Merge tag 'ras_core_for_v5.16_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull RAS updates from Borislav Petkov:

 - Get rid of a bunch of function pointers used in MCA land in favor of
   normal functions. This is in preparation of making the MCA code
   noinstr-aware

 - When the kernel copies data from user addresses and it encounters a
   machine check, a SIGBUS is sent to that process. Change this action
   to either an -EFAULT which is returned to the user or a short write,
   making the recovery action a lot more user-friendly

* tag 'ras_core_for_v5.16_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mce: Sort mca_config members to get rid of unnecessary padding
  x86/mce: Get rid of the ->quirk_no_way_out() indirect call
  x86/mce: Get rid of msr_ops
  x86/mce: Get rid of machine_check_vector
  x86/mce: Get rid of the mce_severity function pointer
  x86/mce: Drop copyin special case for #MC
  x86/mce: Change to not send SIGBUS error during copy from user

arch/x86/include/asm/mce.h

@@ -205,28 +205,16 @@ struct cper_ia_proc_ctx;
 int mcheck_init(void);
 void mcheck_cpu_init(struct cpuinfo_x86 *c);
 void mcheck_cpu_clear(struct cpuinfo_x86 *c);
-void mcheck_vendor_init_severity(void);
 int apei_smca_report_x86_error(struct cper_ia_proc_ctx *ctx_info,
 			       u64 lapic_id);
 #else
 static inline int mcheck_init(void) { return 0; }
 static inline void mcheck_cpu_init(struct cpuinfo_x86 *c) {}
 static inline void mcheck_cpu_clear(struct cpuinfo_x86 *c) {}
-static inline void mcheck_vendor_init_severity(void) {}
 static inline int apei_smca_report_x86_error(struct cper_ia_proc_ctx *ctx_info,
 					     u64 lapic_id) { return -EINVAL; }
 #endif
 
-#ifdef CONFIG_X86_ANCIENT_MCE
-void intel_p5_mcheck_init(struct cpuinfo_x86 *c);
-void winchip_mcheck_init(struct cpuinfo_x86 *c);
-static inline void enable_p5_mce(void) { mce_p5_enabled = 1; }
-#else
-static inline void intel_p5_mcheck_init(struct cpuinfo_x86 *c) {}
-static inline void winchip_mcheck_init(struct cpuinfo_x86 *c) {}
-static inline void enable_p5_mce(void) {}
-#endif
-
 void mce_setup(struct mce *m);
 void mce_log(struct mce *m);
 DECLARE_PER_CPU(struct device *, mce_device);

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

@@ -526,7 +526,7 @@ static u32 get_block_address(u32 current_addr, u32 low, u32 high,
 	/* Fall back to method we used for older processors: */
 	switch (block) {
 	case 0:
-		addr = msr_ops.misc(bank);
+		addr = mca_msr_reg(bank, MCA_MISC);
 		break;
 	case 1:
 		offset = ((low & MASK_BLKPTR_LO) >> 21);
@@ -978,8 +978,8 @@ static void log_error_deferred(unsigned int bank)
 {
 	bool defrd;
 
-	defrd = _log_error_bank(bank, msr_ops.status(bank),
-					msr_ops.addr(bank), 0);
+	defrd = _log_error_bank(bank, mca_msr_reg(bank, MCA_STATUS),
+				mca_msr_reg(bank, MCA_ADDR), 0);
 
 	if (!mce_flags.smca)
 		return;
@@ -1009,7 +1009,7 @@ static void amd_deferred_error_interrupt(void)
 
 static void log_error_thresholding(unsigned int bank, u64 misc)
 {
-	_log_error_bank(bank, msr_ops.status(bank), msr_ops.addr(bank), misc);
+	_log_error_bank(bank, mca_msr_reg(bank, MCA_STATUS), mca_msr_reg(bank, MCA_ADDR), misc);
 }
 
 static void log_and_reset_block(struct threshold_block *block)
@@ -1397,7 +1397,7 @@ static int threshold_create_bank(struct threshold_bank **bp, unsigned int cpu,
 		}
 	}
 
