14 files changed, 181 insertions, 71 deletions

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index e6cf2ad350d1..9727b3b48bd1 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -193,7 +193,7 @@
 #define X86_FEATURE_HW_PSTATE	( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
 #define X86_FEATURE_HWP		( 7*32+ 10) /* "hwp" Intel HWP */
-#define X86_FEATURE_HWP_NOITFY	( 7*32+ 11) /* Intel HWP_NOTIFY */
+#define X86_FEATURE_HWP_NOTIFY	( 7*32+ 11) /* Intel HWP_NOTIFY */
 #define X86_FEATURE_HWP_ACT_WINDOW ( 7*32+ 12) /* Intel HWP_ACT_WINDOW */
 #define X86_FEATURE_HWP_EPP	( 7*32+13) /* Intel HWP_EPP */
 #define X86_FEATURE_HWP_PKG_REQ ( 7*32+14) /* Intel HWP_PKG_REQ */
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 83aea8055119..4c20dd333412 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -336,10 +336,10 @@ HYPERVISOR_update_descriptor(u64 ma, u64 desc)
 	return _hypercall4(int, update_descriptor, ma, ma>>32, desc, desc>>32);
 }
 
-static inline int
+static inline long
 HYPERVISOR_memory_op(unsigned int cmd, void *arg)
 {
-	return _hypercall2(int, memory_op, cmd, arg);
+	return _hypercall2(long, memory_op, cmd, arg);
 }
 
 static inline int
diff --git a/arch/x86/include/uapi/asm/bitsperlong.h b/arch/x86/include/uapi/asm/bitsperlong.h
index b0ae1c4dc791..217909b4d6f5 100644
--- a/arch/x86/include/uapi/asm/bitsperlong.h
+++ b/arch/x86/include/uapi/asm/bitsperlong.h
@@ -1,7 +1,7 @@
 #ifndef __ASM_X86_BITSPERLONG_H
 #define __ASM_X86_BITSPERLONG_H
 
-#ifdef __x86_64__
+#if defined(__x86_64__) && !defined(__ILP32__)
 # define __BITS_PER_LONG 64
 #else
 # define __BITS_PER_LONG 32
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 381c8b9b3a33..20e242ea1bc4 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -34,11 +34,10 @@
 struct ms_hyperv_info ms_hyperv;
 EXPORT_SYMBOL_GPL(ms_hyperv);
 
-static void (*hv_kexec_handler)(void);
-static void (*hv_crash_handler)(struct pt_regs *regs);
-
 #if IS_ENABLED(CONFIG_HYPERV)
 static void (*vmbus_handler)(void);
+static void (*hv_kexec_handler)(void);
+static void (*hv_crash_handler)(struct pt_regs *regs);
 
 void hyperv_vector_handler(struct pt_regs *regs)
 {
@@ -96,8 +95,8 @@ void hv_remove_crash_handler(void)
 	hv_crash_handler = NULL;
 }
 EXPORT_SYMBOL_GPL(hv_remove_crash_handler);
-#endif
 
+#ifdef CONFIG_KEXEC_CORE
 static void hv_machine_shutdown(void)
 {
 	if (kexec_in_progress && hv_kexec_handler)
@@ -111,7 +110,8 @@ static void hv_machine_crash_shutdown(struct pt_regs *regs)
 		hv_crash_handler(regs);
 	native_machine_crash_shutdown(regs);
 }
-
+#endif /* CONFIG_KEXEC_CORE */
+#endif /* CONFIG_HYPERV */
 
 static uint32_t  __init ms_hyperv_platform(void)
 {
@@ -186,8 +186,10 @@ static void __init ms_hyperv_init_platform(void)
 	no_timer_check = 1;
 #endif
 
+#if IS_ENABLED(CONFIG_HYPERV) && defined(CONFIG_KEXEC_CORE)
 	machine_ops.shutdown = hv_machine_shutdown;
 	machine_ops.crash_shutdown = hv_machine_crash_shutdown;
+#endif
 	mark_tsc_unstable("running on Hyper-V");
 }
 
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 3d423a101fae..608fb26c7254 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -37,7 +37,7 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 		{ X86_FEATURE_PLN,		CR_EAX, 4, 0x00000006, 0 },
 		{ X86_FEATURE_PTS,		CR_EAX, 6, 0x00000006, 0 },
 		{ X86_FEATURE_HWP,		CR_EAX, 7, 0x00000006, 0 },
-		{ X86_FEATURE_HWP_NOITFY,	CR_EAX, 8, 0x00000006, 0 },
+		{ X86_FEATURE_HWP_NOTIFY,	CR_EAX, 8, 0x00000006, 0 },
 		{ X86_FEATURE_HWP_ACT_WINDOW,	CR_EAX, 9, 0x00000006, 0 },
 		{ X86_FEATURE_HWP_EPP,		CR_EAX,10, 0x00000006, 0 },
 		{ X86_FEATURE_HWP_PKG_REQ,	CR_EAX,11, 0x00000006, 0 },
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index e068d6683dba..74ca2fe7a0b3 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -185,10 +185,9 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
 }
 
