summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/ds.c (follow)
Commit message (Collapse)AuthorAgeFilesLines
* x86, perf, bts, mm: Delete the never used BTS-ptrace codePeter Zijlstra2010-03-261-1437/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | Support for the PMU's BTS features has been upstreamed in v2.6.32, but we still have the old and disabled ptrace-BTS, as Linus noticed it not so long ago. It's buggy: TIF_DEBUGCTLMSR is trampling all over that MSR without regard for other uses (perf) and doesn't provide the flexibility needed for perf either. Its users are ptrace-block-step and ptrace-bts, since ptrace-bts was never used and ptrace-block-step can be implemented using a much simpler approach. So axe all 3000 lines of it. That includes the *locked_memory*() APIs in mm/mlock.c as well. Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Roland McGrath <roland@redhat.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Markus Metzger <markus.t.metzger@intel.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Andrew Morton <akpm@linux-foundation.org> LKML-Reference: <20100325135413.938004390@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* percpu: make percpu symbols in x86 uniqueTejun Heo2009-10-291-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch updates percpu related symbols in x86 such that percpu symbols are unique and don't clash with local symbols. This serves two purposes of decreasing the possibility of global percpu symbol collision and allowing dropping per_cpu__ prefix from percpu symbols. * arch/x86/kernel/cpu/common.c: rename local variable to avoid collision * arch/x86/kvm/svm.c: s/svm_data/sd/ for local variables to avoid collision * arch/x86/kernel/cpu/cpu_debug.c: s/cpu_arr/cpud_arr/ s/priv_arr/cpud_priv_arr/ s/cpu_priv_count/cpud_priv_count/ * arch/x86/kernel/cpu/intel_cacheinfo.c: s/cpuid4_info/ici_cpuid4_info/ s/cache_kobject/ici_cache_kobject/ s/index_kobject/ici_index_kobject/ * arch/x86/kernel/ds.c: s/cpu_context/cpu_ds_context/ Partly based on Rusty Russell's "alloc_percpu: rename percpu vars which cause name clashes" patch. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: (kvm) Avi Kivity <avi@redhat.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: x86@kernel.org
* x86: ds.c fix invalid assignmentJaswinder Singh Rajput2009-06-201-3/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Fixes the type mixups that cause the following sparse warnings: CHECK arch/x86/kernel/ds.c arch/x86/kernel/ds.c:549:19: warning: incorrect type in argument 2 (invalid types) arch/x86/kernel/ds.c:549:19: expected bad type enum bts_field field arch/x86/kernel/ds.c:549:19: got int arch/x86/kernel/ds.c:514:35: error: incompatible types for operation (*) arch/x86/kernel/ds.c:514:35: left side has type unsigned char static [unsigned] [toplevel] sizeof_ptr_field arch/x86/kernel/ds.c:514:35: right side has type bad type enum bts_field field arch/x86/kernel/ds.c:514:7: error: invalid assignment arch/x86/kernel/ds.c:514:35: error: incompatible types for operation (*) arch/x86/kernel/ds.c:514:35: left side has type unsigned char static [unsigned] [toplevel] sizeof_ptr_field arch/x86/kernel/ds.c:514:35: right side has type bad type enum bts_field field arch/x86/kernel/ds.c:514:7: error: invalid assignment arch/x86/kernel/ds.c:514:35: error: incompatible types for operation (*) arch/x86/kernel/ds.c:514:35: left side has type unsigned char static [unsigned] [toplevel] sizeof_ptr_field arch/x86/kernel/ds.c:514:35: right side has type bad type enum bts_field field arch/x86/kernel/ds.c:514:7: error: invalid assignment arch/x86/kernel/ds.c:514:35: error: incompatible types for operation (*) arch/x86/kernel/ds.c:514:35: left side has type unsigned char static [unsigned] [toplevel] sizeof_ptr_field arch/x86/kernel/ds.c:514:35: right side has type bad type enum bts_field field arch/x86/kernel/ds.c:514:7: error: invalid assignment arch/x86/kernel/ds.c:514:35: error: incompatible types for operation (*) arch/x86/kernel/ds.c:514:35: left side has type unsigned char static [unsigned] [toplevel] sizeof_ptr_field arch/x86/kernel/ds.c:514:35: right side has type bad type enum bts_field field arch/x86/kernel/ds.c:514:7: error: invalid assignment arch/x86/kernel/ds.c:514:35: error: incompatible types for operation (*) arch/x86/kernel/ds.c:514:35: left side has type unsigned char static [unsigned] [toplevel] sizeof_ptr_field