switch the block layer to use kmap_local_page v2

@@ -224,4 +224,11 @@ do {								\
 	__kunmap_local(__addr);					\
 } while (0)
 
+#define kunmap_local_dirty(__page, __addr)			\
+do {								\
+	if (!PageSlab(__page))					\
+		flush_kernel_dcache_page(__page);		\
+	kunmap_local(__addr);					\
+} while (0)
+
 #endif

@@ -93,6 +93,10 @@ static inline void kmap_flush_unused(void);
  * On HIGHMEM enabled systems mapping a highmem page has the side effect of
  * disabling migration in order to keep the virtual address stable across
  * preemption. No caller of kmap_local_page() can rely on this side effect.
+ *
+ * If data is written to the returned kernel mapping, the callers needs to
+ * unmap the mapping using kunmap_local_dirty(), else kunmap_local() should
+ * be used.
  */
 static inline void *kmap_local_page(struct page *page);
 

@@ -333,7 +333,7 @@ static inline void memcpy_to_page(struct page *page, size_t offset,
 
 	VM_BUG_ON(offset + len > PAGE_SIZE);
 	memcpy(to + offset, from, len);
-	kunmap_local(to);
+	kunmap_local_dirty(page, to);
 }
 
 static inline void memzero_page(struct page *page, size_t offset, size_t len)

@@ -338,9 +338,9 @@ static inline void memcpy_to_page(struct page *page, size_t offset,
 
 static inline void memzero_page(struct page *page, size_t offset, size_t len)
 {
-	char *addr = kmap_atomic(page);
+	char *addr = kmap_local_page(page);
 	memset(addr + offset, 0, len);
-	kunmap_atomic(addr);
+	kunmap_local_dirty(page, addr);
 }
 
 #endif /* _LINUX_HIGHMEM_H */

@@ -7,8 +7,6 @@
 #ifndef __ASM_RC32434_RB_H
 #define __ASM_RC32434_RB_H
 
-#include <linux/genhd.h>
-
 #define REGBASE		0x18000000
 #define IDT434_REG_BASE ((volatile void *) KSEG1ADDR(REGBASE))
 #define UART0BASE	0x58000

@@ -4,8 +4,8 @@
  *
  * Copyright (C) 2001 Ming Lei <ming.lei@canonical.com>
  */
-#ifndef __LINUX_BVEC_ITER_H
-#define __LINUX_BVEC_ITER_H
+#ifndef __LINUX_BVEC_H
+#define __LINUX_BVEC_H
 
 #include <linux/bug.h>
 #include <linux/errno.h>

@@ -183,4 +183,4 @@ static inline void bvec_advance(const struct bio_vec *bvec,
 	}
 }
 
-#endif /* __LINUX_BVEC_ITER_H */
+#endif /* __LINUX_BVEC_H */

@@ -7,6 +7,7 @@
 #ifndef __LINUX_BVEC_H
 #define __LINUX_BVEC_H
 
+#include <linux/highmem.h>
 #include <linux/bug.h>
 #include <linux/errno.h>
 #include <linux/limits.h>

@@ -183,4 +184,16 @@ static inline void bvec_advance(const struct bio_vec *bvec,
 	}
 }
 
+/**
+ * bvec_kmap_local - map a bvec into the kernel virtual address space
+ * @bvec: bvec to map
+ *
+ * Must be called on single-page bvecs only.  Call kunmap_local on the returned
+ * address to unmap.
+ */
+static inline void *bvec_kmap_local(struct bio_vec *bvec)
+{
+	return kmap_local_page(bvec->bv_page) + bvec->bv_offset;
+}
+
 #endif /* __LINUX_BVEC_H */

@@ -196,4 +196,37 @@ static inline void *bvec_kmap_local(struct bio_vec *bvec)
 	return kmap_local_page(bvec->bv_page) + bvec->bv_offset;
 }
 
+/**
+ * memcpy_from_bvec - copy data from a bvec
+ * @bvec: bvec to copy from
+ *
+ * Must be called on single-page bvecs only.
+ */
+static inline void memcpy_from_bvec(char *to, struct bio_vec *bvec)
+{
+	memcpy_from_page(to, bvec->bv_page, bvec->bv_offset, bvec->bv_len);
+}
+
+/**
+ * memcpy_to_bvec - copy data to a bvec
+ * @bvec: bvec to copy to
+ *
+ * Must be called on single-page bvecs only.
+ */
+static inline void memcpy_to_bvec(struct bio_vec *bvec, const char *from)
+{
+	memcpy_to_page(bvec->bv_page, bvec->bv_offset, from, bvec->bv_len);
+}
+
+/**
+ * memzero_bvec - zero all data in a bvec
+ * @bvec: bvec to zero
+ *
+ * Must be called on single-page bvecs only.
+ */
+static inline void memzero_bvec(struct bio_vec *bvec)
+{
+	memzero_page(bvec->bv_page, bvec->bv_offset, bvec->bv_len);
+}
+
 #endif /* __LINUX_BVEC_H */

