From a50d03e3b8b68df13e47dcbde6c5d39b4237c479 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Wed, 16 Dec 2020 10:57:58 -0800 Subject: [PATCH] perf sort: Add sort option for data page size Add a new sort option "data_page_size" for --mem-mode sort. With this option applied, perf can sort and report by sample's data page size. Here is an example: perf report --stdio --mem-mode --sort=comm,symbol,phys_daddr,data_page_size # To display the perf.data header info, please use # --header/--header-only options. # # # Total Lost Samples: 0 # # Samples: 9K of event 'mem-loads:uP' # Total weight : 9028 # Sort order : comm,symbol,phys_daddr,data_page_size # # Overhead Command Symbol Data Physical # Address # Data Page Size # ........ ....... ............................ # ...................... ...................... # 11.19% dtlb [.] touch_buffer [.] 0x00000003fec82ea8 4K 8.61% dtlb [.] GetTickCount [.] 0x00000003c4f2c8a8 4K 4.52% dtlb [.] GetTickCount [.] 0x00000003fec82f58 4K 4.33% dtlb [.] __gettimeofday [.] 0x00000003fec82f48 4K 4.32% dtlb [.] GetTickCount [.] 0x00000003fec82f78 4K 4.28% dtlb [.] GetTickCount [.] 0x00000003fec82f50 4K 4.23% dtlb [.] GetTickCount [.] 0x00000003fec82f70 4K 4.11% dtlb [.] GetTickCount [.] 0x00000003fec82f68 4K 4.00% dtlb [.] Calibrate [.] 0x00000003fec82f98 4K 3.91% dtlb [.] Calibrate [.] 0x00000003fec82f90 4K 3.43% dtlb [.] touch_buffer [.] 0x00000003fec82e98 4K 3.42% dtlb [.] touch_buffer [.] 0x00000003fec82e90 4K 0.09% dtlb [.] DoDependentLoads [.] 0x000000036ea084c0 2M 0.08% dtlb [.] DoDependentLoads [.] 0x000000032b010b80 2M Signed-off-by: Kan Liang Acked-by: Jiri Olsa Acked-by: Namhyung Kim Cc: Andi Kleen Cc: Mark Rutland Cc: Michael Ellerman Cc: Stephane Eranian Cc: Will Deacon Link: http://lore.kernel.org/lkml/20201216185805.9981-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-report.txt | 1 + tools/perf/util/hist.c | 3 +++ tools/perf/util/hist.h | 1 + tools/perf/util/machine.c | 7 ++++-- tools/perf/util/map_symbol.h | 1 + tools/perf/util/sort.c | 30 ++++++++++++++++++++++++ tools/perf/util/sort.h | 1 + 7 files changed, 42 insertions(+), 2 deletions(-) diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index d068103690ccc..8f7f4e9605d89 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -150,6 +150,7 @@ OPTIONS - snoop: type of snoop (if any) for the data at the time of the sample - dcacheline: the cacheline the data address is on at the time of the sample - phys_daddr: physical address of data being executed on at the time of sample + - data_page_size: the data page size of data being executed on at the time of sample And the default sort keys are changed to local_weight, mem, sym, dso, symbol_daddr, dso_daddr, snoop, tlb, locked, see '--mem-mode'. diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 7feeaa07c7776..a08fb9ea411bd 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -188,6 +188,9 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__new_col_len(hists, HISTC_MEM_PHYS_DADDR, unresolved_col_width + 4 + 2); + hists__new_col_len(hists, HISTC_MEM_DATA_PAGE_SIZE, + unresolved_col_width + 4 + 2); + } else { symlen = unresolved_col_width + 4 + 2; hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, symlen); diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index df6c6eea09605..14f66330923d6 