diff options
author | Borislav Petkov <bp@suse.de> | 2021-12-20 21:43:28 +0100 |
---|---|---|
committer | Borislav Petkov <bp@suse.de> | 2022-02-23 11:09:25 +0100 |
commit | 7f1b8e0d6360178e3527d4f14e6921c254a86035 (patch) | |
tree | 21fd1faf6a1cbe36343dc8330da52c750bee7a33 /arch/x86/kernel | |
parent | 8ca97812c3c830573f965a07bbd84223e8c5f5bd (diff) | |
download | linux-7f1b8e0d6360178e3527d4f14e6921c254a86035.tar.bz2 |
x86/mce: Remove the tolerance level control
This is pretty much unused and not really useful. What is more, all
relevant MCA hardware has recoverable machine checks support so there's
no real need to tweak MCA tolerance levels in order to *maybe* extend
machine lifetime.
So rip it out.
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lore.kernel.org/r/YcDq8PxvKtTENl/e@zn.tnic
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r-- | arch/x86/kernel/cpu/mce/core.c | 53 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/mce/internal.h | 3 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/mce/severity.c | 21 |
3 files changed, 30 insertions, 47 deletions
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 3d766e6247bc..6c9b5dac38fd 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -86,14 +86,6 @@ struct mce_vendor_flags mce_flags __read_mostly; struct mca_config mca_cfg __read_mostly = { .bootlog = -1, - /* - * Tolerant levels: - * 0: always panic on uncorrected errors, log corrected errors - * 1: panic or SIGBUS on uncorrected errors, log corrected errors - * 2: SIGBUS or log uncorrected errors (if possible), log corr. errors - * 3: never panic or SIGBUS, log all errors (for testing only) - */ - .tolerant = 1, .monarch_timeout = -1 }; @@ -753,7 +745,7 @@ log_it: goto clear_it; mce_read_aux(&m, i); - m.severity = mce_severity(&m, NULL, mca_cfg.tolerant, NULL, false); + m.severity = mce_severity(&m, NULL, NULL, false); /* * Don't get the IP here because it's unlikely to * have anything to do with the actual error location. @@ -887,7 +879,7 @@ static __always_inline int mce_no_way_out(struct mce *m, char **msg, unsigned lo quirk_sandybridge_ifu(i, m, regs); m->bank = i; - if (mce_severity(m, regs, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) { + if (mce_severity(m, regs, &tmp, true) >= MCE_PANIC_SEVERITY) { mce_read_aux(m, i); *msg = tmp; return 1; @@ -935,12 +927,11 @@ static noinstr 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 (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); - } + 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); + ret = 1; goto out; } @@ -1004,9 +995,9 @@ static void mce_reign(void) * This dumps all the mces in the log buffer and stops the * other CPUs. */ - if (m && global_worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3) { + if (m && global_worst >= MCE_PANIC_SEVERITY) { /* call mce_severity() to get "msg" for panic */ - mce_severity(m, NULL, mca_cfg.tolerant, &msg, true); + mce_severity(m, NULL, &msg, true); mce_panic("Fatal machine check", m, msg); } @@ -1020,7 +1011,7 @@ static void mce_reign(void) * No machine check event found. Must be some external * source or one CPU is hung. Panic. */ - if (global_worst <= MCE_KEEP_SEVERITY && mca_cfg.tolerant < 3) + if (global_worst <= MCE_KEEP_SEVERITY) mce_panic("Fatal machine check from unknown source", NULL, NULL); /* @@ -1267,7 +1258,7 @@ __mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *final, /* Set taint even when machine check was not enabled. */ taint++; - severity = mce_severity(m, regs, cfg->tolerant, NULL, true); + severity = mce_severity(m, regs, NULL, true); /* * When machine check was for corrected/deferred handler don't @@ -1425,7 +1416,6 @@ noinstr void do_machine_check(struct pt_regs *regs) int worst = 0, order, no_way_out, kill_current_task, lmce, taint = 0; DECLARE_BITMAP(valid_banks, MAX_NR_BANKS) = { 0 }; DECLARE_BITMAP(toclear, MAX_NR_BANKS) = { 0 }; - struct mca_config *cfg = &mca_cfg; struct mce m, *final; char *msg = NULL; @@ -1447,7 +1437,7 @@ noinstr void do_machine_check(struct pt_regs *regs) /* * If no_way_out gets set, there is no safe way to recover from this - * MCE. If mca_cfg.tolerant is cranked up, we'll try anyway. + * MCE. */ no_way_out = 0; @@ -1481,7 +1471,7 @@ noinstr void do_machine_check(struct pt_regs *regs) * severity is MCE_AR_SEVERITY we have other options. */ if (!(m.mcgstatus & MCG_STATUS_RIPV)) - kill_current_task = (cfg->tolerant == 3) ? 