summaryrefslogtreecommitdiffstats
path: root/drivers/block
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/block')
-rw-r--r--drivers/block/Kconfig2
-rw-r--r--drivers/block/Makefile1
-rw-r--r--drivers/block/nvme-core.c610
-rw-r--r--drivers/block/nvme-scsi.c147
-rw-r--r--drivers/block/zram/Kconfig24
-rw-r--r--drivers/block/zram/Makefile3
-rw-r--r--drivers/block/zram/zram_drv.c958
-rw-r--r--drivers/block/zram/zram_drv.h109
8 files changed, 1749 insertions, 105 deletions
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index 9ffa90c6201c..014a1cfc41c5 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -108,6 +108,8 @@ source "drivers/block/paride/Kconfig"
source "drivers/block/mtip32xx/Kconfig"
+source "drivers/block/zram/Kconfig"
+
config BLK_CPQ_DA
tristate "Compaq SMART2 support"
depends on PCI && VIRT_TO_BUS && 0
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index 816d979c3266..02b688d1438d 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -42,6 +42,7 @@ obj-$(CONFIG_BLK_DEV_PCIESSD_MTIP32XX) += mtip32xx/
obj-$(CONFIG_BLK_DEV_RSXX) += rsxx/
obj-$(CONFIG_BLK_DEV_NULL_BLK) += null_blk.o
+obj-$(CONFIG_ZRAM) += zram/
nvme-y := nvme-core.o nvme-scsi.o
skd-y := skd_main.o
diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index 1f14ac403945..51824d1f23ea 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -46,7 +46,6 @@
#define NVME_Q_DEPTH 1024
#define SQ_SIZE(depth) (depth * sizeof(struct nvme_command))
#define CQ_SIZE(depth) (depth * sizeof(struct nvme_completion))
-#define NVME_MINORS 64
#define ADMIN_TIMEOUT (60 * HZ)
static int nvme_major;
@@ -58,6 +57,17 @@ module_param(use_threaded_interrupts, int, 0);
static DEFINE_SPINLOCK(dev_list_lock);
static LIST_HEAD(dev_list);
static struct task_struct *nvme_thread;
+static struct workqueue_struct *nvme_workq;
+
+static void nvme_reset_failed_dev(struct work_struct *ws);
+
+struct async_cmd_info {
+ struct kthread_work work;
+ struct kthread_worker *worker;
+ u32 result;
+ int status;
+ void *ctx;
+};
/*
* An NVM Express queue. Each device has at least two (one for admin
@@ -66,6 +76,7 @@ static struct task_struct *nvme_thread;
struct nvme_queue {
struct device *q_dmadev;
struct nvme_dev *dev;
+ char irqname[24]; /* nvme4294967295-65535\0 */
spinlock_t q_lock;
struct nvme_command *sq_cmds;
volatile struct nvme_completion *cqes;
@@ -80,9 +91,11 @@ struct nvme_queue {
u16 sq_head;
u16 sq_tail;
u16 cq_head;
+ u16 qid;
u8 cq_phase;
u8 cqe_seen;
u8 q_suspended;
+ struct async_cmd_info cmdinfo;
unsigned long cmdid_data[];
};
@@ -97,6 +110,7 @@ static inline void _nvme_check_size(void)
BUILD_BUG_ON(sizeof(struct nvme_delete_queue) != 64);
BUILD_BUG_ON(sizeof(struct nvme_features) != 64);
BUILD_BUG_ON(sizeof(struct nvme_format_cmd) != 64);
+ BUILD_BUG_ON(sizeof(struct nvme_abort_cmd) != 64);
BUILD_BUG_ON(sizeof(struct nvme_command) != 64);
BUILD_BUG_ON(sizeof(struct nvme_id_ctrl) != 4096);
BUILD_BUG_ON(sizeof(struct nvme_id_ns) != 4096);
@@ -111,6 +125,7 @@ struct nvme_cmd_info {
nvme_completion_fn fn;
void *ctx;
unsigned long timeout;
+ int aborted;
};
static struct nvme_cmd_info *nvme_cmd_info(struct nvme_queue *nvmeq)
@@ -154,6 +169,7 @@ static int alloc_cmdid(struct nvme_queue *nvmeq, void *ctx,
info[cmdid].fn = handler;
info[cmdid].ctx = ctx;
info[cmdid].timeout = jiffies + timeout;
+ info[cmdid].aborted = 0;
return cmdid;
}
@@ -172,6 +188,7 @@ static int alloc_cmdid_killable(struct nvme_queue *nvmeq, void *ctx,
#define CMD_CTX_COMPLETED (0x310 + CMD_CTX_BASE)
#define CMD_CTX_INVALID (0x314 + CMD_CTX_BASE)
#define CMD_CTX_FLUSH (0x318 + CMD_CTX_BASE)
+#define CMD_CTX_ABORT (0x31C + CMD_CTX_BASE)
static void special_completion(struct nvme_dev *dev, void *ctx,
struct nvme_completion *cqe)
@@ -180,6 +197,10 @@ static void special_completion(struct nvme_dev *dev, void *ctx,
return;
if (ctx == CMD_CTX_FLUSH)
return;
+ if (ctx == CMD_CTX_ABORT) {
+ ++dev->abort_limit;
+ return;
+ }
if (ctx == CMD_CTX_COMPLETED) {
dev_warn(&dev->pci_dev->dev,
"completed id %d twice on queue %d\n",
@@ -196,6 +217,15 @@ static void special_completion(struct nvme_dev *dev, void *ctx,
dev_warn(&dev->pci_dev->dev, "Unknown special completion %p\n", ctx);
}
+static void async_completion(struct nvme_dev *dev, void *ctx,
+ struct nvme_completion *cqe)
+{
+ struct async_cmd_info *cmdinfo = ctx;
+ cmdinfo->result = le32_to_cpup(&cqe->result);
+ cmdinfo->status = le16_to_cpup(&cqe->status) >> 1;
+ queue_kthread_work(cmdinfo->worker, &cmdinfo->work);
+}
+
/*
* Called with local interrupts disabled and the q_lock held. May not sleep.
*/
@@ -693,7 +723,7 @@ static int nvme_process_cq(struct nvme_queue *nvmeq)
if (head == nvmeq->cq_head && phase == nvmeq->cq_phase)
return 0;
- writel(head, nvmeq->q_db + (1 << nvmeq->dev->db_stride));
+ writel(head, nvmeq->q_db + nvmeq->dev->db_stride);
nvmeq->cq_head = head;
nvmeq->cq_phase = phase;
@@ -804,12 +834,34 @@ int nvme_submit_sync_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd,
return cmdinfo.status;
}
+static int nvme_submit_async_cmd(struct nvme_queue *nvmeq,
+ struct nvme_command *cmd,
+ struct async_cmd_info *cmdinfo, unsigned timeout)
+{
+ int cmdid;
+
+ cmdid = alloc_cmdid_killable(nvmeq, cmdinfo, async_completion, timeout);
+ if (cmdid < 0)
+ return cmdid;
+ cmdinfo->status = -EINTR;
+ cmd->common.command_id = cmdid;
+ nvme_submit_cmd(nvmeq, cmd);
+ return 0;
+}
+
int nvme_submit_admin_cmd(struct nvme_dev *dev, struct nvme_command *cmd,
u32 *result)
{
return nvme_submit_sync_cmd(dev->queues[0], cmd, result, ADMIN_TIMEOUT);
}
+static int nvme_submit_admin_cmd_async(struct nvme_dev *dev,
+ struct nvme_command *cmd, struct async_cmd_info *cmdinfo)
+{
+ return nvme_submit_async_cmd(dev->queues[0], cmd, cmdinfo,
+ ADMIN_TIMEOUT);
+}
+
static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16 id)
{
int status;
@@ -920,6 +972,56 @@ int nvme_set_features(struct nvme_dev *dev, unsigned fid, unsigned dword11,
}
/**
+ * nvme_abort_cmd - Attempt aborting a command
+ * @cmdid: Command id of a timed out IO
+ * @queue: The queue with timed out IO
+ *
+ * Schedule controller reset if the command was already aborted once before and
+ * still hasn't been returned to the driver, or if this is the admin queue.
+ */
+static void nvme_abort_cmd(int cmdid, struct nvme_queue *nvmeq)
+{
+ int a_cmdid;
+ struct nvme_command cmd;
+ struct nvme_dev *dev = nvmeq->dev;
+ struct nvme_cmd_info *info = nvme_cmd_info(nvmeq);
+
+ if (!nvmeq->qid || info[cmdid].aborted) {
+ if (work_busy(&dev->reset_work))
+ return;
+ list_del_init(&dev->node);
+ dev_warn(&dev->pci_dev->dev,
+ "I/O %d QID %d timeout, reset controller\n", cmdid,
+ nvmeq->qid);
+ PREPARE_WORK(&dev->reset_work, nvme_reset_failed_dev);
+ queue_work(nvme_workq, &dev->reset_work);
+ return;
+ }
+
+ if (!dev->abort_limit)
+ return;
+
+ a_cmdid = alloc_cmdid(dev->queues[0], CMD_CTX_ABORT, special_completion,
+ ADMIN_TIMEOUT);
+ if (a_cmdid < 0)
+ return;
+
+ memset(&cmd, 0, sizeof(cmd));
+ cmd.abort.opcode = nvme_admin_abort_cmd;
+ cmd.abort.cid = cmdid;
+ cmd.abort.sqid = cpu_to_le16(nvmeq->qid);
+ cmd.abort.command_id = a_cmdid;
+
+ --dev->abort_limit;
+ info[cmdid].aborted = 1;
+ info[cmdid].timeout = jiffies + ADMIN_TIMEOUT;
+
+ dev_warn(nvmeq->q_dmadev, "Aborting I/O %d QID %d\n", cmdid,
+ nvmeq->qid);
+ nvme_submit_cmd(dev->queues[0], &cmd);
+}
+
+/**
* 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
@@ -942,7 +1044,12 @@ static void nvme_cancel_ios(struct nvme_queue *nvmeq, bool timeout)
continue;
if (info[cmdid].ctx == CMD_CTX_CANCELLED)
continue;
- dev_warn(nvmeq->q_dmadev, "Cancelling I/O %d\n", cmdid);
+ if (timeout && nvmeq->dev->initialized) {
+ nvme_abort_cmd(cmdid, nvmeq);
+ continue;
+ }
+ dev_warn(nvmeq->q_dmadev, "Cancelling I/O %d QID %d\n", cmdid,
+ nvmeq->qid);
ctx = cancel_cmdid(nvmeq, cmdid, &fn);
fn(nvmeq->dev, ctx, &cqe);
}
@@ -964,26 +1071,31 @@ static void nvme_free_queue(struct nvme_queue *nvmeq)
kfree(nvmeq);
}
-static void nvme_free_queues(struct nvme_dev *dev)
+static void nvme_free_queues(struct nvme_dev *dev, int lowest)
{
int i;
- for (i = dev->queue_count - 1; i >= 0; i--) {
+ for (i = dev->queue_count - 1; i >= lowest; i--) {
nvme_free_queue(dev->queues[i]);
dev->queue_count--;
dev->queues[i] = NULL;
}
}
-static void nvme_disable_queue(struct nvme_dev *dev, int qid)
+/**
+ * nvme_suspend_queue - put queue into suspended state
+ * @nvmeq - queue to suspend
+ *
+ * Returns 1 if already suspended, 0 otherwise.
