From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
stable@vger.kernel.org,
"Rafael J. Wysocki" <rafael.j.wysocki@intel.com>,
WANG Chao <chao.wang@ucloud.cn>,
Linus Torvalds <torvalds@linux-foundation.org>
Subject: [PATCH 4.14 22/38] x86 / CPU: Avoid unnecessary IPIs in arch_freq_get_on_cpu()
Date: Mon, 8 Jan 2018 13:59:15 +0100 [thread overview]
Message-ID: <20180108125917.354574436@linuxfoundation.org> (raw)
In-Reply-To: <20180108125915.951963528@linuxfoundation.org>
4.14-stable review patch. If anyone has any objections, please let me know.
------------------
From: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
commit b29c6ef7bb1257853c1e31616d84f55e561cf631 upstream.
Even though aperfmperf_snapshot_khz() caches the samples.khz value to
return if called again in a sufficiently short time, its caller,
arch_freq_get_on_cpu(), still uses smp_call_function_single() to run it
which may allow user space to trigger an IPI storm by reading from the
scaling_cur_freq cpufreq sysfs file in a tight loop.
To avoid that, move the decision on whether or not to return the cached
samples.khz value to arch_freq_get_on_cpu().
This change was part of commit 941f5f0f6ef5 ("x86: CPU: Fix up "cpu MHz"
in /proc/cpuinfo"), but it was not the reason for the revert and it
remains applicable.
Fixes: 4815d3c56d1e (cpufreq: x86: Make scaling_cur_freq behave more as expected)
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: WANG Chao <chao.wang@ucloud.cn>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
arch/x86/kernel/cpu/aperfmperf.c | 11 +++++++----
1 file changed, 7 insertions(+), 4 deletions(-)
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -42,10 +42,6 @@ static void aperfmperf_snapshot_khz(void
s64 time_delta = ktime_ms_delta(now, s->time);
unsigned long flags;
- /* Don't bother re-computing within the cache threshold time. */
- if (time_delta < APERFMPERF_CACHE_THRESHOLD_MS)
- return;
-
local_irq_save(flags);
rdmsrl(MSR_IA32_APERF, aperf);
rdmsrl(MSR_IA32_MPERF, mperf);
@@ -74,6 +70,7 @@ static void aperfmperf_snapshot_khz(void
unsigned int arch_freq_get_on_cpu(int cpu)
{
+ s64 time_delta;
unsigned int khz;
if (!cpu_khz)
@@ -82,6 +79,12 @@ unsigned int arch_freq_get_on_cpu(int cp
if (!static_cpu_has(X86_FEATURE_APERFMPERF))
return 0;
+ /* Don't bother re-computing within the cache threshold time. */
+ time_delta = ktime_ms_delta(ktime_get(), per_cpu(samples.time, cpu));
+ khz = per_cpu(samples.khz, cpu);
+ if (khz && time_delta < APERFMPERF_CACHE_THRESHOLD_MS)
+ return khz;
+
smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, 1);
khz = per_cpu(samples.khz, cpu);
if (khz)
next prev parent reply other threads:[~2018-01-08 12:59 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-01-08 12:58 [PATCH 4.14 00/38] 4.14.13-stable review Greg Kroah-Hartman
2018-01-08 12:58 ` [PATCH 4.14 01/38] x86/mm: Set MODULES_END to 0xffffffffff000000 Greg Kroah-Hartman
2018-01-08 12:58 ` [PATCH 4.14 02/38] x86/mm: Map cpu_entry_area at the same place on 4/5 level Greg Kroah-Hartman
2018-01-08 12:58 ` [PATCH 4.14 03/38] x86/kaslr: Fix the vaddr_end mess Greg Kroah-Hartman
2018-01-08 12:58 ` [PATCH 4.14 04/38] x86/events/intel/ds: Use the proper cache flush method for mapping ds buffers Greg Kroah-Hartman
2018-01-08 12:58 ` [PATCH 4.14 05/38] x86/tlb: Drop the _GPL from the cpu_tlbstate export Greg Kroah-Hartman
2018-01-08 12:58 ` [PATCH 4.14 06/38] x86/alternatives: Add missing \n at end of ALTERNATIVE inline asm Greg Kroah-Hartman
2018-01-08 12:59 ` [PATCH 4.14 07/38] x86/pti: Rename BUG_CPU_INSECURE to BUG_CPU_MELTDOWN Greg Kroah-Hartman
