diff options
495 files changed, 28130 insertions, 7500 deletions
@@ -1412,8 +1412,8 @@ P: 1024D/77D4FC9B F5C5 1C20 1DFC DEC3 3107 54A4 2332 ADFC 77D4 FC9B D: National Language Support D: Linux Internationalization Project D: German Localization for Linux and GNU software -S: Kriemhildring 12a -S: 65795 Hattersheim am Main +S: Auf der Fittel 18 +S: 53347 Alfter S: Germany N: Christoph Hellwig @@ -3580,6 +3580,12 @@ N: Dirk Verworner D: Co-author of German book ``Linux-Kernel-Programmierung'' D: Co-founder of Berlin Linux User Group +N: Riku Voipio +E: riku.voipio@iki.fi +D: Author of PCA9532 LED and Fintek f75375s hwmon driver +D: Some random ARM board patches +S: Finland + N: Patrick Volkerding E: volkerdi@ftp.cdrom.com D: Produced the Slackware distribution, updated the SVGAlib diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX index 2a39aeba1464..d05737aaa84b 100644 --- a/Documentation/00-INDEX +++ b/Documentation/00-INDEX @@ -86,6 +86,8 @@ cachetlb.txt - describes the cache/TLB flushing interfaces Linux uses. cdrom/ - directory with information on the CD-ROM drivers that Linux has. +cgroups/ + - cgroups features, including cpusets and memory controller. connector/ - docs on the netlink based userspace<->kernel space communication mod. console/ @@ -98,8 +100,6 @@ cpu-load.txt - document describing how CPU load statistics are collected. cpuidle/ - info on CPU_IDLE, CPU idle state management subsystem. -cpusets.txt - - documents the cpusets feature; assign CPUs and Mem to a set of tasks. cputopology.txt - documentation on how CPU topology info is exported via sysfs. cris/ diff --git a/Documentation/ABI/testing/debugfs-kmemtrace b/Documentation/ABI/testing/debugfs-kmemtrace new file mode 100644 index 000000000000..5e6a92a02d85 --- /dev/null +++ b/Documentation/ABI/testing/debugfs-kmemtrace @@ -0,0 +1,71 @@ +What: /sys/kernel/debug/kmemtrace/ +Date: July 2008 +Contact: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> +Description: + +In kmemtrace-enabled kernels, the following files are created: + +/sys/kernel/debug/kmemtrace/ + cpu<n> (0400) Per-CPU tracing data, see below. (binary) + total_overruns (0400) Total number of bytes which were dropped from + cpu<n> files because of full buffer condition, + non-binary. (text) + abi_version (0400) Kernel's kmemtrace ABI version. (text) + +Each per-CPU file should be read according to the relay interface. That is, +the reader should set affinity to that specific CPU and, as currently done by +the userspace application (though there are other methods), use poll() with +an infinite timeout before every read(). Otherwise, erroneous data may be +read. The binary data has the following _core_ format: + + Event ID (1 byte) Unsigned integer, one of: + 0 - represents an allocation (KMEMTRACE_EVENT_ALLOC) + 1 - represents a freeing of previously allocated memory + (KMEMTRACE_EVENT_FREE) + Type ID (1 byte) Unsigned integer, one of: + 0 - this is a kmalloc() / kfree() + 1 - this is a kmem_cache_alloc() / kmem_cache_free() + 2 - this is a __get_free_pages() et al. + Event size (2 bytes) Unsigned integer representing the + size of this event. Used to extend + kmemtrace. Discard the bytes you + don't know about. + Sequence number (4 bytes) Signed integer used to reorder data + logged on SMP machines. Wraparound + must be taken into account, although + it is unlikely. + Caller address (8 bytes) Return address to the caller. + Pointer to mem (8 bytes) Pointer to target memory area. Can be + NULL, but not all such calls might be + recorded. + +In case of KMEMTRACE_EVENT_ALLOC events, the next fields follow: + + Requested bytes (8 bytes) Total number of requested bytes, + unsigned, must not be zero. + Allocated bytes (8 bytes) Total number of actually allocated + bytes, unsigned, must not be lower + than requested bytes. + Requested flags (4 bytes) GFP flags supplied by the caller. + Target CPU (4 bytes) Signed integer, valid for event id 1. + If equal to -1, target CPU is the same + as origin CPU, but the reverse might + not be true. + +The data is made available in the same endianness the machine has. + +Other event ids and type ids may be defined and added. Other fields may be +added by increasing event size, but see below for details. +Every modification to the ABI, including new id definitions, are followed +by bumping the ABI version by one. + +Adding new data to the packet (features) is done at the end of the mandatory +data: + Feature size (2 byte) + Feature ID (1 byte) + Feature data (Feature size - 3 bytes) + + +Users: + kmemtrace-user - git://repo.or.cz/kmemtrace-user.git + diff --git a/Documentation/cgroups/00-INDEX b/Documentation/cgroups/00-INDEX new file mode 100644 index 000000000000..3f58fa3d6d00 --- /dev/null +++ b/Documentation/cgroups/00-INDEX @@ -0,0 +1,18 @@ +00-INDEX + - this file +cgroups.txt + - Control Groups definition, implementation details, examples and API. +cpuacct.txt + - CPU Accounting Controller; account CPU usage for groups of tasks. +cpusets.txt + - documents the cpusets feature; assign CPUs and Mem to a set of tasks. +devices.txt + - Device Whitelist Controller; description, interface and security. +freezer-subsystem.txt + - checkpointing; rationale to not use signals, interface. +memcg_test.txt + - Memory Resource Controller; implementation details. +memory.txt + - Memory Resource Controller; design, accounting, interface, testing. +resource_counter.txt + - Resource Counter API. diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt index 4ea852345a47..6eb1a97e88ce 100644 --- a/Documentation/cgroups/cgroups.txt +++ b/Documentation/cgroups/cgroups.txt @@ -56,7 +56,7 @@ hierarchy, and a set of subsystems; each subsystem has system-specific state attached to each cgroup in the hierarchy. Each hierarchy has an instance of the cgroup virtual filesystem associated with it. -At any one time there may be multiple active hierachies of task +At any one time there may be multiple active hierarchies of task cgroups. Each hierarchy is a partition of all tasks in the system. User level code may create and destroy cgroups by name in an @@ -124,10 +124,10 @@ following lines: / \ Prof (15%) students (5%) -Browsers like firefox/lynx go into the WWW network class, while (k)nfsd go +Browsers like Firefox/Lynx go into the WWW network class, while (k)nfsd go into NFS network class. -At the same time firefox/lynx will share an appropriate CPU/Memory class +At the same time Firefox/Lynx will share an appropriate CPU/Memory class depending on who launched it (prof/student). With the ability to classify tasks differently for different resources @@ -325,7 +325,7 @@ and then start a subshell 'sh' in that cgroup: Creating, modifying, using the cgroups can be done through the cgroup virtual filesystem. -To mount a cgroup hierarchy will all available subsystems, type: +To mount a cgroup hierarchy with all available subsystems, type: # mount -t cgroup xxx /dev/cgroup The "xxx" is not interpreted by the cgroup code, but will appear in @@ -539,7 +539,7 @@ always handled well. void post_clone(struct cgroup_subsys *ss, struct cgroup *cgrp) (cgroup_mutex held by caller) -Called at the end of cgroup_clone() to do any paramater +Called at the end of cgroup_clone() to do any parameter initialization which might be required before a task could attach. For example in cpusets, no task may attach before 'cpus' and 'mems' are set up. diff --git a/Documentation/cgroups/cpusets.txt b/Documentation/cgroups/cpusets.txt index 0611e9528c7c..f9ca389dddf4 100644 --- a/Documentation/cgroups/cpusets.txt +++ b/Documentation/cgroups/cpusets.txt @@ -131,7 +131,7 @@ Cpusets extends these two mechanisms as follows: - The hierarchy of cpusets can be mounted at /dev/cpuset, for browsing and manipulation from user space. - A cpuset may be marked exclusive, which ensures that no other - cpuset (except direct ancestors and descendents) may contain + cpuset (except direct ancestors and descendants) may contain any overlapping CPUs or Memory Nodes. - You can list all the tasks (by pid) attached to any cpuset. @@ -226,7 +226,7 @@ nodes with memory--using the cpuset_track_online_nodes() hook. -------------------------------- If a cpuset is cpu or mem exclusive, no other cpuset, other than -a direct ancestor or descendent, may share any of the same CPUs or +a direct ancestor or descendant, may share any of the same CPUs or Memory Nodes. A cpuset that is mem_exclusive *or* mem_hardwall is "hardwalled", @@ -427,7 +427,7 @@ child cpusets have this flag enabled. When doing this, you don't usually want to leave any unpinned tasks in the top cpuset that might use non-trivial amounts of CPU, as such tasks may be artificially constrained to some subset of CPUs, depending on -the particulars of this flag setting in descendent cpusets. Even if +the particulars of this flag setting in descendant cpusets. Even if such a task could use spare CPU cycles in some other CPUs, the kernel scheduler might not consider the possibility of load balancing that task to that underused CPU. @@ -531,9 +531,9 @@ be idle. Of course it takes some searching cost to find movable tasks and/or idle CPUs, the scheduler might not search all CPUs in the domain -everytime. In fact, in some architectures, the searching ranges on +every time. In fact, in some architectures, the searching ranges on events are limited in the same socket or node where the CPU locates, -while the load balance on tick searchs all. +while the load balance on tick searches all. For example, assume CPU Z is relatively far from CPU X. Even if CPU Z is idle while CPU X and the siblings are busy, scheduler can't migrate @@ -601,7 +601,7 @@ its new cpuset, then the task will continue to use whatever subset of MPOL_BIND nodes are still allowed in the new cpuset. If the task was using MPOL_BIND and now none of its MPOL_BIND nodes are allowed in the new cpuset, then the task will be essentially treated as if it -was MPOL_BIND bound to the new cpuset (even though its numa placement, +was MPOL_BIND bound to the new cpuset (even though its NUMA placement, as queried by get_mempolicy(), doesn't change). If a task is moved from one cpuset to another, then the kernel will adjust the tasks memory placement, as above, the next time that the kernel attempts diff --git a/Documentation/cgroups/devices.txt b/Documentation/cgroups/devices.txt index 7cc6e6a60672..57ca4c89fe5c 100644 --- a/Documentation/cgroups/devices.txt +++ b/Documentation/cgroups/devices.txt @@ -42,7 +42,7 @@ suffice, but we can decide the best way to adequately restrict movement as people get some experience with this. We may just want to require CAP_SYS_ADMIN, which at least is a separate bit from CAP_MKNOD. We may want to just refuse moving to a cgroup which -isn't a descendent of the current one. Or we may want to use +isn't a descendant of the current one. Or we may want to use CAP_MAC_ADMIN, since we really are trying to lock down root. CAP_SYS_ADMIN is needed to modify the whitelist or move another diff --git a/Documentation/cgroups/memcg_test.txt b/Documentation/cgroups/memcg_test.txt index 8a11caf417a0..72db89ed0609 100644 --- a/Documentation/cgroups/memcg_test.txt +++ b/Documentation/cgroups/memcg_test.txt @@ -356,7 +356,7 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y. (Shell-B) # move all tasks in /cgroup/test to /cgroup # /sbin/swapoff -a - # rmdir /test/cgroup + # rmdir /cgroup/test # kill malloc task. Of course, tmpfs v.s. swapoff test should be tested, too. diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt index e1501964df1e..a98a7fe7aabb 100644 --- a/Documentation/cgroups/memory.txt +++ b/Documentation/cgroups/memory.txt @@ -302,7 +302,7 @@ will be charged as a new owner of it. unevictable - # of pages cannot be reclaimed.(mlocked etc) Below is depend on CONFIG_DEBUG_VM. - inactive_ratio - VM inernal parameter. (see mm/page_alloc.c) + inactive_ratio - VM internal parameter. (see mm/page_alloc.c) recent_rotated_anon - VM internal parameter. (see mm/vmscan.c) recent_rotated_file - VM internal parameter. (see mm/vmscan.c) recent_scanned_anon - VM internal parameter. (see mm/vmscan.c) diff --git a/Documentation/devices.txt b/Documentation/devices.txt index 62254d4510c6..327de1624759 100644 --- a/Documentation/devices.txt +++ b/Documentation/devices.txt @@ -1,7 +1,7 @@ LINUX ALLOCATED DEVICES (2.6+ version) - Maintained by Torben Mathiasen <device@lanana.org> + Maintained by Alan Cox <device@lanana.org> Last revised: 29 November 2006 @@ -67,6 +67,11 @@ up to date. Due to the number of registrations I have to maintain it in "batch mode", so there is likely additional registrations that haven't been listed yet. +Fourth, remember that Linux now has extensive support for dynamic allocation +of device numbering and can use sysfs and udev to handle the naming needs. +There are still some exceptions in the serial and boot device area. Before +asking for a device number make sure you actually need one. + Finally, sometimes I have to play "namespace police." Please don't be offended. I often get submissions for /dev names that would be bound to cause conflicts down the road. I am trying to avoid getting in a @@ -101,7 +106,7 @@ Your cooperation is appreciated. 0 = /dev/ram0 First RAM disk 1 = /dev/ram1 Second RAM disk ... - 250 = /dev/initrd Initial RAM disk {2.6} + 250 = /dev/initrd Initial RAM disk Older kernels had /dev/ramdisk (1, 1) here. /dev/initrd refers to a RAM disk which was preloaded @@ -340,7 +345,7 @@ Your cooperation is appreciated. 14 = /dev/touchscreen/ucb1x00 UCB 1x00 touchscreen 15 = /dev/touchscreen/mk712 MK712 touchscreen 128 = /dev/beep Fancy beep device - 129 = /dev/modreq Kernel module load request {2.6} + 129 = 130 = /dev/watchdog Watchdog timer port 131 = /dev/temperature Machine internal temperature 132 = /dev/hwtrap Hardware fault trap @@ -350,10 +355,10 @@ Your cooperation is appreciated. 139 = /dev/openprom SPARC OpenBoot PROM 140 = /dev/relay8 Berkshire Products Octal relay card 141 = /dev/relay16 Berkshire Products ISO-16 relay card - 142 = /dev/msr x86 model-specific registers {2.6} + 142 = 143 = /dev/pciconf PCI configuration space 144 = /dev/nvram Non-volatile configuration RAM - 145 = /dev/hfmodem Soundcard shortwave modem control {2.6} + 145 = /dev/hfmodem Soundcard shortwave modem control 146 = /dev/graphics Linux/SGI graphics device 147 = /dev/opengl Linux/SGI OpenGL pipe 148 = /dev/gfx Linux/SGI graphics effects device @@ -435,6 +440,9 @@ Your cooperation is appreciated. 228 = /dev/hpet HPET driver 229 = /dev/fuse Fuse (virtual filesystem in user-space) 230 = /dev/midishare MidiShare driver + 231 = /dev/snapshot System memory snapshot device + 232 = /dev/kvm Kernel-based virtual machine (hardware virtualization extensions) + 233 = /dev/kmview View-OS A process with a view 240-254 Reserved for local use 255 Reserved for MISC_DYNAMIC_MINOR @@ -466,10 +474,7 @@ Your cooperation is appreciated. The device names specified are proposed -- if there are "standard" names for these devices, please let me know. - 12 block MSCDEX CD-ROM callback support {2.6} - 0 = /dev/dos_cd0 First MSCDEX CD-ROM - 1 = /dev/dos_cd1 Second MSCDEX CD-ROM - ... + 12 block 13 char Input core 0 = /dev/input/js0 First joystick @@ -498,7 +503,7 @@ Your cooperation is appreciated. 2 = /dev/midi00 First MIDI port 3 = /dev/dsp Digital audio 4 = /dev/audio Sun-compatible digital audio - 6 = /dev/sndstat Sound card status information {2.6} + 6 = 7 = /dev/audioctl SPARC audio control device 8 = /dev/sequencer2 Sequencer -- alternate device 16 = /dev/mixer1 Second soundcard mixer control @@ -510,14 +515,7 @@ Your cooperation is appreciated. 34 = /dev/midi02 Third MIDI port 50 = /dev/midi03 Fourth MIDI port - 14 block BIOS harddrive callback support {2.6} - 0 = /dev/dos_hda First BIOS harddrive whole disk - 64 = /dev/dos_hdb Second BIOS harddrive whole disk - 128 = /dev/dos_hdc Third BIOS harddrive whole disk - 192 = /dev/dos_hdd Fourth BIOS harddrive whole disk - - Partitions are handled in the same way as IDE disks - (see major number 3). + 14 block 15 char Joystick 0 = /dev/js0 First analog joystick @@ -535,14 +533,14 @@ Your cooperation is appreciated. 16 block GoldStar CD-ROM 0 = /dev/gscd GoldStar CD-ROM - 17 char Chase serial card + 17 char OBSOLETE (was Chase serial card) 0 = /dev/ttyH0 First Chase port 1 = /dev/ttyH1 Second Chase port ... 17 block Optics Storage CD-ROM 0 = /dev/optcd Optics Storage CD-ROM - 18 char Chase serial card - alternate devices + 18 char OBSOLETE (was Chase serial card - alternate devices) 0 = /dev/cuh0 Callout device for ttyH0 1 = /dev/cuh1 Callout device for ttyH1 ... @@ -644,8 +642,7 @@ Your cooperation is appreciated. 2 = /dev/sbpcd2 Panasonic CD-ROM controller 0 unit 2 3 = /dev/sbpcd3 Panasonic CD-ROM controller 0 unit 3 - 26 char Quanta WinVision frame grabber {2.6} - 0 = /dev/wvisfgrab Quanta WinVision frame grabber + 26 char 26 block Second Matsushita (Panasonic/SoundBlaster) CD-ROM 0 = /dev/sbpcd4 Panasonic CD-ROM controller 1 unit 0 @@ -872,7 +869,7 @@ Your cooperation is appreciated. and "user level packet I/O." This board is also accessible as a standard networking "eth" device. - 38 block Reserved for Linux/AP+ + 38 block OBSOLETE (was Linux/AP+) 39 char ML-16P experimental I/O board 0 = /dev/ml16pa-a0 First card, first analog channel @@ -892,29 +889,16 @@ Your cooperation is appreciated. 50 = /dev/ml16pb-c1 Second card, second counter/timer 51 = /dev/ml16pb-c2 Second card, third counter/timer ... - 39 block Reserved for Linux/AP+ + 39 block - 40 char Matrox Meteor frame grabber {2.6} - 0 = /dev/mmetfgrab Matrox Meteor frame grabber + 40 char - 40 block Syquest EZ135 parallel port removable drive - 0 = /dev/eza Parallel EZ135 drive, whole disk - - This device is obsolete and will be removed in a - future version of Linux. It has been replaced with - the parallel port IDE disk driver at major number 45. - Partitions are handled in the same way as IDE disks - (see major number 3). + 40 block 41 char Yet Another Micro Monitor 0 = /dev/yamm Yet Another Micro Monitor - 41 block MicroSolutions BackPack parallel port CD-ROM - 0 = /dev/bpcd BackPack CD-ROM - - This device is obsolete and will be removed in a - future version of Linux. It has been replaced with - the parallel port ATAPI CD-ROM driver at major number 46. + 41 block 42 char Demo/sample use @@ -1681,13 +1665,7 @@ Your cooperation is appreciated. disks (see major number 3) except that the limit on partitions is 15. - 93 char IBM Smart Capture Card frame grabber {2.6} - 0 = /dev/iscc0 First Smart Capture Card - 1 = /dev/iscc1 Second Smart Capture Card - ... - 128 = /dev/isccctl0 First Smart Capture Card control - 129 = /dev/isccctl1 Second Smart Capture Card control - ... + 93 char 93 block NAND Flash Translation Layer filesystem 0 = /dev/nftla First NFTL layer @@ -1695,10 +1673,7 @@ Your cooperation is appreciated. ... 240 = /dev/nftlp 16th NTFL layer - 94 char miroVIDEO DC10/30 capture/playback device {2.6} - 0 = /dev/dcxx0 First capture card - 1 = /dev/dcxx1 Second capture card - ... + 94 char 94 block IBM S/390 DASD block storage 0 = /dev/dasda First DASD device, major @@ -1791,11 +1766,7 @@ Your cooperation is appreciated. ... 15 = /dev/amiraid/ar?p15 15th partition -102 char Philips SAA5249 Teletext signal decoder {2.6} - 0 = /dev/tlk0 First Teletext decoder - 1 = /dev/tlk1 Second Teletext decoder - 2 = /dev/tlk2 Third Teletext decoder - 3 = /dev/tlk3 Fourth Teletext decoder +102 char 102 block Compressed block device 0 = /dev/cbd/a First compressed block device, whole device @@ -1916,10 +1887,7 @@ Your cooperation is appreciated. DAC960 (see major number 48) except that the limit on partitions is 15. -111 char Philips SAA7146-based audio/video card {2.6} - 0 = /dev/av0 First A/V card - 1 = /dev/av1 Second A/V card - ... +111 char 111 block Compaq Next Generation Drive Array, eighth controller 0 = /dev/cciss/c7d0 First logical drive, whole disk @@ -2079,8 +2047,8 @@ Your cooperation is appreciated. ... 119 char VMware virtual network control - 0 = /dev/vmnet0 1st virtual network - 1 = /dev/vmnet1 2nd virtual network + 0 = /dev/vnet0 1st virtual network + 1 = /dev/vnet1 2nd virtual network ... 120-127 char LOCAL/EXPERIMENTAL USE @@ -2450,7 +2418,7 @@ Your cooperation is appreciated. 2 = /dev/raw/raw2 Second raw I/O device ... -163 char UNASSIGNED (was Radio Tech BIM-XXX-RS232 radio modem - see 51) +163 char 164 char Chase Research AT/PCI-Fast serial card 0 = /dev/ttyCH0 AT/PCI-Fast board 0, port 0 @@ -2542,6 +2510,12 @@ Your cooperation is appreciated. 1 = /dev/clanvi1 Second cLAN adapter ... +179 block MMC block devices + 0 = /dev/mmcblk0 First SD/MMC card + 1 = /dev/mmcblk0p1 First partition on first MMC card + 8 = /dev/mmcblk1 Second SD/MMC card + ... + 179 char CCube DVXChip-based PCI products 0 = /dev/dvxirq0 First DVX device 1 = /dev/dvxirq1 Second DVX device @@ -2560,6 +2534,9 @@ Your cooperation is appreciated. 96 = /dev/usb/hiddev0 1st USB HID device ... 111 = /dev/usb/hiddev15 16th USB HID device + 112 = /dev/usb/auer0 1st auerswald ISDN device + ... + 127 = /dev/usb/auer15 16th auerswald ISDN device 128 = /dev/usb/brlvgr0 First Braille Voyager device ... 131 = /dev/usb/brlvgr3 Fourth Braille Voyager device @@ -2810,6 +2787,16 @@ Your cooperation is appreciated. ... 190 = /dev/ttyUL3 Xilinx uartlite - port 3 191 = /dev/xvc0 Xen virtual console - port 0 + 192 = /dev/ttyPZ0 pmac_zilog - port 0 + ... + 195 = /dev/ttyPZ3 pmac_zilog - port 3 + 196 = /dev/ttyTX0 TX39/49 serial port 0 + ... + 204 = /dev/ttyTX7 TX39/49 serial port 7 + 205 = /dev/ttySC0 SC26xx serial port 0 + 206 = /dev/ttySC1 SC26xx serial port 1 + 207 = /dev/ttySC2 SC26xx serial port 2 + 208 = /dev/ttySC3 SC26xx serial port 3 205 char Low-density serial ports (alternate device) 0 = /dev/culu0 Callout device for ttyLU0 @@ -3145,6 +3132,14 @@ Your cooperation is appreciated. 1 = /dev/blockrom1 Second ROM card's translation layer interface ... +259 block Block Extended Major + Used dynamically to hold additional partition minor + numbers and allow large numbers of partitions per device + +259 char FPGA configuration interfaces + 0 = /dev/icap0 First Xilinx internal configuration + 1 = /dev/icap1 Second Xilinx internal configuration + 260 char OSD (Object-based-device) SCSI Device 0 = /dev/osd0 First OSD Device 1 = /dev/osd1 Second OSD Device diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index a23361e80c64..39246fc11257 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -283,13 +283,6 @@ Who: Glauber Costa <gcosta@redhat.com> --------------------------- -What: remove HID compat support -When: 2.6.29 -Why: needed only as a temporary solution until distros fix themselves up -Who: Jiri Slaby <jirislaby@gmail.com> - ---------------------------- - What: print_fn_descriptor_symbol() When: October 2009 Why: The %pF vsprintf format provides the same functionality in a diff --git a/Documentation/filesystems/ext3.txt b/Documentation/filesystems/ext3.txt index e5f3833a6ef8..570f9bd9be2b 100644 --- a/Documentation/filesystems/ext3.txt +++ b/Documentation/filesystems/ext3.txt @@ -14,6 +14,11 @@ Options When mounting an ext3 filesystem, the following option are accepted: (*) == default +ro Mount filesystem read only. Note that ext3 will replay + the journal (and thus write to the partition) even when + mounted "read only". Mount options "ro,noload" can be + used to prevent writes to the filesystem. + journal=update Update the ext3 file system's journal to the current format. @@ -27,7 +32,9 @@ journal_dev=devnum When the external journal device's major/minor numbers identified through its new major/minor numbers encoded in devnum. -noload Don't load the journal on mounting. +noload Don't load the journal on mounting. Note that this forces + mount of inconsistent filesystem, which can lead to + various problems. data=journal All data are committed into the journal prior to being written into the main file system. @@ -92,9 +99,12 @@ nocheck debug Extra debugging information is sent to syslog. -errors=remount-ro(*) Remount the filesystem read-only on an error. +errors=remount-ro Remount the filesystem read-only on an error. errors=continue Keep going on a filesystem error. errors=panic Panic and halt the machine if an error occurs. + (These mount options override the errors behavior + specified in the superblock, which can be + configured using tune2fs.) data_err=ignore(*) Just print an error message if an error occurs in a file data buffer in ordered mode. diff --git a/Documentation/ftrace.txt b/Documentation/ftrace.txt index 803b1318b13d..fd9a3e693813 100644 --- a/Documentation/ftrace.txt +++ b/Documentation/ftrace.txt @@ -15,31 +15,31 @@ Introduction Ftrace is an internal tracer designed to help out developers and designers of systems to find what is going on inside the kernel. -It can be used for debugging or analyzing latencies and performance -issues that take place outside of user-space. +It can be used for debugging or analyzing latencies and +performance issues that take place outside of user-space. Although ftrace is the function tracer, it also includes an -infrastructure that allows for other types of tracing. Some of the -tracers that are currently in ftrace include a tracer to trace -context switches, the time it takes for a high priority task to -run after it was woken up, the time interrupts are disabled, and -more (ftrace allows for tracer plugins, which means that the list of -tracers can always grow). +infrastructure that allows for other types of tracing. Some of +the tracers that are currently in ftrace include a tracer to +trace context switches, the time it takes for a high priority +task to run after it was woken up, the time interrupts are +disabled, and more (ftrace allows for tracer plugins, which +means that the list of tracers can always grow). The File System --------------- -Ftrace uses the debugfs file system to hold the control files as well -as the files to display output. +Ftrace uses the debugfs file system to hold the control files as +well as the files to display output. To mount the debugfs system: # mkdir /debug # mount -t debugfs nodev /debug -(Note: it is more common to mount at /sys/kernel/debug, but for simplicity - this document will use /debug) +( Note: it is more common to mount at /sys/kernel/debug, but for + simplicity this document will use /debug) That's it! (assuming that you have ftrace configured into your kernel) @@ -50,90 +50,124 @@ of ftrace. Here is a list of some of the key files: Note: all time values are in microseconds. - current_tracer: This is used to set or display the current tracer - that is configured. - - available_tracers: This holds the different types of tracers that - have been compiled into the kernel. The tracers - listed here can be configured by echoing their name - into current_tracer. - - tracing_enabled: This sets or displays whether the current_tracer - is activated and tracing or not. Echo 0 into this - file to disable the tracer or 1 to enable it. - - trace: This file holds the output of the trace in a human readable - format (described below). - - latency_trace: This file shows the same trace but the information - is organized more to display possible latencies - in the system (described below). - - trace_pipe: The output is the same as the "trace" file but this - file is meant to be streamed with live tracing. - Reads from this file will block until new data - is retrieved. Unlike the "trace" and "latency_trace" - files, this file is a consumer. This means reading - from this file causes sequential reads to display - more current data. Once data is read from this - file, it is consumed, and will not be read - again with a sequential read. The "trace" and - "latency_trace" files are static, and if the - tracer is not adding more data, they will display - the same information every time they are read. - - trace_options: This file lets the user control the amount of data - that is displayed in one of the above output - files. - - trace_max_latency: Some of the tracers record the max latency. - For example, the time interrupts are disabled. - This time is saved in this file. The max trace - will also be stored, and displayed by either - "trace" or "latency_trace". A new max trace will - only be recorded if the latency is greater than - the value in this file. (in microseconds) - - buffer_size_kb: This sets or displays the number of kilobytes each CPU - buffer can hold. The tracer buffers are the same size - for each CPU. The displayed number is the size of the - CPU buffer and not total size of all buffers. The - trace buffers are allocated in pages (blocks of memory - that the kernel uses for allocation, usually 4 KB in size). - If the last page allocated has room for more bytes - than requested, the rest of the page will be used, - making the actual allocation bigger than requested. - (Note, the size may not be a multiple of the page size due - to buffer managment overhead.) - - This can only be updated when the current_tracer - is set to "nop". - - tracing_cpumask: This is a mask that lets the user only trace - on specified CPUS. The format is a hex string - representing the CPUS. - - set_ftrace_filter: When dynamic ftrace is configured in (see the - section below "dynamic ftrace"), the code is dynamically - modified (code text rewrite) to disable calling of the - function profiler (mcount). This lets tracing be configured - in with practically no overhead in performance. This also - has a side effect of enabling or disabling specific functions - to be traced. Echoing names of functions into this file - will limit the trace to only those functions. - - set_ftrace_notrace: This has an effect opposite to that of - set_ftrace_filter. Any function that is added here will not - be traced. If a function exists in both set_ftrace_filter - and set_ftrace_notrace, the function will _not_ be traced. - - set_ftrace_pid: Have the function tracer only trace a single thread. - - available_filter_functions: This lists the functions that ftrace - has processed and can trace. These are the function - names that you can pass to "set_ftrace_filter" or - "set_ftrace_notrace". (See the section "dynamic ftrace" - below for more details.) + current_tracer: + + This is used to set or display the current tracer + that is configured. + + available_tracers: + + This holds the different types of tracers that + have been compiled into the kernel. The + tracers listed here can be configured by + echoing their name into current_tracer. + + tracing_enabled: + + This sets or displays whether the current_tracer + is activated and tracing or not. Echo 0 into this + file to disable the tracer or 1 to enable it. + + trace: + + This file holds the output of the trace in a human + readable format (described below). + + latency_trace: + + This file shows the same trace but the information + is organized more to display possible latencies + in the system (described below). + + trace_pipe: + + The output is the same as the "trace" file but this + file is meant to be streamed with live tracing. + Reads from this file will block until new data + is retrieved. Unlike the "trace" and "latency_trace" + files, this file is a consumer. This means reading + from this file causes sequential reads to display + more current data. Once data is read from this + file, it is consumed, and will not be read + again with a sequential read. The "trace" and + "latency_trace" files are static, and if the + tracer is not adding more data, they will display + the same information every time they are read. + + trace_options: + + This file lets the user control the amount of data + that is displayed in one of the above output + files. + + tracing_max_latency: + + Some of the tracers record the max latency. + For example, the time interrupts are disabled. + This time is saved in this file. The max trace + will also be stored, and displayed by either + "trace" or "latency_trace". A new max trace will + only be recorded if the latency is greater than + the value in this file. (in microseconds) + + buffer_size_kb: + + This sets or displays the number of kilobytes each CPU + buffer can hold. The tracer buffers are the same size + for each CPU. The displayed number is the size of the + CPU buffer and not total size of all buffers. The + trace buffers are allocated in pages (blocks of memory + that the kernel uses for allocation, usually 4 KB in size). + If the last page allocated has room for more bytes + than requested, the rest of the page will be used, + making the actual allocation bigger than requested. + ( Note, the size may not be a multiple of the page size + due to buffer managment overhead. ) + + This can only be updated when the current_tracer + is set to "nop". + + tracing_cpumask: + + This is a mask that lets the user only trace + on specified CPUS. The format is a hex string + representing the CPUS. + + set_ftrace_filter: + + When dynamic ftrace is configured in (see the + section below "dynamic ftrace"), the code is dynamically + modified (code text rewrite) to disable calling of the + function profiler (mcount). This lets tracing be configured + in with practically no overhead in performance. This also + has a side effect of enabling or disabling specific functions + to be traced. Echoing names of functions into this file + will limit the trace to only those functions. + + set_ftrace_notrace: + + This has an effect opposite to that of + set_ftrace_filter. Any function that is added here will not + be traced. If a function exists in both set_ftrace_filter + and set_ftrace_notrace, the function will _not_ be traced. + + set_ftrace_pid: + + Have the function tracer only trace a single thread. + + set_graph_function: + + Set a "trigger" function where tracing should start + with the function graph tracer (See the section + "dynamic ftrace" for more details). + + available_filter_functions: + + This lists the functions that ftrace + has processed and can trace. These are the function + names that you can pass to "set_ftrace_filter" or + "set_ftrace_notrace". (See the section "dynamic ftrace" + below for more details.) The Tracers @@ -141,36 +175,66 @@ The Tracers Here is the list of current tracers that may be configured. - function - function tracer that uses mcount to trace all functions. + "function" + + Function call tracer to trace all kernel functions. + + "function_graph_tracer" + + Similar to the function tracer except that the + function tracer probes the functions on their entry + whereas the function graph tracer traces on both entry + and exit of the functions. It then provides the ability + to draw a graph of function calls similar to C code + source. - sched_switch - traces the context switches between tasks. + "sched_switch" - irqsoff - traces the areas that disable interrupts and saves - the trace with the longest max latency. - See tracing_max_latency. When a new max is recorded, - it replaces the old trace. It is best to view this - trace via the latency_trace file. + Traces the context switches and wakeups between tasks. - preemptoff - Similar to irqsoff but traces and records the amount of - time for which preemption is disabled. + "irqsoff" - preemptirqsoff - Similar to irqsoff and preemptoff, but traces and - records the largest time for which irqs and/or preemption - is disabled. + Traces the areas that disable interrupts and saves + the trace with the longest max latency. + See tracing_max_latency. When a new max is recorded, + it replaces the old trace. It is best to view this + trace via the latency_trace file. - wakeup - Traces and records the max latency that it takes for - the highest priority task to get scheduled after - it has been woken up. + "preemptoff" - nop - This is not a tracer. To remove all tracers from tracing - simply echo "nop" into current_tracer. + Similar to irqsoff but traces and records the amount of + time for which preemption is disabled. + + "preemptirqsoff" + + Similar to irqsoff and preemptoff, but traces and + records the largest time for which irqs and/or preemption + is disabled. + + "wakeup" + + Traces and records the max latency that it takes for + the highest priority task to get scheduled after + it has been woken up. + + "hw-branch-tracer" + + Uses the BTS CPU feature on x86 CPUs to traces all + branches executed. + + "nop" + + This is the "trace nothing" tracer. To remove all + tracers from tracing simply echo "nop" into + current_tracer. Examples of using the tracer ---------------------------- -Here are typical examples of using the tracers when controlling them only -with the debugfs interface (without using any user-land utilities). +Here are typical examples of using the tracers when controlling +them only with the debugfs interface (without using any +user-land utilities). Output format: -------------- @@ -187,16 +251,16 @@ Here is an example of the output format of the file "trace" bash-4251 [01] 10152.583855: _atomic_dec_and_lock <-dput -------- -A header is printed with the tracer name that is represented by the trace. -In this case the tracer is "function". Then a header showing the format. Task -name "bash", the task PID "4251", the CPU that it was running on -"01", the timestamp in <secs>.<usecs> format, the function name that was -traced "path_put" and the parent function that called this function -"path_walk". The timestamp is the time at which the function was -entered. +A header is printed with the tracer name that is represented by +the trace. In this case the tracer is "function". Then a header +showing the format. Task name "bash", the task PID "4251", the +CPU that it was running on "01", the timestamp in <secs>.<usecs> +format, the function name that was traced "path_put" and the +parent function that called this function "path_walk". The +timestamp is the time at which the function was entered. -The sched_switch tracer also includes tracing of task wakeups and -context switches. +The sched_switch tracer also includes tracing of task wakeups +and context switches. ksoftirqd/1-7 [01] 1453.070013: 7:115:R + 2916:115:S ksoftirqd/1-7 [01] 1453.070013: 7:115:R + 10:115:S @@ -205,8 +269,8 @@ context switches. kondemand/1-2916 [01] 1453.070013: 2916:115:S ==> 7:115:R ksoftirqd/1-7 [01] 1453.070013: 7:115:S ==> 0:140:R -Wake ups are represented by a "+" and the context switches are shown as -"==>". The format is: +Wake ups are represented by a "+" and the context switches are +shown as "==>". The format is: Context switches: @@ -220,19 +284,20 @@ Wake ups are represented by a "+" and the context switches are shown as <pid>:<prio>:<state> + <pid>:<prio>:<state> -The prio is the internal kernel priority, which is the inverse of the -priority that is usually displayed by user-space tools. Zero represents -the highest priority (99). Prio 100 starts the "nice" priorities with -100 being equal to nice -20 and 139 being nice 19. The prio "140" is -reserved for the idle task which is the lowest priority thread (pid 0). +The prio is the internal kernel priority, which is the inverse +of the priority that is usually displayed by user-space tools. +Zero represents the highest priority (99). Prio 100 starts the +"nice" priorities with 100 being equal to nice -20 and 139 being +nice 19. The prio "140" is reserved for the idle task which is +the lowest priority thread (pid 0). Latency trace format -------------------- -For traces that display latency times, the latency_trace file gives -somewhat more information to see why a latency happened. Here is a typical -trace. +For traces that display latency times, the latency_trace file +gives somewhat more information to see why a latency happened. +Here is a typical trace. # tracer: irqsoff # @@ -259,20 +324,20 @@ irqsoff latency trace v1.1.5 on 2.6.26-rc8 <idle>-0 0d.s1 98us : trace_hardirqs_on (do_softirq) +This shows that the current tracer is "irqsoff" tracing the time +for which interrupts were disabled. It gives the trace version +and the version of the kernel upon which this was executed on +(2.6.26-rc8). Then it displays the max latency in microsecs (97 +us). The number of trace entries displayed and the total number +recorded (both are three: #3/3). The type of preemption that was +used (PREEMPT). VP, KP, SP, and HP are always zero and are +reserved for later use. #P is the number of online CPUS (#P:2). -This shows that the current tracer is "irqsoff" tracing the time for which -interrupts were disabled. It gives the trace version and the version -of the kernel upon which this was executed on (2.6.26-rc8). Then it displays -the max latency in microsecs (97 us). The number of trace entries displayed -and the total number recorded (both are three: #3/3). The type of -preemption that was used (PREEMPT). VP, KP, SP, and HP are always zero -and are reserved for later use. #P is the number of online CPUS (#P:2). - -The task is the process that was running when the latency occurred. -(swapper pid: 0). +The task is the process that was running when the latency +occurred. (swapper pid: 0). -The start and stop (the functions in which the interrupts were disabled and -enabled respectively) that caused the latencies: +The start and stop (the functions in which the interrupts were +disabled and enabled respectively) that caused the latencies: apic_timer_interrupt is where the interrupts were disabled. do_softirq is where they were enabled again. @@ -308,12 +373,12 @@ The above is mostly meaningful for kernel developers. latency_trace file is relative to the start of the trace. delay: This is just to help catch your eye a bit better. And - needs to be fixed to be only relative to the same CPU. - The marks are determined by the difference between this - current trace and the next trace. - '!' - greater than preempt_mark_thresh (default 100) - '+' - greater than 1 microsecond - ' ' - less than or equal to 1 microsecond. + needs to be fixed to be only relative to the same CPU. + The marks are determined by the difference between this + current trace and the next trace. + '!' - greater than preempt_mark_thresh (default 100) + '+' - greater than 1 microsecond + ' ' - less than or equal to 1 microsecond. The rest is the same as the 'trace' file. @@ -321,14 +386,15 @@ The above is mostly meaningful for kernel developers. trace_options ------------- -The trace_options file is used to control what gets printed in the trace -output. To see what is available, simply cat the file: +The trace_options file is used to control what gets printed in +the trace output. To see what is available, simply cat the file: cat /debug/tracing/trace_options print-parent nosym-offset nosym-addr noverbose noraw nohex nobin \ - noblock nostacktrace nosched-tree nouserstacktrace nosym-userobj + noblock nostacktrace nosched-tree nouserstacktrace nosym-userobj -To disable one of the options, echo in the option prepended with "no". +To disable one of the options, echo in the option prepended with +"no". echo noprint-parent > /debug/tracing/trace_options @@ -338,8 +404,8 @@ To enable an option, leave off the "no". Here are the available options: - print-parent - On function traces, display the calling function - as well as the function being traced. + print-parent - On function traces, display the calling (parent) + function as well as the function being traced. print-parent: bash-4000 [01] 1477.606694: simple_strtoul <-strict_strtoul @@ -348,15 +414,16 @@ Here are the available options: bash-4000 [01] 1477.606694: simple_strtoul - sym-offset - Display not only the function name, but also the offset - in the function. For example, instead of seeing just - "ktime_get", you will see "ktime_get+0xb/0x20". + sym-offset - Display not only the function name, but also the + offset in the function. For example, instead of + seeing just "ktime_get", you will see + "ktime_get+0xb/0x20". sym-offset: bash-4000 [01] 1477.606694: simple_strtoul+0x6/0xa0 - sym-addr - this will also display the function address as well as - the function name. + sym-addr - this will also display the function address as well + as the function name. sym-addr: bash-4000 [01] 1477.606694: simple_strtoul <c0339346> @@ -366,35 +433,41 @@ Here are the available options: bash 4000 1 0 00000000 00010a95 [58127d26] 1720.415ms \ (+0.000ms): simple_strtoul (strict_strtoul) - raw - This will display raw numbers. This option is best for use with - user applications that can translate the raw numbers better than - having it done in the kernel. + raw - This will display raw numbers. This option is best for + use with user applications that can translate the raw + numbers better than having it done in the kernel. - hex - Similar to raw, but the numbers will be in a hexadecimal format. + hex - Similar to raw, but the numbers will be in a hexadecimal + format. bin - This will print out the formats in raw binary. block - TBD (needs update) - stacktrace - This is one of the options that changes the trace itself. - When a trace is recorded, so is the stack of functions. - This allows for back traces of trace sites. + stacktrace - This is one of the options that changes the trace + itself. When a trace is recorded, so is the stack + of functions. This allows for back traces of + trace sites. - userstacktrace - This option changes the trace. - It records a stacktrace of the current userspace thread. + userstacktrace - This option changes the trace. It records a + stacktrace of the current userspace thread. - sym-userobj - when user stacktrace are enabled, look up which object the - address belongs to, and print a relative address - This is especially useful when ASLR is on, otherwise you don't - get a chance to resolve the address to object/file/line after the app is no - longer running + sym-userobj - when user stacktrace are enabled, look up which + object the address belongs to, and print a + relative address. This is especially useful when + ASLR is on, otherwise you don't get a chance to + resolve the address to object/file/line after + the app is no longer running - The lookup is performed when you read trace,trace_pipe,latency_trace. Example: + The lookup is performed when you read + trace,trace_pipe,latency_trace. Example: a.out-1623 [000] 40874.465068: /root/a.out[+0x480] <-/root/a.out[+0 x494] <- /root/a.out[+0x4a8] <- /lib/libc-2.7.so[+0x1e1a6] - sched-tree - TBD (any users??) + sched-tree - trace all tasks that are on the runqueue, at + every scheduling event. Will add overhead if + there's a lot of tasks running at once. sched_switch @@ -431,18 +504,19 @@ of how to use it. [...] -As we have discussed previously about this format, the header shows -the name of the trace and points to the options. The "FUNCTION" -is a misnomer since here it represents the wake ups and context -switches. +As we have discussed previously about this format, the header +shows the name of the trace and points to the options. The +"FUNCTION" is a misnomer since here it represents the wake ups +and context switches. -The sched_switch file only lists the wake ups (represented with '+') -and context switches ('==>') with the previous task or current task -first followed by the next task or task waking up. The format for both -of these is PID:KERNEL-PRIO:TASK-STATE. Remember that the KERNEL-PRIO -is the inverse of the actual priority with zero (0) being the highest -priority and the nice values starting at 100 (nice -20). Below is -a quick chart to map the kernel priority to user land priorities. +The sched_switch file only lists the wake ups (represented with +'+') and context switches ('==>') with the previous task or +current task first followed by the next task or task waking up. +The format for both of these is PID:KERNEL-PRIO:TASK-STATE. +Remember that the KERNEL-PRIO is the inverse of the actual +priority with zero (0) being the highest priority and the nice +values starting at 100 (nice -20). Below is a quick chart to map +the kernel priority to user land priorities. Kernel priority: 0 to 99 ==> user RT priority 99 to 0 Kernel priority: 100 to 139 ==> user nice -20 to 19 @@ -463,10 +537,10 @@ The task states are: ftrace_enabled -------------- -The following tracers (listed below) give different output depending -on whether or not the sysctl ftrace_enabled is set. To set ftrace_enabled, -one can either use the sysctl function or set it via the proc -file system interface. +The following tracers (listed below) give different output +depending on whether or not the sysctl ftrace_enabled is set. To +set ftrace_enabled, one can either use the sysctl function or +set it via the proc file system interface. sysctl kernel.ftrace_enabled=1 @@ -474,12 +548,12 @@ file system interface. echo 1 > /proc/sys/kernel/ftrace_enabled -To disable ftrace_enabled simply replace the '1' with '0' in -the above commands. +To disable ftrace_enabled simply replace the '1' with '0' in the +above commands. -When ftrace_enabled is set the tracers will also record the functions -that are within the trace. The descriptions of the tracers -will also show an example with ftrace enabled. +When ftrace_enabled is set the tracers will also record the +functions that are within the trace. The descriptions of the +tracers will also show an example with ftrace enabled. irqsoff @@ -487,17 +561,18 @@ irqsoff When interrupts are disabled, the CPU can not react to any other external event (besides NMIs and SMIs). This prevents the timer -interrupt from triggering or the mouse interrupt from letting the -kernel know of a new mouse event. The result is a latency with the -reaction time. +interrupt from triggering or the mouse interrupt from letting +the kernel know of a new mouse event. The result is a latency +with the reaction time. -The irqsoff tracer tracks the time for which interrupts are disabled. -When a new maximum latency is hit, the tracer saves the trace leading up -to that latency point so that every time a new maximum is reached, the old -saved trace is discarded and the new trace is saved. +The irqsoff tracer tracks the time for which interrupts are +disabled. When a new maximum latency is hit, the tracer saves +the trace leading up to that latency point so that every time a +new maximum is reached, the old saved trace is discarded and the +new trace is saved. -To reset the maximum, echo 0 into tracing_max_latency. Here is an -example: +To reset the maximum, echo 0 into tracing_max_latency. Here is +an example: # echo irqsoff > /debug/tracing/current_tracer # echo 0 > /debug/tracing/tracing_max_latency @@ -532,10 +607,11 @@ irqsoff latency trace v1.1.5 on 2.6.26 Here we see that that we had a latency of 12 microsecs (which is -very good). The _write_lock_irq in sys_setpgid disabled interrupts. -The difference between the 12 and the displayed timestamp 14us occurred -because the clock was incremented between the time of recording the max -latency and the time of recording the function that had that latency. +very good). The _write_lock_irq in sys_setpgid disabled +interrupts. The difference between the 12 and the displayed +timestamp 14us occurred because the clock was incremented +between the time of recording the max latency and the time of +recording the function that had that latency. Note the above example had ftrace_enabled not set. If we set the ftrace_enabled, we get a much larger output: @@ -586,24 +662,24 @@ irqsoff latency trace v1.1.5 on 2.6.26-rc8 Here we traced a 50 microsecond latency. But we also see all the -functions that were called during that time. Note that by enabling -function tracing, we incur an added overhead. This overhead may -extend the latency times. But nevertheless, this trace has provided -some very helpful debugging information. +functions that were called during that time. Note that by +enabling function tracing, we incur an added overhead. This +overhead may extend the latency times. But nevertheless, this +trace has provided some very helpful debugging information. preemptoff ---------- -When preemption is disabled, we may be able to receive interrupts but -the task cannot be preempted and a higher priority task must wait -for preemption to be enabled again before it can preempt a lower -priority task. +When preemption is disabled, we may be able to receive +interrupts but the task cannot be preempted and a higher +priority task must wait for preemption to be enabled again +before it can preempt a lower priority task. The preemptoff tracer traces the places that disable preemption. -Like the irqsoff tracer, it records the maximum latency for which preemption -was disabled. The control of preemptoff tracer is much like the irqsoff -tracer. +Like the irqsoff tracer, it records the maximum latency for +which preemption was disabled. The control of preemptoff tracer +is much like the irqsoff tracer. # echo preemptoff > /debug/tracing/current_tracer # echo 0 > /debug/tracing/tracing_max_latency @@ -637,11 +713,12 @@ preemptoff latency trace v1.1.5 on 2.6.26-rc8 sshd-4261 0d.s1 30us : trace_preempt_on (__do_softirq) -This has some more changes. Preemption was disabled when an interrupt -came in (notice the 'h'), and was enabled while doing a softirq. -(notice the 's'). But we also see that interrupts have been disabled -when entering the preempt off section and leaving it (the 'd'). -We do not know if interrupts were enabled in the mean time. +This has some more changes. Preemption was disabled when an +interrupt came in (notice the 'h'), and was enabled while doing +a softirq. (notice the 's'). But we also see that interrupts +have been disabled when entering the preempt off section and +leaving it (the 'd'). We do not know if interrupts were enabled +in the mean time. # tracer: preemptoff # @@ -700,28 +777,30 @@ preemptoff latency trace v1.1.5 on 2.6.26-rc8 sshd-4261 0d.s1 64us : trace_preempt_on (__do_softirq) -The above is an example of the preemptoff trace with ftrace_enabled -set. Here we see that interrupts were disabled the entire time. -The irq_enter code lets us know that we entered an interrupt 'h'. -Before that, the functions being traced still show that it is not -in an interrupt, but we can see from the functions themselves that -this is not the case. +The above is an example of the preemptoff trace with +ftrace_enabled set. Here we see that interrupts were disabled +the entire time. The irq_enter code lets us know that we entered +an interrupt 'h'. Before that, the functions being traced still +show that it is not in an interrupt, but we can see from the +functions themselves that this is not the case. -Notice that __do_softirq when called does not have a preempt_count. -It may seem that we missed a preempt enabling. What really happened -is that the preempt count is held on the thread's stack and we -switched to the softirq stack (4K stacks in effect). The code -does not copy the preempt count, but because interrupts are disabled, -we do not need to worry about it. Having a tracer like this is good -for letting people know what really happens inside the kernel. +Notice that __do_softirq when called does not have a +preempt_count. It may seem that we missed a preempt enabling. +What really happened is that the preempt count is held on the +thread's stack and we switched to the softirq stack (4K stacks +in effect). The code does not copy the preempt count, but +because interrupts are disabled, we do not need to worry about +it. Having a tracer like this is good for letting people know +what really happens inside the kernel. preemptirqsoff -------------- -Knowing the locations that have interrupts disabled or preemption -disabled for the longest times is helpful. But sometimes we would -like to know when either preemption and/or interrupts are disabled. +Knowing the locations that have interrupts disabled or +preemption disabled for the longest times is helpful. But +sometimes we would like to know when either preemption and/or +interrupts are disabled. Consider the following code: @@ -741,11 +820,13 @@ The preemptoff tracer will record the total length of call_function_with_irqs_and_preemption_off() and call_function_with_preemption_off(). -But neither will trace the time that interrupts and/or preemption -is disabled. This total time is the time that we can not schedule. -To record this time, use the preemptirqsoff tracer. +But neither will trace the time that interrupts and/or +preemption is disabled. This total time is the time that we can +not schedule. To record this time, use the preemptirqsoff +tracer. -Again, using this trace is much like the irqsoff and preemptoff tracers. +Again, using this trace is much like the irqsoff and preemptoff +tracers. # echo preemptirqsoff > /debug/tracing/current_tracer # echo 0 > /debug/tracing/tracing_max_latency @@ -781,9 +862,10 @@ preemptirqsoff latency trace v1.1.5 on 2.6.26-rc8 The trace_hardirqs_off_thunk is called from assembly on x86 when -interrupts are disabled in the assembly code. Without the function -tracing, we do not know if interrupts were enabled within the preemption -points. We do see that it started with preemption enabled. +interrupts are disabled in the assembly code. Without the +function tracing, we do not know if interrupts were enabled +within the preemption points. We do see that it started with +preemption enabled. Here is a trace with ftrace_enabled set: @@ -871,40 +953,42 @@ preemptirqsoff latency trace v1.1.5 on 2.6.26-rc8 sshd-4261 0d.s1 105us : trace_preempt_on (__do_softirq) -This is a very interesting trace. It started with the preemption of -the ls task. We see that the task had the "need_resched" bit set -via the 'N' in the trace. Interrupts were disabled before the spin_lock -at the beginning of the trace. We see that a schedule took place to run -sshd. When the interrupts were enabled, we took an interrupt. -On return from the interrupt handler, the softirq ran. We took another -interrupt while running the softirq as we see from the capital 'H'. +This is a very interesting trace. It started with the preemption +of the ls task. We see that the task had the "need_resched" bit +set via the 'N' in the trace. Interrupts were disabled before +the spin_lock at the beginning of the trace. We see that a +schedule took place to run sshd. When the interrupts were +enabled, we took an interrupt. On return from the interrupt +handler, the softirq ran. We took another interrupt while +running the softirq as we see from the capital 'H'. wakeup ------ -In a Real-Time environment it is very important to know the wakeup -time it takes for the highest priority task that is woken up to the -time that it executes. This is also known as "schedule latency". -I stress the point that this is about RT tasks. It is also important -to know the scheduling latency of non-RT tasks, but the average -schedule latency is better for non-RT tasks. Tools like -LatencyTop are more appropriate for such measurements. +In a Real-Time environment it is very important to know the +wakeup time it takes for the highest priority task that is woken +up to the time that it executes. This is also known as "schedule +latency". I stress the point that this is about RT tasks. It is +also important to know the scheduling latency of non-RT tasks, +but the average schedule latency is better for non-RT tasks. +Tools like LatencyTop are more appropriate for such +measurements. Real-Time environments are interested in the worst case latency. -That is the longest latency it takes for something to happen, and -not the average. We can have a very fast scheduler that may only -have a large latency once in a while, but that would not work well -with Real-Time tasks. The wakeup tracer was designed to record -the worst case wakeups of RT tasks. Non-RT tasks are not recorded -because the tracer only records one worst case and tracing non-RT -tasks that are unpredictable will overwrite the worst case latency -of RT tasks. - -Since this tracer only deals with RT tasks, we will run this slightly -differently than we did with the previous tracers. Instead of performing -an 'ls', we will run 'sleep 1' under 'chrt' which changes the -priority of the task. +That is the longest latency it takes for something to happen, +and not the average. We can have a very fast scheduler that may +only have a large latency once in a while, but that would not +work well with Real-Time tasks. The wakeup tracer was designed +to record the worst case wakeups of RT tasks. Non-RT tasks are +not recorded because the tracer only records one worst case and +tracing non-RT tasks that are unpredictable will overwrite the +worst case latency of RT tasks. + +Since this tracer only deals with RT tasks, we will run this +slightly differently than we did with the previous tracers. +Instead of performing an 'ls', we will run 'sleep 1' under +'chrt' which changes the priority of the task. # echo wakeup > /debug/tracing/current_tracer # echo 0 > /debug/tracing/tracing_max_latency @@ -934,17 +1018,16 @@ wakeup latency trace v1.1.5 on 2.6.26-rc8 <idle>-0 1d..4 4us : schedule (cpu_idle) +Running this on an idle system, we see that it only took 4 +microseconds to perform the task switch. Note, since the trace +marker in the schedule is before the actual "switch", we stop +the tracing when the recorded task is about to schedule in. This +may change if we add a new marker at the end of the scheduler. -Running this on an idle system, we see that it only took 4 microseconds -to perform the task switch. Note, since the trace marker in the -schedule is before the actual "switch", we stop the tracing when -the recorded task is about to schedule in. This may change if -we add a new marker at the end of the scheduler. - -Notice that the recorded task is 'sleep' with the PID of 4901 and it -has an rt_prio of 5. This priority is user-space priority and not -the internal kernel priority. The policy is 1 for SCHED_FIFO and 2 -for SCHED_RR. +Notice that the recorded task is 'sleep' with the PID of 4901 +and it has an rt_prio of 5. This priority is user-space priority +and not the internal kernel priority. The policy is 1 for +SCHED_FIFO and 2 for SCHED_RR. Doing the same with chrt -r 5 and ftrace_enabled set. @@ -1001,24 +1084,25 @@ ksoftirq-7 1d..6 49us : _spin_unlock (tracing_record_cmdline) ksoftirq-7 1d..6 49us : sub_preempt_count (_spin_unlock) ksoftirq-7 1d..4 50us : schedule (__cond_resched) -The interrupt went off while running ksoftirqd. This task runs at -SCHED_OTHER. Why did not we see the 'N' set early? This may be -a harmless bug with x86_32 and 4K stacks. On x86_32 with 4K stacks -configured, the interrupt and softirq run with their own stack. -Some information is held on the top of the task's stack (need_resched -and preempt_count are both stored there). The setting of the NEED_RESCHED -bit is done directly to the task's stack, but the reading of the -NEED_RESCHED is done by looking at the current stack, which in this case -is the stack for the hard interrupt. This hides the fact that NEED_RESCHED -has been set. We do not see the 'N' until we switch back to the task's +The interrupt went off while running ksoftirqd. This task runs +at SCHED_OTHER. Why did not we see the 'N' set early? This may +be a harmless bug with x86_32 and 4K stacks. On x86_32 with 4K +stacks configured, the interrupt and softirq run with their own +stack. Some information is held on the top of the task's stack +(need_resched and preempt_count are both stored there). The +setting of the NEED_RESCHED bit is done directly to the task's +stack, but the reading of the NEED_RESCHED is done by looking at +the current stack, which in this case is the stack for the hard +interrupt. This hides the fact that NEED_RESCHED has been set. +We do not see the 'N' until we switch back to the task's assigned stack. function -------- This tracer is the function tracer. Enabling the function tracer -can be done from the debug file system. Make sure the ftrace_enabled is -set; otherwise this tracer is a nop. +can be done from the debug file system. Make sure the +ftrace_enabled is set; otherwise this tracer is a nop. # sysctl kernel.ftrace_enabled=1 # echo function > /debug/tracing/current_tracer @@ -1048,14 +1132,15 @@ set; otherwise this tracer is a nop. [...] -Note: function tracer uses ring buffers to store the above entries. -The newest data may overwrite the oldest data. Sometimes using echo to -stop the trace is not sufficient because the tracing could have overwritten -the data that you wanted to record. For this reason, it is sometimes better to -disable tracing directly from a program. This allows you to stop the -tracing at the point that you hit the part that you are interested in. -To disable the tracing directly from a C program, something like following -code snippet can be used: +Note: function tracer uses ring buffers to store the above +entries. The newest data may overwrite the oldest data. +Sometimes using echo to stop the trace is not sufficient because +the tracing could have overwritten the data that you wanted to +record. For this reason, it is sometimes better to disable +tracing directly from a program. This allows you to stop the +tracing at the point that you hit the part that you are +interested in. To disable the tracing directly from a C program, +something like following code snippet can be used: int trace_fd; [...] @@ -1070,10 +1155,10 @@ int main(int argc, char *argv[]) { } Note: Here we hard coded the path name. The debugfs mount is not -guaranteed to be at /debug (and is more commonly at /sys/kernel/debug). -For simple one time traces, the above is sufficent. For anything else, -a search through /proc/mounts may be needed to find where the debugfs -file-system is mounted. +guaranteed to be at /debug (and is more commonly at +/sys/kernel/debug). For simple one time traces, the above is +sufficent. For anything else, a search through /proc/mounts may +be needed to find where the debugfs file-system is mounted. Single thread tracing @@ -1152,49 +1237,297 @@ int main (int argc, char **argv) return 0; } + +hw-branch-tracer (x86 only) +--------------------------- + +This tracer uses the x86 last branch tracing hardware feature to +collect a branch trace on all cpus with relatively low overhead. + +The tracer uses a fixed-size circular buffer per cpu and only +traces ring 0 branches. The trace file dumps that buffer in the +following format: + +# tracer: hw-branch-tracer +# +# CPU# TO <- FROM + 0 scheduler_tick+0xb5/0x1bf <- task_tick_idle+0x5/0x6 + 2 run_posix_cpu_timers+0x2b/0x72a <- run_posix_cpu_timers+0x25/0x72a + 0 scheduler_tick+0x139/0x1bf <- scheduler_tick+0xed/0x1bf + 0 scheduler_tick+0x17c/0x1bf <- scheduler_tick+0x148/0x1bf + 2 run_posix_cpu_timers+0x9e/0x72a <- run_posix_cpu_timers+0x5e/0x72a + 0 scheduler_tick+0x1b6/0x1bf <- scheduler_tick+0x1aa/0x1bf + + +The tracer may be used to dump the trace for the oops'ing cpu on +a kernel oops into the system log. To enable this, +ftrace_dump_on_oops must be set. To set ftrace_dump_on_oops, one +can either use the sysctl function or set it via the proc system +interface. + + sysctl kernel.ftrace_dump_on_oops=1 + +or + + echo 1 > /proc/sys/kernel/ftrace_dump_on_oops + + +Here's an example of such a dump after a null pointer +dereference in a kernel module: + +[57848.105921] BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 +[57848.106019] IP: [<ffffffffa0000006>] open+0x6/0x14 [oops] +[57848.106019] PGD 2354e9067 PUD 2375e7067 PMD 0 +[57848.106019] Oops: 0002 [#1] SMP +[57848.106019] last sysfs file: /sys/devices/pci0000:00/0000:00:1e.0/0000:20:05.0/local_cpus +[57848.106019] Dumping ftrace buffer: +[57848.106019] --------------------------------- +[...] +[57848.106019] 0 chrdev_open+0xe6/0x165 <- cdev_put+0x23/0x24 +[57848.106019] 0 chrdev_open+0x117/0x165 <- chrdev_open+0xfa/0x165 +[57848.106019] 0 chrdev_open+0x120/0x165 <- chrdev_open+0x11c/0x165 +[57848.106019] 0 chrdev_open+0x134/0x165 <- chrdev_open+0x12b/0x165 +[57848.106019] 0 open+0x0/0x14 [oops] <- chrdev_open+0x144/0x165 +[57848.106019] 0 page_fault+0x0/0x30 <- open+0x6/0x14 [oops] +[57848.106019] 0 error_entry+0x0/0x5b <- page_fault+0x4/0x30 +[57848.106019] 0 error_kernelspace+0x0/0x31 <- error_entry+0x59/0x5b +[57848.106019] 0 error_sti+0x0/0x1 <- error_kernelspace+0x2d/0x31 +[57848.106019] 0 page_fault+0x9/0x30 <- error_sti+0x0/0x1 +[57848.106019] 0 do_page_fault+0x0/0x881 <- page_fault+0x1a/0x30 +[...] +[57848.106019] 0 do_page_fault+0x66b/0x881 <- is_prefetch+0x1ee/0x1f2 +[57848.106019] 0 do_page_fault+0x6e0/0x881 <- do_page_fault+0x67a/0x881 +[57848.106019] 0 oops_begin+0x0/0x96 <- do_page_fault+0x6e0/0x881 +[57848.106019] 0 trace_hw_branch_oops+0x0/0x2d <- oops_begin+0x9/0x96 +[...] +[57848.106019] 0 ds_suspend_bts+0x2a/0xe3 <- ds_suspend_bts+0x1a/0xe3 +[57848.106019] --------------------------------- +[57848.106019] CPU 0 +[57848.106019] Modules linked in: oops +[57848.106019] Pid: 5542, comm: cat Tainted: G W 2.6.28 #23 +[57848.106019] RIP: 0010:[<ffffffffa0000006>] [<ffffffffa0000006>] open+0x6/0x14 [oops] +[57848.106019] RSP: 0018:ffff880235457d48 EFLAGS: 00010246 +[...] + + +function graph tracer +--------------------------- + +This tracer is similar to the function tracer except that it +probes a function on its entry and its exit. This is done by +using a dynamically allocated stack of return addresses in each +task_struct. On function entry the tracer overwrites the return +address of each function traced to set a custom probe. Thus the +original return address is stored on the stack of return address +in the task_struct. + +Probing on both ends of a function leads to special features +such as: + +- measure of a function's time execution +- having a reliable call stack to draw function calls graph + +This tracer is useful in several situations: + +- you want to find the reason of a strange kernel behavior and + need to see what happens in detail on any areas (or specific + ones). + +- you are experiencing weird latencies but it's difficult to + find its origin. + +- you want to find quickly which path is taken by a specific + function + +- you just want to peek inside a working kernel and want to see + what happens there. + +# tracer: function_graph +# +# CPU DURATION FUNCTION CALLS +# | | | | | | | + + 0) | sys_open() { + 0) | do_sys_open() { + 0) | getname() { + 0) | kmem_cache_alloc() { + 0) 1.382 us | __might_sleep(); + 0) 2.478 us | } + 0) | strncpy_from_user() { + 0) | might_fault() { + 0) 1.389 us | __might_sleep(); + 0) 2.553 us | } + 0) 3.807 us | } + 0) 7.876 us | } + 0) | alloc_fd() { + 0) 0.668 us | _spin_lock(); + 0) 0.570 us | expand_files(); + 0) 0.586 us | _spin_unlock(); + + +There are several columns that can be dynamically +enabled/disabled. You can use every combination of options you +want, depending on your needs. + +- The cpu number on which the function executed is default + enabled. It is sometimes better to only trace one cpu (see + tracing_cpu_mask file) or you might sometimes see unordered + function calls while cpu tracing switch. + + hide: echo nofuncgraph-cpu > /debug/tracing/trace_options + show: echo funcgraph-cpu > /debug/tracing/trace_options + +- The duration (function's time of execution) is displayed on + the closing bracket line of a function or on the same line + than the current function in case of a leaf one. It is default + enabled. + + hide: echo nofuncgraph-duration > /debug/tracing/trace_options + show: echo funcgraph-duration > /debug/tracing/trace_options + +- The overhead field precedes the duration field in case of + reached duration thresholds. + + hide: echo nofuncgraph-overhead > /debug/tracing/trace_options + show: echo funcgraph-overhead > /debug/tracing/trace_options + depends on: funcgraph-duration + + ie: + + 0) | up_write() { + 0) 0.646 us | _spin_lock_irqsave(); + 0) 0.684 us | _spin_unlock_irqrestore(); + 0) 3.123 us | } + 0) 0.548 us | fput(); + 0) + 58.628 us | } + + [...] + + 0) | putname() { + 0) | kmem_cache_free() { + 0) 0.518 us | __phys_addr(); + 0) 1.757 us | } + 0) 2.861 us | } + 0) ! 115.305 us | } + 0) ! 116.402 us | } + + + means that the function exceeded 10 usecs. + ! means that the function exceeded 100 usecs. + + +- The task/pid field displays the thread cmdline and pid which + executed the function. It is default disabled. + + hide: echo nofuncgraph-proc > /debug/tracing/trace_options + show: echo funcgraph-proc > /debug/tracing/trace_options + + ie: + + # tracer: function_graph + # + # CPU TASK/PID DURATION FUNCTION CALLS + # | | | | | | | | | + 0) sh-4802 | | d_free() { + 0) sh-4802 | | call_rcu() { + 0) sh-4802 | | __call_rcu() { + 0) sh-4802 | 0.616 us | rcu_process_gp_end(); + 0) sh-4802 | 0.586 us | check_for_new_grace_period(); + 0) sh-4802 | 2.899 us | } + 0) sh-4802 | 4.040 us | } + 0) sh-4802 | 5.151 us | } + 0) sh-4802 | + 49.370 us | } + + +- The absolute time field is an absolute timestamp given by the + system clock since it started. A snapshot of this time is + given on each entry/exit of functions + + hide: echo nofuncgraph-abstime > /debug/tracing/trace_options + show: echo funcgraph-abstime > /debug/tracing/trace_options + + ie: + + # + # TIME CPU DURATION FUNCTION CALLS + # | | | | | | | | + 360.774522 | 1) 0.541 us | } + 360.774522 | 1) 4.663 us | } + 360.774523 | 1) 0.541 us | __wake_up_bit(); + 360.774524 | 1) 6.796 us | } + 360.774524 | 1) 7.952 us | } + 360.774525 | 1) 9.063 us | } + 360.774525 | 1) 0.615 us | journal_mark_dirty(); + 360.774527 | 1) 0.578 us | __brelse(); + 360.774528 | 1) | reiserfs_prepare_for_journal() { + 360.774528 | 1) | unlock_buffer() { + 360.774529 | 1) | wake_up_bit() { + 360.774529 | 1) | bit_waitqueue() { + 360.774530 | 1) 0.594 us | __phys_addr(); + + +You can put some comments on specific functions by using +trace_printk() For example, if you want to put a comment inside +the __might_sleep() function, you just have to include +<linux/ftrace.h> and call trace_printk() inside __might_sleep() + +trace_printk("I'm a comment!\n") + +will produce: + + 1) | __might_sleep() { + 1) | /* I'm a comment! */ + 1) 1.449 us | } + + +You might find other useful features for this tracer in the +following "dynamic ftrace" section such as tracing only specific +functions or tasks. + dynamic ftrace -------------- If CONFIG_DYNAMIC_FTRACE is set, the system will run with virtually no overhead when function tracing is disabled. The way this works is the mcount function call (placed at the start of -every kernel function, produced by the -pg switch in gcc), starts -of pointing to a simple return. (Enabling FTRACE will include the --pg switch in the compiling of the kernel.) +every kernel function, produced by the -pg switch in gcc), +starts of pointing to a simple return. (Enabling FTRACE will +include the -pg switch in the compiling of the kernel.) At compile time every C file object is run through the recordmcount.pl script (located in the scripts directory). This script will process the C object using objdump to find all the -locations in the .text section that call mcount. (Note, only -the .text section is processed, since processing other sections -like .init.text may cause races due to those sections being freed). +locations in the .text section that call mcount. (Note, only the +.text section is processed, since processing other sections like +.init.text may cause races due to those sections being freed). -A new section called "__mcount_loc" is created that holds references -to all the mcount call sites in the .text section. This section is -compiled back into the original object. The final linker will add -all these references into a single table. +A new section called "__mcount_loc" is created that holds +references to all the mcount call sites in the .text section. +This section is compiled back into the original object. The +final linker will add all these references into a single table. On boot up, before SMP is initialized, the dynamic ftrace code -scans this table and updates all the locations into nops. It also -records the locations, which are added to the available_filter_functions -list. Modules are processed as they are loaded and before they are -executed. When a module is unloaded, it also removes its functions from -the ftrace function list. This is automatic in the module unload -code, and the module author does not need to worry about it. - -When tracing is enabled, kstop_machine is called to prevent races -with the CPUS executing code being modified (which can cause the -CPU to do undesireable things), and the nops are patched back -to calls. But this time, they do not call mcount (which is just -a function stub). They now call into the ftrace infrastructure. +scans this table and updates all the locations into nops. It +also records the locations, which are added to the +available_filter_functions list. Modules are processed as they +are loaded and before they are executed. When a module is +unloaded, it also removes its functions from the ftrace function +list. This is automatic in the module unload code, and the +module author does not need to worry about it. + +When tracing is enabled, kstop_machine is called to prevent +races with the CPUS executing code being modified (which can +cause the CPU to do undesireable things), and the nops are +patched back to calls. But this time, they do not call mcount +(which is just a function stub). They now call into the ftrace +infrastructure. One special side-effect to the recording of the functions being traced is that we can now selectively choose which functions we -wish to trace and which ones we want the mcount calls to remain as -nops. +wish to trace and which ones we want the mcount calls to remain +as nops. -Two files are used, one for enabling and one for disabling the tracing -of specified functions. They are: +Two files are used, one for enabling and one for disabling the +tracing of specified functions. They are: set_ftrace_filter @@ -1202,8 +1535,8 @@ and set_ftrace_notrace -A list of available functions that you can add to these files is listed -in: +A list of available functions that you can add to these files is +listed in: available_filter_functions @@ -1240,8 +1573,8 @@ hrtimer_interrupt sys_nanosleep -Perhaps this is not enough. The filters also allow simple wild cards. -Only the following are currently available +Perhaps this is not enough. The filters also allow simple wild +cards. Only the following are currently available <match>* - will match functions that begin with <match> *<match> - will match functions that end with <match> @@ -1251,9 +1584,9 @@ These are the only wild cards which are supported. <match>*<match> will not work. -Note: It is better to use quotes to enclose the wild cards, otherwise - the shell may expand the parameters into names of files in the local - directory. +Note: It is better to use quotes to enclose the wild cards, + otherwise the shell may expand the parameters into names + of files in the local directory. # echo 'hrtimer_*' > /debug/tracing/set_ftrace_filter @@ -1299,7 +1632,8 @@ This is because the '>' and '>>' act just like they do in bash. To rewrite the filters, use '>' To append to the filters, use '>>' -To clear out a filter so that all functions will be recorded again: +To clear out a filter so that all functions will be recorded +again: # echo > /debug/tracing/set_ftrace_filter # cat /debug/tracing/set_ftrace_filter @@ -1331,7 +1665,8 @@ hrtimer_get_res hrtimer_init_sleeper -The set_ftrace_notrace prevents those functions from being traced. +The set_ftrace_notrace prevents those functions from being +traced. # echo '*preempt*' '*lock*' > /debug/tracing/set_ftrace_notrace @@ -1353,13 +1688,75 @@ Produces: We can see that there's no more lock or preempt tracing. + +Dynamic ftrace with the function graph tracer +--------------------------------------------- + +Although what has been explained above concerns both the +function tracer and the function-graph-tracer, there are some +special features only available in the function-graph tracer. + +If you want to trace only one function and all of its children, +you just have to echo its name into set_graph_function: + + echo __do_fault > set_graph_function + +will produce the following "expanded" trace of the __do_fault() +function: + + 0) | __do_fault() { + 0) | filemap_fault() { + 0) | find_lock_page() { + 0) 0.804 us | find_get_page(); + 0) | __might_sleep() { + 0) 1.329 us | } + 0) 3.904 us | } + 0) 4.979 us | } + 0) 0.653 us | _spin_lock(); + 0) 0.578 us | page_add_file_rmap(); + 0) 0.525 us | native_set_pte_at(); + 0) 0.585 us | _spin_unlock(); + 0) | unlock_page() { + 0) 0.541 us | page_waitqueue(); + 0) 0.639 us | __wake_up_bit(); + 0) 2.786 us | } + 0) + 14.237 us | } + 0) | __do_fault() { + 0) | filemap_fault() { + 0) | find_lock_page() { + 0) 0.698 us | find_get_page(); + 0) | __might_sleep() { + 0) 1.412 us | } + 0) 3.950 us | } + 0) 5.098 us | } + 0) 0.631 us | _spin_lock(); + 0) 0.571 us | page_add_file_rmap(); + 0) 0.526 us | native_set_pte_at(); + 0) 0.586 us | _spin_unlock(); + 0) | unlock_page() { + 0) 0.533 us | page_waitqueue(); + 0) 0.638 us | __wake_up_bit(); + 0) 2.793 us | } + 0) + 14.012 us | } + +You can also expand several functions at once: + + echo sys_open > set_graph_function + echo sys_close >> set_graph_function + +Now if you want to go back to trace all functions you can clear +this special filter via: + + echo > set_graph_function + + trace_pipe ---------- -The trace_pipe outputs the same content as the trace file, but the effect -on the tracing is different. Every read from trace_pipe is consumed. -This means that subsequent reads will be different. The trace -is live. +The trace_pipe outputs the same content as the trace file, but +the effect on the tracing is different. Every read from +trace_pipe is consumed. This means that subsequent reads will be +different. The trace is live. # echo function > /debug/tracing/current_tracer # cat /debug/tracing/trace_pipe > /tmp/trace.out & @@ -1387,38 +1784,45 @@ is live. bash-4043 [00] 41.267111: select_task_rq_rt <-try_to_wake_up -Note, reading the trace_pipe file will block until more input is added. -By changing the tracer, trace_pipe will issue an EOF. We needed -to set the function tracer _before_ we "cat" the trace_pipe file. +Note, reading the trace_pipe file will block until more input is +added. By changing the tracer, trace_pipe will issue an EOF. We +needed to set the function tracer _before_ we "cat" the +trace_pipe file. trace entries ------------- -Having too much or not enough data can be troublesome in diagnosing -an issue in the kernel. The file buffer_size_kb is used to modify -the size of the internal trace buffers. The number listed -is the number of entries that can be recorded per CPU. To know -the full size, multiply the number of possible CPUS with the -number of entries. +Having too much or not enough data can be troublesome in +diagnosing an issue in the kernel. The file buffer_size_kb is +used to modify the size of the internal trace buffers. The +number listed is the number of entries that can be recorded per +CPU. To know the full size, multiply the number of possible CPUS +with the number of entries. # cat /debug/tracing/buffer_size_kb 1408 (units kilobytes) -Note, to modify this, you must have tracing completely disabled. To do that, -echo "nop" into the current_tracer. If the current_tracer is not set -to "nop", an EINVAL error will be returned. +Note, to modify this, you must have tracing completely disabled. +To do that, echo "nop" into the current_tracer. If the +current_tracer is not set to "nop", an EINVAL error will be +returned. # echo nop > /debug/tracing/current_tracer # echo 10000 > /debug/tracing/buffer_size_kb # cat /debug/tracing/buffer_size_kb 10000 (units kilobytes) -The number of pages which will be allocated is limited to a percentage -of available memory. Allocating too much will produce an error. +The number of pages which will be allocated is limited to a +percentage of available memory. Allocating too much will produce +an error. # echo 1000000000000 > /debug/tracing/buffer_size_kb -bash: echo: write error: Cannot allocate memory # cat /debug/tracing/buffer_size_kb 85 +----------- + +More details can be found in the source code, in the +kernel/tracing/*.c files. diff --git a/Documentation/ia64/kvm.txt b/Documentation/ia64/kvm.txt index 84f7cb3d5bec..ffb5c80bec3e 100644 --- a/Documentation/ia64/kvm.txt +++ b/Documentation/ia64/kvm.txt @@ -42,7 +42,7 @@ Note: For step 2, please make sure that host page size == TARGET_PAGE_SIZE of qe hg clone http://xenbits.xensource.com/ext/efi-vfirmware.hg you can get the firmware's binary in the directory of efi-vfirmware.hg/binaries. - (3) Rename the firware you owned to Flash.fd, and copy it to /usr/local/share/qemu + (3) Rename the firmware you owned to Flash.fd, and copy it to /usr/local/share/qemu 4. Boot up Linux or Windows guests: 4.1 Create or install a image for guest boot. If you have xen experience, it should be easy. diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index bdc0c433e88c..8932c58850be 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -50,6 +50,7 @@ parameter is applicable: ISAPNP ISA PnP code is enabled. ISDN Appropriate ISDN support is enabled. JOY Appropriate joystick support is enabled. + KMEMTRACE kmemtrace is enabled. LIBATA Libata driver is enabled LP Printer support is enabled. LOOP Loopback device support is enabled. @@ -617,6 +618,9 @@ and is between 256 and 4096 characters. It is defined in the file debug_objects [KNL] Enable object debugging + no_debug_objects + [KNL] Disable object debugging + debugpat [X86] Enable PAT debugging decnet.addr= [HW,NET] @@ -1078,6 +1082,15 @@ and is between 256 and 4096 characters. It is defined in the file use the HighMem zone if it exists, and the Normal zone if it does not. + kmemtrace.enable= [KNL,KMEMTRACE] Format: { yes | no } + Controls whether kmemtrace is enabled + at boot-time. + + kmemtrace.subbufs=n [KNL,KMEMTRACE] Overrides the number of + subbufs kmemtrace's relay channel has. Set this + higher than default (KMEMTRACE_N_SUBBUFS in code) if + you experience buffer overruns. + movablecore=nn[KMG] [KNL,X86-32,IA-64,PPC,X86-64] This parameter is similar to kernelcore except it specifies the amount of memory used for migratable allocations. @@ -1605,7 +1618,7 @@ and is between 256 and 4096 characters. It is defined in the file nosoftlockup [KNL] Disable the soft-lockup detector. noswapaccount [KNL] Disable accounting of swap in memory resource - controller. (See Documentation/controllers/memory.txt) + controller. (See Documentation/cgroups/memory.txt) nosync [HW,M68K] Disables sync negotiation for all devices. @@ -1955,7 +1968,7 @@ and is between 256 and 4096 characters. It is defined in the file relax_domain_level= [KNL, SMP] Set scheduler's default relax_domain_level. - See Documentation/cpusets.txt. + See Documentation/cgroups/cpusets.txt. reserve= [KNL,BUGS] Force the kernel to ignore some iomem area @@ -2364,6 +2377,8 @@ and is between 256 and 4096 characters. It is defined in the file tp720= [HW,PS2] + trace_buf_size=nn[KMG] [ftrace] will set tracing buffer size. + trix= [HW,OSS] MediaTrix AudioTrix Pro Format: <io>,<irq>,<dma>,<dma2>,<sb_io>,<sb_irq>,<sb_dma>,<mpu_io>,<mpu_irq> diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/firmware.txt b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/firmware.txt index 6c238f59b2a9..249db3a15d15 100644 --- a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/firmware.txt +++ b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/firmware.txt @@ -1,6 +1,6 @@ * Uploaded QE firmware - If a new firwmare has been uploaded to the QE (usually by the + If a new firmware has been uploaded to the QE (usually by the boot loader), then a 'firmware' child node should be added to the QE node. This node provides information on the uploaded firmware that device drivers may need. diff --git a/Documentation/scheduler/sched-rt-group.txt b/Documentation/scheduler/sched-rt-group.txt index 3ef339f491e0..5ba4d3fc625a 100644 --- a/Documentation/scheduler/sched-rt-group.txt +++ b/Documentation/scheduler/sched-rt-group.txt @@ -126,7 +126,7 @@ This uses the /cgroup virtual file system and "/cgroup/<cgroup>/cpu.rt_runtime_u to control the CPU time reserved for each control group instead. For more information on working with control groups, you should read -Documentation/cgroups.txt as well. +Documentation/cgroups/cgroups.txt as well. Group settings are checked against the following limits in order to keep the configuration schedulable: diff --git a/Documentation/sysrq.txt b/Documentation/sysrq.txt index afa2946892da..cf42b820ff9d 100644 --- a/Documentation/sysrq.txt +++ b/Documentation/sysrq.txt @@ -115,6 +115,8 @@ On all - write a character to /proc/sysrq-trigger. e.g.: 'x' - Used by xmon interface on ppc/powerpc platforms. +'z' - Dump the ftrace buffer + '0'-'9' - Sets the console log level, controlling which kernel messages will be printed to your console. ('0', for example would make it so that only emergency messages like PANICs or OOPSes would diff --git a/Documentation/tracepoints.txt b/Documentation/tracepoints.txt index 6f0a044f5b5e..c0e1ceed75a4 100644 --- a/Documentation/tracepoints.txt +++ b/Documentation/tracepoints.txt @@ -45,8 +45,8 @@ In include/trace/subsys.h : #include <linux/tracepoint.h> DECLARE_TRACE(subsys_eventname, - TPPROTO(int firstarg, struct task_struct *p), - TPARGS(firstarg, p)); + TP_PROTO(int firstarg, struct task_struct *p), + TP_ARGS(firstarg, p)); In subsys/file.c (where the tracing statement must be added) : @@ -66,10 +66,10 @@ Where : - subsys is the name of your subsystem. - eventname is the name of the event to trace. -- TPPROTO(int firstarg, struct task_struct *p) is the prototype of the +- TP_PROTO(int firstarg, struct task_struct *p) is the prototype of the function called by this tracepoint. -- TPARGS(firstarg, p) are the parameters names, same as found in the +- TP_ARGS(firstarg, p) are the parameters names, same as found in the prototype. Connecting a function (probe) to a tracepoint is done by providing a @@ -103,13 +103,14 @@ used to export the defined tracepoints. * Probe / tracepoint example -See the example provided in samples/tracepoints/src +See the example provided in samples/tracepoints -Compile them with your kernel. +Compile them with your kernel. They are built during 'make' (not +'make modules') when CONFIG_SAMPLE_TRACEPOINTS=m. Run, as root : -modprobe tracepoint-example (insmod order is not important) -modprobe tracepoint-probe-example -cat /proc/tracepoint-example (returns an expected error) -rmmod tracepoint-example tracepoint-probe-example +modprobe tracepoint-sample (insmod order is not important) +modprobe tracepoint-probe-sample +cat /proc/tracepoint-sample (returns an expected error) +rmmod tracepoint-sample tracepoint-probe-sample dmesg diff --git a/Documentation/vm/kmemtrace.txt b/Documentation/vm/kmemtrace.txt new file mode 100644 index 000000000000..a956d9b7f943 --- /dev/null +++ b/Documentation/vm/kmemtrace.txt @@ -0,0 +1,126 @@ + kmemtrace - Kernel Memory Tracer + + by Eduard - Gabriel Munteanu + <eduard.munteanu@linux360.ro> + +I. Introduction +=============== + +kmemtrace helps kernel developers figure out two things: +1) how different allocators (SLAB, SLUB etc.) perform +2) how kernel code allocates memory and how much + +To do this, we trace every allocation and export information to the userspace +through the relay interface. We export things such as the number of requested +bytes, the number of bytes actually allocated (i.e. including internal +fragmentation), whether this is a slab allocation or a plain kmalloc() and so +on. + +The actual analysis is performed by a userspace tool (see section III for +details on where to get it from). It logs the data exported by the kernel, +processes it and (as of writing this) can provide the following information: +- the total amount of memory allocated and fragmentation per call-site +- the amount of memory allocated and fragmentation per allocation +- total memory allocated and fragmentation in the collected dataset +- number of cross-CPU allocation and frees (makes sense in NUMA environments) + +Moreover, it can potentially find inconsistent and erroneous behavior in +kernel code, such as using slab free functions on kmalloc'ed memory or +allocating less memory than requested (but not truly failed allocations). + +kmemtrace also makes provisions for tracing on some arch and analysing the +data on another. + +II. Design and goals +==================== + +kmemtrace was designed to handle rather large amounts of data. Thus, it uses +the relay interface to export whatever is logged to userspace, which then +stores it. Analysis and reporting is done asynchronously, that is, after the +data is collected and stored. By design, it allows one to log and analyse +on different machines and different arches. + +As of writing this, the ABI is not considered stable, though it might not +change much. However, no guarantees are made about compatibility yet. When +deemed stable, the ABI should still allow easy extension while maintaining +backward compatibility. This is described further in Documentation/ABI. + +Summary of design goals: + - allow logging and analysis to be done across different machines + - be fast and anticipate usage in high-load environments (*) + - be reasonably extensible + - make it possible for GNU/Linux distributions to have kmemtrace + included in their repositories + +(*) - one of the reasons Pekka Enberg's original userspace data analysis + tool's code was rewritten from Perl to C (although this is more than a + simple conversion) + + +III. Quick usage guide +====================== + +1) Get a kernel that supports kmemtrace and build it accordingly (i.e. enable +CONFIG_KMEMTRACE). + +2) Get the userspace tool and build it: +$ git-clone git://repo.or.cz/kmemtrace-user.git # current repository +$ cd kmemtrace-user/ +$ ./autogen.sh +$ ./configure +$ make + +3) Boot the kmemtrace-enabled kernel if you haven't, preferably in the +'single' runlevel (so that relay buffers don't fill up easily), and run +kmemtrace: +# '$' does not mean user, but root here. +$ mount -t debugfs none /sys/kernel/debug +$ mount -t proc none /proc +$ cd path/to/kmemtrace-user/ +$ ./kmemtraced +Wait a bit, then stop it with CTRL+C. +$ cat /sys/kernel/debug/kmemtrace/total_overruns # Check if we didn't + # overrun, should + # be zero. +$ (Optionally) [Run kmemtrace_check separately on each cpu[0-9]*.out file to + check its correctness] +$ ./kmemtrace-report + +Now you should have a nice and short summary of how the allocator performs. + +IV. FAQ and known issues +======================== + +Q: 'cat /sys/kernel/debug/kmemtrace/total_overruns' is non-zero, how do I fix +this? Should I worry? +A: If it's non-zero, this affects kmemtrace's accuracy, depending on how +large the number is. You can fix it by supplying a higher +'kmemtrace.subbufs=N' kernel parameter. +--- + +Q: kmemtrace_check reports errors, how do I fix this? Should I worry? +A: This is a bug and should be reported. It can occur for a variety of +reasons: + - possible bugs in relay code + - possible misuse of relay by kmemtrace + - timestamps being collected unorderly +Or you may fix it yourself and send us a patch. +--- + +Q: kmemtrace_report shows many errors, how do I fix this? Should I worry? +A: This is a known issue and I'm working on it. These might be true errors +in kernel code, which may have inconsistent behavior (e.g. allocating memory +with kmem_cache_alloc() and freeing it with kfree()). Pekka Enberg pointed +out this behavior may work with SLAB, but may fail with other allocators. + +It may also be due to lack of tracing in some unusual allocator functions. + +We don't want bug reports regarding this issue yet. +--- + +V. See also +=========== + +Documentation/kernel-parameters.txt +Documentation/ABI/testing/debugfs-kmemtrace + diff --git a/Documentation/vm/numa_memory_policy.txt b/Documentation/vm/numa_memory_policy.txt index 6aaaeb38730c..be45dbb9d7f2 100644 --- a/Documentation/vm/numa_memory_policy.txt +++ b/Documentation/vm/numa_memory_policy.txt @@ -8,7 +8,8 @@ The current memory policy support was added to Linux 2.6 around May 2004. This document attempts to describe the concepts and APIs of the 2.6 memory policy support. -Memory policies should not be confused with cpusets (Documentation/cpusets.txt) +Memory policies should not be confused with cpusets +(Documentation/cgroups/cpusets.txt) which is an administrative mechanism for restricting the nodes from which memory may be allocated by a set of processes. Memory policies are a programming interface that a NUMA-aware application can take advantage of. When diff --git a/Documentation/vm/page_migration b/Documentation/vm/page_migration index d5fdfd34bbaf..6513fe2d90b8 100644 --- a/Documentation/vm/page_migration +++ b/Documentation/vm/page_migration @@ -37,7 +37,8 @@ locations. Larger installations usually partition the system using cpusets into sections of nodes. Paul Jackson has equipped cpusets with the ability to -move pages when a task is moved to another cpuset (See ../cpusets.txt). +move pages when a task is moved to another cpuset (See +Documentation/cgroups/cpusets.txt). Cpusets allows the automation of process locality. If a task is moved to a new cpuset then also all its pages are moved with it so that the performance of the process does not sink dramatically. Also the pages diff --git a/Documentation/x86/x86_64/fake-numa-for-cpusets b/Documentation/x86/x86_64/fake-numa-for-cpusets index 33bb56655991..0f11d9becb0b 100644 --- a/Documentation/x86/x86_64/fake-numa-for-cpusets +++ b/Documentation/x86/x86_64/fake-numa-for-cpusets @@ -7,7 +7,8 @@ you can create fake NUMA nodes that represent contiguous chunks of memory and assign them to cpusets and their attached tasks. This is a way of limiting the amount of system memory that are available to a certain class of tasks. -For more information on the features of cpusets, see Documentation/cpusets.txt. +For more information on the features of cpusets, see +Documentation/cgroups/cpusets.txt. There are a number of different configurations you can use for your needs. For more information on the numa=fake command line option and its various ways of configuring fake nodes, see Documentation/x86/x86_64/boot-options.txt. @@ -32,7 +33,7 @@ A machine may be split as follows with "numa=fake=4*512," as reported by dmesg: On node 3 totalpages: 131072 Now following the instructions for mounting the cpusets filesystem from -Documentation/cpusets.txt, you can assign fake nodes (i.e. contiguous memory +Documentation/cgroups/cpusets.txt, you can assign fake nodes (i.e. contiguous memory address spaces) to individual cpusets: [root@xroads /]# mkdir exampleset diff --git a/MAINTAINERS b/MAINTAINERS index 6fe6f39a3d31..30677193d019 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1763,6 +1763,12 @@ M: viro@zeniv.linux.org.uk L: linux-fsdevel@vger.kernel.org S: Maintained +FINTEK F75375S HARDWARE MONITOR AND FAN CONTROLLER DRIVER +P: Riku Voipio +M: riku.vipio@iki.fi +L: lm-sensors@lm-sensors.org +S: Maintained + FIREWIRE SUBSYSTEM (drivers/firewire, <linux/firewire*.h>) P: Kristian Hoegsberg, Stefan Richter M: krh@redhat.com, stefanr@s5r6.in-berlin.de @@ -2648,6 +2654,12 @@ M: jason.wessel@windriver.com L: kgdb-bugreport@lists.sourceforge.net S: Maintained +KMEMTRACE +P: Eduard - Gabriel Munteanu +M: eduard.munteanu@linux360.ro +L: linux-kernel@vger.kernel.org +S: Maintained + KPROBES P: Ananth N Mavinakayanahalli M: ananth@in.ibm.com @@ -2918,6 +2930,12 @@ M: buytenh@marvell.com L: netdev@vger.kernel.org S: Supported +MARVELL SOC MMC/SD/SDIO CONTROLLER DRIVER +P: Nicolas Pitre +M: nico@cam.org +L: linux-kernel@vger.kernel.org +S: Maintained + MARVELL YUKON / SYSKONNECT DRIVER P: Mirko Lindner M: mlindner@syskonnect.de @@ -3408,6 +3426,11 @@ P: Jim Cromie M: jim.cromie@gmail.com S: Maintained +PCA9532 LED DRIVER +P: Riku Voipio +M: riku.voipio@iki.fi +S: Maintained + PCI ERROR RECOVERY P: Linas Vepstas M: linas@austin.ibm.com @@ -3905,7 +3928,14 @@ S: Maintained SECURE DIGITAL HOST CONTROLLER INTERFACE (SDHCI) DRIVER P: Pierre Ossman M: drzeus-sdhci@drzeus.cx -L: sdhci-devel@list.drzeus.cx +L: sdhci-devel@lists.ossman.eu +S: Maintained + +SECURE DIGITAL HOST CONTROLLER INTERFACE, OPEN FIRMWARE BINDINGS (SDHCI-OF) +P: Anton Vorontsov +M: avorontsov@ru.mvista.com +L: linuxppc-dev@ozlabs.org +L: sdhci-devel@lists.ossman.eu S: Maintained SECURITY SUBSYSTEM @@ -4383,6 +4413,11 @@ L: tlinux-users@tce.toshiba-dme.co.jp W: http://www.buzzard.org.uk/toshiba/ S: Maintained +TMIO MMC DRIVER +P: Ian Molton +M: ian@mnementh.co.uk +S: Maintained + TPM DEVICE DRIVER P: Debora Velarde M: debora@linux.vnet.ibm.com diff --git a/arch/Kconfig b/arch/Kconfig index 830c16a2b801..dc81b34c5d82 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -6,6 +6,7 @@ config OPROFILE tristate "OProfile system profiling (EXPERIMENTAL)" depends on PROFILING depends on HAVE_OPROFILE + depends on TRACING_SUPPORT select TRACING select RING_BUFFER help diff --git a/arch/alpha/include/asm/ftrace.h b/arch/alpha/include/asm/ftrace.h new file mode 100644 index 000000000000..40a8c178f10d --- /dev/null +++ b/arch/alpha/include/asm/ftrace.h @@ -0,0 +1 @@ +/* empty */ diff --git a/arch/alpha/include/asm/hardirq.h b/arch/alpha/include/asm/hardirq.h index d953e234daa8..88971460fa6c 100644 --- a/arch/alpha/include/asm/hardirq.h +++ b/arch/alpha/include/asm/hardirq.h @@ -14,17 +14,4 @@ typedef struct { void ack_bad_irq(unsigned int irq); -#define HARDIRQ_BITS 12 - -/* - * The hardirq mask has to be large enough to have - * space for potentially nestable IRQ sources in the system - * to nest on a single CPU. On Alpha, interrupts are masked at the CPU - * by IPL as well as at the system level. We only have 8 IPLs (UNIX PALcode) - * so we really only have 8 nestable IRQs, but allow some overhead - */ -#if (1 << HARDIRQ_BITS) < 16 -#error HARDIRQ_BITS is too low! -#endif - #endif /* _ALPHA_HARDIRQ_H */ diff --git a/arch/arm/boot/compressed/misc.c b/arch/arm/boot/compressed/misc.c index 393c81641314..9e6e512f0117 100644 --- a/arch/arm/boot/compressed/misc.c +++ b/arch/arm/boot/compressed/misc.c @@ -18,7 +18,10 @@ unsigned int __machine_arch_type; -#include <linux/string.h> +#include <linux/compiler.h> /* for inline */ +#include <linux/types.h> /* for size_t */ +#include <linux/stddef.h> /* for NULL */ +#include <asm/string.h> #ifdef STANDALONE_DEBUG #define putstr printf diff --git a/arch/arm/mach-netx/include/mach/netx-regs.h b/arch/arm/mach-netx/include/mach/netx-regs.h index 08c60ff227be..5a03e7ccb01a 100644 --- a/arch/arm/mach-netx/include/mach/netx-regs.h +++ b/arch/arm/mach-netx/include/mach/netx-regs.h @@ -80,7 +80,7 @@ #define NETX_PA_XPEC(no) (NETX_IO_PHYS + NETX_OFS_XPEC(no)) #define NETX_PA_VIC (NETX_IO_PHYS + NETX_OFS_VIC) -/* virual addresses */ +/* virtual addresses */ #define NETX_VA_SYSTEM (NETX_IO_VIRT + NETX_OFS_SYSTEM) #define NETX_VA_MEMCR (NETX_IO_VIRT + NETX_OFS_MEMCR) #define NETX_VA_DPMAS (NETX_IO_VIRT + NETX_OFS_DPMAS) diff --git a/arch/arm/mach-omap1/Kconfig b/arch/arm/mach-omap1/Kconfig index 3f325d3718a9..cd8de89c5fad 100644 --- a/arch/arm/mach-omap1/Kconfig +++ b/arch/arm/mach-omap1/Kconfig @@ -109,7 +109,7 @@ config MACH_OMAP_PALMZ71 help Support for the Palm Zire71 PDA. To boot the kernel, you'll need a PalmOS compatible bootloader; check out - http://hackndev.com/palm/z71 for more informations. + http://hackndev.com/palm/z71 for more information. Say Y here if you have such a PDA, say N otherwise. config MACH_OMAP_PALMTT diff --git a/arch/avr32/Kconfig b/arch/avr32/Kconfig index 05fe3053dcae..414a8ad97f52 100644 --- a/arch/avr32/Kconfig +++ b/arch/avr32/Kconfig @@ -127,13 +127,13 @@ config BOARD_HAMMERHEAD select CPU_AT32AP7000 select USB_ARCH_HAS_HCD help - The Hammerhead platform is built around a AVR32 32-bit microcontroller from Atmel. + The Hammerhead platform is built around an AVR32 32-bit microcontroller from Atmel. It offers versatile peripherals, such as ethernet, usb device, usb host etc. - The board also incooperates a power supply and is a Power over Ethernet (PoE) Powered + The board also incorporates a power supply and is a Power over Ethernet (PoE) Powered Device (PD). - Additonally, a Cyclone III FPGA from Altera is integrated on the board. The FPGA is + Additionally, a Cyclone III FPGA from Altera is integrated on the board. The FPGA is mapped into the 32-bit AVR memory bus. The FPGA offers two DDR2 SDRAM interfaces, which will cover even the most exceptional need of memory bandwidth. Together with the onboard video decoder the board is ready for video processing. diff --git a/arch/avr32/include/asm/ftrace.h b/arch/avr32/include/asm/ftrace.h new file mode 100644 index 000000000000..40a8c178f10d --- /dev/null +++ b/arch/avr32/include/asm/ftrace.h @@ -0,0 +1 @@ +/* empty */ diff --git a/arch/avr32/include/asm/hardirq.h b/arch/avr32/include/asm/hardirq.h index 267354356f60..015bc75ea798 100644 --- a/arch/avr32/include/asm/hardirq.h +++ b/arch/avr32/include/asm/hardirq.h @@ -20,15 +20,4 @@ void ack_bad_irq(unsigned int irq); #endif /* __ASSEMBLY__ */ -#define HARDIRQ_BITS 12 - -/* - * The hardirq mask has to be large enough to have - * space for potentially all IRQ sources in the system - * nesting on a single CPU: - */ -#if (1 << HARDIRQ_BITS) < NR_IRQS -# error HARDIRQ_BITS is too low! -#endif - #endif /* __ASM_AVR32_HARDIRQ_H */ diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig index 0c1f86e3e44a..3640cdc38aac 100644 --- a/arch/blackfin/Kconfig +++ b/arch/blackfin/Kconfig @@ -777,7 +777,7 @@ config CACHELINE_ALIGNED_L1 default n if BF54x depends on !BF531 help - If enabled, cacheline_anligned data is linked + If enabled, cacheline_aligned data is linked into L1 data memory. (less latency) config SYSCALL_TAB_L1 @@ -957,7 +957,7 @@ config MPU memory they do not own. This comes at a performance penalty and is recommended only for debugging. -comment "Asynchonous Memory Configuration" +comment "Asynchronous Memory Configuration" menu "EBIU_AMGCTL Global Control" config C_AMCKEN @@ -989,7 +989,7 @@ config C_B3PEN default n choice - prompt"Enable Asynchonous Memory Banks" + prompt "Enable Asynchronous Memory Banks" default C_AMBEN_ALL config C_AMBEN diff --git a/arch/blackfin/include/asm/ftrace.h b/arch/blackfin/include/asm/ftrace.h new file mode 100644 index 000000000000..40a8c178f10d --- /dev/null +++ b/arch/blackfin/include/asm/ftrace.h @@ -0,0 +1 @@ +/* empty */ diff --git a/arch/cris/Kconfig b/arch/cris/Kconfig index 3462245fe9fb..7adac388a771 100644 --- a/arch/cris/Kconfig +++ b/arch/cris/Kconfig @@ -438,7 +438,7 @@ config ETRAX_SERIAL_PORT0_DMA1_IN help Enables the DMA1 input channel for ser0 (ttyS0). If you do not enable DMA, an interrupt for each character will be - used when receiveing data. + used when receiving data. Normally you want to use DMA, unless you use the DMA channel for something else. @@ -565,7 +565,7 @@ config ETRAX_SERIAL_PORT2_DMA7_IN help Enables the DMA7 input channel for ser2 (ttyS2). If you do not enable DMA, an interrupt for each character will be - used when receiveing data. + used when receiving data. Normally you want to use DMA, unless you use the DMA channel for something else. @@ -604,7 +604,7 @@ config ETRAX_SERIAL_PORT3_DMA3_IN help Enables the DMA3 input channel for ser3 (ttyS3). If you do not enable DMA, an interrupt for each character will be - used when receiveing data. + used when receiving data. Normally you want to use DMA, unless you use the DMA channel for something else. diff --git a/arch/cris/arch-v32/Kconfig b/arch/cris/arch-v32/Kconfig index 005ed2b3f7f4..21bbd93be34f 100644 --- a/arch/cris/arch-v32/Kconfig +++ b/arch/cris/arch-v32/Kconfig @@ -28,7 +28,7 @@ config ETRAX_NBR_LED_GRP_ONE help Select this if you want one Ethernet LED group. This LED group can be used for one or more Ethernet interfaces. However, it is - recomended that each Ethernet interface use a dedicated LED group. + recommended that each Ethernet interface use a dedicated LED group. config ETRAX_NBR_LED_GRP_TWO bool "Use two LED groups" diff --git a/arch/cris/arch-v32/drivers/Kconfig b/arch/cris/arch-v32/drivers/Kconfig index 7a64fcef9d07..b9e328e688be 100644 --- a/arch/cris/arch-v32/drivers/Kconfig +++ b/arch/cris/arch-v32/drivers/Kconfig @@ -342,7 +342,7 @@ config ETRAX_SERIAL_PORT4_DMA9_IN help Enables the DMA9 input channel for ser4 (ttyS4). If you do not enable DMA, an interrupt for each character will be - used when receiveing data. + used when receiving data. Normally you want to use DMA, unless you use the DMA channel for something else. diff --git a/arch/cris/arch-v32/mach-fs/Kconfig b/arch/cris/arch-v32/mach-fs/Kconfig index f6d74475f1c6..774de82abef6 100644 --- a/arch/cris/arch-v32/mach-fs/Kconfig +++ b/arch/cris/arch-v32/mach-fs/Kconfig @@ -59,7 +59,7 @@ config ETRAX_SDRAM_GRP1_CONFIG depends on ETRAX_ARCH_V32 default "0" help - SDRAM configuration for group 1. The defult value is 0 + SDRAM configuration for group 1. The default value is 0 because group 1 is not used in the default configuration, described in the help for SDRAM_GRP0_CONFIG. diff --git a/arch/cris/include/asm/ftrace.h b/arch/cris/include/asm/ftrace.h new file mode 100644 index 000000000000..40a8c178f10d --- /dev/null +++ b/arch/cris/include/asm/ftrace.h @@ -0,0 +1 @@ +/* empty */ diff --git a/arch/h8300/include/asm/ftrace.h b/arch/h8300/include/asm/ftrace.h new file mode 100644 index 000000000000..40a8c178f10d --- /dev/null +++ b/arch/h8300/include/asm/ftrace.h @@ -0,0 +1 @@ +/* empty */ diff --git a/arch/h8300/kernel/timer/tpu.c b/arch/h8300/kernel/timer/tpu.c index ad383caae196..e7c6e614a758 100644 --- a/arch/h8300/kernel/timer/tpu.c +++ b/arch/h8300/kernel/timer/tpu.c @@ -67,7 +67,7 @@ static struct irqaction tpu_irq = { .flags = IRQF_DISABLED | IRQF_TIMER, }; -const static int __initdata divide_rate[] = { +static const int __initdata divide_rate[] = { #if CONFIG_H8300_TPU_CH == 0 1,4,16,64,0,0,0,0, #elif (CONFIG_H8300_TPU_CH == 1) || (CONFIG_H8300_TPU_CH == 5) diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 153e727a6e8e..294a3b13ecac 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -22,6 +22,9 @@ config IA64 select HAVE_OPROFILE select HAVE_KPROBES select HAVE_KRETPROBES + select HAVE_FTRACE_MCOUNT_RECORD + select HAVE_DYNAMIC_FTRACE if (!ITANIUM) + select HAVE_FUNCTION_TRACER select HAVE_DMA_ATTRS select HAVE_KVM select HAVE_ARCH_TRACEHOOK diff --git a/arch/ia64/include/asm/ftrace.h b/arch/ia64/include/asm/ftrace.h new file mode 100644 index 000000000000..d20db3c2a656 --- /dev/null +++ b/arch/ia64/include/asm/ftrace.h @@ -0,0 +1,28 @@ +#ifndef _ASM_IA64_FTRACE_H +#define _ASM_IA64_FTRACE_H + +#ifdef CONFIG_FUNCTION_TRACER +#define MCOUNT_INSN_SIZE 32 /* sizeof mcount call */ + +#ifndef __ASSEMBLY__ +extern void _mcount(unsigned long pfs, unsigned long r1, unsigned long b0, unsigned long r0); +#define mcount _mcount + +#include <asm/kprobes.h> +/* In IA64, MCOUNT_ADDR is set in link time, so it's not a constant at compile time */ +#define MCOUNT_ADDR (((struct fnptr *)mcount)->ip) +#define FTRACE_ADDR (((struct fnptr *)ftrace_caller)->ip) + +static inline unsigned long ftrace_call_adjust(unsigned long addr) +{ + /* second bundle, insn 2 */ + return addr - 0x12; +} + +struct dyn_arch_ftrace { +}; +#endif + +#endif /* CONFIG_FUNCTION_TRACER */ + +#endif /* _ASM_IA64_FTRACE_H */ diff --git a/arch/ia64/include/asm/hardirq.h b/arch/ia64/include/asm/hardirq.h index 140e495b8e0e..d514cd9edb49 100644 --- a/arch/ia64/include/asm/hardirq.h +++ b/arch/ia64/include/asm/hardirq.h @@ -20,16 +20,6 @@ #define local_softirq_pending() (local_cpu_data->softirq_pending) -#define HARDIRQ_BITS 14 - -/* - * The hardirq mask has to be large enough to have space for potentially all IRQ sources - * in the system nesting on a single CPU: - */ -#if (1 << HARDIRQ_BITS) < NR_IRQS -# error HARDIRQ_BITS is too low! -#endif - extern void __iomem *ipi_base_addr; void ack_bad_irq(unsigned int irq); diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile index 5628e9a990a6..6b7edcab0cb5 100644 --- a/arch/ia64/kernel/Makefile +++ b/arch/ia64/kernel/Makefile @@ -2,6 +2,10 @@ # Makefile for the linux kernel. # +ifdef CONFIG_DYNAMIC_FTRACE +CFLAGS_REMOVE_ftrace.o = -pg +endif + extra-y := head.o init_task.o vmlinux.lds obj-y := acpi.o entry.o efi.o efi_stub.o gate-data.o fsys.o ia64_ksyms.o irq.o irq_ia64.o \ @@ -28,6 +32,7 @@ obj-$(CONFIG_IA64_CYCLONE) += cyclone.o obj-$(CONFIG_CPU_FREQ) += cpufreq/ obj-$(CONFIG_IA64_MCA_RECOVERY) += mca_recovery.o obj-$(CONFIG_KPROBES) += kprobes.o jprobes.o +obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o crash.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_IA64_UNCACHED_ALLOCATOR) += uncached.o diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S index ccfdeee9d89f..8dc69669586a 100644 --- a/arch/ia64/kernel/entry.S +++ b/arch/ia64/kernel/entry.S @@ -47,6 +47,7 @@ #include <asm/processor.h> #include <asm/thread_info.h> #include <asm/unistd.h> +#include <asm/ftrace.h> #include "minstate.h" @@ -1404,6 +1405,105 @@ GLOBAL_ENTRY(unw_init_running) br.ret.sptk.many rp END(unw_init_running) +#ifdef CONFIG_FUNCTION_TRACER +#ifdef CONFIG_DYNAMIC_FTRACE +GLOBAL_ENTRY(_mcount) + br ftrace_stub +END(_mcount) + +.here: + br.ret.sptk.many b0 + +GLOBAL_ENTRY(ftrace_caller) + alloc out0 = ar.pfs, 8, 0, 4, 0 + mov out3 = r0 + ;; + mov out2 = b0 + add r3 = 0x20, r3 + mov out1 = r1; + br.call.sptk.many b0 = ftrace_patch_gp + //this might be called from module, so we must patch gp +ftrace_patch_gp: + movl gp=__gp + mov b0 = r3 + ;; +.global ftrace_call; +ftrace_call: +{ + .mlx + nop.m 0x0 + movl r3 = .here;; +} + alloc loc0 = ar.pfs, 4, 4, 2, 0 + ;; + mov loc1 = b0 + mov out0 = b0 + mov loc2 = r8 + mov loc3 = r15 + ;; + adds out0 = -MCOUNT_INSN_SIZE, out0 + mov out1 = in2 + mov b6 = r3 + + br.call.sptk.many b0 = b6 + ;; + mov ar.pfs = loc0 + mov b0 = loc1 + mov r8 = loc2 + mov r15 = loc3 + br ftrace_stub + ;; +END(ftrace_caller) + +#else +GLOBAL_ENTRY(_mcount) + movl r2 = ftrace_stub + movl r3 = ftrace_trace_function;; + ld8 r3 = [r3];; + ld8 r3 = [r3];; + cmp.eq p7,p0 = r2, r3 +(p7) br.sptk.many ftrace_stub + ;; + + alloc loc0 = ar.pfs, 4, 4, 2, 0 + ;; + mov loc1 = b0 + mov out0 = b0 + mov loc2 = r8 + mov loc3 = r15 + ;; + adds out0 = -MCOUNT_INSN_SIZE, out0 + mov out1 = in2 + mov b6 = r3 + + br.call.sptk.many b0 = b6 + ;; + mov ar.pfs = loc0 + mov b0 = loc1 + mov r8 = loc2 + mov r15 = loc3 + br ftrace_stub + ;; +END(_mcount) +#endif + +GLOBAL_ENTRY(ftrace_stub) + mov r3 = b0 + movl r2 = _mcount_ret_helper + ;; + mov b6 = r2 + mov b7 = r3 + br.ret.sptk.many b6 + +_mcount_ret_helper: + mov b0 = r42 + mov r1 = r41 + mov ar.pfs = r40 + br b7 +END(ftrace_stub) + +#endif /* CONFIG_FUNCTION_TRACER */ + .rodata .align 8 .globl sys_call_table diff --git a/arch/ia64/kernel/ftrace.c b/arch/ia64/kernel/ftrace.c new file mode 100644 index 000000000000..7fc8c961b1f7 --- /dev/null +++ b/arch/ia64/kernel/ftrace.c @@ -0,0 +1,206 @@ +/* + * Dynamic function tracing support. + * + * Copyright (C) 2008 Shaohua Li <shaohua.li@intel.com> + * + * For licencing details, see COPYING. + * + * Defines low-level handling of mcount calls when the kernel + * is compiled with the -pg flag. When using dynamic ftrace, the + * mcount call-sites get patched lazily with NOP till they are + * enabled. All code mutation routines here take effect atomically. + */ + +#include <linux/uaccess.h> +#include <linux/ftrace.h> + +#include <asm/cacheflush.h> +#include <asm/patch.h> + +/* In IA64, each function will be added below two bundles with -pg option */ +static unsigned char __attribute__((aligned(8))) +ftrace_orig_code[MCOUNT_INSN_SIZE] = { + 0x02, 0x40, 0x31, 0x10, 0x80, 0x05, /* alloc r40=ar.pfs,12,8,0 */ + 0xb0, 0x02, 0x00, 0x00, 0x42, 0x40, /* mov r43=r0;; */ + 0x05, 0x00, 0xc4, 0x00, /* mov r42=b0 */ + 0x11, 0x48, 0x01, 0x02, 0x00, 0x21, /* mov r41=r1 */ + 0x00, 0x00, 0x00, 0x02, 0x00, 0x00, /* nop.i 0x0 */ + 0x08, 0x00, 0x00, 0x50 /* br.call.sptk.many b0 = _mcount;; */ +}; + +struct ftrace_orig_insn { + u64 dummy1, dummy2, dummy3; + u64 dummy4:64-41+13; + u64 imm20:20; + u64 dummy5:3; + u64 sign:1; + u64 dummy6:4; +}; + +/* mcount stub will be converted below for nop */ +static unsigned char ftrace_nop_code[MCOUNT_INSN_SIZE] = { + 0x00, 0x00, 0x00, 0x00, 0x01, 0x00, /* [MII] nop.m 0x0 */ + 0x30, 0x00, 0x00, 0x60, 0x00, 0x00, /* mov r3=ip */ + 0x00, 0x00, 0x04, 0x00, /* nop.i 0x0 */ + 0x05, 0x00, 0x00, 0x00, 0x01, 0x00, /* [MLX] nop.m 0x0 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* nop.x 0x0;; */ + 0x00, 0x00, 0x04, 0x00 +}; + +static unsigned char *ftrace_nop_replace(void) +{ + return ftrace_nop_code; +} + +/* + * mcount stub will be converted below for call + * Note: Just the last instruction is changed against nop + * */ +static unsigned char __attribute__((aligned(8))) +ftrace_call_code[MCOUNT_INSN_SIZE] = { + 0x00, 0x00, 0x00, 0x00, 0x01, 0x00, /* [MII] nop.m 0x0 */ + 0x30, 0x00, 0x00, 0x60, 0x00, 0x00, /* mov r3=ip */ + 0x00, 0x00, 0x04, 0x00, /* nop.i 0x0 */ + 0x05, 0x00, 0x00, 0x00, 0x01, 0x00, /* [MLX] nop.m 0x0 */ + 0xff, 0xff, 0xff, 0xff, 0x7f, 0x00, /* brl.many .;;*/ + 0xf8, 0xff, 0xff, 0xc8 +}; + +struct ftrace_call_insn { + u64 dummy1, dummy2; + u64 dummy3:48; + u64 imm39_l:16; + u64 imm39_h:23; + u64 dummy4:13; + u64 imm20:20; + u64 dummy5:3; + u64 i:1; + u64 dummy6:4; +}; + +static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) +{ + struct ftrace_call_insn *code = (void *)ftrace_call_code; + unsigned long offset = addr - (ip + 0x10); + + code->imm39_l = offset >> 24; + code->imm39_h = offset >> 40; + code->imm20 = offset >> 4; + code->i = offset >> 63; + return ftrace_call_code; +} + +static int +ftrace_modify_code(unsigned long ip, unsigned char *old_code, + unsigned char *new_code, int do_check) +{ + unsigned char replaced[MCOUNT_INSN_SIZE]; + + /* + * Note: Due to modules and __init, code can + * disappear and change, we need to protect against faulting + * as well as code changing. We do this by using the + * probe_kernel_* functions. + * + * No real locking needed, this code is run through + * kstop_machine, or before SMP starts. + */ + + if (!do_check) + goto skip_check; + + /* read the text we want to modify */ + if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + return -EFAULT; + + /* Make sure it is what we expect it to be */ + if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0) + return -EINVAL; + +skip_check: + /* replace the text with the new text */ + if (probe_kernel_write(((void *)ip), new_code, MCOUNT_INSN_SIZE)) + return -EPERM; + flush_icache_range(ip, ip + MCOUNT_INSN_SIZE); + + return 0; +} + +static int ftrace_make_nop_check(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned char __attribute__((aligned(8))) replaced[MCOUNT_INSN_SIZE]; + unsigned long ip = rec->ip; + + if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + return -EFAULT; + if (rec->flags & FTRACE_FL_CONVERTED) { + struct ftrace_call_insn *call_insn, *tmp_call; + + call_insn = (void *)ftrace_call_code; + tmp_call = (void *)replaced; + call_insn->imm39_l = tmp_call->imm39_l; + call_insn->imm39_h = tmp_call->imm39_h; + call_insn->imm20 = tmp_call->imm20; + call_insn->i = tmp_call->i; + if (memcmp(replaced, ftrace_call_code, MCOUNT_INSN_SIZE) != 0) + return -EINVAL; + return 0; + } else { + struct ftrace_orig_insn *call_insn, *tmp_call; + + call_insn = (void *)ftrace_orig_code; + tmp_call = (void *)replaced; + call_insn->sign = tmp_call->sign; + call_insn->imm20 = tmp_call->imm20; + if (memcmp(replaced, ftrace_orig_code, MCOUNT_INSN_SIZE) != 0) + return -EINVAL; + return 0; + } +} + +int ftrace_make_nop(struct module *mod, + struct dyn_ftrace *rec, unsigned long addr) +{ + int ret; + char *new; + + ret = ftrace_make_nop_check(rec, addr); + if (ret) + return ret; + new = ftrace_nop_replace(); + return ftrace_modify_code(rec->ip, NULL, new, 0); +} + +int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned long ip = rec->ip; + unsigned char *old, *new; + + old= ftrace_nop_replace(); + new = ftrace_call_replace(ip, addr); + return ftrace_modify_code(ip, old, new, 1); +} + +/* in IA64, _mcount can't directly call ftrace_stub. Only jump is ok */ +int ftrace_update_ftrace_func(ftrace_func_t func) +{ + unsigned long ip; + unsigned long addr = ((struct fnptr *)ftrace_call)->ip; + + if (func == ftrace_stub) + return 0; + ip = ((struct fnptr *)func)->ip; + + ia64_patch_imm64(addr + 2, ip); + + flush_icache_range(addr, addr + 16); + return 0; +} + +/* run from kstop_machine */ +int __init ftrace_dyn_arch_init(void *data) +{ + *(unsigned long *)data = 0; + + return 0; +} diff --git a/arch/ia64/kernel/ia64_ksyms.c b/arch/ia64/kernel/ia64_ksyms.c index 6da1f20d7372..2d311864e359 100644 --- a/arch/ia64/kernel/ia64_ksyms.c +++ b/arch/ia64/kernel/ia64_ksyms.c @@ -112,3 +112,9 @@ EXPORT_SYMBOL_GPL(esi_call_phys); #endif extern char ia64_ivt[]; EXPORT_SYMBOL(ia64_ivt); + +#include <asm/ftrace.h> +#ifdef CONFIG_FUNCTION_TRACER +/* mcount is defined in assembly */ +EXPORT_SYMBOL(_mcount); +#endif diff --git a/arch/m68k/include/asm/ftrace.h b/arch/m68k/include/asm/ftrace.h new file mode 100644 index 000000000000..40a8c178f10d --- /dev/null +++ b/arch/m68k/include/asm/ftrace.h @@ -0,0 +1 @@ +/* empty */ diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index dc787190430a..998e5db8cc0f 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -134,7 +134,7 @@ config MACH_JAZZ help This a family of machines based on the MIPS R4030 chipset which was used by several vendors to build RISC/os and Windows NT workstations. - Members include the Acer PICA, MIPS Magnum 4000, MIPS Millenium and + Members include the Acer PICA, MIPS Magnum 4000, MIPS Millennium and Olivetti M700-10 workstations. config LASAT diff --git a/arch/mips/include/asm/ftrace.h b/arch/mips/include/asm/ftrace.h new file mode 100644 index 000000000000..40a8c178f10d --- /dev/null +++ b/arch/mips/include/asm/ftrace.h @@ -0,0 +1 @@ +/* empty */ diff --git a/arch/mips/sgi-ip27/ip27-smp.c b/arch/mips/sgi-ip27/ip27-smp.c index 5b47d6b65275..cbcd7eb83bd1 100644 --- a/arch/mips/sgi-ip27/ip27-smp.c +++ b/arch/mips/sgi-ip27/ip27-smp.c @@ -221,7 +221,7 @@ static void __init ip27_smp_setup(void) * Assumption to be fixed: we're always booted on logical / physical * processor 0. While we're always running on logical processor 0 * this still means this is physical processor zero; it might for - * example be disabled in the firwware. + * example be disabled in the firmware. */ alloc_cpupda(0, 0); } diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 45192dce65c4..9e08d8a69fdf 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -346,7 +346,7 @@ config PHYP_DUMP help Hypervisor-assisted dump is meant to be a kdump replacement offering robustness and speed not possible without system - hypervisor assistence. + hypervisor assistance. If unsure, say "N" diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h index 19f299b7e256..35acac90c8ca 100644 --- a/arch/powerpc/include/asm/mmzone.h +++ b/arch/powerpc/include/asm/mmzone.h @@ -8,6 +8,7 @@ #define _ASM_MMZONE_H_ #ifdef __KERNEL__ +#include <linux/cpumask.h> /* * generic non-linear memory support: diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index 5b5d16b2cac8..5455943f16aa 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -557,7 +557,6 @@ extern void mod_return_to_handler(void); void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) { unsigned long old; - unsigned long long calltime; int faulted; struct ftrace_graph_ent trace; unsigned long return_hooker = (unsigned long)&return_to_handler; @@ -606,10 +605,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) return; } - calltime = cpu_clock(raw_smp_processor_id()); - - if (ftrace_push_return_trace(old, calltime, - self_addr, &trace.depth) == -EBUSY) { + if (ftrace_push_return_trace(old, self_addr, &trace.depth) == -EBUSY) { *parent = old; return; } diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index ffa2a9fd53d0..e3e87078d03f 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -293,7 +293,7 @@ config CPM config OF_RTC bool help - Uses information from the OF or flattened device tree to instatiate + Uses information from the OF or flattened device tree to instantiate platform devices for direct mapped RTC chips like the DS1742 or DS1743. source "arch/powerpc/sysdev/bestcomm/Kconfig" diff --git a/arch/powerpc/sysdev/bestcomm/Kconfig b/arch/powerpc/sysdev/bestcomm/Kconfig index 0b192a1c429d..29e427085efb 100644 --- a/arch/powerpc/sysdev/bestcomm/Kconfig +++ b/arch/powerpc/sysdev/bestcomm/Kconfig @@ -9,8 +9,8 @@ config PPC_BESTCOMM select PPC_LIB_RHEAP help BestComm is the name of the communication coprocessor found - on the Freescale MPC5200 family of processor. It's usage is - optionnal for some drivers (like ATA), but required for + on the Freescale MPC5200 family of processor. Its usage is + optional for some drivers (like ATA), but required for others (like FEC). If you want to use drivers that require DMA operations, diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h index 2009158a4502..72137bc907ac 100644 --- a/arch/s390/include/asm/smp.h +++ b/arch/s390/include/asm/smp.h @@ -92,12 +92,6 @@ extern void arch_send_call_function_ipi(cpumask_t mask); #endif #ifndef CONFIG_SMP -static inline void smp_send_stop(void) -{ - /* Disable all interrupts/machine checks */ - __load_psw_mask(psw_kernel_bits & ~PSW_MASK_MCHECK); -} - #define hard_smp_processor_id() 0 #define smp_cpu_not_running(cpu) 1 #endif diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 8d50d527c595..2d52b515c241 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -640,10 +640,10 @@ config GUSA_RB depends on GUSA && CPU_SH3 || (CPU_SH4 && !CPU_SH4A) help Enabling this option will allow the kernel to implement some - atomic operations using a software implemention of load-locked/ + atomic operations using a software implementation of load-locked/ store-conditional (LLSC). On machines which do not have hardware LLSC, this should be more efficient than the other alternative of - disabling insterrupts around the atomic sequence. + disabling interrupts around the atomic sequence. endmenu diff --git a/arch/sparc/include/asm/mmzone.h b/arch/sparc/include/asm/mmzone.h index ebf5986c12ed..e8c648741ed4 100644 --- a/arch/sparc/include/asm/mmzone.h +++ b/arch/sparc/include/asm/mmzone.h @@ -3,6 +3,8 @@ #ifdef CONFIG_NEED_MULTIPLE_NODES +#include <linux/cpumask.h> + extern struct pglist_data *node_data[]; #define NODE_DATA(nid) (node_data[nid]) diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S index a46c3a21e26d..3a1b7bf03cff 100644 --- a/arch/sparc/kernel/head_64.S +++ b/arch/sparc/kernel/head_64.S @@ -686,7 +686,7 @@ tlb_fixup_done: * point. * * There used to be enormous complexity wrt. transferring - * over from the firwmare's trap table to the Linux kernel's. + * over from the firmware's trap table to the Linux kernel's. * For example, there was a chicken & egg problem wrt. building * the OBP page tables, yet needing to be on the Linux kernel * trap table (to translate PAGE_OFFSET addresses) in order to diff --git a/arch/um/include/asm/ftrace.h b/arch/um/include/asm/ftrace.h new file mode 100644 index 000000000000..40a8c178f10d --- /dev/null +++ b/arch/um/include/asm/ftrace.h @@ -0,0 +1 @@ +/* empty */ diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 3f27e5c0c9c9..5b2196ab8168 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -34,6 +34,8 @@ config X86 select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACE_MCOUNT_TEST + select HAVE_FTRACE_NMI_ENTER if DYNAMIC_FTRACE + select HAVE_FTRACE_SYSCALLS select HAVE_KVM select HAVE_ARCH_KGDB select HAVE_ARCH_TRACEHOOK @@ -1144,7 +1146,7 @@ config NODES_SHIFT depends on NEED_MULTIPLE_NODES ---help--- Specify the maximum number of NUMA Nodes available on the target - system. Increases memory reserved to accomodate various tables. + system. Increases memory reserved to accommodate various tables. config HAVE_ARCH_BOOTMEM def_bool y @@ -1322,7 +1324,7 @@ config MTRR_SANITIZER add writeback entries. Can be disabled with disable_mtrr_cleanup on the kernel command line. - The largest mtrr entry size for a continous block can be set with + The largest mtrr entry size for a continuous block can be set with mtrr_chunk_size. If unsure, say Y. diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index fb737ce5888d..6633b6e7505a 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -57,6 +57,7 @@ $(obj)/cpustr.h: $(obj)/mkcpustr FORCE # How to compile the 16-bit code. Note we always compile for -march=i386, # that way we can complain to the user if the CPU is insufficient. KBUILD_CFLAGS := $(LINUXINCLUDE) -g -Os -D_SETUP -D__KERNEL__ \ + -DDISABLE_BRANCH_PROFILING \ -Wall -Wstrict-prototypes \ -march=i386 -mregparm=3 \ -include $(srctree)/$(src)/code16gcc.h \ @@ -66,7 +67,7 @@ KBUILD_CFLAGS := $(LINUXINCLUDE) -g -Os -D_SETUP -D__KERNEL__ \ $(call cc-option, -fno-unit-at-a-time)) \ $(call cc-option, -fno-stack-protector) \ $(call cc-option, -mpreferred-stack-boundary=2) -KBUILD_CFLAGS += $(call cc-option,-m32) +KBUILD_CFLAGS += $(call cc-option, -m32) KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ $(obj)/bzImage: asflags-y := $(SVGA_MODE) diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 3ca4c194b8e5..65551c9f8571 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -8,6 +8,7 @@ targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma h KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2 KBUILD_CFLAGS += -fno-strict-aliasing -fPIC +KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING cflags-$(CONFIG_X86_64) := -mcmodel=small KBUILD_CFLAGS += $(cflags-y) KBUILD_CFLAGS += $(call cc-option,-ffreestanding) diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h index b3894bf52fcd..e55dfc1ad453 100644 --- a/arch/x86/include/asm/cacheflush.h +++ b/arch/x86/include/asm/cacheflush.h @@ -126,6 +126,11 @@ void clflush_cache_range(void *addr, unsigned int size); #ifdef CONFIG_DEBUG_RODATA void mark_rodata_ro(void); extern const int rodata_test_data; +void set_kernel_text_rw(void); +void set_kernel_text_ro(void); +#else +static inline void set_kernel_text_rw(void) { } +static inline void set_kernel_text_ro(void) { } #endif #ifdef CONFIG_DEBUG_RODATA_TEST diff --git a/arch/x86/include/asm/cpumask.h b/arch/x86/include/asm/cpumask.h index a7f3c75f8ad7..61c852fa346b 100644 --- a/arch/x86/include/asm/cpumask.h +++ b/arch/x86/include/asm/cpumask.h @@ -3,8 +3,6 @@ #ifndef __ASSEMBLY__ #include <linux/cpumask.h> -#ifdef CONFIG_X86_64 - extern cpumask_var_t cpu_callin_mask; extern cpumask_var_t cpu_callout_mask; extern cpumask_var_t cpu_initialized_mask; @@ -12,21 +10,5 @@ extern cpumask_var_t cpu_sibling_setup_mask; extern void setup_cpu_local_masks(void); -#else /* CONFIG_X86_32 */ - -extern cpumask_t cpu_callin_map; -extern cpumask_t cpu_callout_map; -extern cpumask_t cpu_initialized; -extern cpumask_t cpu_sibling_setup_map; - -#define cpu_callin_mask ((struct cpumask *)&cpu_callin_map) -#define cpu_callout_mask ((struct cpumask *)&cpu_callout_map) -#define cpu_initialized_mask ((struct cpumask *)&cpu_initialized) -#define cpu_sibling_setup_mask ((struct cpumask *)&cpu_sibling_setup_map) - -static inline void setup_cpu_local_masks(void) { } - -#endif /* CONFIG_X86_32 */ - #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_CPUMASK_H */ diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 63a79c77d220..81937a5dc77c 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -111,6 +111,8 @@ enum fixed_addresses { #ifdef CONFIG_PARAVIRT FIX_PARAVIRT_BOOTMAP, #endif + FIX_TEXT_POKE0, /* reserve 2 pages for text_poke() */ + FIX_TEXT_POKE1, __end_of_permanent_fixed_addresses, #ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT FIX_OHCI1394_BASE, diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index db24c2278be0..bd2c6511c887 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -28,6 +28,13 @@ #endif +/* FIXME: I don't want to stay hardcoded */ +#ifdef CONFIG_X86_64 +# define FTRACE_SYSCALL_MAX 296 +#else +# define FTRACE_SYSCALL_MAX 333 +#endif + #ifdef CONFIG_FUNCTION_TRACER #define MCOUNT_ADDR ((long)(mcount)) #define MCOUNT_INSN_SIZE 5 /* sizeof mcount call */ diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index a0301bfeb954..b51a1e8b0baf 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -89,12 +89,40 @@ extern void pci_iommu_alloc(void); /* MSI arch hook */ #define arch_setup_msi_irqs arch_setup_msi_irqs -#endif /* __KERNEL__ */ +#define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys) + +#if defined(CONFIG_X86_64) || defined(CONFIG_DMA_API_DEBUG) + +#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) \ + dma_addr_t ADDR_NAME; +#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) \ + __u32 LEN_NAME; +#define pci_unmap_addr(PTR, ADDR_NAME) \ + ((PTR)->ADDR_NAME) +#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \ + (((PTR)->ADDR_NAME) = (VAL)) +#define pci_unmap_len(PTR, LEN_NAME) \ + ((PTR)->LEN_NAME) +#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \ + (((PTR)->LEN_NAME) = (VAL)) -#ifdef CONFIG_X86_32 -# include "pci_32.h" #else -# include "pci_64.h" + +#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) dma_addr_t ADDR_NAME[0]; +#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) unsigned LEN_NAME[0]; +#define pci_unmap_addr(PTR, ADDR_NAME) sizeof((PTR)->ADDR_NAME) +#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \ + do { break; } while (pci_unmap_addr(PTR, ADDR_NAME)) +#define pci_unmap_len(PTR, LEN_NAME) sizeof((PTR)->LEN_NAME) +#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \ + do { break; } while (pci_unmap_len(PTR, LEN_NAME)) + +#endif + +#endif /* __KERNEL__ */ + +#ifdef CONFIG_X86_64 +#include "pci_64.h" #endif /* implement the pci_ DMA API in terms of the generic device dma_ one */ @@ -112,11 +140,6 @@ static inline int __pcibus_to_node(const struct pci_bus *bus) return sd->node; } -static inline cpumask_t __pcibus_to_cpumask(struct pci_bus *bus) -{ - return node_to_cpumask(__pcibus_to_node(bus)); -} - static inline const struct cpumask * cpumask_of_pcibus(const struct pci_bus *bus) { diff --git a/arch/x86/include/asm/pci_32.h b/arch/x86/include/asm/pci_32.h deleted file mode 100644 index 6f1213a6ef4f..000000000000 --- a/arch/x86/include/asm/pci_32.h +++ /dev/null @@ -1,34 +0,0 @@ -#ifndef _ASM_X86_PCI_32_H -#define _ASM_X86_PCI_32_H - - -#ifdef __KERNEL__ - - -/* Dynamic DMA mapping stuff. - * i386 has everything mapped statically. - */ - -struct pci_dev; - -/* The PCI address space does equal the physical memory - * address space. The networking and block device layers use - * this boolean for bounce buffer decisions. - */ -#define PCI_DMA_BUS_IS_PHYS (1) - -/* pci_unmap_{page,single} is a nop so... */ -#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) dma_addr_t ADDR_NAME[0]; -#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) unsigned LEN_NAME[0]; -#define pci_unmap_addr(PTR, ADDR_NAME) sizeof((PTR)->ADDR_NAME) -#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \ - do { break; } while (pci_unmap_addr(PTR, ADDR_NAME)) -#define pci_unmap_len(PTR, LEN_NAME) sizeof((PTR)->LEN_NAME) -#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \ - do { break; } while (pci_unmap_len(PTR, LEN_NAME)) - - -#endif /* __KERNEL__ */ - - -#endif /* _ASM_X86_PCI_32_H */ diff --git a/arch/x86/include/asm/pci_64.h b/arch/x86/include/asm/pci_64.h index 4da207982777..ae5e40f67daf 100644 --- a/arch/x86/include/asm/pci_64.h +++ b/arch/x86/include/asm/pci_64.h @@ -24,28 +24,6 @@ extern int (*pci_config_write)(int seg, int bus, int dev, int fn, extern void dma32_reserve_bootmem(void); -/* The PCI address space does equal the physical memory - * address space. The networking and block device layers use - * this boolean for bounce buffer decisions - * - * On AMD64 it mostly equals, but we set it to zero if a hardware - * IOMMU (gart) of sotware IOMMU (swiotlb) is available. - */ -#define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys) - -#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) \ - dma_addr_t ADDR_NAME; -#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) \ - __u32 LEN_NAME; -#define pci_unmap_addr(PTR, ADDR_NAME) \ - ((PTR)->ADDR_NAME) -#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \ - (((PTR)->ADDR_NAME) = (VAL)) -#define pci_unmap_len(PTR, LEN_NAME) \ - ((PTR)->LEN_NAME) -#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \ - (((PTR)->LEN_NAME) = (VAL)) - #endif /* __KERNEL__ */ #endif /* _ASM_X86_PCI_64_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index ae85a8d66a30..34c52370f2fe 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -94,7 +94,7 @@ struct cpuinfo_x86 { unsigned long loops_per_jiffy; #ifdef CONFIG_SMP /* cpus sharing the last level cache: */ - cpumask_t llc_shared_map; + cpumask_var_t llc_shared_map; #endif /* cpuid returned max cores value: */ u16 x86_max_cores; @@ -736,6 +736,7 @@ static inline void __sti_mwait(unsigned long eax, unsigned long ecx) extern void mwait_idle_with_hints(unsigned long eax, unsigned long ecx); extern void select_idle_routine(const struct cpuinfo_x86 *c); +extern void init_c1e_mask(void); extern unsigned long boot_option_idle_override; extern unsigned long idle_halt; diff --git a/arch/x86/include/asm/ptrace-abi.h b/arch/x86/include/asm/ptrace-abi.h index 8e0f8d199e05..86723035a515 100644 --- a/arch/x86/include/asm/ptrace-abi.h +++ b/arch/x86/include/asm/ptrace-abi.h @@ -80,8 +80,6 @@ #define PTRACE_SINGLEBLOCK 33 /* resume execution until next branch */ -#ifdef CONFIG_X86_PTRACE_BTS - #ifndef __ASSEMBLY__ #include <linux/types.h> @@ -140,6 +138,5 @@ struct ptrace_bts_config { BTS records are read from oldest to newest. Returns number of BTS records drained. */ -#endif /* CONFIG_X86_PTRACE_BTS */ #endif /* _ASM_X86_PTRACE_ABI_H */ diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 47d0e21f2b9e..19e0d88b966d 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -21,19 +21,19 @@ extern int smp_num_siblings; extern unsigned int num_processors; -DECLARE_PER_CPU(cpumask_t, cpu_sibling_map); -DECLARE_PER_CPU(cpumask_t, cpu_core_map); +DECLARE_PER_CPU(cpumask_var_t, cpu_sibling_map); +DECLARE_PER_CPU(cpumask_var_t, cpu_core_map); DECLARE_PER_CPU(u16, cpu_llc_id); DECLARE_PER_CPU(int, cpu_number); static inline struct cpumask *cpu_sibling_mask(int cpu) { - return &per_cpu(cpu_sibling_map, cpu); + return per_cpu(cpu_sibling_map, cpu); } static inline struct cpumask *cpu_core_mask(int cpu) { - return &per_cpu(cpu_core_map, cpu); + return per_cpu(cpu_core_map, cpu); } DECLARE_EARLY_PER_CPU(u16, x86_cpu_to_apicid); @@ -121,9 +121,10 @@ static inline void arch_send_call_function_single_ipi(int cpu) smp_ops.send_call_func_single_ipi(cpu); } -static inline void arch_send_call_function_ipi(cpumask_t mask) +#define arch_send_call_function_ipi_mask arch_send_call_function_ipi_mask +static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask) { - smp_ops.send_call_func_ipi(&mask); + smp_ops.send_call_func_ipi(mask); } void cpu_disable_common(void); diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index df9d5f78385e..8820a73ae090 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -94,6 +94,7 @@ struct thread_info { #define TIF_FORCED_TF 24 /* true if TF in eflags artificially */ #define TIF_DEBUGCTLMSR 25 /* uses thread_struct.debugctlmsr */ #define TIF_DS_AREA_MSR 26 /* uses thread_struct.ds_area_msr */ +#define TIF_SYSCALL_FTRACE 27 /* for ftrace syscall instrumentation */ #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) @@ -115,15 +116,17 @@ struct thread_info { #define _TIF_FORCED_TF (1 << TIF_FORCED_TF) #define _TIF_DEBUGCTLMSR (1 << TIF_DEBUGCTLMSR) #define _TIF_DS_AREA_MSR (1 << TIF_DS_AREA_MSR) +#define _TIF_SYSCALL_FTRACE (1 << TIF_SYSCALL_FTRACE) /* work to do in syscall_trace_enter() */ #define _TIF_WORK_SYSCALL_ENTRY \ - (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | \ + (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | _TIF_SYSCALL_FTRACE | \ _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | _TIF_SINGLESTEP) /* work to do in syscall_trace_leave() */ #define _TIF_WORK_SYSCALL_EXIT \ - (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP) + (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP | \ + _TIF_SYSCALL_FTRACE) /* work to do on interrupt/exception return */ #define _TIF_WORK_MASK \ @@ -132,7 +135,7 @@ struct thread_info { _TIF_SINGLESTEP|_TIF_SECCOMP|_TIF_SYSCALL_EMU)) /* work to do on any return to user space */ -#define _TIF_ALLWORK_MASK (0x0000FFFF & ~_TIF_SECCOMP) +#define _TIF_ALLWORK_MASK ((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_FTRACE) /* Only used for 64 bit */ #define _TIF_DO_NOTIFY_MASK \ diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 744299c0b774..892b119dba6f 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -44,9 +44,6 @@ #ifdef CONFIG_X86_32 -/* Mappings between node number and cpus on that node. */ -extern cpumask_t node_to_cpumask_map[]; - /* Mappings between logical cpu number and node number */ extern int cpu_to_node_map[]; @@ -57,30 +54,8 @@ static inline int cpu_to_node(int cpu) } #define early_cpu_to_node(cpu) cpu_to_node(cpu) -/* Returns a bitmask of CPUs on Node 'node'. - * - * Side note: this function creates the returned cpumask on the stack - * so with a high NR_CPUS count, excessive stack space is used. The - * cpumask_of_node function should be used whenever possible. - */ -static inline cpumask_t node_to_cpumask(int node) -{ - return node_to_cpumask_map[node]; -} - -/* Returns a bitmask of CPUs on Node 'node'. */ -static inline const struct cpumask *cpumask_of_node(int node) -{ - return &node_to_cpumask_map[node]; -} - -static inline void setup_node_to_cpumask_map(void) { } - #else /* CONFIG_X86_64 */ -/* Mappings between node number and cpus on that node. */ -extern cpumask_t *node_to_cpumask_map; - /* Mappings between logical cpu number and node number */ DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map); @@ -91,8 +66,6 @@ DECLARE_PER_CPU(int, node_number); #ifdef CONFIG_DEBUG_PER_CPU_MAPS extern int cpu_to_node(int cpu); extern int early_cpu_to_node(int cpu); -extern const cpumask_t *cpumask_of_node(int node); -extern cpumask_t node_to_cpumask(int node); #else /* !CONFIG_DEBUG_PER_CPU_MAPS */ @@ -108,42 +81,32 @@ static inline int early_cpu_to_node(int cpu) return early_per_cpu(x86_cpu_to_node_map, cpu); } -/* Returns a pointer to the cpumask of CPUs on Node 'node'. */ -static inline const cpumask_t *cpumask_of_node(int node) -{ - return &node_to_cpumask_map[node]; -} +#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */ + +#endif /* CONFIG_X86_64 */ -/* Returns a bitmask of CPUs on Node 'node'. */ -static inline cpumask_t node_to_cpumask(int node) +/* Mappings between node number and cpus on that node. */ +extern cpumask_var_t node_to_cpumask_map[MAX_NUMNODES]; + +#ifdef CONFIG_DEBUG_PER_CPU_MAPS +extern const struct cpumask *cpumask_of_node(int node); +#else +/* Returns a pointer to the cpumask of CPUs on Node 'node'. */ +static inline const struct cpumask *cpumask_of_node(int node) { return node_to_cpumask_map[node]; } - -#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */ +#endif extern void setup_node_to_cpumask_map(void); /* - * Replace default node_to_cpumask_ptr with optimized version - * Deprecated: use "const struct cpumask *mask = cpumask_of_node(node)" - */ -#define node_to_cpumask_ptr(v, node) \ - const cpumask_t *v = cpumask_of_node(node) - -#define node_to_cpumask_ptr_next(v, node) \ - v = cpumask_of_node(node) - -#endif /* CONFIG_X86_64 */ - -/* * Returns the number of the node containing Node 'node'. This * architecture is flat, so it is a pretty simple function! */ #define parent_node(node) (node) #define pcibus_to_node(bus) __pcibus_to_node(bus) -#define pcibus_to_cpumask(bus) __pcibus_to_cpumask(bus) #ifdef CONFIG_X86_32 extern unsigned long node_start_pfn[]; @@ -209,40 +172,24 @@ static inline int early_cpu_to_node(int cpu) return 0; } -static inline const cpumask_t *cpumask_of_node(int node) -{ - return &cpu_online_map; -} -static inline cpumask_t node_to_cpumask(int node) +static inline const struct cpumask *cpumask_of_node(int node) { - return cpu_online_map; + return cpu_online_mask; } static inline void setup_node_to_cpumask_map(void) { } -/* - * Replace default node_to_cpumask_ptr with optimized version - * Deprecated: use "const struct cpumask *mask = cpumask_of_node(node)" - */ -#define node_to_cpumask_ptr(v, node) \ - const cpumask_t *v = cpumask_of_node(node) - -#define node_to_cpumask_ptr_next(v, node) \ - v = cpumask_of_node(node) #endif #include <asm-generic/topology.h> -extern cpumask_t cpu_coregroup_map(int cpu); extern const struct cpumask *cpu_coregroup_mask(int cpu); #ifdef ENABLE_TOPO_DEFINES #define topology_physical_package_id(cpu) (cpu_data(cpu).phys_proc_id) #define topology_core_id(cpu) (cpu_data(cpu).cpu_core_id) -#define topology_core_siblings(cpu) (per_cpu(cpu_core_map, cpu)) -#define topology_thread_siblings(cpu) (per_cpu(cpu_sibling_map, cpu)) -#define topology_core_cpumask(cpu) (&per_cpu(cpu_core_map, cpu)) -#define topology_thread_cpumask(cpu) (&per_cpu(cpu_sibling_map, cpu)) +#define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu)) +#define topology_thread_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu)) /* indicates that pointers to the topology cpumask_t maps are valid */ #define arch_provides_topology_pointers yes @@ -256,7 +203,7 @@ struct pci_bus; void set_pci_bus_resources_arch_default(struct pci_bus *b); #ifdef CONFIG_SMP -#define mc_capable() (cpus_weight(per_cpu(cpu_core_map, 0)) != nr_cpu_ids) +#define mc_capable() (cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids) #define smt_capable() (smp_num_siblings > 1) #endif diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index c611ad64137f..145cce75cda7 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -66,7 +66,8 @@ obj-$(CONFIG_X86_MPPARSE) += mpparse.o obj-y += apic/ obj-$(CONFIG_X86_REBOOTFIXUPS) += reboot_fixups_32.o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o -obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o +obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o +obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o obj-$(CONFIG_KEXEC) += machine_kexec_$(BITS).o obj-$(CONFIG_KEXEC) += relocate_kernel_$(BITS).o crash.o obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 4c80f1557433..f57658702571 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -5,6 +5,7 @@ #include <linux/kprobes.h> #include <linux/mm.h> #include <linux/vmalloc.h> +#include <linux/memory.h> #include <asm/alternative.h> #include <asm/sections.h> #include <asm/pgtable.h> @@ -12,7 +13,9 @@ #include <asm/nmi.h> #include <asm/vsyscall.h> #include <asm/cacheflush.h> +#include <asm/tlbflush.h> #include <asm/io.h> +#include <asm/fixmap.h> #define MAX_PATCH_LEN (255-1) @@ -226,6 +229,7 @@ static void alternatives_smp_lock(u8 **start, u8 **end, u8 *text, u8 *text_end) { u8 **ptr; + mutex_lock(&text_mutex); for (ptr = start; ptr < end; ptr++) { if (*ptr < text) continue; @@ -234,6 +238,7 @@ static void alternatives_smp_lock(u8 **start, u8 **end, u8 *text, u8 *text_end) /* turn DS segment override prefix into lock prefix */ text_poke(*ptr, ((unsigned char []){0xf0}), 1); }; + mutex_unlock(&text_mutex); } static void alternatives_smp_unlock(u8 **start, u8 **end, u8 *text, u8 *text_end) @@ -243,6 +248,7 @@ static void alternatives_smp_unlock(u8 **start, u8 **end, u8 *text, u8 *text_end if (noreplace_smp) return; + mutex_lock(&text_mutex); for (ptr = start; ptr < end; ptr++) { if (*ptr < text) continue; @@ -251,6 +257,7 @@ static void alternatives_smp_unlock(u8 **start, u8 **end, u8 *text, u8 *text_end /* turn lock prefix into DS segment override prefix */ text_poke(*ptr, ((unsigned char []){0x3E}), 1); }; + mutex_unlock(&text_mutex); } struct smp_alt_module { @@ -500,15 +507,16 @@ void *text_poke_early(void *addr, const void *opcode, size_t len) * It means the size must be writable atomically and the address must be aligned * in a way that permits an atomic write. It also makes sure we fit on a single * page. + * + * Note: Must be called under text_mutex. */ void *__kprobes text_poke(void *addr, const void *opcode, size_t len) { + unsigned long flags; char *vaddr; - int nr_pages = 2; struct page *pages[2]; int i; - might_sleep(); if (!core_kernel_text((unsigned long)addr)) { pages[0] = vmalloc_to_page(addr); pages[1] = vmalloc_to_page(addr + PAGE_SIZE); @@ -518,18 +526,21 @@ void *__kprobes text_poke(void *addr, const void *opcode, size_t len) pages[1] = virt_to_page(addr + PAGE_SIZE); } BUG_ON(!pages[0]); - if (!pages[1]) - nr_pages = 1; - vaddr = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL); - BUG_ON(!vaddr); - local_irq_disable(); + local_irq_save(flags); + set_fixmap(FIX_TEXT_POKE0, page_to_phys(pages[0])); + if (pages[1]) + set_fixmap(FIX_TEXT_POKE1, page_to_phys(pages[1])); + vaddr = (char *)fix_to_virt(FIX_TEXT_POKE0); memcpy(&vaddr[(unsigned long)addr & ~PAGE_MASK], opcode, len); - local_irq_enable(); - vunmap(vaddr); + clear_fixmap(FIX_TEXT_POKE0); + if (pages[1]) + clear_fixmap(FIX_TEXT_POKE1); + local_flush_tlb(); sync_core(); /* Could also do a CLFLUSH here to speed up CPU recovery; but that causes hangs on some VIA CPUs. */ for (i = 0; i < len; i++) BUG_ON(((char *)addr)[i] != ((char *)opcode)[i]); + local_irq_restore(flags); return addr; } diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index d806ecaa948f..676cdac385c0 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -26,12 +26,12 @@ static int bigsmp_apic_id_registered(void) return 1; } -static const cpumask_t *bigsmp_target_cpus(void) +static const struct cpumask *bigsmp_target_cpus(void) { #ifdef CONFIG_SMP - return &cpu_online_map; + return cpu_online_mask; #else - return &cpumask_of_cpu(0); + return cpumask_of(0); #endif } @@ -118,9 +118,9 @@ static int bigsmp_check_phys_apicid_present(int boot_cpu_physical_apicid) } /* As we are using single CPU as destination, pick only one CPU here */ -static unsigned int bigsmp_cpu_mask_to_apicid(const cpumask_t *cpumask) +static unsigned int bigsmp_cpu_mask_to_apicid(const struct cpumask *cpumask) { - return bigsmp_cpu_to_logical_apicid(first_cpu(*cpumask)); + return bigsmp_cpu_to_logical_apicid(cpumask_first(cpumask)); } static unsigned int bigsmp_cpu_mask_to_apicid_and(const struct cpumask *cpumask, @@ -188,10 +188,10 @@ static const struct dmi_system_id bigsmp_dmi_table[] = { { } /* NULL entry stops DMI scanning */ }; -static void bigsmp_vector_allocation_domain(int cpu, cpumask_t *retmask) +static void bigsmp_vector_allocation_domain(int cpu, struct cpumask *retmask) { - cpus_clear(*retmask); - cpu_set(cpu, *retmask); + cpumask_clear(retmask); + cpumask_set_cpu(cpu, retmask); } static int probe_bigsmp(void) diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c index 19588f2770ee..1c11b819f245 100644 --- a/arch/x86/kernel/apic/es7000_32.c +++ b/arch/x86/kernel/apic/es7000_32.c @@ -410,7 +410,7 @@ static void es7000_enable_apic_mode(void) WARN(1, "Command failed, status = %x\n", mip_status); } -static void es7000_vector_allocation_domain(int cpu, cpumask_t *retmask) +static void es7000_vector_allocation_domain(int cpu, struct cpumask *retmask) { /* Careful. Some cpus do not strictly honor the set of cpus * specified in the interrupt destination when using lowest @@ -420,7 +420,8 @@ static void es7000_vector_allocation_domain(int cpu, cpumask_t *retmask) * deliver interrupts to the wrong hyperthread when only one * hyperthread was specified in the interrupt desitination. */ - *retmask = (cpumask_t){ { [0] = APIC_ALL_CPUS, } }; + cpumask_clear(retmask); + cpumask_bits(retmask)[0] = APIC_ALL_CPUS; } @@ -455,14 +456,14 @@ static int es7000_apic_id_registered(void) return 1; } -static const cpumask_t *target_cpus_cluster(void) +static const struct cpumask *target_cpus_cluster(void) { - return &CPU_MASK_ALL; + return cpu_all_mask; } -static const cpumask_t *es7000_target_cpus(void) +static const struct cpumask *es7000_target_cpus(void) { - return &cpumask_of_cpu(smp_processor_id()); + return cpumask_of(smp_processor_id()); } static unsigned long @@ -517,7 +518,7 @@ static void es7000_setup_apic_routing(void) "Enabling APIC mode: %s. Using %d I/O APICs, target cpus %lx\n", (apic_version[apic] == 0x14) ? "Physical Cluster" : "Logical Cluster", - nr_ioapics, cpus_addr(*es7000_target_cpus())[0]); + nr_ioapics, cpumask_bits(es7000_target_cpus())[0]); } static int es7000_apicid_to_node(int logical_apicid) @@ -572,7 +573,7 @@ static int es7000_check_phys_apicid_present(int cpu_physical_apicid) return 1; } -static unsigned int es7000_cpu_mask_to_apicid(const cpumask_t *cpumask) +static unsigned int es7000_cpu_mask_to_apicid(const struct cpumask *cpumask) { unsigned int round = 0; int cpu, uninitialized_var(apicid); diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c index bdfad80c3cf1..d6bd62407152 100644 --- a/arch/x86/kernel/apic/nmi.c +++ b/arch/x86/kernel/apic/nmi.c @@ -39,7 +39,7 @@ int unknown_nmi_panic; int nmi_watchdog_enabled; -static cpumask_t backtrace_mask = CPU_MASK_NONE; +static cpumask_var_t backtrace_mask; /* nmi_active: * >0: the lapic NMI watchdog is active, but can be disabled @@ -138,6 +138,7 @@ int __init check_nmi_watchdog(void) if (!prev_nmi_count) goto error; + alloc_cpumask_var(&backtrace_mask, GFP_KERNEL); printk(KERN_INFO "Testing NMI watchdog ... "); #ifdef CONFIG_SMP @@ -413,14 +414,14 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason) touched = 1; } - if (cpu_isset(cpu, backtrace_mask)) { + if (cpumask_test_cpu(cpu, backtrace_mask)) { static DEFINE_SPINLOCK(lock); /* Serialise the printks */ spin_lock(&lock); printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu); dump_stack(); spin_unlock(&lock); - cpu_clear(cpu, backtrace_mask); + cpumask_clear_cpu(cpu, backtrace_mask); } /* Could check oops_in_progress here too, but it's safer not to */ @@ -554,10 +555,10 @@ void __trigger_all_cpu_backtrace(void) { int i; - backtrace_mask = cpu_online_map; + cpumask_copy(backtrace_mask, cpu_online_mask); /* Wait for up to 10 seconds for all CPUs to do the backtrace */ for (i = 0; i < 10 * 1000; i++) { - if (cpus_empty(backtrace_mask)) + if (cpumask_empty(backtrace_mask)) break; mdelay(1); } diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index ba2fc6465534..533e59c6fc82 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -334,9 +334,9 @@ static inline void numaq_smp_callin_clear_local_apic(void) clear_local_APIC(); } -static inline const cpumask_t *numaq_target_cpus(void) +static inline const struct cpumask *numaq_target_cpus(void) { - return &CPU_MASK_ALL; + return cpu_all_mask; } static inline unsigned long @@ -427,7 +427,7 @@ static inline int numaq_check_phys_apicid_present(int boot_cpu_physical_apicid) * We use physical apicids here, not logical, so just return the default * physical broadcast to stop people from breaking us */ -static inline unsigned int numaq_cpu_mask_to_apicid(const cpumask_t *cpumask) +static unsigned int numaq_cpu_mask_to_apicid(const struct cpumask *cpumask) { return 0x0F; } @@ -462,7 +462,7 @@ static int probe_numaq(void) return found_numaq; } -static void numaq_vector_allocation_domain(int cpu, cpumask_t *retmask) +static void numaq_vector_allocation_domain(int cpu, struct cpumask *retmask) { /* Careful. Some cpus do not strictly honor the set of cpus * specified in the interrupt destination when using lowest @@ -472,7 +472,8 @@ static void numaq_vector_allocation_domain(int cpu, cpumask_t *retmask) * deliver interrupts to the wrong hyperthread when only one * hyperthread was specified in the interrupt desitination. */ - *retmask = (cpumask_t){ { [0] = APIC_ALL_CPUS, } }; + cpumask_clear(retmask); + cpumask_bits(retmask)[0] = APIC_ALL_CPUS; } static void numaq_setup_portio_remap(void) diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 141c99a1c264..01eda2ac65e4 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -83,7 +83,8 @@ static void default_vector_allocation_domain(int cpu, struct cpumask *retmask) * deliver interrupts to the wrong hyperthread when only one * hyperthread was specified in the interrupt desitination. */ - *retmask = (cpumask_t) { { [0] = APIC_ALL_CPUS } }; + cpumask_clear(retmask); + cpumask_bits(retmask)[0] = APIC_ALL_CPUS; } /* should be called last. */ diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c index aac52fa873ff..9cfe1f415d81 100644 --- a/arch/x86/kernel/apic/summit_32.c +++ b/arch/x86/kernel/apic/summit_32.c @@ -53,23 +53,19 @@ static unsigned summit_get_apic_id(unsigned long x) return (x >> 24) & 0xFF; } -static inline void summit_send_IPI_mask(const cpumask_t *mask, int vector) +static inline void summit_send_IPI_mask(const struct cpumask *mask, int vector) { default_send_IPI_mask_sequence_logical(mask, vector); } static void summit_send_IPI_allbutself(int vector) { - cpumask_t mask = cpu_online_map; - cpu_clear(smp_processor_id(), mask); - - if (!cpus_empty(mask)) - summit_send_IPI_mask(&mask, vector); + default_send_IPI_mask_allbutself_logical(cpu_online_mask, vector); } static void summit_send_IPI_all(int vector) { - summit_send_IPI_mask(&cpu_online_map, vector); + summit_send_IPI_mask(cpu_online_mask, vector); } #include <asm/tsc.h> @@ -186,13 +182,13 @@ static inline int is_WPEG(struct rio_detail *rio){ #define SUMMIT_APIC_DFR_VALUE (APIC_DFR_CLUSTER) -static const cpumask_t *summit_target_cpus(void) +static const struct cpumask *summit_target_cpus(void) { /* CPU_MASK_ALL (0xff) has undefined behaviour with * dest_LowestPrio mode logical clustered apic interrupt routing * Just start on cpu 0. IRQ balancing will spread load */ - return &cpumask_of_cpu(0); + return cpumask_of(0); } static unsigned long summit_check_apicid_used(physid_mask_t bitmap, int apicid) @@ -289,7 +285,7 @@ static int summit_check_phys_apicid_present(int boot_cpu_physical_apicid) return 1; } -static unsigned int summit_cpu_mask_to_apicid(const cpumask_t *cpumask) +static unsigned int summit_cpu_mask_to_apicid(const struct cpumask *cpumask) { unsigned int round = 0; int cpu, apicid = 0; @@ -346,7 +342,7 @@ static int probe_summit(void) return 0; } -static void summit_vector_allocation_domain(int cpu, cpumask_t *retmask) +static void summit_vector_allocation_domain(int cpu, struct cpumask *retmask) { /* Careful. Some cpus do not strictly honor the set of cpus * specified in the interrupt destination when using lowest @@ -356,7 +352,8 @@ static void summit_vector_allocation_domain(int cpu, cpumask_t *retmask) * deliver interrupts to the wrong hyperthread when only one * hyperthread was specified in the interrupt desitination. */ - *retmask = (cpumask_t){ { [0] = APIC_ALL_CPUS, } }; + cpumask_clear(retmask); + cpumask_bits(retmask)[0] = APIC_ALL_CPUS; } #ifdef CONFIG_X86_SUMMIT_NUMA diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index ac7783a67432..49e0939bac42 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -466,7 +466,7 @@ static const lookup_t error_table[] = { * @err: APM BIOS return code * * Write a meaningful log entry to the kernel log in the event of - * an APM error. + * an APM error. Note that this also handles (negative) kernel errors. */ static void apm_error(char *str, int err) @@ -478,43 +478,14 @@ static void apm_error(char *str, int err) break; if (i < ERROR_COUNT) printk(KERN_NOTICE "apm: %s: %s\n", str, error_table[i].msg); + else if (err < 0) + printk(KERN_NOTICE "apm: %s: linux error code %i\n", str, err); else printk(KERN_NOTICE "apm: %s: unknown error code %#2.2x\n", str, err); } /* - * Lock APM functionality to physical CPU 0 - */ - -#ifdef CONFIG_SMP - -static cpumask_t apm_save_cpus(void) -{ - cpumask_t x = current->cpus_allowed; - /* Some bioses don't like being called from CPU != 0 */ - set_cpus_allowed(current, cpumask_of_cpu(0)); - BUG_ON(smp_processor_id() != 0); - return x; -} - -static inline void apm_restore_cpus(cpumask_t mask) -{ - set_cpus_allowed(current, mask); -} - -#else - -/* - * No CPU lockdown needed on a uniprocessor - */ - -#define apm_save_cpus() (current->cpus_allowed) -#define apm_restore_cpus(x) (void)(x) - -#endif - -/* * These are the actual BIOS calls. Depending on APM_ZERO_SEGS and * apm_info.allow_ints, we are being really paranoid here! Not only * are interrupts disabled, but all the segment registers (except SS) @@ -568,16 +539,23 @@ static inline void apm_irq_restore(unsigned long flags) # define APM_DO_RESTORE_SEGS #endif +struct apm_bios_call { + u32 func; + /* In and out */ + u32 ebx; + u32 ecx; + /* Out only */ + u32 eax; + u32 edx; + u32 esi; + + /* Error: -ENOMEM, or bits 8-15 of eax */ + int err; +}; + /** - * apm_bios_call - Make an APM BIOS 32bit call - * @func: APM function to execute - * @ebx_in: EBX register for call entry - * @ecx_in: ECX register for call entry - * @eax: EAX register return - * @ebx: EBX register return - * @ecx: ECX register return - * @edx: EDX register return - * @esi: ESI register return + * __apm_bios_call - Make an APM BIOS 32bit call + * @_call: pointer to struct apm_bios_call. * * Make an APM call using the 32bit protected mode interface. The * caller is responsible for knowing if APM BIOS is configured and @@ -586,80 +564,142 @@ static inline void apm_irq_restore(unsigned long flags) * flag is loaded into AL. If there is an error, then the error * code is returned in AH (bits 8-15 of eax) and this function * returns non-zero. + * + * Note: this makes the call on the current CPU. */ - -static u8 apm_bios_call(u32 func, u32 ebx_in, u32 ecx_in, - u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, u32 *esi) +static long __apm_bios_call(void *_call) { APM_DECL_SEGS unsigned long flags; - cpumask_t cpus; int cpu; struct desc_struct save_desc_40; struct desc_struct *gdt; - - cpus = apm_save_cpus(); + struct apm_bios_call *call = _call; cpu = get_cpu(); + BUG_ON(cpu != 0); gdt = get_cpu_gdt_table(cpu); save_desc_40 = gdt[0x40 / 8]; gdt[0x40 / 8] = bad_bios_desc; apm_irq_save(flags); APM_DO_SAVE_SEGS; - apm_bios_call_asm(func, ebx_in, ecx_in, eax, ebx, ecx, edx, esi); + apm_bios_call_asm(call->func, call->ebx, call->ecx, + &call->eax, &call->ebx, &call->ecx, &call->edx, + &call->esi); APM_DO_RESTORE_SEGS; apm_irq_restore(flags); gdt[0x40 / 8] = save_desc_40; put_cpu(); - apm_restore_cpus(cpus); - return *eax & 0xff; + return call->eax & 0xff; +} + +/* Run __apm_bios_call or __apm_bios_call_simple on CPU 0 */ +static int on_cpu0(long (*fn)(void *), struct apm_bios_call *call) +{ + int ret; + + /* Don't bother with work_on_cpu in the common case, so we don't + * have to worry about OOM or overhead. */ + if (get_cpu() == 0) { + ret = fn(call); + put_cpu(); + } else { + put_cpu(); + ret = work_on_cpu(0, fn, call); + } + + /* work_on_cpu can fail with -ENOMEM */ + if (ret < 0) + call->err = ret; + else + call->err = (call->eax >> 8) & 0xff; + + return ret; } /** - * apm_bios_call_simple - make a simple APM BIOS 32bit call - * @func: APM function to invoke - * @ebx_in: EBX register value for BIOS call - * @ecx_in: ECX register value for BIOS call - * @eax: EAX register on return from the BIOS call + * apm_bios_call - Make an APM BIOS 32bit call (on CPU 0) + * @call: the apm_bios_call registers. + * + * If there is an error, it is returned in @call.err. + */ +static int apm_bios_call(struct apm_bios_call *call) +{ + return on_cpu0(__apm_bios_call, call); +} + +/** + * __apm_bios_call_simple - Make an APM BIOS 32bit call (on CPU 0) + * @_call: pointer to struct apm_bios_call. * * Make a BIOS call that returns one value only, or just status. * If there is an error, then the error code is returned in AH - * (bits 8-15 of eax) and this function returns non-zero. This is - * used for simpler BIOS operations. This call may hold interrupts - * off for a long time on some laptops. + * (bits 8-15 of eax) and this function returns non-zero (it can + * also return -ENOMEM). This is used for simpler BIOS operations. + * This call may hold interrupts off for a long time on some laptops. + * + * Note: this makes the call on the current CPU. */ - -static u8 apm_bios_call_simple(u32 func, u32 ebx_in, u32 ecx_in, u32 *eax) +static long __apm_bios_call_simple(void *_call) { u8 error; APM_DECL_SEGS unsigned long flags; - cpumask_t cpus; int cpu; struct desc_struct save_desc_40; struct desc_struct *gdt; - - cpus = apm_save_cpus(); + struct apm_bios_call *call = _call; cpu = get_cpu(); + BUG_ON(cpu != 0); gdt = get_cpu_gdt_table(cpu); save_desc_40 = gdt[0x40 / 8]; gdt[0x40 / 8] = bad_bios_desc; apm_irq_save(flags); APM_DO_SAVE_SEGS; - error = apm_bios_call_simple_asm(func, ebx_in, ecx_in, eax); + error = apm_bios_call_simple_asm(call->func, call->ebx, call->ecx, + &call->eax); APM_DO_RESTORE_SEGS; apm_irq_restore(flags); gdt[0x40 / 8] = save_desc_40; put_cpu(); - apm_restore_cpus(cpus); return error; } /** + * apm_bios_call_simple - make a simple APM BIOS 32bit call + * @func: APM function to invoke + * @ebx_in: EBX register value for BIOS call + * @ecx_in: ECX register value for BIOS call + * @eax: EAX register on return from the BIOS call + * @err: bits + * + * Make a BIOS call that returns one value only, or just status. + * If there is an error, then the error code is returned in @err + * and this function returns non-zero. This is used for simpler + * BIOS operations. This call may hold interrupts off for a long + * time on some laptops. + */ +static int apm_bios_call_simple(u32 func, u32 ebx_in, u32 ecx_in, u32 *eax, + int *err) +{ + struct apm_bios_call call; + int ret; + + call.func = func; + call.ebx = ebx_in; + call.ecx = ecx_in; + + ret = on_cpu0(__apm_bios_call_simple, &call); + *eax = call.eax; + *err = call.err; + return ret; +} + +/** * apm_driver_version - APM driver version * @val: loaded with the APM version on return * @@ -678,9 +718,10 @@ static u8 apm_bios_call_simple(u32 func, u32 ebx_in, u32 ecx_in, u32 *eax) static int apm_driver_version(u_short *val) { u32 eax; + int err; - if (apm_bios_call_simple(APM_FUNC_VERSION, 0, *val, &eax)) - return (eax >> 8) & 0xff; + if (apm_bios_call_simple(APM_FUNC_VERSION, 0, *val, &eax, &err)) + return err; *val = eax; return APM_SUCCESS; } @@ -701,22 +742,21 @@ static int apm_driver_version(u_short *val) * that APM 1.2 is in use. If no messges are pending the value 0x80 * is returned (No power management events pending). */ - static int apm_get_event(apm_event_t *event, apm_eventinfo_t *info) { - u32 eax; - u32 ebx; - u32 ecx; - u32 dummy; + struct apm_bios_call call; - if (apm_bios_call(APM_FUNC_GET_EVENT, 0, 0, &eax, &ebx, &ecx, - &dummy, &dummy)) - return (eax >> 8) & 0xff; - *event = ebx; + call.func = APM_FUNC_GET_EVENT; + call.ebx = call.ecx = 0; + + if (apm_bios_call(&call)) + return call.err; + + *event = call.ebx; if (apm_info.connection_version < 0x0102) *info = ~0; /* indicate info not valid */ else - *info = ecx; + *info = call.ecx; return APM_SUCCESS; } @@ -737,9 +777,10 @@ static int apm_get_event(apm_event_t *event, apm_eventinfo_t *info) static int set_power_state(u_short what, u_short state) { u32 eax; + int err; - if (apm_bios_call_simple(APM_FUNC_SET_STATE, what, state, &eax)) - return (eax >> 8) & 0xff; + if (apm_bios_call_simple(APM_FUNC_SET_STATE, what, state, &eax, &err)) + return err; return APM_SUCCESS; } @@ -770,6 +811,7 @@ static int apm_do_idle(void) u8 ret = 0; int idled = 0; int polling; + int err; polling = !!(current_thread_info()->status & TS_POLLING); if (polling) { @@ -782,7 +824,7 @@ static int apm_do_idle(void) } if (!need_resched()) { idled = 1; - ret = apm_bios_call_simple(APM_FUNC_IDLE, 0, 0, &eax); + ret = apm_bios_call_simple(APM_FUNC_IDLE, 0, 0, &eax, &err); } if (polling) current_thread_info()->status |= TS_POLLING; @@ -797,8 +839,7 @@ static int apm_do_idle(void) * Only report the failure the first 5 times. */ if (++t < 5) { - printk(KERN_DEBUG "apm_do_idle failed (%d)\n", - (eax >> 8) & 0xff); + printk(KERN_DEBUG "apm_do_idle failed (%d)\n", err); t = jiffies; } return -1; @@ -816,9 +857,10 @@ static int apm_do_idle(void) static void apm_do_busy(void) { u32 dummy; + int err; if (clock_slowed || ALWAYS_CALL_BUSY) { - (void)apm_bios_call_simple(APM_FUNC_BUSY, 0, 0, &dummy); + (void)apm_bios_call_simple(APM_FUNC_BUSY, 0, 0, &dummy, &err); clock_slowed = 0; } } @@ -937,7 +979,7 @@ static void apm_power_off(void) /* Some bioses don't like being called from CPU != 0 */ if (apm_info.realmode_power_off) { - (void)apm_save_cpus(); + set_cpus_allowed_ptr(current, cpumask_of(0)); machine_real_restart(po_bios_call, sizeof(po_bios_call)); } else { (void)set_system_power_state(APM_STATE_OFF); @@ -956,12 +998,13 @@ static void apm_power_off(void) static int apm_enable_power_management(int enable) { u32 eax; + int err; if ((enable == 0) && (apm_info.bios.flags & APM_BIOS_DISENGAGED)) return APM_NOT_ENGAGED; if (apm_bios_call_simple(APM_FUNC_ENABLE_PM, APM_DEVICE_BALL, - enable, &eax)) - return (eax >> 8) & 0xff; + enable, &eax, &err)) + return err; if (enable) apm_info.bios.flags &= ~APM_BIOS_DISABLED; else @@ -986,24 +1029,23 @@ static int apm_enable_power_management(int enable) static int apm_get_power_status(u_short *status, u_short *bat, u_short *life) { - u32 eax; - u32 ebx; - u32 ecx; - u32 edx; - u32 dummy; + struct apm_bios_call call; + + call.func = APM_FUNC_GET_STATUS; + call.ebx = APM_DEVICE_ALL; + call.ecx = 0; if (apm_info.get_power_status_broken) return APM_32_UNSUPPORTED; - if (apm_bios_call(APM_FUNC_GET_STATUS, APM_DEVICE_ALL, 0, - &eax, &ebx, &ecx, &edx, &dummy)) - return (eax >> 8) & 0xff; - *status = ebx; - *bat = ecx; + if (apm_bios_call(&call)) + return call.err; + *status = call.ebx; + *bat = call.ecx; if (apm_info.get_power_status_swabinminutes) { - *life = swab16((u16)edx); + *life = swab16((u16)call.edx); *life |= 0x8000; } else - *life = edx; + *life = call.edx; return APM_SUCCESS; } @@ -1048,12 +1090,14 @@ static int apm_get_battery_status(u_short which, u_short *status, static int apm_engage_power_management(u_short device, int enable) { u32 eax; + int err; if ((enable == 0) && (device == APM_DEVICE_ALL) && (apm_info.bios.flags & APM_BIOS_DISABLED)) return APM_DISABLED; - if (apm_bios_call_simple(APM_FUNC_ENGAGE_PM, device, enable, &eax)) - return (eax >> 8) & 0xff; + if (apm_bios_call_simple(APM_FUNC_ENGAGE_PM, device, enable, + &eax, &err)) + return err; if (device == APM_DEVICE_ALL) { if (enable) apm_info.bios.flags &= ~APM_BIOS_DISENGAGED; @@ -1689,16 +1733,14 @@ static int apm(void *unused) char *power_stat; char *bat_stat; -#ifdef CONFIG_SMP /* 2002/08/01 - WT * This is to avoid random crashes at boot time during initialization * on SMP systems in case of "apm=power-off" mode. Seen on ASUS A7M266D. * Some bioses don't like being called from CPU != 0. * Method suggested by Ingo Molnar. */ - set_cpus_allowed(current, cpumask_of_cpu(0)); + set_cpus_allowed_ptr(current, cpumask_of(0)); BUG_ON(smp_processor_id() != 0); -#endif if (apm_info.connection_version == 0) { apm_info.connection_version = apm_info.bios.version; diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index e2962cc1e27b..c4f667896c28 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -41,8 +41,6 @@ #include "cpu.h" -#ifdef CONFIG_X86_64 - /* all of these masks are initialized in setup_cpu_local_masks() */ cpumask_var_t cpu_initialized_mask; cpumask_var_t cpu_callout_mask; @@ -60,16 +58,6 @@ void __init setup_cpu_local_masks(void) alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask); } -#else /* CONFIG_X86_32 */ - -cpumask_t cpu_sibling_setup_map; -cpumask_t cpu_callout_map; -cpumask_t cpu_initialized; -cpumask_t cpu_callin_map; - -#endif /* CONFIG_X86_32 */ - - static const struct cpu_dev *this_cpu __cpuinitdata; DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = { @@ -859,6 +847,7 @@ static void vgetcpu_set_mode(void) void __init identify_boot_cpu(void) { identify_cpu(&boot_cpu_data); + init_c1e_mask(); #ifdef CONFIG_X86_32 sysenter_setup(); enable_sep_cpu(); diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c index 23da96e57b17..05209b5cc6ca 100644 --- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -33,7 +33,7 @@ #include <linux/cpufreq.h> #include <linux/compiler.h> #include <linux/dmi.h> -#include <linux/ftrace.h> +#include <trace/power.h> #include <linux/acpi.h> #include <linux/io.h> @@ -72,6 +72,8 @@ struct acpi_cpufreq_data { static DEFINE_PER_CPU(struct acpi_cpufreq_data *, drv_data); +DEFINE_TRACE(power_mark); + /* acpi_perf_data is a pointer to percpu data. */ static struct acpi_processor_performance *acpi_perf_data; diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c index 41ed94915f97..6ac55bd341ae 100644 --- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c +++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c @@ -211,7 +211,7 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy) unsigned int i; #ifdef CONFIG_SMP - cpumask_copy(policy->cpus, &per_cpu(cpu_sibling_map, policy->cpu)); + cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu)); #endif /* Errata workaround */ diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c index a15ac94e0b9b..4709ead2db52 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c @@ -54,7 +54,10 @@ static DEFINE_PER_CPU(struct powernow_k8_data *, powernow_data); static int cpu_family = CPU_OPTERON; #ifndef CONFIG_SMP -DEFINE_PER_CPU(cpumask_t, cpu_core_map); +static inline const struct cpumask *cpu_core_mask(int cpu) +{ + return cpumask_of(0); +} #endif /* Return a frequency in MHz, given an input fid */ @@ -699,7 +702,7 @@ static int fill_powernow_table(struct powernow_k8_data *data, dprintk("cfid 0x%x, cvid 0x%x\n", data->currfid, data->currvid); data->powernow_table = powernow_table; - if (first_cpu(per_cpu(cpu_core_map, data->cpu)) == data->cpu) + if (cpumask_first(cpu_core_mask(data->cpu)) == data->cpu) print_basics(data); for (j = 0; j < data->numps; j++) @@ -862,7 +865,7 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) /* fill in data */ data->numps = data->acpi_data.state_count; - if (first_cpu(per_cpu(cpu_core_map, data->cpu)) == data->cpu) + if (cpumask_first(cpu_core_mask(data->cpu)) == data->cpu) print_basics(data); powernow_k8_acpi_pst_values(data, 0); @@ -1300,7 +1303,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) if (cpu_family == CPU_HW_PSTATE) cpumask_copy(pol->cpus, cpumask_of(pol->cpu)); else - cpumask_copy(pol->cpus, &per_cpu(cpu_core_map, pol->cpu)); + cpumask_copy(pol->cpus, cpu_core_mask(pol->cpu)); data->available_cores = pol->cpus; if (cpu_family == CPU_HW_PSTATE) @@ -1365,7 +1368,7 @@ static unsigned int powernowk8_get(unsigned int cpu) unsigned int khz = 0; unsigned int first; - first = first_cpu(per_cpu(cpu_core_map, cpu)); + first = cpumask_first(cpu_core_mask(cpu)); data = per_cpu(powernow_data, first); if (!data) diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c index 8bbb11adb315..016c1a4fa3fc 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c @@ -321,7 +321,7 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy) /* only run on CPU to be set, or on its sibling */ #ifdef CONFIG_SMP - cpumask_copy(policy->cpus, &per_cpu(cpu_sibling_map, policy->cpu)); + cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu)); #endif cpus_allowed = current->cpus_allowed; diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index c471eb1a389c..483eda96e102 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -159,7 +159,7 @@ struct _cpuid4_info_regs { unsigned long can_disable; }; -#ifdef CONFIG_PCI +#if defined(CONFIG_PCI) && defined(CONFIG_SYSFS) static struct pci_device_id k8_nb_id[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x1103) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x1203) }, @@ -324,15 +324,6 @@ __cpuinit cpuid4_cache_lookup_regs(int index, return 0; } -static int -__cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf) -{ - struct _cpuid4_info_regs *leaf_regs = - (struct _cpuid4_info_regs *)this_leaf; - - return cpuid4_cache_lookup_regs(index, leaf_regs); -} - static int __cpuinit find_num_cache_leaves(void) { unsigned int eax, ebx, ecx, edx; @@ -508,6 +499,8 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) return l2; } +#ifdef CONFIG_SYSFS + /* pointer to _cpuid4_info array (for each cache leaf) */ static DEFINE_PER_CPU(struct _cpuid4_info *, cpuid4_info); #define CPUID4_INFO_IDX(x, y) (&((per_cpu(cpuid4_info, x))[y])) @@ -571,6 +564,15 @@ static void __cpuinit free_cache_attributes(unsigned int cpu) per_cpu(cpuid4_info, cpu) = NULL; } +static int +__cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf) +{ + struct _cpuid4_info_regs *leaf_regs = + (struct _cpuid4_info_regs *)this_leaf; + + return cpuid4_cache_lookup_regs(index, leaf_regs); +} + static void __cpuinit get_cpu_leaves(void *_retval) { int j, *retval = _retval, cpu = smp_processor_id(); @@ -612,8 +614,6 @@ static int __cpuinit detect_cache_attributes(unsigned int cpu) return retval; } -#ifdef CONFIG_SYSFS - #include <linux/kobject.h> #include <linux/sysfs.h> diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c index ca14604611ec..863f89568b1a 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_64.c @@ -990,7 +990,7 @@ static struct sysdev_attribute *mce_attributes[] = { NULL }; -static cpumask_t mce_device_initialized = CPU_MASK_NONE; +static cpumask_var_t mce_device_initialized; /* Per cpu sysdev init. All of the cpus still share the same ctl bank */ static __cpuinit int mce_create_device(unsigned int cpu) @@ -1021,7 +1021,7 @@ static __cpuinit int mce_create_device(unsigned int cpu) if (err) goto error2; } - cpu_set(cpu, mce_device_initialized); + cpumask_set_cpu(cpu, mce_device_initialized); return 0; error2: @@ -1043,7 +1043,7 @@ static __cpuinit void mce_remove_device(unsigned int cpu) { int i; - if (!cpu_isset(cpu, mce_device_initialized)) + if (!cpumask_test_cpu(cpu, mce_device_initialized)) return; for (i = 0; mce_attributes[i]; i++) @@ -1053,7 +1053,7 @@ static __cpuinit void mce_remove_device(unsigned int cpu) sysdev_remove_file(&per_cpu(device_mce, cpu), &bank_attrs[i]); sysdev_unregister(&per_cpu(device_mce,cpu)); - cpu_clear(cpu, mce_device_initialized); + cpumask_clear_cpu(cpu, mce_device_initialized); } /* Make sure there are no machine checks on offlined CPUs. */ @@ -1162,6 +1162,8 @@ static __init int mce_init_device(void) if (!mce_available(&boot_cpu_data)) return -EIO; + alloc_cpumask_var(&mce_device_initialized, GFP_KERNEL); + err = mce_init_banks(); if (err) return err; diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c index 7d01be868870..56dde9c4bc96 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c @@ -485,7 +485,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) #ifdef CONFIG_SMP if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) { /* symlink */ - i = cpumask_first(&per_cpu(cpu_core_map, cpu)); + i = cpumask_first(cpu_core_mask(cpu)); /* first core not up yet */ if (cpu_data(i).cpu_core_id) @@ -505,7 +505,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) if (err) goto out; - cpumask_copy(b->cpus, &per_cpu(cpu_core_map, cpu)); + cpumask_copy(b->cpus, cpu_core_mask(cpu)); per_cpu(threshold_banks, cpu)[bank] = b; goto out; } @@ -529,7 +529,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) #ifndef CONFIG_SMP cpumask_setall(b->cpus); #else - cpumask_copy(b->cpus, &per_cpu(cpu_core_map, cpu)); + cpumask_copy(b->cpus, cpu_core_mask(cpu)); #endif per_cpu(threshold_banks, cpu)[bank] = b; diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c index 57df3d383470..d6b72df89d69 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c @@ -249,7 +249,7 @@ void cmci_rediscover(int dying) for_each_online_cpu (cpu) { if (cpu == dying) continue; - if (set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu))) + if (set_cpus_allowed_ptr(current, cpumask_of(cpu))) continue; /* Recheck banks in case CPUs don't all have the same */ if (cmci_supported(&banks)) diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 37f28fc7cf95..0b776c09aff3 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -462,9 +462,6 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, *base = base_hi << (32 - PAGE_SHIFT) | base_lo >> PAGE_SHIFT; *type = base_lo & 0xff; - printk(KERN_DEBUG " get_mtrr: cpu%d reg%02d base=%010lx size=%010lx %s\n", - cpu, reg, *base, *size, - mtrr_attrib_to_str(*type & 0xff)); out_put_cpu: put_cpu(); } diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index d67e0e48bc2d..f93047fed791 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -14,7 +14,7 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c, if (c->x86_max_cores * smp_num_siblings > 1) { seq_printf(m, "physical id\t: %d\n", c->phys_proc_id); seq_printf(m, "siblings\t: %d\n", - cpus_weight(per_cpu(cpu_core_map, cpu))); + cpumask_weight(cpu_sibling_mask(cpu))); seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id); seq_printf(m, "cpu cores\t: %d\n", c->booted_cores); seq_printf(m, "apicid\t\t: %d\n", c->apicid); @@ -143,9 +143,9 @@ static int show_cpuinfo(struct seq_file *m, void *v) static void *c_start(struct seq_file *m, loff_t *pos) { if (*pos == 0) /* just in case, cpu 0 is not the first */ - *pos = first_cpu(cpu_online_map); + *pos = cpumask_first(cpu_online_mask); else - *pos = next_cpu_nr(*pos - 1, cpu_online_map); + *pos = cpumask_next(*pos - 1, cpu_online_mask); if ((*pos) < nr_cpu_ids) return &cpu_data(*pos); return NULL; diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index dd2130b0fb3e..95ea5fa7d444 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -15,6 +15,7 @@ #include <linux/bug.h> #include <linux/nmi.h> #include <linux/sysfs.h> +#include <linux/ftrace.h> #include <asm/stacktrace.h> @@ -196,6 +197,11 @@ unsigned __kprobes long oops_begin(void) int cpu; unsigned long flags; + /* notify the hw-branch tracer so it may disable tracing and + add the last trace to the trace buffer - + the earlier this happens, the more useful the trace. */ + trace_hw_branch_oops(); + oops_enter(); /* racy, but better than risking deadlock. */ diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 76f7141e0f91..61df77532120 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -18,6 +18,7 @@ #include <linux/init.h> #include <linux/list.h> +#include <asm/cacheflush.h> #include <asm/ftrace.h> #include <linux/ftrace.h> #include <asm/nops.h> @@ -26,6 +27,18 @@ #ifdef CONFIG_DYNAMIC_FTRACE +int ftrace_arch_code_modify_prepare(void) +{ + set_kernel_text_rw(); + return 0; +} + +int ftrace_arch_code_modify_post_process(void) +{ + set_kernel_text_ro(); + return 0; +} + union ftrace_code_union { char code[MCOUNT_INSN_SIZE]; struct { @@ -66,11 +79,11 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) * * 1) Put the instruction pointer into the IP buffer * and the new code into the "code" buffer. - * 2) Set a flag that says we are modifying code - * 3) Wait for any running NMIs to finish. - * 4) Write the code - * 5) clear the flag. - * 6) Wait for any running NMIs to finish. + * 2) Wait for any running NMIs to finish and set a flag that says + * we are modifying code, it is done in an atomic operation. + * 3) Write the code + * 4) clear the flag. + * 5) Wait for any running NMIs to finish. * * If an NMI is executed, the first thing it does is to call * "ftrace_nmi_enter". This will check if the flag is set to write @@ -82,9 +95,9 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) * are the same as what exists. */ -static atomic_t in_nmi = ATOMIC_INIT(0); +#define MOD_CODE_WRITE_FLAG (1 << 31) /* set when NMI should do the write */ +static atomic_t nmi_running = ATOMIC_INIT(0); static int mod_code_status; /* holds return value of text write */ -static int mod_code_write; /* set when NMI should do the write */ static void *mod_code_ip; /* holds the IP to write to */ static void *mod_code_newcode; /* holds the text to write to the IP */ @@ -101,6 +114,20 @@ int ftrace_arch_read_dyn_info(char *buf, int size) return r; } +static void clear_mod_flag(void) +{ + int old = atomic_read(&nmi_running); + + for (;;) { + int new = old & ~MOD_CODE_WRITE_FLAG; + + if (old == new) + break; + + old = atomic_cmpxchg(&nmi_running, old, new); + } +} + static void ftrace_mod_code(void) { /* @@ -111,37 +138,52 @@ static void ftrace_mod_code(void) */ mod_code_status = probe_kernel_write(mod_code_ip, mod_code_newcode, MCOUNT_INSN_SIZE); + + /* if we fail, then kill any new writers */ + if (mod_code_status) + clear_mod_flag(); } void ftrace_nmi_enter(void) { - atomic_inc(&in_nmi); - /* Must have in_nmi seen before reading write flag */ - smp_mb(); - if (mod_code_write) { + if (atomic_inc_return(&nmi_running) & MOD_CODE_WRITE_FLAG) { + smp_rmb(); ftrace_mod_code(); atomic_inc(&nmi_update_count); } + /* Must have previous changes seen before executions */ + smp_mb(); } void ftrace_nmi_exit(void) { - /* Finish all executions before clearing in_nmi */ - smp_wmb(); - atomic_dec(&in_nmi); + /* Finish all executions before clearing nmi_running */ + smp_mb(); + atomic_dec(&nmi_running); +} + +static void wait_for_nmi_and_set_mod_flag(void) +{ + if (!atomic_cmpxchg(&nmi_running, 0, MOD_CODE_WRITE_FLAG)) + return; + + do { + cpu_relax(); + } while (atomic_cmpxchg(&nmi_running, 0, MOD_CODE_WRITE_FLAG)); + + nmi_wait_count++; } static void wait_for_nmi(void) { - int waited = 0; + if (!atomic_read(&nmi_running)) + return; - while (atomic_read(&in_nmi)) { - waited = 1; + do { cpu_relax(); - } + } while (atomic_read(&nmi_running)); - if (waited) - nmi_wait_count++; + nmi_wait_count++; } static int @@ -151,14 +193,9 @@ do_ftrace_mod_code(unsigned long ip, void *new_code) mod_code_newcode = new_code; /* The buffers need to be visible before we let NMIs write them */ - smp_wmb(); - - mod_code_write = 1; - - /* Make sure write bit is visible before we wait on NMIs */ smp_mb(); - wait_for_nmi(); + wait_for_nmi_and_set_mod_flag(); /* Make sure all running NMIs have finished before we write the code */ smp_mb(); @@ -166,13 +203,9 @@ do_ftrace_mod_code(unsigned long ip, void *new_code) ftrace_mod_code(); /* Make sure the write happens before clearing the bit */ - smp_wmb(); - - mod_code_write = 0; - - /* make sure NMIs see the cleared bit */ smp_mb(); + clear_mod_flag(); wait_for_nmi(); return mod_code_status; @@ -368,25 +401,6 @@ int ftrace_disable_ftrace_graph_caller(void) return ftrace_mod_jmp(ip, old_offset, new_offset); } -#else /* CONFIG_DYNAMIC_FTRACE */ - -/* - * These functions are picked from those used on - * this page for dynamic ftrace. They have been - * simplified to ignore all traces in NMI context. - */ -static atomic_t in_nmi; - -void ftrace_nmi_enter(void) -{ - atomic_inc(&in_nmi); -} - -void ftrace_nmi_exit(void) -{ - atomic_dec(&in_nmi); -} - #endif /* !CONFIG_DYNAMIC_FTRACE */ /* @@ -396,14 +410,13 @@ void ftrace_nmi_exit(void) void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) { unsigned long old; - unsigned long long calltime; int faulted; struct ftrace_graph_ent trace; unsigned long return_hooker = (unsigned long) &return_to_handler; /* Nmi's are currently unsupported */ - if (unlikely(atomic_read(&in_nmi))) + if (unlikely(in_nmi())) return; if (unlikely(atomic_read(¤t->tracing_graph_pause))) @@ -439,17 +452,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) return; } - if (unlikely(!