diff options
82 files changed, 1878 insertions, 303 deletions
diff --git a/Documentation/ftrace.txt b/Documentation/ftrace.txt new file mode 100644 index 000000000000..13e4bf054c38 --- /dev/null +++ b/Documentation/ftrace.txt @@ -0,0 +1,1353 @@ + ftrace - Function Tracer + ======================== + +Copyright 2008 Red Hat Inc. +Author: Steven Rostedt <srostedt@redhat.com> + + +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. + +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 is 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. + + +The File System +--------------- + +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 + + +That's it! (assuming that you have ftrace configured into your kernel) + +After mounting the debugfs, you can see a directory called +"tracing". This directory contains the control and output files +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 + has been compiled into the kernel. The tracers + listed here can be configured by echoing in 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 (or non-zero) to + enable it. + + trace : This file holds the output of the trace in a human readable + format. + + latency_trace : This file shows the same trace but the information + is organized more to display possible latencies + in the system. + + 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 isn't adding more data, they will display + the same information every time they are read. + + iter_ctrl : 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) + + trace_entries : This sets or displays the number of trace + entries each CPU buffer can hold. The tracer buffers + are the same size for each CPU, so care must be + taken when modifying the trace_entries. The number + of actually entries will be the number given + times the number of possible CPUS. The buffers + are saved as individual pages, and the actual entries + will always be rounded up to entries per page. + + This can only be updated when the current_tracer + is set to "none". + + NOTE: It is planned on changing the allocated buffers + from being the number of possible CPUS to + the number of online CPUS. + + 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, the + code is dynamically modified 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 in names of functions into this + file will limit the trace to only those files. + + set_ftrace_notrace: This has the opposite effect that + set_ftrace_filter has. 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_ bet traced. + + available_filter_functions : When a function is encountered the first + time by the dynamic tracer, it is recorded and + later the call is converted into a nop. This file + lists the functions that have been recorded + by the dynamic tracer and these functions can + be used to set the ftrace filter by the above + "set_ftrace_filter" file. + + +The Tracers +----------- + +Here are the list of current tracers that can be configured. + + ftrace - function tracer that uses mcount to trace all functions. + It is possible to filter out which functions that are + traced when dynamic ftrace is configured in. + + sched_switch - traces the context switches between tasks. + + irqsoff - traces the areas that disable interrupts and saves off + 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 with the latency_trace file. + + preemptoff - Similar to irqsoff but traces and records the time + preemption is disabled. + + preemptirqsoff - Similar to irqsoff and preemptoff, but traces and + records the largest time 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. + + none - This is not a tracer. To remove all tracers from tracing + simply echo "none" into current_tracer. + + +Examples of using the tracer +---------------------------- + +Here are typical examples of using the tracers with only controlling +them with the debugfs interface (without using any user-land utilities). + +Output format: +-------------- + +Here's an example of the output format of the file "trace" + + -------- +# tracer: ftrace +# +# TASK-PID CPU# TIMESTAMP FUNCTION +# | | | | | + bash-4251 [01] 10152.583854: path_put <-path_walk + bash-4251 [01] 10152.583855: dput <-path_put + bash-4251 [01] 10152.583855: _atomic_dec_and_lock <-dput + -------- + +A header is printed with the trace that is represented. In this case +the tracer is "ftrace". 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 sched_switch tracer also includes tracing of task wake ups 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 + ksoftirqd/1-7 [01] 1453.070013: 7:115:R ==> 10:115:R + events/1-10 [01] 1453.070013: 10:115:S ==> 2916:115:R + 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 show +"==>". The format is: + + Context switches: + + Previous task Next Task + + <pid>:<prio>:<state> ==> <pid>:<prio>:<state> + + Wake ups: + + Current task Task waking up + + <pid>:<prio>:<state> + <pid>:<prio>:<state> + +The prio is the internal kernel priority, which is inverse to 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 +a bit more information to see why a latency happened. Here's a typical +trace. + +# tracer: irqsoff +# +irqsoff latency trace v1.1.5 on 2.6.26-rc8 +-------------------------------------------------------------------- + latency: 97 us, #3/3, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2) + ----------------- + | task: swapper-0 (uid:0 nice:0 policy:0 rt_prio:0) + ----------------- + => started at: apic_timer_interrupt + => ended at: do_softirq + +# _------=> CPU# +# / _-----=> irqs-off +# | / _----=> need-resched +# || / _---=> hardirq/softirq +# ||| / _--=> preempt-depth +# |||| / +# ||||| delay +# cmd pid ||||| time | caller +# \ / ||||| \ | / + <idle>-0 0d..1 0us+: trace_hardirqs_off_thunk (apic_timer_interrupt) + <idle>-0 0d.s. 97us : __do_softirq (do_softirq) + <idle>-0 0d.s1 98us : trace_hardirqs_on (do_softirq) + + +vim:ft=help + + +This shows that the current tracer is "irqsoff" tracing the time +interrupts are disabled. It gives the trace version and the kernel +this was executed on (2.6.26-rc8). Then it displays the max latency +in microsecs (97 us). The number of trace entries displayed +by 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 reserved for later use. #P is the number of online CPUS (#P:2). + +The task is the process that was running when the latency happened. +(swapper pid: 0). + +The start and stop that caused the latencies: + + apic_timer_interrupt is where the interrupts were disabled. + do_softirq is where they were enabled again. + +The next lines after the header are the trace itself. The header +explains which is which. + + cmd: The name of the process in the trace. + + pid: The PID of that process. + + CPU#: The CPU that the process was running on. + + irqs-off: 'd' interrupts are disabled. '.' otherwise. + + need-resched: 'N' task need_resched is set, '.' otherwise. + + hardirq/softirq: + 'H' - hard irq happened inside a softirq. + 'h' - hard irq is running + 's' - soft irq is running + '.' - normal context. + + preempt-depth: The level of preempt_disabled + +The above is mostly meaningful for kernel developers. + + time: This differs from the trace output where as the trace output + contained a absolute timestamp. This timestamp is relative + to the start of the first entry in the 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 is 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. + + +iter_ctrl +--------- + +The iter_ctrl file is used to control what gets printed in the trace +output. To see what is available, simply cat the file: + + cat /debug/tracing/iter_ctrl + print-parent nosym-offset nosym-addr noverbose noraw nohex nobin \ + noblock nostacktrace nosched-tree + +To disable one of the options, echo in the option appended with "no". + + echo noprint-parent > /debug/tracing/iter_ctrl + +To enable an option, leave off the "no". + + echo sym-offest > /debug/tracing/iter_ctrl + +Here are the available options: + + print-parent - On function traces, display the calling function + as well as the function being traced. + + print-parent: + bash-4000 [01] 1477.606694: simple_strtoul <-strict_strtoul + + noprint-parent: + 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: + 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: + bash-4000 [01] 1477.606694: simple_strtoul <c0339346> + + verbose - This deals with the latency_trace file. + + 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. + + 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. + + sched-tree - TBD (any users??) + + +sched_switch +------------ + +This tracer simply records schedule switches. Here's an example +on how to implement it. + + # echo sched_switch > /debug/tracing/current_tracer + # echo 1 > /debug/tracing/tracing_enabled + # sleep 1 + # echo 0 > /debug/tracing/tracing_enabled + # cat /debug/tracing/trace + +# tracer: sched_switch +# +# TASK-PID CPU# TIMESTAMP FUNCTION +# | | | | | + bash-3997 [01] 240.132281: 3997:120:R + 4055:120:R + bash-3997 [01] 240.132284: 3997:120:R ==> 4055:120:R + sleep-4055 [01] 240.132371: 4055:120:S ==> 3997:120:R + bash-3997 [01] 240.132454: 3997:120:R + 4055:120:S + bash-3997 [01] 240.132457: 3997:120:R ==> 4055:120:R + sleep-4055 [01] 240.132460: 4055:120:D ==> 3997:120:R + bash-3997 [01] 240.132463: 3997:120:R + 4055:120:D + bash-3997 [01] 240.132465: 3997:120:R ==> 4055:120:R + <idle>-0 [00] 240.132589: 0:140:R + 4:115:S + <idle>-0 [00] 240.132591: 0:140:R ==> 4:115:R + ksoftirqd/0-4 [00] 240.132595: 4:115:S ==> 0:140:R + <idle>-0 [00] 240.132598: 0:140:R + 4:115:S + <idle>-0 [00] 240.132599: 0:140:R ==> 4:115:R + ksoftirqd/0-4 [00] 240.132603: 4:115:S ==> 0:140:R + sleep-4055 [01] 240.133058: 4055:120:S ==> 3997:120:R + [...] + + +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 only lists the wake ups (represented with '+') +and context switches ('==>') with the previous task or current +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 + Kernel priority: 140 ==> idle task priority + +The task states are: + + R - running : wants to run, may not actually be running + S - sleep : process is waiting to be woken up (handles signals) + D - deep sleep : process must be woken up (ignores signals) + T - stopped : process suspended + t - traced : process is being traced (with something like gdb) + Z - zombie : process waiting to be cleaned up + X - unknown + + +ftrace_enabled +-------------- + +The following tracers 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 + + or + + echo 1 > /proc/sys/kernel/ftrace_enabled + +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. + + +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. + +The irqsoff tracer tracks the time interrupts are disabled and when +they are re-enabled. When a new maximum latency is hit, it saves off +the trace so that it may be retrieved at a later time. Every time a +new maximum in reached, the old saved trace is discarded and the new +trace is saved. + +To reset the maximum, echo 0 into tracing_max_latency. Here's an +example: + + # echo irqsoff > /debug/tracing/current_tracer + # echo 0 > /debug/tracing/tracing_max_latency + # echo 1 > /debug/tracing/tracing_enabled + # ls -ltr + [...] + # echo 0 > /debug/tracing/tracing_enabled + # cat /debug/tracing/latency_trace +# tracer: irqsoff +# +irqsoff latency trace v1.1.5 on 2.6.26-rc8 +-------------------------------------------------------------------- + latency: 6 us, #3/3, CPU#1 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2) + ----------------- + | task: bash-4269 (uid:0 nice:0 policy:0 rt_prio:0) + ----------------- + => started at: copy_page_range + => ended at: copy_page_range + +# _------=> CPU# +# / _-----=> irqs-off +# | / _----=> need-resched +# || / _---=> hardirq/softirq +# ||| / _--=> preempt-depth +# |||| / +# ||||| delay +# cmd pid ||||| time | caller +# \ / ||||| \ | / + bash-4269 1...1 0us+: _spin_lock (copy_page_range) + bash-4269 1...1 7us : _spin_unlock (copy_page_range) + bash-4269 1...2 7us : trace_preempt_on (copy_page_range) + + +vim:ft=help + +Here we see that that we had a latency of 6 microsecs (which is +very good). The spin_lock in copy_page_range disabled interrupts. +The difference between the 6 and the displayed timestamp 7us is +because the clock must have incremented between the time of recording +the max latency and recording the function that had that latency. + +Note the above had ftrace_enabled not set. If we set the ftrace_enabled +we get a much larger output: + +# tracer: irqsoff +# +irqsoff latency trace v1.1.5 on 2.6.26-rc8 +-------------------------------------------------------------------- + latency: 50 us, #101/101, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2) + ----------------- + | task: ls-4339 (uid:0 nice:0 policy:0 rt_prio:0) + ----------------- + => started at: __alloc_pages_internal + => ended at: __alloc_pages_internal + +# _------=> CPU# +# / _-----=> irqs-off +# | / _----=> need-resched +# || / _---=> hardirq/softirq +# ||| / _--=> preempt-depth +# |||| / +# ||||| delay +# cmd pid ||||| time | caller +# \ / ||||| \ | / + ls-4339 0...1 0us+: get_page_from_freelist (__alloc_pages_internal) + ls-4339 0d..1 3us : rmqueue_bulk (get_page_from_freelist) + ls-4339 0d..1 3us : _spin_lock (rmqueue_bulk) + ls-4339 0d..1 4us : add_preempt_count (_spin_lock) + ls-4339 0d..2 4us : __rmqueue (rmqueue_bulk) + ls-4339 0d..2 5us : __rmqueue_smallest (__rmqueue) + ls-4339 0d..2 5us : __mod_zone_page_state (__rmqueue_smallest) + ls-4339 0d..2 6us : __rmqueue (rmqueue_bulk) + ls-4339 0d..2 6us : __rmqueue_smallest (__rmqueue) + ls-4339 0d..2 7us : __mod_zone_page_state (__rmqueue_smallest) + ls-4339 0d..2 7us : __rmqueue (rmqueue_bulk) + ls-4339 0d..2 8us : __rmqueue_smallest (__rmqueue) +[...] + ls-4339 0d..2 46us : __rmqueue_smallest (__rmqueue) + ls-4339 0d..2 47us : __mod_zone_page_state (__rmqueue_smallest) + ls-4339 0d..2 47us : __rmqueue (rmqueue_bulk) + ls-4339 0d..2 48us : __rmqueue_smallest (__rmqueue) + ls-4339 0d..2 48us : __mod_zone_page_state (__rmqueue_smallest) + ls-4339 0d..2 49us : _spin_unlock (rmqueue_bulk) + ls-4339 0d..2 49us : sub_preempt_count (_spin_unlock) + ls-4339 0d..1 50us : get_page_from_freelist (__alloc_pages_internal) + ls-4339 0d..2 51us : trace_hardirqs_on (__alloc_pages_internal) + + +vim:ft=help + + +Here we traced a 50 microsecond latency. But we also see all the +functions that were called during that time. Note that enabling +function tracing we endure an added overhead. This overhead may +extend the latency times. But never the less, this trace has provided +some very helpful debugging. + + +preemptoff +---------- + +When preemption is disabled we may be able to receive interrupts but +the task can not 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 disables preemption. +Like the irqsoff, it records the maximum latency that preemption +was disabled. The control of preemptoff is much like the irqsoff. + + # echo preemptoff > /debug/tracing/current_tracer + # echo 0 > /debug/tracing/tracing_max_latency + # echo 1 > /debug/tracing/tracing_enabled + # ls -ltr + [...] + # echo 0 > /debug/tracing/tracing_enabled + # cat /debug/tracing/latency_trace +# tracer: preemptoff +# +preemptoff latency trace v1.1.5 on 2.6.26-rc8 +-------------------------------------------------------------------- + latency: 29 us, #3/3, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2) + ----------------- + | task: sshd-4261 (uid:0 nice:0 policy:0 rt_prio:0) + ----------------- + => started at: do_IRQ + => ended at: __do_softirq + +# _------=> CPU# +# / _-----=> irqs-off +# | / _----=> need-resched +# || / _---=> hardirq/softirq +# ||| / _--=> preempt-depth +# |||| / +# ||||| delay +# cmd pid ||||| time | caller +# \ / ||||| \ | / + sshd-4261 0d.h. 0us+: irq_enter (do_IRQ) + sshd-4261 0d.s. 29us : _local_bh_enable (__do_softirq) + sshd-4261 0d.s1 30us : trace_preempt_on (__do_softirq) + + +vim:ft=help + +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 +# +preemptoff latency trace v1.1.5 on 2.6.26-rc8 +-------------------------------------------------------------------- + latency: 63 us, #87/87, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2) + ----------------- + | task: sshd-4261 (uid:0 nice:0 policy:0 rt_prio:0) + ----------------- + => started at: remove_wait_queue + => ended at: __do_softirq + +# _------=> CPU# +# / _-----=> irqs-off +# | / _----=> need-resched +# || / _---=> hardirq/softirq +# ||| / _--=> preempt-depth +# |||| / +# ||||| delay +# cmd pid ||||| time | caller +# \ / ||||| \ | / + sshd-4261 0d..1 0us : _spin_lock_irqsave (remove_wait_queue) + sshd-4261 0d..1 1us : _spin_unlock_irqrestore (remove_wait_queue) + sshd-4261 0d..1 2us : do_IRQ (common_interrupt) + sshd-4261 0d..1 2us : irq_enter (do_IRQ) + sshd-4261 0d..1 2us : idle_cpu (irq_enter) + sshd-4261 0d..1 3us : add_preempt_count (irq_enter) + sshd-4261 0d.h1 3us : idle_cpu (irq_enter) + sshd-4261 0d.h. 4us : handle_fasteoi_irq (do_IRQ) +[...] + sshd-4261 0d.h. 12us : add_preempt_count (_spin_lock) + sshd-4261 0d.h1 12us : ack_ioapic_quirk_irq (handle_fasteoi_irq) + sshd-4261 0d.h1 13us : move_native_irq (ack_ioapic_quirk_irq) + sshd-4261 0d.h1 13us : _spin_unlock (handle_fasteoi_irq) + sshd-4261 0d.h1 14us : sub_preempt_count (_spin_unlock) + sshd-4261 0d.h1 14us : irq_exit (do_IRQ) + sshd-4261 0d.h1 15us : sub_preempt_count (irq_exit) + sshd-4261 0d..2 15us : do_softirq (irq_exit) + sshd-4261 0d... 15us : __do_softirq (do_softirq) + sshd-4261 0d... 16us : __local_bh_disable (__do_softirq) + sshd-4261 0d... 16us+: add_preempt_count (__local_bh_disable) + sshd-4261 0d.s4 20us : add_preempt_count (__local_bh_disable) + sshd-4261 0d.s4 21us : sub_preempt_count (local_bh_enable) + sshd-4261 0d.s5 21us : sub_preempt_count (local_bh_enable) +[...] + sshd-4261 0d.s6 41us : add_preempt_count (__local_bh_disable) + sshd-4261 0d.s6 42us : sub_preempt_count (local_bh_enable) + sshd-4261 0d.s7 42us : sub_preempt_count (local_bh_enable) + sshd-4261 0d.s5 43us : add_preempt_count (__local_bh_disable) + sshd-4261 0d.s5 43us : sub_preempt_count (local_bh_enable_ip) + sshd-4261 0d.s6 44us : sub_preempt_count (local_bh_enable_ip) + sshd-4261 0d.s5 44us : add_preempt_count (__local_bh_disable) + sshd-4261 0d.s5 45us : sub_preempt_count (local_bh_enable) +[...] + sshd-4261 0d.s. 63us : _local_bh_enable (__do_softirq) + 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 by the functions themselves that +this is not the case. + +Notice that the __do_softirq when called doesn't have a preempt_count. +It may seem that we missed a preempt enabled. What really happened +is that the preempt count is held on the threads 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 don't need to worry about it. Having a tracer like this is good +to let 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. + +The following code: + + local_irq_disable(); + call_function_with_irqs_off(); + preempt_disable(); + call_function_with_irqs_and_preemption_off(); + local_irq_enable(); + call_function_with_preemption_off(); + preempt_enable(); + +The irqsoff tracer will record the total length of +call_function_with_irqs_off() and +call_function_with_irqs_and_preemption_off(). + +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. + +Again, using this trace is much like the irqsoff and preemptoff tracers. + + # echo preemptoff > /debug/tracing/current_tracer + # echo 0 > /debug/tracing/tracing_max_latency + # echo 1 > /debug/tracing/tracing_enabled + # ls -ltr + [...] + # echo 0 > /debug/tracing/tracing_enabled + # cat /debug/tracing/latency_trace +# tracer: preemptirqsoff +# +preemptirqsoff latency trace v1.1.5 on 2.6.26-rc8 +-------------------------------------------------------------------- + latency: 293 us, #3/3, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2) + ----------------- + | task: ls-4860 (uid:0 nice:0 policy:0 rt_prio:0) + ----------------- + => started at: apic_timer_interrupt + => ended at: __do_softirq + +# _------=> CPU# +# / _-----=> irqs-off +# | / _----=> need-resched +# || / _---=> hardirq/softirq +# ||| / _--=> preempt-depth +# |||| / +# ||||| delay +# cmd pid ||||| time | caller +# \ / ||||| \ | / + ls-4860 0d... 0us!: trace_hardirqs_off_thunk (apic_timer_interrupt) + ls-4860 0d.s. 294us : _local_bh_enable (__do_softirq) + ls-4860 0d.s1 294us : trace_preempt_on (__do_softirq) + + +vim:ft=help + + +The trace_hardirqs_off_thunk is called from assembly on x86 when +interrupts are disabled in the assembly code. Without the function +tracing, we don't 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: + + +# tracer: preemptirqsoff +# +preemptirqsoff latency trace v1.1.5 on 2.6.26-rc8 +-------------------------------------------------------------------- + latency: 105 us, #183/183, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2) + ----------------- + | task: sshd-4261 (uid:0 nice:0 policy:0 rt_prio:0) + ----------------- + => started at: write_chan + => ended at: __do_softirq + +# _------=> CPU# +# / _-----=> irqs-off +# | / _----=> need-resched +# || / _---=> hardirq/softirq +# ||| / _--=> preempt-depth +# |||| / +# ||||| delay +# cmd pid ||||| time | caller +# \ / ||||| \ | / + ls-4473 0.N.. 0us : preempt_schedule (write_chan) + ls-4473 0dN.1 1us : _spin_lock (schedule) + ls-4473 0dN.1 2us : add_preempt_count (_spin_lock) + ls-4473 0d..2 2us : put_prev_task_fair (schedule) +[...] + ls-4473 0d..2 13us : set_normalized_timespec (ktime_get_ts) + ls-4473 0d..2 13us : __switch_to (schedule) + sshd-4261 0d..2 14us : finish_task_switch (schedule) + sshd-4261 0d..2 14us : _spin_unlock_irq (finish_task_switch) + sshd-4261 0d..1 15us : add_preempt_count (_spin_lock_irqsave) + sshd-4261 0d..2 16us : _spin_unlock_irqrestore (hrtick_set) + sshd-4261 0d..2 16us : do_IRQ (common_interrupt) + sshd-4261 0d..2 17us : irq_enter (do_IRQ) + sshd-4261 0d..2 17us : idle_cpu (irq_enter) + sshd-4261 0d..2 18us : add_preempt_count (irq_enter) + sshd-4261 0d.h2 18us : idle_cpu (irq_enter) + sshd-4261 0d.h. 18us : handle_fasteoi_irq (do_IRQ) + sshd-4261 0d.h. 19us : _spin_lock (handle_fasteoi_irq) + sshd-4261 0d.h. 19us : add_preempt_count (_spin_lock) + sshd-4261 0d.h1 20us : _spin_unlock (handle_fasteoi_irq) + sshd-4261 0d.h1 20us : sub_preempt_count (_spin_unlock) +[...] + sshd-4261 0d.h1 28us : _spin_unlock (handle_fasteoi_irq) + sshd-4261 0d.h1 29us : sub_preempt_count (_spin_unlock) + sshd-4261 0d.h2 29us : irq_exit (do_IRQ) + sshd-4261 0d.h2 29us : sub_preempt_count (irq_exit) + sshd-4261 0d..3 30us : do_softirq (irq_exit) + sshd-4261 0d... 30us : __do_softirq (do_softirq) + sshd-4261 0d... 31us : __local_bh_disable (__do_softirq) + sshd-4261 0d... 31us+: add_preempt_count (__local_bh_disable) + sshd-4261 0d.s4 34us : add_preempt_count (__local_bh_disable) +[...] + sshd-4261 0d.s3 43us : sub_preempt_count (local_bh_enable_ip) + sshd-4261 0d.s4 44us : sub_preempt_count (local_bh_enable_ip) + sshd-4261 0d.s3 44us : smp_apic_timer_interrupt (apic_timer_interrupt) + sshd-4261 0d.s3 45us : irq_enter (smp_apic_timer_interrupt) + sshd-4261 0d.s3 45us : idle_cpu (irq_enter) + sshd-4261 0d.s3 46us : add_preempt_count (irq_enter) + sshd-4261 0d.H3 46us : idle_cpu (irq_enter) + sshd-4261 0d.H3 47us : hrtimer_interrupt (smp_apic_timer_interrupt) + sshd-4261 0d.H3 47us : ktime_get (hrtimer_interrupt) +[...] + sshd-4261 0d.H3 81us : tick_program_event (hrtimer_interrupt) + sshd-4261 0d.H3 82us : ktime_get (tick_program_event) + sshd-4261 0d.H3 82us : ktime_get_ts (ktime_get) + sshd-4261 0d.H3 83us : getnstimeofday (ktime_get_ts) + sshd-4261 0d.H3 83us : set_normalized_timespec (ktime_get_ts) + sshd-4261 0d.H3 84us : clockevents_program_event (tick_program_event) + sshd-4261 0d.H3 84us : lapic_next_event (clockevents_program_event) + sshd-4261 0d.H3 85us : irq_exit (smp_apic_timer_interrupt) + sshd-4261 0d.H3 85us : sub_preempt_count (irq_exit) + sshd-4261 0d.s4 86us : sub_preempt_count (irq_exit) + sshd-4261 0d.s3 86us : add_preempt_count (__local_bh_disable) +[...] + sshd-4261 0d.s1 98us : sub_preempt_count (net_rx_action) + sshd-4261 0d.s. 99us : add_preempt_count (_spin_lock_irq) + sshd-4261 0d.s1 99us+: _spin_unlock_irq (run_timer_softirq) + sshd-4261 0d.s. 104us : _local_bh_enable (__do_softirq) + sshd-4261 0d.s. 104us : sub_preempt_count (_local_bh_enable) + sshd-4261 0d.s. 105us : _local_bh_enable (__do_softirq) + 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 +with the 'N' in the trace. Interrupts are disabled in the spin_lock +and the trace started. We see that a schedule took place to run +sshd. When the interrupts were enabled we took an interrupt. +On return of the interrupt the softirq ran. We took another interrupt +while running the softirq as we see with the capital 'H'. + + +wakeup +------ + +In Real-Time environment it is very important to know the wakeup +time it takes for the highest priority task that wakes up to the +time 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 is more appropriate for such measurements. + +Real-Time environments is 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 +different 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 + # echo 1 > /debug/tracing/tracing_enabled + # chrt -f 5 sleep 1 + # echo 0 > /debug/tracing/tracing_enabled + # cat /debug/tracing/latency_trace +# tracer: wakeup +# +wakeup latency trace v1.1.5 on 2.6.26-rc8 +-------------------------------------------------------------------- + latency: 4 us, #2/2, CPU#1 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2) + ----------------- + | task: sleep-4901 (uid:0 nice:0 policy:1 rt_prio:5) + ----------------- + +# _------=> CPU# +# / _-----=> irqs-off +# | / _----=> need-resched +# || / _---=> hardirq/softirq +# ||| / _--=> preempt-depth +# |||| / +# ||||| delay +# cmd pid ||||| time | caller +# \ / ||||| \ | / + <idle>-0 1d.h4 0us+: try_to_wake_up (wake_up_process) + <idle>-0 1d..4 4us : schedule (cpu_idle) + + +vim:ft=help + + +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. + +Doing the same with chrt -r 5 and ftrace_enabled set. + +# tracer: wakeup +# +wakeup latency trace v1.1.5 on 2.6.26-rc8 +-------------------------------------------------------------------- + latency: 50 us, #60/60, CPU#1 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2) + ----------------- + | task: sleep-4068 (uid:0 nice:0 policy:2 rt_prio:5) + ----------------- + +# _------=> CPU# +# / _-----=> irqs-off +# | / _----=> need-resched +# || / _---=> hardirq/softirq +# ||| / _--=> preempt-depth +# |||| / +# ||||| delay +# cmd pid ||||| time | caller +# \ / ||||| \ | / +ksoftirq-7 1d.H3 0us : try_to_wake_up (wake_up_process) +ksoftirq-7 1d.H4 1us : sub_preempt_count (marker_probe_cb) +ksoftirq-7 1d.H3 2us : check_preempt_wakeup (try_to_wake_up) +ksoftirq-7 1d.H3 3us : update_curr (check_preempt_wakeup) +ksoftirq-7 1d.H3 4us : calc_delta_mine (update_curr) +ksoftirq-7 1d.H3 5us : __resched_task (check_preempt_wakeup) +ksoftirq-7 1d.H3 6us : task_wake_up_rt (try_to_wake_up) +ksoftirq-7 1d.H3 7us : _spin_unlock_irqrestore (try_to_wake_up) +[...] +ksoftirq-7 1d.H2 17us : irq_exit (smp_apic_timer_interrupt) +ksoftirq-7 1d.H2 18us : sub_preempt_count (irq_exit) +ksoftirq-7 1d.s3 19us : sub_preempt_count (irq_exit) +ksoftirq-7 1..s2 20us : rcu_process_callbacks (__do_softirq) +[...] +ksoftirq-7 1..s2 26us : __rcu_process_callbacks (rcu_process_callbacks) +ksoftirq-7 1d.s2 27us : _local_bh_enable (__do_softirq) +ksoftirq-7 1d.s2 28us : sub_preempt_count (_local_bh_enable) +ksoftirq-7 1.N.3 29us : sub_preempt_count (ksoftirqd) +ksoftirq-7 1.N.2 30us : _cond_resched (ksoftirqd) +ksoftirq-7 1.N.2 31us : __cond_resched (_cond_resched) +ksoftirq-7 1.N.2 32us : add_preempt_count (__cond_resched) +ksoftirq-7 1.N.2 33us : schedule (__cond_resched) +ksoftirq-7 1.N.2 33us : add_preempt_count (schedule) +ksoftirq-7 1.N.3 34us : hrtick_clear (schedule) +ksoftirq-7 1dN.3 35us : _spin_lock (schedule) +ksoftirq-7 1dN.3 36us : add_preempt_count (_spin_lock) +ksoftirq-7 1d..4 37us : put_prev_task_fair (schedule) +ksoftirq-7 1d..4 38us : update_curr (put_prev_task_fair) +[...] +ksoftirq-7 1d..5 47us : _spin_trylock (tracing_record_cmdline) +ksoftirq-7 