summaryrefslogtreecommitdiffstats
path: root/arch/x86/oprofile/nmi_int.c
AgeCommit message (Collapse)AuthorFilesLines
2010-02-26oprofile/x86: use kzalloc() instead of kmalloc()Robert Richter1-3/+3
Cc: stable@kernel.org Signed-off-by: Robert Richter <robert.richter@amd.com>
2010-02-26oprofile/x86: fix perfctr nmi reservation for mulitplexingRobert Richter1-5/+6
Multiple virtual counters share one physical counter. The reservation of virtual counters fails due to duplicate allocation of the same counter. The counters are already reserved. Thus, virtual counter reservation may removed at all. This also makes the code easier. Cc: stable@kernel.org Signed-off-by: Robert Richter <robert.richter@amd.com>
2010-01-25oprofile/x86: add Xeon 7500 series supportAndi Kleen1-0/+1
Add Xeon 7500 series support to oprofile. Straight forward: it's the same as Core i7, so just detect the model number. No user space changes needed. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Robert Richter <robert.richter@amd.com>
2010-01-25oprofile/x86: fix crash when profiling more than 28 eventsSuravee Suthikulpanit1-1/+1
With multiplexing enabled oprofile crashs when profiling more than 28 events. This patch fixes this. Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com> Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-07-20x86/oprofile: Add counter reservation check for virtual countersRobert Richter1-3/+1
This patch adds a check for the availability of a counter. A virtual counter is used only if its physical counter is not reserved. Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-07-20x86/oprofile: Implement op_x86_virt_to_phys()Robert Richter1-0/+6
This patch implements a common x86 function to convert virtual counter numbers to physical. Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-07-20oprofile: Adding switch counter to oprofile statistic variablesRobert Richter1-7/+0
This patch moves the multiplexing switch counter from x86 code to common oprofile statistic variables. Now the value will be available and usable for all architectures. The initialization and incrementation also moved to common code. Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-07-20x86/oprofile: Implement mux_clone()Robert Richter1-14/+23
To setup a counter for all cpus, its structure is cloned from cpu 0. This patch implements mux_clone() to do this part for multiplexing data. Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-07-20x86/oprofile: Enable multiplexing only if the model supports itRobert Richter1-3/+9
This patch checks if the model supports multiplexing. Only then multiplexing will be enabled. The code is added to the common x86 initialization. Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-07-20x86/oprofile: Add function has_mux() to check multiplexing supportRobert Richter1-1/+18
The check is used to prevent running multiplexing code for models not supporting multiplexing. Before, the code was running but without effect. Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-07-20x86/oprofile: Modify initialization of num_virt_countersRobert Richter1-0/+3
Models that do not yet support counter multiplexing have to setup num_virt_counters. This patch implements the setup from num_counters if num_virt_counters is not set. Thus, num_virt_counters must be setup only for multiplexing support. Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-07-20x86/oprofile: Remove const qualifier from struct op_x86_model_specRobert Richter1-2/+2
This patch removes the const qualifier from struct op_x86_model_spec to make model parameters changable. Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-07-20x86/oprofile: Moving nmi_cpu_switch() in nmi_int.cRobert Richter1-74/+70
This patch moves some code in nmi_int.c to get a single separate multiplexing code section. Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-07-20x86/oprofile: Moving nmi_cpu_save/restore_mpx_registers() in nmi_int.cRobert Richter1-28/+24
This patch moves some code in nmi_int.c to get a single separate multiplexing code section. Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-07-20x86/oprofile: Moving nmi_setup_cpu_mux() in nmi_int.cRobert Richter1-26/+19
This patch moves some code in nmi_int.c to get a single separate multiplexing code section. Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-07-20x86/oprofile: Implement multiplexing setup/shutdown functionsRobert Richter1-36/+40
