iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

nvme updates for Linux 5.14:

Browse Source 
- move the ACPI StorageD3 code to drivers/acpi/ and add quirks for
    certain AMD CPUs (Mario Limonciello)
  - zoned device support for nvmet (Chaitanya Kulkarni)
  - fix the rules for changing the serial number in nvmet (Noam Gottlieb)
  - various small fixes and cleanups (Dan Carpenter, JK Kim,
    Chaitanya Kulkarni, Hannes Reinecke, Wesley Sheng, Geert Uytterhoeven,
    Daniel Wagner)
 -----BEGIN PGP SIGNATURE-----
 
 iQI/BAABCgApFiEEgdbnc3r/njty3Iq9D55TZVIEUYMFAmDRiswLHGhjaEBsc3Qu
 ZGUACgkQD55TZVIEUYOz6g//aalapvqbZJpEUQJUVDRmZM9af6Js1reFYy6AW8D8
 h0rDi3nE7sq76ku6kJDleg5141j9CJJpIpCkxrC2Hc8V41mKEjYbXoHwy0qYTYFY
 iroVq9/pL+qDzXolWu8epWk2bYrxA+UjksvQ1UPMk4cz3fCmlSOe/fr3DrCLQ/Vy
 vE9YhisTGH9HoJzGITp/YG2seNJWql3tSh3dgbmPNZuMaW4+nu3VPjLbSKhJFT7Z
 WZzxopBQdkyyhO+0odPI1qqoYpAmXtKA5k+5Qbk6Cfa6kC8J4xHsmdbQ7MS5P/lc
 zphtHjU8q90vU6Js37Gy2n+IMbeut2feseYVou715jt8j2I14wvotI7w9wuEPUMQ
 BTW3CXmXK0XkS55i/8k1GCrkrZaNyF8Xps3zzC6ZYFlAJGYbur1XEyPFgjPNRmCZ
 G8B/dUG1qQCJd8C0TPm7TGjDKkiPtRu+ICx+rhD82EEIDBOWKm41O4MBLlWSwb3Y
 P9W1+t5LkDKhVPf3C4aZTRJakqAKfeBFCQkXAg98kwiuSFhkw3DelJaaCEUMB8KS
 8pGU9fpsp9nVOmrQjTAkLdVGQyzw7Jj5P7tZmAsjkzu+LT31AmW/4WjPzI2tWCia
 S22sPXRxYH6la2pHFiTH4ksPIsSGEKGhNkYd+cfHpstL9T4c/0cHzQVKoRc9mitR
 Tg0=
 =Gfad
 -----END PGP SIGNATURE-----

Merge tag 'nvme-5.14-2021-06-22' of git://git.infradead.org/nvme into for-5.14/drivers

Pull NVMe updates from Christoph

"nvme updates for Linux 5.14:

 - move the ACPI StorageD3 code to drivers/acpi/ and add quirks for
   certain AMD CPUs (Mario Limonciello)
 - zoned device support for nvmet (Chaitanya Kulkarni)
 - fix the rules for changing the serial number in nvmet (Noam Gottlieb)
 - various small fixes and cleanups (Dan Carpenter, JK Kim,
   Chaitanya Kulkarni, Hannes Reinecke, Wesley Sheng, Geert Uytterhoeven,
   Daniel Wagner)"

* tag 'nvme-5.14-2021-06-22' of git://git.infradead.org/nvme: (38 commits)
  nvmet: use NVMET_MAX_NAMESPACES to set nn value
  nvme.h: add missing nvme_lba_range_type endianness annotations
  nvme: remove zeroout memset call for struct
  nvme-pci: remove zeroout memset call for struct
  nvmet: remove zeroout memset call for struct
  nvmet: add ZBD over ZNS backend support
  nvmet: add Command Set Identifier support
  nvmet: add nvmet_req_bio put helper for backends
  nvmet: add req cns error complete helper
  block: export blk_next_bio()
  nvmet: remove local variable
  nvmet: use nvme status value directly
  nvmet: use u32 type for the local variable nsid
  nvmet: use u32 for nvmet_subsys max_nsid
  nvmet: use req->cmd directly in file-ns fast path
  nvmet: use req->cmd directly in bdev-ns fast path
  nvmet: make ver stable once connection established
  nvmet: allow mn change if subsys not discovered
  nvmet: make sn stable once connection was established
  nvmet: change sn size and check validity
  ...
This commit is contained in:
Jens Axboe 2021-06-24 09:39:02 -06:00
commit 5ed9b35702
28 changed files with 1073 additions and 228 deletions

1
block/blk-lib.c

@ -21,6 +21,7 @@ struct bio *blk_next_bio(struct bio *bio, unsigned int nr_pages, gfp_t gfp)
return new;
}
EXPORT_SYMBOL_GPL(blk_next_bio);
int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp_mask, int flags,

