Merge branch 'master' into gfs2

21 files changed, 1014 insertions, 510 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 8f5b45615f7..5d88489ef2d 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -115,12 +115,17 @@ config SPARSEMEM_EXTREME
 # eventually, we can have this option just 'select SPARSEMEM'
 config MEMORY_HOTPLUG
 	bool "Allow for memory hot-add"
-	depends on SPARSEMEM && HOTPLUG && !SOFTWARE_SUSPEND && ARCH_ENABLE_MEMORY_HOTPLUG
+	depends on SPARSEMEM || X86_64_ACPI_NUMA
+	depends on HOTPLUG && !SOFTWARE_SUSPEND && ARCH_ENABLE_MEMORY_HOTPLUG
 	depends on (IA64 || X86 || PPC64)
 
 comment "Memory hotplug is currently incompatible with Software Suspend"
 	depends on SPARSEMEM && HOTPLUG && SOFTWARE_SUSPEND
 
+config MEMORY_HOTPLUG_SPARSE
+	def_bool y
+	depends on SPARSEMEM && MEMORY_HOTPLUG
+
 # Heavily threaded applications may benefit from splitting the mm-wide
 # page_table_lock, so that faults on different parts of the user address
 # space can be handled with less contention: split it at this NR_CPUS.
diff --git a/mm/Makefile b/mm/Makefile
index 60c56c0b5e1..12b3a4eee88 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -12,11 +12,15 @@ obj-y			:= bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \
 			   readahead.o swap.o truncate.o vmscan.o \
 			   prio_tree.o util.o mmzone.o vmstat.o $(mmu-y)
 
