aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--MAINTAINERS4
-rw-r--r--block/blk-mq.c12
-rw-r--r--block/sed-opal.c6
-rw-r--r--drivers/block/loop.c10
-rw-r--r--drivers/char/random.c2
-rw-r--r--drivers/clocksource/timer-of.c4
-rw-r--r--drivers/nvme/host/core.c132
-rw-r--r--drivers/nvme/host/nvme.h2
-rw-r--r--drivers/nvme/host/pci.c20
-rw-r--r--drivers/nvme/host/rdma.c19
-rw-r--r--drivers/nvme/host/tcp.c4
-rw-r--r--drivers/nvme/target/io-cmd-bdev.c16
-rw-r--r--drivers/nvme/target/tcp.c12
-rw-r--r--drivers/s390/block/dasd_eckd.c81
-rw-r--r--fs/erofs/data.c10
-rw-r--r--fs/erofs/super.c4
-rw-r--r--fs/erofs/zdata.c12
-rw-r--r--fs/io_uring.c8
-rw-r--r--fs/statfs.c17
-rw-r--r--include/uapi/linux/nvme_ioctl.h23
-rw-r--r--include/uapi/linux/pg.h5
-rw-r--r--kernel/sched/membarrier.c1
-rw-r--r--kernel/time/tick-broadcast-hrtimer.c62
23 files changed, 278 insertions, 188 deletions
diff --git a/MAINTAINERS b/MAINTAINERS
index 296de2b51c83..55199ef7fa74 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6112,7 +6112,10 @@ M: Gao Xiang <gaoxiang25@huawei.com>
M: Chao Yu <yuchao0@huawei.com>
L: linux-erofs@lists.ozlabs.org
S: Maintained
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs.git
+F: Documentation/filesystems/erofs.txt
F: fs/erofs/
+F: include/trace/events/erofs.h
ERRSEQ ERROR TRACKING INFRASTRUCTURE
M: Jeff Layton <jlayton@kernel.org>
@@ -9075,6 +9078,7 @@ F: security/keys/
KGDB / KDB /debug_core
M: Jason Wessel <jason.wessel@windriver.com>
M: Daniel Thompson <daniel.thompson@linaro.org>
+R: Douglas Anderson <dianders@chromium.org>
W: http://kgdb.wiki.kernel.org/
L: kgdb-bugreport@lists.sourceforge.net
T: git git://git.kernel.org/pub/scm/linux/kernel/git/jwessel/kgdb.git
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 6e3b15f70cd7..ec791156e9cc 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1992,10 +1992,14 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
/* bypass scheduler for flush rq */
blk_insert_flush(rq);
blk_mq_run_hw_queue(data.hctx, true);
- } else if (plug && (q->nr_hw_queues == 1 || q->mq_ops->commit_rqs)) {
+ } else if (plug && (q->nr_hw_queues == 1 || q->mq_ops->commit_rqs ||
+ !blk_queue_nonrot(q))) {
/*
* Use plugging if we have a ->commit_rqs() hook as well, as
* we know the driver uses bd->last in a smart fashion.
+ *
+ * Use normal plugging if this disk is slow HDD, as sequential
+ * IO may benefit a lot from plug merging.
*/
unsigned int request_count = plug->rq_count;
struct request *last = NULL;
@@ -2012,6 +2016,8 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
}
blk_add_rq_to_plug(plug, rq);
+ } else if (q->elevator) {
+ blk_mq_sched_insert_request(rq, false, true, true);
} else if (plug && !blk_queue_nomerges(q)) {
/*
* We do limited plugging. If the bio can be merged, do that.
@@ -2035,8 +2041,8 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
blk_mq_try_issue_directly(data.hctx, same_queue_rq,
&cookie);
}
- } else if ((q->nr_hw_queues > 1 && is_sync) || (!q->elevator &&
- !data.hctx->dispatch_busy)) {
+ } else if ((q->nr_hw_queues > 1 && is_sync) ||
+ !data.hctx->dispatch_busy) {
blk_mq_try_issue_directly(data.hctx, rq, &cookie);
} else {
blk_mq_sched_insert_request(rq, false, true, true);
diff --git a/block/sed-opal.c b/block/sed-opal.c
index 4e95a9792162..b4c761973ac1 100644
--- a/block/sed-opal.c
+++ b/block/sed-opal.c
@@ -129,7 +129,7 @@ static const u8 opaluid[][OPAL_UID_LENGTH] = {
{ 0x00, 0x00, 0x00, 0x09, 0x00, 0x00, 0x84, 0x01 },
/* tables */
- [OPAL_TABLE_TABLE]
+ [OPAL_TABLE_TABLE] =
{ 0x00, 0x00, 0x00, 0x01, 0x00, 0x00, 0x00, 0x01 },
[OPAL_LOCKINGRANGE_GLOBAL] =
{ 0x00, 0x00, 0x08, 0x02, 0x00, 0x00, 0x00, 0x01 },
@@ -372,8 +372,8 @@ static void check_geometry(struct opal_dev *dev, const void *data)
{
const struct d0_geometry_features *geo = data;
- dev->align = geo->alignment_granularity;
- dev->lowest_lba = geo->lowest_aligned_lba;
+ dev->align = be64_to_cpu(geo->alignment_granularity);
+ dev->lowest_lba = be64_to_cpu(geo->lowest_aligned_lba);
}
static int execute_step(struct opal_dev *dev,
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 1410fa893653..f6f77eaa7217 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -994,6 +994,16 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
blk_queue_write_cache(lo->lo_queue, true, false);
+ if (io_is_direct(lo->lo_backing_file) && inode->i_sb->s_bdev) {
+ /* In case of direct I/O, match underlying block size */
+ unsigned short bsize = bdev_logical_block_size(
+ inode->i_sb->s_bdev);
+
+ blk_queue_logical_block_size(lo->lo_queue, bsize);
+ blk_queue_physical_block_size(lo->lo_queue, bsize);
+ blk_queue_io_min(lo->lo_queue, bsize);
+ }
+
loop_update_rotational(lo);
loop_update_dio(lo);
set_capacity(lo->lo_disk, size);
diff --git a/drivers/char/random.c b/drivers/char/random.c
