diff options
Diffstat (limited to 'Documentation')
51 files changed, 1114 insertions, 297 deletions
diff --git a/Documentation/ABI/testing/sysfs-bus-usb b/Documentation/ABI/testing/sysfs-bus-usb index a986e9bbba3..bcebb9eaedc 100644 --- a/Documentation/ABI/testing/sysfs-bus-usb +++ b/Documentation/ABI/testing/sysfs-bus-usb @@ -160,7 +160,7 @@ Description: match the driver to the device. For example: # echo "046d c315" > /sys/bus/usb/drivers/foo/remove_id -What: /sys/bus/usb/device/.../avoid_reset +What: /sys/bus/usb/device/.../avoid_reset_quirk Date: December 2009 Contact: Oliver Neukum <oliver@neukum.org> Description: diff --git a/Documentation/PCI/PCI-DMA-mapping.txt b/Documentation/DMA-API-HOWTO.txt index 52618ab069a..52618ab069a 100644 --- a/Documentation/PCI/PCI-DMA-mapping.txt +++ b/Documentation/DMA-API-HOWTO.txt diff --git a/Documentation/DocBook/libata.tmpl b/Documentation/DocBook/libata.tmpl index ba997577150..ff3e5bec1c2 100644 --- a/Documentation/DocBook/libata.tmpl +++ b/Documentation/DocBook/libata.tmpl @@ -107,10 +107,6 @@ void (*dev_config) (struct ata_port *, struct ata_device *); issue of SET FEATURES - XFER MODE, and prior to operation. </para> <para> - Called by ata_device_add() after ata_dev_identify() determines - a device is present. - </para> - <para> This entry may be specified as NULL in ata_port_operations. </para> @@ -154,8 +150,8 @@ unsigned int (*mode_filter) (struct ata_port *, struct ata_device *, unsigned in <sect2><title>Taskfile read/write</title> <programlisting> -void (*tf_load) (struct ata_port *ap, struct ata_taskfile *tf); -void (*tf_read) (struct ata_port *ap, struct ata_taskfile *tf); +void (*sff_tf_load) (struct ata_port *ap, struct ata_taskfile *tf); +void (*sff_tf_read) (struct ata_port *ap, struct ata_taskfile *tf); </programlisting> <para> @@ -164,36 +160,35 @@ void (*tf_read) (struct ata_port *ap, struct ata_taskfile *tf); hardware registers / DMA buffers, to obtain the current set of taskfile register values. Most drivers for taskfile-based hardware (PIO or MMIO) use - ata_tf_load() and ata_tf_read() for these hooks. + ata_sff_tf_load() and ata_sff_tf_read() for these hooks. </para> </sect2> <sect2><title>PIO data read/write</title> <programlisting> -void (*data_xfer) (struct ata_device *, unsigned char *, unsigned int, int); +void (*sff_data_xfer) (struct ata_device *, unsigned char *, unsigned int, int); </programlisting> <para> All bmdma-style drivers must implement this hook. This is the low-level operation that actually copies the data bytes during a PIO data transfer. -Typically the driver -will choose one of ata_pio_data_xfer_noirq(), ata_pio_data_xfer(), or -ata_mmio_data_xfer(). +Typically the driver will choose one of ata_sff_data_xfer_noirq(), +ata_sff_data_xfer(), or ata_sff_data_xfer32(). </para> </sect2> <sect2><title>ATA command execute</title> <programlisting> -void (*exec_command)(struct ata_port *ap, struct ata_taskfile *tf); +void (*sff_exec_command)(struct ata_port *ap, struct ata_taskfile *tf); </programlisting> <para> causes an ATA command, previously loaded with ->tf_load(), to be initiated in hardware. - Most drivers for taskfile-based hardware use ata_exec_command() + Most drivers for taskfile-based hardware use ata_sff_exec_command() for this hook. </para> @@ -218,8 +213,8 @@ command. <sect2><title>Read specific ATA shadow registers</title> <programlisting> -u8 (*check_status)(struct ata_port *ap); -u8 (*check_altstatus)(struct ata_port *ap); +u8 (*sff_check_status)(struct ata_port *ap); +u8 (*sff_check_altstatus)(struct ata_port *ap); </programlisting> <para> @@ -227,20 +222,14 @@ u8 (*check_altstatus)(struct ata_port *ap); hardware. On some hardware, reading the Status register has the side effect of clearing the interrupt condition. Most drivers for taskfile-based hardware use - ata_check_status() for this hook. - </para> - <para> - Note that because this is called from ata_device_add(), at - least a dummy function that clears device interrupts must be - provided for all drivers, even if the controller doesn't - actually have a taskfile status register. + ata_sff_check_status() for this hook. </para> </sect2> <sect2><title>Select ATA device on bus</title> <programlisting> -void (*dev_select)(struct ata_port *ap, unsigned int device); +void (*sff_dev_select)(struct ata_port *ap, unsigned int device); </programlisting> <para> @@ -251,9 +240,7 @@ void (*dev_select)(struct ata_port *ap, unsigned int device); </para> <para> Most drivers for taskfile-based hardware use - ata_std_dev_select() for this hook. Controllers which do not - support second drives on a port (such as SATA contollers) will - use ata_noop_dev_select(). + ata_sff_dev_select() for this hook. </para> </sect2> @@ -441,13 +428,13 @@ void (*irq_clear) (struct ata_port *); to struct ata_host_set. </para> <para> - Most legacy IDE drivers use ata_interrupt() for the + Most legacy IDE drivers use ata_sff_interrupt() for the irq_handler hook, which scans all ports in the host_set, determines which queued command was active (if any), and calls - ata_host_intr(ap,qc). + ata_sff_host_intr(ap,qc). </para> <para> - Most legacy IDE drivers use ata_bmdma_irq_clear() for the + Most legacy IDE drivers use ata_sff_irq_clear() for the irq_clear() hook, which simply clears the interrupt and error flags in the DMA status register. </para> @@ -496,10 +483,6 @@ void (*host_stop) (struct ata_host_set *host_set); data from port at this time. </para> <para> - Many drivers use ata_port_stop() as this hook, which frees the - PRD table. - </para> - <para> ->host_stop() is called after all ->port_stop() calls have completed. The hook must finalize hardware shutdown, release DMA and other resources, etc. diff --git a/Documentation/DocBook/tracepoint.tmpl b/Documentation/DocBook/tracepoint.tmpl index 8bca1d5cec0..e8473eae2a2 100644 --- a/Documentation/DocBook/tracepoint.tmpl +++ b/Documentation/DocBook/tracepoint.tmpl @@ -16,6 +16,15 @@ </address> </affiliation> </author> + <author> + <firstname>William</firstname> + <surname>Cohen</surname> + <affiliation> + <address> + <email>wcohen@redhat.com</email> + </address> + </affiliation> + </author> </authorgroup> <legalnotice> @@ -91,4 +100,8 @@ !Iinclude/trace/events/signal.h </chapter> + <chapter id="block"> + <title>Block IO</title> +!Iinclude/trace/events/block.h + </chapter> </book> diff --git a/Documentation/HOWTO b/Documentation/HOWTO index f5395af88a4..40ada93b820 100644 --- a/Documentation/HOWTO +++ b/Documentation/HOWTO @@ -234,7 +234,7 @@ process is as follows: Linus, usually the patches that have already been included in the -next kernel for a few weeks. The preferred way to submit big changes is using git (the kernel's source management tool, more information - can be found at http://git.or.cz/) but plain patches are also just + can be found at http://git-scm.com/) but plain patches are also just fine. - After two weeks a -rc1 kernel is released it is now possible to push only patches that do not include new features that could affect the diff --git a/Documentation/RCU/NMI-RCU.txt b/Documentation/RCU/NMI-RCU.txt index a6d32e65d22..a8536cb8809 100644 --- a/Documentation/RCU/NMI-RCU.txt +++ b/Documentation/RCU/NMI-RCU.txt @@ -34,7 +34,7 @@ NMI handler. cpu = smp_processor_id(); ++nmi_count(cpu); - if (!rcu_dereference(nmi_callback)(regs, cpu)) + if (!rcu_dereference_sched(nmi_callback)(regs, cpu)) default_do_nmi(regs); nmi_exit(); @@ -47,12 +47,13 @@ function pointer. If this handler returns zero, do_nmi() invokes the default_do_nmi() function to handle a machine-specific NMI. Finally, preemption is restored. -Strictly speaking, rcu_dereference() is not needed, since this code runs -only on i386, which does not need rcu_dereference() anyway. However, -it is a good documentation aid, particularly for anyone attempting to -do something similar on Alpha. +In theory, rcu_dereference_sched() is not needed, since this code runs +only on i386, which in theory does not need rcu_dereference_sched() +anyway. However, in practice it is a good documentation aid, particularly +for anyone attempting to do something similar on Alpha or on systems +with aggressive optimizing compilers. -Quick Quiz: Why might the rcu_dereference() be necessary on Alpha, +Quick Quiz: Why might the rcu_dereference_sched() be necessary on Alpha, given that the code referenced by the pointer is read-only? @@ -99,17 +100,21 @@ invoke irq_enter() and irq_exit() on NMI entry and exit, respectively. Answer to Quick Quiz - Why might the rcu_dereference() be necessary on Alpha, given + Why might the rcu_dereference_sched() be necessary on Alpha, given that the code referenced by the pointer is read-only? Answer: The caller to set_nmi_callback() might well have - initialized some data that is to be used by the - new NMI handler. In this case, the rcu_dereference() - would be needed, because otherwise a CPU that received - an NMI just after the new handler was set might see - the pointer to the new NMI handler, but the old - pre-initialized version of the handler's data. - - More important, the rcu_dereference() makes it clear - to someone reading the code that the pointer is being - protected by RCU. + initialized some data that is to be used by the new NMI + handler. In this case, the rcu_dereference_sched() would + be needed, because otherwise a CPU that received an NMI + just after the new handler was set might see the pointer + to the new NMI handler, but the old pre-initialized + version of the handler's data. + + This same sad story can happen on other CPUs when using + a compiler with aggressive pointer-value speculation + optimizations. + + More important, the rcu_dereference_sched() makes it + clear to someone reading the code that the pointer is + being protected by RCU-sched. diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt index cbc180f9019..790d1a81237 100644 --- a/Documentation/RCU/checklist.txt +++ b/Documentation/RCU/checklist.txt @@ -260,7 +260,8 @@ over a rather long period of time, but improvements are always welcome! The reason that it is permissible to use RCU list-traversal primitives when the update-side lock is held is that doing so can be quite helpful in reducing code bloat when common code is - shared between readers and updaters. + shared between readers and updaters. Additional primitives + are provided for this case, as discussed in lockdep.txt. 10. Conversely, if you are in an RCU read-side critical section, and you don't hold the appropriate update-side lock, you -must- @@ -344,8 +345,8 @@ over a rather long period of time, but improvements are always welcome! requiring SRCU's read-side deadlock immunity or low read-side realtime latency. - Note that, rcu_assign_pointer() and rcu_dereference() relate to - SRCU just as they do to other forms of RCU. + Note that, rcu_assign_pointer() relates to SRCU just as they do + to other forms of RCU. 15. The whole point of call_rcu(), synchronize_rcu(), and friends is to wait until all pre-existing readers have finished before diff --git a/Documentation/RCU/lockdep.txt b/Documentation/RCU/lockdep.txt index fe24b58627b..d7a49b2f699 100644 --- a/Documentation/RCU/lockdep.txt +++ b/Documentation/RCU/lockdep.txt @@ -32,9 +32,20 @@ checking of rcu_dereference() primitives: srcu_dereference(p, sp): Check for SRCU read-side critical section. rcu_dereference_check(p, c): - Use