32
drivers/acpi/device_pm.c

@ -1340,4 +1340,36 @@ int acpi_dev_pm_attach(struct device *dev, bool power_on)
return 1;
}
EXPORT_SYMBOL_GPL(acpi_dev_pm_attach);
/**
* acpi_storage_d3 - Check if D3 should be used in the suspend path
* @dev: Device to check
*
* Return %true if the platform firmware wants @dev to be programmed
* into D3hot or D3cold (if supported) in the suspend path, or %false
* when there is no specific preference. On some platforms, if this
* hint is ignored, @dev may remain unresponsive after suspending the
* platform as a whole.
*
* Although the property has storage in the name it actually is
* applied to the PCIe slot and plugging in a non-storage device the
* same platform restrictions will likely apply.
*/
bool acpi_storage_d3(struct device *dev)
{
struct acpi_device *adev = ACPI_COMPANION(dev);
u8 val;
if (force_storage_d3())
return true;
if (!adev)
return false;
if (fwnode_property_read_u8(acpi_fwnode_handle(adev), "StorageD3Enable",
&val))
return false;
return val == 1;
}
EXPORT_SYMBOL_GPL(acpi_storage_d3);
#endif /* CONFIG_PM */

9
drivers/acpi/internal.h

@ -236,6 +236,15 @@ static inline int suspend_nvs_save(void) { return 0; }
static inline void suspend_nvs_restore(void) {}
#endif
#ifdef CONFIG_X86
bool force_storage_d3(void);
#else
static inline bool force_storage_d3(void)
{
return false;
}
#endif
/*--------------------------------------------------------------------------
Device properties
-------------------------------------------------------------------------- */

25
drivers/acpi/x86/utils.c

@ -135,3 +135,28 @@ bool acpi_device_always_present(struct acpi_device *adev)
return ret;
}
/*
* AMD systems from Renoir and Lucienne *require* that the NVME controller
* is put into D3 over a Modern Standby / suspend-to-idle cycle.
*
* This is "typically" accomplished using the `StorageD3Enable`
* property in the _DSD that is checked via the `acpi_storage_d3` function
* but this property was introduced after many of these systems launched
* and most OEM systems don't have it in their BIOS.
*
* The Microsoft documentation for StorageD3Enable mentioned that Windows has
* a hardcoded allowlist for D3 support, which was used for these platforms.
*
* This allows quirking on Linux in a similar fashion.
*/
static const struct x86_cpu_id storage_d3_cpu_ids[] = {
X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 96, NULL), /* Renoir */
X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 104, NULL), /* Lucienne */
{}
};
bool force_storage_d3(void)
{
return x86_match_cpu(storage_d3_cpu_ids);
}

2
drivers/nvme/host/Kconfig

@ -21,7 +21,7 @@ config NVME_MULTIPATH
help
This option enables support for multipath access to NVMe
subsystems. If this option is enabled only a single
/dev/nvmeXnY device will show up for each NVMe namespaces,
/dev/nvmeXnY device will show up for each NVMe namespace,
even if it is accessible through multiple controllers.
config NVME_HWMON

19
drivers/nvme/host/core.c

@ -721,9 +721,7 @@ EXPORT_SYMBOL_GPL(__nvme_check_ready);
static int nvme_toggle_streams(struct nvme_ctrl *ctrl, bool enable)
{
struct nvme_command c;
memset(&c, 0, sizeof(c));
struct nvme_command c = { };
c.directive.opcode = nvme_admin_directive_send;
c.directive.nsid = cpu_to_le32(NVME_NSID_ALL);
@ -748,9 +746,8 @@ static int nvme_enable_streams(struct nvme_ctrl *ctrl)
static int nvme_get_stream_params(struct nvme_ctrl *ctrl,
struct streams_directive_params *s, u32 nsid)
{
struct nvme_command c;
struct nvme_command c = { };
memset(&c, 0, sizeof(c));
memset(s, 0, sizeof(*s));
c.directive.opcode = nvme_admin_directive_recv;
@ -1460,10 +1457,9 @@ static int nvme_features(struct nvme_ctrl *dev, u8 op, unsigned int fid,
unsigned int dword11, void *buffer, size_t buflen, u32 *result)
{
union nvme_result res = { 0 };
struct nvme_command c;
struct nvme_command c = { };
int ret;
memset(&c, 0, sizeof(c));
c.features.opcode = op;
c.features.fid = cpu_to_le32(fid);
c.features.dword11 = cpu_to_le32(dword11);
@ -1591,9 +1587,8 @@ int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo)
static void nvme_init_integrity(struct gendisk *disk, u16 ms, u8 pi_type,
u32 max_integrity_segments)
{
struct blk_integrity integrity;
struct blk_integrity integrity = { };
memset(&integrity, 0, sizeof(integrity));
switch (pi_type) {
case NVME_NS_DPS_PI_TYPE3:
integrity.profile = &t10_pi_type3_crc;
@ -1964,13 +1959,12 @@ static int nvme_send_ns_pr_command(struct nvme_ns *ns, struct nvme_command *c,
static int nvme_pr_command(struct block_device *bdev, u32 cdw10,
u64 key, u64 sa_key, u8 op)
{
struct nvme_command c;
struct nvme_command c = { };
u8 data[16] = { 0, };
put_unaligned_le64(key, &data[0]);
put_unaligned_le64(sa_key, &data[8]);
memset(&c, 0, sizeof(c));
c.common.opcode = op;
c.common.cdw10 = cpu_to_le32(cdw10);
@ -2042,9 +2036,8 @@ int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len,
bool send)
{
struct nvme_ctrl *ctrl = data;
struct nvme_command cmd;
struct nvme_command cmd = { };
memset(&cmd, 0, sizeof(cmd));
if (send)
cmd.common.opcode = nvme_admin_security_send;
else