+ifeq ($(CONFIG_MMU)$(CONFIG_BLOCK),yy)
+obj-y			+= bounce.o
+endif
 obj-$(CONFIG_SWAP)	+= page_io.o swap_state.o swapfile.o thrash.o
 obj-$(CONFIG_HUGETLBFS)	+= hugetlb.o
 obj-$(CONFIG_NUMA) 	+= mempolicy.o
 obj-$(CONFIG_SPARSEMEM)	+= sparse.o
 obj-$(CONFIG_SHMEM) += shmem.o
+obj-$(CONFIG_TMPFS_POSIX_ACL) += shmem_acl.o
 obj-$(CONFIG_TINY_SHMEM) += tiny-shmem.o
 obj-$(CONFIG_SLOB) += slob.o
 obj-$(CONFIG_SLAB) += slab.o
diff --git a/mm/bounce.c b/mm/bounce.c
new file mode 100644
index 00000000000..e4b62d2a402
--- /dev/null
+++ b/mm/bounce.c
@@ -0,0 +1,302 @@
+/* bounce buffer handling for block devices
+ *
+ * - Split from highmem.c
+ */
+
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/swap.h>
+#include <linux/bio.h>
+#include <linux/pagemap.h>
+#include <linux/mempool.h>
+#include <linux/blkdev.h>
+#include <linux/init.h>
+#include <linux/hash.h>
+#include <linux/highmem.h>
+#include <linux/blktrace_api.h>
+#include <asm/tlbflush.h>
+
+#define POOL_SIZE	64
+#define ISA_POOL_SIZE	16
+
+static mempool_t *page_pool, *isa_page_pool;
+
+#ifdef CONFIG_HIGHMEM
+static __init int init_emergency_pool(void)
+{
+	struct sysinfo i;
+	si_meminfo(&i);
+	si_swapinfo(&i);
+
+	if (!i.totalhigh)
+		return 0;
+
+	page_pool = mempool_create_page_pool(POOL_SIZE, 0);
+	BUG_ON(!page_pool);
+	printk("highmem bounce pool size: %d pages\n", POOL_SIZE);
+
+	return 0;
+}
+
+__initcall(init_emergency_pool);
+
+/*
+ * highmem version, map in to vec
+ */
+static void bounce_copy_vec(struct bio_vec *to, unsigned char *vfrom)
+{
+	unsigned long flags;
+	unsigned char *vto;
+
+	local_irq_save(flags);
+	vto = kmap_atomic(to->bv_page, KM_BOUNCE_READ);
+	memcpy(vto + to->bv_offset, vfrom, to->bv_len);
+	kunmap_atomic(vto, KM_BOUNCE_READ);
+	local_irq_restore(flags);
+}
+
+#else /* CONFIG_HIGHMEM */
+
+#define bounce_copy_vec(to, vfrom)	\
+	memcpy(page_address((to)->bv_page) + (to)->bv_offset, vfrom, (to)->bv_len)
+
+#endif /* CONFIG_HIGHMEM */
+
+/*
+ * allocate pages in the DMA region for the ISA pool
+ */
+static void *mempool_alloc_pages_isa(gfp_t gfp_mask, void *data)
+{
+	return mempool_alloc_pages(gfp_mask | GFP_DMA, data);
+}
+
+/*
+ * gets called "every" time someone init's a queue with BLK_BOUNCE_ISA
+ * as the max address, so check if the pool has already been created.
+ */
+int init_emergency_isa_pool(void)
+{
+	if (isa_page_pool)
+		return 0;
+
+	isa_page_pool = mempool_create(ISA_POOL_SIZE, mempool_alloc_pages_isa,
+				       mempool_free_pages, (void *) 0);
+	BUG_ON(!isa_page_pool);
+
+	printk("isa bounce pool size: %d pages\n", ISA_POOL_SIZE);
+	return 0;
+}
+
+/*
+ * Simple bounce buffer support for highmem pages. Depending on the
+ * queue gfp mask set, *to may or may not be a highmem page. kmap it
+ * always, it will do the Right Thing
+ */
+static void copy_to_high_bio_irq(struct bio *to, struct bio *from)
+{
+	unsigned char *vfrom;
+	struct bio_vec *tovec, *fromvec;
+	int i;
+
+	__bio_for_each_segment(tovec, to, i, 0) {
+		fromvec = from->bi_io_vec + i;
+
+		/*
+		 * not bounced
+		 */
+		if (tovec->bv_page == fromvec->bv_page)
+			continue;
+
+		/*
+		 * fromvec->bv_offset and fromvec->bv_len might have been
+		 * modified by the block layer, so use the original copy,
+		 * bounce_copy_vec already uses tovec->bv_len
+		 */
+		vfrom = page_address(fromvec->bv_page) + tovec->bv_offset;
+
+		flush_dcache_page(tovec->bv_page);
+		bounce_copy_vec(tovec, vfrom);
+	}
+}
+
+static void bounce_end_io(struct bio *bio, mempool_t *pool, int err)
+{
+	struct bio *bio_orig = bio->bi_private;
+	struct bio_vec *bvec, *org_vec;
+	int i;
+
+	if (test_bit(BIO_EOPNOTSUPP, &bio->bi_flags))
+		set_bit(BIO_EOPNOTSUPP, &bio_orig->bi_flags);
+
+	/*
+	 * free up bounce indirect pages used
+	 */
+	__bio_for_each_segment(bvec, bio, i, 0) {
+		org_vec = bio_orig->bi_io_vec + i;
+		if (bvec->bv_page == org_vec->bv_page)
+			continue;
+
+		dec_zone_page_state(bvec->bv_page, NR_BOUNCE);
+		mempool_free(bvec->bv_page, pool);
+	}
+
+	bio_endio(bio_orig, bio_orig->bi_size, err);
+	bio_put(bio);
+}
+
