- 04 Jul, 2019 1 commit
-
-
Ingo Molnar authored
perf/core has an earlier version of the x86/cpu tree merged, to avoid conflicts, and due to this we want to pick up this ABI impacting revert as well: 049331f2: ("x86/fsgsbase: Revert FSGSBASE support") Signed-off-by:
Ingo Molnar <mingo@kernel.org>
-
- 03 Jul, 2019 5 commits
-
-
Thomas Gleixner authored
The FSGSBASE series turned out to have serious bugs and there is still an open issue which is not fully understood yet. The confidence in those changes has become close to zero especially as the test cases which have been shipped with that series were obviously never run before sending the final series out to LKML. ./fsgsbase_64 >/dev/null Segmentation fault As the merge window is close, the only sane decision is to revert FSGSBASE support. The revert is necessary as this branch has been merged into perf/core already and rebasing all of that a few days before the merge window is not the most brilliant idea. I could definitely slap myself for not noticing the test case fail when merging that series, but TBH my expectations weren't that low back then. Won't happen again. Revert the following commits: 539bca53 ("x86/entry/64: Fix and clean up paranoid_exit") 2c7b5ac5 ("Documentation/x86/64: Add documentation for GS/FS addressing mode") f987c955 ("x86/elf: Enumerate kernel FSGSBASE capability in AT_HWCAP2") 2032f1f9 ("x86/cpu: Enable FSGSBASE on 64bit by default and add a chicken bit") 5bf0cab6 ("x86/entry/64: Document GSBASE handling in the paranoid path") 708078f6 ("x86/entry/64: Handle FSGSBASE enabled paranoid entry/exit") 79e1932f ("x86/entry/64: Introduce the FIND_PERCPU_BASE macro") 1d07316b ("x86/entry/64: Switch CR3 before SWAPGS in paranoid entry") f60a83df ("x86/process/64: Use FSGSBASE instructions on thread copy and ptrace") 1ab5f3f7 ("x86/process/64: Use FSBSBASE in switch_to() if available") a86b4625 ("x86/fsgsbase/64: Enable FSGSBASE instructions in helper functions") 8b71340d ("x86/fsgsbase/64: Add intrinsics for FSGSBASE instructions") b64ed19b ("x86/cpu: Add 'unsafe_fsgsbase' to enable CR4.FSGSBASE") Signed-off-by:
Thomas Gleixner <tglx@linutronix.de> Acked-by:
-
Andy Lutomirski authored
This refactors do_unexpected_base() to clean up some code. It also fixes the following bugs in test_ptrace_write_gsbase(): - Incorrect printf() format string caused crashes. - Hardcoded 0x7 for the gs selector was not reliably correct. It also documents the fact that the test is expected to fail on old kernels. Fixes: a87730cc ("selftests/x86/fsgsbase: Test ptracer-induced GSBASE write with FSGSBASE") Fixes: 1b6858d5 ("selftests/x86/fsgsbase: Test ptracer-induced GSBASE write") Signed-off-by:
Andy Lutomirski <luto@kernel.org> Signed-off-by:
-
Ingo Molnar authored
Merge tag 'perf-core-for-mingo-5.3-20190703' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo: perf metrics: Andi Kleen: - Fixes for SkylakeX and CascadeLakeX Intel vendor events. - Avoid extra ':' for --raw metrics. - Don't include duration_time in group. perf script: Arnaldo Carvalho de Melo/Jiri Olsa: - Fix processing guest samples. perf diff: Jin Yao: - Do diffs by basic blocks. objtool: Jiri Olsa: - Fix build by linking against tools/lib/ctype.o sources. perf pmu: John Garry: - Support more complex PMU event aliasing. - Add support for Hisi hip08 DDRC, HHA and L3C PMU aliasing. Signed-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by:
-
Ingo Molnar authored
Merge tag 'perf-core-for-mingo-5.3-20190701' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo: perf annotate: Mao Han: - Add support for the csky processor architecture. perf stat: Andi Kleen: - Fix metrics with --no-merge. - Don't merge events in the same PMU. - Fix group lookup for metric group. Intel PT: Adrian Hunter: - Improve CBR (Core to Bus Ratio) packets support. - Fix thread stack return from kernel for kernel only case. - Export power and ptwrite events to sqlite and postgresql. core libraries: Arnaldo Carvalho de Melo: - Find routines in tools/perf/util/ that have implementations in the kernel libraries (lib/*.c), such as strreplace(), strim(), skip_spaces() and