- 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
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEzv7L6UO9uDPlPSfHEsHwGGHeVUoFAmF/s8sACgkQEsHwGGHe
 VUqnaQ/8DIHkIOF6vy2w56snJwCj0XQYNLO+Clf6sHJ7ukWpWDoAi6HzvjqrBmaa
 bQEdOLeO92wGtVutCQ5ndzq2SJ6UFcZtOulpHyzCpwNinhY2QMsPG6pkSzeaAy/e
 aR4gpTY6pyCJyWl5DXXr7FMzBZVaWYdtZ2szPKmW1d1mLeDIdv5d3hInDbZ48XJF
 o+fZx0uuK0CIuDjDujRNvkPbHXLbBSqSLCTRf66o+sCY5ZXHlAipabxa3UmhHKvd
 dBxMrlObAaDBmDjqpc/YpS4IfWZb7+rHQfVmiq5O85ExXx6cyF6vlM7GI/5VBxSA
 2dVcZX/3TsSqGbFdVygbcF6e/Yl1xhP5AE+pBb5jpzbzEaf4oiM8MDhoMAai3lEL
 7CFsXL2oyAzho7QQsUSkv/hffHHrph2/aUZbGJlz6SdeRF9aoIjZANpcwm44TZrk
 c11Fh1MLTDxx8uhCGrYFXqR8QgeTi4B+8d/CEXNJnkLXZMfSUtoL1iIzhBpsGkv3
 r0JOIG2o5dGX2lLhQOiHZ+us33O1e8mvOli9P1jLoDttoKvNqSqLUuwpBCz4sc0E
 ugfarf7v/R07NN+7SIT+O83ZG8dXxIRPzHm/g7wjZYgyOfEBgFSMBKVWXRotPo/f
 aY88sDVyvF5sbYnUcA6zZANBCKAVfilqdMgCyaoGegoNGzDOCYE=
 =bIZq
 -----END PGP SIGNATURE-----

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),
+	defrd = _log_error_bank(bank, mca_msr_reg(bank, MCA_STATUS),
-					msr_ops.addr(bank), 0);
+				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/core.c

@@ -121,8 +121,6 @@ mce_banks_t mce_banks_ce_disabled;
 static struct work_struct mce_work;
 static struct irq_work mce_irq_work;
 
-static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs);
-
 /*
  * CPU/chipset specific EDAC code can register a notifier call here to print
  * MCE errors in a human-readable form.
@@ -176,53 +174,27 @@ void mce_unregister_decode_chain(struct notifier_block *nb)
 }
 EXPORT_SYMBOL_GPL(mce_unregister_decode_chain);
 
-static inline u32 ctl_reg(int bank)
+u32 mca_msr_reg(int bank, enum mca_msr reg)
 {
-	return MSR_IA32_MCx_CTL(bank);
+	if (mce_flags.smca) {
-}
+		switch (reg) {
+		case MCA_CTL:	 return MSR_AMD64_SMCA_MCx_CTL(bank);
+		case MCA_ADDR:	 return MSR_AMD64_SMCA_MCx_ADDR(bank);
+		case MCA_MISC:	 return MSR_AMD64_SMCA_MCx_MISC(bank);
+		case MCA_STATUS: return MSR_AMD64_SMCA_MCx_STATUS(bank);
+		}
+	}
 
-static inline u32 status_reg(int bank)
+	switch (reg) {
-{
+	case MCA_CTL:	 return MSR_IA32_MCx_CTL(bank);
-	return MSR_IA32_MCx_STATUS(bank);
+	case MCA_ADDR:	 return MSR_IA32_MCx_ADDR(bank);
-}
+	case MCA_MISC:	 return MSR_IA32_MCx_MISC(bank);
+	case MCA_STATUS: return MSR_IA32_MCx_STATUS(bank);
+	}
 
-static inline u32 addr_reg(int bank)
+	return 0;
-{
-	return MSR_IA32_MCx_ADDR(bank);
 }
 