index c2f7de9dc543..de434feb873a 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -2520,4 +2520,4 @@ void add_bootloader_randomness(const void *buf, unsigned int size)
else
add_device_randomness(buf, size);
}
-EXPORT_SYMBOL_GPL(add_bootloader_randomness); \ No newline at end of file
+EXPORT_SYMBOL_GPL(add_bootloader_randomness);
diff --git a/drivers/clocksource/timer-of.c b/drivers/clocksource/timer-of.c
index d8c2bd4391d0..11ff701ff4bb 100644
--- a/drivers/clocksource/timer-of.c
+++ b/drivers/clocksource/timer-of.c
@@ -25,7 +25,9 @@ static __init void timer_of_irq_exit(struct of_timer_irq *of_irq)
struct clock_event_device *clkevt = &to->clkevt;
- of_irq->percpu ? free_percpu_irq(of_irq->irq, clkevt) :
+ if (of_irq->percpu)
+ free_percpu_irq(of_irq->irq, clkevt);
+ else
free_irq(of_irq->irq, clkevt);
}
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 108f60b46804..fd7dea36c3b6 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -102,10 +102,13 @@ static void nvme_set_queue_dying(struct nvme_ns *ns)
*/
if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags))
return;
- revalidate_disk(ns->disk);
blk_set_queue_dying(ns->queue);
/* Forcibly unquiesce queues to avoid blocking dispatch */
blk_mq_unquiesce_queue(ns->queue);
+ /*
+ * Revalidate after unblocking dispatchers that may be holding bd_butex
+ */
+ revalidate_disk(ns->disk);
}
static void nvme_queue_scan(struct nvme_ctrl *ctrl)
@@ -847,7 +850,7 @@ out:
static int nvme_submit_user_cmd(struct request_queue *q,
struct nvme_command *cmd, void __user *ubuffer,
unsigned bufflen, void __user *meta_buffer, unsigned meta_len,
- u32 meta_seed, u32 *result, unsigned timeout)
+ u32 meta_seed, u64 *result, unsigned timeout)
{
bool write = nvme_is_write(cmd);
struct nvme_ns *ns = q->queuedata;
@@ -888,7 +891,7 @@ static int nvme_submit_user_cmd(struct request_queue *q,
else
ret = nvme_req(req)->status;
if (result)
- *result = le32_to_cpu(nvme_req(req)->result.u32);
+ *result = le64_to_cpu(nvme_req(req)->result.u64);
if (meta && !ret && !write) {
if (copy_to_user(meta_buffer, meta, meta_len))
ret = -EFAULT;
@@ -1335,6 +1338,54 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
struct nvme_command c;
unsigned timeout = 0;
u32 effects;
+ u64 result;
+ int status;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
+ if (copy_from_user(&cmd, ucmd, sizeof(cmd)))
+ return -EFAULT;
+ if (cmd.flags)
+ return -EINVAL;
+
+ memset(&c, 0, sizeof(c));
+ c.common.opcode = cmd.opcode;
+ c.common.flags = cmd.flags;
+ c.common.nsid = cpu_to_le32(cmd.nsid);
+ c.common.cdw2[0] = cpu_to_le32(cmd.cdw2);
+ c.common.cdw2[1] = cpu_to_le32(cmd.cdw3);
+ c.common.cdw10 = cpu_to_le32(cmd.cdw10);
+ c.common.cdw11 = cpu_to_le32(cmd.cdw11);
+ c.common.cdw12 = cpu_to_le32(cmd.cdw12);
+ c.common.cdw13 = cpu_to_le32(cmd.cdw13);
+ c.common.cdw14 = cpu_to_le32(cmd.cdw14);
+ c.common.cdw15 = cpu_to_le32(cmd.cdw15);
+
+ if (cmd.timeout_ms)
+ timeout = msecs_to_jiffies(cmd.timeout_ms);
+
+ effects = nvme_passthru_start(ctrl, ns, cmd.opcode);
+ status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
+ (void __user *)(uintptr_t)cmd.addr, cmd.data_len,
+ (void __user *)(uintptr_t)cmd.metadata,
+ cmd.metadata_len, 0, &result, timeout);
+ nvme_passthru_end(ctrl, effects);
+
+ if (status >= 0) {
+ if (put_user(result, &ucmd->result))
+ return -EFAULT;
+ }
+
+ return status;
+}
+
+static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
+ struct nvme_passthru_cmd64 __user *ucmd)
+{
+ struct nvme_passthru_cmd64 cmd;
+ struct nvme_command c;
+ unsigned timeout = 0;
+ u32 effects;
int status;
if (!capable(CAP_SYS_ADMIN))
@@ -1405,6 +1456,41 @@ static void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx)
srcu_read_unlock(&head->srcu, idx);
}
+static bool is_ctrl_ioctl(unsigned int cmd)
+{
+ if (cmd == NVME_IOCTL_ADMIN_CMD || cmd == NVME_IOCTL_ADMIN64_CMD)
+ return true;
+ if (is_sed_ioctl(cmd))
+ return true;
+ return false;
+}
+
+static int nvme_handle_ctrl_ioctl(struct nvme_ns *ns, unsigned int cmd,
+ void __user *argp,
+ struct nvme_ns_head *head,
+ int srcu_idx)
+{
+ struct nvme_ctrl *ctrl = ns->ctrl;
+ int ret;
+
+ nvme_get_ctrl(ns->ctrl);
+ nvme_put_ns_from_disk(head, srcu_idx);
+
+ switch (cmd) {
+ case NVME_IOCTL_ADMIN_CMD:
+ ret = nvme_user_cmd(ctrl, NULL, argp);
+ break;
+ case NVME_IOCTL_ADMIN64_CMD:
+ ret = nvme_user_cmd64(ctrl, NULL, argp);
+ break;
+ default:
+ ret = sed_ioctl(ctrl->opal_dev, cmd, argp);
+ break;
+ }
+ nvme_put_ctrl(ctrl);
+ return ret;
+}
+
static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
unsigned int cmd, unsigned long arg)
{
@@ -1422,20 +1508,8 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
* seperately and drop the ns SRCU reference early. This avoids a
* deadlock when deleting namespaces using the passthrough interface.
