Merge branch 'akpm' (patches from Andrew)

Merge even more updates from Andrew Morton:

 - a kernel-wide sweep of show_stack()

 - pagetable cleanups

 - abstract out accesses to mmap_sem - prep for mmap_sem scalability work

 - hch's user acess work

Subsystems affected by this patch series: debug, mm/pagemap, mm/maccess,
mm/documentation.

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (93 commits)
  include/linux/cache.h: expand documentation over __read_mostly
  maccess: return -ERANGE when probe_kernel_read() fails
  x86: use non-set_fs based maccess routines
  maccess: allow architectures to provide kernel probing directly
  maccess: move user access routines together
  maccess: always use strict semantics for probe_kernel_read
  maccess: remove strncpy_from_unsafe
  tracing/kprobes: handle mixed kernel/userspace probes better
  bpf: rework the compat kernel probe handling
  bpf:bpf_seq_printf(): handle potentially unsafe format string better
  bpf: handle the compat string in bpf_trace_copy_string better
  bpf: factor out a bpf_trace_copy_string helper
  maccess: unify the probe kernel arch hooks
  maccess: remove probe_read_common and probe_write_common
  maccess: rename strnlen_unsafe_user to strnlen_user_nofault
  maccess: rename strncpy_from_unsafe_strict to strncpy_from_kernel_nofault
  maccess: rename strncpy_from_unsafe_user to strncpy_from_user_nofault
  maccess: update the top of file comment
  maccess: clarify kerneldoc comments
  maccess: remove duplicate kerneldoc comments
  ...

1 files changed, 30 insertions, 31 deletions

diff --git a/mm/memory.c b/mm/memory.c
index d97e8848892d..dc7f3543b1fd 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -80,7 +80,6 @@
 #include <linux/uaccess.h>
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
-#include <asm/pgtable.h>
 
 #include "internal.h"
 
@@ -1186,7 +1185,7 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
 		 * Here there can be other concurrent MADV_DONTNEED or
 		 * trans huge page faults running, and if the pmd is
 		 * none or trans huge it can change under us. This is
-		 * because MADV_DONTNEED holds the mmap_sem in read
+		 * because MADV_DONTNEED holds the mmap_lock in read
 		 * mode.
 		 */
 		if (pmd_none_or_trans_huge_or_clear_bad(pmd))
@@ -1212,7 +1211,7 @@ static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
 		next = pud_addr_end(addr, end);
 		if (pud_trans_huge(*pud) || pud_devmap(*pud)) {
 			if (next - addr != HPAGE_PUD_SIZE) {
-				VM_BUG_ON_VMA(!rwsem_is_locked(&tlb->mm->mmap_sem), vma);
+				mmap_assert_locked(tlb->mm);
 				split_huge_pud(vma, pud, addr);
 			} else if (zap_huge_pud(tlb, vma, pud, addr))
 				goto next;
@@ -1593,7 +1592,7 @@ int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr,
 	if (addr < vma->vm_start || end_addr >= vma->vm_end)
 		return -EFAULT;
 	if (!(vma->vm_flags & VM_MIXEDMAP)) {
-		BUG_ON(down_read_trylock(&vma->vm_mm->mmap_sem));
+		BUG_ON(mmap_read_trylock(vma->vm_mm));
 		BUG_ON(vma->vm_flags & VM_PFNMAP);
 		vma->vm_flags |= VM_MIXEDMAP;
 	}
@@ -1637,7 +1636,7 @@ EXPORT_SYMBOL(vm_insert_pages);
  * The page does not need to be reserved.
  *
  * Usually this function is called from f_op->mmap() handler
- * under mm->mmap_sem write-lock, so it can change vma->vm_flags.
+ * under mm->mmap_lock write-lock, so it can change vma->vm_flags.
  * Caller must set VM_MIXEDMAP on vma if it wants to call this
  * function from other places, for example from page-fault handler.
  *
@@ -1651,7 +1650,7 @@ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
 	if (!page_count(page))
 		return -EINVAL;
 	if (!(vma->vm_flags & VM_MIXEDMAP)) {
-		BUG_ON(down_read_trylock(&vma->vm_mm->mmap_sem));
+		BUG_ON(mmap_read_trylock(vma->vm_mm));
 		BUG_ON(vma->vm_flags & VM_PFNMAP);
 		vma->vm_flags |= VM_MIXEDMAP;
 	}
@@ -2574,7 +2573,7 @@ static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf)
 	 * mapping may be NULL here because some device drivers do not
 	 * set page.mapping but still dirty their pages
 	 *
-	 * Drop the mmap_sem before waiting on IO, if we can. The file
+	 * Drop the mmap_lock before waiting on IO, if we can. The file
 	 * is pinning the mapping, as per above.
 	 */
 	if ((dirtied || page_mkwrite) && mapping) {
@@ -2624,7 +2623,7 @@ static inline void wp_page_reuse(struct vm_fault *vmf)
 /*
  * Handle the case of a page which we actually need to copy to a new page.
  *
- * Called with mmap_sem locked and the old page referenced, but
+ * Called with mmap_lock locked and the old page referenced, but
  * without the ptl held.
  *
  * High level logic flow:
@@ -2888,9 +2887,9 @@ static vm_fault_t wp_page_shared(struct vm_fault *vmf)
  * change only once the write actually happens. This avoids a few races,
  * and potentially makes it more efficient.
  *
- * We enter with non-exclusive mmap_sem (to exclude vma changes,
+ * We enter with non-exclusive mmap_lock (to exclude vma changes,
  * but allow concurrent faults), with pte both mapped and locked.
- * We return with mmap_sem still held, but pte unmapped and unlocked.
+ * We return with mmap_lock still held, but pte unmapped and unlocked.
  */
 static vm_fault_t do_wp_page(struct vm_fault *vmf)
 	__releases(vmf->ptl)
@@ -3079,11 +3078,11 @@ void unmap_mapping_range(struct address_space *mapping,
 EXPORT_SYMBOL(unmap_mapping_range);
 
 /*
- * We enter with non-exclusive mmap_sem (to exclude vma changes,
+ * We enter with non-exclusive mmap_lock (to exclude vma changes,
  * but allow concurrent faults), and pte mapped but not yet locked.
  * We return with pte unmapped and unlocked.
  *
- * We return with the mmap_sem locked or unlocked in the same cases
+ * We return with the mmap_lock locked or unlocked in the same cases
  * as does filemap_fault().
  */
 vm_fault_t do_swap_page(struct vm_fault *vmf)
@@ -3304,9 +3303,9 @@ out_release:
 }
 
 /*
- * We enter with non-exclusive mmap_sem (to exclude vma changes,
+ * We enter with non-exclusive mmap_lock (to exclude vma changes,
  * but allow concurrent faults), and pte mapped but not yet locked.
- * We return with mmap_sem still held, but pte unmapped and unlocked.
+ * We return with mmap_lock still held, but pte unmapped and unlocked.
  */
 static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 {
@@ -3324,10 +3323,10 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 	 * pte_offset_map() on pmds where a huge pmd might be created
 	 * from a different thread.
 	 *
-	 * pte_alloc_map() is safe to use under down_write(mmap_sem) or when
+	 * pte_alloc_map() is safe to use under mmap_write_lock(mm) or when
 	 * parallel threads are excluded by other means.
 	 *
-	 * Here we only have down_read(mmap_sem).
+	 * Here we only have mmap_read_lock(mm).
 	 */
 	if (pte_alloc(vma->vm_mm, vmf->pmd))
 		return VM_FAULT_OOM;
@@ -3420,7 +3419,7 @@ oom:
 }
 
 /*
- * The mmap_sem must have been held on entry, and may have been
+ * The mmap_lock must have been held on entry, and may have been
  * released depending on flags and vma->vm_ops->fault() return value.
  * See filemap_fault() and __lock_page_retry().
  */
@@ -3929,11 +3928,11 @@ static vm_fault_t do_shared_fault(struct vm_fault *vmf)
 }
 
 /*
- * We enter with non-exclusive mmap_sem (to exclude vma changes,
+ * We enter with non-exclusive mmap_lock (to exclude vma changes,
  * but allow concurrent faults).
- * The mmap_sem may have been released depending on flags and our
+ * The mmap_lock may have been released depending on flags and our
  * return value.  See filemap_fault() and __lock_page_or_retry().
- * If mmap_sem is released, vma may become invalid (for example
+ * If mmap_lock is released, vma may become invalid (for example
  * by other thread calling munmap()).
  */
 static vm_fault_t do_fault(struct vm_fault *vmf)
@@ -4162,10 +4161,10 @@ static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud)
  * with external mmu caches can use to update those (ie the Sparc or
  * PowerPC hashed page tables that act as extended TLBs).
  *
- * We enter with non-exclusive mmap_sem (to exclude vma changes, but allow
+ * We enter with non-exclusive mmap_lock (to exclude vma changes, but allow
  * concurrent faults).
  *
- * The mmap_sem may have been released depending on flags and our return value.
+ * The mmap_lock may have been released depending on flags and our return value.
  * See filemap_fault() and __lock_page_or_retry().
  */
 static vm_fault_t handle_pte_fault(struct vm_fault *vmf)
@@ -4187,7 +4186,7 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf)
 		/*
 		 * A regular pmd is established and it can't morph into a huge
 		 * pmd from under us anymore at this point because we hold the
-		 * mmap_sem read mode and khugepaged takes it in write mode.
+		 * mmap_lock read mode and khugepaged takes it in write mode.
 		 * So now it's safe to run pte_offset_map().
 		 */
 		vmf->pte = pte_offset_map(vmf->pmd, vmf->address);
@@ -4255,7 +4254,7 @@ unlock:
 /*
  * By the time we get here, we already hold the mm semaphore
  *
- * The mmap_sem may have been released depending on flags and our
+ * The mmap_lock may have been released depending on flags and our
  * return value.  See filemap_fault() and __lock_page_or_retry().
  */
 static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
@@ -4350,7 +4349,7 @@ retry_pud:
 /*
  * By the time we get here, we already hold the mm semaphore
  *
- * The mmap_sem may have been released depending on flags and our
+ * The mmap_lock may have been released depending on flags and our
  * return value.  See filemap_fault() and __lock_page_or_retry().
  */
 vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
@@ -4659,7 +4658,7 @@ int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
 	void *old_buf = buf;
 	int write = gup_flags & FOLL_WRITE;
 
-	if (down_read_killable(&mm->mmap_sem))
+	if (mmap_read_lock_killable(mm))
 		return 0;
 
 	/* ignore errors, just check how much was successfully transferred */
@@ -4710,7 +4709,7 @@ int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
 		buf += bytes;
 		addr += bytes;
 	}
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 
 	return buf - old_buf;
 }
@@ -4767,7 +4766,7 @@ void print_vma_addr(char *prefix, unsigned long ip)
 	/*
 	 * we might be running from an atomic context so we cannot sleep
 	 */
-	if (!down_read_trylock(&mm->mmap_sem))
+	if (!mmap_read_trylock(mm))
 		return;
 
 	vma = find_vma(mm, ip);
@@ -4786,7 +4785,7 @@ void print_vma_addr(char *prefix, unsigned long ip)
 			free_page((unsigned long)buf);
 		}
 	}
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 }
 
 #if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP)
@@ -4794,7 +4793,7 @@ void __might_fault(const char *file, int line)
 {
 	/*
 	 * Some code (nfs/sunrpc) uses socket ops on kernel memory while
-	 * holding the mmap_sem, this is safe because kernel memory doesn't
+	 * holding the mmap_lock, this is safe because kernel memory doesn't
 	 * get paged out, therefore we'll never actually fault, and the
 	 * below annotations will generate false positives.
 	 */
@@ -4805,7 +4804,7 @@ void __might_fault(const char *file, int line)
 	__might_sleep(file, line, 0);
 #if defined(CONFIG_DEBUG_ATOMIC_SLEEP)
 	if (current->mm)
-		might_lock_read(&current->mm->mmap_sem);
+		might_lock_read(&current->mm->mmap_lock);
 #endif
 }
 EXPORT_SYMBOL(__might_fault);