Merge tag 'v4.2-rc8' into x86/mm, before applying new changes

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

9 files changed, 384 insertions, 241 deletions

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 181c53bac3a7..9dc909841739 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -13,6 +13,7 @@
 #include <linux/hugetlb.h>		/* hstate_index_to_shift	*/
 #include <linux/prefetch.h>		/* prefetchw			*/
 #include <linux/context_tracking.h>	/* exception_enter(), ...	*/
+#include <linux/uaccess.h>		/* faulthandler_disabled()	*/
 
 #include <asm/traps.h>			/* dotraplinkage, ...		*/
 #include <asm/pgalloc.h>		/* pgd_*(), ...			*/
@@ -1126,9 +1127,9 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
 
 	/*
 	 * If we're in an interrupt, have no user context or are running
-	 * in an atomic region then we must not take the fault:
+	 * in a region with pagefaults disabled then we must not take the fault
 	 */
-	if (unlikely(in_atomic() || !mm)) {
+	if (unlikely(faulthandler_disabled() || !mm)) {
 		bad_area_nosemaphore(regs, error_code, address);
 		return;
 	}
diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
index 4500142bc4aa..eecb207a2037 100644
--- a/arch/x86/mm/highmem_32.c
+++ b/arch/x86/mm/highmem_32.c
@@ -35,7 +35,7 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot)
 	unsigned long vaddr;
 	int idx, type;
 
-	/* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+	preempt_disable();
 	pagefault_disable();
 
 	if (!PageHighMem(page))
@@ -100,6 +100,7 @@ void __kunmap_atomic(void *kvaddr)
 #endif
 
 	pagefault_enable();
+	preempt_enable();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
 
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index c23ab1ee3a9a..68aec42545c2 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -434,7 +434,7 @@ void __init add_highpages_with_active_regions(int nid,
 	phys_addr_t start, end;
 	u64 i;
 
-	for_each_free_mem_range(i, nid, &start, &end, NULL) {
+	for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &start, &end, NULL) {
 		unsigned long pfn = clamp_t(unsigned long, PFN_UP(start),
 					    start_pfn, end_pfn);
 		unsigned long e_pfn = clamp_t(unsigned long, PFN_DOWN(end),
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index a9dc7a37e6a2..9c0ff045fdd4 100644
--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@@ -59,6 +59,7 @@ void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot)
 	unsigned long vaddr;
 	int idx, type;
 
+	preempt_disable();
 	pagefault_disable();
 
 	type = kmap_atomic_idx_push();
@@ -117,5 +118,6 @@ iounmap_atomic(void __iomem *kvaddr)
 	}
 
 	pagefault_enable();
+	preempt_enable();
 }
 EXPORT_SYMBOL_GPL(iounmap_atomic);
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 8405c0c6a535..b9c78f3bcd67 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -63,8 +63,6 @@ static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages,
 		    !PageReserved(pfn_to_page(start_pfn + i)))
 			return 1;
 
-	WARN_ONCE(1, "ioremap on RAM pfn 0x%lx\n", start_pfn);
-
 	return 0;
 }
 
@@ -94,7 +92,6 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 	pgprot_t prot;
 	int retval;
 	void __iomem *ret_addr;
-	int ram_region;
 
 	/* Don't allow wraparound or zero size */
 	last_addr = phys_addr + size - 1;
@@ -117,23 +114,15 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 	/*
 	 * Don't allow anybody to remap normal RAM that we're using..
 	 */
-	/* First check if whole region can be identified as RAM or not */
-	ram_region = region_is_ram(phys_addr, size);
-	if (ram_region > 0) {
-		WARN_ONCE(1, "ioremap on RAM at 0x%lx - 0x%lx\n",
-				(unsigned long int)phys_addr,
-				(unsigned long int)last_addr);
+	pfn      = phys_addr >> PAGE_SHIFT;
+	last_pfn = last_addr >> PAGE_SHIFT;
+	if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL,
+					  __ioremap_check_ram) == 1) {
+		WARN_ONCE(1, "ioremap on RAM at %pa - %pa\n",
+			  &phys_addr, &last_addr);
 		return NULL;
 	}
 
-	/* If could not be identified(-1), check page by page */
-	if (ram_region < 0) {
-		pfn      = phys_addr >> PAGE_SHIFT;
-		last_pfn = last_addr >> PAGE_SHIFT;
-		if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL,
-					  __ioremap_check_ram) == 1)
-			return NULL;
-	}
 	/*
 	 * Mappings have to be page-aligned
 	 */
@@ -408,18 +397,18 @@ void *xlate_dev_mem_ptr(phys_addr_t phys)
 {
 	unsigned long start  = phys &  PAGE_MASK;
 	unsigned long offset = phys & ~PAGE_MASK;
-	unsigned long vaddr;
+	void *vaddr;
 
 	/* If page is RAM, we can use __va. Otherwise ioremap and unmap. */
 	if (page_is_ram(start >> PAGE_SHIFT))
 		return __va(phys);
 
-	vaddr = (unsigned long)ioremap_cache(start, PAGE_SIZE);
+	vaddr = ioremap_cache(start, PAGE_SIZE);
 	/* Only add the offset on success and return NULL if the ioremap() failed: */
 	if (vaddr)
 		vaddr += offset;
 