+static int bounce_end_io_write(struct bio *bio, unsigned int bytes_done, int err)
+{
+	if (bio->bi_size)
+		return 1;
+
+	bounce_end_io(bio, page_pool, err);
+	return 0;
+}
+
+static int bounce_end_io_write_isa(struct bio *bio, unsigned int bytes_done, int err)
+{
+	if (bio->bi_size)
+		return 1;
+
+	bounce_end_io(bio, isa_page_pool, err);
+	return 0;
+}
+
+static void __bounce_end_io_read(struct bio *bio, mempool_t *pool, int err)
+{
+	struct bio *bio_orig = bio->bi_private;
+
+	if (test_bit(BIO_UPTODATE, &bio->bi_flags))
+		copy_to_high_bio_irq(bio_orig, bio);
+
+	bounce_end_io(bio, pool, err);
+}
+
+static int bounce_end_io_read(struct bio *bio, unsigned int bytes_done, int err)
+{
+	if (bio->bi_size)
+		return 1;
+
+	__bounce_end_io_read(bio, page_pool, err);
+	return 0;
+}
+
+static int bounce_end_io_read_isa(struct bio *bio, unsigned int bytes_done, int err)
+{
+	if (bio->bi_size)
+		return 1;
+
+	__bounce_end_io_read(bio, isa_page_pool, err);
+	return 0;
+}
+
+static void __blk_queue_bounce(request_queue_t *q, struct bio **bio_orig,
+			       mempool_t *pool)
+{
+	struct page *page;
+	struct bio *bio = NULL;
+	int i, rw = bio_data_dir(*bio_orig);
+	struct bio_vec *to, *from;
+
+	bio_for_each_segment(from, *bio_orig, i) {
+		page = from->bv_page;
+
+		/*
+		 * is destination page below bounce pfn?
+		 */
+		if (page_to_pfn(page) < q->bounce_pfn)
+			continue;
+
+		/*
+		 * irk, bounce it
+		 */
+		if (!bio)
+			bio = bio_alloc(GFP_NOIO, (*bio_orig)->bi_vcnt);
+
+		to = bio->bi_io_vec + i;
+
+		to->bv_page = mempool_alloc(pool, q->bounce_gfp);
+		to->bv_len = from->bv_len;
+		to->bv_offset = from->bv_offset;
+		inc_zone_page_state(to->bv_page, NR_BOUNCE);
+
+		if (rw == WRITE) {
+			char *vto, *vfrom;
+
+			flush_dcache_page(from->bv_page);
+			vto = page_address(to->bv_page) + to->bv_offset;
+			vfrom = kmap(from->bv_page) + from->bv_offset;
+			memcpy(vto, vfrom, to->bv_len);
+			kunmap(from->bv_page);
+		}
+	}
+
+	/*
+	 * no pages bounced
+	 */
+	if (!bio)
+		return;
+
+	/*
+	 * at least one page was bounced, fill in possible non-highmem
+	 * pages
+	 */
+	__bio_for_each_segment(from, *bio_orig, i, 0) {
+		to = bio_iovec_idx(bio, i);
+		if (!to->bv_page) {
+			to->bv_page = from->bv_page;
+			to->bv_len = from->bv_len;
+			to->bv_offset = from->bv_offset;
+		}
+	}
+
+	bio->bi_bdev = (*bio_orig)->bi_bdev;
+	bio->bi_flags |= (1 << BIO_BOUNCED);
+	bio->bi_sector = (*bio_orig)->bi_sector;
+	bio->bi_rw = (*bio_orig)->bi_rw;
+
+	bio->bi_vcnt = (*bio_orig)->bi_vcnt;
+	bio->bi_idx = (*bio_orig)->bi_idx;
+	bio->bi_size = (*bio_orig)->bi_size;
+
+	if (pool == page_pool) {
+		bio->bi_end_io = bounce_end_io_write;
+		if (rw == READ)
+			bio->bi_end_io = bounce_end_io_read;
+	} else {
+		bio->bi_end_io = bounce_end_io_write_isa;
+		if (rw == READ)
+			bio->bi_end_io = bounce_end_io_read_isa;
+	}
+
+	bio->bi_private = *bio_orig;
+	*bio_orig = bio;
+}
+
+void blk_queue_bounce(request_queue_t *q, struct bio **bio_orig)
+{
+	mempool_t *pool;
+
+	/*
+	 * for non-isa bounce case, just check if the bounce pfn is equal
+	 * to or bigger than the highest pfn in the system -- in that case,
+	 * don't waste time iterating over bio segments
+	 */
+	if (!(q->bounce_gfp & GFP_DMA)) {
+		if (q->bounce_pfn >= blk_max_pfn)
+			return;
+		pool = page_pool;
+	} else {
+		BUG_ON(!isa_page_pool);
+		pool = isa_page_pool;
+	}
+
+	blk_add_trace_bio(q, *bio_orig, BLK_TA_BOUNCE);
+
+	/*
+	 * slow path
+	 */
+	__blk_queue_bounce(q, bio_orig, pool);
+}
+
+EXPORT_SYMBOL(blk_queue_bounce);
diff --git a/mm/filemap.c b/mm/filemap.c
index 87d4a398cd1..fef7d879ddf 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1149,13 +1149,14 @@ success:
  * that can use the page cache directly.
  */
 ssize_t
-__generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
-		unsigned long nr_segs, loff_t *ppos)
+generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
+		unsigned long nr_segs, loff_t pos)
 {
 	struct file *filp = iocb->ki_filp;
 	ssize_t retval;
 	unsigned long seg;
 	size_t count;
+	loff_t *ppos = &iocb->ki_pos;
 
