summaryrefslogtreecommitdiff
path: root/arch/powerpc/perf
AgeCommit message (Collapse)AuthorFilesLines
2013-07-26powerpc/perf: Don't enable if we have zero eventsMichael Ellerman1-2/+5
commit 4ea355b5368bde0574c12430df53334c4be3bdcf upstream. In power_pmu_enable() we still enable the PMU even if we have zero events. This should have no effect but doesn't make much sense. Instead just return after telling the hypervisor that we are not using the PMCs. Signed-off-by: Michael Ellerman <michael@ellerman.id.au> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-07-26powerpc/perf: Use existing out label in power_pmu_enable()Michael Ellerman1-4/+5
commit 0a48843d6c5114cfa4a9540ee4d6af87628cec01 upstream. In power_pmu_enable() we can use the existing out label to reduce the number of return paths. Signed-off-by: Michael Ellerman <michael@ellerman.id.au> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-07-26powerpc/perf: Freeze PMC5/6 if we're not using themMichael Ellerman2-2/+7
commit 7a7a41f9d5b28ac3a916b057a7d3cd3f435ee9a6 upstream. On Power8 we can freeze PMC5 and 6 if we're not using them. Normally they run all the time. As noticed by Anshuman, we should unfreeze them when we disable the PMU as there are legacy tools which expect them to run all the time. Signed-off-by: Michael Ellerman <michael@ellerman.id.au> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-07-26powerpc/perf: Rework disable logic in pmu_disable()Michael Ellerman1-12/+19
commit 378a6ee99e4a431ec84e4e61893445c041c93007 upstream. In pmu_disable() we disable the PMU by setting the FC (Freeze Counters) bit in MMCR0. In order to do this we have to read/modify/write MMCR0. It's possible that we read a value from MMCR0 which has PMAO (PMU Alert Occurred) set. When we write that value back it will cause an interrupt to occur. We will then end up in the PMU interrupt handler even though we are supposed to have just disabled the PMU. We can avoid this by making sure we never write PMAO back. We should not lose interrupts because when the PMU is re-enabled the overflowed values will cause another interrupt. We also reorder the clearing of SAMPLE_ENABLE so that is done after the PMU is frozen. Otherwise there is a small window between the clearing of SAMPLE_ENABLE and the setting of FC where we could take an interrupt and incorrectly see SAMPLE_ENABLE not set. This would for example change the logic in perf_read_regs(). Signed-off-by: Michael Ellerman <michael@ellerman.id.au> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-07-26powerpc/perf: Check that events only include valid bits on Power8Michael Ellerman1-0/+13
commit d8bec4c9cd58f6d3679e09b7293851fb92ad7557 upstream. A mistake we have made in the past is that we pull out the fields we need from the event code, but don't check that there are no unknown bits set. This means that we can't ever assign meaning to those unknown bits in future. Although we have once again failed to do this at release, it is still early days for Power8 so I think we can still slip this in and get away with it. Signed-off-by: Michael Ellerman <michael@ellerman.id.au> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-06-10powerpc/perf: Fix deadlock caused by calling printk() in PMU exceptionMichael Ellerman1-1/+1
In commit bc09c21 "Fix finding overflowed PMC in interrupt" we added a printk() to the PMU exception handler. Unfortunately that is not safe. The problem is that the PMU exception may run even when interrupts are soft disabled, aka NMI context. We do this so that we can profile parts of the kernel that have interrupts soft-disabled. But by calling printk() from the exception handler, we can potentially deadlock in the printk code on logbuf_lock, eg: [c00000038ba575c0] c000000000081928 .vprintk_emit+0xa8/0x540 [c00000038ba576a0] c0000000007bcde8 .printk+0x48/0x58 [c00000038ba57710] c000000000076504 .perf_event_interrupt+0x2d4/0x490 [c00000038ba57810] c00000000001f6f8 .performance_monitor_exception+0x48/0x60 [c00000038ba57880] c0000000000032cc performance_monitor_common+0x14c/0x180 --- Exception: f01 (Performance Monitor) at c0000000007b25d4 ._raw_spin_lock_irq +0x64/0xc0 [c00000038ba57bf0] c00000000007ed90 .devkmsg_read+0xd0/0x5a0 [c00000038ba57d00] c0000000001c2934 .vfs_read+0xc4/0x1e0 [c00000038ba57d90] c0000000001c2cd8 .SyS_read+0x58/0xd0 [c00000038ba57e30] c000000000009d54 syscall_exit+0x0/0x98 --- Exception: c01 (System Call) at 00001fffffbf6f7c SP (3ffff6d4de10) is in userspace Fix it by making sure we only call printk() when we are not in NMI context. Signed-off-by: Michael Ellerman <michael@ellerman.id.au> Cc: <stable@vger.kernel.org> # 3.9 Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2013-06-01powerpc/perf: Add missing SIER supportMichael Ellerman1-12/+25
