Make mce_timed_out() identify holdout CPUs
Subsystems (3)
RFC PATCH 1/1 Make mce_timed_out() identify holdout CPUs
The "Timeout: Not all CPUs entered broadcast exception handler" message will appear from time to time given enough systems, but this message does not identify which CPUs failed to enter the broadcast exception handler. This information would be valuable if available, for example, in order to correlated with other hardware-oriented error messages. This commit therefore maintains a cpumask_t of CPUs that have entered this handler, and prints out which ones failed to enter in the event of a timeout.
Build-tested only.
arch/x86/kernel/cpu/mce/core.c +14 -1
@@ -878,6 +878,12 @@ static atomic_t mce_executing;static atomic_t mce_callin;/* +* Track which CPUs entered and not in order to print holdouts. +*/ +static cpumask_t mce_present_cpus; +static cpumask_t mce_missing_cpus; + +/* * Check if a timeout waiting for other CPUs happened. */ static int mce_timed_out (u64 *t,const char *msg)
@@ -894,8 +900,12 @@ static int mce_timed_out(u64 *t, const char *msg)if (!mca_cfg.monarch_timeout) goto out;if ((s64)*t <SPINUNIT ) { -if (mca_cfg.tolerant <=1 ) +if (mca_cfg.tolerant <=1 ) { +if (!cpumask_andnot (&mce_missing_cpus, cpu_online_mask, &mce_present_cpus)) +pr_info ("%s: MCE holdout CPUs: %*pbl\n" , + __func__,cpumask_pr_args (&mce_missing_cpus));mce_panic (msg,NULL ,NULL ); + } cpu_missing =1 ;return 1 ; }
@@ -1006,6 +1016,7 @@ static int mce_start(int *no_way_out)* is updated before mce_callin. */ order =atomic_inc_return (&mce_callin); +cpumask_set_cpu (smp_processor_id (), &mce_present_cpus);/* * Wait for everyone.
@@ -1114,6 +1125,7 @@ static int mce_end(int order) reset:atomic_set (&global_nwo,0 );atomic_set (&mce_callin,0 ); +cpumask_clear (&mce_present_cpus);barrier ();/*
@@ -2712,6 +2724,7 @@ static void mce_reset(void)atomic_set (&mce_executing,0 );atomic_set (&mce_callin,0 );atomic_set (&global_nwo,0 ); +cpumask_clear (&mce_present_cpus); }static int fake_panic_get (void *data,u64 *val)
Borislav Petkov
maintainerQuoted 5 lines · Paul E. McKenney
The "Timeout: Not all CPUs entered broadcast exception handler" message will appear from time to time given enough systems, but this message does not identify which CPUs failed to enter the broadcast exception handler. This information would be valuable if available, for example, in order to correlated with other hardware-oriented error messages.
Because you're expecting that the CPUs which have not entered the exception handler might have stuck earlier and that's the correlation there?
Quoted 1 line
This commit
That's a tautology. :)
Quoted 46 lines
therefore maintains a
cpumask_tof CPUs that have entered this handler, and prints out which ones failed to enter in the event of a timeout. Build-tested only.Cc Tony Luck <[email protected]>Cc Borislav Petkov <[email protected]>Cc Thomas Gleixner <[email protected]>Cc Ingo Molnar <[email protected]>Cc "H. Peter Anvin" <[email protected]>Cc <[email protected]>Cc <[email protected]>Reported-by Jonathan Lemon <[email protected]>Signed-off-by Paul E. McKenney <[email protected]>arch/x86/kernel/cpu/mce/core.c +11
-1@@ -878,6 +878,12 @@ static atomic_t mce_executing;static atomic_t mce_callin;/* +* Track which CPUs entered and not in order to print holdouts. +*/ +static cpumask_t mce_present_cpus; +static cpumask_t mce_missing_cpus; + +/* * Check if a timeout waiting for other CPUs happened. */ static int mce_timed_out (u64 *t,const char *msg)@@ -894,8 +900,12 @@ static int mce_timed_out(u64 *t, const char *msg)if (!mca_cfg.monarch_timeout) goto out;if ((s64)*t <SPINUNIT ) { -if (mca_cfg.tolerant <=1 ) +if (mca_cfg.tolerant <=1 ) { +if (!cpumask_andnot (&mce_missing_cpus, cpu_online_mask, &mce_present_cpus)) +pr_info ("%s: MCE holdout CPUs: %*pbl\n" , + __func__,cpumask_pr_args (&mce_missing_cpus));mce_panic (msg,NULL ,NULL ); + } cpu_missing =1 ;return 1 ; }
arch/x86/kernel/cpu/mce/core.c static int mce_start(int *no_way_out) · line 1018
Quoted 3 lines
arch/x86/kernel/cpu/mce/core.c +0
-0@@ -1006,6 +1016,7 @@ static int mce_start(int *no_way_out)* is updated before mce_callin. */ order =atomic_inc_return (&mce_callin);
Doesn't a single mce_callin_mask suffice?
