* [PATCH 12/18] scsi: respect unchecked_isa_dma for blk-mq
From: Christoph Hellwig @ 2017-01-25 17:25 UTC (permalink / raw)
To: Jens Axboe
Cc: Mike Snitzer, Junichi Nomura, linux-block, linux-scsi, linux-raid,
dm-devel
In-Reply-To: <1485365126-23210-1-git-send-email-hch@lst.de>
Currently blk-mq always allocates the sense buffer using normal GFP_KERNEL
allocation. Refactor the cmd pool code to split the cmd and sense allocation
and share the code to allocate the sense buffers as well as the sense buffer
slab caches between the legacy and blk-mq path.
Note that this switches to lazy allocation of the sense slab caches - the
slab caches (not the actual allocations) won't be destroy until the scsi
module is unloaded instead of keeping track of hosts using them.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
---
drivers/scsi/hosts.c | 4 ++++
drivers/scsi/scsi.c | 24 ++++---------------
drivers/scsi/scsi_lib.c | 62 +++++++++++++++++++++++++++++++++++++++++++++---
drivers/scsi/scsi_priv.h | 5 ++++
4 files changed, 73 insertions(+), 22 deletions(-)
diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index 258a3f9..6d29c4a 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -213,6 +213,10 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev,
goto fail;
}
+ error = scsi_init_sense_cache(shost);
+ if (error)
+ goto fail;
+
if (shost_use_blk_mq(shost)) {
error = scsi_mq_setup_tags(shost);
if (error)
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index 0f93892..469aa0f 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -100,22 +100,18 @@ EXPORT_SYMBOL(scsi_sd_pm_domain);
struct scsi_host_cmd_pool {
struct kmem_cache *cmd_slab;
- struct kmem_cache *sense_slab;
unsigned int users;
char *cmd_name;
- char *sense_name;
unsigned int slab_flags;
};
static struct scsi_host_cmd_pool scsi_cmd_pool = {
.cmd_name = "scsi_cmd_cache",
- .sense_name = "scsi_sense_cache",
.slab_flags = SLAB_HWCACHE_ALIGN,
};
static struct scsi_host_cmd_pool scsi_cmd_dma_pool = {
.cmd_name = "scsi_cmd_cache(DMA)",
- .sense_name = "scsi_sense_cache(DMA)",
.slab_flags = SLAB_HWCACHE_ALIGN|SLAB_CACHE_DMA,
};
@@ -136,7 +132,7 @@ scsi_host_free_command(struct Scsi_Host *shost, struct scsi_cmnd *cmd)
if (cmd->prot_sdb)
kmem_cache_free(scsi_sdb_cache, cmd->prot_sdb);
- kmem_cache_free(pool->sense_slab, cmd->sense_buffer);
+ scsi_free_sense_buffer(shost, cmd->sense_buffer);
kmem_cache_free(pool->cmd_slab, cmd);
}
@@ -158,7 +154,8 @@ scsi_host_alloc_command(struct Scsi_Host *shost, gfp_t gfp_mask)
if (!cmd)
goto fail;
- cmd->sense_buffer = kmem_cache_alloc(pool->sense_slab, gfp_mask);
+ cmd->sense_buffer = scsi_alloc_sense_buffer(shost, gfp_mask,
+ NUMA_NO_NODE);
if (!cmd->sense_buffer)
goto fail_free_cmd;
@@ -171,7 +168,7 @@ scsi_host_alloc_command(struct Scsi_Host *shost, gfp_t gfp_mask)
return cmd;
fail_free_sense:
- kmem_cache_free(pool->sense_slab, cmd->sense_buffer);
+ scsi_free_sense_buffer(shost, cmd->sense_buffer);
fail_free_cmd:
kmem_cache_free(pool->cmd_slab, cmd);
fail:
@@ -301,7 +298,6 @@ scsi_find_host_cmd_pool(struct Scsi_Host *shost)
static void
scsi_free_host_cmd_pool(struct scsi_host_cmd_pool *pool)
{
- kfree(pool->sense_name);
kfree(pool->cmd_name);
kfree(pool);
}
@@ -317,8 +313,7 @@ scsi_alloc_host_cmd_pool(struct Scsi_Host *shost)
return NULL;
pool->cmd_name = kasprintf(GFP_KERNEL, "%s_cmd", hostt->proc_name);
- pool->sense_name = kasprintf(GFP_KERNEL, "%s_sense", hostt->proc_name);
- if (!pool->cmd_name || !pool->sense_name) {
+ if (!pool->cmd_name) {
scsi_free_host_cmd_pool(pool);
return NULL;
}
@@ -357,12 +352,6 @@ scsi_get_host_cmd_pool(struct Scsi_Host *shost)
pool->slab_flags, NULL);
if (!pool->cmd_slab)
goto out_free_pool;
-
- pool->sense_slab = kmem_cache_create(pool->sense_name,
- SCSI_SENSE_BUFFERSIZE, 0,
- pool->slab_flags, NULL);
- if (!pool->sense_slab)
- goto out_free_slab;
}
pool->users++;
@@ -371,8 +360,6 @@ scsi_get_host_cmd_pool(struct Scsi_Host *shost)
mutex_unlock(&host_cmd_pool_mutex);
return retval;
-out_free_slab:
- kmem_cache_destroy(pool->cmd_slab);
out_free_pool:
if (hostt->cmd_size) {
scsi_free_host_cmd_pool(pool);
@@ -398,7 +385,6 @@ static void scsi_put_host_cmd_pool(struct Scsi_Host *shost)
if (!--pool->users) {
kmem_cache_destroy(pool->cmd_slab);
- kmem_cache_destroy(pool->sense_slab);
if (hostt->cmd_size) {
scsi_free_host_cmd_pool(pool);
hostt->cmd_pool = NULL;
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index e9e1e14..3d6b364 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -39,6 +39,58 @@
struct kmem_cache *scsi_sdb_cache;
+static struct kmem_cache *scsi_sense_cache;
+static struct kmem_cache *scsi_sense_isadma_cache;
+static DEFINE_MUTEX(scsi_sense_cache_mutex);
+
+static inline struct kmem_cache *
+scsi_select_sense_cache(struct Scsi_Host *shost)
+{
+ return shost->unchecked_isa_dma ?
+ scsi_sense_isadma_cache : scsi_sense_cache;
+}
+
+void scsi_free_sense_buffer(struct Scsi_Host *shost,
+ unsigned char *sense_buffer)
+{
+ kmem_cache_free(scsi_select_sense_cache(shost), sense_buffer);
+}
+
+unsigned char *scsi_alloc_sense_buffer(struct Scsi_Host *shost, gfp_t gfp_mask,
+ int numa_node)
+{
+ return kmem_cache_alloc_node(scsi_select_sense_cache(shost), gfp_mask,
+ numa_node);
+}
+
+int scsi_init_sense_cache(struct Scsi_Host *shost)
+{
+ struct kmem_cache *cache;
+ int ret = 0;
+
+ cache = scsi_select_sense_cache(shost);
+ if (cache)
+ return 0;
+
+ mutex_lock(&scsi_sense_cache_mutex);
+ if (shost->unchecked_isa_dma) {
+ scsi_sense_isadma_cache =
+ kmem_cache_create("scsi_sense_cache(DMA)",
+ SCSI_SENSE_BUFFERSIZE, 0,
+ SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA, NULL);
+ if (!scsi_sense_isadma_cache)
+ ret = -ENOMEM;
+ } else {
+ scsi_sense_cache =
+ kmem_cache_create("scsi_sense_cache",
+ SCSI_SENSE_BUFFERSIZE, 0, SLAB_HWCACHE_ALIGN, NULL);
+ if (!scsi_sense_cache)
+ ret = -ENOMEM;
+ }
+
+ mutex_unlock(&scsi_sense_cache_mutex);
+ return ret;
+}
/*
* When to reinvoke queueing after a resource shortage. It's 3 msecs to
@@ -1981,10 +2033,11 @@ static int scsi_init_request(void *data, struct request *rq,
unsigned int hctx_idx, unsigned int request_idx,
unsigned int numa_node)
{
+ struct Scsi_Host *shost = data;
struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
- cmd->sense_buffer = kzalloc_node(SCSI_SENSE_BUFFERSIZE, GFP_KERNEL,
- numa_node);
+ cmd->sense_buffer =
+ scsi_alloc_sense_buffer(shost, GFP_KERNEL, numa_node);
if (!cmd->sense_buffer)
return -ENOMEM;
return 0;
@@ -1993,9 +2046,10 @@ static int scsi_init_request(void *data, struct request *rq,
static void scsi_exit_request(void *data, struct request *rq,
unsigned int hctx_idx, unsigned int request_idx)
{
+ struct Scsi_Host *shost = data;
struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
- kfree(cmd->sense_buffer);
+ scsi_free_sense_buffer(shost, cmd->sense_buffer);
}
static int scsi_map_queues(struct blk_mq_tag_set *set)
@@ -2208,6 +2262,8 @@ int __init scsi_init_queue(void)
void scsi_exit_queue(void)
{
+ kmem_cache_destroy(scsi_sense_cache);
+ kmem_cache_destroy(scsi_sense_isadma_cache);
kmem_cache_destroy(scsi_sdb_cache);
}
diff --git a/drivers/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h
index 193636a..1a712c6 100644
--- a/drivers/scsi/scsi_priv.h
+++ b/drivers/scsi/scsi_priv.h
@@ -30,6 +30,11 @@ extern void scsi_exit_hosts(void);
/* scsi.c */
extern bool scsi_use_blk_mq;
+void scsi_free_sense_buffer(struct Scsi_Host *shost,
+ unsigned char *sense_buffer);
+unsigned char *scsi_alloc_sense_buffer(struct Scsi_Host *shost, gfp_t gfp_mask,
+ int numa_node);
+int scsi_init_sense_cache(struct Scsi_Host *shost);
extern int scsi_setup_command_freelist(struct Scsi_Host *shost);
extern void scsi_destroy_command_freelist(struct Scsi_Host *shost);
#ifdef CONFIG_SCSI_LOGGING
--
2.1.4
^ permalink raw reply related
* [PATCH 13/18] scsi: remove scsi_cmd_dma_pool
From: Christoph Hellwig @ 2017-01-25 17:25 UTC (permalink / raw)
To: Jens Axboe
Cc: Mike Snitzer, Junichi Nomura, linux-block, linux-scsi, linux-raid,
dm-devel
In-Reply-To: <1485365126-23210-1-git-send-email-hch@lst.de>
There is no need for GFP_DMA allocations of the scsi_cmnd structures
themselves, all that might be DMAed to or from is the actual payload,
or the sense buffers.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
---
drivers/scsi/scsi.c | 15 +--------------
1 file changed, 1 insertion(+), 14 deletions(-)
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index 469aa0f..2e24f31 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -102,17 +102,10 @@ struct scsi_host_cmd_pool {
struct kmem_cache *cmd_slab;
unsigned int users;
char *cmd_name;
- unsigned int slab_flags;
};
static struct scsi_host_cmd_pool scsi_cmd_pool = {
.cmd_name = "scsi_cmd_cache",
- .slab_flags = SLAB_HWCACHE_ALIGN,
-};
-
-static struct scsi_host_cmd_pool scsi_cmd_dma_pool = {
- .cmd_name = "scsi_cmd_cache(DMA)",
- .slab_flags = SLAB_HWCACHE_ALIGN|SLAB_CACHE_DMA,
};
static DEFINE_MUTEX(host_cmd_pool_mutex);
@@ -290,8 +283,6 @@ scsi_find_host_cmd_pool(struct Scsi_Host *shost)
{
if (shost->hostt->cmd_size)
return shost->hostt->cmd_pool;
- if (shost->unchecked_isa_dma)
- return &scsi_cmd_dma_pool;
return &scsi_cmd_pool;
}
@@ -318,10 +309,6 @@ scsi_alloc_host_cmd_pool(struct Scsi_Host *shost)
return NULL;
}
- pool->slab_flags = SLAB_HWCACHE_ALIGN;
- if (shost->unchecked_isa_dma)
- pool->slab_flags |= SLAB_CACHE_DMA;
-
if (hostt->cmd_size)
hostt->cmd_pool = pool;
@@ -349,7 +336,7 @@ scsi_get_host_cmd_pool(struct Scsi_Host *shost)
if (!pool->users) {
pool->cmd_slab = kmem_cache_create(pool->cmd_name, cmd_size, 0,
- pool->slab_flags, NULL);
+ SLAB_HWCACHE_ALIGN, NULL);
if (!pool->cmd_slab)
goto out_free_pool;
}
--
2.1.4
^ permalink raw reply related
* [PATCH 14/18] scsi: remove __scsi_alloc_queue
From: Christoph Hellwig @ 2017-01-25 17:25 UTC (permalink / raw)
To: Jens Axboe
Cc: Mike Snitzer, Junichi Nomura, linux-block, linux-scsi, linux-raid,
dm-devel
In-Reply-To: <1485365126-23210-1-git-send-email-hch@lst.de>
Instead do an internal export of __scsi_init_queue for the transport
classes that export BSG nodes.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
---
drivers/scsi/scsi_lib.c | 19 ++++---------------
drivers/scsi/scsi_transport_fc.c | 6 ++++--
drivers/scsi/scsi_transport_iscsi.c | 3 ++-
include/scsi/scsi_host.h | 2 --
include/scsi/scsi_transport.h | 2 ++
5 files changed, 12 insertions(+), 20 deletions(-)
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 3d6b364..7950516 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -2082,7 +2082,7 @@ static u64 scsi_calculate_bounce_limit(struct Scsi_Host *shost)
return bounce_limit;
}
-static void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q)
+void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q)
{
struct device *dev = shost->dma_dev;
@@ -2117,28 +2117,17 @@ static void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q)
*/
blk_queue_dma_alignment(q, 0x03);
}
-
-struct request_queue *__scsi_alloc_queue(struct Scsi_Host *shost,
- request_fn_proc *request_fn)
-{
- struct request_queue *q;
-
- q = blk_init_queue(request_fn, NULL);
- if (!q)
- return NULL;
- __scsi_init_queue(shost, q);
- return q;
-}
-EXPORT_SYMBOL(__scsi_alloc_queue);
+EXPORT_SYMBOL_GPL(__scsi_init_queue);
struct request_queue *scsi_alloc_queue(struct scsi_device *sdev)
{
struct request_queue *q;
- q = __scsi_alloc_queue(sdev->host, scsi_request_fn);
+ q = blk_init_queue(scsi_request_fn, NULL);
if (!q)
return NULL;
+ __scsi_init_queue(sdev->host, q);
blk_queue_prep_rq(q, scsi_prep_fn);
blk_queue_unprep_rq(q, scsi_unprep_fn);
blk_queue_softirq_done(q, scsi_softirq_done);
diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c
index 03577bd..afcedec 100644
--- a/drivers/scsi/scsi_transport_fc.c
+++ b/drivers/scsi/scsi_transport_fc.c
@@ -3776,7 +3776,7 @@ fc_bsg_hostadd(struct Scsi_Host *shost, struct fc_host_attrs *fc_host)
snprintf(bsg_name, sizeof(bsg_name),
"fc_host%d", shost->host_no);
- q = __scsi_alloc_queue(shost, bsg_request_fn);
+ q = blk_init_queue(bsg_request_fn, NULL);
if (!q) {
dev_err(dev,
"fc_host%d: bsg interface failed to initialize - no request queue\n",
@@ -3784,6 +3784,7 @@ fc_bsg_hostadd(struct Scsi_Host *shost, struct fc_host_attrs *fc_host)
return -ENOMEM;
}
+ __scsi_init_queue(shost, q);
err = bsg_setup_queue(dev, q, bsg_name, fc_bsg_dispatch,
i->f->dd_bsg_size);
if (err) {
@@ -3831,12 +3832,13 @@ fc_bsg_rportadd(struct Scsi_Host *shost, struct fc_rport *rport)
if (!i->f->bsg_request)
return -ENOTSUPP;
- q = __scsi_alloc_queue(shost, bsg_request_fn);
+ q = blk_init_queue(bsg_request_fn, NULL);
if (!q) {
dev_err(dev, "bsg interface failed to initialize - no request queue\n");
return -ENOMEM;
}
+ __scsi_init_queue(shost, q);
err = bsg_setup_queue(dev, q, NULL, fc_bsg_dispatch, i->f->dd_bsg_size);
if (err) {
dev_err(dev, "failed to setup bsg queue\n");
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index 42bca61..04ebe6e 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -1544,10 +1544,11 @@ iscsi_bsg_host_add(struct Scsi_Host *shost, struct iscsi_cls_host *ihost)
snprintf(bsg_name, sizeof(bsg_name), "iscsi_host%d", shost->host_no);
- q = __scsi_alloc_queue(shost, bsg_request_fn);
+ q = blk_init_queue(bsg_request_fn, NULL);
if (!q)
return -ENOMEM;
+ __scsi_init_queue(shost, q);
ret = bsg_setup_queue(dev, q, bsg_name, iscsi_bsg_host_dispatch, 0);
if (ret) {
shost_printk(KERN_ERR, shost, "bsg interface failed to "
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 36680f1..f4964d7 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -826,8 +826,6 @@ extern void scsi_block_requests(struct Scsi_Host *);
struct class_container;
-extern struct request_queue *__scsi_alloc_queue(struct Scsi_Host *shost,
- void (*) (struct request_queue *));
/*
* These two functions are used to allocate and free a pseudo device
* which will connect to the host adapter itself rather than any
diff --git a/include/scsi/scsi_transport.h b/include/scsi/scsi_transport.h
index 8129239..b6e07b5 100644
--- a/include/scsi/scsi_transport.h
+++ b/include/scsi/scsi_transport.h
@@ -119,4 +119,6 @@ scsi_transport_device_data(struct scsi_device *sdev)
+ shost->transportt->device_private_offset;
}
+void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q);
+
#endif /* SCSI_TRANSPORT_H */
--
2.1.4
^ permalink raw reply related
* [PATCH 15/18] scsi: allocate scsi_cmnd structures as part of struct request
From: Christoph Hellwig @ 2017-01-25 17:25 UTC (permalink / raw)
To: Jens Axboe
Cc: Mike Snitzer, Junichi Nomura, linux-block, linux-scsi, linux-raid,
dm-devel
In-Reply-To: <1485365126-23210-1-git-send-email-hch@lst.de>
Rely on the new block layer functionality to allocate additional driver
specific data behind struct request instead of implementing it in SCSI
itѕelf.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
---
drivers/scsi/hosts.c | 20 +--
drivers/scsi/scsi.c | 319 ----------------------------------------------
drivers/scsi/scsi_error.c | 17 ++-
drivers/scsi/scsi_lib.c | 122 ++++++++++++------
drivers/scsi/scsi_priv.h | 8 +-
include/scsi/scsi_host.h | 3 -
6 files changed, 95 insertions(+), 394 deletions(-)
diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index 6d29c4a..831a1c8 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -230,19 +230,6 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev,
}
}
- /*
- * Note that we allocate the freelist even for the MQ case for now,
- * as we need a command set aside for scsi_reset_provider. Having
- * the full host freelist and one command available for that is a
- * little heavy-handed, but avoids introducing a special allocator
- * just for this. Eventually the structure of scsi_reset_provider
- * will need a major overhaul.
- */
- error = scsi_setup_command_freelist(shost);
- if (error)
- goto out_destroy_tags;
-
-
if (!shost->shost_gendev.parent)
shost->shost_gendev.parent = dev ? dev : &platform_bus;
if (!dma_dev)
@@ -262,7 +249,7 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev,
error = device_add(&shost->shost_gendev);
if (error)
- goto out_destroy_freelist;
+ goto out_disable_runtime_pm;
scsi_host_set_state(shost, SHOST_RUNNING);
get_device(shost->shost_gendev.parent);
@@ -312,13 +299,11 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev,
device_del(&shost->shost_dev);
out_del_gendev:
device_del(&shost->shost_gendev);
- out_destroy_freelist:
+ out_disable_runtime_pm:
device_disable_async_suspend(&shost->shost_gendev);
pm_runtime_disable(&shost->shost_gendev);
pm_runtime_set_suspended(&shost->shost_gendev);
pm_runtime_put_noidle(&shost->shost_gendev);
- scsi_destroy_command_freelist(shost);
- out_destroy_tags:
if (shost_use_blk_mq(shost))
scsi_mq_destroy_tags(shost);
fail:
@@ -359,7 +344,6 @@ static void scsi_host_dev_release(struct device *dev)
kfree(dev_name(&shost->shost_dev));
}
- scsi_destroy_command_freelist(shost);
if (shost_use_blk_mq(shost)) {
if (shost->tag_set.tags)
scsi_mq_destroy_tags(shost);
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index 2e24f31..3d8d215 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -98,163 +98,6 @@ EXPORT_SYMBOL(scsi_sd_probe_domain);
ASYNC_DOMAIN_EXCLUSIVE(scsi_sd_pm_domain);
EXPORT_SYMBOL(scsi_sd_pm_domain);
-struct scsi_host_cmd_pool {
- struct kmem_cache *cmd_slab;
- unsigned int users;
- char *cmd_name;
-};
-
-static struct scsi_host_cmd_pool scsi_cmd_pool = {
- .cmd_name = "scsi_cmd_cache",
-};
-
-static DEFINE_MUTEX(host_cmd_pool_mutex);
-
-/**
- * scsi_host_free_command - internal function to release a command
- * @shost: host to free the command for
- * @cmd: command to release
- *
- * the command must previously have been allocated by
- * scsi_host_alloc_command.
- */
-static void
-scsi_host_free_command(struct Scsi_Host *shost, struct scsi_cmnd *cmd)
-{
- struct scsi_host_cmd_pool *pool = shost->cmd_pool;
-
- if (cmd->prot_sdb)
- kmem_cache_free(scsi_sdb_cache, cmd->prot_sdb);
- scsi_free_sense_buffer(shost, cmd->sense_buffer);
- kmem_cache_free(pool->cmd_slab, cmd);
-}
-
-/**
- * scsi_host_alloc_command - internal function to allocate command
- * @shost: SCSI host whose pool to allocate from
- * @gfp_mask: mask for the allocation
- *
- * Returns a fully allocated command with sense buffer and protection
- * data buffer (where applicable) or NULL on failure
- */
-static struct scsi_cmnd *
-scsi_host_alloc_command(struct Scsi_Host *shost, gfp_t gfp_mask)
-{
- struct scsi_host_cmd_pool *pool = shost->cmd_pool;
- struct scsi_cmnd *cmd;
-
- cmd = kmem_cache_zalloc(pool->cmd_slab, gfp_mask);
- if (!cmd)
- goto fail;
-
- cmd->sense_buffer = scsi_alloc_sense_buffer(shost, gfp_mask,
- NUMA_NO_NODE);
- if (!cmd->sense_buffer)
- goto fail_free_cmd;
-
- if (scsi_host_get_prot(shost) >= SHOST_DIX_TYPE0_PROTECTION) {
- cmd->prot_sdb = kmem_cache_zalloc(scsi_sdb_cache, gfp_mask);
- if (!cmd->prot_sdb)
- goto fail_free_sense;
- }
-
- return cmd;
-
-fail_free_sense:
- scsi_free_sense_buffer(shost, cmd->sense_buffer);
-fail_free_cmd:
- kmem_cache_free(pool->cmd_slab, cmd);
-fail:
- return NULL;
-}
-
-/**
- * __scsi_get_command - Allocate a struct scsi_cmnd
- * @shost: host to transmit command
- * @gfp_mask: allocation mask
- *
- * Description: allocate a struct scsi_cmd from host's slab, recycling from the
- * host's free_list if necessary.
- */
-static struct scsi_cmnd *
-__scsi_get_command(struct Scsi_Host *shost, gfp_t gfp_mask)
-{
- struct scsi_cmnd *cmd = scsi_host_alloc_command(shost, gfp_mask);
-
- if (unlikely(!cmd)) {
- unsigned long flags;
-
- spin_lock_irqsave(&shost->free_list_lock, flags);
- if (likely(!list_empty(&shost->free_list))) {
- cmd = list_entry(shost->free_list.next,
- struct scsi_cmnd, list);
- list_del_init(&cmd->list);
- }
- spin_unlock_irqrestore(&shost->free_list_lock, flags);
-
- if (cmd) {
- void *buf, *prot;
-
- buf = cmd->sense_buffer;
- prot = cmd->prot_sdb;
-
- memset(cmd, 0, sizeof(*cmd));
-
- cmd->sense_buffer = buf;
- cmd->prot_sdb = prot;
- }
- }
-
- return cmd;
-}
-
-/**
- * scsi_get_command - Allocate and setup a scsi command block
- * @dev: parent scsi device
- * @gfp_mask: allocator flags
- *
- * Returns: The allocated scsi command structure.
