From ee930fffee469d076998274a2ca55e13dc1efb67 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Fri, 10 May 2024 08:50:54 +0000
Subject: [PATCH] enable tun/tap/iptables
---
kernel/drivers/md/dm-table.c | 713 ++++++++++++++++++++++++++++++++++-------------------------
1 files changed, 413 insertions(+), 300 deletions(-)
diff --git a/kernel/drivers/md/dm-table.c b/kernel/drivers/md/dm-table.c
index 51d71b9..743bdb1 100644
--- a/kernel/drivers/md/dm-table.c
+++ b/kernel/drivers/md/dm-table.c
@@ -21,55 +21,12 @@
#include <linux/blk-mq.h>
#include <linux/mount.h>
#include <linux/dax.h>
-#include <linux/bio.h>
-#include <linux/keyslot-manager.h>
#define DM_MSG_PREFIX "table"
-#define MAX_DEPTH 16
#define NODE_SIZE L1_CACHE_BYTES
#define KEYS_PER_NODE (NODE_SIZE / sizeof(sector_t))
#define CHILDREN_PER_NODE (KEYS_PER_NODE + 1)
-
-struct dm_table {
- struct mapped_device *md;
- enum dm_queue_mode type;
-
- /* btree table */
- unsigned int depth;
- unsigned int counts[MAX_DEPTH]; /* in nodes */
- sector_t *index[MAX_DEPTH];
-
- unsigned int num_targets;
- unsigned int num_allocated;
- sector_t *highs;
- struct dm_target *targets;
-
- struct target_type *immutable_target_type;
-
- bool integrity_supported:1;
- bool singleton:1;
- bool all_blk_mq:1;
- unsigned integrity_added:1;
-
- /*
- * Indicates the rw permissions for the new logical
- * device. This should be a combination of FMODE_READ
- * and FMODE_WRITE.
- */
- fmode_t mode;
-
- /* a list of devices used by this table */
- struct list_head devices;
-
- /* events get handed up using this callback */
- void (*event_fn)(void *);
- void *event_context;
-
- struct dm_md_mempools *mempools;
-
- struct list_head target_callbacks;
-};
/*
* Similar to ceiling(log_size(n))
@@ -166,10 +123,8 @@
/*
* Allocate both the target array and offset array at once.
- * Append an empty entry to catch sectors beyond the end of
- * the device.
*/
- n_highs = (sector_t *) dm_vcalloc(num + 1, sizeof(struct dm_target) +
+ n_highs = (sector_t *) dm_vcalloc(num, sizeof(struct dm_target) +
sizeof(sector_t));
if (!n_highs)
return -ENOMEM;
@@ -195,7 +150,6 @@
return -ENOMEM;
INIT_LIST_HEAD(&t->devices);
- INIT_LIST_HEAD(&t->target_callbacks);
if (!num_targets)
num_targets = KEYS_PER_NODE;
@@ -233,6 +187,8 @@
}
}
+static void dm_table_destroy_keyslot_manager(struct dm_table *t);
+
void dm_table_destroy(struct dm_table *t)
{
unsigned int i;
@@ -261,6 +217,8 @@
dm_free_md_mempools(t->mempools);
+ dm_table_destroy_keyslot_manager(t);
+
kfree(t);
}
@@ -284,7 +242,6 @@
static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev,
sector_t start, sector_t len, void *data)
{
- struct request_queue *q;
struct queue_limits *limits = data;
struct block_device *bdev = dev->bdev;
sector_t dev_size =
@@ -292,22 +249,6 @@
unsigned short logical_block_size_sectors =
limits->logical_block_size >> SECTOR_SHIFT;
char b[BDEVNAME_SIZE];
-
- /*
- * Some devices exist without request functions,
- * such as loop devices not yet bound to backing files.
- * Forbid the use of such devices.
- */
- q = bdev_get_queue(bdev);
- if (!q || !q->make_request_fn) {
- DMWARN("%s: %s is not yet initialised: "
- "start=%llu, len=%llu, dev_size=%llu",
- dm_device_name(ti->table->md), bdevname(bdev, b),
- (unsigned long long)start,
- (unsigned long long)len,
- (unsigned long long)dev_size);
- return 1;
- }
if (!dev_size)
return 0;
@@ -383,7 +324,7 @@
* This upgrades the mode on an already open dm_dev, being
* careful to leave things as they were if we fail to reopen the
* device and not to touch the existing bdev field in case
- * it is accessed concurrently inside dm_table_any_congested().
+ * it is accessed concurrently.
*/
static int upgrade_mode(struct dm_dev_internal *dd, fmode_t new_mode,
struct mapped_device *md)
@@ -492,7 +433,8 @@
return 0;
}
- if (bdev_stack_limits(limits, bdev, start) < 0)
+ if (blk_stack_limits(limits, &q->limits,
+ get_start_sect(bdev) + start) < 0)
DMWARN("%s: adding target device %s caused an alignment inconsistency: "
"physical_block_size=%u, logical_block_size=%u, "
"alignment_offset=%u, start=%llu",
@@ -501,9 +443,6 @@
q->limits.logical_block_size,
q->limits.alignment_offset,
(unsigned long long) start << SECTOR_SHIFT);
-
- limits->zoned = blk_queue_zoned_model(q);
-
return 0;
}
@@ -673,7 +612,7 @@
*/
unsigned short remaining = 0;
- struct dm_target *uninitialized_var(ti);
+ struct dm_target *ti;
struct queue_limits ti_limits;
unsigned i;
@@ -796,16 +735,6 @@
goto bad;
}
-#ifdef CONFIG_ARCH_ROCKCHIP
- while (argv && (argc > 1) &&
- strncmp(argv[1], "PARTUUID=", 9) == 0 &&
- name_to_dev_t(argv[1]) == 0) {
- DMINFO("%s: %s: Waiting for device %s ...",
- dm_device_name(t->md), type, argv[1]);
- msleep(100);
- }
-#endif
-
r = tgt->type->ctr(tgt, argc, argv);
kfree(argv);
if (r)
@@ -887,14 +816,12 @@
static bool __table_type_bio_based(enum dm_queue_mode table_type)
{
return (table_type == DM_TYPE_BIO_BASED ||
- table_type == DM_TYPE_DAX_BIO_BASED ||
- table_type == DM_TYPE_NVME_BIO_BASED);
+ table_type == DM_TYPE_DAX_BIO_BASED);
}
static bool __table_type_request_based(enum dm_queue_mode table_type)
{
- return (table_type == DM_TYPE_REQUEST_BASED ||
- table_type == DM_TYPE_MQ_REQUEST_BASED);
+ return table_type == DM_TYPE_REQUEST_BASED;
}
void dm_table_set_type(struct dm_table *t, enum dm_queue_mode type)
@@ -903,13 +830,29 @@
}
EXPORT_SYMBOL_GPL(dm_table_set_type);
-static int device_not_dax_capable(struct dm_target *ti, struct dm_dev *dev,
- sector_t start, sector_t len, void *data)
+/* validate the dax capability of the target device span */
+int device_not_dax_capable(struct dm_target *ti, struct dm_dev *dev,
+ sector_t start, sector_t len, void *data)
{
- return !bdev_dax_supported(dev->bdev, PAGE_SIZE);
+ int blocksize = *(int *) data, id;
+ bool rc;
+
+ id = dax_read_lock();
+ rc = !dax_supported(dev->dax_dev, dev->bdev, blocksize, start, len);
+ dax_read_unlock(id);
+
+ return rc;
}
-static bool dm_table_supports_dax(struct dm_table *t)
+/* Check devices support synchronous DAX */
+static int device_not_dax_synchronous_capable(struct dm_target *ti, struct dm_dev *dev,
+ sector_t start, sector_t len, void *data)
+{
+ return !dev->dax_dev || !dax_synchronous(dev->dax_dev);
+}
+
+bool dm_table_supports_dax(struct dm_table *t,
+ iterate_devices_callout_fn iterate_fn, int *blocksize)
{
struct dm_target *ti;
unsigned i;
@@ -922,42 +865,34 @@
return false;
if (!ti->type->iterate_devices ||
- ti->type->iterate_devices(ti, device_not_dax_capable, NULL))
+ ti->type->iterate_devices(ti, iterate_fn, blocksize))
return false;
}
return true;
}
-static bool dm_table_does_not_support_partial_completion(struct dm_table *t);
-
-struct verify_rq_based_data {
- unsigned sq_count;
- unsigned mq_count;
-};
-
-static int device_is_rq_based(struct dm_target *ti, struct dm_dev *dev,
- sector_t start, sector_t len, void *data)
+static int device_is_rq_stackable(struct dm_target *ti, struct dm_dev *dev,
+ sector_t start, sector_t len, void *data)
{
- struct request_queue *q = bdev_get_queue(dev->bdev);
- struct verify_rq_based_data *v = data;
+ struct block_device *bdev = dev->bdev;
+ struct request_queue *q = bdev_get_queue(bdev);
- if (q->mq_ops)
- v->mq_count++;
- else
- v->sq_count++;
+ /* request-based cannot stack on partitions! */
+ if (bdev_is_partition(bdev))
+ return false;
- return queue_is_rq_based(q);
+ return queue_is_mq(q);
}
static int dm_table_determine_type(struct dm_table *t)
{
unsigned i;
unsigned bio_based = 0, request_based = 0, hybrid = 0;
- struct verify_rq_based_data v = {.sq_count = 0, .mq_count = 0};
struct dm_target *tgt;
struct list_head *devices = dm_table_get_devices(t);
enum dm_queue_mode live_md_type = dm_get_md_type(t->md);
+ int page_size = PAGE_SIZE;
if (t->type != DM_TYPE_NONE) {
/* target already set the table's type */
@@ -966,7 +901,6 @@
goto verify_bio_based;
}
BUG_ON(t->type == DM_TYPE_DAX_BIO_BASED);
- BUG_ON(t->type == DM_TYPE_NVME_BIO_BASED);
goto verify_rq_based;
}
@@ -1002,28 +936,15 @@
verify_bio_based:
/* We must use this table as bio-based */
t->type = DM_TYPE_BIO_BASED;
- if (dm_table_supports_dax(t) ||
+ if (dm_table_supports_dax(t, device_not_dax_capable, &page_size) ||
(list_empty(devices) && live_md_type == DM_TYPE_DAX_BIO_BASED)) {
t->type = DM_TYPE_DAX_BIO_BASED;
- } else {
- /* Check if upgrading to NVMe bio-based is valid or required */
- tgt = dm_table_get_immutable_target(t);
- if (tgt && !tgt->max_io_len && dm_table_does_not_support_partial_completion(t)) {
- t->type = DM_TYPE_NVME_BIO_BASED;
- goto verify_rq_based; /* must be stacked directly on NVMe (blk-mq) */
- } else if (list_empty(devices) && live_md_type == DM_TYPE_NVME_BIO_BASED) {
- t->type = DM_TYPE_NVME_BIO_BASED;
- }
}
return 0;
}
BUG_ON(!request_based); /* No targets in this table */
- /*
- * The only way to establish DM_TYPE_MQ_REQUEST_BASED is by
- * having a compatible target use dm_table_set_type.
- */
t->type = DM_TYPE_REQUEST_BASED;
verify_rq_based:
@@ -1034,8 +955,7 @@
* (e.g. request completion process for partial completion.)
*/
if (t->num_targets > 1) {
- DMERR("%s DM doesn't support multiple targets",
- t->type == DM_TYPE_NVME_BIO_BASED ? "nvme bio-based" : "request-based");
+ DMERR("request-based DM doesn't support multiple targets");
return -EINVAL;
}
@@ -1043,11 +963,9 @@
int srcu_idx;
struct dm_table *live_table = dm_get_live_table(t->md, &srcu_idx);
- /* inherit live table's type and all_blk_mq */
- if (live_table) {
+ /* inherit live table's type */
+ if (live_table)
t->type = live_table->type;
- t->all_blk_mq = live_table->all_blk_mq;
- }
dm_put_live_table(t->md, srcu_idx);
return 0;
}
@@ -1063,19 +981,8 @@
/* Non-request-stackable devices can't be used for request-based dm */
if (!tgt->type->iterate_devices ||
- !tgt->type->iterate_devices(tgt, device_is_rq_based, &v)) {
+ !tgt->type->iterate_devices(tgt, device_is_rq_stackable, NULL)) {
DMERR("table load rejected: including non-request-stackable devices");
- return -EINVAL;
- }
- if (v.sq_count && v.mq_count) {
- DMERR("table load rejected: not all devices are blk-mq request-stackable");
- return -EINVAL;
- }
- t->all_blk_mq = v.mq_count > 0;
-
- if (!t->all_blk_mq &&
- (t->type == DM_TYPE_MQ_REQUEST_BASED || t->type == DM_TYPE_NVME_BIO_BASED)) {
- DMERR("table load rejected: all devices are not blk-mq request-stackable");
return -EINVAL;
}
@@ -1124,11 +1031,6 @@
bool dm_table_request_based(struct dm_table *t)
{
return __table_type_request_based(dm_table_get_type(t));
-}
-
-bool dm_table_all_blk_mq_devices(struct dm_table *t)
-{
- return t->all_blk_mq;
}
static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *md)
@@ -1312,6 +1214,278 @@
return 0;
}
+#ifdef CONFIG_BLK_INLINE_ENCRYPTION
+
+struct dm_keyslot_manager {
+ struct blk_keyslot_manager ksm;
+ struct mapped_device *md;
+};
+
+static int dm_keyslot_evict_callback(struct dm_target *ti, struct dm_dev *dev,
+ sector_t start, sector_t len, void *data)
+{
+ const struct blk_crypto_key *key = data;
+
+ blk_crypto_evict_key(bdev_get_queue(dev->bdev), key);
+ return 0;
+}
+
+/*
+ * When an inline encryption key is evicted from a device-mapper device, evict
+ * it from all the underlying devices.
+ */
+static int dm_keyslot_evict(struct blk_keyslot_manager *ksm,
+ const struct blk_crypto_key *key, unsigned int slot)
+{
+ struct dm_keyslot_manager *dksm = container_of(ksm,
+ struct dm_keyslot_manager,
+ ksm);
+ struct mapped_device *md = dksm->md;
+ struct dm_table *t;
+ int srcu_idx;
+ int i;
+ struct dm_target *ti;
+
+ t = dm_get_live_table(md, &srcu_idx);
+ if (!t)
+ return 0;
+ for (i = 0; i < dm_table_get_num_targets(t); i++) {
+ ti = dm_table_get_target(t, i);
+ if (!ti->type->iterate_devices)
+ continue;
+ ti->type->iterate_devices(ti, dm_keyslot_evict_callback,
+ (void *)key);
+ }
+ dm_put_live_table(md, srcu_idx);
+ return 0;
+}
+
+struct dm_derive_raw_secret_args {
+ const u8 *wrapped_key;
+ unsigned int wrapped_key_size;
+ u8 *secret;
+ unsigned int secret_size;
+ int err;
+};
+
+static int dm_derive_raw_secret_callback(struct dm_target *ti,
+ struct dm_dev *dev, sector_t start,
+ sector_t len, void *data)
+{
+ struct dm_derive_raw_secret_args *args = data;
+ struct request_queue *q = bdev_get_queue(dev->bdev);
+
+ if (!args->err)
+ return 0;
+
+ if (!q->ksm) {
+ args->err = -EOPNOTSUPP;
+ return 0;
+ }
+
+ args->err = blk_ksm_derive_raw_secret(q->ksm, args->wrapped_key,
+ args->wrapped_key_size,
+ args->secret,
+ args->secret_size);
+ /* Try another device in case this fails. */
+ return 0;
+}
+
+/*
+ * Retrieve the raw_secret from the underlying device. Given that only one
+ * raw_secret can exist for a particular wrappedkey, retrieve it only from the
+ * first device that supports derive_raw_secret().
+ */
+static int dm_derive_raw_secret(struct blk_keyslot_manager *ksm,
+ const u8 *wrapped_key,
+ unsigned int wrapped_key_size,
+ u8 *secret, unsigned int secret_size)
+{
+ struct dm_keyslot_manager *dksm = container_of(ksm,
+ struct dm_keyslot_manager,
+ ksm);
+ struct mapped_device *md = dksm->md;
+ struct dm_derive_raw_secret_args args = {
+ .wrapped_key = wrapped_key,
+ .wrapped_key_size = wrapped_key_size,
+ .secret = secret,
+ .secret_size = secret_size,
+ .err = -EOPNOTSUPP,
+ };
+ struct dm_table *t;
+ int srcu_idx;
+ int i;
+ struct dm_target *ti;
+
+ t = dm_get_live_table(md, &srcu_idx);
+ if (!t)
+ return -EOPNOTSUPP;
+ for (i = 0; i < dm_table_get_num_targets(t); i++) {
+ ti = dm_table_get_target(t, i);
+ if (!ti->type->iterate_devices)
+ continue;
+ ti->type->iterate_devices(ti, dm_derive_raw_secret_callback,
+ &args);
+ if (!args.err)
+ break;
+ }
+ dm_put_live_table(md, srcu_idx);
+ return args.err;
+}
+
+
+static struct blk_ksm_ll_ops dm_ksm_ll_ops = {
+ .keyslot_evict = dm_keyslot_evict,
+ .derive_raw_secret = dm_derive_raw_secret,
+};
+
+static int device_intersect_crypto_modes(struct dm_target *ti,
+ struct dm_dev *dev, sector_t start,
+ sector_t len, void *data)
+{
+ struct blk_keyslot_manager *parent = data;
+ struct blk_keyslot_manager *child = bdev_get_queue(dev->bdev)->ksm;
+
+ blk_ksm_intersect_modes(parent, child);
+ return 0;
+}
+
+void dm_destroy_keyslot_manager(struct blk_keyslot_manager *ksm)
+{
+ struct dm_keyslot_manager *dksm = container_of(ksm,
+ struct dm_keyslot_manager,
+ ksm);
+
+ if (!ksm)
+ return;
+
+ blk_ksm_destroy(ksm);
+ kfree(dksm);
+}
+
+static void dm_table_destroy_keyslot_manager(struct dm_table *t)
+{
+ dm_destroy_keyslot_manager(t->ksm);
+ t->ksm = NULL;
+}
+
+/*
+ * Constructs and initializes t->ksm with a keyslot manager that
+ * represents the common set of crypto capabilities of the devices
+ * described by the dm_table. However, if the constructed keyslot
+ * manager does not support a superset of the crypto capabilities
+ * supported by the current keyslot manager of the mapped_device,
+ * it returns an error instead, since we don't support restricting
+ * crypto capabilities on table changes. Finally, if the constructed
+ * keyslot manager doesn't actually support any crypto modes at all,
+ * it just returns NULL.
+ */
+static int dm_table_construct_keyslot_manager(struct dm_table *t)
+{
+ struct dm_keyslot_manager *dksm;
+ struct blk_keyslot_manager *ksm;
+ struct dm_target *ti;
+ unsigned int i;
+ bool ksm_is_empty = true;
+
+ dksm = kmalloc(sizeof(*dksm), GFP_KERNEL);
+ if (!dksm)
+ return -ENOMEM;
+ dksm->md = t->md;
+
+ ksm = &dksm->ksm;
+ blk_ksm_init_passthrough(ksm);
+ ksm->ksm_ll_ops = dm_ksm_ll_ops;
+ ksm->max_dun_bytes_supported = UINT_MAX;
+ memset(ksm->crypto_modes_supported, 0xFF,
+ sizeof(ksm->crypto_modes_supported));
+ ksm->features = BLK_CRYPTO_FEATURE_STANDARD_KEYS |
+ BLK_CRYPTO_FEATURE_WRAPPED_KEYS;
+
+ for (i = 0; i < dm_table_get_num_targets(t); i++) {
+ ti = dm_table_get_target(t, i);
+
+ if (!dm_target_passes_crypto(ti->type)) {
+ blk_ksm_intersect_modes(ksm, NULL);
+ break;
+ }
+ if (!ti->type->iterate_devices)
+ continue;
+ ti->type->iterate_devices(ti, device_intersect_crypto_modes,
+ ksm);
+ }
+
+ if (t->md->queue && !blk_ksm_is_superset(ksm, t->md->queue->ksm)) {
+ DMWARN("Inline encryption capabilities of new DM table were more restrictive than the old table's. This is not supported!");
+ dm_destroy_keyslot_manager(ksm);
+ return -EINVAL;
+ }
+
+ /*
+ * If the new KSM doesn't actually support any crypto modes, we may as
+ * well represent it with a NULL ksm.
+ */
+ ksm_is_empty = true;
+ for (i = 0; i < ARRAY_SIZE(ksm->crypto_modes_supported); i++) {
+ if (ksm->crypto_modes_supported[i]) {
+ ksm_is_empty = false;
+ break;
+ }
+ }
+
+ if (ksm_is_empty) {
+ dm_destroy_keyslot_manager(ksm);
+ ksm = NULL;
+ }
+
+ /*
+ * t->ksm is only set temporarily while the table is being set
+ * up, and it gets set to NULL after the capabilities have
+ * been transferred to the request_queue.
+ */
+ t->ksm = ksm;
+
+ return 0;
+}
+
+static void dm_update_keyslot_manager(struct request_queue *q,
+ struct dm_table *t)
+{
+ if (!t->ksm)
+ return;
+
+ /* Make the ksm less restrictive */
+ if (!q->ksm) {
+ blk_ksm_register(t->ksm, q);
+ } else {
+ blk_ksm_update_capabilities(q->ksm, t->ksm);
+ dm_destroy_keyslot_manager(t->ksm);
+ }
+ t->ksm = NULL;
+}
+
+#else /* CONFIG_BLK_INLINE_ENCRYPTION */
+
+static int dm_table_construct_keyslot_manager(struct dm_table *t)
+{
+ return 0;
+}
+
+void dm_destroy_keyslot_manager(struct blk_keyslot_manager *ksm)
+{
+}
+
+static void dm_table_destroy_keyslot_manager(struct dm_table *t)
+{
+}
+
+static void dm_update_keyslot_manager(struct request_queue *q,
+ struct dm_table *t)
+{
+}
+
+#endif /* !CONFIG_BLK_INLINE_ENCRYPTION */
+
/*
* Prepares the table for use by building the indices,
* setting the type, and allocating mempools.
@@ -1335,6 +1509,12 @@
r = dm_table_register_integrity(t);
if (r) {
DMERR("could not register integrity profile.");
+ return r;
+ }
+
+ r = dm_table_construct_keyslot_manager(t);
+ if (r) {
+ DMERR("could not construct keyslot manager.");
return r;
}
@@ -1381,7 +1561,7 @@
/*
* Search the btree for the correct target.
*
- * Caller should check returned pointer with dm_target_is_valid()
+ * Caller should check returned pointer for NULL
* to trap I/O beyond end of device.
*/
struct dm_target *dm_table_find_target(struct dm_table *t, sector_t sector)
@@ -1390,7 +1570,7 @@
sector_t *node;
if (unlikely(sector >= dm_table_get_size(t)))
- return &t->targets[t->num_targets];
+ return NULL;
for (l = 0; l < t->depth; l++) {
n = get_child(n, k);
@@ -1489,6 +1669,13 @@
return !q || blk_queue_zoned_model(q) != *zoned_model;
}
+/*
+ * Check the device zoned model based on the target feature flag. If the target
+ * has the DM_TARGET_ZONED_HM feature flag set, host-managed zoned devices are
+ * also accepted but all devices must have the same zoned model. If the target
+ * has the DM_TARGET_MIXED_ZONED_MODEL feature set, the devices can have any
+ * zoned model with all zoned devices having the same zone size.
+ */
static bool dm_table_supports_zoned_model(struct dm_table *t,
enum blk_zoned_model zoned_model)
{
@@ -1498,13 +1685,15 @@
for (i = 0; i < dm_table_get_num_targets(t); i++) {
ti = dm_table_get_target(t, i);
- if (zoned_model == BLK_ZONED_HM &&
- !dm_target_supports_zoned_hm(ti->type))
- return false;
-
- if (!ti->type->iterate_devices ||
- ti->type->iterate_devices(ti, device_not_zoned_model, &zoned_model))
- return false;
+ if (dm_target_supports_zoned_hm(ti->type)) {
+ if (!ti->type->iterate_devices ||
+ ti->type->iterate_devices(ti, device_not_zoned_model,
+ &zoned_model))
+ return false;
+ } else if (!dm_target_supports_mixed_zoned_model(ti->type)) {
+ if (zoned_model == BLK_ZONED_HM)
+ return false;
+ }
}
return true;
@@ -1516,9 +1705,17 @@
struct request_queue *q = bdev_get_queue(dev->bdev);
unsigned int *zone_sectors = data;
+ if (!blk_queue_is_zoned(q))
+ return 0;
+
return !q || blk_queue_zone_sectors(q) != *zone_sectors;
}
+/*
+ * Check consistency of zoned model and zone sectors across all targets. For
+ * zone sectors, if the destination device is a zoned block device, it shall
+ * have the specified zone_sectors.
+ */
static int validate_hardware_zoned_model(struct dm_table *table,
enum blk_zoned_model zoned_model,
unsigned int zone_sectors)
@@ -1537,7 +1734,7 @@
return -EINVAL;
if (dm_table_any_dev_attr(table, device_not_matches_zone_sectors, &zone_sectors)) {
- DMERR("%s: zone sectors is not consistent across all devices",
+ DMERR("%s: zone sectors is not consistent across all zoned devices",
dm_device_name(table->md));
return -EINVAL;
}
@@ -1606,22 +1803,6 @@
dm_device_name(table->md),
(unsigned long long) ti->begin,
(unsigned long long) ti->len);
-
- /*
- * FIXME: this should likely be moved to blk_stack_limits(), would
- * also eliminate limits->zoned stacking hack in dm_set_device_limits()
- */
- if (limits->zoned == BLK_ZONED_NONE && ti_limits.zoned != BLK_ZONED_NONE) {
- /*
- * By default, the stacked limits zoned model is set to
- * BLK_ZONED_NONE in blk_set_stacking_limits(). Update
- * this model using the first target model reported
- * that is not BLK_ZONED_NONE. This will be either the
- * first target device zoned model or the model reported
- * by the target .io_hints.
- */
- limits->zoned = ti_limits.zoned;
- }
}
/*
@@ -1674,54 +1855,6 @@
blk_integrity_unregister(dm_disk(t->md));
}
}
-
-#ifdef CONFIG_BLK_INLINE_ENCRYPTION
-static int device_intersect_crypto_modes(struct dm_target *ti,
- struct dm_dev *dev, sector_t start,
- sector_t len, void *data)
-{
- struct keyslot_manager *parent = data;
- struct keyslot_manager *child = bdev_get_queue(dev->bdev)->ksm;
-
- keyslot_manager_intersect_modes(parent, child);
- return 0;
-}
-
-/*
- * Update the inline crypto modes supported by 'q->ksm' to be the intersection
- * of the modes supported by all targets in the table.