Signature · 4 lines
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquetteQuoted 10 lines · Borislav Petkov
Quoted 5 lines · Paul E. McKenney
The "Timeout: Not all CPUs entered broadcast exception handler" message will appear from time to time given enough systems, but this message does not identify which CPUs failed to enter the broadcast exception handler. This information would be valuable if available, for example, in order to correlated with other hardware-oriented error messages.
Because you're expecting that the CPUs which have not entered the exception handler might have stuck earlier and that's the correlation there?
Or that there might have been any number of other error messages that flagged that CPU. For a few examples, watchdogs, hung tasks, and RCU CPU stall warnings.
Quoted 3 lines
Quoted 1 line
This commit
That's a tautology. :)
Not yet, it isn't! Well, except in -rcu. ;-)
Quoted 43 lines
Quoted 43 lines
therefore maintains a
cpumask_tof CPUs that have entered this handler, and prints out which ones failed to enter in the event of a timeout. Build-tested only.Cc Tony Luck <[email protected]>Cc Borislav Petkov <[email protected]>Cc Thomas Gleixner <[email protected]>Cc Ingo Molnar <[email protected]>Cc "H. Peter Anvin" <[email protected]>Cc <[email protected]>Cc <[email protected]>Reported-by Jonathan Lemon <[email protected]>Signed-off-by Paul E. McKenney <[email protected]>arch/x86/kernel/cpu/mce/core.c +11
-1@@ -878,6 +878,12 @@ static atomic_t mce_executing;static atomic_t mce_callin;/* +* Track which CPUs entered and not in order to print holdouts. +*/ +static cpumask_t mce_present_cpus; +static cpumask_t mce_missing_cpus; + +/* * Check if a timeout waiting for other CPUs happened. */ static int mce_timed_out (u64 *t,const char *msg)@@ -894,8 +900,12 @@ static int mce_timed_out(u64 *t, const char *msg)if (!mca_cfg.monarch_timeout) goto out;if ((s64)*t <SPINUNIT ) { -if (mca_cfg.tolerant <=1 ) +if (mca_cfg.tolerant <=1 ) { +if (!cpumask_andnot (&mce_missing_cpus, cpu_online_mask, &mce_present_cpus)) +pr_info ("%s: MCE holdout CPUs: %*pbl\n" , + __func__,cpumask_pr_args (&mce_missing_cpus));mce_panic (msg,NULL ,NULL ); + } cpu_missing =1 ;
Quoted 8 lines
arch/x86/kernel/cpu/mce/core.c static int mce_start(int *no_way_out) · line 1018
Quoted 6 lines
arch/x86/kernel/cpu/mce/core.c +0
-0return 1 ; }@@ -1006,6 +1016,7 @@ static int mce_start(int *no_way_out)* is updated before mce_callin. */ order =atomic_inc_return (&mce_callin);Doesn't a single
mce_callin_masksuffice?
You are suggesting dropping mce_missing_cpus and just doing this?
if (!cpumask_andnot(&mce_present_cpus, cpu_online_mask, &mce_present_cpus))
I was worried (perhaps unnecessarily) about the possibility of CPUs checking in during the printout operation, which would set rather than clear the bit. But perhaps the possible false positives that Tony points out make this race not worth worrying about.
Thoughts?
Thanx, Paul
Borislav Petkov
maintainerQuoted 1 line · Paul E. McKenney
Not yet, it isn't! Well, except in -rcu. ;-)
Of course it is - saying "This commit" in this commit's commit message is very much a tautology. :-)
Quoted 3 lines
You are suggesting dropping
mce_missing_cpusand just doing this?if (!cpumask_andnot(&mce_present_cpus,
cpu_online_mask,&mce_present_cpus))
Yes.
And pls don't call it "holdout CPUs" and change the order so that it is more user-friendly (yap, you don't need __func__ either):
[ 78.946153] mce: Not all CPUs (24-47,120-143) entered the broadcast exception handler. [ 78.946153] Kernel panic - not syncing: Timeout: MCA synchronization.
or so.
And that's fine if it appears twice as long as it is the same info - the MCA code is one complex mess so you can probably guess why I'd like to have new stuff added to it be as simplistic as possible.
Quoted 6 lines
I was worried (perhaps unnecessarily) about the possibility of CPUs checking in during the printout operation, which would set rather than clear the bit. But perhaps the possible false positives that Tony points out make this race not worth worrying about.
Thoughts?
Yah, apparently, it is not going to be a precise report as you wanted it to be but at least it'll tell you which *sockets* you can rule out, if not cores.
