1 files changed, 124 insertions, 35 deletions

diff --git a/block/blk-settings.c b/block/blk-settings.c
index a000daafbfb4..07874e9b609f 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -14,6 +14,8 @@
 #include <linux/jiffies.h>
 #include <linux/gfp.h>
 #include <linux/dma-mapping.h>
+#include <linux/t10-pi.h>
+#include <linux/crc64.h>
 
 #include "blk.h"
 #include "blk-rq-qos.h"
@@ -50,6 +52,8 @@ void blk_set_stacking_limits(struct queue_limits *lim)
 	lim->max_sectors = UINT_MAX;
 	lim->max_dev_sectors = UINT_MAX;
 	lim->max_write_zeroes_sectors = UINT_MAX;
+	lim->max_hw_wzeroes_unmap_sectors = UINT_MAX;
+	lim->max_user_wzeroes_unmap_sectors = UINT_MAX;
 	lim->max_hw_zone_append_sectors = UINT_MAX;
 	lim->max_user_discard_sectors = UINT_MAX;
 }
@@ -58,16 +62,24 @@ EXPORT_SYMBOL(blk_set_stacking_limits);
 void blk_apply_bdi_limits(struct backing_dev_info *bdi,
 		struct queue_limits *lim)
 {
+	u64 io_opt = lim->io_opt;
+
 	/*
 	 * For read-ahead of large files to be effective, we need to read ahead
-	 * at least twice the optimal I/O size.
+	 * at least twice the optimal I/O size. For rotational devices that do
+	 * not report an optimal I/O size (e.g. ATA HDDs), use the maximum I/O
+	 * size to avoid falling back to the (rather inefficient) small default
+	 * read-ahead size.
 	 *
 	 * There is no hardware limitation for the read-ahead size and the user
 	 * might have increased the read-ahead size through sysfs, so don't ever
 	 * decrease it.
 	 */
+	if (!io_opt && (lim->features & BLK_FEAT_ROTATIONAL))
+		io_opt = (u64)lim->max_sectors << SECTOR_SHIFT;
+
 	bdi->ra_pages = max3(bdi->ra_pages,
-				lim->io_opt * 2 / PAGE_SIZE,
+				io_opt * 2 >> PAGE_SHIFT,
 				VM_READAHEAD_PAGES);
 	bdi->io_pages = lim->max_sectors >> PAGE_SECTORS_SHIFT;
 }
@@ -114,7 +126,7 @@ static int blk_validate_integrity_limits(struct queue_limits *lim)
 {
 	struct blk_integrity *bi = &lim->integrity;
 
-	if (!bi->tuple_size) {
+	if (!bi->metadata_size) {
 		if (bi->csum_type != BLK_INTEGRITY_CSUM_NONE ||
 		    bi->tag_size || ((bi->flags & BLK_INTEGRITY_REF_TAG))) {
 			pr_warn("invalid PI settings.\n");
@@ -135,6 +147,42 @@ static int blk_validate_integrity_limits(struct queue_limits *lim)
 		return -EINVAL;
 	}
 
+	if (bi->pi_tuple_size > bi->metadata_size) {
+		pr_warn("pi_tuple_size (%u) exceeds metadata_size (%u)\n",
+			 bi->pi_tuple_size,
+			 bi->metadata_size);
+		return -EINVAL;
+	}
+
+	switch (bi->csum_type) {
+	case BLK_INTEGRITY_CSUM_NONE:
+		if (bi->pi_tuple_size) {
+			pr_warn("pi_tuple_size must be 0 when checksum type \
+				 is none\n");
+			return -EINVAL;
+		}
+		break;
+	case BLK_INTEGRITY_CSUM_CRC:
+	case BLK_INTEGRITY_CSUM_IP:
+		if (bi->pi_tuple_size != sizeof(struct t10_pi_tuple)) {
+			pr_warn("pi_tuple_size mismatch for T10 PI: expected \
+				 %zu, got %u\n",
+				 sizeof(struct t10_pi_tuple),
+				 bi->pi_tuple_size);
+			return -EINVAL;
+		}
+		break;
+	case BLK_INTEGRITY_CSUM_CRC64:
+		if (bi->pi_tuple_size != sizeof(struct crc64_pi_tuple)) {
+			pr_warn("pi_tuple_size mismatch for CRC64 PI: \
+				 expected %zu, got %u\n",
+				 sizeof(struct crc64_pi_tuple),
+				 bi->pi_tuple_size);
+			return -EINVAL;
+		}
+		break;
+	}
+
 	if (!bi->interval_exp)
 		bi->interval_exp = ilog2(lim->logical_block_size);
 
