Merge branch 'x86/kdump' into locking/kcsan, to resolve conflicts

Conflicts:
	arch/x86/purgatory/Makefile

Signed-off-by: Ingo Molnar <mingo@kernel.org>

70 files changed, 1320 insertions, 1441 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index ccb13271895d..70615591a265 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -98,6 +98,7 @@ obj-$(CONFIG_FUNCTION_TRACER)	+= ftrace_$(BITS).o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
 obj-$(CONFIG_FTRACE_SYSCALLS)	+= ftrace.o
 obj-$(CONFIG_X86_TSC)		+= trace_clock.o
+obj-$(CONFIG_CRASH_CORE)	+= crash_core_$(BITS).o
 obj-$(CONFIG_KEXEC_CORE)	+= machine_kexec_$(BITS).o
 obj-$(CONFIG_KEXEC_CORE)	+= relocate_kernel_$(BITS).o crash.o
 obj-$(CONFIG_KEXEC_FILE)	+= kexec-bzimage64.o
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index ca13851f0570..26b7256f590f 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -27,6 +27,17 @@ static char temp_stack[4096];
 #endif
 
 /**
+ * acpi_get_wakeup_address - provide physical address for S3 wakeup
+ *
+ * Returns the physical address where the kernel should be resumed after the
+ * system awakes from S3, e.g. for programming into the firmware waking vector.
+ */
+unsigned long acpi_get_wakeup_address(void)
+{
+	return ((unsigned long)(real_mode_header->wakeup_start));
+}
+
+/**
  * x86_acpi_enter_sleep_state - enter sleep state
  * @state: Sleep state to enter.
  *
diff --git a/arch/x86/kernel/acpi/sleep.h b/arch/x86/kernel/acpi/sleep.h
index fbb60ca4255c..d06c2079b6c1 100644
--- a/arch/x86/kernel/acpi/sleep.h
+++ b/arch/x86/kernel/acpi/sleep.h
@@ -3,7 +3,7 @@
  *	Variables and functions used by the code in sleep.c
  */
 
-#include <asm/realmode.h>
+#include <linux/linkage.h>
 
 extern unsigned long saved_video_mode;
 extern long saved_magic;
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 9ec463fe96f2..15ac0d5f4b40 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -23,6 +23,7 @@
 #include <asm/nmi.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
+#include <asm/insn.h>
 #include <asm/io.h>
 #include <asm/fixmap.h>
 
@@ -936,44 +937,81 @@ static void do_sync_core(void *info)
 	sync_core();
 }
 
-static struct bp_patching_desc {
+void text_poke_sync(void)
+{
+	on_each_cpu(do_sync_core, NULL, 1);
+}
+
+struct text_poke_loc {
+	s32 rel_addr; /* addr := _stext + rel_addr */
+	s32 rel32;
+	u8 opcode;
+	const u8 text[POKE_MAX_OPCODE_SIZE];
+};
+
+struct bp_patching_desc {
 	struct text_poke_loc *vec;
 	int nr_entries;
-} bp_patching;
+	atomic_t refs;
+};
+
+static struct bp_patching_desc *bp_desc;
+
+static inline struct bp_patching_desc *try_get_desc(struct bp_patching_desc **descp)
+{
+	struct bp_patching_desc *desc = READ_ONCE(*descp); /* rcu_dereference */
+
+	if (!desc || !atomic_inc_not_zero(&desc->refs))
+		return NULL;
+
+	return desc;
+}
+
+static inline void put_desc(struct bp_patching_desc *desc)
+{
+	smp_mb__before_atomic();
+	atomic_dec(&desc->refs);
+}
 
-static int patch_cmp(const void *key, const void *elt)
+static inline void *text_poke_addr(struct text_poke_loc *tp)
+{
+	return _stext + tp->rel_addr;
+}
+
+static int notrace patch_cmp(const void *key, const void *elt)
 {
 	struct text_poke_loc *tp = (struct text_poke_loc *) elt;
 
-	if (key < tp->addr)
+	if (key < text_poke_addr(tp))
 		return -1;
-	if (key > tp->addr)
+	if (key > text_poke_addr(tp))
 		return 1;
 	return 0;
 }
 NOKPROBE_SYMBOL(patch_cmp);
 
-int poke_int3_handler(struct pt_regs *regs)
+int notrace poke_int3_handler(struct pt_regs *regs)
 {
+	struct bp_patching_desc *desc;
 	struct text_poke_loc *tp;
+	int len, ret = 0;
 	void *ip;
 
