Haswell mem-store question
Hi Andi,
Joe was playing with our c2c tool today and noticed we were losing store events from perf's mem-stores event. Upon investigation we stumbled into some differences in data that Haswell reports vs. Ivy/Sandy Bridge.
This leaves our tool needing two different paths depending on the architect, which seems odd.
I was hoping you or someone can explain to me the correct way to interpret the mem-stores data.
My current problem is mem_lvl. It can be defined as
/* memory hierarchy (memory level, hit or miss) */
#define PERF_MEM_LVL_NA 0x01 /* not available */ #define PERF_MEM_LVL_HIT 0x02 /* hit level */ #define PERF_MEM_LVL_MISS 0x04 /* miss level */ #define PERF_MEM_LVL_L1 0x08 /* L1 */ #define PERF_MEM_LVL_LFB 0x10 /* Line Fill Buffer */ #define PERF_MEM_LVL_L2 0x20 /* L2 */ #define PERF_MEM_LVL_L3 0x40 /* L3 */ #define PERF_MEM_LVL_LOC_RAM 0x80 /* Local DRAM */ #define PERF_MEM_LVL_REM_RAM1 0x100 /* Remote DRAM (1 hop) */ #define PERF_MEM_LVL_REM_RAM2 0x200 /* Remote DRAM (2 hops) */ #define PERF_MEM_LVL_REM_CCE1 0x400 /* Remote Cache (1 hop) */ #define PERF_MEM_LVL_REM_CCE2 0x800 /* Remote Cache (2 hops) */ #define PERF_MEM_LVL_IO 0x1000 /* I/O memory */ #define PERF_MEM_LVL_UNC 0x2000 /* Uncached memory */ #define PERF_MEM_LVL_SHIFT 5
Currently IVB and SNB use LVL_L1 & (LVL_HIT or LVL_MISS) seen here in arch/x86/kernel/cpu/perf_event_intel_ds.c
static u64 precise_store_data(u64 status)
{
union intel_x86_pebs_dse dse;
u64 val = P(OP, STORE) | P(SNOOP, NA) | P(LVL, L1) | P(TLB, L2);
^^^^^^^^^
defined here
dse.val = status;<snip>
/*
* bit 0: hit L1 data cache
* if not set, then all we know is that
* it missed L1D
*/
if (dse.st_l1d_hit)
val |= P(LVL, HIT);
else
val |= P(LVL, MISS);
^^^^^^^
updated here<snip>
}
However Haswell does something different:
static u64 precise_store_data_hsw(u64 status)
{
union perf_mem_data_src dse;
dse.val = 0;
dse.mem_op = PERF_MEM_OP_STORE;
dse.mem_lvl = PERF_MEM_LVL_NA;
^^^^^^
defines NA here
if (status & 1)
dse.mem_lvl = PERF_MEM_LVL_L1;
^^^^^^^
switch to LVL_L1 here<snip>
}
So our c2c tool kept store statistics to help determine what types of stores are causing conflicts
<snip>
} else if (op & P(OP,STORE)) {
/* store */
stats->t.store++;
if (!daddr) {
stats->t.st_noadrs++;
return -1;
}
if (lvl & P(LVL,HIT)) {
if (lvl & P(LVL,UNC)) stats->t.st_uncache++;
if (lvl & P(LVL,L1 )) stats->t.st_l1hit++;
} else if (lvl & P(LVL,MISS)) {
if (lvl & P(LVL,L1)) stats->t.st_l1miss++;
}
}<snip>
This no longer works on Haswell because Haswell doesn't set LVL_HIT or LVL_MISS any more. Instead it uses LVL_NA or LVL_L1.
So from a generic tool perspective, what is the recommended way to properly capture these stats to cover both arches? The hack I have now is:
} else if (op & P(OP,STORE)) {
/* store */
stats->t.store++;
if (!daddr) {
stats->t.st_noadrs++;
return -1;
}
if ((lvl & P(LVL,HIT)) || (lvl & P(LVL,L1))) {
if (lvl & P(LVL,UNC)) stats->t.st_uncache++;
if (lvl & P(LVL,L1 )) stats->t.st_l1hit++;
} else if ((lvl & P(LVL,MISS)) || (lvl & P(LVL,NA))) {
if (lvl & P(LVL,L1)) stats->t.st_l1miss++;
if (lvl & P(LVL,NA)) stats->t.st_l1miss++;
}
}I am not sure that is really future proof. Thoughts? Help?
Cheers,
Don
Quoted 64 lines · Don Zickus
Hi Andi,
Joe was playing with our c2c tool today and noticed we were losing store events from perf's mem-stores event. Upon investigation we stumbled into some differences in data that Haswell reports vs. Ivy/Sandy Bridge.
This leaves our tool needing two different paths depending on the architect, which seems odd.
I was hoping you or someone can explain to me the correct way to interpret the mem-stores data.