-static inline u32 misc_reg(int bank)
-{
-	return MSR_IA32_MCx_MISC(bank);
-}
-
-static inline u32 smca_ctl_reg(int bank)
-{
-	return MSR_AMD64_SMCA_MCx_CTL(bank);
-}
-
-static inline u32 smca_status_reg(int bank)
-{
-	return MSR_AMD64_SMCA_MCx_STATUS(bank);
-}
-
-static inline u32 smca_addr_reg(int bank)
-{
-	return MSR_AMD64_SMCA_MCx_ADDR(bank);
-}
-
-static inline u32 smca_misc_reg(int bank)
-{
-	return MSR_AMD64_SMCA_MCx_MISC(bank);
-}
-
-struct mca_msr_regs msr_ops = {
-	.ctl	= ctl_reg,
-	.status	= status_reg,
-	.addr	= addr_reg,
-	.misc	= misc_reg
-};
-
 static void __print_mce(struct mce *m)
 {
 	pr_emerg(HW_ERR "CPU %d: Machine Check%s: %Lx Bank %d: %016Lx\n",
@@ -362,11 +334,11 @@ static int msr_to_offset(u32 msr)
 
 	if (msr == mca_cfg.rip_msr)
 		return offsetof(struct mce, ip);
-	if (msr == msr_ops.status(bank))
+	if (msr == mca_msr_reg(bank, MCA_STATUS))
 		return offsetof(struct mce, status);
-	if (msr == msr_ops.addr(bank))
+	if (msr == mca_msr_reg(bank, MCA_ADDR))
 		return offsetof(struct mce, addr);
-	if (msr == msr_ops.misc(bank))
+	if (msr == mca_msr_reg(bank, MCA_MISC))
 		return offsetof(struct mce, misc);
 	if (msr == MSR_IA32_MCG_STATUS)
 		return offsetof(struct mce, mcgstatus);
@@ -667,10 +639,10 @@ static struct notifier_block mce_default_nb = {
 static void mce_read_aux(struct mce *m, int i)
 {
 	if (m->status & MCI_STATUS_MISCV)
-		m->misc = mce_rdmsrl(msr_ops.misc(i));
+		m->misc = mce_rdmsrl(mca_msr_reg(i, MCA_MISC));
 
 	if (m->status & MCI_STATUS_ADDRV) {
-		m->addr = mce_rdmsrl(msr_ops.addr(i));
+		m->addr = mce_rdmsrl(mca_msr_reg(i, MCA_ADDR));
 
 		/*
 		 * Mask the reported address by the reported granularity.
@@ -740,7 +712,7 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 		m.bank = i;
 
 		barrier();
-		m.status = mce_rdmsrl(msr_ops.status(i));
+		m.status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS));
 
 		/* If this entry is not valid, ignore it */
 		if (!(m.status & MCI_STATUS_VAL))
@@ -808,7 +780,7 @@ clear_it:
 		/*
 		 * Clear state for this bank.
 		 */
-		mce_wrmsrl(msr_ops.status(i), 0);
+		mce_wrmsrl(mca_msr_reg(i, MCA_STATUS), 0);
 	}
 
 	/*
@@ -822,6 +794,34 @@ clear_it:
 }
 EXPORT_SYMBOL_GPL(machine_check_poll);
 
+/*
+ * During IFU recovery Sandy Bridge -EP4S processors set the RIPV and
+ * EIPV bits in MCG_STATUS to zero on the affected logical processor (SDM
+ * Vol 3B Table 15-20). But this confuses both the code that determines
+ * whether the machine check occurred in kernel or user mode, and also
+ * the severity assessment code. Pretend that EIPV was set, and take the
+ * ip/cs values from the pt_regs that mce_gather_info() ignored earlier.
+ */
+static void quirk_sandybridge_ifu(int bank, struct mce *m, struct pt_regs *regs)
+{
+	if (bank != 0)
+		return;
+	if ((m->mcgstatus & (MCG_STATUS_EIPV|MCG_STATUS_RIPV)) != 0)
+		return;
+	if ((m->status & (MCI_STATUS_OVER|MCI_STATUS_UC|
+		          MCI_STATUS_EN|MCI_STATUS_MISCV|MCI_STATUS_ADDRV|
+			  MCI_STATUS_PCC|MCI_STATUS_S|MCI_STATUS_AR|
+			  MCACOD)) !=
+			 (MCI_STATUS_UC|MCI_STATUS_EN|
+			  MCI_STATUS_MISCV|MCI_STATUS_ADDRV|MCI_STATUS_S|
+			  MCI_STATUS_AR|MCACOD_INSTR))
+		return;
+
+	m->mcgstatus |= MCG_STATUS_EIPV;
+	m->ip = regs->ip;
+	m->cs = regs->cs;
+}
+
 /*
  * Do a quick check if any of the events requires a panic.
  * This decides if we keep the events around or clear them.
@@ -833,13 +833,13 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
 	int i;
 
 	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
-		m->status = mce_rdmsrl(msr_ops.status(i));
+		m->status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS));
 		if (!(m->status & MCI_STATUS_VAL))
 			continue;
 