-	return (void *)vaddr;
+	return vaddr;
 }
 
 void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr)
@@ -428,7 +417,6 @@ void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr)
 		return;
 
 	iounmap((void __iomem *)((unsigned long)addr & PAGE_MASK));
-	return;
 }
 
 static pte_t bm_pte[PAGE_SIZE/sizeof(pte_t)] __page_aligned_bss;
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 4860906c6b9f..e1840f3db5b5 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -1,3 +1,4 @@
+#define pr_fmt(fmt) "kasan: " fmt
 #include <linux/bootmem.h>
 #include <linux/kasan.h>
 #include <linux/kdebug.h>
@@ -11,7 +12,19 @@
 extern pgd_t early_level4_pgt[PTRS_PER_PGD];
 extern struct range pfn_mapped[E820_X_MAX];
 
-extern unsigned char kasan_zero_page[PAGE_SIZE];
+static pud_t kasan_zero_pud[PTRS_PER_PUD] __page_aligned_bss;
+static pmd_t kasan_zero_pmd[PTRS_PER_PMD] __page_aligned_bss;
+static pte_t kasan_zero_pte[PTRS_PER_PTE] __page_aligned_bss;
+
+/*
+ * This page used as early shadow. We don't use empty_zero_page
+ * at early stages, stack instrumentation could write some garbage
+ * to this page.
+ * Latter we reuse it as zero shadow for large ranges of memory
+ * that allowed to access, but not instrumented by kasan
+ * (vmalloc/vmemmap ...).
+ */
+static unsigned char kasan_zero_page[PAGE_SIZE] __page_aligned_bss;
 
 static int __init map_range(struct range *range)
 {
@@ -36,7 +49,7 @@ static void __init clear_pgds(unsigned long start,
 		pgd_clear(pgd_offset_k(start));
 }
 
-void __init kasan_map_early_shadow(pgd_t *pgd)
+static void __init kasan_map_early_shadow(pgd_t *pgd)
 {
 	int i;
 	unsigned long start = KASAN_SHADOW_START;
@@ -73,7 +86,7 @@ static int __init zero_pmd_populate(pud_t *pud, unsigned long addr,
 	while (IS_ALIGNED(addr, PMD_SIZE) && addr + PMD_SIZE <= end) {
 		WARN_ON(!pmd_none(*pmd));
 		set_pmd(pmd, __pmd(__pa_nodebug(kasan_zero_pte)
-					| __PAGE_KERNEL_RO));
+					| _KERNPG_TABLE));
 		addr += PMD_SIZE;
 		pmd = pmd_offset(pud, addr);
 	}
@@ -99,7 +112,7 @@ static int __init zero_pud_populate(pgd_t *pgd, unsigned long addr,
 	while (IS_ALIGNED(addr, PUD_SIZE) && addr + PUD_SIZE <= end) {
 		WARN_ON(!pud_none(*pud));
 		set_pud(pud, __pud(__pa_nodebug(kasan_zero_pmd)
-					| __PAGE_KERNEL_RO));
+					| _KERNPG_TABLE));
 		addr += PUD_SIZE;
 		pud = pud_offset(pgd, addr);
 	}
@@ -124,7 +137,7 @@ static int __init zero_pgd_populate(unsigned long addr, unsigned long end)
 	while (IS_ALIGNED(addr, PGDIR_SIZE) && addr + PGDIR_SIZE <= end) {
 		WARN_ON(!pgd_none(*pgd));
 		set_pgd(pgd, __pgd(__pa_nodebug(kasan_zero_pud)
-					| __PAGE_KERNEL_RO));
+					| _KERNPG_TABLE));
 		addr += PGDIR_SIZE;
 		pgd = pgd_offset_k(addr);
 	}
@@ -166,6 +179,26 @@ static struct notifier_block kasan_die_notifier = {
 };
 #endif
 
+void __init kasan_early_init(void)
+{
+	int i;
+	pteval_t pte_val = __pa_nodebug(kasan_zero_page) | __PAGE_KERNEL;
+	pmdval_t pmd_val = __pa_nodebug(kasan_zero_pte) | _KERNPG_TABLE;
+	pudval_t pud_val = __pa_nodebug(kasan_zero_pmd) | _KERNPG_TABLE;
+
+	for (i = 0; i < PTRS_PER_PTE; i++)
+		kasan_zero_pte[i] = __pte(pte_val);
+
+	for (i = 0; i < PTRS_PER_PMD; i++)
+		kasan_zero_pmd[i] = __pmd(pmd_val);
+
+	for (i = 0; i < PTRS_PER_PUD; i++)
+		kasan_zero_pud[i] = __pud(pud_val);
+
+	kasan_map_early_shadow(early_level4_pgt);
+	kasan_map_early_shadow(init_level4_pgt);
+}
+
 void __init kasan_init(void)
 {
 	int i;
@@ -176,6 +209,7 @@ void __init kasan_init(void)
 
 	memcpy(early_level4_pgt, init_level4_pgt, sizeof(early_level4_pgt));
 	load_cr3(early_level4_pgt);
+	__flush_tlb_all();
 
 	clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END);
 
@@ -202,5 +236,8 @@ void __init kasan_init(void)
 	memset(kasan_zero_page, 0, PAGE_SIZE);
 
 	load_cr3(init_level4_pgt);
+	__flush_tlb_all();
 	init_task.kasan_depth = 0;
+
+	pr_info("Kernel address sanitizer initialized\n");
 }
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 9d518d693b4b..844b06d67df4 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -126,3 +126,10 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
 	}
 }
+
+const char *arch_vma_name(struct vm_area_struct *vma)
+{
+	if (vma->vm_flags & VM_MPX)
+		return "[mpx]";
+	return NULL;
+}
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index c439ec478216..db1b0bc5017c 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -10,34 +10,35 @@
 #include <linux/syscalls.h>
 #include <linux/sched/sysctl.h>
 