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -56,6 +56,7 @@ enum hist_column { HISTC_MEM_DADDR_SYMBOL, HISTC_MEM_DADDR_DSO, HISTC_MEM_PHYS_DADDR, + HISTC_MEM_DATA_PAGE_SIZE, HISTC_MEM_LOCKED, HISTC_MEM_TLB, HISTC_MEM_LVL, diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 1ae32a81639c6..f841f3503cae6 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -2023,11 +2023,12 @@ static void ip__resolve_ams(struct thread *thread, ams->ms.sym = al.sym; ams->ms.map = al.map; ams->phys_addr = 0; + ams->data_page_size = 0; } static void ip__resolve_data(struct thread *thread, u8 m, struct addr_map_symbol *ams, - u64 addr, u64 phys_addr) + u64 addr, u64 phys_addr, u64 daddr_page_size) { struct addr_location al; @@ -2041,6 +2042,7 @@ static void ip__resolve_data(struct thread *thread, ams->ms.sym = al.sym; ams->ms.map = al.map; ams->phys_addr = phys_addr; + ams->data_page_size = daddr_page_size; } struct mem_info *sample__resolve_mem(struct perf_sample *sample, @@ -2053,7 +2055,8 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample, ip__resolve_ams(al->thread, &mi->iaddr, sample->ip); ip__resolve_data(al->thread, al->cpumode, &mi->daddr, - sample->addr, sample->phys_addr); + sample->addr, sample->phys_addr, + sample->data_page_size); mi->data_src.val = sample->data_src; return mi; diff --git a/tools/perf/util/map_symbol.h b/tools/perf/util/map_symbol.h index 5b8ca93798e9a..7d22ade082c8f 100644 --- a/tools/perf/util/map_symbol.h +++ b/tools/perf/util/map_symbol.h @@ -19,5 +19,6 @@ struct addr_map_symbol { u64 addr; u64 al_addr; u64 phys_addr; + u64 data_page_size; }; #endif // __PERF_MAP_SYMBOL diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 7d87bfcffb3f6..80907bc32683a 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1462,6 +1462,35 @@ struct sort_entry sort_mem_phys_daddr = { .se_width_idx = HISTC_MEM_PHYS_DADDR, }; +static int64_t +sort__data_page_size_cmp(struct hist_entry *left, struct hist_entry *right) +{ + uint64_t l = 0, r = 0; + + if (left->mem_info) + l = left->mem_info->daddr.data_page_size; + if (right->mem_info) + r = right->mem_info->daddr.data_page_size; + + return (int64_t)(r - l); +} + +static int hist_entry__data_page_size_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + char str[PAGE_SIZE_NAME_LEN]; + + return repsep_snprintf(bf, size, "%-*s", width, + get_page_size_name(he->mem_info->daddr.data_page_size, str)); +} + +struct sort_entry sort_mem_data_page_size = { + .se_header = "Data Page Size", + .se_cmp = sort__data_page_size_cmp, + .se_snprintf = hist_entry__data_page_size_snprintf, + .se_width_idx = HISTC_MEM_DATA_PAGE_SIZE, +}; + static int64_t sort__abort_cmp(struct hist_entry *left, struct hist_entry *right) { @@ -1740,6 +1769,7 @@ static struct sort_dimension memory_sort_dimensions[] = { DIM(SORT_MEM_SNOOP, "snoop", sort_mem_snoop), DIM(SORT_MEM_DCACHELINE, "dcacheline", sort_mem_dcacheline), DIM(SORT_MEM_PHYS_DADDR, "phys_daddr", sort_mem_phys_daddr), + DIM(SORT_MEM_DATA_PAGE_SIZE, "data_page_size", sort_mem_data_page_size), }; #undef DIM diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 66d39c4cfe2b3..e50f2b695bc43 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -255,6 +255,7 @@ enum sort_type { SORT_MEM_DCACHELINE, SORT_MEM_IADDR_SYMBOL, SORT_MEM_PHYS_DADDR, + SORT_MEM_DATA_PAGE_SIZE, }; /* -- 2.39.5