explicit check expression "c". + Use explicit check expression "c". This is useful in + code that is invoked by both readers and updaters. rcu_dereference_raw(p) Don't check. (Use sparingly, if at all.) + rcu_dereference_protected(p, c): + Use explicit check expression "c", and omit all barriers + and compiler constraints. This is useful when the data + structure cannot change, for example, in code that is + invoked only by updaters. + rcu_access_pointer(p): + Return the value of the pointer and omit all barriers, + but retain the compiler constraints that prevent duplicating + or coalescsing. This is useful when when testing the + value of the pointer itself, for example, against NULL. The rcu_dereference_check() check expression can be any boolean expression, but would normally include one of the rcu_read_lock_held() @@ -59,7 +70,20 @@ In case (1), the pointer is picked up in an RCU-safe manner for vanilla RCU read-side critical sections, in case (2) the ->file_lock prevents any change from taking place, and finally, in case (3) the current task is the only task accessing the file_struct, again preventing any change -from taking place. +from taking place. If the above statement was invoked only from updater +code, it could instead be written as follows: + + file = rcu_dereference_protected(fdt->fd[fd], + lockdep_is_held(&files->file_lock) || + atomic_read(&files->count) == 1); + +This would verify cases #2 and #3 above, and furthermore lockdep would +complain if this was used in an RCU read-side critical section unless one +of these two cases held. Because rcu_dereference_protected() omits all +barriers and compiler constraints, it generates better code than do the +other flavors of rcu_dereference(). On the other hand, it is illegal +to use rcu_dereference_protected() if either the RCU-protected pointer +or the RCU-protected data that it points to can change concurrently. There are currently only "universal" versions of the rcu_assign_pointer() and RCU list-/tree-traversal primitives, which do not (yet) check for diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt index 1423d2570d7..44c6dcc93d6 100644 --- a/Documentation/RCU/stallwarn.txt +++ b/Documentation/RCU/stallwarn.txt @@ -3,35 +3,79 @@ Using RCU's CPU Stall Detector The CONFIG_RCU_CPU_STALL_DETECTOR kernel config parameter enables RCU's CPU stall detector, which detects conditions that unduly delay RCU grace periods. The stall detector's idea of what constitutes -"unduly delayed" is controlled by a pair of C preprocessor macros: +"unduly delayed" is controlled by a set of C preprocessor macros: RCU_SECONDS_TILL_STALL_CHECK This macro defines the period of time that RCU will wait from the beginning of a grace period until it issues an RCU CPU - stall warning. It is normally ten seconds. + stall warning. This time period is normally ten seconds. RCU_SECONDS_TILL_STALL_RECHECK This macro defines the period of time that RCU will wait after - issuing a stall warning until it issues another stall warning. - It is normally set to thirty seconds. + issuing a stall warning until it issues another stall warning + for the same stall. This time period is normally set to thirty + seconds. RCU_STALL_RAT_DELAY - The CPU stall detector tries to make the offending CPU rat on itself, - as this often gives better-quality stack traces. However, if - the offending CPU does not detect its own stall in the number - of jiffies specified by RCU_STALL_RAT_DELAY, then other CPUs will - complain. This is normally set to two jiffies. + The CPU stall detector tries to make the offending CPU print its + own warnings, as this often gives better-quality stack traces. + However, if the offending CPU does not detect its own stall in + the number of jiffies specified by RCU_STALL_RAT_DELAY, then + some other CPU will complain. This delay is normally set to + two jiffies. -The following problems can result in an RCU CPU stall warning: +When a CPU detects that it is stalling, it will print a message similar +to the following: + +INFO: rcu_sched_state detected stall on CPU 5 (t=2500 jiffies) + +This message indicates that CPU 5 detected that it was causing a stall, +and that the stall was affecting RCU-sched. This message will normally be +followed by a stack dump of the offending CPU. On TREE_RCU kernel builds, +RCU and RCU-sched are implemented by the same underlying mechanism, +while on TREE_PREEMPT_RCU kernel builds, RCU is instead implemented +by rcu_preempt_state. + +On the other hand, if the offending CPU fails to print out a stall-warning +message quickly enough, some other CPU will print a message similar to +the following: + +INFO: rcu_bh_state detected stalls on CPUs/tasks: { 3 5 } (detected by 2, 2502 jiffies) + +This message indicates that CPU 2 detected that CPUs 3 and 5 were both +causing stalls, and that the stall was affecting RCU-bh. This message +will normally be followed by stack dumps for each CPU. Please note that +TREE_PREEMPT_RCU builds can be stalled by tasks as well as by CPUs, +and that the tasks will be indicated by PID, for example, "P3421". +It is even possible for a rcu_preempt_state stall to be caused by both +CPUs -and- tasks, in which case the offending CPUs and tasks will all +be called out in the list. + +Finally, if the grace period ends just as the stall warning starts +printing, there will be a spurious stall-warning message: + +INFO: rcu_bh_state detected stalls on CPUs/tasks: { } (detected by 4, 2502 jiffies) + +This is rare, but does happen from time to time in real life. + +So your kernel printed an RCU CPU stall warning. The next question is +"What caused it?" The following problems can result in RCU CPU stall +warnings: o A CPU looping in an RCU read-side critical section. -o A CPU looping with interrupts disabled. +o A CPU looping with interrupts disabled. This condition can + result in RCU-sched and RCU-bh stalls. -o A CPU looping with preemption disabled. +o A CPU looping with preemption disabled. This condition can + result in RCU-sched stalls and, if ksoftirqd is in use, RCU-bh + stalls. + +o A CPU looping with bottom halves disabled. This condition can + result in RCU-sched and RCU-bh stalls. o For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel without invoking schedule(). @@ -39,20 +83,24 @@ o For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel o A bug in the RCU implementation. o A hardware failure. This is quite unlikely, but has occurred - at least once in a former life. A CPU failed in a running system, + at least once in real life. A CPU failed in a running system, becoming unresponsive, but not causing an immediate crash. This resulted in a series of RCU CPU stall warnings, eventually leading the realization that the CPU had failed. -The RCU, RCU-sched, and RCU-bh implementations have CPU stall warning. -SRCU does not do so directly, but its calls to synchronize_sched() will -result in RCU-sched detecting any CPU stalls that might be occurring. - -To diagnose the cause of the stall, inspect the stack traces. The offending -function will usually be near the top of the stack. If you have a series -of stall warnings from a single extended stall, comparing the stack traces -can often help determine where the stall is occurring, which will usually -be in the function nearest the top of the stack that stays the same from -trace to trace. +The RCU, RCU-sched, and RCU-bh implementations have CPU stall +warning. SRCU does not have its own CPU stall warnings, but its +calls to synchronize_sched() will result in RCU-sched detecting +RCU-sched-related CPU stalls. Please note that RCU only detects +CPU stalls when there is a grace period in progress. No grace period, +no CPU stall warnings. + +To diagnose the cause of the stall, inspect the stack traces. +The offending function will usually be near the top of the stack. +If you have a series of stall warnings from a single extended stall, +comparing the stack traces can often help determine where the stall +is occurring, which will usually be in the function nearest the top of +that portion of the stack which remains the same from trace to trace. +If you can reliably trigger the stall, ftrace can be quite helpful. RCU bugs can often be debugged with the help of CONFIG_RCU_TRACE. diff --git a/Documentation/RCU/torture.txt b/Documentation/RCU/torture.txt index 0e50bc2aa1e..5d9016795fd 100644 --- a/Documentation/RCU/torture.txt +++ b/Documentation/RCU/torture.txt @@ -182,16 +182,6 @@ Similarly, sched_expedited RCU provides the following: sched_expedited-torture: Reader Pipe: 12660320201 95875 0 0 0 0 0 0 0 0 0 sched_expedited-torture: Reader Batch: 12660424885 0 0 0 0 0 0 0 0 0 0 sched_expedited-torture: Free-Block Circulation: 1090795 1090795 1090794 1090793 1090792 1090791 1090790 1090789 1090788 1090787 0 - state: -1 / 0:0 3:0 4:0 - -As before, the first four lines are similar to those for RCU. -The last line shows the task-migration state. The first number is --1 if synchronize_sched_expedited() is idle, -2 if in the process of -posting wakeups to the migration kthreads, and N when waiting on CPU N. -Each of the colon-separated fields following the "/" is a CPU:state pair. -Valid states are "0" for idle, "1" for waiting for quiescent state, -"2" for passed through quiescent state, and "3" when a race with a -CPU-hotplug event forces use of the synchronize_sched() primitive. USAGE diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt index 8608fd85e92..efd8cc95c06 100644 --- a/Documentation/RCU/trace.txt +++ b/Documentation/RCU/trace.txt @@ -256,23 +256,23 @@ o Each element of the form "1/1 0:127 ^0" represents one struct The output of "cat rcu/rcu_pending" looks as follows: rcu_sched: - 0 np=255892 qsp=53936 cbr=0 cng=14417 gpc=10033 gps=24320 nf=6445 nn=146741 - 1 np=261224 qsp=54638 cbr=0 cng=25723 gpc=16310 gps=2849 nf=5912 nn=155792 - 2 np=237496 qsp=49664 cbr=0 cng=2762 gpc=45478 gps=1762 nf=1201 nn=136629 - 3 np=236249 qsp=48766 cbr=0 cng=286 gpc=48049 gps=1218 nf=207 nn=137723 - 4 np=221310 qsp=46850 cbr=0 cng=26 gpc=43161 gps=4634 nf=3529 nn=123110 - 5 np=237332 qsp=48449 cbr=0 cng=54 gpc=47920 gps=3252 nf=201 nn=137456 - 6 np=219995 qsp=46718 cbr=0 cng=50 gpc=42098 gps=6093 nf=4202 nn=120834 - 7 np=249893 qsp=49390 cbr=0 cng=72 gpc=38400 gps=17102 nf=41 nn=144888 + 0 np=255892 qsp=53936 rpq=85 cbr=0 cng=14417 gpc=10033 gps=24320 nf=6445 nn=146741 + 1 np=261224 qsp=54638 rpq=33 cbr=0 cng=25723 gpc=16310 gps=2849 nf=5912 nn=155792 + 2 np=237496 qsp=49664 rpq=23 cbr=0 cng=2762 gpc=45478 gps=1762 nf=1201 nn=136629 + 3 np=236249 qsp=48766 rpq=98 cbr=0 cng=286 gpc=48049 gps=1218 nf=207 nn=137723 + 4 np=221310 qsp=46850 rpq=7 cbr=0 cng=26 gpc=43161 gps=4634 nf=3529 nn=123110 + 5 np=237332 qsp=48449 rpq=9 cbr=0 cng=54 gpc=47920 gps=3252 nf=201 nn=137456 + 6 np=219995 qsp=46718 rpq=12 cbr=0 cng=50 gpc=42098 gps=6093 nf=4202 nn=120834 + 7 np=249893 qsp=49390 rpq=42 cbr=0 cng=72 gpc=38400 gps=17102 nf=41 nn=144888 rcu_bh: - 0 np=146741 qsp=1419 cbr=0 cng=6 gpc=0 gps=0 nf=2 nn=145314 - 1 np=155792 qsp=12597 cbr=0 cng=0 gpc=4 gps=8 nf=3 nn=143180 - 2 np=136629 qsp=18680 cbr=0 cng=0 gpc=7 gps=6 nf=0 nn=117936 - 3 np=137723 qsp=2843 cbr=0 cng=0 gpc=10 gps=7 nf=0 nn=134863 - 4 np=123110 qsp=12433 cbr=0 cng=0 gpc=4 gps=2 nf=0 nn=110671 - 5 np=137456 qsp=4210 cbr=0 cng=0 gpc=6 gps=5 nf=0 nn=133235 - 6 np=120834 qsp=9902 cbr=0 cng=0 gpc=6 