 		__set_bit(i, validp);
-		if (quirk_no_way_out)
+		if (mce_flags.snb_ifu_quirk)
-			quirk_no_way_out(i, m, regs);
+			quirk_sandybridge_ifu(i, m, regs);
 
 		m->bank = i;
 		if (mce_severity(m, regs, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) {
@@ -1126,7 +1126,7 @@ static void mce_clear_state(unsigned long *toclear)
 
 	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
 		if (test_bit(i, toclear))
-			mce_wrmsrl(msr_ops.status(i), 0);
+			mce_wrmsrl(mca_msr_reg(i, MCA_STATUS), 0);
 	}
 }
 
@@ -1185,7 +1185,7 @@ static void __mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *fin
 		m->addr = 0;
 		m->bank = i;
 
-		m->status = mce_rdmsrl(msr_ops.status(i));
+		m->status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS));
 		if (!(m->status & MCI_STATUS_VAL))
 			continue;
 
@@ -1254,7 +1254,7 @@ static void kill_me_maybe(struct callback_head *cb)
 		flags |= MF_MUST_KILL;
 
 	ret = memory_failure(p->mce_addr >> PAGE_SHIFT, flags);
-	if (!ret && !(p->mce_kflags & MCE_IN_KERNEL_COPYIN)) {
+	if (!ret) {
 		set_mce_nospec(p->mce_addr >> PAGE_SHIFT, p->mce_whole_page);
 		sync_core();
 		return;
@@ -1268,15 +1268,21 @@ static void kill_me_maybe(struct callback_head *cb)
 	if (ret == -EHWPOISON)
 		return;
 
-	if (p->mce_vaddr != (void __user *)-1l) {
+	pr_err("Memory error not recovered");
-		force_sig_mceerr(BUS_MCEERR_AR, p->mce_vaddr, PAGE_SHIFT);
+	kill_me_now(cb);
-	} else {
-		pr_err("Memory error not recovered");
-		kill_me_now(cb);
-	}
 }
 
-static void queue_task_work(struct mce *m, char *msg, int kill_current_task)
+static void kill_me_never(struct callback_head *cb)
+{
+	struct task_struct *p = container_of(cb, struct task_struct, mce_kill_me);
+
+	p->mce_count = 0;
+	pr_err("Kernel accessed poison in user space at %llx\n", p->mce_addr);
+	if (!memory_failure(p->mce_addr >> PAGE_SHIFT, 0))
+		set_mce_nospec(p->mce_addr >> PAGE_SHIFT, p->mce_whole_page);
+}
+
+static void queue_task_work(struct mce *m, char *msg, void (*func)(struct callback_head *))
 {
 	int count = ++current->mce_count;
 
@@ -1286,11 +1292,7 @@ static void queue_task_work(struct mce *m, char *msg, int kill_current_task)
 		current->mce_kflags = m->kflags;
 		current->mce_ripv = !!(m->mcgstatus & MCG_STATUS_RIPV);
 		current->mce_whole_page = whole_page(m);
-
+		current->mce_kill_me.func = func;
-		if (kill_current_task)
-			current->mce_kill_me.func = kill_me_now;
-		else
-			current->mce_kill_me.func = kill_me_maybe;
 	}
 
 	/* Ten is likely overkill. Don't expect more than two faults before task_work() */
@@ -1308,6 +1310,15 @@ static void queue_task_work(struct mce *m, char *msg, int kill_current_task)
 	task_work_add(current, &current->mce_kill_me, TWA_RESUME);
 }
 
+/* Handle unconfigured int18 (should never happen) */
+static noinstr void unexpected_machine_check(struct pt_regs *regs)
+{
+	instrumentation_begin();
+	pr_err("CPU#%d: Unexpected int18 (Machine Check)\n",
+	       smp_processor_id());
+	instrumentation_end();
+}
+
 /*
  * The actual machine check handler. This only handles real
  * exceptions when something got corrupted coming in through int 18.
@@ -1328,36 +1339,43 @@ static void queue_task_work(struct mce *m, char *msg, int kill_current_task)
  */
 noinstr void do_machine_check(struct pt_regs *regs)
 {
+	int worst = 0, order, no_way_out, kill_current_task, lmce;
 	DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
 	DECLARE_BITMAP(toclear, MAX_NR_BANKS);
 	struct mca_config *cfg = &mca_cfg;
 	struct mce m, *final;
 	char *msg = NULL;
-	int worst = 0;
+
+	if (unlikely(mce_flags.p5))
+		return pentium_machine_check(regs);
+	else if (unlikely(mce_flags.winchip))
+		return winchip_machine_check(regs);
+	else if (unlikely(!mca_cfg.initialized))
+		return unexpected_machine_check(regs);
 
 	/*
 	 * Establish sequential order between the CPUs entering the machine
 	 * check handler.
 	 */
-	int order = -1;
+	order = -1;
 