@@ -495,16 +495,11 @@ EXPORT_SYMBOL(bio_kmalloc);
 
 void zero_fill_bio(struct bio *bio)
 {
-	unsigned long flags;
 	struct bio_vec bv;
 	struct bvec_iter iter;
 
-	bio_for_each_segment(bv, bio, iter) {
-		char *data = bvec_kmap_irq(&bv, &flags);
-		memset(data, 0, bv.bv_len);
-		flush_dcache_page(bv.bv_page);
-		bvec_kunmap_irq(data, &flags);
-	}
+	bio_for_each_segment(bv, bio, iter)
+		memzero_bvec(&bv);
 }
 EXPORT_SYMBOL(zero_fill_bio);
 

@@ -1219,24 +1219,13 @@ static void rbd_dev_mapping_clear(struct rbd_device *rbd_dev)
 	rbd_dev->mapping.size = 0;
 }
 
-static void zero_bvec(struct bio_vec *bv)
-{
-	void *buf;
-	unsigned long flags;
-
-	buf = bvec_kmap_irq(bv, &flags);
-	memset(buf, 0, bv->bv_len);
-	flush_dcache_page(bv->bv_page);
-	bvec_kunmap_irq(buf, &flags);
-}
-
 static void zero_bios(struct ceph_bio_iter *bio_pos, u32 off, u32 bytes)
 {
 	struct ceph_bio_iter it = *bio_pos;
 
 	ceph_bio_iter_advance(&it, off);
 	ceph_bio_iter_advance_step(&it, bytes, ({
-		zero_bvec(&bv);
+		memzero_bvec(&bv);
 	}));
 }
 

@@ -1246,7 +1235,7 @@ static void zero_bvecs(struct ceph_bvec_iter *bvec_pos, u32 off, u32 bytes)
 
 	ceph_bvec_iter_advance(&it, off);
 	ceph_bvec_iter_advance_step(&it, bytes, ({
-		zero_bvec(&bv);
+		memzero_bvec(&bv);
 	}));
 }
 

@@ -1205,14 +1205,13 @@ static void memcpy_flushcache_optimized(void *dest, void *source, size_t size)
 static void bio_copy_block(struct dm_writecache *wc, struct bio *bio, void *data)
 {
 	void *buf;
-	unsigned long flags;
 	unsigned size;
 	int rw = bio_data_dir(bio);
 	unsigned remaining_size = wc->block_size;
 
 	do {
 		struct bio_vec bv = bio_iter_iovec(bio, bio->bi_iter);
-		buf = bvec_kmap_irq(&bv, &flags);
+		buf = bvec_kmap_local(&bv);
 		size = bv.bv_len;
 		if (unlikely(size > remaining_size))
 			size = remaining_size;

@@ -1230,7 +1229,7 @@ static void bio_copy_block(struct dm_writecache *wc, struct bio *bio, void *data
 			memcpy_flushcache_optimized(data, buf, size);
 		}
 
-		bvec_kunmap_irq(buf, &flags);
+		kunmap_local(buf);
 
 		data = (char *)data + size;
 		remaining_size -= size;

@@ -83,26 +83,13 @@ static void ps3disk_scatter_gather(struct ps3_storage_device *dev,
 	unsigned int offset = 0;
 	struct req_iterator iter;
 	struct bio_vec bvec;
-	unsigned int i = 0;
-	size_t size;
-	void *buf;
 
 	rq_for_each_segment(bvec, req, iter) {
-		unsigned long flags;
-		dev_dbg(&dev->sbd.core, "%s:%u: bio %u: %u sectors from %llu\n",
-			__func__, __LINE__, i, bio_sectors(iter.bio),
-			iter.bio->bi_iter.bi_sector);
-
-		size = bvec.bv_len;
-		buf = bvec_kmap_irq(&bvec, &flags);
 		if (gather)
-			memcpy(dev->bounce_buf+offset, buf, size);
+			memcpy_from_bvec(dev->bounce_buf + offset, &bvec);
 		else
-			memcpy(buf, dev->bounce_buf+offset, size);
-		offset += size;
-		flush_kernel_dcache_page(bvec.bv_page);
-		bvec_kunmap_irq(buf, &flags);
-		i++;
+			memcpy_to_bvec(&bvec, dev->bounce_buf + offset);
+		offset += bvec.bv_len;
 	}
 }
 

@@ -5,7 +5,6 @@
 #ifndef __LINUX_BIO_H
 #define __LINUX_BIO_H
 
-#include <linux/highmem.h>
 #include <linux/mempool.h>
 #include <linux/ioprio.h>
 /* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */

@@ -519,47 +518,6 @@ static inline void bio_clone_blkg_association(struct bio *dst,
 					      struct bio *src) { }
 #endif	/* CONFIG_BLK_CGROUP */
 
-#ifdef CONFIG_HIGHMEM
-/*
- * remember never ever reenable interrupts between a bvec_kmap_irq and
- * bvec_kunmap_irq!
- */
-static inline char *bvec_kmap_irq(struct bio_vec *bvec, unsigned long *flags)
-{
-	unsigned long addr;
-
-	/*
-	 * might not be a highmem page, but the preempt/irq count
-	 * balancing is a lot nicer this way
-	 */
-	local_irq_save(*flags);
-	addr = (unsigned long) kmap_atomic(bvec->bv_page);
-
-	BUG_ON(addr & ~PAGE_MASK);
-
-	return (char *) addr + bvec->bv_offset;
-}
-
-static inline void bvec_kunmap_irq(char *buffer, unsigned long *flags)
-{
-	unsigned long ptr = (unsigned long) buffer & PAGE_MASK;
-
-	kunmap_atomic((void *) ptr);
-	local_irq_restore(*flags);
-}
-
-#else
-static inline char *bvec_kmap_irq(struct bio_vec *bvec, unsigned long *flags)
-{
-	return page_address(bvec->bv_page) + bvec->bv_offset;
-}
-
-static inline void bvec_kunmap_irq(char *buffer, unsigned long *flags)
-{
-	*flags = 0;
-}
-#endif
-
 /*
  * BIO list management for use by remapping drivers (e.g. DM or MD) and loop.
  *

@@ -1186,27 +1186,15 @@ EXPORT_SYMBOL(bio_advance);
 void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter,
 			struct bio *src, struct bvec_iter *src_iter)
 {
-	struct bio_vec src_bv, dst_bv;
-	void *src_p, *dst_p;
-	unsigned bytes;
-
 	while (src_iter->bi_size && dst_iter->bi_size) {
-		src_bv = bio_iter_iovec(src, *src_iter);
-		dst_bv = bio_iter_iovec(dst, *dst_iter);
-
-		bytes = min(src_bv.bv_len, dst_bv.bv_len);
-
-		src_p = kmap_atomic(src_bv.bv_page);
-		dst_p = kmap_atomic(dst_bv.bv_page);
-
-		memcpy(dst_p + dst_bv.bv_offset,
-		       src_p + src_bv.bv_offset,
-		       bytes);
-
-		kunmap_atomic(dst_p);
-		kunmap_atomic(src_p);
-
-		flush_dcache_page(dst_bv.bv_page);
+		struct bio_vec src_bv = bio_iter_iovec(src, *src_iter);
+		struct bio_vec dst_bv = bio_iter_iovec(dst, *dst_iter);
+		unsigned int bytes = min(src_bv.bv_len, dst_bv.bv_len);
+		void *src_buf;
+
+		src_buf = bvec_kmap_local(&src_bv);
+		memcpy_to_bvec(&dst_bv, src_buf);
+		kunmap_local(src_buf);
 
 		bio_advance_iter_single(src, src_iter, bytes);
 		bio_advance_iter_single(dst, dst_iter, bytes);

@@ -67,18 +67,6 @@ static __init int init_emergency_pool(void)
 
 __initcall(init_emergency_pool);
 
-/*
- * highmem version, map in to vec
- */
-static void bounce_copy_vec(struct bio_vec *to, unsigned char *vfrom)
-{
-	unsigned char *vto;
-
-	vto = kmap_atomic(to->bv_page);
-	memcpy(vto + to->bv_offset, vfrom, to->bv_len);
-	kunmap_atomic(vto);
-}
-
 /*
  * 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

@@ -86,7 +74,6 @@ static void bounce_copy_vec(struct bio_vec *to, unsigned char *vfrom)
  */
 static void copy_to_high_bio_irq(struct bio *to, struct bio *from)
 {
-	unsigned char *vfrom;
 	struct bio_vec tovec, fromvec;
 	struct bvec_iter iter;
 	/*

@@ -104,11 +91,8 @@ static void copy_to_high_bio_irq(struct bio *to, struct bio *from)
 			 * 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;
-
-			bounce_copy_vec(&tovec, vfrom);
-			flush_dcache_page(tovec.bv_page);
+			memcpy_to_bvec(&tovec, page_address(fromvec.bv_page) +
+				       tovec.bv_offset);
 		}
 		bio_advance_iter(from, &from_iter, tovec.bv_len);
 	}

