summaryrefslogtreecommitdiff
path: root/drivers/block
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/block')
-rw-r--r--drivers/block/aoe/aoecmd.c1
-rw-r--r--drivers/block/cciss_scsi.c1
-rw-r--r--drivers/block/drbd/drbd_bitmap.c15
-rw-r--r--drivers/block/drbd/drbd_int.h1
-rw-r--r--drivers/block/drbd/drbd_main.c28
-rw-r--r--drivers/block/drbd/drbd_nl.c4
-rw-r--r--drivers/block/drbd/drbd_req.c36
-rw-r--r--drivers/block/mtip32xx/mtip32xx.c38
-rw-r--r--drivers/block/mtip32xx/mtip32xx.h10
-rw-r--r--drivers/block/nbd.c9
-rw-r--r--drivers/block/nvme.c153
-rw-r--r--drivers/block/rbd.c7
-rw-r--r--drivers/block/xen-blkback/blkback.c2
13 files changed, 211 insertions, 94 deletions
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index de0435e63b02..887f68f6d79a 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -35,6 +35,7 @@ new_skb(ulong len)
skb_reset_mac_header(skb);
skb_reset_network_header(skb);
skb->protocol = __constant_htons(ETH_P_AOE);
+ skb_checksum_none_assert(skb);
}
return skb;
}
diff --git a/drivers/block/cciss_scsi.c b/drivers/block/cciss_scsi.c
index 38aa6dda6b81..da3311129a0c 100644
--- a/drivers/block/cciss_scsi.c
+++ b/drivers/block/cciss_scsi.c
@@ -795,6 +795,7 @@ static void complete_scsi_command(CommandList_struct *c, int timeout,
}
break;
case CMD_PROTOCOL_ERR:
+ cmd->result = DID_ERROR << 16;
dev_warn(&h->pdev->dev,
"%p has protocol error\n", c);
break;
diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c
index ba91b408abad..d84566496746 100644
--- a/drivers/block/drbd/drbd_bitmap.c
+++ b/drivers/block/drbd/drbd_bitmap.c
@@ -889,6 +889,7 @@ struct bm_aio_ctx {
unsigned int done;
unsigned flags;
#define BM_AIO_COPY_PAGES 1
+#define BM_WRITE_ALL_PAGES 2
int error;
struct kref kref;
};
@@ -1059,7 +1060,8 @@ static int bm_rw(struct drbd_conf *mdev, int rw, unsigned flags, unsigned lazy_w
if (lazy_writeout_upper_idx && i == lazy_writeout_upper_idx)
break;
if (rw & WRITE) {
- if (bm_test_page_unchanged(b->bm_pages[i])) {
+ if (!(flags & BM_WRITE_ALL_PAGES) &&
+ bm_test_page_unchanged(b->bm_pages[i])) {
dynamic_dev_dbg(DEV, "skipped bm write for idx %u\n", i);
continue;
}
@@ -1141,6 +1143,17 @@ int drbd_bm_write(struct drbd_conf *mdev) __must_hold(local)
}
/**
+ * drbd_bm_write_all() - Write the whole bitmap to its on disk location.
+ * @mdev: DRBD device.
+ *
+ * Will write all pages.
+ */
+int drbd_bm_write_all(struct drbd_conf *mdev) __must_hold(local)
+{
+ return bm_rw(mdev, WRITE, BM_WRITE_ALL_PAGES, 0);
+}
+
+/**
* drbd_bm_lazy_write_out() - Write bitmap pages 0 to @upper_idx-1, if they have changed.
* @mdev: DRBD device.