12
drivers/nvme/host/fabrics.c

@ -190,11 +190,10 @@ EXPORT_SYMBOL_GPL(nvmf_reg_read32);
*/
int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val)
{
struct nvme_command cmd;
struct nvme_command cmd = { };
union nvme_result res;
int ret;
memset(&cmd, 0, sizeof(cmd));
cmd.prop_get.opcode = nvme_fabrics_command;
cmd.prop_get.fctype = nvme_fabrics_type_property_get;
cmd.prop_get.attrib = 1;
@ -236,10 +235,9 @@ EXPORT_SYMBOL_GPL(nvmf_reg_read64);
*/
int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val)
{
struct nvme_command cmd;
struct nvme_command cmd = { };
int ret;
memset(&cmd, 0, sizeof(cmd));
cmd.prop_set.opcode = nvme_fabrics_command;
cmd.prop_set.fctype = nvme_fabrics_type_property_set;
cmd.prop_set.attrib = 0;
@ -364,12 +362,11 @@ static void nvmf_log_connect_error(struct nvme_ctrl *ctrl,
*/
int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl)
{
struct nvme_command cmd;
struct nvme_command cmd = { };
union nvme_result res;
struct nvmf_connect_data *data;
int ret;
memset(&cmd, 0, sizeof(cmd));
cmd.connect.opcode = nvme_fabrics_command;
cmd.connect.fctype = nvme_fabrics_type_connect;
cmd.connect.qid = 0;
@ -432,12 +429,11 @@ EXPORT_SYMBOL_GPL(nvmf_connect_admin_queue);
*/
int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid, bool poll)
{
struct nvme_command cmd;
struct nvme_command cmd = { };
struct nvmf_connect_data *data;
union nvme_result res;
int ret;
memset(&cmd, 0, sizeof(cmd));
cmd.connect.opcode = nvme_fabrics_command;
cmd.connect.fctype = nvme_fabrics_type_connect;
cmd.connect.qid = cpu_to_le16(qid);

2
drivers/nvme/host/fc.c

@ -3111,7 +3111,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
}
/* FC-NVME supports normal SGL Data Block Descriptors */
if (!(ctrl->ctrl.sgls & ((1 << 0) | (1 << 1)))) {
if (!nvme_ctrl_sgl_supported(&ctrl->ctrl)) {
dev_err(ctrl->ctrl.device,
"Mandatory sgls are not supported!\n");
goto out_disconnect_admin_queue;

26
drivers/nvme/host/ioctl.c

@ -177,6 +177,20 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
metadata, meta_len, lower_32_bits(io.slba), NULL, 0);
}
static bool nvme_validate_passthru_nsid(struct nvme_ctrl *ctrl,
struct nvme_ns *ns, __u32 nsid)
{
if (ns && nsid != ns->head->ns_id) {
dev_err(ctrl->device,
"%s: nsid (%u) in cmd does not match nsid (%u)"
"of namespace\n",
current->comm, nsid, ns->head->ns_id);
return false;
}
return true;
}
static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
struct nvme_passthru_cmd __user *ucmd)
{
@ -192,12 +206,8 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
return -EFAULT;
if (cmd.flags)
return -EINVAL;
if (ns && cmd.nsid != ns->head->ns_id) {
dev_err(ctrl->device,
"%s: nsid (%u) in cmd does not match nsid (%u) of namespace\n",
current->comm, cmd.nsid, ns->head->ns_id);
if (!nvme_validate_passthru_nsid(ctrl, ns, cmd.nsid))
return -EINVAL;
}
memset(&c, 0, sizeof(c));
c.common.opcode = cmd.opcode;
@ -242,12 +252,8 @@ static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
return -EFAULT;
if (cmd.flags)
return -EINVAL;
if (ns && cmd.nsid != ns->head->ns_id) {
dev_err(ctrl->device,
"%s: nsid (%u) in cmd does not match nsid (%u) of namespace\n",
current->comm, cmd.nsid, ns->head->ns_id);
if (!nvme_validate_passthru_nsid(ctrl, ns, cmd.nsid))
return -EINVAL;
}
memset(&c, 0, sizeof(c));
c.common.opcode = cmd.opcode;