*/
- if (cmd == NVME_IOCTL_ADMIN_CMD || is_sed_ioctl(cmd)) {
- struct nvme_ctrl *ctrl = ns->ctrl;
-
- nvme_get_ctrl(ns->ctrl);
- nvme_put_ns_from_disk(head, srcu_idx);
-
- if (cmd == NVME_IOCTL_ADMIN_CMD)
- ret = nvme_user_cmd(ctrl, NULL, argp);
- else
- ret = sed_ioctl(ctrl->opal_dev, cmd, argp);
-
- nvme_put_ctrl(ctrl);
- return ret;
- }
+ if (is_ctrl_ioctl(cmd))
+ return nvme_handle_ctrl_ioctl(ns, cmd, argp, head, srcu_idx);
switch (cmd) {
case NVME_IOCTL_ID:
@@ -1448,6 +1522,9 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
case NVME_IOCTL_SUBMIT_IO:
ret = nvme_submit_io(ns, argp);
break;
+ case NVME_IOCTL_IO64_CMD:
+ ret = nvme_user_cmd64(ns->ctrl, ns, argp);
+ break;
default:
if (ns->ndev)
ret = nvme_nvm_ioctl(ns, cmd, arg);
@@ -2289,6 +2366,16 @@ static const struct nvme_core_quirk_entry core_quirks[] = {
.vid = 0x14a4,
.fr = "22301111",
.quirks = NVME_QUIRK_SIMPLE_SUSPEND,
+ },
+ {
+ /*
+ * This Kingston E8FK11.T firmware version has no interrupt
+ * after resume with actions related to suspend to idle
+ * https://bugzilla.kernel.org/show_bug.cgi?id=204887
+ */
+ .vid = 0x2646,
+ .fr = "E8FK11.T",
+ .quirks = NVME_QUIRK_SIMPLE_SUSPEND,
}
};
@@ -2540,8 +2627,9 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
list_add_tail(&subsys->entry, &nvme_subsystems);
}
- if (sysfs_create_link(&subsys->dev.kobj, &ctrl->device->kobj,
- dev_name(ctrl->device))) {
+ ret = sysfs_create_link(&subsys->dev.kobj, &ctrl->device->kobj,
+ dev_name(ctrl->device));
+ if (ret) {
dev_err(ctrl->device,
"failed to create sysfs link from subsystem.\n");
goto out_put_subsystem;
@@ -2838,6 +2926,8 @@ static long nvme_dev_ioctl(struct file *file, unsigned int cmd,
switch (cmd) {
case NVME_IOCTL_ADMIN_CMD:
return nvme_user_cmd(ctrl, NULL, argp);
+ case NVME_IOCTL_ADMIN64_CMD:
+ return nvme_user_cmd64(ctrl, NULL, argp);
case NVME_IOCTL_IO_CMD:
return nvme_dev_user_cmd(ctrl, argp);
case NVME_IOCTL_RESET:
@@ -3045,6 +3135,8 @@ static DEVICE_ATTR(field, S_IRUGO, field##_show, NULL);
nvme_show_int_function(cntlid);
nvme_show_int_function(numa_node);
+nvme_show_int_function(queue_count);
+nvme_show_int_function(sqsize);
static ssize_t nvme_sysfs_delete(struct device *dev,
struct device_attribute *attr, const char *buf,
@@ -3125,6 +3217,8 @@ static struct attribute *nvme_dev_attrs[] = {
&dev_attr_address.attr,
&dev_attr_state.attr,
&dev_attr_numa_node.attr,
+ &dev_attr_queue_count.attr,
+ &dev_attr_sqsize.attr,
NULL
};
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index b5013c101b35..38a83ef5bcd3 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -221,6 +221,7 @@ struct nvme_ctrl {
u16 oacs;
u16 nssa;
u16 nr_streams;
+ u16 sqsize;
u32 max_namespaces;
atomic_t abort_limit;
u8 vwc;
@@ -269,7 +270,6 @@ struct nvme_ctrl {
u16 hmmaxd;
/* Fabrics only */
- u16 sqsize;
u32 ioccsz;
u32 iorcsz;
u16 icdoff;
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index c0808f9eb8ab..bb88681f4dc3 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2946,11 +2946,21 @@ static int nvme_suspend(struct device *dev)
if (ret < 0)
goto unfreeze;
+ /*
+ * A saved state prevents pci pm from generically controlling the
+ * device's power. If we're using protocol specific settings, we don't
+ * want pci interfering.
