Merging upstream version 6.9.7.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

3 files changed, 133 insertions, 54 deletions

diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index f005c66f37..055da410ac 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -37,12 +37,6 @@
 
 #define pr_fmt(fmt) "cma: " fmt
 
-#ifdef CONFIG_CMA_DEBUG
-#ifndef DEBUG
-#  define DEBUG
-#endif
-#endif
-
 #include <asm/page.h>
 
 #include <linux/memblock.h>
diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c
index 02205ab53b..f7f3d14fa6 100644
--- a/kernel/dma/map_benchmark.c
+++ b/kernel/dma/map_benchmark.c
@@ -101,7 +101,6 @@ static int do_map_benchmark(struct map_benchmark_data *map)
 	struct task_struct **tsk;
 	int threads = map->bparam.threads;
 	int node = map->bparam.node;
-	const cpumask_t *cpu_mask = cpumask_of_node(node);
 	u64 loops;
 	int ret = 0;
 	int i;
@@ -118,11 +117,13 @@ static int do_map_benchmark(struct map_benchmark_data *map)
 		if (IS_ERR(tsk[i])) {
 			pr_err("create dma_map thread failed\n");
 			ret = PTR_ERR(tsk[i]);
+			while (--i >= 0)
+				kthread_stop(tsk[i]);
 			goto out;
 		}
 
 		if (node != NUMA_NO_NODE)
-			kthread_bind_mask(tsk[i], cpu_mask);
+			kthread_bind_mask(tsk[i], cpumask_of_node(node));
 	}
 
 	/* clear the old value in the previous benchmark */
@@ -139,13 +140,17 @@ static int do_map_benchmark(struct map_benchmark_data *map)
 
 	msleep_interruptible(map->bparam.seconds * 1000);
 
-	/* wait for the completion of benchmark threads */
+	/* wait for the completion of all started benchmark threads */
 	for (i = 0; i < threads; i++) {
-		ret = kthread_stop(tsk[i]);
-		if (ret)
-			goto out;
+		int kthread_ret = kthread_stop_put(tsk[i]);
+
+		if (kthread_ret)
+			ret = kthread_ret;
 	}
 
+	if (ret)
+		goto out;
+
 	loops = atomic64_read(&map->loops);
 	if (likely(loops > 0)) {
 		u64 map_variance, unmap_variance;
@@ -170,8 +175,6 @@ static int do_map_benchmark(struct map_benchmark_data *map)
 	}
 
 out:
-	for (i = 0; i < threads; i++)
-		put_task_struct(tsk[i]);
 	put_device(map->dev);
 	kfree(tsk);
 	return ret;
@@ -208,7 +211,8 @@ static long map_benchmark_ioctl(struct file *file, unsigned int cmd,
 		}
 
 		if (map->bparam.node != NUMA_NO_NODE &&
-		    !node_possible(map->bparam.node)) {
+		    (map->bparam.node < 0 || map->bparam.node >= MAX_NUMNODES ||
+		     !node_possible(map->bparam.node))) {
 			pr_err("invalid numa node\n");
 			return -EINVAL;
 		}
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 1955b42f42..0de66f0ff4 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -69,11 +69,14 @@
  * @alloc_size:	Size of the allocated buffer.
  * @list:	The free list describing the number of free entries available
  *		from each index.
+ * @pad_slots:	Number of preceding padding slots. Valid only in the first
+ *		allocated non-padding slot.
  */
 struct io_tlb_slot {
 	phys_addr_t orig_addr;
 	size_t alloc_size;
-	unsigned int list;
+	unsigned short list;
+	unsigned short pad_slots;
 };
 
 static bool swiotlb_force_bounce;
@@ -287,6 +290,7 @@ static void swiotlb_init_io_tlb_pool(struct io_tlb_pool *mem, phys_addr_t start,
 					 mem->nslabs - i);
 		mem->slots[i].orig_addr = INVALID_PHYS_ADDR;
 		mem->slots[i].alloc_size = 0;
+		mem->slots[i].pad_slots = 0;
 	}
 
 	memset(vaddr, 0, bytes);
@@ -821,12 +825,30 @@ void swiotlb_dev_init(struct device *dev)
 #endif
 }
 