arch/x86/kernel/ds.c:514:35: right side has type bad type enum bts_field field arch/x86/kernel/ds.c:514:7: error: invalid assignment arch/x86/kernel/ds.c:520:35: error: incompatible types for operation (*) arch/x86/kernel/ds.c:520:35: left side has type unsigned char static [unsigned] [toplevel] sizeof_ptr_field arch/x86/kernel/ds.c:520:35: right side has type bad type enum bts_field field arch/x86/kernel/ds.c:520:7: error: invalid assignment arch/x86/kernel/ds.c:520:35: error: incompatible types for operation (*) Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com> Cc: Markus Metzger <markus.t.metzger@intel.com> LKML-Reference: <1245494740.8613.12.camel@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86, ds: support Core i7Markus Metzger2009-04-071-7/+62
| | | | | | | | | | | | | | | | Add debug store support for Core i7. Core i7 adds a reset value for each performance counter and a new PEBS record format. Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> Cc: roland@redhat.com Cc: eranian@googlemail.com Cc: oleg@redhat.com Cc: juan.villacis@intel.com Cc: ak@linux.jf.intel.com LKML-Reference: <20090403144607.088997000@intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86, ds: allow small debug store buffersMarkus Metzger2009-04-071-2/+7
| | | | | | | | | | | | | | | | | Check the buffer size more precisely to allow buffers for exactly one element provided the base address is already properly aligned. Add a debug store selftest. Reported-by: Stephane Eranian <eranian@googlemail.com> Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> Cc: roland@redhat.com Cc: eranian@googlemail.com Cc: oleg@redhat.com Cc: juan.villacis@intel.com Cc: ak@linux.jf.intel.com LKML-Reference: <20090403144606.139137000@intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86, ds: fix bad ds_reset_pebs()Markus Metzger2009-04-071-1/+1
| | | | | | | | | | | | | | | Ds_reset_pebs() passed the wrong qualifier to a shared function resulting in a reset of bts, rather than pebs. Reported-by: Stephane Eranian <eranian@googlemail.com> Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> Cc: roland@redhat.com Cc: eranian@googlemail.com Cc: oleg@redhat.com Cc: juan.villacis@intel.com Cc: ak@linux.jf.intel.com LKML-Reference: <20090403144605.206510000@intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86, ds: dont use TIF_DEBUGCTLMSRMarkus Metzger2009-04-071-5/+0
| | | | | | | | | | | | | | Debug store already uses TIF_DS_AREA_MSR to trigger debug store context switch handling. No need to use TIF_DEBUGCTLMSR, as well. Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> Cc: roland@redhat.com Cc: eranian@googlemail.com Cc: oleg@redhat.com Cc: juan.villacis@intel.com Cc: ak@linux.jf.intel.com LKML-Reference: <20090403144604.256645000@intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86, ds: use single debug store cpu configurationMarkus Metzger2009-04-071-2/+5
| | | | | | | | | | | | | | Use a single configuration for all cpus. Reported-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> Cc: roland@redhat.com Cc: eranian@googlemail.com Cc: oleg@redhat.com Cc: juan.villacis@intel.com Cc: ak@linux.jf.intel.com LKML-Reference: <20090403144602.191165000@intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86, ds: add leakage warningMarkus Metzger2009-04-071-10/+0
| | | | | | | | | | | | | | | | | | | | | Add a warning in case a debug store context is not removed before the task it is attached to is freed. Remove the old warning at thread exit. It is too early. Declare the debug store context field in thread_struct unconditionally. Remove ds_copy_thread() and ds_exit_thread() and do the work directly in process*.c. Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> Cc: roland@redhat.com Cc: eranian@googlemail.com Cc: oleg@redhat.com Cc: juan.villacis@intel.com Cc: ak@linux.jf.intel.com LKML-Reference: <20090403144601.254472000@intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86, bts, hw-branch-tracer: add _noirq variants to the debug store interfaceMarkus Metzger2009-04-071-107/+367