reuse them after making a copy into tools/lib and tools/include/. This continues the effort of having tools/ code looking as much as possible like kernel source code, to help encourage people to work on both the kernel and in tools hosted in the kernel sources. That in turn will help moving stuff that uses those routines to tools/lib/perf/ where they will be made available for use in other tools. In the process ditch old cruft, remove unused variables and add missing include directives for headers providing things used in places that were building by sheer luck. Kyle Meyer: - Bump MAX_NR_CPUS and MAX_CACHES to get these tools to work on more machines. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
The 'perf kvm' command set up things so that we can record, report, top, etc, but not 'script', so make 'perf script' be able to process samples by allowing to pass guest kallsyms, vmlinux, modules, etc, and if at least one of those is provided, set perf_guest to true so that guest samples get properly resolved. Testing it: # perf kvm --guest --guestkallsyms /wb/rhel6.kallsyms --guestmodules /wb/rhel6.modules record -e cycles:Gk ^C[ perf record: Woken up 7 times to write data ] [ perf record: Captured and wrote 3.602 MB perf.data.guest (10492 samples) ] # # perf evlist -i perf.data.guest cycles:Gk # perf evlist -v -i perf.data.guest cycles:Gk: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CPU|PERIOD, read_format: ID, disabled: 1, inherit: 1, exclude_user: 1, exclude_hv: 1, mmap: 1, comm: 1, freq: 1, task: 1, sample_id_all: 1, exclude_host: 1, mmap2: 1, comm_exec: 1, ksymbol: 1, bpf_event: 1 # # perf kvm --guestkallsyms /wb/rhel6.kallsyms --guestmodules /wb/rhel6.modules report --stdio -s sym | head -30 # To display the perf.data header info, please use --header/--header-only options. # # # Total Lost Samples: 0 # # Samples: 10K of event 'cycles:Gk' # Event count (approx.): 2434201408 # # Overhead Symbol # ........ .............................................. # 11.93% [g] avtab_search_node 3.95% [g] sidtab_context_to_sid 2.41% [g] n_tty_write 2.20% [g] _spin_unlock_irqrestore 1.37% [g] _aesni_dec4 1.33% [g] kmem_cache_alloc 1.07% [g] native_write_cr0 0.99% [g] kfree 0.95% [g] _spin_lock 0.91% [g] __memset 0.87% [g] schedule 0.83% [g] _spin_lock_irqsave 0.76% [g] __kmalloc 0.67% [g] avc_has_perm_noaudit 0.66% [g] kmem_cache_free 0.65% [g] glue_xts_crypt_128bit 0.59% [g] __d_lookup 0.59% [g] __audit_syscall_exit 0.56% [g] __memcpy # Then, when trying to use perf script to generate a python script and then process the events after adding a python hook for non-tracepoint events: # perf script -i perf.data.guest -g python generated Python script: perf-script.py # vim perf-script.py # tail -2 perf-script.py def process_event(param_dict): print(param_dict["symbol"]) # # perf script -i perf.data.guest -s perf-script.py | head in trace_begin vmx_vmexit vmx_vmexit vmx_vmexit vmx_vmexit vmx_vmexit vmx_vmexit vmx_vmexit vmx_vmexit vmx_vmexit 231 # We'd see just the vmx_vmexit, i.e. the samples from the guest don't show up. After this patch: # perf script --guestkallsyms /wb/rhel6.kallsyms --guestmodules /wb/rhel6.modules -i perf.data.guest -s perf-script.py 2> /dev/null | head -30 in trace_begin apic_timer_interrupt apic_timer_interrupt apic_timer_interrupt apic_timer_interrupt apic_timer_interrupt save_args do_timer drain_array inode_permission avc_has_perm_noaudit run_timer_softirq apic_timer_interrupt apic_timer_interrupt apic_timer_interrupt apic_timer_interrupt apic_timer_interrupt kvm_guest_apic_eoi_write run_posix_cpu_timers _spin_lock handle_pte_fault rcu_irq_enter delay_tsc delay_tsc native_read_tsc apic_timer_interrupt sys_open internal_add_timer list_del rcu_exit_nohz # Jiri Olsa noticed we need to set 'perf_guest' to true if we want to process guest samples and I made it be set if one of the guest files settings get set via the command line options added in this patch, that match those present in the 'perf kvm' command. We probably want to have 'perf record', 'perf report' etc to notice that there are guest samples and do the right thing, which is to look for files with some suffix that make it be associated with the guest used to collect the samples, i.e. if a vmlinux file is passed, we can get the build-id from it, if not some other identifier or simply looking for "kallsyms.guest", for instance, in the current directory. Reported-by:Mariano Pache <npache@redhat.com> Tested-by:
-
- 02 Jul, 2019 29 commits
-
-
Andi Kleen authored
The Memory_BW metric generates groups including duration_time, which maps to a software event. For some reason this makes the group always not count. Always put duration_time outside a group when generating metrics. It's always the same time, so no need to group it. Signed-off-by:
Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20190628220737.13259-3-andi@firstfloor.orgSigned-off-by:
-
Andi Kleen authored
When printing the metrics raw, don't print : after the metricgroups. This helps the command line completion to complete those too. Signed-off-by:
-
Andi Kleen authored
- Add a missing filter for the DRAM_Latency / DRAM_Parallel_Reads metrics - Remove the useless PMM_* metrics from Skylake Signed-off-by:
-
Andi Kleen authored
- Fix a typo in the man page - Fix a tip that doesn't make any sense. Signed-off-by:
-
John Garry authored
Add support for Hisi hip08 L3C PMU aliasing. The kernel driver is in drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c Signed-off-by:
John Garry <john.garry@huawei.com> Acked-by:
Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Hendrik Brueckner <brueckner@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Poirier <mathieu.poirier@linaro.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Shaokun Zhang <zhangshaokun@hisilicon.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linuxarm@huawei.com Link: http://lkml.kernel.org/r/1561732552-143038-5-git-send-email-john.garry@huawei.comSigned-off-by:
-
John Garry authored
Add support for Hisi hip08 HHA PMU aliasing. The kernel driver is in drivers/perf/hisilicon/hisi_uncore_hha_pmu.c Signed-off-by:
-
John Garry authored
Add support for Hisi hip08 DDRC PMU aliasing. We can now do something like this: $perf list [snip] uncore ddrc: uncore_hisi_ddrc.act_cmd [DDRC active commands. Unit: hisi_sccl,ddrc] uncore_hisi_ddrc.flux_rcmd [DDRC read commands. Unit: hisi_sccl,ddrc] uncore_hisi_ddrc.flux_wcmd [DDRC write commands. Unit: hisi_sccl,ddrc] uncore_hisi_ddrc.flux_wr [DDRC precharge commands. Unit: hisi_sccl,ddrc] uncore_hisi_ddrc.rnk_chg [DDRC rank commands. Unit: hisi_sccl,ddrc] uncore_hisi_ddrc.rw_chg [DDRC read and write changes. Unit: hisi_sccl,ddrc] Performance counter stats for 'system wide': 0 uncore_hisi_ddrc.flux_rcmd [hisi_sccl1_ddrc0] 0 uncore_hisi_ddrc.flux_rcmd [hisi_sccl3_ddrc1] 0 uncore_hisi_ddrc.flux_rcmd [hisi_sccl5_ddrc2] 0 uncore_hisi_ddrc.flux_rcmd [hisi_sccl7_ddrc3] 0 uncore_hisi_ddrc.flux_rcmd [hisi_sccl5_ddrc0] 0 uncore_hisi_ddrc.flux_rcmd [hisi_sccl7_ddrc1] 0 uncore_hisi_ddrc.flux_rcmd [hisi_sccl1_ddrc3] 0 uncore_hisi_ddrc.flux_rcmd [hisi_sccl1_ddrc1] 0 uncore_hisi_ddrc.flux_rcmd [hisi_sccl3_ddrc2] 0 uncore_hisi_ddrc.flux_rcmd [hisi_sccl5_ddrc3] 0 uncore_hisi_ddrc.flux_rcmd [hisi_sccl3_ddrc0] 0 uncore_hisi_ddrc.flux_rcmd [hisi_sccl5_ddrc1] 0 uncore_hisi_ddrc.flux_rcmd [hisi_sccl7_ddrc2] 0 uncore_hisi_ddrc.flux_rcmd [hisi_sccl7_ddrc0] 20,421 uncore_hisi_ddrc.flux_rcmd [hisi_sccl1_ddrc2] 0 uncore_hisi_ddrc.flux_rcmd [hisi_sccl3_ddrc3] 1.001559011 seconds time elapsed The kernel driver is in drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c Signed-off-by: -
John Garry authored
The jevent "Unit" field is used for uncore PMU alias definition. The form uncore_pmu_example_X is supported, where "X" is a wildcard, to support multiple instances of the same PMU in a system. Unfortunately this format not suitable for all uncore PMUs; take the Hisi DDRC uncore PMU for example, where the name is in the form hisi_scclX_ddrcY. For for current jevent parsing, we would be required to hardcode an uncore alias translation for each possible value of X. This is not scalable. Instead, add support for "Unit" field in the form "hisi_sccl,ddrc", where we can match by hisi_scclX and ddrcY. Tokens in Unit field are delimited by ','. Signed-off-by:
-
Jin Yao authored
Documentation the new computation selection 'cycles'. v4: --- Change the column 'Block cycles diff [start:end]' to '[Program Block Range] Cycles Diff' Signed-off-by:
Jin Yao <yao.jin@linux.intel.com> Reviewed-by:
-
Jin Yao authored
$ perf record -b ./div $ perf record -b ./div Following is the default perf diff output $ perf diff # Event 'cycles' # # Baseline Delta Abs Shared Object Symbol # ........ ......... ................ .................................. # 48.75% +0.33% div [.] main 8.21% -0.20% div [.] compute_flag 19.02% -0.12% libc-2.23.so [.] __random_r 16.17% -0.09% libc-2.23.so [.] __random 2.27% -0.03% div [.] rand@plt +0.02% [i915] [k] gen8_irq_handler 5.52% +0.02% libc-2.23.so [.] rand This patch creates a new computation selection 'cycles'. $ perf diff -c cycles # Event 'cycles' # # Baseline [Program Block Range] Cycles Diff Shared Object Symbol # ........ ....................................... ......................................... # 48.75% [div.c:42 -> div.c:45] 147 div [.] main 48.75% [div.c:31 -> div.c:40] 4 div [.] main 48.75% [div.c:40 -> div.c:40] 0 div [.] main 48.75% [div.c:42 -> div.c:42] 0 div [.] main 48.75% [div.c:42 -> div.c:44] 0 div [.] main 19.02% [random_r.c:357 -> random_r.c:360] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:373] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:376] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:380] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:392] 0 libc-2.23.so [.] __random_r 16.17% [random.c:288 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:295] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:297] 0 libc-2.23.so [.] __random 16.17% [random.c:291 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:293 -> random.c:293] 0 libc-2.23.so [.] __random 8.21% [div.c:22 -> div.c:22] 148 div [.] compute_flag 8.21% [div.c:22 -> div.c:25] 0 div [.] compute_flag 8.21% [div.c:27 -> div.c:28] 0 div [.] compute_flag 5.52% [rand.c:26 -> rand.c:27] 0 libc-2.23.so [.] rand 5.52% [rand.c:26 -> rand.c:28] 0 libc-2.23.so [.] rand 2.27% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.01% [entry_64.S:694 -> entry_64.S:694] 16 [vmlinux] [k] native_irq_return_iret 0.00% [fair.c:7676 -> fair.c:7665] 162 [vmlinux] [k] update_blocked_averages "[Program Block Range]" indicates the range of program basic block (start -> end). If we can find the source line it prints the source line otherwise it prints the symbol+offset instead. v4: --- Use source lines or symbol+offset to indicate the basic block. It should be easier to understand. v3: --- Cast 'struct hist_entry' to 'struct block_hist' in hist_entry__block_fprintf. Use symbol_conf.report_block to check if executing hist_entry__block_fprintf. v2: --- Keep standard perf diff format and display the 'Baseline' and 'Shared Object'. The output is sorted by "Baseline" and the basic blocks in the same function are sorted by cycles diff. Signed-off-by: -
Jin Yao authored
The target is to compare the performance difference (cycles diff) for the same basic blocks in different data files. The same basic block means same function, same start address and same end address. This patch finds the same basic blocks from different data files and link them together and resort by the cycles diff. v3: --- The block stuffs are maintained by new structure 'block_hist', so this patch is update accordingly. v2: --- Since now the basic block hists is changed to per symbol, the patch only links the basic block hists for the same symbol in different data files. Signed-off-by:
-
Jin Yao authored