+ */
+ pci_save_state(pdev);
+
ret = nvme_set_power_state(ctrl, ctrl->npss);
if (ret < 0)
goto unfreeze;
if (ret) {
+ /* discard the saved state */
+ pci_load_saved_state(pdev, NULL);
+
/*
* Clearing npss forces a controller reset on resume. The
* correct value will be resdicovered then.
@@ -2958,14 +2968,7 @@ static int nvme_suspend(struct device *dev)
nvme_dev_disable(ndev, true);
ctrl->npss = 0;
ret = 0;
- goto unfreeze;
}
- /*
- * A saved state prevents pci pm from generically controlling the
- * device's power. If we're using protocol specific settings, we don't
- * want pci interfering.
- */
- pci_save_state(pdev);
unfreeze:
nvme_unfreeze(ctrl);
return ret;
@@ -3090,6 +3093,9 @@ static const struct pci_device_id nvme_id_table[] = {
.driver_data = NVME_QUIRK_LIGHTNVM, },
{ PCI_DEVICE(0x10ec, 0x5762), /* ADATA SX6000LNP */
.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, },
+ { PCI_DEVICE(0x1cc1, 0x8201), /* ADATA SX8200PNP 512GB */
+ .driver_data = NVME_QUIRK_NO_DEEPEST_PS |
+ NVME_QUIRK_IGNORE_DEV_SUBNQN, },
{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) },
{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) },
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index dfa07bb9dfeb..4d280160dd3f 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -427,7 +427,7 @@ static void nvme_rdma_destroy_queue_ib(struct nvme_rdma_queue *queue)
static int nvme_rdma_get_max_fr_pages(struct ib_device *ibdev)
{
return min_t(u32, NVME_RDMA_MAX_SEGMENTS,
- ibdev->attrs.max_fast_reg_page_list_len);
+ ibdev->attrs.max_fast_reg_page_list_len - 1);
}
static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue)
@@ -437,7 +437,7 @@ static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue)
const int cq_factor = send_wr_factor + 1; /* + RECV */
int comp_vector, idx = nvme_rdma_queue_idx(queue);
enum ib_poll_context poll_ctx;
- int ret;
+ int ret, pages_per_mr;
queue->device = nvme_rdma_find_get_device(queue->cm_id);
if (!queue->device) {
@@ -479,10 +479,16 @@ static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue)
goto out_destroy_qp;
}
+ /*
+ * Currently we don't use SG_GAPS MR's so if the first entry is
+ * misaligned we'll end up using two entries for a single data page,
+ * so one additional entry is required.
+ */
+ pages_per_mr = nvme_rdma_get_max_fr_pages(ibdev) + 1;
ret = ib_mr_pool_init(queue->qp, &queue->qp->rdma_mrs,
queue->queue_size,
IB_MR_TYPE_MEM_REG,
- nvme_rdma_get_max_fr_pages(ibdev), 0);
+ pages_per_mr, 0);
if (ret) {
dev_err(queue->ctrl->ctrl.device,
"failed to initialize MR pool sized %d for QID %d\n",
@@ -614,7 +620,8 @@ static int nvme_rdma_start_queue(struct nvme_rdma_ctrl *ctrl, int idx)
if (!ret) {
set_bit(NVME_RDMA_Q_LIVE, &queue->flags);
} else {
- __nvme_rdma_stop_queue(queue);
+ if (test_bit(NVME_RDMA_Q_ALLOCATED, &queue->flags))
+ __nvme_rdma_stop_queue(queue);
dev_info(ctrl->ctrl.device,
"failed to connect queue: %d ret=%d\n", idx, ret);
}
@@ -820,8 +827,8 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl,
if (error)
goto out_stop_queue;
- ctrl->ctrl.max_hw_sectors =
- (ctrl->max_fr_pages - 1) << (ilog2(SZ_4K) - 9);
+ ctrl->ctrl.max_segments = ctrl->max_fr_pages;
+ ctrl->ctrl.max_hw_sectors = ctrl->max_fr_pages << (ilog2(SZ_4K) - 9);
blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 4ffd5957637a..385a5212c10f 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1042,7 +1042,7 @@ static void nvme_tcp_io_work(struct work_struct *w)
{
struct nvme_tcp_queue *queue =
container_of(w, struct nvme_tcp_queue, io_work);
- unsigned long start = jiffies + msecs_to_jiffies(1);
+ unsigned long deadline = jiffies + msecs_to_jiffies(1);
do {
bool pending = false;
@@ -1067,7 +1067,7 @@ static void nvme_tcp_io_work(struct work_struct *w)
if (!pending)
return;
- } while (time_after(jiffies, start)); /* quota is exhausted */
+ } while (!time_after(jiffies, deadline)); /* quota is exhausted */
queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work);
}
diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c
index de0bff70ebb6..32008d85172b 100644
--- a/drivers/nvme/target/io-cmd-bdev.c
+++ b/drivers/nvme/target/io-cmd-bdev.c
@@ -11,10 +11,10 @@
void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id)
{
const struct queue_limits *ql = &bdev_get_queue(bdev)->limits;
- /* Number of physical blocks per logical block. */
- const u32 ppl = ql->physical_block_size / ql->logical_block_size;
- /* Physical blocks per logical block, 0's based. */
- const __le16 ppl0b = to0based(ppl);
+ /* Number of logical blocks per physical block. */
+ const u32 lpp = ql->physical_block_size / ql->logical_block_size;
+ /* Logical blocks per physical block, 0's based. */
+ const __le16 lpp0b = to0based(lpp);
/*
* For NVMe 1.2 and later, bit 1 indicates that the fields NAWUN,
@@ -25,9 +25,9 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id)
* field from the identify controller data structure should be used.