* @upper_idx: 0: write all changed pages; +ve: page index to stop scanning for changed pages
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index b2ca143d0053..b953cc7c9c00 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1469,6 +1469,7 @@ extern int drbd_bm_e_weight(struct drbd_conf *mdev, unsigned long enr);
extern int drbd_bm_write_page(struct drbd_conf *mdev, unsigned int idx) __must_hold(local);
extern int drbd_bm_read(struct drbd_conf *mdev) __must_hold(local);
extern int drbd_bm_write(struct drbd_conf *mdev) __must_hold(local);
+extern int drbd_bm_write_all(struct drbd_conf *mdev) __must_hold(local);
extern int drbd_bm_write_copy_pages(struct drbd_conf *mdev) __must_hold(local);
extern unsigned long drbd_bm_ALe_set_all(struct drbd_conf *mdev,
unsigned long al_enr);
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index dbe6135a2abe..f93a0320e952 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -79,6 +79,7 @@ static int w_md_sync(struct drbd_conf *mdev, struct drbd_work *w, int unused);
static void md_sync_timer_fn(unsigned long data);
static int w_bitmap_io(struct drbd_conf *mdev, struct drbd_work *w, int unused);
static int w_go_diskless(struct drbd_conf *mdev, struct drbd_work *w, int unused);
+static void _tl_clear(struct drbd_conf *mdev);
MODULE_AUTHOR("Philipp Reisner <phil@linbit.com>, "
"Lars Ellenberg <lars@linbit.com>");
@@ -432,19 +433,10 @@ static void _tl_restart(struct drbd_conf *mdev, enum drbd_req_event what)
/* Actions operating on the disk state, also want to work on
requests that got barrier acked. */
- switch (what) {
- case fail_frozen_disk_io:
- case restart_frozen_disk_io:
- list_for_each_safe(le, tle, &mdev->barrier_acked_requests) {
- req = list_entry(le, struct drbd_request, tl_requests);
- _req_mod(req, what);
- }
- case connection_lost_while_pending:
- case resend:
- break;
- default:
- dev_err(DEV, "what = %d in _tl_restart()\n", what);
+ list_for_each_safe(le, tle, &mdev->barrier_acked_requests) {
+ req = list_entry(le, struct drbd_request, tl_requests);
+ _req_mod(req, what);
}
}
@@ -459,11 +451,16 @@ static void _tl_restart(struct drbd_conf *mdev, enum drbd_req_event what)
*/
void tl_clear(struct drbd_conf *mdev)
{
+ spin_lock_irq(&mdev->req_lock);
+ _tl_clear(mdev);
+ spin_unlock_irq(&mdev->req_lock);
+}
+
+static void _tl_clear(struct drbd_conf *mdev)
+{
struct list_head *le, *tle;
struct drbd_request *r;
- spin_lock_irq(&mdev->req_lock);
-
_tl_restart(mdev, connection_lost_while_pending);
/* we expect this list to be empty. */
@@ -482,7 +479,6 @@ void tl_clear(struct drbd_conf *mdev)
memset(mdev->app_reads_hash, 0, APP_R_HSIZE*sizeof(void *));
- spin_unlock_irq(&mdev->req_lock);
}
void tl_restart(struct drbd_conf *mdev, enum drbd_req_event what)
@@ -1476,12 +1472,12 @@ static void after_state_ch(struct drbd_conf *mdev, union drbd_state os,
if (ns.susp_fen) {
/* case1: The outdate peer handler is successful: */
if (os.pdsk > D_OUTDATED && ns.pdsk <= D_OUTDATED) {
- tl_clear(mdev);
if (test_bit(NEW_CUR_UUID, &mdev->flags)) {
drbd_uuid_new_current(mdev);
clear_bit(NEW_CUR_UUID, &mdev->flags);
}
spin_lock_irq(&mdev->req_lock);
+ _tl_clear(mdev);
_drbd_set_state(_NS(mdev, susp_fen, 0), CS_VERBOSE, NULL);
spin_unlock_irq(&mdev->req_lock);
}
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index fb9dce8daa24..edb490aad8b4 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -674,8 +674,8 @@ enum determine_dev_size drbd_determine_dev_size(struct drbd_conf *mdev, enum dds
la_size_changed && md_moved ? "size changed and md moved" :
la_size_changed ? "size changed" : "md moved");
/* next line implicitly does drbd_suspend_io()+drbd_resume_io() */
- err = drbd_bitmap_io(mdev, &drbd_bm_write,
- "size changed", BM_LOCKED_MASK);
+ err = drbd_bitmap_io(mdev, md_moved ? &drbd_bm_write_all : &drbd_bm_write,
+ "size changed", BM_LOCKED_MASK);
if (err) {
rv = dev_size_error;
goto out;
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 910335c30927..01b2ac641c7b 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -695,6 +695,12 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what,
break;
case resend:
+ /* Simply complete (local only) READs. */
+ if (!(req->rq_state & RQ_WRITE) && !req->w.cb) {
+ _req_may_be_done(req, m);
+ break;
+ }
+
/* If RQ_NET_OK is already set, we got a P_WRITE_ACK or P_RECV_ACK
before the connection loss (B&C only); only P_BARRIER_ACK was missing.