12
drivers/nvme/host/multipath.c

@ -435,11 +435,6 @@ static void nvme_requeue_work(struct work_struct *work)
next = bio->bi_next;
bio->bi_next = NULL;
/*
* Reset disk to the mpath node and resubmit to select a new
* path.
*/
bio_set_dev(bio, head->disk->part0);
submit_bio_noacct(bio);
}
}
@ -818,6 +813,13 @@ int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
!(ctrl->subsys->cmic & NVME_CTRL_CMIC_ANA))
return 0;
if (!ctrl->max_namespaces ||
ctrl->max_namespaces > le32_to_cpu(id->nn)) {
dev_err(ctrl->device,
"Invalid MNAN value %u\n", ctrl->max_namespaces);
return -EINVAL;
}
ctrl->anacap = id->anacap;
ctrl->anatt = id->anatt;
ctrl->nanagrpid = le32_to_cpu(id->nanagrpid);

5
drivers/nvme/host/nvme.h

@ -869,6 +869,11 @@ static inline void nvme_hwmon_exit(struct nvme_ctrl *ctrl)
}
#endif
static inline bool nvme_ctrl_sgl_supported(struct nvme_ctrl *ctrl)
{
return ctrl->sgls & ((1 << 0) | (1 << 1));
}
u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
u8 opcode);
void nvme_execute_passthru_rq(struct request *rq);