My current problem is
mem_lvl. It can be defined as/* memory hierarchy (memory level, hit or miss) */
#define PERF_MEM_LVL_NA 0x01 /* not available */ #define PERF_MEM_LVL_HIT 0x02 /* hit level */ #define PERF_MEM_LVL_MISS 0x04 /* miss level */ #define PERF_MEM_LVL_L1 0x08 /* L1 */ #define PERF_MEM_LVL_LFB 0x10 /* Line Fill Buffer */ #define PERF_MEM_LVL_L2 0x20 /* L2 */ #define PERF_MEM_LVL_L3 0x40 /* L3 */ #define PERF_MEM_LVL_LOC_RAM 0x80 /* Local DRAM */ #define PERF_MEM_LVL_REM_RAM1 0x100 /* Remote DRAM (1 hop) */ #define PERF_MEM_LVL_REM_RAM2 0x200 /* Remote DRAM (2 hops) */ #define PERF_MEM_LVL_REM_CCE1 0x400 /* Remote Cache (1 hop) */ #define PERF_MEM_LVL_REM_CCE2 0x800 /* Remote Cache (2 hops) */ #define PERF_MEM_LVL_IO 0x1000 /* I/O memory */ #define PERF_MEM_LVL_UNC 0x2000 /* Uncached memory */ #define PERF_MEM_LVL_SHIFT 5Currently IVB and SNB use
LVL_L1& (LVL_HITorLVL_MISS) seen here inarch/x86/kernel/cpu/perf_event_intel_ds.cstatic u64
precise_store_data(u64 status){ union intel_x86_pebs_dse dse; u64 val = P(OP, STORE) | P(SNOOP, NA) | P(LVL, L1) | P(TLB, L2); ^^^^^^^^^ defined here dse.val = status;<snip>
/* * bit 0: hit L1 data cache * if not set, then all we know is that * it missed L1D */ if (dse.st_l1d_hit) val |= P(LVL, HIT); else val |= P(LVL, MISS); ^^^^^^^ updated here<snip>
}However Haswell does something different:
static u64
precise_store_data_hsw(u64 status)
Quoted 15 lines
{
union perf_mem_data_src dse;
dse.val = 0;
dse.mem_op = PERF_MEM_OP_STORE;
dse.mem_lvl = PERF_MEM_LVL_NA;
^^^^^^
defines NA here
if (status & 1)
dse.mem_lvl = PERF_MEM_LVL_L1;
^^^^^^^
switch to LVL_L1 hereI think this code has a problem here.
I need to mark the hit or miss status.
I think it should do:
if (status & 1)
dse.mem_lvl = PERF_MEM_LVL_L1|PERF_MEM_LVL_HIT;
else
dse.mem_lvl = PERF_MEM_LVL_L1|PERF_MEM_LVL_MISS;Otherwise you have L1 as the level with no hit/miss info.
Quoted 54 lines
<snip>
}So our c2c tool kept store statistics to help determine what types of stores are causing conflicts
<snip>
} else if (op & P(OP,STORE)) { /* store */ stats->t.store++; if (!daddr) { stats->t.st_noadrs++; return -1; } if (lvl & P(LVL,HIT)) { if (lvl & P(LVL,UNC)) stats->t.st_uncache++; if (lvl & P(LVL,L1 )) stats->t.st_l1hit++; } else if (lvl & P(LVL,MISS)) { if (lvl & P(LVL,L1)) stats->t.st_l1miss++; } }<snip>
This no longer works on Haswell because Haswell doesn't set
LVL_HITorLVL_MISSany more. Instead it usesLVL_NAorLVL_L1.So from a generic tool perspective, what is the recommended way to properly capture these stats to cover both arches? The hack I have now is:
} else if (op & P(OP,STORE)) { /* store */ stats->t.store++; if (!daddr) { stats->t.st_noadrs++; return -1; } if ((lvl & P(LVL,HIT)) || (lvl & P(LVL,L1))) { if (lvl & P(LVL,UNC)) stats->t.st_uncache++; if (lvl & P(LVL,L1 )) stats->t.st_l1hit++; } else if ((lvl & P(LVL,MISS)) || (lvl & P(LVL,NA))) { if (lvl & P(LVL,L1)) stats->t.st_l1miss++; if (lvl & P(LVL,NA)) stats->t.st_l1miss++; } }I am not sure that is really future proof. Thoughts? Help?
Cheers,
Don
Quoted 8 lines
I think it should do:
if (status & 1)
dse.mem_lvl = PERF_MEM_LVL_L1|PERF_MEM_LVL_HIT; else dse.mem_lvl = PERF_MEM_LVL_L1|PERF_MEM_LVL_MISS;Otherwise you have L1 as the level with no hit/miss info.
Agreed.
BTW the line before is also not always corect, and any event not explicitely store can only fill in NA
-Andi