@@ -181,6 +229,8 @@ static void blk_atomic_writes_update_limits(struct queue_limits *lim)
 static void blk_validate_atomic_write_limits(struct queue_limits *lim)
 {
 	unsigned int boundary_sectors;
+	unsigned int atomic_write_hw_max_sectors =
+			lim->atomic_write_hw_max >> SECTOR_SHIFT;
 
 	if (!(lim->features & BLK_FEAT_ATOMIC_WRITES))
 		goto unsupported;
@@ -202,6 +252,10 @@ static void blk_validate_atomic_write_limits(struct queue_limits *lim)
 			 lim->atomic_write_hw_max))
 		goto unsupported;
 
+	if (WARN_ON_ONCE(lim->chunk_sectors &&
+			atomic_write_hw_max_sectors > lim->chunk_sectors))
+		goto unsupported;
+
 	boundary_sectors = lim->atomic_write_hw_boundary >> SECTOR_SHIFT;
 
 	if (boundary_sectors) {
@@ -266,8 +320,12 @@ int blk_validate_limits(struct queue_limits *lim)
 		pr_warn("Invalid logical block size (%d)\n", lim->logical_block_size);
 		return -EINVAL;
 	}
-	if (lim->physical_block_size < lim->logical_block_size)
+	if (lim->physical_block_size < lim->logical_block_size) {
 		lim->physical_block_size = lim->logical_block_size;
+	} else if (!is_power_of_2(lim->physical_block_size)) {
+		pr_warn("Invalid physical block size (%d)\n", lim->physical_block_size);
+		return -EINVAL;
+	}
 
 	/*
 	 * The minimum I/O size defaults to the physical block size unless
@@ -333,15 +391,28 @@ int blk_validate_limits(struct queue_limits *lim)
 	if (!lim->max_segments)
 		lim->max_segments = BLK_MAX_SEGMENTS;
 
+	if (lim->max_hw_wzeroes_unmap_sectors &&
+	    lim->max_hw_wzeroes_unmap_sectors != lim->max_write_zeroes_sectors)
+		return -EINVAL;
+	lim->max_wzeroes_unmap_sectors = min(lim->max_hw_wzeroes_unmap_sectors,
+			lim->max_user_wzeroes_unmap_sectors);
+
 	lim->max_discard_sectors =
 		min(lim->max_hw_discard_sectors, lim->max_user_discard_sectors);
 
+	/*
+	 * When discard is not supported, discard_granularity should be reported
+	 * as 0 to userspace.
+	 */
+	if (lim->max_discard_sectors)
+		lim->discard_granularity =
+			max(lim->discard_granularity, lim->physical_block_size);
+	else
+		lim->discard_granularity = 0;
+
 	if (!lim->max_discard_segments)
 		lim->max_discard_segments = 1;
 
-	if (lim->discard_granularity < lim->physical_block_size)
-		lim->discard_granularity = lim->physical_block_size;
-
 	/*
 	 * By default there is no limit on the segment boundary alignment,
 	 * but if there is one it can't be smaller than the page size as
@@ -418,10 +489,11 @@ int blk_set_default_limits(struct queue_limits *lim)
 {
 	/*
 	 * Most defaults are set by capping the bounds in blk_validate_limits,
-	 * but max_user_discard_sectors is special and needs an explicit
-	 * initialization to the max value here.
+	 * but these limits are special and need an explicit initialization to
+	 * the max value here.
 	 */
 	lim->max_user_discard_sectors = UINT_MAX;
+	lim->max_user_wzeroes_unmap_sectors = UINT_MAX;
 	return blk_validate_limits(lim);
 }
 
@@ -589,41 +661,50 @@ static bool blk_stack_atomic_writes_boundary_head(struct queue_limits *t,
 	return true;
 }
 
-
-/* Check stacking of first bottom device */
-static bool blk_stack_atomic_writes_head(struct queue_limits *t,
-				struct queue_limits *b)
+static void blk_stack_atomic_writes_chunk_sectors(struct queue_limits *t)
 {
-	if (b->atomic_write_hw_boundary &&
-	    !blk_stack_atomic_writes_boundary_head(t, b))
-		return false;
+	unsigned int chunk_bytes;
 
-	if (t->io_min <= SECTOR_SIZE) {
-		/* No chunk sectors, so use bottom device values directly */
-		t->atomic_write_hw_unit_max = b->atomic_write_hw_unit_max;
-		t->atomic_write_hw_unit_min = b->atomic_write_hw_unit_min;
-		t->atomic_write_hw_max = b->atomic_write_hw_max;
-		return true;
-	}
+	if (!t->chunk_sectors)
+		return;
+
+	/*
+	 * If chunk sectors is so large that its value in bytes overflows
+	 * UINT_MAX, then just shift it down so it definitely will fit.
+	 * We don't support atomic writes of such a large size anyway.
+	 */
+	if (check_shl_overflow(t->chunk_sectors, SECTOR_SHIFT, &chunk_bytes))
+		chunk_bytes = t->chunk_sectors;
 