gps=3 nf=2 nn=110921 - 7 np=144888 qsp=26336 cbr=0 cng=0 gpc=8 gps=2 nf=0 nn=118542 + 0 np=146741 qsp=1419 rpq=6 cbr=0 cng=6 gpc=0 gps=0 nf=2 nn=145314 + 1 np=155792 qsp=12597 rpq=3 cbr=0 cng=0 gpc=4 gps=8 nf=3 nn=143180 + 2 np=136629 qsp=18680 rpq=1 cbr=0 cng=0 gpc=7 gps=6 nf=0 nn=117936 + 3 np=137723 qsp=2843 rpq=0 cbr=0 cng=0 gpc=10 gps=7 nf=0 nn=134863 + 4 np=123110 qsp=12433 rpq=0 cbr=0 cng=0 gpc=4 gps=2 nf=0 nn=110671 + 5 np=137456 qsp=4210 rpq=1 cbr=0 cng=0 gpc=6 gps=5 nf=0 nn=133235 + 6 np=120834 qsp=9902 rpq=2 cbr=0 cng=0 gpc=6 gps=3 nf=2 nn=110921 + 7 np=144888 qsp=26336 rpq=0 cbr=0 cng=0 gpc=8 gps=2 nf=0 nn=118542 As always, this is once again split into "rcu_sched" and "rcu_bh" portions, with CONFIG_TREE_PREEMPT_RCU kernels having an additional @@ -284,6 +284,9 @@ o "np" is the number of times that __rcu_pending() has been invoked o "qsp" is the number of times that the RCU was waiting for a quiescent state from this CPU. +o "rpq" is the number of times that the CPU had passed through + a quiescent state, but not yet reported it to RCU. + o "cbr" is the number of times that this CPU had RCU callbacks that had passed through a grace period, and were thus ready to be invoked. diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt index 1dc00ee9716..cfaac34c455 100644 --- a/Documentation/RCU/whatisRCU.txt +++ b/Documentation/RCU/whatisRCU.txt @@ -840,6 +840,12 @@ SRCU: Initialization/cleanup init_srcu_struct cleanup_srcu_struct +All: lockdep-checked RCU-protected pointer access + + rcu_dereference_check + rcu_dereference_protected + rcu_access_pointer + See the comment headers in the source code (or the docbook generated from them) for more information. diff --git a/Documentation/block/biodoc.txt b/Documentation/block/biodoc.txt index 6fab97ea7e6..508b5b2b028 100644 --- a/Documentation/block/biodoc.txt +++ b/Documentation/block/biodoc.txt @@ -1162,8 +1162,8 @@ where a driver received a request ala this before: As mentioned, there is no virtual mapping of a bio. For DMA, this is not a problem as the driver probably never will need a virtual mapping. -Instead it needs a bus mapping (pci_map_page for a single segment or -use blk_rq_map_sg for scatter gather) to be able to ship it to the driver. For +Instead it needs a bus mapping (dma_map_page for a single segment or +use dma_map_sg for scatter gather) to be able to ship it to the driver. For PIO drivers (or drivers that need to revert to PIO transfer once in a while (IDE for example)), where the CPU is doing the actual data transfer a virtual mapping is needed. If the driver supports highmem I/O, diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt index fd588ff0e29..a1ca5924faf 100644 --- a/Documentation/cgroups/cgroups.txt +++ b/Documentation/cgroups/cgroups.txt @@ -235,8 +235,7 @@ containing the following files describing that cgroup: - cgroup.procs: list of tgids in the cgroup. This list is not guaranteed to be sorted or free of duplicate tgids, and userspace should sort/uniquify the list if this property is required. - Writing a tgid into this file moves all threads with that tgid into - this cgroup. + This is a read-only file, for now. - notify_on_release flag: run the release agent on exit? - release_agent: the path to use for release notifications (this file exists in the top cgroup only) diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt index f8bc802d70b..3a6aecd078b 100644 --- a/Documentation/cgroups/memory.txt +++ b/Documentation/cgroups/memory.txt @@ -340,7 +340,7 @@ Note: 5.3 swappiness Similar to /proc/sys/vm/swappiness, but affecting a hierarchy of groups only. - Following cgroups' swapiness can't be changed. + Following cgroups' swappiness can't be changed. - root cgroup (uses /proc/sys/vm/swappiness). - a cgroup which uses hierarchy and it has child cgroup. - a cgroup which uses hierarchy and not the root of hierarchy. diff --git a/Documentation/circular-buffers.txt b/Documentation/circular-buffers.txt new file mode 100644 index 00000000000..8117e5bf606 --- /dev/null +++ b/Documentation/circular-buffers.txt @@ -0,0 +1,234 @@ + ================ + CIRCULAR BUFFERS + ================ + +By: David Howells <dhowells@redhat.com> + Paul E. McKenney <paulmck@linux.vnet.ibm.com> + + +Linux provides a number of features that can be used to implement circular +buffering. There are two sets of such features: + + (1) Convenience functions for determining information about power-of-2 sized + buffers. + + (2) Memory barriers for when the producer and the consumer of objects in the + buffer don't want to share a lock. + +To use these facilities, as discussed below, there needs to be just one +producer and just one consumer. It is possible to handle multiple producers by +serialising them, and to handle multiple consumers by serialising them. + + +Contents: + + (*) What is a circular buffer? + + (*) Measuring power-of-2 buffers. + + (*) Using memory barriers with circular buffers. + - The producer. + - The consumer. + + +========================== +WHAT IS A CIRCULAR BUFFER? +========================== + +First of all, what is a circular buffer? A circular buffer is a buffer of +fixed, finite size into which there are two indices: + + (1) A 'head' index - the point at which the producer inserts items into the + buffer. + + (2) A 'tail' index - the point at which the consumer finds the next item in + the buffer. + +Typically when the tail pointer is equal to the head pointer, the buffer is +empty; and the buffer is full when the head pointer is one less than the tail +pointer. + +The head index is incremented when items are added, and the tail index when +items are removed. The tail index should never jump the head index, and both +indices should be wrapped to 0 when they reach the end of the buffer, thus +allowing an infinite amount of data to flow through the buffer. + +Typically, items will all be of the same unit size, but this isn't strictly +required to use the techniques below. The indices can be increased by more +than 1 if multiple items or variable-sized items are to be included in the +buffer, provided that neither index overtakes the other. The implementer must +be careful, however, as a region more than one unit in size may wrap the end of +the buffer and be broken into two segments. + + +============================ +MEASURING POWER-OF-2 BUFFERS +============================ + +Calculation of the occupancy or the remaining capacity of an arbitrarily sized +circular buffer would normally be a slow operation, requiring the use of a +modulus (divide) instruction. However, if the buffer is of a power-of-2 size, +then a much quicker bitwise-AND instruction can be used instead. + +Linux provides a set of macros for handling power-of-2 circular buffers. These +can be made use of by: + + #include <linux/circ_buf.h> + +The macros are: + + (*) Measure the remaining capacity of a buffer: + + CIRC_SPACE(head_index, tail_index, buffer_size); + + This returns the amount of space left in the buffer[1] into which items + can be inserted. + + + (*) Measure the maximum consecutive immediate space in a buffer: + + CIRC_SPACE_TO_END(head_index, tail_index, buffer_size); + + This returns the amount of consecutive space left in the buffer[1] into + which items can be immediately inserted without having to wrap back to the + beginning of the buffer. + + + (*) Measure the occupancy of a buffer: + + CIRC_CNT(head_index, tail_index, buffer_size); + + This returns the number of items currently occupying a buffer[2]. + + + (*) Measure the non-wrapping occupancy of a buffer: + + CIRC_CNT_TO_END(head_index, tail_index, buffer_size); + + This returns the number of consecutive items[2] that can be extracted from + the buffer without having to wrap back to the beginning of the buffer. + + +Each of these macros will nominally return a value between 0 and buffer_size-1, +however: + + [1] CIRC_SPACE*() are intended to be used in the producer. To the producer + they will return a lower bound as the producer controls the head index, + but the consumer may still be depleting the buffer on another CPU and + moving the tail index. + + To the consumer it will show an upper bound as the producer may be busy + depleting the space. + + [2] CIRC_CNT*() are intended to be used in the consumer. To the consumer they + will return a lower bound as the consumer controls the tail index, but the + producer may still be filling the buffer on another CPU and moving the + head index. + + To the producer it will show an upper bound as the consumer may be busy + emptying the buffer. + + [3] To a third party, the order in which the writes to the indices by the + producer and consumer become visible cannot be guaranteed as they are + independent and may be made on different CPUs - so the result in such a + situation will merely be a guess, and may even be negative. + + +=========================================== +USING MEMORY BARRIERS WITH CIRCULAR BUFFERS +=========================================== + +By using memory barriers in conjunction with circular buffers, you can avoid +the need to: + + (1) use a single lock to govern access to both ends of the buffer, thus + allowing the buffer to be filled and emptied at the same time; and + + (2) use atomic counter operations. + +There are two sides to this: the producer that fills the buffer, and the +consumer that empties it. Only one thing should be filling a buffer at any one +time, and only one thing should be emptying a buffer at any one time, but the +two sides can operate simultaneously. + + +THE PRODUCER +------------ + +The producer will look something like this: + + spin_lock(&producer_lock); + + unsigned long head = buffer->head; + unsigned long tail = ACCESS_ONCE(buffer->tail); + + if (CIRC_SPACE(head, tail, buffer->size) >= 1) { + /* insert one item into the buffer */ + struct item *item = buffer[head]; + + produce_item(item); + + smp_wmb(); /* commit the item before incrementing the head */ + + buffer->head = (head + 1) & (buffer->size - 1); + + /* wake_up() will make sure that the head is committed before + * waking anyone up */ + wake_up(consumer); + } + + spin_unlock(&producer_lock); + +This will instruct the CPU that the contents of the new item must be written +before the head index makes it available to the consumer and then instructs the +CPU that the revised head index must be written before the consumer is woken. + +Note that wake_up() doesn't have to be the exact mechanism used, but whatever +is used must guarantee a (write) memory barrier between the update of the head +index and the change of state of the consumer, if a change of state occurs. + + +THE CONSUMER +------------ + +The consumer will look something like this: + + spin_lock(&consumer_lock); + + unsigned long head = ACCESS_ONCE(buffer->head); + unsigned long tail = buffer->tail; + + if (CIRC_CNT(head, tail, buffer->size) >= 1) { + /* read index before reading contents at that index */ + smp_read_barrier_depends(); + + /* extract one item from the buffer */ + struct item *item = buffer[tail]; + + consume_item(item); + + smp_mb(); /* finish reading descriptor before incrementing tail */ + + buffer->tail = (tail + 1) & (buffer->size - 1); + } + + spin_unlock(&consumer_lock); + +This will instruct the CPU to make sure the index is up to date before reading +the new item, and then it shall make sure the CPU has