Merge branch 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 mm updates from Ingo Molnar:
 "Lots of changes in this cycle:

   - Lots of CPA (change page attribute) optimizations and related
     cleanups (Thomas Gleixner, Peter Zijstra)

   - Make lazy TLB mode even lazier (Rik van Riel)

   - Fault handler cleanups and improvements (Dave Hansen)

   - kdump, vmcore: Enable kdumping encrypted memory with AMD SME
     enabled (Lianbo Jiang)

   - Clean up VM layout documentation (Baoquan He, Ingo Molnar)

   - ... plus misc other fixes and enhancements"

* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (51 commits)
  x86/stackprotector: Remove the call to boot_init_stack_canary() from cpu_startup_entry()
  x86/mm: Kill stray kernel fault handling comment
  x86/mm: Do not warn about PCI BIOS W+X mappings
  resource: Clean it up a bit
  resource: Fix find_next_iomem_res() iteration issue
  resource: Include resource end in walk_*() interfaces
  x86/kexec: Correct KEXEC_BACKUP_SRC_END off-by-one error
  x86/mm: Remove spurious fault pkey check
  x86/mm/vsyscall: Consider vsyscall page part of user address space
  x86/mm: Add vsyscall address helper
  x86/mm: Fix exception table comments
  x86/mm: Add clarifying comments for user addr space
  x86/mm: Break out user address space handling
  x86/mm: Break out kernel address space handling
  x86/mm: Clarify hardware vs. software "error_code"
  x86/mm/tlb: Make lazy TLB mode lazier
  x86/mm/tlb: Add freed_tables element to flush_tlb_info
  x86/mm/tlb: Add freed_tables argument to flush_tlb_mm_range
  smp,cpumask: introduce on_each_cpu_cond_mask
  smp: use __cpumask_set_cpu in on_each_cpu_cond
  ...

6 files changed, 94 insertions, 102 deletions

diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 23a83a4da38a..86ef06d3dbe3 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -471,6 +471,10 @@ static struct page *kimage_alloc_crash_control_pages(struct kimage *image,
 		}
 	}
 
+	/* Ensure that these pages are decrypted if SME is enabled. */
+	if (pages)
+		arch_kexec_post_alloc_pages(page_address(pages), 1 << order, 0);
+
 	return pages;
 }
 
@@ -867,6 +871,7 @@ static int kimage_load_crash_segment(struct kimage *image,
 			result  = -ENOMEM;
 			goto out;
 		}
+		arch_kexec_post_alloc_pages(page_address(page), 1, 0);
 		ptr = kmap(page);
 		ptr += maddr & ~PAGE_MASK;
 		mchunk = min_t(size_t, mbytes,
@@ -884,6 +889,7 @@ static int kimage_load_crash_segment(struct kimage *image,
 			result = copy_from_user(ptr, buf, uchunk);
 		kexec_flush_icache_page(page);
 		kunmap(page);
+		arch_kexec_pre_free_pages(page_address(page), 1);
 		if (result) {
 			result = -EFAULT;
 			goto out;
diff --git a/kernel/resource.c b/kernel/resource.c
index 30e1bc68503b..b3a3a1fc499e 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -318,33 +318,34 @@ int release_resource(struct resource *old)
 
 EXPORT_SYMBOL(release_resource);
 
-/*
- * Finds the lowest iomem resource existing within [res->start.res->end).
- * The caller must specify res->start, res->end, res->flags, and optionally
- * desc.  If found, returns 0, res is overwritten, if not found, returns -1.
- * This function walks the whole tree and not just first level children until
- * and unless first_level_children_only is true.
+/**
+ * Finds the lowest iomem resource that covers part of [start..end].  The
+ * caller must specify start, end, flags, and desc (which may be
+ * IORES_DESC_NONE).
+ *
+ * If a resource is found, returns 0 and *res is overwritten with the part
+ * of the resource that's within [start..end]; if none is found, returns
+ * -1.
+ *
+ * This function walks the whole tree and not just first level children
+ * unless @first_lvl is true.
  */
-static int find_next_iomem_res(struct resource *res, unsigned long desc,
-			       bool first_level_children_only)
+static int find_next_iomem_res(resource_size_t start, resource_size_t end,
+			       unsigned long flags, unsigned long desc,
+			       bool first_lvl, struct resource *res)
 {
-	resource_size_t start, end;
 	struct resource *p;
-	bool sibling_only = false;
 
-	BUG_ON(!res);
-
-	start = res->start;
-	end = res->end;
-	BUG_ON(start >= end);
+	if (!res)
+		return -EINVAL;
 
-	if (first_level_children_only)
-		sibling_only = true;
+	if (start >= end)
+		return -EINVAL;
 
 	read_lock(&resource_lock);
 
-	for (p = iomem_resource.child; p; p = next_resource(p, sibling_only)) {
-		if ((p->flags & res->flags) != res->flags)
+	for (p = iomem_resource.child; p; p = next_resource(p, first_lvl)) {
+		if ((p->flags & flags) != flags)
 			continue;
 		if ((desc != IORES_DESC_NONE) && (desc != p->desc))
 			continue;
@@ -352,45 +353,43 @@ static int find_next_iomem_res(struct resource *res, unsigned long desc,
 			p = NULL;
 			break;
 		}
-		if ((p->end >= start) && (p->start < end))
+		if ((p->end >= start) && (p->start <= end))
 			break;
 	}
 
 	read_unlock(&resource_lock);
 	if (!p)
 		return -1;
+
 	/* copy data */
-	if (res->start < p->start)
-		res->start = p->start;
-	if (res->end > p->end)
-		res->end = p->end;
+	res->start = max(start, p->start);
+	res->end = min(end, p->end);
 	res->flags = p->flags;
 	res->desc = p->desc;
 	return 0;
 }
 
-static int __walk_iomem_res_desc(struct resource *res, unsigned long desc,
-				 bool first_level_children_only,
-				 void *arg,
+static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end,
+				 unsigned long flags, unsigned long desc,
+				 bool first_lvl, void *arg,
 				 int (*func)(struct resource *, void *))
 {
-	u64 orig_end = res->end;
+	struct resource res;
 	int ret = -1;
 
-	while ((res->start < res->end) &&
-	       !find_next_iomem_res(res, desc, first_level_children_only)) {
-		ret = (*func)(res, arg);
+	while (start < end &&
+	       !find_next_iomem_res(start, end, flags, desc, first_lvl, &res)) {
+		ret = (*func)(&res, arg);
 		if (ret)
 			break;
 
-		res->start = res->end + 1;
-		res->end = orig_end;
+		start = res.end + 1;
 	}
 
 	return ret;
 }
 
-/*
+/**
  * Walks through iomem resources and calls func() with matching resource
  * ranges. This walks through whole tree and not just first level children.
  * All the memory ranges which overlap start,end and also match flags and
@@ -407,13 +406,7 @@ static int __walk_iomem_res_desc(struct resource *res, unsigned long desc,
 int walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start,
 		u64 end, void *arg, int (*func)(struct resource *, void *))
 {
-	struct resource res;
-
-	res.start = start;
-	res.end = end;
-	res.flags = flags;
-
-	return __walk_iomem_res_desc(&res, desc, false, arg, func);
+	return __walk_iomem_res_desc(start, end, flags, desc, false, arg, func);
 }
 EXPORT_SYMBOL_GPL(walk_iomem_res_desc);
 
@@ -425,15 +418,11 @@ EXPORT_SYMBOL_GPL(walk_iomem_res_desc);
  * ranges.
  */
 int walk_system_ram_res(u64 start, u64 end, void *arg,
-				int (*func)(struct resource *, void *))
+			int (*func)(struct resource *, void *))
 {
-	struct resource res;
+	unsigned long flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
 
-	res.start = start;
-	res.end = end;
-	res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
-
-	return __walk_iomem_res_desc(&res, IORES_DESC_NONE, true,
+	return __walk_iomem_res_desc(start, end, flags, IORES_DESC_NONE, true,
 				     arg, func);
 }
 
@@ -444,13 +433,9 @@ int walk_system_ram_res(u64 start, u64 end, void *arg,
 int walk_mem_res(u64 start, u64 end, void *arg,
 		 int (*func)(struct resource *, void *))
 {
-	struct resource res;
-
-	res.start = start;
-	res.end = end;
-	res.flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+	unsigned long flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 
-	return __walk_iomem_res_desc(&res, IORES_DESC_NONE, true,
+	return __walk_iomem_res_desc(start, end, flags, IORES_DESC_NONE, true,
 				     arg, func);
 }
 
@@ -462,27 +447,27 @@ int walk_mem_res(u64 start, u64 end, void *arg,
  * It is to be used only for System RAM.
  */
 int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages,
-		void *arg, int (*func)(unsigned long, unsigned long, void *))
+			  void *arg, int (*func)(unsigned long, unsigned long, void *))
 {
+	resource_size_t start, end;
+	unsigned long flags;
 	struct resource res;
 	unsigned long pfn, end_pfn;
-	u64 orig_end;
 	int ret = -1;
 
-	res.start = (u64) start_pfn << PAGE_SHIFT;
-	res.end = ((u64)(start_pfn + nr_pages) << PAGE_SHIFT) - 1;
-	res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
-	orig_end = res.end;
-	while ((res.start < res.end) &&
-		(find_next_iomem_res(&res, IORES_DESC_NONE, true) >= 0)) {
+	start = (u64) start_pfn << PAGE_SHIFT;
+	end = ((u64)(start_pfn + nr_pages) << PAGE_SHIFT) - 1;
+	flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+	while (start < end &&
+	       !find_next_iomem_res(start, end, flags, IORES_DESC_NONE,
+				    true, &res)) {
 		pfn = (res.start + PAGE_SIZE - 1) >> PAGE_SHIFT;
 		end_pfn = (res.end + 1) >> PAGE_SHIFT;
 		if (end_pfn > pfn)
 			ret = (*func)(pfn, end_pfn - pfn, arg);
 		if (ret)
 			break;
-		res.start = res.end + 1;
-		res.end = orig_end;
+		start = res.end + 1;
 	}
 	return ret;
 }
@@ -658,8 +643,8 @@ static int find_resource(struct resource *root, struct resource *new,
  * @constraint: the size and alignment constraints to be met.
  */
 static int reallocate_resource(struct resource *root, struct resource *old,
-			resource_size_t newsize,
-			struct resource_constraint  *constraint)
+			       resource_size_t newsize,
+			       struct resource_constraint *constraint)
 {
 	int err=0;
 	struct resource new = *old;
@@ -972,7 +957,7 @@ skip:
  * Existing children of the resource are assumed to be immutable.
  */
 int adjust_resource(struct resource *res, resource_size_t start,
-			resource_size_t size)
+		    resource_size_t size)
 {
 	int result;
 
@@ -983,9 +968,9 @@ int adjust_resource(struct resource *res, resource_size_t start,
 }
 EXPORT_SYMBOL(adjust_resource);
 
-static void __init __reserve_region_with_split(struct resource *root,
-		resource_size_t start, resource_size_t end,
-		const char *name)
+static void __init
+__reserve_region_with_split(struct resource *root, resource_size_t start,
+			    resource_size_t end, const char *name)
 {
 	struct resource *parent = root;
 	struct resource *conflict;
@@ -1044,9 +1029,9 @@ static void __init __reserve_region_with_split(struct resource *root,
 
 }
 
-void __init reserve_region_with_split(struct resource *root,
-		resource_size_t start, resource_size_t end,
-		const char *name)
+void __init
+reserve_region_with_split(struct resource *root, resource_size_t start,
+			  resource_size_t end, const char *name)
 {
 	int abort = 0;
 
@@ -1172,7 +1157,7 @@ EXPORT_SYMBOL(__request_region);
  * The described resource region must match a currently busy region.
  */
 void __release_region(struct resource *parent, resource_size_t start,
-			resource_size_t n)
+		      resource_size_t n)
 {
 	struct resource **p;
 	resource_size_t end;
@@ -1234,7 +1219,7 @@ EXPORT_SYMBOL(__release_region);
  *   simplicity.  Enhance this logic when necessary.
  */
 int release_mem_region_adjustable(struct resource *parent,
-			resource_size_t start, resource_size_t size)
+				  resource_size_t start, resource_size_t size)
 {
 	struct resource **p;
 	struct resource *res;
@@ -1410,9 +1395,9 @@ static int devm_region_match(struct device *dev, void *res, void *match_data)
 		this->start == match->start && this->n == match->n;
 }
 
-struct resource * __devm_request_region(struct device *dev,
-				struct resource *parent, resource_size_t start,
-				resource_size_t n, const char *name)
+struct resource *
+__devm_request_region(struct device *dev, struct resource *parent,
+		      resource_size_t start, resource_size_t n, const char *name)
 {
 	struct region_devres *dr = NULL;
 	struct resource *res;
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 16f84142f2f4..f5516bae0c1b 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -347,21 +347,6 @@ EXPORT_SYMBOL_GPL(play_idle);
 
 void cpu_startup_entry(enum cpuhp_state state)
 {
-	/*
-	 * This #ifdef needs to die, but it's too late in the cycle to
-	 * make this generic (ARM and SH have never invoked the canary
-	 * init for the non boot CPUs!). Will be fixed in 3.11
-	 */
-#ifdef CONFIG_X86
-	/*
-	 * If we're the non-boot CPU, nothing set the stack canary up
-	 * for us. The boot CPU already has it initialized but no harm
-	 * in doing it again. This is a good place for updating it, as
-	 * we wont ever return from this function (so the invalid
-	 * canaries already on the stack wont ever trigger).
-	 */
-	boot_init_stack_canary();
-#endif
 	arch_cpu_idle_prepare();
 	cpuhp_online_idle(state);
 	while (1)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index fc24f2b8c646..b8c007713b3b 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -56,7 +56,6 @@
 #include <linux/profile.h>
 #include <linux/rcupdate_wait.h>
 #include <linux/security.h>
-#include <linux/stackprotector.h>
 #include <linux/stop_machine.h>
 #include <linux/suspend.h>
 #include <linux/swait.h>
diff --git a/kernel/smp.c b/kernel/smp.c
index d86eec5f51c1..163c451af42e 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -669,9 +669,9 @@ EXPORT_SYMBOL(on_each_cpu_mask);
  * You must not call this function with disabled interrupts or
  * from a hardware interrupt handler or from a bottom half handler.
  */
-void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
+void on_each_cpu_cond_mask(bool (*cond_func)(int cpu, void *info),
 			smp_call_func_t func, void *info, bool wait,
-			gfp_t gfp_flags)
+			gfp_t gfp_flags, const struct cpumask *mask)
 {
 	cpumask_var_t cpus;
 	int cpu, ret;
@@ -680,9 +680,9 @@ void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
 
 	if (likely(zalloc_cpumask_var(&cpus, (gfp_flags|__GFP_NOWARN)))) {
 		preempt_disable();
-		for_each_online_cpu(cpu)
+		for_each_cpu(cpu, mask)
 			if (cond_func(cpu, info))
-				cpumask_set_cpu(cpu, cpus);
+				__cpumask_set_cpu(cpu, cpus);
 		on_each_cpu_mask(cpus, func, info, wait);
 		preempt_enable();
 		free_cpumask_var(cpus);
@@ -692,7 +692,7 @@ void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
 		 * just have to IPI them one by one.
 		 */
 		preempt_disable();
-		for_each_online_cpu(cpu)
+		for_each_cpu(cpu, mask)
 			if (cond_func(cpu, info)) {
 				ret = smp_call_function_single(cpu, func,
 								info, wait);
@@ -701,6 +701,15 @@ void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
 		preempt_enable();
 	}
 }
+EXPORT_SYMBOL(on_each_cpu_cond_mask);
+
+void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
+			smp_call_func_t func, void *info, bool wait,
+			gfp_t gfp_flags)
+{
+	on_each_cpu_cond_mask(cond_func, func, info, wait, gfp_flags,
+				cpu_online_mask);
+}
 EXPORT_SYMBOL(on_each_cpu_cond);
 
 static void do_nothing(void *unused)
diff --git a/kernel/up.c b/kernel/up.c
index 42c46bf3e0a5..ff536f9cc8a2 100644
--- a/kernel/up.c
+++ b/kernel/up.c
@@ -68,9 +68,9 @@ EXPORT_SYMBOL(on_each_cpu_mask);
  * Preemption is disabled here to make sure the cond_func is called under the
  * same condtions in UP and SMP.
  */
-void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
-		      smp_call_func_t func, void *info, bool wait,
-		      gfp_t gfp_flags)
+void on_each_cpu_cond_mask(bool (*cond_func)(int cpu, void *info),
+			   smp_call_func_t func, void *info, bool wait,
+			   gfp_t gfp_flags, const struct cpumask *mask)
 {
 	unsigned long flags;
 
@@ -82,6 +82,14 @@ void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
 	}
 	preempt_enable();
 }
+EXPORT_SYMBOL(on_each_cpu_cond_mask);
+
+void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
+		      smp_call_func_t func, void *info, bool wait,
+		      gfp_t gfp_flags)
+{
+	on_each_cpu_cond_mask(cond_func, func, info, wait, gfp_flags, NULL);
+}
 EXPORT_SYMBOL(on_each_cpu_cond);
 
 int smp_call_on_cpu(unsigned int cpu, int (*func)(void *), void *par, bool phys)