*/
id->nsfeat |= 1 << 1;
- id->nawun = ppl0b;
- id->nawupf = ppl0b;
- id->nacwu = ppl0b;
+ id->nawun = lpp0b;
+ id->nawupf = lpp0b;
+ id->nacwu = lpp0b;
/*
* Bit 4 indicates that the fields NPWG, NPWA, NPDG, NPDA, and
@@ -36,7 +36,7 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id)
*/
id->nsfeat |= 1 << 4;
/* NPWG = Namespace Preferred Write Granularity. 0's based */
- id->npwg = ppl0b;
+ id->npwg = lpp0b;
/* NPWA = Namespace Preferred Write Alignment. 0's based */
id->npwa = id->npwg;
/* NPDG = Namespace Preferred Deallocate Granularity. 0's based */
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index bf4f03474e89..d535080b781f 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -348,8 +348,7 @@ static int nvmet_tcp_map_data(struct nvmet_tcp_cmd *cmd)
return 0;
err:
- if (cmd->req.sg_cnt)
- sgl_free(cmd->req.sg);
+ sgl_free(cmd->req.sg);
return NVME_SC_INTERNAL;
}
@@ -554,8 +553,7 @@ static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd)
if (queue->nvme_sq.sqhd_disabled) {
kfree(cmd->iov);
- if (cmd->req.sg_cnt)
- sgl_free(cmd->req.sg);
+ sgl_free(cmd->req.sg);
}
return 1;
@@ -586,8 +584,7 @@ static int nvmet_try_send_response(struct nvmet_tcp_cmd *cmd,
return -EAGAIN;
kfree(cmd->iov);
- if (cmd->req.sg_cnt)
- sgl_free(cmd->req.sg);
+ sgl_free(cmd->req.sg);
cmd->queue->snd_cmd = NULL;
nvmet_tcp_put_cmd(cmd);
return 1;
@@ -1310,8 +1307,7 @@ static void nvmet_tcp_finish_cmd(struct nvmet_tcp_cmd *cmd)
nvmet_req_uninit(&cmd->req);
nvmet_tcp_unmap_pdu_iovec(cmd);
kfree(cmd->iov);
- if (cmd->req.sg_cnt)
- sgl_free(cmd->req.sg);
+ sgl_free(cmd->req.sg);
}
static void nvmet_tcp_uninit_data_in_cmds(struct nvmet_tcp_queue *queue)
diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index fc53e1e221f0..c94184d080f8 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -1553,8 +1553,8 @@ static int dasd_eckd_read_vol_info(struct dasd_device *device)
if (rc == 0) {
memcpy(&private->vsq, vsq, sizeof(*vsq));
} else {
- dev_warn(&device->cdev->dev,
- "Reading the volume storage information failed with rc=%d\n", rc);
+ DBF_EVENT_DEVID(DBF_WARNING, device->cdev,
+ "Reading the volume storage information failed with rc=%d", rc);
}
if (useglobal)
@@ -1737,8 +1737,8 @@ static int dasd_eckd_read_ext_pool_info(struct dasd_device *device)
if (rc == 0) {
dasd_eckd_cpy_ext_pool_data(device, lcq);
} else {
- dev_warn(&device->cdev->dev,
- "Reading the logical configuration failed with rc=%d\n", rc);
+ DBF_EVENT_DEVID(DBF_WARNING, device->cdev,
+ "Reading the logical configuration failed with rc=%d", rc);
}
dasd_sfree_request(cqr, cqr->memdev);
@@ -2020,14 +2020,10 @@ dasd_eckd_check_characteristics(struct dasd_device *device)
dasd_eckd_read_features(device);
/* Read Volume Information */
- rc = dasd_eckd_read_vol_info(device);
- if (rc)
- goto out_err3;
+ dasd_eckd_read_vol_info(device);
/* Read Extent Pool Information */
- rc = dasd_eckd_read_ext_pool_info(device);
- if (rc)
- goto out_err3;
+ dasd_eckd_read_ext_pool_info(device);
/* Read Device Characteristics */
rc = dasd_generic_read_dev_chars(device, DASD_ECKD_MAGIC,
@@ -2059,9 +2055,6 @@ dasd_eckd_check_characteristics(struct dasd_device *device)
if (readonly)
set_bit(DASD_FLAG_DEVICE_RO, &device->flags);
- if (dasd_eckd_is_ese(device))
- dasd_set_feature(device->cdev, DASD_FEATURE_DISCARD, 1);
-
