From 41ce0564bfe2e129d56730418d8c0a9f9f2d31b5 Mon Sep 17 00:00:00 2001 From: Youquan Song Date: Tue, 6 Oct 2020 14:09:05 -0700 Subject: [PATCH] x86/mce: Pass pointer to saved pt_regs to severity calculation routines New recovery features require additional information about processor state when a machine check occurred. Pass pt_regs down to the routines that need it. No functional change. Signed-off-by: Youquan Song Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20201006210910.21062-2-tony.luck@intel.com --- arch/x86/kernel/cpu/mce/core.c | 14 +++++++------- arch/x86/kernel/cpu/mce/internal.h | 3 ++- arch/x86/kernel/cpu/mce/severity.c | 14 ++++++++------ 3 files changed, 17 insertions(+), 14 deletions(-) diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index b5b70f4b351d..2d6caf09e8e6 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -807,7 +807,7 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) goto clear_it; mce_read_aux(&m, i); - m.severity = mce_severity(&m, mca_cfg.tolerant, NULL, false); + m.severity = mce_severity(&m, NULL, mca_cfg.tolerant, NULL, false); /* * Don't get the IP here because it's unlikely to * have anything to do with the actual error location. @@ -856,7 +856,7 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, quirk_no_way_out(i, m, regs); m->bank = i; - if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) { + if (mce_severity(m, regs, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) { mce_read_aux(m, i); *msg = tmp; return 1; @@ -956,7 +956,7 @@ static void mce_reign(void) */ if (m && global_worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3) { /* call mce_severity() to get "msg" for panic */ - mce_severity(m, mca_cfg.tolerant, &msg, true); + mce_severity(m, NULL, mca_cfg.tolerant, &msg, true); mce_panic("Fatal machine check", m, msg); } @@ -1167,7 +1167,7 @@ static noinstr bool mce_check_crashing_cpu(void) return false; } -static void __mc_scan_banks(struct mce *m, struct mce *final, +static void __mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *final, unsigned long *toclear, unsigned long *valid_banks, int no_way_out, int *worst) { @@ -1202,7 +1202,7 @@ static void __mc_scan_banks(struct mce *m, struct mce *final, /* Set taint even when machine check was not enabled. */ add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); - severity = mce_severity(m, cfg->tolerant, NULL, true); + severity = mce_severity(m, regs, cfg->tolerant, NULL, true); /* * When machine check was for corrected/deferred handler don't @@ -1354,7 +1354,7 @@ noinstr void do_machine_check(struct pt_regs *regs) order = mce_start(&no_way_out); } - __mc_scan_banks(&m, final, toclear, valid_banks, no_way_out, &worst); + __mc_scan_banks(&m, regs, final, toclear, valid_banks, no_way_out, &worst); if (!no_way_out) mce_clear_state(toclear); @@ -1376,7 +1376,7 @@ noinstr void do_machine_check(struct pt_regs *regs) * make sure we have the right "msg". */ if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3) { - mce_severity(&m, cfg->tolerant, &msg, true); + mce_severity(&m, regs, cfg->tolerant, &msg, true); mce_panic("Local fatal machine check!", &m, msg); } } diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h index b122610e9046..88dcc79cfb07 100644 --- a/arch/x86/kernel/cpu/mce/internal.h +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -38,7 +38,8 @@ int mce_gen_pool_add(struct mce *mce); int mce_gen_pool_init(void); struct llist_node *mce_gen_pool_prepare_records(void); -extern int (*mce_severity)(struct mce *a, int tolerant, char **msg, bool is_excp); +extern int (*mce_severity)(struct mce *a, struct pt_regs *regs, + int tolerant, char **msg, bool is_excp); struct dentry *mce_get_debugfs_dir(void); extern mce_banks_t mce_banks_ce_disabled; diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c index e0722461bb57..0b072dc231ad 100644 --- a/arch/x86/kernel/cpu/mce/severity.c +++ b/arch/x86/kernel/cpu/mce/severity.c @@ -223,7 +223,7 @@ static struct severity { * distinguish an exception taken in user from from one * taken in the kernel. */ -static int error_context(struct mce *m) +static int error_context(struct mce *m, struct pt_regs *regs) { if ((m->cs & 3) == 3) return IN_USER; @@ -267,9 +267,10 @@ static int mce_severity_amd_smca(struct mce *m, enum context err_ctx) * See AMD Error Scope Hierarchy table in a newer BKDG. For example * 49125_15h_Models_30h-3Fh_BKDG.pdf, section "RAS Features" */ -static int mce_severity_amd(struct mce *m, int tolerant, char **msg, bool is_excp) +static int mce_severity_amd(struct mce *m, struct pt_regs *regs, int tolerant, + char **msg, bool is_excp) { - enum context ctx = error_context(m); + enum context ctx = error_context(m, regs); /* Processor Context Corrupt, no need to fumble too much, die! */ if (m->status & MCI_STATUS_PCC) @@ -319,10 +320,11 @@ static int mce_severity_amd(struct mce *m, int tolerant, char **msg, bool is_exc return MCE_KEEP_SEVERITY; } -static int mce_severity_intel(struct mce *m, int tolerant, char **msg, bool is_excp) +static int mce_severity_intel(struct mce *m, struct pt_regs *regs, + int tolerant, char **msg, bool is_excp) { enum exception excp = (is_excp ? EXCP_CONTEXT : NO_EXCP); - enum context ctx = error_context(m); + enum context ctx = error_context(m, regs); struct severity *s; for (s = severities;; s++) { @@ -356,7 +358,7 @@ static int mce_severity_intel(struct mce *m, int tolerant, char **msg, bool is_e } /* Default to mce_severity_intel */ -int (*mce_severity)(struct mce *m, int tolerant, char **msg, bool is_excp) = +int (*mce_severity)(struct mce *m, struct pt_regs *regs, int tolerant, char **msg, bool is_excp) = mce_severity_intel; void __init mcheck_vendor_init_severity(void)