Merge branch 'iommu-generic-allocator'

Sowmini Varadhan says:

====================
Generic IOMMU pooled allocator

Investigation of network performance on Sparc shows a high
degree of locking contention in the IOMMU allocator, and it
was noticed that the PowerPC code has a better locking model.

This patch series tries to extract the generic parts of the
PowerPC code so that it can be shared across multiple PCI
devices and architectures.

v10: resend patchv9 without RFC tag, and a new mail Message-Id,
(previous non-RFC attempt did not show up on the patchwork queue?)

Full revision history below:
v2 changes:
  - incorporate David Miller editorial comments: sparc specific
    fields moved from iommu-common into sparc's iommu_64.h
  - make the npools value an input parameter, for the case when
    the iommu map size is not very large
  - cookie_to_index mapping, and optimizations for span-boundary
    check, for use case such as LDC.

v3: eliminate iommu_sparc, rearrange the ->demap indirection to
    be invoked under the pool lock.

v4: David Miller review changes:
  - s/IOMMU_ERROR_CODE/DMA_ERROR_CODE
  - page_table_map_base and page_table_shift are unsigned long, not u32.

v5: removed ->cookie_to_index and ->demap indirection from the
    iommu_tbl_ops The caller needs to call these functions as needed,
    before invoking the generic arena allocator functions.
    Added the "skip_span_boundary" argument to iommu_tbl_pool_init() for
    those callers like LDC which do no care about span boundary checks.

v6: removed iommu_tbl_ops, and instead pass the ->flush_all as
    an indirection to iommu_tbl_pool_init(); only invoke ->flush_all
    when there is no large_pool, based on the assumption that large-pool
    usage is infrequently encountered

v7: moved pool_hash initialization to lib/iommu-common.c and cleaned up
    code duplication from sun4v/sun4u/ldc.

v8: Addresses BenH comments with one exception: I've left the
    IOMMU_POOL_HASH as is, so that powerpc can tailor it to their
    convenience.  Discard trylock for simple spin_lock to acquire pool

v9: Addresses latest BenH comments: need_flush checks, add support
    for dma mask and align_order.

v10: resend without RFC tag, and new mail Message-Id.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

arch/sparc/include/asm/iommu_64.h

@@ -16,6 +16,7 @@
 #define IOPTE_WRITE   0x0000000000000002UL
 
 #define IOMMU_NUM_CTXS	4096
+#include <linux/iommu-common.h>
 
 struct iommu_arena {
 	unsigned long	*map;
@@ -24,11 +25,10 @@ struct iommu_arena {
 };
 
 struct iommu {
+	struct iommu_map_table	tbl;
 	spinlock_t		lock;
-	struct iommu_arena	arena;
-	void			(*flush_all)(struct iommu *);
+	u32			dma_addr_mask;
 	iopte_t			*page_table;
-	u32			page_table_map_base;
 	unsigned long		iommu_control;
 	unsigned long		iommu_tsbbase;
 	unsigned long		iommu_flush;
@@ -40,7 +40,6 @@ struct iommu {
 	unsigned long		dummy_page_pa;
 	unsigned long		ctx_lowest_free;
 	DECLARE_BITMAP(ctx_bitmap, IOMMU_NUM_CTXS);
-	u32			dma_addr_mask;
 };
 
 struct strbuf {

arch/sparc/kernel/iommu_common.h

@@ -48,12 +48,4 @@ static inline int is_span_boundary(unsigned long entry,
 	return iommu_is_span_boundary(entry, nr, shift, boundary_size);
 }
 
-unsigned long iommu_range_alloc(struct device *dev,
-				struct iommu *iommu,
-				unsigned long npages,
-				unsigned long *handle);
-void iommu_range_free(struct iommu *iommu,
-		      dma_addr_t dma_addr,
-		      unsigned long npages);
-
 #endif /* _IOMMU_COMMON_H */

arch/sparc/kernel/ldc.c

@@ -15,6 +15,7 @@
 #include <linux/list.h>
 #include <linux/init.h>
 #include <linux/bitmap.h>
+#include <linux/iommu-common.h>
 