Trowing them out of the TL here by pretending we got a BARRIER_ACK
@@ -834,7 +840,15 @@ static int drbd_make_request_common(struct drbd_conf *mdev, struct bio *bio, uns
req->private_bio = NULL;
}
if (rw == WRITE) {
- remote = 1;
+ /* Need to replicate writes. Unless it is an empty flush,
+ * which is better mapped to a DRBD P_BARRIER packet,
+ * also for drbd wire protocol compatibility reasons. */
+ if (unlikely(size == 0)) {
+ /* The only size==0 bios we expect are empty flushes. */
+ D_ASSERT(bio->bi_rw & REQ_FLUSH);
+ remote = 0;
+ } else
+ remote = 1;
} else {
/* READ || READA */
if (local) {
@@ -870,8 +884,11 @@ static int drbd_make_request_common(struct drbd_conf *mdev, struct bio *bio, uns
* extent. This waits for any resync activity in the corresponding
* resync extent to finish, and, if necessary, pulls in the target
* extent into the activity log, which involves further disk io because
- * of transactional on-disk meta data updates. */
- if (rw == WRITE && local && !test_bit(AL_SUSPENDED, &mdev->flags)) {
+ * of transactional on-disk meta data updates.
+ * Empty flushes don't need to go into the activity log, they can only
+ * flush data for pending writes which are already in there. */
+ if (rw == WRITE && local && size
+ && !test_bit(AL_SUSPENDED, &mdev->flags)) {
req->rq_state |= RQ_IN_ACT_LOG;
drbd_al_begin_io(mdev, sector);
}
@@ -994,7 +1011,10 @@ allocate_barrier:
if (rw == WRITE && _req_conflicts(req))
goto fail_conflicting;
- list_add_tail(&req->tl_requests, &mdev->newest_tle->requests);
+ /* no point in adding empty flushes to the transfer log,
+ * they are mapped to drbd barriers already. */
+ if (likely(size!=0))
+ list_add_tail(&req->tl_requests, &mdev->newest_tle->requests);
/* NOTE remote first: to get the concurrent write detection right,
* we must register the request before start of local IO. */
@@ -1014,6 +1034,14 @@ allocate_barrier:
mdev->net_conf->on_congestion != OC_BLOCK && mdev->agreed_pro_version >= 96)
maybe_pull_ahead(mdev);
+ /* If this was a flush, queue a drbd barrier/start a new epoch.
+ * Unless the current epoch was empty anyways, or we are not currently
+ * replicating, in which case there is no point. */
+ if (unlikely(bio->bi_rw & REQ_FLUSH)
+ && mdev->newest_tle->n_writes
+ && drbd_should_do_remote(mdev->state))
+ queue_barrier(mdev);
+
spin_unlock_irq(&mdev->req_lock);
kfree(b); /* if someone else has beaten us to it... */
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index a8fddeb3d638..f946d31d6917 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -1148,11 +1148,15 @@ static bool mtip_pause_ncq(struct mtip_port *port,
reply = port->rxfis + RX_FIS_D2H_REG;
task_file_data = readl(port->mmio+PORT_TFDATA);
- if ((task_file_data & 1) || (fis->command == ATA_CMD_SEC_ERASE_UNIT))
+ if (fis->command == ATA_CMD_SEC_ERASE_UNIT)
+ clear_bit(MTIP_DDF_SEC_LOCK_BIT, &port->dd->dd_flag);
+
+ if ((task_file_data & 1))
return false;
if (fis->command == ATA_CMD_SEC_ERASE_PREP) {
set_bit(MTIP_PF_SE_ACTIVE_BIT, &port->flags);
+ set_bit(MTIP_DDF_SEC_LOCK_BIT, &port->dd->dd_flag);
port->ic_pause_timer = jiffies;
return true;
