diff options
author | Marc Zyngier <maz@kernel.org> | 2023-05-28 09:02:05 +0100 |
---|---|---|
committer | Will Deacon <will@kernel.org> | 2023-06-05 15:39:59 +0100 |
commit | 8be3593b9efa8903d2ee7bb9cdf57a8e56c66f36 (patch) | |
tree | 394165bec082fa80641e466554bfb1dc85c67856 /include/vdso | |
parent | 71746c995cac92fcf6a65661b51211cf2009d7f0 (diff) |
drivers/perf: apple_m1: Force 63bit counters for M2 CPUs
Sidharth reports that on M2, the PMU never generates any interrupt
when using 'perf record', which is a annoying as you get no sample.
I'm temped to say "no sample, no problem", but others may have
a different opinion.
Upon investigation, it appears that the counters on M2 are
significantly different from the ones on M1, as they count on
64 bits instead of 48. Which of course, in the fine M1 tradition,
means that we can only use 63 bits, as the top bit is used to signal
the interrupt...
This results in having to introduce yet another flag to indicate yet
another odd counter width. Who knows what the next crazy implementation
will do...
With this, perf can work out the correct offset, and 'perf record'
works as intended.
Tested on M2 and M2-Pro CPUs.
Cc: Janne Grunau <j@jannau.net>
Cc: Hector Martin <marcan@marcan.st>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Will Deacon <will@kernel.org>
Fixes: 7d0bfb7c9977 ("drivers/perf: apple_m1: Add Apple M2 support")
Reported-by: Sidharth Kshatriya <sid.kshatriya@gmail.com>
Tested-by: Sidharth Kshatriya <sid.kshatriya@gmail.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230528080205.288446-1-maz@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
Diffstat (limited to 'include/vdso')
0 files changed, 0 insertions, 0 deletions