:-)
Signature · 4 lines
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquettePaul E. McKenney
Tested-by Tony LuckQuoted 5 lines · Borislav Petkov
Quoted 1 line · Paul E. McKenney
Not yet, it isn't! Well, except in -rcu. ;-)
Of course it is - saying "This commit" in this commit's commit message is very much a tautology. :-)
Tautology? Maybe self-referential? ;-)
Quoted 5 lines
Quoted 3 lines
You are suggesting dropping
mce_missing_cpusand just doing this?if (!cpumask_andnot(&mce_present_cpus,
cpu_online_mask,&mce_present_cpus))Yes.
I could drop mce_present_cpus, and then initialize mce_missing_cpus to CPU_MASK_ALL, and have each CPU clear its bit on entry using cpumask_clear_cpu(). Then cpumask_and() it with cpu_online_mask and print it out. That allows late-arriving CPUs to be properly accounted for, most of the time, anyway.
Quoted 1 line
And pls don't call it "holdout CPUs"
How about "missing CPUs"? That is what I used in the meantime, please see below. If you have something you would prefer that it be called, please let me know.
Quoted 7 lines
and change the order so that it is
more user-friendly (yap, you don't need__func__either):[ 78.946153] mce: Not all CPUs (24-47,120-143) entered the broadcast exception handler. [ 78.946153] Kernel panic - not syncing: Timeout: MCA synchronization.or so.
I removed __func__, but the pr_info() already precedes the mce_panic(). Do I need a udelay() after the pr_info() or some such? If so, how long should is spin?
Quoted 3 lines
And that's fine if it appears twice as long as it is the same info - the MCA code is one complex mess so you can probably guess why I'd like to have new stuff added to it be as simplistic as possible.
Works for me. ;-)
Quoted 5 lines
Quoted 5 lines
I was worried (perhaps unnecessarily) about the possibility of CPUs checking in during the printout operation, which would set rather than clear the bit. But perhaps the possible false positives that Tony points out make this race not worth worrying about.
Quoted 7 lines
Quoted 1 line
Thoughts?
Yah, apparently, it is not going to be a precise report as you wanted it to be but at least it'll tell you which *sockets* you can rule out, if not cores.
:-)
Some information is usually better than none. And I bet that failing hardware is capable of all sorts of tricks at all sorts of levels. ;-)
Updated patch below. Is this what you had in mind?
Thanx, Paul
------------------------------------------------------------------------
commit 4b4b57692fdd3b111098eda94df7529f85c54406
Author: Paul E. McKenney <[email protected]> Date: Wed Dec 23 17:04:19 2020 -0800
x86/mce: Make mce_timed_out() identify holdout CPUs
The "Timeout: Not all CPUs entered broadcast exception handler" message will appear from time to time given enough systems, but this message does not identify which CPUs failed to enter the broadcast exception handler. This information would be valuable if available, for example, in order to correlated with other hardware-oriented error messages. This commit therefore maintains a cpumask_t of CPUs that have entered this handler, and prints out which ones failed to enter in the event of a timeout.
arch/x86/kernel/cpu/mce/core.c +13 -1
@@ -878,6 +878,11 @@ static atomic_t mce_executing;static atomic_t mce_callin;/* +* Track which CPUs entered and not in order to print holdouts. +*/ +static cpumask_t mce_missing_cpus =CPU_MASK_ALL ; + +/* * Check if a timeout waiting for other CPUs happened. */ static int mce_timed_out (u64 *t,const char *msg)
@@ -894,8 +899,12 @@ static int mce_timed_out(u64 *t, const char *msg)if (!mca_cfg.monarch_timeout) goto out;if ((s64)*t <SPINUNIT ) { -if (mca_cfg.tolerant <=1 ) +if (mca_cfg.tolerant <=1 ) { +if (cpumask_and (&mce_missing_cpus, cpu_online_mask, &mce_missing_cpus)) +pr_info ("MCE missing CPUs (may include false positives): %*pbl\n" , +cpumask_pr_args (&mce_missing_cpus));mce_panic (msg,NULL ,NULL ); + } cpu_missing =1 ;return 1 ; }
@@ -1006,6 +1015,7 @@ static int mce_start(int *no_way_out)* is updated before mce_callin. */ order =atomic_inc_return (&mce_callin); +cpumask_clear_cpu (smp_processor_id (), &mce_missing_cpus);/* * Wait for everyone.
@@ -1114,6 +1124,7 @@ static int mce_end(int order) reset:atomic_set (&global_nwo,0 );atomic_set (&mce_callin,0 ); +cpumask_setall (&mce_missing_cpus);barrier ();/*
@@ -2712,6 +2723,7 @@ static void mce_reset(void)atomic_set (&mce_executing,0 );atomic_set (&mce_callin,0 );atomic_set (&global_nwo,0 ); +cpumask_setall (&mce_missing_cpus); }static int fake_panic_get (void *data,u64 *val)
Quoted 2 lines · Paul E. McKenney
Some information is usually better than none. And I bet that failing hardware is capable of all sorts of tricks at all sorts of levels. ;-)
Tell me about it.
Quoted 1 line
Updated patch below. Is this what you had in mind?
