1 files changed, 122 insertions, 58 deletions

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 8a2b8e791314..edc429b7d736 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -42,6 +42,9 @@
 #include <linux/export.h>
 #include <linux/jump_label.h>
 #include <linux/set_memory.h>
+#include <linux/sync_core.h>
+#include <linux/task_work.h>
+#include <linux/kexec.h>
 
 #include <asm/intel-family.h>
 #include <asm/processor.h>
@@ -315,6 +318,7 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp)
 	struct llist_node *pending;
 	struct mce_evt_llist *l;
 	int apei_err = 0;
+	struct page *p;
 
 	/*
 	 * Allow instrumentation around external facilities usage. Not that it
@@ -370,6 +374,20 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp)
 	if (!fake_panic) {
 		if (panic_timeout == 0)
 			panic_timeout = mca_cfg.panic_timeout;
+
+		/*
+		 * Kdump skips the poisoned page in order to avoid
+		 * touching the error bits again. Poison the page even
+		 * if the error is fatal and the machine is about to
+		 * panic.
+		 */
+		if (kexec_crash_loaded()) {
+			if (final && (final->status & MCI_STATUS_ADDRV)) {
+				p = pfn_to_online_page(final->addr >> PAGE_SHIFT);
+				if (p)
+					SetPageHWPoison(p);
+			}
+		}
 		panic(msg);
 	} else
 		pr_emerg(HW_ERR "Fake kernel panic: %s\n", msg);
@@ -397,13 +415,16 @@ static int msr_to_offset(u32 msr)
 	return -1;
 }
 
-__visible bool ex_handler_rdmsr_fault(const struct exception_table_entry *fixup,
-				      struct pt_regs *regs, int trapnr,
-				      unsigned long error_code,
-				      unsigned long fault_addr)
+static void ex_handler_msr_mce(struct pt_regs *regs, bool wrmsr)
 {
-	pr_emerg("MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pS)\n",
-		 (unsigned int)regs->cx, regs->ip, (void *)regs->ip);
+	if (wrmsr) {
+		pr_emerg("MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pS)\n",
+			 (unsigned int)regs->cx, (unsigned int)regs->dx, (unsigned int)regs->ax,
+			 regs->ip, (void *)regs->ip);
+	} else {
+		pr_emerg("MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pS)\n",
+			 (unsigned int)regs->cx, regs->ip, (void *)regs->ip);
+	}
 
 	show_stack_regs(regs);
 
@@ -411,7 +432,14 @@ __visible bool ex_handler_rdmsr_fault(const struct exception_table_entry *fixup,
 
 	while (true)
 		cpu_relax();
+}
 
+__visible bool ex_handler_rdmsr_fault(const struct exception_table_entry *fixup,
+				      struct pt_regs *regs, int trapnr,
+				      unsigned long error_code,
+				      unsigned long fault_addr)
+{
+	ex_handler_msr_mce(regs, false);
 	return true;
 }
 
@@ -447,17 +475,7 @@ __visible bool ex_handler_wrmsr_fault(const struct exception_table_entry *fixup,
 				      unsigned long error_code,
 				      unsigned long fault_addr)
 {
-	pr_emerg("MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pS)\n",
-		 (unsigned int)regs->cx, (unsigned int)regs->dx, (unsigned int)regs->ax,
-		  regs->ip, (void *)regs->ip);
-
-	show_stack_regs(regs);
-
-	panic("MCA architectural violation!\n");
-
-	while (true)
-		cpu_relax();
-
+	ex_handler_msr_mce(regs, true);
 	return true;
 }
 
@@ -824,7 +842,7 @@ log_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
@@ -879,7 +897,7 @@ 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;
@@ -957,7 +975,6 @@ static void mce_reign(void)
 	struct mce *m = NULL;
 	int global_worst = 0;
 	char *msg = NULL;
-	char *nmsg = NULL;
 
 	/*
 	 * This CPU is the Monarch and the other CPUs have run
@@ -965,12 +982,10 @@ static void mce_reign(void)
 	 * Grade the severity of the errors of all the CPUs.
 	 */
 	for_each_possible_cpu(cpu) {
-		int severity = mce_severity(&per_cpu(mces_seen, cpu),
-					    mca_cfg.tolerant,
-					    &nmsg, true);
-		if (severity > global_worst) {
-			msg = nmsg;
-			global_worst = severity;
+		struct mce *mtmp = &per_cpu(mces_seen, cpu);
+
+		if (mtmp->severity > global_worst) {
+			global_worst = mtmp->severity;
 			m = &per_cpu(mces_seen, cpu);
 		}
 	}
@@ -980,8 +995,11 @@ 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 && mca_cfg.tolerant < 3) {
+		/* call mce_severity() to get "msg" for panic */
+		mce_severity(m, NULL, mca_cfg.tolerant, &msg, true);
 		mce_panic("Fatal machine check", m, msg);
+	}
 
 	/*
 	 * For UC somewhere we let the CPU who detects it handle it.
@@ -1163,23 +1181,6 @@ static void mce_clear_state(unsigned long *toclear)
 	}
 }
 