} else if ((fis->command == ATA_CMD_DOWNLOAD_MICRO) &&
@@ -1900,7 +1904,7 @@ static int exec_drive_command(struct mtip_port *port, u8 *command,
int rv = 0, xfer_sz = command[3];
if (xfer_sz) {
- if (user_buffer)
+ if (!user_buffer)
return -EFAULT;
buf = dmam_alloc_coherent(&port->dd->pdev->dev,
@@ -2043,7 +2047,7 @@ static void mtip_set_timeout(struct host_to_dev_fis *fis, unsigned int *timeout)
*timeout = 240000; /* 4 minutes */
break;
case ATA_CMD_STANDBYNOW1:
- *timeout = 10000; /* 10 seconds */
+ *timeout = 120000; /* 2 minutes */
break;
case 0xF7:
case 0xFA:
@@ -2588,9 +2592,6 @@ static ssize_t mtip_hw_read_registers(struct file *f, char __user *ubuf,
if (!len || size)
return 0;
- if (size < 0)
- return -EINVAL;
-
size += sprintf(&buf[size], "H/ S ACTive : [ 0x");
for (n = dd->slot_groups-1; n >= 0; n--)
@@ -2660,9 +2661,6 @@ static ssize_t mtip_hw_read_flags(struct file *f, char __user *ubuf,
if (!len || size)
return 0;
- if (size < 0)
- return -EINVAL;
-
size += sprintf(&buf[size], "Flag-port : [ %08lX ]\n",
dd->port->flags);
size += sprintf(&buf[size], "Flag-dd : [ %08lX ]\n",
@@ -3214,8 +3212,8 @@ static int mtip_hw_init(struct driver_data *dd)
"Unable to check write protect progress\n");
else
dev_info(&dd->pdev->dev,
- "Write protect progress: %d%% (%d blocks)\n",
- attr242.cur, attr242.data);
+ "Write protect progress: %u%% (%u blocks)\n",
+ attr242.cur, le32_to_cpu(attr242.data));
return rv;
out3:
@@ -3619,6 +3617,10 @@ static void mtip_make_request(struct request_queue *queue, struct bio *bio)
bio_endio(bio, -ENODATA);
return;
}
+ if (unlikely(test_bit(MTIP_DDF_SEC_LOCK_BIT, &dd->dd_flag))) {
+ bio_endio(bio, -ENODATA);
+ return;
+ }
}
if (unlikely(!bio_has_data(bio))) {
@@ -4168,7 +4170,13 @@ static void mtip_pci_shutdown(struct pci_dev *pdev)
/* Table of device ids supported by this driver. */
static DEFINE_PCI_DEVICE_TABLE(mtip_pci_tbl) = {
- { PCI_DEVICE(PCI_VENDOR_ID_MICRON, P320_DEVICE_ID) },
+ { PCI_DEVICE(PCI_VENDOR_ID_MICRON, P320H_DEVICE_ID) },
+ { PCI_DEVICE(PCI_VENDOR_ID_MICRON, P320M_DEVICE_ID) },
+ { PCI_DEVICE(PCI_VENDOR_ID_MICRON, P320S_DEVICE_ID) },
+ { PCI_DEVICE(PCI_VENDOR_ID_MICRON, P325M_DEVICE_ID) },
+ { PCI_DEVICE(PCI_VENDOR_ID_MICRON, P420H_DEVICE_ID) },
+ { PCI_DEVICE(PCI_VENDOR_ID_MICRON, P420M_DEVICE_ID) },
+ { PCI_DEVICE(PCI_VENDOR_ID_MICRON, P425M_DEVICE_ID) },
{ 0 }
};
@@ -4199,12 +4207,12 @@ static int __init mtip_init(void)
{
int error;
- printk(KERN_INFO MTIP_DRV_NAME " Version " MTIP_DRV_VERSION "\n");
+ pr_info(MTIP_DRV_NAME " Version " MTIP_DRV_VERSION "\n");
/* Allocate a major block device number to use with this driver. */
error = register_blkdev(0, MTIP_DRV_NAME);
if (error <= 0) {
- printk(KERN_ERR "Unable to register block device (%d)\n",
+ pr_err("Unable to register block device (%d)\n",
error);
return -EBUSY;
}
@@ -4213,7 +4221,7 @@ static int __init mtip_init(void)
if (!dfs_parent) {
dfs_parent = debugfs_create_dir("rssd", NULL);
if (IS_ERR_OR_NULL(dfs_parent)) {
- printk(KERN_WARNING "Error creating debugfs parent\n");
+ pr_warn("Error creating debugfs parent\n");
dfs_parent = NULL;
}
}