Commit 8f61aa3 "Add support for SIER" missed updates to siar_valid() and perf_get_data_addr(). In both cases we need to check the SIER instead of mmcra. Signed-off-by: Michael Ellerman <michael@ellerman.id.au> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2013-06-01powerpc/perf: Revert to original NO_SIPR logicMichael Ellerman1-24/+6
This is a revert and then some of commit 860aad7 "Add regs_no_sipr()". This workaround was only needed on early chip versions. As before NO_SIPR becomes a static flag of the PMU struct. Signed-off-by: Michael Ellerman <michael@ellerman.id.au> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2013-05-14powerpc/perf: Fix setting of "to" addresses for BHRBMichael Neuling1-1/+30
Currently we only set the "to" address in the branch stack when the CPU explicitly gives us a value. Unfortunately it only does this for XL form branches (eg blr, bctr, bctar) and not I and B form branches (eg b, bc). Fortunately if we read the instruction from memory we can extract the offset of a branch and calculate the target address. This adds a function power_pmu_bhrb_to() to calculate the target/to address of the corresponding I and B form branches. It handles branches in both user and kernel spaces. It also plumbs this into the perf brhb reading code. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2013-05-14powerpc/pmu: Fix order of interpreting BHRB target entriesMichael Neuling1-43/+46
The current Branch History Rolling Buffer (BHRB) code misinterprets the order of entries in the hardware buffer. It assumes that a branch target address will be read _after_ its corresponding branch. In reality the branch target comes before (lower mfbhrb entry) it's corresponding branch. This is a rewrite of the code to take this into account. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2013-05-14powerpc/perf: Move BHRB code into CONFIG_PPC64 regionMichael Neuling1-121/+127
The new Branch History Rolling buffer (BHRB) code is only useful on 64bit processors, so move it into the #ifdef CONFIG_PPC64 region. This avoids code bloat on 32bit systems. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2013-04-26powerpc/perf: Enable branch stack sampling frameworkAnshuman Khandual1-3/+164
Provides basic enablement for perf branch stack sampling framework on POWER8 processor based platforms. Adds new BHRB related elements into cpu_hw_event structure to represent current BHRB config, BHRB filter configuration, manage context and to hold output BHRB buffer during PMU interrupt before passing to the user space. This also enables processing of BHRB data and converts them into generic perf branch stack data format. Signed-off-by: Anshuman Khandual <khandual@linux.vnet.ibm.com> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2013-04-26powerpc/perf: Define BHRB generic functions, data and flags for POWER8Anshuman Khandual1-1/+56
This patch populates BHRB specific data for power_pmu structure. It also implements POWER8 specific BHRB filter and configuration functions. Signed-off-by: Anshuman Khandual <khandual@linux.vnet.ibm.com> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2013-04-26powerpc/perf: Add basic assembly code to read BHRB entries on POWER8Anshuman Khandual2-1/+45
This patch adds the basic assembly code to read BHRB buffer. BHRB entries are valid only after a PMU interrupt has happened (when MMCR0[PMAO]=1) and BHRB has been freezed. BHRB read should not be attempted when it is still enabled (MMCR0[PMAE]=1) and getting updated, as this can produce non-deterministic results. Signed-off-by: Anshuman Khandual <khandual@linux.vnet.ibm.com> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2013-04-26powerpc/perf: Power8 PMU supportMichael Ellerman2-1/+539