1d..5 48us : add_preempt_count (_spin_trylock) +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 didn't we see the 'N' set early? This may be +a harmless bug with x86_32 and 4K stacks. The need_reched() function +that tests if we need to reschedule looks on the actual stack. +Where as the setting of the NEED_RESCHED bit happens on the +task's stack. But because we are in a hard interrupt, the test +is with the interrupts stack which has that to be false. We don't +see the 'N' until we switch back to the task's stack. + +ftrace +------ + +ftrace is not only the name of the tracing infrastructure, but it +is also a name of one of the tracers. The 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. + + # sysctl kernel.ftrace_enabled=1 + # echo ftrace > /debug/tracing/current_tracer + # echo 1 > /debug/tracing/tracing_enabled + # usleep 1 + # echo 0 > /debug/tracing/tracing_enabled + # cat /debug/tracing/trace +# tracer: ftrace +# +# TASK-PID CPU# TIMESTAMP FUNCTION +# | | | | | + bash-4003 [00] 123.638713: finish_task_switch <-schedule + bash-4003 [00] 123.638714: _spin_unlock_irq <-finish_task_switch + bash-4003 [00] 123.638714: sub_preempt_count <-_spin_unlock_irq + bash-4003 [00] 123.638715: hrtick_set <-schedule + bash-4003 [00] 123.638715: _spin_lock_irqsave <-hrtick_set + bash-4003 [00] 123.638716: add_preempt_count <-_spin_lock_irqsave + bash-4003 [00] 123.638716: _spin_unlock_irqrestore <-hrtick_set + bash-4003 [00] 123.638717: sub_preempt_count <-_spin_unlock_irqrestore + bash-4003 [00] 123.638717: hrtick_clear <-hrtick_set + bash-4003 [00] 123.638718: sub_preempt_count <-schedule + bash-4003 [00] 123.638718: sub_preempt_count <-preempt_schedule + bash-4003 [00] 123.638719: wait_for_completion <-__stop_machine_run + bash-4003 [00] 123.638719: wait_for_common <-wait_for_completion + bash-4003 [00] 123.638720: _spin_lock_irq <-wait_for_common + bash-4003 [00] 123.638720: add_preempt_count <-_spin_lock_irq +[...] + + +Note: It is sometimes better to enable or disable tracing directly from +a program, because the buffer may be overflowed by the echo commands +before you get to the point you want to trace. It is also easier to +stop the tracing at the point that you hit the part that you are +interested in. Since the ftrace buffer is a ring buffer with the +oldest data being overwritten, usually it is sufficient to start the +tracer with an echo command but have you code stop it. Something +like the following is usually appropriate for this. + +int trace_fd; +[...] +int main(int argc, char *argv[]) { + [...] + trace_fd = open("/debug/tracing/tracing_enabled", O_WRONLY); + [...] + if (condition_hit()) { + write(trace_fd, "0", 1); + } + [...] +} + + +dynamic ftrace +-------------- + +If CONFIG_DYNAMIC_FTRACE is set, then 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. + +When dynamic ftrace is initialized, it calls kstop_machine to make it +act like a uniprocessor so that it can freely modify code without +worrying about other processors executing that same code. At +initialization, the mcount calls are change to call a "record_ip" +function. After this, the first time a kernel function is called, +it has the calling address saved in a hash table. + +Later on the ftraced kernel thread is awoken and will again call +kstop_machine if new functions have been recorded. The ftraced thread +will change all calls to mcount to "nop". Just calling mcount +and having mcount return has shown a 10% overhead. By converting +it to a nop, there is no recordable overhead to the system. + +One special side-effect to the recording of the functions being +traced, is that we can now selectively choose which functions we +want to trace and which ones we want the mcount calls to remain as +nops. + +Two files that contain to the enabling and disabling of recorded +functions are: + + set_ftrace_filter + +and + + set_ftrace_notrace + +A list of available functions that you can add to this files is listed +in: + + available_filter_functions + + # cat /debug/tracing/available_filter_functions +put_prev_task_idle +kmem_cache_create +pick_next_task_rt +get_online_cpus +pick_next_task_fair +mutex_lock +[...] + +If I'm only interested in sys_nanosleep and hrtimer_interrupt: + + # echo sys_nanosleep hrtimer_interrupt \ + > /debug/tracing/set_ftrace_filter + # echo ftrace > /debug/tracing/current_tracer + # echo 1 > /debug/tracing/tracing_enabled + # usleep 1 + # echo 0 > /debug/tracing/tracing_enabled + # cat /debug/tracing/trace +# tracer: ftrace +# +# TASK-PID CPU# TIMESTAMP FUNCTION +# | | | | | + usleep-4134 [00] 1317.070017: hrtimer_interrupt <-smp_apic_timer_interrupt + usleep-4134 [00] 1317.070111: sys_nanosleep <-syscall_call + <idle>-0 [00] 1317.070115: hrtimer_interrupt <-smp_apic_timer_interrupt + +To see what functions are being traced, you can cat the file: + + # cat /debug/tracing/set_ftrace_filter +hrtimer_interrupt +sys_nanosleep + + +Perhaps this isn't enough. The filters also allow simple wild cards. +Only the following is currently available + + <match>* - will match functions that begins with <match> + *<match> - will match functions that end with <match> + *<match>* - will match functions that have <match> in it + +Thats all the wild cards that are allowed. + + <match>*<match> will not work. + + # echo hrtimer_* > /debug/tracing/set_ftrace_filter + +Produces: + +# tracer: ftrace +# +# TASK-PID CPU# TIMESTAMP FUNCTION +# | | | | | + bash-4003 [00] 1480.611794: hrtimer_init <-copy_process + bash-4003 [00] 1480.611941: hrtimer_start <-hrtick_set + bash-4003 [00] 1480.611956: hrtimer_cancel <-hrtick_clear + bash-4003 [00] 1480.611956: hrtimer_try_to_cancel <-hrtimer_cancel + <idle>-0 [00] 1480.612019: hrtimer_get_next_event <-get_next_timer_interrupt + <idle>-0 [00] 1480.612025: hrtimer_get_next_event <-get_next_timer_interrupt + <idle>-0 [00] 1480.612032: hrtimer_get_next_event <-get_next_timer_interrupt + <idle>-0 [00] 1480.612037: hrtimer_get_next_event <-get_next_timer_interrupt + <idle>-0 [00] 1480.612382: hrtimer_get_next_event <-get_next_timer_interrupt + + +Notice that we lost the sys_nanosleep. + + # cat /debug/tracing/set_ftrace_filter +hrtimer_run_queues +hrtimer_run_pending +hrtimer_init +hrtimer_cancel +hrtimer_try_to_cancel +hrtimer_forward +hrtimer_start +hrtimer_reprogram +hrtimer_force_reprogram +hrtimer_get_next_event +hrtimer_interrupt +hrtimer_nanosleep +hrtimer_wakeup +hrtimer_get_remaining +hrtimer_get_res +hrtimer_init_sleeper + + +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. + + # echo > /debug/tracing/set_ftrace_filter + # cat /debug/tracing/set_ftrace_filter + # + +Again, now we want to append. + + # echo sys_nanosleep > /debug/tracing/set_ftrace_filter + # cat /debug/tracing/set_ftrace_filter +sys_nanosleep + # echo hrtimer_* >> /debug/tracing/set_ftrace_filter + # cat /debug/tracing/set_ftrace_filter +hrtimer_run_queues +hrtimer_run_pending +hrtimer_init +hrtimer_cancel +hrtimer_try_to_cancel +hrtimer_forward +hrtimer_start +hrtimer_reprogram +hrtimer_force_reprogram +hrtimer_get_next_event +hrtimer_interrupt +sys_nanosleep +hrtimer_nanosleep +hrtimer_wakeup +hrtimer_get_remaining +hrtimer_get_res +hrtimer_init_sleeper + + +The set_ftrace_notrace prevents those functions from being traced. + + # echo '*preempt*' '*lock*' > /debug/tracing/set_ftrace_notrace + +Produces: + +# tracer: ftrace +# +# TASK-PID CPU# TIMESTAMP FUNCTION +# | | | | | + bash-4043 [01] 115.281644: finish_task_switch <-schedule + bash-4043 [01] 115.281645: hrtick_set <-schedule + bash-4043 [01] 115.281645: hrtick_clear <-hrtick_set + bash-4043 [01] 115.281646: wait_for_completion <-__stop_machine_run + bash-4043 [01] 115.281647: wait_for_common <-wait_for_completion + bash-4043 [01] 115.281647: kthread_stop <-stop_machine_run + bash-4043 [01] 115.281648: init_waitqueue_head <-kthread_stop + bash-4043 [01] 115.281648: wake_up_process <-kthread_stop + bash-4043 [01] 115.281649: try_to_wake_up <-wake_up_process + +We can see that there's no more lock or preempt tracing. + +ftraced +------- + +As mentioned above, when dynamic ftrace is configured in, a kernel +thread wakes up once a second and checks to see if there are mcount +calls that need to be converted into nops. If there is not, then +it simply goes back to sleep. But if there is, it will call +kstop_machine to convert the calls to nops. + +There may be a case that you do not want this added latency. +Perhaps you are doing some audio recording and this activity might +cause skips in the playback. There is an interface to disable +and enable the ftraced kernel thread. + + # echo 0 > /debug/tracing/ftraced_enabled + +This will disable the calling of the kstop_machine to update the +mcount calls to nops. Remember that there's a large overhead +to calling mcount. Without this kernel thread, that overhead will +exist. + +Any write to the ftraced_enabled file will cause the kstop_machine +to run if there are recorded calls to mcount. This means that a +user can manually perform the updates when they want to by simply +echoing a '0' into the ftraced_enabled file. + +The updates are also done at the beginning of enabling a tracer +that uses ftrace function recording. + + +trace_pipe +---------- + +The trace_pipe outputs the same as trace, 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 ftrace > /debug/tracing/current_tracer + # cat /debug/tracing/trace_pipe > /tmp/trace.out & +[1] 4153 + # echo 1 > /debug/tracing/tracing_enabled + # usleep 1 + # echo 0 > /debug/tracing/tracing_enabled + # cat /debug/tracing/trace +# tracer: ftrace +# +# TASK-PID CPU# TIMESTAMP FUNCTION +# | | | | | + + # + # cat /tmp/trace.out + bash-4043 [00] 41.267106: finish_task_switch <-schedule + bash-4043 [00] 41.267106: hrtick_set <-schedule + bash-4043 [00] 41.267107: hrtick_clear <-hrtick_set + bash-4043 [00] 41.267108: wait_for_completion <-__stop_machine_run + bash-4043 [00] 41.267108: wait_for_common <-wait_for_completion + bash-4043 [00] 41.267109: kthread_stop <-stop_machine_run + bash-4043 [00] 41.267109: init_waitqueue_head <-kthread_stop + bash-4043 [00] 41.267110: wake_up_process <-kthread_stop + bash-4043 [00] 41.267110: try_to_wake_up <-wake_up_process + bash-4043 [00] 41.267111: select_task_rq_rt <-try_to_wake_up + + +Note, reading the trace_pipe will block until more input is added. +By changing the tracer, trace_pipe will issue an EOF. We needed +to set the ftrace tracer _before_ cating the trace_pipe file. + + +trace entries +------------- + +Having too much or not enough data can be troublesome in diagnosing +some issue in the kernel. The file trace_entries is used to modify +the size of the internal trace buffers. The numbers 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/trace_entries +65620 + +Note, to modify this you must have tracing fulling disabled. To do that, +echo "none" into the current_tracer. + + # echo none > /debug/tracing/current_tracer + # echo 100000 > /debug/tracing/trace_entries + # cat /debug/tracing/trace_entries +100045 + + +Notice that we echoed in 100,000 but the size is 100,045. The entries +are held by individual pages. It allocates the number of pages it takes +to fulfill the request. If more entries may fit on the last page +it will add them. + + # echo 1 > /debug/tracing/trace_entries + # cat /debug/tracing/trace_entries +85 + +This shows us that 85 entries can fit on a single page. + +The number of pages that will be allocated is a percentage of available +memory. Allocating too much will produces an error. + + # echo 1000000000000 > /debug/tracing/trace_entries +-bash: echo: write error: Cannot allocate memory + # cat /debug/tracing/trace_entries +85 + @@ -1,7 +1,7 @@ VERSION = 2 PATCHLEVEL = 6 SUBLEVEL = 26 -EXTRAVERSION = -rc8 +EXTRAVERSION = -rc9 NAME = Rotary Wombat # *DOCUMENTATION* diff --git a/arch/mips/mm/c-r3k.c b/arch/mips/mm/c-r3k.c index 76935e320214..27a5b466c85c 100644 --- a/arch/mips/mm/c-r3k.c +++ b/arch/mips/mm/c-r3k.c @@ -26,7 +26,7 @@ static unsigned long icache_size, dcache_size; /* Size in bytes */ static unsigned long icache_lsize, dcache_lsize; /* Size in bytes */ -unsigned long __init r3k_cache_size(unsigned long ca_flags) +unsigned long __cpuinit r3k_cache_size(unsigned long ca_flags) { unsigned long flags, status, dummy, size; volatile unsigned long *p; @@ -61,7 +61,7 @@ unsigned long __init r3k_cache_size(unsigned long ca_flags) return size * sizeof(*p); } -unsigned long __init r3k_cache_lsize(unsigned long ca_flags) +unsigned long __cpuinit r3k_cache_lsize(unsigned long ca_flags) { unsigned long flags, status, lsize, i; volatile unsigned long *p; @@ -90,7 +90,7 @@ unsigned long __init r3k_cache_lsize(unsigned long ca_flags) return lsize * sizeof(*p); } -static void __init r3k_probe_cache(void) +static void __cpuinit r3k_probe_cache(void) { dcache_size = r3k_cache_size(ST0_ISC); if (dcache_size) diff --git a/arch/mips/mm/page.c b/arch/mips/mm/page.c index 1edf0cbbeede..1417c6494858 100644 --- a/arch/mips/mm/page.c +++ b/arch/mips/mm/page.c @@ -235,13 +235,12 @@ static void __cpuinit set_prefetch_parameters(void) } /* * Too much unrolling will overflow the available space in - * clear_space_array / copy_page_array. 