diff --git a/drivers/block/mtip32xx/mtip32xx.h b/drivers/block/mtip32xx/mtip32xx.h
index f51fc23d17bb..18627a1d04c5 100644
--- a/drivers/block/mtip32xx/mtip32xx.h
+++ b/drivers/block/mtip32xx/mtip32xx.h
@@ -76,7 +76,13 @@
/* Micron Vendor ID & P320x SSD Device ID */
#define PCI_VENDOR_ID_MICRON 0x1344
-#define P320_DEVICE_ID 0x5150
+#define P320H_DEVICE_ID 0x5150
+#define P320M_DEVICE_ID 0x5151
+#define P320S_DEVICE_ID 0x5152
+#define P325M_DEVICE_ID 0x5153
+#define P420H_DEVICE_ID 0x5160
+#define P420M_DEVICE_ID 0x5161
+#define P425M_DEVICE_ID 0x5163
/* Driver name and version strings */
#define MTIP_DRV_NAME "mtip32xx"
@@ -131,10 +137,12 @@ enum {
MTIP_PF_SVC_THD_STOP_BIT = 8,
/* below are bit numbers in 'dd_flag' defined in driver_data */
+ MTIP_DDF_SEC_LOCK_BIT = 0,
MTIP_DDF_REMOVE_PENDING_BIT = 1,
MTIP_DDF_OVER_TEMP_BIT = 2,
MTIP_DDF_WRITE_PROTECT_BIT = 3,
MTIP_DDF_STOP_IO = ((1 << MTIP_DDF_REMOVE_PENDING_BIT) | \
+ (1 << MTIP_DDF_SEC_LOCK_BIT) | \
(1 << MTIP_DDF_OVER_TEMP_BIT) | \
(1 << MTIP_DDF_WRITE_PROTECT_BIT)),
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index d07c9f7fded6..0c03411c59eb 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -449,6 +449,14 @@ static void nbd_clear_que(struct nbd_device *nbd)
req->errors++;
nbd_end_request(req);
}
+
+ while (!list_empty(&nbd->waiting_queue)) {
+ req = list_entry(nbd->waiting_queue.next, struct request,
+ queuelist);
+ list_del_init(&req->queuelist);
+ req->errors++;
+ nbd_end_request(req);
+ }
}
@@ -598,6 +606,7 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
nbd->file = NULL;
nbd_clear_que(nbd);
BUG_ON(!list_empty(&nbd->queue_head));
+ BUG_ON(!list_empty(&nbd->waiting_queue));
if (file)
fput(file);
return 0;
diff --git a/drivers/block/nvme.c b/drivers/block/nvme.c
index 38a2d0631882..ad16c68c8645 100644
--- a/drivers/block/nvme.c
+++ b/drivers/block/nvme.c
@@ -79,6 +79,7 @@ struct nvme_dev {
char serial[20];
char model[40];
char firmware_rev[8];
+ u32 max_hw_sectors;
};
/*
@@ -835,15 +836,15 @@ static int nvme_identify(struct nvme_dev *dev, unsigned nsid, unsigned cns,
}
static int nvme_get_features(struct nvme_dev *dev, unsigned fid,
- unsigned dword11, dma_addr_t dma_addr)
+ unsigned nsid, dma_addr_t dma_addr)
{
struct nvme_command c;
memset(&c, 0, sizeof(c));
c.features.opcode = nvme_admin_get_features;
+ c.features.nsid = cpu_to_le32(nsid);
c.features.prp1 = cpu_to_le64(dma_addr);
c.features.fid = cpu_to_le32(fid);
- c.features.dword11 = cpu_to_le32(dword11);
return nvme_submit_admin_cmd(dev, &c, NULL);
}
@@ -862,11 +863,51 @@ static int nvme_set_features(struct nvme_dev *dev, unsigned fid,
return nvme_submit_admin_cmd(dev, &c, result);
}
+/**
+ * nvme_cancel_ios - Cancel outstanding I/Os
+ * @queue: The queue to cancel I/Os on
+ * @timeout: True to only cancel I/Os which have timed out
+ */
+static void nvme_cancel_ios(struct nvme_queue *nvmeq, bool timeout)
+{
+ int depth = nvmeq->q_depth - 1;
+ struct nvme_cmd_info *info = nvme_cmd_info(nvmeq);
+ unsigned long now = jiffies;
+ int cmdid;
+
+ for_each_set_bit(cmdid, nvmeq->cmdid_data, depth) {
+ void *ctx;
+ nvme_completion_fn fn;
+ static struct nvme_completion cqe = {