60
drivers/nvme/host/pci.c

@ -307,13 +307,12 @@ static void nvme_dbbuf_free(struct nvme_queue *nvmeq)
static void nvme_dbbuf_set(struct nvme_dev *dev)
{
struct nvme_command c;
struct nvme_command c = { };
unsigned int i;
if (!dev->dbbuf_dbs)
return;
memset(&c, 0, sizeof(c));
c.dbbuf.opcode = nvme_admin_dbbuf;
c.dbbuf.prp1 = cpu_to_le64(dev->dbbuf_dbs_dma_addr);
c.dbbuf.prp2 = cpu_to_le64(dev->dbbuf_eis_dma_addr);
@ -536,7 +535,7 @@ static inline bool nvme_pci_use_sgls(struct nvme_dev *dev, struct request *req)
avg_seg_size = DIV_ROUND_UP(blk_rq_payload_bytes(req), nseg);
if (!(dev->ctrl.sgls & ((1 << 0) | (1 << 1))))
if (!nvme_ctrl_sgl_supported(&dev->ctrl))
return false;
if (!iod->nvmeq->qid)
return false;
@ -559,7 +558,6 @@ static void nvme_free_prps(struct nvme_dev *dev, struct request *req)
dma_pool_free(dev->prp_page_pool, prp_list, dma_addr);
dma_addr = next_dma_addr;
}
}
static void nvme_free_sgls(struct nvme_dev *dev, struct request *req)
@ -576,7 +574,6 @@ static void nvme_free_sgls(struct nvme_dev *dev, struct request *req)
dma_pool_free(dev->prp_page_pool, sg_list, dma_addr);
dma_addr = next_dma_addr;
}
}
static void nvme_unmap_sg(struct nvme_dev *dev, struct request *req)
@ -855,7 +852,7 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
&cmnd->rw, &bv);
if (iod->nvmeq->qid && sgl_threshold &&
dev->ctrl.sgls & ((1 << 0) | (1 << 1)))
nvme_ctrl_sgl_supported(&dev->ctrl))
return nvme_setup_sgl_simple(dev, req,
&cmnd->rw, &bv);
}
@ -1032,7 +1029,7 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
static inline void nvme_update_cq_head(struct nvme_queue *nvmeq)
{
u16 tmp = nvmeq->cq_head + 1;
u32 tmp = nvmeq->cq_head + 1;
if (tmp == nvmeq->q_depth) {
nvmeq->cq_head = 0;
@ -1114,9 +1111,8 @@ static void nvme_pci_submit_async_event(struct nvme_ctrl *ctrl)
{
struct nvme_dev *dev = to_nvme_dev(ctrl);
struct nvme_queue *nvmeq = &dev->queues[0];
struct nvme_command c;
struct nvme_command c = { };
memset(&c, 0, sizeof(c));
c.common.opcode = nvme_admin_async_event;
c.common.command_id = NVME_AQ_BLK_MQ_DEPTH;
nvme_submit_cmd(nvmeq, &c, true);
@ -1124,9 +1120,8 @@ static void nvme_pci_submit_async_event(struct nvme_ctrl *ctrl)
static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16 id)
{
struct nvme_command c;
struct nvme_command c = { };
memset(&c, 0, sizeof(c));
c.delete_queue.opcode = opcode;
c.delete_queue.qid = cpu_to_le16(id);
@ -1136,7 +1131,7 @@ static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16 id)
static int adapter_alloc_cq(struct nvme_dev *dev, u16 qid,
struct nvme_queue *nvmeq, s16 vector)
{
struct nvme_command c;
struct nvme_command c = { };
int flags = NVME_QUEUE_PHYS_CONTIG;
if (!test_bit(NVMEQ_POLLED, &nvmeq->flags))
@ -1146,7 +1141,6 @@ static int adapter_alloc_cq(struct nvme_dev *dev, u16 qid,
* Note: we (ab)use the fact that the prp fields survive if no data
* is attached to the request.
*/
memset(&c, 0, sizeof(c));
c.create_cq.opcode = nvme_admin_create_cq;
c.create_cq.prp1 = cpu_to_le64(nvmeq->cq_dma_addr);
c.create_cq.cqid = cpu_to_le16(qid);
@ -1161,7 +1155,7 @@ static int adapter_alloc_sq(struct nvme_dev *dev, u16 qid,
struct nvme_queue *nvmeq)
{
struct nvme_ctrl *ctrl = &dev->ctrl;
struct nvme_command c;
struct nvme_command c = { };
int flags = NVME_QUEUE_PHYS_CONTIG;
/*
@ -1176,7 +1170,6 @@ static int adapter_alloc_sq(struct nvme_dev *dev, u16 qid,
* Note: we (ab)use the fact that the prp fields survive if no data
* is attached to the request.
*/
memset(&c, 0, sizeof(c));
c.create_sq.opcode = nvme_admin_create_sq;
c.create_sq.prp1 = cpu_to_le64(nvmeq->sq_dma_addr);
c.create_sq.sqid = cpu_to_le16(qid);
@ -1257,7 +1250,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
struct nvme_queue *nvmeq = iod->nvmeq;
struct nvme_dev *dev = nvmeq->dev;
struct request *abort_req;
struct nvme_command cmd;
struct nvme_command cmd = { };
u32 csts = readl(dev->bar + NVME_REG_CSTS);
/* If PCI error recovery process is happening, we cannot reset or
@ -1337,7 +1330,6 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
}
iod->aborted = 1;
memset(&cmd, 0, sizeof(cmd));
cmd.abort.opcode = nvme_admin_abort_cmd;
cmd.abort.cid = req->tag;
cmd.abort.sqid = cpu_to_le16(nvmeq->qid);
@ -1888,10 +1880,9 @@ static int nvme_set_host_mem(struct nvme_dev *dev, u32 bits)
{
u32 host_mem_size = dev->host_mem_size >> NVME_CTRL_PAGE_SHIFT;
u64 dma_addr = dev->host_mem_descs_dma;
struct nvme_command c;
struct nvme_command c = { };
int ret;
memset(&c, 0, sizeof(c));
c.features.opcode = nvme_admin_set_features;
c.features.fid = cpu_to_le32(NVME_FEAT_HOST_MEM_BUF);
c.features.dword11 = cpu_to_le32(bits);
@ -2265,9 +2256,8 @@ static int nvme_delete_queue(struct nvme_queue *nvmeq, u8 opcode)
{
struct request_queue *q = nvmeq->dev->ctrl.admin_q;
struct request *req;
struct nvme_command cmd;
struct nvme_command cmd = { };
memset(&cmd, 0, sizeof(cmd));
cmd.delete_queue.opcode = opcode;
cmd.delete_queue.qid = cpu_to_le16(nvmeq->qid);
@ -2828,32 +2818,6 @@ static unsigned long check_vendor_combination_bug(struct pci_dev *pdev)
return 0;
}
#ifdef CONFIG_ACPI
static bool nvme_acpi_storage_d3(struct pci_dev *dev)
{
struct acpi_device *adev = ACPI_COMPANION(&dev->dev);
u8 val;
/*
* Look for _DSD property specifying that the storage device on the port
* must use D3 to support deep platform power savings during
* suspend-to-idle.
*/
if (!adev)
return false;
if (fwnode_property_read_u8(acpi_fwnode_handle(adev), "StorageD3Enable",
&val))
return false;
return val == 1;
}
#else
static inline bool nvme_acpi_storage_d3(struct pci_dev *dev)
{
return false;
}
#endif /* CONFIG_ACPI */
static void nvme_async_probe(void *data, async_cookie_t cookie)
{
struct nvme_dev *dev = data;
@ -2903,7 +2867,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
quirks |= check_vendor_combination_bug(pdev);
if (!noacpi && nvme_acpi_storage_d3(pdev)) {
if (!noacpi && acpi_storage_d3(&pdev->dev)) {
/*
* Some systems use a bios work around to ask for D3 on
* platforms that support kernel managed suspend.