 	/*
 	 * 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.
 	 */
-	int no_way_out = 0;
+	no_way_out = 0;
 
 	/*
 	 * If kill_current_task is not set, there might be a way to recover from this
 	 * error.
 	 */
-	int kill_current_task = 0;
+	kill_current_task = 0;
 
 	/*
 	 * MCEs are always local on AMD. Same is determined by MCG_STATUS_LMCES
 	 * on Intel.
 	 */
-	int lmce = 1;
+	lmce = 1;
 
 	this_cpu_inc(mce_exception_count);
 
@@ -1441,7 +1459,10 @@ noinstr void do_machine_check(struct pt_regs *regs)
 		/* If this triggers there is no way to recover. Die hard. */
 		BUG_ON(!on_thread_stack() || !user_mode(regs));
 
-		queue_task_work(&m, msg, kill_current_task);
+		if (kill_current_task)
+			queue_task_work(&m, msg, kill_me_now);
+		else
+			queue_task_work(&m, msg, kill_me_maybe);
 
 	} else {
 		/*
@@ -1459,7 +1480,7 @@ noinstr void do_machine_check(struct pt_regs *regs)
 		}
 
 		if (m.kflags & MCE_IN_KERNEL_COPYIN)
-			queue_task_work(&m, msg, kill_current_task);
+			queue_task_work(&m, msg, kill_me_never);
 	}
 out:
 	mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
@@ -1669,8 +1690,8 @@ static void __mcheck_cpu_init_clear_banks(void)
 
 		if (!b->init)
 			continue;
-		wrmsrl(msr_ops.ctl(i), b->ctl);
+		wrmsrl(mca_msr_reg(i, MCA_CTL), b->ctl);
-		wrmsrl(msr_ops.status(i), 0);
+		wrmsrl(mca_msr_reg(i, MCA_STATUS), 0);
 	}
 }
 
@@ -1696,39 +1717,11 @@ static void __mcheck_cpu_check_banks(void)
 		if (!b->init)
 			continue;
 
-		rdmsrl(msr_ops.ctl(i), msrval);
+		rdmsrl(mca_msr_reg(i, MCA_CTL), msrval);
 		b->init = !!msrval;
 	}
 }
 
-/*
- * During IFU recovery Sandy Bridge -EP4S processors set the RIPV and
- * EIPV bits in MCG_STATUS to zero on the affected logical processor (SDM
- * Vol 3B Table 15-20). But this confuses both the code that determines
- * whether the machine check occurred in kernel or user mode, and also
- * the severity assessment code. Pretend that EIPV was set, and take the
- * ip/cs values from the pt_regs that mce_gather_info() ignored earlier.
- */
-static void quirk_sandybridge_ifu(int bank, struct mce *m, struct pt_regs *regs)
-{
-	if (bank != 0)
-		return;
-	if ((m->mcgstatus & (MCG_STATUS_EIPV|MCG_STATUS_RIPV)) != 0)
-		return;
-	if ((m->status & (MCI_STATUS_OVER|MCI_STATUS_UC|
-		          MCI_STATUS_EN|MCI_STATUS_MISCV|MCI_STATUS_ADDRV|
-			  MCI_STATUS_PCC|MCI_STATUS_S|MCI_STATUS_AR|
-			  MCACOD)) !=
-			 (MCI_STATUS_UC|MCI_STATUS_EN|
-			  MCI_STATUS_MISCV|MCI_STATUS_ADDRV|MCI_STATUS_S|
-			  MCI_STATUS_AR|MCACOD_INSTR))
-		return;
-
-	m->mcgstatus |= MCG_STATUS_EIPV;
-	m->ip = regs->ip;
-	m->cs = regs->cs;
-}
-
 /* Add per CPU specific workarounds here */
 static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
 {
@@ -1802,7 +1795,7 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
 			cfg->bootlog = 0;
 
 		if (c->x86 == 6 && c->x86_model == 45)
-			quirk_no_way_out = quirk_sandybridge_ifu;
+			mce_flags.snb_ifu_quirk = 1;
 	}
 
 	if (c->x86_vendor == X86_VENDOR_ZHAOXIN) {
@@ -1832,9 +1825,11 @@ static int __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c)
 	switch (c->x86_vendor) {
 	case X86_VENDOR_INTEL:
 		intel_p5_mcheck_init(c);
+		mce_flags.p5 = 1;
 		return 1;
 	case X86_VENDOR_CENTAUR:
 		winchip_mcheck_init(c);
+		mce_flags.winchip = 1;
 		return 1;
 	default:
 		return 0;
@@ -1853,13 +1848,6 @@ static void __mcheck_cpu_init_early(struct cpuinfo_x86 *c)
 		mce_flags.succor	 = !!cpu_has(c, X86_FEATURE_SUCCOR);
 		mce_flags.smca		 = !!cpu_has(c, X86_FEATURE_SMCA);
 		mce_flags.amd_threshold	 = 1;
-
-		if (mce_flags.smca) {
-			msr_ops.ctl	= smca_ctl_reg;
-			msr_ops.status	= smca_status_reg;
-			msr_ops.addr	= smca_addr_reg;
-			msr_ops.misc	= smca_misc_reg;
-		}
 	}
 }
 