+ */
+static int nvme_suspend_queue(struct nvme_queue *nvmeq)
{
- struct nvme_queue *nvmeq = dev->queues[qid];
- int vector = dev->entry[nvmeq->cq_vector].vector;
+ int vector = nvmeq->dev->entry[nvmeq->cq_vector].vector;
spin_lock_irq(&nvmeq->q_lock);
if (nvmeq->q_suspended) {
spin_unlock_irq(&nvmeq->q_lock);
- return;
+ return 1;
}
nvmeq->q_suspended = 1;
spin_unlock_irq(&nvmeq->q_lock);
@@ -991,18 +1103,35 @@ static void nvme_disable_queue(struct nvme_dev *dev, int qid)
irq_set_affinity_hint(vector, NULL);
free_irq(vector, nvmeq);
- /* Don't tell the adapter to delete the admin queue */
- if (qid) {
- adapter_delete_sq(dev, qid);
- adapter_delete_cq(dev, qid);
- }
+ return 0;
+}
+static void nvme_clear_queue(struct nvme_queue *nvmeq)
+{
spin_lock_irq(&nvmeq->q_lock);
nvme_process_cq(nvmeq);
nvme_cancel_ios(nvmeq, false);
spin_unlock_irq(&nvmeq->q_lock);
}
+static void nvme_disable_queue(struct nvme_dev *dev, int qid)
+{
+ struct nvme_queue *nvmeq = dev->queues[qid];
+
+ if (!nvmeq)
+ return;
+ if (nvme_suspend_queue(nvmeq))
+ return;
+
+ /* Don't tell the adapter to delete the admin queue.
+ * Don't tell a removed adapter to delete IO queues. */
+ if (qid && readl(&dev->bar->csts) != -1) {
+ adapter_delete_sq(dev, qid);
+ adapter_delete_cq(dev, qid);
+ }
+ nvme_clear_queue(nvmeq);
+}
+
static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
int depth, int vector)
{
@@ -1025,15 +1154,18 @@ static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
nvmeq->q_dmadev = dmadev;
nvmeq->dev = dev;
+ snprintf(nvmeq->irqname, sizeof(nvmeq->irqname), "nvme%dq%d",
+ dev->instance, qid);
spin_lock_init(&nvmeq->q_lock);
nvmeq->cq_head = 0;
nvmeq->cq_phase = 1;
init_waitqueue_head(&nvmeq->sq_full);
init_waitqueue_entry(&nvmeq->sq_cong_wait, nvme_thread);
bio_list_init(&nvmeq->sq_cong);
- nvmeq->q_db = &dev->dbs[qid << (dev->db_stride + 1)];
+ nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
nvmeq->q_depth = depth;
nvmeq->cq_vector = vector;
+ nvmeq->qid = qid;
nvmeq->q_suspended = 1;
dev->queue_count++;
@@ -1052,11 +1184,10 @@ static int queue_request_irq(struct nvme_dev *dev, struct nvme_queue *nvmeq,
{
if (use_threaded_interrupts)
return request_threaded_irq(dev->entry[nvmeq->cq_vector].vector,
- nvme_irq_check, nvme_irq,
- IRQF_DISABLED | IRQF_SHARED,
+ nvme_irq_check, nvme_irq, IRQF_SHARED,
name, nvmeq);
return request_irq(dev->entry[nvmeq->cq_vector].vector, nvme_irq,
- IRQF_DISABLED | IRQF_SHARED, name, nvmeq);
+ IRQF_SHARED, name, nvmeq);
}
static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid)
@@ -1067,7 +1198,7 @@ static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid)
nvmeq->sq_tail = 0;
nvmeq->cq_head = 0;
nvmeq->cq_phase = 1;
- nvmeq->q_db = &dev->dbs[qid << (dev->db_stride + 1)];
+ nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
memset(nvmeq->cmdid_data, 0, extra);
memset((void *)nvmeq->cqes, 0, CQ_SIZE(nvmeq->q_depth));
nvme_cancel_ios(nvmeq, false);
@@ -1087,13 +1218,13 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
if (result < 0)
goto release_cq;
- result = queue_request_irq(dev, nvmeq, "nvme");
+ result = queue_request_irq(dev, nvmeq, nvmeq->irqname);
if (result < 0)
goto release_sq;
- spin_lock(&nvmeq->q_lock);
+ spin_lock_irq(&nvmeq->q_lock);
nvme_init_queue(nvmeq, qid);
- spin_unlock(&nvmeq->q_lock);
+ spin_unlock_irq(&nvmeq->q_lock);
return result;
@@ -1205,13 +1336,13 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
if (result)
return result;
- result = queue_request_irq(dev, nvmeq, "nvme admin");
+ result = queue_request_irq(dev, nvmeq, nvmeq->irqname);
if (result)
return result;
- spin_lock(&nvmeq->q_lock);
+ spin_lock_irq(&nvmeq->q_lock);
nvme_init_queue(nvmeq, 0);
- spin_unlock(&nvmeq->q_lock);
+ spin_unlock_irq(&nvmeq->q_lock);
return result;
}
@@ -1487,10 +1618,47 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd,
}
}
+#ifdef CONFIG_COMPAT
+static int nvme_compat_ioctl(struct block_device *bdev, fmode_t mode,
+ unsigned int cmd, unsigned long arg)
+{
+ struct nvme_ns *ns = bdev->bd_disk->private_data;
+
+ switch (cmd) {
+ case SG_IO:
+ return nvme_sg_io32(ns, arg);
+ }
+ return nvme_ioctl(bdev, mode, cmd, arg);
+}
+#else
+#define nvme_compat_ioctl NULL
+#endif
+
+static int nvme_open(struct block_device *bdev, fmode_t mode)
+{
+ struct nvme_ns *ns = bdev->bd_disk->private_data;
+ struct nvme_dev *dev = ns->dev;
+
+ kref_get(&dev->kref);
+ return 0;
+}
+
+static void nvme_free_dev(struct kref *kref);
+
+static void nvme_release(struct gendisk *disk, fmode_t mode)
+{
+ struct nvme_ns *ns = disk->private_data;
+ struct nvme_dev *dev = ns->dev;
+
+ kref_put(&dev->kref, nvme_free_dev);
+}
+
static const struct block_device_operations nvme_fops = {
.owner = THIS_MODULE,
.ioctl = nvme_ioctl,
- .compat_ioctl = nvme_ioctl,
+ .compat_ioctl = nvme_compat_ioctl,
+ .open = nvme_open,
+ .release = nvme_release,
};
static void nvme_resubmit_bios(struct nvme_queue *nvmeq)
@@ -1514,13 +1682,25 @@ static void nvme_resubmit_bios(struct nvme_queue *nvmeq)
static int nvme_kthread(void *data)
{
- struct nvme_dev *dev;
+ struct nvme_dev *dev, *next;
while (!kthread_should_stop()) {
set_current_state(TASK_INTERRUPTIBLE);
spin_lock(&dev_list_lock);
- list_for_each_entry(dev, &dev_list, node) {
+ list_for_each_entry_safe(dev, next, &dev_list, node) {
int i;
+ if (readl(&dev->bar->csts) & NVME_CSTS_CFS &&
+ dev->initialized) {
+ if (work_busy(&dev->reset_work))
+ continue;
+ list_del_init(&dev->node);
+ dev_warn(&dev->pci_dev->dev,
+ "Failed status, reset controller\n");
+ PREPARE_WORK(&dev->reset_work,
+ nvme_reset_failed_dev);
+ queue_work(nvme_workq, &dev->reset_work);
+ continue;
+ }
for (i = 0; i < dev->queue_count; i++) {
struct nvme_queue *nvmeq = dev->queues[i];
if (!nvmeq)
@@ -1541,33 +1721,6 @@ static int nvme_kthread(void *data)
return 0;
}
-static DEFINE_IDA(nvme_index_ida);
-
-static int nvme_get_ns_idx(void)
-{
- int index, error;
-
- do {
- if (!ida_pre_get(&nvme_index_ida, GFP_KERNEL))
- return -1;
-
- spin_lock(&dev_list_lock);
- error = ida_get_new(&nvme_index_ida, &index);
- spin_unlock(&dev_list_lock);
- } while (error == -EAGAIN);
-
- if (error)
- index = -1;
- return index;
-}
-
-static void nvme_put_ns_idx(int index)
-{
- spin_lock(&dev_list_lock);
- ida_remove(&nvme_index_ida, index);
- spin_unlock(&dev_list_lock);
-}
-
static void nvme_config_discard(struct nvme_ns *ns)
{
u32 logical_block_size = queue_logical_block_size(ns->queue);
@@ -1601,7 +1754,7 @@ static struct nvme_ns *nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid,
ns->dev = dev;
ns->queue->queuedata = ns;
- disk = alloc_disk(NVME_MINORS);
+ disk = alloc_disk(0);
if (!disk)
goto out_free_queue;
ns->ns_id = nsid;
@@ -1614,12 +1767,12 @@ static struct nvme_ns *nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid,
blk_queue_max_hw_sectors(ns->queue, dev->max_hw_sectors);
disk->major = nvme_major;
- disk->minors = NVME_MINORS;
- disk->first_minor = NVME_MINORS * nvme_get_ns_idx();
+ disk->first_minor = 0;
disk->fops = &nvme_fops;
disk->private_data = ns;
disk->queue = ns->queue;
disk->driverfs_dev = &dev->pci_dev->dev;
+ disk->flags = GENHD_FL_EXT_DEVT;
sprintf(disk->disk_name, "nvme%dn%d", dev->instance, nsid);
set_capacity(disk, le64_to_cpup(&id->nsze) << (ns->lba_shift - 9));
@@ -1635,15 +1788,6 @@ static struct nvme_ns *nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid,
return NULL;
}
-static void nvme_ns_free(struct nvme_ns *ns)
-{
- int index = ns->disk->first_minor / NVME_MINORS;
- put_disk(ns->disk);
- nvme_put_ns_idx(index);
- blk_cleanup_queue(ns->queue);
- kfree(ns);
-}
-
static int set_queue_count(struct nvme_dev *dev, int count)
{
int status;
@@ -1659,11 +1803,12 @@ static int set_queue_count(struct nvme_dev *dev, int count)
static size_t db_bar_size(struct nvme_dev *dev, unsigned nr_io_queues)
{
- return 4096 + ((nr_io_queues + 1) << (dev->db_stride + 3));