-static int do_memory_failure(struct mce *m)
-{
-	int flags = MF_ACTION_REQUIRED;
-	int ret;
-
-	pr_err("Uncorrected hardware memory error in user-access at %llx", m->addr);
-	if (!(m->mcgstatus & MCG_STATUS_RIPV))
-		flags |= MF_MUST_KILL;
-	ret = memory_failure(m->addr >> PAGE_SHIFT, flags);
-	if (ret)
-		pr_err("Memory error not recovered");
-	else
-		set_mce_nospec(m->addr >> PAGE_SHIFT, whole_page(m));
-	return ret;
-}
-
-
 /*
  * Cases where we avoid rendezvous handler timeout:
  * 1) If this CPU is offline.
@@ -1207,7 +1208,7 @@ static bool __mc_check_crashing_cpu(int cpu)
 	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)
 {
@@ -1242,7 +1243,7 @@ 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
@@ -1275,6 +1276,50 @@ static void __mc_scan_banks(struct mce *m, struct mce *final,
 	*m = *final;
 }
 
+static void kill_me_now(struct callback_head *ch)
+{
+	force_sig(SIGBUS);
+}
+
+static void kill_me_maybe(struct callback_head *cb)
+{
+	struct task_struct *p = container_of(cb, struct task_struct, mce_kill_me);
+	int flags = MF_ACTION_REQUIRED;
+
+	pr_err("Uncorrected hardware memory error in user-access at %llx", p->mce_addr);
+
+	if (!p->mce_ripv)
+		flags |= MF_MUST_KILL;
+
+	if (!memory_failure(p->mce_addr >> PAGE_SHIFT, flags) &&
+	    !(p->mce_kflags & MCE_IN_KERNEL_COPYIN)) {
+		set_mce_nospec(p->mce_addr >> PAGE_SHIFT, p->mce_whole_page);
+		return;
+	}
+
+	if (p->mce_vaddr != (void __user *)-1l) {
+		force_sig_mceerr(BUS_MCEERR_AR, p->mce_vaddr, PAGE_SHIFT);
+	} else {
+		pr_err("Memory error not recovered");
+		kill_me_now(cb);
+	}
+}
+
+static void queue_task_work(struct mce *m, int kill_it)
+{
+	current->mce_addr = m->addr;
+	current->mce_kflags = m->kflags;
+	current->mce_ripv = !!(m->mcgstatus & MCG_STATUS_RIPV);
+	current->mce_whole_page = whole_page(m);
+
+	if (kill_it)
+		current->mce_kill_me.func = kill_me_now;
+	else
+		current->mce_kill_me.func = kill_me_maybe;
+
+	task_work_add(current, &current->mce_kill_me, true);
+}
+
 /*
  * The actual machine check handler. This only handles real
  * exceptions when something got corrupted coming in through int 18.
@@ -1286,8 +1331,14 @@ static void __mc_scan_banks(struct mce *m, struct mce *final,
  * On Intel systems this is entered on all CPUs in parallel through
  * MCE broadcast. However some CPUs might be broken beyond repair,
  * so be always careful when synchronizing with others.
+ *
+ * Tracing and kprobes are disabled: if we interrupted a kernel context
+ * with IF=1, we need to minimize stack usage.  There are also recursion
+ * issues: if the machine check was due to a failure of the memory
+ * backing the user stack, tracing that reads the user stack will cause
+ * potentially infinite recursion.
  */
-void do_machine_check(struct pt_regs *regs, long error_code)
+void noinstr do_machine_check(struct pt_regs *regs, long error_code)
 {
 	DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
 	DECLARE_BITMAP(toclear, MAX_NR_BANKS);
@@ -1368,7 +1419,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 		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);
@@ -1392,7 +1443,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 		 * 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);
 		}
 	}
@@ -1418,16 +1469,28 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 
 	/* Fault was in user mode and we need to take some action */
 	if ((m.cs & 3) == 3) {
-		ist_begin_non_atomic(regs);
-		local_irq_enable();
+		/* If this triggers there is no way to recover. Die hard. */
+		BUG_ON(!on_thread_stack() || !user_mode(regs));
+
+		queue_task_work(&m, kill_it);
 
-		if (kill_it || do_memory_failure(&m))
-			force_sig(SIGBUS);
-		local_irq_disable();
-		ist_end_non_atomic();
 	} else {
-		if (!fixup_exception(regs, X86_TRAP_MC, error_code, 0))
-			mce_panic("Failed kernel mode recovery", &m, NULL);
+		/*
+		 * Handle an MCE which has happened in kernel space but from
+		 * which the kernel can recover: ex_has_fault_handler() has
+		 * already verified that the rIP at which the error happened is
+		 * a rIP from which the kernel can recover (by jumping to
+		 * recovery code specified in _ASM_EXTABLE_FAULT()) and the
+		 * corresponding exception handler which would do that is the
+		 * proper one.
+		 */
+		if (m.kflags & MCE_IN_KERNEL_RECOV) {
+			if (!fixup_exception(regs, X86_TRAP_MC, error_code, 0))
+				mce_panic("Failed kernel mode recovery", &m, msg);
+		}
+
+		if (m.kflags & MCE_IN_KERNEL_COPYIN)
+			queue_task_work(&m, kill_it);
 	}
 
 out_ist:
@@ -1916,10 +1979,11 @@ static void unexpected_machine_check(struct pt_regs *regs, long error_code)
 void (*machine_check_vector)(struct pt_regs *, long error_code) =
 						unexpected_machine_check;
 
-dotraplinkage void do_mce(struct pt_regs *regs, long error_code)
+dotraplinkage notrace void do_mce(struct pt_regs *regs, long error_code)
 {
 	machine_check_vector(regs, error_code);
 }
+NOKPROBE_SYMBOL(do_mce);
 
 /*
  * Called for each booted CPU to set up machine checks.