 #ifdef CONFIG_KEXEC_FILE
-static int get_nr_ram_ranges_callback(unsigned long start_pfn,
-				unsigned long nr_pfn, void *arg)
+static int get_nr_ram_ranges_callback(u64 start, u64 end, void *arg)
 {
-	int *nr_ranges = arg;
+	unsigned int *nr_ranges = arg;
 
 	(*nr_ranges)++;
 	return 0;
@@ -214,7 +213,7 @@ static void fill_up_crash_elf_data(struct crash_elf_data *ced,
 
 	ced->image = image;
 
-	walk_system_ram_range(0, -1, &nr_ranges,
+	walk_system_ram_res(0, -1, &nr_ranges,
 				get_nr_ram_ranges_callback);
 
 	ced->max_nr_ranges = nr_ranges;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 6d0e62ae8516..39e585a554b7 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -506,3 +506,58 @@ unsigned long arch_randomize_brk(struct mm_struct *mm)
 	return randomize_range(mm->brk, range_end, 0) ? : mm->brk;
 }
 
+/*
+ * Called from fs/proc with a reference on @p to find the function
+ * which called into schedule(). This needs to be done carefully
+ * because the task might wake up and we might look at a stack
+ * changing under us.
+ */
+unsigned long get_wchan(struct task_struct *p)
+{
+	unsigned long start, bottom, top, sp, fp, ip;
+	int count = 0;
+
+	if (!p || p == current || p->state == TASK_RUNNING)
+		return 0;
+
+	start = (unsigned long)task_stack_page(p);
+	if (!start)
+		return 0;
+
+	/*
+	 * Layout of the stack page:
+	 *
+	 * ----------- topmax = start + THREAD_SIZE - sizeof(unsigned long)
+	 * PADDING
+	 * ----------- top = topmax - TOP_OF_KERNEL_STACK_PADDING
+	 * stack
+	 * ----------- bottom = start + sizeof(thread_info)
+	 * thread_info
+	 * ----------- start
+	 *
+	 * The tasks stack pointer points at the location where the
+	 * framepointer is stored. The data on the stack is:
+	 * ... IP FP ... IP FP
+	 *
+	 * We need to read FP and IP, so we need to adjust the upper
+	 * bound by another unsigned long.
+	 */
+	top = start + THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING;
+	top -= 2 * sizeof(unsigned long);
+	bottom = start + sizeof(struct thread_info);
+
+	sp = READ_ONCE(p->thread.sp);
+	if (sp < bottom || sp > top)
+		return 0;
+
+	fp = READ_ONCE(*(unsigned long *)sp);
+	do {
+		if (fp < bottom || fp > top)
+			return 0;
+		ip = READ_ONCE(*(unsigned long *)(fp + sizeof(unsigned long)));
+		if (!in_sched_functions(ip))
+			return ip;
+		fp = READ_ONCE(*(unsigned long *)fp);
+	} while (count++ < 16 && p->state != TASK_RUNNING);
+	return 0;
+}
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index c13df2c735f8..737527b40e5b 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -324,31 +324,3 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
 	return prev_p;
 }
-
-#define top_esp                (THREAD_SIZE - sizeof(unsigned long))
-#define top_ebp                (THREAD_SIZE - 2*sizeof(unsigned long))
-
-unsigned long get_wchan(struct task_struct *p)
-{
-	unsigned long bp, sp, ip;
-	unsigned long stack_page;
-	int count = 0;
-	if (!p || p == current || p->state == TASK_RUNNING)
-		return 0;
-	stack_page = (unsigned long)task_stack_page(p);
-	sp = p->thread.sp;
-	if (!stack_page || sp < stack_page || sp > top_esp+stack_page)
-		return 0;
-	/* include/asm-i386/system.h:switch_to() pushes bp last. */
-	bp = *(unsigned long *) sp;
-	do {
-		if (bp < stack_page || bp > top_ebp+stack_page)
-			return 0;
-		ip = *(unsigned long *) (bp+4);
-		if (!in_sched_functions(ip))
-			return ip;
-		bp = *(unsigned long *) bp;
-	} while (count++ < 16);
-	return 0;
-}
-
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 3c1bbcf12924..b35921a670b2 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -499,30 +499,6 @@ void set_personality_ia32(bool x32)
 }
 EXPORT_SYMBOL_GPL(set_personality_ia32);
 
