summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorYazen Ghannam <Yazen.Ghannam@amd.com>2016-11-08 09:35:06 +0100
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2016-11-26 09:54:51 +0100
commitaea9d760b8bae270224db112ebe81b3900861d42 (patch)
tree0fb88f5105e1acf14ddafa2b0cf7b14e442cbd76
parent4eb9a81002485a7abfa53a334dde5bc10328079f (diff)
downloademulator-kernel-aea9d760b8bae270224db112ebe81b3900861d42.tar.gz
emulator-kernel-aea9d760b8bae270224db112ebe81b3900861d42.tar.bz2
emulator-kernel-aea9d760b8bae270224db112ebe81b3900861d42.zip
x86/cpu/AMD: Fix cpu_llc_id for AMD Fam17h systems
commit b0b6e86846093c5f8820386bc01515f857dd8faa upstream. cpu_llc_id (Last Level Cache ID) derivation on AMD Fam17h has an underflow bug when extracting the socket_id value. It starts from 0 so subtracting 1 from it will result in an invalid value. This breaks scheduling topology later on since the cpu_llc_id will be incorrect. For example, the the cpu_llc_id of the *other* CPU in the loops in set_cpu_sibling_map() underflows and we're generating the funniest thread_siblings masks and then when I run 8 threads of nbench, they get spread around the LLC domains in a very strange pattern which doesn't give you the normal scheduling spread one would expect for performance. Other things like EDAC use cpu_llc_id so they will be b0rked too. So, the APIC ID is preset in APICx020 for bits 3 and above: they contain the core complex, node and socket IDs. The LLC is at the core complex level so we can find a unique cpu_llc_id by right shifting the APICID by 3 because then the least significant bit will be the Core Complex ID. Tested-by: Borislav Petkov <bp@suse.de> Signed-off-by: Yazen Ghannam <Yazen.Ghannam@amd.com> [ Cleaned up and extended the commit message. ] Signed-off-by: Borislav Petkov <bp@suse.de> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Aravind Gopalakrishnan <aravindksg.lkml@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Fixes: 3849e91f571d ("x86/AMD: Fix last level cache topology for AMD Fam17h systems") Link: http://lkml.kernel.org/r/20161108083506.rvqb5h4chrcptj7d@pd.tnic Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-rw-r--r--arch/x86/kernel/cpu/amd.c6
1 files changed, 1 insertions, 5 deletions
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 6cb5834062a3..e2defc7593a4 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -352,7 +352,6 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c)
#ifdef CONFIG_SMP
unsigned bits;
int cpu = smp_processor_id();
- unsigned int socket_id, core_complex_id;
bits = c->x86_coreid_bits;
/* Low order bits define the core id (index of core in socket) */
@@ -370,10 +369,7 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c)
if (c->x86 != 0x17 || !cpuid_edx(0x80000006))
return;
- socket_id = (c->apicid >> bits) - 1;
- core_complex_id = (c->apicid & ((1 << bits) - 1)) >> 3;
-
- per_cpu(cpu_llc_id, cpu) = (socket_id << 3) | core_complex_id;
+ per_cpu(cpu_llc_id, cpu) = c->apicid >> 3;
#endif
}