This patch adds support for the power8 PMU to perf. Work is ongoing to add generic cache events. Signed-off-by: Michael Ellerman <michael@ellerman.id.au> Acked-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2013-04-26powerpc/perf: Add support for SIERMichael Ellerman1-0/+19
On power8 we have a new SIER (Sampled Instruction Event Register), which captures information about instructions when we have random sampling enabled. Add support for loading the SIER into pt_regs, overloading regs->dar. Also set the new NO_SIPR flag in regs->result if we don't have SIPR. Update regs_sihv/sipr() to look for SIPR/SIHV in SIER. Signed-off-by: Michael Ellerman <michael@ellerman.id.au> Acked-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2013-04-26powerpc/perf: Add regs_no_sipr()Michael Ellerman1-3/+12
On power8 the presence or absence of SIPR depends on settings at runtime, so convert to using a dynamic flag for NO_SIPR. Existing backends that set NO_SIPR unconditionally set the dynamic flag obviously. Signed-off-by: Michael Ellerman <michael@ellerman.id.au> Acked-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2013-04-26powerpc/perf: Add an accessor for regs->resultMichael Ellerman1-2/+7
Add an accessor for regs->result so we can use it to store more flags in future. Signed-off-by: Michael Ellerman <michael@ellerman.id.au> Acked-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2013-04-26powerpc/perf: Convert mmcra_sipr/sihv() to regs_sipr/sihv()Michael Ellerman1-9/+11
On power8 the SIPR and SIHV are not in MMCRA, so convert the routines to take regs and change the names accordingly. Signed-off-by: Michael Ellerman <michael@ellerman.id.au> Acked-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2013-04-26powerpc/perf: Add an explict flag indicating presence of SLOT fieldMichael Ellerman3-2/+4
In perf_ip_adjust() we potentially use the MMCRA[SLOT] field to adjust the reported IP of a sampled instruction. Currently the logic is written so that if the backend does NOT have the PPMU_ALT_SIPR flag set then we assume MMCRA[SLOT] exists. However on power8 we do not want to set ALT_SIPR (it's in a third location), and we also do not have MMCRA[SLOT]. So add a new flag which only indicates whether MMCRA[SLOT] exists. Naively we'd set it on everything except power6/7, because they set ALT_SIPR, and we've reversed the polarity of the flag. But it's more complicated than that. mpc7450 is 32-bit, and uses its own version of perf_ip_adjust() which doesn't use MMCRA[SLOT], so it doesn't need the new flag set and the behaviour is unchanged. PPC970 (and I assume power4) don't have MMCRA[SLOT], so shouldn't have the new flag set. This is a behaviour change on those cpus, though we were probably getting lucky and the bits in question were 0. power5 and power5+ set the new flag, behaviour unchanged. power6 & power7 do not set the new flag, behaviour unchanged. Signed-off-by: Michael Ellerman <michael@ellerman.id.au> Acked-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2013-03-18Merge tag 'perf-urgent-for-mingo' of ↵Ingo Molnar1-0/+13
git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent Pull perf/urgent fixes from Arnaldo Carvalho de Melo: . perf probe: Fix segfault due to testing the wrong pointer for NULL, from Ananth N Mavinakayanahalli. . libtraceevent: Remove hard coded include to /usr/local/include in Makefile, which causes cross builds to include host header files, fix from Jack Mitchell. . perf record: Use the right target interface for synthesizing threads when --cpu/-C option is used, fix from Jiri Olsa. . Check if -DFORTIFY_SOURCE=2 is allowed, as gcc 4.7.2 defines it and then the build is broken when it is redefined in perf, fix from Marcin Slusarz. . Fix build with NO_NEWT=1, that can happen explicitely or when the newt-devel package is not installed, from Michael Ellerman. . perf/POWER7: Create a sysfs format entry for Power7 events, missing patch from a patchseries already merged, from Sukadev Bhattiprolu. . Fix LIBNUMA build with glibc 2.12 and older, from Vinson Lee. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-03-14perf/POWER7: Create a sysfs format entry for Power7 eventsSukadev Bhattiprolu1-0/+13