- */
-struct scsi_cmnd *scsi_get_command(struct scsi_device *dev, gfp_t gfp_mask)
-{
- struct scsi_cmnd *cmd = __scsi_get_command(dev->host, gfp_mask);
- unsigned long flags;
-
- if (unlikely(cmd == NULL))
- return NULL;
-
- cmd->device = dev;
- INIT_LIST_HEAD(&cmd->list);
- INIT_DELAYED_WORK(&cmd->abort_work, scmd_eh_abort_handler);
- spin_lock_irqsave(&dev->list_lock, flags);
- list_add_tail(&cmd->list, &dev->cmd_list);
- spin_unlock_irqrestore(&dev->list_lock, flags);
- cmd->jiffies_at_alloc = jiffies;
- return cmd;
-}
-
-/**
- * __scsi_put_command - Free a struct scsi_cmnd
- * @shost: dev->host
- * @cmd: Command to free
- */
-static void __scsi_put_command(struct Scsi_Host *shost, struct scsi_cmnd *cmd)
-{
- unsigned long flags;
-
- if (unlikely(list_empty(&shost->free_list))) {
- spin_lock_irqsave(&shost->free_list_lock, flags);
- if (list_empty(&shost->free_list)) {
- list_add(&cmd->list, &shost->free_list);
- cmd = NULL;
- }
- spin_unlock_irqrestore(&shost->free_list_lock, flags);
- }
-
- if (likely(cmd != NULL))
- scsi_host_free_command(shost, cmd);
-}
-
/**
* scsi_put_command - Free a scsi command block
* @cmd: command block to free
@@ -274,168 +117,6 @@ void scsi_put_command(struct scsi_cmnd *cmd)
spin_unlock_irqrestore(&cmd->device->list_lock, flags);
BUG_ON(delayed_work_pending(&cmd->abort_work));
-
- __scsi_put_command(cmd->device->host, cmd);
-}
-
-static struct scsi_host_cmd_pool *
-scsi_find_host_cmd_pool(struct Scsi_Host *shost)
-{
- if (shost->hostt->cmd_size)
- return shost->hostt->cmd_pool;
- return &scsi_cmd_pool;
-}
-
-static void
-scsi_free_host_cmd_pool(struct scsi_host_cmd_pool *pool)
-{
- kfree(pool->cmd_name);
- kfree(pool);
-}
-
-static struct scsi_host_cmd_pool *
-scsi_alloc_host_cmd_pool(struct Scsi_Host *shost)
-{
- struct scsi_host_template *hostt = shost->hostt;
- struct scsi_host_cmd_pool *pool;
-
- pool = kzalloc(sizeof(*pool), GFP_KERNEL);
- if (!pool)
- return NULL;
-
- pool->cmd_name = kasprintf(GFP_KERNEL, "%s_cmd", hostt->proc_name);
- if (!pool->cmd_name) {
- scsi_free_host_cmd_pool(pool);
- return NULL;
- }
-
- if (hostt->cmd_size)
- hostt->cmd_pool = pool;
-
- return pool;
-}
-
-static struct scsi_host_cmd_pool *
-scsi_get_host_cmd_pool(struct Scsi_Host *shost)
-{
- struct scsi_host_template *hostt = shost->hostt;
- struct scsi_host_cmd_pool *retval = NULL, *pool;
- size_t cmd_size = sizeof(struct scsi_cmnd) + hostt->cmd_size;
-
- /*
- * Select a command slab for this host and create it if not
- * yet existent.
- */
- mutex_lock(&host_cmd_pool_mutex);
- pool = scsi_find_host_cmd_pool(shost);
- if (!pool) {
- pool = scsi_alloc_host_cmd_pool(shost);
- if (!pool)
- goto out;
- }
-
- if (!pool->users) {
- pool->cmd_slab = kmem_cache_create(pool->cmd_name, cmd_size, 0,
- SLAB_HWCACHE_ALIGN, NULL);
- if (!pool->cmd_slab)
- goto out_free_pool;
- }
-
- pool->users++;
- retval = pool;
-out:
- mutex_unlock(&host_cmd_pool_mutex);
- return retval;
-
-out_free_pool:
- if (hostt->cmd_size) {
- scsi_free_host_cmd_pool(pool);
- hostt->cmd_pool = NULL;
- }
- goto out;
-}
-
-static void scsi_put_host_cmd_pool(struct Scsi_Host *shost)
-{
- struct scsi_host_template *hostt = shost->hostt;
- struct scsi_host_cmd_pool *pool;
-
- mutex_lock(&host_cmd_pool_mutex);
- pool = scsi_find_host_cmd_pool(shost);
-
- /*
- * This may happen if a driver has a mismatched get and put
- * of the command pool; the driver should be implicated in
- * the stack trace
- */
- BUG_ON(pool->users == 0);
-
- if (!--pool->users) {
- kmem_cache_destroy(pool->cmd_slab);
- if (hostt->cmd_size) {
- scsi_free_host_cmd_pool(pool);
- hostt->cmd_pool = NULL;
- }
- }
- mutex_unlock(&host_cmd_pool_mutex);
-}
-
-/**
- * scsi_setup_command_freelist - Setup the command freelist for a scsi host.
- * @shost: host to allocate the freelist for.
- *
- * Description: The command freelist protects against system-wide out of memory
- * deadlock by preallocating one SCSI command structure for each host, so the
- * system can always write to a swap file on a device associated with that host.
- *
- * Returns: Nothing.
- */
-int scsi_setup_command_freelist(struct Scsi_Host *shost)
-{
- struct scsi_cmnd *cmd;
-
- spin_lock_init(&shost->free_list_lock);
- INIT_LIST_HEAD(&shost->free_list);
-
- shost->cmd_pool = scsi_get_host_cmd_pool(shost);
- if (!shost->cmd_pool)
- return -ENOMEM;
-
- /*
- * Get one backup command for this host.
- */
- cmd = scsi_host_alloc_command(shost, GFP_KERNEL);
- if (!cmd) {
- scsi_put_host_cmd_pool(shost);
- shost->cmd_pool = NULL;
- return -ENOMEM;
- }
- list_add(&cmd->list, &shost->free_list);
- return 0;
-}
-
-/**
- * scsi_destroy_command_freelist - Release the command freelist for a scsi host.
- * @shost: host whose freelist is going to be destroyed
- */
-void scsi_destroy_command_freelist(struct Scsi_Host *shost)
-{
- /*
- * If cmd_pool is NULL the free list was not initialized, so
- * do not attempt to release resources.
- */
- if (!shost->cmd_pool)
- return;
-
- while (!list_empty(&shost->free_list)) {
- struct scsi_cmnd *cmd;
-
- cmd = list_entry(shost->free_list.next, struct scsi_cmnd, list);
- list_del_init(&cmd->list);
- scsi_host_free_command(shost, cmd);
- }
- shost->cmd_pool = NULL;
- scsi_put_host_cmd_pool(shost);
}
#ifdef CONFIG_SCSI_LOGGING
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 996e134..7c08460 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -2331,7 +2331,7 @@ scsi_ioctl_reset(struct scsi_device *dev, int __user *arg)
{
struct scsi_cmnd *scmd;
struct Scsi_Host *shost = dev->host;
- struct request req;
+ struct request *rq;
unsigned long flags;
int error = 0, rtn, val;
@@ -2346,14 +2346,16 @@ scsi_ioctl_reset(struct scsi_device *dev, int __user *arg)
return -EIO;
error = -EIO;
- scmd = scsi_get_command(dev, GFP_KERNEL);
- if (!scmd)
+ rq = kzalloc(sizeof(struct request) + sizeof(struct scsi_cmnd) +
+ shost->hostt->cmd_size, GFP_KERNEL);
+ if (!rq)
goto out_put_autopm_host;
+ blk_rq_init(NULL, rq);
- blk_rq_init(NULL, &req);
- scmd->request = &req;
-
- scmd->cmnd = req.cmd;
+ scmd = (struct scsi_cmnd *)(rq + 1);
+ scsi_init_command(dev, scmd);
+ scmd->request = rq;
+ scmd->cmnd = rq->cmd;
scmd->scsi_done = scsi_reset_provider_done_command;
memset(&scmd->sdb, 0, sizeof(scmd->sdb));
@@ -2413,6 +2415,7 @@ scsi_ioctl_reset(struct scsi_device *dev, int __user *arg)
scsi_run_host_queues(shost);
scsi_put_command(scmd);
+ kfree(rq);
out_put_autopm_host:
scsi_autopm_put_host(shost);
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 7950516..81ff5ad 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -37,8 +37,7 @@
#include "scsi_priv.h"
#include "scsi_logging.h"
-
-struct kmem_cache *scsi_sdb_cache;
+static struct kmem_cache *scsi_sdb_cache;
static struct kmem_cache *scsi_sense_cache;
static struct kmem_cache *scsi_sense_isadma_cache;
static DEFINE_MUTEX(scsi_sense_cache_mutex);
@@ -50,14 +49,14 @@ scsi_select_sense_cache(struct Scsi_Host *shost)
scsi_sense_isadma_cache : scsi_sense_cache;
}
-void scsi_free_sense_buffer(struct Scsi_Host *shost,
+static void scsi_free_sense_buffer(struct Scsi_Host *shost,
unsigned char *sense_buffer)
{
kmem_cache_free(scsi_select_sense_cache(shost), sense_buffer);
}
-unsigned char *scsi_alloc_sense_buffer(struct Scsi_Host *shost, gfp_t gfp_mask,
- int numa_node)
+static unsigned char *scsi_alloc_sense_buffer(struct Scsi_Host *shost,
+ gfp_t gfp_mask, int numa_node)
{
return kmem_cache_alloc_node(scsi_select_sense_cache(shost), gfp_mask,
numa_node);
@@ -697,14 +696,13 @@ static bool scsi_end_request(struct request *req, int error,
if (bidi_bytes)
scsi_release_bidi_buffers(cmd);
+ scsi_release_buffers(cmd);
+ scsi_put_command(cmd);
spin_lock_irqsave(q->queue_lock, flags);
blk_finish_request(req, error);
spin_unlock_irqrestore(q->queue_lock, flags);
- scsi_release_buffers(cmd);
-
- scsi_put_command(cmd);
scsi_run_queue(q);
}
@@ -1161,34 +1159,22 @@ int scsi_init_io(struct scsi_cmnd *cmd)
}
EXPORT_SYMBOL(scsi_init_io);
-static struct scsi_cmnd *scsi_get_cmd_from_req(struct scsi_device *sdev,
- struct request *req)
+void scsi_init_command(struct scsi_device *dev, struct scsi_cmnd *cmd)
{
- struct scsi_cmnd *cmd;
-
- if (!req->special) {
- /* Bail if we can't get a reference to the device */
- if (!get_device(&sdev->sdev_gendev))
- return NULL;
-
- cmd = scsi_get_command(sdev, GFP_ATOMIC);
- if (unlikely(!cmd)) {
- put_device(&sdev->sdev_gendev);
- return NULL;
- }
- req->special = cmd;
- } else {
- cmd = req->special;
- }
-
- /* pull a tag out of the request if we have one */
- cmd->tag = req->tag;
- cmd->request = req;
+ void *buf = cmd->sense_buffer;
+ void *prot = cmd->prot_sdb;
+ unsigned long flags;
- cmd->cmnd = req->cmd;
- cmd->prot_op = SCSI_PROT_NORMAL;
+ memset(cmd, 0, sizeof(*cmd));
+ cmd->device = dev;
+ cmd->sense_buffer = buf;
+ cmd->prot_sdb = prot;
+ INIT_DELAYED_WORK(&cmd->abort_work, scmd_eh_abort_handler);
+ cmd->jiffies_at_alloc = jiffies;
- return cmd;
+ spin_lock_irqsave(&dev->list_lock, flags);
+ list_add_tail(&cmd->list, &dev->cmd_list);
+ spin_unlock_irqrestore(&dev->list_lock, flags);
}
static int scsi_setup_blk_pc_cmnd(struct scsi_device *sdev, struct request *req)
@@ -1349,19 +1335,29 @@ scsi_prep_return(struct request_queue *q, struct request *req, int ret)
static int scsi_prep_fn(struct request_queue *q, struct request *req)
{
struct scsi_device *sdev = q->queuedata;
- struct scsi_cmnd *cmd;
+ struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(req);
int ret;
ret = scsi_prep_state_check(sdev, req);
if (ret != BLKPREP_OK)
goto out;
- cmd = scsi_get_cmd_from_req(sdev, req);
- if (unlikely(!cmd)) {
- ret = BLKPREP_DEFER;
- goto out;
+ if (!req->special) {
+ /* Bail if we can't get a reference to the device */
+ if (unlikely(!get_device(&sdev->sdev_gendev))) {
+ ret = BLKPREP_DEFER;
+ goto out;
+ }
+
+ scsi_init_command(sdev, cmd);
+ req->special = cmd;
}
+ cmd->tag = req->tag;
+ cmd->request = req;
+ cmd->cmnd = req->cmd;
+ cmd->prot_op = SCSI_PROT_NORMAL;
+
ret = scsi_setup_cmnd(sdev, req);
out:
return scsi_prep_return(q, req, ret);
@@ -2119,15 +2115,61 @@ void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q)
}
EXPORT_SYMBOL_GPL(__scsi_init_queue);
+static int scsi_init_rq(struct request_queue *q, struct request *rq, gfp_t gfp)
+{
+ struct Scsi_Host *shost = q->rq_alloc_data;
+ struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
+
+ memset(cmd, 0, sizeof(*cmd));
+
+ cmd->sense_buffer = scsi_alloc_sense_buffer(shost, gfp, NUMA_NO_NODE);
+ if (!cmd->sense_buffer)
+ goto fail;
+
+ if (scsi_host_get_prot(shost) >= SHOST_DIX_TYPE0_PROTECTION) {
+ cmd->prot_sdb = kmem_cache_zalloc(scsi_sdb_cache, gfp);
+ if (!cmd->prot_sdb)
+ goto fail_free_sense;
+ }
+
+ return 0;
+
+fail_free_sense:
+ scsi_free_sense_buffer(shost, cmd->sense_buffer);
+fail:
+ return -ENOMEM;
+}
+
+static void scsi_exit_rq(struct request_queue *q, struct request *rq)
+{
+ struct Scsi_Host *shost = q->rq_alloc_data;
+ struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
+
+ if (cmd->prot_sdb)
+ kmem_cache_free(scsi_sdb_cache, cmd->prot_sdb);
+ scsi_free_sense_buffer(shost, cmd->sense_buffer);
+}
+
struct request_queue *scsi_alloc_queue(struct scsi_device *sdev)
{
+ struct Scsi_Host *shost = sdev->host;
struct request_queue *q;
- q = blk_init_queue(scsi_request_fn, NULL);
+ q = blk_alloc_queue_node(GFP_KERNEL, NUMA_NO_NODE);
if (!q)
return NULL;
+ q->cmd_size = sizeof(struct scsi_cmnd) + shost->hostt->cmd_size;
+ q->rq_alloc_data = shost;
+ q->request_fn = scsi_request_fn;
+ q->init_rq_fn = scsi_init_rq;
+ q->exit_rq_fn = scsi_exit_rq;
+
+ if (blk_init_allocated_queue(q) < 0) {
+ blk_cleanup_queue(q);
+ return NULL;
+ }
- __scsi_init_queue(sdev->host, q);
+ __scsi_init_queue(shost, q);
blk_queue_prep_rq(q, scsi_prep_fn);
blk_queue_unprep_rq(q, scsi_unprep_fn);
blk_queue_softirq_done(q, scsi_softirq_done);
diff --git a/drivers/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h
index 1a712c6..99bfc98 100644
--- a/drivers/scsi/scsi_priv.h
+++ b/drivers/scsi/scsi_priv.h
@@ -30,13 +30,8 @@ extern void scsi_exit_hosts(void);
/* scsi.c */
extern bool scsi_use_blk_mq;
-void scsi_free_sense_buffer(struct Scsi_Host *shost,
- unsigned char *sense_buffer);
-unsigned char *scsi_alloc_sense_buffer(struct Scsi_Host *shost, gfp_t gfp_mask,
- int numa_node);
int scsi_init_sense_cache(struct Scsi_Host *shost);
-extern int scsi_setup_command_freelist(struct Scsi_Host *shost);
-extern void scsi_destroy_command_freelist(struct Scsi_Host *shost);
+void scsi_init_command(struct scsi_device *dev, struct scsi_cmnd *cmd);
#ifdef CONFIG_SCSI_LOGGING
void scsi_log_send(struct scsi_cmnd *cmd);
void scsi_log_completion(struct scsi_cmnd *cmd, int disposition);
@@ -101,7 +96,6 @@ extern void scsi_exit_queue(void);
extern void scsi_evt_thread(struct work_struct *work);
struct request_queue;
struct request;
-extern struct kmem_cache *scsi_sdb_cache;
/* scsi_proc.c */
#ifdef CONFIG_SCSI_PROC_FS
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index f4964d7..3cd8c3b 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -551,9 +551,6 @@ struct Scsi_Host {
struct list_head __devices;
struct list_head __targets;
- struct scsi_host_cmd_pool *cmd_pool;
- spinlock_t free_list_lock;
- struct list_head free_list; /* backup store of cmd structs */
struct list_head starved_list;
spinlock_t default_lock;
--
2.1.4
^ permalink raw reply related
* [PATCH 16/18] block/bsg: move queue creation into bsg_setup_queue
From: Christoph Hellwig @ 2017-01-25 17:25 UTC (permalink / raw)
To: Jens Axboe
Cc: Mike Snitzer, Junichi Nomura, linux-block, linux-scsi, linux-raid,
dm-devel
In-Reply-To: <1485365126-23210-1-git-send-email-hch@lst.de>
Simply the boilerplate code needed for bsg nodes a bit.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
---
block/bsg-lib.c | 21 +++++++++++----------
drivers/scsi/scsi_transport_fc.c | 36 ++++++++----------------------------
drivers/scsi/scsi_transport_iscsi.c | 15 ++++-----------
include/linux/bsg-lib.h | 5 ++---
4 files changed, 25 insertions(+), 52 deletions(-)
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index 9d652a9..c74acf4 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -177,7 +177,7 @@ static int bsg_create_job(struct device *dev, struct request *req)
*
* Drivers/subsys should pass this to the queue init function.
*/
-void bsg_request_fn(struct request_queue *q)
+static void bsg_request_fn(struct request_queue *q)
__releases(q->queue_lock)
__acquires(q->queue_lock)
{
@@ -214,24 +214,24 @@ void bsg_request_fn(struct request_queue *q)
put_device(dev);
spin_lock_irq(q->queue_lock);
}
-EXPORT_SYMBOL_GPL(bsg_request_fn);
/**
* bsg_setup_queue - Create and add the bsg hooks so we can receive requests
* @dev: device to attach bsg device to
- * @q: request queue setup by caller
* @name: device to give bsg device
* @job_fn: bsg job handler
* @dd_job_size: size of LLD data needed for each job
- *
- * The caller should have setup the reuqest queue with bsg_request_fn
- * as the request_fn.