This patch implements nmi_setup_mux() and nmi_shutdown_mux() functions to setup/shutdown multiplexing. Multiplexing code in nmi_int.c is now much more separated. Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-07-20oprofile: Introduce op_x86_phys_to_virt()Robert Richter1-20/+23
This new function translates physical to virtual counter numbers. Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-07-20x86/oprofile: Fix initialization of switch_indexRobert Richter1-7/+9
Variable switch_index must be initialized for each cpu. This patch fixes the initialization by moving it to the per-cpu init function nmi_cpu_setup(). Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-07-20x86/oprofile: Use per_cpu() instead of __get_cpu_var()Robert Richter1-2/+2
__get_cpu_var() calls smp_processor_id(). When the cpu id is already known, instead use per_cpu() to avoid generating the id again. Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-07-20oprofile: Implement performance counter multiplexingJason Yeh1-5/+157
The number of hardware counters is limited. The multiplexing feature enables OProfile to gather more events than counters are provided by the hardware. This is realized by switching between events at an user specified time interval. A new file (/dev/oprofile/time_slice) is added for the user to specify the timer interval in ms. If the number of events to profile is higher than the number of hardware counters available, the patch will schedule a work queue that switches the event counter and re-writes the different sets of values into it. The switching mechanism needs to be implemented for each architecture to support multiplexing. This patch only implements AMD CPU support, but multiplexing can be easily extended for other models and architectures. There are follow-on patches that rework parts of this patch. Signed-off-by: Jason Yeh <jason.yeh@amd.com> Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-07-14x86/oprofile: Whitespaces changes onlyRobert Richter1-6/+6
This patch fixes whitespace changes of code that will be touched in follow-on patches. Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-07-14x86/oprofile: Rework and simplify nmi_cpu_setup()Robert Richter1-10/+3
This patch removes the function nmi_save_registers(). Per-cpu code is now executed only in the function nmi_cpu_setup(). Also, it renames the per-cpu function nmi_restore_registers() to nmi_cpu_restore_registers(). Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-07-14Merge commit 'v2.6.31-rc3'; commit 'tip/oprofile' into oprofile/coreRobert Richter1-1/+1
Conflicts: drivers/oprofile/oprofile_stats.c drivers/usb/otg/Kconfig drivers/usb/otg/Makefile Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-07-10x86/oprofile: rename kernel parameter for architectural perfmon to arch_perfmonRobert Richter1-1/+1
The short name of the achitecture is 'arch_perfmon'. This patch changes the kernel parameter to use this name. Cc: Andi Kleen <andi@firstfloor.org> Signed-off-by: Robert Richter <robert.richter@amd.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-12x86/oprofile: fix initialization of arch_perfmon for core_i7Robert Richter1-2/+3
Commit: e419294 x86/oprofile: moving arch_perfmon counter setup to op_x86_model_spec.init introduced a bug in the initialization of core_i7 leading to the incorrect model setup to &op_ppro_spec. This patch fixes this. Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-06-12Merge commit 'tip/perfcounters-for-linus' into oprofile/masterRobert Richter1-3/+4
Conflicts: arch/x86/oprofile/op_model_ppro.c Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-06-11x86/oprofile: remove some local variables in MSR save/restore functionsRobert Richter1-8/+4
The patch removes some local variables in these functions. Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-06-11x86/oprofile: use 64 bit values to save MSR statesRobert Richter1-20/+8
This patch removes struct op_saved_msr and replaces it by an u64 variable. This makes code easier and it is possible to use 64 bit MSR functions. Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-06-11x86/oprofile: replace macros to calculate control registerRobert Richter1-0/+20
