Merge tag 'ras_core_for_v5.19_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 RAS updates from Borislav Petkov:

 - Simplification of the AMD MCE error severity grading logic along with
   supplying critical panic MCEs with accompanying error messages for
   more human-friendly diagnostics.

 - Misc fixes

* tag 'ras_core_for_v5.19_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mce: Add messages for panic errors in AMD's MCE grading
  x86/mce: Simplify AMD severity grading logic
  x86/MCE/AMD: Fix memory leak when threshold_create_bank() fails
  x86/mce: Avoid unnecessary padding in struct mce_bank

Author: torvalds

arch/x86/kernel/cpu/mce/amd.c

@@ -1294,10 +1294,23 @@ static void threshold_remove_bank(struct threshold_bank *bank)
 	kfree(bank);
 }
 
+static void __threshold_remove_device(struct threshold_bank **bp)
+{
+	unsigned int bank, numbanks = this_cpu_read(mce_num_banks);
+
+	for (bank = 0; bank < numbanks; bank++) {
+		if (!bp[bank])
+			continue;
+
+		threshold_remove_bank(bp[bank]);
+		bp[bank] = NULL;
+	}
+	kfree(bp);
+}
+
 int mce_threshold_remove_device(unsigned int cpu)
 {
 	struct threshold_bank **bp = this_cpu_read(threshold_banks);
-	unsigned int bank, numbanks = this_cpu_read(mce_num_banks);
 
 	if (!bp)
 		return 0;
@@ -1308,13 +1321,7 @@ int mce_threshold_remove_device(unsigned int cpu)
 	 */
 	this_cpu_write(threshold_banks, NULL);
 
-	for (bank = 0; bank < numbanks; bank++) {
-		if (bp[bank]) {
-			threshold_remove_bank(bp[bank]);
-			bp[bank] = NULL;
-		}
-	}
-	kfree(bp);
+	__threshold_remove_device(bp);
 	return 0;
 }
 
@@ -1351,15 +1358,14 @@ int mce_threshold_create_device(unsigned int cpu)
 		if (!(this_cpu_read(bank_map) & (1 << bank)))
 			continue;
 		err = threshold_create_bank(bp, cpu, bank);
-		if (err)
-			goto out_err;
+		if (err) {
+			__threshold_remove_device(bp);
+			return err;
+		}
 	}
 	this_cpu_write(threshold_banks, bp);
 
 	if (thresholding_irq_en)
 		mce_threshold_vector = amd_threshold_interrupt;
 	return 0;
-out_err:
-	mce_threshold_remove_device(cpu);
-	return err;
 }

arch/x86/kernel/cpu/mce/core.c

@@ -69,7 +69,9 @@ DEFINE_PER_CPU_READ_MOSTLY(unsigned int, mce_num_banks);
 
 struct mce_bank {
 	u64			ctl;			/* subevents to enable */
-	bool			init;			/* initialise bank? */
+
+	__u64 init			: 1,		/* initialise bank? */
+	      __reserved_1		: 63;
 };
 static DEFINE_PER_CPU_READ_MOSTLY(struct mce_bank[MAX_NR_BANKS], mce_banks_array);
 

arch/x86/kernel/cpu/mce/severity.c

@@ -301,85 +301,65 @@ static noinstr int error_context(struct mce *m, struct pt_regs *regs)
 	}
 }
 
-static __always_inline int mce_severity_amd_smca(struct mce *m, enum context err_ctx)
+/* See AMD PPR(s) section Machine Check Error Handling. */
+static noinstr int mce_severity_amd(struct mce *m, struct pt_regs *regs, char **msg, bool is_excp)
 {
-	u64 mcx_cfg;
+	char *panic_msg = NULL;
+	int ret;
 