Create a sysfs entry, '/sys/bus/event_source/devices/cpu/format/event' which describes the format of the POWER7 PMU events. This code is based on corresponding code in x86. Changelog[v4]: [Michael Ellerman, Paul Mckerras] The event format is different for other POWER cpus. So move the code to POWER7-specific, power7-pmu.c Also, the POWER7 format uses bits 0-19 not 0-20. Changelog[v2]: [Jiri Osla] Use PMU_FORMAT_ATTR rather than duplicating code. Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Acked-by: Paul Mackerras <paulus@samba.org> Tested-by: Michael Ellerman <michael@ellerman.id.au> Cc: Andi Kleen <ak@linux.intel.com> Cc: Anton Blanchard <anton@au1.ibm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Michael Ellerman <michael@ellerman.id.au> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Robert Richter <robert.richter@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: benh@kernel.crashing.org Cc: linuxppc-dev@ozlabs.org Link: http://lkml.kernel.org/r/20130306054826.GA14627@us.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-02-24Merge branch 'next' of ↵Linus Torvalds2-29/+66
git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc Pull powerpc updates from Benjamin Herrenschmidt: "So from the depth of frozen Minnesota, here's the powerpc pull request for 3.9. It has a few interesting highlights, in addition to the usual bunch of bug fixes, minor updates, embedded device tree updates and new boards: - Hand tuned asm implementation of SHA1 (by Paulus & Michael Ellerman) - Support for Doorbell interrupts on Power8 (kind of fast thread-thread IPIs) by Ian Munsie - Long overdue cleanup of the way we handle relocation of our open firmware trampoline (prom_init.c) on 64-bit by Anton Blanchard - Support for saving/restoring & context switching the PPR (Processor Priority Register) on server processors that support it. This allows the kernel to preserve thread priorities established by userspace. By Haren Myneni. - DAWR (new watchpoint facility) support on Power8 by Michael Neuling - Ability to change the DSCR (Data Stream Control Register) which controls cache prefetching on a running process via ptrace by Alexey Kardashevskiy - Support for context switching the TAR register on Power8 (new branch target register meant to be used by some new specific userspace perf event interrupt facility which is yet to be enabled) by Ian Munsie. - Improve preservation of the CFAR register (which captures the origin of a branch) on various exception conditions by Paulus. - Move the Bestcomm DMA driver from arch powerpc to drivers/dma where it belongs by Philippe De Muyter - Support for Transactional Memory on Power8 by Michael Neuling (based on original work by Matt Evans). For those curious about the feature, the patch contains a pretty good description." (See commit db8ff907027b: "powerpc: Documentation for transactional memory on powerpc" for the mentioned description added to the file Documentation/powerpc/transactional_memory.txt) * 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (140 commits) powerpc/kexec: Disable hard IRQ before kexec powerpc/85xx: l2sram - Add compatible string for BSC9131 platform powerpc/85xx: bsc9131 - Correct typo in SDHC device node powerpc/e500/qemu-e500: enable coreint powerpc/mpic: allow coreint to be determined by MPIC version powerpc/fsl_pci: Store the pci ctlr device ptr in the pci ctlr struct powerpc/85xx: Board support for ppa8548 powerpc/fsl: remove extraneous DIU platform functions arch/powerpc/platforms/85xx/p1022_ds.c: adjust duplicate test powerpc: Documentation for transactional memory on powerpc powerpc: Add transactional memory to pseries and ppc64 defconfigs powerpc: Add config option for transactional memory powerpc: Add transactional memory to POWER8 cpu features powerpc: Add new transactional memory state to the signal context powerpc: Hook in new transactional memory code powerpc: Routines for FP/VSX/VMX unavailable during a transaction powerpc: Add transactional memory unavaliable execption handler powerpc: Add reclaim and recheckpoint functions for context switching transactional memory processes powerpc: Add FP/VSX and VMX register load functions for transactional memory powerpc: Add helper functions for transactional memory context switching ...
