From 0b7c1528fb741803396da68a9d8d285ff7db731c Mon Sep 17 00:00:00 2001 From: William Cohen Date: Tue, 30 Jan 2018 22:28:13 -0500 Subject: [PATCH 01/27] perf vendor events aarch64: Add JSON metrics for ARM Cortex-A53 Processor Add JSON metrics for ARM Cortex-A53 Processor. Unlike the Intel processors there isn't a script that automatically generated these files. The patch was manually generated from the documentation and the previous oprofile ARM Cortex ac53 event file patch I made. The relevant documentation is in the "12.9 Events" section of the ARM Cortex A53 MPCore Processor Revision: r0p4 Technical Reference Manual. The ARM Cortex A53 manual is available at: http://infocenter.arm.com/help/topic/com.arm.doc.ddi0500g/DDI0500G_cortex_a53_trm.pdf Use that to look for additional information about the events. Signed-off-by: William Cohen Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20180131032813.9564-1-wcohen@redhat.com [ Added references provided by William Cohen ] Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/arm64/cortex-a53/branch.json | 27 ++++++++++ .../pmu-events/arch/arm64/cortex-a53/bus.json | 22 ++++++++ .../arch/arm64/cortex-a53/cache.json | 27 ++++++++++ .../arch/arm64/cortex-a53/memory.json | 22 ++++++++ .../arch/arm64/cortex-a53/other.json | 32 ++++++++++++ .../arch/arm64/cortex-a53/pipeline.json | 52 +++++++++++++++++++ tools/perf/pmu-events/arch/arm64/mapfile.csv | 1 + 7 files changed, 183 insertions(+) create mode 100644 tools/perf/pmu-events/arch/arm64/cortex-a53/branch.json create mode 100644 tools/perf/pmu-events/arch/arm64/cortex-a53/bus.json create mode 100644 tools/perf/pmu-events/arch/arm64/cortex-a53/cache.json create mode 100644 tools/perf/pmu-events/arch/arm64/cortex-a53/memory.json create mode 100644 tools/perf/pmu-events/arch/arm64/cortex-a53/other.json create mode 100644 tools/perf/pmu-events/arch/arm64/cortex-a53/pipeline.json diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/branch.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/branch.json new file mode 100644 index 000000000000..3b6208763e50 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/cortex-a53/branch.json @@ -0,0 +1,27 @@ +[ + {, + "EventCode": "0x7A", + "EventName": "BR_INDIRECT_SPEC", + "BriefDescription": "Branch speculatively executed - Indirect branch" + }, + {, + "EventCode": "0xC9", + "EventName": "BR_COND", + "BriefDescription": "Conditional branch executed" + }, + {, + "EventCode": "0xCA", + "EventName": "BR_INDIRECT_MISPRED", + "BriefDescription": "Indirect branch mispredicted" + }, + {, + "EventCode": "0xCB", + "EventName": "BR_INDIRECT_MISPRED_ADDR", + "BriefDescription": "Indirect branch mispredicted because of address miscompare" + }, + {, + "EventCode": "0xCC", + "EventName": "BR_COND_MISPRED", + "BriefDescription": "Conditional branch mispredicted" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/bus.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/bus.json new file mode 100644 index 000000000000..480d9f7460ab --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/cortex-a53/bus.json @@ -0,0 +1,22 @@ +[ + {, + "EventCode": "0x60", + "EventName": "BUS_ACCESS_LD", + "BriefDescription": "Bus access - Read" + }, + {, + "EventCode": "0x61", + "EventName": "BUS_ACCESS_ST", + "BriefDescription": "Bus access - Write" + }, + {, + "EventCode": "0xC0", + "EventName": "EXT_MEM_REQ", + "BriefDescription": "External memory request" + }, + {, + "EventCode": "0xC1", + "EventName": "EXT_MEM_REQ_NC", + "BriefDescription": "Non-cacheable external memory request" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/cache.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/cache.json new file mode 100644 index 000000000000..11baad6344b9 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/cortex-a53/cache.json @@ -0,0 +1,27 @@ +[ + {, + "EventCode": "0xC2", + "EventName": "PREFETCH_LINEFILL", + "BriefDescription": "Linefill because of prefetch" + }, + {, + "EventCode": "0xC3", + "EventName": "PREFETCH_LINEFILL_DROP", + "BriefDescription": "Instruction Cache Throttle occurred" + }, + {, + "EventCode": "0xC4", + "EventName": "READ_ALLOC_ENTER", + "BriefDescription": "Entering read allocate mode" + }, + {, + "EventCode": "0xC5", + "EventName": "READ_ALLOC", + "BriefDescription": "Read allocate mode" + }, + {, + "EventCode": "0xC8", + "EventName": "EXT_SNOOP", + "BriefDescription": "SCU Snooped data from another CPU for this CPU" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/memory.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/memory.json new file mode 100644 index 000000000000..480d9f7460ab --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/cortex-a53/memory.json @@ -0,0 +1,22 @@ +[ + {, + "EventCode": "0x60", + "EventName": "BUS_ACCESS_LD", + "BriefDescription": "Bus access - Read" + }, + {, + "EventCode": "0x61", + "EventName": "BUS_ACCESS_ST", + "BriefDescription": "Bus access - Write" + }, + {, + "EventCode": "0xC0", + "EventName": "EXT_MEM_REQ", + "BriefDescription": "External memory request" + }, + {, + "EventCode": "0xC1", + "EventName": "EXT_MEM_REQ_NC", + "BriefDescription": "Non-cacheable external memory request" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/other.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/other.json new file mode 100644 index 000000000000..73a22402d003 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/cortex-a53/other.json @@ -0,0 +1,32 @@ +[ + {, + "EventCode": "0x86", + "EventName": "EXC_IRQ", + "BriefDescription": "Exception taken, IRQ" + }, + {, + "EventCode": "0x87", + "EventName": "EXC_FIQ", + "BriefDescription": "Exception taken, FIQ" + }, + {, + "EventCode": "0xC6", + "EventName": "PRE_DECODE_ERR", + "BriefDescription": "Pre-decode error" + }, + {, + "EventCode": "0xD0", + "EventName": "L1I_CACHE_ERR", + "BriefDescription": "L1 Instruction Cache (data or tag) memory error" + }, + {, + "EventCode": "0xD1", + "EventName": "L1D_CACHE_ERR", + "BriefDescription": "L1 Data Cache (data, tag or dirty) memory error, correctable or non-correctable" + }, + {, + "EventCode": "0xD2", + "EventName": "TLB_ERR", + "BriefDescription": "TLB memory error" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/pipeline.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/pipeline.json new file mode 100644 index 000000000000..3149fb90555a --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/cortex-a53/pipeline.json @@ -0,0 +1,52 @@ +[ + {, + "EventCode": "0xC7", + "EventName": "STALL_SB_FULL", + "BriefDescription": "Data Write operation that stalls the pipeline because the store buffer is full" + }, + {, + "EventCode": "0xE0", + "EventName": "OTHER_IQ_DEP_STALL", + "BriefDescription": "Cycles that the DPU IQ is empty and that is not because of a recent micro-TLB miss, instruction cache miss or pre-decode error" + }, + {, + "EventCode": "0xE1", + "EventName": "IC_DEP_STALL", + "BriefDescription": "Cycles the DPU IQ is empty and there is an instruction cache miss being processed" + }, + {, + "EventCode": "0xE2", + "EventName": "IUTLB_DEP_STALL", + "BriefDescription": "Cycles the DPU IQ is empty and there is an instruction micro-TLB miss being processed" + }, + {, + "EventCode": "0xE3", + "EventName": "DECODE_DEP_STALL", + "BriefDescription": "Cycles the DPU IQ is empty and there is a pre-decode error being processed" + }, + {, + "EventCode": "0xE4", + "EventName": "OTHER_INTERLOCK_STALL", + "BriefDescription": "Cycles there is an interlock other than Advanced SIMD/Floating-point instructions or load/store instruction" + }, + {, + "EventCode": "0xE5", + "EventName": "AGU_DEP_STALL", + "BriefDescription": "Cycles there is an interlock for a load/store instruction waiting for data to calculate the address in the AGU" + }, + {, + "EventCode": "0xE6", + "EventName": "SIMD_DEP_STALL", + "BriefDescription": "Cycles there is an interlock for an Advanced SIMD/Floating-point operation." + }, + {, + "EventCode": "0xE7", + "EventName": "LD_DEP_STALL", + "BriefDescription": "Cycles there is a stall in the Wr stage because of a load miss" + }, + {, + "EventCode": "0xE8", + "EventName": "ST_DEP_STALL", + "BriefDescription": "Cycles there is a stall in the Wr stage because of a store" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/mapfile.csv b/tools/perf/pmu-events/arch/arm64/mapfile.csv index 219d6756134e..e61c9ca6cf9e 100644 --- a/tools/perf/pmu-events/arch/arm64/mapfile.csv +++ b/tools/perf/pmu-events/arch/arm64/mapfile.csv @@ -13,3 +13,4 @@ # #Family-model,Version,Filename,EventType 0x00000000420f5160,v1,cavium,core +0x00000000410fd03[[:xdigit:]],v1,cortex-a53,core From 6888ff66c44ffa3077ed69e978902d0ff4b84ae1 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Thu, 18 Jan 2018 13:26:16 -0800 Subject: [PATCH 02/27] perf evlist: Remove stale mmap read for backward perf_evlist__mmap_read_catchup() and perf_evlist__mmap_read_backward() are only for overwrite mode. But they read the evlist->mmap buffer which is for non-overwrite mode. It did not bring any serious problem yet, because there is no one use it. Remove the unused interfaces. Signed-off-by: Kan Liang Acked-by: Jiri Olsa Acked-by: Wang Nan Cc: Andi Kleen Cc: Jin Yao Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1516310792-208685-2-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evlist.c | 17 ----------------- tools/perf/util/evlist.h | 4 ---- 2 files changed, 21 deletions(-) diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index ac35cd214feb..e5fc14e53c05 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -715,28 +715,11 @@ union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, int return perf_mmap__read_forward(md); } -union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist, int idx) -{ - struct perf_mmap *md = &evlist->mmap[idx]; - - /* - * No need to check messup for backward ring buffer: - * We can always read arbitrary long data from a backward - * ring buffer unless we forget to pause it before reading. - */ - return perf_mmap__read_backward(md); -} - union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) { return perf_evlist__mmap_read_forward(evlist, idx); } -void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx) -{ - perf_mmap__read_catchup(&evlist->mmap[idx]); -} - void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx) { perf_mmap__consume(&evlist->mmap[idx], false); diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 75f8e0ad5d76..336b838e6957 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -133,10 +133,6 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx); union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, int idx); -union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist, - int idx); -void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx); - void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx); int perf_evlist__open(struct perf_evlist *evlist); From dc6c35c679e96987dc83a003f30bc2cc33c84c00 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Thu, 18 Jan 2018 13:26:17 -0800 Subject: [PATCH 03/27] perf mmap: Recalculate size for overwrite mode In perf_mmap__push(), the 'size' need to be recalculated, otherwise the invalid data might be pushed to the record in overwrite mode. The issue is introduced by commit 7fb4b407a124 ("perf mmap: Don't discard prev in backward mode"). When the ring buffer is full in overwrite mode, backward_rb_find_range() will be called to recalculate the 'start' and 'end'. The 'size' needs to be recalculated accordingly. Unconditionally recalculate the 'size', not just for full ring buffer in overwrite mode. Because: - There is no harmful to recalculate the 'size' for other cases. - The code of calculating 'start' and 'end' will be factored out later. The new function does not need to return 'size'. Signed-off-by: Kan Liang Acked-by: Jiri Olsa Cc: Andi Kleen Cc: Jin Yao Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Fixes: 7fb4b407a124 ("perf mmap: Don't discard prev in backward mode") Link: http://lkml.kernel.org/r/1516310792-208685-3-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/mmap.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c index 05076e683938..97cf4fab564b 100644 --- a/tools/perf/util/mmap.c +++ b/tools/perf/util/mmap.c @@ -302,6 +302,8 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite, return -1; } + size = end - start; + if ((start & md->mask) + size != (end & md->mask)) { buf = &data[start & md->mask]; size = md->mask + 1 - (start & md->mask); From f92c8cbe597a5a2ccec702dff824f3fe0f3623eb Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Thu, 18 Jan 2018 13:26:18 -0800 Subject: [PATCH 04/27] perf mmap: Cleanup perf_mmap__push() The first assignment for 'start' and 'end' is redundant. Signed-off-by: Kan Liang Acked-by: Jiri Olsa Cc: Andi Kleen Cc: Jin Yao Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1516310792-208685-4-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/mmap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c index 97cf4fab564b..fbbbe87f0308 100644 --- a/tools/perf/util/mmap.c +++ b/tools/perf/util/mmap.c @@ -272,7 +272,7 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite, { u64 head = perf_mmap__read_head(md); u64 old = md->prev; - u64 end = head, start = old; + u64 end, start; unsigned char *data = md->base + page_size; unsigned long size; void *buf; From 8872481bd04850b19e053dc579de5a11b83b16fc Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Thu, 18 Jan 2018 13:26:19 -0800 Subject: [PATCH 05/27] perf mmap: Introduce perf_mmap__read_init() The new function perf_mmap__read_init() is factored out from perf_mmap__push(). It is to calculate the 'start' and 'end' of the available data in ringbuffer. No functional change. Signed-off-by: Kan Liang Acked-by: Jiri Olsa Cc: Andi Kleen Cc: Jin Yao Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1516310792-208685-5-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/mmap.c | 37 +++++++++++++++++++++++++++---------- tools/perf/util/mmap.h | 2 ++ 2 files changed, 29 insertions(+), 10 deletions(-) diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c index fbbbe87f0308..c19a4e640e8e 100644 --- a/tools/perf/util/mmap.c +++ b/tools/perf/util/mmap.c @@ -267,24 +267,24 @@ static int overwrite_rb_find_range(void *buf, int mask, u64 head, u64 *start, u6 return -1; } -int perf_mmap__push(struct perf_mmap *md, bool overwrite, - void *to, int push(void *to, void *buf, size_t size)) +/* + * Report the start and end of the available data in ringbuffer + */ +int perf_mmap__read_init(struct perf_mmap *md, bool overwrite, + u64 *startp, u64 *endp) { u64 head = perf_mmap__read_head(md); u64 old = md->prev; - u64 end, start; unsigned char *data = md->base + page_size; unsigned long size; - void *buf; - int rc = 0; - start = overwrite ? head : old; - end = overwrite ? old : head; + *startp = overwrite ? head : old; + *endp = overwrite ? old : head; - if (start == end) + if (*startp == *endp) return 0; - size = end - start; + size = *endp - *startp; if (size > (unsigned long)(md->mask) + 1) { if (!overwrite) { WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n"); @@ -298,10 +298,27 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite, * Backward ring buffer is full. We still have a chance to read * most of data from it. */ - if (overwrite_rb_find_range(data, md->mask, head, &start, &end)) + if (overwrite_rb_find_range(data, md->mask, head, startp, endp)) return -1; } + return 1; +} + +int perf_mmap__push(struct perf_mmap *md, bool overwrite, + void *to, int push(void *to, void *buf, size_t size)) +{ + u64 head = perf_mmap__read_head(md); + u64 end, start; + unsigned char *data = md->base + page_size; + unsigned long size; + void *buf; + int rc = 0; + + rc = perf_mmap__read_init(md, overwrite, &start, &end); + if (rc < 1) + return rc; + size = end - start; if ((start & md->mask) + size != (end & md->mask)) { diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h index e43d7b55a55f..9ab2b48df65b 100644 --- a/tools/perf/util/mmap.h +++ b/tools/perf/util/mmap.h @@ -94,4 +94,6 @@ int perf_mmap__push(struct perf_mmap *md, bool backward, size_t perf_mmap__mmap_len(struct perf_mmap *map); +int perf_mmap__read_init(struct perf_mmap *md, bool overwrite, + u64 *startp, u64 *endp); #endif /*__PERF_MMAP_H */ From 189f2cc91f9f2efef5d5f4dde43684c01b5f6f2f Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Thu, 18 Jan 2018 13:26:20 -0800 Subject: [PATCH 06/27] perf mmap: Add new return value logic for perf_mmap__read_init() Improve the readability by using meaningful enum (-EAGAIN, -EINVAL and 0) to replace the three returning states (0, -1 and 1). Suggested-by: Wang Nan Signed-off-by: Kan Liang Acked-by: Jiri Olsa Cc: Andi Kleen Cc: Jin Yao Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1516310792-208685-6-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/mmap.