-	err = allocate_threshold_blocks(cpu, b, bank, 0, msr_ops.misc(bank));
+	err = allocate_threshold_blocks(cpu, b, bank, 0, mca_msr_reg(bank, MCA_MISC));
 	if (err)
 		goto out_kobj;
 

arch/x86/kernel/cpu/mce/internal.h

@@ -8,9 +8,6 @@
 #include <linux/device.h>
 #include <asm/mce.h>
 
-/* Pointer to the installed machine check handler for this CPU setup. */
-extern void (*machine_check_vector)(struct pt_regs *);
-
 enum severity_level {
 	MCE_NO_SEVERITY,
 	MCE_DEFERRED_SEVERITY,
@@ -38,8 +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);
 
-extern 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, int tolerant, char **msg, bool is_excp);
 struct dentry *mce_get_debugfs_dir(void);
 
 extern mce_banks_t mce_banks_ce_disabled;
@@ -117,23 +113,25 @@ static inline void mce_unregister_injector_chain(struct notifier_block *nb)	{ }
 #endif
 
 struct mca_config {
-	bool dont_log_ce;
-	bool cmci_disabled;
-	bool ignore_ce;
-	bool print_all;
-
 	__u64 lmce_disabled		: 1,
 	      disabled			: 1,
 	      ser			: 1,
 	      recovery			: 1,
 	      bios_cmci_threshold	: 1,
-	      __reserved		: 59;
+	      /* Proper #MC exception handler is set */
+	      initialized		: 1,
+	      __reserved		: 58;
+
+	bool dont_log_ce;
+	bool cmci_disabled;
+	bool ignore_ce;
+	bool print_all;
 
-	s8 bootlog;
 	int tolerant;
 	int monarch_timeout;
 	int panic_timeout;
 	u32 rip_msr;
+	s8 bootlog;
 };
 
 extern struct mca_config mca_cfg;
@@ -163,19 +161,28 @@ struct mce_vendor_flags {
 	/* AMD-style error thresholding banks present. */
 	amd_threshold		: 1,
 
-	__reserved_0		: 60;
+	/* Pentium, family 5-style MCA */
+	p5			: 1,
+
+	/* Centaur Winchip C6-style MCA */
+	winchip			: 1,
+
+	/* SandyBridge IFU quirk */
+	snb_ifu_quirk		: 1,
+
+	__reserved_0		: 57;
 };
 
 extern struct mce_vendor_flags mce_flags;
 
-struct mca_msr_regs {
-	u32 (*ctl)	(int bank);
-	u32 (*status)	(int bank);
-	u32 (*addr)	(int bank);
-	u32 (*misc)	(int bank);
+enum mca_msr {
+	MCA_CTL,
+	MCA_STATUS,
+	MCA_ADDR,
+	MCA_MISC,
 };
 
-extern struct mca_msr_regs msr_ops;
+u32 mca_msr_reg(int bank, enum mca_msr reg);
 
 /* Decide whether to add MCE record to MCE event pool or filter it out. */
 extern bool filter_mce(struct mce *m);
@@ -186,4 +193,18 @@ extern bool amd_filter_mce(struct mce *m);
 static inline bool amd_filter_mce(struct mce *m) { return false; }
 #endif
 