 #include <asm/hypervisor.h>
 #include <asm/iommu.h>
@@ -27,6 +28,10 @@
 #define DRV_MODULE_VERSION	"1.1"
 #define DRV_MODULE_RELDATE	"July 22, 2008"
 
+#define COOKIE_PGSZ_CODE	0xf000000000000000ULL
+#define COOKIE_PGSZ_CODE_SHIFT	60ULL
+
+
 static char version[] =
 	DRV_MODULE_NAME ".c:v" DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")\n";
 #define LDC_PACKET_SIZE		64
@@ -98,10 +103,10 @@ static const struct ldc_mode_ops stream_ops;
 int ldom_domaining_enabled;
 
 struct ldc_iommu {
-	/* Protects arena alloc/free.  */
+	/* Protects ldc_unmap.  */
 	spinlock_t			lock;
-	struct iommu_arena		arena;
 	struct ldc_mtable_entry		*page_table;
+	struct iommu_map_table		iommu_map_table;
 };
 
 struct ldc_channel {
@@ -998,31 +1003,59 @@ static void free_queue(unsigned long num_entries, struct ldc_packet *q)
 	free_pages((unsigned long)q, order);
 }
 
+static unsigned long ldc_cookie_to_index(u64 cookie, void *arg)
+{
+	u64 szcode = cookie >> COOKIE_PGSZ_CODE_SHIFT;
+	/* struct ldc_iommu *ldc_iommu = (struct ldc_iommu *)arg; */
+
+	cookie &= ~COOKIE_PGSZ_CODE;
+
+	return (cookie >> (13ULL + (szcode * 3ULL)));
+}
+
+static void ldc_demap(struct ldc_iommu *iommu, unsigned long id, u64 cookie,
+		      unsigned long entry, unsigned long npages)
+{
+	struct ldc_mtable_entry *base;
+	unsigned long i, shift;
+
+	shift = (cookie >> COOKIE_PGSZ_CODE_SHIFT) * 3;
+	base = iommu->page_table + entry;
+	for (i = 0; i < npages; i++) {
+		if (base->cookie)
+			sun4v_ldc_revoke(id, cookie + (i << shift),
+					 base->cookie);
+		base->mte = 0;
+	}
+}
+
 /* XXX Make this configurable... XXX */
 #define LDC_IOTABLE_SIZE	(8 * 1024)
 
-static int ldc_iommu_init(struct ldc_channel *lp)
+static int ldc_iommu_init(const char *name, struct ldc_channel *lp)
 {
 	unsigned long sz, num_tsb_entries, tsbsize, order;
-	struct ldc_iommu *iommu = &lp->iommu;
+	struct ldc_iommu *ldc_iommu = &lp->iommu;
+	struct iommu_map_table *iommu = &ldc_iommu->iommu_map_table;
 	struct ldc_mtable_entry *table;
 	unsigned long hv_err;
 	int err;
 
 	num_tsb_entries = LDC_IOTABLE_SIZE;
 	tsbsize = num_tsb_entries * sizeof(struct ldc_mtable_entry);
-
-	spin_lock_init(&iommu->lock);
+	spin_lock_init(&ldc_iommu->lock);
 
 	sz = num_tsb_entries / 8;
 	sz = (sz + 7UL) & ~7UL;
-	iommu->arena.map = kzalloc(sz, GFP_KERNEL);
-	if (!iommu->arena.map) {
+	iommu->map = kzalloc(sz, GFP_KERNEL);
+	if (!iommu->map) {
 		printk(KERN_ERR PFX "Alloc of arena map failed, sz=%lu\n", sz);
 		return -ENOMEM;
 	}
-
-	iommu->arena.limit = num_tsb_entries;
+	iommu_tbl_pool_init(iommu, num_tsb_entries, PAGE_SHIFT,
+			    NULL, false /* no large pool */,
+			    1 /* npools */,
+			    true /* skip span boundary check */);
 
 	order = get_order(tsbsize);
 
@@ -1037,7 +1070,7 @@ static int ldc_iommu_init(struct ldc_channel *lp)
 
 	memset(table, 0, PAGE_SIZE << order);
 
-	iommu->page_table = table;
+	ldc_iommu->page_table = table;
 
 	hv_err = sun4v_ldc_set_map_table(lp->id, __pa(table),
 					 num_tsb_entries);
@@ -1049,31 +1082,32 @@ static int ldc_iommu_init(struct ldc_channel *lp)
 
 out_free_table:
 	free_pages((unsigned long) table, order);
-	iommu->page_table = NULL;
+	ldc_iommu->page_table = NULL;
 
 out_free_map:
-	kfree(iommu->arena.map);
-	iommu->arena.map = NULL;
+	kfree(iommu->map);
+	iommu->map = NULL;
 
 	return err;
 }
 
 static void ldc_iommu_release(struct ldc_channel *lp)
 {
-	struct ldc_iommu *iommu = &lp->iommu;
+	struct ldc_iommu *ldc_iommu = &lp->iommu;
+	struct iommu_map_table *iommu = &ldc_iommu->iommu_map_table;
 	unsigned long num_tsb_entries, tsbsize, order;
 
 	(void) sun4v_ldc_set_map_table(lp->id, 0, 0);
 
-	num_tsb_entries = iommu->arena.limit;
+	num_tsb_entries = iommu->poolsize * iommu->nr_pools;
 	tsbsize = num_tsb_entries * sizeof(struct ldc_mtable_entry);
 	order = get_order(tsbsize);
 
-	free_pages((unsigned long) iommu->page_table, order);
-	iommu->page_table = NULL;
+	free_pages((unsigned long) ldc_iommu->page_table, order);
+	ldc_iommu->page_table = NULL;
 
-	kfree(iommu->arena.map);
-	iommu->arena.map = NULL;
+	kfree(iommu->map);
+	iommu->map = NULL;
 }
 
 struct ldc_channel *ldc_alloc(unsigned long id,
@@ -1140,7 +1174,7 @@ struct ldc_channel *ldc_alloc(unsigned long id,
 
 	lp->id = id;
 
-	err = ldc_iommu_init(lp);
+	err = ldc_iommu_init(name, lp);
 	if (err)
 		goto out_free_ldc;
 
@@ -1885,40 +1919,6 @@ int ldc_read(struct ldc_channel *lp, void *buf, unsigned int size)
 }
 EXPORT_SYMBOL(ldc_read);
 
-static long arena_alloc(struct ldc_iommu *iommu, unsigned long npages)
-{
-	struct iommu_arena *arena = &iommu->arena;
-	unsigned long n, start, end, limit;
-	int pass;
-
-	limit = arena->limit;
-	start = arena->hint;
-	pass = 0;
-
-again:
-	n = bitmap_find_next_zero_area(arena->map, limit, start, npages, 0);
-	end = n + npages;
-	if (unlikely(end >= limit)) {
-		if (likely(pass < 1)) {
-			limit = start;
-			start = 0;
-			pass++;
-			goto again;
-		} else {
-			/* Scanned the whole thing, give up. */
-			return -1;
-		}
-	}
-	bitmap_set(arena->map, n, npages);
-
-	arena->hint = end;
-
-	return n;
-}
-
-#define COOKIE_PGSZ_CODE	0xf000000000000000ULL
-#define COOKIE_PGSZ_CODE_SHIFT	60ULL
-
 static u64 pagesize_code(void)
 {
 	switch (PAGE_SIZE) {
@@ -1945,23 +1945,14 @@ static u64 make_cookie(u64 index, u64 pgsz_code, u64 page_offset)
 		page_offset);
 }
 
-static u64 cookie_to_index(u64 cookie, unsigned long *shift)
-{
-	u64 szcode = cookie >> COOKIE_PGSZ_CODE_SHIFT;
-
-	cookie &= ~COOKIE_PGSZ_CODE;
-
-	*shift = szcode * 3;
-
-	return (cookie >> (13ULL + (szcode * 3ULL)));
-}
 
 static struct ldc_mtable_entry *alloc_npages(struct ldc_iommu *iommu,
 					     unsigned long npages)
 {
 	long entry;
 
-	entry = arena_alloc(iommu, npages);
+	entry = iommu_tbl_range_alloc(NULL, &iommu->iommu_map_table,
+				      npages, NULL, (unsigned long)-1, 0);
 	if (unlikely(entry < 0))
 		return NULL;
 
@@ -2090,7 +2081,7 @@ int ldc_map_sg(struct ldc_channel *lp,
 	       struct ldc_trans_cookie *cookies, int ncookies,
 	       unsigned int map_perm)
 {
-	unsigned long i, npages, flags;
+	unsigned long i, npages;
 	struct ldc_mtable_entry *base;
 	struct cookie_state state;
 	struct ldc_iommu *iommu;
@@ -2109,9 +2100,7 @@ int ldc_map_sg(struct ldc_channel *lp,
 
 	iommu = &lp->iommu;
 
-	spin_lock_irqsave(&iommu->lock, flags);
 	base = alloc_npages(iommu, npages);
-	spin_unlock_irqrestore(&iommu->lock, flags);
 
 	if (!base)
 		return -ENOMEM;
@@ -2136,7 +2125,7 @@ int ldc_map_single(struct ldc_channel *lp,
 		   struct ldc_trans_cookie *cookies, int ncookies,
 		   unsigned int map_perm)
 {
-	unsigned long npages, pa, flags;
+	unsigned long npages, pa;
 	struct ldc_mtable_entry *base;
 	struct cookie_state state;
 	struct ldc_iommu *iommu;
@@ -2152,9 +2141,7 @@ int ldc_map_single(struct ldc_channel *lp,
 
 	iommu = &lp->iommu;
 
-	spin_lock_irqsave(&iommu->lock, flags);
 	base = alloc_npages(iommu, npages);
-	spin_unlock_irqrestore(&iommu->lock, flags);
 
 	if (!base)
 		return -ENOMEM;
@@ -2172,35 +2159,25 @@ int ldc_map_single(struct ldc_channel *lp,
 }
 EXPORT_SYMBOL(ldc_map_single);
 
+
 static void free_npages(unsigned long id, struct ldc_iommu *iommu,
 			u64 cookie, u64 size)
 {
-	struct iommu_arena *arena = &iommu->arena;
-	unsigned long i, shift, index, npages;
-	struct ldc_mtable_entry *base;
+	unsigned long npages, entry;
 
 	npages = PAGE_ALIGN(((cookie & ~PAGE_MASK) + size)) >> PAGE_SHIFT;
-	index = cookie_to_index(cookie, &shift);
-	base = iommu->page_table + index;
 
-	BUG_ON(index > arena->limit ||
-	       (index + npages) > arena->limit);
-
-	for (i = 0; i < npages; i++) {
-		if (base->cookie)
-			sun4v_ldc_revoke(id, cookie + (i << shift),
-					 base->cookie);
-		base->mte = 0;
-		__clear_bit(index + i, arena->map);
-	}
+	entry = ldc_cookie_to_index(cookie, iommu);
+	ldc_demap(iommu, id, cookie, entry, npages);
+	iommu_tbl_range_free(&iommu->iommu_map_table, cookie, npages, entry);
 }
 
 void ldc_unmap(struct ldc_channel *lp, struct ldc_trans_cookie *cookies,
 	       int ncookies)
 {
 	struct ldc_iommu *iommu = &lp->iommu;
-	unsigned long flags;
 	int i;
+	unsigned long flags;
 