 	/*
-	 * We need to look at the following bits:
-	 * - "succor" bit (data poisoning support), and
-	 * - TCC bit (Task Context Corrupt)
-	 * in MCi_STATUS to determine error severity.
+	 * Default return value: Action required, the error must be handled
+	 * immediately.
 	 */
-	if (!mce_flags.succor)
-		return MCE_PANIC_SEVERITY;
-
-	mcx_cfg = mce_rdmsrl(MSR_AMD64_SMCA_MCx_CONFIG(m->bank));
-
-	/* TCC (Task context corrupt). If set and if IN_KERNEL, panic. */
-	if ((mcx_cfg & MCI_CONFIG_MCAX) &&
-	    (m->status & MCI_STATUS_TCC) &&
-	    (err_ctx == IN_KERNEL))
-		return MCE_PANIC_SEVERITY;
-
-	 /* ...otherwise invoke hwpoison handler. */
-	return MCE_AR_SEVERITY;
-}
-
-/*
- * 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, char **msg, bool is_excp)
-{
-	enum context ctx = error_context(m, regs);
+	ret = MCE_AR_SEVERITY;
 
 	/* Processor Context Corrupt, no need to fumble too much, die! */
-	if (m->status & MCI_STATUS_PCC)
-		return MCE_PANIC_SEVERITY;
-
-	if (m->status & MCI_STATUS_UC) {
-
-		if (ctx == IN_KERNEL)
-			return MCE_PANIC_SEVERITY;
+	if (m->status & MCI_STATUS_PCC) {
+		panic_msg = "Processor Context Corrupt";
+		ret = MCE_PANIC_SEVERITY;
+		goto out;
+	}
 
-		/*
-		 * On older systems where overflow_recov flag is not present, we
-		 * should simply panic if an error overflow occurs. If
-		 * overflow_recov flag is present and set, then software can try
-		 * to at least kill process to prolong system operation.
-		 */
-		if (mce_flags.overflow_recov) {
-			if (mce_flags.smca)
-				return mce_severity_amd_smca(m, ctx);
-
-			/* kill current process */
-			return MCE_AR_SEVERITY;
-		} else {
-			/* at least one error was not logged */
-			if (m->status & MCI_STATUS_OVER)
-				return MCE_PANIC_SEVERITY;
-		}
-
-		/*
-		 * For any other case, return MCE_UC_SEVERITY so that we log the
-		 * error and exit #MC handler.
-		 */
-		return MCE_UC_SEVERITY;
+	if (m->status & MCI_STATUS_DEFERRED) {
+		ret = MCE_DEFERRED_SEVERITY;
+		goto out;
 	}
 
 	/*
-	 * deferred error: poll handler catches these and adds to mce_ring so
-	 * memory-failure can take recovery actions.
+	 * If the UC bit is not set, the system either corrected or deferred
+	 * the error. No action will be required after logging the error.
 	 */
-	if (m->status & MCI_STATUS_DEFERRED)
-		return MCE_DEFERRED_SEVERITY;
+	if (!(m->status & MCI_STATUS_UC)) {
+		ret = MCE_KEEP_SEVERITY;
+		goto out;
+	}
 
 	/*
-	 * corrected error: poll handler catches these and passes responsibility
-	 * of decoding the error to EDAC
+	 * On MCA overflow, without the MCA overflow recovery feature the
+	 * system will not be able to recover, panic.
 	 */
-	return MCE_KEEP_SEVERITY;
+	if ((m->status & MCI_STATUS_OVER) && !mce_flags.overflow_recov) {
+		panic_msg = "Overflowed uncorrected error without MCA Overflow Recovery";
+		ret = MCE_PANIC_SEVERITY;
+		goto out;
+	}
+
+	if (!mce_flags.succor) {
+		panic_msg = "Uncorrected error without MCA Recovery";
+		ret = MCE_PANIC_SEVERITY;
+		goto out;
+	}
+
+	if (error_context(m, regs) == IN_KERNEL) {
+		panic_msg = "Uncorrected unrecoverable error in kernel context";
+		ret = MCE_PANIC_SEVERITY;
+	}
+
+out:
+	if (msg && panic_msg)
+		*msg = panic_msg;
+
+	return ret;
 }
 
 static noinstr int mce_severity_intel(struct mce *m, struct pt_regs *regs, char **msg, bool is_excp)