+ return 4096 + ((nr_io_queues + 1) * 8 * dev->db_stride);
}
static int nvme_setup_io_queues(struct nvme_dev *dev)
{
+ struct nvme_queue *adminq = dev->queues[0];
struct pci_dev *pdev = dev->pci_dev;
int result, cpu, i, vecs, nr_io_queues, size, q_depth;
@@ -1690,7 +1835,7 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
}
/* Deregister the admin queue's interrupt */
- free_irq(dev->entry[0].vector, dev->queues[0]);
+ free_irq(dev->entry[0].vector, adminq);
vecs = nr_io_queues;
for (i = 0; i < vecs; i++)
@@ -1728,9 +1873,9 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
*/
nr_io_queues = vecs;
- result = queue_request_irq(dev, dev->queues[0], "nvme admin");
+ result = queue_request_irq(dev, adminq, adminq->irqname);
if (result) {
- dev->queues[0]->q_suspended = 1;
+ adminq->q_suspended = 1;
goto free_queues;
}
@@ -1739,9 +1884,9 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
for (i = dev->queue_count - 1; i > nr_io_queues; i--) {
struct nvme_queue *nvmeq = dev->queues[i];
- spin_lock(&nvmeq->q_lock);
+ spin_lock_irq(&nvmeq->q_lock);
nvme_cancel_ios(nvmeq, false);
- spin_unlock(&nvmeq->q_lock);
+ spin_unlock_irq(&nvmeq->q_lock);
nvme_free_queue(nvmeq);
dev->queue_count--;
@@ -1782,7 +1927,7 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
return 0;
free_queues:
- nvme_free_queues(dev);
+ nvme_free_queues(dev, 1);
return result;
}
@@ -1794,6 +1939,7 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
*/
static int nvme_dev_add(struct nvme_dev *dev)
{
+ struct pci_dev *pdev = dev->pci_dev;
int res;
unsigned nn, i;
struct nvme_ns *ns;
@@ -1803,8 +1949,7 @@ static int nvme_dev_add(struct nvme_dev *dev)
dma_addr_t dma_addr;
int shift = NVME_CAP_MPSMIN(readq(&dev->bar->cap)) + 12;
- mem = dma_alloc_coherent(&dev->pci_dev->dev, 8192, &dma_addr,
- GFP_KERNEL);
+ mem = dma_alloc_coherent(&pdev->dev, 8192, &dma_addr, GFP_KERNEL);
if (!mem)
return -ENOMEM;
@@ -1817,13 +1962,14 @@ static int nvme_dev_add(struct nvme_dev *dev)
ctrl = mem;
nn = le32_to_cpup(&ctrl->nn);
dev->oncs = le16_to_cpup(&ctrl->oncs);
+ dev->abort_limit = ctrl->acl + 1;
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)
dev->max_hw_sectors = 1 << (ctrl->mdts + shift - 9);
- if ((dev->pci_dev->vendor == PCI_VENDOR_ID_INTEL) &&
- (dev->pci_dev->device == 0x0953) && ctrl->vs[3])
+ if ((pdev->vendor == PCI_VENDOR_ID_INTEL) &&
+ (pdev->device == 0x0953) && ctrl->vs[3])
dev->stripe_size = 1 << (ctrl->vs[3] + shift);
id_ns = mem;
@@ -1871,16 +2017,21 @@ static int nvme_dev_map(struct nvme_dev *dev)
dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)))
goto disable;
- pci_set_drvdata(pdev, dev);
dev->bar = ioremap(pci_resource_start(pdev, 0), 8192);
if (!dev->bar)
goto disable;
-
- dev->db_stride = NVME_CAP_STRIDE(readq(&dev->bar->cap));
+ if (readl(&dev->bar->csts) == -1) {
+ result = -ENODEV;
+ goto unmap;
+ }
+ dev->db_stride = 1 << NVME_CAP_STRIDE(readq(&dev->bar->cap));
dev->dbs = ((void __iomem *)dev->bar) + 4096;
return 0;
+ unmap:
+ iounmap(dev->bar);
+ dev->bar = NULL;
disable:
pci_release_regions(pdev);
disable_pci:
@@ -1898,37 +2049,183 @@ static void nvme_dev_unmap(struct nvme_dev *dev)
if (dev->bar) {
iounmap(dev->bar);
dev->bar = NULL;
+ pci_release_regions(dev->pci_dev);
}
- pci_release_regions(dev->pci_dev);
if (pci_is_enabled(dev->pci_dev))
pci_disable_device(dev->pci_dev);
}
+struct nvme_delq_ctx {
+ struct task_struct *waiter;
+ struct kthread_worker *worker;
+ atomic_t refcount;
+};
+
+static void nvme_wait_dq(struct nvme_delq_ctx *dq, struct nvme_dev *dev)
+{
+ dq->waiter = current;
+ mb();
+
+ for (;;) {
+ set_current_state(TASK_KILLABLE);
+ if (!atomic_read(&dq->refcount))
+ break;
+ if (!schedule_timeout(ADMIN_TIMEOUT) ||
+ fatal_signal_pending(current)) {
+ set_current_state(TASK_RUNNING);
+
+ nvme_disable_ctrl(dev, readq(&dev->bar->cap));
+ nvme_disable_queue(dev, 0);
+
+ send_sig(SIGKILL, dq->worker->task, 1);
+ flush_kthread_worker(dq->worker);
+ return;
+ }
+ }
+ set_current_state(TASK_RUNNING);
+}
+
+static void nvme_put_dq(struct nvme_delq_ctx *dq)
+{
+ atomic_dec(&dq->refcount);
+ if (dq->waiter)
+ wake_up_process(dq->waiter);
+}
+
+static struct nvme_delq_ctx *nvme_get_dq(struct nvme_delq_ctx *dq)
+{
+ atomic_inc(&dq->refcount);
+ return dq;
+}
+
+static void nvme_del_queue_end(struct nvme_queue *nvmeq)
+{
+ struct nvme_delq_ctx *dq = nvmeq->cmdinfo.ctx;
+
+ nvme_clear_queue(nvmeq);
+ nvme_put_dq(dq);
+}
+
+static int adapter_async_del_queue(struct nvme_queue *nvmeq, u8 opcode,
+ kthread_work_func_t fn)
+{
+ struct nvme_command c;
+
+ memset(&c, 0, sizeof(c));
+ c.delete_queue.opcode = opcode;
+ c.delete_queue.qid = cpu_to_le16(nvmeq->qid);
+
+ init_kthread_work(&nvmeq->cmdinfo.work, fn);
+ return nvme_submit_admin_cmd_async(nvmeq->dev, &c, &nvmeq->cmdinfo);
+}
+
+static void nvme_del_cq_work_handler(struct kthread_work *work)
+{
+ struct nvme_queue *nvmeq = container_of(work, struct nvme_queue,
+ cmdinfo.work);
+ nvme_del_queue_end(nvmeq);
+}
+
+static int nvme_delete_cq(struct nvme_queue *nvmeq)
+{
+ return adapter_async_del_queue(nvmeq, nvme_admin_delete_cq,
+ nvme_del_cq_work_handler);
+}
+
+static void nvme_del_sq_work_handler(struct kthread_work *work)
+{
+ struct nvme_queue *nvmeq = container_of(work, struct nvme_queue,
+ cmdinfo.work);
+ int status = nvmeq->cmdinfo.status;
+
+ if (!status)
+ status = nvme_delete_cq(nvmeq);
+ if (status)
+ nvme_del_queue_end(nvmeq);
+}
+
+static int nvme_delete_sq(struct nvme_queue *nvmeq)
+{
+ return adapter_async_del_queue(nvmeq, nvme_admin_delete_sq,
+ nvme_del_sq_work_handler);
+}
+
+static void nvme_del_queue_start(struct kthread_work *work)
+{
+ struct nvme_queue *nvmeq = container_of(work, struct nvme_queue,
+ cmdinfo.work);
+ allow_signal(SIGKILL);
+ if (nvme_delete_sq(nvmeq))
+ nvme_del_queue_end(nvmeq);
+}
+
+static void nvme_disable_io_queues(struct nvme_dev *dev)
+{
+ int i;
+ DEFINE_KTHREAD_WORKER_ONSTACK(worker);
+ struct nvme_delq_ctx dq;
+ struct task_struct *kworker_task = kthread_run(kthread_worker_fn,
+ &worker, "nvme%d", dev->instance);
+
+ if (IS_ERR(kworker_task)) {
+ dev_err(&dev->pci_dev->dev,
+ "Failed to create queue del task\n");
+ for (i = dev->queue_count - 1; i > 0; i--)
+ nvme_disable_queue(dev, i);
+ return;
+ }
+
+ dq.waiter = NULL;
+ atomic_set(&dq.refcount, 0);
+ dq.worker = &worker;
+ for (i = dev->queue_count - 1; i > 0; i--) {
+ struct nvme_queue *nvmeq = dev->queues[i];
+
+ if (nvme_suspend_queue(nvmeq))
+ continue;
+ nvmeq->cmdinfo.ctx = nvme_get_dq(&dq);
+ nvmeq->cmdinfo.worker = dq.worker;
+ init_kthread_work(&nvmeq->cmdinfo.work, nvme_del_queue_start);
+ queue_kthread_work(dq.worker, &nvmeq->cmdinfo.work);
+ }
+ nvme_wait_dq(&dq, dev);
+ kthread_stop(kworker_task);
+}
+
static void nvme_dev_shutdown(struct nvme_dev *dev)
{
int i;
- for (i = dev->queue_count - 1; i >= 0; i--)
- nvme_disable_queue(dev, i);
+ dev->initialized = 0;
spin_lock(&dev_list_lock);
list_del_init(&dev->node);
spin_unlock(&dev_list_lock);
- if (dev->bar)
+ if (!dev->bar || (dev->bar && readl(&dev->bar->csts) == -1)) {
+ for (i = dev->queue_count - 1; i >= 0; i--) {
+ struct nvme_queue *nvmeq = dev->queues[i];
+ nvme_suspend_queue(nvmeq);
+ nvme_clear_queue(nvmeq);
+ }
+ } else {
+ nvme_disable_io_queues(dev);
nvme_shutdown_ctrl(dev);
+ nvme_disable_queue(dev, 0);
+ }
nvme_dev_unmap(dev);
}
static void nvme_dev_remove(struct nvme_dev *dev)
{
- struct nvme_ns *ns, *next;
+ struct nvme_ns *ns;
- list_for_each_entry_safe(ns, next, &dev->namespaces, list) {
- list_del(&ns->list);
- del_gendisk(ns->disk);
- nvme_ns_free(ns);
+ list_for_each_entry(ns, &dev->namespaces, list) {
+ if (ns->disk->flags & GENHD_FL_UP)
+ del_gendisk(ns->disk);
+ if (!blk_queue_dying(ns->queue))
+ blk_cleanup_queue(ns->queue);
}
}
@@ -1985,14 +2282,22 @@ static void nvme_release_instance(struct nvme_dev *dev)
spin_unlock(&dev_list_lock);
}