Ok, so I've massaged it into the below locally while taking another detailed look. Made the pr_info pr_emerg and poked at the text more, as I do. :)
Lemme know if something else needs to be adjusted, otherwise I'll queue it.
Thx.
---
Author: Paul E. McKenney <[email protected]> Date: Wed Dec 23 17:04:19 2020 -0800
x86/mce: Make mce_timed_out() identify holdout CPUs
The
"Timeout: Not all CPUs entered broadcast exception handler"
message will appear from time to time given enough systems, but this message does not identify which CPUs failed to enter the broadcast exception handler. This information would be valuable if available, for example, in order to correlate with other hardware-oriented error messages.
Add a cpumask of CPUs which maintains which CPUs have entered this handler, and print out which ones failed to enter in the event of a timeout.
[ bp: Massage. ]
arch/x86/kernel/cpu/mce/core.c +14 -1
@@ -877,6 +877,12 @@ static atomic_t mce_executing;*/ static atomic_t mce_callin; +/* +* Track which CPUs entered the MCA broadcast synchronization and which not in +* order to print holdouts. +*/ +static cpumask_t mce_missing_cpus =CPU_MASK_ALL ; +/* * Check if a timeout waiting for other CPUs happened. */
@@ -894,8 +900,12 @@ static int mce_timed_out(u64 *t, const char *msg)if (!mca_cfg.monarch_timeout) goto out;if ((s64)*t <SPINUNIT ) { -if (mca_cfg.tolerant <=1 ) +if (mca_cfg.tolerant <=1 ) { +if (cpumask_and (&mce_missing_cpus, cpu_online_mask, &mce_missing_cpus)) +pr_emerg ("CPUs not responding to MCE broadcast (may include false positives): %*pbl\n" , +cpumask_pr_args (&mce_missing_cpus));mce_panic (msg,NULL ,NULL ); + } cpu_missing =1 ;return 1 ; }
@@ -1006,6 +1016,7 @@ static int mce_start(int *no_way_out)* is updated before mce_callin. */ order =atomic_inc_return (&mce_callin); +cpumask_clear_cpu (smp_processor_id (), &mce_missing_cpus);/* * Wait for everyone.
@@ -1114,6 +1125,7 @@ static int mce_end(int order) reset:atomic_set (&global_nwo,0 );atomic_set (&mce_callin,0 ); +cpumask_setall (&mce_missing_cpus);barrier ();/*
@@ -2712,6 +2724,7 @@ static void mce_reset(void)atomic_set (&mce_executing,0 );atomic_set (&mce_callin,0 );atomic_set (&global_nwo,0 ); +cpumask_setall (&mce_missing_cpus); }static int fake_panic_get (void *data,u64 *val)
Signature · 4 lines
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquetteQuoted 6 lines · Borislav Petkov
Quoted 2 lines · Paul E. McKenney
Some information is usually better than none. And I bet that failing hardware is capable of all sorts of tricks at all sorts of levels. ;-)
Tell me about it.
Quoted 8 lines
Quoted 1 line
Updated patch below. Is this what you had in mind?
Ok, so I've massaged it into the below locally while taking another detailed look. Made the
pr_infopr_emergand poked at the text more, as I do. :)Lemme know if something else needs to be adjusted, otherwise I'll queue it.
Looks good to me! I agree that your change to the pr_emerg() string is much better than my original. And good point on your added comment, plus it was fun to see that my original "holdouts" wording has not completely vanished. ;-)
Thank you very much!!!
Thanx, Paul
Quoted 91 lines
Thx.
---
Author: Paul E. McKenney <[email protected]> Date: Wed Dec 23 17:04:19 2020 -0800x86/mce: Make
mce_timed_out()identify holdout CPUsThe
"Timeout: Not all CPUs entered broadcast exception handler"
message will appear from time to time given enough systems, but this message does not identify which CPUs failed to enter the broadcast exception handler. This information would be valuable if available, for example, in order to correlate with other hardware-oriented error messages.
Add a cpumask of CPUs which maintains which CPUs have entered this handler, and print out which ones failed to enter in the event of a timeout.