__kernel_text_address(old))) { - ftrace_graph_stop(); - *parent = old; - WARN_ON(1); - return; - } - - calltime = cpu_clock(raw_smp_processor_id()); - - if (ftrace_push_return_trace(old, calltime, - self_addr, &trace.depth) == -EBUSY) { + if (ftrace_push_return_trace(old, self_addr, &trace.depth) == -EBUSY) { *parent = old; return; } @@ -463,3 +466,66 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) } } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + +#ifdef CONFIG_FTRACE_SYSCALLS + +extern unsigned long __start_syscalls_metadata[]; +extern unsigned long __stop_syscalls_metadata[]; +extern unsigned long *sys_call_table; + +static struct syscall_metadata **syscalls_metadata; + +static struct syscall_metadata *find_syscall_meta(unsigned long *syscall) +{ + struct syscall_metadata *start; + struct syscall_metadata *stop; + char str[KSYM_SYMBOL_LEN]; + + + start = (struct syscall_metadata *)__start_syscalls_metadata; + stop = (struct syscall_metadata *)__stop_syscalls_metadata; + kallsyms_lookup((unsigned long) syscall, NULL, NULL, NULL, str); + + for ( ; start < stop; start++) { + if (start->name && !strcmp(start->name, str)) + return start; + } + return NULL; +} + +struct syscall_metadata *syscall_nr_to_meta(int nr) +{ + if (!syscalls_metadata || nr >= FTRACE_SYSCALL_MAX || nr < 0) + return NULL; + + return syscalls_metadata[nr]; +} + +void arch_init_ftrace_syscalls(void) +{ + int i; + struct syscall_metadata *meta; + unsigned long **psys_syscall_table = &sys_call_table; + static atomic_t refs; + + if (atomic_inc_return(&refs) != 1) + goto end; + + syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) * + FTRACE_SYSCALL_MAX, GFP_KERNEL); + if (!syscalls_metadata) { + WARN_ON(1); + return; + } + + for (i = 0; i < FTRACE_SYSCALL_MAX; i++) { + meta = find_syscall_meta(psys_syscall_table[i]); + syscalls_metadata[i] = meta; + } + return; + + /* Paranoid: avoid overflow */ +end: + atomic_dec(&refs); +} +#endif diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 55b94614e348..7b5169d2b000 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -638,13 +638,13 @@ static void __used __kprobes kretprobe_trampoline_holder(void) #else " pushf\n" /* - * Skip cs, ip, orig_ax. + * Skip cs, ip, orig_ax and gs. * trampoline_handler() will plug in these values */ - " subl $12, %esp\n" + " subl $16, %esp\n" " pushl %fs\n" - " pushl %ds\n" " pushl %es\n" + " pushl %ds\n" " pushl %eax\n" " pushl %ebp\n" " pushl %edi\n" @@ -655,10 +655,10 @@ static void __used __kprobes kretprobe_trampoline_holder(void) " movl %esp, %eax\n" " call trampoline_handler\n" /* Move flags to cs */ - " movl 52(%esp), %edx\n" - " movl %edx, 48(%esp)\n" + " movl 56(%esp), %edx\n" + " movl %edx, 52(%esp)\n" /* Replace saved flags with true return address. */ - " movl %eax, 52(%esp)\n" + " movl %eax, 56(%esp)\n" " popl %ebx\n" " popl %ecx\n" " popl %edx\n" @@ -666,8 +666,8 @@ static void __used __kprobes kretprobe_trampoline_holder(void) " popl %edi\n" " popl %ebp\n" " popl %eax\n" - /* Skip ip, orig_ax, es, ds, fs */ - " addl $20, %esp\n" + /* Skip ds, es, fs, gs, orig_ax and ip */ + " addl $24, %esp\n" " popf\n" #endif " ret\n"); @@ -691,6 +691,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs) regs->cs = __KERNEL_CS; #else regs->cs = __KERNEL_CS | get_kernel_rpl(); + regs->gs = 0; #endif regs->ip = trampoline_address; regs->orig_ax = ~0UL; diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index c25fdb382292..453b5795a5c6 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -12,31 +12,30 @@ * * Licensed under the terms of the GNU General Public * License version 2. See file COPYING for details. -*/ - + */ +#include <linux/platform_device.h> #include <linux/capability.h> -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/sched.h> -#include <linux/cpumask.h> -#include <linux/module.h> -#include <linux/slab.h> -#include <linux/vmalloc.h> #include <linux/miscdevice.h> +#include <linux/firmware.h> #include <linux/spinlock.h> -#include <linux/mm.h> -#include <linux/fs.h> +#include <linux/cpumask.h> +#include <linux/pci_ids.h> +#include <linux/uaccess.h> +#include <linux/vmalloc.h> +#include <linux/kernel.h> +#include <linux/module.h> #include <linux/mutex.h> +#include <linux/sched.h> +#include <linux/init.h> +#include <linux/slab.h> #include <linux/cpu.h> -#include <linux/firmware.h> -#include <linux/platform_device.h> #include <linux/pci.h> -#include <linux/pci_ids.h> -#include <linux/uaccess.h> +#include <linux/fs.h> +#include <linux/mm.h> -#include <asm/msr.h> -#include <asm/processor.h> #include <asm/microcode.h> +#include <asm/processor.h> +#include <asm/msr.h> MODULE_DESCRIPTION("AMD Microcode Update Driver"); MODULE_AUTHOR("Peter Oruba"); @@ -72,8 +71,8 @@ struct microcode_header_amd { } __attribute__((packed)); struct microcode_amd { - struct microcode_header_amd hdr; - unsigned int mpb[0]; + struct microcode_header_amd hdr; + unsigned int mpb[0]; }; #define UCODE_MAX_SIZE 2048 @@ -184,8 +183,8 @@ static int get_ucode_data(void *to, const u8 *from, size_t n) return 0; } -static void *get_next_ucode(const u8 *buf, unsigned int size, - unsigned int *mc_size) +static void * +get_next_ucode(const u8 *buf, unsigned int size, unsigned int *mc_size) { unsigned int total_size; u8 section_hdr[UCODE_CONTAINER_SECTION_HDR]; @@ -223,7 +222,6 @@ static void *get_next_ucode(const u8 *buf, unsigned int size, return mc; } - static int install_equiv_cpu_table(const u8 *buf) { u8 *container_hdr[UCODE_CONTAINER_HEADER_SIZE]; @@ -372,4 +370,3 @@ struct microcode_ops * __init init_amd_microcode(void) { return µcode_amd_ops; } - diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c index c9b721ba968c..a0f3851ef310 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -70,67 +70,78 @@ * Fix sigmatch() macro to handle old CPUs with pf == 0. * Thanks to Stuart Swales for pointing out this bug. */ +#include <linux/platform_device.h> #include <linux/capability.h> -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/sched.h> +#include <linux/miscdevice.h> +#include <linux/firmware.h> #include <linux/smp_lock.h> +#include <linux/spinlock.h> #include <linux/cpumask.h> -#include <linux/module.h> -#include <linux/slab.h> +#include <linux/uaccess.h> #include <linux/vmalloc.h> -#include <linux/miscdevice.h> -#include <linux/spinlock.h> -#include <linux/mm.h> -#include <linux/fs.h> +#include <linux/kernel.h> +#include <linux/module.h> #include <linux/mutex.h> +#include <linux/sched.h> +#include <linux/init.h> +#include <linux/slab.h> #include <linux/cpu.h> -#include <linux/firmware.h> -#include <linux/platform_device.h> +#include <linux/fs.h> +#include <linux/mm.h> -#include <asm/msr.h> -#include <asm/uaccess.h> -#include <asm/processor.h> #include <asm/microcode.h> +#include <asm/processor.h> +#include <asm/msr.h> MODULE_DESCRIPTION("Microcode Update Driver"); MODULE_AUTHOR("Tigran Aivazian <tigran@aivazian.fsnet.co.uk>"); MODULE_LICENSE("GPL"); -#define MICROCODE_VERSION "2.00" +#define MICROCODE_VERSION "2.00" -static struct microcode_ops *microcode_ops; +static struct microcode_ops *microcode_ops; /* no concurrent ->write()s are allowed on /dev/cpu/microcode */ static DEFINE_MUTEX(microcode_mutex); -struct ucode_cpu_info ucode_cpu_info[NR_CPUS]; +struct ucode_cpu_info ucode_cpu_info[NR_CPUS]; EXPORT_SYMBOL_GPL(ucode_cpu_info); #ifdef CONFIG_MICROCODE_OLD_INTERFACE +struct update_for_cpu { + const void __user *buf; + size_t size; +}; + +static long update_for_cpu(void *_ufc) +{ + struct update_for_cpu *ufc = _ufc; + int error; + + error = microcode_ops->request_microcode_user(smp_processor_id(), + ufc->buf, ufc->size); + if (error < 0) + return error; + if (!error) + microcode_ops->apply_microcode(smp_processor_id()); + return error; +} + static int do_microcode_update(const void __user *buf, size_t size) { - cpumask_t old; int error = 0; int cpu; - - old = current->cpus_allowed; + struct update_for_cpu ufc = { .buf = buf, .size = size }; for_each_online_cpu(cpu) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu; if (!uci->valid) continue; - - set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)); - error = microcode_ops->request_microcode_user(cpu, buf, size); + error = work_on_cpu(cpu, update_for_cpu, &ufc); if (error < 0) - goto out; - if (!error) - microcode_ops->apply_microcode(cpu); + break; } -out: - set_cpus_allowed_ptr(current, &old); return error; } @@ -198,18 +209,33 @@ static void microcode_dev_exit(void) MODULE_ALIAS_MISCDEV(MICROCODE_MINOR); #else -#define microcode_dev_init() 0 -#define microcode_dev_exit() do { } while (0) +#define microcode_dev_init() 0 +#define microcode_dev_exit() do { } while (0) #endif /* fake device for request_firmware */ -static struct platform_device *microcode_pdev; +static struct platform_device *microcode_pdev; + +static long reload_for_cpu(void *unused) +{ + struct ucode_cpu_info *uci = ucode_cpu_info + smp_processor_id(); + int err = 0; + + mutex_lock(µcode_mutex); + if (uci->valid) { + err = microcode_ops->request_microcode_fw(smp_processor_id(), + µcode_pdev->dev); + if (!err) + microcode_ops->apply_microcode(smp_processor_id()); + } + mutex_unlock(µcode_mutex); + return err; +} static ssize_t reload_store(struct sys_device *dev, struct sysdev_attribute *attr, const char *buf, size_t sz) { - struct ucode_cpu_info *uci = ucode_cpu_info + dev->id; char *end; unsigned long val = simple_strtoul(buf, &end, 0); int err = 0; @@ -218,21 +244,9 @@ static ssize_t reload_store(struct sys_device *dev, if (end == buf) return -EINVAL; if (val == 1) { - cpumask_t old = current->cpus_allowed; - get_online_cpus(); - if (cpu_online(cpu)) { - set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)); - mutex_lock(µcode_mutex); - if (uci->valid) { - err = microcode_ops->request_microcode_fw(cpu, - µcode_pdev->dev); - if (!err) - microcode_ops->apply_microcode(cpu); - } - mutex_unlock(µcode_mutex); - set_cpus_allowed_ptr(current, &old); - } + if (cpu_online(cpu)) + err = work_on_cpu(cpu, reload_for_cpu, NULL); put_online_cpus(); } if (err) @@ -268,8 +282,8 @@ static struct attribute *mc_default_attrs[] = { }; static struct attribute_group mc_attr_group = { - .attrs = mc_default_attrs, - .name = "microcode", + .attrs = mc_default_attrs, + .name = "microcode", }; static void __microcode_fini_cpu(int cpu) @@ -328,9 +342,9 @@ static int microcode_resume_cpu(int cpu) return 0; } -static void microcode_update_cpu(int cpu) +static long microcode_update_cpu(void *unused) { - struct ucode_cpu_info *uci = ucode_cpu_info + cpu; + struct ucode_cpu_info *uci = ucode_cpu_info + smp_processor_id(); int err = 0; /* @@ -338,30 +352,27 @@ static void microcode_update_cpu(int cpu) * otherwise just request a firmware: */ if (uci->valid) { - err = microcode_resume_cpu(cpu); - } else { - collect_cpu_info(cpu); + err = microcode_resume_cpu(smp_processor_id()); + } else { + collect_cpu_info(smp_processor_id()); if (uci->valid && system_state == SYSTEM_RUNNING) - err = microcode_ops->request_microcode_fw(cpu, + err = microcode_ops->request_microcode_fw( + smp_processor_id(), µcode_pdev->dev); } if (!err) - microcode_ops->apply_microcode(cpu); + microcode_ops->apply_microcode(smp_processor_id()); + return err; } -static void microcode_init_cpu(int cpu) +static int microcode_init_cpu(int cpu) { - cpumask_t old = current->cpus_allowed; - - set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)); - /* We should bind the task to the CPU */ - BUG_ON(raw_smp_processor_id() != cpu); - + int err; mutex_lock(µcode_mutex); - microcode_update_cpu(cpu); + err = work_on_cpu(cpu, microcode_update_cpu, NULL); mutex_unlock(µcode_mutex); - set_cpus_allowed_ptr(current, &old); + return err; } static int mc_sysdev_add(struct sys_device *sys_dev) @@ -379,8 +390,11 @@ static int mc_sysdev_add(struct sys_device *sys_dev) if (err) return err; - microcode_init_cpu(cpu); - return 0; + err = microcode_init_cpu(cpu); + if (err) + sysfs_remove_group(&sys_dev->kobj, &mc_attr_group); + + return err; } static int mc_sysdev_remove(struct sys_device *sys_dev) @@ -404,14 +418,14 @@ static int mc_sysdev_resume(struct sys_device *dev) return 0; /* only CPU 0 will apply ucode here */ - microcode_update_cpu(0); + microcode_update_cpu(NULL); return 0; } static struct sysdev_driver mc_sysdev_driver = { - .add = mc_sysdev_add, - .remove = mc_sysdev_remove, - .resume = mc_sysdev_resume, + .add = mc_sysdev_add, + .remove = mc_sysdev_remove, + .resume = mc_sysdev_resume, }; static __cpuinit int @@ -424,7 +438,9 @@ mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu) switch (action) { case CPU_ONLINE: case CPU_ONLINE_FROZEN: - microcode_init_cpu(cpu); + if (microcode_init_cpu(cpu)) + printk(KERN_ERR "microcode: failed to init CPU%d\n", + cpu); case CPU_DOWN_FAILED: case CPU_DOWN_FAILED_FROZEN: pr_debug("microcode: CPU%d added\n", cpu); @@ -448,7 +464,7 @@ mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu) } static struct notifier_block __refdata mc_cpu_notifier = { - .notifier_call = mc_cpu_callback, + .notifier_call = mc_cpu_callback, }; static int __init microcode_init(void) diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c index 5e9f4fc51385..149b9ec7c1ab 100644 --- a/arch/x86/kernel/microcode_intel.c +++ b/arch/x86/kernel/microcode_intel.c @@ -70,28 +70,28 @@ * Fix sigmatch() macro to handle old CPUs with pf == 0. * Thanks to Stuart Swales for pointing out this bug. */ +#include <linux/platform_device.h> #include <linux/capability.h> -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/sched.h> +#include <linux/miscdevice.h> +#include <linux/firmware.h> #include <linux/smp_lock.h> +#include <linux/spinlock.h> #include <linux/cpumask.h> -#include <linux/module.h> -#include <linux/slab.h> +#include <linux/uaccess.h> #include <linux/vmalloc.h> -#include <linux/miscdevice.h> -#include <linux/spinlock.h> -#include <linux/mm.h> -#include <linux/fs.h> +#include <linux/kernel.h> +#include <linux/module.h> #include <linux/mutex.h> +#include <linux/sched.h> +#include <linux/init.h> +#include <linux/slab.h> #include <linux/cpu.h> -#include <linux/firmware.h> -#include <linux/platform_device.h> -#include <linux/uaccess.h> +#include <linux/fs.h> +#include <linux/mm.h> -#include <asm/msr.h> -#include <asm/processor.h> #include <asm/microcode.h> +#include <asm/processor.h> +#include <asm/msr.h> MODULE_DESCRIPTION("Microcode Update Driver"); MODULE_AUTHOR("Tigran Aivazian <tigran@aivazian.fsnet.co.uk>"); @@ -129,12 +129,13 @@ struct extended_sigtable { struct extended_signature sigs[0]; }; -#define DEFAULT_UCODE_DATASIZE (2000) +#define DEFAULT_UCODE_DATASIZE (2000) #define MC_HEADER_SIZE (sizeof(struct microcode_header_intel)) #define DEFAULT_UCODE_TOTALSIZE (DEFAULT_UCODE_DATASIZE + MC_HEADER_SIZE) #define EXT_HEADER_SIZE (sizeof(struct extended_sigtable)) #define EXT_SIGNATURE_SIZE (sizeof(struct extended_signature)) #define DWSIZE (sizeof(u32)) + #define get_totalsize(mc) \ (((struct microcode_intel *)mc)->hdr.totalsize ? \ ((struct microcode_intel *)mc)->hdr.totalsize : \ @@ -197,30 +198,31 @@ static inline int update_match_cpu(struct cpu_signature *csig, int sig, int pf) } static inline int -update_match_revision(struct microcode_header_intel *mc_header, int rev) +update_match_revision(struct microcode_header_intel *mc_header, int rev) { return (mc_header->rev <= rev) ? 0 : 1; } static int microcode_sanity_check(void *mc) { + unsigned long total_size, data_size, ext_table_size; struct microcode_header_intel *mc_header = mc; struct extended_sigtable *ext_header = NULL; - struct extended_signature *ext_sig; - unsigned long total_size, data_size, ext_table_size; int sum, orig_sum, ext_sigcount = 0, i; + struct extended_signature *ext_sig; total_size = get_totalsize(mc_header); data_size = get_datasize(mc_header); + if (data_size + MC_HEADER_SIZE > total_size) { printk(KERN_ERR "microcode: error! " - "Bad data size in microcode data file\n"); + "Bad data size in microcode data file\n"); return -EINVAL; } if (mc_header->ldrver != 1 || mc_header->hdrver != 1) { printk(KERN_ERR "microcode: error! " - "Unknown microcode update format\n"); + "Unknown microcode update format\n"); return -EINVAL; } ext_table_size = total_size - (MC_HEADER_SIZE + data_size); @@ -318,11 +320,15 @@ get_matching_microcode(struct cpu_signature *cpu_sig, void *mc, int rev) static void apply_microcode(int cpu) { + struct microcode_intel *mc_intel; + struct ucode_cpu_info *uci; unsigned long flags; unsigned int val[2]; - int cpu_num = raw_smp_processor_id(); - struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - struct microcode_intel *mc_intel = uci->mc; + int cpu_num; + + cpu_num = raw_smp_processor_id(); + uci = ucode_cpu_info + cpu; + mc_intel = uci->mc; /* We should bind the task to the CPU */ BUG_ON(cpu_num != cpu); @@ -348,15 +354,17 @@ static void apply_microcode(int cpu) spin_unlock_irqrestore(µcode_update_lock, flags); if (val[1] != mc_intel->hdr.rev) { printk(KERN_ERR "microcode: CPU%d update from revision " - "0x%x to 0x%x failed\n", cpu_num, uci->cpu_sig.rev, val[1]); + "0x%x to 0x%x failed\n", + cpu_num, uci->cpu_sig.rev, val[1]); return; } printk(KERN_INFO "microcode: CPU%d updated from revision " - "0x%x to 0x%x, date = %04x-%02x-%02x \n", + "0x%x to 0x%x, date = %04x-%02x-%02x \n", cpu_num, uci->cpu_sig.rev, val[1], mc_intel->hdr.date & 0xffff, mc_intel->hdr.date >> 24, (mc_intel->hdr.date >> 16) & 0xff); + uci->cpu_sig.rev = val[1]; } @@ -404,18 +412,23 @@ static int generic_load_microcode(int cpu, void *data, size_t size, leftover -= mc_size; } - if (new_mc) { - if (!leftover) { - if (uci->mc) - vfree(uci->mc); - uci->mc = (struct microcode_intel *)new_mc; - pr_debug("microcode: CPU%d found a matching microcode update with" - " version 0x%x (current=0x%x)\n", - cpu, new_rev, uci->cpu_sig.rev); - } else - vfree(new_mc); + if (!new_mc) + goto out; + + if (leftover) { + vfree(new_mc); + goto out; } + if (uci->mc) + vfree(uci->mc); + uci->mc = (struct microcode_intel *)new_mc; + + pr_debug("microcode: CPU%d found a matching microcode update with" + " version 0x%x (current=0x%x)\n", + cpu, new_rev, uci->cpu_sig.rev); + + out: return (int)leftover; } diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 156f87582c6c..ca989158e847 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -8,7 +8,7 @@ #include <linux/module.h> #include <linux/pm.h> #include <linux/clockchips.h> -#include <linux/ftrace.h> +#include <trace/power.h> #include <asm/system.h> #include <asm/apic.h> #include <asm/idle.h> @@ -22,6 +22,9 @@ EXPORT_SYMBOL(idle_nomwait); struct kmem_cache *task_xstate_cachep; +DEFINE_TRACE(power_start); +DEFINE_TRACE(power_end); + int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { *dst = *src; @@ -325,7 +328,7 @@ void stop_this_cpu(void *dummy) /* * Remove this CPU: */ - cpu_clear(smp_processor_id(), cpu_online_map); + set_cpu_online(smp_processor_id(), false); disable_local_APIC(); for (;;) { @@ -475,12 +478,13 @@ static int __cpuinit check_c1e_idle(const struct cpuinfo_x86 *c) return 1; } -static cpumask_t c1e_mask = CPU_MASK_NONE; +static cpumask_var_t c1e_mask; static int c1e_detected; void c1e_remove_cpu(int cpu) { - cpu_clear(cpu, c1e_mask); + if (c1e_mask != NULL) + cpumask_clear_cpu(cpu, c1e_mask); } /* @@ -509,8 +513,8 @@ static void c1e_idle(void) if (c1e_detected) { int cpu = smp_processor_id(); - if (!cpu_isset(cpu, c1e_mask)) { - cpu_set(cpu, c1e_mask); + if (!cpumask_test_cpu(cpu, c1e_mask)) { + cpumask_set_cpu(cpu, c1e_mask); /* * Force broadcast so ACPI can not interfere. Needs * to run with interrupts enabled as it uses @@ -562,6 +566,15 @@ void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c) pm_idle = default_idle; } +void __init init_c1e_mask(void) +{ + /* If we're using c1e_idle, we need to allocate c1e_mask. */ + if (pm_idle == c1e_idle) { + alloc_cpumask_var(&c1e_mask, GFP_KERNEL); + cpumask_clear(c1e_mask); + } +} + static int __init idle_setup(char *str) { if (!str) diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index b7cc21bc6ae0..fe9345c967de 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -21,6 +21,7 @@ #include <linux/audit.h> #include <linux/seccomp.h> #include <linux/signal.h> +#include <linux/ftrace.h> #include <asm/uaccess.h> #include <asm/pgtable.h> @@ -1415,6 +1416,9 @@ asmregparm long syscall_trace_enter(struct pt_regs *regs) tracehook_report_syscall_entry(regs)) ret = -1L; + if (unlikely(test_thread_flag(TIF_SYSCALL_FTRACE))) + ftrace_syscall_enter(regs); + if (unlikely(current->audit_context)) { if (IS_IA32) audit_syscall_entry(AUDIT_ARCH_I386, @@ -1438,6 +1442,9 @@ asmregparm void syscall_trace_leave(struct pt_regs *regs) if (unlikely(current->audit_context)) audit_syscall_exit(AUDITSC_RESULT(regs->ax), regs->ax); + if (unlikely(test_thread_flag(TIF_SYSCALL_FTRACE))) + ftrace_syscall_exit(regs); + if (test_thread_flag(TIF_SYSCALL_TRACE)) tracehook_report_syscall_exit(regs, 0); diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 400331b50a53..3a97a4cf1872 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -153,7 +153,6 @@ static struct page * __init pcpur_get_page(unsigned int cpu, int pageno) static ssize_t __init setup_pcpu_remap(size_t static_size) { static struct vm_struct vm; - pg_data_t *last; size_t ptrs_size, dyn_size; unsigned int cpu; ssize_t ret; @@ -162,22 +161,9 @@ static ssize_t __init setup_pcpu_remap(size_t static_size) * If large page isn't supported, there's no benefit in doing * this. Also, on non-NUMA, embedding is better. */ - if (!cpu_has_pse || pcpu_need_numa()) + if (!cpu_has_pse || !pcpu_need_numa()) return -EINVAL; - last = NULL; - for_each_possible_cpu(cpu) { - int node = early_cpu_to_node(cpu); - - if (node_online(node) && NODE_DATA(node) && - last && last != NODE_DATA(node)) - goto proceed; - - last = NODE_DATA(node); - } - return -EINVAL; - -proceed: /* * Currently supports only single page. Supporting multiple * pages won't be too difficult if it ever becomes necessary. diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index dfcc74ab0ab6..14425166b8e3 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -221,7 +221,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, if (!onsigstack) { /* This is the X/Open sanctioned signal stack switching. */ if (ka->sa.sa_flags & SA_ONSTACK) { - if (sas_ss_flags(sp) == 0) + if (current->sas_ss_size) sp = current->sas_ss_sp + current->sas_ss_size; } else { #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index ef7d10170c30..58d24ef917d8 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -101,11 +101,11 @@ EXPORT_SYMBOL(smp_num_siblings); DEFINE_PER_CPU(u16, cpu_llc_id) = BAD_APICID; /* representing HT siblings of each logical CPU */ -DEFINE_PER_CPU(cpumask_t, cpu_sibling_map); +DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map); EXPORT_PER_CPU_SYMBOL(cpu_sibling_map); /* representing HT and core siblings of each logical CPU */ -DEFINE_PER_CPU(cpumask_t, cpu_core_map); +DEFINE_PER_CPU(cpumask_var_t, cpu_core_map); EXPORT_PER_CPU_SYMBOL(cpu_core_map); /* Per CPU bogomips and other parameters */ @@ -115,11 +115,6 @@ EXPORT_PER_CPU_SYMBOL(cpu_info); atomic_t init_deasserted; #if defined(CONFIG_NUMA) && defined(CONFIG_X86_32) - -/* which logical CPUs are on which nodes */ -cpumask_t node_to_cpumask_map[MAX_NUMNODES] __read_mostly = - { [0 ... MAX_NUMNODES-1] = CPU_MASK_NONE }; -EXPORT_SYMBOL(node_to_cpumask_map); /* which node each logical CPU is on */ int cpu_to_node_map[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = 0 }; EXPORT_SYMBOL(cpu_to_node_map); @@ -128,7 +123,7 @@ EXPORT_SYMBOL(cpu_to_node_map); static void map_cpu_to_node(int cpu, int node) { printk(KERN_INFO "Mapping cpu %d to node %d\n", cpu, node); - cpumask_set_cpu(cpu, &node_to_cpumask_map[node]); + cpumask_set_cpu(cpu, node_to_cpumask_map[node]); cpu_to_node_map[cpu] = node; } @@ -139,7 +134,7 @@ static void unmap_cpu_to_node(int cpu) printk(KERN_INFO "Unmapping cpu %d from all nodes\n", cpu); for (node = 0; node < MAX_NUMNODES; node++) - cpumask_clear_cpu(cpu, &node_to_cpumask_map[node]); + cpumask_clear_cpu(cpu, node_to_cpumask_map[node]); cpu_to_node_map[cpu] = 0; } #else /* !(CONFIG_NUMA && CONFIG_X86_32) */ @@ -301,7 +296,7 @@ notrace static void __cpuinit start_secondary(void *unused) __flush_tlb_all(); #endif - /* This must be done before setting cpu_online_map */ + /* This must be done before setting cpu_online_mask */ set_cpu_sibling_map(raw_smp_processor_id()); wmb(); @@ -334,6 +329,23 @@ notrace static void __cpuinit start_secondary(void *unused) cpu_idle(); } +#ifdef CONFIG_CPUMASK_OFFSTACK +/* In this case, llc_shared_map is a pointer to a cpumask. */ +static inline void copy_cpuinfo_x86(struct cpuinfo_x86 *dst, + const struct cpuinfo_x86 *src) +{ + struct cpumask *llc = dst->llc_shared_map; + *dst = *src; + dst->llc_shared_map = llc; +} +#else +static inline void copy_cpuinfo_x86(struct cpuinfo_x86 *dst, + const struct cpuinfo_x86 *src) +{ + *dst = *src; +} +#endif /* CONFIG_CPUMASK_OFFSTACK */ + /* * The bootstrap kernel entry code has set these up. Save them for * a given CPU @@ -343,7 +355,7 @@ void __cpuinit smp_store_cpu_info(int id) { struct cpuinfo_x86 *c = &cpu_data(id); - *c = boot_cpu_data; + copy_cpuinfo_x86(c, &boot_cpu_data); c->cpu_index = id; if (id != 0) identify_secondary_cpu(c); @@ -367,15 +379,15 @@ void __cpuinit set_cpu_sibling_map(int cpu) cpumask_set_cpu(cpu, cpu_sibling_mask(i)); cpumask_set_cpu(i, cpu_core_mask(cpu)); cpumask_set_cpu(cpu, cpu_core_mask(i)); - cpumask_set_cpu(i, &c->llc_shared_map); - cpumask_set_cpu(cpu, &o->llc_shared_map); + cpumask_set_cpu(i, c->llc_shared_map); + cpumask_set_cpu(cpu, o->llc_shared_map); } } } else { cpumask_set_cpu(cpu, cpu_sibling_mask(cpu)); } - cpumask_set_cpu(cpu, &c->llc_shared_map); + cpumask_set_cpu(cpu, c->llc_shared_map); if (current_cpu_data.x86_max_cores == 1) { cpumask_copy(cpu_core_mask(cpu), cpu_sibling_mask(cpu)); @@ -386,8 +398,8 @@ void __cpuinit set_cpu_sibling_map(int cpu) for_each_cpu(i, cpu_sibling_setup_mask) { if (per_cpu(cpu_llc_id, cpu) != BAD_APICID && per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) { - cpumask_set_cpu(i, &c->llc_shared_map); - cpumask_set_cpu(cpu, &cpu_data(i).llc_shared_map); + cpumask_set_cpu(i, c->llc_shared_map); + cpumask_set_cpu(cpu, cpu_data(i).llc_shared_map); } if (c->phys_proc_id == cpu_data(i).phys_proc_id) { cpumask_set_cpu(i, cpu_core_mask(cpu)); @@ -425,12 +437,7 @@ const struct cpumask *cpu_coregroup_mask(int cpu) if (sched_mc_power_savings || sched_smt_power_savings) return cpu_core_mask(cpu); else - return &c->llc_shared_map; -} - -cpumask_t cpu_coregroup_map(int cpu) -{ - return *cpu_coregroup_mask(cpu); + return c->llc_shared_map; } static void impress_friends(void) @@ -897,9 +904,8 @@ int __cpuinit native_cpu_up(unsigned int cpu) */ static __init void disable_smp(void) { - /* use the read/write pointers to the present and possible maps */ - cpumask_copy(&cpu_present_map, cpumask_of(0)); - cpumask_copy(&cpu_possible_map, cpumask_of(0)); + init_cpu_present(cpumask_of(0)); + init_cpu_possible(cpumask_of(0)); smpboot_clear_io_apic_irqs(); if (smp_found_config) @@ -1031,6 +1037,8 @@ static void __init smp_cpu_index_default(void) */ void __init native_smp_prepare_cpus(unsigned int max_cpus) { + unsigned int i; + preempt_disable(); smp_cpu_index_default(); current_cpu_data = boot_cpu_data; @@ -1044,6 +1052,14 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) boot_cpu_logical_apicid = logical_smp_processor_id(); #endif current_thread_info()->cpu = 0; /* needed? */ + for_each_possible_cpu(i) { + alloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL); + alloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL); + alloc_cpumask_var(&cpu_data(i).llc_shared_map, GFP_KERNEL); + cpumask_clear(per_cpu(cpu_core_map, i)); + cpumask_clear(per_cpu(cpu_sibling_map, i)); + cpumask_clear(cpu_data(i).llc_shared_map); + } set_cpu_sibling_map(0); enable_IR_x2apic(); @@ -1132,11 +1148,11 @@ early_param("possible_cpus", _setup_possible_cpus); /* - * cpu_possible_map should be static, it cannot change as cpu's + * cpu_possible_mask should be static, it cannot change as cpu's * are onlined, or offlined. The reason is per-cpu data-structures * are allocated by some modules at init time, and dont expect to * do this dynamically on cpu arrival/departure. - * cpu_present_map on the other hand can change dynamically. + * cpu_present_mask on the other hand can change dynamically. * In case when cpu_hotplug is not compiled, then we resort to current * behaviour, which is cpu_possible == cpu_present. * - Ashok Raj diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c index 79c073247284..deb5ebb32c3b 100644 --- a/arch/x86/kernel/tlb_uv.c +++ b/arch/x86/kernel/tlb_uv.c @@ -275,6 +275,8 @@ const struct cpumask *uv_flush_send_and_wait(int cpu, int this_blade, return NULL; } +static DEFINE_PER_CPU(cpumask_var_t, uv_flush_tlb_mask); + /** * uv_flush_tlb_others - globally purge translation cache of a virtual * address or all TLB's @@ -304,8 +306,7 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm, unsigned long va, unsigned int cpu) { - static DEFINE_PER_CPU(cpumask_t, flush_tlb_mask); - struct cpumask *flush_mask = &__get_cpu_var(flush_tlb_mask); + struct cpumask *flush_mask = __get_cpu_var(uv_flush_tlb_mask); int i; int bit; int blade; @@ -755,6 +756,10 @@ static int __init uv_bau_init(void) if (!is_uv_system()) return 0; + for_each_possible_cpu(cur_cpu) + alloc_cpumask_var_node(&per_cpu(uv_flush_tlb_mask, cur_cpu), + GFP_KERNEL, cpu_to_node(cur_cpu)); + uv_bau_retry_limit = 1; uv_nshift = uv_hub_info->n_val; uv_mmask = (1UL << uv_hub_info->n_val) - 1; diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 0a303c3ed11f..a58504ea78cc 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -59,7 +59,8 @@ config KVM_AMD config KVM_TRACE bool "KVM trace support" - depends on KVM && MARKERS && SYSFS + depends on KVM && SYSFS + select MARKERS select RELAY select DEBUG_FS default n diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 08537747cb58..fdd30d08ab52 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -14,7 +14,7 @@ obj-$(CONFIG_MMIOTRACE) += mmiotrace.o mmiotrace-y := kmmio.o pf_in.o mmio-mod.o obj-$(CONFIG_MMIOTRACE_TEST) += testmmiotrace.o -obj-$(CONFIG_NUMA) += numa_$(BITS).o +obj-$(CONFIG_NUMA) += numa.o numa_$(BITS).o obj-$(CONFIG_K8_NUMA) += k8topology_64.o obj-$(CONFIG_ACPI_NUMA) += srat_$(BITS).o diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index db81e9a8556b..749559ed80f5 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -1054,17 +1054,47 @@ static noinline int do_test_wp_bit(void) const int rodata_test_data = 0xC3; EXPORT_SYMBOL_GPL(rodata_test_data); +static int kernel_set_to_readonly; + +void set_kernel_text_rw(void) +{ + unsigned long start = PFN_ALIGN(_text); + unsigned long size = PFN_ALIGN(_etext) - start; + + if (!kernel_set_to_readonly) + return; + + pr_debug("Set kernel text: %lx - %lx for read write\n", + start, start+size); + + set_pages_rw(virt_to_page(start), size >> PAGE_SHIFT); +} + +void set_kernel_text_ro(void) +{ + unsigned long start = PFN_ALIGN(_text); + unsigned long size = PFN_ALIGN(_etext) - start; + + if (!kernel_set_to_readonly) + return; + + pr_debug("Set kernel text: %lx - %lx for read only\n", + start, start+size); + + set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); +} + void mark_rodata_ro(void) { unsigned long start = PFN_ALIGN(_text); unsigned long size = PFN_ALIGN(_etext) - start; -#ifndef CONFIG_DYNAMIC_FTRACE - /* Dynamic tracing modifies the kernel text section */ set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); printk(KERN_INFO "Write protecting the kernel text: %luk\n", size >> 10); + kernel_set_to_readonly = 1; + #ifdef CONFIG_CPA_DEBUG printk(KERN_INFO "Testing CPA: Reverting %lx-%lx\n", start, start+size); @@ -1073,7 +1103,6 @@ void mark_rodata_ro(void) printk(KERN_INFO "Testing CPA: write protecting again\n"); set_pages_ro(virt_to_page(start), size>>PAGE_SHIFT); #endif -#endif /* CONFIG_DYNAMIC_FTRACE */ start += size; size = (unsigned long)__end_rodata - start; diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 54efa57d1c03..1753e8020df6 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -734,21 +734,48 @@ void __init mem_init(void) const int rodata_test_data = 0xC3; EXPORT_SYMBOL_GPL(rodata_test_data); +static int kernel_set_to_readonly; + +void set_kernel_text_rw(void) +{ + unsigned long start = PFN_ALIGN(_stext); + unsigned long end = PFN_ALIGN(__start_rodata); + + if (!kernel_set_to_readonly) + return; + + pr_debug("Set kernel text: %lx - %lx for read write\n", + start, end); + + set_memory_rw(start, (end - start) >> PAGE_SHIFT); +} + +void set_kernel_text_ro(void) +{ + unsigned long start = PFN_ALIGN(_stext); + unsigned long end = PFN_ALIGN(__start_rodata); + + if (!kernel_set_to_readonly) + return; + + pr_debug("Set kernel text: %lx - %lx for read only\n", + start, end); + + set_memory_ro(start, (end - start) >> PAGE_SHIFT); +} + void mark_rodata_ro(void) { unsigned long start = PFN_ALIGN(_stext), end = PFN_ALIGN(__end_rodata); unsigned long rodata_start = ((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK; -#ifdef CONFIG_DYNAMIC_FTRACE - /* Dynamic tracing modifies the kernel text section */ - start = rodata_start; -#endif - printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n", (end - start) >> 10); set_memory_ro(start, (end - start) >> PAGE_SHIFT); + kernel_set_to_readonly = 1; + /* * The rodata section (but not the kernel text!) should also be * not-executable. diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c index e331f77348a7..8056545e2d39 100644 --- a/arch/x86/mm/iomap_32.c +++ b/arch/x86/mm/iomap_32.c @@ -23,7 +23,7 @@ int is_io_mapping_possible(resource_size_t base, unsigned long size) { -#ifndef CONFIG_X86_PAE +#if !defined(CONFIG_X86_PAE) && defined(CONFIG_PHYS_ADDR_T_64BIT) /* There is no way to map greater than 1 << 32 address without PAE */ if (base + size > 0x100000000ULL) return 0; diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c index 2c4baa88f2cb..c9342ed8b402 100644 --- a/arch/x86/mm/mmio-mod.c +++ b/arch/x86/mm/mmio-mod.c @@ -378,27 +378,34 @@ static void clear_trace_list(void) } #ifdef CONFIG_HOTPLUG_CPU -static cpumask_t downed_cpus; +static cpumask_var_t downed_cpus; static void enter_uniprocessor(void) { int cpu; int err; + if (downed_cpus == NULL && + !alloc_cpumask_var(&downed_cpus, GFP_KERNEL)) { + pr_notice(NAME "Failed to allocate mask\n"); + goto out; + } + get_online_cpus(); - downed_cpus = cpu_online_map; - cpu_clear(first_cpu(cpu_online_map), downed_cpus); + cpumask_copy(downed_cpus, cpu_online_mask); + cpumask_clear_cpu(cpumask_first(cpu_online_mask), downed_cpus); if (num_online_cpus() > 1) pr_notice(NAME "Disabling non-boot CPUs...\n"); put_online_cpus(); - for_each_cpu_mask(cpu, downed_cpus) { + for_each_cpu(cpu, downed_cpus) { err = cpu_down(cpu); if (!err) pr_info(NAME "CPU%d is down.\n", cpu); else pr_err(NAME "Error taking CPU%d down: %d\n", cpu, err); } +out: if (num_online_cpus() > 1) pr_warning(NAME "multiple CPUs still online, " "may miss events.\n"); @@ -411,10 +418,10 @@ static void __ref leave_uniprocessor(void) int cpu; int err; - if (cpus_weight(downed_cpus) == 0) + if (downed_cpus == NULL || cpumask_weight(downed_cpus) == 0) return; pr_notice(NAME "Re-enabling CPUs...\n"); - for_each_cpu_mask(cpu, downed_cpus) { + for_each_cpu(cpu, downed_cpus) { err = cpu_up(cpu); if (!err) pr_info(NAME "enabled CPU%d.\n", cpu); diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c new file mode 100644 index 000000000000..550df481accd --- /dev/null +++ b/arch/x86/mm/numa.c @@ -0,0 +1,67 @@ +/* Common code for 32 and 64-bit NUMA */ +#include <linux/topology.h> +#include <linux/module.h> +#include <linux/bootmem.h> + +#ifdef CONFIG_DEBUG_PER_CPU_MAPS +# define DBG(x...) printk(KERN_DEBUG x) +#else +# define DBG(x...) +#endif + +/* + * Which logical CPUs are on which nodes + */ +cpumask_var_t node_to_cpumask_map[MAX_NUMNODES]; +EXPORT_SYMBOL(node_to_cpumask_map); + +/* + * Allocate node_to_cpumask_map based on number of available nodes + * Requires node_possible_map to be valid. + * + * Note: node_to_cpumask() is not valid until after this is done. + * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.) + */ +void __init setup_node_to_cpumask_map(void) +{ + unsigned int node, num = 0; + + /* setup nr_node_ids if not done yet */ + if (nr_node_ids == MAX_NUMNODES) { + for_each_node_mask(node, node_possible_map) + num = node; + nr_node_ids = num + 1; + } + + /* allocate the map */ + for (node = 0; node < nr_node_ids; node++) + alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]); + + /* cpumask_of_node() will now work */ + pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids); +} + +#ifdef CONFIG_DEBUG_PER_CPU_MAPS +/* + * Returns a pointer to the bitmask of CPUs on Node 'node'. + */ +const struct cpumask *cpumask_of_node(int node) +{ + if (node >= nr_node_ids) { + printk(KERN_WARNING + "cpumask_of_node(%d): node > nr_node_ids(%d)\n", + node, nr_node_ids); + dump_stack(); + return cpu_none_mask; + } + if (node_to_cpumask_map[node] == NULL) { + printk(KERN_WARNING + "cpumask_of_node(%d): no node_to_cpumask_map!\n", + node); + dump_stack(); + return cpu_online_mask; + } + return node_to_cpumask_map[node]; +} +EXPORT_SYMBOL(cpumask_of_node); +#endif diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index 64c9cf043cdd..d73aaa892371 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -20,12 +20,6 @@ #include <asm/acpi.h> #include <asm/k8.h> -#ifdef CONFIG_DEBUG_PER_CPU_MAPS -# define DBG(x...) printk(KERN_DEBUG x) -#else -# define DBG(x...) -#endif - struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; EXPORT_SYMBOL(node_data); @@ -49,12 +43,6 @@ DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE); EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map); /* - * Which logical CPUs are on which nodes - */ -cpumask_t *node_to_cpumask_map; -EXPORT_SYMBOL(node_to_cpumask_map); - -/* * Given a shift value, try to populate memnodemap[] * Returns : * 1 if OK @@ -661,36 +649,6 @@ void __init init_cpu_to_node(void) #endif -/* - * Allocate node_to_cpumask_map based on number of available nodes - * Requires node_possible_map to be valid. - * - * Note: node_to_cpumask() is not valid until after this is done. - * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.) - */ -void __init setup_node_to_cpumask_map(void) -{ - unsigned int node, num = 0; - cpumask_t *map; - - /* setup nr_node_ids if not done yet */ - if (nr_node_ids == MAX_NUMNODES) { - for_each_node_mask(node, node_possible_map) - num = node; - nr_node_ids = num + 1; - } - - /* allocate the map */ - map = alloc_bootmem_low(nr_node_ids * sizeof(cpumask_t)); - DBG("node_to_cpumask_map at %p for %d nodes\n", map, nr_node_ids); - - pr_debug("Node to cpumask map at %p for %d nodes\n", - map, nr_node_ids); - - /* node_to_cpumask() will now work */ - node_to_cpumask_map = map; -} - void __cpuinit numa_set_node(int cpu, int node) { int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map); @@ -723,12 +681,12 @@ void __cpuinit numa_clear_node(int cpu) void __cpuinit numa_add_cpu(int cpu) { - cpu_set(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]); + cpumask_set_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]); } void __cpuinit numa_remove_cpu(int cpu) { - cpu_clear(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]); + cpumask_clear_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]); } #else /* CONFIG_DEBUG_PER_CPU_MAPS */ @@ -739,20 +697,20 @@ void __cpuinit numa_remove_cpu(int cpu) static void __cpuinit numa_set_cpumask(int cpu, int enable) { int node = early_cpu_to_node(cpu); - cpumask_t *mask; + struct cpumask *mask; char buf[64]; - if (node_to_cpumask_map == NULL) { - printk(KERN_ERR "node_to_cpumask_map NULL\n"); + mask = node_to_cpumask_map[node]; + if (mask == NULL) { + printk(KERN_ERR "node_to_cpumask_map[%i] NULL\n", node); dump_stack(); return; } - mask = &node_to_cpumask_map[node]; if (enable) - cpu_set(cpu, *mask); + cpumask_set_cpu(cpu, mask); else - cpu_clear(cpu, *mask); + cpumask_clear_cpu(cpu, mask); cpulist_scnprintf(buf, sizeof(buf), mask); printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n", @@ -799,59 +757,6 @@ int early_cpu_to_node(int cpu) return per_cpu(x86_cpu_to_node_map, cpu); } - -/* empty cpumask */ -static const cpumask_t cpu_mask_none; - -/* - * Returns a pointer to the bitmask of CPUs on Node 'node'. - */ -const cpumask_t *cpumask_of_node(int node) -{ - if (node_to_cpumask_map == NULL) { - printk(KERN_WARNING - "cpumask_of_node(%d): no node_to_cpumask_map!\n", - node); - dump_stack(); - return (const cpumask_t *)&cpu_online_map; - } - if (node >= nr_node_ids) { - printk(KERN_WARNING - "cpumask_of_node(%d): node > nr_node_ids(%d)\n", - node, nr_node_ids); - dump_stack(); - return &cpu_mask_none; - } - return &node_to_cpumask_map[node]; -} -EXPORT_SYMBOL(cpumask_of_node); - -/* - * Returns a bitmask of CPUs on Node 'node'. - * - * Side note: this function creates the returned cpumask on the stack - * so with a high NR_CPUS count, excessive stack space is used. The - * node_to_cpumask_ptr function should be used whenever possible. - */ -cpumask_t node_to_cpumask(int node) -{ - if (node_to_cpumask_map == NULL) { - printk(KERN_WARNING - "node_to_cpumask(%d): no node_to_cpumask_map!\n", node); - dump_stack(); - return cpu_online_map; - } - if (node >= nr_node_ids) { - printk(KERN_WARNING - "node_to_cpumask(%d): node > nr_node_ids(%d)\n", - node, nr_node_ids); - dump_stack(); - return cpu_mask_none; - } - return node_to_cpumask_map[node]; -} -EXPORT_SYMBOL(node_to_cpumask); - /* * --------- end of debug versions of the numa functions --------- */ diff --git a/arch/x86/oprofile/op_model_p4.c b/arch/x86/oprofile/op_model_p4.c index 4c4a51c90bc2..819b131fd752 100644 --- a/arch/x86/oprofile/op_model_p4.c +++ b/arch/x86/oprofile/op_model_p4.c @@ -380,7 +380,7 @@ static unsigned int get_stagger(void) { #ifdef CONFIG_SMP int cpu = smp_processor_id(); - return (cpu != first_cpu(per_cpu(cpu_sibling_map, cpu))); + return cpu != cpumask_first(__get_cpu_var(cpu_sibling_map)); #endif return 0; } diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index f234a37bd428..f1817f71e009 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -258,24 +258,7 @@ void pcibios_set_master(struct pci_dev *dev) pci_write_config_byte(dev, PCI_LATENCY_TIMER, lat); } -static void pci_unmap_page_range(struct vm_area_struct *vma) -{ - u64 addr = (u64)vma->vm_pgoff << PAGE_SHIFT; - free_memtype(addr, addr + vma->vm_end - vma->vm_start); -} - -static void pci_track_mmap_page_range(struct vm_area_struct *vma) -{ - u64 addr = (u64)vma->vm_pgoff << PAGE_SHIFT; - unsigned long flags = pgprot_val(vma->vm_page_prot) - & _PAGE_CACHE_MASK; - - reserve_memtype(addr, addr + vma->vm_end - vma->vm_start, flags, NULL); -} - static struct vm_operations_struct pci_mmap_ops = { - .open = pci_track_mmap_page_range, - .close = pci_unmap_page_range, .access = generic_access_phys, }; @@ -283,11 +266,6 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, enum pci_mmap_state mmap_state, int write_combine) { unsigned long prot; - u64 addr = vma->vm_pgoff << PAGE_SHIFT; - unsigned long len = vma->vm_end - vma->vm_start; - unsigned long flags; - unsigned long new_flags; - int retval; /* I/O space cannot be accessed via normal processor loads and * stores on this platform. @@ -308,30 +286,6 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, vma->vm_page_prot = __pgprot(prot); - flags = pgprot_val(vma->vm_page_prot) & _PAGE_CACHE_MASK; - retval = reserve_memtype(addr, addr + len, flags, &new_flags); - if (retval) - return retval; - - if (flags != new_flags) { - if (!is_new_memtype_allowed(flags, new_flags)) { - free_memtype(addr, addr+len); - return -EINVAL; - } - flags = new_flags; - vma->vm_page_prot = __pgprot( - (pgprot_val(vma->vm_page_prot) & ~_PAGE_CACHE_MASK) | - flags); - } - - if (((vma->vm_pgoff < max_low_pfn_mapped) || - (vma->vm_pgoff >= (1UL<<(32 - PAGE_SHIFT)) && - vma->vm_pgoff < max_pfn_mapped)) && - ioremap_change_attr((unsigned long)__va(addr), len, flags)) { - free_memtype(addr, addr + len); - return -EINVAL; - } - if (io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, vma->vm_end - vma->vm_start, vma->vm_page_prot)) diff --git a/arch/x86/power/Makefile b/arch/x86/power/Makefile index 9ff4d5b55ad1..58b32db33125 100644 --- a/arch/x86/power/Makefile +++ b/arch/x86/power/Makefile @@ -1,2 +1,7 @@ +# __restore_processor_state() restores %gs after S3 resume and so should not +# itself be stack-protected +nostackp := $(call cc-option, -fno-stack-protector) +CFLAGS_cpu_$(BITS).o := $(nostackp) + obj-$(CONFIG_PM_SLEEP) += cpu_$(BITS).o obj-$(CONFIG_HIBERNATION) += hibernate_$(BITS).o hibernate_asm_$(BITS).o diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 8d470562ffc9..585a6e330837 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -158,7 +158,7 @@ static void __init xen_fill_possible_map(void) rc = HYPERVISOR_vcpu_op(VCPUOP_is_up, i, NULL); if (rc >= 0) { num_processors++; - cpu_set(i, cpu_possible_map); + set_cpu_possible(i, true); } } } @@ -197,7 +197,7 @@ static void __init xen_smp_prepare_cpus(unsigned int max_cpus) while ((num_possible_cpus() > 1) && (num_possible_cpus() > max_cpus)) { for (cpu = nr_cpu_ids - 1; !cpu_possible(cpu); cpu--) continue; - cpu_clear(cpu, cpu_possible_map); + set_cpu_possible(cpu, false); } for_each_possible_cpu (cpu) { @@ -210,7 +210,7 @@ static void __init xen_smp_prepare_cpus(unsigned int max_cpus) if (IS_ERR(idle)) panic("failed fork for CPU %d", cpu); - cpu_set(cpu, cpu_present_map); + set_cpu_present(cpu, true); } } diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index 981200830432..fa6dc4dd3b19 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -4,16 +4,13 @@ mainmenu "Linux/Xtensa Kernel Configuration" config FRAME_POINTER - bool - default n + def_bool n config ZONE_DMA - bool - default y + def_bool y config XTENSA - bool - default y + def_bool y select HAVE_IDE help Xtensa processors are 32-bit RISC machines designed by Tensilica @@ -24,28 +21,25 @@ config XTENSA a home page at <http://xtensa.sourceforge.net/>. config RWSEM_XCHGADD_ALGORITHM - bool - default y + def_bool y config GENERIC_FIND_NEXT_BIT - bool - default y + def_bool y config GENERIC_HWEIGHT - bool - default y + def_bool y config GENERIC_HARDIRQS - bool - default y + def_bool y + +config GENERIC_GPIO + def_bool y config ARCH_HAS_ILOG2_U32 - bool - default n + def_bool n config ARCH_HAS_ILOG2_U64 - bool - default n + def_bool n config NO_IOPORT def_bool y @@ -54,9 +48,18 @@ config HZ int default 100 +config GENERIC_TIME + def_bool y + source "init/Kconfig" source "kernel/Kconfig.freezer" +config MMU + def_bool n + +config VARIANT_IRQ_SWITCH + def_bool n + menu "Processor type and features" choice @@ -65,38 +68,41 @@ choice config XTENSA_VARIANT_FSF bool "fsf - default (not generic) configuration" + select MMU config XTENSA_VARIANT_DC232B bool "dc232b - Diamond 232L Standard Core Rev.B (LE)" + select MMU help - This variant refers to Tensilica's Diamond 232L Standard core Rev.B (LE). -endchoice + This variant refers to Tensilica's Diamond 232L Standard core Rev.B (LE). -config MMU - bool - default y +config XTENSA_VARIANT_S6000 + bool "s6000 - Stretch software configurable processor" + select VARIANT_IRQ_SWITCH + select ARCH_REQUIRE_GPIOLIB +endchoice config XTENSA_UNALIGNED_USER bool "Unaligned memory access in use space" - ---help--- - The Xtensa architecture currently does not handle unaligned - memory accesses in hardware but through an exception handler. - Per default, unaligned memory accesses are disabled in user space. + help + The Xtensa architecture currently does not handle unaligned + memory accesses in hardware but through an exception handler. + Per default, unaligned memory accesses are disabled in user space. - Say Y here to enable unaligned memory access in user space. + Say Y here to enable unaligned memory access in user space. config PREEMPT bool "Preemptible Kernel" - ---help--- - This option reduces the latency of the kernel when reacting to - real-time or interactive events by allowing a low priority process to - be preempted even if it is in kernel mode executing a system call. - Unfortunately the kernel code has some race conditions if both - CONFIG_SMP and CONFIG_PREEMPT are enabled, so this option is - currently disabled if you are building an SMP kernel. + help + This option reduces the latency of the kernel when reacting to + real-time or interactive events by allowing a low priority process to + be preempted even if it is in kernel mode executing a system call. + Unfortunately the kernel code has some race conditions if both + CONFIG_SMP and CONFIG_PREEMPT are enabled, so this option is + currently disabled if you are building an SMP kernel. - Say Y here if you are building a kernel for a desktop, embedded - or real-time system. Say N if you are unsure. + Say Y here if you are building a kernel for a desktop, embedded + or real-time system. Say N if you are unsure. config MATH_EMULATION bool "Math emulation" @@ -105,6 +111,32 @@ config MATH_EMULATION endmenu +config XTENSA_CALIBRATE_CCOUNT + def_bool n + help + On some platforms (XT2000, for example), the CPU clock rate can + vary. The frequency can be determined, however, by measuring + against a well known, fixed frequency, such as an UART oscillator. + +config SERIAL_CONSOLE + def_bool n + +config XTENSA_ISS_NETWORK + def_bool n + +menu "Bus options" + +config PCI + bool "PCI support" + default y + help + Find out whether you have a PCI motherboard. PCI is the name of a + bus system, i.e. the way the CPU talks to the other stuff inside + your box. Other bus systems are ISA, EISA, MicroChannel (MCA) or + VESA. If you have PCI, say Y, otherwise N. + +source "drivers/pci/Kconfig" + menu "Platform options" choice @@ -113,33 +145,35 @@ choice config XTENSA_PLATFORM_ISS bool "ISS" + select XTENSA_CALIBRATE_CCOUNT + select SERIAL_CONSOLE + select XTENSA_ISS_NETWORK help ISS is an acronym for Tensilica's Instruction Set Simulator. config XTENSA_PLATFORM_XT2000 bool "XT2000" + select XTENSA_CALIBRATE_CCOUNT + select PCI help XT2000 is the name of Tensilica's feature-rich emulation platform. This hardware is capable of running a full Linux distribution. -endchoice +config XTENSA_PLATFORM_S6105 + bool "S6105" + select SERIAL_CONSOLE +endchoice -config XTENSA_CALIBRATE_CCOUNT - bool "Auto calibration of the CPU clock rate" - ---help--- - On some platforms (XT2000, for example), the CPU clock rate can - vary. The frequency can be determined, however, by measuring - against a well known, fixed frequency, such as an UART oscillator. config XTENSA_CPU_CLOCK int "CPU clock rate [MHz]" depends on !XTENSA_CALIBRATE_CCOUNT - default "16" + default 16 config GENERIC_CALIBRATE_DELAY bool "Auto calibration of the BogoMIPS value" - ---help--- + help The BogoMIPS value can easily be derived from the CPU frequency. config CMDLINE_BOOL @@ -156,52 +190,27 @@ config CMDLINE time by entering them here. As a minimum, you should specify the memory size and the root device (e.g., mem=64M root=/dev/nfs). -config SERIAL_CONSOLE - bool - depends on XTENSA_PLATFORM_ISS - default y - -config XTENSA_ISS_NETWORK - bool - depends on XTENSA_PLATFORM_ISS - default y - source "mm/Kconfig" endmenu -menu "Bus options" - -config PCI - bool "PCI support" if !XTENSA_PLATFORM_ISS - depends on !XTENSA_PLATFORM_ISS - default y +config HOTPLUG + bool "Support for hot-pluggable devices" help - Find out whether you have a PCI motherboard. PCI is the name of a - bus system, i.e. the way the CPU talks to the other stuff inside - your box. Other bus systems are ISA, EISA, MicroChannel (MCA) or - VESA. If you have PCI, say Y, otherwise N. + Say Y here if you want to plug devices into your computer while + the system is running, and be able to use them quickly. In many + cases, the devices can likewise be unplugged at any time too. -source "drivers/pci/Kconfig" + One well known example of this is PCMCIA- or PC-cards, credit-card + size devices such as network cards, modems or hard drives which are + plugged into slots found on all modern laptop computers. Another + example, used on modern desktops as well as laptops, is USB. -config HOTPLUG - - bool "Support for hot-pluggable devices" - ---help--- - Say Y here if you want to plug devices into your computer while - the system is running, and be able to use them quickly. In many - cases, the devices can likewise be unplugged at any time too. - - One well known example of this is PCMCIA- or PC-cards, credit-card - size devices such as network cards, modems or hard drives which are - plugged into slots found on all modern laptop computers. Another - example, used on modern desktops as well as laptops, is USB. - - Enable HOTPLUG and build a modular kernel. Get agent software - (from <http://linux-hotplug.sourceforge.net/>) and install it. - Then your kernel will automatically call out to a user mode "policy - agent" (/sbin/hotplug) to load modules and set up software needed - to use devices as you hotplug them. + Enable HOTPLUG and build a modular kernel. Get agent software + (from <http://linux-hotplug.sourceforge.net/>) and install it. + Then your kernel will automatically call out to a user mode "policy + agent" (/sbin/hotplug) to load modules and set up software needed + to use devices as you hotplug them. source "drivers/pcmcia/Kconfig" @@ -213,9 +222,8 @@ menu "Executable file formats" # only elf supported config KCORE_ELF - bool + def_bool y depends on PROC_FS - default y help If you enabled support for /proc file system then the file /proc/kcore will contain the kernel core image in ELF format. This @@ -240,7 +248,7 @@ source "fs/Kconfig" menu "Xtensa initrd options" depends on BLK_DEV_INITRD - config EMBEDDED_RAMDISK +config EMBEDDED_RAMDISK bool "Embed root filesystem ramdisk into the kernel" config EMBEDDED_RAMDISK_IMAGE diff --git a/arch/xtensa/Makefile b/arch/xtensa/Makefile index 1da55fe4beff..4caffac3ca2e 100644 --- a/arch/xtensa/Makefile +++ b/arch/xtensa/Makefile @@ -15,6 +15,7 @@ variant-$(CONFIG_XTENSA_VARIANT_FSF) := fsf variant-$(CONFIG_XTENSA_VARIANT_DC232B) := dc232b +variant-$(CONFIG_XTENSA_VARIANT_S6000) := s6000 variant-$(CONFIG_XTENSA_VARIANT_LINUX_CUSTOM) := custom VARIANT = $(variant-y) @@ -24,6 +25,7 @@ export VARIANT platform-$(CONFIG_XTENSA_PLATFORM_XT2000) := xt2000 platform-$(CONFIG_XTENSA_PLATFORM_ISS) := iss +platform-$(CONFIG_XTENSA_PLATFORM_S6105) := s6105 PLATFORM = $(platform-y) export PLATFORM @@ -62,20 +64,23 @@ ifneq ($(VARIANT),) endif endif -# +# Only build variant and/or platform if it includes a Makefile + +buildvar := $(shell test -a $(srctree)/arch/xtensa/variants/$(VARIANT)/Makefile && echo arch/xtensa/variants/$(VARIANT)/) +buildplf := $(shell test -a $(srctree)/arch/xtensa/platforms/$(PLATFORM)/Makefile && echo arch/xtensa/platforms/$(PLATFORM)/) + +# Find libgcc.a LIBGCC := $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name) head-y := arch/xtensa/kernel/head.o core-y += arch/xtensa/kernel/ arch/xtensa/mm/ -ifneq ($(PLATFORM),) -core-y += arch/xtensa/platforms/$(PLATFORM)/ -endif +core-y += $(buildvar) $(buildplf) + libs-y += arch/xtensa/lib/ $(LIBGCC) boot := arch/xtensa/boot - all: zImage bzImage : zImage diff --git a/arch/xtensa/configs/s6105_defconfig b/arch/xtensa/configs/s6105_defconfig new file mode 100644 index 000000000000..6e1deff41590 --- /dev/null +++ b/arch/xtensa/configs/s6105_defconfig @@ -0,0 +1,530 @@ +# +# Automatically generated make config: don't edit +# Linux kernel version: 2.6.29-rc7-s6 +# Tue Mar 10 11:09:26 2009 +# +# CONFIG_FRAME_POINTER is not set +CONFIG_ZONE_DMA=y +CONFIG_XTENSA=y +CONFIG_RWSEM_XCHGADD_ALGORITHM=y +CONFIG_GENERIC_FIND_NEXT_BIT=y +CONFIG_GENERIC_HWEIGHT=y +CONFIG_GENERIC_HARDIRQS=y +CONFIG_GENERIC_GPIO=y +# CONFIG_ARCH_HAS_ILOG2_U32 is not set +# CONFIG_ARCH_HAS_ILOG2_U64 is not set +CONFIG_NO_IOPORT=y +CONFIG_HZ=100 +CONFIG_GENERIC_TIME=y +CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" + +# +# General setup +# +CONFIG_EXPERIMENTAL=y +CONFIG_BROKEN_ON_SMP=y +CONFIG_LOCK_KERNEL=y +CONFIG_INIT_ENV_ARG_LIMIT=32 +CONFIG_LOCALVERSION="" +CONFIG_LOCALVERSION_AUTO=y +CONFIG_SYSVIPC=y +CONFIG_SYSVIPC_SYSCTL=y +# CONFIG_POSIX_MQUEUE is not set +# CONFIG_BSD_PROCESS_ACCT is not set +# CONFIG_TASKSTATS is not set +# CONFIG_AUDIT is not set + +# +# RCU Subsystem +# +# CONFIG_CLASSIC_RCU is not set +# CONFIG_TREE_RCU is not set +CONFIG_PREEMPT_RCU=y +# CONFIG_RCU_TRACE is not set +# CONFIG_TREE_RCU_TRACE is not set +# CONFIG_PREEMPT_RCU_TRACE is not set +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_LOG_BUF_SHIFT=16 +# CONFIG_GROUP_SCHED is not set +# CONFIG_CGROUPS is not set +# CONFIG_SYSFS_DEPRECATED_V2 is not set +# CONFIG_RELAY is not set +# CONFIG_NAMESPACES is not set +CONFIG_BLK_DEV_INITRD=y +CONFIG_INITRAMFS_SOURCE="" +CONFIG_CC_OPTIMIZE_FOR_SIZE=y +CONFIG_SYSCTL=y +CONFIG_EMBEDDED=y +CONFIG_SYSCTL_SYSCALL=y +CONFIG_KALLSYMS=y +# CONFIG_KALLSYMS_ALL is not set +# CONFIG_KALLSYMS_EXTRA_PASS is not set +# CONFIG_HOTPLUG is not set +CONFIG_PRINTK=y +CONFIG_BUG=y +CONFIG_ELF_CORE=y +# CONFIG_COMPAT_BRK is not set +CONFIG_BASE_FULL=y +CONFIG_FUTEX=y +CONFIG_ANON_INODES=y +CONFIG_EPOLL=y +CONFIG_SIGNALFD=y +CONFIG_TIMERFD=y +CONFIG_EVENTFD=y +CONFIG_AIO=y +CONFIG_VM_EVENT_COUNTERS=y +CONFIG_SLAB=y +# CONFIG_SLUB is not set +# CONFIG_SLOB is not set +# CONFIG_PROFILING is not set +# CONFIG_HAVE_GENERIC_DMA_COHERENT is not set +CONFIG_SLABINFO=y +CONFIG_RT_MUTEXES=y +CONFIG_BASE_SMALL=0 +# CONFIG_MODULES is not set +CONFIG_BLOCK=y +# CONFIG_LBD is not set +# CONFIG_BLK_DEV_IO_TRACE is not set +# CONFIG_BLK_DEV_BSG is not set +# CONFIG_BLK_DEV_INTEGRITY is not set + +# +# IO Schedulers +# +CONFIG_IOSCHED_NOOP=y +# CONFIG_IOSCHED_AS is not set +# CONFIG_IOSCHED_DEADLINE is not set +CONFIG_IOSCHED_CFQ=y +# CONFIG_DEFAULT_AS is not set +# CONFIG_DEFAULT_DEADLINE is not set +CONFIG_DEFAULT_CFQ=y +# CONFIG_DEFAULT_NOOP is not set +CONFIG_DEFAULT_IOSCHED="cfq" +# CONFIG_FREEZER is not set +# CONFIG_MMU is not set +CONFIG_VARIANT_IRQ_SWITCH=y + +# +# Processor type and features +# +# CONFIG_XTENSA_VARIANT_FSF is not set +# CONFIG_XTENSA_VARIANT_DC232B is not set +CONFIG_XTENSA_VARIANT_S6000=y +# CONFIG_XTENSA_UNALIGNED_USER is not set +CONFIG_PREEMPT=y +# CONFIG_MATH_EMULATION is not set +# CONFIG_HIGHMEM is not set +# CONFIG_XTENSA_CALIBRATE_CCOUNT is not set +CONFIG_SERIAL_CONSOLE=y +# CONFIG_XTENSA_ISS_NETWORK is not set + +# +# Bus options +# +# CONFIG_PCI is not set +# CONFIG_ARCH_SUPPORTS_MSI is not set + +# +# Platform options +# +# CONFIG_XTENSA_PLATFORM_ISS is not set +# CONFIG_XTENSA_PLATFORM_XT2000 is not set +CONFIG_XTENSA_PLATFORM_S6105=y +CONFIG_XTENSA_CPU_CLOCK=300 +CONFIG_GENERIC_CALIBRATE_DELAY=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyS1,38400 debug bootmem_debug loglevel=7" +CONFIG_SELECT_MEMORY_MODEL=y +CONFIG_FLATMEM_MANUAL=y +# CONFIG_DISCONTIGMEM_MANUAL is not set +# CONFIG_SPARSEMEM_MANUAL is not set +CONFIG_FLATMEM=y +CONFIG_FLAT_NODE_MEM_MAP=y +CONFIG_PAGEFLAGS_EXTENDED=y +CONFIG_SPLIT_PTLOCK_CPUS=4 +# CONFIG_PHYS_ADDR_T_64BIT is not set +CONFIG_ZONE_DMA_FLAG=1 +CONFIG_VIRT_TO_BUS=y + +# +# Executable file formats +# +CONFIG_KCORE_ELF=y +CONFIG_BINFMT_FLAT=y +# CONFIG_BINFMT_ZFLAT is not set +# CONFIG_BINFMT_SHARED_FLAT is not set +# CONFIG_HAVE_AOUT is not set +# CONFIG_BINFMT_MISC is not set +CONFIG_NET=y + +# +# Networking options +# +CONFIG_COMPAT_NET_DEV_OPS=y +CONFIG_PACKET=y +# CONFIG_PACKET_MMAP is not set +CONFIG_UNIX=y +# CONFIG_NET_KEY is not set +CONFIG_INET=y +# CONFIG_IP_MULTICAST is not set +# CONFIG_IP_ADVANCED_ROUTER is not set +CONFIG_IP_FIB_HASH=y +# CONFIG_IP_PNP is not set +# CONFIG_NET_IPIP is not set +# CONFIG_NET_IPGRE is not set +# CONFIG_ARPD is not set +# CONFIG_SYN_COOKIES is not set +# CONFIG_INET_AH is not set +# CONFIG_INET_ESP is not set +# CONFIG_INET_IPCOMP is not set +# CONFIG_INET_XFRM_TUNNEL is not set +# CONFIG_INET_TUNNEL is not set +# CONFIG_INET_XFRM_MODE_TRANSPORT is not set +# CONFIG_INET_XFRM_MODE_TUNNEL is not set +# CONFIG_INET_XFRM_MODE_BEET is not set +# CONFIG_INET_LRO is not set +# CONFIG_INET_DIAG is not set +# CONFIG_TCP_CONG_ADVANCED is not set +CONFIG_TCP_CONG_CUBIC=y +CONFIG_DEFAULT_TCP_CONG="cubic" +# CONFIG_TCP_MD5SIG is not set +# CONFIG_IPV6 is not set +# CONFIG_NETWORK_SECMARK is not set +# CONFIG_NETFILTER is not set +# CONFIG_IP_DCCP is not set +# CONFIG_IP_SCTP is not set +# CONFIG_TIPC is not set +# CONFIG_ATM is not set +# CONFIG_BRIDGE is not set +# CONFIG_NET_DSA is not set +# CONFIG_VLAN_8021Q is not set +# CONFIG_DECNET is not set +# CONFIG_LLC2 is not set +# CONFIG_IPX is not set +# CONFIG_ATALK is not set +# CONFIG_X25 is not set +# CONFIG_LAPB is not set +# CONFIG_ECONET is not set +# CONFIG_WAN_ROUTER is not set +# CONFIG_NET_SCHED is not set +# CONFIG_DCB is not set + +# +# Network testing +# +# CONFIG_NET_PKTGEN is not set +# CONFIG_HAMRADIO is not set +# CONFIG_CAN is not set +# CONFIG_IRDA is not set +# CONFIG_BT is not set +# CONFIG_AF_RXRPC is not set +# CONFIG_PHONET is not set +# CONFIG_WIRELESS is not set +# CONFIG_WIMAX is not set +# CONFIG_RFKILL is not set +# CONFIG_NET_9P is not set + +# +# Device Drivers +# + +# +# Generic Driver Options +# +CONFIG_STANDALONE=y +CONFIG_PREVENT_FIRMWARE_BUILD=y +# CONFIG_DEBUG_DRIVER is not set +# CONFIG_DEBUG_DEVRES is not set +# CONFIG_SYS_HYPERVISOR is not set +# CONFIG_CONNECTOR is not set +# CONFIG_MTD is not set +# CONFIG_PARPORT is not set +CONFIG_BLK_DEV=y +# CONFIG_BLK_DEV_COW_COMMON is not set +# CONFIG_BLK_DEV_LOOP is not set +# CONFIG_BLK_DEV_NBD is not set +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_COUNT=16 +CONFIG_BLK_DEV_RAM_SIZE=4096 +# CONFIG_BLK_DEV_XIP is not set +# CONFIG_CDROM_PKTCDVD is not set +# CONFIG_ATA_OVER_ETH is not set +# CONFIG_BLK_DEV_HD is not set +# CONFIG_MISC_DEVICES is not set +CONFIG_HAVE_IDE=y +# CONFIG_IDE is not set + +# +# SCSI device support +# +# CONFIG_RAID_ATTRS is not set +# CONFIG_SCSI is not set +# CONFIG_SCSI_DMA is not set +# CONFIG_SCSI_NETLINK is not set +# CONFIG_ATA is not set +# CONFIG_MD is not set +# CONFIG_NETDEVICES is not set +# CONFIG_ISDN is not set +# CONFIG_PHONE is not set + +# +# Input device support +# +# CONFIG_INPUT is not set + +# +# Hardware I/O ports +# +# CONFIG_SERIO is not set +# CONFIG_GAMEPORT is not set + +# +# Character devices +# +# CONFIG_VT is not set +# CONFIG_DEVKMEM is not set +# CONFIG_SERIAL_NONSTANDARD is not set + +# +# Serial drivers +# +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250_NR_UARTS=2 +CONFIG_SERIAL_8250_RUNTIME_UARTS=2 +# CONFIG_SERIAL_8250_EXTENDED is not set + +# +# Non-8250 serial port support +# +CONFIG_SERIAL_CORE=y +CONFIG_SERIAL_CORE_CONSOLE=y +CONFIG_UNIX98_PTYS=y +# CONFIG_DEVPTS_MULTIPLE_INSTANCES is not set +# CONFIG_LEGACY_PTYS is not set +# CONFIG_IPMI_HANDLER is not set +# CONFIG_HW_RANDOM is not set +# CONFIG_RTC is not set +# CONFIG_GEN_RTC is not set +# CONFIG_R3964 is not set +# CONFIG_RAW_DRIVER is not set +# CONFIG_TCG_TPM is not set +# CONFIG_I2C is not set +# CONFIG_SPI is not set +CONFIG_ARCH_REQUIRE_GPIOLIB=y +CONFIG_GPIOLIB=y +# CONFIG_DEBUG_GPIO is not set +# CONFIG_GPIO_SYSFS is not set + +# +# Memory mapped GPIO expanders: +# + +# +# I2C GPIO expanders: +# + +# +# PCI GPIO expanders: +# + +# +# SPI GPIO expanders: +# +# CONFIG_W1 is not set +# CONFIG_POWER_SUPPLY is not set +# CONFIG_HWMON is not set +# CONFIG_THERMAL is not set +# CONFIG_THERMAL_HWMON is not set +# CONFIG_WATCHDOG is not set +CONFIG_SSB_POSSIBLE=y + +# +# Sonics Silicon Backplane +# +# CONFIG_SSB is not set + +# +# Multifunction device drivers +# +# CONFIG_MFD_CORE is not set +# CONFIG_MFD_SM501 is not set +# CONFIG_HTC_PASIC3 is not set +# CONFIG_MFD_TMIO is not set +# CONFIG_REGULATOR is not set + +# +# Multimedia devices +# + +# +# Multimedia core support +# +# CONFIG_VIDEO_DEV is not set +# CONFIG_DVB_CORE is not set +# CONFIG_VIDEO_MEDIA is not set + +# +# Multimedia drivers +# +# CONFIG_DAB is not set + +# +# Graphics support +# +# CONFIG_VGASTATE is not set +# CONFIG_VIDEO_OUTPUT_CONTROL is not set +# CONFIG_FB is not set +# CONFIG_BACKLIGHT_LCD_SUPPORT is not set + +# +# Display device support +# +# CONFIG_DISPLAY_SUPPORT is not set +# CONFIG_SOUND is not set +# CONFIG_USB_SUPPORT is not set +# CONFIG_MMC is not set +# CONFIG_MEMSTICK is not set +# CONFIG_NEW_LEDS is not set +# CONFIG_ACCESSIBILITY is not set +# CONFIG_RTC_CLASS is not set +# CONFIG_DMADEVICES is not set +# CONFIG_UIO is not set +# CONFIG_STAGING is not set + +# +# File systems +# +# CONFIG_EXT2_FS is not set +# CONFIG_EXT3_FS is not set +# CONFIG_EXT4_FS is not set +# CONFIG_REISERFS_FS is not set +# CONFIG_JFS_FS is not set +# CONFIG_FS_POSIX_ACL is not set +CONFIG_FILE_LOCKING=y +# CONFIG_XFS_FS is not set +# CONFIG_OCFS2_FS is not set +# CONFIG_BTRFS_FS is not set +# CONFIG_DNOTIFY is not set +# CONFIG_INOTIFY is not set +# CONFIG_QUOTA is not set +# CONFIG_AUTOFS_FS is not set +# CONFIG_AUTOFS4_FS is not set +# CONFIG_FUSE_FS is not set + +# +# CD-ROM/DVD Filesystems +# +# CONFIG_ISO9660_FS is not set +# CONFIG_UDF_FS is not set + +# +# DOS/FAT/NT Filesystems +# +# CONFIG_MSDOS_FS is not set +# CONFIG_VFAT_FS is not set +# CONFIG_NTFS_FS is not set + +# +# Pseudo filesystems +# +CONFIG_PROC_FS=y +CONFIG_PROC_SYSCTL=y +CONFIG_SYSFS=y +# CONFIG_TMPFS is not set +# CONFIG_HUGETLB_PAGE is not set +# CONFIG_CONFIGFS_FS is not set +# CONFIG_MISC_FILESYSTEMS is not set +# CONFIG_NETWORK_FILESYSTEMS is not set + +# +# Partition Types +# +# CONFIG_PARTITION_ADVANCED is not set +CONFIG_MSDOS_PARTITION=y +# CONFIG_NLS is not set +# CONFIG_DLM is not set + +# +# Xtensa initrd options +# +# CONFIG_EMBEDDED_RAMDISK is not set + +# +# Kernel hacking +# +CONFIG_PRINTK_TIME=y +# CONFIG_ENABLE_WARN_DEPRECATED is not set +# CONFIG_ENABLE_MUST_CHECK is not set +CONFIG_FRAME_WARN=1024 +# CONFIG_MAGIC_SYSRQ is not set +# CONFIG_UNUSED_SYMBOLS is not set +# CONFIG_DEBUG_FS is not set +# CONFIG_HEADERS_CHECK is not set +CONFIG_DEBUG_KERNEL=y +CONFIG_DEBUG_SHIRQ=y +CONFIG_DETECT_SOFTLOCKUP=y +# CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC is not set +CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE=0 +# CONFIG_SCHED_DEBUG is not set +# CONFIG_SCHEDSTATS is not set +# CONFIG_TIMER_STATS is not set +# CONFIG_DEBUG_OBJECTS is not set +# CONFIG_DEBUG_SLAB is not set +# CONFIG_DEBUG_RT_MUTEXES is not set +# CONFIG_RT_MUTEX_TESTER is not set +CONFIG_DEBUG_SPINLOCK=y +CONFIG_DEBUG_MUTEXES=y +CONFIG_DEBUG_SPINLOCK_SLEEP=y +# CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set +# CONFIG_DEBUG_KOBJECT is not set +# CONFIG_DEBUG_INFO is not set +# CONFIG_DEBUG_VM is not set +CONFIG_DEBUG_NOMMU_REGIONS=y +# CONFIG_DEBUG_WRITECOUNT is not set +# CONFIG_DEBUG_MEMORY_INIT is not set +# CONFIG_DEBUG_LIST is not set +# CONFIG_DEBUG_SG is not set +# CONFIG_DEBUG_NOTIFIERS is not set +# CONFIG_BOOT_PRINTK_DELAY is not set +# CONFIG_RCU_TORTURE_TEST is not set +# CONFIG_BACKTRACE_SELF_TEST is not set +# CONFIG_DEBUG_BLOCK_EXT_DEVT is not set +# CONFIG_FAULT_INJECTION is not set +# CONFIG_SYSCTL_SYSCALL_CHECK is not set + +# +# Tracers +# +# CONFIG_PREEMPT_TRACER is not set +# CONFIG_SCHED_TRACER is not set +# CONFIG_CONTEXT_SWITCH_TRACER is not set +# CONFIG_BOOT_TRACER is not set +# CONFIG_TRACE_BRANCH_PROFILING is not set +# CONFIG_DYNAMIC_PRINTK_DEBUG is not set +# CONFIG_SAMPLES is not set + +# +# Security options +# +# CONFIG_KEYS is not set +# CONFIG_SECURITY is not set +# CONFIG_SECURITYFS is not set +# CONFIG_SECURITY_FILE_CAPABILITIES is not set +# CONFIG_CRYPTO is not set + +# +# Library routines +# +CONFIG_GENERIC_FIND_LAST_BIT=y +# CONFIG_CRC_CCITT is not set +# CONFIG_CRC16 is not set +# CONFIG_CRC_T10DIF is not set +# CONFIG_CRC_ITU_T is not set +# CONFIG_CRC32 is not set +# CONFIG_CRC7 is not set +# CONFIG_LIBCRC32C is not set +CONFIG_PLIST=y +CONFIG_HAS_IOMEM=y +CONFIG_HAS_DMA=y diff --git a/arch/xtensa/include/asm/cacheflush.h b/arch/xtensa/include/asm/cacheflush.h index 94c4c53a099e..8fc1c0c8de07 100644 --- a/arch/xtensa/include/asm/cacheflush.h +++ b/arch/xtensa/include/asm/cacheflush.h @@ -65,13 +65,17 @@ extern void __flush_invalidate_dcache_range(unsigned long, unsigned long); # define __flush_invalidate_dcache_range(p,s) __invalidate_dcache_range(p,s) #endif -#if (DCACHE_WAY_SIZE > PAGE_SIZE) +#if defined(CONFIG_MMU) && (DCACHE_WAY_SIZE > PAGE_SIZE) extern void __flush_invalidate_dcache_page_alias(unsigned long, unsigned long); +#else +static inline void __flush_invalidate_dcache_page_alias(unsigned long virt, + unsigned long phys) { } #endif -#if (ICACHE_WAY_SIZE > PAGE_SIZE) +#if defined(CONFIG_MMU) && (ICACHE_WAY_SIZE > PAGE_SIZE) extern void __invalidate_icache_page_alias(unsigned long, unsigned long); #else -# define __invalidate_icache_page_alias(v,p) do { } while(0) +static inline void __invalidate_icache_page_alias(unsigned long virt, + unsigned long phys) { } #endif /* diff --git a/arch/xtensa/include/asm/dma.h b/arch/xtensa/include/asm/dma.h index e30f3abf48f0..137ca3945b07 100644 --- a/arch/xtensa/include/asm/dma.h +++ b/arch/xtensa/include/asm/dma.h @@ -44,8 +44,9 @@ * the value desired). */ +#ifndef MAX_DMA_ADDRESS #define MAX_DMA_ADDRESS (PAGE_OFFSET + XCHAL_KIO_SIZE - 1) - +#endif /* Reserve and release a DMA channel */ extern int request_dma(unsigned int dmanr, const char * device_id); diff --git a/arch/xtensa/include/asm/flat.h b/arch/xtensa/include/asm/flat.h new file mode 100644 index 000000000000..94c44abf15e4 --- /dev/null +++ b/arch/xtensa/include/asm/flat.h @@ -0,0 +1,12 @@ +#ifndef __ASM_XTENSA_FLAT_H +#define __ASM_XTENSA_FLAT_H + +#define flat_argvp_envp_on_stack() 0 +#define flat_old_ram_flag(flags) (flags) +#define flat_reloc_valid(reloc, size) ((reloc) <= (size)) +#define flat_get_addr_from_rp(rp, relval, flags, p) get_unaligned(rp) +#define flat_put_addr_at_rp(rp, val, relval ) put_unaligned(val, rp) +#define flat_get_relocate_addr(rel) (rel) +#define flat_set_persistent(relval, p) 0 + +#endif /* __ASM_XTENSA_FLAT_H */ diff --git a/arch/xtensa/include/asm/ftrace.h b/arch/xtensa/include/asm/ftrace.h new file mode 100644 index 000000000000..40a8c178f10d --- /dev/null +++ b/arch/xtensa/include/asm/ftrace.h @@ -0,0 +1 @@ +/* empty */ diff --git a/arch/xtensa/include/asm/gpio.h b/arch/xtensa/include/asm/gpio.h new file mode 100644 index 000000000000..0763b0763960 --- /dev/null +++ b/arch/xtensa/include/asm/gpio.h @@ -0,0 +1,56 @@ +/* + * Generic GPIO API implementation for xtensa. + * + * Stolen from x86, which is derived from the generic GPIO API for powerpc: + * + * Copyright (c) 2007-2008 MontaVista Software, Inc. + * + * Author: Anton Vorontsov <avorontsov@ru.mvista.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. + */ + +#ifndef _ASM_XTENSA_GPIO_H +#define _ASM_XTENSA_GPIO_H + +#include <asm-generic/gpio.h> + +#ifdef CONFIG_GPIOLIB + +/* + * Just call gpiolib. + */ +static inline int gpio_get_value(unsigned int gpio) +{ + return __gpio_get_value(gpio); +} + +static inline void gpio_set_value(unsigned int gpio, int value) +{ + __gpio_set_value(gpio, value); +} + +static inline int gpio_cansleep(unsigned int gpio) +{ + return __gpio_cansleep(gpio); +} + +/* + * Not implemented, yet. + */ +static inline int gpio_to_irq(unsigned int gpio) +{ + return -ENOSYS; +} + +static inline int irq_to_gpio(unsigned int irq) +{ + return -EINVAL; +} + +#endif /* CONFIG_GPIOLIB */ + +#endif /* _ASM_XTENSA_GPIO_H */ diff --git a/arch/xtensa/include/asm/io.h b/arch/xtensa/include/asm/io.h index 07b7299dab20..d04cd3a625fa 100644 --- a/arch/xtensa/include/asm/io.h +++ b/arch/xtensa/include/asm/io.h @@ -69,21 +69,28 @@ static inline void * phys_to_virt(unsigned long address) static inline void *ioremap(unsigned long offset, unsigned long size) { +#ifdef CONFIG_MMU if (offset >= XCHAL_KIO_PADDR && offset < XCHAL_KIO_PADDR + XCHAL_KIO_SIZE) return (void*)(offset-XCHAL_KIO_PADDR+XCHAL_KIO_BYPASS_VADDR); - else BUG(); +#else + return (void *)offset; +#endif } static inline void *ioremap_nocache(unsigned long offset, unsigned long size) { +#ifdef CONFIG_MMU if (offset >= XCHAL_KIO_PADDR && offset < XCHAL_KIO_PADDR + XCHAL_KIO_SIZE) return (void*)(offset-XCHAL_KIO_PADDR+XCHAL_KIO_CACHED_VADDR); else BUG(); +#else + return (void *)offset; +#endif } static inline void iounmap(void *addr) diff --git a/arch/xtensa/include/asm/irq.h b/arch/xtensa/include/asm/irq.h index 1620d1e0e695..dfac82dc52ad 100644 --- a/arch/xtensa/include/asm/irq.h +++ b/arch/xtensa/include/asm/irq.h @@ -14,6 +14,13 @@ #include <platform/hardware.h> #include <variant/core.h> +#ifdef CONFIG_VARIANT_IRQ_SWITCH +#include <variant/irq.h> +#else +static inline void variant_irq_enable(unsigned int irq) { } +static inline void variant_irq_disable(unsigned int irq) { } +#endif + #ifndef PLATFORM_NR_IRQS # define PLATFORM_NR_IRQS 0 #endif diff --git a/arch/xtensa/include/asm/mmu.h b/arch/xtensa/include/asm/mmu.h index 44c5bb04c55c..04890d6e2335 100644 --- a/arch/xtensa/include/asm/mmu.h +++ b/arch/xtensa/include/asm/mmu.h @@ -11,7 +11,12 @@ #ifndef _XTENSA_MMU_H #define _XTENSA_MMU_H +#ifndef CONFIG_MMU +#include <asm/nommu.h> +#else + /* Default "unsigned long" context */ typedef unsigned long mm_context_t; +#endif /* CONFIG_MMU */ #endif /* _XTENSA_MMU_H */ diff --git a/arch/xtensa/include/asm/mmu_context.h b/arch/xtensa/include/asm/mmu_context.h index c0fd8e5b4513..dbd8731a876a 100644 --- a/arch/xtensa/include/asm/mmu_context.h +++ b/arch/xtensa/include/asm/mmu_context.h @@ -13,16 +13,20 @@ #ifndef _XTENSA_MMU_CONTEXT_H #define _XTENSA_MMU_CONTEXT_H +#ifndef CONFIG_MMU +#include <asm/nommu_context.h> +#else + #include <linux/stringify.h> #include <linux/sched.h> +#include <variant/core.h> + #include <asm/pgtable.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> #include <asm-generic/mm_hooks.h> -#define XCHAL_MMU_ASID_BITS 8 - #if (XCHAL_HAVE_TLBS != 1) # error "Linux must have an MMU!" #endif @@ -133,4 +137,5 @@ static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) } +#endif /* CONFIG_MMU */ #endif /* _XTENSA_MMU_CONTEXT_H */ diff --git a/arch/xtensa/include/asm/nommu.h b/arch/xtensa/include/asm/nommu.h new file mode 100644 index 000000000000..dce2c438c5ba --- /dev/null +++ b/arch/xtensa/include/asm/nommu.h @@ -0,0 +1,3 @@ +typedef struct { + unsigned long end_brk; +} mm_context_t; diff --git a/arch/xtensa/include/asm/nommu_context.h b/arch/xtensa/include/asm/nommu_context.h new file mode 100644 index 000000000000..599e7a2e729d --- /dev/null +++ b/arch/xtensa/include/asm/nommu_context.h @@ -0,0 +1,25 @@ +static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) +{ +} + +static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) +{ + return 0; +} + +static inline void destroy_context(struct mm_struct *mm) +{ +} + +static inline void activate_mm(struct mm_struct *prev, struct mm_struct *next) +{ +} + +static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, + struct task_struct *tsk) +{ +} + +static inline void deactivate_mm(struct task_struct *tsk, struct mm_struct *mm) +{ +} diff --git a/arch/xtensa/include/asm/page.h b/arch/xtensa/include/asm/page.h index 11f7dc2dbec7..17e0c5383b10 100644 --- a/arch/xtensa/include/asm/page.h +++ b/arch/xtensa/include/asm/page.h @@ -14,6 +14,7 @@ #include <asm/processor.h> #include <asm/types.h> #include <asm/cache.h> +#include <platform/hardware.h> /* * Fixed TLB translations in the processor. @@ -32,8 +33,14 @@ #define PAGE_SIZE (__XTENSA_UL_CONST(1) << PAGE_SHIFT) #define PAGE_MASK (~(PAGE_SIZE-1)) +#ifdef CONFIG_MMU #define PAGE_OFFSET XCHAL_KSEG_CACHED_VADDR #define MAX_MEM_PFN XCHAL_KSEG_SIZE +#else +#define PAGE_OFFSET 0 +#define MAX_MEM_PFN (PLATFORM_DEFAULT_MEM_START + PLATFORM_DEFAULT_MEM_SIZE) +#endif + #define PGTABLE_START 0x80000000 /* @@ -150,9 +157,11 @@ extern void copy_user_page(void*, void*, unsigned long, struct page*); * addresses. */ +#define ARCH_PFN_OFFSET (PLATFORM_DEFAULT_MEM_START >> PAGE_SHIFT) + #define __pa(x) ((unsigned long) (x) - PAGE_OFFSET) #define __va(x) ((void *)((unsigned long) (x) + PAGE_OFFSET)) -#define pfn_valid(pfn) ((unsigned long)pfn < max_mapnr) +#define pfn_valid(pfn) ((pfn) >= ARCH_PFN_OFFSET && ((pfn) - ARCH_PFN_OFFSET) < max_mapnr) #ifdef CONFIG_DISCONTIGMEM # error CONFIG_DISCONTIGMEM not supported #endif @@ -162,8 +171,9 @@ extern void copy_user_page(void*, void*, unsigned long, struct page*); #define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT) #define page_to_phys(page) (page_to_pfn(page) << PAGE_SHIFT) +#ifdef CONFIG_MMU #define WANT_PAGE_VIRTUAL - +#endif #endif /* __ASSEMBLY__ */ diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h index 8014d96b21f1..a138770c358e 100644 --- a/arch/xtensa/include/asm/pgtable.h +++ b/arch/xtensa/include/asm/pgtable.h @@ -183,7 +183,15 @@ extern unsigned long empty_zero_page[1024]; #define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) +#ifdef CONFIG_MMU extern pgd_t swapper_pg_dir[PAGE_SIZE/sizeof(pgd_t)]; +extern void paging_init(void); +extern void pgtable_cache_init(void); +#else +# define swapper_pg_dir NULL +static inline void paging_init(void) { } +static inline void pgtable_cache_init(void) { } +#endif /* * The pmd contains the kernel virtual address of the pte page. @@ -383,8 +391,6 @@ ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) #else -extern void paging_init(void); - #define kern_addr_valid(addr) (1) extern void update_mmu_cache(struct vm_area_struct * vma, @@ -398,9 +404,6 @@ extern void update_mmu_cache(struct vm_area_struct * vma, #define io_remap_pfn_range(vma,from,pfn,size,prot) \ remap_pfn_range(vma, from, pfn, size, prot) - -extern void pgtable_cache_init(void); - typedef pte_t *pte_addr_t; #endif /* !defined (__ASSEMBLY__) */ diff --git a/arch/xtensa/include/asm/platform.h b/arch/xtensa/include/asm/platform.h index e3d5a48ad495..7d936e58e9be 100644 --- a/arch/xtensa/include/asm/platform.h +++ b/arch/xtensa/include/asm/platform.h @@ -74,16 +74,5 @@ extern int platform_pcibios_fixup (void); */ extern void platform_calibrate_ccount (void); -/* - * platform_get_rtc_time returns RTC seconds (returns 0 for no error) - */ -extern int platform_get_rtc_time(time_t*); - -/* - * platform_set_rtc_time set RTC seconds (returns 0 for no error) - */ -extern int platform_set_rtc_time(time_t); - - #endif /* _XTENSA_PLATFORM_H */ diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h index 07387d3b99f4..0ea4937c0b61 100644 --- a/arch/xtensa/include/asm/processor.h +++ b/arch/xtensa/include/asm/processor.h @@ -13,6 +13,7 @@ #include <variant/core.h> #include <asm/coprocessor.h> +#include <platform/hardware.h> #include <linux/compiler.h> #include <asm/ptrace.h> @@ -25,6 +26,8 @@ # error Linux requires the Xtensa Windowed Registers Option. #endif +#define ARCH_SLAB_MINALIGN XCHAL_DATA_WIDTH + /* * User space process size: 1 GB. * Windowed call ABI requires caller and callee to be located within the same @@ -33,7 +36,12 @@ * the 1 GB requirement applies to the stack as well. */ +#ifdef CONFIG_MMU #define TASK_SIZE __XTENSA_UL_CONST(0x40000000) +#else +#define TASK_SIZE (PLATFORM_DEFAULT_MEM_START + PLATFORM_DEFAULT_MEM_SIZE) +#endif + #define STACK_TOP TASK_SIZE #define STACK_TOP_MAX STACK_TOP diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S index a51d36a27389..80d24c485fd3 100644 --- a/arch/xtensa/kernel/entry.S +++ b/arch/xtensa/kernel/entry.S @@ -1463,6 +1463,7 @@ ENTRY(_spill_registers) callx0 a0 # should not return 1: j 1b +#ifdef CONFIG_MMU /* * We should never get here. Bail out! */ @@ -1775,7 +1776,7 @@ ENTRY(fast_store_prohibited) bbsi.l a2, PS_UM_BIT, 1f j _kernel_exception 1: j _user_exception - +#endif /* CONFIG_MMU */ /* * System Calls. diff --git a/arch/xtensa/kernel/head.S b/arch/xtensa/kernel/head.S index 67e69139520b..0817f9db836e 100644 --- a/arch/xtensa/kernel/head.S +++ b/arch/xtensa/kernel/head.S @@ -53,7 +53,7 @@ _start: _j 2f 2: l32r a0, 1b jx a0 - .text + .section .init.text, "ax" .align 4 _startup: @@ -235,8 +235,9 @@ should_never_return: */ .section ".bss.page_aligned", "w" +#ifdef CONFIG_MMU ENTRY(swapper_pg_dir) .fill PAGE_SIZE, 1, 0 +#endif ENTRY(empty_zero_page) .fill PAGE_SIZE, 1, 0 - diff --git a/arch/xtensa/kernel/irq.c b/arch/xtensa/kernel/irq.c index f3b66fba5b8f..a36c85edd045 100644 --- a/arch/xtensa/kernel/irq.c +++ b/arch/xtensa/kernel/irq.c @@ -132,6 +132,18 @@ static void xtensa_irq_unmask(unsigned int irq) set_sr (cached_irq_mask, INTENABLE); } +static void xtensa_irq_enable(unsigned int irq) +{ + variant_irq_enable(irq); + xtensa_irq_unmask(irq); +} + +static void xtensa_irq_disable(unsigned int irq) +{ + xtensa_irq_mask(irq); + variant_irq_disable(irq); +} + static void xtensa_irq_ack(unsigned int irq) { set_sr(1 << irq, INTCLEAR); @@ -146,6 +158,8 @@ static int xtensa_irq_retrigger(unsigned int irq) static struct irq_chip xtensa_irq_chip = { .name = "xtensa", + .enable = xtensa_irq_enable, + .disable = xtensa_irq_disable, .mask = xtensa_irq_mask, .unmask = xtensa_irq_unmask, .ack = xtensa_irq_ack, diff --git a/arch/xtensa/kernel/platform.c b/arch/xtensa/kernel/platform.c index 69675f216062..1b91a97f1d84 100644 --- a/arch/xtensa/kernel/platform.c +++ b/arch/xtensa/kernel/platform.c @@ -36,8 +36,6 @@ _F(void, power_off, (void), { while(1); }); _F(void, idle, (void), { __asm__ __volatile__ ("waiti 0" ::: "memory"); }); _F(void, heartbeat, (void), { }); _F(int, pcibios_fixup, (void), { return 0; }); -_F(int, get_rtc_time, (time_t* t), { return 0; }); -_F(int, set_rtc_time, (time_t t), { return 0; }); #ifdef CONFIG_XTENSA_CALIBRATE_CCOUNT _F(void, calibrate_ccount, (void), diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c index 4ec1633c2941..1e5a034fe011 100644 --- a/arch/xtensa/kernel/setup.c +++ b/arch/xtensa/kernel/setup.c @@ -84,7 +84,13 @@ sysmem_info_t __initdata sysmem; int initrd_is_mapped; #endif +#ifdef CONFIG_MMU extern void init_mmu(void); +#else +static inline void init_mmu(void) { } +#endif + +extern void zones_init(void); /* * Boot parameter parsing. @@ -286,6 +292,7 @@ void __init setup_arch(char **cmdline_p) paging_init(); + zones_init(); #ifdef CONFIG_VT # if defined(CONFIG_VGA_CONSOLE) diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c index 8df1e842f6d4..8848120d291b 100644 --- a/arch/xtensa/kernel/time.c +++ b/arch/xtensa/kernel/time.c @@ -14,7 +14,7 @@ #include <linux/errno.h> #include <linux/time.h> -#include <linux/timex.h> +#include <linux/clocksource.h> #include <linux/interrupt.h> #include <linux/module.h> #include <linux/init.h> @@ -25,27 +25,31 @@ #include <asm/timex.h> #include <asm/platform.h> - -DEFINE_SPINLOCK(rtc_lock); -EXPORT_SYMBOL(rtc_lock); - - #ifdef CONFIG_XTENSA_CALIBRATE_CCOUNT unsigned long ccount_per_jiffy; /* per 1/HZ */ unsigned long nsec_per_ccount; /* nsec per ccount increment */ #endif -static long last_rtc_update = 0; - -/* - * Scheduler clock - returns current tim in nanosec units. - */ - -unsigned long long sched_clock(void) +static cycle_t ccount_read(void) { - return (unsigned long long)jiffies * (1000000000 / HZ); + return (cycle_t)get_ccount(); } +static struct clocksource ccount_clocksource = { + .name = "ccount", + .rating = 200, + .read = ccount_read, + .mask = CLOCKSOURCE_MASK(32), + /* + * With a shift of 22 the lower limit of the cpu clock is + * 1MHz, where NSEC_PER_CCOUNT is 1000 or a bit less than + * 2^10: Since we have 32 bits and the multiplicator can + * already take up as much as 10 bits, this leaves us with + * remaining upper 22 bits. + */ + .shift = 22, +}; + static irqreturn_t timer_interrupt(int irq, void *dev_id); static struct irqaction timer_irqaction = { .handler = timer_interrupt, @@ -55,11 +59,11 @@ static struct irqaction timer_irqaction = { void __init time_init(void) { - time_t sec_o, sec_n = 0; + xtime.tv_nsec = 0; + xtime.tv_sec = read_persistent_clock(); - /* The platform must provide a function to calibrate the processor - * speed for the CALIBRATE. - */ + set_normalized_timespec(&wall_to_monotonic, + -xtime.tv_sec, -xtime.tv_nsec); #ifdef CONFIG_XTENSA_CALIBRATE_CCOUNT printk("Calibrating CPU frequency "); @@ -67,19 +71,10 @@ void __init time_init(void) printk("%d.%02d MHz\n", (int)ccount_per_jiffy/(1000000/HZ), (int)(ccount_per_jiffy/(10000/HZ))%100); #endif - - /* Set time from RTC (if provided) */ - - if (platform_get_rtc_time(&sec_o) == 0) - while (platform_get_rtc_time(&sec_n)) - if (sec_o != sec_n) - break; - - xtime.tv_nsec = 0; - last_rtc_update = xtime.tv_sec = sec_n; - - set_normalized_timespec(&wall_to_monotonic, - -xtime.tv_sec, -xtime.tv_nsec); + ccount_clocksource.mult = + clocksource_hz2mult(CCOUNT_PER_JIFFY * HZ, + ccount_clocksource.shift); + clocksource_register(&ccount_clocksource); /* Initialize the linux timer interrupt. */ @@ -87,69 +82,6 @@ void __init time_init(void) set_linux_timer(get_ccount() + CCOUNT_PER_JIFFY); } - -int do_settimeofday(struct timespec *tv) -{ - time_t wtm_sec, sec = tv->tv_sec; - long wtm_nsec, nsec = tv->tv_nsec; - unsigned long delta; - - if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC) - return -EINVAL; - - write_seqlock_irq(&xtime_lock); - - /* This is revolting. We need to set "xtime" correctly. However, the - * value in this location is the value at the most recent update of - * wall time. Discover what correction gettimeofday() would have - * made, and then undo it! - */ - - delta = CCOUNT_PER_JIFFY; - delta += get_ccount() - get_linux_timer(); - nsec -= delta * NSEC_PER_CCOUNT; - - wtm_sec = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec); - wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec); - - set_normalized_timespec(&xtime, sec, nsec); - set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec); - - ntp_clear(); - write_sequnlock_irq(&xtime_lock); - return 0; -} - -EXPORT_SYMBOL(do_settimeofday); - - -void do_gettimeofday(struct timeval *tv) -{ - unsigned long flags; - unsigned long volatile sec, usec, delta, seq; - - do { - seq = read_seqbegin_irqsave(&xtime_lock, flags); - - sec = xtime.tv_sec; - usec = (xtime.tv_nsec / NSEC_PER_USEC); - - delta = get_linux_timer() - get_ccount(); - - } while (read_seqretry_irqrestore(&xtime_lock, seq, flags)); - - usec += (((unsigned long) CCOUNT_PER_JIFFY - delta) - * (unsigned long) NSEC_PER_CCOUNT) / NSEC_PER_USEC; - - for (; usec >= 1000000; sec++, usec -= 1000000) - ; - - tv->tv_sec = sec; - tv->tv_usec = usec; -} - -EXPORT_SYMBOL(do_gettimeofday); - /* * The timer interrupt is called HZ times per second. */ @@ -178,16 +110,6 @@ again: next += CCOUNT_PER_JIFFY; set_linux_timer(next); - if (ntp_synced() && - xtime.tv_sec - last_rtc_update >= 659 && - abs((xtime.tv_nsec/1000)-(1000000-1000000/HZ))<5000000/HZ) { - - if (platform_set_rtc_time(xtime.tv_sec+1) == 0) - last_rtc_update = xtime.tv_sec+1; - else - /* Do it again in 60 s */ - last_rtc_update += 60; - } write_sequnlock(&xtime_lock); } @@ -213,4 +135,3 @@ void __cpuinit calibrate_delay(void) (loops_per_jiffy/(10000/HZ)) % 100); } #endif - diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c index c44f830b6c7a..9f0b71189e94 100644 --- a/arch/xtensa/kernel/traps.c +++ b/arch/xtensa/kernel/traps.c @@ -104,6 +104,7 @@ static dispatch_init_table_t __initdata dispatch_init_table[] = { #endif { EXCCAUSE_UNALIGNED, KRNL, fast_unaligned }, #endif +#ifdef CONFIG_MMU { EXCCAUSE_ITLB_MISS, 0, do_page_fault }, { EXCCAUSE_ITLB_MISS, USER|KRNL, fast_second_level_miss}, { EXCCAUSE_ITLB_MULTIHIT, 0, do_multihit }, @@ -118,6 +119,7 @@ static dispatch_init_table_t __initdata dispatch_init_table[] = { { EXCCAUSE_STORE_CACHE_ATTRIBUTE, USER|KRNL, fast_store_prohibited }, { EXCCAUSE_STORE_CACHE_ATTRIBUTE, 0, do_page_fault }, { EXCCAUSE_LOAD_CACHE_ATTRIBUTE, 0, do_page_fault }, +#endif /* CONFIG_MMU */ /* XCCHAL_EXCCAUSE_FLOATING_POINT unhandled */ #if XTENSA_HAVE_COPROCESSOR(0) COPROCESSOR(0), @@ -372,11 +374,10 @@ void show_trace(struct task_struct *task, unsigned long *sp) unsigned long a0, a1, pc; unsigned long sp_start, sp_end; - a1 = (unsigned long)sp; - - if (a1 == 0) - __asm__ __volatile__ ("mov %0, a1\n" : "=a"(a1)); - + if (sp) + a1 = (unsigned long)sp; + else + a1 = task->thread.sp; sp_start = a1 & ~(THREAD_SIZE-1); sp_end = sp_start + THREAD_SIZE; @@ -418,9 +419,8 @@ void show_stack(struct task_struct *task, unsigned long *sp) int i = 0; unsigned long *stack; - if (sp == 0) - __asm__ __volatile__ ("mov %0, a1\n" : "=a"(sp)); - + if (!sp) + sp = (unsigned long *)task->thread.sp; stack = sp; printk("\nStack: "); diff --git a/arch/xtensa/kernel/vectors.S b/arch/xtensa/kernel/vectors.S index eb2d7bb69ee0..74a7518faf16 100644 --- a/arch/xtensa/kernel/vectors.S +++ b/arch/xtensa/kernel/vectors.S @@ -309,6 +309,7 @@ ENTRY(_DoubleExceptionVector) * All other exceptions are unexpected and thus unrecoverable! */ +#ifdef CONFIG_MMU .extern fast_second_level_miss_double_kernel .Lksp: /* a0: a0, a1: a1, a2: a2, a3: trashed, depc: depc, excsave: a3 */ @@ -319,6 +320,9 @@ ENTRY(_DoubleExceptionVector) bnez a3, .Lunrecoverable 1: movi a3, fast_second_level_miss_double_kernel jx a3 +#else +.equ .Lksp, .Lunrecoverable +#endif /* Critical! We can't handle this situation. PANIC! */ diff --git a/arch/xtensa/kernel/vmlinux.lds.S b/arch/xtensa/kernel/vmlinux.lds.S index d506774f4b05..c1be9a4a740c 100644 --- a/arch/xtensa/kernel/vmlinux.lds.S +++ b/arch/xtensa/kernel/vmlinux.lds.S @@ -17,6 +17,7 @@ #include <asm-generic/vmlinux.lds.h> #include <variant/core.h> +#include <platform/hardware.h> OUTPUT_ARCH(xtensa) ENTRY(_start) @@ -26,7 +27,9 @@ jiffies = jiffies_64 + 4; jiffies = jiffies_64; #endif +#ifndef KERNELOFFSET #define KERNELOFFSET 0xd0001000 +#endif /* Note: In the following macros, it would be nice to specify only the vector name and section kind and construct "sym" and "section" using diff --git a/arch/xtensa/mm/Makefile b/arch/xtensa/mm/Makefile index 64e304a2f884..f0b646d2f843 100644 --- a/arch/xtensa/mm/Makefile +++ b/arch/xtensa/mm/Makefile @@ -2,4 +2,5 @@ # Makefile for the Linux/Xtensa-specific parts of the memory manager. # -obj-y := init.o fault.o tlb.o misc.o cache.o +obj-y := init.o cache.o misc.o +obj-$(CONFIG_MMU) += fault.o mmu.o tlb.o diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c index 34163cfaaffc..427e14fa43c5 100644 --- a/arch/xtensa/mm/init.c +++ b/arch/xtensa/mm/init.c @@ -24,15 +24,8 @@ #include <linux/mm.h> #include <linux/slab.h> -#include <asm/pgtable.h> #include <asm/bootparam.h> -#include <asm/mmu_context.h> -#include <asm/tlb.h> #include <asm/page.h> -#include <asm/pgalloc.h> - - -DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); /* References to section boundaries */ @@ -130,7 +123,8 @@ void __init bootmem_init(void) /* Find an area to use for the bootmem bitmap. */ - bootmap_size = bootmem_bootmap_pages(max_low_pfn) << PAGE_SHIFT; + bootmap_size = bootmem_bootmap_pages(max_low_pfn - min_low_pfn); + bootmap_size <<= PAGE_SHIFT; bootmap_start = ~0; for (i=0; i<sysmem.nr_banks; i++) @@ -145,8 +139,9 @@ void __init bootmem_init(void) /* Reserve the bootmem bitmap area */ mem_reserve(bootmap_start, bootmap_start + bootmap_size, 1); - bootmap_size = init_bootmem_node(NODE_DATA(0), min_low_pfn, + bootmap_size = init_bootmem_node(NODE_DATA(0), bootmap_start >> PAGE_SHIFT, + min_low_pfn, max_low_pfn); /* Add all remaining memory pieces into the bootmem map */ @@ -158,14 +153,14 @@ void __init bootmem_init(void) } -void __init paging_init(void) +void __init zones_init(void) { unsigned long zones_size[MAX_NR_ZONES]; int i; /* All pages are DMA-able, so we put them all in the DMA zone. */ - zones_size[ZONE_DMA] = max_low_pfn; + zones_size[ZONE_DMA] = max_low_pfn - ARCH_PFN_OFFSET; for (i = 1; i < MAX_NR_ZONES; i++) zones_size[i] = 0; @@ -173,40 +168,7 @@ void __init paging_init(void) zones_size[ZONE_HIGHMEM] = max_pfn - max_low_pfn; #endif - /* Initialize the kernel's page tables. */ - - memset(swapper_pg_dir, 0, PAGE_SIZE); - - free_area_init(zones_size); -} - -/* - * Flush the mmu and reset associated register to default values. - */ - -void __init init_mmu (void) -{ - /* Writing zeros to the <t>TLBCFG special registers ensure - * that valid values exist in the register. For existing - * PGSZID<w> fields, zero selects the first element of the - * page-size array. For nonexistent PGSZID<w> fields, zero is - * the best value to write. Also, when changing PGSZID<w> - * fields, the corresponding TLB must be flushed. - */ - set_itlbcfg_register (0); - set_dtlbcfg_register (0); - flush_tlb_all (); - - /* Set rasid register to a known value. */ - - set_rasid_register (ASID_USER_FIRST); - - /* Set PTEVADDR special register to the start of the page - * table, which is in kernel mappable space (ie. not - * statically mapped). This register's value is undefined on - * reset. - */ - set_ptevaddr_register (PGTABLE_START); + free_area_init_node(0, zones_size, ARCH_PFN_OFFSET, NULL); } /* @@ -218,8 +180,8 @@ void __init mem_init(void) unsigned long codesize, reservedpages, datasize, initsize; unsigned long highmemsize, tmp, ram; - max_mapnr = num_physpages = max_low_pfn; - high_memory = (void *) __va(max_mapnr << PAGE_SHIFT); + max_mapnr = num_physpages = max_low_pfn - ARCH_PFN_OFFSET; + high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT); highmemsize = 0; #ifdef CONFIG_HIGHMEM @@ -229,7 +191,7 @@ void __init mem_init(void) totalram_pages += free_all_bootmem(); reservedpages = ram = 0; - for (tmp = 0; tmp < max_low_pfn; tmp++) { + for (tmp = 0; tmp < max_mapnr; tmp++) { ram++; if (PageReserved(mem_map+tmp)) reservedpages++; @@ -279,23 +241,3 @@ void free_initmem(void) printk("Freeing unused kernel memory: %dk freed\n", (&__init_end - &__init_begin) >> 10); } - -struct kmem_cache *pgtable_cache __read_mostly; - -static void pgd_ctor(void* addr) -{ - pte_t* ptep = (pte_t*)addr; - int i; - - for (i = 0; i < 1024; i++, ptep++) - pte_clear(NULL, 0, ptep); - -} - -void __init pgtable_cache_init(void) -{ - pgtable_cache = kmem_cache_create("pgd", - PAGE_SIZE, PAGE_SIZE, - SLAB_HWCACHE_ALIGN, - pgd_ctor); -} diff --git a/arch/xtensa/mm/misc.S b/arch/xtensa/mm/misc.S index c885664211d1..b048406d8756 100644 --- a/arch/xtensa/mm/misc.S +++ b/arch/xtensa/mm/misc.S @@ -84,6 +84,7 @@ ENTRY(copy_page) retw +#ifdef CONFIG_MMU /* * If we have to deal with cache aliasing, we use temporary memory mappings * to ensure that the source and destination pages have the same color as @@ -311,6 +312,7 @@ ENTRY(__invalidate_icache_page_alias) /* End of special treatment in tlb miss exception */ ENTRY(__tlbtemp_mapping_end) +#endif /* CONFIG_MMU /* * void __invalidate_icache_page(ulong start) diff --git a/arch/xtensa/mm/mmu.c b/arch/xtensa/mm/mmu.c new file mode 100644 index 000000000000..4bb91a970f1f --- /dev/null +++ b/arch/xtensa/mm/mmu.c @@ -0,0 +1,70 @@ +/* + * xtensa mmu stuff + * + * Extracted from init.c + */ +#include <linux/percpu.h> +#include <linux/init.h> +#include <linux/string.h> +#include <linux/slab.h> +#include <linux/cache.h> + +#include <asm/tlb.h> +#include <asm/tlbflush.h> +#include <asm/mmu_context.h> +#include <asm/page.h> + +DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); + +void __init paging_init(void) +{ + memset(swapper_pg_dir, 0, PAGE_SIZE); +} + +/* + * Flush the mmu and reset associated register to default values. + */ +void __init init_mmu(void) +{ + /* Writing zeros to the <t>TLBCFG special registers ensure + * that valid values exist in the register. For existing + * PGSZID<w> fields, zero selects the first element of the + * page-size array. For nonexistent PGSZID<w> fields, zero is + * the best value to write. Also, when changing PGSZID<w> + * fields, the corresponding TLB must be flushed. + */ + set_itlbcfg_register(0); + set_dtlbcfg_register(0); + flush_tlb_all(); + + /* Set rasid register to a known value. */ + + set_rasid_register(ASID_USER_FIRST); + + /* Set PTEVADDR special register to the start of the page + * table, which is in kernel mappable space (ie. not + * statically mapped). This register's value is undefined on + * reset. + */ + set_ptevaddr_register(PGTABLE_START); +} + +struct kmem_cache *pgtable_cache __read_mostly; + +static void pgd_ctor(void *addr) +{ + pte_t *ptep = (pte_t *)addr; + int i; + + for (i = 0; i < 1024; i++, ptep++) + pte_clear(NULL, 0, ptep); + +} + +void __init pgtable_cache_init(void) +{ + pgtable_cache = kmem_cache_create("pgd", + PAGE_SIZE, PAGE_SIZE, + SLAB_HWCACHE_ALIGN, + pgd_ctor); +} diff --git a/arch/xtensa/platforms/s6105/Makefile b/arch/xtensa/platforms/s6105/Makefile new file mode 100644 index 000000000000..0be6194bcb72 --- /dev/null +++ b/arch/xtensa/platforms/s6105/Makefile @@ -0,0 +1,3 @@ +# Makefile for the Stretch S6105 eval board + +obj-y := setup.o device.o diff --git a/arch/xtensa/platforms/s6105/device.c b/arch/xtensa/platforms/s6105/device.c new file mode 100644 index 000000000000..78b08be5a92d --- /dev/null +++ b/arch/xtensa/platforms/s6105/device.c @@ -0,0 +1,67 @@ +/* + * s6105 platform devices + * + * Copyright (c) 2009 emlix GmbH + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/platform_device.h> +#include <linux/serial.h> +#include <linux/serial_8250.h> + +#include <variant/hardware.h> + +#define UART_INTNUM 4 + +static const signed char uart_irq_mappings[] = { + S6_INTC_UART(0), + S6_INTC_UART(1), + -1, +}; + +const signed char *platform_irq_mappings[NR_IRQS] = { + [UART_INTNUM] = uart_irq_mappings, +}; + +static struct plat_serial8250_port serial_platform_data[] = { + { + .membase = (void *)S6_REG_UART + 0x0000, + .mapbase = S6_REG_UART + 0x0000, + .irq = UART_INTNUM, + .uartclk = S6_SCLK, + .regshift = 2, + .iotype = SERIAL_IO_MEM, + .flags = ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST, + }, + { + .membase = (void *)S6_REG_UART + 0x1000, + .mapbase = S6_REG_UART + 0x1000, + .irq = UART_INTNUM, + .uartclk = S6_SCLK, + .regshift = 2, + .iotype = SERIAL_IO_MEM, + .flags = ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST, + }, + { }, +}; + +static struct platform_device platform_devices[] = { + { + .name = "serial8250", + .id = PLAT8250_DEV_PLATFORM, + .dev = { + .platform_data = serial_platform_data, + }, + }, +}; + +static int __init device_init(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(platform_devices); i++) + platform_device_register(&platform_devices[i]); + return 0; +} +arch_initcall_sync(device_init); diff --git a/arch/xtensa/platforms/s6105/include/platform/gpio.h b/arch/xtensa/platforms/s6105/include/platform/gpio.h new file mode 100644 index 000000000000..fa11aa4b61e9 --- /dev/null +++ b/arch/xtensa/platforms/s6105/include/platform/gpio.h @@ -0,0 +1,27 @@ +#ifndef __ASM_XTENSA_S6105_GPIO_H +#define __ASM_XTENSA_S6105_GPIO_H + +#define GPIO_BP_TEMP_ALARM 0 +#define GPIO_PB_RESET_IN 1 +#define GPIO_EXP_IRQ 2 +#define GPIO_TRIGGER_IRQ 3 +#define GPIO_RTC_IRQ 4 +#define GPIO_PHY_IRQ 5 +#define GPIO_IMAGER_RESET 6 +#define GPIO_SD_IRQ 7 +#define GPIO_MINI_BOOT_INH 8 +#define GPIO_BOARD_RESET 9 +#define GPIO_EXP_PRESENT 10 +#define GPIO_LED1_NGREEN 12 +#define GPIO_LED1_RED 13 +#define GPIO_LED0_NGREEN 14 +#define GPIO_LED0_NRED 15 +#define GPIO_SPI_CS0 16 +#define GPIO_SPI_CS1 17 +#define GPIO_SPI_CS3 19 +#define GPIO_SPI_CS4 20 +#define GPIO_SD_WP 21 +#define GPIO_BP_RESET 22 +#define GPIO_ALARM_OUT 23 + +#endif /* __ASM_XTENSA_S6105_GPIO_H */ diff --git a/arch/xtensa/platforms/s6105/include/platform/hardware.h b/arch/xtensa/platforms/s6105/include/platform/hardware.h new file mode 100644 index 000000000000..d628efac7089 --- /dev/null +++ b/arch/xtensa/platforms/s6105/include/platform/hardware.h @@ -0,0 +1,11 @@ +#ifndef __XTENSA_S6105_HARDWARE_H +#define __XTENSA_S6105_HARDWARE_H + +#define PLATFORM_DEFAULT_MEM_START 0x40000000 +#define PLATFORM_DEFAULT_MEM_SIZE 0x08000000 + +#define MAX_DMA_ADDRESS 0 + +#define KERNELOFFSET (PLATFORM_DEFAULT_MEM_START + 0x1000) + +#endif /* __XTENSA_S6105_HARDWARE_H */ diff --git a/arch/xtensa/platforms/s6105/include/platform/serial.h b/arch/xtensa/platforms/s6105/include/platform/serial.h new file mode 100644 index 000000000000..c8a771e5981b --- /dev/null +++ b/arch/xtensa/platforms/s6105/include/platform/serial.h @@ -0,0 +1,8 @@ +#ifndef __ASM_XTENSA_S6105_SERIAL_H +#define __ASM_XTENSA_S6105_SERIAL_H + +#include <variant/hardware.h> + +#define BASE_BAUD (S6_SCLK / 16) + +#endif /* __ASM_XTENSA_S6105_SERIAL_H */ diff --git a/arch/xtensa/platforms/s6105/setup.c b/arch/xtensa/platforms/s6105/setup.c new file mode 100644 index 000000000000..ae041d5027a2 --- /dev/null +++ b/arch/xtensa/platforms/s6105/setup.c @@ -0,0 +1,61 @@ +/* + * s6105 control routines + * + * Copyright (c) 2009 emlix GmbH + */ +#include <linux/irq.h> +#include <linux/io.h> +#include <linux/gpio.h> + +#include <asm/bootparam.h> + +#include <variant/hardware.h> +#include <platform/gpio.h> + +void platform_halt(void) +{ + local_irq_disable(); + while (1) + ; +} + +void platform_power_off(void) +{ + platform_halt(); +} + +void platform_restart(void) +{ + platform_halt(); +} + +void __init platform_setup(char **cmdline) +{ + unsigned long reg; + + reg = readl(S6_REG_GREG1 + S6_GREG1_CLKGATE); + reg &= ~(1 << S6_GREG1_BLOCK_SB); + writel(reg, S6_REG_GREG1 + S6_GREG1_CLKGATE); + + reg = readl(S6_REG_GREG1 + S6_GREG1_BLOCKENA); + reg |= 1 << S6_GREG1_BLOCK_SB; + writel(reg, S6_REG_GREG1 + S6_GREG1_BLOCKENA); + + printk(KERN_NOTICE "S6105 on Stretch S6000 - " + "Copyright (C) 2009 emlix GmbH <info@emlix.com>\n"); +} + +void __init platform_init(bp_tag_t *first) +{ + gpio_request(GPIO_LED1_NGREEN, "led1_green"); + gpio_request(GPIO_LED1_RED, "led1_red"); + gpio_direction_output(GPIO_LED1_NGREEN, 1); +} + +void platform_heartbeat(void) +{ + static unsigned int c; + + if (!(++c & 0x4F)) + gpio_direction_output(GPIO_LED1_RED, !(c & 0x10)); +} diff --git a/arch/xtensa/platforms/xt2000/include/platform/hardware.h b/arch/xtensa/platforms/xt2000/include/platform/hardware.h index 41459ad07766..886ef156ded3 100644 --- a/arch/xtensa/platforms/xt2000/include/platform/hardware.h +++ b/arch/xtensa/platforms/xt2000/include/platform/hardware.h @@ -16,7 +16,6 @@ #define _XTENSA_XT2000_HARDWARE_H #include <variant/core.h> -#include <asm/io.h> /* * Memory configuration. diff --git a/arch/xtensa/variants/s6000/Makefile b/arch/xtensa/variants/s6000/Makefile new file mode 100644 index 000000000000..03b3975468bd --- /dev/null +++ b/arch/xtensa/variants/s6000/Makefile @@ -0,0 +1,3 @@ +# s6000 Makefile + +obj-y += irq.o gpio.o diff --git a/arch/xtensa/variants/s6000/gpio.c b/arch/xtensa/variants/s6000/gpio.c new file mode 100644 index 000000000000..33a8d952934c --- /dev/null +++ b/arch/xtensa/variants/s6000/gpio.c @@ -0,0 +1,71 @@ +/* + * s6000 gpio driver + * + * Copyright (c) 2009 emlix GmbH + * Authors: Oskar Schirmer <os@emlix.com> + * Johannes Weiner <jw@emlix.com> + */ +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/io.h> +#include <linux/gpio.h> + +#include <variant/hardware.h> + +#define S6_GPIO_DATA 0x000 +#define S6_GPIO_IS 0x404 +#define S6_GPIO_IBE 0x408 +#define S6_GPIO_IEV 0x40C +#define S6_GPIO_IE 0x410 +#define S6_GPIO_RIS 0x414 +#define S6_GPIO_MIS 0x418 +#define S6_GPIO_IC 0x41C +#define S6_GPIO_AFSEL 0x420 +#define S6_GPIO_DIR 0x800 +#define S6_GPIO_BANK(nr) ((nr) * 0x1000) +#define S6_GPIO_MASK(nr) (4 << (nr)) +#define S6_GPIO_OFFSET(nr) \ + (S6_GPIO_BANK((nr) >> 3) + S6_GPIO_MASK((nr) & 7)) + +static int direction_input(struct gpio_chip *chip, unsigned int off) +{ + writeb(0, S6_REG_GPIO + S6_GPIO_DIR + S6_GPIO_OFFSET(off)); + return 0; +} + +static int get(struct gpio_chip *chip, unsigned int off) +{ + return readb(S6_REG_GPIO + S6_GPIO_DATA + S6_GPIO_OFFSET(off)); +} + +static int direction_output(struct gpio_chip *chip, unsigned int off, int val) +{ + unsigned rel = S6_GPIO_OFFSET(off); + writeb(~0, S6_REG_GPIO + S6_GPIO_DIR + rel); + writeb(val ? ~0 : 0, S6_REG_GPIO + S6_GPIO_DATA + rel); + return 0; +} + +static void set(struct gpio_chip *chip, unsigned int off, int val) +{ + writeb(val ? ~0 : 0, S6_REG_GPIO + S6_GPIO_DATA + S6_GPIO_OFFSET(off)); +} + +static struct gpio_chip gpiochip = { + .owner = THIS_MODULE, + .direction_input = direction_input, + .get = get, + .direction_output = direction_output, + .set = set, + .base = 0, + .ngpio = 24, + .can_sleep = 0, /* no blocking io needed */ + .exported = 0, /* no exporting to userspace */ +}; + +static int gpio_init(void) +{ + return gpiochip_add(&gpiochip); +} +device_initcall(gpio_init); diff --git a/arch/xtensa/variants/s6000/include/variant/core.h b/arch/xtensa/variants/s6000/include/variant/core.h new file mode 100644 index 000000000000..af007953027e --- /dev/null +++ b/arch/xtensa/variants/s6000/include/variant/core.h @@ -0,0 +1,431 @@ +/* + * Xtensa processor core configuration information. + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (c) 1999-2008 Tensilica Inc. + */ + +#ifndef _XTENSA_CORE_CONFIGURATION_H +#define _XTENSA_CORE_CONFIGURATION_H + + +/**************************************************************************** + Parameters Useful for Any Code, USER or PRIVILEGED + ****************************************************************************/ + +/* + * Note: Macros of the form XCHAL_HAVE_*** have a value of 1 if the option is + * configured, and a value of 0 otherwise. These macros are always defined. + */ + + +/*---------------------------------------------------------------------- + ISA + ----------------------------------------------------------------------*/ + +#define XCHAL_HAVE_BE 0 /* big-endian byte ordering */ +#define XCHAL_HAVE_WINDOWED 1 /* windowed registers option */ +#define XCHAL_NUM_AREGS 64 /* num of physical addr regs */ +#define XCHAL_NUM_AREGS_LOG2 6 /* log2(XCHAL_NUM_AREGS) */ +#define XCHAL_MAX_INSTRUCTION_SIZE 8 /* max instr bytes (3..8) */ +#define XCHAL_HAVE_DEBUG 1 /* debug option */ +#define XCHAL_HAVE_DENSITY 1 /* 16-bit instructions */ +#define XCHAL_HAVE_LOOPS 1 /* zero-overhead loops */ +#define XCHAL_HAVE_NSA 1 /* NSA/NSAU instructions */ +#define XCHAL_HAVE_MINMAX 1 /* MIN/MAX instructions */ +#define XCHAL_HAVE_SEXT 1 /* SEXT instruction */ +#define XCHAL_HAVE_CLAMPS 1 /* CLAMPS instruction */ +#define XCHAL_HAVE_MUL16 1 /* MUL16S/MUL16U instructions */ +#define XCHAL_HAVE_MUL32 1 /* MULL instruction */ +#define XCHAL_HAVE_MUL32_HIGH 1 /* MULUH/MULSH instructions */ +#define XCHAL_HAVE_DIV32 0 /* QUOS/QUOU/REMS/REMU instructions */ +#define XCHAL_HAVE_L32R 1 /* L32R instruction */ +#define XCHAL_HAVE_ABSOLUTE_LITERALS 1 /* non-PC-rel (extended) L32R */ +#define XCHAL_HAVE_CONST16 0 /* CONST16 instruction */ +#define XCHAL_HAVE_ADDX 1 /* ADDX#/SUBX# instructions */ +#define XCHAL_HAVE_WIDE_BRANCHES 0 /* B*.W18 or B*.W15 instr's */ +#define XCHAL_HAVE_PREDICTED_BRANCHES 0 /* B[EQ/EQZ/NE/NEZ]T instr's */ +#define XCHAL_HAVE_CALL4AND12 1 /* (obsolete option) */ +#define XCHAL_HAVE_ABS 1 /* ABS instruction */ +/*#define XCHAL_HAVE_POPC 0*/ /* POPC instruction */ +/*#define XCHAL_HAVE_CRC 0*/ /* CRC instruction */ +#define XCHAL_HAVE_RELEASE_SYNC 0 /* L32AI/S32RI instructions */ +#define XCHAL_HAVE_S32C1I 0 /* S32C1I instruction */ +#define XCHAL_HAVE_SPECULATION 0 /* speculation */ +#define XCHAL_HAVE_FULL_RESET 0 /* all regs/state reset */ +#define XCHAL_NUM_CONTEXTS 1 /* */ +#define XCHAL_NUM_MISC_REGS 4 /* num of scratch regs (0..4) */ +#define XCHAL_HAVE_TAP_MASTER 0 /* JTAG TAP control instr's */ +#define XCHAL_HAVE_PRID 0 /* processor ID register */ +#define XCHAL_HAVE_THREADPTR 0 /* THREADPTR register */ +#define XCHAL_HAVE_BOOLEANS 1 /* boolean registers */ +#define XCHAL_HAVE_CP 1 /* CPENABLE reg (coprocessor) */ +#define XCHAL_CP_MAXCFG 8 /* max allowed cp id plus one */ +#define XCHAL_HAVE_MAC16 0 /* MAC16 package */ +#define XCHAL_HAVE_VECTORFPU2005 0 /* vector floating-point pkg */ +#define XCHAL_HAVE_FP 1 /* floating point pkg */ +#define XCHAL_HAVE_VECTRA1 0 /* Vectra I pkg */ +#define XCHAL_HAVE_VECTRALX 0 /* Vectra LX pkg */ +#define XCHAL_HAVE_HIFI2 0 /* HiFi2 Audio Engine pkg */ + + +/*---------------------------------------------------------------------- + MISC + ----------------------------------------------------------------------*/ + +#define XCHAL_NUM_WRITEBUFFER_ENTRIES 8 /* size of write buffer */ +#define XCHAL_INST_FETCH_WIDTH 8 /* instr-fetch width in bytes */ +#define XCHAL_DATA_WIDTH 16 /* data width in bytes */ +/* In T1050, applies to selected core load and store instructions (see ISA): */ +#define XCHAL_UNALIGNED_LOAD_EXCEPTION 1 /* unaligned loads cause exc. */ +#define XCHAL_UNALIGNED_STORE_EXCEPTION 1 /* unaligned stores cause exc.*/ + +#define XCHAL_SW_VERSION 701001 /* sw version of this header */ + +#define XCHAL_CORE_ID "stretch_bali" /* alphanum core name + (CoreID) set in the Xtensa + Processor Generator */ + +#define XCHAL_BUILD_UNIQUE_ID 0x000104B9 /* 22-bit sw build ID */ + +/* + * These definitions describe the hardware targeted by this software. + */ +#define XCHAL_HW_CONFIGID0 0xC2F3F9FE /* ConfigID hi 32 bits*/ +#define XCHAL_HW_CONFIGID1 0x054104B9 /* ConfigID lo 32 bits*/ +#define XCHAL_HW_VERSION_NAME "LX1.0.2" /* full version name */ +#define XCHAL_HW_VERSION_MAJOR 2100 /* major ver# of targeted hw */ +#define XCHAL_HW_VERSION_MINOR 2 /* minor ver# of targeted hw */ +#define XCHAL_HW_VERSION 210002 /* major*100+minor */ +#define XCHAL_HW_REL_LX1 1 +#define XCHAL_HW_REL_LX1_0 1 +#define XCHAL_HW_REL_LX1_0_2 1 +#define XCHAL_HW_CONFIGID_RELIABLE 1 +/* If software targets a *range* of hardware versions, these are the bounds: */ +#define XCHAL_HW_MIN_VERSION_MAJOR 2100 /* major v of earliest tgt hw */ +#define XCHAL_HW_MIN_VERSION_MINOR 2 /* minor v of earliest tgt hw */ +#define XCHAL_HW_MIN_VERSION 210002 /* earliest targeted hw */ +#define XCHAL_HW_MAX_VERSION_MAJOR 2100 /* major v of latest tgt hw */ +#define XCHAL_HW_MAX_VERSION_MINOR 2 /* minor v of latest tgt hw */ +#define XCHAL_HW_MAX_VERSION 210002 /* latest targeted hw */ + + +/*---------------------------------------------------------------------- + CACHE + ----------------------------------------------------------------------*/ + +#define XCHAL_ICACHE_LINESIZE 16 /* I-cache line size in bytes */ +#define XCHAL_DCACHE_LINESIZE 16 /* D-cache line size in bytes */ +#define XCHAL_ICACHE_LINEWIDTH 4 /* log2(I line size in bytes) */ +#define XCHAL_DCACHE_LINEWIDTH 4 /* log2(D line size in bytes) */ + +#define XCHAL_ICACHE_SIZE 32768 /* I-cache size in bytes or 0 */ +#define XCHAL_DCACHE_SIZE 32768 /* D-cache size in bytes or 0 */ + +#define XCHAL_DCACHE_IS_WRITEBACK 1 /* writeback feature */ + + + + +/**************************************************************************** + Parameters Useful for PRIVILEGED (Supervisory or Non-Virtualized) Code + ****************************************************************************/ + + +#ifndef XTENSA_HAL_NON_PRIVILEGED_ONLY + +/*---------------------------------------------------------------------- + CACHE + ----------------------------------------------------------------------*/ + +#define XCHAL_HAVE_PIF 1 /* any outbound PIF present */ + +/* If present, cache size in bytes == (ways * 2^(linewidth + setwidth)). */ + +/* Number of cache sets in log2(lines per way): */ +#define XCHAL_ICACHE_SETWIDTH 9 +#define XCHAL_DCACHE_SETWIDTH 10 + +/* Cache set associativity (number of ways): */ +#define XCHAL_ICACHE_WAYS 4 +#define XCHAL_DCACHE_WAYS 2 + +/* Cache features: */ +#define XCHAL_ICACHE_LINE_LOCKABLE 1 +#define XCHAL_DCACHE_LINE_LOCKABLE 0 +#define XCHAL_ICACHE_ECC_PARITY 0 +#define XCHAL_DCACHE_ECC_PARITY 0 + +/* Number of encoded cache attr bits (see <xtensa/hal.h> for decoded bits): */ +#define XCHAL_CA_BITS 4 + + +/*---------------------------------------------------------------------- + INTERNAL I/D RAM/ROMs and XLMI + ----------------------------------------------------------------------*/ + +#define XCHAL_NUM_INSTROM 0 /* number of core instr. ROMs */ +#define XCHAL_NUM_INSTRAM 0 /* number of core instr. RAMs */ +#define XCHAL_NUM_DATAROM 0 /* number of core data ROMs */ +#define XCHAL_NUM_DATARAM 1 /* number of core data RAMs */ +#define XCHAL_NUM_URAM 0 /* number of core unified RAMs*/ +#define XCHAL_NUM_XLMI 1 /* number of core XLMI ports */ + +/* Data RAM 0: */ +#define XCHAL_DATARAM0_VADDR 0x3FFF0000 +#define XCHAL_DATARAM0_PADDR 0x3FFF0000 +#define XCHAL_DATARAM0_SIZE 65536 +#define XCHAL_DATARAM0_ECC_PARITY 0 + +/* XLMI Port 0: */ +#define XCHAL_XLMI0_VADDR 0x37F80000 +#define XCHAL_XLMI0_PADDR 0x37F80000 +#define XCHAL_XLMI0_SIZE 262144 +#define XCHAL_XLMI0_ECC_PARITY 0 + + +/*---------------------------------------------------------------------- + INTERRUPTS and TIMERS + ----------------------------------------------------------------------*/ + +#define XCHAL_HAVE_INTERRUPTS 1 /* interrupt option */ +#define XCHAL_HAVE_HIGHPRI_INTERRUPTS 1 /* med/high-pri. interrupts */ +#define XCHAL_HAVE_NMI 1 /* non-maskable interrupt */ +#define XCHAL_HAVE_CCOUNT 1 /* CCOUNT reg. (timer option) */ +#define XCHAL_NUM_TIMERS 3 /* number of CCOMPAREn regs */ +#define XCHAL_NUM_INTERRUPTS 27 /* number of interrupts */ +#define XCHAL_NUM_INTERRUPTS_LOG2 5 /* ceil(log2(NUM_INTERRUPTS)) */ +#define XCHAL_NUM_EXTINTERRUPTS 20 /* num of external interrupts */ +#define XCHAL_NUM_INTLEVELS 4 /* number of interrupt levels + (not including level zero) */ +#define XCHAL_EXCM_LEVEL 1 /* level masked by PS.EXCM */ + /* (always 1 in XEA1; levels 2 .. EXCM_LEVEL are "medium priority") */ + +/* Masks of interrupts at each interrupt level: */ +#define XCHAL_INTLEVEL1_MASK 0x01F07FFF +#define XCHAL_INTLEVEL2_MASK 0x02018000 +#define XCHAL_INTLEVEL3_MASK 0x04060000 +#define XCHAL_INTLEVEL4_MASK 0x00000000 +#define XCHAL_INTLEVEL5_MASK 0x00080000 +#define XCHAL_INTLEVEL6_MASK 0x00000000 +#define XCHAL_INTLEVEL7_MASK 0x00000000 + +/* Masks of interrupts at each range 1..n of interrupt levels: */ +#define XCHAL_INTLEVEL1_ANDBELOW_MASK 0x01F07FFF +#define XCHAL_INTLEVEL2_ANDBELOW_MASK 0x03F1FFFF +#define XCHAL_INTLEVEL3_ANDBELOW_MASK 0x07F7FFFF +#define XCHAL_INTLEVEL4_ANDBELOW_MASK 0x07F7FFFF +#define XCHAL_INTLEVEL5_ANDBELOW_MASK 0x07FFFFFF +#define XCHAL_INTLEVEL6_ANDBELOW_MASK 0x07FFFFFF +#define XCHAL_INTLEVEL7_ANDBELOW_MASK 0x07FFFFFF + +/* Level of each interrupt: */ +#define XCHAL_INT0_LEVEL 1 +#define XCHAL_INT1_LEVEL 1 +#define XCHAL_INT2_LEVEL 1 +#define XCHAL_INT3_LEVEL 1 +#define XCHAL_INT4_LEVEL 1 +#define XCHAL_INT5_LEVEL 1 +#define XCHAL_INT6_LEVEL 1 +#define XCHAL_INT7_LEVEL 1 +#define XCHAL_INT8_LEVEL 1 +#define XCHAL_INT9_LEVEL 1 +#define XCHAL_INT10_LEVEL 1 +#define XCHAL_INT11_LEVEL 1 +#define XCHAL_INT12_LEVEL 1 +#define XCHAL_INT13_LEVEL 1 +#define XCHAL_INT14_LEVEL 1 +#define XCHAL_INT15_LEVEL 2 +#define XCHAL_INT16_LEVEL 2 +#define XCHAL_INT17_LEVEL 3 +#define XCHAL_INT18_LEVEL 3 +#define XCHAL_INT19_LEVEL 5 +#define XCHAL_INT20_LEVEL 1 +#define XCHAL_INT21_LEVEL 1 +#define XCHAL_INT22_LEVEL 1 +#define XCHAL_INT23_LEVEL 1 +#define XCHAL_INT24_LEVEL 1 +#define XCHAL_INT25_LEVEL 2 +#define XCHAL_INT26_LEVEL 3 +#define XCHAL_DEBUGLEVEL 4 /* debug interrupt level */ +#define XCHAL_HAVE_DEBUG_EXTERN_INT 1 /* OCD external db interrupt */ +#define XCHAL_NMILEVEL 5 /* NMI "level" (for use with + EXCSAVE/EPS/EPC_n, RFI n) */ + +/* Type of each interrupt: */ +#define XCHAL_INT0_TYPE XTHAL_INTTYPE_EXTERN_LEVEL +#define XCHAL_INT1_TYPE XTHAL_INTTYPE_EXTERN_LEVEL +#define XCHAL_INT2_TYPE XTHAL_INTTYPE_EXTERN_LEVEL +#define XCHAL_INT3_TYPE XTHAL_INTTYPE_EXTERN_LEVEL +#define XCHAL_INT4_TYPE XTHAL_INTTYPE_EXTERN_LEVEL +#define XCHAL_INT5_TYPE XTHAL_INTTYPE_EXTERN_LEVEL +#define XCHAL_INT6_TYPE XTHAL_INTTYPE_EXTERN_LEVEL +#define XCHAL_INT7_TYPE XTHAL_INTTYPE_EXTERN_LEVEL +#define XCHAL_INT8_TYPE XTHAL_INTTYPE_EXTERN_LEVEL +#define XCHAL_INT9_TYPE XTHAL_INTTYPE_EXTERN_LEVEL +#define XCHAL_INT10_TYPE XTHAL_INTTYPE_EXTERN_LEVEL +#define XCHAL_INT11_TYPE XTHAL_INTTYPE_EXTERN_LEVEL +#define XCHAL_INT12_TYPE XTHAL_INTTYPE_EXTERN_LEVEL +#define XCHAL_INT13_TYPE XTHAL_INTTYPE_EXTERN_LEVEL +#define XCHAL_INT14_TYPE XTHAL_INTTYPE_EXTERN_LEVEL +#define XCHAL_INT15_TYPE XTHAL_INTTYPE_EXTERN_LEVEL +#define XCHAL_INT16_TYPE XTHAL_INTTYPE_EXTERN_LEVEL +#define XCHAL_INT17_TYPE XTHAL_INTTYPE_EXTERN_LEVEL +#define XCHAL_INT18_TYPE XTHAL_INTTYPE_EXTERN_LEVEL +#define XCHAL_INT19_TYPE XTHAL_INTTYPE_NMI +#define XCHAL_INT20_TYPE XTHAL_INTTYPE_SOFTWARE +#define XCHAL_INT21_TYPE XTHAL_INTTYPE_SOFTWARE +#define XCHAL_INT22_TYPE XTHAL_INTTYPE_SOFTWARE +#define XCHAL_INT23_TYPE XTHAL_INTTYPE_SOFTWARE +#define XCHAL_INT24_TYPE XTHAL_INTTYPE_TIMER +#define XCHAL_INT25_TYPE XTHAL_INTTYPE_TIMER +#define XCHAL_INT26_TYPE XTHAL_INTTYPE_TIMER + +/* Masks of interrupts for each type of interrupt: */ +#define XCHAL_INTTYPE_MASK_UNCONFIGURED 0xF8000000 +#define XCHAL_INTTYPE_MASK_SOFTWARE 0x00F00000 +#define XCHAL_INTTYPE_MASK_EXTERN_EDGE 0x00000000 +#define XCHAL_INTTYPE_MASK_EXTERN_LEVEL 0x0007FFFF +#define XCHAL_INTTYPE_MASK_TIMER 0x07000000 +#define XCHAL_INTTYPE_MASK_NMI 0x00080000 +#define XCHAL_INTTYPE_MASK_WRITE_ERROR 0x00000000 + +/* Interrupt numbers assigned to specific interrupt sources: */ +#define XCHAL_TIMER0_INTERRUPT 24 /* CCOMPARE0 */ +#define XCHAL_TIMER1_INTERRUPT 25 /* CCOMPARE1 */ +#define XCHAL_TIMER2_INTERRUPT 26 /* CCOMPARE2 */ +#define XCHAL_TIMER3_INTERRUPT XTHAL_TIMER_UNCONFIGURED +#define XCHAL_NMI_INTERRUPT 19 /* non-maskable interrupt */ + +/* Interrupt numbers for levels at which only one interrupt is configured: */ +#define XCHAL_INTLEVEL5_NUM 19 +/* (There are many interrupts each at level(s) 1, 2, 3.) */ + + +/* + * External interrupt vectors/levels. + * These macros describe how Xtensa processor interrupt numbers + * (as numbered internally, eg. in INTERRUPT and INTENABLE registers) + * map to external BInterrupt<n> pins, for those interrupts + * configured as external (level-triggered, edge-triggered, or NMI). + * See the Xtensa processor databook for more details. + */ + +/* Core interrupt numbers mapped to each EXTERNAL interrupt number: */ +#define XCHAL_EXTINT0_NUM 0 /* (intlevel 1) */ +#define XCHAL_EXTINT1_NUM 1 /* (intlevel 1) */ +#define XCHAL_EXTINT2_NUM 2 /* (intlevel 1) */ +#define XCHAL_EXTINT3_NUM 3 /* (intlevel 1) */ +#define XCHAL_EXTINT4_NUM 4 /* (intlevel 1) */ +#define XCHAL_EXTINT5_NUM 5 /* (intlevel 1) */ +#define XCHAL_EXTINT6_NUM 6 /* (intlevel 1) */ +#define XCHAL_EXTINT7_NUM 7 /* (intlevel 1) */ +#define XCHAL_EXTINT8_NUM 8 /* (intlevel 1) */ +#define XCHAL_EXTINT9_NUM 9 /* (intlevel 1) */ +#define XCHAL_EXTINT10_NUM 10 /* (intlevel 1) */ +#define XCHAL_EXTINT11_NUM 11 /* (intlevel 1) */ +#define XCHAL_EXTINT12_NUM 12 /* (intlevel 1) */ +#define XCHAL_EXTINT13_NUM 13 /* (intlevel 1) */ +#define XCHAL_EXTINT14_NUM 14 /* (intlevel 1) */ +#define XCHAL_EXTINT15_NUM 15 /* (intlevel 2) */ +#define XCHAL_EXTINT16_NUM 16 /* (intlevel 2) */ +#define XCHAL_EXTINT17_NUM 17 /* (intlevel 3) */ +#define XCHAL_EXTINT18_NUM 18 /* (intlevel 3) */ +#define XCHAL_EXTINT19_NUM 19 /* (intlevel 5) */ + + +/*---------------------------------------------------------------------- + EXCEPTIONS and VECTORS + ----------------------------------------------------------------------*/ + +#define XCHAL_XEA_VERSION 2 /* Xtensa Exception Architecture + number: 1 == XEA1 (old) + 2 == XEA2 (new) + 0 == XEAX (extern) */ +#define XCHAL_HAVE_XEA1 0 /* Exception Architecture 1 */ +#define XCHAL_HAVE_XEA2 1 /* Exception Architecture 2 */ +#define XCHAL_HAVE_XEAX 0 /* External Exception Arch. */ +#define XCHAL_HAVE_EXCEPTIONS 1 /* exception option */ +#define XCHAL_HAVE_MEM_ECC_PARITY 0 /* local memory ECC/parity */ +#define XCHAL_HAVE_VECTOR_SELECT 0 /* relocatable vectors */ +#define XCHAL_HAVE_VECBASE 0 /* relocatable vectors */ + +#define XCHAL_RESET_VECOFS 0x00000000 +#define XCHAL_RESET_VECTOR_VADDR 0x3FFE03D0 +#define XCHAL_RESET_VECTOR_PADDR 0x3FFE03D0 +#define XCHAL_USER_VECOFS 0x00000000 +#define XCHAL_USER_VECTOR_VADDR 0x40000220 +#define XCHAL_USER_VECTOR_PADDR 0x40000220 +#define XCHAL_KERNEL_VECOFS 0x00000000 +#define XCHAL_KERNEL_VECTOR_VADDR 0x40000200 +#define XCHAL_KERNEL_VECTOR_PADDR 0x40000200 +#define XCHAL_DOUBLEEXC_VECOFS 0x00000000 +#define XCHAL_DOUBLEEXC_VECTOR_VADDR 0x400002A0 +#define XCHAL_DOUBLEEXC_VECTOR_PADDR 0x400002A0 +#define XCHAL_WINDOW_OF4_VECOFS 0x00000000 +#define XCHAL_WINDOW_UF4_VECOFS 0x00000040 +#define XCHAL_WINDOW_OF8_VECOFS 0x00000080 +#define XCHAL_WINDOW_UF8_VECOFS 0x000000C0 +#define XCHAL_WINDOW_OF12_VECOFS 0x00000100 +#define XCHAL_WINDOW_UF12_VECOFS 0x00000140 +#define XCHAL_WINDOW_VECTORS_VADDR 0x40000000 +#define XCHAL_WINDOW_VECTORS_PADDR 0x40000000 +#define XCHAL_INTLEVEL2_VECOFS 0x00000000 +#define XCHAL_INTLEVEL2_VECTOR_VADDR 0x40000240 +#define XCHAL_INTLEVEL2_VECTOR_PADDR 0x40000240 +#define XCHAL_INTLEVEL3_VECOFS 0x00000000 +#define XCHAL_INTLEVEL3_VECTOR_VADDR 0x40000260 +#define XCHAL_INTLEVEL3_VECTOR_PADDR 0x40000260 +#define XCHAL_INTLEVEL4_VECOFS 0x00000000 +#define XCHAL_INTLEVEL4_VECTOR_VADDR 0x40000390 +#define XCHAL_INTLEVEL4_VECTOR_PADDR 0x40000390 +#define XCHAL_DEBUG_VECOFS XCHAL_INTLEVEL4_VECOFS +#define XCHAL_DEBUG_VECTOR_VADDR XCHAL_INTLEVEL4_VECTOR_VADDR +#define XCHAL_DEBUG_VECTOR_PADDR XCHAL_INTLEVEL4_VECTOR_PADDR +#define XCHAL_NMI_VECOFS 0x00000000 +#define XCHAL_NMI_VECTOR_VADDR 0x400003B0 +#define XCHAL_NMI_VECTOR_PADDR 0x400003B0 +#define XCHAL_INTLEVEL5_VECOFS XCHAL_NMI_VECOFS +#define XCHAL_INTLEVEL5_VECTOR_VADDR XCHAL_NMI_VECTOR_VADDR +#define XCHAL_INTLEVEL5_VECTOR_PADDR XCHAL_NMI_VECTOR_PADDR + + +/*---------------------------------------------------------------------- + DEBUG + ----------------------------------------------------------------------*/ + +#define XCHAL_HAVE_OCD 1 /* OnChipDebug option */ +#define XCHAL_NUM_IBREAK 2 /* number of IBREAKn regs */ +#define XCHAL_NUM_DBREAK 2 /* number of DBREAKn regs */ +#define XCHAL_HAVE_OCD_DIR_ARRAY 1 /* faster OCD option */ + + +/*---------------------------------------------------------------------- + MMU + ----------------------------------------------------------------------*/ + +/* See core-matmap.h header file for more details. */ + +#define XCHAL_HAVE_TLBS 1 /* inverse of HAVE_CACHEATTR */ +#define XCHAL_HAVE_SPANNING_WAY 1 /* one way maps I+D 4GB vaddr */ +#define XCHAL_HAVE_IDENTITY_MAP 1 /* vaddr == paddr always */ +#define XCHAL_HAVE_CACHEATTR 0 /* CACHEATTR register present */ +#define XCHAL_HAVE_MIMIC_CACHEATTR 1 /* region protection */ +#define XCHAL_HAVE_XLT_CACHEATTR 0 /* region prot. w/translation */ +#define XCHAL_HAVE_PTP_MMU 0 /* full MMU (with page table + [autorefill] and protection) + usable for an MMU-based OS */ +/* If none of the above last 4 are set, it's a custom TLB configuration. */ + +#define XCHAL_MMU_ASID_BITS 0 /* number of bits in ASIDs */ +#define XCHAL_MMU_RINGS 1 /* number of rings (1..4) */ +#define XCHAL_MMU_RING_BITS 0 /* num of bits in RING field */ + +#endif /* !XTENSA_HAL_NON_PRIVILEGED_ONLY */ + + +#endif /* _XTENSA_CORE_CONFIGURATION_H */ + diff --git a/arch/xtensa/variants/s6000/include/variant/hardware.h b/arch/xtensa/variants/s6000/include/variant/hardware.h new file mode 100644 index 000000000000..5d9ba098d84a --- /dev/null +++ b/arch/xtensa/variants/s6000/include/variant/hardware.h @@ -0,0 +1,259 @@ +#ifndef __XTENSA_S6000_HARDWARE_H +#define __XTENSA_S6000_HARDWARE_H + +#define S6_SCLK 1843200 + +#define S6_MEM_REG 0x20000000 +#define S6_MEM_EFI 0x33F00000 +#define S6_MEM_PCIE_DATARAM1 0x34000000 +#define S6_MEM_XLMI 0x37F80000 +#define S6_MEM_PIF_DATARAM1 0x37FFC000 +#define S6_MEM_GMAC 0x38000000 +#define S6_MEM_I2S 0x3A000000 +#define S6_MEM_EGIB 0x3C000000 +#define S6_MEM_PCIE_CFG 0x3E000000 +#define S6_MEM_PIF_DATARAM 0x3FFE0000 +#define S6_MEM_XLMI_DATARAM 0x3FFF0000 +#define S6_MEM_DDR 0x40000000 +#define S6_MEM_PCIE_APER 0xC0000000 +#define S6_MEM_AUX 0xF0000000 + +/* Device addresses */ + +#define S6_REG_SCB S6_MEM_REG +#define S6_REG_NB (S6_REG_SCB + 0x10000) +#define S6_REG_LMSDMA (S6_REG_SCB + 0x20000) +#define S6_REG_NI (S6_REG_SCB + 0x30000) +#define S6_REG_NIDMA (S6_REG_SCB + 0x40000) +#define S6_REG_NS (S6_REG_SCB + 0x50000) +#define S6_REG_DDR (S6_REG_SCB + 0x60000) +#define S6_REG_GREG1 (S6_REG_SCB + 0x70000) +#define S6_REG_DP (S6_REG_SCB + 0x80000) +#define S6_REG_DPDMA (S6_REG_SCB + 0x90000) +#define S6_REG_EGIB (S6_REG_SCB + 0xA0000) +#define S6_REG_PCIE (S6_REG_SCB + 0xB0000) +#define S6_REG_I2S (S6_REG_SCB + 0xC0000) +#define S6_REG_GMAC (S6_REG_SCB + 0xD0000) +#define S6_REG_HIFDMA (S6_REG_SCB + 0xE0000) +#define S6_REG_GREG2 (S6_REG_SCB + 0xF0000) + +#define S6_REG_APB S6_REG_SCB +#define S6_REG_UART (S6_REG_APB + 0x0000) +#define S6_REG_INTC (S6_REG_APB + 0x2000) +#define S6_REG_SPI (S6_REG_APB + 0x3000) +#define S6_REG_I2C (S6_REG_APB + 0x4000) +#define S6_REG_GPIO (S6_REG_APB + 0x8000) + +/* Global register block */ + +#define S6_GREG1_PLL_LOCKCLEAR 0x000 +#define S6_GREG1_PLL_LOCK_SYS 0 +#define S6_GREG1_PLL_LOCK_IO 1 +#define S6_GREG1_PLL_LOCK_AIM 2 +#define S6_GREG1_PLL_LOCK_DP0 3 +#define S6_GREG1_PLL_LOCK_DP2 4 +#define S6_GREG1_PLL_LOCK_DDR 5 +#define S6_GREG1_PLL_LOCKSTAT 0x004 +#define S6_GREG1_PLL_LOCKSTAT_CURLOCK 0 +#define S6_GREG1_PLL_LOCKSTAT_EVERUNLCK 8 +#define S6_GREG1_PLLSEL 0x010 +#define S6_GREG1_PLLSEL_AIM 0 +#define S6_GREG1_PLLSEL_AIM_DDR2 0 +#define S6_GREG1_PLLSEL_AIM_300MHZ 1 +#define S6_GREG1_PLLSEL_AIM_240MHZ 2 +#define S6_GREG1_PLLSEL_AIM_200MHZ 3 +#define S6_GREG1_PLLSEL_AIM_150MHZ 4 +#define S6_GREG1_PLLSEL_AIM_120MHZ 5 +#define S6_GREG1_PLLSEL_AIM_40MHZ 6 +#define S6_GREG1_PLLSEL_AIM_PLLAIMREF 7 +#define S6_GREG1_PLLSEL_AIM_MASK 7 +#define S6_GREG1_PLLSEL_DDR 8 +#define S6_GREG1_PLLSEL_DDR_HS 0 +#define S6_GREG1_PLLSEL_DDR_333MHZ 1 +#define S6_GREG1_PLLSEL_DDR_250MHZ 2 +#define S6_GREG1_PLLSEL_DDR_200MHZ 3 +#define S6_GREG1_PLLSEL_DDR_167MHZ 4 +#define S6_GREG1_PLLSEL_DDR_100MHZ 5 +#define S6_GREG1_PLLSEL_DDR_33MHZ 6 +#define S6_GREG1_PLLSEL_DDR_PLLIOREF 7 +#define S6_GREG1_PLLSEL_DDR_MASK 7 +#define S6_GREG1_PLLSEL_GMAC 16 +#define S6_GREG1_PLLSEL_GMAC_125MHZ 0 +#define S6_GREG1_PLLSEL_GMAC_25MHZ 1 +#define S6_GREG1_PLLSEL_GMAC_2500KHZ 2 +#define S6_GREG1_PLLSEL_GMAC_EXTERN 3 +#define S6_GREG1_PLLSEL_GMAC_MASK 3 +#define S6_GREG1_PLLSEL_GMII 18 +#define S6_GREG1_PLLSEL_GMII_111MHZ 0 +#define S6_GREG1_PLLSEL_GMII_IOREF 1 +#define S6_GREG1_PLLSEL_GMII_NONE 2 +#define S6_GREG1_PLLSEL_GMII_125MHZ 3 +#define S6_GREG1_PLLSEL_GMII_MASK 3 +#define S6_GREG1_SYSUNLOCKCNT 0x020 +#define S6_GREG1_IOUNLOCKCNT 0x024 +#define S6_GREG1_AIMUNLOCKCNT 0x028 +#define S6_GREG1_DP0UNLOCKCNT 0x02C +#define S6_GREG1_DP2UNLOCKCNT 0x030 +#define S6_GREG1_DDRUNLOCKCNT 0x034 +#define S6_GREG1_CLKBAL0 0x040 +#define S6_GREG1_CLKBAL0_LSGB 0 +#define S6_GREG1_CLKBAL0_LSPX 8 +#define S6_GREG1_CLKBAL0_MEMDO 16 +#define S6_GREG1_CLKBAL0_HSXT1 24 +#define S6_GREG1_CLKBAL1 0x044 +#define S6_GREG1_CLKBAL1_HSISEF 0 +#define S6_GREG1_CLKBAL1_HSNI 8 +#define S6_GREG1_CLKBAL1_HSNS 16 +#define S6_GREG1_CLKBAL1_HSISEFCFG 24 +#define S6_GREG1_CLKBAL2 0x048 +#define S6_GREG1_CLKBAL2_LSNB 0 +#define S6_GREG1_CLKBAL2_LSSB 8 +#define S6_GREG1_CLKBAL2_LSREST 24 +#define S6_GREG1_CLKBAL3 0x04C +#define S6_GREG1_CLKBAL3_ISEFXAD 0 +#define S6_GREG1_CLKBAL3_ISEFLMS 8 +#define S6_GREG1_CLKBAL3_ISEFISEF 16 +#define S6_GREG1_CLKBAL3_DDRDD 24 +#define S6_GREG1_CLKBAL4 0x050 +#define S6_GREG1_CLKBAL4_DDRDP 0 +#define S6_GREG1_CLKBAL4_DDRDO 8 +#define S6_GREG1_CLKBAL4_DDRNB 16 +#define S6_GREG1_CLKBAL4_DDRLMS 24 +#define S6_GREG1_BLOCKENA 0x100 +#define S6_GREG1_BLOCK_DDR 0 +#define S6_GREG1_BLOCK_DP 1 +#define S6_GREG1_BLOCK_NSNI 2 +#define S6_GREG1_BLOCK_PCIE 3 +#define S6_GREG1_BLOCK_GMAC 4 +#define S6_GREG1_BLOCK_I2S 5 +#define S6_GREG1_BLOCK_EGIB 6 +#define S6_GREG1_BLOCK_SB 7 +#define S6_GREG1_BLOCK_XT1 8 +#define S6_GREG1_CLKGATE 0x104 +#define S6_GREG1_BGATE_AIMNORTH 9 +#define S6_GREG1_BGATE_AIMEAST 10 +#define S6_GREG1_BGATE_AIMWEST 11 +#define S6_GREG1_BGATE_AIMSOUTH 12 +#define S6_GREG1_CHIPRES 0x108 +#define S6_GREG1_CHIPRES_SOFTRES 0 +#define S6_GREG1_CHIPRES_LOSTLOCK 1 +#define S6_GREG1_RESETCAUSE 0x10C +#define S6_GREG1_RESETCAUSE_RESETN 0 +#define S6_GREG1_RESETCAUSE_GLOBAL 1 +#define S6_GREG1_RESETCAUSE_WDOGTIMER 2 +#define S6_GREG1_RESETCAUSE_SWCHIP 3 +#define S6_GREG1_RESETCAUSE_PLLSYSLOSS 4 +#define S6_GREG1_RESETCAUSE_PCIE 5 +#define S6_GREG1_RESETCAUSE_CREATEDGLOB 6 +#define S6_GREG1_REFCLOCKCNT 0x110 +#define S6_GREG1_RESETTIMER 0x114 +#define S6_GREG1_NMITIMER 0x118 +#define S6_GREG1_GLOBAL_TIMER 0x11C +#define S6_GREG1_TIMER0 0x180 +#define S6_GREG1_TIMER1 0x184 +#define S6_GREG1_UARTCLOCKSEL 0x204 +#define S6_GREG1_CHIPVERSPACKG 0x208 +#define S6_GREG1_CHIPVERSPACKG_CHIPVID 0 +#define S6_GREG1_CHIPVERSPACKG_PACKSEL 8 +#define S6_GREG1_ONDIETERMCTRL 0x20C +#define S6_GREG1_ONDIETERMCTRL_WEST 0 +#define S6_GREG1_ONDIETERMCTRL_NORTH 2 +#define S6_GREG1_ONDIETERMCTRL_EAST 4 +#define S6_GREG1_ONDIETERMCTRL_SOUTH 6 +#define S6_GREG1_ONDIETERMCTRL_NONE 0 +#define S6_GREG1_ONDIETERMCTRL_75OHM 2 +#define S6_GREG1_ONDIETERMCTRL_MASK 3 +#define S6_GREG1_BOOT_CFG0 0x210 +#define S6_GREG1_BOOT_CFG0_AIMSTRONG 1 +#define S6_GREG1_BOOT_CFG0_MINIBOOTDL 2 +#define S6_GREG1_BOOT_CFG0_OCDGPIO8SET 5 +#define S6_GREG1_BOOT_CFG0_OCDGPIOENA 6 +#define S6_GREG1_BOOT_CFG0_DOWNSTREAM 7 +#define S6_GREG1_BOOT_CFG0_PLLSYSDIV 8 +#define S6_GREG1_BOOT_CFG0_PLLSYSDIV_300MHZ 1 +#define S6_GREG1_BOOT_CFG0_PLLSYSDIV_240MHZ 2 +#define S6_GREG1_BOOT_CFG0_PLLSYSDIV_200MHZ 3 +#define S6_GREG1_BOOT_CFG0_PLLSYSDIV_150MHZ 4 +#define S6_GREG1_BOOT_CFG0_PLLSYSDIV_120MHZ 5 +#define S6_GREG1_BOOT_CFG0_PLLSYSDIV_40MHZ 6 +#define S6_GREG1_BOOT_CFG0_PLLSYSDIV_MASK 7 +#define S6_GREG1_BOOT_CFG0_BALHSLMS 12 +#define S6_GREG1_BOOT_CFG0_BALHSNB 18 +#define S6_GREG1_BOOT_CFG0_BALHSXAD 24 +#define S6_GREG1_BOOT_CFG1 0x214 +#define S6_GREG1_BOOT_CFG1_PCIE1LANE 1 +#define S6_GREG1_BOOT_CFG1_MPLLPRESCALE 2 +#define S6_GREG1_BOOT_CFG1_MPLLNCY 4 +#define S6_GREG1_BOOT_CFG1_MPLLNCY5 9 +#define S6_GREG1_BOOT_CFG1_BALHSREST 14 +#define S6_GREG1_BOOT_CFG1_BALHSPSMEMS 20 +#define S6_GREG1_BOOT_CFG1_BALLSGI 26 +#define S6_GREG1_BOOT_CFG2 0x218 +#define S6_GREG1_BOOT_CFG2_PEID 0 +#define S6_GREG1_BOOT_CFG3 0x21C +#define S6_GREG1_DRAMBUSYHOLDOF 0x220 +#define S6_GREG1_DRAMBUSYHOLDOF_XT0 0 +#define S6_GREG1_DRAMBUSYHOLDOF_XT1 4 +#define S6_GREG1_DRAMBUSYHOLDOF_XT_MASK 7 +#define S6_GREG1_PCIEBAR1SIZE 0x224 +#define S6_GREG1_PCIEBAR2SIZE 0x228 +#define S6_GREG1_PCIEVENDOR 0x22C +#define S6_GREG1_PCIEDEVICE 0x230 +#define S6_GREG1_PCIEREV 0x234 +#define S6_GREG1_PCIECLASS 0x238 +#define S6_GREG1_XT1DCACHEMISS 0x240 +#define S6_GREG1_XT1ICACHEMISS 0x244 +#define S6_GREG1_HWSEMAPHORE(n) (0x400 + 4 * (n)) +#define S6_GREG1_HWSEMAPHORE_NB 16 + +/* peripheral interrupt numbers */ + +#define S6_INTC_GPIO(n) (n) /* 0..3 */ +#define S6_INTC_I2C 4 +#define S6_INTC_SPI 5 +#define S6_INTC_NB_ERR 6 +#define S6_INTC_DMA_LMSERR 7 +#define S6_INTC_DMA_LMSLOWWMRK(n) (8 + (n)) /* 0..11 */ +#define S6_INTC_DMA_LMSPENDCNT(n) (20 + (n)) /* 0..11 */ +#define S6_INTC_DMA HOSTLOWWMRK(n) (32 + (n)) /* 0..6 */ +#define S6_INTC_DMA_HOSTPENDCNT(n) (39 + (n)) /* 0..6 */ +#define S6_INTC_DMA_HOSTERR 46 +#define S6_INTC_UART(n) (47 + (n)) /* 0..1 */ +#define S6_INTC_XAD 49 +#define S6_INTC_NI_ERR 50 +#define S6_INTC_NI_INFIFOFULL 51 +#define S6_INTC_DMA_NIERR 52 +#define S6_INTC_DMA_NILOWWMRK(n) (53 + (n)) /* 0..3 */ +#define S6_INTC_DMA_NIPENDCNT(n) (57 + (n)) /* 0..3 */ +#define S6_INTC_DDR 61 +#define S6_INTC_NS_ERR 62 +#define S6_INTC_EFI_CFGERR 63 +#define S6_INTC_EFI_ISEFTEST 64 +#define S6_INTC_EFI_WRITEERR 65 +#define S6_INTC_NMI_TIMER 66 +#define S6_INTC_PLLLOCK_SYS 67 +#define S6_INTC_PLLLOCK_IO 68 +#define S6_INTC_PLLLOCK_AIM 69 +#define S6_INTC_PLLLOCK_DP0 70 +#define S6_INTC_PLLLOCK_DP2 71 +#define S6_INTC_I2S_ERR 72 +#define S6_INTC_GMAC_STAT 73 +#define S6_INTC_GMAC_ERR 74 +#define S6_INTC_GIB_ERR 75 +#define S6_INTC_PCIE_ERR 76 +#define S6_INTC_PCIE_MSI(n) (77 + (n)) /* 0..3 */ +#define S6_INTC_PCIE_INTA 81 +#define S6_INTC_PCIE_INTB 82 +#define S6_INTC_PCIE_INTC 83 +#define S6_INTC_PCIE_INTD 84 +#define S6_INTC_SW(n) (85 + (n)) /* 0..9 */ +#define S6_INTC_SW_ENABLE(n) (85 + 256 + (n)) +#define S6_INTC_DMA_DP_ERR 95 +#define S6_INTC_DMA_DPLOWWMRK(n) (96 + (n)) /* 0..3 */ +#define S6_INTC_DMA_DPPENDCNT(n) (100 + (n)) /* 0..3 */ +#define S6_INTC_DMA_DPTERMCNT(n) (104 + (n)) /* 0..3 */ +#define S6_INTC_TIMER0 108 +#define S6_INTC_TIMER1 109 +#define S6_INTC_DMA_HOSTTERMCNT(n) (110 + (n)) /* 0..6 */ + +#endif /* __XTENSA_S6000_HARDWARE_H */ diff --git a/arch/xtensa/variants/s6000/include/variant/irq.h b/arch/xtensa/variants/s6000/include/variant/irq.h new file mode 100644 index 000000000000..fa031cb0acc4 --- /dev/null +++ b/arch/xtensa/variants/s6000/include/variant/irq.h @@ -0,0 +1,9 @@ +#ifndef __XTENSA_S6000_IRQ_H +#define __XTENSA_S6000_IRQ_H + +#define NO_IRQ (-1) + +extern void variant_irq_enable(unsigned int irq); +extern void variant_irq_disable(unsigned int irq); + +#endif /* __XTENSA_S6000_IRQ_H */ diff --git a/arch/xtensa/variants/s6000/include/variant/tie-asm.h b/arch/xtensa/variants/s6000/include/variant/tie-asm.h new file mode 100644 index 000000000000..f02d0a3a2e20 --- /dev/null +++ b/arch/xtensa/variants/s6000/include/variant/tie-asm.h @@ -0,0 +1,304 @@ +/* + * This header file contains assembly-language definitions (assembly + * macros, etc.) for this specific Xtensa processor's TIE extensions + * and options. It is customized to this Xtensa processor configuration. + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 1999-2008 Tensilica Inc. + */ + +#ifndef _XTENSA_CORE_TIE_ASM_H +#define _XTENSA_CORE_TIE_ASM_H + +/* Selection parameter values for save-area save/restore macros: */ +/* Option vs. TIE: */ +#define XTHAL_SAS_TIE 0x0001 /* custom extension or coprocessor */ +#define XTHAL_SAS_OPT 0x0002 /* optional (and not a coprocessor) */ +/* Whether used automatically by compiler: */ +#define XTHAL_SAS_NOCC 0x0004 /* not used by compiler w/o special opts/code */ +#define XTHAL_SAS_CC 0x0008 /* used by compiler without special opts/code */ +/* ABI handling across function calls: */ +#define XTHAL_SAS_CALR 0x0010 /* caller-saved */ +#define XTHAL_SAS_CALE 0x0020 /* callee-saved */ +#define XTHAL_SAS_GLOB 0x0040 /* global across function calls (in thread) */ +/* Misc */ +#define XTHAL_SAS_ALL 0xFFFF /* include all default NCP contents */ + + + +/* Macro to save all non-coprocessor (extra) custom TIE and optional state + * (not including zero-overhead loop registers). + * Save area ptr (clobbered): ptr (16 byte aligned) + * Scratch regs (clobbered): at1..at4 (only first XCHAL_NCP_NUM_ATMPS needed) + */ + .macro xchal_ncp_store ptr at1 at2 at3 at4 continue=0 ofs=-1 select=XTHAL_SAS_ALL + xchal_sa_start \continue, \ofs + .ifeq (XTHAL_SAS_OPT | XTHAL_SAS_NOCC | XTHAL_SAS_CALR) & ~\select + xchal_sa_align \ptr, 0, 1024-4, 4, 4 + rsr \at1, BR // boolean option + s32i \at1, \ptr, .Lxchal_ofs_ + 0 + .set .Lxchal_ofs_, .Lxchal_ofs_ + 4 + .endif + .endm // xchal_ncp_store + +/* Macro to save all non-coprocessor (extra) custom TIE and optional state + * (not including zero-overhead loop registers). + * Save area ptr (clobbered): ptr (16 byte aligned) + * Scratch regs (clobbered): at1..at4 (only first XCHAL_NCP_NUM_ATMPS needed) + */ + .macro xchal_ncp_load ptr at1 at2 at3 at4 continue=0 ofs=-1 select=XTHAL_SAS_ALL + xchal_sa_start \continue, \ofs + .ifeq (XTHAL_SAS_OPT | XTHAL_SAS_NOCC | XTHAL_SAS_CALR) & ~\select + xchal_sa_align \ptr, 0, 1024-4, 4, 4 + l32i \at1, \ptr, .Lxchal_ofs_ + 0 + wsr \at1, BR // boolean option + .set .Lxchal_ofs_, .Lxchal_ofs_ + 4 + .endif + .endm // xchal_ncp_load + + + +#define XCHAL_NCP_NUM_ATMPS 1 + + + +/* Macro to save the state of TIE coprocessor FPU. + * Save area ptr (clobbered): ptr (16 byte aligned) + * Scratch regs (clobbered): at1..at4 (only first XCHAL_CP0_NUM_ATMPS needed) + */ +#define xchal_cp_FPU_store xchal_cp0_store +/* #define xchal_cp_FPU_store_a2 xchal_cp0_store a2 a3 a4 a5 a6 */ + .macro xchal_cp0_store ptr at1 at2 at3 at4 continue=0 ofs=-1 select=XTHAL_SAS_ALL + xchal_sa_start \continue, \ofs + .ifeq (XTHAL_SAS_TIE | XTHAL_SAS_NOCC | XTHAL_SAS_CALR) & ~\select + xchal_sa_align \ptr, 0, 0, 1, 16 + rur232 \at1 // FCR + s32i \at1, \ptr, 0 + rur233 \at1 // FSR + s32i \at1, \ptr, 4 + SSI f0, \ptr, 8 + SSI f1, \ptr, 12 + SSI f2, \ptr, 16 + SSI f3, \ptr, 20 + SSI f4, \ptr, 24 + SSI f5, \ptr, 28 + SSI f6, \ptr, 32 + SSI f7, \ptr, 36 + SSI f8, \ptr, 40 + SSI f9, \ptr, 44 + SSI f10, \ptr, 48 + SSI f11, \ptr, 52 + SSI f12, \ptr, 56 + SSI f13, \ptr, 60 + SSI f14, \ptr, 64 + SSI f15, \ptr, 68 + .set .Lxchal_ofs_, .Lxchal_ofs_ + 72 + .endif + .endm // xchal_cp0_store + +/* Macro to restore the state of TIE coprocessor FPU. + * Save area ptr (clobbered): ptr (16 byte aligned) + * Scratch regs (clobbered): at1..at4 (only first XCHAL_CP0_NUM_ATMPS needed) + */ +#define xchal_cp_FPU_load xchal_cp0_load +/* #define xchal_cp_FPU_load_a2 xchal_cp0_load a2 a3 a4 a5 a6 */ + .macro xchal_cp0_load ptr at1 at2 at3 at4 continue=0 ofs=-1 select=XTHAL_SAS_ALL + xchal_sa_start \continue, \ofs + .ifeq (XTHAL_SAS_TIE | XTHAL_SAS_NOCC | XTHAL_SAS_CALR) & ~\select + xchal_sa_align \ptr, 0, 0, 1, 16 + l32i \at1, \ptr, 0 + wur232 \at1 // FCR + l32i \at1, \ptr, 4 + wur233 \at1 // FSR + LSI f0, \ptr, 8 + LSI f1, \ptr, 12 + LSI f2, \ptr, 16 + LSI f3, \ptr, 20 + LSI f4, \ptr, 24 + LSI f5, \ptr, 28 + LSI f6, \ptr, 32 + LSI f7, \ptr, 36 + LSI f8, \ptr, 40 + LSI f9, \ptr, 44 + LSI f10, \ptr, 48 + LSI f11, \ptr, 52 + LSI f12, \ptr, 56 + LSI f13, \ptr, 60 + LSI f14, \ptr, 64 + LSI f15, \ptr, 68 + .set .Lxchal_ofs_, .Lxchal_ofs_ + 72 + .endif + .endm // xchal_cp0_load + +#define XCHAL_CP0_NUM_ATMPS 1 + +/* Macro to save the state of TIE coprocessor XAD. + * Save area ptr (clobbered): ptr (16 byte aligned) + * Scratch regs (clobbered): at1..at4 (only first XCHAL_CP6_NUM_ATMPS needed) + */ +#define xchal_cp_XAD_store xchal_cp6_store +/* #define xchal_cp_XAD_store_a2 xchal_cp6_store a2 a3 a4 a5 a6 */ + .macro xchal_cp6_store ptr at1 at2 at3 at4 continue=0 ofs=-1 select=XTHAL_SAS_ALL + xchal_sa_start \continue, \ofs + .ifeq (XTHAL_SAS_TIE | XTHAL_SAS_NOCC | XTHAL_SAS_CALR) & ~\select + xchal_sa_align \ptr, 0, 0, 1, 16 + rur0 \at1 // LDCBHI + s32i \at1, \ptr, 0 + rur1 \at1 // LDCBLO + s32i \at1, \ptr, 4 + rur2 \at1 // STCBHI + s32i \at1, \ptr, 8 + rur3 \at1 // STCBLO + s32i \at1, \ptr, 12 + rur8 \at1 // LDBRBASE + s32i \at1, \ptr, 16 + rur9 \at1 // LDBROFF + s32i \at1, \ptr, 20 + rur10 \at1 // LDBRINC + s32i \at1, \ptr, 24 + rur11 \at1 // STBRBASE + s32i \at1, \ptr, 28 + rur12 \at1 // STBROFF + s32i \at1, \ptr, 32 + rur13 \at1 // STBRINC + s32i \at1, \ptr, 36 + rur24 \at1 // SCRATCH0 + s32i \at1, \ptr, 40 + rur25 \at1 // SCRATCH1 + s32i \at1, \ptr, 44 + rur26 \at1 // SCRATCH2 + s32i \at1, \ptr, 48 + rur27 \at1 // SCRATCH3 + s32i \at1, \ptr, 52 + WRAS128I wra0, \ptr, 64 + WRAS128I wra1, \ptr, 80 + WRAS128I wra2, \ptr, 96 + WRAS128I wra3, \ptr, 112 + WRAS128I wra4, \ptr, 128 + WRAS128I wra5, \ptr, 144 + WRAS128I wra6, \ptr, 160 + WRAS128I wra7, \ptr, 176 + WRAS128I wra8, \ptr, 192 + WRAS128I wra9, \ptr, 208 + WRAS128I wra10, \ptr, 224 + WRAS128I wra11, \ptr, 240 + WRAS128I wra12, \ptr, 256 + WRAS128I wra13, \ptr, 272 + WRAS128I wra14, \ptr, 288 + WRAS128I wra15, \ptr, 304 + WRBS128I wrb0, \ptr, 320 + WRBS128I wrb1, \ptr, 336 + WRBS128I wrb2, \ptr, 352 + WRBS128I wrb3, \ptr, 368 + WRBS128I wrb4, \ptr, 384 + WRBS128I wrb5, \ptr, 400 + WRBS128I wrb6, \ptr, 416 + WRBS128I wrb7, \ptr, 432 + WRBS128I wrb8, \ptr, 448 + WRBS128I wrb9, \ptr, 464 + WRBS128I wrb10, \ptr, 480 + WRBS128I wrb11, \ptr, 496 + WRBS128I wrb12, \ptr, 512 + WRBS128I wrb13, \ptr, 528 + WRBS128I wrb14, \ptr, 544 + WRBS128I wrb15, \ptr, 560 + .set .Lxchal_ofs_, .Lxchal_ofs_ + 576 + .endif + .endm // xchal_cp6_store + +/* Macro to restore the state of TIE coprocessor XAD. + * Save area ptr (clobbered): ptr (16 byte aligned) + * Scratch regs (clobbered): at1..at4 (only first XCHAL_CP6_NUM_ATMPS needed) + */ +#define xchal_cp_XAD_load xchal_cp6_load +/* #define xchal_cp_XAD_load_a2 xchal_cp6_load a2 a3 a4 a5 a6 */ + .macro xchal_cp6_load ptr at1 at2 at3 at4 continue=0 ofs=-1 select=XTHAL_SAS_ALL + xchal_sa_start \continue, \ofs + .ifeq (XTHAL_SAS_TIE | XTHAL_SAS_NOCC | XTHAL_SAS_CALR) & ~\select + xchal_sa_align \ptr, 0, 0, 1, 16 + l32i \at1, \ptr, 0 + wur0 \at1 // LDCBHI + l32i \at1, \ptr, 4 + wur1 \at1 // LDCBLO + l32i \at1, \ptr, 8 + wur2 \at1 // STCBHI + l32i \at1, \ptr, 12 + wur3 \at1 // STCBLO + l32i \at1, \ptr, 16 + wur8 \at1 // LDBRBASE + l32i \at1, \ptr, 20 + wur9 \at1 // LDBROFF + l32i \at1, \ptr, 24 + wur10 \at1 // LDBRINC + l32i \at1, \ptr, 28 + wur11 \at1 // STBRBASE + l32i \at1, \ptr, 32 + wur12 \at1 // STBROFF + l32i \at1, \ptr, 36 + wur13 \at1 // STBRINC + l32i \at1, \ptr, 40 + wur24 \at1 // SCRATCH0 + l32i \at1, \ptr, 44 + wur25 \at1 // SCRATCH1 + l32i \at1, \ptr, 48 + wur26 \at1 // SCRATCH2 + l32i \at1, \ptr, 52 + wur27 \at1 // SCRATCH3 + WRBL128I wrb0, \ptr, 320 + WRBL128I wrb1, \ptr, 336 + WRBL128I wrb2, \ptr, 352 + WRBL128I wrb3, \ptr, 368 + WRBL128I wrb4, \ptr, 384 + WRBL128I wrb5, \ptr, 400 + WRBL128I wrb6, \ptr, 416 + WRBL128I wrb7, \ptr, 432 + WRBL128I wrb8, \ptr, 448 + WRBL128I wrb9, \ptr, 464 + WRBL128I wrb10, \ptr, 480 + WRBL128I wrb11, \ptr, 496 + WRBL128I wrb12, \ptr, 512 + WRBL128I wrb13, \ptr, 528 + WRBL128I wrb14, \ptr, 544 + WRBL128I wrb15, \ptr, 560 + WRAL128I wra0, \ptr, 64 + WRAL128I wra1, \ptr, 80 + WRAL128I wra2, \ptr, 96 + WRAL128I wra3, \ptr, 112 + WRAL128I wra4, \ptr, 128 + WRAL128I wra5, \ptr, 144 + WRAL128I wra6, \ptr, 160 + WRAL128I wra7, \ptr, 176 + WRAL128I wra8, \ptr, 192 + WRAL128I wra9, \ptr, 208 + WRAL128I wra10, \ptr, 224 + WRAL128I wra11, \ptr, 240 + WRAL128I wra12, \ptr, 256 + WRAL128I wra13, \ptr, 272 + WRAL128I wra14, \ptr, 288 + WRAL128I wra15, \ptr, 304 + .set .Lxchal_ofs_, .Lxchal_ofs_ + 576 + .endif + .endm // xchal_cp6_load + +#define XCHAL_CP6_NUM_ATMPS 1 +#define XCHAL_SA_NUM_ATMPS 1 + + /* Empty macros for unconfigured coprocessors: */ + .macro xchal_cp1_store p a b c d continue=0 ofs=-1 select=-1 ; .endm + .macro xchal_cp1_load p a b c d continue=0 ofs=-1 select=-1 ; .endm + .macro xchal_cp2_store p a b c d continue=0 ofs=-1 select=-1 ; .endm + .macro xchal_cp2_load p a b c d continue=0 ofs=-1 select=-1 ; .endm + .macro xchal_cp3_store p a b c d continue=0 ofs=-1 select=-1 ; .endm + .macro xchal_cp3_load p a b c d continue=0 ofs=-1 select=-1 ; .endm + .macro xchal_cp4_store p a b c d continue=0 ofs=-1 select=-1 ; .endm + .macro xchal_cp4_load p a b c d continue=0 ofs=-1 select=-1 ; .endm + .macro xchal_cp5_store p a b c d continue=0 ofs=-1 select=-1 ; .endm + .macro xchal_cp5_load p a b c d continue=0 ofs=-1 select=-1 ; .endm + .macro xchal_cp7_store p a b c d continue=0 ofs=-1 select=-1 ; .endm + .macro xchal_cp7_load p a b c d continue=0 ofs=-1 select=-1 ; .endm + +#endif /*_XTENSA_CORE_TIE_ASM_H*/ + diff --git a/arch/xtensa/variants/s6000/include/variant/tie.h b/arch/xtensa/variants/s6000/include/variant/tie.h new file mode 100644 index 000000000000..be7ea843d5df --- /dev/null +++ b/arch/xtensa/variants/s6000/include/variant/tie.h @@ -0,0 +1,191 @@ +/* + * This header file describes this specific Xtensa processor's TIE extensions + * that extend basic Xtensa core functionality. It is customized to this + * Xtensa processor configuration. + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 1999-2008 Tensilica Inc. + */ + +#ifndef _XTENSA_CORE_TIE_H +#define _XTENSA_CORE_TIE_H + +#define XCHAL_CP_NUM 2 /* number of coprocessors */ +#define XCHAL_CP_MAX 7 /* max CP ID + 1 (0 if none) */ +#define XCHAL_CP_MASK 0x41 /* bitmask of all CPs by ID */ +#define XCHAL_CP_PORT_MASK 0x00 /* bitmask of only port CPs */ + +/* Basic parameters of each coprocessor: */ +#define XCHAL_CP0_NAME "FPU" +#define XCHAL_CP0_IDENT FPU +#define XCHAL_CP0_SA_SIZE 72 /* size of state save area */ +#define XCHAL_CP0_SA_ALIGN 4 /* min alignment of save area */ +#define XCHAL_CP_ID_FPU 0 /* coprocessor ID (0..7) */ +#define XCHAL_CP6_NAME "XAD" +#define XCHAL_CP6_IDENT XAD +#define XCHAL_CP6_SA_SIZE 576 /* size of state save area */ +#define XCHAL_CP6_SA_ALIGN 16 /* min alignment of save area */ +#define XCHAL_CP_ID_XAD 6 /* coprocessor ID (0..7) */ + +/* Filler info for unassigned coprocessors, to simplify arrays etc: */ +#define XCHAL_CP1_SA_SIZE 0 +#define XCHAL_CP1_SA_ALIGN 1 +#define XCHAL_CP2_SA_SIZE 0 +#define XCHAL_CP2_SA_ALIGN 1 +#define XCHAL_CP3_SA_SIZE 0 +#define XCHAL_CP3_SA_ALIGN 1 +#define XCHAL_CP4_SA_SIZE 0 +#define XCHAL_CP4_SA_ALIGN 1 +#define XCHAL_CP5_SA_SIZE 0 +#define XCHAL_CP5_SA_ALIGN 1 +#define XCHAL_CP7_SA_SIZE 0 +#define XCHAL_CP7_SA_ALIGN 1 + +/* Save area for non-coprocessor optional and custom (TIE) state: */ +#define XCHAL_NCP_SA_SIZE 4 +#define XCHAL_NCP_SA_ALIGN 4 + +/* Total save area for optional and custom state (NCP + CPn): */ +#define XCHAL_TOTAL_SA_SIZE 672 /* with 16-byte align padding */ +#define XCHAL_TOTAL_SA_ALIGN 16 /* actual minimum alignment */ + +/* + * Detailed contents of save areas. + * NOTE: caller must define the XCHAL_SA_REG macro (not defined here) + * before expanding the XCHAL_xxx_SA_LIST() macros. + * + * XCHAL_SA_REG(s,ccused,abikind,kind,opt,name,galign,align,asize, + * dbnum,base,regnum,bitsz,gapsz,reset,x...) + * + * s = passed from XCHAL_*_LIST(s), eg. to select how to expand + * ccused = set if used by compiler without special options or code + * abikind = 0 (caller-saved), 1 (callee-saved), or 2 (thread-global) + * kind = 0 (special reg), 1 (TIE user reg), or 2 (TIE regfile reg) + * opt = 0 (custom TIE extension or coprocessor), or 1 (optional reg) + * name = lowercase reg name (no quotes) + * galign = group byte alignment (power of 2) (galign >= align) + * align = register byte alignment (power of 2) + * asize = allocated size in bytes (asize*8 == bitsz + gapsz + padsz) + * (not including any pad bytes required to galign this or next reg) + * dbnum = unique target number f/debug (see <xtensa-libdb-macros.h>) + * base = reg shortname w/o index (or sr=special, ur=TIE user reg) + * regnum = reg index in regfile, or special/TIE-user reg number + * bitsz = number of significant bits (regfile width, or ur/sr mask bits) + * gapsz = intervening bits, if bitsz bits not stored contiguously + * (padsz = pad bits at end [TIE regfile] or at msbits [ur,sr] of asize) + * reset = register reset value (or 0 if undefined at reset) + * x = reserved for future use (0 until then) + * + * To filter out certain registers, e.g. to expand only the non-global + * registers used by the compiler, you can do something like this: + * + * #define XCHAL_SA_REG(s,ccused,p...) SELCC##ccused(p) + * #define SELCC0(p...) + * #define SELCC1(abikind,p...) SELAK##abikind(p) + * #define SELAK0(p...) REG(p) + * #define SELAK1(p...) REG(p) + * #define SELAK2(p...) + * #define REG(kind,tie,name,galn,aln,asz,csz,dbnum,base,rnum,bsz,rst,x...) \ + * ...what you want to expand... + */ + +#define XCHAL_NCP_SA_NUM 1 +#define XCHAL_NCP_SA_LIST(s) \ + XCHAL_SA_REG(s,0,0,0,1, br, 4, 4, 4,0x0204, sr,4 , 16,0,0,0) + +#define XCHAL_CP0_SA_NUM 18 +#define XCHAL_CP0_SA_LIST(s) \ + XCHAL_SA_REG(s,0,0,1,0, fcr, 4, 4, 4,0x03E8, ur,232, 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,1,0, fsr, 4, 4, 4,0x03E9, ur,233, 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, f0, 4, 4, 4,0x0030, f,0 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, f1, 4, 4, 4,0x0031, f,1 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, f2, 4, 4, 4,0x0032, f,2 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, f3, 4, 4, 4,0x0033, f,3 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, f4, 4, 4, 4,0x0034, f,4 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, f5, 4, 4, 4,0x0035, f,5 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, f6, 4, 4, 4,0x0036, f,6 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, f7, 4, 4, 4,0x0037, f,7 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, f8, 4, 4, 4,0x0038, f,8 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, f9, 4, 4, 4,0x0039, f,9 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, f10, 4, 4, 4,0x003A, f,10 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, f11, 4, 4, 4,0x003B, f,11 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, f12, 4, 4, 4,0x003C, f,12 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, f13, 4, 4, 4,0x003D, f,13 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, f14, 4, 4, 4,0x003E, f,14 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, f15, 4, 4, 4,0x003F, f,15 , 32,0,0,0) + +#define XCHAL_CP1_SA_NUM 0 +#define XCHAL_CP1_SA_LIST(s) /* empty */ + +#define XCHAL_CP2_SA_NUM 0 +#define XCHAL_CP2_SA_LIST(s) /* empty */ + +#define XCHAL_CP3_SA_NUM 0 +#define XCHAL_CP3_SA_LIST(s) /* empty */ + +#define XCHAL_CP4_SA_NUM 0 +#define XCHAL_CP4_SA_LIST(s) /* empty */ + +#define XCHAL_CP5_SA_NUM 0 +#define XCHAL_CP5_SA_LIST(s) /* empty */ + +#define XCHAL_CP6_SA_NUM 46 +#define XCHAL_CP6_SA_LIST(s) \ + XCHAL_SA_REG(s,0,0,1,0, ldcbhi,16, 4, 4,0x0300, ur,0 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,1,0, ldcblo, 4, 4, 4,0x0301, ur,1 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,1,0, stcbhi, 4, 4, 4,0x0302, ur,2 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,1,0, stcblo, 4, 4, 4,0x0303, ur,3 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,1,0, ldbrbase, 4, 4, 4,0x0308, ur,8 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,1,0, ldbroff, 4, 4, 4,0x0309, ur,9 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,1,0, ldbrinc, 4, 4, 4,0x030A, ur,10 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,1,0, stbrbase, 4, 4, 4,0x030B, ur,11 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,1,0, stbroff, 4, 4, 4,0x030C, ur,12 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,1,0, stbrinc, 4, 4, 4,0x030D, ur,13 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,1,0, scratch0, 4, 4, 4,0x0318, ur,24 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,1,0, scratch1, 4, 4, 4,0x0319, ur,25 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,1,0, scratch2, 4, 4, 4,0x031A, ur,26 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,1,0, scratch3, 4, 4, 4,0x031B, ur,27 , 32,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wra0,16,16,16,0x1010, wra,0 ,128,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wra1,16,16,16,0x1011, wra,1 ,128,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wra2,16,16,16,0x1012, wra,2 ,128,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wra3,16,16,16,0x1013, wra,3 ,128,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wra4,16,16,16,0x1014, wra,4 ,128,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wra5,16,16,16,0x1015, wra,5 ,128,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wra6,16,16,16,0x1016, wra,6 ,128,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wra7,16,16,16,0x1017, wra,7 ,128,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wra8,16,16,16,0x1018, wra,8 ,128,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wra9,16,16,16,0x1019, wra,9 ,128,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wra10,16,16,16,0x101A, wra,10 ,128,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wra11,16,16,16,0x101B, wra,11 ,128,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wra12,16,16,16,0x101C, wra,12 ,128,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wra13,16,16,16,0x101D, wra,13 ,128,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wra14,16,16,16,0x101E, wra,14 ,128,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wra15,16,16,16,0x101F, wra,15 ,128,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wrb0,16,16,16,0x1020, wrb,0 ,128,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wrb1,16,16,16,0x1021, wrb,1 ,128,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wrb2,16,16,16,0x1022, wrb,2 ,128,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wrb3,16,16,16,0x1023, wrb,3 ,128,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wrb4,16,16,16,0x1024, wrb,4 ,128,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wrb5,16,16,16,0x1025, wrb,5 ,128,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wrb6,16,16,16,0x1026, wrb,6 ,128,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wrb7,16,16,16,0x1027, wrb,7 ,128,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wrb8,16,16,16,0x1028, wrb,8 ,128,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wrb9,16,16,16,0x1029, wrb,9 ,128,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wrb10,16,16,16,0x102A, wrb,10 ,128,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wrb11,16,16,16,0x102B, wrb,11 ,128,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wrb12,16,16,16,0x102C, wrb,12 ,128,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wrb13,16,16,16,0x102D, wrb,13 ,128,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wrb14,16,16,16,0x102E, wrb,14 ,128,0,0,0) \ + XCHAL_SA_REG(s,0,0,2,0, wrb15,16,16,16,0x102F, wrb,15 ,128,0,0,0) + +#define XCHAL_CP7_SA_NUM 0 +#define XCHAL_CP7_SA_LIST(s) /* empty */ + +/* Byte length of instruction from its first nibble (op0 field), per FLIX. */ +#define XCHAL_OP0_FORMAT_LENGTHS 3,3,3,3,3,3,3,3,2,2,2,2,2,2,8,8 + +#endif /*_XTENSA_CORE_TIE_H*/ + diff --git a/arch/xtensa/variants/s6000/irq.c b/arch/xtensa/variants/s6000/irq.c new file mode 100644 index 000000000000..6651e3285fcf --- /dev/null +++ b/arch/xtensa/variants/s6000/irq.c @@ -0,0 +1,74 @@ +/* + * s6000 irq crossbar + * + * Copyright (c) 2009 emlix GmbH + * Authors: Johannes Weiner <jw@emlix.com> + * Oskar Schirmer <os@emlix.com> + */ +#include <linux/io.h> +#include <asm/irq.h> +#include <variant/hardware.h> + +/* S6_REG_INTC */ +#define INTC_STATUS 0x000 +#define INTC_RAW 0x010 +#define INTC_STATUS_AG 0x100 +#define INTC_CFG(n) (0x200 + 4 * (n)) + +/* + * The s6000 has a crossbar that multiplexes interrupt output lines + * from the peripherals to input lines on the xtensa core. + * + * We leave the mapping decisions to the platform as it depends on the + * actually connected peripherals which distribution makes sense. + */ +extern const signed char *platform_irq_mappings[NR_IRQS]; + +static unsigned long scp_to_intc_enable[] = { +#define TO_INTC_ENABLE(n) (((n) << 1) + 1) + TO_INTC_ENABLE(0), + TO_INTC_ENABLE(1), + TO_INTC_ENABLE(2), + TO_INTC_ENABLE(3), + TO_INTC_ENABLE(4), + TO_INTC_ENABLE(5), + TO_INTC_ENABLE(6), + TO_INTC_ENABLE(7), + TO_INTC_ENABLE(8), + TO_INTC_ENABLE(9), + TO_INTC_ENABLE(10), + TO_INTC_ENABLE(11), + TO_INTC_ENABLE(12), + -1, + -1, + TO_INTC_ENABLE(13), + -1, + TO_INTC_ENABLE(14), + -1, + TO_INTC_ENABLE(15), +#undef TO_INTC_ENABLE +}; + +static void irq_set(unsigned int irq, int enable) +{ + unsigned long en; + const signed char *m = platform_irq_mappings[irq]; + + if (!m) + return; + en = enable ? scp_to_intc_enable[irq] : 0; + while (*m >= 0) { + writel(en, S6_REG_INTC + INTC_CFG(*m)); + m++; + } +} + +void variant_irq_enable(unsigned int irq) +{ + irq_set(irq, 1); +} + +void variant_irq_disable(unsigned int irq) +{ + irq_set(irq, 0); +} diff --git a/block/Kconfig b/block/Kconfig index 0cbb3b88b59a..e7d12782bcfb 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -44,22 +44,6 @@ config LBD If unsure, say N. -config BLK_DEV_IO_TRACE - bool "Support for tracing block io actions" - depends on SYSFS - select RELAY - select DEBUG_FS - select TRACEPOINTS - help - Say Y here if you want to be able to trace the block layer actions - on a given queue. Tracing allows you to see any traffic happening - on a block device queue. For more information (and the userspace - support tools needed), fetch the blktrace tools from: - - git://git.kernel.dk/blktrace.git - - If unsure, say N. - config BLK_DEV_BSG bool "Block layer SG support v4 (EXPERIMENTAL)" depends on EXPERIMENTAL diff --git a/block/Makefile b/block/Makefile index bfe73049f939..e9fa4dd690f2 100644 --- a/block/Makefile +++ b/block/Makefile @@ -13,6 +13,5 @@ obj-$(CONFIG_IOSCHED_AS) += as-iosched.o obj-$(CONFIG_IOSCHED_DEADLINE) += deadline-iosched.o obj-$(CONFIG_IOSCHED_CFQ) += cfq-iosched.o -obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o obj-$(CONFIG_BLOCK_COMPAT) += compat_ioctl.o obj-$(CONFIG_BLK_DEV_INTEGRITY) += blk-integrity.o diff --git a/block/blk-softirq.c b/block/blk-softirq.c index ce0efc6b26dc..ee9c21602228 100644 --- a/block/blk-softirq.c +++ b/block/blk-softirq.c @@ -64,7 +64,7 @@ static int raise_blk_irq(int cpu, struct request *rq) data->info = rq; data->flags = 0; - __smp_call_function_single(cpu, data); + __smp_call_function_single(cpu, data, 0); return 0; } diff --git a/block/blk.h b/block/blk.h index 0dce92c37496..3ee94358b43d 100644 --- a/block/blk.h +++ b/block/blk.h @@ -102,7 +102,7 @@ static inline int blk_cpu_to_group(int cpu) const struct cpumask *mask = cpu_coregroup_mask(cpu); return cpumask_first(mask); #elif defined(CONFIG_SCHED_SMT) - return first_cpu(per_cpu(cpu_sibling_map, cpu)); + return cpumask_first(topology_thread_cpumask(cpu)); #else return cpu; #endif diff --git a/crypto/async_tx/async_tx.c b/crypto/async_tx/async_tx.c index f21147f3626a..06eb6cc09fef 100644 --- a/crypto/async_tx/async_tx.c +++ b/crypto/async_tx/async_tx.c @@ -30,7 +30,7 @@ #ifdef CONFIG_DMA_ENGINE static int __init async_tx_init(void) { - dmaengine_get(); + async_dmaengine_get(); printk(KERN_INFO "async_tx: api initialized (async)\n"); @@ -39,7 +39,7 @@ static int __init async_tx_init(void) static void __exit async_tx_exit(void) { - dmaengine_put(); + async_dmaengine_put(); } /** @@ -56,7 +56,7 @@ __async_tx_find_channel(struct dma_async_tx_descriptor *depend_tx, if (depend_tx && dma_has_cap(tx_type, depend_tx->chan->device->cap_mask)) return depend_tx->chan; - return dma_find_channel(tx_type); + return async_dma_find_channel(tx_type); } EXPORT_SYMBOL_GPL(__async_tx_find_channel); #else diff --git a/crypto/async_tx/async_xor.c b/crypto/async_tx/async_xor.c index 595b78672b36..95fe2c8d6c51 100644 --- a/crypto/async_tx/async_xor.c +++ b/crypto/async_tx/async_xor.c @@ -30,11 +30,8 @@ #include <linux/raid/xor.h> #include <linux/async_tx.h> -/* do_async_xor - dma map the pages and perform the xor with an engine. - * This routine is marked __always_inline so it can be compiled away - * when CONFIG_DMA_ENGINE=n - */ -static __always_inline struct dma_async_tx_descriptor * +/* do_async_xor - dma map the pages and perform the xor with an engine */ +static __async_inline struct dma_async_tx_descriptor * do_async_xor(struct dma_chan *chan, struct page *dest, struct page **src_list, unsigned int offset, int src_cnt, size_t len, enum async_tx_flags flags, diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c index c11f9aeca706..1ba9d61ea69a 100644 --- a/drivers/acpi/thermal.c +++ b/drivers/acpi/thermal.c @@ -367,7 +367,7 @@ static int acpi_thermal_trips_update(struct acpi_thermal *tz, int flag) /* * Treat freezing temperatures as invalid as well; some * BIOSes return really low values and cause reboots at startup. - * Below zero (Celcius) values clearly aren't right for sure.. + * Below zero (Celsius) values clearly aren't right for sure.. * ... so lets discard those as invalid. */ if (ACPI_FAILURE(status) || diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig index 0bcf26464670..9120717c0701 100644 --- a/drivers/ata/Kconfig +++ b/drivers/ata/Kconfig @@ -86,7 +86,7 @@ config ATA_SFF For users with exclusively modern controllers like AHCI, Silicon Image 3124, or Marvell 6440, you may choose to - disable this uneeded SFF support. + disable this unneeded SFF support. If unsure, say Y. diff --git a/drivers/base/node.c b/drivers/base/node.c index f8f578a71b25..40b809742a1c 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -24,7 +24,7 @@ static struct sysdev_class node_class = { static ssize_t node_read_cpumap(struct sys_device *dev, int type, char *buf) { struct node *node_dev = to_node(dev); - node_to_cpumask_ptr(mask, node_dev->sysdev.id); + const struct cpumask *mask = cpumask_of_node(node_dev->sysdev.id); int len; /* 2008/04/07: buf currently PAGE_SIZE, need 9 chars per 32 bits. */ diff --git a/drivers/base/sys.c b/drivers/base/sys.c index 76ce75bad91e..3236b434b964 100644 --- a/drivers/base/sys.c +++ b/drivers/base/sys.c @@ -300,7 +300,7 @@ void sysdev_unregister(struct sys_device *sysdev) * and the class driver. * * Note: The list is iterated in reverse order, so that we shut down - * child devices before we shut down thier parents. The list ordering + * child devices before we shut down their parents. The list ordering * is guaranteed by virtue of the fact that child devices are registered * after their parents. */ diff --git a/drivers/char/bsr.c b/drivers/char/bsr.c index f6094ae0ef33..140ea10ecb88 100644 --- a/drivers/char/bsr.c +++ b/drivers/char/bsr.c @@ -140,7 +140,7 @@ static int bsr_open(struct inode * inode, struct file * filp) return 0; } -const static struct file_operations bsr_fops = { +static const struct file_operations bsr_fops = { .owner = THIS_MODULE, .mmap = bsr_mmap, .open = bsr_open, diff --git a/drivers/char/sysrq.c b/drivers/char/sysrq.c index ebea9b2c30a5..6de020d078e1 100644 --- a/drivers/char/sysrq.c +++ b/drivers/char/sysrq.c @@ -283,7 +283,7 @@ static void sysrq_ftrace_dump(int key, struct tty_struct *tty) } static struct sysrq_key_op sysrq_ftrace_dump_op = { .handler = sysrq_ftrace_dump, - .help_msg = "dumpZ-ftrace-buffer", + .help_msg = "dump-ftrace-buffer(Z)", .action_msg = "Dump ftrace buffer", .enable_mask = SYSRQ_ENABLE_DUMP, }; diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index 48ea59e79672..3b3c01b6f1ee 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -98,6 +98,17 @@ config NET_DMA Say Y here if you enabled INTEL_IOATDMA or FSL_DMA, otherwise say N. +config ASYNC_TX_DMA + bool "Async_tx: Offload support for the async_tx api" + depends on DMA_ENGINE + help + This allows the async_tx api to take advantage of offload engines for + memcpy, memset, xor, and raid6 p+q operations. If your platform has + a dma engine that can perform raid operations and you have enabled + MD_RAID456 say Y. + + If unsure, say N. + config DMATEST tristate "DMA Test client" depends on DMA_ENGINE diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index 280a9d263eb3..92438e9dacc3 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -507,6 +507,7 @@ struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, dma_filter_fn fn, v * published in the general-purpose allocator */ dma_cap_set(DMA_PRIVATE, device->cap_mask); + device->privatecnt++; err = dma_chan_get(chan); if (err == -ENODEV) { @@ -518,6 +519,8 @@ struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, dma_filter_fn fn, v dma_chan_name(chan), err); else break; + if (--device->privatecnt == 0) + dma_cap_clear(DMA_PRIVATE, device->cap_mask); chan->private = NULL; chan = NULL; } @@ -537,6 +540,9 @@ void dma_release_channel(struct dma_chan *chan) WARN_ONCE(chan->client_count != 1, "chan reference count %d != 1\n", chan->client_count); dma_chan_put(chan); + /* drop PRIVATE cap enabled by __dma_request_channel() */ + if (--chan->device->privatecnt == 0) + dma_cap_clear(DMA_PRIVATE, chan->device->cap_mask); chan->private = NULL; mutex_unlock(&dma_list_mutex); } @@ -602,6 +608,24 @@ void dmaengine_put(void) } EXPORT_SYMBOL(dmaengine_put); +static int get_dma_id(struct dma_device *device) +{ + int rc; + + idr_retry: + if (!idr_pre_get(&dma_idr, GFP_KERNEL)) + return -ENOMEM; + mutex_lock(&dma_list_mutex); + rc = idr_get_new(&dma_idr, NULL, &device->dev_id); + mutex_unlock(&dma_list_mutex); + if (rc == -EAGAIN) + goto idr_retry; + else if (rc != 0) + return rc; + + return 0; +} + /** * dma_async_device_register - registers DMA devices found * @device: &dma_device @@ -640,27 +664,25 @@ int dma_async_device_register(struct dma_device *device) idr_ref = kmalloc(sizeof(*idr_ref), GFP_KERNEL); if (!idr_ref) return -ENOMEM; - atomic_set(idr_ref, 0); - idr_retry: - if (!idr_pre_get(&dma_idr, GFP_KERNEL)) - return -ENOMEM; - mutex_lock(&dma_list_mutex); - rc = idr_get_new(&dma_idr, NULL, &device->dev_id); - mutex_unlock(&dma_list_mutex); - if (rc == -EAGAIN) - goto idr_retry; - else if (rc != 0) + rc = get_dma_id(device); + if (rc != 0) { + kfree(idr_ref); return rc; + } + + atomic_set(idr_ref, 0); /* represent channels in sysfs. Probably want devs too */ list_for_each_entry(chan, &device->channels, device_node) { + rc = -ENOMEM; chan->local = alloc_percpu(typeof(*chan->local)); if (chan->local == NULL) - continue; + goto err_out; chan->dev = kzalloc(sizeof(*chan->dev), GFP_KERNEL); if (chan->dev == NULL) { free_percpu(chan->local); - continue; + chan->local = NULL; + goto err_out; } chan->chan_id = chancnt++; @@ -677,6 +699,8 @@ int dma_async_device_register(struct dma_device *device) if (rc) { free_percpu(chan->local); chan->local = NULL; + kfree(chan->dev); + atomic_dec(idr_ref); goto err_out; } chan->client_count = 0; @@ -701,12 +725,23 @@ int dma_async_device_register(struct dma_device *device) } } list_add_tail_rcu(&device->global_node, &dma_device_list); + if (dma_has_cap(DMA_PRIVATE, device->cap_mask)) + device->privatecnt++; /* Always private */ dma_channel_rebalance(); mutex_unlock(&dma_list_mutex); return 0; err_out: + /* if we never registered a channel just release the idr */ + if (atomic_read(idr_ref) == 0) { + mutex_lock(&dma_list_mutex); + idr_remove(&dma_idr, device->dev_id); + mutex_unlock(&dma_list_mutex); + kfree(idr_ref); + return rc; + } + list_for_each_entry(chan, &device->channels, device_node) { if (chan->local == NULL) continue; @@ -893,6 +928,7 @@ void dma_async_tx_descriptor_init(struct dma_async_tx_descriptor *tx, { tx->chan = chan; spin_lock_init(&tx->lock); + INIT_LIST_HEAD(&tx->tx_list); } EXPORT_SYMBOL(dma_async_tx_descriptor_init); diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c index e190d8b30700..a27c0fb1bc11 100644 --- a/drivers/dma/dmatest.c +++ b/drivers/dma/dmatest.c @@ -38,6 +38,11 @@ module_param(max_channels, uint, S_IRUGO); MODULE_PARM_DESC(max_channels, "Maximum number of channels to use (default: all)"); +static unsigned int xor_sources = 3; +module_param(xor_sources, uint, S_IRUGO); +MODULE_PARM_DESC(xor_sources, + "Number of xor source buffers (default: 3)"); + /* * Initialization patterns. All bytes in the source buffer has bit 7 * set, all bytes in the destination buffer has bit 7 cleared. @@ -59,8 +64,9 @@ struct dmatest_thread { struct list_head node; struct task_struct *task; struct dma_chan *chan; - u8 *srcbuf; - u8 *dstbuf; + u8 **srcs; + u8 **dsts; + enum dma_transaction_type type; }; struct dmatest_chan { @@ -98,30 +104,37 @@ static unsigned long dmatest_random(void) return buf; } -static void dmatest_init_srcbuf(u8 *buf, unsigned int start, unsigned int len) +static void dmatest_init_srcs(u8 **bufs, unsigned int start, unsigned int len) { unsigned int i; - - for (i = 0; i < start; i++) - buf[i] = PATTERN_SRC | (~i & PATTERN_COUNT_MASK); - for ( ; i < start + len; i++) - buf[i] = PATTERN_SRC | PATTERN_COPY - | (~i & PATTERN_COUNT_MASK);; - for ( ; i < test_buf_size; i++) - buf[i] = PATTERN_SRC | (~i & PATTERN_COUNT_MASK); + u8 *buf; + + for (; (buf = *bufs); bufs++) { + for (i = 0; i < start; i++) + buf[i] = PATTERN_SRC | (~i & PATTERN_COUNT_MASK); + for ( ; i < start + len; i++) + buf[i] = PATTERN_SRC | PATTERN_COPY + | (~i & PATTERN_COUNT_MASK);; + for ( ; i < test_buf_size; i++) + buf[i] = PATTERN_SRC | (~i & PATTERN_COUNT_MASK); + buf++; + } } -static void dmatest_init_dstbuf(u8 *buf, unsigned int start, unsigned int len) +static void dmatest_init_dsts(u8 **bufs, unsigned int start, unsigned int len) { unsigned int i; - - for (i = 0; i < start; i++) - buf[i] = PATTERN_DST | (~i & PATTERN_COUNT_MASK); - for ( ; i < start + len; i++) - buf[i] = PATTERN_DST | PATTERN_OVERWRITE - | (~i & PATTERN_COUNT_MASK); - for ( ; i < test_buf_size; i++) - buf[i] = PATTERN_DST | (~i & PATTERN_COUNT_MASK); + u8 *buf; + + for (; (buf = *bufs); bufs++) { + for (i = 0; i < start; i++) + buf[i] = PATTERN_DST | (~i & PATTERN_COUNT_MASK); + for ( ; i < start + len; i++) + buf[i] = PATTERN_DST | PATTERN_OVERWRITE + | (~i & PATTERN_COUNT_MASK); + for ( ; i < test_buf_size; i++) + buf[i] = PATTERN_DST | (~i & PATTERN_COUNT_MASK); + } } static void dmatest_mismatch(u8 actual, u8 pattern, unsigned int index, @@ -150,23 +163,30 @@ static void dmatest_mismatch(u8 actual, u8 pattern, unsigned int index, thread_name, index, expected, actual); } -static unsigned int dmatest_verify(u8 *buf, unsigned int start, +static unsigned int dmatest_verify(u8 **bufs, unsigned int start, unsigned int end, unsigned int counter, u8 pattern, bool is_srcbuf) { unsigned int i; unsigned int error_count = 0; u8 actual; - - for (i = start; i < end; i++) { - actual = buf[i]; - if (actual != (pattern | (~counter & PATTERN_COUNT_MASK))) { - if (error_count < 32) - dmatest_mismatch(actual, pattern, i, counter, - is_srcbuf); - error_count++; + u8 expected; + u8 *buf; + unsigned int counter_orig = counter; + + for (; (buf = *bufs); bufs++) { + counter = counter_orig; + for (i = start; i < end; i++) { + actual = buf[i]; + expected = pattern | (~counter & PATTERN_COUNT_MASK); + if (actual != expected) { + if (error_count < 32) + dmatest_mismatch(actual, pattern, i, + counter, is_srcbuf); + error_count++; + } + counter++; } - counter++; } if (error_count > 32) @@ -176,12 +196,17 @@ static unsigned int dmatest_verify(u8 *buf, unsigned int start, return error_count; } +static void dmatest_callback(void *completion) +{ + complete(completion); +} + /* * This function repeatedly tests DMA transfers of various lengths and - * offsets until it is told to exit by kthread_stop(). There may be - * multiple threads running this function in parallel for a single - * channel, and there may be multiple channels being tested in - * parallel. + * offsets for a given operation type until it is told to exit by + * kthread_stop(). There may be multiple threads running this function + * in parallel for a single channel, and there may be multiple channels + * being tested in parallel. * * Before each test, the source and destination buffer is initialized * with a known pattern. This pattern is different depending on @@ -201,25 +226,57 @@ static int dmatest_func(void *data) unsigned int total_tests = 0; dma_cookie_t cookie; enum dma_status status; + enum dma_ctrl_flags flags; int ret; + int src_cnt; + int dst_cnt; + int i; thread_name = current->comm; ret = -ENOMEM; - thread->srcbuf = kmalloc(test_buf_size, GFP_KERNEL); - if (!thread->srcbuf) - goto err_srcbuf; - thread->dstbuf = kmalloc(test_buf_size, GFP_KERNEL); - if (!thread->dstbuf) - goto err_dstbuf; smp_rmb(); chan = thread->chan; + if (thread->type == DMA_MEMCPY) + src_cnt = dst_cnt = 1; + else if (thread->type == DMA_XOR) { + src_cnt = xor_sources | 1; /* force odd to ensure dst = src */ + dst_cnt = 1; + } else + goto err_srcs; + + thread->srcs = kcalloc(src_cnt+1, sizeof(u8 *), GFP_KERNEL); + if (!thread->srcs) + goto err_srcs; + for (i = 0; i < src_cnt; i++) { + thread->srcs[i] = kmalloc(test_buf_size, GFP_KERNEL); + if (!thread->srcs[i]) + goto err_srcbuf; + } + thread->srcs[i] = NULL; + + thread->dsts = kcalloc(dst_cnt+1, sizeof(u8 *), GFP_KERNEL); + if (!thread->dsts) + goto err_dsts; + for (i = 0; i < dst_cnt; i++) { + thread->dsts[i] = kmalloc(test_buf_size, GFP_KERNEL); + if (!thread->dsts[i]) + goto err_dstbuf; + } + thread->dsts[i] = NULL; + + set_user_nice(current, 10); + + flags = DMA_CTRL_ACK | DMA_COMPL_SKIP_DEST_UNMAP | DMA_PREP_INTERRUPT; while (!kthread_should_stop()) { struct dma_device *dev = chan->device; - struct dma_async_tx_descriptor *tx; - dma_addr_t dma_src, dma_dest; + struct dma_async_tx_descriptor *tx = NULL; + dma_addr_t dma_srcs[src_cnt]; + dma_addr_t dma_dsts[dst_cnt]; + struct completion cmp; + unsigned long tmo = msecs_to_jiffies(3000); total_tests++; @@ -227,22 +284,41 @@ static int dmatest_func(void *data) src_off = dmatest_random() % (test_buf_size - len + 1); dst_off = dmatest_random() % (test_buf_size - len + 1); - dmatest_init_srcbuf(thread->srcbuf, src_off, len); - dmatest_init_dstbuf(thread->dstbuf, dst_off, len); + dmatest_init_srcs(thread->srcs, src_off, len); + dmatest_init_dsts(thread->dsts, dst_off, len); - dma_src = dma_map_single(dev->dev, thread->srcbuf + src_off, - len, DMA_TO_DEVICE); + for (i = 0; i < src_cnt; i++) { + u8 *buf = thread->srcs[i] + src_off; + + dma_srcs[i] = dma_map_single(dev->dev, buf, len, + DMA_TO_DEVICE); + } /* map with DMA_BIDIRECTIONAL to force writeback/invalidate */ - dma_dest = dma_map_single(dev->dev, thread->dstbuf, - test_buf_size, DMA_BIDIRECTIONAL); + for (i = 0; i < dst_cnt; i++) { + dma_dsts[i] = dma_map_single(dev->dev, thread->dsts[i], + test_buf_size, + DMA_BIDIRECTIONAL); + } + + if (thread->type == DMA_MEMCPY) + tx = dev->device_prep_dma_memcpy(chan, + dma_dsts[0] + dst_off, + dma_srcs[0], len, + flags); + else if (thread->type == DMA_XOR) + tx = dev->device_prep_dma_xor(chan, + dma_dsts[0] + dst_off, + dma_srcs, xor_sources, + len, flags); - tx = dev->device_prep_dma_memcpy(chan, dma_dest + dst_off, - dma_src, len, - DMA_CTRL_ACK | DMA_COMPL_SKIP_DEST_UNMAP); if (!tx) { - dma_unmap_single(dev->dev, dma_src, len, DMA_TO_DEVICE); - dma_unmap_single(dev->dev, dma_dest, - test_buf_size, DMA_BIDIRECTIONAL); + for (i = 0; i < src_cnt; i++) + dma_unmap_single(dev->dev, dma_srcs[i], len, + DMA_TO_DEVICE); + for (i = 0; i < dst_cnt; i++) + dma_unmap_single(dev->dev, dma_dsts[i], + test_buf_size, + DMA_BIDIRECTIONAL); pr_warning("%s: #%u: prep error with src_off=0x%x " "dst_off=0x%x len=0x%x\n", thread_name, total_tests - 1, @@ -251,7 +327,10 @@ static int dmatest_func(void *data) failed_tests++; continue; } - tx->callback = NULL; + + init_completion(&cmp); + tx->callback = dmatest_callback; + tx->callback_param = &cmp; cookie = tx->tx_submit(tx); if (dma_submit_error(cookie)) { @@ -263,44 +342,50 @@ static int dmatest_func(void *data) failed_tests++; continue; } - dma_async_memcpy_issue_pending(chan); + dma_async_issue_pending(chan); - do { - msleep(1); - status = dma_async_memcpy_complete( - chan, cookie, NULL, NULL); - } while (status == DMA_IN_PROGRESS); + tmo = wait_for_completion_timeout(&cmp, tmo); + status = dma_async_is_tx_complete(chan, cookie, NULL, NULL); - if (status == DMA_ERROR) { - pr_warning("%s: #%u: error during copy\n", - thread_name, total_tests - 1); + if (tmo == 0) { + pr_warning("%s: #%u: test timed out\n", + thread_name, total_tests - 1); + failed_tests++; + continue; + } else if (status != DMA_SUCCESS) { + pr_warning("%s: #%u: got completion callback," + " but status is \'%s\'\n", + thread_name, total_tests - 1, + status == DMA_ERROR ? "error" : "in progress"); failed_tests++; continue; } + /* Unmap by myself (see DMA_COMPL_SKIP_DEST_UNMAP above) */ - dma_unmap_single(dev->dev, dma_dest, - test_buf_size, DMA_BIDIRECTIONAL); + for (i = 0; i < dst_cnt; i++) + dma_unmap_single(dev->dev, dma_dsts[i], test_buf_size, + DMA_BIDIRECTIONAL); error_count = 0; pr_debug("%s: verifying source buffer...\n", thread_name); - error_count += dmatest_verify(thread->srcbuf, 0, src_off, + error_count += dmatest_verify(thread->srcs, 0, src_off, 0, PATTERN_SRC, true); - error_count += dmatest_verify(thread->srcbuf, src_off, + error_count += dmatest_verify(thread->srcs, src_off, src_off + len, src_off, PATTERN_SRC | PATTERN_COPY, true); - error_count += dmatest_verify(thread->srcbuf, src_off + len, + error_count += dmatest_verify(thread->srcs, src_off + len, test_buf_size, src_off + len, PATTERN_SRC, true); pr_debug("%s: verifying dest buffer...\n", thread->task->comm); - error_count += dmatest_verify(thread->dstbuf, 0, dst_off, + error_count += dmatest_verify(thread->dsts, 0, dst_off, 0, PATTERN_DST, false); - error_count += dmatest_verify(thread->dstbuf, dst_off, + error_count += dmatest_verify(thread->dsts, dst_off, dst_off + len, src_off, PATTERN_SRC | PATTERN_COPY, false); - error_count += dmatest_verify(thread->dstbuf, dst_off + len, + error_count += dmatest_verify(thread->dsts, dst_off + len, test_buf_size, dst_off + len, PATTERN_DST, false); @@ -319,10 +404,16 @@ static int dmatest_func(void *data) } ret = 0; - kfree(thread->dstbuf); + for (i = 0; thread->dsts[i]; i++) + kfree(thread->dsts[i]); err_dstbuf: - kfree(thread->srcbuf); + kfree(thread->dsts); +err_dsts: + for (i = 0; thread->srcs[i]; i++) + kfree(thread->srcs[i]); err_srcbuf: + kfree(thread->srcs); +err_srcs: pr_notice("%s: terminating after %u tests, %u failures (status %d)\n", thread_name, total_tests, failed_tests, ret); return ret; @@ -344,35 +435,36 @@ static void dmatest_cleanup_channel(struct dmatest_chan *dtc) kfree(dtc); } -static int dmatest_add_channel(struct dma_chan *chan) +static int dmatest_add_threads(struct dmatest_chan *dtc, enum dma_transaction_type type) { - struct dmatest_chan *dtc; - struct dmatest_thread *thread; - unsigned int i; - - dtc = kmalloc(sizeof(struct dmatest_chan), GFP_KERNEL); - if (!dtc) { - pr_warning("dmatest: No memory for %s\n", dma_chan_name(chan)); - return -ENOMEM; - } + struct dmatest_thread *thread; + struct dma_chan *chan = dtc->chan; + char *op; + unsigned int i; - dtc->chan = chan; - INIT_LIST_HEAD(&dtc->threads); + if (type == DMA_MEMCPY) + op = "copy"; + else if (type == DMA_XOR) + op = "xor"; + else + return -EINVAL; for (i = 0; i < threads_per_chan; i++) { thread = kzalloc(sizeof(struct dmatest_thread), GFP_KERNEL); if (!thread) { - pr_warning("dmatest: No memory for %s-test%u\n", - dma_chan_name(chan), i); + pr_warning("dmatest: No memory for %s-%s%u\n", + dma_chan_name(chan), op, i); + break; } thread->chan = dtc->chan; + thread->type = type; smp_wmb(); - thread->task = kthread_run(dmatest_func, thread, "%s-test%u", - dma_chan_name(chan), i); + thread->task = kthread_run(dmatest_func, thread, "%s-%s%u", + dma_chan_name(chan), op, i); if (IS_ERR(thread->task)) { - pr_warning("dmatest: Failed to run thread %s-test%u\n", - dma_chan_name(chan), i); + pr_warning("dmatest: Failed to run thread %s-%s%u\n", + dma_chan_name(chan), op, i); kfree(thread); break; } @@ -382,7 +474,36 @@ static int dmatest_add_channel(struct dma_chan *chan) list_add_tail(&thread->node, &dtc->threads); } - pr_info("dmatest: Started %u threads using %s\n", i, dma_chan_name(chan)); + return i; +} + +static int dmatest_add_channel(struct dma_chan *chan) +{ + struct dmatest_chan *dtc; + struct dma_device *dma_dev = chan->device; + unsigned int thread_count = 0; + unsigned int cnt; + + dtc = kmalloc(sizeof(struct dmatest_chan), GFP_KERNEL); + if (!dtc) { + pr_warning("dmatest: No memory for %s\n", dma_chan_name(chan)); + return -ENOMEM; + } + + dtc->chan = chan; + INIT_LIST_HEAD(&dtc->threads); + + if (dma_has_cap(DMA_MEMCPY, dma_dev->cap_mask)) { + cnt = dmatest_add_threads(dtc, DMA_MEMCPY); + thread_count += cnt > 0 ?: 0; + } + if (dma_has_cap(DMA_XOR, dma_dev->cap_mask)) { + cnt = dmatest_add_threads(dtc, DMA_XOR); + thread_count += cnt > 0 ?: 0; + } + + pr_info("dmatest: Started %u threads using %s\n", + thread_count, dma_chan_name(chan)); list_add_tail(&dtc->node, &dmatest_channels); nr_channels++; diff --git a/drivers/dma/dw_dmac.c b/drivers/dma/dw_dmac.c index 20ad3d26bec2..98c9a847bf51 100644 --- a/drivers/dma/dw_dmac.c +++ b/drivers/dma/dw_dmac.c @@ -363,6 +363,82 @@ static void dwc_handle_error(struct dw_dma *dw, struct dw_dma_chan *dwc) dwc_descriptor_complete(dwc, bad_desc); } +/* --------------------- Cyclic DMA API extensions -------------------- */ + +inline dma_addr_t dw_dma_get_src_addr(struct dma_chan *chan) +{ + struct dw_dma_chan *dwc = to_dw_dma_chan(chan); + return channel_readl(dwc, SAR); +} +EXPORT_SYMBOL(dw_dma_get_src_addr); + +inline dma_addr_t dw_dma_get_dst_addr(struct dma_chan *chan) +{ + struct dw_dma_chan *dwc = to_dw_dma_chan(chan); + return channel_readl(dwc, DAR); +} +EXPORT_SYMBOL(dw_dma_get_dst_addr); + +/* called with dwc->lock held and all DMAC interrupts disabled */ +static void dwc_handle_cyclic(struct dw_dma *dw, struct dw_dma_chan *dwc, + u32 status_block, u32 status_err, u32 status_xfer) +{ + if (status_block & dwc->mask) { + void (*callback)(void *param); + void *callback_param; + + dev_vdbg(chan2dev(&dwc->chan), "new cyclic period llp 0x%08x\n", + channel_readl(dwc, LLP)); + dma_writel(dw, CLEAR.BLOCK, dwc->mask); + + callback = dwc->cdesc->period_callback; + callback_param = dwc->cdesc->period_callback_param; + if (callback) { + spin_unlock(&dwc->lock); + callback(callback_param); + spin_lock(&dwc->lock); + } + } + + /* + * Error and transfer complete are highly unlikely, and will most + * likely be due to a configuration error by the user. + */ + if (unlikely(status_err & dwc->mask) || + unlikely(status_xfer & dwc->mask)) { + int i; + + dev_err(chan2dev(&dwc->chan), "cyclic DMA unexpected %s " + "interrupt, stopping DMA transfer\n", + status_xfer ? "xfer" : "error"); + dev_err(chan2dev(&dwc->chan), + " SAR: 0x%x DAR: 0x%x LLP: 0x%x CTL: 0x%x:%08x\n", + channel_readl(dwc, SAR), + channel_readl(dwc, DAR), + channel_readl(dwc, LLP), + channel_readl(dwc, CTL_HI), + channel_readl(dwc, CTL_LO)); + + channel_clear_bit(dw, CH_EN, dwc->mask); + while (dma_readl(dw, CH_EN) & dwc->mask) + cpu_relax(); + + /* make sure DMA does not restart by loading a new list */ + channel_writel(dwc, LLP, 0); + channel_writel(dwc, CTL_LO, 0); + channel_writel(dwc, CTL_HI, 0); + + dma_writel(dw, CLEAR.BLOCK, dwc->mask); + dma_writel(dw, CLEAR.ERROR, dwc->mask); + dma_writel(dw, CLEAR.XFER, dwc->mask); + + for (i = 0; i < dwc->cdesc->periods; i++) + dwc_dump_lli(dwc, &dwc->cdesc->desc[i]->lli); + } +} + +/* ------------------------------------------------------------------------- */ + static void dw_dma_tasklet(unsigned long data) { struct dw_dma *dw = (struct dw_dma *)data; @@ -382,7 +458,10 @@ static void dw_dma_tasklet(unsigned long data) for (i = 0; i < dw->dma.chancnt; i++) { dwc = &dw->chan[i]; spin_lock(&dwc->lock); - if (status_err & (1 << i)) + if (test_bit(DW_DMA_IS_CYCLIC, &dwc->flags)) + dwc_handle_cyclic(dw, dwc, status_block, status_err, + status_xfer); + else if (status_err & (1 << i)) dwc_handle_error(dw, dwc); else if ((status_block | status_xfer) & (1 << i)) dwc_scan_descriptors(dw, dwc); @@ -826,7 +905,6 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan) dma_async_tx_descriptor_init(&desc->txd, chan); desc->txd.tx_submit = dwc_tx_submit; desc->txd.flags = DMA_CTRL_ACK; - INIT_LIST_HEAD(&desc->txd.tx_list); desc->txd.phys = dma_map_single(chan2parent(chan), &desc->lli, sizeof(desc->lli), DMA_TO_DEVICE); dwc_desc_put(dwc, desc); @@ -884,6 +962,257 @@ static void dwc_free_chan_resources(struct dma_chan *chan) dev_vdbg(chan2dev(chan), "free_chan_resources done\n"); } +/* --------------------- Cyclic DMA API extensions -------------------- */ + +/** + * dw_dma_cyclic_start - start the cyclic DMA transfer + * @chan: the DMA channel to start + * + * Must be called with soft interrupts disabled. Returns zero on success or + * -errno on failure. + */ +int dw_dma_cyclic_start(struct dma_chan *chan) +{ + struct dw_dma_chan *dwc = to_dw_dma_chan(chan); + struct dw_dma *dw = to_dw_dma(dwc->chan.device); + + if (!test_bit(DW_DMA_IS_CYCLIC, &dwc->flags)) { + dev_err(chan2dev(&dwc->chan), "missing prep for cyclic DMA\n"); + return -ENODEV; + } + + spin_lock(&dwc->lock); + + /* assert channel is idle */ + if (dma_readl(dw, CH_EN) & dwc->mask) { + dev_err(chan2dev(&dwc->chan), + "BUG: Attempted to start non-idle channel\n"); + dev_err(chan2dev(&dwc->chan), + " SAR: 0x%x DAR: 0x%x LLP: 0x%x CTL: 0x%x:%08x\n", + channel_readl(dwc, SAR), + channel_readl(dwc, DAR), + channel_readl(dwc, LLP), + channel_readl(dwc, CTL_HI), + channel_readl(dwc, CTL_LO)); + spin_unlock(&dwc->lock); + return -EBUSY; + } + + dma_writel(dw, CLEAR.BLOCK, dwc->mask); + dma_writel(dw, CLEAR.ERROR, dwc->mask); + dma_writel(dw, CLEAR.XFER, dwc->mask); + + /* setup DMAC channel registers */ + channel_writel(dwc, LLP, dwc->cdesc->desc[0]->txd.phys); + channel_writel(dwc, CTL_LO, DWC_CTLL_LLP_D_EN | DWC_CTLL_LLP_S_EN); + channel_writel(dwc, CTL_HI, 0); + + channel_set_bit(dw, CH_EN, dwc->mask); + + spin_unlock(&dwc->lock); + + return 0; +} +EXPORT_SYMBOL(dw_dma_cyclic_start); + +/** + * dw_dma_cyclic_stop - stop the cyclic DMA transfer + * @chan: the DMA channel to stop + * + * Must be called with soft interrupts disabled. + */ +void dw_dma_cyclic_stop(struct dma_chan *chan) +{ + struct dw_dma_chan *dwc = to_dw_dma_chan(chan); + struct dw_dma *dw = to_dw_dma(dwc->chan.device); + + spin_lock(&dwc->lock); + + channel_clear_bit(dw, CH_EN, dwc->mask); + while (dma_readl(dw, CH_EN) & dwc->mask) + cpu_relax(); + + spin_unlock(&dwc->lock); +} +EXPORT_SYMBOL(dw_dma_cyclic_stop); + +/** + * dw_dma_cyclic_prep - prepare the cyclic DMA transfer + * @chan: the DMA channel to prepare + * @buf_addr: physical DMA address where the buffer starts + * @buf_len: total number of bytes for the entire buffer + * @period_len: number of bytes for each period + * @direction: transfer direction, to or from device + * + * Must be called before trying to start the transfer. Returns a valid struct + * dw_cyclic_desc if successful or an ERR_PTR(-errno) if not successful. + */ +struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan, + dma_addr_t buf_addr, size_t buf_len, size_t period_len, + enum dma_data_direction direction) +{ + struct dw_dma_chan *dwc = to_dw_dma_chan(chan); + struct dw_cyclic_desc *cdesc; + struct dw_cyclic_desc *retval = NULL; + struct dw_desc *desc; + struct dw_desc *last = NULL; + struct dw_dma_slave *dws = chan->private; + unsigned long was_cyclic; + unsigned int reg_width; + unsigned int periods; + unsigned int i; + + spin_lock_bh(&dwc->lock); + if (!list_empty(&dwc->queue) || !list_empty(&dwc->active_list)) { + spin_unlock_bh(&dwc->lock); + dev_dbg(chan2dev(&dwc->chan), + "queue and/or active list are not empty\n"); + return ERR_PTR(-EBUSY); + } + + was_cyclic = test_and_set_bit(DW_DMA_IS_CYCLIC, &dwc->flags); + spin_unlock_bh(&dwc->lock); + if (was_cyclic) { + dev_dbg(chan2dev(&dwc->chan), + "channel already prepared for cyclic DMA\n"); + return ERR_PTR(-EBUSY); + } + + retval = ERR_PTR(-EINVAL); + reg_width = dws->reg_width; + periods = buf_len / period_len; + + /* Check for too big/unaligned periods and unaligned DMA buffer. */ + if (period_len > (DWC_MAX_COUNT << reg_width)) + goto out_err; + if (unlikely(period_len & ((1 << reg_width) - 1))) + goto out_err; + if (unlikely(buf_addr & ((1 << reg_width) - 1))) + goto out_err; + if (unlikely(!(direction & (DMA_TO_DEVICE | DMA_FROM_DEVICE)))) + goto out_err; + + retval = ERR_PTR(-ENOMEM); + + if (periods > NR_DESCS_PER_CHANNEL) + goto out_err; + + cdesc = kzalloc(sizeof(struct dw_cyclic_desc), GFP_KERNEL); + if (!cdesc) + goto out_err; + + cdesc->desc = kzalloc(sizeof(struct dw_desc *) * periods, GFP_KERNEL); + if (!cdesc->desc) + goto out_err_alloc; + + for (i = 0; i < periods; i++) { + desc = dwc_desc_get(dwc); + if (!desc) + goto out_err_desc_get; + + switch (direction) { + case DMA_TO_DEVICE: + desc->lli.dar = dws->tx_reg; + desc->lli.sar = buf_addr + (period_len * i); + desc->lli.ctllo = (DWC_DEFAULT_CTLLO + | DWC_CTLL_DST_WIDTH(reg_width) + | DWC_CTLL_SRC_WIDTH(reg_width) + | DWC_CTLL_DST_FIX + | DWC_CTLL_SRC_INC + | DWC_CTLL_FC_M2P + | DWC_CTLL_INT_EN); + break; + case DMA_FROM_DEVICE: + desc->lli.dar = buf_addr + (period_len * i); + desc->lli.sar = dws->rx_reg; + desc->lli.ctllo = (DWC_DEFAULT_CTLLO + | DWC_CTLL_SRC_WIDTH(reg_width) + | DWC_CTLL_DST_WIDTH(reg_width) + | DWC_CTLL_DST_INC + | DWC_CTLL_SRC_FIX + | DWC_CTLL_FC_P2M + | DWC_CTLL_INT_EN); + break; + default: + break; + } + + desc->lli.ctlhi = (period_len >> reg_width); + cdesc->desc[i] = desc; + + if (last) { + last->lli.llp = desc->txd.phys; + dma_sync_single_for_device(chan2parent(chan), + last->txd.phys, sizeof(last->lli), + DMA_TO_DEVICE); + } + + last = desc; + } + + /* lets make a cyclic list */ + last->lli.llp = cdesc->desc[0]->txd.phys; + dma_sync_single_for_device(chan2parent(chan), last->txd.phys, + sizeof(last->lli), DMA_TO_DEVICE); + + dev_dbg(chan2dev(&dwc->chan), "cyclic prepared buf 0x%08x len %zu " + "period %zu periods %d\n", buf_addr, buf_len, + period_len, periods); + + cdesc->periods = periods; + dwc->cdesc = cdesc; + + return cdesc; + +out_err_desc_get: + while (i--) + dwc_desc_put(dwc, cdesc->desc[i]); +out_err_alloc: + kfree(cdesc); +out_err: + clear_bit(DW_DMA_IS_CYCLIC, &dwc->flags); + return (struct dw_cyclic_desc *)retval; +} +EXPORT_SYMBOL(dw_dma_cyclic_prep); + +/** + * dw_dma_cyclic_free - free a prepared cyclic DMA transfer + * @chan: the DMA channel to free + */ +void dw_dma_cyclic_free(struct dma_chan *chan) +{ + struct dw_dma_chan *dwc = to_dw_dma_chan(chan); + struct dw_dma *dw = to_dw_dma(dwc->chan.device); + struct dw_cyclic_desc *cdesc = dwc->cdesc; + int i; + + dev_dbg(chan2dev(&dwc->chan), "cyclic free\n"); + + if (!cdesc) + return; + + spin_lock_bh(&dwc->lock); + + channel_clear_bit(dw, CH_EN, dwc->mask); + while (dma_readl(dw, CH_EN) & dwc->mask) + cpu_relax(); + + dma_writel(dw, CLEAR.BLOCK, dwc->mask); + dma_writel(dw, CLEAR.ERROR, dwc->mask); + dma_writel(dw, CLEAR.XFER, dwc->mask); + + spin_unlock_bh(&dwc->lock); + + for (i = 0; i < cdesc->periods; i++) + dwc_desc_put(dwc, cdesc->desc[i]); + + kfree(cdesc->desc); + kfree(cdesc); + + clear_bit(DW_DMA_IS_CYCLIC, &dwc->flags); +} +EXPORT_SYMBOL(dw_dma_cyclic_free); + /*----------------------------------------------------------------------*/ static void dw_dma_off(struct dw_dma *dw) diff --git a/drivers/dma/dw_dmac_regs.h b/drivers/dma/dw_dmac_regs.h index b252b202c5cf..13a580767031 100644 --- a/drivers/dma/dw_dmac_regs.h +++ b/drivers/dma/dw_dmac_regs.h @@ -126,6 +126,10 @@ struct dw_dma_regs { #define DW_REGLEN 0x400 +enum dw_dmac_flags { + DW_DMA_IS_CYCLIC = 0, +}; + struct dw_dma_chan { struct dma_chan chan; void __iomem *ch_regs; @@ -134,10 +138,12 @@ struct dw_dma_chan { spinlock_t lock; /* these other elements are all protected by lock */ + unsigned long flags; dma_cookie_t completed; struct list_head active_list; struct list_head queue; struct list_head free_list; + struct dw_cyclic_desc *cdesc; unsigned int descs_allocated; }; @@ -158,7 +164,6 @@ static inline struct dw_dma_chan *to_dw_dma_chan(struct dma_chan *chan) return container_of(chan, struct dw_dma_chan, chan); } - struct dw_dma { struct dma_device dma; void __iomem *regs; diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c index 86d6da47f558..da8a8ed9e411 100644 --- a/drivers/dma/fsldma.c +++ b/drivers/dma/fsldma.c @@ -354,7 +354,6 @@ static struct fsl_desc_sw *fsl_dma_alloc_descriptor( dma_async_tx_descriptor_init(&desc_sw->async_tx, &fsl_chan->common); desc_sw->async_tx.tx_submit = fsl_dma_tx_submit; - INIT_LIST_HEAD(&desc_sw->async_tx.tx_list); desc_sw->async_tx.phys = pdesc; } diff --git a/drivers/dma/ioat_dma.c b/drivers/dma/ioat_dma.c index 5905cd36bcd2..e4fc33c1c32f 100644 --- a/drivers/dma/ioat_dma.c +++ b/drivers/dma/ioat_dma.c @@ -693,7 +693,6 @@ static struct ioat_desc_sw *ioat_dma_alloc_descriptor( desc_sw->async_tx.tx_submit = ioat2_tx_submit; break; } - INIT_LIST_HEAD(&desc_sw->async_tx.tx_list); desc_sw->hw = desc; desc_sw->async_tx.phys = phys; diff --git a/drivers/dma/iop-adma.c b/drivers/dma/iop-adma.c index 16adbe61cfb2..2f052265122f 100644 --- a/drivers/dma/iop-adma.c +++ b/drivers/dma/iop-adma.c @@ -498,7 +498,6 @@ static int iop_adma_alloc_chan_resources(struct dma_chan *chan) slot->async_tx.tx_submit = iop_adma_tx_submit; INIT_LIST_HEAD(&slot->chain_node); INIT_LIST_HEAD(&slot->slot_node); - INIT_LIST_HEAD(&slot->async_tx.tx_list); hw_desc = (char *) iop_chan->device->dma_desc_pool; slot->async_tx.phys = (dma_addr_t) &hw_desc[idx * IOP_ADMA_SLOT_SIZE]; diff --git a/drivers/dma/ipu/ipu_idmac.c b/drivers/dma/ipu/ipu_idmac.c index da781d107895..e202a6ce5573 100644 --- a/drivers/dma/ipu/ipu_idmac.c +++ b/drivers/dma/ipu/ipu_idmac.c @@ -28,6 +28,9 @@ #define FS_VF_IN_VALID 0x00000002 #define FS_ENC_IN_VALID 0x00000001 +static int ipu_disable_channel(struct idmac *idmac, struct idmac_channel *ichan, + bool wait_for_stop); + /* * There can be only one, we could allocate it dynamically, but then we'd have * to add an extra parameter to some functions, and use something as ugly as @@ -107,7 +110,7 @@ static uint32_t bytes_per_pixel(enum pixel_fmt fmt) } } -/* Enable / disable direct write to memory by the Camera Sensor Interface */ +/* Enable direct write to memory by the Camera Sensor Interface */ static void ipu_ic_enable_task(struct ipu *ipu, enum ipu_channel channel) { uint32_t ic_conf, mask; @@ -126,6 +129,7 @@ static void ipu_ic_enable_task(struct ipu *ipu, enum ipu_channel channel) idmac_write_icreg(ipu, ic_conf, IC_CONF); } +/* Called under spin_lock_irqsave(&ipu_data.lock) */ static void ipu_ic_disable_task(struct ipu *ipu, enum ipu_channel channel) { uint32_t ic_conf, mask; @@ -422,7 +426,7 @@ static void ipu_ch_param_set_size(union chan_param_mem *params, break; default: dev_err(ipu_data.dev, - "mxc ipu: unimplemented pixel format %d\n", pixel_fmt); + "mx3 ipu: unimplemented pixel format %d\n", pixel_fmt); break; } @@ -433,20 +437,20 @@ static void ipu_ch_param_set_burst_size(union chan_param_mem *params, uint16_t burst_pixels) { params->pp.npb = burst_pixels - 1; -}; +} static void ipu_ch_param_set_buffer(union chan_param_mem *params, dma_addr_t buf0, dma_addr_t buf1) { params->pp.eba0 = buf0; params->pp.eba1 = buf1; -}; +} static void ipu_ch_param_set_rotation(union chan_param_mem *params, enum ipu_rotate_mode rotate) { params->pp.bam = rotate; -}; +} static void ipu_write_param_mem(uint32_t addr, uint32_t *data, uint32_t num_words) @@ -571,7 +575,7 @@ static uint32_t dma_param_addr(uint32_t dma_ch) { /* Channel Parameter Memory */ return 0x10000 | (dma_ch << 4); -}; +} static void ipu_channel_set_priority(struct ipu *ipu, enum ipu_channel channel, bool prio) @@ -611,7 +615,8 @@ static uint32_t ipu_channel_conf_mask(enum ipu_channel channel) /** * ipu_enable_channel() - enable an IPU channel. - * @channel: channel ID. + * @idmac: IPU DMAC context. + * @ichan: IDMAC channel. * @return: 0 on success or negative error code on failure. */ static int ipu_enable_channel(struct idmac *idmac, struct idmac_channel *ichan) @@ -649,7 +654,7 @@ static int ipu_enable_channel(struct idmac *idmac, struct idmac_channel *ichan) /** * ipu_init_channel_buffer() - initialize a buffer for logical IPU channel. - * @channel: channel ID. + * @ichan: IDMAC channel. * @pixel_fmt: pixel format of buffer. Pixel format is a FOURCC ASCII code. * @width: width of buffer in pixels. * @height: height of buffer in pixels. @@ -687,7 +692,7 @@ static int ipu_init_channel_buffer(struct idmac_channel *ichan, } /* IC channel's stride must be a multiple of 8 pixels */ - if ((channel <= 13) && (stride % 8)) { + if ((channel <= IDMAC_IC_13) && (stride % 8)) { dev_err(ipu->dev, "Stride must be 8 pixel multiple\n"); return -EINVAL; } @@ -752,7 +757,7 @@ static void ipu_select_buffer(enum ipu_channel channel, int buffer_n) /** * ipu_update_channel_buffer() - update physical address of a channel buffer. - * @channel: channel ID. + * @ichan: IDMAC channel. * @buffer_n: buffer number to update. * 0 or 1 are the only valid values. * @phyaddr: buffer physical address. @@ -760,9 +765,10 @@ static void ipu_select_buffer(enum ipu_channel channel, int buffer_n) * function will fail if the buffer is set to ready. */ /* Called under spin_lock(_irqsave)(&ichan->lock) */ -static int ipu_update_channel_buffer(enum ipu_channel channel, +static int ipu_update_channel_buffer(struct idmac_channel *ichan, int buffer_n, dma_addr_t phyaddr) { + enum ipu_channel channel = ichan->dma_chan.chan_id; uint32_t reg; unsigned long flags; @@ -771,8 +777,8 @@ static int ipu_update_channel_buffer(enum ipu_channel channel, if (buffer_n == 0) { reg = idmac_read_ipureg(&ipu_data, IPU_CHA_BUF0_RDY); if (reg & (1UL << channel)) { - spin_unlock_irqrestore(&ipu_data.lock, flags); - return -EACCES; + ipu_ic_disable_task(&ipu_data, channel); + ichan->status = IPU_CHANNEL_READY; } /* 44.3.3.1.9 - Row Number 1 (WORD1, offset 0) */ @@ -782,8 +788,8 @@ static int ipu_update_channel_buffer(enum ipu_channel channel, } else { reg = idmac_read_ipureg(&ipu_data, IPU_CHA_BUF1_RDY); if (reg & (1UL << channel)) { - spin_unlock_irqrestore(&ipu_data.lock, flags); - return -EACCES; + ipu_ic_disable_task(&ipu_data, channel); + ichan->status = IPU_CHANNEL_READY; } /* Check if double-buffering is already enabled */ @@ -805,6 +811,39 @@ static int ipu_update_channel_buffer(enum ipu_channel channel, } /* Called under spin_lock_irqsave(&ichan->lock) */ +static int ipu_submit_buffer(struct idmac_channel *ichan, + struct idmac_tx_desc *desc, struct scatterlist *sg, int buf_idx) +{ + unsigned int chan_id = ichan->dma_chan.chan_id; + struct device *dev = &ichan->dma_chan.dev->device; + int ret; + + if (async_tx_test_ack(&desc->txd)) + return -EINTR; + + /* + * On first invocation this shouldn't be necessary, the call to + * ipu_init_channel_buffer() above will set addresses for us, so we + * could make it conditional on status >= IPU_CHANNEL_ENABLED, but + * doing it again shouldn't hurt either. + */ + ret = ipu_update_channel_buffer(ichan, buf_idx, + sg_dma_address(sg)); + + if (ret < 0) { + dev_err(dev, "Updating sg %p on channel 0x%x buffer %d failed!