+static void nvme_free_namespaces(struct nvme_dev *dev)
+{
+ struct nvme_ns *ns, *next;
+
+ list_for_each_entry_safe(ns, next, &dev->namespaces, list) {
+ list_del(&ns->list);
+ put_disk(ns->disk);
+ kfree(ns);
+ }
+}
+
static void nvme_free_dev(struct kref *kref)
{
struct nvme_dev *dev = container_of(kref, struct nvme_dev, kref);
- nvme_dev_remove(dev);
- nvme_dev_shutdown(dev);
- nvme_free_queues(dev);
- nvme_release_instance(dev);
- nvme_release_prp_pools(dev);
+
+ nvme_free_namespaces(dev);
kfree(dev->queues);
kfree(dev->entry);
kfree(dev);
@@ -2056,6 +2361,7 @@ static int nvme_dev_start(struct nvme_dev *dev)
return result;
disable:
+ nvme_disable_queue(dev, 0);
spin_lock(&dev_list_lock);
list_del_init(&dev->node);
spin_unlock(&dev_list_lock);
@@ -2064,6 +2370,71 @@ static int nvme_dev_start(struct nvme_dev *dev)
return result;
}
+static int nvme_remove_dead_ctrl(void *arg)
+{
+ struct nvme_dev *dev = (struct nvme_dev *)arg;
+ struct pci_dev *pdev = dev->pci_dev;
+
+ if (pci_get_drvdata(pdev))
+ pci_stop_and_remove_bus_device(pdev);
+ kref_put(&dev->kref, nvme_free_dev);
+ return 0;
+}
+
+static void nvme_remove_disks(struct work_struct *ws)
+{
+ int i;
+ struct nvme_dev *dev = container_of(ws, struct nvme_dev, reset_work);
+
+ nvme_dev_remove(dev);
+ spin_lock(&dev_list_lock);
+ for (i = dev->queue_count - 1; i > 0; i--) {
+ BUG_ON(!dev->queues[i] || !dev->queues[i]->q_suspended);
+ nvme_free_queue(dev->queues[i]);
+ dev->queue_count--;
+ dev->queues[i] = NULL;
+ }
+ spin_unlock(&dev_list_lock);
+}
+
+static int nvme_dev_resume(struct nvme_dev *dev)
+{
+ int ret;
+
+ ret = nvme_dev_start(dev);
+ if (ret && ret != -EBUSY)
+ return ret;
+ if (ret == -EBUSY) {
+ spin_lock(&dev_list_lock);
+ PREPARE_WORK(&dev->reset_work, nvme_remove_disks);
+ queue_work(nvme_workq, &dev->reset_work);
+ spin_unlock(&dev_list_lock);
+ }
+ dev->initialized = 1;
+ return 0;
+}
+
+static void nvme_dev_reset(struct nvme_dev *dev)
+{
+ nvme_dev_shutdown(dev);
+ if (nvme_dev_resume(dev)) {
+ dev_err(&dev->pci_dev->dev, "Device failed to resume\n");
+ kref_get(&dev->kref);
+ if (IS_ERR(kthread_run(nvme_remove_dead_ctrl, dev, "nvme%d",
+ dev->instance))) {
+ dev_err(&dev->pci_dev->dev,
+ "Failed to start controller remove task\n");
+ kref_put(&dev->kref, nvme_free_dev);
+ }
+ }
+}
+
+static void nvme_reset_failed_dev(struct work_struct *ws)
+{
+ struct nvme_dev *dev = container_of(ws, struct nvme_dev, reset_work);
+ nvme_dev_reset(dev);
+}
+
static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
int result = -ENOMEM;
@@ -2082,8 +2453,9 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
goto free;
INIT_LIST_HEAD(&dev->namespaces);
+ INIT_WORK(&dev->reset_work, nvme_reset_failed_dev);
dev->pci_dev = pdev;
-
+ pci_set_drvdata(pdev, dev);
result = nvme_set_instance(dev);
if (result)
goto free;
@@ -2099,6 +2471,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
goto release_pools;
}
+ kref_init(&dev->kref);
result = nvme_dev_add(dev);
if (result)
goto shutdown;
@@ -2113,15 +2486,16 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
if (result)
goto remove;
- kref_init(&dev->kref);
+ dev->initialized = 1;
return 0;
remove:
nvme_dev_remove(dev);
+ nvme_free_namespaces(dev);
shutdown:
nvme_dev_shutdown(dev);
release_pools:
- nvme_free_queues(dev);
+ nvme_free_queues(dev, 0);
nvme_release_prp_pools(dev);
release:
nvme_release_instance(dev);
@@ -2132,10 +2506,28 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
return result;
}
+static void nvme_shutdown(struct pci_dev *pdev)
+{
+ struct nvme_dev *dev = pci_get_drvdata(pdev);
+ nvme_dev_shutdown(dev);
+}
+
static void nvme_remove(struct pci_dev *pdev)
{
struct nvme_dev *dev = pci_get_drvdata(pdev);
+
+ spin_lock(&dev_list_lock);
+ list_del_init(&dev->node);
+ spin_unlock(&dev_list_lock);
+
+ pci_set_drvdata(pdev, NULL);
+ flush_work(&dev->reset_work);
misc_deregister(&dev->miscdev);
+ nvme_dev_remove(dev);
+ nvme_dev_shutdown(dev);
+ nvme_free_queues(dev, 0);
+ nvme_release_instance(dev);
+ nvme_release_prp_pools(dev);
kref_put(&dev->kref, nvme_free_dev);
}
@@ -2159,13 +2551,12 @@ static int nvme_resume(struct device *dev)
{
struct pci_dev *pdev = to_pci_dev(dev);
struct nvme_dev *ndev = pci_get_drvdata(pdev);
- int ret;
- ret = nvme_dev_start(ndev);
- /* XXX: should remove gendisks if resume fails */
- if (ret)
- nvme_free_queues(ndev);
- return ret;
+ if (nvme_dev_resume(ndev) && !work_busy(&ndev->reset_work)) {
+ PREPARE_WORK(&ndev->reset_work, nvme_reset_failed_dev);
+ queue_work(nvme_workq, &ndev->reset_work);
+ }
+ return 0;
}
static SIMPLE_DEV_PM_OPS(nvme_dev_pm_ops, nvme_suspend, nvme_resume);
@@ -2192,6 +2583,7 @@ static struct pci_driver nvme_driver = {
.id_table = nvme_id_table,
.probe = nvme_probe,
.remove = nvme_remove,
+ .shutdown = nvme_shutdown,
.driver = {
.pm = &nvme_dev_pm_ops,
},
@@ -2206,9 +2598,14 @@ static int __init nvme_init(void)
if (IS_ERR(nvme_thread))
return PTR_ERR(nvme_thread);
+ result = -ENOMEM;
+ nvme_workq = create_singlethread_workqueue("nvme");
+ if (!nvme_workq)
+ goto kill_kthread;
+
result = register_blkdev(nvme_major, "nvme");
if (result < 0)
- goto kill_kthread;
+ goto kill_workq;
else if (result > 0)
nvme_major = result;
@@ -2219,6 +2616,8 @@ static int __init nvme_init(void)
unregister_blkdev:
unregister_blkdev(nvme_major, "nvme");
+ kill_workq:
+ destroy_workqueue(nvme_workq);
kill_kthread:
kthread_stop(nvme_thread);
return result;
@@ -2228,6 +2627,7 @@ static void __exit nvme_exit(void)
{
pci_unregister_driver(&nvme_driver);
unregister_blkdev(nvme_major, "nvme");
+ destroy_workqueue(nvme_workq);
kthread_stop(nvme_thread);
}
diff --git a/drivers/block/nvme-scsi.c b/drivers/block/nvme-scsi.c
index 4a4ff4eb8e23..4a0ceb64e269 100644
--- a/drivers/block/nvme-scsi.c
+++ b/drivers/block/nvme-scsi.c
@@ -25,6 +25,7 @@
#include <linux/bio.h>
#include <linux/bitops.h>
#include <linux/blkdev.h>
+#include <linux/compat.h>
#include <linux/delay.h>
#include <linux/errno.h>
#include <linux/fs.h>
@@ -3038,6 +3039,152 @@ int nvme_sg_io(struct nvme_ns *ns, struct sg_io_hdr __user *u_hdr)
return retcode;
}
+#ifdef CONFIG_COMPAT
+typedef struct sg_io_hdr32 {
+ compat_int_t interface_id; /* [i] 'S' for SCSI generic (required) */
+ compat_int_t dxfer_direction; /* [i] data transfer direction */
+ unsigned char cmd_len; /* [i] SCSI command length ( <= 16 bytes) */
+ unsigned char mx_sb_len; /* [i] max length to write to sbp */
+ unsigned short iovec_count; /* [i] 0 implies no scatter gather */
+ compat_uint_t dxfer_len; /* [i] byte count of data transfer */
+ compat_uint_t dxferp; /* [i], [*io] points to data transfer memory
+ or scatter gather list */
+ compat_uptr_t cmdp; /* [i], [*i] points to command to perform */
+ compat_uptr_t sbp; /* [i], [*o] points to sense_buffer memory */
+ compat_uint_t timeout; /* [i] MAX_UINT->no timeout (unit: millisec) */
+ compat_uint_t flags; /* [i] 0 -> default, see SG_FLAG... */
+ compat_int_t pack_id; /* [i->o] unused internally (normally) */
+ compat_uptr_t usr_ptr; /* [i->o] unused internally */
+ unsigned char status; /* [o] scsi status */
+ unsigned char masked_status; /* [o] shifted, masked scsi status */
+ unsigned char msg_status; /* [o] messaging level data (optional) */
+ unsigned char sb_len_wr; /* [o] byte count actually written to sbp */
+ unsigned short host_status; /* [o] errors from host adapter */
+ unsigned short driver_status; /* [o] errors from software driver */
+ compat_int_t resid; /* [o] dxfer_len - actual_transferred */
+ compat_uint_t duration; /* [o] time taken by cmd (unit: millisec) */
+ compat_uint_t info; /* [o] auxiliary information */
+} sg_io_hdr32_t; /* 64 bytes long (on sparc32) */
+
+typedef struct sg_iovec32 {
+ compat_uint_t iov_base;
+ compat_uint_t iov_len;
+} sg_iovec32_t;
+
+static int sg_build_iovec(sg_io_hdr_t __user *sgio, void __user *dxferp, u16 iovec_count)
+{