 	count = 0;
 	for (seg = 0; seg < nr_segs; seg++) {
@@ -1179,7 +1180,7 @@ __generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 
 	/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
 	if (filp->f_flags & O_DIRECT) {
-		loff_t pos = *ppos, size;
+		loff_t size;
 		struct address_space *mapping;
 		struct inode *inode;
 
@@ -1225,33 +1226,8 @@ __generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 out:
 	return retval;
 }
-EXPORT_SYMBOL(__generic_file_aio_read);
-
-ssize_t
-generic_file_aio_read(struct kiocb *iocb, char __user *buf, size_t count, loff_t pos)
-{
-	struct iovec local_iov = { .iov_base = buf, .iov_len = count };
-
-	BUG_ON(iocb->ki_pos != pos);
-	return __generic_file_aio_read(iocb, &local_iov, 1, &iocb->ki_pos);
-}
 EXPORT_SYMBOL(generic_file_aio_read);
 
-ssize_t
-generic_file_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos)
-{
-	struct iovec local_iov = { .iov_base = buf, .iov_len = count };
-	struct kiocb kiocb;
-	ssize_t ret;
-
-	init_sync_kiocb(&kiocb, filp);
-	ret = __generic_file_aio_read(&kiocb, &local_iov, 1, ppos);
-	if (-EIOCBQUEUED == ret)
-		ret = wait_on_sync_kiocb(&kiocb);
-	return ret;
-}
-EXPORT_SYMBOL(generic_file_read);
-
 int file_send_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size)
 {
 	ssize_t written;
@@ -1473,7 +1449,7 @@ outside_data_content:
 	 * accessible..
 	 */
 	if (area->vm_mm == current->mm)
-		return NULL;
+		return NOPAGE_SIGBUS;
 	/* Fall through to the non-read-ahead case */
 no_cached_page:
 	/*
@@ -1498,7 +1474,7 @@ no_cached_page:
 	 */
 	if (error == -ENOMEM)
 		return NOPAGE_OOM;
-	return NULL;
+	return NOPAGE_SIGBUS;
 
 page_not_uptodate:
 	if (!did_readaround) {
@@ -1567,7 +1543,7 @@ page_not_uptodate:
 	 */
 	shrink_readahead_size_eio(file, ra);
 	page_cache_release(page);
-	return NULL;
+	return NOPAGE_SIGBUS;
 }
 EXPORT_SYMBOL(filemap_nopage);
 
@@ -2022,6 +1998,7 @@ inline int generic_write_checks(struct file *file, loff_t *pos, size_t *count, i
 		if (unlikely(*pos + *count > inode->i_sb->s_maxbytes))
 			*count = inode->i_sb->s_maxbytes - *pos;
 	} else {
+#ifdef CONFIG_BLOCK
 		loff_t isize;
 		if (bdev_read_only(I_BDEV(inode)))
 			return -EPERM;
@@ -2033,6 +2010,9 @@ inline int generic_write_checks(struct file *file, loff_t *pos, size_t *count, i
 
 		if (*pos + *count > isize)
 			*count = isize - *pos;
+#else
+		return -EPERM;
+#endif
 	}
 	return 0;
 }
@@ -2313,22 +2293,22 @@ out:
 	current->backing_dev_info = NULL;
 	return written ? written : err;
 }
-EXPORT_SYMBOL(generic_file_aio_write_nolock);
 
-ssize_t
-generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
-				unsigned long nr_segs, loff_t *ppos)
+ssize_t generic_file_aio_write_nolock(struct kiocb *iocb,
+		const struct iovec *iov, unsigned long nr_segs, loff_t pos)
 {
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
 	struct inode *inode = mapping->host;
 	ssize_t ret;
-	loff_t pos = *ppos;
 
-	ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs, ppos);
+	BUG_ON(iocb->ki_pos != pos);
+
+	ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs,
+			&iocb->ki_pos);
 
 	if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
-		int err;
+		ssize_t err;
 
 		err = sync_page_range_nolock(inode, mapping, pos, ret);
 		if (err < 0)
@@ -2336,51 +2316,21 @@ generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
 	}
 	return ret;
 }
+EXPORT_SYMBOL(generic_file_aio_write_nolock);
 