finished reading the item +before it writes the new tail pointer, which will erase the item. + + +Note the use of ACCESS_ONCE() in both algorithms to read the opposition index. +This prevents the compiler from discarding and reloading its cached value - +which some compilers will do across smp_read_barrier_depends(). This isn't +strictly needed if you can be sure that the opposition index will _only_ be +used the once. + + +=============== +FURTHER READING +=============== + +See also Documentation/memory-barriers.txt for a description of Linux's memory +barrier facilities. diff --git a/Documentation/connector/cn_test.c b/Documentation/connector/cn_test.c index b07add3467f..7764594778d 100644 --- a/Documentation/connector/cn_test.c +++ b/Documentation/connector/cn_test.c @@ -25,6 +25,7 @@ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/skbuff.h> +#include <linux/slab.h> #include <linux/timer.h> #include <linux/connector.h> diff --git a/Documentation/fb/imacfb.txt b/Documentation/fb/efifb.txt index 316ec9bb7de..a59916c29b3 100644 --- a/Documentation/fb/imacfb.txt +++ b/Documentation/fb/efifb.txt @@ -1,9 +1,9 @@ -What is imacfb? +What is efifb? =============== This is a generic EFI platform driver for Intel based Apple computers. -Imacfb is only for EFI booted Intel Macs. +efifb is only for EFI booted Intel Macs. Supported Hardware ================== @@ -16,16 +16,16 @@ MacMini How to use it? ============== -Imacfb does not have any kind of autodetection of your machine. +efifb does not have any kind of autodetection of your machine. You have to add the following kernel parameters in your elilo.conf: Macbook : - video=imacfb:macbook + video=efifb:macbook MacMini : - video=imacfb:mini + video=efifb:mini Macbook Pro 15", iMac 17" : - video=imacfb:i17 + video=efifb:i17 Macbook Pro 17", iMac 20" : - video=imacfb:i20 + video=efifb:i20 -- Edgar Hucek <gimli@dark-green.com> diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index ed511af0f79..05df0b7514b 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -589,3 +589,26 @@ Why: Useful in 2003, implementation is a hack. Generally invoked by accident today. Seen as doing more harm than good. Who: Len Brown <len.brown@intel.com> + +---------------------------- + +What: video4linux /dev/vtx teletext API support +When: 2.6.35 +Files: drivers/media/video/saa5246a.c drivers/media/video/saa5249.c + include/linux/videotext.h +Why: The vtx device nodes have been superseded by vbi device nodes + for many years. No applications exist that use the vtx support. + Of the two i2c drivers that actually support this API the saa5249 + has been impossible to use for a year now and no known hardware + that supports this device exists. The saa5246a is theoretically + supported by the old mxb boards, but it never actually worked. + + In summary: there is no hardware that can use this API and there + are no applications actually implementing this API. + + The vtx support still reserves minors 192-223 and we would really + like to reuse those for upcoming new functionality. In the unlikely + event that new hardware appears that wants to use the functionality + provided by the vtx API, then that functionality should be build + around the sliced VBI API instead. +Who: Hans Verkuil <hverkuil@xs4all.nl> diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX index 3bae418c6ad..4303614b5ad 100644 --- a/Documentation/filesystems/00-INDEX +++ b/Documentation/filesystems/00-INDEX @@ -16,6 +16,8 @@ befs.txt - information about the BeOS filesystem for Linux. bfs.txt - info for the SCO UnixWare Boot Filesystem (BFS). +ceph.txt + - info for the Ceph Distributed File System cifs.txt - description of the CIFS filesystem. coda.txt diff --git a/Documentation/filesystems/9p.txt b/Documentation/filesystems/9p.txt index 57e0b80a527..c0236e753bc 100644 --- a/Documentation/filesystems/9p.txt +++ b/Documentation/filesystems/9p.txt @@ -37,6 +37,15 @@ For Plan 9 From User Space applications (http://swtch.com/plan9) mount -t 9p `namespace`/acme /mnt/9 -o trans=unix,uname=$USER +For server running on QEMU host with virtio transport: + + mount -t 9p -o trans=virtio <mount_tag> /mnt/9 + +where mount_tag is the tag associated by the server to each of the exported +mount points. Each 9P export is seen by the client as a virtio device with an +associated "mount_tag" property. Available mount tags can be +seen by reading /sys/bus/virtio/drivers/9pnet_virtio/virtio<n>/mount_tag files. + OPTIONS ======= @@ -47,7 +56,7 @@ OPTIONS fd - used passed file descriptors for connection (see rfdno and wfdno) virtio - connect to the next virtio channel available - (from lguest or KVM with trans_virtio module) + (from QEMU with trans_virtio module) rdma - connect to a specified RDMA channel uname=name user name to attempt mount as on the remote server. The @@ -85,7 +94,12 @@ OPTIONS port=n port to connect to on the remote server - noextend force legacy mode (no 9p2000.u semantics) + noextend force legacy mode (no 9p2000.u or 9p2000.L semantics) + + version=name Select 9P protocol version. Valid options are: + 9p2000 - Legacy mode (same as noextend) + 9p2000.u - Use 9P2000.u protocol + 9p2000.L - Use 9P2000.L protocol dfltuid attempt to mount as a particular uid diff --git a/Documentation/filesystems/ceph.txt b/Documentation/filesystems/ceph.txt new file mode 100644 index 00000000000..0660c9f5dee --- /dev/null +++ b/Documentation/filesystems/ceph.txt @@ -0,0 +1,140 @@ +Ceph Distributed File System +============================ + +Ceph is a distributed network file system designed to provide good +performance, reliability, and scalability. + +Basic features include: + + * POSIX semantics + * Seamless scaling from 1 to many thousands of nodes + * High availability and reliability. No single point of failure. + * N-way replication of data across storage nodes + * Fast recovery from node failures + * Automatic rebalancing of data on node addition/removal + * Easy deployment: most FS components are userspace daemons + +Also, + * Flexible snapshots (on any directory) + * Recursive accounting (nested files, directories, bytes) + +In contrast to cluster filesystems like GFS, OCFS2, and GPFS that rely +on symmetric access by all clients to shared block devices, Ceph +separates data and metadata management into independent server +clusters, similar to Lustre. Unlike Lustre, however, metadata and +storage nodes run entirely as user space daemons. Storage nodes +utilize btrfs to store data objects, leveraging its advanced features +(checksumming, metadata replication, etc.). File data is striped +across storage nodes in large chunks to distribute workload and +facilitate high throughputs. When storage nodes fail, data is +re-replicated in a distributed fashion by the storage nodes themselves +(with some minimal coordination from a cluster monitor), making the +system extremely efficient and scalable. + +Metadata servers effectively form a large, consistent, distributed +in-memory cache above the file namespace that is extremely scalable, +dynamically redistributes metadata in response to workload changes, +and can tolerate arbitrary (well, non-Byzantine) node failures. The +metadata server takes a somewhat unconventional approach to metadata +storage to significantly improve performance for common workloads. In +particular, inodes with only a single link are embedded in +directories, allowing entire directories of dentries and inodes to be +loaded into its cache with a single I/O operation. The contents of +extremely large directories can be fragmented and managed by +independent metadata servers, allowing scalable concurrent access. + +The system offers automatic data rebalancing/migration when scaling +from a small cluster of just a few nodes to many hundreds, without +requiring an administrator carve the data set into static volumes or +go through the tedious process of migrating data between servers. +When the file system approaches full, new nodes can be easily added +and things will "just work." + +Ceph includes flexible snapshot mechanism that allows a user to create +a snapshot on any subdirectory (and its nested contents) in the +system. Snapshot creation and deletion are as simple as 'mkdir +.snap/foo' and 'rmdir .snap/foo'. + +Ceph also provides some recursive accounting on directories for nested +files and bytes. That is, a 'getfattr -d foo' on any directory in the +system will reveal the total number of nested regular files and +subdirectories, and a summation of all nested file sizes. This makes +the identification of large disk space consumers relatively quick, as +no 'du' or similar recursive scan of the file system is required. + + +Mount Syntax +============ + +The basic mount syntax is: + + # mount -t ceph monip[:port][,monip2[:port]...]:/[subdir] mnt + +You only need to specify a single monitor, as the client will get the +full list when it connects. (However, if the monitor you specify +happens to be down, the mount won't succeed.) The port can be left +off if the monitor is using the default. So if the monitor is at +1.2.3.4, + + # mount -t ceph 1.2.3.4:/ /mnt/ceph + +is sufficient. If /sbin/mount.ceph is installed, a hostname can be +used instead of an IP address. + + + +Mount Options +============= + + ip=A.B.C.D[:N] + Specify the IP and/or port the client should bind to locally. + There is normally not much reason to do this. If the IP is not + specified, the client's IP address is determined by looking at the + address it's connection to the monitor originates from. + + wsize=X + Specify the maximum write size in bytes. By default there is no + maximum. Ceph will normally size writes based on the file stripe + size. + + rsize=X + Specify the maximum readahead. + + mount_timeout=X + Specify the timeout value for mount (in seconds), in the case + of a non-responsive Ceph file system. The default is 30 + seconds. + + rbytes + When stat() is called on a directory, set st_size to 'rbytes', + the summation of file sizes over all files nested beneath that + directory. This is the default. + + norbytes + When stat() is called on a directory, set st_size to the + number of entries in that directory. + + nocrc + Disable CRC32C calculation for data writes. If set, the storage node + must rely on TCP's error correction to detect data corruption + in the data payload. + + noasyncreaddir + Disable client's use its local cache to satisfy readdir + requests. (This does not change correctness; the client uses + cached metadata only when a lease or capability ensures it is + valid.) + + +More Information +================ + +For more information on Ceph, see the home page at + http://ceph.newdream.net/ + +The Linux kernel client source tree is available at + git://ceph.newdream.net/git/ceph-client.git + git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git + +and the source for the full system is at + git://ceph.newdream.net/git/ceph.git diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index a4f30faa4f1..1e359b62c40 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -316,7 +316,7 @@ address perms offset dev inode pathname 08049000-0804a000 rw-p 00001000 03:00 8312 /opt/test 0804a000-0806b000 rw-p 00000000 00:00 0 [heap] a7cb1000-a7cb2000 ---p 00000000 00:00 0 -a7cb2000-a7eb2000 rw-p 00000000 00:00 0 [threadstack:001ff4b4] +a7cb2000-a7eb2000 rw-p 00000000 00:00 0 a7eb2000-a7eb3000 ---p 00000000 00:00 0 a7eb3000-a7ed5000 rw-p 00000000 00:00 0 a7ed5000-a8008000 r-xp 00000000 03:00 4222 /lib/libc.so.6 @@ -352,7 +352,6 @@ is not associated with a file: [stack] = the stack of the main process [vdso] = the "virtual dynamic shared object", the kernel system call handler - [threadstack:xxxxxxxx] = the stack of the thread, xxxxxxxx is the stack size or if empty, the mapping is anonymous. diff --git a/Documentation/filesystems/tmpfs.txt b/Documentation/filesystems/tmpfs.txt index 3015da0c6b2..fe09a2cb185 100644 --- a/Documentation/filesystems/tmpfs.txt +++ b/Documentation/filesystems/tmpfs.txt @@ -82,11 +82,13 @@ tmpfs has a mount option to set the NUMA memory allocation policy for all files in that instance (if CONFIG_NUMA is enabled) - which can be adjusted on the fly via 'mount -o remount ...' -mpol=default prefers to allocate memory from the local node +mpol=default use the process allocation policy + (see set_mempolicy(2)) mpol=prefer:Node prefers to allocate memory from the given Node mpol=bind:NodeList allocates memory only from nodes in NodeList mpol=interleave prefers to allocate from each node in turn mpol=interleave:NodeList allocates from each node of NodeList in turn +mpol=local prefers to allocate memory from the local node NodeList format is a comma-separated list of decimal numbers and ranges, a range being two hyphen-separated decimal numbers, the smallest and @@ -134,3 +136,5 @@ Author: Christoph Rohland <cr@sap.com>, 1.12.01 Updated: Hugh Dickins, 4 June 2007 +Updated: + KOSAKI Motohiro, 16 Mar 2010 diff --git a/Documentation/i2c/writing-clients b/Documentation/i2c/writing-clients index 3219ee0dbfe..5ebf5af1d71 100644 --- a/Documentation/i2c/writing-clients +++ b/Documentation/i2c/writing-clients @@ -74,6 +74,11 @@ structure at all. You should use this to keep device-specific data. /* retrieve the value */ void *i2c_get_clientdata(const struct i2c_client *client); +Note that starting with kernel 2.6.34, you don't have to set the `data' field +to NULL in remove() or if probe() failed anymore. The i2c-core does this +automatically on these occasions. Those are also the only times the core will +touch this field. + Accessing the client ==================== diff --git a/Documentation/input/elantech.txt b/Documentation/input/elantech.txt index a10c3b6ba7c..56941ae1f5d 100644 --- a/Documentation/input/elantech.txt +++ b/Documentation/input/elantech.txt @@ -333,14 +333,14 @@ byte 0: byte 1: bit 7 6 5 4 3 2 1 0 - x15 x14 x13 x12 x11 x10 x9 x8 + . . . . . x10 x9 x8 byte 2: bit 7 6 5 4 3 2 1 0 x7 x6 x5 x4 x4 x2 x1 x0 - x15..x0 = absolute x value (horizontal) + x10..x0 = absolute x value (horizontal) byte 3: @@ -350,14 +350,14 @@ byte 3: byte 4: bit 7 6 5 4 3 2 1 0 - y15 y14 y13 y12 y11 y10 y8 y8 + . . . . . . y9 y8 byte 5: bit 7 6 5 4 3 2 1 0 y7 y6 y5 y4 y3 y2 y1 y0 - y15..y0 = absolute y value (vertical) + y9..y0 = absolute y value (vertical) 4.2.2 Two finger touch diff --git a/Documentation/input/multi-touch-protocol.txt b/Documentation/input/multi-touch-protocol.txt index 8490480ce43..c0fc1c75fd8 100644 --- a/Documentation/input/multi-touch-protocol.txt +++ b/Documentation/input/multi-touch-protocol.txt @@ -68,6 +68,22 @@ like: SYN_MT_REPORT SYN_REPORT +Here is the sequence after lifting one of the fingers: + + ABS_MT_POSITION_X + ABS_MT_POSITION_Y + SYN_MT_REPORT + SYN_REPORT + +And here is the sequence after lifting the remaining finger: + + SYN_MT_REPORT + SYN_REPORT + +If the driver reports one of BTN_TOUCH or ABS_PRESSURE in addition to the +ABS_MT events, the last SYN_MT_REPORT event may be omitted. Otherwise, the +last SYN_REPORT will be dropped by the input core, resulting in no +zero-finger event reaching userland. Event Semantics --------------- @@ -217,11 +233,6 @@ where examples can be found. difference between the contact position and the approaching tool position could be used to derive tilt. [2] The list can of course be extended. -[3] The multi-touch X driver is currently in the prototyping stage. At the -time of writing (April 2009), the MT protocol is not yet merged, and the -prototype implements finger matching, basic mouse support and two-finger -scrolling. The project aims at improving the quality of current multi-touch -functionality available in the Synaptics X driver, and in addition -implement more advanced gestures. +[3] Multitouch X driver project: http://bitmath.org/code/multitouch/. [4] See the section on event computation. [5] See the section on finger tracking. diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt index 35c9b51d20e..dd5806f4fcc 100644 --- a/Documentation/ioctl/ioctl-number.txt +++ b/Documentation/ioctl/ioctl-number.txt @@ -291,6 +291,7 @@ Code Seq#(hex) Include File Comments 0x92 00-0F drivers/usb/mon/mon_bin.c 0x93 60-7F linux/auto_fs.h 0x94 all fs/btrfs/ioctl.h +0x97 00-7F fs/ceph/ioctl.h Ceph file system 0x99 00-0F 537-Addinboard driver <mailto:buk@buks.ipn.de> 0xA0 all linux/sdp/sdp.h Industrial Device Project diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index e4cbca58536..567b7a8eb87 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -320,15 +320,12 @@ and is between 256 and 4096 characters. It is defined in the file amd_iommu= [HW,X86-84] Pass parameters to the AMD IOMMU driver in the system. Possible values are: - isolate - enable device isolation (each device, as far - as possible, will get its own protection - domain) [default] - share - put every device behind one IOMMU into the - same protection domain fullflush - enable flushing of IO/TLB entries when they are unmapped. Otherwise they are flushed before they will be reused, which is a lot of faster + off - do not initialize any AMD IOMMU found in + the system amijoy.map= [HW,JOY] Amiga joystick support Map of devices attached to JOY0DAT and JOY1DAT @@ -789,8 +786,12 @@ and is between 256 and 4096 characters. It is defined in the file as early as possible in order to facilitate early boot debugging. - ftrace_dump_on_oops + ftrace_dump_on_oops[=orig_cpu] [FTRACE] will dump the trace buffers on oops. + If no parameter is passed, ftrace will dump + buffers of all CPUs, but if you pass orig_cpu, it will + dump only the buffer of the CPU that triggered the + oops. ftrace_filter=[function-list] [FTRACE] Limit the functions traced by the function @@ -1199,7 +1200,7 @@ and is between 256 and 4096 characters. It is defined in the file libata.force= [LIBATA] Force configurations. The format is comma separated list of "[ID:]VAL" where ID is - PORT[:DEVICE]. PORT and DEVICE are decimal numbers + PORT[.DEVICE]. PORT and DEVICE are decimal numbers matching port, link or device. Basically, it matches the ATA ID string printed on console by libata. If the whole ID part is omitted, the last PORT and DEVICE diff --git a/Documentation/kobject.txt b/Documentation/kobject.txt index bdb13817e1e..3ab2472509c 100644 --- a/Documentation/kobject.txt +++ b/Documentation/kobject.txt @@ -59,37 +59,56 @@ nice to have in other objects. The C language does not allow for the direct expression of inheritance, so other techniques - such as structure embedding - must be used. -So, for example, the UIO code has a structure that defines the memory -region associated with a uio device: +(As an aside, for those familiar with the kernel linked list implementation, +this is analogous as to how "list_head" structs are rarely useful on +their own, but are invariably found embedded in the larger objects of +interest.) -struct uio_mem { +So, for example, the UIO code in drivers/uio/uio.c has a structure that +defines the memory region associated with a uio device: + + struct uio_map { struct kobject kobj; - unsigned long addr; - unsigned long size; - int memtype; - void __iomem *internal_addr; -}; + struct uio_mem *mem; + }; -If you have a struct uio_mem structure, finding its embedded kobject is +If you have a struct uio_map structure, finding its embedded kobject is just a matter of using the kobj member. Code that works with kobjects will often have the opposite problem, however: given a struct kobject pointer, what is the pointer to the containing structure? You must avoid tricks (such as assuming that the kobject is at the beginning of the structure) and, instead, use the container_of() macro, found in <linux/kernel.h>: - container_of(pointer, type, member) + container_of(pointer, type, member) + +where: + + * "pointer" is the pointer to the embedded kobject, + * "type" is the type of the containing structure, and + * "member" is the name of the structure field to which "pointer" points. + +The return value from container_of() is a pointer to the corresponding +container type. So, for example, a pointer "kp" to a struct kobject +embedded *within* a struct uio_map could be converted to a pointer to the +*containing* uio_map structure with: + + struct uio_map *u_map = container_of(kp, struct uio_map, kobj); + +For convenience, programmers often define a simple macro for "back-casting" +kobject pointers to the containing type. Exactly this happens in the +earlier drivers/uio/uio.c, as you can see here: + + struct uio_map { + struct kobject kobj; + struct uio_mem *mem; + }; -where pointer is the pointer to the embedded kobject, type is the type of -the containing structure, and member is the name of the structure field to -which pointer points. The return value from container_of() is a pointer to -the given type. So, for example, a pointer "kp" to a struct kobject -embedded within a struct uio_mem could be converted to a pointer to the -containing uio_mem structure with: + #define to_map(map) container_of(map, struct uio_map, kobj) - struct uio_mem *u_mem = container_of(kp, struct uio_mem, kobj); +where the macro argument "map" is a pointer to the struct kobject in +question. That macro is subsequently invoked with: -Programmers often define a simple macro for "back-casting" kobject pointers -to the containing type. + struct uio_map *map = to_map(kobj); Initialization of kobjects @@ -387,4 +406,5 @@ called, and the objects in the former circle release each other. Example code to copy from For a more complete example of using ksets and kobjects properly, see the -sample/kobject/kset-example.c code. +example programs samples/kobject/{kobject-example.c,kset-example.c}, +which will be built as loadable modules if you select CONFIG_SAMPLE_KOBJECT. diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt index 2f9115c0ae6..61c291cddf1 100644 --- a/Documentation/kprobes.txt +++ b/Documentation/kprobes.txt @@ -165,8 +165,8 @@ the user entry_handler invocation is also skipped. 