[ bp: Massage. ]
Reported-by Jonathan Lemon <[email protected]>Signed-off-by Paul E. McKenney <[email protected]>Signed-off-by Borislav Petkov <[email protected]>Tested-by Tony Luck <[email protected]>arch/x86/kernel/cpu/mce/core.c +14
-1@@ -877,6 +877,12 @@ static atomic_t mce_executing;*/ static atomic_t mce_callin; +/* +* Track which CPUs entered the MCA broadcast synchronization and which not in +* order to print holdouts. +*/ +static cpumask_t mce_missing_cpus =CPU_MASK_ALL ; +/* * Check if a timeout waiting for other CPUs happened. */ @@ -894,8 +900,12 @@ static int mce_timed_out(u64 *t, const char *msg)if (!mca_cfg.monarch_timeout) goto out;if ((s64)*t <SPINUNIT ) { -if (mca_cfg.tolerant <=1 ) +if (mca_cfg.tolerant <=1 ) { +if (cpumask_and (&mce_missing_cpus, cpu_online_mask, &mce_missing_cpus)) +pr_emerg ("CPUs not responding to MCE broadcast (may include false positives): %*pbl\n" , +cpumask_pr_args (&mce_missing_cpus));mce_panic (msg,NULL ,NULL ); + } cpu_missing =1 ;return 1 ; }@@ -1006,6 +1016,7 @@ static int mce_start(int *no_way_out)* is updated before mce_callin. */ order =atomic_inc_return (&mce_callin); +cpumask_clear_cpu (smp_processor_id (), &mce_missing_cpus);/* * Wait for everyone. @@ -1114,6 +1125,7 @@ static int mce_end(int order) reset:atomic_set (&global_nwo,0 );atomic_set (&mce_callin,0 ); +cpumask_setall (&mce_missing_cpus);barrier ();/* @@ -2712,6 +2724,7 @@ static void mce_reset(void)atomic_set (&mce_executing,0 );atomic_set (&mce_callin,0 );atomic_set (&global_nwo,0 ); +cpumask_setall (&mce_missing_cpus); }static int fake_panic_get (void *data,u64 *val)Signature · 5 lines
-- Regards/Gruss, Boris. https://people.kernel.org/tglx/notes-about-netiquette
Borislav Petkov
maintainerQuoted 2 lines · Paul E. McKenney
Looks good to me! I agree that your change to the
pr_emerg()string is much better than my original.
Well, the rest of the MCE code uses pr_emerg on that path so...
Quoted 2 lines
And good point on your added comment, plus it was fun to see that my original "holdouts" wording has not completely vanished. ;-)
I had to leave it in seeing how you love that formulation. :-P
Quoted 1 line
Thank you very much!!!
Thanks too Paul!
/me queues.
Signature · 4 lines
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquetteLuck, Tony
maintainerQuoted 7 lines
The "Timeout: Not all CPUs entered broadcast exception handler" message will appear from time to time given enough systems, but this message does not identify which CPUs failed to enter the broadcast exception handler. This information would be valuable if available, for example, in order to correlated with other hardware-oriented error messages. This commit therefore maintains a
cpumask_tof CPUs that have entered this handler, and prints out which ones failed to enter in the event of a timeout.
I tried doing this a while back, but found that in my test case where I forced an error that would cause both threads from one core to be "missing", the output was highly unpredictable. Some random number of extra CPUs were reported as missing. After I added some extra breadcrumbs it became clear that pretty much all the CPUs (except the missing pair) entered do_machine_check(), but some got hung up at various points beyond the entry point. My only theory was that they were trying to snoop caches from the dead core (or access some other resource held by the dead core) and so they hung too.
Your code is much neater than mine ... and perhaps works in other cases, but maybe the message needs to allow for the fact that some of the cores that are reported missing may just be collateral damage from the initial problem.
If I get time in the next day or two, I'll run my old test against your code to see what happens.
-Tony
Quoted 17 lines · Tony
Quoted 7 lines
The "Timeout: Not all CPUs entered broadcast exception handler" message will appear from time to time given enough systems, but this message does not identify which CPUs failed to enter the broadcast exception handler. This information would be valuable if available, for example, in order to correlated with other hardware-oriented error messages. This commit therefore maintains a
cpumask_tof CPUs that have entered this handler, and prints out which ones failed to enter in the event of a timeout.I tried doing this a while back, but found that in my test case where I forced an error that would cause both threads from one core to be "missing", the output was highly unpredictable. Some random number of extra CPUs were reported as missing. After I added some extra breadcrumbs it became clear that pretty much all the CPUs (except the missing pair) entered
do_machine_check(), but some got hung up at various points beyond the entry point. My only theory was that they were trying to snoop caches from the dead core (or access some other resource held by the dead core) and so they hung too.
Quoted 3 lines
Your code is much neater than mine ... and perhaps works in other cases, but maybe the message needs to allow for the fact that some of the cores that are reported missing may just be collateral damage from the initial problem.
Understood. The system is probably not in the best shape if this code is ever executed, after all. ;-)
So how about like this?
pr_info("%s: MCE holdout CPUs (may include false positives): %*pbl\n",
Easy enough if so!
Quoted 2 lines
If I get time in the next day or two, I'll run my old test against your code to see what happens.
Thank you very much in advance!