+#ifdef CONFIG_X86_ANCIENT_MCE
+void intel_p5_mcheck_init(struct cpuinfo_x86 *c);
+void winchip_mcheck_init(struct cpuinfo_x86 *c);
+noinstr void pentium_machine_check(struct pt_regs *regs);
+noinstr void winchip_machine_check(struct pt_regs *regs);
+static inline void enable_p5_mce(void) { mce_p5_enabled = 1; }
+#else
+static inline void intel_p5_mcheck_init(struct cpuinfo_x86 *c) {}
+static inline void winchip_mcheck_init(struct cpuinfo_x86 *c) {}
+static inline void enable_p5_mce(void) {}
+static inline void pentium_machine_check(struct pt_regs *regs) {}
+static inline void winchip_machine_check(struct pt_regs *regs) {}
+#endif
+
 #endif /* __X86_MCE_INTERNAL_H__ */

arch/x86/kernel/cpu/mce/p5.c

@@ -21,7 +21,7 @@
 int mce_p5_enabled __read_mostly;
 
 /* Machine check handler for Pentium class Intel CPUs: */
-static noinstr void pentium_machine_check(struct pt_regs *regs)
+noinstr void pentium_machine_check(struct pt_regs *regs)
 {
 	u32 loaddr, hi, lotype;
 
@@ -54,10 +54,6 @@ void intel_p5_mcheck_init(struct cpuinfo_x86 *c)
 	if (!cpu_has(c, X86_FEATURE_MCE))
 		return;
 
-	machine_check_vector = pentium_machine_check;
-	/* Make sure the vector pointer is visible before we enable MCEs: */
-	wmb();
-
 	/* Read registers before enabling: */
 	rdmsr(MSR_IA32_P5_MC_ADDR, l, h);
 	rdmsr(MSR_IA32_P5_MC_TYPE, l, h);

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

@@ -407,15 +407,14 @@ static int mce_severity_intel(struct mce *m, struct pt_regs *regs,
 	}
 }
 
-/* Default to mce_severity_intel */
-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)
+int mce_severity(struct mce *m, struct pt_regs *regs, int tolerant, char **msg,
+		 bool is_excp)
 {
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
 	    boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
-		mce_severity = mce_severity_amd;
+		return mce_severity_amd(m, regs, tolerant, msg, is_excp);
+	else
+		return mce_severity_intel(m, regs, tolerant, msg, is_excp);
 }
 
 #ifdef CONFIG_DEBUG_FS

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

@@ -17,7 +17,7 @@
 #include "internal.h"
 
 /* Machine check handler for WinChip C6: */
-static noinstr void winchip_machine_check(struct pt_regs *regs)
+noinstr void winchip_machine_check(struct pt_regs *regs)
 {
 	instrumentation_begin();
 	pr_emerg("CPU0: Machine Check Exception.\n");
@@ -30,10 +30,6 @@ void winchip_mcheck_init(struct cpuinfo_x86 *c)
 {
 	u32 lo, hi;
 
-	machine_check_vector = winchip_machine_check;
-	/* Make sure the vector pointer is visible before we enable MCEs: */
-	wmb();
-
 	rdmsr(MSR_IDT_FCR1, lo, hi);
 	lo |= (1<<2);	/* Enable EIERRINT (int 18 MCE) */
 	lo &= ~(1<<4);	/* Enable MCE */

arch/x86/lib/copy_user_64.S

@@ -234,24 +234,11 @@ EXPORT_SYMBOL(copy_user_enhanced_fast_string)
  */
 SYM_CODE_START_LOCAL(.Lcopy_user_handle_tail)
 	movl %edx,%ecx
-	cmp $X86_TRAP_MC,%eax		/* check if X86_TRAP_MC */
-	je 3f
 1:	rep movsb
 2:	mov %ecx,%eax
 	ASM_CLAC
 	ret
 
-	/*
-	 * Return zero to pretend that this copy succeeded. This
-	 * is counter-intuitive, but needed to prevent the code
-	 * in lib/iov_iter.c from retrying and running back into
-	 * the poison cache line again. The machine check handler
-	 * will ensure that a SIGBUS is sent to the task.
-	 */
-3:	xorl %eax,%eax
-	ASM_CLAC
-	ret
-
 	_ASM_EXTABLE_CPY(1b, 2b)
 SYM_CODE_END(.Lcopy_user_handle_tail)