- *
- * For any mode to be supported at all, all targets must have explicitly
- * declared that they can pass through inline crypto support. For a particular
- * mode to be supported, all underlying devices must also support it.
- *
- * Assume that 'q->ksm' initially declares all modes to be supported.
- */
-static void dm_calculate_supported_crypto_modes(struct dm_table *t,
- struct request_queue *q)
-{
- struct dm_target *ti;
- unsigned int i;
-
- for (i = 0; i < dm_table_get_num_targets(t); i++) {
- ti = dm_table_get_target(t, i);
-
- if (!ti->may_passthrough_inline_crypto) {
- keyslot_manager_intersect_modes(q->ksm, NULL);
- return;
- }
- if (!ti->type->iterate_devices)
- continue;
- ti->type->iterate_devices(ti, device_intersect_crypto_modes,
- q->ksm);
- }
-}
-#else /* CONFIG_BLK_INLINE_ENCRYPTION */
-static inline void dm_calculate_supported_crypto_modes(struct dm_table *t,
- struct request_queue *q)
-{
-}
-#endif /* !CONFIG_BLK_INLINE_ENCRYPTION */
static int device_flush_capable(struct dm_target *ti, struct dm_dev *dev,
sector_t start, sector_t len, void *data)
@@ -1790,28 +1923,6 @@
return q && !blk_queue_add_random(q);
}
-static int queue_no_sg_merge(struct dm_target *ti, struct dm_dev *dev,
- sector_t start, sector_t len, void *data)
-{
- struct request_queue *q = bdev_get_queue(dev->bdev);
-
- return q && test_bit(QUEUE_FLAG_NO_SG_MERGE, &q->queue_flags);
-}
-
-static int device_is_partial_completion(struct dm_target *ti, struct dm_dev *dev,
- sector_t start, sector_t len, void *data)
-{
- char b[BDEVNAME_SIZE];
-
- /* For now, NVMe devices are the only devices of this class */
- return (strncmp(bdevname(dev->bdev, b), "nvme", 4) != 0);
-}
-
-static bool dm_table_does_not_support_partial_completion(struct dm_table *t)
-{
- return !dm_table_any_dev_attr(t, device_is_partial_completion, NULL);
-}
-
static int device_not_write_same_capable(struct dm_target *ti, struct dm_dev *dev,
sector_t start, sector_t len, void *data)
{
@@ -1860,6 +1971,33 @@
if (!ti->type->iterate_devices ||
ti->type->iterate_devices(ti, device_not_write_zeroes_capable, NULL))
+ return false;
+ }
+
+ return true;
+}
+
+static int device_not_nowait_capable(struct dm_target *ti, struct dm_dev *dev,
+ sector_t start, sector_t len, void *data)
+{
+ struct request_queue *q = bdev_get_queue(dev->bdev);
+
+ return q && !blk_queue_nowait(q);
+}
+
+static bool dm_table_supports_nowait(struct dm_table *t)
+{
+ struct dm_target *ti;
+ unsigned i = 0;
+
+ while (i < dm_table_get_num_targets(t)) {
+ ti = dm_table_get_target(t, i++);
+
+ if (!dm_target_supports_nowait(ti->type))
+ return false;
+
+ if (!ti->type->iterate_devices ||
+ ti->type->iterate_devices(ti, device_not_nowait_capable, NULL))
return false;
}
@@ -1933,18 +2071,24 @@
{
struct request_queue *q = bdev_get_queue(dev->bdev);
- return q && bdi_cap_stable_pages_required(q->backing_dev_info);
+ return q && blk_queue_stable_writes(q);
}
void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
struct queue_limits *limits)
{
bool wc = false, fua = false;
+ int page_size = PAGE_SIZE;
/*
* Copy table's limits to the DM device's request_queue
*/
q->limits = *limits;
+
+ if (dm_table_supports_nowait(t))
+ blk_queue_flag_set(QUEUE_FLAG_NOWAIT, q);
+ else
+ blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, q);
if (!dm_table_supports_discards(t)) {
blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q);
@@ -1967,8 +2111,11 @@
}
blk_queue_write_cache(q, wc, fua);
- if (dm_table_supports_dax(t))
+ if (dm_table_supports_dax(t, device_not_dax_capable, &page_size)) {
blk_queue_flag_set(QUEUE_FLAG_DAX, q);
+ if (dm_table_supports_dax(t, device_not_dax_synchronous_capable, NULL))
+ set_dax_synchronous(t->md->dax_dev);
+ }
else
blk_queue_flag_clear(QUEUE_FLAG_DAX, q);
@@ -1986,14 +2133,7 @@
if (!dm_table_supports_write_zeroes(t))
q->limits.max_write_zeroes_sectors = 0;
- if (dm_table_any_dev_attr(t, queue_no_sg_merge, NULL))
- blk_queue_flag_set(QUEUE_FLAG_NO_SG_MERGE, q);
- else
- blk_queue_flag_clear(QUEUE_FLAG_NO_SG_MERGE, q);
-
dm_table_verify_integrity(t);
-
- dm_calculate_supported_crypto_modes(t, q);
/*
* Some devices don't use blk_integrity but still want stable pages
@@ -2003,9 +2143,9 @@
* don't want error, zero, etc to require stable pages.