 	spin_lock_irqsave(&iommu->lock, flags);
 	for (i = 0; i < ncookies; i++) {

include/linux/iommu-common.h

+#ifndef _LINUX_IOMMU_COMMON_H
+#define _LINUX_IOMMU_COMMON_H
+
+#include <linux/spinlock_types.h>
+#include <linux/device.h>
+#include <asm/page.h>
+
+#define IOMMU_POOL_HASHBITS     4
+#define IOMMU_NR_POOLS          (1 << IOMMU_POOL_HASHBITS)
+
+struct iommu_pool {
+	unsigned long	start;
+	unsigned long	end;
+	unsigned long	hint;
+	spinlock_t	lock;
+};
+
+struct iommu_map_table {
+	unsigned long		table_map_base;
+	unsigned long		table_shift;
+	unsigned long		nr_pools;
+	void			(*lazy_flush)(struct iommu_map_table *);
+	unsigned long		poolsize;
+	struct iommu_pool	pools[IOMMU_NR_POOLS];
+	u32			flags;
+#define	IOMMU_HAS_LARGE_POOL	0x00000001
+#define	IOMMU_NO_SPAN_BOUND	0x00000002
+#define	IOMMU_NEED_FLUSH	0x00000004
+	struct iommu_pool	large_pool;
+	unsigned long		*map;
+};
+
+extern void iommu_tbl_pool_init(struct iommu_map_table *iommu,
+				unsigned long num_entries,
+				u32 table_shift,
+				void (*lazy_flush)(struct iommu_map_table *),
+				bool large_pool, u32 npools,
+				bool skip_span_boundary_check);
+
+extern unsigned long iommu_tbl_range_alloc(struct device *dev,
+					   struct iommu_map_table *iommu,
+					   unsigned long npages,
+					   unsigned long *handle,
+					   unsigned long mask,
+					   unsigned int align_order);
+
+extern void iommu_tbl_range_free(struct iommu_map_table *iommu,
+				 u64 dma_addr, unsigned long npages,
+				 unsigned long entry);
+
+#endif

lib/Makefile

@@ -106,7 +106,7 @@ obj-$(CONFIG_AUDIT_GENERIC) += audit.o
 obj-$(CONFIG_AUDIT_COMPAT_GENERIC) += compat_audit.o
 
 obj-$(CONFIG_SWIOTLB) += swiotlb.o
-obj-$(CONFIG_IOMMU_HELPER) += iommu-helper.o
+obj-$(CONFIG_IOMMU_HELPER) += iommu-helper.o iommu-common.o
 obj-$(CONFIG_FAULT_INJECTION) += fault-inject.o
 obj-$(CONFIG_NOTIFIER_ERROR_INJECTION) += notifier-error-inject.o
 obj-$(CONFIG_CPU_NOTIFIER_ERROR_INJECT) += cpu-notifier-error-inject.o