-#include <asm/i387.h>
 #include <asm/insn.h>
 #include <asm/mman.h>
 #include <asm/mmu_context.h>
 #include <asm/mpx.h>
 #include <asm/processor.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
 
-static const char *mpx_mapping_name(struct vm_area_struct *vma)
+#define CREATE_TRACE_POINTS
+#include <asm/trace/mpx.h>
+
+static inline unsigned long mpx_bd_size_bytes(struct mm_struct *mm)
 {
-	return "[mpx]";
+	if (is_64bit_mm(mm))
+		return MPX_BD_SIZE_BYTES_64;
+	else
+		return MPX_BD_SIZE_BYTES_32;
 }
 
-static struct vm_operations_struct mpx_vma_ops = {
-	.name = mpx_mapping_name,
-};
-
-static int is_mpx_vma(struct vm_area_struct *vma)
+static inline unsigned long mpx_bt_size_bytes(struct mm_struct *mm)
 {
-	return (vma->vm_ops == &mpx_vma_ops);
+	if (is_64bit_mm(mm))
+		return MPX_BT_SIZE_BYTES_64;
+	else
+		return MPX_BT_SIZE_BYTES_32;
 }
 
 /*
  * This is really a simplified "vm_mmap". it only handles MPX
  * bounds tables (the bounds directory is user-allocated).
- *
- * Later on, we use the vma->vm_ops to uniquely identify these
- * VMAs.
  */
 static unsigned long mpx_mmap(unsigned long len)
 {
@@ -47,8 +48,8 @@ static unsigned long mpx_mmap(unsigned long len)
 	vm_flags_t vm_flags;
 	struct vm_area_struct *vma;
 
-	/* Only bounds table and bounds directory can be allocated here */
-	if (len != MPX_BD_SIZE_BYTES && len != MPX_BT_SIZE_BYTES)
+	/* Only bounds table can be allocated here */
+	if (len != mpx_bt_size_bytes(mm))
 		return -EINVAL;
 
 	down_write(&mm->mmap_sem);
@@ -83,7 +84,6 @@ static unsigned long mpx_mmap(unsigned long len)
 		ret = -ENOMEM;
 		goto out;
 	}
-	vma->vm_ops = &mpx_vma_ops;
 
 	if (vm_flags & VM_LOCKED) {
 		up_write(&mm->mmap_sem);
@@ -272,10 +272,9 @@ bad_opcode:
  *
  * The caller is expected to kfree() the returned siginfo_t.
  */
-siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
-				struct xsave_struct *xsave_buf)
+siginfo_t *mpx_generate_siginfo(struct pt_regs *regs)
 {
-	struct bndreg *bndregs, *bndreg;
+	const struct bndreg *bndregs, *bndreg;
 	siginfo_t *info = NULL;
 	struct insn insn;
 	uint8_t bndregno;
@@ -295,8 +294,8 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
 		err = -EINVAL;
 		goto err_out;
 	}
-	/* get the bndregs _area_ of the xsave structure */
-	bndregs = get_xsave_addr(xsave_buf, XSTATE_BNDREGS);
+	/* get bndregs field from current task's xsave area */
+	bndregs = get_xsave_field_ptr(XSTATE_BNDREGS);
 	if (!bndregs) {
 		err = -EINVAL;
 		goto err_out;
@@ -334,6 +333,7 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
 		err = -EINVAL;
 		goto err_out;
 	}
+	trace_mpx_bounds_register_exception(info->si_addr, bndreg);
 	return info;
 err_out:
 	/* info might be NULL, but kfree() handles that */
@@ -341,25 +341,18 @@ err_out:
 	return ERR_PTR(err);
 }
 
-static __user void *task_get_bounds_dir(struct task_struct *tsk)
+static __user void *mpx_get_bounds_dir(void)
 {
-	struct bndcsr *bndcsr;
+	const struct bndcsr *bndcsr;
 
 	if (!cpu_feature_enabled(X86_FEATURE_MPX))
 		return MPX_INVALID_BOUNDS_DIR;
 
 	/*
-	 * 32-bit binaries on 64-bit kernels are currently
-	 * unsupported.
-	 */
-	if (IS_ENABLED(CONFIG_X86_64) && test_thread_flag(TIF_IA32))
-		return MPX_INVALID_BOUNDS_DIR;
-	/*
 	 * The bounds directory pointer is stored in a register
 	 * only accessible if we first do an xsave.
 	 */
-	fpu_save_init(&tsk->thread.fpu);
-	bndcsr = get_xsave_addr(&tsk->thread.fpu.state->xsave, XSTATE_BNDCSR);
+	bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR);
 	if (!bndcsr)
 		return MPX_INVALID_BOUNDS_DIR;
 
@@ -378,10 +371,10 @@ static __user void *task_get_bounds_dir(struct task_struct *tsk)
 		(bndcsr->bndcfgu & MPX_BNDCFG_ADDR_MASK);
 }
 
-int mpx_enable_management(struct task_struct *tsk)
+int mpx_enable_management(void)
 {
 	void __user *bd_base = MPX_INVALID_BOUNDS_DIR;
-	struct mm_struct *mm = tsk->mm;
+	struct mm_struct *mm = current->mm;
 	int ret = 0;
 