+	if (user_mode(regs))
+		return 0;
+
 	/*
 	 * Having observed our INT3 instruction, we now must observe
-	 * bp_patching.nr_entries.
+	 * bp_desc:
 	 *
-	 *	nr_entries != 0			INT3
+	 *	bp_desc = desc			INT3
 	 *	WMB				RMB
-	 *	write INT3			if (nr_entries)
-	 *
-	 * Idem for other elements in bp_patching.
+	 *	write INT3			if (desc)
 	 */
 	smp_rmb();
 
-	if (likely(!bp_patching.nr_entries))
-		return 0;
-
-	if (user_mode(regs))
+	desc = try_get_desc(&bp_desc);
+	if (!desc)
 		return 0;
 
 	/*
@@ -984,19 +1022,20 @@ int poke_int3_handler(struct pt_regs *regs)
 	/*
 	 * Skip the binary search if there is a single member in the vector.
 	 */
-	if (unlikely(bp_patching.nr_entries > 1)) {
-		tp = bsearch(ip, bp_patching.vec, bp_patching.nr_entries,
+	if (unlikely(desc->nr_entries > 1)) {
+		tp = bsearch(ip, desc->vec, desc->nr_entries,
 			     sizeof(struct text_poke_loc),
 			     patch_cmp);
 		if (!tp)
-			return 0;
+			goto out_put;
 	} else {
-		tp = bp_patching.vec;
-		if (tp->addr != ip)
-			return 0;
+		tp = desc->vec;
+		if (text_poke_addr(tp) != ip)
+			goto out_put;
 	}
 
-	ip += tp->len;
+	len = text_opcode_size(tp->opcode);
+	ip += len;
 
 	switch (tp->opcode) {
 	case INT3_INSN_OPCODE:
@@ -1004,7 +1043,7 @@ int poke_int3_handler(struct pt_regs *regs)
 		 * Someone poked an explicit INT3, they'll want to handle it,
 		 * do not consume.
 		 */
-		return 0;
+		goto out_put;
 
 	case CALL_INSN_OPCODE:
 		int3_emulate_call(regs, (long)ip + tp->rel32);
@@ -1019,10 +1058,18 @@ int poke_int3_handler(struct pt_regs *regs)
 		BUG();
 	}
 
-	return 1;
+	ret = 1;
+
+out_put:
+	put_desc(desc);
+	return ret;
 }
 NOKPROBE_SYMBOL(poke_int3_handler);
 
+#define TP_VEC_MAX (PAGE_SIZE / sizeof(struct text_poke_loc))
+static struct text_poke_loc tp_vec[TP_VEC_MAX];
+static int tp_vec_nr;
+
 /**
  * text_poke_bp_batch() -- update instructions on live kernel on SMP
  * @tp:			vector of instructions to patch
@@ -1044,16 +1091,20 @@ NOKPROBE_SYMBOL(poke_int3_handler);
  *		  replacing opcode
  *	- sync cores
  */
-void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
+static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
 {
+	struct bp_patching_desc desc = {
+		.vec = tp,
+		.nr_entries = nr_entries,
+		.refs = ATOMIC_INIT(1),
+	};
 	unsigned char int3 = INT3_INSN_OPCODE;
 	unsigned int i;
 	int do_sync;
 
 	lockdep_assert_held(&text_mutex);
 
-	bp_patching.vec = tp;
-	bp_patching.nr_entries = nr_entries;
+	smp_store_release(&bp_desc, &desc); /* rcu_assign_pointer */
 
 	/*
 	 * Corresponding read barrier in int3 notifier for making sure the
@@ -1065,18 +1116,20 @@ void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
 	 * First step: add a int3 trap to the address that will be patched.
 	 */
 	for (i = 0; i < nr_entries; i++)
-		text_poke(tp[i].addr, &int3, sizeof(int3));
+		text_poke(text_poke_addr(&tp[i]), &int3, INT3_INSN_SIZE);
 
-	on_each_cpu(do_sync_core, NULL, 1);
+	text_poke_sync();
 