lib/iommu-common.c

+/*
+ * IOMMU mmap management and range allocation functions.
+ * Based almost entirely upon the powerpc iommu allocator.
+ */
+
+#include <linux/export.h>
+#include <linux/bitmap.h>
+#include <linux/bug.h>
+#include <linux/iommu-helper.h>
+#include <linux/iommu-common.h>
+#include <linux/dma-mapping.h>
+#include <linux/hash.h>
+
+#ifndef	DMA_ERROR_CODE
+#define	DMA_ERROR_CODE (~(dma_addr_t)0x0)
+#endif
+
+unsigned long iommu_large_alloc = 15;
+
+static	DEFINE_PER_CPU(unsigned int, iommu_pool_hash);
+
+static inline bool need_flush(struct iommu_map_table *iommu)
+{
+	return (iommu->lazy_flush != NULL &&
+		(iommu->flags & IOMMU_NEED_FLUSH) != 0);
+}
+
+static inline void set_flush(struct iommu_map_table *iommu)
+{
+	iommu->flags |= IOMMU_NEED_FLUSH;
+}
+
+static inline void clear_flush(struct iommu_map_table *iommu)
+{
+	iommu->flags &= ~IOMMU_NEED_FLUSH;
+}
+
+static void setup_iommu_pool_hash(void)
+{
+	unsigned int i;
+	static bool do_once;
+
+	if (do_once)
+		return;
+	do_once = true;
+	for_each_possible_cpu(i)
+		per_cpu(iommu_pool_hash, i) = hash_32(i, IOMMU_POOL_HASHBITS);
+}
+
+/*
+ * Initialize iommu_pool entries for the iommu_map_table. `num_entries'
+ * is the number of table entries. If `large_pool' is set to true,
+ * the top 1/4 of the table will be set aside for pool allocations
+ * of more than iommu_large_alloc pages.
+ */
+extern void iommu_tbl_pool_init(struct iommu_map_table *iommu,
+				unsigned long num_entries,
+				u32 table_shift,
+				void (*lazy_flush)(struct iommu_map_table *),
+				bool large_pool, u32 npools,
+				bool skip_span_boundary_check)
+{
+	unsigned int start, i;
+	struct iommu_pool *p = &(iommu->large_pool);
+
+	setup_iommu_pool_hash();
+	if (npools == 0)
+		iommu->nr_pools = IOMMU_NR_POOLS;
+	else
+		iommu->nr_pools = npools;
+	BUG_ON(npools > IOMMU_NR_POOLS);
+
+	iommu->table_shift = table_shift;
+	iommu->lazy_flush = lazy_flush;
+	start = 0;
+	if (skip_span_boundary_check)
+		iommu->flags |= IOMMU_NO_SPAN_BOUND;
+	if (large_pool)
+		iommu->flags |= IOMMU_HAS_LARGE_POOL;
+
+	if (!large_pool)
+		iommu->poolsize = num_entries/iommu->nr_pools;
+	else
+		iommu->poolsize = (num_entries * 3 / 4)/iommu->nr_pools;
+	for (i = 0; i < iommu->nr_pools; i++) {
+		spin_lock_init(&(iommu->pools[i].lock));
+		iommu->pools[i].start = start;
+		iommu->pools[i].hint = start;
+		start += iommu->poolsize; /* start for next pool */
+		iommu->pools[i].end = start - 1;
+	}
+	if (!large_pool)
+		return;
+	/* initialize large_pool */
+	spin_lock_init(&(p->lock));
+	p->start = start;
+	p->hint = p->start;
+	p->end = num_entries;
+}
+EXPORT_SYMBOL(iommu_tbl_pool_init);
+
+unsigned long iommu_tbl_range_alloc(struct device *dev,
+				struct iommu_map_table *iommu,
+				unsigned long npages,
+				unsigned long *handle,
+				unsigned long mask,
+				unsigned int align_order)
+{
+	unsigned int pool_hash = __this_cpu_read(iommu_pool_hash);
+	unsigned long n, end, start, limit, boundary_size;
+	struct iommu_pool *pool;
+	int pass = 0;
+	unsigned int pool_nr;
+	unsigned int npools = iommu->nr_pools;
+	unsigned long flags;
+	bool large_pool = ((iommu->flags & IOMMU_HAS_LARGE_POOL) != 0);
+	bool largealloc = (large_pool && npages > iommu_large_alloc);
+	unsigned long shift;
+	unsigned long align_mask = 0;
+
+	if (align_order > 0)
+		align_mask = 0xffffffffffffffffl >> (64 - align_order);
+
+	/* Sanity check */
+	if (unlikely(npages == 0)) {
+		WARN_ON_ONCE(1);
+		return DMA_ERROR_CODE;
+	}
+
+	if (largealloc) {
+		pool = &(iommu->large_pool);
+		pool_nr = 0; /* to keep compiler happy */
+	} else {
+		/* pick out pool_nr */
+		pool_nr =  pool_hash & (npools - 1);
+		pool = &(iommu->pools[pool_nr]);
+	}
+	spin_lock_irqsave(&pool->lock, flags);
+
+ again:
+	if (pass == 0 && handle && *handle &&