*/
if (dm_table_any_dev_attr(t, device_requires_stable_pages, NULL))
- q->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
+ blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q);
else
- q->backing_dev_info->capabilities &= ~BDI_CAP_STABLE_WRITES;
+ blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, q);
/*
* Determine whether or not this queue's I/O timings contribute
@@ -2017,8 +2157,20 @@
dm_table_any_dev_attr(t, device_is_not_random, NULL))
blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, q);
- /* io_pages is used for readahead */
- q->backing_dev_info->io_pages = limits->max_sectors >> (PAGE_SHIFT - 9);
+ /*
+ * For a zoned target, the number of zones should be updated for the
+ * correct value to be exposed in sysfs queue/nr_zones. For a BIO based
+ * target, this is all that is needed.
+ */
+#ifdef CONFIG_BLK_DEV_ZONED
+ if (blk_queue_is_zoned(q)) {
+ WARN_ON_ONCE(queue_is_mq(q));
+ q->nr_zones = blkdev_nr_zones(t->md->disk);
+ }
+#endif
+
+ dm_update_keyslot_manager(q, t);
+ blk_queue_update_readahead(q);
}
unsigned int dm_table_get_num_targets(struct dm_table *t)
@@ -2123,64 +2275,25 @@
return 0;
}
-void dm_table_add_target_callbacks(struct dm_table *t, struct dm_target_callbacks *cb)
-{
- list_add(&cb->list, &t->target_callbacks);
-}
-EXPORT_SYMBOL_GPL(dm_table_add_target_callbacks);
-
-int dm_table_any_congested(struct dm_table *t, int bdi_bits)
-{
- struct dm_dev_internal *dd;
- struct list_head *devices = dm_table_get_devices(t);
- struct dm_target_callbacks *cb;
- int r = 0;
-
- list_for_each_entry(dd, devices, list) {
- struct request_queue *q = bdev_get_queue(dd->dm_dev->bdev);
- char b[BDEVNAME_SIZE];
-
- if (likely(q))
- r |= bdi_congested(q->backing_dev_info, bdi_bits);
- else
- DMWARN_LIMIT("%s: any_congested: nonexistent device %s",
- dm_device_name(t->md),
- bdevname(dd->dm_dev->bdev, b));
- }
-
- list_for_each_entry(cb, &t->target_callbacks, list)
- if (cb->congested_fn)
- r |= cb->congested_fn(cb, bdi_bits);
-
- return r;
-}
-
struct mapped_device *dm_table_get_md(struct dm_table *t)
{
return t->md;
}
EXPORT_SYMBOL(dm_table_get_md);
+const char *dm_table_device_name(struct dm_table *t)
+{
+ return dm_device_name(t->md);
+}
+EXPORT_SYMBOL_GPL(dm_table_device_name);
+
void dm_table_run_md_queue_async(struct dm_table *t)
{
- struct mapped_device *md;
- struct request_queue *queue;
- unsigned long flags;
-
if (!dm_table_request_based(t))
return;
- md = dm_table_get_md(t);
- queue = dm_get_md_queue(md);
- if (queue) {
- if (queue->mq_ops)
- blk_mq_run_hw_queues(queue, true);
- else {
- spin_lock_irqsave(queue->queue_lock, flags);
- blk_run_queue_async(queue);
- spin_unlock_irqrestore(queue->queue_lock, flags);
- }
- }
+ if (t->md->queue)
+ blk_mq_run_hw_queues(t->md->queue, true);
}
EXPORT_SYMBOL(dm_table_run_md_queue_async);
--
Gitblit v1.6.2