1.4 How Does Jump Optimization Work? -If you configured your kernel with CONFIG_OPTPROBES=y (currently -this option is supported on x86/x86-64, non-preemptive kernel) and +If your kernel is built with CONFIG_OPTPROBES=y (currently this flag +is automatically set 'y' on x86/x86-64, non-preemptive kernel) and the "debug.kprobes_optimization" kernel parameter is set to 1 (see sysctl(8)), Kprobes tries to reduce probe-hit overhead by using a jump instruction instead of a breakpoint instruction at each probepoint. @@ -271,8 +271,6 @@ tweak the kernel's execution path, you need to suppress optimization, using one of the following techniques: - Specify an empty function for the kprobe's post_handler or break_handler. or -- Config CONFIG_OPTPROBES=n. - or - Execute 'sysctl -w debug.kprobes_optimization=n' 2. Architectures Supported @@ -307,10 +305,6 @@ it useful to "Compile the kernel with debug info" (CONFIG_DEBUG_INFO), so you can use "objdump -d -l vmlinux" to see the source-to-object code mapping. -If you want to reduce probing overhead, set "Kprobes jump optimization -support" (CONFIG_OPTPROBES) to "y". You can find this option under the -"Kprobes" line. - 4. API Reference The Kprobes API includes a "register" function and an "unregister" diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt index 7f5809eddee..631ad2f1b22 100644 --- a/Documentation/memory-barriers.txt +++ b/Documentation/memory-barriers.txt @@ -3,6 +3,7 @@ ============================ By: David Howells <dhowells@redhat.com> + Paul E. McKenney <paulmck@linux.vnet.ibm.com> Contents: @@ -60,6 +61,10 @@ Contents: - And then there's the Alpha. + (*) Example uses. + + - Circular buffers. + (*) References. @@ -2226,6 +2231,21 @@ The Alpha defines the Linux kernel's memory barrier model. See the subsection on "Cache Coherency" above. +============ +EXAMPLE USES +============ + +CIRCULAR BUFFERS +---------------- + +Memory barriers can be used to implement circular buffering without the need +of a lock to serialise the producer with the consumer. See: + + Documentation/circular-buffers.txt + +for details. + + ========== REFERENCES ========== diff --git a/Documentation/networking/Makefile b/Documentation/networking/Makefile index 6d8af1ac56c..5aba7a33aee 100644 --- a/Documentation/networking/Makefile +++ b/Documentation/networking/Makefile @@ -6,3 +6,5 @@ hostprogs-y := ifenslave # Tell kbuild to always build the programs always := $(hostprogs-y) + +obj-m := timestamping/ diff --git a/Documentation/networking/stmmac.txt b/Documentation/networking/stmmac.txt new file mode 100644 index 00000000000..7ee770b5ef5 --- /dev/null +++ b/Documentation/networking/stmmac.txt @@ -0,0 +1,143 @@ + STMicroelectronics 10/100/1000 Synopsys Ethernet driver + +Copyright (C) 2007-2010 STMicroelectronics Ltd +Author: Giuseppe Cavallaro <peppe.cavallaro@st.com> + +This is the driver for the MAC 10/100/1000 on-chip Ethernet controllers +(Synopsys IP blocks); it has been fully tested on STLinux platforms. + +Currently this network device driver is for all STM embedded MAC/GMAC +(7xxx SoCs). + +DWC Ether MAC 10/100/1000 Universal version 3.41a and DWC Ether MAC 10/100 +Universal version 4.0 have been used for developing the first code +implementation. + +Please, for more information also visit: www.stlinux.com + +1) Kernel Configuration +The kernel configuration option is STMMAC_ETH: + Device Drivers ---> Network device support ---> Ethernet (1000 Mbit) ---> + STMicroelectronics 10/100/1000 Ethernet driver (STMMAC_ETH) + +2) Driver parameters list: + debug: message level (0: no output, 16: all); + phyaddr: to manually provide the physical address to the PHY device; + dma_rxsize: DMA rx ring size; + dma_txsize: DMA tx ring size; + buf_sz: DMA buffer size; + tc: control the HW FIFO threshold; + tx_coe: Enable/Disable Tx Checksum Offload engine; + watchdog: transmit timeout (in milliseconds); + flow_ctrl: Flow control ability [on/off]; + pause: Flow Control Pause Time; + tmrate: timer period (only if timer optimisation is configured). + +3) Command line options +Driver parameters can be also passed in command line by using: + stmmaceth=dma_rxsize:128,dma_txsize:512 + +4) Driver information and notes + +4.1) Transmit process +The xmit method is invoked when the kernel needs to transmit a packet; it sets +the descriptors in the ring and informs the DMA engine that there is a packet +ready to be transmitted. +Once the controller has finished transmitting the packet, an interrupt is +triggered; So the driver will be able to release the socket buffers. +By default, the driver sets the NETIF_F_SG bit in the features field of the +net_device structure enabling the scatter/gather feature. + +4.2) Receive process +When one or more packets are received, an interrupt happens. The interrupts +are not queued so the driver has to scan all the descriptors in the ring during +the receive process. +This is based on NAPI so the interrupt handler signals only if there is work to be +done, and it exits. +Then the poll method will be scheduled at some future point. +The incoming packets are stored, by the DMA, in a list of pre-allocated socket +buffers in order to avoid the memcpy (Zero-copy). + +4.3) Timer-Driver Interrupt +Instead of having the device that asynchronously notifies the frame receptions, the +driver configures a timer to generate an interrupt at regular intervals. +Based on the granularity of the timer, the frames that are received by the device +will experience different levels of latency. Some NICs have dedicated timer +device to perform this task. STMMAC can use either the RTC device or the TMU +channel 2 on STLinux platforms. +The timers frequency can be passed to the driver as parameter; when change it, +take care of both hardware capability and network stability/performance impact. +Several performance tests on STM platforms showed this optimisation allows to spare +the CPU while having the maximum throughput. + +4.4) WOL +Wake up on Lan feature through Magic Frame is only supported for the GMAC +core. + +4.5) DMA descriptors +Driver handles both normal and enhanced descriptors. The latter has been only +tested on DWC Ether MAC 10/100/1000 Universal version 3.41a. + +4.6) Ethtool support +Ethtool is supported. Driver statistics and internal errors can be taken using: +ethtool -S ethX command. It is possible to dump registers etc. + +4.7) Jumbo and Segmentation Offloading +Jumbo frames are supported and tested for the GMAC. +The GSO has been also added but it's performed in software. +LRO is not supported. + +4.8) Physical +The driver is compatible with PAL to work with PHY and GPHY devices. + +4.9) Platform information +Several information came from the platform; please refer to the +driver's Header file in include/linux directory. + +struct plat_stmmacenet_data { + int bus_id; + int pbl; + int has_gmac; + void (*fix_mac_speed)(void *priv, unsigned int speed); + void (*bus_setup)(unsigned long ioaddr); +#ifdef CONFIG_STM_DRIVERS + struct stm_pad_config *pad_config; +#endif + void *bsp_priv; +}; + +Where: +- pbl (Programmable Burst Length) is maximum number of + beats to be transferred in one DMA transaction. + GMAC also enables the 4xPBL by default. +- fix_mac_speed and bus_setup are used to configure internal target + registers (on STM platforms); +- has_gmac: GMAC core is on board (get it at run-time in the next step); +- bus_id: bus identifier. + +struct plat_stmmacphy_data { + int bus_id; + int phy_addr; + unsigned int phy_mask; + int interface; + int (*phy_reset)(void *priv); + void *priv; +}; + +Where: +- bus_id: bus identifier; +- phy_addr: physical address used for the attached phy device; + set it to -1 to get it at run-time; +- interface: physical MII interface mode; +- phy_reset: hook to reset HW function. + +TODO: +- Continue to make the driver more generic and suitable for other Synopsys + Ethernet controllers used on other architectures (i.e. ARM). +- 10G controllers are not supported. +- MAC uses Normal descriptors and GMAC uses enhanced ones. + This is a limit that should be reviewed. MAC could want to + use the enhanced structure. +- Checksumming: Rx/Tx csum is done in HW in case of GMAC only. +- Review the timer optimisation code to use an embedded device that seems to be + available in new chip generations. diff --git a/Documentation/networking/timestamping.txt b/Documentation/networking/timestamping.txt index 0e58b453917..e8c8f4f06c6 100644 --- a/Documentation/networking/timestamping.txt +++ b/Documentation/networking/timestamping.txt @@ -41,11 +41,12 @@ SOF_TIMESTAMPING_SOFTWARE: return system time stamp generated in SOF_TIMESTAMPING_TX/RX determine how time stamps are generated. SOF_TIMESTAMPING_RAW/SYS determine how they are reported in the following control message: - struct scm_timestamping { - struct timespec systime; - struct timespec hwtimetrans; - struct timespec hwtimeraw; - }; + +struct scm_timestamping { + struct timespec systime; + struct timespec hwtimetrans; + struct timespec hwtimeraw; +}; recvmsg() can be used to get this control message for regular incoming packets. For send time stamps the outgoing packet is looped back to @@ -87,12 +88,13 @@ by the network device and will be empty without that support. SIOCSHWTSTAMP: Hardware time stamping must also be initialized for each device driver -that is expected to do hardware time stamping. The parameter is: +that is expected to do hardware time stamping. The parameter is defined in +/include/linux/net_tstamp.h as: struct hwtstamp_config { - int flags; /* no flags defined right now, must be zero */ - int tx_type; /* HWTSTAMP_TX_* */ - int rx_filter; /* HWTSTAMP_FILTER_* */ + int flags; /* no flags defined right now, must be zero */ + int tx_type; /* HWTSTAMP_TX_* */ + int rx_filter; /* HWTSTAMP_FILTER_* */ }; Desired behavior is passed into the kernel and to a specific device by @@ -139,42 +141,56 @@ enum { /* time stamp any incoming packet */ HWTSTAMP_FILTER_ALL, - /* return value: time stamp all packets requested plus some others */ - HWTSTAMP_FILTER_SOME, + /* return value: time stamp all packets requested plus some others */ + HWTSTAMP_FILTER_SOME, /* PTP v1, UDP, any kind of event packet */ HWTSTAMP_FILTER_PTP_V1_L4_EVENT, - ... + /* for the complete list of values, please check + * the include file /include/linux/net_tstamp.h + */ }; DEVICE IMPLEMENTATION A driver which supports hardware time stamping must support the -SIOCSHWTSTAMP ioctl. Time stamps for received packets must be stored -in the skb with skb_hwtstamp_set(). +SIOCSHWTSTAMP ioctl and update the supplied struct hwtstamp_config with +the actual values as described in the section on SIOCSHWTSTAMP. + +Time stamps for received packets must be stored in the skb. To get a pointer +to the shared time stamp structure of the skb call skb_hwtstamps(). Then +set the time stamps in the structure: + +struct skb_shared_hwtstamps { + /* hardware time stamp transformed into duration + * since arbitrary point in time + */ + ktime_t hwtstamp; + ktime_t syststamp; /* hwtstamp transformed to system time base */ +}; Time stamps for outgoing packets are to be generated as follows: -- In hard_start_xmit(), check if skb_hwtstamp_check_tx_hardware() - returns non-zero. If yes, then the driver is expected - to do hardware time stamping. +- In hard_start_xmit(), check if skb_tx(skb)->hardware is set no-zero. + If yes, then the driver is expected to do hardware time stamping. - If this is possible for the skb and requested, then declare - that the driver is doing the time stamping by calling - skb_hwtstamp_tx_in_progress(). A driver not supporting - hardware time stamping doesn't do that. A driver must never - touch sk_buff::tstamp! It is used to store how time stamping - for an outgoing packets is to be done. + that the driver is doing the time stamping by setting the field + skb_tx(skb)->in_progress non-zero. You might want to keep a pointer + to the associated skb for the next step and not free the skb. A driver + not supporting hardware time stamping doesn't do that. A driver must + never touch sk_buff::tstamp! It is used to store software generated + time stamps by the network subsystem. - As soon