This patch introduces op_x86_get_ctrl() to calculate the value of the performance control register. This is generic code usable for all models. The event and reserved masks are model specific and stored in struct op_x86_model_spec. 64 bit MSR functions are used now. The patch removes many hard to read macros used for ctrl calculation. The function op_x86_get_ctrl() is common code and the first step to further merge performance counter implementations for x86 models. Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-06-11x86/oprofile: pass the model to setup_ctrs() functionsRobert Richter1-1/+1
In follow-on patches the setup_ctrs() functions will need data that describes the model. This patch extends the function argument list to pass a pointer of the model to these function. Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-06-11x86/oprofile: simplify AMD cpu init codeRobert Richter1-8/+7
Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-06-11Merge branch 'linus' into perfcounters/coreIngo Molnar1-4/+23
Conflicts: arch/x86/kernel/irqinit.c arch/x86/kernel/irqinit_64.c arch/x86/kernel/traps.c arch/x86/mm/fault.c include/linux/sched.h kernel/exit.c
2009-06-10x86/oprofile: moving arch_perfmon counter setup to op_x86_model_spec.initRobert Richter1-12/+9
The function arch_perfmon_init() in nmi_int.c is model specific. This patch moves it to op_model_ppro.c by using the init function pointer in struct op_x86_model_spec. Cc: Andi Kleen <ak@linux.intel.com> Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-05-08oprofile: introduce module_param oprofile.cpu_typeRobert Richter1-2/+11
This patch removes module_param oprofile.force_arch_perfmon and introduces oprofile.cpu_type=archperfmon instead. This new parameter can be reused for other models and architectures. Currently only archperfmon is supported. Cc: Andi Kleen <ak@linux.intel.com> Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-05-08oprofile: add support for Core i7 and AtomAndi Kleen1-0/+7
The registers are about the same as other Family 6 CPUs so we only need to add detection. I'm not completely happy with calling Nehalem Core i7 because there will be undoubtedly other Nehalem based CPUs in the future with different marketing names, but it's the best we got for now. Requires updated oprofile userland for the new event files. If you don't want to update right now you can also use oprofile.force_arch_perfmon=1 (added in the next patch) with 0.9.4 Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-05-08oprofile: remove undocumented oprofile.p4force optionAndi Kleen1-4/+1
There are no new P4s and the oprofile code knows about all existing ones, so we don't really need the p4force option anymore. Remove it. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-05-08oprofile: re-add force_arch_perfmon optionAndi Kleen1-0/+6
This re-adds the force_arch_perfmon option that was in the original arch perfmon patchkit. Originally this was rejected in favour of a generalized perfmon=name option, but it turned out implementing the later in a reliable way is hard (and it would have been easy to crash the kernel if a user gets it wrong) But now Atom and Core i7 support being readded a user would need to update their oprofile userland to beyond 0.9.4 to use oprofile again on Atom or Core i7. To avoid this problem readd the force_arch_perfmon option. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Robert Richter <robert.richter@amd.com>
2009-02-04perfcounters: fix "perf counters kill oprofile" bugMike Galbraith1-3/+4
With oprofile as a module, and unloaded by profiling script, both oprofile and kerneltop work fine.. unless you leave kerneltop running when you start profiling, then you may see badness. Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-03x86/oprofile: fix Intel cpu family 6 detectionWilliam Cohen1-3/+2