8 words sounds generous, - * but a R4000 with 128 byte L2 line length can exceed even that. + * clear_space_array / copy_page_array. */ - half_clear_loop_size = min(8 * clear_word_size, + half_clear_loop_size = min(16 * clear_word_size, max(cache_line_size >> 1, 4 * clear_word_size)); - half_copy_loop_size = min(8 * copy_word_size, + half_copy_loop_size = min(16 * copy_word_size, max(cache_line_size >> 1, 4 * copy_word_size)); } @@ -263,21 +262,23 @@ static inline void __cpuinit build_clear_pref(u32 **buf, int off) if (pref_bias_clear_store) { uasm_i_pref(buf, pref_dst_mode, pref_bias_clear_store + off, A0); - } else if (cpu_has_cache_cdex_s) { - uasm_i_cache(buf, Create_Dirty_Excl_SD, off, A0); - } else if (cpu_has_cache_cdex_p) { - if (R4600_V1_HIT_CACHEOP_WAR && cpu_is_r4600_v1_x()) { - uasm_i_nop(buf); - uasm_i_nop(buf); - uasm_i_nop(buf); - uasm_i_nop(buf); - } + } else if (cache_line_size == (half_clear_loop_size << 1)) { + if (cpu_has_cache_cdex_s) { + uasm_i_cache(buf, Create_Dirty_Excl_SD, off, A0); + } else if (cpu_has_cache_cdex_p) { + if (R4600_V1_HIT_CACHEOP_WAR && cpu_is_r4600_v1_x()) { + uasm_i_nop(buf); + uasm_i_nop(buf); + uasm_i_nop(buf); + uasm_i_nop(buf); + } - if (R4600_V2_HIT_CACHEOP_WAR && cpu_is_r4600_v2_x()) - uasm_i_lw(buf, ZERO, ZERO, AT); + if (R4600_V2_HIT_CACHEOP_WAR && cpu_is_r4600_v2_x()) + uasm_i_lw(buf, ZERO, ZERO, AT); - uasm_i_cache(buf, Create_Dirty_Excl_D, off, A0); - } + uasm_i_cache(buf, Create_Dirty_Excl_D, off, A0); + } + } } void __cpuinit build_clear_page(void) @@ -403,20 +404,22 @@ static inline void build_copy_store_pref(u32 **buf, int off) if (pref_bias_copy_store) { uasm_i_pref(buf, pref_dst_mode, pref_bias_copy_store + off, A0); - } else if (cpu_has_cache_cdex_s) { - uasm_i_cache(buf, Create_Dirty_Excl_SD, off, A0); - } else if (cpu_has_cache_cdex_p) { - if (R4600_V1_HIT_CACHEOP_WAR && cpu_is_r4600_v1_x()) { - uasm_i_nop(buf); - uasm_i_nop(buf); - uasm_i_nop(buf); - uasm_i_nop(buf); - } + } else if (cache_line_size == (half_copy_loop_size << 1)) { + if (cpu_has_cache_cdex_s) { + uasm_i_cache(buf, Create_Dirty_Excl_SD, off, A0); + } else if (cpu_has_cache_cdex_p) { + if (R4600_V1_HIT_CACHEOP_WAR && cpu_is_r4600_v1_x()) { + uasm_i_nop(buf); + uasm_i_nop(buf); + uasm_i_nop(buf); + uasm_i_nop(buf); + } - if (R4600_V2_HIT_CACHEOP_WAR && cpu_is_r4600_v2_x()) - uasm_i_lw(buf, ZERO, ZERO, AT); + if (R4600_V2_HIT_CACHEOP_WAR && cpu_is_r4600_v2_x()) + uasm_i_lw(buf, ZERO, ZERO, AT); - uasm_i_cache(buf, Create_Dirty_Excl_D, off, A0); + uasm_i_cache(buf, Create_Dirty_Excl_D, off, A0); + } } } diff --git a/arch/mips/mm/sc-rm7k.c b/arch/mips/mm/sc-rm7k.c index fc227f3b1199..e3abfb2d7e86 100644 --- a/arch/mips/mm/sc-rm7k.c +++ b/arch/mips/mm/sc-rm7k.c @@ -86,7 +86,7 @@ static void rm7k_sc_inv(unsigned long addr, unsigned long size) /* * This function is executed in uncached address space. */ -static __init void __rm7k_sc_enable(void) +static __cpuinit void __rm7k_sc_enable(void) { int i; @@ -107,7 +107,7 @@ static __init void __rm7k_sc_enable(void) } } -static __init void rm7k_sc_enable(void) +static __cpuinit void rm7k_sc_enable(void) { if (read_c0_config() & RM7K_CONF_SE) return; diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index cf37f5ca4b71..4d96e1db55ee 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -33,13 +33,14 @@ static struct legacy_serial_info { phys_addr_t taddr; } legacy_serial_infos[MAX_LEGACY_SERIAL_PORTS]; -static struct __initdata of_device_id parents[] = { +static struct __initdata of_device_id legacy_serial_parents[] = { {.type = "soc",}, {.type = "tsi-bridge",}, {.type = "opb", }, {.compatible = "ibm,opb",}, {.compatible = "simple-bus",}, {.compatible = "wrs,epld-localbus",}, + {}, }; static unsigned int legacy_serial_count; @@ -327,7 +328,7 @@ void __init find_legacy_serial_ports(void) struct device_node *parent = of_get_parent(np); if (!parent) continue; - if (of_match_node(parents, parent) != NULL) { + if (of_match_node(legacy_serial_parents, parent) != NULL) { index = add_legacy_soc_port(np, np); if (index >= 0 && np == stdout) legacy_serial_console = index; diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c index e79ad8afda07..3f37a6e62771 100644 --- a/arch/powerpc/kernel/of_platform.c +++ b/arch/powerpc/kernel/of_platform.c @@ -76,6 +76,8 @@ struct of_device* of_platform_device_create(struct device_node *np, return NULL; dev->dma_mask = 0xffffffffUL; + dev->dev.coherent_dma_mask = DMA_32BIT_MASK; + dev->dev.bus = &of_platform_bus_type; /* We do not fill the DMA ops for platform devices by default. diff --git a/arch/um/Makefile b/arch/um/Makefile index dbeab15e7bb7..ca40397017b9 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -77,7 +77,6 @@ include $(srctree)/$(ARCH_DIR)/Makefile-os-$(OS) KERNEL_DEFINES = $(strip -Derrno=kernel_errno -Dsigprocmask=kernel_sigprocmask \ -Dmktime=kernel_mktime $(ARCH_KERNEL_DEFINES)) KBUILD_CFLAGS += $(KERNEL_DEFINES) -KBUILD_CFLAGS += $(call cc-option,-fno-unit-at-a-time,) PHONY += linux diff --git a/arch/um/Makefile-i386 b/arch/um/Makefile-i386 index 561e373bd850..302cbe504543 100644 --- a/arch/um/Makefile-i386 +++ b/arch/um/Makefile-i386 @@ -32,4 +32,11 @@ cflags-y += $(call cc-option,-mpreferred-stack-boundary=2) # an unresolved reference. cflags-y += -ffreestanding +# Disable unit-at-a-time mode on pre-gcc-4.0 compilers, it makes gcc use +# a lot more stack due to the lack of sharing of stacklots. Also, gcc +# 4.3.0 needs -funit-at-a-time for extern inline functions. +KBUILD_CFLAGS += $(shell if [ $(call cc-version) -lt 0400 ] ; then \ + echo $(call cc-option,-fno-unit-at-a-time); \ + else echo $(call cc-option,-funit-at-a-time); fi ;) + KBUILD_CFLAGS += $(cflags-y) diff --git a/arch/um/Makefile-x86_64 b/arch/um/Makefile-x86_64 index 8ed362f93582..a9cd7e77a7ab 100644 --- a/arch/um/Makefile-x86_64 +++ b/arch/um/Makefile-x86_64 @@ -21,3 +21,6 @@ HEADER_ARCH := x86 LINK-$(CONFIG_LD_SCRIPT_DYN) += -Wl,-rpath,/lib64 LINK-y += -m64 + +# Do unit-at-a-time unconditionally on x86_64, following the host +KBUILD_CFLAGS += $(call cc-option,-funit-at-a-time) diff --git a/arch/x86/kernel/.gitignore b/arch/x86/kernel/.gitignore index 4ea38a39aed4..08f4fd731469 100644 --- a/arch/x86/kernel/.gitignore +++ b/arch/x86/kernel/.gitignore @@ -1,2 +1,3 @@ vsyscall.lds vsyscall_32.lds +vmlinux.lds diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 940185ecaeda..6e64aaf00d1d 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -328,18 +328,18 @@ static struct dmi_system_id __devinitdata pciprobe_dmi_table[] = { #endif { .callback = set_bf_sort, - .ident = "HP ProLiant DL360", + .ident = "HP ProLiant DL385 G2", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "HP"), - DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL360"), + DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL385 G2"), }, }, { .callback = set_bf_sort, - .ident = "HP ProLiant DL380", + .ident = "HP ProLiant DL585 G2", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "HP"), - DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL380"), + DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL585 G2"), }, }, {} diff --git a/crypto/chainiv.c b/crypto/chainiv.c index 6da3f577e4db..9affadee3287 100644 --- a/crypto/chainiv.c +++ b/crypto/chainiv.c @@ -117,6 +117,7 @@ static int chainiv_init(struct crypto_tfm *tfm) static int async_chainiv_schedule_work(struct async_chainiv_ctx *ctx) { int queued; + int err = ctx->err; if (!ctx->queue.qlen) { smp_mb__before_clear_bit(); @@ -131,7 +132,7 @@ static int async_chainiv_schedule_work(struct async_chainiv_ctx *ctx) BUG_ON(!queued); out: - return ctx->err; + return err; } static int async_chainiv_postpone_request(struct skcipher_givcrypt_request *req) @@ -227,6 +228,7 @@ static void async_chainiv_do_postponed(struct work_struct *work) postponed); struct skcipher_givcrypt_request *req; struct ablkcipher_request *subreq; + int err; /* Only handle one request at a time to avoid hogging keventd. */ spin_lock_bh(&ctx->lock); @@ -241,7 +243,11 @@ static void async_chainiv_do_postponed(struct work_struct *work) subreq = skcipher_givcrypt_reqctx(req); subreq->base.flags |= CRYPTO_TFM_REQ_MAY_SLEEP; - async_chainiv_givencrypt_tail(req); + err = async_chainiv_givencrypt_tail(req); + + local_bh_disable(); + skcipher_givcrypt_complete(req, err); + local_bh_enable(); } static int async_chainiv_init(struct crypto_tfm *tfm) diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c index 6beabc5abd07..e47f6e02133c 100644 --- a/crypto/tcrypt.c +++ b/crypto/tcrypt.c @@ -586,12 +586,6 @@ static void test_cipher(char *algo, int enc, j = 0; for (i = 0; i < tcount; i++) { - data = kzalloc(template[i].ilen, GFP_KERNEL); - if (!data) - continue; - - memcpy(data, template[i].input, template[i].ilen); - if (template[i].iv) memcpy(iv, template[i].iv, MAX_IVLEN); else @@ -613,10 +607,8 @@ static void test_cipher(char *algo, int enc, printk("setkey() failed flags=%x\n", crypto_ablkcipher_get_flags(tfm)); - if (!template[i].fail) { - kfree(data); + if (!template[i].fail) goto out; - } } temp = 0; diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 061817a3a0e5..5e6468a7ca4b 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -1777,7 +1777,7 @@ static irqreturn_t ahci_interrupt(int irq, void *dev_instance) struct ahci_host_priv *hpriv; unsigned int i, handled = 0; void __iomem *mmio; - u32 irq_stat; + u32 irq_stat, irq_masked; VPRINTK("ENTER\n"); @@ -1786,16 +1786,17 @@ static irqreturn_t ahci_interrupt(int irq, void *dev_instance) /* sigh. 0xffffffff is a valid return from h/w */ irq_stat = readl(mmio + HOST_IRQ_STAT); - irq_stat &= hpriv->port_map; if (!irq_stat) return IRQ_NONE; + irq_masked = irq_stat & hpriv->port_map; + spin_lock(&host->lock); for (i = 0; i < host->n_ports; i++) { struct ata_port *ap; - if (!(irq_stat & (1 << i))) + if (!(irq_masked & (1 << i))) continue; ap = host->ports[i]; @@ -1812,6 +1813,15 @@ static irqreturn_t ahci_interrupt(int irq, void *dev_instance) handled = 1; } + /* HOST_IRQ_STAT behaves as level triggered latch meaning that + * it should be cleared after all the port events are cleared; + * otherwise, it will raise a spurious interrupt after each + * valid one. Please read section 10.6.2 of ahci 1.1 for more + * information. + * + * Also, use the unmasked value to clear interrupt as spurious + * pending event on a dummy port might cause screaming IRQ. + */ writel(irq_stat, mmio + HOST_IRQ_STAT); spin_unlock(&host->lock); diff --git a/drivers/ide/arm/palm_bk3710.c b/drivers/ide/arm/palm_bk3710.c index cc24803fadff..2f2b4f4cf229 100644 --- a/drivers/ide/arm/palm_bk3710.c +++ b/drivers/ide/arm/palm_bk3710.c @@ -76,7 +76,7 @@ struct palm_bk3710_udmatiming { #include "../ide-timing.h" -static long ide_palm_clk; +static unsigned ideclk_period; /* in nanoseconds */ static const struct palm_bk3710_udmatiming palm_bk3710_udmatimings[6] = { {160, 240}, /* UDMA Mode 0 */ @@ -86,8 +86,6 @@ static const struct palm_bk3710_udmatiming palm_bk3710_udmatimings[6] = { {85, 60}, /* UDMA Mode 4 */ }; -static struct clk *ideclkp; - static void palm_bk3710_setudmamode(void __iomem *base, unsigned int dev, unsigned int mode) { @@ -97,10 +95,10 @@ static void palm_bk3710_setudmamode(void __iomem *base, unsigned int dev, /* DMA Data Setup */ t0 = DIV_ROUND_UP(palm_bk3710_udmatimings[mode].cycletime, - ide_palm_clk) - 1; - tenv = DIV_ROUND_UP(20, ide_palm_clk) - 1; + ideclk_period) - 1; + tenv = DIV_ROUND_UP(20, ideclk_period) - 1; trp = DIV_ROUND_UP(palm_bk3710_udmatimings[mode].rptime, - ide_palm_clk) - 1; + ideclk_period) - 1; /* udmatim Register */ val16 = readw(base + BK3710_UDMATIM) & (dev ? 0xFF0F : 0xFFF0); @@ -141,8 +139,8 @@ static void palm_bk3710_setdmamode(void __iomem *base, unsigned int dev, cycletime = max_t(int, t->cycle, min_cycle); /* DMA Data Setup */ - t0 = DIV_ROUND_UP(cycletime, ide_palm_clk); - td = DIV_ROUND_UP(t->active, ide_palm_clk); + t0 = DIV_ROUND_UP(cycletime, ideclk_period); + td = DIV_ROUND_UP(t->active, ideclk_period); tkw = t0 - td - 1; td -= 1; @@ -168,9 +166,9 @@ static void palm_bk3710_setpiomode(void __iomem *base, ide_drive_t *mate, struct ide_timing *t; /* PIO Data Setup */ - t0 = DIV_ROUND_UP(cycletime, ide_palm_clk); + t0 = DIV_ROUND_UP(cycletime, ideclk_period); t2 = DIV_ROUND_UP(ide_timing_find_mode(XFER_PIO_0 + mode)->active, - ide_palm_clk); + ideclk_period); t2i = t0 - t2 - 1; t2 -= 1; @@ -192,8 +190,8 @@ static void palm_bk3710_setpiomode(void __iomem *base, ide_drive_t *mate, /* TASKFILE Setup */ t = ide_timing_find_mode(XFER_PIO_0 + mode); - t0 = DIV_ROUND_UP(t->cyc8b, ide_palm_clk); - t2 = DIV_ROUND_UP(t->act8b, ide_palm_clk); + t0 = DIV_ROUND_UP(t->cyc8b, ideclk_period); + t2 = DIV_ROUND_UP(t->act8b, ideclk_period); t2i = t0 - t2 - 1; t2 -= 1; @@ -350,22 +348,22 @@ static const struct ide_port_info __devinitdata palm_bk3710_port_info = { static int __devinit palm_bk3710_probe(struct platform_device *pdev) { - struct clk *clkp; + struct clk *clk; struct resource *mem, *irq; ide_hwif_t *hwif; - unsigned long base; + unsigned long base, rate; int i; hw_regs_t hw; u8 idx[4] = { 0xff, 0xff, 0xff, 0xff }; - clkp = clk_get(NULL, "IDECLK"); - if (IS_ERR(clkp)) + clk = clk_get(NULL, "IDECLK"); + if (IS_ERR(clk)) return -ENODEV; - ideclkp = clkp; - clk_enable(ideclkp); - ide_palm_clk = clk_get_rate(ideclkp)/100000; - ide_palm_clk = (10000/ide_palm_clk) + 1; + clk_enable(clk); + rate = clk_get_rate(clk); + ideclk_period = 1000000000UL / rate; + /* Register the IDE interface with Linux ATA Interface */ memset(&hw, 0, sizeof(hw)); diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c index 380fa0c8cc84..26e68b65b7cf 100644 --- a/drivers/ide/ide-probe.c +++ b/drivers/ide/ide-probe.c @@ -646,8 +646,6 @@ static int ide_register_port(ide_hwif_t *hwif) goto out; } - get_device(&hwif->gendev); - hwif->portdev = device_create_drvdata(ide_port_class, &hwif->gendev, MKDEV(0, 0), hwif, hwif->name); if (IS_ERR(hwif->portdev)) { @@ -1220,16 +1218,12 @@ static void drive_release_dev (struct device *dev) complete(&drive->gendev_rel_comp); } -#ifndef ide_default_irq -#define ide_default_irq(irq) 0 -#endif - static int hwif_init(ide_hwif_t *hwif) { int old_irq; if (!hwif->irq) { - hwif->irq = ide_default_irq(hwif->io_ports.data_addr); + hwif->irq = __ide_default_irq(hwif->io_ports.data_addr); if (!hwif->irq) { printk("%s: DISABLED, NO IRQ\n", hwif->name); return 0; @@ -1259,7 +1253,7 @@ static int hwif_init(ide_hwif_t *hwif) * It failed to initialise. Find the default IRQ for * this port and try that. */ - hwif->irq = ide_default_irq(hwif->io_ports.data_addr); + hwif->irq = __ide_default_irq(hwif->io_ports.data_addr); if (!hwif->irq) { printk("%s: Disabled unable to get IRQ %d.