+ sg_iovec_t __user *iov = (sg_iovec_t __user *) (sgio + 1);
+ sg_iovec32_t __user *iov32 = dxferp;
+ int i;
+
+ for (i = 0; i < iovec_count; i++) {
+ u32 base, len;
+
+ if (get_user(base, &iov32[i].iov_base) ||
+ get_user(len, &iov32[i].iov_len) ||
+ put_user(compat_ptr(base), &iov[i].iov_base) ||
+ put_user(len, &iov[i].iov_len))
+ return -EFAULT;
+ }
+
+ if (put_user(iov, &sgio->dxferp))
+ return -EFAULT;
+ return 0;
+}
+
+int nvme_sg_io32(struct nvme_ns *ns, unsigned long arg)
+{
+ sg_io_hdr32_t __user *sgio32 = (sg_io_hdr32_t __user *)arg;
+ sg_io_hdr_t __user *sgio;
+ u16 iovec_count;
+ u32 data;
+ void __user *dxferp;
+ int err;
+ int interface_id;
+
+ if (get_user(interface_id, &sgio32->interface_id))
+ return -EFAULT;
+ if (interface_id != 'S')
+ return -EINVAL;
+
+ if (get_user(iovec_count, &sgio32->iovec_count))
+ return -EFAULT;
+
+ {
+ void __user *top = compat_alloc_user_space(0);
+ void __user *new = compat_alloc_user_space(sizeof(sg_io_hdr_t) +
+ (iovec_count * sizeof(sg_iovec_t)));
+ if (new > top)
+ return -EINVAL;
+
+ sgio = new;
+ }
+
+ /* Ok, now construct. */
+ if (copy_in_user(&sgio->interface_id, &sgio32->interface_id,
+ (2 * sizeof(int)) +
+ (2 * sizeof(unsigned char)) +
+ (1 * sizeof(unsigned short)) +
+ (1 * sizeof(unsigned int))))
+ return -EFAULT;
+
+ if (get_user(data, &sgio32->dxferp))
+ return -EFAULT;
+ dxferp = compat_ptr(data);
+ if (iovec_count) {
+ if (sg_build_iovec(sgio, dxferp, iovec_count))
+ return -EFAULT;
+ } else {
+ if (put_user(dxferp, &sgio->dxferp))
+ return -EFAULT;
+ }
+
+ {
+ unsigned char __user *cmdp;
+ unsigned char __user *sbp;
+
+ if (get_user(data, &sgio32->cmdp))
+ return -EFAULT;
+ cmdp = compat_ptr(data);
+
+ if (get_user(data, &sgio32->sbp))
+ return -EFAULT;
+ sbp = compat_ptr(data);
+
+ if (put_user(cmdp, &sgio->cmdp) ||
+ put_user(sbp, &sgio->sbp))
+ return -EFAULT;
+ }
+
+ if (copy_in_user(&sgio->timeout, &sgio32->timeout,
+ 3 * sizeof(int)))
+ return -EFAULT;
+
+ if (get_user(data, &sgio32->usr_ptr))
+ return -EFAULT;
+ if (put_user(compat_ptr(data), &sgio->usr_ptr))
+ return -EFAULT;
+
+ err = nvme_sg_io(ns, sgio);
+ if (err >= 0) {
+ void __user *datap;
+
+ if (copy_in_user(&sgio32->pack_id, &sgio->pack_id,
+ sizeof(int)) ||
+ get_user(datap, &sgio->usr_ptr) ||
+ put_user((u32)(unsigned long)datap,
+ &sgio32->usr_ptr) ||
+ copy_in_user(&sgio32->status, &sgio->status,
+ (4 * sizeof(unsigned char)) +
+ (2 * sizeof(unsigned short)) +
+ (3 * sizeof(int))))
+ err = -EFAULT;
+ }
+
+ return err;
+}
+#endif
+
int nvme_sg_get_version_num(int __user *ip)
{
return put_user(sg_version_num, ip);
diff --git a/drivers/block/zram/Kconfig b/drivers/block/zram/Kconfig
new file mode 100644
index 000000000000..3450be850399
--- /dev/null
+++ b/drivers/block/zram/Kconfig
@@ -0,0 +1,24 @@
+config ZRAM
+ tristate "Compressed RAM block device support"
+ depends on BLOCK && SYSFS && ZSMALLOC
+ select LZO_COMPRESS
+ select LZO_DECOMPRESS
+ default n
+ help
+ Creates virtual block devices called /dev/zramX (X = 0, 1, ...).
+ Pages written to these disks are compressed and stored in memory
+ itself. These disks allow very fast I/O and compression provides
+ good amounts of memory savings.
+
+ It has several use cases, for example: /tmp storage, use as swap
+ disks and maybe many more.
+
+ See zram.txt for more information.
+
+config ZRAM_DEBUG
+ bool "Compressed RAM block device debug support"
+ depends on ZRAM
+ default n
+ help
+ This option adds additional debugging code to the compressed
+ RAM block device driver.
diff --git a/drivers/block/zram/Makefile b/drivers/block/zram/Makefile
new file mode 100644
index 000000000000..cb0f9ced6a93
--- /dev/null
+++ b/drivers/block/zram/Makefile
@@ -0,0 +1,3 @@
+zram-y := zram_drv.o
+
+obj-$(CONFIG_ZRAM) += zram.o
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
new file mode 100644
index 000000000000..011e55d820b1
--- /dev/null
+++ b/drivers/block/zram/zram_drv.c
@@ -0,0 +1,958 @@
+/*
+ * Compressed RAM block device
+ *
+ * Copyright (C) 2008, 2009, 2010 Nitin Gupta
+ * 2012, 2013 Minchan Kim
+ *
+ * This code is released using a dual license strategy: BSD/GPL
+ * You can choose the licence that better fits your requirements.
+ *
+ * Released under the terms of 3-clause BSD License
+ * Released under the terms of GNU General Public License Version 2.0
+ *
+ */
+
+#define KMSG_COMPONENT "zram"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#ifdef CONFIG_ZRAM_DEBUG
+#define DEBUG
+#endif
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/bio.h>
+#include <linux/bitops.h>
+#include <linux/blkdev.h>
+#include <linux/buffer_head.h>
+#include <linux/device.h>
+#include <linux/genhd.h>
+#include <linux/highmem.h>
+#include <linux/slab.h>
+#include <linux/lzo.h>
+#include <linux/string.h>
+#include <linux/vmalloc.h>
+
+#include "zram_drv.h"
+
+/* Globals */
+static int zram_major;
+static struct zram *zram_devices;
+
+/* Module params (documentation at end) */
+static unsigned int num_devices = 1;
+
+static inline struct zram *dev_to_zram(struct device *dev)
+{
+ return (struct zram *)dev_to_disk(dev)->private_data;
+}
+
+static ssize_t disksize_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct zram *zram = dev_to_zram(dev);
+
+ return sprintf(buf, "%llu\n", zram->disksize);
+}
+
+static ssize_t initstate_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct zram *zram = dev_to_zram(dev);
+
+ return sprintf(buf, "%u\n", zram->init_done);
+}
+
+static ssize_t num_reads_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct zram *zram = dev_to_zram(dev);
+
+ return sprintf(buf, "%llu\n",
+ (u64)atomic64_read(&zram->stats.num_reads));
+}
+
+static ssize_t num_writes_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct zram *zram = dev_to_zram(dev);
+
+ return sprintf(buf, "%llu\n",
+ (u64)atomic64_read(&zram->stats.num_writes));
+}
+
+static ssize_t invalid_io_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct zram *zram = dev_to_zram(dev);
+
+ return sprintf(buf, "%llu\n",
+ (u64)atomic64_read(&zram->stats.invalid_io));
+}
+
+static ssize_t notify_free_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct zram *zram = dev_to_zram(dev);
+
+ return sprintf(buf, "%llu\n",
+ (u64)atomic64_read(&zram->stats.notify_free));
+}
+
+static ssize_t zero_pages_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct zram *zram = dev_to_zram(dev);
+
+ return sprintf(buf, "%u\n", atomic_read(&zram->stats.pages_zero));
+}
+
+static ssize_t orig_data_size_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct zram *zram = dev_to_zram(dev);
+
+ return sprintf(buf, "%llu\n",
+ (u64)(atomic_read(&zram->stats.pages_stored)) << PAGE_SHIFT);
+}
+
+static ssize_t compr_data_size_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct zram *zram = dev_to_zram(dev);
+
+ return sprintf(buf, "%llu\n",
+ (u64)atomic64_read(&zram->stats.compr_size));
+}
+
+static ssize_t mem_used_total_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ u64 val = 0;
+ struct zram *zram = dev_to_zram(dev);
+ struct zram_meta *meta = zram->meta;
+
+ down_read(&zram->init_lock);
+ if (zram->init_done)
+ val = zs_get_total_size_bytes(meta->mem_pool);
+ up_read(&zram->init_lock);
+
+ return sprintf(buf, "%llu\n", val);
+}
+
+/* flag operations needs meta->tb_lock */
+static int zram_test_flag(struct zram_meta *meta, u32 index,
+ enum zram_pageflags flag)
+{
+ return meta->table[index].flags & BIT(flag);
+}
+
+static void zram_set_flag(struct zram_meta *meta, u32 index,
+ enum zram_pageflags flag)
+{
+ meta->table[index].flags |= BIT(flag);
+}
+
+static void zram_clear_flag(struct zram_meta *meta, u32 index,
+ enum zram_pageflags flag)
+{
+ meta->table[index].flags &= ~BIT(flag);
+}
+
+static inline int is_partial_io(struct bio_vec *bvec)
+{
+ return bvec->bv_len != PAGE_SIZE;
+}
+
+/*
+ * Check if request is within bounds and aligned on zram logical blocks.
