diff options
author | Ashwin Chaugule <ashwin.chaugule@linaro.org> | 2014-05-07 10:18:36 -0400 |
---|---|---|
committer | Ashwin Chaugule <ashwin.chaugule@linaro.org> | 2014-05-15 10:16:30 -0400 |
commit | c814ca029e1015bb0ecec312f4bb9751ba1a711a (patch) | |
tree | 75ff2a914c476700b4a2272c523416d7d4cb3328 /arch/arm64/kernel/smp.c | |
parent | e1cd3b361a4f1dd323252543f40d43509d80affa (diff) | |
download | linux-c814ca029e1015bb0ecec312f4bb9751ba1a711a.tar.bz2 |
ARM: Check if a CPU has gone offline
PSCIv0.2 adds a new function called AFFINITY_INFO, which
can be used to query if a specified CPU has actually gone
offline. Calling this function via cpu_kill ensures that
a CPU has quiesced after a call to cpu_die. This helps
prevent the CPU from doing arbitrary bad things when data
or instructions are clobbered (as happens with kexec)
in the window between a CPU announcing that it is dead
and said CPU leaving the kernel.
Signed-off-by: Ashwin Chaugule <ashwin.chaugule@linaro.org>
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Diffstat (limited to 'arch/arm64/kernel/smp.c')
-rw-r--r-- | arch/arm64/kernel/smp.c | 22 |
1 files changed, 22 insertions, 0 deletions
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index f0a141dd5655..c3cb160edc69 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -228,6 +228,19 @@ int __cpu_disable(void) return 0; } +static int op_cpu_kill(unsigned int cpu) +{ + /* + * If we have no means of synchronising with the dying CPU, then assume + * that it is really dead. We can only wait for an arbitrary length of + * time and hope that it's dead, so let's skip the wait and just hope. + */ + if (!cpu_ops[cpu]->cpu_kill) + return 1; + + return cpu_ops[cpu]->cpu_kill(cpu); +} + static DECLARE_COMPLETION(cpu_died); /* @@ -241,6 +254,15 @@ void __cpu_die(unsigned int cpu) return; } pr_notice("CPU%u: shutdown\n", cpu); + + /* + * Now that the dying CPU is beyond the point of no return w.r.t. + * in-kernel synchronisation, try to get the firwmare to help us to + * verify that it has really left the kernel before we consider + * clobbering anything it might still be using. + */ + if (!op_cpu_kill(cpu)) + pr_warn("CPU%d may not have shut down cleanly\n", cpu); } /* |