\n", + sg, chan_id, buf_idx); + return ret; + } + + ipu_select_buffer(chan_id, buf_idx); + dev_dbg(dev, "Updated sg %p on channel 0x%x buffer %d\n", + sg, chan_id, buf_idx); + + return 0; +} + +/* Called under spin_lock_irqsave(&ichan->lock) */ static int ipu_submit_channel_buffers(struct idmac_channel *ichan, struct idmac_tx_desc *desc) { @@ -815,20 +854,10 @@ static int ipu_submit_channel_buffers(struct idmac_channel *ichan, if (!ichan->sg[i]) { ichan->sg[i] = sg; - /* - * On first invocation this shouldn't be necessary, the - * call to ipu_init_channel_buffer() above will set - * addresses for us, so we could make it conditional - * on status >= IPU_CHANNEL_ENABLED, but doing it again - * shouldn't hurt either. - */ - ret = ipu_update_channel_buffer(ichan->dma_chan.chan_id, i, - sg_dma_address(sg)); + ret = ipu_submit_buffer(ichan, desc, sg, i); if (ret < 0) return ret; - ipu_select_buffer(ichan->dma_chan.chan_id, i); - sg = sg_next(sg); } } @@ -842,19 +871,22 @@ static dma_cookie_t idmac_tx_submit(struct dma_async_tx_descriptor *tx) struct idmac_channel *ichan = to_idmac_chan(tx->chan); struct idmac *idmac = to_idmac(tx->chan->device); struct ipu *ipu = to_ipu(idmac); + struct device *dev = &ichan->dma_chan.dev->device; dma_cookie_t cookie; unsigned long flags; + int ret; /* Sanity check */ if (!list_empty(&desc->list)) { /* The descriptor doesn't belong to client */ - dev_err(&ichan->dma_chan.dev->device, - "Descriptor %p not prepared!\n", tx); + dev_err(dev, "Descriptor %p not prepared!\n", tx); return -EBUSY; } mutex_lock(&ichan->chan_mutex); + async_tx_clear_ack(tx); + if (ichan->status < IPU_CHANNEL_READY) { struct idmac_video_param *video = &ichan->params.video; /* @@ -878,16 +910,7 @@ static dma_cookie_t idmac_tx_submit(struct dma_async_tx_descriptor *tx) goto out; } - /* ipu->lock can be taken under ichan->lock, but not v.v. */ - spin_lock_irqsave(&ichan->lock, flags); - - /* submit_buffers() atomically verifies and fills empty sg slots */ - cookie = ipu_submit_channel_buffers(ichan, desc); - - spin_unlock_irqrestore(&ichan->lock, flags); - - if (cookie < 0) - goto out; + dev_dbg(dev, "Submitting sg %p\n", &desc->sg[0]); cookie = ichan->dma_chan.cookie; @@ -897,24 +920,40 @@ static dma_cookie_t idmac_tx_submit(struct dma_async_tx_descriptor *tx) /* from dmaengine.h: "last cookie value returned to client" */ ichan->dma_chan.cookie = cookie; tx->cookie = cookie; + + /* ipu->lock can be taken under ichan->lock, but not v.v. */ spin_lock_irqsave(&ichan->lock, flags); + list_add_tail(&desc->list, &ichan->queue); + /* submit_buffers() atomically verifies and fills empty sg slots */ + ret = ipu_submit_channel_buffers(ichan, desc); + spin_unlock_irqrestore(&ichan->lock, flags); + if (ret < 0) { + cookie = ret; + goto dequeue; + } + if (ichan->status < IPU_CHANNEL_ENABLED) { - int ret = ipu_enable_channel(idmac, ichan); + ret = ipu_enable_channel(idmac, ichan); if (ret < 0) { cookie = ret; - spin_lock_irqsave(&ichan->lock, flags); - list_del_init(&desc->list); - spin_unlock_irqrestore(&ichan->lock, flags); - tx->cookie = cookie; - ichan->dma_chan.cookie = cookie; + goto dequeue; } } dump_idmac_reg(ipu); +dequeue: + if (cookie < 0) { + spin_lock_irqsave(&ichan->lock, flags); + list_del_init(&desc->list); + spin_unlock_irqrestore(&ichan->lock, flags); + tx->cookie = cookie; + ichan->dma_chan.cookie = cookie; + } + out: mutex_unlock(&ichan->chan_mutex); @@ -944,8 +983,6 @@ static int idmac_desc_alloc(struct idmac_channel *ichan, int n) memset(txd, 0, sizeof(*txd)); dma_async_tx_descriptor_init(txd, &ichan->dma_chan); txd->tx_submit = idmac_tx_submit; - txd->chan = &ichan->dma_chan; - INIT_LIST_HEAD(&txd->tx_list); list_add(&desc->list, &ichan->free_list); @@ -1161,6 +1198,24 @@ static int ipu_disable_channel(struct idmac *idmac, struct idmac_channel *ichan, return 0; } +static struct scatterlist *idmac_sg_next(struct idmac_channel *ichan, + struct idmac_tx_desc **desc, struct scatterlist *sg) +{ + struct scatterlist *sgnew = sg ? sg_next(sg) : NULL; + + if (sgnew) + /* next sg-element in this list */ + return sgnew; + + if ((*desc)->list.next == &ichan->queue) + /* No more descriptors on the queue */ + return NULL; + + /* Fetch next descriptor */ + *desc = list_entry((*desc)->list.next, struct idmac_tx_desc, list); + return (*desc)->sg; +} + /* * We have several possibilities here: * current BUF next BUF @@ -1176,23 +1231,46 @@ static int ipu_disable_channel(struct idmac *idmac, struct idmac_channel *ichan, static irqreturn_t idmac_interrupt(int irq, void *dev_id) { struct idmac_channel *ichan = dev_id; + struct device *dev = &ichan->dma_chan.dev->device; unsigned int chan_id = ichan->dma_chan.chan_id; struct scatterlist **sg, *sgnext, *sgnew = NULL; /* Next transfer descriptor */ - struct idmac_tx_desc *desc = NULL, *descnew; + struct idmac_tx_desc *desc, *descnew; dma_async_tx_callback callback; void *callback_param; bool done = false; - u32 ready0 = idmac_read_ipureg(&ipu_data, IPU_CHA_BUF0_RDY), - ready1 = idmac_read_ipureg(&ipu_data, IPU_CHA_BUF1_RDY), - curbuf = idmac_read_ipureg(&ipu_data, IPU_CHA_CUR_BUF); + u32 ready0, ready1, curbuf, err; + unsigned long flags; /* IDMAC has cleared the respective BUFx_RDY bit, we manage the buffer */ - pr_debug("IDMAC irq %d\n", irq); + dev_dbg(dev, "IDMAC irq %d, buf %d\n", irq, ichan->active_buffer); + + spin_lock_irqsave(&ipu_data.lock, flags); + + ready0 = idmac_read_ipureg(&ipu_data, IPU_CHA_BUF0_RDY); + ready1 = idmac_read_ipureg(&ipu_data, IPU_CHA_BUF1_RDY); + curbuf = idmac_read_ipureg(&ipu_data, IPU_CHA_CUR_BUF); + err = idmac_read_ipureg(&ipu_data, IPU_INT_STAT_4); + + if (err & (1 << chan_id)) { + idmac_write_ipureg(&ipu_data, 1 << chan_id, IPU_INT_STAT_4); + spin_unlock_irqrestore(&ipu_data.lock, flags); + /* + * Doing this + * ichan->sg[0] = ichan->sg[1] = NULL; + * you can force channel re-enable on the next tx_submit(), but + * this is dirty - think about descriptors with multiple + * sg elements. + */ + dev_warn(dev, "NFB4EOF on channel %d, ready %x, %x, cur %x\n", + chan_id, ready0, ready1, curbuf); + return IRQ_HANDLED; + } + spin_unlock_irqrestore(&ipu_data.lock, flags); + /* Other interrupts do not interfere with this channel */ spin_lock(&ichan->lock); - if (unlikely(chan_id != IDMAC_SDC_0 && chan_id != IDMAC_SDC_1 && ((curbuf >> chan_id) & 1) == ichan->active_buffer)) { int i = 100; @@ -1207,19 +1285,23 @@ static irqreturn_t idmac_interrupt(int irq, void *dev_id) if (!i) { spin_unlock(&ichan->lock); - dev_dbg(ichan->dma_chan.device->dev, + dev_dbg(dev, "IRQ on active buffer on channel %x, active " "%d, ready %x, %x, current %x!\n", chan_id, ichan->active_buffer, ready0, ready1, curbuf); return IRQ_NONE; - } + } else + dev_dbg(dev, + "Buffer deactivated on channel %x, active " + "%d, ready %x, %x, current %x, rest %d!\n", chan_id, + ichan->active_buffer, ready0, ready1, curbuf, i); } if (unlikely((ichan->active_buffer && (ready1 >> chan_id) & 1) || (!ichan->active_buffer && (ready0 >> chan_id) & 1) )) { spin_unlock(&ichan->lock); - dev_dbg(ichan->dma_chan.device->dev, + dev_dbg(dev, "IRQ with active buffer still ready on channel %x, " "active %d, ready %x, %x!\n", chan_id, ichan->active_buffer, ready0, ready1); @@ -1227,8 +1309,9 @@ static irqreturn_t idmac_interrupt(int irq, void *dev_id) } if (unlikely(list_empty(&ichan->queue))) { + ichan->sg[ichan->active_buffer] = NULL; spin_unlock(&ichan->lock); - dev_err(ichan->dma_chan.device->dev, + dev_err(dev, "IRQ without queued buffers on channel %x, active %d, " "ready %x, %x!\n", chan_id, ichan->active_buffer, ready0, ready1); @@ -1243,40 +1326,44 @@ static irqreturn_t idmac_interrupt(int irq, void *dev_id) sg = &ichan->sg[ichan->active_buffer]; sgnext = ichan->sg[!ichan->active_buffer]; + if (!*sg) { + spin_unlock(&ichan->lock); + return IRQ_HANDLED; + } + + desc = list_entry(ichan->queue.next, struct idmac_tx_desc, list); + descnew = desc; + + dev_dbg(dev, "IDMAC irq %d, dma 0x%08x, next dma 0x%08x, current %d, curbuf 0x%08x\n", + irq, sg_dma_address(*sg), sgnext ? sg_dma_address(sgnext) : 0, ichan->active_buffer, curbuf); + + /* Find the descriptor of sgnext */ + sgnew = idmac_sg_next(ichan, &descnew, *sg); + if (sgnext != sgnew) + dev_err(dev, "Submitted buffer %p, next buffer %p\n", sgnext, sgnew); + /* * if sgnext == NULL sg must be the last element in a scatterlist and * queue must be empty */ if (unlikely(!sgnext)) { - if (unlikely(sg_next(*sg))) { - dev_err(ichan->dma_chan.device->dev, - "Broken buffer-update locking on channel %x!\n", - chan_id); - /* We'll let the user catch up */ + if (!WARN_ON(sg_next(*sg))) + dev_dbg(dev, "Underrun on channel %x\n", chan_id); + ichan->sg[!ichan->active_buffer] = sgnew; + + if (unlikely(sgnew)) { + ipu_submit_buffer(ichan, descnew, sgnew, !ichan->active_buffer); } else { - /* Underrun */ + spin_lock_irqsave(&ipu_data.lock, flags); ipu_ic_disable_task(&ipu_data, chan_id); - dev_dbg(ichan->dma_chan.device->dev, - "Underrun on channel %x\n", chan_id); + spin_unlock_irqrestore(&ipu_data.lock, flags); ichan->status = IPU_CHANNEL_READY; /* Continue to check for complete descriptor */ } } - desc = list_entry(ichan->queue.next, struct idmac_tx_desc, list); - - /* First calculate and submit the next sg element */ - if (likely(sgnext)) - sgnew = sg_next(sgnext); - - if (unlikely(!sgnew)) { - /* Start a new scatterlist, if any queued */ - if (likely(desc->list.next != &ichan->queue)) { - descnew = list_entry(desc->list.next, - struct idmac_tx_desc, list); - sgnew = &descnew->sg[0]; - } - } + /* Calculate and submit the next sg element */ + sgnew = idmac_sg_next(ichan, &descnew, sgnew); if (unlikely(!sg_next(*sg)) || !sgnext) { /* @@ -1289,17 +1376,13 @@ static irqreturn_t idmac_interrupt(int irq, void *dev_id) *sg = sgnew; - if (likely(sgnew)) { - int ret; - - ret = ipu_update_channel_buffer(chan_id, ichan->active_buffer, - sg_dma_address(*sg)); - if (ret < 0) - dev_err(ichan->dma_chan.device->dev, - "Failed to update buffer on channel %x buffer %d!\n", - chan_id, ichan->active_buffer); - else - ipu_select_buffer(chan_id, ichan->active_buffer); + if (likely(sgnew) && + ipu_submit_buffer(ichan, descnew, sgnew, ichan->active_buffer) < 0) { + callback = desc->txd.callback; + callback_param = desc->txd.callback_param; + spin_unlock(&ichan->lock); + callback(callback_param); + spin_lock(&ichan->lock); } /* Flip the active buffer - even if update above failed */ @@ -1327,13 +1410,20 @@ static void ipu_gc_tasklet(unsigned long arg) struct idmac_channel *ichan = ipu->channel + i; struct idmac_tx_desc *desc; unsigned long flags; - int j; + struct scatterlist *sg; + int j, k; for (j = 0; j < ichan->n_tx_desc; j++) { desc = ichan->desc + j; spin_lock_irqsave(&ichan->lock, flags); if (async_tx_test_ack(&desc->txd)) { list_move(&desc->list, &ichan->free_list); + for_each_sg(desc->sg, sg, desc->sg_len, k) { + if (ichan->sg[0] == sg) + ichan->sg[0] = NULL; + else if (ichan->sg[1] == sg) + ichan->sg[1] = NULL; + } async_tx_clear_ack(&desc->txd); } spin_unlock_irqrestore(&ichan->lock, flags); @@ -1341,13 +1431,7 @@ static void ipu_gc_tasklet(unsigned long arg) } } -/* - * At the time .device_alloc_chan_resources() method is called, we cannot know, - * whether the client will accept the channel. Thus we must only check, if we - * can satisfy client's request but the only real criterion to verify, whether - * the client has accepted our offer is the client_count. That's why we have to - * perform the rest of our allocation tasks on the first call to this function. - */ +/* Allocate and initialise a transfer descriptor. */ static struct dma_async_tx_descriptor *idmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, unsigned int sg_len, enum dma_data_direction direction, unsigned long tx_flags) @@ -1358,8 +1442,8 @@ static struct dma_async_tx_descriptor *idmac_prep_slave_sg(struct dma_chan *chan unsigned long flags; /* We only can handle these three channels so far */ - if (ichan->dma_chan.chan_id != IDMAC_SDC_0 && ichan->dma_chan.chan_id != IDMAC_SDC_1 && - ichan->dma_chan.chan_id != IDMAC_IC_7) + if (chan->chan_id != IDMAC_SDC_0 && chan->chan_id != IDMAC_SDC_1 && + chan->chan_id != IDMAC_IC_7) return NULL; if (direction != DMA_FROM_DEVICE && direction != DMA_TO_DEVICE) { @@ -1400,7 +1484,7 @@ static void idmac_issue_pending(struct dma_chan *chan) /* This is not always needed, but doesn't hurt either */ spin_lock_irqsave(&ipu->lock, flags); - ipu_select_buffer(ichan->dma_chan.chan_id, ichan->active_buffer); + ipu_select_buffer(chan->chan_id, ichan->active_buffer); spin_unlock_irqrestore(&ipu->lock, flags); /* @@ -1432,8 +1516,7 @@ static void __idmac_terminate_all(struct dma_chan *chan) struct idmac_tx_desc *desc = ichan->desc + i; if (list_empty(&desc->list)) /* Descriptor was prepared, but not submitted */ - list_add(&desc->list, - &ichan->free_list); + list_add(&desc->list, &ichan->free_list); async_tx_clear_ack(&desc->txd); } @@ -1458,6 +1541,28 @@ static void idmac_terminate_all(struct dma_chan *chan) mutex_unlock(&ichan->chan_mutex); } +#ifdef DEBUG +static irqreturn_t ic_sof_irq(int irq, void *dev_id) +{ + struct idmac_channel *ichan = dev_id; + printk(KERN_DEBUG "Got SOF IRQ %d on Channel %d\n", + irq, ichan->dma_chan.chan_id); + disable_irq(irq); + return IRQ_HANDLED; +} + +static irqreturn_t ic_eof_irq(int irq, void *dev_id) +{ + struct idmac_channel *ichan = dev_id; + printk(KERN_DEBUG "Got EOF IRQ %d on Channel %d\n", + irq, ichan->dma_chan.chan_id); + disable_irq(irq); + return IRQ_HANDLED; +} + +static int ic_sof = -EINVAL, ic_eof = -EINVAL; +#endif + static int idmac_alloc_chan_resources(struct dma_chan *chan) { struct idmac_channel *ichan = to_idmac_chan(chan); @@ -1471,31 +1576,49 @@ static int idmac_alloc_chan_resources(struct dma_chan *chan) chan->cookie = 1; ichan->completed = -ENXIO; - ret = ipu_irq_map(ichan->dma_chan.chan_id); + ret = ipu_irq_map(chan->chan_id); if (ret < 0) goto eimap; ichan->eof_irq = ret; + + /* + * Important to first disable the channel, because maybe someone + * used it before us, e.g., the bootloader + */ + ipu_disable_channel(idmac, ichan, true); + + ret = ipu_init_channel(idmac, ichan); + if (ret < 0) + goto eichan; + ret = request_irq(ichan->eof_irq, idmac_interrupt, 0, ichan->eof_name, ichan); if (ret < 0) goto erirq; - ret = ipu_init_channel(idmac, ichan); - if (ret < 0) - goto eichan; +#ifdef DEBUG + if (chan->chan_id == IDMAC_IC_7) { + ic_sof = ipu_irq_map(69); + if (ic_sof > 0) + request_irq(ic_sof, ic_sof_irq, 0, "IC SOF", ichan); + ic_eof = ipu_irq_map(70); + if (ic_eof > 0) + request_irq(ic_eof, ic_eof_irq, 0, "IC EOF", ichan); + } +#endif ichan->status = IPU_CHANNEL_INITIALIZED; - dev_dbg(&ichan->dma_chan.dev->device, "Found channel 0x%x, irq %d\n", - ichan->dma_chan.chan_id, ichan->eof_irq); + dev_dbg(&chan->dev->device, "Found channel 0x%x, irq %d\n", + chan->chan_id, ichan->eof_irq); return ret; -eichan: - free_irq(ichan->eof_irq, ichan); erirq: - ipu_irq_unmap(ichan->dma_chan.chan_id); + ipu_uninit_channel(idmac, ichan); +eichan: + ipu_irq_unmap(chan->chan_id); eimap: return ret; } @@ -1510,8 +1633,22 @@ static void idmac_free_chan_resources(struct dma_chan *chan) __idmac_terminate_all(chan); if (ichan->status > IPU_CHANNEL_FREE) { +#ifdef DEBUG + if (chan->chan_id == IDMAC_IC_7) { + if (ic_sof > 0) { + free_irq(ic_sof, ichan); + ipu_irq_unmap(69); + ic_sof = -EINVAL; + } + if (ic_eof > 0) { + free_irq(ic_eof, ichan); + ipu_irq_unmap(70); + ic_eof = -EINVAL; + } + } +#endif free_irq(ichan->eof_irq, ichan); - ipu_irq_unmap(ichan->dma_chan.chan_id); + ipu_irq_unmap(chan->chan_id); } ichan->status = IPU_CHANNEL_FREE; @@ -1573,7 +1710,7 @@ static int __init ipu_idmac_init(struct ipu *ipu) dma_chan->device = &idmac->dma; dma_chan->cookie = 1; dma_chan->chan_id = i; - list_add_tail(&ichan->dma_chan.device_node, &dma->channels); + list_add_tail(&dma_chan->device_node, &dma->channels); } idmac_write_icreg(ipu, 0x00000070, IDMAC_CONF); @@ -1581,7 +1718,7 @@ static int __init ipu_idmac_init(struct ipu *ipu) return dma_async_device_register(&idmac->dma); } -static void ipu_idmac_exit(struct ipu *ipu) +static void __exit ipu_idmac_exit(struct ipu *ipu) { int i; struct idmac *idmac = &ipu->idmac; @@ -1600,7 +1737,7 @@ static void ipu_idmac_exit(struct ipu *ipu) * IPU common probe / remove */ -static int ipu_probe(struct platform_device *pdev) +static int __init ipu_probe(struct platform_device *pdev) { struct ipu_platform_data *pdata = pdev->dev.platform_data; struct resource *mem_ipu, *mem_ic; @@ -1700,7 +1837,7 @@ err_noirq: return ret; } -static int ipu_remove(struct platform_device *pdev) +static int __exit ipu_remove(struct platform_device *pdev) { struct ipu *ipu = platform_get_drvdata(pdev); @@ -1725,7 +1862,7 @@ static struct platform_driver ipu_platform_driver = { .name = "ipu-core", .owner = THIS_MODULE, }, - .remove = ipu_remove, + .remove = __exit_p(ipu_remove), }; static int __init ipu_init(void) diff --git a/drivers/dma/ipu/ipu_irq.c b/drivers/dma/ipu/ipu_irq.c index 83f532cc767f..dd8ebc75b667 100644 --- a/drivers/dma/ipu/ipu_irq.c +++ b/drivers/dma/ipu/ipu_irq.c @@ -352,7 +352,7 @@ static struct irq_chip ipu_irq_chip = { }; /* Install the IRQ handler */ -int ipu_irq_attach_irq(struct ipu *ipu, struct platform_device *dev) +int __init ipu_irq_attach_irq(struct ipu *ipu, struct platform_device *dev) { struct ipu_platform_data *pdata = dev->dev.platform_data; unsigned int irq, irq_base, i; diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c index cb7f26fb9f18..ddab94f51224 100644 --- a/drivers/dma/mv_xor.c +++ b/drivers/dma/mv_xor.c @@ -632,7 +632,6 @@ static int mv_xor_alloc_chan_resources(struct dma_chan *chan) slot->async_tx.tx_submit = mv_xor_tx_submit; INIT_LIST_HEAD(&slot->chain_node); INIT_LIST_HEAD(&slot->slot_node); - INIT_LIST_HEAD(&slot->async_tx.tx_list); hw_desc = (char *) mv_chan->device->dma_desc_pool; slot->async_tx.phys = (dma_addr_t) &hw_desc[idx * MV_XOR_SLOT_SIZE]; diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 3d2565441b36..edb02530e461 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -42,9 +42,9 @@ config DEBUG_GPIO depends on DEBUG_KERNEL help Say Y here to add some extra checks and diagnostics to GPIO calls. - The checks help ensure that GPIOs have been properly initialized - before they are used and that sleeping calls aren not made from - nonsleeping contexts. They can make bitbanged serial protocols + These checks help ensure that GPIOs have been properly initialized + before they are used, and that sleeping calls are not made from + non-sleeping contexts. They can make bitbanged serial protocols slower. The diagnostics help catch the type of setup errors that are most common when setting up new platforms or boards. diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig index e85c8fe9ffcf..7e67dcb3d4f6 100644 --- a/drivers/hid/Kconfig +++ b/drivers/hid/Kconfig @@ -29,11 +29,11 @@ config HID For docs and specs, see http://www.usb.org/developers/hidpage/ - If unsure, say Y + If unsure, say Y. config HID_DEBUG bool "HID debugging support" - default y if !EMBEDDED + default y depends on HID ---help--- This option lets the HID layer output diagnostics about its internal @@ -44,7 +44,7 @@ config HID_DEBUG This feature is useful for those who are either debugging the HID parser or any HID hardware device. - If unsure, say N + If unsure, say Y. config HIDRAW bool "/dev/hidraw raw HID device support" @@ -70,18 +70,6 @@ source "drivers/hid/usbhid/Kconfig" menu "Special HID drivers" depends on HID -config HID_COMPAT - bool "Load all HID drivers on hid core load" - default y - ---help--- - Compatible option for older userspace. If you have system without udev - support of module loading through aliases and also old - module-init-tools which can't handle hid bus, choose Y here. Otherwise - say N. If you say N and your userspace is old enough, the only - functionality you lose is modules autoloading. - - If unsure, say Y. - config HID_A4TECH tristate "A4 tech" if EMBEDDED depends on USB_HID @@ -128,6 +116,14 @@ config HID_CYPRESS ---help--- Support for cypress mouse and barcode readers. +config DRAGONRISE_FF + tristate "DragonRise Inc. force feedback support" + depends on USB_HID + select INPUT_FF_MEMLESS + ---help--- + Say Y here if you want to enable force feedback support for DragonRise Inc. + game controllers. + config HID_EZKEY tristate "Ezkey" if EMBEDDED depends on USB_HID @@ -135,6 +131,13 @@ config HID_EZKEY ---help--- Support for Ezkey BTC 8193 keyboard. +config HID_KYE + tristate "Kye" if EMBEDDED + depends on USB_HID + default !EMBEDDED + ---help--- + Support for Kye/Genius Ergo Mouse. + config HID_GYRATION tristate "Gyration" if EMBEDDED depends on USB_HID @@ -142,6 +145,13 @@ config HID_GYRATION ---help--- Support for Gyration remote control. +config HID_KENSINGTON + tristate "Kensington" if EMBEDDED + depends on USB_HID + default !EMBEDDED + ---help--- + Support for Kensington Slimblade Trackball. + config HID_LOGITECH tristate "Logitech" if EMBEDDED depends on USB_HID @@ -243,7 +253,7 @@ config GREENASIA_FF select INPUT_FF_MEMLESS ---help--- Say Y here if you have a GreenAsia (Product ID 0x12) based game controller - (like MANTA Warior MM816 and SpeedLink Strike2 SL-6635) or adapter + (like MANTA Warrior MM816 and SpeedLink Strike2 SL-6635) or adapter and want to enable force feedback support for it. config HID_TOPSEED diff --git a/drivers/hid/Makefile b/drivers/hid/Makefile index fbd021f153f1..1f7cb0fd4505 100644 --- a/drivers/hid/Makefile +++ b/drivers/hid/Makefile @@ -8,10 +8,6 @@ obj-$(CONFIG_HID) += hid.o hid-$(CONFIG_HID_DEBUG) += hid-debug.o hid-$(CONFIG_HIDRAW) += hidraw.o -ifdef CONFIG_HID_COMPAT -obj-m += hid-dummy.o -endif - hid-logitech-objs := hid-lg.o ifdef CONFIG_LOGITECH_FF hid-logitech-objs += hid-lgff.o @@ -26,8 +22,11 @@ obj-$(CONFIG_HID_BELKIN) += hid-belkin.o obj-$(CONFIG_HID_CHERRY) += hid-cherry.o obj-$(CONFIG_HID_CHICONY) += hid-chicony.o obj-$(CONFIG_HID_CYPRESS) += hid-cypress.o +obj-$(CONFIG_DRAGONRISE_FF) += hid-drff.o obj-$(CONFIG_HID_EZKEY) += hid-ezkey.o obj-$(CONFIG_HID_GYRATION) += hid-gyration.o +obj-$(CONFIG_HID_KENSINGTON) += hid-kensington.o +obj-$(CONFIG_HID_KYE) += hid-kye.o obj-$(CONFIG_HID_LOGITECH) += hid-logitech.o obj-$(CONFIG_HID_MICROSOFT) += hid-microsoft.o obj-$(CONFIG_HID_MONTEREY) += hid-monterey.o diff --git a/drivers/hid/hid-a4tech.c b/drivers/hid/hid-a4tech.c index ebca00e6c103..42ea359e94cf 100644 --- a/drivers/hid/hid-a4tech.c +++ b/drivers/hid/hid-a4tech.c @@ -158,5 +158,3 @@ static void a4_exit(void) module_init(a4_init); module_exit(a4_exit); MODULE_LICENSE("GPL"); - -HID_COMPAT_LOAD_DRIVER(a4tech); diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c index aa28aed0e46c..7359d9d88e46 100644 --- a/drivers/hid/hid-apple.c +++ b/drivers/hid/hid-apple.c @@ -53,7 +53,7 @@ struct apple_key_translation { u8 flags; }; -static struct apple_key_translation apple_fn_keys[] = { +static const struct apple_key_translation apple_fn_keys[] = { { KEY_BACKSPACE, KEY_DELETE }, { KEY_ENTER, KEY_INSERT }, { KEY_F1, KEY_BRIGHTNESSDOWN, APPLE_FLAG_FKEY }, @@ -75,7 +75,7 @@ static struct apple_key_translation apple_fn_keys[] = { { } }; -static struct apple_key_translation powerbook_fn_keys[] = { +static const struct apple_key_translation powerbook_fn_keys[] = { { KEY_BACKSPACE, KEY_DELETE }, { KEY_F1, KEY_BRIGHTNESSDOWN, APPLE_FLAG_FKEY }, { KEY_F2, KEY_BRIGHTNESSUP, APPLE_FLAG_FKEY }, @@ -94,7 +94,7 @@ static struct apple_key_translation powerbook_fn_keys[] = { { } }; -static struct apple_key_translation powerbook_numlock_keys[] = { +static const struct apple_key_translation powerbook_numlock_keys[] = { { KEY_J, KEY_KP1 }, { KEY_K, KEY_KP2 }, { KEY_L, KEY_KP3 }, @@ -117,16 +117,16 @@ static struct apple_key_translation powerbook_numlock_keys[] = { { } }; -static struct apple_key_translation apple_iso_keyboard[] = { +static const struct apple_key_translation apple_iso_keyboard[] = { { KEY_GRAVE, KEY_102ND }, { KEY_102ND, KEY_GRAVE }, { } }; -static struct apple_key_translation *apple_find_translation( - struct apple_key_translation *table, u16 from) +static const struct apple_key_translation *apple_find_translation( + const struct apple_key_translation *table, u16 from) { - struct apple_key_translation *trans; + const struct apple_key_translation *trans; /* Look for the translation */ for (trans = table; trans->from; trans++) @@ -140,7 +140,7 @@ static int hidinput_apple_event(struct hid_device *hid, struct input_dev *input, struct hid_usage *usage, __s32 value) { struct apple_sc *asc = hid_get_drvdata(hid); - struct apple_key_translation *trans; + const struct apple_key_translation *trans; if (usage->code == KEY_FN) { asc->fn_on = !!value; @@ -253,7 +253,7 @@ static void apple_report_fixup(struct hid_device *hdev, __u8 *rdesc, static void apple_setup_input(struct input_dev *input) { - struct apple_key_translation *trans; + const struct apple_key_translation *trans; set_bit(KEY_NUMLOCK, input->keybit); @@ -387,6 +387,12 @@ static const struct hid_device_id apple_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_GEYSER4_JIS), .driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN | APPLE_RDESC_JIS }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_MINI_ANSI), + .driver_data = APPLE_HAS_FN }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_MINI_ISO), + .driver_data = APPLE_HAS_FN | APPLE_ISO_KEYBOARD }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_MINI_JIS), + .driver_data = APPLE_HAS_FN }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_ANSI), .driver_data = APPLE_HAS_FN }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_ISO), @@ -468,5 +474,3 @@ static void apple_exit(void) module_init(apple_init); module_exit(apple_exit); MODULE_LICENSE("GPL"); - -HID_COMPAT_LOAD_DRIVER(apple); diff --git a/drivers/hid/hid-belkin.c b/drivers/hid/hid-belkin.c index 12c8a9ba6ed6..2f6723133a4b 100644 --- a/drivers/hid/hid-belkin.c +++ b/drivers/hid/hid-belkin.c @@ -101,5 +101,3 @@ static void belkin_exit(void) module_init(belkin_init); module_exit(belkin_exit); MODULE_LICENSE("GPL"); - -HID_COMPAT_LOAD_DRIVER(belkin); diff --git a/drivers/hid/hid-cherry.c b/drivers/hid/hid-cherry.c index b833b9769aba..ab8209e7e45c 100644 --- a/drivers/hid/hid-cherry.c +++ b/drivers/hid/hid-cherry.c @@ -83,5 +83,3 @@ static void ch_exit(void) module_init(ch_init); module_exit(ch_exit); MODULE_LICENSE("GPL"); - -HID_COMPAT_LOAD_DRIVER(cherry); diff --git a/drivers/hid/hid-chicony.c b/drivers/hid/hid-chicony.c index a54d4096e0f7..7f91076d8493 100644 --- a/drivers/hid/hid-chicony.c +++ b/drivers/hid/hid-chicony.c @@ -76,5 +76,3 @@ static void ch_exit(void) module_init(ch_init); module_exit(ch_exit); MODULE_LICENSE("GPL"); - -HID_COMPAT_LOAD_DRIVER(chicony); diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 1cc967448f4d..5746a5903bce 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1236,6 +1236,9 @@ static const struct hid_device_id hid_blacklist[] = { { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_GEYSER4_ANSI) }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_GEYSER4_ISO) }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_GEYSER4_JIS) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_MINI_ANSI) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_MINI_ISO) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_MINI_JIS) }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_ANSI) }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_ISO) }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_JIS) }, @@ -1262,6 +1265,7 @@ static const struct hid_device_id hid_blacklist[] = { { HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_BARCODE_1) }, { HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_BARCODE_2) }, { HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_MOUSE) }, + { HID_USB_DEVICE(USB_VENDOR_ID_DRAGONRISE, 0x0006) }, { HID_USB_DEVICE(USB_VENDOR_ID_EZKEY, USB_DEVICE_ID_BTC_8193) }, { HID_USB_DEVICE(USB_VENDOR_ID_GAMERON, USB_DEVICE_ID_GAMERON_DUAL_PSX_ADAPTOR) }, { HID_USB_DEVICE(USB_VENDOR_ID_GAMERON, USB_DEVICE_ID_GAMERON_DUAL_PCS_ADAPTOR) }, @@ -1269,6 +1273,8 @@ static const struct hid_device_id hid_blacklist[] = { { HID_USB_DEVICE(USB_VENDOR_ID_GREENASIA, 0x0012) }, { HID_USB_DEVICE(USB_VENDOR_ID_GYRATION, USB_DEVICE_ID_GYRATION_REMOTE) }, { HID_USB_DEVICE(USB_VENDOR_ID_GYRATION, USB_DEVICE_ID_GYRATION_REMOTE_2) }, + { HID_USB_DEVICE(USB_VENDOR_ID_KENSINGTON, USB_DEVICE_ID_KS_SLIMBLADE) }, + { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_ERGO_525V) }, { HID_USB_DEVICE(USB_VENDOR_ID_LABTEC, USB_DEVICE_ID_LABTEC_WIRELESS_KEYBOARD) }, { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_MX3000_RECEIVER) }, { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_S510_RECEIVER) }, @@ -1813,14 +1819,21 @@ void hid_unregister_driver(struct hid_driver *hdrv) } EXPORT_SYMBOL_GPL(hid_unregister_driver); -#ifdef CONFIG_HID_COMPAT -static void hid_compat_load(struct work_struct *ws) +int hid_check_keys_pressed(struct hid_device *hid) { - request_module("hid-dummy"); + struct hid_input *hidinput; + int i; + + list_for_each_entry(hidinput, &hid->inputs, list) { + for (i = 0; i < BITS_TO_LONGS(KEY_MAX); i++) + if (hidinput->input->key[i]) + return 1; + } + + return 0; } -static DECLARE_WORK(hid_compat_work, hid_compat_load); -static struct workqueue_struct *hid_compat_wq; -#endif + +EXPORT_SYMBOL_GPL(hid_check_keys_pressed); static int __init hid_init(void) { @@ -1836,15 +1849,6 @@ static int __init hid_init(void) if (ret) goto err_bus; -#ifdef CONFIG_HID_COMPAT - hid_compat_wq = create_singlethread_workqueue("hid_compat"); - if (!hid_compat_wq) { - hidraw_exit(); - goto err; - } - queue_work(hid_compat_wq, &hid_compat_work); -#endif - return 0; err_bus: bus_unregister(&hid_bus_type); @@ -1854,9 +1858,6 @@ err: static void __exit hid_exit(void) { -#ifdef CONFIG_HID_COMPAT - destroy_workqueue(hid_compat_wq); -#endif hidraw_exit(); bus_unregister(&hid_bus_type); } diff --git a/drivers/hid/hid-cypress.c b/drivers/hid/hid-cypress.c index 5d69d27b935d..9d6d3b91773b 100644 --- a/drivers/hid/hid-cypress.c +++ b/drivers/hid/hid-cypress.c @@ -154,5 +154,3 @@ static void cp_exit(void) module_init(cp_init); module_exit(cp_exit); MODULE_LICENSE("GPL"); - -HID_COMPAT_LOAD_DRIVER(cypress); diff --git a/drivers/hid/hid-drff.c b/drivers/hid/hid-drff.c new file mode 100644 index 000000000000..34f3eb65100b --- /dev/null +++ b/drivers/hid/hid-drff.c @@ -0,0 +1,188 @@ +/* + * Force feedback support for DragonRise Inc. game controllers + * + * From what I have gathered, these devices are mass produced in China and are + * distributed under several vendors. They often share the same design as + * the original PlayStation DualShock controller. + * + * 0079:0006 "DragonRise Inc. Generic USB Joystick " + * - tested with a Tesun USB-703 game controller. + * + * Copyright (c) 2009 Richard Walmsley <richwalm@gmail.com> + */ + +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include <linux/input.h> +#include <linux/usb.h> +#include <linux/hid.h> + +#include "hid-ids.h" +#include "usbhid/usbhid.h" + +struct drff_device { + struct hid_report *report; +}; + +static int drff_play(struct input_dev *dev, void *data, + struct ff_effect *effect) +{ + struct hid_device *hid = input_get_drvdata(dev); + struct drff_device *drff = data; + int strong, weak; + + strong = effect->u.rumble.strong_magnitude; + weak = effect->u.rumble.weak_magnitude; + + dbg_hid("called with 0x%04x 0x%04x", strong, weak); + + if (strong || weak) { + strong = strong * 0xff / 0xffff; + weak = weak * 0xff / 0xffff; + + /* While reverse engineering this device, I found that when + this value is set, it causes the strong rumble to function + at a near maximum speed, so we'll bypass it. */ + if (weak == 0x0a) + weak = 0x0b; + + drff->report->field[0]->value[0] = 0x51; + drff->report->field[0]->value[1] = 0x00; + drff->report->field[0]->value[2] = weak; + drff->report->field[0]->value[4] = strong; + usbhid_submit_report(hid, drff->report, USB_DIR_OUT); + + drff->report->field[0]->value[0] = 0xfa; + drff->report->field[0]->value[1] = 0xfe; + } else { + drff->report->field[0]->value[0] = 0xf3; + drff->report->field[0]->value[1] = 0x00; + } + + drff->report->field[0]->value[2] = 0x00; + drff->report->field[0]->value[4] = 0x00; + dbg_hid("running with 0x%02x 0x%02x", strong, weak); + usbhid_submit_report(hid, drff->report, USB_DIR_OUT); + + return 0; +} + +static int drff_init(struct hid_device *hid) +{ + struct drff_device *drff; + struct hid_report *report; + struct hid_input *hidinput = list_first_entry(&hid->inputs, + struct hid_input, list); + struct list_head *report_list = + &hid->report_enum[HID_OUTPUT_REPORT].report_list; + struct input_dev *dev = hidinput->input; + int error; + + if (list_empty(report_list)) { + dev_err(&hid->dev, "no output reports found\n"); + return -ENODEV; + } + + report = list_first_entry(report_list, struct hid_report, list); + if (report->maxfield < 1) { + dev_err(&hid->dev, "no fields in the report\n"); + return -ENODEV; + } + + if (report->field[0]->report_count < 7) { + dev_err(&hid->dev, "not enough values in the field\n"); + return -ENODEV; + } + + drff = kzalloc(sizeof(struct drff_device), GFP_KERNEL); + if (!drff) + return -ENOMEM; + + set_bit(FF_RUMBLE, dev->ffbit); + + error = input_ff_create_memless(dev, drff, drff_play); + if (error) { + kfree(drff); + return error; + } + + drff->report = report; + drff->report->field[0]->value[0] = 0xf3; + drff->report->field[0]->value[1] = 0x00; + drff->report->field[0]->value[2] = 0x00; + drff->report->field[0]->value[3] = 0x00; + drff->report->field[0]->value[4] = 0x00; + drff->report->field[0]->value[5] = 0x00; + drff->report->field[0]->value[6] = 0x00; + usbhid_submit_report(hid, drff->report, USB_DIR_OUT); + + dev_info(&hid->dev, "Force Feedback for DragonRise Inc. game " + "controllers by Richard Walmsley <richwalm@gmail.com>\n"); + + return 0; +} + +static int dr_probe(struct hid_device *hdev, const struct hid_device_id *id) +{ + int ret; + + dev_dbg(&hdev->dev, "DragonRise Inc. HID hardware probe..."); + + ret = hid_parse(hdev); + if (ret) { + dev_err(&hdev->dev, "parse failed\n"); + goto err; + } + + ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT & ~HID_CONNECT_FF); + if (ret) { + dev_err(&hdev->dev, "hw start failed\n"); + goto err; + } + + drff_init(hdev); + + return 0; +err: + return ret; +} + +static const struct hid_device_id dr_devices[] = { + { HID_USB_DEVICE(USB_VENDOR_ID_DRAGONRISE, 0x0006), }, + { } +}; +MODULE_DEVICE_TABLE(hid, dr_devices); + +static struct hid_driver dr_driver = { + .name = "dragonrise", + .id_table = dr_devices, + .probe = dr_probe, +}; + +static int __init dr_init(void) +{ + return hid_register_driver(&dr_driver); +} + +static void __exit dr_exit(void) +{ + hid_unregister_driver(&dr_driver); +} + +module_init(dr_init); +module_exit(dr_exit); +MODULE_LICENSE("GPL"); diff --git a/drivers/hid/hid-dummy.c b/drivers/hid/hid-dummy.c deleted file mode 100644 index b4cc0f743d63..000000000000 --- a/drivers/hid/hid-dummy.c +++ /dev/null @@ -1,78 +0,0 @@ -#include <linux/autoconf.h> -#include <linux/module.h> -#include <linux/hid.h> - -static int __init hid_dummy_init(void) -{ -#ifdef CONFIG_HID_A4TECH_MODULE - HID_COMPAT_CALL_DRIVER(a4tech); -#endif -#ifdef CONFIG_HID_APPLE_MODULE - HID_COMPAT_CALL_DRIVER(apple); -#endif -#ifdef CONFIG_HID_BELKIN_MODULE - HID_COMPAT_CALL_DRIVER(belkin); -#endif -#ifdef CONFIG_HID_BRIGHT_MODULE - HID_COMPAT_CALL_DRIVER(bright); -#endif -#ifdef CONFIG_HID_CHERRY_MODULE - HID_COMPAT_CALL_DRIVER(cherry); -#endif -#ifdef CONFIG_HID_CHICONY_MODULE - HID_COMPAT_CALL_DRIVER(chicony); -#endif -#ifdef CONFIG_HID_CYPRESS_MODULE - HID_COMPAT_CALL_DRIVER(cypress); -#endif -#ifdef CONFIG_HID_DELL_MODULE - HID_COMPAT_CALL_DRIVER(dell); -#endif -#ifdef CONFIG_HID_EZKEY_MODULE - HID_COMPAT_CALL_DRIVER(ezkey); -#endif -#ifdef CONFIG_HID_GYRATION_MODULE - HID_COMPAT_CALL_DRIVER(gyration); -#endif -#ifdef CONFIG_HID_LOGITECH_MODULE - HID_COMPAT_CALL_DRIVER(logitech); -#endif -#ifdef CONFIG_HID_MICROSOFT_MODULE - HID_COMPAT_CALL_DRIVER(microsoft); -#endif -#ifdef CONFIG_HID_MONTEREY_MODULE - HID_COMPAT_CALL_DRIVER(monterey); -#endif -#ifdef CONFIG_HID_NTRIG_MODULE - HID_COMPAT_CALL_DRIVER(ntrig); -#endif -#ifdef CONFIG_HID_PANTHERLORD_MODULE - HID_COMPAT_CALL_DRIVER(pantherlord); -#endif -#ifdef CONFIG_HID_PETALYNX_MODULE - HID_COMPAT_CALL_DRIVER(petalynx); -#endif -#ifdef CONFIG_HID_SAMSUNG_MODULE - HID_COMPAT_CALL_DRIVER(samsung); -#endif -#ifdef CONFIG_HID_SONY_MODULE - HID_COMPAT_CALL_DRIVER(sony); -#endif -#ifdef CONFIG_HID_SUNPLUS_MODULE - HID_COMPAT_CALL_DRIVER(sunplus); -#endif -#ifdef CONFIG_GREENASIA_FF_MODULE - HID_COMPAT_CALL_DRIVER(greenasia); -#endif -#ifdef CONFIG_THRUSTMASTER_FF_MODULE - HID_COMPAT_CALL_DRIVER(thrustmaster); -#endif -#ifdef CONFIG_ZEROPLUS_FF_MODULE - HID_COMPAT_CALL_DRIVER(zeroplus); -#endif - - return -EIO; -} -module_init(hid_dummy_init); - -MODULE_LICENSE("GPL"); diff --git a/drivers/hid/hid-ezkey.c b/drivers/hid/hid-ezkey.c index deb42f931b7e..0a1fe054799b 100644 --- a/drivers/hid/hid-ezkey.c +++ b/drivers/hid/hid-ezkey.c @@ -91,5 +91,3 @@ static void ez_exit(void) module_init(ez_init); module_exit(ez_exit); MODULE_LICENSE("GPL"); - -HID_COMPAT_LOAD_DRIVER(ezkey); diff --git a/drivers/hid/hid-gaff.c b/drivers/hid/hid-gaff.c index 71211f6a4f02..510ad3ab8d33 100644 --- a/drivers/hid/hid-gaff.c +++ b/drivers/hid/hid-gaff.c @@ -181,5 +181,3 @@ static void __exit ga_exit(void) module_init(ga_init); module_exit(ga_exit); MODULE_LICENSE("GPL"); - -HID_COMPAT_LOAD_DRIVER(greenasia); diff --git a/drivers/hid/hid-gyration.c b/drivers/hid/hid-gyration.c index 04a0afec52ac..d42d222097a8 100644 --- a/drivers/hid/hid-gyration.c +++ b/drivers/hid/hid-gyration.c @@ -94,5 +94,3 @@ static void gyration_exit(void) module_init(gyration_init); module_exit(gyration_exit); MODULE_LICENSE("GPL"); - -HID_COMPAT_LOAD_DRIVER(gyration); diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 88511970508d..bdeda4c7cc13 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -67,6 +67,9 @@ #define USB_DEVICE_ID_APPLE_GEYSER4_ANSI 0x021a #define USB_DEVICE_ID_APPLE_GEYSER4_ISO 0x021b #define USB_DEVICE_ID_APPLE_GEYSER4_JIS 0x021c +#define USB_DEVICE_ID_APPLE_ALU_MINI_ANSI 0x021d +#define USB_DEVICE_ID_APPLE_ALU_MINI_ISO 0x021e +#define USB_DEVICE_ID_APPLE_ALU_MINI_JIS 0x021f #define USB_DEVICE_ID_APPLE_ALU_ANSI 0x0220 #define USB_DEVICE_ID_APPLE_ALU_ISO 0x0221 #define USB_DEVICE_ID_APPLE_ALU_JIS 0x0222 @@ -148,6 +151,8 @@ #define USB_VENDOR_ID_DMI 0x0c0b #define USB_DEVICE_ID_DMI_ENC 0x5fab +#define USB_VENDOR_ID_DRAGONRISE 0x0079 + #define USB_VENDOR_ID_ELO 0x04E7 #define USB_DEVICE_ID_ELO_TS2700 0x0020 @@ -272,6 +277,9 @@ #define USB_DEVICE_ID_LD_POWERCONTROL 0x2030 #define USB_DEVICE_ID_LD_MACHINETEST 0x2040 +#define USB_VENDOR_ID_KENSINGTON 0x047d +#define USB_DEVICE_ID_KS_SLIMBLADE 0x2041 + #define USB_VENDOR_ID_LOGITECH 0x046d #define USB_DEVICE_ID_LOGITECH_RECEIVER 0xc101 #define USB_DEVICE_ID_LOGITECH_HARMONY_FIRST 0xc110 @@ -418,6 +426,8 @@ #define USB_VENDOR_ID_ZEROPLUS 0x0c12 #define USB_VENDOR_ID_KYE 0x0458 +#define USB_DEVICE_ID_KYE_ERGO_525V 0x0087 #define USB_DEVICE_ID_KYE_GPEN_560 0x5003 + #endif diff --git a/drivers/hid/hid-kensington.c b/drivers/hid/hid-kensington.c new file mode 100644 index 000000000000..7353bd79cbe9 --- /dev/null +++ b/drivers/hid/hid-kensington.c @@ -0,0 +1,63 @@ +/* + * HID driver for Kensigton Slimblade Trackball + * + * Copyright (c) 2009 Jiri Kosina + */ + +/* + * 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. + */ + +#include <linux/device.h> +#include <linux/input.h> +#include <linux/hid.h> +#include <linux/module.h> + +#include "hid-ids.h" + +#define ks_map_key(c) hid_map_usage(hi, usage, bit, max, EV_KEY, (c)) + +static int ks_input_mapping(struct hid_device *hdev, struct hid_input *hi, + struct hid_field *field, struct hid_usage *usage, + unsigned long **bit, int *max) +{ + if ((usage->hid & HID_USAGE_PAGE) != HID_UP_MSVENDOR) + return 0; + + switch (usage->hid & HID_USAGE) { + case 0x01: ks_map_key(BTN_MIDDLE); break; + case 0x02: ks_map_key(BTN_SIDE); break; + default: + return 0; + } + return 1; +} + +static const struct hid_device_id ks_devices[] = { + { HID_USB_DEVICE(USB_VENDOR_ID_KENSINGTON, USB_DEVICE_ID_KS_SLIMBLADE) }, + { } +}; +MODULE_DEVICE_TABLE(hid, ks_devices); + +static struct hid_driver ks_driver = { + .name = "kensington", + .id_table = ks_devices, + .input_mapping = ks_input_mapping, +}; + +static int ks_init(void) +{ + return hid_register_driver(&ks_driver); +} + +static void ks_exit(void) +{ + hid_unregister_driver(&ks_driver); +} + +module_init(ks_init); +module_exit(ks_exit); +MODULE_LICENSE("GPL"); diff --git a/drivers/hid/hid-kye.c b/drivers/hid/hid-kye.c new file mode 100644 index 000000000000..72ee3fec56d9 --- /dev/null +++ b/drivers/hid/hid-kye.c @@ -0,0 +1,69 @@ +/* + * HID driver for Kye/Genius devices not fully compliant with HID standard + * + * Copyright (c) 2009 Jiri Kosina + * Copyright (c) 2009 Tomas Hanak + */ + +/* + * 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. + */ + +#include <linux/device.h> +#include <linux/hid.h> +#include <linux/module.h> + +#include "hid-ids.h" + +/* the fixups that need to be done: + * - change led usage page to button for extra buttons + * - report size 8 count 1 must be size 1 count 8 for button bitfield + * - change the button usage range to 4-7 for the extra buttons + */ +static void kye_report_fixup(struct hid_device *hdev, __u8 *rdesc, + unsigned int rsize) +{ + if (rsize >= 74 && + rdesc[61] == 0x05 && rdesc[62] == 0x08 && + rdesc[63] == 0x19 && rdesc[64] == 0x08 && + rdesc[65] == 0x29 && rdesc[66] == 0x0f && + rdesc[71] == 0x75 && rdesc[72] == 0x08 && + rdesc[73] == 0x95 && rdesc[74] == 0x01) { + dev_info(&hdev->dev, "fixing up Kye/Genius Ergo Mouse report " + "descriptor\n"); + rdesc[62] = 0x09; + rdesc[64] = 0x04; + rdesc[66] = 0x07; + rdesc[72] = 0x01; + rdesc[74] = 0x08; + } +} + +static const struct hid_device_id kye_devices[] = { + { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_ERGO_525V) }, + { } +}; +MODULE_DEVICE_TABLE(hid, kye_devices); + +static struct hid_driver kye_driver = { + .name = "kye", + .id_table = kye_devices, + .report_fixup = kye_report_fixup, +}; + +static int kye_init(void) +{ + return hid_register_driver(&kye_driver); +} + +static void kye_exit(void) +{ + hid_unregister_driver(&kye_driver); +} + +module_init(kye_init); +module_exit(kye_exit); +MODULE_LICENSE("GPL"); diff --git a/drivers/hid/hid-lg.c b/drivers/hid/hid-lg.c index 83e07c9f4144..7b80cb694982 100644 --- a/drivers/hid/hid-lg.c +++ b/drivers/hid/hid-lg.c @@ -326,5 +326,3 @@ static void lg_exit(void) module_init(lg_init); module_exit(lg_exit); MODULE_LICENSE("GPL"); - -HID_COMPAT_LOAD_DRIVER(logitech); diff --git a/drivers/hid/hid-microsoft.c b/drivers/hid/hid-microsoft.c index 25b10dcad90d..5e9e37a0506d 100644 --- a/drivers/hid/hid-microsoft.c +++ b/drivers/hid/hid-microsoft.c @@ -210,5 +210,3 @@ static void ms_exit(void) module_init(ms_init); module_exit(ms_exit); MODULE_LICENSE("GPL"); - -HID_COMPAT_LOAD_DRIVER(microsoft); diff --git a/drivers/hid/hid-monterey.c b/drivers/hid/hid-monterey.c index f3a85a065f18..240f87618be6 100644 --- a/drivers/hid/hid-monterey.c +++ b/drivers/hid/hid-monterey.c @@ -78,5 +78,3 @@ static void mr_exit(void) module_init(mr_init); module_exit(mr_exit); MODULE_LICENSE("GPL"); - -HID_COMPAT_LOAD_DRIVER(monterey); diff --git a/drivers/hid/hid-ntrig.c b/drivers/hid/hid-ntrig.c index db44fbd7bdf6..c5b252be9c21 100644 --- a/drivers/hid/hid-ntrig.c +++ b/drivers/hid/hid-ntrig.c @@ -78,5 +78,3 @@ static void ntrig_exit(void) module_init(ntrig_init); module_exit(ntrig_exit); MODULE_LICENSE("GPL"); - -HID_COMPAT_LOAD_DRIVER(ntrig); diff --git a/drivers/hid/hid-petalynx.c b/drivers/hid/hid-petalynx.c index 10945fe12d50..2e83e8ff891a 100644 --- a/drivers/hid/hid-petalynx.c +++ b/drivers/hid/hid-petalynx.c @@ -118,5 +118,3 @@ static void pl_exit(void) module_init(pl_init); module_exit(pl_exit); MODULE_LICENSE("GPL"); - -HID_COMPAT_LOAD_DRIVER(petalynx); diff --git a/drivers/hid/hid-pl.c b/drivers/hid/hid-pl.c index 46941f979b9d..4db9a3483760 100644 --- a/drivers/hid/hid-pl.c +++ b/drivers/hid/hid-pl.c @@ -9,9 +9,12 @@ * - contains two reports, one for each port (HID_QUIRK_MULTI_INPUT) * * 0e8f:0003 "GreenAsia Inc. USB Joystick " - * - tested with K??ng Gaming gamepad + * - tested with König Gaming gamepad * - * Copyright (c) 2007 Anssi Hannula <anssi.hannula@gmail.com> + * 0e8f:0003 "GASIA USB Gamepad" + * - another version of the König gamepad + * + * Copyright (c) 2007, 2009 Anssi Hannula <anssi.hannula@gmail.com> */ /* @@ -46,6 +49,8 @@ struct plff_device { struct hid_report *report; + s32 *strong; + s32 *weak; }; static int hid_plff_play(struct input_dev *dev, void *data, @@ -62,8 +67,8 @@ static int hid_plff_play(struct input_dev *dev, void *data, left = left * 0x7f / 0xffff; right = right * 0x7f / 0xffff; - plff->report->field[0]->value[2] = left; - plff->report->field[0]->value[3] = right; + *plff->strong = left; + *plff->weak = right; debug("running with 0x%02x 0x%02x", left, right); usbhid_submit_report(hid, plff->report, USB_DIR_OUT); @@ -80,6 +85,8 @@ static int plff_init(struct hid_device *hid) struct list_head *report_ptr = report_list; struct input_dev *dev; int error; + s32 *strong; + s32 *weak; /* The device contains one output report per physical device, all containing 1 field, which contains 4 ff00.0002 usages and 4 16bit @@ -87,7 +94,12 @@ static int plff_init(struct hid_device *hid) The input reports also contain a field which contains 8 ff00.0001 usages and 8 boolean values. Their meaning is - currently unknown. */ + currently unknown. + + A version of the 0e8f:0003 exists that has all the values in + separate fields and misses the extra input field, thus resembling + Zeroplus (hid-zpff) devices. + */ if (list_empty(report_list)) { dev_err(&hid->dev, "no output reports found\n"); @@ -110,8 +122,21 @@ static int plff_init(struct hid_device *hid) return -ENODEV; } - if (report->field[0]->report_count < 4) { - dev_err(&hid->dev, "not enough values in the field\n"); + if (report->field[0]->report_count >= 4) { + report->field[0]->value[0] = 0x00; + report->field[0]->value[1] = 0x00; + strong = &report->field[0]->value[2]; + weak = &report->field[0]->value[3]; + debug("detected single-field device"); + } else if (report->maxfield >= 4 && report->field[0]->maxusage == 1 && + report->field[0]->usage[0].hid == (HID_UP_LED | 0x43)) { + report->field[0]->value[0] = 0x00; + report->field[1]->value[0] = 0x00; + strong = &report->field[2]->value[0]; + weak = &report->field[3]->value[0]; + debug("detected 4-field device"); + } else { + dev_err(&hid->dev, "not enough fields or values\n"); return -ENODEV; } @@ -130,10 +155,11 @@ static int plff_init(struct hid_device *hid) } plff->report = report; - plff->report->field[0]->value[0] = 0x00; - plff->report->field[0]->value[1] = 0x00; - plff->report->field[0]->value[2] = 0x00; - plff->report->field[0]->value[3] = 0x00; + plff->strong = strong; + plff->weak = weak; + + *strong = 0x00; + *weak = 0x00; usbhid_submit_report(hid, plff->report, USB_DIR_OUT); } @@ -180,7 +206,7 @@ static const struct hid_device_id pl_devices[] = { .driver_data = 1 }, /* Twin USB Joystick */ { HID_USB_DEVICE(USB_VENDOR_ID_GAMERON, USB_DEVICE_ID_GAMERON_DUAL_PCS_ADAPTOR), .driver_data = 1 }, /* Twin USB Joystick */ - { HID_USB_DEVICE(USB_VENDOR_ID_GREENASIA, 0x0003), }, /* GreenAsia Inc. USB Joystick */ + { HID_USB_DEVICE(USB_VENDOR_ID_GREENASIA, 0x0003), }, { } }; MODULE_DEVICE_TABLE(hid, pl_devices); @@ -204,5 +230,3 @@ static void pl_exit(void) module_init(pl_init); module_exit(pl_exit); MODULE_LICENSE("GPL"); - -HID_COMPAT_LOAD_DRIVER(pantherlord); diff --git a/drivers/hid/hid-samsung.c b/drivers/hid/hid-samsung.c index 15f3c0492450..07083aa6c19a 100644 --- a/drivers/hid/hid-samsung.c +++ b/drivers/hid/hid-samsung.c @@ -96,5 +96,3 @@ static void samsung_exit(void) module_init(samsung_init); module_exit(samsung_exit); MODULE_LICENSE("GPL"); - -HID_COMPAT_LOAD_DRIVER(samsung); diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c index dd5a3979a4de..c2599388a350 100644 --- a/drivers/hid/hid-sony.c +++ b/drivers/hid/hid-sony.c @@ -148,5 +148,3 @@ static void sony_exit(void) module_init(sony_init); module_exit(sony_exit); MODULE_LICENSE("GPL"); - -HID_COMPAT_LOAD_DRIVER(sony); diff --git a/drivers/hid/hid-sunplus.c b/drivers/hid/hid-sunplus.c index 5ba68f7dbb78..e0a8fd36a85b 100644 --- a/drivers/hid/hid-sunplus.c +++ b/drivers/hid/hid-sunplus.c @@ -78,5 +78,3 @@ static void sp_exit(void) module_init(sp_init); module_exit(sp_exit); MODULE_LICENSE("GPL"); - -HID_COMPAT_LOAD_DRIVER(sunplus); diff --git a/drivers/hid/hid-tmff.c b/drivers/hid/hid-tmff.c index 1b7cba0f7e1f..7c1f7b50330c 100644 --- a/drivers/hid/hid-tmff.c +++ b/drivers/hid/hid-tmff.c @@ -265,5 +265,3 @@ static void tm_exit(void) module_init(tm_init); module_exit(tm_exit); MODULE_LICENSE("GPL"); - -HID_COMPAT_LOAD_DRIVER(thrustmaster); diff --git a/drivers/hid/hid-topseed.c b/drivers/hid/hid-topseed.c index cca64a0564a9..152ccfabeba5 100644 --- a/drivers/hid/hid-topseed.c +++ b/drivers/hid/hid-topseed.c @@ -73,5 +73,3 @@ static void ts_exit(void) module_init(ts_init); module_exit(ts_exit); MODULE_LICENSE("GPL"); - -HID_COMPAT_LOAD_DRIVER(topseed); diff --git a/drivers/hid/hid-zpff.c b/drivers/hid/hid-zpff.c index ea82f3718b21..85a198a18537 100644 --- a/drivers/hid/hid-zpff.c +++ b/drivers/hid/hid-zpff.c @@ -158,5 +158,3 @@ static void zp_exit(void) module_init(zp_init); module_exit(zp_exit); MODULE_LICENSE("GPL"); - -HID_COMPAT_LOAD_DRIVER(zeroplus); diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c index 02b19db5442e..e263d4731179 100644 --- a/drivers/hid/hidraw.c +++ b/drivers/hid/hidraw.c @@ -181,9 +181,17 @@ static int hidraw_open(struct inode *inode, struct file *file) dev = hidraw_table[minor]; if (!dev->open++) { + if (dev->hid->ll_driver->power) { + err = dev->hid->ll_driver->power(dev->hid, PM_HINT_FULLON); + if (err < 0) + goto out_unlock; + } err = dev->hid->ll_driver->open(dev->hid); - if (err < 0) + if (err < 0) { + if (dev->hid->ll_driver->power) + dev->hid->ll_driver->power(dev->hid, PM_HINT_NORMAL); dev->open--; + } } out_unlock: @@ -209,10 +217,13 @@ static int hidraw_release(struct inode * inode, struct file * file) list_del(&list->node); dev = hidraw_table[minor]; if (!--dev->open) { - if (list->hidraw->exist) + if (list->hidraw->exist) { + if (dev->hid->ll_driver->power) + dev->hid->ll_driver->power(dev->hid, PM_HINT_NORMAL); dev->hid->ll_driver->close(dev->hid); - else + } else { kfree(list->hidraw); + } } kfree(list); diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c index f0a0f72238ab..4306cb1b8ce5 100644 --- a/drivers/hid/usbhid/hid-core.c +++ b/drivers/hid/usbhid/hid-core.c @@ -5,6 +5,7 @@ * Copyright (c) 2000-2005 Vojtech Pavlik <vojtech@suse.cz> * Copyright (c) 2005 Michael Haboustak <mike-@cinci.rr.com> for Concept2, Inc * Copyright (c) 2006-2008 Jiri Kosina + * Copyright (c) 2007-2008 Oliver Neukum */ /* @@ -27,6 +28,7 @@ #include <asm/byteorder.h> #include <linux/input.h> #include <linux/wait.h> +#include <linux/workqueue.h> #include <linux/usb.h> @@ -53,6 +55,10 @@ static unsigned int hid_mousepoll_interval; module_param_named(mousepoll, hid_mousepoll_interval, uint, 0644); MODULE_PARM_DESC(mousepoll, "Polling interval of mice"); +static unsigned int ignoreled; +module_param_named(ignoreled, ignoreled, uint, 0644); +MODULE_PARM_DESC(ignoreled, "Autosuspend with active leds"); + /* Quirks specified at module load time */ static char *quirks_param[MAX_USBHID_BOOT_QUIRKS] = { [ 0 ... (MAX_USBHID_BOOT_QUIRKS - 1) ] = NULL }; module_param_array_named(quirks, quirks_param, charp, NULL, 0444); @@ -63,8 +69,13 @@ MODULE_PARM_DESC(quirks, "Add/modify USB HID quirks by specifying " /* * Input submission and I/O error handler. */ +static DEFINE_MUTEX(hid_open_mut); +static struct workqueue_struct *resumption_waker; static void hid_io_error(struct hid_device *hid); +static int hid_submit_out(struct hid_device *hid); +static int hid_submit_ctrl(struct hid_device *hid); +static void hid_cancel_delayed_stuff(struct usbhid_device *usbhid); /* Start up the input URB */ static int hid_start_in(struct hid_device *hid) @@ -73,15 +84,16 @@ static int hid_start_in(struct hid_device *hid) int rc = 0; struct usbhid_device *usbhid = hid->driver_data; - spin_lock_irqsave(&usbhid->inlock, flags); - if (hid->open > 0 && !test_bit(HID_SUSPENDED, &usbhid->iofl) && + spin_lock_irqsave(&usbhid->lock, flags); + if (hid->open > 0 && !test_bit(HID_DISCONNECTED, &usbhid->iofl) && + !test_bit(HID_REPORTED_IDLE, &usbhid->iofl) && !test_and_set_bit(HID_IN_RUNNING, &usbhid->iofl)) { rc = usb_submit_urb(usbhid->urbin, GFP_ATOMIC); if (rc != 0) clear_bit(HID_IN_RUNNING, &usbhid->iofl); } - spin_unlock_irqrestore(&usbhid->inlock, flags); + spin_unlock_irqrestore(&usbhid->lock, flags); return rc; } @@ -145,7 +157,7 @@ static void hid_io_error(struct hid_device *hid) unsigned long flags; struct usbhid_device *usbhid = hid->driver_data; - spin_lock_irqsave(&usbhid->inlock, flags); + spin_lock_irqsave(&usbhid->lock, flags); /* Stop when disconnected */ if (test_bit(HID_DISCONNECTED, &usbhid->iofl)) @@ -175,7 +187,51 @@ static void hid_io_error(struct hid_device *hid) mod_timer(&usbhid->io_retry, jiffies + msecs_to_jiffies(usbhid->retry_delay)); done: - spin_unlock_irqrestore(&usbhid->inlock, flags); + spin_unlock_irqrestore(&usbhid->lock, flags); +} + +static void usbhid_mark_busy(struct usbhid_device *usbhid) +{ + struct usb_interface *intf = usbhid->intf; + + usb_mark_last_busy(interface_to_usbdev(intf)); +} + +static int usbhid_restart_out_queue(struct usbhid_device *usbhid) +{ + struct hid_device *hid = usb_get_intfdata(usbhid->intf); + int kicked; + + if (!hid) + return 0; + + if ((kicked = (usbhid->outhead != usbhid->outtail))) { + dbg("Kicking head %d tail %d", usbhid->outhead, usbhid->outtail); + if (hid_submit_out(hid)) { + clear_bit(HID_OUT_RUNNING, &usbhid->iofl); + wake_up(&usbhid->wait); + } + } + return kicked; +} + +static int usbhid_restart_ctrl_queue(struct usbhid_device *usbhid) +{ + struct hid_device *hid = usb_get_intfdata(usbhid->intf); + int kicked; + + WARN_ON(hid == NULL); + if (!hid) + return 0; + + if ((kicked = (usbhid->ctrlhead != usbhid->ctrltail))) { + dbg("Kicking head %d tail %d", usbhid->ctrlhead, usbhid->ctrltail); + if (hid_submit_ctrl(hid)) { + clear_bit(HID_CTRL_RUNNING, &usbhid->iofl); + wake_up(&usbhid->wait); + } + } + return kicked; } /* @@ -190,12 +246,23 @@ static void hid_irq_in(struct urb *urb) switch (urb->status) { case 0: /* success */ + usbhid_mark_busy(usbhid); usbhid->retry_delay = 0; hid_input_report(urb->context, HID_INPUT_REPORT, urb->transfer_buffer, urb->actual_length, 1); + /* + * autosuspend refused while keys are pressed + * because most keyboards don't wake up when + * a key is released + */ + if (hid_check_keys_pressed(hid)) + set_bit(HID_KEYS_PRESSED, &usbhid->iofl); + else + clear_bit(HID_KEYS_PRESSED, &usbhid->iofl); break; case -EPIPE: /* stall */ + usbhid_mark_busy(usbhid); clear_bit(HID_IN_RUNNING, &usbhid->iofl); set_bit(HID_CLEAR_HALT, &usbhid->iofl); schedule_work(&usbhid->reset_work); @@ -209,6 +276,7 @@ static void hid_irq_in(struct urb *urb) case -EPROTO: /* protocol error or unplug */ case -ETIME: /* protocol error or unplug */ case -ETIMEDOUT: /* Should never happen, but... */ + usbhid_mark_busy(usbhid); clear_bit(HID_IN_RUNNING, &usbhid->iofl); hid_io_error(hid); return; @@ -239,16 +307,25 @@ static int hid_submit_out(struct hid_device *hid) report = usbhid->out[usbhid->outtail].report; raw_report = usbhid->out[usbhid->outtail].raw_report; - usbhid->urbout->transfer_buffer_length = ((report->size - 1) >> 3) + 1 + (report->id > 0); - usbhid->urbout->dev = hid_to_usb_dev(hid); - memcpy(usbhid->outbuf, raw_report, usbhid->urbout->transfer_buffer_length); - kfree(raw_report); + if (!test_bit(HID_REPORTED_IDLE, &usbhid->iofl)) { + usbhid->urbout->transfer_buffer_length = ((report->size - 1) >> 3) + 1 + (report->id > 0); + usbhid->urbout->dev = hid_to_usb_dev(hid); + memcpy(usbhid->outbuf, raw_report, usbhid->urbout->transfer_buffer_length); + kfree(raw_report); - dbg_hid("submitting out urb\n"); + dbg_hid("submitting out urb\n"); - if (usb_submit_urb(usbhid->urbout, GFP_ATOMIC)) { - err_hid("usb_submit_urb(out) failed"); - return -1; + if (usb_submit_urb(usbhid->urbout, GFP_ATOMIC)) { + err_hid("usb_submit_urb(out) failed"); + return -1; + } + } else { + /* + * queue work to wake up the device. + * as the work queue is freezeable, this is safe + * with respect to STD and STR + */ + queue_work(resumption_waker, &usbhid->restart_work); } return 0; @@ -266,41 +343,50 @@ static int hid_submit_ctrl(struct hid_device *hid) raw_report = usbhid->ctrl[usbhid->ctrltail].raw_report; dir = usbhid->ctrl[usbhid->ctrltail].dir; - len = ((report->size - 1) >> 3) + 1 + (report->id > 0); - if (dir == USB_DIR_OUT) { - usbhid->urbctrl->pipe = usb_sndctrlpipe(hid_to_usb_dev(hid), 0); - usbhid->urbctrl->transfer_buffer_length = len; - memcpy(usbhid->ctrlbuf, raw_report, len); - kfree(raw_report); - } else { - int maxpacket, padlen; - - usbhid->urbctrl->pipe = usb_rcvctrlpipe(hid_to_usb_dev(hid), 0); - maxpacket = usb_maxpacket(hid_to_usb_dev(hid), usbhid->urbctrl->pipe, 0); - if (maxpacket > 0) { - padlen = DIV_ROUND_UP(len, maxpacket); - padlen *= maxpacket; - if (padlen > usbhid->bufsize) - padlen = usbhid->bufsize; - } else - padlen = 0; - usbhid->urbctrl->transfer_buffer_length = padlen; - } - usbhid->urbctrl->dev = hid_to_usb_dev(hid); + if (!test_bit(HID_REPORTED_IDLE, &usbhid->iofl)) { + len = ((report->size - 1) >> 3) + 1 + (report->id > 0); + if (dir == USB_DIR_OUT) { + usbhid->urbctrl->pipe = usb_sndctrlpipe(hid_to_usb_dev(hid), 0); + usbhid->urbctrl->transfer_buffer_length = len; + memcpy(usbhid->ctrlbuf, raw_report, len); + kfree(raw_report); + } else { + int maxpacket, padlen; + + usbhid->urbctrl->pipe = usb_rcvctrlpipe(hid_to_usb_dev(hid), 0); + maxpacket = usb_maxpacket(hid_to_usb_dev(hid), usbhid->urbctrl->pipe, 0); + if (maxpacket > 0) { + padlen = DIV_ROUND_UP(len, maxpacket); + padlen *= maxpacket; + if (padlen > usbhid->bufsize) + padlen = usbhid->bufsize; + } else + padlen = 0; + usbhid->urbctrl->transfer_buffer_length = padlen; + } + usbhid->urbctrl->dev = hid_to_usb_dev(hid); - usbhid->cr->bRequestType = USB_TYPE_CLASS | USB_RECIP_INTERFACE | dir; - usbhid->cr->bRequest = (dir == USB_DIR_OUT) ? HID_REQ_SET_REPORT : HID_REQ_GET_REPORT; - usbhid->cr->wValue = cpu_to_le16(((report->type + 1) << 8) | report->id); - usbhid->cr->wIndex = cpu_to_le16(usbhid->ifnum); - usbhid->cr->wLength = cpu_to_le16(len); + usbhid->cr->bRequestType = USB_TYPE_CLASS | USB_RECIP_INTERFACE | dir; + usbhid->cr->bRequest = (dir == USB_DIR_OUT) ? HID_REQ_SET_REPORT : HID_REQ_GET_REPORT; + usbhid->cr->wValue = cpu_to_le16(((report->type + 1) << 8) | report->id); + usbhid->cr->wIndex = cpu_to_le16(usbhid->ifnum); + usbhid->cr->wLength = cpu_to_le16(len); - dbg_hid("submitting ctrl urb: %s wValue=0x%04x wIndex=0x%04x wLength=%u\n", - usbhid->cr->bRequest == HID_REQ_SET_REPORT ? "Set_Report" : "Get_Report", - usbhid->cr->wValue, usbhid->cr->wIndex, usbhid->cr->wLength); + dbg_hid("submitting ctrl urb: %s wValue=0x%04x wIndex=0x%04x wLength=%u\n", + usbhid->cr->bRequest == HID_REQ_SET_REPORT ? "Set_Report" : "Get_Report", + usbhid->cr->wValue, usbhid->cr->wIndex, usbhid->cr->wLength); - if (usb_submit_urb(usbhid->urbctrl, GFP_ATOMIC)) { - err_hid("usb_submit_urb(ctrl) failed"); - return -1; + if (usb_submit_urb(usbhid->urbctrl, GFP_ATOMIC)) { + err_hid("usb_submit_urb(ctrl) failed"); + return -1; + } + } else { + /* + * queue work to wake up the device. + * as the work queue is freezeable, this is safe + * with respect to STD and STR + */ + queue_work(resumption_waker, &usbhid->restart_work); } return 0; @@ -332,7 +418,7 @@ static void hid_irq_out(struct urb *urb) "received\n", urb->status); } - spin_lock_irqsave(&usbhid->outlock, flags); + spin_lock_irqsave(&usbhid->lock, flags); if (unplug) usbhid->outtail = usbhid->outhead; @@ -344,12 +430,12 @@ static void hid_irq_out(struct urb *urb) clear_bit(HID_OUT_RUNNING, &usbhid->iofl); wake_up(&usbhid->wait); } - spin_unlock_irqrestore(&usbhid->outlock, flags); + spin_unlock_irqrestore(&usbhid->lock, flags); return; } clear_bit(HID_OUT_RUNNING, &usbhid->iofl); - spin_unlock_irqrestore(&usbhid->outlock, flags); + spin_unlock_irqrestore(&usbhid->lock, flags); wake_up(&usbhid->wait); } @@ -361,12 +447,11 @@ static void hid_ctrl(struct urb *urb) { struct hid_device *hid = urb->context; struct usbhid_device *usbhid = hid->driver_data; - unsigned long flags; - int unplug = 0; + int unplug = 0, status = urb->status; - spin_lock_irqsave(&usbhid->ctrllock, flags); + spin_lock(&usbhid->lock); - switch (urb->status) { + switch (status) { case 0: /* success */ if (usbhid->ctrl[usbhid->ctrltail].dir == USB_DIR_IN) hid_input_report(urb->context, @@ -383,7 +468,7 @@ static void hid_ctrl(struct urb *urb) break; default: /* error */ dev_warn(&urb->dev->dev, "ctrl urb status %d " - "received\n", urb->status); + "received\n", status); } if (unplug) @@ -396,19 +481,18 @@ static void hid_ctrl(struct urb *urb) clear_bit(HID_CTRL_RUNNING, &usbhid->iofl); wake_up(&usbhid->wait); } - spin_unlock_irqrestore(&usbhid->ctrllock, flags); + spin_unlock(&usbhid->lock); return; } clear_bit(HID_CTRL_RUNNING, &usbhid->iofl); - spin_unlock_irqrestore(&usbhid->ctrllock, flags); + spin_unlock(&usbhid->lock); wake_up(&usbhid->wait); } -void usbhid_submit_report(struct hid_device *hid, struct hid_report *report, unsigned char dir) +void __usbhid_submit_report(struct hid_device *hid, struct hid_report *report, unsigned char dir) { int head; - unsigned long flags; struct usbhid_device *usbhid = hid->driver_data; int len = ((report->size - 1) >> 3) + 1 + (report->id > 0); @@ -416,18 +500,13 @@ void usbhid_submit_report(struct hid_device *hid, struct hid_report *report, uns return; if (usbhid->urbout && dir == USB_DIR_OUT && report->type == HID_OUTPUT_REPORT) { - - spin_lock_irqsave(&usbhid->outlock, flags); - if ((head = (usbhid->outhead + 1) & (HID_OUTPUT_FIFO_SIZE - 1)) == usbhid->outtail) { - spin_unlock_irqrestore(&usbhid->outlock, flags); dev_warn(&hid->dev, "output queue full\n"); return; } usbhid->out[usbhid->outhead].raw_report = kmalloc(len, GFP_ATOMIC); if (!usbhid->out[usbhid->outhead].raw_report) { - spin_unlock_irqrestore(&usbhid->outlock, flags); dev_warn(&hid->dev, "output queueing failed\n"); return; } @@ -438,15 +517,10 @@ void usbhid_submit_report(struct hid_device *hid, struct hid_report *report, uns if (!test_and_set_bit(HID_OUT_RUNNING, &usbhid->iofl)) if (hid_submit_out(hid)) clear_bit(HID_OUT_RUNNING, &usbhid->iofl); - - spin_unlock_irqrestore(&usbhid->outlock, flags); return; } - spin_lock_irqsave(&usbhid->ctrllock, flags); - if ((head = (usbhid->ctrlhead + 1) & (HID_CONTROL_FIFO_SIZE - 1)) == usbhid->ctrltail) { - spin_unlock_irqrestore(&usbhid->ctrllock, flags); dev_warn(&hid->dev, "control queue full\n"); return; } @@ -454,7 +528,6 @@ void usbhid_submit_report(struct hid_device *hid, struct hid_report *report, uns if (dir == USB_DIR_OUT) { usbhid->ctrl[usbhid->ctrlhead].raw_report = kmalloc(len, GFP_ATOMIC); if (!usbhid->ctrl[usbhid->ctrlhead].raw_report) { - spin_unlock_irqrestore(&usbhid->ctrllock, flags); dev_warn(&hid->dev, "control queueing failed\n"); return; } @@ -467,15 +540,25 @@ void usbhid_submit_report(struct hid_device *hid, struct hid_report *report, uns if (!test_and_set_bit(HID_CTRL_RUNNING, &usbhid->iofl)) if (hid_submit_ctrl(hid)) clear_bit(HID_CTRL_RUNNING, &usbhid->iofl); +} + +void usbhid_submit_report(struct hid_device *hid, struct hid_report *report, unsigned char dir) +{ + struct usbhid_device *usbhid = hid->driver_data; + unsigned long flags; - spin_unlock_irqrestore(&usbhid->ctrllock, flags); + spin_lock_irqsave(&usbhid->lock, flags); + __usbhid_submit_report(hid, report, dir); + spin_unlock_irqrestore(&usbhid->lock, flags); } EXPORT_SYMBOL_GPL(usbhid_submit_report); static int usb_hidinput_input_event(struct input_dev *dev, unsigned int type, unsigned int code, int value) { struct hid_device *hid = input_get_drvdata(dev); + struct usbhid_device *usbhid = hid->driver_data; struct hid_field *field; + unsigned long flags; int offset; if (type == EV_FF) @@ -490,6 +573,15 @@ static int usb_hidinput_input_event(struct input_dev *dev, unsigned int type, un } hid_set_field(field, offset, value); + if (value) { + spin_lock_irqsave(&usbhid->lock, flags); + usbhid->ledcount++; + spin_unlock_irqrestore(&usbhid->lock, flags); + } else { + spin_lock_irqsave(&usbhid->lock, flags); + usbhid->ledcount--; + spin_unlock_irqrestore(&usbhid->lock, flags); + } usbhid_submit_report(hid, field->report, USB_DIR_OUT); return 0; @@ -538,15 +630,22 @@ int usbhid_open(struct hid_device *hid) struct usbhid_device *usbhid = hid->driver_data; int res; + mutex_lock(&hid_open_mut); if (!hid->open++) { res = usb_autopm_get_interface(usbhid->intf); + /* the device must be awake to reliable request remote wakeup */ if (res < 0) { hid->open--; + mutex_unlock(&hid_open_mut); return -EIO; } + usbhid->intf->needs_remote_wakeup = 1; + if (hid_start_in(hid)) + hid_io_error(hid); + + usb_autopm_put_interface(usbhid->intf); } - if (hid_start_in(hid)) - hid_io_error(hid); + mutex_unlock(&hid_open_mut); return 0; } @@ -554,10 +653,22 @@ void usbhid_close(struct hid_device *hid) { struct usbhid_device *usbhid = hid->driver_data; + mutex_lock(&hid_open_mut); + + /* protecting hid->open to make sure we don't restart + * data acquistion due to a resumption we no longer + * care about + */ + spin_lock_irq(&usbhid->lock); if (!--hid->open) { + spin_unlock_irq(&usbhid->lock); usb_kill_urb(usbhid->urbin); - usb_autopm_put_interface(usbhid->intf); + flush_scheduled_work(); + usbhid->intf->needs_remote_wakeup = 0; + } else { + spin_unlock_irq(&usbhid->lock); } + mutex_unlock(&hid_open_mut); } /* @@ -687,6 +798,25 @@ static int usbhid_output_raw_report(struct hid_device *hid, __u8 *buf, size_t co return ret; } +static void usbhid_restart_queues(struct usbhid_device *usbhid) +{ + if (usbhid->urbout) + usbhid_restart_out_queue(usbhid); + usbhid_restart_ctrl_queue(usbhid); +} + +static void __usbhid_restart_queues(struct work_struct *work) +{ + struct usbhid_device *usbhid = + container_of(work, struct usbhid_device, restart_work); + int r; + + r = usb_autopm_get_interface(usbhid->intf); + if (r < 0) + return; + usb_autopm_put_interface(usbhid->intf); +} + static void hid_free_buffers(struct usb_device *dev, struct hid_device *hid) { struct usbhid_device *usbhid = hid->driver_data; @@ -711,6 +841,9 @@ static int usbhid_parse(struct hid_device *hid) quirks = usbhid_lookup_quirk(le16_to_cpu(dev->descriptor.idVendor), le16_to_cpu(dev->descriptor.idProduct)); + if (quirks & HID_QUIRK_IGNORE) + return -ENODEV; + /* Many keyboards and mice don't like to be polled for reports, * so we will always set the HID_QUIRK_NOGET flag for them. */ if (interface->desc.bInterfaceSubClass == USB_INTERFACE_SUBCLASS_BOOT) { @@ -850,11 +983,11 @@ static int usbhid_start(struct hid_device *hid) init_waitqueue_head(&usbhid->wait); INIT_WORK(&usbhid->reset_work, hid_reset); + INIT_WORK(&usbhid->restart_work, __usbhid_restart_queues); setup_timer(&usbhid->io_retry, hid_retry_timeout, (unsigned long) hid); - spin_lock_init(&usbhid->inlock); - spin_lock_init(&usbhid->outlock); - spin_lock_init(&usbhid->ctrllock); + spin_lock_init(&usbhid->lock); + spin_lock_init(&usbhid->lock); usbhid->intf = intf; usbhid->ifnum = interface->desc.bInterfaceNumber; @@ -906,15 +1039,14 @@ static void usbhid_stop(struct hid_device *hid) return; clear_bit(HID_STARTED, &usbhid->iofl); - spin_lock_irq(&usbhid->inlock); /* Sync with error handler */ + spin_lock_irq(&usbhid->lock); /* Sync with error handler */ set_bit(HID_DISCONNECTED, &usbhid->iofl); - spin_unlock_irq(&usbhid->inlock); + spin_unlock_irq(&usbhid->lock); usb_kill_urb(usbhid->urbin); usb_kill_urb(usbhid->urbout); usb_kill_urb(usbhid->urbctrl); - del_timer_sync(&usbhid->io_retry); - cancel_work_sync(&usbhid->reset_work); + hid_cancel_delayed_stuff(usbhid); if (hid->claimed & HID_CLAIMED_INPUT) hidinput_disconnect(hid); @@ -935,12 +1067,28 @@ static void usbhid_stop(struct hid_device *hid) hid_free_buffers(hid_to_usb_dev(hid), hid); } +static int usbhid_power(struct hid_device *hid, int lvl) +{ + int r = 0; + + switch (lvl) { + case PM_HINT_FULLON: + r = usbhid_get_power(hid); + break; + case PM_HINT_NORMAL: + usbhid_put_power(hid); + break; + } + return r; +} + static struct hid_ll_driver usb_hid_driver = { .parse = usbhid_parse, .start = usbhid_start, .stop = usbhid_stop, .open = usbhid_open, .close = usbhid_close, + .power = usbhid_power, .hidinput_input_event = usb_hidinput_input_event, }; @@ -1049,19 +1197,126 @@ static void hid_disconnect(struct usb_interface *intf) kfree(usbhid); } +static void hid_cancel_delayed_stuff(struct usbhid_device *usbhid) +{ + del_timer_sync(&usbhid->io_retry); + cancel_work_sync(&usbhid->restart_work); + cancel_work_sync(&usbhid->reset_work); +} + +static void hid_cease_io(struct usbhid_device *usbhid) +{ + del_timer(&usbhid->io_retry); + usb_kill_urb(usbhid->urbin); + usb_kill_urb(usbhid->urbctrl); + usb_kill_urb(usbhid->urbout); +} + +/* Treat USB reset pretty much the same as suspend/resume */ +static int hid_pre_reset(struct usb_interface *intf) +{ + struct hid_device *hid = usb_get_intfdata(intf); + struct usbhid_device *usbhid = hid->driver_data; + + spin_lock_irq(&usbhid->lock); + set_bit(HID_RESET_PENDING, &usbhid->iofl); + spin_unlock_irq(&usbhid->lock); + cancel_work_sync(&usbhid->restart_work); + hid_cease_io(usbhid); + + return 0; +} + +/* Same routine used for post_reset and reset_resume */ +static int hid_post_reset(struct usb_interface *intf) +{ + struct usb_device *dev = interface_to_usbdev (intf); + struct hid_device *hid = usb_get_intfdata(intf); + struct usbhid_device *usbhid = hid->driver_data; + int status; + + spin_lock_irq(&usbhid->lock); + clear_bit(HID_RESET_PENDING, &usbhid->iofl); + spin_unlock_irq(&usbhid->lock); + hid_set_idle(dev, intf->cur_altsetting->desc.bInterfaceNumber, 0, 0); + /* FIXME: Any more reinitialization needed? */ + status = hid_start_in(hid); + if (status < 0) + hid_io_error(hid); + usbhid_restart_queues(usbhid); + + return 0; +} + +int usbhid_get_power(struct hid_device *hid) +{ + struct usbhid_device *usbhid = hid->driver_data; + + return usb_autopm_get_interface(usbhid->intf); +} + +void usbhid_put_power(struct hid_device *hid) +{ + struct usbhid_device *usbhid = hid->driver_data; + + usb_autopm_put_interface(usbhid->intf); +} + + +#ifdef CONFIG_PM static int hid_suspend(struct usb_interface *intf, pm_message_t message) { - struct hid_device *hid = usb_get_intfdata (intf); + struct hid_device *hid = usb_get_intfdata(intf); struct usbhid_device *usbhid = hid->driver_data; + struct usb_device *udev = interface_to_usbdev(intf); + int status; - if (!test_bit(HID_STARTED, &usbhid->iofl)) - return 0; + if (udev->auto_pm) { + spin_lock_irq(&usbhid->lock); /* Sync with error handler */ + if (!test_bit(HID_RESET_PENDING, &usbhid->iofl) + && !test_bit(HID_CLEAR_HALT, &usbhid->iofl) + && !test_bit(HID_OUT_RUNNING, &usbhid->iofl) + && !test_bit(HID_CTRL_RUNNING, &usbhid->iofl) + && !test_bit(HID_KEYS_PRESSED, &usbhid->iofl) + && (!usbhid->ledcount || ignoreled)) + { + set_bit(HID_REPORTED_IDLE, &usbhid->iofl); + spin_unlock_irq(&usbhid->lock); + } else { + usbhid_mark_busy(usbhid); + spin_unlock_irq(&usbhid->lock); + return -EBUSY; + } - spin_lock_irq(&usbhid->inlock); /* Sync with error handler */ - set_bit(HID_SUSPENDED, &usbhid->iofl); - spin_unlock_irq(&usbhid->inlock); - del_timer_sync(&usbhid->io_retry); - usb_kill_urb(usbhid->urbin); + } else { + spin_lock_irq(&usbhid->lock); + set_bit(HID_REPORTED_IDLE, &usbhid->iofl); + spin_unlock_irq(&usbhid->lock); + if (usbhid_wait_io(hid) < 0) + return -EIO; + } + + if (!ignoreled && udev->auto_pm) { + spin_lock_irq(&usbhid->lock); + if (test_bit(HID_LED_ON, &usbhid->iofl)) { + spin_unlock_irq(&usbhid->lock); + usbhid_mark_busy(usbhid); + return -EBUSY; + } + spin_unlock_irq(&usbhid->lock); + } + + hid_cancel_delayed_stuff(usbhid); + hid_cease_io(usbhid); + + if (udev->auto_pm && test_bit(HID_KEYS_PRESSED, &usbhid->iofl)) { + /* lost race against keypresses */ + status = hid_start_in(hid); + if (status < 0) + hid_io_error(hid); + usbhid_mark_busy(usbhid); + return -EBUSY; + } dev_dbg(&intf->dev, "suspend\n"); return 0; } @@ -1075,32 +1330,33 @@ static int hid_resume(struct usb_interface *intf) if (!test_bit(HID_STARTED, &usbhid->iofl)) return 0; - clear_bit(HID_SUSPENDED, &usbhid->iofl); + clear_bit(HID_REPORTED_IDLE, &usbhid->iofl); + usbhid_mark_busy(usbhid); + + if (test_bit(HID_CLEAR_HALT, &usbhid->iofl) || + test_bit(HID_RESET_PENDING, &usbhid->iofl)) + schedule_work(&usbhid->reset_work); usbhid->retry_delay = 0; status = hid_start_in(hid); - dev_dbg(&intf->dev, "resume status %d\n", status); - return status; -} + if (status < 0) + hid_io_error(hid); + usbhid_restart_queues(usbhid); -/* Treat USB reset pretty much the same as suspend/resume */ -static int hid_pre_reset(struct usb_interface *intf) -{ - /* FIXME: What if the interface is already suspended? */ - hid_suspend(intf, PMSG_ON); + dev_dbg(&intf->dev, "resume status %d\n", status); return 0; } -/* Same routine used for post_reset and reset_resume */ -static int hid_post_reset(struct usb_interface *intf) +static int hid_reset_resume(struct usb_interface *intf) { - struct usb_device *dev = interface_to_usbdev (intf); - - hid_set_idle(dev, intf->cur_altsetting->desc.bInterfaceNumber, 0, 0); - /* FIXME: Any more reinitialization needed? */ + struct hid_device *hid = usb_get_intfdata(intf); + struct usbhid_device *usbhid = hid->driver_data; - return hid_resume(intf); + clear_bit(HID_REPORTED_IDLE, &usbhid->iofl); + return hid_post_reset(intf); } +#endif /* CONFIG_PM */ + static struct usb_device_id hid_usb_ids [] = { { .match_flags = USB_DEVICE_ID_MATCH_INT_CLASS, .bInterfaceClass = USB_INTERFACE_CLASS_HID }, @@ -1113,9 +1369,11 @@ static struct usb_driver hid_driver = { .name = "usbhid", .probe = hid_probe, .disconnect = hid_disconnect, +#ifdef CONFIG_PM .suspend = hid_suspend, .resume = hid_resume, - .reset_resume = hid_post_reset, + .reset_resume = hid_reset_resume, +#endif .pre_reset = hid_pre_reset, .post_reset = hid_post_reset, .id_table = hid_usb_ids, @@ -1134,7 +1392,11 @@ static struct hid_driver hid_usb_driver = { static int __init hid_init(void) { - int retval; + int retval = -ENOMEM; + + resumption_waker = create_freezeable_workqueue("usbhid_resumer"); + if (!resumption_waker) + goto no_queue; retval = hid_register_driver(&hid_usb_driver); if (retval) goto hid_register_fail; @@ -1158,6 +1420,8 @@ hiddev_init_fail: usbhid_quirks_init_fail: hid_unregister_driver(&hid_usb_driver); hid_register_fail: + destroy_workqueue(resumption_waker); +no_queue: return retval; } @@ -1167,6 +1431,7 @@ static void __exit hid_exit(void) hiddev_exit(); usbhid_quirks_exit(); hid_unregister_driver(&hid_usb_driver); + destroy_workqueue(resumption_waker); } module_init(hid_init); diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c index aa214170baf4..e9b436d2d944 100644 --- a/drivers/hid/usbhid/hiddev.c +++ b/drivers/hid/usbhid/hiddev.c @@ -246,10 +246,12 @@ static int hiddev_release(struct inode * inode, struct file * file) spin_unlock_irqrestore(&list->hiddev->list_lock, flags); if (!--list->hiddev->open) { - if (list->hiddev->exist) + if (list->hiddev->exist) { usbhid_close(list->hiddev->hid); - else + usbhid_put_power(list->hiddev->hid); + } else { kfree(list->hiddev); + } } kfree(list); @@ -300,6 +302,17 @@ static int hiddev_open(struct inode *inode, struct file *file) list_add_tail(&list->node, &hiddev_table[i]->list); spin_unlock_irq(&list->hiddev->list_lock); + if (!list->hiddev->open++) + if (list->hiddev->exist) { + struct hid_device *hid = hiddev_table[i]->hid; + res = usbhid_get_power(hid); + if (res < 0) { + res = -EIO; + goto bail; + } + usbhid_open(hid); + } + return 0; bail: file->private_data = NULL; @@ -875,16 +888,21 @@ int hiddev_connect(struct hid_device *hid, unsigned int force) hiddev->hid = hid; hiddev->exist = 1; + /* when lock_kernel() usage is fixed in usb_open(), + * we could also fix it here */ + lock_kernel(); retval = usb_register_dev(usbhid->intf, &hiddev_class); if (retval) { err_hid("Not able to get a minor for this device."); hid->hiddev = NULL; + unlock_kernel(); kfree(hiddev); return -1; } else { hid->minor = usbhid->intf->minor; hiddev_table[usbhid->intf->minor - HIDDEV_MINOR_BASE] = hiddev; } + unlock_kernel(); return 0; } diff --git a/drivers/hid/usbhid/usbhid.h b/drivers/hid/usbhid/usbhid.h index 9eb30564be9c..08f505ca2e3d 100644 --- a/drivers/hid/usbhid/usbhid.h +++ b/drivers/hid/usbhid/usbhid.h @@ -38,7 +38,10 @@ int usbhid_wait_io(struct hid_device* hid); void usbhid_close(struct hid_device *hid); int usbhid_open(struct hid_device *hid); void usbhid_init_reports(struct hid_device *hid); -void usbhid_submit_report(struct hid_device *hid, struct hid_report *report, unsigned char dir); +void usbhid_submit_report +(struct hid_device *hid, struct hid_report *report, unsigned char dir); +int usbhid_get_power(struct hid_device *hid); +void usbhid_put_power(struct hid_device *hid); /* iofl flags */ #define HID_CTRL_RUNNING 1 @@ -49,6 +52,9 @@ void usbhid_submit_report(struct hid_device *hid, struct hid_report *report, uns #define HID_CLEAR_HALT 6 #define HID_DISCONNECTED 7 #define HID_STARTED 8 +#define HID_REPORTED_IDLE 9 +#define HID_KEYS_PRESSED 10 +#define HID_LED_ON 11 /* * USB-specific HID struct, to be pointed to @@ -66,7 +72,6 @@ struct usbhid_device { struct urb *urbin; /* Input URB */ char *inbuf; /* Input buffer */ dma_addr_t inbuf_dma; /* Input buffer dma */ - spinlock_t inlock; /* Input fifo spinlock */ struct urb *urbctrl; /* Control URB */ struct usb_ctrlrequest *cr; /* Control request struct */ @@ -75,21 +80,22 @@ struct usbhid_device { unsigned char ctrlhead, ctrltail; /* Control fifo head & tail */ char *ctrlbuf; /* Control buffer */ dma_addr_t ctrlbuf_dma; /* Control buffer dma */ - spinlock_t ctrllock; /* Control fifo spinlock */ struct urb *urbout; /* Output URB */ struct hid_output_fifo out[HID_CONTROL_FIFO_SIZE]; /* Output pipe fifo */ unsigned char outhead, outtail; /* Output pipe fifo head & tail */ char *outbuf; /* Output buffer */ dma_addr_t outbuf_dma; /* Output buffer dma */ - spinlock_t outlock; /* Output fifo spinlock */ + spinlock_t lock; /* fifo spinlock */ unsigned long iofl; /* I/O flags (CTRL_RUNNING, OUT_RUNNING) */ struct timer_list io_retry; /* Retry timer */ unsigned long stop_retry; /* Time to give up, in jiffies */ unsigned int retry_delay; /* Delay length in ms */ struct work_struct reset_work; /* Task context for resets */ + struct work_struct restart_work; /* waking up for output to be done in a task */ wait_queue_head_t wait; /* For sleeping */ + int ledcount; /* counting the number of active leds */ }; #define hid_to_usb_dev(hid_dev) \ diff --git a/drivers/hwmon/f75375s.c b/drivers/hwmon/f75375s.c index 18a1ba888165..e2107e533ede 100644 --- a/drivers/hwmon/f75375s.c +++ b/drivers/hwmon/f75375s.c @@ -1,7 +1,7 @@ /* * f75375s.c - driver for the Fintek F75375/SP and F75373 * hardware monitoring features - * Copyright (C) 2006-2007 Riku Voipio <riku.voipio@movial.fi> + * Copyright (C) 2006-2007 Riku Voipio * * Datasheets available at: * @@ -721,7 +721,7 @@ static void __exit sensors_f75375_exit(void) i2c_del_driver(&f75375_driver); } -MODULE_AUTHOR("Riku Voipio <riku.voipio@movial.fi>"); +MODULE_AUTHOR("Riku Voipio"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("F75373/F75375 hardware monitoring driver"); diff --git a/drivers/input/Kconfig b/drivers/input/Kconfig index 5f9d860925a1..cd50c00ab20f 100644 --- a/drivers/input/Kconfig +++ b/drivers/input/Kconfig @@ -143,7 +143,7 @@ config INPUT_APMPOWER ---help--- Say Y here if you want suspend key events to trigger a user requested suspend through APM. This is useful on embedded - systems where such behviour is desired without userspace + systems where such behaviour is desired without userspace interaction. If unsure, say N. To compile this driver as a module, choose M here: the diff --git a/drivers/input/mouse/gpio_mouse.c b/drivers/input/mouse/gpio_mouse.c index 0db8d16c5edd..5e5eb88d8d1e 100644 --- a/drivers/input/mouse/gpio_mouse.c +++ b/drivers/input/mouse/gpio_mouse.c @@ -18,7 +18,7 @@ /* * Timer function which is run every scan_ms ms when the device is opened. - * The dev input varaible is set to the the input_dev pointer. + * The dev input variable is set to the the input_dev pointer. */ static void gpio_mouse_scan(struct input_polled_dev *dev) { diff --git a/drivers/input/touchscreen/ads7846.c b/drivers/input/touchscreen/ads7846.c index 7c27c8b9b6d0..056ac77e2cf0 100644 --- a/drivers/input/touchscreen/ads7846.c +++ b/drivers/input/touchscreen/ads7846.c @@ -295,7 +295,7 @@ name ## _show(struct device *dev, struct device_attribute *attr, char *buf) \ static DEVICE_ATTR(name, S_IRUGO, name ## _show, NULL); -/* Sysfs conventions report temperatures in millidegrees Celcius. +/* Sysfs conventions report temperatures in millidegrees Celsius. * ADS7846 could use the low-accuracy two-sample scheme, but can't do the high * accuracy scheme without calibration data. For now we won't try either; * userspace sees raw sensor values, and must scale/calibrate appropriately. diff --git a/drivers/isdn/mISDN/Kconfig b/drivers/isdn/mISDN/Kconfig index 4938355c4072..1747a02a019a 100644 --- a/drivers/isdn/mISDN/Kconfig +++ b/drivers/isdn/mISDN/Kconfig @@ -14,13 +14,15 @@ config MISDN_DSP depends on MISDN help Enable support for digital audio processing capability. + This module may be used for special applications that require - cross connecting of bchannels, conferencing, dtmf decoding + cross connecting of bchannels, conferencing, dtmf decoding, echo cancelation, tone generation, and Blowfish encryption and - decryption. - It may use hardware features if available. + decryption. It may use hardware features if available. + E.g. it is required for PBX4Linux. Go to http://isdn.eversberg.eu - and get more informations about this module and it's usage. + and get more information about this module and its usage. + If unsure, say 'N'. config MISDN_L1OIP diff --git a/drivers/isdn/mISDN/l1oip_codec.c b/drivers/isdn/mISDN/l1oip_codec.c index 2ec4b28d9edc..e4ecba3d48df 100644 --- a/drivers/isdn/mISDN/l1oip_codec.c +++ b/drivers/isdn/mISDN/l1oip_codec.c @@ -331,7 +331,7 @@ l1oip_4bit_alloc(int ulaw) /* alloc conversion tables */ table_com = vmalloc(65536); table_dec = vmalloc(512); - if (!table_com | !table_dec) { + if (!table_com || !table_dec) { l1oip_4bit_free(); return -ENOMEM; } diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig index 556aeca0d860..d9db17624f12 100644 --- a/drivers/leds/Kconfig +++ b/drivers/leds/Kconfig @@ -100,7 +100,7 @@ config LEDS_HP6XX tristate "LED Support for the HP Jornada 6xx" depends on LEDS_CLASS && SH_HP6XX help - This option enables led support for the handheld + This option enables LED support for the handheld HP Jornada 620/660/680/690. config LEDS_PCA9532 @@ -108,7 +108,7 @@ config LEDS_PCA9532 depends on LEDS_CLASS && I2C && INPUT && EXPERIMENTAL help This option enables support for NXP pca9532 - led controller. It is generally only usefull + LED controller. It is generally only useful as a platform driver config LEDS_GPIO @@ -144,7 +144,7 @@ config LEDS_CLEVO_MAIL Positivo Mobile (Clevo M5x0V) If your model is not listed here you can try the "nodetect" - module paramter. + module parameter. To compile this driver as a module, choose M here: the module will be called leds-clevo-mail. diff --git a/drivers/leds/leds-pca9532.c b/drivers/leds/leds-pca9532.c index 76ec7498e2d5..bd3b431c9710 100644 --- a/drivers/leds/leds-pca9532.c +++ b/drivers/leds/leds-pca9532.c @@ -1,7 +1,7 @@ /* * pca9532.c - 16-bit Led dimmer * - * Copyright (C) 2008 Riku Voipio <riku.voipio@movial.fi> + * Copyright (C) 2008 Riku Voipio * * 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 @@ -367,7 +367,7 @@ static void __exit pca9532_exit(void) i2c_del_driver(&pca9532_driver); } -MODULE_AUTHOR("Riku Voipio <riku.voipio@movial.fi>"); +MODULE_AUTHOR("Riku Voipio"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("PCA 9532 LED dimmer"); diff --git a/drivers/media/common/tuners/Kconfig b/drivers/media/common/tuners/Kconfig index 52c3f65b12d6..607d319ce8ed 100644 --- a/drivers/media/common/tuners/Kconfig +++ b/drivers/media/common/tuners/Kconfig @@ -148,7 +148,7 @@ config MEDIA_TUNER_XC5000 default m if MEDIA_TUNER_CUSTOMISE help A driver for the silicon tuner XC5000 from Xceive. - This device is only used inside a SiP called togther with a + This device is only used inside a SiP called together with a demodulator for now. config MEDIA_TUNER_MXL5005S diff --git a/drivers/media/dvb/frontends/Kconfig b/drivers/media/dvb/frontends/Kconfig index a206cee23f73..a486a7f81fa9 100644 --- a/drivers/media/dvb/frontends/Kconfig +++ b/drivers/media/dvb/frontends/Kconfig @@ -479,7 +479,7 @@ config DVB_TUNER_DIB0070 default m if DVB_FE_CUSTOMISE help A driver for the silicon baseband tuner DiB0070 from DiBcom. - This device is only used inside a SiP called togther with a + This device is only used inside a SiP called together with a demodulator for now. comment "SEC control devices for DVB-S" diff --git a/drivers/media/dvb/frontends/drx397xD.c b/drivers/media/dvb/frontends/drx397xD.c index 1e81e713df63..172f1f928f02 100644 --- a/drivers/media/dvb/frontends/drx397xD.c +++ b/drivers/media/dvb/frontends/drx397xD.c @@ -74,7 +74,7 @@ static struct { } fw[] = { #define _FW_ENTRY(a, b, c) { \ .name = a, \ - .file = 0, \ + .file = NULL, \ .lock = __RW_LOCK_UNLOCKED(fw[c].lock), \ .refcnt = 0, \ .data = { } } diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index 06a2b0f7737c..75f35dbb11dc 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -88,7 +88,7 @@ config MENELAUS help If you say yes here you get support for the Texas Instruments TWL92330/Menelaus Power Management chip. This include voltage - regulators, Dual slot memory card tranceivers, real-time clock + regulators, Dual slot memory card transceivers, real-time clock and other features that are often used in portable devices like cell phones and PDAs. diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig index 0b92b2f6ea68..6d1ac180f6ee 100644 --- a/drivers/misc/Kconfig +++ b/drivers/misc/Kconfig @@ -18,8 +18,8 @@ config ATMEL_PWM depends on AVR32 || ARCH_AT91SAM9263 || ARCH_AT91SAM9RL || ARCH_AT91CAP9 help This option enables device driver support for the PWM channels - on certain Atmel prcoessors. Pulse Width Modulation is used for - purposes including software controlled power-efficent backlights + on certain Atmel processors. Pulse Width Modulation is used for + purposes including software controlled power-efficient backlights on LCD displays, motor control, and waveform generation. config ATMEL_TCLIB @@ -142,7 +142,7 @@ config ATMEL_SSC tristate "Device driver for Atmel SSC peripheral" depends on AVR32 || ARCH_AT91 ---help--- - This option enables device driver support for Atmel Syncronized + This option enables device driver support for Atmel Synchronized Serial Communication peripheral (SSC). The SSC peripheral supports a wide variety of serial frame based diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c index 513eb09a638f..fe8041e619ea 100644 --- a/drivers/mmc/card/block.c +++ b/drivers/mmc/card/block.c @@ -41,6 +41,8 @@ #include "queue.h" +MODULE_ALIAS("mmc:block"); + /* * max 8 partitions per card */ diff --git a/drivers/mmc/core/bus.c b/drivers/mmc/core/bus.c index f210a8ee6861..bdb165f93046 100644 --- a/drivers/mmc/core/bus.c +++ b/drivers/mmc/core/bus.c @@ -84,6 +84,14 @@ mmc_bus_uevent(struct device *dev, struct kobj_uevent_env *env) } retval = add_uevent_var(env, "MMC_NAME=%s", mmc_card_name(card)); + if (retval) + return retval; + + /* + * Request the mmc_block device. Note: that this is a direct request + * for the module it carries no information as to what is inserted. + */ + retval = add_uevent_var(env, "MODALIAS=mmc:block"); return retval; } diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index 1445ea8f10a6..fa073ab3fa34 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -298,6 +298,21 @@ void mmc_set_data_timeout(struct mmc_data *data, const struct mmc_card *card) data->timeout_clks = 0; } } + /* + * Some cards need very high timeouts if driven in SPI mode. + * The worst observed timeout was 900ms after writing a + * continuous stream of data until the internal logic + * overflowed. + */ + if (mmc_host_is_spi(card->host)) { + if (data->flags & MMC_DATA_WRITE) { + if (data->timeout_ns < 1000000000) + data->timeout_ns = 1000000000; /* 1s */ + } else { + if (data->timeout_ns < 100000000) + data->timeout_ns = 100000000; /* 100ms */ + } + } } EXPORT_SYMBOL(mmc_set_data_timeout); @@ -915,6 +930,7 @@ void mmc_stop_host(struct mmc_host *host) spin_unlock_irqrestore(&host->lock, flags); #endif + cancel_delayed_work(&host->detect); mmc_flush_scheduled_work(); mmc_bus_get(host); @@ -942,6 +958,7 @@ void mmc_stop_host(struct mmc_host *host) */ int mmc_suspend_host(struct mmc_host *host, pm_message_t state) { + cancel_delayed_work(&host->detect); mmc_flush_scheduled_work(); mmc_bus_get(host); @@ -975,6 +992,7 @@ int mmc_resume_host(struct mmc_host *host) mmc_bus_get(host); if (host->bus_ops && !host->bus_dead) { mmc_power_up(host); + mmc_select_voltage(host, host->ocr); BUG_ON(!host->bus_ops->resume); host->bus_ops->resume(host); } diff --git a/drivers/mmc/core/debugfs.c b/drivers/mmc/core/debugfs.c index 1237bb4c722b..610dbd1fcc82 100644 --- a/drivers/mmc/core/debugfs.c +++ b/drivers/mmc/core/debugfs.c @@ -184,6 +184,68 @@ static int mmc_dbg_card_status_get(void *data, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(mmc_dbg_card_status_fops, mmc_dbg_card_status_get, NULL, "%08llx\n"); +#define EXT_CSD_STR_LEN 1025 + +static int mmc_ext_csd_open(struct inode *inode, struct file *filp) +{ + struct mmc_card *card = inode->i_private; + char *buf; + ssize_t n = 0; + u8 *ext_csd; + int err, i; + + buf = kmalloc(EXT_CSD_STR_LEN + 1, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + ext_csd = kmalloc(512, GFP_KERNEL); + if (!ext_csd) { + err = -ENOMEM; + goto out_free; + } + + mmc_claim_host(card->host); + err = mmc_send_ext_csd(card, ext_csd); + mmc_release_host(card->host); + if (err) + goto out_free; + + for (i = 511; i >= 0; i--) + n += sprintf(buf + n, "%02x", ext_csd[i]); + n += sprintf(buf + n, "\n"); + BUG_ON(n != EXT_CSD_STR_LEN); + + filp->private_data = buf; + kfree(ext_csd); + return 0; + +out_free: + kfree(buf); + kfree(ext_csd); + return err; +} + +static ssize_t mmc_ext_csd_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char *buf = filp->private_data; + + return simple_read_from_buffer(ubuf, cnt, ppos, + buf, EXT_CSD_STR_LEN); +} + +static int mmc_ext_csd_release(struct inode *inode, struct file *file) +{ + kfree(file->private_data); + return 0; +} + +static struct file_operations mmc_dbg_ext_csd_fops = { + .open = mmc_ext_csd_open, + .read = mmc_ext_csd_read, + .release = mmc_ext_csd_release, +}; + void mmc_add_card_debugfs(struct mmc_card *card) { struct mmc_host *host = card->host; @@ -211,6 +273,11 @@ void mmc_add_card_debugfs(struct mmc_card *card) &mmc_dbg_card_status_fops)) goto err; + if (mmc_card_mmc(card)) + if (!debugfs_create_file("ext_csd", S_IRUSR, root, card, + &mmc_dbg_ext_csd_fops)) + goto err; + return; err: diff --git a/drivers/mmc/core/sdio_cis.c b/drivers/mmc/core/sdio_cis.c index 956bd7677502..963f2937c5e3 100644 --- a/drivers/mmc/core/sdio_cis.c +++ b/drivers/mmc/core/sdio_cis.c @@ -223,10 +223,18 @@ static int sdio_read_cis(struct mmc_card *card, struct sdio_func *func) if (tpl_code == 0xff) break; + /* null entries have no link field or data */ + if (tpl_code == 0x00) + continue; + ret = mmc_io_rw_direct(card, 0, 0, ptr++, 0, &tpl_link); if (ret) break; + /* a size of 0xff also means we're done */ + if (tpl_link == 0xff) + break; + this = kmalloc(sizeof(*this) + tpl_link, GFP_KERNEL); if (!this) return -ENOMEM; diff --git a/drivers/mmc/core/sdio_ops.c b/drivers/mmc/core/sdio_ops.c index c8fa095a4488..4eb7825fd1a7 100644 --- a/drivers/mmc/core/sdio_ops.c +++ b/drivers/mmc/core/sdio_ops.c @@ -76,6 +76,10 @@ int mmc_io_rw_direct(struct mmc_card *card, int write, unsigned fn, BUG_ON(!card); BUG_ON(fn > 7); + /* sanity check */ + if (addr & ~0x1FFFF) + return -EINVAL; + memset(&cmd, 0, sizeof(struct mmc_command)); cmd.opcode = SD_IO_RW_DIRECT; @@ -125,6 +129,10 @@ int mmc_io_rw_extended(struct mmc_card *card, int write, unsigned fn, WARN_ON(blocks == 0); WARN_ON(blksz == 0); + /* sanity check */ + if (addr & ~0x1FFFF) + return -EINVAL; + memset(&mrq, 0, sizeof(struct mmc_request)); memset(&cmd, 0, sizeof(struct mmc_command)); memset(&data, 0, sizeof(struct mmc_data)); diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig index 99d4b28d52ed..b4cf691f3f64 100644 --- a/drivers/mmc/host/Kconfig +++ b/drivers/mmc/host/Kconfig @@ -37,6 +37,13 @@ config MMC_SDHCI If unsure, say N. +config MMC_SDHCI_IO_ACCESSORS + bool + depends on MMC_SDHCI + help + This is silent Kconfig symbol that is selected by the drivers that + need to overwrite SDHCI IO memory accessors. + config MMC_SDHCI_PCI tristate "SDHCI support on PCI bus" depends on MMC_SDHCI && PCI @@ -65,6 +72,17 @@ config MMC_RICOH_MMC If unsure, say Y. +config MMC_SDHCI_OF + tristate "SDHCI support on OpenFirmware platforms" + depends on MMC_SDHCI && PPC_OF + select MMC_SDHCI_IO_ACCESSORS + help + This selects the OF support for Secure Digital Host Controller + Interfaces. So far, only the Freescale eSDHC controller is known + to exist on OF platforms. + + If unsure, say N. + config MMC_OMAP tristate "TI OMAP Multimedia Card Interface support" depends on ARCH_OMAP @@ -171,13 +189,24 @@ config MMC_TIFM_SD To compile this driver as a module, choose M here: the module will be called tifm_sd. +config MMC_MVSDIO + tristate "Marvell MMC/SD/SDIO host driver" + depends on PLAT_ORION + ---help--- + This selects the Marvell SDIO host driver. + SDIO may currently be found on the Kirkwood 88F6281 and 88F6192 + SoC controllers. + + To compile this driver as a module, choose M here: the + module will be called mvsdio. + config MMC_SPI tristate "MMC/SD/SDIO over SPI" depends on SPI_MASTER && !HIGHMEM && HAS_DMA select CRC7 select CRC_ITU_T help - Some systems accss MMC/SD/SDIO cards using a SPI controller + Some systems access MMC/SD/SDIO cards using a SPI controller instead of using a "native" MMC/SD/SDIO controller. This has a disadvantage of being relatively high overhead, but a compensating advantage of working on many systems without dedicated MMC/SD/SDIO diff --git a/drivers/mmc/host/Makefile b/drivers/mmc/host/Makefile index dedec55861d9..970a997620e1 100644 --- a/drivers/mmc/host/Makefile +++ b/drivers/mmc/host/Makefile @@ -13,6 +13,7 @@ obj-$(CONFIG_MMC_MXC) += mxcmmc.o obj-$(CONFIG_MMC_SDHCI) += sdhci.o obj-$(CONFIG_MMC_SDHCI_PCI) += sdhci-pci.o obj-$(CONFIG_MMC_RICOH_MMC) += ricoh_mmc.o +obj-$(CONFIG_MMC_SDHCI_OF) += sdhci-of.o obj-$(CONFIG_MMC_WBSD) += wbsd.o obj-$(CONFIG_MMC_AU1X) += au1xmmc.o obj-$(CONFIG_MMC_OMAP) += omap.o @@ -20,6 +21,7 @@ obj-$(CONFIG_MMC_OMAP_HS) += omap_hsmmc.o obj-$(CONFIG_MMC_AT91) += at91_mci.o obj-$(CONFIG_MMC_ATMELMCI) += atmel-mci.o obj-$(CONFIG_MMC_TIFM_SD) += tifm_sd.o +obj-$(CONFIG_MMC_MVSDIO) += mvsdio.o obj-$(CONFIG_MMC_SPI) += mmc_spi.o ifeq ($(CONFIG_OF),y) obj-$(CONFIG_MMC_SPI) += of_mmc_spi.o diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c index e94e92001e7c..cf6a100bb38f 100644 --- a/drivers/mmc/host/atmel-mci.c +++ b/drivers/mmc/host/atmel-mci.c @@ -812,7 +812,7 @@ static void atmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) slot->sdc_reg |= MCI_SDCBUS_1BIT; break; case MMC_BUS_WIDTH_4: - slot->sdc_reg = MCI_SDCBUS_4BIT; + slot->sdc_reg |= MCI_SDCBUS_4BIT; break; } diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c index 87e211df68ac..72f8bde4877a 100644 --- a/drivers/mmc/host/mmc_spi.c +++ b/drivers/mmc/host/mmc_spi.c @@ -279,8 +279,11 @@ static int mmc_spi_response_get(struct mmc_spi_host *host, * so it can always DMA directly into the target buffer. * It'd probably be better to memcpy() the first chunk and * avoid extra i/o calls... + * + * Note we check for more than 8 bytes, because in practice, + * some SD cards are slow... */ - for (i = 2; i < 9; i++) { + for (i = 2; i < 16; i++) { value = mmc_spi_readbytes(host, 1); if (value < 0) goto done; @@ -609,6 +612,7 @@ mmc_spi_writeblock(struct mmc_spi_host *host, struct spi_transfer *t, struct spi_device *spi = host->spi; int status, i; struct scratch *scratch = host->data; + u32 pattern; if (host->mmc->use_spi_crc) scratch->crc_val = cpu_to_be16( @@ -636,8 +640,27 @@ mmc_spi_writeblock(struct mmc_spi_host *host, struct spi_transfer *t, * doesn't necessarily tell whether the write operation succeeded; * it just says if the transmission was ok and whether *earlier* * writes succeeded; see the standard. + * + * In practice, there are (even modern SDHC-)cards which are late + * in sending the response, and miss the time frame by a few bits, + * so we have to cope with this situation and check the response + * bit-by-bit. Arggh!!! */ - switch (SPI_MMC_RESPONSE_CODE(scratch->status[0])) { + pattern = scratch->status[0] << 24; + pattern |= scratch->status[1] << 16; + pattern |= scratch->status[2] << 8; + pattern |= scratch->status[3]; + + /* First 3 bit of pattern are undefined */ + pattern |= 0xE0000000; + + /* left-adjust to leading 0 bit */ + while (pattern & 0x80000000) + pattern <<= 1; + /* right-adjust for pattern matching. Code is in bit 4..0 now. */ + pattern >>= 27; + + switch (pattern) { case SPI_RESPONSE_ACCEPTED: status = 0; break; @@ -668,8 +691,9 @@ mmc_spi_writeblock(struct mmc_spi_host *host, struct spi_transfer *t, /* Return when not busy. If we didn't collect that status yet, * we'll need some more I/O. */ - for (i = 1; i < sizeof(scratch->status); i++) { - if (scratch->status[i] != 0) + for (i = 4; i < sizeof(scratch->status); i++) { + /* card is non-busy if the most recent bit is 1 */ + if (scratch->status[i] & 0x01) return 0; } return mmc_spi_wait_unbusy(host, timeout); @@ -1204,10 +1228,12 @@ static int mmc_spi_probe(struct spi_device *spi) /* MMC and SD specs only seem to care that sampling is on the * rising edge ... meaning SPI modes 0 or 3. So either SPI mode - * should be legit. We'll use mode 0 since it seems to be a - * bit less troublesome on some hardware ... unclear why. + * should be legit. We'll use mode 0 since the steady state is 0, + * which is appropriate for hotplugging, unless the platform data + * specify mode 3 (if hardware is not compatible to mode 0). */ - spi->mode = SPI_MODE_0; + if (spi->mode != SPI_MODE_3) + spi->mode = SPI_MODE_0; spi->bits_per_word = 8; status = spi_setup(spi); diff --git a/drivers/mmc/host/mvsdio.c b/drivers/mmc/host/mvsdio.c new file mode 100644 index 000000000000..b5c375d94ab3 --- /dev/null +++ b/drivers/mmc/host/mvsdio.c @@ -0,0 +1,885 @@ +/* + * Marvell MMC/SD/SDIO driver + * + * Authors: Maen Suleiman, Nicolas Pitre + * Copyright (C) 2008-2009 Marvell Ltd. + * + * 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. + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/io.h> +#include <linux/platform_device.h> +#include <linux/mbus.h> +#include <linux/delay.h> +#include <linux/interrupt.h> +#include <linux/dma-mapping.h> +#include <linux/scatterlist.h> +#include <linux/irq.h> +#include <linux/gpio.h> +#include <linux/mmc/host.h> + +#include <asm/sizes.h> +#include <asm/unaligned.h> +#include <plat/mvsdio.h> + +#include "mvsdio.h" + +#define DRIVER_NAME "mvsdio" + +static int maxfreq = MVSD_CLOCKRATE_MAX; +static int nodma; + +struct mvsd_host { + void __iomem *base; + struct mmc_request *mrq; + spinlock_t lock; + unsigned int xfer_mode; + unsigned int intr_en; + unsigned int ctrl; + unsigned int pio_size; + void *pio_ptr; + unsigned int sg_frags; + unsigned int ns_per_clk; + unsigned int clock; + unsigned int base_clock; + struct timer_list timer; + struct mmc_host *mmc; + struct device *dev; + struct resource *res; + int irq; + int gpio_card_detect; + int gpio_write_protect; +}; + +#define mvsd_write(offs, val) writel(val, iobase + (offs)) +#define mvsd_read(offs) readl(iobase + (offs)) + +static int mvsd_setup_data(struct mvsd_host *host, struct mmc_data *data) +{ + void __iomem *iobase = host->base; + unsigned int tmout; + int tmout_index; + + /* If timeout=0 then maximum timeout index is used. */ + tmout = DIV_ROUND_UP(data->timeout_ns, host->ns_per_clk); + tmout += data->timeout_clks; + tmout_index = fls(tmout - 1) - 12; + if (tmout_index < 0) + tmout_index = 0; + if (tmout_index > MVSD_HOST_CTRL_TMOUT_MAX) + tmout_index = MVSD_HOST_CTRL_TMOUT_MAX; + + dev_dbg(host->dev, "data %s at 0x%08x: blocks=%d blksz=%d tmout=%u (%d)\n", + (data->flags & MMC_DATA_READ) ? "read" : "write", + (u32)sg_virt(data->sg), data->blocks, data->blksz, + tmout, tmout_index); + + host->ctrl &= ~MVSD_HOST_CTRL_TMOUT_MASK; + host->ctrl |= MVSD_HOST_CTRL_TMOUT(tmout_index); + mvsd_write(MVSD_HOST_CTRL, host->ctrl); + mvsd_write(MVSD_BLK_COUNT, data->blocks); + mvsd_write(MVSD_BLK_SIZE, data->blksz); + + if (nodma || (data->blksz | data->sg->offset) & 3) { + /* + * We cannot do DMA on a buffer which offset or size + * is not aligned on a 4-byte boundary. + */ + host->pio_size = data->blocks * data->blksz; + host->pio_ptr = sg_virt(data->sg); + if (!nodma) + printk(KERN_DEBUG "%s: fallback to PIO for data " + "at 0x%p size %d\n", + mmc_hostname(host->mmc), + host->pio_ptr, host->pio_size); + return 1; + } else { + dma_addr_t phys_addr; + int dma_dir = (data->flags & MMC_DATA_READ) ? + DMA_FROM_DEVICE : DMA_TO_DEVICE; + host->sg_frags = dma_map_sg(mmc_dev(host->mmc), data->sg, + data->sg_len, dma_dir); + phys_addr = sg_dma_address(data->sg); + mvsd_write(MVSD_SYS_ADDR_LOW, (u32)phys_addr & 0xffff); + mvsd_write(MVSD_SYS_ADDR_HI, (u32)phys_addr >> 16); + return 0; + } +} + +static void mvsd_request(struct mmc_host *mmc, struct mmc_request *mrq) +{ + struct mvsd_host *host = mmc_priv(mmc); + void __iomem *iobase = host->base; + struct mmc_command *cmd = mrq->cmd; + u32 cmdreg = 0, xfer = 0, intr = 0; + unsigned long flags; + + BUG_ON(host->mrq != NULL); + host->mrq = mrq; + + dev_dbg(host->dev, "cmd %d (hw state 0x%04x)\n", + cmd->opcode, mvsd_read(MVSD_HW_STATE)); + + cmdreg = MVSD_CMD_INDEX(cmd->opcode); + + if (cmd->flags & MMC_RSP_BUSY) + cmdreg |= MVSD_CMD_RSP_48BUSY; + else if (cmd->flags & MMC_RSP_136) + cmdreg |= MVSD_CMD_RSP_136; + else if (cmd->flags & MMC_RSP_PRESENT) + cmdreg |= MVSD_CMD_RSP_48; + else + cmdreg |= MVSD_CMD_RSP_NONE; + + if (cmd->flags & MMC_RSP_CRC) + cmdreg |= MVSD_CMD_CHECK_CMDCRC; + + if (cmd->flags & MMC_RSP_OPCODE) + cmdreg |= MVSD_CMD_INDX_CHECK; + + if (cmd->flags & MMC_RSP_PRESENT) { + cmdreg |= MVSD_UNEXPECTED_RESP; + intr |= MVSD_NOR_UNEXP_RSP; + } + + if (mrq->data) { + struct mmc_data *data = mrq->data; + int pio; + + cmdreg |= MVSD_CMD_DATA_PRESENT | MVSD_CMD_CHECK_DATACRC16; + xfer |= MVSD_XFER_MODE_HW_WR_DATA_EN; + if (data->flags & MMC_DATA_READ) + xfer |= MVSD_XFER_MODE_TO_HOST; + + pio = mvsd_setup_data(host, data); + if (pio) { + xfer |= MVSD_XFER_MODE_PIO; + /* PIO section of mvsd_irq has comments on those bits */ + if (data->flags & MMC_DATA_WRITE) + intr |= MVSD_NOR_TX_AVAIL; + else if (host->pio_size > 32) + intr |= MVSD_NOR_RX_FIFO_8W; + else + intr |= MVSD_NOR_RX_READY; + } + + if (data->stop) { + struct mmc_command *stop = data->stop; + u32 cmd12reg = 0; + + mvsd_write(MVSD_AUTOCMD12_ARG_LOW, stop->arg & 0xffff); + mvsd_write(MVSD_AUTOCMD12_ARG_HI, stop->arg >> 16); + + if (stop->flags & MMC_RSP_BUSY) + cmd12reg |= MVSD_AUTOCMD12_BUSY; + if (stop->flags & MMC_RSP_OPCODE) + cmd12reg |= MVSD_AUTOCMD12_INDX_CHECK; + cmd12reg |= MVSD_AUTOCMD12_INDEX(stop->opcode); + mvsd_write(MVSD_AUTOCMD12_CMD, cmd12reg); + + xfer |= MVSD_XFER_MODE_AUTO_CMD12; + intr |= MVSD_NOR_AUTOCMD12_DONE; + } else { + intr |= MVSD_NOR_XFER_DONE; + } + } else { + intr |= MVSD_NOR_CMD_DONE; + } + + mvsd_write(MVSD_ARG_LOW, cmd->arg & 0xffff); + mvsd_write(MVSD_ARG_HI, cmd->arg >> 16); + + spin_lock_irqsave(&host->lock, flags); + + host->xfer_mode &= MVSD_XFER_MODE_INT_CHK_EN; + host->xfer_mode |= xfer; + mvsd_write(MVSD_XFER_MODE, host->xfer_mode); + + mvsd_write(MVSD_NOR_INTR_STATUS, ~MVSD_NOR_CARD_INT); + mvsd_write(MVSD_ERR_INTR_STATUS, 0xffff); + mvsd_write(MVSD_CMD, cmdreg); + + host->intr_en &= MVSD_NOR_CARD_INT; + host->intr_en |= intr | MVSD_NOR_ERROR; + mvsd_write(MVSD_NOR_INTR_EN, host->intr_en); + mvsd_write(MVSD_ERR_INTR_EN, 0xffff); + + mod_timer(&host->timer, jiffies + 5 * HZ); + + spin_unlock_irqrestore(&host->lock, flags); +} + +static u32 mvsd_finish_cmd(struct mvsd_host *host, struct mmc_command *cmd, + u32 err_status) +{ + void __iomem *iobase = host->base; + + if (cmd->flags & MMC_RSP_136) { + unsigned int response[8], i; + for (i = 0; i < 8; i++) + response[i] = mvsd_read(MVSD_RSP(i)); + cmd->resp[0] = ((response[0] & 0x03ff) << 22) | + ((response[1] & 0xffff) << 6) | + ((response[2] & 0xfc00) >> 10); + cmd->resp[1] = ((response[2] & 0x03ff) << 22) | + ((response[3] & 0xffff) << 6) | + ((response[4] & 0xfc00) >> 10); + cmd->resp[2] = ((response[4] & 0x03ff) << 22) | + ((response[5] & 0xffff) << 6) | + ((response[6] & 0xfc00) >> 10); + cmd->resp[3] = ((response[6] & 0x03ff) << 22) | + ((response[7] & 0x3fff) << 8); + } else if (cmd->flags & MMC_RSP_PRESENT) { + unsigned int response[3], i; + for (i = 0; i < 3; i++) + response[i] = mvsd_read(MVSD_RSP(i)); + cmd->resp[0] = ((response[2] & 0x003f) << (8 - 8)) | + ((response[1] & 0xffff) << (14 - 8)) | + ((response[0] & 0x03ff) << (30 - 8)); + cmd->resp[1] = ((response[0] & 0xfc00) >> 10); + cmd->resp[2] = 0; + cmd->resp[3] = 0; + } + + if (err_status & MVSD_ERR_CMD_TIMEOUT) { + cmd->error = -ETIMEDOUT; + } else if (err_status & (MVSD_ERR_CMD_CRC | MVSD_ERR_CMD_ENDBIT | + MVSD_ERR_CMD_INDEX | MVSD_ERR_CMD_STARTBIT)) { + cmd->error = -EILSEQ; + } + err_status &= ~(MVSD_ERR_CMD_TIMEOUT | MVSD_ERR_CMD_CRC | + MVSD_ERR_CMD_ENDBIT | MVSD_ERR_CMD_INDEX | + MVSD_ERR_CMD_STARTBIT); + + return err_status; +} + +static u32 mvsd_finish_data(struct mvsd_host *host, struct mmc_data *data, + u32 err_status) +{ + void __iomem *iobase = host->base; + + if (host->pio_ptr) { + host->pio_ptr = NULL; + host->pio_size = 0; + } else { + dma_unmap_sg(mmc_dev(host->mmc), data->sg, host->sg_frags, + (data->flags & MMC_DATA_READ) ? + DMA_FROM_DEVICE : DMA_TO_DEVICE); + } + + if (err_status & MVSD_ERR_DATA_TIMEOUT) + data->error = -ETIMEDOUT; + else if (err_status & (MVSD_ERR_DATA_CRC | MVSD_ERR_DATA_ENDBIT)) + data->error = -EILSEQ; + else if (err_status & MVSD_ERR_XFER_SIZE) + data->error = -EBADE; + err_status &= ~(MVSD_ERR_DATA_TIMEOUT | MVSD_ERR_DATA_CRC | + MVSD_ERR_DATA_ENDBIT | MVSD_ERR_XFER_SIZE); + + dev_dbg(host->dev, "data done: blocks_left=%d, bytes_left=%d\n", + mvsd_read(MVSD_CURR_BLK_LEFT), mvsd_read(MVSD_CURR_BYTE_LEFT)); + data->bytes_xfered = + (data->blocks - mvsd_read(MVSD_CURR_BLK_LEFT)) * data->blksz; + /* We can't be sure about the last block when errors are detected */ + if (data->bytes_xfered && data->error) + data->bytes_xfered -= data->blksz; + + /* Handle Auto cmd 12 response */ + if (data->stop) { + unsigned int response[3], i; + for (i = 0; i < 3; i++) + response[i] = mvsd_read(MVSD_AUTO_RSP(i)); + data->stop->resp[0] = ((response[2] & 0x003f) << (8 - 8)) | + ((response[1] & 0xffff) << (14 - 8)) | + ((response[0] & 0x03ff) << (30 - 8)); + data->stop->resp[1] = ((response[0] & 0xfc00) >> 10); + data->stop->resp[2] = 0; + data->stop->resp[3] = 0; + + if (err_status & MVSD_ERR_AUTOCMD12) { + u32 err_cmd12 = mvsd_read(MVSD_AUTOCMD12_ERR_STATUS); + dev_dbg(host->dev, "c12err 0x%04x\n", err_cmd12); + if (err_cmd12 & MVSD_AUTOCMD12_ERR_NOTEXE) + data->stop->error = -ENOEXEC; + else if (err_cmd12 & MVSD_AUTOCMD12_ERR_TIMEOUT) + data->stop->error = -ETIMEDOUT; + else if (err_cmd12) + data->stop->error = -EILSEQ; + err_status &= ~MVSD_ERR_AUTOCMD12; + } + } + + return err_status; +} + +static irqreturn_t mvsd_irq(int irq, void *dev) +{ + struct mvsd_host *host = dev; + void __iomem *iobase = host->base; + u32 intr_status, intr_done_mask; + int irq_handled = 0; + + intr_status = mvsd_read(MVSD_NOR_INTR_STATUS); + dev_dbg(host->dev, "intr 0x%04x intr_en 0x%04x hw_state 0x%04x\n", + intr_status, mvsd_read(MVSD_NOR_INTR_EN), + mvsd_read(MVSD_HW_STATE)); + + spin_lock(&host->lock); + + /* PIO handling, if needed. Messy business... */ + if (host->pio_size && + (intr_status & host->intr_en & + (MVSD_NOR_RX_READY | MVSD_NOR_RX_FIFO_8W))) { + u16 *p = host->pio_ptr; + int s = host->pio_size; + while (s >= 32 && (intr_status & MVSD_NOR_RX_FIFO_8W)) { + readsw(iobase + MVSD_FIFO, p, 16); + p += 16; + s -= 32; + intr_status = mvsd_read(MVSD_NOR_INTR_STATUS); + } + /* + * Normally we'd use < 32 here, but the RX_FIFO_8W bit + * doesn't appear to assert when there is exactly 32 bytes + * (8 words) left to fetch in a transfer. + */ + if (s <= 32) { + while (s >= 4 && (intr_status & MVSD_NOR_RX_READY)) { + put_unaligned(mvsd_read(MVSD_FIFO), p++); + put_unaligned(mvsd_read(MVSD_FIFO), p++); + s -= 4; + intr_status = mvsd_read(MVSD_NOR_INTR_STATUS); + } + if (s && s < 4 && (intr_status & MVSD_NOR_RX_READY)) { + u16 val[2] = {0, 0}; + val[0] = mvsd_read(MVSD_FIFO); + val[1] = mvsd_read(MVSD_FIFO); + memcpy(p, &val, s); + s = 0; + intr_status = mvsd_read(MVSD_NOR_INTR_STATUS); + } + if (s == 0) { + host->intr_en &= + ~(MVSD_NOR_RX_READY | MVSD_NOR_RX_FIFO_8W); + mvsd_write(MVSD_NOR_INTR_EN, host->intr_en); + } else if (host->intr_en & MVSD_NOR_RX_FIFO_8W) { + host->intr_en &= ~MVSD_NOR_RX_FIFO_8W; + host->intr_en |= MVSD_NOR_RX_READY; + mvsd_write(MVSD_NOR_INTR_EN, host->intr_en); + } + } + dev_dbg(host->dev, "pio %d intr 0x%04x hw_state 0x%04x\n", + s, intr_status, mvsd_read(MVSD_HW_STATE)); + host->pio_ptr = p; + host->pio_size = s; + irq_handled = 1; + } else if (host->pio_size && + (intr_status & host->intr_en & + (MVSD_NOR_TX_AVAIL | MVSD_NOR_TX_FIFO_8W))) { + u16 *p = host->pio_ptr; + int s = host->pio_size; + /* + * The TX_FIFO_8W bit is unreliable. When set, bursting + * 16 halfwords all at once in the FIFO drops data. Actually + * TX_AVAIL does go off after only one word is pushed even if + * TX_FIFO_8W remains set. + */ + while (s >= 4 && (intr_status & MVSD_NOR_TX_AVAIL)) { + mvsd_write(MVSD_FIFO, get_unaligned(p++)); + mvsd_write(MVSD_FIFO, get_unaligned(p++)); + s -= 4; + intr_status = mvsd_read(MVSD_NOR_INTR_STATUS); + } + if (s < 4) { + if (s && (intr_status & MVSD_NOR_TX_AVAIL)) { + u16 val[2] = {0, 0}; + memcpy(&val, p, s); + mvsd_write(MVSD_FIFO, val[0]); + mvsd_write(MVSD_FIFO, val[1]); + s = 0; + intr_status = mvsd_read(MVSD_NOR_INTR_STATUS); + } + if (s == 0) { + host->intr_en &= + ~(MVSD_NOR_TX_AVAIL | MVSD_NOR_TX_FIFO_8W); + mvsd_write(MVSD_NOR_INTR_EN, host->intr_en); + } + } + dev_dbg(host->dev, "pio %d intr 0x%04x hw_state 0x%04x\n", + s, intr_status, mvsd_read(MVSD_HW_STATE)); + host->pio_ptr = p; + host->pio_size = s; + irq_handled = 1; + } + + mvsd_write(MVSD_NOR_INTR_STATUS, intr_status); + + intr_done_mask = MVSD_NOR_CARD_INT | MVSD_NOR_RX_READY | + MVSD_NOR_RX_FIFO_8W | MVSD_NOR_TX_FIFO_8W; + if (intr_status & host->intr_en & ~intr_done_mask) { + struct mmc_request *mrq = host->mrq; + struct mmc_command *cmd = mrq->cmd; + u32 err_status = 0; + + del_timer(&host->timer); + host->mrq = NULL; + + host->intr_en &= MVSD_NOR_CARD_INT; + mvsd_write(MVSD_NOR_INTR_EN, host->intr_en); + mvsd_write(MVSD_ERR_INTR_EN, 0); + + spin_unlock(&host->lock); + + if (intr_status & MVSD_NOR_UNEXP_RSP) { + cmd->error = -EPROTO; + } else if (intr_status & MVSD_NOR_ERROR) { + err_status = mvsd_read(MVSD_ERR_INTR_STATUS); + dev_dbg(host->dev, "err 0x%04x\n", err_status); + } + + err_status = mvsd_finish_cmd(host, cmd, err_status); + if (mrq->data) + err_status = mvsd_finish_data(host, mrq->data, err_status); + if (err_status) { + printk(KERN_ERR "%s: unhandled error status %#04x\n", + mmc_hostname(host->mmc), err_status); + cmd->error = -ENOMSG; + } + + mmc_request_done(host->mmc, mrq); + irq_handled = 1; + } else + spin_unlock(&host->lock); + + if (intr_status & MVSD_NOR_CARD_INT) { + mmc_signal_sdio_irq(host->mmc); + irq_handled = 1; + } + + if (irq_handled) + return IRQ_HANDLED; + + printk(KERN_ERR "%s: unhandled interrupt status=0x%04x en=0x%04x " + "pio=%d\n", mmc_hostname(host->mmc), intr_status, + host->intr_en, host->pio_size); + return IRQ_NONE; +} + +static void mvsd_timeout_timer(unsigned long data) +{ + struct mvsd_host *host = (struct mvsd_host *)data; + void __iomem *iobase = host->base; + struct mmc_request *mrq; + unsigned long flags; + + spin_lock_irqsave(&host->lock, flags); + mrq = host->mrq; + if (mrq) { + printk(KERN_ERR "%s: Timeout waiting for hardware interrupt.\n", + mmc_hostname(host->mmc)); + printk(KERN_ERR "%s: hw_state=0x%04x, intr_status=0x%04x " + "intr_en=0x%04x\n", mmc_hostname(host->mmc), + mvsd_read(MVSD_HW_STATE), + mvsd_read(MVSD_NOR_INTR_STATUS), + mvsd_read(MVSD_NOR_INTR_EN)); + + host->mrq = NULL; + + mvsd_write(MVSD_SW_RESET, MVSD_SW_RESET_NOW); + + host->xfer_mode &= MVSD_XFER_MODE_INT_CHK_EN; + mvsd_write(MVSD_XFER_MODE, host->xfer_mode); + + host->intr_en &= MVSD_NOR_CARD_INT; + mvsd_write(MVSD_NOR_INTR_EN, host->intr_en); + mvsd_write(MVSD_ERR_INTR_EN, 0); + mvsd_write(MVSD_ERR_INTR_STATUS, 0xffff); + + mrq->cmd->error = -ETIMEDOUT; + mvsd_finish_cmd(host, mrq->cmd, 0); + if (mrq->data) { + mrq->data->error = -ETIMEDOUT; + mvsd_finish_data(host, mrq->data, 0); + } + } + spin_unlock_irqrestore(&host->lock, flags); + + if (mrq) + mmc_request_done(host->mmc, mrq); +} + +static irqreturn_t mvsd_card_detect_irq(int irq, void *dev) +{ + struct mvsd_host *host = dev; + mmc_detect_change(host->mmc, msecs_to_jiffies(100)); + return IRQ_HANDLED; +} + +static void mvsd_enable_sdio_irq(struct mmc_host *mmc, int enable) +{ + struct mvsd_host *host = mmc_priv(mmc); + void __iomem *iobase = host->base; + unsigned long flags; + + spin_lock_irqsave(&host->lock, flags); + if (enable) { + host->xfer_mode |= MVSD_XFER_MODE_INT_CHK_EN; + host->intr_en |= MVSD_NOR_CARD_INT; + } else { + host->xfer_mode &= ~MVSD_XFER_MODE_INT_CHK_EN; + host->intr_en &= ~MVSD_NOR_CARD_INT; + } + mvsd_write(MVSD_XFER_MODE, host->xfer_mode); + mvsd_write(MVSD_NOR_INTR_EN, host->intr_en); + spin_unlock_irqrestore(&host->lock, flags); +} + +static int mvsd_get_ro(struct mmc_host *mmc) +{ + struct mvsd_host *host = mmc_priv(mmc); + + if (host->gpio_write_protect) + return gpio_get_value(host->gpio_write_protect); + + /* + * Board doesn't support read only detection; let the mmc core + * decide what to do. + */ + return -ENOSYS; +} + +static void mvsd_power_up(struct mvsd_host *host) +{ + void __iomem *iobase = host->base; + dev_dbg(host->dev, "power up\n"); + mvsd_write(MVSD_NOR_INTR_EN, 0); + mvsd_write(MVSD_ERR_INTR_EN, 0); + mvsd_write(MVSD_SW_RESET, MVSD_SW_RESET_NOW); + mvsd_write(MVSD_XFER_MODE, 0); + mvsd_write(MVSD_NOR_STATUS_EN, 0xffff); + mvsd_write(MVSD_ERR_STATUS_EN, 0xffff); + mvsd_write(MVSD_NOR_INTR_STATUS, 0xffff); + mvsd_write(MVSD_ERR_INTR_STATUS, 0xffff); +} + +static void mvsd_power_down(struct mvsd_host *host) +{ + void __iomem *iobase = host->base; + dev_dbg(host->dev, "power down\n"); + mvsd_write(MVSD_NOR_INTR_EN, 0); + mvsd_write(MVSD_ERR_INTR_EN, 0); + mvsd_write(MVSD_SW_RESET, MVSD_SW_RESET_NOW); + mvsd_write(MVSD_XFER_MODE, MVSD_XFER_MODE_STOP_CLK); + mvsd_write(MVSD_NOR_STATUS_EN, 0); + mvsd_write(MVSD_ERR_STATUS_EN, 0); + mvsd_write(MVSD_NOR_INTR_STATUS, 0xffff); + mvsd_write(MVSD_ERR_INTR_STATUS, 0xffff); +} + +static void mvsd_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) +{ + struct mvsd_host *host = mmc_priv(mmc); + void __iomem *iobase = host->base; + u32 ctrl_reg = 0; + + if (ios->power_mode == MMC_POWER_UP) + mvsd_power_up(host); + + if (ios->clock == 0) { + mvsd_write(MVSD_XFER_MODE, MVSD_XFER_MODE_STOP_CLK); + mvsd_write(MVSD_CLK_DIV, MVSD_BASE_DIV_MAX); + host->clock = 0; + dev_dbg(host->dev, "clock off\n"); + } else if (ios->clock != host->clock) { + u32 m = DIV_ROUND_UP(host->base_clock, ios->clock) - 1; + if (m > MVSD_BASE_DIV_MAX) + m = MVSD_BASE_DIV_MAX; + mvsd_write(MVSD_CLK_DIV, m); + host->clock = ios->clock; + host->ns_per_clk = 1000000000 / (host->base_clock / (m+1)); + dev_dbg(host->dev, "clock=%d (%d), div=0x%04x\n", + ios->clock, host->base_clock / (m+1), m); + } + + /* default transfer mode */ + ctrl_reg |= MVSD_HOST_CTRL_BIG_ENDIAN; + ctrl_reg &= ~MVSD_HOST_CTRL_LSB_FIRST; + + /* default to maximum timeout */ + ctrl_reg |= MVSD_HOST_CTRL_TMOUT_MASK; + ctrl_reg |= MVSD_HOST_CTRL_TMOUT_EN; + + if (ios->bus_mode == MMC_BUSMODE_PUSHPULL) + ctrl_reg |= MVSD_HOST_CTRL_PUSH_PULL_EN; + + if (ios->bus_width == MMC_BUS_WIDTH_4) + ctrl_reg |= MVSD_HOST_CTRL_DATA_WIDTH_4_BITS; + + if (ios->timing == MMC_TIMING_MMC_HS || + ios->timing == MMC_TIMING_SD_HS) + ctrl_reg |= MVSD_HOST_CTRL_HI_SPEED_EN; + + host->ctrl = ctrl_reg; + mvsd_write(MVSD_HOST_CTRL, ctrl_reg); + dev_dbg(host->dev, "ctrl 0x%04x: %s %s %s\n", ctrl_reg, + (ctrl_reg & MVSD_HOST_CTRL_PUSH_PULL_EN) ? + "push-pull" : "open-drain", + (ctrl_reg & MVSD_HOST_CTRL_DATA_WIDTH_4_BITS) ? + "4bit-width" : "1bit-width", + (ctrl_reg & MVSD_HOST_CTRL_HI_SPEED_EN) ? + "high-speed" : ""); + + if (ios->power_mode == MMC_POWER_OFF) + mvsd_power_down(host); +} + +static const struct mmc_host_ops mvsd_ops = { + .request = mvsd_request, + .get_ro = mvsd_get_ro, + .set_ios = mvsd_set_ios, + .enable_sdio_irq = mvsd_enable_sdio_irq, +}; + +static void __init mv_conf_mbus_windows(struct mvsd_host *host, + struct mbus_dram_target_info *dram) +{ + void __iomem *iobase = host->base; + int i; + + for (i = 0; i < 4; i++) { + writel(0, iobase + MVSD_WINDOW_CTRL(i)); + writel(0, iobase + MVSD_WINDOW_BASE(i)); + } + + for (i = 0; i < dram->num_cs; i++) { + struct mbus_dram_window *cs = dram->cs + i; + writel(((cs->size - 1) & 0xffff0000) | + (cs->mbus_attr << 8) | + (dram->mbus_dram_target_id << 4) | 1, + iobase + MVSD_WINDOW_CTRL(i)); + writel(cs->base, iobase + MVSD_WINDOW_BASE(i)); + } +} + +static int __init mvsd_probe(struct platform_device *pdev) +{ + struct mmc_host *mmc = NULL; + struct mvsd_host *host = NULL; + const struct mvsdio_platform_data *mvsd_data; + struct resource *r; + int ret, irq; + + r = platform_get_resource(pdev, IORESOURCE_MEM, 0); + irq = platform_get_irq(pdev, 0); + mvsd_data = pdev->dev.platform_data; + if (!r || irq < 0 || !mvsd_data) + return -ENXIO; + + r = request_mem_region(r->start, SZ_1K, DRIVER_NAME); + if (!r) + return -EBUSY; + + mmc = mmc_alloc_host(sizeof(struct mvsd_host), &pdev->dev); + if (!mmc) { + ret = -ENOMEM; + goto out; + } + + host = mmc_priv(mmc); + host->mmc = mmc; + host->dev = &pdev->dev; + host->res = r; + host->base_clock = mvsd_data->clock / 2; + + mmc->ops = &mvsd_ops; + + mmc->ocr_avail = MMC_VDD_32_33 | MMC_VDD_33_34; + mmc->caps = MMC_CAP_4_BIT_DATA | MMC_CAP_SDIO_IRQ | + MMC_CAP_SD_HIGHSPEED | MMC_CAP_MMC_HIGHSPEED; + + mmc->f_min = DIV_ROUND_UP(host->base_clock, MVSD_BASE_DIV_MAX); + mmc->f_max = maxfreq; + + mmc->max_blk_size = 2048; + mmc->max_blk_count = 65535; + + mmc->max_hw_segs = 1; + mmc->max_phys_segs = 1; + mmc->max_seg_size = mmc->max_blk_size * mmc->max_blk_count; + mmc->max_req_size = mmc->max_blk_size * mmc->max_blk_count; + + spin_lock_init(&host->lock); + + host->base = ioremap(r->start, SZ_4K); + if (!host->base) { + ret = -ENOMEM; + goto out; + } + + /* (Re-)program MBUS remapping windows if we are asked to. */ + if (mvsd_data->dram != NULL) + mv_conf_mbus_windows(host, mvsd_data->dram); + + mvsd_power_down(host); + + ret = request_irq(irq, mvsd_irq, 0, DRIVER_NAME, host); + if (ret) { + printk(KERN_ERR "%s: cannot assign irq %d\n", DRIVER_NAME, irq); + goto out; + } else + host->irq = irq; + + if (mvsd_data->gpio_card_detect) { + ret = gpio_request(mvsd_data->gpio_card_detect, + DRIVER_NAME " cd"); + if (ret == 0) { + gpio_direction_input(mvsd_data->gpio_card_detect); + irq = gpio_to_irq(mvsd_data->gpio_card_detect); + ret = request_irq(irq, mvsd_card_detect_irq, + IRQ_TYPE_EDGE_RISING | IRQ_TYPE_EDGE_FALLING, + DRIVER_NAME " cd", host); + if (ret == 0) + host->gpio_card_detect = + mvsd_data->gpio_card_detect; + else + gpio_free(mvsd_data->gpio_card_detect); + } + } + if (!host->gpio_card_detect) + mmc->caps |= MMC_CAP_NEEDS_POLL; + + if (mvsd_data->gpio_write_protect) { + ret = gpio_request(mvsd_data->gpio_write_protect, + DRIVER_NAME " wp"); + if (ret == 0) { + gpio_direction_input(mvsd_data->gpio_write_protect); + host->gpio_write_protect = + mvsd_data->gpio_write_protect; + } + } + + setup_timer(&host->timer, mvsd_timeout_timer, (unsigned long)host); + platform_set_drvdata(pdev, mmc); + ret = mmc_add_host(mmc); + if (ret) + goto out; + + printk(KERN_NOTICE "%s: %s driver initialized, ", + mmc_hostname(mmc), DRIVER_NAME); + if (host->gpio_card_detect) + printk("using GPIO %d for card detection\n", + host->gpio_card_detect); + else + printk("lacking card detect (fall back to polling)\n"); + return 0; + +out: + if (host) { + if (host->irq) + free_irq(host->irq, host); + if (host->gpio_card_detect) { + free_irq(gpio_to_irq(host->gpio_card_detect), host); + gpio_free(host->gpio_card_detect); + } + if (host->gpio_write_protect) + gpio_free(host->gpio_write_protect); + if (host->base) + iounmap(host->base); + } + if (r) + release_resource(r); + if (mmc) + mmc_free_host(mmc); + + return ret; +} + +static int __exit mvsd_remove(struct platform_device *pdev) +{ + struct mmc_host *mmc = platform_get_drvdata(pdev); + + if (mmc) { + struct mvsd_host *host = mmc_priv(mmc); + + if (host->gpio_card_detect) { + free_irq(gpio_to_irq(host->gpio_card_detect), host); + gpio_free(host->gpio_card_detect); + } + mmc_remove_host(mmc); + free_irq(host->irq, host); + if (host->gpio_write_protect) + gpio_free(host->gpio_write_protect); + del_timer_sync(&host->timer); + mvsd_power_down(host); + iounmap(host->base); + release_resource(host->res); + mmc_free_host(mmc); + } + platform_set_drvdata(pdev, NULL); + return 0; +} + +#ifdef CONFIG_PM +static int mvsd_suspend(struct platform_device *dev, pm_message_t state, + u32 level) +{ + struct mmc_host *mmc = platform_get_drvdata(dev); + int ret = 0; + + if (mmc && level == SUSPEND_DISABLE) + ret = mmc_suspend_host(mmc, state); + + return ret; +} + +static int mvsd_resume(struct platform_device *dev, u32 level) +{ + struct mmc_host *mmc = platform_dev_get_drvdata(dev); + int ret = 0; + + if (mmc && level == RESUME_ENABLE) + ret = mmc_resume_host(mmc); + + return ret; +} +#else +#define mvsd_suspend NULL +#define mvsd_resume NULL +#endif + +static struct platform_driver mvsd_driver = { + .remove = __exit_p(mvsd_remove), + .suspend = mvsd_suspend, + .resume = mvsd_resume, + .driver = { + .name = DRIVER_NAME, + }, +}; + +static int __init mvsd_init(void) +{ + return platform_driver_probe(&mvsd_driver, mvsd_probe); +} + +static void __exit mvsd_exit(void) +{ + platform_driver_unregister(&mvsd_driver); +} + +module_init(mvsd_init); +module_exit(mvsd_exit); + +/* maximum card clock frequency (default 50MHz) */ +module_param(maxfreq, int, 0); + +/* force PIO transfers all the time */ +module_param(nodma, int, 0); + +MODULE_AUTHOR("Maen Suleiman, Nicolas Pitre"); +MODULE_DESCRIPTION("Marvell MMC,SD,SDIO Host Controller driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/mmc/host/mvsdio.h b/drivers/mmc/host/mvsdio.h new file mode 100644 index 000000000000..7d9727b9f5aa --- /dev/null +++ b/drivers/mmc/host/mvsdio.h @@ -0,0 +1,190 @@ +/* + * Copyright (C) 2008 Marvell Semiconductors, 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 version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __MVSDIO_H +#define __MVSDIO_H + +/* + * Clock rates + */ + +#define MVSD_CLOCKRATE_MAX 50000000 +#define MVSD_BASE_DIV_MAX 0x7ff + + +/* + * Register offsets + */ + +#define MVSD_SYS_ADDR_LOW 0x000 +#define MVSD_SYS_ADDR_HI 0x004 +#define MVSD_BLK_SIZE 0x008 +#define MVSD_BLK_COUNT 0x00c +#define MVSD_ARG_LOW 0x010 +#define MVSD_ARG_HI 0x014 +#define MVSD_XFER_MODE 0x018 +#define MVSD_CMD 0x01c +#define MVSD_RSP(i) (0x020 + ((i)<<2)) +#define MVSD_RSP0 0x020 +#define MVSD_RSP1 0x024 +#define MVSD_RSP2 0x028 +#define MVSD_RSP3 0x02c +#define MVSD_RSP4 0x030 +#define MVSD_RSP5 0x034 +#define MVSD_RSP6 0x038 +#define MVSD_RSP7 0x03c +#define MVSD_FIFO 0x040 +#define MVSD_RSP_CRC7 0x044 +#define MVSD_HW_STATE 0x048 +#define MVSD_HOST_CTRL 0x050 +#define MVSD_BLK_GAP_CTRL 0x054 +#define MVSD_CLK_CTRL 0x058 +#define MVSD_SW_RESET 0x05c +#define MVSD_NOR_INTR_STATUS 0x060 +#define MVSD_ERR_INTR_STATUS 0x064 +#define MVSD_NOR_STATUS_EN 0x068 +#define MVSD_ERR_STATUS_EN 0x06c +#define MVSD_NOR_INTR_EN 0x070 +#define MVSD_ERR_INTR_EN 0x074 +#define MVSD_AUTOCMD12_ERR_STATUS 0x078 +#define MVSD_CURR_BYTE_LEFT 0x07c +#define MVSD_CURR_BLK_LEFT 0x080 +#define MVSD_AUTOCMD12_ARG_LOW 0x084 +#define MVSD_AUTOCMD12_ARG_HI 0x088 +#define MVSD_AUTOCMD12_CMD 0x08c +#define MVSD_AUTO_RSP(i) (0x090 + ((i)<<2)) +#define MVSD_AUTO_RSP0 0x090 +#define MVSD_AUTO_RSP1 0x094 +#define MVSD_AUTO_RSP2 0x098 +#define MVSD_CLK_DIV 0x128 + +#define MVSD_WINDOW_CTRL(i) (0x108 + ((i) << 3)) +#define MVSD_WINDOW_BASE(i) (0x10c + ((i) << 3)) + + +/* + * MVSD_CMD + */ + +#define MVSD_CMD_RSP_NONE (0 << 0) +#define MVSD_CMD_RSP_136 (1 << 0) +#define MVSD_CMD_RSP_48 (2 << 0) +#define MVSD_CMD_RSP_48BUSY (3 << 0) + +#define MVSD_CMD_CHECK_DATACRC16 (1 << 2) +#define MVSD_CMD_CHECK_CMDCRC (1 << 3) +#define MVSD_CMD_INDX_CHECK (1 << 4) +#define MVSD_CMD_DATA_PRESENT (1 << 5) +#define MVSD_UNEXPECTED_RESP (1 << 7) +#define MVSD_CMD_INDEX(x) ((x) << 8) + + +/* + * MVSD_AUTOCMD12_CMD + */ + +#define MVSD_AUTOCMD12_BUSY (1 << 0) +#define MVSD_AUTOCMD12_INDX_CHECK (1 << 1) +#define MVSD_AUTOCMD12_INDEX(x) ((x) << 8) + +/* + * MVSD_XFER_MODE + */ + +#define MVSD_XFER_MODE_WR_DATA_START (1 << 0) +#define MVSD_XFER_MODE_HW_WR_DATA_EN (1 << 1) +#define MVSD_XFER_MODE_AUTO_CMD12 (1 << 2) +#define MVSD_XFER_MODE_INT_CHK_EN (1 << 3) +#define MVSD_XFER_MODE_TO_HOST (1 << 4) +#define MVSD_XFER_MODE_STOP_CLK (1 << 5) +#define MVSD_XFER_MODE_PIO (1 << 6) + + +/* + * MVSD_HOST_CTRL + */ + +#define MVSD_HOST_CTRL_PUSH_PULL_EN (1 << 0) + +#define MVSD_HOST_CTRL_CARD_TYPE_MEM_ONLY (0 << 1) +#define MVSD_HOST_CTRL_CARD_TYPE_IO_ONLY (1 << 1) +#define MVSD_HOST_CTRL_CARD_TYPE_IO_MEM_COMBO (2 << 1) +#define MVSD_HOST_CTRL_CARD_TYPE_IO_MMC (3 << 1) +#define MVSD_HOST_CTRL_CARD_TYPE_MASK (3 << 1) + +#define MVSD_HOST_CTRL_BIG_ENDIAN (1 << 3) +#define MVSD_HOST_CTRL_LSB_FIRST (1 << 4) +#define MVSD_HOST_CTRL_DATA_WIDTH_4_BITS (1 << 9) +#define MVSD_HOST_CTRL_HI_SPEED_EN (1 << 10) + +#define MVSD_HOST_CTRL_TMOUT_MAX 0xf +#define MVSD_HOST_CTRL_TMOUT_MASK (0xf << 11) +#define MVSD_HOST_CTRL_TMOUT(x) ((x) << 11) +#define MVSD_HOST_CTRL_TMOUT_EN (1 << 15) + + +/* + * MVSD_SW_RESET + */ + +#define MVSD_SW_RESET_NOW (1 << 8) + + +/* + * Normal interrupt status bits + */ + +#define MVSD_NOR_CMD_DONE (1 << 0) +#define MVSD_NOR_XFER_DONE (1 << 1) +#define MVSD_NOR_BLK_GAP_EVT (1 << 2) +#define MVSD_NOR_DMA_DONE (1 << 3) +#define MVSD_NOR_TX_AVAIL (1 << 4) +#define MVSD_NOR_RX_READY (1 << 5) +#define MVSD_NOR_CARD_INT (1 << 8) +#define MVSD_NOR_READ_WAIT_ON (1 << 9) +#define MVSD_NOR_RX_FIFO_8W (1 << 10) +#define MVSD_NOR_TX_FIFO_8W (1 << 11) +#define MVSD_NOR_SUSPEND_ON (1 << 12) +#define MVSD_NOR_AUTOCMD12_DONE (1 << 13) +#define MVSD_NOR_UNEXP_RSP (1 << 14) +#define MVSD_NOR_ERROR (1 << 15) + + +/* + * Error status bits + */ + +#define MVSD_ERR_CMD_TIMEOUT (1 << 0) +#define MVSD_ERR_CMD_CRC (1 << 1) +#define MVSD_ERR_CMD_ENDBIT (1 << 2) +#define MVSD_ERR_CMD_INDEX (1 << 3) +#define MVSD_ERR_DATA_TIMEOUT (1 << 4) +#define MVSD_ERR_DATA_CRC (1 << 5) +#define MVSD_ERR_DATA_ENDBIT (1 << 6) +#define MVSD_ERR_AUTOCMD12 (1 << 8) +#define MVSD_ERR_CMD_STARTBIT (1 << 9) +#define MVSD_ERR_XFER_SIZE (1 << 10) +#define MVSD_ERR_RESP_T_BIT (1 << 11) +#define MVSD_ERR_CRC_ENDBIT (1 << 12) +#define MVSD_ERR_CRC_STARTBIT (1 << 13) +#define MVSD_ERR_CRC_STATUS (1 << 14) + + +/* + * CMD12 error status bits + */ + +#define MVSD_AUTOCMD12_ERR_NOTEXE (1 << 0) +#define MVSD_AUTOCMD12_ERR_TIMEOUT (1 << 1) +#define MVSD_AUTOCMD12_ERR_CRC (1 << 2) +#define MVSD_AUTOCMD12_ERR_ENDBIT (1 << 3) +#define MVSD_AUTOCMD12_ERR_INDEX (1 << 4) +#define MVSD_AUTOCMD12_ERR_RESP_T_BIT (1 << 5) +#define MVSD_AUTOCMD12_ERR_RESP_STARTBIT (1 << 6) + +#endif diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c index 3916a5618e28..d183be6f2a5f 100644 --- a/drivers/mmc/host/omap_hsmmc.c +++ b/drivers/mmc/host/omap_hsmmc.c @@ -56,6 +56,7 @@ #define SDVS18 (0x5 << 9) #define SDVS30 (0x6 << 9) #define SDVS33 (0x7 << 9) +#define SDVS_MASK 0x00000E00 #define SDVSCLR 0xFFFFF1FF #define SDVSDET 0x00000400 #define AUTOIDLE 0x1 @@ -76,6 +77,7 @@ #define MSBS (1 << 5) #define BCE (1 << 1) #define FOUR_BIT (1 << 1) +#define DW8 (1 << 5) #define CC 0x1 #define TC 0x02 #define OD 0x1 @@ -98,10 +100,8 @@ */ #define OMAP_MMC1_DEVID 0 #define OMAP_MMC2_DEVID 1 +#define OMAP_MMC3_DEVID 2 -#define OMAP_MMC_DATADIR_NONE 0 -#define OMAP_MMC_DATADIR_READ 1 -#define OMAP_MMC_DATADIR_WRITE 2 #define MMC_TIMEOUT_MS 20 #define OMAP_MMC_MASTER_CLOCK 96000000 #define DRIVER_NAME "mmci-omap-hs" @@ -137,18 +137,18 @@ struct mmc_omap_host { resource_size_t mapbase; unsigned int id; unsigned int dma_len; - unsigned int dma_dir; + unsigned int dma_sg_idx; unsigned char bus_mode; - unsigned char datadir; u32 *buffer; u32 bytesleft; int suspended; int irq; int carddetect; int use_dma, dma_ch; - int initstr; + int dma_line_tx, dma_line_rx; int slot_id; int dbclk_enabled; + int response_busy; struct omap_mmc_platform_data *pdata; }; @@ -218,7 +218,7 @@ mmc_omap_show_slot_name(struct device *dev, struct device_attribute *attr, struct mmc_omap_host *host = mmc_priv(mmc); struct omap_mmc_slot_data slot = host->pdata->slots[host->slot_id]; - return sprintf(buf, "slot:%s\n", slot.name); + return sprintf(buf, "%s\n", slot.name); } static DEVICE_ATTR(slot_name, S_IRUGO, mmc_omap_show_slot_name, NULL); @@ -243,10 +243,14 @@ mmc_omap_start_command(struct mmc_omap_host *host, struct mmc_command *cmd, OMAP_HSMMC_WRITE(host->base, ISE, INT_EN_MASK); OMAP_HSMMC_WRITE(host->base, IE, INT_EN_MASK); + host->response_busy = 0; if (cmd->flags & MMC_RSP_PRESENT) { if (cmd->flags & MMC_RSP_136) resptype = 1; - else + else if (cmd->flags & MMC_RSP_BUSY) { + resptype = 3; + host->response_busy = 1; + } else resptype = 2; } @@ -275,19 +279,35 @@ mmc_omap_start_command(struct mmc_omap_host *host, struct mmc_command *cmd, OMAP_HSMMC_WRITE(host->base, CMD, cmdreg); } +static int +mmc_omap_get_dma_dir(struct mmc_omap_host *host, struct mmc_data *data) +{ + if (data->flags & MMC_DATA_WRITE) + return DMA_TO_DEVICE; + else + return DMA_FROM_DEVICE; +} + /* * Notify the transfer complete to MMC core */ static void mmc_omap_xfer_done(struct mmc_omap_host *host, struct mmc_data *data) { + if (!data) { + struct mmc_request *mrq = host->mrq; + + host->mrq = NULL; + mmc_omap_fclk_lazy_disable(host); + mmc_request_done(host->mmc, mrq); + return; + } + host->data = NULL; if (host->use_dma && host->dma_ch != -1) dma_unmap_sg(mmc_dev(host->mmc), data->sg, host->dma_len, - host->dma_dir); - - host->datadir = OMAP_MMC_DATADIR_NONE; + mmc_omap_get_dma_dir(host, data)); if (!data->error) data->bytes_xfered += data->blocks * (data->blksz); @@ -322,7 +342,7 @@ mmc_omap_cmd_done(struct mmc_omap_host *host, struct mmc_command *cmd) cmd->resp[0] = OMAP_HSMMC_READ(host->base, RSP10); } } - if (host->data == NULL || cmd->error) { + if ((host->data == NULL && !host->response_busy) || cmd->error) { host->mrq = NULL; mmc_request_done(host->mmc, cmd->mrq); } @@ -331,19 +351,18 @@ mmc_omap_cmd_done(struct mmc_omap_host *host, struct mmc_command *cmd) /* * DMA clean up for command errors */ -static void mmc_dma_cleanup(struct mmc_omap_host *host) +static void mmc_dma_cleanup(struct mmc_omap_host *host, int errno) { - host->data->error = -ETIMEDOUT; + host->data->error = errno; if (host->use_dma && host->dma_ch != -1) { dma_unmap_sg(mmc_dev(host->mmc), host->data->sg, host->dma_len, - host->dma_dir); + mmc_omap_get_dma_dir(host, host->data)); omap_free_dma(host->dma_ch); host->dma_ch = -1; up(&host->sem); } host->data = NULL; - host->datadir = OMAP_MMC_DATADIR_NONE; } /* @@ -412,7 +431,7 @@ static irqreturn_t mmc_omap_irq(int irq, void *dev_id) struct mmc_data *data; int end_cmd = 0, end_trans = 0, status; - if (host->cmd == NULL && host->data == NULL) { + if (host->mrq == NULL) { OMAP_HSMMC_WRITE(host->base, STAT, OMAP_HSMMC_READ(host->base, STAT)); return IRQ_HANDLED; @@ -437,18 +456,24 @@ static irqreturn_t mmc_omap_irq(int irq, void *dev_id) } end_cmd = 1; } - if (host->data) { - mmc_dma_cleanup(host); + if (host->data || host->response_busy) { + if (host->data) + mmc_dma_cleanup(host, -ETIMEDOUT); + host->response_busy = 0; mmc_omap_reset_controller_fsm(host, SRD); } } if ((status & DATA_TIMEOUT) || (status & DATA_CRC)) { - if (host->data) { - if (status & DATA_TIMEOUT) - mmc_dma_cleanup(host); + if (host->data || host->response_busy) { + int err = (status & DATA_TIMEOUT) ? + -ETIMEDOUT : -EILSEQ; + + if (host->data) + mmc_dma_cleanup(host, err); else - host->data->error = -EILSEQ; + host->mrq->cmd->error = err; + host->response_busy = 0; mmc_omap_reset_controller_fsm(host, SRD); end_trans = 1; } @@ -473,6 +498,19 @@ static irqreturn_t mmc_omap_irq(int irq, void *dev_id) return IRQ_HANDLED; } +static void set_sd_bus_power(struct mmc_omap_host *host) +{ + unsigned long i; + + OMAP_HSMMC_WRITE(host->base, HCTL, + OMAP_HSMMC_READ(host->base, HCTL) | SDBP); + for (i = 0; i < loops_per_jiffy; i++) { + if (OMAP_HSMMC_READ(host->base, HCTL) & SDBP) + break; + cpu_relax(); + } +} + /* * Switch MMC interface voltage ... only relevant for MMC1. * @@ -485,9 +523,6 @@ static int omap_mmc_switch_opcond(struct mmc_omap_host *host, int vdd) u32 reg_val = 0; int ret; - if (host->id != OMAP_MMC1_DEVID) - return 0; - /* Disable the clocks */ clk_disable(host->fclk); clk_disable(host->iclk); @@ -532,9 +567,7 @@ static int omap_mmc_switch_opcond(struct mmc_omap_host *host, int vdd) reg_val |= SDVS30; OMAP_HSMMC_WRITE(host->base, HCTL, reg_val); - - OMAP_HSMMC_WRITE(host->base, HCTL, - OMAP_HSMMC_READ(host->base, HCTL) | SDBP); + set_sd_bus_power(host); return 0; err: @@ -551,7 +584,10 @@ static void mmc_omap_detect(struct work_struct *work) mmc_carddetect_work); struct omap_mmc_slot_data *slot = &mmc_slot(host); - host->carddetect = slot->card_detect(slot->card_detect_irq); + if (mmc_slot(host).card_detect) + host->carddetect = slot->card_detect(slot->card_detect_irq); + else + host->carddetect = -ENOSYS; sysfs_notify(&host->mmc->class_dev.kobj, NULL, "cover_switch"); if (host->carddetect) { @@ -574,6 +610,48 @@ static irqreturn_t omap_mmc_cd_handler(int irq, void *dev_id) return IRQ_HANDLED; } +static int mmc_omap_get_dma_sync_dev(struct mmc_omap_host *host, + struct mmc_data *data) +{ + int sync_dev; + + if (data->flags & MMC_DATA_WRITE) + sync_dev = host->dma_line_tx; + else + sync_dev = host->dma_line_rx; + return sync_dev; +} + +static void mmc_omap_config_dma_params(struct mmc_omap_host *host, + struct mmc_data *data, + struct scatterlist *sgl) +{ + int blksz, nblk, dma_ch; + + dma_ch = host->dma_ch; + if (data->flags & MMC_DATA_WRITE) { + omap_set_dma_dest_params(dma_ch, 0, OMAP_DMA_AMODE_CONSTANT, + (host->mapbase + OMAP_HSMMC_DATA), 0, 0); + omap_set_dma_src_params(dma_ch, 0, OMAP_DMA_AMODE_POST_INC, + sg_dma_address(sgl), 0, 0); + } else { + omap_set_dma_src_params(dma_ch, 0, OMAP_DMA_AMODE_CONSTANT, + (host->mapbase + OMAP_HSMMC_DATA), 0, 0); + omap_set_dma_dest_params(dma_ch, 0, OMAP_DMA_AMODE_POST_INC, + sg_dma_address(sgl), 0, 0); + } + + blksz = host->data->blksz; + nblk = sg_dma_len(sgl) / blksz; + + omap_set_dma_transfer_params(dma_ch, OMAP_DMA_DATA_TYPE_S32, + blksz / 4, nblk, OMAP_DMA_SYNC_FRAME, + mmc_omap_get_dma_sync_dev(host, data), + !(data->flags & MMC_DATA_WRITE)); + + omap_start_dma(dma_ch); +} + /* * DMA call back function */ @@ -587,6 +665,14 @@ static void mmc_omap_dma_cb(int lch, u16 ch_status, void *data) if (host->dma_ch < 0) return; + host->dma_sg_idx++; + if (host->dma_sg_idx < host->dma_len) { + /* Fire up the next transfer. */ + mmc_omap_config_dma_params(host, host->data, + host->data->sg + host->dma_sg_idx); + return; + } + omap_free_dma(host->dma_ch); host->dma_ch = -1; /* @@ -597,38 +683,28 @@ static void mmc_omap_dma_cb(int lch, u16 ch_status, void *data) } /* - * Configure dma src and destination parameters - */ -static int mmc_omap_config_dma_param(int sync_dir, struct mmc_omap_host *host, - struct mmc_data *data) -{ - if (sync_dir == 0) { - omap_set_dma_dest_params(host->dma_ch, 0, - OMAP_DMA_AMODE_CONSTANT, - (host->mapbase + OMAP_HSMMC_DATA), 0, 0); - omap_set_dma_src_params(host->dma_ch, 0, - OMAP_DMA_AMODE_POST_INC, - sg_dma_address(&data->sg[0]), 0, 0); - } else { - omap_set_dma_src_params(host->dma_ch, 0, - OMAP_DMA_AMODE_CONSTANT, - (host->mapbase + OMAP_HSMMC_DATA), 0, 0); - omap_set_dma_dest_params(host->dma_ch, 0, - OMAP_DMA_AMODE_POST_INC, - sg_dma_address(&data->sg[0]), 0, 0); - } - return 0; -} -/* * Routine to configure and start DMA for the MMC card */ static int mmc_omap_start_dma_transfer(struct mmc_omap_host *host, struct mmc_request *req) { - int sync_dev, sync_dir = 0; - int dma_ch = 0, ret = 0, err = 1; + int dma_ch = 0, ret = 0, err = 1, i; struct mmc_data *data = req->data; + /* Sanity check: all the SG entries must be aligned by block size. */ + for (i = 0; i < host->dma_len; i++) { + struct scatterlist *sgl; + + sgl = data->sg + i; + if (sgl->length % data->blksz) + return -EINVAL; + } + if ((data->blksz % 4) != 0) + /* REVISIT: The MMC buffer increments only when MSB is written. + * Return error for blksz which is non multiple of four. + */ + return -EINVAL; + /* * If for some reason the DMA transfer is still active, * we wait for timeout period and free the dma @@ -647,49 +723,22 @@ mmc_omap_start_dma_transfer(struct mmc_omap_host *host, struct mmc_request *req) return err; } - if (!(data->flags & MMC_DATA_WRITE)) { - host->dma_dir = DMA_FROM_DEVICE; - if (host->id == OMAP_MMC1_DEVID) - sync_dev = OMAP24XX_DMA_MMC1_RX; - else - sync_dev = OMAP24XX_DMA_MMC2_RX; - } else { - host->dma_dir = DMA_TO_DEVICE; - if (host->id == OMAP_MMC1_DEVID) - sync_dev = OMAP24XX_DMA_MMC1_TX; - else - sync_dev = OMAP24XX_DMA_MMC2_TX; - } - - ret = omap_request_dma(sync_dev, "MMC/SD", mmc_omap_dma_cb, - host, &dma_ch); + ret = omap_request_dma(mmc_omap_get_dma_sync_dev(host, data), "MMC/SD", + mmc_omap_dma_cb,host, &dma_ch); if (ret != 0) { - dev_dbg(mmc_dev(host->mmc), + dev_err(mmc_dev(host->mmc), "%s: omap_request_dma() failed with %d\n", mmc_hostname(host->mmc), ret); return ret; } host->dma_len = dma_map_sg(mmc_dev(host->mmc), data->sg, - data->sg_len, host->dma_dir); + data->sg_len, mmc_omap_get_dma_dir(host, data)); host->dma_ch = dma_ch; + host->dma_sg_idx = 0; - if (!(data->flags & MMC_DATA_WRITE)) - mmc_omap_config_dma_param(1, host, data); - else - mmc_omap_config_dma_param(0, host, data); - - if ((data->blksz % 4) == 0) - omap_set_dma_transfer_params(dma_ch, OMAP_DMA_DATA_TYPE_S32, - (data->blksz / 4), data->blocks, OMAP_DMA_SYNC_FRAME, - sync_dev, sync_dir); - else - /* REVISIT: The MMC buffer increments only when MSB is written. - * Return error for blksz which is non multiple of four. - */ - return -EINVAL; + mmc_omap_config_dma_params(host, data, data->sg); - omap_start_dma(dma_ch); return 0; } @@ -739,7 +788,6 @@ mmc_omap_prepare_data(struct mmc_omap_host *host, struct mmc_request *req) host->data = req->data; if (req->data == NULL) { - host->datadir = OMAP_MMC_DATADIR_NONE; OMAP_HSMMC_WRITE(host->base, BLK, 0); return 0; } @@ -748,9 +796,6 @@ mmc_omap_prepare_data(struct mmc_omap_host *host, struct mmc_request *req) | (req->data->blocks << 16)); set_data_timeout(host, req); - host->datadir = (req->data->flags & MMC_DATA_WRITE) ? - OMAP_MMC_DATADIR_WRITE : OMAP_MMC_DATADIR_READ; - if (host->use_dma) { ret = mmc_omap_start_dma_transfer(host, req); if (ret != 0) { @@ -782,36 +827,29 @@ static void omap_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) u16 dsor = 0; unsigned long regval; unsigned long timeout; + u32 con; switch (ios->power_mode) { case MMC_POWER_OFF: mmc_slot(host).set_power(host->dev, host->slot_id, 0, 0); - /* - * Reset interface voltage to 3V if it's 1.8V now; - * only relevant on MMC-1, the others always use 1.8V. - * - * REVISIT: If we are able to detect cards after unplugging - * a 1.8V card, this code should not be needed. - */ - if (host->id != OMAP_MMC1_DEVID) - break; - if (!(OMAP_HSMMC_READ(host->base, HCTL) & SDVSDET)) { - int vdd = fls(host->mmc->ocr_avail) - 1; - if (omap_mmc_switch_opcond(host, vdd) != 0) - host->mmc->ios.vdd = vdd; - } break; case MMC_POWER_UP: mmc_slot(host).set_power(host->dev, host->slot_id, 1, ios->vdd); break; } + con = OMAP_HSMMC_READ(host->base, CON); switch (mmc->ios.bus_width) { + case MMC_BUS_WIDTH_8: + OMAP_HSMMC_WRITE(host->base, CON, con | DW8); + break; case MMC_BUS_WIDTH_4: + OMAP_HSMMC_WRITE(host->base, CON, con & ~DW8); OMAP_HSMMC_WRITE(host->base, HCTL, OMAP_HSMMC_READ(host->base, HCTL) | FOUR_BIT); break; case MMC_BUS_WIDTH_1: + OMAP_HSMMC_WRITE(host->base, CON, con & ~DW8); OMAP_HSMMC_WRITE(host->base, HCTL, OMAP_HSMMC_READ(host->base, HCTL) & ~FOUR_BIT); break; @@ -891,6 +929,33 @@ static int omap_hsmmc_get_ro(struct mmc_host *mmc) return pdata->slots[0].get_ro(host->dev, 0); } +static void omap_hsmmc_init(struct mmc_omap_host *host) +{ + u32 hctl, capa, value; + + /* Only MMC1 supports 3.0V */ + if (host->id == OMAP_MMC1_DEVID) { + hctl = SDVS30; + capa = VS30 | VS18; + } else { + hctl = SDVS18; + capa = VS18; + } + + value = OMAP_HSMMC_READ(host->base, HCTL) & ~SDVS_MASK; + OMAP_HSMMC_WRITE(host->base, HCTL, value | hctl); + + value = OMAP_HSMMC_READ(host->base, CAPA); + OMAP_HSMMC_WRITE(host->base, CAPA, value | capa); + + /* Set the controller to AUTO IDLE mode */ + value = OMAP_HSMMC_READ(host->base, SYSCONFIG); + OMAP_HSMMC_WRITE(host->base, SYSCONFIG, value | AUTOIDLE); + + /* Set SD bus power bit */ + set_sd_bus_power(host); +} + static struct mmc_host_ops mmc_omap_ops = { .request = omap_mmc_request, .set_ios = omap_mmc_set_ios, @@ -906,7 +971,6 @@ static int __init omap_mmc_probe(struct platform_device *pdev) struct mmc_omap_host *host = NULL; struct resource *res; int ret = 0, irq; - u32 hctl, capa; if (pdata == NULL) { dev_err(&pdev->dev, "Platform Data is missing\n"); @@ -996,10 +1060,11 @@ static int __init omap_mmc_probe(struct platform_device *pdev) else host->dbclk_enabled = 1; -#ifdef CONFIG_MMC_BLOCK_BOUNCE - mmc->max_phys_segs = 1; - mmc->max_hw_segs = 1; -#endif + /* Since we do only SG emulation, we can have as many segs + * as we want. */ + mmc->max_phys_segs = 1024; + mmc->max_hw_segs = 1024; + mmc->max_blk_size = 512; /* Block Length at max can be 1024 */ mmc->max_blk_count = 0xFFFF; /* No. of Blocks is 16 bits */ mmc->max_req_size = mmc->max_blk_size * mmc->max_blk_count; @@ -1008,31 +1073,31 @@ static int __init omap_mmc_probe(struct platform_device *pdev) mmc->ocr_avail = mmc_slot(host).ocr_mask; mmc->caps |= MMC_CAP_MMC_HIGHSPEED | MMC_CAP_SD_HIGHSPEED; - if (pdata->slots[host->slot_id].wires >= 4) + if (pdata->slots[host->slot_id].wires >= 8) + mmc->caps |= MMC_CAP_8_BIT_DATA; + else if (pdata->slots[host->slot_id].wires >= 4) mmc->caps |= MMC_CAP_4_BIT_DATA; - /* Only MMC1 supports 3.0V */ - if (host->id == OMAP_MMC1_DEVID) { - hctl = SDVS30; - capa = VS30 | VS18; - } else { - hctl = SDVS18; - capa = VS18; - } - - OMAP_HSMMC_WRITE(host->base, HCTL, - OMAP_HSMMC_READ(host->base, HCTL) | hctl); - - OMAP_HSMMC_WRITE(host->base, CAPA, - OMAP_HSMMC_READ(host->base, CAPA) | capa); - - /* Set the controller to AUTO IDLE mode */ - OMAP_HSMMC_WRITE(host->base, SYSCONFIG, - OMAP_HSMMC_READ(host->base, SYSCONFIG) | AUTOIDLE); + omap_hsmmc_init(host); - /* Set SD bus power bit */ - OMAP_HSMMC_WRITE(host->base, HCTL, - OMAP_HSMMC_READ(host->base, HCTL) | SDBP); + /* Select DMA lines */ + switch (host->id) { + case OMAP_MMC1_DEVID: + host->dma_line_tx = OMAP24XX_DMA_MMC1_TX; + host->dma_line_rx = OMAP24XX_DMA_MMC1_RX; + break; + case OMAP_MMC2_DEVID: + host->dma_line_tx = OMAP24XX_DMA_MMC2_TX; + host->dma_line_rx = OMAP24XX_DMA_MMC2_RX; + break; + case OMAP_MMC3_DEVID: + host->dma_line_tx = OMAP34XX_DMA_MMC3_TX; + host->dma_line_rx = OMAP34XX_DMA_MMC3_RX; + break; + default: + dev_err(mmc_dev(host->mmc), "Invalid MMC id\n"); + goto err_irq; + } /* Request IRQ for MMC operations */ ret = request_irq(host->irq, mmc_omap_irq, IRQF_DISABLED, @@ -1051,7 +1116,7 @@ static int __init omap_mmc_probe(struct platform_device *pdev) } /* Request IRQ for card detect */ - if ((mmc_slot(host).card_detect_irq) && (mmc_slot(host).card_detect)) { + if ((mmc_slot(host).card_detect_irq)) { ret = request_irq(mmc_slot(host).card_detect_irq, omap_mmc_cd_handler, IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING @@ -1074,8 +1139,8 @@ static int __init omap_mmc_probe(struct platform_device *pdev) if (ret < 0) goto err_slot_name; } - if (mmc_slot(host).card_detect_irq && mmc_slot(host).card_detect && - host->pdata->slots[host->slot_id].get_cover_state) { + if (mmc_slot(host).card_detect_irq && + host->pdata->slots[host->slot_id].get_cover_state) { ret = device_create_file(&mmc->class_dev, &dev_attr_cover_switch); if (ret < 0) @@ -1173,20 +1238,8 @@ static int omap_mmc_suspend(struct platform_device *pdev, pm_message_t state) " level suspend\n"); } - if (host->id == OMAP_MMC1_DEVID - && !(OMAP_HSMMC_READ(host->base, HCTL) - & SDVSDET)) { - OMAP_HSMMC_WRITE(host->base, HCTL, - OMAP_HSMMC_READ(host->base, HCTL) - & SDVSCLR); - OMAP_HSMMC_WRITE(host->base, HCTL, - OMAP_HSMMC_READ(host->base, HCTL) - | SDVS30); - OMAP_HSMMC_WRITE(host->base, HCTL, - OMAP_HSMMC_READ(host->base, HCTL) - | SDBP); - } - + OMAP_HSMMC_WRITE(host->base, HCTL, + OMAP_HSMMC_READ(host->base, HCTL) & ~SDBP); clk_disable(host->fclk); clk_disable(host->iclk); clk_disable(host->dbclk); @@ -1222,6 +1275,8 @@ static int omap_mmc_resume(struct platform_device *pdev) dev_dbg(mmc_dev(host->mmc), "Enabling debounce clk failed\n"); + omap_hsmmc_init(host); + if (host->pdata->resume) { ret = host->pdata->resume(&pdev->dev, host->slot_id); if (ret) diff --git a/drivers/mmc/host/sdhci-of.c b/drivers/mmc/host/sdhci-of.c new file mode 100644 index 000000000000..3ff4ac3abe8b --- /dev/null +++ b/drivers/mmc/host/sdhci-of.c @@ -0,0 +1,309 @@ +/* + * OpenFirmware bindings for Secure Digital Host Controller Interface. + * + * Copyright (c) 2007 Freescale Semiconductor, Inc. + * Copyright (c) 2009 MontaVista Software, Inc. + * + * Authors: Xiaobo Xie <X.Xie@freescale.com> + * Anton Vorontsov <avorontsov@ru.mvista.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. + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/io.h> +#include <linux/interrupt.h> +#include <linux/delay.h> +#include <linux/of.h> +#include <linux/of_platform.h> +#include <linux/mmc/host.h> +#include "sdhci.h" + +struct sdhci_of_data { + unsigned int quirks; + struct sdhci_ops ops; +}; + +struct sdhci_of_host { + unsigned int clock; + u16 xfer_mode_shadow; +}; + +/* + * Ops and quirks for the Freescale eSDHC controller. + */ + +#define ESDHC_DMA_SYSCTL 0x40c +#define ESDHC_DMA_SNOOP 0x00000040 + +#define ESDHC_SYSTEM_CONTROL 0x2c +#define ESDHC_CLOCK_MASK 0x0000fff0 +#define ESDHC_PREDIV_SHIFT 8 +#define ESDHC_DIVIDER_SHIFT 4 +#define ESDHC_CLOCK_PEREN 0x00000004 +#define ESDHC_CLOCK_HCKEN 0x00000002 +#define ESDHC_CLOCK_IPGEN 0x00000001 + +static u32 esdhc_readl(struct sdhci_host *host, int reg) +{ + return in_be32(host->ioaddr + reg); +} + +static u16 esdhc_readw(struct sdhci_host *host, int reg) +{ + return in_be16(host->ioaddr + (reg ^ 0x2)); +} + +static u8 esdhc_readb(struct sdhci_host *host, int reg) +{ + return in_8(host->ioaddr + (reg ^ 0x3)); +} + +static void esdhc_writel(struct sdhci_host *host, u32 val, int reg) +{ + out_be32(host->ioaddr + reg, val); +} + +static void esdhc_writew(struct sdhci_host *host, u16 val, int reg) +{ + struct sdhci_of_host *of_host = sdhci_priv(host); + int base = reg & ~0x3; + int shift = (reg & 0x2) * 8; + + switch (reg) { + case SDHCI_TRANSFER_MODE: + /* + * Postpone this write, we must do it together with a + * command write that is down below. + */ + of_host->xfer_mode_shadow = val; + return; + case SDHCI_COMMAND: + esdhc_writel(host, val << 16 | of_host->xfer_mode_shadow, + SDHCI_TRANSFER_MODE); + return; + case SDHCI_BLOCK_SIZE: + /* + * Two last DMA bits are reserved, and first one is used for + * non-standard blksz of 4096 bytes that we don't support + * yet. So clear the DMA boundary bits. + */ + val &= ~SDHCI_MAKE_BLKSZ(0x7, 0); + /* fall through */ + } + clrsetbits_be32(host->ioaddr + base, 0xffff << shift, val << shift); +} + +static void esdhc_writeb(struct sdhci_host *host, u8 val, int reg) +{ + int base = reg & ~0x3; + int shift = (reg & 0x3) * 8; + + clrsetbits_be32(host->ioaddr + base , 0xff << shift, val << shift); +} + +static void esdhc_set_clock(struct sdhci_host *host, unsigned int clock) +{ + int div; + int pre_div = 2; + + clrbits32(host->ioaddr + ESDHC_SYSTEM_CONTROL, ESDHC_CLOCK_IPGEN | + ESDHC_CLOCK_HCKEN | ESDHC_CLOCK_PEREN | ESDHC_CLOCK_MASK); + + if (clock == 0) + goto out; + + if (host->max_clk / 16 > clock) { + for (; pre_div < 256; pre_div *= 2) { + if (host->max_clk / pre_div < clock * 16) + break; + } + } + + for (div = 1; div <= 16; div++) { + if (host->max_clk / (div * pre_div) <= clock) + break; + } + + pre_div >>= 1; + + setbits32(host->ioaddr + ESDHC_SYSTEM_CONTROL, ESDHC_CLOCK_IPGEN | + ESDHC_CLOCK_HCKEN | ESDHC_CLOCK_PEREN | + div << ESDHC_DIVIDER_SHIFT | pre_div << ESDHC_PREDIV_SHIFT); + mdelay(100); +out: + host->clock = clock; +} + +static int esdhc_enable_dma(struct sdhci_host *host) +{ + setbits32(host->ioaddr + ESDHC_DMA_SYSCTL, ESDHC_DMA_SNOOP); + return 0; +} + +static unsigned int esdhc_get_max_clock(struct sdhci_host *host) +{ + struct sdhci_of_host *of_host = sdhci_priv(host); + + return of_host->clock; +} + +static unsigned int esdhc_get_timeout_clock(struct sdhci_host *host) +{ + struct sdhci_of_host *of_host = sdhci_priv(host); + + return of_host->clock / 1000; +} + +static struct sdhci_of_data sdhci_esdhc = { + .quirks = SDHCI_QUIRK_FORCE_BLK_SZ_2048 | + SDHCI_QUIRK_BROKEN_CARD_DETECTION | + SDHCI_QUIRK_INVERTED_WRITE_PROTECT | + SDHCI_QUIRK_NO_BUSY_IRQ | + SDHCI_QUIRK_NONSTANDARD_CLOCK | + SDHCI_QUIRK_PIO_NEEDS_DELAY | + SDHCI_QUIRK_RESTORE_IRQS_AFTER_RESET | + SDHCI_QUIRK_NO_CARD_NO_RESET, + .ops = { + .readl = esdhc_readl, + .readw = esdhc_readw, + .readb = esdhc_readb, + .writel = esdhc_writel, + .writew = esdhc_writew, + .writeb = esdhc_writeb, + .set_clock = esdhc_set_clock, + .enable_dma = esdhc_enable_dma, + .get_max_clock = esdhc_get_max_clock, + .get_timeout_clock = esdhc_get_timeout_clock, + }, +}; + +#ifdef CONFIG_PM + +static int sdhci_of_suspend(struct of_device *ofdev, pm_message_t state) +{ + struct sdhci_host *host = dev_get_drvdata(&ofdev->dev); + + return mmc_suspend_host(host->mmc, state); +} + +static int sdhci_of_resume(struct of_device *ofdev) +{ + struct sdhci_host *host = dev_get_drvdata(&ofdev->dev); + + return mmc_resume_host(host->mmc); +} + +#else + +#define sdhci_of_suspend NULL +#define sdhci_of_resume NULL + +#endif + +static int __devinit sdhci_of_probe(struct of_device *ofdev, + const struct of_device_id *match) +{ + struct device_node *np = ofdev->node; + struct sdhci_of_data *sdhci_of_data = match->data; + struct sdhci_host *host; + struct sdhci_of_host *of_host; + const u32 *clk; + int size; + int ret; + + if (!of_device_is_available(np)) + return -ENODEV; + + host = sdhci_alloc_host(&ofdev->dev, sizeof(*of_host)); + if (!host) + return -ENOMEM; + + of_host = sdhci_priv(host); + dev_set_drvdata(&ofdev->dev, host); + + host->ioaddr = of_iomap(np, 0); + if (!host->ioaddr) { + ret = -ENOMEM; + goto err_addr_map; + } + + host->irq = irq_of_parse_and_map(np, 0); + if (!host->irq) { + ret = -EINVAL; + goto err_no_irq; + } + + host->hw_name = dev_name(&ofdev->dev); + if (sdhci_of_data) { + host->quirks = sdhci_of_data->quirks; + host->ops = &sdhci_of_data->ops; + } + + clk = of_get_property(np, "clock-frequency", &size); + if (clk && size == sizeof(*clk) && *clk) + of_host->clock = *clk; + + ret = sdhci_add_host(host); + if (ret) + goto err_add_host; + + return 0; + +err_add_host: + irq_dispose_mapping(host->irq); +err_no_irq: + iounmap(host->ioaddr); +err_addr_map: + sdhci_free_host(host); + return ret; +} + +static int __devexit sdhci_of_remove(struct of_device *ofdev) +{ + struct sdhci_host *host = dev_get_drvdata(&ofdev->dev); + + sdhci_remove_host(host, 0); + sdhci_free_host(host); + irq_dispose_mapping(host->irq); + iounmap(host->ioaddr); + return 0; +} + +static const struct of_device_id sdhci_of_match[] = { + { .compatible = "fsl,mpc8379-esdhc", .data = &sdhci_esdhc, }, + { .compatible = "fsl,mpc8536-esdhc", .data = &sdhci_esdhc, }, + { .compatible = "generic-sdhci", }, + {}, +}; +MODULE_DEVICE_TABLE(of, sdhci_of_match); + +static struct of_platform_driver sdhci_of_driver = { + .driver.name = "sdhci-of", + .match_table = sdhci_of_match, + .probe = sdhci_of_probe, + .remove = __devexit_p(sdhci_of_remove), + .suspend = sdhci_of_suspend, + .resume = sdhci_of_resume, +}; + +static int __init sdhci_of_init(void) +{ + return of_register_platform_driver(&sdhci_of_driver); +} +module_init(sdhci_of_init); + +static void __exit sdhci_of_exit(void) +{ + of_unregister_platform_driver(&sdhci_of_driver); +} +module_exit(sdhci_of_exit); + +MODULE_DESCRIPTION("Secure Digital Host Controller Interface OF driver"); +MODULE_AUTHOR("Xiaobo Xie <X.Xie@freescale.com>, " + "Anton Vorontsov <avorontsov@ru.mvista.com>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index accb592764ed..30d8e3d4e6fd 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -48,35 +48,35 @@ static void sdhci_dumpregs(struct sdhci_host *host) printk(KERN_DEBUG DRIVER_NAME ": ============== REGISTER DUMP ==============\n"); printk(KERN_DEBUG DRIVER_NAME ": Sys addr: 0x%08x | Version: 0x%08x\n", - readl(host->ioaddr + SDHCI_DMA_ADDRESS), - readw(host->ioaddr + SDHCI_HOST_VERSION)); + sdhci_readl(host, SDHCI_DMA_ADDRESS), + sdhci_readw(host, SDHCI_HOST_VERSION)); printk(KERN_DEBUG DRIVER_NAME ": Blk size: 0x%08x | Blk cnt: 0x%08x\n", - readw(host->ioaddr + SDHCI_BLOCK_SIZE), - readw(host->ioaddr + SDHCI_BLOCK_COUNT)); + sdhci_readw(host, SDHCI_BLOCK_SIZE), + sdhci_readw(host, SDHCI_BLOCK_COUNT)); printk(KERN_DEBUG DRIVER_NAME ": Argument: 0x%08x | Trn mode: 0x%08x\n", - readl(host->ioaddr + SDHCI_ARGUMENT), - readw(host->ioaddr + SDHCI_TRANSFER_MODE)); + sdhci_readl(host, SDHCI_ARGUMENT), + sdhci_readw(host, SDHCI_TRANSFER_MODE)); printk(KERN_DEBUG DRIVER_NAME ": Present: 0x%08x | Host ctl: 0x%08x\n", - readl(host->ioaddr + SDHCI_PRESENT_STATE), - readb(host->ioaddr + SDHCI_HOST_CONTROL)); + sdhci_readl(host, SDHCI_PRESENT_STATE), + sdhci_readb(host, SDHCI_HOST_CONTROL)); printk(KERN_DEBUG DRIVER_NAME ": Power: 0x%08x | Blk gap: 0x%08x\n", - readb(host->ioaddr + SDHCI_POWER_CONTROL), - readb(host->ioaddr + SDHCI_BLOCK_GAP_CONTROL)); + sdhci_readb(host, SDHCI_POWER_CONTROL), + sdhci_readb(host, SDHCI_BLOCK_GAP_CONTROL)); printk(KERN_DEBUG DRIVER_NAME ": Wake-up: 0x%08x | Clock: 0x%08x\n", - readb(host->ioaddr + SDHCI_WAKE_UP_CONTROL), - readw(host->ioaddr + SDHCI_CLOCK_CONTROL)); + sdhci_readb(host, SDHCI_WAKE_UP_CONTROL), + sdhci_readw(host, SDHCI_CLOCK_CONTROL)); printk(KERN_DEBUG DRIVER_NAME ": Timeout: 0x%08x | Int stat: 0x%08x\n", - readb(host->ioaddr + SDHCI_TIMEOUT_CONTROL), - readl(host->ioaddr + SDHCI_INT_STATUS)); + sdhci_readb(host, SDHCI_TIMEOUT_CONTROL), + sdhci_readl(host, SDHCI_INT_STATUS)); printk(KERN_DEBUG DRIVER_NAME ": Int enab: 0x%08x | Sig enab: 0x%08x\n", - readl(host->ioaddr + SDHCI_INT_ENABLE), - readl(host->ioaddr + SDHCI_SIGNAL_ENABLE)); + sdhci_readl(host, SDHCI_INT_ENABLE), + sdhci_readl(host, SDHCI_SIGNAL_ENABLE)); printk(KERN_DEBUG DRIVER_NAME ": AC12 err: 0x%08x | Slot int: 0x%08x\n", - readw(host->ioaddr + SDHCI_ACMD12_ERR), - readw(host->ioaddr + SDHCI_SLOT_INT_STATUS)); + sdhci_readw(host, SDHCI_ACMD12_ERR), + sdhci_readw(host, SDHCI_SLOT_INT_STATUS)); printk(KERN_DEBUG DRIVER_NAME ": Caps: 0x%08x | Max curr: 0x%08x\n", - readl(host->ioaddr + SDHCI_CAPABILITIES), - readl(host->ioaddr + SDHCI_MAX_CURRENT)); + sdhci_readl(host, SDHCI_CAPABILITIES), + sdhci_readl(host, SDHCI_MAX_CURRENT)); printk(KERN_DEBUG DRIVER_NAME ": ===========================================\n"); } @@ -87,17 +87,65 @@ static void sdhci_dumpregs(struct sdhci_host *host) * * \*****************************************************************************/ +static void sdhci_clear_set_irqs(struct sdhci_host *host, u32 clear, u32 set) +{ + u32 ier; + + ier = sdhci_readl(host, SDHCI_INT_ENABLE); + ier &= ~clear; + ier |= set; + sdhci_writel(host, ier, SDHCI_INT_ENABLE); + sdhci_writel(host, ier, SDHCI_SIGNAL_ENABLE); +} + +static void sdhci_unmask_irqs(struct sdhci_host *host, u32 irqs) +{ + sdhci_clear_set_irqs(host, 0, irqs); +} + +static void sdhci_mask_irqs(struct sdhci_host *host, u32 irqs) +{ + sdhci_clear_set_irqs(host, irqs, 0); +} + +static void sdhci_set_card_detection(struct sdhci_host *host, bool enable) +{ + u32 irqs = SDHCI_INT_CARD_REMOVE | SDHCI_INT_CARD_INSERT; + + if (host->quirks & SDHCI_QUIRK_BROKEN_CARD_DETECTION) + return; + + if (enable) + sdhci_unmask_irqs(host, irqs); + else + sdhci_mask_irqs(host, irqs); +} + +static void sdhci_enable_card_detection(struct sdhci_host *host) +{ + sdhci_set_card_detection(host, true); +} + +static void sdhci_disable_card_detection(struct sdhci_host *host) +{ + sdhci_set_card_detection(host, false); +} + static void sdhci_reset(struct sdhci_host *host, u8 mask) { unsigned long timeout; + u32 uninitialized_var(ier); if (host->quirks & SDHCI_QUIRK_NO_CARD_NO_RESET) { - if (!(readl(host->ioaddr + SDHCI_PRESENT_STATE) & + if (!(sdhci_readl(host, SDHCI_PRESENT_STATE) & SDHCI_CARD_PRESENT)) return; } - writeb(mask, host->ioaddr + SDHCI_SOFTWARE_RESET); + if (host->quirks & SDHCI_QUIRK_RESTORE_IRQS_AFTER_RESET) + ier = sdhci_readl(host, SDHCI_INT_ENABLE); + + sdhci_writeb(host, mask, SDHCI_SOFTWARE_RESET); if (mask & SDHCI_RESET_ALL) host->clock = 0; @@ -106,7 +154,7 @@ static void sdhci_reset(struct sdhci_host *host, u8 mask) timeout = 100; /* hw clears the bit when it's done */ - while (readb(host->ioaddr + SDHCI_SOFTWARE_RESET) & mask) { + while (sdhci_readb(host, SDHCI_SOFTWARE_RESET) & mask) { if (timeout == 0) { printk(KERN_ERR "%s: Reset 0x%x never completed.\n", mmc_hostname(host->mmc), (int)mask); @@ -116,42 +164,44 @@ static void sdhci_reset(struct sdhci_host *host, u8 mask) timeout--; mdelay(1); } + + if (host->quirks & SDHCI_QUIRK_RESTORE_IRQS_AFTER_RESET) + sdhci_clear_set_irqs(host, SDHCI_INT_ALL_MASK, ier); } static void sdhci_init(struct sdhci_host *host) { - u32 intmask; - sdhci_reset(host, SDHCI_RESET_ALL); - intmask = SDHCI_INT_BUS_POWER | SDHCI_INT_DATA_END_BIT | + sdhci_clear_set_irqs(host, SDHCI_INT_ALL_MASK, + SDHCI_INT_BUS_POWER | SDHCI_INT_DATA_END_BIT | SDHCI_INT_DATA_CRC | SDHCI_INT_DATA_TIMEOUT | SDHCI_INT_INDEX | SDHCI_INT_END_BIT | SDHCI_INT_CRC | SDHCI_INT_TIMEOUT | - SDHCI_INT_CARD_REMOVE | SDHCI_INT_CARD_INSERT | - SDHCI_INT_DATA_AVAIL | SDHCI_INT_SPACE_AVAIL | - SDHCI_INT_DMA_END | SDHCI_INT_DATA_END | SDHCI_INT_RESPONSE | - SDHCI_INT_ADMA_ERROR; + SDHCI_INT_DATA_END | SDHCI_INT_RESPONSE); +} - writel(intmask, host->ioaddr + SDHCI_INT_ENABLE); - writel(intmask, host->ioaddr + SDHCI_SIGNAL_ENABLE); +static void sdhci_reinit(struct sdhci_host *host) +{ + sdhci_init(host); + sdhci_enable_card_detection(host); } static void sdhci_activate_led(struct sdhci_host *host) { u8 ctrl; - ctrl = readb(host->ioaddr + SDHCI_HOST_CONTROL); + ctrl = sdhci_readb(host, SDHCI_HOST_CONTROL); ctrl |= SDHCI_CTRL_LED; - writeb(ctrl, host->ioaddr + SDHCI_HOST_CONTROL); + sdhci_writeb(host, ctrl, SDHCI_HOST_CONTROL); } static void sdhci_deactivate_led(struct sdhci_host *host) { u8 ctrl; - ctrl = readb(host->ioaddr + SDHCI_HOST_CONTROL); + ctrl = sdhci_readb(host, SDHCI_HOST_CONTROL); ctrl &= ~SDHCI_CTRL_LED; - writeb(ctrl, host->ioaddr + SDHCI_HOST_CONTROL); + sdhci_writeb(host, ctrl, SDHCI_HOST_CONTROL); } #ifdef SDHCI_USE_LEDS_CLASS @@ -205,7 +255,7 @@ static void sdhci_read_block_pio(struct sdhci_host *host) while (len) { if (chunk == 0) { - scratch = readl(host->ioaddr + SDHCI_BUFFER); + scratch = sdhci_readl(host, SDHCI_BUFFER); chunk = 4; } @@ -257,7 +307,7 @@ static void sdhci_write_block_pio(struct sdhci_host *host) len--; if ((chunk == 4) || ((len == 0) && (blksize == 0))) { - writel(scratch, host->ioaddr + SDHCI_BUFFER); + sdhci_writel(host, scratch, SDHCI_BUFFER); chunk = 0; scratch = 0; } @@ -292,7 +342,10 @@ static void sdhci_transfer_pio(struct sdhci_host *host) (host->data->blocks == 1)) mask = ~0; - while (readl(host->ioaddr + SDHCI_PRESENT_STATE) & mask) { + while (sdhci_readl(host, SDHCI_PRESENT_STATE) & mask) { + if (host->quirks & SDHCI_QUIRK_PIO_NEEDS_DELAY) + udelay(100); + if (host->data->flags & MMC_DATA_READ) sdhci_read_block_pio(host); else @@ -561,6 +614,17 @@ static u8 sdhci_calc_timeout(struct sdhci_host *host, struct mmc_data *data) return count; } +static void sdhci_set_transfer_irqs(struct sdhci_host *host) +{ + u32 pio_irqs = SDHCI_INT_DATA_AVAIL | SDHCI_INT_SPACE_AVAIL; + u32 dma_irqs = SDHCI_INT_DMA_END | SDHCI_INT_ADMA_ERROR; + + if (host->flags & SDHCI_REQ_USE_DMA) + sdhci_clear_set_irqs(host, pio_irqs, dma_irqs); + else + sdhci_clear_set_irqs(host, dma_irqs, pio_irqs); +} + static void sdhci_prepare_data(struct sdhci_host *host, struct mmc_data *data) { u8 count; @@ -581,7 +645,7 @@ static void sdhci_prepare_data(struct sdhci_host *host, struct mmc_data *data) host->data_early = 0; count = sdhci_calc_timeout(host, data); - writeb(count, host->ioaddr + SDHCI_TIMEOUT_CONTROL); + sdhci_writeb(host, count, SDHCI_TIMEOUT_CONTROL); if (host->flags & SDHCI_USE_DMA) host->flags |= SDHCI_REQ_USE_DMA; @@ -661,8 +725,8 @@ static void sdhci_prepare_data(struct sdhci_host *host, struct mmc_data *data) WARN_ON(1); host->flags &= ~SDHCI_REQ_USE_DMA; } else { - writel(host->adma_addr, - host->ioaddr + SDHCI_ADMA_ADDRESS); + sdhci_writel(host, host->adma_addr, + SDHCI_ADMA_ADDRESS); } } else { int sg_cnt; @@ -681,8 +745,8 @@ static void sdhci_prepare_data(struct sdhci_host *host, struct mmc_data *data) host->flags &= ~SDHCI_REQ_USE_DMA; } else { WARN_ON(sg_cnt != 1); - writel(sg_dma_address(data->sg), - host->ioaddr + SDHCI_DMA_ADDRESS); + sdhci_writel(host, sg_dma_address(data->sg), + SDHCI_DMA_ADDRESS); } } } @@ -693,14 +757,14 @@ static void sdhci_prepare_data(struct sdhci_host *host, struct mmc_data *data) * is ADMA. */ if (host->version >= SDHCI_SPEC_200) { - ctrl = readb(host->ioaddr + SDHCI_HOST_CONTROL); + ctrl = sdhci_readb(host, SDHCI_HOST_CONTROL); ctrl &= ~SDHCI_CTRL_DMA_MASK; if ((host->flags & SDHCI_REQ_USE_DMA) && (host->flags & SDHCI_USE_ADMA)) ctrl |= SDHCI_CTRL_ADMA32; else ctrl |= SDHCI_CTRL_SDMA; - writeb(ctrl, host->ioaddr + SDHCI_HOST_CONTROL); + sdhci_writeb(host, ctrl, SDHCI_HOST_CONTROL); } if (!(host->flags & SDHCI_REQ_USE_DMA)) { @@ -709,10 +773,11 @@ static void sdhci_prepare_data(struct sdhci_host *host, struct mmc_data *data) host->blocks = data->blocks; } + sdhci_set_transfer_irqs(host); + /* We do not handle DMA boundaries, so set it to max (512 KiB) */ - writew(SDHCI_MAKE_BLKSZ(7, data->blksz), - host->ioaddr + SDHCI_BLOCK_SIZE); - writew(data->blocks, host->ioaddr + SDHCI_BLOCK_COUNT); + sdhci_writew(host, SDHCI_MAKE_BLKSZ(7, data->blksz), SDHCI_BLOCK_SIZE); + sdhci_writew(host, data->blocks, SDHCI_BLOCK_COUNT); } static void sdhci_set_transfer_mode(struct sdhci_host *host, @@ -733,7 +798,7 @@ static void sdhci_set_transfer_mode(struct sdhci_host *host, if (host->flags & SDHCI_REQ_USE_DMA) mode |= SDHCI_TRNS_DMA; - writew(mode, host->ioaddr + SDHCI_TRANSFER_MODE); + sdhci_writew(host, mode, SDHCI_TRANSFER_MODE); } static void sdhci_finish_data(struct sdhci_host *host) @@ -802,7 +867,7 @@ static void sdhci_send_command(struct sdhci_host *host, struct mmc_command *cmd) if (host->mrq->data && (cmd == host->mrq->data->stop)) mask &= ~SDHCI_DATA_INHIBIT; - while (readl(host->ioaddr + SDHCI_PRESENT_STATE) & mask) { + while (sdhci_readl(host, SDHCI_PRESENT_STATE) & mask) { if (timeout == 0) { printk(KERN_ERR "%s: Controller never released " "inhibit bit(s).\n", mmc_hostname(host->mmc)); @@ -821,7 +886,7 @@ static void sdhci_send_command(struct sdhci_host *host, struct mmc_command *cmd) sdhci_prepare_data(host, cmd->data); - writel(cmd->arg, host->ioaddr + SDHCI_ARGUMENT); + sdhci_writel(host, cmd->arg, SDHCI_ARGUMENT); sdhci_set_transfer_mode(host, cmd->data); @@ -849,8 +914,7 @@ static void sdhci_send_command(struct sdhci_host *host, struct mmc_command *cmd) if (cmd->data) flags |= SDHCI_CMD_DATA; - writew(SDHCI_MAKE_CMD(cmd->opcode, flags), - host->ioaddr + SDHCI_COMMAND); + sdhci_writew(host, SDHCI_MAKE_CMD(cmd->opcode, flags), SDHCI_COMMAND); } static void sdhci_finish_command(struct sdhci_host *host) @@ -863,15 +927,15 @@ static void sdhci_finish_command(struct sdhci_host *host) if (host->cmd->flags & MMC_RSP_136) { /* CRC is stripped so we need to do some shifting. */ for (i = 0;i < 4;i++) { - host->cmd->resp[i] = readl(host->ioaddr + + host->cmd->resp[i] = sdhci_readl(host, SDHCI_RESPONSE + (3-i)*4) << 8; if (i != 3) host->cmd->resp[i] |= - readb(host->ioaddr + + sdhci_readb(host, SDHCI_RESPONSE + (3-i)*4-1); } } else { - host->cmd->resp[0] = readl(host->ioaddr + SDHCI_RESPONSE); + host->cmd->resp[0] = sdhci_readl(host, SDHCI_RESPONSE); } } @@ -895,7 +959,13 @@ static void sdhci_set_clock(struct sdhci_host *host, unsigned int clock) if (clock == host->clock) return; - writew(0, host->ioaddr + SDHCI_CLOCK_CONTROL); + if (host->ops->set_clock) { + host->ops->set_clock(host, clock); + if (host->quirks & SDHCI_QUIRK_NONSTANDARD_CLOCK) + return; + } + + sdhci_writew(host, 0, SDHCI_CLOCK_CONTROL); if (clock == 0) goto out; @@ -908,11 +978,11 @@ static void sdhci_set_clock(struct sdhci_host *host, unsigned int clock) clk = div << SDHCI_DIVIDER_SHIFT; clk |= SDHCI_CLOCK_INT_EN; - writew(clk, host->ioaddr + SDHCI_CLOCK_CONTROL); + sdhci_writew(host, clk, SDHCI_CLOCK_CONTROL); /* Wait max 10 ms */ timeout = 10; - while (!((clk = readw(host->ioaddr + SDHCI_CLOCK_CONTROL)) + while (!((clk = sdhci_readw(host, SDHCI_CLOCK_CONTROL)) & SDHCI_CLOCK_INT_STABLE)) { if (timeout == 0) { printk(KERN_ERR "%s: Internal clock never " @@ -925,7 +995,7 @@ static void sdhci_set_clock(struct sdhci_host *host, unsigned int clock) } clk |= SDHCI_CLOCK_CARD_EN; - writew(clk, host->ioaddr + SDHCI_CLOCK_CONTROL); + sdhci_writew(host, clk, SDHCI_CLOCK_CONTROL); out: host->clock = clock; @@ -939,7 +1009,7 @@ static void sdhci_set_power(struct sdhci_host *host, unsigned short power) return; if (power == (unsigned short)-1) { - writeb(0, host->ioaddr + SDHCI_POWER_CONTROL); + sdhci_writeb(host, 0, SDHCI_POWER_CONTROL); goto out; } @@ -948,7 +1018,7 @@ static void sdhci_set_power(struct sdhci_host *host, unsigned short power) * a new value. Some controllers don't seem to like this though. */ if (!(host->quirks & SDHCI_QUIRK_SINGLE_POWER_WRITE)) - writeb(0, host->ioaddr + SDHCI_POWER_CONTROL); + sdhci_writeb(host, 0, SDHCI_POWER_CONTROL); pwr = SDHCI_POWER_ON; @@ -973,10 +1043,9 @@ static void sdhci_set_power(struct sdhci_host *host, unsigned short power) * and set turn on power at the same time, so set the voltage first. */ if ((host->quirks & SDHCI_QUIRK_NO_SIMULT_VDD_AND_POWER)) - writeb(pwr & ~SDHCI_POWER_ON, - host->ioaddr + SDHCI_POWER_CONTROL); + sdhci_writeb(host, pwr & ~SDHCI_POWER_ON, SDHCI_POWER_CONTROL); - writeb(pwr, host->ioaddr + SDHCI_POWER_CONTROL); + sdhci_writeb(host, pwr, SDHCI_POWER_CONTROL); out: host->power = power; @@ -991,6 +1060,7 @@ out: static void sdhci_request(struct mmc_host *mmc, struct mmc_request *mrq) { struct sdhci_host *host; + bool present; unsigned long flags; host = mmc_priv(mmc); @@ -1005,8 +1075,14 @@ static void sdhci_request(struct mmc_host *mmc, struct mmc_request *mrq) host->mrq = mrq; - if (!(readl(host->ioaddr + SDHCI_PRESENT_STATE) & SDHCI_CARD_PRESENT) - || (host->flags & SDHCI_DEVICE_DEAD)) { + /* If polling, assume that the card is always present. */ + if (host->quirks & SDHCI_QUIRK_BROKEN_CARD_DETECTION) + present = true; + else + present = sdhci_readl(host, SDHCI_PRESENT_STATE) & + SDHCI_CARD_PRESENT; + + if (!present || host->flags & SDHCI_DEVICE_DEAD) { host->mrq->cmd->error = -ENOMEDIUM; tasklet_schedule(&host->finish_tasklet); } else @@ -1034,8 +1110,8 @@ static void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) * Should clear out any weird states. */ if (ios->power_mode == MMC_POWER_OFF) { - writel(0, host->ioaddr + SDHCI_SIGNAL_ENABLE); - sdhci_init(host); + sdhci_writel(host, 0, SDHCI_SIGNAL_ENABLE); + sdhci_reinit(host); } sdhci_set_clock(host, ios->clock); @@ -1045,7 +1121,7 @@ static void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) else sdhci_set_power(host, ios->vdd); - ctrl = readb(host->ioaddr + SDHCI_HOST_CONTROL); + ctrl = sdhci_readb(host, SDHCI_HOST_CONTROL); if (ios->bus_width == MMC_BUS_WIDTH_4) ctrl |= SDHCI_CTRL_4BITBUS; @@ -1057,7 +1133,7 @@ static void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) else ctrl &= ~SDHCI_CTRL_HISPD; - writeb(ctrl, host->ioaddr + SDHCI_HOST_CONTROL); + sdhci_writeb(host, ctrl, SDHCI_HOST_CONTROL); /* * Some (ENE) controllers go apeshit on some ios operation, @@ -1085,10 +1161,12 @@ static int sdhci_get_ro(struct mmc_host *mmc) if (host->flags & SDHCI_DEVICE_DEAD) present = 0; else - present = readl(host->ioaddr + SDHCI_PRESENT_STATE); + present = sdhci_readl(host, SDHCI_PRESENT_STATE); spin_unlock_irqrestore(&host->lock, flags); + if (host->quirks & SDHCI_QUIRK_INVERTED_WRITE_PROTECT) + return !!(present & SDHCI_WRITE_PROTECT); return !(present & SDHCI_WRITE_PROTECT); } @@ -1096,7 +1174,6 @@ static void sdhci_enable_sdio_irq(struct mmc_host *mmc, int enable) { struct sdhci_host *host; unsigned long flags; - u32 ier; host = mmc_priv(mmc); @@ -1105,15 +1182,10 @@ static void sdhci_enable_sdio_irq(struct mmc_host *mmc, int enable) if (host->flags & SDHCI_DEVICE_DEAD) goto out; - ier = readl(host->ioaddr + SDHCI_INT_ENABLE); - - ier &= ~SDHCI_INT_CARD_INT; if (enable) - ier |= SDHCI_INT_CARD_INT; - - writel(ier, host->ioaddr + SDHCI_INT_ENABLE); - writel(ier, host->ioaddr + SDHCI_SIGNAL_ENABLE); - + sdhci_unmask_irqs(host, SDHCI_INT_CARD_INT); + else + sdhci_mask_irqs(host, SDHCI_INT_CARD_INT); out: mmiowb(); @@ -1142,7 +1214,7 @@ static void sdhci_tasklet_card(unsigned long param) spin_lock_irqsave(&host->lock, flags); - if (!(readl(host->ioaddr + SDHCI_PRESENT_STATE) & SDHCI_CARD_PRESENT)) { + if (!(sdhci_readl(host, SDHCI_PRESENT_STATE) & SDHCI_CARD_PRESENT)) { if (host->mrq) { printk(KERN_ERR "%s: Card removed during transfer!\n", mmc_hostname(host->mmc)); @@ -1346,8 +1418,8 @@ static void sdhci_data_irq(struct sdhci_host *host, u32 intmask) * we need to at least restart the transfer. */ if (intmask & SDHCI_INT_DMA_END) - writel(readl(host->ioaddr + SDHCI_DMA_ADDRESS), - host->ioaddr + SDHCI_DMA_ADDRESS); + sdhci_writel(host, sdhci_readl(host, SDHCI_DMA_ADDRESS), + SDHCI_DMA_ADDRESS); if (intmask & SDHCI_INT_DATA_END) { if (host->cmd) { @@ -1373,7 +1445,7 @@ static irqreturn_t sdhci_irq(int irq, void *dev_id) spin_lock(&host->lock); - intmask = readl(host->ioaddr + SDHCI_INT_STATUS); + intmask = sdhci_readl(host, SDHCI_INT_STATUS); if (!intmask || intmask == 0xffffffff) { result = IRQ_NONE; @@ -1384,22 +1456,22 @@ static irqreturn_t sdhci_irq(int irq, void *dev_id) mmc_hostname(host->mmc), intmask); if (intmask & (SDHCI_INT_CARD_INSERT | SDHCI_INT_CARD_REMOVE)) { - writel(intmask & (SDHCI_INT_CARD_INSERT | SDHCI_INT_CARD_REMOVE), - host->ioaddr + SDHCI_INT_STATUS); + sdhci_writel(host, intmask & (SDHCI_INT_CARD_INSERT | + SDHCI_INT_CARD_REMOVE), SDHCI_INT_STATUS); tasklet_schedule(&host->card_tasklet); } intmask &= ~(SDHCI_INT_CARD_INSERT | SDHCI_INT_CARD_REMOVE); if (intmask & SDHCI_INT_CMD_MASK) { - writel(intmask & SDHCI_INT_CMD_MASK, - host->ioaddr + SDHCI_INT_STATUS); + sdhci_writel(host, intmask & SDHCI_INT_CMD_MASK, + SDHCI_INT_STATUS); sdhci_cmd_irq(host, intmask & SDHCI_INT_CMD_MASK); } if (intmask & SDHCI_INT_DATA_MASK) { - writel(intmask & SDHCI_INT_DATA_MASK, - host->ioaddr + SDHCI_INT_STATUS); + sdhci_writel(host, intmask & SDHCI_INT_DATA_MASK, + SDHCI_INT_STATUS); sdhci_data_irq(host, intmask & SDHCI_INT_DATA_MASK); } @@ -1410,7 +1482,7 @@ static irqreturn_t sdhci_irq(int irq, void *dev_id) if (intmask & SDHCI_INT_BUS_POWER) { printk(KERN_ERR "%s: Card is consuming too much power!\n", mmc_hostname(host->mmc)); - writel(SDHCI_INT_BUS_POWER, host->ioaddr + SDHCI_INT_STATUS); + sdhci_writel(host, SDHCI_INT_BUS_POWER, SDHCI_INT_STATUS); } intmask &= ~SDHCI_INT_BUS_POWER; @@ -1425,7 +1497,7 @@ static irqreturn_t sdhci_irq(int irq, void *dev_id) mmc_hostname(host->mmc), intmask); sdhci_dumpregs(host); - writel(intmask, host->ioaddr + SDHCI_INT_STATUS); + sdhci_writel(host, intmask, SDHCI_INT_STATUS); } result = IRQ_HANDLED; @@ -1455,6 +1527,8 @@ int sdhci_suspend_host(struct sdhci_host *host, pm_message_t state) { int ret; + sdhci_disable_card_detection(host); + ret = mmc_suspend_host(host->mmc, state); if (ret) return ret; @@ -1487,6 +1561,8 @@ int sdhci_resume_host(struct sdhci_host *host) if (ret) return ret; + sdhci_enable_card_detection(host); + return 0; } @@ -1537,7 +1613,7 @@ int sdhci_add_host(struct sdhci_host *host) sdhci_reset(host, SDHCI_RESET_ALL); - host->version = readw(host->ioaddr + SDHCI_HOST_VERSION); + host->version = sdhci_readw(host, SDHCI_HOST_VERSION); host->version = (host->version & SDHCI_SPEC_VER_MASK) >> SDHCI_SPEC_VER_SHIFT; if (host->version > SDHCI_SPEC_200) { @@ -1546,7 +1622,7 @@ int sdhci_add_host(struct sdhci_host *host) host->version); } - caps = readl(host->ioaddr + SDHCI_CAPABILITIES); + caps = sdhci_readl(host, SDHCI_CAPABILITIES); if (host->quirks & SDHCI_QUIRK_FORCE_DMA) host->flags |= SDHCI_USE_DMA; @@ -1614,19 +1690,27 @@ int sdhci_add_host(struct sdhci_host *host) host->max_clk = (caps & SDHCI_CLOCK_BASE_MASK) >> SDHCI_CLOCK_BASE_SHIFT; + host->max_clk *= 1000000; if (host->max_clk == 0) { - printk(KERN_ERR "%s: Hardware doesn't specify base clock " - "frequency.\n", mmc_hostname(mmc)); - return -ENODEV; + if (!host->ops->get_max_clock) { + printk(KERN_ERR + "%s: Hardware doesn't specify base clock " + "frequency.\n", mmc_hostname(mmc)); + return -ENODEV; + } + host->max_clk = host->ops->get_max_clock(host); } - host->max_clk *= 1000000; host->timeout_clk = (caps & SDHCI_TIMEOUT_CLK_MASK) >> SDHCI_TIMEOUT_CLK_SHIFT; if (host->timeout_clk == 0) { - printk(KERN_ERR "%s: Hardware doesn't specify timeout clock " - "frequency.\n", mmc_hostname(mmc)); - return -ENODEV; + if (!host->ops->get_timeout_clock) { + printk(KERN_ERR + "%s: Hardware doesn't specify timeout clock " + "frequency.\n", mmc_hostname(mmc)); + return -ENODEV; + } + host->timeout_clk = host->ops->get_timeout_clock(host); } if (caps & SDHCI_TIMEOUT_CLK_UNIT) host->timeout_clk *= 1000; @@ -1642,6 +1726,9 @@ int sdhci_add_host(struct sdhci_host *host) if (caps & SDHCI_CAN_DO_HISPD) mmc->caps |= MMC_CAP_SD_HIGHSPEED; + if (host->quirks & SDHCI_QUIRK_BROKEN_CARD_DETECTION) + mmc->caps |= MMC_CAP_NEEDS_POLL; + mmc->ocr_avail = 0; if (caps & SDHCI_CAN_VDD_330) mmc->ocr_avail |= MMC_VDD_32_33|MMC_VDD_33_34; @@ -1690,13 +1777,19 @@ int sdhci_add_host(struct sdhci_host *host) * Maximum block size. This varies from controller to controller and * is specified in the capabilities register. */ - mmc->max_blk_size = (caps & SDHCI_MAX_BLOCK_MASK) >> SDHCI_MAX_BLOCK_SHIFT; - if (mmc->max_blk_size >= 3) { - printk(KERN_WARNING "%s: Invalid maximum block size, " - "assuming 512 bytes\n", mmc_hostname(mmc)); - mmc->max_blk_size = 512; - } else - mmc->max_blk_size = 512 << mmc->max_blk_size; + if (host->quirks & SDHCI_QUIRK_FORCE_BLK_SZ_2048) { + mmc->max_blk_size = 2; + } else { + mmc->max_blk_size = (caps & SDHCI_MAX_BLOCK_MASK) >> + SDHCI_MAX_BLOCK_SHIFT; + if (mmc->max_blk_size >= 3) { + printk(KERN_WARNING "%s: Invalid maximum block size, " + "assuming 512 bytes\n", mmc_hostname(mmc)); + mmc->max_blk_size = 0; + } + } + + mmc->max_blk_size = 512 << mmc->max_blk_size; /* * Maximum block count. @@ -1746,6 +1839,8 @@ int sdhci_add_host(struct sdhci_host *host) (host->flags & SDHCI_USE_ADMA)?"A":"", (host->flags & SDHCI_USE_DMA)?"DMA":"PIO"); + sdhci_enable_card_detection(host); + return 0; #ifdef SDHCI_USE_LEDS_CLASS @@ -1782,6 +1877,8 @@ void sdhci_remove_host(struct sdhci_host *host, int dead) spin_unlock_irqrestore(&host->lock, flags); } + sdhci_disable_card_detection(host); + mmc_remove_host(host->mmc); #ifdef SDHCI_USE_LEDS_CLASS diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h index 43c37c68d07a..f20a834f4309 100644 --- a/drivers/mmc/host/sdhci.h +++ b/drivers/mmc/host/sdhci.h @@ -10,6 +10,9 @@ */ #include <linux/scatterlist.h> +#include <linux/compiler.h> +#include <linux/types.h> +#include <linux/io.h> /* * Controller registers @@ -123,6 +126,7 @@ SDHCI_INT_DATA_AVAIL | SDHCI_INT_SPACE_AVAIL | \ SDHCI_INT_DATA_TIMEOUT | SDHCI_INT_DATA_CRC | \ SDHCI_INT_DATA_END_BIT) +#define SDHCI_INT_ALL_MASK ((unsigned int)-1) #define SDHCI_ACMD12_ERR 0x3C @@ -210,6 +214,18 @@ struct sdhci_host { #define SDHCI_QUIRK_BROKEN_SMALL_PIO (1<<13) /* Controller does not provide transfer-complete interrupt when not busy */ #define SDHCI_QUIRK_NO_BUSY_IRQ (1<<14) +/* Controller has unreliable card detection */ +#define SDHCI_QUIRK_BROKEN_CARD_DETECTION (1<<15) +/* Controller reports inverted write-protect state */ +#define SDHCI_QUIRK_INVERTED_WRITE_PROTECT (1<<16) +/* Controller has nonstandard clock management */ +#define SDHCI_QUIRK_NONSTANDARD_CLOCK (1<<17) +/* Controller does not like fast PIO transfers */ +#define SDHCI_QUIRK_PIO_NEEDS_DELAY (1<<18) +/* Controller losing signal/interrupt enable states after reset */ +#define SDHCI_QUIRK_RESTORE_IRQS_AFTER_RESET (1<<19) +/* Controller has to be forced to use block size of 2048 bytes */ +#define SDHCI_QUIRK_FORCE_BLK_SZ_2048 (1<<20) int irq; /* Device IRQ */ void __iomem * ioaddr; /* Mapped address */ @@ -267,9 +283,105 @@ struct sdhci_host { struct sdhci_ops { +#ifdef CONFIG_MMC_SDHCI_IO_ACCESSORS + u32 (*readl)(struct sdhci_host *host, int reg); + u16 (*readw)(struct sdhci_host *host, int reg); + u8 (*readb)(struct sdhci_host *host, int reg); + void (*writel)(struct sdhci_host *host, u32 val, int reg); + void (*writew)(struct sdhci_host *host, u16 val, int reg); + void (*writeb)(struct sdhci_host *host, u8 val, int reg); +#endif + + void (*set_clock)(struct sdhci_host *host, unsigned int clock); + int (*enable_dma)(struct sdhci_host *host); + unsigned int (*get_max_clock)(struct sdhci_host *host); + unsigned int (*get_timeout_clock)(struct sdhci_host *host); }; +#ifdef CONFIG_MMC_SDHCI_IO_ACCESSORS + +static inline void sdhci_writel(struct sdhci_host *host, u32 val, int reg) +{ + if (unlikely(host->ops->writel)) + host->ops->writel(host, val, reg); + else + writel(val, host->ioaddr + reg); +} + +static inline void sdhci_writew(struct sdhci_host *host, u16 val, int reg) +{ + if (unlikely(host->ops->writew)) + host->ops->writew(host, val, reg); + else + writew(val, host->ioaddr + reg); +} + +static inline void sdhci_writeb(struct sdhci_host *host, u8 val, int reg) +{ + if (unlikely(host->ops->writeb)) + host->ops->writeb(host, val, reg); + else + writeb(val, host->ioaddr + reg); +} + +static inline u32 sdhci_readl(struct sdhci_host *host, int reg) +{ + if (unlikely(host->ops->readl)) + return host->ops->readl(host, reg); + else + return readl(host->ioaddr + reg); +} + +static inline u16 sdhci_readw(struct sdhci_host *host, int reg) +{ + if (unlikely(host->ops->readw)) + return host->ops->readw(host, reg); + else + return readw(host->ioaddr + reg); +} + +static inline u8 sdhci_readb(struct sdhci_host *host, int reg) +{ + if (unlikely(host->ops->readb)) + return host->ops->readb(host, reg); + else + return readb(host->ioaddr + reg); +} + +#else + +static inline void sdhci_writel(struct sdhci_host *host, u32 val, int reg) +{ + writel(val, host->ioaddr + reg); +} + +static inline void sdhci_writew(struct sdhci_host *host, u16 val, int reg) +{ + writew(val, host->ioaddr + reg); +} + +static inline void sdhci_writeb(struct sdhci_host *host, u8 val, int reg) +{ + writeb(val, host->ioaddr + reg); +} + +static inline u32 sdhci_readl(struct sdhci_host *host, int reg) +{ + return readl(host->ioaddr + reg); +} + +static inline u16 sdhci_readw(struct sdhci_host *host, int reg) +{ + return readw(host->ioaddr + reg); +} + +static inline u8 sdhci_readb(struct sdhci_host *host, int reg) +{ + return readb(host->ioaddr + reg); +} + +#endif /* CONFIG_MMC_SDHCI_IO_ACCESSORS */ extern struct sdhci_host *sdhci_alloc_host(struct device *dev, size_t priv_size); diff --git a/drivers/mmc/host/tmio_mmc.c b/drivers/mmc/host/tmio_mmc.c index 6a7a61904833..63fbd5b7d312 100644 --- a/drivers/mmc/host/tmio_mmc.c +++ b/drivers/mmc/host/tmio_mmc.c @@ -568,11 +568,11 @@ static int __devinit tmio_mmc_probe(struct platform_device *dev) host->mmc = mmc; platform_set_drvdata(dev, mmc); - host->ctl = ioremap(res_ctl->start, res_ctl->end - res_ctl->start); + host->ctl = ioremap(res_ctl->start, resource_size(res_ctl)); if (!host->ctl) goto host_free; - host->cnf = ioremap(res_cnf->start, res_cnf->end - res_cnf->start); + host->cnf = ioremap(res_cnf->start, resource_size(res_cnf)); if (!host->cnf) goto unmap_ctl; @@ -650,10 +650,10 @@ static int __devexit tmio_mmc_remove(struct platform_device *dev) if (mmc) { struct tmio_mmc_host *host = mmc_priv(mmc); mmc_remove_host(mmc); - mmc_free_host(mmc); free_irq(host->irq, host); iounmap(host->ctl); iounmap(host->cnf); + mmc_free_host(mmc); } return 0; diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h index ba2b4240a86a..9c831ab2ece6 100644 --- a/drivers/mmc/host/tmio_mmc.h +++ b/drivers/mmc/host/tmio_mmc.h @@ -8,6 +8,9 @@ * published by the Free Software Foundation. * */ + +#include <linux/highmem.h> + #define CNF_CMD 0x04 #define CNF_CTL_BASE 0x10 #define CNF_INT_PIN 0x3d diff --git a/drivers/mtd/nand/diskonchip.c b/drivers/mtd/nand/diskonchip.c index e4226e02d63e..e51c1ed7ac18 100644 --- a/drivers/mtd/nand/diskonchip.c +++ b/drivers/mtd/nand/diskonchip.c @@ -1773,4 +1773,4 @@ module_exit(cleanup_nanddoc); MODULE_LICENSE("GPL"); MODULE_AUTHOR("David Woodhouse <dwmw2@infradead.org>"); -MODULE_DESCRIPTION("M-Systems DiskOnChip 2000, Millennium and Millennium Plus device driver\n"); +MODULE_DESCRIPTION("M-Systems DiskOnChip 2000, Millennium and Millennium Plus device driver"); diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c index 0c3afccde8a2..5f71371eb1b0 100644 --- a/drivers/mtd/nand/nand_base.c +++ b/drivers/mtd/nand/nand_base.c @@ -2720,14 +2720,14 @@ int nand_scan_tail(struct mtd_info *mtd) return chip->scan_bbt(mtd); } -/* module_text_address() isn't exported, and it's mostly a pointless +/* is_module_text_address() isn't exported, and it's mostly a pointless test if this is a module _anyway_ -- they'd have to try _really_ hard to call us from in-kernel code if the core NAND support is modular. */ #ifdef MODULE #define caller_is_module() (1) #else #define caller_is_module() \ - module_text_address((unsigned long)__builtin_return_address(0)) + is_module_text_address((unsigned long)__builtin_return_address(0)) #endif /** diff --git a/drivers/mtd/tests/mtd_oobtest.c b/drivers/mtd/tests/mtd_oobtest.c index afbc3f8126db..a18e8d2f2557 100644 --- a/drivers/mtd/tests/mtd_oobtest.c +++ b/drivers/mtd/tests/mtd_oobtest.c @@ -136,7 +136,7 @@ static int write_eraseblock(int ebnum) ops.ooblen = use_len; ops.oobretlen = 0; ops.ooboffs = use_offset; - ops.datbuf = 0; + ops.datbuf = NULL; ops.oobbuf = writebuf; err = mtd->write_oob(mtd, addr, &ops); if (err || ops.oobretlen != use_len) { @@ -189,7 +189,7 @@ static int verify_eraseblock(int ebnum) ops.ooblen = use_len; ops.oobretlen = 0; ops.ooboffs = use_offset; - ops.datbuf = 0; + ops.datbuf = NULL; ops.oobbuf = readbuf; err = mtd->read_oob(mtd, addr, &ops); if (err || ops.oobretlen != use_len) { @@ -216,7 +216,7 @@ static int verify_eraseblock(int ebnum) ops.ooblen = mtd->ecclayout->oobavail; ops.oobretlen = 0; ops.ooboffs = 0; - ops.datbuf = 0; + ops.datbuf = NULL; ops.oobbuf = readbuf; err = mtd->read_oob(mtd, addr, &ops); if (err || ops.oobretlen != mtd->ecclayout->oobavail) { @@ -281,7 +281,7 @@ static int verify_eraseblock_in_one_go(int ebnum) ops.ooblen = len; ops.oobretlen = 0; ops.ooboffs = 0; - ops.datbuf = 0; + ops.datbuf = NULL; ops.oobbuf = readbuf; err = mtd->read_oob(mtd, addr, &ops); if (err || ops.oobretlen != len) { @@ -522,7 +522,7 @@ static int __init mtd_oobtest_init(void) ops.ooblen = 1; ops.oobretlen = 0; ops.ooboffs = mtd->ecclayout->oobavail; - ops.datbuf = 0; + ops.datbuf = NULL; ops.oobbuf = writebuf; printk(PRINT_PREF "attempting to start write past end of OOB\n"); printk(PRINT_PREF "an error is expected...\n"); @@ -542,7 +542,7 @@ static int __init mtd_oobtest_init(void) ops.ooblen = 1; ops.oobretlen = 0; ops.ooboffs = mtd->ecclayout->oobavail; - ops.datbuf = 0; + ops.datbuf = NULL; ops.oobbuf = readbuf; printk(PRINT_PREF "attempting to start read past end of OOB\n"); printk(PRINT_PREF "an error is expected...\n"); @@ -566,7 +566,7 @@ static int __init mtd_oobtest_init(void) ops.ooblen = mtd->ecclayout->oobavail + 1; ops.oobretlen = 0; ops.ooboffs = 0; - ops.datbuf = 0; + ops.datbuf = NULL; ops.oobbuf = writebuf; printk(PRINT_PREF "attempting to write past end of device\n"); printk(PRINT_PREF "an error is expected...\n"); @@ -586,7 +586,7 @@ static int __init mtd_oobtest_init(void) ops.ooblen = mtd->ecclayout->oobavail + 1; ops.oobretlen = 0; ops.ooboffs = 0; - ops.datbuf = 0; + ops.datbuf = NULL; ops.oobbuf = readbuf; printk(PRINT_PREF "attempting to read past end of device\n"); printk(PRINT_PREF "an error is expected...\n"); @@ -610,7 +610,7 @@ static int __init mtd_oobtest_init(void) ops.ooblen = mtd->ecclayout->oobavail; ops.oobretlen = 0; ops.ooboffs = 1; - ops.datbuf = 0; + ops.datbuf = NULL; ops.oobbuf = writebuf; printk(PRINT_PREF "attempting to write past end of device\n"); printk(PRINT_PREF "an error is expected...\n"); @@ -630,7 +630,7 @@ static int __init mtd_oobtest_init(void) ops.ooblen = mtd->ecclayout->oobavail; ops.oobretlen = 0; ops.ooboffs = 1; - ops.datbuf = 0; + ops.datbuf = NULL; ops.oobbuf = readbuf; printk(PRINT_PREF "attempting to read past end of device\n"); printk(PRINT_PREF "an error is expected...