 	/*
 	 * Second step: update all but the first byte of the patched range.
 	 */
 	for (do_sync = 0, i = 0; i < nr_entries; i++) {
-		if (tp[i].len - sizeof(int3) > 0) {
-			text_poke((char *)tp[i].addr + sizeof(int3),
-				  (const char *)tp[i].text + sizeof(int3),
-				  tp[i].len - sizeof(int3));
+		int len = text_opcode_size(tp[i].opcode);
+
+		if (len - INT3_INSN_SIZE > 0) {
+			text_poke(text_poke_addr(&tp[i]) + INT3_INSN_SIZE,
+				  (const char *)tp[i].text + INT3_INSN_SIZE,
+				  len - INT3_INSN_SIZE);
 			do_sync++;
 		}
 	}
@@ -1087,7 +1140,7 @@ void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
 		 * not necessary and we'd be safe even without it. But
 		 * better safe than sorry (plus there's not only Intel).
 		 */
-		on_each_cpu(do_sync_core, NULL, 1);
+		text_poke_sync();
 	}
 
 	/*
@@ -1098,19 +1151,20 @@ void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
 		if (tp[i].text[0] == INT3_INSN_OPCODE)
 			continue;
 
-		text_poke(tp[i].addr, tp[i].text, sizeof(int3));
+		text_poke(text_poke_addr(&tp[i]), tp[i].text, INT3_INSN_SIZE);
 		do_sync++;
 	}
 
 	if (do_sync)
-		on_each_cpu(do_sync_core, NULL, 1);
+		text_poke_sync();
 
 	/*
-	 * sync_core() implies an smp_mb() and orders this store against
-	 * the writing of the new instruction.
+	 * Remove and synchronize_rcu(), except we have a very primitive
+	 * refcount based completion.
 	 */
-	bp_patching.vec = NULL;
-	bp_patching.nr_entries = 0;
+	WRITE_ONCE(bp_desc, NULL); /* RCU_INIT_POINTER */
+	if (!atomic_dec_and_test(&desc.refs))
+		atomic_cond_read_acquire(&desc.refs, !VAL);
 }
 
 void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
@@ -1118,11 +1172,7 @@ void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
 {
 	struct insn insn;
 
-	if (!opcode)
-		opcode = (void *)tp->text;
-	else
-		memcpy((void *)tp->text, opcode, len);
-
+	memcpy((void *)tp->text, opcode, len);
 	if (!emulate)
 		emulate = opcode;
 
@@ -1132,8 +1182,7 @@ void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
 	BUG_ON(!insn_complete(&insn));
 	BUG_ON(len != insn.length);
 
-	tp->addr = addr;
-	tp->len = len;
+	tp->rel_addr = addr - (void *)_stext;
 	tp->opcode = insn.opcode.bytes[0];
 
 	switch (tp->opcode) {
@@ -1167,6 +1216,55 @@ void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
 	}
 }
 
+/*
+ * We hard rely on the tp_vec being ordered; ensure this is so by flushing
+ * early if needed.
+ */
+static bool tp_order_fail(void *addr)
+{
+	struct text_poke_loc *tp;
+
+	if (!tp_vec_nr)
+		return false;
+
+	if (!addr) /* force */
+		return true;
+
+	tp = &tp_vec[tp_vec_nr - 1];
+	if ((unsigned long)text_poke_addr(tp) > (unsigned long)addr)
+		return true;
+
+	return false;
+}
+
+static void text_poke_flush(void *addr)
+{
+	if (tp_vec_nr == TP_VEC_MAX || tp_order_fail(addr)) {
+		text_poke_bp_batch(tp_vec, tp_vec_nr);
+		tp_vec_nr = 0;
+	}
+}
+
+void text_poke_finish(void)
+{
+	text_poke_flush(NULL);
+}
+
+void __ref text_poke_queue(void *addr, const void *opcode, size_t len, const void *emulate)
+{
+	struct text_poke_loc *tp;
+
+	if (unlikely(system_state == SYSTEM_BOOTING)) {
+		text_poke_early(addr, opcode, len);
+		return;
+	}
+
+	text_poke_flush(addr);
+
+	tp = &tp_vec[tp_vec_nr++];
+	text_poke_loc_init(tp, addr, opcode, len, emulate);
+}
+
 /**
  * text_poke_bp() -- update instructions on live kernel on SMP
  * @addr:	address to patch
@@ -1178,10 +1276,15 @@ void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
  * dynamically allocated memory. This function should be used when it is
  * not possible to allocate memory.
  */
-void text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate)
+void __ref text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate)
 {
 	struct text_poke_loc tp;
 