dev_info(&device->cdev->dev, "New DASD %04X/%02X (CU %04X/%02X) "
"with %d cylinders, %d heads, %d sectors%s\n",
private->rdc_data.dev_type,
@@ -3695,14 +3688,6 @@ static int dasd_eckd_release_space(struct dasd_device *device,
return -EINVAL;
}
-static struct dasd_ccw_req *
-dasd_eckd_build_cp_discard(struct dasd_device *device, struct dasd_block *block,
- struct request *req, sector_t first_trk,
- sector_t last_trk)
-{
- return dasd_eckd_dso_ras(device, block, req, first_trk, last_trk, 1);
-}
-
static struct dasd_ccw_req *dasd_eckd_build_cp_cmd_single(
struct dasd_device *startdev,
struct dasd_block *block,
@@ -4447,10 +4432,6 @@ static struct dasd_ccw_req *dasd_eckd_build_cp(struct dasd_device *startdev,
cmdwtd = private->features.feature[12] & 0x40;
use_prefix = private->features.feature[8] & 0x01;
- if (req_op(req) == REQ_OP_DISCARD)
- return dasd_eckd_build_cp_discard(startdev, block, req,
- first_trk, last_trk);
-
cqr = NULL;
if (cdlspecial || dasd_page_cache) {
/* do nothing, just fall through to the cmd mode single case */
@@ -4729,14 +4710,12 @@ static struct dasd_ccw_req *dasd_eckd_build_alias_cp(struct dasd_device *base,
struct dasd_block *block,
struct request *req)
{
- struct dasd_device *startdev = NULL;
struct dasd_eckd_private *private;
- struct dasd_ccw_req *cqr;
+ struct dasd_device *startdev;
unsigned long flags;
+ struct dasd_ccw_req *cqr;
- /* Discard requests can only be processed on base devices */
- if (req_op(req) != REQ_OP_DISCARD)
- startdev = dasd_alias_get_start_dev(base);
+ startdev = dasd_alias_get_start_dev(base);
if (!startdev)
startdev = base;
private = startdev->private;
@@ -5663,14 +5642,10 @@ static int dasd_eckd_restore_device(struct dasd_device *device)
dasd_eckd_read_features(device);
/* Read Volume Information */
- rc = dasd_eckd_read_vol_info(device);
- if (rc)
- goto out_err2;
+ dasd_eckd_read_vol_info(device);
/* Read Extent Pool Information */
- rc = dasd_eckd_read_ext_pool_info(device);
- if (rc)
- goto out_err2;
+ dasd_eckd_read_ext_pool_info(device);
/* Read Device Characteristics */
rc = dasd_generic_read_dev_chars(device, DASD_ECKD_MAGIC,
@@ -6521,20 +6496,8 @@ static void dasd_eckd_setup_blk_queue(struct dasd_block *block)
unsigned int logical_block_size = block->bp_block;
struct request_queue *q = block->request_queue;
struct dasd_device *device = block->base;
- struct dasd_eckd_private *private;
- unsigned int max_discard_sectors;
- unsigned int max_bytes;
- unsigned int ext_bytes; /* Extent Size in Bytes */
- int recs_per_trk;
- int trks_per_cyl;
- int ext_limit;
- int ext_size; /* Extent Size in Cylinders */
int max;
- private = device->private;
- trks_per_cyl = private->rdc_data.trk_per_cyl;
- recs_per_trk = recs_per_track(&private->rdc_data, 0, logical_block_size);
-
if (device->features & DASD_FEATURE_USERAW) {
/*
* the max_blocks value for raw_track access is 256
@@ -6555,28 +6518,6 @@ static void dasd_eckd_setup_blk_queue(struct dasd_block *block)
/* With page sized segments each segment can be translated into one idaw/tidaw */
blk_queue_max_segment_size(q, PAGE_SIZE);
blk_queue_segment_boundary(q, PAGE_SIZE - 1);
-
- if (dasd_eckd_is_ese(device)) {
- /*
- * Depending on the extent size, up to UINT_MAX bytes can be
- * accepted. However, neither DASD_ECKD_RAS_EXTS_MAX nor the
- * device limits should be exceeded.