-static ssize_t
-__generic_file_write_nolock(struct file *file, const struct iovec *iov,
-				unsigned long nr_segs, loff_t *ppos)
-{
-	struct kiocb kiocb;
-	ssize_t ret;
-
-	init_sync_kiocb(&kiocb, file);
-	ret = __generic_file_aio_write_nolock(&kiocb, iov, nr_segs, ppos);
-	if (ret == -EIOCBQUEUED)
-		ret = wait_on_sync_kiocb(&kiocb);
-	return ret;
-}
-
-ssize_t
-generic_file_write_nolock(struct file *file, const struct iovec *iov,
-				unsigned long nr_segs, loff_t *ppos)
-{
-	struct kiocb kiocb;
-	ssize_t ret;
-
-	init_sync_kiocb(&kiocb, file);
-	ret = generic_file_aio_write_nolock(&kiocb, iov, nr_segs, ppos);
-	if (-EIOCBQUEUED == ret)
-		ret = wait_on_sync_kiocb(&kiocb);
-	return ret;
-}
-EXPORT_SYMBOL(generic_file_write_nolock);
-
-ssize_t generic_file_aio_write(struct kiocb *iocb, const char __user *buf,
-			       size_t count, loff_t pos)
+ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
+		unsigned long nr_segs, loff_t pos)
 {
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
 	struct inode *inode = mapping->host;
 	ssize_t ret;
-	struct iovec local_iov = { .iov_base = (void __user *)buf,
-					.iov_len = count };
 
 	BUG_ON(iocb->ki_pos != pos);
 
 	mutex_lock(&inode->i_mutex);
-	ret = __generic_file_aio_write_nolock(iocb, &local_iov, 1,
-						&iocb->ki_pos);
+	ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs,
+			&iocb->ki_pos);
 	mutex_unlock(&inode->i_mutex);
 
 	if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
@@ -2394,66 +2344,6 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const char __user *buf,
 }
 EXPORT_SYMBOL(generic_file_aio_write);
 
-ssize_t generic_file_write(struct file *file, const char __user *buf,
-			   size_t count, loff_t *ppos)
-{
-	struct address_space *mapping = file->f_mapping;
-	struct inode *inode = mapping->host;
-	ssize_t	ret;
-	struct iovec local_iov = { .iov_base = (void __user *)buf,
-					.iov_len = count };
-
-	mutex_lock(&inode->i_mutex);
-	ret = __generic_file_write_nolock(file, &local_iov, 1, ppos);
-	mutex_unlock(&inode->i_mutex);
-
-	if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
-		ssize_t err;
-
-		err = sync_page_range(inode, mapping, *ppos - ret, ret);
-		if (err < 0)
-			ret = err;
-	}
-	return ret;
-}
-EXPORT_SYMBOL(generic_file_write);
-
-ssize_t generic_file_readv(struct file *filp, const struct iovec *iov,
-			unsigned long nr_segs, loff_t *ppos)
-{
-	struct kiocb kiocb;
-	ssize_t ret;
-
-	init_sync_kiocb(&kiocb, filp);
-	ret = __generic_file_aio_read(&kiocb, iov, nr_segs, ppos);
-	if (-EIOCBQUEUED == ret)
-		ret = wait_on_sync_kiocb(&kiocb);
-	return ret;
-}
-EXPORT_SYMBOL(generic_file_readv);
-
-ssize_t generic_file_writev(struct file *file, const struct iovec *iov,
-			unsigned long nr_segs, loff_t *ppos)
-{
-	struct address_space *mapping = file->f_mapping;
-	struct inode *inode = mapping->host;
-	ssize_t ret;
-
-	mutex_lock(&inode->i_mutex);
-	ret = __generic_file_write_nolock(file, iov, nr_segs, ppos);
-	mutex_unlock(&inode->i_mutex);
-
-	if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
-		int err;
-
-		err = sync_page_range(inode, mapping, *ppos - ret, ret);
-		if (err < 0)
-			ret = err;
-	}
-	return ret;
-}
-EXPORT_SYMBOL(generic_file_writev);
-
 /*
  * Called under i_mutex for writes to S_ISREG files.   Returns -EIO if something
  * went wrong during pagecache shootdown.
@@ -2493,3 +2383,33 @@ generic_file_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
 	}
 	return retval;
 }
+
+/**
+ * try_to_release_page() - release old fs-specific metadata on a page
+ *
+ * @page: the page which the kernel is trying to free
+ * @gfp_mask: memory allocation flags (and I/O mode)
+ *
+ * The address_space is to try to release any data against the page
+ * (presumably at page->private).  If the release was successful, return `1'.
+ * Otherwise return zero.
+ *
+ * The @gfp_mask argument specifies whether I/O may be performed to release
+ * this page (__GFP_IO), and whether the call may block (__GFP_WAIT).
+ *
+ * NOTE: @gfp_mask may go away, and this function may become non-blocking.
+ */
+int try_to_release_page(struct page *page, gfp_t gfp_mask)
+{
+	struct address_space * const mapping = page->mapping;
+
+	BUG_ON(!PageLocked(page));
+	if (PageWriteback(page))
+		return 0;
+
+	if (mapping && mapping->a_ops->releasepage)
+		return mapping->a_ops->releasepage(page, gfp_mask);
+	return try_to_free_buffers(page);
+}
+
+EXPORT_SYMBOL(try_to_release_page);
diff --git a/mm/fremap.c b/mm/fremap.c
index aa30618ec6b..7a9d0f5d246 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -39,7 +39,7 @@ static int zap_pte(struct mm_struct *mm, struct vm_area_struct *vma,
 	} else {
 		if (!pte_file(pte))
 			free_swap_and_cache(pte_to_swp_entry(pte));
-		pte_clear(mm, addr, ptep);
+		pte_clear_not_present_full(mm, addr, ptep, 0);
 	}
 	return !!page;
 }
diff --git a/mm/highmem.c b/mm/highmem.c
index ee5519b176e..0206e7e5018 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -29,13 +29,6 @@
 #include <linux/blktrace_api.h>
 #include <asm/tlbflush.h>
 