+ .status = cpu_to_le16(NVME_SC_ABORT_REQ) << 1,
+ };
+
+ if (timeout && !time_after(now, info[cmdid].timeout))
+ continue;
+ dev_warn(nvmeq->q_dmadev, "Cancelling I/O %d\n", cmdid);
+ ctx = cancel_cmdid(nvmeq, cmdid, &fn);
+ fn(nvmeq->dev, ctx, &cqe);
+ }
+}
+
+static void nvme_free_queue_mem(struct nvme_queue *nvmeq)
+{
+ dma_free_coherent(nvmeq->q_dmadev, CQ_SIZE(nvmeq->q_depth),
+ (void *)nvmeq->cqes, nvmeq->cq_dma_addr);
+ dma_free_coherent(nvmeq->q_dmadev, SQ_SIZE(nvmeq->q_depth),
+ nvmeq->sq_cmds, nvmeq->sq_dma_addr);
+ kfree(nvmeq);
+}
+
static void nvme_free_queue(struct nvme_dev *dev, int qid)
{
struct nvme_queue *nvmeq = dev->queues[qid];
int vector = dev->entry[nvmeq->cq_vector].vector;
+ spin_lock_irq(&nvmeq->q_lock);
+ nvme_cancel_ios(nvmeq, false);
+ spin_unlock_irq(&nvmeq->q_lock);
+
irq_set_affinity_hint(vector, NULL);
free_irq(vector, nvmeq);
@@ -876,18 +917,15 @@ static void nvme_free_queue(struct nvme_dev *dev, int qid)
adapter_delete_cq(dev, qid);
}
- dma_free_coherent(nvmeq->q_dmadev, CQ_SIZE(nvmeq->q_depth),
- (void *)nvmeq->cqes, nvmeq->cq_dma_addr);
- dma_free_coherent(nvmeq->q_dmadev, SQ_SIZE(nvmeq->q_depth),
- nvmeq->sq_cmds, nvmeq->sq_dma_addr);
- kfree(nvmeq);
+ nvme_free_queue_mem(nvmeq);
}
static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
int depth, int vector)
{
struct device *dmadev = &dev->pci_dev->dev;
- unsigned extra = (depth / 8) + (depth * sizeof(struct nvme_cmd_info));
+ unsigned extra = DIV_ROUND_UP(depth, 8) + (depth *
+ sizeof(struct nvme_cmd_info));
struct nvme_queue *nvmeq = kzalloc(sizeof(*nvmeq) + extra, GFP_KERNEL);
if (!nvmeq)
return NULL;
@@ -975,7 +1013,7 @@ static __devinit struct nvme_queue *nvme_create_queue(struct nvme_dev *dev,
static int __devinit nvme_configure_admin_queue(struct nvme_dev *dev)
{
- int result;
+ int result = 0;
u32 aqa;
u64 cap;
unsigned long timeout;
@@ -1005,17 +1043,22 @@ static int __devinit nvme_configure_admin_queue(struct nvme_dev *dev)
timeout = ((NVME_CAP_TIMEOUT(cap) + 1) * HZ / 2) + jiffies;
dev->db_stride = NVME_CAP_STRIDE(cap);
- while (!(readl(&dev->bar->csts) & NVME_CSTS_RDY)) {
+ while (!result && !(readl(&dev->bar->csts) & NVME_CSTS_RDY)) {
msleep(100);
if (fatal_signal_pending(current))
- return -EINTR;
+ result = -EINTR;
if (time_after(jiffies, timeout)) {
dev_err(&dev->pci_dev->dev,
"Device not ready; aborting initialisation\n");
- return -ENODEV;
+ result = -ENODEV;
}
}
+ if (result) {
+ nvme_free_queue_mem(nvmeq);
+ return result;
+ }
+
result = queue_request_irq(dev, nvmeq, "nvme admin");
dev->queues[0] = nvmeq;
return result;
@@ -1037,6 +1080,8 @@ static struct nvme_iod *nvme_map_user_pages(struct nvme_dev *dev, int write,
offset = offset_in_page(addr);
count = DIV_ROUND_UP(offset + length, PAGE_SIZE);
pages = kcalloc(count, sizeof(*pages), GFP_KERNEL);
+ if (!pages)
+ return ERR_PTR(-ENOMEM);
err = get_user_pages_fast(addr, count, 1, pages);
if (err < count) {
@@ -1146,14 +1191,13 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
return status;
}
-static int nvme_user_admin_cmd(struct nvme_ns *ns,
+static int nvme_user_admin_cmd(struct nvme_dev *dev,