+	    (*handle >= pool->start) && (*handle < pool->end))
+		start = *handle;
+	else
+		start = pool->hint;
+
+	limit = pool->end;
+
+	/* The case below can happen if we have a small segment appended
+	 * to a large, or when the previous alloc was at the very end of
+	 * the available space. If so, go back to the beginning. If a
+	 * flush is needed, it will get done based on the return value
+	 * from iommu_area_alloc() below.
+	 */
+	if (start >= limit)
+		start = pool->start;
+	shift = iommu->table_map_base >> iommu->table_shift;
+	if (limit + shift > mask) {
+		limit = mask - shift + 1;
+		/* If we're constrained on address range, first try
+		 * at the masked hint to avoid O(n) search complexity,
+		 * but on second pass, start at 0 in pool 0.
+		 */
+		if ((start & mask) >= limit || pass > 0) {
+			spin_unlock(&(pool->lock));
+			pool = &(iommu->pools[0]);
+			spin_lock(&(pool->lock));
+			start = pool->start;
+		} else {
+			start &= mask;
+		}
+	}
+
+	if (dev)
+		boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
+				      1 << iommu->table_shift);
+	else
+		boundary_size = ALIGN(1ULL << 32, 1 << iommu->table_shift);
+
+	boundary_size = boundary_size >> iommu->table_shift;
+	/*
+	 * if the skip_span_boundary_check had been set during init, we set
+	 * things up so that iommu_is_span_boundary() merely checks if the
+	 * (index + npages) < num_tsb_entries
+	 */
+	if ((iommu->flags & IOMMU_NO_SPAN_BOUND) != 0) {
+		shift = 0;
+		boundary_size = iommu->poolsize * iommu->nr_pools;
+	}
+	n = iommu_area_alloc(iommu->map, limit, start, npages, shift,
+			     boundary_size, align_mask);
+	if (n == -1) {
+		if (likely(pass == 0)) {
+			/* First failure, rescan from the beginning.  */
+			pool->hint = pool->start;
+			set_flush(iommu);
+			pass++;
+			goto again;
+		} else if (!largealloc && pass <= iommu->nr_pools) {
+			spin_unlock(&(pool->lock));
+			pool_nr = (pool_nr + 1) & (iommu->nr_pools - 1);
+			pool = &(iommu->pools[pool_nr]);
+			spin_lock(&(pool->lock));
+			pool->hint = pool->start;
+			set_flush(iommu);
+			pass++;
+			goto again;
+		} else {
+			/* give up */
+			n = DMA_ERROR_CODE;
+			goto bail;
+		}
+	}
+	if (n < pool->hint || need_flush(iommu)) {
+		clear_flush(iommu);
+		iommu->lazy_flush(iommu);
+	}
+
+	end = n + npages;
+	pool->hint = end;
+
+	/* Update handle for SG allocations */
+	if (handle)
+		*handle = end;
+bail:
+	spin_unlock_irqrestore(&(pool->lock), flags);
+
+	return n;
+}
+EXPORT_SYMBOL(iommu_tbl_range_alloc);
+
+static struct iommu_pool *get_pool(struct iommu_map_table *tbl,
+				   unsigned long entry)
+{
+	struct iommu_pool *p;
+	unsigned long largepool_start = tbl->large_pool.start;
+	bool large_pool = ((tbl->flags & IOMMU_HAS_LARGE_POOL) != 0);
+
+	/* The large pool is the last pool at the top of the table */
+	if (large_pool && entry >= largepool_start) {
+		p = &tbl->large_pool;
+	} else {
+		unsigned int pool_nr = entry / tbl->poolsize;
+
+		BUG_ON(pool_nr >= tbl->nr_pools);
+		p = &tbl->pools[pool_nr];
+	}
+	return p;
+}
+
+/* Caller supplies the index of the entry into the iommu map table
+ * itself when the mapping from dma_addr to the entry is not the
+ * default addr->entry mapping below.
+ */
+void iommu_tbl_range_free(struct iommu_map_table *iommu, u64 dma_addr,
+			  unsigned long npages, unsigned long entry)
+{
+	struct iommu_pool *pool;
+	unsigned long flags;
+	unsigned long shift = iommu->table_shift;
+
+	if (entry == DMA_ERROR_CODE) /* use default addr->entry mapping */
+		entry = (dma_addr - iommu->table_map_base) >> shift;
+	pool = get_pool(iommu, entry);
+
+	spin_lock_irqsave(&(pool->lock), flags);
+	bitmap_clear(iommu->map, entry, npages);
+	spin_unlock_irqrestore(&(pool->lock), flags);
+}
+EXPORT_SYMBOL(iommu_tbl_range_free);