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c index c19a4e640e8e..38fa69dc635e 100644 --- a/tools/perf/util/mmap.c +++ b/tools/perf/util/mmap.c @@ -282,7 +282,7 @@ int perf_mmap__read_init(struct perf_mmap *md, bool overwrite, *endp = overwrite ? old : head; if (*startp == *endp) - return 0; + return -EAGAIN; size = *endp - *startp; if (size > (unsigned long)(md->mask) + 1) { @@ -291,7 +291,7 @@ int perf_mmap__read_init(struct perf_mmap *md, bool overwrite, md->prev = head; perf_mmap__consume(md, overwrite); - return 0; + return -EAGAIN; } /* @@ -299,10 +299,10 @@ int perf_mmap__read_init(struct perf_mmap *md, bool overwrite, * most of data from it. */ if (overwrite_rb_find_range(data, md->mask, head, startp, endp)) - return -1; + return -EINVAL; } - return 1; + return 0; } int perf_mmap__push(struct perf_mmap *md, bool overwrite, @@ -316,8 +316,8 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite, int rc = 0; rc = perf_mmap__read_init(md, overwrite, &start, &end); - if (rc < 1) - return rc; + if (rc < 0) + return (rc == -EAGAIN) ? 0 : -1; size = end - start; From b4b036b4c76341a5034e872aca3727c4988a7304 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Thu, 18 Jan 2018 13:26:21 -0800 Subject: [PATCH 07/27] perf mmap: Discard 'prev' in perf_mmap__read() The 'start' and 'prev' variables are duplicates in perf_mmap__read(). Use 'map->prev' to replace 'start' in perf_mmap__read_*(). Suggested-by: Wang Nan Signed-off-by: Kan Liang Acked-by: Jiri Olsa Cc: Andi Kleen Cc: Jin Yao Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1516310792-208685-7-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/mmap.c | 28 ++++++++++------------------ 1 file changed, 10 insertions(+), 18 deletions(-) diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c index 38fa69dc635e..125bfda9d037 100644 --- a/tools/perf/util/mmap.c +++ b/tools/perf/util/mmap.c @@ -22,29 +22,27 @@ size_t perf_mmap__mmap_len(struct perf_mmap *map) /* When check_messup is true, 'end' must points to a good entry */ static union perf_event *perf_mmap__read(struct perf_mmap *map, - u64 start, u64 end, u64 *prev) + u64 *startp, u64 end) { unsigned char *data = map->base + page_size; union perf_event *event = NULL; - int diff = end - start; + int diff = end - *startp; if (diff >= (int)sizeof(event->header)) { size_t size; - event = (union perf_event *)&data[start & map->mask]; + event = (union perf_event *)&data[*startp & map->mask]; size = event->header.size; - if (size < sizeof(event->header) || diff < (int)size) { - event = NULL; - goto broken_event; - } + if (size < sizeof(event->header) || diff < (int)size) + return NULL; /* * Event straddles the mmap boundary -- header should always * be inside due to u64 alignment of output. */ - if ((start & map->mask) + size != ((start + size) & map->mask)) { - unsigned int offset = start; + if ((*startp & map->mask) + size != ((*startp + size) & map->mask)) { + unsigned int offset = *startp; unsigned int len = min(sizeof(*event), size), cpy; void *dst = map->event_copy; @@ -59,20 +57,15 @@ static union perf_event *perf_mmap__read(struct perf_mmap *map, event = (union perf_event *)map->event_copy; } - start += size; + *startp += size; } -broken_event: - if (prev) - *prev = start; - return event; } union perf_event *perf_mmap__read_forward(struct perf_mmap *map) { u64 head; - u64 old = map->prev; /* * Check if event was unmapped due to a POLLHUP/POLLERR. @@ -82,13 +75,12 @@ union perf_event *perf_mmap__read_forward(struct perf_mmap *map) head = perf_mmap__read_head(map); - return perf_mmap__read(map, old, head, &map->prev); + return perf_mmap__read(map, &map->prev, head); } union perf_event *perf_mmap__read_backward(struct perf_mmap *map) { u64 head, end; - u64 start = map->prev; /* * Check if event was unmapped due to a POLLHUP/POLLERR. @@ -118,7 +110,7 @@ union perf_event *perf_mmap__read_backward(struct perf_mmap *map) else end = head + map->mask + 1; - return perf_mmap__read(map, start, end, &map->prev); + return perf_mmap__read(map, &map->prev, end); } void perf_mmap__read_catchup(struct perf_mmap *map) From ee023de05f35484691f7d9e5c1f92195ac4d64d2 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Thu, 18 Jan 2018 13:26:22 -0800 Subject: [PATCH 08/27] perf mmap: Introduce perf_mmap__read_done() The direction of overwrite mode is backward. The last perf_mmap__read() will set tail to map->prev. Need to correct the map->prev to head which is the end of next read. It will be used later. Signed-off-by: Kan Liang Acked-by: Jiri Olsa Cc: Andi Kleen Cc: Jin Yao Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1516310792-208685-8-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/mmap.c | 11 +++++++++++ tools/perf/util/mmap.h | 1 + 2 files changed, 12 insertions(+) diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c index 125bfda9d037..4f59eaefc706 100644 --- a/tools/perf/util/mmap.c +++ b/tools/perf/util/mmap.c @@ -338,3 +338,14 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite, out: return rc; } + +/* + * Mandatory for overwrite mode + * The direction of overwrite mode is backward. + * The last perf_mmap__read() will set tail to map->prev. + * Need to correct the map->prev to head which is the end of next read. + */ +void perf_mmap__read_done(struct perf_mmap *map) +{ + map->prev = perf_mmap__read_head(map); +} diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h index 9ab2b48df65b..95549d4af943 100644 --- a/tools/perf/util/mmap.h +++ b/tools/perf/util/mmap.h @@ -96,4 +96,5 @@ size_t perf_mmap__mmap_len(struct perf_mmap *map); int perf_mmap__read_init(struct perf_mmap *md, bool overwrite, u64 *startp, u64 *endp); +void perf_mmap__read_done(struct perf_mmap *map); #endif /*__PERF_MMAP_H */ From 7bb45972952db9298fe5cc440160dcad1a66bfbc Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Thu, 18 Jan 2018 13:26:23 -0800 Subject: [PATCH 09/27] perf mmap: Introduce perf_mmap__read_event() Except for 'perf record', the other perf tools read events one by one from the ring buffer using perf_mmap__read_forward(). But it only supports non-overwrite mode. Introduce perf_mmap__read_event() to support both non-overwrite and overwrite mode. Usage: perf_mmap__read_init() while(event = perf_mmap__read_event()) { //process the event perf_mmap__consume() } perf_mmap__read_done() It cannot use perf_mmap__read_backward(). Because it always reads the stale buffer which is already processed. Furthermore, the forward and backward concepts have been removed. The perf_mmap__read_backward() will be replaced and discarded later. Signed-off-by: Kan Liang Acked-by: Jiri Olsa Cc: Andi Kleen Cc: Jin Yao Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1516310792-208685-9-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/mmap.c | 39 +++++++++++++++++++++++++++++++++++++++ tools/perf/util/mmap.h | 4 ++++ 2 files changed, 43 insertions(+) diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c index 4f59eaefc706..f804926778b7 100644 --- a/tools/perf/util/mmap.c +++ b/tools/perf/util/mmap.c @@ -113,6 +113,45 @@ union perf_event *perf_mmap__read_backward(struct perf_mmap *map) return perf_mmap__read(map, &map->prev, end); } +/* + * Read event from ring buffer one by one. + * Return one event for each call. + * + * Usage: + * perf_mmap__read_init() + * while(event = perf_mmap__read_event()) { + * //process the event + * perf_mmap__consume() + * } + * perf_mmap__read_done() + */ +union perf_event *perf_mmap__read_event(struct perf_mmap *map, + bool overwrite, + u64 *startp, u64 end) +{ + union perf_event *event; + + /* + * Check if event was unmapped due to a POLLHUP/POLLERR. + */ + if (!refcount_read(&map->refcnt)) + return NULL; + + if (startp == NULL) + return NULL; + + /* non-overwirte doesn't pause the ringbuffer */ + if (!overwrite) + end = perf_mmap__read_head(map); + + event = perf_mmap__read(map, startp, end); + + if (!overwrite) + map->prev = *startp; + + return event; +} + void perf_mmap__read_catchup(struct perf_mmap *map) { u64 head; diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h index 95549d4af943..28718543dd42 100644 --- a/tools/perf/util/mmap.h +++ b/tools/perf/util/mmap.h @@ -89,6 +89,10 @@ static inline void perf_mmap__write_tail(struct perf_mmap *md, u64 tail) union perf_event *perf_mmap__read_forward(struct perf_mmap *map); union perf_event *perf_mmap__read_backward(struct perf_mmap *map); +union perf_event *perf_mmap__read_event(struct perf_mmap *map, + bool overwrite, + u64 *startp, u64 end); + int perf_mmap__push(struct perf_mmap *md, bool backward, void *to, int push(void *to, void *buf, size_t size)); From 600a7cfe88de2c6e44e23d61dd721b996b790eb2 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Thu, 18 Jan 2018 13:26:24 -0800 Subject: [PATCH 10/27] perf test: Update mmap read functions for backward-ring-buffer test Use the new perf_mmap__read_* interfaces for overwrite ringbuffer test. Commiter notes: Testing: [root@seventh ~]# perf test -v backward 48: Read backward ring buffer : --- start --- test child forked, pid 8309 Using CPUID GenuineIntel-6-9E mmap size 1052672B mmap size 8192B Finished reading overwrite ring buffer: rewind test child finished with 0 ---- end ---- Read backward ring buffer: Ok [root@seventh ~]# Signed-off-by: Kan Liang Acked-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Andi Kleen Cc: Jin Yao Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1516310792-208685-10-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/backward-ring-buffer.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c index 4035d43523c3..e0b1b414d466 100644 --- a/tools/perf/tests/backward-ring-buffer.c +++ b/tools/perf/tests/backward-ring-buffer.c @@ -31,10 +31,12 @@ static int count_samples(struct perf_evlist *evlist, int *sample_count, int i; for (i = 0; i < evlist->nr_mmaps; i++) { + struct perf_mmap *map = &evlist->overwrite_mmap[i]; union perf_event *event; + u64 start, end; - perf_mmap__read_catchup(&evlist->overwrite_mmap[i]); - while ((event = perf_mmap__read_backward(&evlist->overwrite_mmap[i])) != NULL) { + perf_mmap__read_init(map, true, &start, &end); + while ((event = perf_mmap__read_event(map, true, &start, end)) != NULL) { const u32 type = event->header.type; switch (type) { @@ -49,6 +51,7 @@ static int count_samples(struct perf_evlist *evlist, int *sample_count, return TEST_FAIL; } } + perf_mmap__read_done(map); } return TEST_OK; } From 3effc2f165a842d640873e29d4c5cc1650143aef Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Thu, 18 Jan 2018 13:26:25 -0800 Subject: [PATCH 11/27] perf mmap: Discard legacy interface for mmap read Discards perf_mmap__read_backward() and perf_mmap__read_catchup(). No tools use them. There are tools still use perf_mmap__read_forward(). Keep it, but add comments to point to the new interface for future use. Signed-off-by: Kan Liang Acked-by: Jiri Olsa Cc: Andi Kleen Cc: Jin Yao Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1516310792-208685-11-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/mmap.c | 50 ++++-------------------------------------- tools/perf/util/mmap.h | 3 --- 2 files changed, 4 insertions(+), 49 deletions(-) diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c index f804926778b7..91531a7c8fbf 100644 --- a/tools/perf/util/mmap.c +++ b/tools/perf/util/mmap.c @@ -63,6 +63,10 @@ static union perf_event *perf_mmap__read(struct perf_mmap *map, return event; } +/* + * legacy interface for mmap read. + * Don't use it. Use perf_mmap__read_event(). + */ union perf_event *perf_mmap__read_forward(struct perf_mmap *map) { u64 head; @@ -78,41 +82,6 @@ union perf_event *perf_mmap__read_forward(struct perf_mmap *map) return perf_mmap__read(map, &map->prev, head); } -union perf_event *perf_mmap__read_backward(struct perf_mmap *map) -{ - u64 head, end; - - /* - * Check if event was unmapped due to a POLLHUP/POLLERR. - */ - if (!refcount_read(&map->refcnt)) - return NULL; - - head = perf_mmap__read_head(map); - if (!head) - return NULL; - - /* - * 'head' pointer starts from 0. Kernel minus sizeof(record) form - * it each time when kernel writes to it, so in fact 'head' is - * negative. 