 	/*
@@ -390,11 +383,12 @@ int mpx_enable_management(struct task_struct *tsk)
 	 * directory into XSAVE/XRSTOR Save Area and enable MPX through
 	 * XRSTOR instruction.
 	 *
-	 * fpu_xsave() is expected to be very expensive. Storing the bounds
-	 * directory here means that we do not have to do xsave in the unmap
-	 * path; we can just use mm->bd_addr instead.
+	 * The copy_xregs_to_kernel() beneath get_xsave_field_ptr() is
+	 * expected to be relatively expensive. Storing the bounds
+	 * directory here means that we do not have to do xsave in the
+	 * unmap path; we can just use mm->bd_addr instead.
 	 */
-	bd_base = task_get_bounds_dir(tsk);
+	bd_base = mpx_get_bounds_dir();
 	down_write(&mm->mmap_sem);
 	mm->bd_addr = bd_base;
 	if (mm->bd_addr == MPX_INVALID_BOUNDS_DIR)
@@ -404,7 +398,7 @@ int mpx_enable_management(struct task_struct *tsk)
 	return ret;
 }
 
-int mpx_disable_management(struct task_struct *tsk)
+int mpx_disable_management(void)
 {
 	struct mm_struct *mm = current->mm;
 
@@ -417,29 +411,59 @@ int mpx_disable_management(struct task_struct *tsk)
 	return 0;
 }
 
+static int mpx_cmpxchg_bd_entry(struct mm_struct *mm,
+		unsigned long *curval,
+		unsigned long __user *addr,
+		unsigned long old_val, unsigned long new_val)
+{
+	int ret;
+	/*
+	 * user_atomic_cmpxchg_inatomic() actually uses sizeof()
+	 * the pointer that we pass to it to figure out how much
+	 * data to cmpxchg.  We have to be careful here not to
+	 * pass a pointer to a 64-bit data type when we only want
+	 * a 32-bit copy.
+	 */
+	if (is_64bit_mm(mm)) {
+		ret = user_atomic_cmpxchg_inatomic(curval,
+				addr, old_val, new_val);
+	} else {
+		u32 uninitialized_var(curval_32);
+		u32 old_val_32 = old_val;
+		u32 new_val_32 = new_val;
+		u32 __user *addr_32 = (u32 __user *)addr;
+
+		ret = user_atomic_cmpxchg_inatomic(&curval_32,
+				addr_32, old_val_32, new_val_32);
+		*curval = curval_32;
+	}
+	return ret;
+}
+
 /*
- * With 32-bit mode, MPX_BT_SIZE_BYTES is 4MB, and the size of each
- * bounds table is 16KB. With 64-bit mode, MPX_BT_SIZE_BYTES is 2GB,
+ * With 32-bit mode, a bounds directory is 4MB, and the size of each
+ * bounds table is 16KB. With 64-bit mode, a bounds directory is 2GB,
  * and the size of each bounds table is 4MB.
  */
-static int allocate_bt(long __user *bd_entry)
+static int allocate_bt(struct mm_struct *mm, long __user *bd_entry)
 {
 	unsigned long expected_old_val = 0;
 	unsigned long actual_old_val = 0;
 	unsigned long bt_addr;
+	unsigned long bd_new_entry;
 	int ret = 0;
 
 	/*
 	 * Carve the virtual space out of userspace for the new
 	 * bounds table:
 	 */
-	bt_addr = mpx_mmap(MPX_BT_SIZE_BYTES);
+	bt_addr = mpx_mmap(mpx_bt_size_bytes(mm));
 	if (IS_ERR((void *)bt_addr))
 		return PTR_ERR((void *)bt_addr);
 	/*
 	 * Set the valid flag (kinda like _PAGE_PRESENT in a pte)
 	 */
-	bt_addr = bt_addr | MPX_BD_ENTRY_VALID_FLAG;
+	bd_new_entry = bt_addr | MPX_BD_ENTRY_VALID_FLAG;
 
 	/*
 	 * Go poke the address of the new bounds table in to the
@@ -452,8 +476,8 @@ static int allocate_bt(long __user *bd_entry)
 	 * mmap_sem at this point, unlike some of the other part
 	 * of the MPX code that have to pagefault_disable().
 	 */
-	ret = user_atomic_cmpxchg_inatomic(&actual_old_val, bd_entry,
-					   expected_old_val, bt_addr);
+	ret = mpx_cmpxchg_bd_entry(mm, &actual_old_val,	bd_entry,
+				   expected_old_val, bd_new_entry);
 	if (ret)
 		goto out_unmap;
 
@@ -481,9 +505,10 @@ static int allocate_bt(long __user *bd_entry)
 		ret = -EINVAL;
 		goto out_unmap;
 	}
+	trace_mpx_new_bounds_table(bt_addr);
 	return 0;
 out_unmap:
-	vm_munmap(bt_addr & MPX_BT_ADDR_MASK, MPX_BT_SIZE_BYTES);
+	vm_munmap(bt_addr, mpx_bt_size_bytes(mm));
 	return ret;
 }
 
@@ -498,12 +523,13 @@ out_unmap:
  * bound table is 16KB. With 64-bit mode, the size of BD is 2GB,
  * and the size of each bound table is 4MB.
  */
-static int do_mpx_bt_fault(struct xsave_struct *xsave_buf)
+static int do_mpx_bt_fault(void)
 {
 	unsigned long bd_entry, bd_base;
-	struct bndcsr *bndcsr;
+	const struct bndcsr *bndcsr;
+	struct mm_struct *mm = current->mm;
 