-/*
- * Return the offset into a iotlb slot required to keep the device happy.
+/**
+ * swiotlb_align_offset() - Get required offset into an IO TLB allocation.
+ * @dev:         Owning device.
+ * @align_mask:  Allocation alignment mask.
+ * @addr:        DMA address.
+ *
+ * Return the minimum offset from the start of an IO TLB allocation which is
+ * required for a given buffer address and allocation alignment to keep the
+ * device happy.
+ *
+ * First, the address bits covered by min_align_mask must be identical in the
+ * original address and the bounce buffer address. High bits are preserved by
+ * choosing a suitable IO TLB slot, but bits below IO_TLB_SHIFT require extra
+ * padding bytes before the bounce buffer.
+ *
+ * Second, @align_mask specifies which bits of the first allocated slot must
+ * be zero. This may require allocating additional padding slots, and then the
+ * offset (in bytes) from the first such padding slot is returned.
  */
-static unsigned int swiotlb_align_offset(struct device *dev, u64 addr)
+static unsigned int swiotlb_align_offset(struct device *dev,
+					 unsigned int align_mask, u64 addr)
 {
-	return addr & dma_get_min_align_mask(dev) & (IO_TLB_SIZE - 1);
+	return addr & dma_get_min_align_mask(dev) &
+		(align_mask | (IO_TLB_SIZE - 1));
 }
 
 /*
@@ -841,27 +863,23 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size
 	size_t alloc_size = mem->slots[index].alloc_size;
 	unsigned long pfn = PFN_DOWN(orig_addr);
 	unsigned char *vaddr = mem->vaddr + tlb_addr - mem->start;
-	unsigned int tlb_offset, orig_addr_offset;
+	int tlb_offset;
 
 	if (orig_addr == INVALID_PHYS_ADDR)
 		return;
 
-	tlb_offset = tlb_addr & (IO_TLB_SIZE - 1);
-	orig_addr_offset = swiotlb_align_offset(dev, orig_addr);
-	if (tlb_offset < orig_addr_offset) {
-		dev_WARN_ONCE(dev, 1,
-			"Access before mapping start detected. orig offset %u, requested offset %u.\n",
-			orig_addr_offset, tlb_offset);
-		return;
-	}
-
-	tlb_offset -= orig_addr_offset;
-	if (tlb_offset > alloc_size) {
-		dev_WARN_ONCE(dev, 1,
-			"Buffer overflow detected. Allocation size: %zu. Mapping size: %zu+%u.\n",
-			alloc_size, size, tlb_offset);
-		return;
-	}
+	/*
+	 * It's valid for tlb_offset to be negative. This can happen when the
+	 * "offset" returned by swiotlb_align_offset() is non-zero, and the
+	 * tlb_addr is pointing within the first "offset" bytes of the second
+	 * or subsequent slots of the allocated swiotlb area. While it's not
+	 * valid for tlb_addr to be pointing within the first "offset" bytes
+	 * of the first slot, there's no way to check for such an error since
+	 * this function can't distinguish the first slot from the second and
+	 * subsequent slots.
+	 */
+	tlb_offset = (tlb_addr & (IO_TLB_SIZE - 1)) -
+		     swiotlb_align_offset(dev, 0, orig_addr);
 
 	orig_addr += tlb_offset;
 	alloc_size -= tlb_offset;
@@ -956,6 +974,28 @@ static void dec_used(struct io_tlb_mem *mem, unsigned int nslots)
 }
 #endif /* CONFIG_DEBUG_FS */
 
+#ifdef CONFIG_SWIOTLB_DYNAMIC
+#ifdef CONFIG_DEBUG_FS
+static void inc_transient_used(struct io_tlb_mem *mem, unsigned int nslots)
+{
+	atomic_long_add(nslots, &mem->transient_nslabs);
+}
+
+static void dec_transient_used(struct io_tlb_mem *mem, unsigned int nslots)
+{
+	atomic_long_sub(nslots, &mem->transient_nslabs);
+}
+
+#else /* !CONFIG_DEBUG_FS */
+static void inc_transient_used(struct io_tlb_mem *mem, unsigned int nslots)
+{
+}
+static void dec_transient_used(struct io_tlb_mem *mem, unsigned int nslots)
+{
+}
+#endif /* CONFIG_DEBUG_FS */
+#endif /* CONFIG_SWIOTLB_DYNAMIC */
+
 /**
  * swiotlb_search_pool_area() - search one memory area in one pool
  * @dev:	Device which maps the buffer.
@@ -983,7 +1023,7 @@ static int swiotlb_search_pool_area(struct device *dev, struct io_tlb_pool *pool
 	unsigned long max_slots = get_max_slots(boundary_mask);
 	unsigned int iotlb_align_mask = dma_get_min_align_mask(dev);
 	unsigned int nslots = nr_slots(alloc_size), stride;
-	unsigned int offset = swiotlb_align_offset(dev, orig_addr);
+	unsigned int offset = swiotlb_align_offset(dev, 0, orig_addr);
 	unsigned int index, slots_checked, count = 0, i;
 	unsigned long flags;
 	unsigned int slot_base;
@@ -993,6 +1033,17 @@ static int swiotlb_search_pool_area(struct device *dev, struct io_tlb_pool *pool
 	BUG_ON(area_index >= pool->nareas);
 
 	/*
+	 * Historically, swiotlb allocations >= PAGE_SIZE were guaranteed to be
+	 * page-aligned in the absence of any other alignment requirements.
+	 * 'alloc_align_mask' was later introduced to specify the alignment
+	 * explicitly, however this is passed as zero for streaming mappings
+	 * and so we preserve the old behaviour there in case any drivers are
+	 * relying on it.
+	 */
+	if (!alloc_align_mask && !iotlb_align_mask && alloc_size >= PAGE_SIZE)
+		alloc_align_mask = PAGE_SIZE - 1;
+
+	/*
 	 * Ensure that the allocation is at least slot-aligned and update
 	 * 'iotlb_align_mask' to ignore bits that will be preserved when
 	 * offsetting into the allocation.
@@ -1006,13 +1057,6 @@ static int swiotlb_search_pool_area(struct device *dev, struct io_tlb_pool *pool
 	 */
 	stride = get_max_slots(max(alloc_align_mask, iotlb_align_mask));
 
-	/*
-	 * For allocations of PAGE_SIZE or larger only look for page aligned
-	 * allocations.
-	 */
-	if (alloc_size >= PAGE_SIZE)
-		stride = umax(stride, PAGE_SHIFT - IO_TLB_SHIFT + 1);
-
 	spin_lock_irqsave(&area->lock, flags);
 	if (unlikely(nslots > pool->area_nslabs - area->used))
 		goto not_found;
@@ -1179,6 +1223,7 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
 	spin_lock_irqsave(&dev->dma_io_tlb_lock, flags);
 	list_add_rcu(&pool->node, &dev->dma_io_tlb_pools);
 	spin_unlock_irqrestore(&dev->dma_io_tlb_lock, flags);
+	inc_transient_used(mem, pool->nslabs);
 
 found:
 	WRITE_ONCE(dev->dma_uses_io_tlb, true);
@@ -1301,11 +1346,12 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
 		unsigned long attrs)
 {
 	struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
-	unsigned int offset = swiotlb_align_offset(dev, orig_addr);
+	unsigned int offset;
 	struct io_tlb_pool *pool;
 	unsigned int i;
 	int index;
 	phys_addr_t tlb_addr;
+	unsigned short pad_slots;
 
 	if (!mem || !mem->nslabs) {
 		dev_warn_ratelimited(dev,
@@ -1322,6 +1368,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
 		return (phys_addr_t)DMA_MAPPING_ERROR;
 	}
 
+	offset = swiotlb_align_offset(dev, alloc_align_mask, orig_addr);
 	index = swiotlb_find_slots(dev, orig_addr,
 				   alloc_size + offset, alloc_align_mask, &pool);
 	if (index == -1) {
@@ -1337,6 +1384,10 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
 	 * This is needed when we sync the memory.  Then we sync the buffer if
 	 * needed.
 	 */
+	pad_slots = offset >> IO_TLB_SHIFT;
+	offset &= (IO_TLB_SIZE - 1);
+	index += pad_slots;
+	pool->slots[index].pad_slots = pad_slots;
 	for (i = 0; i < nr_slots(alloc_size + offset); i++)
 		pool->slots[index + i].orig_addr = slot_addr(orig_addr, i);
 	tlb_addr = slot_addr(pool->start, index) + offset;
@@ -1357,13 +1408,17 @@ static void swiotlb_release_slots(struct device *dev, phys_addr_t tlb_addr)
 {
 	struct io_tlb_pool *mem = swiotlb_find_pool(dev, tlb_addr);
 	unsigned long flags;
-	unsigned int offset = swiotlb_align_offset(dev, tlb_addr);
-	int index = (tlb_addr - offset - mem->start) >> IO_TLB_SHIFT;
-	int nslots = nr_slots(mem->slots[index].alloc_size + offset);
-	int aindex = index / mem->area_nslabs;
-	struct io_tlb_area *area = &mem->areas[aindex];
+	unsigned int offset = swiotlb_align_offset(dev, 0, tlb_addr);
+	int index, nslots, aindex;
+	struct io_tlb_area *area;
 	int count, i;
 
+	index = (tlb_addr - offset - mem->start) >> IO_TLB_SHIFT;
+	index -= mem->slots[index].pad_slots;
+	nslots = nr_slots(mem->slots[index].alloc_size + offset);
+	aindex = index / mem->area_nslabs;
+	area = &mem->areas[aindex];
+
 	/*
 	 * Return the buffer to the free list by setting the corresponding
 	 * entries to indicate the number of contiguous entries available.
@@ -1386,6 +1441,7 @@ static void swiotlb_release_slots(struct device *dev, phys_addr_t tlb_addr)
 		mem->slots[i].list = ++count;
 		mem->slots[i].orig_addr = INVALID_PHYS_ADDR;
 		mem->slots[i].alloc_size = 0;
+		mem->slots[i].pad_slots = 0;
 	}
 
 	/*
@@ -1424,6 +1480,7 @@ static bool swiotlb_del_transient(struct device *dev, phys_addr_t tlb_addr)
 
 	dec_used(dev->dma_io_tlb_mem, pool->nslabs);
 	swiotlb_del_pool(dev, pool);
+	dec_transient_used(dev->dma_io_tlb_mem, pool->nslabs);
 	return true;
 }
 
@@ -1566,6 +1623,23 @@ phys_addr_t default_swiotlb_limit(void)
 }
 
 #ifdef CONFIG_DEBUG_FS
+#ifdef CONFIG_SWIOTLB_DYNAMIC
+static unsigned long mem_transient_used(struct io_tlb_mem *mem)
+{
+	return atomic_long_read(&mem->transient_nslabs);
+}
+
+static int io_tlb_transient_used_get(void *data, u64 *val)
+{
+	struct io_tlb_mem *mem = data;
+
+	*val = mem_transient_used(mem);
+	return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(fops_io_tlb_transient_used, io_tlb_transient_used_get,
+			 NULL, "%llu\n");
+#endif /* CONFIG_SWIOTLB_DYNAMIC */
 
 static int io_tlb_used_get(void *data, u64 *val)
 {
@@ -1602,9 +1676,6 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_io_tlb_hiwater, io_tlb_hiwater_get,
 static void swiotlb_create_debugfs_files(struct io_tlb_mem *mem,
 					 const char *dirname)
 {
-	atomic_long_set(&mem->total_used, 0);
-	atomic_long_set(&mem->used_hiwater, 0);
-
 	mem->debugfs = debugfs_create_dir(dirname, io_tlb_default_mem.debugfs);
 	if (!mem->nslabs)
 		return;
@@ -1614,6 +1685,10 @@ static void swiotlb_create_debugfs_files(struct io_tlb_mem *mem,
 			&fops_io_tlb_used);
 	debugfs_create_file("io_tlb_used_hiwater", 0600, mem->debugfs, mem,
 			&fops_io_tlb_hiwater);
+#ifdef CONFIG_SWIOTLB_DYNAMIC
+	debugfs_create_file("io_tlb_transient_nslabs", 0400, mem->debugfs,
+			    mem, &fops_io_tlb_transient_used);
+#endif
 }
 
 static int __init swiotlb_create_default_debugfs(void)
@@ -1652,6 +1727,12 @@ struct page *swiotlb_alloc(struct device *dev, size_t size)
 		return NULL;
 
 	tlb_addr = slot_addr(pool->start, index);
+	if (unlikely(!PAGE_ALIGNED(tlb_addr))) {
+		dev_WARN_ONCE(dev, 1, "Cannot allocate pages from non page-aligned swiotlb addr 0x%pa.\n",
+			      &tlb_addr);
+		swiotlb_release_slots(dev, tlb_addr);
+		return NULL;
+	}
 
 	return pfn_to_page(PFN_DOWN(tlb_addr));
 }