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 <kan.liang@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Stephane Eranian <eranian@google.com>
Cc: Will Deacon <will@kernel.org>
Link: http://lore.kernel.org/lkml/20201216185805.9981-3-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
- 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'.
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);
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,
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;
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,
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;
u64 addr;
u64 al_addr;
u64 phys_addr;
+ u64 data_page_size;
};
#endif // __PERF_MAP_SYMBOL
.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)
{
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
SORT_MEM_DCACHELINE,
SORT_MEM_IADDR_SYMBOL,
SORT_MEM_PHYS_DADDR,
+ SORT_MEM_DATA_PAGE_SIZE,
};
/*