\n"); @@ -670,7 +670,7 @@ static int __init mtd_oobtest_init(void) ops.ooblen = sz; ops.oobretlen = 0; ops.ooboffs = 0; - ops.datbuf = 0; + ops.datbuf = NULL; ops.oobbuf = writebuf; err = mtd->write_oob(mtd, addr, &ops); if (err) @@ -698,7 +698,7 @@ static int __init mtd_oobtest_init(void) ops.ooblen = mtd->ecclayout->oobavail * 2; ops.oobretlen = 0; ops.ooboffs = 0; - ops.datbuf = 0; + ops.datbuf = NULL; ops.oobbuf = readbuf; err = mtd->read_oob(mtd, addr, &ops); if (err) diff --git a/drivers/mtd/tests/mtd_readtest.c b/drivers/mtd/tests/mtd_readtest.c index 645e77fdc63d..79fc4530987b 100644 --- a/drivers/mtd/tests/mtd_readtest.c +++ b/drivers/mtd/tests/mtd_readtest.c @@ -71,7 +71,7 @@ static int read_eraseblock_by_page(int ebnum) ops.ooblen = mtd->oobsize; ops.oobretlen = 0; ops.ooboffs = 0; - ops.datbuf = 0; + ops.datbuf = NULL; ops.oobbuf = oobbuf; ret = mtd->read_oob(mtd, addr, &ops); if (ret || ops.oobretlen != mtd->oobsize) { diff --git a/drivers/net/sb1250-mac.c b/drivers/net/sb1250-mac.c index 88dd2e09832f..ce7551e17ba7 100644 --- a/drivers/net/sb1250-mac.c +++ b/drivers/net/sb1250-mac.c @@ -2299,7 +2299,7 @@ static int sbmac_init(struct platform_device *pldev, long long base) eaddr = sc->sbm_hwaddr; /* - * Read the ethernet address. The firwmare left this programmed + * Read the ethernet address. The firmware left this programmed * for us in the ethernet address register for each mac. */ diff --git a/drivers/net/skfp/h/hwmtm.h b/drivers/net/skfp/h/hwmtm.h index 1a606d4bfe5e..e1a7e5f683dc 100644 --- a/drivers/net/skfp/h/hwmtm.h +++ b/drivers/net/skfp/h/hwmtm.h @@ -145,7 +145,7 @@ struct hw_modul { int leave_isr ; /* leave fddi_isr immedeately if set */ int isr_flag ; /* set, when HWM is entered from isr */ /* - * varaibles for the current transmit frame + * variables for the current transmit frame */ struct s_smt_tx_queue *tx_p ; /* pointer to the transmit queue */ u_long tx_descr ; /* tx descriptor for FORMAC+ */ diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c index 1205c2a22657..437683aab32c 100644 --- a/drivers/net/tg3.c +++ b/drivers/net/tg3.c @@ -11225,7 +11225,7 @@ static int __devinit tg3_phy_probe(struct tg3 *tp) return tg3_phy_init(tp); /* Reading the PHY ID register can conflict with ASF - * firwmare access to the PHY hardware. + * firmware access to the PHY hardware. */ err = 0; if ((tp->tg3_flags & TG3_FLAG_ENABLE_ASF) || diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c index 00945f7c1e9b..25c9ef6a1815 100644 --- a/drivers/net/wan/farsync.c +++ b/drivers/net/wan/farsync.c @@ -69,7 +69,7 @@ MODULE_LICENSE("GPL"); #endif /* - * Modules parameters and associated varaibles + * Modules parameters and associated variables */ static int fst_txq_low = FST_LOW_WATER_MARK; static int fst_txq_high = FST_HIGH_WATER_MARK; diff --git a/drivers/net/wireless/ipw2x00/ipw2100.c b/drivers/net/wireless/ipw2x00/ipw2100.c index 115b70487502..f4e963ba768b 100644 --- a/drivers/net/wireless/ipw2x00/ipw2100.c +++ b/drivers/net/wireless/ipw2x00/ipw2100.c @@ -2362,7 +2362,7 @@ static void ipw2100_corruption_detected(struct ipw2100_priv *priv, int i) i * sizeof(struct ipw2100_status)); #ifdef IPW2100_DEBUG_C3 - /* Halt the fimrware so we can get a good image */ + /* Halt the firmware so we can get a good image */ write_register(priv->net_dev, IPW_REG_RESET_REG, IPW_AUX_HOST_RESET_REG_STOP_MASTER); j = 5; diff --git a/drivers/net/wireless/ipw2x00/ipw2200.c b/drivers/net/wireless/ipw2x00/ipw2200.c index 4a92af1d7877..e17a4593e1f5 100644 --- a/drivers/net/wireless/ipw2x00/ipw2200.c +++ b/drivers/net/wireless/ipw2x00/ipw2200.c @@ -8844,7 +8844,7 @@ static int ipw_wx_set_mode(struct net_device *dev, #endif /* CONFIG_IPW2200_MONITOR */ /* Free the existing firmware and reset the fw_loaded - * flag so ipw_load() will bring in the new firmawre */ + * flag so ipw_load() will bring in the new firmware */ free_firmware(); priv->ieee->iw_mode = wrqu->mode; diff --git a/drivers/net/wireless/iwlwifi/iwl-agn.c b/drivers/net/wireless/iwlwifi/iwl-agn.c index 663dc83be501..3889158b359c 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn.c @@ -1337,7 +1337,7 @@ static int iwl_read_ucode(struct iwl_priv *priv) /* api_ver should match the api version forming part of the * firmware filename ... but we don't check for that and only rely - * on the API version read from firware header from here on forward */ + * on the API version read from firmware header from here on forward */ if (api_ver < api_min || api_ver > api_max) { IWL_ERR(priv, "Driver unable to support your firmware API. " diff --git a/drivers/net/wireless/iwlwifi/iwl3945-base.c b/drivers/net/wireless/iwlwifi/iwl3945-base.c index a71b08ca7c71..9d5f97dd7c73 100644 --- a/drivers/net/wireless/iwlwifi/iwl3945-base.c +++ b/drivers/net/wireless/iwlwifi/iwl3945-base.c @@ -2562,7 +2562,7 @@ static int iwl3945_read_ucode(struct iwl_priv *priv) /* api_ver should match the api version forming part of the * firmware filename ... but we don't check for that and only rely - * on the API version read from firware header from here on forward */ + * on the API version read from firmware header from here on forward */ if (api_ver < api_min || api_ver > api_max) { IWL_ERR(priv, "Driver unable to support your firmware API. " diff --git a/drivers/net/wireless/libertas/cmd.c b/drivers/net/wireless/libertas/cmd.c index 639dd02d3d31..8c3605cdc64c 100644 --- a/drivers/net/wireless/libertas/cmd.c +++ b/drivers/net/wireless/libertas/cmd.c @@ -1649,7 +1649,7 @@ static struct cmd_ctrl_node *lbs_get_cmd_ctrl_node(struct lbs_private *priv) /** * @brief This function executes next command in command - * pending queue. It will put fimware back to PS mode + * pending queue. It will put firmware back to PS mode * if applicable. * * @param priv A pointer to struct lbs_private structure diff --git a/drivers/oprofile/buffer_sync.c b/drivers/oprofile/buffer_sync.c index 2c9aa49e43cd..8574622e36a5 100644 --- a/drivers/oprofile/buffer_sync.c +++ b/drivers/oprofile/buffer_sync.c @@ -154,6 +154,10 @@ int sync_start(void) { int err; + if (!alloc_cpumask_var(&marked_cpus, GFP_KERNEL)) + return -ENOMEM; + cpumask_clear(marked_cpus); + start_cpu_work(); err = task_handoff_register(&task_free_nb); @@ -179,6 +183,7 @@ out2: task_handoff_unregister(&task_free_nb); out1: end_sync(); + free_cpumask_var(marked_cpus); goto out; } @@ -190,6 +195,7 @@ void sync_stop(void) profile_event_unregister(PROFILE_TASK_EXIT, &task_exit_nb); task_handoff_unregister(&task_free_nb); end_sync(); + free_cpumask_var(marked_cpus); } @@ -565,20 +571,6 @@ void sync_buffer(int cpu) mutex_unlock(&buffer_mutex); } -int __init buffer_sync_init(void) -{ - if (!alloc_cpumask_var(&marked_cpus, GFP_KERNEL)) - return -ENOMEM; - - cpumask_clear(marked_cpus); - return 0; -} - -void buffer_sync_cleanup(void) -{ - free_cpumask_var(marked_cpus); -} - /* The function can be used to add a buffer worth of data directly to * the kernel buffer. The buffer is assumed to be a circular buffer. * Take the entries from index start and end at index end, wrapping diff --git a/drivers/oprofile/buffer_sync.h b/drivers/oprofile/buffer_sync.h index 0ebf5db62679..3110732c1835 100644 --- a/drivers/oprofile/buffer_sync.h +++ b/drivers/oprofile/buffer_sync.h @@ -19,8 +19,4 @@ void sync_stop(void); /* sync the given CPU's buffer */ void sync_buffer(int cpu); -/* initialize/destroy the buffer system. */ -int buffer_sync_init(void); -void buffer_sync_cleanup(void); - #endif /* OPROFILE_BUFFER_SYNC_H */ diff --git a/drivers/oprofile/cpu_buffer.c b/drivers/oprofile/cpu_buffer.c index e76d715e4342..f0e99d4c066b 100644 --- a/drivers/oprofile/cpu_buffer.c +++ b/drivers/oprofile/cpu_buffer.c @@ -161,7 +161,7 @@ struct op_sample { entry->event = ring_buffer_lock_reserve (op_ring_buffer_write, sizeof(struct op_sample) + - size * sizeof(entry->sample->data[0]), &entry->irq_flags); + size * sizeof(entry->sample->data[0])); if (entry->event) entry->sample = ring_buffer_event_data(entry->event); else @@ -178,8 +178,7 @@ struct op_sample int op_cpu_buffer_write_commit(struct op_entry *entry) { - return ring_buffer_unlock_commit(op_ring_buffer_write, entry->event, - entry->irq_flags); + return ring_buffer_unlock_commit(op_ring_buffer_write, entry->event); } struct op_sample *op_cpu_buffer_read_entry(struct op_entry *entry, int cpu) diff --git a/drivers/oprofile/oprof.c b/drivers/oprofile/oprof.c index ced39f602292..3cffce90f82a 100644 --- a/drivers/oprofile/oprof.c +++ b/drivers/oprofile/oprof.c @@ -183,10 +183,6 @@ static int __init oprofile_init(void) { int err; - err = buffer_sync_init(); - if (err) - return err; - err = oprofile_arch_init(&oprofile_ops); if (err < 0 || timer) { @@ -195,10 +191,8 @@ static int __init oprofile_init(void) } err = oprofilefs_register(); - if (err) { + if (err) oprofile_arch_exit(); - buffer_sync_cleanup(); - } return err; } @@ -208,7 +202,6 @@ static void __exit oprofile_exit(void) { oprofilefs_unregister(); oprofile_arch_exit(); - buffer_sync_cleanup(); } diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index c0cbbb5a245e..d76c4c85367e 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -277,10 +277,9 @@ static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev, node = dev_to_node(&dev->dev); if (node >= 0) { int cpu; - node_to_cpumask_ptr(nodecpumask, node); get_online_cpus(); - cpu = cpumask_any_and(nodecpumask, cpu_online_mask); + cpu = cpumask_any_and(cpumask_of_node(node), cpu_online_mask); if (cpu < nr_cpu_ids) error = work_on_cpu(cpu, local_pci_probe, &ddi); else diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index fe7ac2cea7c9..445fb6f7ea3f 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -593,7 +593,7 @@ EXPORT_SYMBOL_GPL(__pci_complete_power_transition); * @dev: PCI device to handle. * @state: PCI power state (D0, D1, D2, D3hot) to put the device into. * - * Transition a device to a new power state, using the platform formware and/or + * Transition a device to a new power state, using the platform firmware and/or * the device's PCI PM registers. * * RETURN VALUE: diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 3dad27a385d3..d99f1cd435a2 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -5811,7 +5811,7 @@ static struct ibm_struct volume_driver_data = { * ThinkPads from this same time period (and earlier) probably lack the * tachometer as well. * - * Unfortunately a lot of ThinkPads with new-style ECs but whose firwmare + * Unfortunately a lot of ThinkPads with new-style ECs but whose firmware * was never fixed by IBM to report the EC firmware version string * probably support the tachometer (like the early X models), so * detecting it is quite hard. We need more data to know for sure. diff --git a/drivers/power/bq27x00_battery.c b/drivers/power/bq27x00_battery.c index 0c056fcc01ce..62bb98124e26 100644 --- a/drivers/power/bq27x00_battery.c +++ b/drivers/power/bq27x00_battery.c @@ -83,7 +83,7 @@ static int bq27x00_read(u8 reg, int *rt_value, int b_single, } /* - * Return the battery temperature in Celcius degrees + * Return the battery temperature in Celsius degrees * Or < 0 if something fails. */ static int bq27x00_battery_temperature(struct bq27x00_device_info *di) diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index e2f44e6c0bcb..20297c521e50 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -1380,7 +1380,7 @@ config SCSI_LPFC_DEBUG_FS bool "Emulex LightPulse Fibre Channel debugfs Support" depends on SCSI_LPFC && DEBUG_FS help - This makes debugging infomation from the lpfc driver + This makes debugging information from the lpfc driver available via the debugfs filesystem. config SCSI_SIM710 @@ -1388,7 +1388,7 @@ config SCSI_SIM710 depends on (EISA || MCA) && SCSI select SCSI_SPI_ATTRS ---help--- - This driver for NCR53c710 based SCSI host adapters. + This driver is for NCR53c710 based SCSI host adapters. It currently supports Compaq EISA cards and NCR MCA cards diff --git a/drivers/serial/Kconfig b/drivers/serial/Kconfig index 9be11b0963f2..aa9d3a4c2d50 100644 --- a/drivers/serial/Kconfig +++ b/drivers/serial/Kconfig @@ -1374,7 +1374,7 @@ config SERIAL_BFIN_SPORT depends on BLACKFIN && EXPERIMENTAL select SERIAL_CORE help - Enble support SPORT emulate UART on Blackfin series. + Enable SPORT emulate UART on Blackfin series. To compile this driver as a module, choose M here: the module will be called bfin_sport_uart. diff --git a/drivers/staging/Kconfig b/drivers/staging/Kconfig index 7ea9d918387f..0dcf9ca0b0ac 100644 --- a/drivers/staging/Kconfig +++ b/drivers/staging/Kconfig @@ -4,7 +4,7 @@ menuconfig STAGING ---help--- This option allows you to select a number of drivers that are not of the "normal" Linux kernel quality level. These drivers - are placed here in order to get a wider audience for use of + are placed here in order to get a wider audience to make use of them. Please note that these drivers are under heavy development, may or may not work, and may contain userspace interfaces that most likely will be changed in the near @@ -12,7 +12,7 @@ menuconfig STAGING Using any of these drivers will taint your kernel which might affect support options from both the community, and various - commercial support orginizations. + commercial support organizations. If you wish to work on these drivers, to help improve them, or to report problems you have with them, please see the diff --git a/drivers/staging/comedi/Kconfig b/drivers/staging/comedi/Kconfig index 6365a2023d52..2d819d278b0e 100644 --- a/drivers/staging/comedi/Kconfig +++ b/drivers/staging/comedi/Kconfig @@ -1,9 +1,9 @@ config COMEDI - tristate "Data Acquision support (comedi)" + tristate "Data acquisition support (comedi)" default N depends on m ---help--- - Enable support a wide range of data acquision devices + Enable support a wide range of data acquisition devices for Linux. config COMEDI_DEBUG diff --git a/drivers/staging/go7007/Kconfig b/drivers/staging/go7007/Kconfig index f2cf7f66ae05..ca6ade6c4b47 100644 --- a/drivers/staging/go7007/Kconfig +++ b/drivers/staging/go7007/Kconfig @@ -10,7 +10,7 @@ config VIDEO_GO7007 select CRC32 default N ---help--- - This is a video4linux driver for some wierd device... + This is a video4linux driver for some weird device... To compile this driver as a module, choose M here: the module will be called go7007 @@ -20,7 +20,7 @@ config VIDEO_GO7007_USB depends on VIDEO_GO7007 && USB default N ---help--- - This is a video4linux driver for some wierd device... + This is a video4linux driver for some weird device... To compile this driver as a module, choose M here: the module will be called go7007-usb diff --git a/drivers/staging/otus/hal/hpmain.c b/drivers/staging/otus/hal/hpmain.c index 72c9e89979c9..322585be2c88 100644 --- a/drivers/staging/otus/hal/hpmain.c +++ b/drivers/staging/otus/hal/hpmain.c @@ -152,7 +152,7 @@ u16_t zfHpInit(zdev_t* dev, u32_t frequency) else { #ifndef ZM_OTUS_LINUX_PHASE_2 - /* donwload the normal frimware */ + /* download the normal firmware */ if ((ret = zfFirmwareDownload(dev, (u32_t*)zcFwImage, (u32_t)zcFwImageSize, ZM_FIRMWARE_WLAN_ADDR)) != ZM_SUCCESS) { diff --git a/drivers/staging/panel/Kconfig b/drivers/staging/panel/Kconfig index c4b30f2a549b..3abe7c9d558d 100644 --- a/drivers/staging/panel/Kconfig +++ b/drivers/staging/panel/Kconfig @@ -110,7 +110,7 @@ config PANEL_LCD_BWIDTH ---help--- Most LCDs use a standard controller which supports hardware lines of 40 characters, although sometimes only 16, 20 or 24 of them are really wired - to the terminal. This results in some non-visible but adressable characters, + to the terminal. This results in some non-visible but addressable characters, and is the case for most parallel LCDs. Other LCDs, and some serial ones, however, use the same line width internally as what is visible. The KS0074 for example, uses 16 characters per line for 16 visible characters per line. diff --git a/drivers/usb/atm/ueagle-atm.c b/drivers/usb/atm/ueagle-atm.c index b6483dd98acc..9cf9ff69e3e3 100644 --- a/drivers/usb/atm/ueagle-atm.c +++ b/drivers/usb/atm/ueagle-atm.c @@ -626,7 +626,7 @@ static void uea_upload_pre_firmware(const struct firmware *fw_entry, void *conte goto err_fw_corrupted; /* - * Start to upload formware : send reset + * Start to upload firmware : send reset */ value = 1; ret = uea_send_modem_cmd(usb, F8051_USBCS, sizeof(value), &value); diff --git a/drivers/usb/gadget/Kconfig b/drivers/usb/gadget/Kconfig index 770b3eaa9184..080bb1e4b847 100644 --- a/drivers/usb/gadget/Kconfig +++ b/drivers/usb/gadget/Kconfig @@ -392,7 +392,7 @@ config USB_GADGET_FSL_QE controllers having QE or CPM2, given minor tweaks. Set CONFIG_USB_GADGET to "m" to build this driver as a - dynmically linked module called "fsl_qe_udc". + dynamically linked module called "fsl_qe_udc". config USB_FSL_QE tristate diff --git a/drivers/usb/serial/ChangeLog.history b/drivers/usb/serial/ChangeLog.history index c1b279939bbf..f13fd488ebec 100644 --- a/drivers/usb/serial/ChangeLog.history +++ b/drivers/usb/serial/ChangeLog.history @@ -715,7 +715,7 @@ io_edgeport.c Change Log comments: 0.2 (01/30/2000) greg kroah-hartman Milestone 1 release. - Device is found by USB subsystem, enumerated, fimware is downloaded + Device is found by USB subsystem, enumerated, firmware is downloaded and the descriptors are printed to the debug log, config is set, and green light starts to blink. Open port works, and data can be sent and received at the default settings of the UART. Loopback connector diff --git a/drivers/usb/serial/Kconfig b/drivers/usb/serial/Kconfig index a65f9196b0a0..c480ea4c19f2 100644 --- a/drivers/usb/serial/Kconfig +++ b/drivers/usb/serial/Kconfig @@ -518,8 +518,8 @@ config USB_SERIAL_SIERRAWIRELESS help Say M here if you want to use Sierra Wireless devices. - Many deviecs have a feature known as TRU-Install, for those devices - to work properly the USB Storage Sierra feature must be enabled. + Many devices have a feature known as TRU-Install. For those devices + to work properly, the USB Storage Sierra feature must be enabled. To compile this driver as a module, choose M here: the module will be called sierra. diff --git a/drivers/usb/wusbcore/security.c b/drivers/usb/wusbcore/security.c index 8118db7f1d8d..b2f149fedcc5 100644 --- a/drivers/usb/wusbcore/security.c +++ b/drivers/usb/wusbcore/security.c @@ -562,7 +562,7 @@ void wusbhc_gtk_rekey(struct wusbhc *wusbhc) struct wusb_dev *wusb_dev; wusb_dev = wusbhc->port[p].wusb_dev; - if (!wusb_dev || !wusb_dev->usb_dev | !wusb_dev->usb_dev->authenticated) + if (!wusb_dev || !wusb_dev->usb_dev || !wusb_dev->usb_dev->authenticated) continue; usb_fill_control_urb(wusb_dev->set_gtk_urb, wusb_dev->usb_dev, diff --git a/drivers/uwb/Kconfig b/drivers/uwb/Kconfig index ca783127af36..bac8e7a6f17b 100644 --- a/drivers/uwb/Kconfig +++ b/drivers/uwb/Kconfig @@ -48,10 +48,10 @@ config UWB_WHCI help This driver enables the radio controller for WHCI cards. - WHCI is an specification developed by Intel + WHCI is a specification developed by Intel (http://www.intel.com/technology/comms/wusb/whci.htm) much in the spirit of USB's EHCI, but for UWB and Wireless USB - radio/host controllers connected via memmory mapping (eg: + radio/host controllers connected via memory mapping (eg: PCI). Most of these cards come also with a Wireless USB host controller. diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index 526187c8a12d..8ac9cddac575 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -37,7 +37,7 @@ config XEN_COMPAT_XENFS The old xenstore userspace tools expect to find "xenbus" under /proc/xen, but "xenbus" is now found at the root of the xenfs filesystem. Selecting this causes the kernel to create - the compatibilty mount point /proc/xen if it is running on + the compatibility mount point /proc/xen if it is running on a xen platform. If in doubt, say yes. diff --git a/drivers/xen/cpu_hotplug.c b/drivers/xen/cpu_hotplug.c index 974f56d1ebe1..5f54c01c1568 100644 --- a/drivers/xen/cpu_hotplug.c +++ b/drivers/xen/cpu_hotplug.c @@ -10,7 +10,7 @@ static void enable_hotplug_cpu(int cpu) if (!cpu_present(cpu)) arch_register_cpu(cpu); - cpu_set(cpu, cpu_present_map); + set_cpu_present(cpu, true); } static void disable_hotplug_cpu(int cpu) @@ -18,7 +18,7 @@ static void disable_hotplug_cpu(int cpu) if (cpu_present(cpu)) arch_unregister_cpu(cpu); - cpu_clear(cpu, cpu_present_map); + set_cpu_present(cpu, false); } static void vcpu_hotplug(unsigned int cpu) @@ -1420,8 +1420,7 @@ static void bio_pair_end_2(struct bio *bi, int err) } /* - * split a bio - only worry about a bio with a single page - * in it's iovec + * split a bio - only worry about a bio with a single page in its iovec */ struct bio_pair *bio_split(struct bio *bi, int first_sectors) { diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c index c84ca1f5259a..51bfdfc8fcda 100644 --- a/fs/btrfs/async-thread.c +++ b/fs/btrfs/async-thread.c @@ -20,7 +20,6 @@ #include <linux/list.h> #include <linux/spinlock.h> #include <linux/freezer.h> -#include <linux/ftrace.h> #include "async-thread.h" #define WORK_QUEUED_BIT 0 @@ -195,6 +194,9 @@ again_locked: if (!list_empty(&worker->pending)) continue; + if (kthread_should_stop()) + break; + /* still no more work?, sleep for real */ spin_lock_irq(&worker->lock); set_current_state(TASK_INTERRUPTIBLE); @@ -208,7 +210,8 @@ again_locked: worker->working = 0; spin_unlock_irq(&worker->lock); - schedule(); + if (!kthread_should_stop()) + schedule(); } __set_current_state(TASK_RUNNING); } diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index dbb724124633..e5b2533b691a 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -1244,9 +1244,9 @@ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans, * readahead one full node of leaves, finding things that are close * to the block in 'slot', and triggering ra on them. */ -static noinline void reada_for_search(struct btrfs_root *root, - struct btrfs_path *path, - int level, int slot, u64 objectid) +static void reada_for_search(struct btrfs_root *root, + struct btrfs_path *path, + int level, int slot, u64 objectid) { struct extent_buffer *node; struct btrfs_disk_key disk_key; @@ -1447,6 +1447,117 @@ noinline void btrfs_unlock_up_safe(struct btrfs_path *path, int level) } /* + * helper function for btrfs_search_slot. The goal is to find a block + * in cache without setting the path to blocking. If we find the block + * we return zero and the path is unchanged. + * + * If we can't find the block, we set the path blocking and do some + * reada. -EAGAIN is returned and the search must be repeated. + */ +static int +read_block_for_search(struct btrfs_trans_handle *trans, + struct btrfs_root *root, struct btrfs_path *p, + struct extent_buffer **eb_ret, int level, int slot, + struct btrfs_key *key) +{ + u64 blocknr; + u64 gen; + u32 blocksize; + struct extent_buffer *b = *eb_ret; + struct extent_buffer *tmp; + + blocknr = btrfs_node_blockptr(b, slot); + gen = btrfs_node_ptr_generation(b, slot); + blocksize = btrfs_level_size(root, level - 1); + + tmp = btrfs_find_tree_block(root, blocknr, blocksize); + if (tmp && btrfs_buffer_uptodate(tmp, gen)) { + *eb_ret = tmp; + return 0; + } + + /* + * reduce lock contention at high levels + * of the btree by dropping locks before + * we read. + */ + btrfs_release_path(NULL, p); + if (tmp) + free_extent_buffer(tmp); + if (p->reada) + reada_for_search(root, p, level, slot, key->objectid); + + tmp = read_tree_block(root, blocknr, blocksize, gen); + if (tmp) + free_extent_buffer(tmp); + return -EAGAIN; +} + +/* + * helper function for btrfs_search_slot. This does all of the checks + * for node-level blocks and does any balancing required based on + * the ins_len. + * + * If no extra work was required, zero is returned. If we had to + * drop the path, -EAGAIN is returned and btrfs_search_slot must + * start over + */ +static int +setup_nodes_for_search(struct btrfs_trans_handle *trans, + struct btrfs_root *root, struct btrfs_path *p, + struct extent_buffer *b, int level, int ins_len) +{ + int ret; + if ((p->search_for_split || ins_len > 0) && btrfs_header_nritems(b) >= + BTRFS_NODEPTRS_PER_BLOCK(root) - 3) { + int sret; + + sret = reada_for_balance(root, p, level); + if (sret) + goto again; + + btrfs_set_path_blocking(p); + sret = split_node(trans, root, p, level); + btrfs_clear_path_blocking(p, NULL); + + BUG_ON(sret > 0); + if (sret) { + ret = sret; + goto done; + } + b = p->nodes[level]; + } else if (ins_len < 0 && btrfs_header_nritems(b) < + BTRFS_NODEPTRS_PER_BLOCK(root) / 4) { + int sret; + + sret = reada_for_balance(root, p, level); + if (sret) + goto again; + + btrfs_set_path_blocking(p); + sret = balance_level(trans, root, p, level); + btrfs_clear_path_blocking(p, NULL); + + if (sret) { + ret = sret; + goto done; + } + b = p->nodes[level]; + if (!b) { + btrfs_release_path(NULL, p); + goto again; + } + BUG_ON(btrfs_header_nritems(b) == 1); + } + return 0; + +again: + ret = -EAGAIN; +done: + return ret; +} + +/* * look for key in the tree. path is filled in with nodes along the way * if key is found, we return zero and you can find the item in the leaf * level of the path (level 0) @@ -1464,16 +1575,11 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root ins_len, int cow) { struct extent_buffer *b; - struct extent_buffer *tmp; int slot; int ret; int level; - int should_reada = p->reada; int lowest_unlock = 1; - int blocksize; u8 lowest_level = 0; - u64 blocknr; - u64 gen; lowest_level = p->lowest_level; WARN_ON(lowest_level && ins_len > 0); @@ -1502,7 +1608,11 @@ again: if (cow) { int wret; - /* is a cow on this block not required */ + /* + * if we don't really need to cow this block + * then we don't want to set the path blocking, + * so we test it here + */ if (btrfs_header_generation(b) == trans->transid && btrfs_header_owner(b) == root->root_key.objectid && !btrfs_header_flag(b, BTRFS_HEADER_FLAG_WRITTEN)) { @@ -1557,51 +1667,15 @@ cow_done: if (ret && slot > 0) slot -= 1; p->slots[level] = slot; - if ((p->search_for_split || ins_len > 0) && - btrfs_header_nritems(b) >= - BTRFS_NODEPTRS_PER_BLOCK(root) - 3) { - int sret; - - sret = reada_for_balance(root, p, level); - if (sret) - goto again; - - btrfs_set_path_blocking(p); - sret = split_node(trans, root, p, level); - btrfs_clear_path_blocking(p, NULL); - - BUG_ON(sret > 0); - if (sret) { - ret = sret; - goto done; - } - b = p->nodes[level]; - slot = p->slots[level]; - } else if (ins_len < 0 && - btrfs_header_nritems(b) < - BTRFS_NODEPTRS_PER_BLOCK(root) / 4) { - int sret; - - sret = reada_for_balance(root, p, level); - if (sret) - goto again; - - btrfs_set_path_blocking(p); - sret = balance_level(trans, root, p, level); - btrfs_clear_path_blocking(p, NULL); + ret = setup_nodes_for_search(trans, root, p, b, level, + ins_len); + if (ret == -EAGAIN) + goto again; + else if (ret) + goto done; + b = p->nodes[level]; + slot = p->slots[level]; - if (sret) { - ret = sret; - goto done; - } - b = p->nodes[level]; - if (!b) { - btrfs_release_path(NULL, p); - goto again; - } - slot = p->slots[level]; - BUG_ON(btrfs_header_nritems(b) == 1); - } unlock_up(p, level, lowest_unlock); /* this is only true while dropping a snapshot */ @@ -1610,44 +1684,11 @@ cow_done: goto done; } - blocknr = btrfs_node_blockptr(b, slot); - gen = btrfs_node_ptr_generation(b, slot); - blocksize = btrfs_level_size(root, level - 1); + ret = read_block_for_search(trans, root, p, + &b, level, slot, key); + if (ret == -EAGAIN) + goto again; - tmp = btrfs_find_tree_block(root, blocknr, blocksize); - if (tmp && btrfs_buffer_uptodate(tmp, gen)) { - b = tmp; - } else { - /* - * reduce lock contention at high levels - * of the btree by dropping locks before - * we read. - */ - if (level > 0) { - btrfs_release_path(NULL, p); - if (tmp) - free_extent_buffer(tmp); - if (should_reada) - reada_for_search(root, p, - level, slot, - key->objectid); - - tmp = read_tree_block(root, blocknr, - blocksize, gen); - if (tmp) - free_extent_buffer(tmp); - goto again; - } else { - btrfs_set_path_blocking(p); - if (tmp) - free_extent_buffer(tmp); - if (should_reada) - reada_for_search(root, p, - level, slot, - key->objectid); - b = read_node_slot(root, b, slot); - } - } if (!p->skip_locking) { int lret; @@ -2116,8 +2157,7 @@ static int insert_ptr(struct btrfs_trans_handle *trans, struct btrfs_root BUG_ON(!path->nodes[level]); lower = path->nodes[level]; nritems = btrfs_header_nritems(lower); - if (slot > nritems) - BUG(); + BUG_ON(slot > nritems); if (nritems == BTRFS_NODEPTRS_PER_BLOCK(root)) BUG(); if (slot != nritems) { @@ -4086,28 +4126,44 @@ next: int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path) { int slot; - int level = 1; + int level; struct extent_buffer *c; - struct extent_buffer *next = NULL; + struct extent_buffer *next; struct btrfs_key key; u32 nritems; int ret; + int old_spinning = path->leave_spinning; + int force_blocking = 0; nritems = btrfs_header_nritems(path->nodes[0]); if (nritems == 0) return 1; - btrfs_item_key_to_cpu(path->nodes[0], &key, nritems - 1); + /* + * we take the blocks in an order that upsets lockdep. Using + * blocking mode is the only way around it. + */ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + force_blocking = 1; +#endif + btrfs_item_key_to_cpu(path->nodes[0], &key, nritems - 1); +again: + level = 1; + next = NULL; btrfs_release_path(root, path); + path->keep_locks = 1; + + if (!force_blocking) + path->leave_spinning = 1; + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); path->keep_locks = 0; if (ret < 0) return ret; - btrfs_set_path_blocking(path); nritems = btrfs_header_nritems(path->nodes[0]); /* * by releasing the path above we dropped all our locks. A balance @@ -4117,19 +4173,24 @@ int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path) */ if (nritems > 0 && path->slots[0] < nritems - 1) { path->slots[0]++; + ret = 0; goto done; } while (level < BTRFS_MAX_LEVEL) { - if (!path->nodes[level]) - return 1; + if (!path->nodes[level]) { + ret = 1; + goto done; + } slot = path->slots[level] + 1; c = path->nodes[level]; if (slot >= btrfs_header_nritems(c)) { level++; - if (level == BTRFS_MAX_LEVEL) - return 1; + if (level == BTRFS_MAX_LEVEL) { + ret = 1; + goto done; + } continue; } @@ -4138,16 +4199,22 @@ int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path) free_extent_buffer(next); } - /* the path was set to blocking above */ - if (level == 1 && (path->locks[1] || path->skip_locking) && - path->reada) - reada_for_search(root, path, level, slot, 0); + next = c; + ret = read_block_for_search(NULL, root, path, &next, level, + slot, &key); + if (ret == -EAGAIN) + goto again; - next = read_node_slot(root, c, slot); if (!path->skip_locking) { - btrfs_assert_tree_locked(c); - btrfs_tree_lock(next); - btrfs_set_lock_blocking(next); + ret = btrfs_try_spin_lock(next); + if (!ret) { + btrfs_set_path_blocking(path); + btrfs_tree_lock(next); + if (!force_blocking) + btrfs_clear_path_blocking(path, next); + } + if (force_blocking) + btrfs_set_lock_blocking(next); } break; } @@ -4157,27 +4224,42 @@ int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path) c = path->nodes[level]; if (path->locks[level]) btrfs_tree_unlock(c); + free_extent_buffer(c); path->nodes[level] = next; path->slots[level] = 0; if (!path->skip_locking) path->locks[level] = 1; + if (!level) break; - btrfs_set_path_blocking(path); - if (level == 1 && path->locks[1] && path->reada) - reada_for_search(root, path, level, slot, 0); - next = read_node_slot(root, next, 0); + ret = read_block_for_search(NULL, root, path, &next, level, + 0, &key); + if (ret == -EAGAIN) + goto again; + if (!path->skip_locking) { btrfs_assert_tree_locked(path->nodes[level]); - btrfs_tree_lock(next); - btrfs_set_lock_blocking(next); + ret = btrfs_try_spin_lock(next); + if (!ret) { + btrfs_set_path_blocking(path); + btrfs_tree_lock(next); + if (!force_blocking) + btrfs_clear_path_blocking(path, next); + } + if (force_blocking) + btrfs_set_lock_blocking(next); } } + ret = 0; done: unlock_up(path, 0, 1); - return 0; + path->leave_spinning = old_spinning; + if (!old_spinning) + btrfs_set_path_blocking(path); + + return ret; } /* diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 9417713542a2..ad96495dedc5 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -143,12 +143,15 @@ static int btrfs_csum_sizes[] = { 4, 0 }; #define BTRFS_FT_MAX 9 /* - * the key defines the order in the tree, and so it also defines (optimal) - * block layout. objectid corresonds to the inode number. The flags - * tells us things about the object, and is a kind of stream selector. - * so for a given inode, keys with flags of 1 might refer to the inode - * data, flags of 2 may point to file data in the btree and flags == 3 - * may point to extents. + * The key defines the order in the tree, and so it also defines (optimal) + * block layout. + * + * objectid corresponds to the inode number. + * + * type tells us things about the object, and is a kind of stream selector. + * so for a given inode, keys with type of 1 might refer to the inode data, + * type of 2 may point to file data in the btree and type == 3 may point to + * extents. * * offset is the starting byte offset for this key in the stream. * @@ -200,7 +203,7 @@ struct btrfs_dev_item { /* * starting byte of this partition on the device, - * to allowr for stripe alignment in the future + * to allow for stripe alignment in the future */ __le64 start_offset; @@ -633,18 +636,35 @@ struct btrfs_space_info { struct rw_semaphore groups_sem; }; -struct btrfs_free_space { - struct rb_node bytes_index; - struct rb_node offset_index; - u64 offset; - u64 bytes; +/* + * free clusters are used to claim free space in relatively large chunks, + * allowing us to do less seeky writes. They are used for all metadata + * allocations and data allocations in ssd mode. + */ +struct btrfs_free_cluster { + spinlock_t lock; + spinlock_t refill_lock; + struct rb_root root; + + /* largest extent in this cluster */ + u64 max_size; + + /* first extent starting offset */ + u64 window_start; + + struct btrfs_block_group_cache *block_group; + /* + * when a cluster is allocated from a block group, we put the + * cluster onto a list in the block group so that it can + * be freed before the block group is freed. + */ + struct list_head block_group_list; }; struct btrfs_block_group_cache { struct btrfs_key key; struct btrfs_block_group_item item; spinlock_t lock; - struct mutex alloc_mutex; struct mutex cache_mutex; u64 pinned; u64 reserved; @@ -656,6 +676,7 @@ struct btrfs_block_group_cache { struct btrfs_space_info *space_info; /* free space cache stuff */ + spinlock_t tree_lock; struct rb_root free_space_bytes; struct rb_root free_space_offset; @@ -667,6 +688,11 @@ struct btrfs_block_group_cache { /* usage count */ atomic_t count; + + /* List of struct btrfs_free_clusters for this block group. + * Today it will only have one thing on it, but that may change + */ + struct list_head cluster_list; }; struct btrfs_leaf_ref_tree { @@ -728,7 +754,6 @@ struct btrfs_fs_info { struct mutex tree_log_mutex; struct mutex transaction_kthread_mutex; struct mutex cleaner_mutex; - struct mutex pinned_mutex; struct mutex chunk_mutex; struct mutex drop_mutex; struct mutex volume_mutex; @@ -839,8 +864,12 @@ struct btrfs_fs_info { spinlock_t delalloc_lock; spinlock_t new_trans_lock; u64 delalloc_bytes; - u64 last_alloc; - u64 last_data_alloc; + + /* data_alloc_cluster is only used in ssd mode */ + struct btrfs_free_cluster data_alloc_cluster; + + /* all metadata allocations go through this cluster */ + struct btrfs_free_cluster meta_alloc_cluster; spinlock_t ref_cache_lock; u64 total_ref_cache_size; @@ -932,7 +961,6 @@ struct btrfs_root { }; /* - * inode items have the data typically returned from stat and store other * info about object characteristics. There is one for every file and dir in * the FS @@ -963,7 +991,7 @@ struct btrfs_root { #define BTRFS_EXTENT_CSUM_KEY 128 /* - * root items point to tree roots. There are typically in the root + * root items point to tree roots. They are typically in the root * tree used by the super block to find all the other trees */ #define BTRFS_ROOT_ITEM_KEY 132 @@ -1010,6 +1038,8 @@ struct btrfs_root { #define BTRFS_MOUNT_SSD (1 << 3) #define BTRFS_MOUNT_DEGRADED (1 << 4) #define BTRFS_MOUNT_COMPRESS (1 << 5) +#define BTRFS_MOUNT_NOTREELOG (1 << 6) +#define BTRFS_MOUNT_FLUSHONCOMMIT (1 << 7) #define btrfs_clear_opt(o, opt) ((o) &= ~BTRFS_MOUNT_##opt) #define btrfs_set_opt(o, opt) ((o) |= BTRFS_MOUNT_##opt) @@ -1748,6 +1778,7 @@ static inline struct dentry *fdentry(struct file *file) } /* extent-tree.c */ +void btrfs_put_block_group(struct btrfs_block_group_cache *cache); int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, struct btrfs_root *root, unsigned long count); int btrfs_lookup_extent(struct btrfs_root *root, u64 start, u64 len); @@ -2174,21 +2205,4 @@ int btrfs_check_acl(struct inode *inode, int mask); int btrfs_init_acl(struct inode *inode, struct inode *dir); int btrfs_acl_chmod(struct inode *inode); -/* free-space-cache.c */ -int btrfs_add_free_space(struct btrfs_block_group_cache *block_group, - u64 bytenr, u64 size); -int btrfs_add_free_space_lock(struct btrfs_block_group_cache *block_group, - u64 offset, u64 bytes); -int btrfs_remove_free_space(struct btrfs_block_group_cache *block_group, - u64 bytenr, u64 size); -int btrfs_remove_free_space_lock(struct btrfs_block_group_cache *block_group, - u64 offset, u64 bytes); -void btrfs_remove_free_space_cache(struct btrfs_block_group_cache - *block_group); -struct btrfs_free_space *btrfs_find_free_space(struct btrfs_block_group_cache - *block_group, u64 offset, - u64 bytes); -void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group, - u64 bytes); -u64 btrfs_block_group_free_space(struct btrfs_block_group_cache *block_group); #endif diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index cbf7dc8ae3ec..d6c01c096a40 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -18,7 +18,6 @@ #include <linux/sched.h> #include <linux/sort.h> -#include <linux/ftrace.h> #include "ctree.h" #include "delayed-ref.h" #include "transaction.h" diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 92d73929d381..92caa8035f36 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -38,6 +38,7 @@ #include "locking.h" #include "ref-cache.h" #include "tree-log.h" +#include "free-space-cache.h" static struct extent_io_ops btree_extent_io_ops; static void end_workqueue_fn(struct btrfs_work *work); @@ -1412,8 +1413,6 @@ static int bio_ready_for_csum(struct bio *bio) ret = extent_range_uptodate(io_tree, start + length, start + buf_len - 1); - if (ret == 1) - return ret; return ret; } @@ -1647,12 +1646,15 @@ struct btrfs_root *open_ctree(struct super_block *sb, mutex_init(&fs_info->ordered_operations_mutex); mutex_init(&fs_info->tree_log_mutex); mutex_init(&fs_info->drop_mutex); - mutex_init(&fs_info->pinned_mutex); mutex_init(&fs_info->chunk_mutex); mutex_init(&fs_info->transaction_kthread_mutex); mutex_init(&fs_info->cleaner_mutex); mutex_init(&fs_info->volume_mutex); mutex_init(&fs_info->tree_reloc_mutex); + + btrfs_init_free_cluster(&fs_info->meta_alloc_cluster); + btrfs_init_free_cluster(&fs_info->data_alloc_cluster); + init_waitqueue_head(&fs_info->transaction_throttle); init_waitqueue_head(&fs_info->transaction_wait); init_waitqueue_head(&fs_info->async_submit_wait); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index f5e7cae63d80..178df4c67de4 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -31,6 +31,7 @@ #include "volumes.h" #include "locking.h" #include "ref-cache.h" +#include "free-space-cache.h" #define PENDING_EXTENT_INSERT 0 #define PENDING_EXTENT_DELETE 1 @@ -166,7 +167,6 @@ static int add_new_free_space(struct btrfs_block_group_cache *block_group, u64 extent_start, extent_end, size; int ret; - mutex_lock(&info->pinned_mutex); while (start < end) { ret = find_first_extent_bit(&info->pinned_extents, start, &extent_start, &extent_end, @@ -192,7 +192,6 @@ static int add_new_free_space(struct btrfs_block_group_cache *block_group, ret = btrfs_add_free_space(block_group, start, size); BUG_ON(ret); } - mutex_unlock(&info->pinned_mutex); return 0; } @@ -291,8 +290,8 @@ next: block_group->key.objectid + block_group->key.offset); - remove_sb_from_cache(root, block_group); block_group->cached = 1; + remove_sb_from_cache(root, block_group); ret = 0; err: btrfs_free_path(path); @@ -326,7 +325,7 @@ struct btrfs_block_group_cache *btrfs_lookup_block_group( return cache; } -static inline void put_block_group(struct btrfs_block_group_cache *cache) +void btrfs_put_block_group(struct btrfs_block_group_cache *cache) { if (atomic_dec_and_test(&cache->count)) kfree(cache); @@ -399,12 +398,12 @@ again: div_factor(cache->key.offset, factor)) { group_start = cache->key.objectid; spin_unlock(&cache->lock); - put_block_group(cache); + btrfs_put_block_group(cache); goto found; } } spin_unlock(&cache->lock); - put_block_group(cache); + btrfs_put_block_group(cache); cond_resched(); } if (!wrapped) { @@ -1594,7 +1593,7 @@ int btrfs_extent_readonly(struct btrfs_root *root, u64 bytenr) if (!block_group || block_group->ro) readonly = 1; if (block_group) - put_block_group(block_group); + btrfs_put_block_group(block_group); return readonly; } @@ -2018,7 +2017,7 @@ static int update_block_group(struct btrfs_trans_handle *trans, WARN_ON(ret); } } - put_block_group(cache); + btrfs_put_block_group(cache); total -= num_bytes; bytenr += num_bytes; } @@ -2035,7 +2034,7 @@ static u64 first_logical_byte(struct btrfs_root *root, u64 search_start) return 0; bytenr = cache->key.objectid; - put_block_group(cache); + btrfs_put_block_group(cache); return bytenr; } @@ -2047,7 +2046,6 @@ int btrfs_update_pinned_extents(struct btrfs_root *root, struct btrfs_block_group_cache *cache; struct btrfs_fs_info *fs_info = root->fs_info; - WARN_ON(!mutex_is_locked(&root->fs_info->pinned_mutex)); if (pin) { set_extent_dirty(&fs_info->pinned_extents, bytenr, bytenr + num - 1, GFP_NOFS); @@ -2055,7 +2053,6 @@ int btrfs_update_pinned_extents(struct btrfs_root *root, clear_extent_dirty(&fs_info->pinned_extents, bytenr, bytenr + num - 1, GFP_NOFS); } - mutex_unlock(&root->fs_info->pinned_mutex); while (num > 0) { cache = btrfs_lookup_block_group(fs_info, bytenr); @@ -2081,7 +2078,7 @@ int btrfs_update_pinned_extents(struct btrfs_root *root, if (cache->cached) btrfs_add_free_space(cache, bytenr, len); } - put_block_group(cache); + btrfs_put_block_group(cache); bytenr += len; num -= len; } @@ -2112,7 +2109,7 @@ static int update_reserved_extents(struct btrfs_root *root, } spin_unlock(&cache->lock); spin_unlock(&cache->space_info->lock); - put_block_group(cache); + btrfs_put_block_group(cache); bytenr += len; num -= len; } @@ -2127,7 +2124,6 @@ int btrfs_copy_pinned(struct btrfs_root *root, struct extent_io_tree *copy) struct extent_io_tree *pinned_extents = &root->fs_info->pinned_extents; int ret; - mutex_lock(&root->fs_info->pinned_mutex); while (1) { ret = find_first_extent_bit(pinned_extents, last, &start, &end, EXTENT_DIRTY); @@ -2136,7 +2132,6 @@ int btrfs_copy_pinned(struct btrfs_root *root, struct extent_io_tree *copy) set_extent_dirty(copy, start, end, GFP_NOFS); last = end + 1; } - mutex_unlock(&root->fs_info->pinned_mutex); return 0; } @@ -2149,7 +2144,6 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans, int ret; while (1) { - mutex_lock(&root->fs_info->pinned_mutex); ret = find_first_extent_bit(unpin, 0, &start, &end, EXTENT_DIRTY); if (ret) @@ -2163,7 +2157,6 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans, cond_resched(); } - mutex_unlock(&root->fs_info->pinned_mutex); return ret; } @@ -2205,7 +2198,6 @@ static int pin_down_bytes(struct btrfs_trans_handle *trans, free_extent_buffer(buf); pinit: btrfs_set_path_blocking(path); - mutex_lock(&root->fs_info->pinned_mutex); /* unlocks the pinned mutex */ btrfs_update_pinned_extents(root, bytenr, num_bytes, 1); @@ -2511,8 +2503,6 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans, */ if (root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID && owner_objectid < BTRFS_FIRST_FREE_OBJECTID) { - mutex_lock(&root->fs_info->pinned_mutex); - /* unlocks the pinned mutex */ btrfs_update_pinned_extents(root, bytenr, num_bytes, 1); update_reserved_extents(root, bytenr, num_bytes, 0); @@ -2554,228 +2544,237 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans, { int ret = 0; struct btrfs_root *root = orig_root->fs_info->extent_root; - u64 total_needed = num_bytes; - u64 *last_ptr = NULL; - u64 last_wanted = 0; + struct btrfs_free_cluster *last_ptr = NULL; struct btrfs_block_group_cache *block_group = NULL; - int chunk_alloc_done = 0; int empty_cluster = 2 * 1024 * 1024; int allowed_chunk_alloc = 0; - struct list_head *head = NULL, *cur = NULL; - int loop = 0; - int extra_loop = 0; struct btrfs_space_info *space_info; + int last_ptr_loop = 0; + int loop = 0; WARN_ON(num_bytes < root->sectorsize); btrfs_set_key_type(ins, BTRFS_EXTENT_ITEM_KEY); ins->objectid = 0; ins->offset = 0; + space_info = __find_space_info(root->fs_info, data); + if (orig_root->ref_cows || empty_size) allowed_chunk_alloc = 1; if (data & BTRFS_BLOCK_GROUP_METADATA) { - last_ptr = &root->fs_info->last_alloc; + last_ptr = &root->fs_info->meta_alloc_cluster; if (!btrfs_test_opt(root, SSD)) empty_cluster = 64 * 1024; } - if ((data & BTRFS_BLOCK_GROUP_DATA) && btrfs_test_opt(root, SSD)) - last_ptr = &root->fs_info->last_data_alloc; + if ((data & BTRFS_BLOCK_GROUP_DATA) && btrfs_test_opt(root, SSD)) { + last_ptr = &root->fs_info->data_alloc_cluster; + } if (last_ptr) { - if (*last_ptr) { - hint_byte = *last_ptr; - last_wanted = *last_ptr; - } else - empty_size += empty_cluster; - } else { - empty_cluster = 0; + spin_lock(&last_ptr->lock); + if (last_ptr->block_group) + hint_byte = last_ptr->window_start; + spin_unlock(&last_ptr->lock); } + search_start = max(search_start, first_logical_byte(root, 0)); search_start = max(search_start, hint_byte); - if (last_wanted && search_start != last_wanted) { - last_wanted = 0; - empty_size += empty_cluster; + if (!last_ptr) { + empty_cluster = 0; + loop = 1; } - total_needed += empty_size; - block_group = btrfs_lookup_block_group(root->fs_info, search_start); - if (!block_group) - block_group = btrfs_lookup_first_block_group(root->fs_info, - search_start); - space_info = __find_space_info(root->fs_info, data); + if (search_start == hint_byte) { + block_group = btrfs_lookup_block_group(root->fs_info, + search_start); + if (block_group && block_group_bits(block_group, data)) { + down_read(&space_info->groups_sem); + goto have_block_group; + } else if (block_group) { + btrfs_put_block_group(block_group); + } + } +search: down_read(&space_info->groups_sem); - while (1) { - struct btrfs_free_space *free_space; - /* - * the only way this happens if our hint points to a block - * group thats not of the proper type, while looping this - * should never happen - */ - if (empty_size) - extra_loop = 1; + list_for_each_entry(block_group, &space_info->block_groups, list) { + u64 offset; - if (!block_group) - goto new_group_no_lock; + atomic_inc(&block_group->count); + search_start = block_group->key.objectid; +have_block_group: if (unlikely(!block_group->cached)) { mutex_lock(&block_group->cache_mutex); ret = cache_block_group(root, block_group); mutex_unlock(&block_group->cache_mutex); - if (ret) + if (ret) { + btrfs_put_block_group(block_group); break; + } } - mutex_lock(&block_group->alloc_mutex); - if (unlikely(!block_group_bits(block_group, data))) - goto new_group; - if (unlikely(block_group->ro)) - goto new_group; + goto loop; - free_space = btrfs_find_free_space(block_group, search_start, - total_needed); - if (free_space) { - u64 start = block_group->key.objectid; - u64 end = block_group->key.objectid + - block_group->key.offset; + if (last_ptr) { + /* + * the refill lock keeps out other + * people trying to start a new cluster + */ + spin_lock(&last_ptr->refill_lock); + offset = btrfs_alloc_from_cluster(block_group, last_ptr, + num_bytes, search_start); + if (offset) { + /* we have a block, we're done */ + spin_unlock(&last_ptr->refill_lock); + goto checks; + } - search_start = stripe_align(root, free_space->offset); + spin_lock(&last_ptr->lock); + /* + * whoops, this cluster doesn't actually point to + * this block group. Get a ref on the block + * group is does point to and try again + */ + if (!last_ptr_loop && last_ptr->block_group && + last_ptr->block_group != block_group) { + + btrfs_put_block_group(block_group); + block_group = last_ptr->block_group; + atomic_inc(&block_group->count); + spin_unlock(&last_ptr->lock); + spin_unlock(&last_ptr->refill_lock); + + last_ptr_loop = 1; + search_start = block_group->key.objectid; + goto have_block_group; + } + spin_unlock(&last_ptr->lock); - /* move on to the next group */ - if (search_start + num_bytes >= search_end) - goto new_group; + /* + * this cluster didn't work out, free it and + * start over + */ + btrfs_return_cluster_to_free_space(NULL, last_ptr); - /* move on to the next group */ - if (search_start + num_bytes > end) - goto new_group; + last_ptr_loop = 0; - if (last_wanted && search_start != last_wanted) { - total_needed += empty_cluster; - empty_size += empty_cluster; - last_wanted = 0; + /* allocate a cluster in this block group */ + ret = btrfs_find_space_cluster(trans, + block_group, last_ptr, + offset, num_bytes, + empty_cluster + empty_size); + if (ret == 0) { /* - * if search_start is still in this block group - * then we just re-search this block group + * now pull our allocation out of this + * cluster */ - if (search_start >= start && - search_start < end) { - mutex_unlock(&block_group->alloc_mutex); - continue; + offset = btrfs_alloc_from_cluster(block_group, + last_ptr, num_bytes, + search_start); + if (offset) { + /* we found one, proceed */ + spin_unlock(&last_ptr->refill_lock); + goto checks; } - - /* else we go to the next block group */ - goto new_group; } - - if (exclude_nr > 0 && - (search_start + num_bytes > exclude_start && - search_start < exclude_start + exclude_nr)) { - search_start = exclude_start + exclude_nr; - /* - * if search_start is still in this block group - * then we just re-search this block group - */ - if (search_start >= start && - search_start < end) { - mutex_unlock(&block_group->alloc_mutex); - last_wanted = 0; - continue; - } - - /* else we go to the next block group */ - goto new_group; + /* + * at this point we either didn't find a cluster + * or we weren't able to allocate a block from our + * cluster. Free the cluster we've been trying + * to use, and go to the next block group + */ + if (loop < 2) { + btrfs_return_cluster_to_free_space(NULL, + last_ptr); + spin_unlock(&last_ptr->refill_lock); + goto loop; } + spin_unlock(&last_ptr->refill_lock); + } - ins->objectid = search_start; - ins->offset = num_bytes; + offset = btrfs_find_space_for_alloc(block_group, search_start, + num_bytes, empty_size); + if (!offset) + goto loop; +checks: + search_start = stripe_align(root, offset); + + /* move on to the next group */ + if (search_start + num_bytes >= search_end) { + btrfs_add_free_space(block_group, offset, num_bytes); + goto loop; + } - btrfs_remove_free_space_lock(block_group, search_start, - num_bytes); - /* we are all good, lets return */ - mutex_unlock(&block_group->alloc_mutex); - break; + /* move on to the next group */ + if (search_start + num_bytes > + block_group->key.objectid + block_group->key.offset) { + btrfs_add_free_space(block_group, offset, num_bytes); + goto loop; } -new_group: - mutex_unlock(&block_group->alloc_mutex); - put_block_group(block_group); - block_group = NULL; -new_group_no_lock: - /* don't try to compare new allocations against the - * last allocation any more - */ - last_wanted = 0; - /* - * Here's how this works. - * loop == 0: we were searching a block group via a hint - * and didn't find anything, so we start at - * the head of the block groups and keep searching - * loop == 1: we're searching through all of the block groups - * if we hit the head again we have searched - * all of the block groups for this space and we - * need to try and allocate, if we cant error out. - * loop == 2: we allocated more space and are looping through - * all of the block groups again. - */ - if (loop == 0) { - head = &space_info->block_groups; - cur = head->next; - loop++; - } else if (loop == 1 && cur == head) { - int keep_going; - - /* at this point we give up on the empty_size - * allocations and just try to allocate the min - * space. - * - * The extra_loop field was set if an empty_size - * allocation was attempted above, and if this - * is try we need to try the loop again without - * the additional empty_size. + if (exclude_nr > 0 && + (search_start + num_bytes > exclude_start && + search_start < exclude_start + exclude_nr)) { + search_start = exclude_start + exclude_nr; + + btrfs_add_free_space(block_group, offset, num_bytes); + /* + * if search_start is still in this block group + * then we just re-search this block group */ - total_needed -= empty_size; - empty_size = 0; - keep_going = extra_loop; - loop++; + if (search_start >= block_group->key.objectid && + search_start < (block_group->key.objectid + + block_group->key.offset)) + goto have_block_group; + goto loop; + } - if (allowed_chunk_alloc && !chunk_alloc_done) { - up_read(&space_info->groups_sem); - ret = do_chunk_alloc(trans, root, num_bytes + - 2 * 1024 * 1024, data, 1); - down_read(&space_info->groups_sem); - if (ret < 0) - goto loop_check; - head = &space_info->block_groups; - /* - * we've allocated a new chunk, keep - * trying - */ - keep_going = 1; - chunk_alloc_done = 1; - } else if (!allowed_chunk_alloc) { - space_info->force_alloc = 1; - } -loop_check: - if (keep_going) { - cur = head->next; - extra_loop = 0; - } else { - break; - } - } else if (cur == head) { - break; + ins->objectid = search_start; + ins->offset = num_bytes; + + if (offset < search_start) + btrfs_add_free_space(block_group, offset, + search_start - offset); + BUG_ON(offset > search_start); + + /* we are all good, lets return */ + break; +loop: + btrfs_put_block_group(block_group); + } + up_read(&space_info->groups_sem); + + /* loop == 0, try to find a clustered alloc in every block group + * loop == 1, try again after forcing a chunk allocation + * loop == 2, set empty_size and empty_cluster to 0 and try again + */ + if (!ins->objectid && loop < 3 && + (empty_size || empty_cluster || allowed_chunk_alloc)) { + if (loop >= 2) { + empty_size = 0; + empty_cluster = 0; } - block_group = list_entry(cur, struct btrfs_block_group_cache, - list); - atomic_inc(&block_group->count); + if (allowed_chunk_alloc) { + ret = do_chunk_alloc(trans, root, num_bytes + + 2 * 1024 * 1024, data, 1); + allowed_chunk_alloc = 0; + } else { + space_info->force_alloc = 1; + } - search_start = block_group->key.objectid; - cur = cur->next; + if (loop < 3) { + loop++; + goto search; + } + ret = -ENOSPC; + } else if (!ins->objectid) { + ret = -ENOSPC; } /* we found what we needed */ @@ -2783,21 +2782,10 @@ loop_check: if (!(data & BTRFS_BLOCK_GROUP_DATA)) trans->block_group = block_group->key.objectid; - if (last_ptr) - *last_ptr = ins->objectid + ins->offset; + btrfs_put_block_group(block_group); ret = 0; - } else if (!ret) { - printk(KERN_ERR "btrfs searching for %llu bytes, " - "num_bytes %llu, loop %d, allowed_alloc %d\n", - (unsigned long long)total_needed, - (unsigned long long)num_bytes, - loop, allowed_chunk_alloc); - ret = -ENOSPC; } - if (block_group) - put_block_group(block_group); - up_read(&space_info->groups_sem); return ret; } @@ -2902,7 +2890,7 @@ int btrfs_free_reserved_extent(struct btrfs_root *root, u64 start, u64 len) ret = btrfs_discard_extent(root, start, len); btrfs_add_free_space(cache, start, len); - put_block_group(cache); + btrfs_put_block_group(cache); update_reserved_extents(root, start, len, 0); return ret; @@ -3040,7 +3028,7 @@ int btrfs_alloc_logged_extent(struct btrfs_trans_handle *trans, ret = btrfs_remove_free_space(block_group, ins->objectid, ins->offset); BUG_ON(ret); - put_block_group(block_group); + btrfs_put_block_group(block_group); ret = __btrfs_alloc_reserved_extent(trans, root, parent, root_objectid, ref_generation, owner, ins, 1); return ret; @@ -5729,7 +5717,7 @@ next: WARN_ON(block_group->reserved > 0); WARN_ON(btrfs_block_group_used(&block_group->item) > 0); spin_unlock(&block_group->lock); - put_block_group(block_group); + btrfs_put_block_group(block_group); ret = 0; out: btrfs_free_path(path); @@ -5856,9 +5844,10 @@ int btrfs_read_block_groups(struct btrfs_root *root) atomic_set(&cache->count, 1); spin_lock_init(&cache->lock); - mutex_init(&cache->alloc_mutex); + spin_lock_init(&cache->tree_lock); mutex_init(&cache->cache_mutex); INIT_LIST_HEAD(&cache->list); + INIT_LIST_HEAD(&cache->cluster_list); read_extent_buffer(leaf, &cache->item, btrfs_item_ptr_offset(leaf, path->slots[0]), sizeof(cache->item)); @@ -5912,9 +5901,10 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, cache->key.type = BTRFS_BLOCK_GROUP_ITEM_KEY; atomic_set(&cache->count, 1); spin_lock_init(&cache->lock); - mutex_init(&cache->alloc_mutex); + spin_lock_init(&cache->tree_lock); mutex_init(&cache->cache_mutex); INIT_LIST_HEAD(&cache->list); + INIT_LIST_HEAD(&cache->cluster_list); btrfs_set_block_group_used(&cache->item, bytes_used); btrfs_set_block_group_chunk_objectid(&cache->item, chunk_objectid); @@ -5974,8 +5964,8 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, spin_unlock(&block_group->space_info->lock); block_group->space_info->full = 0; - put_block_group(block_group); - put_block_group(block_group); + btrfs_put_block_group(block_group); + btrfs_put_block_group(block_group); ret = btrfs_search_slot(trans, root, &key, path, -1, 1); if (ret > 0) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 08085af089e2..eb2bee8b7fbf 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2884,25 +2884,19 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, disko = 0; flags = 0; - switch (em->block_start) { - case EXTENT_MAP_LAST_BYTE: + if (em->block_start == EXTENT_MAP_LAST_BYTE) { end = 1; flags |= FIEMAP_EXTENT_LAST; - break; - case EXTENT_MAP_HOLE: + } else if (em->block_start == EXTENT_MAP_HOLE) { flags |= FIEMAP_EXTENT_UNWRITTEN; - break; - case EXTENT_MAP_INLINE: + } else if (em->block_start == EXTENT_MAP_INLINE) { flags |= (FIEMAP_EXTENT_DATA_INLINE | FIEMAP_EXTENT_NOT_ALIGNED); - break; - case EXTENT_MAP_DELALLOC: + } else if (em->block_start == EXTENT_MAP_DELALLOC) { flags |= (FIEMAP_EXTENT_DELALLOC | FIEMAP_EXTENT_UNKNOWN); - break; - default: + } else { disko = em->block_start; - break; } if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) flags |= FIEMAP_EXTENT_ENCODED; diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 50da69da20ce..b187917b36fa 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -234,7 +234,6 @@ int add_extent_mapping(struct extent_map_tree *tree, rb = tree_insert(&tree->map, em->start, &em->rb_node); if (rb) { ret = -EEXIST; - free_extent_map(merge); goto out; } atomic_inc(&em->refs); diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index d1e5f0e84c58..768b9523662d 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -18,6 +18,15 @@ #include <linux/sched.h> #include "ctree.h" +#include "free-space-cache.h" +#include "transaction.h" + +struct btrfs_free_space { + struct rb_node bytes_index; + struct rb_node offset_index; + u64 offset; + u64 bytes; +}; static int tree_insert_offset(struct rb_root *root, u64 offset, struct rb_node *node) @@ -68,14 +77,24 @@ static int tree_insert_bytes(struct rb_root *root, u64 bytes, } /* - * searches the tree for the given offset. If contains is set we will return - * the free space that contains the given offset. If contains is not set we - * will return the free space that starts at or after the given offset and is - * at least bytes long. + * searches the tree for the given offset. + * + * fuzzy == 1: this is used for allocations where we are given a hint of where + * to look for free space. Because the hint may not be completely on an offset + * mark, or the hint may no longer point to free space we need to fudge our + * results a bit. So we look for free space starting at or after offset with at + * least bytes size. We prefer to find as close to the given offset as we can. + * Also if the offset is within a free space range, then we will return the free + * space that contains the given offset, which means we can return a free space + * chunk with an offset before the provided offset. + * + * fuzzy == 0: this is just a normal tree search. Give us the free space that + * starts at the given offset which is at least bytes size, and if its not there + * return NULL. */ static struct btrfs_free_space *tree_search_offset(struct rb_root *root, u64 offset, u64 bytes, - int contains) + int fuzzy) { struct rb_node *n = root->rb_node; struct btrfs_free_space *entry, *ret = NULL; @@ -84,13 +103,14 @@ static struct btrfs_free_space *tree_search_offset(struct rb_root *root, entry = rb_entry(n, struct btrfs_free_space, offset_index); if (offset < entry->offset) { - if (!contains && + if (fuzzy && (!ret || entry->offset < ret->offset) && (bytes <= entry->bytes)) ret = entry; n = n->rb_left; } else if (offset > entry->offset) { - if ((entry->offset + entry->bytes - 1) >= offset && + if (fuzzy && + (entry->offset + entry->bytes - 1) >= offset && bytes <= entry->bytes) { ret = entry; break; @@ -171,6 +191,7 @@ static int link_free_space(struct btrfs_block_group_cache *block_group, int ret = 0; + BUG_ON(!info->bytes); ret = tree_insert_offset(&block_group->free_space_offset, info->offset, &info->offset_index); if (ret) @@ -184,108 +205,70 @@ static int link_free_space(struct btrfs_block_group_cache *block_group, return ret; } -static int __btrfs_add_free_space(struct btrfs_block_group_cache *block_group, - u64 offset, u64 bytes) +int btrfs_add_free_space(struct btrfs_block_group_cache *block_group, + u64 offset, u64 bytes) { struct btrfs_free_space *right_info; struct btrfs_free_space *left_info; struct btrfs_free_space *info = NULL; - struct btrfs_free_space *alloc_info; int ret = 0; - alloc_info = kzalloc(sizeof(struct btrfs_free_space), GFP_NOFS); - if (!alloc_info) + info = kzalloc(sizeof(struct btrfs_free_space), GFP_NOFS); + if (!info) return -ENOMEM; + info->offset = offset; + info->bytes = bytes; + + spin_lock(&block_group->tree_lock); + /* * first we want to see if there is free space adjacent to the range we * are adding, if there is remove that struct and add a new one to * cover the entire range */ right_info = tree_search_offset(&block_group->free_space_offset, - offset+bytes, 0, 1); + offset+bytes, 0, 0); left_info = tree_search_offset(&block_group->free_space_offset, offset-1, 0, 1); - if (right_info && right_info->offset == offset+bytes) { + if (right_info) { unlink_free_space(block_group, right_info); - info = right_info; - info->offset = offset; - info->bytes += bytes; - } else if (right_info && right_info->offset != offset+bytes) { - printk(KERN_ERR "btrfs adding space in the middle of an " - "existing free space area. existing: " - "offset=%llu, bytes=%llu. new: offset=%llu, " - "bytes=%llu\n", (unsigned long long)right_info->offset, - (unsigned long long)right_info->bytes, - (unsigned long long)offset, - (unsigned long long)bytes); - BUG(); + info->bytes += right_info->bytes; + kfree(right_info); } - if (left_info) { + if (left_info && left_info->offset + left_info->bytes == offset) { unlink_free_space(block_group, left_info); - - if (unlikely((left_info->offset + left_info->bytes) != - offset)) { - printk(KERN_ERR "btrfs free space to the left " - "of new free space isn't " - "quite right. existing: offset=%llu, " - "bytes=%llu. new: offset=%llu, bytes=%llu\n", - (unsigned long long)left_info->offset, - (unsigned long long)left_info->bytes, - (unsigned long long)offset, - (unsigned long long)bytes); - BUG(); - } - - if (info) { - info->offset = left_info->offset; - info->bytes += left_info->bytes; - kfree(left_info); - } else { - info = left_info; - info->bytes += bytes; - } + info->offset = left_info->offset; + info->bytes += left_info->bytes; + kfree(left_info); } - if (info) { - ret = link_free_space(block_group, info); - if (!ret) - info = NULL; - goto out; - } - - info = alloc_info; - alloc_info = NULL; - info->offset = offset; - info->bytes = bytes; - ret = link_free_space(block_group, info); if (ret) kfree(info); -out: + + spin_unlock(&block_group->tree_lock); + if (ret) { printk(KERN_ERR "btrfs: unable to add free space :%d\n", ret); - if (ret == -EEXIST) - BUG(); + BUG_ON(ret == -EEXIST); } - kfree(alloc_info); - return ret; } -static int -__btrfs_remove_free_space(struct btrfs_block_group_cache *block_group, - u64 offset, u64 bytes) +int btrfs_remove_free_space(struct btrfs_block_group_cache *block_group, + u64 offset, u64 bytes) { struct btrfs_free_space *info; int ret = 0; + spin_lock(&block_group->tree_lock); + info = tree_search_offset(&block_group->free_space_offset, offset, 0, 1); - if (info && info->offset == offset) { if (info->bytes < bytes) { printk(KERN_ERR "Found free space at %llu, size %llu," @@ -295,12 +278,14 @@ __btrfs_remove_free_space(struct btrfs_block_group_cache *block_group, (unsigned long long)bytes); WARN_ON(1); ret = -EINVAL; + spin_unlock(&block_group->tree_lock); goto out; } unlink_free_space(block_group, info); if (info->bytes == bytes) { kfree(info); + spin_unlock(&block_group->tree_lock); goto out; } @@ -308,6 +293,7 @@ __btrfs_remove_free_space(struct btrfs_block_group_cache *block_group, info->bytes -= bytes; ret = link_free_space(block_group, info); + spin_unlock(&block_group->tree_lock); BUG_ON(ret); } else if (info && info->offset < offset && info->offset + info->bytes >= offset + bytes) { @@ -333,70 +319,33 @@ __btrfs_remove_free_space(struct btrfs_block_group_cache *block_group, */ kfree(info); } - + spin_unlock(&block_group->tree_lock); /* step two, insert a new info struct to cover anything * before the hole */ - ret = __btrfs_add_free_space(block_group, old_start, - offset - old_start); + ret = btrfs_add_free_space(block_group, old_start, + offset - old_start); BUG_ON(ret); } else { + spin_unlock(&block_group->tree_lock); + if (!info) { + printk(KERN_ERR "couldn't find space %llu to free\n", + (unsigned long long)offset); + printk(KERN_ERR "cached is %d, offset %llu bytes %llu\n", + block_group->cached, block_group->key.objectid, + block_group->key.offset); + btrfs_dump_free_space(block_group, bytes); + } else if (info) { + printk(KERN_ERR "hmm, found offset=%llu bytes=%llu, " + "but wanted offset=%llu bytes=%llu\n", + info->offset, info->bytes, offset, bytes); + } WARN_ON(1); } out: return ret; } -int btrfs_add_free_space(struct btrfs_block_group_cache *block_group, - u64 offset, u64 bytes) -{ - int ret; - struct btrfs_free_space *sp; - - mutex_lock(&block_group->alloc_mutex); - ret = __btrfs_add_free_space(block_group, offset, bytes); - sp = tree_search_offset(&block_group->free_space_offset, offset, 0, 1); - BUG_ON(!sp); - mutex_unlock(&block_group->alloc_mutex); - - return ret; -} - -int btrfs_add_free_space_lock(struct btrfs_block_group_cache *block_group, - u64 offset, u64 bytes) -{ - int ret; - struct btrfs_free_space *sp; - - ret = __btrfs_add_free_space(block_group, offset, bytes); - sp = tree_search_offset(&block_group->free_space_offset, offset, 0, 1); - BUG_ON(!sp); - - return ret; -} - -int btrfs_remove_free_space(struct btrfs_block_group_cache *block_group, - u64 offset, u64 bytes) -{ - int ret = 0; - - mutex_lock(&block_group->alloc_mutex); - ret = __btrfs_remove_free_space(block_group, offset, bytes); - mutex_unlock(&block_group->alloc_mutex); - - return ret; -} - -int btrfs_remove_free_space_lock(struct btrfs_block_group_cache *block_group, - u64 offset, u64 bytes) -{ - int ret; - - ret = __btrfs_remove_free_space(block_group, offset, bytes); - - return ret; -} - void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group, u64 bytes) { @@ -408,6 +357,8 @@ void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group, info = rb_entry(n, struct btrfs_free_space, offset_index); if (info->bytes >= bytes) count++; + printk(KERN_ERR "entry offset %llu, bytes %llu\n", info->offset, + info->bytes); } printk(KERN_INFO "%d blocks of free space at or bigger than bytes is" "\n", count); @@ -428,68 +379,337 @@ u64 btrfs_block_group_free_space(struct btrfs_block_group_cache *block_group) return ret; } +/* + * for a given cluster, put all of its extents back into the free + * space cache. If the block group passed doesn't match the block group + * pointed to by the cluster, someone else raced in and freed the + * cluster already. In that case, we just return without changing anything + */ +static int +__btrfs_return_cluster_to_free_space( + struct btrfs_block_group_cache *block_group, + struct btrfs_free_cluster *cluster) +{ + struct btrfs_free_space *entry; + struct rb_node *node; + + spin_lock(&cluster->lock); + if (cluster->block_group != block_group) + goto out; + + cluster->window_start = 0; + node = rb_first(&cluster->root); + while(node) { + entry = rb_entry(node, struct btrfs_free_space, offset_index); + node = rb_next(&entry->offset_index); + rb_erase(&entry->offset_index, &cluster->root); + link_free_space(block_group, entry); + } + list_del_init(&cluster->block_group_list); + + btrfs_put_block_group(cluster->block_group); + cluster->block_group = NULL; + cluster->root.rb_node = NULL; +out: + spin_unlock(&cluster->lock); + return 0; +} + void btrfs_remove_free_space_cache(struct btrfs_block_group_cache *block_group) { struct btrfs_free_space *info; struct rb_node *node; + struct btrfs_free_cluster *cluster; + struct btrfs_free_cluster *safe; + + spin_lock(&block_group->tree_lock); + + list_for_each_entry_safe(cluster, safe, &block_group->cluster_list, + block_group_list) { + + WARN_ON(cluster->block_group != block_group); + __btrfs_return_cluster_to_free_space(block_group, cluster); + } - mutex_lock(&block_group->alloc_mutex); while ((node = rb_last(&block_group->free_space_bytes)) != NULL) { info = rb_entry(node, struct btrfs_free_space, bytes_index); unlink_free_space(block_group, info); kfree(info); if (need_resched()) { - mutex_unlock(&block_group->alloc_mutex); + spin_unlock(&block_group->tree_lock); cond_resched(); - mutex_lock(&block_group->alloc_mutex); + spin_lock(&block_group->tree_lock); } } - mutex_unlock(&block_group->alloc_mutex); + spin_unlock(&block_group->tree_lock); } -#if 0 -static struct btrfs_free_space *btrfs_find_free_space_offset(struct - btrfs_block_group_cache - *block_group, u64 offset, - u64 bytes) +u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group, + u64 offset, u64 bytes, u64 empty_size) { - struct btrfs_free_space *ret; + struct btrfs_free_space *entry = NULL; + u64 ret = 0; - mutex_lock(&block_group->alloc_mutex); - ret = tree_search_offset(&block_group->free_space_offset, offset, - bytes, 0); - mutex_unlock(&block_group->alloc_mutex); + spin_lock(&block_group->tree_lock); + entry = tree_search_offset(&block_group->free_space_offset, offset, + bytes + empty_size, 1); + if (!entry) + entry = tree_search_bytes(&block_group->free_space_bytes, + offset, bytes + empty_size); + if (entry) { + unlink_free_space(block_group, entry); + ret = entry->offset; + entry->offset += bytes; + entry->bytes -= bytes; + + if (!entry->bytes) + kfree(entry); + else + link_free_space(block_group, entry); + } + spin_unlock(&block_group->tree_lock); return ret; } -static struct btrfs_free_space *btrfs_find_free_space_bytes(struct - btrfs_block_group_cache - *block_group, u64 offset, - u64 bytes) +/* + * given a cluster, put all of its extents back into the free space + * cache. If a block group is passed, this function will only free + * a cluster that belongs to the passed block group. + * + * Otherwise, it'll get a reference on the block group pointed to by the + * cluster and remove the cluster from it. + */ +int btrfs_return_cluster_to_free_space( + struct btrfs_block_group_cache *block_group, + struct btrfs_free_cluster *cluster) { - struct btrfs_free_space *ret; + int ret; - mutex_lock(&block_group->alloc_mutex); + /* first, get a safe pointer to the block group */ + spin_lock(&cluster->lock); + if (!block_group) { + block_group = cluster->block_group; + if (!block_group) { + spin_unlock(&cluster->lock); + return 0; + } + } else if (cluster->block_group != block_group) { + /* someone else has already freed it don't redo their work */ + spin_unlock(&cluster->lock); + return 0; + } + atomic_inc(&block_group->count); + spin_unlock(&cluster->lock); - ret = tree_search_bytes(&block_group->free_space_bytes, offset, bytes); - mutex_unlock(&block_group->alloc_mutex); + /* now return any extents the cluster had on it */ + spin_lock(&block_group->tree_lock); + ret = __btrfs_return_cluster_to_free_space(block_group, cluster); + spin_unlock(&block_group->tree_lock); + /* finally drop our ref */ + btrfs_put_block_group(block_group); return ret; } -#endif -struct btrfs_free_space *btrfs_find_free_space(struct btrfs_block_group_cache - *block_group, u64 offset, - u64 bytes) +/* + * given a cluster, try to allocate 'bytes' from it, returns 0 + * if it couldn't find anything suitably large, or a logical disk offset + * if things worked out + */ +u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group, + struct btrfs_free_cluster *cluster, u64 bytes, + u64 min_start) +{ + struct btrfs_free_space *entry = NULL; + struct rb_node *node; + u64 ret = 0; + + spin_lock(&cluster->lock); + if (bytes > cluster->max_size) + goto out; + + if (cluster->block_group != block_group) + goto out; + + node = rb_first(&cluster->root); + if (!node) + goto out; + + entry = rb_entry(node, struct btrfs_free_space, offset_index); + + while(1) { + if (entry->bytes < bytes || entry->offset < min_start) { + struct rb_node *node; + + node = rb_next(&entry->offset_index); + if (!node) + break; + entry = rb_entry(node, struct btrfs_free_space, + offset_index); + continue; + } + ret = entry->offset; + + entry->offset += bytes; + entry->bytes -= bytes; + + if (entry->bytes == 0) { + rb_erase(&entry->offset_index, &cluster->root); + kfree(entry); + } + break; + } +out: + spin_unlock(&cluster->lock); + return ret; +} + +/* + * here we try to find a cluster of blocks in a block group. The goal + * is to find at least bytes free and up to empty_size + bytes free. + * We might not find them all in one contiguous area. + * + * returns zero and sets up cluster if things worked out, otherwise + * it returns -enospc + */ +int btrfs_find_space_cluster(struct btrfs_trans_handle *trans, + struct btrfs_block_group_cache *block_group, + struct btrfs_free_cluster *cluster, + u64 offset, u64 bytes, u64 empty_size) { - struct btrfs_free_space *ret = NULL; + struct btrfs_free_space *entry = NULL; + struct rb_node *node; + struct btrfs_free_space *next; + struct btrfs_free_space *last; + u64 min_bytes; + u64 window_start; + u64 window_free; + u64 max_extent = 0; + int total_retries = 0; + int ret; + + /* for metadata, allow allocates with more holes */ + if (block_group->flags & BTRFS_BLOCK_GROUP_METADATA) { + /* + * we want to do larger allocations when we are + * flushing out the delayed refs, it helps prevent + * making more work as we go along. + */ + if (trans->transaction->delayed_refs.flushing) + min_bytes = max(bytes, (bytes + empty_size) >> 1); + else + min_bytes = max(bytes, (bytes + empty_size) >> 4); + } else + min_bytes = max(bytes, (bytes + empty_size) >> 2); + + spin_lock(&block_group->tree_lock); + spin_lock(&cluster->lock); + + /* someone already found a cluster, hooray */ + if (cluster->block_group) { + ret = 0; + goto out; + } +again: + min_bytes = min(min_bytes, bytes + empty_size); + entry = tree_search_bytes(&block_group->free_space_bytes, + offset, min_bytes); + if (!entry) { + ret = -ENOSPC; + goto out; + } + window_start = entry->offset; + window_free = entry->bytes; + last = entry; + max_extent = entry->bytes; + + while(1) { + /* out window is just right, lets fill it */ + if (window_free >= bytes + empty_size) + break; - ret = tree_search_offset(&block_group->free_space_offset, offset, - bytes, 0); - if (!ret) - ret = tree_search_bytes(&block_group->free_space_bytes, - offset, bytes); + node = rb_next(&last->offset_index); + if (!node) { + ret = -ENOSPC; + goto out; + } + next = rb_entry(node, struct btrfs_free_space, offset_index); + + /* + * we haven't filled the empty size and the window is + * very large. reset and try again + */ + if (next->offset - window_start > (bytes + empty_size) * 2) { + entry = next; + window_start = entry->offset; + window_free = entry->bytes; + last = entry; + max_extent = 0; + total_retries++; + if (total_retries % 256 == 0) { + if (min_bytes >= (bytes + empty_size)) { + ret = -ENOSPC; + goto out; + } + /* + * grow our allocation a bit, we're not having + * much luck + */ + min_bytes *= 2; + goto again; + } + } else { + last = next; + window_free += next->bytes; + if (entry->bytes > max_extent) + max_extent = entry->bytes; + } + } + + cluster->window_start = entry->offset; + + /* + * now we've found our entries, pull them out of the free space + * cache and put them into the cluster rbtree + * + * The cluster includes an rbtree, but only uses the offset index + * of each free space cache entry. + */ + while(1) { + node = rb_next(&entry->offset_index); + unlink_free_space(block_group, entry); + ret = tree_insert_offset(&cluster->root, entry->offset, + &entry->offset_index); + BUG_ON(ret); + + if (!node || entry == last) + break; + + entry = rb_entry(node, struct btrfs_free_space, offset_index); + } + ret = 0; + cluster->max_size = max_extent; + atomic_inc(&block_group->count); + list_add_tail(&cluster->block_group_list, &block_group->cluster_list); + cluster->block_group = block_group; +out: + spin_unlock(&cluster->lock); + spin_unlock(&block_group->tree_lock); return ret; } + +/* + * simple code to zero out a cluster + */ +void btrfs_init_free_cluster(struct btrfs_free_cluster *cluster) +{ + spin_lock_init(&cluster->lock); + spin_lock_init(&cluster->refill_lock); + cluster->root.rb_node = NULL; + cluster->max_size = 0; + INIT_LIST_HEAD(&cluster->block_group_list); + cluster->block_group = NULL; +} + diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h new file mode 100644 index 000000000000..ab0bdc0a63ce --- /dev/null +++ b/fs/btrfs/free-space-cache.h @@ -0,0 +1,44 @@ +/* + * Copyright (C) 2009 Oracle. 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 v2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public + * License along with this program; if not, write to the + * Free Software Foundation, Inc., 59 Temple Place - Suite 330, + * Boston, MA 021110-1307, USA. + */ + +#ifndef __BTRFS_FREE_SPACE_CACHE +#define __BTRFS_FREE_SPACE_CACHE + +int btrfs_add_free_space(struct btrfs_block_group_cache *block_group, + u64 bytenr, u64 size); +int btrfs_remove_free_space(struct btrfs_block_group_cache *block_group, + u64 bytenr, u64 size); +void btrfs_remove_free_space_cache(struct btrfs_block_group_cache + *block_group); +u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group, + u64 offset, u64 bytes, u64 empty_size); +void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group, + u64 bytes); +u64 btrfs_block_group_free_space(struct btrfs_block_group_cache *block_group); +int btrfs_find_space_cluster(struct btrfs_trans_handle *trans, + struct btrfs_block_group_cache *block_group, + struct btrfs_free_cluster *cluster, + u64 offset, u64 bytes, u64 empty_size); +void btrfs_init_free_cluster(struct btrfs_free_cluster *cluster); +u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group, + struct btrfs_free_cluster *cluster, u64 bytes, + u64 min_start); +int btrfs_return_cluster_to_free_space( + struct btrfs_block_group_cache *block_group, + struct btrfs_free_cluster *cluster); +#endif diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 06d8db5afb08..a0d1dd492a58 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3481,8 +3481,10 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans, if (dir) { ret = btrfs_set_inode_index(dir, index); - if (ret) + if (ret) { + iput(inode); return ERR_PTR(ret); + } } /* * index_cnt is ignored for everything but a dir, @@ -3565,6 +3567,7 @@ fail: if (dir) BTRFS_I(dir)->index_cnt--; btrfs_free_path(path); + iput(inode); return ERR_PTR(ret); } diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c index a5310c0f41e2..1c36e5cd8f55 100644 --- a/fs/btrfs/locking.c +++ b/fs/btrfs/locking.c @@ -60,8 +60,8 @@ void btrfs_clear_lock_blocking(struct extent_buffer *eb) /* * unfortunately, many of the places that currently set a lock to blocking - * don't end up blocking for every long, and often they don't block - * at all. For a dbench 50 run, if we don't spin one the blocking bit + * don't end up blocking for very long, and often they don't block + * at all. For a dbench 50 run, if we don't spin on the blocking bit * at all, the context switch rate can jump up to 400,000/sec or more. * * So, we're still stuck with this crummy spin on the blocking bit, diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 19a4daf03ccb..9744af9d71e9 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -24,6 +24,7 @@ #include <linux/highmem.h> #include <linux/time.h> #include <linux/init.h> +#include <linux/seq_file.h> #include <linux/string.h> #include <linux/smp_lock.h> #include <linux/backing-dev.h> @@ -66,7 +67,8 @@ static void btrfs_put_super(struct super_block *sb) enum { Opt_degraded, Opt_subvol, Opt_device, Opt_nodatasum, Opt_nodatacow, Opt_max_extent, Opt_max_inline, Opt_alloc_start, Opt_nobarrier, - Opt_ssd, Opt_thread_pool, Opt_noacl, Opt_compress, Opt_err, + Opt_ssd, Opt_thread_pool, Opt_noacl, Opt_compress, Opt_notreelog, + Opt_flushoncommit, Opt_err, }; static match_table_t tokens = { @@ -83,6 +85,8 @@ static match_table_t tokens = { {Opt_compress, "compress"}, {Opt_ssd, "ssd"}, {Opt_noacl, "noacl"}, + {Opt_notreelog, "notreelog"}, + {Opt_flushoncommit, "flushoncommit"}, {Opt_err, NULL}, }; @@ -222,6 +226,14 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) case Opt_noacl: root->fs_info->sb->s_flags &= ~MS_POSIXACL; break; + case Opt_notreelog: + printk(KERN_INFO "btrfs: disabling tree log\n"); + btrfs_set_opt(info->mount_opt, NOTREELOG); + break; + case Opt_flushoncommit: + printk(KERN_INFO "btrfs: turning on flush-on-commit\n"); + btrfs_set_opt(info->mount_opt, FLUSHONCOMMIT); + break; default: break; } @@ -363,9 +375,8 @@ fail_close: int btrfs_sync_fs(struct super_block *sb, int wait) { struct btrfs_trans_handle *trans; - struct btrfs_root *root; + struct btrfs_root *root = btrfs_sb(sb); int ret; - root = btrfs_sb(sb); if (sb->s_flags & MS_RDONLY) return 0; @@ -385,6 +396,41 @@ int btrfs_sync_fs(struct super_block *sb, int wait) return ret; } +static int btrfs_show_options(struct seq_file *seq, struct vfsmount *vfs) +{ + struct btrfs_root *root = btrfs_sb(vfs->mnt_sb); + struct btrfs_fs_info *info = root->fs_info; + + if (btrfs_test_opt(root, DEGRADED)) + seq_puts(seq, ",degraded"); + if (btrfs_test_opt(root, NODATASUM)) + seq_puts(seq, ",nodatasum"); + if (btrfs_test_opt(root, NODATACOW)) + seq_puts(seq, ",nodatacow"); + if (btrfs_test_opt(root, NOBARRIER)) + seq_puts(seq, ",nobarrier"); + if (info->max_extent != (u64)-1) + seq_printf(seq, ",max_extent=%llu", info->max_extent); + if (info->max_inline != 8192 * 1024) + seq_printf(seq, ",max_inline=%llu", info->max_inline); + if (info->alloc_start != 0) + seq_printf(seq, ",alloc_start=%llu", info->alloc_start); + if (info->thread_pool_size != min_t(unsigned long, + num_online_cpus() + 2, 8)) + seq_printf(seq, ",thread_pool=%d", info->thread_pool_size); + if (btrfs_test_opt(root, COMPRESS)) + seq_puts(seq, ",compress"); + if (btrfs_test_opt(root, SSD)) + seq_puts(seq, ",ssd"); + if (btrfs_test_opt(root, NOTREELOG)) + seq_puts(seq, ",no-treelog"); + if (btrfs_test_opt(root, FLUSHONCOMMIT)) + seq_puts(seq, ",flush-on-commit"); + if (!(root->fs_info->sb->s_flags & MS_POSIXACL)) + seq_puts(seq, ",noacl"); + return 0; +} + static void btrfs_write_super(struct super_block *sb) { sb->s_dirt = 0; @@ -630,7 +676,7 @@ static struct super_operations btrfs_super_ops = { .put_super = btrfs_put_super, .write_super = btrfs_write_super, .sync_fs = btrfs_sync_fs, - .show_options = generic_show_options, + .show_options = btrfs_show_options, .write_inode = btrfs_write_inode, .dirty_inode = btrfs_dirty_inode, .alloc_inode = btrfs_alloc_inode, diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 664782c6a2df..2869b3361eb6 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -53,8 +53,6 @@ static noinline int join_transaction(struct btrfs_root *root) GFP_NOFS); BUG_ON(!cur_trans); root->fs_info->generation++; - root->fs_info->last_alloc = 0; - root->fs_info->last_data_alloc = 0; cur_trans->num_writers = 1; cur_trans->num_joined = 0; cur_trans->transid = root->fs_info->generation; @@ -974,6 +972,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, int ret; int should_grow = 0; unsigned long now = get_seconds(); + int flush_on_commit = btrfs_test_opt(root, FLUSHONCOMMIT); btrfs_run_ordered_operations(root, 0); @@ -1053,7 +1052,9 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, mutex_unlock(&root->fs_info->trans_mutex); - if (snap_pending) { + if (flush_on_commit || snap_pending) { + if (flush_on_commit) + btrfs_start_delalloc_inodes(root); ret = btrfs_wait_ordered_extents(root, 1); BUG_ON(ret); } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index fc9b87a7975b..25f20ea11f27 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -262,11 +262,9 @@ static int process_one_buffer(struct btrfs_root *log, struct extent_buffer *eb, struct walk_control *wc, u64 gen) { - if (wc->pin) { - mutex_lock(&log->fs_info->pinned_mutex); + if (wc->pin) btrfs_update_pinned_extents(log->fs_info->extent_root, eb->start, eb->len, 1); - } if (btrfs_buffer_uptodate(eb, gen)) { if (wc->write) @@ -1224,8 +1222,7 @@ insert: ret = insert_one_name(trans, root, path, key->objectid, key->offset, name, name_len, log_type, &log_key); - if (ret && ret != -ENOENT) - BUG(); + BUG_ON(ret && ret != -ENOENT); goto out; } @@ -2900,6 +2897,11 @@ int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, sb = inode->i_sb; + if (btrfs_test_opt(root, NOTREELOG)) { + ret = 1; + goto end_no_trans; + } + if (root->fs_info->last_trans_log_full_commit > root->fs_info->last_trans_committed) { ret = 1; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index dd06e18e5aac..e0913e469728 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -20,6 +20,7 @@ #include <linux/buffer_head.h> #include <linux/blkdev.h> #include <linux/random.h> +#include <linux/iocontext.h> #include <asm/div64.h> #include "compat.h" #include "ctree.h" @@ -145,8 +146,9 @@ static noinline int run_scheduled_bios(struct btrfs_device *device) int again = 0; unsigned long num_run = 0; unsigned long limit; + unsigned long last_waited = 0; - bdi = device->bdev->bd_inode->i_mapping->backing_dev_info; + bdi = blk_get_backing_dev_info(device->bdev); fs_info = device->dev_root->fs_info; limit = btrfs_async_submit_limit(fs_info); limit = limit * 2 / 3; @@ -207,7 +209,32 @@ loop_lock: if (pending && bdi_write_congested(bdi) && num_run > 16 && fs_info->fs_devices->open_devices > 1) { struct bio *old_head; + struct io_context *ioc; + ioc = current->io_context; + + /* + * the main goal here is that we don't want to + * block if we're going to be able to submit + * more requests without blocking. + * + * This code does two great things, it pokes into + * the elevator code from a filesystem _and_ + * it makes assumptions about how batching works. + */ + if (ioc && ioc->nr_batch_requests > 0 && + time_before(jiffies, ioc->last_waited + HZ/50UL) && + (last_waited == 0 || + ioc->last_waited == last_waited)) { + /* + * we want to go through our batch of + * requests and stop. So, we copy out + * the ioc->last_waited time and test + * against it before looping + */ + last_waited = ioc->last_waited; + continue; + } spin_lock(&device->io_lock); old_head = device->pending_bios; @@ -231,6 +258,18 @@ loop_lock: if (device->pending_bios) goto loop_lock; spin_unlock(&device->io_lock); + + /* + * IO has already been through a long path to get here. Checksumming, + * async helper threads, perhaps compression. We've done a pretty + * good job of collecting a batch of IO and should just unplug + * the device right away. + * + * This will help anyone who is waiting on the IO, they might have + * already unplugged, but managed to do so before the bio they + * cared about found its way down here. + */ + blk_run_backing_dev(bdi, NULL); done: return 0; } diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 86c44e9ae110..2185de72ff7d 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -76,7 +76,7 @@ struct btrfs_device { struct btrfs_fs_devices { u8 fsid[BTRFS_FSID_SIZE]; /* FS specific uuid */ - /* the device with this id has the most recent coyp of the super */ + /* the device with this id has the most recent copy of the super */ u64 latest_devid; u64 latest_trans; u64 num_devices; diff --git a/fs/compat.c b/fs/compat.c index 1c859dae758f..3f84d5f15889 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -1236,7 +1236,7 @@ compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec, asmlinkage ssize_t compat_sys_preadv(unsigned long fd, const struct compat_iovec __user *vec, - unsigned long vlen, u32 pos_high, u32 pos_low) + unsigned long vlen, u32 pos_low, u32 pos_high) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; struct file *file; @@ -1293,7 +1293,7 @@ compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec, asmlinkage ssize_t compat_sys_pwritev(unsigned long fd, const struct compat_iovec __user *vec, - unsigned long vlen, u32 pos_high, u32 pos_low) + unsigned long vlen, u32 pos_low, u32 pos_high) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; struct file *file; diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 81ae9ea3c6e1..0662ba6de85a 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -30,6 +30,7 @@ static struct vfsmount *debugfs_mount; static int debugfs_mount_count; +static bool debugfs_registered; static struct inode *debugfs_get_inode(struct super_block *sb, int mode, dev_t dev) { @@ -496,6 +497,16 @@ exit: } EXPORT_SYMBOL_GPL(debugfs_rename); +/** + * debugfs_initialized - Tells whether debugfs has been registered + */ +bool debugfs_initialized(void) +{ + return debugfs_registered; +} +EXPORT_SYMBOL_GPL(debugfs_initialized); + + static struct kobject *debug_kobj; static int __init debugfs_init(void) @@ -509,11 +520,16 @@ static int __init debugfs_init(void) retval = register_filesystem(&debug_fs_type); if (retval) kobject_put(debug_kobj); + else + debugfs_registered = true; + return retval; } static void __exit debugfs_exit(void) { + debugfs_registered = false; + simple_release_fs(&debugfs_mount, &debugfs_mount_count); unregister_filesystem(&debug_fs_type); kobject_put(debug_kobj); diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index 7505482a08fa..418b6f3b0ae8 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -18,7 +18,7 @@ config EXT4_FS filesystem; while there will be some performance gains from the delayed allocation and inode table readahead, the best performance gains will require enabling ext4 features in the - filesystem, or formating a new filesystem as an ext4 + filesystem, or formatting a new filesystem as an ext4 filesystem initially. To compile this file system support as a module, choose M here. The diff --git a/fs/file_table.c b/fs/file_table.c index b74a8e1da913..54018fe48840 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -169,7 +169,6 @@ struct file *alloc_file(struct vfsmount *mnt, struct dentry *dentry, fmode_t mode, const struct file_operations *fop) { struct file *file; - struct path; file = get_empty_filp(); if (!file) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index eed480639902..91013ff7dd53 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -435,7 +435,7 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) * If older_than_this is non-NULL, then only write out inodes which * had their first dirtying at a time earlier than *older_than_this. * - * If we're a pdlfush thread, then implement pdflush collision avoidance + * If we're a pdflush thread, then implement pdflush collision avoidance * against the entire list. * * If `bdi' is non-zero then we're being asked to writeback a specific queue. diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 06da05261e04..8b8eebc5614b 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1032,6 +1032,7 @@ static int fuse_readdir(struct file *file, void *dstbuf, filldir_t filldir) fuse_put_request(fc, req); return -ENOMEM; } + req->out.argpages = 1; req->num_pages = 1; req->pages[0] = page; fuse_read_fill(req, file, inode, file->f_pos, PAGE_SIZE, FUSE_READDIR); diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 4e340fedf768..2b25133524a3 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -386,7 +386,6 @@ void fuse_read_fill(struct fuse_req *req, struct file *file, req->in.numargs = 1; req->in.args[0].size = sizeof(struct fuse_read_in); req->in.args[0].value = inarg; - req->out.argpages = 1; req->out.argvar = 1; req->out.numargs = 1; req->out.args[0].size = count; @@ -453,6 +452,7 @@ static int fuse_readpage(struct file *file, struct page *page) attr_ver = fuse_get_attr_version(fc); req->out.page_zeroing = 1; + req->out.argpages = 1; req->num_pages = 1; req->pages[0] = page; num_read = fuse_send_read(req, file, inode, pos, count, NULL); @@ -510,6 +510,8 @@ static void fuse_send_readpages(struct fuse_req *req, struct file *file, struct fuse_conn *fc = get_fuse_conn(inode); loff_t pos = page_offset(req->pages[0]); size_t count = req->num_pages << PAGE_CACHE_SHIFT; + + req->out.argpages = 1; req->out.page_zeroing = 1; fuse_read_fill(req, file, inode, pos, count, FUSE_READ); req->misc.read.attr_ver = fuse_get_attr_version(fc); @@ -621,7 +623,6 @@ static void fuse_write_fill(struct fuse_req *req, struct file *file, inarg->flags = file ? file->f_flags : 0; req->in.h.opcode = FUSE_WRITE; req->in.h.nodeid = get_node_id(inode); - req->in.argpages = 1; req->in.numargs = 2; if (fc->minor < 9) req->in.args[0].size = FUSE_COMPAT_WRITE_IN_SIZE; @@ -695,6 +696,7 @@ static int fuse_buffered_write(struct file *file, struct inode *inode, if (IS_ERR(req)) return PTR_ERR(req); + req->in.argpages = 1; req->num_pages = 1; req->pages[0] = page; req->page_offset = offset; @@ -771,6 +773,7 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req, size_t count = 0; int err; + req->in.argpages = 1; req->page_offset = offset; do { @@ -935,21 +938,28 @@ static void fuse_release_user_pages(struct fuse_req *req, int write) } static int fuse_get_user_pages(struct fuse_req *req, const char __user *buf, - unsigned nbytes, int write) + unsigned *nbytesp, int write) { + unsigned nbytes = *nbytesp; unsigned long user_addr = (unsigned long) buf; unsigned offset = user_addr & ~PAGE_MASK; int npages; - /* This doesn't work with nfsd */ - if (!current->mm) - return -EPERM; + /* Special case for kernel I/O: can copy directly into the buffer */ + if (segment_eq(get_fs(), KERNEL_DS)) { + if (write) + req->in.args[1].value = (void *) user_addr; + else + req->out.args[0].value = (void *) user_addr; + + return 0; + } nbytes = min(nbytes, (unsigned) FUSE_MAX_PAGES_PER_REQ << PAGE_SHIFT); npages = (nbytes + offset + PAGE_SIZE - 1) >> PAGE_SHIFT; npages = clamp(npages, 1, FUSE_MAX_PAGES_PER_REQ); down_read(¤t->mm->mmap_sem); - npages = get_user_pages(current, current->mm, user_addr, npages, write, + npages = get_user_pages(current, current->mm, user_addr, npages, !write, 0, req->pages, NULL); up_read(¤t->mm->mmap_sem); if (npages < 0) @@ -957,6 +967,15 @@ static int fuse_get_user_pages(struct fuse_req *req, const char __user *buf, req->num_pages = npages; req->page_offset = offset; + + if (write) + req->in.argpages = 1; + else + req->out.argpages = 1; + + nbytes = (req->num_pages << PAGE_SHIFT) - req->page_offset; + *nbytesp = min(*nbytesp, nbytes); + return 0; } @@ -979,15 +998,13 @@ static ssize_t fuse_direct_io(struct file *file, const char __user *buf, while (count) { size_t nres; - size_t nbytes_limit = min(count, nmax); - size_t nbytes; - int err = fuse_get_user_pages(req, buf, nbytes_limit, !write); + size_t nbytes = min(count, nmax); + int err = fuse_get_user_pages(req, buf, &nbytes, write); if (err) { res = err; break; } - nbytes = (req->num_pages << PAGE_SHIFT) - req->page_offset; - nbytes = min(nbytes_limit, nbytes); + if (write) nres = fuse_send_write(req, file, inode, pos, nbytes, current->files); @@ -1163,6 +1180,7 @@ static int fuse_writepage_locked(struct page *page) fuse_write_fill(req, NULL, ff, inode, page_offset(page), 0, 1); copy_highpage(tmp_page, page); + req->in.argpages = 1; req->num_pages = 1; req->pages[0] = tmp_page; req->page_offset = 0; @@ -1274,6 +1292,15 @@ static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma) return 0; } +static int fuse_direct_mmap(struct file *file, struct vm_area_struct *vma) +{ + /* Can't provide the coherency needed for MAP_SHARED */ + if (vma->vm_flags & VM_MAYSHARE) + return -ENODEV; + + return generic_file_mmap(file, vma); +} + static int convert_fuse_file_lock(const struct fuse_file_lock *ffl, struct file_lock *fl) { @@ -1908,6 +1935,7 @@ static const struct file_operations fuse_direct_io_file_operations = { .llseek = fuse_file_llseek, .read = fuse_direct_read, .write = fuse_direct_write, + .mmap = fuse_direct_mmap, .open = fuse_open, .flush = fuse_flush, .release = fuse_release, @@ -1917,7 +1945,7 @@ static const struct file_operations fuse_direct_io_file_operations = { .unlocked_ioctl = fuse_file_ioctl, .compat_ioctl = fuse_file_compat_ioctl, .poll = fuse_file_poll, - /* no mmap and splice_read */ + /* no splice_read */ }; static const struct address_space_operations fuse_file_aops = { diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index 19e3a96aa02c..678a067d9251 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -294,6 +294,55 @@ static struct ocfs2_extent_tree_operations ocfs2_xattr_tree_et_ops = { .eo_fill_max_leaf_clusters = ocfs2_xattr_tree_fill_max_leaf_clusters, }; +static void ocfs2_dx_root_set_last_eb_blk(struct ocfs2_extent_tree *et, + u64 blkno) +{ + struct ocfs2_dx_root_block *dx_root = et->et_object; + + dx_root->dr_last_eb_blk = cpu_to_le64(blkno); +} + +static u64 ocfs2_dx_root_get_last_eb_blk(struct ocfs2_extent_tree *et) +{ + struct ocfs2_dx_root_block *dx_root = et->et_object; + + return le64_to_cpu(dx_root->dr_last_eb_blk); +} + +static void ocfs2_dx_root_update_clusters(struct inode *inode, + struct ocfs2_extent_tree *et, + u32 clusters) +{ + struct ocfs2_dx_root_block *dx_root = et->et_object; + + le32_add_cpu(&dx_root->dr_clusters, clusters); +} + +static int ocfs2_dx_root_sanity_check(struct inode *inode, + struct ocfs2_extent_tree *et) +{ + struct ocfs2_dx_root_block *dx_root = et->et_object; + + BUG_ON(!OCFS2_IS_VALID_DX_ROOT(dx_root)); + + return 0; +} + +static void ocfs2_dx_root_fill_root_el(struct ocfs2_extent_tree *et) +{ + struct ocfs2_dx_root_block *dx_root = et->et_object; + + et->et_root_el = &dx_root->dr_list; +} + +static struct ocfs2_extent_tree_operations ocfs2_dx_root_et_ops = { + .eo_set_last_eb_blk = ocfs2_dx_root_set_last_eb_blk, + .eo_get_last_eb_blk = ocfs2_dx_root_get_last_eb_blk, + .eo_update_clusters = ocfs2_dx_root_update_clusters, + .eo_sanity_check = ocfs2_dx_root_sanity_check, + .eo_fill_root_el = ocfs2_dx_root_fill_root_el, +}; + static void __ocfs2_init_extent_tree(struct ocfs2_extent_tree *et, struct inode *inode, struct buffer_head *bh, @@ -339,6 +388,14 @@ void ocfs2_init_xattr_value_extent_tree(struct ocfs2_extent_tree *et, &ocfs2_xattr_value_et_ops); } +void ocfs2_init_dx_root_extent_tree(struct ocfs2_extent_tree *et, + struct inode *inode, + struct buffer_head *bh) +{ + __ocfs2_init_extent_tree(et, inode, bh, ocfs2_journal_access_dr, + NULL, &ocfs2_dx_root_et_ops); +} + static inline void ocfs2_et_set_last_eb_blk(struct ocfs2_extent_tree *et, u64 new_last_eb_blk) { diff --git a/fs/ocfs2/alloc.h b/fs/ocfs2/alloc.h index cceff5c37f47..353254ba29e1 100644 --- a/fs/ocfs2/alloc.h +++ b/fs/ocfs2/alloc.h @@ -75,6 +75,9 @@ struct ocfs2_xattr_value_buf; void ocfs2_init_xattr_value_extent_tree(struct ocfs2_extent_tree *et, struct inode *inode, struct ocfs2_xattr_value_buf *vb); +void ocfs2_init_dx_root_extent_tree(struct ocfs2_extent_tree *et, + struct inode *inode, + struct buffer_head *bh); /* * Read an extent block into *bh. If *bh is NULL, a bh will be diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 8e1709a679b7..b2c52b3a1484 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -1956,15 +1956,16 @@ static int ocfs2_write_end(struct file *file, struct address_space *mapping, } const struct address_space_operations ocfs2_aops = { - .readpage = ocfs2_readpage, - .readpages = ocfs2_readpages, - .writepage = ocfs2_writepage, - .write_begin = ocfs2_write_begin, - .write_end = ocfs2_write_end, - .bmap = ocfs2_bmap, - .sync_page = block_sync_page, - .direct_IO = ocfs2_direct_IO, - .invalidatepage = ocfs2_invalidatepage, - .releasepage = ocfs2_releasepage, - .migratepage = buffer_migrate_page, + .readpage = ocfs2_readpage, + .readpages = ocfs2_readpages, + .writepage = ocfs2_writepage, + .write_begin = ocfs2_write_begin, + .write_end = ocfs2_write_end, + .bmap = ocfs2_bmap, + .sync_page = block_sync_page, + .direct_IO = ocfs2_direct_IO, + .invalidatepage = ocfs2_invalidatepage, + .releasepage = ocfs2_releasepage, + .migratepage = buffer_migrate_page, + .is_partially_uptodate = block_is_partially_uptodate, }; diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 04697ba7f73e..4f85eceab376 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -33,6 +33,7 @@ #include <linux/random.h> #include <linux/crc32.h> #include <linux/time.h> +#include <linux/debugfs.h> #include "heartbeat.h" #include "tcp.h" @@ -60,6 +61,11 @@ static unsigned long o2hb_live_node_bitmap[BITS_TO_LONGS(O2NM_MAX_NODES)]; static LIST_HEAD(o2hb_node_events); static DECLARE_WAIT_QUEUE_HEAD(o2hb_steady_queue); +#define O2HB_DEBUG_DIR "o2hb" +#define O2HB_DEBUG_LIVENODES "livenodes" +static struct dentry *o2hb_debug_dir; +static struct dentry *o2hb_debug_livenodes; + static LIST_HEAD(o2hb_all_regions); static struct o2hb_callback { @@ -905,7 +911,77 @@ static int o2hb_thread(void *data) return 0; } -void o2hb_init(void) +#ifdef CONFIG_DEBUG_FS +static int o2hb_debug_open(struct inode *inode, struct file *file) +{ + unsigned long map[BITS_TO_LONGS(O2NM_MAX_NODES)]; + char *buf = NULL; + int i = -1; + int out = 0; + + buf = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!buf) + goto bail; + + o2hb_fill_node_map(map, sizeof(map)); + + while ((i = find_next_bit(map, O2NM_MAX_NODES, i + 1)) < O2NM_MAX_NODES) + out += snprintf(buf + out, PAGE_SIZE - out, "%d ", i); + out += snprintf(buf + out, PAGE_SIZE - out, "\n"); + + i_size_write(inode, out); + + file->private_data = buf; + + return 0; +bail: + return -ENOMEM; +} + +static int o2hb_debug_release(struct inode *inode, struct file *file) +{ + kfree(file->private_data); + return 0; +} + +static ssize_t o2hb_debug_read(struct file *file, char __user *buf, + size_t nbytes, loff_t *ppos) +{ + return simple_read_from_buffer(buf, nbytes, ppos, file->private_data, + i_size_read(file->f_mapping->host)); +} +#else +static int o2hb_debug_open(struct inode *inode, struct file *file) +{ + return 0; +} +static int o2hb_debug_release(struct inode *inode, struct file *file) +{ + return 0; +} +static ssize_t o2hb_debug_read(struct file *file, char __user *buf, + size_t nbytes, loff_t *ppos) +{ + return 0; +} +#endif /* CONFIG_DEBUG_FS */ + +static struct file_operations o2hb_debug_fops = { + .open = o2hb_debug_open, + .release = o2hb_debug_release, + .read = o2hb_debug_read, + .llseek = generic_file_llseek, +}; + +void o2hb_exit(void) +{ + if (o2hb_debug_livenodes) + debugfs_remove(o2hb_debug_livenodes); + if (o2hb_debug_dir) + debugfs_remove(o2hb_debug_dir); +} + +int o2hb_init(void) { int i; @@ -918,6 +994,24 @@ void o2hb_init(void) INIT_LIST_HEAD(&o2hb_node_events); memset(o2hb_live_node_bitmap, 0, sizeof(o2hb_live_node_bitmap)); + + o2hb_debug_dir = debugfs_create_dir(O2HB_DEBUG_DIR, NULL); + if (!o2hb_debug_dir) { + mlog_errno(-ENOMEM); + return -ENOMEM; + } + + o2hb_debug_livenodes = debugfs_create_file(O2HB_DEBUG_LIVENODES, + S_IFREG|S_IRUSR, + o2hb_debug_dir, NULL, + &o2hb_debug_fops); + if (!o2hb_debug_livenodes) { + mlog_errno(-ENOMEM); + debugfs_remove(o2hb_debug_dir); + return -ENOMEM; + } + + return 0; } /* if we're already in a callback then we're already serialized by the sem */ diff --git a/fs/ocfs2/cluster/heartbeat.h b/fs/ocfs2/cluster/heartbeat.h index e511339886b3..2f1649253b49 100644 --- a/fs/ocfs2/cluster/heartbeat.h +++ b/fs/ocfs2/cluster/heartbeat.h @@ -75,7 +75,8 @@ void o2hb_unregister_callback(const char *region_uuid, struct o2hb_callback_func *hc); void o2hb_fill_node_map(unsigned long *map, unsigned bytes); -void o2hb_init(void); +void o2hb_exit(void); +int o2hb_init(void); int o2hb_check_node_heartbeating(u8 node_num); int o2hb_check_node_heartbeating_from_callback(u8 node_num); int o2hb_check_local_node_heartbeating(void); diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c index 70e8fa9e2539..7ee6188bc79a 100644 --- a/fs/ocfs2/cluster/nodemanager.c +++ b/fs/ocfs2/cluster/nodemanager.c @@ -881,6 +881,7 @@ static void __exit exit_o2nm(void) o2cb_sys_shutdown(); o2net_exit(); + o2hb_exit(); } static int __init init_o2nm(void) @@ -889,11 +890,13 @@ static int __init init_o2nm(void) cluster_print_version(); - o2hb_init(); + ret = o2hb_init(); + if (ret) + goto out; ret = o2net_init(); if (ret) - goto out; + goto out_o2hb; ret = o2net_register_hb_callbacks(); if (ret) @@ -916,6 +919,8 @@ out_callbacks: o2net_unregister_hb_callbacks(); out_o2net: o2net_exit(); +out_o2hb: + o2hb_exit(); out: return ret; } diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index f2c4098cf337..e71160cda110 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -41,6 +41,7 @@ #include <linux/slab.h> #include <linux/highmem.h> #include <linux/quotaops.h> +#include <linux/sort.h> #define MLOG_MASK_PREFIX ML_NAMEI #include <cluster/masklog.h> @@ -58,6 +59,7 @@ #include "namei.h" #include "suballoc.h" #include "super.h" +#include "sysfile.h" #include "uptodate.h" #include "buffer_head_io.h" @@ -71,11 +73,6 @@ static unsigned char ocfs2_filetype_table[] = { DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK }; -static int ocfs2_extend_dir(struct ocfs2_super *osb, - struct inode *dir, - struct buffer_head *parent_fe_bh, - unsigned int blocks_wanted, - struct buffer_head **new_de_bh); static int ocfs2_do_extend_dir(struct super_block *sb, handle_t *handle, struct inode *dir, @@ -83,22 +80,36 @@ static int ocfs2_do_extend_dir(struct super_block *sb, struct ocfs2_alloc_context *data_ac, struct ocfs2_alloc_context *meta_ac, struct buffer_head **new_bh); +static int ocfs2_dir_indexed(struct inode *inode); /* * These are distinct checks because future versions of the file system will * want to have a trailing dirent structure independent of indexing. */ -static int ocfs2_dir_has_trailer(struct inode *dir) +static int ocfs2_supports_dir_trailer(struct inode *dir) { + struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); + if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) return 0; - return ocfs2_meta_ecc(OCFS2_SB(dir->i_sb)); + return ocfs2_meta_ecc(osb) || ocfs2_dir_indexed(dir); } -static int ocfs2_supports_dir_trailer(struct ocfs2_super *osb) +/* + * "new' here refers to the point at which we're creating a new + * directory via "mkdir()", but also when we're expanding an inline + * directory. In either case, we don't yet have the indexing bit set + * on the directory, so the standard checks will fail in when metaecc + * is turned off. Only directory-initialization type functions should + * use this then. Everything else wants ocfs2_supports_dir_trailer() + */ +static int ocfs2_new_dir_wants_trailer(struct inode *dir) { - return ocfs2_meta_ecc(osb); + struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); + + return ocfs2_meta_ecc(osb) || + ocfs2_supports_indexed_dirs(osb); } static inline unsigned int ocfs2_dir_trailer_blk_off(struct super_block *sb) @@ -130,7 +141,7 @@ static int ocfs2_skip_dir_trailer(struct inode *dir, { unsigned long toff = blklen - sizeof(struct ocfs2_dir_block_trailer); - if (!ocfs2_dir_has_trailer(dir)) + if (!ocfs2_supports_dir_trailer(dir)) return 0; if (offset != toff) @@ -140,7 +151,7 @@ static int ocfs2_skip_dir_trailer(struct inode *dir, } static void ocfs2_init_dir_trailer(struct inode *inode, - struct buffer_head *bh) + struct buffer_head *bh, u16 rec_len) { struct ocfs2_dir_block_trailer *trailer; @@ -150,6 +161,153 @@ static void ocfs2_init_dir_trailer(struct inode *inode, cpu_to_le16(sizeof(struct ocfs2_dir_block_trailer)); trailer->db_parent_dinode = cpu_to_le64(OCFS2_I(inode)->ip_blkno); trailer->db_blkno = cpu_to_le64(bh->b_blocknr); + trailer->db_free_rec_len = cpu_to_le16(rec_len); +} +/* + * Link an unindexed block with a dir trailer structure into the index free + * list. This function will modify dirdata_bh, but assumes you've already + * passed it to the journal. + */ +static int ocfs2_dx_dir_link_trailer(struct inode *dir, handle_t *handle, + struct buffer_head *dx_root_bh, + struct buffer_head *dirdata_bh) +{ + int ret; + struct ocfs2_dx_root_block *dx_root; + struct ocfs2_dir_block_trailer *trailer; + + ret = ocfs2_journal_access_dr(handle, dir, dx_root_bh, + OCFS2_JOURNAL_ACCESS_WRITE); + if (ret) { + mlog_errno(ret); + goto out; + } + trailer = ocfs2_trailer_from_bh(dirdata_bh, dir->i_sb); + dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data; + + trailer->db_free_next = dx_root->dr_free_blk; + dx_root->dr_free_blk = cpu_to_le64(dirdata_bh->b_blocknr); + + ocfs2_journal_dirty(handle, dx_root_bh); + +out: + return ret; +} + +static int ocfs2_free_list_at_root(struct ocfs2_dir_lookup_result *res) +{ + return res->dl_prev_leaf_bh == NULL; +} + +void ocfs2_free_dir_lookup_result(struct ocfs2_dir_lookup_result *res) +{ + brelse(res->dl_dx_root_bh); + brelse(res->dl_leaf_bh); + brelse(res->dl_dx_leaf_bh); + brelse(res->dl_prev_leaf_bh); +} + +static int ocfs2_dir_indexed(struct inode *inode) +{ + if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INDEXED_DIR_FL) + return 1; + return 0; +} + +static inline int ocfs2_dx_root_inline(struct ocfs2_dx_root_block *dx_root) +{ + return dx_root->dr_flags & OCFS2_DX_FLAG_INLINE; +} + +/* + * Hashing code adapted from ext3 + */ +#define DELTA 0x9E3779B9 + +static void TEA_transform(__u32 buf[4], __u32 const in[]) +{ + __u32 sum = 0; + __u32 b0 = buf[0], b1 = buf[1]; + __u32 a = in[0], b = in[1], c = in[2], d = in[3]; + int n = 16; + + do { + sum += DELTA; + b0 += ((b1 << 4)+a) ^ (b1+sum) ^ ((b1 >> 5)+b); + b1 += ((b0 << 4)+c) ^ (b0+sum) ^ ((b0 >> 5)+d); + } while (--n); + + buf[0] += b0; + buf[1] += b1; +} + +static void str2hashbuf(const char *msg, int len, __u32 *buf, int num) +{ + __u32 pad, val; + int i; + + pad = (__u32)len | ((__u32)len << 8); + pad |= pad << 16; + + val = pad; + if (len > num*4) + len = num * 4; + for (i = 0; i < len; i++) { + if ((i % 4) == 0) + val = pad; + val = msg[i] + (val << 8); + if ((i % 4) == 3) { + *buf++ = val; + val = pad; + num--; + } + } + if (--num >= 0) + *buf++ = val; + while (--num >= 0) + *buf++ = pad; +} + +static void ocfs2_dx_dir_name_hash(struct inode *dir, const char *name, int len, + struct ocfs2_dx_hinfo *hinfo) +{ + struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); + const char *p; + __u32 in[8], buf[4]; + + /* + * XXX: Is this really necessary, if the index is never looked + * at by readdir? Is a hash value of '0' a bad idea? + */ + if ((len == 1 && !strncmp(".", name, 1)) || + (len == 2 && !strncmp("..", name, 2))) { + buf[0] = buf[1] = 0; + goto out; + } + +#ifdef OCFS2_DEBUG_DX_DIRS + /* + * This makes it very easy to debug indexing problems. We + * should never allow this to be selected without hand editing + * this file though. + */ + buf[0] = buf[1] = len; + goto out; +#endif + + memcpy(buf, osb->osb_dx_seed, sizeof(buf)); + + p = name; + while (len > 0) { + str2hashbuf(p, len, in, 4); + TEA_transform(buf, in); + len -= 16; + p += 16; + } + +out: + hinfo->major_hash = buf[0]; + hinfo->minor_hash = buf[1]; } /* @@ -312,6 +470,52 @@ static int ocfs2_validate_dir_block(struct super_block *sb, } /* + * Validate a directory trailer. + * + * We check the trailer here rather than in ocfs2_validate_dir_block() + * because that function doesn't have the inode to test. + */ +static int ocfs2_check_dir_trailer(struct inode *dir, struct buffer_head *bh) +{ + int rc = 0; + struct ocfs2_dir_block_trailer *trailer; + + trailer = ocfs2_trailer_from_bh(bh, dir->i_sb); + if (!OCFS2_IS_VALID_DIR_TRAILER(trailer)) { + rc = -EINVAL; + ocfs2_error(dir->i_sb, + "Invalid dirblock #%llu: " + "signature = %.*s\n", + (unsigned long long)bh->b_blocknr, 7, + trailer->db_signature); + goto out; + } + if (le64_to_cpu(trailer->db_blkno) != bh->b_blocknr) { + rc = -EINVAL; + ocfs2_error(dir->i_sb, + "Directory block #%llu has an invalid " + "db_blkno of %llu", + (unsigned long long)bh->b_blocknr, + (unsigned long long)le64_to_cpu(trailer->db_blkno)); + goto out; + } + if (le64_to_cpu(trailer->db_parent_dinode) != + OCFS2_I(dir)->ip_blkno) { + rc = -EINVAL; + ocfs2_error(dir->i_sb, + "Directory block #%llu on dinode " + "#%llu has an invalid parent_dinode " + "of %llu", + (unsigned long long)bh->b_blocknr, + (unsigned long long)OCFS2_I(dir)->ip_blkno, + (unsigned long long)le64_to_cpu(trailer->db_blkno)); + goto out; + } +out: + return rc; +} + +/* * This function forces all errors to -EIO for consistency with its * predecessor, ocfs2_bread(). We haven't audited what returning the * real error codes would do to callers. We log the real codes with @@ -322,7 +526,6 @@ static int ocfs2_read_dir_block(struct inode *inode, u64 v_block, { int rc = 0; struct buffer_head *tmp = *bh; - struct ocfs2_dir_block_trailer *trailer; rc = ocfs2_read_virt_blocks(inode, v_block, 1, &tmp, flags, ocfs2_validate_dir_block); @@ -331,42 +534,13 @@ static int ocfs2_read_dir_block(struct inode *inode, u64 v_block, goto out; } - /* - * We check the trailer here rather than in - * ocfs2_validate_dir_block() because that function doesn't have - * the inode to test. - */ if (!(flags & OCFS2_BH_READAHEAD) && - ocfs2_dir_has_trailer(inode)) { - trailer = ocfs2_trailer_from_bh(tmp, inode->i_sb); - if (!OCFS2_IS_VALID_DIR_TRAILER(trailer)) { - rc = -EINVAL; - ocfs2_error(inode->i_sb, - "Invalid dirblock #%llu: " - "signature = %.*s\n", - (unsigned long long)tmp->b_blocknr, 7, - trailer->db_signature); - goto out; - } - if (le64_to_cpu(trailer->db_blkno) != tmp->b_blocknr) { - rc = -EINVAL; - ocfs2_error(inode->i_sb, - "Directory block #%llu has an invalid " - "db_blkno of %llu", - (unsigned long long)tmp->b_blocknr, - (unsigned long long)le64_to_cpu(trailer->db_blkno)); - goto out; - } - if (le64_to_cpu(trailer->db_parent_dinode) != - OCFS2_I(inode)->ip_blkno) { - rc = -EINVAL; - ocfs2_error(inode->i_sb, - "Directory block #%llu on dinode " - "#%llu has an invalid parent_dinode " - "of %llu", - (unsigned long long)tmp->b_blocknr, - (unsigned long long)OCFS2_I(inode)->ip_blkno, - (unsigned long long)le64_to_cpu(trailer->db_blkno)); + ocfs2_supports_dir_trailer(inode)) { + rc = ocfs2_check_dir_trailer(inode, tmp); + if (rc) { + if (!*bh) + brelse(tmp); + mlog_errno(rc); goto out; } } @@ -379,6 +553,141 @@ out: return rc ? -EIO : 0; } +/* + * Read the block at 'phys' which belongs to this directory + * inode. This function does no virtual->physical block translation - + * what's passed in is assumed to be a valid directory block. + */ +static int ocfs2_read_dir_block_direct(struct inode *dir, u64 phys, + struct buffer_head **bh) +{ + int ret; + struct buffer_head *tmp = *bh; + + ret = ocfs2_read_block(dir, phys, &tmp, ocfs2_validate_dir_block); + if (ret) { + mlog_errno(ret); + goto out; + } + + if (ocfs2_supports_dir_trailer(dir)) { + ret = ocfs2_check_dir_trailer(dir, tmp); + if (ret) { + if (!*bh) + brelse(tmp); + mlog_errno(ret); + goto out; + } + } + + if (!ret && !*bh) + *bh = tmp; +out: + return ret; +} + +static int ocfs2_validate_dx_root(struct super_block *sb, + struct buffer_head *bh) +{ + int ret; + struct ocfs2_dx_root_block *dx_root; + + BUG_ON(!buffer_uptodate(bh)); + + dx_root = (struct ocfs2_dx_root_block *) bh->b_data; + + ret = ocfs2_validate_meta_ecc(sb, bh->b_data, &dx_root->dr_check); + if (ret) { + mlog(ML_ERROR, + "Checksum failed for dir index root block %llu\n", + (unsigned long long)bh->b_blocknr); + return ret; + } + + if (!OCFS2_IS_VALID_DX_ROOT(dx_root)) { + ocfs2_error(sb, + "Dir Index Root # %llu has bad signature %.*s", + (unsigned long long)le64_to_cpu(dx_root->dr_blkno), + 7, dx_root->dr_signature); + return -EINVAL; + } + + return 0; +} + +static int ocfs2_read_dx_root(struct inode *dir, struct ocfs2_dinode *di, + struct buffer_head **dx_root_bh) +{ + int ret; + u64 blkno = le64_to_cpu(di->i_dx_root); + struct buffer_head *tmp = *dx_root_bh; + + ret = ocfs2_read_block(dir, blkno, &tmp, ocfs2_validate_dx_root); + + /* If ocfs2_read_block() got us a new bh, pass it up. */ + if (!ret && !*dx_root_bh) + *dx_root_bh = tmp; + + return ret; +} + +static int ocfs2_validate_dx_leaf(struct super_block *sb, + struct buffer_head *bh) +{ + int ret; + struct ocfs2_dx_leaf *dx_leaf = (struct ocfs2_dx_leaf *)bh->b_data; + + BUG_ON(!buffer_uptodate(bh)); + + ret = ocfs2_validate_meta_ecc(sb, bh->b_data, &dx_leaf->dl_check); + if (ret) { + mlog(ML_ERROR, + "Checksum failed for dir index leaf block %llu\n", + (unsigned long long)bh->b_blocknr); + return ret; + } + + if (!OCFS2_IS_VALID_DX_LEAF(dx_leaf)) { + ocfs2_error(sb, "Dir Index Leaf has bad signature %.*s", + 7, dx_leaf->dl_signature); + return -EROFS; + } + + return 0; +} + +static int ocfs2_read_dx_leaf(struct inode *dir, u64 blkno, + struct buffer_head **dx_leaf_bh) +{ + int ret; + struct buffer_head *tmp = *dx_leaf_bh; + + ret = ocfs2_read_block(dir, blkno, &tmp, ocfs2_validate_dx_leaf); + + /* If ocfs2_read_block() got us a new bh, pass it up. */ + if (!ret && !*dx_leaf_bh) + *dx_leaf_bh = tmp; + + return ret; +} + +/* + * Read a series of dx_leaf blocks. This expects all buffer_head + * pointers to be NULL on function entry. + */ +static int ocfs2_read_dx_leaves(struct inode *dir, u64 start, int num, + struct buffer_head **dx_leaf_bhs) +{ + int ret; + + ret = ocfs2_read_blocks(dir, start, num, dx_leaf_bhs, 0, + ocfs2_validate_dx_leaf); + if (ret) + mlog_errno(ret); + + return ret; +} + static struct buffer_head *ocfs2_find_entry_el(const char *name, int namelen, struct inode *dir, struct ocfs2_dir_entry **res_dir) @@ -480,39 +789,340 @@ cleanup_and_exit: return ret; } +static int ocfs2_dx_dir_lookup_rec(struct inode *inode, + struct ocfs2_extent_list *el, + u32 major_hash, + u32 *ret_cpos, + u64 *ret_phys_blkno, + unsigned int *ret_clen) +{ + int ret = 0, i, found; + struct buffer_head *eb_bh = NULL; + struct ocfs2_extent_block *eb; + struct ocfs2_extent_rec *rec = NULL; + + if (el->l_tree_depth) { + ret = ocfs2_find_leaf(inode, el, major_hash, &eb_bh); + if (ret) { + mlog_errno(ret); + goto out; + } + + eb = (struct ocfs2_extent_block *) eb_bh->b_data; + el = &eb->h_list; + + if (el->l_tree_depth) { + ocfs2_error(inode->i_sb, + "Inode %lu has non zero tree depth in " + "btree tree block %llu\n", inode->i_ino, + (unsigned long long)eb_bh->b_blocknr); + ret = -EROFS; + goto out; + } + } + + found = 0; + for (i = le16_to_cpu(el->l_next_free_rec) - 1; i >= 0; i--) { + rec = &el->l_recs[i]; + + if (le32_to_cpu(rec->e_cpos) <= major_hash) { + found = 1; + break; + } + } + + if (!found) { + ocfs2_error(inode->i_sb, "Inode %lu has bad extent " + "record (%u, %u, 0) in btree", inode->i_ino, + le32_to_cpu(rec->e_cpos), + ocfs2_rec_clusters(el, rec)); + ret = -EROFS; + goto out; + } + + if (ret_phys_blkno) + *ret_phys_blkno = le64_to_cpu(rec->e_blkno); + if (ret_cpos) + *ret_cpos = le32_to_cpu(rec->e_cpos); + if (ret_clen) + *ret_clen = le16_to_cpu(rec->e_leaf_clusters); + +out: + brelse(eb_bh); + return ret; +} + +/* + * Returns the block index, from the start of the cluster which this + * hash belongs too. + */ +static inline unsigned int __ocfs2_dx_dir_hash_idx(struct ocfs2_super *osb, + u32 minor_hash) +{ + return minor_hash & osb->osb_dx_mask; +} + +static inline unsigned int ocfs2_dx_dir_hash_idx(struct ocfs2_super *osb, + struct ocfs2_dx_hinfo *hinfo) +{ + return __ocfs2_dx_dir_hash_idx(osb, hinfo->minor_hash); +} + +static int ocfs2_dx_dir_lookup(struct inode *inode, + struct ocfs2_extent_list *el, + struct ocfs2_dx_hinfo *hinfo, + u32 *ret_cpos, + u64 *ret_phys_blkno) +{ + int ret = 0; + unsigned int cend, uninitialized_var(clen); + u32 uninitialized_var(cpos); + u64 uninitialized_var(blkno); + u32 name_hash = hinfo->major_hash; + + ret = ocfs2_dx_dir_lookup_rec(inode, el, name_hash, &cpos, &blkno, + &clen); + if (ret) { + mlog_errno(ret); + goto out; + } + + cend = cpos + clen; + if (name_hash >= cend) { + /* We want the last cluster */ + blkno += ocfs2_clusters_to_blocks(inode->i_sb, clen - 1); + cpos += clen - 1; + } else { + blkno += ocfs2_clusters_to_blocks(inode->i_sb, + name_hash - cpos); + cpos = name_hash; + } + + /* + * We now have the cluster which should hold our entry. To + * find the exact block from the start of the cluster to + * search, we take the lower bits of the hash. + */ + blkno += ocfs2_dx_dir_hash_idx(OCFS2_SB(inode->i_sb), hinfo); + + if (ret_phys_blkno) + *ret_phys_blkno = blkno; + if (ret_cpos) + *ret_cpos = cpos; + +out: + + return ret; +} + +static int ocfs2_dx_dir_search(const char *name, int namelen, + struct inode *dir, + struct ocfs2_dx_root_block *dx_root, + struct ocfs2_dir_lookup_result *res) +{ + int ret, i, found; + u64 uninitialized_var(phys); + struct buffer_head *dx_leaf_bh = NULL; + struct ocfs2_dx_leaf *dx_leaf; + struct ocfs2_dx_entry *dx_entry = NULL; + struct buffer_head *dir_ent_bh = NULL; + struct ocfs2_dir_entry *dir_ent = NULL; + struct ocfs2_dx_hinfo *hinfo = &res->dl_hinfo; + struct ocfs2_extent_list *dr_el; + struct ocfs2_dx_entry_list *entry_list; + + ocfs2_dx_dir_name_hash(dir, name, namelen, &res->dl_hinfo); + + if (ocfs2_dx_root_inline(dx_root)) { + entry_list = &dx_root->dr_entries; + goto search; + } + + dr_el = &dx_root->dr_list; + + ret = ocfs2_dx_dir_lookup(dir, dr_el, hinfo, NULL, &phys); + if (ret) { + mlog_errno(ret); + goto out; + } + + mlog(0, "Dir %llu: name: \"%.*s\", lookup of hash: %u.0x%x " + "returns: %llu\n", + (unsigned long long)OCFS2_I(dir)->ip_blkno, + namelen, name, hinfo->major_hash, hinfo->minor_hash, + (unsigned long long)phys); + + ret = ocfs2_read_dx_leaf(dir, phys, &dx_leaf_bh); + if (ret) { + mlog_errno(ret); + goto out; + } + + dx_leaf = (struct ocfs2_dx_leaf *) dx_leaf_bh->b_data; + + mlog(0, "leaf info: num_used: %d, count: %d\n", + le16_to_cpu(dx_leaf->dl_list.de_num_used), + le16_to_cpu(dx_leaf->dl_list.de_count)); + + entry_list = &dx_leaf->dl_list; + +search: + /* + * Empty leaf is legal, so no need to check for that. + */ + found = 0; + for (i = 0; i < le16_to_cpu(entry_list->de_num_used); i++) { + dx_entry = &entry_list->de_entries[i]; + + if (hinfo->major_hash != le32_to_cpu(dx_entry->dx_major_hash) + || hinfo->minor_hash != le32_to_cpu(dx_entry->dx_minor_hash)) + continue; + + /* + * Search unindexed leaf block now. We're not + * guaranteed to find anything. + */ + ret = ocfs2_read_dir_block_direct(dir, + le64_to_cpu(dx_entry->dx_dirent_blk), + &dir_ent_bh); + if (ret) { + mlog_errno(ret); + goto out; + } + + /* + * XXX: We should check the unindexed block here, + * before using it. + */ + + found = ocfs2_search_dirblock(dir_ent_bh, dir, name, namelen, + 0, dir_ent_bh->b_data, + dir->i_sb->s_blocksize, &dir_ent); + if (found == 1) + break; + + if (found == -1) { + /* This means we found a bad directory entry. */ + ret = -EIO; + mlog_errno(ret); + goto out; + } + + brelse(dir_ent_bh); + dir_ent_bh = NULL; + } + + if (found <= 0) { + ret = -ENOENT; + goto out; + } + + res->dl_leaf_bh = dir_ent_bh; + res->dl_entry = dir_ent; + res->dl_dx_leaf_bh = dx_leaf_bh; + res->dl_dx_entry = dx_entry; + + ret = 0; +out: + if (ret) { + brelse(dx_leaf_bh); + brelse(dir_ent_bh); + } + return ret; +} + +static int ocfs2_find_entry_dx(const char *name, int namelen, + struct inode *dir, + struct ocfs2_dir_lookup_result *lookup) +{ + int ret; + struct buffer_head *di_bh = NULL; + struct ocfs2_dinode *di; + struct buffer_head *dx_root_bh = NULL; + struct ocfs2_dx_root_block *dx_root; + + ret = ocfs2_read_inode_block(dir, &di_bh); + if (ret) { + mlog_errno(ret); + goto out; + } + + di = (struct ocfs2_dinode *)di_bh->b_data; + + ret = ocfs2_read_dx_root(dir, di, &dx_root_bh); + if (ret) { + mlog_errno(ret); + goto out; + } + dx_root = (struct ocfs2_dx_root_block *) dx_root_bh->b_data; + + ret = ocfs2_dx_dir_search(name, namelen, dir, dx_root, lookup); + if (ret) { + if (ret != -ENOENT) + mlog_errno(ret); + goto out; + } + + lookup->dl_dx_root_bh = dx_root_bh; + dx_root_bh = NULL; +out: + brelse(di_bh); + brelse(dx_root_bh); + return ret; +} + /* * Try to find an entry of the provided name within 'dir'. * - * If nothing was found, NULL is returned. Otherwise, a buffer_head - * and pointer to the dir entry are passed back. + * If nothing was found, -ENOENT is returned. Otherwise, zero is + * returned and the struct 'res' will contain information useful to + * other directory manipulation functions. * * Caller can NOT assume anything about the contents of the - * buffer_head - it is passed back only so that it can be passed into - * any one of the manipulation functions (add entry, delete entry, - * etc). As an example, bh in the extent directory case is a data - * block, in the inline-data case it actually points to an inode. + * buffer_heads - they are passed back only so that it can be passed + * into any one of the manipulation functions (add entry, delete + * entry, etc). As an example, bh in the extent directory case is a + * data block, in the inline-data case it actually points to an inode, + * in the indexed directory case, multiple buffers are involved. */ -struct buffer_head *ocfs2_find_entry(const char *name, int namelen, - struct inode *dir, - struct ocfs2_dir_entry **res_dir) +int ocfs2_find_entry(const char *name, int namelen, + struct inode *dir, struct ocfs2_dir_lookup_result *lookup) { - *res_dir = NULL; + struct buffer_head *bh; + struct ocfs2_dir_entry *res_dir = NULL; + if (ocfs2_dir_indexed(dir)) + return ocfs2_find_entry_dx(name, namelen, dir, lookup); + + /* + * The unindexed dir code only uses part of the lookup + * structure, so there's no reason to push it down further + * than this. + */ if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) - return ocfs2_find_entry_id(name, namelen, dir, res_dir); + bh = ocfs2_find_entry_id(name, namelen, dir, &res_dir); + else + bh = ocfs2_find_entry_el(name, namelen, dir, &res_dir); + + if (bh == NULL) + return -ENOENT; - return ocfs2_find_entry_el(name, namelen, dir, res_dir); + lookup->dl_leaf_bh = bh; + lookup->dl_entry = res_dir; + return 0; } /* * Update inode number and type of a previously found directory entry. */ int ocfs2_update_entry(struct inode *dir, handle_t *handle, - struct buffer_head *de_bh, struct ocfs2_dir_entry *de, + struct ocfs2_dir_lookup_result *res, struct inode *new_entry_inode) { int ret; ocfs2_journal_access_func access = ocfs2_journal_access_db; + struct ocfs2_dir_entry *de = res->dl_entry; + struct buffer_head *de_bh = res->dl_leaf_bh; /* * The same code works fine for both inline-data and extent @@ -538,6 +1148,10 @@ out: return ret; } +/* + * __ocfs2_delete_entry deletes a directory entry by merging it with the + * previous entry + */ static int __ocfs2_delete_entry(handle_t *handle, struct inode *dir, struct ocfs2_dir_entry *de_del, struct buffer_head *bh, char *first_de, @@ -587,6 +1201,181 @@ bail: return status; } +static unsigned int ocfs2_figure_dirent_hole(struct ocfs2_dir_entry *de) +{ + unsigned int hole; + + if (le64_to_cpu(de->inode) == 0) + hole = le16_to_cpu(de->rec_len); + else + hole = le16_to_cpu(de->rec_len) - + OCFS2_DIR_REC_LEN(de->name_len); + + return hole; +} + +static int ocfs2_find_max_rec_len(struct super_block *sb, + struct buffer_head *dirblock_bh) +{ + int size, this_hole, largest_hole = 0; + char *trailer, *de_buf, *limit, *start = dirblock_bh->b_data; + struct ocfs2_dir_entry *de; + + trailer = (char *)ocfs2_trailer_from_bh(dirblock_bh, sb); + size = ocfs2_dir_trailer_blk_off(sb); + limit = start + size; + de_buf = start; + de = (struct ocfs2_dir_entry *)de_buf; + do { + if (de_buf != trailer) { + this_hole = ocfs2_figure_dirent_hole(de); + if (this_hole > largest_hole) + largest_hole = this_hole; + } + + de_buf += le16_to_cpu(de->rec_len); + de = (struct ocfs2_dir_entry *)de_buf; + } while (de_buf < limit); + + if (largest_hole >= OCFS2_DIR_MIN_REC_LEN) + return largest_hole; + return 0; +} + +static void ocfs2_dx_list_remove_entry(struct ocfs2_dx_entry_list *entry_list, + int index) +{ + int num_used = le16_to_cpu(entry_list->de_num_used); + + if (num_used == 1 || index == (num_used - 1)) + goto clear; + + memmove(&entry_list->de_entries[index], + &entry_list->de_entries[index + 1], + (num_used - index - 1)*sizeof(struct ocfs2_dx_entry)); +clear: + num_used--; + memset(&entry_list->de_entries[num_used], 0, + sizeof(struct ocfs2_dx_entry)); + entry_list->de_num_used = cpu_to_le16(num_used); +} + +static int ocfs2_delete_entry_dx(handle_t *handle, struct inode *dir, + struct ocfs2_dir_lookup_result *lookup) +{ + int ret, index, max_rec_len, add_to_free_list = 0; + struct buffer_head *dx_root_bh = lookup->dl_dx_root_bh; + struct buffer_head *leaf_bh = lookup->dl_leaf_bh; + struct ocfs2_dx_leaf *dx_leaf; + struct ocfs2_dx_entry *dx_entry = lookup->dl_dx_entry; + struct ocfs2_dir_block_trailer *trailer; + struct ocfs2_dx_root_block *dx_root; + struct ocfs2_dx_entry_list *entry_list; + + /* + * This function gets a bit messy because we might have to + * modify the root block, regardless of whether the indexed + * entries are stored inline. + */ + + /* + * *Only* set 'entry_list' here, based on where we're looking + * for the indexed entries. Later, we might still want to + * journal both blocks, based on free list state. + */ + dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data; + if (ocfs2_dx_root_inline(dx_root)) { + entry_list = &dx_root->dr_entries; + } else { + dx_leaf = (struct ocfs2_dx_leaf *) lookup->dl_dx_leaf_bh->b_data; + entry_list = &dx_leaf->dl_list; + } + + /* Neither of these are a disk corruption - that should have + * been caught by lookup, before we got here. */ + BUG_ON(le16_to_cpu(entry_list->de_count) <= 0); + BUG_ON(le16_to_cpu(entry_list->de_num_used) <= 0); + + index = (char *)dx_entry - (char *)entry_list->de_entries; + index /= sizeof(*dx_entry); + + if (index >= le16_to_cpu(entry_list->de_num_used)) { + mlog(ML_ERROR, "Dir %llu: Bad dx_entry ptr idx %d, (%p, %p)\n", + (unsigned long long)OCFS2_I(dir)->ip_blkno, index, + entry_list, dx_entry); + return -EIO; + } + + /* + * We know that removal of this dirent will leave enough room + * for a new one, so add this block to the free list if it + * isn't already there. + */ + trailer = ocfs2_trailer_from_bh(leaf_bh, dir->i_sb); + if (trailer->db_free_rec_len == 0) + add_to_free_list = 1; + + /* + * Add the block holding our index into the journal before + * removing the unindexed entry. If we get an error return + * from __ocfs2_delete_entry(), then it hasn't removed the + * entry yet. Likewise, successful return means we *must* + * remove the indexed entry. + * + * We're also careful to journal the root tree block here as + * the entry count needs to be updated. Also, we might be + * adding to the start of the free list. + */ + ret = ocfs2_journal_access_dr(handle, dir, dx_root_bh, + OCFS2_JOURNAL_ACCESS_WRITE); + if (ret) { + mlog_errno(ret); + goto out; + } + + if (!ocfs2_dx_root_inline(dx_root)) { + ret = ocfs2_journal_access_dl(handle, dir, + lookup->dl_dx_leaf_bh, + OCFS2_JOURNAL_ACCESS_WRITE); + if (ret) { + mlog_errno(ret); + goto out; + } + } + + mlog(0, "Dir %llu: delete entry at index: %d\n", + (unsigned long long)OCFS2_I(dir)->ip_blkno, index); + + ret = __ocfs2_delete_entry(handle, dir, lookup->dl_entry, + leaf_bh, leaf_bh->b_data, leaf_bh->b_size); + if (ret) { + mlog_errno(ret); + goto out; + } + + max_rec_len = ocfs2_find_max_rec_len(dir->i_sb, leaf_bh); + trailer->db_free_rec_len = cpu_to_le16(max_rec_len); + if (add_to_free_list) { + trailer->db_free_next = dx_root->dr_free_blk; + dx_root->dr_free_blk = cpu_to_le64(leaf_bh->b_blocknr); + ocfs2_journal_dirty(handle, dx_root_bh); + } + + /* leaf_bh was journal_accessed for us in __ocfs2_delete_entry */ + ocfs2_journal_dirty(handle, leaf_bh); + + le32_add_cpu(&dx_root->dr_num_entries, -1); + ocfs2_journal_dirty(handle, dx_root_bh); + + ocfs2_dx_list_remove_entry(entry_list, index); + + if (!ocfs2_dx_root_inline(dx_root)) + ocfs2_journal_dirty(handle, lookup->dl_dx_leaf_bh); + +out: + return ret; +} + static inline int ocfs2_delete_entry_id(handle_t *handle, struct inode *dir, struct ocfs2_dir_entry *de_del, @@ -624,18 +1413,22 @@ static inline int ocfs2_delete_entry_el(handle_t *handle, } /* - * ocfs2_delete_entry deletes a directory entry by merging it with the - * previous entry + * Delete a directory entry. Hide the details of directory + * implementation from the caller. */ int ocfs2_delete_entry(handle_t *handle, struct inode *dir, - struct ocfs2_dir_entry *de_del, - struct buffer_head *bh) + struct ocfs2_dir_lookup_result *res) { + if (ocfs2_dir_indexed(dir)) + return ocfs2_delete_entry_dx(handle, dir, res); + if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) - return ocfs2_delete_entry_id(handle, dir, de_del, bh); + return ocfs2_delete_entry_id(handle, dir, res->dl_entry, + res->dl_leaf_bh); - return ocfs2_delete_entry_el(handle, dir, de_del, bh); + return ocfs2_delete_entry_el(handle, dir, res->dl_entry, + res->dl_leaf_bh); } /* @@ -663,18 +1456,166 @@ static inline int ocfs2_dirent_would_fit(struct ocfs2_dir_entry *de, return 0; } +static void ocfs2_dx_dir_leaf_insert_tail(struct ocfs2_dx_leaf *dx_leaf, + struct ocfs2_dx_entry *dx_new_entry) +{ + int i; + + i = le16_to_cpu(dx_leaf->dl_list.de_num_used); + dx_leaf->dl_list.de_entries[i] = *dx_new_entry; + + le16_add_cpu(&dx_leaf->dl_list.de_num_used, 1); +} + +static void ocfs2_dx_entry_list_insert(struct ocfs2_dx_entry_list *entry_list, + struct ocfs2_dx_hinfo *hinfo, + u64 dirent_blk) +{ + int i; + struct ocfs2_dx_entry *dx_entry; + + i = le16_to_cpu(entry_list->de_num_used); + dx_entry = &entry_list->de_entries[i]; + + memset(dx_entry, 0, sizeof(*dx_entry)); + dx_entry->dx_major_hash = cpu_to_le32(hinfo->major_hash); + dx_entry->dx_minor_hash = cpu_to_le32(hinfo->minor_hash); + dx_entry->dx_dirent_blk = cpu_to_le64(dirent_blk); + + le16_add_cpu(&entry_list->de_num_used, 1); +} + +static int __ocfs2_dx_dir_leaf_insert(struct inode *dir, handle_t *handle, + struct ocfs2_dx_hinfo *hinfo, + u64 dirent_blk, + struct buffer_head *dx_leaf_bh) +{ + int ret; + struct ocfs2_dx_leaf *dx_leaf; + + ret = ocfs2_journal_access_dl(handle, dir, dx_leaf_bh, + OCFS2_JOURNAL_ACCESS_WRITE); + if (ret) { + mlog_errno(ret); + goto out; + } + + dx_leaf = (struct ocfs2_dx_leaf *)dx_leaf_bh->b_data; + ocfs2_dx_entry_list_insert(&dx_leaf->dl_list, hinfo, dirent_blk); + ocfs2_journal_dirty(handle, dx_leaf_bh); + +out: + return ret; +} + +static void ocfs2_dx_inline_root_insert(struct inode *dir, handle_t *handle, + struct ocfs2_dx_hinfo *hinfo, + u64 dirent_blk, + struct ocfs2_dx_root_block *dx_root) +{ + ocfs2_dx_entry_list_insert(&dx_root->dr_entries, hinfo, dirent_blk); +} + +static int ocfs2_dx_dir_insert(struct inode *dir, handle_t *handle, + struct ocfs2_dir_lookup_result *lookup) +{ + int ret = 0; + struct ocfs2_dx_root_block *dx_root; + struct buffer_head *dx_root_bh = lookup->dl_dx_root_bh; + + ret = ocfs2_journal_access_dr(handle, dir, dx_root_bh, + OCFS2_JOURNAL_ACCESS_WRITE); + if (ret) { + mlog_errno(ret); + goto out; + } + + dx_root = (struct ocfs2_dx_root_block *)lookup->dl_dx_root_bh->b_data; + if (ocfs2_dx_root_inline(dx_root)) { + ocfs2_dx_inline_root_insert(dir, handle, + &lookup->dl_hinfo, + lookup->dl_leaf_bh->b_blocknr, + dx_root); + } else { + ret = __ocfs2_dx_dir_leaf_insert(dir, handle, &lookup->dl_hinfo, + lookup->dl_leaf_bh->b_blocknr, + lookup->dl_dx_leaf_bh); + if (ret) + goto out; + } + + le32_add_cpu(&dx_root->dr_num_entries, 1); + ocfs2_journal_dirty(handle, dx_root_bh); + +out: + return ret; +} + +static void ocfs2_remove_block_from_free_list(struct inode *dir, + handle_t *handle, + struct ocfs2_dir_lookup_result *lookup) +{ + struct ocfs2_dir_block_trailer *trailer, *prev; + struct ocfs2_dx_root_block *dx_root; + struct buffer_head *bh; + + trailer = ocfs2_trailer_from_bh(lookup->dl_leaf_bh, dir->i_sb); + + if (ocfs2_free_list_at_root(lookup)) { + bh = lookup->dl_dx_root_bh; + dx_root = (struct ocfs2_dx_root_block *)bh->b_data; + dx_root->dr_free_blk = trailer->db_free_next; + } else { + bh = lookup->dl_prev_leaf_bh; + prev = ocfs2_trailer_from_bh(bh, dir->i_sb); + prev->db_free_next = trailer->db_free_next; + } + + trailer->db_free_rec_len = cpu_to_le16(0); + trailer->db_free_next = cpu_to_le64(0); + + ocfs2_journal_dirty(handle, bh); + ocfs2_journal_dirty(handle, lookup->dl_leaf_bh); +} + +/* + * This expects that a journal write has been reserved on + * lookup->dl_prev_leaf_bh or lookup->dl_dx_root_bh + */ +static void ocfs2_recalc_free_list(struct inode *dir, handle_t *handle, + struct ocfs2_dir_lookup_result *lookup) +{ + int max_rec_len; + struct ocfs2_dir_block_trailer *trailer; + + /* Walk dl_leaf_bh to figure out what the new free rec_len is. */ + max_rec_len = ocfs2_find_max_rec_len(dir->i_sb, lookup->dl_leaf_bh); + if (max_rec_len) { + /* + * There's still room in this block, so no need to remove it + * from the free list. In this case, we just want to update + * the rec len accounting. + */ + trailer = ocfs2_trailer_from_bh(lookup->dl_leaf_bh, dir->i_sb); + trailer->db_free_rec_len = cpu_to_le16(max_rec_len); + ocfs2_journal_dirty(handle, lookup->dl_leaf_bh); + } else { + ocfs2_remove_block_from_free_list(dir, handle, lookup); + } +} + /* we don't always have a dentry for what we want to add, so people * like orphan dir can call this instead. * - * If you pass me insert_bh, I'll skip the search of the other dir - * blocks and put the record in there. + * The lookup context must have been filled from + * ocfs2_prepare_dir_for_insert. */ int __ocfs2_add_entry(handle_t *handle, struct inode *dir, const char *name, int namelen, struct inode *inode, u64 blkno, struct buffer_head *parent_fe_bh, - struct buffer_head *insert_bh) + struct ocfs2_dir_lookup_result *lookup) { unsigned long offset; unsigned short rec_len; @@ -683,6 +1624,7 @@ int __ocfs2_add_entry(handle_t *handle, struct super_block *sb = dir->i_sb; int retval, status; unsigned int size = sb->s_blocksize; + struct buffer_head *insert_bh = lookup->dl_leaf_bh; char *data_start = insert_bh->b_data; mlog_entry_void(); @@ -690,7 +1632,31 @@ int __ocfs2_add_entry(handle_t *handle, if (!namelen) return -EINVAL; - if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { + if (ocfs2_dir_indexed(dir)) { + struct buffer_head *bh; + + /* + * An indexed dir may require that we update the free space + * list. Reserve a write to the previous node in the list so + * that we don't fail later. + * + * XXX: This can be either a dx_root_block, or an unindexed + * directory tree leaf block. + */ + if (ocfs2_free_list_at_root(lookup)) { + bh = lookup->dl_dx_root_bh; + retval = ocfs2_journal_access_dr(handle, dir, bh, + OCFS2_JOURNAL_ACCESS_WRITE); + } else { + bh = lookup->dl_prev_leaf_bh; + retval = ocfs2_journal_access_db(handle, dir, bh, + OCFS2_JOURNAL_ACCESS_WRITE); + } + if (retval) { + mlog_errno(retval); + return retval; + } + } else if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { data_start = di->id2.i_data.id_data; size = i_size_read(dir); @@ -737,10 +1703,22 @@ int __ocfs2_add_entry(handle_t *handle, status = ocfs2_journal_access_di(handle, dir, insert_bh, OCFS2_JOURNAL_ACCESS_WRITE); - else + else { status = ocfs2_journal_access_db(handle, dir, insert_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + OCFS2_JOURNAL_ACCESS_WRITE); + + if (ocfs2_dir_indexed(dir)) { + status = ocfs2_dx_dir_insert(dir, + handle, + lookup); + if (status) { + mlog_errno(status); + goto bail; + } + } + } + /* By now the buffer is marked for journaling */ offset += le16_to_cpu(de->rec_len); if (le64_to_cpu(de->inode)) { @@ -761,6 +1739,9 @@ int __ocfs2_add_entry(handle_t *handle, de->name_len = namelen; memcpy(de->name, name, namelen); + if (ocfs2_dir_indexed(dir)) + ocfs2_recalc_free_list(dir, handle, lookup); + dir->i_version++; status = ocfs2_journal_dirty(handle, insert_bh); retval = 0; @@ -870,6 +1851,10 @@ out: return 0; } +/* + * NOTE: This function can be called against unindexed directories, + * and indexed ones. + */ static int ocfs2_dir_foreach_blk_el(struct inode *inode, u64 *f_version, loff_t *f_pos, void *priv, @@ -1071,31 +2056,22 @@ int ocfs2_find_files_on_disk(const char *name, int namelen, u64 *blkno, struct inode *inode, - struct buffer_head **dirent_bh, - struct ocfs2_dir_entry **dirent) + struct ocfs2_dir_lookup_result *lookup) { int status = -ENOENT; - mlog_entry("(name=%.*s, blkno=%p, inode=%p, dirent_bh=%p, dirent=%p)\n", - namelen, name, blkno, inode, dirent_bh, dirent); + mlog(0, "name=%.*s, blkno=%p, inode=%llu\n", namelen, name, blkno, + (unsigned long long)OCFS2_I(inode)->ip_blkno); - *dirent_bh = ocfs2_find_entry(name, namelen, inode, dirent); - if (!*dirent_bh || !*dirent) { - status = -ENOENT; + status = ocfs2_find_entry(name, namelen, inode, lookup); + if (status) goto leave; - } - *blkno = le64_to_cpu((*dirent)->inode); + *blkno = le64_to_cpu(lookup->dl_entry->inode); status = 0; leave: - if (status < 0) { - *dirent = NULL; - brelse(*dirent_bh); - *dirent_bh = NULL; - } - mlog_exit(status); return status; } @@ -1107,11 +2083,10 @@ int ocfs2_lookup_ino_from_name(struct inode *dir, const char *name, int namelen, u64 *blkno) { int ret; - struct buffer_head *bh = NULL; - struct ocfs2_dir_entry *dirent = NULL; + struct ocfs2_dir_lookup_result lookup = { NULL, }; - ret = ocfs2_find_files_on_disk(name, namelen, blkno, dir, &bh, &dirent); - brelse(bh); + ret = ocfs2_find_files_on_disk(name, namelen, blkno, dir, &lookup); + ocfs2_free_dir_lookup_result(&lookup); return ret; } @@ -1128,20 +2103,18 @@ int ocfs2_check_dir_for_entry(struct inode *dir, int namelen) { int ret; - struct buffer_head *dirent_bh = NULL; - struct ocfs2_dir_entry *dirent = NULL; + struct ocfs2_dir_lookup_result lookup = { NULL, }; mlog_entry("dir %llu, name '%.*s'\n", (unsigned long long)OCFS2_I(dir)->ip_blkno, namelen, name); ret = -EEXIST; - dirent_bh = ocfs2_find_entry(name, namelen, dir, &dirent); - if (dirent_bh) + if (ocfs2_find_entry(name, namelen, dir, &lookup) == 0) goto bail; ret = 0; bail: - brelse(dirent_bh); + ocfs2_free_dir_lookup_result(&lookup); mlog_exit(ret); return ret; @@ -1151,6 +2124,7 @@ struct ocfs2_empty_dir_priv { unsigned seen_dot; unsigned seen_dot_dot; unsigned seen_other; + unsigned dx_dir; }; static int ocfs2_empty_dir_filldir(void *priv, const char *name, int name_len, loff_t pos, u64 ino, unsigned type) @@ -1160,6 +2134,13 @@ static int ocfs2_empty_dir_filldir(void *priv, const char *name, int name_len, /* * Check the positions of "." and ".." records to be sure * they're in the correct place. + * + * Indexed directories don't need to proceed past the first + * two entries, so we end the scan after seeing '..'. Despite + * that, we allow the scan to proceed In the event that we + * have a corrupted indexed directory (no dot or dot dot + * entries). This allows us to double check for existing + * entries which might not have been found in the index. */ if (name_len == 1 && !strncmp(".", name, 1) && pos == 0) { p->seen_dot = 1; @@ -1169,16 +2150,57 @@ static int ocfs2_empty_dir_filldir(void *priv, const char *name, int name_len, if (name_len == 2 && !strncmp("..", name, 2) && pos == OCFS2_DIR_REC_LEN(1)) { p->seen_dot_dot = 1; + + if (p->dx_dir && p->seen_dot) + return 1; + return 0; } p->seen_other = 1; return 1; } + +static int ocfs2_empty_dir_dx(struct inode *inode, + struct ocfs2_empty_dir_priv *priv) +{ + int ret; + struct buffer_head *di_bh = NULL; + struct buffer_head *dx_root_bh = NULL; + struct ocfs2_dinode *di; + struct ocfs2_dx_root_block *dx_root; + + priv->dx_dir = 1; + + ret = ocfs2_read_inode_block(inode, &di_bh); + if (ret) { + mlog_errno(ret); + goto out; + } + di = (struct ocfs2_dinode *)di_bh->b_data; + + ret = ocfs2_read_dx_root(inode, di, &dx_root_bh); + if (ret) { + mlog_errno(ret); + goto out; + } + dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data; + + if (le32_to_cpu(dx_root->dr_num_entries) != 2) + priv->seen_other = 1; + +out: + brelse(di_bh); + brelse(dx_root_bh); + return ret; +} + /* * routine to check that the specified directory is empty (for rmdir) * * Returns 1 if dir is empty, zero otherwise. + * + * XXX: This is a performance problem for unindexed directories. */ int ocfs2_empty_dir(struct inode *inode) { @@ -1188,6 +2210,16 @@ int ocfs2_empty_dir(struct inode *inode) memset(&priv, 0, sizeof(priv)); + if (ocfs2_dir_indexed(inode)) { + ret = ocfs2_empty_dir_dx(inode, &priv); + if (ret) + mlog_errno(ret); + /* + * We still run ocfs2_dir_foreach to get the checks + * for "." and "..". + */ + } + ret = ocfs2_dir_foreach(inode, &start, &priv, ocfs2_empty_dir_filldir); if (ret) mlog_errno(ret); @@ -1280,7 +2312,8 @@ static int ocfs2_fill_new_dir_el(struct ocfs2_super *osb, struct inode *parent, struct inode *inode, struct buffer_head *fe_bh, - struct ocfs2_alloc_context *data_ac) + struct ocfs2_alloc_context *data_ac, + struct buffer_head **ret_new_bh) { int status; unsigned int size = osb->sb->s_blocksize; @@ -1289,7 +2322,7 @@ static int ocfs2_fill_new_dir_el(struct ocfs2_super *osb, mlog_entry_void(); - if (ocfs2_supports_dir_trailer(osb)) + if (ocfs2_new_dir_wants_trailer(inode)) size = ocfs2_dir_trailer_blk_off(parent->i_sb); status = ocfs2_do_extend_dir(osb->sb, handle, inode, fe_bh, @@ -1310,8 +2343,19 @@ static int ocfs2_fill_new_dir_el(struct ocfs2_super *osb, memset(new_bh->b_data, 0, osb->sb->s_blocksize); de = ocfs2_fill_initial_dirents(inode, parent, new_bh->b_data, size); - if (ocfs2_supports_dir_trailer(osb)) - ocfs2_init_dir_trailer(inode, new_bh); + if (ocfs2_new_dir_wants_trailer(inode)) { + int size = le16_to_cpu(de->rec_len); + + /* + * Figure out the size of the hole left over after + * insertion of '.' and '..'. The trailer wants this + * information. + */ + size -= OCFS2_DIR_REC_LEN(2); + size -= sizeof(struct ocfs2_dir_block_trailer); + + ocfs2_init_dir_trailer(inode, new_bh, size); + } status = ocfs2_journal_dirty(handle, new_bh); if (status < 0) { @@ -1329,6 +2373,10 @@ static int ocfs2_fill_new_dir_el(struct ocfs2_super *osb, } status = 0; + if (ret_new_bh) { + *ret_new_bh = new_bh; + new_bh = NULL; + } bail: brelse(new_bh); @@ -1336,20 +2384,427 @@ bail: return status; } +static int ocfs2_dx_dir_attach_index(struct ocfs2_super *osb, + handle_t *handle, struct inode *dir, + struct buffer_head *di_bh, + struct buffer_head *dirdata_bh, + struct ocfs2_alloc_context *meta_ac, + int dx_inline, u32 num_entries, + struct buffer_head **ret_dx_root_bh) +{ + int ret; + struct ocfs2_dinode *di = (struct ocfs2_dinode *) di_bh->b_data; + u16 dr_suballoc_bit; + u64 dr_blkno; + unsigned int num_bits; + struct buffer_head *dx_root_bh = NULL; + struct ocfs2_dx_root_block *dx_root; + struct ocfs2_dir_block_trailer *trailer = + ocfs2_trailer_from_bh(dirdata_bh, dir->i_sb); + + ret = ocfs2_claim_metadata(osb, handle, meta_ac, 1, &dr_suballoc_bit, + &num_bits, &dr_blkno); + if (ret) { + mlog_errno(ret); + goto out; + } + + mlog(0, "Dir %llu, attach new index block: %llu\n", + (unsigned long long)OCFS2_I(dir)->ip_blkno, + (unsigned long long)dr_blkno); + + dx_root_bh = sb_getblk(osb->sb, dr_blkno); + if (dx_root_bh == NULL) { + ret = -EIO; + goto out; + } + ocfs2_set_new_buffer_uptodate(dir, dx_root_bh); + + ret = ocfs2_journal_access_dr(handle, dir, dx_root_bh, + OCFS2_JOURNAL_ACCESS_CREATE); + if (ret < 0) { + mlog_errno(ret); + goto out; + } + + dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data; + memset(dx_root, 0, osb->sb->s_blocksize); + strcpy(dx_root->dr_signature, OCFS2_DX_ROOT_SIGNATURE); + dx_root->dr_suballoc_slot = cpu_to_le16(osb->slot_num); + dx_root->dr_suballoc_bit = cpu_to_le16(dr_suballoc_bit); + dx_root->dr_fs_generation = cpu_to_le32(osb->fs_generation); + dx_root->dr_blkno = cpu_to_le64(dr_blkno); + dx_root->dr_dir_blkno = cpu_to_le64(OCFS2_I(dir)->ip_blkno); + dx_root->dr_num_entries = cpu_to_le32(num_entries); + if (le16_to_cpu(trailer->db_free_rec_len)) + dx_root->dr_free_blk = cpu_to_le64(dirdata_bh->b_blocknr); + else + dx_root->dr_free_blk = cpu_to_le64(0); + + if (dx_inline) { + dx_root->dr_flags |= OCFS2_DX_FLAG_INLINE; + dx_root->dr_entries.de_count = + cpu_to_le16(ocfs2_dx_entries_per_root(osb->sb)); + } else { + dx_root->dr_list.l_count = + cpu_to_le16(ocfs2_extent_recs_per_dx_root(osb->sb)); + } + + ret = ocfs2_journal_dirty(handle, dx_root_bh); + if (ret) + mlog_errno(ret); + + ret = ocfs2_journal_access_di(handle, dir, di_bh, + OCFS2_JOURNAL_ACCESS_CREATE); + if (ret) { + mlog_errno(ret); + goto out; + } + + di->i_dx_root = cpu_to_le64(dr_blkno); + + OCFS2_I(dir)->ip_dyn_features |= OCFS2_INDEXED_DIR_FL; + di->i_dyn_features = cpu_to_le16(OCFS2_I(dir)->ip_dyn_features); + + ret = ocfs2_journal_dirty(handle, di_bh); + if (ret) + mlog_errno(ret); + + *ret_dx_root_bh = dx_root_bh; + dx_root_bh = NULL; + +out: + brelse(dx_root_bh); + return ret; +} + +static int ocfs2_dx_dir_format_cluster(struct ocfs2_super *osb, + handle_t *handle, struct inode *dir, + struct buffer_head **dx_leaves, + int num_dx_leaves, u64 start_blk) +{ + int ret, i; + struct ocfs2_dx_leaf *dx_leaf; + struct buffer_head *bh; + + for (i = 0; i < num_dx_leaves; i++) { + bh = sb_getblk(osb->sb, start_blk + i); + if (bh == NULL) { + ret = -EIO; + goto out; + } + dx_leaves[i] = bh; + + ocfs2_set_new_buffer_uptodate(dir, bh); + + ret = ocfs2_journal_access_dl(handle, dir, bh, + OCFS2_JOURNAL_ACCESS_CREATE); + if (ret < 0) { + mlog_errno(ret); + goto out; + } + + dx_leaf = (struct ocfs2_dx_leaf *) bh->b_data; + + memset(dx_leaf, 0, osb->sb->s_blocksize); + strcpy(dx_leaf->dl_signature, OCFS2_DX_LEAF_SIGNATURE); + dx_leaf->dl_fs_generation = cpu_to_le32(osb->fs_generation); + dx_leaf->dl_blkno = cpu_to_le64(bh->b_blocknr); + dx_leaf->dl_list.de_count = + cpu_to_le16(ocfs2_dx_entries_per_leaf(osb->sb)); + + mlog(0, + "Dir %llu, format dx_leaf: %llu, entry count: %u\n", + (unsigned long long)OCFS2_I(dir)->ip_blkno, + (unsigned long long)bh->b_blocknr, + le16_to_cpu(dx_leaf->dl_list.de_count)); + + ocfs2_journal_dirty(handle, bh); + } + + ret = 0; +out: + return ret; +} + +/* + * Allocates and formats a new cluster for use in an indexed dir + * leaf. This version will not do the extent insert, so that it can be + * used by operations which need careful ordering. + */ +static int __ocfs2_dx_dir_new_cluster(struct inode *dir, + u32 cpos, handle_t *handle, + struct ocfs2_alloc_context *data_ac, + struct buffer_head **dx_leaves, + int num_dx_leaves, u64 *ret_phys_blkno) +{ + int ret; + u32 phys, num; + u64 phys_blkno; + struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); + + /* + * XXX: For create, this should claim cluster for the index + * *before* the unindexed insert so that we have a better + * chance of contiguousness as the directory grows in number + * of entries. + */ + ret = __ocfs2_claim_clusters(osb, handle, data_ac, 1, 1, &phys, &num); + if (ret) { + mlog_errno(ret); + goto out; + } + + /* + * Format the new cluster first. That way, we're inserting + * valid data. + */ + phys_blkno = ocfs2_clusters_to_blocks(osb->sb, phys); + ret = ocfs2_dx_dir_format_cluster(osb, handle, dir, dx_leaves, + num_dx_leaves, phys_blkno); + if (ret) { + mlog_errno(ret); + goto out; + } + + *ret_phys_blkno = phys_blkno; +out: + return ret; +} + +static int ocfs2_dx_dir_new_cluster(struct inode *dir, + struct ocfs2_extent_tree *et, + u32 cpos, handle_t *handle, + struct ocfs2_alloc_context *data_ac, + struct ocfs2_alloc_context *meta_ac, + struct buffer_head **dx_leaves, + int num_dx_leaves) +{ + int ret; + u64 phys_blkno; + struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); + + ret = __ocfs2_dx_dir_new_cluster(dir, cpos, handle, data_ac, dx_leaves, + num_dx_leaves, &phys_blkno); + if (ret) { + mlog_errno(ret); + goto out; + } + + ret = ocfs2_insert_extent(osb, handle, dir, et, cpos, phys_blkno, 1, 0, + meta_ac); + if (ret) + mlog_errno(ret); +out: + return ret; +} + +static struct buffer_head **ocfs2_dx_dir_kmalloc_leaves(struct super_block *sb, + int *ret_num_leaves) +{ + int num_dx_leaves = ocfs2_clusters_to_blocks(sb, 1); + struct buffer_head **dx_leaves; + + dx_leaves = kcalloc(num_dx_leaves, sizeof(struct buffer_head *), + GFP_NOFS); + if (dx_leaves && ret_num_leaves) + *ret_num_leaves = num_dx_leaves; + + return dx_leaves; +} + +static int ocfs2_fill_new_dir_dx(struct ocfs2_super *osb, + handle_t *handle, + struct inode *parent, + struct inode *inode, + struct buffer_head *di_bh, + struct ocfs2_alloc_context *data_ac, + struct ocfs2_alloc_context *meta_ac) +{ + int ret; + struct buffer_head *leaf_bh = NULL; + struct buffer_head *dx_root_bh = NULL; + struct ocfs2_dx_hinfo hinfo; + struct ocfs2_dx_root_block *dx_root; + struct ocfs2_dx_entry_list *entry_list; + + /* + * Our strategy is to create the directory as though it were + * unindexed, then add the index block. This works with very + * little complication since the state of a new directory is a + * very well known quantity. + * + * Essentially, we have two dirents ("." and ".."), in the 1st + * block which need indexing. These are easily inserted into + * the index block. + */ + + ret = ocfs2_fill_new_dir_el(osb, handle, parent, inode, di_bh, + data_ac, &leaf_bh); + if (ret) { + mlog_errno(ret); + goto out; + } + + ret = ocfs2_dx_dir_attach_index(osb, handle, inode, di_bh, leaf_bh, + meta_ac, 1, 2, &dx_root_bh); + if (ret) { + mlog_errno(ret); + goto out; + } + dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data; + entry_list = &dx_root->dr_entries; + + /* Buffer has been journaled for us by ocfs2_dx_dir_attach_index */ + ocfs2_dx_dir_name_hash(inode, ".", 1, &hinfo); + ocfs2_dx_entry_list_insert(entry_list, &hinfo, leaf_bh->b_blocknr); + + ocfs2_dx_dir_name_hash(inode, "..", 2, &hinfo); + ocfs2_dx_entry_list_insert(entry_list, &hinfo, leaf_bh->b_blocknr); + +out: + brelse(dx_root_bh); + brelse(leaf_bh); + return ret; +} + int ocfs2_fill_new_dir(struct ocfs2_super *osb, handle_t *handle, struct inode *parent, struct inode *inode, struct buffer_head *fe_bh, - struct ocfs2_alloc_context *data_ac) + struct ocfs2_alloc_context *data_ac, + struct ocfs2_alloc_context *meta_ac) + { BUG_ON(!ocfs2_supports_inline_data(osb) && data_ac == NULL); if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) return ocfs2_fill_new_dir_id(osb, handle, parent, inode, fe_bh); + if (ocfs2_supports_indexed_dirs(osb)) + return ocfs2_fill_new_dir_dx(osb, handle, parent, inode, fe_bh, + data_ac, meta_ac); + return ocfs2_fill_new_dir_el(osb, handle, parent, inode, fe_bh, - data_ac); + data_ac, NULL); +} + +static int ocfs2_dx_dir_index_block(struct inode *dir, + handle_t *handle, + struct buffer_head **dx_leaves, + int num_dx_leaves, + u32 *num_dx_entries, + struct buffer_head *dirent_bh) +{ + int ret, namelen, i; + char *de_buf, *limit; + struct ocfs2_dir_entry *de; + struct buffer_head *dx_leaf_bh; + struct ocfs2_dx_hinfo hinfo; + u64 dirent_blk = dirent_bh->b_blocknr; + + de_buf = dirent_bh->b_data; + limit = de_buf + dir->i_sb->s_blocksize; + + while (de_buf < limit) { + de = (struct ocfs2_dir_entry *)de_buf; + + namelen = de->name_len; + if (!namelen || !de->inode) + goto inc; + + ocfs2_dx_dir_name_hash(dir, de->name, namelen, &hinfo); + + i = ocfs2_dx_dir_hash_idx(OCFS2_SB(dir->i_sb), &hinfo); + dx_leaf_bh = dx_leaves[i]; + + ret = __ocfs2_dx_dir_leaf_insert(dir, handle, &hinfo, + dirent_blk, dx_leaf_bh); + if (ret) { + mlog_errno(ret); + goto out; + } + + *num_dx_entries = *num_dx_entries + 1; + +inc: + de_buf += le16_to_cpu(de->rec_len); + } + +out: + return ret; +} + +/* + * XXX: This expects dx_root_bh to already be part of the transaction. + */ +static void ocfs2_dx_dir_index_root_block(struct inode *dir, + struct buffer_head *dx_root_bh, + struct buffer_head *dirent_bh) +{ + char *de_buf, *limit; + struct ocfs2_dx_root_block *dx_root; + struct ocfs2_dir_entry *de; + struct ocfs2_dx_hinfo hinfo; + u64 dirent_blk = dirent_bh->b_blocknr; + + dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data; + + de_buf = dirent_bh->b_data; + limit = de_buf + dir->i_sb->s_blocksize; + + while (de_buf < limit) { + de = (struct ocfs2_dir_entry *)de_buf; + + if (!de->name_len || !de->inode) + goto inc; + + ocfs2_dx_dir_name_hash(dir, de->name, de->name_len, &hinfo); + + mlog(0, + "dir: %llu, major: 0x%x minor: 0x%x, index: %u, name: %.*s\n", + (unsigned long long)dir->i_ino, hinfo.major_hash, + hinfo.minor_hash, + le16_to_cpu(dx_root->dr_entries.de_num_used), + de->name_len, de->name); + + ocfs2_dx_entry_list_insert(&dx_root->dr_entries, &hinfo, + dirent_blk); + + le32_add_cpu(&dx_root->dr_num_entries, 1); +inc: + de_buf += le16_to_cpu(de->rec_len); + } +} + +/* + * Count the number of inline directory entries in di_bh and compare + * them against the number of entries we can hold in an inline dx root + * block. + */ +static int ocfs2_new_dx_should_be_inline(struct inode *dir, + struct buffer_head *di_bh) +{ + int dirent_count = 0; + char *de_buf, *limit; + struct ocfs2_dir_entry *de; + struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; + + de_buf = di->id2.i_data.id_data; + limit = de_buf + i_size_read(dir); + + while (de_buf < limit) { + de = (struct ocfs2_dir_entry *)de_buf; + + if (de->name_len && de->inode) + dirent_count++; + + de_buf += le16_to_cpu(de->rec_len); + } + + /* We are careful to leave room for one extra record. */ + return dirent_count < ocfs2_dx_entries_per_root(dir->i_sb); } /* @@ -1358,18 +2813,26 @@ int ocfs2_fill_new_dir(struct ocfs2_super *osb, * expansion from an inline directory to one with extents. The first dir block * in that case is taken from the inline data portion of the inode block. * + * This will also return the largest amount of contiguous space for a dirent + * in the block. That value is *not* necessarily the last dirent, even after + * expansion. The directory indexing code wants this value for free space + * accounting. We do this here since we're already walking the entire dir + * block. + * * We add the dir trailer if this filesystem wants it. */ -static void ocfs2_expand_last_dirent(char *start, unsigned int old_size, - struct super_block *sb) +static unsigned int ocfs2_expand_last_dirent(char *start, unsigned int old_size, + struct inode *dir) { + struct super_block *sb = dir->i_sb; struct ocfs2_dir_entry *de; struct ocfs2_dir_entry *prev_de; char *de_buf, *limit; unsigned int new_size = sb->s_blocksize; - unsigned int bytes; + unsigned int bytes, this_hole; + unsigned int largest_hole = 0; - if (ocfs2_supports_dir_trailer(OCFS2_SB(sb))) + if (ocfs2_new_dir_wants_trailer(dir)) new_size = ocfs2_dir_trailer_blk_off(sb); bytes = new_size - old_size; @@ -1378,12 +2841,26 @@ static void ocfs2_expand_last_dirent(char *start, unsigned int old_size, de_buf = start; de = (struct ocfs2_dir_entry *)de_buf; do { + this_hole = ocfs2_figure_dirent_hole(de); + if (this_hole > largest_hole) + largest_hole = this_hole; + prev_de = de; de_buf += le16_to_cpu(de->rec_len); de = (struct ocfs2_dir_entry *)de_buf; } while (de_buf < limit); le16_add_cpu(&prev_de->rec_len, bytes); + + /* We need to double check this after modification of the final + * dirent. */ + this_hole = ocfs2_figure_dirent_hole(prev_de); + if (this_hole > largest_hole) + largest_hole = this_hole; + + if (largest_hole >= OCFS2_DIR_MIN_REC_LEN) + return largest_hole; + return 0; } /* @@ -1396,29 +2873,61 @@ static void ocfs2_expand_last_dirent(char *start, unsigned int old_size, */ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh, unsigned int blocks_wanted, + struct ocfs2_dir_lookup_result *lookup, struct buffer_head **first_block_bh) { - u32 alloc, bit_off, len; + u32 alloc, dx_alloc, bit_off, len, num_dx_entries = 0; struct super_block *sb = dir->i_sb; - int ret, credits = ocfs2_inline_to_extents_credits(sb); - u64 blkno, bytes = blocks_wanted << sb->s_blocksize_bits; + int ret, i, num_dx_leaves = 0, dx_inline = 0, + credits = ocfs2_inline_to_extents_credits(sb); + u64 dx_insert_blkno, blkno, + bytes = blocks_wanted << sb->s_blocksize_bits; struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); struct ocfs2_inode_info *oi = OCFS2_I(dir); struct ocfs2_alloc_context *data_ac; + struct ocfs2_alloc_context *meta_ac = NULL; struct buffer_head *dirdata_bh = NULL; + struct buffer_head *dx_root_bh = NULL; + struct buffer_head **dx_leaves = NULL; struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; handle_t *handle; struct ocfs2_extent_tree et; - int did_quota = 0; + struct ocfs2_extent_tree dx_et; + int did_quota = 0, bytes_allocated = 0; ocfs2_init_dinode_extent_tree(&et, dir, di_bh); alloc = ocfs2_clusters_for_bytes(sb, bytes); + dx_alloc = 0; + + if (ocfs2_supports_indexed_dirs(osb)) { + credits += ocfs2_add_dir_index_credits(sb); + + dx_inline = ocfs2_new_dx_should_be_inline(dir, di_bh); + if (!dx_inline) { + /* Add one more cluster for an index leaf */ + dx_alloc++; + dx_leaves = ocfs2_dx_dir_kmalloc_leaves(sb, + &num_dx_leaves); + if (!dx_leaves) { + ret = -ENOMEM; + mlog_errno(ret); + goto out; + } + } + + /* This gets us the dx_root */ + ret = ocfs2_reserve_new_metadata_blocks(osb, 1, &meta_ac); + if (ret) { + mlog_errno(ret); + goto out; + } + } /* - * We should never need more than 2 clusters for this - - * maximum dirent size is far less than one block. In fact, - * the only time we'd need more than one cluster is if + * We should never need more than 2 clusters for the unindexed + * tree - maximum dirent size is far less than one block. In + * fact, the only time we'd need more than one cluster is if * blocksize == clustersize and the dirent won't fit in the * extra space that the expansion to a single block gives. As * of today, that only happens on 4k/4k file systems. @@ -1435,7 +2944,7 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh, /* * Prepare for worst case allocation scenario of two separate - * extents. + * extents in the unindexed tree. */ if (alloc == 2) credits += OCFS2_SUBALLOC_ALLOC; @@ -1448,11 +2957,29 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh, } if (vfs_dq_alloc_space_nodirty(dir, - ocfs2_clusters_to_bytes(osb->sb, alloc))) { + ocfs2_clusters_to_bytes(osb->sb, + alloc + dx_alloc))) { ret = -EDQUOT; goto out_commit; } did_quota = 1; + + if (ocfs2_supports_indexed_dirs(osb) && !dx_inline) { + /* + * Allocate our index cluster first, to maximize the + * possibility that unindexed leaves grow + * contiguously. + */ + ret = __ocfs2_dx_dir_new_cluster(dir, 0, handle, data_ac, + dx_leaves, num_dx_leaves, + &dx_insert_blkno); + if (ret) { + mlog_errno(ret); + goto out_commit; + } + bytes_allocated += ocfs2_clusters_to_bytes(dir->i_sb, 1); + } + /* * Try to claim as many clusters as the bitmap can give though * if we only get one now, that's enough to continue. The rest @@ -1463,6 +2990,7 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh, mlog_errno(ret); goto out_commit; } + bytes_allocated += ocfs2_clusters_to_bytes(dir->i_sb, 1); /* * Operations are carefully ordered so that we set up the new @@ -1489,9 +3017,16 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh, memcpy(dirdata_bh->b_data, di->id2.i_data.id_data, i_size_read(dir)); memset(dirdata_bh->b_data + i_size_read(dir), 0, sb->s_blocksize - i_size_read(dir)); - ocfs2_expand_last_dirent(dirdata_bh->b_data, i_size_read(dir), sb); - if (ocfs2_supports_dir_trailer(osb)) - ocfs2_init_dir_trailer(dir, dirdata_bh); + i = ocfs2_expand_last_dirent(dirdata_bh->b_data, i_size_read(dir), dir); + if (ocfs2_new_dir_wants_trailer(dir)) { + /* + * Prepare the dir trailer up front. It will otherwise look + * like a valid dirent. Even if inserting the index fails + * (unlikely), then all we'll have done is given first dir + * block a small amount of fragmentation. + */ + ocfs2_init_dir_trailer(dir, dirdata_bh, i); + } ret = ocfs2_journal_dirty(handle, dirdata_bh); if (ret) { @@ -1499,6 +3034,24 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh, goto out_commit; } + if (ocfs2_supports_indexed_dirs(osb) && !dx_inline) { + /* + * Dx dirs with an external cluster need to do this up + * front. Inline dx root's get handled later, after + * we've allocated our root block. We get passed back + * a total number of items so that dr_num_entries can + * be correctly set once the dx_root has been + * allocated. + */ + ret = ocfs2_dx_dir_index_block(dir, handle, dx_leaves, + num_dx_leaves, &num_dx_entries, + dirdata_bh); + if (ret) { + mlog_errno(ret); + goto out_commit; + } + } + /* * Set extent, i_size, etc on the directory. After this, the * inode should contain the same exact dirents as before and @@ -1551,6 +3104,27 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh, goto out_commit; } + if (ocfs2_supports_indexed_dirs(osb)) { + ret = ocfs2_dx_dir_attach_index(osb, handle, dir, di_bh, + dirdata_bh, meta_ac, dx_inline, + num_dx_entries, &dx_root_bh); + if (ret) { + mlog_errno(ret); + goto out_commit; + } + + if (dx_inline) { + ocfs2_dx_dir_index_root_block(dir, dx_root_bh, + dirdata_bh); + } else { + ocfs2_init_dx_root_extent_tree(&dx_et, dir, dx_root_bh); + ret = ocfs2_insert_extent(osb, handle, dir, &dx_et, 0, + dx_insert_blkno, 1, 0, NULL); + if (ret) + mlog_errno(ret); + } + } + /* * We asked for two clusters, but only got one in the 1st * pass. Claim the 2nd cluster as a separate extent. @@ -1570,15 +3144,32 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh, mlog_errno(ret); goto out_commit; } + bytes_allocated += ocfs2_clusters_to_bytes(dir->i_sb, 1); } *first_block_bh = dirdata_bh; dirdata_bh = NULL; + if (ocfs2_supports_indexed_dirs(osb)) { + unsigned int off; + + if (!dx_inline) { + /* + * We need to return the correct block within the + * cluster which should hold our entry. + */ + off = ocfs2_dx_dir_hash_idx(OCFS2_SB(dir->i_sb), + &lookup->dl_hinfo); + get_bh(dx_leaves[off]); + lookup->dl_dx_leaf_bh = dx_leaves[off]; + } + lookup->dl_dx_root_bh = dx_root_bh; + dx_root_bh = NULL; + } out_commit: if (ret < 0 && did_quota) - vfs_dq_free_space_nodirty(dir, - ocfs2_clusters_to_bytes(osb->sb, 2)); + vfs_dq_free_space_nodirty(dir, bytes_allocated); + ocfs2_commit_trans(osb, handle); out_sem: @@ -1587,8 +3178,17 @@ out_sem: out: if (data_ac) ocfs2_free_alloc_context(data_ac); + if (meta_ac) + ocfs2_free_alloc_context(meta_ac); + + if (dx_leaves) { + for (i = 0; i < num_dx_leaves; i++) + brelse(dx_leaves[i]); + kfree(dx_leaves); + } brelse(dirdata_bh); + brelse(dx_root_bh); return ret; } @@ -1658,11 +3258,14 @@ bail: * is to be turned into an extent based one. The size of the dirent to * insert might be larger than the space gained by growing to just one * block, so we may have to grow the inode by two blocks in that case. + * + * If the directory is already indexed, dx_root_bh must be provided. */ static int ocfs2_extend_dir(struct ocfs2_super *osb, struct inode *dir, struct buffer_head *parent_fe_bh, unsigned int blocks_wanted, + struct ocfs2_dir_lookup_result *lookup, struct buffer_head **new_de_bh) { int status = 0; @@ -1677,17 +3280,29 @@ static int ocfs2_extend_dir(struct ocfs2_super *osb, struct ocfs2_dir_entry * de; struct super_block *sb = osb->sb; struct ocfs2_extent_tree et; + struct buffer_head *dx_root_bh = lookup->dl_dx_root_bh; mlog_entry_void(); if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { + /* + * This would be a code error as an inline directory should + * never have an index root. + */ + BUG_ON(dx_root_bh); + status = ocfs2_expand_inline_dir(dir, parent_fe_bh, - blocks_wanted, &new_bh); + blocks_wanted, lookup, + &new_bh); if (status) { mlog_errno(status); goto bail; } + /* Expansion from inline to an indexed directory will + * have given us this. */ + dx_root_bh = lookup->dl_dx_root_bh; + if (blocks_wanted == 1) { /* * If the new dirent will fit inside the space @@ -1751,6 +3366,10 @@ static int ocfs2_extend_dir(struct ocfs2_super *osb, } do_extend: + if (ocfs2_dir_indexed(dir)) + credits++; /* For attaching the new dirent block to the + * dx_root */ + down_write(&OCFS2_I(dir)->ip_alloc_sem); drop_alloc_sem = 1; @@ -1781,9 +3400,19 @@ do_extend: de = (struct ocfs2_dir_entry *) new_bh->b_data; de->inode = 0; - if (ocfs2_dir_has_trailer(dir)) { + if (ocfs2_supports_dir_trailer(dir)) { de->rec_len = cpu_to_le16(ocfs2_dir_trailer_blk_off(sb)); - ocfs2_init_dir_trailer(dir, new_bh); + + ocfs2_init_dir_trailer(dir, new_bh, le16_to_cpu(de->rec_len)); + + if (ocfs2_dir_indexed(dir)) { + status = ocfs2_dx_dir_link_trailer(dir, handle, + dx_root_bh, new_bh); + if (status) { + mlog_errno(status); + goto bail; + } + } } else { de->rec_len = cpu_to_le16(sb->s_blocksize); } @@ -1839,7 +3468,7 @@ static int ocfs2_find_dir_space_id(struct inode *dir, struct buffer_head *di_bh, * This calculates how many free bytes we'd have in block zero, should * this function force expansion to an extent tree. */ - if (ocfs2_supports_dir_trailer(OCFS2_SB(sb))) + if (ocfs2_new_dir_wants_trailer(dir)) free_space = ocfs2_dir_trailer_blk_off(sb) - i_size_read(dir); else free_space = dir->i_sb->s_blocksize - i_size_read(dir); @@ -1970,12 +3599,766 @@ bail: return status; } +static int dx_leaf_sort_cmp(const void *a, const void *b) +{ + const struct ocfs2_dx_entry *entry1 = a; + const struct ocfs2_dx_entry *entry2 = b; + u32 major_hash1 = le32_to_cpu(entry1->dx_major_hash); + u32 major_hash2 = le32_to_cpu(entry2->dx_major_hash); + u32 minor_hash1 = le32_to_cpu(entry1->dx_minor_hash); + u32 minor_hash2 = le32_to_cpu(entry2->dx_minor_hash); + + if (major_hash1 > major_hash2) + return 1; + if (major_hash1 < major_hash2) + return -1; + + /* + * It is not strictly necessary to sort by minor + */ + if (minor_hash1 > minor_hash2) + return 1; + if (minor_hash1 < minor_hash2) + return -1; + return 0; +} + +static void dx_leaf_sort_swap(void *a, void *b, int size) +{ + struct ocfs2_dx_entry *entry1 = a; + struct ocfs2_dx_entry *entry2 = b; + struct ocfs2_dx_entry tmp; + + BUG_ON(size != sizeof(*entry1)); + + tmp = *entry1; + *entry1 = *entry2; + *entry2 = tmp; +} + +static int ocfs2_dx_leaf_same_major(struct ocfs2_dx_leaf *dx_leaf) +{ + struct ocfs2_dx_entry_list *dl_list = &dx_leaf->dl_list; + int i, num = le16_to_cpu(dl_list->de_num_used); + + for (i = 0; i < (num - 1); i++) { + if (le32_to_cpu(dl_list->de_entries[i].dx_major_hash) != + le32_to_cpu(dl_list->de_entries[i + 1].dx_major_hash)) + return 0; + } + + return 1; +} + +/* + * Find the optimal value to split this leaf on. This expects the leaf + * entries to be in sorted order. + * + * leaf_cpos is the cpos of the leaf we're splitting. insert_hash is + * the hash we want to insert. + * + * This function is only concerned with the major hash - that which + * determines which cluster an item belongs to. + */ +static int ocfs2_dx_dir_find_leaf_split(struct ocfs2_dx_leaf *dx_leaf, + u32 leaf_cpos, u32 insert_hash, + u32 *split_hash) +{ + struct ocfs2_dx_entry_list *dl_list = &dx_leaf->dl_list; + int i, num_used = le16_to_cpu(dl_list->de_num_used); + int allsame; + + /* + * There's a couple rare, but nasty corner cases we have to + * check for here. All of them involve a leaf where all value + * have the same hash, which is what we look for first. + * + * Most of the time, all of the above is false, and we simply + * pick the median value for a split. + */ + allsame = ocfs2_dx_leaf_same_major(dx_leaf); + if (allsame) { + u32 val = le32_to_cpu(dl_list->de_entries[0].dx_major_hash); + + if (val == insert_hash) { + /* + * No matter where we would choose to split, + * the new entry would want to occupy the same + * block as these. Since there's no space left + * in their existing block, we know there + * won't be space after the split. + */ + return -ENOSPC; + } + + if (val == leaf_cpos) { + /* + * Because val is the same as leaf_cpos (which + * is the smallest value this leaf can have), + * yet is not equal to insert_hash, then we + * know that insert_hash *must* be larger than + * val (and leaf_cpos). At least cpos+1 in value. + * + * We also know then, that there cannot be an + * adjacent extent (otherwise we'd be looking + * at it). Choosing this value gives us a + * chance to get some contiguousness. + */ + *split_hash = leaf_cpos + 1; + return 0; + } + + if (val > insert_hash) { + /* + * val can not be the same as insert hash, and + * also must be larger than leaf_cpos. Also, + * we know that there can't be a leaf between + * cpos and val, otherwise the entries with + * hash 'val' would be there. + */ + *split_hash = val; + return 0; + } + + *split_hash = insert_hash; + return 0; + } + + /* + * Since the records are sorted and the checks above + * guaranteed that not all records in this block are the same, + * we simple travel forward, from the median, and pick the 1st + * record whose value is larger than leaf_cpos. + */ + for (i = (num_used / 2); i < num_used; i++) + if (le32_to_cpu(dl_list->de_entries[i].dx_major_hash) > + leaf_cpos) + break; + + BUG_ON(i == num_used); /* Should be impossible */ + *split_hash = le32_to_cpu(dl_list->de_entries[i].dx_major_hash); + return 0; +} + +/* + * Transfer all entries in orig_dx_leaves whose major hash is equal to or + * larger than split_hash into new_dx_leaves. We use a temporary + * buffer (tmp_dx_leaf) to make the changes to the original leaf blocks. + * + * Since the block offset inside a leaf (cluster) is a constant mask + * of minor_hash, we can optimize - an item at block offset X within + * the original cluster, will be at offset X within the new cluster. + */ +static void ocfs2_dx_dir_transfer_leaf(struct inode *dir, u32 split_hash, + handle_t *handle, + struct ocfs2_dx_leaf *tmp_dx_leaf, + struct buffer_head **orig_dx_leaves, + struct buffer_head **new_dx_leaves, + int num_dx_leaves) +{ + int i, j, num_used; + u32 major_hash; + struct ocfs2_dx_leaf *orig_dx_leaf, *new_dx_leaf; + struct ocfs2_dx_entry_list *orig_list, *new_list, *tmp_list; + struct ocfs2_dx_entry *dx_entry; + + tmp_list = &tmp_dx_leaf->dl_list; + + for (i = 0; i < num_dx_leaves; i++) { + orig_dx_leaf = (struct ocfs2_dx_leaf *) orig_dx_leaves[i]->b_data; + orig_list = &orig_dx_leaf->dl_list; + new_dx_leaf = (struct ocfs2_dx_leaf *) new_dx_leaves[i]->b_data; + new_list = &new_dx_leaf->dl_list; + + num_used = le16_to_cpu(orig_list->de_num_used); + + memcpy(tmp_dx_leaf, orig_dx_leaf, dir->i_sb->s_blocksize); + tmp_list->de_num_used = cpu_to_le16(0); + memset(&tmp_list->de_entries, 0, sizeof(*dx_entry)*num_used); + + for (j = 0; j < num_used; j++) { + dx_entry = &orig_list->de_entries[j]; + major_hash = le32_to_cpu(dx_entry->dx_major_hash); + if (major_hash >= split_hash) + ocfs2_dx_dir_leaf_insert_tail(new_dx_leaf, + dx_entry); + else + ocfs2_dx_dir_leaf_insert_tail(tmp_dx_leaf, + dx_entry); + } + memcpy(orig_dx_leaf, tmp_dx_leaf, dir->i_sb->s_blocksize); + + ocfs2_journal_dirty(handle, orig_dx_leaves[i]); + ocfs2_journal_dirty(handle, new_dx_leaves[i]); + } +} + +static int ocfs2_dx_dir_rebalance_credits(struct ocfs2_super *osb, + struct ocfs2_dx_root_block *dx_root) +{ + int credits = ocfs2_clusters_to_blocks(osb->sb, 2); + + credits += ocfs2_calc_extend_credits(osb->sb, &dx_root->dr_list, 1); + credits += ocfs2_quota_trans_credits(osb->sb); + return credits; +} + +/* + * Find the median value in dx_leaf_bh and allocate a new leaf to move + * half our entries into. + */ +static int ocfs2_dx_dir_rebalance(struct ocfs2_super *osb, struct inode *dir, + struct buffer_head *dx_root_bh, + struct buffer_head *dx_leaf_bh, + struct ocfs2_dx_hinfo *hinfo, u32 leaf_cpos, + u64 leaf_blkno) +{ + struct ocfs2_dx_leaf *dx_leaf = (struct ocfs2_dx_leaf *)dx_leaf_bh->b_data; + int credits, ret, i, num_used, did_quota = 0; + u32 cpos, split_hash, insert_hash = hinfo->major_hash; + u64 orig_leaves_start; + int num_dx_leaves; + struct buffer_head **orig_dx_leaves = NULL; + struct buffer_head **new_dx_leaves = NULL; + struct ocfs2_alloc_context *data_ac = NULL, *meta_ac = NULL; + struct ocfs2_extent_tree et; + handle_t *handle = NULL; + struct ocfs2_dx_root_block *dx_root; + struct ocfs2_dx_leaf *tmp_dx_leaf = NULL; + + mlog(0, "DX Dir: %llu, rebalance leaf leaf_blkno: %llu insert: %u\n", + (unsigned long long)OCFS2_I(dir)->ip_blkno, + (unsigned long long)leaf_blkno, insert_hash); + + ocfs2_init_dx_root_extent_tree(&et, dir, dx_root_bh); + + dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data; + /* + * XXX: This is a rather large limit. We should use a more + * realistic value. + */ + if (le32_to_cpu(dx_root->dr_clusters) == UINT_MAX) + return -ENOSPC; + + num_used = le16_to_cpu(dx_leaf->dl_list.de_num_used); + if (num_used < le16_to_cpu(dx_leaf->dl_list.de_count)) { + mlog(ML_ERROR, "DX Dir: %llu, Asked to rebalance empty leaf: " + "%llu, %d\n", (unsigned long long)OCFS2_I(dir)->ip_blkno, + (unsigned long long)leaf_blkno, num_used); + ret = -EIO; + goto out; + } + + orig_dx_leaves = ocfs2_dx_dir_kmalloc_leaves(osb->sb, &num_dx_leaves); + if (!orig_dx_leaves) { + ret = -ENOMEM; + mlog_errno(ret); + goto out; + } + + new_dx_leaves = ocfs2_dx_dir_kmalloc_leaves(osb->sb, NULL); + if (!new_dx_leaves) { + ret = -ENOMEM; + mlog_errno(ret); + goto out; + } + + ret = ocfs2_lock_allocators(dir, &et, 1, 0, &data_ac, &meta_ac); + if (ret) { + if (ret != -ENOSPC) + mlog_errno(ret); + goto out; + } + + credits = ocfs2_dx_dir_rebalance_credits(osb, dx_root); + handle = ocfs2_start_trans(osb, credits); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + handle = NULL; + mlog_errno(ret); + goto out; + } + + if (vfs_dq_alloc_space_nodirty(dir, + ocfs2_clusters_to_bytes(dir->i_sb, 1))) { + ret = -EDQUOT; + goto out_commit; + } + did_quota = 1; + + ret = ocfs2_journal_access_dl(handle, dir, dx_leaf_bh, + OCFS2_JOURNAL_ACCESS_WRITE); + if (ret) { + mlog_errno(ret); + goto out_commit; + } + + /* + * This block is changing anyway, so we can sort it in place. + */ + sort(dx_leaf->dl_list.de_entries, num_used, + sizeof(struct ocfs2_dx_entry), dx_leaf_sort_cmp, + dx_leaf_sort_swap); + + ret = ocfs2_journal_dirty(handle, dx_leaf_bh); + if (ret) { + mlog_errno(ret); + goto out_commit; + } + + ret = ocfs2_dx_dir_find_leaf_split(dx_leaf, leaf_cpos, insert_hash, + &split_hash); + if (ret) { + mlog_errno(ret); + goto out_commit; + } + + mlog(0, "Split leaf (%u) at %u, insert major hash is %u\n", + leaf_cpos, split_hash, insert_hash); + + /* + * We have to carefully order operations here. There are items + * which want to be in the new cluster before insert, but in + * order to put those items in the new cluster, we alter the + * old cluster. A failure to insert gets nasty. + * + * So, start by reserving writes to the old + * cluster. ocfs2_dx_dir_new_cluster will reserve writes on + * the new cluster for us, before inserting it. The insert + * won't happen if there's an error before that. Once the + * insert is done then, we can transfer from one leaf into the + * other without fear of hitting any error. + */ + + /* + * The leaf transfer wants some scratch space so that we don't + * wind up doing a bunch of expensive memmove(). + */ + tmp_dx_leaf = kmalloc(osb->sb->s_blocksize, GFP_NOFS); + if (!tmp_dx_leaf) { + ret = -ENOMEM; + mlog_errno(ret); + goto out_commit; + } + + orig_leaves_start = ocfs2_block_to_cluster_start(dir->i_sb, leaf_blkno); + ret = ocfs2_read_dx_leaves(dir, orig_leaves_start, num_dx_leaves, + orig_dx_leaves); + if (ret) { + mlog_errno(ret); + goto out_commit; + } + + for (i = 0; i < num_dx_leaves; i++) { + ret = ocfs2_journal_access_dl(handle, dir, orig_dx_leaves[i], + OCFS2_JOURNAL_ACCESS_WRITE); + if (ret) { + mlog_errno(ret); + goto out_commit; + } + } + + cpos = split_hash; + ret = ocfs2_dx_dir_new_cluster(dir, &et, cpos, handle, + data_ac, meta_ac, new_dx_leaves, + num_dx_leaves); + if (ret) { + mlog_errno(ret); + goto out_commit; + } + + ocfs2_dx_dir_transfer_leaf(dir, split_hash, handle, tmp_dx_leaf, + orig_dx_leaves, new_dx_leaves, num_dx_leaves); + +out_commit: + if (ret < 0 && did_quota) + vfs_dq_free_space_nodirty(dir, + ocfs2_clusters_to_bytes(dir->i_sb, 1)); + + ocfs2_commit_trans(osb, handle); + +out: + if (orig_dx_leaves || new_dx_leaves) { + for (i = 0; i < num_dx_leaves; i++) { + if (orig_dx_leaves) + brelse(orig_dx_leaves[i]); + if (new_dx_leaves) + brelse(new_dx_leaves[i]); + } + kfree(orig_dx_leaves); + kfree(new_dx_leaves); + } + + if (meta_ac) + ocfs2_free_alloc_context(meta_ac); + if (data_ac) + ocfs2_free_alloc_context(data_ac); + + kfree(tmp_dx_leaf); + return ret; +} + +static int ocfs2_find_dir_space_dx(struct ocfs2_super *osb, struct inode *dir, + struct buffer_head *di_bh, + struct buffer_head *dx_root_bh, + const char *name, int namelen, + struct ocfs2_dir_lookup_result *lookup) +{ + int ret, rebalanced = 0; + struct ocfs2_dx_root_block *dx_root; + struct buffer_head *dx_leaf_bh = NULL; + struct ocfs2_dx_leaf *dx_leaf; + u64 blkno; + u32 leaf_cpos; + + dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data; + +restart_search: + ret = ocfs2_dx_dir_lookup(dir, &dx_root->dr_list, &lookup->dl_hinfo, + &leaf_cpos, &blkno); + if (ret) { + mlog_errno(ret); + goto out; + } + + ret = ocfs2_read_dx_leaf(dir, blkno, &dx_leaf_bh); + if (ret) { + mlog_errno(ret); + goto out; + } + + dx_leaf = (struct ocfs2_dx_leaf *)dx_leaf_bh->b_data; + + if (le16_to_cpu(dx_leaf->dl_list.de_num_used) >= + le16_to_cpu(dx_leaf->dl_list.de_count)) { + if (rebalanced) { + /* + * Rebalancing should have provided us with + * space in an appropriate leaf. + * + * XXX: Is this an abnormal condition then? + * Should we print a message here? + */ + ret = -ENOSPC; + goto out; + } + + ret = ocfs2_dx_dir_rebalance(osb, dir, dx_root_bh, dx_leaf_bh, + &lookup->dl_hinfo, leaf_cpos, + blkno); + if (ret) { + if (ret != -ENOSPC) + mlog_errno(ret); + goto out; + } + + /* + * Restart the lookup. The rebalance might have + * changed which block our item fits into. Mark our + * progress, so we only execute this once. + */ + brelse(dx_leaf_bh); + dx_leaf_bh = NULL; + rebalanced = 1; + goto restart_search; + } + + lookup->dl_dx_leaf_bh = dx_leaf_bh; + dx_leaf_bh = NULL; + +out: + brelse(dx_leaf_bh); + return ret; +} + +static int ocfs2_search_dx_free_list(struct inode *dir, + struct buffer_head *dx_root_bh, + int namelen, + struct ocfs2_dir_lookup_result *lookup) +{ + int ret = -ENOSPC; + struct buffer_head *leaf_bh = NULL, *prev_leaf_bh = NULL; + struct ocfs2_dir_block_trailer *db; + u64 next_block; + int rec_len = OCFS2_DIR_REC_LEN(namelen); + struct ocfs2_dx_root_block *dx_root; + + dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data; + next_block = le64_to_cpu(dx_root->dr_free_blk); + + while (next_block) { + brelse(prev_leaf_bh); + prev_leaf_bh = leaf_bh; + leaf_bh = NULL; + + ret = ocfs2_read_dir_block_direct(dir, next_block, &leaf_bh); + if (ret) { + mlog_errno(ret); + goto out; + } + + db = ocfs2_trailer_from_bh(leaf_bh, dir->i_sb); + if (rec_len <= le16_to_cpu(db->db_free_rec_len)) { + lookup->dl_leaf_bh = leaf_bh; + lookup->dl_prev_leaf_bh = prev_leaf_bh; + leaf_bh = NULL; + prev_leaf_bh = NULL; + break; + } + + next_block = le64_to_cpu(db->db_free_next); + } + + if (!next_block) + ret = -ENOSPC; + +out: + + brelse(leaf_bh); + brelse(prev_leaf_bh); + return ret; +} + +static int ocfs2_expand_inline_dx_root(struct inode *dir, + struct buffer_head *dx_root_bh) +{ + int ret, num_dx_leaves, i, j, did_quota = 0; + struct buffer_head **dx_leaves = NULL; + struct ocfs2_extent_tree et; + u64 insert_blkno; + struct ocfs2_alloc_context *data_ac = NULL; + struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); + handle_t *handle = NULL; + struct ocfs2_dx_root_block *dx_root; + struct ocfs2_dx_entry_list *entry_list; + struct ocfs2_dx_entry *dx_entry; + struct ocfs2_dx_leaf *target_leaf; + + ret = ocfs2_reserve_clusters(osb, 1, &data_ac); + if (ret) { + mlog_errno(ret); + goto out; + } + + dx_leaves = ocfs2_dx_dir_kmalloc_leaves(osb->sb, &num_dx_leaves); + if (!dx_leaves) { + ret = -ENOMEM; + mlog_errno(ret); + goto out; + } + + handle = ocfs2_start_trans(osb, ocfs2_calc_dxi_expand_credits(osb->sb)); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + mlog_errno(ret); + goto out; + } + + if (vfs_dq_alloc_space_nodirty(dir, + ocfs2_clusters_to_bytes(osb->sb, 1))) { + ret = -EDQUOT; + goto out_commit; + } + did_quota = 1; + + /* + * We do this up front, before the allocation, so that a + * failure to add the dx_root_bh to the journal won't result + * us losing clusters. + */ + ret = ocfs2_journal_access_dr(handle, dir, dx_root_bh, + OCFS2_JOURNAL_ACCESS_WRITE); + if (ret) { + mlog_errno(ret); + goto out_commit; + } + + ret = __ocfs2_dx_dir_new_cluster(dir, 0, handle, data_ac, dx_leaves, + num_dx_leaves, &insert_blkno); + if (ret) { + mlog_errno(ret); + goto out_commit; + } + + /* + * Transfer the entries from our dx_root into the appropriate + * block + */ + dx_root = (struct ocfs2_dx_root_block *) dx_root_bh->b_data; + entry_list = &dx_root->dr_entries; + + for (i = 0; i < le16_to_cpu(entry_list->de_num_used); i++) { + dx_entry = &entry_list->de_entries[i]; + + j = __ocfs2_dx_dir_hash_idx(osb, + le32_to_cpu(dx_entry->dx_minor_hash)); + target_leaf = (struct ocfs2_dx_leaf *)dx_leaves[j]->b_data; + + ocfs2_dx_dir_leaf_insert_tail(target_leaf, dx_entry); + + /* Each leaf has been passed to the journal already + * via __ocfs2_dx_dir_new_cluster() */ + } + + dx_root->dr_flags &= ~OCFS2_DX_FLAG_INLINE; + memset(&dx_root->dr_list, 0, osb->sb->s_blocksize - + offsetof(struct ocfs2_dx_root_block, dr_list)); + dx_root->dr_list.l_count = + cpu_to_le16(ocfs2_extent_recs_per_dx_root(osb->sb)); + + /* This should never fail considering we start with an empty + * dx_root. */ + ocfs2_init_dx_root_extent_tree(&et, dir, dx_root_bh); + ret = ocfs2_insert_extent(osb, handle, dir, &et, 0, + insert_blkno, 1, 0, NULL); + if (ret) + mlog_errno(ret); + did_quota = 0; + + ocfs2_journal_dirty(handle, dx_root_bh); + +out_commit: + if (ret < 0 && did_quota) + vfs_dq_free_space_nodirty(dir, + ocfs2_clusters_to_bytes(dir->i_sb, 1)); + + ocfs2_commit_trans(osb, handle); + +out: + if (data_ac) + ocfs2_free_alloc_context(data_ac); + + if (dx_leaves) { + for (i = 0; i < num_dx_leaves; i++) + brelse(dx_leaves[i]); + kfree(dx_leaves); + } + return ret; +} + +static int ocfs2_inline_dx_has_space(struct buffer_head *dx_root_bh) +{ + struct ocfs2_dx_root_block *dx_root; + struct ocfs2_dx_entry_list *entry_list; + + dx_root = (struct ocfs2_dx_root_block *) dx_root_bh->b_data; + entry_list = &dx_root->dr_entries; + + if (le16_to_cpu(entry_list->de_num_used) >= + le16_to_cpu(entry_list->de_count)) + return -ENOSPC; + + return 0; +} + +static int ocfs2_prepare_dx_dir_for_insert(struct inode *dir, + struct buffer_head *di_bh, + const char *name, + int namelen, + struct ocfs2_dir_lookup_result *lookup) +{ + int ret, free_dx_root = 1; + struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); + struct buffer_head *dx_root_bh = NULL; + struct buffer_head *leaf_bh = NULL; + struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; + struct ocfs2_dx_root_block *dx_root; + + ret = ocfs2_read_dx_root(dir, di, &dx_root_bh); + if (ret) { + mlog_errno(ret); + goto out; + } + + dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data; + if (le32_to_cpu(dx_root->dr_num_entries) == OCFS2_DX_ENTRIES_MAX) { + ret = -ENOSPC; + mlog_errno(ret); + goto out; + } + + if (ocfs2_dx_root_inline(dx_root)) { + ret = ocfs2_inline_dx_has_space(dx_root_bh); + + if (ret == 0) + goto search_el; + + /* + * We ran out of room in the root block. Expand it to + * an extent, then allow ocfs2_find_dir_space_dx to do + * the rest. + */ + ret = ocfs2_expand_inline_dx_root(dir, dx_root_bh); + if (ret) { + mlog_errno(ret); + goto out; + } + } + + /* + * Insert preparation for an indexed directory is split into two + * steps. The call to find_dir_space_dx reserves room in the index for + * an additional item. If we run out of space there, it's a real error + * we can't continue on. + */ + ret = ocfs2_find_dir_space_dx(osb, dir, di_bh, dx_root_bh, name, + namelen, lookup); + if (ret) { + mlog_errno(ret); + goto out; + } + +search_el: + /* + * Next, we need to find space in the unindexed tree. This call + * searches using the free space linked list. If the unindexed tree + * lacks sufficient space, we'll expand it below. The expansion code + * is smart enough to add any new blocks to the free space list. + */ + ret = ocfs2_search_dx_free_list(dir, dx_root_bh, namelen, lookup); + if (ret && ret != -ENOSPC) { + mlog_errno(ret); + goto out; + } + + /* Do this up here - ocfs2_extend_dir might need the dx_root */ + lookup->dl_dx_root_bh = dx_root_bh; + free_dx_root = 0; + + if (ret == -ENOSPC) { + ret = ocfs2_extend_dir(osb, dir, di_bh, 1, lookup, &leaf_bh); + + if (ret) { + mlog_errno(ret); + goto out; + } + + /* + * We make the assumption here that new leaf blocks are added + * to the front of our free list. + */ + lookup->dl_prev_leaf_bh = NULL; + lookup->dl_leaf_bh = leaf_bh; + } + +out: + if (free_dx_root) + brelse(dx_root_bh); + return ret; +} + +/* + * Get a directory ready for insert. Any directory allocation required + * happens here. Success returns zero, and enough context in the dir + * lookup result that ocfs2_add_entry() will be able complete the task + * with minimal performance impact. + */ int ocfs2_prepare_dir_for_insert(struct ocfs2_super *osb, struct inode *dir, struct buffer_head *parent_fe_bh, const char *name, int namelen, - struct buffer_head **ret_de_bh) + struct ocfs2_dir_lookup_result *lookup) { int ret; unsigned int blocks_wanted = 1; @@ -1984,14 +4367,34 @@ int ocfs2_prepare_dir_for_insert(struct ocfs2_super *osb, mlog(0, "getting ready to insert namelen %d into dir %llu\n", namelen, (unsigned long long)OCFS2_I(dir)->ip_blkno); - *ret_de_bh = NULL; - if (!namelen) { ret = -EINVAL; mlog_errno(ret); goto out; } + /* + * Do this up front to reduce confusion. + * + * The directory might start inline, then be turned into an + * indexed one, in which case we'd need to hash deep inside + * ocfs2_find_dir_space_id(). Since + * ocfs2_prepare_dx_dir_for_insert() also needs this hash + * done, there seems no point in spreading out the calls. We + * can optimize away the case where the file system doesn't + * support indexing. + */ + if (ocfs2_supports_indexed_dirs(osb)) + ocfs2_dx_dir_name_hash(dir, name, namelen, &lookup->dl_hinfo); + + if (ocfs2_dir_indexed(dir)) { + ret = ocfs2_prepare_dx_dir_for_insert(dir, parent_fe_bh, + name, namelen, lookup); + if (ret) + mlog_errno(ret); + goto out; + } + if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { ret = ocfs2_find_dir_space_id(dir, parent_fe_bh, name, namelen, &bh, &blocks_wanted); @@ -2010,7 +4413,7 @@ int ocfs2_prepare_dir_for_insert(struct ocfs2_super *osb, BUG_ON(bh); ret = ocfs2_extend_dir(osb, dir, parent_fe_bh, blocks_wanted, - &bh); + lookup, &bh); if (ret) { if (ret != -ENOSPC) mlog_errno(ret); @@ -2020,9 +4423,154 @@ int ocfs2_prepare_dir_for_insert(struct ocfs2_super *osb, BUG_ON(!bh); } - *ret_de_bh = bh; + lookup->dl_leaf_bh = bh; bh = NULL; out: brelse(bh); return ret; } + +static int ocfs2_dx_dir_remove_index(struct inode *dir, + struct buffer_head *di_bh, + struct buffer_head *dx_root_bh) +{ + int ret; + struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); + struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; + struct ocfs2_dx_root_block *dx_root; + struct inode *dx_alloc_inode = NULL; + struct buffer_head *dx_alloc_bh = NULL; + handle_t *handle; + u64 blk; + u16 bit; + u64 bg_blkno; + + dx_root = (struct ocfs2_dx_root_block *) dx_root_bh->b_data; + + dx_alloc_inode = ocfs2_get_system_file_inode(osb, + EXTENT_ALLOC_SYSTEM_INODE, + le16_to_cpu(dx_root->dr_suballoc_slot)); + if (!dx_alloc_inode) { + ret = -ENOMEM; + mlog_errno(ret); + goto out; + } + mutex_lock(&dx_alloc_inode->i_mutex); + + ret = ocfs2_inode_lock(dx_alloc_inode, &dx_alloc_bh, 1); + if (ret) { + mlog_errno(ret); + goto out_mutex; + } + + handle = ocfs2_start_trans(osb, OCFS2_DX_ROOT_REMOVE_CREDITS); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + mlog_errno(ret); + goto out_unlock; + } + + ret = ocfs2_journal_access_di(handle, dir, di_bh, + OCFS2_JOURNAL_ACCESS_WRITE); + if (ret) { + mlog_errno(ret); + goto out_commit; + } + + OCFS2_I(dir)->ip_dyn_features &= ~OCFS2_INDEXED_DIR_FL; + di->i_dyn_features = cpu_to_le16(OCFS2_I(dir)->ip_dyn_features); + di->i_dx_root = cpu_to_le64(0ULL); + + ocfs2_journal_dirty(handle, di_bh); + + blk = le64_to_cpu(dx_root->dr_blkno); + bit = le16_to_cpu(dx_root->dr_suballoc_bit); + bg_blkno = ocfs2_which_suballoc_group(blk, bit); + ret = ocfs2_free_suballoc_bits(handle, dx_alloc_inode, dx_alloc_bh, + bit, bg_blkno, 1); + if (ret) + mlog_errno(ret); + +out_commit: + ocfs2_commit_trans(osb, handle); + +out_unlock: + ocfs2_inode_unlock(dx_alloc_inode, 1); + +out_mutex: + mutex_unlock(&dx_alloc_inode->i_mutex); + brelse(dx_alloc_bh); +out: + iput(dx_alloc_inode); + return ret; +} + +int ocfs2_dx_dir_truncate(struct inode *dir, struct buffer_head *di_bh) +{ + int ret; + unsigned int uninitialized_var(clen); + u32 major_hash = UINT_MAX, p_cpos, uninitialized_var(cpos); + u64 uninitialized_var(blkno); + struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); + struct buffer_head *dx_root_bh = NULL; + struct ocfs2_dx_root_block *dx_root; + struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; + struct ocfs2_cached_dealloc_ctxt dealloc; + struct ocfs2_extent_tree et; + + ocfs2_init_dealloc_ctxt(&dealloc); + + if (!ocfs2_dir_indexed(dir)) + return 0; + + ret = ocfs2_read_dx_root(dir, di, &dx_root_bh); + if (ret) { + mlog_errno(ret); + goto out; + } + dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data; + + if (ocfs2_dx_root_inline(dx_root)) + goto remove_index; + + ocfs2_init_dx_root_extent_tree(&et, dir, dx_root_bh); + + /* XXX: What if dr_clusters is too large? */ + while (le32_to_cpu(dx_root->dr_clusters)) { + ret = ocfs2_dx_dir_lookup_rec(dir, &dx_root->dr_list, + major_hash, &cpos, &blkno, &clen); + if (ret) { + mlog_errno(ret); + goto out; + } + + p_cpos = ocfs2_blocks_to_clusters(dir->i_sb, blkno); + + ret = ocfs2_remove_btree_range(dir, &et, cpos, p_cpos, clen, + &dealloc); + if (ret) { + mlog_errno(ret); + goto out; + } + + if (cpos == 0) + break; + + major_hash = cpos - 1; + } + +remove_index: + ret = ocfs2_dx_dir_remove_index(dir, di_bh, dx_root_bh); + if (ret) { + mlog_errno(ret); + goto out; + } + + ocfs2_remove_from_cache(dir, dx_root_bh); +out: + ocfs2_schedule_truncate_log_flush(osb, 1); + ocfs2_run_deallocs(osb, &dealloc); + + brelse(dx_root_bh); + return ret; +} diff --git a/fs/ocfs2/dir.h b/fs/ocfs2/dir.h index c511e2e18e9f..e683f3deb645 100644 --- a/fs/ocfs2/dir.h +++ b/fs/ocfs2/dir.h @@ -26,44 +26,70 @@ #ifndef OCFS2_DIR_H #define OCFS2_DIR_H -struct buffer_head *ocfs2_find_entry(const char *name, - int namelen, - struct inode *dir, - struct ocfs2_dir_entry **res_dir); +struct ocfs2_dx_hinfo { + u32 major_hash; + u32 minor_hash; +}; + +struct ocfs2_dir_lookup_result { + struct buffer_head *dl_leaf_bh; /* Unindexed leaf + * block */ + struct ocfs2_dir_entry *dl_entry; /* Target dirent in + * unindexed leaf */ + + struct buffer_head *dl_dx_root_bh; /* Root of indexed + * tree */ + + struct buffer_head *dl_dx_leaf_bh; /* Indexed leaf block */ + struct ocfs2_dx_entry *dl_dx_entry; /* Target dx_entry in + * indexed leaf */ + struct ocfs2_dx_hinfo dl_hinfo; /* Name hash results */ + + struct buffer_head *dl_prev_leaf_bh;/* Previous entry in + * dir free space + * list. NULL if + * previous entry is + * dx root block. */ +}; + +void ocfs2_free_dir_lookup_result(struct ocfs2_dir_lookup_result *res); + +int ocfs2_find_entry(const char *name, int namelen, + struct inode *dir, + struct ocfs2_dir_lookup_result *lookup); int ocfs2_delete_entry(handle_t *handle, struct inode *dir, - struct ocfs2_dir_entry *de_del, - struct buffer_head *bh); + struct ocfs2_dir_lookup_result *res); int __ocfs2_add_entry(handle_t *handle, struct inode *dir, const char *name, int namelen, struct inode *inode, u64 blkno, struct buffer_head *parent_fe_bh, - struct buffer_head *insert_bh); + struct ocfs2_dir_lookup_result *lookup); static inline int ocfs2_add_entry(handle_t *handle, struct dentry *dentry, struct inode *inode, u64 blkno, struct buffer_head *parent_fe_bh, - struct buffer_head *insert_bh) + struct ocfs2_dir_lookup_result *lookup) { return __ocfs2_add_entry(handle, dentry->d_parent->d_inode, dentry->d_name.name, dentry->d_name.len, - inode, blkno, parent_fe_bh, insert_bh); + inode, blkno, parent_fe_bh, lookup); } int ocfs2_update_entry(struct inode *dir, handle_t *handle, - struct buffer_head *de_bh, struct ocfs2_dir_entry *de, + struct ocfs2_dir_lookup_result *res, struct inode *new_entry_inode); int ocfs2_check_dir_for_entry(struct inode *dir, const char *name, int namelen); int ocfs2_empty_dir(struct inode *inode); + int ocfs2_find_files_on_disk(const char *name, int namelen, u64 *blkno, struct inode *inode, - struct buffer_head **dirent_bh, - struct ocfs2_dir_entry **dirent); + struct ocfs2_dir_lookup_result *res); int ocfs2_lookup_ino_from_name(struct inode *dir, const char *name, int namelen, u64 *blkno); int ocfs2_readdir(struct file *filp, void *dirent, filldir_t filldir); @@ -74,14 +100,17 @@ int ocfs2_prepare_dir_for_insert(struct ocfs2_super *osb, struct buffer_head *parent_fe_bh, const char *name, int namelen, - struct buffer_head **ret_de_bh); + struct ocfs2_dir_lookup_result *lookup); struct ocfs2_alloc_context; int ocfs2_fill_new_dir(struct ocfs2_super *osb, handle_t *handle, struct inode *parent, struct inode *inode, struct buffer_head *fe_bh, - struct ocfs2_alloc_context *data_ac); + struct ocfs2_alloc_context *data_ac, + struct ocfs2_alloc_context *meta_ac); + +int ocfs2_dx_dir_truncate(struct inode *dir, struct buffer_head *di_bh); struct ocfs2_dir_block_trailer *ocfs2_dir_trailer_from_size(int blocksize, void *data); diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h index bb53714813ab..0102be35980c 100644 --- a/fs/ocfs2/dlm/dlmcommon.h +++ b/fs/ocfs2/dlm/dlmcommon.h @@ -52,16 +52,12 @@ enum dlm_mle_type { DLM_MLE_BLOCK, DLM_MLE_MASTER, - DLM_MLE_MIGRATION -}; - -struct dlm_lock_name { - u8 len; - u8 name[DLM_LOCKID_NAME_MAX]; + DLM_MLE_MIGRATION, + DLM_MLE_NUM_TYPES }; struct dlm_master_list_entry { - struct list_head list; + struct hlist_node master_hash_node; struct list_head hb_events; struct dlm_ctxt *dlm; spinlock_t spinlock; @@ -78,10 +74,10 @@ struct dlm_master_list_entry { enum dlm_mle_type type; struct o2hb_callback_func mle_hb_up; struct o2hb_callback_func mle_hb_down; - union { - struct dlm_lock_resource *res; - struct dlm_lock_name name; - } u; + struct dlm_lock_resource *mleres; + unsigned char mname[DLM_LOCKID_NAME_MAX]; + unsigned int mnamelen; + unsigned int mnamehash; }; enum dlm_ast_type { @@ -151,13 +147,14 @@ struct dlm_ctxt unsigned long recovery_map[BITS_TO_LONGS(O2NM_MAX_NODES)]; struct dlm_recovery_ctxt reco; spinlock_t master_lock; - struct list_head master_list; + struct hlist_head **master_hash; struct list_head mle_hb_events; /* these give a really vague idea of the system load */ - atomic_t local_resources; - atomic_t remote_resources; - atomic_t unknown_resources; + atomic_t mle_tot_count[DLM_MLE_NUM_TYPES]; + atomic_t mle_cur_count[DLM_MLE_NUM_TYPES]; + atomic_t res_tot_count; + atomic_t res_cur_count; struct dlm_debug_ctxt *dlm_debug_ctxt; struct dentry *dlm_debugfs_subroot; @@ -195,6 +192,13 @@ static inline struct hlist_head *dlm_lockres_hash(struct dlm_ctxt *dlm, unsigned return dlm->lockres_hash[(i / DLM_BUCKETS_PER_PAGE) % DLM_HASH_PAGES] + (i % DLM_BUCKETS_PER_PAGE); } +static inline struct hlist_head *dlm_master_hash(struct dlm_ctxt *dlm, + unsigned i) +{ + return dlm->master_hash[(i / DLM_BUCKETS_PER_PAGE) % DLM_HASH_PAGES] + + (i % DLM_BUCKETS_PER_PAGE); +} + /* these keventd work queue items are for less-frequently * called functions that cannot be directly called from the * net message handlers for some reason, usually because @@ -848,9 +852,7 @@ struct dlm_lock_resource * dlm_lookup_lockres(struct dlm_ctxt *dlm, unsigned int len); int dlm_is_host_down(int errno); -void dlm_change_lockres_owner(struct dlm_ctxt *dlm, - struct dlm_lock_resource *res, - u8 owner); + struct dlm_lock_resource * dlm_get_lock_resource(struct dlm_ctxt *dlm, const char *lockid, int namelen, @@ -1008,6 +1010,9 @@ static inline void __dlm_wait_on_lockres(struct dlm_lock_resource *res) DLM_LOCK_RES_MIGRATING)); } +void __dlm_unlink_mle(struct dlm_ctxt *dlm, struct dlm_master_list_entry *mle); +void __dlm_insert_mle(struct dlm_ctxt *dlm, struct dlm_master_list_entry *mle); + /* create/destroy slab caches */ int dlm_init_master_caches(void); void dlm_destroy_master_caches(void); @@ -1110,6 +1115,23 @@ static inline int dlm_node_iter_next(struct dlm_node_iter *iter) return bit; } +static inline void dlm_set_lockres_owner(struct dlm_ctxt *dlm, + struct dlm_lock_resource *res, + u8 owner) +{ + assert_spin_locked(&res->spinlock); + + res->owner = owner; +} +static inline void dlm_change_lockres_owner(struct dlm_ctxt *dlm, + struct dlm_lock_resource *res, + u8 owner) +{ + assert_spin_locked(&res->spinlock); + + if (owner != res->owner) + dlm_set_lockres_owner(dlm, res, owner); +} #endif /* DLMCOMMON_H */ diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c index b32f60a5acfb..df52f706f669 100644 --- a/fs/ocfs2/dlm/dlmdebug.c +++ b/fs/ocfs2/dlm/dlmdebug.c @@ -287,18 +287,8 @@ static int stringify_nodemap(unsigned long *nodemap, int maxnodes, static int dump_mle(struct dlm_master_list_entry *mle, char *buf, int len) { int out = 0; - unsigned int namelen; - const char *name; char *mle_type; - if (mle->type != DLM_MLE_MASTER) { - namelen = mle->u.name.len; - name = mle->u.name.name; - } else { - namelen = mle->u.res->lockname.len; - name = mle->u.res->lockname.name; - } - if (mle->type == DLM_MLE_BLOCK) mle_type = "BLK"; else if (mle->type == DLM_MLE_MASTER) @@ -306,7 +296,7 @@ static int dump_mle(struct dlm_master_list_entry *mle, char *buf, int len) else mle_type = "MIG"; - out += stringify_lockname(name, namelen, buf + out, len - out); + out += stringify_lockname(mle->mname, mle->mnamelen, buf + out, len - out); out += snprintf(buf + out, len - out, "\t%3s\tmas=%3u\tnew=%3u\tevt=%1d\tuse=%1d\tref=%3d\n", mle_type, mle->master, mle->new_master, @@ -501,23 +491,33 @@ static struct file_operations debug_purgelist_fops = { static int debug_mle_print(struct dlm_ctxt *dlm, struct debug_buffer *db) { struct dlm_master_list_entry *mle; - int out = 0; - unsigned long total = 0; + struct hlist_head *bucket; + struct hlist_node *list; + int i, out = 0; + unsigned long total = 0, longest = 0, bktcnt; out += snprintf(db->buf + out, db->len - out, "Dumping MLEs for Domain: %s\n", dlm->name); spin_lock(&dlm->master_lock); - list_for_each_entry(mle, &dlm->master_list, list) { - ++total; - if (db->len - out < 200) - continue; - out += dump_mle(mle, db->buf + out, db->len - out); + for (i = 0; i < DLM_HASH_BUCKETS; i++) { + bucket = dlm_master_hash(dlm, i); + hlist_for_each(list, bucket) { + mle = hlist_entry(list, struct dlm_master_list_entry, + master_hash_node); + ++total; + ++bktcnt; + if (db->len - out < 200) + continue; + out += dump_mle(mle, db->buf + out, db->len - out); + } + longest = max(longest, bktcnt); + bktcnt = 0; } spin_unlock(&dlm->master_lock); out += snprintf(db->buf + out, db->len - out, - "Total on list: %ld\n", total); + "Total: %ld, Longest: %ld\n", total, longest); return out; } @@ -756,12 +756,8 @@ static int debug_state_print(struct dlm_ctxt *dlm, struct debug_buffer *db) int out = 0; struct dlm_reco_node_data *node; char *state; - int lres, rres, ures, tres; - - lres = atomic_read(&dlm->local_resources); - rres = atomic_read(&dlm->remote_resources); - ures = atomic_read(&dlm->unknown_resources); - tres = lres + rres + ures; + int cur_mles = 0, tot_mles = 0; + int i; spin_lock(&dlm->spinlock); @@ -804,21 +800,48 @@ static int debug_state_print(struct dlm_ctxt *dlm, struct debug_buffer *db) db->buf + out, db->len - out); out += snprintf(db->buf + out, db->len - out, "\n"); - /* Mastered Resources Total: xxx Locally: xxx Remotely: ... */ + /* Lock Resources: xxx (xxx) */ + out += snprintf(db->buf + out, db->len - out, + "Lock Resources: %d (%d)\n", + atomic_read(&dlm->res_cur_count), + atomic_read(&dlm->res_tot_count)); + + for (i = 0; i < DLM_MLE_NUM_TYPES; ++i) + tot_mles += atomic_read(&dlm->mle_tot_count[i]); + + for (i = 0; i < DLM_MLE_NUM_TYPES; ++i) + cur_mles += atomic_read(&dlm->mle_cur_count[i]); + + /* MLEs: xxx (xxx) */ + out += snprintf(db->buf + out, db->len - out, + "MLEs: %d (%d)\n", cur_mles, tot_mles); + + /* Blocking: xxx (xxx) */ + out += snprintf(db->buf + out, db->len - out, + " Blocking: %d (%d)\n", + atomic_read(&dlm->mle_cur_count[DLM_MLE_BLOCK]), + atomic_read(&dlm->mle_tot_count[DLM_MLE_BLOCK])); + + /* Mastery: xxx (xxx) */ + out += snprintf(db->buf + out, db->len - out, + " Mastery: %d (%d)\n", + atomic_read(&dlm->mle_cur_count[DLM_MLE_MASTER]), + atomic_read(&dlm->mle_tot_count[DLM_MLE_MASTER])); + + /* Migration: xxx (xxx) */ out += snprintf(db->buf + out, db->len - out, - "Mastered Resources Total: %d Locally: %d " - "Remotely: %d Unknown: %d\n", - tres, lres, rres, ures); + " Migration: %d (%d)\n", + atomic_read(&dlm->mle_cur_count[DLM_MLE_MIGRATION]), + atomic_read(&dlm->mle_tot_count[DLM_MLE_MIGRATION])); /* Lists: Dirty=Empty Purge=InUse PendingASTs=Empty ... */ out += snprintf(db->buf + out, db->len - out, "Lists: Dirty=%s Purge=%s PendingASTs=%s " - "PendingBASTs=%s Master=%s\n", + "PendingBASTs=%s\n", (list_empty(&dlm->dirty_list) ? "Empty" : "InUse"), (list_empty(&dlm->purge_list) ? "Empty" : "InUse"), (list_empty(&dlm->pending_asts) ? "Empty" : "InUse"), - (list_empty(&dlm->pending_basts) ? "Empty" : "InUse"), - (list_empty(&dlm->master_list) ? "Empty" : "InUse")); + (list_empty(&dlm->pending_basts) ? "Empty" : "InUse")); /* Purge Count: xxx Refs: xxx */ out += snprintf(db->buf + out, db->len - out, diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c index d8d578f45613..4d9e6b288dd8 100644 --- a/fs/ocfs2/dlm/dlmdomain.c +++ b/fs/ocfs2/dlm/dlmdomain.c @@ -304,6 +304,9 @@ static void dlm_free_ctxt_mem(struct dlm_ctxt *dlm) if (dlm->lockres_hash) dlm_free_pagevec((void **)dlm->lockres_hash, DLM_HASH_PAGES); + if (dlm->master_hash) + dlm_free_pagevec((void **)dlm->master_hash, DLM_HASH_PAGES); + if (dlm->name) kfree(dlm->name); @@ -1534,12 +1537,27 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain, for (i = 0; i < DLM_HASH_BUCKETS; i++) INIT_HLIST_HEAD(dlm_lockres_hash(dlm, i)); + dlm->master_hash = (struct hlist_head **) + dlm_alloc_pagevec(DLM_HASH_PAGES); + if (!dlm->master_hash) { + mlog_errno(-ENOMEM); + dlm_free_pagevec((void **)dlm->lockres_hash, DLM_HASH_PAGES); + kfree(dlm->name); + kfree(dlm); + dlm = NULL; + goto leave; + } + + for (i = 0; i < DLM_HASH_BUCKETS; i++) + INIT_HLIST_HEAD(dlm_master_hash(dlm, i)); + strcpy(dlm->name, domain); dlm->key = key; dlm->node_num = o2nm_this_node(); ret = dlm_create_debugfs_subroot(dlm); if (ret < 0) { + dlm_free_pagevec((void **)dlm->master_hash, DLM_HASH_PAGES); dlm_free_pagevec((void **)dlm->lockres_hash, DLM_HASH_PAGES); kfree(dlm->name); kfree(dlm); @@ -1579,7 +1597,6 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain, init_waitqueue_head(&dlm->reco.event); init_waitqueue_head(&dlm->ast_wq); init_waitqueue_head(&dlm->migration_wq); - INIT_LIST_HEAD(&dlm->master_list); INIT_LIST_HEAD(&dlm->mle_hb_events); dlm->joining_node = DLM_LOCK_RES_OWNER_UNKNOWN; @@ -1587,9 +1604,13 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain, dlm->reco.new_master = O2NM_INVALID_NODE_NUM; dlm->reco.dead_node = O2NM_INVALID_NODE_NUM; - atomic_set(&dlm->local_resources, 0); - atomic_set(&dlm->remote_resources, 0); - atomic_set(&dlm->unknown_resources, 0); + + atomic_set(&dlm->res_tot_count, 0); + atomic_set(&dlm->res_cur_count, 0); + for (i = 0; i < DLM_MLE_NUM_TYPES; ++i) { + atomic_set(&dlm->mle_tot_count[i], 0); + atomic_set(&dlm->mle_cur_count[i], 0); + } spin_lock_init(&dlm->work_lock); INIT_LIST_HEAD(&dlm->work_list); diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 0a2813947853..f8b653fcd4dd 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -73,22 +73,13 @@ static inline int dlm_mle_equal(struct dlm_ctxt *dlm, const char *name, unsigned int namelen) { - struct dlm_lock_resource *res; - if (dlm != mle->dlm) return 0; - if (mle->type == DLM_MLE_BLOCK || - mle->type == DLM_MLE_MIGRATION) { - if (namelen != mle->u.name.len || - memcmp(name, mle->u.name.name, namelen)!