For my own testing, is this still the right thing to use?
https://github.com/andikleen/mce-inject
Thanx, Paul
Luck, Tony
maintainerQuoted 22 lines · Paul E. McKenney
Quoted 17 lines · Tony
Quoted 7 lines
The "Timeout: Not all CPUs entered broadcast exception handler" message will appear from time to time given enough systems, but this message does not identify which CPUs failed to enter the broadcast exception handler. This information would be valuable if available, for example, in order to correlated with other hardware-oriented error messages. This commit therefore maintains a
cpumask_tof CPUs that have entered this handler, and prints out which ones failed to enter in the event of a timeout.I tried doing this a while back, but found that in my test case where I forced an error that would cause both threads from one core to be "missing", the output was highly unpredictable. Some random number of extra CPUs were reported as missing. After I added some extra breadcrumbs it became clear that pretty much all the CPUs (except the missing pair) entered
do_machine_check(), but some got hung up at various points beyond the entry point. My only theory was that they were trying to snoop caches from the dead core (or access some other resource held by the dead core) and so they hung too.Quoted 3 lines
Your code is much neater than mine ... and perhaps works in other cases, but maybe the message needs to allow for the fact that some of the cores that are reported missing may just be collateral damage from the initial problem.
Quoted 6 lines
Understood. The system is probably not in the best shape if this code is ever executed, after all. ;-)
So how about like this?
pr_info("%s: MCE holdout CPUs (may include false positives): %*pbl\n",
That looks fine.
Quoted 5 lines
Easy enough if so!
Quoted 2 lines
If I get time in the next day or two, I'll run my old test against your code to see what happens.
I got time today (plenty of meetings in which to run experiments in background).
This code:
- if (mca_cfg.tolerant <= 1)
+ if (mca_cfg.tolerant <= 1) {
+ if (!cpumask_andnot(&mce_missing_cpus, cpu_online_mask, &mce_present_cpus))
+ pr_info("%s: MCE holdout CPUs: %*pbl\n",
+ __func__, cpumask_pr_args(&mce_missing_cpus));
mce_panic(msg, NULL, NULL);didn't trigger ... so maybe that cpumask_andnot() didn't return the value you expected?
I added a:
+ pr_info("%s: MCE present CPUs: %*pbl\n", __func__, cpumask_pr_args(&mce_present_cpus));
to check that the mask was being set correctly, and saw:
[ 219.329767] mce: mce_timed_out: MCE present CPUs: 0-23,48-119,144-191
So the every core of socket 1 failed to show up for this test.
Quoted 3 lines
For my own testing, is this still the right thing to use?
That fakes up errors (by hooking into the mce_rdmsr() code to return arbitrary user supplied values). The plus side of this is that you can fake any error signature without needing special h/w or f/w. The downside is that it is all fake and you can't create situations where some CPUs don't show up in the machine check handler.
-Tony
Quoted 30 lines · Tony
Quoted 22 lines · Paul E. McKenney
Quoted 17 lines · Tony
Quoted 7 lines
The "Timeout: Not all CPUs entered broadcast exception handler" message will appear from time to time given enough systems, but this message does not identify which CPUs failed to enter the broadcast exception handler. This information would be valuable if available, for example, in order to correlated with other hardware-oriented error messages. This commit therefore maintains a
cpumask_tof CPUs that have entered this handler, and prints out which ones failed to enter in the event of a timeout.I tried doing this a while back, but found that in my test case where I forced an error that would cause both threads from one core to be "missing", the output was highly unpredictable. Some random number of extra CPUs were reported as missing. After I added some extra breadcrumbs it became clear that pretty much all the CPUs (except the missing pair) entered
do_machine_check(), but some got hung up at various points beyond the entry point. My only theory was that they were trying to snoop caches from the dead core (or access some other resource held by the dead core) and so they hung too.Quoted 3 lines
Your code is much neater than mine ... and perhaps works in other cases, but maybe the message needs to allow for the fact that some of the cores that are reported missing may just be collateral damage from the initial problem.
Quoted 6 lines
Understood. The system is probably not in the best shape if this code is ever executed, after all. ;-)
So how about like this?
pr_info("%s: MCE holdout CPUs (may include false positives): %*pbl\n",
Quoted 8 lines
That looks fine.
Quoted 5 lines
Easy enough if so!
Quoted 2 lines
If I get time in the next day or two, I'll run my old test against your code to see what happens.
I got time today (plenty of meetings in which to run experiments in background).
Thank you very much!
Quoted 13 lines
This code:
(quoted diff) +4
-1- if (mca_cfg.tolerant <= 1) + if (mca_cfg.tolerant <= 1) { + if (!cpumask_andnot(&mce_missing_cpus, cpu_online_mask, &mce_present_cpus)) + pr_info("%s: MCE holdout CPUs: %*pbl\n", + __func__, cpumask_pr_args(&mce_missing_cpus)); mce_panic(msg, NULL, NULL);didn't trigger ... so maybe that
cpumask_andnot()didn't return the value you expected?I added a:
Quoted 7 lines
+
pr_info("%s: MCE present CPUs: %*pbl\n", __func__, cpumask_pr_args(&mce_present_cpus));to check that the mask was being set correctly, and saw:
[ 219.329767] mce: mce_timed_out: MCE present CPUs: 0-23,48-119,144-191So the every core of socket 1 failed to show up for this test.