2013-01-31perf/POWER7: Make some POWER7 events available in sysfsSukadev Bhattiprolu1-0/+18
Make some POWER7-specific perf events available in sysfs. $ /bin/ls -1 /sys/bus/event_source/devices/cpu/events/ branch-instructions branch-misses cache-misses cache-references cpu-cycles instructions PM_BRU_FIN PM_BRU_MPRED PM_CMPLU_STALL PM_CYC PM_GCT_NOSLOT_CYC PM_INST_CMPL PM_LD_MISS_L1 PM_LD_REF_L1 stalled-cycles-backend stalled-cycles-frontend where the 'PM_*' events are POWER specific and the others are the generic events. This will enable users to specify these events with their symbolic names rather than with their raw code. perf stat -e 'cpu/PM_CYC' ... Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Anton Blanchard <anton@au1.ibm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Robert Richter <robert.richter@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: linuxppc-dev@ozlabs.org Link: http://lkml.kernel.org/r/20130123062528.GE13720@us.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-01-31perf/POWER7: Make generic event translations available in sysfsSukadev Bhattiprolu2-0/+46
Make the generic perf events in POWER7 available via sysfs. $ ls /sys/bus/event_source/devices/cpu/events branch-instructions branch-misses cache-misses cache-references cpu-cycles instructions stalled-cycles-backend stalled-cycles-frontend $ cat /sys/bus/event_source/devices/cpu/events/cache-misses event=0x400f0 This patch is based on commits that implement this functionality on x86. Eg: commit a47473939db20e3961b200eb00acf5fcf084d755 Author: Jiri Olsa <jolsa@redhat.com> Date: Wed Oct 10 14:53:11 2012 +0200 perf/x86: Make hardware event translations available in sysfs Changelog:[v2] [Jiri Osla] Drop EVENT_ID() macro since it is only used once. Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Anton Blanchard <anton@au1.ibm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Robert Richter <robert.richter@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: linuxppc-dev@ozlabs.org Link: http://lkml.kernel.org/r/20130123062454.GD13720@us.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-01-31perf/Power7: Use macros to identify perf eventsSukadev Bhattiprolu1-8/+20
Define and use macros to identify perf events codes This would make it easier and more readable when these event codes need to be used in more than one place. Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Anton Blanchard <anton@au1.ibm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Robert Richter <robert.richter@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: linuxppc-dev@ozlabs.org Link: http://lkml.kernel.org/r/20130123062353.GB13720@us.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-01-29perf/Power: PERF_EVENT_IOC_ENABLE does not reenable eventsukadev@linux.vnet.ibm.com1-0/+8
perf/Power: PERF_EVENT_IOC_ENABLE does not reenable event If we disable a perf event because we exceeded the specified ->event_limit, power_pmu_stop() sets the PERF_HES_STOPPED flag on the event. If the application then re-enables the event using PERF_EVENT_IOC_ENABLE ioctl, we don't ever clear this STOPPED flag. Consequently, the user space is never notified of the event. Following message has more background and test case. http://lists.eecs.utk.edu/pipermail/ptools-perfapi/2012-October/002528.html Used the following test cases to verify that this patch works on latest PAPI. $ papi.git/src/ctests/nonthread PAPI_TOT_CYC@5000000 $ papi.git/src/ctests/overflow_single_event Changelog[v2]: - [Paul Mackerras] Also clear PERF_HES_UPTODATE flag since we are restarting the event; cleanup comments and patch description. Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2013-01-10powerpc/perf: Fix for PMCs not making progressMichael Neuling1-0/+2
On POWER7 when we have really small counts left before overflow, we can take a PMU IRQ, but the PMC gets wound back to just before the overflow. If the kernel is setting the PMC to a value just before the overflow, we can get interrupted again without the PMC making any progress (ie another buggy overflow). In this case, we can end up making no forward progress, with the PMC interrupt returning us to the same count over and over. The below detects when we are making no forward progress (ie. delta = 0) and then increases the amount left before the overflow. This stops us from locking up. Signed-off-by: Michael Neuling <mikey@neuling.org> Reviewed-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> cc: Paul Mackerras <paulus@samba.org> cc: Anton Blanchard <anton@samba.org> cc: Linux PPC dev <linuxppc-dev@ozlabs.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2013-01-10powerpc/perf: Fix finding overflowed PMC in interruptMichael Neuling1-29/+54