*/
-int bsg_setup_queue(struct device *dev, struct request_queue *q,
- char *name, bsg_job_fn *job_fn, int dd_job_size)
+struct request_queue *bsg_setup_queue(struct device *dev, char *name,
+ bsg_job_fn *job_fn, int dd_job_size)
{
+ struct request_queue *q;
int ret;
+ q = blk_init_queue(bsg_request_fn, NULL);
+ if (!q)
+ return ERR_PTR(-ENOMEM);
+
q->queuedata = dev;
q->bsg_job_size = dd_job_size;
q->bsg_job_fn = job_fn;
@@ -243,9 +243,10 @@ int bsg_setup_queue(struct device *dev, struct request_queue *q,
if (ret) {
printk(KERN_ERR "%s: bsg interface failed to "
"initialize - register queue\n", dev->kobj.name);
- return ret;
+ blk_cleanup_queue(q);
+ return ERR_PTR(ret);
}
- return 0;
+ return q;
}
EXPORT_SYMBOL_GPL(bsg_setup_queue);
diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c
index afcedec..13dcb9b 100644
--- a/drivers/scsi/scsi_transport_fc.c
+++ b/drivers/scsi/scsi_transport_fc.c
@@ -3765,7 +3765,6 @@ fc_bsg_hostadd(struct Scsi_Host *shost, struct fc_host_attrs *fc_host)
struct device *dev = &shost->shost_gendev;
struct fc_internal *i = to_fc_internal(shost->transportt);
struct request_queue *q;
- int err;
char bsg_name[20];
fc_host->rqst_q = NULL;
@@ -3776,24 +3775,14 @@ fc_bsg_hostadd(struct Scsi_Host *shost, struct fc_host_attrs *fc_host)
snprintf(bsg_name, sizeof(bsg_name),
"fc_host%d", shost->host_no);
- q = blk_init_queue(bsg_request_fn, NULL);
- if (!q) {
- dev_err(dev,
- "fc_host%d: bsg interface failed to initialize - no request queue\n",
- shost->host_no);
- return -ENOMEM;
- }
-
- __scsi_init_queue(shost, q);
- err = bsg_setup_queue(dev, q, bsg_name, fc_bsg_dispatch,
- i->f->dd_bsg_size);
- if (err) {
+ q = bsg_setup_queue(dev, bsg_name, fc_bsg_dispatch, i->f->dd_bsg_size);
+ if (IS_ERR(q)) {
dev_err(dev,
"fc_host%d: bsg interface failed to initialize - setup queue\n",
shost->host_no);
- blk_cleanup_queue(q);
- return err;
+ return PTR_ERR(q);
}
+ __scsi_init_queue(shost, q);
blk_queue_rq_timed_out(q, fc_bsg_job_timeout);
blk_queue_rq_timeout(q, FC_DEFAULT_BSG_TIMEOUT);
fc_host->rqst_q = q;
@@ -3825,27 +3814,18 @@ fc_bsg_rportadd(struct Scsi_Host *shost, struct fc_rport *rport)
struct device *dev = &rport->dev;
struct fc_internal *i = to_fc_internal(shost->transportt);
struct request_queue *q;
- int err;
rport->rqst_q = NULL;
if (!i->f->bsg_request)
return -ENOTSUPP;
- q = blk_init_queue(bsg_request_fn, NULL);
- if (!q) {
- dev_err(dev, "bsg interface failed to initialize - no request queue\n");
- return -ENOMEM;
- }
-
- __scsi_init_queue(shost, q);
- err = bsg_setup_queue(dev, q, NULL, fc_bsg_dispatch, i->f->dd_bsg_size);
- if (err) {
+ q = bsg_setup_queue(dev, NULL, fc_bsg_dispatch, i->f->dd_bsg_size);
+ if (IS_ERR(q)) {
dev_err(dev, "failed to setup bsg queue\n");
- blk_cleanup_queue(q);
- return err;
+ return PTR_ERR(q);
}
-
+ __scsi_init_queue(shost, q);
blk_queue_prep_rq(q, fc_bsg_rport_prep);
blk_queue_rq_timed_out(q, fc_bsg_job_timeout);
blk_queue_rq_timeout(q, BLK_DEFAULT_SG_TIMEOUT);
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index 04ebe6e..568c9f2 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -1537,25 +1537,18 @@ iscsi_bsg_host_add(struct Scsi_Host *shost, struct iscsi_cls_host *ihost)
struct iscsi_internal *i = to_iscsi_internal(shost->transportt);
struct request_queue *q;
char bsg_name[20];
- int ret;
if (!i->iscsi_transport->bsg_request)
return -ENOTSUPP;
snprintf(bsg_name, sizeof(bsg_name), "iscsi_host%d", shost->host_no);
-
- q = blk_init_queue(bsg_request_fn, NULL);
- if (!q)
- return -ENOMEM;
-
- __scsi_init_queue(shost, q);
- ret = bsg_setup_queue(dev, q, bsg_name, iscsi_bsg_host_dispatch, 0);
- if (ret) {
+ q = bsg_setup_queue(dev, bsg_name, iscsi_bsg_host_dispatch, 0);
+ if (IS_ERR(q)) {
shost_printk(KERN_ERR, shost, "bsg interface failed to "
"initialize - no request queue\n");
- blk_cleanup_queue(q);
- return ret;
+ return PTR_ERR(q);
}
+ __scsi_init_queue(shost, q);
ihost->bsg_q = q;
return 0;
diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h
index 657a718..e34dde2 100644
--- a/include/linux/bsg-lib.h
+++ b/include/linux/bsg-lib.h
@@ -66,9 +66,8 @@ struct bsg_job {
void bsg_job_done(struct bsg_job *job, int result,
unsigned int reply_payload_rcv_len);
-int bsg_setup_queue(struct device *dev, struct request_queue *q, char *name,
- bsg_job_fn *job_fn, int dd_job_size);
-void bsg_request_fn(struct request_queue *q);
+struct request_queue *bsg_setup_queue(struct device *dev, char *name,
+ bsg_job_fn *job_fn, int dd_job_size);
void bsg_job_put(struct bsg_job *job);
int __must_check bsg_job_get(struct bsg_job *job);
--
2.1.4
^ permalink raw reply related
* [PATCH 17/18] block: split scsi_request out of struct request
From: Christoph Hellwig @ 2017-01-25 17:25 UTC (permalink / raw)
To: Jens Axboe
Cc: Mike Snitzer, Junichi Nomura, linux-block, linux-scsi, linux-raid,
dm-devel
In-Reply-To: <1485365126-23210-1-git-send-email-hch@lst.de>
And require all drivers that want to support BLOCK_PC to allocate it
as the first thing of their private data. To support this the legacy
IDE and BSG code is switched to set cmd_size on their queues to let
the block layer allocate the additional space.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
block/blk-core.c | 31 -----------
block/blk-exec.c | 12 -----
block/blk-mq.c | 10 ----
block/bsg-lib.c | 34 ++++++++----
block/bsg.c | 47 ++++++++---------
block/scsi_ioctl.c | 87 ++++++++++++++++++------------
drivers/ata/libata-scsi.c | 2 +-
drivers/block/cciss.c | 28 +++++-----
drivers/block/pktcdvd.c | 6 +--
drivers/block/virtio_blk.c | 11 ++--
drivers/cdrom/cdrom.c | 32 +++++------
drivers/ide/ide-atapi.c | 43 ++++++++-------
drivers/ide/ide-cd.c | 91 +++++++++++++++-----------------
drivers/ide/ide-cd_ioctl.c | 1 +
drivers/ide/ide-cd_verbose.c | 6 +--
drivers/ide/ide-devsets.c | 9 ++--
drivers/ide/ide-disk.c | 1 +
drivers/ide/ide-eh.c | 2 +-
drivers/ide/ide-floppy.c | 4 +-
drivers/ide/ide-io.c | 3 +-
drivers/ide/ide-ioctls.c | 6 ++-
drivers/ide/ide-park.c | 12 +++--
drivers/ide/ide-pm.c | 2 +
drivers/ide/ide-probe.c | 36 +++++++++++--
drivers/ide/ide-tape.c | 32 +++++------
drivers/ide/ide-taskfile.c | 1 +
drivers/ide/sis5513.c | 2 +-
drivers/message/fusion/mptsas.c | 8 +--
drivers/scsi/libfc/fc_lport.c | 2 +-
drivers/scsi/libsas/sas_expander.c | 8 +--
drivers/scsi/libsas/sas_host_smp.c | 38 ++++++-------
drivers/scsi/mpt3sas/mpt3sas_transport.c | 8 +--
drivers/scsi/osd/osd_initiator.c | 19 +++----
drivers/scsi/osst.c | 15 +++---
drivers/scsi/qla2xxx/qla_bsg.c | 2 +-
drivers/scsi/qla2xxx/qla_isr.c | 6 ++-
drivers/scsi/qla2xxx/qla_mr.c | 2 +-
drivers/scsi/scsi_error.c | 22 ++++----
drivers/scsi/scsi_lib.c | 48 +++++++++--------
drivers/scsi/scsi_transport_sas.c | 5 ++
drivers/scsi/sd.c | 4 +-
drivers/scsi/sg.c | 30 ++++++-----
drivers/scsi/st.c | 22 ++++----
drivers/target/target_core_pscsi.c | 11 ++--
fs/nfsd/blocklayout.c | 17 +++---
include/linux/blkdev.h | 11 ----
include/linux/blktrace_api.h | 3 +-
include/linux/ide.h | 8 ++-
include/scsi/scsi_cmnd.h | 2 +
include/scsi/scsi_request.h | 28 ++++++++++
kernel/trace/blktrace.c | 32 +++++------
51 files changed, 483 insertions(+), 419 deletions(-)
create mode 100644 include/scsi/scsi_request.h
diff --git a/block/blk-core.c b/block/blk-core.c
index 7de7164..33c5d05e 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -132,8 +132,6 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
rq->__sector = (sector_t) -1;
INIT_HLIST_NODE(&rq->hash);
RB_CLEAR_NODE(&rq->rb_node);
- rq->cmd = rq->__cmd;
- rq->cmd_len = BLK_MAX_CDB;
rq->tag = -1;
rq->internal_tag = -1;
rq->start_time = jiffies;
@@ -160,8 +158,6 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
void blk_dump_rq_flags(struct request *rq, char *msg)
{
- int bit;
-
printk(KERN_INFO "%s: dev %s: type=%x, flags=%llx\n", msg,
rq->rq_disk ? rq->rq_disk->disk_name : "?", rq->cmd_type,
(unsigned long long) rq->cmd_flags);
@@ -171,13 +167,6 @@ void blk_dump_rq_flags(struct request *rq, char *msg)
blk_rq_sectors(rq), blk_rq_cur_sectors(rq));
printk(KERN_INFO " bio %p, biotail %p, len %u\n",
rq->bio, rq->biotail, blk_rq_bytes(rq));
-
- if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
- printk(KERN_INFO " cdb: ");
- for (bit = 0; bit < BLK_MAX_CDB; bit++)
- printk("%02x ", rq->cmd[bit]);
- printk("\n");
- }
}
EXPORT_SYMBOL(blk_dump_rq_flags);
@@ -1316,18 +1305,6 @@ struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
EXPORT_SYMBOL(blk_get_request);
/**
- * blk_rq_set_block_pc - initialize a request to type BLOCK_PC
- * @rq: request to be initialized
- *
- */
-void blk_rq_set_block_pc(struct request *rq)
-{
- rq->cmd_type = REQ_TYPE_BLOCK_PC;
- memset(rq->__cmd, 0, sizeof(rq->__cmd));
-}
-EXPORT_SYMBOL(blk_rq_set_block_pc);
-
-/**
* blk_requeue_request - put a request back on queue
* @q: request queue where request should be inserted
* @rq: request to be inserted
@@ -2459,14 +2436,6 @@ void blk_start_request(struct request *req)
wbt_issue(req->q->rq_wb, &req->issue_stat);
}
- /*
- * We are now handing the request to the hardware, initialize
- * resid_len to full count and add the timeout handler.
- */
- req->resid_len = blk_rq_bytes(req);
- if (unlikely(blk_bidi_rq(req)))
- req->next_rq->resid_len = blk_rq_bytes(req->next_rq);
-
BUG_ON(test_bit(REQ_ATOM_COMPLETE, &req->atomic_flags));
blk_add_timer(req);
}
diff --git a/block/blk-exec.c b/block/blk-exec.c
index 86656fd..8dd4a6d 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -101,16 +101,9 @@ int blk_execute_rq(struct request_queue *q, struct gendisk *bd_disk,
struct request *rq, int at_head)
{
DECLARE_COMPLETION_ONSTACK(wait);
- char sense[SCSI_SENSE_BUFFERSIZE];
int err = 0;
unsigned long hang_check;
- if (!rq->sense) {
- memset(sense, 0, sizeof(sense));
- rq->sense = sense;
- rq->sense_len = 0;
- }
-
rq->end_io_data = &wait;
blk_execute_rq_nowait(q, bd_disk, rq, at_head, blk_end_sync_rq);
@@ -124,11 +117,6 @@ int blk_execute_rq(struct request_queue *q, struct gendisk *bd_disk,
if (rq->errors)
err = -EIO;
- if (rq->sense == sense) {
- rq->sense = NULL;
- rq->sense_len = 0;
- }
-
return err;
}
EXPORT_SYMBOL(blk_execute_rq);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index e229f8a..8364086 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -199,13 +199,7 @@ void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
rq->special = NULL;
/* tag was already set */
rq->errors = 0;
-
- rq->cmd = rq->__cmd;
-
rq->extra_len = 0;
- rq->sense_len = 0;
- rq->resid_len = 0;
- rq->sense = NULL;
INIT_LIST_HEAD(&rq->timeout_list);
rq->timeout = 0;
@@ -487,10 +481,6 @@ void blk_mq_start_request(struct request *rq)
trace_block_rq_issue(q, rq);
- rq->resid_len = blk_rq_bytes(rq);
- if (unlikely(blk_bidi_rq(rq)))
- rq->next_rq->resid_len = blk_rq_bytes(rq->next_rq);
-
if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
blk_stat_set_issue_time(&rq->issue_stat);
rq->rq_flags |= RQF_STATS;
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index c74acf4..cd15f9d 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -71,22 +71,24 @@ void bsg_job_done(struct bsg_job *job, int result,
{
struct request *req = job->req;
struct request *rsp = req->next_rq;
+ struct scsi_request *rq = scsi_req(req);
int err;
err = job->req->errors = result;
if (err < 0)
/* we're only returning the result field in the reply */
- job->req->sense_len = sizeof(u32);
+ rq->sense_len = sizeof(u32);
else
- job->req->sense_len = job->reply_len;
+ rq->sense_len = job->reply_len;
/* we assume all request payload was transferred, residual == 0 */
- req->resid_len = 0;
+ rq->resid_len = 0;
if (rsp) {
- WARN_ON(reply_payload_rcv_len > rsp->resid_len);
+ WARN_ON(reply_payload_rcv_len > scsi_req(rsp)->resid_len);
/* set reply (bidi) residual */
- rsp->resid_len -= min(reply_payload_rcv_len, rsp->resid_len);
+ scsi_req(rsp)->resid_len -=
+ min(reply_payload_rcv_len, scsi_req(rsp)->resid_len);
}
blk_complete_request(req);
}
@@ -113,6 +115,7 @@ static int bsg_map_buffer(struct bsg_buffer *buf, struct request *req)
if (!buf->sg_list)
return -ENOMEM;
sg_init_table(buf->sg_list, req->nr_phys_segments);
+ scsi_req(req)->resid_len = blk_rq_bytes(req);
buf->sg_cnt = blk_rq_map_sg(req->q, req, buf->sg_list);
buf->payload_len = blk_rq_bytes(req);
return 0;
@@ -127,6 +130,7 @@ static int bsg_create_job(struct device *dev, struct request *req)
{
struct request *rsp = req->next_rq;
struct request_queue *q = req->q;
+ struct scsi_request *rq = scsi_req(req);
struct bsg_job *job;
int ret;
@@ -140,9 +144,9 @@ static int bsg_create_job(struct device *dev, struct request *req)
job->req = req;
if (q->bsg_job_size)
job->dd_data = (void *)&job[1];
- job->request = req->cmd;
- job->request_len = req->cmd_len;
- job->reply = req->sense;
+ job->request = rq->cmd;
+ job->request_len = rq->cmd_len;
+ job->reply = rq->sense;
job->reply_len = SCSI_SENSE_BUFFERSIZE; /* Size of sense buffer
* allocated */
if (req->bio) {
@@ -228,9 +232,15 @@ struct request_queue *bsg_setup_queue(struct device *dev, char *name,
struct request_queue *q;
int ret;
- q = blk_init_queue(bsg_request_fn, NULL);
+ q = blk_alloc_queue(GFP_KERNEL);
if (!q)
return ERR_PTR(-ENOMEM);
+ q->cmd_size = sizeof(struct scsi_request);
+ q->request_fn = bsg_request_fn;
+
+ ret = blk_init_allocated_queue(q);
+ if (ret)
+ goto out_cleanup_queue;
q->queuedata = dev;
q->bsg_job_size = dd_job_size;
@@ -243,10 +253,12 @@ struct request_queue *bsg_setup_queue(struct device *dev, char *name,
if (ret) {
printk(KERN_ERR "%s: bsg interface failed to "
"initialize - register queue\n", dev->kobj.name);
- blk_cleanup_queue(q);
- return ERR_PTR(ret);
+ goto out_cleanup_queue;
}
return q;
+out_cleanup_queue:
+ blk_cleanup_queue(q);
+ return ERR_PTR(ret);
}
EXPORT_SYMBOL_GPL(bsg_setup_queue);
diff --git a/block/bsg.c b/block/bsg.c
index a57046d..e34c332 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -85,7 +85,6 @@ struct bsg_command {
struct bio *bidi_bio;
int err;
struct sg_io_v4 hdr;
- char sense[SCSI_SENSE_BUFFERSIZE];
};
static void bsg_free_command(struct bsg_command *bc)
@@ -140,18 +139,20 @@ static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq,
struct sg_io_v4 *hdr, struct bsg_device *bd,
fmode_t has_write_perm)
{
+ struct scsi_request *req = scsi_req(rq);
+
if (hdr->request_len > BLK_MAX_CDB) {
- rq->cmd = kzalloc(hdr->request_len, GFP_KERNEL);
- if (!rq->cmd)
+ req->cmd = kzalloc(hdr->request_len, GFP_KERNEL);
+ if (!req->cmd)
return -ENOMEM;
}
- if (copy_from_user(rq->cmd, (void __user *)(unsigned long)hdr->request,
+ if (copy_from_user(req->cmd, (void __user *)(unsigned long)hdr->request,
hdr->request_len))
return -EFAULT;
if (hdr->subprotocol == BSG_SUB_PROTOCOL_SCSI_CMD) {
- if (blk_verify_command(rq->cmd, has_write_perm))
+ if (blk_verify_command(req->cmd, has_write_perm))
return -EPERM;
} else if (!capable(CAP_SYS_RAWIO))
return -EPERM;
@@ -159,7 +160,7 @@ static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq,
/*
* fill in request structure
*/
- rq->cmd_len = hdr->request_len;
+ req->cmd_len = hdr->request_len;
rq->timeout = msecs_to_jiffies(hdr->timeout);
if (!rq->timeout)
@@ -205,8 +206,7 @@ bsg_validate_sgv4_hdr(struct sg_io_v4 *hdr, int *rw)
* map sg_io_v4 to a request.
*/
static struct request *
-bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm,
- u8 *sense)
+bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm)
{
struct request_queue *q = bd->queue;
struct request *rq, *next_rq = NULL;
@@ -236,7 +236,7 @@ bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm,
rq = blk_get_request(q, rw, GFP_KERNEL);
if (IS_ERR(rq))
return rq;
- blk_rq_set_block_pc(rq);
+ scsi_req_init(rq);
ret = blk_fill_sgv4_hdr_rq(q, rq, hdr, bd, has_write_perm);
if (ret)
@@ -280,13 +280,9 @@ bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm,
goto out;
}
- rq->sense = sense;
- rq->sense_len = 0;
-
return rq;
out:
- if (rq->cmd != rq->__cmd)
- kfree(rq->cmd);
+ scsi_req_free_cmd(scsi_req(rq));
blk_put_request(rq);
if (next_rq) {
blk_rq_unmap_user(next_rq->bio);
@@ -393,6 +389,7 @@ static struct bsg_command *bsg_get_done_cmd(struct bsg_device *bd)
static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
struct bio *bio, struct bio *bidi_bio)
{
+ struct scsi_request *req = scsi_req(rq);
int ret = 0;
dprintk("rq %p bio %p 0x%x\n", rq, bio, rq->errors);
@@ -407,12 +404,12 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
hdr->info |= SG_INFO_CHECK;
hdr->response_len = 0;
- if (rq->sense_len && hdr->response) {
+ if (req->sense_len && hdr->response) {
int len = min_t(unsigned int, hdr->max_response_len,
- rq->sense_len);
+ req->sense_len);
ret = copy_to_user((void __user *)(unsigned long)hdr->response,
- rq->sense, len);
+ req->sense, len);
if (!ret)
hdr->response_len = len;
else
@@ -420,14 +417,14 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
}
if (rq->next_rq) {
- hdr->dout_resid = rq->resid_len;
- hdr->din_resid = rq->next_rq->resid_len;
+ hdr->dout_resid = req->resid_len;
+ hdr->din_resid = scsi_req(rq->next_rq)->resid_len;
blk_rq_unmap_user(bidi_bio);
blk_put_request(rq->next_rq);
} else if (rq_data_dir(rq) == READ)
- hdr->din_resid = rq->resid_len;
+ hdr->din_resid = req->resid_len;
else
- hdr->dout_resid = rq->resid_len;
+ hdr->dout_resid = req->resid_len;
/*
* If the request generated a negative error number, return it
@@ -439,8 +436,7 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
ret = rq->errors;
blk_rq_unmap_user(bio);
- if (rq->cmd != rq->__cmd)
- kfree(rq->cmd);
+ scsi_req_free_cmd(req);
blk_put_request(rq);
return ret;
@@ -625,7 +621,7 @@ static int __bsg_write(struct bsg_device *bd, const char __user *buf,
/*
* get a request, fill in the blanks, and add to request queue
*/
- rq = bsg_map_hdr(bd, &bc->hdr, has_write_perm, bc->sense);
+ rq = bsg_map_hdr(bd, &bc->hdr, has_write_perm);
if (IS_ERR(rq)) {
ret = PTR_ERR(rq);
rq = NULL;
@@ -911,12 +907,11 @@ static long bsg_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
struct bio *bio, *bidi_bio = NULL;
struct sg_io_v4 hdr;
int at_head;
- u8 sense[SCSI_SENSE_BUFFERSIZE];
if (copy_from_user(&hdr, uarg, sizeof(hdr)))
return -EFAULT;
- rq = bsg_map_hdr(bd, &hdr, file->f_mode & FMODE_WRITE, sense);
+ rq = bsg_map_hdr(bd, &hdr, file->f_mode & FMODE_WRITE);
if (IS_ERR(rq))
return PTR_ERR(rq);
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index c2b6492..e542144 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -230,15 +230,17 @@ EXPORT_SYMBOL(blk_verify_command);
static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq,
struct sg_io_hdr *hdr, fmode_t mode)
{
- if (copy_from_user(rq->cmd, hdr->cmdp, hdr->cmd_len))
+ struct scsi_request *req = scsi_req(rq);
+
+ if (copy_from_user(req->cmd, hdr->cmdp, hdr->cmd_len))
return -EFAULT;
- if (blk_verify_command(rq->cmd, mode & FMODE_WRITE))
+ if (blk_verify_command(req->cmd, mode & FMODE_WRITE))
return -EPERM;
/*
* fill in request structure
*/
- rq->cmd_len = hdr->cmd_len;
+ req->cmd_len = hdr->cmd_len;
rq->timeout = msecs_to_jiffies(hdr->timeout);
if (!rq->timeout)
@@ -254,6 +256,7 @@ static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq,
static int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr,
struct bio *bio)
{
+ struct scsi_request *req = scsi_req(rq);
int r, ret = 0;
/*
@@ -267,13 +270,13 @@ static int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr,
hdr->info = 0;
if (hdr->masked_status || hdr->host_status || hdr->driver_status)
hdr->info |= SG_INFO_CHECK;
- hdr->resid = rq->resid_len;
+ hdr->resid = req->resid_len;
hdr->sb_len_wr = 0;
- if (rq->sense_len && hdr->sbp) {
- int len = min((unsigned int) hdr->mx_sb_len, rq->sense_len);
+ if (req->sense_len && hdr->sbp) {
+ int len = min((unsigned int) hdr->mx_sb_len, req->sense_len);
- if (!copy_to_user(hdr->sbp, rq->sense, len))
+ if (!copy_to_user(hdr->sbp, req->sense, len))
hdr->sb_len_wr = len;
else
ret = -EFAULT;
@@ -294,7 +297,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
int writing = 0;
int at_head = 0;
struct request *rq;
- char sense[SCSI_SENSE_BUFFERSIZE];
+ struct scsi_request *req;
struct bio *bio;
if (hdr->interface_id != 'S')
@@ -321,11 +324,12 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
rq = blk_get_request(q, writing ? WRITE : READ, GFP_KERNEL);
if (IS_ERR(rq))
return PTR_ERR(rq);
- blk_rq_set_block_pc(rq);
+ req = scsi_req(rq);
+ scsi_req_init(rq);
if (hdr->cmd_len > BLK_MAX_CDB) {
- rq->cmd = kzalloc(hdr->cmd_len, GFP_KERNEL);
- if (!rq->cmd)
+ req->cmd = kzalloc(hdr->cmd_len, GFP_KERNEL);
+ if (!req->cmd)
goto out_put_request;
}
@@ -357,9 +361,6 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
goto out_free_cdb;
bio = rq->bio;
- memset(sense, 0, sizeof(sense));
- rq->sense = sense;
- rq->sense_len = 0;
rq->retries = 0;
start_time = jiffies;
@@ -375,8 +376,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
ret = blk_complete_sghdr_rq(rq, hdr, bio);
out_free_cdb:
- if (rq->cmd != rq->__cmd)
- kfree(rq->cmd);
+ scsi_req_free_cmd(req);
out_put_request:
blk_put_request(rq);
return ret;
@@ -420,9 +420,10 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
struct scsi_ioctl_command __user *sic)
{
struct request *rq;
+ struct scsi_request *req;
int err;
unsigned int in_len, out_len, bytes, opcode, cmdlen;
- char *buffer = NULL, sense[SCSI_SENSE_BUFFERSIZE];
+ char *buffer = NULL;
if (!sic)
return -EINVAL;
@@ -452,7 +453,8 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
err = PTR_ERR(rq);
goto error_free_buffer;
}
- blk_rq_set_block_pc(rq);
+ req = scsi_req(rq);
+ scsi_req_init(rq);
cmdlen = COMMAND_SIZE(opcode);
@@ -460,14 +462,14 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
* get command and data to send to device, if any
*/
err = -EFAULT;
- rq->cmd_len = cmdlen;
- if (copy_from_user(rq->cmd, sic->data, cmdlen))
+ req->cmd_len = cmdlen;
+ if (copy_from_user(req->cmd, sic->data, cmdlen))
goto error;
if (in_len && copy_from_user(buffer, sic->data + cmdlen, in_len))
goto error;
- err = blk_verify_command(rq->cmd, mode & FMODE_WRITE);
+ err = blk_verify_command(req->cmd, mode & FMODE_WRITE);
if (err)
goto error;
@@ -503,18 +505,14 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
goto error;
}
- memset(sense, 0, sizeof(sense));
- rq->sense = sense;
- rq->sense_len = 0;
-
blk_execute_rq(q, disk, rq, 0);
err = rq->errors & 0xff; /* only 8 bit SCSI status */
if (err) {
- if (rq->sense_len && rq->sense) {
- bytes = (OMAX_SB_LEN > rq->sense_len) ?
- rq->sense_len : OMAX_SB_LEN;
- if (copy_to_user(sic->data, rq->sense, bytes))
+ if (req->sense_len && req->sense) {
+ bytes = (OMAX_SB_LEN > req->sense_len) ?