\n", hwif->name, old_irq); diff --git a/drivers/ide/ide.c b/drivers/ide/ide.c index c758dcb13b14..300431d080a9 100644 --- a/drivers/ide/ide.c +++ b/drivers/ide/ide.c @@ -315,13 +315,14 @@ void ide_unregister(ide_hwif_t *hwif) BUG_ON(in_interrupt()); BUG_ON(irqs_disabled()); + mutex_lock(&ide_cfg_mtx); - spin_lock_irq(&ide_lock); - if (!hwif->present) - goto abort; - __ide_port_unregister_devices(hwif); - hwif->present = 0; + spin_lock_irq(&ide_lock); + if (hwif->present) { + __ide_port_unregister_devices(hwif); + hwif->present = 0; + } spin_unlock_irq(&ide_lock); ide_proc_unregister_port(hwif); @@ -351,16 +352,15 @@ void ide_unregister(ide_hwif_t *hwif) blk_unregister_region(MKDEV(hwif->major, 0), MAX_DRIVES<<PARTN_BITS); kfree(hwif->sg_table); unregister_blkdev(hwif->major, hwif->name); - spin_lock_irq(&ide_lock); if (hwif->dma_base) ide_release_dma_engine(hwif); + spin_lock_irq(&ide_lock); /* restore hwif data to pristine status */ ide_init_port_data(hwif, hwif->index); - -abort: spin_unlock_irq(&ide_lock); + mutex_unlock(&ide_cfg_mtx); } @@ -1094,13 +1094,6 @@ struct bus_type ide_bus_type = { EXPORT_SYMBOL_GPL(ide_bus_type); -static void ide_port_class_release(struct device *portdev) -{ - ide_hwif_t *hwif = dev_get_drvdata(portdev); - - put_device(&hwif->gendev); -} - int ide_vlb_clk; EXPORT_SYMBOL_GPL(ide_vlb_clk); @@ -1305,7 +1298,6 @@ static int __init ide_init(void) ret = PTR_ERR(ide_port_class); goto out_port_class; } - ide_port_class->dev_release = ide_port_class_release; init_ide_data(); diff --git a/drivers/ide/pci/it8213.c b/drivers/ide/pci/it8213.c index 9053c8771e6e..2b71bdf74e73 100644 --- a/drivers/ide/pci/it8213.c +++ b/drivers/ide/pci/it8213.c @@ -184,8 +184,7 @@ static const struct ide_port_info it8213_chipsets[] __devinitdata = { static int __devinit it8213_init_one(struct pci_dev *dev, const struct pci_device_id *id) { - ide_setup_pci_device(dev, &it8213_chipsets[id->driver_data]); - return 0; + return ide_setup_pci_device(dev, &it8213_chipsets[id->driver_data]); } static const struct pci_device_id it8213_pci_tbl[] = { diff --git a/drivers/ide/pci/ns87415.c b/drivers/ide/pci/ns87415.c index fec4955f449b..a7a41bb82778 100644 --- a/drivers/ide/pci/ns87415.c +++ b/drivers/ide/pci/ns87415.c @@ -225,10 +225,6 @@ static int ns87415_dma_setup(ide_drive_t *drive) return 1; } -#ifndef ide_default_irq -#define ide_default_irq(irq) 0 -#endif - static void __devinit init_hwif_ns87415 (ide_hwif_t *hwif) { struct pci_dev *dev = to_pci_dev(hwif->dev); @@ -288,7 +284,7 @@ static void __devinit init_hwif_ns87415 (ide_hwif_t *hwif) } if (!using_inta) - hwif->irq = ide_default_irq(hwif->io_ports.data_addr); + hwif->irq = __ide_default_irq(hwif->io_ports.data_addr); else if (!hwif->irq && hwif->mate && hwif->mate->irq) hwif->irq = hwif->mate->irq; /* share IRQ with mate */ diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c index 8934178a23ee..95f82cfb6c54 100644 --- a/drivers/infiniband/hw/cxgb3/iwch_provider.c +++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c @@ -1096,7 +1096,9 @@ static ssize_t show_fw_ver(struct device *dev, struct device_attribute *attr, ch struct net_device *lldev = iwch_dev->rdev.t3cdev_p->lldev; PDBG("%s dev 0x%p\n", __func__, dev); + rtnl_lock(); lldev->ethtool_ops->get_drvinfo(lldev, &info); + rtnl_unlock(); return sprintf(buf, "%s\n", info.fw_version); } @@ -1109,7 +1111,9 @@ static ssize_t show_hca(struct device *dev, struct device_attribute *attr, struct net_device *lldev = iwch_dev->rdev.t3cdev_p->lldev; PDBG("%s dev 0x%p\n", __func__, dev); + rtnl_lock(); lldev->ethtool_ops->get_drvinfo(lldev, &info); + rtnl_unlock(); return sprintf(buf, "%s\n", info.driver); } diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 54c8ee28fcc4..3b27df52456b 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -2017,12 +2017,7 @@ static int __handle_issuing_new_read_requests5(struct stripe_head *sh, */ s->uptodate++; return 0; /* uptodate + compute == disks */ - } else if ((s->uptodate < disks - 1) && - test_bit(R5_Insync, &dev->flags)) { - /* Note: we hold off compute operations while checks are - * in flight, but we still prefer 'compute' over 'read' - * hence we only read if (uptodate < * disks-1) - */ + } else if (test_bit(R5_Insync, &dev->flags)) { set_bit(R5_LOCKED, &dev->flags); set_bit(R5_Wantread, &dev->flags); if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending)) diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c index 65210fca37ed..d89475d36988 100644 --- a/drivers/mmc/host/pxamci.c +++ b/drivers/mmc/host/pxamci.c @@ -114,6 +114,7 @@ static void pxamci_setup_data(struct pxamci_host *host, struct mmc_data *data) unsigned int nob = data->blocks; unsigned long long clks; unsigned int timeout; + bool dalgn = 0; u32 dcmd; int i; @@ -152,6 +153,9 @@ static void pxamci_setup_data(struct pxamci_host *host, struct mmc_data *data) host->sg_cpu[i].dcmd = dcmd | length; if (length & 31 && !(data->flags & MMC_DATA_READ)) host->sg_cpu[i].dcmd |= DCMD_ENDIRQEN; + /* Not aligned to 8-byte boundary? */ + if (sg_dma_address(&data->sg[i]) & 0x7) + dalgn = 1; if (data->flags & MMC_DATA_READ) { host->sg_cpu[i].dsadr = host->res->start + MMC_RXFIFO; host->sg_cpu[i].dtadr = sg_dma_address(&data->sg[i]); @@ -165,6 +169,15 @@ static void pxamci_setup_data(struct pxamci_host *host, struct mmc_data *data) host->sg_cpu[host->dma_len - 1].ddadr = DDADR_STOP; wmb(); + /* + * The PXA27x DMA controller encounters overhead when working with + * unaligned (to 8-byte boundaries) data, so switch on byte alignment + * mode only if we have unaligned data. + */ + if (dalgn) + DALGN |= (1 << host->dma); + else + DALGN &= (1 << host->dma); DDADR(host->dma) = host->sg_dma; DCSR(host->dma) = DCSR_RUN; } diff --git a/drivers/net/ehea/ehea.h b/drivers/net/ehea/ehea.h index fe872fbd671e..e01926b7b5b7 100644 --- a/drivers/net/ehea/ehea.h +++ b/drivers/net/ehea/ehea.h @@ -40,7 +40,7 @@ #include <asm/io.h> #define DRV_NAME "ehea" -#define DRV_VERSION "EHEA_0091" +#define DRV_VERSION "EHEA_0092" /* eHEA capability flags */ #define DLPAR_PORT_ADD_REM 1 @@ -452,7 +452,7 @@ struct ehea_bcmc_reg_entry { struct ehea_bcmc_reg_array { struct ehea_bcmc_reg_entry *arr; int num_entries; - struct mutex lock; + spinlock_t lock; }; #define EHEA_PORT_UP 1 @@ -478,6 +478,7 @@ struct ehea_port { int num_add_tx_qps; int num_mcs; int resets; + u64 flags; u64 mac_addr; u32 logical_port_id; u32 port_speed; @@ -501,7 +502,8 @@ struct port_res_cfg { }; enum ehea_flag_bits { - __EHEA_STOP_XFER + __EHEA_STOP_XFER, + __EHEA_DISABLE_PORT_RESET }; void ehea_set_ethtool_ops(struct net_device *netdev); diff --git a/drivers/net/ehea/ehea_main.c b/drivers/net/ehea/ehea_main.c index 075fd547421e..0920b796bd78 100644 --- a/drivers/net/ehea/ehea_main.c +++ b/drivers/net/ehea/ehea_main.c @@ -118,6 +118,7 @@ static struct of_device_id ehea_device_table[] = { }, {}, }; +MODULE_DEVICE_TABLE(of, ehea_device_table); static struct of_platform_driver ehea_driver = { .name = "ehea", @@ -137,6 +138,12 @@ void ehea_dump(void *adr, int len, char *msg) } } +void ehea_schedule_port_reset(struct ehea_port *port) +{ + if (!test_bit(__EHEA_DISABLE_PORT_RESET, &port->flags)) + schedule_work(&port->reset_task); +} + static void ehea_update_firmware_handles(void) { struct ehea_fw_handle_entry *arr = NULL; @@ -241,7 +248,7 @@ static void ehea_update_bcmc_registrations(void) } if (num_registrations) { - arr = kzalloc(num_registrations * sizeof(*arr), GFP_KERNEL); + arr = kzalloc(num_registrations * sizeof(*arr), GFP_ATOMIC); if (!arr) return; /* Keep the existing array */ } else @@ -301,7 +308,7 @@ static struct net_device_stats *ehea_get_stats(struct net_device *dev) memset(stats, 0, sizeof(*stats)); - cb2 = kzalloc(PAGE_SIZE, GFP_KERNEL); + cb2 = kzalloc(PAGE_SIZE, GFP_ATOMIC); if (!cb2) { ehea_error("no mem for cb2"); goto out; @@ -587,7 +594,7 @@ static int ehea_treat_poll_error(struct ehea_port_res *pr, int rq, "Resetting port.", pr->qp->init_attr.qp_nr); ehea_dump(cqe, sizeof(*cqe), "CQE"); } - schedule_work(&pr->port->reset_task); + ehea_schedule_port_reset(pr->port); return 1; } @@ -616,7 +623,7 @@ static int get_skb_hdr(struct sk_buff *skb, void **iphdr, *tcph = tcp_hdr(skb); /* check if ip header and tcp header are complete */ - if (iph->tot_len < ip_len + tcp_hdrlen(skb)) + if (ntohs(iph->tot_len) < ip_len + tcp_hdrlen(skb)) return -1; *hdr_flags = LRO_IPV4 | LRO_TCP; @@ -765,7 +772,7 @@ static struct ehea_cqe *ehea_proc_cqes(struct ehea_port_res *pr, int my_quota) ehea_error("Send Completion Error: Resetting port"); if (netif_msg_tx_err(pr->port)) ehea_dump(cqe, sizeof(*cqe), "Send CQE"); - schedule_work(&pr->port->reset_task); + ehea_schedule_port_reset(pr->port); break; } @@ -885,7 +892,7 @@ static irqreturn_t ehea_qp_aff_irq_handler(int irq, void *param) eqe = ehea_poll_eq(port->qp_eq); } - schedule_work(&port->reset_task); + ehea_schedule_port_reset(port); return IRQ_HANDLED; } @@ -1763,7 +1770,7 @@ static int ehea_set_mac_addr(struct net_device *dev, void *sa) memcpy(dev->dev_addr, mac_addr->sa_data, dev->addr_len); - mutex_lock(&ehea_bcmc_regs.lock); + spin_lock(&ehea_bcmc_regs.lock); /* Deregister old MAC in pHYP */ if (port->state == EHEA_PORT_UP) { @@ -1785,7 +1792,7 @@ static int ehea_set_mac_addr(struct net_device *dev, void *sa) out_upregs: ehea_update_bcmc_registrations(); - mutex_unlock(&ehea_bcmc_regs.lock); + spin_unlock(&ehea_bcmc_regs.lock); out_free: kfree(cb0); out: @@ -1947,7 +1954,7 @@ static void ehea_set_multicast_list(struct net_device *dev) } ehea_promiscuous(dev, 0); - mutex_lock(&ehea_bcmc_regs.lock); + spin_lock(&ehea_bcmc_regs.lock); if (dev->flags & IFF_ALLMULTI) { ehea_allmulti(dev, 1); @@ -1978,7 +1985,7 @@ static void ehea_set_multicast_list(struct net_device *dev) } out: ehea_update_bcmc_registrations(); - mutex_unlock(&ehea_bcmc_regs.lock); + spin_unlock(&ehea_bcmc_regs.lock); return; } @@ -2497,7 +2504,7 @@ static int ehea_up(struct net_device *dev) } } - mutex_lock(&ehea_bcmc_regs.lock); + spin_lock(&ehea_bcmc_regs.lock); ret = ehea_broadcast_reg_helper(port, H_REG_BCMC); if (ret) { @@ -2520,7 +2527,7 @@ out: ehea_info("Failed starting %s. ret=%i", dev->name, ret); ehea_update_bcmc_registrations(); - mutex_unlock(&ehea_bcmc_regs.lock); + spin_unlock(&ehea_bcmc_regs.lock); ehea_update_firmware_handles(); mutex_unlock(&ehea_fw_handles.lock); @@ -2575,7 +2582,7 @@ static int ehea_down(struct net_device *dev) mutex_lock(&ehea_fw_handles.lock); - mutex_lock(&ehea_bcmc_regs.lock); + spin_lock(&ehea_bcmc_regs.lock); ehea_drop_multicast_list(dev); ehea_broadcast_reg_helper(port, H_DEREG_BCMC); @@ -2584,7 +2591,7 @@ static int ehea_down(struct net_device *dev) port->state = EHEA_PORT_DOWN; ehea_update_bcmc_registrations(); - mutex_unlock(&ehea_bcmc_regs.lock); + spin_unlock(&ehea_bcmc_regs.lock); ret = ehea_clean_all_portres(port); if (ret) @@ -2605,13 +2612,14 @@ static int ehea_stop(struct net_device *dev) if (netif_msg_ifdown(port)) ehea_info("disabling port %s", dev->name); + set_bit(__EHEA_DISABLE_PORT_RESET, &port->flags); cancel_work_sync(&port->reset_task); - mutex_lock(&port->port_lock); netif_stop_queue(dev); port_napi_disable(port); ret = ehea_down(dev); mutex_unlock(&port->port_lock); + clear_bit(__EHEA_DISABLE_PORT_RESET, &port->flags); return ret; } @@ -2941,7 +2949,7 @@ static void ehea_tx_watchdog(struct net_device *dev) if (netif_carrier_ok(dev) && !test_bit(__EHEA_STOP_XFER, &ehea_driver_flags)) - schedule_work(&port->reset_task); + ehea_schedule_port_reset(port); } int ehea_sense_adapter_attr(struct ehea_adapter *adapter) @@ -3590,7 +3598,7 @@ int __init ehea_module_init(void) memset(&ehea_bcmc_regs, 0, sizeof(ehea_bcmc_regs)); mutex_init(&ehea_fw_handles.lock); - mutex_init(&ehea_bcmc_regs.lock); + spin_lock_init(&ehea_bcmc_regs.lock); ret = check_module_parm(); if (ret) diff --git a/drivers/net/forcedeth.c b/drivers/net/forcedeth.c index 2cb244763292..20d4fe96a81c 100644 --- a/drivers/net/forcedeth.c +++ b/drivers/net/forcedeth.c @@ -4194,12 +4194,23 @@ static int nv_set_settings(struct net_device *dev, struct ethtool_cmd *ecmd) netif_carrier_off(dev); if (netif_running(dev)) { + unsigned long flags; + nv_disable_irq(dev); netif_tx_lock_bh(dev); - spin_lock(&np->lock); + /* with plain spinlock lockdep complains */ + spin_lock_irqsave(&np->lock, flags); /* stop engines */ + /* FIXME: + * this can take some time, and interrupts are disabled + * due to spin_lock_irqsave, but let's hope no daemon + * is going to change the settings very often... + * Worst case: + * NV_RXSTOP_DELAY1MAX + NV_TXSTOP_DELAY1MAX + * + some minor delays, which is up to a second approximately + */ nv_stop_rxtx(dev); - spin_unlock(&np->lock); + spin_unlock_irqrestore(&np->lock, flags); netif_tx_unlock_bh(dev); } diff --git a/drivers/net/fs_enet/mac-fcc.c b/drivers/net/fs_enet/mac-fcc.c index e36321152d50..8268b3535b30 100644 --- a/drivers/net/fs_enet/mac-fcc.c +++ b/drivers/net/fs_enet/mac-fcc.c @@ -463,6 +463,9 @@ static void restart(struct net_device *dev) else C32(fccp, fcc_fpsmr, FCC_PSMR_FDE | FCC_PSMR_LPB); + /* Restore multicast and promiscuous settings */ + set_multicast_list(dev); + S32(fccp, fcc_gfmr, FCC_GFMR_ENR | FCC_GFMR_ENT); } diff --git a/drivers/net/ibm_newemac/core.c b/drivers/net/ibm_newemac/core.c index 5d2108c5ac7c..babc79ad490b 100644 --- a/drivers/net/ibm_newemac/core.c +++ b/drivers/net/ibm_newemac/core.c @@ -1636,6 +1636,12 @@ static int emac_poll_rx(void *param, int budget) goto next; } + if (len < ETH_HLEN) { + ++dev->estats.rx_dropped_stack; + emac_recycle_rx_skb(dev, slot, len); + goto next; + } + if (len && len < EMAC_RX_COPY_THRESH) { struct sk_buff *copy_skb = alloc_skb(len + EMAC_RX_SKB_HEADROOM + 2, GFP_ATOMIC); @@ -2719,6 +2725,8 @@ static int __devinit emac_probe(struct of_device *ofdev, /* Clean rings */ memset(dev->tx_desc, 0, NUM_TX_BUFF * sizeof(struct mal_descriptor)); memset(dev->rx_desc, 0, NUM_RX_BUFF * sizeof(struct mal_descriptor)); + memset(dev->tx_skb, 0, NUM_TX_BUFF * sizeof(struct sk_buff *)); + memset(dev->rx_skb, 0, NUM_RX_BUFF * sizeof(struct sk_buff *)); /* Attach to ZMII, if needed */ if (emac_has_feature(dev, EMAC_FTR_HAS_ZMII) && diff --git a/drivers/net/pasemi_mac.c b/drivers/net/pasemi_mac.c index 3b2a6c598088..993d87c9296f 100644 --- a/drivers/net/pasemi_mac.c +++ b/drivers/net/pasemi_mac.c @@ -277,7 +277,7 @@ static int get_skb_hdr(struct sk_buff *skb, void **iphdr, *tcph = tcp_hdr(skb); /* check if ip header and tcp header are complete */ - if (iph->tot_len < ip_len + tcp_hdrlen(skb)) + if (ntohs(iph->tot_len) < ip_len + tcp_hdrlen(skb)) return -1; *hdr_flags = LRO_IPV4 | LRO_TCP; diff --git a/drivers/net/wan/hdlc_fr.c b/drivers/net/wan/hdlc_fr.c index 520bb0b1a9a2..6d35155c7145 100644 --- a/drivers/net/wan/hdlc_fr.c +++ b/drivers/net/wan/hdlc_fr.c @@ -1008,6 +1008,7 @@ static int fr_rx(struct sk_buff *skb) stats->rx_bytes += skb->len; if (pvc->state.becn) stats->rx_compressed++; + skb->dev = dev; netif_rx(skb); return NET_RX_SUCCESS; } else { diff --git a/drivers/net/wireless/iwlwifi/iwl-3945.c b/drivers/net/wireless/iwlwifi/iwl-3945.c index 62a3d8f8563e..f5387a7a76c0 100644 --- a/drivers/net/wireless/iwlwifi/iwl-3945.c +++ b/drivers/net/wireless/iwlwifi/iwl-3945.c @@ -588,8 +588,12 @@ static void iwl3945_add_radiotap(struct iwl3945_priv *priv, if (rate == -1) iwl3945_rt->rt_rate = 0; - else + else { + if (stats->band == IEEE80211_BAND_5GHZ) + rate += IWL_FIRST_OFDM_RATE; + iwl3945_rt->rt_rate = iwl3945_rates[rate].ieee; + } /* antenna number */ antenna = phy_flags_hw & RX_RES_PHY_FLAGS_ANTENNA_MSK; diff --git a/drivers/net/wireless/iwlwifi/iwl-4965.c b/drivers/net/wireless/iwlwifi/iwl-4965.c index bf19eb8aafd0..de330ae0ca95 100644 --- a/drivers/net/wireless/iwlwifi/iwl-4965.c +++ b/drivers/net/wireless/iwlwifi/iwl-4965.c @@ -3528,8 +3528,12 @@ static void iwl4965_add_radiotap(struct iwl_priv *priv, if (rate == -1) iwl4965_rt->rt_rate = 0; - else + else { + if (stats->band == IEEE80211_BAND_5GHZ) + rate += IWL_FIRST_OFDM_RATE; + iwl4965_rt->rt_rate = iwl4965_rates[rate].ieee; + } /* * "antenna number" diff --git a/drivers/net/wireless/iwlwifi/iwl3945-base.c b/drivers/net/wireless/iwlwifi/iwl3945-base.c index b1b3c523185d..6027e1119c3f 100644 --- a/drivers/net/wireless/iwlwifi/iwl3945-base.c +++ b/drivers/net/wireless/iwlwifi/iwl3945-base.c @@ -6687,7 +6687,8 @@ static int iwl3945_mac_tx(struct ieee80211_hw *hw, struct sk_buff *skb, if (priv->iw_mode == IEEE80211_IF_TYPE_MNTR) { IWL_DEBUG_MAC80211("leave - monitor\n"); - return -1; + dev_kfree_skb_any(skb); + return 0; } IWL_DEBUG_TX("dev->xmit(%d bytes) at rate 0x%02x\n", skb->len, diff --git a/drivers/net/wireless/iwlwifi/iwl4965-base.c b/drivers/net/wireless/iwlwifi/iwl4965-base.c index 5ed16ce78468..0bd55bb19739 100644 --- a/drivers/net/wireless/iwlwifi/iwl4965-base.c +++ b/drivers/net/wireless/iwlwifi/iwl4965-base.c @@ -6237,7 +6237,8 @@ static int iwl4965_mac_tx(struct ieee80211_hw *hw, struct sk_buff *skb, if (priv->iw_mode == IEEE80211_IF_TYPE_MNTR) { IWL_DEBUG_MAC80211("leave - monitor\n"); - return -1; + dev_kfree_skb_any(skb); + return 0; } IWL_DEBUG_TX("dev->xmit(%d bytes) at rate 0x%02x\n", skb->len, diff --git a/drivers/net/wireless/libertas/if_usb.c b/drivers/net/wireless/libertas/if_usb.c index 8032df72aaab..36288b29abf7 100644 --- a/drivers/net/wireless/libertas/if_usb.c +++ b/drivers/net/wireless/libertas/if_usb.c @@ -925,6 +925,7 @@ static struct usb_driver if_usb_driver = { .id_table = if_usb_table, .suspend = if_usb_suspend, .resume = if_usb_resume, + .reset_resume = if_usb_resume, }; static int __init if_usb_init_module(void) diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 7158dbb6e4b4..42a436478b78 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -924,6 +924,15 @@ static int register_root_hub(struct usb_hcd *hcd) return retval; } +void usb_enable_root_hub_irq (struct usb_bus *bus) +{ + struct usb_hcd *hcd; + + hcd = container_of (bus, struct usb_hcd, self); + if (hcd->driver->hub_irq_enable && hcd->state != HC_STATE_HALT) + hcd->driver->hub_irq_enable (hcd); +} + /*-------------------------------------------------------------------------*/ diff --git a/drivers/usb/core/hcd.h b/drivers/usb/core/hcd.h index a0bf5df6cb6f..b9de1569b39e 100644 --- a/drivers/usb/core/hcd.h +++ b/drivers/usb/core/hcd.h @@ -210,6 +210,8 @@ struct hc_driver { int (*bus_suspend)(struct usb_hcd *); int (*bus_resume)(struct usb_hcd *); int (*start_port_reset)(struct usb_hcd *, unsigned port_num); + void (*hub_irq_enable)(struct usb_hcd *); + /* Needed only if port-change IRQs are level-triggered */ /* force handover of high-speed port to full-speed companion */ void (*relinquish_port)(struct usb_hcd *, int); diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 512d2d57d41e..4cfe32a16c37 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -2073,6 +2073,8 @@ int usb_port_resume(struct usb_device *udev) } clear_bit(port1, hub->busy_bits); + if (!hub->hdev->parent && !hub->busy_bits[0]) + usb_enable_root_hub_irq(hub->hdev->bus); if (status == 0) status = finish_port_resume(udev); @@ -3002,6 +3004,11 @@ static void hub_events(void) hub->activating = 0; + /* If this is a root hub, tell the HCD it's okay to + * re-enable port-change interrupts now. */ + if (!hdev->parent && !hub->busy_bits[0]) + usb_enable_root_hub_irq(hdev->bus); + loop_autopm: /* Allow autosuspend if we're not going to run again */ if (list_empty(&hub->event_list)) @@ -3227,6 +3234,8 @@ int usb_reset_device(struct usb_device *udev) break; } clear_bit(port1, parent_hub->busy_bits); + if (!parent_hdev->parent && !parent_hub->busy_bits[0]) + usb_enable_root_hub_irq(parent_hdev->bus); if (ret < 0) goto re_enumerate; diff --git a/drivers/usb/host/ohci-at91.c b/drivers/usb/host/ohci-at91.c index c96db1153dcf..e534f9de0f05 100644 --- a/drivers/usb/host/ohci-at91.c +++ b/drivers/usb/host/ohci-at91.c @@ -261,6 +261,7 @@ static const struct hc_driver ohci_at91_hc_driver = { */ .hub_status_data = ohci_hub_status_data, .hub_control = ohci_hub_control, + .hub_irq_enable = ohci_rhsc_enable, #ifdef CONFIG_PM .bus_suspend = ohci_bus_suspend, .bus_resume = ohci_bus_resume, diff --git a/drivers/usb/host/ohci-au1xxx.c b/drivers/usb/host/ohci-au1xxx.c index 1b9abdba920b..f90fe0c7373f 100644 --- a/drivers/usb/host/ohci-au1xxx.c +++ b/drivers/usb/host/ohci-au1xxx.c @@ -288,6 +288,7 @@ static const struct hc_driver ohci_au1xxx_hc_driver = { */ .hub_status_data = ohci_hub_status_data, .hub_control = ohci_hub_control, + .hub_irq_enable = ohci_rhsc_enable, #ifdef CONFIG_PM .bus_suspend = ohci_bus_suspend, .bus_resume = ohci_bus_resume, diff --git a/drivers/usb/host/ohci-ep93xx.c b/drivers/usb/host/ohci-ep93xx.c index 06aadfb0ec29..5adaf36e47d0 100644 --- a/drivers/usb/host/ohci-ep93xx.c +++ b/drivers/usb/host/ohci-ep93xx.c @@ -135,6 +135,7 @@ static struct hc_driver ohci_ep93xx_hc_driver = { .get_frame_number = ohci_get_frame, .hub_status_data = ohci_hub_status_data, .hub_control = ohci_hub_control, + .hub_irq_enable = ohci_rhsc_enable, #ifdef CONFIG_PM .bus_suspend = ohci_bus_suspend, .bus_resume = ohci_bus_resume, diff --git a/drivers/usb/host/ohci-hub.c b/drivers/usb/host/ohci-hub.c index 79a78029f896..b56739221d11 100644 --- a/drivers/usb/host/ohci-hub.c +++ b/drivers/usb/host/ohci-hub.c @@ -36,6 +36,18 @@ /*-------------------------------------------------------------------------*/ +/* hcd->hub_irq_enable() */ +static void ohci_rhsc_enable (struct usb_hcd *hcd) +{ + struct ohci_hcd *ohci = hcd_to_ohci (hcd); + + spin_lock_irq(&ohci->lock); + if (!ohci->autostop) + del_timer(&hcd->rh_timer); /* Prevent next poll */ + ohci_writel(ohci, OHCI_INTR_RHSC, &ohci->regs->intrenable); + spin_unlock_irq(&ohci->lock); +} + #define OHCI_SCHED_ENABLES \ (OHCI_CTRL_CLE|OHCI_CTRL_BLE|OHCI_CTRL_PLE|OHCI_CTRL_IE) @@ -362,28 +374,18 @@ static int ohci_root_hub_state_changes(struct ohci_hcd *ohci, int changed, int any_connected) { int poll_rh = 1; - int rhsc; - rhsc = ohci_readl(ohci, &ohci->regs->intrenable) & OHCI_INTR_RHSC; switch (ohci->hc_control & OHCI_CTRL_HCFS) { case OHCI_USB_OPER: - /* If no status changes are pending, enable status-change - * interrupts. - */ - if (!rhsc && !changed) { - rhsc = OHCI_INTR_RHSC; - ohci_writel(ohci, rhsc, &ohci->regs->intrenable); - } - - /* Keep on polling until we know a device is connected - * and RHSC is enabled, or until we autostop. - */ + /* keep on polling until we know a device is connected + * and RHSC is enabled */ if (!ohci->autostop) { if (any_connected || !device_may_wakeup(&ohci_to_hcd(ohci) ->self.root_hub->dev)) { - if (rhsc) + if (ohci_readl(ohci, &ohci->regs->intrenable) & + OHCI_INTR_RHSC) poll_rh = 0; } else { ohci->autostop = 1; @@ -396,13 +398,12 @@ static int ohci_root_hub_state_changes(struct ohci_hcd *ohci, int changed, ohci->autostop = 0; ohci->next_statechange = jiffies + STATECHANGE_DELAY; - } else if (rhsc && time_after_eq(jiffies, + } else if (time_after_eq(jiffies, ohci->next_statechange) && !ohci->ed_rm_list && !(ohci->hc_control & OHCI_SCHED_ENABLES)) { ohci_rh_suspend(ohci, 1); - poll_rh = 0; } } break; @@ -416,12 +417,6 @@ static int ohci_root_hub_state_changes(struct ohci_hcd *ohci, int changed, else usb_hcd_resume_root_hub(ohci_to_hcd(ohci)); } else { - if (!rhsc && (ohci->autostop || - ohci_to_hcd(ohci)->self.root_hub-> - do_remote_wakeup)) - ohci_writel(ohci, OHCI_INTR_RHSC, - &ohci->regs->intrenable); - /* everything is idle, no need for polling */ poll_rh = 0; } @@ -443,16 +438,12 @@ static inline int ohci_rh_resume(struct ohci_hcd *ohci) static int ohci_root_hub_state_changes(struct ohci_hcd *ohci, int changed, int any_connected) { - /* If RHSC is enabled, don't poll */ - if (ohci_readl(ohci, &ohci->regs->intrenable) & OHCI_INTR_RHSC) - return 0; + int poll_rh = 1; - /* If no status changes are pending, enable status-change interrupts */ - if (!changed) { - ohci_writel(ohci, OHCI_INTR_RHSC, &ohci->regs->intrenable); - return 0; - } - return 1; + /* keep on polling until RHSC is enabled */ + if (ohci_readl(ohci, &ohci->regs->intrenable) & OHCI_INTR_RHSC) + poll_rh = 0; + return poll_rh; } #endif /* CONFIG_PM */ diff --git a/drivers/usb/host/ohci-lh7a404.c b/drivers/usb/host/ohci-lh7a404.c index 96d14fa1d833..13c12ed22252 100644 --- a/drivers/usb/host/ohci-lh7a404.c +++ b/drivers/usb/host/ohci-lh7a404.c @@ -193,6 +193,7 @@ static const struct hc_driver ohci_lh7a404_hc_driver = { */ .hub_status_data = ohci_hub_status_data, .hub_control = ohci_hub_control, + .hub_irq_enable = ohci_rhsc_enable, #ifdef CONFIG_PM .bus_suspend = ohci_bus_suspend, .bus_resume = ohci_bus_resume, diff --git a/drivers/usb/host/ohci-omap.c b/drivers/usb/host/ohci-omap.c index 6859fb5f1d6f..3a7c24c03671 100644 --- a/drivers/usb/host/ohci-omap.c +++ b/drivers/usb/host/ohci-omap.c @@ -466,6 +466,7 @@ static const struct hc_driver ohci_omap_hc_driver = { */ .hub_status_data = ohci_hub_status_data, .hub_control = ohci_hub_control, + .hub_irq_enable = ohci_rhsc_enable, #ifdef CONFIG_PM .bus_suspend = ohci_bus_suspend, .bus_resume = ohci_bus_resume, diff --git a/drivers/usb/host/ohci-pci.c b/drivers/usb/host/ohci-pci.c index 3bf175d95a23..4696cc912e16 100644 --- a/drivers/usb/host/ohci-pci.c +++ b/drivers/usb/host/ohci-pci.c @@ -327,6 +327,7 @@ static const struct hc_driver ohci_pci_hc_driver = { */ .hub_status_data = ohci_hub_status_data, .hub_control = ohci_hub_control, + .hub_irq_enable = ohci_rhsc_enable, #ifdef CONFIG_PM .bus_suspend = ohci_bus_suspend, .bus_resume = ohci_bus_resume, diff --git a/drivers/usb/host/ohci-pnx4008.c b/drivers/usb/host/ohci-pnx4008.c index 664f07ee8732..28b458f20cc3 100644 --- a/drivers/usb/host/ohci-pnx4008.c +++ b/drivers/usb/host/ohci-pnx4008.c @@ -280,6 +280,7 @@ static const struct hc_driver ohci_pnx4008_hc_driver = { */ .hub_status_data = ohci_hub_status_data, .hub_control = ohci_hub_control, + .hub_irq_enable = ohci_rhsc_enable, #ifdef CONFIG_PM .bus_suspend = ohci_bus_suspend, .bus_resume = ohci_bus_resume, diff --git a/drivers/usb/host/ohci-pnx8550.c b/drivers/usb/host/ohci-pnx8550.c index 28467e288a93..605d59cba28e 100644 --- a/drivers/usb/host/ohci-pnx8550.c +++ b/drivers/usb/host/ohci-pnx8550.c @@ -201,6 +201,7 @@ static const struct hc_driver ohci_pnx8550_hc_driver = { */ .hub_status_data = ohci_hub_status_data, .hub_control = ohci_hub_control, + .hub_irq_enable = ohci_rhsc_enable, #ifdef CONFIG_PM .bus_suspend = ohci_bus_suspend, .bus_resume = ohci_bus_resume, diff --git a/drivers/usb/host/ohci-ppc-of.c b/drivers/usb/host/ohci-ppc-of.c index 50e55db13636..a67252791223 100644 --- a/drivers/usb/host/ohci-ppc-of.c +++ b/drivers/usb/host/ohci-ppc-of.c @@ -72,6 +72,7 @@ static const struct hc_driver ohci_ppc_of_hc_driver = { */ .hub_status_data = ohci_hub_status_data, .hub_control = ohci_hub_control, + .hub_irq_enable = ohci_rhsc_enable, #ifdef CONFIG_PM .bus_suspend = ohci_bus_suspend, .bus_resume = ohci_bus_resume, diff --git a/drivers/usb/host/ohci-ppc-soc.c b/drivers/usb/host/ohci-ppc-soc.c index cd3398b675b2..523c30125577 100644 --- a/drivers/usb/host/ohci-ppc-soc.c +++ b/drivers/usb/host/ohci-ppc-soc.c @@ -172,6 +172,7 @@ static const struct hc_driver ohci_ppc_soc_hc_driver = { */ .hub_status_data = ohci_hub_status_data, .hub_control = ohci_hub_control, + .hub_irq_enable = ohci_rhsc_enable, #ifdef CONFIG_PM .bus_suspend = ohci_bus_suspend, .bus_resume = ohci_bus_resume, diff --git a/drivers/usb/host/ohci-ps3.c b/drivers/usb/host/ohci-ps3.c index bfdeb0d22d05..c1935ae537f8 100644 --- a/drivers/usb/host/ohci-ps3.c +++ b/drivers/usb/host/ohci-ps3.c @@ -68,6 +68,7 @@ static const struct hc_driver ps3_ohci_hc_driver = { .get_frame_number = ohci_get_frame, .hub_status_data = ohci_hub_status_data, .hub_control = ohci_hub_control, + .hub_irq_enable = ohci_rhsc_enable, .start_port_reset = ohci_start_port_reset, #if defined(CONFIG_PM) .bus_suspend = ohci_bus_suspend, diff --git a/drivers/usb/host/ohci-pxa27x.c b/drivers/usb/host/ohci-pxa27x.c index 70b0d4b459e7..d4ee27d92be8 100644 --- a/drivers/usb/host/ohci-pxa27x.c +++ b/drivers/usb/host/ohci-pxa27x.c @@ -298,6 +298,7 @@ static const struct hc_driver ohci_pxa27x_hc_driver = { */ .hub_status_data = ohci_hub_status_data, .hub_control = ohci_hub_control, + .hub_irq_enable = ohci_rhsc_enable, #ifdef CONFIG_PM .bus_suspend = ohci_bus_suspend, .bus_resume = ohci_bus_resume, diff --git a/drivers/usb/host/ohci-s3c2410.c b/drivers/usb/host/ohci-s3c2410.c index a73d2ff322e2..ead4772f0f27 100644 --- a/drivers/usb/host/ohci-s3c2410.c +++ b/drivers/usb/host/ohci-s3c2410.c @@ -466,6 +466,7 @@ static const struct hc_driver ohci_s3c2410_hc_driver = { */ .hub_status_data = ohci_s3c2410_hub_status_data, .hub_control = ohci_s3c2410_hub_control, + .hub_irq_enable = ohci_rhsc_enable, #ifdef CONFIG_PM .bus_suspend = ohci_bus_suspend, .bus_resume = ohci_bus_resume, diff --git a/drivers/usb/host/ohci-sa1111.c b/drivers/usb/host/ohci-sa1111.c index 99438c65981b..0f48f2d99226 100644 --- a/drivers/usb/host/ohci-sa1111.c +++ b/drivers/usb/host/ohci-sa1111.c @@ -231,6 +231,7 @@ static const struct hc_driver ohci_sa1111_hc_driver = { */ .hub_status_data = ohci_hub_status_data, .hub_control = ohci_hub_control, + .hub_irq_enable = ohci_rhsc_enable, #ifdef CONFIG_PM .bus_suspend = ohci_bus_suspend, .bus_resume = ohci_bus_resume, diff --git a/drivers/usb/host/ohci-sh.c b/drivers/usb/host/ohci-sh.c index 60f03cc7ec4f..e7ee607278fe 100644 --- a/drivers/usb/host/ohci-sh.c +++ b/drivers/usb/host/ohci-sh.c @@ -68,6 +68,7 @@ static const struct hc_driver ohci_sh_hc_driver = { */ .hub_status_data = ohci_hub_status_data, .hub_control = ohci_hub_control, + .hub_irq_enable = ohci_rhsc_enable, #ifdef CONFIG_PM .bus_suspend = ohci_bus_suspend, .bus_resume = ohci_bus_resume, diff --git a/drivers/usb/host/ohci-sm501.c b/drivers/usb/host/ohci-sm501.c index e899a77dfb83..e610698c6b60 100644 --- a/drivers/usb/host/ohci-sm501.c +++ b/drivers/usb/host/ohci-sm501.c @@ -75,6 +75,7 @@ static const struct hc_driver ohci_sm501_hc_driver = { */ .hub_status_data = ohci_hub_status_data, .hub_control = ohci_hub_control, + .hub_irq_enable = ohci_rhsc_enable, #ifdef CONFIG_PM .bus_suspend = ohci_bus_suspend, .bus_resume = ohci_bus_resume, diff --git a/drivers/usb/host/ohci-ssb.c b/drivers/usb/host/ohci-ssb.c index c4265caec780..7275186db315 100644 --- a/drivers/usb/host/ohci-ssb.c +++ b/drivers/usb/host/ohci-ssb.c @@ -81,6 +81,7 @@ static const struct hc_driver ssb_ohci_hc_driver = { .hub_status_data = ohci_hub_status_data, .hub_control = ohci_hub_control, + .hub_irq_enable = ohci_rhsc_enable, #ifdef CONFIG_PM .bus_suspend = ohci_bus_suspend, .bus_resume = ohci_bus_resume, diff --git a/drivers/usb/host/u132-hcd.c b/drivers/usb/host/u132-hcd.c index f29307405bb3..9b6323f768b2 100644 --- a/drivers/usb/host/u132-hcd.c +++ b/drivers/usb/host/u132-hcd.c @@ -2934,6 +2934,16 @@ static int u132_start_port_reset(struct usb_hcd *hcd, unsigned port_num) return 0; } +static void u132_hub_irq_enable(struct usb_hcd *hcd) +{ + struct u132 *u132 = hcd_to_u132(hcd); + if (u132->going > 1) { + dev_err(&u132->platform_dev->dev, "device has been removed %d\n" + , u132->going); + } else if (u132->going > 0) + dev_err(&u132->platform_dev->dev, "device is being removed\n"); +} + #ifdef CONFIG_PM static int u132_bus_suspend(struct usb_hcd *hcd) @@ -2985,6 +2995,7 @@ static struct hc_driver u132_hc_driver = { .bus_suspend = u132_bus_suspend, .bus_resume = u132_bus_resume, .start_port_reset = u132_start_port_reset, + .hub_irq_enable = u132_hub_irq_enable, }; /* diff --git a/drivers/video/fsl-diu-fb.c b/drivers/video/fsl-diu-fb.c index 712dabc6269f..09d7e22c6fef 100644 --- a/drivers/video/fsl-diu-fb.c +++ b/drivers/video/fsl-diu-fb.c @@ -1324,7 +1324,7 @@ static int fsl_diu_suspend(struct of_device *ofdev, pm_message_t state) { struct fsl_diu_data *machine_data; - machine_data = dev_get_drvdata(&dev->dev); + machine_data = dev_get_drvdata(&ofdev->dev); disable_lcdc(machine_data->fsl_diu_info[0]); return 0; @@ -1334,7 +1334,7 @@ static int fsl_diu_resume(struct of_device *ofdev) { struct fsl_diu_data *machine_data; - machine_data = dev_get_drvdata(&dev->dev); + machine_data = dev_get_drvdata(&ofdev->dev); enable_lcdc(machine_data->fsl_diu_info[0]); return 0; diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 58d43daec084..982a2064fe4c 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -204,7 +204,7 @@ int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page *page) * Note: assumes we have exclusive access to this mapping either * through inode->i_mutex or some other mechanism. */ - if (page->index == 0 && invalidate_inode_pages2_range(inode->i_mapping, PAGE_CACHE_SIZE, -1) < 0) { + if (invalidate_inode_pages2_range(inode->i_mapping, page->index + 1, -1) < 0) { /* Should never happen */ nfs_zap_mapping(inode, inode->i_mapping); } diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index efc015c6128a..44f87caf3683 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -606,7 +606,9 @@ static void dlm_init_lockres(struct dlm_ctxt *dlm, res->last_used = 0; + spin_lock(&dlm->spinlock); list_add_tail(&res->tracking, &dlm->tracking_list); + spin_unlock(&dlm->spinlock); memset(res->lvb, 0, DLM_LVB_LEN); memset(res->refmap, 0, sizeof(res->refmap)); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index ab8ccc9d14ff..c492449f3b45 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -476,10 +476,10 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, return -ESRCH; mm = get_task_mm(task); if (mm) { - static struct mm_walk clear_refs_walk; - memset(&clear_refs_walk, 0, sizeof(clear_refs_walk)); - clear_refs_walk.pmd_entry = clear_refs_pte_range; - clear_refs_walk.mm = mm; + struct mm_walk clear_refs_walk = { + .pmd_entry = clear_refs_pte_range, + .mm = mm, + }; down_read(&mm->mmap_sem); for (vma = mm->mmap; vma; vma = vma->vm_next) { clear_refs_walk.private = vma; @@ -602,11 +602,6 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, return err; } -static struct mm_walk pagemap_walk = { - .pmd_entry = pagemap_pte_range, - .pte_hole = pagemap_pte_hole -}; - /* * /proc/pid/pagemap - an array mapping virtual pages to pfns * @@ -641,6 +636,11 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, struct pagemapread pm; int pagecount; int ret = -ESRCH; + struct mm_walk pagemap_walk; + unsigned long src; + unsigned long svpfn; + unsigned long start_vaddr; + unsigned long end_vaddr; if (!task) goto out; @@ -659,11 +659,15 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, if (!mm) goto out_task; - ret = -ENOMEM; + uaddr = (unsigned long)buf & PAGE_MASK; uend = (unsigned long)(buf + count); pagecount = (PAGE_ALIGN(uend) - uaddr) / PAGE_SIZE; - pages = kmalloc(pagecount * sizeof(struct page *), GFP_KERNEL); + ret = 0; + if (pagecount == 0) + goto out_mm; + pages = kcalloc(pagecount, sizeof(struct page *), GFP_KERNEL); + ret = -ENOMEM; if (!pages) goto out_mm; @@ -684,33 +688,33 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, pm.out = (u64 *)buf; pm.end = (u64 *)(buf + count); - if (!ptrace_may_attach(task)) { - ret = -EIO; - } else { - unsigned long src = *ppos; - unsigned long svpfn = src / PM_ENTRY_BYTES; - unsigned long start_vaddr = svpfn << PAGE_SHIFT; - unsigned long end_vaddr = TASK_SIZE_OF(task); - - /* watch out for wraparound */ - if (svpfn > TASK_SIZE_OF(task) >> PAGE_SHIFT) - start_vaddr = end_vaddr; - - /* - * The odds are that this will stop walking way - * before end_vaddr, because the length of the - * user buffer is tracked in "pm", and the walk - * will stop when we hit the end of the buffer. - */ - ret = walk_page_range(start_vaddr, end_vaddr, - &pagemap_walk); - if (ret == PM_END_OF_BUFFER) - ret = 0; - /* don't need mmap_sem for these, but this looks cleaner */ - *ppos += (char *)pm.out - buf; - if (!ret) - ret = (char *)pm.out - buf; - } + pagemap_walk.pmd_entry = pagemap_pte_range; + pagemap_walk.pte_hole = pagemap_pte_hole; + pagemap_walk.mm = mm; + pagemap_walk.private = ± + + src = *ppos; + svpfn = src / PM_ENTRY_BYTES; + start_vaddr = svpfn << PAGE_SHIFT; + end_vaddr = TASK_SIZE_OF(task); + + /* watch out for wraparound */ + if (svpfn > TASK_SIZE_OF(task) >> PAGE_SHIFT) + start_vaddr = end_vaddr; + + /* + * The odds are that this will stop walking way + * before end_vaddr, because the length of the + * user buffer is tracked in "pm", and the walk + * will stop when we hit the end of the buffer. + */ + ret = walk_page_range(start_vaddr, end_vaddr, &pagemap_walk); + if (ret == PM_END_OF_BUFFER) + ret = 0; + /* don't need mmap_sem for these, but this looks cleaner */ + *ppos += (char *)pm.out - buf; + if (!ret) + ret = (char *)pm.out - buf; out_pages: for (; pagecount; pagecount--) { diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 57917932212e..192269698a8a 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -45,6 +45,8 @@ void reiserfs_delete_inode(struct inode *inode) goto out; reiserfs_update_inode_transaction(inode); + reiserfs_discard_prealloc(&th, inode); + err = reiserfs_delete_object(&th, inode); /* Do quota update inside a transaction for journaled quotas. We must do that diff --git a/include/asm-powerpc/hugetlb.h b/include/asm-powerpc/hugetlb.h index 649c6c3b87b3..be32ff02f4a0 100644 --- a/include/asm-powerpc/hugetlb.h +++ b/include/asm-powerpc/hugetlb.h @@ -49,12 +49,6 @@ static inline pte_t huge_pte_wrprotect(pte_t pte) return pte_wrprotect(pte); } -static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, - unsigned long addr, pte_t *ptep) -{ - ptep_set_wrprotect(mm, addr, ptep); -} - static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte, int dirty) diff --git a/include/asm-powerpc/pgtable-ppc64.h b/include/asm-powerpc/pgtable-ppc64.h index cc6a43ba41d0..7686569a0bef 100644 --- a/include/asm-powerpc/pgtable-ppc64.h +++ b/include/asm-powerpc/pgtable-ppc64.h @@ -314,6 +314,16 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, old = pte_update(mm, addr, ptep, _PAGE_RW, 0); } +static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + unsigned long old; + + if ((pte_val(*ptep) & _PAGE_RW) == 0) + return; + old = pte_update(mm, addr, ptep, _PAGE_RW, 1); +} + /* * We currently remove entries from the hashtable regardless of whether * the entry was young or dirty. The generic routines only flush if the diff --git a/include/asm-s390/pgtable.h b/include/asm-s390/pgtable.h index c7f4f8e3e297..bd0ea191dfa9 100644 --- a/include/asm-s390/pgtable.h +++ b/include/asm-s390/pgtable.h @@ -223,6 +223,9 @@ extern char empty_zero_page[PAGE_SIZE]; #define _PAGE_SPECIAL 0x004 /* SW associated with special page */ #define __HAVE_ARCH_PTE_SPECIAL +/* Set of bits not changed in pte_modify */ +#define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_SPECIAL) + /* Six different types of pages. */ #define _PAGE_TYPE_EMPTY 0x400 #define _PAGE_TYPE_NONE 0x401 @@ -681,7 +684,7 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *pt */ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { - pte_val(pte) &= PAGE_MASK; + pte_val(pte) &= _PAGE_CHG_MASK; pte_val(pte) |= pgprot_val(newprot); return pte; } diff --git a/include/asm-x86/kvm_para.h b/include/asm-x86/kvm_para.h index bfd9900742bf..76f392146daa 100644 --- a/include/asm-x86/kvm_para.h +++ b/include/asm-x86/kvm_para.h @@ -71,7 +71,8 @@ static inline long kvm_hypercall0(unsigned int nr) long ret; asm volatile(KVM_HYPERCALL : "=a"(ret) - : "a"(nr)); + : "a"(nr) + : "memory"); return ret; } @@ -80,7 +81,8 @@ static inline long kvm_hypercall1(unsigned int nr, unsigned long p1) long ret; asm volatile(KVM_HYPERCALL : "=a"(ret) - : "a"(nr), "b"(p1)); + : "a"(nr), "b"(p1) + : "memory"); return ret; } @@ -90,7 +92,8 @@ static inline long kvm_hypercall2(unsigned int nr, unsigned long p1, long ret; asm volatile(KVM_HYPERCALL : "=a"(ret) - : "a"(nr), "b"(p1), "c"(p2)); + : "a"(nr), "b"(p1), "c"(p2) + : "memory"); return ret; } @@ -100,7 +103,8 @@ static inline long kvm_hypercall3(unsigned int nr, unsigned long p1, long ret; asm volatile(KVM_HYPERCALL : "=a"(ret) - : "a"(nr), "b"(p1), "c"(p2), "d"(p3)); + : "a"(nr), "b"(p1), "c"(p2), "d"(p3) + : "memory"); return ret; } @@ -111,7 +115,8 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1, long ret; asm volatile(KVM_HYPERCALL : "=a"(ret) - : "a"(nr), "b"(p1), "c"(p2), "d"(p3), "S"(p4)); + : "a"(nr), "b"(p1), "c"(p2), "d"(p3), "S"(p4) + : "memory"); return ret; } diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h index f4a5871767f5..4aaa4afb1cb9 100644 --- a/include/linux/debug_locks.h +++ b/include/linux/debug_locks.h @@ -1,6 +1,8 @@ #ifndef __LINUX_DEBUG_LOCKING_H #define __LINUX_DEBUG_LOCKING_H +#include <linux/kernel.h> + struct task_struct; extern int debug_locks; @@ -11,14 +13,6 @@ extern int debug_locks_silent; */ extern int debug_locks_off(void); -/* - * In the debug case we carry the caller's instruction pointer into - * other functions, but we dont want the function argument overhead - * in the nondebug case - hence these macros: - */ -#define _RET_IP_ (unsigned long)__builtin_return_address(0) -#define _THIS_IP_ ({ __label__ __here; __here: (unsigned long)&&__here; }) - #define DEBUG_LOCKS_WARN_ON(c) \ ({ \ int __ret = 0; \ diff --git a/include/linux/ide.h b/include/linux/ide.h index 9918772bf274..eddb6daadf4a 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -189,6 +189,21 @@ static inline void ide_std_init_ports(hw_regs_t *hw, hw->io_ports.ctl_addr = ctl_addr; } +/* for IDE PCI controllers in legacy mode, temporary */ +static inline int __ide_default_irq(unsigned long base) +{ + switch (base) { +#ifdef CONFIG_IA64 + case 0x1f0: return isa_irq_to_vector(14); + case 0x170: return isa_irq_to_vector(15); +#else + case 0x1f0: return 14; + case 0x170: return 15; +#endif + } + return 0; +} + #include <asm/ide.h> #if !defined(MAX_HWIFS) || defined(CONFIG_EMBEDDED) diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 792bf0aa779b..2e70006c7fa8 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -46,6 +46,9 @@ extern const char linux_proc_banner[]; #define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) #define roundup(x, y) ((((x) + ((y) - 1)) / (y)) * (y)) +#define _RET_IP_ (unsigned long)__builtin_return_address(0) +#define _THIS_IP_ ({ __label__ __here; __here: (unsigned long)&&__here; }) + #ifdef CONFIG_LBD # include <asm/div64.h> # define sector_div(a, b) do_div(a, b) diff --git a/kernel/kprobes.c b/kernel/kprobes.c index d4998f81e229..1485ca8d0e00 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -79,7 +79,7 @@ static DEFINE_PER_CPU(struct kprobe *, kprobe_instance) = NULL; * * For such cases, we now have a blacklist */ -struct kprobe_blackpoint kprobe_blacklist[] = { +static struct kprobe_blackpoint kprobe_blacklist[] = { {"preempt_schedule",}, {NULL} /* Terminator */ }; diff --git a/kernel/printk.c b/kernel/printk.c index 8fb01c32aa3b..e2129e83fd75 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -666,7 +666,7 @@ static int acquire_console_semaphore_for_printk(unsigned int cpu) return retval; } -const char printk_recursion_bug_msg [] = +static const char printk_recursion_bug_msg [] = KERN_CRIT "BUG: recent printk recursion!