+ */
+static inline int valid_io_request(struct zram *zram, struct bio *bio)
+{
+ u64 start, end, bound;
+
+ /* unaligned request */
+ if (unlikely(bio->bi_iter.bi_sector &
+ (ZRAM_SECTOR_PER_LOGICAL_BLOCK - 1)))
+ return 0;
+ if (unlikely(bio->bi_iter.bi_size & (ZRAM_LOGICAL_BLOCK_SIZE - 1)))
+ return 0;
+
+ start = bio->bi_iter.bi_sector;
+ end = start + (bio->bi_iter.bi_size >> SECTOR_SHIFT);
+ bound = zram->disksize >> SECTOR_SHIFT;
+ /* out of range range */
+ if (unlikely(start >= bound || end > bound || start > end))
+ return 0;
+
+ /* I/O request is valid */
+ return 1;
+}
+
+static void zram_meta_free(struct zram_meta *meta)
+{
+ zs_destroy_pool(meta->mem_pool);
+ kfree(meta->compress_workmem);
+ free_pages((unsigned long)meta->compress_buffer, 1);
+ vfree(meta->table);
+ kfree(meta);
+}
+
+static struct zram_meta *zram_meta_alloc(u64 disksize)
+{
+ size_t num_pages;
+ struct zram_meta *meta = kmalloc(sizeof(*meta), GFP_KERNEL);
+ if (!meta)
+ goto out;
+
+ meta->compress_workmem = kzalloc(LZO1X_MEM_COMPRESS, GFP_KERNEL);
+ if (!meta->compress_workmem)
+ goto free_meta;
+
+ meta->compress_buffer =
+ (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 1);
+ if (!meta->compress_buffer) {
+ pr_err("Error allocating compressor buffer space\n");
+ goto free_workmem;
+ }
+
+ num_pages = disksize >> PAGE_SHIFT;
+ meta->table = vzalloc(num_pages * sizeof(*meta->table));
+ if (!meta->table) {
+ pr_err("Error allocating zram address table\n");
+ goto free_buffer;
+ }
+
+ meta->mem_pool = zs_create_pool(GFP_NOIO | __GFP_HIGHMEM);
+ if (!meta->mem_pool) {
+ pr_err("Error creating memory pool\n");
+ goto free_table;
+ }
+
+ rwlock_init(&meta->tb_lock);
+ mutex_init(&meta->buffer_lock);
+ return meta;
+
+free_table:
+ vfree(meta->table);
+free_buffer:
+ free_pages((unsigned long)meta->compress_buffer, 1);
+free_workmem:
+ kfree(meta->compress_workmem);
+free_meta:
+ kfree(meta);
+ meta = NULL;
+out:
+ return meta;
+}
+
+static void update_position(u32 *index, int *offset, struct bio_vec *bvec)
+{
+ if (*offset + bvec->bv_len >= PAGE_SIZE)
+ (*index)++;
+ *offset = (*offset + bvec->bv_len) % PAGE_SIZE;
+}
+
+static int page_zero_filled(void *ptr)
+{
+ unsigned int pos;
+ unsigned long *page;
+
+ page = (unsigned long *)ptr;
+
+ for (pos = 0; pos != PAGE_SIZE / sizeof(*page); pos++) {
+ if (page[pos])
+ return 0;
+ }
+
+ return 1;
+}
+
+static void handle_zero_page(struct bio_vec *bvec)
+{
+ struct page *page = bvec->bv_page;
+ void *user_mem;
+
+ user_mem = kmap_atomic(page);
+ if (is_partial_io(bvec))
+ memset(user_mem + bvec->bv_offset, 0, bvec->bv_len);
+ else
+ clear_page(user_mem);
+ kunmap_atomic(user_mem);
+
+ flush_dcache_page(page);
+}
+
+/* NOTE: caller should hold meta->tb_lock with write-side */
+static void zram_free_page(struct zram *zram, size_t index)
+{
+ struct zram_meta *meta = zram->meta;
+ unsigned long handle = meta->table[index].handle;
+ u16 size = meta->table[index].size;
+
+ if (unlikely(!handle)) {
+ /*
+ * No memory is allocated for zero filled pages.
+ * Simply clear zero page flag.
+ */
+ if (zram_test_flag(meta, index, ZRAM_ZERO)) {
+ zram_clear_flag(meta, index, ZRAM_ZERO);
+ atomic_dec(&zram->stats.pages_zero);
+ }
+ return;
+ }
+
+ if (unlikely(size > max_zpage_size))
+ atomic_dec(&zram->stats.bad_compress);
+
+ zs_free(meta->mem_pool, handle);
+
+ if (size <= PAGE_SIZE / 2)
+ atomic_dec(&zram->stats.good_compress);
+
+ atomic64_sub(meta->table[index].size, &zram->stats.compr_size);
+ atomic_dec(&zram->stats.pages_stored);
+
+ meta->table[index].handle = 0;
+ meta->table[index].size = 0;
+}
+
+static int zram_decompress_page(struct zram *zram, char *mem, u32 index)
+{
+ int ret = LZO_E_OK;
+ size_t clen = PAGE_SIZE;
+ unsigned char *cmem;
+ struct zram_meta *meta = zram->meta;
+ unsigned long handle;
+ u16 size;
+
+ read_lock(&meta->tb_lock);
+ handle = meta->table[index].handle;
+ size = meta->table[index].size;
+
+ if (!handle || zram_test_flag(meta, index, ZRAM_ZERO)) {
+ read_unlock(&meta->tb_lock);
+ clear_page(mem);
+ return 0;
+ }
+
+ cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_RO);
+ if (size == PAGE_SIZE)
+ copy_page(mem, cmem);
+ else
+ ret = lzo1x_decompress_safe(cmem, size, mem, &clen);
+ zs_unmap_object(meta->mem_pool, handle);
+ read_unlock(&meta->tb_lock);
+
+ /* Should NEVER happen. Return bio error if it does. */
+ if (unlikely(ret != LZO_E_OK)) {
+ pr_err("Decompression failed! err=%d, page=%u\n", ret, index);
+ atomic64_inc(&zram->stats.failed_reads);
+ return ret;
+ }
+
+ return 0;
+}
+
+static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
+ u32 index, int offset, struct bio *bio)
+{
+ int ret;
+ struct page *page;
+ unsigned char *user_mem, *uncmem = NULL;
+ struct zram_meta *meta = zram->meta;
+ page = bvec->bv_page;
+
+ read_lock(&meta->tb_lock);
+ if (unlikely(!meta->table[index].handle) ||
+ zram_test_flag(meta, index, ZRAM_ZERO)) {
+ read_unlock(&meta->tb_lock);
+ handle_zero_page(bvec);
+ return 0;
+ }
+ read_unlock(&meta->tb_lock);
+
+ if (is_partial_io(bvec))
+ /* Use a temporary buffer to decompress the page */
+ uncmem = kmalloc(PAGE_SIZE, GFP_NOIO);
+
+ user_mem = kmap_atomic(page);
+ if (!is_partial_io(bvec))
+ uncmem = user_mem;
+
+ if (!uncmem) {
+ pr_info("Unable to allocate temp memory\n");
+ ret = -ENOMEM;
+ goto out_cleanup;
+ }
+
+ ret = zram_decompress_page(zram, uncmem, index);
+ /* Should NEVER happen. Return bio error if it does. */
+ if (unlikely(ret != LZO_E_OK))
+ goto out_cleanup;
+
+ if (is_partial_io(bvec))
+ memcpy(user_mem + bvec->bv_offset, uncmem + offset,
+ bvec->bv_len);
+
+ flush_dcache_page(page);
+ ret = 0;
+out_cleanup:
+ kunmap_atomic(user_mem);
+ if (is_partial_io(bvec))
+ kfree(uncmem);
+ return ret;
+}
+
+static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
+ int offset)
+{
+ int ret = 0;
+ size_t clen;
+ unsigned long handle;
+ struct page *page;
+ unsigned char *user_mem, *cmem, *src, *uncmem = NULL;
+ struct zram_meta *meta = zram->meta;
+ bool locked = false;
+
+ page = bvec->bv_page;
+ src = meta->compress_buffer;
+
+ if (is_partial_io(bvec)) {
+ /*
+ * This is a partial IO. We need to read the full page
+ * before to write the changes.