+ req->sense_len : OMAX_SB_LEN;
+ if (copy_to_user(sic->data, req->sense, bytes))
err = -EFAULT;
}
} else {
@@ -542,11 +540,11 @@ static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk,
rq = blk_get_request(q, WRITE, __GFP_RECLAIM);
if (IS_ERR(rq))
return PTR_ERR(rq);
- blk_rq_set_block_pc(rq);
+ scsi_req_init(rq);
rq->timeout = BLK_DEFAULT_SG_TIMEOUT;
- rq->cmd[0] = cmd;
- rq->cmd[4] = data;
- rq->cmd_len = 6;
+ scsi_req(rq)->cmd[0] = cmd;
+ scsi_req(rq)->cmd[4] = data;
+ scsi_req(rq)->cmd_len = 6;
err = blk_execute_rq(q, bd_disk, rq, 0);
blk_put_request(rq);
@@ -743,6 +741,29 @@ int scsi_cmd_blk_ioctl(struct block_device *bd, fmode_t mode,
}
EXPORT_SYMBOL(scsi_cmd_blk_ioctl);
+/**
+ * scsi_req_init - initialize a request to type BLOCK_PC
+ * @rq: request to be initialized
+ *
+ */
+void scsi_req_init(struct request *rq)
+{
+ struct scsi_request *req = scsi_req(rq);
+
+ rq->cmd_type = REQ_TYPE_BLOCK_PC;
+ memset(req->__cmd, 0, sizeof(req->__cmd));
+ req->cmd = req->__cmd;
+ req->cmd_len = BLK_MAX_CDB;
+ req->sense_len = 0;
+}
+EXPORT_SYMBOL(scsi_req_init);
+
+int scsi_cmd_buf_len(struct request *rq)
+{
+ return scsi_req(rq)->cmd_len * 3;
+}
+EXPORT_SYMBOL(scsi_cmd_buf_len);
+
static int __init blk_scsi_ioctl_init(void)
{
blk_set_cmd_filter_defaults(&blk_default_cmd_filter);
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 1f863e7..6abd739 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -1271,7 +1271,7 @@ static int atapi_drain_needed(struct request *rq)
if (!blk_rq_bytes(rq) || op_is_write(req_op(rq)))
return 0;
- return atapi_cmd_type(rq->cmd[0]) == ATAPI_MISC;
+ return atapi_cmd_type(scsi_req(rq)->cmd[0]) == ATAPI_MISC;
}
static int ata_scsi_dev_config(struct scsi_device *sdev,
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index e5c5b8e..b93bb73 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -52,6 +52,7 @@
#include <scsi/scsi.h>
#include <scsi/sg.h>
#include <scsi/scsi_ioctl.h>
+#include <scsi/scsi_request.h>
#include <linux/cdrom.h>
#include <linux/scatterlist.h>
#include <linux/kthread.h>
@@ -1854,7 +1855,7 @@ static void cciss_softirq_done(struct request *rq)
/* set the residual count for pc requests */
if (rq->cmd_type == REQ_TYPE_BLOCK_PC)
- rq->resid_len = c->err_info->ResidualCnt;
+ scsi_req(rq)->resid_len = c->err_info->ResidualCnt;
blk_end_request_all(rq, (rq->errors == 0) ? 0 : -EIO);
@@ -1941,9 +1942,16 @@ static void cciss_get_serial_no(ctlr_info_t *h, int logvol,
static int cciss_add_disk(ctlr_info_t *h, struct gendisk *disk,
int drv_index)
{
- disk->queue = blk_init_queue(do_cciss_request, &h->lock);
+ disk->queue = blk_alloc_queue(GFP_KERNEL);
if (!disk->queue)
goto init_queue_failure;
+
+ disk->queue->cmd_size = sizeof(struct scsi_request);
+ disk->queue->request_fn = do_cciss_request;
+ disk->queue->queue_lock = &h->lock;
+ if (blk_init_allocated_queue(disk->queue) < 0)
+ goto cleanup_queue;
+
sprintf(disk->disk_name, "cciss/c%dd%d", h->ctlr, drv_index);
disk->major = h->major;
disk->first_minor = drv_index << NWD_SHIFT;
@@ -3111,15 +3119,7 @@ static inline int evaluate_target_status(ctlr_info_t *h,
return error_value;
}
- /* SG_IO or similar, copy sense data back */
- if (cmd->rq->sense) {
- if (cmd->rq->sense_len > cmd->err_info->SenseLen)
- cmd->rq->sense_len = cmd->err_info->SenseLen;
- memcpy(cmd->rq->sense, cmd->err_info->SenseInfo,
- cmd->rq->sense_len);
- } else
- cmd->rq->sense_len = 0;
-
+ scsi_req(cmd->rq)->sense_len = cmd->err_info->SenseLen;
return error_value;
}
@@ -3150,7 +3150,6 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
dev_warn(&h->pdev->dev, "cmd %p has"
" completed with data underrun "
"reported\n", cmd);
- cmd->rq->resid_len = cmd->err_info->ResidualCnt;
}
break;
case CMD_DATA_OVERRUN:
@@ -3426,8 +3425,9 @@ static void do_cciss_request(struct request_queue *q)
c->Request.CDB[14] = c->Request.CDB[15] = 0;
}
} else if (creq->cmd_type == REQ_TYPE_BLOCK_PC) {
- c->Request.CDBLen = creq->cmd_len;
- memcpy(c->Request.CDB, creq->cmd, BLK_MAX_CDB);
+ c->Request.CDBLen = scsi_req(creq)->cmd_len;
+ memcpy(c->Request.CDB, scsi_req(creq)->cmd, BLK_MAX_CDB);
+ scsi_req(creq)->sense = c->err_info->SenseInfo;
} else {
dev_warn(&h->pdev->dev, "bad request type %d\n",
creq->cmd_type);
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 1b94c1c..918a92c 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -707,7 +707,7 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *
WRITE : READ, __GFP_RECLAIM);
if (IS_ERR(rq))
return PTR_ERR(rq);
- blk_rq_set_block_pc(rq);
+ scsi_req_init(rq);
if (cgc->buflen) {
ret = blk_rq_map_kern(q, rq, cgc->buffer, cgc->buflen,
@@ -716,8 +716,8 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *
goto out;
}
- rq->cmd_len = COMMAND_SIZE(cgc->cmd[0]);
- memcpy(rq->cmd, cgc->cmd, CDROM_PACKET_SIZE);
+ scsi_req(rq)->cmd_len = COMMAND_SIZE(cgc->cmd[0]);
+ memcpy(scsi_req(rq)->cmd, cgc->cmd, CDROM_PACKET_SIZE);
rq->timeout = 60*HZ;
if (cgc->quiet)
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 10332c2..3027d2e 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -52,6 +52,7 @@ struct virtio_blk {
};
struct virtblk_req {
+ struct scsi_request sreq; /* for SCSI passthrough */
struct request *req;
struct virtio_blk_outhdr out_hdr;
struct virtio_scsi_inhdr in_hdr;
@@ -91,7 +92,7 @@ static int __virtblk_add_req(struct virtqueue *vq,
* inhdr with additional status information.
*/
if (type == cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_SCSI_CMD)) {
- sg_init_one(&cmd, vbr->req->cmd, vbr->req->cmd_len);
+ sg_init_one(&cmd, vbr->sreq.cmd, vbr->sreq.cmd_len);
sgs[num_out++] = &cmd;
}
@@ -103,7 +104,6 @@ static int __virtblk_add_req(struct virtqueue *vq,
}
if (type == cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_SCSI_CMD)) {
- memcpy(vbr->sense, vbr->req->sense, SCSI_SENSE_BUFFERSIZE);
sg_init_one(&sense, vbr->sense, SCSI_SENSE_BUFFERSIZE);
sgs[num_out + num_in++] = &sense;
sg_init_one(&inhdr, &vbr->in_hdr, sizeof(vbr->in_hdr));
@@ -123,8 +123,10 @@ static inline void virtblk_request_done(struct request *req)
int error = virtblk_result(vbr);
if (req->cmd_type == REQ_TYPE_BLOCK_PC) {
- req->resid_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.residual);
- req->sense_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.sense_len);
+ scsi_req(req)->resid_len =
+ virtio32_to_cpu(vblk->vdev, vbr->in_hdr.residual);
+ vbr->sreq.sense_len =
+ virtio32_to_cpu(vblk->vdev, vbr->in_hdr.sense_len);
req->errors = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.errors);
} else if (req->cmd_type == REQ_TYPE_DRV_PRIV) {
req->errors = (error != 0);
@@ -538,6 +540,7 @@ static int virtblk_init_request(void *data, struct request *rq,
struct virtio_blk *vblk = data;
struct virtblk_req *vbr = blk_mq_rq_to_pdu(rq);
+ vbr->sreq.sense = vbr->sense;
sg_init_table(vbr->sg, vblk->sg_elems);
return 0;
}
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index 59cca72..36f5237 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -281,8 +281,8 @@
#include <linux/fcntl.h>
#include <linux/blkdev.h>
#include <linux/times.h>
-
#include <linux/uaccess.h>
+#include <scsi/scsi_request.h>
/* used to tell the module to turn on full debugging messages */
static bool debug;
@@ -2172,6 +2172,7 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf,
{
struct request_queue *q = cdi->disk->queue;
struct request *rq;
+ struct scsi_request *req;
struct bio *bio;
unsigned int len;
int nr, ret = 0;
@@ -2195,7 +2196,8 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf,
ret = PTR_ERR(rq);
break;
}
- blk_rq_set_block_pc(rq);
+ req = scsi_req(rq);
+ scsi_req_init(rq);
ret = blk_rq_map_user(q, rq, NULL, ubuf, len, GFP_KERNEL);
if (ret) {
@@ -2203,23 +2205,23 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf,
break;
}
- rq->cmd[0] = GPCMD_READ_CD;
- rq->cmd[1] = 1 << 2;
- rq->cmd[2] = (lba >> 24) & 0xff;
- rq->cmd[3] = (lba >> 16) & 0xff;
- rq->cmd[4] = (lba >> 8) & 0xff;
- rq->cmd[5] = lba & 0xff;
- rq->cmd[6] = (nr >> 16) & 0xff;
- rq->cmd[7] = (nr >> 8) & 0xff;
- rq->cmd[8] = nr & 0xff;
- rq->cmd[9] = 0xf8;
-
- rq->cmd_len = 12;
+ req->cmd[0] = GPCMD_READ_CD;
+ req->cmd[1] = 1 << 2;
+ req->cmd[2] = (lba >> 24) & 0xff;
+ req->cmd[3] = (lba >> 16) & 0xff;
+ req->cmd[4] = (lba >> 8) & 0xff;
+ req->cmd[5] = lba & 0xff;
+ req->cmd[6] = (nr >> 16) & 0xff;
+ req->cmd[7] = (nr >> 8) & 0xff;
+ req->cmd[8] = nr & 0xff;
+ req->cmd[9] = 0xf8;
+
+ req->cmd_len = 12;
rq->timeout = 60 * HZ;
bio = rq->bio;
if (blk_execute_rq(q, cdi->disk, rq, 0)) {
- struct request_sense *s = rq->sense;
+ struct request_sense *s = req->sense;
ret = -EIO;
cdi->last_sense = s->sense_key;
}
diff --git a/drivers/ide/ide-atapi.c b/drivers/ide/ide-atapi.c
index f90ea22..7c826ec 100644
--- a/drivers/ide/ide-atapi.c
+++ b/drivers/ide/ide-atapi.c
@@ -93,6 +93,7 @@ int ide_queue_pc_tail(ide_drive_t *drive, struct gendisk *disk,
int error;
rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
+ scsi_req_init(rq);
rq->cmd_type = REQ_TYPE_DRV_PRIV;
rq->special = (char *)pc;
@@ -103,9 +104,9 @@ int ide_queue_pc_tail(ide_drive_t *drive, struct gendisk *disk,
goto put_req;
}
- memcpy(rq->cmd, pc->c, 12);
+ memcpy(scsi_req(rq)->cmd, pc->c, 12);
if (drive->media == ide_tape)
- rq->cmd[13] = REQ_IDETAPE_PC1;
+ scsi_req(rq)->cmd[13] = REQ_IDETAPE_PC1;
error = blk_execute_rq(drive->queue, disk, rq, 0);
put_req:
blk_put_request(rq);
@@ -171,7 +172,8 @@ EXPORT_SYMBOL_GPL(ide_create_request_sense_cmd);
void ide_prep_sense(ide_drive_t *drive, struct request *rq)
{
struct request_sense *sense = &drive->sense_data;
- struct request *sense_rq = &drive->sense_rq;
+ struct request *sense_rq = drive->sense_rq;
+ struct scsi_request *req = scsi_req(sense_rq);
unsigned int cmd_len, sense_len;
int err;
@@ -197,6 +199,7 @@ void ide_prep_sense(ide_drive_t *drive, struct request *rq)
memset(sense, 0, sizeof(*sense));
blk_rq_init(rq->q, sense_rq);
+ scsi_req_init(sense_rq);
err = blk_rq_map_kern(drive->queue, sense_rq, sense, sense_len,
GFP_NOIO);
@@ -208,13 +211,13 @@ void ide_prep_sense(ide_drive_t *drive, struct request *rq)
}
sense_rq->rq_disk = rq->rq_disk;
- sense_rq->cmd[0] = GPCMD_REQUEST_SENSE;
- sense_rq->cmd[4] = cmd_len;
sense_rq->cmd_type = REQ_TYPE_ATA_SENSE;
sense_rq->rq_flags |= RQF_PREEMPT;
+ req->cmd[0] = GPCMD_REQUEST_SENSE;
+ req->cmd[4] = cmd_len;
if (drive->media == ide_tape)
- sense_rq->cmd[13] = REQ_IDETAPE_PC1;
+ req->cmd[13] = REQ_IDETAPE_PC1;
drive->sense_rq_armed = true;
}
@@ -229,12 +232,12 @@ int ide_queue_sense_rq(ide_drive_t *drive, void *special)
return -ENOMEM;
}
- drive->sense_rq.special = special;
+ drive->sense_rq->special = special;
drive->sense_rq_armed = false;
drive->hwif->rq = NULL;
- elv_add_request(drive->queue, &drive->sense_rq, ELEVATOR_INSERT_FRONT);
+ elv_add_request(drive->queue, drive->sense_rq, ELEVATOR_INSERT_FRONT);
return 0;
}
EXPORT_SYMBOL_GPL(ide_queue_sense_rq);
@@ -247,14 +250,14 @@ EXPORT_SYMBOL_GPL(ide_queue_sense_rq);
void ide_retry_pc(ide_drive_t *drive)
{
struct request *failed_rq = drive->hwif->rq;
- struct request *sense_rq = &drive->sense_rq;
+ struct request *sense_rq = drive->sense_rq;
struct ide_atapi_pc *pc = &drive->request_sense_pc;
(void)ide_read_error(drive);
/* init pc from sense_rq */
ide_init_pc(pc);
- memcpy(pc->c, sense_rq->cmd, 12);
+ memcpy(pc->c, scsi_req(sense_rq)->cmd, 12);
if (drive->media == ide_tape)
drive->atapi_flags |= IDE_AFLAG_IGNORE_DSC;
@@ -286,7 +289,7 @@ int ide_cd_expiry(ide_drive_t *drive)
* commands/drives support that. Let ide_timer_expiry keep polling us
* for these.
*/
- switch (rq->cmd[0]) {
+ switch (scsi_req(rq)->cmd[0]) {
case GPCMD_BLANK:
case GPCMD_FORMAT_UNIT:
case GPCMD_RESERVE_RZONE_TRACK:
@@ -297,7 +300,7 @@ int ide_cd_expiry(ide_drive_t *drive)
default:
if (!(rq->rq_flags & RQF_QUIET))
printk(KERN_INFO PFX "cmd 0x%x timed out\n",
- rq->cmd[0]);
+ scsi_req(rq)->cmd[0]);
wait = 0;
break;
}
@@ -420,7 +423,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
? "write" : "read");
pc->flags |= PC_FLAG_DMA_ERROR;
} else
- rq->resid_len = 0;
+ scsi_req(rq)->resid_len = 0;
debug_log("%s: DMA finished\n", drive->name);
}
@@ -436,7 +439,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
local_irq_enable_in_hardirq();
if (drive->media == ide_tape &&
- (stat & ATA_ERR) && rq->cmd[0] == REQUEST_SENSE)
+ (stat & ATA_ERR) && scsi_req(rq)->cmd[0] == REQUEST_SENSE)
stat &= ~ATA_ERR;
if ((stat & ATA_ERR) || (pc->flags & PC_FLAG_DMA_ERROR)) {
@@ -446,7 +449,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
if (drive->media != ide_tape)
pc->rq->errors++;
- if (rq->cmd[0] == REQUEST_SENSE) {
+ if (scsi_req(rq)->cmd[0] == REQUEST_SENSE) {
printk(KERN_ERR PFX "%s: I/O error in request "
"sense command\n", drive->name);
return ide_do_reset(drive);
@@ -512,7 +515,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
ide_pio_bytes(drive, cmd, write, done);
/* Update transferred byte count */
- rq->resid_len -= done;
+ scsi_req(rq)->resid_len -= done;
bcount -= done;
@@ -520,7 +523,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
ide_pad_transfer(drive, write, bcount);
debug_log("[cmd %x] transferred %d bytes, padded %d bytes, resid: %u\n",
- rq->cmd[0], done, bcount, rq->resid_len);
+ rq->cmd[0], done, bcount, scsi_req(rq)->resid_len);
/* And set the interrupt handler again */
ide_set_handler(drive, ide_pc_intr, timeout);
@@ -603,7 +606,7 @@ static ide_startstop_t ide_transfer_pc(ide_drive_t *drive)
if (dev_is_idecd(drive)) {
/* ATAPI commands get padded out to 12 bytes minimum */
- cmd_len = COMMAND_SIZE(rq->cmd[0]);
+ cmd_len = COMMAND_SIZE(scsi_req(rq)->cmd[0]);
if (cmd_len < ATAPI_MIN_CDB_BYTES)
cmd_len = ATAPI_MIN_CDB_BYTES;
@@ -650,7 +653,7 @@ static ide_startstop_t ide_transfer_pc(ide_drive_t *drive)
/* Send the actual packet */
if ((drive->atapi_flags & IDE_AFLAG_ZIP_DRIVE) == 0)
- hwif->tp_ops->output_data(drive, NULL, rq->cmd, cmd_len);
+ hwif->tp_ops->output_data(drive, NULL, scsi_req(rq)->cmd, cmd_len);
/* Begin DMA, if necessary */
if (dev_is_idecd(drive)) {
@@ -695,7 +698,7 @@ ide_startstop_t ide_issue_pc(ide_drive_t *drive, struct ide_cmd *cmd)
bytes, 63 * 1024));
/* We haven't transferred any data yet */
- rq->resid_len = bcount;
+ scsi_req(rq)->resid_len = bcount;
if (pc->flags & PC_FLAG_DMA_ERROR) {
pc->flags &= ~PC_FLAG_DMA_ERROR;
diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index 9cbd217..6eb9872 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -121,7 +121,7 @@ static int cdrom_log_sense(ide_drive_t *drive, struct request *rq)
* don't log START_STOP unit with LoEj set, since we cannot
* reliably check if drive can auto-close
*/
- if (rq->cmd[0] == GPCMD_START_STOP_UNIT && sense->asc == 0x24)
+ if (scsi_req(rq)->cmd[0] == GPCMD_START_STOP_UNIT && sense->asc == 0x24)
break;
log = 1;
break;
@@ -163,7 +163,7 @@ static void cdrom_analyze_sense_data(ide_drive_t *drive,
* toc has not been recorded yet, it will fail with 05/24/00 (which is a
* confusing error)
*/
- if (failed_command && failed_command->cmd[0] == GPCMD_READ_TOC_PMA_ATIP)
+ if (failed_command && scsi_req(failed_command)->cmd[0] == GPCMD_READ_TOC_PMA_ATIP)
if (sense->sense_key == 0x05 && sense->asc == 0x24)
return;
@@ -219,15 +219,12 @@ static void ide_cd_complete_failed_rq(ide_drive_t *drive, struct request *rq)
void *sense = bio_data(rq->bio);
if (failed) {
- if (failed->sense) {
- /*
- * Sense is always read into drive->sense_data.
- * Copy back if the failed request has its
- * sense pointer set.
- */
- memcpy(failed->sense, sense, 18);
- failed->sense_len = rq->sense_len;
- }
+ /*
+ * Sense is always read into drive->sense_data, copy back to the
+ * original request.
+ */
+ memcpy(scsi_req(failed)->sense, sense, 18);
+ scsi_req(failed)->sense_len = scsi_req(rq)->sense_len;
cdrom_analyze_sense_data(drive, failed);
if (ide_end_rq(drive, failed, -EIO, blk_rq_bytes(failed)))
@@ -338,7 +335,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat)
*
* cdrom_log_sense() knows this!
*/
- if (rq->cmd[0] == GPCMD_START_STOP_UNIT)
+ if (scsi_req(rq)->cmd[0] == GPCMD_START_STOP_UNIT)
break;
/* fall-through */
case DATA_PROTECT:
@@ -414,7 +411,7 @@ static void ide_cd_request_sense_fixup(ide_drive_t *drive, struct ide_cmd *cmd)
* Some of the trailing request sense fields are optional,
* and some drives don't send them. Sigh.
*/
- if (rq->cmd[0] == GPCMD_REQUEST_SENSE &&
+ if (scsi_req(rq)->cmd[0] == GPCMD_REQUEST_SENSE &&
cmd->nleft > 0 && cmd->nleft <= 5)
cmd->nleft = 0;
}
@@ -425,12 +422,8 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
req_flags_t rq_flags)
{
struct cdrom_info *info = drive->driver_data;
- struct request_sense local_sense;
int retries = 10;
- req_flags_t flags = 0;
-
- if (!sense)
- sense = &local_sense;
+ bool failed;
ide_debug_log(IDE_DBG_PC, "cmd[0]: 0x%x, write: 0x%x, timeout: %d, "
"rq_flags: 0x%x",
@@ -440,12 +433,12 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
do {
struct request *rq;
int error;
+ bool delay = false;
rq = blk_get_request(drive->queue, write, __GFP_RECLAIM);
-
- memcpy(rq->cmd, cmd, BLK_MAX_CDB);
+ scsi_req_init(rq);
+ memcpy(scsi_req(rq)->cmd, cmd, BLK_MAX_CDB);
rq->cmd_type = REQ_TYPE_ATA_PC;
- rq->sense = sense;
rq->rq_flags |= rq_flags;
rq->timeout = timeout;
if (buffer) {
@@ -460,21 +453,21 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
error = blk_execute_rq(drive->queue, info->disk, rq, 0);
if (buffer)
- *bufflen = rq->resid_len;
-
- flags = rq->rq_flags;
- blk_put_request(rq);
+ *bufflen = scsi_req(rq)->resid_len;
+ if (sense)
+ memcpy(sense, scsi_req(rq)->sense, sizeof(*sense));
/*
* FIXME: we should probably abort/retry or something in case of
* failure.
*/
- if (flags & RQF_FAILED) {
+ failed = (rq->rq_flags & RQF_FAILED) != 0;
+ if (failed) {
/*
* The request failed. Retry if it was due to a unit
* attention status (usually means media was changed).
*/
- struct request_sense *reqbuf = sense;
+ struct request_sense *reqbuf = scsi_req(rq)->sense;
if (reqbuf->sense_key == UNIT_ATTENTION)
cdrom_saw_media_change(drive);
@@ -485,19 +478,20 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
* a disk. Retry, but wait a little to give
* the drive time to complete the load.