=0) - return 0; - } else { - res = mle->u.res; - if (namelen != res->lockname.len || - memcmp(res->lockname.name, name, namelen) != 0) - return 0; - } + if (namelen != mle->mnamelen || + memcmp(name, mle->mname, namelen) != 0) + return 0; + return 1; } @@ -283,7 +274,7 @@ static void dlm_init_mle(struct dlm_master_list_entry *mle, mle->dlm = dlm; mle->type = type; - INIT_LIST_HEAD(&mle->list); + INIT_HLIST_NODE(&mle->master_hash_node); INIT_LIST_HEAD(&mle->hb_events); memset(mle->maybe_map, 0, sizeof(mle->maybe_map)); spin_lock_init(&mle->spinlock); @@ -295,19 +286,27 @@ static void dlm_init_mle(struct dlm_master_list_entry *mle, mle->new_master = O2NM_MAX_NODES; mle->inuse = 0; + BUG_ON(mle->type != DLM_MLE_BLOCK && + mle->type != DLM_MLE_MASTER && + mle->type != DLM_MLE_MIGRATION); + if (mle->type == DLM_MLE_MASTER) { BUG_ON(!res); - mle->u.res = res; - } else if (mle->type == DLM_MLE_BLOCK) { - BUG_ON(!name); - memcpy(mle->u.name.name, name, namelen); - mle->u.name.len = namelen; - } else /* DLM_MLE_MIGRATION */ { + mle->mleres = res; + memcpy(mle->mname, res->lockname.name, res->lockname.len); + mle->mnamelen = res->lockname.len; + mle->mnamehash = res->lockname.hash; + } else { BUG_ON(!name); - memcpy(mle->u.name.name, name, namelen); - mle->u.name.len = namelen; + mle->mleres = NULL; + memcpy(mle->mname, name, namelen); + mle->mnamelen = namelen; + mle->mnamehash = dlm_lockid_hash(name, namelen); } + atomic_inc(&dlm->mle_tot_count[mle->type]); + atomic_inc(&dlm->mle_cur_count[mle->type]); + /* copy off the node_map and register hb callbacks on our copy */ memcpy(mle->node_map, dlm->domain_map, sizeof(mle->node_map)); memcpy(mle->vote_map, dlm->domain_map, sizeof(mle->vote_map)); @@ -318,6 +317,24 @@ static void dlm_init_mle(struct dlm_master_list_entry *mle, __dlm_mle_attach_hb_events(dlm, mle); } +void __dlm_unlink_mle(struct dlm_ctxt *dlm, struct dlm_master_list_entry *mle) +{ + assert_spin_locked(&dlm->spinlock); + assert_spin_locked(&dlm->master_lock); + + if (!hlist_unhashed(&mle->master_hash_node)) + hlist_del_init(&mle->master_hash_node); +} + +void __dlm_insert_mle(struct dlm_ctxt *dlm, struct dlm_master_list_entry *mle) +{ + struct hlist_head *bucket; + + assert_spin_locked(&dlm->master_lock); + + bucket = dlm_master_hash(dlm, mle->mnamehash); + hlist_add_head(&mle->master_hash_node, bucket); +} /* returns 1 if found, 0 if not */ static int dlm_find_mle(struct dlm_ctxt *dlm, @@ -325,10 +342,17 @@ static int dlm_find_mle(struct dlm_ctxt *dlm, char *name, unsigned int namelen) { struct dlm_master_list_entry *tmpmle; + struct hlist_head *bucket; + struct hlist_node *list; + unsigned int hash; assert_spin_locked(&dlm->master_lock); - list_for_each_entry(tmpmle, &dlm->master_list, list) { + hash = dlm_lockid_hash(name, namelen); + bucket = dlm_master_hash(dlm, hash); + hlist_for_each(list, bucket) { + tmpmle = hlist_entry(list, struct dlm_master_list_entry, + master_hash_node); if (!dlm_mle_equal(dlm, tmpmle, name, namelen)) continue; dlm_get_mle(tmpmle); @@ -408,24 +432,20 @@ static void dlm_mle_release(struct kref *kref) mle = container_of(kref, struct dlm_master_list_entry, mle_refs); dlm = mle->dlm; - if (mle->type != DLM_MLE_MASTER) { - mlog(0, "calling mle_release for %.*s, type %d\n", - mle->u.name.len, mle->u.name.name, mle->type); - } else { - mlog(0, "calling mle_release for %.*s, type %d\n", - mle->u.res->lockname.len, - mle->u.res->lockname.name, mle->type); - } assert_spin_locked(&dlm->spinlock); assert_spin_locked(&dlm->master_lock); + mlog(0, "Releasing mle for %.*s, type %d\n", mle->mnamelen, mle->mname, + mle->type); + /* remove from list if not already */ - if (!list_empty(&mle->list)) - list_del_init(&mle->list); + __dlm_unlink_mle(dlm, mle); /* detach the mle from the domain node up/down events */ __dlm_mle_detach_hb_events(dlm, mle); + atomic_dec(&dlm->mle_cur_count[mle->type]); + /* NOTE: kfree under spinlock here. * if this is bad, we can move this to a freelist. */ kmem_cache_free(dlm_mle_cache, mle); @@ -465,43 +485,6 @@ void dlm_destroy_master_caches(void) kmem_cache_destroy(dlm_lockres_cache); } -static void dlm_set_lockres_owner(struct dlm_ctxt *dlm, - struct dlm_lock_resource *res, - u8 owner) -{ - assert_spin_locked(&res->spinlock); - - mlog_entry("%.*s, %u\n", res->lockname.len, res->lockname.name, owner); - - if (owner == dlm->node_num) - atomic_inc(&dlm->local_resources); - else if (owner == DLM_LOCK_RES_OWNER_UNKNOWN) - atomic_inc(&dlm->unknown_resources); - else - atomic_inc(&dlm->remote_resources); - - res->owner = owner; -} - -void dlm_change_lockres_owner(struct dlm_ctxt *dlm, - struct dlm_lock_resource *res, u8 owner) -{ - assert_spin_locked(&res->spinlock); - - if (owner == res->owner) - return; - - if (res->owner == dlm->node_num) - atomic_dec(&dlm->local_resources); - else if (res->owner == DLM_LOCK_RES_OWNER_UNKNOWN) - atomic_dec(&dlm->unknown_resources); - else - atomic_dec(&dlm->remote_resources); - - dlm_set_lockres_owner(dlm, res, owner); -} - - static void dlm_lockres_release(struct kref *kref) { struct dlm_lock_resource *res; @@ -527,6 +510,8 @@ static void dlm_lockres_release(struct kref *kref) } spin_unlock(&dlm->track_lock); + atomic_dec(&dlm->res_cur_count); + dlm_put(dlm); if (!hlist_unhashed(&res->hash_node) || @@ -607,6 +592,9 @@ static void dlm_init_lockres(struct dlm_ctxt *dlm, kref_init(&res->refs); + atomic_inc(&dlm->res_tot_count); + atomic_inc(&dlm->res_cur_count); + /* just for consistency */ spin_lock(&res->spinlock); dlm_set_lockres_owner(dlm, res, DLM_LOCK_RES_OWNER_UNKNOWN); @@ -843,7 +831,7 @@ lookup: alloc_mle = NULL; dlm_init_mle(mle, DLM_MLE_MASTER, dlm, res, NULL, 0); set_bit(dlm->node_num, mle->maybe_map); - list_add(&mle->list, &dlm->master_list); + __dlm_insert_mle(dlm, mle); /* still holding the dlm spinlock, check the recovery map * to see if there are any nodes that still need to be @@ -1270,7 +1258,7 @@ static int dlm_restart_lock_mastery(struct dlm_ctxt *dlm, res->lockname.len, res->lockname.name); mle->type = DLM_MLE_MASTER; - mle->u.res = res; + mle->mleres = res; } } } @@ -1315,14 +1303,8 @@ static int dlm_do_master_request(struct dlm_lock_resource *res, BUG_ON(mle->type == DLM_MLE_MIGRATION); - if (mle->type != DLM_MLE_MASTER) { - request.namelen = mle->u.name.len; - memcpy(request.name, mle->u.name.name, request.namelen); - } else { - request.namelen = mle->u.res->lockname.len; - memcpy(request.name, mle->u.res->lockname.name, - request.namelen); - } + request.namelen = (u8)mle->mnamelen; + memcpy(request.name, mle->mname, request.namelen); again: ret = o2net_send_message(DLM_MASTER_REQUEST_MSG, dlm->key, &request, @@ -1575,7 +1557,7 @@ way_up_top: // "add the block.\n"); dlm_init_mle(mle, DLM_MLE_BLOCK, dlm, NULL, name, namelen); set_bit(request->node_idx, mle->maybe_map); - list_add(&mle->list, &dlm->master_list); + __dlm_insert_mle(dlm, mle); response = DLM_MASTER_RESP_NO; } else { // mlog(0, "mle was found\n"); @@ -1967,7 +1949,7 @@ ok: assert->node_idx, rr, extra_ref, mle->inuse); dlm_print_one_mle(mle); } - list_del_init(&mle->list); + __dlm_unlink_mle(dlm, mle); __dlm_mle_detach_hb_events(dlm, mle); __dlm_put_mle(mle); if (extra_ref) { @@ -3159,10 +3141,8 @@ static int dlm_add_migration_mle(struct dlm_ctxt *dlm, tmp->master = master; atomic_set(&tmp->woken, 1); wake_up(&tmp->wq); - /* remove it from the list so that only one - * mle will be found */ - list_del_init(&tmp->list); - /* this was obviously WRONG. mle is uninited here. should be tmp. */ + /* remove it so that only one mle will be found */ + __dlm_unlink_mle(dlm, tmp); __dlm_mle_detach_hb_events(dlm, tmp); ret = DLM_MIGRATE_RESPONSE_MASTERY_REF; mlog(0, "%s:%.*s: master=%u, newmaster=%u, " @@ -3181,137 +3161,164 @@ static int dlm_add_migration_mle(struct dlm_ctxt *dlm, mle->master = master; /* do this for consistency with other mle types */ set_bit(new_master, mle->maybe_map); - list_add(&mle->list, &dlm->master_list); + __dlm_insert_mle(dlm, mle); return ret; } - -void dlm_clean_master_list(struct dlm_ctxt *dlm, u8 dead_node) +/* + * Sets the owner of the lockres, associated to the mle, to UNKNOWN + */ +static struct dlm_lock_resource *dlm_reset_mleres_owner(struct dlm_ctxt *dlm, + struct dlm_master_list_entry *mle) { - struct dlm_master_list_entry *mle, *next; struct dlm_lock_resource *res; - unsigned int hash; - mlog_entry("dlm=%s, dead node=%u\n", dlm->name, dead_node); -top: - assert_spin_locked(&dlm->spinlock); + /* Find the lockres associated to the mle and set its owner to UNK */ + res = __dlm_lookup_lockres(dlm, mle->mname, mle->mnamelen, + mle->mnamehash); + if (res) { + spin_unlock(&dlm->master_lock); - /* clean the master list */ - spin_lock(&dlm->master_lock); - list_for_each_entry_safe(mle, next, &dlm->master_list, list) { - BUG_ON(mle->type != DLM_MLE_BLOCK && - mle->type != DLM_MLE_MASTER && - mle->type != DLM_MLE_MIGRATION); - - /* MASTER mles are initiated locally. the waiting - * process will notice the node map change - * shortly. let that happen as normal. */ - if (mle->type == DLM_MLE_MASTER) - continue; + /* move lockres onto recovery list */ + spin_lock(&res->spinlock); + dlm_set_lockres_owner(dlm, res, DLM_LOCK_RES_OWNER_UNKNOWN); + dlm_move_lockres_to_recovery_list(dlm, res); + spin_unlock(&res->spinlock); + dlm_lockres_put(res); + /* about to get rid of mle, detach from heartbeat */ + __dlm_mle_detach_hb_events(dlm, mle); - /* BLOCK mles are initiated by other nodes. - * need to clean up if the dead node would have - * been the master. */ - if (mle->type == DLM_MLE_BLOCK) { - int bit; + /* dump the mle */ + spin_lock(&dlm->master_lock); + __dlm_put_mle(mle); + spin_unlock(&dlm->master_lock); + } - spin_lock(&mle->spinlock); - bit = find_next_bit(mle->maybe_map, O2NM_MAX_NODES, 0); - if (bit != dead_node) { - mlog(0, "mle found, but dead node %u would " - "not have been master\n", dead_node); - spin_unlock(&mle->spinlock); - } else { - /* must drop the refcount by one since the - * assert_master will never arrive. this - * may result in the mle being unlinked and - * freed, but there may still be a process - * waiting in the dlmlock path which is fine. */ - mlog(0, "node %u was expected master\n", - dead_node); - atomic_set(&mle->woken, 1); - spin_unlock(&mle->spinlock); - wake_up(&mle->wq); - /* do not need events any longer, so detach - * from heartbeat */ - __dlm_mle_detach_hb_events(dlm, mle); - __dlm_put_mle(mle); - } - continue; - } + return res; +} - /* everything else is a MIGRATION mle */ - - /* the rule for MIGRATION mles is that the master - * becomes UNKNOWN if *either* the original or - * the new master dies. all UNKNOWN lockreses - * are sent to whichever node becomes the recovery - * master. the new master is responsible for - * determining if there is still a master for - * this lockres, or if he needs to take over - * mastery. either way, this node should expect - * another message to resolve this. */ - if (mle->master != dead_node && - mle->new_master != dead_node) - continue; +static void dlm_clean_migration_mle(struct dlm_ctxt *dlm, + struct dlm_master_list_entry *mle) +{ + __dlm_mle_detach_hb_events(dlm, mle); - /* if we have reached this point, this mle needs to - * be removed from the list and freed. */ + spin_lock(&mle->spinlock); + __dlm_unlink_mle(dlm, mle); + atomic_set(&mle->woken, 1); + spin_unlock(&mle->spinlock); - /* remove from the list early. NOTE: unlinking - * list_head while in list_for_each_safe */ - __dlm_mle_detach_hb_events(dlm, mle); - spin_lock(&mle->spinlock); - list_del_init(&mle->list); + wake_up(&mle->wq); +} + +static void dlm_clean_block_mle(struct dlm_ctxt *dlm, + struct dlm_master_list_entry *mle, u8 dead_node) +{ + int bit; + + BUG_ON(mle->type != DLM_MLE_BLOCK); + + spin_lock(&mle->spinlock); + bit = find_next_bit(mle->maybe_map, O2NM_MAX_NODES, 0); + if (bit != dead_node) { + mlog(0, "mle found, but dead node %u would not have been " + "master\n", dead_node); + spin_unlock(&mle->spinlock); + } else { + /* Must drop the refcount by one since the assert_master will + * never arrive. This may result in the mle being unlinked and + * freed, but there may still be a process waiting in the + * dlmlock path which is fine. */ + mlog(0, "node %u was expected master\n", dead_node); atomic_set(&mle->woken, 1); spin_unlock(&mle->spinlock); wake_up(&mle->wq); - mlog(0, "%s: node %u died during migration from " - "%u to %u!\n", dlm->name, dead_node, - mle->master, mle->new_master); - /* if there is a lockres associated with this - * mle, find it and set its owner to UNKNOWN */ - hash = dlm_lockid_hash(mle->u.name.name, mle->u.name.len); - res = __dlm_lookup_lockres(dlm, mle->u.name.name, - mle->u.name.len, hash); - if (res) { - /* unfortunately if we hit this rare case, our - * lock ordering is messed. we need to drop - * the master lock so that we can take the - * lockres lock, meaning that we will have to - * restart from the head of list. */ - spin_unlock(&dlm->master_lock); + /* Do not need events any longer, so detach from heartbeat */ + __dlm_mle_detach_hb_events(dlm, mle); + __dlm_put_mle(mle); + } +} - /* move lockres onto recovery list */ - spin_lock(&res->spinlock); - dlm_set_lockres_owner(dlm, res, - DLM_LOCK_RES_OWNER_UNKNOWN); - dlm_move_lockres_to_recovery_list(dlm, res); - spin_unlock(&res->spinlock); - dlm_lockres_put(res); +void dlm_clean_master_list(struct dlm_ctxt *dlm, u8 dead_node) +{ + struct dlm_master_list_entry *mle; + struct dlm_lock_resource *res; + struct hlist_head *bucket; + struct hlist_node *list; + unsigned int i; - /* about to get rid of mle, detach from heartbeat */ - __dlm_mle_detach_hb_events(dlm, mle); + mlog_entry("dlm=%s, dead node=%u\n", dlm->name, dead_node); +top: + assert_spin_locked(&dlm->spinlock); - /* dump the mle */ - spin_lock(&dlm->master_lock); - __dlm_put_mle(mle); - spin_unlock(&dlm->master_lock); + /* clean the master list */ + spin_lock(&dlm->master_lock); + for (i = 0; i < DLM_HASH_BUCKETS; i++) { + bucket = dlm_master_hash(dlm, i); + hlist_for_each(list, bucket) { + mle = hlist_entry(list, struct dlm_master_list_entry, + master_hash_node); + + BUG_ON(mle->type != DLM_MLE_BLOCK && + mle->type != DLM_MLE_MASTER && + mle->type != DLM_MLE_MIGRATION); + + /* MASTER mles are initiated locally. The waiting + * process will notice the node map change shortly. + * Let that happen as normal. */ + if (mle->type == DLM_MLE_MASTER) + continue; + + /* BLOCK mles are initiated by other nodes. Need to + * clean up if the dead node would have been the + * master. */ + if (mle->type == DLM_MLE_BLOCK) { + dlm_clean_block_mle(dlm, mle, dead_node); + continue; + } - /* restart */ - goto top; - } + /* Everything else is a MIGRATION mle */ + + /* The rule for MIGRATION mles is that the master + * becomes UNKNOWN if *either* the original or the new + * master dies. All UNKNOWN lockres' are sent to + * whichever node becomes the recovery master. The new + * master is responsible for determining if there is + * still a master for this lockres, or if he needs to + * take over mastery. Either way, this node should + * expect another message to resolve this. */ + + if (mle->master != dead_node && + mle->new_master != dead_node) + continue; + + /* If we have reached this point, this mle needs to be + * removed from the list and freed. */ + dlm_clean_migration_mle(dlm, mle); + + mlog(0, "%s: node %u died during migration from " + "%u to %u!\n", dlm->name, dead_node, mle->master, + mle->new_master); + + /* If we find a lockres associated with the mle, we've + * hit this rare case that messes up our lock ordering. + * If so, we need to drop the master lock so that we can + * take the lockres lock, meaning that we will have to + * restart from the head of list. */ + res = dlm_reset_mleres_owner(dlm, mle); + if (res) + /* restart */ + goto top; - /* this may be the last reference */ - __dlm_put_mle(mle); + /* This may be the last reference */ + __dlm_put_mle(mle); + } } spin_unlock(&dlm->master_lock); } - int dlm_finish_migration(struct dlm_ctxt *dlm, struct dlm_lock_resource *res, u8 old_master) { diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c index 4060bb328bc8..d490b66ad9d7 100644 --- a/fs/ocfs2/dlm/dlmthread.c +++ b/fs/ocfs2/dlm/dlmthread.c @@ -162,12 +162,28 @@ static int dlm_purge_lockres(struct dlm_ctxt *dlm, spin_lock(&res->spinlock); if (!__dlm_lockres_unused(res)) { - spin_unlock(&res->spinlock); mlog(0, "%s:%.*s: tried to purge but not unused\n", dlm->name, res->lockname.len, res->lockname.name); - return -ENOTEMPTY; + __dlm_print_one_lock_resource(res); + spin_unlock(&res->spinlock); + BUG(); } + + if (res->state & DLM_LOCK_RES_MIGRATING) { + mlog(0, "%s:%.*s: Delay dropref as this lockres is " + "being remastered\n", dlm->name, res->lockname.len, + res->lockname.name); + /* Re-add the lockres to the end of the purge list */ + if (!list_empty(&res->purge)) { + list_del_init(&res->purge); + list_add_tail(&res->purge, &dlm->purge_list); + } + spin_unlock(&res->spinlock); + return 0; + } + master = (res->owner == dlm->node_num); + if (!master) res->state |= DLM_LOCK_RES_DROPPING_REF; spin_unlock(&res->spinlock); diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 7219a86d34cc..e15fc7d50827 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -244,6 +244,10 @@ static struct ocfs2_lock_res_ops ocfs2_rename_lops = { .flags = 0, }; +static struct ocfs2_lock_res_ops ocfs2_nfs_sync_lops = { + .flags = 0, +}; + static struct ocfs2_lock_res_ops ocfs2_dentry_lops = { .get_osb = ocfs2_get_dentry_osb, .post_unlock = ocfs2_dentry_post_unlock, @@ -622,6 +626,17 @@ static void ocfs2_rename_lock_res_init(struct ocfs2_lock_res *res, &ocfs2_rename_lops, osb); } +static void ocfs2_nfs_sync_lock_res_init(struct ocfs2_lock_res *res, + struct ocfs2_super *osb) +{ + /* nfs_sync lockres doesn't come from a slab so we call init + * once on it manually. */ + ocfs2_lock_res_init_once(res); + ocfs2_build_lock_name(OCFS2_LOCK_TYPE_NFS_SYNC, 0, 0, res->l_name); + ocfs2_lock_res_init_common(osb, res, OCFS2_LOCK_TYPE_NFS_SYNC, + &ocfs2_nfs_sync_lops, osb); +} + void ocfs2_file_lock_res_init(struct ocfs2_lock_res *lockres, struct ocfs2_file_private *fp) { @@ -2417,6 +2432,34 @@ void ocfs2_rename_unlock(struct ocfs2_super *osb) ocfs2_cluster_unlock(osb, lockres, DLM_LOCK_EX); } +int ocfs2_nfs_sync_lock(struct ocfs2_super *osb, int ex) +{ + int status; + struct ocfs2_lock_res *lockres = &osb->osb_nfs_sync_lockres; + + if (ocfs2_is_hard_readonly(osb)) + return -EROFS; + + if (ocfs2_mount_local(osb)) + return 0; + + status = ocfs2_cluster_lock(osb, lockres, ex ? LKM_EXMODE : LKM_PRMODE, + 0, 0); + if (status < 0) + mlog(ML_ERROR, "lock on nfs sync lock failed %d\n", status); + + return status; +} + +void ocfs2_nfs_sync_unlock(struct ocfs2_super *osb, int ex) +{ + struct ocfs2_lock_res *lockres = &osb->osb_nfs_sync_lockres; + + if (!ocfs2_mount_local(osb)) + ocfs2_cluster_unlock(osb, lockres, + ex ? LKM_EXMODE : LKM_PRMODE); +} + int ocfs2_dentry_lock(struct dentry *dentry, int ex) { int ret; @@ -2798,6 +2841,7 @@ int ocfs2_dlm_init(struct ocfs2_super *osb) local: ocfs2_super_lock_res_init(&osb->osb_super_lockres, osb); ocfs2_rename_lock_res_init(&osb->osb_rename_lockres, osb); + ocfs2_nfs_sync_lock_res_init(&osb->osb_nfs_sync_lockres, osb); osb->cconn = conn; @@ -2833,6 +2877,7 @@ void ocfs2_dlm_shutdown(struct ocfs2_super *osb, ocfs2_lock_res_free(&osb->osb_super_lockres); ocfs2_lock_res_free(&osb->osb_rename_lockres); + ocfs2_lock_res_free(&osb->osb_nfs_sync_lockres); ocfs2_cluster_disconnect(osb->cconn, hangup_pending); osb->cconn = NULL; @@ -3015,6 +3060,7 @@ static void ocfs2_drop_osb_locks(struct ocfs2_super *osb) { ocfs2_simple_drop_lockres(osb, &osb->osb_super_lockres); ocfs2_simple_drop_lockres(osb, &osb->osb_rename_lockres); + ocfs2_simple_drop_lockres(osb, &osb->osb_nfs_sync_lockres); } int ocfs2_drop_inode_locks(struct inode *inode) diff --git a/fs/ocfs2/dlmglue.h b/fs/ocfs2/dlmglue.h index 3f8d9986b8e0..e1fd5721cd7f 100644 --- a/fs/ocfs2/dlmglue.h +++ b/fs/ocfs2/dlmglue.h @@ -115,6 +115,8 @@ void ocfs2_super_unlock(struct ocfs2_super *osb, int ex); int ocfs2_rename_lock(struct ocfs2_super *osb); void ocfs2_rename_unlock(struct ocfs2_super *osb); +int ocfs2_nfs_sync_lock(struct ocfs2_super *osb, int ex); +void ocfs2_nfs_sync_unlock(struct ocfs2_super *osb, int ex); int ocfs2_dentry_lock(struct dentry *dentry, int ex); void ocfs2_dentry_unlock(struct dentry *dentry, int ex); int ocfs2_file_lock(struct file *file, int ex, int trylock); diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c index 2f27b332d8b3..de3da8eb558c 100644 --- a/fs/ocfs2/export.c +++ b/fs/ocfs2/export.c @@ -31,6 +31,7 @@ #include "ocfs2.h" +#include "alloc.h" #include "dir.h" #include "dlmglue.h" #include "dcache.h" @@ -38,6 +39,7 @@ #include "inode.h" #include "buffer_head_io.h" +#include "suballoc.h" struct ocfs2_inode_handle { @@ -49,29 +51,97 @@ static struct dentry *ocfs2_get_dentry(struct super_block *sb, struct ocfs2_inode_handle *handle) { struct inode *inode; + struct ocfs2_super *osb = OCFS2_SB(sb); + u64 blkno = handle->ih_blkno; + int status, set; struct dentry *result; mlog_entry("(0x%p, 0x%p)\n", sb, handle); - if (handle->ih_blkno == 0) { - mlog_errno(-ESTALE); - return ERR_PTR(-ESTALE); + if (blkno == 0) { + mlog(0, "nfs wants inode with blkno: 0\n"); + result = ERR_PTR(-ESTALE); + goto bail; + } + + inode = ocfs2_ilookup(sb, blkno); + /* + * If the inode exists in memory, we only need to check it's + * generation number + */ + if (inode) + goto check_gen; + + /* + * This will synchronize us against ocfs2_delete_inode() on + * all nodes + */ + status = ocfs2_nfs_sync_lock(osb, 1); + if (status < 0) { + mlog(ML_ERROR, "getting nfs sync lock(EX) failed %d\n", status); + goto check_err; + } + + status = ocfs2_test_inode_bit(osb, blkno, &set); + if (status < 0) { + if (status == -EINVAL) { + /* + * The blkno NFS gave us doesn't even show up + * as an inode, we return -ESTALE to be + * nice + */ + mlog(0, "test inode bit failed %d\n", status); + status = -ESTALE; + } else { + mlog(ML_ERROR, "test inode bit failed %d\n", status); + } + goto unlock_nfs_sync; + } + + /* If the inode allocator bit is clear, this inode must be stale */ + if (!set) { + mlog(0, "inode %llu suballoc bit is clear\n", blkno); + status = -ESTALE; + goto unlock_nfs_sync; } - inode = ocfs2_iget(OCFS2_SB(sb), handle->ih_blkno, 0, 0); + inode = ocfs2_iget(osb, blkno, 0, 0); - if (IS_ERR(inode)) - return (void *)inode; +unlock_nfs_sync: + ocfs2_nfs_sync_unlock(osb, 1); +check_err: + if (status < 0) { + if (status == -ESTALE) { + mlog(0, "stale inode ino: %llu generation: %u\n", + blkno, handle->ih_generation); + } + result = ERR_PTR(status); + goto bail; + } + + if (IS_ERR(inode)) { + mlog_errno(PTR_ERR(inode)); + result = (void *)inode; + goto bail; + } + +check_gen: if (handle->ih_generation != inode->i_generation) { iput(inode); - return ERR_PTR(-ESTALE); + mlog(0, "stale inode ino: %llu generation: %u\n", blkno, + handle->ih_generation); + result = ERR_PTR(-ESTALE); + goto bail; } result = d_obtain_alias(inode); if (!IS_ERR(result)) result->d_op = &ocfs2_dentry_ops; + else + mlog_errno(PTR_ERR(result)); +bail: mlog_exit_ptr(result); return result; } diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index 229e707bc050..10e1fa87396a 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -38,6 +38,7 @@ #include "ocfs2.h" #include "alloc.h" +#include "dir.h" #include "blockcheck.h" #include "dlmglue.h" #include "extent_map.h" @@ -112,6 +113,17 @@ void ocfs2_get_inode_flags(struct ocfs2_inode_info *oi) oi->ip_attr |= OCFS2_DIRSYNC_FL; } +struct inode *ocfs2_ilookup(struct super_block *sb, u64 blkno) +{ + struct ocfs2_find_inode_args args; + + args.fi_blkno = blkno; + args.fi_flags = 0; + args.fi_ino = ino_from_blkno(sb, blkno); + args.fi_sysfile_type = 0; + + return ilookup5(sb, blkno, ocfs2_find_actor, &args); +} struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 blkno, unsigned flags, int sysfile_type) { @@ -275,7 +287,7 @@ void ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe, (unsigned long long)OCFS2_I(inode)->ip_blkno, (unsigned long long)le64_to_cpu(fe->i_blkno)); - inode->i_nlink = le16_to_cpu(fe->i_links_count); + inode->i_nlink = ocfs2_read_links_count(fe); if (fe->i_flags & cpu_to_le32(OCFS2_SYSTEM_FL)) { OCFS2_I(inode)->ip_flags |= OCFS2_INODE_SYSTEM_FILE; @@ -351,6 +363,8 @@ void ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe, ocfs2_set_inode_flags(inode); + OCFS2_I(inode)->ip_last_used_slot = 0; + OCFS2_I(inode)->ip_last_used_group = 0; mlog_exit_void(); } @@ -606,7 +620,7 @@ static int ocfs2_remove_inode(struct inode *inode, } handle = ocfs2_start_trans(osb, OCFS2_DELETE_INODE_CREDITS + - ocfs2_quota_trans_credits(inode->i_sb)); + ocfs2_quota_trans_credits(inode->i_sb)); if (IS_ERR(handle)) { status = PTR_ERR(handle); mlog_errno(status); @@ -740,6 +754,15 @@ static int ocfs2_wipe_inode(struct inode *inode, goto bail_unlock_dir; } + /* Remove any dir index tree */ + if (S_ISDIR(inode->i_mode)) { + status = ocfs2_dx_dir_truncate(inode, di_bh); + if (status) { + mlog_errno(status); + goto bail_unlock_dir; + } + } + /*Free extended attribute resources associated with this inode.*/ status = ocfs2_xattr_remove(inode, di_bh); if (status < 0) { @@ -949,6 +972,17 @@ void ocfs2_delete_inode(struct inode *inode) goto bail; } + /* + * Synchronize us against ocfs2_get_dentry. We take this in + * shared mode so that all nodes can still concurrently + * process deletes. + */ + status = ocfs2_nfs_sync_lock(OCFS2_SB(inode->i_sb), 0); + if (status < 0) { + mlog(ML_ERROR, "getting nfs sync lock(PR) failed %d\n", status); + ocfs2_cleanup_delete_inode(inode, 0); + goto bail_unblock; + } /* Lock down the inode. This gives us an up to date view of * it's metadata (for verification), and allows us to * serialize delete_inode on multiple nodes. @@ -962,7 +996,7 @@ void ocfs2_delete_inode(struct inode *inode) if (status != -ENOENT) mlog_errno(status); ocfs2_cleanup_delete_inode(inode, 0); - goto bail_unblock; + goto bail_unlock_nfs_sync; } /* Query the cluster. This will be the final decision made @@ -1005,6 +1039,10 @@ void ocfs2_delete_inode(struct inode *inode) bail_unlock_inode: ocfs2_inode_unlock(inode, 1); brelse(di_bh); + +bail_unlock_nfs_sync: + ocfs2_nfs_sync_unlock(OCFS2_SB(inode->i_sb), 0); + bail_unblock: status = sigprocmask(SIG_SETMASK, &oldset, NULL); if (status < 0) @@ -1205,7 +1243,7 @@ int ocfs2_mark_inode_dirty(handle_t *handle, spin_unlock(&OCFS2_I(inode)->ip_lock); fe->i_size = cpu_to_le64(i_size_read(inode)); - fe->i_links_count = cpu_to_le16(inode->i_nlink); + ocfs2_set_links_count(fe, inode->i_nlink); fe->i_uid = cpu_to_le32(inode->i_uid); fe->i_gid = cpu_to_le32(inode->i_gid); fe->i_mode = cpu_to_le16(inode->i_mode); @@ -1242,7 +1280,7 @@ void ocfs2_refresh_inode(struct inode *inode, OCFS2_I(inode)->ip_dyn_features = le16_to_cpu(fe->i_dyn_features); ocfs2_set_inode_flags(inode); i_size_write(inode, le64_to_cpu(fe->i_size)); - inode->i_nlink = le16_to_cpu(fe->i_links_count); + inode->i_nlink = ocfs2_read_links_count(fe); inode->i_uid = le32_to_cpu(fe->i_uid); inode->i_gid = le32_to_cpu(fe->i_gid); inode->i_mode = le16_to_cpu(fe->i_mode); diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h index eb3c302b38d3..ea71525aad41 100644 --- a/fs/ocfs2/inode.h +++ b/fs/ocfs2/inode.h @@ -72,6 +72,10 @@ struct ocfs2_inode_info struct inode vfs_inode; struct jbd2_inode ip_jinode; + + /* Only valid if the inode is the dir. */ + u32 ip_last_used_slot; + u64 ip_last_used_group; }; /* @@ -124,6 +128,7 @@ void ocfs2_drop_inode(struct inode *inode); /* Flags for ocfs2_iget() */ #define OCFS2_FI_FLAG_SYSFILE 0x1 #define OCFS2_FI_FLAG_ORPHAN_RECOVERY 0x2 +struct inode *ocfs2_ilookup(struct super_block *sb, u64 feoff); struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 feoff, unsigned flags, int sysfile_type); int ocfs2_inode_init_private(struct inode *inode); diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 57d7d25a2b9a..a20a0f1e37fd 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -65,6 +65,11 @@ static int ocfs2_trylock_journal(struct ocfs2_super *osb, static int ocfs2_recover_orphans(struct ocfs2_super *osb, int slot); static int ocfs2_commit_thread(void *arg); +static void ocfs2_queue_recovery_completion(struct ocfs2_journal *journal, + int slot_num, + struct ocfs2_dinode *la_dinode, + struct ocfs2_dinode *tl_dinode, + struct ocfs2_quota_recovery *qrec); static inline int ocfs2_wait_on_mount(struct ocfs2_super *osb) { @@ -76,18 +81,97 @@ static inline int ocfs2_wait_on_quotas(struct ocfs2_super *osb) return __ocfs2_wait_on_mount(osb, 1); } - - /* - * The recovery_list is a simple linked list of node numbers to recover. - * It is protected by the recovery_lock. + * This replay_map is to track online/offline slots, so we could recover + * offline slots during recovery and mount */ -struct ocfs2_recovery_map { - unsigned int rm_used; - unsigned int *rm_entries; +enum ocfs2_replay_state { + REPLAY_UNNEEDED = 0, /* Replay is not needed, so ignore this map */ + REPLAY_NEEDED, /* Replay slots marked in rm_replay_slots */ + REPLAY_DONE /* Replay was already queued */ }; +struct ocfs2_replay_map { + unsigned int rm_slots; + enum ocfs2_replay_state rm_state; + unsigned char rm_replay_slots[0]; +}; + +void ocfs2_replay_map_set_state(struct ocfs2_super *osb, int state) +{ + if (!osb->replay_map) + return; + + /* If we've already queued the replay, we don't have any more to do */ + if (osb->replay_map->rm_state == REPLAY_DONE) + return; + + osb->replay_map->rm_state = state; +} + +int ocfs2_compute_replay_slots(struct ocfs2_super *osb) +{ + struct ocfs2_replay_map *replay_map; + int i, node_num; + + /* If replay map is already set, we don't do it again */ + if (osb->replay_map) + return 0; + + replay_map = kzalloc(sizeof(struct ocfs2_replay_map) + + (osb->max_slots * sizeof(char)), GFP_KERNEL); + + if (!replay_map) { + mlog_errno(-ENOMEM); + return -ENOMEM; + } + + spin_lock(&osb->osb_lock); + + replay_map->rm_slots = osb->max_slots; + replay_map->rm_state = REPLAY_UNNEEDED; + + /* set rm_replay_slots for offline slot(s) */ + for (i = 0; i < replay_map->rm_slots; i++) { + if (ocfs2_slot_to_node_num_locked(osb, i, &node_num) == -ENOENT) + replay_map->rm_replay_slots[i] = 1; + } + + osb->replay_map = replay_map; + spin_unlock(&osb->osb_lock); + return 0; +} + +void ocfs2_queue_replay_slots(struct ocfs2_super *osb) +{ + struct ocfs2_replay_map *replay_map = osb->replay_map; + int i; + + if (!replay_map) + return; + + if (replay_map->rm_state != REPLAY_NEEDED) + return; + + for (i = 0; i < replay_map->rm_slots; i++) + if (replay_map->rm_replay_slots[i]) + ocfs2_queue_recovery_completion(osb->journal, i, NULL, + NULL, NULL); + replay_map->rm_state = REPLAY_DONE; +} + +void ocfs2_free_replay_slots(struct ocfs2_super *osb) +{ + struct ocfs2_replay_map *replay_map = osb->replay_map; + + if (!osb->replay_map) + return; + + kfree(replay_map); + osb->replay_map = NULL; +} + int ocfs2_recovery_init(struct ocfs2_super *osb) { struct ocfs2_recovery_map *rm; @@ -496,6 +580,22 @@ static struct ocfs2_triggers dq_triggers = { }, }; +static struct ocfs2_triggers dr_triggers = { + .ot_triggers = { + .t_commit = ocfs2_commit_trigger, + .t_abort = ocfs2_abort_trigger, + }, + .ot_offset = offsetof(struct ocfs2_dx_root_block, dr_check), +}; + +static struct ocfs2_triggers dl_triggers = { + .ot_triggers = { + .t_commit = ocfs2_commit_trigger, + .t_abort = ocfs2_abort_trigger, + }, + .ot_offset = offsetof(struct ocfs2_dx_leaf, dl_check), +}; + static int __ocfs2_journal_access(handle_t *handle, struct inode *inode, struct buffer_head *bh, @@ -600,6 +700,20 @@ int ocfs2_journal_access_dq(handle_t *handle, struct inode *inode, type); } +int ocfs2_journal_access_dr(handle_t *handle, struct inode *inode, + struct buffer_head *bh, int type) +{ + return __ocfs2_journal_access(handle, inode, bh, &dr_triggers, + type); +} + +int ocfs2_journal_access_dl(handle_t *handle, struct inode *inode, + struct buffer_head *bh, int type) +{ + return __ocfs2_journal_access(handle, inode, bh, &dl_triggers, + type); +} + int ocfs2_journal_access(handle_t *handle, struct inode *inode, struct buffer_head *bh, int type) { @@ -1176,24 +1290,24 @@ static void ocfs2_queue_recovery_completion(struct ocfs2_journal *journal, } /* Called by the mount code to queue recovery the last part of - * recovery for it's own slot. */ + * recovery for it's own and offline slot(s). */ void ocfs2_complete_mount_recovery(struct ocfs2_super *osb) { struct ocfs2_journal *journal = osb->journal; - if (osb->dirty) { - /* No need to queue up our truncate_log as regular - * cleanup will catch that. */ - ocfs2_queue_recovery_completion(journal, - osb->slot_num, - osb->local_alloc_copy, - NULL, - NULL); - ocfs2_schedule_truncate_log_flush(osb, 0); + /* No need to queue up our truncate_log as regular cleanup will catch + * that */ + ocfs2_queue_recovery_completion(journal, osb->slot_num, + osb->local_alloc_copy, NULL, NULL); + ocfs2_schedule_truncate_log_flush(osb, 0); - osb->local_alloc_copy = NULL; - osb->dirty = 0; - } + osb->local_alloc_copy = NULL; + osb->dirty = 0; + + /* queue to recover orphan slots for all offline slots */ + ocfs2_replay_map_set_state(osb, REPLAY_NEEDED); + ocfs2_queue_replay_slots(osb); + ocfs2_free_replay_slots(osb); } void ocfs2_complete_quota_recovery(struct ocfs2_super *osb) @@ -1236,6 +1350,14 @@ restart: goto bail; } + status = ocfs2_compute_replay_slots(osb); + if (status < 0) + mlog_errno(status); + + /* queue recovery for our own slot */ + ocfs2_queue_recovery_completion(osb->journal, osb->slot_num, NULL, + NULL, NULL); + spin_lock(&osb->osb_lock); while (rm->rm_used) { /* It's always safe to remove entry zero, as we won't @@ -1301,11 +1423,8 @@ skip_recovery: ocfs2_super_unlock(osb, 1); - /* We always run recovery on our own orphan dir - the dead - * node(s) may have disallowd a previos inode delete. Re-processing - * is therefore required. */ - ocfs2_queue_recovery_completion(osb->journal, osb->slot_num, NULL, - NULL, NULL); + /* queue recovery for offline slots */ + ocfs2_queue_replay_slots(osb); bail: mutex_lock(&osb->recovery_lock); @@ -1314,6 +1433,7 @@ bail: goto restart; } + ocfs2_free_replay_slots(osb); osb->recovery_thread_task = NULL; mb(); /* sync with ocfs2_recovery_thread_running */ wake_up(&osb->recovery_event); @@ -1465,6 +1585,9 @@ static int ocfs2_replay_journal(struct ocfs2_super *osb, goto done; } + /* we need to run complete recovery for offline orphan slots */ + ocfs2_replay_map_set_state(osb, REPLAY_NEEDED); + mlog(ML_NOTICE, "Recovering node %d from slot %d on device (%u,%u)\n", node_num, slot_num, MAJOR(osb->sb->s_dev), MINOR(osb->sb->s_dev)); diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h index 172850a9a12a..619dd7f6c053 100644 --- a/fs/ocfs2/journal.h +++ b/fs/ocfs2/journal.h @@ -38,6 +38,17 @@ enum ocfs2_journal_state { struct ocfs2_super; struct ocfs2_dinode; +/* + * The recovery_list is a simple linked list of node numbers to recover. + * It is protected by the recovery_lock. + */ + +struct ocfs2_recovery_map { + unsigned int rm_used; + unsigned int *rm_entries; +}; + + struct ocfs2_journal { enum ocfs2_journal_state j_state; /* Journals current state */ @@ -139,6 +150,7 @@ void ocfs2_wait_for_recovery(struct ocfs2_super *osb); int ocfs2_recovery_init(struct ocfs2_super *osb); void ocfs2_recovery_exit(struct ocfs2_super *osb); +int ocfs2_compute_replay_slots(struct ocfs2_super *osb); /* * Journal Control: * Initialize, Load, Shutdown, Wipe a journal. @@ -266,6 +278,12 @@ int ocfs2_journal_access_dq(handle_t *handle, struct inode *inode, /* dirblock */ int ocfs2_journal_access_db(handle_t *handle, struct inode *inode, struct buffer_head *bh, int type); +/* ocfs2_dx_root_block */ +int ocfs2_journal_access_dr(handle_t *handle, struct inode *inode, + struct buffer_head *bh, int type); +/* ocfs2_dx_leaf */ +int ocfs2_journal_access_dl(handle_t *handle, struct inode *inode, + struct buffer_head *bh, int type); /* Anything that has no ecc */ int ocfs2_journal_access(handle_t *handle, struct inode *inode, struct buffer_head *bh, int type); @@ -368,14 +386,29 @@ static inline int ocfs2_remove_extent_credits(struct super_block *sb) } /* data block for new dir/symlink, 2 for bitmap updates (bitmap fe + - * bitmap block for the new bit) */ -#define OCFS2_DIR_LINK_ADDITIONAL_CREDITS (1 + 2) + * bitmap block for the new bit) dx_root update for free list */ +#define OCFS2_DIR_LINK_ADDITIONAL_CREDITS (1 + 2 + 1) + +static inline int ocfs2_add_dir_index_credits(struct super_block *sb) +{ + /* 1 block for index, 2 allocs (data, metadata), 1 clusters + * worth of blocks for initial extent. */ + return 1 + 2 * OCFS2_SUBALLOC_ALLOC + + ocfs2_clusters_to_blocks(sb, 1); +} -/* parent fe, parent block, new file entry, inode alloc fe, inode alloc - * group descriptor + mkdir/symlink blocks + quota update */ -static inline int ocfs2_mknod_credits(struct super_block *sb) +/* parent fe, parent block, new file entry, index leaf, inode alloc fe, inode + * alloc group descriptor + mkdir/symlink blocks + dir blocks + xattr + * blocks + quota update */ +static inline int ocfs2_mknod_credits(struct super_block *sb, int is_dir, + int xattr_credits) { - return 3 + OCFS2_SUBALLOC_ALLOC + OCFS2_DIR_LINK_ADDITIONAL_CREDITS + + int dir_credits = OCFS2_DIR_LINK_ADDITIONAL_CREDITS; + + if (is_dir) + dir_credits += ocfs2_add_dir_index_credits(sb); + + return 4 + OCFS2_SUBALLOC_ALLOC + dir_credits + xattr_credits + ocfs2_quota_trans_credits(sb); } @@ -388,31 +421,31 @@ static inline int ocfs2_mknod_credits(struct super_block *sb) #define OCFS2_SIMPLE_DIR_EXTEND_CREDITS (2) /* file update (nlink, etc) + directory mtime/ctime + dir entry block + quota - * update on dir */ + * update on dir + index leaf + dx root update for free list */ static inline int ocfs2_link_credits(struct super_block *sb) { - return 2*OCFS2_INODE_UPDATE_CREDITS + 1 + + return 2*OCFS2_INODE_UPDATE_CREDITS + 3 + ocfs2_quota_trans_credits(sb); } /* inode + dir inode (if we unlink a dir), + dir entry block + orphan - * dir inode link */ + * dir inode link + dir inode index leaf + dir index root */ static inline int ocfs2_unlink_credits(struct super_block *sb) { /* The quota update from ocfs2_link_credits is unused here... */ - return 2 * OCFS2_INODE_UPDATE_CREDITS + 1 + ocfs2_link_credits(sb); + return 2 * OCFS2_INODE_UPDATE_CREDITS + 3 + ocfs2_link_credits(sb); } /* dinode + orphan dir dinode + inode alloc dinode + orphan dir entry + - * inode alloc group descriptor */ -#define OCFS2_DELETE_INODE_CREDITS (3 * OCFS2_INODE_UPDATE_CREDITS + 1 + 1) + * inode alloc group descriptor + orphan dir index leaf */ +#define OCFS2_DELETE_INODE_CREDITS (3 * OCFS2_INODE_UPDATE_CREDITS + 3) /* dinode update, old dir dinode update, new dir dinode update, old * dir dir entry, new dir dir entry, dir entry update for renaming - * directory + target unlink */ + * directory + target unlink + 3 x dir index leaves */ static inline int ocfs2_rename_credits(struct super_block *sb) { - return 3 * OCFS2_INODE_UPDATE_CREDITS + 3 + ocfs2_unlink_credits(sb); + return 3 * OCFS2_INODE_UPDATE_CREDITS + 6 + ocfs2_unlink_credits(sb); } /* global bitmap dinode, group desc., relinked group, @@ -422,6 +455,20 @@ static inline int ocfs2_rename_credits(struct super_block *sb) + OCFS2_INODE_UPDATE_CREDITS \ + OCFS2_XATTR_BLOCK_UPDATE_CREDITS) +/* inode update, removal of dx root block from allocator */ +#define OCFS2_DX_ROOT_REMOVE_CREDITS (OCFS2_INODE_UPDATE_CREDITS + \ + OCFS2_SUBALLOC_FREE) + +static inline int ocfs2_calc_dxi_expand_credits(struct super_block *sb) +{ + int credits = 1 + OCFS2_SUBALLOC_ALLOC; + + credits += ocfs2_clusters_to_blocks(sb, 1); + credits += ocfs2_quota_trans_credits(sb); + + return credits; +} + /* * Please note that the caller must make sure that root_el is the root * of extent tree. So for an inode, it should be &fe->id2.i_list. Otherwise @@ -457,7 +504,7 @@ static inline int ocfs2_calc_extend_credits(struct super_block *sb, static inline int ocfs2_calc_symlink_credits(struct super_block *sb) { - int blocks = ocfs2_mknod_credits(sb); + int blocks = ocfs2_mknod_credits(sb, 0, 0); /* links can be longer than one block so we may update many * within our single allocated extent. */ diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c index ec70cdbe77fc..bac7e6abaf47 100644 --- a/fs/ocfs2/localalloc.c +++ b/fs/ocfs2/localalloc.c @@ -28,7 +28,6 @@ #include <linux/slab.h> #include <linux/highmem.h> #include <linux/bitops.h> -#include <linux/debugfs.h> #define MLOG_MASK_PREFIX ML_DISK_ALLOC #include <cluster/masklog.h> @@ -75,84 +74,6 @@ static int ocfs2_local_alloc_new_window(struct ocfs2_super *osb, static int ocfs2_local_alloc_slide_window(struct ocfs2_super *osb, struct inode *local_alloc_inode); -#ifdef CONFIG_OCFS2_FS_STATS - -static int ocfs2_la_debug_open(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - -#define LA_DEBUG_BUF_SZ PAGE_CACHE_SIZE -#define LA_DEBUG_VER 1 -static ssize_t ocfs2_la_debug_read(struct file *file, char __user *userbuf, - size_t count, loff_t *ppos) -{ - static DEFINE_MUTEX(la_debug_mutex); - struct ocfs2_super *osb = file->private_data; - int written, ret; - char *buf = osb->local_alloc_debug_buf; - - mutex_lock(&la_debug_mutex); - memset(buf, 0, LA_DEBUG_BUF_SZ); - - written = snprintf(buf, LA_DEBUG_BUF_SZ, - "0x%x\t0x%llx\t%u\t%u\t0x%x\n", - LA_DEBUG_VER, - (unsigned long long)osb->la_last_gd, - osb->local_alloc_default_bits, - osb->local_alloc_bits, osb->local_alloc_state); - - ret = simple_read_from_buffer(userbuf, count, ppos, buf, written); - - mutex_unlock(&la_debug_mutex); - return ret; -} - -static const struct file_operations ocfs2_la_debug_fops = { - .open = ocfs2_la_debug_open, - .read = ocfs2_la_debug_read, -}; - -static void ocfs2_init_la_debug(struct ocfs2_super *osb) -{ - osb->local_alloc_debug_buf = kmalloc(LA_DEBUG_BUF_SZ, GFP_NOFS); - if (!osb->local_alloc_debug_buf) - return; - - osb->local_alloc_debug = debugfs_create_file("local_alloc_stats", - S_IFREG|S_IRUSR, - osb->osb_debug_root, - osb, - &ocfs2_la_debug_fops); - if (!osb->local_alloc_debug) { - kfree(osb->local_alloc_debug_buf); - osb->local_alloc_debug_buf = NULL; - } -} - -static void ocfs2_shutdown_la_debug(struct ocfs2_super *osb) -{ - if (osb->local_alloc_debug) - debugfs_remove(osb->local_alloc_debug); - - if (osb->local_alloc_debug_buf) - kfree(osb->local_alloc_debug_buf); - - osb->local_alloc_debug_buf = NULL; - osb->local_alloc_debug = NULL; -} -#else /* CONFIG_OCFS2_FS_STATS */ -static void ocfs2_init_la_debug(struct ocfs2_super *osb) -{ - return; -} -static void ocfs2_shutdown_la_debug(struct ocfs2_super *osb) -{ - return; -} -#endif - static inline int ocfs2_la_state_enabled(struct ocfs2_super *osb) { return (osb->local_alloc_state == OCFS2_LA_THROTTLED || @@ -226,8 +147,6 @@ int ocfs2_load_local_alloc(struct ocfs2_super *osb) mlog_entry_void(); - ocfs2_init_la_debug(osb); - if (osb->local_alloc_bits == 0) goto bail; @@ -299,9 +218,6 @@ bail: if (inode) iput(inode); - if (status < 0) - ocfs2_shutdown_la_debug(osb); - mlog(0, "Local alloc window bits = %d\n", osb->local_alloc_bits); mlog_exit(status); @@ -331,8 +247,6 @@ void ocfs2_shutdown_local_alloc(struct ocfs2_super *osb) cancel_delayed_work(&osb->la_enable_wq); flush_workqueue(ocfs2_wq); - ocfs2_shutdown_la_debug(osb); - if (osb->local_alloc_state == OCFS2_LA_UNUSED) goto out; diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 4b11762f249e..2220f93f668b 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -80,14 +80,14 @@ static int ocfs2_prepare_orphan_dir(struct ocfs2_super *osb, struct inode **ret_orphan_dir, struct inode *inode, char *name, - struct buffer_head **de_bh); + struct ocfs2_dir_lookup_result *lookup); static int ocfs2_orphan_add(struct ocfs2_super *osb, handle_t *handle, struct inode *inode, struct ocfs2_dinode *fe, char *name, - struct buffer_head *de_bh, + struct ocfs2_dir_lookup_result *lookup, struct inode *orphan_dir_inode); static int ocfs2_create_symlink_data(struct ocfs2_super *osb, @@ -228,17 +228,18 @@ static int ocfs2_mknod(struct inode *dir, struct ocfs2_super *osb; struct ocfs2_dinode *dirfe; struct buffer_head *new_fe_bh = NULL; - struct buffer_head *de_bh = NULL; struct inode *inode = NULL; struct ocfs2_alloc_context *inode_ac = NULL; struct ocfs2_alloc_context *data_ac = NULL; - struct ocfs2_alloc_context *xattr_ac = NULL; + struct ocfs2_alloc_context *meta_ac = NULL; int want_clusters = 0; + int want_meta = 0; int xattr_credits = 0; struct ocfs2_security_xattr_info si = { .enable = 1, }; int did_quota_inode = 0; + struct ocfs2_dir_lookup_result lookup = { NULL, }; mlog_entry("(0x%p, 0x%p, %d, %lu, '%.*s')\n", dir, dentry, mode, (unsigned long)dev, dentry->d_name.len, @@ -254,13 +255,13 @@ static int ocfs2_mknod(struct inode *dir, return status; } - if (S_ISDIR(mode) && (dir->i_nlink >= OCFS2_LINK_MAX)) { + if (S_ISDIR(mode) && (dir->i_nlink >= ocfs2_link_max(osb))) { status = -EMLINK; goto leave; } dirfe = (struct ocfs2_dinode *) parent_fe_bh->b_data; - if (!dirfe->i_links_count) { + if (!ocfs2_read_links_count(dirfe)) { /* can't make a file in a deleted directory. */ status = -ENOENT; goto leave; @@ -274,7 +275,7 @@ static int ocfs2_mknod(struct inode *dir, /* get a spot inside the dir. */ status = ocfs2_prepare_dir_for_insert(osb, dir, parent_fe_bh, dentry->d_name.name, - dentry->d_name.len, &de_bh); + dentry->d_name.len, &lookup); if (status < 0) { mlog_errno(status); goto leave; @@ -308,17 +309,29 @@ static int ocfs2_mknod(struct inode *dir, /* calculate meta data/clusters for setting security and acl xattr */ status = ocfs2_calc_xattr_init(dir, parent_fe_bh, mode, - &si, &want_clusters, - &xattr_credits, &xattr_ac); + &si, &want_clusters, + &xattr_credits, &want_meta); if (status < 0) { mlog_errno(status); goto leave; } /* Reserve a cluster if creating an extent based directory. */ - if (S_ISDIR(mode) && !ocfs2_supports_inline_data(osb)) + if (S_ISDIR(mode) && !ocfs2_supports_inline_data(osb)) { want_clusters += 1; + /* Dir indexing requires extra space as well */ + if (ocfs2_supports_indexed_dirs(osb)) + want_meta++; + } + + status = ocfs2_reserve_new_metadata_blocks(osb, want_meta, &meta_ac); + if (status < 0) { + if (status != -ENOSPC) + mlog_errno(status); + goto leave; + } + status = ocfs2_reserve_clusters(osb, want_clusters, &data_ac); if (status < 0) { if (status != -ENOSPC) @@ -326,8 +339,9 @@ static int ocfs2_mknod(struct inode *dir, goto leave; } - handle = ocfs2_start_trans(osb, ocfs2_mknod_credits(osb->sb) + - xattr_credits); + handle = ocfs2_start_trans(osb, ocfs2_mknod_credits(osb->sb, + S_ISDIR(mode), + xattr_credits)); if (IS_ERR(handle)) { status = PTR_ERR(handle); handle = NULL; @@ -355,7 +369,7 @@ static int ocfs2_mknod(struct inode *dir, if (S_ISDIR(mode)) { status = ocfs2_fill_new_dir(osb, handle, dir, inode, - new_fe_bh, data_ac); + new_fe_bh, data_ac, meta_ac); if (status < 0) { mlog_errno(status); goto leave; @@ -367,7 +381,7 @@ static int ocfs2_mknod(struct inode *dir, mlog_errno(status); goto leave; } - le16_add_cpu(&dirfe->i_links_count, 1); + ocfs2_add_links_count(dirfe, 1); status = ocfs2_journal_dirty(handle, parent_fe_bh); if (status < 0) { mlog_errno(status); @@ -377,7 +391,7 @@ static int ocfs2_mknod(struct inode *dir, } status = ocfs2_init_acl(handle, inode, dir, new_fe_bh, parent_fe_bh, - xattr_ac, data_ac); + meta_ac, data_ac); if (status < 0) { mlog_errno(status); goto leave; @@ -385,7 +399,7 @@ static int ocfs2_mknod(struct inode *dir, if (si.enable) { status = ocfs2_init_security_set(handle, inode, new_fe_bh, &si, - xattr_ac, data_ac); + meta_ac, data_ac); if (status < 0) { mlog_errno(status); goto leave; @@ -394,7 +408,7 @@ static int ocfs2_mknod(struct inode *dir, status = ocfs2_add_entry(handle, dentry, inode, OCFS2_I(inode)->ip_blkno, parent_fe_bh, - de_bh); + &lookup); if (status < 0) { mlog_errno(status); goto leave; @@ -423,11 +437,12 @@ leave: mlog(0, "Disk is full\n"); brelse(new_fe_bh); - brelse(de_bh); brelse(parent_fe_bh); kfree(si.name); kfree(si.value); + ocfs2_free_dir_lookup_result(&lookup); + if ((status < 0) && inode) { clear_nlink(inode); iput(inode); @@ -439,8 +454,8 @@ leave: if (data_ac) ocfs2_free_alloc_context(data_ac); - if (xattr_ac) - ocfs2_free_alloc_context(xattr_ac); + if (meta_ac) + ocfs2_free_alloc_context(meta_ac); mlog_exit(status); @@ -462,6 +477,7 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb, struct ocfs2_extent_list *fel; u64 fe_blkno = 0; u16 suballoc_bit; + u16 feat; mlog_entry("(0x%p, 0x%p, %d, %lu, '%.*s')\n", dir, dentry, inode->i_mode, (unsigned long)dev, dentry->d_name.len, @@ -469,8 +485,8 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb, *new_fe_bh = NULL; - status = ocfs2_claim_new_inode(osb, handle, inode_ac, &suballoc_bit, - &fe_blkno); + status = ocfs2_claim_new_inode(osb, handle, dir, parent_fe_bh, + inode_ac, &suballoc_bit, &fe_blkno); if (status < 0) { mlog_errno(status); goto leave; @@ -513,7 +529,8 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb, fe->i_mode = cpu_to_le16(inode->i_mode); if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) fe->id1.dev1.i_rdev = cpu_to_le64(huge_encode_dev(dev)); - fe->i_links_count = cpu_to_le16(inode->i_nlink); + + ocfs2_set_links_count(fe, inode->i_nlink); fe->i_last_eb_blk = 0; strcpy(fe->i_signature, OCFS2_INODE_SIGNATURE); @@ -525,11 +542,11 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb, fe->i_dtime = 0; /* - * If supported, directories start with inline data. + * If supported, directories start with inline data. If inline + * isn't supported, but indexing is, we start them as indexed. */ + feat = le16_to_cpu(fe->i_dyn_features); if (S_ISDIR(inode->i_mode) && ocfs2_supports_inline_data(osb)) { - u16 feat = le16_to_cpu(fe->i_dyn_features); - fe->i_dyn_features = cpu_to_le16(feat | OCFS2_INLINE_DATA_FL); fe->id2.i_data.id_count = cpu_to_le16( @@ -608,9 +625,9 @@ static int ocfs2_link(struct dentry *old_dentry, int err; struct buffer_head *fe_bh = NULL; struct buffer_head *parent_fe_bh = NULL; - struct buffer_head *de_bh = NULL; struct ocfs2_dinode *fe = NULL; struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); + struct ocfs2_dir_lookup_result lookup = { NULL, }; mlog_entry("(inode=%lu, old='%.*s' new='%.*s')\n", inode->i_ino, old_dentry->d_name.len, old_dentry->d_name.name, @@ -638,7 +655,7 @@ static int ocfs2_link(struct dentry *old_dentry, err = ocfs2_prepare_dir_for_insert(osb, dir, parent_fe_bh, dentry->d_name.name, - dentry->d_name.len, &de_bh); + dentry->d_name.len, &lookup); if (err < 0) { mlog_errno(err); goto out; @@ -652,7 +669,7 @@ static int ocfs2_link(struct dentry *old_dentry, } fe = (struct ocfs2_dinode *) fe_bh->b_data; - if (le16_to_cpu(fe->i_links_count) >= OCFS2_LINK_MAX) { + if (ocfs2_read_links_count(fe) >= ocfs2_link_max(osb)) { err = -EMLINK; goto out_unlock_inode; } @@ -674,13 +691,13 @@ static int ocfs2_link(struct dentry *old_dentry, inc_nlink(inode); inode->i_ctime = CURRENT_TIME; - fe->i_links_count = cpu_to_le16(inode->i_nlink); + ocfs2_set_links_count(fe, inode->i_nlink); fe->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec); fe->i_ctime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec); err = ocfs2_journal_dirty(handle, fe_bh); if (err < 0) { - le16_add_cpu(&fe->i_links_count, -1); + ocfs2_add_links_count(fe, -1); drop_nlink(inode); mlog_errno(err); goto out_commit; @@ -688,9 +705,9 @@ static int ocfs2_link(struct dentry *old_dentry, err = ocfs2_add_entry(handle, dentry, inode, OCFS2_I(inode)->ip_blkno, - parent_fe_bh, de_bh); + parent_fe_bh, &lookup); if (err) { - le16_add_cpu(&fe->i_links_count, -1); + ocfs2_add_links_count(fe, -1); drop_nlink(inode); mlog_errno(err); goto out_commit; @@ -714,10 +731,11 @@ out_unlock_inode: out: ocfs2_inode_unlock(dir, 1); - brelse(de_bh); brelse(fe_bh); brelse(parent_fe_bh); + ocfs2_free_dir_lookup_result(&lookup); + mlog_exit(err); return err; @@ -766,10 +784,9 @@ static int ocfs2_unlink(struct inode *dir, struct buffer_head *fe_bh = NULL; struct buffer_head *parent_node_bh = NULL; handle_t *handle = NULL; - struct ocfs2_dir_entry *dirent = NULL; - struct buffer_head *dirent_bh = NULL; char orphan_name[OCFS2_ORPHAN_NAMELEN + 1]; - struct buffer_head *orphan_entry_bh = NULL; + struct ocfs2_dir_lookup_result lookup = { NULL, }; + struct ocfs2_dir_lookup_result orphan_insert = { NULL, }; mlog_entry("(0x%p, 0x%p, '%.*s')\n", dir, dentry, dentry->d_name.len, dentry->d_name.name); @@ -791,8 +808,8 @@ static int ocfs2_unlink(struct inode *dir, } status = ocfs2_find_files_on_disk(dentry->d_name.name, - dentry->d_name.len, &blkno, - dir, &dirent_bh, &dirent); + dentry->d_name.len, &blkno, dir, + &lookup); if (status < 0) { if (status != -ENOENT) mlog_errno(status); @@ -817,10 +834,7 @@ static int ocfs2_unlink(struct inode *dir, child_locked = 1; if (S_ISDIR(inode->i_mode)) { - if (!ocfs2_empty_dir(inode)) { - status = -ENOTEMPTY; - goto leave; - } else if (inode->i_nlink != 2) { + if (inode->i_nlink != 2 || !ocfs2_empty_dir(inode)) { status = -ENOTEMPTY; goto leave; } @@ -836,8 +850,7 @@ static int ocfs2_unlink(struct inode *dir, if (inode_is_unlinkable(inode)) { status = ocfs2_prepare_orphan_dir(osb, &orphan_dir, inode, - orphan_name, - &orphan_entry_bh); + orphan_name, &orphan_insert); if (status < 0) { mlog_errno(status); goto leave; @@ -863,7 +876,7 @@ static int ocfs2_unlink(struct inode *dir, if (inode_is_unlinkable(inode)) { status = ocfs2_orphan_add(osb, handle, inode, fe, orphan_name, - orphan_entry_bh, orphan_dir); + &orphan_insert, orphan_dir); if (status < 0) { mlog_errno(status); goto leave; @@ -871,7 +884,7 @@ static int ocfs2_unlink(struct inode *dir, } /* delete the name from the parent dir */ - status = ocfs2_delete_entry(handle, dir, dirent, dirent_bh); + status = ocfs2_delete_entry(handle, dir, &lookup); if (status < 0) { mlog_errno(status); goto leave; @@ -880,7 +893,7 @@ static int ocfs2_unlink(struct inode *dir, if (S_ISDIR(inode->i_mode)) drop_nlink(inode); drop_nlink(inode); - fe->i_links_count = cpu_to_le16(inode->i_nlink); + ocfs2_set_links_count(fe, inode->i_nlink); status = ocfs2_journal_dirty(handle, fe_bh); if (status < 0) { @@ -916,9 +929,10 @@ leave: } brelse(fe_bh); - brelse(dirent_bh); brelse(parent_node_bh); - brelse(orphan_entry_bh); + + ocfs2_free_dir_lookup_result(&orphan_insert); + ocfs2_free_dir_lookup_result(&lookup); mlog_exit(status); @@ -1004,8 +1018,8 @@ static int ocfs2_rename(struct inode *old_dir, struct inode *new_dir, struct dentry *new_dentry) { - int status = 0, rename_lock = 0, parents_locked = 0; - int old_child_locked = 0, new_child_locked = 0; + int status = 0, rename_lock = 0, parents_locked = 0, target_exists = 0; + int old_child_locked = 0, new_child_locked = 0, update_dot_dot = 0; struct inode *old_inode = old_dentry->d_inode; struct inode *new_inode = new_dentry->d_inode; struct inode *orphan_dir = NULL; @@ -1020,13 +1034,13 @@ static int ocfs2_rename(struct inode *old_dir, handle_t *handle = NULL; struct buffer_head *old_dir_bh = NULL; struct buffer_head *new_dir_bh = NULL; - struct ocfs2_dir_entry *old_inode_dot_dot_de = NULL, *old_de = NULL, - *new_de = NULL; - struct buffer_head *new_de_bh = NULL, *old_de_bh = NULL; // bhs for above - struct buffer_head *old_inode_de_bh = NULL; // if old_dentry is a dir, - // this is the 1st dirent bh nlink_t old_dir_nlink = old_dir->i_nlink; struct ocfs2_dinode *old_di; + struct ocfs2_dir_lookup_result old_inode_dot_dot_res = { NULL, }; + struct ocfs2_dir_lookup_result target_lookup_res = { NULL, }; + struct ocfs2_dir_lookup_result old_entry_lookup = { NULL, }; + struct ocfs2_dir_lookup_result orphan_insert = { NULL, }; + struct ocfs2_dir_lookup_result target_insert = { NULL, }; /* At some point it might be nice to break this function up a * bit. */ @@ -1108,9 +1122,10 @@ static int ocfs2_rename(struct inode *old_dir, if (S_ISDIR(old_inode->i_mode)) { u64 old_inode_parent; + update_dot_dot = 1; status = ocfs2_find_files_on_disk("..", 2, &old_inode_parent, - old_inode, &old_inode_de_bh, - &old_inode_dot_dot_de); + old_inode, + &old_inode_dot_dot_res); if (status) { status = -EIO; goto bail; @@ -1122,7 +1137,7 @@ static int ocfs2_rename(struct inode *old_dir, } if (!new_inode && new_dir != old_dir && - new_dir->i_nlink >= OCFS2_LINK_MAX) { + new_dir->i_nlink >= ocfs2_link_max(osb)) { status = -EMLINK; goto bail; } @@ -1151,8 +1166,8 @@ static int ocfs2_rename(struct inode *old_dir, * to delete it */ status = ocfs2_find_files_on_disk(new_dentry->d_name.name, new_dentry->d_name.len, - &newfe_blkno, new_dir, &new_de_bh, - &new_de); + &newfe_blkno, new_dir, + &target_lookup_res); /* The only error we allow here is -ENOENT because the new * file not existing is perfectly valid. */ if ((status < 0) && (status != -ENOENT)) { @@ -1161,8 +1176,10 @@ static int ocfs2_rename(struct inode *old_dir, mlog_errno(status); goto bail; } + if (status == 0) + target_exists = 1; - if (!new_de && new_inode) { + if (!target_exists && new_inode) { /* * Target was unlinked by another node while we were * waiting to get to ocfs2_rename(). There isn't @@ -1175,7 +1192,7 @@ static int ocfs2_rename(struct inode *old_dir, /* In case we need to overwrite an existing file, we blow it * away first */ - if (new_de) { + if (target_exists) { /* VFS didn't think there existed an inode here, but * someone else in the cluster must have raced our * rename to create one. Today we error cleanly, in @@ -1216,8 +1233,8 @@ static int ocfs2_rename(struct inode *old_dir, newfe = (struct ocfs2_dinode *) newfe_bh->b_data; - mlog(0, "aha rename over existing... new_de=%p new_blkno=%llu " - "newfebh=%p bhblocknr=%llu\n", new_de, + mlog(0, "aha rename over existing... new_blkno=%llu " + "newfebh=%p bhblocknr=%llu\n", (unsigned long long)newfe_blkno, newfe_bh, newfe_bh ? (unsigned long long)newfe_bh->b_blocknr : 0ULL); @@ -1225,7 +1242,7 @@ static int ocfs2_rename(struct inode *old_dir, status = ocfs2_prepare_orphan_dir(osb, &orphan_dir, new_inode, orphan_name, - &orphan_entry_bh); + &orphan_insert); if (status < 0) { mlog_errno(status); goto bail; @@ -1243,7 +1260,7 @@ static int ocfs2_rename(struct inode *old_dir, status = ocfs2_prepare_dir_for_insert(osb, new_dir, new_dir_bh, new_dentry->d_name.name, new_dentry->d_name.len, - &insert_entry_bh); + &target_insert); if (status < 0) { mlog_errno(status); goto bail; @@ -1258,10 +1275,10 @@ static int ocfs2_rename(struct inode *old_dir, goto bail; } - if (new_de) { + if (target_exists) { if (S_ISDIR(new_inode->i_mode)) { - if (!ocfs2_empty_dir(new_inode) || - new_inode->i_nlink != 2) { + if (new_inode->i_nlink != 2 || + !ocfs2_empty_dir(new_inode)) { status = -ENOTEMPTY; goto bail; } @@ -1274,10 +1291,10 @@ static int ocfs2_rename(struct inode *old_dir, } if (S_ISDIR(new_inode->i_mode) || - (newfe->i_links_count == cpu_to_le16(1))){ + (ocfs2_read_links_count(newfe) == 1)) { status = ocfs2_orphan_add(osb, handle, new_inode, newfe, orphan_name, - orphan_entry_bh, orphan_dir); + &orphan_insert, orphan_dir); if (status < 0) { mlog_errno(status); goto bail; @@ -1285,8 +1302,8 @@ static int ocfs2_rename(struct inode *old_dir, } /* change the dirent to point to the correct inode */ - status = ocfs2_update_entry(new_dir, handle, new_de_bh, - new_de, old_inode); + status = ocfs2_update_entry(new_dir, handle, &target_lookup_res, + old_inode); if (status < 0) { mlog_errno(status); goto bail; @@ -1294,9 +1311,9 @@ static int ocfs2_rename(struct inode *old_dir, new_dir->i_version++; if (S_ISDIR(new_inode->i_mode)) - newfe->i_links_count = 0; + ocfs2_set_links_count(newfe, 0); else - le16_add_cpu(&newfe->i_links_count, -1); + ocfs2_add_links_count(newfe, -1); status = ocfs2_journal_dirty(handle, newfe_bh); if (status < 0) { @@ -1307,7 +1324,7 @@ static int ocfs2_rename(struct inode *old_dir, /* if the name was not found in new_dir, add it now */ status = ocfs2_add_entry(handle, new_dentry, old_inode, OCFS2_I(old_inode)->ip_blkno, - new_dir_bh, insert_entry_bh); + new_dir_bh, &target_insert); } old_inode->i_ctime = CURRENT_TIME; @@ -1334,15 +1351,13 @@ static int ocfs2_rename(struct inode *old_dir, * because the insert might have changed the type of directory * we're dealing with. */ - old_de_bh = ocfs2_find_entry(old_dentry->d_name.name, - old_dentry->d_name.len, - old_dir, &old_de); - if (!old_de_bh) { - status = -EIO; + status = ocfs2_find_entry(old_dentry->d_name.name, + old_dentry->d_name.len, old_dir, + &old_entry_lookup); + if (status) goto bail; - } - status = ocfs2_delete_entry(handle, old_dir, old_de, old_de_bh); + status = ocfs2_delete_entry(handle, old_dir, &old_entry_lookup); if (status < 0) { mlog_errno(status); goto bail; @@ -1353,9 +1368,10 @@ static int ocfs2_rename(struct inode *old_dir, new_inode->i_ctime = CURRENT_TIME; } old_dir->i_ctime = old_dir->i_mtime = CURRENT_TIME; - if (old_inode_de_bh) { - status = ocfs2_update_entry(old_inode, handle, old_inode_de_bh, - old_inode_dot_dot_de, new_dir); + + if (update_dot_dot) { + status = ocfs2_update_entry(old_inode, handle, + &old_inode_dot_dot_res, new_dir); old_dir->i_nlink--; if (new_inode) { new_inode->i_nlink--; @@ -1391,14 +1407,13 @@ static int ocfs2_rename(struct inode *old_dir, } else { struct ocfs2_dinode *fe; status = ocfs2_journal_access_di(handle, old_dir, - old_dir_bh, - OCFS2_JOURNAL_ACCESS_WRITE); + old_dir_bh, + OCFS2_JOURNAL_ACCESS_WRITE); fe = (struct ocfs2_dinode *) old_dir_bh->b_data; - fe->i_links_count = cpu_to_le16(old_dir->i_nlink); + ocfs2_set_links_count(fe, old_dir->i_nlink); status = ocfs2_journal_dirty(handle, old_dir_bh); } } - ocfs2_dentry_move(old_dentry, new_dentry, old_dir, new_dir); status = 0; bail: @@ -1429,13 +1444,17 @@ bail: if (new_inode) iput(new_inode); + + ocfs2_free_dir_lookup_result(&target_lookup_res); + ocfs2_free_dir_lookup_result(&old_entry_lookup); + ocfs2_free_dir_lookup_result(&old_inode_dot_dot_res); + ocfs2_free_dir_lookup_result(&orphan_insert); + ocfs2_free_dir_lookup_result(&target_insert); + brelse(newfe_bh); brelse(old_inode_bh); brelse(old_dir_bh); brelse(new_dir_bh); - brelse(new_de_bh); - brelse(old_de_bh); - brelse(old_inode_de_bh); brelse(orphan_entry_bh); brelse(insert_entry_bh); @@ -1558,7 +1577,6 @@ static int ocfs2_symlink(struct inode *dir, struct inode *inode = NULL; struct super_block *sb; struct buffer_head *new_fe_bh = NULL; - struct buffer_head *de_bh = NULL; struct buffer_head *parent_fe_bh = NULL; struct ocfs2_dinode *fe = NULL; struct ocfs2_dinode *dirfe; @@ -1572,6 +1590,7 @@ static int ocfs2_symlink(struct inode *dir, .enable = 1, }; int did_quota = 0, did_quota_inode = 0; + struct ocfs2_dir_lookup_result lookup = { NULL, }; mlog_entry("(0x%p, 0x%p, symname='%s' actual='%.*s')\n", dir, dentry, symname, dentry->d_name.len, dentry->d_name.name); @@ -1592,7 +1611,7 @@ static int ocfs2_symlink(struct inode *dir, } dirfe = (struct ocfs2_dinode *) parent_fe_bh->b_data; - if (!dirfe->i_links_count) { + if (!ocfs2_read_links_count(dirfe)) { /* can't make a file in a deleted directory. */ status = -ENOENT; goto bail; @@ -1605,7 +1624,7 @@ static int ocfs2_symlink(struct inode *dir, status = ocfs2_prepare_dir_for_insert(osb, dir, parent_fe_bh, dentry->d_name.name, - dentry->d_name.len, &de_bh); + dentry->d_name.len, &lookup); if (status < 0) { mlog_errno(status); goto bail; @@ -1744,7 +1763,7 @@ static int ocfs2_symlink(struct inode *dir, status = ocfs2_add_entry(handle, dentry, inode, le64_to_cpu(fe->i_blkno), parent_fe_bh, - de_bh); + &lookup); if (status < 0) { mlog_errno(status); goto bail; @@ -1772,9 +1791,9 @@ bail: brelse(new_fe_bh); brelse(parent_fe_bh); - brelse(de_bh); kfree(si.name); kfree(si.value); + ocfs2_free_dir_lookup_result(&lookup); if (inode_ac) ocfs2_free_alloc_context(inode_ac); if (data_ac) @@ -1826,7 +1845,7 @@ static int ocfs2_prepare_orphan_dir(struct ocfs2_super *osb, struct inode **ret_orphan_dir, struct inode *inode, char *name, - struct buffer_head **de_bh) + struct ocfs2_dir_lookup_result *lookup) { struct inode *orphan_dir_inode; struct buffer_head *orphan_dir_bh = NULL; @@ -1857,7 +1876,7 @@ static int ocfs2_prepare_orphan_dir(struct ocfs2_super *osb, status = ocfs2_prepare_dir_for_insert(osb, orphan_dir_inode, orphan_dir_bh, name, - OCFS2_ORPHAN_NAMELEN, de_bh); + OCFS2_ORPHAN_NAMELEN, lookup); if (status < 0) { ocfs2_inode_unlock(orphan_dir_inode, 1); @@ -1884,7 +1903,7 @@ static int ocfs2_orphan_add(struct ocfs2_super *osb, struct inode *inode, struct ocfs2_dinode *fe, char *name, - struct buffer_head *de_bh, + struct ocfs2_dir_lookup_result *lookup, struct inode *orphan_dir_inode) { struct buffer_head *orphan_dir_bh = NULL; @@ -1910,8 +1929,8 @@ static int ocfs2_orphan_add(struct ocfs2_super *osb, * underneath us... */ orphan_fe = (struct ocfs2_dinode *) orphan_dir_bh->b_data; if (S_ISDIR(inode->i_mode)) - le16_add_cpu(&orphan_fe->i_links_count, 1); - orphan_dir_inode->i_nlink = le16_to_cpu(orphan_fe->i_links_count); + ocfs2_add_links_count(orphan_fe, 1); + orphan_dir_inode->i_nlink = ocfs2_read_links_count(orphan_fe); status = ocfs2_journal_dirty(handle, orphan_dir_bh); if (status < 0) { @@ -1922,7 +1941,7 @@ static int ocfs2_orphan_add(struct ocfs2_super *osb, status = __ocfs2_add_entry(handle, orphan_dir_inode, name, OCFS2_ORPHAN_NAMELEN, inode, OCFS2_I(inode)->ip_blkno, - orphan_dir_bh, de_bh); + orphan_dir_bh, lookup); if (status < 0) { mlog_errno(status); goto leave; @@ -1955,8 +1974,7 @@ int ocfs2_orphan_del(struct ocfs2_super *osb, char name[OCFS2_ORPHAN_NAMELEN + 1]; struct ocfs2_dinode *orphan_fe; int status = 0; - struct buffer_head *target_de_bh = NULL; - struct ocfs2_dir_entry *target_de = NULL; + struct ocfs2_dir_lookup_result lookup = { NULL, }; mlog_entry_void(); @@ -1971,17 +1989,15 @@ int ocfs2_orphan_del(struct ocfs2_super *osb, OCFS2_ORPHAN_NAMELEN); /* find it's spot in the orphan directory */ - target_de_bh = ocfs2_find_entry(name, OCFS2_ORPHAN_NAMELEN, - orphan_dir_inode, &target_de); - if (!target_de_bh) { - status = -ENOENT; + status = ocfs2_find_entry(name, OCFS2_ORPHAN_NAMELEN, orphan_dir_inode, + &lookup); + if (status) { mlog_errno(status); goto leave; } /* remove it from the orphan directory */ - status = ocfs2_delete_entry(handle, orphan_dir_inode, target_de, - target_de_bh); + status = ocfs2_delete_entry(handle, orphan_dir_inode, &lookup); if (status < 0) { mlog_errno(status); goto leave; @@ -1997,8 +2013,8 @@ int ocfs2_orphan_del(struct ocfs2_super *osb, /* do the i_nlink dance! :) */ orphan_fe = (struct ocfs2_dinode *) orphan_dir_bh->b_data; if (S_ISDIR(inode->i_mode)) - le16_add_cpu(&orphan_fe->i_links_count, -1); - orphan_dir_inode->i_nlink = le16_to_cpu(orphan_fe->i_links_count); + ocfs2_add_links_count(orphan_fe, -1); + orphan_dir_inode->i_nlink = ocfs2_read_links_count(orphan_fe); status = ocfs2_journal_dirty(handle, orphan_dir_bh); if (status < 0) { @@ -2007,7 +2023,7 @@ int ocfs2_orphan_del(struct ocfs2_super *osb, } leave: - brelse(target_de_bh); + ocfs2_free_dir_lookup_result(&lookup); mlog_exit(status); return status; diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 946d3c34b90b..1386281950db 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -209,6 +209,7 @@ enum ocfs2_mount_options struct ocfs2_journal; struct ocfs2_slot_info; struct ocfs2_recovery_map; +struct ocfs2_replay_map; struct ocfs2_quota_recovery; struct ocfs2_dentry_lock; struct ocfs2_super @@ -264,6 +265,7 @@ struct ocfs2_super atomic_t vol_state; struct mutex recovery_lock; struct ocfs2_recovery_map *recovery_map; + struct ocfs2_replay_map *replay_map; struct task_struct *recovery_thread_task; int disable_recovery; wait_queue_head_t checkpoint_event; @@ -287,11 +289,6 @@ struct ocfs2_super u64 la_last_gd; -#ifdef CONFIG_OCFS2_FS_STATS - struct dentry *local_alloc_debug; - char *local_alloc_debug_buf; -#endif - /* Next three fields are for local node slot recovery during * mount. */ int dirty; @@ -305,9 +302,11 @@ struct ocfs2_super struct ocfs2_cluster_connection *cconn; struct ocfs2_lock_res osb_super_lockres; struct ocfs2_lock_res osb_rename_lockres; + struct ocfs2_lock_res osb_nfs_sync_lockres; struct ocfs2_dlm_debug *osb_dlm_debug; struct dentry *osb_debug_root; + struct dentry *osb_ctxt; wait_queue_head_t recovery_event; @@ -344,6 +343,12 @@ struct ocfs2_super /* used to protect metaecc calculation check of xattr. */ spinlock_t osb_xattr_lock; + + unsigned int osb_dx_mask; + u32 osb_dx_seed[4]; + + /* the group we used to allocate inodes. */ + u64 osb_inode_alloc_group; }; #define OCFS2_SB(sb) ((struct ocfs2_super *)(sb)->s_fs_info) @@ -402,6 +407,51 @@ static inline int ocfs2_meta_ecc(struct ocfs2_super *osb) return 0; } +static inline int ocfs2_supports_indexed_dirs(struct ocfs2_super *osb) +{ + if (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_INDEXED_DIRS) + return 1; + return 0; +} + +static inline unsigned int ocfs2_link_max(struct ocfs2_super *osb) +{ + if (ocfs2_supports_indexed_dirs(osb)) + return OCFS2_DX_LINK_MAX; + return OCFS2_LINK_MAX; +} + +static inline unsigned int ocfs2_read_links_count(struct ocfs2_dinode *di) +{ + u32 nlink = le16_to_cpu(di->i_links_count); + u32 hi = le16_to_cpu(di->i_links_count_hi); + + if (di->i_dyn_features & cpu_to_le16(OCFS2_INDEXED_DIR_FL)) + nlink |= (hi << OCFS2_LINKS_HI_SHIFT); + + return nlink; +} + +static inline void ocfs2_set_links_count(struct ocfs2_dinode *di, u32 nlink) +{ + u16 lo, hi; + + lo = nlink; + hi = nlink >> OCFS2_LINKS_HI_SHIFT; + + di->i_links_count = cpu_to_le16(lo); + di->i_links_count_hi = cpu_to_le16(hi); +} + +static inline void ocfs2_add_links_count(struct ocfs2_dinode *di, int n) +{ + u32 links = ocfs2_read_links_count(di); + + links += n; + + ocfs2_set_links_count(di, links); +} + /* set / clear functions because cluster events can make these happen * in parallel so we want the transitions to be atomic. this also * means that any future flags osb_flags must be protected by spinlock @@ -482,6 +532,12 @@ static inline int ocfs2_uses_extended_slot_map(struct ocfs2_super *osb) #define OCFS2_IS_VALID_DIR_TRAILER(ptr) \ (!strcmp((ptr)->db_signature, OCFS2_DIR_TRAILER_SIGNATURE)) +#define OCFS2_IS_VALID_DX_ROOT(ptr) \ + (!strcmp((ptr)->dr_signature, OCFS2_DX_ROOT_SIGNATURE)) + +#define OCFS2_IS_VALID_DX_LEAF(ptr) \ + (!strcmp((ptr)->dl_signature, OCFS2_DX_LEAF_SIGNATURE)) + static inline unsigned long ino_from_blkno(struct super_block *sb, u64 blkno) { @@ -532,6 +588,16 @@ static inline u64 ocfs2_clusters_to_bytes(struct super_block *sb, return (u64)clusters << OCFS2_SB(sb)->s_clustersize_bits; } +static inline u64 ocfs2_block_to_cluster_start(struct super_block *sb, + u64 blocks) +{ + int bits = OCFS2_SB(sb)->s_clustersize_bits - sb->s_blocksize_bits; + unsigned int clusters; + + clusters = ocfs2_blocks_to_clusters(sb, blocks); + return (u64)clusters << bits; +} + static inline u64 ocfs2_align_bytes_to_clusters(struct super_block *sb, u64 bytes) { diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h index 2332ef740f4f..7ab6e9e5e77c 100644 --- a/fs/ocfs2/ocfs2_fs.h +++ b/fs/ocfs2/ocfs2_fs.h @@ -66,6 +66,8 @@ #define OCFS2_GROUP_DESC_SIGNATURE "GROUP01" #define OCFS2_XATTR_BLOCK_SIGNATURE "XATTR01" #define OCFS2_DIR_TRAILER_SIGNATURE "DIRTRL1" +#define OCFS2_DX_ROOT_SIGNATURE "DXDIR01" +#define OCFS2_DX_LEAF_SIGNATURE "DXLEAF1" /* Compatibility flags */ #define OCFS2_HAS_COMPAT_FEATURE(sb,mask) \ @@ -95,7 +97,8 @@ | OCFS2_FEATURE_INCOMPAT_EXTENDED_SLOT_MAP \ | OCFS2_FEATURE_INCOMPAT_USERSPACE_STACK \ | OCFS2_FEATURE_INCOMPAT_XATTR \ - | OCFS2_FEATURE_INCOMPAT_META_ECC) + | OCFS2_FEATURE_INCOMPAT_META_ECC \ + | OCFS2_FEATURE_INCOMPAT_INDEXED_DIRS) #define OCFS2_FEATURE_RO_COMPAT_SUPP (OCFS2_FEATURE_RO_COMPAT_UNWRITTEN \ | OCFS2_FEATURE_RO_COMPAT_USRQUOTA \ | OCFS2_FEATURE_RO_COMPAT_GRPQUOTA) @@ -151,6 +154,9 @@ /* Support for extended attributes */ #define OCFS2_FEATURE_INCOMPAT_XATTR 0x0200 +/* Support for indexed directores */ +#define OCFS2_FEATURE_INCOMPAT_INDEXED_DIRS 0x0400 + /* Metadata checksum and error correction */ #define OCFS2_FEATURE_INCOMPAT_META_ECC 0x0800 @@ -411,8 +417,12 @@ static struct ocfs2_system_inode_info ocfs2_system_inodes[NUM_SYSTEM_INODES] = { #define OCFS2_DIR_REC_LEN(name_len) (((name_len) + OCFS2_DIR_MEMBER_LEN + \ OCFS2_DIR_ROUND) & \ ~OCFS2_DIR_ROUND) +#define OCFS2_DIR_MIN_REC_LEN OCFS2_DIR_REC_LEN(1) #define OCFS2_LINK_MAX 32000 +#define OCFS2_DX_LINK_MAX ((1U << 31) - 1U) +#define OCFS2_LINKS_HI_SHIFT 16 +#define OCFS2_DX_ENTRIES_MAX (0xffffffffU) #define S_SHIFT 12 static unsigned char ocfs2_type_by_mode[S_IFMT >> S_SHIFT] = { @@ -628,8 +638,9 @@ struct ocfs2_super_block { /*B8*/ __le16 s_xattr_inline_size; /* extended attribute inline size for this fs*/ __le16 s_reserved0; - __le32 s_reserved1; -/*C0*/ __le64 s_reserved2[16]; /* Fill out superblock */ + __le32 s_dx_seed[3]; /* seed[0-2] for dx dir hash. + * s_uuid_hash serves as seed[3]. */ +/*C0*/ __le64 s_reserved2[15]; /* Fill out superblock */ /*140*/ /* @@ -679,7 +690,7 @@ struct ocfs2_dinode { belongs to */ __le16 i_suballoc_bit; /* Bit offset in suballocator block group */ -/*10*/ __le16 i_reserved0; +/*10*/ __le16 i_links_count_hi; /* High 16 bits of links count */ __le16 i_xattr_inline_size; __le32 i_clusters; /* Cluster count */ __le32 i_uid; /* Owner UID */ @@ -705,7 +716,8 @@ struct ocfs2_dinode { __le16 i_dyn_features; __le64 i_xattr_loc; /*80*/ struct ocfs2_block_check i_check; /* Error checking */ -/*88*/ __le64 i_reserved2[6]; +/*88*/ __le64 i_dx_root; /* Pointer to dir index root block */ + __le64 i_reserved2[5]; /*B8*/ union { __le64 i_pad1; /* Generic way to refer to this 64bit union */ @@ -781,6 +793,90 @@ struct ocfs2_dir_block_trailer { /*40*/ }; + /* + * A directory entry in the indexed tree. We don't store the full name here, + * but instead provide a pointer to the full dirent in the unindexed tree. + * + * We also store name_len here so as to reduce the number of leaf blocks we + * need to search in case of collisions. + */ +struct ocfs2_dx_entry { + __le32 dx_major_hash; /* Used to find logical + * cluster in index */ + __le32 dx_minor_hash; /* Lower bits used to find + * block in cluster */ + __le64 dx_dirent_blk; /* Physical block in unindexed + * tree holding this dirent. */ +}; + +struct ocfs2_dx_entry_list { + __le32 de_reserved; + __le16 de_count; /* Maximum number of entries + * possible in de_entries */ + __le16 de_num_used; /* Current number of + * de_entries entries */ + struct ocfs2_dx_entry de_entries[0]; /* Indexed dir entries + * in a packed array of + * length de_num_used */ +}; + +#define OCFS2_DX_FLAG_INLINE 0x01 + +/* + * A directory indexing block. Each indexed directory has one of these, + * pointed to by ocfs2_dinode. + * + * This block stores an indexed btree root, and a set of free space + * start-of-list pointers. + */ +struct ocfs2_dx_root_block { + __u8 dr_signature[8]; /* Signature for verification */ + struct ocfs2_block_check dr_check; /* Error checking */ + __le16 dr_suballoc_slot; /* Slot suballocator this + * block belongs to. */ + __le16 dr_suballoc_bit; /* Bit offset in suballocator + * block group */ + __le32 dr_fs_generation; /* Must match super block */ + __le64 dr_blkno; /* Offset on disk, in blocks */ + __le64 dr_last_eb_blk; /* Pointer to last + * extent block */ + __le32 dr_clusters; /* Clusters allocated + * to the indexed tree. */ + __u8 dr_flags; /* OCFS2_DX_FLAG_* flags */ + __u8 dr_reserved0; + __le16 dr_reserved1; + __le64 dr_dir_blkno; /* Pointer to parent inode */ + __le32 dr_num_entries; /* Total number of + * names stored in + * this directory.*/ + __le32 dr_reserved2; + __le64 dr_free_blk; /* Pointer to head of free + * unindexed block list. */ + __le64 dr_reserved3[15]; + union { + struct ocfs2_extent_list dr_list; /* Keep this aligned to 128 + * bits for maximum space + * efficiency. */ + struct ocfs2_dx_entry_list dr_entries; /* In-root-block list of + * entries. We grow out + * to extents if this + * gets too big. */ + }; +}; + +/* + * The header of a leaf block in the indexed tree. + */ +struct ocfs2_dx_leaf { + __u8 dl_signature[8];/* Signature for verification */ + struct ocfs2_block_check dl_check; /* Error checking */ + __le64 dl_blkno; /* Offset on disk, in blocks */ + __le32 dl_fs_generation;/* Must match super block */ + __le32 dl_reserved0; + __le64 dl_reserved1; + struct ocfs2_dx_entry_list dl_list; +}; + /* * On disk allocator group structure for OCFS2 */ @@ -1112,6 +1208,16 @@ static inline int ocfs2_extent_recs_per_inode_with_xattr( return size / sizeof(struct ocfs2_extent_rec); } +static inline int ocfs2_extent_recs_per_dx_root(struct super_block *sb) +{ + int size; + + size = sb->s_blocksize - + offsetof(struct ocfs2_dx_root_block, dr_list.l_recs); + + return size / sizeof(struct ocfs2_extent_rec); +} + static inline int ocfs2_chain_recs_per_inode(struct super_block *sb) { int size; @@ -1132,6 +1238,26 @@ static inline u16 ocfs2_extent_recs_per_eb(struct super_block *sb) return size / sizeof(struct ocfs2_extent_rec); } +static inline int ocfs2_dx_entries_per_leaf(struct super_block *sb) +{ + int size; + + size = sb->s_blocksize - + offsetof(struct ocfs2_dx_leaf, dl_list.de_entries); + + return size / sizeof(struct ocfs2_dx_entry); +} + +static inline int ocfs2_dx_entries_per_root(struct super_block *sb) +{ + int size; + + size = sb->s_blocksize - + offsetof(struct ocfs2_dx_root_block, dr_entries.de_entries); + + return size / sizeof(struct ocfs2_dx_entry); +} + static inline u16 ocfs2_local_alloc_size(struct super_block *sb) { u16 size; diff --git a/fs/ocfs2/ocfs2_lockid.h b/fs/ocfs2/ocfs2_lockid.h index eb6f50c9ceca..a53ce87481bf 100644 --- a/fs/ocfs2/ocfs2_lockid.h +++ b/fs/ocfs2/ocfs2_lockid.h @@ -47,6 +47,7 @@ enum ocfs2_lock_type { OCFS2_LOCK_TYPE_OPEN, OCFS2_LOCK_TYPE_FLOCK, OCFS2_LOCK_TYPE_QINFO, + OCFS2_LOCK_TYPE_NFS_SYNC, OCFS2_NUM_LOCK_TYPES }; @@ -81,6 +82,9 @@ static inline char ocfs2_lock_type_char(enum ocfs2_lock_type type) case OCFS2_LOCK_TYPE_QINFO: c = 'Q'; break; + case OCFS2_LOCK_TYPE_NFS_SYNC: + c = 'Y'; + break; default: c = '\0'; } diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index a69628603e18..b4ca5911caaf 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -48,7 +48,8 @@ #include "buffer_head_io.h" #define NOT_ALLOC_NEW_GROUP 0 -#define ALLOC_NEW_GROUP 1 +#define ALLOC_NEW_GROUP 0x1 +#define ALLOC_GROUPS_FROM_GLOBAL 0x2 #define OCFS2_MAX_INODES_TO_STEAL 1024 @@ -64,7 +65,9 @@ static int ocfs2_block_group_fill(handle_t *handle, static int ocfs2_block_group_alloc(struct ocfs2_super *osb, struct inode *alloc_inode, struct buffer_head *bh, - u64 max_block); + u64 max_block, + u64 *last_alloc_group, + int flags); static int ocfs2_cluster_group_search(struct inode *inode, struct buffer_head *group_bh, @@ -116,6 +119,7 @@ static inline void ocfs2_block_to_cluster_group(struct inode *inode, u16 *bg_bit_off); static int ocfs2_reserve_clusters_with_limit(struct ocfs2_super *osb, u32 bits_wanted, u64 max_block, + int flags, struct ocfs2_alloc_context **ac); void ocfs2_free_ac_resource(struct ocfs2_alloc_context *ac) @@ -403,7 +407,9 @@ static inline u16 ocfs2_find_smallest_chain(struct ocfs2_chain_list *cl) static int ocfs2_block_group_alloc(struct ocfs2_super *osb, struct inode *alloc_inode, struct buffer_head *bh, - u64 max_block) + u64 max_block, + u64 *last_alloc_group, + int flags) { int status, credits; struct ocfs2_dinode *fe = (struct ocfs2_dinode *) bh->b_data; @@ -423,7 +429,7 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb, cl = &fe->id2.i_chain; status = ocfs2_reserve_clusters_with_limit(osb, le16_to_cpu(cl->cl_cpg), - max_block, &ac); + max_block, flags, &ac); if (status < 0) { if (status != -ENOSPC) mlog_errno(status); @@ -440,6 +446,11 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb, goto bail; } + if (last_alloc_group && *last_alloc_group != 0) { + mlog(0, "use old allocation group %llu for block group alloc\n", + (unsigned long long)*last_alloc_group); + ac->ac_last_group = *last_alloc_group; + } status = ocfs2_claim_clusters(osb, handle, ac, @@ -514,6 +525,11 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb, alloc_inode->i_blocks = ocfs2_inode_sector_count(alloc_inode); status = 0; + + /* save the new last alloc group so that the caller can cache it. */ + if (last_alloc_group) + *last_alloc_group = ac->ac_last_group; + bail: if (handle) ocfs2_commit_trans(osb, handle); @@ -531,7 +547,8 @@ static int ocfs2_reserve_suballoc_bits(struct ocfs2_super *osb, struct ocfs2_alloc_context *ac, int type, u32 slot, - int alloc_new_group) + u64 *last_alloc_group, + int flags) { int status; u32 bits_wanted = ac->ac_bits_wanted; @@ -587,7 +604,7 @@ static int ocfs2_reserve_suballoc_bits(struct ocfs2_super *osb, goto bail; } - if (alloc_new_group != ALLOC_NEW_GROUP) { + if (!(flags & ALLOC_NEW_GROUP)) { mlog(0, "Alloc File %u Full: wanted=%u, free_bits=%u, " "and we don't alloc a new group for it.\n", slot, bits_wanted, free_bits); @@ -596,7 +613,8 @@ static int ocfs2_reserve_suballoc_bits(struct ocfs2_super *osb, } status = ocfs2_block_group_alloc(osb, alloc_inode, bh, - ac->ac_max_block); + ac->ac_max_block, + last_alloc_group, flags); if (status < 0) { if (status != -ENOSPC) mlog_errno(status); @@ -640,7 +658,7 @@ int ocfs2_reserve_new_metadata_blocks(struct ocfs2_super *osb, status = ocfs2_reserve_suballoc_bits(osb, (*ac), EXTENT_ALLOC_SYSTEM_INODE, - slot, ALLOC_NEW_GROUP); + slot, NULL, ALLOC_NEW_GROUP); if (status < 0) { if (status != -ENOSPC) mlog_errno(status); @@ -686,7 +704,8 @@ static int ocfs2_steal_inode_from_other_nodes(struct ocfs2_super *osb, status = ocfs2_reserve_suballoc_bits(osb, ac, INODE_ALLOC_SYSTEM_INODE, - slot, NOT_ALLOC_NEW_GROUP); + slot, NULL, + NOT_ALLOC_NEW_GROUP); if (status >= 0) { ocfs2_set_inode_steal_slot(osb, slot); break; @@ -703,6 +722,7 @@ int ocfs2_reserve_new_inode(struct ocfs2_super *osb, { int status; s16 slot = ocfs2_get_inode_steal_slot(osb); + u64 alloc_group; *ac = kzalloc(sizeof(struct ocfs2_alloc_context), GFP_KERNEL); if (!(*ac)) { @@ -738,12 +758,22 @@ int ocfs2_reserve_new_inode(struct ocfs2_super *osb, goto inode_steal; atomic_set(&osb->s_num_inodes_stolen, 0); + alloc_group = osb->osb_inode_alloc_group; status = ocfs2_reserve_suballoc_bits(osb, *ac, INODE_ALLOC_SYSTEM_INODE, - osb->slot_num, ALLOC_NEW_GROUP); + osb->slot_num, + &alloc_group, + ALLOC_NEW_GROUP | + ALLOC_GROUPS_FROM_GLOBAL); if (status >= 0) { status = 0; + spin_lock(&osb->osb_lock); + osb->osb_inode_alloc_group = alloc_group; + spin_unlock(&osb->osb_lock); + mlog(0, "after reservation, new allocation group is " + "%llu\n", (unsigned long long)alloc_group); + /* * Some inodes must be freed by us, so try to allocate * from our own next time. @@ -790,7 +820,7 @@ int ocfs2_reserve_cluster_bitmap_bits(struct ocfs2_super *osb, status = ocfs2_reserve_suballoc_bits(osb, ac, GLOBAL_BITMAP_SYSTEM_INODE, - OCFS2_INVALID_SLOT, + OCFS2_INVALID_SLOT, NULL, ALLOC_NEW_GROUP); if (status < 0 && status != -ENOSPC) { mlog_errno(status); @@ -806,6 +836,7 @@ bail: * things a bit. */ static int ocfs2_reserve_clusters_with_limit(struct ocfs2_super *osb, u32 bits_wanted, u64 max_block, + int flags, struct ocfs2_alloc_context **ac) { int status; @@ -823,7 +854,8 @@ static int ocfs2_reserve_clusters_with_limit(struct ocfs2_super *osb, (*ac)->ac_max_block = max_block; status = -ENOSPC; - if (ocfs2_alloc_should_use_local(osb, bits_wanted)) { + if (!(flags & ALLOC_GROUPS_FROM_GLOBAL) && + ocfs2_alloc_should_use_local(osb, bits_wanted)) { status = ocfs2_reserve_local_alloc_bits(osb, bits_wanted, *ac); @@ -861,7 +893,8 @@ int ocfs2_reserve_clusters(struct ocfs2_super *osb, u32 bits_wanted, struct ocfs2_alloc_context **ac) { - return ocfs2_reserve_clusters_with_limit(osb, bits_wanted, 0, ac); + return ocfs2_reserve_clusters_with_limit(osb, bits_wanted, 0, + ALLOC_NEW_GROUP, ac); } /* @@ -1618,8 +1651,41 @@ bail: return status; } +static void ocfs2_init_inode_ac_group(struct inode *dir, + struct buffer_head *parent_fe_bh, + struct ocfs2_alloc_context *ac) +{ + struct ocfs2_dinode *fe = (struct ocfs2_dinode *)parent_fe_bh->b_data; + /* + * Try to allocate inodes from some specific group. + * + * If the parent dir has recorded the last group used in allocation, + * cool, use it. Otherwise if we try to allocate new inode from the + * same slot the parent dir belongs to, use the same chunk. + * + * We are very careful here to avoid the mistake of setting + * ac_last_group to a group descriptor from a different (unlocked) slot. + */ + if (OCFS2_I(dir)->ip_last_used_group && + OCFS2_I(dir)->ip_last_used_slot == ac->ac_alloc_slot) + ac->ac_last_group = OCFS2_I(dir)->ip_last_used_group; + else if (le16_to_cpu(fe->i_suballoc_slot) == ac->ac_alloc_slot) + ac->ac_last_group = ocfs2_which_suballoc_group( + le64_to_cpu(fe->i_blkno), + le16_to_cpu(fe->i_suballoc_bit)); +} + +static inline void ocfs2_save_inode_ac_group(struct inode *dir, + struct ocfs2_alloc_context *ac) +{ + OCFS2_I(dir)->ip_last_used_group = ac->ac_last_group; + OCFS2_I(dir)->ip_last_used_slot = ac->ac_alloc_slot; +} + int ocfs2_claim_new_inode(struct ocfs2_super *osb, handle_t *handle, + struct inode *dir, + struct buffer_head *parent_fe_bh, struct ocfs2_alloc_context *ac, u16 *suballoc_bit, u64 *fe_blkno) @@ -1635,6 +1701,8 @@ int ocfs2_claim_new_inode(struct ocfs2_super *osb, BUG_ON(ac->ac_bits_wanted != 1); BUG_ON(ac->ac_which != OCFS2_AC_USE_INODE); + ocfs2_init_inode_ac_group(dir, parent_fe_bh, ac); + status = ocfs2_claim_suballoc_bits(osb, ac, handle, @@ -1653,6 +1721,7 @@ int ocfs2_claim_new_inode(struct ocfs2_super *osb, *fe_blkno = bg_blkno + (u64) (*suballoc_bit); ac->ac_bits_given++; + ocfs2_save_inode_ac_group(dir, ac); status = 0; bail: mlog_exit(status); @@ -2116,3 +2185,162 @@ out: return ret; } + +/* + * Read the inode specified by blkno to get suballoc_slot and + * suballoc_bit. + */ +static int ocfs2_get_suballoc_slot_bit(struct ocfs2_super *osb, u64 blkno, + u16 *suballoc_slot, u16 *suballoc_bit) +{ + int status; + struct buffer_head *inode_bh = NULL; + struct ocfs2_dinode *inode_fe; + + mlog_entry("blkno: %llu\n", blkno); + + /* dirty read disk */ + status = ocfs2_read_blocks_sync(osb, blkno, 1, &inode_bh); + if (status < 0) { + mlog(ML_ERROR, "read block %llu failed %d\n", blkno, status); + goto bail; + } + + inode_fe = (struct ocfs2_dinode *) inode_bh->b_data; + if (!OCFS2_IS_VALID_DINODE(inode_fe)) { + mlog(ML_ERROR, "invalid inode %llu requested\n", blkno); + status = -EINVAL; + goto bail; + } + + if (le16_to_cpu(inode_fe->i_suballoc_slot) != OCFS2_INVALID_SLOT && + (u32)le16_to_cpu(inode_fe->i_suballoc_slot) > osb->max_slots - 1) { + mlog(ML_ERROR, "inode %llu has invalid suballoc slot %u\n", + blkno, (u32)le16_to_cpu(inode_fe->i_suballoc_slot)); + status = -EINVAL; + goto bail; + } + + if (suballoc_slot) + *suballoc_slot = le16_to_cpu(inode_fe->i_suballoc_slot); + if (suballoc_bit) + *suballoc_bit = le16_to_cpu(inode_fe->i_suballoc_bit); + +bail: + brelse(inode_bh); + + mlog_exit(status); + return status; +} + +/* + * test whether bit is SET in allocator bitmap or not. on success, 0 + * is returned and *res is 1 for SET; 0 otherwise. when fails, errno + * is returned and *res is meaningless. Call this after you have + * cluster locked against suballoc, or you may get a result based on + * non-up2date contents + */ +static int ocfs2_test_suballoc_bit(struct ocfs2_super *osb, + struct inode *suballoc, + struct buffer_head *alloc_bh, u64 blkno, + u16 bit, int *res) +{ + struct ocfs2_dinode *alloc_fe; + struct ocfs2_group_desc *group; + struct buffer_head *group_bh = NULL; + u64 bg_blkno; + int status; + + mlog_entry("blkno: %llu bit: %u\n", blkno, (unsigned int)bit); + + alloc_fe = (struct ocfs2_dinode *)alloc_bh->b_data; + if ((bit + 1) > ocfs2_bits_per_group(&alloc_fe->id2.i_chain)) { + mlog(ML_ERROR, "suballoc bit %u out of range of %u\n", + (unsigned int)bit, + ocfs2_bits_per_group(&alloc_fe->id2.i_chain)); + status = -EINVAL; + goto bail; + } + + bg_blkno = ocfs2_which_suballoc_group(blkno, bit); + status = ocfs2_read_group_descriptor(suballoc, alloc_fe, bg_blkno, + &group_bh); + if (status < 0) { + mlog(ML_ERROR, "read group %llu failed %d\n", bg_blkno, status); + goto bail; + } + + group = (struct ocfs2_group_desc *) group_bh->b_data; + *res = ocfs2_test_bit(bit, (unsigned long *)group->bg_bitmap); + +bail: + brelse(group_bh); + + mlog_exit(status); + return status; +} + +/* + * Test if the bit representing this inode (blkno) is set in the + * suballocator. + * + * On success, 0 is returned and *res is 1 for SET; 0 otherwise. + * + * In the event of failure, a negative value is returned and *res is + * meaningless. + * + * Callers must make sure to hold nfs_sync_lock to prevent + * ocfs2_delete_inode() on another node from accessing the same + * suballocator concurrently. + */ +int ocfs2_test_inode_bit(struct ocfs2_super *osb, u64 blkno, int *res) +{ + int status; + u16 suballoc_bit = 0, suballoc_slot = 0; + struct inode *inode_alloc_inode; + struct buffer_head *alloc_bh = NULL; + + mlog_entry("blkno: %llu", blkno); + + status = ocfs2_get_suballoc_slot_bit(osb, blkno, &suballoc_slot, + &suballoc_bit); + if (status < 0) { + mlog(ML_ERROR, "get alloc slot and bit failed %d\n", status); + goto bail; + } + + inode_alloc_inode = + ocfs2_get_system_file_inode(osb, INODE_ALLOC_SYSTEM_INODE, + suballoc_slot); + if (!inode_alloc_inode) { + /* the error code could be inaccurate, but we are not able to + * get the correct one. */ + status = -EINVAL; + mlog(ML_ERROR, "unable to get alloc inode in slot %u\n", + (u32)suballoc_slot); + goto bail; + } + + mutex_lock(&inode_alloc_inode->i_mutex); + status = ocfs2_inode_lock(inode_alloc_inode, &alloc_bh, 0); + if (status < 0) { + mutex_unlock(&inode_alloc_inode->i_mutex); + mlog(ML_ERROR, "lock on alloc inode on slot %u failed %d\n", + (u32)suballoc_slot, status); + goto bail; + } + + status = ocfs2_test_suballoc_bit(osb, inode_alloc_inode, alloc_bh, + blkno, suballoc_bit, res); + if (status < 0) + mlog(ML_ERROR, "test suballoc bit failed %d\n", status); + + ocfs2_inode_unlock(inode_alloc_inode, 0); + mutex_unlock(&inode_alloc_inode->i_mutex); + + iput(inode_alloc_inode); + brelse(alloc_bh); +bail: + mlog_exit(status); + return status; +} diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h index e3c13c77f9e8..8c9a78a43164 100644 --- a/fs/ocfs2/suballoc.h +++ b/fs/ocfs2/suballoc.h @@ -88,6 +88,8 @@ int ocfs2_claim_metadata(struct ocfs2_super *osb, u64 *blkno_start); int ocfs2_claim_new_inode(struct ocfs2_super *osb, handle_t *handle, + struct inode *dir, + struct buffer_head *parent_fe_bh, struct ocfs2_alloc_context *ac, u16 *suballoc_bit, u64 *fe_blkno); @@ -186,4 +188,6 @@ int ocfs2_lock_allocators(struct inode *inode, struct ocfs2_extent_tree *et, u32 clusters_to_add, u32 extents_to_split, struct ocfs2_alloc_context **data_ac, struct ocfs2_alloc_context **meta_ac); + +int ocfs2_test_inode_bit(struct ocfs2_super *osb, u64 blkno, int *res); #endif /* _CHAINALLOC_H_ */ diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 7ac83a81ee55..79ff8d9d37e0 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -201,6 +201,170 @@ static const match_table_t tokens = { {Opt_err, NULL} }; +#ifdef CONFIG_DEBUG_FS +static int ocfs2_osb_dump(struct ocfs2_super *osb, char *buf, int len) +{ + int out = 0; + int i; + struct ocfs2_cluster_connection *cconn = osb->cconn; + struct ocfs2_recovery_map *rm = osb->recovery_map; + + out += snprintf(buf + out, len - out, + "%10s => Id: %-s Uuid: %-s Gen: 0x%X Label: %-s\n", + "Device", osb->dev_str, osb->uuid_str, + osb->fs_generation, osb->vol_label); + + out += snprintf(buf + out, len - out, + "%10s => State: %d Flags: 0x%lX\n", "Volume", + atomic_read(&osb->vol_state), osb->osb_flags); + + out += snprintf(buf + out, len - out, + "%10s => Block: %lu Cluster: %d\n", "Sizes", + osb->sb->s_blocksize, osb->s_clustersize); + + out += snprintf(buf + out, len - out, + "%10s => Compat: 0x%X Incompat: 0x%X " + "ROcompat: 0x%X\n", + "Features", osb->s_feature_compat, + osb->s_feature_incompat, osb->s_feature_ro_compat); + + out += snprintf(buf + out, len - out, + "%10s => Opts: 0x%lX AtimeQuanta: %u\n", "Mount", + osb->s_mount_opt, osb->s_atime_quantum); + + out += snprintf(buf + out, len - out, + "%10s => Stack: %s Name: %*s Version: %d.%d\n", + "Cluster", + (*osb->osb_cluster_stack == '\0' ? + "o2cb" : osb->osb_cluster_stack), + cconn->cc_namelen, cconn->cc_name, + cconn->cc_version.pv_major, cconn->cc_version.pv_minor); + + spin_lock(&osb->dc_task_lock); + out += snprintf(buf + out, len - out, + "%10s => Pid: %d Count: %lu WakeSeq: %lu " + "WorkSeq: %lu\n", "DownCnvt", + task_pid_nr(osb->dc_task), osb->blocked_lock_count, + osb->dc_wake_sequence, osb->dc_work_sequence); + spin_unlock(&osb->dc_task_lock); + + spin_lock(&osb->osb_lock); + out += snprintf(buf + out, len - out, "%10s => Pid: %d Nodes:", + "Recovery", + (osb->recovery_thread_task ? + task_pid_nr(osb->recovery_thread_task) : -1)); + if (rm->rm_used == 0) + out += snprintf(buf + out, len - out, " None\n"); + else { + for (i = 0; i < rm->rm_used; i++) + out += snprintf(buf + out, len - out, " %d", + rm->rm_entries[i]); + out += snprintf(buf + out, len - out, "\n"); + } + spin_unlock(&osb->osb_lock); + + out += snprintf(buf + out, len - out, + "%10s => Pid: %d Interval: %lu Needs: %d\n", "Commit", + task_pid_nr(osb->commit_task), osb->osb_commit_interval, + atomic_read(&osb->needs_checkpoint)); + + out += snprintf(buf + out, len - out, + "%10s => State: %d NumTxns: %d TxnId: %lu\n", + "Journal", osb->journal->j_state, + atomic_read(&osb->journal->j_num_trans), + osb->journal->j_trans_id); + + out += snprintf(buf + out, len - out, + "%10s => GlobalAllocs: %d LocalAllocs: %d " + "SubAllocs: %d LAWinMoves: %d SAExtends: %d\n", + "Stats", + atomic_read(&osb->alloc_stats.bitmap_data), + atomic_read(&osb->alloc_stats.local_data), + atomic_read(&osb->alloc_stats.bg_allocs), + atomic_read(&osb->alloc_stats.moves), + atomic_read(&osb->alloc_stats.bg_extends)); + + out += snprintf(buf + out, len - out, + "%10s => State: %u Descriptor: %llu Size: %u bits " + "Default: %u bits\n", + "LocalAlloc", osb->local_alloc_state, + (unsigned long long)osb->la_last_gd, + osb->local_alloc_bits, osb->local_alloc_default_bits); + + spin_lock(&osb->osb_lock); + out += snprintf(buf + out, len - out, + "%10s => Slot: %d NumStolen: %d\n", "Steal", + osb->s_inode_steal_slot, + atomic_read(&osb->s_num_inodes_stolen)); + spin_unlock(&osb->osb_lock); + + out += snprintf(buf + out, len - out, "%10s => %3s %10s\n", + "Slots", "Num", "RecoGen"); + + for (i = 0; i < osb->max_slots; ++i) { + out += snprintf(buf + out, len - out, + "%10s %c %3d %10d\n", + " ", + (i == osb->slot_num ? '*' : ' '), + i, osb->slot_recovery_generations[i]); + } + + return out; +} + +static int ocfs2_osb_debug_open(struct inode *inode, struct file *file) +{ + struct ocfs2_super *osb = inode->i_private; + char *buf = NULL; + + buf = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!buf) + goto bail; + + i_size_write(inode, ocfs2_osb_dump(osb, buf, PAGE_SIZE)); + + file->private_data = buf; + + return 0; +bail: + return -ENOMEM; +} + +static int ocfs2_debug_release(struct inode *inode, struct file *file) +{ + kfree(file->private_data); + return 0; +} + +static ssize_t ocfs2_debug_read(struct file *file, char __user *buf, + size_t nbytes, loff_t *ppos) +{ + return simple_read_from_buffer(buf, nbytes, ppos, file->private_data, + i_size_read(file->f_mapping->host)); +} +#else +static int ocfs2_osb_debug_open(struct inode *inode, struct file *file) +{ + return 0; +} +static int ocfs2_debug_release(struct inode *inode, struct file *file) +{ + return 0; +} +static ssize_t ocfs2_debug_read(struct file *file, char __user *buf, + size_t nbytes, loff_t *ppos) +{ + return 0; +} +#endif /* CONFIG_DEBUG_FS */ + +static struct file_operations ocfs2_osb_debug_fops = { + .open = ocfs2_osb_debug_open, + .release = ocfs2_debug_release, + .read = ocfs2_debug_read, + .llseek = generic_file_llseek, +}; + /* * write_super and sync_fs ripped right out of ext3. */ @@ -926,6 +1090,16 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) goto read_super_error; } + osb->osb_ctxt = debugfs_create_file("fs_state", S_IFREG|S_IRUSR, + osb->osb_debug_root, + osb, + &ocfs2_osb_debug_fops); + if (!osb->osb_ctxt) { + status = -EINVAL; + mlog_errno(status); + goto read_super_error; + } + status = ocfs2_mount_volume(sb); if (osb->root_inode) inode = igrab(osb->root_inode); @@ -1620,6 +1794,8 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err) osb = OCFS2_SB(sb); BUG_ON(!osb); + debugfs_remove(osb->osb_ctxt); + ocfs2_disable_quotas(osb); ocfs2_shutdown_local_alloc(osb); @@ -1742,6 +1918,12 @@ static int ocfs2_initialize_super(struct super_block *sb, bbits = le32_to_cpu(di->id2.i_super.s_blocksize_bits); sb->s_maxbytes = ocfs2_max_file_offset(bbits, cbits); + osb->osb_dx_mask = (1 << (cbits - bbits)) - 1; + + for (i = 0; i < 3; i++) + osb->osb_dx_seed[i] = le32_to_cpu(di->id2.i_super.s_dx_seed[i]); + osb->osb_dx_seed[3] = le32_to_cpu(di->id2.i_super.s_uuid_hash); + osb->sb = sb; /* Save off for ocfs2_rw_direct */ osb->s_sectsize_bits = blksize_bits(sector_size); @@ -2130,6 +2312,12 @@ static int ocfs2_check_volume(struct ocfs2_super *osb) * lock, and it's marked as dirty, set the bit in the recover * map and launch a recovery thread for it. */ status = ocfs2_mark_dead_nodes(osb); + if (status < 0) { + mlog_errno(status); + goto finally; + } + + status = ocfs2_compute_replay_slots(osb); if (status < 0) mlog_errno(status); diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 2563df89fc2a..15631019dc63 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -512,7 +512,7 @@ int ocfs2_calc_xattr_init(struct inode *dir, struct ocfs2_security_xattr_info *si, int *want_clusters, int *xattr_credits, - struct ocfs2_alloc_context **xattr_ac) + int *want_meta) { int ret = 0; struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); @@ -554,11 +554,7 @@ int ocfs2_calc_xattr_init(struct inode *dir, if (dir->i_sb->s_blocksize == OCFS2_MIN_BLOCKSIZE || (S_ISDIR(mode) && ocfs2_supports_inline_data(osb)) || (s_size + a_size) > OCFS2_XATTR_FREE_IN_IBODY) { - ret = ocfs2_reserve_new_metadata_blocks(osb, 1, xattr_ac); - if (ret) { - mlog_errno(ret); - return ret; - } + *want_meta = *want_meta + 1; *xattr_credits += OCFS2_XATTR_BLOCK_CREATE_CREDITS; } diff --git a/fs/ocfs2/xattr.h b/fs/ocfs2/xattr.h index 5a1ebc789f7e..1ca7e9a1b7bc 100644 --- a/fs/ocfs2/xattr.h +++ b/fs/ocfs2/xattr.h @@ -68,7 +68,7 @@ int ocfs2_calc_security_init(struct inode *, int *, int *, struct ocfs2_alloc_context **); int ocfs2_calc_xattr_init(struct inode *, struct buffer_head *, int, struct ocfs2_security_xattr_info *, - int *, int *, struct ocfs2_alloc_context **); + int *, int *, int *); /* * xattrs can live inside an inode, as part of an external xattr block, diff --git a/fs/partitions/check.c b/fs/partitions/check.c index 38e337d51ced..99e33ef40be4 100644 --- a/fs/partitions/check.c +++ b/fs/partitions/check.c @@ -19,6 +19,7 @@ #include <linux/kmod.h> #include <linux/ctype.h> #include <linux/genhd.h> +#include <linux/blktrace_api.h> #include "check.h" @@ -294,6 +295,9 @@ static struct attribute_group part_attr_group = { static struct attribute_group *part_attr_groups[] = { &part_attr_group, +#ifdef CONFIG_BLK_DEV_IO_TRACE + &blk_trace_attr_group, +#endif NULL }; diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c index b446d7ad0b0d..7e14d1a04001 100644 --- a/fs/proc/nommu.c +++ b/fs/proc/nommu.c @@ -76,7 +76,7 @@ static int nommu_region_show(struct seq_file *m, struct vm_region *region) /* * display a list of all the REGIONs the kernel knows about - * - nommu kernals have a single flat list + * - nommu kernels have a single flat list */ static int nommu_region_list_show(struct seq_file *m, void *_p) { diff --git a/fs/read_write.c b/fs/read_write.c index 6d5d8ff238aa..9d1e76bb9ee1 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -731,10 +731,16 @@ SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec, return ret; } +static inline loff_t pos_from_hilo(unsigned long high, unsigned long low) +{ +#define HALF_LONG_BITS (BITS_PER_LONG / 2) + return (((loff_t)high << HALF_LONG_BITS) << HALF_LONG_BITS) | low; +} + SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec, - unsigned long, vlen, u32, pos_high, u32, pos_low) + unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) { - loff_t pos = ((loff_t)pos_high << 32) | pos_low; + loff_t pos = pos_from_hilo(pos_h, pos_l); struct file *file; ssize_t ret = -EBADF; int fput_needed; @@ -757,9 +763,9 @@ SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec, } SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec, - unsigned long, vlen, u32, pos_high, u32, pos_low) + unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) { - loff_t pos = ((loff_t)pos_high << 32) | pos_low; + loff_t pos = pos_from_hilo(pos_h, pos_l); struct file *file; ssize_t ret = -EBADF; int fput_needed; diff --git a/fs/ubifs/Kconfig b/fs/ubifs/Kconfig index e35b54d5059d..830e3f76f442 100644 --- a/fs/ubifs/Kconfig +++ b/fs/ubifs/Kconfig @@ -22,7 +22,7 @@ config UBIFS_FS_ADVANCED_COMPR depends on UBIFS_FS help This option allows to explicitly choose which compressions, if any, - are enabled in UBIFS. Removing compressors means inbility to read + are enabled in UBIFS. Removing compressors means inability to read existing file systems. If unsure, say 'N'. @@ -32,7 +32,7 @@ config UBIFS_FS_LZO depends on UBIFS_FS default y help - LZO compressor is generally faster then zlib but compresses worse. + LZO compressor is generally faster than zlib but compresses worse. Say 'Y' if unsure. config UBIFS_FS_ZLIB diff --git a/include/asm-frv/ftrace.h b/include/asm-frv/ftrace.h new file mode 100644 index 000000000000..40a8c178f10d --- /dev/null +++ b/include/asm-frv/ftrace.h @@ -0,0 +1 @@ +/* empty */ diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index a654d724d3b0..7fa660fd449c 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -61,6 +61,30 @@ #define BRANCH_PROFILE() #endif +#ifdef CONFIG_EVENT_TRACER +#define FTRACE_EVENTS() VMLINUX_SYMBOL(__start_ftrace_events) = .; \ + *(_ftrace_events) \ + VMLINUX_SYMBOL(__stop_ftrace_events) = .; +#else +#define FTRACE_EVENTS() +#endif + +#ifdef CONFIG_TRACING +#define TRACE_PRINTKS() VMLINUX_SYMBOL(__start___trace_bprintk_fmt) = .; \ + *(__trace_printk_fmt) /* Trace_printk fmt' pointer */ \ + VMLINUX_SYMBOL(__stop___trace_bprintk_fmt) = .; +#else +#define TRACE_PRINTKS() +#endif + +#ifdef CONFIG_FTRACE_SYSCALLS +#define TRACE_SYSCALLS() VMLINUX_SYMBOL(__start_syscalls_metadata) = .; \ + *(__syscalls_metadata) \ + VMLINUX_SYMBOL(__stop_syscalls_metadata) = .; +#else +#define TRACE_SYSCALLS() +#endif + /* .data section */ #define DATA_DATA \ *(.data) \ @@ -86,7 +110,10 @@ *(__verbose) \ VMLINUX_SYMBOL(__stop___verbose) = .; \ LIKELY_PROFILE() \ - BRANCH_PROFILE() + BRANCH_PROFILE() \ + TRACE_PRINTKS() \ + FTRACE_EVENTS() \ + TRACE_SYSCALLS() #define RO_DATA(align) \ . = ALIGN((align)); \ diff --git a/include/asm-m32r/ftrace.h b/include/asm-m32r/ftrace.h new file mode 100644 index 000000000000..40a8c178f10d --- /dev/null +++ b/include/asm-m32r/ftrace.h @@ -0,0 +1 @@ +/* empty */ diff --git a/include/asm-mn10300/ftrace.h b/include/asm-mn10300/ftrace.h new file mode 100644 index 000000000000..40a8c178f10d --- /dev/null +++ b/include/asm-mn10300/ftrace.h @@ -0,0 +1 @@ +/* empty */ diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h index 45f6297821bd..5fc2ef8d97fa 100644 --- a/include/linux/async_tx.h +++ b/include/linux/async_tx.h @@ -21,6 +21,15 @@ #include <linux/spinlock.h> #include <linux/interrupt.h> +/* on architectures without dma-mapping capabilities we need to ensure + * that the asynchronous path compiles away + */ +#ifdef CONFIG_HAS_DMA +#define __async_inline +#else +#define __async_inline __always_inline +#endif + /** * dma_chan_ref - object used to manage dma channels received from the * dmaengine core. diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 6e915878e88c..d960889e92ef 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -144,6 +144,9 @@ struct blk_user_trace_setup { #ifdef __KERNEL__ #if defined(CONFIG_BLK_DEV_IO_TRACE) + +#include <linux/sysfs.h> + struct blk_trace { int trace_state; struct rchan *rchan; @@ -194,6 +197,8 @@ extern int blk_trace_setup(struct request_queue *q, char *name, dev_t dev, extern int blk_trace_startstop(struct request_queue *q, int start); extern int blk_trace_remove(struct request_queue *q); +extern struct attribute_group blk_trace_attr_group; + #else /* !CONFIG_BLK_DEV_IO_TRACE */ #define blk_trace_ioctl(bdev, cmd, arg) (-ENOTTY) #define blk_trace_shutdown(q) do { } while (0) diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 4316a546beb5..665fa70e4094 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -365,7 +365,10 @@ int cgroup_task_count(const struct cgroup *cgrp); /* Return true if cgrp is a descendant of the task's cgroup */ int cgroup_is_descendant(const struct cgroup *cgrp, struct task_struct *task); -/* Control Group subsystem type. See Documentation/cgroups.txt for details */ +/* + * Control Group subsystem type. + * See Documentation/cgroups/cgroups.txt for details + */ struct cgroup_subsys { struct cgroup_subsys_state *(*create)(struct cgroup_subsys *ss, diff --git a/include/linux/compat.h b/include/linux/compat.h index 9723edd6455c..f2ded21f9a3c 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -193,10 +193,10 @@ asmlinkage ssize_t compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec, unsigned long vlen); asmlinkage ssize_t compat_sys_preadv(unsigned long fd, const struct compat_iovec __user *vec, - unsigned long vlen, u32 pos_high, u32 pos_low); + unsigned long vlen, u32 pos_low, u32 pos_high); asmlinkage ssize_t compat_sys_pwritev(unsigned long fd, const struct compat_iovec __user *vec, - unsigned long vlen, u32 pos_high, u32 pos_low); + unsigned long vlen, u32 pos_low, u32 pos_high); int compat_do_execve(char * filename, compat_uptr_t __user *argv, compat_uptr_t __user *envp, struct pt_regs * regs); diff --git a/include/linux/compiler.h b/include/linux/compiler.h index d95da1020f1c..6faa7e549de4 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -68,6 +68,7 @@ struct ftrace_branch_data { unsigned long miss; unsigned long hit; }; + unsigned long miss_hit[2]; }; }; @@ -125,10 +126,7 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); .line = __LINE__, \ }; \ ______r = !!(cond); \ - if (______r) \ - ______f.hit++; \ - else \ - ______f.miss++; \ + ______f.miss_hit[______r]++; \ ______r; \ })) #endif /* CONFIG_PROFILE_ALL_BRANCHES */ diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index af0e01d4c663..eb5c2ba2f81a 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -71,6 +71,9 @@ struct dentry *debugfs_create_bool(const char *name, mode_t mode, struct dentry *debugfs_create_blob(const char *name, mode_t mode, struct dentry *parent, struct debugfs_blob_wrapper *blob); + +bool debugfs_initialized(void); + #else #include <linux/err.h> @@ -183,6 +186,11 @@ static inline struct dentry *debugfs_create_blob(const char *name, mode_t mode, return ERR_PTR(-ENODEV); } +static inline bool debugfs_initialized(void) +{ + return false; +} + #endif #endif diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 1956c8d46d32..2e2aa3df170c 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -23,9 +23,6 @@ #include <linux/device.h> #include <linux/uio.h> -#include <linux/kref.h> -#include <linux/completion.h> -#include <linux/rcupdate.h> #include <linux/dma-mapping.h> /** @@ -205,6 +202,7 @@ struct dma_async_tx_descriptor { /** * struct dma_device - info on the entity supplying DMA services * @chancnt: how many DMA channels are supported + * @privatecnt: how many DMA channels are requested by dma_request_channel * @channels: the list of struct dma_chan * @global_node: list_head for global dma_device_list * @cap_mask: one or more dma_capability flags @@ -227,6 +225,7 @@ struct dma_async_tx_descriptor { struct dma_device { unsigned int chancnt; + unsigned int privatecnt; struct list_head channels; struct list_head global_node; dma_cap_mask_t cap_mask; @@ -291,6 +290,24 @@ static inline void net_dmaengine_put(void) } #endif +#ifdef CONFIG_ASYNC_TX_DMA +#define async_dmaengine_get() dmaengine_get() +#define async_dmaengine_put() dmaengine_put() +#define async_dma_find_channel(type) dma_find_channel(type) +#else +static inline void async_dmaengine_get(void) +{ +} +static inline void async_dmaengine_put(void) +{ +} +static inline struct dma_chan * +async_dma_find_channel(enum dma_transaction_type type) +{ + return NULL; +} +#endif + dma_cookie_t dma_async_memcpy_buf_to_buf(struct dma_chan *chan, void *dest, void *src, size_t len); dma_cookie_t dma_async_memcpy_buf_to_pg(struct dma_chan *chan, @@ -337,6 +354,13 @@ __dma_cap_set(enum dma_transaction_type tx_type, dma_cap_mask_t *dstp) set_bit(tx_type, dstp->bits); } +#define dma_cap_clear(tx, mask) __dma_cap_clear((tx), &(mask)) +static inline void +__dma_cap_clear(enum dma_transaction_type tx_type, dma_cap_mask_t *dstp) +{ + clear_bit(tx_type, dstp->bits); +} + #define dma_cap_zero(mask) __dma_cap_zero(&(mask)) static inline void __dma_cap_zero(dma_cap_mask_t *dstp) { diff --git a/include/linux/dw_dmac.h b/include/linux/dw_dmac.h index d797dde247f7..c8aad713a046 100644 --- a/include/linux/dw_dmac.h +++ b/include/linux/dw_dmac.h @@ -74,4 +74,23 @@ struct dw_dma_slave { #define DWC_CFGL_HS_DST_POL (1 << 18) /* dst handshake active low */ #define DWC_CFGL_HS_SRC_POL (1 << 19) /* src handshake active low */ +/* DMA API extensions */ +struct dw_cyclic_desc { + struct dw_desc **desc; + unsigned long periods; + void (*period_callback)(void *param); + void *period_callback_param; +}; + +struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan, + dma_addr_t buf_addr, size_t buf_len, size_t period_len, + enum dma_data_direction direction); +void dw_dma_cyclic_free(struct dma_chan *chan); +int dw_dma_cyclic_start(struct dma_chan *chan); +void dw_dma_cyclic_stop(struct dma_chan *chan); + +dma_addr_t dw_dma_get_src_addr(struct dma_chan *chan); + +dma_addr_t dw_dma_get_dst_addr(struct dma_chan *chan); + #endif /* DW_DMAC_H */ diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index a7f8134c594e..015a3d22cf74 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -1,15 +1,18 @@ #ifndef _LINUX_FTRACE_H #define _LINUX_FTRACE_H -#include <linux/linkage.h> -#include <linux/fs.h> -#include <linux/ktime.h> -#include <linux/init.h> -#include <linux/types.h> -#include <linux/module.h> +#include <linux/trace_clock.h> #include <linux/kallsyms.h> +#include <linux/linkage.h> #include <linux/bitops.h> +#include <linux/module.h> +#include <linux/ktime.h> #include <linux/sched.h> +#include <linux/types.h> +#include <linux/init.h> +#include <linux/fs.h> + +#include <asm/ftrace.h> #ifdef CONFIG_FUNCTION_TRACER @@ -95,9 +98,41 @@ stack_trace_sysctl(struct ctl_table *table, int write, loff_t *ppos); #endif +struct ftrace_func_command { + struct list_head list; + char *name; + int (*func)(char *func, char *cmd, + char *params, int enable); +}; + #ifdef CONFIG_DYNAMIC_FTRACE -/* asm/ftrace.h must be defined for archs supporting dynamic ftrace */ -#include <asm/ftrace.h> + +int ftrace_arch_code_modify_prepare(void); +int ftrace_arch_code_modify_post_process(void); + +struct seq_file; + +struct ftrace_probe_ops { + void (*func)(unsigned long ip, + unsigned long parent_ip, + void **data); + int (*callback)(unsigned long ip, void **data); + void (*free)(void **data); + int (*print)(struct seq_file *m, + unsigned long ip, + struct ftrace_probe_ops *ops, + void *data); +}; + +extern int +register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, + void *data); +extern void +unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, + void *data); +extern void +unregister_ftrace_function_probe_func(char *glob, struct ftrace_probe_ops *ops); +extern void unregister_ftrace_function_probe_all(char *glob); enum { FTRACE_FL_FREE = (1 << 0), @@ -110,15 +145,23 @@ enum { }; struct dyn_ftrace { - struct list_head list; - unsigned long ip; /* address of mcount call-site */ - unsigned long flags; - struct dyn_arch_ftrace arch; + union { + unsigned long ip; /* address of mcount call-site */ + struct dyn_ftrace *freelist; + }; + union { + unsigned long flags; + struct dyn_ftrace *newlist; + }; + struct dyn_arch_ftrace arch; }; int ftrace_force_update(void); void ftrace_set_filter(unsigned char *buf, int len, int reset); +int register_ftrace_command(struct ftrace_func_command *cmd); +int unregister_ftrace_command(struct ftrace_func_command *cmd); + /* defined in arch */ extern int ftrace_ip_converted(unsigned long ip); extern int ftrace_dyn_arch_init(void *data); @@ -126,6 +169,10 @@ extern int ftrace_update_ftrace_func(ftrace_func_t func); extern void ftrace_caller(void); extern void ftrace_call(void); extern void mcount_call(void); + +#ifndef FTRACE_ADDR +#define FTRACE_ADDR ((unsigned long)ftrace_caller) +#endif #ifdef CONFIG_FUNCTION_GRAPH_TRACER extern void ftrace_graph_caller(void); extern int ftrace_enable_ftrace_graph_caller(void); @@ -136,7 +183,7 @@ static inline int ftrace_disable_ftrace_graph_caller(void) { return 0; } #endif /** - * ftrace_make_nop - convert code into top + * ftrace_make_nop - convert code into nop * @mod: module structure if called by module load initialization * @rec: the mcount call site record * @addr: the address that the call site should be calling @@ -181,7 +228,6 @@ extern int ftrace_make_nop(struct module *mod, */ extern int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr); - /* May be defined in arch */ extern int ftrace_arch_read_dyn_info(char *buf, int size); @@ -198,6 +244,14 @@ extern void ftrace_enable_daemon(void); # define ftrace_disable_daemon() do { } while (0) # define ftrace_enable_daemon() do { } while (0) static inline void ftrace_release(void *start, unsigned long size) { } +static inline int register_ftrace_command(struct ftrace_func_command *cmd) +{ + return -EINVAL; +} +static inline int unregister_ftrace_command(char *cmd_name) +{ + return -EINVAL; +} #endif /* CONFIG_DYNAMIC_FTRACE */ /* totally disable ftrace - can not re-enable after this */ @@ -233,24 +287,25 @@ static inline void __ftrace_enabled_restore(int enabled) #endif } -#ifdef CONFIG_FRAME_POINTER -/* TODO: need to fix this for ARM */ -# define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0)) -# define CALLER_ADDR1 ((unsigned long)__builtin_return_address(1)) -# define CALLER_ADDR2 ((unsigned long)__builtin_return_address(2)) -# define CALLER_ADDR3 ((unsigned long)__builtin_return_address(3)) -# define CALLER_ADDR4 ((unsigned long)__builtin_return_address(4)) -# define CALLER_ADDR5 ((unsigned long)__builtin_return_address(5)) -# define CALLER_ADDR6 ((unsigned long)__builtin_return_address(6)) -#else -# define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0)) -# define CALLER_ADDR1 0UL -# define CALLER_ADDR2 0UL -# define CALLER_ADDR3 0UL -# define CALLER_ADDR4 0UL -# define CALLER_ADDR5 0UL -# define CALLER_ADDR6 0UL -#endif +#ifndef HAVE_ARCH_CALLER_ADDR +# ifdef CONFIG_FRAME_POINTER +# define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0)) +# define CALLER_ADDR1 ((unsigned long)__builtin_return_address(1)) +# define CALLER_ADDR2 ((unsigned long)__builtin_return_address(2)) +# define CALLER_ADDR3 ((unsigned long)__builtin_return_address(3)) +# define CALLER_ADDR4 ((unsigned long)__builtin_return_address(4)) +# define CALLER_ADDR5 ((unsigned long)__builtin_return_address(5)) +# define CALLER_ADDR6 ((unsigned long)__builtin_return_address(6)) +# else +# define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0)) +# define CALLER_ADDR1 0UL +# define CALLER_ADDR2 0UL +# define CALLER_ADDR3 0UL +# define CALLER_ADDR4 0UL +# define CALLER_ADDR5 0UL +# define CALLER_ADDR6 0UL +# endif +#endif /* ifndef HAVE_ARCH_CALLER_ADDR */ #ifdef CONFIG_IRQSOFF_TRACER extern void time_hardirqs_on(unsigned long a0, unsigned long a1); @@ -268,54 +323,6 @@ static inline void __ftrace_enabled_restore(int enabled) # define trace_preempt_off(a0, a1) do { } while (0) #endif -#ifdef CONFIG_TRACING -extern int ftrace_dump_on_oops; - -extern void tracing_start(void); -extern void tracing_stop(void); -extern void ftrace_off_permanent(void); - -extern void -ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3); - -/** - * ftrace_printk - printf formatting in the ftrace buffer - * @fmt: the printf format for printing - * - * Note: __ftrace_printk is an internal function for ftrace_printk and - * the @ip is passed in via the ftrace_printk macro. - * - * This function allows a kernel developer to debug fast path sections - * that printk is not appropriate for. By scattering in various - * printk like tracing in the code, a developer can quickly see - * where problems are occurring. - * - * This is intended as a debugging tool for the developer only. - * Please refrain from leaving ftrace_printks scattered around in - * your code. - */ -# define ftrace_printk(fmt...) __ftrace_printk(_THIS_IP_, fmt) -extern int -__ftrace_printk(unsigned long ip, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); -extern void ftrace_dump(void); -#else -static inline void -ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { } -static inline int -ftrace_printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 2))); - -static inline void tracing_start(void) { } -static inline void tracing_stop(void) { } -static inline void ftrace_off_permanent(void) { } -static inline int -ftrace_printk(const char *fmt, ...) -{ - return 0; -} -static inline void ftrace_dump(void) { } -#endif - #ifdef CONFIG_FTRACE_MCOUNT_RECORD extern void ftrace_init(void); extern void ftrace_init_module(struct module *mod, @@ -327,36 +334,6 @@ ftrace_init_module(struct module *mod, unsigned long *start, unsigned long *end) { } #endif -enum { - POWER_NONE = 0, - POWER_CSTATE = 1, - POWER_PSTATE = 2, -}; - -struct power_trace { -#ifdef CONFIG_POWER_TRACER - ktime_t stamp; - ktime_t end; - int type; - int state; -#endif -}; - -#ifdef CONFIG_POWER_TRACER -extern void trace_power_start(struct power_trace *it, unsigned int type, - unsigned int state); -extern void trace_power_mark(struct power_trace *it, unsigned int type, - unsigned int state); -extern void trace_power_end(struct power_trace *it); -#else -static inline void trace_power_start(struct power_trace *it, unsigned int type, - unsigned int state) { } -static inline void trace_power_mark(struct power_trace *it, unsigned int type, - unsigned int state) { } -static inline void trace_power_end(struct power_trace *it) { } -#endif - - /* * Structure that defines an entry function trace. */ @@ -398,8 +375,7 @@ struct ftrace_ret_stack { extern void return_to_handler(void); extern int -ftrace_push_return_trace(unsigned long ret, unsigned long long time, - unsigned long func, int *depth); +ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth); extern void ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret); @@ -514,6 +490,50 @@ static inline int test_tsk_trace_graph(struct task_struct *tsk) return tsk->trace & TSK_TRACE_FL_GRAPH; } +extern int ftrace_dump_on_oops; + #endif /* CONFIG_TRACING */ + +#ifdef CONFIG_HW_BRANCH_TRACER + +void trace_hw_branch(u64 from, u64 to); +void trace_hw_branch_oops(void); + +#else /* CONFIG_HW_BRANCH_TRACER */ + +static inline void trace_hw_branch(u64 from, u64 to) {} +static inline void trace_hw_branch_oops(void) {} + +#endif /* CONFIG_HW_BRANCH_TRACER */ + +/* + * A syscall entry in the ftrace syscalls array. + * + * @name: name of the syscall + * @nb_args: number of parameters it takes + * @types: list of types as strings + * @args: list of args as strings (args[i] matches types[i]) + */ +struct syscall_metadata { + const char *name; + int nb_args; + const char **types; + const char **args; +}; + +#ifdef CONFIG_FTRACE_SYSCALLS +extern void arch_init_ftrace_syscalls(void); +extern struct syscall_metadata *syscall_nr_to_meta(int nr); +extern void start_ftrace_syscalls(void); +extern void stop_ftrace_syscalls(void); +extern void ftrace_syscall_enter(struct pt_regs *regs); +extern void ftrace_syscall_exit(struct pt_regs *regs); +#else +static inline void start_ftrace_syscalls(void) { } +static inline void stop_ftrace_syscalls(void) { } +static inline void ftrace_syscall_enter(struct pt_regs *regs) { } +static inline void ftrace_syscall_exit(struct pt_regs *regs) { } +#endif + #endif /* _LINUX_FTRACE_H */ diff --git a/include/linux/ftrace_irq.h b/include/linux/ftrace_irq.h index 366a054d0b05..dca7bf8cffe2 100644 --- a/include/linux/ftrace_irq.h +++ b/include/linux/ftrace_irq.h @@ -2,7 +2,7 @@ #define _LINUX_FTRACE_IRQ_H -#if defined(CONFIG_DYNAMIC_FTRACE) || defined(CONFIG_FUNCTION_GRAPH_TRACER) +#ifdef CONFIG_FTRACE_NMI_ENTER extern void ftrace_nmi_enter(void); extern void ftrace_nmi_exit(void); #else diff --git a/include/linux/gfp.h b/include/linux/gfp.h index dd20cd78faa8..0bbc15f54536 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -4,6 +4,7 @@ #include <linux/mmzone.h> #include <linux/stddef.h> #include <linux/linkage.h> +#include <linux/topology.h> struct vm_area_struct; diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index f83288347dda..faa1cf848bcd 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -15,55 +15,61 @@ * - bits 0-7 are the preemption count (max preemption depth: 256) * - bits 8-15 are the softirq count (max # of softirqs: 256) * - * The hardirq count can be overridden per architecture, the default is: + * The hardirq count can in theory reach the same as NR_IRQS. + * In reality, the number of nested IRQS is limited to the stack + * size as well. For archs with over 1000 IRQS it is not practical + * to expect that they will all nest. We give a max of 10 bits for + * hardirq nesting. An arch may choose to give less than 10 bits. + * m68k expects it to be 8. * - * - bits 16-27 are the hardirq count (max # of hardirqs: 4096) - * - ( bit 28 is the PREEMPT_ACTIVE flag. ) + * - bits 16-25 are the hardirq count (max # of nested hardirqs: 1024) + * - bit 26 is the NMI_MASK + * - bit 28 is the PREEMPT_ACTIVE flag * * PREEMPT_MASK: 0x000000ff * SOFTIRQ_MASK: 0x0000ff00 - * HARDIRQ_MASK: 0x0fff0000 + * HARDIRQ_MASK: 0x03ff0000 + * NMI_MASK: 0x04000000 */ #define PREEMPT_BITS 8 #define SOFTIRQ_BITS 8 +#define NMI_BITS 1 -#ifndef HARDIRQ_BITS -#define HARDIRQ_BITS 12 +#define MAX_HARDIRQ_BITS 10 -#ifndef MAX_HARDIRQS_PER_CPU -#define MAX_HARDIRQS_PER_CPU NR_IRQS +#ifndef HARDIRQ_BITS +# define HARDIRQ_BITS MAX_HARDIRQ_BITS #endif -/* - * The hardirq mask has to be large enough to have space for potentially - * all IRQ sources in the system nesting on a single CPU. - */ -#if (1 << HARDIRQ_BITS) < MAX_HARDIRQS_PER_CPU -# error HARDIRQ_BITS is too low! -#endif +#if HARDIRQ_BITS > MAX_HARDIRQ_BITS +#error HARDIRQ_BITS too high! #endif #define PREEMPT_SHIFT 0 #define SOFTIRQ_SHIFT (PREEMPT_SHIFT + PREEMPT_BITS) #define HARDIRQ_SHIFT (SOFTIRQ_SHIFT + SOFTIRQ_BITS) +#define NMI_SHIFT (HARDIRQ_SHIFT + HARDIRQ_BITS) #define __IRQ_MASK(x) ((1UL << (x))-1) #define PREEMPT_MASK (__IRQ_MASK(PREEMPT_BITS) << PREEMPT_SHIFT) #define SOFTIRQ_MASK (__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT) #define HARDIRQ_MASK (__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT) +#define NMI_MASK (__IRQ_MASK(NMI_BITS) << NMI_SHIFT) #define PREEMPT_OFFSET (1UL << PREEMPT_SHIFT) #define SOFTIRQ_OFFSET (1UL << SOFTIRQ_SHIFT) #define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT) +#define NMI_OFFSET (1UL << NMI_SHIFT) -#if PREEMPT_ACTIVE < (1 << (HARDIRQ_SHIFT + HARDIRQ_BITS)) +#if PREEMPT_ACTIVE < (1 << (NMI_SHIFT + NMI_BITS)) #error PREEMPT_ACTIVE is too low! #endif #define hardirq_count() (preempt_count() & HARDIRQ_MASK) #define softirq_count() (preempt_count() & SOFTIRQ_MASK) -#define irq_count() (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK)) +#define irq_count() (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \ + | NMI_MASK)) /* * Are we doing bottom half or hardware interrupt processing? @@ -73,6 +79,11 @@ #define in_softirq() (softirq_count()) #define in_interrupt() (irq_count()) +/* + * Are we in NMI context? + */ +#define in_nmi() (preempt_count() & NMI_MASK) + #if defined(CONFIG_PREEMPT) # define PREEMPT_INATOMIC_BASE kernel_locked() # define PREEMPT_CHECK_OFFSET 1 @@ -164,20 +175,24 @@ extern void irq_enter(void); */ extern void irq_exit(void); -#define nmi_enter() \ - do { \ - ftrace_nmi_enter(); \ - lockdep_off(); \ - rcu_nmi_enter(); \ - __irq_enter(); \ +#define nmi_enter() \ + do { \ + ftrace_nmi_enter(); \ + BUG_ON(in_nmi()); \ + add_preempt_count(NMI_OFFSET + HARDIRQ_OFFSET); \ + lockdep_off(); \ + rcu_nmi_enter(); \ + trace_hardirq_enter(); \ } while (0) -#define nmi_exit() \ - do { \ - __irq_exit(); \ - rcu_nmi_exit(); \ - lockdep_on(); \ - ftrace_nmi_exit(); \ +#define nmi_exit() \ + do { \ + trace_hardirq_exit(); \ + rcu_nmi_exit(); \ + lockdep_on(); \ + BUG_ON(!in_nmi()); \ + sub_preempt_count(NMI_OFFSET + HARDIRQ_OFFSET); \ + ftrace_nmi_exit(); \ } while (0) #endif /* LINUX_HARDIRQ_H */ diff --git a/include/linux/hid.h b/include/linux/hid.h index fa8ee9cef7be..a72876e43589 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -270,6 +270,7 @@ struct hid_item { #define HID_QUIRK_INVERT 0x00000001 #define HID_QUIRK_NOTOUCH 0x00000002 +#define HID_QUIRK_IGNORE 0x00000004 #define HID_QUIRK_NOGET 0x00000008 #define HID_QUIRK_BADPAD 0x00000020 #define HID_QUIRK_MULTI_INPUT 0x00000040 @@ -603,12 +604,17 @@ struct hid_ll_driver { int (*open)(struct hid_device *hdev); void (*close)(struct hid_device *hdev); + int (*power)(struct hid_device *hdev, int level); + int (*hidinput_input_event) (struct input_dev *idev, unsigned int type, unsigned int code, int value); int (*parse)(struct hid_device *hdev); }; +#define PM_HINT_FULLON 1<<5 +#define PM_HINT_NORMAL 1<<1 + /* Applications from HID Usage Tables 4/8/99 Version 1.1 */ /* We ignore a few input applications that are not widely used */ #define IS_INPUT_APPLICATION(a) (((a >= 0x00010000) && (a <= 0x00010008)) || (a == 0x00010080) || (a == 0x000c0001) || (a == 0x000d0002)) @@ -641,6 +647,7 @@ int hidinput_find_field(struct hid_device *hid, unsigned int type, unsigned int void hid_output_report(struct hid_report *report, __u8 *data); struct hid_device *hid_allocate_device(void); int hid_parse_report(struct hid_device *hid, __u8 *start, unsigned size); +int hid_check_keys_pressed(struct hid_device *hid); int hid_connect(struct hid_device *hid, unsigned int connect_mask); /** @@ -791,21 +798,5 @@ dbg_hid(const char *fmt, ...) __FILE__ , ## arg) #endif /* HID_FF */ -#ifdef __KERNEL__ -#ifdef CONFIG_HID_COMPAT -#define HID_COMPAT_LOAD_DRIVER(name) \ -/* prototype to avoid sparse warning */ \ -extern void hid_compat_##name(void); \ -void hid_compat_##name(void) { } \ -EXPORT_SYMBOL(hid_compat_##name) -#else -#define HID_COMPAT_LOAD_DRIVER(name) -#endif /* HID_COMPAT */ -#define HID_COMPAT_CALL_DRIVER(name) do { \ - extern void hid_compat_##name(void); \ - hid_compat_##name(); \ -} while (0) -#endif /* __KERNEL__ */ - #endif diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index c68bffd182bb..ce2c07d99fc3 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -278,6 +278,11 @@ enum NR_SOFTIRQS }; +/* map softirq index to softirq name. update 'softirq_to_name' in + * kernel/softirq.c when adding a new softirq. + */ +extern char *softirq_to_name[NR_SOFTIRQS]; + /* softirq mask and active fields moved to irq_cpustat_t in * asm/hardirq.h to get better cache usage. KAO */ diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 74bde13224c9..b02a3f1d46a0 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -24,8 +24,8 @@ # define trace_softirqs_enabled(p) ((p)->softirqs_enabled) # define trace_hardirq_enter() do { current->hardirq_context++; } while (0) # define trace_hardirq_exit() do { current->hardirq_context--; } while (0) -# define trace_softirq_enter() do { current->softirq_context++; } while (0) -# define trace_softirq_exit() do { current->softirq_context--; } while (0) +# define lockdep_softirq_enter() do { current->softirq_context++; } while (0) +# define lockdep_softirq_exit() do { current->softirq_context--; } while (0) # define INIT_TRACE_IRQFLAGS .softirqs_enabled = 1, #else # define trace_hardirqs_on() do { } while (0) @@ -38,8 +38,8 @@ # define trace_softirqs_enabled(p) 0 # define trace_hardirq_enter() do { } while (0) # define trace_hardirq_exit() do { } while (0) -# define trace_softirq_enter() do { } while (0) -# define trace_softirq_exit() do { } while (0) +# define lockdep_softirq_enter() do { } while (0) +# define lockdep_softirq_exit() do { } while (0) # define INIT_TRACE_IRQFLAGS #endif diff --git a/include/linux/jbd.h b/include/linux/jbd.h index 2c6943152c21..53ae4399da2d 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -35,7 +35,7 @@ #define journal_oom_retry 1 /* - * Define JBD_PARANIOD_IOFAIL to cause a kernel BUG() if ext3 finds + * Define JBD_PARANOID_IOFAIL to cause a kernel BUG() if ext3 finds * certain classes of error which can occur due to failed IOs. Under * normal use we want ext3 to continue after such errors, because * hardware _can_ fail, but for debugging purposes when running tests on diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index f3fe34391d8e..792274269f2b 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -13,10 +13,17 @@ #define KSYM_SYMBOL_LEN (sizeof("%s+%#lx/%#lx [%s]") + (KSYM_NAME_LEN - 1) + \ 2*(BITS_PER_LONG*3/10) + (MODULE_NAME_LEN - 1) + 1) +struct module; + #ifdef CONFIG_KALLSYMS /* Lookup the address for a symbol. Returns 0 if not found. */ unsigned long kallsyms_lookup_name(const char *name); +/* Call a function on each kallsyms symbol in the core kernel */ +int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, + unsigned long), + void *data); + extern int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize, unsigned long *offset); @@ -43,6 +50,14 @@ static inline unsigned long kallsyms_lookup_name(const char *name) return 0; } +static inline int kallsyms_on_each_symbol(int (*fn)(void *, const char *, + struct module *, + unsigned long), + void *data) +{ + return 0; +} + static inline int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize, unsigned long *offset) diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 556d781e69fe..d9e75ec7def5 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -242,6 +242,19 @@ extern struct ratelimit_state printk_ratelimit_state; extern int printk_ratelimit(void); extern bool printk_timed_ratelimit(unsigned long *caller_jiffies, unsigned int interval_msec); + +/* + * Print a one-time message (analogous to WARN_ONCE() et al): + */ +#define printk_once(x...) ({ \ + static int __print_once = 1; \ + \ + if (__print_once) { \ + __print_once = 0; \ + printk(x); \ + } \ +}) + void log_buf_kexec_setup(void); #else static inline int vprintk(const char *s, va_list args) @@ -254,6 +267,10 @@ static inline int printk_ratelimit(void) { return 0; } static inline bool printk_timed_ratelimit(unsigned long *caller_jiffies, \ unsigned int interval_msec) \ { return false; } + +/* No effect, but we still get type checking even in the !PRINTK case: */ +#define printk_once(x...) printk(x) + static inline void log_buf_kexec_setup(void) { } @@ -375,6 +392,139 @@ static inline char *pack_hex_byte(char *buf, u8 byte) #endif /* + * General tracing related utility functions - trace_printk(), + * tracing_on/tracing_off and tracing_start()/tracing_stop + * + * Use tracing_on/tracing_off when you want to quickly turn on or off + * tracing. It simply enables or disables the recording of the trace events. + * This also corresponds to the user space debugfs/tracing/tracing_on + * file, which gives a means for the kernel and userspace to interact. + * Place a tracing_off() in the kernel where you want tracing to end. + * From user space, examine the trace, and then echo 1 > tracing_on + * to continue tracing. + * + * tracing_stop/tracing_start has slightly more overhead. It is used + * by things like suspend to ram where disabling the recording of the + * trace is not enough, but tracing must actually stop because things + * like calling smp_processor_id() may crash the system. + * + * Most likely, you want to use tracing_on/tracing_off. + */ +#ifdef CONFIG_RING_BUFFER +void tracing_on(void); +void tracing_off(void); +/* trace_off_permanent stops recording with no way to bring it back */ +void tracing_off_permanent(void); +int tracing_is_on(void); +#else +static inline void tracing_on(void) { } +static inline void tracing_off(void) { } +static inline void tracing_off_permanent(void) { } +static inline int tracing_is_on(void) { return 0; } +#endif +#ifdef CONFIG_TRACING +extern void tracing_start(void); +extern void tracing_stop(void); +extern void ftrace_off_permanent(void); + +extern void +ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3); + +static inline void __attribute__ ((format (printf, 1, 2))) +____trace_printk_check_format(const char *fmt, ...) +{ +} +#define __trace_printk_check_format(fmt, args...) \ +do { \ + if (0) \ + ____trace_printk_check_format(fmt, ##args); \ +} while (0) + +/** + * trace_printk - printf formatting in the ftrace buffer + * @fmt: the printf format for printing + * + * Note: __trace_printk is an internal function for trace_printk and + * the @ip is passed in via the trace_printk macro. + * + * This function allows a kernel developer to debug fast path sections + * that printk is not appropriate for. By scattering in various + * printk like tracing in the code, a developer can quickly see + * where problems are occurring. + * + * This is intended as a debugging tool for the developer only. + * Please refrain from leaving trace_printks scattered around in + * your code. + */ + +#define trace_printk(fmt, args...) \ +do { \ + __trace_printk_check_format(fmt, ##args); \ + if (__builtin_constant_p(fmt)) { \ + static const char *trace_printk_fmt \ + __attribute__((section("__trace_printk_fmt"))) = \ + __builtin_constant_p(fmt) ? fmt : NULL; \ + \ + __trace_bprintk(_THIS_IP_, trace_printk_fmt, ##args); \ + } else \ + __trace_printk(_THIS_IP_, fmt, ##args); \ +} while (0) + +extern int +__trace_bprintk(unsigned long ip, const char *fmt, ...) + __attribute__ ((format (printf, 2, 3))); + +extern int +__trace_printk(unsigned long ip, const char *fmt, ...) + __attribute__ ((format (printf, 2, 3))); + +/* + * The double __builtin_constant_p is because gcc will give us an error + * if we try to allocate the static variable to fmt if it is not a + * constant. Even with the outer if statement. + */ +#define ftrace_vprintk(fmt, vargs) \ +do { \ + if (__builtin_constant_p(fmt)) { \ + static const char *trace_printk_fmt \ + __attribute__((section("__trace_printk_fmt"))) = \ + __builtin_constant_p(fmt) ? fmt : NULL; \ + \ + __ftrace_vbprintk(_THIS_IP_, trace_printk_fmt, vargs); \ + } else \ + __ftrace_vprintk(_THIS_IP_, fmt, vargs); \ +} while (0) + +extern int +__ftrace_vbprintk(unsigned long ip, const char *fmt, va_list ap); + +extern int +__ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap); + +extern void ftrace_dump(void); +#else +static inline void +ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { } +static inline int +trace_printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 2))); + +static inline void tracing_start(void) { } +static inline void tracing_stop(void) { } +static inline void ftrace_off_permanent(void) { } +static inline int +trace_printk(const char *fmt, ...) +{ + return 0; +} +static inline int +ftrace_vprintk(const char *fmt, va_list ap) +{ + return 0; +} +static inline void ftrace_dump(void) { } +#endif /* CONFIG_TRACING */ + +/* * Display an IP address in readable format. */ diff --git a/include/linux/kmod.h b/include/linux/kmod.h index 92213a9194e1..d5fa565086d1 100644 --- a/include/linux/kmod.h +++ b/include/linux/kmod.h @@ -29,10 +29,15 @@ #ifdef CONFIG_MODULES /* modprobe exit status on success, -ve on error. Return value * usually useless though. */ -extern int request_module(const char * name, ...) __attribute__ ((format (printf, 1, 2))); -#define try_then_request_module(x, mod...) ((x) ?: (request_module(mod), (x))) +extern int __request_module(bool wait, const char *name, ...) \ + __attribute__((format(printf, 2, 3))); +#define request_module(mod...) __request_module(true, mod) +#define request_module_nowait(mod...) __request_module(false, mod) +#define try_then_request_module(x, mod...) \ + ((x) ?: (__request_module(false, mod), (x))) #else -static inline int request_module(const char * name, ...) { return -ENOSYS; } +static inline int request_module(const char *name, ...) { return -ENOSYS; } +static inline int request_module_nowait(const char *name, ...) { return -ENOSYS; } #define try_then_request_module(x, mod...) (x) #endif diff --git a/include/linux/libata.h b/include/linux/libata.h index 76262d83656b..b450a2628855 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -379,7 +379,7 @@ enum { ATA_HORKAGE_BRIDGE_OK = (1 << 10), /* no bridge limits */ ATA_HORKAGE_ATAPI_MOD16_DMA = (1 << 11), /* use ATAPI DMA for commands not multiple of 16 bytes */ - ATA_HORKAGE_FIRMWARE_WARN = (1 << 12), /* firwmare update warning */ + ATA_HORKAGE_FIRMWARE_WARN = (1 << 12), /* firmware update warning */ ATA_HORKAGE_1_5_GBPS = (1 << 13), /* force 1.5 Gbps */ /* DMA mask for user DMA control: User visible values; DO NOT diff --git a/include/linux/memory.h b/include/linux/memory.h index 42767d1a62e7..37fa19b34ef5 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -110,4 +110,10 @@ struct memory_accessor { off_t offset, size_t count); }; +/* + * Kernel text modification mutex, used for code patching. Users of this lock + * can sleep. + */ +extern struct mutex text_mutex; + #endif /* _LINUX_MEMORY_H_ */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 26ef24076b76..186ec6ab334d 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -764,12 +764,6 @@ extern int numa_zonelist_order_handler(struct ctl_table *, int, extern char numa_zonelist_order[]; #define NUMA_ZONELIST_ORDER_LEN 16 /* string buffer size */ -#include <linux/topology.h> -/* Returns the number of the current Node. */ -#ifndef numa_node_id -#define numa_node_id() (cpu_to_node(raw_smp_processor_id())) -#endif - #ifndef CONFIG_NEED_MULTIPLE_NODES extern struct pglist_data contig_page_data; diff --git a/include/linux/module.h b/include/linux/module.h index 145a75528cc1..627ac082e2a6 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -248,6 +248,10 @@ struct module const unsigned long *crcs; unsigned int num_syms; + /* Kernel parameters. */ + struct kernel_param *kp; + unsigned int num_kp; + /* GPL-only exported symbols. */ unsigned int num_gpl_syms; const struct kernel_symbol *gpl_syms; @@ -329,6 +333,11 @@ struct module unsigned int num_tracepoints; #endif +#ifdef CONFIG_TRACING + const char **trace_bprintk_fmt_start; + unsigned int num_trace_bprintk_fmt; +#endif + #ifdef CONFIG_MODULE_UNLOAD /* What modules depend on me? */ struct list_head modules_which_use_me; @@ -350,6 +359,8 @@ struct module #define MODULE_ARCH_INIT {} #endif +extern struct mutex module_mutex; + /* FIXME: It'd be nice to isolate modules during init, too, so they aren't used before they (may) fail. But presently too much code (IDE & SCSI) require entry into the module during init.*/ @@ -358,10 +369,10 @@ static inline int module_is_live(struct module *mod) return mod->state != MODULE_STATE_GOING; } -/* Is this address in a module? (second is with no locks, for oops) */ -struct module *module_text_address(unsigned long addr); struct module *__module_text_address(unsigned long addr); -int is_module_address(unsigned long addr); +struct module *__module_address(unsigned long addr); +bool is_module_address(unsigned long addr); +bool is_module_text_address(unsigned long addr); static inline int within_module_core(unsigned long addr, struct module *mod) { @@ -375,6 +386,31 @@ static inline int within_module_init(unsigned long addr, struct module *mod) addr < (unsigned long)mod->module_init + mod->init_size; } +/* Search for module by name: must hold module_mutex. */ +struct module *find_module(const char *name); + +struct symsearch { + const struct kernel_symbol *start, *stop; + const unsigned long *crcs; + enum { + NOT_GPL_ONLY, + GPL_ONLY, + WILL_BE_GPL_ONLY, + } licence; + bool unused; +}; + +/* Search for an exported symbol by name. */ +const struct kernel_symbol *find_symbol(const char *name, + struct module **owner, + const unsigned long **crc, + bool gplok, + bool warn); + +/* Walk the exported symbol table */ +bool each_symbol(bool (*fn)(const struct symsearch *arr, struct module *owner, + unsigned int symnum, void *data), void *data); + /* Returns 0 and fills in value, defined and namebuf, or -ERANGE if symnum out of range. */ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, @@ -383,6 +419,10 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, /* Look for this name: can be of form module:name. */ unsigned long module_kallsyms_lookup_name(const char *name); +int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, + struct module *, unsigned long), + void *data); + extern void __module_put_and_exit(struct module *mod, long code) __attribute__((noreturn)); #define module_put_and_exit(code) __module_put_and_exit(THIS_MODULE, code); @@ -444,6 +484,7 @@ static inline void __module_get(struct module *module) #define symbol_put_addr(p) do { } while(0) #endif /* CONFIG_MODULE_UNLOAD */ +int use_module(struct module *a, struct module *b); /* This is a #define so the string doesn't get put in every .o file */ #define module_name(mod) \ @@ -490,21 +531,24 @@ search_module_extables(unsigned long addr) return NULL; } -/* Is this address in a module? */ -static inline struct module *module_text_address(unsigned long addr) +static inline struct module *__module_address(unsigned long addr) { return NULL; } -/* Is this address in a module? (don't take a lock, we're oopsing) */ static inline struct module *__module_text_address(unsigned long addr) { return NULL; } -static inline int is_module_address(unsigned long addr) +static inline bool is_module_address(unsigned long addr) { - return 0; + return false; +} + +static inline bool is_module_text_address(unsigned long addr) +{ + return false; } /* Get/put a kernel symbol (calls should be symmetric) */ @@ -559,6 +603,14 @@ static inline unsigned long module_kallsyms_lookup_name(const char *name) return 0; } +static inline int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, + struct module *, + unsigned long), + void *data) +{ + return 0; +} + static inline int register_module_notifier(struct notifier_block * nb) { /* no events will happen anyway, so this can always succeed */ diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index e4af3399ef48..a4f0b931846c 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -138,6 +138,16 @@ extern int parse_args(const char *name, unsigned num, int (*unknown)(char *param, char *val)); +/* Called by module remove. */ +#ifdef CONFIG_SYSFS +extern void destroy_params(const struct kernel_param *params, unsigned num); +#else +static inline void destroy_params(const struct kernel_param *params, + unsigned num) +{ +} +#endif /* !CONFIG_SYSFS */ + /* All the helper functions */ /* The macros to do compile-time type checking stolen from Jakub Jelinek, who IIRC came up with this idea for the 2.4 module init code. */ diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 3945f803d514..7c775751392c 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -28,4 +28,4 @@ int pwm_enable(struct pwm_device *pwm); */ void pwm_disable(struct pwm_device *pwm); -#endif /* __ASM_ARCH_PWM_H */ +#endif /* __LINUX_PWM_H */ diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index b3b359660082..e1b7b2173885 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -8,7 +8,7 @@ struct ring_buffer; struct ring_buffer_iter; /* - * Don't reference this struct directly, use functions below. + * Don't refer to this struct directly, use functions below. */ struct ring_buffer_event { u32 type:2, len:3, time_delta:27; @@ -18,10 +18,13 @@ struct ring_buffer_event { /** * enum ring_buffer_type - internal ring buffer types * - * @RINGBUF_TYPE_PADDING: Left over page padding - * array is ignored - * size is variable depending on how much + * @RINGBUF_TYPE_PADDING: Left over page padding or discarded event + * If time_delta is 0: + * array is ignored + * size is variable depending on how much * padding is needed + * If time_delta is non zero: + * everything else same as RINGBUF_TYPE_DATA * * @RINGBUF_TYPE_TIME_EXTEND: Extend the time delta * array[0] = time delta (28 .. 59) @@ -65,6 +68,8 @@ ring_buffer_event_time_delta(struct ring_buffer_event *event) return event->time_delta; } +void ring_buffer_event_discard(struct ring_buffer_event *event); + /* * size is in bytes for each per CPU buffer. */ @@ -74,13 +79,10 @@ void ring_buffer_free(struct ring_buffer *buffer); int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size); -struct ring_buffer_event * -ring_buffer_lock_reserve(struct ring_buffer *buffer, - unsigned long length, - unsigned long *flags); +struct ring_buffer_event *ring_buffer_lock_reserve(struct ring_buffer *buffer, + unsigned long length); int ring_buffer_unlock_commit(struct ring_buffer *buffer, - struct ring_buffer_event *event, - unsigned long flags); + struct ring_buffer_event *event); int ring_buffer_write(struct ring_buffer *buffer, unsigned long length, void *data); @@ -121,17 +123,19 @@ unsigned long ring_buffer_overruns(struct ring_buffer *buffer); unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu); unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu); -u64 ring_buffer_time_stamp(int cpu); -void ring_buffer_normalize_time_stamp(int cpu, u64 *ts); +u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu); +void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer, + int cpu, u64 *ts); +void ring_buffer_set_clock(struct ring_buffer *buffer, + u64 (*clock)(void)); + +size_t ring_buffer_page_len(void *page); -void tracing_on(void); -void tracing_off(void); -void tracing_off_permanent(void); void *ring_buffer_alloc_read_page(struct ring_buffer *buffer); void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data); -int ring_buffer_read_page(struct ring_buffer *buffer, - void **data_page, int cpu, int full); +int ring_buffer_read_page(struct ring_buffer *buffer, void **data_page, + size_t len, int cpu, int full); enum ring_buffer_flags { RB_FL_OVERWRITE = 1 << 0, diff --git a/include/linux/sched.h b/include/linux/sched.h index 9da5aa0771ef..b94f3541f67b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -138,6 +138,8 @@ extern unsigned long nr_uninterruptible(void); extern unsigned long nr_active(void); extern unsigned long nr_iowait(void); +extern unsigned long get_parent_ip(unsigned long addr); + struct seq_file; struct cfs_rq; struct task_group; @@ -1405,6 +1407,8 @@ struct task_struct { int curr_ret_stack; /* Stack of return addresses for return function tracing */ struct ftrace_ret_stack *ret_stack; + /* time stamp for last schedule */ + unsigned long long ftrace_timestamp; /* * Number of functions that haven't been traced * because of depth overrun. diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index 6ca6a7b66d75..f4523651fa42 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -14,6 +14,7 @@ #include <asm/page.h> /* kmalloc_sizes.h needs PAGE_SIZE */ #include <asm/cache.h> /* kmalloc_sizes.h needs L1_CACHE_BYTES */ #include <linux/compiler.h> +#include <trace/kmemtrace.h> /* Size description struct for general caches. */ struct cache_sizes { @@ -28,8 +29,26 @@ extern struct cache_sizes malloc_sizes[]; void *kmem_cache_alloc(struct kmem_cache *, gfp_t); void *__kmalloc(size_t size, gfp_t flags); -static inline void *kmalloc(size_t size, gfp_t flags) +#ifdef CONFIG_KMEMTRACE +extern void *kmem_cache_alloc_notrace(struct kmem_cache *cachep, gfp_t flags); +extern size_t slab_buffer_size(struct kmem_cache *cachep); +#else +static __always_inline void * +kmem_cache_alloc_notrace(struct kmem_cache *cachep, gfp_t flags) { + return kmem_cache_alloc(cachep, flags); +} +static inline size_t slab_buffer_size(struct kmem_cache *cachep) +{ + return 0; +} +#endif + +static __always_inline void *kmalloc(size_t size, gfp_t flags) +{ + struct kmem_cache *cachep; + void *ret; + if (__builtin_constant_p(size)) { int i = 0; @@ -47,10 +66,17 @@ static inline void *kmalloc(size_t size, gfp_t flags) found: #ifdef CONFIG_ZONE_DMA if (flags & GFP_DMA) - return kmem_cache_alloc(malloc_sizes[i].cs_dmacachep, - flags); + cachep = malloc_sizes[i].cs_dmacachep; + else #endif - return kmem_cache_alloc(malloc_sizes[i].cs_cachep, flags); + cachep = malloc_sizes[i].cs_cachep; + + ret = kmem_cache_alloc_notrace(cachep, flags); + + kmemtrace_mark_alloc(KMEMTRACE_TYPE_KMALLOC, _THIS_IP_, ret, + size, slab_buffer_size(cachep), flags); + + return ret; } return __kmalloc(size, flags); } @@ -59,8 +85,25 @@ found: extern void *__kmalloc_node(size_t size, gfp_t flags, int node); extern void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node); -static inline void *kmalloc_node(size_t size, gfp_t flags, int node) +#ifdef CONFIG_KMEMTRACE +extern void *kmem_cache_alloc_node_notrace(struct kmem_cache *cachep, + gfp_t flags, + int nodeid); +#else +static __always_inline void * +kmem_cache_alloc_node_notrace(struct kmem_cache *cachep, + gfp_t flags, + int nodeid) +{ + return kmem_cache_alloc_node(cachep, flags, nodeid); +} +#endif + +static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) { + struct kmem_cache *cachep; + void *ret; + if (__builtin_constant_p(size)) { int i = 0; @@ -78,11 +121,18 @@ static inline void *kmalloc_node(size_t size, gfp_t flags, int node) found: #ifdef CONFIG_ZONE_DMA if (flags & GFP_DMA) - return kmem_cache_alloc_node(malloc_sizes[i].cs_dmacachep, - flags, node); + cachep = malloc_sizes[i].cs_dmacachep; + else #endif - return kmem_cache_alloc_node(malloc_sizes[i].cs_cachep, - flags, node); + cachep = malloc_sizes[i].cs_cachep; + + ret = kmem_cache_alloc_node_notrace(cachep, flags, node); + + kmemtrace_mark_alloc_node(KMEMTRACE_TYPE_KMALLOC, _THIS_IP_, + ret, size, slab_buffer_size(cachep), + flags, node); + + return ret; } return __kmalloc_node(size, flags, node); } diff --git a/include/linux/slob_def.h b/include/linux/slob_def.h index 59a3fa476ab9..0ec00b39d006 100644 --- a/include/linux/slob_def.h +++ b/include/linux/slob_def.h @@ -3,14 +3,15 @@ void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node); -static inline void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags) +static __always_inline void *kmem_cache_alloc(struct kmem_cache *cachep, + gfp_t flags) { return kmem_cache_alloc_node(cachep, flags, -1); } void *__kmalloc_node(size_t size, gfp_t flags, int node); -static inline void *kmalloc_node(size_t size, gfp_t flags, int node) +static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) { return __kmalloc_node(size, flags, node); } @@ -23,12 +24,12 @@ static inline void *kmalloc_node(size_t size, gfp_t flags, int node) * kmalloc is the normal method of allocating memory * in the kernel. */ -static inline void *kmalloc(size_t size, gfp_t flags) +static __always_inline void *kmalloc(size_t size, gfp_t flags) { return __kmalloc_node(size, flags, -1); } -static inline void *__kmalloc(size_t size, gfp_t flags) +static __always_inline void *__kmalloc(size_t size, gfp_t flags) { return kmalloc(size, flags); } diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index e37b6aa8a9fb..a1f90528e70b 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -10,6 +10,7 @@ #include <linux/gfp.h> #include <linux/workqueue.h> #include <linux/kobject.h> +#include <trace/kmemtrace.h> enum stat_item { ALLOC_FASTPATH, /* Allocation from cpu slab */ @@ -217,13 +218,31 @@ static __always_inline struct kmem_cache *kmalloc_slab(size_t size) void *kmem_cache_alloc(struct kmem_cache *, gfp_t); void *__kmalloc(size_t size, gfp_t flags); +#ifdef CONFIG_KMEMTRACE +extern void *kmem_cache_alloc_notrace(struct kmem_cache *s, gfp_t gfpflags); +#else +static __always_inline void * +kmem_cache_alloc_notrace(struct kmem_cache *s, gfp_t gfpflags) +{ + return kmem_cache_alloc(s, gfpflags); +} +#endif + static __always_inline void *kmalloc_large(size_t size, gfp_t flags) { - return (void *)__get_free_pages(flags | __GFP_COMP, get_order(size)); + unsigned int order = get_order(size); + void *ret = (void *) __get_free_pages(flags | __GFP_COMP, order); + + kmemtrace_mark_alloc(KMEMTRACE_TYPE_KMALLOC, _THIS_IP_, ret, + size, PAGE_SIZE << order, flags); + + return ret; } static __always_inline void *kmalloc(size_t size, gfp_t flags) { + void *ret; + if (__builtin_constant_p(size)) { if (size > SLUB_MAX_SIZE) return kmalloc_large(size, flags); @@ -234,7 +253,13 @@ static __always_inline void *kmalloc(size_t size, gfp_t flags) if (!s) return ZERO_SIZE_PTR; - return kmem_cache_alloc(s, flags); + ret = kmem_cache_alloc_notrace(s, flags); + + kmemtrace_mark_alloc(KMEMTRACE_TYPE_KMALLOC, + _THIS_IP_, ret, + size, s->size, flags); + + return ret; } } return __kmalloc(size, flags); @@ -244,8 +269,24 @@ static __always_inline void *kmalloc(size_t size, gfp_t flags) void *__kmalloc_node(size_t size, gfp_t flags, int node); void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node); +#ifdef CONFIG_KMEMTRACE +extern void *kmem_cache_alloc_node_notrace(struct kmem_cache *s, + gfp_t gfpflags, + int node); +#else +static __always_inline void * +kmem_cache_alloc_node_notrace(struct kmem_cache *s, + gfp_t gfpflags, + int node) +{ + return kmem_cache_alloc_node(s, gfpflags, node); +} +#endif + static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) { + void *ret; + if (__builtin_constant_p(size) && size <= SLUB_MAX_SIZE && !(flags & SLUB_DMA)) { struct kmem_cache *s = kmalloc_slab(size); @@ -253,7 +294,13 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) if (!s) return ZERO_SIZE_PTR; - return kmem_cache_alloc_node(s, flags, node); + ret = kmem_cache_alloc_node_notrace(s, flags, node); + + kmemtrace_mark_alloc_node(KMEMTRACE_TYPE_KMALLOC, + _THIS_IP_, ret, + size, s->size, flags, node); + + return ret; } return __kmalloc_node(size, flags, node); } diff --git a/include/linux/smp.h b/include/linux/smp.h index bbacb7baa446..a69db820eed6 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -38,7 +38,7 @@ int smp_call_function_single(int cpuid, void (*func) (void *info), void *info, /* * main cross-CPU interfaces, handles INIT, TLB flush, STOP, etc. * (defined in asm header): - */ + */ /* * stops all CPUs but the current one: @@ -82,7 +82,8 @@ smp_call_function_mask(cpumask_t mask, void(*func)(void *info), void *info, return 0; } -void __smp_call_function_single(int cpuid, struct call_single_data *data); +void __smp_call_function_single(int cpuid, struct call_single_data *data, + int wait); /* * Generic and arch helpers @@ -121,6 +122,8 @@ extern unsigned int setup_max_cpus; #else /* !SMP */ +static inline void smp_send_stop(void) { } + /* * These macros fold the SMP functionality into a single CPU system */ diff --git a/include/linux/string.h b/include/linux/string.h index 8852739f36df..489019ef1694 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -10,6 +10,7 @@ #include <linux/compiler.h> /* for inline */ #include <linux/types.h> /* for size_t */ #include <linux/stddef.h> /* for NULL */ +#include <stdarg.h> extern char *strndup_user(const char __user *, long); extern void *memdup_user(const void __user *, size_t); @@ -112,8 +113,23 @@ extern void argv_free(char **argv); extern bool sysfs_streq(const char *s1, const char *s2); +#ifdef CONFIG_BINARY_PRINTF +int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args); +int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf); +int bprintf(u32 *bin_buf, size_t size, const char *fmt, ...) __printf(3, 4); +#endif + extern ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos, const void *from, size_t available); +/** + * strstarts - does @str start with @prefix? + * @str: string to examine + * @prefix: prefix to look for. + */ +static inline bool strstarts(const char *str, const char *prefix) +{ + return strncmp(str, prefix, strlen(prefix)) == 0; +} #endif #endif /* _LINUX_STRING_H_ */ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index b299a82a05e7..6470f74074af 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -65,6 +65,7 @@ struct old_linux_dirent; #include <asm/signal.h> #include <linux/quota.h> #include <linux/key.h> +#include <linux/ftrace.h> #define __SC_DECL1(t1, a1) t1 a1 #define __SC_DECL2(t2, a2, ...) t2 a2, __SC_DECL1(__VA_ARGS__) @@ -95,7 +96,46 @@ struct old_linux_dirent; #define __SC_TEST5(t5, a5, ...) __SC_TEST(t5); __SC_TEST4(__VA_ARGS__) #define __SC_TEST6(t6, a6, ...) __SC_TEST(t6); __SC_TEST5(__VA_ARGS__) +#ifdef CONFIG_FTRACE_SYSCALLS +#define __SC_STR_ADECL1(t, a) #a +#define __SC_STR_ADECL2(t, a, ...) #a, __SC_STR_ADECL1(__VA_ARGS__) +#define __SC_STR_ADECL3(t, a, ...) #a, __SC_STR_ADECL2(__VA_ARGS__) +#define __SC_STR_ADECL4(t, a, ...) #a, __SC_STR_ADECL3(__VA_ARGS__) +#define __SC_STR_ADECL5(t, a, ...) #a, __SC_STR_ADECL4(__VA_ARGS__) +#define __SC_STR_ADECL6(t, a, ...) #a, __SC_STR_ADECL5(__VA_ARGS__) + +#define __SC_STR_TDECL1(t, a) #t +#define __SC_STR_TDECL2(t, a, ...) #t, __SC_STR_TDECL1(__VA_ARGS__) +#define __SC_STR_TDECL3(t, a, ...) #t, __SC_STR_TDECL2(__VA_ARGS__) +#define __SC_STR_TDECL4(t, a, ...) #t, __SC_STR_TDECL3(__VA_ARGS__) +#define __SC_STR_TDECL5(t, a, ...) #t, __SC_STR_TDECL4(__VA_ARGS__) +#define __SC_STR_TDECL6(t, a, ...) #t, __SC_STR_TDECL5(__VA_ARGS__) + +#define SYSCALL_METADATA(sname, nb) \ + static const struct syscall_metadata __used \ + __attribute__((__aligned__(4))) \ + __attribute__((section("__syscalls_metadata"))) \ + __syscall_meta_##sname = { \ + .name = "sys"#sname, \ + .nb_args = nb, \ + .types = types_##sname, \ + .args = args_##sname, \ + } + +#define SYSCALL_DEFINE0(sname) \ + static const struct syscall_metadata __used \ + __attribute__((__aligned__(4))) \ + __attribute__((section("__syscalls_metadata"))) \ + __syscall_meta_##sname = { \ + .name = "sys_"#sname, \ + .nb_args = 0, \ + }; \ + asmlinkage long sys_##sname(void) + +#else #define SYSCALL_DEFINE0(name) asmlinkage long sys_##name(void) +#endif + #define SYSCALL_DEFINE1(name, ...) SYSCALL_DEFINEx(1, _##name, __VA_ARGS__) #define SYSCALL_DEFINE2(name, ...) SYSCALL_DEFINEx(2, _##name, __VA_ARGS__) #define SYSCALL_DEFINE3(name, ...) SYSCALL_DEFINEx(3, _##name, __VA_ARGS__) @@ -117,10 +157,26 @@ struct old_linux_dirent; #endif #endif +#ifdef CONFIG_FTRACE_SYSCALLS +#define SYSCALL_DEFINEx(x, sname, ...) \ + static const char *types_##sname[] = { \ + __SC_STR_TDECL##x(__VA_ARGS__) \ + }; \ + static const char *args_##sname[] = { \ + __SC_STR_ADECL##x(__VA_ARGS__) \ + }; \ + SYSCALL_METADATA(sname, x); \ + __SYSCALL_DEFINEx(x, sname, __VA_ARGS__) +#else +#define SYSCALL_DEFINEx(x, sname, ...) \ + __SYSCALL_DEFINEx(x, sname, __VA_ARGS__) +#endif + #ifdef CONFIG_HAVE_SYSCALL_WRAPPERS #define SYSCALL_DEFINE(name) static inline long SYSC_##name -#define SYSCALL_DEFINEx(x, name, ...) \ + +#define __SYSCALL_DEFINEx(x, name, ...) \ asmlinkage long sys##name(__SC_DECL##x(__VA_ARGS__)); \ static inline long SYSC##name(__SC_DECL##x(__VA_ARGS__)); \ asmlinkage long SyS##name(__SC_LONG##x(__VA_ARGS__)) \ @@ -134,7 +190,7 @@ struct old_linux_dirent; #else /* CONFIG_HAVE_SYSCALL_WRAPPERS */ #define SYSCALL_DEFINE(name) asmlinkage long sys_##name -#define SYSCALL_DEFINEx(x, name, ...) \ +#define __SYSCALL_DEFINEx(x, name, ...) \ asmlinkage long sys##name(__SC_DECL##x(__VA_ARGS__)) #endif /* CONFIG_HAVE_SYSCALL_WRAPPERS */ @@ -462,9 +518,9 @@ asmlinkage long sys_pread64(unsigned int fd, char __user *buf, asmlinkage long sys_pwrite64(unsigned int fd, const char __user *buf, size_t count, loff_t pos); asmlinkage long sys_preadv(unsigned long fd, const struct iovec __user *vec, - unsigned long vlen, u32 pos_high, u32 pos_low); + unsigned long vlen, unsigned long pos_l, unsigned long pos_h); asmlinkage long sys_pwritev(unsigned long fd, const struct iovec __user *vec, - unsigned long vlen, u32 pos_high, u32 pos_low); + unsigned long vlen, unsigned long pos_l, unsigned long pos_h); asmlinkage long sys_getcwd(char __user *buf, unsigned long size); asmlinkage long sys_mkdir(const char __user *pathname, int mode); asmlinkage long sys_chdir(const char __user *filename); diff --git a/include/linux/topology.h b/include/linux/topology.h index a16b9e06f2e5..7402c1a27c4f 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -38,11 +38,7 @@ #endif #ifndef nr_cpus_node -#define nr_cpus_node(node) \ - ({ \ - node_to_cpumask_ptr(__tmp__, node); \ - cpus_weight(*__tmp__); \ - }) +#define nr_cpus_node(node) cpumask_weight(cpumask_of_node(node)) #endif #define for_each_node_with_cpus(node) \ @@ -200,4 +196,9 @@ int arch_update_cpu_topology(void); #define topology_core_cpumask(cpu) cpumask_of(cpu) #endif +/* Returns the number of the current Node. */ +#ifndef numa_node_id +#define numa_node_id() (cpu_to_node(raw_smp_processor_id())) +#endif + #endif /* _LINUX_TOPOLOGY_H */ diff --git a/include/linux/trace_clock.h b/include/linux/trace_clock.h new file mode 100644 index 000000000000..7a8130384087 --- /dev/null +++ b/include/linux/trace_clock.h @@ -0,0 +1,19 @@ +#ifndef _LINUX_TRACE_CLOCK_H +#define _LINUX_TRACE_CLOCK_H + +/* + * 3 trace clock variants, with differing scalability/precision + * tradeoffs: + * + * - local: CPU-local trace clock + * - medium: scalable global clock with some jitter + * - global: globally monotonic, serialized clock + */ +#include <linux/compiler.h> +#include <linux/types.h> + +extern u64 notrace trace_clock_local(void); +extern u64 notrace trace_clock(void); +extern u64 notrace trace_clock_global(void); + +#endif /* _LINUX_TRACE_CLOCK_H */ diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 757005458366..d35a7ee7611f 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -31,8 +31,8 @@ struct tracepoint { * Keep in sync with vmlinux.lds.h. */ -#define TPPROTO(args...) args -#define TPARGS(args...) args +#define TP_PROTO(args...) args +#define TP_ARGS(args...) args #ifdef CONFIG_TRACEPOINTS @@ -65,7 +65,7 @@ struct tracepoint { { \ if (unlikely(__tracepoint_##name.state)) \ __DO_TRACE(&__tracepoint_##name, \ - TPPROTO(proto), TPARGS(args)); \ + TP_PROTO(proto), TP_ARGS(args)); \ } \ static inline int register_trace_##name(void (*probe)(proto)) \ { \ @@ -153,4 +153,114 @@ static inline void tracepoint_synchronize_unregister(void) synchronize_sched(); } +#define PARAMS(args...) args +#define TRACE_FORMAT(name, proto, args, fmt) \ + DECLARE_TRACE(name, PARAMS(proto), PARAMS(args)) + + +/* + * For use with the TRACE_EVENT macro: + * + * We define a tracepoint, its arguments, its printk format + * and its 'fast binay record' layout. + * + * Firstly, name your tracepoint via TRACE_EVENT(name : the + * 'subsystem_event' notation is fine. + * + * Think about this whole construct as the + * 'trace_sched_switch() function' from now on. + * + * + * TRACE_EVENT(sched_switch, + * + * * + * * A function has a regular function arguments + * * prototype, declare it via TP_PROTO(): + * * + * + * TP_PROTO(struct rq *rq, struct task_struct *prev, + * struct task_struct *next), + * + * * + * * Define the call signature of the 'function'. + * * (Design sidenote: we use this instead of a + * * TP_PROTO1/TP_PROTO2/TP_PROTO3 ugliness.) + * * + * + * TP_ARGS(rq, prev, next), + * + * * + * * Fast binary tracing: define the trace record via + * * TP_STRUCT__entry(). You can think about it like a + * * regular C structure local variable definition. + * * + * * This is how the trace record is structured and will + * * be saved into the ring buffer. These are the fields + * * that will be exposed to user-space in + * * /debug/tracing/events/<*>/format. + * * + * * The declared 'local variable' is called '__entry' + * * + * * __field(pid_t, prev_prid) is equivalent to a standard declariton: + * * + * * pid_t prev_pid; + * * + * * __array(char, prev_comm, TASK_COMM_LEN) is equivalent to: + * * + * * char prev_comm[TASK_COMM_LEN]; + * * + * + * TP_STRUCT__entry( + * __array( char, prev_comm, TASK_COMM_LEN ) + * __field( pid_t, prev_pid ) + * __field( int, prev_prio ) + * __array( char, next_comm, TASK_COMM_LEN ) + * __field( pid_t, next_pid ) + * __field( int, next_prio ) + * ), + * + * * + * * Assign the entry into the trace record, by embedding + * * a full C statement block into TP_fast_assign(). You + * * can refer to the trace record as '__entry' - + * * otherwise you can put arbitrary C code in here. + * * + * * Note: this C code will execute every time a trace event + * * happens, on an active tracepoint. + * * + * + * TP_fast_assign( + * memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN); + * __entry->prev_pid = prev->pid; + * __entry->prev_prio = prev->prio; + * memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN); + * __entry->next_pid = next->pid; + * __entry->next_prio = next->prio; + * ) + * + * * + * * Formatted output of a trace record via TP_printk(). + * * This is how the tracepoint will appear under ftrace + * * plugins that make use of this tracepoint. + * * + * * (raw-binary tracing wont actually perform this step.) + * * + * + * TP_printk("task %s:%d [%d] ==> %s:%d [%d]", + * __entry->prev_comm, __entry->prev_pid, __entry->prev_prio, + * __entry->next_comm, __entry->next_pid, __entry->next_prio), + * + * ); + * + * This macro construct is thus used for the regular printk format + * tracing setup, it is used to construct a function pointer based + * tracepoint callback (this is used by programmatic plugins and + * can also by used by generic instrumentation like SystemTap), and + * it is also used to expose a structured trace record in + * /debug/tracing/events/. + */ + +#define TRACE_EVENT(name, proto, args, struct, assign, print) \ + DECLARE_TRACE(name, PARAMS(proto), PARAMS(args)) + #endif diff --git a/include/linux/usb/wusb.h b/include/linux/usb/wusb.h index 5f401b644ed5..429c631d2aad 100644 --- a/include/linux/usb/wusb.h +++ b/include/linux/usb/wusb.h @@ -80,8 +80,7 @@ struct wusb_ckhdid { u8 data[16]; } __attribute__((packed)); -const static -struct wusb_ckhdid wusb_ckhdid_zero = { .data = { 0 } }; +static const struct wusb_ckhdid wusb_ckhdid_zero = { .data = { 0 } }; #define WUSB_CKHDID_STRSIZE (3 * sizeof(struct wusb_ckhdid) + 1) diff --git a/include/trace/block.h b/include/trace/block.h index 25c6a1fd5b77..25b7068b819e 100644 --- a/include/trace/block.h +++ b/include/trace/block.h @@ -5,72 +5,72 @@ #include <linux/tracepoint.h> DECLARE_TRACE(block_rq_abort, - TPPROTO(struct request_queue *q, struct request *rq), - TPARGS(q, rq)); + TP_PROTO(struct request_queue *q, struct request *rq), + TP_ARGS(q, rq)); DECLARE_TRACE(block_rq_insert, - TPPROTO(struct request_queue *q, struct request *rq), - TPARGS(q, rq)); + TP_PROTO(struct request_queue *q, struct request *rq), + TP_ARGS(q, rq)); DECLARE_TRACE(block_rq_issue, - TPPROTO(struct request_queue *q, struct request *rq), - TPARGS(q, rq)); + TP_PROTO(struct request_queue *q, struct request *rq), + TP_ARGS(q, rq)); DECLARE_TRACE(block_rq_requeue, - TPPROTO(struct request_queue *q, struct request *rq), - TPARGS(q, rq)); + TP_PROTO(struct request_queue *q, struct request *rq), + TP_ARGS(q, rq)); DECLARE_TRACE(block_rq_complete, - TPPROTO(struct request_queue *q, struct request *rq), - TPARGS(q, rq)); + TP_PROTO(struct request_queue *q, struct request *rq), + TP_ARGS(q, rq)); DECLARE_TRACE(block_bio_bounce, - TPPROTO(struct request_queue *q, struct bio *bio), - TPARGS(q, bio)); + TP_PROTO(struct request_queue *q, struct bio *bio), + TP_ARGS(q, bio)); DECLARE_TRACE(block_bio_complete, - TPPROTO(struct request_queue *q, struct bio *bio), - TPARGS(q, bio)); + TP_PROTO(struct request_queue *q, struct bio *bio), + TP_ARGS(q, bio)); DECLARE_TRACE(block_bio_backmerge, - TPPROTO(struct request_queue *q, struct bio *bio), - TPARGS(q, bio)); + TP_PROTO(struct request_queue *q, struct bio *bio), + TP_ARGS(q, bio)); DECLARE_TRACE(block_bio_frontmerge, - TPPROTO(struct request_queue *q, struct bio *bio), - TPARGS(q, bio)); + TP_PROTO(struct request_queue *q, struct bio *bio), + TP_ARGS(q, bio)); DECLARE_TRACE(block_bio_queue, - TPPROTO(struct request_queue *q, struct bio *bio), - TPARGS(q, bio)); + TP_PROTO(struct request_queue *q, struct bio *bio), + TP_ARGS(q, bio)); DECLARE_TRACE(block_getrq, - TPPROTO(struct request_queue *q, struct bio *bio, int rw), - TPARGS(q, bio, rw)); + TP_PROTO(struct request_queue *q, struct bio *bio, int rw), + TP_ARGS(q, bio, rw)); DECLARE_TRACE(block_sleeprq, - TPPROTO(struct request_queue *q, struct bio *bio, int rw), - TPARGS(q, bio, rw)); + TP_PROTO(struct request_queue *q, struct bio *bio, int rw), + TP_ARGS(q, bio, rw)); DECLARE_TRACE(block_plug, - TPPROTO(struct request_queue *q), - TPARGS(q)); + TP_PROTO(struct request_queue *q), + TP_ARGS(q)); DECLARE_TRACE(block_unplug_timer, - TPPROTO(struct request_queue *q), - TPARGS(q)); + TP_PROTO(struct request_queue *q), + TP_ARGS(q)); DECLARE_TRACE(block_unplug_io, - TPPROTO(struct request_queue *q), - TPARGS(q)); + TP_PROTO(struct request_queue *q), + TP_ARGS(q)); DECLARE_TRACE(block_split, - TPPROTO(struct request_queue *q, struct bio *bio, unsigned int pdu), - TPARGS(q, bio, pdu)); + TP_PROTO(struct request_queue *q, struct bio *bio, unsigned int pdu), + TP_ARGS(q, bio, pdu)); DECLARE_TRACE(block_remap, - TPPROTO(struct request_queue *q, struct bio *bio, dev_t dev, - sector_t from, sector_t to), - TPARGS(q, bio, dev, from, to)); + TP_PROTO(struct request_queue *q, struct bio *bio, dev_t dev, + sector_t from, sector_t to), + TP_ARGS(q, bio, dev, from, to)); #endif diff --git a/include/trace/irq.h b/include/trace/irq.h new file mode 100644 index 000000000000..ff5d4495dc37 --- /dev/null +++ b/include/trace/irq.h @@ -0,0 +1,9 @@ +#ifndef _TRACE_IRQ_H +#define _TRACE_IRQ_H + +#include <linux/interrupt.h> +#include <linux/tracepoint.h> + +#include <trace/irq_event_types.h> + +#endif diff --git a/include/trace/irq_event_types.h b/include/trace/irq_event_types.h new file mode 100644 index 000000000000..85964ebd47ec --- /dev/null +++ b/include/trace/irq_event_types.h @@ -0,0 +1,55 @@ + +/* use <trace/irq.h> instead */ +#ifndef TRACE_FORMAT +# error Do not include this file directly. +# error Unless you know what you are doing. +#endif + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM irq + +/* + * Tracepoint for entry of interrupt handler: + */ +TRACE_FORMAT(irq_handler_entry, + TP_PROTO(int irq, struct irqaction *action), + TP_ARGS(irq, action), + TP_FMT("irq=%d handler=%s", irq, action->name) + ); + +/* + * Tracepoint for return of an interrupt handler: + */ +TRACE_EVENT(irq_handler_exit, + + TP_PROTO(int irq, struct irqaction *action, int ret), + + TP_ARGS(irq, action, ret), + + TP_STRUCT__entry( + __field( int, irq ) + __field( int, ret ) + ), + + TP_fast_assign( + __entry->irq = irq; + __entry->ret = ret; + ), + + TP_printk("irq=%d return=%s", + __entry->irq, __entry->ret ? "handled" : "unhandled") +); + +TRACE_FORMAT(softirq_entry, + TP_PROTO(struct softirq_action *h, struct softirq_action *vec), + TP_ARGS(h, vec), + TP_FMT("softirq=%d action=%s", (int)(h - vec), softirq_to_name[h-vec]) + ); + +TRACE_FORMAT(softirq_exit, + TP_PROTO(struct softirq_action *h, struct softirq_action *vec), + TP_ARGS(h, vec), + TP_FMT("softirq=%d action=%s", (int)(h - vec), softirq_to_name[h-vec]) + ); + +#undef TRACE_SYSTEM diff --git a/include/trace/kmemtrace.h b/include/trace/kmemtrace.h new file mode 100644 index 000000000000..ad8b7857855a --- /dev/null +++ b/include/trace/kmemtrace.h @@ -0,0 +1,75 @@ +/* + * Copyright (C) 2008 Eduard - Gabriel Munteanu + * + * This file is released under GPL version 2. + */ + +#ifndef _LINUX_KMEMTRACE_H +#define _LINUX_KMEMTRACE_H + +#ifdef __KERNEL__ + +#include <linux/types.h> +#include <linux/marker.h> + +enum kmemtrace_type_id { + KMEMTRACE_TYPE_KMALLOC = 0, /* kmalloc() or kfree(). */ + KMEMTRACE_TYPE_CACHE, /* kmem_cache_*(). */ + KMEMTRACE_TYPE_PAGES, /* __get_free_pages() and friends. */ +}; + +#ifdef CONFIG_KMEMTRACE + +extern void kmemtrace_init(void); + +extern void kmemtrace_mark_alloc_node(enum kmemtrace_type_id type_id, + unsigned long call_site, + const void *ptr, + size_t bytes_req, + size_t bytes_alloc, + gfp_t gfp_flags, + int node); + +extern void kmemtrace_mark_free(enum kmemtrace_type_id type_id, + unsigned long call_site, + const void *ptr); + +#else /* CONFIG_KMEMTRACE */ + +static inline void kmemtrace_init(void) +{ +} + +static inline void kmemtrace_mark_alloc_node(enum kmemtrace_type_id type_id, + unsigned long call_site, + const void *ptr, + size_t bytes_req, + size_t bytes_alloc, + gfp_t gfp_flags, + int node) +{ +} + +static inline void kmemtrace_mark_free(enum kmemtrace_type_id type_id, + unsigned long call_site, + const void *ptr) +{ +} + +#endif /* CONFIG_KMEMTRACE */ + +static inline void kmemtrace_mark_alloc(enum kmemtrace_type_id type_id, + unsigned long call_site, + const void *ptr, + size_t bytes_req, + size_t bytes_alloc, + gfp_t gfp_flags) +{ + kmemtrace_mark_alloc_node(type_id, call_site, ptr, + bytes_req, bytes_alloc, gfp_flags, -1); +} + +#endif /* __KERNEL__ */ + +#endif /* _LINUX_KMEMTRACE_H */ + diff --git a/include/trace/lockdep.h b/include/trace/lockdep.h new file mode 100644 index 000000000000..5ca67df87f2a --- /dev/null +++ b/include/trace/lockdep.h @@ -0,0 +1,9 @@ +#ifndef _TRACE_LOCKDEP_H +#define _TRACE_LOCKDEP_H + +#include <linux/lockdep.h> +#include <linux/tracepoint.h> + +#include <trace/lockdep_event_types.h> + +#endif diff --git a/include/trace/lockdep_event_types.h b/include/trace/lockdep_event_types.h new file mode 100644 index 000000000000..adccfcd2ec8f --- /dev/null +++ b/include/trace/lockdep_event_types.h @@ -0,0 +1,44 @@ + +#ifndef TRACE_FORMAT +# error Do not include this file directly. +# error Unless you know what you are doing. +#endif + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM lock + +#ifdef CONFIG_LOCKDEP + +TRACE_FORMAT(lock_acquire, + TP_PROTO(struct lockdep_map *lock, unsigned int subclass, + int trylock, int read, int check, + struct lockdep_map *next_lock, unsigned long ip), + TP_ARGS(lock, subclass, trylock, read, check, next_lock, ip), + TP_FMT("%s%s%s", trylock ? "try " : "", + read ? "read " : "", lock->name) + ); + +TRACE_FORMAT(lock_release, + TP_PROTO(struct lockdep_map *lock, int nested, unsigned long ip), + TP_ARGS(lock, nested, ip), + TP_FMT("%s", lock->name) + ); + +#ifdef CONFIG_LOCK_STAT + +TRACE_FORMAT(lock_contended, + TP_PROTO(struct lockdep_map *lock, unsigned long ip), + TP_ARGS(lock, ip), + TP_FMT("%s", lock->name) + ); + +TRACE_FORMAT(lock_acquired, + TP_PROTO(struct lockdep_map *lock, unsigned long ip), + TP_ARGS(lock, ip), + TP_FMT("%s", lock->name) + ); + +#endif +#endif + +#undef TRACE_SYSTEM diff --git a/include/trace/power.h b/include/trace/power.h new file mode 100644 index 000000000000..ef204666e983 --- /dev/null +++ b/include/trace/power.h @@ -0,0 +1,32 @@ +#ifndef _TRACE_POWER_H +#define _TRACE_POWER_H + +#include <linux/ktime.h> +#include <linux/tracepoint.h> + +enum { + POWER_NONE = 0, + POWER_CSTATE = 1, + POWER_PSTATE = 2, +}; + +struct power_trace { + ktime_t stamp; + ktime_t end; + int type; + int state; +}; + +DECLARE_TRACE(power_start, + TP_PROTO(struct power_trace *it, unsigned int type, unsigned int state), + TP_ARGS(it, type, state)); + +DECLARE_TRACE(power_mark, + TP_PROTO(struct power_trace *it, unsigned int type, unsigned int state), + TP_ARGS(it, type, state)); + +DECLARE_TRACE(power_end, + TP_PROTO(struct power_trace *it), + TP_ARGS(it)); + +#endif /* _TRACE_POWER_H */ diff --git a/include/trace/sched.h b/include/trace/sched.h index 0d81098ee9fc..4e372a1a29bf 100644 --- a/include/trace/sched.h +++ b/include/trace/sched.h @@ -4,53 +4,6 @@ #include <linux/sched.h> #include <linux/tracepoint.h> -DECLARE_TRACE(sched_kthread_stop, - TPPROTO(struct task_struct *t), - TPARGS(t)); - -DECLARE_TRACE(sched_kthread_stop_ret, - TPPROTO(int ret), - TPARGS(ret)); - -DECLARE_TRACE(sched_wait_task, - TPPROTO(struct rq *rq, struct task_struct *p), - TPARGS(rq, p)); - -DECLARE_TRACE(sched_wakeup, - TPPROTO(struct rq *rq, struct task_struct *p, int success), - TPARGS(rq, p, success)); - -DECLARE_TRACE(sched_wakeup_new, - TPPROTO(struct rq *rq, struct task_struct *p, int success), - TPARGS(rq, p, success)); - -DECLARE_TRACE(sched_switch, - TPPROTO(struct rq *rq, struct task_struct *prev, - struct task_struct *next), - TPARGS(rq, prev, next)); - -DECLARE_TRACE(sched_migrate_task, - TPPROTO(struct task_struct *p, int orig_cpu, int dest_cpu), - TPARGS(p, orig_cpu, dest_cpu)); - -DECLARE_TRACE(sched_process_free, - TPPROTO(struct task_struct *p), - TPARGS(p)); - -DECLARE_TRACE(sched_process_exit, - TPPROTO(struct task_struct *p), - TPARGS(p)); - -DECLARE_TRACE(sched_process_wait, - TPPROTO(struct pid *pid), - TPARGS(pid)); - -DECLARE_TRACE(sched_process_fork, - TPPROTO(struct task_struct *parent, struct task_struct *child), - TPARGS(parent, child)); - -DECLARE_TRACE(sched_signal_send, - TPPROTO(int sig, struct task_struct *p), - TPARGS(sig, p)); +#include <trace/sched_event_types.h> #endif diff --git a/include/trace/sched_event_types.h b/include/trace/sched_event_types.h new file mode 100644 index 000000000000..63547dc1125f --- /dev/null +++ b/include/trace/sched_event_types.h @@ -0,0 +1,337 @@ + +/* use <trace/sched.h> instead */ +#ifndef TRACE_EVENT +# error Do not include this file directly. +# error Unless you know what you are doing. +#endif + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM sched + +/* + * Tracepoint for calling kthread_stop, performed to end a kthread: + */ +TRACE_EVENT(sched_kthread_stop, + + TP_PROTO(struct task_struct *t), + + TP_ARGS(t), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + ), + + TP_fast_assign( + memcpy(__entry->comm, t->comm, TASK_COMM_LEN); + __entry->pid = t->pid; + ), + + TP_printk("task %s:%d", __entry->comm, __entry->pid) +); + +/* + * Tracepoint for the return value of the kthread stopping: + */ +TRACE_EVENT(sched_kthread_stop_ret, + + TP_PROTO(int ret), + + TP_ARGS(ret), + + TP_STRUCT__entry( + __field( int, ret ) + ), + + TP_fast_assign( + __entry->ret = ret; + ), + + TP_printk("ret %d", __entry->ret) +); + +/* + * Tracepoint for waiting on task to unschedule: + * + * (NOTE: the 'rq' argument is not used by generic trace events, + * but used by the latency tracer plugin. ) + */ +TRACE_EVENT(sched_wait_task, + + TP_PROTO(struct rq *rq, struct task_struct *p), + + TP_ARGS(rq, p), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + __field( int, prio ) + ), + + TP_fast_assign( + memcpy(__entry->comm, p->comm, TASK_COMM_LEN); + __entry->pid = p->pid; + __entry->prio = p->prio; + ), + + TP_printk("task %s:%d [%d]", + __entry->comm, __entry->pid, __entry->prio) +); + +/* + * Tracepoint for waking up a task: + * + * (NOTE: the 'rq' argument is not used by generic trace events, + * but used by the latency tracer plugin. ) + */ +TRACE_EVENT(sched_wakeup, + + TP_PROTO(struct rq *rq, struct task_struct *p, int success), + + TP_ARGS(rq, p, success), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + __field( int, prio ) + __field( int, success ) + ), + + TP_fast_assign( + memcpy(__entry->comm, p->comm, TASK_COMM_LEN); + __entry->pid = p->pid; + __entry->prio = p->prio; + __entry->success = success; + ), + + TP_printk("task %s:%d [%d] success=%d", + __entry->comm, __entry->pid, __entry->prio, + __entry->success) +); + +/* + * Tracepoint for waking up a new task: + * + * (NOTE: the 'rq' argument is not used by generic trace events, + * but used by the latency tracer plugin. ) + */ +TRACE_EVENT(sched_wakeup_new, + + TP_PROTO(struct rq *rq, struct task_struct *p, int success), + + TP_ARGS(rq, p, success), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + __field( int, prio ) + __field( int, success ) + ), + + TP_fast_assign( + memcpy(__entry->comm, p->comm, TASK_COMM_LEN); + __entry->pid = p->pid; + __entry->prio = p->prio; + __entry->success = success; + ), + + TP_printk("task %s:%d [%d] success=%d", + __entry->comm, __entry->pid, __entry->prio, + __entry->success) +); + +/* + * Tracepoint for task switches, performed by the scheduler: + * + * (NOTE: the 'rq' argument is not used by generic trace events, + * but used by the latency tracer plugin. ) + */ +TRACE_EVENT(sched_switch, + + TP_PROTO(struct rq *rq, struct task_struct *prev, + struct task_struct *next), + + TP_ARGS(rq, prev, next), + + TP_STRUCT__entry( + __array( char, prev_comm, TASK_COMM_LEN ) + __field( pid_t, prev_pid ) + __field( int, prev_prio ) + __array( char, next_comm, TASK_COMM_LEN ) + __field( pid_t, next_pid ) + __field( int, next_prio ) + ), + + TP_fast_assign( + memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN); + __entry->prev_pid = prev->pid; + __entry->prev_prio = prev->prio; + memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN); + __entry->next_pid = next->pid; + __entry->next_prio = next->prio; + ), + + TP_printk("task %s:%d [%d] ==> %s:%d [%d]", + __entry->prev_comm, __entry->prev_pid, __entry->prev_prio, + __entry->next_comm, __entry->next_pid, __entry->next_prio) +); + +/* + * Tracepoint for a task being migrated: + */ +TRACE_EVENT(sched_migrate_task, + + TP_PROTO(struct task_struct *p, int orig_cpu, int dest_cpu), + + TP_ARGS(p, orig_cpu, dest_cpu), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + __field( int, prio ) + __field( int, orig_cpu ) + __field( int, dest_cpu ) + ), + + TP_fast_assign( + memcpy(__entry->comm, p->comm, TASK_COMM_LEN); + __entry->pid = p->pid; + __entry->prio = p->prio; + __entry->orig_cpu = orig_cpu; + __entry->dest_cpu = dest_cpu; + ), + + TP_printk("task %s:%d [%d] from: %d to: %d", + __entry->comm, __entry->pid, __entry->prio, + __entry->orig_cpu, __entry->dest_cpu) +); + +/* + * Tracepoint for freeing a task: + */ +TRACE_EVENT(sched_process_free, + + TP_PROTO(struct task_struct *p), + + TP_ARGS(p), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + __field( int, prio ) + ), + + TP_fast_assign( + memcpy(__entry->comm, p->comm, TASK_COMM_LEN); + __entry->pid = p->pid; + __entry->prio = p->prio; + ), + + TP_printk("task %s:%d [%d]", + __entry->comm, __entry->pid, __entry->prio) +); + +/* + * Tracepoint for a task exiting: + */ +TRACE_EVENT(sched_process_exit, + + TP_PROTO(struct task_struct *p), + + TP_ARGS(p), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + __field( int, prio ) + ), + + TP_fast_assign( + memcpy(__entry->comm, p->comm, TASK_COMM_LEN); + __entry->pid = p->pid; + __entry->prio = p->prio; + ), + + TP_printk("task %s:%d [%d]", + __entry->comm, __entry->pid, __entry->prio) +); + +/* + * Tracepoint for a waiting task: + */ +TRACE_EVENT(sched_process_wait, + + TP_PROTO(struct pid *pid), + + TP_ARGS(pid), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + __field( int, prio ) + ), + + TP_fast_assign( + memcpy(__entry->comm, current->comm, TASK_COMM_LEN); + __entry->pid = pid_nr(pid); + __entry->prio = current->prio; + ), + + TP_printk("task %s:%d [%d]", + __entry->comm, __entry->pid, __entry->prio) +); + +/* + * Tracepoint for do_fork: + */ +TRACE_EVENT(sched_process_fork, + + TP_PROTO(struct task_struct *parent, struct task_struct *child), + + TP_ARGS(parent, child), + + TP_STRUCT__entry( + __array( char, parent_comm, TASK_COMM_LEN ) + __field( pid_t, parent_pid ) + __array( char, child_comm, TASK_COMM_LEN ) + __field( pid_t, child_pid ) + ), + + TP_fast_assign( + memcpy(__entry->parent_comm, parent->comm, TASK_COMM_LEN); + __entry->parent_pid = parent->pid; + memcpy(__entry->child_comm, child->comm, TASK_COMM_LEN); + __entry->child_pid = child->pid; + ), + + TP_printk("parent %s:%d child %s:%d", + __entry->parent_comm, __entry->parent_pid, + __entry->child_comm, __entry->child_pid) +); + +/* + * Tracepoint for sending a signal: + */ +TRACE_EVENT(sched_signal_send, + + TP_PROTO(int sig, struct task_struct *p), + + TP_ARGS(sig, p), + + TP_STRUCT__entry( + __field( int, sig ) + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + ), + + TP_fast_assign( + memcpy(__entry->comm, p->comm, TASK_COMM_LEN); + __entry->pid = p->pid; + __entry->sig = sig; + ), + + TP_printk("sig: %d task %s:%d", + __entry->sig, __entry->comm, __entry->pid) +); + +#undef TRACE_SYSTEM diff --git a/include/trace/skb.h b/include/trace/skb.h index a96610f92f69..b66206d9be72 100644 --- a/include/trace/skb.h +++ b/include/trace/skb.h @@ -5,7 +5,7 @@ #include <linux/tracepoint.h> DECLARE_TRACE(kfree_skb, - TPPROTO(struct sk_buff *skb, void *location), - TPARGS(skb, location)); + TP_PROTO(struct sk_buff *skb, void *location), + TP_ARGS(skb, location)); #endif diff --git a/include/trace/trace_event_types.h b/include/trace/trace_event_types.h new file mode 100644 index 000000000000..df56f5694be6 --- /dev/null +++ b/include/trace/trace_event_types.h @@ -0,0 +1,5 @@ +/* trace/<type>_event_types.h here */ + +#include <trace/sched_event_types.h> +#include <trace/irq_event_types.h> +#include <trace/lockdep_event_types.h> diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h new file mode 100644 index 000000000000..fd13750ca4ba --- /dev/null +++ b/include/trace/trace_events.h @@ -0,0 +1,5 @@ +/* trace/<type>.h here */ + +#include <trace/sched.h> +#include <trace/irq.h> +#include <trace/lockdep.h> diff --git a/include/trace/workqueue.h b/include/trace/workqueue.h new file mode 100644 index 000000000000..7626523deeba --- /dev/null +++ b/include/trace/workqueue.h @@ -0,0 +1,25 @@ +#ifndef __TRACE_WORKQUEUE_H +#define __TRACE_WORKQUEUE_H + +#include <linux/tracepoint.h> +#include <linux/workqueue.h> +#include <linux/sched.h> + +DECLARE_TRACE(workqueue_insertion, + TP_PROTO(struct task_struct *wq_thread, struct work_struct *work), + TP_ARGS(wq_thread, work)); + +DECLARE_TRACE(workqueue_execution, + TP_PROTO(struct task_struct *wq_thread, struct work_struct *work), + TP_ARGS(wq_thread, work)); + +/* Trace the creation of one workqueue thread on a cpu */ +DECLARE_TRACE(workqueue_creation, + TP_PROTO(struct task_struct *wq_thread, int cpu), + TP_ARGS(wq_thread, cpu)); + +DECLARE_TRACE(workqueue_destruction, + TP_PROTO(struct task_struct *wq_thread), + TP_ARGS(wq_thread)); + +#endif /* __TRACE_WORKQUEUE_H */ diff --git a/init/Kconfig b/init/Kconfig index 236a79377b8e..09c79537ae09 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -565,7 +565,7 @@ config CGROUP_MEM_RES_CTLR select MM_OWNER help Provides a memory resource controller that manages both anonymous - memory and page cache. (See Documentation/controllers/memory.txt) + memory and page cache. (See Documentation/cgroups/memory.txt) Note that setting this option increases fixed memory overhead associated with each page of memory in the system. By this, @@ -689,7 +689,7 @@ config PID_NS depends on NAMESPACES && EXPERIMENTAL help Support process id namespaces. This allows having multiple - process with the same pid as long as they are in different + processes with the same pid as long as they are in different pid namespaces. This is a building block of containers. Unless you want to work with an experimental feature @@ -954,7 +954,7 @@ config COMPAT_BRK Randomizing heap placement makes heap exploits harder, but it also breaks ancient binaries (including anything libc5 based). This option changes the bootup default to heap randomization - disabled, and can be overriden runtime by setting + disabled, and can be overridden at runtime by setting /proc/sys/kernel/randomize_va_space to 2. On non-ancient distros (post-2000 ones) N is usually a safe choice. @@ -1007,7 +1007,7 @@ config TRACEPOINTS config MARKERS bool "Activate markers" - depends on TRACEPOINTS + select TRACEPOINTS help Place an empty function call at each marker site. Can be dynamically changed for a probe function. @@ -1124,7 +1124,7 @@ config INIT_ALL_POSSIBLE cpu_possible_map, some of them chose to initialize cpu_possible_map with all 1s, and others with all 0s. When they were centralised, it was better to provide this option than to break all the archs - and have several arch maintainers persuing me down dark alleys. + and have several arch maintainers pursuing me down dark alleys. config STOP_MACHINE bool diff --git a/init/main.c b/init/main.c index 07c8658ffca5..3585f073d636 100644 --- a/init/main.c +++ b/init/main.c @@ -71,6 +71,7 @@ #include <asm/setup.h> #include <asm/sections.h> #include <asm/cacheflush.h> +#include <trace/kmemtrace.h> #ifdef CONFIG_X86_LOCAL_APIC #include <asm/smp.h> @@ -648,6 +649,7 @@ asmlinkage void __init start_kernel(void) enable_debug_pagealloc(); cpu_hotplug_init(); kmem_cache_init(); + kmemtrace_init(); debug_objects_mem_init(); idr_init_cache(); setup_per_cpu_pageset(); @@ -769,6 +771,7 @@ static void __init do_basic_setup(void) { rcu_init_sched(); /* needed by module_init stage. */ init_workqueues(); + cpuset_init_smp(); usermodehelper_init(); driver_init(); init_irq_proc(); @@ -863,8 +866,6 @@ static int __init kernel_init(void * unused) smp_init(); sched_init_smp(); - cpuset_init_smp(); - do_basic_setup(); /* diff --git a/kernel/extable.c b/kernel/extable.c index e136ed8d82ba..7f8f263f8524 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -15,11 +15,22 @@ along with this program; if not, write to the Free Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +#include <linux/ftrace.h> +#include <linux/memory.h> #include <linux/module.h> +#include <linux/mutex.h> #include <linux/init.h> -#include <linux/ftrace.h> -#include <asm/uaccess.h> + #include <asm/sections.h> +#include <asm/uaccess.h> + +/* + * mutex protecting text section modification (dynamic code patching). + * some users need to sleep (allocating memory...) while they hold this lock. + * + * NOT exported to modules - patching kernel text is a really delicate matter. + */ +DEFINE_MUTEX(text_mutex); extern struct exception_table_entry __start___ex_table[]; extern struct exception_table_entry __stop___ex_table[]; @@ -41,31 +52,50 @@ const struct exception_table_entry *search_exception_tables(unsigned long addr) return e; } -__notrace_funcgraph int core_kernel_text(unsigned long addr) +static inline int init_kernel_text(unsigned long addr) +{ + if (addr >= (unsigned long)_sinittext && + addr <= (unsigned long)_einittext) + return 1; + return 0; +} + +int core_kernel_text(unsigned long addr) { if (addr >= (unsigned long)_stext && addr <= (unsigned long)_etext) return 1; if (system_state == SYSTEM_BOOTING && - addr >= (unsigned long)_sinittext && - addr <= (unsigned long)_einittext) + init_kernel_text(addr)) return 1; return 0; } -__notrace_funcgraph int __kernel_text_address(unsigned long addr) +int __kernel_text_address(unsigned long addr) { if (core_kernel_text(addr)) return 1; - return __module_text_address(addr) != NULL; + if (is_module_text_address(addr)) + return 1; + /* + * There might be init symbols in saved stacktraces. + * Give those symbols a chance to be printed in + * backtraces (such as lockdep traces). + * + * Since we are after the module-symbols check, there's + * no danger of address overlap: + */ + if (init_kernel_text(addr)) + return 1; + return 0; } int kernel_text_address(unsigned long addr) { if (core_kernel_text(addr)) return 1; - return module_text_address(addr) != NULL; + return is_module_text_address(addr); } /* @@ -81,5 +111,5 @@ int func_ptr_is_kernel_text(void *ptr) addr = (unsigned long) dereference_function_descriptor(ptr); if (core_kernel_text(addr)) return 1; - return module_text_address(addr) != NULL; + return is_module_text_address(addr); } diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 9ebf77968871..343acecae629 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -17,6 +17,7 @@ #include <linux/kernel_stat.h> #include <linux/rculist.h> #include <linux/hash.h> +#include <trace/irq.h> #include <linux/bootmem.h> #include "internals.h" @@ -338,6 +339,9 @@ irqreturn_t no_action(int cpl, void *dev_id) return IRQ_NONE; } +DEFINE_TRACE(irq_handler_entry); +DEFINE_TRACE(irq_handler_exit); + /** * handle_IRQ_event - irq action chain handler * @irq: the interrupt number @@ -356,7 +360,9 @@ irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action) local_irq_enable_in_hardirq(); do { + trace_irq_handler_entry(irq, action); ret = action->handler(irq, action->dev_id); + trace_irq_handler_exit(irq, action, ret); if (ret == IRQ_HANDLED) status |= action->flags; retval |= ret; diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 7b8b0f21a5b1..374faf9bfdc7 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -161,6 +161,25 @@ unsigned long kallsyms_lookup_name(const char *name) return module_kallsyms_lookup_name(name); } +int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, + unsigned long), + void *data) +{ + char namebuf[KSYM_NAME_LEN]; + unsigned long i; + unsigned int off; + int ret; + + for (i = 0, off = 0; i < kallsyms_num_syms; i++) { + off = kallsyms_expand_symbol(off, namebuf); + ret = fn(data, namebuf, NULL, kallsyms_addresses[i]); + if (ret != 0) + return ret; + } + return module_kallsyms_on_each_symbol(fn, data); +} +EXPORT_SYMBOL_GPL(kallsyms_on_each_symbol); + static unsigned long get_symbol_pos(unsigned long addr, unsigned long *symbolsize, unsigned long *offset) diff --git a/kernel/kmod.c b/kernel/kmod.c index f0c8f545180d..b750675251e5 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -50,7 +50,8 @@ static struct workqueue_struct *khelper_wq; char modprobe_path[KMOD_PATH_LEN] = "/sbin/modprobe"; /** - * request_module - try to load a kernel module + * __request_module - try to load a kernel module + * @wait: wait (or not) for the operation to complete * @fmt: printf style format string for the name of the module * @...: arguments as specified in the format string * @@ -63,7 +64,7 @@ char modprobe_path[KMOD_PATH_LEN] = "/sbin/modprobe"; * If module auto-loading support is disabled then this function * becomes a no-operation. */ -int request_module(const char *fmt, ...) +int __request_module(bool wait, const char *fmt, ...) { va_list args; char module_name[MODULE_NAME_LEN]; @@ -108,11 +109,12 @@ int request_module(const char *fmt, ...) return -ENOMEM; } - ret = call_usermodehelper(modprobe_path, argv, envp, 1); + ret = call_usermodehelper(modprobe_path, argv, envp, + wait ? UMH_WAIT_PROC : UMH_WAIT_EXEC); atomic_dec(&kmod_concurrent); return ret; } -EXPORT_SYMBOL(request_module); +EXPORT_SYMBOL(__request_module); #endif /* CONFIG_MODULES */ struct subprocess_info { diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 7ba8cd9845cb..5016bfb682b9 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -43,6 +43,7 @@ #include <linux/seq_file.h> #include <linux/debugfs.h> #include <linux/kdebug.h> +#include <linux/memory.h> #include <asm-generic/sections.h> #include <asm/cacheflush.h> @@ -699,9 +700,10 @@ int __kprobes register_kprobe(struct kprobe *p) goto out; } + mutex_lock(&text_mutex); ret = arch_prepare_kprobe(p); if (ret) - goto out; + goto out_unlock_text; INIT_HLIST_NODE(&p->hlist); hlist_add_head_rcu(&p->hlist, @@ -710,6 +712,8 @@ int __kprobes register_kprobe(struct kprobe *p) if (kprobe_enabled) arch_arm_kprobe(p); +out_unlock_text: + mutex_unlock(&text_mutex); out: mutex_unlock(&kprobe_mutex); @@ -746,8 +750,11 @@ valid_p: * enabled and not gone - otherwise, the breakpoint would * already have been removed. We save on flushing icache. */ - if (kprobe_enabled && !kprobe_gone(old_p)) + if (kprobe_enabled && !kprobe_gone(old_p)) { + mutex_lock(&text_mutex); arch_disarm_kprobe(p); + mutex_unlock(&text_mutex); + } hlist_del_rcu(&old_p->hlist); } else { if (p->break_handler && !kprobe_gone(p)) @@ -912,10 +919,8 @@ static int __kprobes pre_handler_kretprobe(struct kprobe *p, ri->rp = rp; ri->task = current; - if (rp->entry_handler && rp->entry_handler(ri, regs)) { - spin_unlock_irqrestore(&rp->lock, flags); + if (rp->entry_handler && rp->entry_handler(ri, regs)) return 0; - } arch_prepare_kretprobe(ri, regs); @@ -1280,12 +1285,14 @@ static void __kprobes enable_all_kprobes(void) if (kprobe_enabled) goto already_enabled; + mutex_lock(&text_mutex); for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry_rcu(p, node, head, hlist) if (!kprobe_gone(p)) arch_arm_kprobe(p); } + mutex_unlock(&text_mutex); kprobe_enabled = true; printk(KERN_INFO "Kprobes globally enabled\n"); @@ -1310,6 +1317,7 @@ static void __kprobes disable_all_kprobes(void) kprobe_enabled = false; printk(KERN_INFO "Kprobes globally disabled\n"); + mutex_lock(&text_mutex); for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry_rcu(p, node, head, hlist) { @@ -1318,6 +1326,7 @@ static void __kprobes disable_all_kprobes(void) } } + mutex_unlock(&text_mutex); mutex_unlock(&kprobe_mutex); /* Allow all currently running kprobes to complete */ synchronize_sched(); diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 3673a3f44d9d..81b5f33970b8 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -42,6 +42,7 @@ #include <linux/hash.h> #include <linux/ftrace.h> #include <linux/stringify.h> +#include <trace/lockdep.h> #include <asm/sections.h> @@ -433,13 +434,6 @@ atomic_t nr_find_usage_forwards_checks; atomic_t nr_find_usage_forwards_recursions; atomic_t nr_find_usage_backwards_checks; atomic_t nr_find_usage_backwards_recursions; -# define debug_atomic_inc(ptr) atomic_inc(ptr) -# define debug_atomic_dec(ptr) atomic_dec(ptr) -# define debug_atomic_read(ptr) atomic_read(ptr) -#else -# define debug_atomic_inc(ptr) do { } while (0) -# define debug_atomic_dec(ptr) do { } while (0) -# define debug_atomic_read(ptr) 0 #endif /* @@ -1900,9 +1894,9 @@ print_irq_inversion_bug(struct task_struct *curr, struct lock_class *other, curr->comm, task_pid_nr(curr)); print_lock(this); if (forwards) - printk("but this lock took another, %s-irq-unsafe lock in the past:\n", irqclass); + printk("but this lock took another, %s-unsafe lock in the past:\n", irqclass); else - printk("but this lock was taken by another, %s-irq-safe lock in the past:\n", irqclass); + printk("but this lock was taken by another, %s-safe lock in the past:\n", irqclass); print_lock_name(other); printk("\n\nand interrupts could create inverse lock ordering between them.