If a PMC is about to overflow on a counter that's on an active perf event (ie. less than 256 from the end) and a _different_ PMC overflows just at this time (a PMC that's not on an active perf event), we currently mark the event as found, but in reality it's not as it's likely the other PMC that caused the IRQ. Since we mark it as found the second catch all for overflows doesn't run, and we don't reset the overflowing PMC ever. Hence we keep hitting that same PMC IRQ over and over and don't reset the actual overflowing counter. This is a rewrite of the perf interrupt handler for book3s to get around this. We now check to see if any of the PMCs have actually overflowed (ie >= 0x80000000). If yes, record it for active counters and just reset it for inactive counters. If it's not overflowed, then we check to see if it's one of the buggy power7 counters and if it is, record it and continue. If none of the PMCs match this, then we make note that we couldn't find the PMC that caused the IRQ. Signed-off-by: Michael Neuling <mikey@neuling.org> Reviewed-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> cc: Paul Mackerras <paulus@samba.org> cc: Anton Blanchard <anton@samba.org> cc: Linux PPC dev <linuxppc-dev@ozlabs.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2013-01-10powerpc/perf: Add stalled-cycles eventsChris Freehill1-0/+2
Support for stalled-cycles-frontend and stalled-cycles-backend is added for e500-based processors. The following mappings are used: stalled-cycles-frontend or idle-cycles-frontend: Com:18 Cycles decode stalled stalled-cycles-backend or idle-cycles-backend Com:19 cycles issue stalled Signed-off-by: Chris Freehill <chrisf@freescale.com> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2012-11-15powerpc/perf: Add missing L2 constraint handling in Power7 PMUMichael Ellerman1-3/+14
If we have two cache events that require different settings of the L2SEL bits in MMCR1 then we can not schedule those events simultaneously. Add logic to the constraint handling to express that. Signed-off-by: Michael Ellerman <michael@ellerman.id.au> Acked-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2012-10-18Revert "powerpc/perf: Use pmc_overflow() to detect rolled back events"Benjamin Herrenschmidt1-1/+1
This reverts commit 813312110bede27bffd082c25cd31730bd567beb. This revert was requested by the author of the patch as it seems to cause system hangs with some low frequency events
2012-09-27powerpc/perf: Sample only if SIAR-Valid bit is set in P7+sukadev@linux.vnet.ibm.com2-6/+41
powerpc/perf: Sample only if SIAR-Valid bit is set in P7+ On POWER7+ two new bits (mmcra[35] and mmcra[36]) indicate whether the contents of SIAR and SDAR are valid. For marked instructions on P7+, we must save the contents of SIAR and SDAR registers only if these new bits are set. This code/check for the SIAR-Valid bit is specific to P7+, so rather than waste a CPU-feature bit use the PVR flag. Note that Carl Love proposed a similar change for oprofile: https://lkml.org/lkml/2012/6/22/309 Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2012-09-07Merge branch 'merge' into nextBenjamin Herrenschmidt1-1/+1
Brings in various bug fixes from 3.6-rcX
2012-09-05powerpc: Rename 64-bit PVR constants to PVR_fooMichael Ellerman1-1/+1
We have an old FIXME in reg.h which points out that we should standardise on PVR_foo for our PVR #defines. Currently we use PVR_ on 32-bit and PV_ on 64-bit. So do that rename and remove the FIXME. Seeing as we're touching all but one usage of __is_processor(), rename it to something less ugly and more indicative of what it does, which is simply to check the PVR version. Signed-off-by: Michael Ellerman <michael@ellerman.id.au> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2012-08-24powerpc/perf: Use pmc_overflow() to detect rolled back eventsSukadev Bhattiprolu1-1/+1