-	bndcsr = get_xsave_addr(xsave_buf, XSTATE_BNDCSR);
+	bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR);
 	if (!bndcsr)
 		return -EINVAL;
 	/*
@@ -520,13 +546,13 @@ static int do_mpx_bt_fault(struct xsave_struct *xsave_buf)
 	 * the directory is.
 	 */
 	if ((bd_entry < bd_base) ||
-	    (bd_entry >= bd_base + MPX_BD_SIZE_BYTES))
+	    (bd_entry >= bd_base + mpx_bd_size_bytes(mm)))
 		return -EINVAL;
 
-	return allocate_bt((long __user *)bd_entry);
+	return allocate_bt(mm, (long __user *)bd_entry);
 }
 
-int mpx_handle_bd_fault(struct xsave_struct *xsave_buf)
+int mpx_handle_bd_fault(void)
 {
 	/*
 	 * Userspace never asked us to manage the bounds tables,
@@ -535,7 +561,7 @@ int mpx_handle_bd_fault(struct xsave_struct *xsave_buf)
 	if (!kernel_managing_mpx_tables(current->mm))
 		return -EINVAL;
 
-	if (do_mpx_bt_fault(xsave_buf)) {
+	if (do_mpx_bt_fault()) {
 		force_sig(SIGSEGV, current);
 		/*
 		 * The force_sig() is essentially "handling" this
@@ -572,29 +598,55 @@ static int mpx_resolve_fault(long __user *addr, int write)
 	return 0;
 }
 
+static unsigned long mpx_bd_entry_to_bt_addr(struct mm_struct *mm,
+					     unsigned long bd_entry)
+{
+	unsigned long bt_addr = bd_entry;
+	int align_to_bytes;
+	/*
+	 * Bit 0 in a bt_entry is always the valid bit.
+	 */
+	bt_addr &= ~MPX_BD_ENTRY_VALID_FLAG;
+	/*
+	 * Tables are naturally aligned at 8-byte boundaries
+	 * on 64-bit and 4-byte boundaries on 32-bit.  The
+	 * documentation makes it appear that the low bits
+	 * are ignored by the hardware, so we do the same.
+	 */
+	if (is_64bit_mm(mm))
+		align_to_bytes = 8;
+	else
+		align_to_bytes = 4;
+	bt_addr &= ~(align_to_bytes-1);
+	return bt_addr;
+}
+
 /*
  * Get the base of bounds tables pointed by specific bounds
  * directory entry.
  */
 static int get_bt_addr(struct mm_struct *mm,
-			long __user *bd_entry, unsigned long *bt_addr)
+			long __user *bd_entry_ptr,
+			unsigned long *bt_addr_result)
 {
 	int ret;
 	int valid_bit;
+	unsigned long bd_entry;
+	unsigned long bt_addr;
 
-	if (!access_ok(VERIFY_READ, (bd_entry), sizeof(*bd_entry)))
+	if (!access_ok(VERIFY_READ, (bd_entry_ptr), sizeof(*bd_entry_ptr)))
 		return -EFAULT;
 
 	while (1) {
 		int need_write = 0;
 
 		pagefault_disable();
-		ret = get_user(*bt_addr, bd_entry);
+		ret = get_user(bd_entry, bd_entry_ptr);
 		pagefault_enable();
 		if (!ret)
 			break;
 		if (ret == -EFAULT)
-			ret = mpx_resolve_fault(bd_entry, need_write);
+			ret = mpx_resolve_fault(bd_entry_ptr, need_write);
 		/*
 		 * If we could not resolve the fault, consider it
 		 * userspace's fault and error out.
@@ -603,8 +655,8 @@ static int get_bt_addr(struct mm_struct *mm,
 			return ret;
 	}
 
-	valid_bit = *bt_addr & MPX_BD_ENTRY_VALID_FLAG;
-	*bt_addr &= MPX_BT_ADDR_MASK;
+	valid_bit = bd_entry & MPX_BD_ENTRY_VALID_FLAG;
+	bt_addr = mpx_bd_entry_to_bt_addr(mm, bd_entry);
 
 	/*
 	 * When the kernel is managing bounds tables, a bounds directory
@@ -613,7 +665,7 @@ static int get_bt_addr(struct mm_struct *mm,
 	 * data in the address field, we know something is wrong. This
 	 * -EINVAL return will cause a SIGSEGV.
 	 */
-	if (!valid_bit && *bt_addr)
+	if (!valid_bit && bt_addr)
 		return -EINVAL;
 	/*
 	 * Do we have an completely zeroed bt entry?  That is OK.  It
@@ -624,19 +676,100 @@ static int get_bt_addr(struct mm_struct *mm,
 	if (!valid_bit)
 		return -ENOENT;
 