4
drivers/nvme/host/tcp.c

@ -1988,11 +1988,13 @@ static int nvme_tcp_setup_ctrl(struct nvme_ctrl *ctrl, bool new)
return ret;
if (ctrl->icdoff) {
ret = -EOPNOTSUPP;
dev_err(ctrl->device, "icdoff is not supported!\n");
goto destroy_admin;
}
if (!(ctrl->sgls & ((1 << 0) | (1 << 1)))) {
if (!nvme_ctrl_sgl_supported(ctrl)) {
ret = -EOPNOTSUPP;
dev_err(ctrl->device, "Mandatory sgls are not supported!\n");
goto destroy_admin;
}

1
drivers/nvme/target/Makefile

@ -12,6 +12,7 @@ obj-$(CONFIG_NVME_TARGET_TCP) += nvmet-tcp.o
nvmet-y += core.o configfs.o admin-cmd.o fabrics-cmd.o \
discovery.o io-cmd-file.o io-cmd-bdev.o
nvmet-$(CONFIG_NVME_TARGET_PASSTHRU) += passthru.o
nvmet-$(CONFIG_BLK_DEV_ZONED) += zns.o
nvme-loop-y += loop.o
nvmet-rdma-y += rdma.o
nvmet-fc-y += fc.o

155
drivers/nvme/target/admin-cmd.c

@ -162,15 +162,8 @@ out:
nvmet_req_complete(req, status);
}
static void nvmet_execute_get_log_cmd_effects_ns(struct nvmet_req *req)
static void nvmet_get_cmd_effects_nvm(struct nvme_effects_log *log)
{
u16 status = NVME_SC_INTERNAL;
struct nvme_effects_log *log;
log = kzalloc(sizeof(*log), GFP_KERNEL);
if (!log)
goto out;
log->acs[nvme_admin_get_log_page] = cpu_to_le32(1 << 0);
log->acs[nvme_admin_identify] = cpu_to_le32(1 << 0);
log->acs[nvme_admin_abort_cmd] = cpu_to_le32(1 << 0);
@ -184,9 +177,45 @@ static void nvmet_execute_get_log_cmd_effects_ns(struct nvmet_req *req)
log->iocs[nvme_cmd_flush] = cpu_to_le32(1 << 0);
log->iocs[nvme_cmd_dsm] = cpu_to_le32(1 << 0);
log->iocs[nvme_cmd_write_zeroes] = cpu_to_le32(1 << 0);
}
static void nvmet_get_cmd_effects_zns(struct nvme_effects_log *log)
{
log->iocs[nvme_cmd_zone_append] = cpu_to_le32(1 << 0);
log->iocs[nvme_cmd_zone_mgmt_send] = cpu_to_le32(1 << 0);
log->iocs[nvme_cmd_zone_mgmt_recv] = cpu_to_le32(1 << 0);
}
static void nvmet_execute_get_log_cmd_effects_ns(struct nvmet_req *req)
{
struct nvme_effects_log *log;
u16 status = NVME_SC_SUCCESS;
log = kzalloc(sizeof(*log), GFP_KERNEL);
if (!log) {
status = NVME_SC_INTERNAL;
goto out;
}
switch (req->cmd->get_log_page.csi) {
case NVME_CSI_NVM:
nvmet_get_cmd_effects_nvm(log);
break;
case NVME_CSI_ZNS:
if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED)) {
status = NVME_SC_INVALID_IO_CMD_SET;
goto free;
}
nvmet_get_cmd_effects_nvm(log);
nvmet_get_cmd_effects_zns(log);
break;
default:
status = NVME_SC_INVALID_LOG_PAGE;
goto free;
}
status = nvmet_copy_to_sgl(req, 0, log, sizeof(*log));
free:
kfree(log);
out:
nvmet_req_complete(req, status);
@ -313,22 +342,6 @@ static void nvmet_execute_get_log_page(struct nvmet_req *req)
nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR);
}
static u16 nvmet_set_model_number(struct nvmet_subsys *subsys)
{
u16 status = 0;
mutex_lock(&subsys->lock);
if (!subsys->model_number) {
subsys->model_number =
kstrdup(NVMET_DEFAULT_CTRL_MODEL, GFP_KERNEL);
if (!subsys->model_number)
status = NVME_SC_INTERNAL;
}
mutex_unlock(&subsys->lock);
return status;
}
static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
{
struct nvmet_ctrl *ctrl = req->sq->ctrl;
@ -337,14 +350,10 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
u32 cmd_capsule_size;
u16 status = 0;
/*
* If there is no model number yet, set it now. It will then remain
* stable for the life time of the subsystem.
*/
if (!subsys->model_number) {
status = nvmet_set_model_number(subsys);
if (status)