-static mempool_t *page_pool, *isa_page_pool;
-
-static void *mempool_alloc_pages_isa(gfp_t gfp_mask, void *data)
-{
-	return mempool_alloc_pages(gfp_mask | GFP_DMA, data);
-}
-
 /*
  * Virtual_count is not a pure "count".
  *  0 means that it is not mapped, and has not been mapped
@@ -217,282 +210,8 @@ void fastcall kunmap_high(struct page *page)
 }
 
 EXPORT_SYMBOL(kunmap_high);
-
-#define POOL_SIZE	64
-
-static __init int init_emergency_pool(void)
-{
-	struct sysinfo i;
-	si_meminfo(&i);
-	si_swapinfo(&i);
-        
-	if (!i.totalhigh)
-		return 0;
-
-	page_pool = mempool_create_page_pool(POOL_SIZE, 0);
-	BUG_ON(!page_pool);
-	printk("highmem bounce pool size: %d pages\n", POOL_SIZE);
-
-	return 0;
-}
-
-__initcall(init_emergency_pool);
-
-/*
- * highmem version, map in to vec
- */
-static void bounce_copy_vec(struct bio_vec *to, unsigned char *vfrom)
-{
-	unsigned long flags;
-	unsigned char *vto;
-
-	local_irq_save(flags);
-	vto = kmap_atomic(to->bv_page, KM_BOUNCE_READ);
-	memcpy(vto + to->bv_offset, vfrom, to->bv_len);
-	kunmap_atomic(vto, KM_BOUNCE_READ);
-	local_irq_restore(flags);
-}
-
-#else /* CONFIG_HIGHMEM */
-
-#define bounce_copy_vec(to, vfrom)	\
-	memcpy(page_address((to)->bv_page) + (to)->bv_offset, vfrom, (to)->bv_len)
-
 #endif
 