| | | | | | | | | | | | | | | | | | | | | | | | | | | | The hw-branch-tracer uses debug store functions from an on_each_cpu() context, which is simply wrong since the functions may sleep. Add _noirq variants for most functions, which may be called with interrupts disabled. Separate per-cpu and per-task tracing and allow per-cpu tracing to be controlled from any cpu. Make the hw-branch-tracer use the new debug store interface, synchronize with hotplug cpu event using get/put_online_cpus(), and remove the unnecessary spinlock. Make the ptrace bts and the ds selftest code use the new interface. Defer the ds selftest. Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> Cc: roland@redhat.com Cc: eranian@googlemail.com Cc: oleg@redhat.com Cc: juan.villacis@intel.com Cc: ak@linux.jf.intel.com LKML-Reference: <20090403144555.658136000@intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86, bts: use trace_clock_global() for timestampsMarkus Metzger2009-04-071-8/+9
| | | | | | | | | | | | | | | | Rename the bts_struct timestamp field to event. Use trace_clock_global() for time measurement. Reported-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> Cc: roland@redhat.com Cc: eranian@googlemail.com Cc: oleg@redhat.com Cc: juan.villacis@intel.com Cc: ak@linux.jf.intel.com LKML-Reference: <20090403144553.773216000@intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86, bts: fix race between per-task and per-cpu branch tracingMarkus Metzger2009-04-071-31/+41
| | | | | | | | | | | | | | | | | | | | | | | Per-task branch tracing installs a debug store context with the traced task. This immediately results in the branch trace control bits to be cleared for the next context switch of that task, if not set before. Either per-cpu or per-task tracing are allowed at the same time. An active per-cpu tracing would be disabled even if the per-task tracing request is rejected and the task debug store context removed. Check the tracing type (per-cpu or per-task) before installing a task debug store context. Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> Cc: roland@redhat.com Cc: eranian@googlemail.com Cc: oleg@redhat.com Cc: juan.villacis@intel.com Cc: ak@linux.jf.intel.com LKML-Reference: <20090403144552.856000000@intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86, bts: wait until traced task has been scheduled outMarkus Metzger2009-04-071-4/+19
| | | | | | | | | | | | | | | | | | | | | | | | In order to stop branch tracing for a running task, we need to first clear the branch tracing control bits before we may free the tracing buffer. If the traced task is running, the cpu might still trace that task after the branch trace control bits have cleared. Wait until the traced task has been scheduled out before proceeding. A similar problem affects the task debug store context. We first remove the context, then we need to wait until the task has been scheduled out before we can free the context memory. Reviewed-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> Cc: roland@redhat.com Cc: eranian@googlemail.com Cc: juan.villacis@intel.com Cc: ak@linux.jf.intel.com LKML-Reference: <20090403144551.919636000@intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86, bts: fix race when bts tracer is removedMarkus Metzger2009-04-071-21/+37
| | | | | | | | | | | | | | | | | | | | | | | | | | When the bts tracer is removed while the traced task is running, the write to clear the bts tracer pointer races with context switch code. Read the tracer once during a context switch. When a new tracer is installed, the bts tracer is set in the ds context before the tracer is initialized in order to claim the context for that tracer. This may result in write accesses using an uninitialized trace configuration when scheduling timestamps have been requested. Store active tracing flags separately and only set active flags after the tracing configuration has been initialized. Reviewed-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> Cc: roland@redhat.com Cc: eranian@googlemail.com Cc: juan.villacis@intel.com Cc: ak@linux.jf.intel.com LKML-Reference: <20090403144548.881338000@intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86, bts: use atomic memory allocationMarkus Metzger2009-03-191-4/+17
| | | | | | | | | | | | Ds_request_bts() needs to allocate memory. It uses GFP_KERNEL. Hw-branch-tracer calls ds_request_bts() within on_each_cpu(). Use atomic memory allocation to allow it to be used in that context. Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> LKML-Reference: <20090318192700.A6038@sedona.ch.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86, bts: detect size of DS fields, fixIngo Molnar2009-03-131-1/+1