For certain speculative events on Power7, 'perf stat' reports far higher event count than 'perf record' for the same event. As described in following commit, a performance monitor exception is raised even when the the performance events are rolled back. commit 0837e3242c73566fc1c0196b4ec61779c25ffc93 Author: Anton Blanchard <anton@samba.org> Date: Wed Mar 9 14:38:42 2011 +1100 perf_event_interrupt() records an event only when an overflow occurs. But this check for overflow is a simple 'if (val < 0)'. Because the events are rolled back, this check for overflow fails and the event is not recorded. perf_event_interrupt() later uses pmc_overflow() to detect the overflow and resets the counters and the events are lost completely. To properly detect the overflow of rolled back events, use pmc_overflow() even when recording events. To reproduce: $ cat strcpy.c #include <stdio.h> #include <string.h> main() { char buf[256]; alarm(5); while(1) strcpy(buf, "string1"); } $ perf record -e r20014 ./strcpy $ perf report -n > report.1 $ perf stat -e r20014 > report.2 # Compare report.1 and report.2 Reported-by: Maynard Johnson <mpjohn@us.ibm.com> Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2012-07-10powerpc/perf: Use perf_instruction_pointer in callchainsAnton Blanchard1-3/+3
We use SIAR or regs->nip for the instruction pointer depending on the PMU configuration, but we always use regs->nip in the callchain. Use perf_instruction_pointer so the backtrace is consistent. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2012-07-10powerpc/perf: Always use pt_regs for userspace samplesAnton Blanchard1-1/+22
At the moment we always use the SIAR if the PMU supports continuous sampling. Unfortunately the SIAR and the PMU exception are not synchronised for non marked events so we can end up with callchains that dont make sense. The following patch checks the HV and PR bits for samples coming from userspace and always uses pt_regs for them. Userspace will never have interrupts off so there is no real advantage to using the SIAR for non marked events in userspace. I had experimented with a patch that did a similar thing for kernel samples but we lost a significant amount of information. I was unable to profile any of our early exception code for example. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2012-07-10powerpc/perf: Move code to select SIAR or pt_regs into perf_read_regsAnton Blanchard1-22/+25
The logic to choose whether to use the SIAR or get the information out of pt_regs is going to get more complicated, so do it once in perf_read_regs. We overload regs->result which is gross but we are already doing it with regs->dsisr. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2012-07-10powerpc/perf: Create mmcra_sihv/mmcra_sipv helpersAnton Blanchard1-9/+22
We want to access the MMCRA_SIHV and MMCRA_SIPR bits elsewhere so create mmcra_sihv and mmcra_sipr which hide the differences between the old and new layout of the bits. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2012-05-09perf: Pass last sampling period to perf_sample_data_init()Robert Richter2-4/+2
We always need to pass the last sample period to perf_sample_data_init(), otherwise the event distribution will be wrong. Thus, modifiyng the function interface with the required period as argument. So basically a pattern like this: perf_sample_data_init(&data, ~0ULL); data.period = event->hw.last_period; will now be like that: perf_sample_data_init(&data, ~0ULL, event->hw.last_period); Avoids unininitialized data.period and simplifies code. Signed-off-by: Robert Richter <robert.richter@amd.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1333390758-10893-3-git-send-email-robert.richter@amd.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-03-28powerpc/perf: Fix instruction address sampling on 970 and Power4Benjamin Herrenschmidt3-5/+43