goto out;
if (!subsys->subsys_discovered) {
mutex_lock(&subsys->lock);
subsys->subsys_discovered = true;
mutex_unlock(&subsys->lock);
}
id = kzalloc(sizeof(*id), GFP_KERNEL);
@ -357,9 +366,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
id->vid = 0;
id->ssvid = 0;
memset(id->sn, ' ', sizeof(id->sn));
bin2hex(id->sn, &ctrl->subsys->serial,
min(sizeof(ctrl->subsys->serial), sizeof(id->sn) / 2));
memcpy(id->sn, ctrl->subsys->serial, NVMET_SN_MAX_SIZE);
memcpy_and_pad(id->mn, sizeof(id->mn), subsys->model_number,
strlen(subsys->model_number), ' ');
memcpy_and_pad(id->fr, sizeof(id->fr),
@ -415,7 +422,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
/* no enforcement soft-limit for maxcmd - pick arbitrary high value */
id->maxcmd = cpu_to_le16(NVMET_MAX_CMD);
id->nn = cpu_to_le32(ctrl->subsys->max_nsid);
id->nn = cpu_to_le32(NVMET_MAX_NAMESPACES);
id->mnan = cpu_to_le32(NVMET_MAX_NAMESPACES);
id->oncs = cpu_to_le16(NVME_CTRL_ONCS_DSM |
NVME_CTRL_ONCS_WRITE_ZEROES);
@ -635,6 +642,12 @@ static void nvmet_execute_identify_desclist(struct nvmet_req *req)
goto out;
}
status = nvmet_copy_ns_identifier(req, NVME_NIDT_CSI,
NVME_NIDT_CSI_LEN,
&req->ns->csi, &off);
if (status)
goto out;
if (sg_zero_buffer(req->sg, req->sg_cnt, NVME_IDENTIFY_DATA_SIZE - off,
off) != NVME_IDENTIFY_DATA_SIZE - off)
status = NVME_SC_INTERNAL | NVME_SC_DNR;
@ -643,6 +656,23 @@ out:
nvmet_req_complete(req, status);
}
static bool nvmet_handle_identify_desclist(struct nvmet_req *req)
{
switch (req->cmd->identify.csi) {
case NVME_CSI_NVM:
nvmet_execute_identify_desclist(req);
return true;
case NVME_CSI_ZNS:
if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) {
nvmet_execute_identify_desclist(req);
return true;
}
return false;
default:
return false;
}
}
static void nvmet_execute_identify(struct nvmet_req *req)
{
if (!nvmet_check_transfer_len(req, NVME_IDENTIFY_DATA_SIZE))
@ -650,19 +680,54 @@ static void nvmet_execute_identify(struct nvmet_req *req)
switch (req->cmd->identify.cns) {
case NVME_ID_CNS_NS:
return nvmet_execute_identify_ns(req);
switch (req->cmd->identify.csi) {
case NVME_CSI_NVM:
return nvmet_execute_identify_ns(req);
default:
break;
}
break;
case NVME_ID_CNS_CS_NS:
if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) {
switch (req->cmd->identify.csi) {
case NVME_CSI_ZNS:
return nvmet_execute_identify_cns_cs_ns(req);
default:
break;
}
}
break;
case NVME_ID_CNS_CTRL:
return nvmet_execute_identify_ctrl(req);
switch (req->cmd->identify.csi) {
case NVME_CSI_NVM:
return nvmet_execute_identify_ctrl(req);
}
break;
case NVME_ID_CNS_CS_CTRL:
if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) {
switch (req->cmd->identify.csi) {
case NVME_CSI_ZNS:
return nvmet_execute_identify_cns_cs_ctrl(req);
default:
break;
}
}
break;
case NVME_ID_CNS_NS_ACTIVE_LIST:
return nvmet_execute_identify_nslist(req);
switch (req->cmd->identify.csi) {
case NVME_CSI_NVM:
return nvmet_execute_identify_nslist(req);
default:
break;
}
break;
case NVME_ID_CNS_NS_DESC_LIST:
return nvmet_execute_identify_desclist(req);
if (nvmet_handle_identify_desclist(req) == true)
return;
break;
}
pr_debug("unhandled identify cns %d on qid %d\n",
req->cmd->identify.cns, req->sq->qid);
req->error_loc = offsetof(struct nvme_identify, cns);
nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR);
nvmet_req_cns_error_complete(req);
}
/*