struct nvme_admin_cmd __user *ucmd)
{
- struct nvme_dev *dev = ns->dev;
struct nvme_admin_cmd cmd;
struct nvme_command c;
int status, length;
- struct nvme_iod *iod;
+ struct nvme_iod *uninitialized_var(iod);
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
@@ -1204,7 +1248,7 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd,
case NVME_IOCTL_ID:
return ns->ns_id;
case NVME_IOCTL_ADMIN_CMD:
- return nvme_user_admin_cmd(ns, (void __user *)arg);
+ return nvme_user_admin_cmd(ns->dev, (void __user *)arg);
case NVME_IOCTL_SUBMIT_IO:
return nvme_submit_io(ns, (void __user *)arg);
default:
@@ -1218,26 +1262,6 @@ static const struct block_device_operations nvme_fops = {
.compat_ioctl = nvme_ioctl,
};
-static void nvme_timeout_ios(struct nvme_queue *nvmeq)
-{
- int depth = nvmeq->q_depth - 1;
- struct nvme_cmd_info *info = nvme_cmd_info(nvmeq);
- unsigned long now = jiffies;
- int cmdid;
-
- for_each_set_bit(cmdid, nvmeq->cmdid_data, depth) {
- void *ctx;
- nvme_completion_fn fn;
- static struct nvme_completion cqe = { .status = cpu_to_le16(NVME_SC_ABORT_REQ) << 1, };
-
- if (!time_after(now, info[cmdid].timeout))
- continue;
- dev_warn(nvmeq->q_dmadev, "Timing out I/O %d\n", cmdid);
- ctx = cancel_cmdid(nvmeq, cmdid, &fn);
- fn(nvmeq->dev, ctx, &cqe);
- }
-}
-
static void nvme_resubmit_bios(struct nvme_queue *nvmeq)
{
while (bio_list_peek(&nvmeq->sq_cong)) {
@@ -1269,7 +1293,7 @@ static int nvme_kthread(void *data)
spin_lock_irq(&nvmeq->q_lock);
if (nvme_process_cq(nvmeq))
printk("process_cq did something\n");
- nvme_timeout_ios(nvmeq);
+ nvme_cancel_ios(nvmeq, true);
nvme_resubmit_bios(nvmeq);
spin_unlock_irq(&nvmeq->q_lock);
}
@@ -1339,6 +1363,9 @@ static struct nvme_ns *nvme_alloc_ns(struct nvme_dev *dev, int nsid,
ns->disk = disk;
lbaf = id->flbas & 0xf;
ns->lba_shift = id->lbaf[lbaf].ds;
+ blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift);
+ if (dev->max_hw_sectors)
+ blk_queue_max_hw_sectors(ns->queue, dev->max_hw_sectors);
disk->major = nvme_major;
disk->minors = NVME_MINORS;
@@ -1383,7 +1410,7 @@ static int set_queue_count(struct nvme_dev *dev, int count)
static int __devinit nvme_setup_io_queues(struct nvme_dev *dev)
{
- int result, cpu, i, nr_io_queues, db_bar_size;
+ int result, cpu, i, nr_io_queues, db_bar_size, q_depth;
nr_io_queues = num_online_cpus();
result = set_queue_count(dev, nr_io_queues);
@@ -1429,9 +1456,10 @@ static int __devinit nvme_setup_io_queues(struct nvme_dev *dev)
cpu = cpumask_next(cpu, cpu_online_mask);
}
+ q_depth = min_t(int, NVME_CAP_MQES(readq(&dev->bar->cap)) + 1,
+ NVME_Q_DEPTH);
for (i = 0; i < nr_io_queues; i++) {
- dev->queues[i + 1] = nvme_create_queue(dev, i + 1,
- NVME_Q_DEPTH, i);
+ dev->queues[i + 1] = nvme_create_queue(dev, i + 1, q_depth, i);
if (IS_ERR(dev->queues[i + 1]))
return PTR_ERR(dev->queues[i + 1]);
dev->queue_count++;
@@ -1480,6 +1508,10 @@ static int __devinit nvme_dev_add(struct nvme_dev *dev)
memcpy(dev->serial, ctrl->sn, sizeof(ctrl->sn));
memcpy(dev->model, ctrl->mn, sizeof(ctrl->mn));
memcpy(dev->firmware_rev, ctrl->fr, sizeof(ctrl->fr));
+ if (ctrl->mdts) {
+ int shift = NVME_CAP_MPSMIN(readq(&dev->bar->cap)) + 12;