\n\n"); @@ -2015,7 +2009,8 @@ typedef int (*check_usage_f)(struct task_struct *, struct held_lock *, enum lock_usage_bit bit, const char *name); static int -mark_lock_irq(struct task_struct *curr, struct held_lock *this, int new_bit) +mark_lock_irq(struct task_struct *curr, struct held_lock *this, + enum lock_usage_bit new_bit) { int excl_bit = exclusive_bit(new_bit); int read = new_bit & 1; @@ -2043,7 +2038,7 @@ mark_lock_irq(struct task_struct *curr, struct held_lock *this, int new_bit) * states. */ if ((!read || !dir || STRICT_READ_CHECKS) && - !usage(curr, this, excl_bit, state_name(new_bit))) + !usage(curr, this, excl_bit, state_name(new_bit & ~1))) return 0; /* @@ -2929,6 +2924,8 @@ void lock_set_class(struct lockdep_map *lock, const char *name, } EXPORT_SYMBOL_GPL(lock_set_class); +DEFINE_TRACE(lock_acquire); + /* * We are not always called with irqs disabled - do that here, * and also avoid lockdep recursion: @@ -2939,6 +2936,8 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass, { unsigned long flags; + trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip); + if (unlikely(current->lockdep_recursion)) return; @@ -2953,11 +2952,15 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass, } EXPORT_SYMBOL_GPL(lock_acquire); +DEFINE_TRACE(lock_release); + void lock_release(struct lockdep_map *lock, int nested, unsigned long ip) { unsigned long flags; + trace_lock_release(lock, nested, ip); + if (unlikely(current->lockdep_recursion)) return; @@ -3106,10 +3109,14 @@ found_it: lock->ip = ip; } +DEFINE_TRACE(lock_contended); + void lock_contended(struct lockdep_map *lock, unsigned long ip) { unsigned long flags; + trace_lock_contended(lock, ip); + if (unlikely(!lock_stat)) return; @@ -3125,10 +3132,14 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip) } EXPORT_SYMBOL_GPL(lock_contended); +DEFINE_TRACE(lock_acquired); + void lock_acquired(struct lockdep_map *lock, unsigned long ip) { unsigned long flags; + trace_lock_acquired(lock, ip); + if (unlikely(!lock_stat)) return; diff --git a/kernel/module.c b/kernel/module.c index f77ac320d0b5..c268a771595c 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -68,7 +68,8 @@ /* List of modules, protected by module_mutex or preempt_disable * (delete uses stop_machine/add uses RCU list operations). */ -static DEFINE_MUTEX(module_mutex); +DEFINE_MUTEX(module_mutex); +EXPORT_SYMBOL_GPL(module_mutex); static LIST_HEAD(modules); /* Waiting for a module to finish initializing? */ @@ -76,7 +77,7 @@ static DECLARE_WAIT_QUEUE_HEAD(module_wq); static BLOCKING_NOTIFIER_HEAD(module_notify_list); -/* Bounds of module allocation, for speeding __module_text_address */ +/* Bounds of module allocation, for speeding __module_address */ static unsigned long module_addr_min = -1UL, module_addr_max = 0; int register_module_notifier(struct notifier_block * nb) @@ -186,17 +187,6 @@ extern const unsigned long __start___kcrctab_unused_gpl[]; #define symversion(base, idx) ((base != NULL) ? ((base) + (idx)) : NULL) #endif -struct symsearch { - const struct kernel_symbol *start, *stop; - const unsigned long *crcs; - enum { - NOT_GPL_ONLY, - GPL_ONLY, - WILL_BE_GPL_ONLY, - } licence; - bool unused; -}; - static bool each_symbol_in_section(const struct symsearch *arr, unsigned int arrsize, struct module *owner, @@ -217,10 +207,8 @@ static bool each_symbol_in_section(const struct symsearch *arr, } /* Returns true as soon as fn returns true, otherwise false. */ -static bool each_symbol(bool (*fn)(const struct symsearch *arr, - struct module *owner, - unsigned int symnum, void *data), - void *data) +bool each_symbol(bool (*fn)(const struct symsearch *arr, struct module *owner, + unsigned int symnum, void *data), void *data) { struct module *mod; const struct symsearch arr[] = { @@ -273,6 +261,7 @@ static bool each_symbol(bool (*fn)(const struct symsearch *arr, } return false; } +EXPORT_SYMBOL_GPL(each_symbol); struct find_symbol_arg { /* Input */ @@ -283,7 +272,7 @@ struct find_symbol_arg { /* Output */ struct module *owner; const unsigned long *crc; - unsigned long value; + const struct kernel_symbol *sym; }; static bool find_symbol_in_section(const struct symsearch *syms, @@ -324,17 +313,17 @@ static bool find_symbol_in_section(const struct symsearch *syms, fsa->owner = owner; fsa->crc = symversion(syms->crcs, symnum); - fsa->value = syms->start[symnum].value; + fsa->sym = &syms->start[symnum]; return true; } -/* Find a symbol, return value, (optional) crc and (optional) module - * which owns it */ -static unsigned long find_symbol(const char *name, - struct module **owner, - const unsigned long **crc, - bool gplok, - bool warn) +/* Find a symbol and return it, along with, (optional) crc and + * (optional) module which owns it */ +const struct kernel_symbol *find_symbol(const char *name, + struct module **owner, + const unsigned long **crc, + bool gplok, + bool warn) { struct find_symbol_arg fsa; @@ -347,15 +336,16 @@ static unsigned long find_symbol(const char *name, *owner = fsa.owner; if (crc) *crc = fsa.crc; - return fsa.value; + return fsa.sym; } DEBUGP("Failed to find symbol %s\n", name); - return -ENOENT; + return NULL; } +EXPORT_SYMBOL_GPL(find_symbol); /* Search for module by name: must hold module_mutex. */ -static struct module *find_module(const char *name) +struct module *find_module(const char *name) { struct module *mod; @@ -365,6 +355,7 @@ static struct module *find_module(const char *name) } return NULL; } +EXPORT_SYMBOL_GPL(find_module); #ifdef CONFIG_SMP @@ -641,7 +632,7 @@ static int already_uses(struct module *a, struct module *b) } /* Module a uses b */ -static int use_module(struct module *a, struct module *b) +int use_module(struct module *a, struct module *b) { struct module_use *use; int no_warn, err; @@ -674,6 +665,7 @@ static int use_module(struct module *a, struct module *b) no_warn = sysfs_create_link(b->holders_dir, &a->mkobj.kobj, a->name); return 1; } +EXPORT_SYMBOL_GPL(use_module); /* Clear the unload stuff of the module. */ static void module_unload_free(struct module *mod) @@ -894,7 +886,7 @@ void __symbol_put(const char *symbol) struct module *owner; preempt_disable(); - if (IS_ERR_VALUE(find_symbol(symbol, &owner, NULL, true, false))) + if (!find_symbol(symbol, &owner, NULL, true, false)) BUG(); module_put(owner); preempt_enable(); @@ -908,8 +900,10 @@ void symbol_put_addr(void *addr) if (core_kernel_text((unsigned long)addr)) return; - if (!(modaddr = module_text_address((unsigned long)addr))) - BUG(); + /* module_text_address is safe here: we're supposed to have reference + * to module from symbol_get, so it can't go away. */ + modaddr = __module_text_address((unsigned long)addr); + BUG_ON(!modaddr); module_put(modaddr); } EXPORT_SYMBOL_GPL(symbol_put_addr); @@ -949,10 +943,11 @@ static inline void module_unload_free(struct module *mod) { } -static inline int use_module(struct module *a, struct module *b) +int use_module(struct module *a, struct module *b) { return strong_try_module_get(b) == 0; } +EXPORT_SYMBOL_GPL(use_module); static inline void module_unload_init(struct module *mod) { @@ -995,12 +990,12 @@ static struct module_attribute *modinfo_attrs[] = { static const char vermagic[] = VERMAGIC_STRING; -static int try_to_force_load(struct module *mod, const char *symname) +static int try_to_force_load(struct module *mod, const char *reason) { #ifdef CONFIG_MODULE_FORCE_LOAD if (!test_taint(TAINT_FORCED_MODULE)) - printk("%s: no version for \"%s\" found: kernel tainted.\n", - mod->name, symname); + printk(KERN_WARNING "%s: %s: kernel tainted.\n", + mod->name, reason); add_taint_module(mod, TAINT_FORCED_MODULE); return 0; #else @@ -1057,9 +1052,9 @@ static inline int check_modstruct_version(Elf_Shdr *sechdrs, { const unsigned long *crc; - if (IS_ERR_VALUE(find_symbol("struct_module", NULL, &crc, true, false))) + if (!find_symbol("module_layout", NULL, &crc, true, false)) BUG(); - return check_version(sechdrs, versindex, "struct_module", mod, crc); + return check_version(sechdrs, versindex, "module_layout", mod, crc); } /* First part is kernel version, which we ignore if module has crcs. */ @@ -1098,25 +1093,25 @@ static inline int same_magic(const char *amagic, const char *bmagic, /* Resolve a symbol for this module. I.e. if we find one, record usage. Must be holding module_mutex. */ -static unsigned long resolve_symbol(Elf_Shdr *sechdrs, - unsigned int versindex, - const char *name, - struct module *mod) +static const struct kernel_symbol *resolve_symbol(Elf_Shdr *sechdrs, + unsigned int versindex, + const char *name, + struct module *mod) { struct module *owner; - unsigned long ret; + const struct kernel_symbol *sym; const unsigned long *crc; - ret = find_symbol(name, &owner, &crc, + sym = find_symbol(name, &owner, &crc, !(mod->taints & (1 << TAINT_PROPRIETARY_MODULE)), true); - if (!IS_ERR_VALUE(ret)) { - /* use_module can fail due to OOM, - or module initialization or unloading */ + /* use_module can fail due to OOM, + or module initialization or unloading */ + if (sym) { if (!check_version(sechdrs, versindex, name, mod, crc) || !use_module(mod, owner)) - ret = -EINVAL; + sym = NULL; } - return ret; + return sym; } /* @@ -1491,6 +1486,9 @@ static void free_module(struct module *mod) /* Module unload stuff */ module_unload_free(mod); + /* Free any allocated parameters. */ + destroy_params(mod->kp, mod->num_kp); + /* release any pointers to mcount in this module */ ftrace_release(mod->module_core, mod->core_size); @@ -1513,17 +1511,15 @@ static void free_module(struct module *mod) void *__symbol_get(const char *symbol) { struct module *owner; - unsigned long value; + const struct kernel_symbol *sym; preempt_disable(); - value = find_symbol(symbol, &owner, NULL, true, true); - if (IS_ERR_VALUE(value)) - value = 0; - else if (strong_try_module_get(owner)) - value = 0; + sym = find_symbol(symbol, &owner, NULL, true, true); + if (sym && strong_try_module_get(owner)) + sym = NULL; preempt_enable(); - return (void *)value; + return sym ? (void *)sym->value : NULL; } EXPORT_SYMBOL_GPL(__symbol_get); @@ -1551,8 +1547,7 @@ static int verify_export_symbols(struct module *mod) for (i = 0; i < ARRAY_SIZE(arr); i++) { for (s = arr[i].sym; s < arr[i].sym + arr[i].num; s++) { - if (!IS_ERR_VALUE(find_symbol(s->name, &owner, - NULL, true, false))) { + if (find_symbol(s->name, &owner, NULL, true, false)) { printk(KERN_ERR "%s: exports duplicate symbol %s" " (owned by %s)\n", @@ -1576,6 +1571,7 @@ static int simplify_symbols(Elf_Shdr *sechdrs, unsigned long secbase; unsigned int i, n = sechdrs[symindex].sh_size / sizeof(Elf_Sym); int ret = 0; + const struct kernel_symbol *ksym; for (i = 1; i < n; i++) { switch (sym[i].st_shndx) { @@ -1595,13 +1591,14 @@ static int simplify_symbols(Elf_Shdr *sechdrs, break; case SHN_UNDEF: - sym[i].st_value - = resolve_symbol(sechdrs, versindex, - strtab + sym[i].st_name, mod); - + ksym = resolve_symbol(sechdrs, versindex, + strtab + sym[i].st_name, mod); /* Ok if resolved. */ - if (!IS_ERR_VALUE(sym[i].st_value)) + if (ksym) { + sym[i].st_value = ksym->value; break; + } + /* Ok if weak. */ if (ELF_ST_BIND(sym[i].st_info) == STB_WEAK) break; @@ -1676,8 +1673,7 @@ static void layout_sections(struct module *mod, if ((s->sh_flags & masks[m][0]) != masks[m][0] || (s->sh_flags & masks[m][1]) || s->sh_entsize != ~0UL - || strncmp(secstrings + s->sh_name, - ".init", 5) == 0) + || strstarts(secstrings + s->sh_name, ".init")) continue; s->sh_entsize = get_offset(mod, &mod->core_size, s, i); DEBUGP("\t%s\n", secstrings + s->sh_name); @@ -1694,8 +1690,7 @@ static void layout_sections(struct module *mod, if ((s->sh_flags & masks[m][0]) != masks[m][0] || (s->sh_flags & masks[m][1]) || s->sh_entsize != ~0UL - || strncmp(secstrings + s->sh_name, - ".init", 5) != 0) + || !strstarts(secstrings + s->sh_name, ".init")) continue; s->sh_entsize = (get_offset(mod, &mod->init_size, s, i) | INIT_OFFSET_MASK); @@ -1828,8 +1823,7 @@ static char elf_type(const Elf_Sym *sym, else return 'b'; } - if (strncmp(secstrings + sechdrs[sym->st_shndx].sh_name, - ".debug", strlen(".debug")) == 0) + if (strstarts(secstrings + sechdrs[sym->st_shndx].sh_name, ".debug")) return 'n'; return '?'; } @@ -1898,8 +1892,7 @@ static noinline struct module *load_module(void __user *umod, unsigned int symindex = 0; unsigned int strindex = 0; unsigned int modindex, versindex, infoindex, pcpuindex; - unsigned int num_kp, num_mcount; - struct kernel_param *kp; + unsigned int num_mcount; struct module *mod; long err = 0; void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */ @@ -1916,12 +1909,6 @@ static noinline struct module *load_module(void __user *umod, if (len > 64 * 1024 * 1024 || (hdr = vmalloc(len)) == NULL) return ERR_PTR(-ENOMEM); - /* Create stop_machine threads since the error path relies on - * a non-failing stop_machine call. */ - err = stop_machine_create(); - if (err) - goto free_hdr; - if (copy_from_user(hdr, umod, len) != 0) { err = -EFAULT; goto free_hdr; @@ -1962,9 +1949,12 @@ static noinline struct module *load_module(void __user *umod, } #ifndef CONFIG_MODULE_UNLOAD /* Don't load .exit sections */ - if (strncmp(secstrings+sechdrs[i].sh_name, ".exit", 5) == 0) + if (strstarts(secstrings+sechdrs[i].sh_name, ".exit")) sechdrs[i].sh_flags &= ~(unsigned long)SHF_ALLOC; #endif + /* Don't keep __versions around; it's just for loading. */ + if (strcmp(secstrings + sechdrs[i].sh_name, "__versions") == 0) + sechdrs[i].sh_flags &= ~(unsigned long)SHF_ALLOC; } modindex = find_sec(hdr, sechdrs, secstrings, @@ -2006,7 +1996,7 @@ static noinline struct module *load_module(void __user *umod, modmagic = get_modinfo(sechdrs, infoindex, "vermagic"); /* This is allowed: modprobe --force will invalidate it. */ if (!modmagic) { - err = try_to_force_load(mod, "magic"); + err = try_to_force_load(mod, "bad vermagic"); if (err) goto free_hdr; } else if (!same_magic(modmagic, vermagic, versindex)) { @@ -2144,8 +2134,8 @@ static noinline struct module *load_module(void __user *umod, /* Now we've got everything in the final locations, we can * find optional sections. */ - kp = section_objs(hdr, sechdrs, secstrings, "__param", sizeof(*kp), - &num_kp); + mod->kp = section_objs(hdr, sechdrs, secstrings, "__param", + sizeof(*mod->kp), &mod->num_kp); mod->syms = section_objs(hdr, sechdrs, secstrings, "__ksymtab", sizeof(*mod->syms), &mod->num_syms); mod->crcs = section_addr(hdr, sechdrs, secstrings, "__kcrctab"); @@ -2195,8 +2185,8 @@ static noinline struct module *load_module(void __user *umod, || (mod->num_unused_gpl_syms && !mod->unused_gpl_crcs) #endif ) { - printk(KERN_WARNING "%s: No versions for exported symbols.\n", mod->name); - err = try_to_force_load(mod, "nocrc"); + err = try_to_force_load(mod, + "no versions for exported symbols"); if (err) goto cleanup; } @@ -2291,11 +2281,11 @@ static noinline struct module *load_module(void __user *umod, */ list_add_rcu(&mod->list, &modules); - err = parse_args(mod->name, mod->args, kp, num_kp, NULL); + err = parse_args(mod->name, mod->args, mod->kp, mod->num_kp, NULL); if (err < 0) goto unlink; - err = mod_sysfs_setup(mod, kp, num_kp); + err = mod_sysfs_setup(mod, mod->kp, mod->num_kp); if (err < 0) goto unlink; add_sect_attrs(mod, hdr->e_shnum, secstrings, sechdrs); @@ -2304,12 +2294,13 @@ static noinline struct module *load_module(void __user *umod, /* Get rid of temporary copy */ vfree(hdr); - stop_machine_destroy(); /* Done! */ return mod; unlink: - stop_machine(__unlink_module, mod, NULL); + /* Unlink carefully: kallsyms could be walking list. */ + list_del_rcu(&mod->list); + synchronize_sched(); module_arch_cleanup(mod); cleanup: kobject_del(&mod->mkobj.kobj); @@ -2317,8 +2308,8 @@ static noinline struct module *load_module(void __user *umod, ftrace_release(mod->module_core, mod->core_size); free_unload: module_unload_free(mod); - free_init: #if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP) + free_init: percpu_modfree(mod->refptr); #endif module_free(mod, mod->module_init); @@ -2332,7 +2323,6 @@ static noinline struct module *load_module(void __user *umod, kfree(args); free_hdr: vfree(hdr); - stop_machine_destroy(); return ERR_PTR(err); truncated: @@ -2609,6 +2599,25 @@ unsigned long module_kallsyms_lookup_name(const char *name) preempt_enable(); return ret; } + +int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, + struct module *, unsigned long), + void *data) +{ + struct module *mod; + unsigned int i; + int ret; + + list_for_each_entry(mod, &modules, list) { + for (i = 0; i < mod->num_symtab; i++) { + ret = fn(data, mod->strtab + mod->symtab[i].st_name, + mod, mod->symtab[i].st_value); + if (ret != 0) + return ret; + } + } + return 0; +} #endif /* CONFIG_KALLSYMS */ static char *module_flags(struct module *mod, char *buf) @@ -2744,29 +2753,31 @@ const struct exception_table_entry *search_module_extables(unsigned long addr) } /* - * Is this a valid module address? + * is_module_address - is this address inside a module? + * @addr: the address to check. + * + * See is_module_text_address() if you simply want to see if the address + * is code (not data). */ -int is_module_address(unsigned long addr) +bool is_module_address(unsigned long addr) { - struct module *mod; + bool ret; preempt_disable(); - - list_for_each_entry_rcu(mod, &modules, list) { - if (within_module_core(addr, mod)) { - preempt_enable(); - return 1; - } - } - + ret = __module_address(addr) != NULL; preempt_enable(); - return 0; + return ret; } - -/* Is this a valid kernel address? */ -__notrace_funcgraph struct module *__module_text_address(unsigned long addr) +/* + * __module_address - get the module which contains an address. + * @addr: the address. + * + * Must be called with preempt disabled or module mutex held so that + * module doesn't get freed during this. + */ +struct module *__module_address(unsigned long addr) { struct module *mod; @@ -2774,22 +2785,51 @@ __notrace_funcgraph struct module *__module_text_address(unsigned long addr) return NULL; list_for_each_entry_rcu(mod, &modules, list) - if (within(addr, mod->module_init, mod->init_text_size) - || within(addr, mod->module_core, mod->core_text_size)) + if (within_module_core(addr, mod) + || within_module_init(addr, mod)) return mod; return NULL; } +EXPORT_SYMBOL_GPL(__module_address); -struct module *module_text_address(unsigned long addr) +/* + * is_module_text_address - is this address inside module code? + * @addr: the address to check. + * + * See is_module_address() if you simply want to see if the address is + * anywhere in a module. See kernel_text_address() for testing if an + * address corresponds to kernel or module code. + */ +bool is_module_text_address(unsigned long addr) { - struct module *mod; + bool ret; preempt_disable(); - mod = __module_text_address(addr); + ret = __module_text_address(addr) != NULL; preempt_enable(); + return ret; +} + +/* + * __module_text_address - get the module whose code contains an address. + * @addr: the address. + * + * Must be called with preempt disabled or module mutex held so that + * module doesn't get freed during this. + */ +struct module *__module_text_address(unsigned long addr) +{ + struct module *mod = __module_address(addr); + if (mod) { + /* Make sure it's within the text section. */ + if (!within(addr, mod->module_init, mod->init_text_size) + && !within(addr, mod->module_core, mod->core_text_size)) + mod = NULL; + } return mod; } +EXPORT_SYMBOL_GPL(__module_text_address); /* Don't grab lock, we're oopsing. */ void print_modules(void) @@ -2809,9 +2849,17 @@ void print_modules(void) } #ifdef CONFIG_MODVERSIONS -/* Generate the signature for struct module here, too, for modversions. */ -void struct_module(struct module *mod) { return; } -EXPORT_SYMBOL(struct_module); +/* Generate the signature for all relevant module structures here. + * If these change, we don't want to try to parse the module. */ +void module_layout(struct module *mod, + struct modversion_info *ver, + struct kernel_param *kp, + struct kernel_symbol *ks, + struct marker *marker, + struct tracepoint *tp) +{ +} +EXPORT_SYMBOL(module_layout); #endif #ifdef CONFIG_MARKERS diff --git a/kernel/panic.c b/kernel/panic.c index 32fe4eff1b89..3fd8c5bf8b39 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -8,19 +8,19 @@ * This function is used through-out the kernel (including mm and fs) * to indicate a major problem. */ +#include <linux/debug_locks.h> +#include <linux/interrupt.h> +#include <linux/kallsyms.h> +#include <linux/notifier.h> #include <linux/module.h> -#include <linux/sched.h> -#include <linux/delay.h> +#include <linux/random.h> #include <linux/reboot.h> -#include <linux/notifier.h> -#include <linux/init.h> +#include <linux/delay.h> +#include <linux/kexec.h> +#include <linux/sched.h> #include <linux/sysrq.h> -#include <linux/interrupt.h> +#include <linux/init.h> #include <linux/nmi.h> -#include <linux/kexec.h> -#include <linux/debug_locks.h> -#include <linux/random.h> -#include <linux/kallsyms.h> #include <linux/dmi.h> int panic_on_oops; @@ -52,19 +52,15 @@ EXPORT_SYMBOL(panic_blink); * * This function never returns. */ - NORET_TYPE void panic(const char * fmt, ...) { - long i; static char buf[1024]; va_list args; -#if defined(CONFIG_S390) - unsigned long caller = (unsigned long) __builtin_return_address(0); -#endif + long i; /* - * It's possible to come here directly from a panic-assertion and not - * have preempt disabled. Some functions called from here want + * It's possible to come here directly from a panic-assertion and + * not have preempt disabled. Some functions called from here want * preempt to be disabled. No point enabling it later though... */ preempt_disable(); @@ -77,7 +73,6 @@ NORET_TYPE void panic(const char * fmt, ...) #ifdef CONFIG_DEBUG_BUGVERBOSE dump_stack(); #endif - bust_spinlocks(0); /* * If we have crashed and we have a crash kernel loaded let it handle @@ -86,14 +81,12 @@ NORET_TYPE void panic(const char * fmt, ...) */ crash_kexec(NULL); -#ifdef CONFIG_SMP /* * Note smp_send_stop is the usual smp shutdown function, which * unfortunately means it may not be hardened to work in a panic * situation. */ smp_send_stop(); -#endif atomic_notifier_call_chain(&panic_notifier_list, 0, buf); @@ -102,19 +95,21 @@ NORET_TYPE void panic(const char * fmt, ...) if (panic_timeout > 0) { /* - * Delay timeout seconds before rebooting the machine. - * We can't use the "normal" timers since we just panicked.. - */ - printk(KERN_EMERG "Rebooting in %d seconds..",panic_timeout); + * Delay timeout seconds before rebooting the machine. + * We can't use the "normal" timers since we just panicked. + */ + printk(KERN_EMERG "Rebooting in %d seconds..", panic_timeout); + for (i = 0; i < panic_timeout*1000; ) { touch_nmi_watchdog(); i += panic_blink(i); mdelay(1); i++; } - /* This will not be a clean reboot, with everything - * shutting down. But if there is a chance of - * rebooting the system it will be rebooted. + /* + * This will not be a clean reboot, with everything + * shutting down. But if there is a chance of + * rebooting the system it will be rebooted. */ emergency_restart(); } @@ -127,38 +122,44 @@ NORET_TYPE void panic(const char * fmt, ...) } #endif #if defined(CONFIG_S390) - disabled_wait(caller); + { + unsigned long caller; + + caller = (unsigned long)__builtin_return_address(0); + disabled_wait(caller); + } #endif local_irq_enable(); - for (i = 0;;) { + for (i = 0; ; ) { touch_softlockup_watchdog(); i += panic_blink(i); mdelay(1); i++; } + bust_spinlocks(0); } EXPORT_SYMBOL(panic); struct tnt { - u8 bit; - char true; - char false; + u8 bit; + char true; + char false; }; static const struct tnt tnts[] = { - { TAINT_PROPRIETARY_MODULE, 'P', 'G' }, - { TAINT_FORCED_MODULE, 'F', ' ' }, - { TAINT_UNSAFE_SMP, 'S', ' ' }, - { TAINT_FORCED_RMMOD, 'R', ' ' }, - { TAINT_MACHINE_CHECK, 'M', ' ' }, - { TAINT_BAD_PAGE, 'B', ' ' }, - { TAINT_USER, 'U', ' ' }, - { TAINT_DIE, 'D', ' ' }, - { TAINT_OVERRIDDEN_ACPI_TABLE, 'A', ' ' }, - { TAINT_WARN, 'W', ' ' }, - { TAINT_CRAP, 'C', ' ' }, + { TAINT_PROPRIETARY_MODULE, 'P', 'G' }, + { TAINT_FORCED_MODULE, 'F', ' ' }, + { TAINT_UNSAFE_SMP, 'S', ' ' }, + { TAINT_FORCED_RMMOD, 'R', ' ' }, + { TAINT_MACHINE_CHECK, 'M', ' ' }, + { TAINT_BAD_PAGE, 'B', ' ' }, + { TAINT_USER, 'U', ' ' }, + { TAINT_DIE, 'D', ' ' }, + { TAINT_OVERRIDDEN_ACPI_TABLE, 'A', ' ' }, + { TAINT_WARN, 'W', ' ' }, + { TAINT_CRAP, 'C', ' ' }, }; /** @@ -195,7 +196,8 @@ const char *print_tainted(void) *s = 0; } else snprintf(buf, sizeof(buf), "Not tainted"); - return(buf); + + return buf; } int test_taint(unsigned flag) @@ -211,7 +213,8 @@ unsigned long get_taint(void) void add_taint(unsigned flag) { - debug_locks = 0; /* can't trust the integrity of the kernel anymore */ + /* can't trust the integrity of the kernel anymore: */ + debug_locks = 0; set_bit(flag, &tainted_mask); } EXPORT_SYMBOL(add_taint); @@ -266,8 +269,8 @@ static void do_oops_enter_exit(void) } /* - * Return true if the calling CPU is allowed to print oops-related info. This - * is a bit racy.. + * Return true if the calling CPU is allowed to print oops-related info. + * This is a bit racy.. */ int oops_may_print(void) { @@ -276,20 +279,22 @@ int oops_may_print(void) /* * Called when the architecture enters its oops handler, before it prints - * anything. If this is the first CPU to oops, and it's oopsing the first time - * then let it proceed. + * anything. If this is the first CPU to oops, and it's oopsing the first + * time then let it proceed. * - * This is all enabled by the pause_on_oops kernel boot option. We do all this - * to ensure that oopses don't scroll off the screen. It has the side-effect - * of preventing later-oopsing CPUs from mucking up the display, too. + * This is all enabled by the pause_on_oops kernel boot option. We do all + * this to ensure that oopses don't scroll off the screen. It has the + * side-effect of preventing later-oopsing CPUs from mucking up the display, + * too. * - * It turns out that the CPU which is allowed to print ends up pausing for the - * right duration, whereas all the other CPUs pause for twice as long: once in - * oops_enter(), once in oops_exit(). + * It turns out that the CPU which is allowed to print ends up pausing for + * the right duration, whereas all the other CPUs pause for twice as long: + * once in oops_enter(), once in oops_exit(). */ void oops_enter(void) { - debug_locks_off(); /* can't trust the integrity of the kernel anymore */ + /* can't trust the integrity of the kernel anymore: */ + debug_locks_off(); do_oops_enter_exit(); } diff --git a/kernel/params.c b/kernel/params.c index a1e3025b19a9..de273ec85bd2 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -24,6 +24,9 @@ #include <linux/err.h> #include <linux/slab.h> +/* We abuse the high bits of "perm" to record whether we kmalloc'ed. */ +#define KPARAM_KMALLOCED 0x80000000 + #if 0 #define DEBUGP printk #else @@ -217,7 +220,19 @@ int param_set_charp(const char *val, struct kernel_param *kp) return -ENOSPC; } - *(char **)kp->arg = (char *)val; + if (kp->perm & KPARAM_KMALLOCED) + kfree(*(char **)kp->arg); + + /* This is a hack. We can't need to strdup in early boot, and we + * don't need to; this mangled commandline is preserved. */ + if (slab_is_available()) { + kp->perm |= KPARAM_KMALLOCED; + *(char **)kp->arg = kstrdup(val, GFP_KERNEL); + if (!kp->arg) + return -ENOMEM; + } else + *(const char **)kp->arg = val; + return 0; } @@ -571,6 +586,15 @@ void module_param_sysfs_remove(struct module *mod) } #endif +void destroy_params(const struct kernel_param *params, unsigned num) +{ + unsigned int i; + + for (i = 0; i < num; i++) + if (params[i].perm & KPARAM_KMALLOCED) + kfree(*(char **)params[i].arg); +} + static void __init kernel_add_sysfs_param(const char *name, struct kernel_param *kparam, unsigned int name_skip) diff --git a/kernel/power/disk.c b/kernel/power/disk.c index f3db382c2b2d..5f21ab2bbcdf 100644 --- a/kernel/power/disk.c +++ b/kernel/power/disk.c @@ -289,7 +289,7 @@ static int create_image(int platform_mode) * hibernation_snapshot - quiesce devices and create the hibernation * snapshot image. * @platform_mode - if set, use the platform driver, if available, to - * prepare the platform frimware for the power transition. + * prepare the platform firmware for the power transition. * * Must be called with pm_mutex held */ @@ -412,7 +412,7 @@ static int resume_target_kernel(bool platform_mode) * hibernation_restore - quiesce devices and restore the hibernation * snapshot image. If successful, control returns in hibernation_snaphot() * @platform_mode - if set, use the platform driver, if available, to - * prepare the platform frimware for the transition. + * prepare the platform firmware for the transition. * * Must be called with pm_mutex held */ diff --git a/kernel/printk.c b/kernel/printk.c index a5f61a9acedb..5052b5497c67 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -1311,8 +1311,11 @@ EXPORT_SYMBOL(printk_ratelimit); bool printk_timed_ratelimit(unsigned long *caller_jiffies, unsigned int interval_msecs) { - if (*caller_jiffies == 0 || time_after(jiffies, *caller_jiffies)) { - *caller_jiffies = jiffies + msecs_to_jiffies(interval_msecs); + if (*caller_jiffies == 0 + || !time_in_range(jiffies, *caller_jiffies, + *caller_jiffies + + msecs_to_jiffies(interval_msecs))) { + *caller_jiffies = jiffies; return true; } return false; diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 5105f5a6a2ce..aaad0ec34194 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -687,8 +687,6 @@ SYSCALL_DEFINE4(ptrace, long, request, long, pid, long, addr, long, data) goto out_put_task_struct; ret = arch_ptrace(child, request, addr, data); - if (ret < 0) - goto out_put_task_struct; out_put_task_struct: put_task_struct(child); diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index cae8a059cf47..2c7b8457d0d2 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -122,6 +122,8 @@ static void rcu_barrier_func(void *type) } } +static inline void wait_migrated_callbacks(void); + /* * Orchestrate the specified type of RCU barrier, waiting for all * RCU callbacks of the specified type to complete. @@ -147,6 +149,7 @@ static void _rcu_barrier(enum rcu_barrier type) complete(&rcu_barrier_completion); wait_for_completion(&rcu_barrier_completion); mutex_unlock(&rcu_barrier_mutex); + wait_migrated_callbacks(); } /** @@ -176,9 +179,50 @@ void rcu_barrier_sched(void) } EXPORT_SYMBOL_GPL(rcu_barrier_sched); +static atomic_t rcu_migrate_type_count = ATOMIC_INIT(0); +static struct rcu_head rcu_migrate_head[3]; +static DECLARE_WAIT_QUEUE_HEAD(rcu_migrate_wq); + +static void rcu_migrate_callback(struct rcu_head *notused) +{ + if (atomic_dec_and_test(&rcu_migrate_type_count)) + wake_up(&rcu_migrate_wq); +} + +static inline void wait_migrated_callbacks(void) +{ + wait_event(rcu_migrate_wq, !atomic_read(&rcu_migrate_type_count)); +} + +static int __cpuinit rcu_barrier_cpu_hotplug(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + if (action == CPU_DYING) { + /* + * preempt_disable() in on_each_cpu() prevents stop_machine(), + * so when "on_each_cpu(rcu_barrier_func, (void *)type, 1);" + * returns, all online cpus have queued rcu_barrier_func(), + * and the dead cpu(if it exist) queues rcu_migrate_callback()s. + * + * These callbacks ensure _rcu_barrier() waits for all + * RCU callbacks of the specified type to complete. + */ + atomic_set(&rcu_migrate_type_count, 3); + call_rcu_bh(rcu_migrate_head, rcu_migrate_callback); + call_rcu_sched(rcu_migrate_head + 1, rcu_migrate_callback); + call_rcu(rcu_migrate_head + 2, rcu_migrate_callback); + } else if (action == CPU_POST_DEAD) { + /* rcu_migrate_head is protected by cpu_add_remove_lock */ + wait_migrated_callbacks(); + } + + return NOTIFY_OK; +} + void __init rcu_init(void) { __rcu_init(); + hotcpu_notifier(rcu_barrier_cpu_hotplug, 0); } void rcu_scheduler_starting(void) diff --git a/kernel/relay.c b/kernel/relay.c index e92db8c06acf..bc188549788f 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -677,9 +677,7 @@ int relay_late_setup_files(struct rchan *chan, */ for_each_online_cpu(i) { if (unlikely(!chan->buf[i])) { - printk(KERN_ERR "relay_late_setup_files: CPU %u " - "has no buffer, it must have!\n", i); - BUG(); + WARN_ONCE(1, KERN_ERR "CPU has no buffer!\n"); err = -EINVAL; break; } diff --git a/kernel/sched.c b/kernel/sched.c index 73513f4e19df..bec249885e17 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1110,7 +1110,7 @@ static void hrtick_start(struct rq *rq, u64 delay) if (rq == this_rq()) { hrtimer_restart(timer); } else if (!rq->hrtick_csd_pending) { - __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd); + __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 0); rq->hrtick_csd_pending = 1; } } @@ -3818,19 +3818,23 @@ find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle, */ #define MAX_PINNED_INTERVAL 512 +/* Working cpumask for load_balance and load_balance_newidle. */ +static DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask); + /* * Check this_cpu to ensure it is balanced within domain. Attempt to move * tasks if there is an imbalance. */ static int load_balance(int this_cpu, struct rq *this_rq, struct sched_domain *sd, enum cpu_idle_type idle, - int *balance, struct cpumask *cpus) + int *balance) { int ld_moved, all_pinned = 0, active_balance = 0, sd_idle = 0; struct sched_group *group; unsigned long imbalance; struct rq *busiest; unsigned long flags; + struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask); cpumask_setall(cpus); @@ -3985,8 +3989,7 @@ out: * this_rq is locked. */ static int -load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd, - struct cpumask *cpus) +load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd) { struct sched_group *group; struct rq *busiest = NULL; @@ -3994,6 +3997,7 @@ load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd, int ld_moved = 0; int sd_idle = 0; int all_pinned = 0; + struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask); cpumask_setall(cpus); @@ -4134,10 +4138,6 @@ static void idle_balance(int this_cpu, struct rq *this_rq) struct sched_domain *sd; int pulled_task = 0; unsigned long next_balance = jiffies + HZ; - cpumask_var_t tmpmask; - - if (!alloc_cpumask_var(&tmpmask, GFP_ATOMIC)) - return; for_each_domain(this_cpu, sd) { unsigned long interval; @@ -4148,7 +4148,7 @@ static void idle_balance(int this_cpu, struct rq *this_rq) if (sd->flags & SD_BALANCE_NEWIDLE) /* If we've pulled tasks over stop searching: */ pulled_task = load_balance_newidle(this_cpu, this_rq, - sd, tmpmask); + sd); interval = msecs_to_jiffies(sd->balance_interval); if (time_after(next_balance, sd->last_balance + interval)) @@ -4163,7 +4163,6 @@ static void idle_balance(int this_cpu, struct rq *this_rq) */ this_rq->next_balance = next_balance; } - free_cpumask_var(tmpmask); } /* @@ -4313,11 +4312,6 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle) unsigned long next_balance = jiffies + 60*HZ; int update_next_balance = 0; int need_serialize; - cpumask_var_t tmp; - - /* Fails alloc? Rebalancing probably not a priority right now. */ - if (!alloc_cpumask_var(&tmp, GFP_ATOMIC)) - return; for_each_domain(cpu, sd) { if (!(sd->flags & SD_LOAD_BALANCE)) @@ -4342,7 +4336,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle) } if (time_after_eq(jiffies, sd->last_balance + interval)) { - if (load_balance(cpu, rq, sd, idle, &balance, tmp)) { + if (load_balance(cpu, rq, sd, idle, &balance)) { /* * We've pulled tasks over so either we're no * longer idle, or one of our SMT siblings is @@ -4376,8 +4370,6 @@ out: */ if (likely(update_next_balance)) rq->next_balance = next_balance; - - free_cpumask_var(tmp); } /* @@ -4781,10 +4773,7 @@ void scheduler_tick(void) #endif } -#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \ - defined(CONFIG_PREEMPT_TRACER)) - -static inline unsigned long get_parent_ip(unsigned long addr) +unsigned long get_parent_ip(unsigned long addr) { if (in_lock_functions(addr)) { addr = CALLER_ADDR2; @@ -4794,6 +4783,9 @@ static inline unsigned long get_parent_ip(unsigned long addr) return addr; } +#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \ + defined(CONFIG_PREEMPT_TRACER)) + void __kprobes add_preempt_count(int val) { #ifdef CONFIG_DEBUG_PREEMPT @@ -7728,7 +7720,7 @@ cpu_to_core_group(int cpu, const struct cpumask *cpu_map, { int group; - cpumask_and(mask, &per_cpu(cpu_sibling_map, cpu), cpu_map); + cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map); group = cpumask_first(mask); if (sg) *sg = &per_cpu(sched_group_core, group).sg; @@ -7757,7 +7749,7 @@ cpu_to_phys_group(int cpu, const struct cpumask *cpu_map, cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map); group = cpumask_first(mask); #elif defined(CONFIG_SCHED_SMT) - cpumask_and(mask, &per_cpu(cpu_sibling_map, cpu), cpu_map); + cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map); group = cpumask_first(mask); #else group = cpu; @@ -8100,7 +8092,7 @@ static int __build_sched_domains(const struct cpumask *cpu_map, SD_INIT(sd, SIBLING); set_domain_attribute(sd, attr); cpumask_and(sched_domain_span(sd), - &per_cpu(cpu_sibling_map, i), cpu_map); + topology_thread_cpumask(i), cpu_map); sd->parent = p; p->child = sd; cpu_to_cpu_group(i, cpu_map, &sd->groups, tmpmask); @@ -8111,7 +8103,7 @@ static int __build_sched_domains(const struct cpumask *cpu_map, /* Set up CPU (sibling) groups */ for_each_cpu(i, cpu_map) { cpumask_and(this_sibling_map, - &per_cpu(cpu_sibling_map, i), cpu_map); + topology_thread_cpumask(i), cpu_map); if (i != cpumask_first(this_sibling_map)) continue; @@ -8787,6 +8779,9 @@ void __init sched_init(void) #ifdef CONFIG_USER_SCHED alloc_size *= 2; #endif +#ifdef CONFIG_CPUMASK_OFFSTACK + alloc_size += num_possible_cpus() * cpumask_size(); +#endif /* * As sched_init() is called before page_alloc is setup, * we use alloc_bootmem(). @@ -8824,6 +8819,12 @@ void __init sched_init(void) ptr += nr_cpu_ids * sizeof(void **); #endif /* CONFIG_USER_SCHED */ #endif /* CONFIG_RT_GROUP_SCHED */ +#ifdef CONFIG_CPUMASK_OFFSTACK + for_each_possible_cpu(i) { + per_cpu(load_balance_tmpmask, i) = (void *)ptr; + ptr += cpumask_size(); + } +#endif /* CONFIG_CPUMASK_OFFSTACK */ } #ifdef CONFIG_SMP diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c index 390f33234bd0..819f17ac796e 100644 --- a/kernel/sched_clock.c +++ b/kernel/sched_clock.c @@ -25,6 +25,7 @@ * consistent between cpus (never more than 2 jiffies difference). */ #include <linux/spinlock.h> +#include <linux/hardirq.h> #include <linux/module.h> #include <linux/percpu.h> #include <linux/ktime.h> @@ -154,6 +155,17 @@ u64 sched_clock_cpu(int cpu) return sched_clock(); scd = cpu_sdc(cpu); + + /* + * Normally this is not called in NMI context - but if it is, + * trying to do any locking here is totally lethal. + */ + if (unlikely(in_nmi())) + return scd->clock; + + if (unlikely(!sched_clock_running)) + return 0ull; + WARN_ON_ONCE(!irqs_disabled()); now = sched_clock(); diff --git a/kernel/smp.c b/kernel/smp.c index bbedbb7efe32..858baac568ee 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -2,40 +2,82 @@ * Generic helpers for smp ipi calls * * (C) Jens Axboe <jens.axboe@oracle.com> 2008 - * */ -#include <linux/init.h> -#include <linux/module.h> -#include <linux/percpu.h> #include <linux/rcupdate.h> #include <linux/rculist.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/percpu.h> +#include <linux/init.h> #include <linux/smp.h> +#include <linux/cpu.h> static DEFINE_PER_CPU(struct call_single_queue, call_single_queue); -static LIST_HEAD(call_function_queue); -__cacheline_aligned_in_smp DEFINE_SPINLOCK(call_function_lock); + +static struct { + struct list_head queue; + spinlock_t lock; +} call_function __cacheline_aligned_in_smp = + { + .queue = LIST_HEAD_INIT(call_function.queue), + .lock = __SPIN_LOCK_UNLOCKED(call_function.lock), + }; enum { - CSD_FLAG_WAIT = 0x01, - CSD_FLAG_ALLOC = 0x02, - CSD_FLAG_LOCK = 0x04, + CSD_FLAG_LOCK = 0x01, }; struct call_function_data { - struct call_single_data csd; - spinlock_t lock; - unsigned int refs; - struct rcu_head rcu_head; - unsigned long cpumask_bits[]; + struct call_single_data csd; + spinlock_t lock; + unsigned int refs; + cpumask_var_t cpumask; }; struct call_single_queue { - struct list_head list; - spinlock_t lock; + struct list_head list; + spinlock_t lock; +}; + +static DEFINE_PER_CPU(struct call_function_data, cfd_data) = { + .lock = __SPIN_LOCK_UNLOCKED(cfd_data.lock), +}; + +static int +hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu) +{ + long cpu = (long)hcpu; + struct call_function_data *cfd = &per_cpu(cfd_data, cpu); + + switch (action) { + case CPU_UP_PREPARE: + case CPU_UP_PREPARE_FROZEN: + if (!alloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL, + cpu_to_node(cpu))) + return NOTIFY_BAD; + break; + +#ifdef CONFIG_CPU_HOTPLUG + case CPU_UP_CANCELED: + case CPU_UP_CANCELED_FROZEN: + + case CPU_DEAD: + case CPU_DEAD_FROZEN: + free_cpumask_var(cfd->cpumask); + break; +#endif + }; + + return NOTIFY_OK; +} + +static struct notifier_block __cpuinitdata hotplug_cfd_notifier = { + .notifier_call = hotplug_cfd, }; static int __cpuinit init_call_single_data(void) { + void *cpu = (void *)(long)smp_processor_id(); int i; for_each_possible_cpu(i) { @@ -44,29 +86,63 @@ static int __cpuinit init_call_single_data(void) spin_lock_init(&q->lock); INIT_LIST_HEAD(&q->list); } + + hotplug_cfd(&hotplug_cfd_notifier, CPU_UP_PREPARE, cpu); + register_cpu_notifier(&hotplug_cfd_notifier); + return 0; } early_initcall(init_call_single_data); -static void csd_flag_wait(struct call_single_data *data) +/* + * csd_lock/csd_unlock used to serialize access to per-cpu csd resources + * + * For non-synchronous ipi calls the csd can still be in use by the + * previous function call. For multi-cpu calls its even more interesting + * as we'll have to ensure no other cpu is observing our csd. + */ +static void csd_lock_wait(struct call_single_data *data) { - /* Wait for response */ - do { - if (!(data->flags & CSD_FLAG_WAIT)) - break; + while (data->flags & CSD_FLAG_LOCK) cpu_relax(); - } while (1); +} + +static void csd_lock(struct call_single_data *data) +{ + csd_lock_wait(data); + data->flags = CSD_FLAG_LOCK; + + /* + * prevent CPU from reordering the above assignment + * to ->flags with any subsequent assignments to other + * fields of the specified call_single_data structure: + */ + smp_mb(); +} + +static void csd_unlock(struct call_single_data *data) +{ + WARN_ON(!(data->flags & CSD_FLAG_LOCK)); + + /* + * ensure we're all done before releasing data: + */ + smp_mb(); + + data->flags &= ~CSD_FLAG_LOCK; } /* - * Insert a previously allocated call_single_data element for execution - * on the given CPU. data must already have ->func, ->info, and ->flags set. + * Insert a previously allocated call_single_data element + * for execution on the given CPU. data must already have + * ->func, ->info, and ->flags set. */ -static void generic_exec_single(int cpu, struct call_single_data *data) +static +void generic_exec_single(int cpu, struct call_single_data *data, int wait) { struct call_single_queue *dst = &per_cpu(call_single_queue, cpu); - int wait = data->flags & CSD_FLAG_WAIT, ipi; unsigned long flags; + int ipi; spin_lock_irqsave(&dst->lock, flags); ipi = list_empty(&dst->list); @@ -74,24 +150,21 @@ static void generic_exec_single(int cpu, struct call_single_data *data) spin_unlock_irqrestore(&dst->lock, flags); /* - * Make the list addition visible before sending the ipi. + * The list addition should be visible before sending the IPI + * handler locks the list to pull the entry off it because of + * normal cache coherency rules implied by spinlocks. + * + * If IPIs can go out of order to the cache coherency protocol + * in an architecture, sufficient synchronisation should be added + * to arch code to make it appear to obey cache coherency WRT + * locking and barrier primitives. Generic code isn't really + * equipped to do the right thing... */ - smp_mb(); - if (ipi) arch_send_call_function_single_ipi(cpu); if (wait) - csd_flag_wait(data); -} - -static void rcu_free_call_data(struct rcu_head *head) -{ - struct call_function_data *data; - - data = container_of(head, struct call_function_data, rcu_head); - - kfree(data); + csd_lock_wait(data); } /* @@ -104,99 +177,83 @@ void generic_smp_call_function_interrupt(void) int cpu = get_cpu(); /* - * It's ok to use list_for_each_rcu() here even though we may delete - * 'pos', since list_del_rcu() doesn't clear ->next + * Ensure entry is visible on call_function_queue after we have + * entered the IPI. See comment in smp_call_function_many. + * If we don't have this, then we may miss an entry on the list + * and never get another IPI to process it. + */ + smp_mb(); + + /* + * It's ok to use list_for_each_rcu() here even though we may + * delete 'pos', since list_del_rcu() doesn't clear ->next */ - rcu_read_lock(); - list_for_each_entry_rcu(data, &call_function_queue, csd.list) { + list_for_each_entry_rcu(data, &call_function.queue, csd.list) { int refs; - if (!cpumask_test_cpu(cpu, to_cpumask(data->cpumask_bits))) + spin_lock(&data->lock); + if (!cpumask_test_cpu(cpu, data->cpumask)) { + spin_unlock(&data->lock); continue; + } + cpumask_clear_cpu(cpu, data->cpumask); + spin_unlock(&data->lock); data->csd.func(data->csd.info); spin_lock(&data->lock); - cpumask_clear_cpu(cpu, to_cpumask(data->cpumask_bits)); WARN_ON(data->refs == 0); - data->refs--; - refs = data->refs; + refs = --data->refs; + if (!refs) { + spin_lock(&call_function.lock); + list_del_rcu(&data->csd.list); + spin_unlock(&call_function.lock); + } spin_unlock(&data->lock); if (refs) continue; - spin_lock(&call_function_lock); - list_del_rcu(&data->csd.list); - spin_unlock(&call_function_lock); - - if (data->csd.flags & CSD_FLAG_WAIT) { - /* - * serialize stores to data with the flag clear - * and wakeup - */ - smp_wmb(); - data->csd.flags &= ~CSD_FLAG_WAIT; - } - if (data->csd.flags & CSD_FLAG_ALLOC) - call_rcu(&data->rcu_head, rcu_free_call_data); + csd_unlock(&data->csd); } - rcu_read_unlock(); put_cpu(); } /* - * Invoked by arch to handle an IPI for call function single. Must be called - * from the arch with interrupts disabled. + * Invoked by arch to handle an IPI for call function single. Must be + * called from the arch with interrupts disabled. */ void generic_smp_call_function_single_interrupt(void) { struct call_single_queue *q = &__get_cpu_var(call_single_queue); + unsigned int data_flags; LIST_HEAD(list); - /* - * Need to see other stores to list head for checking whether - * list is empty without holding q->lock - */ - smp_read_barrier_depends(); - while (!list_empty(&q->list)) { - unsigned int data_flags; - - spin_lock(&q->lock); - list_replace_init(&q->list, &list); - spin_unlock(&q->lock); - - while (!list_empty(&list)) { - struct call_single_data *data; - - data = list_entry(list.next, struct call_single_data, - list); - list_del(&data->list); - - /* - * 'data' can be invalid after this call if - * flags == 0 (when called through - * generic_exec_single(), so save them away before - * making the call. - */ - data_flags = data->flags; - - data->func(data->info); - - if (data_flags & CSD_FLAG_WAIT) { - smp_wmb(); - data->flags &= ~CSD_FLAG_WAIT; - } else if (data_flags & CSD_FLAG_LOCK) { - smp_wmb(); - data->flags &= ~CSD_FLAG_LOCK; - } else if (data_flags & CSD_FLAG_ALLOC) - kfree(data); - } + spin_lock(&q->lock); + list_replace_init(&q->list, &list); + spin_unlock(&q->lock); + + while (!list_empty(&list)) { + struct call_single_data *data; + + data = list_entry(list.next, struct call_single_data, list); + list_del(&data->list); + + /* + * 'data' can be invalid after this call if flags == 0 + * (when called through generic_exec_single()), + * so save them away before making the call: + */ + data_flags = data->flags; + + data->func(data->info); + /* - * See comment on outer loop + * Unlocked CSDs are valid through generic_exec_single(): */ - smp_read_barrier_depends(); + if (data_flags & CSD_FLAG_LOCK) + csd_unlock(data); } } @@ -215,65 +272,45 @@ static DEFINE_PER_CPU(struct call_single_data, csd_data); int smp_call_function_single(int cpu, void (*func) (void *info), void *info, int wait) { - struct call_single_data d; + struct call_single_data d = { + .flags = 0, + }; unsigned long flags; - /* prevent preemption and reschedule on another processor, - as well as CPU removal */ - int me = get_cpu(); + int this_cpu; int err = 0; + /* + * prevent preemption and reschedule on another processor, + * as well as CPU removal + */ + this_cpu = get_cpu(); + /* Can deadlock when called with interrupts disabled */ - WARN_ON(irqs_disabled()); + WARN_ON_ONCE(irqs_disabled() && !oops_in_progress); - if (cpu == me) { + if (cpu == this_cpu) { local_irq_save(flags); func(info); local_irq_restore(flags); - } else if ((unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) { - struct call_single_data *data; + } else { + if ((unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) { + struct call_single_data *data = &d; + + if (!wait) + data = &__get_cpu_var(csd_data); - if (!wait) { - /* - * We are calling a function on a single CPU - * and we are not going to wait for it to finish. - * We first try to allocate the data, but if we - * fail, we fall back to use a per cpu data to pass - * the information to that CPU. Since all callers - * of this code will use the same data, we must - * synchronize the callers to prevent a new caller - * from corrupting the data before the callee - * can access it. - * - * The CSD_FLAG_LOCK is used to let us know when - * the IPI handler is done with the data. - * The first caller will set it, and the callee - * will clear it. The next caller must wait for - * it to clear before we set it again. This - * will make sure the callee is done with the - * data before a new caller will use it. - */ - data = kmalloc(sizeof(*data), GFP_ATOMIC); - if (data) - data->flags = CSD_FLAG_ALLOC; - else { - data = &per_cpu(csd_data, me); - while (data->flags & CSD_FLAG_LOCK) - cpu_relax(); - data->flags = CSD_FLAG_LOCK; - } + csd_lock(data); + + data->func = func; + data->info = info; + generic_exec_single(cpu, data, wait); } else { - data = &d; - data->flags = CSD_FLAG_WAIT; + err = -ENXIO; /* CPU not online */ } - - data->func = func; - data->info = info; - generic_exec_single(cpu, data); - } else { - err = -ENXIO; /* CPU not online */ } put_cpu(); + return err; } EXPORT_SYMBOL(smp_call_function_single); @@ -283,23 +320,26 @@ EXPORT_SYMBOL(smp_call_function_single); * @cpu: The CPU to run on. * @data: Pre-allocated and setup data structure * - * Like smp_call_function_single(), but allow caller to pass in a pre-allocated - * data structure. Useful for embedding @data inside other structures, for - * instance. - * + * Like smp_call_function_single(), but allow caller to pass in a + * pre-allocated data structure. Useful for embedding @data inside + * other structures, for instance. */ -void __smp_call_function_single(int cpu, struct call_single_data *data) +void __smp_call_function_single(int cpu, struct call_single_data *data, + int wait) { + csd_lock(data); + /* Can deadlock when called with interrupts disabled */ - WARN_ON((data->flags & CSD_FLAG_WAIT) && irqs_disabled()); + WARN_ON_ONCE(wait && irqs_disabled() && !oops_in_progress); - generic_exec_single(cpu, data); + generic_exec_single(cpu, data, wait); } -/* FIXME: Shim for archs using old arch_send_call_function_ipi API. */ +/* Deprecated: shim for archs using old arch_send_call_function_ipi API. */ + #ifndef arch_send_call_function_ipi_mask -#define arch_send_call_function_ipi_mask(maskp) \ - arch_send_call_function_ipi(*(maskp)) +# define arch_send_call_function_ipi_mask(maskp) \ + arch_send_call_function_ipi(*(maskp)) #endif /** @@ -307,7 +347,8 @@ void __smp_call_function_single(int cpu, struct call_single_data *data) * @mask: The set of cpus to run on (only runs on online subset). * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. - * @wait: If true, wait (atomically) until function has completed on other CPUs. + * @wait: If true, wait (atomically) until function has completed + * on other CPUs. * * If @wait is true, then returns once @func has returned. Note that @wait * will be implicitly turned on in case of allocation failures, since @@ -318,27 +359,27 @@ void __smp_call_function_single(int cpu, struct call_single_data *data) * must be disabled when calling this function. */ void smp_call_function_many(const struct cpumask *mask, - void (*func)(void *), void *info, - bool wait) + void (*func)(void *), void *info, bool wait) { struct call_function_data *data; unsigned long flags; - int cpu, next_cpu; + int cpu, next_cpu, this_cpu = smp_processor_id(); /* Can deadlock when called with interrupts disabled */ - WARN_ON(irqs_disabled()); + WARN_ON_ONCE(irqs_disabled() && !oops_in_progress); - /* So, what's a CPU they want? Ignoring this one. */ + /* So, what's a CPU they want? Ignoring this one. */ cpu = cpumask_first_and(mask, cpu_online_mask); - if (cpu == smp_processor_id()) + if (cpu == this_cpu) cpu = cpumask_next_and(cpu, mask, cpu_online_mask); + /* No online cpus? We're done. */ if (cpu >= nr_cpu_ids) return; /* Do we have another CPU which isn't us? */ next_cpu = cpumask_next_and(cpu, mask, cpu_online_mask); - if (next_cpu == smp_processor_id()) + if (next_cpu == this_cpu) next_cpu = cpumask_next_and(next_cpu, mask, cpu_online_mask); /* Fastpath: do that cpu by itself. */ @@ -347,43 +388,40 @@ void smp_call_function_many(const struct cpumask *mask, return; } - data = kmalloc(sizeof(*data) + cpumask_size(), GFP_ATOMIC); - if (unlikely(!data)) { - /* Slow path. */ - for_each_online_cpu(cpu) { - if (cpu == smp_processor_id()) - continue; - if (cpumask_test_cpu(cpu, mask)) - smp_call_function_single(cpu, func, info, wait); - } - return; - } + data = &__get_cpu_var(cfd_data); + csd_lock(&data->csd); - spin_lock_init(&data->lock); - data->csd.flags = CSD_FLAG_ALLOC; - if (wait) - data->csd.flags |= CSD_FLAG_WAIT; + spin_lock_irqsave(&data->lock, flags); data->csd.func = func; data->csd.info = info; - cpumask_and(to_cpumask(data->cpumask_bits), mask, cpu_online_mask); - cpumask_clear_cpu(smp_processor_id(), to_cpumask(data->cpumask_bits)); - data->refs = cpumask_weight(to_cpumask(data->cpumask_bits)); + cpumask_and(data->cpumask, mask, cpu_online_mask); + cpumask_clear_cpu(this_cpu, data->cpumask); + data->refs = cpumask_weight(data->cpumask); - spin_lock_irqsave(&call_function_lock, flags); - list_add_tail_rcu(&data->csd.list, &call_function_queue); - spin_unlock_irqrestore(&call_function_lock, flags); + spin_lock(&call_function.lock); + /* + * Place entry at the _HEAD_ of the list, so that any cpu still + * observing the entry in generic_smp_call_function_interrupt() + * will not miss any other list entries: + */ + list_add_rcu(&data->csd.list, &call_function.queue); + spin_unlock(&call_function.lock); + + spin_unlock_irqrestore(&data->lock, flags); /* * Make the list addition visible before sending the ipi. + * (IPIs must obey or appear to obey normal Linux cache + * coherency rules -- see comment in generic_exec_single). */ smp_mb(); /* Send a message to all CPUs in the map */ - arch_send_call_function_ipi_mask(to_cpumask(data->cpumask_bits)); + arch_send_call_function_ipi_mask(data->cpumask); - /* optionally wait for the CPUs to complete */ + /* Optionally wait for the CPUs to complete */ if (wait) - csd_flag_wait(&data->csd); + csd_lock_wait(&data->csd); } EXPORT_SYMBOL(smp_call_function_many); @@ -391,7 +429,8 @@ EXPORT_SYMBOL(smp_call_function_many); * smp_call_function(): Run a function on all other CPUs. * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. - * @wait: If true, wait (atomically) until function has completed on other CPUs. + * @wait: If true, wait (atomically) until function has completed + * on other CPUs. * * Returns 0. * @@ -407,26 +446,27 @@ int smp_call_function(void (*func)(void *), void *info, int wait) preempt_disable(); smp_call_function_many(cpu_online_mask, func, info, wait); preempt_enable(); + return 0; } EXPORT_SYMBOL(smp_call_function); void ipi_call_lock(void) { - spin_lock(&call_function_lock); + spin_lock(&call_function.lock); } void ipi_call_unlock(void) { - spin_unlock(&call_function_lock); + spin_unlock(&call_function.lock); } void ipi_call_lock_irq(void) { - spin_lock_irq(&call_function_lock); + spin_lock_irq(&call_function.lock); } void ipi_call_unlock_irq(void) { - spin_unlock_irq(&call_function_lock); + spin_unlock_irq(&call_function.lock); } diff --git a/kernel/softirq.c b/kernel/softirq.c index 57d3f67f6f38..d105a82543d0 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -21,8 +21,10 @@ #include <linux/freezer.h> #include <linux/kthread.h> #include <linux/rcupdate.h> +#include <linux/ftrace.h> #include <linux/smp.h> #include <linux/tick.h> +#include <trace/irq.h> #include <asm/irq.h> /* @@ -52,6 +54,11 @@ static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp static DEFINE_PER_CPU(struct task_struct *, ksoftirqd); +char *softirq_to_name[NR_SOFTIRQS] = { + "HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", + "TASKLET", "SCHED", "HRTIMER", "RCU" +}; + /* * we cannot loop indefinitely here to avoid userspace starvation, * but we also don't want to introduce a worst case 1/HZ latency @@ -79,13 +86,23 @@ static void __local_bh_disable(unsigned long ip) WARN_ON_ONCE(in_irq()); raw_local_irq_save(flags); - add_preempt_count(SOFTIRQ_OFFSET); + /* + * The preempt tracer hooks into add_preempt_count and will break + * lockdep because it calls back into lockdep after SOFTIRQ_OFFSET + * is set and before current->softirq_enabled is cleared. + * We must manually increment preempt_count here and manually + * call the trace_preempt_off later. + */ + preempt_count() += SOFTIRQ_OFFSET; /* * Were softirqs turned off above: */ if (softirq_count() == SOFTIRQ_OFFSET) trace_softirqs_off(ip); raw_local_irq_restore(flags); + + if (preempt_count() == SOFTIRQ_OFFSET) + trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); } #else /* !CONFIG_TRACE_IRQFLAGS */ static inline void __local_bh_disable(unsigned long ip) @@ -169,6 +186,9 @@ EXPORT_SYMBOL(local_bh_enable_ip); */ #define MAX_SOFTIRQ_RESTART 10 +DEFINE_TRACE(softirq_entry); +DEFINE_TRACE(softirq_exit); + asmlinkage void __do_softirq(void) { struct softirq_action *h; @@ -180,7 +200,7 @@ asmlinkage void __do_softirq(void) account_system_vtime(current); __local_bh_disable((unsigned long)__builtin_return_address(0)); - trace_softirq_enter(); + lockdep_softirq_enter(); cpu = smp_processor_id(); restart: @@ -195,12 +215,14 @@ restart: if (pending & 1) { int prev_count = preempt_count(); + trace_softirq_entry(h, softirq_vec); h->action(h); - + trace_softirq_exit(h, softirq_vec); if (unlikely(prev_count != preempt_count())) { - printk(KERN_ERR "huh, entered softirq %td %p" + printk(KERN_ERR "huh, entered softirq %td %s %p" "with preempt_count %08x," " exited with %08x?\n", h - softirq_vec, + softirq_to_name[h - softirq_vec], h->action, prev_count, preempt_count()); preempt_count() = prev_count; } @@ -220,7 +242,7 @@ restart: if (pending) wakeup_softirqd(); - trace_softirq_exit(); + lockdep_softirq_exit(); account_system_vtime(current); _local_bh_enable(); @@ -496,7 +518,7 @@ static int __try_remote_softirq(struct call_single_data *cp, int cpu, int softir cp->flags = 0; cp->priv = softirq; - __smp_call_function_single(cpu, cp); + __smp_call_function_single(cpu, cp, 0); return 0; } return 1; diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 34e707e5ab87..2246141bda4d 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -9,6 +9,9 @@ config USER_STACKTRACE_SUPPORT config NOP_TRACER bool +config HAVE_FTRACE_NMI_ENTER + bool + config HAVE_FUNCTION_TRACER bool @@ -31,12 +34,20 @@ config HAVE_FTRACE_MCOUNT_RECORD config HAVE_HW_BRANCH_TRACER bool +config HAVE_FTRACE_SYSCALLS + bool + config TRACER_MAX_TRACE bool config RING_BUFFER bool +config FTRACE_NMI_ENTER + bool + depends on HAVE_FTRACE_NMI_ENTER + default y + config TRACING bool select DEBUG_FS @@ -44,13 +55,29 @@ config TRACING select STACKTRACE if STACKTRACE_SUPPORT select TRACEPOINTS select NOP_TRACER + select BINARY_PRINTF + +# +# Minimum requirements an architecture has to meet for us to +# be able to offer generic tracing facilities: +# +config TRACING_SUPPORT + bool + # PPC32 has no irqflags tracing support, but it can use most of the + # tracers anyway, they were tested to build and work. Note that new + # exceptions to this list aren't welcomed, better implement the + # irqflags tracing for your architecture. + depends on TRACE_IRQFLAGS_SUPPORT || PPC32 + depends on STACKTRACE_SUPPORT + default y + +if TRACING_SUPPORT menu "Tracers" config FUNCTION_TRACER bool "Kernel Function Tracer" depends on HAVE_FUNCTION_TRACER - depends on DEBUG_KERNEL select FRAME_POINTER select KALLSYMS select TRACING @@ -72,18 +99,16 @@ config FUNCTION_GRAPH_TRACER help Enable the kernel to trace a function at both its return and its entry. - It's first purpose is to trace the duration of functions and - draw a call graph for each thread with some informations like - the return value. - This is done by setting the current return address on the current - task structure into a stack of calls. + Its first purpose is to trace the duration of functions and + draw a call graph for each thread with some information like + the return value. This is done by setting the current return + address on the current task structure into a stack of calls. config IRQSOFF_TRACER bool "Interrupts-off Latency Tracer" default n depends on TRACE_IRQFLAGS_SUPPORT depends on GENERIC_TIME - depends on DEBUG_KERNEL select TRACE_IRQFLAGS select TRACING select TRACER_MAX_TRACE @@ -106,7 +131,6 @@ config PREEMPT_TRACER default n depends on GENERIC_TIME depends on PREEMPT - depends on DEBUG_KERNEL select TRACING select TRACER_MAX_TRACE help @@ -127,13 +151,13 @@ config SYSPROF_TRACER bool "Sysprof Tracer" depends on X86 select TRACING + select CONTEXT_SWITCH_TRACER help This tracer provides the trace needed by the 'Sysprof' userspace tool. config SCHED_TRACER bool "Scheduling Latency Tracer" - depends on DEBUG_KERNEL select TRACING select CONTEXT_SWITCH_TRACER select TRACER_MAX_TRACE @@ -143,16 +167,30 @@ config SCHED_TRACER config CONTEXT_SWITCH_TRACER bool "Trace process context switches" - depends on DEBUG_KERNEL select TRACING select MARKERS help This tracer gets called from the context switch and records all switching of tasks. +config EVENT_TRACER + bool "Trace various events in the kernel" + select TRACING + help + This tracer hooks to various trace points in the kernel + allowing the user to pick and choose which trace point they + want to trace. + +config FTRACE_SYSCALLS + bool "Trace syscalls" + depends on HAVE_FTRACE_SYSCALLS + select TRACING + select KALLSYMS + help + Basic tracer to catch the syscall entry and exit events. + config BOOT_TRACER bool "Trace boot initcalls" - depends on DEBUG_KERNEL select TRACING select CONTEXT_SWITCH_TRACER help @@ -165,13 +203,11 @@ config BOOT_TRACER representation of the delays during initcalls - but the raw /debug/tracing/trace text output is readable too. - ( Note that tracing self tests can't be enabled if this tracer is - selected, because the self-tests are an initcall as well and that - would invalidate the boot trace. ) + You must pass in ftrace=initcall to the kernel command line + to enable this on bootup. config TRACE_BRANCH_PROFILING bool "Trace likely/unlikely profiler" - depends on DEBUG_KERNEL select TRACING help This tracer profiles all the the likely and unlikely macros @@ -224,7 +260,6 @@ config BRANCH_TRACER config POWER_TRACER bool "Trace power consumption behavior" - depends on DEBUG_KERNEL depends on X86 select TRACING help @@ -236,7 +271,6 @@ config POWER_TRACER config STACK_TRACER bool "Trace max stack" depends on HAVE_FUNCTION_TRACER - depends on DEBUG_KERNEL select FUNCTION_TRACER select STACKTRACE select KALLSYMS @@ -266,11 +300,66 @@ config HW_BRANCH_TRACER This tracer records all branches on the system in a circular buffer giving access to the last N branches for each cpu. +config KMEMTRACE + bool "Trace SLAB allocations" + select TRACING + help + kmemtrace provides tracing for slab allocator functions, such as + kmalloc, kfree, kmem_cache_alloc, kmem_cache_free etc.. Collected + data is then fed to the userspace application in order to analyse + allocation hotspots, internal fragmentation and so on, making it + possible to see how well an allocator performs, as well as debug + and profile kernel code. + + This requires an userspace application to use. See + Documentation/vm/kmemtrace.txt for more information. + + Saying Y will make the kernel somewhat larger and slower. However, + if you disable kmemtrace at run-time or boot-time, the performance + impact is minimal (depending on the arch the kernel is built for). + + If unsure, say N. + +config WORKQUEUE_TRACER + bool "Trace workqueues" + select TRACING + help + The workqueue tracer provides some statistical informations + about each cpu workqueue thread such as the number of the + works inserted and executed since their creation. It can help + to evaluate the amount of work each of them have to perform. + For example it can help a developer to decide whether he should + choose a per cpu workqueue instead of a singlethreaded one. + +config BLK_DEV_IO_TRACE + bool "Support for tracing block io actions" + depends on SYSFS + depends on BLOCK + select RELAY + select DEBUG_FS + select TRACEPOINTS + select TRACING + select STACKTRACE + help + Say Y here if you want to be able to trace the block layer actions + on a given queue. Tracing allows you to see any traffic happening + on a block device queue. For more information (and the userspace + support tools needed), fetch the blktrace tools from: + + git://git.kernel.dk/blktrace.git + + Tracing also is possible using the ftrace interface, e.g.: + + echo 1 > /sys/block/sda/sda1/trace/enable + echo blk > /sys/kernel/debug/tracing/current_tracer + cat /sys/kernel/debug/tracing/trace_pipe + + If unsure, say N. + config DYNAMIC_FTRACE bool "enable/disable ftrace tracepoints dynamically" depends on FUNCTION_TRACER depends on HAVE_DYNAMIC_FTRACE - depends on DEBUG_KERNEL default y help This option will modify all the calls to ftrace dynamically @@ -296,7 +385,7 @@ config FTRACE_SELFTEST config FTRACE_STARTUP_TEST bool "Perform a startup test on ftrace" - depends on TRACING && DEBUG_KERNEL && !BOOT_TRACER + depends on TRACING select FTRACE_SELFTEST help This option performs a series of startup tests on ftrace. On bootup @@ -306,7 +395,7 @@ config FTRACE_STARTUP_TEST config MMIOTRACE bool "Memory mapped IO tracing" - depends on HAVE_MMIOTRACE_SUPPORT && DEBUG_KERNEL && PCI + depends on HAVE_MMIOTRACE_SUPPORT && PCI select TRACING help Mmiotrace traces Memory Mapped I/O access and is meant for @@ -328,3 +417,6 @@ config MMIOTRACE_TEST Say N, unless you absolutely know what you are doing. endmenu + +endif # TRACING_SUPPORT + diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index 349d5a93653f..2630f5121ec1 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -19,6 +19,10 @@ obj-$(CONFIG_FUNCTION_TRACER) += libftrace.o obj-$(CONFIG_RING_BUFFER) += ring_buffer.o obj-$(CONFIG_TRACING) += trace.o +obj-$(CONFIG_TRACING) += trace_clock.o +obj-$(CONFIG_TRACING) += trace_output.o +obj-$(CONFIG_TRACING) += trace_stat.o +obj-$(CONFIG_TRACING) += trace_printk.o obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o obj-$(CONFIG_SYSPROF_TRACER) += trace_sysprof.o obj-$(CONFIG_FUNCTION_TRACER) += trace_functions.o @@ -33,5 +37,14 @@ obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o obj-$(CONFIG_HW_BRANCH_TRACER) += trace_hw_branches.o obj-$(CONFIG_POWER_TRACER) += trace_power.o +obj-$(CONFIG_KMEMTRACE) += kmemtrace.o +obj-$(CONFIG_WORKQUEUE_TRACER) += trace_workqueue.o +obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o +obj-$(CONFIG_EVENT_TRACER) += trace_events.o +obj-$(CONFIG_EVENT_TRACER) += events.o +obj-$(CONFIG_EVENT_TRACER) += trace_export.o +obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o +obj-$(CONFIG_EVENT_PROFILE) += trace_event_profile.o +obj-$(CONFIG_EVENT_TRACER) += trace_events_filter.o libftrace-y := ftrace.o diff --git a/block/blktrace.c b/kernel/trace/blktrace.c index 028120a0965a..947c5b3f90c4 100644 --- a/block/blktrace.c +++ b/kernel/trace/blktrace.c @@ -24,15 +24,32 @@ #include <linux/debugfs.h> #include <linux/time.h> #include <trace/block.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> +#include "trace_output.h" static unsigned int blktrace_seq __read_mostly = 1; +static struct trace_array *blk_tr; +static bool blk_tracer_enabled __read_mostly; + +/* Select an alternative, minimalistic output than the original one */ +#define TRACE_BLK_OPT_CLASSIC 0x1 + +static struct tracer_opt blk_tracer_opts[] = { + /* Default disable the minimalistic output */ + { TRACER_OPT(blk_classic, TRACE_BLK_OPT_CLASSIC) }, + { } +}; + +static struct tracer_flags blk_tracer_flags = { + .val = 0, + .opts = blk_tracer_opts, +}; + /* Global reference count of probes */ -static DEFINE_MUTEX(blk_probe_mutex); static atomic_t blk_probes_ref = ATOMIC_INIT(0); -static int blk_register_tracepoints(void); +static void blk_register_tracepoints(void); static void blk_unregister_tracepoints(void); /* @@ -42,19 +59,39 @@ static void trace_note(struct blk_trace *bt, pid_t pid, int action, const void *data, size_t len) { struct blk_io_trace *t; + struct ring_buffer_event *event = NULL; + int pc = 0; + int cpu = smp_processor_id(); + bool blk_tracer = blk_tracer_enabled; + + if (blk_tracer) { + pc = preempt_count(); + event = trace_buffer_lock_reserve(blk_tr, TRACE_BLK, + sizeof(*t) + len, + 0, pc); + if (!event) + return; + t = ring_buffer_event_data(event); + goto record_it; + } + + if (!bt->rchan) + return; t = relay_reserve(bt->rchan, sizeof(*t) + len); if (t) { - const int cpu = smp_processor_id(); - t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION; t->time = ktime_to_ns(ktime_get()); +record_it: t->device = bt->dev; t->action = action; t->pid = pid; t->cpu = cpu; t->pdu_len = len; memcpy((void *) t + sizeof(*t), data, len); + + if (blk_tracer) + trace_buffer_unlock_commit(blk_tr, event, 0, pc); } } @@ -90,6 +127,10 @@ void __trace_note_message(struct blk_trace *bt, const char *fmt, ...) unsigned long flags; char *buf; + if (unlikely(bt->trace_state != Blktrace_running && + !blk_tracer_enabled)) + return; + local_irq_save(flags); buf = per_cpu_ptr(bt->msg_data, smp_processor_id()); va_start(args, fmt); @@ -117,11 +158,12 @@ static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector, /* * Data direction bit lookup */ -static u32 ddir_act[2] __read_mostly = { BLK_TC_ACT(BLK_TC_READ), BLK_TC_ACT(BLK_TC_WRITE) }; +static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ), + BLK_TC_ACT(BLK_TC_WRITE) }; /* The ilog2() calls fall out because they're constant */ -#define MASK_TC_BIT(rw, __name) ( (rw & (1 << BIO_RW_ ## __name)) << \ - (ilog2(BLK_TC_ ## __name) + BLK_TC_SHIFT - BIO_RW_ ## __name) ) +#define MASK_TC_BIT(rw, __name) ((rw & (1 << BIO_RW_ ## __name)) << \ + (ilog2(BLK_TC_ ## __name) + BLK_TC_SHIFT - BIO_RW_ ## __name)) /* * The worker for the various blk_add_trace*() types. Fills out a @@ -131,13 +173,15 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, int rw, u32 what, int error, int pdu_len, void *pdu_data) { struct task_struct *tsk = current; + struct ring_buffer_event *event = NULL; struct blk_io_trace *t; - unsigned long flags; + unsigned long flags = 0; unsigned long *sequence; pid_t pid; - int cpu; + int cpu, pc = 0; + bool blk_tracer = blk_tracer_enabled; - if (unlikely(bt->trace_state != Blktrace_running)) + if (unlikely(bt->trace_state != Blktrace_running && !blk_tracer)) return; what |= ddir_act[rw & WRITE]; @@ -150,6 +194,20 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, pid = tsk->pid; if (unlikely(act_log_check(bt, what, sector, pid))) return; + cpu = raw_smp_processor_id(); + + if (blk_tracer) { + tracing_record_cmdline(current); + + pc = preempt_count(); + event = trace_buffer_lock_reserve(blk_tr, TRACE_BLK, + sizeof(*t) + pdu_len, + 0, pc); + if (!event) + return; + t = ring_buffer_event_data(event); + goto record_it; + } /* * A word about the locking here - we disable interrupts to reserve @@ -163,23 +221,35 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, t = relay_reserve(bt->rchan, sizeof(*t) + pdu_len); if (t) { - cpu = smp_processor_id(); sequence = per_cpu_ptr(bt->sequence, cpu); t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION; t->sequence = ++(*sequence); t->time = ktime_to_ns(ktime_get()); +record_it: + /* + * These two are not needed in ftrace as they are in the + * generic trace_entry, filled by tracing_generic_entry_update, + * but for the trace_event->bin() synthesizer benefit we do it + * here too. + */ + t->cpu = cpu; + t->pid = pid; + t->sector = sector; t->bytes = bytes; t->action = what; - t->pid = pid; t->device = bt->dev; - t->cpu = cpu; t->error = error; t->pdu_len = pdu_len; if (pdu_len) memcpy((void *) t + sizeof(*t), pdu_data, pdu_len); + + if (blk_tracer) { + trace_buffer_unlock_commit(blk_tr, event, 0, pc); + return; + } } local_irq_restore(flags); @@ -188,7 +258,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, static struct dentry *blk_tree_root; static DEFINE_MUTEX(blk_tree_mutex); -static void blk_trace_cleanup(struct blk_trace *bt) +static void blk_trace_free(struct blk_trace *bt) { debugfs_remove(bt->msg_file); debugfs_remove(bt->dropped_file); @@ -196,10 +266,13 @@ static void blk_trace_cleanup(struct blk_trace *bt) free_percpu(bt->sequence); free_percpu(bt->msg_data); kfree(bt); - mutex_lock(&blk_probe_mutex); +} + +static void blk_trace_cleanup(struct blk_trace *bt) +{ + blk_trace_free(bt); if (atomic_dec_and_test(&blk_probes_ref)) blk_unregister_tracepoints(); - mutex_unlock(&blk_probe_mutex); } int blk_trace_remove(struct request_queue *q) @@ -210,8 +283,7 @@ int blk_trace_remove(struct request_queue *q) if (!bt) return -EINVAL; - if (bt->trace_state == Blktrace_setup || - bt->trace_state == Blktrace_stopped) + if (bt->trace_state != Blktrace_running) blk_trace_cleanup(bt); return 0; @@ -354,11 +426,11 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, if (buts->name[i] == '/') buts->name[i] = '_'; - ret = -ENOMEM; bt = kzalloc(sizeof(*bt), GFP_KERNEL); if (!bt) - goto err; + return -ENOMEM; + ret = -ENOMEM; bt->sequence = alloc_percpu(unsigned long); if (!bt->sequence) goto err; @@ -369,11 +441,15 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, ret = -ENOENT; + mutex_lock(&blk_tree_mutex); if (!blk_tree_root) { blk_tree_root = debugfs_create_dir("block", NULL); - if (!blk_tree_root) - return -ENOMEM; + if (!blk_tree_root) { + mutex_unlock(&blk_tree_mutex); + goto err; + } } + mutex_unlock(&blk_tree_mutex); dir = debugfs_create_dir(buts->name, blk_tree_root); @@ -385,7 +461,8 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, atomic_set(&bt->dropped, 0); ret = -EIO; - bt->dropped_file = debugfs_create_file("dropped", 0444, dir, bt, &blk_dropped_fops); + bt->dropped_file = debugfs_create_file("dropped", 0444, dir, bt, + &blk_dropped_fops); if (!bt->dropped_file) goto err; @@ -410,14 +487,6 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, bt->pid = buts->pid; bt->trace_state = Blktrace_setup; - mutex_lock(&blk_probe_mutex); - if (atomic_add_return(1, &blk_probes_ref) == 1) { - ret = blk_register_tracepoints(); - if (ret) - goto probe_err; - } - mutex_unlock(&blk_probe_mutex); - ret = -EBUSY; old_bt = xchg(&q->blk_trace, bt); if (old_bt) { @@ -425,22 +494,12 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, goto err; } + if (atomic_inc_return(&blk_probes_ref) == 1) + blk_register_tracepoints(); + return 0; -probe_err: - atomic_dec(&blk_probes_ref); - mutex_unlock(&blk_probe_mutex); err: - if (bt) { - if (bt->msg_file) - debugfs_remove(bt->msg_file); - if (bt->dropped_file) - debugfs_remove(bt->dropped_file); - free_percpu(bt->sequence); - free_percpu(bt->msg_data); - if (bt->rchan) - relay_close(bt->rchan); - kfree(bt); - } + blk_trace_free(bt); return ret; } @@ -467,10 +526,10 @@ EXPORT_SYMBOL_GPL(blk_trace_setup); int blk_trace_startstop(struct request_queue *q, int start) { - struct blk_trace *bt; int ret; + struct blk_trace *bt = q->blk_trace; - if ((bt = q->blk_trace) == NULL) + if (bt == NULL) return -EINVAL; /* @@ -503,7 +562,7 @@ EXPORT_SYMBOL_GPL(blk_trace_startstop); /** * blk_trace_ioctl: - handle the ioctls associated with tracing * @bdev: the block device - * @cmd: the ioctl cmd + * @cmd: the ioctl cmd * @arg: the argument data, if any * **/ @@ -606,12 +665,14 @@ static void blk_add_trace_rq_issue(struct request_queue *q, struct request *rq) blk_add_trace_rq(q, rq, BLK_TA_ISSUE); } -static void blk_add_trace_rq_requeue(struct request_queue *q, struct request *rq) +static void blk_add_trace_rq_requeue(struct request_queue *q, + struct request *rq) { blk_add_trace_rq(q, rq, BLK_TA_REQUEUE); } -static void blk_add_trace_rq_complete(struct request_queue *q, struct request *rq) +static void blk_add_trace_rq_complete(struct request_queue *q, + struct request *rq) { blk_add_trace_rq(q, rq, BLK_TA_COMPLETE); } @@ -648,12 +709,14 @@ static void blk_add_trace_bio_complete(struct request_queue *q, struct bio *bio) blk_add_trace_bio(q, bio, BLK_TA_COMPLETE); } -static void blk_add_trace_bio_backmerge(struct request_queue *q, struct bio *bio) +static void blk_add_trace_bio_backmerge(struct request_queue *q, + struct bio *bio) { blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE); } -static void blk_add_trace_bio_frontmerge(struct request_queue *q, struct bio *bio) +static void blk_add_trace_bio_frontmerge(struct request_queue *q, + struct bio *bio) { blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE); } @@ -663,7 +726,8 @@ static void blk_add_trace_bio_queue(struct request_queue *q, struct bio *bio) blk_add_trace_bio(q, bio, BLK_TA_QUEUE); } -static void blk_add_trace_getrq(struct request_queue *q, struct bio *bio, int rw) +static void blk_add_trace_getrq(struct request_queue *q, + struct bio *bio, int rw) { if (bio) blk_add_trace_bio(q, bio, BLK_TA_GETRQ); @@ -676,7 +740,8 @@ static void blk_add_trace_getrq(struct request_queue *q, struct bio *bio, int rw } -static void blk_add_trace_sleeprq(struct request_queue *q, struct bio *bio, int rw) +static void blk_add_trace_sleeprq(struct request_queue *q, + struct bio *bio, int rw) { if (bio) blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ); @@ -684,7 +749,8 @@ static void blk_add_trace_sleeprq(struct request_queue *q, struct bio *bio, int struct blk_trace *bt = q->blk_trace; if (bt) - __blk_add_trace(bt, 0, 0, rw, BLK_TA_SLEEPRQ, 0, 0, NULL); + __blk_add_trace(bt, 0, 0, rw, BLK_TA_SLEEPRQ, + 0, 0, NULL); } } @@ -795,7 +861,7 @@ void blk_add_driver_data(struct request_queue *q, } EXPORT_SYMBOL_GPL(blk_add_driver_data); -static int blk_register_tracepoints(void) +static void blk_register_tracepoints(void) { int ret; @@ -833,7 +899,6 @@ static int blk_register_tracepoints(void) WARN_ON(ret); ret = register_trace_block_remap(blk_add_trace_remap); WARN_ON(ret); - return 0; } static void blk_unregister_tracepoints(void) @@ -858,3 +923,627 @@ static void blk_unregister_tracepoints(void) tracepoint_synchronize_unregister(); } + +/* + * struct blk_io_tracer formatting routines + */ + +static void fill_rwbs(char *rwbs, const struct blk_io_trace *t) +{ + int i = 0; + int tc = t->action >> BLK_TC_SHIFT; + + if (t->action == BLK_TN_MESSAGE) { + rwbs[i++] = 'N'; + goto out; + } + + if (tc & BLK_TC_DISCARD) + rwbs[i++] = 'D'; + else if (tc & BLK_TC_WRITE) + rwbs[i++] = 'W'; + else if (t->bytes) + rwbs[i++] = 'R'; + else + rwbs[i++] = 'N'; + + if (tc & BLK_TC_AHEAD) + rwbs[i++] = 'A'; + if (tc & BLK_TC_BARRIER) + rwbs[i++] = 'B'; + if (tc & BLK_TC_SYNC) + rwbs[i++] = 'S'; + if (tc & BLK_TC_META) + rwbs[i++] = 'M'; +out: + rwbs[i] = '\0'; +} + +static inline +const struct blk_io_trace *te_blk_io_trace(const struct trace_entry *ent) +{ + return (const struct blk_io_trace *)ent; +} + +static inline const void *pdu_start(const struct trace_entry *ent) +{ + return te_blk_io_trace(ent) + 1; +} + +static inline u32 t_sec(const struct trace_entry *ent) +{ + return te_blk_io_trace(ent)->bytes >> 9; +} + +static inline unsigned long long t_sector(const struct trace_entry *ent) +{ + return te_blk_io_trace(ent)->sector; +} + +static inline __u16 t_error(const struct trace_entry *ent) +{ + return te_blk_io_trace(ent)->error; +} + +static __u64 get_pdu_int(const struct trace_entry *ent) +{ + const __u64 *val = pdu_start(ent); + return be64_to_cpu(*val); +} + +static void get_pdu_remap(const struct trace_entry *ent, + struct blk_io_trace_remap *r) +{ + const struct blk_io_trace_remap *__r = pdu_start(ent); + __u64 sector = __r->sector; + + r->device = be32_to_cpu(__r->device); + r->device_from = be32_to_cpu(__r->device_from); + r->sector = be64_to_cpu(sector); +} + +typedef int (blk_log_action_t) (struct trace_iterator *iter, const char *act); + +static int blk_log_action_classic(struct trace_iterator *iter, const char *act) +{ + char rwbs[6]; + unsigned long long ts = iter->ts; + unsigned long nsec_rem = do_div(ts, NSEC_PER_SEC); + unsigned secs = (unsigned long)ts; + const struct blk_io_trace *t = te_blk_io_trace(iter->ent); + + fill_rwbs(rwbs, t); + + return trace_seq_printf(&iter->seq, + "%3d,%-3d %2d %5d.%09lu %5u %2s %3s ", + MAJOR(t->device), MINOR(t->device), iter->cpu, + secs, nsec_rem, iter->ent->pid, act, rwbs); +} + +static int blk_log_action(struct trace_iterator *iter, const char *act) +{ + char rwbs[6]; + const struct blk_io_trace *t = te_blk_io_trace(iter->ent); + + fill_rwbs(rwbs, t); + return trace_seq_printf(&iter->seq, "%3d,%-3d %2s %3s ", + MAJOR(t->device), MINOR(t->device), act, rwbs); +} + +static int blk_log_generic(struct trace_seq *s, const struct trace_entry *ent) +{ + char cmd[TASK_COMM_LEN]; + + trace_find_cmdline(ent->pid, cmd); + + if (t_sec(ent)) + return trace_seq_printf(s, "%llu + %u [%s]\n", + t_sector(ent), t_sec(ent), cmd); + return trace_seq_printf(s, "[%s]\n", cmd); +} + +static int blk_log_with_error(struct trace_seq *s, + const struct trace_entry *ent) +{ + if (t_sec(ent)) + return trace_seq_printf(s, "%llu + %u [%d]\n", t_sector(ent), + t_sec(ent), t_error(ent)); + return trace_seq_printf(s, "%llu [%d]\n", t_sector(ent), t_error(ent)); +} + +static int blk_log_remap(struct trace_seq *s, const struct trace_entry *ent) +{ + struct blk_io_trace_remap r = { .device = 0, }; + + get_pdu_remap(ent, &r); + return trace_seq_printf(s, "%llu + %u <- (%d,%d) %llu\n", + t_sector(ent), + t_sec(ent), MAJOR(r.device), MINOR(r.device), + (unsigned long long)r.sector); +} + +static int blk_log_plug(struct trace_seq *s, const struct trace_entry *ent) +{ + char cmd[TASK_COMM_LEN]; + + trace_find_cmdline(ent->pid, cmd); + + return trace_seq_printf(s, "[%s]\n", cmd); +} + +static int blk_log_unplug(struct trace_seq *s, const struct trace_entry *ent) +{ + char cmd[TASK_COMM_LEN]; + + trace_find_cmdline(ent->pid, cmd); + + return trace_seq_printf(s, "[%s] %llu\n", cmd, get_pdu_int(ent)); +} + +static int blk_log_split(struct trace_seq *s, const struct trace_entry *ent) +{ + char cmd[TASK_COMM_LEN]; + + trace_find_cmdline(ent->pid, cmd); + + return trace_seq_printf(s, "%llu / %llu [%s]\n", t_sector(ent), + get_pdu_int(ent), cmd); +} + +static int blk_log_msg(struct trace_seq *s, const struct trace_entry *ent) +{ + int ret; + const struct blk_io_trace *t = te_blk_io_trace(ent); + + ret = trace_seq_putmem(s, t + 1, t->pdu_len); + if (ret) + return trace_seq_putc(s, '\n'); + return ret; +} + +/* + * struct tracer operations + */ + +static void blk_tracer_print_header(struct seq_file *m) +{ + if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CLASSIC)) + return; + seq_puts(m, "# DEV CPU TIMESTAMP PID ACT FLG\n" + "# | | | | | |\n"); +} + +static void blk_tracer_start(struct trace_array *tr) +{ + blk_tracer_enabled = true; + trace_flags &= ~TRACE_ITER_CONTEXT_INFO; +} + +static int blk_tracer_init(struct trace_array *tr) +{ + blk_tr = tr; + blk_tracer_start(tr); + return 0; +} + +static void blk_tracer_stop(struct trace_array *tr) +{ + blk_tracer_enabled = false; + trace_flags |= TRACE_ITER_CONTEXT_INFO; +} + +static void blk_tracer_reset(struct trace_array *tr) +{ + blk_tracer_stop(tr); +} + +static const struct { + const char *act[2]; + int (*print)(struct trace_seq *s, const struct trace_entry *ent); +} what2act[] = { + [__BLK_TA_QUEUE] = {{ "Q", "queue" }, blk_log_generic }, + [__BLK_TA_BACKMERGE] = {{ "M", "backmerge" }, blk_log_generic }, + [__BLK_TA_FRONTMERGE] = {{ "F", "frontmerge" }, blk_log_generic }, + [__BLK_TA_GETRQ] = {{ "G", "getrq" }, blk_log_generic }, + [__BLK_TA_SLEEPRQ] = {{ "S", "sleeprq" }, blk_log_generic }, + [__BLK_TA_REQUEUE] = {{ "R", "requeue" }, blk_log_with_error }, + [__BLK_TA_ISSUE] = {{ "D", "issue" }, blk_log_generic }, + [__BLK_TA_COMPLETE] = {{ "C", "complete" }, blk_log_with_error }, + [__BLK_TA_PLUG] = {{ "P", "plug" }, blk_log_plug }, + [__BLK_TA_UNPLUG_IO] = {{ "U", "unplug_io" }, blk_log_unplug }, + [__BLK_TA_UNPLUG_TIMER] = {{ "UT", "unplug_timer" }, blk_log_unplug }, + [__BLK_TA_INSERT] = {{ "I", "insert" }, blk_log_generic }, + [__BLK_TA_SPLIT] = {{ "X", "split" }, blk_log_split }, + [__BLK_TA_BOUNCE] = {{ "B", "bounce" }, blk_log_generic }, + [__BLK_TA_REMAP] = {{ "A", "remap" }, blk_log_remap }, +}; + +static enum print_line_t print_one_line(struct trace_iterator *iter, + bool classic) +{ + struct trace_seq *s = &iter->seq; + const struct blk_io_trace *t; + u16 what; + int ret; + bool long_act; + blk_log_action_t *log_action; + + t = te_blk_io_trace(iter->ent); + what = t->action & ((1 << BLK_TC_SHIFT) - 1); + long_act = !!(trace_flags & TRACE_ITER_VERBOSE); + log_action = classic ? &blk_log_action_classic : &blk_log_action; + + if (t->action == BLK_TN_MESSAGE) { + ret = log_action(iter, long_act ? "message" : "m"); + if (ret) + ret = blk_log_msg(s, iter->ent); + goto out; + } + + if (unlikely(what == 0 || what >= ARRAY_SIZE(what2act))) + ret = trace_seq_printf(s, "Bad pc action %x\n", what); + else { + ret = log_action(iter, what2act[what].act[long_act]); + if (ret) + ret = what2act[what].print(s, iter->ent); + } +out: + return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE; +} + +static enum print_line_t blk_trace_event_print(struct trace_iterator *iter, + int flags) +{ + if (!trace_print_context(iter)) + return TRACE_TYPE_PARTIAL_LINE; + + return print_one_line(iter, false); +} + +static int blk_trace_synthesize_old_trace(struct trace_iterator *iter) +{ + struct trace_seq *s = &iter->seq; + struct blk_io_trace *t = (struct blk_io_trace *)iter->ent; + const int offset = offsetof(struct blk_io_trace, sector); + struct blk_io_trace old = { + .magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION, + .time = iter->ts, + }; + + if (!trace_seq_putmem(s, &old, offset)) + return 0; + return trace_seq_putmem(s, &t->sector, + sizeof(old) - offset + t->pdu_len); +} + +static enum print_line_t +blk_trace_event_print_binary(struct trace_iterator *iter, int flags) +{ + return blk_trace_synthesize_old_trace(iter) ? + TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE; +} + +static enum print_line_t blk_tracer_print_line(struct trace_iterator *iter) +{ + if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CLASSIC)) + return TRACE_TYPE_UNHANDLED; + + return print_one_line(iter, true); +} + +static struct tracer blk_tracer __read_mostly = { + .name = "blk", + .init = blk_tracer_init, + .reset = blk_tracer_reset, + .start = blk_tracer_start, + .stop = blk_tracer_stop, + .print_header = blk_tracer_print_header, + .print_line = blk_tracer_print_line, + .flags = &blk_tracer_flags, +}; + +static struct trace_event trace_blk_event = { + .type = TRACE_BLK, + .trace = blk_trace_event_print, + .binary = blk_trace_event_print_binary, +}; + +static int __init init_blk_tracer(void) +{ + if (!register_ftrace_event(&trace_blk_event)) { + pr_warning("Warning: could not register block events\n"); + return 1; + } + + if (register_tracer(&blk_tracer) != 0) { + pr_warning("Warning: could not register the block tracer\n"); + unregister_ftrace_event(&trace_blk_event); + return 1; + } + + return 0; +} + +device_initcall(init_blk_tracer); + +static int blk_trace_remove_queue(struct request_queue *q) +{ + struct blk_trace *bt; + + bt = xchg(&q->blk_trace, NULL); + if (bt == NULL) + return -EINVAL; + + if (atomic_dec_and_test(&blk_probes_ref)) + blk_unregister_tracepoints(); + + blk_trace_free(bt); + return 0; +} + +/* + * Setup everything required to start tracing + */ +static int blk_trace_setup_queue(struct request_queue *q, dev_t dev) +{ + struct blk_trace *old_bt, *bt = NULL; + int ret = -ENOMEM; + + bt = kzalloc(sizeof(*bt), GFP_KERNEL); + if (!bt) + return -ENOMEM; + + bt->msg_data = __alloc_percpu(BLK_TN_MAX_MSG, __alignof__(char)); + if (!bt->msg_data) + goto free_bt; + + bt->dev = dev; + bt->act_mask = (u16)-1; + bt->end_lba = -1ULL; + + old_bt = xchg(&q->blk_trace, bt); + if (old_bt != NULL) { + (void)xchg(&q->blk_trace, old_bt); + ret = -EBUSY; + goto free_bt; + } + + if (atomic_inc_return(&blk_probes_ref) == 1) + blk_register_tracepoints(); + return 0; + +free_bt: + blk_trace_free(bt); + return ret; +} + +/* + * sysfs interface to enable and configure tracing + */ + +static ssize_t sysfs_blk_trace_attr_show(struct device *dev, + struct device_attribute *attr, + char *buf); +static ssize_t sysfs_blk_trace_attr_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count); +#define BLK_TRACE_DEVICE_ATTR(_name) \ + DEVICE_ATTR(_name, S_IRUGO | S_IWUSR, \ + sysfs_blk_trace_attr_show, \ + sysfs_blk_trace_attr_store) + +static BLK_TRACE_DEVICE_ATTR(enable); +static BLK_TRACE_DEVICE_ATTR(act_mask); +static BLK_TRACE_DEVICE_ATTR(pid); +static BLK_TRACE_DEVICE_ATTR(start_lba); +static BLK_TRACE_DEVICE_ATTR(end_lba); + +static struct attribute *blk_trace_attrs[] = { + &dev_attr_enable.attr, + &dev_attr_act_mask.attr, + &dev_attr_pid.attr, + &dev_attr_start_lba.attr, + &dev_attr_end_lba.attr, + NULL +}; + +struct attribute_group blk_trace_attr_group = { + .name = "trace", + .attrs = blk_trace_attrs, +}; + +static const struct { + int mask; + const char *str; +} mask_maps[] = { + { BLK_TC_READ, "read" }, + { BLK_TC_WRITE, "write" }, + { BLK_TC_BARRIER, "barrier" }, + { BLK_TC_SYNC, "sync" }, + { BLK_TC_QUEUE, "queue" }, + { BLK_TC_REQUEUE, "requeue" }, + { BLK_TC_ISSUE, "issue" }, + { BLK_TC_COMPLETE, "complete" }, + { BLK_TC_FS, "fs" }, + { BLK_TC_PC, "pc" }, + { BLK_TC_AHEAD, "ahead" }, + { BLK_TC_META, "meta" }, + { BLK_TC_DISCARD, "discard" }, + { BLK_TC_DRV_DATA, "drv_data" }, +}; + +static int blk_trace_str2mask(const char *str) +{ + int i; + int mask = 0; + char *s, *token; + + s = kstrdup(str, GFP_KERNEL); + if (s == NULL) + return -ENOMEM; + s = strstrip(s); + + while (1) { + token = strsep(&s, ","); + if (token == NULL) + break; + + if (*token == '\0') + continue; + + for (i = 0; i < ARRAY_SIZE(mask_maps); i++) { + if (strcasecmp(token, mask_maps[i].str) == 0) { + mask |= mask_maps[i].mask; + break; + } + } + if (i == ARRAY_SIZE(mask_maps)) { + mask = -EINVAL; + break; + } + } + kfree(s); + + return mask; +} + +static ssize_t blk_trace_mask2str(char *buf, int mask) +{ + int i; + char *p = buf; + + for (i = 0; i < ARRAY_SIZE(mask_maps); i++) { + if (mask & mask_maps[i].mask) { + p += sprintf(p, "%s%s", + (p == buf) ? "" : ",", mask_maps[i].str); + } + } + *p++ = '\n'; + + return p - buf; +} + +static struct request_queue *blk_trace_get_queue(struct block_device *bdev) +{ + if (bdev->bd_disk == NULL) + return NULL; + + return bdev_get_queue(bdev); +} + +static ssize_t sysfs_blk_trace_attr_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct hd_struct *p = dev_to_part(dev); + struct request_queue *q; + struct block_device *bdev; + ssize_t ret = -ENXIO; + + lock_kernel(); + bdev = bdget(part_devt(p)); + if (bdev == NULL) + goto out_unlock_kernel; + + q = blk_trace_get_queue(bdev); + if (q == NULL) + goto out_bdput; + + mutex_lock(&bdev->bd_mutex); + + if (attr == &dev_attr_enable) { + ret = sprintf(buf, "%u\n", !!q->blk_trace); + goto out_unlock_bdev; + } + + if (q->blk_trace == NULL) + ret = sprintf(buf, "disabled\n"); + else if (attr == &dev_attr_act_mask) + ret = blk_trace_mask2str(buf, q->blk_trace->act_mask); + else if (attr == &dev_attr_pid) + ret = sprintf(buf, "%u\n", q->blk_trace->pid); + else if (attr == &dev_attr_start_lba) + ret = sprintf(buf, "%llu\n", q->blk_trace->start_lba); + else if (attr == &dev_attr_end_lba) + ret = sprintf(buf, "%llu\n", q->blk_trace->end_lba); + +out_unlock_bdev: + mutex_unlock(&bdev->bd_mutex); +out_bdput: + bdput(bdev); +out_unlock_kernel: + unlock_kernel(); + return ret; +} + +static ssize_t sysfs_blk_trace_attr_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct block_device *bdev; + struct request_queue *q; + struct hd_struct *p; + u64 value; + ssize_t ret = -EINVAL; + + if (count == 0) + goto out; + + if (attr == &dev_attr_act_mask) { + if (sscanf(buf, "%llx", &value) != 1) { + /* Assume it is a list of trace category names */ + ret = blk_trace_str2mask(buf); + if (ret < 0) + goto out; + value = ret; + } + } else if (sscanf(buf, "%llu", &value) != 1) + goto out; + + ret = -ENXIO; + + lock_kernel(); + p = dev_to_part(dev); + bdev = bdget(part_devt(p)); + if (bdev == NULL) + goto out_unlock_kernel; + + q = blk_trace_get_queue(bdev); + if (q == NULL) + goto out_bdput; + + mutex_lock(&bdev->bd_mutex); + + if (attr == &dev_attr_enable) { + if (value) + ret = blk_trace_setup_queue(q, bdev->bd_dev); + else + ret = blk_trace_remove_queue(q); + goto out_unlock_bdev; + } + + ret = 0; + if (q->blk_trace == NULL) + ret = blk_trace_setup_queue(q, bdev->bd_dev); + + if (ret == 0) { + if (attr == &dev_attr_act_mask) + q->blk_trace->act_mask = value; + else if (attr == &dev_attr_pid) + q->blk_trace->pid = value; + else if (attr == &dev_attr_start_lba) + q->blk_trace->start_lba = value; + else if (attr == &dev_attr_end_lba) + q->blk_trace->end_lba = value; + } + +out_unlock_bdev: + mutex_unlock(&bdev->bd_mutex); +out_bdput: + bdput(bdev); +out_unlock_kernel: + unlock_kernel(); +out: + return ret ? ret : count; +} + diff --git a/kernel/trace/events.c b/kernel/trace/events.c new file mode 100644 index 000000000000..246f2aa6dc46 --- /dev/null +++ b/kernel/trace/events.c @@ -0,0 +1,14 @@ +/* + * This is the place to register all trace points as events. + */ + +#include <linux/stringify.h> + +#include <trace/trace_events.h> + +#include "trace_output.h" + +#include "trace_events_stage_1.h" +#include "trace_events_stage_2.h" +#include "trace_events_stage_3.h" + diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index fdf913dfc7e8..f1ed080406c3 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -27,6 +27,9 @@ #include <linux/sysctl.h> #include <linux/ctype.h> #include <linux/list.h> +#include <linux/hash.h> + +#include <trace/sched.h> #include <asm/ftrace.h> @@ -44,14 +47,14 @@ ftrace_kill(); \ } while (0) +/* hash bits for specific function selection */ +#define FTRACE_HASH_BITS 7 +#define FTRACE_FUNC_HASHSIZE (1 << FTRACE_HASH_BITS) + /* ftrace_enabled is a method to turn ftrace on or off */ int ftrace_enabled __read_mostly; static int last_ftrace_enabled; -/* set when tracing only a pid */ -struct pid *ftrace_pid_trace; -static struct pid * const ftrace_swapper_pid = &init_struct_pid; - /* Quick disabling of function tracer. */ int function_trace_stop; @@ -61,9 +64,7 @@ int function_trace_stop; */ static int ftrace_disabled __read_mostly; -static DEFINE_SPINLOCK(ftrace_lock); -static DEFINE_MUTEX(ftrace_sysctl_lock); -static DEFINE_MUTEX(ftrace_start_lock); +static DEFINE_MUTEX(ftrace_lock); static struct ftrace_ops ftrace_list_end __read_mostly = { @@ -134,9 +135,6 @@ static void ftrace_test_stop_func(unsigned long ip, unsigned long parent_ip) static int __register_ftrace_function(struct ftrace_ops *ops) { - /* should not be called from interrupt context */ - spin_lock(&ftrace_lock); - ops->next = ftrace_list; /* * We are entering ops into the ftrace_list but another @@ -172,18 +170,12 @@ static int __register_ftrace_function(struct ftrace_ops *ops) #endif } - spin_unlock(&ftrace_lock); - return 0; } static int __unregister_ftrace_function(struct ftrace_ops *ops) { struct ftrace_ops **p; - int ret = 0; - - /* should not be called from interrupt context */ - spin_lock(&ftrace_lock); /* * If we are removing the last function, then simply point @@ -192,17 +184,15 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops) if (ftrace_list == ops && ops->next == &ftrace_list_end) { ftrace_trace_function = ftrace_stub; ftrace_list = &ftrace_list_end; - goto out; + return 0; } for (p = &ftrace_list; *p != &ftrace_list_end; p = &(*p)->next) if (*p == ops) break; - if (*p != ops) { - ret = -1; - goto out; - } + if (*p != ops) + return -1; *p = (*p)->next; @@ -223,21 +213,15 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops) } } - out: - spin_unlock(&ftrace_lock); - - return ret; + return 0; } static void ftrace_update_pid_func(void) { ftrace_func_t func; - /* should not be called from interrupt context */ - spin_lock(&ftrace_lock); - if (ftrace_trace_function == ftrace_stub) - goto out; + return; func = ftrace_trace_function; @@ -254,23 +238,29 @@ static void ftrace_update_pid_func(void) #else __ftrace_trace_function = func; #endif - - out: - spin_unlock(&ftrace_lock); } +/* set when tracing only a pid */ +struct pid *ftrace_pid_trace; +static struct pid * const ftrace_swapper_pid = &init_struct_pid; + #ifdef CONFIG_DYNAMIC_FTRACE + #ifndef CONFIG_FTRACE_MCOUNT_RECORD # error Dynamic ftrace depends on MCOUNT_RECORD #endif -/* - * Since MCOUNT_ADDR may point to mcount itself, we do not want - * to get it confused by reading a reference in the code as we - * are parsing on objcopy output of text. Use a variable for - * it instead. - */ -static unsigned long mcount_addr = MCOUNT_ADDR; +static struct hlist_head ftrace_func_hash[FTRACE_FUNC_HASHSIZE] __read_mostly; + +struct ftrace_func_probe { + struct hlist_node node; + struct ftrace_probe_ops *ops; + unsigned long flags; + unsigned long ip; + void *data; + struct rcu_head rcu; +}; + enum { FTRACE_ENABLE_CALLS = (1 << 0), @@ -284,13 +274,13 @@ enum { static int ftrace_filtered; -static LIST_HEAD(ftrace_new_addrs); +static struct dyn_ftrace *ftrace_new_addrs; static DEFINE_MUTEX(ftrace_regex_lock); struct ftrace_page { struct ftrace_page *next; - unsigned long index; + int index; struct dyn_ftrace records[]; }; @@ -305,6 +295,19 @@ static struct ftrace_page *ftrace_pages; static struct dyn_ftrace *ftrace_free_records; +/* + * This is a double for. Do not use 'break' to break out of the loop, + * you must use a goto. + */ +#define do_for_each_ftrace_rec(pg, rec) \ + for (pg = ftrace_pages_start; pg; pg = pg->next) { \ + int _____i; \ + for (_____i = 0; _____i < pg->index; _____i++) { \ + rec = &pg->records[_____i]; + +#define while_for_each_ftrace_rec() \ + } \ + } #ifdef CONFIG_KPROBES @@ -338,7 +341,7 @@ static inline int record_frozen(struct dyn_ftrace *rec) static void ftrace_free_rec(struct dyn_ftrace *rec) { - rec->ip = (unsigned long)ftrace_free_records; + rec->freelist = ftrace_free_records; ftrace_free_records = rec; rec->flags |= FTRACE_FL_FREE; } @@ -349,23 +352,22 @@ void ftrace_release(void *start, unsigned long size) struct ftrace_page *pg; unsigned long s = (unsigned long)start; unsigned long e = s + size; - int i; if (ftrace_disabled || !start) return; - /* should not be called from interrupt context */ - spin_lock(&ftrace_lock); - - for (pg = ftrace_pages_start; pg; pg = pg->next) { - for (i = 0; i < pg->index; i++) { - rec = &pg->records[i]; - - if ((rec->ip >= s) && (rec->ip < e)) - ftrace_free_rec(rec); + mutex_lock(&ftrace_lock); + do_for_each_ftrace_rec(pg, rec) { + if ((rec->ip >= s) && (rec->ip < e)) { + /* + * rec->ip is changed in ftrace_free_rec() + * It should not between s and e if record was freed. + */ + FTRACE_WARN_ON(rec->flags & FTRACE_FL_FREE); + ftrace_free_rec(rec); } - } - spin_unlock(&ftrace_lock); + } while_for_each_ftrace_rec(); + mutex_unlock(&ftrace_lock); } static struct dyn_ftrace *ftrace_alloc_dyn_node(unsigned long ip) @@ -382,7 +384,7 @@ static struct dyn_ftrace *ftrace_alloc_dyn_node(unsigned long ip) return NULL; } - ftrace_free_records = (void *)rec->ip; + ftrace_free_records = rec->freelist; memset(rec, 0, sizeof(*rec)); return rec; } @@ -414,8 +416,8 @@ ftrace_record_ip(unsigned long ip) return NULL; rec->ip = ip; - - list_add(&rec->list, &ftrace_new_addrs); + rec->newlist = ftrace_new_addrs; + ftrace_new_addrs = rec; return rec; } @@ -461,10 +463,10 @@ static void ftrace_bug(int failed, unsigned long ip) static int __ftrace_replace_code(struct dyn_ftrace *rec, int enable) { - unsigned long ip, fl; unsigned long ftrace_addr; + unsigned long ip, fl; - ftrace_addr = (unsigned long)ftrace_caller; + ftrace_addr = (unsigned long)FTRACE_ADDR; ip = rec->ip; @@ -473,7 +475,7 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable) * it is not enabled then do nothing. * * If this record is not to be traced and - * it is enabled then disabled it. + * it is enabled then disable it. * */ if (rec->flags & FTRACE_FL_NOTRACE) { @@ -493,7 +495,7 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable) if (fl == (FTRACE_FL_FILTER | FTRACE_FL_ENABLED)) return 0; - /* Record is not filtered and is not enabled do nothing */ + /* Record is not filtered or enabled, do nothing */ if (!fl) return 0; @@ -515,7 +517,7 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable) } else { - /* if record is not enabled do nothing */ + /* if record is not enabled, do nothing */ if (!(rec->flags & FTRACE_FL_ENABLED)) return 0; @@ -531,41 +533,41 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable) static void ftrace_replace_code(int enable) { - int i, failed; struct dyn_ftrace *rec; struct ftrace_page *pg; + int failed; - for (pg = ftrace_pages_start; pg; pg = pg->next) { - for (i = 0; i < pg->index; i++) { - rec = &pg->records[i]; - - /* - * Skip over free records and records that have - * failed. - */ - if (rec->flags & FTRACE_FL_FREE || - rec->flags & FTRACE_FL_FAILED) - continue; + do_for_each_ftrace_rec(pg, rec) { + /* + * Skip over free records, records that have + * failed and not converted. + */ + if (rec->flags & FTRACE_FL_FREE || + rec->flags & FTRACE_FL_FAILED || + !(rec->flags & FTRACE_FL_CONVERTED)) + continue; - /* ignore updates to this record's mcount site */ - if (get_kprobe((void *)rec->ip)) { - freeze_record(rec); - continue; - } else { - unfreeze_record(rec); - } + /* ignore updates to this record's mcount site */ + if (get_kprobe((void *)rec->ip)) { + freeze_record(rec); + continue; + } else { + unfreeze_record(rec); + } - failed = __ftrace_replace_code(rec, enable); - if (failed && (rec->flags & FTRACE_FL_CONVERTED)) { - rec->flags |= FTRACE_FL_FAILED; - if ((system_state == SYSTEM_BOOTING) || - !core_kernel_text(rec->ip)) { - ftrace_free_rec(rec); - } else - ftrace_bug(failed, rec->ip); - } + failed = __ftrace_replace_code(rec, enable); + if (failed) { + rec->flags |= FTRACE_FL_FAILED; + if ((system_state == SYSTEM_BOOTING) || + !core_kernel_text(rec->ip)) { + ftrace_free_rec(rec); + } else { + ftrace_bug(failed, rec->ip); + /* Stop processing */ + return; + } } - } + } while_for_each_ftrace_rec(); } static int @@ -576,7 +578,7 @@ ftrace_code_disable(struct module *mod, struct dyn_ftrace *rec) ip = rec->ip; - ret = ftrace_make_nop(mod, rec, mcount_addr); + ret = ftrace_make_nop(mod, rec, MCOUNT_ADDR); if (ret) { ftrace_bug(ret, ip); rec->flags |= FTRACE_FL_FAILED; @@ -585,6 +587,24 @@ ftrace_code_disable(struct module *mod, struct dyn_ftrace *rec) return 1; } +/* + * archs can override this function if they must do something + * before the modifying code is performed. + */ +int __weak ftrace_arch_code_modify_prepare(void) +{ + return 0; +} + +/* + * archs can override this function if they must do something + * after the modifying code is performed. + */ +int __weak ftrace_arch_code_modify_post_process(void) +{ + return 0; +} + static int __ftrace_modify_code(void *data) { int *command = data; @@ -607,7 +627,17 @@ static int __ftrace_modify_code(void *data) static void ftrace_run_update_code(int command) { + int ret; + + ret = ftrace_arch_code_modify_prepare(); + FTRACE_WARN_ON(ret); + if (ret) + return; + stop_machine(__ftrace_modify_code, &command, NULL); + + ret = ftrace_arch_code_modify_post_process(); + FTRACE_WARN_ON(ret); } static ftrace_func_t saved_ftrace_func; @@ -631,13 +661,10 @@ static void ftrace_startup(int command) if (unlikely(ftrace_disabled)) return; - mutex_lock(&ftrace_start_lock); ftrace_start_up++; command |= FTRACE_ENABLE_CALLS; ftrace_startup_enable(command); - - mutex_unlock(&ftrace_start_lock); } static void ftrace_shutdown(int command) @@ -645,7 +672,6 @@ static void ftrace_shutdown(int command) if (unlikely(ftrace_disabled)) return; - mutex_lock(&ftrace_start_lock); ftrace_start_up--; if (!ftrace_start_up) command |= FTRACE_DISABLE_CALLS; @@ -656,11 +682,9 @@ static void ftrace_shutdown(int command) } if (!command || !ftrace_enabled) - goto out; + return; ftrace_run_update_code(command); - out: - mutex_unlock(&ftrace_start_lock); } static void ftrace_startup_sysctl(void) @@ -670,7 +694,6 @@ static void ftrace_startup_sysctl(void) if (unlikely(ftrace_disabled)) return; - mutex_lock(&ftrace_start_lock); /* Force update next time */ saved_ftrace_func = NULL; /* ftrace_start_up is true if we want ftrace running */ @@ -678,7 +701,6 @@ static void ftrace_startup_sysctl(void) command |= FTRACE_ENABLE_CALLS; ftrace_run_update_code(command); - mutex_unlock(&ftrace_start_lock); } static void ftrace_shutdown_sysctl(void) @@ -688,13 +710,11 @@ static void ftrace_shutdown_sysctl(void) if (unlikely(ftrace_disabled)) return; - mutex_lock(&ftrace_start_lock); /* ftrace_start_up is true if ftrace is running */ if (ftrace_start_up) command |= FTRACE_DISABLE_CALLS; ftrace_run_update_code(command); - mutex_unlock(&ftrace_start_lock); } static cycle_t ftrace_update_time; @@ -703,19 +723,21 @@ unsigned long ftrace_update_tot_cnt; static int ftrace_update_code(struct module *mod) { - struct dyn_ftrace *p, *t; + struct dyn_ftrace *p; cycle_t start, stop; start = ftrace_now(raw_smp_processor_id()); ftrace_update_cnt = 0; - list_for_each_entry_safe(p, t, &ftrace_new_addrs, list) { + while (ftrace_new_addrs) { /* If something went wrong, bail without enabling anything */ if (unlikely(ftrace_disabled)) return -1; - list_del_init(&p->list); + p = ftrace_new_addrs; + ftrace_new_addrs = p->newlist; + p->flags = 0L; /* convert record (i.e, patch mcount-call with NOP) */ if (ftrace_code_disable(mod, p)) { @@ -781,13 +803,16 @@ enum { FTRACE_ITER_CONT = (1 << 1), FTRACE_ITER_NOTRACE = (1 << 2), FTRACE_ITER_FAILURES = (1 << 3), + FTRACE_ITER_PRINTALL = (1 << 4), + FTRACE_ITER_HASH = (1 << 5), }; #define FTRACE_BUFF_MAX (KSYM_SYMBOL_LEN+4) /* room for wildcards */ struct ftrace_iterator { struct ftrace_page *pg; - unsigned idx; + int hidx; + int idx; unsigned flags; unsigned char buffer[FTRACE_BUFF_MAX+1]; unsigned buffer_idx; @@ -795,15 +820,89 @@ struct ftrace_iterator { }; static void * +t_hash_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct ftrace_iterator *iter = m->private; + struct hlist_node *hnd = v; + struct hlist_head *hhd; + + WARN_ON(!(iter->flags & FTRACE_ITER_HASH)); + + (*pos)++; + + retry: + if (iter->hidx >= FTRACE_FUNC_HASHSIZE) + return NULL; + + hhd = &ftrace_func_hash[iter->hidx]; + + if (hlist_empty(hhd)) { + iter->hidx++; + hnd = NULL; + goto retry; + } + + if (!hnd) + hnd = hhd->first; + else { + hnd = hnd->next; + if (!hnd) { + iter->hidx++; + goto retry; + } + } + + return hnd; +} + +static void *t_hash_start(struct seq_file *m, loff_t *pos) +{ + struct ftrace_iterator *iter = m->private; + void *p = NULL; + + iter->flags |= FTRACE_ITER_HASH; + + return t_hash_next(m, p, pos); +} + +static int t_hash_show(struct seq_file *m, void *v) +{ + struct ftrace_func_probe *rec; + struct hlist_node *hnd = v; + char str[KSYM_SYMBOL_LEN]; + + rec = hlist_entry(hnd, struct ftrace_func_probe, node); + + if (rec->ops->print) + return rec->ops->print(m, rec->ip, rec->ops, rec->data); + + kallsyms_lookup(rec->ip, NULL, NULL, NULL, str); + seq_printf(m, "%s:", str); + + kallsyms_lookup((unsigned long)rec->ops->func, NULL, NULL, NULL, str); + seq_printf(m, "%s", str); + + if (rec->data) + seq_printf(m, ":%p", rec->data); + seq_putc(m, '\n'); + + return 0; +} + +static void * t_next(struct seq_file *m, void *v, loff_t *pos) { struct ftrace_iterator *iter = m->private; struct dyn_ftrace *rec = NULL; + if (iter->flags & FTRACE_ITER_HASH) + return t_hash_next(m, v, pos); + (*pos)++; - /* should not be called from interrupt context */ - spin_lock(&ftrace_lock); + if (iter->flags & FTRACE_ITER_PRINTALL) + return NULL; + retry: if (iter->idx >= iter->pg->index) { if (iter->pg->next) { @@ -832,7 +931,6 @@ t_next(struct seq_file *m, void *v, loff_t *pos) goto retry; } } - spin_unlock(&ftrace_lock); return rec; } @@ -842,6 +940,23 @@ static void *t_start(struct seq_file *m, loff_t *pos) struct ftrace_iterator *iter = m->private; void *p = NULL; + mutex_lock(&ftrace_lock); + /* + * For set_ftrace_filter reading, if we have the filter + * off, we can short cut and just print out that all + * functions are enabled. + */ + if (iter->flags & FTRACE_ITER_FILTER && !ftrace_filtered) { + if (*pos > 0) + return t_hash_start(m, pos); + iter->flags |= FTRACE_ITER_PRINTALL; + (*pos)++; + return iter; + } + + if (iter->flags & FTRACE_ITER_HASH) + return t_hash_start(m, pos); + if (*pos > 0) { if (iter->idx < 0) return p; @@ -851,18 +966,31 @@ static void *t_start(struct seq_file *m, loff_t *pos) p = t_next(m, p, pos); + if (!p) + return t_hash_start(m, pos); + return p; } static void t_stop(struct seq_file *m, void *p) { + mutex_unlock(&ftrace_lock); } static int t_show(struct seq_file *m, void *v) { + struct ftrace_iterator *iter = m->private; struct dyn_ftrace *rec = v; char str[KSYM_SYMBOL_LEN]; + if (iter->flags & FTRACE_ITER_HASH) + return t_hash_show(m, v); + + if (iter->flags & FTRACE_ITER_PRINTALL) { + seq_printf(m, "#### all functions enabled ####\n"); + return 0; + } + if (!rec) return 0; @@ -941,23 +1069,16 @@ static void ftrace_filter_reset(int enable) struct ftrace_page *pg; struct dyn_ftrace *rec; unsigned long type = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE; - unsigned i; - /* should not be called from interrupt context */ - spin_lock(&ftrace_lock); + mutex_lock(&ftrace_lock); if (enable) ftrace_filtered = 0; - pg = ftrace_pages_start; - while (pg) { - for (i = 0; i < pg->index; i++) { - rec = &pg->records[i]; - if (rec->flags & FTRACE_FL_FAILED) - continue; - rec->flags &= ~type; - } - pg = pg->next; - } - spin_unlock(&ftrace_lock); + do_for_each_ftrace_rec(pg, rec) { + if (rec->flags & FTRACE_FL_FAILED) + continue; + rec->flags &= ~type; + } while_for_each_ftrace_rec(); + mutex_unlock(&ftrace_lock); } static int @@ -1008,16 +1129,6 @@ ftrace_notrace_open(struct inode *inode, struct file *file) return ftrace_regex_open(inode, file, 0); } -static ssize_t -ftrace_regex_read(struct file *file, char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - if (file->f_mode & FMODE_READ) - return seq_read(file, ubuf, cnt, ppos); - else - return -EPERM; -} - static loff_t ftrace_regex_lseek(struct file *file, loff_t offset, int origin) { @@ -1038,86 +1149,536 @@ enum { MATCH_END_ONLY, }; -static void -ftrace_match(unsigned char *buff, int len, int enable) +/* + * (static function - no need for kernel doc) + * + * Pass in a buffer containing a glob and this function will + * set search to point to the search part of the buffer and + * return the type of search it is (see enum above). + * This does modify buff. + * + * Returns enum type. + * search returns the pointer to use for comparison. + * not returns 1 if buff started with a '!' + * 0 otherwise. + */ +static int +ftrace_setup_glob(char *buff, int len, char **search, int *not) { - char str[KSYM_SYMBOL_LEN]; - char *search = NULL; - struct ftrace_page *pg; - struct dyn_ftrace *rec; int type = MATCH_FULL; - unsigned long flag = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE; - unsigned i, match = 0, search_len = 0; - int not = 0; + int i; if (buff[0] == '!') { - not = 1; + *not = 1; buff++; len--; - } + } else + *not = 0; + + *search = buff; for (i = 0; i < len; i++) { if (buff[i] == '*') { if (!i) { - search = buff + i + 1; + *search = buff + 1; type = MATCH_END_ONLY; - search_len = len - (i + 1); } else { - if (type == MATCH_END_ONLY) { + if (type == MATCH_END_ONLY) type = MATCH_MIDDLE_ONLY; - } else { - match = i; + else type = MATCH_FRONT_ONLY; - } buff[i] = 0; break; } } } - /* should not be called from interrupt context */ - spin_lock(&ftrace_lock); - if (enable) - ftrace_filtered = 1; - pg = ftrace_pages_start; - while (pg) { - for (i = 0; i < pg->index; i++) { - int matched = 0; - char *ptr; - - rec = &pg->records[i]; - if (rec->flags & FTRACE_FL_FAILED) + return type; +} + +static int ftrace_match(char *str, char *regex, int len, int type) +{ + int matched = 0; + char *ptr; + + switch (type) { + case MATCH_FULL: + if (strcmp(str, regex) == 0) + matched = 1; + break; + case MATCH_FRONT_ONLY: + if (strncmp(str, regex, len) == 0) + matched = 1; + break; + case MATCH_MIDDLE_ONLY: + if (strstr(str, regex)) + matched = 1; + break; + case MATCH_END_ONLY: + ptr = strstr(str, regex); + if (ptr && (ptr[len] == 0)) + matched = 1; + break; + } + + return matched; +} + +static int +ftrace_match_record(struct dyn_ftrace *rec, char *regex, int len, int type) +{ + char str[KSYM_SYMBOL_LEN]; + + kallsyms_lookup(rec->ip, NULL, NULL, NULL, str); + return ftrace_match(str, regex, len, type); +} + +static void ftrace_match_records(char *buff, int len, int enable) +{ + unsigned int search_len; + struct ftrace_page *pg; + struct dyn_ftrace *rec; + unsigned long flag; + char *search; + int type; + int not; + + flag = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE; + type = ftrace_setup_glob(buff, len, &search, ¬); + + search_len = strlen(search); + + mutex_lock(&ftrace_lock); + do_for_each_ftrace_rec(pg, rec) { + + if (rec->flags & FTRACE_FL_FAILED) + continue; + + if (ftrace_match_record(rec, search, search_len, type)) { + if (not) + rec->flags &= ~flag; + else + rec->flags |= flag; + } + /* + * Only enable filtering if we have a function that + * is filtered on. + */ + if (enable && (rec->flags & FTRACE_FL_FILTER)) + ftrace_filtered = 1; + } while_for_each_ftrace_rec(); + mutex_unlock(&ftrace_lock); +} + +static int +ftrace_match_module_record(struct dyn_ftrace *rec, char *mod, + char *regex, int len, int type) +{ + char str[KSYM_SYMBOL_LEN]; + char *modname; + + kallsyms_lookup(rec->ip, NULL, NULL, &modname, str); + + if (!modname || strcmp(modname, mod)) + return 0; + + /* blank search means to match all funcs in the mod */ + if (len) + return ftrace_match(str, regex, len, type); + else + return 1; +} + +static void ftrace_match_module_records(char *buff, char *mod, int enable) +{ + unsigned search_len = 0; + struct ftrace_page *pg; + struct dyn_ftrace *rec; + int type = MATCH_FULL; + char *search = buff; + unsigned long flag; + int not = 0; + + flag = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE; + + /* blank or '*' mean the same */ + if (strcmp(buff, "*") == 0) + buff[0] = 0; + + /* handle the case of 'dont filter this module' */ + if (strcmp(buff, "!") == 0 || strcmp(buff, "!*") == 0) { + buff[0] = 0; + not = 1; + } + + if (strlen(buff)) { + type = ftrace_setup_glob(buff, strlen(buff), &search, ¬); + search_len = strlen(search); + } + + mutex_lock(&ftrace_lock); + do_for_each_ftrace_rec(pg, rec) { + + if (rec->flags & FTRACE_FL_FAILED) + continue; + + if (ftrace_match_module_record(rec, mod, + search, search_len, type)) { + if (not) + rec->flags &= ~flag; + else + rec->flags |= flag; + } + if (enable && (rec->flags & FTRACE_FL_FILTER)) + ftrace_filtered = 1; + + } while_for_each_ftrace_rec(); + mutex_unlock(&ftrace_lock); +} + +/* + * We register the module command as a template to show others how + * to register the a command as well. + */ + +static int +ftrace_mod_callback(char *func, char *cmd, char *param, int enable) +{ + char *mod; + + /* + * cmd == 'mod' because we only registered this func + * for the 'mod' ftrace_func_command. + * But if you register one func with multiple commands, + * you can tell which command was used by the cmd + * parameter. + */ + + /* we must have a module name */ + if (!param) + return -EINVAL; + + mod = strsep(¶m, ":"); + if (!strlen(mod)) + return -EINVAL; + + ftrace_match_module_records(func, mod, enable); + return 0; +} + +static struct ftrace_func_command ftrace_mod_cmd = { + .name = "mod", + .func = ftrace_mod_callback, +}; + +static int __init ftrace_mod_cmd_init(void) +{ + return register_ftrace_command(&ftrace_mod_cmd); +} +device_initcall(ftrace_mod_cmd_init); + +static void +function_trace_probe_call(unsigned long ip, unsigned long parent_ip) +{ + struct ftrace_func_probe *entry; + struct hlist_head *hhd; + struct hlist_node *n; + unsigned long key; + int resched; + + key = hash_long(ip, FTRACE_HASH_BITS); + + hhd = &ftrace_func_hash[key]; + + if (hlist_empty(hhd)) + return; + + /* + * Disable preemption for these calls to prevent a RCU grace + * period. This syncs the hash iteration and freeing of items + * on the hash. rcu_read_lock is too dangerous here. + */ + resched = ftrace_preempt_disable(); + hlist_for_each_entry_rcu(entry, n, hhd, node) { + if (entry->ip == ip) + entry->ops->func(ip, parent_ip, &entry->data); + } + ftrace_preempt_enable(resched); +} + +static struct ftrace_ops trace_probe_ops __read_mostly = +{ + .func = function_trace_probe_call, +}; + +static int ftrace_probe_registered; + +static void __enable_ftrace_function_probe(void) +{ + int i; + + if (ftrace_probe_registered) + return; + + for (i = 0; i < FTRACE_FUNC_HASHSIZE; i++) { + struct hlist_head *hhd = &ftrace_func_hash[i]; + if (hhd->first) + break; + } + /* Nothing registered? */ + if (i == FTRACE_FUNC_HASHSIZE) + return; + + __register_ftrace_function(&trace_probe_ops); + ftrace_startup(0); + ftrace_probe_registered = 1; +} + +static void __disable_ftrace_function_probe(void) +{ + int i; + + if (!ftrace_probe_registered) + return; + + for (i = 0; i < FTRACE_FUNC_HASHSIZE; i++) { + struct hlist_head *hhd = &ftrace_func_hash[i]; + if (hhd->first) + return; + } + + /* no more funcs left */ + __unregister_ftrace_function(&trace_probe_ops); + ftrace_shutdown(0); + ftrace_probe_registered = 0; +} + + +static void ftrace_free_entry_rcu(struct rcu_head *rhp) +{ + struct ftrace_func_probe *entry = + container_of(rhp, struct ftrace_func_probe, rcu); + + if (entry->ops->free) + entry->ops->free(&entry->data); + kfree(entry); +} + + +int +register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, + void *data) +{ + struct ftrace_func_probe *entry; + struct ftrace_page *pg; + struct dyn_ftrace *rec; + int type, len, not; + unsigned long key; + int count = 0; + char *search; + + type = ftrace_setup_glob(glob, strlen(glob), &search, ¬); + len = strlen(search); + + /* we do not support '!' for function probes */ + if (WARN_ON(not)) + return -EINVAL; + + mutex_lock(&ftrace_lock); + do_for_each_ftrace_rec(pg, rec) { + + if (rec->flags & FTRACE_FL_FAILED) + continue; + + if (!ftrace_match_record(rec, search, len, type)) + continue; + + entry = kmalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) { + /* If we did not process any, then return error */ + if (!count) + count = -ENOMEM; + goto out_unlock; + } + + count++; + + entry->data = data; + + /* + * The caller might want to do something special + * for each function we find. We call the callback + * to give the caller an opportunity to do so. + */ + if (ops->callback) { + if (ops->callback(rec->ip, &entry->data) < 0) { + /* caller does not like this func */ + kfree(entry); continue; - kallsyms_lookup(rec->ip, NULL, NULL, NULL, str); - switch (type) { - case MATCH_FULL: - if (strcmp(str, buff) == 0) - matched = 1; - break; - case MATCH_FRONT_ONLY: - if (memcmp(str, buff, match) == 0) - matched = 1; - break; - case MATCH_MIDDLE_ONLY: - if (strstr(str, search)) - matched = 1; - break; - case MATCH_END_ONLY: - ptr = strstr(str, search); - if (ptr && (ptr[search_len] == 0)) - matched = 1; - break; } - if (matched) { - if (not) - rec->flags &= ~flag; - else - rec->flags |= flag; + } + + entry->ops = ops; + entry->ip = rec->ip; + + key = hash_long(entry->ip, FTRACE_HASH_BITS); + hlist_add_head_rcu(&entry->node, &ftrace_func_hash[key]); + + } while_for_each_ftrace_rec(); + __enable_ftrace_function_probe(); + + out_unlock: + mutex_unlock(&ftrace_lock); + + return count; +} + +enum { + PROBE_TEST_FUNC = 1, + PROBE_TEST_DATA = 2 +}; + +static void +__unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, + void *data, int flags) +{ + struct ftrace_func_probe *entry; + struct hlist_node *n, *tmp; + char str[KSYM_SYMBOL_LEN]; + int type = MATCH_FULL; + int i, len = 0; + char *search; + + if (glob && (strcmp(glob, "*") || !strlen(glob))) + glob = NULL; + else { + int not; + + type = ftrace_setup_glob(glob, strlen(glob), &search, ¬); + len = strlen(search); + + /* we do not support '!' for function probes */ + if (WARN_ON(not)) + return; + } + + mutex_lock(&ftrace_lock); + for (i = 0; i < FTRACE_FUNC_HASHSIZE; i++) { + struct hlist_head *hhd = &ftrace_func_hash[i]; + + hlist_for_each_entry_safe(entry, n, tmp, hhd, node) { + + /* break up if statements for readability */ + if ((flags & PROBE_TEST_FUNC) && entry->ops != ops) + continue; + + if ((flags & PROBE_TEST_DATA) && entry->data != data) + continue; + + /* do this last, since it is the most expensive */ + if (glob) { + kallsyms_lookup(entry->ip, NULL, NULL, + NULL, str); + if (!ftrace_match(str, glob, len, type)) + continue; } + + hlist_del(&entry->node); + call_rcu(&entry->rcu, ftrace_free_entry_rcu); } - pg = pg->next; } - spin_unlock(&ftrace_lock); + __disable_ftrace_function_probe(); + mutex_unlock(&ftrace_lock); +} + +void +unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, + void *data) +{ + __unregister_ftrace_function_probe(glob, ops, data, + PROBE_TEST_FUNC | PROBE_TEST_DATA); +} + +void +unregister_ftrace_function_probe_func(char *glob, struct ftrace_probe_ops *ops) +{ + __unregister_ftrace_function_probe(glob, ops, NULL, PROBE_TEST_FUNC); +} + +void unregister_ftrace_function_probe_all(char *glob) +{ + __unregister_ftrace_function_probe(glob, NULL, NULL, 0); +} + +static LIST_HEAD(ftrace_commands); +static DEFINE_MUTEX(ftrace_cmd_mutex); + +int register_ftrace_command(struct ftrace_func_command *cmd) +{ + struct ftrace_func_command *p; + int ret = 0; + + mutex_lock(&ftrace_cmd_mutex); + list_for_each_entry(p, &ftrace_commands, list) { + if (strcmp(cmd->name, p->name) == 0) { + ret = -EBUSY; + goto out_unlock; + } + } + list_add(&cmd->list, &ftrace_commands); + out_unlock: + mutex_unlock(&ftrace_cmd_mutex); + + return ret; +} + +int unregister_ftrace_command(struct ftrace_func_command *cmd) +{ + struct ftrace_func_command *p, *n; + int ret = -ENODEV; + + mutex_lock(&ftrace_cmd_mutex); + list_for_each_entry_safe(p, n, &ftrace_commands, list) { + if (strcmp(cmd->name, p->name) == 0) { + ret = 0; + list_del_init(&p->list); + goto out_unlock; + } + } + out_unlock: + mutex_unlock(&ftrace_cmd_mutex); + + return ret; +} + +static int ftrace_process_regex(char *buff, int len, int enable) +{ + char *func, *command, *next = buff; + struct ftrace_func_command *p; + int ret = -EINVAL; + + func = strsep(&next, ":"); + + if (!next) { + ftrace_match_records(func, len, enable); + return 0; + } + + /* command found */ + + command = strsep(&next, ":"); + + mutex_lock(&ftrace_cmd_mutex); + list_for_each_entry(p, &ftrace_commands, list) { + if (strcmp(p->name, command) == 0) { + ret = p->func(func, command, next, enable); + goto out_unlock; + } + } + out_unlock: + mutex_unlock(&ftrace_cmd_mutex); + + return ret; } static ssize_t @@ -1187,7 +1748,10 @@ ftrace_regex_write(struct file *file, const char __user *ubuf, if (isspace(ch)) { iter->filtered++; iter->buffer[iter->buffer_idx] = 0; - ftrace_match(iter->buffer, iter->buffer_idx, enable); + ret = ftrace_process_regex(iter->buffer, + iter->buffer_idx, enable); + if (ret) + goto out; iter->buffer_idx = 0; } else iter->flags |= FTRACE_ITER_CONT; @@ -1226,7 +1790,7 @@ ftrace_set_regex(unsigned char *buf, int len, int reset, int enable) if (reset) ftrace_filter_reset(enable); if (buf) - ftrace_match(buf, len, enable); + ftrace_match_records(buf, len, enable); mutex_unlock(&ftrace_regex_lock); } @@ -1276,15 +1840,13 @@ ftrace_regex_release(struct inode *inode, struct file *file, int enable) if (iter->buffer_idx) { iter->filtered++; iter->buffer[iter->buffer_idx] = 0; - ftrace_match(iter->buffer, iter->buffer_idx, enable); + ftrace_match_records(iter->buffer, iter->buffer_idx, enable); } - mutex_lock(&ftrace_sysctl_lock); - mutex_lock(&ftrace_start_lock); + mutex_lock(&ftrace_lock); if (ftrace_start_up && ftrace_enabled) ftrace_run_update_code(FTRACE_ENABLE_CALLS); - mutex_unlock(&ftrace_start_lock); - mutex_unlock(&ftrace_sysctl_lock); + mutex_unlock(&ftrace_lock); kfree(iter); mutex_unlock(&ftrace_regex_lock); @@ -1303,31 +1865,31 @@ ftrace_notrace_release(struct inode *inode, struct file *file) return ftrace_regex_release(inode, file, 0); } -static struct file_operations ftrace_avail_fops = { +static const struct file_operations ftrace_avail_fops = { .open = ftrace_avail_open, .read = seq_read, .llseek = seq_lseek, .release = ftrace_avail_release, }; -static struct file_operations ftrace_failures_fops = { +static const struct file_operations ftrace_failures_fops = { .open = ftrace_failures_open, .read = seq_read, .llseek = seq_lseek, .release = ftrace_avail_release, }; -static struct file_operations ftrace_filter_fops = { +static const struct file_operations ftrace_filter_fops = { .open = ftrace_filter_open, - .read = ftrace_regex_read, + .read = seq_read, .write = ftrace_filter_write, .llseek = ftrace_regex_lseek, .release = ftrace_filter_release, }; -static struct file_operations ftrace_notrace_fops = { +static const struct file_operations ftrace_notrace_fops = { .open = ftrace_notrace_open, - .read = ftrace_regex_read, + .read = seq_read, .write = ftrace_notrace_write, .llseek = ftrace_regex_lseek, .release = ftrace_notrace_release, @@ -1360,6 +1922,10 @@ static void *g_start(struct seq_file *m, loff_t *pos) mutex_lock(&graph_lock); + /* Nothing, tell g_show to print all functions are enabled */ + if (!ftrace_graph_count && !*pos) + return (void *)1; + p = g_next(m, p, pos); return p; @@ -1378,6 +1944,11 @@ static int g_show(struct seq_file *m, void *v) if (!ptr) return 0; + if (ptr == (unsigned long *)1) { + seq_printf(m, "#### all functions enabled ####\n"); + return 0; + } + kallsyms_lookup(*ptr, NULL, NULL, NULL, str); seq_printf(m, "%s\n", str); @@ -1420,53 +1991,53 @@ ftrace_graph_open(struct inode *inode, struct file *file) return ret; } -static ssize_t -ftrace_graph_read(struct file *file, char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - if (file->f_mode & FMODE_READ) - return seq_read(file, ubuf, cnt, ppos); - else - return -EPERM; -} - static int -ftrace_set_func(unsigned long *array, int idx, char *buffer) +ftrace_set_func(unsigned long *array, int *idx, char *buffer) { - char str[KSYM_SYMBOL_LEN]; struct dyn_ftrace *rec; struct ftrace_page *pg; + int search_len; int found = 0; - int i, j; + int type, not; + char *search; + bool exists; + int i; if (ftrace_disabled) return -ENODEV; - /* should not be called from interrupt context */ - spin_lock(&ftrace_lock); + /* decode regex */ + type = ftrace_setup_glob(buffer, strlen(buffer), &search, ¬); + if (not) + return -EINVAL; + + search_len = strlen(search); - for (pg = ftrace_pages_start; pg; pg = pg->next) { - for (i = 0; i < pg->index; i++) { - rec = &pg->records[i]; + mutex_lock(&ftrace_lock); + do_for_each_ftrace_rec(pg, rec) { - if (rec->flags & (FTRACE_FL_FAILED | FTRACE_FL_FREE)) - continue; + if (*idx >= FTRACE_GRAPH_MAX_FUNCS) + break; + + if (rec->flags & (FTRACE_FL_FAILED | FTRACE_FL_FREE)) + continue; - kallsyms_lookup(rec->ip, NULL, NULL, NULL, str); - if (strcmp(str, buffer) == 0) { + if (ftrace_match_record(rec, search, search_len, type)) { + /* ensure it is not already in the array */ + exists = false; + for (i = 0; i < *idx; i++) + if (array[i] == rec->ip) { + exists = true; + break; + } + if (!exists) { + array[(*idx)++] = rec->ip; found = 1; - for (j = 0; j < idx; j++) - if (array[j] == rec->ip) { - found = 0; - break; - } - if (found) - array[idx] = rec->ip; - break; } } - } - spin_unlock(&ftrace_lock); + } while_for_each_ftrace_rec(); + + mutex_unlock(&ftrace_lock); return found ? 0 : -EINVAL; } @@ -1534,13 +2105,11 @@ ftrace_graph_write(struct file *file, const char __user *ubuf, } buffer[index] = 0; - /* we allow only one at a time */ - ret = ftrace_set_func(array, ftrace_graph_count, buffer); + /* we allow only one expression at a time */ + ret = ftrace_set_func(array, &ftrace_graph_count, buffer); if (ret) goto out; - ftrace_graph_count++; - file->f_pos += read; ret = read; @@ -1552,7 +2121,7 @@ ftrace_graph_write(struct file *file, const char __user *ubuf, static const struct file_operations ftrace_graph_fops = { .open = ftrace_graph_open, - .read = ftrace_graph_read, + .read = seq_read, .write = ftrace_graph_write, }; #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ @@ -1604,7 +2173,7 @@ static int ftrace_convert_nops(struct module *mod, unsigned long addr; unsigned long flags; - mutex_lock(&ftrace_start_lock); + mutex_lock(&ftrace_lock); p = start; while (p < end) { addr = ftrace_call_adjust(*p++); @@ -1623,7 +2192,7 @@ static int ftrace_convert_nops(struct module *mod, local_irq_save(flags); ftrace_update_code(mod); local_irq_restore(flags); - mutex_unlock(&ftrace_start_lock); + mutex_unlock(&ftrace_lock); return 0; } @@ -1700,7 +2269,7 @@ ftrace_pid_read(struct file *file, char __user *ubuf, if (ftrace_pid_trace == ftrace_swapper_pid) r = sprintf(buf, "swapper tasks\n"); else if (ftrace_pid_trace) - r = sprintf(buf, "%u\n", pid_nr(ftrace_pid_trace)); + r = sprintf(buf, "%u\n", pid_vnr(ftrace_pid_trace)); else r = sprintf(buf, "no pid\n"); @@ -1796,7 +2365,7 @@ ftrace_pid_write(struct file *filp, const char __user *ubuf, if (ret < 0) return ret; - mutex_lock(&ftrace_start_lock); + mutex_lock(&ftrace_lock); if (val < 0) { /* disable pid tracing */ if (!ftrace_pid_trace) @@ -1835,12 +2404,12 @@ ftrace_pid_write(struct file *filp, const char __user *ubuf, ftrace_startup_enable(0); out: - mutex_unlock(&ftrace_start_lock); + mutex_unlock(&ftrace_lock); return cnt; } -static struct file_operations ftrace_pid_fops = { +static const struct file_operations ftrace_pid_fops = { .read = ftrace_pid_read, .write = ftrace_pid_write, }; @@ -1863,7 +2432,6 @@ static __init int ftrace_init_debugfs(void) "'set_ftrace_pid' entry\n"); return 0; } - fs_initcall(ftrace_init_debugfs); /** @@ -1898,17 +2466,17 @@ int register_ftrace_function(struct ftrace_ops *ops) if (unlikely(ftrace_disabled)) return -1; - mutex_lock(&ftrace_sysctl_lock); + mutex_lock(&ftrace_lock); ret = __register_ftrace_function(ops); ftrace_startup(0); - mutex_unlock(&ftrace_sysctl_lock); + mutex_unlock(&ftrace_lock); return ret; } /** - * unregister_ftrace_function - unresgister a function for profiling. + * unregister_ftrace_function - unregister a function for profiling. * @ops - ops structure that holds the function to unregister * * Unregister a function that was added to be called by ftrace profiling. @@ -1917,10 +2485,10 @@ int unregister_ftrace_function(struct ftrace_ops *ops) { int ret; - mutex_lock(&ftrace_sysctl_lock); + mutex_lock(&ftrace_lock); ret = __unregister_ftrace_function(ops); ftrace_shutdown(0); - mutex_unlock(&ftrace_sysctl_lock); + mutex_unlock(&ftrace_lock); return ret; } @@ -1935,7 +2503,7 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, if (unlikely(ftrace_disabled)) return -ENODEV; - mutex_lock(&ftrace_sysctl_lock); + mutex_lock(&ftrace_lock); ret = proc_dointvec(table, write, file, buffer, lenp, ppos); @@ -1964,7 +2532,7 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, } out: - mutex_unlock(&ftrace_sysctl_lock); + mutex_unlock(&ftrace_lock); return ret; } @@ -2029,6 +2597,38 @@ free: return ret; } +static void +ftrace_graph_probe_sched_switch(struct rq *__rq, struct task_struct *prev, + struct task_struct *next) +{ + unsigned long long timestamp; + int index; + + /* + * Does the user want to count the time a function was asleep. + * If so, do not update the time stamps. + */ + if (trace_flags & TRACE_ITER_SLEEP_TIME) + return; + + timestamp = trace_clock_local(); + + prev->ftrace_timestamp = timestamp; + + /* only process tasks that we timestamped */ + if (!next->ftrace_timestamp) + return; + + /* + * Update all the counters in next to make up for the + * time next was sleeping. + */ + timestamp -= next->ftrace_timestamp; + + for (index = next->curr_ret_stack; index >= 0; index--) + next->ret_stack[index].calltime += timestamp; +} + /* Allocate a return stack for each task */ static int start_graph_tracing(void) { @@ -2050,6 +2650,13 @@ static int start_graph_tracing(void) ret = alloc_retstack_tasklist(ret_stack_list); } while (ret == -EAGAIN); + if (!ret) { + ret = register_trace_sched_switch(ftrace_graph_probe_sched_switch); + if (ret) + pr_info("ftrace_graph: Couldn't activate tracepoint" + " probe to kernel_sched_switch\n"); + } + kfree(ret_stack_list); return ret; } @@ -2080,7 +2687,13 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc, { int ret = 0; - mutex_lock(&ftrace_sysctl_lock); + mutex_lock(&ftrace_lock); + + /* we currently allow only one tracer registered at a time */ + if (atomic_read(&ftrace_graph_active)) { + ret = -EBUSY; + goto out; + } ftrace_suspend_notifier.notifier_call = ftrace_suspend_notifier_call; register_pm_notifier(&ftrace_suspend_notifier); @@ -2098,21 +2711,26 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc, ftrace_startup(FTRACE_START_FUNC_RET); out: - mutex_unlock(&ftrace_sysctl_lock); + mutex_unlock(&ftrace_lock); return ret; } void unregister_ftrace_graph(void) { - mutex_lock(&ftrace_sysctl_lock); + mutex_lock(&ftrace_lock); + + if (!unlikely(atomic_read(&ftrace_graph_active))) + goto out; atomic_dec(&ftrace_graph_active); + unregister_trace_sched_switch(ftrace_graph_probe_sched_switch); ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub; ftrace_graph_entry = ftrace_graph_entry_stub; ftrace_shutdown(FTRACE_STOP_FUNC_RET); unregister_pm_notifier(&ftrace_suspend_notifier); - mutex_unlock(&ftrace_sysctl_lock); + out: + mutex_unlock(&ftrace_lock); } /* Allocate a return stack for newly created task */ @@ -2127,6 +2745,7 @@ void ftrace_graph_init_task(struct task_struct *t) t->curr_ret_stack = -1; atomic_set(&t->tracing_graph_pause, 0); atomic_set(&t->trace_overrun, 0); + t->ftrace_timestamp = 0; } else t->ret_stack = NULL; } diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c new file mode 100644 index 000000000000..ae201b3eda89 --- /dev/null +++ b/kernel/trace/kmemtrace.c @@ -0,0 +1,339 @@ +/* + * Memory allocator tracing + * + * Copyright (C) 2008 Eduard - Gabriel Munteanu + * Copyright (C) 2008 Pekka Enberg <penberg@cs.helsinki.fi> + * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com> + */ + +#include <linux/dcache.h> +#include <linux/debugfs.h> +#include <linux/fs.h> +#include <linux/seq_file.h> +#include <trace/kmemtrace.h> + +#include "trace.h" +#include "trace_output.h" + +/* Select an alternative, minimalistic output than the original one */ +#define TRACE_KMEM_OPT_MINIMAL 0x1 + +static struct tracer_opt kmem_opts[] = { + /* Default disable the minimalistic output */ + { TRACER_OPT(kmem_minimalistic, TRACE_KMEM_OPT_MINIMAL) }, + { } +}; + +static struct tracer_flags kmem_tracer_flags = { + .val = 0, + .opts = kmem_opts +}; + + +static bool kmem_tracing_enabled __read_mostly; +static struct trace_array *kmemtrace_array; + +static int kmem_trace_init(struct trace_array *tr) +{ + int cpu; + kmemtrace_array = tr; + + for_each_cpu_mask(cpu, cpu_possible_map) + tracing_reset(tr, cpu); + + kmem_tracing_enabled = true; + + return 0; +} + +static void kmem_trace_reset(struct trace_array *tr) +{ + kmem_tracing_enabled = false; +} + +static void kmemtrace_headers(struct seq_file *s) +{ + /* Don't need headers for the original kmemtrace output */ + if (!(kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL)) + return; + + seq_printf(s, "#\n"); + seq_printf(s, "# ALLOC TYPE REQ GIVEN FLAGS " + " POINTER NODE CALLER\n"); + seq_printf(s, "# FREE | | | | " + " | | | |\n"); + seq_printf(s, "# |\n\n"); +} + +/* + * The two following functions give the original output from kmemtrace, + * or something close to....perhaps they need some missing things + */ +static enum print_line_t +kmemtrace_print_alloc_original(struct trace_iterator *iter, + struct kmemtrace_alloc_entry *entry) +{ + struct trace_seq *s = &iter->seq; + int ret; + + /* Taken from the old linux/kmemtrace.h */ + ret = trace_seq_printf(s, "type_id %d call_site %lu ptr %lu " + "bytes_req %lu bytes_alloc %lu gfp_flags %lu node %d\n", + entry->type_id, entry->call_site, (unsigned long) entry->ptr, + (unsigned long) entry->bytes_req, (unsigned long) entry->bytes_alloc, + (unsigned long) entry->gfp_flags, entry->node); + + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t +kmemtrace_print_free_original(struct trace_iterator *iter, + struct kmemtrace_free_entry *entry) +{ + struct trace_seq *s = &iter->seq; + int ret; + + /* Taken from the old linux/kmemtrace.h */ + ret = trace_seq_printf(s, "type_id %d call_site %lu ptr %lu\n", + entry->type_id, entry->call_site, (unsigned long) entry->ptr); + + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + + +/* The two other following provide a more minimalistic output */ +static enum print_line_t +kmemtrace_print_alloc_compress(struct trace_iterator *iter, + struct kmemtrace_alloc_entry *entry) +{ + struct trace_seq *s = &iter->seq; + int ret; + + /* Alloc entry */ + ret = trace_seq_printf(s, " + "); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + /* Type */ + switch (entry->type_id) { + case KMEMTRACE_TYPE_KMALLOC: + ret = trace_seq_printf(s, "K "); + break; + case KMEMTRACE_TYPE_CACHE: + ret = trace_seq_printf(s, "C "); + break; + case KMEMTRACE_TYPE_PAGES: + ret = trace_seq_printf(s, "P "); + break; + default: + ret = trace_seq_printf(s, "? "); + } + + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + /* Requested */ + ret = trace_seq_printf(s, "%4zu ", entry->bytes_req); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + /* Allocated */ + ret = trace_seq_printf(s, "%4zu ", entry->bytes_alloc); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + /* Flags + * TODO: would be better to see the name of the GFP flag names + */ + ret = trace_seq_printf(s, "%08x ", entry->gfp_flags); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + /* Pointer to allocated */ + ret = trace_seq_printf(s, "0x%tx ", (ptrdiff_t)entry->ptr); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + /* Node */ + ret = trace_seq_printf(s, "%4d ", entry->node); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + /* Call site */ + ret = seq_print_ip_sym(s, entry->call_site, 0); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + if (!trace_seq_printf(s, "\n")) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t +kmemtrace_print_free_compress(struct trace_iterator *iter, + struct kmemtrace_free_entry *entry) +{ + struct trace_seq *s = &iter->seq; + int ret; + + /* Free entry */ + ret = trace_seq_printf(s, " - "); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + /* Type */ + switch (entry->type_id) { + case KMEMTRACE_TYPE_KMALLOC: + ret = trace_seq_printf(s, "K "); + break; + case KMEMTRACE_TYPE_CACHE: + ret = trace_seq_printf(s, "C "); + break; + case KMEMTRACE_TYPE_PAGES: + ret = trace_seq_printf(s, "P "); + break; + default: + ret = trace_seq_printf(s, "? "); + } + + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + /* Skip requested/allocated/flags */ + ret = trace_seq_printf(s, " "); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + /* Pointer to allocated */ + ret = trace_seq_printf(s, "0x%tx ", (ptrdiff_t)entry->ptr); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + /* Skip node */ + ret = trace_seq_printf(s, " "); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + /* Call site */ + ret = seq_print_ip_sym(s, entry->call_site, 0); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + if (!trace_seq_printf(s, "\n")) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t kmemtrace_print_line(struct trace_iterator *iter) +{ + struct trace_entry *entry = iter->ent; + + switch (entry->type) { + case TRACE_KMEM_ALLOC: { + struct kmemtrace_alloc_entry *field; + trace_assign_type(field, entry); + if (kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL) + return kmemtrace_print_alloc_compress(iter, field); + else + return kmemtrace_print_alloc_original(iter, field); + } + + case TRACE_KMEM_FREE: { + struct kmemtrace_free_entry *field; + trace_assign_type(field, entry); + if (kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL) + return kmemtrace_print_free_compress(iter, field); + else + return kmemtrace_print_free_original(iter, field); + } + + default: + return TRACE_TYPE_UNHANDLED; + } +} + +/* Trace allocations */ +void kmemtrace_mark_alloc_node(enum kmemtrace_type_id type_id, + unsigned long call_site, + const void *ptr, + size_t bytes_req, + size_t bytes_alloc, + gfp_t gfp_flags, + int node) +{ + struct ring_buffer_event *event; + struct kmemtrace_alloc_entry *entry; + struct trace_array *tr = kmemtrace_array; + + if (!kmem_tracing_enabled) + return; + + event = trace_buffer_lock_reserve(tr, TRACE_KMEM_ALLOC, + sizeof(*entry), 0, 0); + if (!event) + return; + entry = ring_buffer_event_data(event); + + entry->call_site = call_site; + entry->ptr = ptr; + entry->bytes_req = bytes_req; + entry->bytes_alloc = bytes_alloc; + entry->gfp_flags = gfp_flags; + entry->node = node; + + trace_buffer_unlock_commit(tr, event, 0, 0); +} +EXPORT_SYMBOL(kmemtrace_mark_alloc_node); + +void kmemtrace_mark_free(enum kmemtrace_type_id type_id, + unsigned long call_site, + const void *ptr) +{ + struct ring_buffer_event *event; + struct kmemtrace_free_entry *entry; + struct trace_array *tr = kmemtrace_array; + + if (!kmem_tracing_enabled) + return; + + event = trace_buffer_lock_reserve(tr, TRACE_KMEM_FREE, + sizeof(*entry), 0, 0); + if (!event) + return; + entry = ring_buffer_event_data(event); + entry->type_id = type_id; + entry->call_site = call_site; + entry->ptr = ptr; + + trace_buffer_unlock_commit(tr, event, 0, 0); +} +EXPORT_SYMBOL(kmemtrace_mark_free); + +static struct tracer kmem_tracer __read_mostly = { + .name = "kmemtrace", + .init = kmem_trace_init, + .reset = kmem_trace_reset, + .print_line = kmemtrace_print_line, + .print_header = kmemtrace_headers, + .flags = &kmem_tracer_flags +}; + +void kmemtrace_init(void) +{ + /* earliest opportunity to start kmem tracing */ +} + +static int __init init_kmem_tracer(void) +{ + return register_tracer(&kmem_tracer); +} + +device_initcall(init_kmem_tracer); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index bd38c5cfd8ad..960cbf44c844 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -4,21 +4,92 @@ * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com> */ #include <linux/ring_buffer.h> +#include <linux/trace_clock.h> +#include <linux/ftrace_irq.h> #include <linux/spinlock.h> #include <linux/debugfs.h> #include <linux/uaccess.h> +#include <linux/hardirq.h> #include <linux/module.h> #include <linux/percpu.h> #include <linux/mutex.h> -#include <linux/sched.h> /* used for sched_clock() (for now) */ #include <linux/init.h> #include <linux/hash.h> #include <linux/list.h> +#include <linux/cpu.h> #include <linux/fs.h> #include "trace.h" /* + * The ring buffer is made up of a list of pages. A separate list of pages is + * allocated for each CPU. A writer may only write to a buffer that is + * associated with the CPU it is currently executing on. A reader may read + * from any per cpu buffer. + * + * The reader is special. For each per cpu buffer, the reader has its own + * reader page. When a reader has read the entire reader page, this reader + * page is swapped with another page in the ring buffer. + * + * Now, as long as the writer is off the reader page, the reader can do what + * ever it wants with that page. The writer will never write to that page + * again (as long as it is out of the ring buffer). + * + * Here's some silly ASCII art. + * + * +------+ + * |reader| RING BUFFER + * |page | + * +------+ +---+ +---+ +---+ + * | |-->| |-->| | + * +---+ +---+ +---+ + * ^ | + * | | + * +---------------+ + * + * + * +------+ + * |reader| RING BUFFER + * |page |------------------v + * +------+ +---+ +---+ +---+ + * | |-->| |-->| | + * +---+ +---+ +---+ + * ^ | + * | | + * +---------------+ + * + * + * +------+ + * |reader| RING BUFFER + * |page |------------------v + * +------+ +---+ +---+ +---+ + * ^ | |-->| |-->| | + * | +---+ +---+ +---+ + * | | + * | | + * +------------------------------+ + * + * + * +------+ + * |buffer| RING BUFFER + * |page |------------------v + * +------+ +---+ +---+ +---+ + * ^ | | | |-->| | + * | New +---+ +---+ +---+ + * | Reader------^ | + * | page | + * +------------------------------+ + * + * + * After we make this swap, the reader can hand this page off to the splice + * code and be done with it. It can even allocate a new page if it needs to + * and swap that into the ring buffer. + * + * We will be using cmpxchg soon to make all this lockless. + * + */ + +/* * A fast way to enable or disable all ring buffers is to * call tracing_on or tracing_off. Turning off the ring buffers * prevents all ring buffers from being recorded to. @@ -57,7 +128,9 @@ enum { RB_BUFFERS_DISABLED = 1 << RB_BUFFERS_DISABLED_BIT, }; -static long ring_buffer_flags __read_mostly = RB_BUFFERS_ON; +static unsigned long ring_buffer_flags __read_mostly = RB_BUFFERS_ON; + +#define BUF_PAGE_HDR_SIZE offsetof(struct buffer_data_page, data) /** * tracing_on - enable all tracing buffers @@ -89,59 +162,92 @@ EXPORT_SYMBOL_GPL(tracing_off); * tracing_off_permanent - permanently disable ring buffers * * This function, once called, will disable all ring buffers - * permanenty. + * permanently. */ void tracing_off_permanent(void) { set_bit(RB_BUFFERS_DISABLED_BIT, &ring_buffer_flags); } +/** + * tracing_is_on - show state of ring buffers enabled + */ +int tracing_is_on(void) +{ + return ring_buffer_flags == RB_BUFFERS_ON; +} +EXPORT_SYMBOL_GPL(tracing_is_on); + #include "trace.h" -/* Up this if you want to test the TIME_EXTENTS and normalization */ -#define DEBUG_SHIFT 0 +#define RB_EVNT_HDR_SIZE (offsetof(struct ring_buffer_event, array)) +#define RB_ALIGNMENT 4U +#define RB_MAX_SMALL_DATA 28 + +enum { + RB_LEN_TIME_EXTEND = 8, + RB_LEN_TIME_STAMP = 16, +}; -/* FIXME!!! */ -u64 ring_buffer_time_stamp(int cpu) +static inline int rb_null_event(struct ring_buffer_event *event) { - u64 time; + return event->type == RINGBUF_TYPE_PADDING && event->time_delta == 0; +} - preempt_disable_notrace(); - /* shift to debug/test normalization and TIME_EXTENTS */ - time = sched_clock() << DEBUG_SHIFT; - preempt_enable_no_resched_notrace(); +static inline int rb_discarded_event(struct ring_buffer_event *event) +{ + return event->type == RINGBUF_TYPE_PADDING && event->time_delta; +} - return time; +static void rb_event_set_padding(struct ring_buffer_event *event) +{ + event->type = RINGBUF_TYPE_PADDING; + event->time_delta = 0; } -EXPORT_SYMBOL_GPL(ring_buffer_time_stamp); -void ring_buffer_normalize_time_stamp(int cpu, u64 *ts) +/** + * ring_buffer_event_discard - discard an event in the ring buffer + * @buffer: the ring buffer + * @event: the event to discard + * + * Sometimes a event that is in the ring buffer needs to be ignored. + * This function lets the user discard an event in the ring buffer + * and then that event will not be read later. + * + * Note, it is up to the user to be careful with this, and protect + * against races. If the user discards an event that has been consumed + * it is possible that it could corrupt the ring buffer. + */ +void ring_buffer_event_discard(struct ring_buffer_event *event) { - /* Just stupid testing the normalize function and deltas */ - *ts >>= DEBUG_SHIFT; + event->type = RINGBUF_TYPE_PADDING; + /* time delta must be non zero */ + if (!event->time_delta) + event->time_delta = 1; } -EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp); -#define RB_EVNT_HDR_SIZE (sizeof(struct ring_buffer_event)) -#define RB_ALIGNMENT_SHIFT 2 -#define RB_ALIGNMENT (1 << RB_ALIGNMENT_SHIFT) -#define RB_MAX_SMALL_DATA 28 +static unsigned +rb_event_data_length(struct ring_buffer_event *event) +{ + unsigned length; -enum { - RB_LEN_TIME_EXTEND = 8, - RB_LEN_TIME_STAMP = 16, -}; + if (event->len) + length = event->len * RB_ALIGNMENT; + else + length = event->array[0]; + return length + RB_EVNT_HDR_SIZE; +} /* inline for ring buffer fast paths */ -static inline unsigned +static unsigned rb_event_length(struct ring_buffer_event *event) { - unsigned length; - switch (event->type) { case RINGBUF_TYPE_PADDING: - /* undefined */ - return -1; + if (rb_null_event(event)) + /* undefined */ + return -1; + return rb_event_data_length(event); case RINGBUF_TYPE_TIME_EXTEND: return RB_LEN_TIME_EXTEND; @@ -150,11 +256,7 @@ rb_event_length(struct ring_buffer_event *event) return RB_LEN_TIME_STAMP; case RINGBUF_TYPE_DATA: - if (event->len) - length = event->len << RB_ALIGNMENT_SHIFT; - else - length = event->array[0]; - return length + RB_EVNT_HDR_SIZE; + return rb_event_data_length(event); default: BUG(); } @@ -179,7 +281,7 @@ unsigned ring_buffer_event_length(struct ring_buffer_event *event) EXPORT_SYMBOL_GPL(ring_buffer_event_length); /* inline for ring buffer fast paths */ -static inline void * +static void * rb_event_data(struct ring_buffer_event *event) { BUG_ON(event->type != RINGBUF_TYPE_DATA); @@ -209,7 +311,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_data); struct buffer_data_page { u64 time_stamp; /* page time stamp */ - local_t commit; /* write commited index */ + local_t commit; /* write committed index */ unsigned char data[]; /* data of buffer page */ }; @@ -225,14 +327,25 @@ static void rb_init_page(struct buffer_data_page *bpage) local_set(&bpage->commit, 0); } +/** + * ring_buffer_page_len - the size of data on the page. + * @page: The page to read + * + * Returns the amount of data on the page, including buffer page header. + */ +size_t ring_buffer_page_len(void *page) +{ + return local_read(&((struct buffer_data_page *)page)->commit) + + BUF_PAGE_HDR_SIZE; +} + /* * Also stolen from mm/slob.c. Thanks to Mathieu Desnoyers for pointing * this issue out. */ -static inline void free_buffer_page(struct buffer_page *bpage) +static void free_buffer_page(struct buffer_page *bpage) { - if (bpage->page) - free_page((unsigned long)bpage->page); + free_page((unsigned long)bpage->page); kfree(bpage); } @@ -246,7 +359,7 @@ static inline int test_time_stamp(u64 delta) return 0; } -#define BUF_PAGE_SIZE (PAGE_SIZE - offsetof(struct buffer_data_page, data)) +#define BUF_PAGE_SIZE (PAGE_SIZE - BUF_PAGE_HDR_SIZE) /* * head_page == tail_page && head == tail then buffer is empty. @@ -260,7 +373,7 @@ struct ring_buffer_per_cpu { struct list_head pages; struct buffer_page *head_page; /* read from head */ struct buffer_page *tail_page; /* write to tail */ - struct buffer_page *commit_page; /* commited pages */ + struct buffer_page *commit_page; /* committed pages */ struct buffer_page *reader_page; unsigned long overrun; unsigned long entries; @@ -273,12 +386,17 @@ struct ring_buffer { unsigned pages; unsigned flags; int cpus; - cpumask_var_t cpumask; atomic_t record_disabled; + cpumask_var_t cpumask; struct mutex mutex; struct ring_buffer_per_cpu **buffers; + +#ifdef CONFIG_HOTPLUG_CPU + struct notifier_block cpu_notify; +#endif + u64 (*clock)(void); }; struct ring_buffer_iter { @@ -299,11 +417,35 @@ struct ring_buffer_iter { _____ret; \ }) +/* Up this if you want to test the TIME_EXTENTS and normalization */ +#define DEBUG_SHIFT 0 + +u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu) +{ + u64 time; + + preempt_disable_notrace(); + /* shift to debug/test normalization and TIME_EXTENTS */ + time = buffer->clock() << DEBUG_SHIFT; + preempt_enable_no_resched_notrace(); + + return time; +} +EXPORT_SYMBOL_GPL(ring_buffer_time_stamp); + +void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer, + int cpu, u64 *ts) +{ + /* Just stupid testing the normalize function and deltas */ + *ts >>= DEBUG_SHIFT; +} +EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp); + /** * check_pages - integrity check of buffer pages * @cpu_buffer: CPU buffer with pages to test * - * As a safty measure we check to make sure the data pages have not + * As a safety measure we check to make sure the data pages have not * been corrupted. */ static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer) @@ -421,7 +563,6 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer) struct list_head *head = &cpu_buffer->pages; struct buffer_page *bpage, *tmp; - list_del_init(&cpu_buffer->reader_page->list); free_buffer_page(cpu_buffer->reader_page); list_for_each_entry_safe(bpage, tmp, head, list) { @@ -437,6 +578,11 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer) */ extern int ring_buffer_page_too_big(void); +#ifdef CONFIG_HOTPLUG_CPU +static int rb_cpu_notify(struct notifier_block *self, + unsigned long action, void *hcpu); +#endif + /** * ring_buffer_alloc - allocate a new ring_buffer * @size: the size in bytes per cpu that is needed. @@ -469,12 +615,23 @@ struct ring_buffer *ring_buffer_alloc(unsigned long size, unsigned flags) buffer->pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE); buffer->flags = flags; + buffer->clock = trace_clock_local; /* need at least two pages */ if (buffer->pages == 1) buffer->pages++; + /* + * In case of non-hotplug cpu, if the ring-buffer is allocated + * in early initcall, it will not be notified of secondary cpus. + * In that off case, we need to allocate for all possible cpus. + */ +#ifdef CONFIG_HOTPLUG_CPU + get_online_cpus(); + cpumask_copy(buffer->cpumask, cpu_online_mask); +#else cpumask_copy(buffer->cpumask, cpu_possible_mask); +#endif buffer->cpus = nr_cpu_ids; bsize = sizeof(void *) * nr_cpu_ids; @@ -490,6 +647,13 @@ struct ring_buffer *ring_buffer_alloc(unsigned long size, unsigned flags) goto fail_free_buffers; } +#ifdef CONFIG_HOTPLUG_CPU + buffer->cpu_notify.notifier_call = rb_cpu_notify; + buffer->cpu_notify.priority = 0; + register_cpu_notifier(&buffer->cpu_notify); +#endif + + put_online_cpus(); mutex_init(&buffer->mutex); return buffer; @@ -503,6 +667,7 @@ struct ring_buffer *ring_buffer_alloc(unsigned long size, unsigned flags) fail_free_cpumask: free_cpumask_var(buffer->cpumask); + put_online_cpus(); fail_free_buffer: kfree(buffer); @@ -519,15 +684,29 @@ ring_buffer_free(struct ring_buffer *buffer) { int cpu; + get_online_cpus(); + +#ifdef CONFIG_HOTPLUG_CPU + unregister_cpu_notifier(&buffer->cpu_notify); +#endif + for_each_buffer_cpu(buffer, cpu) rb_free_cpu_buffer(buffer->buffers[cpu]); + put_online_cpus(); + free_cpumask_var(buffer->cpumask); kfree(buffer); } EXPORT_SYMBOL_GPL(ring_buffer_free); +void ring_buffer_set_clock(struct ring_buffer *buffer, + u64 (*clock)(void)) +{ + buffer->clock = clock; +} + static void rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer); static void @@ -627,16 +806,15 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size) return size; mutex_lock(&buffer->mutex); + get_online_cpus(); nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE); if (size < buffer_size) { /* easy case, just free pages */ - if (RB_WARN_ON(buffer, nr_pages >= buffer->pages)) { - mutex_unlock(&buffer->mutex); - return -1; - } + if (RB_WARN_ON(buffer, nr_pages >= buffer->pages)) + goto out_fail; rm_pages = buffer->pages - nr_pages; @@ -655,10 +833,8 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size) * add these pages to the cpu_buffers. Otherwise we just free * them all and return -ENOMEM; */ - if (RB_WARN_ON(buffer, nr_pages <= buffer->pages)) { - mutex_unlock(&buffer->mutex); - return -1; - } + if (RB_WARN_ON(buffer, nr_pages <= buffer->pages)) + goto out_fail; new_pages = nr_pages - buffer->pages; @@ -683,13 +859,12 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size) rb_insert_pages(cpu_buffer, &pages, new_pages); } - if (RB_WARN_ON(buffer, !list_empty(&pages))) { - mutex_unlock(&buffer->mutex); - return -1; - } + if (RB_WARN_ON(buffer, !list_empty(&pages))) + goto out_fail; out: buffer->pages = nr_pages; + put_online_cpus(); mutex_unlock(&buffer->mutex); return size; @@ -699,15 +874,20 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size) list_del_init(&bpage->list); free_buffer_page(bpage); } + put_online_cpus(); mutex_unlock(&buffer->mutex); return -ENOMEM; -} -EXPORT_SYMBOL_GPL(ring_buffer_resize); -static inline int rb_null_event(struct ring_buffer_event *event) -{ - return event->type == RINGBUF_TYPE_PADDING; + /* + * Something went totally wrong, and we are too paranoid + * to even clean up the mess. + */ + out_fail: + put_online_cpus(); + mutex_unlock(&buffer->mutex); + return -1; } +EXPORT_SYMBOL_GPL(ring_buffer_resize); static inline void * __rb_data_page_index(struct buffer_data_page *bpage, unsigned index) @@ -811,7 +991,7 @@ rb_event_index(struct ring_buffer_event *event) return (addr & ~PAGE_MASK) - (PAGE_SIZE - BUF_PAGE_SIZE); } -static inline int +static int rb_is_commit(struct ring_buffer_per_cpu *cpu_buffer, struct ring_buffer_event *event) { @@ -825,7 +1005,7 @@ rb_is_commit(struct ring_buffer_per_cpu *cpu_buffer, rb_commit_index(cpu_buffer) == index; } -static inline void +static void rb_set_commit_event(struct ring_buffer_per_cpu *cpu_buffer, struct ring_buffer_event *event) { @@ -850,7 +1030,7 @@ rb_set_commit_event(struct ring_buffer_per_cpu *cpu_buffer, local_set(&cpu_buffer->commit_page->page->commit, index); } -static inline void +static void rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer) { /* @@ -896,7 +1076,7 @@ static void rb_reset_reader_page(struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->reader_page->read = 0; } -static inline void rb_inc_iter(struct ring_buffer_iter *iter) +static void rb_inc_iter(struct ring_buffer_iter *iter) { struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; @@ -926,7 +1106,7 @@ static inline void rb_inc_iter(struct ring_buffer_iter *iter) * and with this, we can determine what to place into the * data field. */ -static inline void +static void rb_update_event(struct ring_buffer_event *event, unsigned type, unsigned length) { @@ -938,15 +1118,11 @@ rb_update_event(struct ring_buffer_event *event, break; case RINGBUF_TYPE_TIME_EXTEND: - event->len = - (RB_LEN_TIME_EXTEND + (RB_ALIGNMENT-1)) - >> RB_ALIGNMENT_SHIFT; + event->len = DIV_ROUND_UP(RB_LEN_TIME_EXTEND, RB_ALIGNMENT); break; case RINGBUF_TYPE_TIME_STAMP: - event->len = - (RB_LEN_TIME_STAMP + (RB_ALIGNMENT-1)) - >> RB_ALIGNMENT_SHIFT; + event->len = DIV_ROUND_UP(RB_LEN_TIME_STAMP, RB_ALIGNMENT); break; case RINGBUF_TYPE_DATA: @@ -955,16 +1131,14 @@ rb_update_event(struct ring_buffer_event *event, event->len = 0; event->array[0] = length; } else - event->len = - (length + (RB_ALIGNMENT-1)) - >> RB_ALIGNMENT_SHIFT; + event->len = DIV_ROUND_UP(length, RB_ALIGNMENT); break; default: BUG(); } } -static inline unsigned rb_calculate_event_length(unsigned length) +static unsigned rb_calculate_event_length(unsigned length) { struct ring_buffer_event event; /* Used only for sizeof array */ @@ -990,6 +1164,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, struct ring_buffer *buffer = cpu_buffer->buffer; struct ring_buffer_event *event; unsigned long flags; + bool lock_taken = false; commit_page = cpu_buffer->commit_page; /* we just need to protect against interrupts */ @@ -1003,7 +1178,30 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, struct buffer_page *next_page = tail_page; local_irq_save(flags); - __raw_spin_lock(&cpu_buffer->lock); + /* + * Since the write to the buffer is still not + * fully lockless, we must be careful with NMIs. + * The locks in the writers are taken when a write + * crosses to a new page. The locks protect against + * races with the readers (this will soon be fixed + * with a lockless solution). + * + * Because we can not protect against NMIs, and we + * want to keep traces reentrant, we need to manage + * what happens when we are in an NMI. + * + * NMIs can happen after we take the lock. + * If we are in an NMI, only take the lock + * if it is not already taken. Otherwise + * simply fail. + */ + if (unlikely(in_nmi())) { + if (!__raw_spin_trylock(&cpu_buffer->lock)) + goto out_reset; + } else + __raw_spin_lock(&cpu_buffer->lock); + + lock_taken = true; rb_inc_page(cpu_buffer, &next_page); @@ -1012,7 +1210,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, /* we grabbed the lock before incrementing */ if (RB_WARN_ON(cpu_buffer, next_page == reader_page)) - goto out_unlock; + goto out_reset; /* * If for some reason, we had an interrupt storm that made @@ -1021,12 +1219,12 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, */ if (unlikely(next_page == commit_page)) { WARN_ON_ONCE(1); - goto out_unlock; + goto out_reset; } if (next_page == head_page) { if (!