'end' pointer is made manually by adding the size of - * the ring buffer to 'head' pointer, means the validate data can - * read is the whole ring buffer. If 'end' is positive, the ring - * buffer has not fully filled, so we must adjust 'end' to 0. - * - * However, since both 'head' and 'end' is unsigned, we can't - * simply compare 'end' against 0. Here we compare '-head' and - * the size of the ring buffer, where -head is the number of bytes - * kernel write to the ring buffer. - */ - if (-head < (u64)(map->mask + 1)) - end = 0; - else - end = head + map->mask + 1; - - return perf_mmap__read(map, &map->prev, end); -} - /* * Read event from ring buffer one by one. * Return one event for each call. @@ -152,17 +121,6 @@ union perf_event *perf_mmap__read_event(struct perf_mmap *map, return event; } -void perf_mmap__read_catchup(struct perf_mmap *map) -{ - u64 head; - - if (!refcount_read(&map->refcnt)) - return; - - head = perf_mmap__read_head(map); - map->prev = head; -} - static bool perf_mmap__empty(struct perf_mmap *map) { return perf_mmap__read_head(map) == map->prev && !map->auxtrace_mmap.base; diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h index 28718543dd42..ec7d3a24e276 100644 --- a/tools/perf/util/mmap.h +++ b/tools/perf/util/mmap.h @@ -65,8 +65,6 @@ void perf_mmap__put(struct perf_mmap *map); void perf_mmap__consume(struct perf_mmap *map, bool overwrite); -void perf_mmap__read_catchup(struct perf_mmap *md); - static inline u64 perf_mmap__read_head(struct perf_mmap *mm) { struct perf_event_mmap_page *pc = mm->base; @@ -87,7 +85,6 @@ static inline void perf_mmap__write_tail(struct perf_mmap *md, u64 tail) } union perf_event *perf_mmap__read_forward(struct perf_mmap *map); -union perf_event *perf_mmap__read_backward(struct perf_mmap *map); union perf_event *perf_mmap__read_event(struct perf_mmap *map, bool overwrite, From 63878a53cedc3df31bd4ba8740a49fa0fc116ac6 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Thu, 18 Jan 2018 13:26:26 -0800 Subject: [PATCH 12/27] perf top: Check per-event overwrite term Per-event overwrite term is not forbidden in 'perf top', which can bring problems. Because 'perf top' only support non-overwrite mode now. Add new rules and check regarding to overwrite term for 'perf top'. - All events either have same per-event term or don't have per-event mode setting. Otherwise, it will error out. - Per-event overwrite term should be consistent as opts->overwrite. If not, updating the opts->overwrite according to per-event term. Make it possible to support either non-overwrite or overwrite mode. The overwrite mode is forbidden now, which will be removed when the overwrite mode is supported later. Signed-off-by: Kan Liang Acked-by: Jiri Olsa Cc: Andi Kleen Cc: Jin Yao Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1516310792-208685-12-git-send-email-kan.liang@intel.com [ Renamed perf_top_overwrite_check to perf_top__overwrite_check, to follow existing convention ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-top.c | 73 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 73 insertions(+) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index c6ccda52117d..17783798924a 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -881,6 +881,68 @@ static void perf_top__mmap_read(struct perf_top *top) perf_top__mmap_read_idx(top, i); } +/* + * Check per-event overwrite term. + * perf top should support consistent term for all events. + * - All events don't have per-event term + * E.g. "cpu/cpu-cycles/,cpu/instructions/" + * Nothing change, return 0. + * - All events have same per-event term + * E.g. "cpu/cpu-cycles,no-overwrite/,cpu/instructions,no-overwrite/ + * Using the per-event setting to replace the opts->overwrite if + * they are different, then return 0. + * - Events have different per-event term + * E.g. "cpu/cpu-cycles,overwrite/,cpu/instructions,no-overwrite/" + * Return -1 + * - Some of the event set per-event term, but some not. + * E.g. "cpu/cpu-cycles/,cpu/instructions,no-overwrite/" + * Return -1 + */ +static int perf_top__overwrite_check(struct perf_top *top) +{ + struct record_opts *opts = &top->record_opts; + struct perf_evlist *evlist = top->evlist; + struct perf_evsel_config_term *term; + struct list_head *config_terms; + struct perf_evsel *evsel; + int set, overwrite = -1; + + evlist__for_each_entry(evlist, evsel) { + set = -1; + config_terms = &evsel->config_terms; + list_for_each_entry(term, config_terms, list) { + if (term->type == PERF_EVSEL__CONFIG_TERM_OVERWRITE) + set = term->val.overwrite ? 1 : 0; + } + + /* no term for current and previous event (likely) */ + if ((overwrite < 0) && (set < 0)) + continue; + + /* has term for both current and previous event, compare */ + if ((overwrite >= 0) && (set >= 0) && (overwrite != set)) + return -1; + + /* no term for current event but has term for previous one */ + if ((overwrite >= 0) && (set < 0)) + return -1; + + /* has term for current event */ + if ((overwrite < 0) && (set >= 0)) { + /* if it's first event, set overwrite */ + if (evsel == perf_evlist__first(evlist)) + overwrite = set; + else + return -1; + } + } + + if ((overwrite >= 0) && (opts->overwrite != overwrite)) + opts->overwrite = overwrite; + + return 0; +} + static int perf_top__start_counters(struct perf_top *top) { char msg[BUFSIZ]; @@ -888,6 +950,17 @@ static int perf_top__start_counters(struct perf_top *top) struct perf_evlist *evlist = top->evlist; struct record_opts *opts = &top->record_opts; + if (perf_top__overwrite_check(top)) { + ui__error("perf top only support consistent per-event " + "overwrite setting for all events\n"); + goto out_err; + } + + if (opts->overwrite) { + ui__error("not support overwrite mode yet\n"); + goto out_err; + } + perf_evlist__config(evlist, opts, &callchain_param); evlist__for_each_entry(evlist, counter) { From 9a831b3a32c5daf5d7cc672334d51930f78e4ea3 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 2 Feb 2018 11:27:25 -0300 Subject: [PATCH 13/27] perf evsel: Expose the perf_missing_features struct As tools may need to adjust to missing features, as 'perf top' will, in the next csets, to cope with a missing 'write_backward' feature. Cc: Andi Kleen Cc: Jin Yao Cc: Jiri Olsa Cc: Kan Liang Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-jelngl9q1ooaizvkcput9tic@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 12 +----------- tools/perf/util/evsel.h | 14 ++++++++++++++ 2 files changed, 15 insertions(+), 11 deletions(-) diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index ff359c9ece2e..ef351688b797 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -41,17 +41,7 @@ #include "sane_ctype.h" -static struct { - bool sample_id_all; - bool exclude_guest; - bool mmap2; - bool cloexec; - bool clockid; - bool clockid_wrong; - bool lbr_flags; - bool write_backward; - bool group_read; -} perf_missing_features; +struct perf_missing_features perf_missing_features; static clockid_t clockid; diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 846e41644525..a7487c6d1866 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -149,6 +149,20 @@ union u64_swap { u32 val32[2]; }; +struct perf_missing_features { + bool sample_id_all; + bool exclude_guest; + bool mmap2; + bool cloexec; + bool clockid; + bool clockid_wrong; + bool lbr_flags; + bool write_backward; + bool group_read; +}; + +extern struct perf_missing_features perf_missing_features; + struct cpu_map; struct target; struct thread_map; From 204721d7eabe6ee98aafce791ce3efdbc4715834 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Thu, 18 Jan 2018 13:26:28 -0800 Subject: [PATCH 14/27] perf top: Add overwrite fall back Switch to non-overwrite mode if kernel doesnot support overwrite ringbuffer. It's only effect when overwrite mode is supported. No change to current behavior. Signed-off-by: Kan Liang Acked-by: Jiri Olsa Cc: Andi Kleen Cc: Jin Yao Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1516310792-208685-14-git-send-email-kan.liang@intel.com [ Use perf_missing_features.write_backward instead of the non merged is_write_backward_fail() ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-top.c | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 17783798924a..ee4bba1e282c 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -943,6 +943,27 @@ static int perf_top__overwrite_check(struct perf_top *top) return 0; } +static int perf_top_overwrite_fallback(struct perf_top *top, + struct perf_evsel *evsel) +{ + struct record_opts *opts = &top->record_opts; + struct perf_evlist *evlist = top->evlist; + struct perf_evsel *counter; + + if (!opts->overwrite) + return 0; + + /* only fall back when first event fails */ + if (evsel != perf_evlist__first(evlist)) + return 0; + + evlist__for_each_entry(evlist, counter) + counter->attr.write_backward = false; + opts->overwrite = false; + ui__warning("fall back to non-overwrite mode\n"); + return 1; +} + static int perf_top__start_counters(struct perf_top *top) { char msg[BUFSIZ]; @@ -967,6 +988,21 @@ static int perf_top__start_counters(struct perf_top *top) try_again: if (perf_evsel__open(counter, top->evlist->cpus, top->evlist->threads) < 0) { + + /* + * Specially handle overwrite fall back. + * Because perf top is the only tool which has + * overwrite mode by default, support + * both overwrite and non-overwrite mode, and + * require consistent mode for all events. + * + * May move it to generic code with more tools + * have similar attribute. + */ + if (perf_missing_features.write_backward && + perf_top_overwrite_fallback(top, counter)) + goto try_again; + if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) { if (verbose > 0) ui__warning("%s\n", msg); From 06cc1a470ab237b991901729b125404c164f3660 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Thu, 18 Jan 2018 13:26:29 -0800 Subject: [PATCH 15/27] perf hists browser: Add parameter to disable lost event warning For overwrite mode, the ringbuffer will be paused. The event lost is expected. It needs a way to notify the browser not print the warning. It will be used later for perf top to disable lost event warning in overwrite mode. There is no behavior change for now. Signed-off-by: Kan Liang Acked-by: Jiri Olsa Cc: Andi Kleen Cc: Jin Yao Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1516310792-208685-15-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-c2c.c | 4 ++-- tools/perf/builtin-report.c | 3 ++- tools/perf/builtin-top.c | 2 +- tools/perf/ui/browsers/hists.c | 38 ++++++++++++++++++++++------------ tools/perf/ui/browsers/hists.h | 3 ++- tools/perf/util/hist.h | 6 ++++-- 6 files changed, 36 insertions(+), 20 deletions(-) diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index c0815a37fdb5..539c3d460158 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -2245,7 +2245,7 @@ static int perf_c2c__browse_cacheline(struct hist_entry *he) c2c_browser__update_nr_entries(browser); while (1) { - key = hist_browser__run(browser, "? - help"); + key = hist_browser__run(browser, "? - help", true); switch (key) { case 's': @@ -2314,7 +2314,7 @@ static int perf_c2c__hists_browse(struct hists *hists) c2c_browser__update_nr_entries(browser); while (1) { - key = hist_browser__run(browser, "? - help"); + key = hist_browser__run(browser, "? - help", true); switch (key) { case 'q': diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 42a52dcc41cd..4ad5dc649716 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -530,7 +530,8 @@ static int report__browse_hists(struct report *rep) case 1: ret = perf_evlist__tui_browse_hists(evlist, help, NULL, rep->min_percent, - &session->header.env); + &session->header.env, + true); /* * Usually "ret" is the last pressed key, and we only * care if the key notifies us to switch data file. diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index ee4bba1e282c..7def861a9ec4 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -611,7 +611,7 @@ static void *display_thread_tui(void *arg) perf_evlist__tui_browse_hists(top->evlist, help, &hbt, top->min_percent, - &top->session->header.env); + &top->session->header.env, true); done = 1; return NULL; diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 68146f4620a5..6495ee55d9c3 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -608,7 +608,8 @@ static int hist_browser__title(struct hist_browser *browser, char *bf, size_t si return browser->title ? browser->title(browser, bf, size) : 0; } -int hist_browser__run(struct hist_browser *browser, const char *help) +int hist_browser__run(struct hist_browser *browser, const char *help, + bool warn_lost_event) { int key; char title[160]; @@ -638,8 +639,9 @@ int hist_browser__run(struct hist_browser *browser, const char *help) nr_entries = hist_browser__nr_entries(browser); ui_browser__update_nr_entries(&browser->b, nr_entries); - if (browser->hists->stats.nr_lost_warned != - browser->hists->stats.nr_events[PERF_RECORD_LOST]) { + if (warn_lost_event && + (browser->hists->stats.nr_lost_warned != + browser->hists->stats.nr_events[PERF_RECORD_LOST])) { browser->hists->stats.nr_lost_warned = browser->hists->stats.nr_events[PERF_RECORD_LOST]; ui_browser__warn_lost_events(&browser->b); @@ -2763,7 +2765,8 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, bool left_exits, struct hist_browser_timer *hbt, float min_pcnt, - struct perf_env *env) + struct perf_env *env, + bool warn_lost_event) { struct hists *hists = evsel__hists(evsel); struct hist_browser *browser = perf_evsel_browser__new(evsel, hbt, env); @@ -2844,7 +2847,8 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, nr_options = 0; - key = hist_browser__run(browser, helpline); + key = hist_browser__run(browser, helpline, + warn_lost_event); if (browser->he_selection != NULL) { thread = hist_browser__selected_thread(browser); @@ -3184,7 +3188,8 @@ static void perf_evsel_menu__write(struct ui_browser *browser, static int perf_evsel_menu__run(struct perf_evsel_menu *menu, int nr_events, const char *help, - struct hist_browser_timer *hbt) + struct hist_browser_timer *hbt, + bool warn_lost_event) { struct perf_evlist *evlist = menu->b.priv; struct perf_evsel *pos; @@ -3203,7 +3208,9 @@ static int perf_evsel_menu__run(struct perf_evsel_menu *menu, case K_TIMER: hbt->timer(hbt->arg); - if (!menu->lost_events_warned && menu->lost_events) { + if (!menu->lost_events_warned && + menu->lost_events && + warn_lost_event) { ui_browser__warn_lost_events(&menu->b); menu->lost_events_warned = true; } @@ -3224,7 +3231,8 @@ static int perf_evsel_menu__run(struct perf_evsel_menu *menu, key = perf_evsel__hists_browse(pos, nr_events, help, true, hbt, menu->min_pcnt, - menu->env); + menu->env, + warn_lost_event); ui_browser__show_title(&menu->b, title); switch (key) { case K_TAB: @@ -3282,7 +3290,8 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist, int nr_entries, const char *help, struct hist_browser_timer *hbt, float min_pcnt, - struct perf_env *env) + struct perf_env *env, + bool warn_lost_event) { struct perf_evsel *pos; struct perf_evsel_menu menu = { @@ -3309,13 +3318,15 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist, menu.b.width = line_len; } - return perf_evsel_menu__run(&menu, nr_entries, help, hbt); + return