-unsigned long get_wchan(struct task_struct *p)
-{
-	unsigned long stack;
-	u64 fp, ip;
-	int count = 0;
-
-	if (!p || p == current || p->state == TASK_RUNNING)
-		return 0;
-	stack = (unsigned long)task_stack_page(p);
-	if (p->thread.sp < stack || p->thread.sp >= stack+THREAD_SIZE)
-		return 0;
-	fp = *(u64 *)(p->thread.sp);
-	do {
-		if (fp < (unsigned long)stack ||
-		    fp >= (unsigned long)stack+THREAD_SIZE)
-			return 0;
-		ip = *(u64 *)(fp+8);
-		if (!in_sched_functions(ip))
-			return ip;
-		fp = *(u64 *)fp;
-	} while (count++ < 16);
-	return 0;
-}
-
 long do_arch_prctl(struct task_struct *task, int code, unsigned long addr)
 {
 	int ret = 0;
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 30564e2752d3..df48430c279b 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1132,7 +1132,7 @@ void mark_rodata_ro(void)
 	 * has been zapped already via cleanup_highmem().
 	 */
 	all_end = roundup((unsigned long)_brk_end, PMD_SIZE);
-	set_memory_nx(rodata_start, (all_end - rodata_start) >> PAGE_SHIFT);
+	set_memory_nx(text_end, (all_end - text_end) >> PAGE_SHIFT);
 
 	rodata_test();
 
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 1db84c0758b7..6a28ded74211 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -705,6 +705,70 @@ out:
 }
 
 /*
+ * Iterate the EFI memory map in reverse order because the regions
+ * will be mapped top-down. The end result is the same as if we had
+ * mapped things forward, but doesn't require us to change the
+ * existing implementation of efi_map_region().
+ */
+static inline void *efi_map_next_entry_reverse(void *entry)
+{
+	/* Initial call */
+	if (!entry)
+		return memmap.map_end - memmap.desc_size;
+
+	entry -= memmap.desc_size;
+	if (entry < memmap.map)
+		return NULL;
+
+	return entry;
+}
+
+/*
+ * efi_map_next_entry - Return the next EFI memory map descriptor
+ * @entry: Previous EFI memory map descriptor
+ *
+ * This is a helper function to iterate over the EFI memory map, which
+ * we do in different orders depending on the current configuration.
+ *
+ * To begin traversing the memory map @entry must be %NULL.
+ *
+ * Returns %NULL when we reach the end of the memory map.
+ */
+static void *efi_map_next_entry(void *entry)
+{
+	if (!efi_enabled(EFI_OLD_MEMMAP) && efi_enabled(EFI_64BIT)) {
+		/*
+		 * Starting in UEFI v2.5 the EFI_PROPERTIES_TABLE
+		 * config table feature requires us to map all entries
+		 * in the same order as they appear in the EFI memory
+		 * map. That is to say, entry N must have a lower
+		 * virtual address than entry N+1. This is because the
+		 * firmware toolchain leaves relative references in
+		 * the code/data sections, which are split and become
+		 * separate EFI memory regions. Mapping things
+		 * out-of-order leads to the firmware accessing
+		 * unmapped addresses.
+		 *
+		 * Since we need to map things this way whether or not
+		 * the kernel actually makes use of
+		 * EFI_PROPERTIES_TABLE, let's just switch to this
+		 * scheme by default for 64-bit.
+		 */
+		return efi_map_next_entry_reverse(entry);
+	}
+
+	/* Initial call */
+	if (!entry)
+		return memmap.map;
+
+	entry += memmap.desc_size;
+	if (entry >= memmap.map_end)
+		return NULL;
+
+	return entry;
+}
+
+/*
  * Map the efi memory ranges of the runtime services and update new_mmap with
  * virtual addresses.
  */
@@ -714,7 +778,8 @@ static void * __init efi_map_regions(int *count, int *pg_shift)
 	unsigned long left = 0;
 	efi_memory_desc_t *md;
 
-	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+	p = NULL;
+	while ((p = efi_map_next_entry(p))) {
 		md = p;
 		if (!(md->attribute & EFI_MEMORY_RUNTIME)) {
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 30d12afe52ed..993b7a71386d 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -33,6 +33,10 @@
 #include <linux/memblock.h>
 #include <linux/edd.h>
 