+ dev->max_hw_sectors = 1 << (ctrl->mdts + shift - 9);
+ }
id_ns = mem;
for (i = 1; i <= nn; i++) {
@@ -1523,8 +1555,6 @@ static int nvme_dev_remove(struct nvme_dev *dev)
list_del(&dev->node);
spin_unlock(&dev_list_lock);
- /* TODO: wait all I/O finished or cancel them */
-
list_for_each_entry_safe(ns, next, &dev->namespaces, list) {
list_del(&ns->list);
del_gendisk(ns->disk);
@@ -1560,15 +1590,33 @@ static void nvme_release_prp_pools(struct nvme_dev *dev)
dma_pool_destroy(dev->prp_small_pool);
}
-/* XXX: Use an ida or something to let remove / add work correctly */
-static void nvme_set_instance(struct nvme_dev *dev)
+static DEFINE_IDA(nvme_instance_ida);
+
+static int nvme_set_instance(struct nvme_dev *dev)
{
- static int instance;
- dev->instance = instance++;
+ int instance, error;
+
+ do {
+ if (!ida_pre_get(&nvme_instance_ida, GFP_KERNEL))
+ return -ENODEV;
+
+ spin_lock(&dev_list_lock);
+ error = ida_get_new(&nvme_instance_ida, &instance);
+ spin_unlock(&dev_list_lock);
+ } while (error == -EAGAIN);
+
+ if (error)
+ return -ENODEV;
+
+ dev->instance = instance;
+ return 0;
}
static void nvme_release_instance(struct nvme_dev *dev)
{
+ spin_lock(&dev_list_lock);
+ ida_remove(&nvme_instance_ida, dev->instance);
+ spin_unlock(&dev_list_lock);
}
static int __devinit nvme_probe(struct pci_dev *pdev,
@@ -1601,7 +1649,10 @@ static int __devinit nvme_probe(struct pci_dev *pdev,
pci_set_drvdata(pdev, dev);
dma_set_mask(&pdev->dev, DMA_BIT_MASK(64));
dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64));
- nvme_set_instance(dev);
+ result = nvme_set_instance(dev);
+ if (result)
+ goto disable;
+
dev->entry[0].vector = pdev->irq;
result = nvme_setup_prp_pools(dev);
@@ -1704,15 +1755,17 @@ static struct pci_driver nvme_driver = {
static int __init nvme_init(void)
{
- int result = -EBUSY;
+ int result;
nvme_thread = kthread_run(nvme_kthread, NULL, "nvme");
if (IS_ERR(nvme_thread))
return PTR_ERR(nvme_thread);
- nvme_major = register_blkdev(nvme_major, "nvme");
- if (nvme_major <= 0)
+ result = register_blkdev(nvme_major, "nvme");
+ if (result < 0)
goto kill_kthread;
+ else if (result > 0)
+ nvme_major = result;
result = pci_register_driver(&nvme_driver);
if (result)
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 9917943a3572..54a55f03115d 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -246,13 +246,12 @@ static int rbd_open(struct block_device *bdev, fmode_t mode)
{
struct rbd_device *rbd_dev = bdev->bd_disk->private_data;
- rbd_get_dev(rbd_dev);
-
- set_device_ro(bdev, rbd_dev->read_only);
-
if ((mode & FMODE_WRITE) && rbd_dev->read_only)
return -EROFS;
+ rbd_get_dev(rbd_dev);
+ set_device_ro(bdev, rbd_dev->read_only);
+
return 0;
}
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index 73f196ca713f..c6decb901e5e 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -337,7 +337,7 @@ static void xen_blkbk_unmap(struct pending_req *req)
invcount++;
}
- ret = gnttab_unmap_refs(unmap, pages, invcount, false);
+ ret = gnttab_unmap_refs(unmap, NULL, pages, invcount);
BUG_ON(ret);
}
generated by cgit v1.2.3 (git 2.39.0) at 2025-01-16 09:14:03 +0300