perf_evsel_menu__run(&menu, nr_entries, help, + hbt, warn_lost_event); } int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, struct hist_browser_timer *hbt, float min_pcnt, - struct perf_env *env) + struct perf_env *env, + bool warn_lost_event) { int nr_entries = evlist->nr_entries; @@ -3325,7 +3336,7 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, return perf_evsel__hists_browse(first, nr_entries, help, false, hbt, min_pcnt, - env); + env, warn_lost_event); } if (symbol_conf.event_group) { @@ -3342,5 +3353,6 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, } return __perf_evlist__tui_browse_hists(evlist, nr_entries, help, - hbt, min_pcnt, env); + hbt, min_pcnt, env, + warn_lost_event); } diff --git a/tools/perf/ui/browsers/hists.h b/tools/perf/ui/browsers/hists.h index ba431777f559..9428bee076f2 100644 --- a/tools/perf/ui/browsers/hists.h +++ b/tools/perf/ui/browsers/hists.h @@ -28,7 +28,8 @@ struct hist_browser { struct hist_browser *hist_browser__new(struct hists *hists); void hist_browser__delete(struct hist_browser *browser); -int hist_browser__run(struct hist_browser *browser, const char *help); +int hist_browser__run(struct hist_browser *browser, const char *help, + bool warn_lost_event); void hist_browser__init(struct hist_browser *browser, struct hists *hists); #endif /* _PERF_UI_BROWSER_HISTS_H_ */ diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index f6630cb95eff..02721b579746 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -430,7 +430,8 @@ int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel, int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, struct hist_browser_timer *hbt, float min_pcnt, - struct perf_env *env); + struct perf_env *env, + bool warn_lost_event); int script_browse(const char *script_opt); #else static inline @@ -438,7 +439,8 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused, const char *help __maybe_unused, struct hist_browser_timer *hbt __maybe_unused, float min_pcnt __maybe_unused, - struct perf_env *env __maybe_unused) + struct perf_env *env __maybe_unused, + bool warn_lost_event __maybe_unused) { return 0; } From a1ff5b05e988ca3620027148cd61013408ea4194 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Thu, 18 Jan 2018 13:26:30 -0800 Subject: [PATCH 16/27] perf top: Remove lost events checking There would be some records lost in overwrite mode because of pausing the ringbuffer. It has little impact for the accuracy of the snapshot and could be tolerated by 'perf top'. Remove the lost events checking. Signed-off-by: Kan Liang Acked-by: Jiri Olsa Cc: Andi Kleen Cc: Jin Yao Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1516310792-208685-16-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-top.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 7def861a9ec4..59653062bb48 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -283,8 +283,9 @@ static void perf_top__print_sym_table(struct perf_top *top) printf("%-*.*s\n", win_width, win_width, graph_dotted_line); - if (hists->stats.nr_lost_warned != - hists->stats.nr_events[PERF_RECORD_LOST]) { + if (!top->record_opts.overwrite && + (hists->stats.nr_lost_warned != + hists->stats.nr_events[PERF_RECORD_LOST])) { hists->stats.nr_lost_warned = hists->stats.nr_events[PERF_RECORD_LOST]; color_fprintf(stdout, PERF_COLOR_RED, @@ -611,7 +612,8 @@ static void *display_thread_tui(void *arg) perf_evlist__tui_browse_hists(top->evlist, help, &hbt, top->min_percent, - &top->session->header.env, true); + &top->session->header.env, + !top->record_opts.overwrite); done = 1; return NULL; From ebebbf082357f86cc84a4d46ce897a5750e41b7a Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Thu, 18 Jan 2018 13:26:31 -0800 Subject: [PATCH 17/27] perf top: Switch default mode to overwrite mode perf_top__mmap_read() has a severe performance issue in the Knights Landing/Mill platform, when monitoring heavy load systems. It costs several minutes to finish, which is unacceptable. Currently, 'perf top' uses the non overwrite mode. For non overwrite mode, it tries to read everything in the ringbuffer and doesn't pause it. Once there are lots of samples delivered persistently, the processing time could be very long. Also, the latest samples could be lost when the ringbuffer is full. For overwrite mode, it takes a snapshot for the system by pausing the ringbuffer, which could significantly reduce the processing time. Also, the overwrite mode always keep the latest samples. Considering the real time requirement for 'perf top', the overwrite mode is more suitable for it. Actually, 'perf top' was overwrite mode. It is changed to non overwrite mode since commit 93fc64f14472 ("perf top: Switch to non overwrite mode"). It's better to change it back to overwrite mode by default. For the kernel which doesn't support overwrite mode, it will fall back to non overwrite mode. There would be some records lost in overwrite mode because of pausing the ringbuffer. It has little impact for the accuracy of the snapshot and can be tolerated. For overwrite mode, unconditionally wait 100 ms before each snapshot. It also reduces the overhead caused by pausing ringbuffer, especially on light load system. Signed-off-by: Kan Liang Acked-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Andi Kleen Cc: Jin Yao Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1516310792-208685-17-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-top.c | 34 +++++++++++++++++++++++++--------- 1 file changed, 25 insertions(+), 9 deletions(-) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 59653062bb48..2b4914f34ed6 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -809,15 +809,23 @@ static void perf_event__process_sample(struct perf_tool *tool, static void perf_top__mmap_read_idx(struct perf_top *top, int idx) { + struct record_opts *opts = &top->record_opts; + struct perf_evlist *evlist = top->evlist; struct perf_sample sample; struct perf_evsel *evsel; + struct perf_mmap *md; struct perf_session *session = top->session; union perf_event *event; struct machine *machine; + u64 end, start; int ret; - while ((event = perf_evlist__mmap_read(top->evlist, idx)) != NULL) { - ret = perf_evlist__parse_sample(top->evlist, event, &sample); + md = opts->overwrite ? &evlist->overwrite_mmap[idx] : &evlist->mmap[idx]; + if (perf_mmap__read_init(md, opts->overwrite, &start, &end) < 0) + return; + + while ((event = perf_mmap__read_event(md, opts->overwrite, &start, end)) != NULL) { + ret = perf_evlist__parse_sample(evlist, event, &sample); if (ret) { pr_err("Can't parse sample, err = %d\n", ret); goto next_event; @@ -871,16 +879,28 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) } else ++session->evlist->stats.nr_unknown_events; next_event: - perf_evlist__mmap_consume(top->evlist, idx); + perf_mmap__consume(md, opts->overwrite); } + + perf_mmap__read_done(md); } static void perf_top__mmap_read(struct perf_top *top) { + bool overwrite = top->record_opts.overwrite; + struct perf_evlist *evlist = top->evlist; int i; + if (overwrite) + perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_DATA_PENDING); + for (i = 0; i < top->evlist->nr_mmaps; i++) perf_top__mmap_read_idx(top, i); + + if (overwrite) { + perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY); + perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING); + } } /* @@ -979,11 +999,6 @@ static int perf_top__start_counters(struct perf_top *top) goto out_err; } - if (opts->overwrite) { - ui__error("not support overwrite mode yet\n"); - goto out_err; - } - perf_evlist__config(evlist, opts, &callchain_param); evlist__for_each_entry(evlist, counter) { @@ -1144,7 +1159,7 @@ static int __cmd_top(struct perf_top *top) perf_top__mmap_read(top); - if (hits == top->samples) + if (opts->overwrite || (hits == top->samples)) ret = perf_evlist__poll(top->evlist, 100); if (resize) { @@ -1238,6 +1253,7 @@ int cmd_top(int argc, const char **argv) .uses_mmap = true, }, .proc_map_timeout = 500, + .overwrite = 1, }, .max_stack = sysctl_perf_event_max_stack, .sym_pcnt_filter = 5, From 8cc42de736b617827a4e7664fb8d7a325bc125bc Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Thu, 18 Jan 2018 13:26:32 -0800 Subject: [PATCH 18/27] perf top: Check the latency of perf_top__mmap_read() The latency of perf_top__mmap_read() should be lower than refresh time. If not, give some hints to reduce the latency. Signed-off-by: Kan Liang Acked-by: Jiri Olsa Cc: Andi Kleen Cc: Jin Yao Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1516310792-208685-18-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-top.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 2b4914f34ed6..b7c823ba8374 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -889,8 +889,10 @@ static void perf_top__mmap_read(struct perf_top *top) { bool overwrite = top->record_opts.overwrite; struct perf_evlist *evlist = top->evlist; + unsigned long long start, end; int i; + start = rdclock(); if (overwrite) perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_DATA_PENDING); @@ -901,6 +903,13 @@ static void perf_top__mmap_read(struct perf_top *top) perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY); perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING); } + end = rdclock(); + + if ((end - start) > (unsigned long long)top->delay_secs * NSEC_PER_SEC) + ui__warning("Too slow to read ring buffer.\n" + "Please try increasing the period (-c) or\n" + "decreasing the freq (-F) or\n" + "limiting the number of CPUs (-C)\n"); } /* From 6677d26c8befa462eab9be6c5335a939011e7e65 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 29 Jan 2018 15:03:59 +0200 Subject: [PATCH 19/27] perf tools: Substitute yet another strtoull() Instead of home grown function let's use what library provides us. Signed-off-by: Andriy Shevchenko Acked-by: Jiri Olsa Link: http://lkml.kernel.org/r/20180129130359.1490-1-andriy.shevchenko@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/util.c | 24 ++---------------------- 1 file changed, 2 insertions(+), 22 deletions(-) diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 443892dabedb..1019bbc5dbd8 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -340,35 +340,15 @@ size_t hex_width(u64 v) return n; } -static int hex(char ch) -{ - if ((ch >= '0') && (ch <= '9')) - return ch - '0'; - if ((ch >= 'a') && (ch <= 'f')) - return ch - 'a' + 10; - if ((ch >= 'A') && (ch <= 'F')) - return ch - 'A' + 10; - return -1; -} - /* * While we find nice hex chars, build a long_val. * Return number of chars processed. */ int hex2u64(const char *ptr, u64 *long_val) { - const char *p = ptr; - *long_val = 0; + char *p; - while (*p) { - const int hex_val = hex(*p); - - if (hex_val < 0) - break; - - *long_val = (*long_val << 4) | hex_val; - p++; - } + *long_val = strtoull(ptr, &p, 16); return p - ptr; } From ba7e851642f48002def3450b279598c187721fd0 Mon Sep 17 00:00:00 2001 From: Sangwon Hong Date: Mon, 5 Feb 2018 20:48:35 +0900 Subject: [PATCH 20/27] perf data: Document missing --force option Add the --force option to the man page. Signed-off-by: Sangwon Hong Cc: Jiri Olsa Cc: Namhyung Kim Cc: Taeung Song Link: http://lkml.kernel.org/r/1517831315-31490-1-git-send-email-qpakzk@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-data.txt | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/perf/Documentation/perf-data.txt b/tools/perf/Documentation/perf-data.txt index f0796a47dfa3..90bb4aabe4f8 100644 --- a/tools/perf/Documentation/perf-data.txt +++ b/tools/perf/Documentation/perf-data.txt @@ -30,6 +30,10 @@ OPTIONS for 'convert' -i:: Specify input perf data file path. +-f:: +--force:: + Don't complain, do it. + -v:: --verbose:: Be more verbose (show counter open errors, etc). From 7a92453620d42c3a5fea94a864dc6aa04c262b93 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Wed, 17 Jan 2018 09:38:31 +0100 Subject: [PATCH 21/27] perf test: Fix test trace+probe_libc_inet_pton.sh for s390x On Intel test case trace+probe_libc_inet_pton.sh succeeds and the output is: [root@f27 perf]# ./perf trace --no-syscalls -e probe_libc:inet_pton/max-stack=3/ ping -6 -c 1 ::1 PING ::1(::1) 56 data bytes 64 bytes from ::1: icmp_seq=1 ttl=64 time=0.037 ms --- ::1 ping statistics --- 1 packets transmitted, 1 received, 0% packet loss, time 0ms rtt min/avg/max/mdev = 0.037/0.037/0.037/0.000 ms 0.000 probe_libc:inet_pton:(7fa40ac618a0)) __GI___inet_pton (/usr/lib64/libc-2.26.so) getaddrinfo (/usr/lib64/libc-2.26.so) main (/usr/bin/ping) The kernel stack unwinder is used, it is specified implicitly as call-graph=fp (frame pointer). On s390x only dwarf is available for stack unwinding. It is also done in user space. This requires different parameter setup and result checking for s390x and Intel. This patch adds separate perf trace setup and result checking for Intel and s390x. On s390x specify this command line to get a call-graph and handle the different call graph result checking: [root@s35lp76 perf]# ./perf trace --no-syscalls -e probe_libc:inet_pton/call-graph=dwarf/ ping -6 -c 1 ::1 PING ::1(::1) 56 data bytes 64 bytes from ::1: icmp_seq=1 ttl=64 time=0.041 ms --- ::1 ping statistics --- 1 packets transmitted, 1 received, 0% packet loss, time 0ms rtt min/avg/max/mdev = 0.041/0.041/0.041/0.000 ms 0.000 probe_libc:inet_pton:(3ffb9942060)) __GI___inet_pton (/usr/lib64/libc-2.26.so) gaih_inet (inlined) __GI_getaddrinfo (inlined) main (/usr/bin/ping) __libc_start_main (/usr/lib64/libc-2.26.so) _start (/usr/bin/ping) [root@s35lp76 perf]# Before: [root@s8360047 perf]# ./perf test -vv 58 58: probe libc's inet_pton & backtrace it with ping : --- start --- test child forked, pid 26349 PING ::1(::1) 56 data bytes 64 bytes from ::1: icmp_seq=1 ttl=64 time=0.079 ms --- ::1 ping statistics --- 1 packets transmitted, 1 received, 0% packet loss, time 0ms rtt min/avg/max/mdev = 0.079/0.079/0.079/0.000 ms 0.000 probe_libc:inet_pton:(3ff925c2060)) test child finished with -1 ---- end ---- probe libc's inet_pton & backtrace it with ping: FAILED! [root@s8360047 perf]# After: [root@s35lp76 perf]# ./perf test -vv 57 57: probe libc's inet_pton & backtrace it with ping : --- start --- test child forked, pid 38708 PING ::1(::1) 56 data bytes 64 bytes from ::1: icmp_seq=1 ttl=64 time=0.038 ms --- ::1 ping statistics --- 1 packets transmitted, 1 received, 0% packet loss, time 0ms rtt min/avg/max/mdev = 0.038/0.038/0.038/0.000 ms 0.000 probe_libc:inet_pton:(3ff87342060)) __GI___inet_pton (/usr/lib64/libc-2.26.so) gaih_inet (inlined) __GI_getaddrinfo (inlined) main (/usr/bin/ping) __libc_start_main (/usr/lib64/libc-2.26.so) _start (/usr/bin/ping) test child finished with 0 ---- end ---- probe libc's inet_pton & backtrace it with ping: Ok [root@s35lp76 perf]# On Intel the test case runs unchanged and succeeds. Signed-off-by: Thomas Richter Reviewed-by: Hendrik Brueckner Tested-by: Arnaldo Carvalho de Melo Cc: Heiko Carstens Cc: Martin Schwidefsky Link: http://lkml.kernel.org/r/20180117083831.101001-1-tmricht@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- .../tests/shell/trace+probe_libc_inet_pton.sh | 21 +++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) diff --git a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh index 8b3da21a08f1..c446c894b297 100755 --- a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh +++ b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh @@ -22,10 +22,23 @@ trace_libc_inet_pton_backtrace() { expected[4]="rtt min.