+#ifdef CONFIG_KEXEC_CORE
+#include <linux/kexec.h>
+#endif
+
 #include <xen/xen.h>
 #include <xen/events.h>
 #include <xen/interface/xen.h>
@@ -1077,6 +1081,7 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
 		/* Fast syscall setup is all done in hypercalls, so
 		   these are all ignored.  Stub them out here to stop
 		   Xen console noise. */
+		break;
 
 	default:
 		if (!pmu_msr_write(msr, low, high, &ret))
@@ -1807,6 +1812,21 @@ static struct notifier_block xen_hvm_cpu_notifier = {
 	.notifier_call	= xen_hvm_cpu_notify,
 };
 
+#ifdef CONFIG_KEXEC_CORE
+static void xen_hvm_shutdown(void)
+{
+	native_machine_shutdown();
+	if (kexec_in_progress)
+		xen_reboot(SHUTDOWN_soft_reset);
+}
+
+static void xen_hvm_crash_shutdown(struct pt_regs *regs)
+{
+	native_machine_crash_shutdown(regs);
+	xen_reboot(SHUTDOWN_soft_reset);
+}
+#endif
+
 static void __init xen_hvm_guest_init(void)
 {
 	if (xen_pv_domain())
@@ -1826,6 +1846,10 @@ static void __init xen_hvm_guest_init(void)
 	x86_init.irqs.intr_init = xen_init_IRQ;
 	xen_hvm_init_time_ops();
 	xen_hvm_init_mmu_ops();
+#ifdef CONFIG_KEXEC_CORE
+	machine_ops.shutdown = xen_hvm_shutdown;
+	machine_ops.crash_shutdown = xen_hvm_crash_shutdown;
+#endif
 }
 #endif
 
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index bfc08b13044b..660b3cfef234 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -112,6 +112,15 @@ static unsigned long *p2m_identity;
 static pte_t *p2m_missing_pte;
 static pte_t *p2m_identity_pte;
 
+/*
+ * Hint at last populated PFN.
+ *
+ * Used to set HYPERVISOR_shared_info->arch.max_pfn so the toolstack
+ * can avoid scanning the whole P2M (which may be sized to account for
+ * hotplugged memory).
+ */
+static unsigned long xen_p2m_last_pfn;
+
 static inline unsigned p2m_top_index(unsigned long pfn)
 {
 	BUG_ON(pfn >= MAX_P2M_PFN);
@@ -270,7 +279,7 @@ void xen_setup_mfn_list_list(void)
 	else
 		HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list =
 			virt_to_mfn(p2m_top_mfn);
-	HYPERVISOR_shared_info->arch.max_pfn = xen_max_p2m_pfn;
+	HYPERVISOR_shared_info->arch.max_pfn = xen_p2m_last_pfn;
 	HYPERVISOR_shared_info->arch.p2m_generation = 0;
 	HYPERVISOR_shared_info->arch.p2m_vaddr = (unsigned long)xen_p2m_addr;
 	HYPERVISOR_shared_info->arch.p2m_cr3 =
@@ -406,6 +415,8 @@ void __init xen_vmalloc_p2m_tree(void)
 	static struct vm_struct vm;
 	unsigned long p2m_limit;
 
+	xen_p2m_last_pfn = xen_max_p2m_pfn;
+
 	p2m_limit = (phys_addr_t)P2M_LIMIT * 1024 * 1024 * 1024 / PAGE_SIZE;
 	vm.flags = VM_ALLOC;
 	vm.size = ALIGN(sizeof(unsigned long) * max(xen_max_p2m_pfn, p2m_limit),
@@ -608,6 +619,12 @@ static bool alloc_p2m(unsigned long pfn)
 			free_p2m_page(p2m);
 	}
 
+	/* Expanded the p2m? */
+	if (pfn > xen_p2m_last_pfn) {
+		xen_p2m_last_pfn = pfn;
+		HYPERVISOR_shared_info->arch.max_pfn = xen_p2m_last_pfn;
+	}
+
 	return true;
 }
 
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index f5ef6746d47a..1c30e4ab1022 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -548,7 +548,7 @@ static unsigned long __init xen_get_max_pages(void)
 {
 	unsigned long max_pages, limit;
 	domid_t domid = DOMID_SELF;
-	int ret;
+	long ret;
 
 	limit = xen_get_pages_limit();
 	max_pages = limit;
@@ -798,7 +798,7 @@ char * __init xen_memory_setup(void)
 		xen_ignore_unusable();
 
 	/* Make sure the Xen-supplied memory map is well-ordered. */
-	sanitize_e820_map(xen_e820_map, xen_e820_map_entries,
+	sanitize_e820_map(xen_e820_map, ARRAY_SIZE(xen_e820_map),
 			  &xen_e820_map_entries);
 
 	max_pages = xen_get_max_pages();