970 and Power4 don't support "continuous sampling" which means that when we aren't in marked instruction sampling mode (marked events), SIAR isn't updated with the last instruction sampled before the perf interrupt. On those processors, we must thus use the exception SRR0 value as the sampled instruction pointer. Those processors also don't support the SIPR and SIHV bits in MMCRA which means we need some kind of heuristic to decide if SIAR values represent kernel or user addresses. Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2012-03-22Merge branch 'next' of ↵Linus Torvalds12-0/+6571
git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc Pull powerpc merge from Benjamin Herrenschmidt: "Here's the powerpc batch for this merge window. It is going to be a bit more nasty than usual as in touching things outside of arch/powerpc mostly due to the big iSeriesectomy :-) We finally got rid of the bugger (legacy iSeries support) which was a PITA to maintain and that nobody really used anymore. Here are some of the highlights: - Legacy iSeries is gone. Thanks Stephen ! There's still some bits and pieces remaining if you do a grep -ir series arch/powerpc but they are harmless and will be removed in the next few weeks hopefully. - The 'fadump' functionality (Firmware Assisted Dump) replaces the previous (equivalent) "pHyp assisted dump"... it's a rewrite of a mechanism to get the hypervisor to do crash dumps on pSeries, the new implementation hopefully being much more reliable. Thanks Mahesh Salgaonkar. - The "EEH" code (pSeries PCI error handling & recovery) got a big spring cleaning, motivated by the need to be able to implement a new backend for it on top of some new different type of firwmare. The work isn't complete yet, but a good chunk of the cleanups is there. Note that this adds a field to struct device_node which is not very nice and which Grant objects to. I will have a patch soon that moves that to a powerpc private data structure (hopefully before rc1) and we'll improve things further later on (hopefully getting rid of the need for that pointer completely). Thanks Gavin Shan. - I dug into our exception & interrupt handling code to improve the way we do lazy interrupt handling (and make it work properly with "edge" triggered interrupt sources), and while at it found & fixed a wagon of issues in those areas, including adding support for page fault retry & fatal signals on page faults. - Your usual random batch of small fixes & updates, including a bunch of new embedded boards, both Freescale and APM based ones, etc..." I fixed up some conflicts with the generalized irq-domain changes from Grant Likely, hopefully correctly. * 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (141 commits) powerpc/ps3: Do not adjust the wrapper load address powerpc: Remove the rest of the legacy iSeries include files powerpc: Remove the remaining CONFIG_PPC_ISERIES pieces init: Remove CONFIG_PPC_ISERIES powerpc: Remove FW_FEATURE ISERIES from arch code tty/hvc_vio: FW_FEATURE_ISERIES is no longer selectable powerpc/spufs: Fix double unlocks powerpc/5200: convert mpc5200 to use of_platform_populate() powerpc/mpc5200: add options to mpc5200_defconfig powerpc/mpc52xx: add a4m072 board support powerpc/mpc5200: update mpc5200_defconfig to fit for charon board Documentation/powerpc/mpc52xx.txt: Checkpatch cleanup powerpc/44x: Add additional device support for APM821xx SoC and Bluestone board powerpc/44x: Add support PCI-E for APM821xx SoC and Bluestone board MAINTAINERS: Update PowerPC 4xx tree powerpc/44x: The bug fixed support for APM821xx SoC and Bluestone board powerpc: document the FSL MPIC message register binding powerpc: add support for MPIC message register API powerpc/fsl: Added aliased MSIIR register address to MSI node in dts powerpc/85xx: mpc8548cds - add 36-bit dts ...
2012-02-23powerpc/perf: Move perf core & PMU code into a subdirectoryMichael Ellerman12-0/+6561
The perf code has grown a lot since it started, and is big enough to warrant its own subdirectory. For reference it's ~60% bigger than the oprofile code. It declutters the kernel directory, makes it simpler to grep for "just perf stuff", and allows us to shorten some filenames. While we're at it, make it more obvious that we have two implementations of the core perf logic. One for (roughly) Book3S CPUs, which was the original implementation, and the other for Freescale embedded CPUs. Signed-off-by: Michael Ellerman <michael@ellerman.id.au> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>