0 : 1; + kill_current_task = 1; /* * Check if this MCE is signaled to only this logical processor, * on Intel, Zhaoxin only. @@ -1498,7 +1488,7 @@ noinstr void do_machine_check(struct pt_regs *regs) * to see it will clear it. */ if (lmce) { - if (no_way_out && cfg->tolerant < 3) + if (no_way_out) mce_panic("Fatal local machine check", &m, msg); } else { order = mce_start(&no_way_out); @@ -1518,7 +1508,7 @@ noinstr void do_machine_check(struct pt_regs *regs) if (!no_way_out) no_way_out = worst >= MCE_PANIC_SEVERITY; - if (no_way_out && cfg->tolerant < 3) + if (no_way_out) mce_panic("Fatal machine check on current CPU", &m, msg); } } else { @@ -1530,8 +1520,8 @@ noinstr void do_machine_check(struct pt_regs *regs) * fatal error. We call "mce_severity()" again to * make sure we have the right "msg". */ - if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3) { - mce_severity(&m, regs, cfg->tolerant, &msg, true); + if (worst >= MCE_PANIC_SEVERITY) { + mce_severity(&m, regs, &msg, true); mce_panic("Local fatal machine check!", &m, msg); } } @@ -2267,10 +2257,9 @@ static int __init mcheck_enable(char *str) cfg->bios_cmci_threshold = 1; else if (!strcmp(str, "recovery")) cfg->recovery = 1; - else if (isdigit(str[0])) { - if (get_option(&str, &cfg->tolerant) == 2) - get_option(&str, &(cfg->monarch_timeout)); - } else { + else if (isdigit(str[0])) + get_option(&str, &(cfg->monarch_timeout)); + else { pr_info("mce argument %s ignored. Please use /sys\n", str); return 0; } @@ -2520,7 +2509,6 @@ static ssize_t store_int_with_restart(struct device *s, return ret; } -static DEVICE_INT_ATTR(tolerant, 0644, mca_cfg.tolerant); static DEVICE_INT_ATTR(monarch_timeout, 0644, mca_cfg.monarch_timeout); static DEVICE_BOOL_ATTR(dont_log_ce, 0644, mca_cfg.dont_log_ce); static DEVICE_BOOL_ATTR(print_all, 0644, mca_cfg.print_all); @@ -2541,7 +2529,6 @@ static struct dev_ext_attribute dev_attr_cmci_disabled = { }; static struct device_attribute *mce_device_attrs[] = { - &dev_attr_tolerant.attr, &dev_attr_check_interval.attr, #ifdef CONFIG_X86_MCELOG_LEGACY &dev_attr_trigger, diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h index 3efb5037c364..4ae0e603f7fa 100644 --- a/arch/x86/kernel/cpu/mce/internal.h +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -35,7 +35,7 @@ int mce_gen_pool_add(struct mce *mce); int mce_gen_pool_init(void); struct llist_node *mce_gen_pool_prepare_records(void); -int mce_severity(struct mce *a, struct pt_regs *regs, int tolerant, char **msg, bool is_excp); +int mce_severity(struct mce *a, struct pt_regs *regs, char **msg, bool is_excp); struct dentry *mce_get_debugfs_dir(void); extern mce_banks_t mce_banks_ce_disabled; @@ -127,7 +127,6 @@ struct mca_config { bool ignore_ce; bool print_all; - int tolerant; int monarch_timeout; int panic_timeout; u32 rip_msr; diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c index ca0d775346fb..1add86935349 100644 --- a/arch/x86/kernel/cpu/mce/severity.c +++ b/arch/x86/kernel/cpu/mce/severity.c @@ -330,8 +330,7 @@ static __always_inline int mce_severity_amd_smca(struct mce *m, enum context err * See AMD Error Scope Hierarchy table in a newer BKDG. For example * 49125_15h_Models_30h-3Fh_BKDG.pdf, section "RAS Features" */ -static noinstr int mce_severity_amd(struct mce *m, struct pt_regs *regs, int tolerant, - char **msg, bool is_excp) +static noinstr int mce_severity_amd(struct mce *m, struct pt_regs *regs, char **msg, bool is_excp) { enum context ctx = error_context(m, regs); @@ -383,8 +382,7 @@ static noinstr int mce_severity_amd(struct mce *m, struct pt_regs *regs, int tol return MCE_KEEP_SEVERITY; } -static noinstr int mce_severity_intel(struct mce *m, struct pt_regs *regs, - int tolerant, char **msg, bool is_excp) +static noinstr int mce_severity_intel(struct mce *m, struct pt_regs *regs, char **msg, bool is_excp) { enum exception excp = (is_excp ? EXCP_CONTEXT : NO_EXCP); enum context ctx = error_context(m, regs); @@ -412,22 +410,21 @@ static noinstr int mce_severity_intel(struct mce *m, struct pt_regs *regs, if (msg) *msg = s->msg; s->covered = 1; - if (s->sev >= MCE_UC_SEVERITY && ctx == IN_KERNEL) { - if (tolerant < 1) - return MCE_PANIC_SEVERITY; - } + + if (s->sev >= MCE_UC_SEVERITY && ctx == IN_KERNEL) + return MCE_PANIC_SEVERITY; + return s->sev; } } -int noinstr mce_severity(struct mce *m, struct pt_regs *regs, int tolerant, char **msg, - bool is_excp) +int noinstr mce_severity(struct mce *m, struct pt_regs *regs, char **msg, bool is_excp) { if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) - return mce_severity_amd(m, regs, tolerant, msg, is_excp); + return mce_severity_amd(m, regs, msg, is_excp); else - return mce_severity_intel(m, regs, tolerant, msg, is_excp); + return mce_severity_intel(m, regs, msg, is_excp); } #ifdef CONFIG_DEBUG_FS |