summaryrefslogtreecommitdiffstats
path: root/arch/xtensa
diff options
context:
space:
mode:
authorNathan Lynch <nathanl@linux.ibm.com>2022-09-26 17:02:50 -0500
committerMichael Ellerman <mpe@ellerman.id.au>2022-09-28 19:22:14 +1000
commitb37ac1894ac3c014863986d6b8ed880195213e78 (patch)
treedb0bd72ac7a3c544908558a0bbfbb13c65c34d47 /arch/xtensa
parentb8f3e48834fe8c86b4f21739c6effd160e2c2c19 (diff)
downloadlinux-b37ac1894ac3c014863986d6b8ed880195213e78.tar.bz2
powerpc/smp: poll cpu_callin_map more aggressively in __cpu_up()
At boot time, it is not necessary to delay between polls of cpu_callin_map when waiting for a kicked CPU to come up. Remove the delay intervals, but preserve the overall deadline (five seconds). At run time, the first poll result is usually negative and we incur a sleeping wait. If we spin on the callin word for a short time first, we can reduce __cpu_up() from dozens of milliseconds to under 1ms in the common case on a P9 LPAR: $ ppc64_cpu --smt=off $ bpftrace -e 'kprobe:__cpu_up { @start[tid] = nsecs; } kretprobe:__cpu_up /@start[tid]/ { @us = hist((nsecs - @start[tid]) / 1000); delete(@start[tid]); }' -c 'ppc64_cpu --smt=on' Before: @us: [16K, 32K) 85 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@| [32K, 64K) 13 |@@@@@@@ | After: @us: [128, 256) 95 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@| [256, 512) 3 |@ | Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20220926220250.157022-1-nathanl@linux.ibm.com
Diffstat (limited to 'arch/xtensa')
0 files changed, 0 insertions, 0 deletions