\n"; static int printk_recursion_bug; diff --git a/kernel/rcupreempt.c b/kernel/rcupreempt.c index 5e02b7740702..41d275a81df5 100644 --- a/kernel/rcupreempt.c +++ b/kernel/rcupreempt.c @@ -925,26 +925,22 @@ void rcu_offline_cpu(int cpu) spin_unlock_irqrestore(&rdp->lock, flags); } -void __devinit rcu_online_cpu(int cpu) -{ - unsigned long flags; - - spin_lock_irqsave(&rcu_ctrlblk.fliplock, flags); - cpu_set(cpu, rcu_cpu_online_map); - spin_unlock_irqrestore(&rcu_ctrlblk.fliplock, flags); -} - #else /* #ifdef CONFIG_HOTPLUG_CPU */ void rcu_offline_cpu(int cpu) { } -void __devinit rcu_online_cpu(int cpu) +#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */ + +void __cpuinit rcu_online_cpu(int cpu) { -} + unsigned long flags; -#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */ + spin_lock_irqsave(&rcu_ctrlblk.fliplock, flags); + cpu_set(cpu, rcu_cpu_online_map); + spin_unlock_irqrestore(&rcu_ctrlblk.fliplock, flags); +} static void rcu_process_callbacks(struct softirq_action *unused) { diff --git a/kernel/softlockup.c b/kernel/softlockup.c index c828c2339cc9..a272d78185eb 100644 --- a/kernel/softlockup.c +++ b/kernel/softlockup.c @@ -120,6 +120,7 @@ void softlockup_tick(void) printk(KERN_ERR "BUG: soft lockup - CPU#%d stuck for %lus! [%s:%d]\n", this_cpu, now - touch_timestamp, current->comm, task_pid_nr(current)); + print_modules(); if (regs) show_regs(regs); else diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 6021757a4496..1dc2d1d18fa8 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -22,6 +22,8 @@ #include <linux/string.h> #include <linux/ctype.h> #include <linux/kernel.h> +#include <linux/kallsyms.h> +#include <linux/uaccess.h> #include <asm/page.h> /* for PAGE_SIZE */ #include <asm/div64.h> @@ -482,6 +484,89 @@ 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) +{ + int len, i; + + if ((unsigned long)s < PAGE_SIZE) + s = "<NULL>"; + + len = strnlen(s, precision); + + if (!(flags & LEFT)) { + while (len < field_width--) { + if (buf < end) + *buf = ' '; + ++buf; + } + } + for (i = 0; i < len; ++i) { + if (buf < end) + *buf = *s; + ++buf; ++s; + } + while (len < field_width--) { + if (buf < end) + *buf = ' '; + ++buf; + } + return buf; +} + +static inline void *dereference_function_descriptor(void *ptr) +{ +#if defined(CONFIG_IA64) || defined(CONFIG_PPC64) + void *p; + if (!probe_kernel_address(ptr, p)) + ptr = p; +#endif + return ptr; +} + +static char *symbol_string(char *buf, char *end, void *ptr, int field_width, int precision, int flags) +{ + 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); +#else + field_width = 2*sizeof(void *); + flags |= SPECIAL | SMALL | ZEROPAD; + return number(buf, end, value, 16, field_width, precision, flags); +#endif +} + +/* + * Show a '%p' thing. A kernel extension is that the '%p' is followed + * by an extra set of alphanumeric characters that are extended format + * specifiers. + * + * Right now we just handle 'F' (for symbolic Function descriptor pointers) + * and 'S' (for Symbolic direct pointers), but this can easily be + * extended in the future (network address types etc). + * + * The difference between 'S' and 'F' is that on ia64 and ppc64 function + * pointers are really function descriptors, which contain a pointer the + * real address. + */ +static char *pointer(const char *fmt, char *buf, char *end, void *ptr, int field_width, int precision, int flags) +{ + switch (*fmt) { + case 'F': + ptr = dereference_function_descriptor(ptr); + /* Fallthrough */ + case 'S': + return symbol_string(buf, end, ptr, field_width, precision, flags); + } + flags |= SMALL; + if (field_width == -1) { + field_width = 2*sizeof(void *); + flags |= ZEROPAD; + } + return number(buf, end, (unsigned long) ptr, 16, field_width, precision, flags); +} + /** * vsnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into @@ -502,11 +587,9 @@ static char *number(char *buf, char *end, unsigned long long num, int base, int */ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args) { - int len; unsigned long long num; - int i, base; + int base; char *str, *end, c; - const char *s; int flags; /* flags to number() */ @@ -622,43 +705,18 @@ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args) continue; case 's': - s = va_arg(args, char *); - if ((unsigned long)s < PAGE_SIZE) - s = "<NULL>"; - - len = strnlen(s, precision); - - if (!(flags & LEFT)) { - while (len < field_width--) { - if (str < end) - *str = ' '; - ++str; - } - } - for (i = 0; i < len; ++i) { - if (str < end) - *str = *s; - ++str; ++s; - } - while (len < field_width--) { - if (str < end) - *str = ' '; - ++str; - } + str = string(str, end, va_arg(args, char *), field_width, precision, flags); continue; case 'p': - flags |= SMALL; - if (field_width == -1) { - field_width = 2*sizeof(void *); - flags |= ZEROPAD; - } - str = number(str, end, - (unsigned long) va_arg(args, void *), - 16, field_width, precision, flags); + 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? */ diff --git a/mm/mempolicy.c b/mm/mempolicy.c index a37a5034f63d..c94e58b192c3 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -729,7 +729,11 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, } else { *policy = pol == &default_policy ? MPOL_DEFAULT : pol->mode; - *policy |= pol->flags; + /* + * Internal mempolicy flags must be masked off before exposing + * the policy to userspace. + */ + *policy |= (pol->flags & MPOL_MODE_FLAGS); } if (vma) { diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index c2397f503b0f..f38cc5317b88 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -442,12 +442,16 @@ int br_del_if(struct net_bridge *br, struct net_device *dev) void __exit br_cleanup_bridges(void) { - struct net_device *dev, *nxt; + struct net_device *dev; rtnl_lock(); - for_each_netdev_safe(&init_net, dev, nxt) - if (dev->priv_flags & IFF_EBRIDGE) +restart: + for_each_netdev(&init_net, dev) { + if (dev->priv_flags & IFF_EBRIDGE) { del_br(dev->priv); + goto restart; + } + } rtnl_unlock(); } diff --git a/net/can/af_can.c b/net/can/af_can.c index 7e8ca2836452..484bbf6dd032 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -205,12 +205,19 @@ static int can_create(struct net *net, struct socket *sock, int protocol) * -ENOBUFS on full driver queue (see net_xmit_errno()) * -ENOMEM when local loopback failed at calling skb_clone() * -EPERM when trying to send on a non-CAN interface + * -EINVAL when the skb->data does not contain a valid CAN frame */ int can_send(struct sk_buff *skb, int loop) { struct sk_buff *newskb = NULL; + struct can_frame *cf = (struct can_frame *)skb->data; int err; + if (skb->len != sizeof(struct can_frame) || cf->can_dlc > 8) { + kfree_skb(skb); + return -EINVAL; + } + if (skb->dev->type != ARPHRD_CAN) { kfree_skb(skb); return -EPERM; @@ -605,6 +612,7 @@ static int can_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct dev_rcv_lists *d; + struct can_frame *cf = (struct can_frame *)skb->data; int matches; if (dev->type != ARPHRD_CAN || dev_net(dev) != &init_net) { @@ -612,6 +620,8 @@ static int can_rcv(struct sk_buff *skb, struct net_device *dev, return 0; } + BUG_ON(skb->len != sizeof(struct can_frame) || cf->can_dlc > 8); + /* update statistics */ can_stats.rx_frames++; can_stats.rx_frames_delta++; diff --git a/net/can/bcm.c b/net/can/bcm.c index d9a3a9d13bed..72c2ce904f83 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -298,7 +298,7 @@ static void bcm_send_to_user(struct bcm_op *op, struct bcm_msg_head *head, if (head->nframes) { /* can_frames starting here */ - firstframe = (struct can_frame *) skb_tail_pointer(skb); + firstframe = (struct can_frame *)skb_tail_pointer(skb); memcpy(skb_put(skb, datalen), frames, datalen); @@ -826,6 +826,10 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, for (i = 0; i < msg_head->nframes; i++) { err = memcpy_fromiovec((u8 *)&op->frames[i], msg->msg_iov, CFSIZ); + + if (op->frames[i].can_dlc > 8) + err = -EINVAL; + if (err < 0) return err; @@ -858,6 +862,10 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, for (i = 0; i < msg_head->nframes; i++) { err = memcpy_fromiovec((u8 *)&op->frames[i], msg->msg_iov, CFSIZ); + + if (op->frames[i].can_dlc > 8) + err = -EINVAL; + if (err < 0) { if (op->frames != &op->sframe) kfree(op->frames); @@ -1164,9 +1172,12 @@ static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk) skb->dev = dev; skb->sk = sk; - can_send(skb, 1); /* send with loopback */ + err = can_send(skb, 1); /* send with loopback */ dev_put(dev); + if (err) + return err; + return CFSIZ + MHSIZ; } @@ -1185,6 +1196,10 @@ static int bcm_sendmsg(struct kiocb *iocb, struct socket *sock, if (!bo->bound) return -ENOTCONN; + /* check for valid message length from userspace */ + if (size < MHSIZ || (size - MHSIZ) % CFSIZ) + return -EINVAL; + /* check for alternative ifindex for this bcm_op */ if (!ifindex && msg->msg_name) { @@ -1259,8 +1274,8 @@ static int bcm_sendmsg(struct kiocb *iocb, struct socket *sock, break; case TX_SEND: - /* we need at least one can_frame */ - if (msg_head.nframes < 1) + /* we need exactly one can_frame behind the msg head */ + if ((msg_head.nframes != 1) || (size != CFSIZ + MHSIZ)) ret = -EINVAL; else ret = bcm_tx_send(msg, ifindex, sk); diff --git a/net/can/raw.c b/net/can/raw.c index 69877b8e7e9c..3e46ee36a1aa 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -632,6 +632,9 @@ static int raw_sendmsg(struct kiocb *iocb, struct socket *sock, } else ifindex = ro->ifindex; + if (size != sizeof(struct can_frame)) + return -EINVAL; + dev = dev_get_by_index(&init_net, ifindex); if (!dev) return -ENXIO; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 850825dc86e6..1d723de18686 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -255,6 +255,7 @@ #include <linux/init.h> #include <linux/fs.h> #include <linux/skbuff.h> +#include <linux/scatterlist.h> #include <linux/splice.h> #include <linux/net.h> #include <linux/socket.h> @@ -1208,7 +1209,8 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, return -ENOTCONN; while ((skb = tcp_recv_skb(sk, seq, &offset)) != NULL) { if (offset < skb->len) { - size_t used, len; + int used; + size_t len; len = skb->len - offset; /* Stop reading if we hit a patch of urgent data */ diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 0517967a68bf..e6fb21b19b86 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -243,10 +243,10 @@ int rpcb_getport_sync(struct sockaddr_in *sin, u32 prog, u32 vers, int prot) } EXPORT_SYMBOL_GPL(rpcb_getport_sync); -static struct rpc_task *rpcb_call_async(struct rpc_clnt *rpcb_clnt, struct rpcbind_args *map, int version) +static struct rpc_task *rpcb_call_async(struct rpc_clnt *rpcb_clnt, struct rpcbind_args *map, struct rpc_procinfo *proc) { struct rpc_message msg = { - .rpc_proc = rpcb_next_version[version].rpc_proc, + .rpc_proc = proc, .rpc_argp = map, .rpc_resp = &map->r_port, }; @@ -271,6 +271,7 @@ static struct rpc_task *rpcb_call_async(struct rpc_clnt *rpcb_clnt, struct rpcbi void rpcb_getport_async(struct rpc_task *task) { struct rpc_clnt *clnt = task->tk_client; + struct rpc_procinfo *proc; u32 bind_version; struct rpc_xprt *xprt = task->tk_xprt; struct rpc_clnt *rpcb_clnt; @@ -280,7 +281,6 @@ void rpcb_getport_async(struct rpc_task *task) struct sockaddr *sap = (struct sockaddr *)&addr; size_t salen; int status; - struct rpcb_info *info; dprintk("RPC: %5u %s(%s, %u, %u, %d)\n", task->tk_pid, __func__, @@ -313,10 +313,12 @@ void rpcb_getport_async(struct rpc_task *task) /* Don't ever use rpcbind v2 for AF_INET6 requests */ switch (sap->sa_family) { case AF_INET: - info = rpcb_next_version; + proc = rpcb_next_version[xprt->bind_index].rpc_proc; + bind_version = rpcb_next_version[xprt->bind_index].rpc_vers; break; case AF_INET6: - info = rpcb_next_version6; + proc = rpcb_next_version6[xprt->bind_index].rpc_proc; + bind_version = rpcb_next_version6[xprt->bind_index].rpc_vers; break; default: status = -EAFNOSUPPORT; @@ -324,14 +326,13 @@ void rpcb_getport_async(struct rpc_task *task) task->tk_pid, __func__); goto bailout_nofree; } - if (info[xprt->bind_index].rpc_proc == NULL) { + if (proc == NULL) { xprt->bind_index = 0; status = -EPFNOSUPPORT; dprintk("RPC: %5u %s: no more getport versions available\n", task->tk_pid, __func__); goto bailout_nofree; } - bind_version = info[xprt->bind_index].rpc_vers; dprintk("RPC: %5u %s: trying rpcbind version %u\n", task->tk_pid, __func__, bind_version); @@ -361,22 +362,20 @@ void rpcb_getport_async(struct rpc_task *task) map->r_addr = rpc_peeraddr2str(rpcb_clnt, RPC_DISPLAY_UNIVERSAL_ADDR); map->r_owner = RPCB_OWNER_STRING; /* ignored for GETADDR */ - child = rpcb_call_async(rpcb_clnt, map, xprt->bind_index); + child = rpcb_call_async(rpcb_clnt, map, proc); rpc_release_client(rpcb_clnt); if (IS_ERR(child)) { status = -EIO; + /* rpcb_map_release() has freed the arguments */ dprintk("RPC: %5u %s: rpc_run_task failed\n", task->tk_pid, __func__); - goto bailout; + goto bailout_nofree; } rpc_put_task(child); task->tk_xprt->stat.bind_count++; return; -bailout: - kfree(map); - xprt_put(xprt); bailout_nofree: rpcb_wake_rpcbind_waiters(xprt, status); bailout_nowake: diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c index 1dcf9f3d1107..44589088941f 100644 --- a/virt/kvm/ioapic.c +++ b/virt/kvm/ioapic.c @@ -278,7 +278,7 @@ static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int gsi) ent->fields.remote_irr = 0; if (!ent->fields.mask && (ioapic->irr & (1 << gsi))) - ioapic_deliver(ioapic, gsi); + ioapic_service(ioapic, gsi); } void kvm_ioapic_update_eoi(struct kvm *kvm, int vector) |