Alan Jenkins wrote: > This is on an EeePC 701, /proc/cpuinfo as attached. > > Is this expected? Will the next release work? > > Thanks, Alan > > # opcontrol --setup --no-vmlinux > cpu_type 'unset' is not valid > you should upgrade oprofile or force the use of timer mode > > # opcontrol -v > opcontrol: oprofile 0.9.4 compiled on Nov 29 2008 22:44:10 > > # cat /dev/oprofile/cpu_type > i386/p6 > # uname -r > 2.6.28-rc6eeepc Hi Alan, Looking at the kernel driver code for oprofile it can return the "i386/p6" for the cpu_type. However, looking at the user-space oprofile code there isn't the matching entry in libop/op_cpu_type.c or the events/unit_mask files in events/i386 directory. The Intel AP-485 says this is a "Intel Pentium M processor model D". Seems like the oprofile kernel driver should be identifying the processor as "i386/p6_mobile" The driver identification code doesn't look quite right in nmi_init.c http://git.kernel.org/?p=linux/kernel/git/sfr/linux-next.git;a=blob;f=arch/x86/oprofile/nmi_int.c;h=022cd41ea9b4106e5884277096e80e9088a7c7a9;hb=HEAD has: 409 case 10 ... 13: 410 *cpu_type = "i386/p6"; 411 break; Referring to the Intel AP-485: case 10 and 11 should produce "i386/piii" case 13 should produce "i386/p6_mobile" I didn't see anything for case 12. Something like the attached patch. I don't have a celeron machine to verify that changes in this area of the kernel fix thing. -Will Signed-off-by: William Cohen <wcohen@redhat.com> Tested-by: Alan Jenkins <alan-jenkins@tuffmail.co.uk> Acked-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Robert Richter <robert.richter@amd.com>
2008-10-15Merge branch 'oprofile/x86-oprofile-for-tip' into oprofile/oprofile-for-tipRobert Richter1-9/+17
Conflicts: arch/x86/oprofile/op_model_ppro.c
2008-10-15x86/oprofile: reordering functions in nmi_int.cRobert Richter1-76/+71
No functional changes. The intension is to remove static function declarations. Signed-off-by: Robert Richter <robert.richter@amd.com>
2008-10-13oprofile: Implement Intel architectural perfmon supportAndi Kleen1-6/+17
Newer Intel CPUs (Core1+) have support for architectural events described in CPUID 0xA. See the IA32 SDM Vol3b.18 for details. The advantage of this is that it can be done without knowing about the specific CPU, because the CPU describes by itself what performance events are supported. This is only a fallback because only a limited set of 6 events are supported. This allows to do profiling on Nehalem and on Atom systems (later not tested) This patch implements support for that in oprofile's Intel Family 6 profiling module. It also has the advantage of supporting an arbitary number of events now as reported by the CPU. Also allow arbitary counter widths >32bit while we're at it. Requires a patched oprofile userland to support the new architecture. v2: update for latest oprofile tree remove force_arch_perfmon Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Robert Richter <robert.richter@amd.com>
2008-10-13oprofile: Don't report Nehalem as core_2Andi Kleen1-3/+0
This essentially reverts Linus' earlier 4b9f12a3779c548b68bc9af7d94030868ad3aa1b commit. Nehalem is not core_2, so it shouldn't be reported as such. However with the earlier arch perfmon patch it will fall back to arch perfmon mode now, so there is no need to fake it as core_2. The only drawback is that Linus will need to patch the arch perfmon support into his oprofile binary now, but I think he can do that. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Robert Richter <robert.richter@amd.com>
2008-09-30Merge branch 'oprofile-for-tip' of ↵Ingo Molnar1-91/+9
git://git.kernel.org/pub/scm/linux/kernel/git/rric/oprofile into oprofile Conflicts: arch/x86/oprofile/nmi_int.c Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-09-30Merge commit 'v2.6.27-rc8' into oprofileIngo Molnar1-6/+39
Conflicts: arch/x86/oprofile/nmi_int.c Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-09-24Merge commit 'v2.6.27-rc5' into tip/oprofileRobert Richter1-3/+36
Conflicts: arch/x86/oprofile/nmi_int.c
2008-09-24Revert "Oprofile Multiplexing Patch"Robert Richter1-92/+8
Reverting commit 1a960b402a51d80abf54e3f8e4972374ffe5f22d for the main branch. Multiplexing will be tracked on a separate feature branch. Conflicts: arch/x86/oprofile/nmi_int.c
2008-09-22x86, oprofile: BUG: using smp_processor_id() in preemptible codeAndrea Righi1-1/+1
