niansa-misc/linux
1
0
Fork 0
mirror of synced 2025-03-06 20:59:54 +01:00
Code Issues Projects Releases Packages Wiki Activity

x86/mce: Do not enter deferred errors into the generic pool twice

Browse source 
We used to have a special ring buffer for deferred errors that
was used to mark problem pages. We replaced that with a generic
pool. Then later converted mce_log() to also use the same pool.
As a result, we end up adding all deferred errors to the pool
twice.

Rearrange this code. Make sure to set the m.severity and
m.usable_addr fields for deferred errors. Then if flags and
mca_cfg.dont_log_ce mean we call mce_log() we are done, because
that will add this entry to the generic pool.

If we skipped mce_log(), then we still want to take action for
the deferred error, so add to the pool.

Change the name of the boolean "error_logged" to "error_seen",
we should set it whether of not we logged an error because the
return value from machine_check_poll() is used to decide whether
storms have subsided or not.

Reported-by: Gong Chen <gong.chen@linux.intel.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-edac <linux-edac@vger.kernel.org>
Link: http://lkml.kernel.org/r/1448350880-5573-2-git-send-email-bp@alien8.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
Tony Luck 2015-11-24 08:41:17 +01:00 • committed by Ingo Molnar
parent 1ec218373b
commit 8b38937b7a
1 changed files with 13 additions and 11 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

24
arch/x86/kernel/cpu/mcheck/mce.c
View file

@ -567,7 +567,7 @@ DEFINE_PER_CPU(unsigned, mce_poll_count);
*/ */
bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
{ {
bool error_logged = false; bool error_seen = false;
struct mce m; struct mce m;
int severity; int severity;
int i; int i;
@ -601,6 +601,8 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
(m.status & (mca_cfg.ser ? MCI_STATUS_S : MCI_STATUS_UC))) (m.status & (mca_cfg.ser ? MCI_STATUS_S : MCI_STATUS_UC)))
continue; continue;
error_seen = true;
mce_read_aux(&m, i); mce_read_aux(&m, i);
if (!(flags & MCP_TIMESTAMP)) if (!(flags & MCP_TIMESTAMP))
@ -608,17 +610,10 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
severity = mce_severity(&m, mca_cfg.tolerant, NULL, false); severity = mce_severity(&m, mca_cfg.tolerant, NULL, false);
/*
* In the cases where we don't have a valid address after all,
* do not add it into the ring buffer.
*/
if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m)) { if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m)) {
if (m.status & MCI_STATUS_ADDRV) { if (m.status & MCI_STATUS_ADDRV) {
m.severity = severity; m.severity = severity;
m.usable_addr = mce_usable_address(&m); m.usable_addr = mce_usable_address(&m);
if (!mce_gen_pool_add(&m))
mce_schedule_work();
} }
} }
@ -626,9 +621,16 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
* Don't get the IP here because it's unlikely to * Don't get the IP here because it's unlikely to
* have anything to do with the actual error location. * have anything to do with the actual error location.
*/ */
if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce) { if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce)
error_logged = true;
mce_log(&m); mce_log(&m);
else if (m.usable_addr) {
/*
* Although we skipped logging this, we still want
* to take action. Add to the pool so the registered
* notifiers will see it.
*/
if (!mce_gen_pool_add(&m))
mce_schedule_work();
} }
/* /*
@ -644,7 +646,7 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
sync_core(); sync_core();
return error_logged; return error_seen;
} }
EXPORT_SYMBOL_GPL(machine_check_poll); EXPORT_SYMBOL_GPL(machine_check_poll);