| | | | | | | | | | | Impact: build fix One usage site was missed in the sizeof_field -> sizeof_ptr_field rename. Cc: Markus Metzger <markus.t.metzger@intel.com> LKML-Reference: <20090313104218.A30096@sedona.ch.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86, bts: cleanupsIngo Molnar2009-03-131-62/+80
| | | | | | | | Impact: cleanup, no code changed Cc: Markus Metzger <markus.t.metzger@intel.com> LKML-Reference: <20090313104218.A30096@sedona.ch.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86, bts: correct comment style in ds.cMarkus Metzger2009-03-131-40/+39
| | | | | | | | Correct the comment style in ds.c. Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> LKML-Reference: <20090313104642.A30149@sedona.ch.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86, bts: add selftest for BTSMarkus Metzger2009-03-131-0/+21
| | | | | | | | | | Perform a selftest of branch trace store when a cpu is initialized. WARN and disable branch trace store support if the selftest fails. Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> LKML-Reference: <20090313104507.A30125@sedona.ch.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86, bts: detect size of DS fieldsMarkus Metzger2009-03-131-40/+44
| | | | | | | | | | | | | | | | | | | | | Impact: more robust DS feature enumeration Detect the size of the pointer-type fields in the DS area configuration via the DTES64 features rather than based on the cpuid. Rename a variable to denote that size to reflect that it only covers the pointer-type fields. Add more boot-time diagnostics giving the detected size and the sizes of BTS and PEBS records. Use the size of the BTS/PEBS record to indicate that the respective feature is not available (if the record size is zero). Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> LKML-Reference: <20090313104218.A30096@sedona.ch.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86, pebs: correct qualifier passed to ds_write_config() from ds_request_pebs()Markus Metzger2009-03-061-1/+1
| | | | | | | | | | | ds_write_config() can write the BTS as well as the PEBS part of the DS config. ds_request_pebs() passes the wrong qualifier, which results in the wrong configuration to be written. Reported-by: Stephane Eranian <eranian@googlemail.com> Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> LKML-Reference: <20090305085721.A22550@sedona.ch.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86, bts: remove bad warningMarkus Metzger2009-03-061-1/+0
| | | | | | | | | | | | | | | | In case a ptraced task is reaped (while the tracer is still attached), ds_exit_thread() is called before ptrace_exit(). The latter will release the bts_tracer and remove the thread's ds_ctx. The former will WARN() if the context is not NULL. Oleg Nesterov submitted patches that move ptrace_exit() before exit_thread() and thus reverse the order of the above calls. Remove the bad warning. I will add it again when Oleg's changes are in. Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> LKML-Reference: <20090305084954.A22000@sedona.ch.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86, ds, bts: cleanup/fix DS configurationMarkus Metzger2009-01-221-14/+17
| | | | | | | | | | Cleanup the cpuid check for DS configuration. This also fixes a Corei7 CPUID enumeration bug. Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86, bts: add fork and exit handlingMarkus Metzger2008-12-201-0/+11
| | | | | | | | | | | | | | | | | | | | Impact: introduce new ptrace facility Add arch_ptrace_untrace() function that is called when the tracer detaches (either voluntarily or when the tracing task dies); ptrace_disable() is only called on a voluntary detach. Add ptrace_fork() and arch_ptrace_fork(). They are called when a traced task is forked. Clear DS and BTS related fields on fork. Release DS resources and reclaim memory in ptrace_untrace(). This releases resources already when the tracing task dies. We used to do that when the traced task dies. Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86, bts: correctly report invalid bts recordsMarkus Metzger2008-12-161-0/+3
| | | | | | | | | | Impact: change the reporting of empty BTS records Correctly report a cleared BTS record as invalid. Used to be reported as branch from 0 to 0. Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86, bts: remove recursion from get_contextMarkus Metzger2008-12-161-33/+25