 	/*
 	 * Find values for limits which work for chunk size.
 	 * b->atomic_write_hw_unit_{min, max} may not be aligned with chunk
-	 * size (t->io_min), as chunk size is not restricted to a power-of-2.
+	 * size, as the chunk size is not restricted to a power-of-2.
 	 * So we need to find highest power-of-2 which works for the chunk
 	 * size.
-	 * As an example scenario, we could have b->unit_max = 16K and
-	 * t->io_min = 24K. For this case, reduce t->unit_max to a value
-	 * aligned with both limits, i.e. 8K in this example.
+	 * As an example scenario, we could have t->unit_max = 16K and
+	 * t->chunk_sectors = 24KB. For this case, reduce t->unit_max to a
+	 * value aligned with both limits, i.e. 8K in this example.
 	 */
-	t->atomic_write_hw_unit_max = b->atomic_write_hw_unit_max;
-	while (t->io_min % t->atomic_write_hw_unit_max)
-		t->atomic_write_hw_unit_max /= 2;
+	t->atomic_write_hw_unit_max = min(t->atomic_write_hw_unit_max,
+					max_pow_of_two_factor(chunk_bytes));
 
-	t->atomic_write_hw_unit_min = min(b->atomic_write_hw_unit_min,
+	t->atomic_write_hw_unit_min = min(t->atomic_write_hw_unit_min,
 					  t->atomic_write_hw_unit_max);
-	t->atomic_write_hw_max = min(b->atomic_write_hw_max, t->io_min);
+	t->atomic_write_hw_max = min(t->atomic_write_hw_max, chunk_bytes);
+}
+
+/* Check stacking of first bottom device */
+static bool blk_stack_atomic_writes_head(struct queue_limits *t,
+				struct queue_limits *b)
+{
+	if (b->atomic_write_hw_boundary &&
+	    !blk_stack_atomic_writes_boundary_head(t, b))
+		return false;
 
+	t->atomic_write_hw_unit_max = b->atomic_write_hw_unit_max;
+	t->atomic_write_hw_unit_min = b->atomic_write_hw_unit_min;
+	t->atomic_write_hw_max = b->atomic_write_hw_max;
 	return true;
 }
 
@@ -651,6 +732,7 @@ static void blk_stack_atomic_writes_limits(struct queue_limits *t,
 
 	if (!blk_stack_atomic_writes_head(t, b))
 		goto unsupported;
+	blk_stack_atomic_writes_chunk_sectors(t);
 	return;
 
 unsupported:
@@ -708,6 +790,13 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 	t->max_dev_sectors = min_not_zero(t->max_dev_sectors, b->max_dev_sectors);
 	t->max_write_zeroes_sectors = min(t->max_write_zeroes_sectors,
 					b->max_write_zeroes_sectors);
+	t->max_user_wzeroes_unmap_sectors =
+			min(t->max_user_wzeroes_unmap_sectors,
+			    b->max_user_wzeroes_unmap_sectors);
+	t->max_hw_wzeroes_unmap_sectors =
+			min(t->max_hw_wzeroes_unmap_sectors,
+			    b->max_hw_wzeroes_unmap_sectors);
+
 	t->max_hw_zone_append_sectors = min(t->max_hw_zone_append_sectors,
 					b->max_hw_zone_append_sectors);
 
@@ -779,7 +868,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 	}
 
 	/* chunk_sectors a multiple of the physical block size? */
-	if ((t->chunk_sectors << 9) & (t->physical_block_size - 1)) {
+	if (t->chunk_sectors % (t->physical_block_size >> SECTOR_SHIFT)) {
 		t->chunk_sectors = 0;
 		t->flags |= BLK_FLAG_MISALIGNED;
 		ret = -1;
@@ -875,7 +964,7 @@ bool queue_limits_stack_integrity(struct queue_limits *t,
 		return true;
 
 	if (ti->flags & BLK_INTEGRITY_STACKED) {
-		if (ti->tuple_size != bi->tuple_size)
+		if (ti->metadata_size != bi->metadata_size)
 			goto incompatible;
 		if (ti->interval_exp != bi->interval_exp)
 			goto incompatible;
@@ -891,7 +980,7 @@ bool queue_limits_stack_integrity(struct queue_limits *t,
 		ti->flags |= (bi->flags & BLK_INTEGRITY_DEVICE_CAPABLE) |
 			     (bi->flags & BLK_INTEGRITY_REF_TAG);
 		ti->csum_type = bi->csum_type;
-		ti->tuple_size = bi->tuple_size;
+		ti->metadata_size = bi->metadata_size;
 		ti->pi_offset = bi->pi_offset;
 		ti->interval_exp = bi->interval_exp;
 		ti->tag_size = bi->tag_size;