*/
- ssleep(2);
+ delay = true;
} else {
/* otherwise, don't retry */
retries = 0;
}
--retries;
}
-
- /* end of retry loop */
- } while ((flags & RQF_FAILED) && retries >= 0);
+ blk_put_request(rq);
+ if (delay)
+ ssleep(2);
+ } while (failed && retries >= 0);
/* return an error if the command failed */
- return (flags & RQF_FAILED) ? -EIO : 0;
+ return failed ? -EIO : 0;
}
/*
@@ -636,7 +630,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
len -= blen;
if (sense && write == 0)
- rq->sense_len += blen;
+ scsi_req(rq)->sense_len += blen;
}
/* pad, if necessary */
@@ -664,7 +658,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
out_end:
if (rq->cmd_type == REQ_TYPE_BLOCK_PC && rc == 0) {
- rq->resid_len = 0;
+ scsi_req(rq)->resid_len = 0;
blk_end_request_all(rq, 0);
hwif->rq = NULL;
} else {
@@ -685,9 +679,9 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
/* make sure it's fully ended */
if (rq->cmd_type != REQ_TYPE_FS) {
- rq->resid_len -= cmd->nbytes - cmd->nleft;
+ scsi_req(rq)->resid_len -= cmd->nbytes - cmd->nleft;
if (uptodate == 0 && (cmd->tf_flags & IDE_TFLAG_WRITE))
- rq->resid_len += cmd->last_xfer_len;
+ scsi_req(rq)->resid_len += cmd->last_xfer_len;
}
ide_complete_rq(drive, uptodate ? 0 : -EIO, blk_rq_bytes(rq));
@@ -1312,28 +1306,29 @@ static int ide_cdrom_prep_fs(struct request_queue *q, struct request *rq)
int hard_sect = queue_logical_block_size(q);
long block = (long)blk_rq_pos(rq) / (hard_sect >> 9);
unsigned long blocks = blk_rq_sectors(rq) / (hard_sect >> 9);
+ struct scsi_request *req = scsi_req(rq);
- memset(rq->cmd, 0, BLK_MAX_CDB);
+ memset(req->cmd, 0, BLK_MAX_CDB);
if (rq_data_dir(rq) == READ)
- rq->cmd[0] = GPCMD_READ_10;
+ req->cmd[0] = GPCMD_READ_10;
else
- rq->cmd[0] = GPCMD_WRITE_10;
+ req->cmd[0] = GPCMD_WRITE_10;
/*
* fill in lba
*/
- rq->cmd[2] = (block >> 24) & 0xff;
- rq->cmd[3] = (block >> 16) & 0xff;
- rq->cmd[4] = (block >> 8) & 0xff;
- rq->cmd[5] = block & 0xff;
+ req->cmd[2] = (block >> 24) & 0xff;
+ req->cmd[3] = (block >> 16) & 0xff;
+ req->cmd[4] = (block >> 8) & 0xff;
+ req->cmd[5] = block & 0xff;
/*
* and transfer length
*/
- rq->cmd[7] = (blocks >> 8) & 0xff;
- rq->cmd[8] = blocks & 0xff;
- rq->cmd_len = 10;
+ req->cmd[7] = (blocks >> 8) & 0xff;
+ req->cmd[8] = blocks & 0xff;
+ req->cmd_len = 10;
return BLKPREP_OK;
}
@@ -1343,7 +1338,7 @@ static int ide_cdrom_prep_fs(struct request_queue *q, struct request *rq)
*/
static int ide_cdrom_prep_pc(struct request *rq)
{
- u8 *c = rq->cmd;
+ u8 *c = scsi_req(rq)->cmd;
/* transform 6-byte read/write commands to the 10-byte version */
if (c[0] == READ_6 || c[0] == WRITE_6) {
@@ -1354,7 +1349,7 @@ static int ide_cdrom_prep_pc(struct request *rq)
c[2] = 0;
c[1] &= 0xe0;
c[0] += (READ_10 - READ_6);
- rq->cmd_len = 10;
+ scsi_req(rq)->cmd_len = 10;
return BLKPREP_OK;
}
diff --git a/drivers/ide/ide-cd_ioctl.c b/drivers/ide/ide-cd_ioctl.c
index f085e3a..da0aa01 100644
--- a/drivers/ide/ide-cd_ioctl.c
+++ b/drivers/ide/ide-cd_ioctl.c
@@ -304,6 +304,7 @@ int ide_cdrom_reset(struct cdrom_device_info *cdi)
int ret;
rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
+ scsi_req_init(rq);
rq->cmd_type = REQ_TYPE_DRV_PRIV;
rq->rq_flags = RQF_QUIET;
ret = blk_execute_rq(drive->queue, cd->disk, rq, 0);
diff --git a/drivers/ide/ide-cd_verbose.c b/drivers/ide/ide-cd_verbose.c
index f079ca2..58a6feb 100644
--- a/drivers/ide/ide-cd_verbose.c
+++ b/drivers/ide/ide-cd_verbose.c
@@ -315,12 +315,12 @@ void ide_cd_log_error(const char *name, struct request *failed_command,
while (hi > lo) {
mid = (lo + hi) / 2;
if (packet_command_texts[mid].packet_command ==
- failed_command->cmd[0]) {
+ scsi_req(failed_command)->cmd[0]) {
s = packet_command_texts[mid].text;
break;
}
if (packet_command_texts[mid].packet_command >
- failed_command->cmd[0])
+ scsi_req(failed_command)->cmd[0])
hi = mid;
else
lo = mid + 1;
@@ -329,7 +329,7 @@ void ide_cd_log_error(const char *name, struct request *failed_command,
printk(KERN_ERR " The failed \"%s\" packet command "
"was: \n \"", s);
for (i = 0; i < BLK_MAX_CDB; i++)
- printk(KERN_CONT "%02x ", failed_command->cmd[i]);
+ printk(KERN_CONT "%02x ", scsi_req(failed_command)->cmd[i]);
printk(KERN_CONT "\"\n");
}
diff --git a/drivers/ide/ide-devsets.c b/drivers/ide/ide-devsets.c
index 0dd43b4..fd56c9d 100644
--- a/drivers/ide/ide-devsets.c
+++ b/drivers/ide/ide-devsets.c
@@ -166,10 +166,11 @@ int ide_devset_execute(ide_drive_t *drive, const struct ide_devset *setting,
return setting->set(drive, arg);
rq = blk_get_request(q, READ, __GFP_RECLAIM);
+ scsi_req_init(rq);
rq->cmd_type = REQ_TYPE_DRV_PRIV;
- rq->cmd_len = 5;
- rq->cmd[0] = REQ_DEVSET_EXEC;
- *(int *)&rq->cmd[1] = arg;
+ scsi_req(rq)->cmd_len = 5;
+ scsi_req(rq)->cmd[0] = REQ_DEVSET_EXEC;
+ *(int *)&scsi_req(rq)->cmd[1] = arg;
rq->special = setting->set;
if (blk_execute_rq(q, NULL, rq, 0))
@@ -183,7 +184,7 @@ ide_startstop_t ide_do_devset(ide_drive_t *drive, struct request *rq)
{
int err, (*setfunc)(ide_drive_t *, int) = rq->special;
- err = setfunc(drive, *(int *)&rq->cmd[1]);
+ err = setfunc(drive, *(int *)&scsi_req(rq)->cmd[1]);
if (err)
rq->errors = err;
ide_complete_rq(drive, err, blk_rq_bytes(rq));
diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c
index 5ceace5..3437c5b 100644
--- a/drivers/ide/ide-disk.c
+++ b/drivers/ide/ide-disk.c
@@ -478,6 +478,7 @@ static int set_multcount(ide_drive_t *drive, int arg)
return -EBUSY;
rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
+ scsi_req_init(rq);
rq->cmd_type = REQ_TYPE_ATA_TASKFILE;
drive->mult_req = arg;
diff --git a/drivers/ide/ide-eh.c b/drivers/ide/ide-eh.c
index d6da011..35e5b89 100644
--- a/drivers/ide/ide-eh.c
+++ b/drivers/ide/ide-eh.c
@@ -148,7 +148,7 @@ static inline void ide_complete_drive_reset(ide_drive_t *drive, int err)
struct request *rq = drive->hwif->rq;
if (rq && rq->cmd_type == REQ_TYPE_DRV_PRIV &&
- rq->cmd[0] == REQ_DRIVE_RESET) {
+ scsi_req(rq)->cmd[0] == REQ_DRIVE_RESET) {
if (err <= 0 && rq->errors == 0)
rq->errors = -EIO;
ide_complete_rq(drive, err ? err : 0, blk_rq_bytes(rq));
diff --git a/drivers/ide/ide-floppy.c b/drivers/ide/ide-floppy.c
index f079d8d..3bd678a 100644
--- a/drivers/ide/ide-floppy.c
+++ b/drivers/ide/ide-floppy.c
@@ -203,7 +203,7 @@ static void idefloppy_create_rw_cmd(ide_drive_t *drive,
put_unaligned(cpu_to_be16(blocks), (unsigned short *)&pc->c[7]);
put_unaligned(cpu_to_be32(block), (unsigned int *) &pc->c[2]);
- memcpy(rq->cmd, pc->c, 12);
+ memcpy(scsi_req(rq)->cmd, pc->c, 12);
pc->rq = rq;
if (cmd == WRITE)
@@ -216,7 +216,7 @@ static void idefloppy_blockpc_cmd(struct ide_disk_obj *floppy,
struct ide_atapi_pc *pc, struct request *rq)
{
ide_init_pc(pc);
- memcpy(pc->c, rq->cmd, sizeof(pc->c));
+ memcpy(pc->c, scsi_req(rq)->cmd, sizeof(pc->c));
pc->rq = rq;
if (blk_rq_bytes(rq)) {
pc->flags |= PC_FLAG_DMA_OK;
diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c
index 201e43f..3378503 100644
--- a/drivers/ide/ide-io.c
+++ b/drivers/ide/ide-io.c
@@ -279,7 +279,7 @@ static ide_startstop_t execute_drive_cmd (ide_drive_t *drive,
static ide_startstop_t ide_special_rq(ide_drive_t *drive, struct request *rq)
{
- u8 cmd = rq->cmd[0];
+ u8 cmd = scsi_req(rq)->cmd[0];
switch (cmd) {
case REQ_PARK_HEADS:
@@ -545,6 +545,7 @@ void do_ide_request(struct request_queue *q)
goto plug_device;
}
+ scsi_req(rq)->resid_len = blk_rq_bytes(rq);
hwif->rq = rq;
spin_unlock_irq(&hwif->lock);
diff --git a/drivers/ide/ide-ioctls.c b/drivers/ide/ide-ioctls.c
index d05db24..a5d22c6 100644
--- a/drivers/ide/ide-ioctls.c
+++ b/drivers/ide/ide-ioctls.c
@@ -126,6 +126,7 @@ static int ide_cmd_ioctl(ide_drive_t *drive, unsigned long arg)
struct request *rq;
rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
+ scsi_req_init(rq);
rq->cmd_type = REQ_TYPE_ATA_TASKFILE;
err = blk_execute_rq(drive->queue, NULL, rq, 0);
blk_put_request(rq);
@@ -222,9 +223,10 @@ static int generic_drive_reset(ide_drive_t *drive)
int ret = 0;
rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
+ scsi_req_init(rq);
rq->cmd_type = REQ_TYPE_DRV_PRIV;
- rq->cmd_len = 1;
- rq->cmd[0] = REQ_DRIVE_RESET;
+ scsi_req(rq)->cmd_len = 1;
+ scsi_req(rq)->cmd[0] = REQ_DRIVE_RESET;
if (blk_execute_rq(drive->queue, NULL, rq, 1))
ret = rq->errors;
blk_put_request(rq);
diff --git a/drivers/ide/ide-park.c b/drivers/ide/ide-park.c
index 2d7dca5..c37604a 100644
--- a/drivers/ide/ide-park.c
+++ b/drivers/ide/ide-park.c
@@ -32,8 +32,9 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout)
spin_unlock_irq(&hwif->lock);
rq = blk_get_request(q, READ, __GFP_RECLAIM);
- rq->cmd[0] = REQ_PARK_HEADS;
- rq->cmd_len = 1;
+ scsi_req_init(rq);
+ scsi_req(rq)->cmd[0] = REQ_PARK_HEADS;
+ scsi_req(rq)->cmd_len = 1;
rq->cmd_type = REQ_TYPE_DRV_PRIV;
rq->special = &timeout;
rc = blk_execute_rq(q, NULL, rq, 1);
@@ -46,11 +47,12 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout)
* timeout has expired, so power management will be reenabled.
*/
rq = blk_get_request(q, READ, GFP_NOWAIT);
+ scsi_req_init(rq);
if (IS_ERR(rq))
goto out;
- rq->cmd[0] = REQ_UNPARK_HEADS;
- rq->cmd_len = 1;
+ scsi_req(rq)->cmd[0] = REQ_UNPARK_HEADS;
+ scsi_req(rq)->cmd_len = 1;
rq->cmd_type = REQ_TYPE_DRV_PRIV;
elv_add_request(q, rq, ELEVATOR_INSERT_FRONT);
@@ -64,7 +66,7 @@ ide_startstop_t ide_do_park_unpark(ide_drive_t *drive, struct request *rq)
struct ide_taskfile *tf = &cmd.tf;
memset(&cmd, 0, sizeof(cmd));
- if (rq->cmd[0] == REQ_PARK_HEADS) {
+ if (scsi_req(rq)->cmd[0] == REQ_PARK_HEADS) {
drive->sleep = *(unsigned long *)rq->special;
drive->dev_flags |= IDE_DFLAG_SLEEPING;
tf->command = ATA_CMD_IDLEIMMEDIATE;
diff --git a/drivers/ide/ide-pm.c b/drivers/ide/ide-pm.c
index a015acd..f6767ab 100644
--- a/drivers/ide/ide-pm.c
+++ b/drivers/ide/ide-pm.c
@@ -19,6 +19,7 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg)
memset(&rqpm, 0, sizeof(rqpm));
rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
+ scsi_req_init(rq);
rq->cmd_type = REQ_TYPE_ATA_PM_SUSPEND;
rq->special = &rqpm;
rqpm.pm_step = IDE_PM_START_SUSPEND;
@@ -89,6 +90,7 @@ int generic_ide_resume(struct device *dev)
memset(&rqpm, 0, sizeof(rqpm));
rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
+ scsi_req_init(rq);
rq->cmd_type = REQ_TYPE_ATA_PM_RESUME;
rq->rq_flags |= RQF_PREEMPT;
rq->special = &rqpm;
diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c
index 330e319..a74ae8df 100644
--- a/drivers/ide/ide-probe.c
+++ b/drivers/ide/ide-probe.c
@@ -741,6 +741,14 @@ static void ide_port_tune_devices(ide_hwif_t *hwif)
}
}
+static int ide_init_rq(struct request_queue *q, struct request *rq, gfp_t gfp)
+{
+ struct ide_request *req = blk_mq_rq_to_pdu(rq);
+
+ req->sreq.sense = req->sense;
+ return 0;
+}
+
/*
* init request queue
*/
@@ -758,11 +766,18 @@ static int ide_init_queue(ide_drive_t *drive)
* limits and LBA48 we could raise it but as yet
* do not.
*/
-
- q = blk_init_queue_node(do_ide_request, NULL, hwif_to_node(hwif));
+ q = blk_alloc_queue_node(GFP_KERNEL, hwif_to_node(hwif));
if (!q)
return 1;
+ q->request_fn = do_ide_request;
+ q->init_rq_fn = ide_init_rq;
+ q->cmd_size = sizeof(struct ide_request);
+ if (blk_init_allocated_queue(q) < 0) {
+ blk_cleanup_queue(q);
+ return 1;
+ }
+
q->queuedata = drive;
blk_queue_segment_boundary(q, 0xffff);
@@ -1131,10 +1146,12 @@ static void ide_port_init_devices_data(ide_hwif_t *hwif)
ide_port_for_each_dev(i, drive, hwif) {
u8 j = (hwif->index * MAX_DRIVES) + i;
u16 *saved_id = drive->id;
+ struct request *saved_sense_rq = drive->sense_rq;
memset(drive, 0, sizeof(*drive));
memset(saved_id, 0, SECTOR_SIZE);
drive->id = saved_id;
+ drive->sense_rq = saved_sense_rq;
drive->media = ide_disk;
drive->select = (i << 4) | ATA_DEVICE_OBS;
@@ -1241,6 +1258,7 @@ static void ide_port_free_devices(ide_hwif_t *hwif)
int i;
ide_port_for_each_dev(i, drive, hwif) {
+ kfree(drive->sense_rq);
kfree(drive->id);
kfree(drive);
}
@@ -1248,11 +1266,10 @@ static void ide_port_free_devices(ide_hwif_t *hwif)
static int ide_port_alloc_devices(ide_hwif_t *hwif, int node)
{
+ ide_drive_t *drive;
int i;
for (i = 0; i < MAX_DRIVES; i++) {
- ide_drive_t *drive;
-
drive = kzalloc_node(sizeof(*drive), GFP_KERNEL, node);
if (drive == NULL)
goto out_nomem;
@@ -1267,12 +1284,21 @@ static int ide_port_alloc_devices(ide_hwif_t *hwif, int node)
*/
drive->id = kzalloc_node(SECTOR_SIZE, GFP_KERNEL, node);
if (drive->id == NULL)
- goto out_nomem;
+ goto out_free_drive;
+
+ drive->sense_rq = kmalloc(sizeof(struct request) +
+ sizeof(struct ide_request), GFP_KERNEL);
+ if (!drive->sense_rq)
+ goto out_free_id;
hwif->devices[i] = drive;
}
return 0;
+out_free_id:
+ kfree(drive->id);
+out_free_drive:
+ kfree(drive);
out_nomem:
ide_port_free_devices(hwif);
return -ENOMEM;
diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c
index 9ecf4e3..f6bc1e2 100644
--- a/drivers/ide/ide-tape.c
+++ b/drivers/ide/ide-tape.c
@@ -282,7 +282,7 @@ static void idetape_analyze_error(ide_drive_t *drive)
/* correct remaining bytes to transfer */
if (pc->flags & PC_FLAG_DMA_ERROR)
- rq->resid_len = tape->blk_size * get_unaligned_be32(&sense[3]);
+ scsi_req(rq)->resid_len = tape->blk_size * get_unaligned_be32(&sense[3]);
/*
* If error was the result of a zero-length read or write command,
@@ -316,7 +316,7 @@ static void idetape_analyze_error(ide_drive_t *drive)
pc->flags |= PC_FLAG_ABORT;
}
if (!(pc->flags & PC_FLAG_ABORT) &&
- (blk_rq_bytes(rq) - rq->resid_len))
+ (blk_rq_bytes(rq) - scsi_req(rq)->resid_len))
pc->retries = IDETAPE_MAX_PC_RETRIES + 1;
}
}
@@ -348,7 +348,7 @@ static int ide_tape_callback(ide_drive_t *drive, int dsc)
"itself - Aborting request!\n");
} else if (pc->c[0] == READ_6 || pc->c[0] == WRITE_6) {
unsigned int blocks =
- (blk_rq_bytes(rq) - rq->resid_len) / tape->blk_size;
+ (blk_rq_bytes(rq) - scsi_req(rq)->resid_len) / tape->blk_size;
tape->avg_size += blocks * tape->blk_size;
@@ -560,7 +560,7 @@ static void ide_tape_create_rw_cmd(idetape_tape_t *tape,
pc->flags |= PC_FLAG_WRITING;
}
- memcpy(rq->cmd, pc->c, 12);
+ memcpy(scsi_req(rq)->cmd, pc->c, 12);
}
static ide_startstop_t idetape_do_request(ide_drive_t *drive,
@@ -570,10 +570,11 @@ static ide_startstop_t idetape_do_request(ide_drive_t *drive,
idetape_tape_t *tape = drive->driver_data;
struct ide_atapi_pc *pc = NULL;
struct ide_cmd cmd;
+ struct scsi_request *req = scsi_req(rq);
u8 stat;
ide_debug_log(IDE_DBG_RQ, "cmd: 0x%x, sector: %llu, nr_sectors: %u",
- rq->cmd[0], (unsigned long long)blk_rq_pos(rq),
+ req->cmd[0], (unsigned long long)blk_rq_pos(rq),
blk_rq_sectors(rq));
BUG_ON(!(rq->cmd_type == REQ_TYPE_DRV_PRIV ||
@@ -592,7 +593,7 @@ static ide_startstop_t idetape_do_request(ide_drive_t *drive,
stat = hwif->tp_ops->read_status(hwif);
if ((drive->dev_flags & IDE_DFLAG_DSC_OVERLAP) == 0 &&
- (rq->cmd[13] & REQ_IDETAPE_PC2) == 0)
+ (req->cmd[13] & REQ_IDETAPE_PC2) == 0)
drive->atapi_flags |= IDE_AFLAG_IGNORE_DSC;
if (drive->dev_flags & IDE_DFLAG_POST_RESET) {
@@ -609,7 +610,7 @@ static ide_startstop_t idetape_do_request(ide_drive_t *drive,
} else if (time_after(jiffies, tape->dsc_timeout)) {
printk(KERN_ERR "ide-tape: %s: DSC timeout\n",
tape->name);
- if (rq->cmd[13] & REQ_IDETAPE_PC2) {
+ if (req->cmd[13] & REQ_IDETAPE_PC2) {
idetape_media_access_finished(drive);
return ide_stopped;
} else {
@@ -626,23 +627,23 @@ static ide_startstop_t idetape_do_request(ide_drive_t *drive,
tape->postponed_rq = false;
}
- if (rq->cmd[13] & REQ_IDETAPE_READ) {
+ if (req->cmd[13] & REQ_IDETAPE_READ) {
pc = &tape->queued_pc;
ide_tape_create_rw_cmd(tape, pc, rq, READ_6);
goto out;
}
- if (rq->cmd[13] & REQ_IDETAPE_WRITE) {
+ if (req->cmd[13] & REQ_IDETAPE_WRITE) {
pc = &tape->queued_pc;
ide_tape_create_rw_cmd(tape, pc, rq, WRITE_6);
goto out;
}
- if (rq->cmd[13] & REQ_IDETAPE_PC1) {
+ if (req->cmd[13] & REQ_IDETAPE_PC1) {
pc = (struct ide_atapi_pc *)rq->special;
- rq->cmd[13] &= ~(REQ_IDETAPE_PC1);
- rq->cmd[13] |= REQ_IDETAPE_PC2;
+ req->cmd[13] &= ~(REQ_IDETAPE_PC1);
+ req->cmd[13] |= REQ_IDETAPE_PC2;
goto out;
}
- if (rq->cmd[13] & REQ_IDETAPE_PC2) {
+ if (req->cmd[13] & REQ_IDETAPE_PC2) {
idetape_media_access_finished(drive);
return ide_stopped;
}
@@ -853,8 +854,9 @@ static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int size)
BUG_ON(size < 0 || size % tape->blk_size);
rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
+ scsi_req_init(rq);
rq->cmd_type = REQ_TYPE_DRV_PRIV;
- rq->cmd[13] = cmd;
+ scsi_req(rq)->cmd[13] = cmd;
rq->rq_disk = tape->disk;
rq->__sector = tape->first_frame;
@@ -868,7 +870,7 @@ static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int size)
blk_execute_rq(drive->queue, tape->disk, rq, 0);
/* calculate the number of transferred bytes and update buffer state */
- size -= rq->resid_len;
+ size -= scsi_req(rq)->resid_len;
tape->cur = tape->buf;
if (cmd == REQ_IDETAPE_READ)
tape->valid = size;
diff --git a/drivers/ide/ide-taskfile.c b/drivers/ide/ide-taskfile.c
index a716693..a393e13 100644
--- a/drivers/ide/ide-taskfile.c
+++ b/drivers/ide/ide-taskfile.c
@@ -431,6 +431,7 @@ int ide_raw_taskfile(ide_drive_t *drive, struct ide_cmd *cmd, u8 *buf,
int rw = !(cmd->tf_flags & IDE_TFLAG_WRITE) ? READ : WRITE;
rq = blk_get_request(drive->queue, rw, __GFP_RECLAIM);
+ scsi_req_init(rq);
rq->cmd_type = REQ_TYPE_ATA_TASKFILE;
/*
diff --git a/drivers/ide/sis5513.c b/drivers/ide/sis5513.c
index 247853e..c3062b5 100644
--- a/drivers/ide/sis5513.c
+++ b/drivers/ide/sis5513.c
@@ -54,7 +54,7 @@
#define DRV_NAME "sis5513"
/* registers layout and init values are chipset family dependent */
-
+#undef ATA_16
#define ATA_16 0x01
#define ATA_33 0x02
#define ATA_66 0x03
diff --git a/drivers/message/fusion/mptsas.c b/drivers/message/fusion/mptsas.c
index 7ee1667..b8c4b2b 100644
--- a/drivers/message/fusion/mptsas.c
+++ b/drivers/message/fusion/mptsas.c
@@ -2320,10 +2320,10 @@ static int mptsas_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
SmpPassthroughReply_t *smprep;
smprep = (SmpPassthroughReply_t *)ioc->sas_mgmt.reply;
- memcpy(req->sense, smprep, sizeof(*smprep));
- req->sense_len = sizeof(*smprep);
- req->resid_len = 0;
- rsp->resid_len -= smprep->ResponseDataLength;
+ memcpy(scsi_req(req)->sense, smprep, sizeof(*smprep));
+ scsi_req(req)->sense_len = sizeof(*smprep);
+ scsi_req(req)->resid_len = 0;
+ scsi_req(rsp)->resid_len -= smprep->ResponseDataLength;
} else {
printk(MYIOC_s_ERR_FMT
"%s: smp passthru reply failed to be returned\n",
diff --git a/drivers/scsi/libfc/fc_lport.c b/drivers/scsi/libfc/fc_lport.c
index 919736a..aa76f36 100644
--- a/drivers/scsi/libfc/fc_lport.c
+++ b/drivers/scsi/libfc/fc_lport.c
@@ -2095,7 +2095,7 @@ int fc_lport_bsg_request(struct bsg_job *job)
bsg_reply->reply_payload_rcv_len = 0;
if (rsp)
- rsp->resid_len = job->reply_payload.payload_len;
+ scsi_req(rsp)->resid_len = job->reply_payload.payload_len;
mutex_lock(&lport->lp_mutex);
diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c
index 022bb6e..570b2cb 100644
--- a/drivers/scsi/libsas/sas_expander.c
+++ b/drivers/scsi/libsas/sas_expander.c
@@ -2174,12 +2174,12 @@ int sas_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
bio_data(rsp->bio), blk_rq_bytes(rsp));
if (ret > 0) {
