb() which pairs with - * smp_mb__after_atomic() before wake_up_page(). - */ - if (ret) - finish_wait(wq, &q->wait); - } - if (!test_and_set_bit(q->key.bit_nr, q->key.flags)) { - if (!ret) - finish_wait(wq, &q->wait); - return 0; - } else if (ret) { - return ret; - } - } -} -EXPORT_SYMBOL(__wait_on_bit_lock); - -int __sched out_of_line_wait_on_bit_lock(void *word, int bit, - wait_bit_action_f *action, unsigned mode) -{ - wait_queue_head_t *wq = bit_waitqueue(word, bit); - DEFINE_WAIT_BIT(wait, word, bit); - - return __wait_on_bit_lock(wq, &wait, action, mode); -} -EXPORT_SYMBOL(out_of_line_wait_on_bit_lock); - -void __wake_up_bit(wait_queue_head_t *wq, void *word, int bit) -{ - struct wait_bit_key key = __WAIT_BIT_KEY_INITIALIZER(word, bit); - if (waitqueue_active(wq)) - __wake_up(wq, TASK_NORMAL, 1, &key); -} -EXPORT_SYMBOL(__wake_up_bit); - -/** - * wake_up_bit - wake up a waiter on a bit - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on - * - * There is a standard hashed waitqueue table for generic use. This - * is the part of the hashtable's accessor API that wakes up waiters - * on a bit. For instance, if one were to have waiters on a bitflag, - * one would call wake_up_bit() after clearing the bit. - * - * In order for this to function properly, as it uses waitqueue_active() - * internally, some kind of memory barrier must be done prior to calling - * this. Typically, this will be smp_mb__after_atomic(), but in some - * cases where bitflags are manipulated non-atomically under a lock, one - * may need to use a less regular barrier, such fs/inode.c's smp_mb(), - * because spin_unlock() does not guarantee a memory barrier. - */ -void wake_up_bit(void *word, int bit) -{ - __wake_up_bit(bit_waitqueue(word, bit), word, bit); -} -EXPORT_SYMBOL(wake_up_bit); - -/* - * Manipulate the atomic_t address to produce a better bit waitqueue table hash - * index (we're keying off bit -1, but that would produce a horrible hash - * value). - */ -static inline wait_queue_head_t *atomic_t_waitqueue(atomic_t *p) -{ - if (BITS_PER_LONG == 64) { - unsigned long q = (unsigned long)p; - return bit_waitqueue((void *)(q & ~1), q & 1); - } - return bit_waitqueue(p, 0); -} - -static int wake_atomic_t_function(wait_queue_t *wait, unsigned mode, int sync, - void *arg) -{ - struct wait_bit_key *key = arg; - struct wait_bit_queue *wait_bit - = container_of(wait, struct wait_bit_queue, wait); - atomic_t *val = key->flags; - - if (wait_bit->key.flags != key->flags || - wait_bit->key.bit_nr != key->bit_nr || - atomic_read(val) != 0) - return 0; - return autoremove_wake_function(wait, mode, sync, key); -} - -/* - * To allow interruptible waiting and asynchronous (i.e. nonblocking) waiting, - * the actions of __wait_on_atomic_t() are permitted return codes. Nonzero - * return codes halt waiting and return. - */ -static __sched -int __wait_on_atomic_t(wait_queue_head_t *wq, struct wait_bit_queue *q, - int (*action)(atomic_t *), unsigned mode) -{ - atomic_t *val; - int ret = 0; - - do { - prepare_to_wait(wq, &q->wait, mode); - val = q->key.flags; - if (atomic_read(val) == 0) - break; - ret = (*action)(val); - } while (!ret && atomic_read(val) != 0); - finish_wait(wq, &q->wait); - return ret; -} - -#define DEFINE_WAIT_ATOMIC_T(name, p) \ - struct wait_bit_queue name = { \ - .key = __WAIT_ATOMIC_T_KEY_INITIALIZER(p), \ - .wait = { \ - .private = current, \ - .func = wake_atomic_t_function, \ - .task_list = \ - LIST_HEAD_INIT((name).wait.task_list), \ - }, \ - } - -__sched int out_of_line_wait_on_atomic_t(atomic_t *p, int (*action)(atomic_t *), - unsigned mode) -{ - wait_queue_head_t *wq = atomic_t_waitqueue(p); - DEFINE_WAIT_ATOMIC_T(wait, p); - - return __wait_on_atomic_t(wq, &wait, action, mode); -} -EXPORT_SYMBOL(out_of_line_wait_on_atomic_t); - -/** - * wake_up_atomic_t - Wake up a waiter on a atomic_t - * @p: The atomic_t being waited on, a kernel virtual address - * - * Wake up anyone waiting for the atomic_t to go to zero. - * - * Abuse the bit-waker function and its waitqueue hash table set (the atomic_t - * check is done by the waiter's wake function, not the by the waker itself). - */ -void wake_up_atomic_t(atomic_t *p) -{ - __wake_up_bit(atomic_t_waitqueue(p), p, WAIT_ATOMIC_T_BIT_NR); -} -EXPORT_SYMBOL(wake_up_atomic_t); - -__sched int bit_wait(struct wait_bit_key *word, int mode) -{ - schedule(); - if (signal_pending_state(mode, current)) - return -EINTR; - return 0; -} -EXPORT_SYMBOL(bit_wait); - -__sched int bit_wait_io(struct wait_bit_key *word, int mode) -{ - io_schedule(); - if (signal_pending_state(mode, current)) - return -EINTR; - return 0; -} -EXPORT_SYMBOL(bit_wait_io); - -__sched int bit_wait_timeout(struct wait_bit_key *word, int mode) -{ - unsigned long now = READ_ONCE(jiffies); - if (time_after_eq(now, word->timeout)) - return -EAGAIN; - schedule_timeout(word->timeout - now); - if (signal_pending_state(mode, current)) - return -EINTR; - return 0; -} -EXPORT_SYMBOL_GPL(bit_wait_timeout); - -__sched int bit_wait_io_timeout(struct wait_bit_key *word, int mode) -{ - unsigned long now = READ_ONCE(jiffies); - if (time_after_eq(now, word->timeout)) - return -EAGAIN; - io_schedule_timeout(word->timeout - now); - if (signal_pending_state(mode, current)) - return -EINTR; - return 0; -} -EXPORT_SYMBOL_GPL(bit_wait_io_timeout); diff --git a/kernel/sched/wait_bit.c b/kernel/sched/wait_bit.c new file mode 100644 index 000000000000..f8159698aa4d --- /dev/null +++ b/kernel/sched/wait_bit.c @@ -0,0 +1,286 @@ +/* + * The implementation of the wait_bit*() and related waiting APIs: + */ +#include <linux/wait_bit.h> +#include <linux/sched/signal.h> +#include <linux/sched/debug.h> +#include <linux/hash.h> + +#define WAIT_TABLE_BITS 8 +#define WAIT_TABLE_SIZE (1 << WAIT_TABLE_BITS) + +static wait_queue_head_t bit_wait_table[WAIT_TABLE_SIZE] __cacheline_aligned; + +wait_queue_head_t *bit_waitqueue(void *word, int bit) +{ + const int shift = BITS_PER_LONG == 32 ? 5 : 6; + unsigned long val = (unsigned long)word << shift | bit; + + return bit_wait_table + hash_long(val, WAIT_TABLE_BITS); +} +EXPORT_SYMBOL(bit_waitqueue); + +int wake_bit_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *arg) +{ + struct wait_bit_key *key = arg; + struct wait_bit_queue_entry *wait_bit = container_of(wq_entry, struct wait_bit_queue_entry, wq_entry); + + if (wait_bit->key.flags != key->flags || + wait_bit->key.bit_nr != key->bit_nr || + test_bit(key->bit_nr, key->flags)) + return 0; + else + return autoremove_wake_function(wq_entry, mode, sync, key); +} +EXPORT_SYMBOL(wake_bit_function); + +/* + * To allow interruptible waiting and asynchronous (i.e. nonblocking) + * waiting, the actions of __wait_on_bit() and __wait_on_bit_lock() are + * permitted return codes. Nonzero return codes halt waiting and return. + */ +int __sched +__wait_on_bit(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, + wait_bit_action_f *action, unsigned mode) +{ + int ret = 0; + + do { + prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode); + if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags)) + ret = (*action)(&wbq_entry->key, mode); + } while (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret); + finish_wait(wq_head, &wbq_entry->wq_entry); + return ret; +} +EXPORT_SYMBOL(__wait_on_bit); + +int __sched out_of_line_wait_on_bit(void *word, int bit, + wait_bit_action_f *action, unsigned mode) +{ + struct wait_queue_head *wq_head = bit_waitqueue(word, bit); + DEFINE_WAIT_BIT(wq_entry, word, bit); + + return __wait_on_bit(wq_head, &wq_entry, action, mode); +} +EXPORT_SYMBOL(out_of_line_wait_on_bit); + +int __sched out_of_line_wait_on_bit_timeout( + void *word, int bit, wait_bit_action_f *action, + unsigned mode, unsigned long timeout) +{ + struct wait_queue_head *wq_head = bit_waitqueue(word, bit); + DEFINE_WAIT_BIT(wq_entry, word, bit); + + wq_entry.key.timeout = jiffies + timeout; + return __wait_on_bit(wq_head, &wq_entry, action, mode); +} +EXPORT_SYMBOL_GPL(out_of_line_wait_on_bit_timeout); + +int __sched +__wait_on_bit_lock(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, + wait_bit_action_f *action, unsigned mode) +{ + int ret = 0; + + for (;;) { + prepare_to_wait_exclusive(wq_head, &wbq_entry->wq_entry, mode); + if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags)) { + ret = action(&wbq_entry->key, mode); + /* + * See the comment in prepare_to_wait_event(). + * finish_wait() does not necessarily takes wwq_head->lock, + * but test_and_set_bit() implies mb() which pairs with + * smp_mb__after_atomic() before wake_up_page(). + */ + if (ret) + finish_wait(wq_head, &wbq_entry->wq_entry); + } + if (!test_and_set_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags)) { + if (!ret) + finish_wait(wq_head, &wbq_entry->wq_entry); + return 0; + } else if (ret) { + return ret; + } + } +} +EXPORT_SYMBOL(__wait_on_bit_lock); + +int __sched out_of_line_wait_on_bit_lock(void *word, int bit, + wait_bit_action_f *action, unsigned mode) +{ + struct wait_queue_head *wq_head = bit_waitqueue(word, bit); + DEFINE_WAIT_BIT(wq_entry, word, bit); + + return __wait_on_bit_lock(wq_head, &wq_entry, action, mode); +} +EXPORT_SYMBOL(out_of_line_wait_on_bit_lock); + +void __wake_up_bit(struct wait_queue_head *wq_head, void *word, int bit) +{ + struct wait_bit_key key = __WAIT_BIT_KEY_INITIALIZER(word, bit); + if (waitqueue_active(wq_head)) + __wake_up(wq_head, TASK_NORMAL, 1, &key); +} +EXPORT_SYMBOL(__wake_up_bit); + +/** + * wake_up_bit - wake up a waiter on a bit + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * + * There is a standard hashed waitqueue table for generic use. This + * is the part of the hashtable's accessor API that wakes up waiters + * on a bit. For instance, if one were to have waiters on a bitflag, + * one would call wake_up_bit() after clearing the bit. + * + * In order for this to function properly, as it uses waitqueue_active() + * internally, some kind of memory barrier must be done prior to calling + * this. Typically, this will be smp_mb__after_atomic(), but in some + * cases where bitflags are manipulated non-atomically under a lock, one + * may need to use a less regular barrier, such fs/inode.c's smp_mb(), + * because spin_unlock() does not guarantee a memory barrier. + */ +void wake_up_bit(void *word, int bit) +{ + __wake_up_bit(bit_waitqueue(word, bit), word, bit); +} +EXPORT_SYMBOL(wake_up_bit); + +/* + * Manipulate the atomic_t address to produce a better bit waitqueue table hash + * index (we're keying off bit -1, but that would produce a horrible hash + * value). + */ +static inline wait_queue_head_t *atomic_t_waitqueue(atomic_t *p) +{ + if (BITS_PER_LONG == 64) { + unsigned long q = (unsigned long)p; + return bit_waitqueue((void *)(q & ~1), q & 1); + } + return bit_waitqueue(p, 0); +} + +static int wake_atomic_t_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, + void *arg) +{ + struct wait_bit_key *key = arg; + struct wait_bit_queue_entry *wait_bit = container_of(wq_entry, struct wait_bit_queue_entry, wq_entry); + atomic_t *val = key->flags; + + if (wait_bit->key.flags != key->flags || + wait_bit->key.bit_nr != key->bit_nr || + atomic_read(val) != 0) + return 0; + return autoremove_wake_function(wq_entry, mode, sync, key); +} + +/* + * To allow interruptible waiting and asynchronous (i.e. nonblocking) waiting, + * the actions of __wait_on_atomic_t() are permitted return codes. Nonzero + * return codes halt waiting and return. + */ +static __sched +int __wait_on_atomic_t(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, + int (*action)(atomic_t *), unsigned mode) +{ + atomic_t *val; + int ret = 0; + + do { + prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode); + val = wbq_entry->key.flags; + if (atomic_read(val) == 0) + break; + ret = (*action)(val); + } while (!ret && atomic_read(val) != 0); + finish_wait(wq_head, &wbq_entry->wq_entry); + return ret; +} + +#define DEFINE_WAIT_ATOMIC_T(name, p) \ + struct wait_bit_queue_entry name = { \ + .key = __WAIT_ATOMIC_T_KEY_INITIALIZER(p), \ + .wq_entry = { \ + .private = current, \ + .func = wake_atomic_t_function, \ + .entry = \ + LIST_HEAD_INIT((name).wq_entry.entry), \ + }, \ + } + +__sched int out_of_line_wait_on_atomic_t(atomic_t *p, int (*action)(atomic_t *), + unsigned mode) +{ + struct wait_queue_head *wq_head = atomic_t_waitqueue(p); + DEFINE_WAIT_ATOMIC_T(wq_entry, p); + + return __wait_on_atomic_t(wq_head, &wq_entry, action, mode); +} +EXPORT_SYMBOL(out_of_line_wait_on_atomic_t); + +/** + * wake_up_atomic_t - Wake up a waiter on a atomic_t + * @p: The atomic_t being waited on, a kernel virtual address + * + * Wake up anyone waiting for the atomic_t to go to zero. + * + * Abuse the bit-waker function and its waitqueue hash table set (the atomic_t + * check is done by the waiter's wake function, not the by the waker itself). + */ +void wake_up_atomic_t(atomic_t *p) +{ + __wake_up_bit(atomic_t_waitqueue(p), p, WAIT_ATOMIC_T_BIT_NR); +} +EXPORT_SYMBOL(wake_up_atomic_t); + +__sched int bit_wait(struct wait_bit_key *word, int mode) +{ + schedule(); + if (signal_pending_state(mode, current)) + return -EINTR; + return 0; +} +EXPORT_SYMBOL(bit_wait); + +__sched int bit_wait_io(struct wait_bit_key *word, int mode) +{ + io_schedule(); + if (signal_pending_state(mode, current)) + return -EINTR; + return 0; +} +EXPORT_SYMBOL(bit_wait_io); + +__sched int bit_wait_timeout(struct wait_bit_key *word, int mode) +{ + unsigned long now = READ_ONCE(jiffies); + if (time_after_eq(now, word->timeout)) + return -EAGAIN; + schedule_timeout(word->timeout - now); + if (signal_pending_state(mode, current)) + return -EINTR; + return 0; +} +EXPORT_SYMBOL_GPL(bit_wait_timeout); + +__sched int bit_wait_io_timeout(struct wait_bit_key *word, int mode) +{ + unsigned long now = READ_ONCE(jiffies); + if (time_after_eq(now, word->timeout)) + return -EAGAIN; + io_schedule_timeout(word->timeout - now); + if (signal_pending_state(mode, current)) + return -EINTR; + return 0; +} +EXPORT_SYMBOL_GPL(bit_wait_io_timeout); + +void __init wait_bit_init(void) +{ + int i; + + for (i = 0; i < WAIT_TABLE_SIZE; i++) + init_waitqueue_head(bit_wait_table + i); +} diff --git a/kernel/signal.c b/kernel/signal.c index d031cd24f8a9..35a570f71f07 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -511,7 +511,8 @@ int unhandled_signal(struct task_struct *tsk, int sig) return !tsk->ptrace; } -static void collect_signal(int sig, struct sigpending *list, siginfo_t *info) +static void collect_signal(int sig, struct sigpending *list, siginfo_t *info, + bool *resched_timer) { struct sigqueue *q, *first = NULL; @@ -533,6 +534,12 @@ static void collect_signal(int sig, struct sigpending *list, siginfo_t *info) still_pending: list_del_init(&first->list); copy_siginfo(info, &first->info); + + *resched_timer = + (first->flags & SIGQUEUE_PREALLOC) && + (info->si_code == SI_TIMER) && + (info->si_sys_private); + __sigqueue_free(first); } else { /* @@ -549,12 +556,12 @@ still_pending: } static int __dequeue_signal(struct sigpending *pending, sigset_t *mask, - siginfo_t *info) + siginfo_t *info, bool *resched_timer) { int sig = next_signal(pending, mask); if (sig) - collect_signal(sig, pending, info); + collect_signal(sig, pending, info, resched_timer); return sig; } @@ -566,15 +573,16 @@ static int __dequeue_signal(struct sigpending *pending, sigset_t *mask, */ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) { + bool resched_timer = false; int signr; /* We only dequeue private signals from ourselves, we don't let * signalfd steal them */ - signr = __dequeue_signal(&tsk->pending, mask, info); + signr = __dequeue_signal(&tsk->pending, mask, info, &resched_timer); if (!signr) { signr = __dequeue_signal(&tsk->signal->shared_pending, - mask, info); + mask, info, &resched_timer); #ifdef CONFIG_POSIX_TIMERS /* * itimer signal ? @@ -622,7 +630,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) current->jobctl |= JOBCTL_STOP_DEQUEUED; } #ifdef CONFIG_POSIX_TIMERS - if ((info->si_code & __SI_MASK) == __SI_TIMER && info->si_sys_private) { + if (resched_timer) { /* * Release the siglock to ensure proper locking order * of timer locks outside of siglocks. Note, we leave @@ -2093,7 +2101,6 @@ static void do_jobctl_trap(void) static int ptrace_signal(int signr, siginfo_t *info) { - ptrace_signal_deliver(); /* * We do not check sig_kernel_stop(signr) but set this marker * unconditionally because we do not know whether debugger will diff --git a/kernel/smp.c b/kernel/smp.c index a817769b53c0..3061483cb3ad 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -30,6 +30,7 @@ enum { struct call_function_data { struct call_single_data __percpu *csd; cpumask_var_t cpumask; + cpumask_var_t cpumask_ipi; }; static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_function_data, cfd_data); @@ -45,9 +46,15 @@ int smpcfd_prepare_cpu(unsigned int cpu) if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL, cpu_to_node(cpu))) return -ENOMEM; + if (!zalloc_cpumask_var_node(&cfd->cpumask_ipi, GFP_KERNEL, + cpu_to_node(cpu))) { + free_cpumask_var(cfd->cpumask); + return -ENOMEM; + } cfd->csd = alloc_percpu(struct call_single_data); if (!cfd->csd) { free_cpumask_var(cfd->cpumask); + free_cpumask_var(cfd->cpumask_ipi); return -ENOMEM; } @@ -59,6 +66,7 @@ int smpcfd_dead_cpu(unsigned int cpu) struct call_function_data *cfd = &per_cpu(cfd_data, cpu); free_cpumask_var(cfd->cpumask); + free_cpumask_var(cfd->cpumask_ipi); free_percpu(cfd->csd); return 0; } @@ -428,12 +436,13 @@ void smp_call_function_many(const struct cpumask *mask, cfd = this_cpu_ptr(&cfd_data); cpumask_and(cfd->cpumask, mask, cpu_online_mask); - cpumask_clear_cpu(this_cpu, cfd->cpumask); + __cpumask_clear_cpu(this_cpu, cfd->cpumask); /* Some callers race with other cpus changing the passed mask */ if (unlikely(!cpumask_weight(cfd->cpumask))) return; + cpumask_clear(cfd->cpumask_ipi); for_each_cpu(cpu, cfd->cpumask) { struct call_single_data *csd = per_cpu_ptr(cfd->csd, cpu); @@ -442,11 +451,12 @@ void smp_call_function_many(const struct cpumask *mask, csd->flags |= CSD_FLAG_SYNCHRONOUS; csd->func = func; csd->info = info; - llist_add(&csd->llist, &per_cpu(call_single_queue, cpu)); + if (llist_add(&csd->llist, &per_cpu(call_single_queue, cpu))) + __cpumask_set_cpu(cpu, cfd->cpumask_ipi); } /* Send a message to all CPUs in the map */ - arch_send_call_function_ipi_mask(cfd->cpumask); + arch_send_call_function_ipi_mask(cfd->cpumask_ipi); if (wait) { for_each_cpu(cpu, cfd->cpumask) { diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c index ece4b177052b..939a158eab11 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -1119,7 +1119,7 @@ static ssize_t bin_uuid(struct file *file, /* Only supports reads */ if (oldval && oldlen) { char buf[UUID_STRING_LEN + 1]; - uuid_be uuid; + uuid_t uuid; result = kernel_read(file, 0, buf, sizeof(buf) - 1); if (result < 0) @@ -1128,7 +1128,7 @@ static ssize_t bin_uuid(struct file *file, buf[result] = '\0'; result = -EIO; - if (uuid_be_to_bin(buf, &uuid)) + if (uuid_parse(buf, &uuid)) goto out; if (oldlen > 16) diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index 4008d9f95dd7..ac09bc29eb08 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -126,56 +126,6 @@ config NO_HZ_FULL_ALL Note the boot CPU will still be kept outside the range to handle the timekeeping duty. -config NO_HZ_FULL_SYSIDLE - bool "Detect full-system idle state for full dynticks system" - depends on NO_HZ_FULL - default n - help - At least one CPU must keep the scheduling-clock tick running for - timekeeping purposes whenever there is a non-idle CPU, where - "non-idle" also includes dynticks CPUs as long as they are - running non-idle tasks. Because the underlying adaptive-tick - support cannot distinguish between all CPUs being idle and - all CPUs each running a single task in dynticks mode, the - underlying support simply ensures that there is always a CPU - handling the scheduling-clock tick, whether or not all CPUs - are idle. This Kconfig option enables scalable detection of - the all-CPUs-idle state, thus allowing the scheduling-clock - tick to be disabled when all CPUs are idle. Note that scalable - detection of the all-CPUs-idle state means that larger systems - will be slower to declare the all-CPUs-idle state. - - Say Y if you would like to help debug all-CPUs-idle detection. - - Say N if you are unsure. - -config NO_HZ_FULL_SYSIDLE_SMALL - int "Number of CPUs above which large-system approach is used" - depends on NO_HZ_FULL_SYSIDLE - range 1 NR_CPUS - default 8 - help - The full-system idle detection mechanism takes a lazy approach - on large systems, as is required to attain decent scalability. - However, on smaller systems, scalability is not anywhere near as - large a concern as is energy efficiency. The sysidle subsystem - therefore uses a fast but non-scalable algorithm for small - systems and a lazier but scalable algorithm for large systems. - This Kconfig parameter defines the number of CPUs in the largest - system that will be considered to be "small". - - The default value will be fine in most cases. Battery-powered - systems that (1) enable NO_HZ_FULL_SYSIDLE, (2) have larger - numbers of CPUs, and (3) are suffering from battery-lifetime - problems due to long sysidle latencies might wish to experiment - with larger values for this Kconfig parameter. On the other - hand, they might be even better served by disabling NO_HZ_FULL - entirely, given that NO_HZ_FULL is intended for HPC and - real-time workloads that at present do not tend to be run on - battery-powered systems. - - Take the default if you are unsure. - config NO_HZ bool "Old Idle dynticks config" depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 93621ae718d3..03918a19cf2d 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -233,6 +233,9 @@ static void clocksource_watchdog(unsigned long data) continue; } + if (cs == curr_clocksource && cs->tick_stable) + cs->tick_stable(cs); + if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) && (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) && (watchdog->flags & CLOCK_SOURCE_IS_CONTINUOUS)) { diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 64c97fc130c4..c7a899c5ce64 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -150,6 +150,12 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) touch_softlockup_watchdog_sched(); if (is_idle_task(current)) ts->idle_jiffies++; + /* + * In case the current tick fired too early past its expected + * expiration, make sure we don't bypass the next clock reprogramming + * to the same deadline. + */ + ts->next_tick = 0; } #endif update_process_times(user_mode(regs)); @@ -554,7 +560,7 @@ static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now) update_ts_time_stats(smp_processor_id(), ts, now, NULL); ts->idle_active = 0; - sched_clock_idle_wakeup_event(0); + sched_clock_idle_wakeup_event(); } static ktime_t tick_nohz_start_idle(struct tick_sched *ts) @@ -660,6 +666,12 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED); else tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); + + /* + * Reset to make sure next tick stop doesn't get fooled by past + * cached clock deadline. + */ + ts->next_tick = 0; } static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, @@ -701,8 +713,6 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, */ delta = next_tick - basemono; if (delta <= (u64)TICK_NSEC) { - tick = 0; - /* * Tell the timer code that the base is not idle, i.e. undo * the effect of get_next_timer_interrupt(): @@ -712,23 +722,8 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, * We've not stopped the tick yet, and there's a timer in the * next period, so no point in stopping it either, bail. */ - if (!ts->tick_stopped) - goto out; - - /* - * If, OTOH, we did stop it, but there's a pending (expired) - * timer reprogram the timer hardware to fire now. - * - * We will not restart the tick proper, just prod the timer - * hardware into firing an interrupt to process the pending - * timers. Just like tick_irq_exit() will not restart the tick - * for 'normal' interrupts. - * - * Only once we exit the idle loop will we re-enable the tick, - * see tick_nohz_idle_exit(). - */ - if (delta == 0) { - tick_nohz_restart(ts, now); + if (!ts->tick_stopped) { + tick = 0; goto out; } } @@ -771,8 +766,16 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, tick = expires; /* Skip reprogram of event if its not changed */ - if (ts->tick_stopped && (expires == dev->next_event)) - goto out; + if (ts->tick_stopped && (expires == ts->next_tick)) { + /* Sanity check: make sure clockevent is actually programmed */ + if (tick == KTIME_MAX || ts->next_tick == hrtimer_get_expires(&ts->sched_timer)) + goto out; + + WARN_ON_ONCE(1); + printk_once("basemono: %llu ts->next_tick: %llu dev->next_event: %llu timer->active: %d timer->expires: %llu\n", + basemono, ts->next_tick, dev->next_event, + hrtimer_active(&ts->sched_timer), hrtimer_get_expires(&ts->sched_timer)); + } /* * nohz_stop_sched_tick can be called several times before @@ -782,8 +785,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, * the scheduler tick in nohz_restart_sched_tick. */ if (!ts->tick_stopped) { - nohz_balance_enter_idle(cpu); - calc_load_enter_idle(); + calc_load_nohz_start(); cpu_load_update_nohz_start(); ts->last_tick = hrtimer_get_expires(&ts->sched_timer); @@ -791,6 +793,8 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, trace_tick_stop(1, TICK_DEP_MASK_NONE); } + ts->next_tick = tick; + /* * If the expiration time == KTIME_MAX, then we simply stop * the tick timer. @@ -801,12 +805,17 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, goto out; } + hrtimer_set_expires(&ts->sched_timer, tick); + if (ts->nohz_mode == NOHZ_MODE_HIGHRES) - hrtimer_start(&ts->sched_timer, tick, HRTIMER_MODE_ABS_PINNED); + hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED); else tick_program_event(tick, 1); out: - /* Update the estimated sleep length */ + /* + * Update the estimated sleep length until the next timer + * (not only the tick). + */ ts->sleep_length = ktime_sub(dev->next_event, now); return tick; } @@ -823,7 +832,7 @@ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now) */ timer_clear_idle(); - calc_load_exit_idle(); + calc_load_nohz_stop(); touch_softlockup_watchdog_sched(); /* * Cancel the scheduled timer and restore the tick @@ -864,6 +873,11 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) if (unlikely(!cpu_online(cpu))) { if (cpu == tick_do_timer_cpu) tick_do_timer_cpu = TICK_DO_TIMER_NONE; + /* + * Make sure the CPU doesn't get fooled by obsolete tick + * deadline if it comes back online later. + */ + ts->next_tick = 0; return false; } @@ -923,8 +937,10 @@ static void __tick_nohz_idle_enter(struct tick_sched *ts) ts->idle_expires = expires; } - if (!was_stopped && ts->tick_stopped) + if (!was_stopped && ts->tick_stopped) { ts->idle_jiffies = ts->last_jiffies; + nohz_balance_enter_idle(cpu); + } } } @@ -1172,6 +1188,8 @@ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer) */ if (regs) tick_sched_handle(ts, regs); + else + ts->next_tick = 0; /* No need to reprogram if we are in idle or full dynticks mode */ if (unlikely(ts->tick_stopped)) diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h index bf38226e5c17..075444e3d48e 100644 --- a/kernel/time/tick-sched.h +++ b/kernel/time/tick-sched.h @@ -27,6 +27,7 @@ enum tick_nohz_mode { * timer is modified for nohz sleeps. This is necessary * to resume the tick timer operation in the timeline * when the CPU returns from nohz sleep. + * @next_tick: Next tick to be fired when in dynticks mode. * @tick_stopped: Indicator that the idle tick has been stopped * @idle_jiffies: jiffies at the entry to idle for idle time accounting * @idle_calls: Total number of idle calls @@ -44,6 +45,7 @@ struct tick_sched { unsigned long check_clocks; enum tick_nohz_mode nohz_mode; ktime_t last_tick; + ktime_t next_tick; int inidle; int tick_stopped; unsigned long idle_jiffies; diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 193c5f5e3f79..bc364f86100a 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -867,7 +867,7 @@ static void blk_add_trace_split(void *ignore, __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf, - BLK_TA_SPLIT, bio->bi_error, sizeof(rpdu), + BLK_TA_SPLIT, bio->bi_status, sizeof(rpdu), &rpdu); } } @@ -900,7 +900,7 @@ static void blk_add_trace_bio_remap(void *ignore, r.sector_from = cpu_to_be64(from); __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, - bio_op(bio), bio->bi_opf, BLK_TA_REMAP, bio->bi_error, + bio_op(bio), bio->bi_opf, BLK_TA_REMAP, bio->bi_status, sizeof(r), &r); } diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 9e5841dc14b5..b308be30dfb9 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -4337,9 +4337,6 @@ static int ftrace_process_regex(struct ftrace_iterator *iter, command = strsep(&next, ":"); - if (WARN_ON_ONCE(!tr)) - return -EINVAL; - mutex_lock(&ftrace_cmd_mutex); list_for_each_entry(p, &ftrace_commands, list) { if (strcmp(p->name, command) == 0) { diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 1122f151466f..091e801145c9 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6881,6 +6881,9 @@ ftrace_trace_snapshot_callback(struct trace_array *tr, struct ftrace_hash *hash, char *number; int ret; + if (!tr) + return -ENODEV; + /* hash funcs only work with set_ftrace_filter */ if (!enable) return -EINVAL; diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index a3bddbfd0874..a0910c0cdf2e 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -654,6 +654,9 @@ ftrace_trace_onoff_callback(struct trace_array *tr, struct ftrace_hash *hash, { struct ftrace_probe_ops *ops; + if (!tr) + return -ENODEV; + /* we register both traceon and traceoff to this callback */ if (strcmp(cmd, "traceon") == 0) ops = param ? &traceon_count_probe_ops : &traceon_probe_ops; @@ -670,6 +673,9 @@ ftrace_stacktrace_callback(struct trace_array *tr, struct ftrace_hash *hash, { struct ftrace_probe_ops *ops; + if (!tr) + return -ENODEV; + ops = param ? &stacktrace_count_probe_ops : &stacktrace_probe_ops; return ftrace_trace_probe_callback(tr, ops, hash, glob, cmd, @@ -682,6 +688,9 @@ ftrace_dump_callback(struct trace_array *tr, struct ftrace_hash *hash, { struct ftrace_probe_ops *ops; + if (!tr) + return -ENODEV; + ops = &dump_probe_ops; /* Only dump once. */ @@ -695,6 +704,9 @@ ftrace_cpudump_callback(struct trace_array *tr, struct ftrace_hash *hash, { struct ftrace_probe_ops *ops; + if (!tr) + return -ENODEV; + ops = &cpudump_probe_ops; /* Only dump once. */ diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index c129fca6ec99..b53c8d369163 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -707,20 +707,16 @@ static int create_trace_kprobe(int argc, char **argv) pr_info("Probe point is not specified.\n"); return -EINVAL; } - if (isdigit(argv[1][0])) { - /* an address specified */ - ret = kstrtoul(&argv[1][0], 0, (unsigned long *)&addr); - if (ret) { - pr_info("Failed to parse address.\n"); - return ret; - } - } else { + + /* try to parse an address. if that fails, try to read the + * input as a symbol. */ + if (kstrtoul(argv[1], 0, (unsigned long *)&addr)) { /* a symbol specified */ symbol = argv[1]; /* TODO: support .init module functions */ ret = traceprobe_split_symbol_offset(symbol, &offset); if (ret) { - pr_info("Failed to parse symbol.\n"); + pr_info("Failed to parse either an address or a symbol.\n"); return ret; } if (offset && is_return && diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 76aa04d4c925..b4a751e8f9d6 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -409,7 +409,9 @@ static const struct file_operations stack_trace_fops = { static int stack_trace_filter_open(struct inode *inode, struct file *file) { - return ftrace_regex_open(&trace_ops, FTRACE_ITER_FILTER, + struct ftrace_ops *ops = inode->i_private; + + return ftrace_regex_open(ops, FTRACE_ITER_FILTER, inode, file); } @@ -476,7 +478,7 @@ static __init int stack_trace_init(void) NULL, &stack_trace_fops); trace_create_file("stack_trace_filter", 0444, d_tracer, - NULL, &stack_trace_filter_fops); + &trace_ops, &stack_trace_filter_fops); if (stack_trace_filter_buf[0]) ftrace_set_early_filter(&trace_ops, stack_trace_filter_buf, 1); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index c74bf39ef764..a86688fabc55 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2864,11 +2864,11 @@ bool flush_work(struct work_struct *work) EXPORT_SYMBOL_GPL(flush_work); struct cwt_wait { - wait_queue_t wait; + wait_queue_entry_t wait; struct work_struct *work; }; -static int cwt_wakefn(wait_queue_t *wait, unsigned mode, int sync, void *key) +static int cwt_wakefn(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct cwt_wait *cwait = container_of(wait, struct cwt_wait, wait); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index e4587ebe52c7..9c5d40a50930 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1052,6 +1052,7 @@ config DEBUG_LOCK_ALLOC depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT select DEBUG_SPINLOCK select DEBUG_MUTEXES + select DEBUG_RT_MUTEXES if RT_MUTEXES select LOCKDEP help This feature will check whether any held lock (spinlock, rwlock, @@ -1067,6 +1068,7 @@ config PROVE_LOCKING select LOCKDEP select DEBUG_SPINLOCK select DEBUG_MUTEXES + select DEBUG_RT_MUTEXES if RT_MUTEXES select DEBUG_LOCK_ALLOC select TRACE_IRQFLAGS default n @@ -1121,6 +1123,7 @@ config LOCK_STAT select LOCKDEP select DEBUG_SPINLOCK select DEBUG_MUTEXES + select DEBUG_RT_MUTEXES if RT_MUTEXES select DEBUG_LOCK_ALLOC default n help @@ -1301,189 +1304,7 @@ config DEBUG_CREDENTIALS If unsure, say N. -menu "RCU Debugging" - -config PROVE_RCU - def_bool PROVE_LOCKING - -config PROVE_RCU_REPEATEDLY - bool "RCU debugging: don't disable PROVE_RCU on first splat" - depends on PROVE_RCU - default n - help - By itself, PROVE_RCU will disable checking upon issuing the - first warning (or "splat"). This feature prevents such - disabling, allowing multiple RCU-lockdep warnings to be printed - on a single reboot. - - Say Y to allow multiple RCU-lockdep warnings per boot. - - Say N if you are unsure. - -config SPARSE_RCU_POINTER - bool "RCU debugging: sparse-based checks for pointer usage" - default n - help - This feature enables the __rcu sparse annotation for - RCU-protected pointers. This annotation will cause sparse - to flag any non-RCU used of annotated pointers. This can be - helpful when debugging RCU usage. Please note that this feature - is not intended to enforce code cleanliness; it is instead merely - a debugging aid. - - Say Y to make sparse flag questionable use of RCU-protected pointers - - Say N if you are unsure. - -config TORTURE_TEST - tristate - default n - -config RCU_PERF_TEST - tristate "performance tests for RCU" - depends on DEBUG_KERNEL - select TORTURE_TEST - select SRCU - select TASKS_RCU - default n - help - This option provides a kernel module that runs performance - tests on the RCU infrastructure. The kernel module may be built - after the fact on the running kernel to be tested, if desired. - - Say Y here if you want RCU performance tests to be built into - the kernel. - Say M if you want the RCU performance tests to build as a module. - Say N if you are unsure. - -config RCU_TORTURE_TEST - tristate "torture tests for RCU" - depends on DEBUG_KERNEL - select TORTURE_TEST - select SRCU - select TASKS_RCU - default n - help - This option provides a kernel module that runs torture tests - on the RCU infrastructure. The kernel module may be built - after the fact on the running kernel to be tested, if desired. - - Say Y here if you want RCU torture tests to be built into - the kernel. - Say M if you want the RCU torture tests to build as a module. - Say N if you are unsure. - -config RCU_TORTURE_TEST_SLOW_PREINIT - bool "Slow down RCU grace-period pre-initialization to expose races" - depends on RCU_TORTURE_TEST - help - This option delays grace-period pre-initialization (the - propagation of CPU-hotplug changes up the rcu_node combining - tree) for a few jiffies between initializing each pair of - consecutive rcu_node structures. This helps to expose races - involving grace-period pre-initialization, in other words, it - makes your kernel less stable. It can also greatly increase - grace-period latency, especially on systems with large numbers - of CPUs. This is useful when torture-testing RCU, but in - almost no other circumstance. - - Say Y here if you want your system to crash and hang more often. - Say N if you want a sane system. - -config RCU_TORTURE_TEST_SLOW_PREINIT_DELAY - int "How much to slow down RCU grace-period pre-initialization" - range 0 5 - default 3 - depends on RCU_TORTURE_TEST_SLOW_PREINIT - help - This option specifies the number of jiffies to wait between - each rcu_node structure pre-initialization step. - -config RCU_TORTURE_TEST_SLOW_INIT - bool "Slow down RCU grace-period initialization to expose races" - depends on RCU_TORTURE_TEST - help - This option delays grace-period initialization for a few - jiffies between initializing each pair of consecutive - rcu_node structures. This helps to expose races involving - grace-period initialization, in other words, it makes your - kernel less stable. It can also greatly increase grace-period - latency, especially on systems with large numbers of CPUs. - This is useful when torture-testing RCU, but in almost no - other circumstance. - - Say Y here if you want your system to crash and hang more often. - Say N if you want a sane system. - -config RCU_TORTURE_TEST_SLOW_INIT_DELAY - int "How much to slow down RCU grace-period initialization" - range 0 5 - default 3 - depends on RCU_TORTURE_TEST_SLOW_INIT - help - This option specifies the number of jiffies to wait between - each rcu_node structure initialization. - -config RCU_TORTURE_TEST_SLOW_CLEANUP - bool "Slow down RCU grace-period cleanup to expose races" - depends on RCU_TORTURE_TEST - help - This option delays grace-period cleanup for a few jiffies - between cleaning up each pair of consecutive rcu_node - structures. This helps to expose races involving grace-period - cleanup, in other words, it makes your kernel less stable. - It can also greatly increase grace-period latency, especially - on systems with large numbers of CPUs. This is useful when - torture-testing RCU, but in almost no other circumstance. - - Say Y here if you want your system to crash and hang more often. - Say N if you want a sane system. - -config RCU_TORTURE_TEST_SLOW_CLEANUP_DELAY - int "How much to slow down RCU grace-period cleanup" - range 0 5 - default 3 - depends on RCU_TORTURE_TEST_SLOW_CLEANUP - help - This option specifies the number of jiffies to wait between - each rcu_node structure cleanup operation. - -config RCU_CPU_STALL_TIMEOUT - int "RCU CPU stall timeout in seconds" - depends on RCU_STALL_COMMON - range 3 300 - default 21 - help - If a given RCU grace period extends more than the specified - number of seconds, a CPU stall warning is printed. If the - RCU grace period persists, additional CPU stall warnings are - printed at more widely spaced intervals. - -config RCU_TRACE - bool "Enable tracing for RCU" - depends on DEBUG_KERNEL - default y if TREE_RCU - select TRACE_CLOCK - help - This option provides tracing in RCU which presents stats - in debugfs for debugging RCU implementation. It also enables - additional tracepoints for ftrace-style event tracing. - - Say Y here if you want to enable RCU tracing - Say N if you are unsure. - -config RCU_EQS_DEBUG - bool "Provide debugging asserts for adding NO_HZ support to an arch" - depends on DEBUG_KERNEL - help - This option provides consistency checks in RCU's handling of - NO_HZ. These checks have proven quite helpful in detecting - bugs in arch-specific NO_HZ code. - - Say N here if you need ultimate kernel/user switch latencies - Say Y if you are unsure - -endmenu # "RCU Debugging" +source "kernel/rcu/Kconfig.debug" config DEBUG_WQ_FORCE_RR_CPU bool "Force round-robin CPU selection for unbound work items" diff --git a/lib/Makefile b/lib/Makefile index 0166fbc0fa81..07fbe6a75692 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -25,9 +25,6 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \ earlycpio.o seq_buf.o siphash.o \ nmi_backtrace.o nodemask.o win_minmax.o -CFLAGS_radix-tree.o += -DCONFIG_SPARSE_RCU_POINTER -CFLAGS_idr.o += -DCONFIG_SPARSE_RCU_POINTER - lib-$(CONFIG_MMU) += ioremap.o lib-$(CONFIG_SMP) += cpumask.o lib-$(CONFIG_DMA_NOOP_OPS) += dma-noop.o diff --git a/lib/cmdline.c b/lib/cmdline.c index 3c6432df7e63..4c0888c4a68d 100644 --- a/lib/cmdline.c +++ b/lib/cmdline.c @@ -23,14 +23,14 @@ * the values[M, M+1, ..., N] into the ints array in get_options. */ -static int get_range(char **str, int *pint) +static int get_range(char **str, int *pint, int n) { int x, inc_counter, upper_range; (*str)++; upper_range = simple_strtol((*str), NULL, 0); inc_counter = upper_range - *pint; - for (x = *pint; x < upper_range; x++) + for (x = *pint; n && x < upper_range; x++, n--) *pint++ = x; return inc_counter; } @@ -97,7 +97,7 @@ char *get_options(const char *str, int nints, int *ints) break; if (res == 3) { int range_nums; - range_nums = get_range((char **)&str, ints + i); + range_nums = get_range((char **)&str, ints + i, nints - i); if (range_nums < 0) break; /* diff --git a/lib/cpumask.c b/lib/cpumask.c index 81dedaab36cc..4731a0895760 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -43,6 +43,38 @@ int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) } EXPORT_SYMBOL(cpumask_any_but); +/** + * cpumask_next_wrap - helper to implement for_each_cpu_wrap + * @n: the cpu prior to the place to search + * @mask: the cpumask pointer + * @start: the start point of the iteration + * @wrap: assume @n crossing @start terminates the iteration + * + * Returns >= nr_cpu_ids on completion + * + * Note: the @wrap argument is required for the start condition when + * we cannot assume @start is set in @mask. + */ +int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap) +{ + int next; + +again: + next = cpumask_next(n, mask); + + if (wrap && n < start && next >= start) { + return nr_cpumask_bits; + + } else if (next >= nr_cpumask_bits) { + wrap = true; + n = -1; + goto again; + } + + return next; +} +EXPORT_SYMBOL(cpumask_next_wrap); + /* These are not inline because of header tangles. */ #ifdef CONFIG_CPUMASK_OFFSTACK /** diff --git a/lib/locking-selftest-rtmutex.h b/lib/locking-selftest-rtmutex.h new file mode 100644 index 000000000000..e3cb83989d16 --- /dev/null +++ b/lib/locking-selftest-rtmutex.h @@ -0,0 +1,11 @@ +#undef LOCK +#define LOCK RTL + +#undef UNLOCK +#define UNLOCK RTU + +#undef RLOCK +#undef WLOCK + +#undef INIT +#define INIT RTI diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c index f3a217ea0388..6f2b135dc5e8 100644 --- a/lib/locking-selftest.c +++ b/lib/locking-selftest.c @@ -21,6 +21,7 @@ #include <linux/interrupt.h> #include <linux/debug_locks.h> #include <linux/irqflags.h> +#include <linux/rtmutex.h> /* * Change this to 1 if you want to see the failure printouts: @@ -46,6 +47,7 @@ __setup("debug_locks_verbose=", setup_debug_locks_verbose); #define LOCKTYPE_MUTEX 0x4 #define LOCKTYPE_RWSEM 0x8 #define LOCKTYPE_WW 0x10 +#define LOCKTYPE_RTMUTEX 0x20 static struct ww_acquire_ctx t, t2; static struct ww_mutex o, o2, o3; @@ -74,6 +76,15 @@ static DECLARE_RWSEM(rwsem_B); static DECLARE_RWSEM(rwsem_C); static DECLARE_RWSEM(rwsem_D); +#ifdef CONFIG_RT_MUTEXES + +static DEFINE_RT_MUTEX(rtmutex_A); +static DEFINE_RT_MUTEX(rtmutex_B); +static DEFINE_RT_MUTEX(rtmutex_C); +static DEFINE_RT_MUTEX(rtmutex_D); + +#endif + /* * Locks that we initialize dynamically as well so that * e.g. X1 and X2 becomes two instances of the same class, @@ -108,6 +119,17 @@ static DECLARE_RWSEM(rwsem_Y2); static DECLARE_RWSEM(rwsem_Z1); static DECLARE_RWSEM(rwsem_Z2); +#ifdef CONFIG_RT_MUTEXES + +static DEFINE_RT_MUTEX(rtmutex_X1); +static DEFINE_RT_MUTEX(rtmutex_X2); +static DEFINE_RT_MUTEX(rtmutex_Y1); +static DEFINE_RT_MUTEX(rtmutex_Y2); +static DEFINE_RT_MUTEX(rtmutex_Z1); +static DEFINE_RT_MUTEX(rtmutex_Z2); + +#endif + /* * non-inlined runtime initializers, to let separate locks share * the same lock-class: @@ -129,6 +151,17 @@ INIT_CLASS_FUNC(Z) static void init_shared_classes(void) { +#ifdef CONFIG_RT_MUTEXES + static struct lock_class_key rt_X, rt_Y, rt_Z; + + __rt_mutex_init(&rtmutex_X1, __func__, &rt_X); + __rt_mutex_init(&rtmutex_X2, __func__, &rt_X); + __rt_mutex_init(&rtmutex_Y1, __func__, &rt_Y); + __rt_mutex_init(&rtmutex_Y2, __func__, &rt_Y); + __rt_mutex_init(&rtmutex_Z1, __func__, &rt_Z); + __rt_mutex_init(&rtmutex_Z2, __func__, &rt_Z); +#endif + init_class_X(&lock_X1, &rwlock_X1, &mutex_X1, &rwsem_X1); init_class_X(&lock_X2, &rwlock_X2, &mutex_X2, &rwsem_X2); @@ -193,6 +226,10 @@ static void init_shared_classes(void) #define MU(x) mutex_unlock(&mutex_##x) #define MI(x) mutex_init(&mutex_##x) +#define RTL(x) rt_mutex_lock(&rtmutex_##x) +#define RTU(x) rt_mutex_unlock(&rtmutex_##x) +#define RTI(x) rt_mutex_init(&rtmutex_##x) + #define WSL(x) down_write(&rwsem_##x) #define WSU(x) up_write(&rwsem_##x) @@ -264,6 +301,11 @@ GENERATE_TESTCASE(AA_wsem) #include "locking-selftest-rsem.h" GENERATE_TESTCASE(AA_rsem) +#ifdef CONFIG_RT_MUTEXES +#include "locking-selftest-rtmutex.h" +GENERATE_TESTCASE(AA_rtmutex); +#endif + #undef E /* @@ -345,6 +387,11 @@ GENERATE_TESTCASE(ABBA_wsem) #include "locking-selftest-rsem.h" GENERATE_TESTCASE(ABBA_rsem) +#ifdef CONFIG_RT_MUTEXES +#include "locking-selftest-rtmutex.h" +GENERATE_TESTCASE(ABBA_rtmutex); +#endif + #undef E /* @@ -373,6 +420,11 @@ GENERATE_TESTCASE(ABBCCA_wsem) #include "locking-selftest-rsem.h" GENERATE_TESTCASE(ABBCCA_rsem) +#ifdef CONFIG_RT_MUTEXES +#include "locking-selftest-rtmutex.h" +GENERATE_TESTCASE(ABBCCA_rtmutex); +#endif + #undef E /* @@ -401,6 +453,11 @@ GENERATE_TESTCASE(ABCABC_wsem) #include "locking-selftest-rsem.h" GENERATE_TESTCASE(ABCABC_rsem) +#ifdef CONFIG_RT_MUTEXES +#include "locking-selftest-rtmutex.h" +GENERATE_TESTCASE(ABCABC_rtmutex); +#endif + #undef E /* @@ -430,6 +487,11 @@ GENERATE_TESTCASE(ABBCCDDA_wsem) #include "locking-selftest-rsem.h" GENERATE_TESTCASE(ABBCCDDA_rsem) +#ifdef CONFIG_RT_MUTEXES +#include "locking-selftest-rtmutex.h" +GENERATE_TESTCASE(ABBCCDDA_rtmutex); +#endif + #undef E /* @@ -458,6 +520,11 @@ GENERATE_TESTCASE(ABCDBDDA_wsem) #include "locking-selftest-rsem.h" GENERATE_TESTCASE(ABCDBDDA_rsem) +#ifdef CONFIG_RT_MUTEXES +#include "locking-selftest-rtmutex.h" +GENERATE_TESTCASE(ABCDBDDA_rtmutex); +#endif + #undef E /* @@ -486,6 +553,11 @@ GENERATE_TESTCASE(ABCDBCDA_wsem) #include "locking-selftest-rsem.h" GENERATE_TESTCASE(ABCDBCDA_rsem) +#ifdef CONFIG_RT_MUTEXES +#include "locking-selftest-rtmutex.h" +GENERATE_TESTCASE(ABCDBCDA_rtmutex); +#endif + #undef E /* @@ -513,33 +585,10 @@ GENERATE_TESTCASE(double_unlock_wsem) #include "locking-selftest-rsem.h" GENERATE_TESTCASE(double_unlock_rsem) -#undef E - -/* - * Bad unlock ordering: - */ -#define E() \ - \ - LOCK(A); \ - LOCK(B); \ - UNLOCK(A); /* fail */ \ - UNLOCK(B); - -/* - * 6 testcases: - */ -#include "locking-selftest-spin.h" -GENERATE_TESTCASE(bad_unlock_order_spin) -#include "locking-selftest-wlock.h" -GENERATE_TESTCASE(bad_unlock_order_wlock) -#include "locking-selftest-rlock.h" -GENERATE_TESTCASE(bad_unlock_order_rlock) -#include "locking-selftest-mutex.h" -GENERATE_TESTCASE(bad_unlock_order_mutex) -#include "locking-selftest-wsem.h" -GENERATE_TESTCASE(bad_unlock_order_wsem) -#include "locking-selftest-rsem.h" -GENERATE_TESTCASE(bad_unlock_order_rsem) +#ifdef CONFIG_RT_MUTEXES +#include "locking-selftest-rtmutex.h" +GENERATE_TESTCASE(double_unlock_rtmutex); +#endif #undef E @@ -567,6 +616,11 @@ GENERATE_TESTCASE(init_held_wsem) #include "locking-selftest-rsem.h" GENERATE_TESTCASE(init_held_rsem) +#ifdef CONFIG_RT_MUTEXES +#include "locking-selftest-rtmutex.h" +GENERATE_TESTCASE(init_held_rtmutex); +#endif + #undef E /* @@ -916,6 +970,9 @@ GENERATE_PERMUTATIONS_3_EVENTS(irq_read_recursion_soft) # define I_MUTEX(x) lockdep_reset_lock(&mutex_##x.dep_map) # define I_RWSEM(x) lockdep_reset_lock(&rwsem_##x.dep_map) # define I_WW(x) lockdep_reset_lock(&x.dep_map) +#ifdef CONFIG_RT_MUTEXES +# define I_RTMUTEX(x) lockdep_reset_lock(&rtmutex_##x.dep_map) +#endif #else # define I_SPINLOCK(x) # define I_RWLOCK(x) @@ -924,12 +981,23 @@ GENERATE_PERMUTATIONS_3_EVENTS(irq_read_recursion_soft) # define I_WW(x) #endif +#ifndef I_RTMUTEX +# define I_RTMUTEX(x) +#endif + +#ifdef CONFIG_RT_MUTEXES +#define I2_RTMUTEX(x) rt_mutex_init(&rtmutex_##x) +#else +#define I2_RTMUTEX(x) +#endif + #define I1(x) \ do { \ I_SPINLOCK(x); \ I_RWLOCK(x); \ I_MUTEX(x); \ I_RWSEM(x); \ + I_RTMUTEX(x); \ } while (0) #define I2(x) \ @@ -938,6 +1006,7 @@ GENERATE_PERMUTATIONS_3_EVENTS(irq_read_recursion_soft) rwlock_init(&rwlock_##x); \ mutex_init(&mutex_##x); \ init_rwsem(&rwsem_##x); \ + I2_RTMUTEX(x); \ } while (0) static void reset_locks(void) @@ -1013,6 +1082,12 @@ static void dotest(void (*testcase_fn)(void), int expected, int lockclass_mask) reset_locks(); } +#ifdef CONFIG_RT_MUTEXES +#define dotest_rt(fn, e, m) dotest((fn), (e), (m)) +#else +#define dotest_rt(fn, e, m) +#endif + static inline void print_testname(const char *testname) { printk("%33s:", testname); @@ -1050,6 +1125,7 @@ static inline void print_testname(const char *testname) dotest(name##_mutex, FAILURE, LOCKTYPE_MUTEX); \ dotest(name##_wsem, FAILURE, LOCKTYPE_RWSEM); \ dotest(name##_rsem, FAILURE, LOCKTYPE_RWSEM); \ + dotest_rt(name##_rtmutex, FAILURE, LOCKTYPE_RTMUTEX); \ pr_cont("\n"); #define DO_TESTCASE_6_SUCCESS(desc, name) \ @@ -1060,6 +1136,7 @@ static inline void print_testname(const char *testname) dotest(name##_mutex, SUCCESS, LOCKTYPE_MUTEX); \ dotest(name##_wsem, SUCCESS, LOCKTYPE_RWSEM); \ dotest(name##_rsem, SUCCESS, LOCKTYPE_RWSEM); \ + dotest_rt(name##_rtmutex, SUCCESS, LOCKTYPE_RTMUTEX); \ pr_cont("\n"); /* @@ -1073,6 +1150,7 @@ static inline void print_testname(const char *testname) dotest(name##_mutex, FAILURE, LOCKTYPE_MUTEX); \ dotest(name##_wsem, FAILURE, LOCKTYPE_RWSEM); \ dotest(name##_rsem, FAILURE, LOCKTYPE_RWSEM); \ + dotest_rt(name##_rtmutex, FAILURE, LOCKTYPE_RTMUTEX); \ pr_cont("\n"); #define DO_TESTCASE_2I(desc, name, nr) \ @@ -1825,7 +1903,6 @@ void locking_selftest(void) DO_TESTCASE_6R("A-B-C-D-B-C-D-A deadlock", ABCDBCDA); DO_TESTCASE_6("double unlock", double_unlock); DO_TESTCASE_6("initialize held", init_held); - DO_TESTCASE_6_SUCCESS("bad unlock order", bad_unlock_order); printk(" --------------------------------------------------------------------------\n"); print_testname("recursive read-lock"); diff --git a/lib/refcount.c b/lib/refcount.c index 9f906783987e..5d0582a9480c 100644 --- a/lib/refcount.c +++ b/lib/refcount.c @@ -37,6 +37,8 @@ #include <linux/refcount.h> #include <linux/bug.h> +#ifdef CONFIG_REFCOUNT_FULL + /** * refcount_add_not_zero - add a value to a refcount unless it is 0 * @i: the value to add to the refcount @@ -225,6 +227,7 @@ void refcount_dec(refcount_t *r) WARN_ONCE(refcount_dec_and_test(r), "refcount_t: decrement hit 0; leaking memory.\n"); } EXPORT_SYMBOL(refcount_dec); +#endif /* CONFIG_REFCOUNT_FULL */ /** * refcount_dec_if_one - decrement a refcount if it is 1 diff --git a/lib/scatterlist.c b/lib/scatterlist.c index c6cf82242d65..be7b4dd6b68d 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -751,3 +751,38 @@ size_t sg_pcopy_to_buffer(struct scatterlist *sgl, unsigned int nents, return sg_copy_buffer(sgl, nents, buf, buflen, skip, true); } EXPORT_SYMBOL(sg_pcopy_to_buffer); + +/** + * sg_zero_buffer - Zero-out a part of a SG list + * @sgl: The SG list + * @nents: Number of SG entries + * @buflen: The number of bytes to zero out + * @skip: Number of bytes to skip before zeroing + * + * Returns the number of bytes zeroed. + **/ +size_t sg_zero_buffer(struct scatterlist *sgl, unsigned int nents, + size_t buflen, off_t skip) +{ + unsigned int offset = 0; + struct sg_mapping_iter miter; + unsigned int sg_flags = SG_MITER_ATOMIC | SG_MITER_TO_SG; + + sg_miter_start(&miter, sgl, nents, sg_flags); + + if (!sg_miter_skip(&miter, skip)) + return false; + + while (offset < buflen && sg_miter_next(&miter)) { + unsigned int len; + + len = min(miter.length, buflen - offset); + memset(miter.addr, 0, len); + + offset += len; + } + + sg_miter_stop(&miter); + return offset; +} +EXPORT_SYMBOL(sg_zero_buffer); diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c index 690d75b132fa..2fb007be0212 100644 --- a/lib/smp_processor_id.c +++ b/lib/smp_processor_id.c @@ -28,7 +28,7 @@ notrace static unsigned int check_preemption_disabled(const char *what1, /* * It is valid to assume CPU-locality during early bootup: */ - if (system_state != SYSTEM_RUNNING) + if (system_state < SYSTEM_SCHEDULING) goto out; /* diff --git a/lib/test_uuid.c b/lib/test_uuid.c index 547d3127a3cf..478c049630b5 100644 --- a/lib/test_uuid.c +++ b/lib/test_uuid.c @@ -11,25 +11,25 @@ struct test_uuid_data { const char *uuid; - uuid_le le; - uuid_be be; + guid_t le; + uuid_t be; }; static const struct test_uuid_data test_uuid_test_data[] = { { .uuid = "c33f4995-3701-450e-9fbf-206a2e98e576", - .le = UUID_LE(0xc33f4995, 0x3701, 0x450e, 0x9f, 0xbf, 0x20, 0x6a, 0x2e, 0x98, 0xe5, 0x76), - .be = UUID_BE(0xc33f4995, 0x3701, 0x450e, 0x9f, 0xbf, 0x20, 0x6a, 0x2e, 0x98, 0xe5, 0x76), + .le = GUID_INIT(0xc33f4995, 0x3701, 0x450e, 0x9f, 0xbf, 0x20, 0x6a, 0x2e, 0x98, 0xe5, 0x76), + .be = UUID_INIT(0xc33f4995, 0x3701, 0x450e, 0x9f, 0xbf, 0x20, 0x6a, 0x2e, 0x98, 0xe5, 0x76), }, { .uuid = "64b4371c-77c1-48f9-8221-29f054fc023b", - .le = UUID_LE(0x64b4371c, 0x77c1, 0x48f9, 0x82, 0x21, 0x29, 0xf0, 0x54, 0xfc, 0x02, 0x3b), - .be = UUID_BE(0x64b4371c, 0x77c1, 0x48f9, 0x82, 0x21, 0x29, 0xf0, 0x54, 0xfc, 0x02, 0x3b), + .le = GUID_INIT(0x64b4371c, 0x77c1, 0x48f9, 0x82, 0x21, 0x29, 0xf0, 0x54, 0xfc, 0x02, 0x3b), + .be = UUID_INIT(0x64b4371c, 0x77c1, 0x48f9, 0x82, 0x21, 0x29, 0xf0, 0x54, 0xfc, 0x02, 0x3b), }, { .uuid = "0cb4ddff-a545-4401-9d06-688af53e7f84", - .le = UUID_LE(0x0cb4ddff, 0xa545, 0x4401, 0x9d, 0x06, 0x68, 0x8a, 0xf5, 0x3e, 0x7f, 0x84), - .be = UUID_BE(0x0cb4ddff, 0xa545, 0x4401, 0x9d, 0x06, 0x68, 0x8a, 0xf5, 0x3e, 0x7f, 0x84), + .le = GUID_INIT(0x0cb4ddff, 0xa545, 0x4401, 0x9d, 0x06, 0x68, 0x8a, 0xf5, 0x3e, 0x7f, 0x84), + .be = UUID_INIT(0x0cb4ddff, 0xa545, 0x4401, 0x9d, 0x06, 0x68, 0x8a, 0xf5, 0x3e, 0x7f, 0x84), }, }; @@ -61,28 +61,28 @@ static void __init test_uuid_failed(const char *prefix, bool wrong, bool be, static void __init test_uuid_test(const struct test_uuid_data *data) { - uuid_le le; - uuid_be be; + guid_t le; + uuid_t be; char buf[48]; /* LE */ total_tests++; - if (uuid_le_to_bin(data->uuid, &le)) + if (guid_parse(data->uuid, &le)) test_uuid_failed("conversion", false, false, data->uuid, NULL); total_tests++; - if (uuid_le_cmp(data->le, le)) { + if (!guid_equal(&data->le, &le)) { sprintf(buf, "%pUl", &le); test_uuid_failed("cmp", false, false, data->uuid, buf); } /* BE */ total_tests++; - if (uuid_be_to_bin(data->uuid, &be)) + if (uuid_parse(data->uuid, &be)) test_uuid_failed("conversion", false, true, data->uuid, NULL); total_tests++; - if (uuid_be_cmp(data->be, be)) { + if (uuid_equal(&data->be, &be)) { sprintf(buf, "%pUb", &be); test_uuid_failed("cmp", false, true, data->uuid, buf); } @@ -90,17 +90,17 @@ static void __init test_uuid_test(const struct test_uuid_data *data) static void __init test_uuid_wrong(const char *data) { - uuid_le le; - uuid_be be; + guid_t le; + uuid_t be; /* LE */ total_tests++; - if (!uuid_le_to_bin(data, &le)) + if (!guid_parse(data, &le)) test_uuid_failed("negative", true, false, data, NULL); /* BE */ total_tests++; - if (!uuid_be_to_bin(data, &be)) + if (!uuid_parse(data, &be)) test_uuid_failed("negative", true, true, data, NULL); } diff --git a/lib/uuid.c b/lib/uuid.c index 37687af77ff8..680b9fb9ba09 100644 --- a/lib/uuid.c +++ b/lib/uuid.c @@ -21,10 +21,13 @@ #include <linux/uuid.h> #include <linux/random.h> -const u8 uuid_le_index[16] = {3,2,1,0,5,4,7,6,8,9,10,11,12,13,14,15}; -EXPORT_SYMBOL(uuid_le_index); -const u8 uuid_be_index[16] = {0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15}; -EXPORT_SYMBOL(uuid_be_index); +const guid_t guid_null; +EXPORT_SYMBOL(guid_null); +const uuid_t uuid_null; +EXPORT_SYMBOL(uuid_null); + +const u8 guid_index[16] = {3,2,1,0,5,4,7,6,8,9,10,11,12,13,14,15}; +const u8 uuid_index[16] = {0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15}; /*************************************************************** * Random UUID interface @@ -53,21 +56,21 @@ static void __uuid_gen_common(__u8 b[16]) b[8] = (b[8] & 0x3F) | 0x80; } -void uuid_le_gen(uuid_le *lu) +void guid_gen(guid_t *lu) { __uuid_gen_common(lu->b); /* version 4 : random generation */ lu->b[7] = (lu->b[7] & 0x0F) | 0x40; } -EXPORT_SYMBOL_GPL(uuid_le_gen); +EXPORT_SYMBOL_GPL(guid_gen); -void uuid_be_gen(uuid_be *bu) +void uuid_gen(uuid_t *bu) { __uuid_gen_common(bu->b); /* version 4 : random generation */ bu->b[6] = (bu->b[6] & 0x0F) | 0x40; } -EXPORT_SYMBOL_GPL(uuid_be_gen); +EXPORT_SYMBOL_GPL(uuid_gen); /** * uuid_is_valid - checks if UUID string valid @@ -97,7 +100,7 @@ bool uuid_is_valid(const char *uuid) } EXPORT_SYMBOL(uuid_is_valid); -static int __uuid_to_bin(const char *uuid, __u8 b[16], const u8 ei[16]) +static int __uuid_parse(const char *uuid, __u8 b[16], const u8 ei[16]) { static const u8 si[16] = {0,2,4,6,9,11,14,16,19,21,24,26,28,30,32,34}; unsigned int i; @@ -115,14 +118,14 @@ static int __uuid_to_bin(const char *uuid, __u8 b[16], const u8 ei[16]) return 0; } -int uuid_le_to_bin(const char *uuid, uuid_le *u) +int guid_parse(const char *uuid, guid_t *u) { - return __uuid_to_bin(uuid, u->b, uuid_le_index); + return __uuid_parse(uuid, u->b, guid_index); } -EXPORT_SYMBOL(uuid_le_to_bin); +EXPORT_SYMBOL(guid_parse); -int uuid_be_to_bin(const char *uuid, uuid_be *u) +int uuid_parse(const char *uuid, uuid_t *u) { - return __uuid_to_bin(uuid, u->b, uuid_be_index); + return __uuid_parse(uuid, u->b, uuid_index); } -EXPORT_SYMBOL(uuid_be_to_bin); +EXPORT_SYMBOL(uuid_parse); diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 2d41de3f98a1..9f37d6208e99 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -1308,14 +1308,14 @@ char *uuid_string(char *buf, char *end, const u8 *addr, char uuid[UUID_STRING_LEN + 1]; char *p = uuid; int i; - const u8 *index = uuid_be_index; + const u8 *index = uuid_index; bool uc = false; switch (*(++fmt)) { case 'L': uc = true; /* fall-through */ case 'l': - index = uuid_le_index; + index = guid_index; break; case 'B': uc = true; diff --git a/mm/Kconfig b/mm/Kconfig index beb7a455915d..398b46064544 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -137,7 +137,7 @@ config HAVE_MEMBLOCK_NODE_MAP config HAVE_MEMBLOCK_PHYS_MAP bool -config HAVE_GENERIC_RCU_GUP +config HAVE_GENERIC_GUP bool config ARCH_DISCARD_MEMBLOCK diff --git a/mm/cleancache.c b/mm/cleancache.c index ba5d8f3e6d68..f7b9fdc79d97 100644 --- a/mm/cleancache.c +++ b/mm/cleancache.c @@ -130,7 +130,7 @@ void __cleancache_init_shared_fs(struct super_block *sb) int pool_id = CLEANCACHE_NO_BACKEND_SHARED; if (cleancache_ops) { - pool_id = cleancache_ops->init_shared_fs(sb->s_uuid, PAGE_SIZE); + pool_id = cleancache_ops->init_shared_fs(&sb->s_uuid, PAGE_SIZE); if (pool_id < 0) pool_id = CLEANCACHE_NO_POOL; } diff --git a/mm/filemap.c b/mm/filemap.c index 6f1be573a5e6..aea58e983a73 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -376,6 +376,38 @@ int filemap_flush(struct address_space *mapping) } EXPORT_SYMBOL(filemap_flush); +/** + * filemap_range_has_page - check if a page exists in range. + * @mapping: address space within which to check + * @start_byte: offset in bytes where the range starts + * @end_byte: offset in bytes where the range ends (inclusive) + * + * Find at least one page in the range supplied, usually used to check if + * direct writing in this range will trigger a writeback. + */ +bool filemap_range_has_page(struct address_space *mapping, + loff_t start_byte, loff_t end_byte) +{ + pgoff_t index = start_byte >> PAGE_SHIFT; + pgoff_t end = end_byte >> PAGE_SHIFT; + struct pagevec pvec; + bool ret; + + if (end_byte < start_byte) + return false; + + if (mapping->nrpages == 0) + return false; + + pagevec_init(&pvec, 0); + if (!pagevec_lookup(&pvec, mapping, index, 1)) + return false; + ret = (pvec.pages[0]->index <= end); + pagevec_release(&pvec); + return ret; +} +EXPORT_SYMBOL(filemap_range_has_page); + static int __filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { @@ -768,10 +800,10 @@ struct wait_page_key { struct wait_page_queue { struct page *page; int bit_nr; - wait_queue_t wait; + wait_queue_entry_t wait; }; -static int wake_page_function(wait_queue_t *wait, unsigned mode, int sync, void *arg) +static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg) { struct wait_page_key *key = arg; struct wait_page_queue *wait_page @@ -834,7 +866,7 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, struct page *page, int bit_nr, int state, bool lock) { struct wait_page_queue wait_page; - wait_queue_t *wait = &wait_page.wait; + wait_queue_entry_t *wait = &wait_page.wait; int ret = 0; init_wait(wait); @@ -845,9 +877,9 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, for (;;) { spin_lock_irq(&q->lock); - if (likely(list_empty(&wait->task_list))) { + if (likely(list_empty(&wait->entry))) { if (lock) - __add_wait_queue_tail_exclusive(q, wait); + __add_wait_queue_entry_tail_exclusive(q, wait); else __add_wait_queue(q, wait); SetPageWaiters(page); @@ -907,7 +939,7 @@ int wait_on_page_bit_killable(struct page *page, int bit_nr) * * Add an arbitrary @waiter to the wait queue for the nominated @page. */ -void add_page_wait_queue(struct page *page, wait_queue_t *waiter) +void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter) { wait_queue_head_t *q = page_waitqueue(page); unsigned long flags; @@ -2038,10 +2070,17 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) loff_t size; size = i_size_read(inode); - retval = filemap_write_and_wait_range(mapping, iocb->ki_pos, - iocb->ki_pos + count - 1); - if (retval < 0) - goto out; + if (iocb->ki_flags & IOCB_NOWAIT) { + if (filemap_range_has_page(mapping, iocb->ki_pos, + iocb->ki_pos + count - 1)) + return -EAGAIN; + } else { + retval = filemap_write_and_wait_range(mapping, + iocb->ki_pos, + iocb->ki_pos + count - 1); + if (retval < 0) + goto out; + } file_accessed(file); @@ -2642,6 +2681,9 @@ inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from) pos = iocb->ki_pos; + if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT)) + return -EINVAL; + if (limit != RLIM_INFINITY) { if (iocb->ki_pos >= limit) { send_sig(SIGXFSZ, current, 0); @@ -2710,9 +2752,17 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from) write_len = iov_iter_count(from); end = (pos + write_len - 1) >> PAGE_SHIFT; - written = filemap_write_and_wait_range(mapping, pos, pos + write_len - 1); - if (written) - goto out; + if (iocb->ki_flags & IOCB_NOWAIT) { + /* If there are pages to writeback, return */ + if (filemap_range_has_page(inode->i_mapping, pos, + pos + iov_iter_count(from))) + return -EAGAIN; + } else { + written = filemap_write_and_wait_range(mapping, pos, + pos + write_len - 1); + if (written) + goto out; + } /* * After a write we want buffered reads to be sure to go to disk to get @@ -1146,7 +1146,7 @@ struct page *get_dump_page(unsigned long addr) #endif /* CONFIG_ELF_CORE */ /* - * Generic RCU Fast GUP + * Generic Fast GUP * * get_user_pages_fast attempts to pin user pages by walking the page * tables directly and avoids taking locks. Thus the walker needs to be @@ -1167,8 +1167,8 @@ struct page *get_dump_page(unsigned long addr) * Before activating this code, please be aware that the following assumptions * are currently made: * - * *) HAVE_RCU_TABLE_FREE is enabled, and tlb_remove_table is used to free - * pages containing page tables. + * *) Either HAVE_RCU_TABLE_FREE is enabled, and tlb_remove_table() is used to + * free pages containing page tables or TLB flushing requires IPI broadcast. * * *) ptes can be read atomically by the architecture. * @@ -1178,7 +1178,7 @@ struct page *get_dump_page(unsigned long addr) * * This code is based heavily on the PowerPC implementation by Nick Piggin. */ -#ifdef CONFIG_HAVE_GENERIC_RCU_GUP +#ifdef CONFIG_HAVE_GENERIC_GUP #ifndef gup_get_pte /* @@ -1668,4 +1668,4 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write, return ret; } -#endif /* CONFIG_HAVE_GENERIC_RCU_GUP */ +#endif /* CONFIG_HAVE_GENERIC_GUP */ diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 945fd1ca49b5..df4ebdb2b10a 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -652,7 +652,6 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page, spin_unlock(ptl); free_page_and_swap_cache(src_page); } - cond_resched(); } } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 94172089f52f..d75b38b66ef6 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -170,7 +170,7 @@ struct mem_cgroup_event { */ poll_table pt; wait_queue_head_t *wqh; - wait_queue_t wait; + wait_queue_entry_t wait; struct work_struct remove; }; @@ -1479,10 +1479,10 @@ static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq); struct oom_wait_info { struct mem_cgroup *memcg; - wait_queue_t wait; + wait_queue_entry_t wait; }; -static int memcg_oom_wake_function(wait_queue_t *wait, +static int memcg_oom_wake_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg) { struct mem_cgroup *wake_memcg = (struct mem_cgroup *)arg; @@ -1570,7 +1570,7 @@ bool mem_cgroup_oom_synchronize(bool handle) owait.wait.flags = 0; owait.wait.func = memcg_oom_wake_function; owait.wait.private = current; - INIT_LIST_HEAD(&owait.wait.task_list); + INIT_LIST_HEAD(&owait.wait.entry); prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE); mem_cgroup_mark_under_oom(memcg); @@ -3725,7 +3725,7 @@ static void memcg_event_remove(struct work_struct *work) * * Called with wqh->lock held and interrupts disabled. */ -static int memcg_event_wake(wait_queue_t *wait, unsigned mode, +static int memcg_event_wake(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct mem_cgroup_event *event = diff --git a/mm/mempool.c b/mm/mempool.c index 47a659dedd44..1c0294858527 100644 --- a/mm/mempool.c +++ b/mm/mempool.c @@ -312,7 +312,7 @@ void *mempool_alloc(mempool_t *pool, gfp_t gfp_mask) { void *element; unsigned long flags; - wait_queue_t wait; + wait_queue_entry_t wait; gfp_t gfp_temp; VM_WARN_ON_ONCE(gfp_mask & __GFP_ZERO); diff --git a/mm/mmap.c b/mm/mmap.c index 8e07976d5e47..a5e3dcd75e79 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1817,7 +1817,8 @@ check_current: /* Check if current node has a suitable gap */ if (gap_start > high_limit) return -ENOMEM; - if (gap_end >= low_limit && gap_end - gap_start >= length) + if (gap_end >= low_limit && + gap_end > gap_start && gap_end - gap_start >= length) goto found; /* Visit right subtree if it looks promising */ @@ -1920,7 +1921,8 @@ check_current: gap_end = vm_start_gap(vma); if (gap_end < low_limit) return -ENOMEM; - if (gap_start <= high_limit && gap_end - gap_start >= length) + if (gap_start <= high_limit && + gap_end > gap_start && gap_end - gap_start >= length) goto found; /* Visit left subtree if it looks promising */ @@ -2228,16 +2230,19 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address) if (!(vma->vm_flags & VM_GROWSUP)) return -EFAULT; - /* Guard against wrapping around to address 0. */ + /* Guard against exceeding limits of the address space. */ address &= PAGE_MASK; - address += PAGE_SIZE; - if (!address) + if (address >= TASK_SIZE) return -ENOMEM; + address += PAGE_SIZE; /* Enforce stack_guard_gap */ gap_addr = address + stack_guard_gap; - if (gap_addr < address) - return -ENOMEM; + + /* Guard against overflow */ + if (gap_addr < address || gap_addr > TASK_SIZE) + gap_addr = TASK_SIZE; + next = vma->vm_next; if (next && next->vm_start < gap_addr) { if (!(next->vm_flags & VM_GROWSUP)) diff --git a/mm/page_io.c b/mm/page_io.c index 23f6d0d3470f..2da71e627812 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -45,7 +45,7 @@ void end_swap_bio_write(struct bio *bio) { struct page *page = bio->bi_io_vec[0].bv_page; - if (bio->bi_error) { + if (bio->bi_status) { SetPageError(page); /* * We failed to write the page out to swap-space. @@ -118,7 +118,7 @@ static void end_swap_bio_read(struct bio *bio) { struct page *page = bio->bi_io_vec[0].bv_page; - if (bio->bi_error) { + if (bio->bi_status) { SetPageError(page); ClearPageUptodate(page); pr_alert("Read-error on swap-device (%u:%u:%llu)\n", diff --git a/mm/rmap.c b/mm/rmap.c index d405f0e0ee96..130c238fe384 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -579,25 +579,13 @@ void page_unlock_anon_vma_read(struct anon_vma *anon_vma) void try_to_unmap_flush(void) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; - int cpu; if (!tlb_ubc->flush_required) return; - cpu = get_cpu(); - - if (cpumask_test_cpu(cpu, &tlb_ubc->cpumask)) { - count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); - local_flush_tlb(); - trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL); - } - - if (cpumask_any_but(&tlb_ubc->cpumask, cpu) < nr_cpu_ids) - flush_tlb_others(&tlb_ubc->cpumask, NULL, 0, TLB_FLUSH_ALL); - cpumask_clear(&tlb_ubc->cpumask); + arch_tlbbatch_flush(&tlb_ubc->arch); tlb_ubc->flush_required = false; tlb_ubc->writable = false; - put_cpu(); } /* Flush iff there are potentially writable TLB entries that can race with IO */ @@ -613,7 +601,7 @@ static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; - cpumask_or(&tlb_ubc->cpumask, &tlb_ubc->cpumask, mm_cpumask(mm)); + arch_tlbbatch_add_mm(&tlb_ubc->arch, mm); tlb_ubc->flush_required = true; /* diff --git a/mm/shmem.c b/mm/shmem.c index e67d6ba4e98e..9100c4952698 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -75,6 +75,7 @@ static struct vfsmount *shm_mnt; #include <uapi/linux/memfd.h> #include <linux/userfaultfd_k.h> #include <linux/rmap.h> +#include <linux/uuid.h> #include <linux/uaccess.h> #include <asm/pgtable.h> @@ -1902,10 +1903,10 @@ unlock: * entry unconditionally - even if something else had already woken the * target. */ -static int synchronous_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key) +static int synchronous_wake_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { int ret = default_wake_function(wait, mode, sync, key); - list_del_init(&wait->task_list); + list_del_init(&wait->entry); return ret; } @@ -2840,7 +2841,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, spin_lock(&inode->i_lock); inode->i_private = NULL; wake_up_all(&shmem_falloc_waitq); - WARN_ON_ONCE(!list_empty(&shmem_falloc_waitq.task_list)); + WARN_ON_ONCE(!list_empty(&shmem_falloc_waitq.head)); spin_unlock(&inode->i_lock); error = 0; goto out; @@ -3761,6 +3762,7 @@ int shmem_fill_super(struct super_block *sb, void *data, int silent) #ifdef CONFIG_TMPFS_POSIX_ACL sb->s_flags |= MS_POSIXACL; #endif + uuid_gen(&sb->s_uuid); inode = shmem_get_inode(sb, NULL, S_IFDIR | sbinfo->mode, 0, VM_NORESERVE); if (!inode) diff --git a/mm/slub.c b/mm/slub.c index 7449593fca72..8addc535bcdc 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -5625,6 +5625,28 @@ static char *create_unique_id(struct kmem_cache *s) return name; } +static void sysfs_slab_remove_workfn(struct work_struct *work) +{ + struct kmem_cache *s = + container_of(work, struct kmem_cache, kobj_remove_work); + + if (!s->kobj.state_in_sysfs) + /* + * For a memcg cache, this may be called during + * deactivation and again on shutdown. Remove only once. + * A cache is never shut down before deactivation is + * complete, so no need to worry about synchronization. + */ + return; + +#ifdef CONFIG_MEMCG + kset_unregister(s->memcg_kset); +#endif + kobject_uevent(&s->kobj, KOBJ_REMOVE); + kobject_del(&s->kobj); + kobject_put(&s->kobj); +} + static int sysfs_slab_add(struct kmem_cache *s) { int err; @@ -5632,6 +5654,8 @@ static int sysfs_slab_add(struct kmem_cache *s) struct kset *kset = cache_kset(s); int unmergeable = slab_unmergeable(s); + INIT_WORK(&s->kobj_remove_work, sysfs_slab_remove_workfn); + if (!kset) { kobject_init(&s->kobj, &slab_ktype); return 0; @@ -5695,20 +5719,8 @@ static void sysfs_slab_remove(struct kmem_cache *s) */ return; - if (!s->kobj.state_in_sysfs) - /* - * For a memcg cache, this may be called during - * deactivation and again on shutdown. Remove only once. - * A cache is never shut down before deactivation is - * complete, so no need to worry about synchronization. - */ - return; - -#ifdef CONFIG_MEMCG - kset_unregister(s->memcg_kset); -#endif - kobject_uevent(&s->kobj, KOBJ_REMOVE); - kobject_del(&s->kobj); + kobject_get(&s->kobj); + schedule_work(&s->kobj_remove_work); } void sysfs_slab_release(struct kmem_cache *s) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 34a1c3e46ed7..ecc97f74ab18 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -287,10 +287,21 @@ struct page *vmalloc_to_page(const void *vmalloc_addr) if (p4d_none(*p4d)) return NULL; pud = pud_offset(p4d, addr); - if (pud_none(*pud)) + + /* + * Don't dereference bad PUD or PMD (below) entries. This will also + * identify huge mappings, which we may encounter on architectures + * that define CONFIG_HAVE_ARCH_HUGE_VMAP=y. Such regions will be + * identified as vmalloc addresses by is_vmalloc_addr(), but are + * not [unambiguously] associated with a struct page, so there is + * no correct value to return for them. + */ + WARN_ON_ONCE(pud_bad(*pud)); + if (pud_none(*pud) || pud_bad(*pud)) return NULL; pmd = pmd_offset(pud, addr); - if (pmd_none(*pmd)) + WARN_ON_ONCE(pmd_bad(*pmd)); + if (pmd_none(*pmd) || pmd_bad(*pmd)) return NULL; ptep = pte_offset_map(pmd, addr); diff --git a/mm/vmscan.c b/mm/vmscan.c index 8ad39bbc79e6..c3c1c6ac62da 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3652,7 +3652,7 @@ int kswapd_run(int nid) pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid); if (IS_ERR(pgdat->kswapd)) { /* failure at boot is fatal */ - BUG_ON(system_state == SYSTEM_BOOTING); + BUG_ON(system_state < SYSTEM_RUNNING); pr_err("Failed to start kswapd on node %d\n", nid); ret = PTR_ERR(pgdat->kswapd); pgdat->kswapd = NULL; diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 467069b73ce1..9649579b5b9f 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -277,7 +277,8 @@ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id) return 0; out_free_newdev: - free_netdev(new_dev); + if (new_dev->reg_state == NETREG_UNINITIALIZED) + free_netdev(new_dev); return err; } diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 7bc2208b6cc4..dca3cdd1a014 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -95,7 +95,7 @@ enum { struct p9_poll_wait { struct p9_conn *conn; - wait_queue_t wait; + wait_queue_entry_t wait; wait_queue_head_t *wait_addr; }; @@ -522,7 +522,7 @@ error: clear_bit(Wworksched, &m->wsched); } -static int p9_pollwake(wait_queue_t *wait, unsigned int mode, int sync, void *key) +static int p9_pollwake(wait_queue_entry_t *wait, unsigned int mode, int sync, void *key) { struct p9_poll_wait *pwait = container_of(wait, struct p9_poll_wait, wait); diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index fbf251fef70f..5c4808b3da2d 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -484,7 +484,7 @@ static int bnep_session(void *arg) struct net_device *dev = s->dev; struct sock *sk = s->sock->sk; struct sk_buff *skb; - wait_queue_t wait; + wait_queue_entry_t wait; BT_DBG(""); diff --git a/net/bluetooth/cmtp/core.c b/net/bluetooth/cmtp/core.c index 9e59b6654126..14f7c8135c31 100644 --- a/net/bluetooth/cmtp/core.c +++ b/net/bluetooth/cmtp/core.c @@ -280,7 +280,7 @@ static int cmtp_session(void *arg) struct cmtp_session *session = arg; struct sock *sk = session->sock->sk; struct sk_buff *skb; - wait_queue_t wait; + wait_queue_entry_t wait; BT_DBG("session %p", session); diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index 0bec4588c3c8..fc31161e98f2 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -1244,7 +1244,7 @@ static void hidp_session_run(struct hidp_session *session) static int hidp_session_thread(void *arg) { struct hidp_session *session = arg; - wait_queue_t ctrl_wait, intr_wait; + wait_queue_entry_t ctrl_wait, intr_wait; BT_DBG("session %p", session); diff --git a/net/core/datagram.c b/net/core/datagram.c index db1866f2ffcf..34678828e2bb 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -68,7 +68,7 @@ static inline int connection_based(struct sock *sk) return sk->sk_type == SOCK_SEQPACKET || sk->sk_type == SOCK_STREAM; } -static int receiver_wake_function(wait_queue_t *wait, unsigned int mode, int sync, +static int receiver_wake_function(wait_queue_entry_t *wait, unsigned int mode, int sync, void *key) { unsigned long bits = (unsigned long)key; diff --git a/net/core/dev.c b/net/core/dev.c index 6d60149287a1..416137c64bf8 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4767,6 +4767,13 @@ struct packet_offload *gro_find_complete_by_type(__be16 type) } EXPORT_SYMBOL(gro_find_complete_by_type); +static void napi_skb_free_stolen_head(struct sk_buff *skb) +{ + skb_dst_drop(skb); + secpath_reset(skb); + kmem_cache_free(skbuff_head_cache, skb); +} + static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) { switch (ret) { @@ -4780,13 +4787,10 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) break; case GRO_MERGED_FREE: - if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) { - skb_dst_drop(skb); - secpath_reset(skb); - kmem_cache_free(skbuff_head_cache, skb); - } else { + if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) + napi_skb_free_stolen_head(skb); + else __kfree_skb(skb); - } break; case GRO_HELD: @@ -4858,10 +4862,16 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, break; case GRO_DROP: - case GRO_MERGED_FREE: napi_reuse_skb(napi, skb); break; + case GRO_MERGED_FREE: + if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) + napi_skb_free_stolen_head(skb); + else + napi_reuse_skb(napi, skb); + break; + case GRO_MERGED: case GRO_CONSUMED: break; @@ -5206,8 +5216,6 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock) if (rc == BUSY_POLL_BUDGET) __napi_schedule(napi); local_bh_enable(); - if (local_softirq_pending()) - do_softirq(); } void napi_busy_loop(unsigned int napi_id, @@ -7785,9 +7793,9 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, } else { netdev_stats_to_stats64(storage, &dev->stats); } - storage->rx_dropped += atomic_long_read(&dev->rx_dropped); - storage->tx_dropped += atomic_long_read(&dev->tx_dropped); - storage->rx_nohandler += atomic_long_read(&dev->rx_nohandler); + storage->rx_dropped += (unsigned long)atomic_long_read(&dev->rx_dropped); + storage->tx_dropped += (unsigned long)atomic_long_read(&dev->tx_dropped); + storage->rx_nohandler += (unsigned long)atomic_long_read(&dev->rx_nohandler); return storage; } EXPORT_SYMBOL(dev_get_stats); diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index b94b1d293506..27fad31784a8 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -410,6 +410,22 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg) if (cmd == SIOCGIFNAME) return dev_ifname(net, (struct ifreq __user *)arg); + /* + * Take care of Wireless Extensions. Unfortunately struct iwreq + * isn't a proper subset of struct ifreq (it's 8 byte shorter) + * so we need to treat it specially, otherwise applications may + * fault if the struct they're passing happens to land at the + * end of a mapped page. + */ + if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) { + struct iwreq iwr; + + if (copy_from_user(&iwr, arg, sizeof(iwr))) + return -EFAULT; + + return wext_handle_ioctl(net, &iwr, cmd, arg); + } + if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) return -EFAULT; @@ -559,9 +575,6 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg) ret = -EFAULT; return ret; } - /* Take care of Wireless Extensions */ - if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) - return wext_handle_ioctl(net, &ifr, cmd, arg); return -ENOTTY; } } diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index f21c4d3aeae0..3bba291c6c32 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -568,7 +568,7 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh, struct net *net = sock_net(skb->sk); struct fib_rule_hdr *frh = nlmsg_data(nlh); struct fib_rules_ops *ops = NULL; - struct fib_rule *rule, *tmp; + struct fib_rule *rule, *r; struct nlattr *tb[FRA_MAX+1]; struct fib_kuid_range range; int err = -EINVAL; @@ -668,16 +668,23 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh, /* * Check if this rule is a target to any of them. If so, + * adjust to the next one with the same preference or * disable them. As this operation is eventually very - * expensive, it is only performed if goto rules have - * actually been added. + * expensive, it is only performed if goto rules, except + * current if it is goto rule, have actually been added. */ if (ops->nr_goto_rules > 0) { - list_for_each_entry(tmp, &ops->rules_list, list) { - if (rtnl_dereference(tmp->ctarget) == rule) { - RCU_INIT_POINTER(tmp->ctarget, NULL); + struct fib_rule *n; + + n = list_next_entry(rule, list); + if (&n->list == &ops->rules_list || n->pref != rule->pref) + n = NULL; + list_for_each_entry(r, &ops->rules_list, list) { + if (rtnl_dereference(r->ctarget) != rule) + continue; + rcu_assign_pointer(r->ctarget, n); + if (!n) ops->unresolved_rules++; - } } } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 5e61456f6bc7..467a2f4510a7 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -931,6 +931,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(1) /* IFLA_LINKMODE */ + nla_total_size(4) /* IFLA_CARRIER_CHANGES */ + nla_total_size(4) /* IFLA_LINK_NETNSID */ + + nla_total_size(4) /* IFLA_GROUP */ + nla_total_size(ext_filter_mask & RTEXT_FILTER_VF ? 4 : 0) /* IFLA_NUM_VF */ + rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */ @@ -1468,6 +1469,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_LINK_NETNSID] = { .type = NLA_S32 }, [IFLA_PROTO_DOWN] = { .type = NLA_U8 }, [IFLA_XDP] = { .type = NLA_NESTED }, + [IFLA_GROUP] = { .type = NLA_U32 }, }; static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 4b9518a0d248..6f95612b4d32 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -188,12 +188,6 @@ static inline void dnrt_free(struct dn_route *rt) call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free); } -static inline void dnrt_drop(struct dn_route *rt) -{ - dst_release(&rt->dst); - call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free); -} - static void dn_dst_check_expire(unsigned long dummy) { int i; @@ -248,7 +242,7 @@ static int dn_dst_gc(struct dst_ops *ops) } *rtp = rt->dst.dn_next; rt->dst.dn_next = NULL; - dnrt_drop(rt); + dnrt_free(rt); break; } spin_unlock_bh(&dn_rt_hash_table[i].lock); @@ -350,7 +344,7 @@ static int dn_insert_route(struct dn_route *rt, unsigned int hash, struct dn_rou dst_use(&rth->dst, now); spin_unlock_bh(&dn_rt_hash_table[hash].lock); - dnrt_drop(rt); + dst_free(&rt->dst); *rp = rth; return 0; } @@ -380,7 +374,7 @@ static void dn_run_flush(unsigned long dummy) for(; rt; rt = next) { next = rcu_dereference_raw(rt->dst.dn_next); RCU_INIT_POINTER(rt->dst.dn_next, NULL); - dst_free((struct dst_entry *)rt); + dnrt_free(rt); } nothing_to_declare: @@ -1187,7 +1181,7 @@ make_route: if (dev_out->flags & IFF_LOOPBACK) flags |= RTCF_LOCAL; - rt = dst_alloc(&dn_dst_ops, dev_out, 1, DST_OBSOLETE_NONE, DST_HOST); + rt = dst_alloc(&dn_dst_ops, dev_out, 0, DST_OBSOLETE_NONE, DST_HOST); if (rt == NULL) goto e_nobufs; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 8f6b5bbcbf69..ec9a396fa466 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1112,6 +1112,7 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im) pmc = kzalloc(sizeof(*pmc), GFP_KERNEL); if (!pmc) return; + spin_lock_init(&pmc->lock); spin_lock_bh(&im->lock); pmc->interface = im->interface; in_dev_hold(in_dev); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 7a3fd25e8913..532b36e9ce2a 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -964,7 +964,8 @@ static int __ip_append_data(struct sock *sk, csummode = CHECKSUM_PARTIAL; cork->length += length; - if ((((length + fragheaderlen) > mtu) || (skb && skb_is_gso(skb))) && + if ((((length + (skb ? skb->len : fragheaderlen)) > mtu) || + (skb && skb_is_gso(skb))) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO) && !dst_xfrm(&rt->dst) && (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx) { diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index b436d0775631..129d1a3616f8 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -446,6 +446,8 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, return 0; drop: + if (tun_dst) + dst_release((struct dst_entry *)tun_dst); kfree_skb(skb); return 0; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b5ea036ca781..40aca7803cf2 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2330,6 +2330,8 @@ int tcp_disconnect(struct sock *sk, int flags) tcp_init_send_head(sk); memset(&tp->rx_opt, 0, sizeof(tp->rx_opt)); __sk_dst_reset(sk); + dst_release(sk->sk_rx_dst); + sk->sk_rx_dst = NULL; tcp_saved_syn_free(tp); /* Clean up fastopen related fields */ diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 6a4fb1e629fb..1d2dbace42ff 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -332,9 +332,9 @@ static void addrconf_mod_rs_timer(struct inet6_dev *idev, static void addrconf_mod_dad_work(struct inet6_ifaddr *ifp, unsigned long delay) { - if (!delayed_work_pending(&ifp->dad_work)) - in6_ifa_hold(ifp); - mod_delayed_work(addrconf_wq, &ifp->dad_work, delay); + in6_ifa_hold(ifp); + if (mod_delayed_work(addrconf_wq, &ifp->dad_work, delay)) + in6_ifa_put(ifp); } static int snmp6_alloc_dev(struct inet6_dev *idev) @@ -3369,6 +3369,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netdev_notifier_changeupper_info *info; struct inet6_dev *idev = __in6_dev_get(dev); + struct net *net = dev_net(dev); int run_pending = 0; int err; @@ -3384,7 +3385,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, case NETDEV_CHANGEMTU: /* if MTU under IPV6_MIN_MTU stop IPv6 on this interface. */ if (dev->mtu < IPV6_MIN_MTU) { - addrconf_ifdown(dev, 1); + addrconf_ifdown(dev, dev != net->loopback_dev); break; } @@ -3500,7 +3501,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, * IPV6_MIN_MTU stop IPv6 on this interface. */ if (dev->mtu < IPV6_MIN_MTU) - addrconf_ifdown(dev, 1); + addrconf_ifdown(dev, dev != net->loopback_dev); } break; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index e011122ebd43..5c786f5ab961 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -250,8 +250,14 @@ ipv4_connected: */ err = ip6_datagram_dst_update(sk, true); - if (err) + if (err) { + /* Reset daddr and dport so that udp_v6_early_demux() + * fails to find this socket + */ + memset(&sk->sk_v6_daddr, 0, sizeof(sk->sk_v6_daddr)); + inet->inet_dport = 0; goto out; + } sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index d950d43ba255..f02f131f6435 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -30,6 +30,25 @@ #include <net/ipv6.h> #include <linux/icmpv6.h> +static __u16 esp6_nexthdr_esp_offset(struct ipv6hdr *ipv6_hdr, int nhlen) +{ + int off = sizeof(struct ipv6hdr); + struct ipv6_opt_hdr *exthdr; + + if (likely(ipv6_hdr->nexthdr == NEXTHDR_ESP)) + return offsetof(struct ipv6hdr, nexthdr); + + while (off < nhlen) { + exthdr = (void *)ipv6_hdr + off; + if (exthdr->nexthdr == NEXTHDR_ESP) + return off; + + off += ipv6_optlen(exthdr); + } + + return 0; +} + static struct sk_buff **esp6_gro_receive(struct sk_buff **head, struct sk_buff *skb) { @@ -38,6 +57,7 @@ static struct sk_buff **esp6_gro_receive(struct sk_buff **head, struct xfrm_state *x; __be32 seq; __be32 spi; + int nhoff; int err; skb_pull(skb, offset); @@ -72,6 +92,11 @@ static struct sk_buff **esp6_gro_receive(struct sk_buff **head, xo->flags |= XFRM_GRO; + nhoff = esp6_nexthdr_esp_offset(ipv6_hdr(skb), offset); + if (!nhoff) + goto out; + + IP6CB(skb)->nhoff = nhoff; XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; XFRM_SPI_SKB_CB(skb)->family = AF_INET6; XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr); diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index eea23b57c6a5..ec849d88a662 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -32,7 +32,6 @@ struct fib6_rule { struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, int flags, pol_lookup_t lookup) { - struct rt6_info *rt; struct fib_lookup_arg arg = { .lookup_ptr = lookup, .flags = FIB_LOOKUP_NOREF, @@ -44,21 +43,11 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, fib_rules_lookup(net->ipv6.fib6_rules_ops, flowi6_to_flowi(fl6), flags, &arg); - rt = arg.result; + if (arg.result) + return arg.result; - if (!rt) { - dst_hold(&net->ipv6.ip6_null_entry->dst); - return &net->ipv6.ip6_null_entry->dst; - } - - if (rt->rt6i_flags & RTF_REJECT && - rt->dst.error == -EAGAIN) { - ip6_rt_put(rt); - rt = net->ipv6.ip6_null_entry; - dst_hold(&rt->dst); - } - - return &rt->dst; + dst_hold(&net->ipv6.ip6_null_entry->dst); + return &net->ipv6.ip6_null_entry->dst; } static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, @@ -121,7 +110,8 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, flp6->saddr = saddr; } err = rt->dst.error; - goto out; + if (err != -EAGAIN) + goto out; } again: ip6_rt_put(rt); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index d4bf2c68a545..e6b78ba0e636 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -289,8 +289,7 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, struct rt6_info *rt; rt = lookup(net, net->ipv6.fib6_main_tbl, fl6, flags); - if (rt->rt6i_flags & RTF_REJECT && - rt->dst.error == -EAGAIN) { + if (rt->dst.error == -EAGAIN) { ip6_rt_put(rt); rt = net->ipv6.ip6_null_entry; dst_hold(&rt->dst); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index bf8a58a1c32d..1699acb2fa2c 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1390,7 +1390,7 @@ emsgsize: */ cork->length += length; - if ((((length + fragheaderlen) > mtu) || + if ((((length + (skb ? skb->len : headersize)) > mtu) || (skb && skb_is_gso(skb))) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO) && !dst_xfrm(&rt->dst) && diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index c3581973f5d7..8c6c3c8e7eef 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -858,6 +858,8 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, return 0; drop: + if (tun_dst) + dst_release((struct dst_entry *)tun_dst); kfree_skb(skb); return 0; } @@ -1246,7 +1248,7 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) fl6.flowi6_proto = IPPROTO_IPIP; fl6.daddr = key->u.ipv6.dst; fl6.flowlabel = key->label; - dsfield = ip6_tclass(key->label); + dsfield = key->tos; } else { if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) encap_limit = t->parms.encap_limit; @@ -1317,7 +1319,7 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) fl6.flowi6_proto = IPPROTO_IPV6; fl6.daddr = key->u.ipv6.dst; fl6.flowlabel = key->label; - dsfield = ip6_tclass(key->label); + dsfield = key->tos; } else { offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb)); /* ip6_tnl_parse_tlv_enc_lim() might have reallocated skb->head */ diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 7cebd954d5bb..322bd62e688b 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3722,7 +3722,11 @@ static int ip6_route_dev_notify(struct notifier_block *this, net->ipv6.ip6_blk_hole_entry->dst.dev = dev; net->ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(dev); #endif - } else if (event == NETDEV_UNREGISTER) { + } else if (event == NETDEV_UNREGISTER && + dev->reg_state != NETREG_UNREGISTERED) { + /* NETDEV_UNREGISTER could be fired for multiple times by + * netdev_wait_allrefs(). Make sure we only call this once. + */ in6_dev_put(net->ipv6.ip6_null_entry->rt6i_idev); #ifdef CONFIG_IPV6_MULTIPLE_TABLES in6_dev_put(net->ipv6.ip6_prohibit_entry->rt6i_idev); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 2378503577b0..f8ad15891cd7 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -305,7 +305,7 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t, * we try harder to allocate. */ kp = (cmax <= 1 || capable(CAP_NET_ADMIN)) ? - kcalloc(cmax, sizeof(*kp), GFP_KERNEL) : + kcalloc(cmax, sizeof(*kp), GFP_KERNEL | __GFP_NOWARN) : NULL; rcu_read_lock(); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 06ec39b79609..75703fda23e7 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -879,7 +879,8 @@ static struct sock *__udp6_lib_demux_lookup(struct net *net, struct sock *sk; udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { - if (INET6_MATCH(sk, net, rmt_addr, loc_addr, ports, dif)) + if (sk->sk_state == TCP_ESTABLISHED && + INET6_MATCH(sk, net, rmt_addr, loc_addr, ports, dif)) return sk; /* Only check first socket in chain */ break; diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index 08a807b29298..3ef5d913e7a3 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -43,8 +43,8 @@ int xfrm6_transport_finish(struct sk_buff *skb, int async) return 1; #endif - ipv6_hdr(skb)->payload_len = htons(skb->len); __skb_push(skb, skb->data - skb_network_header(skb)); + ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); if (xo && (xo->flags & XFRM_GRO)) { skb_mac_header_rebuild(skb); diff --git a/net/key/af_key.c b/net/key/af_key.c index 512dc43d0ce6..b1432b668033 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1157,6 +1157,7 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, goto out; } + err = -ENOBUFS; key = ext_hdrs[SADB_EXT_KEY_AUTH - 1]; if (sa->sadb_sa_auth) { int keysize = 0; @@ -1168,8 +1169,10 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, if (key) keysize = (key->sadb_key_bits + 7) / 8; x->aalg = kmalloc(sizeof(*x->aalg) + keysize, GFP_KERNEL); - if (!x->aalg) + if (!x->aalg) { + err = -ENOMEM; goto out; + } strcpy(x->aalg->alg_name, a->name); x->aalg->alg_key_len = 0; if (key) { @@ -1188,8 +1191,10 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, goto out; } x->calg = kmalloc(sizeof(*x->calg), GFP_KERNEL); - if (!x->calg) + if (!x->calg) { + err = -ENOMEM; goto out; + } strcpy(x->calg->alg_name, a->name); x->props.calgo = sa->sadb_sa_encrypt; } else { @@ -1203,8 +1208,10 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, if (key) keysize = (key->sadb_key_bits + 7) / 8; x->ealg = kmalloc(sizeof(*x->ealg) + keysize, GFP_KERNEL); - if (!x->ealg) + if (!x->ealg) { + err = -ENOMEM; goto out; + } strcpy(x->ealg->alg_name, a->name); x->ealg->alg_key_len = 0; if (key) { @@ -1249,8 +1256,10 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, struct xfrm_encap_tmpl *natt; x->encap = kmalloc(sizeof(*x->encap), GFP_KERNEL); - if (!x->encap) + if (!x->encap) { + err = -ENOMEM; goto out; + } natt = x->encap; n_type = ext_hdrs[SADB_X_EXT_NAT_T_TYPE-1]; @@ -2755,6 +2764,8 @@ static int pfkey_spdflush(struct sock *sk, struct sk_buff *skb, const struct sad int err, err2; err = xfrm_policy_flush(net, XFRM_POLICY_TYPE_MAIN, true); + if (!err) + xfrm_garbage_collect(net); err2 = unicast_flush_resp(sk, hdr); if (err || err2) { if (err == -ESRCH) /* empty table - old silent behavior */ diff --git a/net/rxrpc/key.c b/net/rxrpc/key.c index 0a4e28477ad9..54369225766e 100644 --- a/net/rxrpc/key.c +++ b/net/rxrpc/key.c @@ -217,7 +217,7 @@ static int rxrpc_krb5_decode_principal(struct krb5_principal *princ, unsigned int *_toklen) { const __be32 *xdr = *_xdr; - unsigned int toklen = *_toklen, n_parts, loop, tmp; + unsigned int toklen = *_toklen, n_parts, loop, tmp, paddedlen; /* there must be at least one name, and at least #names+1 length * words */ @@ -247,16 +247,16 @@ static int rxrpc_krb5_decode_principal(struct krb5_principal *princ, toklen -= 4; if (tmp <= 0 || tmp > AFSTOKEN_STRING_MAX) return -EINVAL; - if (tmp > toklen) + paddedlen = (tmp + 3) & ~3; + if (paddedlen > toklen) return -EINVAL; princ->name_parts[loop] = kmalloc(tmp + 1, GFP_KERNEL); if (!princ->name_parts[loop]) return -ENOMEM; memcpy(princ->name_parts[loop], xdr, tmp); princ->name_parts[loop][tmp] = 0; - tmp = (tmp + 3) & ~3; - toklen -= tmp; - xdr += tmp >> 2; + toklen -= paddedlen; + xdr += paddedlen >> 2; } if (toklen < 4) @@ -265,16 +265,16 @@ static int rxrpc_krb5_decode_principal(struct krb5_principal *princ, toklen -= 4; if (tmp <= 0 || tmp > AFSTOKEN_K5_REALM_MAX) return -EINVAL; - if (tmp > toklen) + paddedlen = (tmp + 3) & ~3; + if (paddedlen > toklen) return -EINVAL; princ->realm = kmalloc(tmp + 1, GFP_KERNEL); if (!princ->realm) return -ENOMEM; memcpy(princ->realm, xdr, tmp); princ->realm[tmp] = 0; - tmp = (tmp + 3) & ~3; - toklen -= tmp; - xdr += tmp >> 2; + toklen -= paddedlen; + xdr += paddedlen >> 2; _debug("%s/...@%s", princ->name_parts[0], princ->realm); @@ -293,7 +293,7 @@ static int rxrpc_krb5_decode_tagged_data(struct krb5_tagged_data *td, unsigned int *_toklen) { const __be32 *xdr = *_xdr; - unsigned int toklen = *_toklen, len; + unsigned int toklen = *_toklen, len, paddedlen; /* there must be at least one tag and one length word */ if (toklen <= 8) @@ -307,15 +307,17 @@ static int rxrpc_krb5_decode_tagged_data(struct krb5_tagged_data *td, toklen -= 8; if (len > max_data_size) return -EINVAL; + paddedlen = (len + 3) & ~3; + if (paddedlen > toklen) + return -EINVAL; td->data_len = len; if (len > 0) { td->data = kmemdup(xdr, len, GFP_KERNEL); if (!td->data) return -ENOMEM; - len = (len + 3) & ~3; - toklen -= len; - xdr += len >> 2; + toklen -= paddedlen; + xdr += paddedlen >> 2; } _debug("tag %x len %x", td->tag, td->data_len); @@ -387,7 +389,7 @@ static int rxrpc_krb5_decode_ticket(u8 **_ticket, u16 *_tktlen, const __be32 **_xdr, unsigned int *_toklen) { const __be32 *xdr = *_xdr; - unsigned int toklen = *_toklen, len; + unsigned int toklen = *_toklen, len, paddedlen; /* there must be at least one length word */ if (toklen <= 4) @@ -399,6 +401,9 @@ static int rxrpc_krb5_decode_ticket(u8 **_ticket, u16 *_tktlen, toklen -= 4; if (len > AFSTOKEN_K5_TIX_MAX) return -EINVAL; + paddedlen = (len + 3) & ~3; + if (paddedlen > toklen) + return -EINVAL; *_tktlen = len; _debug("ticket len %u", len); @@ -407,9 +412,8 @@ static int rxrpc_krb5_decode_ticket(u8 **_ticket, u16 *_tktlen, *_ticket = kmemdup(xdr, len, GFP_KERNEL); if (!*_ticket) return -ENOMEM; - len = (len + 3) & ~3; - toklen -= len; - xdr += len >> 2; + toklen -= paddedlen; + xdr += paddedlen >> 2; } *_xdr = xdr; @@ -552,7 +556,7 @@ static int rxrpc_preparse_xdr(struct key_preparsed_payload *prep) { const __be32 *xdr = prep->data, *token; const char *cp; - unsigned int len, tmp, loop, ntoken, toklen, sec_ix; + unsigned int len, paddedlen, loop, ntoken, toklen, sec_ix; size_t datalen = prep->datalen; int ret; @@ -578,22 +582,21 @@ static int rxrpc_preparse_xdr(struct key_preparsed_payload *prep) if (len < 1 || len > AFSTOKEN_CELL_MAX) goto not_xdr; datalen -= 4; - tmp = (len + 3) & ~3; - if (tmp > datalen) + paddedlen = (len + 3) & ~3; + if (paddedlen > datalen) goto not_xdr; cp = (const char *) xdr; for (loop = 0; loop < len; loop++) if (!isprint(cp[loop])) goto not_xdr; - if (len < tmp) - for (; loop < tmp; loop++) - if (cp[loop]) - goto not_xdr; + for (; loop < paddedlen; loop++) + if (cp[loop]) + goto not_xdr; _debug("cellname: [%u/%u] '%*.*s'", - len, tmp, len, len, (const char *) xdr); - datalen -= tmp; - xdr += tmp >> 2; + len, paddedlen, len, len, (const char *) xdr); + datalen -= paddedlen; + xdr += paddedlen >> 2; /* get the token count */ if (datalen < 12) @@ -614,10 +617,11 @@ static int rxrpc_preparse_xdr(struct key_preparsed_payload *prep) sec_ix = ntohl(*xdr); datalen -= 4; _debug("token: [%x/%zx] %x", toklen, datalen, sec_ix); - if (toklen < 20 || toklen > datalen) + paddedlen = (toklen + 3) & ~3; + if (toklen < 20 || toklen > datalen || paddedlen > datalen) goto not_xdr; - datalen -= (toklen + 3) & ~3; - xdr += (toklen + 3) >> 2; + datalen -= paddedlen; + xdr += paddedlen >> 2; } while (--loop > 0); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index e88342fde1bc..cfdbfa18a95e 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1019,7 +1019,8 @@ static struct Qdisc *qdisc_create(struct net_device *dev, return sch; } /* ops->init() failed, we call ->destroy() like qdisc_create_dflt() */ - ops->destroy(sch); + if (ops->destroy) + ops->destroy(sch); err_out3: dev_put(dev); kfree((char *) sch - sch->padded); diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 8c589230794f..3dcd0ecf3d99 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -275,6 +275,7 @@ static void sctp_endpoint_destroy(struct sctp_endpoint *ep) if (sctp_sk(sk)->bind_hash) sctp_put_port(sk); + sctp_sk(sk)->ep = NULL; sock_put(sk); } diff --git a/net/sctp/sctp_diag.c b/net/sctp/sctp_diag.c index 048954eee984..9a647214a91e 100644 --- a/net/sctp/sctp_diag.c +++ b/net/sctp/sctp_diag.c @@ -278,7 +278,6 @@ out: static int sctp_sock_dump(struct sock *sk, void *p) { - struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_comm_param *commp = p; struct sk_buff *skb = commp->skb; struct netlink_callback *cb = commp->cb; @@ -287,7 +286,9 @@ static int sctp_sock_dump(struct sock *sk, void *p) int err = 0; lock_sock(sk); - list_for_each_entry(assoc, &ep->asocs, asocs) { + if (!sctp_sk(sk)->ep) + goto release; + list_for_each_entry(assoc, &sctp_sk(sk)->ep->asocs, asocs) { if (cb->args[4] < cb->args[1]) goto next; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 30aa0a529215..3a8318e518f1 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4666,9 +4666,8 @@ int sctp_for_each_transport(int (*cb)(struct sctp_transport *, void *), if (err) return err; - sctp_transport_get_idx(net, &hti, pos); - obj = sctp_transport_get_next(net, &hti); - for (; obj && !IS_ERR(obj); obj = sctp_transport_get_next(net, &hti)) { + obj = sctp_transport_get_idx(net, &hti, pos + 1); + for (; !IS_ERR_OR_NULL(obj); obj = sctp_transport_get_next(net, &hti)) { struct sctp_transport *transport = obj; if (!sctp_transport_hold(transport)) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 1a0c961f4ffe..c77ced0109b7 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -343,7 +343,7 @@ found: * are still connected to it and there's no way to inform "a polling * implementation" that it should let go of a certain wait queue * - * In order to propagate a wake up, a wait_queue_t of the client + * In order to propagate a wake up, a wait_queue_entry_t of the client * socket is enqueued on the peer_wait queue of the server socket * whose wake function does a wake_up on the ordinary client socket * wait queue. This connection is established whenever a write (or @@ -352,7 +352,7 @@ found: * was relayed. */ -static int unix_dgram_peer_wake_relay(wait_queue_t *q, unsigned mode, int flags, +static int unix_dgram_peer_wake_relay(wait_queue_entry_t *q, unsigned mode, int flags, void *key) { struct unix_sock *u; diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c index 1a4db6790e20..6cdb054484d6 100644 --- a/net/wireless/wext-core.c +++ b/net/wireless/wext-core.c @@ -914,13 +914,12 @@ int call_commit_handler(struct net_device *dev) * Main IOCTl dispatcher. * Check the type of IOCTL and call the appropriate wrapper... */ -static int wireless_process_ioctl(struct net *net, struct ifreq *ifr, +static int wireless_process_ioctl(struct net *net, struct iwreq *iwr, unsigned int cmd, struct iw_request_info *info, wext_ioctl_func standard, wext_ioctl_func private) { - struct iwreq *iwr = (struct iwreq *) ifr; struct net_device *dev; iw_handler handler; @@ -928,7 +927,7 @@ static int wireless_process_ioctl(struct net *net, struct ifreq *ifr, * The copy_to/from_user() of ifr is also dealt with in there */ /* Make sure the device exist */ - if ((dev = __dev_get_by_name(net, ifr->ifr_name)) == NULL) + if ((dev = __dev_get_by_name(net, iwr->ifr_name)) == NULL) return -ENODEV; /* A bunch of special cases, then the generic case... @@ -957,9 +956,6 @@ static int wireless_process_ioctl(struct net *net, struct ifreq *ifr, else if (private) return private(dev, iwr, cmd, info, handler); } - /* Old driver API : call driver ioctl handler */ - if (dev->netdev_ops->ndo_do_ioctl) - return dev->netdev_ops->ndo_do_ioctl(dev, ifr, cmd); return -EOPNOTSUPP; } @@ -977,7 +973,7 @@ static int wext_permission_check(unsigned int cmd) } /* entry point from dev ioctl */ -static int wext_ioctl_dispatch(struct net *net, struct ifreq *ifr, +static int wext_ioctl_dispatch(struct net *net, struct iwreq *iwr, unsigned int cmd, struct iw_request_info *info, wext_ioctl_func standard, wext_ioctl_func private) @@ -987,9 +983,9 @@ static int wext_ioctl_dispatch(struct net *net, struct ifreq *ifr, if (ret) return ret; - dev_load(net, ifr->ifr_name); + dev_load(net, iwr->ifr_name); rtnl_lock(); - ret = wireless_process_ioctl(net, ifr, cmd, info, standard, private); + ret = wireless_process_ioctl(net, iwr, cmd, info, standard, private); rtnl_unlock(); return ret; @@ -1039,18 +1035,18 @@ static int ioctl_standard_call(struct net_device * dev, } -int wext_handle_ioctl(struct net *net, struct ifreq *ifr, unsigned int cmd, +int wext_handle_ioctl(struct net *net, struct iwreq *iwr, unsigned int cmd, void __user *arg) { struct iw_request_info info = { .cmd = cmd, .flags = 0 }; int ret; - ret = wext_ioctl_dispatch(net, ifr, cmd, &info, + ret = wext_ioctl_dispatch(net, iwr, cmd, &info, ioctl_standard_call, ioctl_private_call); if (ret >= 0 && IW_IS_GET(cmd) && - copy_to_user(arg, ifr, sizeof(struct iwreq))) + copy_to_user(arg, iwr, sizeof(struct iwreq))) return -EFAULT; return ret; @@ -1107,7 +1103,7 @@ int compat_wext_handle_ioctl(struct net *net, unsigned int cmd, info.cmd = cmd; info.flags = IW_REQUEST_FLAG_COMPAT; - ret = wext_ioctl_dispatch(net, (struct ifreq *) &iwr, cmd, &info, + ret = wext_ioctl_dispatch(net, &iwr, cmd, &info, compat_standard_call, compat_private_call); diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile index abf81b329dc1..55b2ac300995 100644 --- a/net/xfrm/Makefile +++ b/net/xfrm/Makefile @@ -4,8 +4,7 @@ obj-$(CONFIG_XFRM) := xfrm_policy.o xfrm_state.o xfrm_hash.o \ xfrm_input.o xfrm_output.o \ - xfrm_sysctl.o xfrm_replay.o -obj-$(CONFIG_XFRM_OFFLOAD) += xfrm_device.o + xfrm_sysctl.o xfrm_replay.o xfrm_device.o obj-$(CONFIG_XFRM_STATISTICS) += xfrm_proc.o obj-$(CONFIG_XFRM_ALGO) += xfrm_algo.o obj-$(CONFIG_XFRM_USER) += xfrm_user.o diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 574e6f32f94f..5aba03685d7d 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -22,6 +22,7 @@ #include <net/xfrm.h> #include <linux/notifier.h> +#ifdef CONFIG_XFRM_OFFLOAD int validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features) { int err; @@ -137,6 +138,7 @@ ok: return true; } EXPORT_SYMBOL_GPL(xfrm_dev_offload_ok); +#endif int xfrm_dev_register(struct net_device *dev) { diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index ed4e52d95172..643a18f72032 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1006,10 +1006,6 @@ int xfrm_policy_flush(struct net *net, u8 type, bool task_valid) err = -ESRCH; out: spin_unlock_bh(&net->xfrm.xfrm_policy_lock); - - if (cnt) - xfrm_garbage_collect(net); - return err; } EXPORT_SYMBOL(xfrm_policy_flush); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 38614df33ec8..86116e9aaf3d 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2027,6 +2027,7 @@ static int xfrm_flush_policy(struct sk_buff *skb, struct nlmsghdr *nlh, return 0; return err; } + xfrm_garbage_collect(net); c.data.type = type; c.event = nlh->nlmsg_type; diff --git a/scripts/Makefile.headersinst b/scripts/Makefile.headersinst index ce753a408c56..c583a1e1bd3c 100644 --- a/scripts/Makefile.headersinst +++ b/scripts/Makefile.headersinst @@ -14,7 +14,15 @@ __headers: include scripts/Kbuild.include srcdir := $(srctree)/$(obj) -subdirs := $(patsubst $(srcdir)/%/.,%,$(wildcard $(srcdir)/*/.)) + +# When make is run under a fakechroot environment, the function +# $(wildcard $(srcdir)/*/.) doesn't only return directories, but also regular +# files. So, we are using a combination of sort/dir/wildcard which works +# with fakechroot. +subdirs := $(patsubst $(srcdir)/%/,%,\ + $(filter-out $(srcdir)/,\ + $(sort $(dir $(wildcard $(srcdir)/*/))))) + # caller may set destination dir (when installing to asm/) _dst := $(if $(dst),$(dst),$(obj)) diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 4b9569fa931b..c7e4d73fe1ce 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -5533,23 +5533,6 @@ sub process { } } -# Check for expedited grace periods that interrupt non-idle non-nohz -# online CPUs. These expedited can therefore degrade real-time response -# if used carelessly, and should be avoided where not absolutely -# needed. It is always OK to use synchronize_rcu_expedited() and -# synchronize_sched_expedited() at boot time (before real-time applications -# start) and in error situations where real-time response is compromised in -# any case. Note that synchronize_srcu_expedited() does -not- interrupt -# other CPUs, so don't warn on uses of synchronize_srcu_expedited(). -# Of course, nothing comes for free, and srcu_read_lock() and -# srcu_read_unlock() do contain full memory barriers in payment for -# synchronize_srcu_expedited() non-interruption properties. - if ($line =~ /\b(synchronize_rcu_expedited|synchronize_sched_expedited)\(/) { - WARN("EXPEDITED_RCU_GRACE_PERIOD", - "expedited RCU grace periods should be avoided where they can degrade real-time response\n" . $herecurr); - - } - # check of hardware specific defines if ($line =~ m@^.\s*\#\s*if.*\b(__i386__|__powerpc64__|__sun__|__s390x__)\b@ && $realfile !~ m@include/asm-@) { CHK("ARCH_DEFINES", diff --git a/scripts/genksyms/genksyms.h b/scripts/genksyms/genksyms.h index 3bffdcaaa274..b724a0290c75 100644 --- a/scripts/genksyms/genksyms.h +++ b/scripts/genksyms/genksyms.h @@ -75,7 +75,7 @@ struct string_list *copy_list_range(struct string_list *start, int yylex(void); int yyparse(void); -void error_with_pos(const char *, ...); +void error_with_pos(const char *, ...) __attribute__ ((format(printf, 1, 2))); /*----------------------------------------------------------------------*/ #define xmalloc(size) ({ void *__ptr = malloc(size); \ diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile index 90a091b6ae4d..eb8144643b78 100644 --- a/scripts/kconfig/Makefile +++ b/scripts/kconfig/Makefile @@ -196,7 +196,7 @@ clean-files += config.pot linux.pot # Check that we have the required ncurses stuff installed for lxdialog (menuconfig) PHONY += $(obj)/dochecklxdialog -$(addprefix $(obj)/,$(lxdialog)): $(obj)/dochecklxdialog +$(addprefix $(obj)/, mconf.o $(lxdialog)): $(obj)/dochecklxdialog $(obj)/dochecklxdialog: $(Q)$(CONFIG_SHELL) $(check-lxdialog) -check $(HOSTCC) $(HOST_EXTRACFLAGS) $(HOSTLOADLIBES_mconf) diff --git a/scripts/kconfig/nconf.c b/scripts/kconfig/nconf.c index a9bc5334a478..003114779815 100644 --- a/scripts/kconfig/nconf.c +++ b/scripts/kconfig/nconf.c @@ -271,7 +271,7 @@ static struct mitem k_menu_items[MAX_MENU_ITEMS]; static int items_num; static int global_exit; /* the currently selected button */ -const char *current_instructions = menu_instructions; +static const char *current_instructions = menu_instructions; static char *dialog_input_result; static int dialog_input_result_len; @@ -305,7 +305,7 @@ struct function_keys { }; static const int function_keys_num = 9; -struct function_keys function_keys[] = { +static struct function_keys function_keys[] = { { .key_str = "F1", .func = "Help", @@ -508,7 +508,7 @@ static int get_mext_match(const char *match_str, match_f flag) index = (index + items_num) % items_num; while (true) { char *str = k_menu_items[index].str; - if (strcasestr(str, match_str) != 0) + if (strcasestr(str, match_str) != NULL) return index; if (flag == FIND_NEXT_MATCH_UP || flag == MATCH_TINKER_PATTERN_UP) @@ -1067,7 +1067,7 @@ static int do_match(int key, struct match_state *state, int *ans) static void conf(struct menu *menu) { - struct menu *submenu = 0; + struct menu *submenu = NULL; const char *prompt = menu_get_prompt(menu); struct symbol *sym; int res; @@ -1234,7 +1234,7 @@ static void show_help(struct menu *menu) static void conf_choice(struct menu *menu) { const char *prompt = _(menu_get_prompt(menu)); - struct menu *child = 0; + struct menu *child = NULL; struct symbol *active; int selected_index = 0; int last_top_row = 0; @@ -1456,7 +1456,7 @@ static void conf_save(void) } } -void setup_windows(void) +static void setup_windows(void) { int lines, columns; diff --git a/scripts/kconfig/nconf.gui.c b/scripts/kconfig/nconf.gui.c index 4b2f44c20caf..a64b1c31253e 100644 --- a/scripts/kconfig/nconf.gui.c +++ b/scripts/kconfig/nconf.gui.c @@ -129,7 +129,7 @@ static void no_colors_theme(void) mkattrn(FUNCTION_TEXT, A_REVERSE); } -void set_colors() +void set_colors(void) { start_color(); use_default_colors(); @@ -192,7 +192,7 @@ const char *get_line(const char *text, int line_no) int lines = 0; if (!text) - return 0; + return NULL; for (i = 0; text[i] != '\0' && lines < line_no; i++) if (text[i] == '\n') diff --git a/scripts/tags.sh b/scripts/tags.sh index d661f2f3ef61..d23dcbf17457 100755 --- a/scripts/tags.sh +++ b/scripts/tags.sh @@ -106,6 +106,7 @@ all_compiled_sources() case "$i" in *.