*" expected[5]="[0-9]+\.[0-9]+[[:space:]]+probe_libc:inet_pton:\([[:xdigit:]]+\)" expected[6]=".*inet_pton[[:space:]]\($libc\)$" - expected[7]="getaddrinfo[[:space:]]\($libc\)$" - expected[8]=".*\(.*/bin/ping.*\)$" + case "$(uname -m)" in + s390x) + eventattr='call-graph=dwarf' + expected[7]="gaih_inet[[:space:]]\(inlined\)$" + expected[8]="__GI_getaddrinfo[[:space:]]\(inlined\)$" + expected[9]="main[[:space:]]\(.*/bin/ping.*\)$" + expected[10]="__libc_start_main[[:space:]]\($libc\)$" + expected[11]="_start[[:space:]]\(.*/bin/ping.*\)$" + ;; + *) + eventattr='max-stack=3' + expected[7]="getaddrinfo[[:space:]]\($libc\)$" + expected[8]=".*\(.*/bin/ping.*\)$" + ;; + esac - perf trace --no-syscalls -e probe_libc:inet_pton/max-stack=3/ ping -6 -c 1 ::1 2>&1 | grep -v ^$ | while read line ; do + perf trace --no-syscalls -e probe_libc:inet_pton/$eventattr/ ping -6 -c 1 ::1 2>&1 | grep -v ^$ | while read line ; do echo $line echo "$line" | egrep -q "${expected[$idx]}" if [ $? -ne 0 ] ; then @@ -33,7 +46,7 @@ trace_libc_inet_pton_backtrace() { exit 1 fi let idx+=1 - [ $idx -eq 9 ] && break + [ -z "${expected[$idx]}" ] && break done } From f091f1d6a2b4840c9b631d6138f5354401347863 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 13 Feb 2018 12:54:58 +0100 Subject: [PATCH 22/27] tools/headers: Synchronize kernel ABI headers, v4.16-rc1 Sync the following tooling headers with the latest kernel version: tools/arch/powerpc/include/uapi/asm/kvm.h tools/arch/x86/include/asm/cpufeatures.h tools/include/uapi/drm/i915_drm.h tools/include/uapi/linux/if_link.h tools/include/uapi/linux/kvm.h All the changes are new ABI additions which don't impact their use in existing tooling. Cc: Arnaldo Carvalho de Melo Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Namhyung Kim Cc: Jiri Olsa Cc: Stephen Rothwell Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- tools/arch/powerpc/include/uapi/asm/kvm.h | 2 + tools/arch/x86/include/asm/cpufeatures.h | 1 + tools/include/uapi/drm/i915_drm.h | 77 +++++++++++++++++++ tools/include/uapi/linux/if_link.h | 1 + tools/include/uapi/linux/kvm.h | 90 +++++++++++++++++++++++ 5 files changed, 171 insertions(+) diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h index 637b7263cb86..833ed9a16adf 100644 --- a/tools/arch/powerpc/include/uapi/asm/kvm.h +++ b/tools/arch/powerpc/include/uapi/asm/kvm.h @@ -632,6 +632,8 @@ struct kvm_ppc_cpu_char { #define KVM_REG_PPC_TIDR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbc) #define KVM_REG_PPC_PSSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd) +#define KVM_REG_PPC_DEC_EXPIRY (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbe) + /* Transactional Memory checkpointed state: * This is all GPRs, all VSX regs and a subset of SPRs */ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 1d9199e1c2ad..0dfe4d3f74e2 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -210,6 +210,7 @@ #define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ #define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */ +#define X86_FEATURE_SEV ( 7*32+20) /* AMD Secure Encrypted Virtualization */ #define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index ac3c6503ca27..536ee4febd74 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -86,6 +86,62 @@ enum i915_mocs_table_index { I915_MOCS_CACHED, }; +/* + * Different engines serve different roles, and there may be more than one + * engine serving each role. enum drm_i915_gem_engine_class provides a + * classification of the role of the engine, which may be used when requesting + * operations to be performed on a certain subset of engines, or for providing + * information about that group. + */ +enum drm_i915_gem_engine_class { + I915_ENGINE_CLASS_RENDER = 0, + I915_ENGINE_CLASS_COPY = 1, + I915_ENGINE_CLASS_VIDEO = 2, + I915_ENGINE_CLASS_VIDEO_ENHANCE = 3, + + I915_ENGINE_CLASS_INVALID = -1 +}; + +/** + * DOC: perf_events exposed by i915 through /sys/bus/event_sources/drivers/i915 + * + */ + +enum drm_i915_pmu_engine_sample { + I915_SAMPLE_BUSY = 0, + I915_SAMPLE_WAIT = 1, + I915_SAMPLE_SEMA = 2 +}; + +#define I915_PMU_SAMPLE_BITS (4) +#define I915_PMU_SAMPLE_MASK (0xf) +#define I915_PMU_SAMPLE_INSTANCE_BITS (8) +#define I915_PMU_CLASS_SHIFT \ + (I915_PMU_SAMPLE_BITS + I915_PMU_SAMPLE_INSTANCE_BITS) + +#define __I915_PMU_ENGINE(class, instance, sample) \ + ((class) << I915_PMU_CLASS_SHIFT | \ + (instance) << I915_PMU_SAMPLE_BITS | \ + (sample)) + +#define I915_PMU_ENGINE_BUSY(class, instance) \ + __I915_PMU_ENGINE(class, instance, I915_SAMPLE_BUSY) + +#define I915_PMU_ENGINE_WAIT(class, instance) \ + __I915_PMU_ENGINE(class, instance, I915_SAMPLE_WAIT) + +#define I915_PMU_ENGINE_SEMA(class, instance) \ + __I915_PMU_ENGINE(class, instance, I915_SAMPLE_SEMA) + +#define __I915_PMU_OTHER(x) (__I915_PMU_ENGINE(0xff, 0xff, 0xf) + 1 + (x)) + +#define I915_PMU_ACTUAL_FREQUENCY __I915_PMU_OTHER(0) +#define I915_PMU_REQUESTED_FREQUENCY __I915_PMU_OTHER(1) +#define I915_PMU_INTERRUPTS __I915_PMU_OTHER(2) +#define I915_PMU_RC6_RESIDENCY __I915_PMU_OTHER(3) + +#define I915_PMU_LAST I915_PMU_RC6_RESIDENCY + /* Each region is a minimum of 16k, and there are at most 255 of them. */ #define I915_NR_TEX_REGIONS 255 /* table size 2k - maximum due to use @@ -450,6 +506,27 @@ typedef struct drm_i915_irq_wait { */ #define I915_PARAM_HAS_EXEC_FENCE_ARRAY 49 +/* + * Query whether every context (both per-file default and user created) is + * isolated (insofar as HW supports). If this parameter is not true, then + * freshly created contexts may inherit values from an existing context, + * rather than default HW values. If true, it also ensures (insofar as HW + * supports) that all state set by this context will not leak to any other + * context. + * + * As not every engine across every gen support contexts, the returned + * value reports the support of context isolation for individual engines by + * returning a bitmask of each engine class set to true if that class supports + * isolation. + */ +#define I915_PARAM_HAS_CONTEXT_ISOLATION 50 + +/* Frequency of the command streamer timestamps given by the *_TIMESTAMP + * registers. This used to be fixed per platform but from CNL onwards, this + * might vary depending on the parts. + */ +#define I915_PARAM_CS_TIMESTAMP_FREQUENCY 51 + typedef struct drm_i915_getparam { __s32 param; /* diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index 8616131e2c61..6d9447700e18 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -163,6 +163,7 @@ enum { IFLA_IF_NETNSID, IFLA_CARRIER_UP_COUNT, IFLA_CARRIER_DOWN_COUNT, + IFLA_NEW_IFINDEX, __IFLA_MAX }; diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 8fb90a0819c3..0fb5ef939732 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -1362,6 +1362,96 @@ struct kvm_s390_ucas_mapping { /* Available with KVM_CAP_S390_CMMA_MIGRATION */ #define KVM_S390_GET_CMMA_BITS _IOWR(KVMIO, 0xb8, struct kvm_s390_cmma_log) #define KVM_S390_SET_CMMA_BITS _IOW(KVMIO, 0xb9, struct kvm_s390_cmma_log) +/* Memory Encryption Commands */ +#define KVM_MEMORY_ENCRYPT_OP _IOWR(KVMIO, 0xba, unsigned long) + +struct kvm_enc_region { + __u64 addr; + __u64 size; +}; + +#define KVM_MEMORY_ENCRYPT_REG_REGION _IOR(KVMIO, 0xbb, struct kvm_enc_region) +#define KVM_MEMORY_ENCRYPT_UNREG_REGION _IOR(KVMIO, 0xbc, struct kvm_enc_region) + +/* Secure Encrypted Virtualization command */ +enum sev_cmd_id { + /* Guest initialization commands */ + KVM_SEV_INIT = 0, + KVM_SEV_ES_INIT, + /* Guest launch commands */ + KVM_SEV_LAUNCH_START, + KVM_SEV_LAUNCH_UPDATE_DATA, + KVM_SEV_LAUNCH_UPDATE_VMSA, + KVM_SEV_LAUNCH_SECRET, + KVM_SEV_LAUNCH_MEASURE, + KVM_SEV_LAUNCH_FINISH, + /* Guest migration commands (outgoing) */ + KVM_SEV_SEND_START, + KVM_SEV_SEND_UPDATE_DATA, + KVM_SEV_SEND_UPDATE_VMSA, + KVM_SEV_SEND_FINISH, + /* Guest migration commands (incoming) */ + KVM_SEV_RECEIVE_START, + KVM_SEV_RECEIVE_UPDATE_DATA, + KVM_SEV_RECEIVE_UPDATE_VMSA, + KVM_SEV_RECEIVE_FINISH, + /* Guest status and debug commands */ + KVM_SEV_GUEST_STATUS, + KVM_SEV_DBG_DECRYPT, + KVM_SEV_DBG_ENCRYPT, + /* Guest certificates commands */ + KVM_SEV_CERT_EXPORT, + + KVM_SEV_NR_MAX, +}; + +struct kvm_sev_cmd { + __u32 id; + __u64 data; + __u32 error; + __u32 sev_fd; +}; + +struct kvm_sev_launch_start { + __u32 handle; + __u32 policy; + __u64 dh_uaddr; + __u32 dh_len; + __u64 session_uaddr; + __u32 session_len; +}; + +struct kvm_sev_launch_update_data { + __u64 uaddr; + __u32 len; +}; + + +struct kvm_sev_launch_secret { + __u64 hdr_uaddr; + __u32 hdr_len; + __u64 guest_uaddr; + __u32 guest_len; + __u64 trans_uaddr; + __u32 trans_len; +}; + +struct kvm_sev_launch_measure { + __u64 uaddr; + __u32 len; +}; + +struct kvm_sev_guest_status { + __u32 handle; + __u32 policy; + __u32 state; +}; + +struct kvm_sev_dbg { + __u64 src_uaddr; + __u64 dst_uaddr; + __u32 len; +}; #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) #define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1) From baa676103037e0dd145bb905eb51bc0b2f48fd49 Mon Sep 17 00:00:00 2001 From: Hendrik Brueckner Date: Thu, 8 Feb 2018 12:47:49 +0100 Subject: [PATCH 23/27] perf s390: Grab a copy of arch/s390/kernel/syscall/syscall.tbl Grab a copy of the s390 system call table file introduced with commit 857f46bfb07f53dc112d69bdfb137cc5ec3da7c5 "s390/syscalls: add system call table". Signed-off-by: Hendrik Brueckner Cc: Jiri Olsa Cc: Michael Petlan Cc: Thomas Richter Cc: linux-s390@vger.kernel.org LPU-Reference: 1518090470-2899-3-git-send-email-brueckner@linux.vnet.ibm.com Link: https://lkml.kernel.org/n/tip-hpw7vdjp7g92ivgpddrp5ydq@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- .../perf/arch/s390/entry/syscalls/syscall.tbl | 390 ++++++++++++++++++ 1 file changed, 390 insertions(+) create mode 100644 tools/perf/arch/s390/entry/syscalls/syscall.tbl diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl new file mode 100644 index 000000000000..b38d48464368 --- /dev/null +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -0,0 +1,390 @@ +# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note +# +# System call table for s390 +# +# Format: +# +# +# +# where can be common, 64, or 32 + +1 common exit sys_exit sys_exit +2 common fork sys_fork sys_fork +3 common read sys_read compat_sys_s390_read +4 common write sys_write compat_sys_s390_write +5 common open sys_open compat_sys_open +6 common close sys_close sys_close +7 common restart_syscall sys_restart_syscall sys_restart_syscall +8 common creat sys_creat compat_sys_creat +9 common link sys_link compat_sys_link +10 common unlink sys_unlink compat_sys_unlink +11 common execve sys_execve compat_sys_execve +12 common chdir sys_chdir compat_sys_chdir +13 32 time - compat_sys_time +14 common mknod sys_mknod compat_sys_mknod +15 common chmod sys_chmod compat_sys_chmod +16 32 lchown - compat_sys_s390_lchown16 +19 common lseek sys_lseek compat_sys_lseek +20 common getpid sys_getpid sys_getpid +21 common mount sys_mount compat_sys_mount +22 common umount sys_oldumount compat_sys_oldumount +23 32 setuid - compat_sys_s390_setuid16 +24 32 getuid - compat_sys_s390_getuid16 +25 32 stime - compat_sys_stime +26 common ptrace sys_ptrace compat_sys_ptrace +27 common alarm sys_alarm sys_alarm +29 common pause sys_pause sys_pause +30 common utime sys_utime compat_sys_utime +33 common access sys_access compat_sys_access +34 common nice sys_nice sys_nice +36 common sync sys_sync sys_sync +37 common kill sys_kill sys_kill +38 common rename sys_rename compat_sys_rename +39 common mkdir sys_mkdir compat_sys_mkdir +40 common rmdir sys_rmdir compat_sys_rmdir +41 common dup sys_dup sys_dup +42 common pipe sys_pipe compat_sys_pipe +43 common times sys_times compat_sys_times +45 common brk sys_brk compat_sys_brk +46 32 setgid - compat_sys_s390_setgid16 +47 32 getgid - compat_sys_s390_getgid16 +48 common signal sys_signal compat_sys_signal +49 32 geteuid - compat_sys_s390_geteuid16 +50 32 getegid - compat_sys_s390_getegid16 +51 common acct sys_acct compat_sys_acct +52 common umount2 sys_umount compat_sys_umount +54 common ioctl sys_ioctl compat_sys_ioctl +55 common fcntl sys_fcntl compat_sys_fcntl +57 common setpgid sys_setpgid sys_setpgid +60 common umask sys_umask sys_umask +61 common chroot sys_chroot compat_sys_chroot +62 common ustat sys_ustat compat_sys_ustat +63 common dup2 sys_dup2 sys_dup2 +64 common getppid sys_getppid sys_getppid +65 common getpgrp sys_getpgrp sys_getpgrp +66 common setsid sys_setsid sys_setsid +67 common sigaction sys_sigaction compat_sys_sigaction +70 32 setreuid - compat_sys_s390_setreuid16 +71 32 setregid - compat_sys_s390_setregid16 +72 common sigsuspend sys_sigsuspend compat_sys_sigsuspend +73 common sigpending sys_sigpending compat_sys_sigpending +74 common sethostname sys_sethostname compat_sys_sethostname +75 common setrlimit sys_setrlimit compat_sys_setrlimit +76 32 getrlimit - compat_sys_old_getrlimit +77 common getrusage sys_getrusage compat_sys_getrusage +78 common gettimeofday sys_gettimeofday compat_sys_gettimeofday +79 common settimeofday sys_settimeofday compat_sys_settimeofday +80 32 getgroups - compat_sys_s390_getgroups16 +81 32 setgroups - compat_sys_s390_setgroups16 +83 common symlink sys_symlink compat_sys_symlink +85 common readlink sys_readlink compat_sys_readlink +86 common uselib sys_uselib compat_sys_uselib +87 common swapon sys_swapon compat_sys_swapon +88 common reboot sys_reboot compat_sys_reboot +89 common readdir - compat_sys_old_readdir +90 common mmap sys_old_mmap compat_sys_s390_old_mmap +91 common munmap sys_munmap compat_sys_munmap +92 common truncate sys_truncate compat_sys_truncate +93 common ftruncate sys_ftruncate compat_sys_ftruncate +94 common fchmod sys_fchmod sys_fchmod +95 32 fchown - compat_sys_s390_fchown16 +96 common getpriority sys_getpriority sys_getpriority +97 common setpriority sys_setpriority sys_setpriority +99 common statfs sys_statfs compat_sys_statfs +100 common fstatfs sys_fstatfs compat_sys_fstatfs +101 32 ioperm - - +102 common socketcall sys_socketcall compat_sys_socketcall +103 common syslog sys_syslog compat_sys_syslog +104 common setitimer sys_setitimer compat_sys_setitimer +105 common getitimer sys_getitimer compat_sys_getitimer +106 common stat sys_newstat compat_sys_newstat +107 common lstat sys_newlstat compat_sys_newlstat +108 common fstat sys_newfstat compat_sys_newfstat +110 common lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie +111 common vhangup sys_vhangup sys_vhangup +112 common idle - - +114 common wait4 sys_wait4 compat_sys_wait4 +115 common swapoff sys_swapoff compat_sys_swapoff +116 common sysinfo sys_sysinfo compat_sys_sysinfo +117 common ipc sys_s390_ipc compat_sys_s390_ipc +118 common fsync sys_fsync sys_fsync +119 common sigreturn sys_sigreturn compat_sys_sigreturn +120 common clone sys_clone compat_sys_clone +121 common setdomainname sys_setdomainname compat_sys_setdomainname +122 common uname sys_newuname compat_sys_newuname +124 common adjtimex sys_adjtimex compat_sys_adjtimex +125 common mprotect sys_mprotect compat_sys_mprotect +126 common sigprocmask sys_sigprocmask compat_sys_sigprocmask +127 common create_module - - +128 common init_module sys_init_module compat_sys_init_module +129 common delete_module sys_delete_module compat_sys_delete_module +130 common get_kernel_syms - - +131 common quotactl sys_quotactl compat_sys_quotactl +132 common getpgid sys_getpgid sys_getpgid +133 common fchdir sys_fchdir sys_fchdir +134 common bdflush sys_bdflush compat_sys_bdflush +135 common sysfs sys_sysfs compat_sys_sysfs +136 common personality sys_s390_personality sys_s390_personality +137 common afs_syscall - - +138 32 setfsuid - compat_sys_s390_setfsuid16 +139 32 setfsgid - compat_sys_s390_setfsgid16 +140 32 _llseek - compat_sys_llseek +141 common getdents sys_getdents compat_sys_getdents +142 32 _newselect - compat_sys_select +142 64 select sys_select - +143 common flock sys_flock sys_flock +144 common msync sys_msync compat_sys_msync +145 common readv sys_readv compat_sys_readv +146 common writev sys_writev compat_sys_writev +147 common getsid sys_getsid sys_getsid +148 common fdatasync sys_fdatasync sys_fdatasync +149 common _sysctl sys_sysctl compat_sys_sysctl +150 common mlock sys_mlock compat_sys_mlock +151 common munlock sys_munlock compat_sys_munlock +152 common mlockall sys_mlockall sys_mlockall +153 common munlockall sys_munlockall sys_munlockall +154 common sched_setparam sys_sched_setparam compat_sys_sched_setparam +155 common sched_getparam sys_sched_getparam compat_sys_sched_getparam +156 common sched_setscheduler sys_sched_setscheduler compat_sys_sched_setscheduler +157 common sched_getscheduler sys_sched_getscheduler sys_sched_getscheduler +158 common sched_yield sys_sched_yield sys_sched_yield +159 common sched_get_priority_max sys_sched_get_priority_max sys_sched_get_priority_max +160 common sched_get_priority_min sys_sched_get_priority_min sys_sched_get_priority_min +161 common sched_rr_get_interval sys_sched_rr_get_interval compat_sys_sched_rr_get_interval +162 common nanosleep sys_nanosleep compat_sys_nanosleep +163 common mremap sys_mremap compat_sys_mremap +164 32 setresuid - compat_sys_s390_setresuid16 +165 32 getresuid - compat_sys_s390_getresuid16 +167 common query_module - - +168 common poll sys_poll compat_sys_poll +169 common nfsservctl - - +170 32 setresgid - compat_sys_s390_setresgid16 +171 32 getresgid - compat_sys_s390_getresgid16 +172 common prctl sys_prctl compat_sys_prctl +173 common rt_sigreturn sys_rt_sigreturn compat_sys_rt_sigreturn +174 common rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction +175 common rt_sigprocmask sys_rt_sigprocmask compat_sys_rt_sigprocmask +176 common rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending +177 common rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait +178 common rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo +179 common rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend +180 common pread64 sys_pread64 compat_sys_s390_pread64 +181 common pwrite64 sys_pwrite64 compat_sys_s390_pwrite64 +182 32 chown - compat_sys_s390_chown16 +183 common getcwd sys_getcwd compat_sys_getcwd +184 common capget sys_capget compat_sys_capget +185 common capset sys_capset compat_sys_capset +186 common sigaltstack sys_sigaltstack compat_sys_sigaltstack +187 common sendfile sys_sendfile64 compat_sys_sendfile +188 common getpmsg - - +189 common putpmsg - - +190 common vfork sys_vfork sys_vfork +191 32 ugetrlimit - compat_sys_getrlimit +191 64 getrlimit sys_getrlimit - +192 32 mmap2 - compat_sys_s390_mmap2 +193 32 truncate64 - compat_sys_s390_truncate64 +194 32 ftruncate64 - compat_sys_s390_ftruncate64 +195 32 stat64 - compat_sys_s390_stat64 +196 32 lstat64 - compat_sys_s390_lstat64 +197 32 fstat64 - compat_sys_s390_fstat64 +198 32 lchown32 - compat_sys_lchown +198 64 lchown sys_lchown - +199 32 getuid32 - sys_getuid +199 64 getuid sys_getuid - +200 32 getgid32 - sys_getgid +200 64 getgid sys_getgid - +201 32 geteuid32 - sys_geteuid +201 64 geteuid sys_geteuid - +202 32 getegid32 - sys_getegid +202 64 getegid sys_getegid - +203 32 setreuid32 - sys_setreuid +203 64 setreuid sys_setreuid - +204 32 setregid32 - sys_setregid +204 64 setregid sys_setregid - +205 32 getgroups32 - compat_sys_getgroups +205 64 getgroups sys_getgroups - +206 32 setgroups32 - compat_sys_setgroups +206 64 setgroups sys_setgroups - +207 32 fchown32 - sys_fchown +207 64 fchown sys_fchown - +208 32 setresuid32 - sys_setresuid +208 64 setresuid sys_setresuid - +209 32 getresuid32 - compat_sys_getresuid +209 64 getresuid sys_getresuid - +210 32 setresgid32 - sys_setresgid +210 64 setresgid sys_setresgid - +211 32 getresgid32 - compat_sys_getresgid +211 64 getresgid sys_getresgid - +212 32 chown32 - compat_sys_chown +212 64 chown sys_chown - +213 32 setuid32 - sys_setuid +213 64 setuid sys_setuid - +214 32 setgid32 - sys_setgid +214 64 setgid sys_setgid - +215 32 setfsuid32 - sys_setfsuid +215 64 setfsuid sys_setfsuid - +216 32 setfsgid32 - sys_setfsgid +216 64 setfsgid sys_setfsgid - +217 common pivot_root sys_pivot_root compat_sys_pivot_root +218 common mincore sys_mincore compat_sys_mincore +219 common madvise sys_madvise compat_sys_madvise +220 common getdents64 sys_getdents64 compat_sys_getdents64 +221 32 fcntl64 - compat_sys_fcntl64 +222 common readahead sys_readahead compat_sys_s390_readahead +223 32 sendfile64 - compat_sys_sendfile64 +224 common setxattr sys_setxattr compat_sys_setxattr +225 common lsetxattr sys_lsetxattr compat_sys_lsetxattr +226 common fsetxattr sys_fsetxattr compat_sys_fsetxattr +227 common getxattr sys_getxattr compat_sys_getxattr +228 common lgetxattr sys_lgetxattr compat_sys_lgetxattr +229 common fgetxattr sys_fgetxattr compat_sys_fgetxattr +230 common listxattr sys_listxattr compat_sys_listxattr +231 common llistxattr sys_llistxattr compat_sys_llistxattr +232 common flistxattr sys_flistxattr compat_sys_flistxattr +233 common removexattr sys_removexattr compat_sys_removexattr +234 common lremovexattr sys_lremovexattr compat_sys_lremovexattr +235 common fremovexattr sys_fremovexattr compat_sys_fremovexattr +236 common gettid sys_gettid sys_gettid +237 common tkill sys_tkill sys_tkill +238 common futex sys_futex compat_sys_futex +239 common sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity +240 common sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity +241 common tgkill sys_tgkill sys_tgkill +243 common io_setup sys_io_setup compat_sys_io_setup +244 common io_destroy sys_io_destroy compat_sys_io_destroy +245 common io_getevents sys_io_getevents compat_sys_io_getevents +246 common io_submit sys_io_submit compat_sys_io_submit +247 common io_cancel sys_io_cancel compat_sys_io_cancel +248 common exit_group sys_exit_group sys_exit_group +249 common epoll_create sys_epoll_create sys_epoll_create +250 common epoll_ctl sys_epoll_ctl compat_sys_epoll_ctl +251 common epoll_wait sys_epoll_wait compat_sys_epoll_wait +252 common set_tid_address sys_set_tid_address compat_sys_set_tid_address +253 common fadvise64 sys_fadvise64_64 compat_sys_s390_fadvise64 +254 common timer_create sys_timer_create compat_sys_timer_create +255 common timer_settime sys_timer_settime compat_sys_timer_settime +256 common timer_gettime sys_timer_gettime compat_sys_timer_gettime +257 common timer_getoverrun sys_timer_getoverrun sys_timer_getoverrun +258 common timer_delete sys_timer_delete sys_timer_delete +259 common clock_settime sys_clock_settime compat_sys_clock_settime +260 common clock_gettime sys_clock_gettime compat_sys_clock_gettime +261 common clock_getres sys_clock_getres compat_sys_clock_getres +262 common clock_nanosleep sys_clock_nanosleep compat_sys_clock_nanosleep +264 32 fadvise64_64 - compat_sys_s390_fadvise64_64 +265 common statfs64 sys_statfs64 compat_sys_statfs64 +266 common fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 +267 common remap_file_pages sys_remap_file_pages compat_sys_remap_file_pages +268 common mbind sys_mbind compat_sys_mbind +269 common get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy +270 common set_mempolicy sys_set_mempolicy compat_sys_set_mempolicy +271 common mq_open sys_mq_open compat_sys_mq_open +272 common mq_unlink sys_mq_unlink compat_sys_mq_unlink +273 common mq_timedsend sys_mq_timedsend compat_sys_mq_timedsend +274 common mq_timedreceive sys_mq_timedreceive compat_sys_mq_timedreceive +275 common mq_notify sys_mq_notify compat_sys_mq_notify +276 common mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr +277 common kexec_load sys_kexec_load compat_sys_kexec_load +278 common add_key sys_add_key compat_sys_add_key +279 common request_key sys_request_key compat_sys_request_key +280 common keyctl sys_keyctl compat_sys_keyctl +281 common waitid sys_waitid compat_sys_waitid +282 common ioprio_set sys_ioprio_set sys_ioprio_set +283 common ioprio_get sys_ioprio_get sys_ioprio_get +284 common inotify_init sys_inotify_init sys_inotify_init +285 common inotify_add_watch sys_inotify_add_watch compat_sys_inotify_add_watch +286 common inotify_rm_watch sys_inotify_rm_watch sys_inotify_rm_watch +287 common migrate_pages sys_migrate_pages compat_sys_migrate_pages +288 common openat sys_openat compat_sys_openat +289 common mkdirat sys_mkdirat compat_sys_mkdirat +290 common mknodat sys_mknodat compat_sys_mknodat +291 common fchownat sys_fchownat compat_sys_fchownat +292 common futimesat sys_futimesat compat_sys_futimesat +293 32 fstatat64 - compat_sys_s390_fstatat64 +293 64 newfstatat sys_newfstatat - +294 common unlinkat sys_unlinkat compat_sys_unlinkat +295 common renameat sys_renameat compat_sys_renameat +296 common linkat sys_linkat compat_sys_linkat +297 common symlinkat sys_symlinkat compat_sys_symlinkat +298 common readlinkat sys_readlinkat compat_sys_readlinkat +299 common fchmodat sys_fchmodat compat_sys_fchmodat +300 common faccessat sys_faccessat compat_sys_faccessat +301 common pselect6 sys_pselect6 compat_sys_pselect6 +302 common ppoll sys_ppoll compat_sys_ppoll +303 common unshare sys_unshare compat_sys_unshare +304 common set_robust_list sys_set_robust_list compat_sys_set_robust_list +305 common get_robust_list sys_get_robust_list compat_sys_get_robust_list +306 common splice sys_splice compat_sys_splice +307 common sync_file_range sys_sync_file_range compat_sys_s390_sync_file_range +308 common tee sys_tee compat_sys_tee +309 common vmsplice sys_vmsplice compat_sys_vmsplice +310 common move_pages sys_move_pages compat_sys_move_pages +311 common getcpu sys_getcpu compat_sys_getcpu +312 common epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait +313 common utimes sys_utimes compat_sys_utimes +314 common fallocate sys_fallocate compat_sys_s390_fallocate +315 common utimensat sys_utimensat compat_sys_utimensat +316 common signalfd sys_signalfd compat_sys_signalfd +317 common timerfd - - +318 common eventfd sys_eventfd sys_eventfd +319 common timerfd_create sys_timerfd_create sys_timerfd_create +320 common timerfd_settime sys_timerfd_settime compat_sys_timerfd_settime +321 common timerfd_gettime sys_timerfd_gettime compat_sys_timerfd_gettime +322 common signalfd4 sys_signalfd4 compat_sys_signalfd4 +323 common eventfd2 sys_eventfd2 sys_eventfd2 +324 common inotify_init1 sys_inotify_init1 sys_inotify_init1 +325 common pipe2 sys_pipe2 compat_sys_pipe2 +326 common dup3 sys_dup3 sys_dup3 +327 common epoll_create1 sys_epoll_create1 sys_epoll_create1 +328 common preadv sys_preadv compat_sys_preadv +329 common pwritev sys_pwritev compat_sys_pwritev +330 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo +331 common perf_event_open sys_perf_event_open compat_sys_perf_event_open +332 common fanotify_init sys_fanotify_init sys_fanotify_init +333 common fanotify_mark sys_fanotify_mark compat_sys_fanotify_mark +334 common prlimit64 sys_prlimit64 compat_sys_prlimit64 +335 common name_to_handle_at sys_name_to_handle_at compat_sys_name_to_handle_at +336 common open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at +337 common clock_adjtime sys_clock_adjtime compat_sys_clock_adjtime +338 common syncfs sys_syncfs sys_syncfs +339 common setns sys_setns sys_setns +340 common process_vm_readv sys_process_vm_readv compat_sys_process_vm_readv +341 common process_vm_writev sys_process_vm_writev compat_sys_process_vm_writev +342 common s390_runtime_instr sys_s390_runtime_instr sys_s390_runtime_instr +343 common kcmp sys_kcmp compat_sys_kcmp +344 common finit_module sys_finit_module compat_sys_finit_module +345 common sched_setattr sys_sched_setattr compat_sys_sched_setattr +346 common sched_getattr sys_sched_getattr compat_sys_sched_getattr +347 common renameat2 sys_renameat2 compat_sys_renameat2 +348 common seccomp sys_seccomp compat_sys_seccomp +349 common getrandom sys_getrandom compat_sys_getrandom +350 common memfd_create sys_memfd_create compat_sys_memfd_create +351 common bpf sys_bpf compat_sys_bpf +352 common s390_pci_mmio_write sys_s390_pci_mmio_write compat_sys_s390_pci_mmio_write +353 common s390_pci_mmio_read sys_s390_pci_mmio_read compat_sys_s390_pci_mmio_read +354 common execveat sys_execveat compat_sys_execveat +355 common userfaultfd sys_userfaultfd sys_userfaultfd +356 common membarrier sys_membarrier sys_membarrier +357 common recvmmsg sys_recvmmsg compat_sys_recvmmsg +358 common sendmmsg sys_sendmmsg compat_sys_sendmmsg +359 common socket sys_socket sys_socket +360 common socketpair sys_socketpair compat_sys_socketpair +361 common bind sys_bind compat_sys_bind +362 common connect sys_connect compat_sys_connect +363 common listen sys_listen sys_listen +364 common accept4 sys_accept4 compat_sys_accept4 +365 common getsockopt sys_getsockopt compat_sys_getsockopt +366 common setsockopt sys_setsockopt compat_sys_setsockopt +367 common getsockname sys_getsockname compat_sys_getsockname +368 common getpeername sys_getpeername compat_sys_getpeername +369 