(buffer->flags & RB_FL_OVERWRITE)) - goto out_unlock; + goto out_reset; /* tail_page has not moved yet? */ if (tail_page == cpu_buffer->tail_page) { @@ -1050,7 +1248,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, cpu_buffer->tail_page = next_page; /* reread the time stamp */ - *ts = ring_buffer_time_stamp(cpu_buffer->cpu); + *ts = ring_buffer_time_stamp(buffer, cpu_buffer->cpu); cpu_buffer->tail_page->page->time_stamp = *ts; } @@ -1060,7 +1258,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, if (tail < BUF_PAGE_SIZE) { /* Mark the rest of the page with padding */ event = __rb_page_index(tail_page, tail); - event->type = RINGBUF_TYPE_PADDING; + rb_event_set_padding(event); } if (tail <= BUF_PAGE_SIZE) @@ -1100,12 +1298,13 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, return event; - out_unlock: + out_reset: /* reset write */ if (tail <= BUF_PAGE_SIZE) local_set(&tail_page->write, tail); - __raw_spin_unlock(&cpu_buffer->lock); + if (likely(lock_taken)) + __raw_spin_unlock(&cpu_buffer->lock); local_irq_restore(flags); return NULL; } @@ -1192,7 +1391,7 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer, if (RB_WARN_ON(cpu_buffer, ++nr_loops > 1000)) return NULL; - ts = ring_buffer_time_stamp(cpu_buffer->cpu); + ts = ring_buffer_time_stamp(cpu_buffer->buffer, cpu_buffer->cpu); /* * Only the first commit can update the timestamp. @@ -1265,7 +1464,6 @@ static DEFINE_PER_CPU(int, rb_need_resched); * ring_buffer_lock_reserve - reserve a part of the buffer * @buffer: the ring buffer to reserve from * @length: the length of the data to reserve (excluding event header) - * @flags: a pointer to save the interrupt flags * * Returns a reseverd event on the ring buffer to copy directly to. * The user of this interface will need to get the body to write into @@ -1278,9 +1476,7 @@ static DEFINE_PER_CPU(int, rb_need_resched); * If NULL is returned, then nothing has been allocated or locked. */ struct ring_buffer_event * -ring_buffer_lock_reserve(struct ring_buffer *buffer, - unsigned long length, - unsigned long *flags) +ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length) { struct ring_buffer_per_cpu *cpu_buffer; struct ring_buffer_event *event; @@ -1347,15 +1543,13 @@ static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer, * ring_buffer_unlock_commit - commit a reserved * @buffer: The buffer to commit to * @event: The event pointer to commit. - * @flags: the interrupt flags received from ring_buffer_lock_reserve. * * This commits the data to the ring buffer, and releases any locks held. * * Must be paired with ring_buffer_lock_reserve. */ int ring_buffer_unlock_commit(struct ring_buffer *buffer, - struct ring_buffer_event *event, - unsigned long flags) + struct ring_buffer_event *event) { struct ring_buffer_per_cpu *cpu_buffer; int cpu = raw_smp_processor_id(); @@ -1438,7 +1632,7 @@ int ring_buffer_write(struct ring_buffer *buffer, } EXPORT_SYMBOL_GPL(ring_buffer_write); -static inline int rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer) +static int rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer) { struct buffer_page *reader = cpu_buffer->reader_page; struct buffer_page *head = cpu_buffer->head_page; @@ -1528,12 +1722,15 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_enable_cpu); unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; + unsigned long ret; if (!cpumask_test_cpu(cpu, buffer->cpumask)) return 0; cpu_buffer = buffer->buffers[cpu]; - return cpu_buffer->entries; + ret = cpu_buffer->entries; + + return ret; } EXPORT_SYMBOL_GPL(ring_buffer_entries_cpu); @@ -1545,12 +1742,15 @@ EXPORT_SYMBOL_GPL(ring_buffer_entries_cpu); unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; + unsigned long ret; if (!cpumask_test_cpu(cpu, buffer->cpumask)) return 0; cpu_buffer = buffer->buffers[cpu]; - return cpu_buffer->overrun; + ret = cpu_buffer->overrun; + + return ret; } EXPORT_SYMBOL_GPL(ring_buffer_overrun_cpu); @@ -1627,9 +1827,14 @@ static void rb_iter_reset(struct ring_buffer_iter *iter) */ void ring_buffer_iter_reset(struct ring_buffer_iter *iter) { - struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; + struct ring_buffer_per_cpu *cpu_buffer; unsigned long flags; + if (!iter) + return; + + cpu_buffer = iter->cpu_buffer; + spin_lock_irqsave(&cpu_buffer->reader_lock, flags); rb_iter_reset(iter); spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); @@ -1803,7 +2008,7 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer) event = rb_reader_event(cpu_buffer); - if (event->type == RINGBUF_TYPE_DATA) + if (event->type == RINGBUF_TYPE_DATA || rb_discarded_event(event)) cpu_buffer->entries--; rb_update_read_stamp(cpu_buffer, event); @@ -1864,9 +2069,6 @@ rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts) struct buffer_page *reader; int nr_loops = 0; - if (!cpumask_test_cpu(cpu, buffer->cpumask)) - return NULL; - cpu_buffer = buffer->buffers[cpu]; again: @@ -1889,9 +2091,18 @@ rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts) switch (event->type) { case RINGBUF_TYPE_PADDING: - RB_WARN_ON(cpu_buffer, 1); + if (rb_null_event(event)) + RB_WARN_ON(cpu_buffer, 1); + /* + * Because the writer could be discarding every + * event it creates (which would probably be bad) + * if we were to go back to "again" then we may never + * catch up, and will trigger the warn on, or lock + * the box. Return the padding, and we will release + * the current locks, and try again. + */ rb_advance_reader(cpu_buffer); - return NULL; + return event; case RINGBUF_TYPE_TIME_EXTEND: /* Internal data, OK to advance */ @@ -1906,7 +2117,8 @@ rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts) case RINGBUF_TYPE_DATA: if (ts) { *ts = cpu_buffer->read_stamp + event->time_delta; - ring_buffer_normalize_time_stamp(cpu_buffer->cpu, ts); + ring_buffer_normalize_time_stamp(buffer, + cpu_buffer->cpu, ts); } return event; @@ -1951,8 +2163,12 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) switch (event->type) { case RINGBUF_TYPE_PADDING: - rb_inc_iter(iter); - goto again; + if (rb_null_event(event)) { + rb_inc_iter(iter); + goto again; + } + rb_advance_iter(iter); + return event; case RINGBUF_TYPE_TIME_EXTEND: /* Internal data, OK to advance */ @@ -1967,7 +2183,8 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) case RINGBUF_TYPE_DATA: if (ts) { *ts = iter->read_stamp + event->time_delta; - ring_buffer_normalize_time_stamp(cpu_buffer->cpu, ts); + ring_buffer_normalize_time_stamp(buffer, + cpu_buffer->cpu, ts); } return event; @@ -1995,10 +2212,19 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts) struct ring_buffer_event *event; unsigned long flags; + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return NULL; + + again: spin_lock_irqsave(&cpu_buffer->reader_lock, flags); event = rb_buffer_peek(buffer, cpu, ts); spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + if (event && event->type == RINGBUF_TYPE_PADDING) { + cpu_relax(); + goto again; + } + return event; } @@ -2017,10 +2243,16 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts) struct ring_buffer_event *event; unsigned long flags; + again: spin_lock_irqsave(&cpu_buffer->reader_lock, flags); event = rb_iter_peek(iter, ts); spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + if (event && event->type == RINGBUF_TYPE_PADDING) { + cpu_relax(); + goto again; + } + return event; } @@ -2035,24 +2267,37 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts) struct ring_buffer_event * ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts) { - struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; - struct ring_buffer_event *event; + struct ring_buffer_per_cpu *cpu_buffer; + struct ring_buffer_event *event = NULL; unsigned long flags; + again: + /* might be called in atomic */ + preempt_disable(); + if (!cpumask_test_cpu(cpu, buffer->cpumask)) - return NULL; + goto out; + cpu_buffer = buffer->buffers[cpu]; spin_lock_irqsave(&cpu_buffer->reader_lock, flags); event = rb_buffer_peek(buffer, cpu, ts); if (!event) - goto out; + goto out_unlock; rb_advance_reader(cpu_buffer); - out: + out_unlock: spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + out: + preempt_enable(); + + if (event && event->type == RINGBUF_TYPE_PADDING) { + cpu_relax(); + goto again; + } + return event; } EXPORT_SYMBOL_GPL(ring_buffer_consume); @@ -2131,6 +2376,7 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts) struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; unsigned long flags; + again: spin_lock_irqsave(&cpu_buffer->reader_lock, flags); event = rb_iter_peek(iter, ts); if (!event) @@ -2140,6 +2386,11 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts) out: spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + if (event && event->type == RINGBUF_TYPE_PADDING) { + cpu_relax(); + goto again; + } + return event; } EXPORT_SYMBOL_GPL(ring_buffer_read); @@ -2232,6 +2483,7 @@ int ring_buffer_empty(struct ring_buffer *buffer) if (!rb_per_cpu_empty(cpu_buffer)) return 0; } + return 1; } EXPORT_SYMBOL_GPL(ring_buffer_empty); @@ -2244,12 +2496,16 @@ EXPORT_SYMBOL_GPL(ring_buffer_empty); int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; + int ret; if (!cpumask_test_cpu(cpu, buffer->cpumask)) return 1; cpu_buffer = buffer->buffers[cpu]; - return rb_per_cpu_empty(cpu_buffer); + ret = rb_per_cpu_empty(cpu_buffer); + + + return ret; } EXPORT_SYMBOL_GPL(ring_buffer_empty_cpu); @@ -2268,18 +2524,36 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a, { struct ring_buffer_per_cpu *cpu_buffer_a; struct ring_buffer_per_cpu *cpu_buffer_b; + int ret = -EINVAL; if (!cpumask_test_cpu(cpu, buffer_a->cpumask) || !cpumask_test_cpu(cpu, buffer_b->cpumask)) - return -EINVAL; + goto out; /* At least make sure the two buffers are somewhat the same */ if (buffer_a->pages != buffer_b->pages) - return -EINVAL; + goto out; + + ret = -EAGAIN; + + if (ring_buffer_flags != RB_BUFFERS_ON) + goto out; + + if (atomic_read(&buffer_a->record_disabled)) + goto out; + + if (atomic_read(&buffer_b->record_disabled)) + goto out; cpu_buffer_a = buffer_a->buffers[cpu]; cpu_buffer_b = buffer_b->buffers[cpu]; + if (atomic_read(&cpu_buffer_a->record_disabled)) + goto out; + + if (atomic_read(&cpu_buffer_b->record_disabled)) + goto out; + /* * We can't do a synchronize_sched here because this * function can be called in atomic context. @@ -2298,18 +2572,21 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a, atomic_dec(&cpu_buffer_a->record_disabled); atomic_dec(&cpu_buffer_b->record_disabled); - return 0; + ret = 0; +out: + return ret; } EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu); static void rb_remove_entries(struct ring_buffer_per_cpu *cpu_buffer, - struct buffer_data_page *bpage) + struct buffer_data_page *bpage, + unsigned int offset) { struct ring_buffer_event *event; unsigned long head; __raw_spin_lock(&cpu_buffer->lock); - for (head = 0; head < local_read(&bpage->commit); + for (head = offset; head < local_read(&bpage->commit); head += rb_event_length(event)) { event = __rb_data_page_index(bpage, head); @@ -2340,8 +2617,8 @@ static void rb_remove_entries(struct ring_buffer_per_cpu *cpu_buffer, */ void *ring_buffer_alloc_read_page(struct ring_buffer *buffer) { - unsigned long addr; struct buffer_data_page *bpage; + unsigned long addr; addr = __get_free_page(GFP_KERNEL); if (!addr) @@ -2349,6 +2626,8 @@ void *ring_buffer_alloc_read_page(struct ring_buffer *buffer) bpage = (void *)addr; + rb_init_page(bpage); + return bpage; } @@ -2368,6 +2647,7 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data) * ring_buffer_read_page - extract a page from the ring buffer * @buffer: buffer to extract from * @data_page: the page to use allocated from ring_buffer_alloc_read_page + * @len: amount to extract * @cpu: the cpu of the buffer to extract * @full: should the extraction only happen when the page is full. * @@ -2377,12 +2657,12 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data) * to swap with a page in the ring buffer. * * for example: - * rpage = ring_buffer_alloc_page(buffer); + * rpage = ring_buffer_alloc_read_page(buffer); * if (!rpage) * return error; - * ret = ring_buffer_read_page(buffer, &rpage, cpu, 0); - * if (ret) - * process_page(rpage); + * ret = ring_buffer_read_page(buffer, &rpage, len, cpu, 0); + * if (ret >= 0) + * process_page(rpage, ret); * * When @full is set, the function will not return true unless * the writer is off the reader page. @@ -2393,72 +2673,118 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data) * responsible for that. * * Returns: - * 1 if data has been transferred - * 0 if no data has been transferred. + * >=0 if data has been transferred, returns the offset of consumed data. + * <0 if no data has been transferred. */ int ring_buffer_read_page(struct ring_buffer *buffer, - void **data_page, int cpu, int full) + void **data_page, size_t len, int cpu, int full) { struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; struct ring_buffer_event *event; struct buffer_data_page *bpage; + struct buffer_page *reader; unsigned long flags; - int ret = 0; + unsigned int commit; + unsigned int read; + u64 save_timestamp; + int ret = -1; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + goto out; + + /* + * If len is not big enough to hold the page header, then + * we can not copy anything. + */ + if (len <= BUF_PAGE_HDR_SIZE) + goto out; + + len -= BUF_PAGE_HDR_SIZE; if (!data_page) - return 0; + goto out; bpage = *data_page; if (!bpage) - return 0; + goto out; spin_lock_irqsave(&cpu_buffer->reader_lock, flags); - /* - * rb_buffer_peek will get the next ring buffer if - * the current reader page is empty. - */ - event = rb_buffer_peek(buffer, cpu, NULL); - if (!event) - goto out; + reader = rb_get_reader_page(cpu_buffer); + if (!reader) + goto out_unlock; + + event = rb_reader_event(cpu_buffer); + + read = reader->read; + commit = rb_page_commit(reader); - /* check for data */ - if (!local_read(&cpu_buffer->reader_page->page->commit)) - goto out; /* - * If the writer is already off of the read page, then simply - * switch the read page with the given page. Otherwise - * we need to copy the data from the reader to the writer. + * If this page has been partially read or + * if len is not big enough to read the rest of the page or + * a writer is still on the page, then + * we must copy the data from the page to the buffer. + * Otherwise, we can simply swap the page with the one passed in. */ - if (cpu_buffer->reader_page == cpu_buffer->commit_page) { - unsigned int read = cpu_buffer->reader_page->read; + if (read || (len < (commit - read)) || + cpu_buffer->reader_page == cpu_buffer->commit_page) { + struct buffer_data_page *rpage = cpu_buffer->reader_page->page; + unsigned int rpos = read; + unsigned int pos = 0; + unsigned int size; if (full) - goto out; - /* The writer is still on the reader page, we must copy */ - bpage = cpu_buffer->reader_page->page; - memcpy(bpage->data, - cpu_buffer->reader_page->page->data + read, - local_read(&bpage->commit) - read); + goto out_unlock; + + if (len > (commit - read)) + len = (commit - read); + + size = rb_event_length(event); + + if (len < size) + goto out_unlock; - /* consume what was read */ - cpu_buffer->reader_page += read; + /* save the current timestamp, since the user will need it */ + save_timestamp = cpu_buffer->read_stamp; + /* Need to copy one event at a time */ + do { + memcpy(bpage->data + pos, rpage->data + rpos, size); + + len -= size; + + rb_advance_reader(cpu_buffer); + rpos = reader->read; + pos += size; + + event = rb_reader_event(cpu_buffer); + size = rb_event_length(event); + } while (len > size); + + /* update bpage */ + local_set(&bpage->commit, pos); + bpage->time_stamp = save_timestamp; + + /* we copied everything to the beginning */ + read = 0; } else { /* swap the pages */ rb_init_page(bpage); - bpage = cpu_buffer->reader_page->page; - cpu_buffer->reader_page->page = *data_page; - cpu_buffer->reader_page->read = 0; + bpage = reader->page; + reader->page = *data_page; + local_set(&reader->write, 0); + reader->read = 0; *data_page = bpage; + + /* update the entry counter */ + rb_remove_entries(cpu_buffer, bpage, read); } - ret = 1; + ret = read; - /* update the entry counter */ - rb_remove_entries(cpu_buffer, bpage); - out: + out_unlock: spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + out: return ret; } @@ -2466,7 +2792,7 @@ static ssize_t rb_simple_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - long *p = filp->private_data; + unsigned long *p = filp->private_data; char buf[64]; int r; @@ -2482,9 +2808,9 @@ static ssize_t rb_simple_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { - long *p = filp->private_data; + unsigned long *p = filp->private_data; char buf[64]; - long val; + unsigned long val; int ret; if (cnt >= sizeof(buf)) @@ -2509,7 +2835,7 @@ rb_simple_write(struct file *filp, const char __user *ubuf, return cnt; } -static struct file_operations rb_simple_fops = { +static const struct file_operations rb_simple_fops = { .open = tracing_open_generic, .read = rb_simple_read, .write = rb_simple_write, @@ -2532,3 +2858,42 @@ static __init int rb_init_debugfs(void) } fs_initcall(rb_init_debugfs); + +#ifdef CONFIG_HOTPLUG_CPU +static int rb_cpu_notify(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + struct ring_buffer *buffer = + container_of(self, struct ring_buffer, cpu_notify); + long cpu = (long)hcpu; + + switch (action) { + case CPU_UP_PREPARE: + case CPU_UP_PREPARE_FROZEN: + if (cpu_isset(cpu, *buffer->cpumask)) + return NOTIFY_OK; + + buffer->buffers[cpu] = + rb_allocate_cpu_buffer(buffer, cpu); + if (!buffer->buffers[cpu]) { + WARN(1, "failed to allocate ring buffer on CPU %ld\n", + cpu); + return NOTIFY_OK; + } + smp_wmb(); + cpu_set(cpu, *buffer->cpumask); + break; + case CPU_DOWN_PREPARE: + case CPU_DOWN_PREPARE_FROZEN: + /* + * Do nothing. + * If we were to free the buffer, then the user would + * lose any trace that was in the buffer. + */ + break; + default: + break; + } + return NOTIFY_OK; +} +#endif diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 17bb88d86ac2..a0174a40c563 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -11,32 +11,33 @@ * Copyright (C) 2004-2006 Ingo Molnar * Copyright (C) 2004 William Lee Irwin III */ +#include <linux/ring_buffer.h> #include <linux/utsrelease.h> +#include <linux/stacktrace.h> +#include <linux/writeback.h> #include <linux/kallsyms.h> #include <linux/seq_file.h> #include <linux/notifier.h> +#include <linux/irqflags.h> #include <linux/debugfs.h> #include <linux/pagemap.h> #include <linux/hardirq.h> #include <linux/linkage.h> #include <linux/uaccess.h> +#include <linux/kprobes.h> #include <linux/ftrace.h> #include <linux/module.h> #include <linux/percpu.h> +#include <linux/splice.h> #include <linux/kdebug.h> #include <linux/ctype.h> #include <linux/init.h> #include <linux/poll.h> #include <linux/gfp.h> #include <linux/fs.h> -#include <linux/kprobes.h> -#include <linux/writeback.h> - -#include <linux/stacktrace.h> -#include <linux/ring_buffer.h> -#include <linux/irqflags.h> #include "trace.h" +#include "trace_output.h" #define TRACE_BUFFER_FLAGS (RB_FL_OVERWRITE) @@ -44,14 +45,25 @@ unsigned long __read_mostly tracing_max_latency; unsigned long __read_mostly tracing_thresh; /* + * On boot up, the ring buffer is set to the minimum size, so that + * we do not waste memory on systems that are not using tracing. + */ +static int ring_buffer_expanded; + +/* * We need to change this state when a selftest is running. * A selftest will lurk into the ring-buffer to count the * entries inserted during the selftest although some concurrent - * insertions into the ring-buffer such as ftrace_printk could occurred + * insertions into the ring-buffer such as trace_printk could occurred * at the same time, giving false positive or negative results. */ static bool __read_mostly tracing_selftest_running; +/* + * If a tracer is running, we do not want to run SELFTEST. + */ +static bool __read_mostly tracing_selftest_disabled; + /* For tracers that don't implement custom flags */ static struct tracer_opt dummy_tracer_opt[] = { { } @@ -73,7 +85,7 @@ static int dummy_set_flag(u32 old_flags, u32 bit, int set) * of the tracer is successful. But that is the only place that sets * this back to zero. */ -int tracing_disabled = 1; +static int tracing_disabled = 1; static DEFINE_PER_CPU(local_t, ftrace_cpu_disabled); @@ -91,6 +103,9 @@ static inline void ftrace_enable_cpu(void) static cpumask_var_t __read_mostly tracing_buffer_mask; +/* Define which cpu buffers are currently read in trace_pipe */ +static cpumask_var_t tracing_reader_cpumask; + #define for_each_tracing_cpu(cpu) \ for_each_cpu(cpu, tracing_buffer_mask) @@ -109,14 +124,21 @@ static cpumask_var_t __read_mostly tracing_buffer_mask; */ int ftrace_dump_on_oops; -static int tracing_set_tracer(char *buf); +static int tracing_set_tracer(const char *buf); + +#define BOOTUP_TRACER_SIZE 100 +static char bootup_tracer_buf[BOOTUP_TRACER_SIZE] __initdata; +static char *default_bootup_tracer; static int __init set_ftrace(char *str) { - tracing_set_tracer(str); + strncpy(bootup_tracer_buf, str, BOOTUP_TRACER_SIZE); + default_bootup_tracer = bootup_tracer_buf; + /* We are using ftrace early, expand it */ + ring_buffer_expanded = 1; return 1; } -__setup("ftrace", set_ftrace); +__setup("ftrace=", set_ftrace); static int __init set_ftrace_dump_on_oops(char *str) { @@ -133,13 +155,6 @@ ns2usecs(cycle_t nsec) return nsec; } -cycle_t ftrace_now(int cpu) -{ - u64 ts = ring_buffer_time_stamp(cpu); - ring_buffer_normalize_time_stamp(cpu, &ts); - return ts; -} - /* * The global_trace is the descriptor that holds the tracing * buffers for the live tracing. For each CPU, it contains @@ -156,6 +171,20 @@ static struct trace_array global_trace; static DEFINE_PER_CPU(struct trace_array_cpu, global_trace_cpu); +cycle_t ftrace_now(int cpu) +{ + u64 ts; + + /* Early boot up does not have a buffer yet */ + if (!global_trace.buffer) + return trace_clock_local(); + + ts = ring_buffer_time_stamp(global_trace.buffer, cpu); + ring_buffer_normalize_time_stamp(global_trace.buffer, cpu, &ts); + + return ts; +} + /* * The max_tr is used to snapshot the global_trace when a maximum * latency is reached. Some tracers will use this to store a maximum @@ -186,9 +215,6 @@ int tracing_is_enabled(void) return tracer_enabled; } -/* function tracing enabled */ -int ftrace_function_enabled; - /* * trace_buf_size is the size in bytes that is allocated * for a buffer. Note, the number of bytes is always rounded @@ -229,7 +255,7 @@ static DECLARE_WAIT_QUEUE_HEAD(trace_wait); /* trace_flags holds trace_options default values */ unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK | - TRACE_ITER_ANNOTATE; + TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME; /** * trace_wake_up - wake up tasks waiting for trace input @@ -280,13 +306,17 @@ static const char *trace_options[] = { "block", "stacktrace", "sched-tree", - "ftrace_printk", + "trace_printk", "ftrace_preempt", "branch", "annotate", "userstacktrace", "sym-userobj", "printk-msg-only", + "context-info", + "latency-format", + "global-clock", + "sleep-time", NULL }; @@ -326,146 +356,37 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) data->rt_priority = tsk->rt_priority; /* record this tasks comm */ - tracing_record_cmdline(current); + tracing_record_cmdline(tsk); } -/** - * trace_seq_printf - sequence printing of trace information - * @s: trace sequence descriptor - * @fmt: printf format string - * - * The tracer may use either sequence operations or its own - * copy to user routines. To simplify formating of a trace - * trace_seq_printf is used to store strings into a special - * buffer (@s). Then the output may be either used by - * the sequencer or pulled into another buffer. - */ -int -trace_seq_printf(struct trace_seq *s, const char *fmt, ...) +ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, size_t cnt) { - int len = (PAGE_SIZE - 1) - s->len; - va_list ap; + int len; int ret; - if (!len) - return 0; - - va_start(ap, fmt); - ret = vsnprintf(s->buffer + s->len, len, fmt, ap); - va_end(ap); - - /* If we can't write it all, don't bother writing anything */ - if (ret >= len) - return 0; - - s->len += ret; - - return len; -} - -/** - * trace_seq_puts - trace sequence printing of simple string - * @s: trace sequence descriptor - * @str: simple string to record - * - * The tracer may use either the sequence operations or its own - * copy to user routines. This function records a simple string - * into a special buffer (@s) for later retrieval by a sequencer - * or other mechanism. - */ -static int -trace_seq_puts(struct trace_seq *s, const char *str) -{ - int len = strlen(str); - - if (len > ((PAGE_SIZE - 1) - s->len)) - return 0; - - memcpy(s->buffer + s->len, str, len); - s->len += len; - - return len; -} - -static int -trace_seq_putc(struct trace_seq *s, unsigned char c) -{ - if (s->len >= (PAGE_SIZE - 1)) - return 0; - - s->buffer[s->len++] = c; - - return 1; -} - -static int -trace_seq_putmem(struct trace_seq *s, void *mem, size_t len) -{ - if (len > ((PAGE_SIZE - 1) - s->len)) + if (!cnt) return 0; - memcpy(s->buffer + s->len, mem, len); - s->len += len; - - return len; -} - -#define MAX_MEMHEX_BYTES 8 -#define HEX_CHARS (MAX_MEMHEX_BYTES*2 + 1) - -static int -trace_seq_putmem_hex(struct trace_seq *s, void *mem, size_t len) -{ - unsigned char hex[HEX_CHARS]; - unsigned char *data = mem; - int i, j; - -#ifdef __BIG_ENDIAN - for (i = 0, j = 0; i < len; i++) { -#else - for (i = len-1, j = 0; i >= 0; i--) { -#endif - hex[j++] = hex_asc_hi(data[i]); - hex[j++] = hex_asc_lo(data[i]); - } - hex[j++] = ' '; - - return trace_seq_putmem(s, hex, j); -} - -static int -trace_seq_path(struct trace_seq *s, struct path *path) -{ - unsigned char *p; + if (s->len <= s->readpos) + return -EBUSY; - if (s->len >= (PAGE_SIZE - 1)) - return 0; - p = d_path(path, s->buffer + s->len, PAGE_SIZE - s->len); - if (!IS_ERR(p)) { - p = mangle_path(s->buffer + s->len, p, "\n"); - if (p) { - s->len = p - s->buffer; - return 1; - } - } else { - s->buffer[s->len++] = '?'; - return 1; - } + len = s->len - s->readpos; + if (cnt > len) + cnt = len; + ret = copy_to_user(ubuf, s->buffer + s->readpos, cnt); + if (ret == cnt) + return -EFAULT; - return 0; -} + cnt -= ret; -static void -trace_seq_reset(struct trace_seq *s) -{ - s->len = 0; - s->readpos = 0; + s->readpos += cnt; + return cnt; } -ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, size_t cnt) +static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt) { int len; - int ret; + void *ret; if (s->len <= s->readpos) return -EBUSY; @@ -473,11 +394,11 @@ ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, size_t cnt) len = s->len - s->readpos; if (cnt > len) cnt = len; - ret = copy_to_user(ubuf, s->buffer + s->readpos, cnt); - if (ret) + ret = memcpy(buf, s->buffer + s->readpos, cnt); + if (!ret) return -EFAULT; - s->readpos += len; + s->readpos += cnt; return cnt; } @@ -489,7 +410,7 @@ trace_print_seq(struct seq_file *m, struct trace_seq *s) s->buffer[len] = 0; seq_puts(m, s->buffer); - trace_seq_reset(s); + trace_seq_init(s); } /** @@ -543,7 +464,7 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) ftrace_enable_cpu(); - WARN_ON_ONCE(ret); + WARN_ON_ONCE(ret && ret != -EAGAIN); __update_max_tr(tr, tsk, cpu); __raw_spin_unlock(&ftrace_max_lock); @@ -556,6 +477,8 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) * Register a new plugin tracer. */ int register_tracer(struct tracer *type) +__releases(kernel_lock) +__acquires(kernel_lock) { struct tracer *t; int len; @@ -594,9 +517,12 @@ int register_tracer(struct tracer *type) else if (!type->flags->opts) type->flags->opts = dummy_tracer_opt; + if (!type->wait_pipe) + type->wait_pipe = default_wait_pipe; + #ifdef CONFIG_FTRACE_STARTUP_TEST - if (type->selftest) { + if (type->selftest && !tracing_selftest_disabled) { struct tracer *saved_tracer = current_trace; struct trace_array *tr = &global_trace; int i; @@ -638,8 +564,26 @@ int register_tracer(struct tracer *type) out: tracing_selftest_running = false; mutex_unlock(&trace_types_lock); - lock_kernel(); + if (ret || !default_bootup_tracer) + goto out_unlock; + + if (strncmp(default_bootup_tracer, type->name, BOOTUP_TRACER_SIZE)) + goto out_unlock; + + printk(KERN_INFO "Starting tracer '%s'\n", type->name); + /* Do we want this tracer to start on bootup? */ + tracing_set_tracer(type->name); + default_bootup_tracer = NULL; + /* disable other selftests, since this will break it. */ + tracing_selftest_disabled = 1; +#ifdef CONFIG_FTRACE_STARTUP_TEST + printk(KERN_INFO "Disabling FTRACE selftests due to running tracer '%s'\n", + type->name); +#endif + + out_unlock: + lock_kernel(); return ret; } @@ -658,6 +602,15 @@ void unregister_tracer(struct tracer *type) found: *t = (*t)->next; + + if (type == current_trace && tracer_enabled) { + tracer_enabled = 0; + tracing_stop(); + if (current_trace->stop) + current_trace->stop(&global_trace); + current_trace = &nop_trace; + } + if (strlen(type->name) != max_tracer_type_len) goto out; @@ -689,19 +642,20 @@ void tracing_reset_online_cpus(struct trace_array *tr) } #define SAVED_CMDLINES 128 +#define NO_CMDLINE_MAP UINT_MAX static unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1]; static unsigned map_cmdline_to_pid[SAVED_CMDLINES]; static char saved_cmdlines[SAVED_CMDLINES][TASK_COMM_LEN]; static int cmdline_idx; -static DEFINE_SPINLOCK(trace_cmdline_lock); +static raw_spinlock_t trace_cmdline_lock = __RAW_SPIN_LOCK_UNLOCKED; /* temporary disable recording */ -atomic_t trace_record_cmdline_disabled __read_mostly; +static atomic_t trace_record_cmdline_disabled __read_mostly; static void trace_init_cmdlines(void) { - memset(&map_pid_to_cmdline, -1, sizeof(map_pid_to_cmdline)); - memset(&map_cmdline_to_pid, -1, sizeof(map_cmdline_to_pid)); + memset(&map_pid_to_cmdline, NO_CMDLINE_MAP, sizeof(map_pid_to_cmdline)); + memset(&map_cmdline_to_pid, NO_CMDLINE_MAP, sizeof(map_cmdline_to_pid)); cmdline_idx = 0; } @@ -738,13 +692,12 @@ void tracing_start(void) return; spin_lock_irqsave(&tracing_start_lock, flags); - if (--trace_stop_count) - goto out; - - if (trace_stop_count < 0) { - /* Someone screwed up their debugging */ - WARN_ON_ONCE(1); - trace_stop_count = 0; + if (--trace_stop_count) { + if (trace_stop_count < 0) { + /* Someone screwed up their debugging */ + WARN_ON_ONCE(1); + trace_stop_count = 0; + } goto out; } @@ -794,8 +747,7 @@ void trace_stop_cmdline_recording(void); static void trace_save_cmdline(struct task_struct *tsk) { - unsigned map; - unsigned idx; + unsigned pid, idx; if (!tsk->pid || unlikely(tsk->pid > PID_MAX_DEFAULT)) return; @@ -806,17 +758,24 @@ static void trace_save_cmdline(struct task_struct *tsk) * nor do we want to disable interrupts, * so if we miss here, then better luck next time. */ - if (!spin_trylock(&trace_cmdline_lock)) + if (!__raw_spin_trylock(&trace_cmdline_lock)) return; idx = map_pid_to_cmdline[tsk->pid]; - if (idx >= SAVED_CMDLINES) { + if (idx == NO_CMDLINE_MAP) { idx = (cmdline_idx + 1) % SAVED_CMDLINES; - map = map_cmdline_to_pid[idx]; - if (map <= PID_MAX_DEFAULT) - map_pid_to_cmdline[map] = (unsigned)-1; + /* + * Check whether the cmdline buffer at idx has a pid + * mapped. We are going to overwrite that entry so we + * need to clear the map_pid_to_cmdline. Otherwise we + * would read the new comm for the old pid. + */ + pid = map_cmdline_to_pid[idx]; + if (pid != NO_CMDLINE_MAP) + map_pid_to_cmdline[pid] = NO_CMDLINE_MAP; + map_cmdline_to_pid[idx] = tsk->pid; map_pid_to_cmdline[tsk->pid] = idx; cmdline_idx = idx; @@ -824,33 +783,37 @@ static void trace_save_cmdline(struct task_struct *tsk) memcpy(&saved_cmdlines[idx], tsk->comm, TASK_COMM_LEN); - spin_unlock(&trace_cmdline_lock); + __raw_spin_unlock(&trace_cmdline_lock); } -char *trace_find_cmdline(int pid) +void trace_find_cmdline(int pid, char comm[]) { - char *cmdline = "<...>"; unsigned map; - if (!pid) - return "<idle>"; + if (!pid) { + strcpy(comm, "<idle>"); + return; + } - if (pid > PID_MAX_DEFAULT) - goto out; + if (pid > PID_MAX_DEFAULT) { + strcpy(comm, "<...>"); + return; + } + __raw_spin_lock(&trace_cmdline_lock); map = map_pid_to_cmdline[pid]; - if (map >= SAVED_CMDLINES) - goto out; - - cmdline = saved_cmdlines[map]; + if (map != NO_CMDLINE_MAP) + strcpy(comm, saved_cmdlines[map]); + else + strcpy(comm, "<...>"); - out: - return cmdline; + __raw_spin_unlock(&trace_cmdline_lock); } void tracing_record_cmdline(struct task_struct *tsk) { - if (atomic_read(&trace_record_cmdline_disabled)) + if (atomic_read(&trace_record_cmdline_disabled) || !tracer_enabled || + !tracing_is_on()) return; trace_save_cmdline(tsk); @@ -864,7 +827,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, entry->preempt_count = pc & 0xff; entry->pid = (tsk) ? tsk->pid : 0; - entry->tgid = (tsk) ? tsk->tgid : 0; + entry->tgid = (tsk) ? tsk->tgid : 0; entry->flags = #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT (irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) | @@ -876,78 +839,132 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, (need_resched() ? TRACE_FLAG_NEED_RESCHED : 0); } +struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr, + unsigned char type, + unsigned long len, + unsigned long flags, int pc) +{ + struct ring_buffer_event *event; + + event = ring_buffer_lock_reserve(tr->buffer, len); + if (event != NULL) { + struct trace_entry *ent = ring_buffer_event_data(event); + + tracing_generic_entry_update(ent, flags, pc); + ent->type = type; + } + + return event; +} +static void ftrace_trace_stack(struct trace_array *tr, + unsigned long flags, int skip, int pc); +static void ftrace_trace_userstack(struct trace_array *tr, + unsigned long flags, int pc); + +static inline void __trace_buffer_unlock_commit(struct trace_array *tr, + struct ring_buffer_event *event, + unsigned long flags, int pc, + int wake) +{ + ring_buffer_unlock_commit(tr->buffer, event); + + ftrace_trace_stack(tr, flags, 6, pc); + ftrace_trace_userstack(tr, flags, pc); + + if (wake) + trace_wake_up(); +} + +void trace_buffer_unlock_commit(struct trace_array *tr, + struct ring_buffer_event *event, + unsigned long flags, int pc) +{ + __trace_buffer_unlock_commit(tr, event, flags, pc, 1); +} + +struct ring_buffer_event * +trace_current_buffer_lock_reserve(unsigned char type, unsigned long len, + unsigned long flags, int pc) +{ + return trace_buffer_lock_reserve(&global_trace, + type, len, flags, pc); +} + +void trace_current_buffer_unlock_commit(struct ring_buffer_event *event, + unsigned long flags, int pc) +{ + return __trace_buffer_unlock_commit(&global_trace, event, flags, pc, 1); +} + +void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event, + unsigned long flags, int pc) +{ + return __trace_buffer_unlock_commit(&global_trace, event, flags, pc, 0); +} + void -trace_function(struct trace_array *tr, struct trace_array_cpu *data, +trace_function(struct trace_array *tr, unsigned long ip, unsigned long parent_ip, unsigned long flags, int pc) { struct ring_buffer_event *event; struct ftrace_entry *entry; - unsigned long irq_flags; /* If we are reading the ring buffer, don't trace */ if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled)))) return; - event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), - &irq_flags); + event = trace_buffer_lock_reserve(tr, TRACE_FN, sizeof(*entry), + flags, pc); if (!event) return; entry = ring_buffer_event_data(event); - tracing_generic_entry_update(&entry->ent, flags, pc); - entry->ent.type = TRACE_FN; entry->ip = ip; entry->parent_ip = parent_ip; - ring_buffer_unlock_commit(tr->buffer, event, irq_flags); + ring_buffer_unlock_commit(tr->buffer, event); } #ifdef CONFIG_FUNCTION_GRAPH_TRACER -static void __trace_graph_entry(struct trace_array *tr, - struct trace_array_cpu *data, +static int __trace_graph_entry(struct trace_array *tr, struct ftrace_graph_ent *trace, unsigned long flags, int pc) { struct ring_buffer_event *event; struct ftrace_graph_ent_entry *entry; - unsigned long irq_flags; if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled)))) - return; + return 0; - event = ring_buffer_lock_reserve(global_trace.buffer, sizeof(*entry), - &irq_flags); + event = trace_buffer_lock_reserve(&global_trace, TRACE_GRAPH_ENT, + sizeof(*entry), flags, pc); if (!event) - return; + return 0; entry = ring_buffer_event_data(event); - tracing_generic_entry_update(&entry->ent, flags, pc); - entry->ent.type = TRACE_GRAPH_ENT; entry->graph_ent = *trace; - ring_buffer_unlock_commit(global_trace.buffer, event, irq_flags); + ring_buffer_unlock_commit(global_trace.buffer, event); + + return 1; } static void __trace_graph_return(struct trace_array *tr, - struct trace_array_cpu *data, struct ftrace_graph_ret *trace, unsigned long flags, int pc) { struct ring_buffer_event *event; struct ftrace_graph_ret_entry *entry; - unsigned long irq_flags; if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled)))) return; - event = ring_buffer_lock_reserve(global_trace.buffer, sizeof(*entry), - &irq_flags); + event = trace_buffer_lock_reserve(&global_trace, TRACE_GRAPH_RET, + sizeof(*entry), flags, pc); if (!event) return; entry = ring_buffer_event_data(event); - tracing_generic_entry_update(&entry->ent, flags, pc); - entry->ent.type = TRACE_GRAPH_RET; entry->ret = *trace; - ring_buffer_unlock_commit(global_trace.buffer, event, irq_flags); + ring_buffer_unlock_commit(global_trace.buffer, event); } #endif @@ -957,31 +974,23 @@ ftrace(struct trace_array *tr, struct trace_array_cpu *data, int pc) { if (likely(!atomic_read(&data->disabled))) - trace_function(tr, data, ip, parent_ip, flags, pc); + trace_function(tr, ip, parent_ip, flags, pc); } -static void ftrace_trace_stack(struct trace_array *tr, - struct trace_array_cpu *data, - unsigned long flags, - int skip, int pc) +static void __ftrace_trace_stack(struct trace_array *tr, + unsigned long flags, + int skip, int pc) { #ifdef CONFIG_STACKTRACE struct ring_buffer_event *event; struct stack_entry *entry; struct stack_trace trace; - unsigned long irq_flags; - if (!(trace_flags & TRACE_ITER_STACKTRACE)) - return; - - event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), - &irq_flags); + event = trace_buffer_lock_reserve(tr, TRACE_STACK, + sizeof(*entry), flags, pc); if (!event) return; entry = ring_buffer_event_data(event); - tracing_generic_entry_update(&entry->ent, flags, pc); - entry->ent.type = TRACE_STACK; - memset(&entry->caller, 0, sizeof(entry->caller)); trace.nr_entries = 0; @@ -990,38 +999,43 @@ static void ftrace_trace_stack(struct trace_array *tr, trace.entries = entry->caller; save_stack_trace(&trace); - ring_buffer_unlock_commit(tr->buffer, event, irq_flags); + ring_buffer_unlock_commit(tr->buffer, event); #endif } +static void ftrace_trace_stack(struct trace_array *tr, + unsigned long flags, + int skip, int pc) +{ + if (!(trace_flags & TRACE_ITER_STACKTRACE)) + return; + + __ftrace_trace_stack(tr, flags, skip, pc); +} + void __trace_stack(struct trace_array *tr, - struct trace_array_cpu *data, unsigned long flags, - int skip) + int skip, int pc) { - ftrace_trace_stack(tr, data, flags, skip, preempt_count()); + __ftrace_trace_stack(tr, flags, skip, pc); } static void ftrace_trace_userstack(struct trace_array *tr, - struct trace_array_cpu *data, - unsigned long flags, int pc) + unsigned long flags, int pc) { #ifdef CONFIG_STACKTRACE struct ring_buffer_event *event; struct userstack_entry *entry; struct stack_trace trace; - unsigned long irq_flags; if (!(trace_flags & TRACE_ITER_USERSTACKTRACE)) return; - event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), - &irq_flags); + event = trace_buffer_lock_reserve(tr, TRACE_USER_STACK, + sizeof(*entry), flags, pc); if (!event) return; entry = ring_buffer_event_data(event); - tracing_generic_entry_update(&entry->ent, flags, pc); - entry->ent.type = TRACE_USER_STACK; memset(&entry->caller, 0, sizeof(entry->caller)); @@ -1031,70 +1045,58 @@ static void ftrace_trace_userstack(struct trace_array *tr, trace.entries = entry->caller; save_stack_trace_user(&trace); - ring_buffer_unlock_commit(tr->buffer, event, irq_flags); + ring_buffer_unlock_commit(tr->buffer, event); #endif } -void __trace_userstack(struct trace_array *tr, - struct trace_array_cpu *data, - unsigned long flags) +#ifdef UNUSED +static void __trace_userstack(struct trace_array *tr, unsigned long flags) { - ftrace_trace_userstack(tr, data, flags, preempt_count()); + ftrace_trace_userstack(tr, flags, preempt_count()); } +#endif /* UNUSED */ static void -ftrace_trace_special(void *__tr, void *__data, +ftrace_trace_special(void *__tr, unsigned long arg1, unsigned long arg2, unsigned long arg3, int pc) { struct ring_buffer_event *event; - struct trace_array_cpu *data = __data; struct trace_array *tr = __tr; struct special_entry *entry; - unsigned long irq_flags; - event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), - &irq_flags); + event = trace_buffer_lock_reserve(tr, TRACE_SPECIAL, + sizeof(*entry), 0, pc); if (!event) return; entry = ring_buffer_event_data(event); - tracing_generic_entry_update(&entry->ent, 0, pc); - entry->ent.type = TRACE_SPECIAL; entry->arg1 = arg1; entry->arg2 = arg2; entry->arg3 = arg3; - ring_buffer_unlock_commit(tr->buffer, event, irq_flags); - ftrace_trace_stack(tr, data, irq_flags, 4, pc); - ftrace_trace_userstack(tr, data, irq_flags, pc); - - trace_wake_up(); + trace_buffer_unlock_commit(tr, event, 0, pc); } void __trace_special(void *__tr, void *__data, unsigned long arg1, unsigned long arg2, unsigned long arg3) { - ftrace_trace_special(__tr, __data, arg1, arg2, arg3, preempt_count()); + ftrace_trace_special(__tr, arg1, arg2, arg3, preempt_count()); } void tracing_sched_switch_trace(struct trace_array *tr, - struct trace_array_cpu *data, struct task_struct *prev, struct task_struct *next, unsigned long flags, int pc) { struct ring_buffer_event *event; struct ctx_switch_entry *entry; - unsigned long irq_flags; - event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), - &irq_flags); + event = trace_buffer_lock_reserve(tr, TRACE_CTX, + sizeof(*entry), flags, pc); if (!event) return; entry = ring_buffer_event_data(event); - tracing_generic_entry_update(&entry->ent, flags, pc); - entry->ent.type = TRACE_CTX; entry->prev_pid = prev->pid; entry->prev_prio = prev->prio; entry->prev_state = prev->state; @@ -1102,29 +1104,23 @@ tracing_sched_switch_trace(struct trace_array *tr, entry->next_prio = next->prio; entry->next_state = next->state; entry->next_cpu = task_cpu(next); - ring_buffer_unlock_commit(tr->buffer, event, irq_flags); - ftrace_trace_stack(tr, data, flags, 5, pc); - ftrace_trace_userstack(tr, data, flags, pc); + trace_buffer_unlock_commit(tr, event, flags, pc); } void tracing_sched_wakeup_trace(struct trace_array *tr, - struct trace_array_cpu *data, struct task_struct *wakee, struct task_struct *curr, unsigned long flags, int pc) { struct ring_buffer_event *event; struct ctx_switch_entry *entry; - unsigned long irq_flags; - event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), - &irq_flags); + event = trace_buffer_lock_reserve(tr, TRACE_WAKE, + sizeof(*entry), flags, pc); if (!event) return; entry = ring_buffer_event_data(event); - tracing_generic_entry_update(&entry->ent, flags, pc); - entry->ent.type = TRACE_WAKE; entry->prev_pid = curr->pid; entry->prev_prio = curr->prio; entry->prev_state = curr->state; @@ -1132,11 +1128,10 @@ tracing_sched_wakeup_trace(struct trace_array *tr, entry->next_prio = wakee->prio; entry->next_state = wakee->state; entry->next_cpu = task_cpu(wakee); - ring_buffer_unlock_commit(tr->buffer, event, irq_flags); - ftrace_trace_stack(tr, data, flags, 6, pc); - ftrace_trace_userstack(tr, data, flags, pc); - trace_wake_up(); + ring_buffer_unlock_commit(tr->buffer, event); + ftrace_trace_stack(tr, flags, 6, pc); + ftrace_trace_userstack(tr, flags, pc); } void @@ -1157,66 +1152,7 @@ ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) data = tr->data[cpu]; if (likely(atomic_inc_return(&data->disabled) == 1)) - ftrace_trace_special(tr, data, arg1, arg2, arg3, pc); - - atomic_dec(&data->disabled); - local_irq_restore(flags); -} - -#ifdef CONFIG_FUNCTION_TRACER -static void -function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip) -{ - struct trace_array *tr = &global_trace; - struct trace_array_cpu *data; - unsigned long flags; - long disabled; - int cpu, resched; - int pc; - - if (unlikely(!ftrace_function_enabled)) - return; - - pc = preempt_count(); - resched = ftrace_preempt_disable(); - local_save_flags(flags); - cpu = raw_smp_processor_id(); - data = tr->data[cpu]; - disabled = atomic_inc_return(&data->disabled); - - if (likely(disabled == 1)) - trace_function(tr, data, ip, parent_ip, flags, pc); - - atomic_dec(&data->disabled); - ftrace_preempt_enable(resched); -} - -static void -function_trace_call(unsigned long ip, unsigned long parent_ip) -{ - struct trace_array *tr = &global_trace; - struct trace_array_cpu *data; - unsigned long flags; - long disabled; - int cpu; - int pc; - - if (unlikely(!ftrace_function_enabled)) - return; - - /* - * Need to use raw, since this must be called before the - * recursive protection is performed. - */ - local_irq_save(flags); - cpu = raw_smp_processor_id(); - data = tr->data[cpu]; - disabled = atomic_inc_return(&data->disabled); - - if (likely(disabled == 1)) { - pc = preempt_count(); - trace_function(tr, data, ip, parent_ip, flags, pc); - } + ftrace_trace_special(tr, arg1, arg2, arg3, pc); atomic_dec(&data->disabled); local_irq_restore(flags); @@ -1229,6 +1165,7 @@ int trace_graph_entry(struct ftrace_graph_ent *trace) struct trace_array_cpu *data; unsigned long flags; long disabled; + int ret; int cpu; int pc; @@ -1244,15 +1181,18 @@ int trace_graph_entry(struct ftrace_graph_ent *trace) disabled = atomic_inc_return(&data->disabled); if (likely(disabled == 1)) { pc = preempt_count(); - __trace_graph_entry(tr, data, trace, flags, pc); + ret = __trace_graph_entry(tr, trace, flags, pc); + } else { + ret = 0; } /* Only do the atomic if it is not already set */ if (!test_tsk_trace_graph(current)) set_tsk_trace_graph(current); + atomic_dec(&data->disabled); local_irq_restore(flags); - return 1; + return ret; } void trace_graph_return(struct ftrace_graph_ret *trace) @@ -1270,7 +1210,7 @@ void trace_graph_return(struct ftrace_graph_ret *trace) disabled = atomic_inc_return(&data->disabled); if (likely(disabled == 1)) { pc = preempt_count(); - __trace_graph_return(tr, data, trace, flags, pc); + __trace_graph_return(tr, trace, flags, pc); } if (!trace->depth) clear_tsk_trace_graph(current); @@ -1279,30 +1219,122 @@ void trace_graph_return(struct ftrace_graph_ret *trace) } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ -static struct ftrace_ops trace_ops __read_mostly = -{ - .func = function_trace_call, -}; -void tracing_start_function_trace(void) +/** + * trace_vbprintk - write binary msg to tracing buffer + * + */ +int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) { - ftrace_function_enabled = 0; + static raw_spinlock_t trace_buf_lock = + (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED; + static u32 trace_buf[TRACE_BUF_SIZE]; - if (trace_flags & TRACE_ITER_PREEMPTONLY) - trace_ops.func = function_trace_call_preempt_only; - else - trace_ops.func = function_trace_call; + struct ring_buffer_event *event; + struct trace_array *tr = &global_trace; + struct trace_array_cpu *data; + struct bprint_entry *entry; + unsigned long flags; + int resched; + int cpu, len = 0, size, pc; + + if (unlikely(tracing_selftest_running || tracing_disabled)) + return 0; + + /* Don't pollute graph traces with trace_vprintk internals */ + pause_graph_tracing(); + + pc = preempt_count(); + resched = ftrace_preempt_disable(); + cpu = raw_smp_processor_id(); + data = tr->data[cpu]; + + if (unlikely(atomic_read(&data->disabled))) + goto out; + + /* Lockdep uses trace_printk for lock tracing */ + local_irq_save(flags); + __raw_spin_lock(&trace_buf_lock); + len = vbin_printf(trace_buf, TRACE_BUF_SIZE, fmt, args); + + if (len > TRACE_BUF_SIZE || len < 0) + goto out_unlock; + + size = sizeof(*entry) + sizeof(u32) * len; + event = trace_buffer_lock_reserve(tr, TRACE_BPRINT, size, flags, pc); + if (!event) + goto out_unlock; + entry = ring_buffer_event_data(event); + entry->ip = ip; + entry->fmt = fmt; + + memcpy(entry->buf, trace_buf, sizeof(u32) * len); + ring_buffer_unlock_commit(tr->buffer, event); + +out_unlock: + __raw_spin_unlock(&trace_buf_lock); + local_irq_restore(flags); + +out: + ftrace_preempt_enable(resched); + unpause_graph_tracing(); - register_ftrace_function(&trace_ops); - ftrace_function_enabled = 1; + return len; } +EXPORT_SYMBOL_GPL(trace_vbprintk); -void tracing_stop_function_trace(void) +int trace_vprintk(unsigned long ip, const char *fmt, va_list args) { - ftrace_function_enabled = 0; - unregister_ftrace_function(&trace_ops); + static raw_spinlock_t trace_buf_lock = __RAW_SPIN_LOCK_UNLOCKED; + static char trace_buf[TRACE_BUF_SIZE]; + + struct ring_buffer_event *event; + struct trace_array *tr = &global_trace; + struct trace_array_cpu *data; + int cpu, len = 0, size, pc; + struct print_entry *entry; + unsigned long irq_flags; + + if (tracing_disabled || tracing_selftest_running) + return 0; + + pc = preempt_count(); + preempt_disable_notrace(); + cpu = raw_smp_processor_id(); + data = tr->data[cpu]; + + if (unlikely(atomic_read(&data->disabled))) + goto out; + + pause_graph_tracing(); + raw_local_irq_save(irq_flags); + __raw_spin_lock(&trace_buf_lock); + len = vsnprintf(trace_buf, TRACE_BUF_SIZE, fmt, args); + + len = min(len, TRACE_BUF_SIZE-1); + trace_buf[len] = 0; + + size = sizeof(*entry) + len + 1; + event = trace_buffer_lock_reserve(tr, TRACE_PRINT, size, irq_flags, pc); + if (!event) + goto out_unlock; + entry = ring_buffer_event_data(event); + entry->ip = ip; + + memcpy(&entry->buf, trace_buf, len); + entry->buf[len] = 0; + ring_buffer_unlock_commit(tr->buffer, event); + + out_unlock: + __raw_spin_unlock(&trace_buf_lock); + raw_local_irq_restore(irq_flags); + unpause_graph_tracing(); + out: + preempt_enable_notrace(); + + return len; } -#endif +EXPORT_SYMBOL_GPL(trace_vprintk); enum trace_file_type { TRACE_FILE_LAT_FMT = 1, @@ -1345,10 +1377,25 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts) { struct ring_buffer *buffer = iter->tr->buffer; struct trace_entry *ent, *next = NULL; + int cpu_file = iter->cpu_file; u64 next_ts = 0, ts; int next_cpu = -1; int cpu; + /* + * If we are in a per_cpu trace file, don't bother by iterating over + * all cpu and peek directly. + */ + if (cpu_file > TRACE_PIPE_ALL_CPU) { + if (ring_buffer_empty_cpu(buffer, cpu_file)) + return NULL; + ent = peek_next_entry(iter, cpu_file, ent_ts); + if (ent_cpu) + *ent_cpu = cpu_file; + + return ent; + } + for_each_tracing_cpu(cpu) { if (ring_buffer_empty_cpu(buffer, cpu)) @@ -1376,8 +1423,8 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts) } /* Find the next real entry, without updating the iterator itself */ -static struct trace_entry * -find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts) +struct trace_entry *trace_find_next_entry(struct trace_iterator *iter, + int *ent_cpu, u64 *ent_ts) { return __find_next_entry(iter, ent_cpu, ent_ts); } @@ -1426,19 +1473,32 @@ static void *s_next(struct seq_file *m, void *v, loff_t *pos) return ent; } +/* + * No necessary locking here. The worst thing which can + * happen is loosing events consumed at the same time + * by a trace_pipe reader. + * Other than that, we don't risk to crash the ring buffer + * because it serializes the readers. + * + * The current tracer is copied to avoid a global locking + * all around. + */ static void *s_start(struct seq_file *m, loff_t *pos) { struct trace_iterator *iter = m->private; + static struct tracer *old_tracer; + int cpu_file = iter->cpu_file; void *p = NULL; loff_t l = 0; int cpu; + /* copy the tracer to avoid using a global lock all around */ mutex_lock(&trace_types_lock); - - if (!current_trace || current_trace != iter->trace) { - mutex_unlock(&trace_types_lock); - return NULL; + if (unlikely(old_tracer != current_trace && current_trace)) { + old_tracer = current_trace; + *iter->trace = *current_trace; } + mutex_unlock(&trace_types_lock); atomic_inc(&trace_record_cmdline_disabled); @@ -1449,9 +1509,12 @@ static void *s_start(struct seq_file *m, loff_t *pos) ftrace_disable_cpu(); - for_each_tracing_cpu(cpu) { - ring_buffer_iter_reset(iter->buffer_iter[cpu]); - } + if (cpu_file == TRACE_PIPE_ALL_CPU) { + for_each_tracing_cpu(cpu) + ring_buffer_iter_reset(iter->buffer_iter[cpu]); + } else + ring_buffer_iter_reset(iter->buffer_iter[cpu_file]); + ftrace_enable_cpu(); @@ -1469,155 +1532,6 @@ static void *s_start(struct seq_file *m, loff_t *pos) static void s_stop(struct seq_file *m, void *p) { atomic_dec(&trace_record_cmdline_disabled); - mutex_unlock(&trace_types_lock); -} - -#ifdef CONFIG_KRETPROBES -static inline const char *kretprobed(const char *name) -{ - static const char tramp_name[] = "kretprobe_trampoline"; - int size = sizeof(tramp_name); - - if (strncmp(tramp_name, name, size) == 0) - return "[unknown/kretprobe'd]"; - return name; -} -#else -static inline const char *kretprobed(const char *name) -{ - return name; -} -#endif /* CONFIG_KRETPROBES */ - -static int -seq_print_sym_short(struct trace_seq *s, const char *fmt, unsigned long address) -{ -#ifdef CONFIG_KALLSYMS - char str[KSYM_SYMBOL_LEN]; - const char *name; - - kallsyms_lookup(address, NULL, NULL, NULL, str); - - name = kretprobed(str); - - return trace_seq_printf(s, fmt, name); -#endif - return 1; -} - -static int -seq_print_sym_offset(struct trace_seq *s, const char *fmt, - unsigned long address) -{ -#ifdef CONFIG_KALLSYMS - char str[KSYM_SYMBOL_LEN]; - const char *name; - - sprint_symbol(str, address); - name = kretprobed(str); - - return trace_seq_printf(s, fmt, name); -#endif - return 1; -} - -#ifndef CONFIG_64BIT -# define IP_FMT "%08lx" -#else -# define IP_FMT "%016lx" -#endif - -int -seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags) -{ - int ret; - - if (!ip) - return trace_seq_printf(s, "0"); - - if (sym_flags & TRACE_ITER_SYM_OFFSET) - ret = seq_print_sym_offset(s, "%s", ip); - else - ret = seq_print_sym_short(s, "%s", ip); - - if (!ret) - return 0; - - if (sym_flags & TRACE_ITER_SYM_ADDR) - ret = trace_seq_printf(s, " <" IP_FMT ">", ip); - return ret; -} - -static inline int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm, - unsigned long ip, unsigned long sym_flags) -{ - struct file *file = NULL; - unsigned long vmstart = 0; - int ret = 1; - - if (mm) { - const struct vm_area_struct *vma; - - down_read(&mm->mmap_sem); - vma = find_vma(mm, ip); - if (vma) { - file = vma->vm_file; - vmstart = vma->vm_start; - } - if (file) { - ret = trace_seq_path(s, &file->f_path); - if (ret) - ret = trace_seq_printf(s, "[+0x%lx]", ip - vmstart); - } - up_read(&mm->mmap_sem); - } - if (ret && ((sym_flags & TRACE_ITER_SYM_ADDR) || !file)) - ret = trace_seq_printf(s, " <" IP_FMT ">", ip); - return ret; -} - -static int -seq_print_userip_objs(const struct userstack_entry *entry, struct trace_seq *s, - unsigned long sym_flags) -{ - struct mm_struct *mm = NULL; - int ret = 1; - unsigned int i; - - if (trace_flags & TRACE_ITER_SYM_USEROBJ) { - struct task_struct *task; - /* - * we do the lookup on the thread group leader, - * since individual threads might have already quit! - */ - rcu_read_lock(); - task = find_task_by_vpid(entry->ent.tgid); - if (task) - mm = get_task_mm(task); - rcu_read_unlock(); - } - - for (i = 0; i < FTRACE_STACK_ENTRIES; i++) { - unsigned long ip = entry->caller[i]; - - if (ip == ULONG_MAX || !ret) - break; - if (i && ret) - ret = trace_seq_puts(s, " <- "); - if (!ip) { - if (ret) - ret = trace_seq_puts(s, "??"); - continue; - } - if (!ret) - break; - if (ret) - ret = seq_print_user_ip(s, mm, ip, sym_flags); - } - - if (mm) - mmput(mm); - return ret; } static void print_lat_help_header(struct seq_file *m) @@ -1658,11 +1572,11 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter) total = entries + ring_buffer_overruns(iter->tr->buffer); - seq_printf(m, "%s latency trace v1.1.5 on %s\n", + seq_printf(m, "# %s latency trace v1.1.5 on %s\n", name, UTS_RELEASE); - seq_puts(m, "-----------------------------------" + seq_puts(m, "# -----------------------------------" "---------------------------------\n"); - seq_printf(m, " latency: %lu us, #%lu/%lu, CPU#%d |" + seq_printf(m, "# latency: %lu us, #%lu/%lu, CPU#%d |" " (M:%s VP:%d, KP:%d, SP:%d HP:%d", nsecs_to_usecs(data->saved_latency), entries, @@ -1684,121 +1598,24 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter) #else seq_puts(m, ")\n"); #endif - seq_puts(m, " -----------------\n"); - seq_printf(m, " | task: %.16s-%d " + seq_puts(m, "# -----------------\n"); + seq_printf(m, "# | task: %.16s-%d " "(uid:%d nice:%ld policy:%ld rt_prio:%ld)\n", data->comm, data->pid, data->uid, data->nice, data->policy, data->rt_priority); - seq_puts(m, " -----------------\n"); + seq_puts(m, "# -----------------\n"); if (data->critical_start) { - seq_puts(m, " => started at: "); + seq_puts(m, "# => started at: "); seq_print_ip_sym(&iter->seq, data->critical_start, sym_flags); trace_print_seq(m, &iter->seq); - seq_puts(m, "\n => ended at: "); + seq_puts(m, "\n# => ended at: "); seq_print_ip_sym(&iter->seq, data->critical_end, sym_flags); trace_print_seq(m, &iter->seq); - seq_puts(m, "\n"); - } - - seq_puts(m, "\n"); -} - -static void -lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu) -{ - int hardirq, softirq; - char *comm; - - comm = trace_find_cmdline(entry->pid); - - trace_seq_printf(s, "%8.8s-%-5d ", comm, entry->pid); - trace_seq_printf(s, "%3d", cpu); - trace_seq_printf(s, "%c%c", - (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' : - (entry->flags & TRACE_FLAG_IRQS_NOSUPPORT) ? 'X' : '.', - ((entry->flags & TRACE_FLAG_NEED_RESCHED) ? 'N' : '.')); - - hardirq = entry->flags & TRACE_FLAG_HARDIRQ; - softirq = entry->flags & TRACE_FLAG_SOFTIRQ; - if (hardirq && softirq) { - trace_seq_putc(s, 'H'); - } else { - if (hardirq) { - trace_seq_putc(s, 'h'); - } else { - if (softirq) - trace_seq_putc(s, 's'); - else - trace_seq_putc(s, '.'); - } - } - - if (entry->preempt_count) - trace_seq_printf(s, "%x", entry->preempt_count); - else - trace_seq_puts(s, "."); -} - -unsigned long preempt_mark_thresh = 100; - -static void -lat_print_timestamp(struct trace_seq *s, u64 abs_usecs, - unsigned long rel_usecs) -{ - trace_seq_printf(s, " %4lldus", abs_usecs); - if (rel_usecs > preempt_mark_thresh) - trace_seq_puts(s, "!: "); - else if (rel_usecs > 1) - trace_seq_puts(s, "+: "); - else - trace_seq_puts(s, " : "); -} - -static const char state_to_char[] = TASK_STATE_TO_CHAR_STR; - -static int task_state_char(unsigned long state) -{ - int bit = state ? __ffs(state) + 1 : 0; - - return bit < sizeof(state_to_char) - 1 ? state_to_char[bit] : '?'; -} - -/* - * The message is supposed to contain an ending newline. - * If the printing stops prematurely, try to add a newline of our own. - */ -void trace_seq_print_cont(struct trace_seq *s, struct trace_iterator *iter) -{ - struct trace_entry *ent; - struct trace_field_cont *cont; - bool ok = true; - - ent = peek_next_entry(iter, iter->cpu, NULL); - if (!ent || ent->type != TRACE_CONT) { - trace_seq_putc(s, '\n'); - return; + seq_puts(m, "#\n"); } - do { - cont = (struct trace_field_cont *)ent; - if (ok) - ok = (trace_seq_printf(s, "%s", cont->buf) > 0); - - ftrace_disable_cpu(); - - if (iter->buffer_iter[iter->cpu]) - ring_buffer_read(iter->buffer_iter[iter->cpu], NULL); - else - ring_buffer_consume(iter->tr->buffer, iter->cpu, NULL); - - ftrace_enable_cpu(); - - ent = peek_next_entry(iter, iter->cpu, NULL); - } while (ent && ent->type == TRACE_CONT); - - if (!ok) - trace_seq_putc(s, '\n'); + seq_puts(m, "#\n"); } static void test_cpu_buff_start(struct trace_iterator *iter) @@ -1818,472 +1635,89 @@ static void test_cpu_buff_start(struct trace_iterator *iter) trace_seq_printf(s, "##### CPU %u buffer started ####\n", iter->cpu); } -static enum print_line_t -print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu) -{ - struct trace_seq *s = &iter->seq; - unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK); - struct trace_entry *next_entry; - unsigned long verbose = (trace_flags & TRACE_ITER_VERBOSE); - struct trace_entry *entry = iter->ent; - unsigned long abs_usecs; - unsigned long rel_usecs; - u64 next_ts; - char *comm; - int S, T; - int i; - - if (entry->type == TRACE_CONT) - return TRACE_TYPE_HANDLED; - - test_cpu_buff_start(iter); - - next_entry = find_next_entry(iter, NULL, &next_ts); - if (!next_entry) - next_ts = iter->ts; - rel_usecs = ns2usecs(next_ts - iter->ts); - abs_usecs = ns2usecs(iter->ts - iter->tr->time_start); - - if (verbose) { - comm = trace_find_cmdline(entry->pid); - trace_seq_printf(s, "%16s %5d %3d %d %08x %08x [%08lx]" - " %ld.%03ldms (+%ld.%03ldms): ", - comm, - entry->pid, cpu, entry->flags, - entry->preempt_count, trace_idx, - ns2usecs(iter->ts), - abs_usecs/1000, - abs_usecs % 1000, rel_usecs/1000, - rel_usecs % 1000); - } else { - lat_print_generic(s, entry, cpu); - lat_print_timestamp(s, abs_usecs, rel_usecs); - } - switch (entry->type) { - case TRACE_FN: { - struct ftrace_entry *field; - - trace_assign_type(field, entry); - - seq_print_ip_sym(s, field->ip, sym_flags); - trace_seq_puts(s, " ("); - seq_print_ip_sym(s, field->parent_ip, sym_flags); - trace_seq_puts(s, ")\n"); - break; - } - case TRACE_CTX: - case TRACE_WAKE: { - struct ctx_switch_entry *field; - - trace_assign_type(field, entry); - - T = task_state_char(field->next_state); - S = task_state_char(field->prev_state); - comm = trace_find_cmdline(field->next_pid); - trace_seq_printf(s, " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n", - field->prev_pid, - field->prev_prio, - S, entry->type == TRACE_CTX ? "==>" : " +", - field->next_cpu, - field->next_pid, - field->next_prio, - T, comm); - break; - } - case TRACE_SPECIAL: { - struct special_entry *field; - - trace_assign_type(field, entry); - - trace_seq_printf(s, "# %ld %ld %ld\n", - field->arg1, - field->arg2, - field->arg3); - break; - } - case TRACE_STACK: { - struct stack_entry *field; - - trace_assign_type(field, entry); - - for (i = 0; i < FTRACE_STACK_ENTRIES; i++) { - if (i) - trace_seq_puts(s, " <= "); - seq_print_ip_sym(s, field->caller[i], sym_flags); - } - trace_seq_puts(s, "\n"); - break; - } - case TRACE_PRINT: { - struct print_entry *field; - - trace_assign_type(field, entry); - - seq_print_ip_sym(s, field->ip, sym_flags); - trace_seq_printf(s, ": %s", field->buf); - if (entry->flags & TRACE_FLAG_CONT) - trace_seq_print_cont(s, iter); - break; - } - case TRACE_BRANCH: { - struct trace_branch *field; - - trace_assign_type(field, entry); - - trace_seq_printf(s, "[%s] %s:%s:%d\n", - field->correct ? " ok " : " MISS ", - field->func, - field->file, - field->line); - break; - } - case TRACE_USER_STACK: { - struct userstack_entry *field; - - trace_assign_type(field, entry); - - seq_print_userip_objs(field, s, sym_flags); - trace_seq_putc(s, '\n'); - break; - } - default: - trace_seq_printf(s, "Unknown type %d\n", entry->type); - } - return TRACE_TYPE_HANDLED; -} - static enum print_line_t print_trace_fmt(struct trace_iterator *iter) { struct trace_seq *s = &iter->seq; unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK); struct trace_entry *entry; - unsigned long usec_rem; - unsigned long long t; - unsigned long secs; - char *comm; - int ret; - int S, T; - int i; + struct trace_event *event; entry = iter->ent; - if (entry->type == TRACE_CONT) - return TRACE_TYPE_HANDLED; - test_cpu_buff_start(iter); - comm = trace_find_cmdline(iter->ent->pid); - - t = ns2usecs(iter->ts); - usec_rem = do_div(t, 1000000ULL); - secs = (unsigned long)t; - - ret = trace_seq_printf(s, "%16s-%-5d ", comm, entry->pid); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - ret = trace_seq_printf(s, "[%03d] ", iter->cpu); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - ret = trace_seq_printf(s, "%5lu.%06lu: ", secs, usec_rem); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - - switch (entry->type) { - case TRACE_FN: { - struct ftrace_entry *field; - - trace_assign_type(field, entry); - - ret = seq_print_ip_sym(s, field->ip, sym_flags); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - if ((sym_flags & TRACE_ITER_PRINT_PARENT) && - field->parent_ip) { - ret = trace_seq_printf(s, " <-"); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - ret = seq_print_ip_sym(s, - field->parent_ip, - sym_flags); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - } - ret = trace_seq_printf(s, "\n"); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - break; - } - case TRACE_CTX: - case TRACE_WAKE: { - struct ctx_switch_entry *field; - - trace_assign_type(field, entry); - - T = task_state_char(field->next_state); - S = task_state_char(field->prev_state); - ret = trace_seq_printf(s, " %5d:%3d:%c %s [%03d] %5d:%3d:%c\n", - field->prev_pid, - field->prev_prio, - S, - entry->type == TRACE_CTX ? "==>" : " +", - field->next_cpu, - field->next_pid, - field->next_prio, - T); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - break; - } - case TRACE_SPECIAL: { - struct special_entry *field; - - trace_assign_type(field, entry); + event = ftrace_find_event(entry->type); - ret = trace_seq_printf(s, "# %ld %ld %ld\n", - field->arg1, - field->arg2, - field->arg3); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - break; - } - case TRACE_STACK: { - struct stack_entry *field; - - trace_assign_type(field, entry); - - for (i = 0; i < FTRACE_STACK_ENTRIES; i++) { - if (i) { - ret = trace_seq_puts(s, " <= "); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - } - ret = seq_print_ip_sym(s, field->caller[i], - sym_flags); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; + if (trace_flags & TRACE_ITER_CONTEXT_INFO) { + if (iter->iter_flags & TRACE_FILE_LAT_FMT) { + if (!trace_print_lat_context(iter)) + goto partial; + } else { + if (!trace_print_context(iter)) + goto partial; } - ret = trace_seq_puts(s, "\n"); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - break; - } - case TRACE_PRINT: { - struct print_entry *field; - - trace_assign_type(field, entry); - - seq_print_ip_sym(s, field->ip, sym_flags); - trace_seq_printf(s, ": %s", field->buf); - if (entry->flags & TRACE_FLAG_CONT) - trace_seq_print_cont(s, iter); - break; - } - case TRACE_GRAPH_RET: { - return print_graph_function(iter); - } - case TRACE_GRAPH_ENT: { - return print_graph_function(iter); } - case TRACE_BRANCH: { - struct trace_branch *field; - trace_assign_type(field, entry); + if (event) + return event->trace(iter, sym_flags); - trace_seq_printf(s, "[%s] %s:%s:%d\n", - field->correct ? " ok " : " MISS ", - field->func, - field->file, - field->line); - break; - } - case TRACE_USER_STACK: { - struct userstack_entry *field; - - trace_assign_type(field, entry); + if (!trace_seq_printf(s, "Unknown type %d\n", entry->type)) + goto partial; - ret = seq_print_userip_objs(field, s, sym_flags); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - ret = trace_seq_putc(s, '\n'); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - break; - } - } return TRACE_TYPE_HANDLED; +partial: + return TRACE_TYPE_PARTIAL_LINE; } static enum print_line_t print_raw_fmt(struct trace_iterator *iter) { struct trace_seq *s = &iter->seq; struct trace_entry *entry; - int ret; - int S, T; + struct trace_event *event; entry = iter->ent; - if (entry->type == TRACE_CONT) - return TRACE_TYPE_HANDLED; - - ret = trace_seq_printf(s, "%d %d %llu ", - entry->pid, iter->cpu, iter->ts); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - - switch (entry->type) { - case TRACE_FN: { - struct ftrace_entry *field; - - trace_assign_type(field, entry); - - ret = trace_seq_printf(s, "%x %x\n", - field->ip, - field->parent_ip); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - break; - } - case TRACE_CTX: - case TRACE_WAKE: { - struct ctx_switch_entry *field; - - trace_assign_type(field, entry); - - T = task_state_char(field->next_state); - S = entry->type == TRACE_WAKE ? '+' : - task_state_char(field->prev_state); - ret = trace_seq_printf(s, "%d %d %c %d %d %d %c\n", - field->prev_pid, - field->prev_prio, - S, - field->next_cpu, - field->next_pid, - field->next_prio, - T); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - break; + if (trace_flags & TRACE_ITER_CONTEXT_INFO) { + if (!trace_seq_printf(s, "%d %d %llu ", + entry->pid, iter->cpu, iter->ts)) + goto partial; } - case TRACE_SPECIAL: - case TRACE_USER_STACK: - case TRACE_STACK: { - struct special_entry *field; - trace_assign_type(field, entry); + event = ftrace_find_event(entry->type); + if (event) + return event->raw(iter, 0); - ret = trace_seq_printf(s, "# %ld %ld %ld\n", - field->arg1, - field->arg2, - field->arg3); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - break; - } - case TRACE_PRINT: { - struct print_entry *field; - - trace_assign_type(field, entry); + if (!trace_seq_printf(s, "%d ?\n", entry->type)) + goto partial; - trace_seq_printf(s, "# %lx %s", field->ip, field->buf); - if (entry->flags & TRACE_FLAG_CONT) - trace_seq_print_cont(s, iter); - break; - } - } return TRACE_TYPE_HANDLED; +partial: + return TRACE_TYPE_PARTIAL_LINE; } -#define SEQ_PUT_FIELD_RET(s, x) \ -do { \ - if (!trace_seq_putmem(s, &(x), sizeof(x))) \ - return 0; \ -} while (0) - -#define SEQ_PUT_HEX_FIELD_RET(s, x) \ -do { \ - BUILD_BUG_ON(sizeof(x) > MAX_MEMHEX_BYTES); \ - if (!trace_seq_putmem_hex(s, &(x), sizeof(x))) \ - return 0; \ -} while (0) - static enum print_line_t print_hex_fmt(struct trace_iterator *iter) { struct trace_seq *s = &iter->seq; unsigned char newline = '\n'; struct trace_entry *entry; - int S, T; + struct trace_event *event; entry = iter->ent; - if (entry->type == TRACE_CONT) - return TRACE_TYPE_HANDLED; - - SEQ_PUT_HEX_FIELD_RET(s, entry->pid); - SEQ_PUT_HEX_FIELD_RET(s, iter->cpu); - SEQ_PUT_HEX_FIELD_RET(s, iter->ts); - - switch (entry->type) { - case TRACE_FN: { - struct ftrace_entry *field; - - trace_assign_type(field, entry); - - SEQ_PUT_HEX_FIELD_RET(s, field->ip); - SEQ_PUT_HEX_FIELD_RET(s, field->parent_ip); - break; - } - case TRACE_CTX: - case TRACE_WAKE: { - struct ctx_switch_entry *field; - - trace_assign_type(field, entry); - - T = task_state_char(field->next_state); - S = entry->type == TRACE_WAKE ? '+' : - task_state_char(field->prev_state); - SEQ_PUT_HEX_FIELD_RET(s, field->prev_pid); - SEQ_PUT_HEX_FIELD_RET(s, field->prev_prio); - SEQ_PUT_HEX_FIELD_RET(s, S); - SEQ_PUT_HEX_FIELD_RET(s, field->next_cpu); - SEQ_PUT_HEX_FIELD_RET(s, field->next_pid); - SEQ_PUT_HEX_FIELD_RET(s, field->next_prio); - SEQ_PUT_HEX_FIELD_RET(s, T); - break; + if (trace_flags & TRACE_ITER_CONTEXT_INFO) { + SEQ_PUT_HEX_FIELD_RET(s, entry->pid); + SEQ_PUT_HEX_FIELD_RET(s, iter->cpu); + SEQ_PUT_HEX_FIELD_RET(s, iter->ts); } - case TRACE_SPECIAL: - case TRACE_USER_STACK: - case TRACE_STACK: { - struct special_entry *field; - trace_assign_type(field, entry); - - SEQ_PUT_HEX_FIELD_RET(s, field->arg1); - SEQ_PUT_HEX_FIELD_RET(s, field->arg2); - SEQ_PUT_HEX_FIELD_RET(s, field->arg3); - break; - } + event = ftrace_find_event(entry->type); + if (event) { + enum print_line_t ret = event->hex(iter, 0); + if (ret != TRACE_TYPE_HANDLED) + return ret; } - SEQ_PUT_FIELD_RET(s, newline); - - return TRACE_TYPE_HANDLED; -} - -static enum print_line_t print_printk_msg_only(struct trace_iterator *iter) -{ - struct trace_seq *s = &iter->seq; - struct trace_entry *entry = iter->ent; - struct print_entry *field; - int ret; - - trace_assign_type(field, entry); - - ret = trace_seq_printf(s, field->buf); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - if (entry->flags & TRACE_FLAG_CONT) - trace_seq_print_cont(s, iter); + SEQ_PUT_FIELD_RET(s, newline); return TRACE_TYPE_HANDLED; } @@ -2292,59 +1726,37 @@ static enum print_line_t print_bin_fmt(struct trace_iterator *iter) { struct trace_seq *s = &iter->seq; struct trace_entry *entry; + struct trace_event *event; entry = iter->ent; - if (entry->type == TRACE_CONT) - return TRACE_TYPE_HANDLED; - - SEQ_PUT_FIELD_RET(s, entry->pid); - SEQ_PUT_FIELD_RET(s, entry->cpu); - SEQ_PUT_FIELD_RET(s, iter->ts); - - switch (entry->type) { - case TRACE_FN: { - struct ftrace_entry *field; - - trace_assign_type(field, entry); - - SEQ_PUT_FIELD_RET(s, field->ip); - SEQ_PUT_FIELD_RET(s, field->parent_ip); - break; - } - case TRACE_CTX: { - struct ctx_switch_entry *field; - - trace_assign_type(field, entry); - - SEQ_PUT_FIELD_RET(s, field->prev_pid); - SEQ_PUT_FIELD_RET(s, field->prev_prio); - SEQ_PUT_FIELD_RET(s, field->prev_state); - SEQ_PUT_FIELD_RET(s, field->next_pid); - SEQ_PUT_FIELD_RET(s, field->next_prio); - SEQ_PUT_FIELD_RET(s, field->next_state); - break; + if (trace_flags & TRACE_ITER_CONTEXT_INFO) { + SEQ_PUT_FIELD_RET(s, entry->pid); + SEQ_PUT_FIELD_RET(s, iter->cpu); + SEQ_PUT_FIELD_RET(s, iter->ts); } - case TRACE_SPECIAL: - case TRACE_USER_STACK: - case TRACE_STACK: { - struct special_entry *field; - trace_assign_type(field, entry); - - SEQ_PUT_FIELD_RET(s, field->arg1); - SEQ_PUT_FIELD_RET(s, field->arg2); - SEQ_PUT_FIELD_RET(s, field->arg3); - break; - } - } - return 1; + event = ftrace_find_event(entry->type); + return event ? event->binary(iter, 0) : TRACE_TYPE_HANDLED; } static int trace_empty(struct trace_iterator *iter) { int cpu; + /* If we are looking at one CPU buffer, only check that one */ + if (iter->cpu_file != TRACE_PIPE_ALL_CPU) { + cpu = iter->cpu_file; + if (iter->buffer_iter[cpu]) { + if (!ring_buffer_iter_empty(iter->buffer_iter[cpu])) + return 0; + } else { + if (!ring_buffer_empty_cpu(iter->tr->buffer, cpu)) + return 0; + } + return 1; + } + for_each_tracing_cpu(cpu) { if (iter->buffer_iter[cpu]) { if (!ring_buffer_iter_empty(iter->buffer_iter[cpu])) @@ -2368,10 +1780,15 @@ static enum print_line_t print_trace_line(struct trace_iterator *iter) return ret; } + if (iter->ent->type == TRACE_BPRINT && + trace_flags & TRACE_ITER_PRINTK && + trace_flags & TRACE_ITER_PRINTK_MSGONLY) + return trace_print_bprintk_msg_only(iter); + if (iter->ent->type == TRACE_PRINT && trace_flags & TRACE_ITER_PRINTK && trace_flags & TRACE_ITER_PRINTK_MSGONLY) - return print_printk_msg_only(iter); + return trace_print_printk_msg_only(iter); if (trace_flags & TRACE_ITER_BIN) return print_bin_fmt(iter); @@ -2382,9 +1799,6 @@ static enum print_line_t print_trace_line(struct trace_iterator *iter) if (trace_flags & TRACE_ITER_RAW) return print_raw_fmt(iter); - if (iter->iter_flags & TRACE_FILE_LAT_FMT) - return print_lat_fmt(iter, iter->idx, iter->cpu); - return print_trace_fmt(iter); } @@ -2426,30 +1840,40 @@ static struct seq_operations tracer_seq_ops = { }; static struct trace_iterator * -__tracing_open(struct inode *inode, struct file *file, int *ret) +__tracing_open(struct inode *inode, struct file *file) { + long cpu_file = (long) inode->i_private; + void *fail_ret = ERR_PTR(-ENOMEM); struct trace_iterator *iter; struct seq_file *m; - int cpu; + int cpu, ret; - if (tracing_disabled) { - *ret = -ENODEV; - return NULL; - } + if (tracing_disabled) + return ERR_PTR(-ENODEV); iter = kzalloc(sizeof(*iter), GFP_KERNEL); - if (!iter) { - *ret = -ENOMEM; - goto out; - } + if (!iter) + return ERR_PTR(-ENOMEM); + /* + * We make a copy of the current tracer to avoid concurrent + * changes on it while we are reading. + */ mutex_lock(&trace_types_lock); + iter->trace = kzalloc(sizeof(*iter->trace), GFP_KERNEL); + if (!iter->trace) + goto fail; + + if (current_trace) + *iter->trace = *current_trace; + if (current_trace && current_trace->print_max) iter->tr = &max_tr; else - iter->tr = inode->i_private; - iter->trace = current_trace; + iter->tr = &global_trace; iter->pos = -1; + mutex_init(&iter->mutex); + iter->cpu_file = cpu_file; /* Notify the tracer early; before we stop tracing. */ if (iter->trace && iter->trace->open) @@ -2459,20 +1883,24 @@ __tracing_open(struct inode *inode, struct file *file, int *ret) if (ring_buffer_overruns(iter->tr->buffer)) iter->iter_flags |= TRACE_FILE_ANNOTATE; + if (iter->cpu_file == TRACE_PIPE_ALL_CPU) { + for_each_tracing_cpu(cpu) { - for_each_tracing_cpu(cpu) { - + iter->buffer_iter[cpu] = + ring_buffer_read_start(iter->tr->buffer, cpu); + } + } else { + cpu = iter->cpu_file; iter->buffer_iter[cpu] = - ring_buffer_read_start(iter->tr->buffer, cpu); - - if (!iter->buffer_iter[cpu]) - goto fail_buffer; + ring_buffer_read_start(iter->tr->buffer, cpu); } /* TODO stop tracer */ - *ret = seq_open(file, &tracer_seq_ops); - if (*ret) + ret = seq_open(file, &tracer_seq_ops); + if (ret < 0) { + fail_ret = ERR_PTR(ret); goto fail_buffer; + } m = file->private_data; m->private = iter; @@ -2482,7 +1910,6 @@ __tracing_open(struct inode *inode, struct file *file, int *ret) mutex_unlock(&trace_types_lock); - out: return iter; fail_buffer: @@ -2490,10 +1917,12 @@ __tracing_open(struct inode *inode, struct file *file, int *ret) if (iter->buffer_iter[cpu]) ring_buffer_read_finish(iter->buffer_iter[cpu]); } + fail: mutex_unlock(&trace_types_lock); + kfree(iter->trace); kfree(iter); - return ERR_PTR(-ENOMEM); + return fail_ret; } int tracing_open_generic(struct inode *inode, struct file *filp) @@ -2505,12 +1934,17 @@ int tracing_open_generic(struct inode *inode, struct file *filp) return 0; } -int tracing_release(struct inode *inode, struct file *file) +static int tracing_release(struct inode *inode, struct file *file) { struct seq_file *m = (struct seq_file *)file->private_data; - struct trace_iterator *iter = m->private; + struct trace_iterator *iter; int cpu; + if (!(file->f_mode & FMODE_READ)) + return 0; + + iter = m->private; + mutex_lock(&trace_types_lock); for_each_tracing_cpu(cpu) { if (iter->buffer_iter[cpu]) @@ -2525,33 +1959,38 @@ int tracing_release(struct inode *inode, struct file *file) mutex_unlock(&trace_types_lock); seq_release(inode, file); + mutex_destroy(&iter->mutex); + kfree(iter->trace); kfree(iter); return 0; } static int tracing_open(struct inode *inode, struct file *file) { - int ret; - - __tracing_open(inode, file, &ret); - - return ret; -} - -static int tracing_lt_open(struct inode *inode, struct file *file) -{ struct trace_iterator *iter; - int ret; + int ret = 0; - iter = __tracing_open(inode, file, &ret); + /* If this file was open for write, then erase contents */ + if ((file->f_mode & FMODE_WRITE) && + !(file->f_flags & O_APPEND)) { + long cpu = (long) inode->i_private; - if (!ret) - iter->iter_flags |= TRACE_FILE_LAT_FMT; + if (cpu == TRACE_PIPE_ALL_CPU) + tracing_reset_online_cpus(&global_trace); + else + tracing_reset(&global_trace, cpu); + } + if (file->f_mode & FMODE_READ) { + iter = __tracing_open(inode, file); + if (IS_ERR(iter)) + ret = PTR_ERR(iter); + else if (trace_flags & TRACE_ITER_LATENCY_FMT) + iter->iter_flags |= TRACE_FILE_LAT_FMT; + } return ret; } - static void * t_next(struct seq_file *m, void *v, loff_t *pos) { @@ -2623,21 +2062,22 @@ static int show_traces_open(struct inode *inode, struct file *file) return ret; } -static struct file_operations tracing_fops = { - .open = tracing_open, - .read = seq_read, - .llseek = seq_lseek, - .release = tracing_release, -}; +static ssize_t +tracing_write_stub(struct file *filp, const char __user *ubuf, + size_t count, loff_t *ppos) +{ + return count; +} -static struct file_operations tracing_lt_fops = { - .open = tracing_lt_open, +static const struct file_operations tracing_fops = { + .open = tracing_open, .read = seq_read, + .write = tracing_write_stub, .llseek = seq_lseek, .release = tracing_release, }; -static struct file_operations show_traces_fops = { +static const struct file_operations show_traces_fops = { .open = show_traces_open, .read = seq_read, .release = seq_release, @@ -2730,7 +2170,7 @@ err_unlock: return err; } -static struct file_operations tracing_cpumask_fops = { +static const struct file_operations tracing_cpumask_fops = { .open = tracing_open_generic, .read = tracing_cpumask_read, .write = tracing_cpumask_write, @@ -2740,57 +2180,62 @@ static ssize_t tracing_trace_options_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - int i; + struct tracer_opt *trace_opts; + u32 tracer_flags; + int len = 0; char *buf; int r = 0; - int len = 0; - u32 tracer_flags = current_trace->flags->val; - struct tracer_opt *trace_opts = current_trace->flags->opts; + int i; - /* calulate max size */ + /* calculate max size */ for (i = 0; trace_options[i]; i++) { len += strlen(trace_options[i]); - len += 3; /* "no" and space */ + len += 3; /* "no" and newline */ } + mutex_lock(&trace_types_lock); + tracer_flags = current_trace->flags->val; + trace_opts = current_trace->flags->opts; + /* * Increase the size with names of options specific * of the current tracer. */ for (i = 0; trace_opts[i].name; i++) { len += strlen(trace_opts[i].name); - len += 3; /* "no" and space */ + len += 3; /* "no" and newline */ } /* +2 for \n and \0 */ buf = kmalloc(len + 2, GFP_KERNEL); - if (!buf) + if (!buf) { + mutex_unlock(&trace_types_lock); return -ENOMEM; + } for (i = 0; trace_options[i]; i++) { if (trace_flags & (1 << i)) - r += sprintf(buf + r, "%s ", trace_options[i]); + r += sprintf(buf + r, "%s\n", trace_options[i]); else - r += sprintf(buf + r, "no%s ", trace_options[i]); + r += sprintf(buf + r, "no%s\n", trace_options[i]); } for (i = 0; trace_opts[i].name; i++) { if (tracer_flags & trace_opts[i].bit) - r += sprintf(buf + r, "%s ", + r += sprintf(buf + r, "%s\n", trace_opts[i].name); else - r += sprintf(buf + r, "no%s ", + r += sprintf(buf + r, "no%s\n", trace_opts[i].name); } + mutex_unlock(&trace_types_lock); - r += sprintf(buf + r, "\n"); WARN_ON(r >= len + 2); r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r); kfree(buf); - return r; } @@ -2828,6 +2273,34 @@ static int set_tracer_option(struct tracer *trace, char *cmp, int neg) return 0; } +static void set_tracer_flags(unsigned int mask, int enabled) +{ + /* do nothing if flag is already set */ + if (!!(trace_flags & mask) == !!enabled) + return; + + if (enabled) + trace_flags |= mask; + else + trace_flags &= ~mask; + + if (mask == TRACE_ITER_GLOBAL_CLK) { + u64 (*func)(void); + + if (enabled) + func = trace_clock_global; + else + func = trace_clock_local; + + mutex_lock(&trace_types_lock); + ring_buffer_set_clock(global_trace.buffer, func); + + if (max_tr.buffer) + ring_buffer_set_clock(max_tr.buffer, func); + mutex_unlock(&trace_types_lock); + } +} + static ssize_t tracing_trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) @@ -2855,17 +2328,16 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf, int len = strlen(trace_options[i]); if (strncmp(cmp, trace_options[i], len) == 0) { - if (neg) - trace_flags &= ~(1 << i); - else - trace_flags |= (1 << i); + set_tracer_flags(1 << i, !neg); break; } } /* If no option could be set, test the specific tracer options */ if (!trace_options[i]) { + mutex_lock(&trace_types_lock); ret = set_tracer_option(current_trace, cmp, neg); + mutex_unlock(&trace_types_lock); if (ret) return ret; } @@ -2875,7 +2347,7 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf, return cnt; } -static struct file_operations tracing_iter_fops = { +static const struct file_operations tracing_iter_fops = { .open = tracing_open_generic, .read = tracing_trace_options_read, .write = tracing_trace_options_write, @@ -2908,7 +2380,7 @@ tracing_readme_read(struct file *filp, char __user *ubuf, readme_msg, strlen(readme_msg)); } -static struct file_operations tracing_readme_fops = { +static const struct file_operations tracing_readme_fops = { .open = tracing_open_generic, .read = tracing_readme_read, }; @@ -2930,7 +2402,7 @@ tracing_ctrl_write(struct file *filp, const char __user *ubuf, { struct trace_array *tr = filp->private_data; char buf[64]; - long val; + unsigned long val; int ret; if (cnt >= sizeof(buf)) @@ -2985,13 +2457,105 @@ tracing_set_trace_read(struct file *filp, char __user *ubuf, return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } -static int tracing_set_tracer(char *buf) +int tracer_init(struct tracer *t, struct trace_array *tr) +{ + tracing_reset_online_cpus(tr); + return t->init(tr); +} + +static int tracing_resize_ring_buffer(unsigned long size) +{ + int ret; + + /* + * If kernel or user changes the size of the ring buffer + * we use the size that was given, and we can forget about + * expanding it later. + */ + ring_buffer_expanded = 1; + + ret = ring_buffer_resize(global_trace.buffer, size); + if (ret < 0) + return ret; + + ret = ring_buffer_resize(max_tr.buffer, size); + if (ret < 0) { + int r; + + r = ring_buffer_resize(global_trace.buffer, + global_trace.entries); + if (r < 0) { + /* + * AARGH! We are left with different + * size max buffer!!!! + * The max buffer is our "snapshot" buffer. + * When a tracer needs a snapshot (one of the + * latency tracers), it swaps the max buffer + * with the saved snap shot. We succeeded to + * update the size of the main buffer, but failed to + * update the size of the max buffer. But when we tried + * to reset the main buffer to the original size, we + * failed there too. This is very unlikely to + * happen, but if it does, warn and kill all + * tracing. + */ + WARN_ON(1); + tracing_disabled = 1; + } + return ret; + } + + global_trace.entries = size; + + return ret; +} + +/** + * tracing_update_buffers - used by tracing facility to expand ring buffers + * + * To save on memory when the tracing is never used on a system with it + * configured in. The ring buffers are set to a minimum size. But once + * a user starts to use the tracing facility, then they need to grow + * to their default size. + * + * This function is to be called when a tracer is about to be used. + */ +int tracing_update_buffers(void) +{ + int ret = 0; + + mutex_lock(&trace_types_lock); + if (!ring_buffer_expanded) + ret = tracing_resize_ring_buffer(trace_buf_size); + mutex_unlock(&trace_types_lock); + + return ret; +} + +struct trace_option_dentry; + +static struct trace_option_dentry * +create_trace_option_files(struct tracer *tracer); + +static void +destroy_trace_option_files(struct trace_option_dentry *topts); + +static int tracing_set_tracer(const char *buf) { + static struct trace_option_dentry *topts; struct trace_array *tr = &global_trace; struct tracer *t; int ret = 0; mutex_lock(&trace_types_lock); + + if (!ring_buffer_expanded) { + ret = tracing_resize_ring_buffer(trace_buf_size); + if (ret < 0) + goto out; + ret = 0; + } + for (t = trace_types; t; t = t->next) { if (strcmp(t->name, buf) == 0) break; @@ -3007,9 +2571,14 @@ static int tracing_set_tracer(char *buf) if (current_trace && current_trace->reset) current_trace->reset(tr); + destroy_trace_option_files(topts); + current_trace = t; + + topts = create_trace_option_files(current_trace); + if (t->init) { - ret = t->init(tr); + ret = tracer_init(t, tr); if (ret) goto out; } @@ -3072,9 +2641,9 @@ static ssize_t tracing_max_lat_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { - long *ptr = filp->private_data; + unsigned long *ptr = filp->private_data; char buf[64]; - long val; + unsigned long val; int ret; if (cnt >= sizeof(buf)) @@ -3094,54 +2663,96 @@ tracing_max_lat_write(struct file *filp, const char __user *ubuf, return cnt; } -static atomic_t tracing_reader; - static int tracing_open_pipe(struct inode *inode, struct file *filp) { + long cpu_file = (long) inode->i_private; struct trace_iterator *iter; + int ret = 0; if (tracing_disabled) return -ENODEV; - /* We only allow for reader of the pipe */ - if (atomic_inc_return(&tracing_reader) != 1) { - atomic_dec(&tracing_reader); - return -EBUSY; + mutex_lock(&trace_types_lock); + + /* We only allow one reader per cpu */ + if (cpu_file == TRACE_PIPE_ALL_CPU) { + if (!cpumask_empty(tracing_reader_cpumask)) { + ret = -EBUSY; + goto out; + } + cpumask_setall(tracing_reader_cpumask); + } else { + if (!cpumask_test_cpu(cpu_file, tracing_reader_cpumask)) + cpumask_set_cpu(cpu_file, tracing_reader_cpumask); + else { + ret = -EBUSY; + goto out; + } } /* create a buffer to store the information to pass to userspace */ iter = kzalloc(sizeof(*iter), GFP_KERNEL); - if (!iter) - return -ENOMEM; + if (!iter) { + ret = -ENOMEM; + goto out; + } - if (!alloc_cpumask_var(&iter->started, GFP_KERNEL)) { - kfree(iter); - return -ENOMEM; + /* + * We make a copy of the current tracer to avoid concurrent + * changes on it while we are reading. + */ + iter->trace = kmalloc(sizeof(*iter->trace), GFP_KERNEL); + if (!iter->trace) { + ret = -ENOMEM; + goto fail; } + if (current_trace) + *iter->trace = *current_trace; - mutex_lock(&trace_types_lock); + if (!alloc_cpumask_var(&iter->started, GFP_KERNEL)) { + ret = -ENOMEM; + goto fail; + } /* trace pipe does not show start of buffer */ cpumask_setall(iter->started); + iter->cpu_file = cpu_file; iter->tr = &global_trace; - iter->trace = current_trace; + mutex_init(&iter->mutex); filp->private_data = iter; if (iter->trace->pipe_open) iter->trace->pipe_open(iter); + +out: mutex_unlock(&trace_types_lock); + return ret; - return 0; +fail: + kfree(iter->trace); + kfree(iter); + mutex_unlock(&trace_types_lock); + return ret; } static int tracing_release_pipe(struct inode *inode, struct file *file) { struct trace_iterator *iter = file->private_data; + mutex_lock(&trace_types_lock); + + if (iter->cpu_file == TRACE_PIPE_ALL_CPU) + cpumask_clear(tracing_reader_cpumask); + else + cpumask_clear_cpu(iter->cpu_file, tracing_reader_cpumask); + + mutex_unlock(&trace_types_lock); + free_cpumask_var(iter->started); + mutex_destroy(&iter->mutex); + kfree(iter->trace); kfree(iter); - atomic_dec(&tracing_reader); return 0; } @@ -3167,67 +2778,57 @@ tracing_poll_pipe(struct file *filp, poll_table *poll_table) } } -/* - * Consumer reader. - */ -static ssize_t -tracing_read_pipe(struct file *filp, char __user *ubuf, - size_t cnt, loff_t *ppos) + +void default_wait_pipe(struct trace_iterator *iter) { - struct trace_iterator *iter = filp->private_data; - ssize_t sret; + DEFINE_WAIT(wait); - /* return any leftover data */ - sret = trace_seq_to_user(&iter->seq, ubuf, cnt); - if (sret != -EBUSY) - return sret; + prepare_to_wait(&trace_wait, &wait, TASK_INTERRUPTIBLE); - trace_seq_reset(&iter->seq); + if (trace_empty(iter)) + schedule(); - mutex_lock(&trace_types_lock); - if (iter->trace->read) { - sret = iter->trace->read(iter, filp, ubuf, cnt, ppos); - if (sret) - goto out; - } + finish_wait(&trace_wait, &wait); +} + +/* + * This is a make-shift waitqueue. + * A tracer might use this callback on some rare cases: + * + * 1) the current tracer might hold the runqueue lock when it wakes up + * a reader, hence a deadlock (sched, function, and function graph tracers) + * 2) the function tracers, trace all functions, we don't want + * the overhead of calling wake_up and friends + * (and tracing them too) + * + * Anyway, this is really very primitive wakeup. + */ +void poll_wait_pipe(struct trace_iterator *iter) +{ + set_current_state(TASK_INTERRUPTIBLE); + /* sleep for 100 msecs, and try again. */ + schedule_timeout(HZ / 10); +} + +/* Must be called with trace_types_lock mutex held. */ +static int tracing_wait_pipe(struct file *filp) +{ + struct trace_iterator *iter = filp->private_data; -waitagain: - sret = 0; while (trace_empty(iter)) { if ((filp->f_flags & O_NONBLOCK)) { - sret = -EAGAIN; - goto out; + return -EAGAIN; } - /* - * This is a make-shift waitqueue. The reason we don't use - * an actual wait queue is because: - * 1) we only ever have one waiter - * 2) the tracing, traces all functions, we don't want - * the overhead of calling wake_up and friends - * (and tracing them too) - * Anyway, this is really very primitive wakeup. - */ - set_current_state(TASK_INTERRUPTIBLE); - iter->tr->waiter = current; - - mutex_unlock(&trace_types_lock); - - /* sleep for 100 msecs, and try again. */ - schedule_timeout(HZ/10); - - mutex_lock(&trace_types_lock); + mutex_unlock(&iter->mutex); - iter->tr->waiter = NULL; + iter->trace->wait_pipe(iter); - if (signal_pending(current)) { - sret = -EINTR; - goto out; - } + mutex_lock(&iter->mutex); - if (iter->trace != current_trace) - goto out; + if (signal_pending(current)) + return -EINTR; /* * We block until we read something and tracing is disabled. @@ -3240,13 +2841,59 @@ waitagain: */ if (!tracer_enabled && iter->pos) break; + } + + return 1; +} + +/* + * Consumer reader. + */ +static ssize_t +tracing_read_pipe(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct trace_iterator *iter = filp->private_data; + static struct tracer *old_tracer; + ssize_t sret; - continue; + /* return any leftover data */ + sret = trace_seq_to_user(&iter->seq, ubuf, cnt); + if (sret != -EBUSY) + return sret; + + trace_seq_init(&iter->seq); + + /* copy the tracer to avoid using a global lock all around */ + mutex_lock(&trace_types_lock); + if (unlikely(old_tracer != current_trace && current_trace)) { + old_tracer = current_trace; + *iter->trace = *current_trace; + } + mutex_unlock(&trace_types_lock); + + /* + * Avoid more than one consumer on a single file descriptor + * This is just a matter of traces coherency, the ring buffer itself + * is protected. + */ + mutex_lock(&iter->mutex); + if (iter->trace->read) { + sret = iter->trace->read(iter, filp, ubuf, cnt, ppos); + if (sret) + goto out; } +waitagain: + sret = tracing_wait_pipe(filp); + if (sret <= 0) + goto out; + /* stop when tracing is finished */ - if (trace_empty(iter)) + if (trace_empty(iter)) { + sret = 0; goto out; + } if (cnt >= PAGE_SIZE) cnt = PAGE_SIZE - 1; @@ -3267,8 +2914,8 @@ waitagain: iter->seq.len = len; break; } - - trace_consume(iter); + if (ret != TRACE_TYPE_NO_CONSUME) + trace_consume(iter); if (iter->seq.len >= cnt) break; @@ -3277,7 +2924,7 @@ waitagain: /* Now copy what we have to the user */ sret = trace_seq_to_user(&iter->seq, ubuf, cnt); if (iter->seq.readpos >= iter->seq.len) - trace_seq_reset(&iter->seq); + trace_seq_init(&iter->seq); /* * If there was nothing to send to user, inspite of consuming trace @@ -3287,20 +2934,165 @@ waitagain: goto waitagain; out: - mutex_unlock(&trace_types_lock); + mutex_unlock(&iter->mutex); return sret; } +static void tracing_pipe_buf_release(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) +{ + __free_page(buf->page); +} + +static void tracing_spd_release_pipe(struct splice_pipe_desc *spd, + unsigned int idx) +{ + __free_page(spd->pages[idx]); +} + +static struct pipe_buf_operations tracing_pipe_buf_ops = { + .can_merge = 0, + .map = generic_pipe_buf_map, + .unmap = generic_pipe_buf_unmap, + .confirm = generic_pipe_buf_confirm, + .release = tracing_pipe_buf_release, + .steal = generic_pipe_buf_steal, + .get = generic_pipe_buf_get, +}; + +static size_t +tracing_fill_pipe_page(size_t rem, struct trace_iterator *iter) +{ + size_t count; + int ret; + + /* Seq buffer is page-sized, exactly what we need. */ + for (;;) { + count = iter->seq.len; + ret = print_trace_line(iter); + count = iter->seq.len - count; + if (rem < count) { + rem = 0; + iter->seq.len -= count; + break; + } + if (ret == TRACE_TYPE_PARTIAL_LINE) { + iter->seq.len -= count; + break; + } + + trace_consume(iter); + rem -= count; + if (!find_next_entry_inc(iter)) { + rem = 0; + iter->ent = NULL; + break; + } + } + + return rem; +} + +static ssize_t tracing_splice_read_pipe(struct file *filp, + loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, + unsigned int flags) +{ + struct page *pages[PIPE_BUFFERS]; + struct partial_page partial[PIPE_BUFFERS]; + struct trace_iterator *iter = filp->private_data; + struct splice_pipe_desc spd = { + .pages = pages, + .partial = partial, + .nr_pages = 0, /* This gets updated below. */ + .flags = flags, + .ops = &tracing_pipe_buf_ops, + .spd_release = tracing_spd_release_pipe, + }; + static struct tracer *old_tracer; + ssize_t ret; + size_t rem; + unsigned int i; + + /* copy the tracer to avoid using a global lock all around */ + mutex_lock(&trace_types_lock); + if (unlikely(old_tracer != current_trace && current_trace)) { + old_tracer = current_trace; + *iter->trace = *current_trace; + } + mutex_unlock(&trace_types_lock); + + mutex_lock(&iter->mutex); + + if (iter->trace->splice_read) { + ret = iter->trace->splice_read(iter, filp, + ppos, pipe, len, flags); + if (ret) + goto out_err; + } + + ret = tracing_wait_pipe(filp); + if (ret <= 0) + goto out_err; + + if (!iter->ent && !find_next_entry_inc(iter)) { + ret = -EFAULT; + goto out_err; + } + + /* Fill as many pages as possible. */ + for (i = 0, rem = len; i < PIPE_BUFFERS && rem; i++) { + pages[i] = alloc_page(GFP_KERNEL); + if (!pages[i]) + break; + + rem = tracing_fill_pipe_page(rem, iter); + + /* Copy the data into the page, so we can start over. */ + ret = trace_seq_to_buffer(&iter->seq, + page_address(pages[i]), + iter->seq.len); + if (ret < 0) { + __free_page(pages[i]); + break; + } + partial[i].offset = 0; + partial[i].len = iter->seq.len; + + trace_seq_init(&iter->seq); + } + + mutex_unlock(&iter->mutex); + + spd.nr_pages = i; + + return splice_to_pipe(pipe, &spd); + +out_err: + mutex_unlock(&iter->mutex); + + return ret; +} + static ssize_t tracing_entries_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; - char buf[64]; + char buf[96]; int r; - r = sprintf(buf, "%lu\n", tr->entries >> 10); + mutex_lock(&trace_types_lock); + if (!ring_buffer_expanded) + r = sprintf(buf, "%lu (expanded: %lu)\n", + tr->entries >> 10, + trace_buf_size >> 10); + else + r = sprintf(buf, "%lu\n", tr->entries >> 10); + mutex_unlock(&trace_types_lock); + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } @@ -3344,28 +3136,11 @@ tracing_entries_write(struct file *filp, const char __user *ubuf, val <<= 10; if (val != global_trace.entries) { - ret = ring_buffer_resize(global_trace.buffer, val); - if (ret < 0) { - cnt = ret; - goto out; - } - - ret = ring_buffer_resize(max_tr.buffer, val); + ret = tracing_resize_ring_buffer(val); if (ret < 0) { - int r; cnt = ret; - r = ring_buffer_resize(global_trace.buffer, - global_trace.entries); - if (r < 0) { - /* AARGH! We are left with different - * size max buffer!!!! */ - WARN_ON(1); - tracing_disabled = 1; - } goto out; } - - global_trace.entries = val; } filp->f_pos += cnt; @@ -3393,7 +3168,7 @@ static int mark_printk(const char *fmt, ...) int ret; va_list args; va_start(args, fmt); - ret = trace_vprintk(0, -1, fmt, args); + ret = trace_vprintk(0, fmt, args); va_end(args); return ret; } @@ -3433,42 +3208,288 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, return cnt; } -static struct file_operations tracing_max_lat_fops = { +static const struct file_operations tracing_max_lat_fops = { .open = tracing_open_generic, .read = tracing_max_lat_read, .write = tracing_max_lat_write, }; -static struct file_operations tracing_ctrl_fops = { +static const struct file_operations tracing_ctrl_fops = { .open = tracing_open_generic, .read = tracing_ctrl_read, .write = tracing_ctrl_write, }; -static struct file_operations set_tracer_fops = { +static const struct file_operations set_tracer_fops = { .open = tracing_open_generic, .read = tracing_set_trace_read, .write = tracing_set_trace_write, }; -static struct file_operations tracing_pipe_fops = { +static const struct file_operations tracing_pipe_fops = { .open = tracing_open_pipe, .poll = tracing_poll_pipe, .read = tracing_read_pipe, + .splice_read = tracing_splice_read_pipe, .release = tracing_release_pipe, }; -static struct file_operations tracing_entries_fops = { +static const struct file_operations tracing_entries_fops = { .open = tracing_open_generic, .read = tracing_entries_read, .write = tracing_entries_write, }; -static struct file_operations tracing_mark_fops = { +static const struct file_operations tracing_mark_fops = { .open = tracing_open_generic, .write = tracing_mark_write, }; +struct ftrace_buffer_info { + struct trace_array *tr; + void *spare; + int cpu; + unsigned int read; +}; + +static int tracing_buffers_open(struct inode *inode, struct file *filp) +{ + int cpu = (int)(long)inode->i_private; + struct ftrace_buffer_info *info; + + if (tracing_disabled) + return -ENODEV; + + info = kzalloc(sizeof(*info), GFP_KERNEL); + if (!info) + return -ENOMEM; + + info->tr = &global_trace; + info->cpu = cpu; + info->spare = ring_buffer_alloc_read_page(info->tr->buffer); + /* Force reading ring buffer for first read */ + info->read = (unsigned int)-1; + if (!info->spare) + goto out; + + filp->private_data = info; + + return 0; + + out: + kfree(info); + return -ENOMEM; +} + +static ssize_t +tracing_buffers_read(struct file *filp, char __user *ubuf, + size_t count, loff_t *ppos) +{ + struct ftrace_buffer_info *info = filp->private_data; + unsigned int pos; + ssize_t ret; + size_t size; + + if (!count) + return 0; + + /* Do we have previous read data to read? */ + if (info->read < PAGE_SIZE) + goto read; + + info->read = 0; + + ret = ring_buffer_read_page(info->tr->buffer, + &info->spare, + count, + info->cpu, 0); + if (ret < 0) + return 0; + + pos = ring_buffer_page_len(info->spare); + + if (pos < PAGE_SIZE) + memset(info->spare + pos, 0, PAGE_SIZE - pos); + +read: + size = PAGE_SIZE - info->read; + if (size > count) + size = count; + + ret = copy_to_user(ubuf, info->spare + info->read, size); + if (ret == size) + return -EFAULT; + size -= ret; + + *ppos += size; + info->read += size; + + return size; +} + +static int tracing_buffers_release(struct inode *inode, struct file *file) +{ + struct ftrace_buffer_info *info = file->private_data; + + ring_buffer_free_read_page(info->tr->buffer, info->spare); + kfree(info); + + return 0; +} + +struct buffer_ref { + struct ring_buffer *buffer; + void *page; + int ref; +}; + +static void buffer_pipe_buf_release(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) +{ + struct buffer_ref *ref = (struct buffer_ref *)buf->private; + + if (--ref->ref) + return; + + ring_buffer_free_read_page(ref->buffer, ref->page); + kfree(ref); + buf->private = 0; +} + +static int buffer_pipe_buf_steal(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) +{ + return 1; +} + +static void buffer_pipe_buf_get(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) +{ + struct buffer_ref *ref = (struct buffer_ref *)buf->private; + + ref->ref++; +} + +/* Pipe buffer operations for a buffer. */ +static struct pipe_buf_operations buffer_pipe_buf_ops = { + .can_merge = 0, + .map = generic_pipe_buf_map, + .unmap = generic_pipe_buf_unmap, + .confirm = generic_pipe_buf_confirm, + .release = buffer_pipe_buf_release, + .steal = buffer_pipe_buf_steal, + .get = buffer_pipe_buf_get, +}; + +/* + * Callback from splice_to_pipe(), if we need to release some pages + * at the end of the spd in case we error'ed out in filling the pipe. + */ +static void buffer_spd_release(struct splice_pipe_desc *spd, unsigned int i) +{ + struct buffer_ref *ref = + (struct buffer_ref *)spd->partial[i].private; + + if (--ref->ref) + return; + + ring_buffer_free_read_page(ref->buffer, ref->page); + kfree(ref); + spd->partial[i].private = 0; +} + +static ssize_t +tracing_buffers_splice_read(struct file *file, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags) +{ + struct ftrace_buffer_info *info = file->private_data; + struct partial_page partial[PIPE_BUFFERS]; + struct page *pages[PIPE_BUFFERS]; + struct splice_pipe_desc spd = { + .pages = pages, + .partial = partial, + .flags = flags, + .ops = &buffer_pipe_buf_ops, + .spd_release = buffer_spd_release, + }; + struct buffer_ref *ref; + int size, i; + size_t ret; + + /* + * We can't seek on a buffer input + */ + if (unlikely(*ppos)) + return -ESPIPE; + + + for (i = 0; i < PIPE_BUFFERS && len; i++, len -= size) { + struct page *page; + int r; + + ref = kzalloc(sizeof(*ref), GFP_KERNEL); + if (!ref) + break; + + ref->buffer = info->tr->buffer; + ref->page = ring_buffer_alloc_read_page(ref->buffer); + if (!ref->page) { + kfree(ref); + break; + } + + r = ring_buffer_read_page(ref->buffer, &ref->page, + len, info->cpu, 0); + if (r < 0) { + ring_buffer_free_read_page(ref->buffer, + ref->page); + kfree(ref); + break; + } + + /* + * zero out any left over data, this is going to + * user land. + */ + size = ring_buffer_page_len(ref->page); + if (size < PAGE_SIZE) + memset(ref->page + size, 0, PAGE_SIZE - size); + + page = virt_to_page(ref->page); + + spd.pages[i] = page; + spd.partial[i].len = PAGE_SIZE; + spd.partial[i].offset = 0; + spd.partial[i].private = (unsigned long)ref; + spd.nr_pages++; + } + + spd.nr_pages = i; + + /* did we read anything? */ + if (!spd.nr_pages) { + if (flags & SPLICE_F_NONBLOCK) + ret = -EAGAIN; + else + ret = 0; + /* TODO: block */ + return ret; + } + + ret = splice_to_pipe(pipe, &spd); + + return ret; +} + +static const struct file_operations tracing_buffers_fops = { + .open = tracing_buffers_open, + .read = tracing_buffers_read, + .release = tracing_buffers_release, + .splice_read = tracing_buffers_splice_read, + .llseek = no_llseek, +}; + #ifdef CONFIG_DYNAMIC_FTRACE int __weak ftrace_arch_read_dyn_info(char *buf, int size) @@ -3500,7 +3521,7 @@ tracing_read_dyn_info(struct file *filp, char __user *ubuf, return r; } -static struct file_operations tracing_dyn_info_fops = { +static const struct file_operations tracing_dyn_info_fops = { .open = tracing_open_generic, .read = tracing_read_dyn_info, }; @@ -3515,6 +3536,9 @@ struct dentry *tracing_init_dentry(void) if (d_tracer) return d_tracer; + if (!debugfs_initialized()) + return NULL; + d_tracer = debugfs_create_dir("tracing", NULL); if (!d_tracer && !once) { @@ -3526,15 +3550,350 @@ struct dentry *tracing_init_dentry(void) return d_tracer; } +static struct dentry *d_percpu; + +struct dentry *tracing_dentry_percpu(void) +{ + static int once; + struct dentry *d_tracer; + + if (d_percpu) + return d_percpu; + + d_tracer = tracing_init_dentry(); + + if (!d_tracer) + return NULL; + + d_percpu = debugfs_create_dir("per_cpu", d_tracer); + + if (!d_percpu && !once) { + once = 1; + pr_warning("Could not create debugfs directory 'per_cpu'\n"); + return NULL; + } + + return d_percpu; +} + +static void tracing_init_debugfs_percpu(long cpu) +{ + struct dentry *d_percpu = tracing_dentry_percpu(); + struct dentry *entry, *d_cpu; + /* strlen(cpu) + MAX(log10(cpu)) + '\0' */ + char cpu_dir[7]; + + if (cpu > 999 || cpu < 0) + return; + + sprintf(cpu_dir, "cpu%ld", cpu); + d_cpu = debugfs_create_dir(cpu_dir, d_percpu); + if (!d_cpu) { + pr_warning("Could not create debugfs '%s' entry\n", cpu_dir); + return; + } + + /* per cpu trace_pipe */ + entry = debugfs_create_file("trace_pipe", 0444, d_cpu, + (void *) cpu, &tracing_pipe_fops); + if (!entry) + pr_warning("Could not create debugfs 'trace_pipe' entry\n"); + + /* per cpu trace */ + entry = debugfs_create_file("trace", 0644, d_cpu, + (void *) cpu, &tracing_fops); + if (!entry) + pr_warning("Could not create debugfs 'trace' entry\n"); + + entry = debugfs_create_file("trace_pipe_raw", 0444, d_cpu, + (void *) cpu, &tracing_buffers_fops); + if (!entry) + pr_warning("Could not create debugfs 'trace_pipe_raw' entry\n"); +} + #ifdef CONFIG_FTRACE_SELFTEST /* Let selftest have access to static functions in this file */ #include "trace_selftest.c" #endif +struct trace_option_dentry { + struct tracer_opt *opt; + struct tracer_flags *flags; + struct dentry *entry; +}; + +static ssize_t +trace_options_read(struct file *filp, char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + struct trace_option_dentry *topt = filp->private_data; + char *buf; + + if (topt->flags->val & topt->opt->bit) + buf = "1\n"; + else + buf = "0\n"; + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, 2); +} + +static ssize_t +trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + struct trace_option_dentry *topt = filp->private_data; + unsigned long val; + char buf[64]; + int ret; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + ret = strict_strtoul(buf, 10, &val); + if (ret < 0) + return ret; + + ret = 0; + switch (val) { + case 0: + /* do nothing if already cleared */ + if (!(topt->flags->val & topt->opt->bit)) + break; + + mutex_lock(&trace_types_lock); + if (current_trace->set_flag) + ret = current_trace->set_flag(topt->flags->val, + topt->opt->bit, 0); + mutex_unlock(&trace_types_lock); + if (ret) + return ret; + topt->flags->val &= ~topt->opt->bit; + break; + case 1: + /* do nothing if already set */ + if (topt->flags->val & topt->opt->bit) + break; + + mutex_lock(&trace_types_lock); + if (current_trace->set_flag) + ret = current_trace->set_flag(topt->flags->val, + topt->opt->bit, 1); + mutex_unlock(&trace_types_lock); + if (ret) + return ret; + topt->flags->val |= topt->opt->bit; + break; + + default: + return -EINVAL; + } + + *ppos += cnt; + + return cnt; +} + + +static const struct file_operations trace_options_fops = { + .open = tracing_open_generic, + .read = trace_options_read, + .write = trace_options_write, +}; + +static ssize_t +trace_options_core_read(struct file *filp, char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + long index = (long)filp->private_data; + char *buf; + + if (trace_flags & (1 << index)) + buf = "1\n"; + else + buf = "0\n"; + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, 2); +} + +static ssize_t +trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + long index = (long)filp->private_data; + char buf[64]; + unsigned long val; + int ret; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + ret = strict_strtoul(buf, 10, &val); + if (ret < 0) + return ret; + + switch (val) { + case 0: + trace_flags &= ~(1 << index); + break; + case 1: + trace_flags |= 1 << index; + break; + + default: + return -EINVAL; + } + + *ppos += cnt; + + return cnt; +} + +static const struct file_operations trace_options_core_fops = { + .open = tracing_open_generic, + .read = trace_options_core_read, + .write = trace_options_core_write, +}; + +static struct dentry *trace_options_init_dentry(void) +{ + struct dentry *d_tracer; + static struct dentry *t_options; + + if (t_options) + return t_options; + + d_tracer = tracing_init_dentry(); + if (!d_tracer) + return NULL; + + t_options = debugfs_create_dir("options", d_tracer); + if (!t_options) { + pr_warning("Could not create debugfs directory 'options'\n"); + return NULL; + } + + return t_options; +} + +static void +create_trace_option_file(struct trace_option_dentry *topt, + struct tracer_flags *flags, + struct tracer_opt *opt) +{ + struct dentry *t_options; + struct dentry *entry; + + t_options = trace_options_init_dentry(); + if (!t_options) + return; + + topt->flags = flags; + topt->opt = opt; + + entry = debugfs_create_file(opt->name, 0644, t_options, topt, + &trace_options_fops); + + topt->entry = entry; + +} + +static struct trace_option_dentry * +create_trace_option_files(struct tracer *tracer) +{ + struct trace_option_dentry *topts; + struct tracer_flags *flags; + struct tracer_opt *opts; + int cnt; + + if (!tracer) + return NULL; + + flags = tracer->flags; + + if (!flags || !flags->opts) + return NULL; + + opts = flags->opts; + + for (cnt = 0; opts[cnt].name; cnt++) + ; + + topts = kcalloc(cnt + 1, sizeof(*topts), GFP_KERNEL); + if (!topts) + return NULL; + + for (cnt = 0; opts[cnt].name; cnt++) + create_trace_option_file(&topts[cnt], flags, + &opts[cnt]); + + return topts; +} + +static void +destroy_trace_option_files(struct trace_option_dentry *topts) +{ + int cnt; + + if (!topts) + return; + + for (cnt = 0; topts[cnt].opt; cnt++) { + if (topts[cnt].entry) + debugfs_remove(topts[cnt].entry); + } + + kfree(topts); +} + +static struct dentry * +create_trace_option_core_file(const char *option, long index) +{ + struct dentry *t_options; + struct dentry *entry; + + t_options = trace_options_init_dentry(); + if (!t_options) + return NULL; + + entry = debugfs_create_file(option, 0644, t_options, (void *)index, + &trace_options_core_fops); + + return entry; +} + +static __init void create_trace_options_dir(void) +{ + struct dentry *t_options; + struct dentry *entry; + int i; + + t_options = trace_options_init_dentry(); + if (!t_options) + return; + + for (i = 0; trace_options[i]; i++) { + entry = create_trace_option_core_file(trace_options[i], i); + if (!entry) + pr_warning("Could not create debugfs %s entry\n", + trace_options[i]); + } +} + static __init int tracer_init_debugfs(void) { struct dentry *d_tracer; struct dentry *entry; + int cpu; d_tracer = tracing_init_dentry(); @@ -3548,18 +3907,15 @@ static __init int tracer_init_debugfs(void) if (!entry) pr_warning("Could not create debugfs 'trace_options' entry\n"); + create_trace_options_dir(); + entry = debugfs_create_file("tracing_cpumask", 0644, d_tracer, NULL, &tracing_cpumask_fops); if (!entry) pr_warning("Could not create debugfs 'tracing_cpumask' entry\n"); - entry = debugfs_create_file("latency_trace", 0444, d_tracer, - &global_trace, &tracing_lt_fops); - if (!entry) - pr_warning("Could not create debugfs 'latency_trace' entry\n"); - - entry = debugfs_create_file("trace", 0444, d_tracer, - &global_trace, &tracing_fops); + entry = debugfs_create_file("trace", 0644, d_tracer, + (void *) TRACE_PIPE_ALL_CPU, &tracing_fops); if (!entry) pr_warning("Could not create debugfs 'trace' entry\n"); @@ -3590,8 +3946,8 @@ static __init int tracer_init_debugfs(void) if (!entry) pr_warning("Could not create debugfs 'README' entry\n"); - entry = debugfs_create_file("trace_pipe", 0644, d_tracer, - NULL, &tracing_pipe_fops); + entry = debugfs_create_file("trace_pipe", 0444, d_tracer, + (void *) TRACE_PIPE_ALL_CPU, &tracing_pipe_fops); if (!entry) pr_warning("Could not create debugfs " "'trace_pipe' entry\n"); @@ -3619,77 +3975,12 @@ static __init int tracer_init_debugfs(void) #ifdef CONFIG_SYSPROF_TRACER init_tracer_sysprof_debugfs(d_tracer); #endif - return 0; -} - -int trace_vprintk(unsigned long ip, int depth, const char *fmt, va_list args) -{ - static DEFINE_SPINLOCK(trace_buf_lock); - static char trace_buf[TRACE_BUF_SIZE]; - - struct ring_buffer_event *event; - struct trace_array *tr = &global_trace; - struct trace_array_cpu *data; - int cpu, len = 0, size, pc; - struct print_entry *entry; - unsigned long irq_flags; - - if (tracing_disabled || tracing_selftest_running) - return 0; - - pc = preempt_count(); - preempt_disable_notrace(); - cpu = raw_smp_processor_id(); - data = tr->data[cpu]; - - if (unlikely(atomic_read(&data->disabled))) - goto out; - - pause_graph_tracing(); - spin_lock_irqsave(&trace_buf_lock, irq_flags); - len = vsnprintf(trace_buf, TRACE_BUF_SIZE, fmt, args); - - len = min(len, TRACE_BUF_SIZE-1); - trace_buf[len] = 0; - - size = sizeof(*entry) + len + 1; - event = ring_buffer_lock_reserve(tr->buffer, size, &irq_flags); - if (!event) - goto out_unlock; - entry = ring_buffer_event_data(event); - tracing_generic_entry_update(&entry->ent, irq_flags, pc); - entry->ent.type = TRACE_PRINT; - entry->ip = ip; - entry->depth = depth; - - memcpy(&entry->buf, trace_buf, len); - entry->buf[len] = 0; - ring_buffer_unlock_commit(tr->buffer, event, irq_flags); - - out_unlock: - spin_unlock_irqrestore(&trace_buf_lock, irq_flags); - unpause_graph_tracing(); - out: - preempt_enable_notrace(); - - return len; -} -EXPORT_SYMBOL_GPL(trace_vprintk); -int __ftrace_printk(unsigned long ip, const char *fmt, ...) -{ - int ret; - va_list ap; - - if (!(trace_flags & TRACE_ITER_PRINTK)) - return 0; + for_each_tracing_cpu(cpu) + tracing_init_debugfs_percpu(cpu); - va_start(ap, fmt); - ret = trace_vprintk(ip, task_curr_ret_stack(current), fmt, ap); - va_end(ap); - return ret; + return 0; } -EXPORT_SYMBOL_GPL(__ftrace_printk); static int trace_panic_handler(struct notifier_block *this, unsigned long event, void *unused) @@ -3750,14 +4041,15 @@ trace_printk_seq(struct trace_seq *s) printk(KERN_TRACE "%s", s->buffer); - trace_seq_reset(s); + trace_seq_init(s); } -void ftrace_dump(void) +static void __ftrace_dump(bool disable_tracing) { static DEFINE_SPINLOCK(ftrace_dump_lock); /* use static because iter can be a bit big for the stack */ static struct trace_iterator iter; + unsigned int old_userobj; static int dump_ran; unsigned long flags; int cnt = 0, cpu; @@ -3769,21 +4061,26 @@ void ftrace_dump(void) dump_ran = 1; - /* No turning back! */ tracing_off(); - ftrace_kill(); + + if (disable_tracing) + ftrace_kill(); for_each_tracing_cpu(cpu) { atomic_inc(&global_trace.data[cpu]->disabled); } + old_userobj = trace_flags & TRACE_ITER_SYM_USEROBJ; + /* don't look at user memory in panic mode */ trace_flags &= ~TRACE_ITER_SYM_USEROBJ; printk(KERN_TRACE "Dumping ftrace buffer:\n"); + /* Simulate the iterator */ iter.tr = &global_trace; iter.trace = current_trace; + iter.cpu_file = TRACE_PIPE_ALL_CPU; /* * We need to stop all tracing on all CPUS to read the @@ -3819,13 +4116,30 @@ void ftrace_dump(void) else printk(KERN_TRACE "---------------------------------\n"); + /* Re-enable tracing if requested */ + if (!disable_tracing) { + trace_flags |= old_userobj; + + for_each_tracing_cpu(cpu) { + atomic_dec(&global_trace.data[cpu]->disabled); + } + tracing_on(); + } + out: spin_unlock_irqrestore(&ftrace_dump_lock, flags); } +/* By default: disable tracing after the dump */ +void ftrace_dump(void) +{ + __ftrace_dump(true); +} + __init static int tracer_alloc_buffers(void) { struct trace_array_cpu *data; + int ring_buf_size; int i; int ret = -ENOMEM; @@ -3835,11 +4149,21 @@ __init static int tracer_alloc_buffers(void) if (!alloc_cpumask_var(&tracing_cpumask, GFP_KERNEL)) goto out_free_buffer_mask; + if (!alloc_cpumask_var(&tracing_reader_cpumask, GFP_KERNEL)) + goto out_free_tracing_cpumask; + + /* To save memory, keep the ring buffer size to its minimum */ + if (ring_buffer_expanded) + ring_buf_size = trace_buf_size; + else + ring_buf_size = 1; + cpumask_copy(tracing_buffer_mask, cpu_possible_mask); cpumask_copy(tracing_cpumask, cpu_all_mask); + cpumask_clear(tracing_reader_cpumask); /* TODO: make the number of buffers hot pluggable with CPUS */ - global_trace.buffer = ring_buffer_alloc(trace_buf_size, + global_trace.buffer = ring_buffer_alloc(ring_buf_size, TRACE_BUFFER_FLAGS); if (!global_trace.buffer) { printk(KERN_ERR "tracer: failed to allocate ring buffer!\n"); @@ -3850,7 +4174,7 @@ __init static int tracer_alloc_buffers(void) #ifdef CONFIG_TRACER_MAX_TRACE - max_tr.buffer = ring_buffer_alloc(trace_buf_size, + max_tr.buffer = ring_buffer_alloc(ring_buf_size, TRACE_BUFFER_FLAGS); if (!max_tr.buffer) { printk(KERN_ERR "tracer: failed to allocate max ring buffer!\n"); @@ -3871,14 +4195,10 @@ __init static int tracer_alloc_buffers(void) trace_init_cmdlines(); register_tracer(&nop_trace); + current_trace = &nop_trace; #ifdef CONFIG_BOOT_TRACER register_tracer(&boot_tracer); - current_trace = &boot_tracer; - current_trace->init(&global_trace); -#else - current_trace = &nop_trace; #endif - /* All seems OK, enable tracing */ tracing_disabled = 0; @@ -3886,14 +4206,38 @@ __init static int tracer_alloc_buffers(void) &trace_panic_notifier); register_die_notifier(&trace_die_notifier); - ret = 0; + + return 0; out_free_cpumask: + free_cpumask_var(tracing_reader_cpumask); +out_free_tracing_cpumask: free_cpumask_var(tracing_cpumask); out_free_buffer_mask: free_cpumask_var(tracing_buffer_mask); out: return ret; } + +__init static int clear_boot_tracer(void) +{ + /* + * The default tracer at boot buffer is an init section. + * This function is called in lateinit. If we did not + * find the boot tracer, then clear it out, to prevent + * later registration from accessing the buffer that is + * about to be freed. + */ + if (!default_bootup_tracer) + return 0; + + printk(KERN_INFO "ftrace bootup tracer '%s' not registered.\n", + default_bootup_tracer); + default_bootup_tracer = NULL; + + return 0; +} + early_initcall(tracer_alloc_buffers); fs_initcall(tracer_init_debugfs); +late_initcall(clear_boot_tracer); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 4d3d381bfd95..cb0ce3fc36d3 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -9,6 +9,8 @@ #include <linux/mmiotrace.h> #include <linux/ftrace.h> #include <trace/boot.h> +#include <trace/kmemtrace.h> +#include <trace/power.h> enum trace_type { __TRACE_FIRST_TYPE = 0, @@ -16,9 +18,9 @@ enum trace_type { TRACE_FN, TRACE_CTX, TRACE_WAKE, - TRACE_CONT, TRACE_STACK, TRACE_PRINT, + TRACE_BPRINT, TRACE_SPECIAL, TRACE_MMIO_RW, TRACE_MMIO_MAP, @@ -29,9 +31,14 @@ enum trace_type { TRACE_GRAPH_ENT, TRACE_USER_STACK, TRACE_HW_BRANCHES, + TRACE_SYSCALL_ENTER, + TRACE_SYSCALL_EXIT, + TRACE_KMEM_ALLOC, + TRACE_KMEM_FREE, TRACE_POWER, + TRACE_BLK, - __TRACE_LAST_TYPE + __TRACE_LAST_TYPE, }; /* @@ -42,7 +49,6 @@ enum trace_type { */ struct trace_entry { unsigned char type; - unsigned char cpu; unsigned char flags; unsigned char preempt_count; int pid; @@ -60,13 +66,13 @@ struct ftrace_entry { /* Function call entry */ struct ftrace_graph_ent_entry { - struct trace_entry ent; + struct trace_entry ent; struct ftrace_graph_ent graph_ent; }; /* Function return entry */ struct ftrace_graph_ret_entry { - struct trace_entry ent; + struct trace_entry ent; struct ftrace_graph_ret ret; }; extern struct tracer boot_tracer; @@ -112,12 +118,18 @@ struct userstack_entry { }; /* - * ftrace_printk entry: + * trace_printk entry: */ +struct bprint_entry { + struct trace_entry ent; + unsigned long ip; + const char *fmt; + u32 buf[]; +}; + struct print_entry { struct trace_entry ent; unsigned long ip; - int depth; char buf[]; }; @@ -170,15 +182,45 @@ struct trace_power { struct power_trace state_data; }; +struct kmemtrace_alloc_entry { + struct trace_entry ent; + enum kmemtrace_type_id type_id; + unsigned long call_site; + const void *ptr; + size_t bytes_req; + size_t bytes_alloc; + gfp_t gfp_flags; + int node; +}; + +struct kmemtrace_free_entry { + struct trace_entry ent; + enum kmemtrace_type_id type_id; + unsigned long call_site; + const void *ptr; +}; + +struct syscall_trace_enter { + struct trace_entry ent; + int nr; + unsigned long args[]; +}; + +struct syscall_trace_exit { + struct trace_entry ent; + int nr; + unsigned long ret; +}; + + /* * trace_flag_type is an enumeration that holds different * states when a trace occurs. These are: * IRQS_OFF - interrupts were disabled - * IRQS_NOSUPPORT - arch does not support irqs_disabled_flags + * IRQS_NOSUPPORT - arch does not support irqs_disabled_flags * NEED_RESCED - reschedule is requested * HARDIRQ - inside an interrupt handler * SOFTIRQ - inside a softirq handler - * CONT - multiple entries hold the trace item */ enum trace_flag_type { TRACE_FLAG_IRQS_OFF = 0x01, @@ -186,7 +228,6 @@ enum trace_flag_type { TRACE_FLAG_NEED_RESCHED = 0x04, TRACE_FLAG_HARDIRQ = 0x08, TRACE_FLAG_SOFTIRQ = 0x10, - TRACE_FLAG_CONT = 0x20, }; #define TRACE_BUF_SIZE 1024 @@ -198,6 +239,7 @@ enum trace_flag_type { */ struct trace_array_cpu { atomic_t disabled; + void *buffer_page; /* ring buffer spare */ /* these fields get copied into max-trace: */ unsigned long trace_idx; @@ -262,10 +304,10 @@ extern void __ftrace_bad_type(void); do { \ IF_ASSIGN(var, ent, struct ftrace_entry, TRACE_FN); \ IF_ASSIGN(var, ent, struct ctx_switch_entry, 0); \ - IF_ASSIGN(var, ent, struct trace_field_cont, TRACE_CONT); \ IF_ASSIGN(var, ent, struct stack_entry, TRACE_STACK); \ IF_ASSIGN(var, ent, struct userstack_entry, TRACE_USER_STACK);\ IF_ASSIGN(var, ent, struct print_entry, TRACE_PRINT); \ + IF_ASSIGN(var, ent, struct bprint_entry, TRACE_BPRINT); \ IF_ASSIGN(var, ent, struct special_entry, 0); \ IF_ASSIGN(var, ent, struct trace_mmiotrace_rw, \ TRACE_MMIO_RW); \ @@ -279,7 +321,15 @@ extern void __ftrace_bad_type(void); IF_ASSIGN(var, ent, struct ftrace_graph_ret_entry, \ TRACE_GRAPH_RET); \ IF_ASSIGN(var, ent, struct hw_branch_entry, TRACE_HW_BRANCHES);\ - IF_ASSIGN(var, ent, struct trace_power, TRACE_POWER); \ + IF_ASSIGN(var, ent, struct trace_power, TRACE_POWER); \ + IF_ASSIGN(var, ent, struct kmemtrace_alloc_entry, \ + TRACE_KMEM_ALLOC); \ + IF_ASSIGN(var, ent, struct kmemtrace_free_entry, \ + TRACE_KMEM_FREE); \ + IF_ASSIGN(var, ent, struct syscall_trace_enter, \ + TRACE_SYSCALL_ENTER); \ + IF_ASSIGN(var, ent, struct syscall_trace_exit, \ + TRACE_SYSCALL_EXIT); \ __ftrace_bad_type(); \ } while (0) @@ -287,7 +337,8 @@ extern void __ftrace_bad_type(void); enum print_line_t { TRACE_TYPE_PARTIAL_LINE = 0, /* Retry after flushing the seq */ TRACE_TYPE_HANDLED = 1, - TRACE_TYPE_UNHANDLED = 2 /* Relay to other output functions */ + TRACE_TYPE_UNHANDLED = 2, /* Relay to other output functions */ + TRACE_TYPE_NO_CONSUME = 3 /* Handled but ask to not consume */ }; @@ -297,8 +348,8 @@ enum print_line_t { * flags value in struct tracer_flags. */ struct tracer_opt { - const char *name; /* Will appear on the trace_options file */ - u32 bit; /* Mask assigned in val field in tracer_flags */ + const char *name; /* Will appear on the trace_options file */ + u32 bit; /* Mask assigned in val field in tracer_flags */ }; /* @@ -307,28 +358,51 @@ struct tracer_opt { */ struct tracer_flags { u32 val; - struct tracer_opt *opts; + struct tracer_opt *opts; }; /* Makes more easy to define a tracer opt */ #define TRACER_OPT(s, b) .name = #s, .bit = b -/* - * A specific tracer, represented by methods that operate on a trace array: + +/** + * struct tracer - a specific tracer and its callbacks to interact with debugfs + * @name: the name chosen to select it on the available_tracers file + * @init: called when one switches to this tracer (echo name > current_tracer) + * @reset: called when one switches to another tracer + * @start: called when tracing is unpaused (echo 1 > tracing_enabled) + * @stop: called when tracing is paused (echo 0 > tracing_enabled) + * @open: called when the trace file is opened + * @pipe_open: called when the trace_pipe file is opened + * @wait_pipe: override how the user waits for traces on trace_pipe + * @close: called when the trace file is released + * @read: override the default read callback on trace_pipe + * @splice_read: override the default splice_read callback on trace_pipe + * @selftest: selftest to run on boot (see trace_selftest.c) + * @print_headers: override the first lines that describe your columns + * @print_line: callback that prints a trace + * @set_flag: signals one of your private flags changed (trace_options file) + * @flags: your private flags */ struct tracer { const char *name; - /* Your tracer should raise a warning if init fails */ int (*init)(struct trace_array *tr); void (*reset)(struct trace_array *tr); void (*start)(struct trace_array *tr); void (*stop)(struct trace_array *tr); void (*open)(struct trace_iterator *iter); void (*pipe_open)(struct trace_iterator *iter); + void (*wait_pipe)(struct trace_iterator *iter); void (*close)(struct trace_iterator *iter); ssize_t (*read)(struct trace_iterator *iter, struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos); + ssize_t (*splice_read)(struct trace_iterator *iter, + struct file *filp, + loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, + unsigned int flags); #ifdef CONFIG_FTRACE_STARTUP_TEST int (*selftest)(struct tracer *trace, struct trace_array *tr); @@ -339,7 +413,8 @@ struct tracer { int (*set_flag)(u32 old_flags, u32 bit, int set); struct tracer *next; int print_max; - struct tracer_flags *flags; + struct tracer_flags *flags; + struct tracer_stat *stats; }; struct trace_seq { @@ -348,6 +423,16 @@ struct trace_seq { unsigned int readpos; }; +static inline void +trace_seq_init(struct trace_seq *s) +{ + s->len = 0; + s->readpos = 0; +} + + +#define TRACE_PIPE_ALL_CPU -1 + /* * Trace iterator - used by printout routines who present trace * results to users and which routines might sleep, etc: @@ -356,6 +441,8 @@ struct trace_iterator { struct trace_array *tr; struct tracer *trace; void *private; + int cpu_file; + struct mutex mutex; struct ring_buffer_iter *buffer_iter[NR_CPUS]; /* The below is zeroed out in pipe_read */ @@ -371,6 +458,7 @@ struct trace_iterator { cpumask_var_t started; }; +int tracer_init(struct tracer *t, struct trace_array *tr); int tracing_is_enabled(void); void trace_wake_up(void); void tracing_reset(struct trace_array *tr, int cpu); @@ -379,26 +467,50 @@ int tracing_open_generic(struct inode *inode, struct file *filp); struct dentry *tracing_init_dentry(void); void init_tracer_sysprof_debugfs(struct dentry *d_tracer); +struct ring_buffer_event; + +struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr, + unsigned char type, + unsigned long len, + unsigned long flags, + int pc); +void trace_buffer_unlock_commit(struct trace_array *tr, + struct ring_buffer_event *event, + unsigned long flags, int pc); + +struct ring_buffer_event * +trace_current_buffer_lock_reserve(unsigned char type, unsigned long len, + unsigned long flags, int pc); +void trace_current_buffer_unlock_commit(struct ring_buffer_event *event, + unsigned long flags, int pc); +void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event, + unsigned long flags, int pc); + struct trace_entry *tracing_get_trace_entry(struct trace_array *tr, struct trace_array_cpu *data); + +struct trace_entry *trace_find_next_entry(struct trace_iterator *iter, + int *ent_cpu, u64 *ent_ts); + void tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, int pc); +void default_wait_pipe(struct trace_iterator *iter); +void poll_wait_pipe(struct trace_iterator *iter); + void ftrace(struct trace_array *tr, struct trace_array_cpu *data, unsigned long ip, unsigned long parent_ip, unsigned long flags, int pc); void tracing_sched_switch_trace(struct trace_array *tr, - struct trace_array_cpu *data, struct task_struct *prev, struct task_struct *next, unsigned long flags, int pc); void tracing_record_cmdline(struct task_struct *tsk); void tracing_sched_wakeup_trace(struct trace_array *tr, - struct trace_array_cpu *data, struct task_struct *wakee, struct task_struct *cur, unsigned long flags, int pc); @@ -408,14 +520,12 @@ void trace_special(struct trace_array *tr, unsigned long arg2, unsigned long arg3, int pc); void trace_function(struct trace_array *tr, - struct trace_array_cpu *data, unsigned long ip, unsigned long parent_ip, unsigned long flags, int pc); void trace_graph_return(struct ftrace_graph_ret *trace); int trace_graph_entry(struct ftrace_graph_ent *trace); -void trace_hw_branch(struct trace_array *tr, u64 from, u64 to); void tracing_start_cmdline_record(void); void tracing_stop_cmdline_record(void); @@ -434,15 +544,11 @@ void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu); void update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu); -extern cycle_t ftrace_now(int cpu); +void __trace_stack(struct trace_array *tr, + unsigned long flags, + int skip, int pc); -#ifdef CONFIG_FUNCTION_TRACER -void tracing_start_function_trace(void); -void tracing_stop_function_trace(void); -#else -# define tracing_start_function_trace() do { } while (0) -# define tracing_stop_function_trace() do { } while (0) -#endif +extern cycle_t ftrace_now(int cpu); #ifdef CONFIG_CONTEXT_SWITCH_TRACER typedef void @@ -456,10 +562,10 @@ struct tracer_switch_ops { void *private; struct tracer_switch_ops *next; }; - -char *trace_find_cmdline(int pid); #endif /* CONFIG_CONTEXT_SWITCH_TRACER */ +extern void trace_find_cmdline(int pid, char comm[]); + #ifdef CONFIG_DYNAMIC_FTRACE extern unsigned long ftrace_update_tot_cnt; #define DYN_FTRACE_TEST_NAME trace_selftest_dynamic_test_func @@ -469,6 +575,8 @@ extern int DYN_FTRACE_TEST_NAME(void); #ifdef CONFIG_FTRACE_STARTUP_TEST extern int trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr); +extern int trace_selftest_startup_function_graph(struct tracer *trace, + struct trace_array *tr); extern int trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr); extern int trace_selftest_startup_preemptoff(struct tracer *trace, @@ -488,18 +596,11 @@ extern int trace_selftest_startup_branch(struct tracer *trace, #endif /* CONFIG_FTRACE_STARTUP_TEST */ extern void *head_page(struct trace_array_cpu *data); -extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...); -extern void trace_seq_print_cont(struct trace_seq *s, - struct trace_iterator *iter); - -extern int -seq_print_ip_sym(struct trace_seq *s, unsigned long ip, - unsigned long sym_flags); -extern ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, - size_t cnt); extern long ns2usecs(cycle_t nsec); extern int -trace_vprintk(unsigned long ip, int depth, const char *fmt, va_list args); +trace_vbprintk(unsigned long ip, const char *fmt, va_list args); +extern int +trace_vprintk(unsigned long ip, const char *fmt, va_list args); extern unsigned long trace_flags; @@ -580,7 +681,11 @@ enum trace_iterator_flags { TRACE_ITER_ANNOTATE = 0x2000, TRACE_ITER_USERSTACKTRACE = 0x4000, TRACE_ITER_SYM_USEROBJ = 0x8000, - TRACE_ITER_PRINTK_MSGONLY = 0x10000 + TRACE_ITER_PRINTK_MSGONLY = 0x10000, + TRACE_ITER_CONTEXT_INFO = 0x20000, /* Print pid/cpu/time */ + TRACE_ITER_LATENCY_FMT = 0x40000, + TRACE_ITER_GLOBAL_CLK = 0x80000, + TRACE_ITER_SLEEP_TIME = 0x100000, }; /* @@ -601,12 +706,12 @@ extern struct tracer nop_trace; * preempt_enable (after a disable), a schedule might take place * causing an infinite recursion. * - * To prevent this, we read the need_recshed flag before + * To prevent this, we read the need_resched flag before * disabling preemption. When we want to enable preemption we * check the flag, if it is set, then we call preempt_enable_no_resched. * Otherwise, we call preempt_enable. * - * The rational for doing the above is that if need resched is set + * The rational for doing the above is that if need_resched is set * and we have yet to reschedule, we are either in an atomic location * (where we do not need to check for scheduling) or we are inside * the scheduler and do not want to resched. @@ -627,7 +732,7 @@ static inline int ftrace_preempt_disable(void) * * This is a scheduler safe way to enable preemption and not miss * any preemption checks. The disabled saved the state of preemption. - * If resched is set, then we were either inside an atomic or + * If resched is set, then we are either inside an atomic or * are inside the scheduler (we would have already scheduled * otherwise). In this case, we do not want to call normal * preempt_enable, but preempt_enable_no_resched instead. @@ -664,4 +769,118 @@ static inline void trace_branch_disable(void) } #endif /* CONFIG_BRANCH_TRACER */ +/* set ring buffers to default size if not already done so */ +int tracing_update_buffers(void); + +/* trace event type bit fields, not numeric */ +enum { + TRACE_EVENT_TYPE_PRINTF = 1, + TRACE_EVENT_TYPE_RAW = 2, +}; + +struct ftrace_event_field { + struct list_head link; + char *name; + char *type; + int offset; + int size; +}; + +struct ftrace_event_call { + char *name; + char *system; + struct dentry *dir; + int enabled; + int (*regfunc)(void); + void (*unregfunc)(void); + int id; + int (*raw_init)(void); + int (*show_format)(struct trace_seq *s); + int (*define_fields)(void); + struct list_head fields; + struct filter_pred **preds; + +#ifdef CONFIG_EVENT_PROFILE + atomic_t profile_count; + int (*profile_enable)(struct ftrace_event_call *); + void (*profile_disable)(struct ftrace_event_call *); +#endif +}; + +struct event_subsystem { + struct list_head list; + const char *name; + struct dentry *entry; + struct filter_pred **preds; +}; + +#define events_for_each(event) \ + for (event = __start_ftrace_events; \ + (unsigned long)event < (unsigned long)__stop_ftrace_events; \ + event++) + +#define MAX_FILTER_PRED 8 + +struct filter_pred; + +typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event); + +struct filter_pred { + filter_pred_fn_t fn; + u64 val; + char *str_val; + int str_len; + char *field_name; + int offset; + int not; + int or; + int compound; + int clear; +}; + +int trace_define_field(struct ftrace_event_call *call, char *type, + char *name, int offset, int size); +extern void filter_free_pred(struct filter_pred *pred); +extern void filter_print_preds(struct filter_pred **preds, + struct trace_seq *s); +extern int filter_parse(char **pbuf, struct filter_pred *pred); +extern int filter_add_pred(struct ftrace_event_call *call, + struct filter_pred *pred); +extern void filter_free_preds(struct ftrace_event_call *call); +extern int filter_match_preds(struct ftrace_event_call *call, void *rec); +extern void filter_free_subsystem_preds(struct event_subsystem *system); +extern int filter_add_subsystem_pred(struct event_subsystem *system, + struct filter_pred *pred); + +void event_trace_printk(unsigned long ip, const char *fmt, ...); +extern struct ftrace_event_call __start_ftrace_events[]; +extern struct ftrace_event_call __stop_ftrace_events[]; + +#define for_each_event(event) \ + for (event = __start_ftrace_events; \ + (unsigned long)event < (unsigned long)__stop_ftrace_events; \ + event++) + +extern const char *__start___trace_bprintk_fmt[]; +extern const char *__stop___trace_bprintk_fmt[]; + +/* + * The double __builtin_constant_p is because gcc will give us an error + * if we try to allocate the static variable to fmt if it is not a + * constant. Even with the outer if statement optimizing out. + */ +#define event_trace_printk(ip, fmt, args...) \ +do { \ + __trace_printk_check_format(fmt, ##args); \ + tracing_record_cmdline(current); \ + if (__builtin_constant_p(fmt)) { \ + static const char *trace_printk_fmt \ + __attribute__((section("__trace_printk_fmt"))) = \ + __builtin_constant_p(fmt) ? fmt : NULL; \ + \ + __trace_bprintk(ip, trace_printk_fmt, ##args); \ + } else \ + __trace_printk(ip, fmt, ##args); \ +} while (0) + #endif /* _LINUX_KERNEL_TRACE_H */ diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c index 366c8c333e13..7a30fc4c3642 100644 --- a/kernel/trace/trace_boot.c +++ b/kernel/trace/trace_boot.c @@ -11,6 +11,7 @@ #include <linux/kallsyms.h> #include "trace.h" +#include "trace_output.h" static struct trace_array *boot_trace; static bool pre_initcalls_finished; @@ -27,13 +28,13 @@ void start_boot_trace(void) void enable_boot_trace(void) { - if (pre_initcalls_finished) + if (boot_trace && pre_initcalls_finished) tracing_start_sched_switch_record(); } void disable_boot_trace(void) { - if (pre_initcalls_finished) + if (boot_trace && pre_initcalls_finished) tracing_stop_sched_switch_record(); } @@ -42,6 +43,9 @@ static int boot_trace_init(struct trace_array *tr) int cpu; boot_trace = tr; + if (!tr) + return 0; + for_each_cpu(cpu, cpu_possible_mask) tracing_reset(tr, cpu); @@ -128,10 +132,9 @@ void trace_boot_call(struct boot_trace_call *bt, initcall_t fn) { struct ring_buffer_event *event; struct trace_boot_call *entry; - unsigned long irq_flags; struct trace_array *tr = boot_trace; - if (!pre_initcalls_finished) + if (!tr || !pre_initcalls_finished) return; /* Get its name now since this function could @@ -140,18 +143,13 @@ void trace_boot_call(struct boot_trace_call *bt, initcall_t fn) sprint_symbol(bt->func, (unsigned long)fn); preempt_disable(); - event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), - &irq_flags); + event = trace_buffer_lock_reserve(tr, TRACE_BOOT_CALL, + sizeof(*entry), 0, 0); if (!event) goto out; entry = ring_buffer_event_data(event); - tracing_generic_entry_update(&entry->ent, 0, 0); - entry->ent.type = TRACE_BOOT_CALL; entry->boot_call = *bt; - ring_buffer_unlock_commit(tr->buffer, event, irq_flags); - - trace_wake_up(); - + trace_buffer_unlock_commit(tr, event, 0, 0); out: preempt_enable(); } @@ -160,27 +158,21 @@ void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn) { struct ring_buffer_event *event; struct trace_boot_ret *entry; - unsigned long irq_flags; struct trace_array *tr = boot_trace; - if (!pre_initcalls_finished) + if (!tr || !pre_initcalls_finished) return; sprint_symbol(bt->func, (unsigned long)fn); preempt_disable(); - event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), - &irq_flags); + event = trace_buffer_lock_reserve(tr, TRACE_BOOT_RET, + sizeof(*entry), 0, 0); if (!event) goto out; entry = ring_buffer_event_data(event); - tracing_generic_entry_update(&entry->ent, 0, 0); - entry->ent.type = TRACE_BOOT_RET; entry->boot_ret = *bt; - ring_buffer_unlock_commit(tr->buffer, event, irq_flags); - - trace_wake_up(); - + trace_buffer_unlock_commit(tr, event, 0, 0); out: preempt_enable(); } diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c index 6c00feb3bac7..ad8c22efff41 100644 --- a/kernel/trace/trace_branch.c +++ b/kernel/trace/trace_branch.c @@ -14,12 +14,17 @@ #include <linux/hash.h> #include <linux/fs.h> #include <asm/local.h> + #include "trace.h" +#include "trace_stat.h" +#include "trace_output.h" #ifdef CONFIG_BRANCH_TRACER +static struct tracer branch_trace; static int branch_tracing_enabled __read_mostly; static DEFINE_MUTEX(branch_tracing_mutex); + static struct trace_array *branch_tracer; static void @@ -28,7 +33,7 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect) struct trace_array *tr = branch_tracer; struct ring_buffer_event *event; struct trace_branch *entry; - unsigned long flags, irq_flags; + unsigned long flags; int cpu, pc; const char *p; @@ -47,15 +52,13 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect) if (atomic_inc_return(&tr->data[cpu]->disabled) != 1) goto out; - event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), - &irq_flags); + pc = preempt_count(); + event = trace_buffer_lock_reserve(tr, TRACE_BRANCH, + sizeof(*entry), flags, pc); if (!event) goto out; - pc = preempt_count(); entry = ring_buffer_event_data(event); - tracing_generic_entry_update(&entry->ent, flags, pc); - entry->ent.type = TRACE_BRANCH; /* Strip off the path, only save the file */ p = f->file + strlen(f->file); @@ -70,7 +73,7 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect) entry->line = f->line; entry->correct = val == expect; - ring_buffer_unlock_commit(tr->buffer, event, irq_flags); + ring_buffer_unlock_commit(tr->buffer, event); out: atomic_dec(&tr->data[cpu]->disabled); @@ -88,8 +91,6 @@ void trace_likely_condition(struct ftrace_branch_data *f, int val, int expect) int enable_branch_tracing(struct trace_array *tr) { - int ret = 0; - mutex_lock(&branch_tracing_mutex); branch_tracer = tr; /* @@ -100,7 +101,7 @@ int enable_branch_tracing(struct trace_array *tr) branch_tracing_enabled++; mutex_unlock(&branch_tracing_mutex); - return ret; + return 0; } void disable_branch_tracing(void) @@ -128,11 +129,6 @@ static void stop_branch_trace(struct trace_array *tr) static int branch_trace_init(struct trace_array *tr) { - int cpu; - - for_each_online_cpu(cpu) - tracing_reset(tr, cpu); - start_branch_trace(tr); return 0; } @@ -142,22 +138,53 @@ static void branch_trace_reset(struct trace_array *tr) stop_branch_trace(tr); } -struct tracer branch_trace __read_mostly = +static enum print_line_t trace_branch_print(struct trace_iterator *iter, + int flags) +{ + struct trace_branch *field; + + trace_assign_type(field, iter->ent); + + if (trace_seq_printf(&iter->seq, "[%s] %s:%s:%d\n", + field->correct ? " ok " : " MISS ", + field->func, + field->file, + field->line)) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + + +static struct trace_event trace_branch_event = { + .type = TRACE_BRANCH, + .trace = trace_branch_print, +}; + +static struct tracer branch_trace __read_mostly = { .name = "branch", .init = branch_trace_init, .reset = branch_trace_reset, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_branch, -#endif +#endif /* CONFIG_FTRACE_SELFTEST */ }; -__init static int init_branch_trace(void) +__init static int init_branch_tracer(void) { + int ret; + + ret = register_ftrace_event(&trace_branch_event); + if (!ret) { + printk(KERN_WARNING "Warning: could not register " + "branch events\n"); + return 1; + } return register_tracer(&branch_trace); } +device_initcall(init_branch_tracer); -device_initcall(init_branch_trace); #else static inline void trace_likely_condition(struct ftrace_branch_data *f, int val, int expect) @@ -183,66 +210,39 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect) } EXPORT_SYMBOL(ftrace_likely_update); -struct ftrace_pointer { - void *start; - void *stop; - int hit; -}; +extern unsigned long __start_annotated_branch_profile[]; +extern unsigned long __stop_annotated_branch_profile[]; -static void * -t_next(struct seq_file *m, void *v, loff_t *pos) +static int annotated_branch_stat_headers(struct seq_file *m) { - const struct ftrace_pointer *f = m->private; - struct ftrace_branch_data *p = v; - - (*pos)++; - - if (v == (void *)1) - return f->start; - - ++p; - - if ((void *)p >= (void *)f->stop) - return NULL; - - return p; + seq_printf(m, " correct incorrect %% "); + seq_printf(m, " Function " + " File Line\n" + " ------- --------- - " + " -------- " + " ---- ----\n"); + return 0; } -static void *t_start(struct seq_file *m, loff_t *pos) +static inline long get_incorrect_percent(struct ftrace_branch_data *p) { - void *t = (void *)1; - loff_t l = 0; - - for (; t && l < *pos; t = t_next(m, t, &l)) - ; + long percent; - return t; -} + if (p->correct) { + percent = p->incorrect * 100; + percent /= p->correct + p->incorrect; + } else + percent = p->incorrect ? 100 : -1; -static void t_stop(struct seq_file *m, void *p) -{ + return percent; } -static int t_show(struct seq_file *m, void *v) +static int branch_stat_show(struct seq_file *m, void *v) { - const struct ftrace_pointer *fp = m->private; struct ftrace_branch_data *p = v; const char *f; long percent; - if (v == (void *)1) { - if (fp->hit) - seq_printf(m, " miss hit %% "); - else - seq_printf(m, " correct incorrect %% "); - seq_printf(m, " Function " - " File Line\n" - " ------- --------- - " - " -------- " - " ---- ----\n"); - return 0; - } - /* Only print the file, not the path */ f = p->file + strlen(p->file); while (f >= p->file && *f != '/') @@ -252,11 +252,7 @@ static int t_show(struct seq_file *m, void *v) /* * The miss is overlayed on correct, and hit on incorrect. */ - if (p->correct) { - percent = p->incorrect * 100; - percent /= p->correct + p->incorrect; - } else - percent = p->incorrect ? 100 : -1; + percent = get_incorrect_percent(p); seq_printf(m, "%8lu %8lu ", p->correct, p->incorrect); if (percent < 0) @@ -267,76 +263,118 @@ static int t_show(struct seq_file *m, void *v) return 0; } -static struct seq_operations tracing_likely_seq_ops = { - .start = t_start, - .next = t_next, - .stop = t_stop, - .show = t_show, +static void *annotated_branch_stat_start(void) +{ + return __start_annotated_branch_profile; +} + +static void * +annotated_branch_stat_next(void *v, int idx) +{ + struct ftrace_branch_data *p = v; + + ++p; + + if ((void *)p >= (void *)__stop_annotated_branch_profile) + return NULL; + + return p; +} + +static int annotated_branch_stat_cmp(void *p1, void *p2) +{ + struct ftrace_branch_data *a = p1; + struct ftrace_branch_data *b = p2; + + long percent_a, percent_b; + + percent_a = get_incorrect_percent(a); + percent_b = get_incorrect_percent(b); + + if (percent_a < percent_b) + return -1; + if (percent_a > percent_b) + return 1; + else + return 0; +} + +static struct tracer_stat annotated_branch_stats = { + .name = "branch_annotated", + .stat_start = annotated_branch_stat_start, + .stat_next = annotated_branch_stat_next, + .stat_cmp = annotated_branch_stat_cmp, + .stat_headers = annotated_branch_stat_headers, + .stat_show = branch_stat_show }; -static int tracing_branch_open(struct inode *inode, struct file *file) +__init static int init_annotated_branch_stats(void) { int ret; - ret = seq_open(file, &tracing_likely_seq_ops); + ret = register_stat_tracer(&annotated_branch_stats); if (!ret) { - struct seq_file *m = file->private_data; - m->private = (void *)inode->i_private; + printk(KERN_WARNING "Warning: could not register " + "annotated branches stats\n"); + return 1; } - - return ret; + return 0; } - -static const struct file_operations tracing_branch_fops = { - .open = tracing_branch_open, - .read = seq_read, - .llseek = seq_lseek, -}; +fs_initcall(init_annotated_branch_stats); #ifdef CONFIG_PROFILE_ALL_BRANCHES + extern unsigned long __start_branch_profile[]; extern unsigned long __stop_branch_profile[]; -static const struct ftrace_pointer ftrace_branch_pos = { - .start = __start_branch_profile, - .stop = __stop_branch_profile, - .hit = 1, -}; +static int all_branch_stat_headers(struct seq_file *m) +{ + seq_printf(m, " miss hit %% "); + seq_printf(m, " Function " + " File Line\n" + " ------- --------- - " + " -------- " + " ---- ----\n"); + return 0; +} -#endif /* CONFIG_PROFILE_ALL_BRANCHES */ +static void *all_branch_stat_start(void) +{ + return __start_branch_profile; +} -extern unsigned long __start_annotated_branch_profile[]; -extern unsigned long __stop_annotated_branch_profile[]; +static void * +all_branch_stat_next(void *v, int idx) +{ + struct ftrace_branch_data *p = v; -static const struct ftrace_pointer ftrace_annotated_branch_pos = { - .start = __start_annotated_branch_profile, - .stop = __stop_annotated_branch_profile, -}; + ++p; -static __init int ftrace_branch_init(void) -{ - struct dentry *d_tracer; - struct dentry *entry; + if ((void *)p >= (void *)__stop_branch_profile) + return NULL; - d_tracer = tracing_init_dentry(); + return p; +} - entry = debugfs_create_file("profile_annotated_branch", 0444, d_tracer, - (void *)&ftrace_annotated_branch_pos, - &tracing_branch_fops); - if (!entry) - pr_warning("Could not create debugfs " - "'profile_annotatet_branch' entry\n"); +static struct tracer_stat all_branch_stats = { + .name = "branch_all", + .stat_start = all_branch_stat_start, + .stat_next = all_branch_stat_next, + .stat_headers = all_branch_stat_headers, + .stat_show = branch_stat_show +}; -#ifdef CONFIG_PROFILE_ALL_BRANCHES - entry = debugfs_create_file("profile_branch", 0444, d_tracer, - (void *)&ftrace_branch_pos, - &tracing_branch_fops); - if (!entry) - pr_warning("Could not create debugfs" - " 'profile_branch' entry\n"); -#endif +__init static int all_annotated_branch_stats(void) +{ + int ret; + ret = register_stat_tracer(&all_branch_stats); + if (!ret) { + printk(KERN_WARNING "Warning: could not register " + "all branches stats\n"); + return 1; + } return 0; } - -device_initcall(ftrace_branch_init); +fs_initcall(all_annotated_branch_stats); +#endif /* CONFIG_PROFILE_ALL_BRANCHES */ diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c new file mode 100644 index 000000000000..b588fd81f7f9 --- /dev/null +++ b/kernel/trace/trace_clock.c @@ -0,0 +1,109 @@ +/* + * tracing clocks + * + * Copyright (C) 2009 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> + * + * Implements 3 trace clock variants, with differing scalability/precision + * tradeoffs: + * + * - local: CPU-local trace clock + * - medium: scalable global clock with some jitter + * - global: globally monotonic, serialized clock + * + * Tracer plugins will chose a default from these clocks. + */ +#include <linux/spinlock.h> +#include <linux/hardirq.h> +#include <linux/module.h> +#include <linux/percpu.h> +#include <linux/sched.h> +#include <linux/ktime.h> +#include <linux/trace_clock.h> + +/* + * trace_clock_local(): the simplest and least coherent tracing clock. + * + * Useful for tracing that does not cross to other CPUs nor + * does it go through idle events. + */ +u64 notrace trace_clock_local(void) +{ + unsigned long flags; + u64 clock; + + /* + * sched_clock() is an architecture implemented, fast, scalable, + * lockless clock. It is not guaranteed to be coherent across + * CPUs, nor across CPU idle events. + */ + raw_local_irq_save(flags); + clock = sched_clock(); + raw_local_irq_restore(flags); + + return clock; +} + +/* + * trace_clock(): 'inbetween' trace clock. Not completely serialized, + * but not completely incorrect when crossing CPUs either. + * + * This is based on cpu_clock(), which will allow at most ~1 jiffy of + * jitter between CPUs. So it's a pretty scalable clock, but there + * can be offsets in the trace data. + */ +u64 notrace trace_clock(void) +{ + return cpu_clock(raw_smp_processor_id()); +} + + +/* + * trace_clock_global(): special globally coherent trace clock + * + * It has higher overhead than the other trace clocks but is still + * an order of magnitude faster than GTOD derived hardware clocks. + * + * Used by plugins that need globally coherent timestamps. + */ + +static u64 prev_trace_clock_time; + +static raw_spinlock_t trace_clock_lock ____cacheline_aligned_in_smp = + (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED; + +u64 notrace trace_clock_global(void) +{ + unsigned long flags; + int this_cpu; + u64 now; + + raw_local_irq_save(flags); + + this_cpu = raw_smp_processor_id(); + now = cpu_clock(this_cpu); + /* + * If in an NMI context then dont risk lockups and return the + * cpu_clock() time: + */ + if (unlikely(in_nmi())) + goto out; + + __raw_spin_lock(&trace_clock_lock); + + /* + * TODO: if this happens often then maybe we should reset + * my_scd->clock to prev_trace_clock_time+1, to make sure + * we start ticking with the local clock from now on? + */ + if ((s64)(now - prev_trace_clock_time) < 0) + now = prev_trace_clock_time + 1; + + prev_trace_clock_time = now; + + __raw_spin_unlock(&trace_clock_lock); + + out: + raw_local_irq_restore(flags); + + return now; +} diff --git a/kernel/trace/trace_event_profile.c b/kernel/trace/trace_event_profile.c new file mode 100644 index 000000000000..22cba9970776 --- /dev/null +++ b/kernel/trace/trace_event_profile.c @@ -0,0 +1,31 @@ +/* + * trace event based perf counter profiling + * + * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra <pzijlstr@redhat.com> + * + */ + +#include "trace.h" + +int ftrace_profile_enable(int event_id) +{ + struct ftrace_event_call *event; + + for_each_event(event) { + if (event->id == event_id) + return event->profile_enable(event); + } + + return -EINVAL; +} + +void ftrace_profile_disable(int event_id) +{ + struct ftrace_event_call *event; + + for_each_event(event) { + if (event->id == event_id) + return event->profile_disable(event); + } +} + diff --git a/kernel/trace/trace_event_types.h b/kernel/trace/trace_event_types.h new file mode 100644 index 000000000000..fd78bee71dd7 --- /dev/null +++ b/kernel/trace/trace_event_types.h @@ -0,0 +1,173 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM ftrace + +/* + * We cheat and use the proto type field as the ID + * and args as the entry type (minus 'struct') + */ +TRACE_EVENT_FORMAT(function, TRACE_FN, ftrace_entry, ignore, + TRACE_STRUCT( + TRACE_FIELD(unsigned long, ip, ip) + TRACE_FIELD(unsigned long, parent_ip, parent_ip) + ), + TP_RAW_FMT(" %lx <-- %lx") +); + +TRACE_EVENT_FORMAT(funcgraph_entry, TRACE_GRAPH_ENT, + ftrace_graph_ent_entry, ignore, + TRACE_STRUCT( + TRACE_FIELD(unsigned long, graph_ent.func, func) + TRACE_FIELD(int, graph_ent.depth, depth) + ), + TP_RAW_FMT("--> %lx (%d)") +); + +TRACE_EVENT_FORMAT(funcgraph_exit, TRACE_GRAPH_RET, + ftrace_graph_ret_entry, ignore, + TRACE_STRUCT( + TRACE_FIELD(unsigned long, ret.func, func) + TRACE_FIELD(int, ret.depth, depth) + ), + TP_RAW_FMT("<-- %lx (%d)") +); + +TRACE_EVENT_FORMAT(wakeup, TRACE_WAKE, ctx_switch_entry, ignore, + TRACE_STRUCT( + TRACE_FIELD(unsigned int, prev_pid, prev_pid) + TRACE_FIELD(unsigned char, prev_prio, prev_prio) + TRACE_FIELD(unsigned char, prev_state, prev_state) + TRACE_FIELD(unsigned int, next_pid, next_pid) + TRACE_FIELD(unsigned char, next_prio, next_prio) + TRACE_FIELD(unsigned char, next_state, next_state) + TRACE_FIELD(unsigned int, next_cpu, next_cpu) + ), + TP_RAW_FMT("%u:%u:%u ==+ %u:%u:%u [%03u]") +); + +TRACE_EVENT_FORMAT(context_switch, TRACE_CTX, ctx_switch_entry, ignore, + TRACE_STRUCT( + TRACE_FIELD(unsigned int, prev_pid, prev_pid) + TRACE_FIELD(unsigned char, prev_prio, prev_prio) + TRACE_FIELD(unsigned char, prev_state, prev_state) + TRACE_FIELD(unsigned int, next_pid, next_pid) + TRACE_FIELD(unsigned char, next_prio, next_prio) + TRACE_FIELD(unsigned char, next_state, next_state) + TRACE_FIELD(unsigned int, next_cpu, next_cpu) + ), + TP_RAW_FMT("%u:%u:%u ==+ %u:%u:%u [%03u]") +); + +TRACE_EVENT_FORMAT(special, TRACE_SPECIAL, special_entry, ignore, + TRACE_STRUCT( + TRACE_FIELD(unsigned long, arg1, arg1) + TRACE_FIELD(unsigned long, arg2, arg2) + TRACE_FIELD(unsigned long, arg3, arg3) + ), + TP_RAW_FMT("(%08lx) (%08lx) (%08lx)") +); + +/* + * Stack-trace entry: + */ + +/* #define FTRACE_STACK_ENTRIES 8 */ + +TRACE_EVENT_FORMAT(kernel_stack, TRACE_STACK, stack_entry, ignore, + TRACE_STRUCT( + TRACE_FIELD(unsigned long, caller[0], stack0) + TRACE_FIELD(unsigned long, caller[1], stack1) + TRACE_FIELD(unsigned long, caller[2], stack2) + TRACE_FIELD(unsigned long, caller[3], stack3) + TRACE_FIELD(unsigned long, caller[4], stack4) + TRACE_FIELD(unsigned long, caller[5], stack5) + TRACE_FIELD(unsigned long, caller[6], stack6) + TRACE_FIELD(unsigned long, caller[7], stack7) + ), + TP_RAW_FMT("\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n" + "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n") +); + +TRACE_EVENT_FORMAT(user_stack, TRACE_USER_STACK, userstack_entry, ignore, + TRACE_STRUCT( + TRACE_FIELD(unsigned long, caller[0], stack0) + TRACE_FIELD(unsigned long, caller[1], stack1) + TRACE_FIELD(unsigned long, caller[2], stack2) + TRACE_FIELD(unsigned long, caller[3], stack3) + TRACE_FIELD(unsigned long, caller[4], stack4) + TRACE_FIELD(unsigned long, caller[5], stack5) + TRACE_FIELD(unsigned long, caller[6], stack6) + TRACE_FIELD(unsigned long, caller[7], stack7) + ), + TP_RAW_FMT("\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n" + "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n") +); + +TRACE_EVENT_FORMAT(bprint, TRACE_BPRINT, bprint_entry, ignore, + TRACE_STRUCT( + TRACE_FIELD(unsigned long, ip, ip) + TRACE_FIELD(char *, fmt, fmt) + TRACE_FIELD_ZERO_CHAR(buf) + ), + TP_RAW_FMT("%08lx (%d) fmt:%p %s") +); + +TRACE_EVENT_FORMAT(print, TRACE_PRINT, print_entry, ignore, + TRACE_STRUCT( + TRACE_FIELD(unsigned long, ip, ip) + TRACE_FIELD_ZERO_CHAR(buf) + ), + TP_RAW_FMT("%08lx (%d) fmt:%p %s") +); + +TRACE_EVENT_FORMAT(branch, TRACE_BRANCH, trace_branch, ignore, + TRACE_STRUCT( + TRACE_FIELD(unsigned int, line, line) + TRACE_FIELD_SPECIAL(char func[TRACE_FUNC_SIZE+1], func, func) + TRACE_FIELD_SPECIAL(char file[TRACE_FUNC_SIZE+1], file, file) + TRACE_FIELD(char, correct, correct) + ), + TP_RAW_FMT("%u:%s:%s (%u)") +); + +TRACE_EVENT_FORMAT(hw_branch, TRACE_HW_BRANCHES, hw_branch_entry, ignore, + TRACE_STRUCT( + TRACE_FIELD(u64, from, from) + TRACE_FIELD(u64, to, to) + ), + TP_RAW_FMT("from: %llx to: %llx") +); + +TRACE_EVENT_FORMAT(power, TRACE_POWER, trace_power, ignore, + TRACE_STRUCT( + TRACE_FIELD(ktime_t, state_data.stamp, stamp) + TRACE_FIELD(ktime_t, state_data.end, end) + TRACE_FIELD(int, state_data.type, type) + TRACE_FIELD(int, state_data.state, state) + ), + TP_RAW_FMT("%llx->%llx type:%u state:%u") +); + +TRACE_EVENT_FORMAT(kmem_alloc, TRACE_KMEM_ALLOC, kmemtrace_alloc_entry, ignore, + TRACE_STRUCT( + TRACE_FIELD(enum kmemtrace_type_id, type_id, type_id) + TRACE_FIELD(unsigned long, call_site, call_site) + TRACE_FIELD(const void *, ptr, ptr) + TRACE_FIELD(size_t, bytes_req, bytes_req) + TRACE_FIELD(size_t, bytes_alloc, bytes_alloc) + TRACE_FIELD(gfp_t, gfp_flags, gfp_flags) + TRACE_FIELD(int, node, node) + ), + TP_RAW_FMT("type:%u call_site:%lx ptr:%p req:%lu alloc:%lu" + " flags:%x node:%d") +); + +TRACE_EVENT_FORMAT(kmem_free, TRACE_KMEM_FREE, kmemtrace_free_entry, ignore, + TRACE_STRUCT( + TRACE_FIELD(enum kmemtrace_type_id, type_id, type_id) + TRACE_FIELD(unsigned long, call_site, call_site) + TRACE_FIELD(const void *, ptr, ptr) + ), + TP_RAW_FMT("type:%u call_site:%lx ptr:%p") +); + +#undef TRACE_SYSTEM diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c new file mode 100644 index 000000000000..64ec4d278ffb --- /dev/null +++ b/kernel/trace/trace_events.c @@ -0,0 +1,824 @@ +/* + * event tracer + * + * Copyright (C) 2008 Red Hat Inc, Steven Rostedt <srostedt@redhat.com> + * + * - Added format output of fields of the trace point. + * This was based off of work by Tom Zanussi <tzanussi@gmail.com>. + * + */ + +#include <linux/debugfs.h> +#include <linux/uaccess.h> +#include <linux/module.h> +#include <linux/ctype.h> + +#include "trace_output.h" + +#define TRACE_SYSTEM "TRACE_SYSTEM" + +static DEFINE_MUTEX(event_mutex); + +int trace_define_field(struct ftrace_event_call *call, char *type, + char *name, int offset, int size) +{ + struct ftrace_event_field *field; + + field = kzalloc(sizeof(*field), GFP_KERNEL); + if (!field) + goto err; + + field->name = kstrdup(name, GFP_KERNEL); + if (!field->name) + goto err; + + field->type = kstrdup(type, GFP_KERNEL); + if (!field->type) + goto err; + + field->offset = offset; + field->size = size; + list_add(&field->link, &call->fields); + + return 0; + +err: + if (field) { + kfree(field->name); + kfree(field->type); + } + kfree(field); + + return -ENOMEM; +} + +static void ftrace_clear_events(void) +{ + struct ftrace_event_call *call = (void *)__start_ftrace_events; + + + while ((unsigned long)call < (unsigned long)__stop_ftrace_events) { + + if (call->enabled) { + call->enabled = 0; + call->unregfunc(); + } + call++; + } +} + +static void ftrace_event_enable_disable(struct ftrace_event_call *call, + int enable) +{ + + switch (enable) { + case 0: + if (call->enabled) { + call->enabled = 0; + call->unregfunc(); + } + break; + case 1: + if (!call->enabled) { + call->enabled = 1; + call->regfunc(); + } + break; + } +} + +static int ftrace_set_clr_event(char *buf, int set) +{ + struct ftrace_event_call *call = __start_ftrace_events; + char *event = NULL, *sub = NULL, *match; + int ret = -EINVAL; + + /* + * The buf format can be <subsystem>:<event-name> + * *:<event-name> means any event by that name. + * :<event-name> is the same. + * + * <subsystem>:* means all events in that subsystem + * <subsystem>: means the same. + * + * <name> (no ':') means all events in a subsystem with + * the name <name> or any event that matches <name> + */ + + match = strsep(&buf, ":"); + if (buf) { + sub = match; + event = buf; + match = NULL; + + if (!strlen(sub) || strcmp(sub, "*") == 0) + sub = NULL; + if (!strlen(event) || strcmp(event, "*") == 0) + event = NULL; + } + + mutex_lock(&event_mutex); + for_each_event(call) { + + if (!call->name || !call->regfunc) + continue; + + if (match && + strcmp(match, call->name) != 0 && + strcmp(match, call->system) != 0) + continue; + + if (sub && strcmp(sub, call->system) != 0) + continue; + + if (event && strcmp(event, call->name) != 0) + continue; + + ftrace_event_enable_disable(call, set); + + ret = 0; + } + mutex_unlock(&event_mutex); + + return ret; +} + +/* 128 should be much more than enough */ +#define EVENT_BUF_SIZE 127 + +static ssize_t +ftrace_event_write(struct file *file, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + size_t read = 0; + int i, set = 1; + ssize_t ret; + char *buf; + char ch; + + if (!cnt || cnt < 0) + return 0; + + ret = tracing_update_buffers(); + if (ret < 0) + return ret; + + ret = get_user(ch, ubuf++); + if (ret) + return ret; + read++; + cnt--; + + /* skip white space */ + while (cnt && isspace(ch)) { + ret = get_user(ch, ubuf++); + if (ret) + return ret; + read++; + cnt--; + } + + /* Only white space found? */ + if (isspace(ch)) { + file->f_pos += read; + ret = read; + return ret; + } + + buf = kmalloc(EVENT_BUF_SIZE+1, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + if (cnt > EVENT_BUF_SIZE) + cnt = EVENT_BUF_SIZE; + + i = 0; + while (cnt && !isspace(ch)) { + if (!i && ch == '!') + set = 0; + else + buf[i++] = ch; + + ret = get_user(ch, ubuf++); + if (ret) + goto out_free; + read++; + cnt--; + } + buf[i] = 0; + + file->f_pos += read; + + ret = ftrace_set_clr_event(buf, set); + if (ret) + goto out_free; + + ret = read; + + out_free: + kfree(buf); + + return ret; +} + +static void * +t_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct ftrace_event_call *call = m->private; + struct ftrace_event_call *next = call; + + (*pos)++; + + for (;;) { + if ((unsigned long)call >= (unsigned long)__stop_ftrace_events) + return NULL; + + /* + * The ftrace subsystem is for showing formats only. + * They can not be enabled or disabled via the event files. + */ + if (call->regfunc) + break; + + call++; + next = call; + } + + m->private = ++next; + + return call; +} + +static void *t_start(struct seq_file *m, loff_t *pos) +{ + return t_next(m, NULL, pos); +} + +static void * +s_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct ftrace_event_call *call = m->private; + struct ftrace_event_call *next; + + (*pos)++; + + retry: + if ((unsigned long)call >= (unsigned long)__stop_ftrace_events) + return NULL; + + if (!call->enabled) { + call++; + goto retry; + } + + next = call; + m->private = ++next; + + return call; +} + +static void *s_start(struct seq_file *m, loff_t *pos) +{ + return s_next(m, NULL, pos); +} + +static int t_show(struct seq_file *m, void *v) +{ + struct ftrace_event_call *call = v; + + if (strcmp(call->system, TRACE_SYSTEM) != 0) + seq_printf(m, "%s:", call->system); + seq_printf(m, "%s\n", call->name); + + return 0; +} + +static void t_stop(struct seq_file *m, void *p) +{ +} + +static int +ftrace_event_seq_open(struct inode *inode, struct file *file) +{ + int ret; + const struct seq_operations *seq_ops; + + if ((file->f_mode & FMODE_WRITE) && + !(file->f_flags & O_APPEND)) + ftrace_clear_events(); + + seq_ops = inode->i_private; + ret = seq_open(file, seq_ops); + if (!ret) { + struct seq_file *m = file->private_data; + + m->private = __start_ftrace_events; + } + return ret; +} + +static ssize_t +event_enable_read(struct file *filp, char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + struct ftrace_event_call *call = filp->private_data; + char *buf; + + if (call->enabled) + buf = "1\n"; + else + buf = "0\n"; + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, 2); +} + +static ssize_t +event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + struct ftrace_event_call *call = filp->private_data; + char buf[64]; + unsigned long val; + int ret; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + ret = strict_strtoul(buf, 10, &val); + if (ret < 0) + return ret; + + ret = tracing_update_buffers(); + if (ret < 0) + return ret; + + switch (val) { + case 0: + case 1: + mutex_lock(&event_mutex); + ftrace_event_enable_disable(call, val); + mutex_unlock(&event_mutex); + break; + + default: + return -EINVAL; + } + + *ppos += cnt; + + return cnt; +} + +#undef FIELD +#define FIELD(type, name) \ + #type, "common_" #name, offsetof(typeof(field), name), \ + sizeof(field.name) + +static int trace_write_header(struct trace_seq *s) +{ + struct trace_entry field; + + /* struct trace_entry */ + return trace_seq_printf(s, + "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n" + "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n" + "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n" + "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n" + "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n" + "\n", + FIELD(unsigned char, type), + FIELD(unsigned char, flags), + FIELD(unsigned char, preempt_count), + FIELD(int, pid), + FIELD(int, tgid)); +} + +static ssize_t +event_format_read(struct file *filp, char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + struct ftrace_event_call *call = filp->private_data; + struct trace_seq *s; + char *buf; + int r; + + if (*ppos) + return 0; + + s = kmalloc(sizeof(*s), GFP_KERNEL); + if (!s) + return -ENOMEM; + + trace_seq_init(s); + + /* If any of the first writes fail, so will the show_format. */ + + trace_seq_printf(s, "name: %s\n", call->name); + trace_seq_printf(s, "ID: %d\n", call->id); + trace_seq_printf(s, "format:\n"); + trace_write_header(s); + + r = call->show_format(s); + if (!r) { + /* + * ug! The format output is bigger than a PAGE!! + */ + buf = "FORMAT TOO BIG\n"; + r = simple_read_from_buffer(ubuf, cnt, ppos, + buf, strlen(buf)); + goto out; + } + + r = simple_read_from_buffer(ubuf, cnt, ppos, + s->buffer, s->len); + out: + kfree(s); + return r; +} + +static ssize_t +event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) +{ + struct ftrace_event_call *call = filp->private_data; + struct trace_seq *s; + int r; + + if (*ppos) + return 0; + + s = kmalloc(sizeof(*s), GFP_KERNEL); + if (!s) + return -ENOMEM; + + trace_seq_init(s); + trace_seq_printf(s, "%d\n", call->id); + + r = simple_read_from_buffer(ubuf, cnt, ppos, + s->buffer, s->len); + kfree(s); + return r; +} + +static ssize_t +event_filter_read(struct file *filp, char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + struct ftrace_event_call *call = filp->private_data; + struct trace_seq *s; + int r; + + if (*ppos) + return 0; + + s = kmalloc(sizeof(*s), GFP_KERNEL); + if (!s) + return -ENOMEM; + + trace_seq_init(s); + + filter_print_preds(call->preds, s); + r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len); + + kfree(s); + + return r; +} + +static ssize_t +event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + struct ftrace_event_call *call = filp->private_data; + char buf[64], *pbuf = buf; + struct filter_pred *pred; + int err; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + pred = kzalloc(sizeof(*pred), GFP_KERNEL); + if (!pred) + return -ENOMEM; + + err = filter_parse(&pbuf, pred); + if (err < 0) { + filter_free_pred(pred); + return err; + } + + if (pred->clear) { + filter_free_preds(call); + filter_free_pred(pred); + return cnt; + } + + if (filter_add_pred(call, pred)) { + filter_free_pred(pred); + return -EINVAL; + } + + *ppos += cnt; + + return cnt; +} + +static ssize_t +subsystem_filter_read(struct file *filp, char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + struct event_subsystem *system = filp->private_data; + struct trace_seq *s; + int r; + + if (*ppos) + return 0; + + s = kmalloc(sizeof(*s), GFP_KERNEL); + if (!s) + return -ENOMEM; + + trace_seq_init(s); + + filter_print_preds(system->preds, s); + r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len); + + kfree(s); + + return r; +} + +static ssize_t +subsystem_filter_write(struct file *filp, const char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + struct event_subsystem *system = filp->private_data; + char buf[64], *pbuf = buf; + struct filter_pred *pred; + int err; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + pred = kzalloc(sizeof(*pred), GFP_KERNEL); + if (!pred) + return -ENOMEM; + + err = filter_parse(&pbuf, pred); + if (err < 0) { + filter_free_pred(pred); + return err; + } + + if (pred->clear) { + filter_free_subsystem_preds(system); + filter_free_pred(pred); + return cnt; + } + + if (filter_add_subsystem_pred(system, pred)) { + filter_free_subsystem_preds(system); + filter_free_pred(pred); + return -EINVAL; + } + + *ppos += cnt; + + return cnt; +} + +static const struct seq_operations show_event_seq_ops = { + .start = t_start, + .next = t_next, + .show = t_show, + .stop = t_stop, +}; + +static const struct seq_operations show_set_event_seq_ops = { + .start = s_start, + .next = s_next, + .show = t_show, + .stop = t_stop, +}; + +static const struct file_operations ftrace_avail_fops = { + .open = ftrace_event_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static const struct file_operations ftrace_set_event_fops = { + .open = ftrace_event_seq_open, + .read = seq_read, + .write = ftrace_event_write, + .llseek = seq_lseek, + .release = seq_release, +}; + +static const struct file_operations ftrace_enable_fops = { + .open = tracing_open_generic, + .read = event_enable_read, + .write = event_enable_write, +}; + +static const struct file_operations ftrace_event_format_fops = { + .open = tracing_open_generic, + .read = event_format_read, +}; + +static const struct file_operations ftrace_event_id_fops = { + .open = tracing_open_generic, + .read = event_id_read, +}; + +static const struct file_operations ftrace_event_filter_fops = { + .open = tracing_open_generic, + .read = event_filter_read, + .write = event_filter_write, +}; + +static const struct file_operations ftrace_subsystem_filter_fops = { + .open = tracing_open_generic, + .read = subsystem_filter_read, + .write = subsystem_filter_write, +}; + +static struct dentry *event_trace_events_dir(void) +{ + static struct dentry *d_tracer; + static struct dentry *d_events; + + if (d_events) + return d_events; + + d_tracer = tracing_init_dentry(); + if (!d_tracer) + return NULL; + + d_events = debugfs_create_dir("events", d_tracer); + if (!d_events) + pr_warning("Could not create debugfs " + "'events' directory\n"); + + return d_events; +} + +static LIST_HEAD(event_subsystems); + +static struct dentry * +event_subsystem_dir(const char *name, struct dentry *d_events) +{ + struct event_subsystem *system; + + /* First see if we did not already create this dir */ + list_for_each_entry(system, &event_subsystems, list) { + if (strcmp(system->name, name) == 0) + return system->entry; + } + + /* need to create new entry */ + system = kmalloc(sizeof(*system), GFP_KERNEL); + if (!system) { + pr_warning("No memory to create event subsystem %s\n", + name); + return d_events; + } + + system->entry = debugfs_create_dir(name, d_events); + if (!system->entry) { + pr_warning("Could not create event subsystem %s\n", + name); + kfree(system); + return d_events; + } + + system->name = name; + list_add(&system->list, &event_subsystems); + + system->preds = NULL; + + return system->entry; +} + +static int +event_create_dir(struct ftrace_event_call *call, struct dentry *d_events) +{ + struct dentry *entry; + int ret; + + /* + * If the trace point header did not define TRACE_SYSTEM + * then the system would be called "TRACE_SYSTEM". + */ + if (strcmp(call->system, "TRACE_SYSTEM") != 0) + d_events = event_subsystem_dir(call->system, d_events); + + if (call->raw_init) { + ret = call->raw_init(); + if (ret < 0) { + pr_warning("Could not initialize trace point" + " events/%s\n", call->name); + return ret; + } + } + + call->dir = debugfs_create_dir(call->name, d_events); + if (!call->dir) { + pr_warning("Could not create debugfs " + "'%s' directory\n", call->name); + return -1; + } + + if (call->regfunc) { + entry = debugfs_create_file("enable", 0644, call->dir, call, + &ftrace_enable_fops); + if (!entry) + pr_warning("Could not create debugfs " + "'%s/enable' entry\n", call->name); + } + + if (call->id) { + entry = debugfs_create_file("id", 0444, call->dir, call, + &ftrace_event_id_fops); + if (!entry) + pr_warning("Could not create debugfs '%s/id' entry\n", + call->name); + } + + if (call->define_fields) { + ret = call->define_fields(); + if (ret < 0) { + pr_warning("Could not initialize trace point" + " events/%s\n", call->name); + return ret; + } + entry = debugfs_create_file("filter", 0644, call->dir, call, + &ftrace_event_filter_fops); + if (!entry) + pr_warning("Could not create debugfs " + "'%s/filter' entry\n", call->name); + } + + /* A trace may not want to export its format */ + if (!call->show_format) + return 0; + + entry = debugfs_create_file("format", 0444, call->dir, call, + &ftrace_event_format_fops); + if (!entry) + pr_warning("Could not create debugfs " + "'%s/format' entry\n", call->name); + + return 0; +} + +static __init int event_trace_init(void) +{ + struct ftrace_event_call *call = __start_ftrace_events; + struct dentry *d_tracer; + struct dentry *entry; + struct dentry *d_events; + + d_tracer = tracing_init_dentry(); + if (!d_tracer) + return 0; + + entry = debugfs_create_file("available_events", 0444, d_tracer, + (void *)&show_event_seq_ops, + &ftrace_avail_fops); + if (!entry) + pr_warning("Could not create debugfs " + "'available_events' entry\n"); + + entry = debugfs_create_file("set_event", 0644, d_tracer, + (void *)&show_set_event_seq_ops, + &ftrace_set_event_fops); + if (!entry) + pr_warning("Could not create debugfs " + "'set_event' entry\n"); + + d_events = event_trace_events_dir(); + if (!d_events) + return 0; + + for_each_event(call) { + /* The linker may leave blanks */ + if (!call->name) + continue; + event_create_dir(call, d_events); + } + + return 0; +} +fs_initcall(event_trace_init); diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c new file mode 100644 index 000000000000..026be412f356 --- /dev/null +++ b/kernel/trace/trace_events_filter.c @@ -0,0 +1,427 @@ +/* + * trace_events_filter - generic event filtering + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) 2009 Tom Zanussi <tzanussi@gmail.com> + */ + +#include <linux/debugfs.h> +#include <linux/uaccess.h> +#include <linux/module.h> +#include <linux/ctype.h> + +#include "trace.h" +#include "trace_output.h" + +static int filter_pred_64(struct filter_pred *pred, void *event) +{ + u64 *addr = (u64 *)(event + pred->offset); + u64 val = (u64)pred->val; + int match; + + match = (val == *addr) ^ pred->not; + + return match; +} + +static int filter_pred_32(struct filter_pred *pred, void *event) +{ + u32 *addr = (u32 *)(event + pred->offset); + u32 val = (u32)pred->val; + int match; + + match = (val == *addr) ^ pred->not; + + return match; +} + +static int filter_pred_16(struct filter_pred *pred, void *event) +{ + u16 *addr = (u16 *)(event + pred->offset); + u16 val = (u16)pred->val; + int match; + + match = (val == *addr) ^ pred->not; + + return match; +} + +static int filter_pred_8(struct filter_pred *pred, void *event) +{ + u8 *addr = (u8 *)(event + pred->offset); + u8 val = (u8)pred->val; + int match; + + match = (val == *addr) ^ pred->not; + + return match; +} + +static int filter_pred_string(struct filter_pred *pred, void *event) +{ + char *addr = (char *)(event + pred->offset); + int cmp, match; + + cmp = strncmp(addr, pred->str_val, pred->str_len); + + match = (!cmp) ^ pred->not; + + return match; +} + +/* return 1 if event matches, 0 otherwise (discard) */ +int filter_match_preds(struct ftrace_event_call *call, void *rec) +{ + int i, matched, and_failed = 0; + struct filter_pred *pred; + + for (i = 0; i < MAX_FILTER_PRED; i++) { + if (call->preds[i]) { + pred = call->preds[i]; + if (and_failed && !pred->or) + continue; + matched = pred->fn(pred, rec); + if (!matched && !pred->or) { + and_failed = 1; + continue; + } else if (matched && pred->or) + return 1; + } else + break; + } + + if (and_failed) + return 0; + + return 1; +} + +void filter_print_preds(struct filter_pred **preds, struct trace_seq *s) +{ + char *field_name; + struct filter_pred *pred; + int i; + + if (!preds) { + trace_seq_printf(s, "none\n"); + return; + } + + for (i = 0; i < MAX_FILTER_PRED; i++) { + if (preds[i]) { + pred = preds[i]; + field_name = pred->field_name; + if (i) + trace_seq_printf(s, pred->or ? "|| " : "&& "); + trace_seq_printf(s, "%s ", field_name); + trace_seq_printf(s, pred->not ? "!= " : "== "); + if (pred->str_val) + trace_seq_printf(s, "%s\n", pred->str_val); + else + trace_seq_printf(s, "%llu\n", pred->val); + } else + break; + } +} + +static struct ftrace_event_field * +find_event_field(struct ftrace_event_call *call, char *name) +{ + struct ftrace_event_field *field; + + list_for_each_entry(field, &call->fields, link) { + if (!strcmp(field->name, name)) + return field; + } + + return NULL; +} + +void filter_free_pred(struct filter_pred *pred) +{ + if (!pred) + return; + + kfree(pred->field_name); + kfree(pred->str_val); + kfree(pred); +} + +void filter_free_preds(struct ftrace_event_call *call) +{ + int i; + + if (call->preds) { + for (i = 0; i < MAX_FILTER_PRED; i++) + filter_free_pred(call->preds[i]); + kfree(call->preds); + call->preds = NULL; + } +} + +void filter_free_subsystem_preds(struct event_subsystem *system) +{ + struct ftrace_event_call *call = __start_ftrace_events; + int i; + + if (system->preds) { + for (i = 0; i < MAX_FILTER_PRED; i++) + filter_free_pred(system->preds[i]); + kfree(system->preds); + system->preds = NULL; + } + + events_for_each(call) { + if (!call->name || !call->regfunc) + continue; + + if (!strcmp(call->system, system->name)) + filter_free_preds(call); + } +} + +static int __filter_add_pred(struct ftrace_event_call *call, + struct filter_pred *pred) +{ + int i; + + if (call->preds && !pred->compound) + filter_free_preds(call); + + if (!call->preds) { + call->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred), + GFP_KERNEL); + if (!call->preds) + return -ENOMEM; + } + + for (i = 0; i < MAX_FILTER_PRED; i++) { + if (!call->preds[i]) { + call->preds[i] = pred; + return 0; + } + } + + return -ENOMEM; +} + +static int is_string_field(const char *type) +{ + if (strchr(type, '[') && strstr(type, "char")) + return 1; + + return 0; +} + +int filter_add_pred(struct ftrace_event_call *call, struct filter_pred *pred) +{ + struct ftrace_event_field *field; + + field = find_event_field(call, pred->field_name); + if (!field) + return -EINVAL; + + pred->offset = field->offset; + + if (is_string_field(field->type)) { + if (!pred->str_val) + return -EINVAL; + pred->fn = filter_pred_string; + pred->str_len = field->size; + return __filter_add_pred(call, pred); + } else { + if (pred->str_val) + return -EINVAL; + } + + switch (field->size) { + case 8: + pred->fn = filter_pred_64; + break; + case 4: + pred->fn = filter_pred_32; + break; + case 2: + pred->fn = filter_pred_16; + break; + case 1: + pred->fn = filter_pred_8; + break; + default: + return -EINVAL; + } + + return __filter_add_pred(call, pred); +} + +static struct filter_pred *copy_pred(struct filter_pred *pred) +{ + struct filter_pred *new_pred = kmalloc(sizeof(*pred), GFP_KERNEL); + if (!new_pred) + return NULL; + + memcpy(new_pred, pred, sizeof(*pred)); + + if (pred->field_name) { + new_pred->field_name = kstrdup(pred->field_name, GFP_KERNEL); + if (!new_pred->field_name) { + kfree(new_pred); + return NULL; + } + } + + if (pred->str_val) { + new_pred->str_val = kstrdup(pred->str_val, GFP_KERNEL); + if (!new_pred->str_val) { + filter_free_pred(new_pred); + return NULL; + } + } + + return new_pred; +} + +int filter_add_subsystem_pred(struct event_subsystem *system, + struct filter_pred *pred) +{ + struct ftrace_event_call *call = __start_ftrace_events; + struct filter_pred *event_pred; + int i; + + if (system->preds && !pred->compound) + filter_free_subsystem_preds(system); + + if (!system->preds) { + system->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred), + GFP_KERNEL); + if (!system->preds) + return -ENOMEM; + } + + for (i = 0; i < MAX_FILTER_PRED; i++) { + if (!system->preds[i]) { + system->preds[i] = pred; + break; + } + } + + if (i == MAX_FILTER_PRED) + return -EINVAL; + + events_for_each(call) { + int err; + + if (!call->name || !call->regfunc) + continue; + + if (strcmp(call->system, system->name)) + continue; + + if (!find_event_field(call, pred->field_name)) + continue; + + event_pred = copy_pred(pred); + if (!event_pred) + goto oom; + + err = filter_add_pred(call, event_pred); + if (err) + filter_free_pred(event_pred); + if (err == -ENOMEM) + goto oom; + } + + return 0; + +oom: + system->preds[i] = NULL; + return -ENOMEM; +} + +int filter_parse(char **pbuf, struct filter_pred *pred) +{ + char *tmp, *tok, *val_str = NULL; + int tok_n = 0; + + /* field ==/!= number, or/and field ==/!= number, number */ + while ((tok = strsep(pbuf, " \n"))) { + if (tok_n == 0) { + if (!strcmp(tok, "0")) { + pred->clear = 1; + return 0; + } else if (!strcmp(tok, "&&")) { + pred->or = 0; + pred->compound = 1; + } else if (!strcmp(tok, "||")) { + pred->or = 1; + pred->compound = 1; + } else + pred->field_name = tok; + tok_n = 1; + continue; + } + if (tok_n == 1) { + if (!pred->field_name) + pred->field_name = tok; + else if (!strcmp(tok, "!=")) + pred->not = 1; + else if (!strcmp(tok, "==")) + pred->not = 0; + else { + pred->field_name = NULL; + return -EINVAL; + } + tok_n = 2; + continue; + } + if (tok_n == 2) { + if (pred->compound) { + if (!strcmp(tok, "!=")) + pred->not = 1; + else if (!strcmp(tok, "==")) + pred->not = 0; + else { + pred->field_name = NULL; + return -EINVAL; + } + } else { + val_str = tok; + break; /* done */ + } + tok_n = 3; + continue; + } + if (tok_n == 3) { + val_str = tok; + break; /* done */ + } + } + + pred->field_name = kstrdup(pred->field_name, GFP_KERNEL); + if (!pred->field_name) + return -ENOMEM; + + pred->val = simple_strtoull(val_str, &tmp, 10); + if (tmp == val_str) { + pred->str_val = kstrdup(val_str, GFP_KERNEL); + if (!pred->str_val) + return -ENOMEM; + } + + return 0; +} + + diff --git a/kernel/trace/trace_events_stage_1.h b/kernel/trace/trace_events_stage_1.h new file mode 100644 index 000000000000..38985f9b379c --- /dev/null +++ b/kernel/trace/trace_events_stage_1.h @@ -0,0 +1,39 @@ +/* + * Stage 1 of the trace events. + * + * Override the macros in <trace/trace_event_types.h> to include the following: + * + * struct ftrace_raw_<call> { + * struct trace_entry ent; + * <type> <item>; + * <type2> <item2>[<len>]; + * [...] + * }; + * + * The <type> <item> is created by the __field(type, item) macro or + * the __array(type2, item2, len) macro. + * We simply do "type item;", and that will create the fields + * in the structure. + */ + +#undef TRACE_FORMAT +#define TRACE_FORMAT(call, proto, args, fmt) + +#undef __array +#define __array(type, item, len) type item[len]; + +#undef __field +#define __field(type, item) type item; + +#undef TP_STRUCT__entry +#define TP_STRUCT__entry(args...) args + +#undef TRACE_EVENT +#define TRACE_EVENT(name, proto, args, tstruct, assign, print) \ + struct ftrace_raw_##name { \ + struct trace_entry ent; \ + tstruct \ + }; \ + static struct ftrace_event_call event_##name + +#include <trace/trace_event_types.h> diff --git a/kernel/trace/trace_events_stage_2.h b/kernel/trace/trace_events_stage_2.h new file mode 100644 index 000000000000..30743f7d4110 --- /dev/null +++ b/kernel/trace/trace_events_stage_2.h @@ -0,0 +1,176 @@ +/* + * Stage 2 of the trace events. + * + * Override the macros in <trace/trace_event_types.h> to include the following: + * + * enum print_line_t + * ftrace_raw_output_<call>(struct trace_iterator *iter, int flags) + * { + * struct trace_seq *s = &iter->seq; + * struct ftrace_raw_<call> *field; <-- defined in stage 1 + * struct trace_entry *entry; + * int ret; + * + * entry = iter->ent; + * + * if (entry->type != event_<call>.id) { + * WARN_ON_ONCE(1); + * return TRACE_TYPE_UNHANDLED; + * } + * + * field = (typeof(field))entry; + * + * ret = trace_seq_printf(s, <TP_printk> "\n"); + * if (!ret) + * return TRACE_TYPE_PARTIAL_LINE; + * + * return TRACE_TYPE_HANDLED; + * } + * + * This is the method used to print the raw event to the trace + * output format. Note, this is not needed if the data is read + * in binary. + */ + +#undef __entry +#define __entry field + +#undef TP_printk +#define TP_printk(fmt, args...) fmt "\n", args + +#undef TRACE_EVENT +#define TRACE_EVENT(call, proto, args, tstruct, assign, print) \ +enum print_line_t \ +ftrace_raw_output_##call(struct trace_iterator *iter, int flags) \ +{ \ + struct trace_seq *s = &iter->seq; \ + struct ftrace_raw_##call *field; \ + struct trace_entry *entry; \ + int ret; \ + \ + entry = iter->ent; \ + \ + if (entry->type != event_##call.id) { \ + WARN_ON_ONCE(1); \ + return TRACE_TYPE_UNHANDLED; \ + } \ + \ + field = (typeof(field))entry; \ + \ + ret = trace_seq_printf(s, #call ": " print); \ + if (!ret) \ + return TRACE_TYPE_PARTIAL_LINE; \ + \ + return TRACE_TYPE_HANDLED; \ +} + +#include <trace/trace_event_types.h> + +/* + * Setup the showing format of trace point. + * + * int + * ftrace_format_##call(struct trace_seq *s) + * { + * struct ftrace_raw_##call field; + * int ret; + * + * ret = trace_seq_printf(s, #type " " #item ";" + * " offset:%u; size:%u;\n", + * offsetof(struct ftrace_raw_##call, item), + * sizeof(field.type)); + * + * } + */ + +#undef TP_STRUCT__entry +#define TP_STRUCT__entry(args...) args + +#undef __field +#define __field(type, item) \ + ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t" \ + "offset:%u;\tsize:%u;\n", \ + (unsigned int)offsetof(typeof(field), item), \ + (unsigned int)sizeof(field.item)); \ + if (!ret) \ + return 0; + +#undef __array +#define __array(type, item, len) \ + ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t" \ + "offset:%u;\tsize:%u;\n", \ + (unsigned int)offsetof(typeof(field), item), \ + (unsigned int)sizeof(field.item)); \ + if (!ret) \ + return 0; + +#undef __entry +#define __entry "REC" + +#undef TP_printk +#define TP_printk(fmt, args...) "%s, %s\n", #fmt, #args + +#undef TP_fast_assign +#define TP_fast_assign(args...) args + +#undef TRACE_EVENT +#define TRACE_EVENT(call, proto, args, tstruct, func, print) \ +static int \ +ftrace_format_##call(struct trace_seq *s) \ +{ \ + struct ftrace_raw_##call field; \ + int ret; \ + \ + tstruct; \ + \ + trace_seq_printf(s, "\nprint fmt: " print); \ + \ + return ret; \ +} + +#include <trace/trace_event_types.h> + +#undef __field +#define __field(type, item) \ + ret = trace_define_field(event_call, #type, #item, \ + offsetof(typeof(field), item), \ + sizeof(field.item)); \ + if (ret) \ + return ret; + +#undef __array +#define __array(type, item, len) \ + ret = trace_define_field(event_call, #type "[" #len "]", #item, \ + offsetof(typeof(field), item), \ + sizeof(field.item)); \ + if (ret) \ + return ret; + +#define __common_field(type, item) \ + ret = trace_define_field(event_call, #type, "common_" #item, \ + offsetof(typeof(field.ent), item), \ + sizeof(field.ent.item)); \ + if (ret) \ + return ret; + +#undef TRACE_EVENT +#define TRACE_EVENT(call, proto, args, tstruct, func, print) \ +int \ +ftrace_define_fields_##call(void) \ +{ \ + struct ftrace_raw_##call field; \ + struct ftrace_event_call *event_call = &event_##call; \ + int ret; \ + \ + __common_field(unsigned char, type); \ + __common_field(unsigned char, flags); \ + __common_field(unsigned char, preempt_count); \ + __common_field(int, pid); \ + __common_field(int, tgid); \ + \ + tstruct; \ + \ + return ret; \ +} + +#include <trace/trace_event_types.h> diff --git a/kernel/trace/trace_events_stage_3.h b/kernel/trace/trace_events_stage_3.h new file mode 100644 index 000000000000..9d2fa78cecca --- /dev/null +++ b/kernel/trace/trace_events_stage_3.h @@ -0,0 +1,281 @@ +/* + * Stage 3 of the trace events. + * + * Override the macros in <trace/trace_event_types.h> to include the following: + * + * static void ftrace_event_<call>(proto) + * { + * event_trace_printk(_RET_IP_, "<call>: " <fmt>); + * } + * + * static int ftrace_reg_event_<call>(void) + * { + * int ret; + * + * ret = register_trace_<call>(ftrace_event_<call>); + * if (!ret) + * pr_info("event trace: Could not activate trace point " + * "probe to <call>"); + * return ret; + * } + * + * static void ftrace_unreg_event_<call>(void) + * { + * unregister_trace_<call>(ftrace_event_<call>); + * } + * + * For those macros defined with TRACE_FORMAT: + * + * static struct ftrace_event_call __used + * __attribute__((__aligned__(4))) + * __attribute__((section("_ftrace_events"))) event_<call> = { + * .name = "<call>", + * .regfunc = ftrace_reg_event_<call>, + * .unregfunc = ftrace_unreg_event_<call>, + * } + * + * + * For those macros defined with TRACE_EVENT: + * + * static struct ftrace_event_call event_<call>; + * + * static void ftrace_raw_event_<call>(proto) + * { + * struct ring_buffer_event *event; + * struct ftrace_raw_<call> *entry; <-- defined in stage 1 + * unsigned long irq_flags; + * int pc; + * + * local_save_flags(irq_flags); + * pc = preempt_count(); + * + * event = trace_current_buffer_lock_reserve(event_<call>.id, + * sizeof(struct ftrace_raw_<call>), + * irq_flags, pc); + * if (!event) + * return; + * entry = ring_buffer_event_data(event); + * + * <assign>; <-- Here we assign the entries by the __field and + * __array macros. + * + * trace_current_buffer_unlock_commit(event, irq_flags, pc); + * } + * + * static int ftrace_raw_reg_event_<call>(void) + * { + * int ret; + * + * ret = register_trace_<call>(ftrace_raw_event_<call>); + * if (!ret) + * pr_info("event trace: Could not activate trace point " + * "probe to <call>"); + * return ret; + * } + * + * static void ftrace_unreg_event_<call>(void) + * { + * unregister_trace_<call>(ftrace_raw_event_<call>); + * } + * + * static struct trace_event ftrace_event_type_<call> = { + * .trace = ftrace_raw_output_<call>, <-- stage 2 + * }; + * + * static int ftrace_raw_init_event_<call>(void) + * { + * int id; + * + * id = register_ftrace_event(&ftrace_event_type_<call>); + * if (!id) + * return -ENODEV; + * event_<call>.id = id; + * return 0; + * } + * + * static struct ftrace_event_call __used + * __attribute__((__aligned__(4))) + * __attribute__((section("_ftrace_events"))) event_<call> = { + * .name = "<call>", + * .system = "<system>", + * .raw_init = ftrace_raw_init_event_<call>, + * .regfunc = ftrace_reg_event_<call>, + * .unregfunc = ftrace_unreg_event_<call>, + * .show_format = ftrace_format_<call>, + * } + * + */ + +#undef TP_FMT +#define TP_FMT(fmt, args...) fmt "\n", ##args + +#ifdef CONFIG_EVENT_PROFILE +#define _TRACE_PROFILE(call, proto, args) \ +static void ftrace_profile_##call(proto) \ +{ \ + extern void perf_tpcounter_event(int); \ + perf_tpcounter_event(event_##call.id); \ +} \ + \ +static int ftrace_profile_enable_##call(struct ftrace_event_call *call) \ +{ \ + int ret = 0; \ + \ + if (!atomic_inc_return(&call->profile_count)) \ + ret = register_trace_##call(ftrace_profile_##call); \ + \ + return ret; \ +} \ + \ +static void ftrace_profile_disable_##call(struct ftrace_event_call *call) \ +{ \ + if (atomic_add_negative(-1, &call->profile_count)) \ + unregister_trace_##call(ftrace_profile_##call); \ +} + +#define _TRACE_PROFILE_INIT(call) \ + .profile_count = ATOMIC_INIT(-1), \ + .profile_enable = ftrace_profile_enable_##call, \ + .profile_disable = ftrace_profile_disable_##call, + +#else +#define _TRACE_PROFILE(call, proto, args) +#define _TRACE_PROFILE_INIT(call) +#endif + +#define _TRACE_FORMAT(call, proto, args, fmt) \ +static void ftrace_event_##call(proto) \ +{ \ + event_trace_printk(_RET_IP_, #call ": " fmt); \ +} \ + \ +static int ftrace_reg_event_##call(void) \ +{ \ + int ret; \ + \ + ret = register_trace_##call(ftrace_event_##call); \ + if (ret) \ + pr_info("event trace: Could not activate trace point " \ + "probe to " #call "\n"); \ + return ret; \ +} \ + \ +static void ftrace_unreg_event_##call(void) \ +{ \ + unregister_trace_##call(ftrace_event_##call); \ +} \ + \ +static struct ftrace_event_call event_##call; \ + \ +static int ftrace_init_event_##call(void) \ +{ \ + int id; \ + \ + id = register_ftrace_event(NULL); \ + if (!id) \ + return -ENODEV; \ + event_##call.id = id; \ + return 0; \ +} + +#undef TRACE_FORMAT +#define TRACE_FORMAT(call, proto, args, fmt) \ +_TRACE_FORMAT(call, PARAMS(proto), PARAMS(args), PARAMS(fmt)) \ +_TRACE_PROFILE(call, PARAMS(proto), PARAMS(args)) \ +static struct ftrace_event_call __used \ +__attribute__((__aligned__(4))) \ +__attribute__((section("_ftrace_events"))) event_##call = { \ + .name = #call, \ + .system = __stringify(TRACE_SYSTEM), \ + .raw_init = ftrace_init_event_##call, \ + .regfunc = ftrace_reg_event_##call, \ + .unregfunc = ftrace_unreg_event_##call, \ + _TRACE_PROFILE_INIT(call) \ +} + +#undef __entry +#define __entry entry + +#undef TRACE_EVENT +#define TRACE_EVENT(call, proto, args, tstruct, assign, print) \ +_TRACE_PROFILE(call, PARAMS(proto), PARAMS(args)) \ + \ +static struct ftrace_event_call event_##call; \ + \ +static void ftrace_raw_event_##call(proto) \ +{ \ + struct ftrace_event_call *call = &event_##call; \ + struct ring_buffer_event *event; \ + struct ftrace_raw_##call *entry; \ + unsigned long irq_flags; \ + int pc; \ + \ + local_save_flags(irq_flags); \ + pc = preempt_count(); \ + \ + event = trace_current_buffer_lock_reserve(event_##call.id, \ + sizeof(struct ftrace_raw_##call), \ + irq_flags, pc); \ + if (!event) \ + return; \ + entry = ring_buffer_event_data(event); \ + \ + assign; \ + \ + if (call->preds && !filter_match_preds(call, entry)) \ + ring_buffer_event_discard(event); \ + \ + trace_nowake_buffer_unlock_commit(event, irq_flags, pc); \ + \ +} \ + \ +static int ftrace_raw_reg_event_##call(void) \ +{ \ + int ret; \ + \ + ret = register_trace_##call(ftrace_raw_event_##call); \ + if (ret) \ + pr_info("event trace: Could not activate trace point " \ + "probe to " #call "\n"); \ + return ret; \ +} \ + \ +static void ftrace_raw_unreg_event_##call(void) \ +{ \ + unregister_trace_##call(ftrace_raw_event_##call); \ +} \ + \ +static struct trace_event ftrace_event_type_##call = { \ + .trace = ftrace_raw_output_##call, \ +}; \ + \ +static int ftrace_raw_init_event_##call(void) \ +{ \ + int id; \ + \ + id = register_ftrace_event(&ftrace_event_type_##call); \ + if (!id) \ + return -ENODEV; \ + event_##call.id = id; \ + INIT_LIST_HEAD(&event_##call.fields); \ + return 0; \ +} \ + \ +static struct ftrace_event_call __used \ +__attribute__((__aligned__(4))) \ +__attribute__((section("_ftrace_events"))) event_##call = { \ + .name = #call, \ + .system = __stringify(TRACE_SYSTEM), \ + .raw_init = ftrace_raw_init_event_##call, \ + .regfunc = ftrace_raw_reg_event_##call, \ + .unregfunc = ftrace_raw_unreg_event_##call, \ + .show_format = ftrace_format_##call, \ + .define_fields = ftrace_define_fields_##call, \ + _TRACE_PROFILE_INIT(call) \ +} + +#include <trace/trace_event_types.h> + +#undef _TRACE_PROFILE +#undef _TRACE_PROFILE_INIT + diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c new file mode 100644 index 000000000000..4d9952d3df50 --- /dev/null +++ b/kernel/trace/trace_export.c @@ -0,0 +1,102 @@ +/* + * trace_export.c - export basic ftrace utilities to user space + * + * Copyright (C) 2009 Steven Rostedt <srostedt@redhat.com> + */ +#include <linux/stringify.h> +#include <linux/kallsyms.h> +#include <linux/seq_file.h> +#include <linux/debugfs.h> +#include <linux/uaccess.h> +#include <linux/ftrace.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/fs.h> + +#include "trace_output.h" + + +#undef TRACE_STRUCT +#define TRACE_STRUCT(args...) args + +#undef TRACE_FIELD +#define TRACE_FIELD(type, item, assign) \ + ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t" \ + "offset:%u;\tsize:%u;\n", \ + (unsigned int)offsetof(typeof(field), item), \ + (unsigned int)sizeof(field.item)); \ + if (!ret) \ + return 0; + + +#undef TRACE_FIELD_SPECIAL +#define TRACE_FIELD_SPECIAL(type_item, item, cmd) \ + ret = trace_seq_printf(s, "\tfield special:" #type_item ";\t" \ + "offset:%u;\tsize:%u;\n", \ + (unsigned int)offsetof(typeof(field), item), \ + (unsigned int)sizeof(field.item)); \ + if (!ret) \ + return 0; + +#undef TRACE_FIELD_ZERO_CHAR +#define TRACE_FIELD_ZERO_CHAR(item) \ + ret = trace_seq_printf(s, "\tfield: char " #item ";\t" \ + "offset:%u;\tsize:0;\n", \ + (unsigned int)offsetof(typeof(field), item)); \ + if (!ret) \ + return 0; + + +#undef TP_RAW_FMT +#define TP_RAW_FMT(args...) args + +#undef TRACE_EVENT_FORMAT +#define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt) \ +static int \ +ftrace_format_##call(struct trace_seq *s) \ +{ \ + struct args field; \ + int ret; \ + \ + tstruct; \ + \ + trace_seq_printf(s, "\nprint fmt: \"%s\"\n", tpfmt); \ + \ + return ret; \ +} + +#include "trace_event_types.h" + +#undef TRACE_ZERO_CHAR +#define TRACE_ZERO_CHAR(arg) + +#undef TRACE_FIELD +#define TRACE_FIELD(type, item, assign)\ + entry->item = assign; + +#undef TRACE_FIELD +#define TRACE_FIELD(type, item, assign)\ + entry->item = assign; + +#undef TP_CMD +#define TP_CMD(cmd...) cmd + +#undef TRACE_ENTRY +#define TRACE_ENTRY entry + +#undef TRACE_FIELD_SPECIAL +#define TRACE_FIELD_SPECIAL(type_item, item, cmd) \ + cmd; + +#undef TRACE_EVENT_FORMAT +#define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt) \ + \ +static struct ftrace_event_call __used \ +__attribute__((__aligned__(4))) \ +__attribute__((section("_ftrace_events"))) event_##call = { \ + .name = #call, \ + .id = proto, \ + .system = __stringify(TRACE_SYSTEM), \ + .show_format = ftrace_format_##call, \ +} +#include "trace_event_types.h" diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 9236d7e25a16..c9a0b7df44ff 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -9,6 +9,7 @@ * Copyright (C) 2004-2006 Ingo Molnar * Copyright (C) 2004 William Lee Irwin III */ +#include <linux/ring_buffer.h> #include <linux/debugfs.h> #include <linux/uaccess.h> #include <linux/ftrace.h> @@ -16,52 +17,388 @@ #include "trace.h" -static void start_function_trace(struct trace_array *tr) +/* function tracing enabled */ +static int ftrace_function_enabled; + +static struct trace_array *func_trace; + +static void tracing_start_function_trace(void); +static void tracing_stop_function_trace(void); + +static int function_trace_init(struct trace_array *tr) { + func_trace = tr; tr->cpu = get_cpu(); - tracing_reset_online_cpus(tr); put_cpu(); tracing_start_cmdline_record(); tracing_start_function_trace(); + return 0; } -static void stop_function_trace(struct trace_array *tr) +static void function_trace_reset(struct trace_array *tr) { tracing_stop_function_trace(); tracing_stop_cmdline_record(); } -static int function_trace_init(struct trace_array *tr) +static void function_trace_start(struct trace_array *tr) { - start_function_trace(tr); - return 0; + tracing_reset_online_cpus(tr); } -static void function_trace_reset(struct trace_array *tr) +static void +function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip) +{ + struct trace_array *tr = func_trace; + struct trace_array_cpu *data; + unsigned long flags; + long disabled; + int cpu, resched; + int pc; + + if (unlikely(!ftrace_function_enabled)) + return; + + pc = preempt_count(); + resched = ftrace_preempt_disable(); + local_save_flags(flags); + cpu = raw_smp_processor_id(); + data = tr->data[cpu]; + disabled = atomic_inc_return(&data->disabled); + + if (likely(disabled == 1)) + trace_function(tr, ip, parent_ip, flags, pc); + + atomic_dec(&data->disabled); + ftrace_preempt_enable(resched); +} + +static void +function_trace_call(unsigned long ip, unsigned long parent_ip) { - stop_function_trace(tr); + struct trace_array *tr = func_trace; + struct trace_array_cpu *data; + unsigned long flags; + long disabled; + int cpu; + int pc; + + if (unlikely(!ftrace_function_enabled)) + return; + + /* + * Need to use raw, since this must be called before the + * recursive protection is performed. + */ + local_irq_save(flags); + cpu = raw_smp_processor_id(); + data = tr->data[cpu]; + disabled = atomic_inc_return(&data->disabled); + + if (likely(disabled == 1)) { + pc = preempt_count(); + trace_function(tr, ip, parent_ip, flags, pc); + } + + atomic_dec(&data->disabled); + local_irq_restore(flags); } -static void function_trace_start(struct trace_array *tr) +static void +function_stack_trace_call(unsigned long ip, unsigned long parent_ip) { - tracing_reset_online_cpus(tr); + struct trace_array *tr = func_trace; + struct trace_array_cpu *data; + unsigned long flags; + long disabled; + int cpu; + int pc; + + if (unlikely(!ftrace_function_enabled)) + return; + + /* + * Need to use raw, since this must be called before the + * recursive protection is performed. + */ + local_irq_save(flags); + cpu = raw_smp_processor_id(); + data = tr->data[cpu]; + disabled = atomic_inc_return(&data->disabled); + + if (likely(disabled == 1)) { + pc = preempt_count(); + trace_function(tr, ip, parent_ip, flags, pc); + /* + * skip over 5 funcs: + * __ftrace_trace_stack, + * __trace_stack, + * function_stack_trace_call + * ftrace_list_func + * ftrace_call + */ + __trace_stack(tr, flags, 5, pc); + } + + atomic_dec(&data->disabled); + local_irq_restore(flags); +} + + +static struct ftrace_ops trace_ops __read_mostly = +{ + .func = function_trace_call, +}; + +static struct ftrace_ops trace_stack_ops __read_mostly = +{ + .func = function_stack_trace_call, +}; + +/* Our two options */ +enum { + TRACE_FUNC_OPT_STACK = 0x1, +}; + +static struct tracer_opt func_opts[] = { +#ifdef CONFIG_STACKTRACE + { TRACER_OPT(func_stack_trace, TRACE_FUNC_OPT_STACK) }, +#endif + { } /* Always set a last empty entry */ +}; + +static struct tracer_flags func_flags = { + .val = 0, /* By default: all flags disabled */ + .opts = func_opts +}; + +static void tracing_start_function_trace(void) +{ + ftrace_function_enabled = 0; + + if (trace_flags & TRACE_ITER_PREEMPTONLY) + trace_ops.func = function_trace_call_preempt_only; + else + trace_ops.func = function_trace_call; + + if (func_flags.val & TRACE_FUNC_OPT_STACK) + register_ftrace_function(&trace_stack_ops); + else + register_ftrace_function(&trace_ops); + + ftrace_function_enabled = 1; +} + +static void tracing_stop_function_trace(void) +{ + ftrace_function_enabled = 0; + /* OK if they are not registered */ + unregister_ftrace_function(&trace_stack_ops); + unregister_ftrace_function(&trace_ops); +} + +static int func_set_flag(u32 old_flags, u32 bit, int set) +{ + if (bit == TRACE_FUNC_OPT_STACK) { + /* do nothing if already set */ + if (!!set == !!