The hist__account_cycles() can account cycles per basic block. The basic block information is saved in cycles_hist structure. This patch processes each symbol, get basic blocks from cycles_hist and add the basic block entries to a new hists (in 'struct block_hist'). Using a hists is because we need to compare, sort and print the basic blocks later. v6: --- Since 'ops' argument is removed from hists__add_entry_block, update the code accordingly. No functional change. v5: --- Since now we still carry block_info in 'struct hist_entry' we don't need to use our own new/free ops for hist entries. And the block_info is released in hist_entry__delete. v3: --- 1. In v2, we put block stuffs in 'struct hist_entry', but it's not a good design. In v3, we create a new 'struct block_hist' and cast the 'struct hist_entry' to 'struct block_hist' in some places, which can avoid adding new stuffs in 'struct hist_entry'. 2. abs() -> labs(), in block_cycles_diff_cmp(). v2: --- v1 adds the basic block entries to per data-file hists but v2 adds the basic block entries to per symbol hists. That is to keep current perf-diff format. Will show the result in next patches. Signed-off-by:
-
Jin Yao authored
We will expand perf diff to support diff cycles of individual programs blocks, so it requires all data files having branch stacks. This patch checks HEADER_BRANCH_STACK in header, and only set the flag has_br_stack when HEADER_BRANCH_STACK are set in all data files. v2: --- Move check_file_brstack() from __cmd_diff() to cmd_diff(). Because later patch will check flag 'has_br_stack' before ui_init(). Signed-off-by:
-
Jin Yao authored
The block_info contains the program basic block information, i.e, contains the start address and the end address of this basic block and how much cycles it takes. We need to compare, sort and even print out the basic block by some orders, i.e. sort by cycles. For this purpose, we add block_info field to hist_entry. In order not to impact current interface, we creates a new function hists__add_entry_block. v6: --- Remove the 'ops' argument in hists__add_entry_block Signed-off-by:
-
Jin Yao authored
'perf diff' currently can only diff symbols(functions). We should expand it to diff cycles of individual programs blocks as reported by timed LBR. This would allow to identify changes in specific code accurately. We need a new structure to maintain the basic block information, such as, symbol(function), start/end address of this block, cycles. This patch creates this structure and with some ops. Signed-off-by:
-
Jiri Olsa authored
Fix objtool build, because it adds _ctype dependency via isspace call patch. Signed-off-by:
-
Andy Lutomirski authored
paranoid_exit needs to restore CR3 before GSBASE. Doing it in the opposite order crashes if the exception came from a context with user GSBASE and user CR3 -- RESTORE_CR3 cannot resture user CR3 if run with user GSBASE. This results in infinitely recursing exceptions if user code does SYSENTER with TF set if both FSGSBASE and PTI are enabled. The old code worked if user code just set TF without SYSENTER because #DB from user mode is special cased in idtentry and paranoid_exit doesn't run. Fix it by cleaning up the spaghetti code. All that paranoid_exit needs to do is to disable IRQs, handle IRQ tracing, then restore CR3, and restore GSBASE. Simply do those actions in that order. Fixes: 708078f6 ("x86/entry/64: Handle FSGSBASE enabled paranoid entry/exit") Reported-by:
Vegard Nossum <vegard.nossum@oracle.com> Signed-off-by:
Chang S. Bae <chang.seok.bae@intel.com> Signed-off-by:
-
Andy Lutomirski authored
It's only used if !CONFIG_IA32_EMULATION, so disable it in normal configs. This will save a few bytes of text and reduce confusion. Signed-off-by:
-
Andy Lutomirski authored
Make sure that both variants of the nasty TF-in-compat-syscall are exercised regardless of what vendor's CPU is running the tests. Also change the intentional signal after SYSCALL to use ud2, which is a lot more comprehensible. This crashes the kernel due to an FSGSBASE bug right now. This test *also* detects a bug in KVM when run on an Intel host. KVM people, feel free to use it to help debug. There's a bunch of code in this test to warn instead of going into an infinite looping when the bug gets triggered. Reported-by:
-
Luke Mujica authored
Change pmu-events.c to not use local include statements. The code that creates the include statements for pmu-events.c is in jevents.c. pmu-events.c is a generated file, and for build systems that put generated files in a separate directory, include statements with local pathing cannot find non-generated files. Signed-off-by:
Luke Mujica <lukemujica@google.com> Cc: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Numfor Mbiziwo-Tiapo <nums@google.com> Cc: Stephane Eranian <eranian@google.com> Link: https://lkml.kernel.org/n/tip-prgnwmaoo1pv9zz4vnv1bjaj@git.kernel.orgSigned-off-by:
-
Mao Han authored
This patch add basic arch initialization and instruction associate support for the csky CPU architecture. E.g.: $ perf annotate --stdio2 Samples: 161 of event 'cpu-clock:pppH', 4000 Hz, Event count (approx.): 40250000, [percent: local period] test_4() /usr/lib/perf-test/callchain_test Percent Disassembly of section .text: 00008420 <test_4>: test_4(): subi sp, sp, 4 st.w r8, (sp, 0x0) mov r8, sp subi sp, sp, 8 subi r3, r8, 4 movi r2, 0 st.w r2, (r3, 0x0) ↓ br 2e 100.00 14: subi r3, r8, 4 ld.w r2, (r3, 0x0) subi r3, r8, 8 st.w r2, (r3, 0x0) subi r3, r8, 4 ld.w r3, (r3, 0x0) addi r2, r3, 1 subi r3, r8, 4 st.w r2, (r3, 0x0) 2e: subi r3, r8, 4 ld.w r2, (r3, 0x0) lrw r3, 0x98967f // 8598 <main+0x28> cmplt r3, r2 ↑ bf 14 mov r0, r0 mov r0, r0 mov sp, r8 ld.w r8, (sp, 0x0) addi sp, sp, 4 ← rts Signed-off-by:Mao Han <han_mao@c-sky.com> Acked-by:
Guo Ren <guoren@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: linux-csky@vger.kernel.org Link: http://lkml.kernel.org/r/d874d7782d9acdad5d98f2f5c4a6fb26fbe41c5d.1561531557.git.han_mao@c-sky.comSigned-off-by:
-
Andi Kleen authored
Since Fixes: 8c5421c0 ("perf pmu: Display pmu name when printing unmerged events in stat") using --no-merge adds the PMU name to the evsel name. This breaks the metric value lookup because the parser doesn't know about this. Remove the extra postfixes for the metric evaluation. Signed-off-by:
-
Andi Kleen authored
The metric group code tries to find a group it added earlier in the evlist. Fix the lookup to handle groups with partially overlaps correctly. When a sub string match fails and we reset the match, we have to compare the first element again. I also renamed the find_evsel function to find_evsel_group to make its purpose clearer. With the earlier changes this fixes: Before: % perf stat -M UPI,IPC sleep 1 ... 1,032,922 uops_retired.retire_slots # 1.1 UPI 1,896,096 inst_retired.any 1,896,096 inst_retired.any 1,177,254 cpu_clk_unhalted.thread After: % perf stat -M UPI,IPC sleep 1 ... 1,013,193 uops_retired.retire_slots # 1.1 UPI 932,033 inst_retired.any 932,033 inst_retired.any # 0.9 IPC 1,091,245 cpu_clk_unhalted.thread Signed-off-by: -
Andi Kleen authored
Event merging is mainly to collapse similar events in lots of different duplicated PMUs. It can break metric displaying. It's possible for two metrics to have the same event, and when the two events happen in a row the second wouldn't be displayed. This would also not show the second metric. To avoid this don't merge events in the same PMU. This makes sense, if we have multiple events in the same PMU there is likely some reason for it (e.g. using multiple groups) and we better not merge them. While in theory it would be possible to construct metrics that have events with the same name in different PMU no current metrics have this problem. This is the fix for perf stat -M UPI,IPC (needs also another bug fix to completely work) Signed-off-by:
-
Andi Kleen authored
After setting up metric groups through the event parser, the metricgroup code looks them up again in the event list. Make sure we only look up events that haven't been used by some other metric. The data structures currently cannot handle more than one metric per event. This avoids problems with multiple events partially overlapping. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
This came from the kernel lib/argv_split.c, so move it to tools/lib/argv_split.c, to get it closer to the kernel structure. We need to audit the usage of argv_split() to figure out if it is really necessary to do have one allocation per argv[] entry, looking at one of its users I guess that is not the case and we probably are even leaking those allocations by not using argv_free() judiciously, for later. With this we further remove stuff from tools/perf/util/, reducing the perf specific codebase and encouraging other tools/ code to use these routines so as to keep the style and constructs used with the kernel. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-j479s1ive9h75w5lfg16jroz@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