common sendto sys_sendto compat_sys_sendto +370 common sendmsg sys_sendmsg compat_sys_sendmsg +371 common recvfrom sys_recvfrom compat_sys_recvfrom +372 common recvmsg sys_recvmsg compat_sys_recvmsg +373 common shutdown sys_shutdown sys_shutdown +374 common mlock2 sys_mlock2 compat_sys_mlock2 +375 common copy_file_range sys_copy_file_range compat_sys_copy_file_range +376 common preadv2 sys_preadv2 compat_sys_preadv2 +377 common pwritev2 sys_pwritev2 compat_sys_pwritev2 +378 common s390_guarded_storage sys_s390_guarded_storage compat_sys_s390_guarded_storage +379 common statx sys_statx compat_sys_statx +380 common s390_sthyi sys_s390_sthyi compat_sys_s390_sthyi From 690d22d9d4423b4522fb44a71145403eef2df834 Mon Sep 17 00:00:00 2001 From: Hendrik Brueckner Date: Thu, 8 Feb 2018 12:47:50 +0100 Subject: [PATCH 24/27] perf s390: Rework system call table creation by using syscall.tbl Recently, s390 uses a syscall.tbl input file to generate its system call table and unistd uapi header files. Hence, update mksyscalltbl to use it as input to create the system table for perf. Signed-off-by: Hendrik Brueckner Cc: Jiri Olsa Cc: Michael Petlan Cc: Thomas Richter Cc: linux-s390@vger.kernel.org LPU-Reference: 1518090470-2899-4-git-send-email-brueckner@linux.vnet.ibm.com Link: https://lkml.kernel.org/n/tip-bdyhllhsq1zgxv2qx4m377y6@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/s390/Makefile | 10 +++++++--- .../perf/arch/s390/entry/syscalls/mksyscalltbl | 18 +++++++----------- 2 files changed, 14 insertions(+), 14 deletions(-) diff --git a/tools/perf/arch/s390/Makefile b/tools/perf/arch/s390/Makefile index 48228de415d0..dfa6e3103437 100644 --- a/tools/perf/arch/s390/Makefile +++ b/tools/perf/arch/s390/Makefile @@ -10,15 +10,19 @@ PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1 out := $(OUTPUT)arch/s390/include/generated/asm header := $(out)/syscalls_64.c -sysdef := $(srctree)/tools/arch/s390/include/uapi/asm/unistd.h -sysprf := $(srctree)/tools/perf/arch/s390/entry/syscalls/ +syskrn := $(srctree)/arch/s390/kernel/syscalls/syscall.tbl +sysprf := $(srctree)/tools/perf/arch/s390/entry/syscalls +sysdef := $(sysprf)/syscall.tbl systbl := $(sysprf)/mksyscalltbl # Create output directory if not already present _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') $(header): $(sysdef) $(systbl) - $(Q)$(SHELL) '$(systbl)' '$(CC)' $(sysdef) > $@ + @(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \ + (diff -B $(sysdef) $(syskrn) >/dev/null) \ + || echo "Warning: Kernel ABI header at '$(sysdef)' differs from latest version at '$(syskrn)'" >&2 )) || true + $(Q)$(SHELL) '$(systbl)' $(sysdef) > $@ clean:: $(call QUIET_CLEAN, s390) $(RM) $(header) diff --git a/tools/perf/arch/s390/entry/syscalls/mksyscalltbl b/tools/perf/arch/s390/entry/syscalls/mksyscalltbl index 7fa0d0abd419..72ecbb676370 100755 --- a/tools/perf/arch/s390/entry/syscalls/mksyscalltbl +++ b/tools/perf/arch/s390/entry/syscalls/mksyscalltbl @@ -3,25 +3,23 @@ # # Generate system call table for perf # -# -# Copyright IBM Corp. 2017 +# Copyright IBM Corp. 2017, 2018 # Author(s): Hendrik Brueckner # -gcc=$1 -input=$2 +SYSCALL_TBL=$1 -if ! test -r $input; then +if ! test -r $SYSCALL_TBL; then echo "Could not read input file" >&2 exit 1 fi create_table() { - local max_nr + local max_nr nr abi sc discard echo 'static const char *syscalltbl_s390_64[] = {' - while read sc nr; do + while read nr abi sc discard; do printf '\t[%d] = "%s",\n' $nr $sc max_nr=$nr done @@ -29,8 +27,6 @@ create_table() echo "#define SYSCALLTBL_S390_64_MAX_ID $max_nr" } - -$gcc -m64 -E -dM -x c $input \ - |sed -ne 's/^#define __NR_//p' \ - |sort -t' ' -k2 -nu \ +grep -E "^[[:digit:]]+[[:space:]]+(common|64)" $SYSCALL_TBL \ + |sort -k1 -n \ |create_table From f1d0b4cde922863004ce3f5f39e8662cc0686c96 Mon Sep 17 00:00:00 2001 From: Hendrik Brueckner Date: Thu, 8 Feb 2018 12:47:48 +0100 Subject: [PATCH 25/27] Revert "tools include s390: Grab a copy of arch/s390/include/uapi/asm/unistd.h" This reverts commit f120c7b187e6c418238710b48723ce141f467543 which is no longer required with the introduction of a syscall.tbl on s390. Signed-off-by: Hendrik Brueckner Cc: Jiri Olsa Cc: Michael Petlan Cc: Thomas Richter Cc: linux-s390@vger.kernel.org LPU-Reference: 1518090470-2899-2-git-send-email-brueckner@linux.vnet.ibm.com Link: https://lkml.kernel.org/n/tip-q1lg0nvhha1tk39ri9aqalcb@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/s390/include/uapi/asm/unistd.h | 412 ---------------------- tools/perf/check-headers.sh | 1 - 2 files changed, 413 deletions(-) delete mode 100644 tools/arch/s390/include/uapi/asm/unistd.h diff --git a/tools/arch/s390/include/uapi/asm/unistd.h b/tools/arch/s390/include/uapi/asm/unistd.h deleted file mode 100644 index 725120939051..000000000000 --- a/tools/arch/s390/include/uapi/asm/unistd.h +++ /dev/null @@ -1,412 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * S390 version - * - * Derived from "include/asm-i386/unistd.h" - */ - -#ifndef _UAPI_ASM_S390_UNISTD_H_ -#define _UAPI_ASM_S390_UNISTD_H_ - -/* - * This file contains the system call numbers. - */ - -#define __NR_exit 1 -#define __NR_fork 2 -#define __NR_read 3 -#define __NR_write 4 -#define __NR_open 5 -#define __NR_close 6 -#define __NR_restart_syscall 7 -#define __NR_creat 8 -#define __NR_link 9 -#define __NR_unlink 10 -#define __NR_execve 11 -#define __NR_chdir 12 -#define __NR_mknod 14 -#define __NR_chmod 15 -#define __NR_lseek 19 -#define __NR_getpid 20 -#define __NR_mount 21 -#define __NR_umount 22 -#define __NR_ptrace 26 -#define __NR_alarm 27 -#define __NR_pause 29 -#define __NR_utime 30 -#define __NR_access 33 -#define __NR_nice 34 -#define __NR_sync 36 -#define __NR_kill 37 -#define __NR_rename 38 -#define __NR_mkdir 39 -#define __NR_rmdir 40 -#define __NR_dup 41 -#define __NR_pipe 42 -#define __NR_times 43 -#define __NR_brk 45 -#define __NR_signal 48 -#define __NR_acct 51 -#define __NR_umount2 52 -#define __NR_ioctl 54 -#define __NR_fcntl 55 -#define __NR_setpgid 57 -#define __NR_umask 60 -#define __NR_chroot 61 -#define __NR_ustat 62 -#define __NR_dup2 63 -#define __NR_getppid 64 -#define __NR_getpgrp 65 -#define __NR_setsid 66 -#define __NR_sigaction 67 -#define __NR_sigsuspend 72 -#define __NR_sigpending 73 -#define __NR_sethostname 74 -#define __NR_setrlimit 75 -#define __NR_getrusage 77 -#define __NR_gettimeofday 78 -#define __NR_settimeofday 79 -#define __NR_symlink 83 -#define __NR_readlink 85 -#define __NR_uselib 86 -#define __NR_swapon 87 -#define __NR_reboot 88 -#define __NR_readdir 89 -#define __NR_mmap 90 -#define __NR_munmap 91 -#define __NR_truncate 92 -#define __NR_ftruncate 93 -#define __NR_fchmod 94 -#define __NR_getpriority 96 -#define __NR_setpriority 97 -#define __NR_statfs 99 -#define __NR_fstatfs 100 -#define __NR_socketcall 102 -#define __NR_syslog 103 -#define __NR_setitimer 104 -#define __NR_getitimer 105 -#define __NR_stat 106 -#define __NR_lstat 107 -#define __NR_fstat 108 -#define __NR_lookup_dcookie 110 -#define __NR_vhangup 111 -#define __NR_idle 112 -#define __NR_wait4 114 -#define __NR_swapoff 115 -#define __NR_sysinfo 116 -#define __NR_ipc 117 -#define __NR_fsync 118 -#define __NR_sigreturn 119 -#define __NR_clone 120 -#define __NR_setdomainname 121 -#define __NR_uname 122 -#define __NR_adjtimex 124 -#define __NR_mprotect 125 -#define __NR_sigprocmask 126 -#define __NR_create_module 127 -#define __NR_init_module 128 -#define __NR_delete_module 129 -#define __NR_get_kernel_syms 130 -#define __NR_quotactl 131 -#define __NR_getpgid 132 -#define __NR_fchdir 133 -#define __NR_bdflush 134 -#define __NR_sysfs 135 -#define __NR_personality 136 -#define __NR_afs_syscall 137 /* Syscall for Andrew File System */ -#define __NR_getdents 141 -#define __NR_flock 143 -#define __NR_msync 144 -#define __NR_readv 145 -#define __NR_writev 146 -#define __NR_getsid 147 -#define __NR_fdatasync 148 -#define __NR__sysctl 149 -#define __NR_mlock 150 -#define __NR_munlock 151 -#define __NR_mlockall 152 -#define __NR_munlockall 153 -#define __NR_sched_setparam 154 -#define __NR_sched_getparam 155 -#define __NR_sched_setscheduler 156 -#define __NR_sched_getscheduler 157 -#define __NR_sched_yield 158 -#define __NR_sched_get_priority_max 159 -#define __NR_sched_get_priority_min 160 -#define __NR_sched_rr_get_interval 161 -#define __NR_nanosleep 162 -#define __NR_mremap 163 -#define __NR_query_module 167 -#define __NR_poll 168 -#define __NR_nfsservctl 169 -#define __NR_prctl 172 -#define __NR_rt_sigreturn 173 -#define __NR_rt_sigaction 174 -#define __NR_rt_sigprocmask 175 -#define __NR_rt_sigpending 176 -#define __NR_rt_sigtimedwait 177 -#define __NR_rt_sigqueueinfo 178 -#define __NR_rt_sigsuspend 179 -#define __NR_pread64 180 -#define __NR_pwrite64 181 -#define __NR_getcwd 183 -#define __NR_capget 184 -#define __NR_capset 185 -#define __NR_sigaltstack 186 -#define __NR_sendfile 187 -#define __NR_getpmsg 188 -#define __NR_putpmsg 189 -#define __NR_vfork 190 -#define __NR_pivot_root 217 -#define __NR_mincore 218 -#define __NR_madvise 219 -#define __NR_getdents64 220 -#define __NR_readahead 222 -#define __NR_setxattr 224 -#define __NR_lsetxattr 225 -#define __NR_fsetxattr 226 -#define __NR_getxattr 227 -#define __NR_lgetxattr 228 -#define __NR_fgetxattr 229 -#define __NR_listxattr 230 -#define __NR_llistxattr 231 -#define __NR_flistxattr 232 -#define __NR_removexattr 233 -#define __NR_lremovexattr 234 -#define __NR_fremovexattr 235 -#define __NR_gettid 236 -#define __NR_tkill 237 -#define __NR_futex 238 -#define __NR_sched_setaffinity 239 -#define __NR_sched_getaffinity 240 -#define __NR_tgkill 241 -/* Number 242 is reserved for tux */ -#define __NR_io_setup 243 -#define __NR_io_destroy 244 -#define __NR_io_getevents 245 -#define __NR_io_submit 246 -#define __NR_io_cancel 247 -#define __NR_exit_group 248 -#define __NR_epoll_create 249 -#define __NR_epoll_ctl 250 -#define __NR_epoll_wait 251 -#define __NR_set_tid_address 252 -#define __NR_fadvise64 253 -#define __NR_timer_create 254 -#define __NR_timer_settime 255 -#define __NR_timer_gettime 256 -#define __NR_timer_getoverrun 257 -#define __NR_timer_delete 258 -#define __NR_clock_settime 259 -#define __NR_clock_gettime 260 -#define __NR_clock_getres 261 -#define __NR_clock_nanosleep 262 -/* Number 263 is reserved for vserver */ -#define __NR_statfs64 265 -#define __NR_fstatfs64 266 -#define __NR_remap_file_pages 267 -#define __NR_mbind 268 -#define __NR_get_mempolicy 269 -#define __NR_set_mempolicy 270 -#define __NR_mq_open 271 -#define __NR_mq_unlink 272 -#define __NR_mq_timedsend 273 -#define __NR_mq_timedreceive 274 -#define __NR_mq_notify 275 -#define __NR_mq_getsetattr 276 -#define __NR_kexec_load 277 -#define __NR_add_key 278 -#define __NR_request_key 279 -#define __NR_keyctl 280 -#define __NR_waitid 281 -#define __NR_ioprio_set 282 -#define __NR_ioprio_get 283 -#define __NR_inotify_init 284 -#define __NR_inotify_add_watch 285 -#define __NR_inotify_rm_watch 286 -#define __NR_migrate_pages 287 -#define __NR_openat 288 -#define __NR_mkdirat 289 -#define __NR_mknodat 290 -#define __NR_fchownat 291 -#define __NR_futimesat 292 -#define __NR_unlinkat 294 -#define __NR_renameat 295 -#define __NR_linkat 296 -#define __NR_symlinkat 297 -#define __NR_readlinkat 298 -#define __NR_fchmodat 299 -#define __NR_faccessat 300 -#define __NR_pselect6 301 -#define __NR_ppoll 302 -#define __NR_unshare 303 -#define __NR_set_robust_list 304 -#define __NR_get_robust_list 305 -#define __NR_splice 306 -#define __NR_sync_file_range 307 -#define __NR_tee 308 -#define __NR_vmsplice 309 -#define __NR_move_pages 310 -#define __NR_getcpu 311 -#define __NR_epoll_pwait 312 -#define __NR_utimes 313 -#define __NR_fallocate 314 -#define __NR_utimensat 315 -#define __NR_signalfd 316 -#define __NR_timerfd 317 -#define __NR_eventfd 318 -#define __NR_timerfd_create 319 -#define __NR_timerfd_settime 320 -#define __NR_timerfd_gettime 321 -#define __NR_signalfd4 322 -#define __NR_eventfd2 323 -#define __NR_inotify_init1 324 -#define __NR_pipe2 325 -#define __NR_dup3 326 -#define __NR_epoll_create1 327 -#define __NR_preadv 328 -#define __NR_pwritev 329 -#define __NR_rt_tgsigqueueinfo 330 -#define __NR_perf_event_open 331 -#define __NR_fanotify_init 332 -#define __NR_fanotify_mark 333 -#define __NR_prlimit64 334 -#define __NR_name_to_handle_at 335 -#define __NR_open_by_handle_at 336 -#define __NR_clock_adjtime 337 -#define __NR_syncfs 338 -#define __NR_setns 339 -#define __NR_process_vm_readv 340 -#define __NR_process_vm_writev 341 -#define __NR_s390_runtime_instr 342 -#define __NR_kcmp 343 -#define __NR_finit_module 344 -#define __NR_sched_setattr 345 -#define __NR_sched_getattr 346 -#define __NR_renameat2 347 -#define __NR_seccomp 348 -#define __NR_getrandom 349 -#define __NR_memfd_create 350 -#define __NR_bpf 351 -#define __NR_s390_pci_mmio_write 352 -#define __NR_s390_pci_mmio_read 353 -#define __NR_execveat 354 -#define __NR_userfaultfd 355 -#define __NR_membarrier 356 -#define __NR_recvmmsg 357 -#define __NR_sendmmsg 358 -#define __NR_socket 359 -#define __NR_socketpair 360 -#define __NR_bind 361 -#define __NR_connect 362 -#define __NR_listen 363 -#define __NR_accept4 364 -#define __NR_getsockopt 365 -#define __NR_setsockopt 366 -#define __NR_getsockname 367 -#define __NR_getpeername 368 -#define __NR_sendto 369 -#define __NR_sendmsg 370 -#define __NR_recvfrom 371 -#define __NR_recvmsg 372 -#define __NR_shutdown 373 -#define __NR_mlock2 374 -#define __NR_copy_file_range 375 -#define __NR_preadv2 376 -#define __NR_pwritev2 377 -#define __NR_s390_guarded_storage 378 -#define __NR_statx 379 -#define __NR_s390_sthyi 380 -#define NR_syscalls 381 - -/* - * There are some system calls that are not present on 64 bit, some - * have a different name although they do the same (e.g. __NR_chown32 - * is __NR_chown on 64 bit). - */ -#ifndef __s390x__ - -#define __NR_time 13 -#define __NR_lchown 16 -#define __NR_setuid 23 -#define __NR_getuid 24 -#define __NR_stime 25 -#define __NR_setgid 46 -#define __NR_getgid 47 -#define __NR_geteuid 49 -#define __NR_getegid 50 -#define __NR_setreuid 70 -#define __NR_setregid 71 -#define __NR_getrlimit 76 -#define __NR_getgroups 80 -#define __NR_setgroups 81 -#define __NR_fchown 95 -#define __NR_ioperm 101 -#define __NR_setfsuid 138 -#define __NR_setfsgid 139 -#define __NR__llseek 140 -#define __NR__newselect 142 -#define __NR_setresuid 164 -#define __NR_getresuid 165 -#define __NR_setresgid 170 -#define __NR_getresgid 171 -#define __NR_chown 182 -#define __NR_ugetrlimit 191 /* SuS compliant getrlimit */ -#define __NR_mmap2 192 -#define __NR_truncate64 193 -#define __NR_ftruncate64 194 -#define __NR_stat64 195 -#define __NR_lstat64 196 -#define __NR_fstat64 197 -#define __NR_lchown32 198 -#define __NR_getuid32 199 -#define __NR_getgid32 200 -#define __NR_geteuid32 201 -#define __NR_getegid32 202 -#define __NR_setreuid32 203 -#define __NR_setregid32 204 -#define __NR_getgroups32 205 -#define __NR_setgroups32 206 -#define __NR_fchown32 207 -#define __NR_setresuid32 208 -#define __NR_getresuid32 209 -#define __NR_setresgid32 210 -#define __NR_getresgid32 211 -#define __NR_chown32 212 -#define __NR_setuid32 213 -#define __NR_setgid32 214 -#define __NR_setfsuid32 215 -#define __NR_setfsgid32 216 -#define __NR_fcntl64 221 -#define __NR_sendfile64 223 -#define __NR_fadvise64_64 264 -#define __NR_fstatat64 293 - -#else - -#define __NR_select 142 -#define __NR_getrlimit 191 /* SuS compliant getrlimit */ -#define __NR_lchown 198 -#define __NR_getuid 199 -#define __NR_getgid 200 -#define __NR_geteuid 201 -#define __NR_getegid 202 -#define __NR_setreuid 203 -#define __NR_setregid 204 -#define __NR_getgroups 205 -#define __NR_setgroups 206 -#define __NR_fchown 207 -#define __NR_setresuid 208 -#define __NR_getresuid 209 -#define __NR_setresgid 210 -#define __NR_getresgid 211 -#define __NR_chown 212 -#define __NR_setuid 213 -#define __NR_setgid 214 -#define __NR_setfsuid 215 -#define __NR_setfsgid 216 -#define __NR_newfstatat 293 - -#endif - -#endif /* _UAPI_ASM_S390_UNISTD_H_ */ diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 51abdb0a4047..790ec25919a0 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -33,7 +33,6 @@ arch/s390/include/uapi/asm/kvm.h arch/s390/include/uapi/asm/kvm_perf.h arch/s390/include/uapi/asm/ptrace.h arch/s390/include/uapi/asm/sie.h -arch/s390/include/uapi/asm/unistd.h arch/arm/include/uapi/asm/kvm.h arch/arm64/include/uapi/asm/kvm.h arch/alpha/include/uapi/asm/errno.h From 12310e3437554328bcd75186cf331bc712cb30b2 Mon Sep 17 00:00:00 2001 From: Jessica Yu Date: Wed, 10 Jan 2018 00:51:23 +0100 Subject: [PATCH 26/27] kprobes: Propagate error from arm_kprobe_ftrace() Improve error handling when arming ftrace-based kprobes. Specifically, if we fail to arm a ftrace-based kprobe, register_kprobe()/enable_kprobe() should report an error instead of success. Previously, this has lead to confusing situations where register_kprobe() would return 0 indicating success, but the kprobe would not be functional if ftrace registration during the kprobe arming process had failed. We should therefore take any errors returned by ftrace into account and propagate this error so that we do not register/enable kprobes that cannot be armed. This can happen if, for example, register_ftrace_function() finds an IPMODIFY conflict (since kprobe_ftrace_ops has this flag set) and returns an error. Such a conflict is possible since livepatches also set the IPMODIFY flag for their ftrace_ops. arm_all_kprobes() keeps its current behavior and attempts to arm all kprobes. It returns the last encountered error and gives a warning if not all probes could be armed. This patch is based on Petr Mladek's original patchset (patches 2 and 3) back in 2015, which improved kprobes error handling, found here: https://lkml.org/lkml/2015/2/26/452 However, further work on this had been paused since then and the patches were not upstreamed. Based-on-patches-by: Petr Mladek Signed-off-by: Jessica Yu Acked-by: Masami Hiramatsu Cc: Ananth N Mavinakayanahalli Cc: Anil S Keshavamurthy Cc: David S . Miller Cc: Jiri Kosina Cc: Joe Lawrence Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Miroslav Benes Cc: Peter Zijlstra Cc: Petr Mladek Cc: Steven Rostedt Cc: Thomas Gleixner Cc: live-patching@vger.kernel.org Link: http://lkml.kernel.org/r/20180109235124.30886-2-jeyu@kernel.org Signed-off-by: Ingo Molnar --- kernel/kprobes.c | 102 +++++++++++++++++++++++++++++++++++------------ 1 file changed, 76 insertions(+), 26 deletions(-) diff --git a/kernel/kprobes.c b/kernel/kprobes.c index da2ccf142358..2d988141ab85 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -978,18 +978,36 @@ static int prepare_kprobe(struct kprobe *p) } /* Caller must lock kprobe_mutex */ -static void arm_kprobe_ftrace(struct kprobe *p) +static int arm_kprobe_ftrace(struct kprobe *p) { - int ret; + int ret = 0; ret = ftrace_set_filter_ip(&kprobe_ftrace_ops, (unsigned long)p->addr, 0, 0); - WARN(ret < 0, "Failed to arm kprobe-ftrace at %p (%d)\n", p->addr, ret); - kprobe_ftrace_enabled++; - if (kprobe_ftrace_enabled == 1) { - ret = register_ftrace_function(&kprobe_ftrace_ops); - WARN(ret < 0, "Failed to init kprobe-ftrace (%d)\n", ret); + if (ret) { + pr_debug("Failed to arm kprobe-ftrace at %p (%d)\n", p->addr, ret); + return ret; } + + if (kprobe_ftrace_enabled == 0) { + ret = register_ftrace_function(&kprobe_ftrace_ops); + if (ret) { + pr_debug("Failed to init kprobe-ftrace (%d)\n", ret); + goto err_ftrace; + } + } + + kprobe_ftrace_enabled++; + return ret; + +err_ftrace: + /* + * Note: Since kprobe_ftrace_ops has IPMODIFY set, and ftrace requires a + * non-empty filter_hash for IPMODIFY ops, we're safe from an accidental + * empty filter_hash which would undesirably trace all functions. + */ + ftrace_set_filter_ip(&kprobe_ftrace_ops, (unsigned long)p->addr, 1, 0); + return ret; } /* Caller must lock kprobe_mutex */ @@ -1008,22 +1026,23 @@ static void disarm_kprobe_ftrace(struct kprobe *p) } #else /* !CONFIG_KPROBES_ON_FTRACE */ #define prepare_kprobe(p) arch_prepare_kprobe(p) -#define arm_kprobe_ftrace(p) do {} while (0) +#define arm_kprobe_ftrace(p) (-ENODEV) #define disarm_kprobe_ftrace(p) do {} while (0) #endif /* Arm a kprobe with text_mutex */ -static void arm_kprobe(struct kprobe *kp) +static int arm_kprobe(struct kprobe *kp) { - if (unlikely(kprobe_ftrace(kp))) { - arm_kprobe_ftrace(kp); - return; - } + if (unlikely(kprobe_ftrace(kp))) + return arm_kprobe_ftrace(kp); + cpus_read_lock(); mutex_lock(&text_mutex); __arm_kprobe(kp); mutex_unlock(&text_mutex); cpus_read_unlock(); + + return 0; } /* Disarm a kprobe with text_mutex */ @@ -1362,9 +1381,15 @@ static int register_aggr_kprobe(struct kprobe *orig_p, struct kprobe *p) if (ret == 0 && kprobe_disabled(ap) && !kprobe_disabled(p)) { ap->flags &= ~KPROBE_FLAG_DISABLED; - if (!kprobes_all_disarmed) + if (!kprobes_all_disarmed) { /* Arm the breakpoint again. */ - arm_kprobe(ap); + ret = arm_kprobe(ap); + if (ret) { + ap->flags |= KPROBE_FLAG_DISABLED; + list_del_rcu(&p->list); + synchronize_sched(); + } + } } return ret; } @@ -1573,8 +1598,14 @@ int register_kprobe(struct kprobe *p) hlist_add_head_rcu(&p->hlist, &kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]); - if (!kprobes_all_disarmed && !kprobe_disabled(p)) - arm_kprobe(p); + if (!kprobes_all_disarmed && !kprobe_disabled(p)) { + ret = arm_kprobe(p); + if (ret) { + hlist_del_rcu(&p->hlist); + synchronize_sched(); + goto out; + } + } /* Try to optimize kprobe */ try_to_optimize_kprobe(p); @@ -2116,7 +2147,9 @@ int enable_kprobe(struct kprobe *kp) if (!kprobes_all_disarmed && kprobe_disabled(p)) { p->flags &= ~KPROBE_FLAG_DISABLED; - arm_kprobe(p); + ret = arm_kprobe(p); + if (ret) + p->flags |= KPROBE_FLAG_DISABLED; } out: mutex_unlock(&kprobe_mutex); @@ -2407,11 +2440,12 @@ static const struct file_operations debugfs_kprobe_blacklist_ops = { .release = seq_release, }; -static void arm_all_kprobes(void) +static int arm_all_kprobes(void) { struct hlist_head *head; struct kprobe *p; - unsigned int i; + unsigned int i, total = 0, errors = 0; + int err, ret = 0; mutex_lock(&kprobe_mutex); @@ -2428,16 +2462,28 @@ static void arm_all_kprobes(void) /* Arming kprobes doesn't optimize kprobe itself */ for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; - hlist_for_each_entry_rcu(p, head, hlist) - if (!kprobe_disabled(p)) - arm_kprobe(p); + /* Arm all kprobes on a best-effort basis */ + hlist_for_each_entry_rcu(p, head, hlist) { + if (!kprobe_disabled(p)) { + err = arm_kprobe(p); + if (err) { + errors++; + ret = err; + } + total++; + } + } } - printk(KERN_INFO "Kprobes globally enabled\n"); + if (errors) + pr_warn("Kprobes globally enabled, but failed to arm %d out of %d probes\n", + errors, total); + else + pr_info("Kprobes globally enabled\n"); already_enabled: mutex_unlock(&kprobe_mutex); - return; + return ret; } static void disarm_all_kprobes(void) @@ -2494,6 +2540,7 @@ static ssize_t write_enabled_file_bool(struct file *file, { char buf[32]; size_t buf_size; + int ret = 0; buf_size = min(count, (sizeof(buf)-1)); if (copy_from_user(buf, user_buf, buf_size)) @@ -2504,7 +2551,7 @@ static ssize_t write_enabled_file_bool(struct file *file, case 'y': case 'Y': case '1': - arm_all_kprobes(); + ret = arm_all_kprobes(); break; case 'n': case 'N': @@ -2515,6 +2562,9 @@ static ssize_t write_enabled_file_bool(struct file *file, return -EINVAL; } + if (ret) + return ret; + return count; } From 297f9233b53a08fd457815e19f1d6f2c3389857b Mon Sep 17 00:00:00 2001 From: Jessica Yu Date: Wed, 10 Jan 2018 00:51:24 +0100 Subject: [PATCH 27/27] kprobes: Propagate error from disarm_kprobe_ftrace() Improve error handling when disarming ftrace-based kprobes. Like with arm_kprobe_ftrace(), propagate any errors from disarm_kprobe_ftrace() so that we do not disable/unregister kprobes that are still armed. In other words, unregister_kprobe() and disable_kprobe() should not report success if the kprobe could not be disarmed. disarm_all_kprobes() keeps its current behavior and attempts to disarm all kprobes. It returns the last encountered error and gives a warning if not all probes could be disarmed. This patch is based on Petr Mladek's original patchset (patches 2 and 3) back in 2015, which improved kprobes error handling, found here: https://lkml.org/lkml/2015/2/26/452 However, further work on this had been paused since then and the patches were not upstreamed. Based-on-patches-by: Petr Mladek Signed-off-by: Jessica Yu Acked-by: Masami Hiramatsu Cc: Ananth N Mavinakayanahalli Cc: Anil S Keshavamurthy Cc: David S . Miller Cc: Jiri Kosina Cc: Joe Lawrence Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Miroslav Benes Cc: Peter Zijlstra Cc: Petr Mladek Cc: Steven Rostedt Cc: Thomas Gleixner Cc: live-patching@vger.kernel.org Link: http://lkml.kernel.org/r/20180109235124.30886-3-jeyu@kernel.org Signed-off-by: Ingo Molnar --- kernel/kprobes.c | 80 ++++++++++++++++++++++++++++++++---------------- 1 file changed, 54 insertions(+), 26 deletions(-) diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 2d988141ab85..102160ff5c66 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1011,23 +1011,27 @@ static int arm_kprobe_ftrace(struct kprobe *p) } /* Caller must lock kprobe_mutex */ -static void disarm_kprobe_ftrace(struct kprobe *p) +static int disarm_kprobe_ftrace(struct kprobe *p) { - int ret; + int ret = 0; + + if (kprobe_ftrace_enabled == 1) { + ret = unregister_ftrace_function(&kprobe_ftrace_ops); + if (WARN(ret < 0, "Failed to unregister kprobe-ftrace (%d)\n", ret)) + return ret; + } kprobe_ftrace_enabled--; - if (kprobe_ftrace_enabled == 0) { - ret = unregister_ftrace_function(&kprobe_ftrace_ops); - WARN(ret < 0, "Failed to init kprobe-ftrace (%d)\n", ret); - } + ret = ftrace_set_filter_ip(&kprobe_ftrace_ops, (unsigned long)p->addr, 1, 0); WARN(ret < 0, "Failed to disarm kprobe-ftrace at %p (%d)\n", p->addr, ret); + return ret; } #else /* !CONFIG_KPROBES_ON_FTRACE */ #define prepare_kprobe(p) arch_prepare_kprobe(p) #define arm_kprobe_ftrace(p) (-ENODEV) -#define disarm_kprobe_ftrace(p) do {} while (0) +#define disarm_kprobe_ftrace(p) (-ENODEV) #endif /* Arm a kprobe with text_mutex */ @@ -1046,18 +1050,18 @@ static int arm_kprobe(struct kprobe *kp) } /* Disarm a kprobe with text_mutex */ -static void disarm_kprobe(struct kprobe *kp, bool reopt) +static int disarm_kprobe(struct kprobe *kp, bool reopt) { - if (unlikely(kprobe_ftrace(kp))) { - disarm_kprobe_ftrace(kp); - return; - } + if (unlikely(kprobe_ftrace(kp))) + return disarm_kprobe_ftrace(kp); cpus_read_lock(); mutex_lock(&text_mutex); __disarm_kprobe(kp, reopt); mutex_unlock(&text_mutex); cpus_read_unlock(); + + return 0; } /* @@ -1639,11 +1643,12 @@ static int aggr_kprobe_disabled(struct kprobe *ap) static struct kprobe *__disable_kprobe(struct kprobe *p) { struct kprobe *orig_p; + int ret; /* Get an original kprobe for return */ orig_p = __get_valid_kprobe(p); if (unlikely(orig_p == NULL)) - return NULL; + return ERR_PTR(-EINVAL); if (!kprobe_disabled(p)) { /* Disable probe if it is a child probe */ @@ -1657,8 +1662,13 @@ static struct kprobe *__disable_kprobe(struct kprobe *p) * should have already been disarmed, so * skip unneed disarming process. */ - if (!kprobes_all_disarmed) - disarm_kprobe(orig_p, true); + if (!kprobes_all_disarmed) { + ret = disarm_kprobe(orig_p, true); + if (ret) { + p->flags &= ~KPROBE_FLAG_DISABLED; + return ERR_PTR(ret); + } + } orig_p->flags |= KPROBE_FLAG_DISABLED; } } @@ -1675,8 +1685,8 @@ static int __unregister_kprobe_top(struct kprobe *p) /* Disable kprobe. This will disarm it if needed. */ ap = __disable_kprobe(p); - if (ap == NULL) - return -EINVAL; + if (IS_ERR(ap)) + return PTR_ERR(ap); if (ap == p) /* @@ -2109,12 +2119,14 @@ static void kill_kprobe(struct kprobe *p) int disable_kprobe(struct kprobe *kp) { int ret = 0; + struct kprobe *p; mutex_lock(&kprobe_mutex); /* Disable this kprobe */ - if (__disable_kprobe(kp) == NULL) - ret = -EINVAL; + p = __disable_kprobe(kp); + if (IS_ERR(p)) + ret = PTR_ERR(p); mutex_unlock(&kprobe_mutex); return ret; @@ -2486,34 +2498,50 @@ static int arm_all_kprobes(void) return ret; } -static void disarm_all_kprobes(void) +static int disarm_all_kprobes(void) { struct hlist_head *head; struct kprobe *p; - unsigned int i; + unsigned int i, total = 0, errors = 0; + int err, ret = 0; mutex_lock(&kprobe_mutex); /* If kprobes are already disarmed, just return */ if (kprobes_all_disarmed) { mutex_unlock(&kprobe_mutex); - return; + return 0; } kprobes_all_disarmed = true; - printk(KERN_INFO "Kprobes globally disabled\n"); for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; + /* Disarm all kprobes on a best-effort basis */ hlist_for_each_entry_rcu(p, head, hlist) { - if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p)) - disarm_kprobe(p, false); + if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p)) { + err = disarm_kprobe(p, false); + if (err) { + errors++; + ret = err; + } + total++; + } } } + + if (errors) + pr_warn("Kprobes globally disabled, but failed to disarm %d out of %d probes\n", + errors, total); + else + pr_info("Kprobes globally disabled\n"); + mutex_unlock(&kprobe_mutex); /* Wait for disarming all kprobes by optimizer */ wait_for_kprobe_optimizer(); + + return ret; } /* @@ -2556,7 +2584,7 @@ static ssize_t write_enabled_file_bool(struct file *file, case 'n': case 'N': case '0': - disarm_all_kprobes(); + ret = disarm_all_kprobes(); break; default: return -EINVAL;