as the driver has sent the packet and/or obtained a hardware time stamp for it, it passes the time stamp back by calling skb_hwtstamp_tx() with the original skb, the raw - hardware time stamp and a handle to the device (necessary - to convert the hardware time stamp to system time). If obtaining - the hardware time stamp somehow fails, then the driver should - not fall back to software time stamping. The rationale is that - this would occur at a later time in the processing pipeline - than other software time stamping and therefore could lead - to unexpected deltas between time stamps. -- If the driver did not call skb_hwtstamp_tx_in_progress(), then + hardware time stamp. skb_hwtstamp_tx() clones the original skb and + adds the timestamps, therefore the original skb has to be freed now. + If obtaining the hardware time stamp somehow fails, then the driver + should not fall back to software time stamping. The rationale is that + this would occur at a later time in the processing pipeline than other + software time stamping and therefore could lead to unexpected deltas + between time stamps. +- If the driver did not call set skb_tx(skb)->in_progress, then dev_hard_start_xmit() checks whether software time stamping is wanted as fallback and potentially generates the time stamp. diff --git a/Documentation/networking/timestamping/Makefile b/Documentation/networking/timestamping/Makefile index 2a1489fdc03..e79973443e9 100644 --- a/Documentation/networking/timestamping/Makefile +++ b/Documentation/networking/timestamping/Makefile @@ -1,6 +1,13 @@ -CPPFLAGS = -I../../../include +# kbuild trick to avoid linker error. Can be omitted if a module is built. +obj- := dummy.o -timestamping: timestamping.c +# List of programs to build +hostprogs-y := timestamping + +# Tell kbuild to always build the programs +always := $(hostprogs-y) + +HOSTCFLAGS_timestamping.o += -I$(objtree)/usr/include clean: rm -f timestamping diff --git a/Documentation/networking/timestamping/timestamping.c b/Documentation/networking/timestamping/timestamping.c index bab619a4821..8ba82bfe6a3 100644 --- a/Documentation/networking/timestamping/timestamping.c +++ b/Documentation/networking/timestamping/timestamping.c @@ -41,9 +41,9 @@ #include <arpa/inet.h> #include <net/if.h> -#include "asm/types.h" -#include "linux/net_tstamp.h" -#include "linux/errqueue.h" +#include <asm/types.h> +#include <linux/net_tstamp.h> +#include <linux/errqueue.h> #ifndef SO_TIMESTAMPING # define SO_TIMESTAMPING 37 @@ -164,7 +164,7 @@ static void printpacket(struct msghdr *msg, int res, gettimeofday(&now, 0); - printf("%ld.%06ld: received %s data, %d bytes from %s, %d bytes control messages\n", + printf("%ld.%06ld: received %s data, %d bytes from %s, %zu bytes control messages\n", (long)now.tv_sec, (long)now.tv_usec, (recvmsg_flags & MSG_ERRQUEUE) ? "error" : "regular", res, @@ -173,7 +173,7 @@ static void printpacket(struct msghdr *msg, int res, for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) { - printf(" cmsg len %d: ", cmsg->cmsg_len); + printf(" cmsg len %zu: ", cmsg->cmsg_len); switch (cmsg->cmsg_level) { case SOL_SOCKET: printf("SOL_SOCKET "); diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe.txt b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe.txt index 6e37be1eeb2..4f8930263dd 100644 --- a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe.txt +++ b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe.txt @@ -21,6 +21,15 @@ Required properties: - fsl,qe-num-snums: define how many serial number(SNUM) the QE can use for the threads. +Optional properties: +- fsl,firmware-phandle: + Usage: required only if there is no fsl,qe-firmware child node + Value type: <phandle> + Definition: Points to a firmware node (see "QE Firmware Node" below) + that contains the firmware that should be uploaded for this QE. + The compatible property for the firmware node should say, + "fsl,qe-firmware". + Recommended properties - brg-frequency : the internal clock source frequency for baud-rate generators in Hz. @@ -59,3 +68,48 @@ Example: reg = <0 c000>; }; }; + +* QE Firmware Node + +This node defines a firmware binary that is embedded in the device tree, for +the purpose of passing the firmware from bootloader to the kernel, or from +the hypervisor to the guest. + +The firmware node itself contains the firmware binary contents, a compatible +property, and any firmware-specific properties. The node should be placed +inside a QE node that needs it. Doing so eliminates the need for a +fsl,firmware-phandle property. Other QE nodes that need the same firmware +should define an fsl,firmware-phandle property that points to the firmware node +in the first QE node. + +The fsl,firmware property can be specified in the DTS (possibly using incbin) +or can be inserted by the boot loader at boot time. + +Required properties: + - compatible + Usage: required + Value type: <string> + Definition: A standard property. Specify a string that indicates what + kind of firmware it is. For QE, this should be "fsl,qe-firmware". + + - fsl,firmware + Usage: required + Value type: <prop-encoded-array>, encoded as an array of bytes + Definition: A standard property. This property contains the firmware + binary "blob". + +Example: + qe1@e0080000 { + compatible = "fsl,qe"; + qe_firmware:qe-firmware { + compatible = "fsl,qe-firmware"; + fsl,firmware = [0x70 0xcd 0x00 0x00 0x01 0x46 0x45 ...]; + }; + ... + }; + + qe2@e0090000 { + compatible = "fsl,qe"; + fsl,firmware-phandle = <&qe_firmware>; + ... + }; diff --git a/Documentation/rbtree.txt b/Documentation/rbtree.txt index aae8355d316..221f38be98f 100644 --- a/Documentation/rbtree.txt +++ b/Documentation/rbtree.txt @@ -190,3 +190,61 @@ Example: for (node = rb_first(&mytree); node; node = rb_next(node)) printk("key=%s\n", rb_entry(node, struct mytype, node)->keystring); +Support for Augmented rbtrees +----------------------------- + +Augmented rbtree is an rbtree with "some" additional data stored in each node. +This data can be used to augment some new functionality to rbtree. +Augmented rbtree is an optional feature built on top of basic rbtree +infrastructure. rbtree user who wants this feature will have an augment +callback function in rb_root initialized. + +This callback function will be called from rbtree core routines whenever +a node has a change in one or both of its children. It is the responsibility +of the callback function to recalculate the additional data that is in the +rb node using new children information. Note that if this new additional +data affects the parent node's additional data, then callback function has +to handle it and do the recursive updates. + + +Interval tree is an example of augmented rb tree. Reference - +"Introduction to Algorithms" by Cormen, Leiserson, Rivest and Stein. +More details about interval trees: + +Classical rbtree has a single key and it cannot be directly used to store +interval ranges like [lo:hi] and do a quick lookup for any overlap with a new +lo:hi or to find whether there is an exact match for a new lo:hi. + +However, rbtree can be augmented to store such interval ranges in a structured +way making it possible to do efficient lookup and exact match. + +This "extra information" stored in each node is the maximum hi +(max_hi) value among all the nodes that are its descendents. This +information can be maintained at each node just be looking at the node +and its immediate children. And this will be used in O(log n) lookup +for lowest match (lowest start address among all possible matches) +with something like: + +find_lowest_match(lo, hi, node) +{ + lowest_match = NULL; + while (node) { + if (max_hi(node->left) > lo) { + // Lowest overlap if any must be on left side + node = node->left; + } else if (overlap(lo, hi, node)) { + lowest_match = node; + break; + } else if (lo > node->lo) { + // Lowest overlap if any must be on right side + node = node->right; + } else { + break; + } + } + return lowest_match; +} + +Finding exact match will be to first find lowest match and then to follow +successor nodes looking for exact match, until the start of a node is beyond +the hi value we are looking for. diff --git a/Documentation/scheduler/sched-design-CFS.txt b/Documentation/scheduler/sched-design-CFS.txt index 6f33593e59e..8239ebbcddc 100644 --- a/Documentation/scheduler/sched-design-CFS.txt +++ b/Documentation/scheduler/sched-design-CFS.txt @@ -211,7 +211,7 @@ provide fair CPU time to each such task group. For example, it may be desirable to first provide fair CPU time to each user on the system and then to each task belonging to a user. -CONFIG_GROUP_SCHED strives to achieve exactly that. It lets tasks to be +CONFIG_CGROUP_SCHED strives to achieve exactly that. It lets tasks to be grouped and divides CPU time fairly among such groups. CONFIG_RT_GROUP_SCHED permits to group real-time (i.e., SCHED_FIFO and @@ -220,38 +220,11 @@ SCHED_RR) tasks. CONFIG_FAIR_GROUP_SCHED permits to group CFS (i.e., SCHED_NORMAL and SCHED_BATCH) tasks. -At present, there are two (mutually exclusive) mechanisms to group tasks for -CPU bandwidth control purposes: - - - Based on user id (CONFIG_USER_SCHED) - - With this option, tasks are grouped according to their user id. - - - Based on "cgroup" pseudo filesystem (CONFIG_CGROUP_SCHED) - - This options needs CONFIG_CGROUPS to be defined, and lets the administrator + These options need CONFIG_CGROUPS to be defined, and let the administrator create arbitrary groups of tasks, using the "cgroup" pseudo filesystem. See Documentation/cgroups/cgroups.txt for more information about this filesystem. -Only one of these options to group tasks can be chosen and not both. - -When CONFIG_USER_SCHED is defined, a directory is created in sysfs for each new -user and a "cpu_share" file is added in that directory. - - # cd /sys/kernel/uids - # cat 512/cpu_share # Display user 512's CPU share - 1024 - # echo 2048 > 512/cpu_share # Modify user 512's CPU share - # cat 512/cpu_share # Display user 512's CPU share - 2048 - # - -CPU bandwidth between two users is divided in the ratio of their CPU shares. -For example: if you would like user "root" to get twice the bandwidth of user -"guest," then set the cpu_share for both the users such that "root"'s cpu_share -is twice "guest"'s cpu_share. - -When CONFIG_CGROUP_SCHED is defined, a "cpu.shares" file is created for each +When CONFIG_FAIR_GROUP_SCHED is defined, a "cpu.shares" file is created for each group created using the pseudo filesystem. See example steps below to create task groups and modify their CPU share using the "cgroups" pseudo filesystem. @@ -273,24 +246,3 @@ task groups and modify their CPU share using the "cgroups" pseudo filesystem. # #Launch gmplayer (or your favourite movie player) # echo <movie_player_pid> > multimedia/tasks - -8. Implementation note: user namespaces - -User namespaces are intended to be hierarchical. But they are currently -only partially implemented. Each of those has ramifications for CFS. - -First, since user namespaces are hierarchical, the /sys/kernel/uids -presentation is inadequate. Eventually we will likely want to use sysfs -tagging to provide private views of /sys/kernel/uids within each user -namespace. - -Second, the hierarchical nature is intended to support completely -unprivileged use of user namespaces. So if using user groups, then -we want the users in a user namespace to be children of the user -who created it. - -That is currently unimplemented. So instead, every user in a new -user namespace will receive 1024 shares just like any user in the -initial user namespace. Note that at the moment creation of a new -user namespace requires each of CAP_SYS_ADMIN, CAP_SETUID, and -CAP_SETGID. diff --git a/Documentation/scheduler/sched-rt-group.txt b/Documentation/scheduler/sched-rt-group.txt index 86eabe6c341..605b0d40329 100644 --- a/Documentation/scheduler/sched-rt-group.txt +++ b/Documentation/scheduler/sched-rt-group.txt @@ -126,23 +126,12 @@ priority! 