+ */
+ uncmem = kmalloc(PAGE_SIZE, GFP_NOIO);
+ if (!uncmem) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ ret = zram_decompress_page(zram, uncmem, index);
+ if (ret)
+ goto out;
+ }
+
+ mutex_lock(&meta->buffer_lock);
+ locked = true;
+ user_mem = kmap_atomic(page);
+
+ if (is_partial_io(bvec)) {
+ memcpy(uncmem + offset, user_mem + bvec->bv_offset,
+ bvec->bv_len);
+ kunmap_atomic(user_mem);
+ user_mem = NULL;
+ } else {
+ uncmem = user_mem;
+ }
+
+ if (page_zero_filled(uncmem)) {
+ kunmap_atomic(user_mem);
+ /* Free memory associated with this sector now. */
+ write_lock(&zram->meta->tb_lock);
+ zram_free_page(zram, index);
+ zram_set_flag(meta, index, ZRAM_ZERO);
+ write_unlock(&zram->meta->tb_lock);
+
+ atomic_inc(&zram->stats.pages_zero);
+ ret = 0;
+ goto out;
+ }
+
+ ret = lzo1x_1_compress(uncmem, PAGE_SIZE, src, &clen,
+ meta->compress_workmem);
+ if (!is_partial_io(bvec)) {
+ kunmap_atomic(user_mem);
+ user_mem = NULL;
+ uncmem = NULL;
+ }
+
+ if (unlikely(ret != LZO_E_OK)) {
+ pr_err("Compression failed! err=%d\n", ret);
+ goto out;
+ }
+
+ if (unlikely(clen > max_zpage_size)) {
+ atomic_inc(&zram->stats.bad_compress);
+ clen = PAGE_SIZE;
+ src = NULL;
+ if (is_partial_io(bvec))
+ src = uncmem;
+ }
+
+ handle = zs_malloc(meta->mem_pool, clen);
+ if (!handle) {
+ pr_info("Error allocating memory for compressed page: %u, size=%zu\n",
+ index, clen);
+ ret = -ENOMEM;
+ goto out;
+ }
+ cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_WO);
+
+ if ((clen == PAGE_SIZE) && !is_partial_io(bvec)) {
+ src = kmap_atomic(page);
+ copy_page(cmem, src);
+ kunmap_atomic(src);
+ } else {
+ memcpy(cmem, src, clen);
+ }
+
+ zs_unmap_object(meta->mem_pool, handle);
+
+ /*
+ * Free memory associated with this sector
+ * before overwriting unused sectors.
+ */
+ write_lock(&zram->meta->tb_lock);
+ zram_free_page(zram, index);
+
+ meta->table[index].handle = handle;
+ meta->table[index].size = clen;
+ write_unlock(&zram->meta->tb_lock);
+
+ /* Update stats */
+ atomic64_add(clen, &zram->stats.compr_size);
+ atomic_inc(&zram->stats.pages_stored);
+ if (clen <= PAGE_SIZE / 2)
+ atomic_inc(&zram->stats.good_compress);
+
+out:
+ if (locked)
+ mutex_unlock(&meta->buffer_lock);
+ if (is_partial_io(bvec))
+ kfree(uncmem);
+
+ if (ret)
+ atomic64_inc(&zram->stats.failed_writes);
+ return ret;
+}
+
+static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
+ int offset, struct bio *bio, int rw)
+{
+ int ret;
+
+ if (rw == READ)
+ ret = zram_bvec_read(zram, bvec, index, offset, bio);
+ else
+ ret = zram_bvec_write(zram, bvec, index, offset);
+
+ return ret;
+}
+
+static void zram_reset_device(struct zram *zram, bool reset_capacity)
+{
+ size_t index;
+ struct zram_meta *meta;
+
+ down_write(&zram->init_lock);
+ if (!zram->init_done) {
+ up_write(&zram->init_lock);
+ return;
+ }
+
+ meta = zram->meta;
+ zram->init_done = 0;
+
+ /* Free all pages that are still in this zram device */
+ for (index = 0; index < zram->disksize >> PAGE_SHIFT; index++) {
+ unsigned long handle = meta->table[index].handle;
+ if (!handle)
+ continue;
+
+ zs_free(meta->mem_pool, handle);
+ }
+
+ zram_meta_free(zram->meta);
+ zram->meta = NULL;
+ /* Reset stats */
+ memset(&zram->stats, 0, sizeof(zram->stats));
+
+ zram->disksize = 0;
+ if (reset_capacity)
+ set_capacity(zram->disk, 0);
+ up_write(&zram->init_lock);
+}
+
+static void zram_init_device(struct zram *zram, struct zram_meta *meta)
+{
+ if (zram->disksize > 2 * (totalram_pages << PAGE_SHIFT)) {
+ pr_info(
+ "There is little point creating a zram of greater than "
+ "twice the size of memory since we expect a 2:1 compression "
+ "ratio. Note that zram uses about 0.1%% of the size of "
+ "the disk when not in use so a huge zram is "
+ "wasteful.\n"
+ "\tMemory Size: %lu kB\n"
+ "\tSize you selected: %llu kB\n"
+ "Continuing anyway ...\n",
+ (totalram_pages << PAGE_SHIFT) >> 10, zram->disksize >> 10
+ );
+ }
+
+ /* zram devices sort of resembles non-rotational disks */
+ queue_flag_set_unlocked(QUEUE_FLAG_NONROT, zram->disk->queue);
+
+ zram->meta = meta;
+ zram->init_done = 1;
+
+ pr_debug("Initialization done!\n");
+}
+
+static ssize_t disksize_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t len)
+{
+ u64 disksize;
+ struct zram_meta *meta;
+ struct zram *zram = dev_to_zram(dev);
+
+ disksize = memparse(buf, NULL);
+ if (!disksize)
+ return -EINVAL;
+
+ disksize = PAGE_ALIGN(disksize);
+ meta = zram_meta_alloc(disksize);
+ down_write(&zram->init_lock);
+ if (zram->init_done) {
+ up_write(&zram->init_lock);
+ zram_meta_free(meta);
+ pr_info("Cannot change disksize for initialized device\n");
+ return -EBUSY;
+ }
+
+ zram->disksize = disksize;
+ set_capacity(zram->disk, zram->disksize >> SECTOR_SHIFT);
+ zram_init_device(zram, meta);
+ up_write(&zram->init_lock);
+
+ return len;
+}
+
+static ssize_t reset_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t len)
+{
+ int ret;
+ unsigned short do_reset;
+ struct zram *zram;
+ struct block_device *bdev;
+
+ zram = dev_to_zram(dev);
+ bdev = bdget_disk(zram->disk, 0);
+
+ if (!bdev)
+ return -ENOMEM;
+
+ /* Do not reset an active device! */
+ if (bdev->bd_holders) {
+ ret = -EBUSY;
+ goto out;
+ }
+
+ ret = kstrtou16(buf, 10, &do_reset);
+ if (ret)
+ goto out;
+
+ if (!do_reset) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /* Make sure all pending I/O is finished */
+ fsync_bdev(bdev);
+ bdput(bdev);
+
+ zram_reset_device(zram, true);
+ return len;
+
+out:
+ bdput(bdev);
+ return ret;
+}
+
+static void __zram_make_request(struct zram *zram, struct bio *bio, int rw)
+{
+ int offset;
+ u32 index;
+ struct bio_vec bvec;
+ struct bvec_iter iter;
+
+ switch (rw) {
+ case READ:
+ atomic64_inc(&zram->stats.num_reads);
+ break;
+ case WRITE:
+ atomic64_inc(&zram->stats.num_writes);
+ break;
+ }
+
+ index = bio->bi_iter.bi_sector >> SECTORS_PER_PAGE_SHIFT;
+ offset = (bio->bi_iter.bi_sector &
+ (SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT;
+
+ bio_for_each_segment(bvec, bio, iter) {
+ int max_transfer_size = PAGE_SIZE - offset;
+
+ if (bvec.bv_len > max_transfer_size) {
+ /*
+ * zram_bvec_rw() can only make operation on a single
+ * zram page. Split the bio vector.
+ */
+ struct bio_vec bv;
+
+ bv.bv_page = bvec.bv_page;
+ bv.bv_len = max_transfer_size;
+ bv.bv_offset = bvec.bv_offset;
+
+ if (zram_bvec_rw(zram, &bv, index, offset, bio, rw) < 0)
+ goto out;
+
+ bv.bv_len = bvec.bv_len - max_transfer_size;
+ bv.bv_offset += max_transfer_size;
+ if (zram_bvec_rw(zram, &bv, index+1, 0, bio, rw) < 0)
+ goto out;
+ } else
+ if (zram_bvec_rw(zram, &bvec, index, offset, bio, rw)
+ < 0)
+ goto out;
+
+ update_position(&index, &offset, &bvec);
+ }
+
+ set_bit(BIO_UPTODATE, &bio->bi_flags);
+ bio_endio(bio, 0);
+ return;
+
+out:
+ bio_io_error(bio);
+}
+
+/*
+ * Handler function for all zram I/O requests.