- */
- ext_size = dasd_eckd_ext_size(device);
- ext_limit = min(private->real_cyl / ext_size, DASD_ECKD_RAS_EXTS_MAX);
- ext_bytes = ext_size * trks_per_cyl * recs_per_trk *
- logical_block_size;
- max_bytes = UINT_MAX - (UINT_MAX % ext_bytes);
- if (max_bytes / ext_bytes > ext_limit)
- max_bytes = ext_bytes * ext_limit;
-
- max_discard_sectors = max_bytes / 512;
-
- blk_queue_max_discard_sectors(q, max_discard_sectors);
- blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
- q->limits.discard_granularity = ext_bytes;
- q->limits.discard_alignment = ext_bytes;
- }
}
static struct ccw_driver dasd_eckd_driver = {
diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index 8a9fcbd0e8ac..fc3a8d8064f8 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -34,11 +34,15 @@ static void erofs_readendio(struct bio *bio)
struct page *erofs_get_meta_page(struct super_block *sb, erofs_blk_t blkaddr)
{
- struct inode *const bd_inode = sb->s_bdev->bd_inode;
- struct address_space *const mapping = bd_inode->i_mapping;
+ struct address_space *const mapping = sb->s_bdev->bd_inode->i_mapping;
+ struct page *page;
- return read_cache_page_gfp(mapping, blkaddr,
+ page = read_cache_page_gfp(mapping, blkaddr,
mapping_gfp_constraint(mapping, ~__GFP_FS));
+ /* should already be PageUptodate */
+ if (!IS_ERR(page))
+ lock_page(page);
+ return page;
}
static int erofs_map_blocks_flatmode(struct inode *inode,
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index caf9a95173b0..0e369494f2f2 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -105,9 +105,9 @@ static int erofs_read_superblock(struct super_block *sb)
int ret;
page = read_mapping_page(sb->s_bdev->bd_inode->i_mapping, 0, NULL);
- if (!page) {
+ if (IS_ERR(page)) {
erofs_err(sb, "cannot read erofs superblock");
- return -EIO;
+ return PTR_ERR(page);
}
sbi = EROFS_SB(sb);
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index 96e34c90f814..fad80c97d247 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -575,7 +575,7 @@ static int z_erofs_do_read_page(struct z_erofs_decompress_frontend *fe,
struct erofs_map_blocks *const map = &fe->map;
struct z_erofs_collector *const clt = &fe->clt;
const loff_t offset = page_offset(page);
- bool tight = (clt->mode >= COLLECT_PRIMARY_HOOKED);
+ bool tight = true;
enum z_erofs_cache_alloctype cache_strategy;
enum z_erofs_page_type page_type;
@@ -628,8 +628,16 @@ restart_now:
preload_compressed_pages(clt, MNGD_MAPPING(sbi),
cache_strategy, pagepool);
- tight &= (clt->mode >= COLLECT_PRIMARY_HOOKED);
hitted:
+ /*
+ * Ensure the current partial page belongs to this submit chain rather
+ * than other concurrent submit chains or the noio(bypass) chain since
+ * those chains are handled asynchronously thus the page cannot be used
+ * for inplace I/O or pagevec (should be processed in strict order.)
+ */
+ tight &= (clt->mode >= COLLECT_PRIMARY_HOOKED &&
+ clt->mode != COLLECT_PRIMARY_FOLLOWED_NOINPLACE);
+
cur = end - min_t(unsigned int, offset + end - map->m_la, end);
if (!(map->m_flags & EROFS_MAP_MAPPED)) {
zero_user_segment(page, cur, end);
diff --git a/fs/io_uring.c b/fs/io_uring.c
index aa8ac557493c..8a0381f1a43b 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1892,15 +1892,15 @@ static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe)
unsigned count, req_dist, tail_index;
struct io_ring_ctx *ctx = req->ctx;
struct list_head *entry;
- struct timespec ts;
+ struct timespec64 ts;
if (unlikely(ctx->flags & IORING_SETUP_IOPOLL))
return -EINVAL;
if (sqe->flags || sqe->ioprio || sqe->buf_index || sqe->timeout_flags ||
sqe->len != 1)
return -EINVAL;
- if (copy_from_user(&ts, (void __user *) (unsigned long) sqe->addr,
- sizeof(ts)))
+
+ if (get_timespec64(&ts, u64_to_user_ptr(sqe->addr)))
return -EFAULT;
/*
@@ -1934,7 +1934,7 @@ static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe)
hrtimer_init(&req->timeout.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
req->timeout.timer.function = io_timeout_fn;
- hrtimer_start(&req->timeout.timer, timespec_to_ktime(ts),
+ hrtimer_start(&req->timeout.timer, timespec64_to_ktime(ts),
HRTIMER_MODE_REL);
return 0;
}
diff --git a/fs/statfs.c b/fs/statfs.c
index eea7af6f2f22..2616424012ea 100644
--- a/fs/statfs.c
+++ b/fs/statfs.c
@@ -318,19 +318,10 @@ COMPAT_SYSCALL_DEFINE2(fstatfs, unsigned int, fd, struct compat_statfs __user *,
static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstatfs *kbuf)
{
struct compat_statfs64 buf;
- if (sizeof(ubuf->f_bsize) == 4) {
- if ((kbuf->f_type | kbuf->f_bsize | kbuf->f_namelen |
- kbuf->f_frsize | kbuf->f_flags) & 0xffffffff00000000ULL)
- return -EOVERFLOW;
- /* f_files and f_ffree may be -1; it's okay
- * to stuff that into 32 bits */
- if (kbuf->f_files != 0xffffffffffffffffULL
- && (kbuf->f_files & 0xffffffff00000000ULL))
- return -EOVERFLOW;
- if (kbuf->f_ffree != 0xffffffffffffffffULL
- && (kbuf->f_ffree & 0xffffffff00000000ULL))
- return -EOVERFLOW;
- }
+
+ if ((kbuf->f_bsize | kbuf->f_frsize) & 0xffffffff00000000ULL)