I'll say that cpumask_andnot() didn't return the value I expected! Mostly because idiot here somehow interpreted "If *@dstp is empty, returns 0, else returns 1" as "Returns true if *dstp is empty". So the check is backwards.
Please see below for an updated patch.
Quoted 9 lines
Quoted 3 lines
For my own testing, is this still the right thing to use?
That fakes up errors (by hooking into the
mce_rdmsr()code to return arbitrary user supplied values). The plus side of this is that you can fake any error signature without needing special h/w or f/w. The downside is that it is all fake and you can't create situations where some CPUs don't show up in the machine check handler.
So I would need to modify the code to test the code. I have done worse things, I suppose. ;-)
Thanx, Paul
------------------------------------------------------------------------
x86/mce: Make mce_timed_out() identify holdout CPUs
The "Timeout: Not all CPUs entered broadcast exception handler" message will appear from time to time given enough systems, but this message does not identify which CPUs failed to enter the broadcast exception handler. This information would be valuable if available, for example, in order to correlated with other hardware-oriented error messages. This commit therefore maintains a cpumask_t of CPUs that have entered this handler, and prints out which ones failed to enter in the event of a timeout.
arch/x86/kernel/cpu/mce/core.c +14 -1
@@ -878,6 +878,12 @@ static atomic_t mce_executing;static atomic_t mce_callin;/* +* Track which CPUs entered and not in order to print holdouts. +*/ +static cpumask_t mce_present_cpus; +static cpumask_t mce_missing_cpus; + +/* * Check if a timeout waiting for other CPUs happened. */ static int mce_timed_out (u64 *t,const char *msg)
@@ -894,8 +900,12 @@ static int mce_timed_out(u64 *t, const char *msg)if (!mca_cfg.monarch_timeout) goto out;if ((s64)*t <SPINUNIT ) { -if (mca_cfg.tolerant <=1 ) +if (mca_cfg.tolerant <=1 ) { +if (cpumask_andnot (&mce_missing_cpus, cpu_online_mask, &mce_present_cpus)) +pr_info ("%s: MCE holdout CPUs (may include false positives): %*pbl\n" , + __func__,cpumask_pr_args (&mce_missing_cpus));mce_panic (msg,NULL ,NULL ); + } cpu_missing =1 ;return 1 ; }
@@ -1006,6 +1016,7 @@ static int mce_start(int *no_way_out)* is updated before mce_callin. */ order =atomic_inc_return (&mce_callin); +cpumask_set_cpu (smp_processor_id (), &mce_present_cpus);/* * Wait for everyone.
@@ -1114,6 +1125,7 @@ static int mce_end(int order) reset:atomic_set (&global_nwo,0 );atomic_set (&mce_callin,0 ); +cpumask_clear (&mce_present_cpus);barrier ();/*
@@ -2712,6 +2724,7 @@ static void mce_reset(void)atomic_set (&mce_executing,0 );atomic_set (&mce_callin,0 );atomic_set (&global_nwo,0 ); +cpumask_clear (&mce_present_cpus); }static int fake_panic_get (void *data,u64 *val)
Quoted 1 line
Please see below for an updated patch.
Yes. That worked:
[ 78.946069] mce: mce_timed_out: MCE holdout CPUs (may include false positives): 24-47,120-143 [ 78.946151] mce: mce_timed_out: MCE holdout CPUs (may include false positives): 24-47,120-143 [ 78.946153] Kernel panic - not syncing: Timeout: Not all CPUs entered broadcast exception handler
I guess that more than one CPU hit the timeout and so your new message was printed twice before the panic code took over?
Once again, the whole of socket 1 is MIA rather than just the pair of threads on one of the cores there. But that's a useful improvement (eliminating the other three sockets on this system).
-Tony
Quoted 10 lines · Tony
Quoted 1 line
Please see below for an updated patch.
Yes. That worked:
[ 78.946069] mce: mce_timed_out: MCE holdout CPUs (may include false positives): 24-47,120-143 [ 78.946151] mce: mce_timed_out: MCE holdout CPUs (may include false positives): 24-47,120-143 [ 78.946153] Kernel panic - not syncing: Timeout: Not all CPUs entered broadcast exception handlerI guess that more than one CPU hit the timeout and so your new message was printed twice before the panic code took over?
Could well be.
It would be easy to add a flag that allowed only one CPU to print the message. Does that make sense? (See off-the-cuff probably-broken delta patch below for one approach.)
Quoted 4 lines
Once again, the whole of socket 1 is MIA rather than just the pair of threads on one of the cores there. But that's a useful improvement (eliminating the other three sockets on this system).
Tested-by Tony Luck <[email protected]>
Thank you very much! I will apply this.