[cS]) j=${i/\.[cS]/\.o} + j="${j#$tree}" if [ -e $j ]; then echo $i fi diff --git a/security/integrity/evm/evm_crypto.c b/security/integrity/evm/evm_crypto.c index d7f282d75cc1..1d32cd20009a 100644 --- a/security/integrity/evm/evm_crypto.c +++ b/security/integrity/evm/evm_crypto.c @@ -164,7 +164,7 @@ static void hmac_add_misc(struct shash_desc *desc, struct inode *inode, hmac_misc.mode = inode->i_mode; crypto_shash_update(desc, (const u8 *)&hmac_misc, sizeof(hmac_misc)); if (evm_hmac_attrs & EVM_ATTR_FSUUID) - crypto_shash_update(desc, inode->i_sb->s_uuid, + crypto_shash_update(desc, &inode->i_sb->s_uuid.b[0], sizeof(inode->i_sb->s_uuid)); crypto_shash_final(desc, digest); } diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index 3ab1067db624..6f885fab9d84 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -61,7 +61,7 @@ struct ima_rule_entry { enum ima_hooks func; int mask; unsigned long fsmagic; - u8 fsuuid[16]; + uuid_t fsuuid; kuid_t uid; kuid_t fowner; bool (*uid_op)(kuid_t, kuid_t); /* Handlers for operators */ @@ -244,7 +244,7 @@ static bool ima_match_rules(struct ima_rule_entry *rule, struct inode *inode, && rule->fsmagic != inode->i_sb->s_magic) return false; if ((rule->flags & IMA_FSUUID) && - memcmp(rule->fsuuid, inode->i_sb->s_uuid, sizeof(rule->fsuuid))) + !uuid_equal(&rule->fsuuid, &inode->i_sb->s_uuid)) return false; if ((rule->flags & IMA_UID) && !rule->uid_op(cred->uid, rule->uid)) return false; @@ -711,14 +711,12 @@ static int ima_parse_rule(char *rule, struct ima_rule_entry *entry) case Opt_fsuuid: ima_log_string(ab, "fsuuid", args[0].from); - if (memchr_inv(entry->fsuuid, 0x00, - sizeof(entry->fsuuid))) { + if (uuid_is_null(&entry->fsuuid)) { result = -EINVAL; break; } - result = blk_part_pack_uuid(args[0].from, - entry->fsuuid); + result = uuid_parse(args[0].from, &entry->fsuuid); if (!result) entry->flags |= IMA_FSUUID; break; @@ -1087,7 +1085,7 @@ int ima_policy_show(struct seq_file *m, void *v) } if (entry->flags & IMA_FSUUID) { - seq_printf(m, "fsuuid=%pU", entry->fsuuid); + seq_printf(m, "fsuuid=%pU", &entry->fsuuid); seq_puts(m, " "); } diff --git a/security/keys/internal.h b/security/keys/internal.h index c0f8682eba69..91bc6214ae57 100644 --- a/security/keys/internal.h +++ b/security/keys/internal.h @@ -13,6 +13,7 @@ #define _INTERNAL_H #include <linux/sched.h> +#include <linux/wait_bit.h> #include <linux/cred.h> #include <linux/key-type.h> #include <linux/task_work.h> diff --git a/sound/core/control.c b/sound/core/control.c index c109b82eef4b..6362da17ac3f 100644 --- a/sound/core/control.c +++ b/sound/core/control.c @@ -1577,7 +1577,7 @@ static ssize_t snd_ctl_read(struct file *file, char __user *buffer, struct snd_ctl_event ev; struct snd_kctl_event *kev; while (list_empty(&ctl->events)) { - wait_queue_t wait; + wait_queue_entry_t wait; if ((file->f_flags & O_NONBLOCK) != 0 || result > 0) { err = -EAGAIN; goto __end_lock; diff --git a/sound/core/hwdep.c b/sound/core/hwdep.c index 9602a7e38d8a..a73baa1242be 100644 --- a/sound/core/hwdep.c +++ b/sound/core/hwdep.c @@ -85,7 +85,7 @@ static int snd_hwdep_open(struct inode *inode, struct file * file) int major = imajor(inode); struct snd_hwdep *hw; int err; - wait_queue_t wait; + wait_queue_entry_t wait; if (major == snd_major) { hw = snd_lookup_minor_data(iminor(inode), diff --git a/sound/core/init.c b/sound/core/init.c index 6bda8436d765..d61d2b3cd521 100644 --- a/sound/core/init.c +++ b/sound/core/init.c @@ -989,7 +989,7 @@ EXPORT_SYMBOL(snd_card_file_remove); */ int snd_power_wait(struct snd_card *card, unsigned int power_state) { - wait_queue_t wait; + wait_queue_entry_t wait; int result = 0; /* fastpath */ diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c index 36baf962f9b0..cd8b7bef8d06 100644 --- a/sound/core/oss/pcm_oss.c +++ b/sound/core/oss/pcm_oss.c @@ -1554,7 +1554,7 @@ static int snd_pcm_oss_sync1(struct snd_pcm_substream *substream, size_t size) ssize_t result = 0; snd_pcm_state_t state; long res; - wait_queue_t wait; + wait_queue_entry_t wait; runtime = substream->runtime; init_waitqueue_entry(&wait, current); @@ -2387,7 +2387,7 @@ static int snd_pcm_oss_open(struct inode *inode, struct file *file) struct snd_pcm_oss_file *pcm_oss_file; struct snd_pcm_oss_setup setup[2]; int nonblock; - wait_queue_t wait; + wait_queue_entry_t wait; err = nonseekable_open(inode, file); if (err < 0) diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index 5088d4b8db22..877176067072 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -1904,7 +1904,7 @@ static int wait_for_avail(struct snd_pcm_substream *substream, { struct snd_pcm_runtime *runtime = substream->runtime; int is_playback = substream->stream == SNDRV_PCM_STREAM_PLAYBACK; - wait_queue_t wait; + wait_queue_entry_t wait; int err = 0; snd_pcm_uframes_t avail = 0; long wait_time, tout; @@ -2492,7 +2492,7 @@ static int pcm_chmap_ctl_get(struct snd_kcontrol *kcontrol, struct snd_pcm_substream *substream; const struct snd_pcm_chmap_elem *map; - if (snd_BUG_ON(!info->chmap)) + if (!info->chmap) return -EINVAL; substream = snd_pcm_chmap_substream(info, idx); if (!substream) @@ -2524,7 +2524,7 @@ static int pcm_chmap_ctl_tlv(struct snd_kcontrol *kcontrol, int op_flag, unsigned int __user *dst; int c, count = 0; - if (snd_BUG_ON(!info->chmap)) + if (!info->chmap) return -EINVAL; if (size < 8) return -ENOMEM; diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 13dec5ec93f2..faa2e2be6f2e 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -1652,7 +1652,7 @@ static int snd_pcm_drain(struct snd_pcm_substream *substream, struct snd_card *card; struct snd_pcm_runtime *runtime; struct snd_pcm_substream *s; - wait_queue_t wait; + wait_queue_entry_t wait; int result = 0; int nonblock = 0; @@ -2353,7 +2353,7 @@ static int snd_pcm_capture_open(struct inode *inode, struct file *file) static int snd_pcm_open(struct file *file, struct snd_pcm *pcm, int stream) { int err; - wait_queue_t wait; + wait_queue_entry_t wait; if (pcm == NULL) { err = -ENODEV; diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index ab890336175f..32588ad05653 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -368,7 +368,7 @@ static int snd_rawmidi_open(struct inode *inode, struct file *file) int err; struct snd_rawmidi *rmidi; struct snd_rawmidi_file *rawmidi_file = NULL; - wait_queue_t wait; + wait_queue_entry_t wait; if ((file->f_flags & O_APPEND) && !(file->f_flags & O_NONBLOCK)) return -EINVAL; /* invalid combination */ @@ -1002,7 +1002,7 @@ static ssize_t snd_rawmidi_read(struct file *file, char __user *buf, size_t coun while (count > 0) { spin_lock_irq(&runtime->lock); while (!snd_rawmidi_ready(substream)) { - wait_queue_t wait; + wait_queue_entry_t wait; if ((file->f_flags & O_NONBLOCK) != 0 || result > 0) { spin_unlock_irq(&runtime->lock); return result > 0 ? result : -EAGAIN; @@ -1306,7 +1306,7 @@ static ssize_t snd_rawmidi_write(struct file *file, const char __user *buf, while (count > 0) { spin_lock_irq(&runtime->lock); while (!snd_rawmidi_ready_append(substream, count)) { - wait_queue_t wait; + wait_queue_entry_t wait; if (file->f_flags & O_NONBLOCK) { spin_unlock_irq(&runtime->lock); return result > 0 ? result : -EAGAIN; @@ -1338,7 +1338,7 @@ static ssize_t snd_rawmidi_write(struct file *file, const char __user *buf, if (file->f_flags & O_DSYNC) { spin_lock_irq(&runtime->lock); while (runtime->avail != runtime->buffer_size) { - wait_queue_t wait; + wait_queue_entry_t wait; unsigned int last_avail = runtime->avail; init_waitqueue_entry(&wait, current); add_wait_queue(&runtime->sleep, &wait); diff --git a/sound/core/seq/seq_fifo.c b/sound/core/seq/seq_fifo.c index 01c4cfe30c9f..a8c2822e0198 100644 --- a/sound/core/seq/seq_fifo.c +++ b/sound/core/seq/seq_fifo.c @@ -179,7 +179,7 @@ int snd_seq_fifo_cell_out(struct snd_seq_fifo *f, { struct snd_seq_event_cell *cell; unsigned long flags; - wait_queue_t wait; + wait_queue_entry_t wait; if (snd_BUG_ON(!f)) return -EINVAL; diff --git a/sound/core/seq/seq_memory.c b/sound/core/seq/seq_memory.c index d4c61ec9be13..d6e9aacdc36b 100644 --- a/sound/core/seq/seq_memory.c +++ b/sound/core/seq/seq_memory.c @@ -227,7 +227,7 @@ static int snd_seq_cell_alloc(struct snd_seq_pool *pool, struct snd_seq_event_cell *cell; unsigned long flags; int err = -EAGAIN; - wait_queue_t wait; + wait_queue_entry_t wait; if (pool == NULL) return -EINVAL; diff --git a/sound/core/timer.c b/sound/core/timer.c index cd67d1c12cf1..884c3066b028 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -1964,7 +1964,7 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer, spin_lock_irq(&tu->qlock); while ((long)count - result >= unit) { while (!tu->qused) { - wait_queue_t wait; + wait_queue_entry_t wait; if ((file->f_flags & O_NONBLOCK) != 0 || result > 0) { err = -EAGAIN; diff --git a/sound/firewire/amdtp-stream.c b/sound/firewire/amdtp-stream.c index 9e6f54f8c45d..1e26854b3425 100644 --- a/sound/firewire/amdtp-stream.c +++ b/sound/firewire/amdtp-stream.c @@ -682,7 +682,9 @@ static void out_stream_callback(struct fw_iso_context *context, u32 tstamp, cycle = increment_cycle_count(cycle, 1); if (s->handle_packet(s, 0, cycle, i) < 0) { s->packet_index = -1; - amdtp_stream_pcm_abort(s); + if (in_interrupt()) + amdtp_stream_pcm_abort(s); + WRITE_ONCE(s->pcm_buffer_pointer, SNDRV_PCM_POS_XRUN); return; } } @@ -734,7 +736,9 @@ static void in_stream_callback(struct fw_iso_context *context, u32 tstamp, /* Queueing error or detecting invalid payload. */ if (i < packets) { s->packet_index = -1; - amdtp_stream_pcm_abort(s); + if (in_interrupt()) + amdtp_stream_pcm_abort(s); + WRITE_ONCE(s->pcm_buffer_pointer, SNDRV_PCM_POS_XRUN); return; } diff --git a/sound/firewire/amdtp-stream.h b/sound/firewire/amdtp-stream.h index 7e8831722821..ea1a91e99875 100644 --- a/sound/firewire/amdtp-stream.h +++ b/sound/firewire/amdtp-stream.h @@ -135,7 +135,7 @@ struct amdtp_stream { /* For a PCM substream processing. */ struct snd_pcm_substream *pcm; struct tasklet_struct period_tasklet; - unsigned int pcm_buffer_pointer; + snd_pcm_uframes_t pcm_buffer_pointer; unsigned int pcm_period_pointer; /* To wait for first packet. */ diff --git a/sound/isa/wavefront/wavefront_synth.c b/sound/isa/wavefront/wavefront_synth.c index 4dae9ff9ef5a..0b1e4b34b299 100644 --- a/sound/isa/wavefront/wavefront_synth.c +++ b/sound/isa/wavefront/wavefront_synth.c @@ -1782,7 +1782,7 @@ wavefront_should_cause_interrupt (snd_wavefront_t *dev, int val, int port, unsigned long timeout) { - wait_queue_t wait; + wait_queue_entry_t wait; init_waitqueue_entry(&wait, current); spin_lock_irq(&dev->irq_lock); diff --git a/sound/pci/hda/hda_codec.h b/sound/pci/hda/hda_codec.h index d6fb2d5d01a7..60ce1cfc300f 100644 --- a/sound/pci/hda/hda_codec.h +++ b/sound/pci/hda/hda_codec.h @@ -295,6 +295,8 @@ struct hda_codec { #define list_for_each_codec(c, bus) \ list_for_each_entry(c, &(bus)->core.codec_list, core.list) +#define list_for_each_codec_safe(c, n, bus) \ + list_for_each_entry_safe(c, n, &(bus)->core.codec_list, core.list) /* snd_hda_codec_read/write optional flags */ #define HDA_RW_NO_RESPONSE_FALLBACK (1 << 0) diff --git a/sound/pci/hda/hda_controller.c b/sound/pci/hda/hda_controller.c index 3715a5725613..1c60beb5b70a 100644 --- a/sound/pci/hda/hda_controller.c +++ b/sound/pci/hda/hda_controller.c @@ -1337,8 +1337,12 @@ EXPORT_SYMBOL_GPL(azx_probe_codecs); /* configure each codec instance */ int azx_codec_configure(struct azx *chip) { - struct hda_codec *codec; - list_for_each_codec(codec, &chip->bus) { + struct hda_codec *codec, *next; + + /* use _safe version here since snd_hda_codec_configure() deregisters + * the device upon error and deletes itself from the bus list. + */ + list_for_each_codec_safe(codec, next, &chip->bus) { snd_hda_codec_configure(codec); } return 0; diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c index 2842c82363c0..71545b56b4c8 100644 --- a/sound/pci/hda/hda_generic.c +++ b/sound/pci/hda/hda_generic.c @@ -3174,6 +3174,7 @@ static int check_dyn_adc_switch(struct hda_codec *codec) spec->input_paths[i][nums]); spec->input_paths[i][nums] = spec->input_paths[i][n]; + spec->input_paths[i][n] = 0; } } nums++; diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 1770f085c2a6..01eb1dc7b5b3 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -370,10 +370,12 @@ enum { #define IS_KBL_LP(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x9d71) #define IS_KBL_H(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa2f0) #define IS_BXT(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x5a98) +#define IS_BXT_T(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x1a98) #define IS_GLK(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x3198) -#define IS_SKL_PLUS(pci) (IS_SKL(pci) || IS_SKL_LP(pci) || IS_BXT(pci)) || \ - IS_KBL(pci) || IS_KBL_LP(pci) || IS_KBL_H(pci) || \ - IS_GLK(pci) +#define IS_CFL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa348) +#define IS_SKL_PLUS(pci) (IS_SKL(pci) || IS_SKL_LP(pci) || IS_BXT(pci) || \ + IS_BXT_T(pci) || IS_KBL(pci) || IS_KBL_LP(pci) || \ + IS_KBL_H(pci) || IS_GLK(pci) || IS_CFL(pci)) static char *driver_short_names[] = { [AZX_DRIVER_ICH] = "HDA Intel", @@ -2378,6 +2380,9 @@ static const struct pci_device_id azx_ids[] = { /* Kabylake-H */ { PCI_DEVICE(0x8086, 0xa2f0), .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_SKYLAKE }, + /* Coffelake */ + { PCI_DEVICE(0x8086, 0xa348), + .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_SKYLAKE}, /* Broxton-P(Apollolake) */ { PCI_DEVICE(0x8086, 0x5a98), .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_BROXTON }, diff --git a/sound/pci/mixart/mixart_core.c b/sound/pci/mixart/mixart_core.c index dccf3db48fe0..8bf2ce32d4a8 100644 --- a/sound/pci/mixart/mixart_core.c +++ b/sound/pci/mixart/mixart_core.c @@ -239,7 +239,7 @@ int snd_mixart_send_msg(struct mixart_mgr *mgr, struct mixart_msg *request, int struct mixart_msg resp; u32 msg_frame = 0; /* set to 0, so it's no notification to wait for, but the answer */ int err; - wait_queue_t wait; + wait_queue_entry_t wait; long timeout; init_waitqueue_entry(&wait, current); @@ -284,7 +284,7 @@ int snd_mixart_send_msg_wait_notif(struct mixart_mgr *mgr, struct mixart_msg *request, u32 notif_event) { int err; - wait_queue_t wait; + wait_queue_entry_t wait; long timeout; if (snd_BUG_ON(!notif_event)) diff --git a/sound/pci/ymfpci/ymfpci_main.c b/sound/pci/ymfpci/ymfpci_main.c index fe4ba463b57c..1114166c685c 100644 --- a/sound/pci/ymfpci/ymfpci_main.c +++ b/sound/pci/ymfpci/ymfpci_main.c @@ -781,7 +781,7 @@ static snd_pcm_uframes_t snd_ymfpci_capture_pointer(struct snd_pcm_substream *su static void snd_ymfpci_irq_wait(struct snd_ymfpci *chip) { - wait_queue_t wait; + wait_queue_entry_t wait; int loops = 4; while (loops-- > 0) { diff --git a/sound/soc/intel/skylake/skl-nhlt.c b/sound/soc/intel/skylake/skl-nhlt.c index e3f06672fd6d..e7d766d56c8e 100644 --- a/sound/soc/intel/skylake/skl-nhlt.c +++ b/sound/soc/intel/skylake/skl-nhlt.c @@ -21,8 +21,9 @@ #include "skl.h" /* Unique identification for getting NHLT blobs */ -static u8 OSC_UUID[16] = {0x6E, 0x88, 0x9F, 0xA6, 0xEB, 0x6C, 0x94, 0x45, - 0xA4, 0x1F, 0x7B, 0x5D, 0xCE, 0x24, 0xC5, 0x53}; +static guid_t osc_guid = + GUID_INIT(0xA69F886E, 0x6CEB, 0x4594, + 0xA4, 0x1F, 0x7B, 0x5D, 0xCE, 0x24, 0xC5, 0x53); struct nhlt_acpi_table *skl_nhlt_init(struct device *dev) { @@ -37,7 +38,7 @@ struct nhlt_acpi_table *skl_nhlt_init(struct device *dev) return NULL; } - obj = acpi_evaluate_dsm(handle, OSC_UUID, 1, 1, NULL); + obj = acpi_evaluate_dsm(handle, &osc_guid, 1, 1, NULL); if (obj && obj->type == ACPI_TYPE_BUFFER) { nhlt_ptr = (struct nhlt_resource_desc *)obj->buffer.pointer; nhlt_table = (struct nhlt_acpi_table *) diff --git a/tools/Makefile b/tools/Makefile index c8a90d01dd8e..221e1ce78b06 100644 --- a/tools/Makefile +++ b/tools/Makefile @@ -19,6 +19,7 @@ help: @echo ' kvm_stat - top-like utility for displaying kvm statistics' @echo ' leds - LEDs tools' @echo ' lguest - a minimal 32-bit x86 hypervisor' + @echo ' liblockdep - user-space wrapper for kernel locking-validator' @echo ' net - misc networking tools' @echo ' perf - Linux performance measurement and analysis tool' @echo ' selftests - various kernel selftests' @@ -89,7 +90,7 @@ freefall: FORCE kvm_stat: FORCE $(call descend,kvm/$@) -all: acpi cgroup cpupower gpio hv firewire lguest \ +all: acpi cgroup cpupower gpio hv firewire lguest liblockdep \ perf selftests turbostat usb \ virtio vm net x86_energy_perf_policy \ tmon freefall objtool kvm_stat @@ -103,6 +104,9 @@ cpupower_install: cgroup_install firewire_install gpio_install hv_install lguest_install perf_install usb_install virtio_install vm_install net_install objtool_install: $(call descend,$(@:_install=),install) +liblockdep_install: + $(call descend,lib/lockdep,install) + selftests_install: $(call descend,testing/$(@:_install=),install) @@ -119,7 +123,7 @@ kvm_stat_install: $(call descend,kvm/$(@:_install=),install) install: acpi_install cgroup_install cpupower_install gpio_install \ - hv_install firewire_install lguest_install \ + hv_install firewire_install lguest_install liblockdep_install \ perf_install selftests_install turbostat_install usb_install \ virtio_install vm_install net_install x86_energy_perf_policy_install \ tmon_install freefall_install objtool_install kvm_stat_install diff --git a/tools/include/asm/sections.h b/tools/include/asm/sections.h new file mode 100644 index 000000000000..a80643d7a7f1 --- /dev/null +++ b/tools/include/asm/sections.h @@ -0,0 +1,4 @@ +#ifndef __TOOLS_INCLUDE_LINUX_ASM_SECTIONS_H +#define __TOOLS_INCLUDE_LINUX_ASM_SECTIONS_H + +#endif /* __TOOLS_INCLUDE_LINUX_ASM_SECTIONS_H */ diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h index 1aecad369af5..969db1981868 100644 --- a/tools/include/linux/bitops.h +++ b/tools/include/linux/bitops.h @@ -61,4 +61,14 @@ static inline unsigned fls_long(unsigned long l) return fls64(l); } +/** + * rol32 - rotate a 32-bit value left + * @word: value to rotate + * @shift: bits to roll + */ +static inline __u32 rol32(__u32 word, unsigned int shift) +{ + return (word << shift) | (word >> ((-shift) & 31)); +} + #endif diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h index 825d44f89a29..bd39b2090ad1 100644 --- a/tools/include/linux/compiler-gcc.h +++ b/tools/include/linux/compiler-gcc.h @@ -19,3 +19,13 @@ /* &a[0] degrades to a pointer: a different type from an array */ #define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) + +#define noinline __attribute__((noinline)) + +#define __packed __attribute__((packed)) + +#define __noreturn __attribute__((noreturn)) + +#define __aligned(x) __attribute__((aligned(x))) +#define __printf(a, b) __attribute__((format(printf, a, b))) +#define __scanf(a, b) __attribute__((format(scanf, a, b))) diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h index 23299d7e7160..d7a5604c38d7 100644 --- a/tools/include/linux/compiler.h +++ b/tools/include/linux/compiler.h @@ -17,6 +17,10 @@ # define __always_inline inline __attribute__((always_inline)) #endif +#ifndef noinline +#define noinline +#endif + /* Are two types/vars the same type (ignoring qualifiers)? */ #ifndef __same_type # define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) @@ -45,6 +49,10 @@ # define __maybe_unused __attribute__((unused)) #endif +#ifndef __used +# define __used __attribute__((__unused__)) +#endif + #ifndef __packed # define __packed __attribute__((__packed__)) #endif @@ -65,6 +73,14 @@ # define unlikely(x) __builtin_expect(!!(x), 0) #endif +#ifndef __init +# define __init +#endif + +#ifndef noinline +# define noinline +#endif + #define uninitialized_var(x) x = *(&(x)) #define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x)) diff --git a/tools/lib/lockdep/uinclude/linux/debug_locks.h b/tools/include/linux/debug_locks.h index f38eb64df794..61cc7f501168 100644 --- a/tools/lib/lockdep/uinclude/linux/debug_locks.h +++ b/tools/include/linux/debug_locks.h @@ -3,8 +3,9 @@ #include <stddef.h> #include <linux/compiler.h> +#include <asm/bug.h> -#define DEBUG_LOCKS_WARN_ON(x) (x) +#define DEBUG_LOCKS_WARN_ON(x) WARN_ON(x) extern bool debug_locks; extern bool debug_locks_silent; diff --git a/tools/include/linux/delay.h b/tools/include/linux/delay.h new file mode 100644 index 000000000000..55aa4173af1f --- /dev/null +++ b/tools/include/linux/delay.h @@ -0,0 +1,4 @@ +#ifndef _TOOLS_INCLUDE_LINUX_DELAY_H +#define _TOOLS_INCLUDE_LINUX_DELAY_H + +#endif /* _TOOLS_INCLUDE_LINUX_DELAY_H */ diff --git a/tools/include/linux/err.h b/tools/include/linux/err.h index bdc3dd8131d4..abf0478a8fb2 100644 --- a/tools/include/linux/err.h +++ b/tools/include/linux/err.h @@ -46,4 +46,9 @@ static inline bool __must_check IS_ERR(__force const void *ptr) return IS_ERR_VALUE((unsigned long)ptr); } +static inline bool __must_check IS_ERR_OR_NULL(__force const void *ptr) +{ + return unlikely(!ptr) || IS_ERR_VALUE((unsigned long)ptr); +} + #endif /* _LINUX_ERR_H */ diff --git a/tools/include/linux/ftrace.h b/tools/include/linux/ftrace.h new file mode 100644 index 000000000000..949f541ce11e --- /dev/null +++ b/tools/include/linux/ftrace.h @@ -0,0 +1,4 @@ +#ifndef _TOOLS_INCLUDE_LINUX_FTRACE_H +#define _TOOLS_INCLUDE_LINUX_FTRACE_H + +#endif /* _TOOLS_INCLUDE_LINUX_FTRACE_H */ diff --git a/tools/include/linux/gfp.h b/tools/include/linux/gfp.h new file mode 100644 index 000000000000..22030756fbc0 --- /dev/null +++ b/tools/include/linux/gfp.h @@ -0,0 +1,4 @@ +#ifndef _TOOLS_INCLUDE_LINUX_GFP_H +#define _TOOLS_INCLUDE_LINUX_GFP_H + +#endif /* _TOOLS_INCLUDE_LINUX_GFP_H */ diff --git a/tools/lib/lockdep/uinclude/linux/hardirq.h b/tools/include/linux/hardirq.h index c8f3f8f58729..c8f3f8f58729 100644 --- a/tools/lib/lockdep/uinclude/linux/hardirq.h +++ b/tools/include/linux/hardirq.h diff --git a/tools/include/linux/interrupt.h b/tools/include/linux/interrupt.h new file mode 100644 index 000000000000..6be25bbdca9e --- /dev/null +++ b/tools/include/linux/interrupt.h @@ -0,0 +1,4 @@ +#ifndef _TOOLS_INCLUDE_LINUX_INTERRUPT_H +#define _TOOLS_INCLUDE_LINUX_INTERRUPT_H + +#endif /* _TOOLS_INCLUDE_LINUX_INTERRUPT_H */ diff --git a/tools/lib/lockdep/uinclude/linux/irqflags.h b/tools/include/linux/irqflags.h index 6cc296f0fad0..df77669cfe1c 100644 --- a/tools/lib/lockdep/uinclude/linux/irqflags.h +++ b/tools/include/linux/irqflags.h @@ -17,19 +17,19 @@ #define raw_local_irq_disable() do { } while (0) #define raw_local_irq_enable() do { } while (0) #define raw_local_irq_save(flags) ((flags) = 0) -#define raw_local_irq_restore(flags) do { } while (0) +#define raw_local_irq_restore(flags) ((void)(flags)) #define raw_local_save_flags(flags) ((flags) = 0) -#define raw_irqs_disabled_flags(flags) do { } while (0) +#define raw_irqs_disabled_flags(flags) ((void)(flags)) #define raw_irqs_disabled() 0 #define raw_safe_halt() #define local_irq_enable() do { } while (0) #define local_irq_disable() do { } while (0) #define local_irq_save(flags) ((flags) = 0) -#define local_irq_restore(flags) do { } while (0) +#define local_irq_restore(flags) ((void)(flags)) #define local_save_flags(flags) ((flags) = 0) #define irqs_disabled() (1) -#define irqs_disabled_flags(flags) (0) +#define irqs_disabled_flags(flags) ((void)(flags), 0) #define safe_halt() do { } while (0) #define trace_lock_release(x, y) diff --git a/tools/include/linux/jhash.h b/tools/include/linux/jhash.h new file mode 100644 index 000000000000..348c6f47e4cc --- /dev/null +++ b/tools/include/linux/jhash.h @@ -0,0 +1,175 @@ +#ifndef _LINUX_JHASH_H +#define _LINUX_JHASH_H + +/* jhash.h: Jenkins hash support. + * + * Copyright (C) 2006. Bob Jenkins (bob_jenkins@burtleburtle.net) + * + * http://burtleburtle.net/bob/hash/ + * + * These are the credits from Bob's sources: + * + * lookup3.c, by Bob Jenkins, May 2006, Public Domain. + * + * These are functions for producing 32-bit hashes for hash table lookup. + * hashword(), hashlittle(), hashlittle2(), hashbig(), mix(), and final() + * are externally useful functions. Routines to test the hash are included + * if SELF_TEST is defined. You can use this free for any purpose. It's in + * the public domain. It has no warranty. + * + * Copyright (C) 2009-2010 Jozsef Kadlecsik (kadlec@blackhole.kfki.hu) + * + * I've modified Bob's hash to be useful in the Linux kernel, and + * any bugs present are my fault. + * Jozsef + */ +#include <linux/bitops.h> +#include <linux/unaligned/packed_struct.h> + +/* Best hash sizes are of power of two */ +#define jhash_size(n) ((u32)1<<(n)) +/* Mask the hash value, i.e (value & jhash_mask(n)) instead of (value % n) */ +#define jhash_mask(n) (jhash_size(n)-1) + +/* __jhash_mix -- mix 3 32-bit values reversibly. */ +#define __jhash_mix(a, b, c) \ +{ \ + a -= c; a ^= rol32(c, 4); c += b; \ + b -= a; b ^= rol32(a, 6); a += c; \ + c -= b; c ^= rol32(b, 8); b += a; \ + a -= c; a ^= rol32(c, 16); c += b; \ + b -= a; b ^= rol32(a, 19); a += c; \ + c -= b; c ^= rol32(b, 4); b += a; \ +} + +/* __jhash_final - final mixing of 3 32-bit values (a,b,c) into c */ +#define __jhash_final(a, b, c) \ +{ \ + c ^= b; c -= rol32(b, 14); \ + a ^= c; a -= rol32(c, 11); \ + b ^= a; b -= rol32(a, 25); \ + c ^= b; c -= rol32(b, 16); \ + a ^= c; a -= rol32(c, 4); \ + b ^= a; b -= rol32(a, 14); \ + c ^= b; c -= rol32(b, 24); \ +} + +/* An arbitrary initial parameter */ +#define JHASH_INITVAL 0xdeadbeef + +/* jhash - hash an arbitrary key + * @k: sequence of bytes as key + * @length: the length of the key + * @initval: the previous hash, or an arbitray value + * + * The generic version, hashes an arbitrary sequence of bytes. + * No alignment or length assumptions are made about the input key. + * + * Returns the hash value of the key. The result depends on endianness. + */ +static inline u32 jhash(const void *key, u32 length, u32 initval) +{ + u32 a, b, c; + const u8 *k = key; + + /* Set up the internal state */ + a = b = c = JHASH_INITVAL + length + initval; + + /* All but the last block: affect some 32 bits of (a,b,c) */ + while (length > 12) { + a += __get_unaligned_cpu32(k); + b += __get_unaligned_cpu32(k + 4); + c += __get_unaligned_cpu32(k + 8); + __jhash_mix(a, b, c); + length -= 12; + k += 12; + } + /* Last block: affect all 32 bits of (c) */ + /* All the case statements fall through */ + switch (length) { + case 12: c += (u32)k[11]<<24; + case 11: c += (u32)k[10]<<16; + case 10: c += (u32)k[9]<<8; + case 9: c += k[8]; + case 8: b += (u32)k[7]<<24; + case 7: b += (u32)k[6]<<16; + case 6: b += (u32)k[5]<<8; + case 5: b += k[4]; + case 4: a += (u32)k[3]<<24; + case 3: a += (u32)k[2]<<16; + case 2: a += (u32)k[1]<<8; + case 1: a += k[0]; + __jhash_final(a, b, c); + case 0: /* Nothing left to add */ + break; + } + + return c; +} + +/* jhash2 - hash an array of u32's + * @k: the key which must be an array of u32's + * @length: the number of u32's in the key + * @initval: the previous hash, or an arbitray value + * + * Returns the hash value of the key. + */ +static inline u32 jhash2(const u32 *k, u32 length, u32 initval) +{ + u32 a, b, c; + + /* Set up the internal state */ + a = b = c = JHASH_INITVAL + (length<<2) + initval; + + /* Handle most of the key */ + while (length > 3) { + a += k[0]; + b += k[1]; + c += k[2]; + __jhash_mix(a, b, c); + length -= 3; + k += 3; + } + + /* Handle the last 3 u32's: all the case statements fall through */ + switch (length) { + case 3: c += k[2]; + case 2: b += k[1]; + case 1: a += k[0]; + __jhash_final(a, b, c); + case 0: /* Nothing left to add */ + break; + } + + return c; +} + + +/* __jhash_nwords - hash exactly 3, 2 or 1 word(s) */ +static inline u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval) +{ + a += initval; + b += initval; + c += initval; + + __jhash_final(a, b, c); + + return c; +} + +static inline u32 jhash_3words(u32 a, u32 b, u32 c, u32 initval) +{ + return __jhash_nwords(a, b, c, initval + JHASH_INITVAL + (3 << 2)); +} + +static inline u32 jhash_2words(u32 a, u32 b, u32 initval) +{ + return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2)); +} + +static inline u32 jhash_1word(u32 a, u32 initval) +{ + return __jhash_nwords(a, 0, 0, initval + JHASH_INITVAL + (1 << 2)); +} + +#endif /* _LINUX_JHASH_H */ diff --git a/tools/lib/lockdep/uinclude/linux/kallsyms.h b/tools/include/linux/kallsyms.h index b0f2dbdf1a15..582cc1e5f3a4 100644 --- a/tools/lib/lockdep/uinclude/linux/kallsyms.h +++ b/tools/include/linux/kallsyms.h @@ -3,6 +3,7 @@ #include <linux/kernel.h> #include <stdio.h> +#include <unistd.h> #define KSYM_NAME_LEN 128 @@ -24,7 +25,7 @@ static inline void print_ip_sym(unsigned long ip) name = backtrace_symbols((void **)&ip, 1); - printf("%s\n", *name); + dprintf(STDOUT_FILENO, "%s\n", *name); free(name); } diff --git a/tools/lib/lockdep/uinclude/linux/kern_levels.h b/tools/include/linux/kern_levels.h index 3b9bade28698..3b9bade28698 100644 --- a/tools/lib/lockdep/uinclude/linux/kern_levels.h +++ b/tools/include/linux/kern_levels.h diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h index 73ccc48126bb..77d2e94ca5df 100644 --- a/tools/include/linux/kernel.h +++ b/tools/include/linux/kernel.h @@ -5,6 +5,8 @@ #include <stddef.h> #include <assert.h> #include <linux/compiler.h> +#include <endian.h> +#include <byteswap.h> #ifndef UINT_MAX #define UINT_MAX (~0U) @@ -32,6 +34,7 @@ (type *)((char *)__mptr - offsetof(type, member)); }) #endif +#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)])) #define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); })) #ifndef max @@ -67,12 +70,33 @@ #endif #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) +#if __BYTE_ORDER == __BIG_ENDIAN +#define cpu_to_le16 bswap_16 +#define cpu_to_le32 bswap_32 +#define cpu_to_le64 bswap_64 +#define le16_to_cpu bswap_16 +#define le32_to_cpu bswap_32 +#define le64_to_cpu bswap_64 +#define cpu_to_be16 +#define cpu_to_be32 +#define cpu_to_be64 +#define be16_to_cpu +#define be32_to_cpu +#define be64_to_cpu +#else +#define cpu_to_le16 +#define cpu_to_le32 +#define cpu_to_le64 +#define le16_to_cpu +#define le32_to_cpu +#define le64_to_cpu +#define cpu_to_be16 bswap_16 +#define cpu_to_be32 bswap_32 +#define cpu_to_be64 bswap_64 +#define be16_to_cpu bswap_16 +#define be32_to_cpu bswap_32 +#define be64_to_cpu bswap_64 +#endif int vscnprintf(char *buf, size_t size, const char *fmt, va_list args); int scnprintf(char * buf, size_t size, const char * fmt, ...); @@ -89,4 +113,7 @@ int scnprintf(char * buf, size_t size, const char * fmt, ...); #define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1) #define round_down(x, y) ((x) & ~__round_mask(x, y)) +#define current_gfp_context(k) 0 +#define synchronize_sched() + #endif diff --git a/tools/lib/lockdep/uinclude/linux/kmemcheck.h b/tools/include/linux/kmemcheck.h index 94d598bc6abe..94d598bc6abe 100644 --- a/tools/lib/lockdep/uinclude/linux/kmemcheck.h +++ b/tools/include/linux/kmemcheck.h diff --git a/tools/include/linux/linkage.h b/tools/include/linux/linkage.h new file mode 100644 index 000000000000..bc763d500262 --- /dev/null +++ b/tools/include/linux/linkage.h @@ -0,0 +1,4 @@ +#ifndef _TOOLS_INCLUDE_LINUX_LINKAGE_H +#define _TOOLS_INCLUDE_LINUX_LINKAGE_H + +#endif /* _TOOLS_INCLUDE_LINUX_LINKAGE_H */ diff --git a/tools/lib/lockdep/uinclude/linux/lockdep.h b/tools/include/linux/lockdep.h index c808c7d02d21..8da3e8effafa 100644 --- a/tools/lib/lockdep/uinclude/linux/lockdep.h +++ b/tools/include/linux/lockdep.h @@ -7,8 +7,15 @@ #include <limits.h> #include <linux/utsname.h> #include <linux/compiler.h> +#include <linux/export.h> +#include <linux/kern_levels.h> +#include <linux/err.h> +#include <linux/rcu.h> +#include <linux/list.h> +#include <linux/hardirq.h> +#include <unistd.h> -#define MAX_LOCK_DEPTH 2000UL +#define MAX_LOCK_DEPTH 63UL #define asmlinkage #define __visible @@ -29,31 +36,32 @@ extern struct task_struct *__curr(void); #define current (__curr()) -#define debug_locks_off() 1 +static inline int debug_locks_off(void) +{ + return 1; +} + #define task_pid_nr(tsk) ((tsk)->pid) #define KSYM_NAME_LEN 128 -#define printk printf +#define printk(...) dprintf(STDOUT_FILENO, __VA_ARGS__) +#define pr_err(format, ...) fprintf (stderr, format, ## __VA_ARGS__) +#define pr_warn pr_err #define list_del_rcu list_del #define atomic_t unsigned long #define atomic_inc(x) ((*(x))++) -static struct new_utsname *init_utsname(void) -{ - static struct new_utsname n = (struct new_utsname) { - .release = "liblockdep", - .version = LIBLOCKDEP_VERSION, - }; - - return &n; -} - #define print_tainted() "" #define static_obj(x) 1 #define debug_show_all_locks() extern void debug_check_no_locks_held(void); +static __used bool __is_kernel_percpu_address(unsigned long addr, void *can_addr) +{ + return false; +} + #endif diff --git a/tools/lib/lockdep/uinclude/linux/module.h b/tools/include/linux/module.h index 09c7a7be8ccc..07055db296f3 100644 --- a/tools/lib/lockdep/uinclude/linux/module.h +++ b/tools/include/linux/module.h @@ -3,4 +3,9 @@ #define module_param(name, type, perm) +static inline bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr) +{ + return false; +} + #endif diff --git a/tools/include/linux/mutex.h b/tools/include/linux/mutex.h new file mode 100644 index 000000000000..a8180d25f2fc --- /dev/null +++ b/tools/include/linux/mutex.h @@ -0,0 +1,4 @@ +#ifndef _TOOLS_INCLUDE_LINUX_MUTEX_H +#define _TOOLS_INCLUDE_LINUX_MUTEX_H + +#endif /* _TOOLS_INCLUDE_LINUX_MUTEX_H */ diff --git a/tools/include/linux/proc_fs.h b/tools/include/linux/proc_fs.h new file mode 100644 index 000000000000..8b3b03b64fda --- /dev/null +++ b/tools/include/linux/proc_fs.h @@ -0,0 +1,4 @@ +#ifndef _TOOLS_INCLUDE_LINUX_PROC_FS_H +#define _TOOLS_INCLUDE_LINUX_PROC_FS_H + +#endif /* _TOOLS_INCLUDE_LINUX_PROC_FS_H */ diff --git a/tools/lib/lockdep/uinclude/linux/rcu.h b/tools/include/linux/rcu.h index 042ee8e463c9..5080649dad04 100644 --- a/tools/lib/lockdep/uinclude/linux/rcu.h +++ b/tools/include/linux/rcu.h @@ -18,4 +18,7 @@ static inline bool rcu_is_watching(void) return false; } +#define rcu_assign_pointer(p, v) ((p) = (v)) +#define RCU_INIT_POINTER(p, v) p=(v) + #endif diff --git a/tools/include/linux/sched/clock.h b/tools/include/linux/sched/clock.h new file mode 100644 index 000000000000..5837d17c4182 --- /dev/null +++ b/tools/include/linux/sched/clock.h @@ -0,0 +1,4 @@ +#ifndef _TOOLS_PERF_LINUX_SCHED_CLOCK_H +#define _TOOLS_PERF_LINUX_SCHED_CLOCK_H + +#endif /* _TOOLS_PERF_LINUX_SCHED_CLOCK_H */ diff --git a/tools/include/linux/sched/mm.h b/tools/include/linux/sched/mm.h new file mode 100644 index 000000000000..c8d9f19c1f35 --- /dev/null +++ b/tools/include/linux/sched/mm.h @@ -0,0 +1,4 @@ +#ifndef _TOOLS_PERF_LINUX_SCHED_MM_H +#define _TOOLS_PERF_LINUX_SCHED_MM_H + +#endif /* _TOOLS_PERF_LINUX_SCHED_MM_H */ diff --git a/tools/include/linux/sched/task.h b/tools/include/linux/sched/task.h new file mode 100644 index 000000000000..a97890eca110 --- /dev/null +++ b/tools/include/linux/sched/task.h @@ -0,0 +1,4 @@ +#ifndef _TOOLS_PERF_LINUX_SCHED_TASK_H +#define _TOOLS_PERF_LINUX_SCHED_TASK_H + +#endif /* _TOOLS_PERF_LINUX_SCHED_TASK_H */ diff --git a/tools/include/linux/seq_file.h b/tools/include/linux/seq_file.h new file mode 100644 index 000000000000..102fd9217f1f --- /dev/null +++ b/tools/include/linux/seq_file.h @@ -0,0 +1,4 @@ +#ifndef _TOOLS_INCLUDE_LINUX_SEQ_FILE_H +#define _TOOLS_INCLUDE_LINUX_SEQ_FILE_H + +#endif /* _TOOLS_INCLUDE_LINUX_SEQ_FILE_H */ diff --git a/tools/include/linux/spinlock.h b/tools/include/linux/spinlock.h index 58397dcb19d6..417cda4f793f 100644 --- a/tools/include/linux/spinlock.h +++ b/tools/include/linux/spinlock.h @@ -1,5 +1,31 @@ +#ifndef __LINUX_SPINLOCK_H_ +#define __LINUX_SPINLOCK_H_ + +#include <pthread.h> +#include <stdbool.h> + #define spinlock_t pthread_mutex_t #define DEFINE_SPINLOCK(x) pthread_mutex_t x = PTHREAD_MUTEX_INITIALIZER; #define spin_lock_irqsave(x, f) (void)f, pthread_mutex_lock(x) #define spin_unlock_irqrestore(x, f) (void)f, pthread_mutex_unlock(x) + +#define arch_spinlock_t pthread_mutex_t +#define __ARCH_SPIN_LOCK_UNLOCKED PTHREAD_MUTEX_INITIALIZER + +static inline void arch_spin_lock(arch_spinlock_t *mutex) +{ + pthread_mutex_lock(mutex); +} + +static inline void arch_spin_unlock(arch_spinlock_t *mutex) +{ + pthread_mutex_unlock(mutex); +} + +static inline bool arch_spin_is_locked(arch_spinlock_t *mutex) +{ + return true; +} + +#endif diff --git a/tools/lib/lockdep/uinclude/linux/stacktrace.h b/tools/include/linux/stacktrace.h index 39aecc6b19d1..39aecc6b19d1 100644 --- a/tools/lib/lockdep/uinclude/linux/stacktrace.h +++ b/tools/include/linux/stacktrace.h diff --git a/tools/include/linux/unaligned/packed_struct.h b/tools/include/linux/unaligned/packed_struct.h new file mode 100644 index 000000000000..c0d817de4df2 --- /dev/null +++ b/tools/include/linux/unaligned/packed_struct.h @@ -0,0 +1,46 @@ +#ifndef _LINUX_UNALIGNED_PACKED_STRUCT_H +#define _LINUX_UNALIGNED_PACKED_STRUCT_H + +#include <linux/kernel.h> + +struct __una_u16 { u16 x; } __packed; +struct __una_u32 { u32 x; } __packed; +struct __una_u64 { u64 x; } __packed; + +static inline u16 __get_unaligned_cpu16(const void *p) +{ + const struct __una_u16 *ptr = (const struct __una_u16 *)p; + return ptr->x; +} + +static inline u32 __get_unaligned_cpu32(const void *p) +{ + const struct __una_u32 *ptr = (const struct __una_u32 *)p; + return ptr->x; +} + +static inline u64 __get_unaligned_cpu64(const void *p) +{ + const struct __una_u64 *ptr = (const struct __una_u64 *)p; + return ptr->x; +} + +static inline void __put_unaligned_cpu16(u16 val, void *p) +{ + struct __una_u16 *ptr = (struct __una_u16 *)p; + ptr->x = val; +} + +static inline void __put_unaligned_cpu32(u32 val, void *p) +{ + struct __una_u32 *ptr = (struct __una_u32 *)p; + ptr->x = val; +} + +static inline void __put_unaligned_cpu64(u64 val, void *p) +{ + struct __una_u64 *ptr = (struct __una_u64 *)p; + ptr->x = val; +} + +#endif /* _LINUX_UNALIGNED_PACKED_STRUCT_H */ diff --git a/tools/include/trace/events/lock.h b/tools/include/trace/events/lock.h new file mode 100644 index 000000000000..5b15fd5ee1af --- /dev/null +++ b/tools/include/trace/events/lock.h @@ -0,0 +1,4 @@ +#ifndef _TOOLS_INCLUDE_TRACE_EVENTS_LOCK_H +#define _TOOLS_INCLUDE_TRACE_EVENTS_LOCK_H + +#endif /* _TOOLS_INCLUDE_TRACE_EVENTS_LOCK_H */ diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c index 809c7721cd24..a7ecf8f469f4 100644 --- a/tools/lib/api/fs/fs.c +++ b/tools/lib/api/fs/fs.c @@ -387,6 +387,22 @@ int filename__read_str(const char *filename, char **buf, size_t *sizep) return err; } +int filename__write_int(const char *filename, int value) +{ + int fd = open(filename, O_WRONLY), err = -1; + char buf[64]; + + if (fd < 0) + return err; + + sprintf(buf, "%d", value); + if (write(fd, buf, sizeof(buf)) == sizeof(buf)) + err = 0; + + close(fd); + return err; +} + int procfs__read_str(const char *entry, char **buf, size_t *sizep) { char path[PATH_MAX]; @@ -480,3 +496,17 @@ int sysctl__read_int(const char *sysctl, int *value) return filename__read_int(path, value); } + +int sysfs__write_int(const char *entry, int value) +{ + char path[PATH_MAX]; + const char *sysfs = sysfs__mountpoint(); + + if (!sysfs) + return -1; + + if (snprintf(path, sizeof(path), "%s/%s", sysfs, entry) >= PATH_MAX) + return -1; + + return filename__write_int(path, value); +} diff --git a/tools/lib/api/fs/fs.h b/tools/lib/api/fs/fs.h index 956c21127d1e..45605348461e 100644 --- a/tools/lib/api/fs/fs.h +++ b/tools/lib/api/fs/fs.h @@ -31,6 +31,8 @@ int filename__read_int(const char *filename, int *value); int filename__read_ull(const char *filename, unsigned long long *value); int filename__read_str(const char *filename, char **buf, size_t *sizep); +int filename__write_int(const char *filename, int value); + int procfs__read_str(const char *entry, char **buf, size_t *sizep); int sysctl__read_int(const char *sysctl, int *value); @@ -38,4 +40,6 @@ int sysfs__read_int(const char *entry, int *value); int sysfs__read_ull(const char *entry, unsigned long long *value); int sysfs__read_str(const char *entry, char **buf, size_t *sizep); int sysfs__read_bool(const char *entry, bool *value); + +int sysfs__write_int(const char *entry, int value); #endif /* __API_FS__ */ diff --git a/tools/lib/lockdep/Makefile b/tools/lib/lockdep/Makefile index 3bc0ef9f8923..ed9ace59d112 100644 --- a/tools/lib/lockdep/Makefile +++ b/tools/lib/lockdep/Makefile @@ -79,6 +79,7 @@ INCLUDES = -I. -I./uinclude -I./include -I../../include $(CONFIG_INCLUDES) # Set compile option CFLAGS if not set elsewhere CFLAGS ?= -g -DCONFIG_LOCKDEP -DCONFIG_STACKTRACE -DCONFIG_PROVE_LOCKING -DBITS_PER_LONG=__WORDSIZE -DLIBLOCKDEP_VERSION='"$(LIBLOCKDEP_VERSION)"' -rdynamic -O0 -g CFLAGS += -fPIC +CFLAGS += -Wall override CFLAGS += $(CONFIG_FLAGS) $(INCLUDES) $(PLUGIN_DIR_SQ) @@ -100,7 +101,7 @@ include $(srctree)/tools/build/Makefile.include do_compile_shared_library = \ ($(print_shared_lib_compile) \ - $(CC) --shared $^ -o $@ -lpthread -ldl -Wl,-soname='"$@"';$(shell ln -sf $@ liblockdep.so)) + $(CC) $(LDFLAGS) --shared $^ -o $@ -lpthread -ldl -Wl,-soname='$(@F)';$(shell ln -sf $(@F) $(@D)/liblockdep.so)) do_build_static_lib = \ ($(print_static_lib_build) \ @@ -118,10 +119,10 @@ all_cmd: $(CMD_TARGETS) $(LIB_IN): force $(Q)$(MAKE) $(build)=liblockdep -liblockdep.so.$(LIBLOCKDEP_VERSION): $(LIB_IN) +$(OUTPUT)liblockdep.so.$(LIBLOCKDEP_VERSION): $(LIB_IN) $(Q)$(do_compile_shared_library) -liblockdep.a: $(LIB_IN) +$(OUTPUT)liblockdep.a: $(LIB_IN) $(Q)$(do_build_static_lib) tags: force @@ -149,7 +150,7 @@ install_lib: all_cmd install: install_lib clean: - $(RM) *.o *~ $(TARGETS) *.a *liblockdep*.so* $(VERSION_FILES) .*.d .*.cmd + $(RM) $(OUTPUT)*.o *~ $(TARGETS) $(OUTPUT)*.a $(OUTPUT)*liblockdep*.so* $(VERSION_FILES) $(OUTPUT).*.d $(OUTPUT).*.cmd $(RM) tags TAGS PHONY += force diff --git a/tools/lib/lockdep/lockdep.c b/tools/lib/lockdep/lockdep.c index a0a2e3a266af..ced6d7443cea 100644 --- a/tools/lib/lockdep/lockdep.c +++ b/tools/lib/lockdep/lockdep.c @@ -1,8 +1,27 @@ #include <linux/lockdep.h> +#include <stdlib.h> /* Trivial API wrappers, we don't (yet) have RCU in user-space: */ #define hlist_for_each_entry_rcu hlist_for_each_entry #define hlist_add_head_rcu hlist_add_head #define hlist_del_rcu hlist_del +#define list_for_each_entry_rcu list_for_each_entry +#define list_add_tail_rcu list_add_tail + +u32 prandom_u32(void) +{ + /* Used only by lock_pin_lock() which is dead code */ + abort(); +} + +static struct new_utsname *init_utsname(void) +{ + static struct new_utsname n = (struct new_utsname) { + .release = "liblockdep", + .version = LIBLOCKDEP_VERSION, + }; + + return &n; +} #include "../../../kernel/locking/lockdep.c" diff --git a/tools/lib/lockdep/preload.c b/tools/lib/lockdep/preload.c index 52844847569c..6a2d3c5d4e92 100644 --- a/tools/lib/lockdep/preload.c +++ b/tools/lib/lockdep/preload.c @@ -4,6 +4,7 @@ #include <dlfcn.h> #include <stdlib.h> #include <sysexits.h> +#include <unistd.h> #include "include/liblockdep/mutex.h" #include "../../include/linux/rbtree.h" @@ -122,8 +123,6 @@ static struct rb_node **__get_lock_node(void *lock, struct rb_node **parent) #define LIBLOCKDEP_STATIC_ENTRIES 1024 #endif -#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) - static struct lock_lookup __locks[LIBLOCKDEP_STATIC_ENTRIES]; static int __locks_nr; @@ -149,7 +148,7 @@ static struct lock_lookup *alloc_lock(void) int idx = __locks_nr++; if (idx >= ARRAY_SIZE(__locks)) { - fprintf(stderr, + dprintf(STDERR_FILENO, "LOCKDEP error: insufficient LIBLOCKDEP_STATIC_ENTRIES\n"); exit(EX_UNAVAILABLE); } diff --git a/tools/lib/lockdep/rbtree.c b/tools/lib/lockdep/rbtree.c index f7f43033c8b7..297c304571f8 100644 --- a/tools/lib/lockdep/rbtree.c +++ b/tools/lib/lockdep/rbtree.c @@ -1 +1 @@ -#include "../../../lib/rbtree.c" +#include "../../lib/rbtree.c" diff --git a/tools/lib/lockdep/run_tests.sh b/tools/lib/lockdep/run_tests.sh index 1069d96248c1..f9b94098fc98 100755 --- a/tools/lib/lockdep/run_tests.sh +++ b/tools/lib/lockdep/run_tests.sh @@ -4,9 +4,9 @@ make &> /dev/null for i in `ls tests/*.c`; do testname=$(basename "$i" .c) - gcc -o tests/$testname -pthread -lpthread $i liblockdep.a -Iinclude -D__USE_LIBLOCKDEP &> /dev/null + gcc -o tests/$testname -pthread $i liblockdep.a -Iinclude -D__USE_LIBLOCKDEP &> /dev/null echo -ne "$testname... " - if [ $(timeout 1 ./tests/$testname | wc -l) -gt 0 ]; then + if [ $(timeout 1 ./tests/$testname 2>&1 | wc -l) -gt 0 ]; then echo "PASSED!" else echo "FAILED!" @@ -18,9 +18,9 @@ done for i in `ls tests/*.c`; do testname=$(basename "$i" .c) - gcc -o tests/$testname -pthread -lpthread -Iinclude $i &> /dev/null + gcc -o tests/$testname -pthread -Iinclude $i &> /dev/null echo -ne "(PRELOAD) $testname... " - if [ $(timeout 1 ./lockdep ./tests/$testname | wc -l) -gt 0 ]; then + if [ $(timeout 1 ./lockdep ./tests/$testname 2>&1 | wc -l) -gt 0 ]; then echo "PASSED!" else echo "FAILED!" diff --git a/tools/lib/lockdep/uinclude/asm/hash.h b/tools/lib/lockdep/uinclude/asm/hash.h deleted file mode 100644 index d82b170bb216..000000000000 --- a/tools/lib/lockdep/uinclude/asm/hash.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __ASM_GENERIC_HASH_H -#define __ASM_GENERIC_HASH_H - -/* Stub */ - -#endif /* __ASM_GENERIC_HASH_H */ diff --git a/tools/lib/lockdep/uinclude/asm/hweight.h b/tools/lib/lockdep/uinclude/asm/hweight.h deleted file mode 100644 index fab00ff936d1..000000000000 --- a/tools/lib/lockdep/uinclude/asm/hweight.h +++ /dev/null @@ -1,3 +0,0 @@ - -/* empty file */ - diff --git a/tools/lib/lockdep/uinclude/asm/sections.h b/tools/lib/lockdep/uinclude/asm/sections.h deleted file mode 100644 index fab00ff936d1..000000000000 --- a/tools/lib/lockdep/uinclude/asm/sections.h +++ /dev/null @@ -1,3 +0,0 @@ - -/* empty file */ - diff --git a/tools/lib/lockdep/uinclude/linux/bitops.h b/tools/lib/lockdep/uinclude/linux/bitops.h deleted file mode 100644 index fab00ff936d1..000000000000 --- a/tools/lib/lockdep/uinclude/linux/bitops.h +++ /dev/null @@ -1,3 +0,0 @@ - -/* empty file */ - diff --git a/tools/lib/lockdep/uinclude/linux/compiler.h b/tools/lib/lockdep/uinclude/linux/compiler.h deleted file mode 100644 index fd3e56a83fc2..000000000000 --- a/tools/lib/lockdep/uinclude/linux/compiler.h +++ /dev/null @@ -1,10 +0,0 @@ -#ifndef _LIBLOCKDEP_LINUX_COMPILER_H_ -#define _LIBLOCKDEP_LINUX_COMPILER_H_ - -#define __used __attribute__((__unused__)) -#define unlikely -#define READ_ONCE(x) (x) -#define WRITE_ONCE(x, val) x=(val) -#define RCU_INIT_POINTER(p, v) p=(v) - -#endif diff --git a/tools/lib/lockdep/uinclude/linux/delay.h b/tools/lib/lockdep/uinclude/linux/delay.h deleted file mode 100644 index fab00ff936d1..000000000000 --- a/tools/lib/lockdep/uinclude/linux/delay.h +++ /dev/null @@ -1,3 +0,0 @@ - -/* empty file */ - diff --git a/tools/lib/lockdep/uinclude/linux/ftrace.h b/tools/lib/lockdep/uinclude/linux/ftrace.h deleted file mode 100644 index fab00ff936d1..000000000000 --- a/tools/lib/lockdep/uinclude/linux/ftrace.h +++ /dev/null @@ -1,3 +0,0 @@ - -/* empty file */ - diff --git a/tools/lib/lockdep/uinclude/linux/gfp.h b/tools/lib/lockdep/uinclude/linux/gfp.h deleted file mode 100644 index fab00ff936d1..000000000000 --- a/tools/lib/lockdep/uinclude/linux/gfp.h +++ /dev/null @@ -1,3 +0,0 @@ - -/* empty file */ - diff --git a/tools/lib/lockdep/uinclude/linux/hash.h b/tools/lib/lockdep/uinclude/linux/hash.h deleted file mode 100644 index 0f8479858dc0..000000000000 --- a/tools/lib/lockdep/uinclude/linux/hash.h +++ /dev/null @@ -1 +0,0 @@ -#include "../../../include/linux/hash.h" diff --git a/tools/lib/lockdep/uinclude/linux/interrupt.h b/tools/lib/lockdep/uinclude/linux/interrupt.h deleted file mode 100644 index fab00ff936d1..000000000000 --- a/tools/lib/lockdep/uinclude/linux/interrupt.h +++ /dev/null @@ -1,3 +0,0 @@ - -/* empty file */ - diff --git a/tools/lib/lockdep/uinclude/linux/kernel.h b/tools/lib/lockdep/uinclude/linux/kernel.h deleted file mode 100644 index 276c7a8b2ed1..000000000000 --- a/tools/lib/lockdep/uinclude/linux/kernel.h +++ /dev/null @@ -1,47 +0,0 @@ -#ifndef _LIBLOCKDEP_LINUX_KERNEL_H_ -#define _LIBLOCKDEP_LINUX_KERNEL_H_ - -#include <linux/export.h> -#include <linux/types.h> -#include <linux/rcu.h> -#include <linux/hardirq.h> -#include <linux/kern_levels.h> - -#ifndef container_of -#define container_of(ptr, type, member) ({ \ - const typeof(((type *)0)->member) * __mptr = (ptr); \ - (type *)((char *)__mptr - offsetof(type, member)); }) -#endif - -#define max(x, y) ({ \ - typeof(x) _max1 = (x); \ - typeof(y) _max2 = (y); \ - (void) (&_max1 == &_max2); \ - _max1 > _max2 ? _max1 : _max2; }) - -#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)])) -#define WARN_ON(x) (x) -#define WARN_ON_ONCE(x) (x) -#define likely(x) (x) -#define WARN(x, y...) (x) -#define uninitialized_var(x) x -#define __init -#define noinline -#define list_add_tail_rcu list_add_tail -#define list_for_each_entry_rcu list_for_each_entry -#define barrier() -#define synchronize_sched() - -#ifndef CALLER_ADDR0 -#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0)) -#endif - -#ifndef _RET_IP_ -#define _RET_IP_ CALLER_ADDR0 -#endif - -#ifndef _THIS_IP_ -#define _THIS_IP_ ({ __label__ __here; __here: (unsigned long)&&__here; }) -#endif - -#endif diff --git a/tools/lib/lockdep/uinclude/linux/linkage.h b/tools/lib/lockdep/uinclude/linux/linkage.h deleted file mode 100644 index fab00ff936d1..000000000000 --- a/tools/lib/lockdep/uinclude/linux/linkage.h +++ /dev/null @@ -1,3 +0,0 @@ - -/* empty file */ - diff --git a/tools/lib/lockdep/uinclude/linux/list.h b/tools/lib/lockdep/uinclude/linux/list.h deleted file mode 100644 index 6e9ef31ed82e..000000000000 --- a/tools/lib/lockdep/uinclude/linux/list.h +++ /dev/null @@ -1 +0,0 @@ -#include "../../../include/linux/list.h" diff --git a/tools/lib/lockdep/uinclude/linux/mutex.h b/tools/lib/lockdep/uinclude/linux/mutex.h deleted file mode 100644 index fab00ff936d1..000000000000 --- a/tools/lib/lockdep/uinclude/linux/mutex.h +++ /dev/null @@ -1,3 +0,0 @@ - -/* empty file */ - diff --git a/tools/lib/lockdep/uinclude/linux/poison.h b/tools/lib/lockdep/uinclude/linux/poison.h deleted file mode 100644 index 0c27bdf14233..000000000000 --- a/tools/lib/lockdep/uinclude/linux/poison.h +++ /dev/null @@ -1 +0,0 @@ -#include "../../../include/linux/poison.h" diff --git a/tools/lib/lockdep/uinclude/linux/prefetch.h b/tools/lib/lockdep/uinclude/linux/prefetch.h deleted file mode 100644 index d73fe6f850ac..000000000000 --- a/tools/lib/lockdep/uinclude/linux/prefetch.