No change in behaviour intended, just reducing the codebase and using something available in tools/lib/. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-oyi6zif3810nwi4uu85odnhv@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
We'll use it to further reduce the size of tools/perf/util/string.c, replacing the strxfrchar() equivalent function we have there. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-x3r61ikjrso1buygxwke8id3@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
Cleaning up a bit more tools/perf/util/ by using things we got from the kernel and have in tools/lib/ Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-7hluuoveryoicvkclshzjf1k@git.kernel.orgSigned-off-by:
-
- 28 Jun, 2019 2 commits
-
-
Ricardo Neri authored
Programming MTRR registers in multi-processor systems is a rather lengthy process. Furthermore, all processors must program these registers in lock step and with interrupts disabled; the process also involves flushing caches and TLBs twice. As a result, the process may take a considerable amount of time. On some platforms, this can lead to a large skew of the refined-jiffies clock source. Early when booting, if no other clock is available (e.g., booting with hpet=disabled), the refined-jiffies clock source is used to monitor the TSC clock source. If the skew of refined-jiffies is too large, Linux wrongly assumes that the TSC is unstable: clocksource: timekeeping watchdog on CPU1: Marking clocksource 'tsc-early' as unstable because the skew is too large: clocksource: 'refined-jiffies' wd_now: fffedc10 wd_last: fffedb90 mask: ffffffff clocksource: 'tsc-early' cs_now: 5eccfddebc cs_last: 5e7e3303d4 mask: ffffffffffffffff tsc: Marking TSC unstable due to clocksource watchdog As per measurements, around 98% of the time needed by the procedure to program MTRRs in multi-processor systems is spent flushing caches with wbinvd(). As per the Section 11.11.8 of the Intel 64 and IA 32 Architectures Software Developer's Manual, it is not necessary to flush caches if the CPU supports cache self-snooping. Thus, skipping the cache flushes can reduce by several tens of milliseconds the time needed to complete the programming of the MTRR registers: Platform Before After 104-core (208 Threads) Skylake 1437ms 28ms 2-core ( 4 Threads) Haswell 114ms 2ms Reported-by:Mohammad Etemadi <mohammad.etemadi@intel.com> Signed-off-by:
Ricardo Neri <ricardo.neri-calderon@linux.intel.com> Signed-off-by:
-
Ricardo Neri authored
Processors which have self-snooping capability can handle conflicting memory type across CPUs by snooping its own cache. However, there exists CPU models in which having conflicting memory types still leads to unpredictable behavior, machine check errors, or hangs. Clear this feature on affected CPUs to prevent its use. Suggested-by:
Alan Cox <alan.cox@intel.com> Signed-off-by:
-
- 26 Jun, 2019 3 commits
-
-
Arnaldo Carvalho de Melo authored
Moving more stuff out of tools/perf/util/ and using the kernel idiom. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-wpj8rktj62yse5dq6ckny6de@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
Since we're working on moving stuff out of tools/perf/util/ to tools/lib/, take the opportunity to adopt routines from the kernel that are equivalent, so that tools/ code look more like the kernel. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: André Goddard Rosa <andre.goddard@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-zqy1zdu2ok17qvi0ytk8z13c@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
No change in behaviour, just using the same kernel idiom for such operation. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: André Goddard Rosa <andre.goddard@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-a85lkptkt0ru40irpga8yf54@git.kernel.orgSigned-off-by:
-