+ return -EOVERFLOW;
+
memset(&buf, 0, sizeof(struct compat_statfs64));
buf.f_type = kbuf->f_type;
buf.f_bsize = kbuf->f_bsize;
diff --git a/include/uapi/linux/nvme_ioctl.h b/include/uapi/linux/nvme_ioctl.h
index 1c215ea1798e..e168dc59e9a0 100644
--- a/include/uapi/linux/nvme_ioctl.h
+++ b/include/uapi/linux/nvme_ioctl.h
@@ -45,6 +45,27 @@ struct nvme_passthru_cmd {
__u32 result;
};
+struct nvme_passthru_cmd64 {
+ __u8 opcode;
+ __u8 flags;
+ __u16 rsvd1;
+ __u32 nsid;
+ __u32 cdw2;
+ __u32 cdw3;
+ __u64 metadata;
+ __u64 addr;
+ __u32 metadata_len;
+ __u32 data_len;
+ __u32 cdw10;
+ __u32 cdw11;
+ __u32 cdw12;
+ __u32 cdw13;
+ __u32 cdw14;
+ __u32 cdw15;
+ __u32 timeout_ms;
+ __u64 result;
+};
+
#define nvme_admin_cmd nvme_passthru_cmd
#define NVME_IOCTL_ID _IO('N', 0x40)
@@ -54,5 +75,7 @@ struct nvme_passthru_cmd {
#define NVME_IOCTL_RESET _IO('N', 0x44)
#define NVME_IOCTL_SUBSYS_RESET _IO('N', 0x45)
#define NVME_IOCTL_RESCAN _IO('N', 0x46)
+#define NVME_IOCTL_ADMIN64_CMD _IOWR('N', 0x47, struct nvme_passthru_cmd64)
+#define NVME_IOCTL_IO64_CMD _IOWR('N', 0x48, struct nvme_passthru_cmd64)
#endif /* _UAPI_LINUX_NVME_IOCTL_H */
diff --git a/include/uapi/linux/pg.h b/include/uapi/linux/pg.h
index 364c350e85cd..62b6f69bd9fb 100644
--- a/include/uapi/linux/pg.h
+++ b/include/uapi/linux/pg.h
@@ -35,6 +35,9 @@
*/
+#ifndef _UAPI_LINUX_PG_H
+#define _UAPI_LINUX_PG_H
+
#define PG_MAGIC 'P'
#define PG_RESET 'Z'
#define PG_COMMAND 'C'
@@ -61,4 +64,4 @@ struct pg_read_hdr {
};
-/* end of pg.h */
+#endif /* _UAPI_LINUX_PG_H */
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
index a39bed2c784f..168479a7d61b 100644
--- a/kernel/sched/membarrier.c
+++ b/kernel/sched/membarrier.c
@@ -174,7 +174,6 @@ static int membarrier_private_expedited(int flags)
*/
if (cpu == raw_smp_processor_id())
continue;
- rcu_read_lock();
p = rcu_dereference(cpu_rq(cpu)->curr);
if (p && p->mm == mm)
__cpumask_set_cpu(cpu, tmpmask);
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
index c1f5bb590b5e..b5a65e212df2 100644
--- a/kernel/time/tick-broadcast-hrtimer.c
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -42,39 +42,39 @@ static int bc_shutdown(struct clock_event_device *evt)
*/
static int bc_set_next(ktime_t expires, struct clock_event_device *bc)
{
- int bc_moved;
/*
- * We try to cancel the timer first. If the callback is on
- * flight on some other cpu then we let it handle it. If we
- * were able to cancel the timer nothing can rearm it as we
- * own broadcast_lock.
+ * This is called either from enter/exit idle code or from the
+ * broadcast handler. In all cases tick_broadcast_lock is held.
*
- * However we can also be called from the event handler of
- * ce_broadcast_hrtimer itself when it expires. We cannot
- * restart the timer because we are in the callback, but we
- * can set the expiry time and let the callback return
- * HRTIMER_RESTART.
+ * hrtimer_cancel() cannot be called here neither from the
+ * broadcast handler nor from the enter/exit idle code. The idle
+ * code can run into the problem described in bc_shutdown() and the
+ * broadcast handler cannot wait for itself to complete for obvious
+ * reasons.
*
- * Since we are in the idle loop at this point and because
- * hrtimer_{start/cancel} functions call into tracing,
- * calls to these functions must be bound within RCU_NONIDLE.
+ * Each caller tries to arm the hrtimer on its own CPU, but if the
+ * hrtimer callbback function is currently running, then
+ * hrtimer_start() cannot move it and the timer stays on the CPU on
+ * which it is assigned at the moment.
+ *
+ * As this can be called from idle code, the hrtimer_start()
+ * invocation has to be wrapped with RCU_NONIDLE() as
+ * hrtimer_start() can call into tracing.
*/
- RCU_NONIDLE(
- {
- bc_moved = hrtimer_try_to_cancel(&bctimer) >= 0;
- if (bc_moved) {
- hrtimer_start(&bctimer, expires,
- HRTIMER_MODE_ABS_PINNED_HARD);
- }
- }
- );
-
- if (bc_moved) {
- /* Bind the "device" to the cpu */
- bc->bound_on = smp_processor_id();
- } else if (bc->bound_on == smp_processor_id()) {
- hrtimer_set_expires(&bctimer, expires);
- }
+ RCU_NONIDLE( {
+ hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED_HARD);
+ /*
+ * The core tick broadcast mode expects bc->bound_on to be set
+ * correctly to prevent a CPU which has the broadcast hrtimer
+ * armed from going deep idle.
+ *
+ * As tick_broadcast_lock is held, nothing can change the cpu
+ * base which was just established in hrtimer_start() above. So
+ * the below access is safe even without holding the hrtimer
+ * base lock.
+ */
+ bc->bound_on = bctimer.base->cpu_base->cpu;
+ } );
return 0;
}
@@ -100,10 +100,6 @@ static enum hrtimer_restart bc_handler(struct hrtimer *t)
{
ce_broadcast_hrtimer.event_handler(&ce_broadcast_hrtimer);
- if (clockevent_state_oneshot(&ce_broadcast_hrtimer))
- if (ce_broadcast_hrtimer.next_event != KTIME_MAX)
- return HRTIMER_RESTART;
-
return HRTIMER_NORESTART;
}
generated by cgit (git 2.34.1) at 2025-06-12 03:09:51 +0000