Add __raw access before setting per cpu variable switch_index, to avoid the following BUG: [ 449.166827] BUG: using smp_processor_id() in preemptible [00000000] code: modprobe/6998 [ 449.166848] caller is op_nmi_init+0xf0/0x2b0 [oprofile] [ 449.166855] Pid: 6998, comm: modprobe Not tainted 2.6.27-rc5-mm1 #29 [ 449.166860] Call Trace: [ 449.166872] [<ffffffff80362d67>] debug_smp_processor_id+0xd7/0xe0 [ 449.166887] [<ffffffffa00181c0>] op_nmi_init+0xf0/0x2b0 [oprofile] [ 449.166902] [<ffffffffa0018000>] oprofile_init+0x0/0x60 [oprofile] [ 449.166915] [<ffffffffa00180a9>] oprofile_arch_init+0x9/0x30 [oprofile] [ 449.166928] [<ffffffffa001801e>] oprofile_init+0x1e/0x60 [oprofile] [ 449.166937] [<ffffffff8020903b>] _stext+0x3b/0x160 [ 449.166946] [<ffffffff80477985>] __mutex_unlock_slowpath+0xe5/0x190 [ 449.166955] [<ffffffff80262c1a>] trace_hardirqs_on_caller+0xca/0x140 [ 449.166965] [<ffffffff8026f7fc>] sys_init_module+0xdc/0x210 [ 449.166972] [<ffffffff8020b7cb>] system_call_fastpath+0x16/0x1b Signed-off-by: Andrea Righi <righi.andrea@gmail.com> Acked-by: Robert Richter <robert.richter@amd.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-09-22x86, oprofile: BUG scheduling while atomicAndrea Righi1-1/+3
nmi_shutdown() calls unregister_die_notifier() from an atomic context after setting preempt_disable() via get_cpu_var(): [ 1049.404154] BUG: scheduling while atomic: oprofiled/7796/0x00000002 [ 1049.404171] INFO: lockdep is turned off. [ 1049.404176] Modules linked in: oprofile af_packet rfcomm l2cap kvm_intel kvm i915 drm acpi_cpufreq cpufreq_userspace cpufreq_conservative cpufreq_ondemand cpufreq_powersave freq_table container sbs sbshc dm_mod arc4 ecb cryptomgr aead snd_hda_intel crypto_blkcipher snd_pcm_oss crypto_algapi snd_pcm iwlagn iwlcore snd_timer iTCO_wdt led_class btusb iTCO_vendor_support snd psmouse bluetooth mac80211 soundcore cfg80211 snd_page_alloc intel_agp video output button battery ac dcdbas evdev ext3 jbd mbcache sg sd_mod piix ata_piix libata scsi_mod dock tg3 libphy ehci_hcd uhci_hcd usbcore thermal processor fan fuse [ 1049.404362] Pid: 7796, comm: oprofiled Not tainted 2.6.27-rc5-mm1 #30 [ 1049.404368] Call Trace: [ 1049.404384] [<ffffffff804769fd>] thread_return+0x4a0/0x7d3 [ 1049.404396] [<ffffffff8026ad92>] generic_exec_single+0x52/0xe0 [ 1049.404405] [<ffffffff8026ae1a>] generic_exec_single+0xda/0xe0 [ 1049.404414] [<ffffffff8026aee3>] smp_call_function_single+0x73/0x150 [ 1049.404423] [<ffffffff804770c5>] schedule_timeout+0x95/0xd0 [ 1049.404430] [<ffffffff80476083>] wait_for_common+0x43/0x180 [ 1049.404438] [<ffffffff80476154>] wait_for_common+0x114/0x180 [ 1049.404448] [<ffffffff80236980>] default_wake_function+0x0/0x10 [ 1049.404457] [<ffffffff8024f810>] synchronize_rcu+0x30/0x40 [ 1049.404463] [<ffffffff8024f890>] wakeme_after_rcu+0x0/0x10 [ 1049.404472] [<ffffffff80479ca0>] _spin_unlock_irqrestore+0x40/0x80 [ 1049.404482] [<ffffffff80256def>] atomic_notifier_chain_unregister+0x3f/0x60 [ 1049.404501] [<ffffffffa03d8801>] nmi_shutdown+0x51/0x90 [oprofile] [ 1049.404517] [<ffffffffa03d6134>] oprofile_shutdown+0x34/0x70 [oprofile] [ 1049.404532] [<ffffffffa03d721e>] event_buffer_release+0xe/0x40 [oprofile] [ 1049.404543] [<ffffffff802bdcdd>] __fput+0xcd/0x240 [ 1049.404551] [<ffffffff802baa74>] filp_close+0x54/0x90 [ 1049.404560] [<ffffffff8023e1d1>] put_files_struct+0xb1/0xd0 [ 1049.404568] [<ffffffff8023f82f>] do_exit+0x18f/0x930 [ 1049.404576] [<ffffffff8020be03>] restore_args+0x0/0x30 [ 1049.404584] [<ffffffff80240006>] do_group_exit+0x36/0xa0 [ 1049.404592] [<ffffffff8020b7cb>] system_call_fastpath+0x16/0x1b This can be easily triggered with 'opcontrol --shutdown'. Simply move get_cpu_var() above unregister_die_notifier(). Signed-off-by: Andrea Righi <righi.andrea@gmail.com> Acked-by: Robert Richter <robert.richter@amd.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-20x86: fix oprofile + hibernation badnessAndi Kleen1-3/+36
Vegard Nossum reported oprofile + hibernation problems: > Now some warnings: > > ------------[ cut here ]------------ > WARNING: at /uio/arkimedes/s29/vegardno/git-working/linux-2.6/kernel/smp.c:328 s > mp_call_function_mask+0x194/0x1a0() The usual problem: the suspend function when interrupts are already disabled calls smp_call_function which is not allowed with interrupt off. But at this point all the other CPUs should be already down anyways, so it should be enough to just drop that. This patch should fix that problem at least by fixing cpu hotplug& suspend support. [ mingo@elte.hu: fixed 5 coding style errors. ] Signed-off-by: Andi Kleen <ak@linux.intel.com> Tested-by: Vegard Nossum <vegard.nossum@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-29 14:27:02 +0000