-#define ISA_POOL_SIZE	16
-
-/*
- * gets called "every" time someone init's a queue with BLK_BOUNCE_ISA
- * as the max address, so check if the pool has already been created.
- */
-int init_emergency_isa_pool(void)
-{
-	if (isa_page_pool)
-		return 0;
-
-	isa_page_pool = mempool_create(ISA_POOL_SIZE, mempool_alloc_pages_isa,
-				       mempool_free_pages, (void *) 0);
-	BUG_ON(!isa_page_pool);
-
-	printk("isa bounce pool size: %d pages\n", ISA_POOL_SIZE);
-	return 0;
-}
-
-/*
- * Simple bounce buffer support for highmem pages. Depending on the
- * queue gfp mask set, *to may or may not be a highmem page. kmap it
- * always, it will do the Right Thing
- */
-static void copy_to_high_bio_irq(struct bio *to, struct bio *from)
-{
-	unsigned char *vfrom;
-	struct bio_vec *tovec, *fromvec;
-	int i;
-
-	__bio_for_each_segment(tovec, to, i, 0) {
-		fromvec = from->bi_io_vec + i;
-
-		/*
-		 * not bounced
-		 */
-		if (tovec->bv_page == fromvec->bv_page)
-			continue;
-
-		/*
-		 * fromvec->bv_offset and fromvec->bv_len might have been
-		 * modified by the block layer, so use the original copy,
-		 * bounce_copy_vec already uses tovec->bv_len
-		 */
-		vfrom = page_address(fromvec->bv_page) + tovec->bv_offset;
-
-		flush_dcache_page(tovec->bv_page);
-		bounce_copy_vec(tovec, vfrom);
-	}
-}
-
-static void bounce_end_io(struct bio *bio, mempool_t *pool, int err)
-{
-	struct bio *bio_orig = bio->bi_private;
-	struct bio_vec *bvec, *org_vec;
-	int i;
-
-	if (test_bit(BIO_EOPNOTSUPP, &bio->bi_flags))
-		set_bit(BIO_EOPNOTSUPP, &bio_orig->bi_flags);
-
-	/*
-	 * free up bounce indirect pages used
-	 */
-	__bio_for_each_segment(bvec, bio, i, 0) {
-		org_vec = bio_orig->bi_io_vec + i;
-		if (bvec->bv_page == org_vec->bv_page)
-			continue;
-
-		dec_zone_page_state(bvec->bv_page, NR_BOUNCE);
-		mempool_free(bvec->bv_page, pool);
-	}
-
-	bio_endio(bio_orig, bio_orig->bi_size, err);
-	bio_put(bio);
-}
-
-static int bounce_end_io_write(struct bio *bio, unsigned int bytes_done, int err)
-{
-	if (bio->bi_size)
-		return 1;
-
-	bounce_end_io(bio, page_pool, err);
-	return 0;
-}
-
-static int bounce_end_io_write_isa(struct bio *bio, unsigned int bytes_done, int err)
-{
-	if (bio->bi_size)
-		return 1;
-
-	bounce_end_io(bio, isa_page_pool, err);
-	return 0;
-}
-
-static void __bounce_end_io_read(struct bio *bio, mempool_t *pool, int err)
-{
-	struct bio *bio_orig = bio->bi_private;
-
-	if (test_bit(BIO_UPTODATE, &bio->bi_flags))
-		copy_to_high_bio_irq(bio_orig, bio);
-
-	bounce_end_io(bio, pool, err);
-}
-
-static int bounce_end_io_read(struct bio *bio, unsigned int bytes_done, int err)
-{
-	if (bio->bi_size)
-		return 1;
-
-	__bounce_end_io_read(bio, page_pool, err);
-	return 0;
-}
-
-static int bounce_end_io_read_isa(struct bio *bio, unsigned int bytes_done, int err)
-{
-	if (bio->bi_size)
-		return 1;
-
-	__bounce_end_io_read(bio, isa_page_pool, err);
-	return 0;
-}
-
-static void __blk_queue_bounce(request_queue_t *q, struct bio **bio_orig,
-			       mempool_t *pool)
-{
-	struct page *page;
-	struct bio *bio = NULL;
-	int i, rw = bio_data_dir(*bio_orig);
-	struct bio_vec *to, *from;
-
-	bio_for_each_segment(from, *bio_orig, i) {
-		page = from->bv_page;
-
-		/*
-		 * is destination page below bounce pfn?
-		 */
-		if (page_to_pfn(page) < q->bounce_pfn)
-			continue;
-
-		/*
-		 * irk, bounce it
-		 */
-		if (!bio)
-			bio = bio_alloc(GFP_NOIO, (*bio_orig)->bi_vcnt);
-
-		to = bio->bi_io_vec + i;
-
-		to->bv_page = mempool_alloc(pool, q->bounce_gfp);
-		to->bv_len = from->bv_len;
-		to->bv_offset = from->bv_offset;
-		inc_zone_page_state(to->bv_page, NR_BOUNCE);
-
-		if (rw == WRITE) {
-			char *vto, *vfrom;
-
-			flush_dcache_page(from->bv_page);
-			vto = page_address(to->bv_page) + to->bv_offset;
-			vfrom = kmap(from->bv_page) + from->bv_offset;
-			memcpy(vto, vfrom, to->bv_len);
-			kunmap(from->bv_page);
-		}
-	}
-
-	/*
-	 * no pages bounced
-	 */
-	if (!bio)
-		return;
-
-	/*
-	 * at least one page was bounced, fill in possible non-highmem
-	 * pages
-	 */
-	__bio_for_each_segment(from, *bio_orig, i, 0) {
-		to = bio_iovec_idx(bio, i);
-		if (!to->bv_page) {
-			to->bv_page = from->bv_page;
-			to->bv_len = from->bv_len;
-			to->bv_offset = from->bv_offset;
-		}
-	}
-
-	bio->bi_bdev = (*bio_orig)->bi_bdev;
-	bio->bi_flags |= (1 << BIO_BOUNCED);
-	bio->bi_sector = (*bio_orig)->bi_sector;
-	bio->bi_rw = (*bio_orig)->bi_rw;
-
-	bio->bi_vcnt = (*bio_orig)->bi_vcnt;
-	bio->bi_idx = (*bio_orig)->bi_idx;
-	bio->bi_size = (*bio_orig)->bi_size;
-
-	if (pool == page_pool) {
-		bio->bi_end_io = bounce_end_io_write;
-		if (rw == READ)
-			bio->bi_end_io = bounce_end_io_read;
-	} else {
-		bio->bi_end_io = bounce_end_io_write_isa;
-		if (rw == READ)
-			bio->bi_end_io = bounce_end_io_read_isa;
-	}
-
-	bio->bi_private = *bio_orig;
-	*bio_orig = bio;
-}
-
-void blk_queue_bounce(request_queue_t *q, struct bio **bio_orig)
-{
-	mempool_t *pool;
-
-	/*
-	 * for non-isa bounce case, just check if the bounce pfn is equal
-	 * to or bigger than the highest pfn in the system -- in that case,
-	 * don't waste time iterating over bio segments
-	 */
-	if (!(q->bounce_gfp & GFP_DMA)) {
-		if (q->bounce_pfn >= blk_max_pfn)
-			return;
-		pool = page_pool;
-	} else {
-		BUG_ON(!isa_page_pool);
-		pool = isa_page_pool;
-	}
-
-	blk_add_trace_bio(q, *bio_orig, BLK_TA_BOUNCE);
-
-	/*
-	 * slow path
-	 */
-	__blk_queue_bounce(q, bio_orig, pool);
-}
-
-EXPORT_SYMBOL(blk_queue_bounce);
-
 #if defined(HASHED_PAGE_VIRTUAL)
 