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _LIBLOCKDEP_LINUX_PREFETCH_H_ -#define _LIBLOCKDEP_LINUX_PREFETCH_H - -static inline void prefetch(void *a __attribute__((unused))) { } - -#endif diff --git a/tools/lib/lockdep/uinclude/linux/proc_fs.h b/tools/lib/lockdep/uinclude/linux/proc_fs.h deleted file mode 100644 index fab00ff936d1..000000000000 --- a/tools/lib/lockdep/uinclude/linux/proc_fs.h +++ /dev/null @@ -1,3 +0,0 @@ - -/* empty file */ - diff --git a/tools/lib/lockdep/uinclude/linux/rbtree_augmented.h b/tools/lib/lockdep/uinclude/linux/rbtree_augmented.h deleted file mode 100644 index c3759477379c..000000000000 --- a/tools/lib/lockdep/uinclude/linux/rbtree_augmented.h +++ /dev/null @@ -1,2 +0,0 @@ -#define __always_inline -#include "../../../include/linux/rbtree_augmented.h" diff --git a/tools/lib/lockdep/uinclude/linux/seq_file.h b/tools/lib/lockdep/uinclude/linux/seq_file.h deleted file mode 100644 index fab00ff936d1..000000000000 --- a/tools/lib/lockdep/uinclude/linux/seq_file.h +++ /dev/null @@ -1,3 +0,0 @@ - -/* empty file */ - diff --git a/tools/lib/lockdep/uinclude/linux/spinlock.h b/tools/lib/lockdep/uinclude/linux/spinlock.h deleted file mode 100644 index 68c1aa2bcba5..000000000000 --- a/tools/lib/lockdep/uinclude/linux/spinlock.h +++ /dev/null @@ -1,25 +0,0 @@ -#ifndef _LIBLOCKDEP_SPINLOCK_H_ -#define _LIBLOCKDEP_SPINLOCK_H_ - -#include <pthread.h> -#include <stdbool.h> - -#define arch_spinlock_t pthread_mutex_t -#define __ARCH_SPIN_LOCK_UNLOCKED PTHREAD_MUTEX_INITIALIZER - -static inline void arch_spin_lock(arch_spinlock_t *mutex) -{ - pthread_mutex_lock(mutex); -} - -static inline void arch_spin_unlock(arch_spinlock_t *mutex) -{ - pthread_mutex_unlock(mutex); -} - -static inline bool arch_spin_is_locked(arch_spinlock_t *mutex) -{ - return true; -} - -#endif diff --git a/tools/lib/lockdep/uinclude/linux/stringify.h b/tools/lib/lockdep/uinclude/linux/stringify.h deleted file mode 100644 index 05dfcd1ac118..000000000000 --- a/tools/lib/lockdep/uinclude/linux/stringify.h +++ /dev/null @@ -1,7 +0,0 @@ -#ifndef _LIBLOCKDEP_LINUX_STRINGIFY_H_ -#define _LIBLOCKDEP_LINUX_STRINGIFY_H_ - -#define __stringify_1(x...) #x -#define __stringify(x...) __stringify_1(x) - -#endif diff --git a/tools/lib/lockdep/uinclude/trace/events/lock.h b/tools/lib/lockdep/uinclude/trace/events/lock.h deleted file mode 100644 index fab00ff936d1..000000000000 --- a/tools/lib/lockdep/uinclude/trace/events/lock.h +++ /dev/null @@ -1,3 +0,0 @@ - -/* empty file */ - diff --git a/tools/objtool/Build b/tools/objtool/Build index d6cdece5e58b..6f2e1987c4d9 100644 --- a/tools/objtool/Build +++ b/tools/objtool/Build @@ -1,5 +1,6 @@ objtool-y += arch/$(SRCARCH)/ objtool-y += builtin-check.o +objtool-y += check.o objtool-y += elf.o objtool-y += special.o objtool-y += objtool.o diff --git a/tools/objtool/Documentation/stack-validation.txt b/tools/objtool/Documentation/stack-validation.txt index 55a60d331f47..17c1195f11f4 100644 --- a/tools/objtool/Documentation/stack-validation.txt +++ b/tools/objtool/Documentation/stack-validation.txt @@ -127,28 +127,13 @@ b) 100% reliable stack traces for DWARF enabled kernels c) Higher live patching compatibility rate - (NOTE: This is not yet implemented) - - Currently with CONFIG_LIVEPATCH there's a basic live patching - framework which is safe for roughly 85-90% of "security" fixes. But - patches can't have complex features like function dependency or - prototype changes, or data structure changes. - - There's a strong need to support patches which have the more complex - features so that the patch compatibility rate for security fixes can - eventually approach something resembling 100%. To achieve that, a - "consistency model" is needed, which allows tasks to be safely - transitioned from an unpatched state to a patched state. - - One of the key requirements of the currently proposed livepatch - consistency model [*] is that it needs to walk the stack of each - sleeping task to determine if it can be transitioned to the patched - state. If objtool can ensure that stack traces are reliable, this - consistency model can be used and the live patching compatibility - rate can be improved significantly. - - [*] https://lkml.kernel.org/r/cover.1423499826.git.jpoimboe@redhat.com + Livepatch has an optional "consistency model", which is needed for + more complex patches. In order for the consistency model to work, + stack traces need to be reliable (or an unreliable condition needs to + be detectable). Objtool makes that possible. + For more details, see the livepatch documentation in the Linux kernel + source tree at Documentation/livepatch/livepatch.txt. Rules ----- @@ -201,80 +186,84 @@ To achieve the validation, objtool enforces the following rules: return normally. -Errors in .S files ------------------- +Objtool warnings +---------------- -If you're getting an error in a compiled .S file which you don't -understand, first make sure that the affected code follows the above -rules. +For asm files, if you're getting an error which doesn't make sense, +first make sure that the affected code follows the above rules. + +For C files, the common culprits are inline asm statements and calls to +"noreturn" functions. See below for more details. + +Another possible cause for errors in C code is if the Makefile removes +-fno-omit-frame-pointer or adds -fomit-frame-pointer to the gcc options. Here are some examples of common warnings reported by objtool, what they mean, and suggestions for how to fix them. -1. asm_file.o: warning: objtool: func()+0x128: call without frame pointer save/setup +1. file.o: warning: objtool: func()+0x128: call without frame pointer save/setup The func() function made a function call without first saving and/or - updating the frame pointer. - - If func() is indeed a callable function, add proper frame pointer - logic using the FRAME_BEGIN and FRAME_END macros. Otherwise, remove - its ELF function annotation by changing ENDPROC to END. + updating the frame pointer, and CONFIG_FRAME_POINTER is enabled. - If you're getting this error in a .c file, see the "Errors in .c - files" section. + If the error is for an asm file, and func() is indeed a callable + function, add proper frame pointer logic using the FRAME_BEGIN and + FRAME_END macros. Otherwise, if it's not a callable function, remove + its ELF function annotation by changing ENDPROC to END, and instead + use the manual CFI hint macros in asm/undwarf.h. + If it's a GCC-compiled .c file, the error may be because the function + uses an inline asm() statement which has a "call" instruction. An + asm() statement with a call instruction must declare the use of the + stack pointer in its output operand. For example, on x86_64: -2. asm_file.o: warning: objtool: .text+0x53: return instruction outside of a callable function - - A return instruction was detected, but objtool couldn't find a way - for a callable function to reach the instruction. + register void *__sp asm("rsp"); + asm volatile("call func" : "+r" (__sp)); - If the return instruction is inside (or reachable from) a callable - function, the function needs to be annotated with the ENTRY/ENDPROC - macros. + Otherwise the stack frame may not get created before the call. - If you _really_ need a return instruction outside of a function, and - are 100% sure that it won't affect stack traces, you can tell - objtool to ignore it. See the "Adding exceptions" section below. +2. file.o: warning: objtool: .text+0x53: unreachable instruction -3. asm_file.o: warning: objtool: func()+0x9: function has unreachable instruction + Objtool couldn't find a code path to reach the instruction. - The instruction lives inside of a callable function, but there's no - possible control flow path from the beginning of the function to the - instruction. + If the error is for an asm file, and the instruction is inside (or + reachable from) a callable function, the function should be annotated + with the ENTRY/ENDPROC macros (ENDPROC is the important one). + Otherwise, the code should probably be annotated with the CFI hint + macros in asm/undwarf.h so objtool and the unwinder can know the + stack state associated with the code. - If the instruction is actually needed, and it's actually in a - callable function, ensure that its function is properly annotated - with ENTRY/ENDPROC. + If you're 100% sure the code won't affect stack traces, or if you're + a just a bad person, you can tell objtool to ignore it. See the + "Adding exceptions" section below. If it's not actually in a callable function (e.g. kernel entry code), change ENDPROC to END. -4. asm_file.o: warning: objtool: func(): can't find starting instruction +4. file.o: warning: objtool: func(): can't find starting instruction or - asm_file.o: warning: objtool: func()+0x11dd: can't decode instruction + file.o: warning: objtool: func()+0x11dd: can't decode instruction - Did you put data in a text section? If so, that can confuse + Does the file have data in a text section? If so, that can confuse objtool's instruction decoder. Move the data to a more appropriate section like .data or .rodata. -5. asm_file.o: warning: objtool: func()+0x6: kernel entry/exit from callable instruction - - This is a kernel entry/exit instruction like sysenter or sysret. - Such instructions aren't allowed in a callable function, and are most - likely part of the kernel entry code. +5. file.o: warning: objtool: func()+0x6: unsupported instruction in callable function - If the instruction isn't actually in a callable function, change - ENDPROC to END. + This is a kernel entry/exit instruction like sysenter or iret. Such + instructions aren't allowed in a callable function, and are most + likely part of the kernel entry code. They should usually not have + the callable function annotation (ENDPROC) and should always be + annotated with the CFI hint macros in asm/undwarf.h. -6. asm_file.o: warning: objtool: func()+0x26: sibling call from callable instruction with changed frame pointer +6. file.o: warning: objtool: func()+0x26: sibling call from callable instruction with modified stack frame - This is a dynamic jump or a jump to an undefined symbol. Stacktool + This is a dynamic jump or a jump to an undefined symbol. Objtool assumed it's a sibling call and detected that the frame pointer wasn't first restored to its original state. @@ -282,24 +271,28 @@ they mean, and suggestions for how to fix them. destination code to the local file. If the instruction is not actually in a callable function (e.g. - kernel entry code), change ENDPROC to END. + kernel entry code), change ENDPROC to END and annotate manually with + the CFI hint macros in asm/undwarf.h. -7. asm_file: warning: objtool: func()+0x5c: frame pointer state mismatch +7. file: warning: objtool: func()+0x5c: stack state mismatch The instruction's frame pointer state is inconsistent, depending on which execution path was taken to reach the instruction. - Make sure the function pushes and sets up the frame pointer (for - x86_64, this means rbp) at the beginning of the function and pops it - at the end of the function. Also make sure that no other code in the - function touches the frame pointer. + Make sure that, when CONFIG_FRAME_POINTER is enabled, the function + pushes and sets up the frame pointer (for x86_64, this means rbp) at + the beginning of the function and pops it at the end of the function. + Also make sure that no other code in the function touches the frame + pointer. + Another possibility is that the code has some asm or inline asm which + does some unusual things to the stack or the frame pointer. In such + cases it's probably appropriate to use the CFI hint macros in + asm/undwarf.h. -Errors in .c files ------------------- -1. c_file.o: warning: objtool: funcA() falls through to next function funcB() +8. file.o: warning: objtool: funcA() falls through to next function funcB() This means that funcA() doesn't end with a return instruction or an unconditional jump, and that objtool has determined that the function @@ -318,22 +311,6 @@ Errors in .c files might be corrupt due to a gcc bug. For more details, see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70646 -2. If you're getting any other objtool error in a compiled .c file, it - may be because the file uses an asm() statement which has a "call" - instruction. An asm() statement with a call instruction must declare - the use of the stack pointer in its output operand. For example, on - x86_64: - - register void *__sp asm("rsp"); - asm volatile("call func" : "+r" (__sp)); - - Otherwise the stack frame may not get created before the call. - -3. Another possible cause for errors in C code is if the Makefile removes - -fno-omit-frame-pointer or adds -fomit-frame-pointer to the gcc options. - -Also see the above section for .S file errors for more information what -the individual error messages mean. If the error doesn't seem to make sense, it could be a bug in objtool. Feel free to ask the objtool maintainer for help. diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile index 27e019c09bd2..0e2765e243c0 100644 --- a/tools/objtool/Makefile +++ b/tools/objtool/Makefile @@ -25,7 +25,7 @@ OBJTOOL_IN := $(OBJTOOL)-in.o all: $(OBJTOOL) INCLUDES := -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi -CFLAGS += -Wall -Werror $(EXTRA_WARNINGS) -fomit-frame-pointer -O2 -g $(INCLUDES) +CFLAGS += -Wall -Werror $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -fomit-frame-pointer -O2 -g $(INCLUDES) LDFLAGS += -lelf $(LIBSUBCMD) # Allow old libelf to be used: diff --git a/tools/objtool/arch.h b/tools/objtool/arch.h index a59e061c0b4a..21aeca874edb 100644 --- a/tools/objtool/arch.h +++ b/tools/objtool/arch.h @@ -19,25 +19,63 @@ #define _ARCH_H #include <stdbool.h> +#include <linux/list.h> #include "elf.h" +#include "cfi.h" -#define INSN_FP_SAVE 1 -#define INSN_FP_SETUP 2 -#define INSN_FP_RESTORE 3 -#define INSN_JUMP_CONDITIONAL 4 -#define INSN_JUMP_UNCONDITIONAL 5 -#define INSN_JUMP_DYNAMIC 6 -#define INSN_CALL 7 -#define INSN_CALL_DYNAMIC 8 -#define INSN_RETURN 9 -#define INSN_CONTEXT_SWITCH 10 -#define INSN_NOP 11 -#define INSN_OTHER 12 +#define INSN_JUMP_CONDITIONAL 1 +#define INSN_JUMP_UNCONDITIONAL 2 +#define INSN_JUMP_DYNAMIC 3 +#define INSN_CALL 4 +#define INSN_CALL_DYNAMIC 5 +#define INSN_RETURN 6 +#define INSN_CONTEXT_SWITCH 7 +#define INSN_STACK 8 +#define INSN_NOP 9 +#define INSN_OTHER 10 #define INSN_LAST INSN_OTHER +enum op_dest_type { + OP_DEST_REG, + OP_DEST_REG_INDIRECT, + OP_DEST_MEM, + OP_DEST_PUSH, + OP_DEST_LEAVE, +}; + +struct op_dest { + enum op_dest_type type; + unsigned char reg; + int offset; +}; + +enum op_src_type { + OP_SRC_REG, + OP_SRC_REG_INDIRECT, + OP_SRC_CONST, + OP_SRC_POP, + OP_SRC_ADD, + OP_SRC_AND, +}; + +struct op_src { + enum op_src_type type; + unsigned char reg; + int offset; +}; + +struct stack_op { + struct op_dest dest; + struct op_src src; +}; + +void arch_initial_func_cfi_state(struct cfi_state *state); + int arch_decode_instruction(struct elf *elf, struct section *sec, unsigned long offset, unsigned int maxlen, unsigned int *len, unsigned char *type, - unsigned long *displacement); + unsigned long *immediate, struct stack_op *op); + +bool arch_callee_saved_reg(unsigned char reg); #endif /* _ARCH_H */ diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 6ac99e3266eb..a36c2eba64e7 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -27,6 +27,17 @@ #include "../../arch.h" #include "../../warn.h" +static unsigned char op_to_cfi_reg[][2] = { + {CFI_AX, CFI_R8}, + {CFI_CX, CFI_R9}, + {CFI_DX, CFI_R10}, + {CFI_BX, CFI_R11}, + {CFI_SP, CFI_R12}, + {CFI_BP, CFI_R13}, + {CFI_SI, CFI_R14}, + {CFI_DI, CFI_R15}, +}; + static int is_x86_64(struct elf *elf) { switch (elf->ehdr.e_machine) { @@ -40,24 +51,50 @@ static int is_x86_64(struct elf *elf) } } +bool arch_callee_saved_reg(unsigned char reg) +{ + switch (reg) { + case CFI_BP: + case CFI_BX: + case CFI_R12: + case CFI_R13: + case CFI_R14: + case CFI_R15: + return true; + + case CFI_AX: + case CFI_CX: + case CFI_DX: + case CFI_SI: + case CFI_DI: + case CFI_SP: + case CFI_R8: + case CFI_R9: + case CFI_R10: + case CFI_R11: + case CFI_RA: + default: + return false; + } +} + int arch_decode_instruction(struct elf *elf, struct section *sec, unsigned long offset, unsigned int maxlen, unsigned int *len, unsigned char *type, - unsigned long *immediate) + unsigned long *immediate, struct stack_op *op) { struct insn insn; - int x86_64; - unsigned char op1, op2, ext; + int x86_64, sign; + unsigned char op1, op2, rex = 0, rex_b = 0, rex_r = 0, rex_w = 0, + modrm = 0, modrm_mod = 0, modrm_rm = 0, modrm_reg = 0, + sib = 0; x86_64 = is_x86_64(elf); if (x86_64 == -1) return -1; - insn_init(&insn, (void *)(sec->data + offset), maxlen, x86_64); + insn_init(&insn, sec->data->d_buf + offset, maxlen, x86_64); insn_get_length(&insn); - insn_get_opcode(&insn); - insn_get_modrm(&insn); - insn_get_immediate(&insn); if (!insn_complete(&insn)) { WARN_FUNC("can't decode instruction", sec, offset); @@ -73,67 +110,323 @@ int arch_decode_instruction(struct elf *elf, struct section *sec, op1 = insn.opcode.bytes[0]; op2 = insn.opcode.bytes[1]; + if (insn.rex_prefix.nbytes) { + rex = insn.rex_prefix.bytes[0]; + rex_w = X86_REX_W(rex) >> 3; + rex_r = X86_REX_R(rex) >> 2; + rex_b = X86_REX_B(rex); + } + + if (insn.modrm.nbytes) { + modrm = insn.modrm.bytes[0]; + modrm_mod = X86_MODRM_MOD(modrm); + modrm_reg = X86_MODRM_REG(modrm); + modrm_rm = X86_MODRM_RM(modrm); + } + + if (insn.sib.nbytes) + sib = insn.sib.bytes[0]; + switch (op1) { - case 0x55: - if (!insn.rex_prefix.nbytes) - /* push rbp */ - *type = INSN_FP_SAVE; + + case 0x1: + case 0x29: + if (rex_w && !rex_b && modrm_mod == 3 && modrm_rm == 4) { + + /* add/sub reg, %rsp */ + *type = INSN_STACK; + op->src.type = OP_SRC_ADD; + op->src.reg = op_to_cfi_reg[modrm_reg][rex_r]; + op->dest.type = OP_SRC_REG; + op->dest.reg = CFI_SP; + } + break; + + case 0x50 ... 0x57: + + /* push reg */ + *type = INSN_STACK; + op->src.type = OP_SRC_REG; + op->src.reg = op_to_cfi_reg[op1 & 0x7][rex_b]; + op->dest.type = OP_DEST_PUSH; + break; - case 0x5d: - if (!insn.rex_prefix.nbytes) - /* pop rbp */ - *type = INSN_FP_RESTORE; + case 0x58 ... 0x5f: + + /* pop reg */ + *type = INSN_STACK; + op->src.type = OP_SRC_POP; + op->dest.type = OP_DEST_REG; + op->dest.reg = op_to_cfi_reg[op1 & 0x7][rex_b]; + + break; + + case 0x68: + case 0x6a: + /* push immediate */ + *type = INSN_STACK; + op->src.type = OP_SRC_CONST; + op->dest.type = OP_DEST_PUSH; break; case 0x70 ... 0x7f: *type = INSN_JUMP_CONDITIONAL; break; + case 0x81: + case 0x83: + if (rex != 0x48) + break; + + if (modrm == 0xe4) { + /* and imm, %rsp */ + *type = INSN_STACK; + op->src.type = OP_SRC_AND; + op->src.reg = CFI_SP; + op->src.offset = insn.immediate.value; + op->dest.type = OP_DEST_REG; + op->dest.reg = CFI_SP; + break; + } + + if (modrm == 0xc4) + sign = 1; + else if (modrm == 0xec) + sign = -1; + else + break; + + /* add/sub imm, %rsp */ + *type = INSN_STACK; + op->src.type = OP_SRC_ADD; + op->src.reg = CFI_SP; + op->src.offset = insn.immediate.value * sign; + op->dest.type = OP_DEST_REG; + op->dest.reg = CFI_SP; + break; + case 0x89: - if (insn.rex_prefix.nbytes == 1 && - insn.rex_prefix.bytes[0] == 0x48 && - insn.modrm.nbytes && insn.modrm.bytes[0] == 0xe5) - /* mov rsp, rbp */ - *type = INSN_FP_SETUP; + if (rex == 0x48 && modrm == 0xe5) { + + /* mov %rsp, %rbp */ + *type = INSN_STACK; + op->src.type = OP_SRC_REG; + op->src.reg = CFI_SP; + op->dest.type = OP_DEST_REG; + op->dest.reg = CFI_BP; + break; + } + /* fallthrough */ + case 0x88: + if (!rex_b && + (modrm_mod == 1 || modrm_mod == 2) && modrm_rm == 5) { + + /* mov reg, disp(%rbp) */ + *type = INSN_STACK; + op->src.type = OP_SRC_REG; + op->src.reg = op_to_cfi_reg[modrm_reg][rex_r]; + op->dest.type = OP_DEST_REG_INDIRECT; + op->dest.reg = CFI_BP; + op->dest.offset = insn.displacement.value; + + } else if (rex_w && !rex_b && modrm_rm == 4 && sib == 0x24) { + + /* mov reg, disp(%rsp) */ + *type = INSN_STACK; + op->src.type = OP_SRC_REG; + op->src.reg = op_to_cfi_reg[modrm_reg][rex_r]; + op->dest.type = OP_DEST_REG_INDIRECT; + op->dest.reg = CFI_SP; + op->dest.offset = insn.displacement.value; + } + + break; + + case 0x8b: + if (rex_w && !rex_b && modrm_mod == 1 && modrm_rm == 5) { + + /* mov disp(%rbp), reg */ + *type = INSN_STACK; + op->src.type = OP_SRC_REG_INDIRECT; + op->src.reg = CFI_BP; + op->src.offset = insn.displacement.value; + op->dest.type = OP_DEST_REG; + op->dest.reg = op_to_cfi_reg[modrm_reg][rex_r]; + + } else if (rex_w && !rex_b && sib == 0x24 && + modrm_mod != 3 && modrm_rm == 4) { + + /* mov disp(%rsp), reg */ + *type = INSN_STACK; + op->src.type = OP_SRC_REG_INDIRECT; + op->src.reg = CFI_SP; + op->src.offset = insn.displacement.value; + op->dest.type = OP_DEST_REG; + op->dest.reg = op_to_cfi_reg[modrm_reg][rex_r]; + } + break; case 0x8d: - if (insn.rex_prefix.nbytes && - insn.rex_prefix.bytes[0] == 0x48 && - insn.modrm.nbytes && insn.modrm.bytes[0] == 0x2c && - insn.sib.nbytes && insn.sib.bytes[0] == 0x24) - /* lea %(rsp), %rbp */ - *type = INSN_FP_SETUP; + if (rex == 0x48 && modrm == 0x65) { + + /* lea -disp(%rbp), %rsp */ + *type = INSN_STACK; + op->src.type = OP_SRC_ADD; + op->src.reg = CFI_BP; + op->src.offset = insn.displacement.value; + op->dest.type = OP_DEST_REG; + op->dest.reg = CFI_SP; + break; + } + + if (rex == 0x4c && modrm == 0x54 && sib == 0x24 && + insn.displacement.value == 8) { + + /* + * lea 0x8(%rsp), %r10 + * + * Here r10 is the "drap" pointer, used as a stack + * pointer helper when the stack gets realigned. + */ + *type = INSN_STACK; + op->src.type = OP_SRC_ADD; + op->src.reg = CFI_SP; + op->src.offset = 8; + op->dest.type = OP_DEST_REG; + op->dest.reg = CFI_R10; + break; + } + + if (rex == 0x4c && modrm == 0x6c && sib == 0x24 && + insn.displacement.value == 16) { + + /* + * lea 0x10(%rsp), %r13 + * + * Here r13 is the "drap" pointer, used as a stack + * pointer helper when the stack gets realigned. + */ + *type = INSN_STACK; + op->src.type = OP_SRC_ADD; + op->src.reg = CFI_SP; + op->src.offset = 16; + op->dest.type = OP_DEST_REG; + op->dest.reg = CFI_R13; + break; + } + + if (rex == 0x49 && modrm == 0x62 && + insn.displacement.value == -8) { + + /* + * lea -0x8(%r10), %rsp + * + * Restoring rsp back to its original value after a + * stack realignment. + */ + *type = INSN_STACK; + op->src.type = OP_SRC_ADD; + op->src.reg = CFI_R10; + op->src.offset = -8; + op->dest.type = OP_DEST_REG; + op->dest.reg = CFI_SP; + break; + } + + if (rex == 0x49 && modrm == 0x65 && + insn.displacement.value == -16) { + + /* + * lea -0x10(%r13), %rsp + * + * Restoring rsp back to its original value after a + * stack realignment. + */ + *type = INSN_STACK; + op->src.type = OP_SRC_ADD; + op->src.reg = CFI_R13; + op->src.offset = -16; + op->dest.type = OP_DEST_REG; + op->dest.reg = CFI_SP; + break; + } + + break; + + case 0x8f: + /* pop to mem */ + *type = INSN_STACK; + op->src.type = OP_SRC_POP; + op->dest.type = OP_DEST_MEM; break; case 0x90: *type = INSN_NOP; break; + case 0x9c: + /* pushf */ + *type = INSN_STACK; + op->src.type = OP_SRC_CONST; + op->dest.type = OP_DEST_PUSH; + break; + + case 0x9d: + /* popf */ + *type = INSN_STACK; + op->src.type = OP_SRC_POP; + op->dest.type = OP_DEST_MEM; + break; + case 0x0f: + if (op2 >= 0x80 && op2 <= 0x8f) *type = INSN_JUMP_CONDITIONAL; else if (op2 == 0x05 || op2 == 0x07 || op2 == 0x34 || op2 == 0x35) + /* sysenter, sysret */ *type = INSN_CONTEXT_SWITCH; + else if (op2 == 0x0d || op2 == 0x1f) + /* nopl/nopw */ *type = INSN_NOP; - else if (op2 == 0x01 && insn.modrm.nbytes && - (insn.modrm.bytes[0] == 0xc2 || - insn.modrm.bytes[0] == 0xd8)) - /* vmlaunch, vmrun */ - *type = INSN_CONTEXT_SWITCH; + + else if (op2 == 0xa0 || op2 == 0xa8) { + + /* push fs/gs */ + *type = INSN_STACK; + op->src.type = OP_SRC_CONST; + op->dest.type = OP_DEST_PUSH; + + } else if (op2 == 0xa1 || op2 == 0xa9) { + + /* pop fs/gs */ + *type = INSN_STACK; + op->src.type = OP_SRC_POP; + op->dest.type = OP_DEST_MEM; + } break; - case 0xc9: /* leave */ - *type = INSN_FP_RESTORE; + case 0xc9: + /* + * leave + * + * equivalent to: + * mov bp, sp + * pop bp + */ + *type = INSN_STACK; + op->dest.type = OP_DEST_LEAVE; + break; - case 0xe3: /* jecxz/jrcxz */ + case 0xe3: + /* jecxz/jrcxz */ *type = INSN_JUMP_CONDITIONAL; break; @@ -158,14 +451,27 @@ int arch_decode_instruction(struct elf *elf, struct section *sec, break; case 0xff: - ext = X86_MODRM_REG(insn.modrm.bytes[0]); - if (ext == 2 || ext == 3) + if (modrm_reg == 2 || modrm_reg == 3) + *type = INSN_CALL_DYNAMIC; - else if (ext == 4) + + else if (modrm_reg == 4) + *type = INSN_JUMP_DYNAMIC; - else if (ext == 5) /*jmpf */ + + else if (modrm_reg == 5) + + /* jmpf */ *type = INSN_CONTEXT_SWITCH; + else if (modrm_reg == 6) { + + /* push from mem */ + *type = INSN_STACK; + op->src.type = OP_SRC_CONST; + op->dest.type = OP_DEST_PUSH; + } + break; default: @@ -176,3 +482,21 @@ int arch_decode_instruction(struct elf *elf, struct section *sec, return 0; } + +void arch_initial_func_cfi_state(struct cfi_state *state) +{ + int i; + + for (i = 0; i < CFI_NUM_REGS; i++) { + state->regs[i].base = CFI_UNDEFINED; + state->regs[i].offset = 0; + } + + /* initial CFA (call frame address) */ + state->cfa.base = CFI_SP; + state->cfa.offset = 8; + + /* initial RA (return address) */ + state->regs[16].base = CFI_CFA; + state->regs[16].offset = -8; +} diff --git a/tools/objtool/arch/x86/insn/x86-opcode-map.txt b/tools/objtool/arch/x86/insn/x86-opcode-map.txt index 767be7c76034..12e377184ee4 100644 --- a/tools/objtool/arch/x86/insn/x86-opcode-map.txt +++ b/tools/objtool/arch/x86/insn/x86-opcode-map.txt @@ -1009,7 +1009,7 @@ GrpTable: Grp15 1: fxstor | RDGSBASE Ry (F3),(11B) 2: vldmxcsr Md (v1) | WRFSBASE Ry (F3),(11B) 3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B) -4: XSAVE +4: XSAVE | ptwrite Ey (F3),(11B) 5: XRSTOR | lfence (11B) 6: XSAVEOPT | clwb (66) | mfence (11B) 7: clflush | clflushopt (66) | sfence (11B) diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c index 5f66697fe1e0..365c34ecab26 100644 --- a/tools/objtool/builtin-check.c +++ b/tools/objtool/builtin-check.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2015 Josh Poimboeuf <jpoimboe@redhat.com> + * Copyright (C) 2015-2017 Josh Poimboeuf <jpoimboe@redhat.com> * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -25,1287 +25,32 @@ * For more information, see tools/objtool/Documentation/stack-validation.txt. */ -#include <string.h> -#include <stdlib.h> #include <subcmd/parse-options.h> - #include "builtin.h" -#include "elf.h" -#include "special.h" -#include "arch.h" -#include "warn.h" - -#include <linux/hashtable.h> -#include <linux/kernel.h> - -#define STATE_FP_SAVED 0x1 -#define STATE_FP_SETUP 0x2 -#define STATE_FENTRY 0x4 - -struct instruction { - struct list_head list; - struct hlist_node hash; - struct section *sec; - unsigned long offset; - unsigned int len, state; - unsigned char type; - unsigned long immediate; - bool alt_group, visited, dead_end; - struct symbol *call_dest; - struct instruction *jump_dest; - struct list_head alts; - struct symbol *func; -}; - -struct alternative { - struct list_head list; - struct instruction *insn; -}; - -struct objtool_file { - struct elf *elf; - struct list_head insn_list; - DECLARE_HASHTABLE(insn_hash, 16); - struct section *rodata, *whitelist; - bool ignore_unreachables, c_file; -}; - -const char *objname; -static bool nofp; - -static struct instruction *find_insn(struct objtool_file *file, - struct section *sec, unsigned long offset) -{ - struct instruction *insn; - - hash_for_each_possible(file->insn_hash, insn, hash, offset) - if (insn->sec == sec && insn->offset == offset) - return insn; - - return NULL; -} - -static struct instruction *next_insn_same_sec(struct objtool_file *file, - struct instruction *insn) -{ - struct instruction *next = list_next_entry(insn, list); - - if (&next->list == &file->insn_list || next->sec != insn->sec) - return NULL; - - return next; -} - -static bool gcov_enabled(struct objtool_file *file) -{ - struct section *sec; - struct symbol *sym; - - list_for_each_entry(sec, &file->elf->sections, list) - list_for_each_entry(sym, &sec->symbol_list, list) - if (!strncmp(sym->name, "__gcov_.", 8)) - return true; - - return false; -} - -#define for_each_insn(file, insn) \ - list_for_each_entry(insn, &file->insn_list, list) - -#define func_for_each_insn(file, func, insn) \ - for (insn = find_insn(file, func->sec, func->offset); \ - insn && &insn->list != &file->insn_list && \ - insn->sec == func->sec && \ - insn->offset < func->offset + func->len; \ - insn = list_next_entry(insn, list)) - -#define func_for_each_insn_continue_reverse(file, func, insn) \ - for (insn = list_prev_entry(insn, list); \ - &insn->list != &file->insn_list && \ - insn->sec == func->sec && insn->offset >= func->offset; \ - insn = list_prev_entry(insn, list)) - -#define sec_for_each_insn_from(file, insn) \ - for (; insn; insn = next_insn_same_sec(file, insn)) - - -/* - * Check if the function has been manually whitelisted with the - * STACK_FRAME_NON_STANDARD macro, or if it should be automatically whitelisted - * due to its use of a context switching instruction. - */ -static bool ignore_func(struct objtool_file *file, struct symbol *func) -{ - struct rela *rela; - struct instruction *insn; - - /* check for STACK_FRAME_NON_STANDARD */ - if (file->whitelist && file->whitelist->rela) - list_for_each_entry(rela, &file->whitelist->rela->rela_list, list) { - if (rela->sym->type == STT_SECTION && - rela->sym->sec == func->sec && - rela->addend == func->offset) - return true; - if (rela->sym->type == STT_FUNC && rela->sym == func) - return true; - } - - /* check if it has a context switching instruction */ - func_for_each_insn(file, func, insn) - if (insn->type == INSN_CONTEXT_SWITCH) - return true; - - return false; -} - -/* - * This checks to see if the given function is a "noreturn" function. - * - * For global functions which are outside the scope of this object file, we - * have to keep a manual list of them. - * - * For local functions, we have to detect them manually by simply looking for - * the lack of a return instruction. - * - * Returns: - * -1: error - * 0: no dead end - * 1: dead end - */ -static int __dead_end_function(struct objtool_file *file, struct symbol *func, - int recursion) -{ - int i; - struct instruction *insn; - bool empty = true; - - /* - * Unfortunately these have to be hard coded because the noreturn - * attribute isn't provided in ELF data. - */ - static const char * const global_noreturns[] = { - "__stack_chk_fail", - "panic", - "do_exit", - "do_task_dead", - "__module_put_and_exit", - "complete_and_exit", - "kvm_spurious_fault", - "__reiserfs_panic", - "lbug_with_loc", - "fortify_panic", - }; - - if (func->bind == STB_WEAK) - return 0; - - if (func->bind == STB_GLOBAL) - for (i = 0; i < ARRAY_SIZE(global_noreturns); i++) - if (!strcmp(func->name, global_noreturns[i])) - return 1; - - if (!func->sec) - return 0; - - func_for_each_insn(file, func, insn) { - empty = false; - - if (insn->type == INSN_RETURN) - return 0; - } - - if (empty) - return 0; - - /* - * A function can have a sibling call instead of a return. In that - * case, the function's dead-end status depends on whether the target - * of the sibling call returns. - */ - func_for_each_insn(file, func, insn) { - if (insn->sec != func->sec || - insn->offset >= func->offset + func->len) - break; - - if (insn->type == INSN_JUMP_UNCONDITIONAL) { - struct instruction *dest = insn->jump_dest; - struct symbol *dest_func; - - if (!dest) - /* sibling call to another file */ - return 0; - - if (dest->sec != func->sec || - dest->offset < func->offset || - dest->offset >= func->offset + func->len) { - /* local sibling call */ - dest_func = find_symbol_by_offset(dest->sec, - dest->offset); - if (!dest_func) - continue; - - if (recursion == 5) { - WARN_FUNC("infinite recursion (objtool bug!)", - dest->sec, dest->offset); - return -1; - } - - return __dead_end_function(file, dest_func, - recursion + 1); - } - } - - if (insn->type == INSN_JUMP_DYNAMIC && list_empty(&insn->alts)) - /* sibling call */ - return 0; - } - - return 1; -} - -static int dead_end_function(struct objtool_file *file, struct symbol *func) -{ - return __dead_end_function(file, func, 0); -} - -/* - * Call the arch-specific instruction decoder for all the instructions and add - * them to the global instruction list. - */ -static int decode_instructions(struct objtool_file *file) -{ - struct section *sec; - struct symbol *func; - unsigned long offset; - struct instruction *insn; - int ret; - - list_for_each_entry(sec, &file->elf->sections, list) { - - if (!(sec->sh.sh_flags & SHF_EXECINSTR)) - continue; - - for (offset = 0; offset < sec->len; offset += insn->len) { - insn = malloc(sizeof(*insn)); - memset(insn, 0, sizeof(*insn)); - - INIT_LIST_HEAD(&insn->alts); - insn->sec = sec; - insn->offset = offset; - - ret = arch_decode_instruction(file->elf, sec, offset, - sec->len - offset, - &insn->len, &insn->type, - &insn->immediate); - if (ret) - return ret; - - if (!insn->type || insn->type > INSN_LAST) { - WARN_FUNC("invalid instruction type %d", - insn->sec, insn->offset, insn->type); - return -1; - } - - hash_add(file->insn_hash, &insn->hash, insn->offset); - list_add_tail(&insn->list, &file->insn_list); - } - - list_for_each_entry(func, &sec->symbol_list, list) { - if (func->type != STT_FUNC) - continue; - - if (!find_insn(file, sec, func->offset)) { - WARN("%s(): can't find starting instruction", - func->name); - return -1; - } - - func_for_each_insn(file, func, insn) - if (!insn->func) - insn->func = func; - } - } - - return 0; -} - -/* - * Find all uses of the unreachable() macro, which are code path dead ends. - */ -static int add_dead_ends(struct objtool_file *file) -{ - struct section *sec; - struct rela *rela; - struct instruction *insn; - bool found; - - sec = find_section_by_name(file->elf, ".rela.discard.unreachable"); - if (!sec) - return 0; - - list_for_each_entry(rela, &sec->rela_list, list) { - if (rela->sym->type != STT_SECTION) { - WARN("unexpected relocation symbol type in %s", sec->name); - return -1; - } - insn = find_insn(file, rela->sym->sec, rela->addend); - if (insn) - insn = list_prev_entry(insn, list); - else if (rela->addend == rela->sym->sec->len) { - found = false; - list_for_each_entry_reverse(insn, &file->insn_list, list) { - if (insn->sec == rela->sym->sec) { - found = true; - break; - } - } - - if (!found) { - WARN("can't find unreachable insn at %s+0x%x", - rela->sym->sec->name, rela->addend); - return -1; - } - } else { - WARN("can't find unreachable insn at %s+0x%x", - rela->sym->sec->name, rela->addend); - return -1; - } - - insn->dead_end = true; - } - - return 0; -} - -/* - * Warnings shouldn't be reported for ignored functions. - */ -static void add_ignores(struct objtool_file *file) -{ - struct instruction *insn; - struct section *sec; - struct symbol *func; - - list_for_each_entry(sec, &file->elf->sections, list) { - list_for_each_entry(func, &sec->symbol_list, list) { - if (func->type != STT_FUNC) - continue; - - if (!ignore_func(file, func)) - continue; - - func_for_each_insn(file, func, insn) - insn->visited = true; - } - } -} - -/* - * Find the destination instructions for all jumps. - */ -static int add_jump_destinations(struct objtool_file *file) -{ - struct instruction *insn; - struct rela *rela; - struct section *dest_sec; - unsigned long dest_off; - - for_each_insn(file, insn) { - if (insn->type != INSN_JUMP_CONDITIONAL && - insn->type != INSN_JUMP_UNCONDITIONAL) - continue; - - /* skip ignores */ - if (insn->visited) - continue; - - rela = find_rela_by_dest_range(insn->sec, insn->offset, - insn->len); - if (!rela) { - dest_sec = insn->sec; - dest_off = insn->offset + insn->len + insn->immediate; - } else if (rela->sym->type == STT_SECTION) { - dest_sec = rela->sym->sec; - dest_off = rela->addend + 4; - } else if (rela->sym->sec->idx) { - dest_sec = rela->sym->sec; - dest_off = rela->sym->sym.st_value + rela->addend + 4; - } else { - /* sibling call */ - insn->jump_dest = 0; - continue; - } - - insn->jump_dest = find_insn(file, dest_sec, dest_off); - if (!insn->jump_dest) { - - /* - * This is a special case where an alt instruction - * jumps past the end of the section. These are - * handled later in handle_group_alt(). - */ - if (!strcmp(insn->sec->name, ".altinstr_replacement")) - continue; - - WARN_FUNC("can't find jump dest instruction at %s+0x%lx", - insn->sec, insn->offset, dest_sec->name, - dest_off); - return -1; - } - } - - return 0; -} - -/* - * Find the destination instructions for all calls. - */ -static int add_call_destinations(struct objtool_file *file) -{ - struct instruction *insn; - unsigned long dest_off; - struct rela *rela; - - for_each_insn(file, insn) { - if (insn->type != INSN_CALL) - continue; - - rela = find_rela_by_dest_range(insn->sec, insn->offset, - insn->len); - if (!rela) { - dest_off = insn->offset + insn->len + insn->immediate; - insn->call_dest = find_symbol_by_offset(insn->sec, - dest_off); - if (!insn->call_dest) { - WARN_FUNC("can't find call dest symbol at offset 0x%lx", - insn->sec, insn->offset, dest_off); - return -1; - } - } else if (rela->sym->type == STT_SECTION) { - insn->call_dest = find_symbol_by_offset(rela->sym->sec, - rela->addend+4); - if (!insn->call_dest || - insn->call_dest->type != STT_FUNC) { - WARN_FUNC("can't find call dest symbol at %s+0x%x", - insn->sec, insn->offset, - rela->sym->sec->name, - rela->addend + 4); - return -1; - } - } else - insn->call_dest = rela->sym; - } - - return 0; -} - -/* - * The .alternatives section requires some extra special care, over and above - * what other special sections require: - * - * 1. Because alternatives are patched in-place, we need to insert a fake jump - * instruction at the end so that validate_branch() skips all the original - * replaced instructions when validating the new instruction path. - * - * 2. An added wrinkle is that the new instruction length might be zero. In - * that case the old instructions are replaced with noops. We simulate that - * by creating a fake jump as the only new instruction. - * - * 3. In some cases, the alternative section includes an instruction which - * conditionally jumps to the _end_ of the entry. We have to modify these - * jumps' destinations to point back to .text rather than the end of the - * entry in .altinstr_replacement. - * - * 4. It has been requested that we don't validate the !POPCNT feature path - * which is a "very very small percentage of machines". - */ -static int handle_group_alt(struct objtool_file *file, - struct special_alt *special_alt, - struct instruction *orig_insn, - struct instruction **new_insn) -{ - struct instruction *last_orig_insn, *last_new_insn, *insn, *fake_jump; - unsigned long dest_off; - - last_orig_insn = NULL; - insn = orig_insn; - sec_for_each_insn_from(file, insn) { - if (insn->offset >= special_alt->orig_off + special_alt->orig_len) - break; - - if (special_alt->skip_orig) - insn->type = INSN_NOP; - - insn->alt_group = true; - last_orig_insn = insn; - } - - if (!next_insn_same_sec(file, last_orig_insn)) { - WARN("%s: don't know how to handle alternatives at end of section", - special_alt->orig_sec->name); - return -1; - } - - fake_jump = malloc(sizeof(*fake_jump)); - if (!fake_jump) { - WARN("malloc failed"); - return -1; - } - memset(fake_jump, 0, sizeof(*fake_jump)); - INIT_LIST_HEAD(&fake_jump->alts); - fake_jump->sec = special_alt->new_sec; - fake_jump->offset = -1; - fake_jump->type = INSN_JUMP_UNCONDITIONAL; - fake_jump->jump_dest = list_next_entry(last_orig_insn, list); - - if (!special_alt->new_len) { - *new_insn = fake_jump; - return 0; - } - - last_new_insn = NULL; - insn = *new_insn; - sec_for_each_insn_from(file, insn) { - if (insn->offset >= special_alt->new_off + special_alt->new_len) - break; - - last_new_insn = insn; - - if (insn->type != INSN_JUMP_CONDITIONAL && - insn->type != INSN_JUMP_UNCONDITIONAL) - continue; - - if (!insn->immediate) - continue; - - dest_off = insn->offset + insn->len + insn->immediate; - if (dest_off == special_alt->new_off + special_alt->new_len) - insn->jump_dest = fake_jump; - - if (!insn->jump_dest) { - WARN_FUNC("can't find alternative jump destination", - insn->sec, insn->offset); - return -1; - } - } - - if (!last_new_insn) { - WARN_FUNC("can't find last new alternative instruction", - special_alt->new_sec, special_alt->new_off); - return -1; - } - - list_add(&fake_jump->list, &last_new_insn->list); - - return 0; -} - -/* - * A jump table entry can either convert a nop to a jump or a jump to a nop. - * If the original instruction is a jump, make the alt entry an effective nop - * by just skipping the original instruction. - */ -static int handle_jump_alt(struct objtool_file *file, - struct special_alt *special_alt, - struct instruction *orig_insn, - struct instruction **new_insn) -{ - if (orig_insn->type == INSN_NOP) - return 0; - - if (orig_insn->type != INSN_JUMP_UNCONDITIONAL) { - WARN_FUNC("unsupported instruction at jump label", - orig_insn->sec, orig_insn->offset); - return -1; - } - - *new_insn = list_next_entry(orig_insn, list); - return 0; -} - -/* - * Read all the special sections which have alternate instructions which can be - * patched in or redirected to at runtime. Each instruction having alternate - * instruction(s) has them added to its insn->alts list, which will be - * traversed in validate_branch(). - */ -static int add_special_section_alts(struct objtool_file *file) -{ - struct list_head special_alts; - struct instruction *orig_insn, *new_insn; - struct special_alt *special_alt, *tmp; - struct alternative *alt; - int ret; - - ret = special_get_alts(file->elf, &special_alts); - if (ret) - return ret; - - list_for_each_entry_safe(special_alt, tmp, &special_alts, list) { - alt = malloc(sizeof(*alt)); - if (!alt) { - WARN("malloc failed"); - ret = -1; - goto out; - } - - orig_insn = find_insn(file, special_alt->orig_sec, - special_alt->orig_off); - if (!orig_insn) { - WARN_FUNC("special: can't find orig instruction", - special_alt->orig_sec, special_alt->orig_off); - ret = -1; - goto out; - } +#include "check.h" - new_insn = NULL; - if (!special_alt->group || special_alt->new_len) { - new_insn = find_insn(file, special_alt->new_sec, - special_alt->new_off); - if (!new_insn) { - WARN_FUNC("special: can't find new instruction", - special_alt->new_sec, - special_alt->new_off); - ret = -1; - goto out; - } - } +bool nofp; - if (special_alt->group) { - ret = handle_group_alt(file, special_alt, orig_insn, - &new_insn); - if (ret) - goto out; - } else if (special_alt->jump_or_nop) { - ret = handle_jump_alt(file, special_alt, orig_insn, - &new_insn); - if (ret) - goto out; - } - - alt->insn = new_insn; - list_add_tail(&alt->list, &orig_insn->alts); - - list_del(&special_alt->list); - free(special_alt); - } - -out: - return ret; -} - -static int add_switch_table(struct objtool_file *file, struct symbol *func, - struct instruction *insn, struct rela *table, - struct rela *next_table) -{ - struct rela *rela = table; - struct instruction *alt_insn; - struct alternative *alt; - - list_for_each_entry_from(rela, &file->rodata->rela->rela_list, list) { - if (rela == next_table) - break; - - if (rela->sym->sec != insn->sec || - rela->addend <= func->offset || - rela->addend >= func->offset + func->len) - break; - - alt_insn = find_insn(file, insn->sec, rela->addend); - if (!alt_insn) { - WARN("%s: can't find instruction at %s+0x%x", - file->rodata->rela->name, insn->sec->name, - rela->addend); - return -1; - } - - alt = malloc(sizeof(*alt)); - if (!alt) { - WARN("malloc failed"); - return -1; - } - - alt->insn = alt_insn; - list_add_tail(&alt->list, &insn->alts); - } - - return 0; -} - -/* - * find_switch_table() - Given a dynamic jump, find the switch jump table in - * .rodata associated with it. - * - * There are 3 basic patterns: - * - * 1. jmpq *[rodata addr](,%reg,8) - * - * This is the most common case by far. It jumps to an address in a simple - * jump table which is stored in .rodata. - * - * 2. jmpq *[rodata addr](%rip) - * - * This is caused by a rare GCC quirk, currently only seen in three driver - * functions in the kernel, only with certain obscure non-distro configs. - * - * As part of an optimization, GCC makes a copy of an existing switch jump - * table, modifies it, and then hard-codes the jump (albeit with an indirect - * jump) to use a single entry in the table. The rest of the jump table and - * some of its jump targets remain as dead code. - * - * In such a case we can just crudely ignore all unreachable instruction - * warnings for the entire object file. Ideally we would just ignore them - * for the function, but that would require redesigning the code quite a - * bit. And honestly that's just not worth doing: unreachable instruction - * warnings are of questionable value anyway, and this is such a rare issue. - * - * 3. mov [rodata addr],%reg1 - * ... some instructions ... - * jmpq *(%reg1,%reg2,8) - * - * This is a fairly uncommon pattern which is new for GCC 6. As of this - * writing, there are 11 occurrences of it in the allmodconfig kernel. - * - * TODO: Once we have DWARF CFI and smarter instruction decoding logic, - * ensure the same register is used in the mov and jump instructions. - */ -static struct rela *find_switch_table(struct objtool_file *file, - struct symbol *func, - struct instruction *insn) -{ - struct rela *text_rela, *rodata_rela; - struct instruction *orig_insn = insn; - - text_rela = find_rela_by_dest_range(insn->sec, insn->offset, insn->len); - if (text_rela && text_rela->sym == file->rodata->sym) { - /* case 1 */ - rodata_rela = find_rela_by_dest(file->rodata, - text_rela->addend); - if (rodata_rela) - return rodata_rela; - - /* case 2 */ - rodata_rela = find_rela_by_dest(file->rodata, - text_rela->addend + 4); - if (!rodata_rela) - return NULL; - file->ignore_unreachables = true; - return rodata_rela; - } - - /* case 3 */ - func_for_each_insn_continue_reverse(file, func, insn) { - if (insn->type == INSN_JUMP_DYNAMIC) - break; - - /* allow small jumps within the range */ - if (insn->type == INSN_JUMP_UNCONDITIONAL && - insn->jump_dest && - (insn->jump_dest->offset <= insn->offset || - insn->jump_dest->offset > orig_insn->offset)) - break; - - /* look for a relocation which references .rodata */ - text_rela = find_rela_by_dest_range(insn->sec, insn->offset, - insn->len); - if (!text_rela || text_rela->sym != file->rodata->sym) - continue; - - /* - * Make sure the .rodata address isn't associated with a - * symbol. gcc jump tables are anonymous data. - */ - if (find_symbol_containing(file->rodata, text_rela->addend)) - continue; - - return find_rela_by_dest(file->rodata, text_rela->addend); - } - - return NULL; -} - -static int add_func_switch_tables(struct objtool_file *file, - struct symbol *func) -{ - struct instruction *insn, *prev_jump = NULL; - struct rela *rela, *prev_rela = NULL; - int ret; - - func_for_each_insn(file, func, insn) { - if (insn->type != INSN_JUMP_DYNAMIC) - continue; - - rela = find_switch_table(file, func, insn); - if (!rela) - continue; - - /* - * We found a switch table, but we don't know yet how big it - * is. Don't add it until we reach the end of the function or - * the beginning of another switch table in the same function. - */ - if (prev_jump) { - ret = add_switch_table(file, func, prev_jump, prev_rela, - rela); - if (ret) - return ret; - } - - prev_jump = insn; - prev_rela = rela; - } - - if (prev_jump) { - ret = add_switch_table(file, func, prev_jump, prev_rela, NULL); - if (ret) - return ret; - } - - return 0; -} - -/* - * For some switch statements, gcc generates a jump table in the .rodata - * section which contains a list of addresses within the function to jump to. - * This finds these jump tables and adds them to the insn->alts lists. - */ -static int add_switch_table_alts(struct objtool_file *file) -{ - struct section *sec; - struct symbol *func; - int ret; - - if (!file->rodata || !file->rodata->rela) - return 0; - - list_for_each_entry(sec, &file->elf->sections, list) { - list_for_each_entry(func, &sec->symbol_list, list) { - if (func->type != STT_FUNC) - continue; - - ret = add_func_switch_tables(file, func); - if (ret) - return ret; - } - } - - return 0; -} - -static int decode_sections(struct objtool_file *file) -{ - int ret; - - ret = decode_instructions(file); - if (ret) - return ret; - - ret = add_dead_ends(file); - if (ret) - return ret; - - add_ignores(file); - - ret = add_jump_destinations(file); - if (ret) - return ret; - - ret = add_call_destinations(file); - if (ret) - return ret; - - ret = add_special_section_alts(file); - if (ret) - return ret; - - ret = add_switch_table_alts(file); - if (ret) - return ret; - - return 0; -} - -static bool is_fentry_call(struct instruction *insn) -{ - if (insn->type == INSN_CALL && - insn->call_dest->type == STT_NOTYPE && - !strcmp(insn->call_dest->name, "__fentry__")) - return true; - - return false; -} - -static bool has_modified_stack_frame(struct instruction *insn) -{ - return (insn->state & STATE_FP_SAVED) || - (insn->state & STATE_FP_SETUP); -} - -static bool has_valid_stack_frame(struct instruction *insn) -{ - return (insn->state & STATE_FP_SAVED) && - (insn->state & STATE_FP_SETUP); -} - -static unsigned int frame_state(unsigned long state) -{ - return (state & (STATE_FP_SAVED | STATE_FP_SETUP)); -} - -/* - * Follow the branch starting at the given instruction, and recursively follow - * any other branches (jumps). Meanwhile, track the frame pointer state at - * each instruction and validate all the rules described in - * tools/objtool/Documentation/stack-validation.txt. - */ -static int validate_branch(struct objtool_file *file, - struct instruction *first, unsigned char first_state) -{ - struct alternative *alt; - struct instruction *insn; - struct section *sec; - struct symbol *func = NULL; - unsigned char state; - int ret; - - insn = first; - sec = insn->sec; - state = first_state; - - if (insn->alt_group && list_empty(&insn->alts)) { - WARN_FUNC("don't know how to handle branch to middle of alternative instruction group", - sec, insn->offset); - return 1; - } - - while (1) { - if (file->c_file && insn->func) { - if (func && func != insn->func) { - WARN("%s() falls through to next function %s()", - func->name, insn->func->name); - return 1; - } - - func = insn->func; - } - - if (insn->visited) { - if (frame_state(insn->state) != frame_state(state)) { - WARN_FUNC("frame pointer state mismatch", - sec, insn->offset); - return 1; - } - - return 0; - } - - insn->visited = true; - insn->state = state; - - list_for_each_entry(alt, &insn->alts, list) { - ret = validate_branch(file, alt->insn, state); - if (ret) - return 1; - } - - switch (insn->type) { - - case INSN_FP_SAVE: - if (!nofp) { - if (state & STATE_FP_SAVED) { - WARN_FUNC("duplicate frame pointer save", - sec, insn->offset); - return 1; - } - state |= STATE_FP_SAVED; - } - break; - - case INSN_FP_SETUP: - if (!nofp) { - if (state & STATE_FP_SETUP) { - WARN_FUNC("duplicate frame pointer setup", - sec, insn->offset); - return 1; - } - state |= STATE_FP_SETUP; - } - break; - - case INSN_FP_RESTORE: - if (!nofp) { - if (has_valid_stack_frame(insn)) - state &= ~STATE_FP_SETUP; - - state &= ~STATE_FP_SAVED; - } - break; - - case INSN_RETURN: - if (!nofp && has_modified_stack_frame(insn)) { - WARN_FUNC("return without frame pointer restore", - sec, insn->offset); - return 1; - } - return 0; - - case INSN_CALL: - if (is_fentry_call(insn)) { - state |= STATE_FENTRY; - break; - } - - ret = dead_end_function(file, insn->call_dest); - if (ret == 1) - return 0; - if (ret == -1) - return 1; - - /* fallthrough */ - case INSN_CALL_DYNAMIC: - if (!nofp && !has_valid_stack_frame(insn)) { - WARN_FUNC("call without frame pointer save/setup", - sec, insn->offset); - return 1; - } - break; - - case INSN_JUMP_CONDITIONAL: - case INSN_JUMP_UNCONDITIONAL: - if (insn->jump_dest) { - ret = validate_branch(file, insn->jump_dest, - state); - if (ret) - return 1; - } else if (has_modified_stack_frame(insn)) { - WARN_FUNC("sibling call from callable instruction with changed frame pointer", - sec, insn->offset); - return 1; - } /* else it's a sibling call */ - - if (insn->type == INSN_JUMP_UNCONDITIONAL) - return 0; - - break; - - case INSN_JUMP_DYNAMIC: - if (list_empty(&insn->alts) && - has_modified_stack_frame(insn)) { - WARN_FUNC("sibling call from callable instruction with changed frame pointer", - sec, insn->offset); - return 1; - } - - return 0; - - default: - break; - } - - if (insn->dead_end) - return 0; - - insn = next_insn_same_sec(file, insn); - if (!insn) { - WARN("%s: unexpected end of section", sec->name); - return 1; - } - } - - return 0; -} - -static bool is_kasan_insn(struct instruction *insn) -{ - return (insn->type == INSN_CALL && - !strcmp(insn->call_dest->name, "__asan_handle_no_return")); -} - -static bool is_ubsan_insn(struct instruction *insn) -{ - return (insn->type == INSN_CALL && - !strcmp(insn->call_dest->name, - "__ubsan_handle_builtin_unreachable")); -} - -static bool ignore_unreachable_insn(struct symbol *func, - struct instruction *insn) -{ - int i; - - if (insn->type == INSN_NOP) - return true; - - /* - * Check if this (or a subsequent) instruction is related to - * CONFIG_UBSAN or CONFIG_KASAN. - * - * End the search at 5 instructions to avoid going into the weeds. - */ - for (i = 0; i < 5; i++) { - - if (is_kasan_insn(insn) || is_ubsan_insn(insn)) - return true; - - if (insn->type == INSN_JUMP_UNCONDITIONAL && insn->jump_dest) { - insn = insn->jump_dest; - continue; - } - - if (insn->offset + insn->len >= func->offset + func->len) - break; - insn = list_next_entry(insn, list); - } - - return false; -} - -static int validate_functions(struct objtool_file *file) -{ - struct section *sec; - struct symbol *func; - struct instruction *insn; - int ret, warnings = 0; - - list_for_each_entry(sec, &file->elf->sections, list) { - list_for_each_entry(func, &sec->symbol_list, list) { - if (func->type != STT_FUNC) - continue; - - insn = find_insn(file, sec, func->offset); - if (!insn) - continue; - - ret = validate_branch(file, insn, 0); - warnings += ret; - } - } - - list_for_each_entry(sec, &file->elf->sections, list) { - list_for_each_entry(func, &sec->symbol_list, list) { - if (func->type != STT_FUNC) - continue; - - func_for_each_insn(file, func, insn) { - if (insn->visited) - continue; - - insn->visited = true; - - if (file->ignore_unreachables || warnings || - ignore_unreachable_insn(func, insn)) - continue; - - /* - * gcov produces a lot of unreachable - * instructions. If we get an unreachable - * warning and the file has gcov enabled, just - * ignore it, and all other such warnings for - * the file. - */ - if (!file->ignore_unreachables && - gcov_enabled(file)) { - file->ignore_unreachables = true; - continue; - } - - WARN_FUNC("function has unreachable instruction", insn->sec, insn->offset); - warnings++; - } - } - } - - return warnings; -} - -static int validate_uncallable_instructions(struct objtool_file *file) -{ - struct instruction *insn; - int warnings = 0; - - for_each_insn(file, insn) { - if (!insn->visited && insn->type == INSN_RETURN) { - WARN_FUNC("return instruction outside of a callable function", - insn->sec, insn->offset); - warnings++; - } - } - - return warnings; -} - -static void cleanup(struct objtool_file *file) -{ - struct instruction *insn, *tmpinsn; - struct alternative *alt, *tmpalt; - - list_for_each_entry_safe(insn, tmpinsn, &file->insn_list, list) { - list_for_each_entry_safe(alt, tmpalt, &insn->alts, list) { - list_del(&alt->list); - free(alt); - } - list_del(&insn->list); - hash_del(&insn->hash); - free(insn); - } - elf_close(file->elf); -} - -const char * const check_usage[] = { +static const char * const check_usage[] = { "objtool check [<options>] file.o", NULL, }; +const struct option check_options[] = { + OPT_BOOLEAN('f', "no-fp", &nofp, "Skip frame pointer validation"), + OPT_END(), +}; + int cmd_check(int argc, const char **argv) { - struct objtool_file file; - int ret, warnings = 0; - - const struct option options[] = { - OPT_BOOLEAN('f', "no-fp", &nofp, "Skip frame pointer validation"), - OPT_END(), - }; + const char *objname; - argc = parse_options(argc, argv, options, check_usage, 0); + argc = parse_options(argc, argv, check_options, check_usage, 0); if (argc != 1) - usage_with_options(check_usage, options); + usage_with_options(check_usage, check_options); objname = argv[0]; - file.elf = elf_open(objname); - if (!file.elf) { - fprintf(stderr, "error reading elf file %s\n", objname); - return 1; - } - - INIT_LIST_HEAD(&file.insn_list); - hash_init(file.insn_hash); - file.whitelist = find_section_by_name(file.elf, ".discard.func_stack_frame_non_standard"); - file.rodata = find_section_by_name(file.elf, ".rodata"); - file.ignore_unreachables = false; - file.c_file = find_section_by_name(file.elf, ".comment"); - - ret = decode_sections(&file); - if (ret < 0) - goto out; - warnings += ret; - - ret = validate_functions(&file); - if (ret < 0) - goto out; - warnings += ret; - - ret = validate_uncallable_instructions(&file); - if (ret < 0) - goto out; - warnings += ret; - -out: - cleanup(&file); - - /* ignore warnings for now until we get all the code cleaned up */ - if (ret || warnings) - return 0; - return 0; + return check(objname, nofp); } diff --git a/tools/objtool/cfi.h b/tools/objtool/cfi.h new file mode 100644 index 000000000000..443ab2c69992 --- /dev/null +++ b/tools/objtool/cfi.h @@ -0,0 +1,55 @@ +/* + * Copyright (C) 2015-2017 Josh Poimboeuf <jpoimboe@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, see <http://www.gnu.org/licenses/>. + */ + +#ifndef _OBJTOOL_CFI_H +#define _OBJTOOL_CFI_H + +#define CFI_UNDEFINED -1 +#define CFI_CFA -2 +#define CFI_SP_INDIRECT -3 +#define CFI_BP_INDIRECT -4 + +#define CFI_AX 0 +#define CFI_DX 1 +#define CFI_CX 2 +#define CFI_BX 3 +#define CFI_SI 4 +#define CFI_DI 5 +#define CFI_BP 6 +#define CFI_SP 7 +#define CFI_R8 8 +#define CFI_R9 9 +#define CFI_R10 10 +#define CFI_R11 11 +#define CFI_R12 12 +#define CFI_R13 13 +#define CFI_R14 14 +#define CFI_R15 15 +#define CFI_RA 16 +#define CFI_NUM_REGS 17 + +struct cfi_reg { + int base; + int offset; +}; + +struct cfi_state { + struct cfi_reg cfa; + struct cfi_reg regs[CFI_NUM_REGS]; +}; + +#endif /* _OBJTOOL_CFI_H */ diff --git a/tools/objtool/check.c b/tools/objtool/check.c new file mode 100644 index 000000000000..fea222192c57 --- /dev/null +++ b/tools/objtool/check.c @@ -0,0 +1,1655 @@ +/* + * Copyright (C) 2015-2017 Josh Poimboeuf <jpoimboe@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, see <http://www.gnu.org/licenses/>. + */ + +#include <string.h> +#include <stdlib.h> + +#include "check.h" +#include "elf.h" +#include "special.h" +#include "arch.h" +#include "warn.h" + +#include <linux/hashtable.h> +#include <linux/kernel.h> + +struct alternative { + struct list_head list; + struct instruction *insn; +}; + +const char *objname; +static bool nofp; +struct cfi_state initial_func_cfi; + +static struct instruction *find_insn(struct objtool_file *file, + struct section *sec, unsigned long offset) +{ + struct instruction *insn; + + hash_for_each_possible(file->insn_hash, insn, hash, offset) + if (insn->sec == sec && insn->offset == offset) + return insn; + + return NULL; +} + +static struct instruction *next_insn_same_sec(struct objtool_file *file, + struct instruction *insn) +{ + struct instruction *next = list_next_entry(insn, list); + + if (!next || &next->list == &file->insn_list || next->sec != insn->sec) + return NULL; + + return next; +} + +static bool gcov_enabled(struct objtool_file *file) +{ + struct section *sec; + struct symbol *sym; + + for_each_sec(file, sec) + list_for_each_entry(sym, &sec->symbol_list, list) + if (!strncmp(sym->name, "__gcov_.", 8)) + return true; + + return false; +} + +#define func_for_each_insn(file, func, insn) \ + for (insn = find_insn(file, func->sec, func->offset); \ + insn && &insn->list != &file->insn_list && \ + insn->sec == func->sec && \ + insn->offset < func->offset + func->len; \ + insn = list_next_entry(insn, list)) + +#define func_for_each_insn_continue_reverse(file, func, insn) \ + for (insn = list_prev_entry(insn, list); \ + &insn->list != &file->insn_list && \ + insn->sec == func->sec && insn->offset >= func->offset; \ + insn = list_prev_entry(insn, list)) + +#define sec_for_each_insn_from(file, insn) \ + for (; insn; insn = next_insn_same_sec(file, insn)) + +#define sec_for_each_insn_continue(file, insn) \ + for (insn = next_insn_same_sec(file, insn); insn; \ + insn = next_insn_same_sec(file, insn)) + +/* + * Check if the function has been manually whitelisted with the + * STACK_FRAME_NON_STANDARD macro, or if it should be automatically whitelisted + * due to its use of a context switching instruction. + */ +static bool ignore_func(struct objtool_file *file, struct symbol *func) +{ + struct rela *rela; + struct instruction *insn; + + /* check for STACK_FRAME_NON_STANDARD */ + if (file->whitelist && file->whitelist->rela) + list_for_each_entry(rela, &file->whitelist->rela->rela_list, list) { + if (rela->sym->type == STT_SECTION && + rela->sym->sec == func->sec && + rela->addend == func->offset) + return true; + if (rela->sym->type == STT_FUNC && rela->sym == func) + return true; + } + + /* check if it has a context switching instruction */ + func_for_each_insn(file, func, insn) + if (insn->type == INSN_CONTEXT_SWITCH) + return true; + + return false; +} + +/* + * This checks to see if the given function is a "noreturn" function. + * + * For global functions which are outside the scope of this object file, we + * have to keep a manual list of them. + * + * For local functions, we have to detect them manually by simply looking for + * the lack of a return instruction. + * + * Returns: + * -1: error + * 0: no dead end + * 1: dead end + */ +static int __dead_end_function(struct objtool_file *file, struct symbol *func, + int recursion) +{ + int i; + struct instruction *insn; + bool empty = true; + + /* + * Unfortunately these have to be hard coded because the noreturn + * attribute isn't provided in ELF data. + */ + static const char * const global_noreturns[] = { + "__stack_chk_fail", + "panic", + "do_exit", + "do_task_dead", + "__module_put_and_exit", + "complete_and_exit", + "kvm_spurious_fault", + "__reiserfs_panic", + "lbug_with_loc", + "fortify_panic", + }; + + if (func->bind == STB_WEAK) + return 0; + + if (func->bind == STB_GLOBAL) + for (i = 0; i < ARRAY_SIZE(global_noreturns); i++) + if (!strcmp(func->name, global_noreturns[i])) + return 1; + + if (!func->sec) + return 0; + + func_for_each_insn(file, func, insn) { + empty = false; + + if (insn->type == INSN_RETURN) + return 0; + } + + if (empty) + return 0; + + /* + * A function can have a sibling call instead of a return. In that + * case, the function's dead-end status depends on whether the target + * of the sibling call returns. + */ + func_for_each_insn(file, func, insn) { + if (insn->sec != func->sec || + insn->offset >= func->offset + func->len) + break; + + if (insn->type == INSN_JUMP_UNCONDITIONAL) { + struct instruction *dest = insn->jump_dest; + struct symbol *dest_func; + + if (!dest) + /* sibling call to another file */ + return 0; + + if (dest->sec != func->sec || + dest->offset < func->offset || + dest->offset >= func->offset + func->len) { + /* local sibling call */ + dest_func = find_symbol_by_offset(dest->sec, + dest->offset); + if (!dest_func) + continue; + + if (recursion == 5) { + WARN_FUNC("infinite recursion (objtool bug!)", + dest->sec, dest->offset); + return -1; + } + + return __dead_end_function(file, dest_func, + recursion + 1); + } + } + + if (insn->type == INSN_JUMP_DYNAMIC && list_empty(&insn->alts)) + /* sibling call */ + return 0; + } + + return 1; +} + +static int dead_end_function(struct objtool_file *file, struct symbol *func) +{ + return __dead_end_function(file, func, 0); +} + +static void clear_insn_state(struct insn_state *state) +{ + int i; + + memset(state, 0, sizeof(*state)); + state->cfa.base = CFI_UNDEFINED; + for (i = 0; i < CFI_NUM_REGS; i++) + state->regs[i].base = CFI_UNDEFINED; + state->drap_reg = CFI_UNDEFINED; +} + +/* + * Call the arch-specific instruction decoder for all the instructions and add + * them to the global instruction list. + */ +static int decode_instructions(struct objtool_file *file) +{ + struct section *sec; + struct symbol *func; + unsigned long offset; + struct instruction *insn; + int ret; + + for_each_sec(file, sec) { + + if (!