Thanx, Paul
------------------------------------------------------------------------
arch/x86/kernel/cpu/mce/core.c +5 -1
@@ -882,6 +882,7 @@ static atomic_t mce_callin;*/ static cpumask_t mce_present_cpus;static cpumask_t mce_missing_cpus; +static atomic_t mce_missing_cpus_gate;/* * Check if a timeout waiting for other CPUs happened.
@@ -900,7 +901,7 @@ static int mce_timed_out(u64 *t, const char *msg)if (!mca_cfg.monarch_timeout) goto out;if ((s64)*t <SPINUNIT ) { -if (mca_cfg.tolerant <=1 ) { +if (mca_cfg.tolerant <=1 && !atomic_xchg (&mce_missing_cpus_gate,1 )) {if (cpumask_andnot (&mce_missing_cpus, cpu_online_mask, &mce_present_cpus))pr_info ("%s: MCE holdout CPUs (may include false positives): %*pbl\n" , __func__,cpumask_pr_args (&mce_missing_cpus));
@@ -1017,6 +1018,7 @@ static int mce_start(int *no_way_out)*/ order =atomic_inc_return (&mce_callin);cpumask_set_cpu (smp_processor_id (), &mce_present_cpus); +atomic_set (&mce_missing_cpus_gate,0 );/* * Wait for everyone.
@@ -1126,6 +1128,7 @@ static int mce_end(int order)atomic_set (&global_nwo,0 );atomic_set (&mce_callin,0 );cpumask_clear (&mce_present_cpus); +atomic_set (&mce_missing_cpus_gate,0 );barrier ();/*
@@ -2725,6 +2728,7 @@ static void mce_reset(void)atomic_set (&mce_callin,0 );atomic_set (&global_nwo,0 );cpumask_clear (&mce_present_cpus); +atomic_set (&mce_missing_cpus_gate,0 ); }static int fake_panic_get (void *data,u64 *val)
[tip: ras/core] x86/mce: Make mce_timed_out() identify holdout CPUs
In reply to Paul E. McKenneyThe following commit has been merged into the ras/core branch of tip:
The following commit has been merged into the ras/core branch of tip:
Commit-ID: 7bb39313cd6239e7eb95198950a02b4ad2a08316 Gitweb: https://git.kernel.org/tip/7bb39313cd6239e7eb95198950a02b4ad2a08316 Author: Paul E. McKenney <[email protected]> AuthorDate: Wed, 23 Dec 2020 17:04:19 -08:00 Committer: Borislav Petkov <[email protected]> CommitterDate: Fri, 08 Jan 2021 18:00:09 +01:00
x86/mce: Make mce_timed_out() identify holdout CPUs
The
"Timeout: Not all CPUs entered broadcast exception handler"
message will appear from time to time given enough systems, but this message does not identify which CPUs failed to enter the broadcast exception handler. This information would be valuable if available, for example, in order to correlate with other hardware-oriented error messages.
Add a cpumask of CPUs which maintains which CPUs have entered this handler, and print out which ones failed to enter in the event of a timeout.
[ bp: Massage. ]
--- arch/x86/kernel/cpu/mce/core.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-)
arch/x86/kernel/cpu/mce/core.c +14 -1
@@ -878,6 +878,12 @@ static atomic_t mce_executing;static atomic_t mce_callin;/* +* Track which CPUs entered the MCA broadcast synchronization and which not in +* order to print holdouts. +*/ +static cpumask_t mce_missing_cpus =CPU_MASK_ALL ; + +/* * Check if a timeout waiting for other CPUs happened. */ static int mce_timed_out (u64 *t,const char *msg)
@@ -894,8 +900,12 @@ static int mce_timed_out(u64 *t, const char *msg)if (!mca_cfg.monarch_timeout) goto out;if ((s64)*t <SPINUNIT ) { -if (mca_cfg.tolerant <=1 ) +if (mca_cfg.tolerant <=1 ) { +if (cpumask_and (&mce_missing_cpus, cpu_online_mask, &mce_missing_cpus)) +pr_emerg ("CPUs not responding to MCE broadcast (may include false positives): %*pbl\n" , +cpumask_pr_args (&mce_missing_cpus));mce_panic (msg,NULL ,NULL ); + } cpu_missing =1 ;return 1 ; }
@@ -1006,6 +1016,7 @@ static int mce_start(int *no_way_out)* is updated before mce_callin. */ order =atomic_inc_return (&mce_callin); +cpumask_clear_cpu (smp_processor_id (), &mce_missing_cpus);/* * Wait for everyone.
@@ -1114,6 +1125,7 @@ static int mce_end(int order) reset:atomic_set (&global_nwo,0 );atomic_set (&mce_callin,0 ); +cpumask_setall (&mce_missing_cpus);barrier ();/*
@@ -2712,6 +2724,7 @@ static void mce_reset(void)atomic_set (&mce_executing,0 );atomic_set (&mce_callin,0 );atomic_set (&global_nwo,0 ); +cpumask_setall (&mce_missing_cpus); }static int fake_panic_get (void *data,u64 *val)