| | | | | | | | | | Impact: cleanup Optimistically allocate a DS context. It is extremely unlikely that one already existed. This simplifies the code a lot. Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86, bts: fix build errorIngo Molnar2008-12-121-1/+1
| | | | | | | | | | | Impact: build fix arch/x86/kernel/ds.c: In function 'ds_request': arch/x86/kernel/ds.c:236: sorry, unimplemented: inlining failed in call to 'ds_get_context': recursive inlining but the recursion here is scary ... Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86, bts: provide in-kernel branch-trace interfaceMarkus Metzger2008-12-121-329/+528
| | | | | | | | | Impact: cleanup Move the BTS bits from ptrace.c into ds.c. Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86, bts: turn BUG_ON into WARN_ON_ONCEMarkus Metzger2008-12-121-2/+2
| | | | | | | | | Impact: make the ds code more debuggable Turn BUG_ON's into WARN_ON_ONCE. Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86, bts, ptrace: move BTS buffer allocation from ds.c into ptrace.cMarkus Metzger2008-11-251-78/+14
| | | | | | | | | | | | | | | Impact: restructure DS memory allocation to be done by the usage site of DS Require pre-allocated buffers in ds.h. Move the BTS buffer allocation for ptrace into ptrace.c. The pointer to the allocated buffer is stored in the traced task's task_struct together with the handle returned by ds_request_bts(). Removes memory accounting code. Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86, bts: base in-kernel ds interface on handlesMarkus Metzger2008-11-251-339/+340
| | | | | | | | | | | | | | | | | | | Impact: generalize the DS code to shared buffers Change the in-kernel ds.h interface to identify the tracer via a handle returned on ds_request_~(). Tracers used to be identified via their task_struct. The changes are required to allow DS to be shared between different tasks, which is needed for perfmon2 and for ftrace. For ptrace, the handle is stored in the traced task's task_struct. This should probably go into a (arch-specific) ptrace context some time. Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
*-. Merge branches 'tracing/core', 'x86/urgent' and 'x86/ptrace' into ↵Ingo Molnar2008-11-251-45/+52
|\ \ | | | | | | | | | | | | | | | | | | tracing/hw-branch-tracing This pulls together all the topic branches that are needed for the DS/BTS/PEBS tracing work.
| | * x86, bts: DS and BTS initializationMarkus Metzger2008-11-101-5/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Impact: widen BTS/PEBS ptrace enablement to more CPU models Move BTS initialisation out of an #ifdef CONFIG_X86_64 guard. Assume core2 BTS and DS layout for future models of family 6 processors. Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | x86, bts: fix wrmsr and spinlock over kmallocMarkus Metzger2008-11-251-37/+40
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Impact: fix sleeping-with-spinlock-held bugs/crashes - Turn a wrmsr to write the DS_AREA MSR into a wrmsrl. - Use irqsave variants of spinlocks. - Do not allocate memory while holding spinlocks. Reported-by: Stephane Eranian <eranian@googlemail.com> Reported-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | x86, pebs: fix PEBS record size configurationMarkus Metzger2008-11-251-0/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Impact: fix DS hw enablement on 64-bit x86 Fix the PEBS record size in the DS configuration. Reported-by: Stephane Eranian <eranian@googlemail.com> Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | x86, bts: exclude ds.c from build when disabledMarkus Metzger2008-11-251-3/+0
|/ / | | | | | | | | | | | | | | | | | | Impact: cleanup Move the CONFIG guard from the .c file into the makefile. Reported-by: Andi Kleen <andi-suse@firstfloor.org> Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* | x86, PEBS/DS: fix code flow in ds_request()Ingo Molnar2008-11-181-5/+21
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | this compiler warning: arch/x86/kernel/ds.c: In function 'ds_request': arch/x86/kernel/ds.c:368: warning: 'context' may be used uninitialized in this function Shows that the code flow in ds_request() is buggy - it goes into the unlock+release-context path even when the context is not allocated yet. First allocate the context, then do the other checks. Also, take care with GFP allocations under the ds_lock spinlock. Cc: <stable@kernel.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* | x86, bts: fix unlock problem in ds.cMarkus Metzger2008-11-161-1/+2
