From a0189c70e5f17f4253dd7bc575c97469900e23d6 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 27 May 2009 21:56:54 +0200 Subject: [PATCH] x86, mce: remove TSC print heuristic Previously mce_panic used a simple heuristic to avoid printing old so far unreported machine check events on a mce panic. This worked by comparing the TSC value at the start of the machine check handler with the event time stamp and only printing newer ones. This has a couple of issues, in particular on systems where the TSC is not fully synchronized between CPUs it could lose events or print old ones. It is also problematic with full system synchronization as it is added by the next patch. Remove the TSC heuristic and instead replace it with a simple heuristic to print corrected errors first and after that uncorrected errors and finally the worst machine check as determined by the machine check handler. This simplifies the code because there is no need to pass the original TSC value around. Contains fixes from Ying Huang [ Impact: bug fix, cleanup ] Signed-off-by: Andi Kleen Signed-off-by: Hidetoshi Seto Cc: Ying Huang Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/mcheck/mce.c | 34 ++++++++++++++++++-------------- 1 file changed, 19 insertions(+), 15 deletions(-) diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 86806e52fc40..6773610061d8 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -158,6 +158,7 @@ void mce_log(struct mce *mce) mcelog.entry[entry].finished = 1; wmb(); + mce->finished = 1; set_bit(0, ¬ify_user); } @@ -190,23 +191,29 @@ static void print_mce(struct mce *m) "and contact your hardware vendor\n"); } -static void mce_panic(char *msg, struct mce *backup, u64 start) +static void mce_panic(char *msg, struct mce *final) { int i; bust_spinlocks(1); console_verbose(); + /* First print corrected ones that are still unlogged */ for (i = 0; i < MCE_LOG_LEN; i++) { - u64 tsc = mcelog.entry[i].tsc; - - if ((s64)(tsc - start) < 0) - continue; - print_mce(&mcelog.entry[i]); - if (backup && mcelog.entry[i].tsc == backup->tsc) - backup = NULL; + struct mce *m = &mcelog.entry[i]; + if ((m->status & MCI_STATUS_VAL) && + !(m->status & MCI_STATUS_UC)) + print_mce(m); } - if (backup) - print_mce(backup); + /* Now print uncorrected but with the final one last */ + for (i = 0; i < MCE_LOG_LEN; i++) { + struct mce *m = &mcelog.entry[i]; + if (!(m->status & MCI_STATUS_VAL)) + continue; + if (!final || memcmp(m, final, sizeof(struct mce))) + print_mce(m); + } + if (final) + print_mce(final); panic(msg); } @@ -362,7 +369,6 @@ void do_machine_check(struct pt_regs *regs, long error_code) { struct mce m, panicm; int panicm_found = 0; - u64 mcestart = 0; int i; /* * If no_way_out gets set, there is no safe way to recover from this @@ -394,7 +400,6 @@ void do_machine_check(struct pt_regs *regs, long error_code) if (!(m.mcgstatus & MCG_STATUS_RIPV)) no_way_out = 1; - rdtscll(mcestart); barrier(); for (i = 0; i < banks; i++) { @@ -478,7 +483,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) * has not set tolerant to an insane level, give up and die. */ if (no_way_out && tolerant < 3) - mce_panic("Machine check", &panicm, mcestart); + mce_panic("Machine check", &panicm); /* * If the error seems to be unrecoverable, something should be @@ -506,8 +511,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) if (user_space) { force_sig(SIGBUS, current); } else if (panic_on_oops || tolerant < 2) { - mce_panic("Uncorrected machine check", - &panicm, mcestart); + mce_panic("Uncorrected machine check", &panicm); } }