/* positive number is the untransferred residual */
- rsp->resid_len = ret;
- req->resid_len = 0;
+ scsi_req(rsp)->resid_len = ret;
+ scsi_req(req)->resid_len = 0;
ret = 0;
} else if (ret == 0) {
- rsp->resid_len = 0;
- req->resid_len = 0;
+ scsi_req(rsp)->resid_len = 0;
+ scsi_req(req)->resid_len = 0;
}
return ret;
diff --git a/drivers/scsi/libsas/sas_host_smp.c b/drivers/scsi/libsas/sas_host_smp.c
index d247925..45cbbc4 100644
--- a/drivers/scsi/libsas/sas_host_smp.c
+++ b/drivers/scsi/libsas/sas_host_smp.c
@@ -274,15 +274,15 @@ int sas_smp_host_handler(struct Scsi_Host *shost, struct request *req,
switch (req_data[1]) {
case SMP_REPORT_GENERAL:
- req->resid_len -= 8;
- rsp->resid_len -= 32;
+ scsi_req(req)->resid_len -= 8;
+ scsi_req(rsp)->resid_len -= 32;
resp_data[2] = SMP_RESP_FUNC_ACC;
resp_data[9] = sas_ha->num_phys;
break;
case SMP_REPORT_MANUF_INFO:
- req->resid_len -= 8;
- rsp->resid_len -= 64;
+ scsi_req(req)->resid_len -= 8;
+ scsi_req(rsp)->resid_len -= 64;
resp_data[2] = SMP_RESP_FUNC_ACC;
memcpy(resp_data + 12, shost->hostt->name,
SAS_EXPANDER_VENDOR_ID_LEN);
@@ -295,13 +295,13 @@ int sas_smp_host_handler(struct Scsi_Host *shost, struct request *req,
break;
case SMP_DISCOVER:
- req->resid_len -= 16;
- if ((int)req->resid_len < 0) {
- req->resid_len = 0;
+ scsi_req(req)->resid_len -= 16;
+ if ((int)scsi_req(req)->resid_len < 0) {
+ scsi_req(req)->resid_len = 0;
error = -EINVAL;
goto out;
}
- rsp->resid_len -= 56;
+ scsi_req(rsp)->resid_len -= 56;
sas_host_smp_discover(sas_ha, resp_data, req_data[9]);
break;
@@ -311,13 +311,13 @@ int sas_smp_host_handler(struct Scsi_Host *shost, struct request *req,
break;
case SMP_REPORT_PHY_SATA:
- req->resid_len -= 16;
- if ((int)req->resid_len < 0) {
- req->resid_len = 0;
+ scsi_req(req)->resid_len -= 16;
+ if ((int)scsi_req(req)->resid_len < 0) {
+ scsi_req(req)->resid_len = 0;
error = -EINVAL;
goto out;
}
- rsp->resid_len -= 60;
+ scsi_req(rsp)->resid_len -= 60;
sas_report_phy_sata(sas_ha, resp_data, req_data[9]);
break;
@@ -331,15 +331,15 @@ int sas_smp_host_handler(struct Scsi_Host *shost, struct request *req,
int to_write = req_data[4];
if (blk_rq_bytes(req) < base_frame_size + to_write * 4 ||
- req->resid_len < base_frame_size + to_write * 4) {
+ scsi_req(req)->resid_len < base_frame_size + to_write * 4) {
resp_data[2] = SMP_RESP_INV_FRM_LEN;
break;
}
to_write = sas_host_smp_write_gpio(sas_ha, resp_data, req_data[2],
req_data[3], to_write, &req_data[8]);
- req->resid_len -= base_frame_size + to_write * 4;
- rsp->resid_len -= 8;
+ scsi_req(req)->resid_len -= base_frame_size + to_write * 4;
+ scsi_req(rsp)->resid_len -= 8;
break;
}
@@ -348,13 +348,13 @@ int sas_smp_host_handler(struct Scsi_Host *shost, struct request *req,
break;
case SMP_PHY_CONTROL:
- req->resid_len -= 44;
- if ((int)req->resid_len < 0) {
- req->resid_len = 0;
+ scsi_req(req)->resid_len -= 44;
+ if ((int)scsi_req(req)->resid_len < 0) {
+ scsi_req(req)->resid_len = 0;
error = -EINVAL;
goto out;
}
- rsp->resid_len -= 8;
+ scsi_req(rsp)->resid_len -= 8;
sas_phy_control(sas_ha, req_data[9], req_data[10],
req_data[32] >> 4, req_data[33] >> 4,
resp_data);
diff --git a/drivers/scsi/mpt3sas/mpt3sas_transport.c b/drivers/scsi/mpt3sas/mpt3sas_transport.c
index 7f1d578..e7a7a70 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_transport.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_transport.c
@@ -2057,10 +2057,10 @@ _transport_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
ioc->name, __func__,
le16_to_cpu(mpi_reply->ResponseDataLength)));
- memcpy(req->sense, mpi_reply, sizeof(*mpi_reply));
- req->sense_len = sizeof(*mpi_reply);
- req->resid_len = 0;
- rsp->resid_len -=
+ memcpy(scsi_req(req)->sense, mpi_reply, sizeof(*mpi_reply));
+ scsi_req(req)->sense_len = sizeof(*mpi_reply);
+ scsi_req(req)->resid_len = 0;
+ scsi_req(rsp)->resid_len -=
le16_to_cpu(mpi_reply->ResponseDataLength);
/* check if the resp needs to be copied from the allocated
diff --git a/drivers/scsi/osd/osd_initiator.c b/drivers/scsi/osd/osd_initiator.c
index ef99f62..fcb040e 100644
--- a/drivers/scsi/osd/osd_initiator.c
+++ b/drivers/scsi/osd/osd_initiator.c
@@ -48,6 +48,7 @@
#include <scsi/osd_sense.h>
#include <scsi/scsi_device.h>
+#include <scsi/scsi_request.h>
#include "osd_debug.h"
@@ -477,11 +478,13 @@ static void _set_error_resid(struct osd_request *or, struct request *req,
{
or->async_error = error;
or->req_errors = req->errors ? : error;
- or->sense_len = req->sense_len;
+ or->sense_len = scsi_req(req)->sense_len;
+ if (or->sense_len)
+ memcpy(or->sense, scsi_req(req)->sense, or->sense_len);
if (or->out.req)
- or->out.residual = or->out.req->resid_len;
+ or->out.residual = scsi_req(or->out.req)->resid_len;
if (or->in.req)
- or->in.residual = or->in.req->resid_len;
+ or->in.residual = scsi_req(or->in.req)->resid_len;
}
int osd_execute_request(struct osd_request *or)
@@ -1565,7 +1568,7 @@ static struct request *_make_request(struct request_queue *q, bool has_write,
req = blk_get_request(q, has_write ? WRITE : READ, flags);
if (IS_ERR(req))
return req;
- blk_rq_set_block_pc(req);
+ scsi_req_init(req);
for_each_bio(bio) {
struct bio *bounce_bio = bio;
@@ -1599,8 +1602,6 @@ static int _init_blk_request(struct osd_request *or,
req->timeout = or->timeout;
req->retries = or->retries;
- req->sense = or->sense;
- req->sense_len = 0;
if (has_out) {
or->out.req = req;
@@ -1612,7 +1613,7 @@ static int _init_blk_request(struct osd_request *or,
ret = PTR_ERR(req);
goto out;
}
- blk_rq_set_block_pc(req);
+ scsi_req_init(req);
or->in.req = or->request->next_rq = req;
}
} else if (has_in)
@@ -1699,8 +1700,8 @@ int osd_finalize_request(struct osd_request *or,
osd_sec_sign_cdb(&or->cdb, cap_key);
- or->request->cmd = or->cdb.buff;
- or->request->cmd_len = _osd_req_cdb_len(or);
+ scsi_req(or->request)->cmd = or->cdb.buff;
+ scsi_req(or->request)->cmd_len = _osd_req_cdb_len(or);
return 0;
}
diff --git a/drivers/scsi/osst.c b/drivers/scsi/osst.c
index e8196c5..d314aa5 100644
--- a/drivers/scsi/osst.c
+++ b/drivers/scsi/osst.c
@@ -322,6 +322,7 @@ static int osst_chk_result(struct osst_tape * STp, struct osst_request * SRpnt)
/* Wakeup from interrupt */
static void osst_end_async(struct request *req, int update)
{
+ struct scsi_request *rq = scsi_req(req);
struct osst_request *SRpnt = req->end_io_data;
struct osst_tape *STp = SRpnt->stp;
struct rq_map_data *mdata = &SRpnt->stp->buffer->map_data;
@@ -330,6 +331,8 @@ static void osst_end_async(struct request *req, int update)
#if DEBUG
STp->write_pending = 0;
#endif
+ if (rq->sense_len)
+ memcpy(SRpnt->sense, rq->sense, SCSI_SENSE_BUFFERSIZE);
if (SRpnt->waiting)
complete(SRpnt->waiting);
@@ -357,6 +360,7 @@ static int osst_execute(struct osst_request *SRpnt, const unsigned char *cmd,
int use_sg, int timeout, int retries)
{
struct request *req;
+ struct scsi_request *rq;
struct page **pages = NULL;
struct rq_map_data *mdata = &SRpnt->stp->buffer->map_data;
@@ -367,7 +371,8 @@ static int osst_execute(struct osst_request *SRpnt, const unsigned char *cmd,
if (IS_ERR(req))
return DRIVER_ERROR << 24;
- blk_rq_set_block_pc(req);
+ rq = scsi_req(req);
+ scsi_req_init(req);
req->rq_flags |= RQF_QUIET;
SRpnt->bio = NULL;
@@ -404,11 +409,9 @@ static int osst_execute(struct osst_request *SRpnt, const unsigned char *cmd,
goto free_req;
}
- req->cmd_len = cmd_len;
- memset(req->cmd, 0, BLK_MAX_CDB); /* ATAPI hates garbage after CDB */
- memcpy(req->cmd, cmd, req->cmd_len);
- req->sense = SRpnt->sense;
- req->sense_len = 0;
+ rq->cmd_len = cmd_len;
+ memset(rq->cmd, 0, BLK_MAX_CDB); /* ATAPI hates garbage after CDB */
+ memcpy(rq->cmd, cmd, rq->cmd_len);
req->timeout = timeout;
req->retries = retries;
req->end_io_data = SRpnt;
diff --git a/drivers/scsi/qla2xxx/qla_bsg.c b/drivers/scsi/qla2xxx/qla_bsg.c
index 1bf8061..40ca75b 100644
--- a/drivers/scsi/qla2xxx/qla_bsg.c
+++ b/drivers/scsi/qla2xxx/qla_bsg.c
@@ -921,7 +921,7 @@ qla2x00_process_loopback(struct bsg_job *bsg_job)
bsg_job->reply_len = sizeof(struct fc_bsg_reply) +
sizeof(response) + sizeof(uint8_t);
- fw_sts_ptr = ((uint8_t *)bsg_job->req->sense) +
+ fw_sts_ptr = ((uint8_t *)scsi_req(bsg_job->req)->sense) +
sizeof(struct fc_bsg_reply);
memcpy(fw_sts_ptr, response, sizeof(response));
fw_sts_ptr += sizeof(response);
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 5093ca9..759f281 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -1472,7 +1472,8 @@ qla24xx_els_ct_entry(scsi_qla_host_t *vha, struct req_que *req,
type, sp->handle, comp_status, fw_status[1], fw_status[2],
le16_to_cpu(((struct els_sts_entry_24xx *)
pkt)->total_byte_count));
- fw_sts_ptr = ((uint8_t*)bsg_job->req->sense) + sizeof(struct fc_bsg_reply);
+ fw_sts_ptr = ((uint8_t*)scsi_req(bsg_job->req)->sense) +
+ sizeof(struct fc_bsg_reply);
memcpy( fw_sts_ptr, fw_status, sizeof(fw_status));
}
else {
@@ -1486,7 +1487,8 @@ qla24xx_els_ct_entry(scsi_qla_host_t *vha, struct req_que *req,
pkt)->error_subcode_2));
res = DID_ERROR << 16;
bsg_reply->reply_payload_rcv_len = 0;
- fw_sts_ptr = ((uint8_t*)bsg_job->req->sense) + sizeof(struct fc_bsg_reply);
+ fw_sts_ptr = ((uint8_t*)scsi_req(bsg_job->req)->sense) +
+ sizeof(struct fc_bsg_reply);
memcpy( fw_sts_ptr, fw_status, sizeof(fw_status));
}
ql_dump_buffer(ql_dbg_user + ql_dbg_buffer, vha, 0x5056,
diff --git a/drivers/scsi/qla2xxx/qla_mr.c b/drivers/scsi/qla2xxx/qla_mr.c
index 02f1de1..96c33e29 100644
--- a/drivers/scsi/qla2xxx/qla_mr.c
+++ b/drivers/scsi/qla2xxx/qla_mr.c
@@ -2244,7 +2244,7 @@ qlafx00_ioctl_iosb_entry(scsi_qla_host_t *vha, struct req_que *req,
memcpy(fstatus.reserved_3,
pkt->reserved_2, 20 * sizeof(uint8_t));
- fw_sts_ptr = ((uint8_t *)bsg_job->req->sense) +
+ fw_sts_ptr = ((uint8_t *)scsi_req(bsg_job->req)->sense) +
sizeof(struct fc_bsg_reply);
memcpy(fw_sts_ptr, (uint8_t *)&fstatus,
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 7c08460..4b40f74 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -1968,6 +1968,7 @@ static void eh_lock_door_done(struct request *req, int uptodate)
static void scsi_eh_lock_door(struct scsi_device *sdev)
{
struct request *req;
+ struct scsi_request *rq;
/*
* blk_get_request with GFP_KERNEL (__GFP_RECLAIM) sleeps until a
@@ -1976,17 +1977,16 @@ static void scsi_eh_lock_door(struct scsi_device *sdev)
req = blk_get_request(sdev->request_queue, READ, GFP_KERNEL);
if (IS_ERR(req))
return;
+ rq = scsi_req(req);
+ scsi_req_init(req);
- blk_rq_set_block_pc(req);
-
- req->cmd[0] = ALLOW_MEDIUM_REMOVAL;
- req->cmd[1] = 0;
- req->cmd[2] = 0;
- req->cmd[3] = 0;
- req->cmd[4] = SCSI_REMOVAL_PREVENT;
- req->cmd[5] = 0;
-
- req->cmd_len = COMMAND_SIZE(req->cmd[0]);
+ rq->cmd[0] = ALLOW_MEDIUM_REMOVAL;
+ rq->cmd[1] = 0;
+ rq->cmd[2] = 0;
+ rq->cmd[3] = 0;
+ rq->cmd[4] = SCSI_REMOVAL_PREVENT;
+ rq->cmd[5] = 0;
+ rq->cmd_len = COMMAND_SIZE(rq->cmd[0]);
req->rq_flags |= RQF_QUIET;
req->timeout = 10 * HZ;
@@ -2355,7 +2355,7 @@ scsi_ioctl_reset(struct scsi_device *dev, int __user *arg)
scmd = (struct scsi_cmnd *)(rq + 1);
scsi_init_command(dev, scmd);
scmd->request = rq;
- scmd->cmnd = rq->cmd;
+ scmd->cmnd = scsi_req(rq)->cmd;
scmd->scsi_done = scsi_reset_provider_done_command;
memset(&scmd->sdb, 0, sizeof(scmd->sdb));
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 81ff5ad..98e4c7b 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -220,21 +220,21 @@ static int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
{
struct request *req;
int write = (data_direction == DMA_TO_DEVICE);
+ struct scsi_request *rq;
int ret = DRIVER_ERROR << 24;
req = blk_get_request(sdev->request_queue, write, __GFP_RECLAIM);
if (IS_ERR(req))
return ret;
- blk_rq_set_block_pc(req);
+ rq = scsi_req(req);
+ scsi_req_init(req);
if (bufflen && blk_rq_map_kern(sdev->request_queue, req,
buffer, bufflen, __GFP_RECLAIM))
goto out;
- req->cmd_len = COMMAND_SIZE(cmd[0]);
- memcpy(req->cmd, cmd, req->cmd_len);
- req->sense = sense;
- req->sense_len = 0;
+ rq->cmd_len = COMMAND_SIZE(cmd[0]);
+ memcpy(rq->cmd, cmd, rq->cmd_len);
req->retries = retries;
req->timeout = timeout;
req->cmd_flags |= flags;
@@ -251,11 +251,13 @@ static int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
* is invalid. Prevent the garbage from being misinterpreted
* and prevent security leaks by zeroing out the excess data.
*/
- if (unlikely(req->resid_len > 0 && req->resid_len <= bufflen))
- memset(buffer + (bufflen - req->resid_len), 0, req->resid_len);
+ if (unlikely(rq->resid_len > 0 && rq->resid_len <= bufflen))
+ memset(buffer + (bufflen - rq->resid_len), 0, rq->resid_len);
if (resid)
- *resid = req->resid_len;
+ *resid = rq->resid_len;
+ if (sense && rq->sense_len)
+ memcpy(sense, rq->sense, SCSI_SENSE_BUFFERSIZE);
ret = req->errors;
out:
blk_put_request(req);
@@ -806,16 +808,13 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
if (req->cmd_type == REQ_TYPE_BLOCK_PC) { /* SG_IO ioctl from block level */
if (result) {
- if (sense_valid && req->sense) {
+ if (sense_valid) {
/*
* SG_IO wants current and deferred errors
*/
- int len = 8 + cmd->sense_buffer[7];
-
- if (len > SCSI_SENSE_BUFFERSIZE)
- len = SCSI_SENSE_BUFFERSIZE;
- memcpy(req->sense, cmd->sense_buffer, len);
- req->sense_len = len;
+ scsi_req(req)->sense_len =
+ min(8 + cmd->sense_buffer[7],
+ SCSI_SENSE_BUFFERSIZE);
}
if (!sense_deferred)
error = __scsi_error_from_host_byte(cmd, result);
@@ -825,14 +824,14 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
*/
req->errors = cmd->result;
- req->resid_len = scsi_get_resid(cmd);
+ scsi_req(req)->resid_len = scsi_get_resid(cmd);
if (scsi_bidi_cmnd(cmd)) {
/*
* Bidi commands Must be complete as a whole,
* both sides at once.
*/
- req->next_rq->resid_len = scsi_in(cmd)->resid;
+ scsi_req(req->next_rq)->resid_len = scsi_in(cmd)->resid;
if (scsi_end_request(req, 0, blk_rq_bytes(req),
blk_rq_bytes(req->next_rq)))
BUG();
@@ -1165,7 +1164,8 @@ void scsi_init_command(struct scsi_device *dev, struct scsi_cmnd *cmd)
void *prot = cmd->prot_sdb;
unsigned long flags;
- memset(cmd, 0, sizeof(*cmd));
+ memset((char *)cmd + sizeof(cmd->req), 0,
+ sizeof(*cmd) - sizeof(cmd->req));
cmd->device = dev;
cmd->sense_buffer = buf;
cmd->prot_sdb = prot;
@@ -1197,7 +1197,8 @@ static int scsi_setup_blk_pc_cmnd(struct scsi_device *sdev, struct request *req)
memset(&cmd->sdb, 0, sizeof(cmd->sdb));
}
- cmd->cmd_len = req->cmd_len;
+ cmd->cmd_len = scsi_req(req)->cmd_len;
+ cmd->cmnd = scsi_req(req)->cmd;
cmd->transfersize = blk_rq_bytes(req);
cmd->allowed = req->retries;
return BLKPREP_OK;
@@ -1217,6 +1218,7 @@ static int scsi_setup_fs_cmnd(struct scsi_device *sdev, struct request *req)
return ret;
}
+ cmd->cmnd = scsi_req(req)->cmd = scsi_req(req)->__cmd;
memset(cmd->cmnd, 0, BLK_MAX_CDB);
return scsi_cmd_to_driver(cmd)->init_command(cmd);
}
@@ -1355,7 +1357,6 @@ static int scsi_prep_fn(struct request_queue *q, struct request *req)
cmd->tag = req->tag;
cmd->request = req;
- cmd->cmnd = req->cmd;
cmd->prot_op = SCSI_PROT_NORMAL;
ret = scsi_setup_cmnd(sdev, req);
@@ -1874,7 +1875,8 @@ static int scsi_mq_prep_fn(struct request *req)
unsigned char *sense_buf = cmd->sense_buffer;
struct scatterlist *sg;
- memset(cmd, 0, sizeof(struct scsi_cmnd));
+ memset((char *)cmd + sizeof(cmd->req), 0,
+ sizeof(*cmd) - sizeof(cmd->req));
req->special = cmd;
@@ -1884,7 +1886,6 @@ static int scsi_mq_prep_fn(struct request *req)
cmd->tag = req->tag;
- cmd->cmnd = req->cmd;
cmd->prot_op = SCSI_PROT_NORMAL;
INIT_LIST_HEAD(&cmd->list);
@@ -1959,7 +1960,6 @@ static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
if (!scsi_host_queue_ready(q, shost, sdev))
goto out_dec_target_busy;
-
if (!(req->rq_flags & RQF_DONTPREP)) {
ret = prep_to_mq(scsi_mq_prep_fn(req));
if (ret != BLK_MQ_RQ_QUEUE_OK)
@@ -2036,6 +2036,7 @@ static int scsi_init_request(void *data, struct request *rq,
scsi_alloc_sense_buffer(shost, GFP_KERNEL, numa_node);
if (!cmd->sense_buffer)
return -ENOMEM;
+ cmd->req.sense = cmd->sense_buffer;
return 0;
}
@@ -2125,6 +2126,7 @@ static int scsi_init_rq(struct request_queue *q, struct request *rq, gfp_t gfp)
cmd->sense_buffer = scsi_alloc_sense_buffer(shost, gfp, NUMA_NO_NODE);
if (!cmd->sense_buffer)
goto fail;
+ cmd->req.sense = cmd->sense_buffer;
if (scsi_host_get_prot(shost) >= SHOST_DIX_TYPE0_PROTECTION) {
cmd->prot_sdb = kmem_cache_zalloc(scsi_sdb_cache, gfp);
diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c
index 60b651b..126a5ee 100644
--- a/drivers/scsi/scsi_transport_sas.c
+++ b/drivers/scsi/scsi_transport_sas.c
@@ -33,6 +33,7 @@
#include <linux/bsg.h>
#include <scsi/scsi.h>
+#include <scsi/scsi_request.h>
#include <scsi/scsi_device.h>
#include <scsi/scsi_host.h>
#include <scsi/scsi_transport.h>
@@ -177,6 +178,10 @@ static void sas_smp_request(struct request_queue *q, struct Scsi_Host *shost,
while ((req = blk_fetch_request(q)) != NULL) {
spin_unlock_irq(q->queue_lock);
+ scsi_req(req)->resid_len = blk_rq_bytes(req);
+ if (req->next_rq)
+ scsi_req(req->next_rq)->resid_len =
+ blk_rq_bytes(req->next_rq);
handler = to_sas_internal(shost->transportt)->f->smp_handler;
ret = handler(shost, rphy, req);
req->errors = ret;
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 1fbb1ec..bc8ce6b 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -781,7 +781,7 @@ static int sd_setup_discard_cmnd(struct scsi_cmnd *cmd)
rq->special_vec.bv_len = len;
rq->rq_flags |= RQF_SPECIAL_PAYLOAD;
- rq->resid_len = len;
+ scsi_req(rq)->resid_len = len;
ret = scsi_init_io(cmd);
out:
@@ -1164,7 +1164,7 @@ static void sd_uninit_command(struct scsi_cmnd *SCpnt)
if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
__free_page(rq->special_vec.bv_page);
- if (SCpnt->cmnd != rq->cmd) {
+ if (SCpnt->cmnd != scsi_req(rq)->cmd) {
mempool_free(SCpnt->cmnd, sd_cdb_pool);
SCpnt->cmnd = NULL;
SCpnt->cmd_len = 0;
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index dbe5b4b..226a8de 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -781,9 +781,7 @@ sg_common_write(Sg_fd * sfp, Sg_request * srp,
}
if (atomic_read(&sdp->detaching)) {
if (srp->bio) {
- if (srp->rq->cmd != srp->rq->__cmd)
- kfree(srp->rq->cmd);
-
+ scsi_req_free_cmd(scsi_req(srp->rq));
blk_end_request_all(srp->rq, -EIO);
srp->rq = NULL;
}
@@ -1279,6 +1277,7 @@ static void
sg_rq_end_io(struct request *rq, int uptodate)
{
struct sg_request *srp = rq->end_io_data;
+ struct scsi_request *req = scsi_req(rq);
Sg_device *sdp;
Sg_fd *sfp;
unsigned long iflags;
@@ -1297,9 +1296,9 @@ sg_rq_end_io(struct request *rq, int uptodate)
if (unlikely(atomic_read(&sdp->detaching)))
pr_info("%s: device detaching\n", __func__);
- sense = rq->sense;
+ sense = req->sense;
result = rq->errors;
- resid = rq->resid_len;
+ resid = req->resid_len;
SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sdp,
"sg_cmd_done: pack_id=%d, res=0x%x\n",
@@ -1333,6 +1332,10 @@ sg_rq_end_io(struct request *rq, int uptodate)
sdp->device->changed = 1;
}
}
+
+ if (req->sense_len)
+ memcpy(srp->sense_b, req->sense, SCSI_SENSE_BUFFERSIZE);
+
/* Rely on write phase to clean out srp status values, so no "else" */
/*
@@ -1342,8 +1345,7 @@ sg_rq_end_io(struct request *rq, int uptodate)
* blk_rq_unmap_user() can be called from user context.