2018-01-08 12:59 ` [PATCH 4.14 08/38] kernel/acct.c: fix the acct->needcheck check in check_free_space() Greg Kroah-Hartman
2018-01-08 12:59 ` [PATCH 4.14 09/38] mm/mprotect: add a cond_resched() inside change_pmd_range() Greg Kroah-Hartman
2018-01-08 12:59 ` [PATCH 4.14 10/38] mm/sparse.c: wrong allocation for mem_section Greg Kroah-Hartman
2018-01-08 12:59 ` [PATCH 4.14 11/38] userfaultfd: clear the vma->vm_userfaultfd_ctx if UFFD_EVENT_FORK fails Greg Kroah-Hartman
2018-01-08 12:59 ` [PATCH 4.14 12/38] btrfs: fix refcount_t usage when deleting btrfs_delayed_nodes Greg Kroah-Hartman
2018-01-08 12:59 ` [PATCH 4.14 13/38] efi/capsule-loader: Reinstate virtual capsule mapping Greg Kroah-Hartman
2018-01-08 12:59 ` [PATCH 4.14 14/38] crypto: n2 - cure use after free Greg Kroah-Hartman
2018-01-08 12:59 ` [PATCH 4.14 15/38] crypto: chacha20poly1305 - validate the digest size Greg Kroah-Hartman
2018-01-08 12:59 ` [PATCH 4.14 16/38] crypto: pcrypt - fix freeing pcrypt instances Greg Kroah-Hartman
2018-01-08 12:59 ` [PATCH 4.14 17/38] crypto: chelsio - select CRYPTO_GF128MUL Greg Kroah-Hartman
2018-01-08 12:59 ` [PATCH 4.14 21/38] fscache: Fix the default for fscache_maybe_release_page() Greg Kroah-Hartman
2018-01-08 12:59 ` Greg Kroah-Hartman [this message]
2018-01-08 12:59 ` [PATCH 4.14 23/38] x86 / CPU: Always show current CPU frequency in /proc/cpuinfo Greg Kroah-Hartman
2018-01-08 12:59 ` [PATCH 4.14 24/38] kernel/signal.c: protect the traced SIGNAL_UNKILLABLE tasks from SIGKILL Greg Kroah-Hartman
2018-01-08 12:59 ` [PATCH 4.14 25/38] kernel/signal.c: protect the SIGNAL_UNKILLABLE tasks from !sig_kernel_only() signals Greg Kroah-Hartman
2018-01-08 12:59 ` [PATCH 4.14 26/38] kernel/signal.c: remove the no longer needed SIGNAL_UNKILLABLE check in complete_signal() Greg Kroah-Hartman
2018-01-08 12:59 ` [PATCH 4.14 27/38] iommu/arm-smmu-v3: Dont free page table ops twice Greg Kroah-Hartman
2018-01-08 12:59 ` [PATCH 4.14 28/38] iommu/arm-smmu-v3: Cope with duplicated Stream IDs Greg Kroah-Hartman
2018-01-08 12:59 ` [PATCH 4.14 29/38] ARC: uaccess: dont use "l" gcc inline asm constraint modifier Greg Kroah-Hartman
2018-01-08 12:59 ` [PATCH 4.14 30/38] powerpc/mm: Fix SEGV on mapped region to return SEGV_ACCERR Greg Kroah-Hartman
2018-01-08 12:59 ` [PATCH 4.14 31/38] Input: elantech - add new icbody type 15 Greg Kroah-Hartman
2018-01-08 12:59 ` [PATCH 4.14 32/38] x86/microcode/AMD: Add support for fam17h microcode loading Greg Kroah-Hartman
2018-01-08 12:59 ` [PATCH 4.14 34/38] parisc: Fix alignment of pa_tlb_lock in assembly on 32-bit SMP kernel Greg Kroah-Hartman
2018-01-08 12:59 ` [PATCH 4.14 35/38] parisc: qemu idle sleep support Greg Kroah-Hartman
2018-01-08 12:59 ` [PATCH 4.14 37/38] KVM: s390: fix cmma migration for multiple memory slots Greg Kroah-Hartman
2018-01-08 12:59 ` [PATCH 4.14 38/38] KVM: s390: prevent buffer overrun on memory hotplug during migration Greg Kroah-Hartman
2018-01-08 20:59 ` [PATCH 4.14 00/38] 4.14.13-stable review Shuah Khan
2018-01-09 9:11 ` Greg Kroah-Hartman
2018-01-09 8:45 ` Naresh Kamboju
2018-01-09 9:27 ` Greg Kroah-Hartman
2018-01-09 13:45 ` Guenter Roeck
2018-01-09 19:07 ` Greg Kroah-Hartman
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20180108125917.354574436@linuxfoundation.org \
--to=gregkh@linuxfoundation.org \
--cc=chao.wang@ucloud.cn \
--cc=linux-kernel@vger.kernel.org \
--cc=rafael.j.wysocki@intel.com \
--cc=stable@vger.kernel.org \
--cc=torvalds@linux-foundation.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).