(sec->sh.sh_flags & SHF_EXECINSTR)) + continue; + + for (offset = 0; offset < sec->len; offset += insn->len) { + insn = malloc(sizeof(*insn)); + if (!insn) { + WARN("malloc failed"); + return -1; + } + memset(insn, 0, sizeof(*insn)); + INIT_LIST_HEAD(&insn->alts); + clear_insn_state(&insn->state); + + insn->sec = sec; + insn->offset = offset; + + ret = arch_decode_instruction(file->elf, sec, offset, + sec->len - offset, + &insn->len, &insn->type, + &insn->immediate, + &insn->stack_op); + if (ret) + return ret; + + if (!insn->type || insn->type > INSN_LAST) { + WARN_FUNC("invalid instruction type %d", + insn->sec, insn->offset, insn->type); + return -1; + } + + hash_add(file->insn_hash, &insn->hash, insn->offset); + list_add_tail(&insn->list, &file->insn_list); + } + + list_for_each_entry(func, &sec->symbol_list, list) { + if (func->type != STT_FUNC) + continue; + + if (!find_insn(file, sec, func->offset)) { + WARN("%s(): can't find starting instruction", + func->name); + return -1; + } + + func_for_each_insn(file, func, insn) + if (!insn->func) + insn->func = func; + } + } + + return 0; +} + +/* + * Find all uses of the unreachable() macro, which are code path dead ends. + */ +static int add_dead_ends(struct objtool_file *file) +{ + struct section *sec; + struct rela *rela; + struct instruction *insn; + bool found; + + sec = find_section_by_name(file->elf, ".rela.discard.unreachable"); + if (!sec) + return 0; + + list_for_each_entry(rela, &sec->rela_list, list) { + if (rela->sym->type != STT_SECTION) { + WARN("unexpected relocation symbol type in %s", sec->name); + return -1; + } + insn = find_insn(file, rela->sym->sec, rela->addend); + if (insn) + insn = list_prev_entry(insn, list); + else if (rela->addend == rela->sym->sec->len) { + found = false; + list_for_each_entry_reverse(insn, &file->insn_list, list) { + if (insn->sec == rela->sym->sec) { + found = true; + break; + } + } + + if (!found) { + WARN("can't find unreachable insn at %s+0x%x", + rela->sym->sec->name, rela->addend); + return -1; + } + } else { + WARN("can't find unreachable insn at %s+0x%x", + rela->sym->sec->name, rela->addend); + return -1; + } + + insn->dead_end = true; + } + + return 0; +} + +/* + * Warnings shouldn't be reported for ignored functions. + */ +static void add_ignores(struct objtool_file *file) +{ + struct instruction *insn; + struct section *sec; + struct symbol *func; + + for_each_sec(file, sec) { + list_for_each_entry(func, &sec->symbol_list, list) { + if (func->type != STT_FUNC) + continue; + + if (!ignore_func(file, func)) + continue; + + func_for_each_insn(file, func, insn) + insn->ignore = true; + } + } +} + +/* + * Find the destination instructions for all jumps. + */ +static int add_jump_destinations(struct objtool_file *file) +{ + struct instruction *insn; + struct rela *rela; + struct section *dest_sec; + unsigned long dest_off; + + for_each_insn(file, insn) { + if (insn->type != INSN_JUMP_CONDITIONAL && + insn->type != INSN_JUMP_UNCONDITIONAL) + continue; + + if (insn->ignore) + continue; + + rela = find_rela_by_dest_range(insn->sec, insn->offset, + insn->len); + if (!rela) { + dest_sec = insn->sec; + dest_off = insn->offset + insn->len + insn->immediate; + } else if (rela->sym->type == STT_SECTION) { + dest_sec = rela->sym->sec; + dest_off = rela->addend + 4; + } else if (rela->sym->sec->idx) { + dest_sec = rela->sym->sec; + dest_off = rela->sym->sym.st_value + rela->addend + 4; + } else { + /* sibling call */ + insn->jump_dest = 0; + continue; + } + + insn->jump_dest = find_insn(file, dest_sec, dest_off); + if (!insn->jump_dest) { + + /* + * This is a special case where an alt instruction + * jumps past the end of the section. These are + * handled later in handle_group_alt(). + */ + if (!strcmp(insn->sec->name, ".altinstr_replacement")) + continue; + + WARN_FUNC("can't find jump dest instruction at %s+0x%lx", + insn->sec, insn->offset, dest_sec->name, + dest_off); + return -1; + } + } + + return 0; +} + +/* + * Find the destination instructions for all calls. + */ +static int add_call_destinations(struct objtool_file *file) +{ + struct instruction *insn; + unsigned long dest_off; + struct rela *rela; + + for_each_insn(file, insn) { + if (insn->type != INSN_CALL) + continue; + + rela = find_rela_by_dest_range(insn->sec, insn->offset, + insn->len); + if (!rela) { + dest_off = insn->offset + insn->len + insn->immediate; + insn->call_dest = find_symbol_by_offset(insn->sec, + dest_off); + if (!insn->call_dest) { + WARN_FUNC("can't find call dest symbol at offset 0x%lx", + insn->sec, insn->offset, dest_off); + return -1; + } + } else if (rela->sym->type == STT_SECTION) { + insn->call_dest = find_symbol_by_offset(rela->sym->sec, + rela->addend+4); + if (!insn->call_dest || + insn->call_dest->type != STT_FUNC) { + WARN_FUNC("can't find call dest symbol at %s+0x%x", + insn->sec, insn->offset, + rela->sym->sec->name, + rela->addend + 4); + return -1; + } + } else + insn->call_dest = rela->sym; + } + + return 0; +} + +/* + * The .alternatives section requires some extra special care, over and above + * what other special sections require: + * + * 1. Because alternatives are patched in-place, we need to insert a fake jump + * instruction at the end so that validate_branch() skips all the original + * replaced instructions when validating the new instruction path. + * + * 2. An added wrinkle is that the new instruction length might be zero. In + * that case the old instructions are replaced with noops. We simulate that + * by creating a fake jump as the only new instruction. + * + * 3. In some cases, the alternative section includes an instruction which + * conditionally jumps to the _end_ of the entry. We have to modify these + * jumps' destinations to point back to .text rather than the end of the + * entry in .altinstr_replacement. + * + * 4. It has been requested that we don't validate the !POPCNT feature path + * which is a "very very small percentage of machines". + */ +static int handle_group_alt(struct objtool_file *file, + struct special_alt *special_alt, + struct instruction *orig_insn, + struct instruction **new_insn) +{ + struct instruction *last_orig_insn, *last_new_insn, *insn, *fake_jump; + unsigned long dest_off; + + last_orig_insn = NULL; + insn = orig_insn; + sec_for_each_insn_from(file, insn) { + if (insn->offset >= special_alt->orig_off + special_alt->orig_len) + break; + + if (special_alt->skip_orig) + insn->type = INSN_NOP; + + insn->alt_group = true; + last_orig_insn = insn; + } + + if (!next_insn_same_sec(file, last_orig_insn)) { + WARN("%s: don't know how to handle alternatives at end of section", + special_alt->orig_sec->name); + return -1; + } + + fake_jump = malloc(sizeof(*fake_jump)); + if (!fake_jump) { + WARN("malloc failed"); + return -1; + } + memset(fake_jump, 0, sizeof(*fake_jump)); + INIT_LIST_HEAD(&fake_jump->alts); + clear_insn_state(&fake_jump->state); + + fake_jump->sec = special_alt->new_sec; + fake_jump->offset = -1; + fake_jump->type = INSN_JUMP_UNCONDITIONAL; + fake_jump->jump_dest = list_next_entry(last_orig_insn, list); + fake_jump->ignore = true; + + if (!special_alt->new_len) { + *new_insn = fake_jump; + return 0; + } + + last_new_insn = NULL; + insn = *new_insn; + sec_for_each_insn_from(file, insn) { + if (insn->offset >= special_alt->new_off + special_alt->new_len) + break; + + last_new_insn = insn; + + if (insn->type != INSN_JUMP_CONDITIONAL && + insn->type != INSN_JUMP_UNCONDITIONAL) + continue; + + if (!insn->immediate) + continue; + + dest_off = insn->offset + insn->len + insn->immediate; + if (dest_off == special_alt->new_off + special_alt->new_len) + insn->jump_dest = fake_jump; + + if (!insn->jump_dest) { + WARN_FUNC("can't find alternative jump destination", + insn->sec, insn->offset); + return -1; + } + } + + if (!last_new_insn) { + WARN_FUNC("can't find last new alternative instruction", + special_alt->new_sec, special_alt->new_off); + return -1; + } + + list_add(&fake_jump->list, &last_new_insn->list); + + return 0; +} + +/* + * A jump table entry can either convert a nop to a jump or a jump to a nop. + * If the original instruction is a jump, make the alt entry an effective nop + * by just skipping the original instruction. + */ +static int handle_jump_alt(struct objtool_file *file, + struct special_alt *special_alt, + struct instruction *orig_insn, + struct instruction **new_insn) +{ + if (orig_insn->type == INSN_NOP) + return 0; + + if (orig_insn->type != INSN_JUMP_UNCONDITIONAL) { + WARN_FUNC("unsupported instruction at jump label", + orig_insn->sec, orig_insn->offset); + return -1; + } + + *new_insn = list_next_entry(orig_insn, list); + return 0; +} + +/* + * Read all the special sections which have alternate instructions which can be + * patched in or redirected to at runtime. Each instruction having alternate + * instruction(s) has them added to its insn->alts list, which will be + * traversed in validate_branch(). + */ +static int add_special_section_alts(struct objtool_file *file) +{ + struct list_head special_alts; + struct instruction *orig_insn, *new_insn; + struct special_alt *special_alt, *tmp; + struct alternative *alt; + int ret; + + ret = special_get_alts(file->elf, &special_alts); + if (ret) + return ret; + + list_for_each_entry_safe(special_alt, tmp, &special_alts, list) { + alt = malloc(sizeof(*alt)); + if (!alt) { + WARN("malloc failed"); + ret = -1; + goto out; + } + + orig_insn = find_insn(file, special_alt->orig_sec, + special_alt->orig_off); + if (!orig_insn) { + WARN_FUNC("special: can't find orig instruction", + special_alt->orig_sec, special_alt->orig_off); + ret = -1; + goto out; + } + + new_insn = NULL; + if (!special_alt->group || special_alt->new_len) { + new_insn = find_insn(file, special_alt->new_sec, + special_alt->new_off); + if (!new_insn) { + WARN_FUNC("special: can't find new instruction", + special_alt->new_sec, + special_alt->new_off); + ret = -1; + goto out; + } + } + + if (special_alt->group) { + ret = handle_group_alt(file, special_alt, orig_insn, + &new_insn); + if (ret) + goto out; + } else if (special_alt->jump_or_nop) { + ret = handle_jump_alt(file, special_alt, orig_insn, + &new_insn); + if (ret) + goto out; + } + + alt->insn = new_insn; + list_add_tail(&alt->list, &orig_insn->alts); + + list_del(&special_alt->list); + free(special_alt); + } + +out: + return ret; +} + +static int add_switch_table(struct objtool_file *file, struct symbol *func, + struct instruction *insn, struct rela *table, + struct rela *next_table) +{ + struct rela *rela = table; + struct instruction *alt_insn; + struct alternative *alt; + + list_for_each_entry_from(rela, &file->rodata->rela->rela_list, list) { + if (rela == next_table) + break; + + if (rela->sym->sec != insn->sec || + rela->addend <= func->offset || + rela->addend >= func->offset + func->len) + break; + + alt_insn = find_insn(file, insn->sec, rela->addend); + if (!alt_insn) { + WARN("%s: can't find instruction at %s+0x%x", + file->rodata->rela->name, insn->sec->name, + rela->addend); + return -1; + } + + alt = malloc(sizeof(*alt)); + if (!alt) { + WARN("malloc failed"); + return -1; + } + + alt->insn = alt_insn; + list_add_tail(&alt->list, &insn->alts); + } + + return 0; +} + +/* + * find_switch_table() - Given a dynamic jump, find the switch jump table in + * .rodata associated with it. + * + * There are 3 basic patterns: + * + * 1. jmpq *[rodata addr](,%reg,8) + * + * This is the most common case by far. It jumps to an address in a simple + * jump table which is stored in .rodata. + * + * 2. jmpq *[rodata addr](%rip) + * + * This is caused by a rare GCC quirk, currently only seen in three driver + * functions in the kernel, only with certain obscure non-distro configs. + * + * As part of an optimization, GCC makes a copy of an existing switch jump + * table, modifies it, and then hard-codes the jump (albeit with an indirect + * jump) to use a single entry in the table. The rest of the jump table and + * some of its jump targets remain as dead code. + * + * In such a case we can just crudely ignore all unreachable instruction + * warnings for the entire object file. Ideally we would just ignore them + * for the function, but that would require redesigning the code quite a + * bit. And honestly that's just not worth doing: unreachable instruction + * warnings are of questionable value anyway, and this is such a rare issue. + * + * 3. mov [rodata addr],%reg1 + * ... some instructions ... + * jmpq *(%reg1,%reg2,8) + * + * This is a fairly uncommon pattern which is new for GCC 6. As of this + * writing, there are 11 occurrences of it in the allmodconfig kernel. + * + * TODO: Once we have DWARF CFI and smarter instruction decoding logic, + * ensure the same register is used in the mov and jump instructions. + */ +static struct rela *find_switch_table(struct objtool_file *file, + struct symbol *func, + struct instruction *insn) +{ + struct rela *text_rela, *rodata_rela; + struct instruction *orig_insn = insn; + + text_rela = find_rela_by_dest_range(insn->sec, insn->offset, insn->len); + if (text_rela && text_rela->sym == file->rodata->sym) { + /* case 1 */ + rodata_rela = find_rela_by_dest(file->rodata, + text_rela->addend); + if (rodata_rela) + return rodata_rela; + + /* case 2 */ + rodata_rela = find_rela_by_dest(file->rodata, + text_rela->addend + 4); + if (!rodata_rela) + return NULL; + file->ignore_unreachables = true; + return rodata_rela; + } + + /* case 3 */ + func_for_each_insn_continue_reverse(file, func, insn) { + if (insn->type == INSN_JUMP_DYNAMIC) + break; + + /* allow small jumps within the range */ + if (insn->type == INSN_JUMP_UNCONDITIONAL && + insn->jump_dest && + (insn->jump_dest->offset <= insn->offset || + insn->jump_dest->offset > orig_insn->offset)) + break; + + /* look for a relocation which references .rodata */ + text_rela = find_rela_by_dest_range(insn->sec, insn->offset, + insn->len); + if (!text_rela || text_rela->sym != file->rodata->sym) + continue; + + /* + * Make sure the .rodata address isn't associated with a + * symbol. gcc jump tables are anonymous data. + */ + if (find_symbol_containing(file->rodata, text_rela->addend)) + continue; + + return find_rela_by_dest(file->rodata, text_rela->addend); + } + + return NULL; +} + +static int add_func_switch_tables(struct objtool_file *file, + struct symbol *func) +{ + struct instruction *insn, *prev_jump = NULL; + struct rela *rela, *prev_rela = NULL; + int ret; + + func_for_each_insn(file, func, insn) { + if (insn->type != INSN_JUMP_DYNAMIC) + continue; + + rela = find_switch_table(file, func, insn); + if (!rela) + continue; + + /* + * We found a switch table, but we don't know yet how big it + * is. Don't add it until we reach the end of the function or + * the beginning of another switch table in the same function. + */ + if (prev_jump) { + ret = add_switch_table(file, func, prev_jump, prev_rela, + rela); + if (ret) + return ret; + } + + prev_jump = insn; + prev_rela = rela; + } + + if (prev_jump) { + ret = add_switch_table(file, func, prev_jump, prev_rela, NULL); + if (ret) + return ret; + } + + return 0; +} + +/* + * For some switch statements, gcc generates a jump table in the .rodata + * section which contains a list of addresses within the function to jump to. + * This finds these jump tables and adds them to the insn->alts lists. + */ +static int add_switch_table_alts(struct objtool_file *file) +{ + struct section *sec; + struct symbol *func; + int ret; + + if (!file->rodata || !file->rodata->rela) + return 0; + + for_each_sec(file, sec) { + list_for_each_entry(func, &sec->symbol_list, list) { + if (func->type != STT_FUNC) + continue; + + ret = add_func_switch_tables(file, func); + if (ret) + return ret; + } + } + + return 0; +} + +static int decode_sections(struct objtool_file *file) +{ + int ret; + + ret = decode_instructions(file); + if (ret) + return ret; + + ret = add_dead_ends(file); + if (ret) + return ret; + + add_ignores(file); + + ret = add_jump_destinations(file); + if (ret) + return ret; + + ret = add_call_destinations(file); + if (ret) + return ret; + + ret = add_special_section_alts(file); + if (ret) + return ret; + + ret = add_switch_table_alts(file); + if (ret) + return ret; + + return 0; +} + +static bool is_fentry_call(struct instruction *insn) +{ + if (insn->type == INSN_CALL && + insn->call_dest->type == STT_NOTYPE && + !strcmp(insn->call_dest->name, "__fentry__")) + return true; + + return false; +} + +static bool has_modified_stack_frame(struct insn_state *state) +{ + int i; + + if (state->cfa.base != initial_func_cfi.cfa.base || + state->cfa.offset != initial_func_cfi.cfa.offset || + state->stack_size != initial_func_cfi.cfa.offset || + state->drap) + return true; + + for (i = 0; i < CFI_NUM_REGS; i++) + if (state->regs[i].base != initial_func_cfi.regs[i].base || + state->regs[i].offset != initial_func_cfi.regs[i].offset) + return true; + + return false; +} + +static bool has_valid_stack_frame(struct insn_state *state) +{ + if (state->cfa.base == CFI_BP && state->regs[CFI_BP].base == CFI_CFA && + state->regs[CFI_BP].offset == -16) + return true; + + if (state->drap && state->regs[CFI_BP].base == CFI_BP) + return true; + + return false; +} + +static void save_reg(struct insn_state *state, unsigned char reg, int base, + int offset) +{ + if ((arch_callee_saved_reg(reg) || + (state->drap && reg == state->drap_reg)) && + state->regs[reg].base == CFI_UNDEFINED) { + state->regs[reg].base = base; + state->regs[reg].offset = offset; + } +} + +static void restore_reg(struct insn_state *state, unsigned char reg) +{ + state->regs[reg].base = CFI_UNDEFINED; + state->regs[reg].offset = 0; +} + +/* + * A note about DRAP stack alignment: + * + * GCC has the concept of a DRAP register, which is used to help keep track of + * the stack pointer when aligning the stack. r10 or r13 is used as the DRAP + * register. The typical DRAP pattern is: + * + * 4c 8d 54 24 08 lea 0x8(%rsp),%r10 + * 48 83 e4 c0 and $0xffffffffffffffc0,%rsp + * 41 ff 72 f8 pushq -0x8(%r10) + * 55 push %rbp + * 48 89 e5 mov %rsp,%rbp + * (more pushes) + * 41 52 push %r10 + * ... + * 41 5a pop %r10 + * (more pops) + * 5d pop %rbp + * 49 8d 62 f8 lea -0x8(%r10),%rsp + * c3 retq + * + * There are some variations in the epilogues, like: + * + * 5b pop %rbx + * 41 5a pop %r10 + * 41 5c pop %r12 + * 41 5d pop %r13 + * 41 5e pop %r14 + * c9 leaveq + * 49 8d 62 f8 lea -0x8(%r10),%rsp + * c3 retq + * + * and: + * + * 4c 8b 55 e8 mov -0x18(%rbp),%r10 + * 48 8b 5d e0 mov -0x20(%rbp),%rbx + * 4c 8b 65 f0 mov -0x10(%rbp),%r12 + * 4c 8b 6d f8 mov -0x8(%rbp),%r13 + * c9 leaveq + * 49 8d 62 f8 lea -0x8(%r10),%rsp + * c3 retq + * + * Sometimes r13 is used as the DRAP register, in which case it's saved and + * restored beforehand: + * + * 41 55 push %r13 + * 4c 8d 6c 24 10 lea 0x10(%rsp),%r13 + * 48 83 e4 f0 and $0xfffffffffffffff0,%rsp + * ... + * 49 8d 65 f0 lea -0x10(%r13),%rsp + * 41 5d pop %r13 + * c3 retq + */ +static int update_insn_state(struct instruction *insn, struct insn_state *state) +{ + struct stack_op *op = &insn->stack_op; + struct cfi_reg *cfa = &state->cfa; + struct cfi_reg *regs = state->regs; + + /* stack operations don't make sense with an undefined CFA */ + if (cfa->base == CFI_UNDEFINED) { + if (insn->func) { + WARN_FUNC("undefined stack state", insn->sec, insn->offset); + return -1; + } + return 0; + } + + switch (op->dest.type) { + + case OP_DEST_REG: + switch (op->src.type) { + + case OP_SRC_REG: + if (cfa->base == op->src.reg && cfa->base == CFI_SP && + op->dest.reg == CFI_BP && regs[CFI_BP].base == CFI_CFA && + regs[CFI_BP].offset == -cfa->offset) { + + /* mov %rsp, %rbp */ + cfa->base = op->dest.reg; + state->bp_scratch = false; + } else if (state->drap) { + + /* drap: mov %rsp, %rbp */ + regs[CFI_BP].base = CFI_BP; + regs[CFI_BP].offset = -state->stack_size; + state->bp_scratch = false; + } else if (!nofp) { + + WARN_FUNC("unknown stack-related register move", + insn->sec, insn->offset); + return -1; + } + + break; + + case OP_SRC_ADD: + if (op->dest.reg == CFI_SP && op->src.reg == CFI_SP) { + + /* add imm, %rsp */ + state->stack_size -= op->src.offset; + if (cfa->base == CFI_SP) + cfa->offset -= op->src.offset; + break; + } + + if (op->dest.reg == CFI_SP && op->src.reg == CFI_BP) { + + /* lea disp(%rbp), %rsp */ + state->stack_size = -(op->src.offset + regs[CFI_BP].offset); + break; + } + + if (op->dest.reg != CFI_BP && op->src.reg == CFI_SP && + cfa->base == CFI_SP) { + + /* drap: lea disp(%rsp), %drap */ + state->drap_reg = op->dest.reg; + break; + } + + if (state->drap && op->dest.reg == CFI_SP && + op->src.reg == state->drap_reg) { + + /* drap: lea disp(%drap), %rsp */ + cfa->base = CFI_SP; + cfa->offset = state->stack_size = -op->src.offset; + state->drap_reg = CFI_UNDEFINED; + state->drap = false; + break; + } + + if (op->dest.reg == state->cfa.base) { + WARN_FUNC("unsupported stack register modification", + insn->sec, insn->offset); + return -1; + } + + break; + + case OP_SRC_AND: + if (op->dest.reg != CFI_SP || + (state->drap_reg != CFI_UNDEFINED && cfa->base != CFI_SP) || + (state->drap_reg == CFI_UNDEFINED && cfa->base != CFI_BP)) { + WARN_FUNC("unsupported stack pointer realignment", + insn->sec, insn->offset); + return -1; + } + + if (state->drap_reg != CFI_UNDEFINED) { + /* drap: and imm, %rsp */ + cfa->base = state->drap_reg; + cfa->offset = state->stack_size = 0; + state->drap = true; + + } + + /* + * Older versions of GCC (4.8ish) realign the stack + * without DRAP, with a frame pointer. + */ + + break; + + case OP_SRC_POP: + if (!state->drap && op->dest.type == OP_DEST_REG && + op->dest.reg == cfa->base) { + + /* pop %rbp */ + cfa->base = CFI_SP; + } + + if (regs[op->dest.reg].offset == -state->stack_size) { + + if (state->drap && cfa->base == CFI_BP_INDIRECT && + op->dest.type == OP_DEST_REG && + op->dest.reg == state->drap_reg) { + + /* drap: pop %drap */ + cfa->base = state->drap_reg; + cfa->offset = 0; + } + + restore_reg(state, op->dest.reg); + } + + state->stack_size -= 8; + if (cfa->base == CFI_SP) + cfa->offset -= 8; + + break; + + case OP_SRC_REG_INDIRECT: + if (state->drap && op->src.reg == CFI_BP && + op->src.offset == regs[op->dest.reg].offset) { + + /* drap: mov disp(%rbp), %reg */ + if (op->dest.reg == state->drap_reg) { + cfa->base = state->drap_reg; + cfa->offset = 0; + } + + restore_reg(state, op->dest.reg); + + } else if (op->src.reg == cfa->base && + op->src.offset == regs[op->dest.reg].offset + cfa->offset) { + + /* mov disp(%rbp), %reg */ + /* mov disp(%rsp), %reg */ + restore_reg(state, op->dest.reg); + } + + break; + + default: + WARN_FUNC("unknown stack-related instruction", + insn->sec, insn->offset); + return -1; + } + + break; + + case OP_DEST_PUSH: + state->stack_size += 8; + if (cfa->base == CFI_SP) + cfa->offset += 8; + + if (op->src.type != OP_SRC_REG) + break; + + if (state->drap) { + if (op->src.reg == cfa->base && op->src.reg == state->drap_reg) { + + /* drap: push %drap */ + cfa->base = CFI_BP_INDIRECT; + cfa->offset = -state->stack_size; + + /* save drap so we know when to undefine it */ + save_reg(state, op->src.reg, CFI_CFA, -state->stack_size); + + } else if (op->src.reg == CFI_BP && cfa->base == state->drap_reg) { + + /* drap: push %rbp */ + state->stack_size = 0; + + } else if (regs[op->src.reg].base == CFI_UNDEFINED) { + + /* drap: push %reg */ + save_reg(state, op->src.reg, CFI_BP, -state->stack_size); + } + + } else { + + /* push %reg */ + save_reg(state, op->src.reg, CFI_CFA, -state->stack_size); + } + + /* detect when asm code uses rbp as a scratch register */ + if (!nofp && insn->func && op->src.reg == CFI_BP && + cfa->base != CFI_BP) + state->bp_scratch = true; + break; + + case OP_DEST_REG_INDIRECT: + + if (state->drap) { + if (op->src.reg == cfa->base && op->src.reg == state->drap_reg) { + + /* drap: mov %drap, disp(%rbp) */ + cfa->base = CFI_BP_INDIRECT; + cfa->offset = op->dest.offset; + + /* save drap so we know when to undefine it */ + save_reg(state, op->src.reg, CFI_CFA, op->dest.offset); + } + + else if (regs[op->src.reg].base == CFI_UNDEFINED) { + + /* drap: mov reg, disp(%rbp) */ + save_reg(state, op->src.reg, CFI_BP, op->dest.offset); + } + + } else if (op->dest.reg == cfa->base) { + + /* mov reg, disp(%rbp) */ + /* mov reg, disp(%rsp) */ + save_reg(state, op->src.reg, CFI_CFA, + op->dest.offset - state->cfa.offset); + } + + break; + + case OP_DEST_LEAVE: + if ((!state->drap && cfa->base != CFI_BP) || + (state->drap && cfa->base != state->drap_reg)) { + WARN_FUNC("leave instruction with modified stack frame", + insn->sec, insn->offset); + return -1; + } + + /* leave (mov %rbp, %rsp; pop %rbp) */ + + state->stack_size = -state->regs[CFI_BP].offset - 8; + restore_reg(state, CFI_BP); + + if (!state->drap) { + cfa->base = CFI_SP; + cfa->offset -= 8; + } + + break; + + case OP_DEST_MEM: + if (op->src.type != OP_SRC_POP) { + WARN_FUNC("unknown stack-related memory operation", + insn->sec, insn->offset); + return -1; + } + + /* pop mem */ + state->stack_size -= 8; + if (cfa->base == CFI_SP) + cfa->offset -= 8; + + break; + + default: + WARN_FUNC("unknown stack-related instruction", + insn->sec, insn->offset); + return -1; + } + + return 0; +} + +static bool insn_state_match(struct instruction *insn, struct insn_state *state) +{ + struct insn_state *state1 = &insn->state, *state2 = state; + int i; + + if (memcmp(&state1->cfa, &state2->cfa, sizeof(state1->cfa))) { + WARN_FUNC("stack state mismatch: cfa1=%d%+d cfa2=%d%+d", + insn->sec, insn->offset, + state1->cfa.base, state1->cfa.offset, + state2->cfa.base, state2->cfa.offset); + + } else if (memcmp(&state1->regs, &state2->regs, sizeof(state1->regs))) { + for (i = 0; i < CFI_NUM_REGS; i++) { + if (!memcmp(&state1->regs[i], &state2->regs[i], + sizeof(struct cfi_reg))) + continue; + + WARN_FUNC("stack state mismatch: reg1[%d]=%d%+d reg2[%d]=%d%+d", + insn->sec, insn->offset, + i, state1->regs[i].base, state1->regs[i].offset, + i, state2->regs[i].base, state2->regs[i].offset); + break; + } + + } else if (state1->drap != state2->drap || + (state1->drap && state1->drap_reg != state2->drap_reg)) { + WARN_FUNC("stack state mismatch: drap1=%d(%d) drap2=%d(%d)", + insn->sec, insn->offset, + state1->drap, state1->drap_reg, + state2->drap, state2->drap_reg); + + } else + return true; + + return false; +} + +/* + * Follow the branch starting at the given instruction, and recursively follow + * any other branches (jumps). Meanwhile, track the frame pointer state at + * each instruction and validate all the rules described in + * tools/objtool/Documentation/stack-validation.txt. + */ +static int validate_branch(struct objtool_file *file, struct instruction *first, + struct insn_state state) +{ + struct alternative *alt; + struct instruction *insn; + struct section *sec; + struct symbol *func = NULL; + int ret; + + insn = first; + sec = insn->sec; + + if (insn->alt_group && list_empty(&insn->alts)) { + WARN_FUNC("don't know how to handle branch to middle of alternative instruction group", + sec, insn->offset); + return -1; + } + + while (1) { + if (file->c_file && insn->func) { + if (func && func != insn->func) { + WARN("%s() falls through to next function %s()", + func->name, insn->func->name); + return 1; + } + } + + func = insn->func; + + if (insn->visited) { + if (!!insn_state_match(insn, &state)) + return 1; + + return 0; + } + + insn->state = state; + + insn->visited = true; + + list_for_each_entry(alt, &insn->alts, list) { + ret = validate_branch(file, alt->insn, state); + if (ret) + return 1; + } + + switch (insn->type) { + + case INSN_RETURN: + if (func && has_modified_stack_frame(&state)) { + WARN_FUNC("return with modified stack frame", + sec, insn->offset); + return 1; + } + + if (state.bp_scratch) { + WARN("%s uses BP as a scratch register", + insn->func->name); + return 1; + } + + return 0; + + case INSN_CALL: + if (is_fentry_call(insn)) + break; + + ret = dead_end_function(file, insn->call_dest); + if (ret == 1) + return 0; + if (ret == -1) + return 1; + + /* fallthrough */ + case INSN_CALL_DYNAMIC: + if (!nofp && func && !has_valid_stack_frame(&state)) { + WARN_FUNC("call without frame pointer save/setup", + sec, insn->offset); + return 1; + } + break; + + case INSN_JUMP_CONDITIONAL: + case INSN_JUMP_UNCONDITIONAL: + if (insn->jump_dest) { + ret = validate_branch(file, insn->jump_dest, + state); + if (ret) + return 1; + } else if (func && has_modified_stack_frame(&state)) { + WARN_FUNC("sibling call from callable instruction with modified stack frame", + sec, insn->offset); + return 1; + } /* else it's a sibling call */ + + if (insn->type == INSN_JUMP_UNCONDITIONAL) + return 0; + + break; + + case INSN_JUMP_DYNAMIC: + if (func && list_empty(&insn->alts) && + has_modified_stack_frame(&state)) { + WARN_FUNC("sibling call from callable instruction with modified stack frame", + sec, insn->offset); + return 1; + } + + return 0; + + case INSN_STACK: + if (update_insn_state(insn, &state)) + return -1; + + break; + + default: + break; + } + + if (insn->dead_end) + return 0; + + insn = next_insn_same_sec(file, insn); + if (!insn) { + WARN("%s: unexpected end of section", sec->name); + return 1; + } + } + + return 0; +} + +static bool is_kasan_insn(struct instruction *insn) +{ + return (insn->type == INSN_CALL && + !strcmp(insn->call_dest->name, "__asan_handle_no_return")); +} + +static bool is_ubsan_insn(struct instruction *insn) +{ + return (insn->type == INSN_CALL && + !strcmp(insn->call_dest->name, + "__ubsan_handle_builtin_unreachable")); +} + +static bool ignore_unreachable_insn(struct instruction *insn) +{ + int i; + + if (insn->ignore || insn->type == INSN_NOP) + return true; + + /* + * Ignore any unused exceptions. This can happen when a whitelisted + * function has an exception table entry. + */ + if (!strcmp(insn->sec->name, ".fixup")) + return true; + + /* + * Check if this (or a subsequent) instruction is related to + * CONFIG_UBSAN or CONFIG_KASAN. + * + * End the search at 5 instructions to avoid going into the weeds. + */ + if (!insn->func) + return false; + for (i = 0; i < 5; i++) { + + if (is_kasan_insn(insn) || is_ubsan_insn(insn)) + return true; + + if (insn->type == INSN_JUMP_UNCONDITIONAL && insn->jump_dest) { + insn = insn->jump_dest; + continue; + } + + if (insn->offset + insn->len >= insn->func->offset + insn->func->len) + break; + insn = list_next_entry(insn, list); + } + + return false; +} + +static int validate_functions(struct objtool_file *file) +{ + struct section *sec; + struct symbol *func; + struct instruction *insn; + struct insn_state state; + int ret, warnings = 0; + + clear_insn_state(&state); + + state.cfa = initial_func_cfi.cfa; + memcpy(&state.regs, &initial_func_cfi.regs, + CFI_NUM_REGS * sizeof(struct cfi_reg)); + state.stack_size = initial_func_cfi.cfa.offset; + + for_each_sec(file, sec) { + list_for_each_entry(func, &sec->symbol_list, list) { + if (func->type != STT_FUNC) + continue; + + insn = find_insn(file, sec, func->offset); + if (!insn || insn->ignore) + continue; + + ret = validate_branch(file, insn, state); + warnings += ret; + } + } + + return warnings; +} + +static int validate_reachable_instructions(struct objtool_file *file) +{ + struct instruction *insn; + + if (file->ignore_unreachables) + return 0; + + for_each_insn(file, insn) { + if (insn->visited || ignore_unreachable_insn(insn)) + continue; + + /* + * gcov produces a lot of unreachable instructions. If we get + * an unreachable warning and the file has gcov enabled, just + * ignore it, and all other such warnings for the file. Do + * this here because this is an expensive function. + */ + if (gcov_enabled(file)) + return 0; + + WARN_FUNC("unreachable instruction", insn->sec, insn->offset); + return 1; + } + + return 0; +} + +static void cleanup(struct objtool_file *file) +{ + struct instruction *insn, *tmpinsn; + struct alternative *alt, *tmpalt; + + list_for_each_entry_safe(insn, tmpinsn, &file->insn_list, list) { + list_for_each_entry_safe(alt, tmpalt, &insn->alts, list) { + list_del(&alt->list); + free(alt); + } + list_del(&insn->list); + hash_del(&insn->hash); + free(insn); + } + elf_close(file->elf); +} + +int check(const char *_objname, bool _nofp) +{ + struct objtool_file file; + int ret, warnings = 0; + + objname = _objname; + nofp = _nofp; + + file.elf = elf_open(objname); + if (!file.elf) + return 1; + + INIT_LIST_HEAD(&file.insn_list); + hash_init(file.insn_hash); + file.whitelist = find_section_by_name(file.elf, ".discard.func_stack_frame_non_standard"); + file.rodata = find_section_by_name(file.elf, ".rodata"); + file.ignore_unreachables = false; + file.c_file = find_section_by_name(file.elf, ".comment"); + + arch_initial_func_cfi_state(&initial_func_cfi); + + ret = decode_sections(&file); + if (ret < 0) + goto out; + warnings += ret; + + if (list_empty(&file.insn_list)) + goto out; + + ret = validate_functions(&file); + if (ret < 0) + goto out; + warnings += ret; + + if (!warnings) { + ret = validate_reachable_instructions(&file); + if (ret < 0) + goto out; + warnings += ret; + } + +out: + cleanup(&file); + + /* ignore warnings for now until we get all the code cleaned up */ + if (ret || warnings) + return 0; + return 0; +} diff --git a/tools/objtool/check.h b/tools/objtool/check.h new file mode 100644 index 000000000000..da85f5b00ec6 --- /dev/null +++ b/tools/objtool/check.h @@ -0,0 +1,66 @@ +/* + * Copyright (C) 2017 Josh Poimboeuf <jpoimboe@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, see <http://www.gnu.org/licenses/>. + */ + +#ifndef _CHECK_H +#define _CHECK_H + +#include <stdbool.h> +#include "elf.h" +#include "cfi.h" +#include "arch.h" +#include <linux/hashtable.h> + +struct insn_state { + struct cfi_reg cfa; + struct cfi_reg regs[CFI_NUM_REGS]; + int stack_size; + bool bp_scratch; + bool drap; + int drap_reg; +}; + +struct instruction { + struct list_head list; + struct hlist_node hash; + struct section *sec; + unsigned long offset; + unsigned int len; + unsigned char type; + unsigned long immediate; + bool alt_group, visited, dead_end, ignore; + struct symbol *call_dest; + struct instruction *jump_dest; + struct list_head alts; + struct symbol *func; + struct stack_op stack_op; + struct insn_state state; +}; + +struct objtool_file { + struct elf *elf; + struct list_head insn_list; + DECLARE_HASHTABLE(insn_hash, 16); + struct section *rodata, *whitelist; + bool ignore_unreachables, c_file; +}; + +int check(const char *objname, bool nofp); + +#define for_each_insn(file, insn) \ + list_for_each_entry(insn, &file->insn_list, list) + +#endif /* _CHECK_H */ diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index d897702ce742..1a7e8aa2af58 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -37,6 +37,9 @@ #define ELF_C_READ_MMAP ELF_C_READ #endif +#define WARN_ELF(format, ...) \ + WARN(format ": %s", ##__VA_ARGS__, elf_errmsg(-1)) + struct section *find_section_by_name(struct elf *elf, const char *name) { struct section *sec; @@ -139,12 +142,12 @@ static int read_sections(struct elf *elf) int i; if (elf_getshdrnum(elf->elf, §ions_nr)) { - perror("elf_getshdrnum"); + WARN_ELF("elf_getshdrnum"); return -1; } if (elf_getshdrstrndx(elf->elf, &shstrndx)) { - perror("elf_getshdrstrndx"); + WARN_ELF("elf_getshdrstrndx"); return -1; } @@ -165,37 +168,36 @@ static int read_sections(struct elf *elf) s = elf_getscn(elf->elf, i); if (!s) { - perror("elf_getscn"); + WARN_ELF("elf_getscn"); return -1; } sec->idx = elf_ndxscn(s); if (!gelf_getshdr(s, &sec->sh)) { - perror("gelf_getshdr"); + WARN_ELF("gelf_getshdr"); return -1; } sec->name = elf_strptr(elf->elf, shstrndx, sec->sh.sh_name); if (!sec->name) { - perror("elf_strptr"); + WARN_ELF("elf_strptr"); return -1; } - sec->elf_data = elf_getdata(s, NULL); - if (!sec->elf_data) { - perror("elf_getdata"); + sec->data = elf_getdata(s, NULL); + if (!sec->data) { + WARN_ELF("elf_getdata"); return -1; } - if (sec->elf_data->d_off != 0 || - sec->elf_data->d_size != sec->sh.sh_size) { + if (sec->data->d_off != 0 || + sec->data->d_size != sec->sh.sh_size) { WARN("unexpected data attributes for %s", sec->name); return -1; } - sec->data = (unsigned long)sec->elf_data->d_buf; - sec->len = sec->elf_data->d_size; + sec->len = sec->data->d_size; } /* sanity check, one more call to elf_nextscn() should return NULL */ @@ -232,15 +234,15 @@ static int read_symbols(struct elf *elf) sym->idx = i; - if (!gelf_getsym(symtab->elf_data, i, &sym->sym)) { - perror("gelf_getsym"); + if (!gelf_getsym(symtab->data, i, &sym->sym)) { + WARN_ELF("gelf_getsym"); goto err; } sym->name = elf_strptr(elf->elf, symtab->sh.sh_link, sym->sym.st_name); if (!sym->name) { - perror("elf_strptr"); + WARN_ELF("elf_strptr"); goto err; } @@ -322,8 +324,8 @@ static int read_relas(struct elf *elf) } memset(rela, 0, sizeof(*rela)); - if (!gelf_getrela(sec->elf_data, i, &rela->rela)) { - perror("gelf_getrela"); + if (!gelf_getrela(sec->data, i, &rela->rela)) { + WARN_ELF("gelf_getrela"); return -1; } @@ -362,12 +364,6 @@ struct elf *elf_open(const char *name) INIT_LIST_HEAD(&elf->sections); - elf->name = strdup(name); - if (!elf->name) { - perror("strdup"); - goto err; - } - elf->fd = open(name, O_RDONLY); if (elf->fd == -1) { perror("open"); @@ -376,12 +372,12 @@ struct elf *elf_open(const char *name) elf->elf = elf_begin(elf->fd, ELF_C_READ_MMAP, NULL); if (!elf->elf) { - perror("elf_begin"); + WARN_ELF("elf_begin"); goto err; } if (!gelf_getehdr(elf->elf, &elf->ehdr)) { - perror("gelf_getehdr"); + WARN_ELF("gelf_getehdr"); goto err; } @@ -407,6 +403,12 @@ void elf_close(struct elf *elf) struct symbol *sym, *tmpsym; struct rela *rela, *tmprela; + if (elf->elf) + elf_end(elf->elf); + + if (elf->fd > 0) + close(elf->fd); + list_for_each_entry_safe(sec, tmpsec, &elf->sections, list) { list_for_each_entry_safe(sym, tmpsym, &sec->symbol_list, list) { list_del(&sym->list); @@ -421,11 +423,6 @@ void elf_close(struct elf *elf) list_del(&sec->list); free(sec); } - if (elf->name) - free(elf->name); - if (elf->fd > 0) - close(elf->fd); - if (elf->elf) - elf_end(elf->elf); + free(elf); } diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h index 731973e1a3f5..343968b778cb 100644 --- a/tools/objtool/elf.h +++ b/tools/objtool/elf.h @@ -37,10 +37,9 @@ struct section { DECLARE_HASHTABLE(rela_hash, 16); struct section *base, *rela; struct symbol *sym; - Elf_Data *elf_data; + Elf_Data *data; char *name; int idx; - unsigned long data; unsigned int len; }; @@ -86,6 +85,7 @@ struct rela *find_rela_by_dest_range(struct section *sec, unsigned long offset, struct symbol *find_containing_func(struct section *sec, unsigned long offset); void elf_close(struct elf *elf); - +#define for_each_sec(file, sec) \ + list_for_each_entry(sec, &file->elf->sections, list) #endif /* _OBJTOOL_ELF_H */ diff --git a/tools/objtool/special.c b/tools/objtool/special.c index bff8abb3a4aa..84f001d52322 100644 --- a/tools/objtool/special.c +++ b/tools/objtool/special.c @@ -91,16 +91,16 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry, alt->jump_or_nop = entry->jump_or_nop; if (alt->group) { - alt->orig_len = *(unsigned char *)(sec->data + offset + + alt->orig_len = *(unsigned char *)(sec->data->d_buf + offset + entry->orig_len); - alt->new_len = *(unsigned char *)(sec->data + offset + + alt->new_len = *(unsigned char *)(sec->data->d_buf + offset + entry->new_len); } if (entry->feature) { unsigned short feature; - feature = *(unsigned short *)(sec->data + offset + + feature = *(unsigned short *)(sec->data->d_buf + offset + entry->feature); /* diff --git a/tools/objtool/warn.h b/tools/objtool/warn.h index ac7e07523e84..afd9f7a05f6d 100644 --- a/tools/objtool/warn.h +++ b/tools/objtool/warn.h @@ -18,6 +18,13 @@ #ifndef _WARN_H #define _WARN_H +#include <stdlib.h> +#include <string.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include "elf.h" + extern const char *objname; static inline char *offstr(struct section *sec, unsigned long offset) @@ -57,4 +64,7 @@ static inline char *offstr(struct section *sec, unsigned long offset) free(_str); \ }) +#define WARN_ELF(format, ...) \ + WARN(format ": %s", ##__VA_ARGS__, elf_errmsg(-1)) + #endif /* _WARN_H */ diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt index b0b3007d3c9c..4b6cdbf8f935 100644 --- a/tools/perf/Documentation/intel-pt.txt +++ b/tools/perf/Documentation/intel-pt.txt @@ -108,6 +108,9 @@ approach is available to export the data to a postgresql database. Refer to script export-to-postgresql.py for more details, and to script call-graph-from-postgresql.py for an example of using the database. +There is also script intel-pt-events.py which provides an example of how to +unpack the raw data for power events and PTWRITE. + As mentioned above, it is easy to capture too much data. One way to limit the data captured is to use 'snapshot' mode which is explained further below. Refer to 'new snapshot option' and 'Intel PT modes of operation' further below. @@ -364,6 +367,42 @@ cyc_thresh Specifies how frequently CYC packets are produced - see cyc CYC packets are not requested by default. +pt Specifies pass-through which enables the 'branch' config term. + + The default config selects 'pt' if it is available, so a user will + never need to specify this term. + +branch Enable branch tracing. Branch tracing is enabled by default so to + disable branch tracing use 'branch=0'. + + The default config selects 'branch' if it is available. + +ptw Enable PTWRITE packets which are produced when a ptwrite instruction + is executed. + + Support for this feature is indicated by: + + /sys/bus/event_source/devices/intel_pt/caps/ptwrite + + which contains "1" if the feature is supported and + "0" otherwise. + +fup_on_ptw Enable a FUP packet to follow the PTWRITE packet. The FUP packet + provides the address of the ptwrite instruction. In the absence of + fup_on_ptw, the decoder will use the address of the previous branch + if branch tracing is enabled, otherwise the address will be zero. + Note that fup_on_ptw will work even when branch tracing is disabled. + +pwr_evt Enable power events. The power events provide information about + changes to the CPU C-state. + + Support for this feature is indicated by: + + /sys/bus/event_source/devices/intel_pt/caps/power_event_trace + + which contains "1" if the feature is supported and + "0" otherwise. + new snapshot option ------------------- @@ -674,13 +713,15 @@ Having no option is the same as which, in turn, is the same as - --itrace=ibxe + --itrace=ibxwpe The letters are: i synthesize "instructions" events b synthesize "branches" events x synthesize "transactions" events + w synthesize "ptwrite" events + p synthesize "power" events c synthesize branches events (calls only) r synthesize branches events (returns only) e synthesize tracing error events @@ -699,7 +740,40 @@ and "r" can be combined to get calls and returns. 'flags' field can be used in perf script to determine whether the event is a tranasaction start, commit or abort. -Error events are new. They show where the decoder lost the trace. Error events +Note that "instructions", "branches" and "transactions" events depend on code +flow packets which can be disabled by using the config term "branch=0". Refer +to the config terms section above. + +"ptwrite" events record the payload of the ptwrite instruction and whether +"fup_on_ptw" was used. "ptwrite" events depend on PTWRITE packets which are +recorded only if the "ptw" config term was used. Refer to the config terms +section above. perf script "synth" field displays "ptwrite" information like +this: "ip: 0 payload: 0x123456789abcdef0" where "ip" is 1 if "fup_on_ptw" was +used. + +"Power" events correspond to power event packets and CBR (core-to-bus ratio) +packets. While CBR packets are always recorded when tracing is enabled, power +event packets are recorded only if the "pwr_evt" config term was used. Refer to +the config terms section above. The power events record information about +C-state changes, whereas CBR is indicative of CPU frequency. perf script +"event,synth" fields display information like this: + cbr: cbr: 22 freq: 2189 MHz (200%) + mwait: hints: 0x60 extensions: 0x1 + pwre: hw: 0 cstate: 2 sub-cstate: 0 + exstop: ip: 1 + pwrx: deepest cstate: 2 last cstate: 2 wake reason: 0x4 +Where: + "cbr" includes the frequency and the percentage of maximum non-turbo + "mwait" shows mwait hints and extensions + "pwre" shows C-state transitions (to a C-state deeper than C0) and + whether initiated by hardware + "exstop" indicates execution stopped and whether the IP was recorded + exactly, + "pwrx" indicates return to C0 +For more details refer to the Intel 64 and IA-32 Architectures Software +Developer Manuals. + +Error events show where the decoder lost the trace. Error events are quite important. Users must know if what they are seeing is a complete picture or not. diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt index e2a4c5e0dbe5..a3abe04c779d 100644 --- a/tools/perf/Documentation/itrace.txt +++ b/tools/perf/Documentation/itrace.txt @@ -3,13 +3,15 @@ c synthesize branches events (calls only) r synthesize branches events (returns only) x synthesize transactions events + w synthesize ptwrite events + p synthesize power events e synthesize error events d create a debug log g synthesize a call chain (use with i or x) l synthesize last branch entries (use with i or x) s skip initial number of events - The default is all events i.e. the same as --itrace=ibxe + The default is all events i.e. the same as --itrace=ibxwpe In addition, the period (default 100000) for instructions events can be specified in units of: @@ -26,8 +28,8 @@ Also the number of last branch entries (default 64, max. 1024) for instructions or transactions events can be specified. - It is also possible to skip events generated (instructions, branches, transactions) - at the beginning. This is useful to ignore initialization code. + It is also possible to skip events generated (instructions, branches, transactions, + ptwrite, power) at the beginning. This is useful to ignore initialization code. --itrace=i0nss1000000 diff --git a/tools/perf/Documentation/perf-ftrace.txt b/tools/perf/Documentation/perf-ftrace.txt index 6e6a8b22c859..721a447f046e 100644 --- a/tools/perf/Documentation/perf-ftrace.txt +++ b/tools/perf/Documentation/perf-ftrace.txt @@ -48,6 +48,39 @@ OPTIONS Ranges of CPUs are specified with -: 0-2. Default is to trace on all online CPUs. +-T:: +--trace-funcs=:: + Only trace functions given by the argument. Multiple functions + can be given by using this option more than once. The function + argument also can be a glob pattern. It will be passed to + 'set_ftrace_filter' in tracefs. + +-N:: +--notrace-funcs=:: + Do not trace functions given by the argument. Like -T option, + this can be used more than once to specify multiple functions + (or glob patterns). It will be passed to 'set_ftrace_notrace' + in tracefs. + +-G:: +--graph-funcs=:: + Set graph filter on the given function (or a glob pattern). + This is useful for the function_graph tracer only and enables + tracing for functions executed from the given function. + This can be used more than once to specify multiple functions. + It will be passed to 'set_graph_function' in tracefs. + +-g:: +--nograph-funcs=:: + Set graph notrace filter on the given function (or a glob pattern). + Like -G option, this is useful for the function_graph tracer only + and disables tracing for function executed from the given function. + This can be used more than once to specify multiple functions. + It will be passed to 'set_graph_notrace' in tracefs. + +-D:: +--graph-depth=:: + Set max depth for function graph tracer to follow SEE ALSO -------- diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 3517e204a2b3..5ee8796be96e 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -116,8 +116,9 @@ OPTIONS --fields:: Comma separated list of fields to print. Options are: comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, - srcline, period, iregs, brstack, brstacksym, flags, bpf-output, brstackinsn, - callindent, insn, insnlen. Field list can be prepended with the type, trace, sw or hw, + srcline, period, iregs, brstack, brstacksym, flags, bpf-output, brstackinsn, brstackoff, + callindent, insn, insnlen, synth. + Field list can be prepended with the type, trace, sw or hw, to indicate to which event type the field list applies. e.g., -F sw:comm,tid,time,ip,sym and -F trace:time,cpu,trace @@ -130,6 +131,14 @@ OPTIONS i.e., the specified fields apply to all event types if the type string is not given. + In addition to overriding fields, it is also possible to add or remove + fields from the defaults. For example + + -F -cpu,+insn + + removes the cpu field and adds the insn field. Adding/removing fields + cannot be mixed with normal overriding. + The arguments are processed in the order received. A later usage can reset a prior request. e.g.: @@ -185,6 +194,9 @@ OPTIONS instruction bytes and the instruction length of the current instruction. + The synth field is used by synthesized events which may be created when + Instruction Trace decoding. + Finally, a user may not set fields to none for all event types. i.e., -F "" is not allowed. @@ -203,6 +215,8 @@ OPTIONS is printed. This is the full execution path leading to the sample. This is only supported when the sample was recorded with perf record -b or -j any. + The brstackoff field will print an offset into a specific dso/binary. + -k:: --vmlinux=<file>:: vmlinux pathname diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index bd0e4417f2be..698076313606 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -239,6 +239,20 @@ taskset. --no-merge:: Do not merge results from same PMUs. +--smi-cost:: +Measure SMI cost if msr/aperf/ and msr/smi/ events are supported. + +During the measurement, the /sys/device/cpu/freeze_on_smi will be set to +freeze core counters on SMI. +The aperf counter will not be effected by the setting. +The cost of SMI can be measured by (aperf - unhalted core cycles). + +In practice, the percentages of SMI cycles is very useful for performance +oriented analysis. --metric_only will be applied by default. +The output is SMI cycles%, equals to (aperf - unhalted core cycles) / aperf + +Users who wants to get the actual value can apply --no-metric-only. + EXAMPLES -------- diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 1f4fbc9a3292..bdf0e87f9b29 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -61,7 +61,7 @@ endif # Disable it on all other architectures in case libdw unwind # support is detected in system. Add supported architectures # to the check. -ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm)) +ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm powerpc)) NO_LIBDW_DWARF_UNWIND := 1 endif diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 29361d9b635a..7ce3d1a25133 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -17,6 +17,7 @@ #include <api/fs/fs.h> #include <linux/bitops.h> +#include <linux/compiler.h> #include <linux/coresight-pmu.h> #include <linux/kernel.h> #include <linux/log2.h> @@ -202,19 +203,18 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, pr_debug2("%s snapshot size: %zu\n", CORESIGHT_ETM_PMU_NAME, opts->auxtrace_snapshot_size); - if (cs_etm_evsel) { - /* - * To obtain the auxtrace buffer file descriptor, the auxtrace - * event must come first. - */ - perf_evlist__to_front(evlist, cs_etm_evsel); - /* - * In the case of per-cpu mmaps, we need the CPU on the - * AUX event. - */ - if (!cpu_map__empty(cpus)) - perf_evsel__set_sample_bit(cs_etm_evsel, CPU); - } + /* + * To obtain the auxtrace buffer file descriptor, the auxtrace + * event must come first. + */ + perf_evlist__to_front(evlist, cs_etm_evsel); + + /* + * In the case of per-cpu mmaps, we need the CPU on the + * AUX event. + */ + if (!cpu_map__empty(cpus)) + perf_evsel__set_sample_bit(cs_etm_evsel, CPU); /* Add dummy event to keep tracking */ if (opts->full_auxtrace) { @@ -583,8 +583,7 @@ static FILE *cs_device__open_file(const char *name) } -static __attribute__((format(printf, 2, 3))) -int cs_device__print_file(const char *name, const char *fmt, ...) +static int __printf(2, 3) cs_device__print_file(const char *name, const char *fmt, ...) { va_list args; FILE *file; diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build index 90ad64b231cd..2e6595310420 100644 --- a/tools/perf/arch/powerpc/util/Build +++ b/tools/perf/arch/powerpc/util/Build @@ -5,4 +5,6 @@ libperf-y += perf_regs.o libperf-$(CONFIG_DWARF) += dwarf-regs.o libperf-$(CONFIG_DWARF) += skip-callchain-idx.o + libperf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o +libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o diff --git a/tools/perf/arch/powerpc/util/unwind-libdw.c b/tools/perf/arch/powerpc/util/unwind-libdw.c new file mode 100644 index 000000000000..3a24b3c43273 --- /dev/null +++ b/tools/perf/arch/powerpc/util/unwind-libdw.c @@ -0,0 +1,73 @@ +#include <elfutils/libdwfl.h> +#include "../../util/unwind-libdw.h" +#include "../../util/perf_regs.h" +#include "../../util/event.h" + +/* See backends/ppc_initreg.c and backends/ppc_regs.c in elfutils. */ +static const int special_regs[3][2] = { + { 65, PERF_REG_POWERPC_LINK }, + { 101, PERF_REG_POWERPC_XER }, + { 109, PERF_REG_POWERPC_CTR }, +}; + +bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) +{ + struct unwind_info *ui = arg; + struct regs_dump *user_regs = &ui->sample->user_regs; + Dwarf_Word dwarf_regs[32], dwarf_nip; + size_t i; + +#define REG(r) ({ \ + Dwarf_Word val = 0; \ + perf_reg_value(&val, user_regs, PERF_REG_POWERPC_##r); \ + val; \ +}) + + dwarf_regs[0] = REG(R0); + dwarf_regs[1] = REG(R1); + dwarf_regs[2] = REG(R2); + dwarf_regs[3] = REG(R3); + dwarf_regs[4] = REG(R4); + dwarf_regs[5] = REG(R5); + dwarf_regs[6] = REG(R6); + dwarf_regs[7] = REG(R7); + dwarf_regs[8] = REG(R8); + dwarf_regs[9] = REG(R9); + dwarf_regs[10] = REG(R10); + dwarf_regs[11] = REG(R11); + dwarf_regs[12] = REG(R12); + dwarf_regs[13] = REG(R13); + dwarf_regs[14] = REG(R14); + dwarf_regs[15] = REG(R15); + dwarf_regs[16] = REG(R16); + dwarf_regs[17] = REG(R17); + dwarf_regs[18] = REG(R18); + dwarf_regs[19] = REG(R19); + dwarf_regs[20] = REG(R20); + dwarf_regs[21] = REG(R21); + dwarf_regs[22] = REG(R22); + dwarf_regs[23] = REG(R23); + dwarf_regs[24] = REG(R24); + dwarf_regs[25] = REG(R25); + dwarf_regs[26] = REG(R26); + dwarf_regs[27] = REG(R27); + dwarf_regs[28] = REG(R28); + dwarf_regs[29] = REG(R29); + dwarf_regs[30] = REG(R30); + dwarf_regs[31] = REG(R31); + if (!dwfl_thread_state_registers(thread, 0, 32, dwarf_regs)) + return false; + + dwarf_nip = REG(NIP); + dwfl_thread_state_register_pc(thread, dwarf_nip); + for (i = 0; i < ARRAY_SIZE(special_regs); i++) { + Dwarf_Word val = 0; + perf_reg_value(&val, user_regs, special_regs[i][1]); + if (!dwfl_thread_state_registers(thread, + special_regs[i][0], 1, + &val)) + return false; + } + + return true; +} diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-32.c b/tools/perf/arch/x86/tests/insn-x86-dat-32.c index 0f196eec9f48..3cbf6fad169f 100644 --- a/tools/perf/arch/x86/tests/insn-x86-dat-32.c +++ b/tools/perf/arch/x86/tests/insn-x86-dat-32.c @@ -1664,3 +1664,15 @@ "0f c7 1d 78 56 34 12 \txrstors 0x12345678",}, {{0x0f, 0xc7, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "", "0f c7 9c c8 78 56 34 12 \txrstors 0x12345678(%eax,%ecx,8)",}, +{{0xf3, 0x0f, 0xae, 0x20, }, 4, 0, "", "", +"f3 0f ae 20 \tptwritel (%eax)",}, +{{0xf3, 0x0f, 0xae, 0x25, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "", +"f3 0f ae 25 78 56 34 12 \tptwritel 0x12345678",}, +{{0xf3, 0x0f, 0xae, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "", +"f3 0f ae a4 c8 78 56 34 12 \tptwritel 0x12345678(%eax,%ecx,8)",}, +{{0xf3, 0x0f, 0xae, 0x20, }, 4, 0, "", "", +"f3 0f ae 20 \tptwritel (%eax)",}, +{{0xf3, 0x0f, 0xae, 0x25, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "", +"f3 0f ae 25 78 56 34 12 \tptwritel 0x12345678",}, +{{0xf3, 0x0f, 0xae, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "", +"f3 0f ae a4 c8 78 56 34 12 \tptwritel 0x12345678(%eax,%ecx,8)",}, diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-64.c b/tools/perf/arch/x86/tests/insn-x86-dat-64.c index af25bc8240d0..aa512fa944dd 100644 --- a/tools/perf/arch/x86/tests/insn-x86-dat-64.c +++ b/tools/perf/arch/x86/tests/insn-x86-dat-64.c @@ -1696,3 +1696,33 @@ "0f c7 9c c8 78 56 34 12 \txrstors 0x12345678(%rax,%rcx,8)",}, {{0x41, 0x0f, 0xc7, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "", "41 0f c7 9c c8 78 56 34 12 \txrstors 0x12345678(%r8,%rcx,8)",}, +{{0xf3, 0x0f, 0xae, 0x20, }, 4, 0, "", "", +"f3 0f ae 20 \tptwritel (%rax)",}, +{{0xf3, 0x41, 0x0f, 0xae, 0x20, }, 5, 0, "", "", +"f3 41 0f ae 20 \tptwritel (%r8)",}, +{{0xf3, 0x0f, 0xae, 0x24, 0x25, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "", +"f3 0f ae 24 25 78 56 34 12 \tptwritel 0x12345678",}, +{{0xf3, 0x0f, 0xae, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "", +"f3 0f ae a4 c8 78 56 34 12 \tptwritel 0x12345678(%rax,%rcx,8)",}, +{{0xf3, 0x41, 0x0f, 0xae, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"f3 41 0f ae a4 c8 78 56 34 12 \tptwritel 0x12345678(%r8,%rcx,8)",}, +{{0xf3, 0x0f, 0xae, 0x20, }, 4, 0, "", "", +"f3 0f ae 20 \tptwritel (%rax)",}, +{{0xf3, 0x41, 0x0f, 0xae, 0x20, }, 5, 0, "", "", +"f3 41 0f ae 20 \tptwritel (%r8)",}, +{{0xf3, 0x0f, 0xae, 0x24, 0x25, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "", +"f3 0f ae 24 25 78 56 34 12 \tptwritel 0x12345678",}, +{{0xf3, 0x0f, 0xae, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "", +"f3 0f ae a4 c8 78 56 34 12 \tptwritel 0x12345678(%rax,%rcx,8)",}, +{{0xf3, 0x41, 0x0f, 0xae, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"f3 41 0f ae a4 c8 78 56 34 12 \tptwritel 0x12345678(%r8,%rcx,8)",}, +{{0xf3, 0x48, 0x0f, 0xae, 0x20, }, 5, 0, "", "", +"f3 48 0f ae 20 \tptwriteq (%rax)",}, +{{0xf3, 0x49, 0x0f, 0xae, 0x20, }, 5, 0, "", "", +"f3 49 0f ae 20 \tptwriteq (%r8)",}, +{{0xf3, 0x48, 0x0f, 0xae, 0x24, 0x25, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"f3 48 0f ae 24 25 78 56 34 12 \tptwriteq 0x12345678",}, +{{0xf3, 0x48, 0x0f, 0xae, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"f3 48 0f ae a4 c8 78 56 34 12 \tptwriteq 0x12345678(%rax,%rcx,8)",}, +{{0xf3, 0x49, 0x0f, 0xae, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"f3 49 0f ae a4 c8 78 56 34 12 \tptwriteq 0x12345678(%r8,%rcx,8)",}, diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-src.c b/tools/perf/arch/x86/tests/insn-x86-dat-src.c index 979487dae8d4..6cdb65d25b79 100644 --- a/tools/perf/arch/x86/tests/insn-x86-dat-src.c +++ b/tools/perf/arch/x86/tests/insn-x86-dat-src.c @@ -1343,6 +1343,26 @@ int main(void) asm volatile("xrstors 0x12345678(%rax,%rcx,8)"); asm volatile("xrstors 0x12345678(%r8,%rcx,8)"); + /* ptwrite */ + + asm volatile("ptwrite (%rax)"); + asm volatile("ptwrite (%r8)"); + asm volatile("ptwrite (0x12345678)"); + asm volatile("ptwrite 0x12345678(%rax,%rcx,8)"); + asm volatile("ptwrite 0x12345678(%r8,%rcx,8)"); + + asm volatile("ptwritel (%rax)"); + asm volatile("ptwritel (%r8)"); + asm volatile("ptwritel (0x12345678)"); + asm volatile("ptwritel 0x12345678(%rax,%rcx,8)"); + asm volatile("ptwritel 0x12345678(%r8,%rcx,8)"); + + asm volatile("ptwriteq (%rax)"); + asm volatile("ptwriteq (%r8)"); + asm volatile("ptwriteq (0x12345678)"); + asm volatile("ptwriteq 0x12345678(%rax,%rcx,8)"); + asm volatile("ptwriteq 0x12345678(%r8,%rcx,8)"); + #else /* #ifdef __x86_64__ */ /* bound r32, mem (same op code as EVEX prefix) */ @@ -2653,6 +2673,16 @@ int main(void) asm volatile("xrstors (0x12345678)"); asm volatile("xrstors 0x12345678(%eax,%ecx,8)"); + /* ptwrite */ + + asm volatile("ptwrite (%eax)"); + asm volatile("ptwrite (0x12345678)"); + asm volatile("ptwrite 0x12345678(%eax,%ecx,8)"); + + asm volatile("ptwritel (%eax)"); + asm volatile("ptwritel (0x12345678)"); + asm volatile("ptwritel 0x12345678(%eax,%ecx,8)"); + #endif /* #ifndef __x86_64__ */ /* Following line is a marker for the awk script - do not change */ diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c index af2bce7a2cd6..781df40b2966 100644 --- a/tools/perf/arch/x86/util/intel-bts.c +++ b/tools/perf/arch/x86/util/intel-bts.c @@ -35,10 +35,6 @@ #define KiB_MASK(x) (KiB(x) - 1) #define MiB_MASK(x) (MiB(x) - 1) -#define INTEL_BTS_DFLT_SAMPLE_SIZE KiB(4) - -#define INTEL_BTS_MAX_SAMPLE_SIZE KiB(60) - struct intel_bts_snapshot_ref { void *ref_buf; size_t ref_offset; diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index f630de0206a1..9535be57033f 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -40,10 +40,6 @@ #define KiB_MASK(x) (KiB(x) - 1) #define MiB_MASK(x) (MiB(x) - 1) -#define INTEL_PT_DEFAULT_SAMPLE_SIZE KiB(4) - -#define INTEL_PT_MAX_SAMPLE_SIZE KiB(60) - #define INTEL_PT_PSB_PERIOD_NEAR 256 struct intel_pt_snapshot_ref { @@ -196,6 +192,7 @@ static u64 intel_pt_default_config(struct perf_pmu *intel_pt_pmu) int psb_cyc, psb_periods, psb_period; int pos = 0; u64 config; + char c; pos += scnprintf(buf + pos, sizeof(buf) - pos, "tsc"); @@ -229,6 +226,10 @@ static u64 intel_pt_default_config(struct perf_pmu *intel_pt_pmu) } } + if (perf_pmu__scan_file(intel_pt_pmu, "format/pt", "%c", &c) == 1 && + perf_pmu__scan_file(intel_pt_pmu, "format/branch", "%c", &c) == 1) + pos += scnprintf(buf + pos, sizeof(buf) - pos, ",pt,branch"); + pr_debug2("%s default config: %s\n", intel_pt_pmu->name, buf); intel_pt_parse_terms(&intel_pt_pmu->format, buf, &config); diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index 27de0c8c5c19..469d65b21122 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -700,7 +700,7 @@ static inline uint32_t lfsr_32(uint32_t lfsr) * kernel (KSM, zero page, etc.) cannot optimize away RAM * accesses: */ -static inline u64 access_data(u64 *data __attribute__((unused)), u64 val) +static inline u64 access_data(u64 *data, u64 val) { if (g->p.data_reads) val += *data; diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index 620a467ee304..475999e48f66 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -1725,10 +1725,10 @@ static int c2c_hists__init_sort(struct perf_hpp_list *hpp_list, char *name) tok; tok = strtok_r(NULL, ", ", &tmp)) { \ ret = _fn(hpp_list, tok); \ if (ret == -EINVAL) { \ - error("Invalid --fields key: `%s'", tok); \ + pr_err("Invalid --fields key: `%s'", tok); \ break; \ } else if (ret == -ESRCH) { \ - error("Unknown --fields key: `%s'", tok); \ + pr_err("Unknown --fields key: `%s'", tok); \ break; \ } \ } \ diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c index 80668fa7556e..ece45582a48d 100644 --- a/tools/perf/builtin-config.c +++ b/tools/perf/builtin-config.c @@ -156,7 +156,7 @@ static int parse_config_arg(char *arg, char **var, char **value) int cmd_config(int argc, const char **argv) { - int i, ret = 0; + int i, ret = -1; struct perf_config_set *set; char *user_config = mkpath("%s/.perfconfig", getenv("HOME")); const char *config_filename; @@ -186,10 +186,8 @@ int cmd_config(int argc, const char **argv) * because of reinitializing with options config file location. */ set = perf_config_set__new(); - if (!set) { - ret = -1; + if (!set) goto out_err; - } switch (actions) { case ACTION_LIST: @@ -197,41 +195,54 @@ int cmd_config(int argc, const char **argv) pr_err("Error: takes no arguments\n"); parse_options_usage(config_usage, config_options, "l", 1); } else { - ret = show_config(set); - if (ret < 0) + if (show_config(set) < 0) { pr_err("Nothing configured, " "please check your %s \n", config_filename); + goto out_err; + } } break; default: - if (argc) { - for (i = 0; argv[i]; i++) { - char *var, *value; - char *arg = strdup(argv[i]); - - if (!arg) { - pr_err("%s: strdup failed\n", __func__); - ret = -1; - break; - } + if (!argc) { + usage_with_options(config_usage, config_options); + break; + } - if (parse_config_arg(arg, &var, &value) < 0) { - free(arg); - ret = -1; - break; - } + for (i = 0; argv[i]; i++) { + char *var, *value; + char *arg = strdup(argv[i]); + + if (!arg) { + pr_err("%s: strdup failed\n", __func__); + goto out_err; + } - if (value == NULL) - ret = show_spec_config(set, var); - else - ret = set_config(set, config_filename, var, value); + if (parse_config_arg(arg, &var, &value) < 0) { free(arg); + goto out_err; } - } else - usage_with_options(config_usage, config_options); + + if (value == NULL) { + if (show_spec_config(set, var) < 0) { + pr_err("%s is not configured: %s\n", + var, config_filename); + free(arg); + goto out_err; + } + } else { + if (set_config(set, config_filename, var, value) < 0) { + pr_err("Failed to set '%s=%s' on %s\n", + var, value, config_filename); + free(arg); + goto out_err; + } + } + free(arg); + } } - perf_config_set__delete(set); + ret = 0; out_err: + perf_config_set__delete(set); return ret; } diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index eec5df80f5a3..0cd4cf6a344b 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -1302,7 +1302,10 @@ static int diff__config(const char *var, const char *value, void *cb __maybe_unused) { if (!strcmp(var, "diff.order")) { - sort_compute = perf_config_int(var, value); + int ret; + if (perf_config_int(&ret, var, value) < 0) + return -1; + sort_compute = ret; return 0; } if (!strcmp(var, "diff.compute")) { diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index 9e0b35cd0eea..dd26c62c9893 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -28,9 +28,19 @@ #define DEFAULT_TRACER "function_graph" struct perf_ftrace { - struct perf_evlist *evlist; - struct target target; - const char *tracer; + struct perf_evlist *evlist; + struct target target; + const char *tracer; + struct list_head filters; + struct list_head notrace; + struct list_head graph_funcs; + struct list_head nograph_funcs; + int graph_depth; +}; + +struct filter_entry { + struct list_head list; + char name[]; }; static bool done; @@ -61,6 +71,7 @@ static int __write_tracing_file(const char *name, const char *val, bool append) int fd, ret = -1; ssize_t size = strlen(val); int flags = O_WRONLY; + char errbuf[512]; file = get_tracing_file(name); if (!file) { @@ -75,14 +86,16 @@ static int __write_tracing_file(const char *name, const char *val, bool append) fd = open(file, flags); if (fd < 0) { - pr_debug("cannot open tracing file: %s\n", name); + pr_debug("cannot open tracing file: %s: %s\n", + name, str_error_r(errno, errbuf, sizeof(errbuf))); goto out; } if (write(fd, val, size) == size) ret = 0; else - pr_debug("write '%s' to tracing/%s failed\n", val, name); + pr_debug("write '%s' to tracing/%s failed: %s\n", + val, name, str_error_r(errno, errbuf, sizeof(errbuf))); close(fd); out: @@ -101,6 +114,7 @@ static int append_tracing_file(const char *name, const char *val) } static int reset_tracing_cpu(void); +static void reset_tracing_filters(void); static int reset_tracing_files(struct perf_ftrace *ftrace __maybe_unused) { @@ -116,6 +130,10 @@ static int reset_tracing_files(struct perf_ftrace *ftrace __maybe_unused) if (reset_tracing_cpu() < 0) return -1; + if (write_tracing_file("max_graph_depth", "0") < 0) + return -1; + + reset_tracing_filters(); return 0; } @@ -181,6 +199,68 @@ static int reset_tracing_cpu(void) return ret; } +static int __set_tracing_filter(const char *filter_file, struct list_head *funcs) +{ + struct filter_entry *pos; + + list_for_each_entry(pos, funcs, list) { + if (append_tracing_file(filter_file, pos->name) < 0) + return -1; + } + + return 0; +} + +static int set_tracing_filters(struct perf_ftrace *ftrace) +{ + int ret; + + ret = __set_tracing_filter("set_ftrace_filter", &ftrace->filters); + if (ret < 0) + return ret; + + ret = __set_tracing_filter("set_ftrace_notrace", &ftrace->notrace); + if (ret < 0) + return ret; + + ret = __set_tracing_filter("set_graph_function", &ftrace->graph_funcs); + if (ret < 0) + return ret; + + /* old kernels do not have this filter */ + __set_tracing_filter("set_graph_notrace", &ftrace->nograph_funcs); + + return ret; +} + +static void reset_tracing_filters(void) +{ + write_tracing_file("set_ftrace_filter", " "); + write_tracing_file("set_ftrace_notrace", " "); + write_tracing_file("set_graph_function", " "); + write_tracing_file("set_graph_notrace", " "); +} + +static int set_tracing_depth(struct perf_ftrace *ftrace) +{ + char buf[16]; + + if (ftrace->graph_depth == 0) + return 0; + + if (ftrace->graph_depth < 0) { + pr_err("invalid graph depth: %d\n", ftrace->graph_depth); + return -1; + } + + snprintf(buf, sizeof(buf), "%d", ftrace->graph_depth); + + if (write_tracing_file("max_graph_depth", buf) < 0) + return -1; + + return 0; +} + static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) { char *trace_file; @@ -223,11 +303,23 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) goto out_reset; } + if (set_tracing_filters(ftrace) < 0) { + pr_err("failed to set tracing filters\n"); + goto out_reset; + } + + if (set_tracing_depth(ftrace) < 0) { + pr_err("failed to set graph depth\n"); + goto out_reset; + } + if (write_tracing_file("current_tracer", ftrace->tracer) < 0) { pr_err("failed to set current_tracer to %s\n", ftrace->tracer); goto out_reset; } + setup_pager(); + trace_file = get_tracing_file("trace_pipe"); if (!trace_file) { pr_err("failed to open trace_pipe\n"); @@ -251,8 +343,6 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) goto out_close_fd; } - setup_pager(); - perf_evlist__start_workload(ftrace->evlist); while (!done) { @@ -307,6 +397,32 @@ static int perf_ftrace_config(const char *var, const char *value, void *cb) return -1; } +static int parse_filter_func(const struct option *opt, const char *str, + int unset __maybe_unused) +{ + struct list_head *head = opt->value; + struct filter_entry *entry; + + entry = malloc(sizeof(*entry) + strlen(str) + 1); + if (entry == NULL) + return -ENOMEM; + + strcpy(entry->name, str); + list_add_tail(&entry->list, head); + + return 0; +} + +static void delete_filter_func(struct list_head *head) +{ + struct filter_entry *pos, *tmp; + + list_for_each_entry_safe(pos, tmp, head, list) { + list_del(&pos->list); + free(pos); + } +} + int cmd_ftrace(int argc, const char **argv) { int ret; @@ -330,9 +446,24 @@ int cmd_ftrace(int argc, const char **argv) "system-wide collection from all CPUs"), OPT_STRING('C', "cpu", &ftrace.target.cpu_list, "cpu", "list of cpus to monitor"), + OPT_CALLBACK('T', "trace-funcs", &ftrace.filters, "func", + "trace given functions only", parse_filter_func), + OPT_CALLBACK('N', "notrace-funcs", &ftrace.notrace, "func", + "do not trace given functions", parse_filter_func), + OPT_CALLBACK('G', "graph-funcs", &ftrace.graph_funcs, "func", + "Set graph filter on given functions", parse_filter_func), + OPT_CALLBACK('g', "nograph-funcs", &ftrace.nograph_funcs, "func", + "Set nograph filter on given functions", parse_filter_func), + OPT_INTEGER('D', "graph-depth", &ftrace.graph_depth, + "Max depth for function graph tracer"), OPT_END() }; + INIT_LIST_HEAD(&ftrace.filters); + INIT_LIST_HEAD(&ftrace.notrace); + INIT_LIST_HEAD(&ftrace.graph_funcs); + INIT_LIST_HEAD(&ftrace.nograph_funcs); + ret = perf_config(perf_ftrace_config, &ftrace); if (ret < 0) return -1; @@ -348,12 +479,14 @@ int cmd_ftrace(int argc, const char **argv) target__strerror(&ftrace.target, ret, errbuf, 512); pr_err("%s\n", errbuf); - return -EINVAL; + goto out_delete_filters; } ftrace.evlist = perf_evlist__new(); - if (ftrace.evlist == NULL) - return -ENOMEM; + if (ftrace.evlist == NULL) { + ret = -ENOMEM; + goto out_delete_filters; + } ret = perf_evlist__create_maps(ftrace.evlist, &ftrace.target); if (ret < 0) @@ -364,5 +497,11 @@ int cmd_ftrace(int argc, const char **argv) out_delete_evlist: perf_evlist__delete(ftrace.evlist); +out_delete_filters: + delete_filter_func(&ftrace.filters); + delete_filter_func(&ftrace.notrace); + delete_filter_func(&ftrace.graph_funcs); + delete_filter_func(&ftrace.nograph_funcs); + return ret; } diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c index 492f8e14ab09..530a7f2fa0f3 100644 --- a/tools/perf/builtin-help.c +++ b/tools/perf/builtin-help.c @@ -108,10 +108,14 @@ out: return ret; } -static void exec_woman_emacs(const char *path, const char *page) +static void exec_failed(const char *cmd) { char sbuf[STRERR_BUFSIZE]; + pr_warning("failed to exec '%s': %s", cmd, str_error_r(errno, sbuf, sizeof(sbuf))); +} +static void exec_woman_emacs(const char *path, const char *page) +{ if (!check_emacsclient_version()) { /* This works only with emacsclient version >= 22. */ char *man_page; @@ -122,8 +126,7 @@ static void exec_woman_emacs(const char *path, const char *page) execlp(path, "emacsclient", "-e", man_page, NULL); free(man_page); } - warning("failed to exec '%s': %s", path, - str_error_r(errno, sbuf, sizeof(sbuf))); + exec_failed(path); } } @@ -134,7 +137,6 @@ static void exec_man_konqueror(const char *path, const char *page) if (display && *display) { char *man_page; const char *filename = "kfmclient"; - char sbuf[STRERR_BUFSIZE]; /* It's simpler to launch konqueror using kfmclient. */ if (path) { @@ -155,33 +157,27 @@ static void exec_man_konqueror(const char *path, const char *page) execlp(path, filename, "newTab", man_page, NULL); free(man_page); } - warning("failed to exec '%s': %s", path, - str_error_r(errno, sbuf, sizeof(sbuf))); + exec_failed(path); } } static void exec_man_man(const char *path, const char *page) { - char sbuf[STRERR_BUFSIZE]; - if (!path) path = "man"; execlp(path, "man", page, NULL); - warning("failed to exec '%s': %s", path, - str_error_r(errno, sbuf, sizeof(sbuf))); + exec_failed(path); } static void exec_man_cmd(const char *cmd, const char *page) { - char sbuf[STRERR_BUFSIZE]; char *shell_cmd; if (asprintf(&shell_cmd, "%s %s", cmd, page) > 0) { execl("/bin/sh", "sh", "-c", shell_cmd, NULL); free(shell_cmd); } - warning("failed to exec '%s': %s", cmd, - str_error_r(errno, sbuf, sizeof(sbuf))); + exec_failed(cmd); } static void add_man_viewer(const char *name) @@ -214,6 +210,12 @@ static void do_add_man_viewer_info(const char *name, man_viewer_info_list = new; } +static void unsupported_man_viewer(const char *name, const char *var) +{ + pr_warning("'%s': path for unsupported man viewer.\n" + "Please consider using 'man.<tool>.%s' instead.", name, var); +} + static int add_man_viewer_path(const char *name, size_t len, const char *value) @@ -221,9 +223,7 @@ static int add_man_viewer_path(const char *name, if (supported_man_viewer(name, len)) do_add_man_viewer_info(name, len, value); else - warning("'%s': path for unsupported man viewer.\n" - "Please consider using 'man.<tool>.cmd' instead.", - name); + unsupported_man_viewer(name, "cmd"); return 0; } @@ -233,9 +233,7 @@ static int add_man_viewer_cmd(const char *name, const char *value) { if (supported_man_viewer(name, len)) - warning("'%s': cmd for supported man viewer.\n" - "Please consider using 'man.<tool>.path' instead.", - name); + unsupported_man_viewer(name, "path"); else do_add_man_viewer_info(name, len, value); @@ -247,8 +245,10 @@ static int add_man_viewer_info(const char *var, const char *value) const char *name = var + 4; const char *subkey = strrchr(name, '.'); - if (!subkey) - return error("Config with no key for man viewer: %s", name); + if (!subkey) { + pr_err("Config with no key for man viewer: %s", name); + return -1; + } if (!strcmp(subkey, ".path")) { if (!value) @@ -261,7 +261,7 @@ static int add_man_viewer_info(const char *var, const char *value) return add_man_viewer_cmd(name, subkey - name, value); } - warning("'%s': unsupported man viewer sub key.", subkey); + pr_warning("'%s': unsupported man viewer sub key.", subkey); return 0; } @@ -332,7 +332,7 @@ static void setup_man_path(void) setenv("MANPATH", new_path, 1); free(new_path); } else { - error("Unable to setup man path"); + pr_err("Unable to setup man path"); } } @@ -349,7 +349,7 @@ static void exec_viewer(const char *name, const char *page) else if (info) exec_man_cmd(info, page); else - warning("'%s': unknown man viewer.", name); + pr_warning("'%s': unknown man viewer.", name); } static int show_man_page(const char *perf_cmd) diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 9409c9464667..0a8a1c45af87 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -1715,7 +1715,7 @@ static int setup_slab_sorting(struct list_head *sort_list, const char *arg) if (!tok) break; if (slab_sort_dimension__add(tok, sort_list) < 0) { - error("Unknown slab --sort key: '%s'", tok); + pr_err("Unknown slab --sort key: '%s'", tok); free(str); return -1; } @@ -1741,7 +1741,7 @@ static int setup_page_sorting(struct list_head *sort_list, const char *arg) if (!tok) break; if (page_sort_dimension__add(tok, sort_list) < 0) { - error("Unknown page --sort key: '%s'", tok); + pr_err("Unknown page --sort key: '%s'", tok); free(str); return -1; } diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index ee7d0a82ccd0..17a14bcce34a 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -453,7 +453,7 @@ try_again: } if (perf_evlist__apply_filters(evlist, &pos)) { - error("failed to set filter \"%s\" on event %s with %d (%s)\n", + pr_err("failed to set filter \"%s\" on event %s with %d (%s)\n", pos->filter, perf_evsel__name(pos), errno, str_error_r(errno, msg, sizeof(msg))); rc = -1; @@ -461,7 +461,7 @@ try_again: } if (perf_evlist__apply_drv_configs(evlist, &pos, &err_term)) { - error("failed to set config \"%s\" on event %s with %d (%s)\n", + pr_err("failed to set config \"%s\" on event %s with %d (%s)\n", err_term->val.drv_cfg, perf_evsel__name(pos), errno, str_error_r(errno, msg, sizeof(msg))); rc = -1; diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 22478ff2b706..79a33eb1a10d 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -94,10 +94,9 @@ static int report__config(const char *var, const char *value, void *cb) symbol_conf.cumulate_callchain = perf_config_bool(var, value); return 0; } - if (!strcmp(var, "report.queue-size")) { - rep->queue_size = perf_config_u64(var, value); - return 0; - } + if (!strcmp(var, "report.queue-size")) + return perf_config_u64(&rep->queue_size, var, value); + if (!strcmp(var, "report.sort_order")) { default_sort_order = strdup(value); return 0; @@ -558,6 +557,7 @@ static int __cmd_report(struct report *rep) ui__error("failed to set cpu bitmap\n"); return ret; } + session->itrace_synth_opts->cpu_bitmap = rep->cpu_bitmap; } if (rep->show_threads) { diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 39996c53995a..322b4def8411 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -2066,7 +2066,7 @@ static void save_task_callchain(struct perf_sched *sched, if (thread__resolve_callchain(thread, cursor, evsel, sample, NULL, NULL, sched->max_stack + 2) != 0) { if (verbose > 0) - error("Failed to resolve callchain. Skipping\n"); + pr_err("Failed to resolve callchain. Skipping\n"); return; } diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 4761b0d7fcb5..83cdc0a61fd6 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -85,6 +85,8 @@ enum perf_output_field { PERF_OUTPUT_INSN = 1U << 21, PERF_OUTPUT_INSNLEN = 1U << 22, PERF_OUTPUT_BRSTACKINSN = 1U << 23, + PERF_OUTPUT_BRSTACKOFF = 1U << 24, + PERF_OUTPUT_SYNTH = 1U << 25, }; struct output_option { @@ -115,6 +117,13 @@ struct output_option { {.str = "insn", .field = PERF_OUTPUT_INSN}, {.str = "insnlen", .field = PERF_OUTPUT_INSNLEN}, {.str = "brstackinsn", .field = PERF_OUTPUT_BRSTACKINSN}, + {.str = "brstackoff", .field = PERF_OUTPUT_BRSTACKOFF}, + {.str = "synth", .field = PERF_OUTPUT_SYNTH}, +}; + +enum { + OUTPUT_TYPE_SYNTH = PERF_TYPE_MAX, + OUTPUT_TYPE_MAX }; /* default set to maintain compatibility with current format */ @@ -124,7 +133,7 @@ static struct { unsigned int print_ip_opts; u64 fields; u64 invalid_fields; -} output[PERF_TYPE_MAX] = { +} output[OUTPUT_TYPE_MAX] = { [PERF_TYPE_HARDWARE] = { .user_set = false, @@ -182,12 +191,44 @@ static struct { .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, }, + + [OUTPUT_TYPE_SYNTH] = { + .user_set = false, + + .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | + PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | + PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | + PERF_OUTPUT_SYM | PERF_OUTPUT_DSO | + PERF_OUTPUT_SYNTH, + + .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, + }, }; +static inline int output_type(unsigned int type) +{ + switch (type) { + case PERF_TYPE_SYNTH: + return OUTPUT_TYPE_SYNTH; + default: + return type; + } +} + +static inline unsigned int attr_type(unsigned int type) +{ + switch (type) { + case OUTPUT_TYPE_SYNTH: + return PERF_TYPE_SYNTH; + default: + return type; + } +} + static bool output_set_by_user(void) { int j; - for (j = 0; j < PERF_TYPE_MAX; ++j) { + for (j = 0; j < OUTPUT_TYPE_MAX; ++j) { if (output[j].user_set) return true; } @@ -208,7 +249,7 @@ static const char *output_field2str(enum perf_output_field field) return str; } -#define PRINT_FIELD(x) (output[attr->type].fields & PERF_OUTPUT_##x) +#define PRINT_FIELD(x) (output[output_type(attr->type)].fields & PERF_OUTPUT_##x) static int perf_evsel__do_check_stype(struct perf_evsel *evsel, u64 sample_type, const char *sample_msg, @@ -216,7 +257,7 @@ static int perf_evsel__do_check_stype(struct perf_evsel *evsel, bool allow_user_set) { struct perf_event_attr *attr = &evsel->attr; - int type = attr->type; + int type = output_type(attr->type); const char *evname; if (attr->sample_type & sample_type) @@ -298,10 +339,10 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, "selected.\n"); return -EINVAL; } - if (PRINT_FIELD(DSO) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) { - pr_err("Display of DSO requested but neither sample IP nor " - "sample address\nis selected. Hence, no addresses to convert " - "to DSO.\n"); + if (PRINT_FIELD(DSO) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR) && + !PRINT_FIELD(BRSTACK) && !PRINT_FIELD(BRSTACKSYM) && !PRINT_FIELD(BRSTACKOFF)) { + pr_err("Display of DSO requested but no address to convert. Select\n" + "sample IP, sample address, brstack, brstacksym, or brstackoff.\n"); return -EINVAL; } if (PRINT_FIELD(SRCLINE) && !PRINT_FIELD(IP)) { @@ -346,7 +387,7 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, static void set_print_ip_opts(struct perf_event_attr *attr) { - unsigned int type = attr->type; + unsigned int type = output_type(attr->type); output[type].print_ip_opts = 0; if (PRINT_FIELD(IP)) @@ -374,16 +415,17 @@ static int perf_session__check_output_opt(struct perf_session *session) unsigned int j; struct perf_evsel *evsel; - for (j = 0; j < PERF_TYPE_MAX; ++j) { - evsel = perf_session__find_first_evtype(session, j); + for (j = 0; j < OUTPUT_TYPE_MAX; ++j) { + evsel = perf_session__find_first_evtype(session, attr_type(j)); /* * even if fields is set to 0 (ie., show nothing) event must * exist if user explicitly includes it on the command line */ - if (!evsel && output[j].user_set && !output[j].wildcard_set) { + if (!evsel && output[j].user_set && !output[j].wildcard_set && + j != OUTPUT_TYPE_SYNTH) { pr_err("%s events do not exist. " - "Remove corresponding -f option to proceed.\n", + "Remove corresponding -F option to proceed.\n", event_type(j)); return -1; } @@ -514,18 +556,43 @@ mispred_str(struct branch_entry *br) return br->flags.predicted ? 'P' : 'M'; } -static void print_sample_brstack(struct perf_sample *sample) +static void print_sample_brstack(struct perf_sample *sample, + struct thread *thread, + struct perf_event_attr *attr) { struct branch_stack *br = sample->branch_stack; - u64 i; + struct addr_location alf, alt; + u64 i, from, to; if (!(br && br->nr)) return; for (i = 0; i < br->nr; i++) { - printf(" 0x%"PRIx64"/0x%"PRIx64"/%c/%c/%c/%d ", - br->entries[i].from, - br->entries[i].to, + from = br->entries[i].from; + to = br->entries[i].to; + + if (PRINT_FIELD(DSO)) { + memset(&alf, 0, sizeof(alf)); + memset(&alt, 0, sizeof(alt)); + thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf); + thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt); + } + + printf("0x%"PRIx64, from); + if (PRINT_FIELD(DSO)) { + printf("("); + map__fprintf_dsoname(alf.map, stdout); + printf(")"); + } + + printf("/0x%"PRIx64, to); + if (PRINT_FIELD(DSO)) { + printf("("); + map__fprintf_dsoname(alt.map, stdout); + printf(")"); + } + + printf("/%c/%c/%c/%d ", mispred_str( br->entries + i), br->entries[i].flags.in_tx? 'X' : '-', br->entries[i].flags.abort? 'A' : '-', @@ -534,7 +601,8 @@ static void print_sample_brstack(struct perf_sample *sample) } static void print_sample_brstacksym(struct perf_sample *sample, - struct thread *thread) + struct thread *thread, + struct perf_event_attr *attr) { struct branch_stack *br = sample->branch_stack; struct addr_location alf, alt; @@ -559,8 +627,18 @@ static void print_sample_brstacksym(struct perf_sample *sample, alt.sym = map__find_symbol(alt.map, alt.addr); symbol__fprintf_symname_offs(alf.sym, &alf, stdout); + if (PRINT_FIELD(DSO)) { + printf("("); + map__fprintf_dsoname(alf.map, stdout); + printf(")"); + } putchar('/'); symbol__fprintf_symname_offs(alt.sym, &alt, stdout); + if (PRINT_FIELD(DSO)) { + printf("("); + map__fprintf_dsoname(alt.map, stdout); + printf(")"); + } printf("/%c/%c/%c/%d ", mispred_str( br->entries + i), br->entries[i].flags.in_tx? 'X' : '-', @@ -569,6 +647,51 @@ static void print_sample_brstacksym(struct perf_sample *sample, } } +static void print_sample_brstackoff(struct perf_sample *sample, + struct thread *thread, + struct perf_event_attr *attr) +{ + struct branch_stack *br = sample->branch_stack; + struct addr_location alf, alt; + u64 i, from, to; + + if (!(br && br->nr)) + return; + + for (i = 0; i < br->nr; i++) { + + memset(&alf, 0, sizeof(alf)); + memset(&alt, 0, sizeof(alt)); + from = br->entries[i].from; + to = br->entries[i].to; + + thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf); + if (alf.map && !alf.map->dso->adjust_symbols) + from = map__map_ip(alf.map, from); + + thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt); + if (alt.map && !alt.map->dso->adjust_symbols) + to = map__map_ip(alt.map, to); + + printf("0x%"PRIx64, from); + if (PRINT_FIELD(DSO)) { + printf("("); + map__fprintf_dsoname(alf.map, stdout); + printf(")"); + } + printf("/0x%"PRIx64, to); + if (PRINT_FIELD(DSO)) { + printf("("); + map__fprintf_dsoname(alt.map, stdout); + printf(")"); + } + printf("/%c/%c/%c/%d ", + mispred_str(br->entries + i), + br->entries[i].flags.in_tx ? 'X' : '-', + br->entries[i].flags.abort ? 'A' : '-', + br->entries[i].flags.cycles); + } +} #define MAXBB 16384UL static int grab_bb(u8 *buffer, u64 start, u64 end, @@ -906,6 +1029,7 @@ static void print_sample_bts(struct perf_sample *sample, struct machine *machine) { struct perf_event_attr *attr = &evsel->attr; + unsigned int type = output_type(attr->type); bool print_srcline_last = false; if (PRINT_FIELD(CALLINDENT)) @@ -913,7 +1037,7 @@ static void print_sample_bts(struct perf_sample *sample, /* print branch_from information */ if (PRINT_FIELD(IP)) { - unsigned int print_opts = output[attr->type].print_ip_opts; + unsigned int print_opts = output[type].print_ip_opts; struct callchain_cursor *cursor = NULL; if (symbol_conf.use_callchain && sample->callchain && @@ -936,7 +1060,7 @@ static void print_sample_bts(struct perf_sample *sample, /* print branch_to information */ if (PRINT_FIELD(ADDR) || ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) && - !output[attr->type].user_set)) { + !output[type].user_set)) { printf(" => "); print_sample_addr(sample, thread, attr); } @@ -1079,6 +1203,127 @@ static void print_sample_bpf_output(struct perf_sample *sample) (char *)(sample->raw_data)); } +static void print_sample_spacing(int len, int spacing) +{ + if (len > 0 && len < spacing) + printf("%*s", spacing - len, ""); +} + +static void print_sample_pt_spacing(int len) +{ + print_sample_spacing(len, 34); +} + +static void print_sample_synth_ptwrite(struct perf_sample *sample) +{ + struct perf_synth_intel_ptwrite *data = perf_sample__synth_ptr(sample); + int len; + + if (perf_sample__bad_synth_size(sample, *data)) + return; + + len = printf(" IP: %u payload: %#" PRIx64 " ", + data->ip, le64_to_cpu(data->payload)); + print_sample_pt_spacing(len); +} + +static void print_sample_synth_mwait(struct perf_sample *sample) +{ + struct perf_synth_intel_mwait *data = perf_sample__synth_ptr(sample); + int len; + + if (perf_sample__bad_synth_size(sample, *data)) + return; + + len = printf(" hints: %#x extensions: %#x ", + data->hints, data->extensions); + print_sample_pt_spacing(len); +} + +static void print_sample_synth_pwre(struct perf_sample *sample) +{ + struct perf_synth_intel_pwre *data = perf_sample__synth_ptr(sample); + int len; + + if (perf_sample__bad_synth_size(sample, *data)) + return; + + len = printf(" hw: %u cstate: %u sub-cstate: %u ", + data->hw, data->cstate, data->subcstate); + print_sample_pt_spacing(len); +} + +static void print_sample_synth_exstop(struct perf_sample *sample) +{ + struct perf_synth_intel_exstop *data = perf_sample__synth_ptr(sample); + int len; + + if (perf_sample__bad_synth_size(sample, *data)) + return; + + len = printf(" IP: %u ", data->ip); + print_sample_pt_spacing(len); +} + +static void print_sample_synth_pwrx(struct perf_sample *sample) +{ + struct perf_synth_intel_pwrx *data = perf_sample__synth_ptr(sample); + int len; + + if (perf_sample__bad_synth_size(sample, *data)) + return; + + len = printf(" deepest cstate: %u last cstate: %u wake reason: %#x ", + data->deepest_cstate, data->last_cstate, + data->wake_reason); + print_sample_pt_spacing(len); +} + +static void print_sample_synth_cbr(struct perf_sample *sample) +{ + struct perf_synth_intel_cbr *data = perf_sample__synth_ptr(sample); + unsigned int percent, freq; + int len; + + if (perf_sample__bad_synth_size(sample, *data)) + return; + + freq = (le32_to_cpu(data->freq) + 500) / 1000; + len = printf(" cbr: %2u freq: %4u MHz ", data->cbr, freq); + if (data->max_nonturbo) { + percent = (5 + (1000 * data->cbr) / data->max_nonturbo) / 10; + len += printf("(%3u%%) ", percent); + } + print_sample_pt_spacing(len); +} + +static void print_sample_synth(struct perf_sample *sample, + struct perf_evsel *evsel) +{ + switch (evsel->attr.config) { + case PERF_SYNTH_INTEL_PTWRITE: + print_sample_synth_ptwrite(sample); + break; + case PERF_SYNTH_INTEL_MWAIT: + print_sample_synth_mwait(sample); + break; + case PERF_SYNTH_INTEL_PWRE: + print_sample_synth_pwre(sample); + break; + case PERF_SYNTH_INTEL_EXSTOP: + print_sample_synth_exstop(sample); + break; + case PERF_SYNTH_INTEL_PWRX: + print_sample_synth_pwrx(sample); + break; + case PERF_SYNTH_INTEL_CBR: + print_sample_synth_cbr(sample); + break; + default: + break; + } +} + struct perf_script { struct perf_tool tool; struct perf_session *session; @@ -1132,8 +1377,9 @@ static void process_event(struct perf_script *script, { struct thread *thread = al->thread; struct perf_event_attr *attr = &evsel->attr; + unsigned int type = output_type(attr->type); - if (output[attr->type].fields == 0) + if (output[type].fields == 0) return; print_sample_start(sample, thread, evsel); @@ -1162,6 +1408,10 @@ static void process_event(struct perf_script *script, if (PRINT_FIELD(TRACE)) event_format__print(evsel->tp_format, sample->cpu, sample->raw_data, sample->raw_size); + + if (attr->type == PERF_TYPE_SYNTH && PRINT_FIELD(SYNTH)) + print_sample_synth(sample, evsel); + if (PRINT_FIELD(ADDR)) print_sample_addr(sample, thread, attr); @@ -1180,16 +1430,18 @@ static void process_event(struct perf_script *script, cursor = &callchain_cursor; putchar(cursor ? '\n' : ' '); - sample__fprintf_sym(sample, al, 0, output[attr->type].print_ip_opts, cursor, stdout); + sample__fprintf_sym(sample, al, 0, output[type].print_ip_opts, cursor, stdout); } if (PRINT_FIELD(IREGS)) print_sample_iregs(sample, attr); if (PRINT_FIELD(BRSTACK)) - print_sample_brstack(sample); + print_sample_brstack(sample, thread, attr); else if (PRINT_FIELD(BRSTACKSYM)) - print_sample_brstacksym(sample, thread); + print_sample_brstacksym(sample, thread, attr); + else if (PRINT_FIELD(BRSTACKOFF)) + print_sample_brstackoff(sample, thread, attr); if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT)) print_sample_bpf_output(sample); @@ -1325,7 +1577,8 @@ static int process_attr(struct perf_tool *tool, union perf_event *event, evlist = *pevlist; evsel = perf_evlist__last(*pevlist); - if (evsel->attr.type >= PERF_TYPE_MAX) + if (evsel->attr.type >= PERF_TYPE_MAX && + evsel->attr.type != PERF_TYPE_SYNTH) return 0; evlist__for_each_entry(evlist, pos) { @@ -1727,6 +1980,7 @@ static int parse_output_fields(const struct option *opt __maybe_unused, int rc = 0; char *str = strdup(arg); int type = -1; + enum { DEFAULT, SET, ADD, REMOVE } change = DEFAULT; if (!str) return -ENOMEM; @@ -1749,6 +2003,8 @@ static int parse_output_fields(const struct option *opt __maybe_unused, type = PERF_TYPE_RAW; else if (!strcmp(str, "break")) type = PERF_TYPE_BREAKPOINT; + else if (!strcmp(str, "synth")) + type = OUTPUT_TYPE_SYNTH; else { fprintf(stderr, "Invalid event type in field string.\n"); rc = -EINVAL; @@ -1772,23 +2028,44 @@ static int parse_output_fields(const struct option *opt __maybe_unused, goto out; } + /* Don't override defaults for +- */ + if (strchr(str, '+') || strchr(str, '-')) + goto parse; + if (output_set_by_user()) pr_warning("Overriding previous field request for all events.\n"); - for (j = 0; j < PERF_TYPE_MAX; ++j) { + for (j = 0; j < OUTPUT_TYPE_MAX; ++j) { output[j].fields = 0; output[j].user_set = true; output[j].wildcard_set = true; } } +parse: for (tok = strtok_r(tok, ",", &strtok_saveptr); tok; tok = strtok_r(NULL, ",", &strtok_saveptr)) { + if (*tok == '+') { + if (change == SET) + goto out_badmix; + change = ADD; + tok++; + } else if (*tok == '-') { + if (change == SET) + goto out_badmix; + change = REMOVE; + tok++; + } else { + if (change != SET && change != DEFAULT) + goto out_badmix; + change = SET; + } + for (i = 0; i < imax; ++i) { if (strcmp(tok, all_output_options[i].str) == 0) break; } if (i == imax && strcmp(tok, "flags") == 0) { - print_flags = true; + print_flags = change == REMOVE ? false : true; continue; } if (i == imax) { @@ -1801,12 +2078,16 @@ static int parse_output_fields(const struct option *opt __maybe_unused, /* add user option to all events types for * which it is valid */ - for (j = 0; j < PERF_TYPE_MAX; ++j) { + for (j = 0; j < OUTPUT_TYPE_MAX; ++j) { if (output[j].invalid_fields & all_output_options[i].field) { pr_warning("\'%s\' not valid for %s events. Ignoring.\n", all_output_options[i].str, event_type(j)); - } else - output[j].fields |= all_output_options[i].field; + } else { + if (change == REMOVE) + output[j].fields &= ~all_output_options[i].field; + else + output[j].fields |= all_output_options[i].field; + } } } else { if (output[type].invalid_fields & all_output_options[i].field) { @@ -1826,7 +2107,11 @@ static int parse_output_fields(const struct option *opt __maybe_unused, "Events will not be displayed.\n", event_type(type)); } } + goto out; +out_badmix: + fprintf(stderr, "Cannot mix +-field with overridden fields\n"); + rc = -EINVAL; out: free(str); return rc; @@ -2444,10 +2729,11 @@ int cmd_script(int argc, const char **argv) symbol__config_symfs), OPT_CALLBACK('F', "fields", NULL, "str", "comma separated output fields prepend with 'type:'. " - "Valid types: hw,sw,trace,raw. " + "+field to add and -field to remove." + "Valid types: hw,sw,trace,raw,synth. " "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso," "addr,symoff,period,iregs,brstack,brstacksym,flags," - "bpf-output,callindent,insn,insnlen,brstackinsn", + "bpf-output,callindent,insn,insnlen,brstackinsn,synth", parse_output_fields), OPT_BOOLEAN('a', "all-cpus", &system_wide, "system-wide collection from all CPUs"), @@ -2706,6 +2992,7 @@ int cmd_script(int argc, const char **argv) err = perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap); if (err < 0) goto out_delete; + itrace_synth_opts.cpu_bitmap = cpu_bitmap; } if (!no_callchain) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index ad9324d1daf9..48ac53b199fc 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -86,6 +86,7 @@ #define DEFAULT_SEPARATOR " " #define CNTR_NOT_SUPPORTED "<not supported>" #define CNTR_NOT_COUNTED "<not counted>" +#define FREEZE_ON_SMI_PATH "devices/cpu/freeze_on_smi" static void print_counters(struct timespec *ts, int argc, const char **argv); @@ -122,6 +123,14 @@ static const char * topdown_attrs[] = { NULL, }; +static const char *smi_cost_attrs = { + "{" + "msr/aperf/," + "msr/smi/," + "cycles" + "}" +}; + static struct perf_evlist *evsel_list; static struct target target = { @@ -137,6 +146,8 @@ static bool null_run = false; static int detailed_run = 0; static bool transaction_run; static bool topdown_run = false; +static bool smi_cost = false; +static bool smi_reset = false; static bool big_num = true; static int big_num_opt = -1; static const char *csv_sep = NULL; @@ -625,14 +636,14 @@ try_again: } if (perf_evlist__apply_filters(evsel_list, &counter)) { - error("failed to set filter \"%s\" on event %s with %d (%s)\n", + pr_err("failed to set filter \"%s\" on event %s with %d (%s)\n", counter->filter, perf_evsel__name(counter), errno, str_error_r(errno, msg, sizeof(msg))); return -1; } if (perf_evlist__apply_drv_configs(evsel_list, &counter, &err_term)) { - error("failed to set config \"%s\" on event %s with %d (%s)\n", + pr_err("failed to set config \"%s\" on event %s with %d (%s)\n", err_term->val.drv_cfg, perf_evsel__name(counter), errno, str_error_r(errno, msg, sizeof(msg))); return -1; @@ -1782,6 +1793,8 @@ static const struct option stat_options[] = { "Only print computed metrics. No raw values", enable_metric_only), OPT_BOOLEAN(0, "topdown", &topdown_run, "measure topdown level 1 statistics"), + OPT_BOOLEAN(0, "smi-cost", &smi_cost, + "measure SMI cost"), OPT_END() }; @@ -2160,6 +2173,39 @@ static int add_default_attributes(void) return 0; } + if (smi_cost) { + int smi; + + if (sysfs__read_int(FREEZE_ON_SMI_PATH, &smi) < 0) { + fprintf(stderr, "freeze_on_smi is not supported.\n"); + return -1; + } + + if (!smi) { + if (sysfs__write_int(FREEZE_ON_SMI_PATH, 1) < 0) { + fprintf(stderr, "Failed to set freeze_on_smi.\n"); + return -1; + } + smi_reset = true; + } + + if (pmu_have_event("msr", "aperf") && + pmu_have_event("msr", "smi")) { + if (!force_metric_only) + metric_only = true; + err = parse_events(evsel_list, smi_cost_attrs, NULL); + } else { + fprintf(stderr, "To measure SMI cost, it needs " + "msr/aperf/, msr/smi/ and cpu/cycles/ support\n"); + return -1; + } + if (err) { + fprintf(stderr, "Cannot set up SMI cost events\n"); + return -1; + } + return 0; + } + if (topdown_run) { char *str = NULL; bool warn = false; @@ -2742,6 +2788,9 @@ int cmd_stat(int argc, const char **argv) perf_stat__exit_aggr_mode(); perf_evlist__free_stats(evsel_list); out: + if (smi_cost && smi_reset) + sysfs__write_int(FREEZE_ON_SMI_PATH, 0); + perf_evlist__delete(evsel_list); return status; } diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 10b6362ca0bf..6052376634c0 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -134,7 +134,7 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he) return err; } - err = symbol__disassemble(sym, map, NULL, 0); + err = symbol__disassemble(sym, map, NULL, 0, NULL); if (err == 0) { out_assign: top->sym_filter_entry = he; @@ -958,7 +958,7 @@ static int __cmd_top(struct perf_top *top) ret = perf_evlist__apply_drv_configs(evlist, &pos, &err_term); if (ret) { - error("failed to set config \"%s\" on event %s with %d (%s)\n", + pr_err("failed to set config \"%s\" on event %s with %d (%s)\n", err_term->val.drv_cfg, perf_evsel__name(pos), errno, str_error_r(errno, msg, sizeof(msg))); goto out_delete; diff --git a/tools/perf/jvmti/jvmti_agent.c b/tools/perf/jvmti/jvmti_agent.c index e9651a9d670e..cf36de7ea255 100644 --- a/tools/perf/jvmti/jvmti_agent.c +++ b/tools/perf/jvmti/jvmti_agent.c @@ -304,7 +304,7 @@ jvmti_close(void *agent) FILE *fp = agent; if (!fp) { - warnx("jvmti: incalid fd in close_agent"); + warnx("jvmti: invalid fd in close_agent"); return -1; } diff --git a/tools/perf/jvmti/jvmti_agent.h b/tools/perf/jvmti/jvmti_agent.h index bedf5d0ba9ff..c53a41f48b63 100644 --- a/tools/perf/jvmti/jvmti_agent.h +++ b/tools/perf/jvmti/jvmti_agent.h @@ -5,8 +5,6 @@ #include <stdint.h> #include <jvmti.h> -#define __unused __attribute__((unused)) - #if defined(__cplusplus) extern "C" { #endif diff --git a/tools/perf/jvmti/libjvmti.c b/tools/perf/jvmti/libjvmti.c index 5612641c69b4..6d710904c837 100644 --- a/tools/perf/jvmti/libjvmti.c +++ b/tools/perf/jvmti/libjvmti.c @@ -1,3 +1,4 @@ +#include <linux/compiler.h> #include <sys/types.h> #include <stdio.h> #include <string.h> @@ -238,7 +239,7 @@ code_generated_cb(jvmtiEnv *jvmti, } JNIEXPORT jint JNICALL -Agent_OnLoad(JavaVM *jvm, char *options, void *reserved __unused) +Agent_OnLoad(JavaVM *jvm, char *options, void *reserved __maybe_unused) { jvmtiEventCallbacks cb; jvmtiCapabilities caps1; @@ -313,7 +314,7 @@ Agent_OnLoad(JavaVM *jvm, char *options, void *reserved __unused) } JNIEXPORT void JNICALL -Agent_OnUnload(JavaVM *jvm __unused) +Agent_OnUnload(JavaVM *jvm __maybe_unused) { int ret; diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index baa073f38334..bd0aabb2bd0f 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -48,10 +48,6 @@ #include "json.h" #include "jevents.h" -#ifndef __maybe_unused -#define __maybe_unused __attribute__((unused)) -#endif - int verbose; char *prog; diff --git a/tools/perf/scripts/python/bin/intel-pt-events-record b/tools/perf/scripts/python/bin/intel-pt-events-record new file mode 100644 index 000000000000..10fe2b6977d4 --- /dev/null +++ b/tools/perf/scripts/python/bin/intel-pt-events-record @@ -0,0 +1,13 @@ +#!/bin/bash + +# +# print Intel PT Power Events and PTWRITE. The intel_pt PMU event needs +# to be specified with appropriate config terms. +# +if ! echo "$@" | grep -q intel_pt ; then + echo "Options must include the Intel PT event e.g. -e intel_pt/pwr_evt,ptw/" + echo "and for power events it probably needs to be system wide i.e. -a option" + echo "For example: -a -e intel_pt/pwr_evt,branch=0/ sleep 1" + exit 1 +fi +perf record $@ diff --git a/tools/perf/scripts/python/bin/intel-pt-events-report b/tools/perf/scripts/python/bin/intel-pt-events-report new file mode 100644 index 000000000000..9a9c92fcd026 --- /dev/null +++ b/tools/perf/scripts/python/bin/intel-pt-events-report @@ -0,0 +1,3 @@ +#!/bin/bash +# description: print Intel PT Power Events and PTWRITE +perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/intel-pt-events.py