 #define PA_HASH_ORDER	7
diff --git a/mm/memory.c b/mm/memory.c
index 601159a46ab..9cf3f341a28 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -467,7 +467,7 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	 */
 	if (is_cow_mapping(vm_flags)) {
 		ptep_set_wrprotect(src_mm, addr, src_pte);
-		pte = *src_pte;
+		pte = pte_wrprotect(pte);
 	}
 
 	/*
@@ -506,6 +506,7 @@ again:
 	src_pte = pte_offset_map_nested(src_pmd, addr);
 	src_ptl = pte_lockptr(src_mm, src_pmd);
 	spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
+	arch_enter_lazy_mmu_mode();
 
 	do {
 		/*
@@ -527,6 +528,7 @@ again:
 		progress += 8;
 	} while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);
 
+	arch_leave_lazy_mmu_mode();
 	spin_unlock(src_ptl);
 	pte_unmap_nested(src_pte - 1);
 	add_mm_rss(dst_mm, rss[0], rss[1]);
@@ -628,6 +630,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 	int anon_rss = 0;
 
 	pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+	arch_enter_lazy_mmu_mode();
 	do {
 		pte_t ptent = *pte;
 		if (pte_none(ptent)) {
@@ -690,10 +693,11 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 			continue;
 		if (!pte_file(ptent))
 			free_swap_and_cache(pte_to_swp_entry(ptent));
-		pte_clear_full(mm, addr, pte, tlb->fullmm);
+		pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
 	} while (pte++, addr += PAGE_SIZE, (addr != end && *zap_work > 0));
 
 	add_mm_rss(mm, file_rss, anon_rss);
+	arch_leave_lazy_mmu_mode();
 	pte_unmap_unlock(pte - 1, ptl);
 
 	return addr;
@@ -1109,6 +1113,7 @@ static int zeromap_pte_range(struct mm_struct *mm, pmd_t *pmd,
 	pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
 	if (!pte)
 		return -ENOMEM;
+	arch_enter_lazy_mmu_mode();
 	do {
 		struct page *page = ZERO_PAGE(addr);
 		pte_t zero_pte = pte_wrprotect(mk_pte(page, prot));
@@ -1118,6 +1123,7 @@ static int zeromap_pte_range(struct mm_struct *mm, pmd_t *pmd,
 		BUG_ON(!pte_none(*pte));
 		set_pte_at(m