@@ -1989,18 +1977,6 @@ bool filter_mce(struct mce *m)
 	return false;
 }
 
-/* Handle unconfigured int18 (should never happen) */
-static noinstr void unexpected_machine_check(struct pt_regs *regs)
-{
-	instrumentation_begin();
-	pr_err("CPU#%d: Unexpected int18 (Machine Check)\n",
-	       smp_processor_id());
-	instrumentation_end();
-}
-
-/* Call the installed machine check handler for this CPU setup. */
-void (*machine_check_vector)(struct pt_regs *) = unexpected_machine_check;
-
 static __always_inline void exc_machine_check_kernel(struct pt_regs *regs)
 {
 	irqentry_state_t irq_state;
@@ -2011,31 +1987,22 @@ static __always_inline void exc_machine_check_kernel(struct pt_regs *regs)
 	 * Only required when from kernel mode. See
 	 * mce_check_crashing_cpu() for details.
 	 */
-	if (machine_check_vector == do_machine_check &&
+	if (mca_cfg.initialized && mce_check_crashing_cpu())
-	    mce_check_crashing_cpu())
 		return;
 
 	irq_state = irqentry_nmi_enter(regs);
-	/*
-	 * The call targets are marked noinstr, but objtool can't figure
-	 * that out because it's an indirect call. Annotate it.
-	 */
-	instrumentation_begin();
 
-	machine_check_vector(regs);
+	do_machine_check(regs);
 
-	instrumentation_end();
 	irqentry_nmi_exit(regs, irq_state);
 }
 
 static __always_inline void exc_machine_check_user(struct pt_regs *regs)
 {
 	irqentry_enter_from_user_mode(regs);
-	instrumentation_begin();
 
-	machine_check_vector(regs);
+	do_machine_check(regs);
 
-	instrumentation_end();
 	irqentry_exit_to_user_mode(regs);
 }
 
@@ -2102,7 +2069,7 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
 		return;
 	}
 
-	machine_check_vector = do_machine_check;
+	mca_cfg.initialized = 1;
 
 	__mcheck_cpu_init_early(c);
 	__mcheck_cpu_init_generic();
@@ -2210,7 +2177,6 @@ int __init mcheck_init(void)
 	mce_register_decode_chain(&early_nb);
 	mce_register_decode_chain(&mce_uc_nb);
 	mce_register_decode_chain(&mce_default_nb);
-	mcheck_vendor_init_severity();
 
 	INIT_WORK(&mce_work, mce_gen_pool_process);
 	init_irq_work(&mce_irq_work, mce_irq_work_cb);
@@ -2235,7 +2201,7 @@ static void mce_disable_error_reporting(void)
 		struct mce_bank *b = &mce_banks[i];
 
 		if (b->init)
-			wrmsrl(msr_ops.ctl(i), 0);
+			wrmsrl(mca_msr_reg(i, MCA_CTL), 0);
 	}
 	return;
 }
@@ -2587,7 +2553,7 @@ static void mce_reenable_cpu(void)
 		struct mce_bank *b = &mce_banks[i];
 
 		if (b->init)
-			wrmsrl(msr_ops.ctl(i), b->ctl);
+			wrmsrl(mca_msr_reg(i, MCA_CTL), b->ctl);
 	}
 }
 

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 mce_severity(struct mce *a, struct pt_regs *regs, int tolerant, char **msg, bool is_excp);
-			   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 {
+enum mca_msr {
-	u32 (*ctl)	(int bank);
+	MCA_CTL,
-	u32 (*status)	(int bank);
+	MCA_STATUS,
-	u32 (*addr)	(int bank);
+	MCA_ADDR,
-	u32 (*misc)	(int bank);
+	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,
-int (*mce_severity)(struct mce *m, struct pt_regs *regs, int tolerant, char **msg, bool is_excp) =
+		 bool is_excp)
-		    mce_severity_intel;
-
-void __init mcheck_vendor_init_severity(void)
 {
 	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)