\ No newline at end of file diff --git a/tools/perf/scripts/python/intel-pt-events.py b/tools/perf/scripts/python/intel-pt-events.py new file mode 100644 index 000000000000..b19172d673af --- /dev/null +++ b/tools/perf/scripts/python/intel-pt-events.py @@ -0,0 +1,128 @@ +# intel-pt-events.py: Print Intel PT Power Events and PTWRITE +# Copyright (c) 2017, Intel Corporation. +# +# This program is free software; you can redistribute it and/or modify it +# under the terms and conditions of the GNU General Public License, +# version 2, as published by the Free Software Foundation. +# +# This program is distributed in the hope 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. + +import os +import sys +import struct + +sys.path.append(os.environ['PERF_EXEC_PATH'] + \ + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') + +# These perf imports are not used at present +#from perf_trace_context import * +#from Core import * + +def trace_begin(): + print "Intel PT Power Events and PTWRITE" + +def trace_end(): + print "End" + +def trace_unhandled(event_name, context, event_fields_dict): + print ' '.join(['%s=%s'%(k,str(v))for k,v in sorted(event_fields_dict.items())]) + +def print_ptwrite(raw_buf): + data = struct.unpack_from("<IQ", raw_buf) + flags = data[0] + payload = data[1] + exact_ip = flags & 1 + print "IP: %u payload: %#x" % (exact_ip, payload), + +def print_cbr(raw_buf): + data = struct.unpack_from("<BBBBII", raw_buf) + cbr = data[0] + f = (data[4] + 500) / 1000 + p = ((cbr * 1000 / data[2]) + 5) / 10 + print "%3u freq: %4u MHz (%3u%%)" % (cbr, f, p), + +def print_mwait(raw_buf): + data = struct.unpack_from("<IQ", raw_buf) + payload = data[1] + hints = payload & 0xff + extensions = (payload >> 32) & 0x3 + print "hints: %#x extensions: %#x" % (hints, extensions), + +def print_pwre(raw_buf): + data = struct.unpack_from("<IQ", raw_buf) + payload = data[1] + hw = (payload >> 7) & 1 + cstate = (payload >> 12) & 0xf + subcstate = (payload >> 8) & 0xf + print "hw: %u cstate: %u sub-cstate: %u" % (hw, cstate, subcstate), + +def print_exstop(raw_buf): + data = struct.unpack_from("<I", raw_buf) + flags = data[0] + exact_ip = flags & 1 + print "IP: %u" % (exact_ip), + +def print_pwrx(raw_buf): + data = struct.unpack_from("<IQ", raw_buf) + payload = data[1] + deepest_cstate = payload & 0xf + last_cstate = (payload >> 4) & 0xf + wake_reason = (payload >> 8) & 0xf + print "deepest cstate: %u last cstate: %u wake reason: %#x" % (deepest_cstate, last_cstate, wake_reason), + +def print_common_start(comm, sample, name): + ts = sample["time"] + cpu = sample["cpu"] + pid = sample["pid"] + tid = sample["tid"] + print "%16s %5u/%-5u [%03u] %9u.%09u %7s:" % (comm, pid, tid, cpu, ts / 1000000000, ts %1000000000, name), + +def print_common_ip(sample, symbol, dso): + ip = sample["ip"] + print "%16x %s (%s)" % (ip, symbol, dso) + +def process_event(param_dict): + event_attr = param_dict["attr"] + sample = param_dict["sample"] + raw_buf = param_dict["raw_buf"] + comm = param_dict["comm"] + name = param_dict["ev_name"] + + # Symbol and dso info are not always resolved + if (param_dict.has_key("dso")): + dso = param_dict["dso"] + else: + dso = "[unknown]" + + if (param_dict.has_key("symbol")): + symbol = param_dict["symbol"] + else: + symbol = "[unknown]" + + if name == "ptwrite": + print_common_start(comm, sample, name) + print_ptwrite(raw_buf) + print_common_ip(sample, symbol, dso) + elif name == "cbr": + print_common_start(comm, sample, name) + print_cbr(raw_buf) + print_common_ip(sample, symbol, dso) + elif name == "mwait": + print_common_start(comm, sample, name) + print_mwait(raw_buf) + print_common_ip(sample, symbol, dso) + elif name == "pwre": + print_common_start(comm, sample, name) + print_pwre(raw_buf) + print_common_ip(sample, symbol, dso) + elif name == "exstop": + print_common_start(comm, sample, name) + print_exstop(raw_buf) + print_common_ip(sample, symbol, dso) + elif name == "pwrx": + print_common_start(comm, sample, name) + print_pwrx(raw_buf) + print_common_ip(sample, symbol, dso) diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c index 0dd77494bb58..0e77b2cf61ec 100644 --- a/tools/perf/tests/attr.c +++ b/tools/perf/tests/attr.c @@ -18,6 +18,7 @@ * permissions. All the event text files are stored there. */ +#include <debug.h> #include <errno.h> #include <inttypes.h> #include <stdlib.h> @@ -29,14 +30,11 @@ #include <sys/stat.h> #include <unistd.h> #include "../perf.h" -#include "util.h" #include <subcmd/exec-cmd.h> #include "tests.h" #define ENV "PERF_TEST_ATTR" -extern int verbose; - static char *dir; void test_attr__init(void) @@ -138,8 +136,10 @@ void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu, { int errno_saved = errno; - if (store_event(attr, pid, cpu, fd, group_fd, flags)) - die("test attr FAILED"); + if (store_event(attr, pid, cpu, fd, group_fd, flags)) { + pr_err("test attr FAILED"); + exit(128); + } errno = errno_saved; } diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py index 1091bd47adfd..cdf21a9d0c35 100644 --- a/tools/perf/tests/attr.py +++ b/tools/perf/tests/attr.py @@ -16,6 +16,13 @@ class Fail(Exception): def getMsg(self): return '\'%s\' - %s' % (self.test.path, self.msg) +class Notest(Exception): + def __init__(self, test, arch): + self.arch = arch + self.test = test + def getMsg(self): + return '[%s] \'%s\'' % (self.arch, self.test.path) + class Unsup(Exception): def __init__(self, test): self.test = test @@ -112,6 +119,9 @@ class Event(dict): # 'command' - perf command name # 'args' - special command arguments # 'ret' - expected command return value (0 by default) +# 'arch' - architecture specific test (optional) +# comma separated list, ! at the beginning +# negates it. # # [eventX:base] # - one or multiple instances in file @@ -134,6 +144,12 @@ class Test(object): except: self.ret = 0 + try: + self.arch = parser.get('config', 'arch') + log.warning("test limitation '%s'" % self.arch) + except: + self.arch = '' + self.expect = {} self.result = {} log.debug(" loading expected events"); @@ -145,6 +161,31 @@ class Test(object): else: return True + def skip_test(self, myarch): + # If architecture not set always run test + if self.arch == '': + # log.warning("test for arch %s is ok" % myarch) + return False + + # Allow multiple values in assignment separated by ',' + arch_list = self.arch.split(',') + + # Handle negated list such as !s390x,ppc + if arch_list[0][0] == '!': + arch_list[0] = arch_list[0][1:] + log.warning("excluded architecture list %s" % arch_list) + for arch_item in arch_list: + # log.warning("test for %s arch is %s" % (arch_item, myarch)) + if arch_item == myarch: + return True + return False + + for arch_item in arch_list: + # log.warning("test for architecture '%s' current '%s'" % (arch_item, myarch)) + if arch_item == myarch: + return False + return True + def load_events(self, path, events): parser_event = ConfigParser.SafeConfigParser() parser_event.read(path) @@ -168,6 +209,11 @@ class Test(object): events[section] = e def run_cmd(self, tempdir): + junk1, junk2, junk3, junk4, myarch = (os.uname()) + + if self.skip_test(myarch): + raise Notest(self, myarch) + cmd = "PERF_TEST_ATTR=%s %s %s -o %s/perf.data %s" % (tempdir, self.perf, self.command, tempdir, self.args) ret = os.WEXITSTATUS(os.system(cmd)) @@ -265,6 +311,8 @@ def run_tests(options): Test(f, options).run() except Unsup, obj: log.warning("unsupp %s" % obj.getMsg()) + except Notest, obj: + log.warning("skipped %s" % obj.getMsg()) def setup_log(verbose): global log diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c index 8ba2c4618fe9..39bbb97cd30a 100644 --- a/tools/perf/tests/bp_signal.c +++ b/tools/perf/tests/bp_signal.c @@ -62,8 +62,7 @@ static void __test_function(volatile long *ptr) } #endif -__attribute__ ((noinline)) -static int test_function(void) +static noinline int test_function(void) { __test_function(&the_var); the_var++; diff --git a/tools/perf/tests/bp_signal_overflow.c b/tools/perf/tests/bp_signal_overflow.c index 89f92fa67cc4..3b1ac6f31b15 100644 --- a/tools/perf/tests/bp_signal_overflow.c +++ b/tools/perf/tests/bp_signal_overflow.c @@ -28,8 +28,7 @@ static int overflows; -__attribute__ ((noinline)) -static int test_function(void) +static noinline int test_function(void) { return time(NULL); } diff --git a/tools/perf/tests/bpf-script-test-prologue.c b/tools/perf/tests/bpf-script-test-prologue.c index 7230e62c70fc..b4ebc75e25ae 100644 --- a/tools/perf/tests/bpf-script-test-prologue.c +++ b/tools/perf/tests/bpf-script-test-prologue.c @@ -10,6 +10,15 @@ #include <uapi/linux/fs.h> +/* + * If CONFIG_PROFILE_ALL_BRANCHES is selected, + * 'if' is redefined after include kernel header. + * Recover 'if' for BPF object code. + */ +#ifdef if +# undef if +#endif + #define FMODE_READ 0x1 #define FMODE_WRITE 0x2 diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index dfe5c89e2049..3e56d08f7995 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -76,8 +76,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) return strcmp((const char *) symbol, funcs[idx]); } -__attribute__ ((noinline)) -static int unwind_thread(struct thread *thread) +static noinline int unwind_thread(struct thread *thread) { struct perf_sample sample; unsigned long cnt = 0; @@ -108,8 +107,7 @@ static int unwind_thread(struct thread *thread) static int global_unwind_retval = -INT_MAX; -__attribute__ ((noinline)) -static int compare(void *p1, void *p2) +static noinline int compare(void *p1, void *p2) { /* Any possible value should be 'thread' */ struct thread *thread = *(struct thread **)p1; @@ -128,8 +126,7 @@ static int compare(void *p1, void *p2) return p1 - p2; } -__attribute__ ((noinline)) -static int krava_3(struct thread *thread) +static noinline int krava_3(struct thread *thread) { struct thread *array[2] = {thread, thread}; void *fp = &bsearch; @@ -147,14 +144,12 @@ static int krava_3(struct thread *thread) return global_unwind_retval; } -__attribute__ ((noinline)) -static int krava_2(struct thread *thread) +static noinline int krava_2(struct thread *thread) { return krava_3(thread); } -__attribute__ ((noinline)) -static int krava_1(struct thread *thread) +static noinline int krava_1(struct thread *thread) { return krava_2(thread); } diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 7fad885491c5..812a053d1941 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -1810,17 +1810,6 @@ static int test_pmu_events(void) return ret; } -static void debug_warn(const char *warn, va_list params) -{ - char msg[1024]; - - if (verbose <= 0) - return; - - vsnprintf(msg, sizeof(msg), warn, params); - fprintf(stderr, " Warning: %s\n", msg); -} - int test__parse_events(int subtest __maybe_unused) { int ret1, ret2 = 0; @@ -1832,8 +1821,6 @@ do { \ ret2 = ret1; \ } while (0) - set_warning_routine(debug_warn); - TEST_EVENTS(test__events); if (test_pmu()) diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index d990ad08a3c6..27f41f28dcb4 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -46,12 +46,15 @@ static struct annotate_browser_opt { .jump_arrows = true, }; +struct arch; + struct annotate_browser { struct ui_browser b; struct rb_root entries; struct rb_node *curr_hot; struct disasm_line *selection; struct disasm_line **offsets; + struct arch *arch; int nr_events; u64 start; int nr_asm_entries; @@ -125,43 +128,57 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int int i, pcnt_width = annotate_browser__pcnt_width(ab); double percent_max = 0.0; char bf[256]; + bool show_title = false; for (i = 0; i < ab->nr_events; i++) { if (bdl->samples[i].percent > percent_max) percent_max = bdl->samples[i].percent; } + if ((row == 0) && (dl->offset == -1 || percent_max == 0.0)) { + if (ab->have_cycles) { + if (dl->ipc == 0.0 && dl->cycles == 0) + show_title = true; + } else + show_title = true; + } + if (dl->offset != -1 && percent_max != 0.0) { - if (percent_max != 0.0) { - for (i = 0; i < ab->nr_events; i++) { - ui_browser__set_percent_color(browser, - bdl->samples[i].percent, - current_entry); - if (annotate_browser__opts.show_total_period) { - ui_browser__printf(browser, "%6" PRIu64 " ", - bdl->samples[i].nr); - } else { - ui_browser__printf(browser, "%6.2f ", - bdl->samples[i].percent); - } + for (i = 0; i < ab->nr_events; i++) { + ui_browser__set_percent_color(browser, + bdl->samples[i].percent, + current_entry); + if (annotate_browser__opts.show_total_period) { + ui_browser__printf(browser, "%6" PRIu64 " ", + bdl->samples[i].nr); + } else { + ui_browser__printf(browser, "%6.2f ", + bdl->samples[i].percent); } - } else { - ui_browser__write_nstring(browser, " ", 7 * ab->nr_events); } } else { ui_browser__set_percent_color(browser, 0, current_entry); - ui_browser__write_nstring(browser, " ", 7 * ab->nr_events); + + if (!show_title) + ui_browser__write_nstring(browser, " ", 7 * ab->nr_events); + else + ui_browser__printf(browser, "%*s", 7, "Percent"); } if (ab->have_cycles) { if (dl->ipc) ui_browser__printf(browser, "%*.2f ", IPC_WIDTH - 1, dl->ipc); - else + else if (!show_title) ui_browser__write_nstring(browser, " ", IPC_WIDTH); + else + ui_browser__printf(browser, "%*s ", IPC_WIDTH - 1, "IPC"); + if (dl->cycles) ui_browser__printf(browser, "%*" PRIu64 " ", CYCLES_WIDTH - 1, dl->cycles); - else + else if (!show_title) ui_browser__write_nstring(browser, " ", CYCLES_WIDTH); + else + ui_browser__printf(browser, "%*s ", CYCLES_WIDTH - 1, "Cycle"); } SLsmg_write_char(' '); @@ -1056,7 +1073,8 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, (nr_pcnt - 1); } - err = symbol__disassemble(sym, map, perf_evsel__env_arch(evsel), sizeof_bdl); + err = symbol__disassemble(sym, map, perf_evsel__env_arch(evsel), + sizeof_bdl, &browser.arch); if (err) { char msg[BUFSIZ]; symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg)); diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c index e99ba86158d2..d903fd493416 100644 --- a/tools/perf/ui/gtk/annotate.c +++ b/tools/perf/ui/gtk/annotate.c @@ -168,7 +168,8 @@ static int symbol__gtk_annotate(struct symbol *sym, struct map *map, if (map->dso->annotate_warned) return -1; - err = symbol__disassemble(sym, map, perf_evsel__env_arch(evsel), 0); + err = symbol__disassemble(sym, map, perf_evsel__env_arch(evsel), + 0, NULL); if (err) { char msg[BUFSIZ]; symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg)); diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index ddbd56df9187..be1caabb9290 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1379,7 +1379,9 @@ static const char *annotate__norm_arch(const char *arch_name) return normalize_arch((char *)arch_name); } -int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_name, size_t privsize) +int symbol__disassemble(struct symbol *sym, struct map *map, + const char *arch_name, size_t privsize, + struct arch **parch) { struct dso *dso = map->dso; char command[PATH_MAX * 2]; @@ -1405,6 +1407,9 @@ int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_na if (arch == NULL) return -ENOTSUP; + if (parch) + *parch = arch; + if (arch->init) { err = arch->init(arch); if (err) { @@ -1901,7 +1906,8 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map, struct rb_root source_line = RB_ROOT; u64 len; - if (symbol__disassemble(sym, map, perf_evsel__env_arch(evsel), 0) < 0) + if (symbol__disassemble(sym, map, perf_evsel__env_arch(evsel), + 0, NULL) < 0) return -1; len = symbol__size(sym); diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 948aa8e6fd39..21055034aedd 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -158,7 +158,9 @@ int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 addr); int symbol__alloc_hist(struct symbol *sym); void symbol__annotate_zero_histograms(struct symbol *sym); -int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_name, size_t privsize); +int symbol__disassemble(struct symbol *sym, struct map *map, + const char *arch_name, size_t privsize, + struct arch **parch); enum symbol_disassemble_errno { SYMBOL_ANNOTATE_ERRNO__SUCCESS = 0, diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 0daf63b9ee3e..5547457566a7 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -322,6 +322,13 @@ static int auxtrace_queues__add_event_buffer(struct auxtrace_queues *queues, return auxtrace_queues__add_buffer(queues, idx, buffer); } +static bool filter_cpu(struct perf_session *session, int cpu) +{ + unsigned long *cpu_bitmap = session->itrace_synth_opts->cpu_bitmap; + + return cpu_bitmap && cpu != -1 && !test_bit(cpu, cpu_bitmap); +} + int auxtrace_queues__add_event(struct auxtrace_queues *queues, struct perf_session *session, union perf_event *event, off_t data_offset, @@ -331,6 +338,9 @@ int auxtrace_queues__add_event(struct auxtrace_queues *queues, unsigned int idx; int err; + if (filter_cpu(session, event->auxtrace.cpu)) + return 0; + buffer = zalloc(sizeof(struct auxtrace_buffer)); if (!buffer) return -ENOMEM; @@ -947,6 +957,8 @@ void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts) synth_opts->instructions = true; synth_opts->branches = true; synth_opts->transactions = true; + synth_opts->ptwrites = true; + synth_opts->pwr_events = true; synth_opts->errors = true; synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE; synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD; @@ -1030,6 +1042,12 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str, case 'x': synth_opts->transactions = true; break; + case 'w': + synth_opts->ptwrites = true; + break; + case 'p': + synth_opts->pwr_events = true; + break; case 'e': synth_opts->errors = true; break; diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index 9f0de72d58e2..33b5e6cdf38c 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -59,6 +59,8 @@ enum itrace_period_type { * @instructions: whether to synthesize 'instructions' events * @branches: whether to synthesize 'branches' events * @transactions: whether to synthesize events for transactions + * @ptwrites: whether to synthesize events for ptwrites + * @pwr_events: whether to synthesize power events * @errors: whether to synthesize decoder error events * @dont_decode: whether to skip decoding entirely * @log: write a decoding log @@ -72,6 +74,7 @@ enum itrace_period_type { * @period: 'instructions' events period * @period_type: 'instructions' events period type * @initial_skip: skip N events at the beginning. + * @cpu_bitmap: CPUs for which to synthesize events, or NULL for all */ struct itrace_synth_opts { bool set; @@ -79,6 +82,8 @@ struct itrace_synth_opts { bool instructions; bool branches; bool transactions; + bool ptwrites; + bool pwr_events; bool errors; bool dont_decode; bool log; @@ -92,6 +97,7 @@ struct itrace_synth_opts { unsigned long long period; enum itrace_period_type period_type; unsigned long initial_skip; + unsigned long *cpu_bitmap; }; /** diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h index 0328f297a748..0175765c05b9 100644 --- a/tools/perf/util/cache.h +++ b/tools/perf/util/cache.h @@ -5,6 +5,7 @@ #include <subcmd/pager.h> #include "../ui/ui.h" +#include <linux/compiler.h> #include <linux/string.h> #define CMD_EXEC_PATH "--exec-path" @@ -24,6 +25,6 @@ static inline int is_absolute_path(const char *path) return path[0] == '/'; } -char *mkpath(const char *fmt, ...) __attribute__((format (printf, 1, 2))); +char *mkpath(const char *fmt, ...) __printf(1, 2); #endif /* __PERF_CACHE_H */ diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 8d724f0fa5a8..31a7dea248d0 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -335,32 +335,42 @@ static int perf_parse_long(const char *value, long *ret) return 0; } -static void die_bad_config(const char *name) +static void bad_config(const char *name) { if (config_file_name) - die("bad config value for '%s' in %s", name, config_file_name); - die("bad config value for '%s'", name); + pr_warning("bad config value for '%s' in %s, ignoring...\n", name, config_file_name); + else + pr_warning("bad config value for '%s', ignoring...\n", name); } -u64 perf_config_u64(const char *name, const char *value) +int perf_config_u64(u64 *dest, const char *name, const char *value) { long long ret = 0; - if (!perf_parse_llong(value, &ret)) - die_bad_config(name); - return (u64) ret; + if (!perf_parse_llong(value, &ret)) { + bad_config(name); + return -1; + } + + *dest = ret; + return 0; } -int perf_config_int(const char *name, const char *value) +int perf_config_int(int *dest, const char *name, const char *value) { long ret = 0; - if (!perf_parse_long(value, &ret)) - die_bad_config(name); - return ret; + if (!perf_parse_long(value, &ret)) { + bad_config(name); + return -1; + } + *dest = ret; + return 0; } static int perf_config_bool_or_int(const char *name, const char *value, int *is_bool) { + int ret; + *is_bool = 1; if (!value) return 1; @@ -371,7 +381,7 @@ static int perf_config_bool_or_int(const char *name, const char *value, int *is_ if (!strcasecmp(value, "false") || !strcasecmp(value, "no") || !strcasecmp(value, "off")) return 0; *is_bool = 0; - return perf_config_int(name, value); + return perf_config_int(&ret, name, value) < 0 ? -1 : ret; } int perf_config_bool(const char *name, const char *value) @@ -657,8 +667,7 @@ static int perf_config_set__init(struct perf_config_set *set) user_config = strdup(mkpath("%s/.perfconfig", home)); if (user_config == NULL) { - warning("Not enough memory to process %s/.perfconfig, " - "ignoring it.", home); + pr_warning("Not enough memory to process %s/.perfconfig, ignoring it.", home); goto out; } @@ -671,8 +680,7 @@ static int perf_config_set__init(struct perf_config_set *set) ret = 0; if (st.st_uid && (st.st_uid != geteuid())) { - warning("File %s not owned by current user or root, " - "ignoring it.", user_config); + pr_warning("File %s not owned by current user or root, ignoring it.", user_config); goto out_free; } @@ -795,7 +803,8 @@ void perf_config_set__delete(struct perf_config_set *set) */ int config_error_nonbool(const char *var) { - return error("Missing value for '%s'", var); + pr_err("Missing value for '%s'", var); + return -1; } void set_buildid_dir(const char *dir) diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h index 1a59a6b43f8b..b6bb11f3f165 100644 --- a/tools/perf/util/config.h +++ b/tools/perf/util/config.h @@ -27,8 +27,8 @@ extern const char *config_exclusive_filename; typedef int (*config_fn_t)(const char *, const char *, void *); int perf_default_config(const char *, const char *, void *); int perf_config(config_fn_t fn, void *); -int perf_config_int(const char *, const char *); -u64 perf_config_u64(const char *, const char *); +int perf_config_int(int *dest, const char *, const char *); +int perf_config_u64(u64 *dest, const char *, const char *); int perf_config_bool(const char *, const char *); int config_error_nonbool(const char *); const char *perf_etc_perfconfig(void); diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index 89d50318833d..3149b70799fd 100644 --- a/tools/perf/util/data-convert-bt.c +++ b/tools/perf/util/data-convert-bt.c @@ -1444,10 +1444,8 @@ static int convert__config(const char *var, const char *value, void *cb) { struct convert *c = cb; - if (!strcmp(var, "convert.queue-size")) { - c->queue_size = perf_config_u64(var, value); - return 0; - } + if (!strcmp(var, "convert.queue-size")) + return perf_config_u64(&c->queue_size, var, value); return 0; } diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index 8a23ea1a71c7..c818bdb1c1ab 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -4,6 +4,7 @@ #include <stdbool.h> #include <string.h> +#include <linux/compiler.h> #include "event.h" #include "../ui/helpline.h" #include "../ui/progress.h" @@ -40,16 +41,16 @@ extern int debug_data_convert; #define STRERR_BUFSIZE 128 /* For the buffer size of str_error_r */ -int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2))); +int dump_printf(const char *fmt, ...) __printf(1, 2); void trace_event(union perf_event *event); -int ui__error(const char *format, ...) __attribute__((format(printf, 1, 2))); -int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2))); +int ui__error(const char *format, ...) __printf(1, 2); +int ui__warning(const char *format, ...) __printf(1, 2); void pr_stat(const char *fmt, ...); -int eprintf(int level, int var, const char *fmt, ...) __attribute__((format(printf, 3, 4))); -int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __attribute__((format(printf, 4, 5))); +int eprintf(int level, int var, const char *fmt, ...) __printf(3, 4); +int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __printf(4, 5); int veprintf(int level, int var, const char *fmt, va_list args); int perf_debug_option(const char *str); diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 7c3fa1c8cbcd..9967c87af7a6 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -252,6 +252,127 @@ enum auxtrace_error_type { PERF_AUXTRACE_ERROR_MAX }; +/* Attribute type for custom synthesized events */ +#define PERF_TYPE_SYNTH (INT_MAX + 1U) + +/* Attribute config for custom synthesized events */ +enum perf_synth_id { + PERF_SYNTH_INTEL_PTWRITE, + PERF_SYNTH_INTEL_MWAIT, + PERF_SYNTH_INTEL_PWRE, + PERF_SYNTH_INTEL_EXSTOP, + PERF_SYNTH_INTEL_PWRX, + PERF_SYNTH_INTEL_CBR, +}; + +/* + * Raw data formats for synthesized events. Note that 4 bytes of padding are + * present to match the 'size' member of PERF_SAMPLE_RAW data which is always + * 8-byte aligned. That means we must dereference raw_data with an offset of 4. + * Refer perf_sample__synth_ptr() and perf_synth__raw_data(). It also means the + * structure sizes are 4 bytes bigger than the raw_size, refer + * perf_synth__raw_size(). + */ + +struct perf_synth_intel_ptwrite { + u32 padding; + union { + struct { + u32 ip : 1, + reserved : 31; + }; + u32 flags; + }; + u64 payload; +}; + +struct perf_synth_intel_mwait { + u32 padding; + u32 reserved; + union { + struct { + u64 hints : 8, + reserved1 : 24, + extensions : 2, + reserved2 : 30; + }; + u64 payload; + }; +}; + +struct perf_synth_intel_pwre { + u32 padding; + u32 reserved; + union { + struct { + u64 reserved1 : 7, + hw : 1, + subcstate : 4, + cstate : 4, + reserved2 : 48; + }; + u64 payload; + }; +}; + +struct perf_synth_intel_exstop { + u32 padding; + union { + struct { + u32 ip : 1, + reserved : 31; + }; + u32 flags; + }; +}; + +struct perf_synth_intel_pwrx { + u32 padding; + u32 reserved; + union { + struct { + u64 deepest_cstate : 4, + last_cstate : 4, + wake_reason : 4, + reserved1 : 52; + }; + u64 payload; + }; +}; + +struct perf_synth_intel_cbr { + u32 padding; + union { + struct { + u32 cbr : 8, + reserved1 : 8, + max_nonturbo : 8, + reserved2 : 8; + }; + u32 flags; + }; + u32 freq; + u32 reserved3; +}; + +/* + * raw_data is always 4 bytes from an 8-byte boundary, so subtract 4 to get + * 8-byte alignment. + */ +static inline void *perf_sample__synth_ptr(struct perf_sample *sample) +{ + return sample->raw_data - 4; +} + +static inline void *perf_synth__raw_data(void *p) +{ + return p + 4; +} + +#define perf_synth__raw_size(d) (sizeof(d) - 4) + +#define perf_sample__bad_synth_size(s, d) ((s)->raw_size < sizeof(d) - 4) + /* * The kernel collects the number of events it couldn't send in a stretch and * when possible sends this number in a PERF_RECORD_LOST event. The number of diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 94cea4398a13..8d601fbdd8d6 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -1,6 +1,7 @@ #ifndef __PERF_EVLIST_H #define __PERF_EVLIST_H 1 +#include <linux/compiler.h> #include <linux/kernel.h> #include <linux/refcount.h> #include <linux/list.h> @@ -34,7 +35,7 @@ struct perf_mmap { refcount_t refcnt; u64 prev; struct auxtrace_mmap auxtrace_mmap; - char event_copy[PERF_SAMPLE_MAX_SIZE] __attribute__((aligned(8))); + char event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8); }; static inline size_t diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index cda44b0e821c..6f4882f8d61f 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -11,13 +11,17 @@ #include <errno.h> #include <inttypes.h> #include <linux/bitops.h> +#include <api/fs/fs.h> #include <api/fs/tracing_path.h> #include <traceevent/event-parse.h> #include <linux/hw_breakpoint.h> #include <linux/perf_event.h> +#include <linux/compiler.h> #include <linux/err.h> #include <sys/ioctl.h> #include <sys/resource.h> +#include <sys/types.h> +#include <dirent.h> #include "asm/bug.h" #include "callchain.h" #include "cgroup.h" @@ -1441,7 +1445,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, } static int __open_attr__fprintf(FILE *fp, const char *name, const char *val, - void *priv __attribute__((unused))) + void *priv __maybe_unused) { return fprintf(fp, " %-32s %s\n", name, val); } @@ -2471,6 +2475,42 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err, return false; } +static bool find_process(const char *name) +{ + size_t len = strlen(name); + DIR *dir; + struct dirent *d; + int ret = -1; + + dir = opendir(procfs__mountpoint()); + if (!dir) + return false; + + /* Walk through the directory. */ + while (ret && (d = readdir(dir)) != NULL) { + char path[PATH_MAX]; + char *data; + size_t size; + + if ((d->d_type != DT_DIR) || + !strcmp(".", d->d_name) || + !strcmp("..", d->d_name)) + continue; + + scnprintf(path, sizeof(path), "%s/%s/comm", + procfs__mountpoint(), d->d_name); + + if (filename__read_str(path, &data, &size)) + continue; + + ret = strncmp(name, data, len); + free(data); + } + + closedir(dir); + return ret ? false : true; +} + int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, int err, char *msg, size_t size) { diff --git a/tools/perf/util/genelf_debug.c b/tools/perf/util/genelf_debug.c index 5980f7d256b1..40789d8603d0 100644 --- a/tools/perf/util/genelf_debug.c +++ b/tools/perf/util/genelf_debug.c @@ -11,6 +11,7 @@ * @remark Copyright 2007 OProfile authors * @author Philippe Elie */ +#include <linux/compiler.h> #include <sys/types.h> #include <stdio.h> #include <getopt.h> @@ -125,7 +126,7 @@ struct debug_line_header { * and filesize, last entry is followed by en empty string. */ /* follow the first program statement */ -} __attribute__((packed)); +} __packed; /* DWARF 2 spec talk only about one possible compilation unit header while * binutils can handle two flavours of dwarf 2, 32 and 64 bits, this is not @@ -138,7 +139,7 @@ struct compilation_unit_header { uhalf version; uword debug_abbrev_offset; ubyte pointer_size; -} __attribute__((packed)); +} __packed; #define DW_LNS_num_opcode (DW_LNS_set_isa + 1) diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index b5baff3007bb..76ed7d03e500 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -8,6 +8,7 @@ #include <unistd.h> #include <stdio.h> #include <stdlib.h> +#include <linux/compiler.h> #include <linux/list.h> #include <linux/kernel.h> #include <linux/bitops.h> @@ -1274,7 +1275,7 @@ error: } static int __desc_attr__fprintf(FILE *fp, const char *name, const char *val, - void *priv __attribute__((unused))) + void *priv __maybe_unused) { return fprintf(fp, ", %s = %s", name, val); } diff --git a/tools/perf/util/help-unknown-cmd.c b/tools/perf/util/help-unknown-cmd.c index 1c88ad6425b8..15b95300d7f3 100644 --- a/tools/perf/util/help-unknown-cmd.c +++ b/tools/perf/util/help-unknown-cmd.c @@ -12,7 +12,7 @@ static int perf_unknown_cmd_config(const char *var, const char *value, void *cb __maybe_unused) { if (!strcmp(var, "help.autocorrect")) - autocorrect = perf_config_int(var,value); + return perf_config_int(&autocorrect, var,value); return 0; } diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c index b2834ac7b1f5..218ee2bac9a5 100644 --- a/tools/perf/util/intel-bts.c +++ b/tools/perf/util/intel-bts.c @@ -866,8 +866,6 @@ static void intel_bts_print_info(u64 *arr, int start, int finish) fprintf(stdout, intel_bts_info_fmts[i], arr[i]); } -u64 intel_bts_auxtrace_info_priv[INTEL_BTS_AUXTRACE_PRIV_SIZE]; - int intel_bts_process_auxtrace_info(union perf_event *event, struct perf_session *session) { diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index 7cf7f7aca4d2..aa1593ce551d 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -64,6 +64,25 @@ enum intel_pt_pkt_state { INTEL_PT_STATE_FUP_NO_TIP, }; +static inline bool intel_pt_sample_time(enum intel_pt_pkt_state pkt_state) +{ + switch (pkt_state) { + case INTEL_PT_STATE_NO_PSB: + case INTEL_PT_STATE_NO_IP: + case INTEL_PT_STATE_ERR_RESYNC: + case INTEL_PT_STATE_IN_SYNC: + case INTEL_PT_STATE_TNT: + return true; + case INTEL_PT_STATE_TIP: + case INTEL_PT_STATE_TIP_PGD: + case INTEL_PT_STATE_FUP: + case INTEL_PT_STATE_FUP_NO_TIP: + return false; + default: + return true; + }; +} + #ifdef INTEL_PT_STRICT #define INTEL_PT_STATE_ERR1 INTEL_PT_STATE_NO_PSB #define INTEL_PT_STATE_ERR2 INTEL_PT_STATE_NO_PSB @@ -87,11 +106,13 @@ struct intel_pt_decoder { const unsigned char *buf; size_t len; bool return_compression; + bool branch_enable; bool mtc_insn; bool pge; bool have_tma; bool have_cyc; bool fixup_last_mtc; + bool have_last_ip; uint64_t pos; uint64_t last_ip; uint64_t ip; @@ -99,6 +120,7 @@ struct intel_pt_decoder { uint64_t timestamp; uint64_t tsc_timestamp; uint64_t ref_timestamp; + uint64_t sample_timestamp; uint64_t ret_addr; uint64_t ctc_timestamp; uint64_t ctc_delta; @@ -119,6 +141,7 @@ struct intel_pt_decoder { int pkt_len; int last_packet_type; unsigned int cbr; + unsigned int cbr_seen; unsigned int max_non_turbo_ratio; double max_non_turbo_ratio_fp; double cbr_cyc_to_tsc; @@ -136,9 +159,18 @@ struct intel_pt_decoder { bool continuous_period; bool overflow; bool set_fup_tx_flags; + bool set_fup_ptw; + bool set_fup_mwait; + bool set_fup_pwre; + bool set_fup_exstop; unsigned int fup_tx_flags; unsigned int tx_flags; + uint64_t fup_ptw_payload; + uint64_t fup_mwait_payload; + uint64_t fup_pwre_payload; + uint64_t cbr_payload; uint64_t timestamp_insn_cnt; + uint64_t sample_insn_cnt; uint64_t stuck_ip; int no_progress; int stuck_ip_prd; @@ -192,6 +224,7 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params) decoder->pgd_ip = params->pgd_ip; decoder->data = params->data; decoder->return_compression = params->return_compression; + decoder->branch_enable = params->branch_enable; decoder->period = params->period; decoder->period_type = params->period_type; @@ -398,6 +431,7 @@ static uint64_t intel_pt_calc_ip(const struct intel_pt_pkt *packet, static inline void intel_pt_set_last_ip(struct intel_pt_decoder *decoder) { decoder->last_ip = intel_pt_calc_ip(&decoder->packet, decoder->last_ip); + decoder->have_last_ip = true; } static inline void intel_pt_set_ip(struct intel_pt_decoder *decoder) @@ -635,6 +669,8 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info) case INTEL_PT_PAD: case INTEL_PT_VMCS: case INTEL_PT_MNT: + case INTEL_PT_PTWRITE: + case INTEL_PT_PTWRITE_IP: return 0; case INTEL_PT_MTC: @@ -675,6 +711,12 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info) break; case INTEL_PT_TSC: + /* + * For now, do not support using TSC packets - refer + * intel_pt_calc_cyc_to_tsc(). + */ + if (data->from_mtc) + return 1; timestamp = pkt_info->packet.payload | (data->timestamp & (0xffULL << 56)); if (data->from_mtc && timestamp < data->timestamp && @@ -733,6 +775,11 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info) case INTEL_PT_TIP_PGD: case INTEL_PT_TRACESTOP: + case INTEL_PT_EXSTOP: + case INTEL_PT_EXSTOP_IP: + case INTEL_PT_MWAIT: + case INTEL_PT_PWRE: + case INTEL_PT_PWRX: case INTEL_PT_OVF: case INTEL_PT_BAD: /* Does not happen */ default: @@ -787,6 +834,14 @@ static void intel_pt_calc_cyc_to_tsc(struct intel_pt_decoder *decoder, .cbr_cyc_to_tsc = 0, }; + /* + * For now, do not support using TSC packets for at least the reasons: + * 1) timing might have stopped + * 2) TSC packets within PSB+ can slip against CYC packets + */ + if (!from_mtc) + return; + intel_pt_pkt_lookahead(decoder, intel_pt_calc_cyc_cb, &data); } @@ -898,6 +953,7 @@ static int intel_pt_walk_insn(struct intel_pt_decoder *decoder, decoder->tot_insn_cnt += insn_cnt; decoder->timestamp_insn_cnt += insn_cnt; + decoder->sample_insn_cnt += insn_cnt; decoder->period_insn_cnt += insn_cnt; if (err) { @@ -990,6 +1046,57 @@ out_no_progress: return err; } +static bool intel_pt_fup_event(struct intel_pt_decoder *decoder) +{ + bool ret = false; + + if (decoder->set_fup_tx_flags) { + decoder->set_fup_tx_flags = false; + decoder->tx_flags = decoder->fup_tx_flags; + decoder->state.type = INTEL_PT_TRANSACTION; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.flags = decoder->fup_tx_flags; + return true; + } + if (decoder->set_fup_ptw) { + decoder->set_fup_ptw = false; + decoder->state.type = INTEL_PT_PTW; + decoder->state.flags |= INTEL_PT_FUP_IP; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.ptw_payload = decoder->fup_ptw_payload; + return true; + } + if (decoder->set_fup_mwait) { + decoder->set_fup_mwait = false; + decoder->state.type = INTEL_PT_MWAIT_OP; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.mwait_payload = decoder->fup_mwait_payload; + ret = true; + } + if (decoder->set_fup_pwre) { + decoder->set_fup_pwre = false; + decoder->state.type |= INTEL_PT_PWR_ENTRY; + decoder->state.type &= ~INTEL_PT_BRANCH; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.pwre_payload = decoder->fup_pwre_payload; + ret = true; + } + if (decoder->set_fup_exstop) { + decoder->set_fup_exstop = false; + decoder->state.type |= INTEL_PT_EX_STOP; + decoder->state.type &= ~INTEL_PT_BRANCH; + decoder->state.flags |= INTEL_PT_FUP_IP; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + ret = true; + } + return ret; +} + static int intel_pt_walk_fup(struct intel_pt_decoder *decoder) { struct intel_pt_insn intel_pt_insn; @@ -1003,15 +1110,8 @@ static int intel_pt_walk_fup(struct intel_pt_decoder *decoder) if (err == INTEL_PT_RETURN) return 0; if (err == -EAGAIN) { - if (decoder->set_fup_tx_flags) { - decoder->set_fup_tx_flags = false; - decoder->tx_flags = decoder->fup_tx_flags; - decoder->state.type = INTEL_PT_TRANSACTION; - decoder->state.from_ip = decoder->ip; - decoder->state.to_ip = 0; - decoder->state.flags = decoder->fup_tx_flags; + if (intel_pt_fup_event(decoder)) return 0; - } return err; } decoder->set_fup_tx_flags = false; @@ -1360,7 +1460,9 @@ static void intel_pt_calc_mtc_timestamp(struct intel_pt_decoder *decoder) static void intel_pt_calc_cbr(struct intel_pt_decoder *decoder) { - unsigned int cbr = decoder->packet.payload; + unsigned int cbr = decoder->packet.payload & 0xff; + + decoder->cbr_payload = decoder->packet.payload; if (decoder->cbr == cbr) return; @@ -1417,6 +1519,13 @@ static int intel_pt_walk_psbend(struct intel_pt_decoder *decoder) case INTEL_PT_TRACESTOP: case INTEL_PT_BAD: case INTEL_PT_PSB: + case INTEL_PT_PTWRITE: + case INTEL_PT_PTWRITE_IP: + case INTEL_PT_EXSTOP: + case INTEL_PT_EXSTOP_IP: + case INTEL_PT_MWAIT: + case INTEL_PT_PWRE: + case INTEL_PT_PWRX: decoder->have_tma = false; intel_pt_log("ERROR: Unexpected packet\n"); return -EAGAIN; @@ -1446,7 +1555,8 @@ static int intel_pt_walk_psbend(struct intel_pt_decoder *decoder) case INTEL_PT_FUP: decoder->pge = true; - intel_pt_set_last_ip(decoder); + if (decoder->packet.count) + intel_pt_set_last_ip(decoder); break; case INTEL_PT_MODE_TSX: @@ -1497,6 +1607,13 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder) case INTEL_PT_MODE_TSX: case INTEL_PT_BAD: case INTEL_PT_PSBEND: + case INTEL_PT_PTWRITE: + case INTEL_PT_PTWRITE_IP: + case INTEL_PT_EXSTOP: + case INTEL_PT_EXSTOP_IP: + case INTEL_PT_MWAIT: + case INTEL_PT_PWRE: + case INTEL_PT_PWRX: intel_pt_log("ERROR: Missing TIP after FUP\n"); decoder->pkt_state = INTEL_PT_STATE_ERR3; return -ENOENT; @@ -1625,6 +1742,15 @@ next: break; } intel_pt_set_last_ip(decoder); + if (!decoder->branch_enable) { + decoder->ip = decoder->last_ip; + if (intel_pt_fup_event(decoder)) + return 0; + no_tip = false; + break; + } + if (decoder->set_fup_mwait) + no_tip = true; err = intel_pt_walk_fup(decoder); if (err != -EAGAIN) { if (err) @@ -1650,6 +1776,8 @@ next: break; case INTEL_PT_PSB: + decoder->last_ip = 0; + decoder->have_last_ip = true; intel_pt_clear_stack(&decoder->stack); err = intel_pt_walk_psbend(decoder); if (err == -EAGAIN) @@ -1696,6 +1824,16 @@ next: case INTEL_PT_CBR: intel_pt_calc_cbr(decoder); + if (!decoder->branch_enable && + decoder->cbr != decoder->cbr_seen) { + decoder->cbr_seen = decoder->cbr; + decoder->state.type = INTEL_PT_CBR_CHG; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.cbr_payload = + decoder->packet.payload; + return 0; + } break; case INTEL_PT_MODE_EXEC: @@ -1722,6 +1860,71 @@ next: case INTEL_PT_PAD: break; + case INTEL_PT_PTWRITE_IP: + decoder->fup_ptw_payload = decoder->packet.payload; + err = intel_pt_get_next_packet(decoder); + if (err) + return err; + if (decoder->packet.type == INTEL_PT_FUP) { + decoder->set_fup_ptw = true; + no_tip = true; + } else { + intel_pt_log_at("ERROR: Missing FUP after PTWRITE", + decoder->pos); + } + goto next; + + case INTEL_PT_PTWRITE: + decoder->state.type = INTEL_PT_PTW; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.ptw_payload = decoder->packet.payload; + return 0; + + case INTEL_PT_MWAIT: + decoder->fup_mwait_payload = decoder->packet.payload; + decoder->set_fup_mwait = true; + break; + + case INTEL_PT_PWRE: + if (decoder->set_fup_mwait) { + decoder->fup_pwre_payload = + decoder->packet.payload; + decoder->set_fup_pwre = true; + break; + } + decoder->state.type = INTEL_PT_PWR_ENTRY; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.pwrx_payload = decoder->packet.payload; + return 0; + + case INTEL_PT_EXSTOP_IP: + err = intel_pt_get_next_packet(decoder); + if (err) + return err; + if (decoder->packet.type == INTEL_PT_FUP) { + decoder->set_fup_exstop = true; + no_tip = true; + } else { + intel_pt_log_at("ERROR: Missing FUP after EXSTOP", + decoder->pos); + } + goto next; + + case INTEL_PT_EXSTOP: + decoder->state.type = INTEL_PT_EX_STOP; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + return 0; + + case INTEL_PT_PWRX: + decoder->state.type = INTEL_PT_PWR_EXIT; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.pwrx_payload = decoder->packet.payload; + return 0; + default: return intel_pt_bug(decoder); } @@ -1730,8 +1933,9 @@ next: static inline bool intel_pt_have_ip(struct intel_pt_decoder *decoder) { - return decoder->last_ip || decoder->packet.count == 0 || - decoder->packet.count == 3 || decoder->packet.count == 6; + return decoder->packet.count && + (decoder->have_last_ip || decoder->packet.count == 3 || + decoder->packet.count == 6); } /* Walk PSB+ packets to get in sync. */ @@ -1750,6 +1954,13 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder) __fallthrough; case INTEL_PT_TIP_PGE: case INTEL_PT_TIP: + case INTEL_PT_PTWRITE: + case INTEL_PT_PTWRITE_IP: + case INTEL_PT_EXSTOP: + case INTEL_PT_EXSTOP_IP: + case INTEL_PT_MWAIT: + case INTEL_PT_PWRE: + case INTEL_PT_PWRX: intel_pt_log("ERROR: Unexpected packet\n"); return -ENOENT; @@ -1854,14 +2065,10 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder) break; case INTEL_PT_FUP: - if (decoder->overflow) { - if (intel_pt_have_ip(decoder)) - intel_pt_set_ip(decoder); - if (decoder->ip) - return 0; - } - if (decoder->packet.count) - intel_pt_set_last_ip(decoder); + if (intel_pt_have_ip(decoder)) + intel_pt_set_ip(decoder); + if (decoder->ip) + return 0; break; case INTEL_PT_MTC: @@ -1910,6 +2117,9 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder) break; case INTEL_PT_PSB: + decoder->last_ip = 0; + decoder->have_last_ip = true; + intel_pt_clear_stack(&decoder->stack); err = intel_pt_walk_psb(decoder); if (err) return err; @@ -1925,6 +2135,13 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder) case INTEL_PT_VMCS: case INTEL_PT_MNT: case INTEL_PT_PAD: + case INTEL_PT_PTWRITE: + case INTEL_PT_PTWRITE_IP: + case INTEL_PT_EXSTOP: + case INTEL_PT_EXSTOP_IP: + case INTEL_PT_MWAIT: + case INTEL_PT_PWRE: + case INTEL_PT_PWRX: default: break; } @@ -1935,6 +2152,19 @@ static int intel_pt_sync_ip(struct intel_pt_decoder *decoder) { int err; + decoder->set_fup_tx_flags = false; + decoder->set_fup_ptw = false; + decoder->set_fup_mwait = false; + decoder->set_fup_pwre = false; + decoder->set_fup_exstop = false; + + if (!decoder->branch_enable) { + decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; + decoder->overflow = false; + decoder->state.type = 0; /* Do not have a sample */ + return 0; + } + intel_pt_log("Scanning for full IP\n"); err = intel_pt_walk_to_ip(decoder); if (err) @@ -2043,6 +2273,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder) decoder->pge = false; decoder->continuous_period = false; + decoder->have_last_ip = false; decoder->last_ip = 0; decoder->ip = 0; intel_pt_clear_stack(&decoder->stack); @@ -2051,6 +2282,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder) if (err) return err; + decoder->have_last_ip = true; decoder->pkt_state = INTEL_PT_STATE_NO_IP; err = intel_pt_walk_psb(decoder); @@ -2069,7 +2301,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder) static uint64_t intel_pt_est_timestamp(struct intel_pt_decoder *decoder) { - uint64_t est = decoder->timestamp_insn_cnt << 1; + uint64_t est = decoder->sample_insn_cnt << 1; if (!decoder->cbr || !decoder->max_non_turbo_ratio) goto out; @@ -2077,7 +2309,7 @@ static uint64_t intel_pt_est_timestamp(struct intel_pt_decoder *decoder) est *= decoder->max_non_turbo_ratio; est /= decoder->cbr; out: - return decoder->timestamp + est; + return decoder->sample_timestamp + est; } const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder) @@ -2093,8 +2325,10 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder) err = intel_pt_sync(decoder); break; case INTEL_PT_STATE_NO_IP: + decoder->have_last_ip = false; decoder->last_ip = 0; - /* Fall through */ + decoder->ip = 0; + __fallthrough; case INTEL_PT_STATE_ERR_RESYNC: err = intel_pt_sync_ip(decoder); break; @@ -2130,15 +2364,29 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder) } } while (err == -ENOLINK); - decoder->state.err = err ? intel_pt_ext_err(err) : 0; - decoder->state.timestamp = decoder->timestamp; + if (err) { + decoder->state.err = intel_pt_ext_err(err); + decoder->state.from_ip = decoder->ip; + decoder->sample_timestamp = decoder->timestamp; + decoder->sample_insn_cnt = decoder->timestamp_insn_cnt; + } else { + decoder->state.err = 0; + if (decoder->cbr != decoder->cbr_seen && decoder->state.type) { + decoder->cbr_seen = decoder->cbr; + decoder->state.type |= INTEL_PT_CBR_CHG; + decoder->state.cbr_payload = decoder->cbr_payload; + } + if (intel_pt_sample_time(decoder->pkt_state)) { + decoder->sample_timestamp = decoder->timestamp; + decoder->sample_insn_cnt = decoder->timestamp_insn_cnt; + } + } + + decoder->state.timestamp = decoder->sample_timestamp; decoder->state.est_timestamp = intel_pt_est_timestamp(decoder); decoder->state.cr3 = decoder->cr3; decoder->state.tot_insn_cnt = decoder->tot_insn_cnt; - if (err) - decoder->state.from_ip = decoder->ip; - return &decoder->state; } diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h index e90619a43c0c..921b22e8ca0e 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h @@ -25,11 +25,18 @@ #define INTEL_PT_IN_TX (1 << 0) #define INTEL_PT_ABORT_TX (1 << 1) #define INTEL_PT_ASYNC (1 << 2) +#define INTEL_PT_FUP_IP (1 << 3) enum intel_pt_sample_type { INTEL_PT_BRANCH = 1 << 0, INTEL_PT_INSTRUCTION = 1 << 1, INTEL_PT_TRANSACTION = 1 << 2, + INTEL_PT_PTW = 1 << 3, + INTEL_PT_MWAIT_OP = 1 << 4, + INTEL_PT_PWR_ENTRY = 1 << 5, + INTEL_PT_EX_STOP = 1 << 6, + INTEL_PT_PWR_EXIT = 1 << 7, + INTEL_PT_CBR_CHG = 1 << 8, }; enum intel_pt_period_type { @@ -63,6 +70,11 @@ struct intel_pt_state { uint64_t timestamp; uint64_t est_timestamp; uint64_t trace_nr; + uint64_t ptw_payload; + uint64_t mwait_payload; + uint64_t pwre_payload; + uint64_t pwrx_payload; + uint64_t cbr_payload; uint32_t flags; enum intel_pt_insn_op insn_op; int insn_len; @@ -87,6 +99,7 @@ struct intel_pt_params { bool (*pgd_ip)(uint64_t ip, void *data); void *data; bool return_compression; + bool branch_enable; uint64_t period; enum intel_pt_period_type period_type; unsigned max_non_turbo_ratio; diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.h b/tools/perf/util/intel-pt-decoder/intel-pt-log.h index debe751dc3d6..45b64f93f358 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-log.h +++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.h @@ -16,6 +16,7 @@ #ifndef INCLUDE__INTEL_PT_LOG_H__ #define INCLUDE__INTEL_PT_LOG_H__ +#include <linux/compiler.h> #include <stdint.h> #include <inttypes.h> @@ -34,8 +35,7 @@ void __intel_pt_log_insn(struct intel_pt_insn *intel_pt_insn, uint64_t ip); void __intel_pt_log_insn_no_data(struct intel_pt_insn *intel_pt_insn, uint64_t ip); -__attribute__((format(printf, 1, 2))) -void __intel_pt_log(const char *fmt, ...); +void __intel_pt_log(const char *fmt, ...) __printf(1, 2); #define intel_pt_log(fmt, ...) \ do { \ diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c index 7528ae4f7e28..ba4c9dd18643 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c @@ -64,6 +64,13 @@ static const char * const packet_name[] = { [INTEL_PT_PIP] = "PIP", [INTEL_PT_OVF] = "OVF", [INTEL_PT_MNT] = "MNT", + [INTEL_PT_PTWRITE] = "PTWRITE", + [INTEL_PT_PTWRITE_IP] = "PTWRITE", + [INTEL_PT_EXSTOP] = "EXSTOP", + [INTEL_PT_EXSTOP_IP] = "EXSTOP", + [INTEL_PT_MWAIT] = "MWAIT", + [INTEL_PT_PWRE] = "PWRE", + [INTEL_PT_PWRX] = "PWRX", }; const char *intel_pt_pkt_name(enum intel_pt_pkt_type type) @@ -123,7 +130,7 @@ static int intel_pt_get_cbr(const unsigned char *buf, size_t len, if (len < 4) return INTEL_PT_NEED_MORE_BYTES; packet->type = INTEL_PT_CBR; - packet->payload = buf[2]; + packet->payload = le16_to_cpu(*(uint16_t *)(buf + 2)); return 4; } @@ -217,12 +224,80 @@ static int intel_pt_get_3byte(const unsigned char *buf, size_t len, } } +static int intel_pt_get_ptwrite(const unsigned char *buf, size_t len, + struct intel_pt_pkt *packet) +{ + packet->count = (buf[1] >> 5) & 0x3; + packet->type = buf[1] & BIT(7) ? INTEL_PT_PTWRITE_IP : + INTEL_PT_PTWRITE; + + switch (packet->count) { + case 0: + if (len < 6) + return INTEL_PT_NEED_MORE_BYTES; + packet->payload = le32_to_cpu(*(uint32_t *)(buf + 2)); + return 6; + case 1: + if (len < 10) + return INTEL_PT_NEED_MORE_BYTES; + packet->payload = le64_to_cpu(*(uint64_t *)(buf + 2)); + return 10; + default: + return INTEL_PT_BAD_PACKET; + } +} + +static int intel_pt_get_exstop(struct intel_pt_pkt *packet) +{ + packet->type = INTEL_PT_EXSTOP; + return 2; +} + +static int intel_pt_get_exstop_ip(struct intel_pt_pkt *packet) +{ + packet->type = INTEL_PT_EXSTOP_IP; + return 2; +} + +static int intel_pt_get_mwait(const unsigned char *buf, size_t len, + struct intel_pt_pkt *packet) +{ + if (len < 10) + return INTEL_PT_NEED_MORE_BYTES; + packet->type = INTEL_PT_MWAIT; + packet->payload = le64_to_cpu(*(uint64_t *)(buf + 2)); + return 10; +} + +static int intel_pt_get_pwre(const unsigned char *buf, size_t len, + struct intel_pt_pkt *packet) +{ + if (len < 4) + return INTEL_PT_NEED_MORE_BYTES; + packet->type = INTEL_PT_PWRE; + memcpy_le64(&packet->payload, buf + 2, 2); + return 4; +} + +static int intel_pt_get_pwrx(const unsigned char *buf, size_t len, + struct intel_pt_pkt *packet) +{ + if (len < 7) + return INTEL_PT_NEED_MORE_BYTES; + packet->type = INTEL_PT_PWRX; + memcpy_le64(&packet->payload, buf + 2, 5); + return 7; +} + static int intel_pt_get_ext(const unsigned char *buf, size_t len, struct intel_pt_pkt *packet) { if (len < 2) return INTEL_PT_NEED_MORE_BYTES; + if ((buf[1] & 0x1f) == 0x12) + return intel_pt_get_ptwrite(buf, len, packet); + switch (buf[1]) { case 0xa3: /* Long TNT */ return intel_pt_get_long_tnt(buf, len, packet); @@ -244,6 +319,16 @@ static int intel_pt_get_ext(const unsigned char *buf, size_t len, return intel_pt_get_tma(buf, len, packet); case 0xC3: /* 3-byte header */ return intel_pt_get_3byte(buf, len, packet); + case 0x62: /* EXSTOP no IP */ + return intel_pt_get_exstop(packet); + case 0xE2: /* EXSTOP with IP */ + return intel_pt_get_exstop_ip(packet); + case 0xC2: /* MWAIT */ + return intel_pt_get_mwait(buf, len, packet); + case 0x22: /* PWRE */ + return intel_pt_get_pwre(buf, len, packet); + case 0xA2: /* PWRX */ + return intel_pt_get_pwrx(buf, len, packet); default: return INTEL_PT_BAD_PACKET; } @@ -522,6 +607,29 @@ int intel_pt_pkt_desc(const struct intel_pt_pkt *packet, char *buf, ret = snprintf(buf, buf_len, "%s 0x%llx (NR=%d)", name, payload, nr); return ret; + case INTEL_PT_PTWRITE: + return snprintf(buf, buf_len, "%s 0x%llx IP:0", name, payload); + case INTEL_PT_PTWRITE_IP: + return snprintf(buf, buf_len, "%s 0x%llx IP:1", name, payload); + case INTEL_PT_EXSTOP: + return snprintf(buf, buf_len, "%s IP:0", name); + case INTEL_PT_EXSTOP_IP: + return snprintf(buf, buf_len, "%s IP:1", name); + case INTEL_PT_MWAIT: + return snprintf(buf, buf_len, "%s 0x%llx Hints 0x%x Extensions 0x%x", + name, payload, (unsigned int)(payload & 0xff), + (unsigned int)((payload >> 32) & 0x3)); + case INTEL_PT_PWRE: + return snprintf(buf, buf_len, "%s 0x%llx HW:%u CState:%u Sub-CState:%u", + name, payload, !!(payload & 0x80), + (unsigned int)((payload >> 12) & 0xf), + (unsigned int)((payload >> 8) & 0xf)); + case INTEL_PT_PWRX: + return snprintf(buf, buf_len, "%s 0x%llx Last CState:%u Deepest CState:%u Wake Reason 0x%x", + name, payload, + (unsigned int)((payload >> 4) & 0xf), + (unsigned int)(payload & 0xf), + (unsigned int)((payload >> 8) & 0xf)); default: break; } diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.h index 781bb79883bd..73ddc3a88d07 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.h +++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.h @@ -52,6 +52,13 @@ enum intel_pt_pkt_type { INTEL_PT_PIP, INTEL_PT_OVF, INTEL_PT_MNT, + INTEL_PT_PTWRITE, + INTEL_PT_PTWRITE_IP, + INTEL_PT_EXSTOP, + INTEL_PT_EXSTOP_IP, + INTEL_PT_MWAIT, + INTEL_PT_PWRE, + INTEL_PT_PWRX, }; struct intel_pt_pkt { diff --git a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt index 767be7c76034..12e377184ee4 100644 --- a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt +++ b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt @@ -1009,7 +1009,7 @@ GrpTable: Grp15 1: fxstor | RDGSBASE Ry (F3),(11B) 2: vldmxcsr Md (v1) | WRFSBASE Ry (F3),(11B) 3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B) -4: XSAVE +4: XSAVE | ptwrite Ey (F3),(11B) 5: XRSTOR | lfence (11B) 6: XSAVEOPT | clwb (66) | mfence (11B) 7: clflush | clflushopt (66) | sfence (11B) diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 4c7718f87a08..b58f9fd1e2ee 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -81,7 +81,6 @@ struct intel_pt { bool sample_instructions; u64 instructions_sample_type; - u64 instructions_sample_period; u64 instructions_id; bool sample_branches; @@ -93,6 +92,18 @@ struct intel_pt { u64 transactions_sample_type; u64 transactions_id; + bool sample_ptwrites; + u64 ptwrites_sample_type; + u64 ptwrites_id; + + bool sample_pwr_events; + u64 pwr_events_sample_type; + u64 mwait_id; + u64 pwre_id; + u64 exstop_id; + u64 pwrx_id; + u64 cbr_id; + bool synth_needs_swap; u64 tsc_bit; @@ -103,6 +114,7 @@ struct intel_pt { u64 cyc_bit; u64 noretcomp_bit; unsigned max_non_turbo_ratio; + unsigned cbr2khz; unsigned long num_events; @@ -668,6 +680,19 @@ static bool intel_pt_return_compression(struct intel_pt *pt) return true; } +static bool intel_pt_branch_enable(struct intel_pt *pt) +{ + struct perf_evsel *evsel; + u64 config; + + evlist__for_each_entry(pt->session->evlist, evsel) { + if (intel_pt_get_config(pt, &evsel->attr, &config) && + (config & 1) && !(config & 0x2000)) + return false; + } + return true; +} + static unsigned int intel_pt_mtc_period(struct intel_pt *pt) { struct perf_evsel *evsel; @@ -799,6 +824,7 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt, params.walk_insn = intel_pt_walk_next_insn; params.data = ptq; params.return_compression = intel_pt_return_compression(pt); + params.branch_enable = intel_pt_branch_enable(pt); params.max_non_turbo_ratio = pt->max_non_turbo_ratio; params.mtc_period = intel_pt_mtc_period(pt); params.tsc_ctc_ratio_n = pt->tsc_ctc_ratio_n; @@ -1044,6 +1070,36 @@ static void intel_pt_update_last_branch_rb(struct intel_pt_queue *ptq) bs->nr += 1; } +static inline bool intel_pt_skip_event(struct intel_pt *pt) +{ + return pt->synth_opts.initial_skip && + pt->num_events++ < pt->synth_opts.initial_skip; +} + +static void intel_pt_prep_b_sample(struct intel_pt *pt, + struct intel_pt_queue *ptq, + union perf_event *event, + struct perf_sample *sample) +{ + event->sample.header.type = PERF_RECORD_SAMPLE; + event->sample.header.misc = PERF_RECORD_MISC_USER; + event->sample.header.size = sizeof(struct perf_event_header); + + if (!pt->timeless_decoding) + sample->time = tsc_to_perf_time(ptq->timestamp, &pt->tc); + + sample->cpumode = PERF_RECORD_MISC_USER; + sample->ip = ptq->state->from_ip; + sample->pid = ptq->pid; + sample->tid = ptq->tid; + sample->addr = ptq->state->to_ip; + sample->period = 1; + sample->cpu = ptq->cpu; + sample->flags = ptq->flags; + sample->insn_len = ptq->insn_len; + memcpy(sample->insn, ptq->insn, INTEL_PT_INSN_BUF_SZ); +} + static int intel_pt_inject_event(union perf_event *event, struct perf_sample *sample, u64 type, bool swapped) @@ -1052,9 +1108,35 @@ static int intel_pt_inject_event(union perf_event *event, return perf_event__synthesize_sample(event, type, 0, sample, swapped); } -static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq) +static inline int intel_pt_opt_inject(struct intel_pt *pt, + union perf_event *event, + struct perf_sample *sample, u64 type) +{ + if (!pt->synth_opts.inject) + return 0; + + return intel_pt_inject_event(event, sample, type, pt->synth_needs_swap); +} + +static int intel_pt_deliver_synth_b_event(struct intel_pt *pt, + union perf_event *event, + struct perf_sample *sample, u64 type) { int ret; + + ret = intel_pt_opt_inject(pt, event, sample, type); + if (ret) + return ret; + + ret = perf_session__deliver_synth_event(pt->session, event, sample); + if (ret) + pr_err("Intel PT: failed to deliver event, error %d\n", ret); + + return ret; +} + +static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq) +{ struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; struct perf_sample sample = { .ip = 0, }; @@ -1066,29 +1148,13 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq) if (pt->branches_filter && !(pt->branches_filter & ptq->flags)) return 0; - if (pt->synth_opts.initial_skip && - pt->num_events++ < pt->synth_opts.initial_skip) + if (intel_pt_skip_event(pt)) return 0; - event->sample.header.type = PERF_RECORD_SAMPLE; - event->sample.header.misc = PERF_RECORD_MISC_USER; - event->sample.header.size = sizeof(struct perf_event_header); + intel_pt_prep_b_sample(pt, ptq, event, &sample); - if (!pt->timeless_decoding) - sample.time = tsc_to_perf_time(ptq->timestamp, &pt->tc); - - sample.cpumode = PERF_RECORD_MISC_USER; - sample.ip = ptq->state->from_ip; - sample.pid = ptq->pid; - sample.tid = ptq->tid; - sample.addr = ptq->state->to_ip; sample.id = ptq->pt->branches_id; sample.stream_id = ptq->pt->branches_id; - sample.period = 1; - sample.cpu = ptq->cpu; - sample.flags = ptq->flags; - sample.insn_len = ptq->insn_len; - memcpy(sample.insn, ptq->insn, INTEL_PT_INSN_BUF_SZ); /* * perf report cannot handle events without a branch stack when using @@ -1105,144 +1171,251 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq) sample.branch_stack = (struct branch_stack *)&dummy_bs; } - if (pt->synth_opts.inject) { - ret = intel_pt_inject_event(event, &sample, - pt->branches_sample_type, - pt->synth_needs_swap); - if (ret) - return ret; + return intel_pt_deliver_synth_b_event(pt, event, &sample, + pt->branches_sample_type); +} + +static void intel_pt_prep_sample(struct intel_pt *pt, + struct intel_pt_queue *ptq, + union perf_event *event, + struct perf_sample *sample) +{ + intel_pt_prep_b_sample(pt, ptq, event, sample); + + if (pt->synth_opts.callchain) { + thread_stack__sample(ptq->thread, ptq->chain, + pt->synth_opts.callchain_sz, sample->ip); + sample->callchain = ptq->chain; } - ret = perf_session__deliver_synth_event(pt->session, event, &sample); - if (ret) - pr_err("Intel Processor Trace: failed to deliver branch event, error %d\n", - ret); + if (pt->synth_opts.last_branch) { + intel_pt_copy_last_branch_rb(ptq); + sample->branch_stack = ptq->last_branch; + } +} + +static inline int intel_pt_deliver_synth_event(struct intel_pt *pt, + struct intel_pt_queue *ptq, + union perf_event *event, + struct perf_sample *sample, + u64 type) +{ + int ret; + + ret = intel_pt_deliver_synth_b_event(pt, event, sample, type); + + if (pt->synth_opts.last_branch) + intel_pt_reset_last_branch_rb(ptq); return ret; } static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq) { - int ret; struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; struct perf_sample sample = { .ip = 0, }; - if (pt->synth_opts.initial_skip && - pt->num_events++ < pt->synth_opts.initial_skip) + if (intel_pt_skip_event(pt)) return 0; - event->sample.header.type = PERF_RECORD_SAMPLE; - event->sample.header.misc = PERF_RECORD_MISC_USER; - event->sample.header.size = sizeof(struct perf_event_header); - - if (!pt->timeless_decoding) - sample.time = tsc_to_perf_time(ptq->timestamp, &pt->tc); + intel_pt_prep_sample(pt, ptq, event, &sample); - sample.cpumode = PERF_RECORD_MISC_USER; - sample.ip = ptq->state->from_ip; - sample.pid = ptq->pid; - sample.tid = ptq->tid; - sample.addr = ptq->state->to_ip; sample.id = ptq->pt->instructions_id; sample.stream_id = ptq->pt->instructions_id; sample.period = ptq->state->tot_insn_cnt - ptq->last_insn_cnt; - sample.cpu = ptq->cpu; - sample.flags = ptq->flags; - sample.insn_len = ptq->insn_len; - memcpy(sample.insn, ptq->insn, INTEL_PT_INSN_BUF_SZ); ptq->last_insn_cnt = ptq->state->tot_insn_cnt; - if (pt->synth_opts.callchain) { - thread_stack__sample(ptq->thread, ptq->chain, - pt->synth_opts.callchain_sz, sample.ip); - sample.callchain = ptq->chain; - } + return intel_pt_deliver_synth_event(pt, ptq, event, &sample, + pt->instructions_sample_type); +} - if (pt->synth_opts.last_branch) { - intel_pt_copy_last_branch_rb(ptq); - sample.branch_stack = ptq->last_branch; - } +static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq) +{ + struct intel_pt *pt = ptq->pt; + union perf_event *event = ptq->event_buf; + struct perf_sample sample = { .ip = 0, }; - if (pt->synth_opts.inject) { - ret = intel_pt_inject_event(event, &sample, - pt->instructions_sample_type, - pt->synth_needs_swap); - if (ret) - return ret; - } + if (intel_pt_skip_event(pt)) + return 0; - ret = perf_session__deliver_synth_event(pt->session, event, &sample); - if (ret) - pr_err("Intel Processor Trace: failed to deliver instruction event, error %d\n", - ret); + intel_pt_prep_sample(pt, ptq, event, &sample); - if (pt->synth_opts.last_branch) - intel_pt_reset_last_branch_rb(ptq); + sample.id = ptq->pt->transactions_id; + sample.stream_id = ptq->pt->transactions_id; - return ret; + return intel_pt_deliver_synth_event(pt, ptq, event, &sample, + pt->transactions_sample_type); } -static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq) +static void intel_pt_prep_p_sample(struct intel_pt *pt, + struct intel_pt_queue *ptq, + union perf_event *event, + struct perf_sample *sample) +{ + intel_pt_prep_sample(pt, ptq, event, sample); + + /* + * Zero IP is used to mean "trace start" but that is not the case for + * power or PTWRITE events with no IP, so clear the flags. + */ + if (!sample->ip) + sample->flags = 0; +} + +static int intel_pt_synth_ptwrite_sample(struct intel_pt_queue *ptq) { - int ret; struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; struct perf_sample sample = { .ip = 0, }; + struct perf_synth_intel_ptwrite raw; - if (pt->synth_opts.initial_skip && - pt->num_events++ < pt->synth_opts.initial_skip) + if (intel_pt_skip_event(pt)) return 0; - event->sample.header.type = PERF_RECORD_SAMPLE; - event->sample.header.misc = PERF_RECORD_MISC_USER; - event->sample.header.size = sizeof(struct perf_event_header); + intel_pt_prep_p_sample(pt, ptq, event, &sample); - if (!pt->timeless_decoding) - sample.time = tsc_to_perf_time(ptq->timestamp, &pt->tc); + sample.id = ptq->pt->ptwrites_id; + sample.stream_id = ptq->pt->ptwrites_id; - sample.cpumode = PERF_RECORD_MISC_USER; - sample.ip = ptq->state->from_ip; - sample.pid = ptq->pid; - sample.tid = ptq->tid; - sample.addr = ptq->state->to_ip; - sample.id = ptq->pt->transactions_id; - sample.stream_id = ptq->pt->transactions_id; - sample.period = 1; - sample.cpu = ptq->cpu; - sample.flags = ptq->flags; - sample.insn_len = ptq->insn_len; - memcpy(sample.insn, ptq->insn, INTEL_PT_INSN_BUF_SZ); + raw.flags = 0; + raw.ip = !!