(func_flags.val & TRACE_FUNC_OPT_STACK)) + return 0; + + if (set) { + unregister_ftrace_function(&trace_ops); + register_ftrace_function(&trace_stack_ops); + } else { + unregister_ftrace_function(&trace_stack_ops); + register_ftrace_function(&trace_ops); + } + + return 0; + } + + return -EINVAL; } static struct tracer function_trace __read_mostly = { - .name = "function", - .init = function_trace_init, - .reset = function_trace_reset, - .start = function_trace_start, + .name = "function", + .init = function_trace_init, + .reset = function_trace_reset, + .start = function_trace_start, + .wait_pipe = poll_wait_pipe, + .flags = &func_flags, + .set_flag = func_set_flag, #ifdef CONFIG_FTRACE_SELFTEST - .selftest = trace_selftest_startup_function, + .selftest = trace_selftest_startup_function, #endif }; +#ifdef CONFIG_DYNAMIC_FTRACE +static void +ftrace_traceon(unsigned long ip, unsigned long parent_ip, void **data) +{ + long *count = (long *)data; + + if (tracing_is_on()) + return; + + if (!*count) + return; + + if (*count != -1) + (*count)--; + + tracing_on(); +} + +static void +ftrace_traceoff(unsigned long ip, unsigned long parent_ip, void **data) +{ + long *count = (long *)data; + + if (!tracing_is_on()) + return; + + if (!*count) + return; + + if (*count != -1) + (*count)--; + + tracing_off(); +} + +static int +ftrace_trace_onoff_print(struct seq_file *m, unsigned long ip, + struct ftrace_probe_ops *ops, void *data); + +static struct ftrace_probe_ops traceon_probe_ops = { + .func = ftrace_traceon, + .print = ftrace_trace_onoff_print, +}; + +static struct ftrace_probe_ops traceoff_probe_ops = { + .func = ftrace_traceoff, + .print = ftrace_trace_onoff_print, +}; + +static int +ftrace_trace_onoff_print(struct seq_file *m, unsigned long ip, + struct ftrace_probe_ops *ops, void *data) +{ + char str[KSYM_SYMBOL_LEN]; + long count = (long)data; + + kallsyms_lookup(ip, NULL, NULL, NULL, str); + seq_printf(m, "%s:", str); + + if (ops == &traceon_probe_ops) + seq_printf(m, "traceon"); + else + seq_printf(m, "traceoff"); + + if (count == -1) + seq_printf(m, ":unlimited\n"); + else + seq_printf(m, ":count=%ld", count); + seq_putc(m, '\n'); + + return 0; +} + +static int +ftrace_trace_onoff_unreg(char *glob, char *cmd, char *param) +{ + struct ftrace_probe_ops *ops; + + /* we register both traceon and traceoff to this callback */ + if (strcmp(cmd, "traceon") == 0) + ops = &traceon_probe_ops; + else + ops = &traceoff_probe_ops; + + unregister_ftrace_function_probe_func(glob, ops); + + return 0; +} + +static int +ftrace_trace_onoff_callback(char *glob, char *cmd, char *param, int enable) +{ + struct ftrace_probe_ops *ops; + void *count = (void *)-1; + char *number; + int ret; + + /* hash funcs only work with set_ftrace_filter */ + if (!enable) + return -EINVAL; + + if (glob[0] == '!') + return ftrace_trace_onoff_unreg(glob+1, cmd, param); + + /* we register both traceon and traceoff to this callback */ + if (strcmp(cmd, "traceon") == 0) + ops = &traceon_probe_ops; + else + ops = &traceoff_probe_ops; + + if (!param) + goto out_reg; + + number = strsep(¶m, ":"); + + if (!strlen(number)) + goto out_reg; + + /* + * We use the callback data field (which is a pointer) + * as our counter. + */ + ret = strict_strtoul(number, 0, (unsigned long *)&count); + if (ret) + return ret; + + out_reg: + ret = register_ftrace_function_probe(glob, ops, count); + + return ret; +} + +static struct ftrace_func_command ftrace_traceon_cmd = { + .name = "traceon", + .func = ftrace_trace_onoff_callback, +}; + +static struct ftrace_func_command ftrace_traceoff_cmd = { + .name = "traceoff", + .func = ftrace_trace_onoff_callback, +}; + +static int __init init_func_cmd_traceon(void) +{ + int ret; + + ret = register_ftrace_command(&ftrace_traceoff_cmd); + if (ret) + return ret; + + ret = register_ftrace_command(&ftrace_traceon_cmd); + if (ret) + unregister_ftrace_command(&ftrace_traceoff_cmd); + return ret; +} +#else +static inline int init_func_cmd_traceon(void) +{ + return 0; +} +#endif /* CONFIG_DYNAMIC_FTRACE */ + static __init int init_function_trace(void) { + init_func_cmd_traceon(); return register_tracer(&function_trace); } - device_initcall(init_function_trace); + diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index dce71a5b51bc..d28687e7b3a7 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -1,7 +1,7 @@ /* * * Function graph tracer. - * Copyright (c) 2008 Frederic Weisbecker <fweisbec@gmail.com> + * Copyright (c) 2008-2009 Frederic Weisbecker <fweisbec@gmail.com> * Mostly borrowed from function tracer which * is Copyright (c) Steven Rostedt <srostedt@redhat.com> * @@ -12,6 +12,12 @@ #include <linux/fs.h> #include "trace.h" +#include "trace_output.h" + +struct fgraph_data { + pid_t last_pid; + int depth; +}; #define TRACE_GRAPH_INDENT 2 @@ -20,9 +26,11 @@ #define TRACE_GRAPH_PRINT_CPU 0x2 #define TRACE_GRAPH_PRINT_OVERHEAD 0x4 #define TRACE_GRAPH_PRINT_PROC 0x8 +#define TRACE_GRAPH_PRINT_DURATION 0x10 +#define TRACE_GRAPH_PRINT_ABS_TIME 0X20 static struct tracer_opt trace_opts[] = { - /* Display overruns ? */ + /* Display overruns? (for self-debug purpose) */ { TRACER_OPT(funcgraph-overrun, TRACE_GRAPH_PRINT_OVERRUN) }, /* Display CPU ? */ { TRACER_OPT(funcgraph-cpu, TRACE_GRAPH_PRINT_CPU) }, @@ -30,23 +38,28 @@ static struct tracer_opt trace_opts[] = { { TRACER_OPT(funcgraph-overhead, TRACE_GRAPH_PRINT_OVERHEAD) }, /* Display proc name/pid */ { TRACER_OPT(funcgraph-proc, TRACE_GRAPH_PRINT_PROC) }, + /* Display duration of execution */ + { TRACER_OPT(funcgraph-duration, TRACE_GRAPH_PRINT_DURATION) }, + /* Display absolute time of an entry */ + { TRACER_OPT(funcgraph-abstime, TRACE_GRAPH_PRINT_ABS_TIME) }, { } /* Empty entry */ }; static struct tracer_flags tracer_flags = { /* Don't display overruns and proc by default */ - .val = TRACE_GRAPH_PRINT_CPU | TRACE_GRAPH_PRINT_OVERHEAD, + .val = TRACE_GRAPH_PRINT_CPU | TRACE_GRAPH_PRINT_OVERHEAD | + TRACE_GRAPH_PRINT_DURATION, .opts = trace_opts }; /* pid on the last trace processed */ -static pid_t last_pid[NR_CPUS] = { [0 ... NR_CPUS-1] = -1 }; + /* Add a function return address to the trace stack on thread info.*/ int -ftrace_push_return_trace(unsigned long ret, unsigned long long time, - unsigned long func, int *depth) +ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth) { + unsigned long long calltime; int index; if (!current->ret_stack) @@ -58,11 +71,13 @@ ftrace_push_return_trace(unsigned long ret, unsigned long long time, return -EBUSY; } + calltime = trace_clock_local(); + index = ++current->curr_ret_stack; barrier(); current->ret_stack[index].ret = ret; current->ret_stack[index].func = func; - current->ret_stack[index].calltime = time; + current->ret_stack[index].calltime = calltime; *depth = index; return 0; @@ -104,7 +119,7 @@ unsigned long ftrace_return_to_handler(void) unsigned long ret; ftrace_pop_return_trace(&trace, &ret); - trace.rettime = cpu_clock(raw_smp_processor_id()); + trace.rettime = trace_clock_local(); ftrace_graph_return(&trace); if (unlikely(!ret)) { @@ -119,12 +134,7 @@ unsigned long ftrace_return_to_handler(void) static int graph_trace_init(struct trace_array *tr) { - int cpu, ret; - - for_each_online_cpu(cpu) - tracing_reset(tr, cpu); - - ret = register_ftrace_graph(&trace_graph_return, + int ret = register_ftrace_graph(&trace_graph_return, &trace_graph_entry); if (ret) return ret; @@ -187,15 +197,15 @@ print_graph_cpu(struct trace_seq *s, int cpu) static enum print_line_t print_graph_proc(struct trace_seq *s, pid_t pid) { - int i; - int ret; - int len; - char comm[8]; - int spaces = 0; + char comm[TASK_COMM_LEN]; /* sign + log10(MAX_INT) + '\0' */ char pid_str[11]; + int spaces = 0; + int ret; + int len; + int i; - strncpy(comm, trace_find_cmdline(pid), 7); + trace_find_cmdline(pid, comm); comm[7] = '\0'; sprintf(pid_str, "%d", pid); @@ -228,17 +238,25 @@ print_graph_proc(struct trace_seq *s, pid_t pid) /* If the pid changed since the last trace, output this event */ static enum print_line_t -verif_pid(struct trace_seq *s, pid_t pid, int cpu) +verif_pid(struct trace_seq *s, pid_t pid, int cpu, struct fgraph_data *data) { pid_t prev_pid; + pid_t *last_pid; int ret; - if (last_pid[cpu] != -1 && last_pid[cpu] == pid) + if (!data) + return TRACE_TYPE_HANDLED; + + last_pid = &(per_cpu_ptr(data, cpu)->last_pid); + + if (*last_pid == pid) return TRACE_TYPE_HANDLED; - prev_pid = last_pid[cpu]; - last_pid[cpu] = pid; + prev_pid = *last_pid; + *last_pid = pid; + if (prev_pid == -1) + return TRACE_TYPE_HANDLED; /* * Context-switch trace line: @@ -250,34 +268,34 @@ verif_pid(struct trace_seq *s, pid_t pid, int cpu) ret = trace_seq_printf(s, " ------------------------------------------\n"); if (!ret) - TRACE_TYPE_PARTIAL_LINE; + return TRACE_TYPE_PARTIAL_LINE; ret = print_graph_cpu(s, cpu); if (ret == TRACE_TYPE_PARTIAL_LINE) - TRACE_TYPE_PARTIAL_LINE; + return TRACE_TYPE_PARTIAL_LINE; ret = print_graph_proc(s, prev_pid); if (ret == TRACE_TYPE_PARTIAL_LINE) - TRACE_TYPE_PARTIAL_LINE; + return TRACE_TYPE_PARTIAL_LINE; ret = trace_seq_printf(s, " => "); if (!ret) - TRACE_TYPE_PARTIAL_LINE; + return TRACE_TYPE_PARTIAL_LINE; ret = print_graph_proc(s, pid); if (ret == TRACE_TYPE_PARTIAL_LINE) - TRACE_TYPE_PARTIAL_LINE; + return TRACE_TYPE_PARTIAL_LINE; ret = trace_seq_printf(s, "\n ------------------------------------------\n\n"); if (!ret) - TRACE_TYPE_PARTIAL_LINE; + return TRACE_TYPE_PARTIAL_LINE; - return ret; + return TRACE_TYPE_HANDLED; } -static bool -trace_branch_is_leaf(struct trace_iterator *iter, +static struct ftrace_graph_ret_entry * +get_return_for_leaf(struct trace_iterator *iter, struct ftrace_graph_ent_entry *curr) { struct ring_buffer_iter *ring_iter; @@ -286,65 +304,123 @@ trace_branch_is_leaf(struct trace_iterator *iter, ring_iter = iter->buffer_iter[iter->cpu]; - if (!ring_iter) - return false; - - event = ring_buffer_iter_peek(ring_iter, NULL); + /* First peek to compare current entry and the next one */ + if (ring_iter) + event = ring_buffer_iter_peek(ring_iter, NULL); + else { + /* We need to consume the current entry to see the next one */ + ring_buffer_consume(iter->tr->buffer, iter->cpu, NULL); + event = ring_buffer_peek(iter->tr->buffer, iter->cpu, + NULL); + } if (!event) - return false; + return NULL; next = ring_buffer_event_data(event); if (next->ent.type != TRACE_GRAPH_RET) - return false; + return NULL; if (curr->ent.pid != next->ent.pid || curr->graph_ent.func != next->ret.func) - return false; + return NULL; + + /* this is a leaf, now advance the iterator */ + if (ring_iter) + ring_buffer_read(ring_iter, NULL); + + return next; +} + +/* Signal a overhead of time execution to the output */ +static int +print_graph_overhead(unsigned long long duration, struct trace_seq *s) +{ + /* If duration disappear, we don't need anything */ + if (!(tracer_flags.val & TRACE_GRAPH_PRINT_DURATION)) + return 1; + + /* Non nested entry or return */ + if (duration == -1) + return trace_seq_printf(s, " "); + + if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERHEAD) { + /* Duration exceeded 100 msecs */ + if (duration > 100000ULL) + return trace_seq_printf(s, "! "); + + /* Duration exceeded 10 msecs */ + if (duration > 10000ULL) + return trace_seq_printf(s, "+ "); + } + + return trace_seq_printf(s, " "); +} + +static int print_graph_abs_time(u64 t, struct trace_seq *s) +{ + unsigned long usecs_rem; + + usecs_rem = do_div(t, NSEC_PER_SEC); + usecs_rem /= 1000; - return true; + return trace_seq_printf(s, "%5lu.%06lu | ", + (unsigned long)t, usecs_rem); } static enum print_line_t -print_graph_irq(struct trace_seq *s, unsigned long addr, - enum trace_type type, int cpu, pid_t pid) +print_graph_irq(struct trace_iterator *iter, unsigned long addr, + enum trace_type type, int cpu, pid_t pid) { int ret; + struct trace_seq *s = &iter->seq; if (addr < (unsigned long)__irqentry_text_start || addr >= (unsigned long)__irqentry_text_end) return TRACE_TYPE_UNHANDLED; - if (type == TRACE_GRAPH_ENT) { - ret = trace_seq_printf(s, "==========> | "); - } else { - /* Cpu */ - if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) { - ret = print_graph_cpu(s, cpu); - if (ret == TRACE_TYPE_PARTIAL_LINE) - return TRACE_TYPE_PARTIAL_LINE; - } - /* Proc */ - if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) { - ret = print_graph_proc(s, pid); - if (ret == TRACE_TYPE_PARTIAL_LINE) - return TRACE_TYPE_PARTIAL_LINE; + /* Absolute time */ + if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME) { + ret = print_graph_abs_time(iter->ts, s); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + } - ret = trace_seq_printf(s, " | "); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - } + /* Cpu */ + if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) { + ret = print_graph_cpu(s, cpu); + if (ret == TRACE_TYPE_PARTIAL_LINE) + return TRACE_TYPE_PARTIAL_LINE; + } + /* Proc */ + if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) { + ret = print_graph_proc(s, pid); + if (ret == TRACE_TYPE_PARTIAL_LINE) + return TRACE_TYPE_PARTIAL_LINE; + ret = trace_seq_printf(s, " | "); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + } - /* No overhead */ - if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERHEAD) { - ret = trace_seq_printf(s, " "); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - } + /* No overhead */ + ret = print_graph_overhead(-1, s); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + if (type == TRACE_GRAPH_ENT) + ret = trace_seq_printf(s, "==========>"); + else + ret = trace_seq_printf(s, "<=========="); + + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + /* Don't close the duration column if haven't one */ + if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) + trace_seq_printf(s, " |"); + ret = trace_seq_printf(s, "\n"); - ret = trace_seq_printf(s, "<========== |\n"); - } if (!ret) return TRACE_TYPE_PARTIAL_LINE; return TRACE_TYPE_HANDLED; @@ -363,7 +439,7 @@ print_graph_duration(unsigned long long duration, struct trace_seq *s) sprintf(msecs_str, "%lu", (unsigned long) duration); /* Print msecs */ - ret = trace_seq_printf(s, msecs_str); + ret = trace_seq_printf(s, "%s", msecs_str); if (!ret) return TRACE_TYPE_PARTIAL_LINE; @@ -396,52 +472,47 @@ print_graph_duration(unsigned long long duration, struct trace_seq *s) } -/* Signal a overhead of time execution to the output */ -static int -print_graph_overhead(unsigned long long duration, struct trace_seq *s) -{ - /* Duration exceeded 100 msecs */ - if (duration > 100000ULL) - return trace_seq_printf(s, "! "); - - /* Duration exceeded 10 msecs */ - if (duration > 10000ULL) - return trace_seq_printf(s, "+ "); - - return trace_seq_printf(s, " "); -} - /* Case of a leaf function on its call entry */ static enum print_line_t print_graph_entry_leaf(struct trace_iterator *iter, - struct ftrace_graph_ent_entry *entry, struct trace_seq *s) + struct ftrace_graph_ent_entry *entry, + struct ftrace_graph_ret_entry *ret_entry, struct trace_seq *s) { - struct ftrace_graph_ret_entry *ret_entry; + struct fgraph_data *data = iter->private; struct ftrace_graph_ret *graph_ret; - struct ring_buffer_event *event; struct ftrace_graph_ent *call; unsigned long long duration; int ret; int i; - event = ring_buffer_read(iter->buffer_iter[iter->cpu], NULL); - ret_entry = ring_buffer_event_data(event); graph_ret = &ret_entry->ret; call = &entry->graph_ent; duration = graph_ret->rettime - graph_ret->calltime; - /* Overhead */ - if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERHEAD) { - ret = print_graph_overhead(duration, s); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; + if (data) { + int cpu = iter->cpu; + int *depth = &(per_cpu_ptr(data, cpu)->depth); + + /* + * Comments display at + 1 to depth. Since + * this is a leaf function, keep the comments + * equal to this depth. + */ + *depth = call->depth - 1; } - /* Duration */ - ret = print_graph_duration(duration, s); - if (ret == TRACE_TYPE_PARTIAL_LINE) + /* Overhead */ + ret = print_graph_overhead(duration, s); + if (!ret) return TRACE_TYPE_PARTIAL_LINE; + /* Duration */ + if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) { + ret = print_graph_duration(duration, s); + if (ret == TRACE_TYPE_PARTIAL_LINE) + return TRACE_TYPE_PARTIAL_LINE; + } + /* Function */ for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++) { ret = trace_seq_printf(s, " "); @@ -461,33 +532,34 @@ print_graph_entry_leaf(struct trace_iterator *iter, } static enum print_line_t -print_graph_entry_nested(struct ftrace_graph_ent_entry *entry, - struct trace_seq *s, pid_t pid, int cpu) +print_graph_entry_nested(struct trace_iterator *iter, + struct ftrace_graph_ent_entry *entry, + struct trace_seq *s, int cpu) { - int i; - int ret; struct ftrace_graph_ent *call = &entry->graph_ent; + struct fgraph_data *data = iter->private; + int ret; + int i; - /* No overhead */ - if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERHEAD) { - ret = trace_seq_printf(s, " "); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; + if (data) { + int cpu = iter->cpu; + int *depth = &(per_cpu_ptr(data, cpu)->depth); + + *depth = call->depth; } - /* Interrupt */ - ret = print_graph_irq(s, call->func, TRACE_GRAPH_ENT, cpu, pid); - if (ret == TRACE_TYPE_UNHANDLED) { - /* No time */ + /* No overhead */ + ret = print_graph_overhead(-1, s); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + /* No time */ + if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) { ret = trace_seq_printf(s, " | "); if (!ret) return TRACE_TYPE_PARTIAL_LINE; - } else { - if (ret == TRACE_TYPE_PARTIAL_LINE) - return TRACE_TYPE_PARTIAL_LINE; } - /* Function */ for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++) { ret = trace_seq_printf(s, " "); @@ -503,20 +575,40 @@ print_graph_entry_nested(struct ftrace_graph_ent_entry *entry, if (!ret) return TRACE_TYPE_PARTIAL_LINE; - return TRACE_TYPE_HANDLED; + /* + * we already consumed the current entry to check the next one + * and see if this is a leaf. + */ + return TRACE_TYPE_NO_CONSUME; } static enum print_line_t -print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s, - struct trace_iterator *iter, int cpu) +print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s, + int type, unsigned long addr) { - int ret; + struct fgraph_data *data = iter->private; struct trace_entry *ent = iter->ent; + int cpu = iter->cpu; + int ret; /* Pid */ - if (verif_pid(s, ent->pid, cpu) == TRACE_TYPE_PARTIAL_LINE) + if (verif_pid(s, ent->pid, cpu, data) == TRACE_TYPE_PARTIAL_LINE) return TRACE_TYPE_PARTIAL_LINE; + if (type) { + /* Interrupt */ + ret = print_graph_irq(iter, addr, type, cpu, ent->pid); + if (ret == TRACE_TYPE_PARTIAL_LINE) + return TRACE_TYPE_PARTIAL_LINE; + } + + /* Absolute time */ + if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME) { + ret = print_graph_abs_time(iter->ts, s); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + } + /* Cpu */ if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) { ret = print_graph_cpu(s, cpu); @@ -535,54 +627,65 @@ print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s, return TRACE_TYPE_PARTIAL_LINE; } - if (trace_branch_is_leaf(iter, field)) - return print_graph_entry_leaf(iter, field, s); + return 0; +} + +static enum print_line_t +print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s, + struct trace_iterator *iter) +{ + int cpu = iter->cpu; + struct ftrace_graph_ent *call = &field->graph_ent; + struct ftrace_graph_ret_entry *leaf_ret; + + if (print_graph_prologue(iter, s, TRACE_GRAPH_ENT, call->func)) + return TRACE_TYPE_PARTIAL_LINE; + + leaf_ret = get_return_for_leaf(iter, field); + if (leaf_ret) + return print_graph_entry_leaf(iter, field, leaf_ret, s); else - return print_graph_entry_nested(field, s, iter->ent->pid, cpu); + return print_graph_entry_nested(iter, field, s, cpu); } static enum print_line_t print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s, - struct trace_entry *ent, int cpu) + struct trace_entry *ent, struct trace_iterator *iter) { - int i; - int ret; unsigned long long duration = trace->rettime - trace->calltime; + struct fgraph_data *data = iter->private; + pid_t pid = ent->pid; + int cpu = iter->cpu; + int ret; + int i; - /* Pid */ - if (verif_pid(s, ent->pid, cpu) == TRACE_TYPE_PARTIAL_LINE) - return TRACE_TYPE_PARTIAL_LINE; + if (data) { + int cpu = iter->cpu; + int *depth = &(per_cpu_ptr(data, cpu)->depth); - /* Cpu */ - if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) { - ret = print_graph_cpu(s, cpu); - if (ret == TRACE_TYPE_PARTIAL_LINE) - return TRACE_TYPE_PARTIAL_LINE; + /* + * Comments display at + 1 to depth. This is the + * return from a function, we now want the comments + * to display at the same level of the bracket. + */ + *depth = trace->depth - 1; } - /* Proc */ - if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) { - ret = print_graph_proc(s, ent->pid); - if (ret == TRACE_TYPE_PARTIAL_LINE) - return TRACE_TYPE_PARTIAL_LINE; - - ret = trace_seq_printf(s, " | "); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - } + if (print_graph_prologue(iter, s, 0, 0)) + return TRACE_TYPE_PARTIAL_LINE; /* Overhead */ - if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERHEAD) { - ret = print_graph_overhead(duration, s); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - } + ret = print_graph_overhead(duration, s); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; /* Duration */ - ret = print_graph_duration(duration, s); - if (ret == TRACE_TYPE_PARTIAL_LINE) - return TRACE_TYPE_PARTIAL_LINE; + if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) { + ret = print_graph_duration(duration, s); + if (ret == TRACE_TYPE_PARTIAL_LINE) + return TRACE_TYPE_PARTIAL_LINE; + } /* Closing brace */ for (i = 0; i < trace->depth * TRACE_GRAPH_INDENT; i++) { @@ -603,7 +706,7 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s, return TRACE_TYPE_PARTIAL_LINE; } - ret = print_graph_irq(s, trace->func, TRACE_GRAPH_RET, cpu, ent->pid); + ret = print_graph_irq(iter, trace->func, TRACE_GRAPH_RET, cpu, pid); if (ret == TRACE_TYPE_PARTIAL_LINE) return TRACE_TYPE_PARTIAL_LINE; @@ -611,61 +714,73 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s, } static enum print_line_t -print_graph_comment(struct print_entry *trace, struct trace_seq *s, - struct trace_entry *ent, struct trace_iterator *iter) +print_graph_comment(struct trace_seq *s, struct trace_entry *ent, + struct trace_iterator *iter) { - int i; + unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK); + struct fgraph_data *data = iter->private; + struct trace_event *event; + int depth = 0; int ret; + int i; - /* Pid */ - if (verif_pid(s, ent->pid, iter->cpu) == TRACE_TYPE_PARTIAL_LINE) - return TRACE_TYPE_PARTIAL_LINE; - - /* Cpu */ - if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) { - ret = print_graph_cpu(s, iter->cpu); - if (ret == TRACE_TYPE_PARTIAL_LINE) - return TRACE_TYPE_PARTIAL_LINE; - } - - /* Proc */ - if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) { - ret = print_graph_proc(s, ent->pid); - if (ret == TRACE_TYPE_PARTIAL_LINE) - return TRACE_TYPE_PARTIAL_LINE; + if (data) + depth = per_cpu_ptr(data, iter->cpu)->depth; - ret = trace_seq_printf(s, " | "); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - } + if (print_graph_prologue(iter, s, 0, 0)) + return TRACE_TYPE_PARTIAL_LINE; /* No overhead */ - if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERHEAD) { - ret = trace_seq_printf(s, " "); + ret = print_graph_overhead(-1, s); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + /* No time */ + if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) { + ret = trace_seq_printf(s, " | "); if (!ret) return TRACE_TYPE_PARTIAL_LINE; } - /* No time */ - ret = trace_seq_printf(s, " | "); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - /* Indentation */ - if (trace->depth > 0) - for (i = 0; i < (trace->depth + 1) * TRACE_GRAPH_INDENT; i++) { + if (depth > 0) + for (i = 0; i < (depth + 1) * TRACE_GRAPH_INDENT; i++) { ret = trace_seq_printf(s, " "); if (!ret) return TRACE_TYPE_PARTIAL_LINE; } /* The comment */ - ret = trace_seq_printf(s, "/* %s", trace->buf); + ret = trace_seq_printf(s, "/* "); if (!ret) return TRACE_TYPE_PARTIAL_LINE; - if (ent->flags & TRACE_FLAG_CONT) - trace_seq_print_cont(s, iter); + switch (iter->ent->type) { + case TRACE_BPRINT: + ret = trace_print_bprintk_msg_only(iter); + if (ret != TRACE_TYPE_HANDLED) + return ret; + break; + case TRACE_PRINT: + ret = trace_print_printk_msg_only(iter); + if (ret != TRACE_TYPE_HANDLED) + return ret; + break; + default: + event = ftrace_find_event(ent->type); + if (!event) + return TRACE_TYPE_UNHANDLED; + + ret = event->trace(iter, sym_flags); + if (ret != TRACE_TYPE_HANDLED) + return ret; + } + + /* Strip ending newline */ + if (s->buffer[s->len - 1] == '\n') { + s->buffer[s->len - 1] = '\0'; + s->len--; + } ret = trace_seq_printf(s, " */\n"); if (!ret) @@ -678,62 +793,91 @@ print_graph_comment(struct print_entry *trace, struct trace_seq *s, enum print_line_t print_graph_function(struct trace_iterator *iter) { - struct trace_seq *s = &iter->seq; struct trace_entry *entry = iter->ent; + struct trace_seq *s = &iter->seq; switch (entry->type) { case TRACE_GRAPH_ENT: { struct ftrace_graph_ent_entry *field; trace_assign_type(field, entry); - return print_graph_entry(field, s, iter, - iter->cpu); + return print_graph_entry(field, s, iter); } case TRACE_GRAPH_RET: { struct ftrace_graph_ret_entry *field; trace_assign_type(field, entry); - return print_graph_return(&field->ret, s, entry, iter->cpu); - } - case TRACE_PRINT: { - struct print_entry *field; - trace_assign_type(field, entry); - return print_graph_comment(field, s, entry, iter); + return print_graph_return(&field->ret, s, entry, iter); } default: - return TRACE_TYPE_UNHANDLED; + return print_graph_comment(s, entry, iter); } + + return TRACE_TYPE_HANDLED; } static void print_graph_headers(struct seq_file *s) { /* 1st line */ seq_printf(s, "# "); + if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME) + seq_printf(s, " TIME "); if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) - seq_printf(s, "CPU "); + seq_printf(s, "CPU"); if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) - seq_printf(s, "TASK/PID "); - if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERHEAD) - seq_printf(s, "OVERHEAD/"); - seq_printf(s, "DURATION FUNCTION CALLS\n"); + seq_printf(s, " TASK/PID "); + if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) + seq_printf(s, " DURATION "); + seq_printf(s, " FUNCTION CALLS\n"); /* 2nd line */ seq_printf(s, "# "); + if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME) + seq_printf(s, " | "); if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) - seq_printf(s, "| "); + seq_printf(s, "| "); if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) - seq_printf(s, "| | "); - if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERHEAD) { - seq_printf(s, "| "); - seq_printf(s, "| | | | |\n"); - } else - seq_printf(s, " | | | | |\n"); + seq_printf(s, " | | "); + if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) + seq_printf(s, " | | "); + seq_printf(s, " | | | |\n"); +} + +static void graph_trace_open(struct trace_iterator *iter) +{ + /* pid and depth on the last trace processed */ + struct fgraph_data *data = alloc_percpu(struct fgraph_data); + int cpu; + + if (!data) + pr_warning("function graph tracer: not enough memory\n"); + else + for_each_possible_cpu(cpu) { + pid_t *pid = &(per_cpu_ptr(data, cpu)->last_pid); + int *depth = &(per_cpu_ptr(data, cpu)->depth); + *pid = -1; + *depth = 0; + } + + iter->private = data; } + +static void graph_trace_close(struct trace_iterator *iter) +{ + free_percpu(iter->private); +} + static struct tracer graph_trace __read_mostly = { - .name = "function_graph", - .init = graph_trace_init, - .reset = graph_trace_reset, + .name = "function_graph", + .open = graph_trace_open, + .close = graph_trace_close, + .wait_pipe = poll_wait_pipe, + .init = graph_trace_init, + .reset = graph_trace_reset, .print_line = print_graph_function, .print_header = print_graph_headers, .flags = &tracer_flags, +#ifdef CONFIG_FTRACE_SELFTEST + .selftest = trace_selftest_startup_function_graph, +#endif }; static __init int init_graph_trace(void) diff --git a/kernel/trace/trace_hw_branches.c b/kernel/trace/trace_hw_branches.c index 649df22d435f..7bfdf4c2347f 100644 --- a/kernel/trace/trace_hw_branches.c +++ b/kernel/trace/trace_hw_branches.c @@ -1,30 +1,53 @@ /* * h/w branch tracer for x86 based on bts * - * Copyright (C) 2008 Markus Metzger <markus.t.metzger@gmail.com> - * + * Copyright (C) 2008-2009 Intel Corporation. + * Markus Metzger <markus.t.metzger@gmail.com>, 2008-2009 */ - -#include <linux/module.h> -#include <linux/fs.h> +#include <linux/spinlock.h> +#include <linux/kallsyms.h> #include <linux/debugfs.h> #include <linux/ftrace.h> -#include <linux/kallsyms.h> +#include <linux/module.h> +#include <linux/cpu.h> +#include <linux/smp.h> +#include <linux/fs.h> #include <asm/ds.h> #include "trace.h" +#include "trace_output.h" #define SIZEOF_BTS (1 << 13) +/* + * The tracer lock protects the below per-cpu tracer array. + * It needs to be held to: + * - start tracing on all cpus + * - stop tracing on all cpus + * - start tracing on a single hotplug cpu + * - stop tracing on a single hotplug cpu + * - read the trace from all cpus + * - read the trace from a single cpu + */ +static DEFINE_SPINLOCK(bts_tracer_lock); static DEFINE_PER_CPU(struct bts_tracer *, tracer); static DEFINE_PER_CPU(unsigned char[SIZEOF_BTS], buffer); #define this_tracer per_cpu(tracer, smp_processor_id()) #define this_buffer per_cpu(buffer, smp_processor_id()) +static int __read_mostly trace_hw_branches_enabled; +static struct trace_array *hw_branch_trace __read_mostly; + +/* + * Start tracing on the current cpu. + * The argument is ignored. + * + * pre: bts_tracer_lock must be locked. + */ static void bts_trace_start_cpu(void *arg) { if (this_tracer) @@ -42,14 +65,20 @@ static void bts_trace_start_cpu(void *arg) static void bts_trace_start(struct trace_array *tr) { - int cpu; + spin_lock(&bts_tracer_lock); - tracing_reset_online_cpus(tr); + on_each_cpu(bts_trace_start_cpu, NULL, 1); + trace_hw_branches_enabled = 1; - for_each_cpu(cpu, cpu_possible_mask) - smp_call_function_single(cpu, bts_trace_start_cpu, NULL, 1); + spin_unlock(&bts_tracer_lock); } +/* + * Stop tracing on the current cpu. + * The argument is ignored. + * + * pre: bts_tracer_lock must be locked. + */ static void bts_trace_stop_cpu(void *arg) { if (this_tracer) { @@ -60,26 +89,60 @@ static void bts_trace_stop_cpu(void *arg) static void bts_trace_stop(struct trace_array *tr) { - int cpu; + spin_lock(&bts_tracer_lock); + + trace_hw_branches_enabled = 0; + on_each_cpu(bts_trace_stop_cpu, NULL, 1); + + spin_unlock(&bts_tracer_lock); +} + +static int __cpuinit bts_hotcpu_handler(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + unsigned int cpu = (unsigned long)hcpu; - for_each_cpu(cpu, cpu_possible_mask) + spin_lock(&bts_tracer_lock); + + if (!trace_hw_branches_enabled) + goto out; + + switch (action) { + case CPU_ONLINE: + case CPU_DOWN_FAILED: + smp_call_function_single(cpu, bts_trace_start_cpu, NULL, 1); + break; + case CPU_DOWN_PREPARE: smp_call_function_single(cpu, bts_trace_stop_cpu, NULL, 1); + break; + } + + out: + spin_unlock(&bts_tracer_lock); + return NOTIFY_DONE; } +static struct notifier_block bts_hotcpu_notifier __cpuinitdata = { + .notifier_call = bts_hotcpu_handler +}; + static int bts_trace_init(struct trace_array *tr) { - tracing_reset_online_cpus(tr); + hw_branch_trace = tr; + bts_trace_start(tr); return 0; } +static void bts_trace_reset(struct trace_array *tr) +{ + bts_trace_stop(tr); +} + static void bts_trace_print_header(struct seq_file *m) { - seq_puts(m, - "# CPU# FROM TO FUNCTION\n"); - seq_puts(m, - "# | | | |\n"); + seq_puts(m, "# CPU# TO <- FROM\n"); } static enum print_line_t bts_trace_print_line(struct trace_iterator *iter) @@ -87,15 +150,15 @@ static enum print_line_t bts_trace_print_line(struct trace_iterator *iter) struct trace_entry *entry = iter->ent; struct trace_seq *seq = &iter->seq; struct hw_branch_entry *it; + unsigned long symflags = TRACE_ITER_SYM_OFFSET; trace_assign_type(it, entry); if (entry->type == TRACE_HW_BRANCHES) { - if (trace_seq_printf(seq, "%4d ", entry->cpu) && - trace_seq_printf(seq, "0x%016llx -> 0x%016llx ", - it->from, it->to) && - (!it->from || - seq_print_ip_sym(seq, it->from, /* sym_flags = */ 0)) && + if (trace_seq_printf(seq, "%4d ", iter->cpu) && + seq_print_ip_sym(seq, it->to, symflags) && + trace_seq_printf(seq, "\t <- ") && + seq_print_ip_sym(seq, it->from, symflags) && trace_seq_printf(seq, "\n")) return TRACE_TYPE_HANDLED; return TRACE_TYPE_PARTIAL_LINE;; @@ -103,26 +166,42 @@ static enum print_line_t bts_trace_print_line(struct trace_iterator *iter) return TRACE_TYPE_UNHANDLED; } -void trace_hw_branch(struct trace_array *tr, u64 from, u64 to) +void trace_hw_branch(u64 from, u64 to) { + struct trace_array *tr = hw_branch_trace; struct ring_buffer_event *event; struct hw_branch_entry *entry; - unsigned long irq; + unsigned long irq1; + int cpu; - event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), &irq); - if (!event) + if (unlikely(!tr)) return; + + if (unlikely(!trace_hw_branches_enabled)) + return; + + local_irq_save(irq1); + cpu = raw_smp_processor_id(); + if (atomic_inc_return(&tr->data[cpu]->disabled) != 1) + goto out; + + event = trace_buffer_lock_reserve(tr, TRACE_HW_BRANCHES, + sizeof(*entry), 0, 0); + if (!event) + goto out; entry = ring_buffer_event_data(event); tracing_generic_entry_update(&entry->ent, 0, from); entry->ent.type = TRACE_HW_BRANCHES; - entry->ent.cpu = smp_processor_id(); entry->from = from; entry->to = to; - ring_buffer_unlock_commit(tr->buffer, event, irq); + trace_buffer_unlock_commit(tr, event, 0, 0); + + out: + atomic_dec(&tr->data[cpu]->disabled); + local_irq_restore(irq1); } -static void trace_bts_at(struct trace_array *tr, - const struct bts_trace *trace, void *at) +static void trace_bts_at(const struct bts_trace *trace, void *at) { struct bts_struct bts; int err = 0; @@ -137,18 +216,29 @@ static void trace_bts_at(struct trace_array *tr, switch (bts.qualifier) { case BTS_BRANCH: - trace_hw_branch(tr, bts.variant.lbr.from, bts.variant.lbr.to); + trace_hw_branch(bts.variant.lbr.from, bts.variant.lbr.to); break; } } +/* + * Collect the trace on the current cpu and write it into the ftrace buffer. + * + * pre: bts_tracer_lock must be locked + */ static void trace_bts_cpu(void *arg) { struct trace_array *tr = (struct trace_array *) arg; const struct bts_trace *trace; unsigned char *at; - if (!this_tracer) + if (unlikely(!tr)) + return; + + if (unlikely(atomic_read(&tr->data[raw_smp_processor_id()]->disabled))) + return; + + if (unlikely(!this_tracer)) return; ds_suspend_bts(this_tracer); @@ -158,11 +248,11 @@ static void trace_bts_cpu(void *arg) for (at = trace->ds.top; (void *)at < trace->ds.end; at += trace->ds.size) - trace_bts_at(tr, trace, at); + trace_bts_at(trace, at); for (at = trace->ds.begin; (void *)at < trace->ds.top; at += trace->ds.size) - trace_bts_at(tr, trace, at); + trace_bts_at(trace, at); out: ds_resume_bts(this_tracer); @@ -170,26 +260,43 @@ out: static void trace_bts_prepare(struct trace_iterator *iter) { - int cpu; + spin_lock(&bts_tracer_lock); + + on_each_cpu(trace_bts_cpu, iter->tr, 1); + + spin_unlock(&bts_tracer_lock); +} + +static void trace_bts_close(struct trace_iterator *iter) +{ + tracing_reset_online_cpus(iter->tr); +} + +void trace_hw_branch_oops(void) +{ + spin_lock(&bts_tracer_lock); + + trace_bts_cpu(hw_branch_trace); - for_each_cpu(cpu, cpu_possible_mask) - smp_call_function_single(cpu, trace_bts_cpu, iter->tr, 1); + spin_unlock(&bts_tracer_lock); } struct tracer bts_tracer __read_mostly = { .name = "hw-branch-tracer", .init = bts_trace_init, - .reset = bts_trace_stop, + .reset = bts_trace_reset, .print_header = bts_trace_print_header, .print_line = bts_trace_print_line, .start = bts_trace_start, .stop = bts_trace_stop, - .open = trace_bts_prepare + .open = trace_bts_prepare, + .close = trace_bts_close }; __init static int init_bts_trace(void) { + register_hotcpu_notifier(&bts_hotcpu_notifier); return register_tracer(&bts_tracer); } device_initcall(init_bts_trace); diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 62a78d943534..b923d13e2fad 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -1,5 +1,5 @@ /* - * trace irqs off criticall timings + * trace irqs off critical timings * * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com> * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com> @@ -32,6 +32,8 @@ enum { static int trace_type __read_mostly; +static int save_lat_flag; + #ifdef CONFIG_PREEMPT_TRACER static inline int preempt_trace(void) @@ -95,7 +97,7 @@ irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip) disabled = atomic_inc_return(&data->disabled); if (likely(disabled == 1)) - trace_function(tr, data, ip, parent_ip, flags, preempt_count()); + trace_function(tr, ip, parent_ip, flags, preempt_count()); atomic_dec(&data->disabled); } @@ -153,7 +155,7 @@ check_critical_timing(struct trace_array *tr, if (!report_latency(delta)) goto out_unlock; - trace_function(tr, data, CALLER_ADDR0, parent_ip, flags, pc); + trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc); latency = nsecs_to_usecs(delta); @@ -177,7 +179,7 @@ out: data->critical_sequence = max_sequence; data->preempt_timestamp = ftrace_now(cpu); tracing_reset(tr, cpu); - trace_function(tr, data, CALLER_ADDR0, parent_ip, flags, pc); + trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc); } static inline void @@ -210,7 +212,7 @@ start_critical_timing(unsigned long ip, unsigned long parent_ip) local_save_flags(flags); - trace_function(tr, data, ip, parent_ip, flags, preempt_count()); + trace_function(tr, ip, parent_ip, flags, preempt_count()); per_cpu(tracing_cpu, cpu) = 1; @@ -244,7 +246,7 @@ stop_critical_timing(unsigned long ip, unsigned long parent_ip) atomic_inc(&data->disabled); local_save_flags(flags); - trace_function(tr, data, ip, parent_ip, flags, preempt_count()); + trace_function(tr, ip, parent_ip, flags, preempt_count()); check_critical_timing(tr, data, parent_ip ? : ip, cpu); data->critical_start = 0; atomic_dec(&data->disabled); @@ -353,33 +355,26 @@ void trace_preempt_off(unsigned long a0, unsigned long a1) } #endif /* CONFIG_PREEMPT_TRACER */ -/* - * save_tracer_enabled is used to save the state of the tracer_enabled - * variable when we disable it when we open a trace output file. - */ -static int save_tracer_enabled; - static void start_irqsoff_tracer(struct trace_array *tr) { register_ftrace_function(&trace_ops); - if (tracing_is_enabled()) { + if (tracing_is_enabled()) tracer_enabled = 1; - save_tracer_enabled = 1; - } else { + else tracer_enabled = 0; - save_tracer_enabled = 0; - } } static void stop_irqsoff_tracer(struct trace_array *tr) { tracer_enabled = 0; - save_tracer_enabled = 0; unregister_ftrace_function(&trace_ops); } static void __irqsoff_tracer_init(struct trace_array *tr) { + save_lat_flag = trace_flags & TRACE_ITER_LATENCY_FMT; + trace_flags |= TRACE_ITER_LATENCY_FMT; + tracing_max_latency = 0; irqsoff_trace = tr; /* make sure that the tracer is visible */ @@ -390,30 +385,19 @@ static void __irqsoff_tracer_init(struct trace_array *tr) static void irqsoff_tracer_reset(struct trace_array *tr) { stop_irqsoff_tracer(tr); + + if (!save_lat_flag) + trace_flags &= ~TRACE_ITER_LATENCY_FMT; } static void irqsoff_tracer_start(struct trace_array *tr) { tracer_enabled = 1; - save_tracer_enabled = 1; } static void irqsoff_tracer_stop(struct trace_array *tr) { tracer_enabled = 0; - save_tracer_enabled = 0; -} - -static void irqsoff_tracer_open(struct trace_iterator *iter) -{ - /* stop the trace while dumping */ - tracer_enabled = 0; -} - -static void irqsoff_tracer_close(struct trace_iterator *iter) -{ - /* restart tracing */ - tracer_enabled = save_tracer_enabled; } #ifdef CONFIG_IRQSOFF_TRACER @@ -431,8 +415,6 @@ static struct tracer irqsoff_tracer __read_mostly = .reset = irqsoff_tracer_reset, .start = irqsoff_tracer_start, .stop = irqsoff_tracer_stop, - .open = irqsoff_tracer_open, - .close = irqsoff_tracer_close, .print_max = 1, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_irqsoff, @@ -459,8 +441,6 @@ static struct tracer preemptoff_tracer __read_mostly = .reset = irqsoff_tracer_reset, .start = irqsoff_tracer_start, .stop = irqsoff_tracer_stop, - .open = irqsoff_tracer_open, - .close = irqsoff_tracer_close, .print_max = 1, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_preemptoff, @@ -489,8 +469,6 @@ static struct tracer preemptirqsoff_tracer __read_mostly = .reset = irqsoff_tracer_reset, .start = irqsoff_tracer_start, .stop = irqsoff_tracer_stop, - .open = irqsoff_tracer_open, - .close = irqsoff_tracer_close, .print_max = 1, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_preemptirqsoff, diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c index 80e503ef6136..8e37fcddd8b4 100644 --- a/kernel/trace/trace_mmiotrace.c +++ b/kernel/trace/trace_mmiotrace.c @@ -12,6 +12,7 @@ #include <asm/atomic.h> #include "trace.h" +#include "trace_output.h" struct header_iter { struct pci_dev *dev; @@ -183,21 +184,22 @@ static enum print_line_t mmio_print_rw(struct trace_iterator *iter) switch (rw->opcode) { case MMIO_READ: ret = trace_seq_printf(s, - "R %d %lu.%06lu %d 0x%llx 0x%lx 0x%lx %d\n", + "R %d %u.%06lu %d 0x%llx 0x%lx 0x%lx %d\n", rw->width, secs, usec_rem, rw->map_id, (unsigned long long)rw->phys, rw->value, rw->pc, 0); break; case MMIO_WRITE: ret = trace_seq_printf(s, - "W %d %lu.%06lu %d 0x%llx 0x%lx 0x%lx %d\n", + "W %d %u.%06lu %d 0x%llx 0x%lx 0x%lx %d\n", rw->width, secs, usec_rem, rw->map_id, (unsigned long long)rw->phys, rw->value, rw->pc, 0); break; case MMIO_UNKNOWN_OP: ret = trace_seq_printf(s, - "UNKNOWN %lu.%06lu %d 0x%llx %02x,%02x,%02x 0x%lx %d\n", + "UNKNOWN %u.%06lu %d 0x%llx %02lx,%02lx," + "%02lx 0x%lx %d\n", secs, usec_rem, rw->map_id, (unsigned long long)rw->phys, (rw->value >> 16) & 0xff, (rw->value >> 8) & 0xff, @@ -229,14 +231,14 @@ static enum print_line_t mmio_print_map(struct trace_iterator *iter) switch (m->opcode) { case MMIO_PROBE: ret = trace_seq_printf(s, - "MAP %lu.%06lu %d 0x%llx 0x%lx 0x%lx 0x%lx %d\n", + "MAP %u.%06lu %d 0x%llx 0x%lx 0x%lx 0x%lx %d\n", secs, usec_rem, m->map_id, (unsigned long long)m->phys, m->virt, m->len, 0UL, 0); break; case MMIO_UNPROBE: ret = trace_seq_printf(s, - "UNMAP %lu.%06lu %d 0x%lx %d\n", + "UNMAP %u.%06lu %d 0x%lx %d\n", secs, usec_rem, m->map_id, 0UL, 0); break; default: @@ -255,18 +257,15 @@ static enum print_line_t mmio_print_mark(struct trace_iterator *iter) const char *msg = print->buf; struct trace_seq *s = &iter->seq; unsigned long long t = ns2usecs(iter->ts); - unsigned long usec_rem = do_div(t, 1000000ULL); + unsigned long usec_rem = do_div(t, USEC_PER_SEC); unsigned secs = (unsigned long)t; int ret; /* The trailing newline must be in the message. */ - ret = trace_seq_printf(s, "MARK %lu.%06lu %s", secs, usec_rem, msg); + ret = trace_seq_printf(s, "MARK %u.%06lu %s", secs, usec_rem, msg); if (!ret) return TRACE_TYPE_PARTIAL_LINE; - if (entry->flags & TRACE_FLAG_CONT) - trace_seq_print_cont(s, iter); - return TRACE_TYPE_HANDLED; } @@ -308,21 +307,17 @@ static void __trace_mmiotrace_rw(struct trace_array *tr, { struct ring_buffer_event *event; struct trace_mmiotrace_rw *entry; - unsigned long irq_flags; + int pc = preempt_count(); - event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), - &irq_flags); + event = trace_buffer_lock_reserve(tr, TRACE_MMIO_RW, + sizeof(*entry), 0, pc); if (!event) { atomic_inc(&dropped_count); return; } entry = ring_buffer_event_data(event); - tracing_generic_entry_update(&entry->ent, 0, preempt_count()); - entry->ent.type = TRACE_MMIO_RW; entry->rw = *rw; - ring_buffer_unlock_commit(tr->buffer, event, irq_flags); - - trace_wake_up(); + trace_buffer_unlock_commit(tr, event, 0, pc); } void mmio_trace_rw(struct mmiotrace_rw *rw) @@ -338,21 +333,17 @@ static void __trace_mmiotrace_map(struct trace_array *tr, { struct ring_buffer_event *event; struct trace_mmiotrace_map *entry; - unsigned long irq_flags; + int pc = preempt_count(); - event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), - &irq_flags); + event = trace_buffer_lock_reserve(tr, TRACE_MMIO_MAP, + sizeof(*entry), 0, pc); if (!event) { atomic_inc(&dropped_count); return; } entry = ring_buffer_event_data(event); - tracing_generic_entry_update(&entry->ent, 0, preempt_count()); - entry->ent.type = TRACE_MMIO_MAP; entry->map = *map; - ring_buffer_unlock_commit(tr->buffer, event, irq_flags); - - trace_wake_up(); + trace_buffer_unlock_commit(tr, event, 0, pc); } void mmio_trace_mapping(struct mmiotrace_map *map) @@ -368,5 +359,5 @@ void mmio_trace_mapping(struct mmiotrace_map *map) int mmio_trace_printk(const char *fmt, va_list args) { - return trace_vprintk(0, -1, fmt, args); + return trace_vprintk(0, fmt, args); } diff --git a/kernel/trace/trace_nop.c b/kernel/trace/trace_nop.c index b9767acd30ac..394f94417e2f 100644 --- a/kernel/trace/trace_nop.c +++ b/kernel/trace/trace_nop.c @@ -47,12 +47,7 @@ static void stop_nop_trace(struct trace_array *tr) static int nop_trace_init(struct trace_array *tr) { - int cpu; ctx_trace = tr; - - for_each_online_cpu(cpu) - tracing_reset(tr, cpu); - start_nop_trace(tr); return 0; } @@ -96,6 +91,7 @@ struct tracer nop_trace __read_mostly = .name = "nop", .init = nop_trace_init, .reset = nop_trace_reset, + .wait_pipe = poll_wait_pipe, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_nop, #endif diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c new file mode 100644 index 000000000000..d72b9a63b247 --- /dev/null +++ b/kernel/trace/trace_output.c @@ -0,0 +1,1017 @@ +/* + * trace_output.c + * + * Copyright (C) 2008 Red Hat Inc, Steven Rostedt <srostedt@redhat.com> + * + */ + +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/ftrace.h> + +#include "trace_output.h" + +/* must be a power of 2 */ +#define EVENT_HASHSIZE 128 + +static DEFINE_MUTEX(trace_event_mutex); +static struct hlist_head event_hash[EVENT_HASHSIZE] __read_mostly; + +static int next_event_type = __TRACE_LAST_TYPE + 1; + +enum print_line_t trace_print_bprintk_msg_only(struct trace_iterator *iter) +{ + struct trace_seq *s = &iter->seq; + struct trace_entry *entry = iter->ent; + struct bprint_entry *field; + int ret; + + trace_assign_type(field, entry); + + ret = trace_seq_bprintf(s, field->fmt, field->buf); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + +enum print_line_t trace_print_printk_msg_only(struct trace_iterator *iter) +{ + struct trace_seq *s = &iter->seq; + struct trace_entry *entry = iter->ent; + struct print_entry *field; + int ret; + + trace_assign_type(field, entry); + + ret = trace_seq_printf(s, "%s", field->buf); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + +/** + * trace_seq_printf - sequence printing of trace information + * @s: trace sequence descriptor + * @fmt: printf format string + * + * The tracer may use either sequence operations or its own + * copy to user routines. To simplify formating of a trace + * trace_seq_printf is used to store strings into a special + * buffer (@s). Then the output may be either used by + * the sequencer or pulled into another buffer. + */ +int +trace_seq_printf(struct trace_seq *s, const char *fmt, ...) +{ + int len = (PAGE_SIZE - 1) - s->len; + va_list ap; + int ret; + + if (!len) + return 0; + + va_start(ap, fmt); + ret = vsnprintf(s->buffer + s->len, len, fmt, ap); + va_end(ap); + + /* If we can't write it all, don't bother writing anything */ + if (ret >= len) + return 0; + + s->len += ret; + + return len; +} + +int trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary) +{ + int len = (PAGE_SIZE - 1) - s->len; + int ret; + + if (!len) + return 0; + + ret = bstr_printf(s->buffer + s->len, len, fmt, binary); + + /* If we can't write it all, don't bother writing anything */ + if (ret >= len) + return 0; + + s->len += ret; + + return len; +} + +/** + * trace_seq_puts - trace sequence printing of simple string + * @s: trace sequence descriptor + * @str: simple string to record + * + * The tracer may use either the sequence operations or its own + * copy to user routines. This function records a simple string + * into a special buffer (@s) for later retrieval by a sequencer + * or other mechanism. + */ +int trace_seq_puts(struct trace_seq *s, const char *str) +{ + int len = strlen(str); + + if (len > ((PAGE_SIZE - 1) - s->len)) + return 0; + + memcpy(s->buffer + s->len, str, len); + s->len += len; + + return len; +} + +int trace_seq_putc(struct trace_seq *s, unsigned char c) +{ + if (s->len >= (PAGE_SIZE - 1)) + return 0; + + s->buffer[s->len++] = c; + + return 1; +} + +int trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len) +{ + if (len > ((PAGE_SIZE - 1) - s->len)) + return 0; + + memcpy(s->buffer + s->len, mem, len); + s->len += len; + + return len; +} + +int trace_seq_putmem_hex(struct trace_seq *s, const void *mem, size_t len) +{ + unsigned char hex[HEX_CHARS]; + const unsigned char *data = mem; + int i, j; + +#ifdef __BIG_ENDIAN + for (i = 0, j = 0; i < len; i++) { +#else + for (i = len-1, j = 0; i >= 0; i--) { +#endif + hex[j++] = hex_asc_hi(data[i]); + hex[j++] = hex_asc_lo(data[i]); + } + hex[j++] = ' '; + + return trace_seq_putmem(s, hex, j); +} + +void *trace_seq_reserve(struct trace_seq *s, size_t len) +{ + void *ret; + + if (len > ((PAGE_SIZE - 1) - s->len)) + return NULL; + + ret = s->buffer + s->len; + s->len += len; + + return ret; +} + +int trace_seq_path(struct trace_seq *s, struct path *path) +{ + unsigned char *p; + + if (s->len >= (PAGE_SIZE - 1)) + return 0; + p = d_path(path, s->buffer + s->len, PAGE_SIZE - s->len); + if (!IS_ERR(p)) { + p = mangle_path(s->buffer + s->len, p, "\n"); + if (p) { + s->len = p - s->buffer; + return 1; + } + } else { + s->buffer[s->len++] = '?'; + return 1; + } + + return 0; +} + +#ifdef CONFIG_KRETPROBES +static inline const char *kretprobed(const char *name) +{ + static const char tramp_name[] = "kretprobe_trampoline"; + int size = sizeof(tramp_name); + + if (strncmp(tramp_name, name, size) == 0) + return "[unknown/kretprobe'd]"; + return name; +} +#else +static inline const char *kretprobed(const char *name) +{ + return name; +} +#endif /* CONFIG_KRETPROBES */ + +static int +seq_print_sym_short(struct trace_seq *s, const char *fmt, unsigned long address) +{ +#ifdef CONFIG_KALLSYMS + char str[KSYM_SYMBOL_LEN]; + const char *name; + + kallsyms_lookup(address, NULL, NULL, NULL, str); + + name = kretprobed(str); + + return trace_seq_printf(s, fmt, name); +#endif + return 1; +} + +static int +seq_print_sym_offset(struct trace_seq *s, const char *fmt, + unsigned long address) +{ +#ifdef CONFIG_KALLSYMS + char str[KSYM_SYMBOL_LEN]; + const char *name; + + sprint_symbol(str, address); + name = kretprobed(str); + + return trace_seq_printf(s, fmt, name); +#endif + return 1; +} + +#ifndef CONFIG_64BIT +# define IP_FMT "%08lx" +#else +# define IP_FMT "%016lx" +#endif + +int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm, + unsigned long ip, unsigned long sym_flags) +{ + struct file *file = NULL; + unsigned long vmstart = 0; + int ret = 1; + + if (mm) { + const struct vm_area_struct *vma; + + down_read(&mm->mmap_sem); + vma = find_vma(mm, ip); + if (vma) { + file = vma->vm_file; + vmstart = vma->vm_start; + } + if (file) { + ret = trace_seq_path(s, &file->f_path); + if (ret) + ret = trace_seq_printf(s, "[+0x%lx]", + ip - vmstart); + } + up_read(&mm->mmap_sem); + } + if (ret && ((sym_flags & TRACE_ITER_SYM_ADDR) || !file)) + ret = trace_seq_printf(s, " <" IP_FMT ">", ip); + return ret; +} + +int +seq_print_userip_objs(const struct userstack_entry *entry, struct trace_seq *s, + unsigned long sym_flags) +{ + struct mm_struct *mm = NULL; + int ret = 1; + unsigned int i; + + if (trace_flags & TRACE_ITER_SYM_USEROBJ) { + struct task_struct *task; + /* + * we do the lookup on the thread group leader, + * since individual threads might have already quit! + */ + rcu_read_lock(); + task = find_task_by_vpid(entry->ent.tgid); + if (task) + mm = get_task_mm(task); + rcu_read_unlock(); + } + + for (i = 0; i < FTRACE_STACK_ENTRIES; i++) { + unsigned long ip = entry->caller[i]; + + if (ip == ULONG_MAX || !ret) + break; + if (i && ret) + ret = trace_seq_puts(s, " <- "); + if (!ip) { + if (ret) + ret = trace_seq_puts(s, "??"); + continue; + } + if (!ret) + break; + if (ret) + ret = seq_print_user_ip(s, mm, ip, sym_flags); + } + + if (mm) + mmput(mm); + return ret; +} + +int +seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags) +{ + int ret; + + if (!ip) + return trace_seq_printf(s, "0"); + + if (sym_flags & TRACE_ITER_SYM_OFFSET) + ret = seq_print_sym_offset(s, "%s", ip); + else + ret = seq_print_sym_short(s, "%s", ip); + + if (!ret) + return 0; + + if (sym_flags & TRACE_ITER_SYM_ADDR) + ret = trace_seq_printf(s, " <" IP_FMT ">", ip); + return ret; +} + +static int +lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu) +{ + int hardirq, softirq; + char comm[TASK_COMM_LEN]; + + trace_find_cmdline(entry->pid, comm); + hardirq = entry->flags & TRACE_FLAG_HARDIRQ; + softirq = entry->flags & TRACE_FLAG_SOFTIRQ; + + if (!trace_seq_printf(s, "%8.8s-%-5d %3d%c%c%c", + comm, entry->pid, cpu, + (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' : + (entry->flags & TRACE_FLAG_IRQS_NOSUPPORT) ? + 'X' : '.', + (entry->flags & TRACE_FLAG_NEED_RESCHED) ? + 'N' : '.', + (hardirq && softirq) ? 'H' : + hardirq ? 'h' : softirq ? 's' : '.')) + return 0; + + if (entry->preempt_count) + return trace_seq_printf(s, "%x", entry->preempt_count); + return trace_seq_puts(s, "."); +} + +static unsigned long preempt_mark_thresh = 100; + +static int +lat_print_timestamp(struct trace_seq *s, u64 abs_usecs, + unsigned long rel_usecs) +{ + return trace_seq_printf(s, " %4lldus%c: ", abs_usecs, + rel_usecs > preempt_mark_thresh ? '!' : + rel_usecs > 1 ? '+' : ' '); +} + +int trace_print_context(struct trace_iterator *iter) +{ + struct trace_seq *s = &iter->seq; + struct trace_entry *entry = iter->ent; + unsigned long long t = ns2usecs(iter->ts); + unsigned long usec_rem = do_div(t, USEC_PER_SEC); + unsigned long secs = (unsigned long)t; + char comm[TASK_COMM_LEN]; + + trace_find_cmdline(entry->pid, comm); + + return trace_seq_printf(s, "%16s-%-5d [%03d] %5lu.%06lu: ", + comm, entry->pid, iter->cpu, secs, usec_rem); +} + +int trace_print_lat_context(struct trace_iterator *iter) +{ + u64 next_ts; + int ret; + struct trace_seq *s = &iter->seq; + struct trace_entry *entry = iter->ent, + *next_entry = trace_find_next_entry(iter, NULL, + &next_ts); + unsigned long verbose = (trace_flags & TRACE_ITER_VERBOSE); + unsigned long abs_usecs = ns2usecs(iter->ts - iter->tr->time_start); + unsigned long rel_usecs; + + if (!next_entry) + next_ts = iter->ts; + rel_usecs = ns2usecs(next_ts - iter->ts); + + if (verbose) { + char comm[TASK_COMM_LEN]; + + trace_find_cmdline(entry->pid, comm); + + ret = trace_seq_printf(s, "%16s %5d %3d %d %08x %08lx [%08lx]" + " %ld.%03ldms (+%ld.%03ldms): ", comm, + entry->pid, iter->cpu, entry->flags, + entry->preempt_count, iter->idx, + ns2usecs(iter->ts), + abs_usecs / USEC_PER_MSEC, + abs_usecs % USEC_PER_MSEC, + rel_usecs / USEC_PER_MSEC, + rel_usecs % USEC_PER_MSEC); + } else { + ret = lat_print_generic(s, entry, iter->cpu); + if (ret) + ret = lat_print_timestamp(s, abs_usecs, rel_usecs); + } + + return ret; +} + +static const char state_to_char[] = TASK_STATE_TO_CHAR_STR; + +static int task_state_char(unsigned long state) +{ + int bit = state ? __ffs(state) + 1 : 0; + + return bit < sizeof(state_to_char) - 1 ? state_to_char[bit] : '?'; +} + +/** + * ftrace_find_event - find a registered event + * @type: the type of event to look for + * + * Returns an event of type @type otherwise NULL + */ +struct trace_event *ftrace_find_event(int type) +{ + struct trace_event *event; + struct hlist_node *n; + unsigned key; + + key = type & (EVENT_HASHSIZE - 1); + + hlist_for_each_entry_rcu(event, n, &event_hash[key], node) { + if (event->type == type) + return event; + } + + return NULL; +} + +/** + * register_ftrace_event - register output for an event type + * @event: the event type to register + * + * Event types are stored in a hash and this hash is used to + * find a way to print an event. If the @event->type is set + * then it will use that type, otherwise it will assign a + * type to use. + * + * If you assign your own type, please make sure it is added + * to the trace_type enum in trace.h, to avoid collisions + * with the dynamic types. + * + * Returns the event type number or zero on error. + */ +int register_ftrace_event(struct trace_event *event) +{ + unsigned key; + int ret = 0; + + mutex_lock(&trace_event_mutex); + + if (!event) { + ret = next_event_type++; + goto out; + } + + if (!event->type) + event->type = next_event_type++; + else if (event->type > __TRACE_LAST_TYPE) { + printk(KERN_WARNING "Need to add type to trace.h\n"); + WARN_ON(1); + } + + if (ftrace_find_event(event->type)) + goto out; + + if (event->trace == NULL) + event->trace = trace_nop_print; + if (event->raw == NULL) + event->raw = trace_nop_print; + if (event->hex == NULL) + event->hex = trace_nop_print; + if (event->binary == NULL) + event->binary = trace_nop_print; + + key = event->type & (EVENT_HASHSIZE - 1); + + hlist_add_head_rcu(&event->node, &event_hash[key]); + + ret = event->type; + out: + mutex_unlock(&trace_event_mutex); + + return ret; +} + +/** + * unregister_ftrace_event - remove a no longer used event + * @event: the event to remove + */ +int unregister_ftrace_event(struct trace_event *event) +{ + mutex_lock(&trace_event_mutex); + hlist_del(&event->node); + mutex_unlock(&trace_event_mutex); + + return 0; +} + +/* + * Standard events + */ + +enum print_line_t trace_nop_print(struct trace_iterator *iter, int flags) +{ + return TRACE_TYPE_HANDLED; +} + +/* TRACE_FN */ +static enum print_line_t trace_fn_trace(struct trace_iterator *iter, int flags) +{ + struct ftrace_entry *field; + struct trace_seq *s = &iter->seq; + + trace_assign_type(field, iter->ent); + + if (!seq_print_ip_sym(s, field->ip, flags)) + goto partial; + + if ((flags & TRACE_ITER_PRINT_PARENT) && field->parent_ip) { + if (!trace_seq_printf(s, " <-")) + goto partial; + if (!seq_print_ip_sym(s, + field->parent_ip, + flags)) + goto partial; + } + if (!trace_seq_printf(s, "\n")) + goto partial; + + return TRACE_TYPE_HANDLED; + + partial: + return TRACE_TYPE_PARTIAL_LINE; +} + +static enum print_line_t trace_fn_raw(struct trace_iterator *iter, int flags) +{ + struct ftrace_entry *field; + + trace_assign_type(field, iter->ent); + + if (!trace_seq_printf(&iter->seq, "%lx %lx\n", + field->ip, + field->parent_ip)) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t trace_fn_hex(struct trace_iterator *iter, int flags) +{ + struct ftrace_entry *field; + struct trace_seq *s = &iter->seq; + + trace_assign_type(field, iter->ent); + + SEQ_PUT_HEX_FIELD_RET(s, field->ip); + SEQ_PUT_HEX_FIELD_RET(s, field->parent_ip); + + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t trace_fn_bin(struct trace_iterator *iter, int flags) +{ + struct ftrace_entry *field; + struct trace_seq *s = &iter->seq; + + trace_assign_type(field, iter->ent); + + SEQ_PUT_FIELD_RET(s, field->ip); + SEQ_PUT_FIELD_RET(s, field->parent_ip); + + return TRACE_TYPE_HANDLED; +} + +static struct trace_event trace_fn_event = { + .type = TRACE_FN, + .trace = trace_fn_trace, + .raw = trace_fn_raw, + .hex = trace_fn_hex, + .binary = trace_fn_bin, +}; + +/* TRACE_CTX an TRACE_WAKE */ +static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter, + char *delim) +{ + struct ctx_switch_entry *field; + char comm[TASK_COMM_LEN]; + int S, T; + + + trace_assign_type(field, iter->ent); + + T = task_state_char(field->next_state); + S = task_state_char(field->prev_state); + trace_find_cmdline(field->next_pid, comm); + if (!trace_seq_printf(&iter->seq, + " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n", + field->prev_pid, + field->prev_prio, + S, delim, + field->next_cpu, + field->next_pid, + field->next_prio, + T, comm)) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t trace_ctx_print(struct trace_iterator *iter, int flags) +{ + return trace_ctxwake_print(iter, "==>"); +} + +static enum print_line_t trace_wake_print(struct trace_iterator *iter, + int flags) +{ + return trace_ctxwake_print(iter, " +"); +} + +static int trace_ctxwake_raw(struct trace_iterator *iter, char S) +{ + struct ctx_switch_entry *field; + int T; + + trace_assign_type(field, iter->ent); + + if (!S) + task_state_char(field->prev_state); + T = task_state_char(field->next_state); + if (!trace_seq_printf(&iter->seq, "%d %d %c %d %d %d %c\n", + field->prev_pid, + field->prev_prio, + S, + field->next_cpu, + field->next_pid, + field->next_prio, + T)) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t trace_ctx_raw(struct trace_iterator *iter, int flags) +{ + return trace_ctxwake_raw(iter, 0); +} + +static enum print_line_t trace_wake_raw(struct trace_iterator *iter, int flags) +{ + return trace_ctxwake_raw(iter, '+'); +} + + +static int trace_ctxwake_hex(struct trace_iterator *iter, char S) +{ + struct ctx_switch_entry *field; + struct trace_seq *s = &iter->seq; + int T; + + trace_assign_type(field, iter->ent); + + if (!S) + task_state_char(field->prev_state); + T = task_state_char(field->next_state); + + SEQ_PUT_HEX_FIELD_RET(s, field->prev_pid); + SEQ_PUT_HEX_FIELD_RET(s, field->prev_prio); + SEQ_PUT_HEX_FIELD_RET(s, S); + SEQ_PUT_HEX_FIELD_RET(s, field->next_cpu); + SEQ_PUT_HEX_FIELD_RET(s, field->next_pid); + SEQ_PUT_HEX_FIELD_RET(s, field->next_prio); + SEQ_PUT_HEX_FIELD_RET(s, T); + + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t trace_ctx_hex(struct trace_iterator *iter, int flags) +{ + return trace_ctxwake_hex(iter, 0); +} + +static enum print_line_t trace_wake_hex(struct trace_iterator *iter, int flags) +{ + return trace_ctxwake_hex(iter, '+'); +} + +static enum print_line_t trace_ctxwake_bin(struct trace_iterator *iter, + int flags) +{ + struct ctx_switch_entry *field; + struct trace_seq *s = &iter->seq; + + trace_assign_type(field, iter->ent); + + SEQ_PUT_FIELD_RET(s, field->prev_pid); + SEQ_PUT_FIELD_RET(s, field->prev_prio); + SEQ_PUT_FIELD_RET(s, field->prev_state); + SEQ_PUT_FIELD_RET(s, field->next_pid); + SEQ_PUT_FIELD_RET(s, field->next_prio); + SEQ_PUT_FIELD_RET(s, field->next_state); + + return TRACE_TYPE_HANDLED; +} + +static struct trace_event trace_ctx_event = { + .type = TRACE_CTX, + .trace = trace_ctx_print, + .raw = trace_ctx_raw, + .hex = trace_ctx_hex, + .binary = trace_ctxwake_bin, +}; + +static struct trace_event trace_wake_event = { + .type = TRACE_WAKE, + .trace = trace_wake_print, + .raw = trace_wake_raw, + .hex = trace_wake_hex, + .binary = trace_ctxwake_bin, +}; + +/* TRACE_SPECIAL */ +static enum print_line_t trace_special_print(struct trace_iterator *iter, + int flags) +{ + struct special_entry *field; + + trace_assign_type(field, iter->ent); + + if (!trace_seq_printf(&iter->seq, "# %ld %ld %ld\n", + field->arg1, + field->arg2, + field->arg3)) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t trace_special_hex(struct trace_iterator *iter, + int flags) +{ + struct special_entry *field; + struct trace_seq *s = &iter->seq; + + trace_assign_type(field, iter->ent); + + SEQ_PUT_HEX_FIELD_RET(s, field->arg1); + SEQ_PUT_HEX_FIELD_RET(s, field->arg2); + SEQ_PUT_HEX_FIELD_RET(s, field->arg3); + + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t trace_special_bin(struct trace_iterator *iter, + int flags) +{ + struct special_entry *field; + struct trace_seq *s = &iter->seq; + + trace_assign_type(field, iter->ent); + + SEQ_PUT_FIELD_RET(s, field->arg1); + SEQ_PUT_FIELD_RET(s, field->arg2); + SEQ_PUT_FIELD_RET(s, field->arg3); + + return TRACE_TYPE_HANDLED; +} + +static struct trace_event trace_special_event = { + .type = TRACE_SPECIAL, + .trace = trace_special_print, + .raw = trace_special_print, + .hex = trace_special_hex, + .binary = trace_special_bin, +}; + +/* TRACE_STACK */ + +static enum print_line_t trace_stack_print(struct trace_iterator *iter, + int flags) +{ + struct stack_entry *field; + struct trace_seq *s = &iter->seq; + int i; + + trace_assign_type(field, iter->ent); + + for (i = 0; i < FTRACE_STACK_ENTRIES; i++) { + if (i) { + if (!trace_seq_puts(s, " <= ")) + goto partial; + + if (!seq_print_ip_sym(s, field->caller[i], flags)) + goto partial; + } + if (!trace_seq_puts(s, "\n")) + goto partial; + } + + return TRACE_TYPE_HANDLED; + + partial: + return TRACE_TYPE_PARTIAL_LINE; +} + +static struct trace_event trace_stack_event = { + .type = TRACE_STACK, + .trace = trace_stack_print, + .raw = trace_special_print, + .hex = trace_special_hex, + .binary = trace_special_bin, +}; + +/* TRACE_USER_STACK */ +static enum print_line_t trace_user_stack_print(struct trace_iterator *iter, + int flags) +{ + struct userstack_entry *field; + struct trace_seq *s = &iter->seq; + + trace_assign_type(field, iter->ent); + + if (!seq_print_userip_objs(field, s, flags)) + goto partial; + + if (!trace_seq_putc(s, '\n')) + goto partial; + + return TRACE_TYPE_HANDLED; + + partial: + return TRACE_TYPE_PARTIAL_LINE; +} + +static struct trace_event trace_user_stack_event = { + .type = TRACE_USER_STACK, + .trace = trace_user_stack_print, + .raw = trace_special_print, + .hex = trace_special_hex, + .binary = trace_special_bin, +}; + +/* TRACE_BPRINT */ +static enum print_line_t +trace_bprint_print(struct trace_iterator *iter, int flags) +{ + struct trace_entry *entry = iter->ent; + struct trace_seq *s = &iter->seq; + struct bprint_entry *field; + + trace_assign_type(field, entry); + + if (!seq_print_ip_sym(s, field->ip, flags)) + goto partial; + + if (!trace_seq_puts(s, ": ")) + goto partial; + + if (!trace_seq_bprintf(s, field->fmt, field->buf)) + goto partial; + + return TRACE_TYPE_HANDLED; + + partial: + return TRACE_TYPE_PARTIAL_LINE; +} + + +static enum print_line_t +trace_bprint_raw(struct trace_iterator *iter, int flags) +{ + struct bprint_entry *field; + struct trace_seq *s = &iter->seq; + + trace_assign_type(field, iter->ent); + + if (!trace_seq_printf(s, ": %lx : ", field->ip)) + goto partial; + + if (!trace_seq_bprintf(s, field->fmt, field->buf)) + goto partial; + + return TRACE_TYPE_HANDLED; + + partial: + return TRACE_TYPE_PARTIAL_LINE; +} + + +static struct trace_event trace_bprint_event = { + .type = TRACE_BPRINT, + .trace = trace_bprint_print, + .raw = trace_bprint_raw, +}; + +/* TRACE_PRINT */ +static enum print_line_t trace_print_print(struct trace_iterator *iter, + int flags) +{ + struct print_entry *field; + struct trace_seq *s = &iter->seq; + + trace_assign_type(field, iter->ent); + + if (!seq_print_ip_sym(s, field->ip, flags)) + goto partial; + + if (!trace_seq_printf(s, ": %s", field->buf)) + goto partial; + + return TRACE_TYPE_HANDLED; + + partial: + return TRACE_TYPE_PARTIAL_LINE; +} + +static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags) +{ + struct print_entry *field; + + trace_assign_type(field, iter->ent); + + if (!trace_seq_printf(&iter->seq, "# %lx %s", field->ip, field->buf)) + goto partial; + + return TRACE_TYPE_HANDLED; + + partial: + return TRACE_TYPE_PARTIAL_LINE; +} + +static struct trace_event trace_print_event = { + .type = TRACE_PRINT, + .trace = trace_print_print, + .raw = trace_print_raw, +}; + + +static struct trace_event *events[] __initdata = { + &trace_fn_event, + &trace_ctx_event, + &trace_wake_event, + &trace_special_event, + &trace_stack_event, + &trace_user_stack_event, + &trace_bprint_event, + &trace_print_event, + NULL +}; + +__init static int init_events(void) +{ + struct trace_event *event; + int i, ret; + + for (i = 0; events[i]; i++) { + event = events[i]; + + ret = register_ftrace_event(event); + if (!ret) { + printk(KERN_WARNING "event %d failed to register\n", + event->type); + WARN_ON_ONCE(1); + } + } + + return 0; +} +device_initcall(init_events); diff --git a/kernel/trace/trace_output.h b/kernel/trace/trace_output.h new file mode 100644 index 000000000000..e0bde39c2dd9 --- /dev/null +++ b/kernel/trace/trace_output.h @@ -0,0 +1,71 @@ +#ifndef __TRACE_EVENTS_H +#define __TRACE_EVENTS_H + +#include "trace.h" + +typedef enum print_line_t (*trace_print_func)(struct trace_iterator *iter, + int flags); + +struct trace_event { + struct hlist_node node; + int type; + trace_print_func trace; + trace_print_func raw; + trace_print_func hex; + trace_print_func binary; +}; + +extern enum print_line_t +trace_print_bprintk_msg_only(struct trace_iterator *iter); +extern enum print_line_t +trace_print_printk_msg_only(struct trace_iterator *iter); + +extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...) + __attribute__ ((format (printf, 2, 3))); +extern int +trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary); +extern int +seq_print_ip_sym(struct trace_seq *s, unsigned long ip, + unsigned long sym_flags); +extern ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, + size_t cnt); +extern int trace_seq_puts(struct trace_seq *s, const char *str); +extern int trace_seq_putc(struct trace_seq *s, unsigned char c); +extern int trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len); +extern int trace_seq_putmem_hex(struct trace_seq *s, const void *mem, + size_t len); +extern void *trace_seq_reserve(struct trace_seq *s, size_t len); +extern int trace_seq_path(struct trace_seq *s, struct path *path); +extern int seq_print_userip_objs(const struct userstack_entry *entry, + struct trace_seq *s, unsigned long sym_flags); +extern int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm, + unsigned long ip, unsigned long sym_flags); + +extern int trace_print_context(struct trace_iterator *iter); +extern int trace_print_lat_context(struct trace_iterator *iter); + +extern struct trace_event *ftrace_find_event(int type); +extern int register_ftrace_event(struct trace_event *event); +extern int unregister_ftrace_event(struct trace_event *event); + +extern enum print_line_t trace_nop_print(struct trace_iterator *iter, + int flags); + +#define MAX_MEMHEX_BYTES 8 +#define HEX_CHARS (MAX_MEMHEX_BYTES*2 + 1) + +#define SEQ_PUT_FIELD_RET(s, x) \ +do { \ + if (!trace_seq_putmem(s, &(x), sizeof(x))) \ + return TRACE_TYPE_PARTIAL_LINE; \ +} while (0) + +#define SEQ_PUT_HEX_FIELD_RET(s, x) \ +do { \ + BUILD_BUG_ON(sizeof(x) > MAX_MEMHEX_BYTES); \ + if (!trace_seq_putmem_hex(s, &(x), sizeof(x))) \ + return TRACE_TYPE_PARTIAL_LINE; \ +} while (0) + +#endif + diff --git a/kernel/trace/trace_power.c b/kernel/trace/trace_power.c index 7bda248daf55..bae791ebcc51 100644 --- a/kernel/trace/trace_power.c +++ b/kernel/trace/trace_power.c @@ -11,15 +11,113 @@ #include <linux/init.h> #include <linux/debugfs.h> -#include <linux/ftrace.h> +#include <trace/power.h> #include <linux/kallsyms.h> #include <linux/module.h> #include "trace.h" +#include "trace_output.h" static struct trace_array *power_trace; static int __read_mostly trace_power_enabled; +static void probe_power_start(struct power_trace *it, unsigned int type, + unsigned int level) +{ + if (!trace_power_enabled) + return; + + memset(it, 0, sizeof(struct power_trace)); + it->state = level; + it->type = type; + it->stamp = ktime_get(); +} + + +static void probe_power_end(struct power_trace *it) +{ + struct ring_buffer_event *event; + struct trace_power *entry; + struct trace_array_cpu *data; + struct trace_array *tr = power_trace; + + if (!trace_power_enabled) + return; + + preempt_disable(); + it->end = ktime_get(); + data = tr->data[smp_processor_id()]; + + event = trace_buffer_lock_reserve(tr, TRACE_POWER, + sizeof(*entry), 0, 0); + if (!event) + goto out; + entry = ring_buffer_event_data(event); + entry->state_data = *it; + trace_buffer_unlock_commit(tr, event, 0, 0); + out: + preempt_enable(); +} + +static void probe_power_mark(struct power_trace *it, unsigned int type, + unsigned int level) +{ + struct ring_buffer_event *event; + struct trace_power *entry; + struct trace_array_cpu *data; + struct trace_array *tr = power_trace; + + if (!trace_power_enabled) + return; + + memset(it, 0, sizeof(struct power_trace)); + it->state = level; + it->type = type; + it->stamp = ktime_get(); + preempt_disable(); + it->end = it->stamp; + data = tr->data[smp_processor_id()]; + + event = trace_buffer_lock_reserve(tr, TRACE_POWER, + sizeof(*entry), 0, 0); + if (!event) + goto out; + entry = ring_buffer_event_data(event); + entry->state_data = *it; + trace_buffer_unlock_commit(tr, event, 0, 0); + out: + preempt_enable(); +} + +static int tracing_power_register(void) +{ + int ret; + + ret = register_trace_power_start(probe_power_start); + if (ret) { + pr_info("power trace: Couldn't activate tracepoint" + " probe to trace_power_start\n"); + return ret; + } + ret = register_trace_power_end(probe_power_end); + if (ret) { + pr_info("power trace: Couldn't activate tracepoint" + " probe to trace_power_end\n"); + goto fail_start; + } + ret = register_trace_power_mark(probe_power_mark); + if (ret) { + pr_info("power trace: Couldn't activate tracepoint" + " probe to trace_power_mark\n"); + goto fail_end; + } + return ret; +fail_end: + unregister_trace_power_end(probe_power_end); +fail_start: + unregister_trace_power_start(probe_power_start); + return ret; +} static void start_power_trace(struct trace_array *tr) { @@ -31,6 +129,14 @@ static void stop_power_trace(struct trace_array *tr) trace_power_enabled = 0; } +static void power_trace_reset(struct trace_array *tr) +{ + trace_power_enabled = 0; + unregister_trace_power_start(probe_power_start); + unregister_trace_power_end(probe_power_end); + unregister_trace_power_mark(probe_power_mark); +} + static int power_trace_init(struct trace_array *tr) { @@ -38,6 +144,7 @@ static int power_trace_init(struct trace_array *tr) power_trace = tr; trace_power_enabled = 1; + tracing_power_register(); for_each_cpu(cpu, cpu_possible_mask) tracing_reset(tr, cpu); @@ -85,7 +192,7 @@ static struct tracer power_tracer __read_mostly = .init = power_trace_init, .start = start_power_trace, .stop = stop_power_trace, - .reset = stop_power_trace, + .reset = power_trace_reset, .print_line = power_print_line, }; @@ -94,86 +201,3 @@ static int init_power_trace(void) return register_tracer(&power_tracer); } device_initcall(init_power_trace); - -void trace_power_start(struct power_trace *it, unsigned int type, - unsigned int level) -{ - if (!trace_power_enabled) - return; - - memset(it, 0, sizeof(struct power_trace)); - it->state = level; - it->type = type; - it->stamp = ktime_get(); -} -EXPORT_SYMBOL_GPL(trace_power_start); - - -void trace_power_end(struct power_trace *it) -{ - struct ring_buffer_event *event; - struct trace_power *entry; - struct trace_array_cpu *data; - unsigned long irq_flags; - struct trace_array *tr = power_trace; - - if (!trace_power_enabled) - return; - - preempt_disable(); - it->end = ktime_get(); - data = tr->data[smp_processor_id()]; - - event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), - &irq_flags); - if (!event) - goto out; - entry = ring_buffer_event_data(event); - tracing_generic_entry_update(&entry->ent, 0, 0); - entry->ent.type = TRACE_POWER; - entry->state_data = *it; - ring_buffer_unlock_commit(tr->buffer, event, irq_flags); - - trace_wake_up(); - - out: - preempt_enable(); -} -EXPORT_SYMBOL_GPL(trace_power_end); - -void trace_power_mark(struct power_trace *it, unsigned int type, - unsigned int level) -{ - struct ring_buffer_event *event; - struct trace_power *entry; - struct trace_array_cpu *data; - unsigned long irq_flags; - struct trace_array *tr = power_trace; - - if (!trace_power_enabled) - return; - - memset(it, 0, sizeof(struct power_trace)); - it->state = level; - it->type = type; - it->stamp = ktime_get(); - preempt_disable(); - it->end = it->stamp; - data = tr->data[smp_processor_id()]; - - event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), - &irq_flags); - if (!event) - goto out; - entry = ring_buffer_event_data(event); - tracing_generic_entry_update(&entry->ent, 0, 0); - entry->ent.type = TRACE_POWER; - entry->state_data = *it; - ring_buffer_unlock_commit(tr->buffer, event, irq_flags); - - trace_wake_up(); - - out: - preempt_enable(); -} -EXPORT_SYMBOL_GPL(trace_power_mark); diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c new file mode 100644 index 000000000000..eb81556107fe --- /dev/null +++ b/kernel/trace/trace_printk.c @@ -0,0 +1,270 @@ +/* + * trace binary printk + * + * Copyright (C) 2008 Lai Jiangshan <laijs@cn.fujitsu.com> + * + */ +#include <linux/seq_file.h> +#include <linux/debugfs.h> +#include <linux/uaccess.h> +#include <linux/kernel.h> +#include <linux/ftrace.h> +#include <linux/string.h> +#include <linux/module.h> +#include <linux/marker.h> +#include <linux/mutex.h> +#include <linux/ctype.h> +#include <linux/list.h> +#include <linux/slab.h> +#include <linux/fs.h> + +#include "trace.h" + +#ifdef CONFIG_MODULES + +/* + * modules trace_printk()'s formats are autosaved in struct trace_bprintk_fmt + * which are queued on trace_bprintk_fmt_list. + */ +static LIST_HEAD(trace_bprintk_fmt_list); + +/* serialize accesses to trace_bprintk_fmt_list */ +static DEFINE_MUTEX(btrace_mutex); + +struct trace_bprintk_fmt { + struct list_head list; + char fmt[0]; +}; + +static inline struct trace_bprintk_fmt *lookup_format(const char *fmt) +{ + struct trace_bprintk_fmt *pos; + list_for_each_entry(pos, &trace_bprintk_fmt_list, list) { + if (!strcmp(pos->fmt, fmt)) + return pos; + } + return NULL; +} + +static +void hold_module_trace_bprintk_format(const char **start, const char **end) +{ + const char **iter; + + mutex_lock(&btrace_mutex); + for (iter = start; iter < end; iter++) { + struct trace_bprintk_fmt *tb_fmt = lookup_format(*iter); + if (tb_fmt) { + *iter = tb_fmt->fmt; + continue; + } + + tb_fmt = kmalloc(offsetof(struct trace_bprintk_fmt, fmt) + + strlen(*iter) + 1, GFP_KERNEL); + if (tb_fmt) { + list_add_tail(&tb_fmt->list, &trace_bprintk_fmt_list); + strcpy(tb_fmt->fmt, *iter); + *iter = tb_fmt->fmt; + } else + *iter = NULL; + } + mutex_unlock(&btrace_mutex); +} + +static int module_trace_bprintk_format_notify(struct notifier_block *self, + unsigned long val, void *data) +{ + struct module *mod = data; + if (mod->num_trace_bprintk_fmt) { + const char **start = mod->trace_bprintk_fmt_start; + const char **end = start + mod->num_trace_bprintk_fmt; + + if (val == MODULE_STATE_COMING) + hold_module_trace_bprintk_format(start, end); + } + return 0; +} + +#else /* !CONFIG_MODULES */ +__init static int +module_trace_bprintk_format_notify(struct notifier_block *self, + unsigned long val, void *data) +{ + return 0; +} +#endif /* CONFIG_MODULES */ + + +__initdata_or_module static +struct notifier_block module_trace_bprintk_format_nb = { + .notifier_call = module_trace_bprintk_format_notify, +}; + +int __trace_bprintk(unsigned long ip, const char *fmt, ...) + { + int ret; + va_list ap; + + if (unlikely(!fmt)) + return 0; + + if (!(trace_flags & TRACE_ITER_PRINTK)) + return 0; + + va_start(ap, fmt); + ret = trace_vbprintk(ip, fmt, ap); + va_end(ap); + return ret; +} +EXPORT_SYMBOL_GPL(__trace_bprintk); + +int __ftrace_vbprintk(unsigned long ip, const char *fmt, va_list ap) + { + if (unlikely(!fmt)) + return 0; + + if (!(trace_flags & TRACE_ITER_PRINTK)) + return 0; + + return trace_vbprintk(ip, fmt, ap); +} +EXPORT_SYMBOL_GPL(__ftrace_vbprintk); + +int __trace_printk(unsigned long ip, const char *fmt, ...) +{ + int ret; + va_list ap; + + if (!(trace_flags & TRACE_ITER_PRINTK)) + return 0; + + va_start(ap, fmt); + ret = trace_vprintk(ip, fmt, ap); + va_end(ap); + return ret; +} +EXPORT_SYMBOL_GPL(__trace_printk); + +int __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap) +{ + if (!(trace_flags & TRACE_ITER_PRINTK)) + return 0; + + return trace_vprintk(ip, fmt, ap); +} +EXPORT_SYMBOL_GPL(__ftrace_vprintk); + +static void * +t_next(struct seq_file *m, void *v, loff_t *pos) +{ + const char **fmt = m->private; + const char **next = fmt; + + (*pos)++; + + if ((unsigned long)fmt >= (unsigned long)__stop___trace_bprintk_fmt) + return NULL; + + next = fmt; + m->private = ++next; + + return fmt; +} + +static void *t_start(struct seq_file *m, loff_t *pos) +{ + return t_next(m, NULL, pos); +} + +static int t_show(struct seq_file *m, void *v) +{ + const char **fmt = v; + const char *str = *fmt; + int i; + + seq_printf(m, "0x%lx : \"", (unsigned long)fmt); + + /* + * Tabs and new lines need to be converted. + */ + for (i = 0; str[i]; i++) { + switch (str[i]) { + case '\n': + seq_puts(m, "\\n"); + break; + case '\t': + seq_puts(m, "\\t"); + break; + case '\\': + seq_puts(m, "\\"); + break; + case '"': + seq_puts(m, "\\\""); + break; + default: + seq_putc(m, str[i]); + } + } + seq_puts(m, "\"\n"); + + return 0; +} + +static void t_stop(struct seq_file *m, void *p) +{ +} + +static const struct seq_operations show_format_seq_ops = { + .start = t_start, + .next = t_next, + .show = t_show, + .stop = t_stop, +}; + +static int +ftrace_formats_open(struct inode *inode, struct file *file) +{ + int ret; + + ret = seq_open(file, &show_format_seq_ops); + if (!ret) { + struct seq_file *m = file->private_data; + + m->private = __start___trace_bprintk_fmt; + } + return ret; +} + +static const struct file_operations ftrace_formats_fops = { + .open = ftrace_formats_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static __init int init_trace_printk_function_export(void) +{ + struct dentry *d_tracer; + struct dentry *entry; + + d_tracer = tracing_init_dentry(); + if (!d_tracer) + return 0; + + entry = debugfs_create_file("printk_formats", 0444, d_tracer, + NULL, &ftrace_formats_fops); + if (!entry) + pr_warning("Could not create debugfs " + "'printk_formats' entry\n"); + + return 0; +} + +fs_initcall(init_trace_printk_function_export); + +static __init int init_trace_printk(void) +{ + return register_module_notifier(&module_trace_bprintk_format_nb); +} + +early_initcall(init_trace_printk); diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c index df175cb4564f..de35f200abd3 100644 --- a/kernel/trace/trace_sched_switch.c +++ b/kernel/trace/trace_sched_switch.c @@ -18,6 +18,7 @@ static struct trace_array *ctx_trace; static int __read_mostly tracer_enabled; static int sched_ref; static DEFINE_MUTEX(sched_register_mutex); +static int sched_stopped; static void probe_sched_switch(struct rq *__rq, struct task_struct *prev, @@ -28,7 +29,7 @@ probe_sched_switch(struct rq *__rq, struct task_struct *prev, int cpu; int pc; - if (!sched_ref) + if (!sched_ref || sched_stopped) return; tracing_record_cmdline(prev); @@ -43,7 +44,7 @@ probe_sched_switch(struct rq *__rq, struct task_struct *prev, data = ctx_trace->data[cpu]; if (likely(!atomic_read(&data->disabled))) - tracing_sched_switch_trace(ctx_trace, data, prev, next, flags, pc); + tracing_sched_switch_trace(ctx_trace, prev, next, flags, pc); local_irq_restore(flags); } @@ -66,7 +67,7 @@ probe_sched_wakeup(struct rq *__rq, struct task_struct *wakee, int success) data = ctx_trace->data[cpu]; if (likely(!atomic_read(&data->disabled))) - tracing_sched_wakeup_trace(ctx_trace, data, wakee, current, + tracing_sched_wakeup_trace(ctx_trace, wakee, current, flags, pc); local_irq_restore(flags); @@ -93,7 +94,7 @@ static int tracing_sched_register(void) ret = register_trace_sched_switch(probe_sched_switch); if (ret) { pr_info("sched trace: Couldn't activate tracepoint" - " probe to kernel_sched_schedule\n"); + " probe to kernel_sched_switch\n"); goto fail_deprobe_wake_new; } @@ -185,12 +186,6 @@ void tracing_sched_switch_assign_trace(struct trace_array *tr) ctx_trace = tr; } -static void start_sched_trace(struct trace_array *tr) -{ - tracing_reset_online_cpus(tr); - tracing_start_sched_switch_record(); -} - static void stop_sched_trace(struct trace_array *tr) { tracing_stop_sched_switch_record(); @@ -199,7 +194,8 @@ static void stop_sched_trace(struct trace_array *tr) static int sched_switch_trace_init(struct trace_array *tr) { ctx_trace = tr; - start_sched_trace(tr); + tracing_reset_online_cpus(tr); + tracing_start_sched_switch_record(); return 0; } @@ -211,13 +207,12 @@ static void sched_switch_trace_reset(struct trace_array *tr) static void sched_switch_trace_start(struct trace_array *tr) { - tracing_reset_online_cpus(tr); - tracing_start_sched_switch(); + sched_stopped = 0; } static void sched_switch_trace_stop(struct trace_array *tr) { - tracing_stop_sched_switch(); + sched_stopped = 1; } static struct tracer sched_switch_trace __read_mostly = @@ -227,6 +222,7 @@ static struct tracer sched_switch_trace __read_mostly = .reset = sched_switch_trace_reset, .start = sched_switch_trace_start, .stop = sched_switch_trace_stop, + .wait_pipe = poll_wait_pipe, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_sched_switch, #endif diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 42ae1e77b6b3..3c5ad6b2ec84 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -25,12 +25,15 @@ static int __read_mostly tracer_enabled; static struct task_struct *wakeup_task; static int wakeup_cpu; static unsigned wakeup_prio = -1; +static int wakeup_rt; static raw_spinlock_t wakeup_lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED; static void __wakeup_reset(struct trace_array *tr); +static int save_lat_flag; + #ifdef CONFIG_FUNCTION_TRACER /* * irqsoff uses its own tracer function to keep the overhead down: @@ -71,7 +74,7 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip) if (task_cpu(wakeup_task) != cpu) goto unlock; - trace_function(tr, data, ip, parent_ip, flags, pc); + trace_function(tr, ip, parent_ip, flags, pc); unlock: __raw_spin_unlock(&wakeup_lock); @@ -151,7 +154,8 @@ probe_wakeup_sched_switch(struct rq *rq, struct task_struct *prev, if (unlikely(!tracer_enabled || next != wakeup_task)) goto out_unlock; - trace_function(wakeup_trace, data, CALLER_ADDR1, CALLER_ADDR2, flags, pc); + trace_function(wakeup_trace, CALLER_ADDR1, CALLER_ADDR2, flags, pc); + tracing_sched_switch_trace(wakeup_trace, prev, next, flags, pc); /* * usecs conversion is slow so we try to delay the conversion @@ -182,13 +186,10 @@ out: static void __wakeup_reset(struct trace_array *tr) { - struct trace_array_cpu *data; int cpu; - for_each_possible_cpu(cpu) { - data = tr->data[cpu]; + for_each_possible_cpu(cpu) tracing_reset(tr, cpu); - } wakeup_cpu = -1; wakeup_prio = -1; @@ -213,6 +214,7 @@ static void wakeup_reset(struct trace_array *tr) static void probe_wakeup(struct rq *rq, struct task_struct *p, int success) { + struct trace_array_cpu *data; int cpu = smp_processor_id(); unsigned long flags; long disabled; @@ -224,7 +226,7 @@ probe_wakeup(struct rq *rq, struct task_struct *p, int success) tracing_record_cmdline(p); tracing_record_cmdline(current); - if (likely(!rt_task(p)) || + if ((wakeup_rt && !rt_task(p)) || p->prio >= wakeup_prio || p->prio >= current->prio) return; @@ -252,9 +254,10 @@ probe_wakeup(struct rq *rq, struct task_struct *p, int success) local_save_flags(flags); - wakeup_trace->data[wakeup_cpu]->preempt_timestamp = ftrace_now(cpu); - trace_function(wakeup_trace, wakeup_trace->data[wakeup_cpu], - CALLER_ADDR1, CALLER_ADDR2, flags, pc); + data = wakeup_trace->data[wakeup_cpu]; + data->preempt_timestamp = ftrace_now(cpu); + tracing_sched_wakeup_trace(wakeup_trace, p, current, flags, pc); + trace_function(wakeup_trace, CALLER_ADDR1, CALLER_ADDR2, flags, pc); out_locked: __raw_spin_unlock(&wakeup_lock); @@ -262,12 +265,6 @@ out: atomic_dec(&wakeup_trace->data[cpu]->disabled); } -/* - * save_tracer_enabled is used to save the state of the tracer_enabled - * variable when we disable it when we open a trace output file. - */ -static int save_tracer_enabled; - static void start_wakeup_tracer(struct trace_array *tr) { int ret; @@ -289,7 +286,7 @@ static void start_wakeup_tracer(struct trace_array *tr) ret = register_trace_sched_switch(probe_wakeup_sched_switch); if (ret) { pr_info("sched trace: Couldn't activate tracepoint" - " probe to kernel_sched_schedule\n"); + " probe to kernel_sched_switch\n"); goto fail_deprobe_wake_new; } @@ -306,13 +303,10 @@ static void start_wakeup_tracer(struct trace_array *tr) register_ftrace_function(&trace_ops); - if (tracing_is_enabled()) { + if (tracing_is_enabled()) tracer_enabled = 1; - save_tracer_enabled = 1; - } else { + else tracer_enabled = 0; - save_tracer_enabled = 0; - } return; fail_deprobe_wake_new: @@ -324,54 +318,54 @@ fail_deprobe: static void stop_wakeup_tracer(struct trace_array *tr) { tracer_enabled = 0; - save_tracer_enabled = 0; unregister_ftrace_function(&trace_ops); unregister_trace_sched_switch(probe_wakeup_sched_switch); unregister_trace_sched_wakeup_new(probe_wakeup); unregister_trace_sched_wakeup(probe_wakeup); } -static int wakeup_tracer_init(struct trace_array *tr) +static int __wakeup_tracer_init(struct trace_array *tr) { + save_lat_flag = trace_flags & TRACE_ITER_LATENCY_FMT; + trace_flags |= TRACE_ITER_LATENCY_FMT; + tracing_max_latency = 0; wakeup_trace = tr; start_wakeup_tracer(tr); return 0; } +static int wakeup_tracer_init(struct trace_array *tr) +{ + wakeup_rt = 0; + return __wakeup_tracer_init(tr); +} + +static int wakeup_rt_tracer_init(struct trace_array *tr) +{ + wakeup_rt = 1; + return __wakeup_tracer_init(tr); +} + static void wakeup_tracer_reset(struct trace_array *tr) { stop_wakeup_tracer(tr); /* make sure we put back any tasks we are tracing */ wakeup_reset(tr); + + if (!save_lat_flag) + trace_flags &= ~TRACE_ITER_LATENCY_FMT; } static void wakeup_tracer_start(struct trace_array *tr) { wakeup_reset(tr); tracer_enabled = 1; - save_tracer_enabled = 1; } static void wakeup_tracer_stop(struct trace_array *tr) { tracer_enabled = 0; - save_tracer_enabled = 0; -} - -static void wakeup_tracer_open(struct trace_iterator *iter) -{ - /* stop the trace while dumping */ - tracer_enabled = 0; -} - -static void wakeup_tracer_close(struct trace_iterator *iter) -{ - /* forget about any processes we were recording */ - if (save_tracer_enabled) { - wakeup_reset(iter->tr); - tracer_enabled = 1; - } } static struct tracer wakeup_tracer __read_mostly = @@ -381,8 +375,20 @@ static struct tracer wakeup_tracer __read_mostly = .reset = wakeup_tracer_reset, .start = wakeup_tracer_start, .stop = wakeup_tracer_stop, - .open = wakeup_tracer_open, - .close = wakeup_tracer_close, + .print_max = 1, +#ifdef CONFIG_FTRACE_SELFTEST + .selftest = trace_selftest_startup_wakeup, +#endif +}; + +static struct tracer wakeup_rt_tracer __read_mostly = +{ + .name = "wakeup_rt", + .init = wakeup_rt_tracer_init, + .reset = wakeup_tracer_reset, + .start = wakeup_tracer_start, + .stop = wakeup_tracer_stop, + .wait_pipe = poll_wait_pipe, .print_max = 1, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_wakeup, @@ -397,6 +403,10 @@ __init static int init_wakeup_tracer(void) if (ret) return ret; + ret = register_tracer(&wakeup_rt_tracer); + if (ret) + return ret; + return 0; } device_initcall(init_wakeup_tracer); diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index bc8e80a86bca..08f4eb2763d1 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -1,5 +1,6 @@ /* Include in trace.c */ +#include <linux/stringify.h> #include <linux/kthread.h> #include <linux/delay.h> @@ -9,11 +10,12 @@ static inline int trace_valid_entry(struct trace_entry *entry) case TRACE_FN: case TRACE_CTX: case TRACE_WAKE: - case TRACE_CONT: case TRACE_STACK: case TRACE_PRINT: case TRACE_SPECIAL: case TRACE_BRANCH: + case TRACE_GRAPH_ENT: + case TRACE_GRAPH_RET: return 1; } return 0; @@ -99,9 +101,6 @@ static inline void warn_failed_init_tracer(struct tracer *trace, int init_ret) #ifdef CONFIG_DYNAMIC_FTRACE -#define __STR(x) #x -#define STR(x) __STR(x) - /* Test dynamic code modification and ftrace filters */ int trace_selftest_startup_dynamic_tracing(struct tracer *trace, struct trace_array *tr, @@ -125,17 +124,17 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace, func(); /* - * Some archs *cough*PowerPC*cough* add charachters to the + * Some archs *cough*PowerPC*cough* add characters to the * start of the function names. We simply put a '*' to - * accomodate them. + * accommodate them. */ - func_name = "*" STR(DYN_FTRACE_TEST_NAME); + func_name = "*" __stringify(DYN_FTRACE_TEST_NAME); /* filter only on our function */ ftrace_set_filter(func_name, strlen(func_name), 1); /* enable tracing */ - ret = trace->init(tr); + ret = tracer_init(trace, tr); if (ret) { warn_failed_init_tracer(trace, ret); goto out; @@ -209,7 +208,7 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr) ftrace_enabled = 1; tracer_enabled = 1; - ret = trace->init(tr); + ret = tracer_init(trace, tr); if (ret) { warn_failed_init_tracer(trace, ret); goto out; @@ -247,6 +246,90 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr) } #endif /* CONFIG_FUNCTION_TRACER */ + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + +/* Maximum number of functions to trace before diagnosing a hang */ +#define GRAPH_MAX_FUNC_TEST 100000000 + +static void __ftrace_dump(bool disable_tracing); +static unsigned int graph_hang_thresh; + +/* Wrap the real function entry probe to avoid possible hanging */ +static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace) +{ + /* This is harmlessly racy, we want to approximately detect a hang */ + if (unlikely(++graph_hang_thresh > GRAPH_MAX_FUNC_TEST)) { + ftrace_graph_stop(); + printk(KERN_WARNING "BUG: Function graph tracer hang!\n"); + if (ftrace_dump_on_oops) + __ftrace_dump(false); + return 0; + } + + return trace_graph_entry(trace); +} + +/* + * Pretty much the same than for the function tracer from which the selftest + * has been borrowed. + */ +int +trace_selftest_startup_function_graph(struct tracer *trace, + struct trace_array *tr) +{ + int ret; + unsigned long count; + + /* + * Simulate the init() callback but we attach a watchdog callback + * to detect and recover from possible hangs + */ + tracing_reset_online_cpus(tr); + ret = register_ftrace_graph(&trace_graph_return, + &trace_graph_entry_watchdog); + if (ret) { + warn_failed_init_tracer(trace, ret); + goto out; + } + tracing_start_cmdline_record(); + + /* Sleep for a 1/10 of a second */ + msleep(100); + + /* Have we just recovered from a hang? */ + if (graph_hang_thresh > GRAPH_MAX_FUNC_TEST) { + tracing_selftest_disabled = true; + ret = -1; + goto out; + } + + tracing_stop(); + + /* check the trace buffer */ + ret = trace_test_buffer(tr, &count); + + trace->reset(tr); + tracing_start(); + + if (!ret && !count) { + printk(KERN_CONT ".. no entries found .."); + ret = -1; + goto out; + } + + /* Don't test dynamic tracing, the function tracer already did */ + +out: + /* Stop it if we failed */ + if (ret) + ftrace_graph_stop(); + + return ret; +} +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + + #ifdef CONFIG_IRQSOFF_TRACER int trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr) @@ -256,7 +339,7 @@ trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr) int ret; /* start the tracing */ - ret = trace->init(tr); + ret = tracer_init(trace, tr); if (ret) { warn_failed_init_tracer(trace, ret); return ret; @@ -268,6 +351,14 @@ trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr) local_irq_disable(); udelay(100); local_irq_enable(); + + /* + * Stop the tracer to avoid a warning subsequent + * to buffer flipping failure because tracing_stop() + * disables the tr and max buffers, making flipping impossible + * in case of parallels max irqs off latencies. + */ + trace->stop(tr); /* stop the tracing. */ tracing_stop(); /* check both trace buffers */ @@ -310,7 +401,7 @@ trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr) } /* start the tracing */ - ret = trace->init(tr); + ret = tracer_init(trace, tr); if (ret) { warn_failed_init_tracer(trace, ret); return ret; @@ -322,6 +413,14 @@ trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr) preempt_disable(); udelay(100); preempt_enable(); + + /* + * Stop the tracer to avoid a warning subsequent + * to buffer flipping failure because tracing_stop() + * disables the tr and max buffers, making flipping impossible + * in case of parallels max preempt off latencies. + */ + trace->stop(tr); /* stop the tracing. */ tracing_stop(); /* check both trace buffers */ @@ -364,10 +463,10 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array * } /* start the tracing */ - ret = trace->init(tr); + ret = tracer_init(trace, tr); if (ret) { warn_failed_init_tracer(trace, ret); - goto out; + goto out_no_start; } /* reset the max latency */ @@ -381,31 +480,35 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array * /* reverse the order of preempt vs irqs */ local_irq_enable(); + /* + * Stop the tracer to avoid a warning subsequent + * to buffer flipping failure because tracing_stop() + * disables the tr and max buffers, making flipping impossible + * in case of parallels max irqs/preempt off latencies. + */ + trace->stop(tr); /* stop the tracing. */ tracing_stop(); /* check both trace buffers */ ret = trace_test_buffer(tr, NULL); - if (ret) { - tracing_start(); + if (ret) goto out; - } ret = trace_test_buffer(&max_tr, &count); - if (ret) { - tracing_start(); + if (ret) goto out; - } if (!ret && !count) { printk(KERN_CONT ".. no entries found .."); ret = -1; - tracing_start(); goto out; } /* do the test by disabling interrupts first this time */ tracing_max_latency = 0; tracing_start(); + trace->start(tr); + preempt_disable(); local_irq_disable(); udelay(100); @@ -413,6 +516,7 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array * /* reverse the order of preempt vs irqs */ local_irq_enable(); + trace->stop(tr); /* stop the tracing. */ tracing_stop(); /* check both trace buffers */ @@ -428,9 +532,10 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array * goto out; } - out: - trace->reset(tr); +out: tracing_start(); +out_no_start: + trace->reset(tr); tracing_max_latency = save_max; return ret; @@ -496,7 +601,7 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr) wait_for_completion(&isrt); /* start the tracing */ - ret = trace->init(tr); + ret = tracer_init(trace, tr); if (ret) { warn_failed_init_tracer(trace, ret); return ret; @@ -557,7 +662,7 @@ trace_selftest_startup_sched_switch(struct tracer *trace, struct trace_array *tr int ret; /* start the tracing */ - ret = trace->init(tr); + ret = tracer_init(trace, tr); if (ret) { warn_failed_init_tracer(trace, ret); return ret; @@ -589,10 +694,10 @@ trace_selftest_startup_sysprof(struct tracer *trace, struct trace_array *tr) int ret; /* start the tracing */ - ret = trace->init(tr); + ret = tracer_init(trace, tr); if (ret) { warn_failed_init_tracer(trace, ret); - return 0; + return ret; } /* Sleep for a 1/10 of a second */ @@ -604,6 +709,11 @@ trace_selftest_startup_sysprof(struct tracer *trace, struct trace_array *tr) trace->reset(tr); tracing_start(); + if (!ret && !count) { + printk(KERN_CONT ".. no entries found .."); + ret = -1; + } + return ret; } #endif /* CONFIG_SYSPROF_TRACER */ @@ -616,7 +726,7 @@ trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr) int ret; /* start the tracing */ - ret = trace->init(tr); + ret = tracer_init(trace, tr); if (ret) { warn_failed_init_tracer(trace, ret); return ret; @@ -631,6 +741,11 @@ trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr) trace->reset(tr); tracing_start(); + if (!ret && !count) { + printk(KERN_CONT ".. no entries found .."); + ret = -1; + } + return ret; } #endif /* CONFIG_BRANCH_TRACER */ diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index d0871bc0aca5..c750f65f9661 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -245,16 +245,31 @@ static int trace_lookup_stack(struct seq_file *m, long i) #endif } +static void print_disabled(struct seq_file *m) +{ + seq_puts(m, "#\n" + "# Stack tracer disabled\n" + "#\n" + "# To enable the stack tracer, either add 'stacktrace' to the\n" + "# kernel command line\n" + "# or 'echo 1 > /proc/sys/kernel/stack_tracer_enabled'\n" + "#\n"); +} + static int t_show(struct seq_file *m, void *v) { long i; int size; if (v == SEQ_START_TOKEN) { - seq_printf(m, " Depth Size Location" + seq_printf(m, " Depth Size Location" " (%d entries)\n" - " ----- ---- --------\n", + " ----- ---- --------\n", max_stack_trace.nr_entries); + + if (!stack_tracer_enabled && !max_stack_size) + print_disabled(m); + return 0; } diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c new file mode 100644 index 000000000000..acdebd771a93 --- /dev/null +++ b/kernel/trace/trace_stat.c @@ -0,0 +1,326 @@ +/* + * Infrastructure for statistic tracing (histogram output). + * + * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com> + * + * Based on the code from trace_branch.c which is + * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com> + * + */ + + +#include <linux/list.h> +#include <linux/debugfs.h> +#include "trace_stat.h" +#include "trace.h" + + +/* List of stat entries from a tracer */ +struct trace_stat_list { + struct list_head list; + void *stat; +}; + +/* A stat session is the stats output in one file */ +struct tracer_stat_session { + struct list_head session_list; + struct tracer_stat *ts; + struct list_head stat_list; + struct mutex stat_mutex; + struct dentry *file; +}; + +/* All of the sessions currently in use. Each stat file embed one session */ +static LIST_HEAD(all_stat_sessions); +static DEFINE_MUTEX(all_stat_sessions_mutex); + +/* The root directory for all stat files */ +static struct dentry *stat_dir; + + +static void reset_stat_session(struct tracer_stat_session *session) +{ + struct trace_stat_list *node, *next; + + list_for_each_entry_safe(node, next, &session->stat_list, list) + kfree(node); + + INIT_LIST_HEAD(&session->stat_list); +} + +static void destroy_session(struct tracer_stat_session *session) +{ + debugfs_remove(session->file); + reset_stat_session(session); + mutex_destroy(&session->stat_mutex); + kfree(session); +} + +/* + * For tracers that don't provide a stat_cmp callback. + * This one will force an immediate insertion on tail of + * the list. + */ +static int dummy_cmp(void *p1, void *p2) +{ + return 1; +} + +/* + * Initialize the stat list at each trace_stat file opening. + * All of these copies and sorting are required on all opening + * since the stats could have changed between two file sessions. + */ +static int stat_seq_init(struct tracer_stat_session *session) +{ + struct trace_stat_list *iter_entry, *new_entry; + struct tracer_stat *ts = session->ts; + void *stat; + int ret = 0; + int i; + + mutex_lock(&session->stat_mutex); + reset_stat_session(session); + + if (!ts->stat_cmp) + ts->stat_cmp = dummy_cmp; + + stat = ts->stat_start(); + if (!stat) + goto exit; + + /* + * The first entry. Actually this is the second, but the first + * one (the stat_list head) is pointless. + */ + new_entry = kmalloc(sizeof(struct trace_stat_list), GFP_KERNEL); + if (!new_entry) { + ret = -ENOMEM; + goto exit; + } + + INIT_LIST_HEAD(&new_entry->list); + + list_add(&new_entry->list, &session->stat_list); + + new_entry->stat = stat; + + /* + * Iterate over the tracer stat entries and store them in a sorted + * list. + */ + for (i = 1; ; i++) { + stat = ts->stat_next(stat, i); + + /* End of insertion */ + if (!stat) + break; + + new_entry = kmalloc(sizeof(struct trace_stat_list), GFP_KERNEL); + if (!new_entry) { + ret = -ENOMEM; + goto exit_free_list; + } + + INIT_LIST_HEAD(&new_entry->list); + new_entry->stat = stat; + + list_for_each_entry_reverse(iter_entry, &session->stat_list, + list) { + + /* Insertion with a descendent sorting */ + if (ts->stat_cmp(iter_entry->stat, + new_entry->stat) >= 0) { + + list_add(&new_entry->list, &iter_entry->list); + break; + } + } + + /* The current larger value */ + if (list_empty(&new_entry->list)) + list_add(&new_entry->list, &session->stat_list); + } +exit: + mutex_unlock(&session->stat_mutex); + return ret; + +exit_free_list: + reset_stat_session(session); + mutex_unlock(&session->stat_mutex); + return ret; +} + + +static void *stat_seq_start(struct seq_file *s, loff_t *pos) +{ + struct tracer_stat_session *session = s->private; + + /* Prevent from tracer switch or stat_list modification */ + mutex_lock(&session->stat_mutex); + + /* If we are in the beginning of the file, print the headers */ + if (!*pos && session->ts->stat_headers) + return SEQ_START_TOKEN; + + return seq_list_start(&session->stat_list, *pos); +} + +static void *stat_seq_next(struct seq_file *s, void *p, loff_t *pos) +{ + struct tracer_stat_session *session = s->private; + + if (p == SEQ_START_TOKEN) + return seq_list_start(&session->stat_list, *pos); + + return seq_list_next(p, &session->stat_list, pos); +} + +static void stat_seq_stop(struct seq_file *s, void *p) +{ + struct tracer_stat_session *session = s->private; + mutex_unlock(&session->stat_mutex); +} + +static int stat_seq_show(struct seq_file *s, void *v) +{ + struct tracer_stat_session *session = s->private; + struct trace_stat_list *l = list_entry(v, struct trace_stat_list, list); + + if (v == SEQ_START_TOKEN) + return session->ts->stat_headers(s); + + return session->ts->stat_show(s, l->stat); +} + +static const struct seq_operations trace_stat_seq_ops = { + .start = stat_seq_start, + .next = stat_seq_next, + .stop = stat_seq_stop, + .show = stat_seq_show +}; + +/* The session stat is refilled and resorted at each stat file opening */ +static int tracing_stat_open(struct inode *inode, struct file *file) +{ + int ret; + + struct tracer_stat_session *session = inode->i_private; + + ret = seq_open(file, &trace_stat_seq_ops); + if (!ret) { + struct seq_file *m = file->private_data; + m->private = session; + ret = stat_seq_init(session); + } + + return ret; +} + +/* + * Avoid consuming memory with our now useless list. + */ +static int tracing_stat_release(struct inode *i, struct file *f) +{ + struct tracer_stat_session *session = i->i_private; + + mutex_lock(&session->stat_mutex); + reset_stat_session(session); + mutex_unlock(&session->stat_mutex); + + return 0; +} + +static const struct file_operations tracing_stat_fops = { + .open = tracing_stat_open, + .read = seq_read, + .llseek = seq_lseek, + .release = tracing_stat_release +}; + +static int tracing_stat_init(void) +{ + struct dentry *d_tracing; + + d_tracing = tracing_init_dentry(); + + stat_dir = debugfs_create_dir("trace_stat", d_tracing); + if (!stat_dir) + pr_warning("Could not create debugfs " + "'trace_stat' entry\n"); + return 0; +} + +static int init_stat_file(struct tracer_stat_session *session) +{ + if (!stat_dir && tracing_stat_init()) + return -ENODEV; + + session->file = debugfs_create_file(session->ts->name, 0644, + stat_dir, + session, &tracing_stat_fops); + if (!session->file) + return -ENOMEM; + return 0; +} + +int register_stat_tracer(struct tracer_stat *trace) +{ + struct tracer_stat_session *session, *node, *tmp; + int ret; + + if (!trace) + return -EINVAL; + + if (!trace->stat_start || !trace->stat_next || !trace->stat_show) + return -EINVAL; + + /* Already registered? */ + mutex_lock(&all_stat_sessions_mutex); + list_for_each_entry_safe(node, tmp, &all_stat_sessions, session_list) { + if (node->ts == trace) { + mutex_unlock(&all_stat_sessions_mutex); + return -EINVAL; + } + } + mutex_unlock(&all_stat_sessions_mutex); + + /* Init the session */ + session = kmalloc(sizeof(struct tracer_stat_session), GFP_KERNEL); + if (!session) + return -ENOMEM; + + session->ts = trace; + INIT_LIST_HEAD(&session->session_list); + INIT_LIST_HEAD(&session->stat_list); + mutex_init(&session->stat_mutex); + session->file = NULL; + + ret = init_stat_file(session); + if (ret) { + destroy_session(session); + return ret; + } + + /* Register */ + mutex_lock(&all_stat_sessions_mutex); + list_add_tail(&session->session_list, &all_stat_sessions); + mutex_unlock(&all_stat_sessions_mutex); + + return 0; +} + +void unregister_stat_tracer(struct tracer_stat *trace) +{ + struct tracer_stat_session *node, *tmp; + + mutex_lock(&all_stat_sessions_mutex); + list_for_each_entry_safe(node, tmp, &all_stat_sessions, session_list) { + if (node->ts == trace) { + list_del(&node->session_list); + destroy_session(node); + break; + } + } + mutex_unlock(&all_stat_sessions_mutex); +} diff --git a/kernel/trace/trace_stat.h b/kernel/trace/trace_stat.h new file mode 100644 index 000000000000..202274cf7f3d --- /dev/null +++ b/kernel/trace/trace_stat.h @@ -0,0 +1,31 @@ +#ifndef __TRACE_STAT_H +#define __TRACE_STAT_H + +#include <linux/seq_file.h> + +/* + * If you want to provide a stat file (one-shot statistics), fill + * an iterator with stat_start/stat_next and a stat_show callbacks. + * The others callbacks are optional. + */ +struct tracer_stat { + /* The name of your stat file */ + const char *name; + /* Iteration over statistic entries */ + void *(*stat_start)(void); + void *(*stat_next)(void *prev, int idx); + /* Compare two entries for stats sorting */ + int (*stat_cmp)(void *p1, void *p2); + /* Print a stat entry */ + int (*stat_show)(struct seq_file *s, void *p); + /* Print the headers of your stat entries */ + int (*stat_headers)(struct seq_file *s); +}; + +/* + * Destroy or create a stat file + */ +extern int register_stat_tracer(struct tracer_stat *trace); +extern void unregister_stat_tracer(struct tracer_stat *trace); + +#endif /* __TRACE_STAT_H */ diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c new file mode 100644 index 000000000000..a2a3af29c943 --- /dev/null +++ b/kernel/trace/trace_syscalls.c @@ -0,0 +1,250 @@ +#include <linux/kernel.h> +#include <linux/ftrace.h> +#include <asm/syscall.h> + +#include "trace_output.h" +#include "trace.h" + +/* Keep a counter of the syscall tracing users */ +static int refcount; + +/* Prevent from races on thread flags toggling */ +static DEFINE_MUTEX(syscall_trace_lock); + +/* Option to display the parameters types */ +enum { + TRACE_SYSCALLS_OPT_TYPES = 0x1, +}; + +static struct tracer_opt syscalls_opts[] = { + { TRACER_OPT(syscall_arg_type, TRACE_SYSCALLS_OPT_TYPES) }, + { } +}; + +static struct tracer_flags syscalls_flags = { + .val = 0, /* By default: no parameters types */ + .opts = syscalls_opts +}; + +enum print_line_t +print_syscall_enter(struct trace_iterator *iter, int flags) +{ + struct trace_seq *s = &iter->seq; + struct trace_entry *ent = iter->ent; + struct syscall_trace_enter *trace; + struct syscall_metadata *entry; + int i, ret, syscall; + + trace_assign_type(trace, ent); + + syscall = trace->nr; + + entry = syscall_nr_to_meta(syscall); + if (!entry) + goto end; + + ret = trace_seq_printf(s, "%s(", entry->name); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + for (i = 0; i < entry->nb_args; i++) { + /* parameter types */ + if (syscalls_flags.val & TRACE_SYSCALLS_OPT_TYPES) { + ret = trace_seq_printf(s, "%s ", entry->types[i]); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + } + /* parameter values */ + ret = trace_seq_printf(s, "%s: %lx%s ", entry->args[i], + trace->args[i], + i == entry->nb_args - 1 ? ")" : ","); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + } + +end: + trace_seq_printf(s, "\n"); + return TRACE_TYPE_HANDLED; +} + +enum print_line_t +print_syscall_exit(struct trace_iterator *iter, int flags) +{ + struct trace_seq *s = &iter->seq; + struct trace_entry *ent = iter->ent; + struct syscall_trace_exit *trace; + int syscall; + struct syscall_metadata *entry; + int ret; + + trace_assign_type(trace, ent); + + syscall = trace->nr; + + entry = syscall_nr_to_meta(syscall); + if (!entry) { + trace_seq_printf(s, "\n"); + return TRACE_TYPE_HANDLED; + } + + ret = trace_seq_printf(s, "%s -> 0x%lx\n", entry->name, + trace->ret); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + +void start_ftrace_syscalls(void) +{ + unsigned long flags; + struct task_struct *g, *t; + + mutex_lock(&syscall_trace_lock); + + /* Don't enable the flag on the tasks twice */ + if (++refcount != 1) + goto unlock; + + arch_init_ftrace_syscalls(); + read_lock_irqsave(&tasklist_lock, flags); + + do_each_thread(g, t) { + set_tsk_thread_flag(t, TIF_SYSCALL_FTRACE); + } while_each_thread(g, t); + + read_unlock_irqrestore(&tasklist_lock, flags); + +unlock: + mutex_unlock(&syscall_trace_lock); +} + +void stop_ftrace_syscalls(void) +{ + unsigned long flags; + struct task_struct *g, *t; + + mutex_lock(&syscall_trace_lock); + + /* There are perhaps still some users */ + if (--refcount) + goto unlock; + + read_lock_irqsave(&tasklist_lock, flags); + + do_each_thread(g, t) { + clear_tsk_thread_flag(t, TIF_SYSCALL_FTRACE); + } while_each_thread(g, t); + + read_unlock_irqrestore(&tasklist_lock, flags); + +unlock: + mutex_unlock(&syscall_trace_lock); +} + +void ftrace_syscall_enter(struct pt_regs *regs) +{ + struct syscall_trace_enter *entry; + struct syscall_metadata *sys_data; + struct ring_buffer_event *event; + int size; + int syscall_nr; + + syscall_nr = syscall_get_nr(current, regs); + + sys_data = syscall_nr_to_meta(syscall_nr); + if (!sys_data) + return; + + size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args; + + event = trace_current_buffer_lock_reserve(TRACE_SYSCALL_ENTER, size, + 0, 0); + if (!event) + return; + + entry = ring_buffer_event_data(event); + entry->nr = syscall_nr; + syscall_get_arguments(current, regs, 0, sys_data->nb_args, entry->args); + + trace_current_buffer_unlock_commit(event, 0, 0); + trace_wake_up(); +} + +void ftrace_syscall_exit(struct pt_regs *regs) +{ + struct syscall_trace_exit *entry; + struct syscall_metadata *sys_data; + struct ring_buffer_event *event; + int syscall_nr; + + syscall_nr = syscall_get_nr(current, regs); + + sys_data = syscall_nr_to_meta(syscall_nr); + if (!sys_data) + return; + + event = trace_current_buffer_lock_reserve(TRACE_SYSCALL_EXIT, + sizeof(*entry), 0, 0); + if (!event) + return; + + entry = ring_buffer_event_data(event); + entry->nr = syscall_nr; + entry->ret = syscall_get_return_value(current, regs); + + trace_current_buffer_unlock_commit(event, 0, 0); + trace_wake_up(); +} + +static int init_syscall_tracer(struct trace_array *tr) +{ + start_ftrace_syscalls(); + + return 0; +} + +static void reset_syscall_tracer(struct trace_array *tr) +{ + stop_ftrace_syscalls(); + tracing_reset_online_cpus(tr); +} + +static struct trace_event syscall_enter_event = { + .type = TRACE_SYSCALL_ENTER, + .trace = print_syscall_enter, +}; + +static struct trace_event syscall_exit_event = { + .type = TRACE_SYSCALL_EXIT, + .trace = print_syscall_exit, +}; + +static struct tracer syscall_tracer __read_mostly = { + .name = "syscall", + .init = init_syscall_tracer, + .reset = reset_syscall_tracer, + .flags = &syscalls_flags, +}; + +__init int register_ftrace_syscalls(void) +{ + int ret; + + ret = register_ftrace_event(&syscall_enter_event); + if (!ret) { + printk(KERN_WARNING "event %d failed to register\n", + syscall_enter_event.type); + WARN_ON_ONCE(1); + } + + ret = register_ftrace_event(&syscall_exit_event); + if (!ret) { + printk(KERN_WARNING "event %d failed to register\n", + syscall_exit_event.type); + WARN_ON_ONCE(1); + } + + return register_tracer(&syscall_tracer); +} +device_initcall(register_ftrace_syscalls); diff --git a/kernel/trace/trace_sysprof.c b/kernel/trace/trace_sysprof.c index eaca5ad803ff..91fd19c2149f 100644 --- a/kernel/trace/trace_sysprof.c +++ b/kernel/trace/trace_sysprof.c @@ -88,7 +88,7 @@ static void backtrace_address(void *data, unsigned long addr, int reliable) } } -const static struct stacktrace_ops backtrace_ops = { +static const struct stacktrace_ops backtrace_ops = { .warning = backtrace_warning, .warning_symbol = backtrace_warning_symbol, .stack = backtrace_stack, @@ -226,15 +226,6 @@ static void stop_stack_timers(void) stop_stack_timer(cpu); } -static void start_stack_trace(struct trace_array *tr) -{ - mutex_lock(&sample_timer_lock); - tracing_reset_online_cpus(tr); - start_stack_timers(); - tracer_enabled = 1; - mutex_unlock(&sample_timer_lock); -} - static void stop_stack_trace(struct trace_array *tr) { mutex_lock(&sample_timer_lock); @@ -247,12 +238,18 @@ static int stack_trace_init(struct trace_array *tr) { sysprof_trace = tr; - start_stack_trace(tr); + tracing_start_cmdline_record(); + + mutex_lock(&sample_timer_lock); + start_stack_timers(); + tracer_enabled = 1; + mutex_unlock(&sample_timer_lock); return 0; } static void stack_trace_reset(struct trace_array *tr) { + tracing_stop_cmdline_record(); stop_stack_trace(tr); } @@ -317,7 +314,7 @@ sysprof_sample_write(struct file *filp, const char __user *ubuf, return cnt; } -static struct file_operations sysprof_sample_fops = { +static const struct file_operations sysprof_sample_fops = { .read = sysprof_sample_read, .write = sysprof_sample_write, }; @@ -330,5 +327,5 @@ void init_tracer_sysprof_debugfs(struct dentry *d_tracer) d_tracer, NULL, &sysprof_sample_fops); if (entry) return; - pr_warning("Could not create debugfs 'dyn_ftrace_total_info' entry\n"); + pr_warning("Could not create debugfs 'sysprof_sample_period' entry\n"); } diff --git a/kernel/trace/trace_workqueue.c b/kernel/trace/trace_workqueue.c new file mode 100644 index 000000000000..797201e4a137 --- /dev/null +++ b/kernel/trace/trace_workqueue.c @@ -0,0 +1,288 @@ +/* + * Workqueue statistical tracer. + * + * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com> + * + */ + + +#include <trace/workqueue.h> +#include <linux/list.h> +#include <linux/percpu.h> +#include "trace_stat.h" +#include "trace.h" + + +/* A cpu workqueue thread */ +struct cpu_workqueue_stats { + struct list_head list; +/* Useful to know if we print the cpu headers */ + bool first_entry; + int cpu; + pid_t pid; +/* Can be inserted from interrupt or user context, need to be atomic */ + atomic_t inserted; +/* + * Don't need to be atomic, works are serialized in a single workqueue thread + * on a single CPU. + */ + unsigned int executed; +}; + +/* List of workqueue threads on one cpu */ +struct workqueue_global_stats { + struct list_head list; + spinlock_t lock; +}; + +/* Don't need a global lock because allocated before the workqueues, and + * never freed. + */ +static DEFINE_PER_CPU(struct workqueue_global_stats, all_workqueue_stat); +#define workqueue_cpu_stat(cpu) (&per_cpu(all_workqueue_stat, cpu)) + +/* Insertion of a work */ +static void +probe_workqueue_insertion(struct task_struct *wq_thread, + struct work_struct *work) +{ + int cpu = cpumask_first(&wq_thread->cpus_allowed); + struct cpu_workqueue_stats *node, *next; + unsigned long flags; + + spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags); + list_for_each_entry_safe(node, next, &workqueue_cpu_stat(cpu)->list, + list) { + if (node->pid == wq_thread->pid) { + atomic_inc(&node->inserted); + goto found; + } + } + pr_debug("trace_workqueue: entry not found\n"); +found: + spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags); +} + +/* Execution of a work */ +static void +probe_workqueue_execution(struct task_struct *wq_thread, + struct work_struct *work) +{ + int cpu = cpumask_first(&wq_thread->cpus_allowed); + struct cpu_workqueue_stats *node, *next; + unsigned long flags; + + spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags); + list_for_each_entry_safe(node, next, &workqueue_cpu_stat(cpu)->list, + list) { + if (node->pid == wq_thread->pid) { + node->executed++; + goto found; + } + } + pr_debug("trace_workqueue: entry not found\n"); +found: + spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags); +} + +/* Creation of a cpu workqueue thread */ +static void probe_workqueue_creation(struct task_struct *wq_thread, int cpu) +{ + struct cpu_workqueue_stats *cws; + unsigned long flags; + + WARN_ON(cpu < 0); + + /* Workqueues are sometimes created in atomic context */ + cws = kzalloc(sizeof(struct cpu_workqueue_stats), GFP_ATOMIC); + if (!cws) { + pr_warning("trace_workqueue: not enough memory\n"); + return; + } + INIT_LIST_HEAD(&cws->list); + cws->cpu = cpu; + + cws->pid = wq_thread->pid; + + spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags); + if (list_empty(&workqueue_cpu_stat(cpu)->list)) + cws->first_entry = true; + list_add_tail(&cws->list, &workqueue_cpu_stat(cpu)->list); + spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags); +} + +/* Destruction of a cpu workqueue thread */ +static void probe_workqueue_destruction(struct task_struct *wq_thread) +{ + /* Workqueue only execute on one cpu */ + int cpu = cpumask_first(&wq_thread->cpus_allowed); + struct cpu_workqueue_stats *node, *next; + unsigned long flags; + + spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags); + list_for_each_entry_safe(node, next, &workqueue_cpu_stat(cpu)->list, + list) { + if (node->pid == wq_thread->pid) { + list_del(&node->list); + kfree(node); + goto found; + } + } + + pr_debug("trace_workqueue: don't find workqueue to destroy\n"); +found: + spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags); + +} + +static struct cpu_workqueue_stats *workqueue_stat_start_cpu(int cpu) +{ + unsigned long flags; + struct cpu_workqueue_stats *ret = NULL; + + + spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags); + + if (!list_empty(&workqueue_cpu_stat(cpu)->list)) + ret = list_entry(workqueue_cpu_stat(cpu)->list.next, + struct cpu_workqueue_stats, list); + + spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags); + + return ret; +} + +static void *workqueue_stat_start(void) +{ + int cpu; + void *ret = NULL; + + for_each_possible_cpu(cpu) { + ret = workqueue_stat_start_cpu(cpu); + if (ret) + return ret; + } + return NULL; +} + +static void *workqueue_stat_next(void *prev, int idx) +{ + struct cpu_workqueue_stats *prev_cws = prev; + int cpu = prev_cws->cpu; + unsigned long flags; + void *ret = NULL; + + spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags); + if (list_is_last(&prev_cws->list, &workqueue_cpu_stat(cpu)->list)) { + spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags); + do { + cpu = cpumask_next(cpu, cpu_possible_mask); + if (cpu >= nr_cpu_ids) + return NULL; + } while (!(ret = workqueue_stat_start_cpu(cpu))); + return ret; + } + spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags); + + return list_entry(prev_cws->list.next, struct cpu_workqueue_stats, + list); +} + +static int workqueue_stat_show(struct seq_file *s, void *p) +{ + struct cpu_workqueue_stats *cws = p; + unsigned long flags; + int cpu = cws->cpu; + struct pid *pid; + struct task_struct *tsk; + + spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags); + if (&cws->list == workqueue_cpu_stat(cpu)->list.next) + seq_printf(s, "\n"); + spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags); + + pid = find_get_pid(cws->pid); + if (pid) { + tsk = get_pid_task(pid, PIDTYPE_PID); + if (tsk) { + seq_printf(s, "%3d %6d %6u %s\n", cws->cpu, + atomic_read(&cws->inserted), cws->executed, + tsk->comm); + put_task_struct(tsk); + } + put_pid(pid); + } + + return 0; +} + +static int workqueue_stat_headers(struct seq_file *s) +{ + seq_printf(s, "# CPU INSERTED EXECUTED NAME\n"); + seq_printf(s, "# | | | |\n"); + return 0; +} + +struct tracer_stat workqueue_stats __read_mostly = { + .name = "workqueues", + .stat_start = workqueue_stat_start, + .stat_next = workqueue_stat_next, + .stat_show = workqueue_stat_show, + .stat_headers = workqueue_stat_headers +}; + + +int __init stat_workqueue_init(void) +{ + if (register_stat_tracer(&workqueue_stats)) { + pr_warning("Unable to register workqueue stat tracer\n"); + return 1; + } + + return 0; +} +fs_initcall(stat_workqueue_init); + +/* + * Workqueues are created very early, just after pre-smp initcalls. + * So we must register our tracepoints at this stage. + */ +int __init trace_workqueue_early_init(void) +{ + int ret, cpu; + + ret = register_trace_workqueue_insertion(probe_workqueue_insertion); + if (ret) + goto out; + + ret = register_trace_workqueue_execution(probe_workqueue_execution); + if (ret) + goto no_insertion; + + ret = register_trace_workqueue_creation(probe_workqueue_creation); + if (ret) + goto no_execution; + + ret = register_trace_workqueue_destruction(probe_workqueue_destruction); + if (ret) + goto no_creation; + + for_each_possible_cpu(cpu) { + spin_lock_init(&workqueue_cpu_stat(cpu)->lock); + INIT_LIST_HEAD(&workqueue_cpu_stat(cpu)->list); + } + + return 0; + +no_creation: + unregister_trace_workqueue_creation(probe_workqueue_creation); +no_execution: + unregister_trace_workqueue_execution(probe_workqueue_execution); +no_insertion: + unregister_trace_workqueue_insertion(probe_workqueue_insertion); +out: + pr_warning("trace_workqueue: unable to trace workqueues\n"); + + return 1; +} +early_initcall(trace_workqueue_early_init); diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index 79602740bbb5..1ef5d3a601c7 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -272,12 +272,15 @@ static void disable_tracepoint(struct tracepoint *elem) * * Updates the probe callback corresponding to a range of tracepoints. */ -void tracepoint_update_probe_range(struct tracepoint *begin, - struct tracepoint *end) +void +tracepoint_update_probe_range(struct tracepoint *begin, struct tracepoint *end) { struct tracepoint *iter; struct tracepoint_entry *mark_entry; + if (!begin) + return; + mutex_lock(&tracepoints_mutex); for (iter = begin; iter < end; iter++) { mark_entry = get_tracepoint(iter->name); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 32f8e0d2bf5a..b6b966ce1451 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -33,6 +33,7 @@ #include <linux/kallsyms.h> #include <linux/debug_locks.h> #include <linux/lockdep.h> +#include <trace/workqueue.h> /* * The per-CPU workqueue (if single thread, we always use the first @@ -123,9 +124,13 @@ struct cpu_workqueue_struct *get_wq_data(struct work_struct *work) return (void *) (atomic_long_read(&work->data) & WORK_STRUCT_WQ_DATA_MASK); } +DEFINE_TRACE(workqueue_insertion); + static void insert_work(struct cpu_workqueue_struct *cwq, struct work_struct *work, struct list_head *head) { + trace_workqueue_insertion(cwq->thread, work); + set_wq_data(work, cwq); /* * Ensure that we get the right work->data if we see the @@ -257,6 +262,8 @@ int queue_delayed_work_on(int cpu, struct workqueue_struct *wq, } EXPORT_SYMBOL_GPL(queue_delayed_work_on); +DEFINE_TRACE(workqueue_execution); + static void run_workqueue(struct cpu_workqueue_struct *cwq) { spin_lock_irq(&cwq->lock); @@ -275,7 +282,7 @@ static void run_workqueue(struct cpu_workqueue_struct *cwq) */ struct lockdep_map lockdep_map = work->lockdep_map; #endif - + trace_workqueue_execution(cwq->thread, work); cwq->current_work = work; list_del_init(cwq->worklist.next); spin_unlock_irq(&cwq->lock); @@ -746,6 +753,8 @@ init_cpu_workqueue(struct workqueue_struct *wq, int cpu) return cwq; } +DEFINE_TRACE(workqueue_creation); + static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu) { struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; @@ -768,6 +777,8 @@ static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu) sched_setscheduler_nocheck(p, SCHED_FIFO, ¶m); cwq->thread = p; + trace_workqueue_creation(cwq->thread, cpu); + return 0; } @@ -849,6 +860,8 @@ struct workqueue_struct *__create_workqueue_key(const char *name, } EXPORT_SYMBOL_GPL(__create_workqueue_key); +DEFINE_TRACE(workqueue_destruction); + static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq) { /* @@ -872,6 +885,7 @@ static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq) * checks list_empty(), and a "normal" queue_work() can't use * a dead CPU. */ + trace_workqueue_destruction(cwq->thread); kthread_stop(cwq->thread); cwq->thread = NULL; } diff --git a/lib/Kconfig b/lib/Kconfig index 2a9c69f34482..8ade0a7a91e0 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -2,6 +2,9 @@ # Library configuration # +config BINARY_PRINTF + def_bool n + menu "Library routines" config BITREVERSE diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 5d99be1fd988..2755a3bd16a1 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -30,7 +30,7 @@ struct debug_bucket { static struct debug_bucket obj_hash[ODEBUG_HASH_SIZE]; -static struct debug_obj obj_static_pool[ODEBUG_POOL_SIZE]; +static struct debug_obj obj_static_pool[ODEBUG_POOL_SIZE] __initdata; static DEFINE_SPINLOCK(pool_lock); @@ -50,12 +50,23 @@ static int debug_objects_enabled __read_mostly static struct debug_obj_descr *descr_test __read_mostly; +static void free_obj_work(struct work_struct *work); +static DECLARE_WORK(debug_obj_work, free_obj_work); + static int __init enable_object_debug(char *str) { debug_objects_enabled = 1; return 0; } + +static int __init disable_object_debug(char *str) +{ + debug_objects_enabled = 0; + return 0; +} + early_param("debug_objects", enable_object_debug); +early_param("no_debug_objects", disable_object_debug); static const char *obj_states[ODEBUG_STATE_MAX] = { [ODEBUG_STATE_NONE] = "none", @@ -146,25 +157,51 @@ alloc_object(void *addr, struct debug_bucket *b, struct debug_obj_descr *descr) } /* - * Put the object back into the pool or give it back to kmem_cache: + * workqueue function to free objects. */ -static void free_object(struct debug_obj *obj) +static void free_obj_work(struct work_struct *work) { - unsigned long idx = (unsigned long)(obj - obj_static_pool); + struct debug_obj *obj; unsigned long flags; - if (obj_pool_free < ODEBUG_POOL_SIZE || idx < ODEBUG_POOL_SIZE) { - spin_lock_irqsave(&pool_lock, flags); - hlist_add_head(&obj->node, &obj_pool); - obj_pool_free++; - obj_pool_used--; - spin_unlock_irqrestore(&pool_lock, flags); - } else { - spin_lock_irqsave(&pool_lock, flags); - obj_pool_used--; + spin_lock_irqsave(&pool_lock, flags); + while (obj_pool_free > ODEBUG_POOL_SIZE) { + obj = hlist_entry(obj_pool.first, typeof(*obj), node); + hlist_del(&obj->node); + obj_pool_free--; + /* + * We release pool_lock across kmem_cache_free() to + * avoid contention on pool_lock. + */ spin_unlock_irqrestore(&pool_lock, flags); kmem_cache_free(obj_cache, obj); + spin_lock_irqsave(&pool_lock, flags); } + spin_unlock_irqrestore(&pool_lock, flags); +} + +/* + * Put the object back into the pool and schedule work to free objects + * if necessary. + */ +static void free_object(struct debug_obj *obj) +{ + unsigned long flags; + int sched = 0; + + spin_lock_irqsave(&pool_lock, flags); + /* + * schedule work when the pool is filled and the cache is + * initialized: + */ + if (obj_pool_free > ODEBUG_POOL_SIZE && obj_cache) + sched = !work_pending(&debug_obj_work); + hlist_add_head(&obj->node, &obj_pool); + obj_pool_free++; + obj_pool_used--; + spin_unlock_irqrestore(&pool_lock, flags); + if (sched) + schedule_work(&debug_obj_work); } /* @@ -876,6 +913,63 @@ void __init debug_objects_early_init(void) } /* + * Convert the statically allocated objects to dynamic ones: + */ +static int debug_objects_replace_static_objects(void) +{ + struct debug_bucket *db = obj_hash; + struct hlist_node *node, *tmp; + struct debug_obj *obj, *new; + HLIST_HEAD(objects); + int i, cnt = 0; + + for (i = 0; i < ODEBUG_POOL_SIZE; i++) { + obj = kmem_cache_zalloc(obj_cache, GFP_KERNEL); + if (!obj) + goto free; + hlist_add_head(&obj->node, &objects); + } + + /* + * When debug_objects_mem_init() is called we know that only + * one CPU is up, so disabling interrupts is enough + * protection. This avoids the lockdep hell of lock ordering. + */ + local_irq_disable(); + + /* Remove the statically allocated objects from the pool */ + hlist_for_each_entry_safe(obj, node, tmp, &obj_pool, node) + hlist_del(&obj->node); + /* Move the allocated objects to the pool */ + hlist_move_list(&objects, &obj_pool); + + /* Replace the active object references */ + for (i = 0; i < ODEBUG_HASH_SIZE; i++, db++) { + hlist_move_list(&db->list, &objects); + + hlist_for_each_entry(obj, node, &objects, node) { + new = hlist_entry(obj_pool.first, typeof(*obj), node); + hlist_del(&new->node); + /* copy object data */ + *new = *obj; + hlist_add_head(&new->node, &db->list); + cnt++; + } + } + + printk(KERN_DEBUG "ODEBUG: %d of %d active objects replaced\n", cnt, + obj_pool_used); + local_irq_enable(); + return 0; +free: + hlist_for_each_entry_safe(obj, node, tmp, &objects, node) { + hlist_del(&obj->node); + kmem_cache_free(obj_cache, obj); + } + return -ENOMEM; +} + +/* * Called after the kmem_caches are functional to setup a dedicated * cache pool, which has the SLAB_DEBUG_OBJECTS flag set. This flag * prevents that the debug code is called on kmem_cache_free() for the @@ -890,8 +984,11 @@ void __init debug_objects_mem_init(void) sizeof (struct debug_obj), 0, SLAB_DEBUG_OBJECTS, NULL); - if (!obj_cache) + if (!obj_cache || debug_objects_replace_static_objects()) { debug_objects_enabled = 0; - else + if (obj_cache) + kmem_cache_destroy(obj_cache); + printk(KERN_WARNING "ODEBUG: out of memory.\n"); + } else debug_objects_selftest(); } diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c index 280332c1827c..619313ed6c46 100644 --- a/lib/locking-selftest.c +++ b/lib/locking-selftest.c @@ -157,11 +157,11 @@ static void init_shared_classes(void) #define SOFTIRQ_ENTER() \ local_bh_disable(); \ local_irq_disable(); \ - trace_softirq_enter(); \ + lockdep_softirq_enter(); \ WARN_ON(!in_softirq()); #define SOFTIRQ_EXIT() \ - trace_softirq_exit(); \ + lockdep_softirq_exit(); \ local_irq_enable(); \ local_bh_enable(); diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 0fbd0121d91d..be3001f912e4 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -396,7 +396,38 @@ static noinline char* put_dec(char *buf, unsigned long long num) #define SMALL 32 /* Must be 32 == 0x20 */ #define SPECIAL 64 /* 0x */ -static char *number(char *buf, char *end, unsigned long long num, int base, int size, int precision, int type) +enum format_type { + FORMAT_TYPE_NONE, /* Just a string part */ + FORMAT_TYPE_WIDTH, + FORMAT_TYPE_PRECISION, + FORMAT_TYPE_CHAR, + FORMAT_TYPE_STR, + FORMAT_TYPE_PTR, + FORMAT_TYPE_PERCENT_CHAR, + FORMAT_TYPE_INVALID, + FORMAT_TYPE_LONG_LONG, + FORMAT_TYPE_ULONG, + FORMAT_TYPE_LONG, + FORMAT_TYPE_USHORT, + FORMAT_TYPE_SHORT, + FORMAT_TYPE_UINT, + FORMAT_TYPE_INT, + FORMAT_TYPE_NRCHARS, + FORMAT_TYPE_SIZE_T, + FORMAT_TYPE_PTRDIFF +}; + +struct printf_spec { + enum format_type type; + int flags; /* flags to number() */ + int field_width; /* width of output field */ + int base; + int precision; /* # of digits/chars */ + int qualifier; +}; + +static char *number(char *buf, char *end, unsigned long long num, + struct printf_spec spec) { /* we are called with base 8, 10 or 16, only, thus don't need "G..." */ static const char digits[16] = "0123456789ABCDEF"; /* "GHIJKLMNOPQRSTUVWXYZ"; */ @@ -404,32 +435,32 @@ static char *number(char *buf, char *end, unsigned long long num, int base, int char tmp[66]; char sign; char locase; - int need_pfx = ((type & SPECIAL) && base != 10); + int need_pfx = ((spec.flags & SPECIAL) && spec.base != 10); int i; /* locase = 0 or 0x20. ORing digits or letters with 'locase' * produces same digits or (maybe lowercased) letters */ - locase = (type & SMALL); - if (type & LEFT) - type &= ~ZEROPAD; + locase = (spec.flags & SMALL); + if (spec.flags & LEFT) + spec.flags &= ~ZEROPAD; sign = 0; - if (type & SIGN) { + if (spec.flags & SIGN) { if ((signed long long) num < 0) { sign = '-'; num = - (signed long long) num; - size--; - } else if (type & PLUS) { + spec.field_width--; + } else if (spec.flags & PLUS) { sign = '+'; - size--; - } else if (type & SPACE) { + spec.field_width--; + } else if (spec.flags & SPACE) { sign = ' '; - size--; + spec.field_width--; } } if (need_pfx) { - size--; - if (base == 16) - size--; + spec.field_width--; + if (spec.base == 16) + spec.field_width--; } /* generate full string in tmp[], in reverse order */ @@ -441,10 +472,10 @@ static char *number(char *buf, char *end, unsigned long long num, int base, int tmp[i++] = (digits[do_div(num,base)] | locase); } while (num != 0); */ - else if (base != 10) { /* 8 or 16 */ - int mask = base - 1; + else if (spec.base != 10) { /* 8 or 16 */ + int mask = spec.base - 1; int shift = 3; - if (base == 16) shift = 4; + if (spec.base == 16) shift = 4; do { tmp[i++] = (digits[((unsigned char)num) & mask] | locase); num >>= shift; @@ -454,12 +485,12 @@ static char *number(char *buf, char *end, unsigned long long num, int base, int } /* printing 100 using %2d gives "100", not "00" */ - if (i > precision) - precision = i; + if (i > spec.precision) + spec.precision = i; /* leading space padding */ - size -= precision; - if (!(type & (ZEROPAD+LEFT))) { - while(--size >= 0) { + spec.field_width -= spec.precision; + if (!(spec.flags & (ZEROPAD+LEFT))) { + while(--spec.field_width >= 0) { if (buf < end) *buf = ' '; ++buf; @@ -476,23 +507,23 @@ static char *number(char *buf, char *end, unsigned long long num, int base, int if (buf < end) *buf = '0'; ++buf; - if (base == 16) { + if (spec.base == 16) { if (buf < end) *buf = ('X' | locase); ++buf; } } /* zero or space padding */ - if (!(type & LEFT)) { - char c = (type & ZEROPAD) ? '0' : ' '; - while (--size >= 0) { + if (!(spec.flags & LEFT)) { + char c = (spec.flags & ZEROPAD) ? '0' : ' '; + while (--spec.field_width >= 0) { if (buf < end) *buf = c; ++buf; } } /* hmm even more zero padding? */ - while (i <= --precision) { + while (i <= --spec.precision) { if (buf < end) *buf = '0'; ++buf; @@ -504,7 +535,7 @@ static char *number(char *buf, char *end, unsigned long long num, int base, int ++buf; } /* trailing space padding */ - while (--size >= 0) { + while (--spec.field_width >= 0) { if (buf < end) *buf = ' '; ++buf; @@ -512,17 +543,17 @@ static char *number(char *buf, char *end, unsigned long long num, int base, int return buf; } -static char *string(char *buf, char *end, char *s, int field_width, int precision, int flags) +static char *string(char *buf, char *end, char *s, struct printf_spec spec) { int len, i; if ((unsigned long)s < PAGE_SIZE) s = "<NULL>"; - len = strnlen(s, precision); + len = strnlen(s, spec.precision); - if (!(flags & LEFT)) { - while (len < field_width--) { + if (!(spec.flags & LEFT)) { + while (len < spec.field_width--) { if (buf < end) *buf = ' '; ++buf; @@ -533,7 +564,7 @@ static char *string(char *buf, char *end, char *s, int field_width, int precisio *buf = *s; ++buf; ++s; } - while (len < field_width--) { + while (len < spec.field_width--) { if (buf < end) *buf = ' '; ++buf; @@ -541,21 +572,24 @@ static char *string(char *buf, char *end, char *s, int field_width, int precisio return buf; } -static char *symbol_string(char *buf, char *end, void *ptr, int field_width, int precision, int flags) +static char *symbol_string(char *buf, char *end, void *ptr, + struct printf_spec spec) { unsigned long value = (unsigned long) ptr; #ifdef CONFIG_KALLSYMS char sym[KSYM_SYMBOL_LEN]; sprint_symbol(sym, value); - return string(buf, end, sym, field_width, precision, flags); + return string(buf, end, sym, spec); #else - field_width = 2*sizeof(void *); - flags |= SPECIAL | SMALL | ZEROPAD; - return number(buf, end, value, 16, field_width, precision, flags); + spec.field_width = 2*sizeof(void *); + spec.flags |= SPECIAL | SMALL | ZEROPAD; + spec.base = 16; + return number(buf, end, value, spec); #endif } -static char *resource_string(char *buf, char *end, struct resource *res, int field_width, int precision, int flags) +static char *resource_string(char *buf, char *end, struct resource *res, + struct printf_spec spec) { #ifndef IO_RSRC_PRINTK_SIZE #define IO_RSRC_PRINTK_SIZE 4 @@ -564,7 +598,11 @@ static char *resource_string(char *buf, char *end, struct resource *res, int fie #ifndef MEM_RSRC_PRINTK_SIZE #define MEM_RSRC_PRINTK_SIZE 8 #endif - + struct printf_spec num_spec = { + .base = 16, + .precision = -1, + .flags = SPECIAL | SMALL | ZEROPAD, + }; /* room for the actual numbers, the two "0x", -, [, ] and the final zero */ char sym[4*sizeof(resource_size_t) + 8]; char *p = sym, *pend = sym + sizeof(sym); @@ -576,17 +614,18 @@ static char *resource_string(char *buf, char *end, struct resource *res, int fie size = MEM_RSRC_PRINTK_SIZE; *p++ = '['; - p = number(p, pend, res->start, 16, size, -1, SPECIAL | SMALL | ZEROPAD); + num_spec.field_width = size; + p = number(p, pend, res->start, num_spec); *p++ = '-'; - p = number(p, pend, res->end, 16, size, -1, SPECIAL | SMALL | ZEROPAD); + p = number(p, pend, res->end, num_spec); *p++ = ']'; *p = 0; - return string(buf, end, sym, field_width, precision, flags); + return string(buf, end, sym, spec); } -static char *mac_address_string(char *buf, char *end, u8 *addr, int field_width, - int precision, int flags) +static char *mac_address_string(char *buf, char *end, u8 *addr, + struct printf_spec spec) { char mac_addr[6 * 3]; /* (6 * 2 hex digits), 5 colons and trailing zero */ char *p = mac_addr; @@ -594,16 +633,17 @@ static char *mac_address_string(char *buf, char *end, u8 *addr, int field_width, for (i = 0; i < 6; i++) { p = pack_hex_byte(p, addr[i]); - if (!(flags & SPECIAL) && i != 5) + if (!(spec.flags & SPECIAL) && i != 5) *p++ = ':'; } *p = '\0'; + spec.flags &= ~SPECIAL; - return string(buf, end, mac_addr, field_width, precision, flags & ~SPECIAL); + return string(buf, end, mac_addr, spec); } -static char *ip6_addr_string(char *buf, char *end, u8 *addr, int field_width, - int precision, int flags) +static char *ip6_addr_string(char *buf, char *end, u8 *addr, + struct printf_spec spec) { char ip6_addr[8 * 5]; /* (8 * 4 hex digits), 7 colons and trailing zero */ char *p = ip6_addr; @@ -612,16 +652,17 @@ static char *ip6_addr_string(char *buf, char *end, u8 *addr, int field_width, for (i = 0; i < 8; i++) { p = pack_hex_byte(p, addr[2 * i]); p = pack_hex_byte(p, addr[2 * i + 1]); - if (!(flags & SPECIAL) && i != 7) + if (!(spec.flags & SPECIAL) && i != 7) *p++ = ':'; } *p = '\0'; + spec.flags &= ~SPECIAL; - return string(buf, end, ip6_addr, field_width, precision, flags & ~SPECIAL); + return string(buf, end, ip6_addr, spec); } -static char *ip4_addr_string(char *buf, char *end, u8 *addr, int field_width, - int precision, int flags) +static char *ip4_addr_string(char *buf, char *end, u8 *addr, + struct printf_spec spec) { char ip4_addr[4 * 4]; /* (4 * 3 decimal digits), 3 dots and trailing zero */ char temp[3]; /* hold each IP quad in reverse order */ @@ -637,8 +678,9 @@ static char *ip4_addr_string(char *buf, char *end, u8 *addr, int field_width, *p++ = '.'; } *p = '\0'; + spec.flags &= ~SPECIAL; - return string(buf, end, ip4_addr, field_width, precision, flags & ~SPECIAL); + return string(buf, end, ip4_addr, spec); } /* @@ -663,41 +705,233 @@ static char *ip4_addr_string(char *buf, char *end, u8 *addr, int field_width, * function pointers are really function descriptors, which contain a * pointer to the real address. */ -static char *pointer(const char *fmt, char *buf, char *end, void *ptr, int field_width, int precision, int flags) +static char *pointer(const char *fmt, char *buf, char *end, void *ptr, + struct printf_spec spec) { if (!ptr) - return string(buf, end, "(null)", field_width, precision, flags); + return string(buf, end, "(null)", spec); switch (*fmt) { case 'F': ptr = dereference_function_descriptor(ptr); /* Fallthrough */ case 'S': - return symbol_string(buf, end, ptr, field_width, precision, flags); + return symbol_string(buf, end, ptr, spec); case 'R': - return resource_string(buf, end, ptr, field_width, precision, flags); + return resource_string(buf, end, ptr, spec); case 'm': - flags |= SPECIAL; + spec.flags |= SPECIAL; /* Fallthrough */ case 'M': - return mac_address_string(buf, end, ptr, field_width, precision, flags); + return mac_address_string(buf, end, ptr, spec); case 'i': - flags |= SPECIAL; + spec.flags |= SPECIAL; /* Fallthrough */ case 'I': if (fmt[1] == '6') - return ip6_addr_string(buf, end, ptr, field_width, precision, flags); + return ip6_addr_string(buf, end, ptr, spec); if (fmt[1] == '4') - return ip4_addr_string(buf, end, ptr, field_width, precision, flags); - flags &= ~SPECIAL; + return ip4_addr_string(buf, end, ptr, spec); + spec.flags &= ~SPECIAL; + break; + } + spec.flags |= SMALL; + if (spec.field_width == -1) { + spec.field_width = 2*sizeof(void *); + spec.flags |= ZEROPAD; + } + spec.base = 16; + + return number(buf, end, (unsigned long) ptr, spec); +} + +/* + * Helper function to decode printf style format. + * Each call decode a token from the format and return the + * number of characters read (or likely the delta where it wants + * to go on the next call). + * The decoded token is returned through the parameters + * + * 'h', 'l', or 'L' for integer fields + * 'z' support added 23/7/1999 S.H. + * 'z' changed to 'Z' --davidm 1/25/99 + * 't' added for ptrdiff_t + * + * @fmt: the format string + * @type of the token returned + * @flags: various flags such as +, -, # tokens.. + * @field_width: overwritten width + * @base: base of the number (octal, hex, ...) + * @precision: precision of a number + * @qualifier: qualifier of a number (long, size_t, ...) + */ +static int format_decode(const char *fmt, struct printf_spec *spec) +{ + const char *start = fmt; + + /* we finished early by reading the field width */ + if (spec->type == FORMAT_TYPE_WIDTH) { + if (spec->field_width < 0) { + spec->field_width = -spec->field_width; + spec->flags |= LEFT; + } + spec->type = FORMAT_TYPE_NONE; + goto precision; + } + + /* we finished early by reading the precision */ + if (spec->type == FORMAT_TYPE_PRECISION) { + if (spec->precision < 0) + spec->precision = 0; + + spec->type = FORMAT_TYPE_NONE; + goto qualifier; + } + + /* By default */ + spec->type = FORMAT_TYPE_NONE; + + for (; *fmt ; ++fmt) { + if (*fmt == '%') + break; + } + + /* Return the current non-format string */ + if (fmt != start || !*fmt) + return fmt - start; + + /* Process flags */ + spec->flags = 0; + + while (1) { /* this also skips first '%' */ + bool found = true; + + ++fmt; + + switch (*fmt) { + case '-': spec->flags |= LEFT; break; + case '+': spec->flags |= PLUS; break; + case ' ': spec->flags |= SPACE; break; + case '#': spec->flags |= SPECIAL; break; + case '0': spec->flags |= ZEROPAD; break; + default: found = false; + } + + if (!found) + break; + } + + /* get field width */ + spec->field_width = -1; + + if (isdigit(*fmt)) + spec->field_width = skip_atoi(&fmt); + else if (*fmt == '*') { + /* it's the next argument */ + spec->type = FORMAT_TYPE_WIDTH; + return ++fmt - start; + } + +precision: + /* get the precision */ + spec->precision = -1; + if (*fmt == '.') { + ++fmt; + if (isdigit(*fmt)) { + spec->precision = skip_atoi(&fmt); + if (spec->precision < 0) + spec->precision = 0; + } else if (*fmt == '*') { + /* it's the next argument */ + spec->type = FORMAT_TYPE_PRECISION; + return ++fmt - start; + } + } + +qualifier: + /* get the conversion qualifier */ + spec->qualifier = -1; + if (*fmt == 'h' || *fmt == 'l' || *fmt == 'L' || + *fmt == 'Z' || *fmt == 'z' || *fmt == 't') { + spec->qualifier = *fmt; + ++fmt; + if (spec->qualifier == 'l' && *fmt == 'l') { + spec->qualifier = 'L'; + ++fmt; + } + } + + /* default base */ + spec->base = 10; + switch (*fmt) { + case 'c': + spec->type = FORMAT_TYPE_CHAR; + return ++fmt - start; + + case 's': + spec->type = FORMAT_TYPE_STR; + return ++fmt - start; + + case 'p': + spec->type = FORMAT_TYPE_PTR; + return fmt - start; + /* skip alnum */ + + case 'n': + spec->type = FORMAT_TYPE_NRCHARS; + return ++fmt - start; + + case '%': + spec->type = FORMAT_TYPE_PERCENT_CHAR; + return ++fmt - start; + + /* integer number formats - set up the flags and "break" */ + case 'o': + spec->base = 8; break; + + case 'x': + spec->flags |= SMALL; + + case 'X': + spec->base = 16; + break; + + case 'd': + case 'i': + spec->flags |= SIGN; + case 'u': + break; + + default: + spec->type = FORMAT_TYPE_INVALID; + return fmt - start; } - flags |= SMALL; - if (field_width == -1) { - field_width = 2*sizeof(void *); - flags |= ZEROPAD; + + if (spec->qualifier == 'L') + spec->type = FORMAT_TYPE_LONG_LONG; + else if (spec->qualifier == 'l') { + if (spec->flags & SIGN) + spec->type = FORMAT_TYPE_LONG; + else + spec->type = FORMAT_TYPE_ULONG; + } else if (spec->qualifier == 'Z' || spec->qualifier == 'z') { + spec->type = FORMAT_TYPE_SIZE_T; + } else if (spec->qualifier == 't') { + spec->type = FORMAT_TYPE_PTRDIFF; + } else if (spec->qualifier == 'h') { + if (spec->flags & SIGN) + spec->type = FORMAT_TYPE_SHORT; + else + spec->type = FORMAT_TYPE_USHORT; + } else { + if (spec->flags & SIGN) + spec->type = FORMAT_TYPE_INT; + else + spec->type = FORMAT_TYPE_UINT; } - return number(buf, end, (unsigned long) ptr, 16, field_width, precision, flags); + + return ++fmt - start; } /** @@ -726,18 +960,9 @@ static char *pointer(const char *fmt, char *buf, char *end, void *ptr, int field int vsnprintf(char *buf, size_t size, const char *fmt, va_list args) { unsigned long long num; - int base; char *str, *end, c; - - int flags; /* flags to number() */ - - int field_width; /* width of output field */ - int precision; /* min. # of digits for integers; max - number of chars for from string */ - int qualifier; /* 'h', 'l', or 'L' for integer fields */ - /* 'z' support added 23/7/1999 S.H. */ - /* 'z' changed to 'Z' --davidm 1/25/99 */ - /* 't' added for ptrdiff_t */ + int read; + struct printf_spec spec = {0}; /* Reject out-of-range values early. Large positive sizes are used for unknown buffer sizes. */ @@ -758,184 +983,144 @@ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args) size = end - buf; } - for (; *fmt ; ++fmt) { - if (*fmt != '%') { - if (str < end) - *str = *fmt; - ++str; - continue; - } + while (*fmt) { + const char *old_fmt = fmt; - /* process flags */ - flags = 0; - repeat: - ++fmt; /* this also skips first '%' */ - switch (*fmt) { - case '-': flags |= LEFT; goto repeat; - case '+': flags |= PLUS; goto repeat; - case ' ': flags |= SPACE; goto repeat; - case '#': flags |= SPECIAL; goto repeat; - case '0': flags |= ZEROPAD; goto repeat; - } + read = format_decode(fmt, &spec); - /* get field width */ - field_width = -1; - if (isdigit(*fmt)) - field_width = skip_atoi(&fmt); - else if (*fmt == '*') { - ++fmt; - /* it's the next argument */ - field_width = va_arg(args, int); - if (field_width < 0) { - field_width = -field_width; - flags |= LEFT; - } - } + fmt += read; - /* get the precision */ - precision = -1; - if (*fmt == '.') { - ++fmt; - if (isdigit(*fmt)) - precision = skip_atoi(&fmt); - else if (*fmt == '*') { - ++fmt; - /* it's the next argument */ - precision = va_arg(args, int); + switch (spec.type) { + case FORMAT_TYPE_NONE: { + int copy = read; + if (str < end) { + if (copy > end - str) + copy = end - str; + memcpy(str, old_fmt, copy); } - if (precision < 0) - precision = 0; + str += read; + break; } - /* get the conversion qualifier */ - qualifier = -1; - if (*fmt == 'h' || *fmt == 'l' || *fmt == 'L' || - *fmt =='Z' || *fmt == 'z' || *fmt == 't') { - qualifier = *fmt; - ++fmt; - if (qualifier == 'l' && *fmt == 'l') { - qualifier = 'L'; - ++fmt; - } - } + case FORMAT_TYPE_WIDTH: + spec.field_width = va_arg(args, int); + break; - /* default base */ - base = 10; + case FORMAT_TYPE_PRECISION: + spec.precision = va_arg(args, int); + break; - switch (*fmt) { - case 'c': - if (!(flags & LEFT)) { - while (--field_width > 0) { - if (str < end) - *str = ' '; - ++str; - } - } - c = (unsigned char) va_arg(args, int); - if (str < end) - *str = c; - ++str; - while (--field_width > 0) { + case FORMAT_TYPE_CHAR: + if (!(spec.flags & LEFT)) { + while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; - } - continue; - - case 's': - str = string(str, end, va_arg(args, char *), field_width, precision, flags); - continue; - - case 'p': - str = pointer(fmt+1, str, end, - va_arg(args, void *), - field_width, precision, flags); - /* Skip all alphanumeric pointer suffixes */ - while (isalnum(fmt[1])) - fmt++; - continue; - - case 'n': - /* FIXME: - * What does C99 say about the overflow case here? */ - if (qualifier == 'l') { - long * ip = va_arg(args, long *); - *ip = (str - buf); - } else if (qualifier == 'Z' || qualifier == 'z') { - size_t * ip = va_arg(args, size_t *); - *ip = (str - buf); - } else { - int * ip = va_arg(args, int *); - *ip = (str - buf); - } - continue; - case '%': + } + } + c = (unsigned char) va_arg(args, int); + if (str < end) + *str = c; + ++str; + while (--spec.field_width > 0) { if (str < end) - *str = '%'; + *str = ' '; ++str; - continue; + } + break; - /* integer number formats - set up the flags and "break" */ - case 'o': - base = 8; - break; + case FORMAT_TYPE_STR: + str = string(str, end, va_arg(args, char *), spec); + break; - case 'x': - flags |= SMALL; - case 'X': - base = 16; - break; + case FORMAT_TYPE_PTR: + str = pointer(fmt+1, str, end, va_arg(args, void *), + spec); + while (isalnum(*fmt)) + fmt++; + break; - case 'd': - case 'i': - flags |= SIGN; - case 'u': - break; + case FORMAT_TYPE_PERCENT_CHAR: + if (str < end) + *str = '%'; + ++str; + break; - default: + case FORMAT_TYPE_INVALID: + if (str < end) + *str = '%'; + ++str; + if (*fmt) { if (str < end) - *str = '%'; + *str = *fmt; ++str; - if (*fmt) { - if (str < end) - *str = *fmt; - ++str; - } else { - --fmt; - } - continue; + } else { + --fmt; + } + break; + + case FORMAT_TYPE_NRCHARS: { + int qualifier = spec.qualifier; + + if (qualifier == 'l') { + long *ip = va_arg(args, long *); + *ip = (str - buf); + } else if (qualifier == 'Z' || + qualifier == 'z') { + size_t *ip = va_arg(args, size_t *); + *ip = (str - buf); + } else { + int *ip = va_arg(args, int *); + *ip = (str - buf); + } + break; } - if (qualifier == 'L') - num = va_arg(args, long long); - else if (qualifier == 'l') { - num = va_arg(args, unsigned long); - if (flags & SIGN) - num = (signed long) num; - } else if (qualifier == 'Z' || qualifier == 'z') { - num = va_arg(args, size_t); - } else if (qualifier == 't') { - num = va_arg(args, ptrdiff_t); - } else if (qualifier == 'h') { - num = (unsigned short) va_arg(args, int); - if (flags & SIGN) - num = (signed short) num; - } else { - num = va_arg(args, unsigned int); - if (flags & SIGN) - num = (signed int) num; + + default: + switch (spec.type) { + case FORMAT_TYPE_LONG_LONG: + num = va_arg(args, long long); + break; + case FORMAT_TYPE_ULONG: + num = va_arg(args, unsigned long); + break; + case FORMAT_TYPE_LONG: + num = va_arg(args, long); + break; + case FORMAT_TYPE_SIZE_T: + num = va_arg(args, size_t); + break; + case FORMAT_TYPE_PTRDIFF: + num = va_arg(args, ptrdiff_t); + break; + case FORMAT_TYPE_USHORT: + num = (unsigned short) va_arg(args, int); + break; + case FORMAT_TYPE_SHORT: + num = (short) va_arg(args, int); + break; + case FORMAT_TYPE_INT: + num = (int) va_arg(args, int); + break; + default: + num = va_arg(args, unsigned int); + } + + str = number(str, end, num, spec); } - str = number(str, end, num, base, - field_width, precision, flags); } + if (size > 0) { if (str < end) *str = '\0'; else end[-1] = '\0'; } + /* the trailing null byte doesn't count towards the total */ return str-buf; + } EXPORT_SYMBOL(vsnprintf); @@ -1058,6 +1243,372 @@ int sprintf(char * buf, const char *fmt, ...) } EXPORT_SYMBOL(sprintf); +#ifdef CONFIG_BINARY_PRINTF +/* + * bprintf service: + * vbin_printf() - VA arguments to binary data + * bstr_printf() - Binary data to text string + */ + +/** + * vbin_printf - Parse a format string and place args' binary value in a buffer + * @bin_buf: The buffer to place args' binary value + * @size: The size of the buffer(by words(32bits), not characters) + * @fmt: The format string to use + * @args: Arguments for the format string + * + * The format follows C99 vsnprintf, except %n is ignored, and its argument + * is skiped. + * + * The return value is the number of words(32bits) which would be generated for + * the given input. + * + * NOTE: + * If the return value is greater than @size, the resulting bin_buf is NOT + * valid for bstr_printf(). + */ +int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args) +{ + struct printf_spec spec = {0}; + char *str, *end; + int read; + + str = (char *)bin_buf; + end = (char *)(bin_buf + size); + +#define save_arg(type) \ +do { \ + if (sizeof(type) == 8) { \ + unsigned long long value; \ + str = PTR_ALIGN(str, sizeof(u32)); \ + value = va_arg(args, unsigned long long); \ + if (str + sizeof(type) <= end) { \ + *(u32 *)str = *(u32 *)&value; \ + *(u32 *)(str + 4) = *((u32 *)&value + 1); \ + } \ + } else { \ + unsigned long value; \ + str = PTR_ALIGN(str, sizeof(type)); \ + value = va_arg(args, int); \ + if (str + sizeof(type) <= end) \ + *(typeof(type) *)str = (type)value; \ + } \ + str += sizeof(type); \ +} while (0) + + + while (*fmt) { + read = format_decode(fmt, &spec); + + fmt += read; + + switch (spec.type) { + case FORMAT_TYPE_NONE: + break; + + case FORMAT_TYPE_WIDTH: + case FORMAT_TYPE_PRECISION: + save_arg(int); + break; + + case FORMAT_TYPE_CHAR: + save_arg(char); + break; + + case FORMAT_TYPE_STR: { + const char *save_str = va_arg(args, char *); + size_t len; + if ((unsigned long)save_str > (unsigned long)-PAGE_SIZE + || (unsigned long)save_str < PAGE_SIZE) + save_str = "<NULL>"; + len = strlen(save_str); + if (str + len + 1 < end) + memcpy(str, save_str, len + 1); + str += len + 1; + break; + } + + case FORMAT_TYPE_PTR: + save_arg(void *); + /* skip all alphanumeric pointer suffixes */ + while (isalnum(*fmt)) + fmt++; + break; + + case FORMAT_TYPE_PERCENT_CHAR: + break; + + case FORMAT_TYPE_INVALID: + if (!*fmt) + --fmt; + break; + + case FORMAT_TYPE_NRCHARS: { + /* skip %n 's argument */ + int qualifier = spec.qualifier; + void *skip_arg; + if (qualifier == 'l') + skip_arg = va_arg(args, long *); + else if (qualifier == 'Z' || qualifier == 'z') + skip_arg = va_arg(args, size_t *); + else + skip_arg = va_arg(args, int *); + break; + } + + default: + switch (spec.type) { + + case FORMAT_TYPE_LONG_LONG: + save_arg(long long); + break; + case FORMAT_TYPE_ULONG: + case FORMAT_TYPE_LONG: + save_arg(unsigned long); + break; + case FORMAT_TYPE_SIZE_T: + save_arg(size_t); + break; + case FORMAT_TYPE_PTRDIFF: + save_arg(ptrdiff_t); + break; + case FORMAT_TYPE_USHORT: + case FORMAT_TYPE_SHORT: + save_arg(short); + break; + default: + save_arg(int); + } + } + } + return (u32 *)(PTR_ALIGN(str, sizeof(u32))) - bin_buf; + +#undef save_arg +} +EXPORT_SYMBOL_GPL(vbin_printf); + +/** + * bstr_printf - Format a string from binary arguments and place it in a buffer + * @buf: The buffer to place the result into + * @size: The size of the buffer, including the trailing null space + * @fmt: The format string to use + * @bin_buf: Binary arguments for the format string + * + * This function like C99 vsnprintf, but the difference is that vsnprintf gets + * arguments from stack, and bstr_printf gets arguments from @bin_buf which is + * a binary buffer that generated by vbin_printf. + * + * The format follows C99 vsnprintf, but has some extensions: + * %pS output the name of a text symbol + * %pF output the name of a function pointer + * %pR output the address range in a struct resource + * %n is ignored + * + * The return value is the number of characters which would + * be generated for the given input, excluding the trailing + * '\0', as per ISO C99. If you want to have the exact + * number of characters written into @buf as return value + * (not including the trailing '\0'), use vscnprintf(). If the + * return is greater than or equal to @size, the resulting + * string is truncated. + */ +int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf) +{ + unsigned long long num; + char *str, *end, c; + const char *args = (const char *)bin_buf; + + struct printf_spec spec = {0}; + + if (unlikely((int) size < 0)) { + /* There can be only one.. */ + static char warn = 1; + WARN_ON(warn); + warn = 0; + return 0; + } + + str = buf; + end = buf + size; + +#define get_arg(type) \ +({ \ + typeof(type) value; \ + if (sizeof(type) == 8) { \ + args = PTR_ALIGN(args, sizeof(u32)); \ + *(u32 *)&value = *(u32 *)args; \ + *((u32 *)&value + 1) = *(u32 *)(args + 4); \ + } else { \ + args = PTR_ALIGN(args, sizeof(type)); \ + value = *(typeof(type) *)args; \ + } \ + args += sizeof(type); \ + value; \ +}) + + /* Make sure end is always >= buf */ + if (end < buf) { + end = ((void *)-1); + size = end - buf; + } + + while (*fmt) { + int read; + const char *old_fmt = fmt; + + read = format_decode(fmt, &spec); + + fmt += read; + + switch (spec.type) { + case FORMAT_TYPE_NONE: { + int copy = read; + if (str < end) { + if (copy > end - str) + copy = end - str; + memcpy(str, old_fmt, copy); + } + str += read; + break; + } + + case FORMAT_TYPE_WIDTH: + spec.field_width = get_arg(int); + break; + + case FORMAT_TYPE_PRECISION: + spec.precision = get_arg(int); + break; + + case FORMAT_TYPE_CHAR: + if (!(spec.flags & LEFT)) { + while (--spec.field_width > 0) { + if (str < end) + *str = ' '; + ++str; + } + } + c = (unsigned char) get_arg(char); + if (str < end) + *str = c; + ++str; + while (--spec.field_width > 0) { + if (str < end) + *str = ' '; + ++str; + } + break; + + case FORMAT_TYPE_STR: { + const char *str_arg = args; + size_t len = strlen(str_arg); + args += len + 1; + str = string(str, end, (char *)str_arg, spec); + break; + } + + case FORMAT_TYPE_PTR: + str = pointer(fmt+1, str, end, get_arg(void *), spec); + while (isalnum(*fmt)) + fmt++; + break; + + case FORMAT_TYPE_PERCENT_CHAR: + if (str < end) + *str = '%'; + ++str; + break; + + case FORMAT_TYPE_INVALID: + if (str < end) + *str = '%'; + ++str; + if (*fmt) { + if (str < end) + *str = *fmt; + ++str; + } else { + --fmt; + } + break; + + case FORMAT_TYPE_NRCHARS: + /* skip */ + break; + + default: + switch (spec.type) { + + case FORMAT_TYPE_LONG_LONG: + num = get_arg(long long); + break; + case FORMAT_TYPE_ULONG: + num = get_arg(unsigned long); + break; + case FORMAT_TYPE_LONG: + num = get_arg(unsigned long); + break; + case FORMAT_TYPE_SIZE_T: + num = get_arg(size_t); + break; + case FORMAT_TYPE_PTRDIFF: + num = get_arg(ptrdiff_t); + break; + case FORMAT_TYPE_USHORT: + num = get_arg(unsigned short); + break; + case FORMAT_TYPE_SHORT: + num = get_arg(short); + break; + case FORMAT_TYPE_UINT: + num = get_arg(unsigned int); + break; + default: + num = get_arg(int); + } + + str = number(str, end, num, spec); + } + } + + if (size > 0) { + if (str < end) + *str = '\0'; + else + end[-1] = '\0'; + } + +#undef get_arg + + /* the trailing null byte doesn't count towards the total */ + return str - buf; +} +EXPORT_SYMBOL_GPL(bstr_printf); + +/** + * bprintf - Parse a format string and place args' binary value in a buffer + * @bin_buf: The buffer to place args' binary value + * @size: The size of the buffer(by words(32bits), not characters) + * @fmt: The format string to use + * @...: Arguments for the format string + * + * The function returns the number of words(u32) written + * into @bin_buf. + */ +int bprintf(u32 *bin_buf, size_t size, const char *fmt, ...) +{ + va_list args; + int ret; + + va_start(args, fmt); + ret = vbin_printf(bin_buf, size, fmt, args); + va_end(args); + return ret; +} +EXPORT_SYMBOL_GPL(bprintf); + +#endif /* CONFIG_BINARY_PRINTF */ + /** * vsscanf - Unformat a buffer into a list of arguments * @buf: input buffer diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 0284e528748d..e2f26991fff1 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -331,7 +331,7 @@ static int destroy_compound_page(struct page *page, unsigned long order) for (i = 1; i < nr_pages; i++) { struct page *p = page + i; - if (unlikely(!PageTail(p) | (p->first_page != page))) { + if (unlikely(!PageTail(p) || (p->first_page != page))) { bad_page(page); bad++; } @@ -2128,7 +2128,7 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask) int n, val; int min_val = INT_MAX; int best_node = -1; - node_to_cpumask_ptr(tmp, 0); + const struct cpumask *tmp = cpumask_of_node(0); /* Use the local node if we haven't already */ if (!node_isset(node, *used_node_mask)) { @@ -2149,8 +2149,8 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask) val += (n < node); /* Give preference to headless and unused nodes */ - node_to_cpumask_ptr_next(tmp, n); - if (!cpus_empty(*tmp)) + tmp = cpumask_of_node(n); + if (!cpumask_empty(tmp)) val += PENALTY_FOR_NODE_WITH_CPUS; /* Slight preference for less loaded node */ diff --git a/mm/quicklist.c b/mm/quicklist.c index 8dbb6805ef35..e66d07d1b4ff 100644 --- a/mm/quicklist.c +++ b/mm/quicklist.c @@ -29,7 +29,7 @@ static unsigned long max_pages(unsigned long min_pages) int node = numa_node_id(); struct zone *zones = NODE_DATA(node)->node_zones; int num_cpus_on_node; - node_to_cpumask_ptr(cpumask_on_node, node); + const struct cpumask *cpumask_on_node = cpumask_of_node(node); node_free_pages = #ifdef CONFIG_ZONE_DMA diff --git a/mm/slab.c b/mm/slab.c index 208323fd37bc..4fc1761c6dc8 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -102,6 +102,7 @@ #include <linux/cpu.h> #include <linux/sysctl.h> #include <linux/module.h> +#include <trace/kmemtrace.h> #include <linux/rcupdate.h> #include <linux/string.h> #include <linux/uaccess.h> @@ -568,6 +569,14 @@ static void **dbg_userword(struct kmem_cache *cachep, void *objp) #endif +#ifdef CONFIG_KMEMTRACE +size_t slab_buffer_size(struct kmem_cache *cachep) +{ + return cachep->buffer_size; +} +EXPORT_SYMBOL(slab_buffer_size); +#endif + /* * Do not go above this order unless 0 objects fit into the slab. */ @@ -1160,7 +1169,7 @@ static void __cpuinit cpuup_canceled(long cpu) struct kmem_cache *cachep; struct kmem_list3 *l3 = NULL; int node = cpu_to_node(cpu); - node_to_cpumask_ptr(mask, node); + const struct cpumask *mask = cpumask_of_node(node); list_for_each_entry(cachep, &cache_chain, next) { struct array_cache *nc; @@ -3554,10 +3563,23 @@ static inline void __cache_free(struct kmem_cache *cachep, void *objp) */ void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags) { - return __cache_alloc(cachep, flags, __builtin_return_address(0)); + void *ret = __cache_alloc(cachep, flags, __builtin_return_address(0)); + + kmemtrace_mark_alloc(KMEMTRACE_TYPE_CACHE, _RET_IP_, ret, + obj_size(cachep), cachep->buffer_size, flags); + + return ret; } EXPORT_SYMBOL(kmem_cache_alloc); +#ifdef CONFIG_KMEMTRACE +void *kmem_cache_alloc_notrace(struct kmem_cache *cachep, gfp_t flags) +{ + return __cache_alloc(cachep, flags, __builtin_return_address(0)); +} +EXPORT_SYMBOL(kmem_cache_alloc_notrace); +#endif + /** * kmem_ptr_validate - check if an untrusted pointer might be a slab entry. * @cachep: the cache we're checking against @@ -3602,23 +3624,47 @@ out: #ifdef CONFIG_NUMA void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid) { - return __cache_alloc_node(cachep, flags, nodeid, - __builtin_return_address(0)); + void *ret = __cache_alloc_node(cachep, flags, nodeid, + __builtin_return_address(0)); + + kmemtrace_mark_alloc_node(KMEMTRACE_TYPE_CACHE, _RET_IP_, ret, + obj_size(cachep), cachep->buffer_size, + flags, nodeid); + + return ret; } EXPORT_SYMBOL(kmem_cache_alloc_node); +#ifdef CONFIG_KMEMTRACE +void *kmem_cache_alloc_node_notrace(struct kmem_cache *cachep, + gfp_t flags, + int nodeid) +{ + return __cache_alloc_node(cachep, flags, nodeid, + __builtin_return_address(0)); +} +EXPORT_SYMBOL(kmem_cache_alloc_node_notrace); +#endif + static __always_inline void * __do_kmalloc_node(size_t size, gfp_t flags, int node, void *caller) { struct kmem_cache *cachep; + void *ret; cachep = kmem_find_general_cachep(size, flags); if (unlikely(ZERO_OR_NULL_PTR(cachep))) return cachep; - return kmem_cache_alloc_node(cachep, flags, node); + ret = kmem_cache_alloc_node_notrace(cachep, flags, node); + + kmemtrace_mark_alloc_node(KMEMTRACE_TYPE_KMALLOC, + (unsigned long) caller, ret, + size, cachep->buffer_size, flags, node); + + return ret; } -#ifdef CONFIG_DEBUG_SLAB +#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_KMEMTRACE) void *__kmalloc_node(size_t size, gfp_t flags, int node) { return __do_kmalloc_node(size, flags, node, @@ -3651,6 +3697,7 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags, void *caller) { struct kmem_cache *cachep; + void *ret; /* If you want to save a few bytes .text space: replace * __ with kmem_. @@ -3660,11 +3707,17 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags, cachep = __find_general_cachep(size, flags); if (unlikely(ZERO_OR_NULL_PTR(cachep))) return cachep; - return __cache_alloc(cachep, flags, caller); + ret = __cache_alloc(cachep, flags, caller); + + kmemtrace_mark_alloc(KMEMTRACE_TYPE_KMALLOC, + (unsigned long) caller, ret, + size, cachep->buffer_size, flags); + + return ret; } -#ifdef CONFIG_DEBUG_SLAB +#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_KMEMTRACE) void *__kmalloc(size_t size, gfp_t flags) { return __do_kmalloc(size, flags, __builtin_return_address(0)); @@ -3703,6 +3756,8 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp) debug_check_no_obj_freed(objp, obj_size(cachep)); __cache_free(cachep, objp); local_irq_restore(flags); + + kmemtrace_mark_free(KMEMTRACE_TYPE_CACHE, _RET_IP_, objp); } EXPORT_SYMBOL(kmem_cache_free); @@ -3729,6 +3784,8 @@ void kfree(const void *objp) debug_check_no_obj_freed(objp, obj_size(c)); __cache_free(c, (void *)objp); local_irq_restore(flags); + + kmemtrace_mark_free(KMEMTRACE_TYPE_KMALLOC, _RET_IP_, objp); } EXPORT_SYMBOL(kfree); diff --git a/mm/slob.c b/mm/slob.c index 7a3411524dac..4dd6516447f2 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -65,6 +65,7 @@ #include <linux/module.h> #include <linux/rcupdate.h> #include <linux/list.h> +#include <trace/kmemtrace.h> #include <asm/atomic.h> /* @@ -474,6 +475,7 @@ void *__kmalloc_node(size_t size, gfp_t gfp, int node) { unsigned int *m; int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); + void *ret; lockdep_trace_alloc(gfp); @@ -482,12 +484,17 @@ void *__kmalloc_node(size_t size, gfp_t gfp, int node) return ZERO_SIZE_PTR; m = slob_alloc(size + align, gfp, align, node); + if (!m) return NULL; *m = size; - return (void *)m + align; + ret = (void *)m + align; + + kmemtrace_mark_alloc_node(KMEMTRACE_TYPE_KMALLOC, + _RET_IP_, ret, + size, size + align, gfp, node); } else { - void *ret; + unsigned int order = get_order(size); ret = slob_new_pages(gfp | __GFP_COMP, get_order(size), node); if (ret) { @@ -495,8 +502,13 @@ void *__kmalloc_node(size_t size, gfp_t gfp, int node) page = virt_to_page(ret); page->private = size; } - return ret; + + kmemtrace_mark_alloc_node(KMEMTRACE_TYPE_KMALLOC, + _RET_IP_, ret, + size, PAGE_SIZE << order, gfp, node); } + + return ret; } EXPORT_SYMBOL(__kmalloc_node); @@ -514,6 +526,8 @@ void kfree(const void *block) slob_free(m, *m + align); } else put_page(&sp->page); + + kmemtrace_mark_free(KMEMTRACE_TYPE_KMALLOC, _RET_IP_, block); } EXPORT_SYMBOL(kfree); @@ -583,10 +597,19 @@ void *kmem_cache_alloc_node(struct kmem_cache *c, gfp_t flags, int node) { void *b; - if (c->size < PAGE_SIZE) + if (c->size < PAGE_SIZE) { b = slob_alloc(c->size, flags, c->align, node); - else + kmemtrace_mark_alloc_node(KMEMTRACE_TYPE_CACHE, + _RET_IP_, b, c->size, + SLOB_UNITS(c->size) * SLOB_UNIT, + flags, node); + } else { b = slob_new_pages(flags, get_order(c->size), node); + kmemtrace_mark_alloc_node(KMEMTRACE_TYPE_CACHE, + _RET_IP_, b, c->size, + PAGE_SIZE << get_order(c->size), + flags, node); + } if (c->ctor) c->ctor(b); @@ -622,6 +645,8 @@ void kmem_cache_free(struct kmem_cache *c, void *b) } else { __kmem_cache_free(b, c->size); } + + kmemtrace_mark_free(KMEMTRACE_TYPE_CACHE, _RET_IP_, b); } EXPORT_SYMBOL(kmem_cache_free); diff --git a/mm/slub.c b/mm/slub.c index c4ea9158c9fb..7aaa121d0ea9 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -16,6 +16,7 @@ #include <linux/slab.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <trace/kmemtrace.h> #include <linux/cpu.h> #include <linux/cpuset.h> #include <linux/mempolicy.h> @@ -1618,18 +1619,46 @@ static __always_inline void *slab_alloc(struct kmem_cache *s, void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags) { - return slab_alloc(s, gfpflags, -1, _RET_IP_); + void *ret = slab_alloc(s, gfpflags, -1, _RET_IP_); + + kmemtrace_mark_alloc(KMEMTRACE_TYPE_CACHE, _RET_IP_, ret, + s->objsize, s->size, gfpflags); + + return ret; } EXPORT_SYMBOL(kmem_cache_alloc); +#ifdef CONFIG_KMEMTRACE +void *kmem_cache_alloc_notrace(struct kmem_cache *s, gfp_t gfpflags) +{ + return slab_alloc(s, gfpflags, -1, _RET_IP_); +} +EXPORT_SYMBOL(kmem_cache_alloc_notrace); +#endif + #ifdef CONFIG_NUMA void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node) { - return slab_alloc(s, gfpflags, node, _RET_IP_); + void *ret = slab_alloc(s, gfpflags, node, _RET_IP_); + + kmemtrace_mark_alloc_node(KMEMTRACE_TYPE_CACHE, _RET_IP_, ret, + s->objsize, s->size, gfpflags, node); + + return ret; } EXPORT_SYMBOL(kmem_cache_alloc_node); #endif +#ifdef CONFIG_KMEMTRACE +void *kmem_cache_alloc_node_notrace(struct kmem_cache *s, + gfp_t gfpflags, + int node) +{ + return slab_alloc(s, gfpflags, node, _RET_IP_); +} +EXPORT_SYMBOL(kmem_cache_alloc_node_notrace); +#endif + /* * Slow patch handling. This may still be called frequently since objects * have a longer lifetime than the cpu slabs in most processing loads. @@ -1737,6 +1766,8 @@ void kmem_cache_free(struct kmem_cache *s, void *x) page = virt_to_head_page(x); slab_free(s, page, x, _RET_IP_); + + kmemtrace_mark_free(KMEMTRACE_TYPE_CACHE, _RET_IP_, x); } EXPORT_SYMBOL(kmem_cache_free); @@ -2659,6 +2690,7 @@ static struct kmem_cache *get_slab(size_t size, gfp_t flags) void *__kmalloc(size_t size, gfp_t flags) { struct kmem_cache *s; + void *ret; if (unlikely(size > SLUB_MAX_SIZE)) return kmalloc_large(size, flags); @@ -2668,7 +2700,12 @@ void *__kmalloc(size_t size, gfp_t flags) if (unlikely(ZERO_OR_NULL_PTR(s))) return s; - return slab_alloc(s, flags, -1, _RET_IP_); + ret = slab_alloc(s, flags, -1, _RET_IP_); + + kmemtrace_mark_alloc(KMEMTRACE_TYPE_KMALLOC, _RET_IP_, ret, + size, s->size, flags); + + return ret; } EXPORT_SYMBOL(__kmalloc); @@ -2687,16 +2724,30 @@ static void *kmalloc_large_node(size_t size, gfp_t flags, int node) void *__kmalloc_node(size_t size, gfp_t flags, int node) { struct kmem_cache *s; + void *ret; - if (unlikely(size > SLUB_MAX_SIZE)) - return kmalloc_large_node(size, flags, node); + if (unlikely(size > SLUB_MAX_SIZE)) { + ret = kmalloc_large_node(size, flags, node); + + kmemtrace_mark_alloc_node(KMEMTRACE_TYPE_KMALLOC, + _RET_IP_, ret, + size, PAGE_SIZE << get_order(size), + flags, node); + + return ret; + } s = get_slab(size, flags); if (unlikely(ZERO_OR_NULL_PTR(s))) return s; - return slab_alloc(s, flags, node, _RET_IP_); + ret = slab_alloc(s, flags, node, _RET_IP_); + + kmemtrace_mark_alloc_node(KMEMTRACE_TYPE_KMALLOC, _RET_IP_, ret, + size, s->size, flags, node); + + return ret; } EXPORT_SYMBOL(__kmalloc_node); #endif @@ -2755,6 +2806,8 @@ void kfree(const void *x) return; } slab_free(page->slab, page, object, _RET_IP_); + + kmemtrace_mark_free(KMEMTRACE_TYPE_KMALLOC, _RET_IP_, x); } EXPORT_SYMBOL(kfree); @@ -3224,6 +3277,7 @@ static struct notifier_block __cpuinitdata slab_notifier = { void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller) { struct kmem_cache *s; + void *ret; if (unlikely(size > SLUB_MAX_SIZE)) return kmalloc_large(size, gfpflags); @@ -3233,13 +3287,20 @@ void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller) if (unlikely(ZERO_OR_NULL_PTR(s))) return s; - return slab_alloc(s, gfpflags, -1, caller); + ret = slab_alloc(s, gfpflags, -1, caller); + + /* Honor the call site pointer we recieved. */ + kmemtrace_mark_alloc(KMEMTRACE_TYPE_KMALLOC, caller, ret, size, + s->size, gfpflags); + + return ret; } void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags, int node, unsigned long caller) { struct kmem_cache *s; + void *ret; if (unlikely(size > SLUB_MAX_SIZE)) return kmalloc_large_node(size, gfpflags, node); @@ -3249,7 +3310,13 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags, if (unlikely(ZERO_OR_NULL_PTR(s))) return s; - return slab_alloc(s, gfpflags, node, caller); + ret = slab_alloc(s, gfpflags, node, caller); + + /* Honor the call site pointer we recieved. */ + kmemtrace_mark_alloc_node(KMEMTRACE_TYPE_KMALLOC, caller, ret, + size, s->size, gfpflags, node); + + return ret; } #ifdef CONFIG_SLUB_DEBUG diff --git a/mm/vmscan.c b/mm/vmscan.c index 425244988bb2..39fdfb14eeaa 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1967,7 +1967,7 @@ static int kswapd(void *p) struct reclaim_state reclaim_state = { .reclaimed_slab = 0, }; - node_to_cpumask_ptr(cpumask, pgdat->node_id); + const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id); lockdep_set_current_reclaim_state(GFP_KERNEL); @@ -2204,7 +2204,9 @@ static int __devinit cpu_callback(struct notifier_block *nfb, if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) { for_each_node_state(nid, N_HIGH_MEMORY) { pg_data_t *pgdat = NODE_DATA(nid); - node_to_cpumask_ptr(mask, pgdat->node_id); + const struct cpumask *mask; + + mask = cpumask_of_node(pgdat->node_id); if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids) /* One of our CPUs online: restore mask */ diff --git a/net/Kconfig b/net/Kconfig index ec93e7e38b38..ce77db4fcec8 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -140,7 +140,7 @@ config NETFILTER_ADVANCED default y help If you say Y here you can select between all the netfilter modules. - If you say N the more ununsual ones will not be shown and the + If you say N the more unusual ones will not be shown and the basic ones needed by most people will default to 'M'. If unsure, say Y. diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index ec992159b5f8..ca8cb326d1d2 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -22,17 +22,17 @@ menuconfig IPV6 if IPV6 config IPV6_PRIVACY - bool "IPv6: Privacy Extensions support" + bool "IPv6: Privacy Extensions (RFC 3041) support" ---help--- Privacy Extensions for Stateless Address Autoconfiguration in IPv6 - support. With this option, additional periodically-alter - pseudo-random global-scope unicast address(es) will assigned to + support. With this option, additional periodically-altered + pseudo-random global-scope unicast address(es) will be assigned to your interface(s). - We use our standard pseudo random algorithm to generate randomized - interface identifier, instead of one described in RFC 3041. + We use our standard pseudo-random algorithm to generate the + randomized interface identifier, instead of one described in RFC 3041. - By default, kernel do not generate temporary addresses. + By default the kernel does not generate temporary addresses. To use temporary addresses, do echo 2 >/proc/sys/net/ipv6/conf/all/use_tempaddr @@ -43,9 +43,9 @@ config IPV6_ROUTER_PREF bool "IPv6: Router Preference (RFC 4191) support" ---help--- Router Preference is an optional extension to the Router - Advertisement message to improve the ability of hosts - to pick more appropriate router, especially when the hosts - is placed in a multi-homed network. + Advertisement message which improves the ability of hosts + to pick an appropriate router, especially when the hosts + are placed in a multi-homed network. If unsure, say N. diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig index 60c16162474c..f3d9ae350fb6 100644 --- a/net/mac80211/Kconfig +++ b/net/mac80211/Kconfig @@ -33,7 +33,7 @@ choice ---help--- This option selects the default rate control algorithm mac80211 will use. Note that this default can still be - overriden through the ieee80211_default_rc_algo module + overridden through the ieee80211_default_rc_algo module parameter if different algorithms are available. config MAC80211_RC_DEFAULT_PID diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 2c967e4f706c..bb279bf59a1b 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -52,7 +52,7 @@ config NF_CT_ACCT Please note that currently this option only sets a default state. You may change it at boot time with nf_conntrack.acct=0/1 kernel - paramater or by loading the nf_conntrack module with acct=0/1. + parameter or by loading the nf_conntrack module with acct=0/1. You may also disable/enable it on a running system with: sysctl net.netfilter.nf_conntrack_acct=0/1 diff --git a/net/phonet/Kconfig b/net/phonet/Kconfig index 51a5669573f2..6ec7d55b1769 100644 --- a/net/phonet/Kconfig +++ b/net/phonet/Kconfig @@ -6,7 +6,7 @@ config PHONET tristate "Phonet protocols family" help The Phone Network protocol (PhoNet) is a packet-oriented - communication protocol developped by Nokia for use with its modems. + communication protocol developed by Nokia for use with its modems. This is required for Maemo to use cellular data connectivity (if supported). It can also be used to control Nokia phones diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig index afd91c78ce8e..443c161eb8bd 100644 --- a/net/sunrpc/Kconfig +++ b/net/sunrpc/Kconfig @@ -47,7 +47,7 @@ config RPCSEC_GSS_SPKM3 select CRYPTO_CBC help Choose Y here to enable Secure RPC using the SPKM3 public key - GSS-API mechansim (RFC 2025). + GSS-API mechanism (RFC 2025). Secure RPC calls with SPKM3 require an auxiliary userspace daemon which may be found in the Linux nfs-utils package diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 9f2f2412a2f3..9b49a6ab8ded 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -317,8 +317,7 @@ svc_pool_map_set_cpumask(struct task_struct *task, unsigned int pidx) } case SVC_POOL_PERNODE: { - node_to_cpumask_ptr(nodecpumask, node); - set_cpus_allowed_ptr(task, nodecpumask); + set_cpus_allowed_ptr(task, cpumask_of_node(node)); break; } } diff --git a/net/wimax/Kconfig b/net/wimax/Kconfig index 18495cdcd10d..1b46747a5f5a 100644 --- a/net/wimax/Kconfig +++ b/net/wimax/Kconfig @@ -8,7 +8,7 @@ # # As well, enablement of the RFKILL code means we need the INPUT layer # support to inject events coming from hw rfkill switches. That -# dependency could be killed if input.h provided appropiate means to +# dependency could be killed if input.h provided appropriate means to # work when input is disabled. comment "WiMAX Wireless Broadband support requires CONFIG_INPUT enabled" diff --git a/samples/tracepoints/tp-samples-trace.h b/samples/tracepoints/tp-samples-trace.h index 01724e04c556..dffdc49878af 100644 --- a/samples/tracepoints/tp-samples-trace.h +++ b/samples/tracepoints/tp-samples-trace.h @@ -5,9 +5,9 @@ #include <linux/tracepoint.h> DECLARE_TRACE(subsys_event, - TPPROTO(struct inode *inode, struct file *file), - TPARGS(inode, file)); + TP_PROTO(struct inode *inode, struct file *file), + TP_ARGS(inode, file)); DECLARE_TRACE(subsys_eventb, - TPPROTO(void), - TPARGS()); + TP_PROTO(void), + TP_ARGS()); #endif diff --git a/samples/tracepoints/tracepoint-sample.c b/samples/tracepoints/tracepoint-sample.c index 68d5dc0310e4..9cf80a11e8b6 100644 --- a/samples/tracepoints/tracepoint-sample.c +++ b/samples/tracepoints/tracepoint-sample.c @@ -1,6 +1,6 @@ /* tracepoint-sample.c * - * Executes a tracepoint when /proc/tracepoint-example is opened. + * Executes a tracepoint when /proc/tracepoint-sample is opened. * * (C) Copyright 2007 Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> * @@ -16,7 +16,7 @@ DEFINE_TRACE(subsys_event); DEFINE_TRACE(subsys_eventb); -struct proc_dir_entry *pentry_example; +struct proc_dir_entry *pentry_sample; static int my_open(struct inode *inode, struct file *file) { @@ -32,25 +32,25 @@ static struct file_operations mark_ops = { .open = my_open, }; -static int __init example_init(void) +static int __init sample_init(void) { - printk(KERN_ALERT "example init\n"); - pentry_example = proc_create("tracepoint-example", 0444, NULL, + printk(KERN_ALERT "sample init\n"); + pentry_sample = proc_create("tracepoint-sample", 0444, NULL, &mark_ops); - if (!pentry_example) + if (!pentry_sample) return -EPERM; return 0; } -static void __exit example_exit(void) +static void __exit sample_exit(void) { - printk(KERN_ALERT "example exit\n"); - remove_proc_entry("tracepoint-example", NULL); + printk(KERN_ALERT "sample exit\n"); + remove_proc_entry("tracepoint-sample", NULL); } -module_init(example_init) -module_exit(example_exit) +module_init(sample_init) +module_exit(sample_exit) MODULE_LICENSE("GPL"); MODULE_AUTHOR("Mathieu Desnoyers"); -MODULE_DESCRIPTION("Tracepoint example"); +MODULE_DESCRIPTION("Tracepoint sample"); diff --git a/scripts/Makefile.build b/scripts/Makefile.build index c7de8b39fcf1..39a9642927d3 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -112,13 +112,13 @@ endif # --------------------------------------------------------------------------- # Default is built-in, unless we know otherwise -modkern_cflags := $(CFLAGS_KERNEL) +modkern_cflags = $(if $(part-of-module), $(CFLAGS_MODULE), $(CFLAGS_KERNEL)) quiet_modtag := $(empty) $(empty) -$(real-objs-m) : modkern_cflags := $(CFLAGS_MODULE) -$(real-objs-m:.o=.i) : modkern_cflags := $(CFLAGS_MODULE) -$(real-objs-m:.o=.s) : modkern_cflags := $(CFLAGS_MODULE) -$(real-objs-m:.o=.lst): modkern_cflags := $(CFLAGS_MODULE) +$(real-objs-m) : part-of-module := y +$(real-objs-m:.o=.i) : part-of-module := y +$(real-objs-m:.o=.s) : part-of-module := y +$(real-objs-m:.o=.lst): part-of-module := y $(real-objs-m) : quiet_modtag := [M] $(real-objs-m:.o=.i) : quiet_modtag := [M] @@ -205,7 +205,8 @@ endif ifdef CONFIG_FTRACE_MCOUNT_RECORD cmd_record_mcount = perl $(srctree)/scripts/recordmcount.pl "$(ARCH)" \ "$(if $(CONFIG_64BIT),64,32)" \ - "$(OBJDUMP)" "$(OBJCOPY)" "$(CC)" "$(LD)" "$(NM)" "$(RM)" "$(MV)" "$(@)"; + "$(OBJDUMP)" "$(OBJCOPY)" "$(CC)" "$(LD)" "$(NM)" "$(RM)" "$(MV)" \ + "$(if $(part-of-module),1,0)" "$(@)"; endif define rule_cc_o_c diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index ad2434b26970..6654cbed965b 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -500,6 +500,51 @@ static void optimize_token_table(void) optimize_result(); } +/* guess for "linker script provide" symbol */ +static int may_be_linker_script_provide_symbol(const struct sym_entry *se) +{ + const char *symbol = (char *)se->sym + 1; + int len = se->len - 1; + + if (len < 8) + return 0; + + if (symbol[0] != '_' || symbol[1] != '_') + return 0; + + /* __start_XXXXX */ + if (!memcmp(symbol + 2, "start_", 6)) + return 1; + + /* __stop_XXXXX */ + if (!memcmp(symbol + 2, "stop_", 5)) + return 1; + + /* __end_XXXXX */ + if (!memcmp(symbol + 2, "end_", 4)) + return 1; + + /* __XXXXX_start */ + if (!memcmp(symbol + len - 6, "_start", 6)) + return 1; + + /* __XXXXX_end */ + if (!memcmp(symbol + len - 4, "_end", 4)) + return 1; + + return 0; +} + +static int prefix_underscores_count(const char *str) +{ + const char *tail = str; + + while (*tail != '_') + tail++; + + return tail - str; +} + static int compare_symbols(const void *a, const void *b) { const struct sym_entry *sa; @@ -521,6 +566,18 @@ static int compare_symbols(const void *a, const void *b) if (wa != wb) return wa - wb; + /* sort by "linker script provide" type */ + wa = may_be_linker_script_provide_symbol(sa); + wb = may_be_linker_script_provide_symbol(sb); + if (wa != wb) + return wa - wb; + + /* sort by the number of prefix underscores */ + wa = prefix_underscores_count((const char *)sa->sym + 1); + wb = prefix_underscores_count((const char *)sb->sym + 1); + if (wa != wb) + return wa - wb; + /* sort by initial order, so that other symbols are left undisturbed */ return sa->start_pos - sb->start_pos; } diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 7e62303133dc..8cc70612984c 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -1607,12 +1607,12 @@ static void read_symbols(char *modname) parse_elf_finish(&info); - /* Our trick to get versioning for struct_module - it's + /* Our trick to get versioning for module struct etc. - it's * never passed as an argument to an exported function, so * the automatic versioning doesn't pick it up, but it's really * important anyhow */ if (modversions) - mod->unres = alloc_symbol("struct_module", 0, mod->unres); + mod->unres = alloc_symbol("module_layout", 0, mod->unres); } #define SZ 500 diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl index fe831412bea9..409596eca124 100755 --- a/scripts/recordmcount.pl +++ b/scripts/recordmcount.pl @@ -100,14 +100,19 @@ $P =~ s@.*/@@g; my $V = '0.1'; -if ($#ARGV < 6) { - print "usage: $P arch objdump objcopy cc ld nm rm mv inputfile\n"; +if ($#ARGV < 7) { + print "usage: $P arch bits objdump objcopy cc ld nm rm mv is_module inputfile\n"; print "version: $V\n"; exit(1); } my ($arch, $bits, $objdump, $objcopy, $cc, - $ld, $nm, $rm, $mv, $inputfile) = @ARGV; + $ld, $nm, $rm, $mv, $is_module, $inputfile) = @ARGV; + +# This file refers to mcount and shouldn't be ftraced, so lets' ignore it +if ($inputfile eq "kernel/trace/ftrace.o") { + exit(0); +} # Acceptable sections to record. my %text_sections = ( @@ -201,6 +206,13 @@ if ($arch eq "x86_64") { $alignment = 2; $section_type = '%progbits'; +} elsif ($arch eq "ia64") { + $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\s_mcount\$"; + $type = "data8"; + + if ($is_module eq "0") { + $cc .= " -mconstant-gp"; + } } else { die "Arch $arch is not supported with CONFIG_FTRACE_MCOUNT_RECORD"; } @@ -263,7 +275,6 @@ if (!$found_version) { "\tDisabling local function references.\n"; } - # # Step 1: find all the local (static functions) and weak symbols. # 't' is local, 'w/W' is weak (we never use a weak function) @@ -331,13 +342,16 @@ sub update_funcs # # Step 2: find the sections and mcount call sites # -open(IN, "$objdump -dr $inputfile|") || die "error running $objdump"; +open(IN, "$objdump -hdr $inputfile|") || die "error running $objdump"; my $text; +my $read_headers = 1; + while (<IN>) { # is it a section? if (/$section_regex/) { + $read_headers = 0; # Only record text sections that we know are safe if (defined($text_sections{$1})) { @@ -371,6 +385,19 @@ while (<IN>) { $ref_func = $text; } } + } elsif ($read_headers && /$mcount_section/) { + # + # Somehow the make process can execute this script on an + # object twice. If it does, we would duplicate the mcount + # section and it will cause the function tracer self test + # to fail. Check if the mcount section exists, and if it does, + # warn and exit. + # + print STDERR "ERROR: $mcount_section already in $inputfile\n" . + "\tThis may be an indication that your build is corrupted.\n" . + "\tDelete $inputfile and try again. If the same object file\n" . + "\tstill causes an issue, then disable CONFIG_DYNAMIC_FTRACE.\n"; + exit(-1); } # is this a call site to mcount? If so, record it to print later diff --git a/sound/oss/pss.c b/sound/oss/pss.c index 16517a5a1301..83f5ee236b12 100644 --- a/sound/oss/pss.c +++ b/sound/oss/pss.c @@ -46,7 +46,7 @@ * load the driver as it did in previous versions. * 04-07-1999: Anthony Barbachan <barbcode@xmen.cis.fordham.edu> * Added module parameter pss_firmware to allow the user to tell - * the driver where the fireware file is located. The default + * the driver where the firmware file is located. The default * setting is the previous hardcoded setting "/etc/sound/pss_synth". * 00-03-03: Christoph Hellwig <chhellwig@infradead.org> * Adapted to module_init/module_exit diff --git a/sound/sh/aica.c b/sound/sh/aica.c index f551233c5a08..583a3693df75 100644 --- a/sound/sh/aica.c +++ b/sound/sh/aica.c @@ -565,7 +565,7 @@ static int load_aica_firmware(void) err = request_firmware(&fw_entry, "aica_firmware.bin", &pd->dev); if (unlikely(err)) return err; - /* write firware into memory */ + /* write firmware into memory */ spu_disable(); spu_memload(0, fw_entry->data, fw_entry->size); spu_enable(); diff --git a/sound/soc/blackfin/Kconfig b/sound/soc/blackfin/Kconfig index 0a2f8f9eff53..811596f4c092 100644 --- a/sound/soc/blackfin/Kconfig +++ b/sound/soc/blackfin/Kconfig @@ -42,7 +42,7 @@ config SND_BF5XX_AC97 You will also need to select the audio interfaces to support below. Note: - AC97 codecs which do not implment the slot-16 mode will not function + AC97 codecs which do not implement the slot-16 mode will not function properly with this driver. This driver is known to work with the Analog Devices line of AC97 codecs. diff --git a/usr/Kconfig b/usr/Kconfig index 588c588791e2..1c3039f28909 100644 --- a/usr/Kconfig +++ b/usr/Kconfig @@ -72,10 +72,8 @@ config RD_LZMA Support loading of a LZMA encoded initial ramdisk or cpio buffer If unsure, say N. -if INITRAMFS_SOURCE!="" - choice - prompt "Built-in initramfs compression mode" + prompt "Built-in initramfs compression mode" if INITRAMFS_SOURCE!="" help This option decides by which algorithm the builtin initramfs will be compressed. Several compression algorithms are @@ -134,14 +132,3 @@ config INITRAMFS_COMPRESSION_LZMA smaller with LZMA in comparison to gzip. endchoice - -endif - -if INITRAMFS_SOURCE="" -# The builtin initramfs is so small so we don't want to bug the user... - -config INITRAMFS_COMPRESSION_NONE - bool - default y - -endif diff --git a/usr/Makefile b/usr/Makefile index b84894b3929d..245145a99c10 100644 --- a/usr/Makefile +++ b/usr/Makefile @@ -6,9 +6,6 @@ klibcdirs:; PHONY += klibcdirs -# No compression -suffix_$(CONFIG_INITRAMFS_COMPRESSION_NONE) = - # Gzip, but no bzip2 suffix_$(CONFIG_INITRAMFS_COMPRESSION_GZIP) = .gz |