+	*bt_addr_result = bt_addr;
 	return 0;
 }
 
+static inline int bt_entry_size_bytes(struct mm_struct *mm)
+{
+	if (is_64bit_mm(mm))
+		return MPX_BT_ENTRY_BYTES_64;
+	else
+		return MPX_BT_ENTRY_BYTES_32;
+}
+
+/*
+ * Take a virtual address and turns it in to the offset in bytes
+ * inside of the bounds table where the bounds table entry
+ * controlling 'addr' can be found.
+ */
+static unsigned long mpx_get_bt_entry_offset_bytes(struct mm_struct *mm,
+		unsigned long addr)
+{
+	unsigned long bt_table_nr_entries;
+	unsigned long offset = addr;
+
+	if (is_64bit_mm(mm)) {
+		/* Bottom 3 bits are ignored on 64-bit */
+		offset >>= 3;
+		bt_table_nr_entries = MPX_BT_NR_ENTRIES_64;
+	} else {
+		/* Bottom 2 bits are ignored on 32-bit */
+		offset >>= 2;
+		bt_table_nr_entries = MPX_BT_NR_ENTRIES_32;
+	}
+	/*
+	 * We know the size of the table in to which we are
+	 * indexing, and we have eliminated all the low bits
+	 * which are ignored for indexing.
+	 *
+	 * Mask out all the high bits which we do not need
+	 * to index in to the table.  Note that the tables
+	 * are always powers of two so this gives us a proper
+	 * mask.
+	 */
+	offset &= (bt_table_nr_entries-1);
+	/*
+	 * We now have an entry offset in terms of *entries* in
+	 * the table.  We need to scale it back up to bytes.
+	 */
+	offset *= bt_entry_size_bytes(mm);
+	return offset;
+}
+
+/*
+ * How much virtual address space does a single bounds
+ * directory entry cover?
+ *
+ * Note, we need a long long because 4GB doesn't fit in
+ * to a long on 32-bit.
+ */
+static inline unsigned long bd_entry_virt_space(struct mm_struct *mm)
+{
+	unsigned long long virt_space = (1ULL << boot_cpu_data.x86_virt_bits);
+	if (is_64bit_mm(mm))
+		return virt_space / MPX_BD_NR_ENTRIES_64;
+	else
+		return virt_space / MPX_BD_NR_ENTRIES_32;
+}
+
 /*
  * Free the backing physical pages of bounds table 'bt_addr'.
  * Assume start...end is within that bounds table.
  */
-static int zap_bt_entries(struct mm_struct *mm,
+static noinline int zap_bt_entries_mapping(struct mm_struct *mm,
 		unsigned long bt_addr,
-		unsigned long start, unsigned long end)
+		unsigned long start_mapping, unsigned long end_mapping)
 {
 	struct vm_area_struct *vma;
 	unsigned long addr, len;
+	unsigned long start;
+	unsigned long end;
+
+	/*
+	 * if we 'end' on a boundary, the offset will be 0 which
+	 * is not what we want.  Back it up a byte to get the
+	 * last bt entry.  Then once we have the entry itself,
+	 * move 'end' back up by the table entry size.
+	 */
+	start = bt_addr + mpx_get_bt_entry_offset_bytes(mm, start_mapping);
+	end   = bt_addr + mpx_get_bt_entry_offset_bytes(mm, end_mapping - 1);
+	/*
+	 * Move end back up by one entry.  Among other things
+	 * this ensures that it remains page-aligned and does
+	 * not screw up zap_page_range()
+	 */
+	end += bt_entry_size_bytes(mm);
 
 	/*
 	 * Find the first overlapping vma. If vma->vm_start > start, there
@@ -648,7 +781,7 @@ static int zap_bt_entries(struct mm_struct *mm,
 		return -EINVAL;
 
 	/*
-	 * A NUMA policy on a VM_MPX VMA could cause this bouds table to
+	 * A NUMA policy on a VM_MPX VMA could cause this bounds table to
 	 * be split. So we need to look across the entire 'start -> end'
 	 * range of this bounds table, find all of the VM_MPX VMAs, and
 	 * zap only those.
@@ -661,32 +794,70 @@ static int zap_bt_entries(struct mm_struct *mm,
 		 * so stop immediately and return an error.  This
 		 * probably results in a SIGSEGV.
 		 */
-		if (!is_mpx_vma(vma))
+		if (!(vma->vm_flags & VM_MPX))
 			return -EINVAL;
 
 		len = min(vma->vm_end, end) - addr;
 		zap_page_range(vma, addr, len, NULL);
+		trace_mpx_unmap_zap(addr, addr+len);
 
 		vma = vma->vm_next;
 		addr = vma->vm_start;
 	}
-
 	return 0;
 }
 
-static int unmap_single_bt(struct mm_struct *mm,
+static unsigned long mpx_get_bd_entry_offset(struct mm_struct *mm,
+		unsigned long addr)
+{
+	/*
+	 * There are several ways to derive the bd offsets.  We
+	 * use the following approach here:
+	 * 1. We know the size of the virtual address space
+	 * 2. We know the number of entries in a bounds table
+	 * 3. We know that each entry covers a fixed amount of
+	 *    virtual address space.
+	 * So, we can just divide the virtual address by the
+	 * virtual space used by one entry to determine which
+	 * entry "controls" the given virtual address.
+	 */
+	if (is_64bit_mm(mm)) {
+		int bd_entry_size = 8; /* 64-bit pointer */
+		/*
+		 * Take the 64-bit addressing hole in to account.
+		 */
+		addr &= ((1UL << boot_cpu_data.x86_virt_bits) - 1);
+		return (addr / bd_entry_virt_space(mm)) * bd_entry_size;
+	} else {
+		int bd_entry_size = 4; /* 32-bit pointer */
+		/*
+		 * 32-bit has no hole so this case needs no mask
+		 */
+		return (addr / bd_entry_virt_space(mm)) * bd_entry_size;
+	}
+	/*
+	 * The two return calls above are exact copies.  If we
+	 * pull out a single copy and put it in here, gcc won't
+	 * realize that we're doing a power-of-2 divide and use
+	 * shifts.  It uses a real divide.  If we put them up
+	 * there, it manages to figure it out (gcc 4.8.3).
+	 */
+}
+
+static int unmap_entire_bt(struct mm_struct *mm,
 		long __user *bd_entry, unsigned long bt_addr)
 {
 	unsigned long expected_old_val = bt_addr | MPX_BD_ENTRY_VALID_FLAG;
-	unsigned long actual_old_val = 0;
+	unsigned long uninitialized_var(actual_old_val);
 	int ret;
 
 	while (1) {
 		int need_write = 1;
+		unsigned long cleared_bd_entry = 0;
 
 		pagefault_disable();
-		ret = user_atomic_cmpxchg_inatomic(&actual_old_val, bd_entry,
-						   expected_old_val, 0);
+		ret = mpx_cmpxchg_bd_entry(mm, &actual_old_val,
+				bd_entry, expected_old_val, cleared_bd_entry);
 		pagefault_enable();
 		if (!ret)
 			break;
@@ -705,9 +876,8 @@ static int unmap_single_bt(struct mm_struct *mm,
 	if (actual_old_val != expected_old_val) {
 		/*
 		 * Someone else raced with us to unmap the table.
-		 * There was no bounds table pointed to by the
-		 * directory, so declare success.  Somebody freed
-		 * it.
+		 * That is OK, since we were both trying to do
+		 * the same thing.  Declare success.
 		 */
 		if (!actual_old_val)
 			return 0;
@@ -720,176 +890,113 @@ static int unmap_single_bt(struct mm_struct *mm,
 		 */
 		return -EINVAL;
 	}
-
 	/*
 	 * Note, we are likely being called under do_munmap() already. To
 	 * 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);
+	return do_munmap(mm, bt_addr, mpx_bt_size_bytes(mm));
 }
 
-/*
- * If the bounds table pointed by bounds directory 'bd_entry' is
- * not shared, unmap this whole bounds table. Otherwise, only free
- * those backing physical pages of bounds table entries covered
- * in this virtual address region start...end.
- */
-static int unmap_shared_bt(struct mm_struct *mm,
-		long __user *bd_entry, unsigned long start,
-		unsigned long end, bool prev_shared, bool next_shared)
+static int try_unmap_single_bt(struct mm_struct *mm,
+	       unsigned long start, unsigned long end)
 {
-	unsigned long bt_addr;
-	int ret;
-
-	ret = get_bt_addr(mm, bd_entry, &bt_addr);
+	struct vm_area_struct *next;
+	struct vm_area_struct *prev;
 	/*
-	 * We could see an "error" ret for not-present bounds
-	 * tables (not really an error), or actual errors, but
-	 * stop unmapping either way.
+	 * "bta" == Bounds Table Area: the area controlled by the
+	 * bounds table that we are unmapping.
 	 */
-	if (ret)
-		return ret;
-
-	if (prev_shared && next_shared)
-		ret = zap_bt_entries(mm, bt_addr,
-				bt_addr+MPX_GET_BT_ENTRY_OFFSET(start),
-				bt_addr+MPX_GET_BT_ENTRY_OFFSET(end));
-	else if (prev_shared)
-		ret = zap_bt_entries(mm, bt_addr,
-				bt_addr+MPX_GET_BT_ENTRY_OFFSET(start),
-				bt_addr+MPX_BT_SIZE_BYTES);
-	else if (next_shared)
-		ret = zap_bt_entries(mm, bt_addr, bt_addr,
-				bt_addr+MPX_GET_BT_ENTRY_OFFSET(end));
-	else
-		ret = unmap_single_bt(mm, bd_entry, bt_addr);
-
-	return ret;
-}
-
-/*
- * A virtual address region being munmap()ed might share bounds table
- * with adjacent VMAs. We only need to free the backing physical
- * memory of these shared bounds tables entries covered in this virtual
- * address region.
- */
-static int unmap_edge_bts(struct mm_struct *mm,
-		unsigned long start, unsigned long end)
-{
+	unsigned long bta_start_vaddr = start & ~(bd_entry_virt_space(mm)-1);
+	unsigned long bta_end_vaddr = bta_start_vaddr + bd_entry_virt_space(mm);
+	unsigned long uninitialized_var(bt_addr);
+	void __user *bde_vaddr;
 	int ret;
-	long __user *bde_start, *bde_end;
-	struct vm_area_struct *prev, *next;
-	bool prev_shared = false, next_shared = false;
-
-	bde_start = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(start);
-	bde_end = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(end-1);
-
 	/*
-	 * Check whether bde_start and bde_end are shared with adjacent
-	 * VMAs.
-	 *
-	 * We already unliked the VMAs from the mm's rbtree so 'start'
+	 * We already unlinked the VMAs from the mm's rbtree so 'start'
 	 * is guaranteed to be in a hole. This gets us the first VMA
 	 * before the hole in to 'prev' and the next VMA after the hole
 	 * in to 'next'.
 	 */
 	next = find_vma_prev(mm, start, &prev);
-	if (prev && (mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(prev->vm_end-1))
-			== bde_start)
-		prev_shared = true;
-	if (next && (mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(next->vm_start))
-			== bde_end)
-		next_shared = true;
-
 	/*
-	 * This virtual address region being munmap()ed is only
-	 * covered by one bounds table.
-	 *
-	 * In this case, if this table is also shared with adjacent
-	 * VMAs, only part of the backing physical memory of the bounds
-	 * table need be freeed. Otherwise the whole bounds table need
-	 * be unmapped.
-	 */
-	if (bde_start == bde_end) {
-		return unmap_shared_bt(mm, bde_start, start, end,
-				prev_shared, next_shared);
+	 * Do not count other MPX bounds table VMAs as neighbors.
+	 * Although theoretically possible, we do not allow bounds
+	 * tables for bounds tables so our heads do not explode.
+	 * If we count them as neighbors here, we may end up with
+	 * lots of tables even though we have no actual table
+	 * entries in use.
+	 */
+	while (next && (next->vm_flags & VM_MPX))
+		next = next->vm_next;
+	while (prev && (prev->vm_flags & VM_MPX))
+		prev = prev->vm_prev;
+	/*
+	 * We know 'start' and 'end' lie within an area controlled
+	 * by a single bounds table.  See if there are any other
+	 * VMAs controlled by that bounds table.  If there are not
+	 * then we can "expand" the are we are unmapping to possibly
+	 * cover the entire table.
+	 */
+	next = find_vma_prev(mm, start, &prev);
+	if ((!prev || prev->vm_end <= bta_start_vaddr) &&
+	    (!next || next->vm_start >= bta_end_vaddr)) {
+		/*
+		 * No neighbor VMAs controlled by same bounds
+		 * table.  Try to unmap the whole thing
+		 */
+		start = bta_start_vaddr;
+		end = bta_end_vaddr;
 	}
 