@@ -400,7 +400,7 @@ static void bio_copy_kern_endio_read(struct bio *bio)
 	struct bvec_iter_all iter_all;
 
 	bio_for_each_segment_all(bvec, bio, iter_all) {
-		memcpy(p, page_address(bvec->bv_page), bvec->bv_len);
+		memcpy_from_bvec(p, bvec);
 		p += bvec->bv_len;
 	}
 

@@ -239,24 +239,19 @@ void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
 	 * because the 'bio' is single-page bvec.
 	 */
 	for (i = 0, to = bio->bi_io_vec; i < bio->bi_vcnt; to++, i++) {
-		struct page *page = to->bv_page;
+		struct page *bounce_page;
 
-		if (!PageHighMem(page))
+		if (!PageHighMem(to->bv_page))
 			continue;
 
-		to->bv_page = mempool_alloc(&page_pool, GFP_NOIO);
-		inc_zone_page_state(to->bv_page, NR_BOUNCE);
+		bounce_page = mempool_alloc(&page_pool, GFP_NOIO);
+		inc_zone_page_state(bounce_page, NR_BOUNCE);
 
 		if (rw == WRITE) {
-			char *vto, *vfrom;
-
-			flush_dcache_page(page);
-
-			vto = page_address(to->bv_page) + to->bv_offset;
-			vfrom = kmap_atomic(page) + to->bv_offset;
-			memcpy(vto, vfrom, to->bv_len);
-			kunmap_atomic(vfrom);
+			flush_dcache_page(to->bv_page);
+			memcpy_from_bvec(page_address(bounce_page), to);
 		}
+		to->bv_page = bounce_page;
 	}
 
 	trace_block_bio_bounce(*bio_orig);

@@ -147,11 +147,10 @@ static void t10_pi_type1_prepare(struct request *rq)
 			break;
 
 		bip_for_each_vec(iv, bip, iter) {
-			void *p, *pmap;
 			unsigned int j;
+			void *p;
 
-			pmap = kmap_atomic(iv.bv_page);
-			p = pmap + iv.bv_offset;
+			p = bvec_kmap_local(&iv);
 			for (j = 0; j < iv.bv_len; j += tuple_sz) {
 				struct t10_pi_tuple *pi = p;
 

@@ -161,8 +160,7 @@ static void t10_pi_type1_prepare(struct request *rq)
 				ref_tag++;
 				p += tuple_sz;
 			}
-
-			kunmap_atomic(pmap);
+			kunmap_local(p);
 		}
 
 		bip->bip_flags |= BIP_MAPPED_INTEGRITY;

@@ -195,11 +193,10 @@ static void t10_pi_type1_complete(struct request *rq, unsigned int nr_bytes)
 		struct bvec_iter iter;
 
 		bip_for_each_vec(iv, bip, iter) {
-			void *p, *pmap;
 			unsigned int j;
+			void *p;
 
-			pmap = kmap_atomic(iv.bv_page);
-			p = pmap + iv.bv_offset;
+			p = bvec_kmap_local(&iv);
 			for (j = 0; j < iv.bv_len && intervals; j += tuple_sz) {
 				struct t10_pi_tuple *pi = p;
 

@@ -210,8 +207,7 @@ static void t10_pi_type1_complete(struct request *rq, unsigned int nr_bytes)
 				intervals--;
 				p += tuple_sz;
 			}
-
-			kunmap_atomic(pmap);
+			kunmap_local(p);
 		}
 	}
 }

@@ -172,18 +172,16 @@ static blk_status_t bio_integrity_process(struct bio *bio,
 	iter.prot_buf = prot_buf;
 
 	__bio_for_each_segment(bv, bio, bviter, *proc_iter) {
-		void *kaddr = kmap_atomic(bv.bv_page);
+		void *kaddr = bvec_kmap_local(&bv);
 
-		iter.data_buf = kaddr + bv.bv_offset;
+		iter.data_buf = kaddr;
 		iter.data_size = bv.bv_len;
-
 		ret = proc_fn(&iter);
-		if (ret) {
-			kunmap_atomic(kaddr);
-			return ret;
-		}
+		kunmap_local(kaddr);
+
+		if (ret)
+			break;
 
-		kunmap_atomic(kaddr);
 	}
 	return ret;
 }

@@ -81,12 +81,7 @@ static inline void scatterwalk_pagedone(struct scatter_walk *walk, int out,
 		struct page *page;
 
 		page = sg_page(walk->sg) + ((walk->offset - 1) >> PAGE_SHIFT);
-		/* Test ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE first as
-		 * PageSlab cannot be optimised away per se due to
-		 * use of volatile pointer.
-		 */
-		if (ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE && !PageSlab(page))
-			flush_dcache_page(page);
+		flush_dcache_page(page);
 	}
 
 	if (more && walk->offset >= walk->sg->offset + walk->sg->length)