2.3 Basis for grouping tasks ---------------------------- -There are two compile-time settings for allocating CPU bandwidth. These are -configured using the "Basis for grouping tasks" multiple choice menu under -General setup > Group CPU Scheduler: - -a. CONFIG_USER_SCHED (aka "Basis for grouping tasks" = "user id") - -This lets you use the virtual files under -"/sys/kernel/uids/<uid>/cpu_rt_runtime_us" to control he CPU time reserved for -each user . - -The other option is: - -.o CONFIG_CGROUP_SCHED (aka "Basis for grouping tasks" = "Control groups") +Enabling CONFIG_RT_GROUP_SCHED lets you explicitly allocate real +CPU bandwidth to task groups. This uses the /cgroup virtual file system and "/cgroup/<cgroup>/cpu.rt_runtime_us" to control the CPU time reserved for each -control group instead. +control group. For more information on working with control groups, you should read Documentation/cgroups/cgroups.txt as well. @@ -161,8 +150,7 @@ For now, this can be simplified to just the following (but see Future plans): =============== There is work in progress to make the scheduling period for each group -("/sys/kernel/uids/<uid>/cpu_rt_period_us" or -"/cgroup/<cgroup>/cpu.rt_period_us" respectively) configurable as well. +("/cgroup/<cgroup>/cpu.rt_period_us") configurable as well. The constraint on the period is that a subgroup must have a smaller or equal period to its parent. But realistically its not very useful _yet_ diff --git a/Documentation/sound/alsa/HD-Audio.txt b/Documentation/sound/alsa/HD-Audio.txt index f4dd3bf99d1..98d14cb8a85 100644 --- a/Documentation/sound/alsa/HD-Audio.txt +++ b/Documentation/sound/alsa/HD-Audio.txt @@ -119,10 +119,18 @@ the codec slots 0 and 1 no matter what the hardware reports. Interrupt Handling ~~~~~~~~~~~~~~~~~~ -In rare but some cases, the interrupt isn't properly handled as -default. You would notice this by the DMA transfer error reported by -ALSA PCM core, for example. Using MSI might help in such a case. -Pass `enable_msi=1` option for enabling MSI. +HD-audio driver uses MSI as default (if available) since 2.6.33 +kernel as MSI works better on some machines, and in general, it's +better for performance. However, Nvidia controllers showed bad +regressions with MSI (especially in a combination with AMD chipset), +thus we disabled MSI for them. + +There seem also still other devices that don't work with MSI. If you +see a regression wrt the sound quality (stuttering, etc) or a lock-up +in the recent kernel, try to pass `enable_msi=0` option to disable +MSI. If it works, you can add the known bad device to the blacklist +defined in hda_intel.c. In such a case, please report and give the +patch back to the upstream developer. HD-AUDIO CODEC diff --git a/Documentation/spi/spidev_test.c b/Documentation/spi/spidev_test.c index 10abd3773e4..16feda90146 100644 --- a/Documentation/spi/spidev_test.c +++ b/Documentation/spi/spidev_test.c @@ -58,7 +58,7 @@ static void transfer(int fd) }; ret = ioctl(fd, SPI_IOC_MESSAGE(1), &tr); - if (ret == 1) + if (ret < 1) pabort("can't send spi message"); for (ret = 0; ret < ARRAY_SIZE(tx); ret++) { diff --git a/Documentation/stable_kernel_rules.txt b/Documentation/stable_kernel_rules.txt index 5effa5bd993..e213f45cf9d 100644 --- a/Documentation/stable_kernel_rules.txt +++ b/Documentation/stable_kernel_rules.txt @@ -18,16 +18,15 @@ Rules on what kind of patches are accepted, and which ones are not, into the - It cannot contain any "trivial" fixes in it (spelling changes, whitespace cleanups, etc). - It must follow the Documentation/SubmittingPatches rules. - - It or an equivalent fix must already exist in Linus' tree. Quote the - respective commit ID in Linus' tree in your patch submission to -stable. + - It or an equivalent fix must already exist in Linus' tree (upstream). Procedure for submitting patches to the -stable tree: - Send the patch, after verifying that it follows the above rules, to - stable@kernel.org. - - To have the patch automatically included in the stable tree, add the - the tag + stable@kernel.org. You must note the upstream commit ID in the changelog + of your submission. + - To have the patch automatically included in the stable tree, add the tag Cc: stable@kernel.org in the sign-off area. Once the patch is merged it will be applied to the stable tree without anything else needing to be done by the author diff --git a/Documentation/trace/events.txt b/Documentation/trace/events.txt index 02ac6ed38b2..778ddf38b82 100644 --- a/Documentation/trace/events.txt +++ b/Documentation/trace/events.txt @@ -90,7 +90,8 @@ In order to facilitate early boot debugging, use boot option: trace_event=[event-list] -The format of this boot option is the same as described in section 2.1. +event-list is a comma separated list of events. See section 2.1 for event +format. 3. Defining an event-enabled tracepoint ======================================= diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt index 03485bfbd79..557c1edecca 100644 --- a/Documentation/trace/ftrace.txt +++ b/Documentation/trace/ftrace.txt @@ -155,6 +155,9 @@ of ftrace. Here is a list of some of the key files: to be traced. Echoing names of functions into this file will limit the trace to only those functions. + This interface also allows for commands to be used. See the + "Filter commands" section for more details. + set_ftrace_notrace: This has an effect opposite to that of @@ -1337,12 +1340,14 @@ 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 + sysctl kernel.ftrace_dump_on_oops=n or - echo 1 > /proc/sys/kernel/ftrace_dump_on_oops + echo n > /proc/sys/kernel/ftrace_dump_on_oops +If n = 1, ftrace will dump buffers of all CPUs, if n = 2 ftrace will +only dump the buffer of the CPU that triggered the oops. Here's an example of such a dump after a null pointer dereference in a kernel module: @@ -1822,6 +1827,47 @@ this special filter via: echo > set_graph_function +Filter commands +--------------- + +A few commands are supported by the set_ftrace_filter interface. +Trace commands have the following format: + +<function>:<command>:<parameter> + +The following commands are supported: + +- mod + This command enables function filtering per module. The + parameter defines the module. For example, if only the write* + functions in the ext3 module are desired, run: + + echo 'write*:mod:ext3' > set_ftrace_filter + + This command interacts with the filter in the same way as + filtering based on function names. Thus, adding more functions + in a different module is accomplished by appending (>>) to the + filter file. Remove specific module functions by prepending + '!': + + echo '!writeback*:mod:ext3' >> set_ftrace_filter + +- traceon/traceoff + These commands turn tracing on and off when the specified + functions are hit. The parameter determines how many times the + tracing system is turned on and off. If unspecified, there is + no limit. For example, to disable tracing when a schedule bug + is hit the first 5 times, run: + + echo '__schedule_bug:traceoff:5' > set_ftrace_filter + + These commands are cumulative whether or not they are appended + to set_ftrace_filter. To remove a command, prepend it by '!' + and drop the parameter: + + echo '!__schedule_bug:traceoff' > set_ftrace_filter + + trace_pipe ---------- diff --git a/Documentation/trace/kprobetrace.txt b/Documentation/trace/kprobetrace.txt index a9100b28eb8..ec94748ae65 100644 --- a/Documentation/trace/kprobetrace.txt +++ b/Documentation/trace/kprobetrace.txt @@ -40,7 +40,9 @@ Synopsis of kprobe_events $stack : Fetch stack address. $retval : Fetch return value.(*) +|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(**) - NAME=FETCHARG: Set NAME as the argument name of FETCHARG. + NAME=FETCHARG : Set NAME as the argument name of FETCHARG. + FETCHARG:TYPE : Set TYPE as the type of FETCHARG. Currently, basic types + (u8/u16/u32/u64/s8/s16/s32/s64) are supported. (*) only for return probe. (**) this is useful for fetching a field of data structures. diff --git a/Documentation/volatile-considered-harmful.txt b/Documentation/volatile-considered-harmful.txt index 991c26a6ef6..db0cb228d64 100644 --- a/Documentation/volatile-considered-harmful.txt +++ b/Documentation/volatile-considered-harmful.txt @@ -63,9 +63,9 @@ way to perform a busy wait is: cpu_relax(); The cpu_relax() call can lower CPU power consumption or yield to a -hyperthreaded twin processor; it also happens to serve as a memory barrier, -so, once again, volatile is unnecessary. Of course, busy-waiting is -generally an anti-social act to begin with. +hyperthreaded twin processor; it also happens to serve as a compiler +barrier, so, once again, volatile is unnecessary. Of course, busy- +waiting is generally an anti-social act to begin with. There are still a few rare situations where volatile makes sense in the kernel: diff --git a/Documentation/watchdog/src/watchdog-simple.c b/Documentation/watchdog/src/watchdog-simple.c index 4cf72f3fa8e..ba45803a221 100644 --- a/Documentation/watchdog/src/watchdog-simple.c +++ b/Documentation/watchdog/src/watchdog-simple.c @@ -17,9 +17,6 @@ int main(void) ret = -1; break; } - ret = fsync(fd); - if (ret) - break; sleep(10); } close(fd); diff --git a/Documentation/watchdog/src/watchdog-test.c b/Documentation/watchdog/src/watchdog-test.c index a750532ffcf..63fdc34ceb9 100644 --- a/Documentation/watchdog/src/watchdog-test.c +++ b/Documentation/watchdog/src/watchdog-test.c @@ -31,6 +31,8 @@ static void keep_alive(void) */ int main(int argc, char *argv[]) { + int flags; + fd = open("/dev/watchdog", O_WRONLY); if (fd == -1) { @@ -41,12 +43,14 @@ int main(int argc, char *argv[]) if (argc > 1) { if (!strncasecmp(argv[1], "-d", 2)) { - ioctl(fd, WDIOC_SETOPTIONS, WDIOS_DISABLECARD); + flags = WDIOS_DISABLECARD; + ioctl(fd, WDIOC_SETOPTIONS, &flags); fprintf(stderr, "Watchdog card disabled.\n"); fflush(stderr); exit(0); } else if (!strncasecmp(argv[1], "-e", 2)) { - ioctl(fd, WDIOC_SETOPTIONS, WDIOS_ENABLECARD); + flags = WDIOS_ENABLECARD; + ioctl(fd, WDIOC_SETOPTIONS, &flags); fprintf(stderr, "Watchdog card enabled.\n"); fflush(stderr); exit(0); diff --git a/Documentation/watchdog/watchdog-api.txt b/Documentation/watchdog/watchdog-api.txt index 4cc4ba9d715..eb7132ed8bb 100644 --- a/Documentation/watchdog/watchdog-api.txt +++ b/Documentation/watchdog/watchdog-api.txt @@ -222,11 +222,10 @@ returned value is the temperature in degrees fahrenheit. ioctl(fd, WDIOC_GETTEMP, &temperature); Finally the SETOPTIONS ioctl can be used to control some aspects of -the cards operation; right now the pcwd driver is the only one -supporting this ioctl. +the cards operation. int options = 0; - ioctl(fd, WDIOC_SETOPTIONS, options); + ioctl(fd, WDIOC_SETOPTIONS, &options); The following options are available: |