*/
srp->rq = NULL;
- if (rq->cmd != rq->__cmd)
- kfree(rq->cmd);
+ scsi_req_free_cmd(scsi_req(rq));
__blk_put_request(rq->q, rq);
write_lock_irqsave(&sfp->rq_list_lock, iflags);
@@ -1658,6 +1660,7 @@ sg_start_req(Sg_request *srp, unsigned char *cmd)
{
int res;
struct request *rq;
+ struct scsi_request *req;
Sg_fd *sfp = srp->parentfp;
sg_io_hdr_t *hp = &srp->header;
int dxfer_len = (int) hp->dxfer_len;
@@ -1700,17 +1703,17 @@ sg_start_req(Sg_request *srp, unsigned char *cmd)
kfree(long_cmdp);
return PTR_ERR(rq);
}
+ req = scsi_req(rq);
- blk_rq_set_block_pc(rq);
+ scsi_req_init(rq);
if (hp->cmd_len > BLK_MAX_CDB)
- rq->cmd = long_cmdp;
- memcpy(rq->cmd, cmd, hp->cmd_len);
- rq->cmd_len = hp->cmd_len;
+ req->cmd = long_cmdp;
+ memcpy(req->cmd, cmd, hp->cmd_len);
+ req->cmd_len = hp->cmd_len;
srp->rq = rq;
rq->end_io_data = srp;
- rq->sense = srp->sense_b;
rq->retries = SG_DEFAULT_RETRIES;
if ((dxfer_len <= 0) || (dxfer_dir == SG_DXFER_NONE))
@@ -1786,8 +1789,7 @@ sg_finish_rem_req(Sg_request *srp)
ret = blk_rq_unmap_user(srp->bio);
if (srp->rq) {
- if (srp->rq->cmd != srp->rq->__cmd)
- kfree(srp->rq->cmd);
+ scsi_req_free_cmd(scsi_req(srp->rq));
blk_put_request(srp->rq);
}
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 5f35b86..4af9001 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -475,7 +475,7 @@ static void st_do_stats(struct scsi_tape *STp, struct request *req)
ktime_t now;
now = ktime_get();
- if (req->cmd[0] == WRITE_6) {
+ if (scsi_req(req)->cmd[0] == WRITE_6) {
now = ktime_sub(now, STp->stats->write_time);
atomic64_add(ktime_to_ns(now), &STp->stats->tot_write_time);
atomic64_add(ktime_to_ns(now), &STp->stats->tot_io_time);
@@ -489,7 +489,7 @@ static void st_do_stats(struct scsi_tape *STp, struct request *req)
} else
atomic64_add(atomic_read(&STp->stats->last_write_size),
&STp->stats->write_byte_cnt);
- } else if (req->cmd[0] == READ_6) {
+ } else if (scsi_req(req)->cmd[0] == READ_6) {
now = ktime_sub(now, STp->stats->read_time);
atomic64_add(ktime_to_ns(now), &STp->stats->tot_read_time);
atomic64_add(ktime_to_ns(now), &STp->stats->tot_io_time);
@@ -514,15 +514,18 @@ static void st_do_stats(struct scsi_tape *STp, struct request *req)
static void st_scsi_execute_end(struct request *req, int uptodate)
{
struct st_request *SRpnt = req->end_io_data;
+ struct scsi_request *rq = scsi_req(req);
struct scsi_tape *STp = SRpnt->stp;
struct bio *tmp;
STp->buffer->cmdstat.midlevel_result = SRpnt->result = req->errors;
- STp->buffer->cmdstat.residual = req->resid_len;
+ STp->buffer->cmdstat.residual = rq->resid_len;
st_do_stats(STp, req);
tmp = SRpnt->bio;
+ if (rq->sense_len)
+ memcpy(SRpnt->sense, rq->sense, SCSI_SENSE_BUFFERSIZE);
if (SRpnt->waiting)
complete(SRpnt->waiting);
@@ -535,6 +538,7 @@ static int st_scsi_execute(struct st_request *SRpnt, const unsigned char *cmd,
int timeout, int retries)
{
struct request *req;
+ struct scsi_request *rq;
struct rq_map_data *mdata = &SRpnt->stp->buffer->map_data;
int err = 0;
int write = (data_direction == DMA_TO_DEVICE);
@@ -544,8 +548,8 @@ static int st_scsi_execute(struct st_request *SRpnt, const unsigned char *cmd,
GFP_KERNEL);
if (IS_ERR(req))
return DRIVER_ERROR << 24;
-
- blk_rq_set_block_pc(req);
+ rq = scsi_req(req);
+ scsi_req_init(req);
req->rq_flags |= RQF_QUIET;
mdata->null_mapped = 1;
@@ -571,11 +575,9 @@ static int st_scsi_execute(struct st_request *SRpnt, const unsigned char *cmd,
}
SRpnt->bio = req->bio;
- req->cmd_len = COMMAND_SIZE(cmd[0]);
- memset(req->cmd, 0, BLK_MAX_CDB);
- memcpy(req->cmd, cmd, req->cmd_len);
- req->sense = SRpnt->sense;
- req->sense_len = 0;
+ rq->cmd_len = COMMAND_SIZE(cmd[0]);
+ memset(rq->cmd, 0, BLK_MAX_CDB);
+ memcpy(rq->cmd, cmd, rq->cmd_len);
req->timeout = timeout;
req->retries = retries;
req->end_io_data = SRpnt;
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index 04d7aa7..e52f4e1 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -1013,7 +1013,7 @@ pscsi_execute_cmd(struct se_cmd *cmd)
goto fail;
}
- blk_rq_set_block_pc(req);
+ scsi_req_init(req);
if (sgl) {
ret = pscsi_map_sg(cmd, sgl, sgl_nents, req);
@@ -1023,10 +1023,8 @@ pscsi_execute_cmd(struct se_cmd *cmd)
req->end_io = pscsi_req_done;
req->end_io_data = cmd;
- req->cmd_len = scsi_command_size(pt->pscsi_cdb);
- req->cmd = &pt->pscsi_cdb[0];
- req->sense = &pt->pscsi_sense[0];
- req->sense_len = 0;
+ scsi_req(req)->cmd_len = scsi_command_size(pt->pscsi_cdb);
+ scsi_req(req)->cmd = &pt->pscsi_cdb[0];
if (pdv->pdv_sd->type == TYPE_DISK)
req->timeout = PS_TIMEOUT_DISK;
else
@@ -1075,7 +1073,7 @@ static void pscsi_req_done(struct request *req, int uptodate)
struct pscsi_plugin_task *pt = cmd->priv;
pt->pscsi_result = req->errors;
- pt->pscsi_resid = req->resid_len;
+ pt->pscsi_resid = scsi_req(req)->resid_len;
cmd->scsi_status = status_byte(pt->pscsi_result) << 1;
if (cmd->scsi_status) {
@@ -1096,6 +1094,7 @@ static void pscsi_req_done(struct request *req, int uptodate)
break;
}
+ memcpy(pt->pscsi_sense, scsi_req(req)->sense, TRANSPORT_SENSE_BUFFER);
__blk_put_request(req->q, req);
kfree(pt);
}
diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
index 0780ff8..930d98c 100644
--- a/fs/nfsd/blocklayout.c
+++ b/fs/nfsd/blocklayout.c
@@ -10,6 +10,7 @@
#include <linux/nfsd/debug.h>
#include <scsi/scsi_proto.h>
#include <scsi/scsi_common.h>
+#include <scsi/scsi_request.h>
#include "blocklayoutxdr.h"
#include "pnfs.h"
@@ -213,6 +214,7 @@ static int nfsd4_scsi_identify_device(struct block_device *bdev,
{
struct request_queue *q = bdev->bd_disk->queue;
struct request *rq;
+ struct scsi_request *req;
size_t bufflen = 252, len, id_len;
u8 *buf, *d, type, assoc;
int error;
@@ -226,18 +228,19 @@ static int nfsd4_scsi_identify_device(struct block_device *bdev,
error = -ENOMEM;
goto out_free_buf;
}
- blk_rq_set_block_pc(rq);
+ req = scsi_req(rq);
+ scsi_req_init(rq);
error = blk_rq_map_kern(q, rq, buf, bufflen, GFP_KERNEL);
if (error)
goto out_put_request;
- rq->cmd[0] = INQUIRY;
- rq->cmd[1] = 1;
- rq->cmd[2] = 0x83;
- rq->cmd[3] = bufflen >> 8;
- rq->cmd[4] = bufflen & 0xff;
- rq->cmd_len = COMMAND_SIZE(INQUIRY);
+ req->cmd[0] = INQUIRY;
+ req->cmd[1] = 1;
+ req->cmd[2] = 0x83;
+ req->cmd[3] = bufflen >> 8;
+ req->cmd[4] = bufflen & 0xff;
+ req->cmd_len = COMMAND_SIZE(INQUIRY);
error = blk_execute_rq(rq->q, NULL, rq, 1);
if (error) {
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 648ecf5..d7f117f 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -227,17 +227,7 @@ struct request {
int errors;
- /*
- * when request is used as a packet command carrier
- */
- unsigned char __cmd[BLK_MAX_CDB];
- unsigned char *cmd;
- unsigned short cmd_len;
-
unsigned int extra_len; /* length of alignment and padding */
- unsigned int sense_len;
- unsigned int resid_len; /* residual count */
- void *sense;
unsigned long deadline;
struct list_head timeout_list;
@@ -919,7 +909,6 @@ extern void blk_rq_init(struct request_queue *q, struct request *rq);
extern void blk_put_request(struct request *);
extern void __blk_put_request(struct request_queue *, struct request *);
extern struct request *blk_get_request(struct request_queue *, int, gfp_t);
-extern void blk_rq_set_block_pc(struct request *);
extern void blk_requeue_request(struct request_queue *, struct request *);
extern int blk_lld_busy(struct request_queue *q);
extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index e417f08..36767ec 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -112,9 +112,10 @@ struct compat_blk_user_trace_setup {
#if defined(CONFIG_EVENT_TRACING) && defined(CONFIG_BLOCK)
+int scsi_cmd_buf_len(struct request *rq);
static inline int blk_cmd_buf_len(struct request *rq)
{
- return (rq->cmd_type == REQ_TYPE_BLOCK_PC) ? rq->cmd_len * 3 : 1;
+ return (rq->cmd_type == REQ_TYPE_BLOCK_PC) ? scsi_cmd_buf_len(rq) : 1;
}
extern void blk_dump_cmd(char *buf, struct request *rq);
diff --git a/include/linux/ide.h b/include/linux/ide.h
index a633898..086fbe1 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -20,6 +20,7 @@
#include <linux/mutex.h>
/* for request_sense */
#include <linux/cdrom.h>
+#include <scsi/scsi_cmnd.h>
#include <asm/byteorder.h>
#include <asm/io.h>
@@ -52,6 +53,11 @@ enum ata_cmd_type_bits {
((rq)->cmd_type == REQ_TYPE_ATA_PM_SUSPEND || \
(rq)->cmd_type == REQ_TYPE_ATA_PM_RESUME)
+struct ide_request {
+ struct scsi_request sreq;
+ u8 sense[SCSI_SENSE_BUFFERSIZE];
+};
+
/* Error codes returned in rq->errors to the higher part of the driver. */
enum {
IDE_DRV_ERROR_GENERAL = 101,
@@ -579,7 +585,7 @@ struct ide_drive_s {
/* current sense rq and buffer */
bool sense_rq_armed;
- struct request sense_rq;
+ struct request *sense_rq;
struct request_sense sense_data;
};
diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h
index 9fc1aec..f708f1a 100644
--- a/include/scsi/scsi_cmnd.h
+++ b/include/scsi/scsi_cmnd.h
@@ -8,6 +8,7 @@
#include <linux/timer.h>
#include <linux/scatterlist.h>
#include <scsi/scsi_device.h>
+#include <scsi/scsi_request.h>
struct Scsi_Host;
struct scsi_driver;
@@ -57,6 +58,7 @@ struct scsi_pointer {
#define SCMD_TAGGED (1 << 0)
struct scsi_cmnd {
+ struct scsi_request req;
struct scsi_device *device;
struct list_head list; /* scsi_cmnd participates in queue lists */
struct list_head eh_entry; /* entry for the host eh_cmd_q */
diff --git a/include/scsi/scsi_request.h b/include/scsi/scsi_request.h
new file mode 100644
index 0000000..c4d86c6
--- /dev/null
+++ b/include/scsi/scsi_request.h
@@ -0,0 +1,28 @@
+#ifndef _SCSI_SCSI_REQUEST_H
+#define _SCSI_SCSI_REQUEST_H
+
+#include <linux/blk-mq.h>
+
+struct scsi_request {
+ unsigned char __cmd[BLK_MAX_CDB];
+ unsigned char *cmd;
+ unsigned short cmd_len;
+ unsigned int sense_len;
+ unsigned int resid_len; /* residual count */
+ void *sense;
+};
+
+static inline struct scsi_request *scsi_req(struct request *rq)
+{
+ return blk_mq_rq_to_pdu(rq);
+}
+
+void scsi_req_init(struct request *);
+
+static inline void scsi_req_free_cmd(struct scsi_request *req)
+{
+ if (req->cmd != req->__cmd)
+ kfree(req->cmd);
+}
+
+#endif /* _SCSI_SCSI_REQUEST_H */
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 95cecbf..69c36e6a 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -27,6 +27,7 @@
#include <linux/time.h>
#include <linux/uaccess.h>
#include <linux/list.h>
+#include <scsi/scsi_request.h>
#include <trace/events/block.h>
@@ -715,7 +716,8 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
what |= BLK_TC_ACT(BLK_TC_PC);
__blk_add_trace(bt, 0, nr_bytes, req_op(rq), rq->cmd_flags,
- what, rq->errors, rq->cmd_len, rq->cmd);
+ what, rq->errors,
+ scsi_req(rq)->cmd_len, scsi_req(rq)->cmd);
} else {
what |= BLK_TC_ACT(BLK_TC_FS);
__blk_add_trace(bt, blk_rq_pos(rq), nr_bytes, req_op(rq),
@@ -1751,32 +1753,32 @@ void blk_trace_remove_sysfs(struct device *dev)
#endif /* CONFIG_BLK_DEV_IO_TRACE */
#ifdef CONFIG_EVENT_TRACING
-
-void blk_dump_cmd(char *buf, struct request *rq)
+static void blk_dump_scsi_cmd(char *buf, struct scsi_request *req)
{
int i, end;
- int len = rq->cmd_len;
- unsigned char *cmd = rq->cmd;
- if (rq->cmd_type != REQ_TYPE_BLOCK_PC) {
- buf[0] = '\0';
- return;
- }
-
- for (end = len - 1; end >= 0; end--)
- if (cmd[end])
+ for (end = req->cmd_len - 1; end >= 0; end--)
+ if (req->cmd[end])
break;
end++;
- for (i = 0; i < len; i++) {
- buf += sprintf(buf, "%s%02x", i == 0 ? "" : " ", cmd[i]);
- if (i == end && end != len - 1) {
+ for (i = 0; i < req->cmd_len; i++) {
+ buf += sprintf(buf, "%s%02x", i == 0 ? "" : " ", req->cmd[i]);
+ if (i == end && end != req->cmd_len - 1) {
sprintf(buf, " ..");
break;
}
}
}
+void blk_dump_cmd(char *buf, struct request *rq)
+{
+ if (rq->cmd_type == REQ_TYPE_BLOCK_PC)
+ blk_dump_scsi_cmd(buf, scsi_req(rq));
+ else
+ buf[0] = '\0';
+}
+
void blk_fill_rwbs(char *rwbs, unsigned int op, int bytes)
{
int i = 0;
--
2.1.4
^ permalink raw reply related
* [PATCH 18/18] block: don't assign cmd_flags in __blk_rq_prep_clone
From: Christoph Hellwig @ 2017-01-25 17:25 UTC (permalink / raw)
To: Jens Axboe
Cc: Mike Snitzer, Junichi Nomura, linux-block, linux-scsi, linux-raid,
dm-devel
In-Reply-To: <1485365126-23210-1-git-send-email-hch@lst.de>
These days we have the proper flags set since request allocation time.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
---
block/blk-core.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/block/blk-core.c b/block/blk-core.c
index 33c5d05e..6bf5ba0 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2983,7 +2983,6 @@ EXPORT_SYMBOL_GPL(blk_rq_unprep_clone);
static void __blk_rq_prep_clone(struct request *dst, struct request *src)
{
dst->cpu = src->cpu;
- dst->cmd_flags = src->cmd_flags | REQ_NOMERGE;
dst->cmd_type = src->cmd_type;
dst->__sector = blk_rq_pos(src);
dst->__data_len = blk_rq_bytes(src);
--
2.1.4
^ permalink raw reply related
* Re: [PATCH] md linear: fix a race between linear_add() and linear_congested()
From: Shaohua Li @ 2017-01-25 18:02 UTC (permalink / raw)
To: colyli; +Cc: linux-raid, Shaohua Li, Neil Brown, stable
In-Reply-To: <1485342943-9330-1-git-send-email-colyli@suse.de>
On Wed, Jan 25, 2017 at 07:15:43PM +0800, colyli@suse.de wrote:
> Recently I receie a report that on Linux v3.0 based kerenl, hot add disk
> to a md linear device causes kernel crash at linear_congested(). From the
> crash image analysis, I find in linear_congested(), mddev->raid_disks
> contains value N, but conf->disks[] only has N-1 pointers available. Then
> a pointer deference to a NULL pointer crashes the kernel.
>
> There is a race between linear_add() and linear_congested(), RCU stuffs
> used in these two functions cannot avoid the race. Since Linuv v4.0
> RCU code is replaced by introducing mddev_suspend(). After checking the
> upstream code, it seems linear_congested() is not called in
> generic_make_request() code patch, so mddev_suspend() cannot provent it
> from being called. The possible race still exists.
>
> Here I explain how the race still exists in current code. For a machine
> has many CPUs, on one CPU, linear_add() is called to add a hard disk to a
> md linear device; at the same time on other CPU, linear_congested() is
> called to detect whether this md linear device is congested before issuing
> an I/O request onto it.
>
> Now I use a possible code execution time sequence to demo how the possible
> race happens,
>
> seq linear_add() linear_congested()
> 0 conf=mddev->private
> 1 oldconf=mddev->private
> 2 mddev->raid_disks++
> 3 for (i=0; i<mddev->raid_disks;i++)
> 4 bdev_get_queue(conf->disks[i].rdev->bdev)
> 5 mddev->private=newconf
Good catch, this makes a lot of sense. However, this looks like an incomplete
fix. step 0 will get the old conf, after step 5, linear_add will free the old
conf. So it's possible linear_congested() will use the freed old conf. I think
this is more likely to happen. The easist fix maybe put rcu_lock in
linear_congested and free the old conf in a rcu callback.
Thanks,
Shaohua
> In linear_add() mddev->raid_disks is increased in time seq 2, and on
> another CPU in linear_congested() the for-loop iterates conf->disks[i] by
> the increased mddev->raid_disks in time seq 3,4. But conf with one more
> element (which is a pointer to struct dev_info type) to conf->disks[] is
> not updated yet, accessing its structure member in time seq 4 will cause a
> NULL pointer deference fault.
>
> The fix is to update mddev->private with new value before increasing
> mddev->raid_disks, and to make sure on other CPUs their are seen to be
> updated in same order as linear_add() does (otherwise the race may still
> happen), a smp_mb() is necessary.
>
> A question is, by this fix, if mddev->private is update to new value in
> linear_add(), but in linear_congested() the for-loop still tests old value
> of mddev->raid_disks, then the iteration will miss the last element of
> conf->disks[]. My answer is don't worry it, it's OK. the reasons are,
> - When updating mddev->private, the md linear device is suspend, no I/O
> may happen, it is safe to missing congestion status of the last
> new-added hard disk.
> - In the worst case linear_congested() returns 0 and I/O sent to this md
> linear device, but the new added hard disk is congested, then the I/O
> request will be blocked for a while if it just happenly hits the new
> added hard disk. linear_congested() is in code path of wb_congested(),
> which is quite hot in write back code path. Comparing to add locking
> code in linear_congested(), the cost of the worst case is acceptable.
>
> The bug is reported on Linux v3.0 based kernel, it can and should be
> applied to all kernels since Linux v3.0. I see linear_add() is merged into
> mainline since Linux v2.6.18, maybe stable kernel maintainers after this
> version may consider to pick this fix as well.
>
> Signed-off-by: Coly Li <colyli@suse.de>
> Cc: Shaohua Li <shli@fb.com>
> Cc: Neil Brown <neilb@suse.com>
> Cc: stable@vger.kernel.org
> ---
> drivers/md/linear.c | 14 +++++++++++++-
> 1 file changed, 13 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/md/linear.c b/drivers/md/linear.c
> index 5975c99..48ccfad 100644
> --- a/drivers/md/linear.c
> +++ b/drivers/md/linear.c
> @@ -196,10 +196,22 @@ static int linear_add(struct mddev *mddev, struct md_rdev *rdev)
> if (!newconf)
> return -ENOMEM;
>
> + /* In linear_congested(), mddev->raid_disks and mddev->private
> + * are accessed without protection by mddev_suspend(). If on
> + * another CPU, in linear_congested() mddev->private is still seen
> + * to contains old value but mddev->raid_disks is seen to have the
> + * increased value, the last iteration to conf->disks[i].rdev will
> + * trigger a NULL pointer deference. To avoid this race, here
> + * mddev->private must be updated before increasing
> + * mddev->raid_disks, and a smp_mb() is required between them. Then
> + * in linear_congested(), we are sure the updated mddev->private is
> + * seen when iterating conf->disks[i].
> + */
> mddev_suspend(mddev);
> oldconf = mddev->private;
> - mddev->raid_disks++;
> mddev->private = newconf;
> + smp_mb();
> + mddev->raid_disks++;
> md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
> set_capacity(mddev->gendisk, mddev->array_sectors);
> mddev_resume(mddev);
> --
> 2.6.6
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-raid" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: performance collapse: 9 mio IOPS to 1.5 mio with MD RAID0
From: Stan Hoeppner @ 2017-01-25 23:01 UTC (permalink / raw)
To: Tobias Oberstein, linux-raid
In-Reply-To: <ebf6cf62-b877-251f-5704-c5c6238a4b91@gmail.com>
On 01/25/2017 05:45 AM, Tobias Oberstein wrote:
> Hi,
>
> I have a storage consisting of 8 NVMe drives (16 logical drives) that
> I verified (FIO) is able to do >9 million 4kB random read IOPS if I
> run FIO on the set of individual NVMes.