+ */
+static void zram_make_request(struct request_queue *queue, struct bio *bio)
+{
+ struct zram *zram = queue->queuedata;
+
+ down_read(&zram->init_lock);
+ if (unlikely(!zram->init_done))
+ goto error;
+
+ if (!valid_io_request(zram, bio)) {
+ atomic64_inc(&zram->stats.invalid_io);
+ goto error;
+ }
+
+ __zram_make_request(zram, bio, bio_data_dir(bio));
+ up_read(&zram->init_lock);
+
+ return;
+
+error:
+ up_read(&zram->init_lock);
+ bio_io_error(bio);
+}
+
+static void zram_slot_free_notify(struct block_device *bdev,
+ unsigned long index)
+{
+ struct zram *zram;
+ struct zram_meta *meta;
+
+ zram = bdev->bd_disk->private_data;
+ meta = zram->meta;
+
+ write_lock(&meta->tb_lock);
+ zram_free_page(zram, index);
+ write_unlock(&meta->tb_lock);
+ atomic64_inc(&zram->stats.notify_free);
+}
+
+static const struct block_device_operations zram_devops = {
+ .swap_slot_free_notify = zram_slot_free_notify,
+ .owner = THIS_MODULE
+};
+
+static DEVICE_ATTR(disksize, S_IRUGO | S_IWUSR,
+ disksize_show, disksize_store);
+static DEVICE_ATTR(initstate, S_IRUGO, initstate_show, NULL);
+static DEVICE_ATTR(reset, S_IWUSR, NULL, reset_store);
+static DEVICE_ATTR(num_reads, S_IRUGO, num_reads_show, NULL);
+static DEVICE_ATTR(num_writes, S_IRUGO, num_writes_show, NULL);
+static DEVICE_ATTR(invalid_io, S_IRUGO, invalid_io_show, NULL);
+static DEVICE_ATTR(notify_free, S_IRUGO, notify_free_show, NULL);
+static DEVICE_ATTR(zero_pages, S_IRUGO, zero_pages_show, NULL);
+static DEVICE_ATTR(orig_data_size, S_IRUGO, orig_data_size_show, NULL);
+static DEVICE_ATTR(compr_data_size, S_IRUGO, compr_data_size_show, NULL);
+static DEVICE_ATTR(mem_used_total, S_IRUGO, mem_used_total_show, NULL);
+
+static struct attribute *zram_disk_attrs[] = {
+ &dev_attr_disksize.attr,
+ &dev_attr_initstate.attr,
+ &dev_attr_reset.attr,
+ &dev_attr_num_reads.attr,
+ &dev_attr_num_writes.attr,
+ &dev_attr_invalid_io.attr,
+ &dev_attr_notify_free.attr,
+ &dev_attr_zero_pages.attr,
+ &dev_attr_orig_data_size.attr,
+ &dev_attr_compr_data_size.attr,
+ &dev_attr_mem_used_total.attr,
+ NULL,
+};
+
+static struct attribute_group zram_disk_attr_group = {
+ .attrs = zram_disk_attrs,
+};
+
+static int create_device(struct zram *zram, int device_id)
+{
+ int ret = -ENOMEM;
+
+ init_rwsem(&zram->init_lock);
+
+ zram->queue = blk_alloc_queue(GFP_KERNEL);
+ if (!zram->queue) {
+ pr_err("Error allocating disk queue for device %d\n",
+ device_id);
+ goto out;
+ }
+
+ blk_queue_make_request(zram->queue, zram_make_request);
+ zram->queue->queuedata = zram;
+
+ /* gendisk structure */
+ zram->disk = alloc_disk(1);
+ if (!zram->disk) {
+ pr_warn("Error allocating disk structure for device %d\n",
+ device_id);
+ goto out_free_queue;
+ }
+
+ zram->disk->major = zram_major;
+ zram->disk->first_minor = device_id;
+ zram->disk->fops = &zram_devops;
+ zram->disk->queue = zram->queue;
+ zram->disk->private_data = zram;
+ snprintf(zram->disk->disk_name, 16, "zram%d", device_id);
+
+ /* Actual capacity set using syfs (/sys/block/zram<id>/disksize */
+ set_capacity(zram->disk, 0);
+
+ /*
+ * To ensure that we always get PAGE_SIZE aligned
+ * and n*PAGE_SIZED sized I/O requests.
+ */
+ blk_queue_physical_block_size(zram->disk->queue, PAGE_SIZE);
+ blk_queue_logical_block_size(zram->disk->queue,
+ ZRAM_LOGICAL_BLOCK_SIZE);
+ blk_queue_io_min(zram->disk->queue, PAGE_SIZE);
+ blk_queue_io_opt(zram->disk->queue, PAGE_SIZE);
+
+ add_disk(zram->disk);
+
+ ret = sysfs_create_group(&disk_to_dev(zram->disk)->kobj,
+ &zram_disk_attr_group);
+ if (ret < 0) {
+ pr_warn("Error creating sysfs group");
+ goto out_free_disk;
+ }
+
+ zram->init_done = 0;
+ return 0;
+
+out_free_disk:
+ del_gendisk(zram->disk);
+ put_disk(zram->disk);
+out_free_queue:
+ blk_cleanup_queue(zram->queue);
+out:
+ return ret;
+}
+
+static void destroy_device(struct zram *zram)
+{
+ sysfs_remove_group(&disk_to_dev(zram->disk)->kobj,
+ &zram_disk_attr_group);
+
+ del_gendisk(zram->disk);
+ put_disk(zram->disk);
+
+ blk_cleanup_queue(zram->queue);
+}
+
+static int __init zram_init(void)
+{
+ int ret, dev_id;
+
+ if (num_devices > max_num_devices) {
+ pr_warn("Invalid value for num_devices: %u\n",
+ num_devices);
+ ret = -EINVAL;
+ goto out;
+ }
+
+ zram_major = register_blkdev(0, "zram");
+ if (zram_major <= 0) {
+ pr_warn("Unable to get major number\n");
+ ret = -EBUSY;
+ goto out;
+ }
+
+ /* Allocate the device array and initialize each one */
+ zram_devices = kzalloc(num_devices * sizeof(struct zram), GFP_KERNEL);
+ if (!zram_devices) {
+ ret = -ENOMEM;
+ goto unregister;
+ }
+
+ for (dev_id = 0; dev_id < num_devices; dev_id++) {
+ ret = create_device(&zram_devices[dev_id], dev_id);
+ if (ret)
+ goto free_devices;
+ }
+
+ pr_info("Created %u device(s) ...\n", num_devices);
+
+ return 0;
+
+free_devices:
+ while (dev_id)
+ destroy_device(&zram_devices[--dev_id]);
+ kfree(zram_devices);
+unregister:
+ unregister_blkdev(zram_major, "zram");
+out:
+ return ret;
+}
+
+static void __exit zram_exit(void)
+{
+ int i;
+ struct zram *zram;
+
+ for (i = 0; i < num_devices; i++) {
+ zram = &zram_devices[i];
+
+ destroy_device(zram);
+ /*
+ * Shouldn't access zram->disk after destroy_device
+ * because destroy_device already released zram->disk.
+ */
+ zram_reset_device(zram, false);
+ }
+
+ unregister_blkdev(zram_major, "zram");
+
+ kfree(zram_devices);
+ pr_debug("Cleanup done!\n");
+}
+
+module_init(zram_init);
+module_exit(zram_exit);
+
+module_param(num_devices, uint, 0);
+MODULE_PARM_DESC(num_devices, "Number of zram devices");
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_AUTHOR("Nitin Gupta <ngupta@vflare.org>");
+MODULE_DESCRIPTION("Compressed RAM Block Device");
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
new file mode 100644
index 000000000000..ad8aa35bae00
--- /dev/null
+++ b/drivers/block/zram/zram_drv.h
@@ -0,0 +1,109 @@
+/*
+ * Compressed RAM block device
+ *
+ * Copyright (C) 2008, 2009, 2010 Nitin Gupta
+ * 2012, 2013 Minchan Kim
+ *
+ * This code is released using a dual license strategy: BSD/GPL
+ * You can choose the licence that better fits your requirements.
+ *
+ * Released under the terms of 3-clause BSD License
+ * Released under the terms of GNU General Public License Version 2.0
+ *
+ */
+
+#ifndef _ZRAM_DRV_H_
+#define _ZRAM_DRV_H_
+
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
+#include <linux/zsmalloc.h>
+
+/*
+ * Some arbitrary value. This is just to catch
+ * invalid value for num_devices module parameter.
+ */
+static const unsigned max_num_devices = 32;
+
+/*-- Configurable parameters */
+
+/*
+ * Pages that compress to size greater than this are stored
+ * uncompressed in memory.
+ */
+static const size_t max_zpage_size = PAGE_SIZE / 4 * 3;
+
+/*
+ * NOTE: max_zpage_size must be less than or equal to:
+ * ZS_MAX_ALLOC_SIZE. Otherwise, zs_malloc() would
+ * always return failure.
+ */
+
+/*-- End of configurable params */
+
+#define SECTOR_SHIFT 9
+#define SECTOR_SIZE (1 << SECTOR_SHIFT)
+#define SECTORS_PER_PAGE_SHIFT (PAGE_SHIFT - SECTOR_SHIFT)
+#define SECTORS_PER_PAGE (1 << SECTORS_PER_PAGE_SHIFT)
+#define ZRAM_LOGICAL_BLOCK_SHIFT 12
+#define ZRAM_LOGICAL_BLOCK_SIZE (1 << ZRAM_LOGICAL_BLOCK_SHIFT)
+#define ZRAM_SECTOR_PER_LOGICAL_BLOCK \
+ (1 << (ZRAM_LOGICAL_BLOCK_SHIFT - SECTOR_SHIFT))
+
+/* Flags for zram pages (table[page_no].flags) */
+enum zram_pageflags {
+ /* Page consists entirely of zeros */
+ ZRAM_ZERO,
+
+ __NR_ZRAM_PAGEFLAGS,
+};
+
+/*-- Data structures */
+
+/* Allocated for each disk page */
+struct table {
+ unsigned long handle;
+ u16 size; /* object size (excluding header) */
+ u8 count; /* object ref count (not yet used) */
+ u8 flags;
+} __aligned(4);
+
+struct zram_stats {
+ atomic64_t compr_size; /* compressed size of pages stored */
+ atomic64_t num_reads; /* failed + successful */
+ atomic64_t num_writes; /* --do-- */
+ atomic64_t failed_reads; /* should NEVER! happen */
+ atomic64_t failed_writes; /* can happen when memory is too low */
+ atomic64_t invalid_io; /* non-page-aligned I/O requests */
+ atomic64_t notify_free; /* no. of swap slot free notifications */
+ atomic_t pages_zero; /* no. of zero filled pages */
+ atomic_t pages_stored; /* no. of pages currently stored */
+ atomic_t good_compress; /* % of pages with compression ratio<=50% */
+ atomic_t bad_compress; /* % of pages with compression ratio>=75% */
+};
+
+struct zram_meta {
+ rwlock_t tb_lock; /* protect table */
+ void *compress_workmem;
+ void *compress_buffer;
+ struct table *table;
+ struct zs_pool *mem_pool;
+ struct mutex buffer_lock; /* protect compress buffers */
+};
+
+struct zram {
+ struct zram_meta *meta;
+ struct request_queue *queue;
+ struct gendisk *disk;
+ int init_done;
+ /* Prevent concurrent execution of device init, reset and R/W request */
+ struct rw_semaphore init_lock;
+ /*
+ * This is the limit on amount of *uncompressed* worth of data
+ * we can store in a disk.
+ */
+ u64 disksize; /* bytes */
+
+ struct zram_stats stats;
+};
+#endif
OpenPOWER on IntegriCloud