+	bde_vaddr = mm->bd_addr + mpx_get_bd_entry_offset(mm, start);
+	ret = get_bt_addr(mm, bde_vaddr, &bt_addr);
 	/*
-	 * If more than one bounds tables are covered in this virtual
-	 * address region being munmap()ed, we need to separately check
-	 * whether bde_start and bde_end are shared with adjacent VMAs.
+	 * No bounds table there, so nothing to unmap.
 	 */
-	ret = unmap_shared_bt(mm, bde_start, start, end, prev_shared, false);
-	if (ret)
-		return ret;
-	ret = unmap_shared_bt(mm, bde_end, start, end, false, next_shared);
+	if (ret == -ENOENT) {
+		ret = 0;
+		return 0;
+	}
 	if (ret)
 		return ret;
-
-	return 0;
+	/*
+	 * We are unmapping an entire table.  Either because the
+	 * unmap that started this whole process was large enough
+	 * to cover an entire table, or that the unmap was small
+	 * but was the area covered by a bounds table.
+	 */
+	if ((start == bta_start_vaddr) &&
+	    (end == bta_end_vaddr))
+		return unmap_entire_bt(mm, bde_vaddr, bt_addr);
+	return zap_bt_entries_mapping(mm, bt_addr, start, end);
 }
 
 static int mpx_unmap_tables(struct mm_struct *mm,
 		unsigned long start, unsigned long end)
 {
-	int ret;
-	long __user *bd_entry, *bde_start, *bde_end;
-	unsigned long bt_addr;
-
-	/*
-	 * "Edge" bounds tables are those which are being used by the region
-	 * (start -> end), but that may be shared with adjacent areas.  If they
-	 * turn out to be completely unshared, they will be freed.  If they are
-	 * shared, we will free the backing store (like an MADV_DONTNEED) for
-	 * areas used by this region.
-	 */
-	ret = unmap_edge_bts(mm, start, end);
-	switch (ret) {
-		/* non-present tables are OK */
-		case 0:
-		case -ENOENT:
-			/* Success, or no tables to unmap */
-			break;
-		case -EINVAL:
-		case -EFAULT:
-		default:
-			return ret;
-	}
-
-	/*
-	 * Only unmap the bounds table that are
-	 *   1. fully covered
-	 *   2. not at the edges of the mapping, even if full aligned
-	 */
-	bde_start = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(start);
-	bde_end = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(end-1);
-	for (bd_entry = bde_start + 1; bd_entry < bde_end; bd_entry++) {
-		ret = get_bt_addr(mm, bd_entry, &bt_addr);
-		switch (ret) {
-			case 0:
-				break;
-			case -ENOENT:
-				/* No table here, try the next one */
-				continue;
-			case -EINVAL:
-			case -EFAULT:
-			default:
-				/*
-				 * Note: we are being strict here.
-				 * Any time we run in to an issue
-				 * unmapping tables, we stop and
-				 * SIGSEGV.
-				 */
-				return ret;
-		}
-
-		ret = unmap_single_bt(mm, bd_entry, bt_addr);
+	unsigned long one_unmap_start;
+	trace_mpx_unmap_search(start, end);
+
+	one_unmap_start = start;
+	while (one_unmap_start < end) {
+		int ret;
+		unsigned long next_unmap_start = ALIGN(one_unmap_start+1,
+						       bd_entry_virt_space(mm));
+		unsigned long one_unmap_end = end;
+		/*
+		 * if the end is beyond the current bounds table,
+		 * move it back so we only deal with a single one
+		 * at a time
+		 */
+		if (one_unmap_end > next_unmap_start)
+			one_unmap_end = next_unmap_start;
+		ret = try_unmap_single_bt(mm, one_unmap_start, one_unmap_end);
 		if (ret)
 			return ret;
-	}
 
+		one_unmap_start = next_unmap_start;
+	}
 	return 0;
 }
 
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 3250f2371aea..90b924acd982 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -117,7 +117,7 @@ static void flush_tlb_func(void *info)
 		} else {
 			unsigned long addr;
 			unsigned long nr_pages =
-				f->flush_end - f->flush_start / PAGE_SIZE;
+				(f->flush_end - f->flush_start) / PAGE_SIZE;
 			addr = f->flush_start;
 			while (addr < f->flush_end) {
 				__flush_tlb_single(addr);