|/ | | | | | | | | | Fix a problem where ds_request() returned an error without releasing the ds lock. Reported-by: Stephane Eranian <eranian@gmail.com> Signed-off-by: Markus Metzger <markus.t.metzger@gmail.com> Cc: <stable@kernel.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86: ds.c ptrace.c integer as NULL pointer sparse fixesHarvey Harrison2008-09-241-2/+2
| | | | | | | | | | | | | | fix: arch/x86/kernel/ptrace.c:763:29: warning: Using plain integer as NULL pointer arch/x86/kernel/ptrace.c:777:46: warning: Using plain integer as NULL pointer arch/x86/kernel/ptrace.c:1115:45: warning: Using plain integer as NULL pointer arch/x86/kernel/ds.c:482:26: warning: Using plain integer as NULL pointer arch/x86/kernel/ds.c:487:25: warning: Using plain integer as NULL pointer Signed-off-by: Harvey Harrison <harvey.harrison@gmail.com> Acked-by: Cyrill Gorcunov <gorcunov@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86: fix ds.c build errorIngo Molnar2008-07-251-0/+1
| | | | | | | | fix: arch/x86/kernel/ds.c: In function ‘ds_allocate_buffer': arch/x86/kernel/ds.c:339: error: implicit declaration of function ‘PAGE_ALIGN' Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86: DS cleanup - dont treat 0 as NULLCyrill Gorcunov2008-05-121-9/+9
| | | | | | | Signed-off-by: Cyrill Gorcunov <gorcunov@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* x86, ptrace: PEBS supportMarkus Metzger2008-05-121-277/+676
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Polish the ds.h interface and add support for PEBS. Ds.c is meant to be the resource allocator for per-thread and per-cpu BTS and PEBS recording. It is used by ptrace/utrace to provide execution tracing of debugged tasks. It will be used by profilers (e.g. perfmon2). It may be used by kernel debuggers to provide a kernel execution trace. Changes in detail: - guard DS and ptrace by CONFIG macros - separate DS and BTS more clearly - simplify field accesses - add functions to manage PEBS buffers - add simple protection/allocation mechanism - added support for Atom Opens: - buffer overflow handling Currently, only circular buffers are supported. This is all we need for debugging. Profilers would want an overflow notification. This is planned to be added when perfmon2 is made to use the ds.h interface. - utrace intermediate layer Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* x86: debug Store - call kfree if only we really need itCyrill Gorcunov2008-04-171-4/+4
| | | | | | | | | | We should call for kfree if only we really need it. Though it's safe to call kfree with NULL pointer passed in this code we've already tested the pointer and can eliminate the call Signed-off-by: Cyrill Gorcunov <gorcunov@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86: fix small sparse warningHarvey Harrison2008-01-311-1/+1
| | | | | | | arch/x86/kernel/ds.c:226:9: warning: Using plain integer as NULL pointer Signed-off-by: Harvey Harrison <harvey.harrison@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86, ptrace: support 32bit-cross-64bit BTS recordingMarkus Metzger2008-01-301-46/+45
| | | | | | | | Support BTS recording of 32bit and 64bit tasks from 32bit or 64bit tasks. Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* x86, ptrace: new ptrace BTS APIMarkus Metzger2008-01-301-5/+51
| | | | | | | | | | | | | | | | Here's the new ptrace BTS API that supports two different overflow handling mechanisms (wrap-around and buffer-full-signal) to support two different use cases (debugging and profiling). It further combines buffer allocation and configuration. Opens: - memory rlimit - overflow signal What would be the right signal to use? Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* x86, ptrace: use jiffies for BTS timestampsMarkus Metzger2008-01-301-20/+10
| | | | | | | | Replace sched_clock() with jiffies for BTS timestamps. Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* x86, ptrace: support for branch trace store(BTS)Markus Metzger2008-01-301-0/+429
Resend using different mail client Changes to the last version: - split implementation into two layers: ds/bts and ptrace - renamed TIF's - save/restore ds save area msr in __switch_to_xtra() - make block-stepping only look at BTF bit Signed-off-by: Markus Metzger <markus.t.metzger@intel.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-27 09:45:32 +0100