Merge branch 'linus' into WIP.x86/boot, to fix up conflicts and to pick up updates

 Conflicts:
	arch/x86/xen/setup.c

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

8 files changed, 104 insertions, 24 deletions

diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index ea9c49adaa1f..58b5bee7ea27 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -15,8 +15,10 @@
 #include <linux/debugfs.h>
 #include <linux/mm.h>
 #include <linux/init.h>
+#include <linux/sched.h>
 #include <linux/seq_file.h>
 
+#include <asm/kasan.h>
 #include <asm/pgtable.h>
 
 /*
@@ -50,6 +52,10 @@ enum address_markers_idx {
 	LOW_KERNEL_NR,
 	VMALLOC_START_NR,
 	VMEMMAP_START_NR,
+#ifdef CONFIG_KASAN
+	KASAN_SHADOW_START_NR,
+	KASAN_SHADOW_END_NR,
+#endif
 # ifdef CONFIG_X86_ESPFIX64
 	ESPFIX_START_NR,
 # endif
@@ -75,6 +81,10 @@ static struct addr_marker address_markers[] = {
 	{ 0/* PAGE_OFFSET */,   "Low Kernel Mapping" },
 	{ 0/* VMALLOC_START */, "vmalloc() Area" },
 	{ 0/* VMEMMAP_START */, "Vmemmap" },
+#ifdef CONFIG_KASAN
+	{ KASAN_SHADOW_START,	"KASAN shadow" },
+	{ KASAN_SHADOW_END,	"KASAN shadow end" },
+#endif
 # ifdef CONFIG_X86_ESPFIX64
 	{ ESPFIX_BASE_ADDR,	"ESPfix Area", 16 },
 # endif
@@ -326,18 +336,31 @@ static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr,
 
 #if PTRS_PER_PUD > 1
 
+/*
+ * This is an optimization for CONFIG_DEBUG_WX=y + CONFIG_KASAN=y
+ * KASAN fills page tables with the same values. Since there is no
+ * point in checking page table more than once we just skip repeated
+ * entries. This saves us dozens of seconds during boot.
+ */
+static bool pud_already_checked(pud_t *prev_pud, pud_t *pud, bool checkwx)
+{
+	return checkwx && prev_pud && (pud_val(*prev_pud) == pud_val(*pud));
+}
+
 static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr,
 							unsigned long P)
 {
 	int i;
 	pud_t *start;
 	pgprotval_t prot;
+	pud_t *prev_pud = NULL;
 
 	start = (pud_t *) pgd_page_vaddr(addr);
 
 	for (i = 0; i < PTRS_PER_PUD; i++) {
 		st->current_address = normalize_addr(P + i * PUD_LEVEL_MULT);
-		if (!pud_none(*start)) {
+		if (!pud_none(*start) &&
+		    !pud_already_checked(prev_pud, start, st->check_wx)) {
 			if (pud_large(*start) || !pud_present(*start)) {
 				prot = pud_flags(*start);
 				note_page(m, st, __pgprot(prot), 2);
@@ -348,6 +371,7 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr,
 		} else
 			note_page(m, st, __pgprot(0), 2);
 
+		prev_pud = start;
 		start++;
 	}
 }
@@ -406,6 +430,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
 		} else
 			note_page(m, &st, __pgprot(0), 1);
 
+		cond_resched();
 		start++;
 	}
 
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index 0d4fb3ebbbac..99c7805a9693 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -154,14 +154,12 @@ static inline void get_head_page_multiple(struct page *page, int nr)
 	SetPageReferenced(page);
 }
 
-static int __gup_device_huge_pmd(pmd_t pmd, unsigned long addr,
+static int __gup_device_huge(unsigned long pfn, unsigned long addr,
 		unsigned long end, struct page **pages, int *nr)
 {
 	int nr_start = *nr;
-	unsigned long pfn = pmd_pfn(pmd);
 	struct dev_pagemap *pgmap = NULL;
 
-	pfn += (addr & ~PMD_MASK) >> PAGE_SHIFT;
 	do {
 		struct page *page = pfn_to_page(pfn);
 
@@ -180,6 +178,24 @@ static int __gup_device_huge_pmd(pmd_t pmd, unsigned long addr,
 	return 1;
 }
 
+static int __gup_device_huge_pmd(pmd_t pmd, unsigned long addr,
+		unsigned long end, struct page **pages, int *nr)
+{
+	unsigned long fault_pfn;
+
+	fault_pfn = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
+	return __gup_device_huge(fault_pfn, addr, end, pages, nr);
+}
+
+static int __gup_device_huge_pud(pud_t pud, unsigned long addr,
+		unsigned long end, struct page **pages, int *nr)
+{
+	unsigned long fault_pfn;
+
+	fault_pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
+	return __gup_device_huge(fault_pfn, addr, end, pages, nr);
+}
+
 static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr,
 		unsigned long end, int write, struct page **pages, int *nr)
 {
@@ -251,9 +267,13 @@ static noinline int gup_huge_pud(pud_t pud, unsigned long addr,
 
 	if (!pte_allows_gup(pud_val(pud), write))
 		return 0;
+
+	VM_BUG_ON(!pfn_valid(pud_pfn(pud)));
+	if (pud_devmap(pud))
+		return __gup_device_huge_pud(pud, addr, end, pages, nr);
+
 	/* hugepages are never "special" */
 	VM_BUG_ON(pud_flags(pud) & _PAGE_SPECIAL);
-	VM_BUG_ON(!pfn_valid(pud_pfn(pud)));
 
 	refs = 0;
 	head = pud_page(pud);
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 70e1ad66d34a..1fa97c941abe 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -864,9 +864,6 @@ static noinline int do_test_wp_bit(void)
 	return flag;
 }
 
-const int rodata_test_data = 0xC3;
-EXPORT_SYMBOL_GPL(rodata_test_data);
-
 int kernel_set_to_readonly __read_mostly;
 
 void set_kernel_text_rw(void)
@@ -939,7 +936,6 @@ void mark_rodata_ro(void)
 	set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
 	printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
 		size >> 10);
-	rodata_test();
 
 #ifdef CONFIG_CPA_DEBUG
 	printk(KERN_INFO "Testing CPA: undo %lx-%lx\n", start, start + size);
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 94e033085f60..f6da869810a8 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -679,7 +679,7 @@ static void __meminit free_pagetable(struct page *page, int order)
 	if (PageReserved(page)) {
 		__ClearPageReserved(page);
 
-		magic = (unsigned long)page->lru.next;
+		magic = (unsigned long)page->freelist;
 		if (magic == SECTION_INFO || magic == MIX_SECTION_INFO) {
 			while (nr_pages--)
 				put_page_bootmem(page++);
@@ -1000,9 +1000,6 @@ void __init mem_init(void)
 	mem_init_print_info(NULL);
 }
 
-const int rodata_test_data = 0xC3;
-EXPORT_SYMBOL_GPL(rodata_test_data);
-
 int kernel_set_to_readonly;
 
 void set_kernel_text_rw(void)
@@ -1071,8 +1068,6 @@ void mark_rodata_ro(void)
 	all_end = roundup((unsigned long)_brk_end, PMD_SIZE);
 	set_memory_nx(text_end, (all_end - text_end) >> PAGE_SHIFT);
 
-	rodata_test();
-
 #ifdef CONFIG_CPA_DEBUG
 	printk(KERN_INFO "Testing CPA: undo %lx-%lx\n", start, end);
 	set_memory_rw(start, (end-start) >> PAGE_SHIFT);
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index af59f808742f..c98079684bdb 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -51,7 +51,7 @@ static unsigned long mpx_mmap(unsigned long len)
 
 	down_write(&mm->mmap_sem);
 	addr = do_mmap(NULL, 0, len, PROT_READ | PROT_WRITE,
-			MAP_ANONYMOUS | MAP_PRIVATE, VM_MPX, 0, &populate);
+		       MAP_ANONYMOUS | MAP_PRIVATE, VM_MPX, 0, &populate, NULL);
 	up_write(&mm->mmap_sem);
 	if (populate)
 		mm_populate(addr, populate);
@@ -796,7 +796,7 @@ static noinline int zap_bt_entries_mapping(struct mm_struct *mm,
 			return -EINVAL;
 
 		len = min(vma->vm_end, end) - addr;
-		zap_page_range(vma, addr, len, NULL);
+		zap_page_range(vma, addr, len);
 		trace_mpx_unmap_zap(addr, addr+len);
 
 		vma = vma->vm_next;
@@ -893,7 +893,7 @@ static int unmap_entire_bt(struct mm_struct *mm,
 	 * avoid recursion, do_munmap() will check whether it comes
 	 * from one bounds table through VM_MPX flag.
 	 */
-	return do_munmap(mm, bt_addr, mpx_bt_size_bytes(mm));
+	return do_munmap(mm, bt_addr, mpx_bt_size_bytes(mm), NULL);
 }
 
 static int try_unmap_single_bt(struct mm_struct *mm,
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 3e1577622cb0..a57e8e02f457 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -214,7 +214,20 @@ static void cpa_flush_array(unsigned long *start, int numpages, int cache,
 			    int in_flags, struct page **pages)
 {
 	unsigned int i, level;
+#ifdef CONFIG_PREEMPT
+	/*
+	 * Avoid wbinvd() because it causes latencies on all CPUs,
+	 * regardless of any CPU isolation that may be in effect.
+	 *
+	 * This should be extended for CAT enabled systems independent of
+	 * PREEMPT because wbinvd() does not respect the CAT partitions and
+	 * this is exposed to unpriviledged users through the graphics
+	 * subsystem.
+	 */
+	unsigned long do_wbinvd = 0;
+#else
 	unsigned long do_wbinvd = cache && numpages >= 1024; /* 4M threshold */
+#endif
 
 	BUG_ON(irqs_disabled());
 
diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c
index 159b52ccd600..d76485b22824 100644
--- a/arch/x86/mm/pat_rbtree.c
+++ b/arch/x86/mm/pat_rbtree.c
@@ -47,7 +47,7 @@ static u64 get_subtree_max_end(struct rb_node *node)
 {
 	u64 ret = 0;
 	if (node) {
-		struct memtype *data = container_of(node, struct memtype, rb);
+		struct memtype *data = rb_entry(node, struct memtype, rb);
 		ret = data->subtree_max_end;
 	}
 	return ret;
@@ -79,7 +79,7 @@ static struct memtype *memtype_rb_lowest_match(struct rb_root *root,
 	struct memtype *last_lower = NULL;
 
 	while (node) {
-		struct memtype *data = container_of(node, struct memtype, rb);
+		struct memtype *data = rb_entry(node, struct memtype, rb);
 
 		if (get_subtree_max_end(node->rb_left) > start) {
 			/* Lowest overlap if any must be on left side */
@@ -121,7 +121,7 @@ static struct memtype *memtype_rb_match(struct rb_root *root,
 
 		node = rb_next(&match->rb);
 		if (node)
-			match = container_of(node, struct memtype, rb);
+			match = rb_entry(node, struct memtype, rb);
 		else
 			match = NULL;
 	}
@@ -150,7 +150,7 @@ static int memtype_rb_check_conflict(struct rb_root *root,
 
 	node = rb_next(&match->rb);
 	while (node) {
-		match = container_of(node, struct memtype, rb);
+		match = rb_entry(node, struct memtype, rb);
 
 		if (match->start >= end) /* Checked all possible matches */
 			goto success;
@@ -181,7 +181,7 @@ static void memtype_rb_insert(struct rb_root *root, struct memtype *newdata)
 	struct rb_node *parent = NULL;
 
 	while (*node) {
-		struct memtype *data = container_of(*node, struct memtype, rb);
+		struct memtype *data = rb_entry(*node, struct memtype, rb);
 
 		parent = *node;
 		if (data->subtree_max_end < newdata->end)
@@ -270,7 +270,7 @@ int rbt_memtype_copy_nth_element(struct memtype *out, loff_t pos)
 	}
 
 	if (node) { /* pos == i */
-		struct memtype *this = container_of(node, struct memtype, rb);
+		struct memtype *this = rb_entry(node, struct memtype, rb);
 		*out = *this;
 		return 0;
 	} else {
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 3feec5af4e67..6cbdff26bb96 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -445,6 +445,26 @@ int pmdp_set_access_flags(struct vm_area_struct *vma,
 
 	return changed;
 }
+
+int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address,
+			  pud_t *pudp, pud_t entry, int dirty)
+{
+	int changed = !pud_same(*pudp, entry);
+
+	VM_BUG_ON(address & ~HPAGE_PUD_MASK);
+
+	if (changed && dirty) {
+		*pudp = entry;
+		/*
+		 * We had a write-protection fault here and changed the pud
+		 * to to more permissive. No need to flush the TLB for that,
+		 * #PF is architecturally guaranteed to do that and in the
+		 * worst-case we'll generate a spurious fault.
+		 */
+	}
+
+	return changed;
+}
 #endif
 
 int ptep_test_and_clear_young(struct vm_area_struct *vma,
@@ -474,6 +494,17 @@ int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 
 	return ret;
 }
+int pudp_test_and_clear_young(struct vm_area_struct *vma,
+			      unsigned long addr, pud_t *pudp)
+{
+	int ret = 0;
+
+	if (pud_young(*pudp))
+		ret = test_and_clear_bit(_PAGE_BIT_ACCESSED,
+					 (unsigned long *)pudp);
+
+	return ret;
+}
 #endif
 
 int ptep_clear_flush_young(struct vm_area_struct *vma,