diff options
| author | Robin Murphy <robin.murphy@arm.com> | 2023-10-20 18:51:27 +0100 |
|---|---|---|
| committer | Will Deacon <will@kernel.org> | 2023-10-23 13:45:42 +0100 |
| commit | ab33c66fd8f124f7c4a35c96fcfbcd262764b0f6 (patch) | |
| tree | 4eba7a98f124c15a0164210d4b5ff554d41a18c7 /drivers/perf | |
| parent | 7633ec2c262fab3e7c5bf3cd3876b5748f584a57 (diff) | |
perf/arm-cmn: Enable per-DTC counter allocation
Finally enable independent per-DTC-domain counter allocation, except on
CMN-600 where we still need to cope with not knowing the domain topology
and thus keep counter indices sychronised across domains. This allows
users to simultaneously count up to 8 targeted events per domain, rather
than 8 globally, for up to 4x wider coverage on maximum configurations.
Even though this now looks deceptively simple, I stand by my previous
assertion that it was a flippin' nightmare to implement; all the real
head-scratchers are hidden in the foundations in the previous patch...
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/849f65566582cb102c6d0843d0f26e231180f8ac.1697824215.git.robin.murphy@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
Diffstat (limited to 'drivers/perf')
| -rw-r--r-- | drivers/perf/arm-cmn.c | 18 |
1 files changed, 10 insertions, 8 deletions
diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c index 675f1638013e..9479e919c063 100644 --- a/drivers/perf/arm-cmn.c +++ b/drivers/perf/arm-cmn.c @@ -1570,7 +1570,7 @@ struct arm_cmn_val { u8 dtm_count[CMN_MAX_DTMS]; u8 occupid[CMN_MAX_DTMS][SEL_MAX]; u8 wp[CMN_MAX_DTMS][4]; - int dtc_count; + int dtc_count[CMN_MAX_DTCS]; bool cycles; }; @@ -1591,7 +1591,8 @@ static void arm_cmn_val_add_event(struct arm_cmn *cmn, struct arm_cmn_val *val, return; } - val->dtc_count++; + for_each_hw_dtc_idx(hw, dtc, idx) + val->dtc_count[dtc]++; for_each_hw_dn(hw, dn, i) { int wp_idx, dtm = dn->dtm, sel = hw->filter_sel; @@ -1638,8 +1639,9 @@ static int arm_cmn_validate_group(struct arm_cmn *cmn, struct perf_event *event) goto done; } - if (val->dtc_count == CMN_DT_NUM_COUNTERS) - goto done; + for (i = 0; i < CMN_MAX_DTCS; i++) + if (val->dtc_count[i] == CMN_DT_NUM_COUNTERS) + goto done; for_each_hw_dn(hw, dn, i) { int wp_idx, wp_cmb, dtm = dn->dtm, sel = hw->filter_sel; @@ -1806,9 +1808,9 @@ static int arm_cmn_event_add(struct perf_event *event, int flags) return 0; } - /* Grab a free global counter first... */ + /* Grab the global counters first... */ for_each_hw_dtc_idx(hw, j, idx) { - if (j > 0) { + if (cmn->part == PART_CMN600 && j > 0) { idx = hw->dtc_idx[0]; } else { idx = 0; @@ -1819,10 +1821,10 @@ static int arm_cmn_event_add(struct perf_event *event, int flags) hw->dtc_idx[j] = idx; } - /* ...then the local counters to feed it. */ + /* ...then the local counters to feed them */ for_each_hw_dn(hw, dn, i) { struct arm_cmn_dtm *dtm = &cmn->dtms[dn->dtm] + hw->dtm_offset; - unsigned int dtm_idx, shift, d = 0; + unsigned int dtm_idx, shift, d = max_t(int, dn->dtc, 0); u64 reg; dtm_idx = 0; |