+	if (unlikely(system_state == SYSTEM_BOOTING)) {
+		text_poke_early(addr, opcode, len);
+		return;
+	}
+
 	text_poke_loc_init(&tp, addr, opcode, len, emulate);
 	text_poke_bp_batch(&tp, 1);
 }
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 251c795b4eb3..69aed0ebbdfc 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -22,6 +22,7 @@
 #define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec
 #define PCI_DEVICE_ID_AMD_17H_M30H_DF_F4 0x1494
 #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F4 0x1444
+#define PCI_DEVICE_ID_AMD_19H_DF_F4	0x1654
 
 /* Protect the PCI config register pairs used for SMN and DF indirect access. */
 static DEFINE_MUTEX(smn_mutex);
@@ -52,6 +53,7 @@ const struct pci_device_id amd_nb_misc_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F3) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F3) },
 	{}
 };
 EXPORT_SYMBOL_GPL(amd_nb_misc_ids);
@@ -66,6 +68,7 @@ static const struct pci_device_id amd_nb_link_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F4) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) },
 	{}
 };
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index 5da106f84e84..fe698f96617c 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -95,7 +95,7 @@ static inline void apbt_set_mapping(void)
 		printk(KERN_WARNING "No timer base from SFI, use default\n");
 		apbt_address = APBT_DEFAULT_BASE;
 	}
-	apbt_virt_address = ioremap_nocache(apbt_address, APBT_MMAP_SIZE);
+	apbt_virt_address = ioremap(apbt_address, APBT_MMAP_SIZE);
 	if (!apbt_virt_address) {
 		pr_debug("Failed mapping APBT phy address at %lu\n",\
 			 (unsigned long)apbt_address);
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 28446fa6bf18..5f973fed3c9f 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -830,8 +830,17 @@ bool __init apic_needs_pit(void)
 	if (!tsc_khz || !cpu_khz)
 		return true;
 
-	/* Is there an APIC at all? */
-	if (!boot_cpu_has(X86_FEATURE_APIC))
+	/* Is there an APIC at all or is it disabled? */
+	if (!boot_cpu_has(X86_FEATURE_APIC) || disable_apic)
+		return true;
+
+	/*
+	 * If interrupt delivery mode is legacy PIC or virtual wire without
+	 * configuration, the local APIC timer wont be set up. Make sure
+	 * that the PIT is initialized.
+	 */
+	if (apic_intr_mode == APIC_PIC ||
+	    apic_intr_mode == APIC_VIRTUAL_WIRE_NO_CONFIG)
 		return true;
 
 	/* Virt guests may lack ARAT, but still have DEADLINE */
@@ -1322,7 +1331,7 @@ void __init sync_Arb_IDs(void)
 
 enum apic_intr_mode_id apic_intr_mode __ro_after_init;
 
-static int __init apic_intr_mode_select(void)
+static int __init __apic_intr_mode_select(void)
 {
 	/* Check kernel option */
 	if (disable_apic) {
@@ -1384,6 +1393,12 @@ static int __init apic_intr_mode_select(void)
 	return APIC_SYMMETRIC_IO;
 }
 
+/* Select the interrupt delivery mode for the BSP */
+void __init apic_intr_mode_select(void)
+{
+	apic_intr_mode = __apic_intr_mode_select();
+}
+
 /*
  * An initial setup of the virtual wire mode.
  */
@@ -1440,8 +1455,6 @@ void __init apic_intr_mode_init(void)
 {
 	bool upmode = IS_ENABLED(CONFIG_UP_LATE_INIT);
 
-	apic_intr_mode = apic_intr_mode_select();
-
 	switch (apic_intr_mode) {
 	case APIC_PIC:
 		pr_info("APIC: Keep in PIC mode(8259)\n");
@@ -2626,6 +2639,13 @@ static int lapic_suspend(void)
 #endif
 
 	local_irq_save(flags);
+
+	/*
+	 * Mask IOAPIC before disabling the local APIC to prevent stale IRR
+	 * entries on some implementations.
+	 */
+	mask_ioapic_entries();
+
 	disable_local_APIC();
 
 	irq_remapping_disable();
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index 7f7533462474..159bd0cb8548 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -23,10 +23,8 @@
 
 static struct irq_domain *msi_default_domain;
 
-static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg)
+static void __irq_msi_compose_msg(struct irq_cfg *cfg, struct msi_msg *msg)
 {
-	struct irq_cfg *cfg = irqd_cfg(data);
-
 	msg->address_hi = MSI_ADDR_BASE_HI;
 
 	if (x2apic_enabled())
@@ -47,6 +45,127 @@ static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg)
 		MSI_DATA_VECTOR(cfg->vector);