>
> However, when I create a MD (RAID-0) over the 16 NVMes and run the
> same tests, performance collapses:
>
> ioengine=sync, invidual NVMes: IOPS=9191k
> ioengine=sync, MD (RAID-0) over NVMes: IOPS=1562k
>
> Using ioengine=psync, the performance collapse isn't as dramatic, but
> still very signifcant:
>
> ioengine=sync, invidual NVMes: IOPS=9395k
> ioengine=sync, MD (RAID-0) over NVMes: IOPS=4117k
>
> --
>
> All detail results (including runs under Linux perf) and FIO control
> files are here
>
> https://github.com/oberstet/scratchbox/tree/master/cruncher/sync-engines-perf
>
>
You don't need 1024 jobs to fill the request queues. Just out of
curiosity, what are the fio results when using fewer jobs and a greater
queue depth, say one job per core, 88 total, with a queue depth of 32?
osq_lock appears to be a per cpu opportunistic spinlock. Might be of
benefit to try even fewer jobs for fewer active cores.
> --
>
> With sync/MD, top in perf is
>
> 82.77% fio [kernel.kallsyms] [k] osq_lock
> 3.12% fio [kernel.kallsyms] [k] nohz_balance_exit_idle
> 1.40% fio [kernel.kallsyms] [k] trigger_load_balance
> 1.01% fio [kernel.kallsyms] [k]
> native_queued_spin_lock_slowpath
>
>
> With psync/MD, top in perf is
>
> 45.56% fio [kernel.kallsyms] [k] md_make_request
> 4.33% fio [kernel.kallsyms] [k] osq_lock
> 3.40% fio [kernel.kallsyms] [k]
> native_queued_spin_lock_slowpath
> 3.23% fio [kernel.kallsyms] [k] _raw_spin_lock
> 2.21% fio [kernel.kallsyms] [k] raid0_make_request
>
> --
>
> Of course there isn't a free lunch, but a performance collapse in this
> order for a RAID-0, that is pure striping, seems excessive.
>
> What's going on?
>
> Cheers,
> /Tobias
>
>
> MD device was created like this:
>
> sudo mdadm --create /dev/md1 \
> --chunk=8 \
> --level=0 \
> --raid-devices=16 \
> /dev/nvme0n1 \
> /dev/nvme1n1 \
> /dev/nvme2n1 \
> /dev/nvme3n1 \
> /dev/nvme4n1 \
> /dev/nvme5n1 \
> /dev/nvme6n1 \
> /dev/nvme7n1 \
> /dev/nvme8n1 \
> /dev/nvme9n1 \
> /dev/nvme10n1 \
> /dev/nvme11n1 \
> /dev/nvme12n1 \
> /dev/nvme13n1 \
> /dev/nvme14n1 \
> /dev/nvme15n1
>
> The NVMes are low-level formatted with 4k sectors. Before, I had 512
> bytes (default), and the perf. collapse was even more dramatic.
>
> The chunk size of 8k is used because this is supposed to carry
> database workloads later.
>
> My target workload is PostgreSQL which is 100% 8k and lseek/read/write
> (not using pread/pwrite or pvread/pvwrite etc).
> --
> To unsubscribe from this list: send the line "unsubscribe linux-raid" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH] md linear: fix a race between linear_add() and linear_congested()
From: NeilBrown @ 2017-01-26 0:04 UTC (permalink / raw)
To: Shaohua Li, colyli; +Cc: linux-raid, Shaohua Li, stable
In-Reply-To: <20170125180258.fil35zckwtebysqr@kernel.org>
[-- Attachment #1: Type: text/plain, Size: 6318 bytes --]
On Wed, Jan 25 2017, Shaohua Li wrote:
> On Wed, Jan 25, 2017 at 07:15:43PM +0800, colyli@suse.de wrote:
>> Recently I receie a report that on Linux v3.0 based kerenl, hot add disk
>> to a md linear device causes kernel crash at linear_congested(). From the
>> crash image analysis, I find in linear_congested(), mddev->raid_disks
>> contains value N, but conf->disks[] only has N-1 pointers available. Then
>> a pointer deference to a NULL pointer crashes the kernel.
>>
>> There is a race between linear_add() and linear_congested(), RCU stuffs
>> used in these two functions cannot avoid the race. Since Linuv v4.0
>> RCU code is replaced by introducing mddev_suspend(). After checking the
>> upstream code, it seems linear_congested() is not called in
>> generic_make_request() code patch, so mddev_suspend() cannot provent it
>> from being called. The possible race still exists.
>>
>> Here I explain how the race still exists in current code. For a machine
>> has many CPUs, on one CPU, linear_add() is called to add a hard disk to a
>> md linear device; at the same time on other CPU, linear_congested() is
>> called to detect whether this md linear device is congested before issuing
>> an I/O request onto it.
>>
>> Now I use a possible code execution time sequence to demo how the possible
>> race happens,
>>
>> seq linear_add() linear_congested()
>> 0 conf=mddev->private
>> 1 oldconf=mddev->private
>> 2 mddev->raid_disks++
>> 3 for (i=0; i<mddev->raid_disks;i++)
>> 4 bdev_get_queue(conf->disks[i].rdev->bdev)
>> 5 mddev->private=newconf
>
> Good catch, this makes a lot of sense. However, this looks like an incomplete
> fix. step 0 will get the old conf, after step 5, linear_add will free the old
> conf. So it's possible linear_congested() will use the freed old conf. I think
> this is more likely to happen. The easist fix maybe put rcu_lock in
> linear_congested and free the old conf in a rcu callback.
We used to use kfree_rcu() but removed it in
Commit: 3be260cc18f8 ("md/linear: remove rcu protections in favour of suspend/resume")
when we changed to suspend/resume the device. That stops all IO, but
doesn't stop the ->congested call.
So we probably should re-introduce kfree_rcu() to free oldconf.
It might also be good to store a copy of raid_disks in
linear_conf, like we do with r5conf, the ensure we never us inconsistent
->raid_disks and ->disks[]
Thanks,
NeilBrown
>
> Thanks,
> Shaohua
>
>> In linear_add() mddev->raid_disks is increased in time seq 2, and on
>> another CPU in linear_congested() the for-loop iterates conf->disks[i] by
>> the increased mddev->raid_disks in time seq 3,4. But conf with one more
>> element (which is a pointer to struct dev_info type) to conf->disks[] is
>> not updated yet, accessing its structure member in time seq 4 will cause a
>> NULL pointer deference fault.
>>
>> The fix is to update mddev->private with new value before increasing
>> mddev->raid_disks, and to make sure on other CPUs their are seen to be
>> updated in same order as linear_add() does (otherwise the race may still
>> happen), a smp_mb() is necessary.
>>
>> A question is, by this fix, if mddev->private is update to new value in
>> linear_add(), but in linear_congested() the for-loop still tests old value
>> of mddev->raid_disks, then the iteration will miss the last element of
>> conf->disks[]. My answer is don't worry it, it's OK. the reasons are,
>> - When updating mddev->private, the md linear device is suspend, no I/O
>> may happen, it is safe to missing congestion status of the last
>> new-added hard disk.
>> - In the worst case linear_congested() returns 0 and I/O sent to this md
>> linear device, but the new added hard disk is congested, then the I/O
>> request will be blocked for a while if it just happenly hits the new
>> added hard disk. linear_congested() is in code path of wb_congested(),
>> which is quite hot in write back code path. Comparing to add locking
>> code in linear_congested(), the cost of the worst case is acceptable.
>>
>> The bug is reported on Linux v3.0 based kernel, it can and should be
>> applied to all kernels since Linux v3.0. I see linear_add() is merged into
>> mainline since Linux v2.6.18, maybe stable kernel maintainers after this
>> version may consider to pick this fix as well.
>>
>> Signed-off-by: Coly Li <colyli@suse.de>
>> Cc: Shaohua Li <shli@fb.com>
>> Cc: Neil Brown <neilb@suse.com>
>> Cc: stable@vger.kernel.org
>> ---
>> drivers/md/linear.c | 14 +++++++++++++-
>> 1 file changed, 13 insertions(+), 1 deletion(-)
>>
>> diff --git a/drivers/md/linear.c b/drivers/md/linear.c
>> index 5975c99..48ccfad 100644
>> --- a/drivers/md/linear.c
>> +++ b/drivers/md/linear.c
>> @@ -196,10 +196,22 @@ static int linear_add(struct mddev *mddev, struct md_rdev *rdev)
>> if (!newconf)
>> return -ENOMEM;
>>
>> + /* In linear_congested(), mddev->raid_disks and mddev->private
>> + * are accessed without protection by mddev_suspend(). If on
>> + * another CPU, in linear_congested() mddev->private is still seen
>> + * to contains old value but mddev->raid_disks is seen to have the
>> + * increased value, the last iteration to conf->disks[i].rdev will
>> + * trigger a NULL pointer deference. To avoid this race, here
>> + * mddev->private must be updated before increasing
>> + * mddev->raid_disks, and a smp_mb() is required between them. Then
>> + * in linear_congested(), we are sure the updated mddev->private is
>> + * seen when iterating conf->disks[i].
>> + */
>> mddev_suspend(mddev);
>> oldconf = mddev->private;
>> - mddev->raid_disks++;
>> mddev->private = newconf;
>> + smp_mb();
>> + mddev->raid_disks++;
>> md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
>> set_capacity(mddev->gendisk, mddev->array_sectors);
>> mddev_resume(mddev);
>> --
>> 2.6.6
>>
>> --
>> To unsubscribe from this list: send the line "unsubscribe linux-raid" in
>> the body of a message to majordomo@vger.kernel.org
>> More majordomo info at http://vger.kernel.org/majordomo-info.html
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 832 bytes --]
^ permalink raw reply
* Re: [PATCH 01/18] block: add a op_is_flush helper
From: Martin K. Petersen @ 2017-01-26 2:58 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Jens Axboe, Mike Snitzer, Junichi Nomura, linux-block, linux-scsi,
linux-raid, dm-devel
In-Reply-To: <1485365126-23210-2-git-send-email-hch@lst.de>
>>>>> "Christoph" == Christoph Hellwig <hch@lst.de> writes:
Christoph> This centralizes the checks for bios that needs to be go into
Christoph> the flush state machine.
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
--
Martin K. Petersen Oracle Linux Engineering
^ permalink raw reply
* Re: [PATCH 02/18] md: cleanup bio op / flags handling in raid1_write_request
From: Martin K. Petersen @ 2017-01-26 2:59 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Jens Axboe, Mike Snitzer, Junichi Nomura, linux-block, linux-scsi,
linux-raid, dm-devel
In-Reply-To: <1485365126-23210-3-git-send-email-hch@lst.de>
>>>>> "Christoph" == Christoph Hellwig <hch@lst.de> writes:
Christoph> No need for the local variables, the bio is still live and we
Christoph> can just assigned the bits we want directly. Make me wonder
Christoph> why we can't assign all the bio flags to start with.
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
--
Martin K. Petersen Oracle Linux Engineering
^ permalink raw reply
* Re: [PATCH 03/18] block: fix elevator init check
From: Martin K. Petersen @ 2017-01-26 3:01 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Jens Axboe, Mike Snitzer, Junichi Nomura, linux-block, linux-scsi,
linux-raid, dm-devel
In-Reply-To: <1485365126-23210-4-git-send-email-hch@lst.de>
>>>>> "Christoph" == Christoph Hellwig <hch@lst.de> writes:
Christoph> We can't initalize the elevator fields for flushes as flush
Christoph> share space in struct request with the elevator data. But
Christoph> currently we can't commnicate that a request is a flush
communicate
Christoph> through blk_get_request as we can only pass READ or WRITE,
Christoph> and the low-level code looks at the possible NULL bio to
Christoph> check for a flush.
Christoph> Fix this by allowing to pass any block op and flags, and by
Christoph> checking for the flush flags in __get_request.
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
--
Martin K. Petersen Oracle Linux Engineering
^ permalink raw reply
* Re: [PATCH 04/18] block: simplify blk_init_allocated_queue
From: Martin K. Petersen @ 2017-01-26 3:02 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Jens Axboe, Mike Snitzer, Junichi Nomura, linux-block, linux-scsi,
linux-raid, dm-devel
In-Reply-To: <1485365126-23210-5-git-send-email-hch@lst.de>
>>>>> "Christoph" == Christoph Hellwig <hch@lst.de> writes:
Christoph> Return an errno value instead of the passed in queue so that
Christoph> the callers don't have to keep track of two queues, and move
Christoph> the assignment of the request_fn and lock to the caller as
Christoph> passing them as argument doesn't simplify anything. While
Christoph> we're at it also remove two pointless NULL assignments, given
Christoph> that the request structure is zeroed on allocation.
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
--
Martin K. Petersen Oracle Linux Engineering
^ permalink raw reply
* Re: [PATCH 05/18] block: allow specifying size for extra command data
From: Martin K. Petersen @ 2017-01-26 3:15 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Jens Axboe, Mike Snitzer, Junichi Nomura, linux-block, linux-scsi,
linux-raid, dm-devel
In-Reply-To: <1485365126-23210-6-git-send-email-hch@lst.de>
>>>>> "Christoph" == Christoph Hellwig <hch@lst.de> writes:
Christoph,
Christoph> This mirrors the blk-mq capabilities to allocate extra
Christoph> drivers-specific data behind struct request by setting a
Christoph> cmd_size field, as well as having a constructor / destructor
Christoph> for it.
Nice!
A couple of minor nits:
+static void *alloc_request_size(gfp_t gfp_mask, void *data)
I like alloc_request_simple() but alloc_request_size() seems a bit
contrived. _reserve? _extra? _special? Don't have any good suggestions,
I'm afraid.
Also a bit heavy on the else brackets a couple of places. But no biggie.
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
--
Martin K. Petersen Oracle Linux Engineering
^ permalink raw reply
* Re: [PATCH 08/18] scsi_dh_rdac: switch to scsi_execute_req_flags()
From: Martin K. Petersen @ 2017-01-26 3:18 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Jens Axboe, Mike Snitzer, Junichi Nomura, linux-block, linux-scsi,
linux-raid, dm-devel, Hannes Reinecke, Hannes Reinecke
In-Reply-To: <1485365126-23210-9-git-send-email-hch@lst.de>
>>>>> "Christoph" == Christoph Hellwig <hch@lst.de> writes:
Christoph> From: Hannes Reinecke <hare@suse.de> Switch to
Christoph> scsi_execute_req_flags() and scsi_get_vpd_page() instead of
Christoph> open-coding it. Using scsi_execute_req_flags() will set
Christoph> REQ_QUIET and REQ_PREEMPT, but this is okay as we're
Christoph> evaluating the errors anyway and should be able to send the
Christoph> command even if the device is quiesced.
Acked-by: Martin K. Petersen <martin.petersen@oracle.com>
--
Martin K. Petersen Oracle Linux Engineering
^ permalink raw reply
* Re: [PATCH 09/18] scsi_dh_emc: switch to scsi_execute_req_flags()
From: Martin K. Petersen @ 2017-01-26 3:19 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Jens Axboe, Mike Snitzer, Junichi Nomura, linux-block, linux-scsi,
linux-raid, dm-devel, Hannes Reinecke, Hannes Reinecke
In-Reply-To: <1485365126-23210-10-git-send-email-hch@lst.de>
>>>>> "Christoph" == Christoph Hellwig <hch@lst.de> writes:
Christoph> From: Hannes Reinecke <hare@suse.de> Switch to
Christoph> scsi_execute_req_flags() and scsi_get_vpd_page() instead of
Christoph> open-coding it. Using scsi_execute_req_flags() will set
Christoph> REQ_QUIET and REQ_PREEMPT, but this is okay as we're
Christoph> evaluating the errors anyway and should be able to send the
Christoph> command even if the device is quiesced.
Acked-by: Martin K. Petersen <martin.petersen@oracle.com>
--
Martin K. Petersen Oracle Linux Engineering
^ permalink raw reply
* Re: [PATCH 10/18] scsi_dh_hp_sw: switch to scsi_execute_req_flags()
From: Martin K. Petersen @ 2017-01-26 3:20 UTC (permalink / raw)
To: Christoph Hellwig
Cc: linux-block, Hannes Reinecke, linux-raid, Mike Snitzer,
linux-scsi, Jens Axboe, dm-devel, Junichi Nomura
In-Reply-To: <1485365126-23210-11-git-send-email-hch@lst.de>
>>>>> "Christoph" == Christoph Hellwig <hch@lst.de> writes:
Christoph> From: Hannes Reinecke <hare@suse.de> Switch to
Christoph> scsi_execute_req_flags() instead of using the block interface
Christoph> directly. This will set REQ_QUIET and REQ_PREEMPT, but this
Christoph> is okay as we're evaluating the errors anyway and should be
Christoph> able to send the command even if the device is quiesced.
Acked-by: Martin K. Petersen <martin.petersen@oracle.com>
--
Martin K. Petersen Oracle Linux Engineering
^ permalink raw reply
* Re: [PATCH 11/18] scsi: remove gfp_flags member in scsi_host_cmd_pool
From: Martin K. Petersen @ 2017-01-26 3:21 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Jens Axboe, Mike Snitzer, Junichi Nomura, linux-block, linux-scsi,
linux-raid, dm-devel
In-Reply-To: <1485365126-23210-12-git-send-email-hch@lst.de>
>>>>> "Christoph" == Christoph Hellwig <hch@lst.de> writes:
Christoph> When using the slab allocator we already decide at cache
Christoph> creation time if an allocation comes from a GFP_DMA pool
Christoph> using the SLAB_CACHE_DMA flag, and there is no point passing
Christoph> the kmalloc-family only GFP_DMA flag to kmem_cache_alloc.
Christoph> Drop all the infrastructure for doing so.
Acked-by: Martin K. Petersen <martin.petersen@oracle.com>
--
Martin K. Petersen Oracle Linux Engineering
^ permalink raw reply
* Re: [PATCH 12/18] scsi: respect unchecked_isa_dma for blk-mq
From: Martin K. Petersen @ 2017-01-26 3:23 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Jens Axboe, Mike Snitzer, Junichi Nomura, linux-block, linux-scsi,
linux-raid, dm-devel
In-Reply-To: <1485365126-23210-13-git-send-email-hch@lst.de>
>>>>> "Christoph" == Christoph Hellwig <hch@lst.de> writes:
Christoph> Currently blk-mq always allocates the sense buffer using
Christoph> normal GFP_KERNEL allocation. Refactor the cmd pool code to
Christoph> split the cmd and sense allocation and share the code to
Christoph> allocate the sense buffers as well as the sense buffer slab
Christoph> caches between the legacy and blk-mq path.
Acked-by: Martin K. Petersen <martin.petersen@oracle.com>
--
Martin K. Petersen Oracle Linux Engineering
^ permalink raw reply
* Re: [PATCH 13/18] scsi: remove scsi_cmd_dma_pool
From: Martin K. Petersen @ 2017-01-26 3:24 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Jens Axboe, Mike Snitzer, Junichi Nomura, linux-block, linux-scsi,
linux-raid, dm-devel
In-Reply-To: <1485365126-23210-14-git-send-email-hch@lst.de>
>>>>> "Christoph" == Christoph Hellwig <hch@lst.de> writes:
Christoph> There is no need for GFP_DMA allocations of the scsi_cmnd
Christoph> structures themselves, all that might be DMAed to or from is
Christoph> the actual payload, or the sense buffers.
Acked-by: Martin K. Petersen <martin.petersen@oracle.com>
--
Martin K. Petersen Oracle Linux Engineering
^ permalink raw reply
* Re: [PATCH 14/18] scsi: remove __scsi_alloc_queue
From: Martin K. Petersen @ 2017-01-26 3:25 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Jens Axboe, Mike Snitzer, Junichi Nomura, linux-block, linux-scsi,
linux-raid, dm-devel
In-Reply-To: <1485365126-23210-15-git-send-email-hch@lst.de>
>>>>> "Christoph" == Christoph Hellwig <hch@lst.de> writes:
Christoph> Instead do an internal export of __scsi_init_queue for the
Christoph> transport classes that export BSG nodes.
Acked-by: Martin K. Petersen <martin.petersen@oracle.com>
--
Martin K. Petersen Oracle Linux Engineering
^ permalink raw reply
* Re: [PATCH 15/18] scsi: allocate scsi_cmnd structures as part of struct request
From: Martin K. Petersen @ 2017-01-26 3:30 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Jens Axboe, Mike Snitzer, Junichi Nomura, linux-block, linux-scsi,
linux-raid, dm-devel
In-Reply-To: <1485365126-23210-16-git-send-email-hch@lst.de>
>>>>> "Christoph" == Christoph Hellwig <hch@lst.de> writes:
Christoph> Rely on the new block layer functionality to allocate
Christoph> additional driver specific data behind struct request instead
Christoph> of implementing it in SCSI itѕelf.
Acked-by: Martin K. Petersen <martin.petersen@oracle.com>
--
Martin K. Petersen Oracle Linux Engineering
^ permalink raw reply
* Re: [PATCH 18/18] block: don't assign cmd_flags in __blk_rq_prep_clone
From: Martin K. Petersen @ 2017-01-26 3:31 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Jens Axboe, Mike Snitzer, Junichi Nomura, linux-block, linux-scsi,
linux-raid, dm-devel
In-Reply-To: <1485365126-23210-19-git-send-email-hch@lst.de>
>>>>> "Christoph" == Christoph Hellwig <hch@lst.de> writes:
Christoph> These days we have the proper flags set since request
Christoph> allocation time.
Acked-by: Martin K. Petersen <martin.petersen@oracle.com>
--
Martin K. Petersen Oracle Linux Engineering
^ permalink raw reply
* Re: performance collapse: 9 mio IOPS to 1.5 mio with MD RAID0
From: Tobias Oberstein @ 2017-01-26 8:35 UTC (permalink / raw)
To: Stan Hoeppner, linux-raid
In-Reply-To: <1d766141-465b-34f2-dbd6-b7f71ecc344c@hardwarefreak.org>
Am 26.01.2017 um 00:01 schrieb Stan Hoeppner:
> On 01/25/2017 05:45 AM, Tobias Oberstein wrote:
>> Hi,
>>
>> I have a storage consisting of 8 NVMe drives (16 logical drives) that
>> I verified (FIO) is able to do >9 million 4kB random read IOPS if I
>> run FIO on the set of individual NVMes.
>>
>> However, when I create a MD (RAID-0) over the 16 NVMes and run the
>> same tests, performance collapses:
>>
>> ioengine=sync, invidual NVMes: IOPS=9191k
>> ioengine=sync, MD (RAID-0) over NVMes: IOPS=1562k
>>
>> Using ioengine=psync, the performance collapse isn't as dramatic, but
>> still very signifcant:
>>
>> ioengine=sync, invidual NVMes: IOPS=9395k
>> ioengine=sync, MD (RAID-0) over NVMes: IOPS=4117k
>>
>> --
>>
>> All detail results (including runs under Linux perf) and FIO control
>> files are here
>>
>> https://github.com/oberstet/scratchbox/tree/master/cruncher/sync-engines-perf
>>
>>
>
> You don't need 1024 jobs to fill the request queues. Just out of
Here is scaling of measured IOPS depending on concurrency for sync engines
https://github.com/oberstet/scratchbox/raw/master/cruncher/Performance%20Results%20-%20NVMe%20Scaling%20with%20IO%20Concurrency.pdf
Note: the top numbers are lower than in what I posted above, because
these measurements were still done with 512 bytes sectors (not with 4k
as above).
> curiosity, what are the fio results when using fewer jobs and a greater
> queue depth, say one job per core, 88 total, with a queue depth of 32?
iodeapth doesn't apply to synchronous io engines (ioengine=sync/psync/..)
>
> osq_lock appears to be a per cpu opportunistic spinlock. Might be of
> benefit to try even fewer jobs for fewer active cores.
with reduced concurrency, I am not able to saturate the storage anymore
in essence, 1 Xeon core is needed per 120k IOPS with ioengine=sync even
on the set of raw NVMe devices (no MD RAID).
for comparison: libaio achieves 600k IOPS / core
SPDK claims (I haven't measured that myself .. Intel claim):
1.8 mio IOPS / core
Cheers,
/Tobias
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox