Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

9 files changed, 132 insertions, 39 deletions

diff --git a/mm/bounce.c b/mm/bounce.c
index 06722c403058..bf0cf7c8387b 100644
--- a/mm/bounce.c
+++ b/mm/bounce.c
@@ -14,6 +14,7 @@
 #include <linux/hash.h>
 #include <linux/highmem.h>
 #include <linux/blktrace_api.h>
+#include <trace/block.h>
 #include <asm/tlbflush.h>
 
 #define POOL_SIZE	64
@@ -21,6 +22,8 @@
 
 static mempool_t *page_pool, *isa_page_pool;
 
+DEFINE_TRACE(block_bio_bounce);
+
 #ifdef CONFIG_HIGHMEM
 static __init int init_emergency_pool(void)
 {
@@ -222,7 +225,7 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
 	if (!bio)
 		return;
 
-	blk_add_trace_bio(q, *bio_orig, BLK_TA_BOUNCE);
+	trace_block_bio_bounce(q, *bio_orig);
 
 	/*
 	 * at least one page was bounced, fill in possible non-highmem
diff --git a/mm/memory.c b/mm/memory.c
index 164951c47305..f01b7eed6e16 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -669,6 +669,16 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	if (is_vm_hugetlb_page(vma))
 		return copy_hugetlb_page_range(dst_mm, src_mm, vma);
 
+	if (unlikely(is_pfn_mapping(vma))) {
+		/*
+		 * We do not free on error cases below as remove_vma
+		 * gets called on error from higher level routine
+		 */
+		ret = track_pfn_vma_copy(vma);
+		if (ret)
+			return ret;
+	}
+
 	/*
 	 * We need to invalidate the secondary MMU mappings only when
 	 * there could be a permission downgrade on the ptes of the
@@ -915,6 +925,9 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp,
 		if (vma->vm_flags & VM_ACCOUNT)
 			*nr_accounted += (end - start) >> PAGE_SHIFT;
 
+		if (unlikely(is_pfn_mapping(vma)))
+			untrack_pfn_vma(vma, 0, 0);
+
 		while (start != end) {
 			if (!tlb_start_valid) {
 				tlb_start = start;
@@ -1430,6 +1443,7 @@ out:
 int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn)
 {
+	int ret;
 	/*
 	 * Technically, architectures with pte_special can avoid all these
 	 * restrictions (same for remap_pfn_range).  However we would like
@@ -1444,7 +1458,15 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 
 	if (addr < vma->vm_start || addr >= vma->vm_end)
 		return -EFAULT;
-	return insert_pfn(vma, addr, pfn, vma->vm_page_prot);
+	if (track_pfn_vma_new(vma, vma->vm_page_prot, pfn, PAGE_SIZE))
+		return -EINVAL;
+
+	ret = insert_pfn(vma, addr, pfn, vma->vm_page_prot);
+
+	if (ret)
+		untrack_pfn_vma(vma, pfn, PAGE_SIZE);
+
+	return ret;
 }
 EXPORT_SYMBOL(vm_insert_pfn);
 
@@ -1575,14 +1597,17 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 	 * behaviour that some programs depend on. We mark the "original"
 	 * un-COW'ed pages by matching them up with "vma->vm_pgoff".
 	 */
-	if (is_cow_mapping(vma->vm_flags)) {
-		if (addr != vma->vm_start || end != vma->vm_end)
-			return -EINVAL;
+	if (addr == vma->vm_start && end == vma->vm_end)
 		vma->vm_pgoff = pfn;
-	}
+	else if (is_cow_mapping(vma->vm_flags))
+		return -EINVAL;
 
 	vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
 
+	err = track_pfn_vma_new(vma, prot, pfn, PAGE_ALIGN(size));
+	if (err)
+		return -EINVAL;
+
 	BUG_ON(addr >= end);
 	pfn -= addr >> PAGE_SHIFT;
 	pgd = pgd_offset(mm, addr);
@@ -1594,6 +1619,10 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 		if (err)
 			break;
 	} while (pgd++, addr = next, addr != end);
+
+	if (err)
+		untrack_pfn_vma(vma, pfn, PAGE_ALIGN(size));
+
 	return err;
 }
 EXPORT_SYMBOL(remap_pfn_range);
@@ -2865,9 +2894,9 @@ int in_gate_area_no_task(unsigned long addr)
 #endif	/* __HAVE_ARCH_GATE_AREA */
 
 #ifdef CONFIG_HAVE_IOREMAP_PROT
-static resource_size_t follow_phys(struct vm_area_struct *vma,
-			unsigned long address, unsigned int flags,
-			unsigned long *prot)
+int follow_phys(struct vm_area_struct *vma,
+		unsigned long address, unsigned int flags,
+		unsigned long *prot, resource_size_t *phys)
 {
 	pgd_t *pgd;
 	pud_t *pud;
@@ -2876,24 +2905,26 @@ static resource_size_t follow_phys(struct vm_area_struct *vma,
 	spinlock_t *ptl;
 	resource_size_t phys_addr = 0;
 	struct mm_struct *mm = vma->vm_mm;
+	int ret = -EINVAL;
 
-	VM_BUG_ON(!(vma->vm_flags & (VM_IO | VM_PFNMAP)));
+	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
+		goto out;
 
 	pgd = pgd_offset(mm, address);
 	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
-		goto no_page_table;
+		goto out;
 
 	pud = pud_offset(pgd, address);
 	if (pud_none(*pud) || unlikely(pud_bad(*pud)))
-		goto no_page_table;
+		goto out;
 
 	pmd = pmd_offset(pud, address);
 	if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
-		goto no_page_table;
+		goto out;
 
 	/* We cannot handle huge page PFN maps. Luckily they don't exist. */
 	if (pmd_huge(*pmd))
-		goto no_page_table;
+		goto out;
 
 	ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
 	if (!ptep)
@@ -2908,13 +2939,13 @@ static resource_size_t follow_phys(struct vm_area_struct *vma,
 	phys_addr <<= PAGE_SHIFT; /* Shift here to avoid overflow on PAE */
 
 	*prot = pgprot_val(pte_pgprot(pte));
+	*phys = phys_addr;
+	ret = 0;
 
 unlock:
 	pte_unmap_unlock(ptep, ptl);
 out:
-	return phys_addr;
-no_page_table:
-	return 0;
+	return ret;
 }
 
 int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
@@ -2925,12 +2956,7 @@ int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
 	void *maddr;
 	int offset = addr & (PAGE_SIZE-1);
 
-	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
-		return -EINVAL;
-
-	phys_addr = follow_phys(vma, addr, write, &prot);
-
-	if (!phys_addr)
+	if (follow_phys(vma, addr, write, &prot, &phys_addr))
 		return -EINVAL;
 
 	maddr = ioremap_prot(phys_addr, PAGE_SIZE, prot);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index e9493b1c1117..e412ffa8e52e 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1114,6 +1114,7 @@ asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode,
 		const unsigned long __user *old_nodes,
 		const unsigned long __user *new_nodes)
 {
+	const struct cred *cred = current_cred(), *tcred;
 	struct mm_struct *mm;
 	struct task_struct *task;
 	nodemask_t old;
@@ -1148,12 +1149,16 @@ asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode,
 	 * capabilities, superuser privileges or the same
 	 * userid as the target process.
 	 */
-	if ((current->euid != task->suid) && (current->euid != task->uid) &&
-	    (current->uid != task->suid) && (current->uid != task->uid) &&
+	rcu_read_lock();
+	tcred = __task_cred(task);
+	if (cred->euid != tcred->suid && cred->euid != tcred->uid &&
+	    cred->uid  != tcred->suid && cred->uid  != tcred->uid &&
 	    !capable(CAP_SYS_NICE)) {
+		rcu_read_unlock();
 		err = -EPERM;
 		goto out;
 	}
+	rcu_read_unlock();
 
 	task_nodes = cpuset_mems_allowed(task);
 	/* Is the user allowed to access the target nodes? */
diff --git a/mm/migrate.c b/mm/migrate.c
index d8f07667fc80..21631ab8c08b 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -998,7 +998,7 @@ static void do_pages_stat_array(struct mm_struct *mm, unsigned long nr_pages,
 		unsigned long addr = (unsigned long)(*pages);
 		struct vm_area_struct *vma;
 		struct page *page;
-		int err;
+		int err = -EFAULT;
 
 		vma = find_vma(mm, addr);
 		if (!vma)
@@ -1075,6 +1075,7 @@ asmlinkage long sys_move_pages(pid_t pid, unsigned long nr_pages,
 			const int __user *nodes,
 			int __user *status, int flags)
 {
+	const struct cred *cred = current_cred(), *tcred;
 	struct task_struct *task;
 	struct mm_struct *mm;
 	int err;
@@ -1105,12 +1106,16 @@ asmlinkage long sys_move_pages(pid_t pid, unsigned long nr_pages,
 	 * capabilities, superuser privileges or the same
 	 * userid as the target process.
 	 */
-	if ((current->euid != task->suid) && (current->euid != task->uid) &&
-	    (current->uid != task->suid) && (current->uid != task->uid) &&
+	rcu_read_lock();
+	tcred = __task_cred(task);
+	if (cred->euid != tcred->suid && cred->euid != tcred->uid &&
+	    cred->uid  != tcred->suid && cred->uid  != tcred->uid &&
 	    !capable(CAP_SYS_NICE)) {
+		rcu_read_unlock();
 		err = -EPERM;
 		goto out;
 	}
+	rcu_read_unlock();
 
  	err = security_task_movememory(task);
  	if (err)
diff --git a/mm/mlock.c b/mm/mlock.c
index 1ada366570cb..3035a56e7616 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -667,3 +667,48 @@ void user_shm_unlock(size_t size, struct user_struct *user)
 	spin_unlock(&shmlock_user_lock);
 	free_uid(user);
 }
+
+void *alloc_locked_buffer(size_t size)
+{
+	unsigned long rlim, vm, pgsz;
+	void *buffer = NULL;
+
+	pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT;
+
+	down_write(&current->mm->mmap_sem);
+
+	rlim = current->signal->rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT;
+	vm   = current->mm->total_vm + pgsz;
+	if (rlim < vm)
+		goto out;
+
+	rlim = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT;
+	vm   = current->mm->locked_vm + pgsz;
+	if (rlim < vm)
+		goto out;
+
+	buffer = kzalloc(size, GFP_KERNEL);
+	if (!buffer)
+		goto out;
+
+	current->mm->total_vm  += pgsz;
+	current->mm->locked_vm += pgsz;
+
+ out:
+	up_write(&current->mm->mmap_sem);
+	return buffer;
+}
+
+void free_locked_buffer(void *buffer, size_t size)
+{
+	unsigned long pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT;
+
+	down_write(&current->mm->mmap_sem);
+
+	current->mm->total_vm  -= pgsz;
+	current->mm->locked_vm -= pgsz;
+
+	up_write(&current->mm->mmap_sem);
+
+	kfree(buffer);
+}
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index a0a01902f551..558f9afe6e4e 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -128,8 +128,8 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
 	 * Superuser processes are usually more important, so we make it
 	 * less likely that we kill those.
 	 */
-	if (has_capability(p, CAP_SYS_ADMIN) ||
-	    has_capability(p, CAP_SYS_RESOURCE))
+	if (has_capability_noaudit(p, CAP_SYS_ADMIN) ||
+	    has_capability_noaudit(p, CAP_SYS_RESOURCE))
 		points /= 4;
 
 	/*
@@ -138,7 +138,7 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
 	 * tend to only have this flag set on applications they think
 	 * of as important.
 	 */
-	if (has_capability(p, CAP_SYS_RAWIO))
+	if (has_capability_noaudit(p, CAP_SYS_RAWIO))
 		points /= 4;
 
 	/*
@@ -299,9 +299,9 @@ static void dump_tasks(const struct mem_cgroup *mem)
 
 		task_lock(p);
 		printk(KERN_INFO "[%5d] %5d %5d %8lu %8lu %3d     %3d %s\n",
-		       p->pid, p->uid, p->tgid, p->mm->total_vm,
-		       get_mm_rss(p->mm), (int)task_cpu(p), p->oomkilladj,
-		       p->comm);
+		       p->pid, __task_cred(p)->uid, p->tgid,
+		       p->mm->total_vm, get_mm_rss(p->mm), (int)task_cpu(p),
+		       p->oomkilladj, p->comm);
 		task_unlock(p);
 	} while_each_thread(g, p);
 }
diff --git a/mm/shmem.c b/mm/shmem.c
index 0ed075215e5f..f1b0d4871f3a 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1513,8 +1513,8 @@ shmem_get_inode(struct super_block *sb, int mode, dev_t dev)
 	inode = new_inode(sb);
 	if (inode) {
 		inode->i_mode = mode;
-		inode->i_uid = current->fsuid;
-		inode->i_gid = current->fsgid;
+		inode->i_uid = current_fsuid();
+		inode->i_gid = current_fsgid();
 		inode->i_blocks = 0;
 		inode->i_mapping->backing_dev_info = &shmem_backing_dev_info;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
@@ -2278,8 +2278,8 @@ static int shmem_fill_super(struct super_block *sb,
 	sbinfo->max_blocks = 0;
 	sbinfo->max_inodes = 0;
 	sbinfo->mode = S_IRWXUGO | S_ISVTX;
-	sbinfo->uid = current->fsuid;
-	sbinfo->gid = current->fsgid;
+	sbinfo->uid = current_fsuid();
+	sbinfo->gid = current_fsgid();
 	sbinfo->mpol = NULL;
 	sb->s_fs_info = sbinfo;
 
diff --git a/mm/slob.c b/mm/slob.c
index cb675d126791..bf7e8fc3aed8 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -535,7 +535,7 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size,
 	struct kmem_cache *c;
 
 	c = slob_alloc(sizeof(struct kmem_cache),
-		flags, ARCH_KMALLOC_MINALIGN, -1);
+		GFP_KERNEL, ARCH_KMALLOC_MINALIGN, -1);
 
 	if (c) {
 		c->name = name;
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 90cb67a5417c..54a9f87e5162 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1462,6 +1462,15 @@ static int __init procswaps_init(void)
 __initcall(procswaps_init);
 #endif /* CONFIG_PROC_FS */
 
+#ifdef MAX_SWAPFILES_CHECK
+static int __init max_swapfiles_check(void)
+{
+	MAX_SWAPFILES_CHECK();
+	return 0;
+}
+late_initcall(max_swapfiles_check);
+#endif
+
 /*
  * Written 01/25/92 by Simmule Turner, heavily changed by Linus.
  *