(ptq->state->flags & INTEL_PT_FUP_IP); + raw.payload = cpu_to_le64(ptq->state->ptw_payload); - if (pt->synth_opts.callchain) { - thread_stack__sample(ptq->thread, ptq->chain, - pt->synth_opts.callchain_sz, sample.ip); - sample.callchain = ptq->chain; - } + sample.raw_size = perf_synth__raw_size(raw); + sample.raw_data = perf_synth__raw_data(&raw); - if (pt->synth_opts.last_branch) { - intel_pt_copy_last_branch_rb(ptq); - sample.branch_stack = ptq->last_branch; - } + return intel_pt_deliver_synth_event(pt, ptq, event, &sample, + pt->ptwrites_sample_type); +} - if (pt->synth_opts.inject) { - ret = intel_pt_inject_event(event, &sample, - pt->transactions_sample_type, - pt->synth_needs_swap); - if (ret) - return ret; - } +static int intel_pt_synth_cbr_sample(struct intel_pt_queue *ptq) +{ + struct intel_pt *pt = ptq->pt; + union perf_event *event = ptq->event_buf; + struct perf_sample sample = { .ip = 0, }; + struct perf_synth_intel_cbr raw; + u32 flags; - ret = perf_session__deliver_synth_event(pt->session, event, &sample); - if (ret) - pr_err("Intel Processor Trace: failed to deliver transaction event, error %d\n", - ret); + if (intel_pt_skip_event(pt)) + return 0; - if (pt->synth_opts.last_branch) - intel_pt_reset_last_branch_rb(ptq); + intel_pt_prep_p_sample(pt, ptq, event, &sample); - return ret; + sample.id = ptq->pt->cbr_id; + sample.stream_id = ptq->pt->cbr_id; + + flags = (u16)ptq->state->cbr_payload | (pt->max_non_turbo_ratio << 16); + raw.flags = cpu_to_le32(flags); + raw.freq = cpu_to_le32(raw.cbr * pt->cbr2khz); + raw.reserved3 = 0; + + sample.raw_size = perf_synth__raw_size(raw); + sample.raw_data = perf_synth__raw_data(&raw); + + return intel_pt_deliver_synth_event(pt, ptq, event, &sample, + pt->pwr_events_sample_type); +} + +static int intel_pt_synth_mwait_sample(struct intel_pt_queue *ptq) +{ + struct intel_pt *pt = ptq->pt; + union perf_event *event = ptq->event_buf; + struct perf_sample sample = { .ip = 0, }; + struct perf_synth_intel_mwait raw; + + if (intel_pt_skip_event(pt)) + return 0; + + intel_pt_prep_p_sample(pt, ptq, event, &sample); + + sample.id = ptq->pt->mwait_id; + sample.stream_id = ptq->pt->mwait_id; + + raw.reserved = 0; + raw.payload = cpu_to_le64(ptq->state->mwait_payload); + + sample.raw_size = perf_synth__raw_size(raw); + sample.raw_data = perf_synth__raw_data(&raw); + + return intel_pt_deliver_synth_event(pt, ptq, event, &sample, + pt->pwr_events_sample_type); +} + +static int intel_pt_synth_pwre_sample(struct intel_pt_queue *ptq) +{ + struct intel_pt *pt = ptq->pt; + union perf_event *event = ptq->event_buf; + struct perf_sample sample = { .ip = 0, }; + struct perf_synth_intel_pwre raw; + + if (intel_pt_skip_event(pt)) + return 0; + + intel_pt_prep_p_sample(pt, ptq, event, &sample); + + sample.id = ptq->pt->pwre_id; + sample.stream_id = ptq->pt->pwre_id; + + raw.reserved = 0; + raw.payload = cpu_to_le64(ptq->state->pwre_payload); + + sample.raw_size = perf_synth__raw_size(raw); + sample.raw_data = perf_synth__raw_data(&raw); + + return intel_pt_deliver_synth_event(pt, ptq, event, &sample, + pt->pwr_events_sample_type); +} + +static int intel_pt_synth_exstop_sample(struct intel_pt_queue *ptq) +{ + struct intel_pt *pt = ptq->pt; + union perf_event *event = ptq->event_buf; + struct perf_sample sample = { .ip = 0, }; + struct perf_synth_intel_exstop raw; + + if (intel_pt_skip_event(pt)) + return 0; + + intel_pt_prep_p_sample(pt, ptq, event, &sample); + + sample.id = ptq->pt->exstop_id; + sample.stream_id = ptq->pt->exstop_id; + + raw.flags = 0; + raw.ip = !!(ptq->state->flags & INTEL_PT_FUP_IP); + + sample.raw_size = perf_synth__raw_size(raw); + sample.raw_data = perf_synth__raw_data(&raw); + + return intel_pt_deliver_synth_event(pt, ptq, event, &sample, + pt->pwr_events_sample_type); +} + +static int intel_pt_synth_pwrx_sample(struct intel_pt_queue *ptq) +{ + struct intel_pt *pt = ptq->pt; + union perf_event *event = ptq->event_buf; + struct perf_sample sample = { .ip = 0, }; + struct perf_synth_intel_pwrx raw; + + if (intel_pt_skip_event(pt)) + return 0; + + intel_pt_prep_p_sample(pt, ptq, event, &sample); + + sample.id = ptq->pt->pwrx_id; + sample.stream_id = ptq->pt->pwrx_id; + + raw.reserved = 0; + raw.payload = cpu_to_le64(ptq->state->pwrx_payload); + + sample.raw_size = perf_synth__raw_size(raw); + sample.raw_data = perf_synth__raw_data(&raw); + + return intel_pt_deliver_synth_event(pt, ptq, event, &sample, + pt->pwr_events_sample_type); } static int intel_pt_synth_error(struct intel_pt *pt, int code, int cpu, @@ -1296,6 +1469,10 @@ static inline bool intel_pt_is_switch_ip(struct intel_pt_queue *ptq, u64 ip) PERF_IP_FLAG_INTERRUPT | PERF_IP_FLAG_TX_ABORT)); } +#define INTEL_PT_PWR_EVT (INTEL_PT_MWAIT_OP | INTEL_PT_PWR_ENTRY | \ + INTEL_PT_EX_STOP | INTEL_PT_PWR_EXIT | \ + INTEL_PT_CBR_CHG) + static int intel_pt_sample(struct intel_pt_queue *ptq) { const struct intel_pt_state *state = ptq->state; @@ -1307,24 +1484,52 @@ static int intel_pt_sample(struct intel_pt_queue *ptq) ptq->have_sample = false; - if (pt->sample_instructions && - (state->type & INTEL_PT_INSTRUCTION) && - (!pt->synth_opts.initial_skip || - pt->num_events++ >= pt->synth_opts.initial_skip)) { + if (pt->sample_pwr_events && (state->type & INTEL_PT_PWR_EVT)) { + if (state->type & INTEL_PT_CBR_CHG) { + err = intel_pt_synth_cbr_sample(ptq); + if (err) + return err; + } + if (state->type & INTEL_PT_MWAIT_OP) { + err = intel_pt_synth_mwait_sample(ptq); + if (err) + return err; + } + if (state->type & INTEL_PT_PWR_ENTRY) { + err = intel_pt_synth_pwre_sample(ptq); + if (err) + return err; + } + if (state->type & INTEL_PT_EX_STOP) { + err = intel_pt_synth_exstop_sample(ptq); + if (err) + return err; + } + if (state->type & INTEL_PT_PWR_EXIT) { + err = intel_pt_synth_pwrx_sample(ptq); + if (err) + return err; + } + } + + if (pt->sample_instructions && (state->type & INTEL_PT_INSTRUCTION)) { err = intel_pt_synth_instruction_sample(ptq); if (err) return err; } - if (pt->sample_transactions && - (state->type & INTEL_PT_TRANSACTION) && - (!pt->synth_opts.initial_skip || - pt->num_events++ >= pt->synth_opts.initial_skip)) { + if (pt->sample_transactions && (state->type & INTEL_PT_TRANSACTION)) { err = intel_pt_synth_transaction_sample(ptq); if (err) return err; } + if (pt->sample_ptwrites && (state->type & INTEL_PT_PTW)) { + err = intel_pt_synth_ptwrite_sample(ptq); + if (err) + return err; + } + if (!(state->type & INTEL_PT_BRANCH)) return 0; @@ -1925,36 +2130,65 @@ static int intel_pt_event_synth(struct perf_tool *tool, NULL); } -static int intel_pt_synth_event(struct perf_session *session, +static int intel_pt_synth_event(struct perf_session *session, const char *name, struct perf_event_attr *attr, u64 id) { struct intel_pt_synth intel_pt_synth; + int err; + + pr_debug("Synthesizing '%s' event with id %" PRIu64 " sample type %#" PRIx64 "\n", + name, id, (u64)attr->sample_type); memset(&intel_pt_synth, 0, sizeof(struct intel_pt_synth)); intel_pt_synth.session = session; - return perf_event__synthesize_attr(&intel_pt_synth.dummy_tool, attr, 1, - &id, intel_pt_event_synth); + err = perf_event__synthesize_attr(&intel_pt_synth.dummy_tool, attr, 1, + &id, intel_pt_event_synth); + if (err) + pr_err("%s: failed to synthesize '%s' event type\n", + __func__, name); + + return err; } -static int intel_pt_synth_events(struct intel_pt *pt, - struct perf_session *session) +static void intel_pt_set_event_name(struct perf_evlist *evlist, u64 id, + const char *name) { - struct perf_evlist *evlist = session->evlist; struct perf_evsel *evsel; - struct perf_event_attr attr; - bool found = false; - u64 id; - int err; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type == pt->pmu_type && evsel->ids) { - found = true; + if (evsel->id && evsel->id[0] == id) { + if (evsel->name) + zfree(&evsel->name); + evsel->name = strdup(name); break; } } +} - if (!found) { +static struct perf_evsel *intel_pt_evsel(struct intel_pt *pt, + struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + + evlist__for_each_entry(evlist, evsel) { + if (evsel->attr.type == pt->pmu_type && evsel->ids) + return evsel; + } + + return NULL; +} + +static int intel_pt_synth_events(struct intel_pt *pt, + struct perf_session *session) +{ + struct perf_evlist *evlist = session->evlist; + struct perf_evsel *evsel = intel_pt_evsel(pt, evlist); + struct perf_event_attr attr; + u64 id; + int err; + + if (!evsel) { pr_debug("There are no selected events with Intel Processor Trace data\n"); return 0; } @@ -1983,6 +2217,25 @@ static int intel_pt_synth_events(struct intel_pt *pt, if (!id) id = 1; + if (pt->synth_opts.branches) { + attr.config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS; + attr.sample_period = 1; + attr.sample_type |= PERF_SAMPLE_ADDR; + err = intel_pt_synth_event(session, "branches", &attr, id); + if (err) + return err; + pt->sample_branches = true; + pt->branches_sample_type = attr.sample_type; + pt->branches_id = id; + id += 1; + attr.sample_type &= ~(u64)PERF_SAMPLE_ADDR; + } + + if (pt->synth_opts.callchain) + attr.sample_type |= PERF_SAMPLE_CALLCHAIN; + if (pt->synth_opts.last_branch) + attr.sample_type |= PERF_SAMPLE_BRANCH_STACK; + if (pt->synth_opts.instructions) { attr.config = PERF_COUNT_HW_INSTRUCTIONS; if (pt->synth_opts.period_type == PERF_ITRACE_PERIOD_NANOSECS) @@ -1990,70 +2243,90 @@ static int intel_pt_synth_events(struct intel_pt *pt, intel_pt_ns_to_ticks(pt, pt->synth_opts.period); else attr.sample_period = pt->synth_opts.period; - pt->instructions_sample_period = attr.sample_period; - if (pt->synth_opts.callchain) - attr.sample_type |= PERF_SAMPLE_CALLCHAIN; - if (pt->synth_opts.last_branch) - attr.sample_type |= PERF_SAMPLE_BRANCH_STACK; - pr_debug("Synthesizing 'instructions' event with id %" PRIu64 " sample type %#" PRIx64 "\n", - id, (u64)attr.sample_type); - err = intel_pt_synth_event(session, &attr, id); - if (err) { - pr_err("%s: failed to synthesize 'instructions' event type\n", - __func__); + err = intel_pt_synth_event(session, "instructions", &attr, id); + if (err) return err; - } pt->sample_instructions = true; pt->instructions_sample_type = attr.sample_type; pt->instructions_id = id; id += 1; } + attr.sample_type &= ~(u64)PERF_SAMPLE_PERIOD; + attr.sample_period = 1; + if (pt->synth_opts.transactions) { attr.config = PERF_COUNT_HW_INSTRUCTIONS; - attr.sample_period = 1; - if (pt->synth_opts.callchain) - attr.sample_type |= PERF_SAMPLE_CALLCHAIN; - if (pt->synth_opts.last_branch) - attr.sample_type |= PERF_SAMPLE_BRANCH_STACK; - pr_debug("Synthesizing 'transactions' event with id %" PRIu64 " sample type %#" PRIx64 "\n", - id, (u64)attr.sample_type); - err = intel_pt_synth_event(session, &attr, id); - if (err) { - pr_err("%s: failed to synthesize 'transactions' event type\n", - __func__); + err = intel_pt_synth_event(session, "transactions", &attr, id); + if (err) return err; - } pt->sample_transactions = true; + pt->transactions_sample_type = attr.sample_type; pt->transactions_id = id; + intel_pt_set_event_name(evlist, id, "transactions"); id += 1; - evlist__for_each_entry(evlist, evsel) { - if (evsel->id && evsel->id[0] == pt->transactions_id) { - if (evsel->name) - zfree(&evsel->name); - evsel->name = strdup("transactions"); - break; - } - } } - if (pt->synth_opts.branches) { - attr.config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS; - attr.sample_period = 1; - attr.sample_type |= PERF_SAMPLE_ADDR; - attr.sample_type &= ~(u64)PERF_SAMPLE_CALLCHAIN; - attr.sample_type &= ~(u64)PERF_SAMPLE_BRANCH_STACK; - pr_debug("Synthesizing 'branches' event with id %" PRIu64 " sample type %#" PRIx64 "\n", - id, (u64)attr.sample_type); - err = intel_pt_synth_event(session, &attr, id); - if (err) { - pr_err("%s: failed to synthesize 'branches' event type\n", - __func__); + attr.type = PERF_TYPE_SYNTH; + attr.sample_type |= PERF_SAMPLE_RAW; + + if (pt->synth_opts.ptwrites) { + attr.config = PERF_SYNTH_INTEL_PTWRITE; + err = intel_pt_synth_event(session, "ptwrite", &attr, id); + if (err) return err; - } - pt->sample_branches = true; - pt->branches_sample_type = attr.sample_type; - pt->branches_id = id; + pt->sample_ptwrites = true; + pt->ptwrites_sample_type = attr.sample_type; + pt->ptwrites_id = id; + intel_pt_set_event_name(evlist, id, "ptwrite"); + id += 1; + } + + if (pt->synth_opts.pwr_events) { + pt->sample_pwr_events = true; + pt->pwr_events_sample_type = attr.sample_type; + + attr.config = PERF_SYNTH_INTEL_CBR; + err = intel_pt_synth_event(session, "cbr", &attr, id); + if (err) + return err; + pt->cbr_id = id; + intel_pt_set_event_name(evlist, id, "cbr"); + id += 1; + } + + if (pt->synth_opts.pwr_events && (evsel->attr.config & 0x10)) { + attr.config = PERF_SYNTH_INTEL_MWAIT; + err = intel_pt_synth_event(session, "mwait", &attr, id); + if (err) + return err; + pt->mwait_id = id; + intel_pt_set_event_name(evlist, id, "mwait"); + id += 1; + + attr.config = PERF_SYNTH_INTEL_PWRE; + err = intel_pt_synth_event(session, "pwre", &attr, id); + if (err) + return err; + pt->pwre_id = id; + intel_pt_set_event_name(evlist, id, "pwre"); + id += 1; + + attr.config = PERF_SYNTH_INTEL_EXSTOP; + err = intel_pt_synth_event(session, "exstop", &attr, id); + if (err) + return err; + pt->exstop_id = id; + intel_pt_set_event_name(evlist, id, "exstop"); + id += 1; + + attr.config = PERF_SYNTH_INTEL_PWRX; + err = intel_pt_synth_event(session, "pwrx", &attr, id); + if (err) + return err; + pt->pwrx_id = id; + intel_pt_set_event_name(evlist, id, "pwrx"); + id += 1; } pt->synth_needs_swap = evsel->needs_swap; @@ -2322,6 +2595,7 @@ int intel_pt_process_auxtrace_info(union perf_event *event, intel_pt_log("TSC frequency %"PRIu64"\n", tsc_freq); intel_pt_log("Maximum non-turbo ratio %u\n", pt->max_non_turbo_ratio); + pt->cbr2khz = tsc_freq / pt->max_non_turbo_ratio / 1000; } if (pt->synth_opts.calls) diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index d7f31cb0a4cb..5de2b86b9880 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1209,10 +1209,12 @@ int machine__create_kernel_maps(struct machine *machine) */ map_groups__fixup_end(&machine->kmaps); - if (machine__get_running_kernel_start(machine, &name, &addr)) { - } else if (maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name, addr)) { - machine__destroy_kernel_maps(machine); - return -1; + if (!machine__get_running_kernel_start(machine, &name, &addr)) { + if (name && + maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name, addr)) { + machine__destroy_kernel_maps(machine); + return -1; + } } return 0; diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index ea7f450dc609..389e9729331f 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -2,6 +2,7 @@ #define __PMU_H #include <linux/bitmap.h> +#include <linux/compiler.h> #include <linux/perf_event.h> #include <stdbool.h> #include "evsel.h" @@ -83,8 +84,7 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet, bool long_desc, bool details_flag); bool pmu_have_event(const char *pname, const char *name); -int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, - ...) __attribute__((format(scanf, 3, 4))); +int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, ...) __scanf(3, 4); int perf_pmu__test(void); diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 84e7e698411e..a2670e9d652d 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -619,7 +619,7 @@ static int post_process_probe_trace_point(struct probe_trace_point *tp, struct map *map, unsigned long offs) { struct symbol *sym; - u64 addr = tp->address + tp->offset - offs; + u64 addr = tp->address - offs; sym = map__find_symbol(map, addr); if (!sym) diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index 373842656fb6..5812947418dd 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -1,6 +1,7 @@ #ifndef _PROBE_EVENT_H #define _PROBE_EVENT_H +#include <linux/compiler.h> #include <stdbool.h> #include "intlist.h" @@ -171,8 +172,7 @@ void arch__fix_tev_from_maps(struct perf_probe_event *pev, struct symbol *sym); /* If there is no space to write, returns -E2BIG. */ -int e_snprintf(char *str, size_t size, const char *format, ...) - __attribute__((format(printf, 3, 4))); +int e_snprintf(char *str, size_t size, const char *format, ...) __printf(3, 4); /* Maximum index number of event-name postfix */ #define MAX_EVENT_INDEX 1024 diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 40de3cb40d21..57b7a00e6f16 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -28,6 +28,7 @@ #include <stdbool.h> #include <errno.h> #include <linux/bitmap.h> +#include <linux/compiler.h> #include <linux/time64.h> #include "../../perf.h" @@ -84,7 +85,7 @@ struct tables { static struct tables tables_global; -static void handler_call_die(const char *handler_name) NORETURN; +static void handler_call_die(const char *handler_name) __noreturn; static void handler_call_die(const char *handler_name) { PyErr_Print(); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 7dc1096264c5..d19c40a81040 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -2035,7 +2035,7 @@ int perf_session__cpu_bitmap(struct perf_session *session, if (!(evsel->attr.sample_type & PERF_SAMPLE_CPU)) { pr_err("File does not contain CPU events. " - "Remove -c option to proceed.\n"); + "Remove -C option to proceed.\n"); return -1; } } diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 5762ae4e9e91..8b327c955a4f 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -2532,12 +2532,12 @@ static int setup_sort_list(struct perf_hpp_list *list, char *str, ret = sort_dimension__add(list, tok, evlist, level); if (ret == -EINVAL) { if (!cacheline_size && !strncasecmp(tok, "dcacheline", strlen(tok))) - error("The \"dcacheline\" --sort key needs to know the cacheline size and it couldn't be determined on this system"); + pr_err("The \"dcacheline\" --sort key needs to know the cacheline size and it couldn't be determined on this system"); else - error("Invalid --sort key: `%s'", tok); + pr_err("Invalid --sort key: `%s'", tok); break; } else if (ret == -ESRCH) { - error("Unknown --sort key: `%s'", tok); + pr_err("Unknown --sort key: `%s'", tok); break; } } @@ -2594,7 +2594,7 @@ static int setup_sort_order(struct perf_evlist *evlist) return 0; if (sort_order[1] == '\0') { - error("Invalid --sort key: `+'"); + pr_err("Invalid --sort key: `+'"); return -EINVAL; } @@ -2604,7 +2604,7 @@ static int setup_sort_order(struct perf_evlist *evlist) */ if (asprintf(&new_sort_order, "%s,%s", get_default_sort_order(evlist), sort_order + 1) < 0) { - error("Not enough memory to set up --sort"); + pr_err("Not enough memory to set up --sort"); return -ENOMEM; } @@ -2668,7 +2668,7 @@ static int __setup_sorting(struct perf_evlist *evlist) str = strdup(sort_keys); if (str == NULL) { - error("Not enough memory to setup sort keys"); + pr_err("Not enough memory to setup sort keys"); return -ENOMEM; } @@ -2678,7 +2678,7 @@ static int __setup_sorting(struct perf_evlist *evlist) if (!is_strict_order(field_order)) { str = setup_overhead(str); if (str == NULL) { - error("Not enough memory to setup overhead keys"); + pr_err("Not enough memory to setup overhead keys"); return -ENOMEM; } } @@ -2834,10 +2834,10 @@ static int setup_output_list(struct perf_hpp_list *list, char *str) tok; tok = strtok_r(NULL, ", ", &tmp)) { ret = output_field_add(list, tok); if (ret == -EINVAL) { - error("Invalid --fields key: `%s'", tok); + pr_err("Invalid --fields key: `%s'", tok); break; } else if (ret == -ESRCH) { - error("Unknown --fields key: `%s'", tok); + pr_err("Unknown --fields key: `%s'", tok); break; } } @@ -2877,7 +2877,7 @@ static int __setup_output_field(void) strp = str = strdup(field_order); if (str == NULL) { - error("Not enough memory to setup output fields"); + pr_err("Not enough memory to setup output fields"); return -ENOMEM; } @@ -2885,7 +2885,7 @@ static int __setup_output_field(void) strp++; if (!strlen(strp)) { - error("Invalid --fields key: `+'"); + pr_err("Invalid --fields key: `+'"); goto out; } diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index ac10cc675d39..719d6cb86952 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -44,6 +44,8 @@ static struct stats runtime_topdown_slots_issued[NUM_CTX][MAX_NR_CPUS]; static struct stats runtime_topdown_slots_retired[NUM_CTX][MAX_NR_CPUS]; static struct stats runtime_topdown_fetch_bubbles[NUM_CTX][MAX_NR_CPUS]; static struct stats runtime_topdown_recovery_bubbles[NUM_CTX][MAX_NR_CPUS]; +static struct stats runtime_smi_num_stats[NUM_CTX][MAX_NR_CPUS]; +static struct stats runtime_aperf_stats[NUM_CTX][MAX_NR_CPUS]; static struct rblist runtime_saved_values; static bool have_frontend_stalled; @@ -157,6 +159,8 @@ void perf_stat__reset_shadow_stats(void) memset(runtime_topdown_slots_issued, 0, sizeof(runtime_topdown_slots_issued)); memset(runtime_topdown_fetch_bubbles, 0, sizeof(runtime_topdown_fetch_bubbles)); memset(runtime_topdown_recovery_bubbles, 0, sizeof(runtime_topdown_recovery_bubbles)); + memset(runtime_smi_num_stats, 0, sizeof(runtime_smi_num_stats)); + memset(runtime_aperf_stats, 0, sizeof(runtime_aperf_stats)); next = rb_first(&runtime_saved_values.entries); while (next) { @@ -217,6 +221,10 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count, update_stats(&runtime_dtlb_cache_stats[ctx][cpu], count[0]); else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB)) update_stats(&runtime_itlb_cache_stats[ctx][cpu], count[0]); + else if (perf_stat_evsel__is(counter, SMI_NUM)) + update_stats(&runtime_smi_num_stats[ctx][cpu], count[0]); + else if (perf_stat_evsel__is(counter, APERF)) + update_stats(&runtime_aperf_stats[ctx][cpu], count[0]); if (counter->collect_stat) { struct saved_value *v = saved_value_lookup(counter, cpu, ctx, @@ -592,6 +600,29 @@ static double td_be_bound(int ctx, int cpu) return sanitize_val(1.0 - sum); } +static void print_smi_cost(int cpu, struct perf_evsel *evsel, + struct perf_stat_output_ctx *out) +{ + double smi_num, aperf, cycles, cost = 0.0; + int ctx = evsel_context(evsel); + const char *color = NULL; + + smi_num = avg_stats(&runtime_smi_num_stats[ctx][cpu]); + aperf = avg_stats(&runtime_aperf_stats[ctx][cpu]); + cycles = avg_stats(&runtime_cycles_stats[ctx][cpu]); + + if ((cycles == 0) || (aperf == 0)) + return; + + if (smi_num) + cost = (aperf - cycles) / aperf * 100.00; + + if (cost > 10) + color = PERF_COLOR_RED; + out->print_metric(out->ctx, color, "%8.1f%%", "SMI cycles%", cost); + out->print_metric(out->ctx, NULL, "%4.0f", "SMI#", smi_num); +} + void perf_stat__print_shadow_stats(struct perf_evsel *evsel, double avg, int cpu, struct perf_stat_output_ctx *out) @@ -825,6 +856,8 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel, } snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit); print_metric(ctxp, NULL, "%8.3f", unit_buf, ratio); + } else if (perf_stat_evsel__is(evsel, SMI_NUM)) { + print_smi_cost(cpu, evsel, out); } else { print_metric(ctxp, NULL, NULL, NULL, 0); } diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index c58174443dc1..53b9a994a3dc 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -86,6 +86,8 @@ static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = { ID(TOPDOWN_SLOTS_RETIRED, topdown-slots-retired), ID(TOPDOWN_FETCH_BUBBLES, topdown-fetch-bubbles), ID(TOPDOWN_RECOVERY_BUBBLES, topdown-recovery-bubbles), + ID(SMI_NUM, msr/smi/), + ID(APERF, msr/aperf/), }; #undef ID diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 0a65ae23f495..7522bf10b03e 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -22,6 +22,8 @@ enum perf_stat_evsel_id { PERF_STAT_EVSEL_ID__TOPDOWN_SLOTS_RETIRED, PERF_STAT_EVSEL_ID__TOPDOWN_FETCH_BUBBLES, PERF_STAT_EVSEL_ID__TOPDOWN_RECOVERY_BUBBLES, + PERF_STAT_EVSEL_ID__SMI_NUM, + PERF_STAT_EVSEL_ID__APERF, PERF_STAT_EVSEL_ID__MAX, }; diff --git a/tools/perf/util/strbuf.h b/tools/perf/util/strbuf.h index 318424ea561d..802d743378af 100644 --- a/tools/perf/util/strbuf.h +++ b/tools/perf/util/strbuf.h @@ -42,6 +42,7 @@ #include <stdarg.h> #include <stddef.h> #include <string.h> +#include <linux/compiler.h> #include <sys/types.h> extern char strbuf_slopbuf[]; @@ -85,8 +86,7 @@ static inline int strbuf_addstr(struct strbuf *sb, const char *s) { return strbuf_add(sb, s, strlen(s)); } -__attribute__((format(printf,2,3))) -int strbuf_addf(struct strbuf *sb, const char *fmt, ...); +int strbuf_addf(struct strbuf *sb, const char *fmt, ...) __printf(2, 3); /* XXX: if read fails, any partial read is undone */ ssize_t strbuf_read(struct strbuf *, int fd, ssize_t hint); diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 746bbee645d9..e0a6e9a6a053 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -24,7 +24,7 @@ #include <errno.h> #include "../perf.h" -#include "util.h" +#include "debug.h" #include "trace-event.h" #include "sane_ctype.h" @@ -150,7 +150,7 @@ void parse_ftrace_printk(struct pevent *pevent, while (line) { addr_str = strtok_r(line, ":", &fmt); if (!addr_str) { - warning("printk format with empty entry"); + pr_warning("printk format with empty entry"); break; } addr = strtoull(addr_str, NULL, 16); diff --git a/tools/perf/util/usage.c b/tools/perf/util/usage.c index 996046a66fe5..6cc9d9888ce0 100644 --- a/tools/perf/util/usage.c +++ b/tools/perf/util/usage.c @@ -9,75 +9,17 @@ #include "util.h" #include "debug.h" -static void report(const char *prefix, const char *err, va_list params) -{ - char msg[1024]; - vsnprintf(msg, sizeof(msg), err, params); - fprintf(stderr, " %s%s\n", prefix, msg); -} - -static NORETURN void usage_builtin(const char *err) +static __noreturn void usage_builtin(const char *err) { fprintf(stderr, "\n Usage: %s\n", err); exit(129); } -static NORETURN void die_builtin(const char *err, va_list params) -{ - report(" Fatal: ", err, params); - exit(128); -} - -static void error_builtin(const char *err, va_list params) -{ - report(" Error: ", err, params); -} - -static void warn_builtin(const char *warn, va_list params) -{ - report(" Warning: ", warn, params); -} - /* If we are in a dlopen()ed .so write to a global variable would segfault * (ugh), so keep things static. */ -static void (*usage_routine)(const char *err) NORETURN = usage_builtin; -static void (*error_routine)(const char *err, va_list params) = error_builtin; -static void (*warn_routine)(const char *err, va_list params) = warn_builtin; - -void set_warning_routine(void (*routine)(const char *err, va_list params)) -{ - warn_routine = routine; -} +static void (*usage_routine)(const char *err) __noreturn = usage_builtin; void usage(const char *err) { usage_routine(err); } - -void die(const char *err, ...) -{ - va_list params; - - va_start(params, err); - die_builtin(err, params); - va_end(params); -} - -int error(const char *err, ...) -{ - va_list params; - - va_start(params, err); - error_routine(err, params); - va_end(params); - return -1; -} - -void warning(const char *warn, ...) -{ - va_list params; - - va_start(params, warn); - warn_routine(warn, params); - va_end(params); -} diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 28c9f335006c..988111e0bab5 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -343,43 +343,6 @@ int perf_event_paranoid(void) return value; } - -bool find_process(const char *name) -{ - size_t len = strlen(name); - DIR *dir; - struct dirent *d; - int ret = -1; - - dir = opendir(procfs__mountpoint()); - if (!dir) - return false; - - /* Walk through the directory. */ - while (ret && (d = readdir(dir)) != NULL) { - char path[PATH_MAX]; - char *data; - size_t size; - - if ((d->d_type != DT_DIR) || - !strcmp(".", d->d_name) || - !strcmp("..", d->d_name)) - continue; - - scnprintf(path, sizeof(path), "%s/%s/comm", - procfs__mountpoint(), d->d_name); - - if (filename__read_str(path, &data, &size)) - continue; - - ret = strncmp(name, data, len); - free(data); - } - - closedir(dir); - return ret ? false : true; -} - static int fetch_ubuntu_kernel_version(unsigned int *puint) { @@ -387,8 +350,12 @@ fetch_ubuntu_kernel_version(unsigned int *puint) size_t line_len = 0; char *ptr, *line = NULL; int version, patchlevel, sublevel, err; - FILE *vsig = fopen("/proc/version_signature", "r"); + FILE *vsig; + + if (!puint) + return 0; + vsig = fopen("/proc/version_signature", "r"); if (!vsig) { pr_debug("Open /proc/version_signature failed: %s\n", strerror(errno)); @@ -418,8 +385,7 @@ fetch_ubuntu_kernel_version(unsigned int *puint) goto errout; } - if (puint) - *puint = (version << 16) + (patchlevel << 8) + sublevel; + *puint = (version << 16) + (patchlevel << 8) + sublevel; err = 0; errout: free(line); @@ -446,6 +412,9 @@ fetch_kernel_version(unsigned int *puint, char *str, str[str_size - 1] = '\0'; } + if (!puint || int_ver_ready) + return 0; + err = sscanf(utsname.release, "%d.%d.%d", &version, &patchlevel, &sublevel); @@ -455,8 +424,7 @@ fetch_kernel_version(unsigned int *puint, char *str, return -1; } - if (puint && !int_ver_ready) - *puint = (version << 16) + (patchlevel << 8) + sublevel; + *puint = (version << 16) + (patchlevel << 8) + sublevel; return 0; } diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 5dfb9bb6482d..2c9e58a45310 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -1,7 +1,6 @@ #ifndef GIT_COMPAT_UTIL_H #define GIT_COMPAT_UTIL_H -#define _ALL_SOURCE 1 #define _BSD_SOURCE 1 /* glibc 2.20 deprecates _BSD_SOURCE in favour of _DEFAULT_SOURCE */ #define _DEFAULT_SOURCE 1 @@ -11,24 +10,12 @@ #include <stddef.h> #include <stdlib.h> #include <stdarg.h> +#include <linux/compiler.h> #include <linux/types.h> -#ifdef __GNUC__ -#define NORETURN __attribute__((__noreturn__)) -#else -#define NORETURN -#ifndef __attribute__ -#define __attribute__(x) -#endif -#endif - /* General helper functions */ -void usage(const char *err) NORETURN; -void die(const char *err, ...) NORETURN __attribute__((format (printf, 1, 2))); -int error(const char *err, ...) __attribute__((format (printf, 1, 2))); -void warning(const char *err, ...) __attribute__((format (printf, 1, 2))); - -void set_warning_routine(void (*routine)(const char *err, va_list params)); +void usage(const char *err) __noreturn; +void die(const char *err, ...) __noreturn __printf(1, 2); static inline void *zalloc(size_t size) { @@ -57,8 +44,6 @@ int hex2u64(const char *ptr, u64 *val); extern unsigned int page_size; extern int cacheline_size; -bool find_process(const char *name); - int fetch_kernel_version(unsigned int *puint, char *str, size_t str_sz); #define KVER_VERSION(x) (((x) >> 16) & 0xff) diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c index 64cae1a5deff..e1f75a1914a1 100644 --- a/tools/testing/nvdimm/test/iomap.c +++ b/tools/testing/nvdimm/test/iomap.c @@ -370,7 +370,7 @@ acpi_status __wrap_acpi_evaluate_object(acpi_handle handle, acpi_string path, } EXPORT_SYMBOL(__wrap_acpi_evaluate_object); -union acpi_object * __wrap_acpi_evaluate_dsm(acpi_handle handle, const u8 *uuid, +union acpi_object * __wrap_acpi_evaluate_dsm(acpi_handle handle, const guid_t *guid, u64 rev, u64 func, union acpi_object *argv4) { union acpi_object *obj = ERR_PTR(-ENXIO); @@ -379,11 +379,11 @@ union acpi_object * __wrap_acpi_evaluate_dsm(acpi_handle handle, const u8 *uuid, rcu_read_lock(); ops = list_first_or_null_rcu(&iomap_head, typeof(*ops), list); if (ops) - obj = ops->evaluate_dsm(handle, uuid, rev, func, argv4); + obj = ops->evaluate_dsm(handle, guid, rev, func, argv4); rcu_read_unlock(); if (IS_ERR(obj)) - return acpi_evaluate_dsm(handle, uuid, rev, func, argv4); + return acpi_evaluate_dsm(handle, guid, rev, func, argv4); return obj; } EXPORT_SYMBOL(__wrap_acpi_evaluate_dsm); diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index c2187178fb13..28859da78edf 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -1559,7 +1559,7 @@ static unsigned long nfit_ctl_handle; union acpi_object *result; static union acpi_object *nfit_test_evaluate_dsm(acpi_handle handle, - const u8 *uuid, u64 rev, u64 func, union acpi_object *argv4) + const guid_t *guid, u64 rev, u64 func, union acpi_object *argv4) { if (handle != &nfit_ctl_handle) return ERR_PTR(-ENXIO); diff --git a/tools/testing/nvdimm/test/nfit_test.h b/tools/testing/nvdimm/test/nfit_test.h index f54c0032c6ff..d3d63dd5ed38 100644 --- a/tools/testing/nvdimm/test/nfit_test.h +++ b/tools/testing/nvdimm/test/nfit_test.h @@ -13,6 +13,7 @@ #ifndef __NFIT_TEST_H__ #define __NFIT_TEST_H__ #include <linux/list.h> +#include <linux/uuid.h> #include <linux/ioport.h> #include <linux/spinlock_types.h> @@ -36,7 +37,8 @@ typedef void *acpi_handle; typedef struct nfit_test_resource *(*nfit_test_lookup_fn)(resource_size_t); typedef union acpi_object *(*nfit_test_evaluate_dsm_fn)(acpi_handle handle, - const u8 *uuid, u64 rev, u64 func, union acpi_object *argv4); + const guid_t *guid, u64 rev, u64 func, + union acpi_object *argv4); void __iomem *__wrap_ioremap_nocache(resource_size_t offset, unsigned long size); void __wrap_iounmap(volatile void __iomem *addr); diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index cabb19b1e371..0ff8c55c0464 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -3749,6 +3749,72 @@ static struct bpf_test tests[] = { .errstr = "invalid bpf_context access", }, { + "leak pointer into ctx 1", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0])), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_STX_XADD(BPF_DW, BPF_REG_1, BPF_REG_2, + offsetof(struct __sk_buff, cb[0])), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 2 }, + .errstr_unpriv = "R2 leaks addr into mem", + .result_unpriv = REJECT, + .result = ACCEPT, + }, + { + "leak pointer into ctx 2", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0])), + BPF_STX_XADD(BPF_DW, BPF_REG_1, BPF_REG_10, + offsetof(struct __sk_buff, cb[0])), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "R10 leaks addr into mem", + .result_unpriv = REJECT, + .result = ACCEPT, + }, + { + "leak pointer into ctx 3", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, + offsetof(struct __sk_buff, cb[0])), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 1 }, + .errstr_unpriv = "R2 leaks addr into ctx", + .result_unpriv = REJECT, + .result = ACCEPT, + }, + { + "leak pointer into map val", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_3, 0), + BPF_STX_XADD(BPF_DW, BPF_REG_0, BPF_REG_6, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 4 }, + .errstr_unpriv = "R6 leaks addr into mem", + .result_unpriv = REJECT, + .result = ACCEPT, + }, + { "helper access to map: full range", .insns = { BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), diff --git a/tools/testing/selftests/ntb/ntb_test.sh b/tools/testing/selftests/ntb/ntb_test.sh index a676d3eefefb..13f5198ba0ee 100755 --- a/tools/testing/selftests/ntb/ntb_test.sh +++ b/tools/testing/selftests/ntb/ntb_test.sh @@ -305,7 +305,7 @@ function perf_test() echo "Running remote perf test $WITH DMA" write_file "" $REMOTE_PERF/run echo -n " " - read_file $LOCAL_PERF/run + read_file $REMOTE_PERF/run echo " Passed" _modprobe -r ntb_perf diff --git a/tools/testing/selftests/rcutorture/bin/configcheck.sh b/tools/testing/selftests/rcutorture/bin/configcheck.sh index eee31e261bf7..70fca318a82b 100755 --- a/tools/testing/selftests/rcutorture/bin/configcheck.sh +++ b/tools/testing/selftests/rcutorture/bin/configcheck.sh @@ -27,7 +27,7 @@ cat $1 > $T/.config cat $2 | sed -e 's/\(.*\)=n/# \1 is not set/' -e 's/^#CHECK#//' | awk ' -BEGIN { +{ print "if grep -q \"" $0 "\" < '"$T/.config"'"; print "then"; print "\t:"; diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh index 00cb0db2643d..c29f2ec0bf9f 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-build.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh @@ -45,7 +45,7 @@ T=/tmp/test-linux.sh.$$ trap 'rm -rf $T' 0 mkdir $T -grep -v 'CONFIG_[A-Z]*_TORTURE_TEST' < ${config_template} > $T/config +grep -v 'CONFIG_[A-Z]*_TORTURE_TEST=' < ${config_template} > $T/config cat << ___EOF___ >> $T/config CONFIG_INITRAMFS_SOURCE="$TORTURE_INITRD" CONFIG_VIRTIO_PCI=y diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index 3b3c1b693ee1..50091de3a911 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -296,10 +296,7 @@ if test -d .git then git status >> $resdir/$ds/testid.txt git rev-parse HEAD >> $resdir/$ds/testid.txt - if ! git diff HEAD > $T/git-diff 2>&1 - then - cp $T/git-diff $resdir/$ds - fi + git diff HEAD >> $resdir/$ds/testid.txt fi ___EOF___ awk < $T/cfgcpu.pack \ diff --git a/tools/testing/selftests/rcutorture/configs/rcu/CFLIST b/tools/testing/selftests/rcutorture/configs/rcu/CFLIST index a3a1a05a2b5c..6a0b9f69faad 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/CFLIST +++ b/tools/testing/selftests/rcutorture/configs/rcu/CFLIST @@ -9,6 +9,8 @@ TREE08 TREE09 SRCU-N SRCU-P +SRCU-t +SRCU-u TINY01 TINY02 TASKS01 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-C.boot b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-C.boot new file mode 100644 index 000000000000..84a7d51b7481 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-C.boot @@ -0,0 +1 @@ +rcutorture.torture_type=srcud diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N index 1a087c3c8bb8..2da8b49589a0 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N +++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N @@ -5,4 +5,4 @@ CONFIG_HOTPLUG_CPU=y CONFIG_PREEMPT_NONE=y CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n -CONFIG_RCU_EXPERT=y +#CHECK#CONFIG_RCU_EXPERT=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P index 4837430a71c0..ab7ccd38232b 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P +++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P @@ -2,7 +2,11 @@ CONFIG_RCU_TRACE=n CONFIG_SMP=y CONFIG_NR_CPUS=8 CONFIG_HOTPLUG_CPU=y +CONFIG_RCU_EXPERT=y +CONFIG_RCU_FANOUT=2 +CONFIG_RCU_FANOUT_LEAF=2 CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=y -#CHECK#CONFIG_RCU_EXPERT=n +CONFIG_DEBUG_LOCK_ALLOC=y +CONFIG_PROVE_LOCKING=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-t b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-t new file mode 100644 index 000000000000..6c78022c8cd8 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-t @@ -0,0 +1,10 @@ +CONFIG_SMP=n +CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=n +#CHECK#CONFIG_TINY_SRCU=y +CONFIG_RCU_TRACE=n +CONFIG_DEBUG_LOCK_ALLOC=n +CONFIG_DEBUG_OBJECTS_RCU_HEAD=n +CONFIG_DEBUG_ATOMIC_SLEEP=y +#CHECK#CONFIG_PREEMPT_COUNT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-t.boot b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-t.boot new file mode 100644 index 000000000000..238bfe3bd0cc --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-t.boot @@ -0,0 +1 @@ +rcutorture.torture_type=srcu diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u new file mode 100644 index 000000000000..6bc24e99862f --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u @@ -0,0 +1,9 @@ +CONFIG_SMP=n +CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=n +#CHECK#CONFIG_TINY_SRCU=y +CONFIG_RCU_TRACE=n +CONFIG_DEBUG_LOCK_ALLOC=n +CONFIG_DEBUG_OBJECTS_RCU_HEAD=n +CONFIG_PREEMPT_COUNT=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u.boot b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u.boot new file mode 100644 index 000000000000..84a7d51b7481 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u.boot @@ -0,0 +1 @@ +rcutorture.torture_type=srcud diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY02 b/tools/testing/selftests/rcutorture/configs/rcu/TINY02 index a59f7686e219..d8674264318d 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TINY02 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY02 @@ -6,10 +6,9 @@ CONFIG_PREEMPT=n CONFIG_HZ_PERIODIC=y CONFIG_NO_HZ_IDLE=n CONFIG_NO_HZ_FULL=n -CONFIG_RCU_TRACE=y CONFIG_PROVE_LOCKING=y -CONFIG_PROVE_RCU_REPEATEDLY=y #CHECK#CONFIG_PROVE_RCU=y CONFIG_DEBUG_LOCK_ALLOC=y +CONFIG_DEBUG_OBJECTS=y CONFIG_DEBUG_OBJECTS_RCU_HEAD=y -CONFIG_PREEMPT_COUNT=y +CONFIG_DEBUG_ATOMIC_SLEEP=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 b/tools/testing/selftests/rcutorture/configs/rcu/TREE01 index 359cb258f639..b5b53973c01e 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01 @@ -10,12 +10,9 @@ CONFIG_RCU_FAST_NO_HZ=y CONFIG_RCU_TRACE=y CONFIG_HOTPLUG_CPU=y CONFIG_MAXSMP=y +CONFIG_CPUMASK_OFFSTACK=y CONFIG_RCU_NOCB_CPU=y -CONFIG_RCU_NOCB_CPU_ZERO=y CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y -CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y -CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y -CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot index adc3abc82fb8..1d14e1383016 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot @@ -1 +1,5 @@ rcutorture.torture_type=rcu_bh maxcpus=8 +rcutree.gp_preinit_delay=3 +rcutree.gp_init_delay=3 +rcutree.gp_cleanup_delay=3 +rcu_nocbs=0 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02 b/tools/testing/selftests/rcutorture/configs/rcu/TREE02 index c1ab5926568b..35e639e39366 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE02 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02 @@ -18,9 +18,6 @@ CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=n CONFIG_RCU_BOOST=n -CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y -CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y -CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y -CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y +CONFIG_DEBUG_OBJECTS=y CONFIG_DEBUG_OBJECTS_RCU_HEAD=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE03 b/tools/testing/selftests/rcutorture/configs/rcu/TREE03 index 3b93ee544e70..2dc31b16e506 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE03 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03 @@ -14,9 +14,5 @@ CONFIG_RCU_FANOUT_LEAF=2 CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_RCU_BOOST=y -CONFIG_RCU_KTHREAD_PRIO=2 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y -CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y -CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y -CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot index 120c0c88d100..5d2cc0bd50a0 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot @@ -1 +1,5 @@ rcutorture.onoff_interval=1 rcutorture.onoff_holdoff=30 +rcutree.gp_preinit_delay=3 +rcutree.gp_init_delay=3 +rcutree.gp_cleanup_delay=3 +rcutree.kthread_prio=2 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 b/tools/testing/selftests/rcutorture/configs/rcu/TREE04 index 5af758e783c7..27d22695d64c 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04 @@ -15,11 +15,7 @@ CONFIG_SUSPEND=n CONFIG_HIBERNATION=n CONFIG_RCU_FANOUT=4 CONFIG_RCU_FANOUT_LEAF=3 -CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y -CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y -CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y -CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y CONFIG_RCU_EQS_DEBUG=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE05 b/tools/testing/selftests/rcutorture/configs/rcu/TREE05 index d4cdc0d74e16..2dde0d9964e3 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE05 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05 @@ -13,12 +13,8 @@ CONFIG_HOTPLUG_CPU=y CONFIG_RCU_FANOUT=6 CONFIG_RCU_FANOUT_LEAF=6 CONFIG_RCU_NOCB_CPU=y -CONFIG_RCU_NOCB_CPU_NONE=y CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y #CHECK#CONFIG_PROVE_RCU=y CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y -CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y -CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y -CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot index 15b3e1a86f74..c7fd050dfcd9 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot @@ -1,2 +1,5 @@ rcutorture.torture_type=sched rcupdate.rcu_self_test_sched=1 +rcutree.gp_preinit_delay=3 +rcutree.gp_init_delay=3 +rcutree.gp_cleanup_delay=3 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 b/tools/testing/selftests/rcutorture/configs/rcu/TREE06 index 4cb02bd28f08..05a4eec3f27b 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06 @@ -18,8 +18,6 @@ CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y #CHECK#CONFIG_PROVE_RCU=y +CONFIG_DEBUG_OBJECTS=y CONFIG_DEBUG_OBJECTS_RCU_HEAD=y CONFIG_RCU_EXPERT=y -CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y -CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y -CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE06.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE06.boot index dd90f28ed700..ad18b52a2cad 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE06.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06.boot @@ -2,3 +2,6 @@ rcupdate.rcu_self_test=1 rcupdate.rcu_self_test_bh=1 rcupdate.rcu_self_test_sched=1 rcutree.rcu_fanout_exact=1 +rcutree.gp_preinit_delay=3 +rcutree.gp_init_delay=3 +rcutree.gp_cleanup_delay=3 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 b/tools/testing/selftests/rcutorture/configs/rcu/TREE07 index b12a3ea1867e..0f4759f4232e 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07 @@ -1,6 +1,5 @@ CONFIG_SMP=y CONFIG_NR_CPUS=16 -CONFIG_CPUMASK_OFFSTACK=y CONFIG_PREEMPT_NONE=y CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n @@ -9,16 +8,11 @@ CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=n CONFIG_NO_HZ_FULL=y CONFIG_NO_HZ_FULL_ALL=n -CONFIG_NO_HZ_FULL_SYSIDLE=y CONFIG_RCU_FAST_NO_HZ=n CONFIG_RCU_TRACE=y CONFIG_HOTPLUG_CPU=y CONFIG_RCU_FANOUT=2 CONFIG_RCU_FANOUT_LEAF=2 -CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y -CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y -CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y -CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08 b/tools/testing/selftests/rcutorture/configs/rcu/TREE08 index 099cc63c6a3b..fb1c763c10c5 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08 @@ -15,7 +15,6 @@ CONFIG_HIBERNATION=n CONFIG_RCU_FANOUT=3 CONFIG_RCU_FANOUT_LEAF=2 CONFIG_RCU_NOCB_CPU=y -CONFIG_RCU_NOCB_CPU_ALL=y CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_PROVE_LOCKING=n CONFIG_RCU_BOOST=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T deleted file mode 100644 index 2ad13f0d29cc..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T +++ /dev/null @@ -1,21 +0,0 @@ -CONFIG_SMP=y -CONFIG_NR_CPUS=16 -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -#CHECK#CONFIG_PREEMPT_RCU=y -CONFIG_HZ_PERIODIC=n -CONFIG_NO_HZ_IDLE=y -CONFIG_NO_HZ_FULL=n -CONFIG_RCU_FAST_NO_HZ=n -CONFIG_RCU_TRACE=y -CONFIG_HOTPLUG_CPU=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_RCU_FANOUT=3 -CONFIG_RCU_FANOUT_LEAF=2 -CONFIG_RCU_NOCB_CPU=y -CONFIG_RCU_NOCB_CPU_ALL=y -CONFIG_DEBUG_LOCK_ALLOC=n -CONFIG_RCU_BOOST=n -CONFIG_DEBUG_OBJECTS_RCU_HEAD=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot index fb066dc82769..1bd8efc4141e 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot @@ -2,3 +2,4 @@ rcutorture.torture_type=sched rcupdate.rcu_self_test=1 rcupdate.rcu_self_test_sched=1 rcutree.rcu_fanout_exact=1 +rcu_nocbs=0-7 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T b/tools/testing/selftests/rcutorture/configs/rcuperf/TINY index 917d2517b5b5..fb05ef5279b4 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T +++ b/tools/testing/selftests/rcutorture/configs/rcuperf/TINY @@ -1,21 +1,16 @@ -CONFIG_SMP=y -CONFIG_NR_CPUS=8 -CONFIG_PREEMPT_NONE=n +CONFIG_SMP=n +CONFIG_PREEMPT_NONE=y CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -#CHECK#CONFIG_PREEMPT_RCU=y +CONFIG_PREEMPT=n +#CHECK#CONFIG_TINY_RCU=y CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=y CONFIG_NO_HZ_FULL=n CONFIG_RCU_FAST_NO_HZ=n -CONFIG_RCU_TRACE=y -CONFIG_HOTPLUG_CPU=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_RCU_FANOUT=3 -CONFIG_RCU_FANOUT_LEAF=3 CONFIG_RCU_NOCB_CPU=n -CONFIG_DEBUG_LOCK_ALLOC=y +CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_PROVE_LOCKING=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n +CONFIG_RCU_EXPERT=y +CONFIG_RCU_TRACE=y diff --git a/tools/testing/selftests/rcutorture/configs/rcuperf/TREE b/tools/testing/selftests/rcutorture/configs/rcuperf/TREE index a312f671a29a..721cfda76ab2 100644 --- a/tools/testing/selftests/rcutorture/configs/rcuperf/TREE +++ b/tools/testing/selftests/rcutorture/configs/rcuperf/TREE @@ -7,7 +7,6 @@ CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=y CONFIG_NO_HZ_FULL=n CONFIG_RCU_FAST_NO_HZ=n -CONFIG_RCU_TRACE=n CONFIG_HOTPLUG_CPU=n CONFIG_SUSPEND=n CONFIG_HIBERNATION=n diff --git a/tools/testing/selftests/rcutorture/configs/rcuperf/TREE54 b/tools/testing/selftests/rcutorture/configs/rcuperf/TREE54 index 985fb170d13c..7629f5dd73b2 100644 --- a/tools/testing/selftests/rcutorture/configs/rcuperf/TREE54 +++ b/tools/testing/selftests/rcutorture/configs/rcuperf/TREE54 @@ -8,7 +8,6 @@ CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=y CONFIG_NO_HZ_FULL=n CONFIG_RCU_FAST_NO_HZ=n -CONFIG_RCU_TRACE=n CONFIG_HOTPLUG_CPU=n CONFIG_SUSPEND=n CONFIG_HIBERNATION=n diff --git a/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt b/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt index 24396ae8355b..a75b16991a92 100644 --- a/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt +++ b/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt @@ -18,7 +18,6 @@ CONFIG_PROVE_RCU In common code tested by TREE_RCU test cases. -CONFIG_NO_HZ_FULL_SYSIDLE CONFIG_RCU_NOCB_CPU Meaningless for TINY_RCU. diff --git a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt index 364801b1a230..9ad3f89c8dc7 100644 --- a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt +++ b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt @@ -9,28 +9,20 @@ CONFIG_DEBUG_OBJECTS_RCU_HEAD -- Do one. CONFIG_HOTPLUG_CPU -- Do half. (Every second.) CONFIG_HZ_PERIODIC -- Do one. CONFIG_NO_HZ_IDLE -- Do those not otherwise specified. (Groups of two.) -CONFIG_NO_HZ_FULL -- Do two, one with CONFIG_NO_HZ_FULL_SYSIDLE. -CONFIG_NO_HZ_FULL_SYSIDLE -- Do one. +CONFIG_NO_HZ_FULL -- Do two, one with partial CPU enablement. CONFIG_PREEMPT -- Do half. (First three and #8.) CONFIG_PROVE_LOCKING -- Do several, covering CONFIG_DEBUG_LOCK_ALLOC=y and not. CONFIG_PROVE_RCU -- Hardwired to CONFIG_PROVE_LOCKING. -CONFIG_PROVE_RCU_REPEATEDLY -- Do one. CONFIG_RCU_BOOST -- one of PREEMPT_RCU. -CONFIG_RCU_KTHREAD_PRIO -- set to 2 for _BOOST testing. CONFIG_RCU_FANOUT -- Cover hierarchy, but overlap with others. CONFIG_RCU_FANOUT_LEAF -- Do one non-default. -CONFIG_RCU_FAST_NO_HZ -- Do one, but not with CONFIG_RCU_NOCB_CPU_ALL. -CONFIG_RCU_NOCB_CPU -- Do three, see below. -CONFIG_RCU_NOCB_CPU_ALL -- Do one. -CONFIG_RCU_NOCB_CPU_NONE -- Do one. -CONFIG_RCU_NOCB_CPU_ZERO -- Do one. +CONFIG_RCU_FAST_NO_HZ -- Do one, but not with all nohz_full CPUs. +CONFIG_RCU_NOCB_CPU -- Do three, one with no rcu_nocbs CPUs, one with + rcu_nocbs=0, and one with all rcu_nocbs CPUs. CONFIG_RCU_TRACE -- Do half. CONFIG_SMP -- Need one !SMP for PREEMPT_RCU. CONFIG_RCU_EXPERT=n -- Do a few, but these have to be vanilla configurations. CONFIG_RCU_EQS_DEBUG -- Do at least one for CONFIG_NO_HZ_FULL and not. -CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP -- Do for all but a couple TREE scenarios. -CONFIG_RCU_TORTURE_TEST_SLOW_INIT -- Do for all but a couple TREE scenarios. -CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT -- Do for all but a couple TREE scenarios. RCU-bh: Do one with PREEMPT and one with !PREEMPT. RCU-sched: Do one with PREEMPT but not BOOST. @@ -52,10 +44,6 @@ CONFIG_64BIT Used only to check CONFIG_RCU_FANOUT value, inspection suffices. -CONFIG_NO_HZ_FULL_SYSIDLE_SMALL - - Defer until Frederic uses this. - CONFIG_PREEMPT_COUNT CONFIG_PREEMPT_RCU @@ -78,30 +66,16 @@ CONFIG_RCU_TORTURE_TEST_RUNNABLE Always used in KVM testing. -CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT_DELAY -CONFIG_RCU_TORTURE_TEST_SLOW_INIT_DELAY -CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP_DELAY - - Inspection suffices, ignore. - CONFIG_PREEMPT_RCU CONFIG_TREE_RCU CONFIG_TINY_RCU These are controlled by CONFIG_PREEMPT and/or CONFIG_SMP. -CONFIG_SPARSE_RCU_POINTER - - Makes sense only for sparse runs, not for kernel builds. - CONFIG_SRCU CONFIG_TASKS_RCU Selected by CONFIG_RCU_TORTURE_TEST, so cannot disable. -CONFIG_RCU_TRACE - - Implied by CONFIG_RCU_TRACE for Tree RCU. - boot parameters ignored: TBD diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk index 8ff89043d0a9..c9e8bc5082a7 100755 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk @@ -1,4 +1,4 @@ -#!/bin/awk -f +#!/usr/bin/awk -f # Modify SRCU for formal verification. The first argument should be srcu.h and # the second should be srcu.c. Outputs modified srcu.h and srcu.c into the diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index a8d540398bbd..9120edf3c94b 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -184,7 +184,7 @@ int __attribute__((weak)) kvm_arch_set_irq_inatomic( * Called with wqh->lock held and interrupts disabled */ static int -irqfd_wakeup(wait_queue_t *wait, unsigned mode, int sync, void *key) +irqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct kvm_kernel_irqfd *irqfd = container_of(wait, struct kvm_kernel_irqfd, wait); |