102
drivers/nvme/target/configfs.c

@ -1007,13 +1007,26 @@ static ssize_t nvmet_subsys_attr_version_show(struct config_item *item,
NVME_MINOR(subsys->ver));
}
static ssize_t nvmet_subsys_attr_version_store(struct config_item *item,
const char *page, size_t count)
static ssize_t
nvmet_subsys_attr_version_store_locked(struct nvmet_subsys *subsys,
const char *page, size_t count)
{
struct nvmet_subsys *subsys = to_subsys(item);
int major, minor, tertiary = 0;
int ret;
if (subsys->subsys_discovered) {
if (NVME_TERTIARY(subsys->ver))
pr_err("Can't set version number. %llu.%llu.%llu is already assigned\n",
NVME_MAJOR(subsys->ver),
NVME_MINOR(subsys->ver),
NVME_TERTIARY(subsys->ver));
else
pr_err("Can't set version number. %llu.%llu is already assigned\n",
NVME_MAJOR(subsys->ver),
NVME_MINOR(subsys->ver));
return -EINVAL;
}
/* passthru subsystems use the underlying controller's version */
if (nvmet_passthru_ctrl(subsys))
return -EINVAL;
@ -1022,35 +1035,84 @@ static ssize_t nvmet_subsys_attr_version_store(struct config_item *item,
if (ret != 2 && ret != 3)
return -EINVAL;
down_write(&nvmet_config_sem);
subsys->ver = NVME_VS(major, minor, tertiary);
up_write(&nvmet_config_sem);
return count;
}
static ssize_t nvmet_subsys_attr_version_store(struct config_item *item,
const char *page, size_t count)
{
struct nvmet_subsys *subsys = to_subsys(item);
ssize_t ret;
down_write(&nvmet_config_sem);
mutex_lock(&subsys->lock);
ret = nvmet_subsys_attr_version_store_locked(subsys, page, count);
mutex_unlock(&subsys->lock);
up_write(&nvmet_config_sem);
return ret;
}
CONFIGFS_ATTR(nvmet_subsys_, attr_version);
/* See Section 1.5 of NVMe 1.4 */
static bool nvmet_is_ascii(const char c)
{
return c >= 0x20 && c <= 0x7e;
}
static ssize_t nvmet_subsys_attr_serial_show(struct config_item *item,
char *page)
{
struct nvmet_subsys *subsys = to_subsys(item);
return snprintf(page, PAGE_SIZE, "%llx\n", subsys->serial);
return snprintf(page, PAGE_SIZE, "%s\n", subsys->serial);
}
static ssize_t
nvmet_subsys_attr_serial_store_locked(struct nvmet_subsys *subsys,
const char *page, size_t count)
{
int pos, len = strcspn(page, "\n");
if (subsys->subsys_discovered) {
pr_err("Can't set serial number. %s is already assigned\n",
subsys->serial);
return -EINVAL;
}
if (!len || len > NVMET_SN_MAX_SIZE) {
pr_err("Serial Number can not be empty or exceed %d Bytes\n",
NVMET_SN_MAX_SIZE);
return -EINVAL;
}
for (pos = 0; pos < len; pos++) {
if (!nvmet_is_ascii(page[pos])) {
pr_err("Serial Number must contain only ASCII strings\n");
return -EINVAL;
}
}
memcpy_and_pad(subsys->serial, NVMET_SN_MAX_SIZE, page, len, ' ');
return count;
}
static ssize_t nvmet_subsys_attr_serial_store(struct config_item *item,
const char *page, size_t count)
{
u64 serial;
if (sscanf(page, "%llx\n", &serial) != 1)
return -EINVAL;
struct nvmet_subsys *subsys = to_subsys(item);
ssize_t ret;
down_write(&nvmet_config_sem);
to_subsys(item)->serial = serial;
mutex_lock(&subsys->lock);
ret = nvmet_subsys_attr_serial_store_locked(subsys, page, count);
mutex_unlock(&subsys->lock);
up_write(&nvmet_config_sem);
return count;
return ret;
}
CONFIGFS_ATTR(nvmet_subsys_, attr_serial);
@ -1118,20 +1180,8 @@ static ssize_t nvmet_subsys_attr_model_show(struct config_item *item,
char *page)
{
struct nvmet_subsys *subsys = to_subsys(item);
int ret;
mutex_lock(&subsys->lock);
ret = snprintf(page, PAGE_SIZE, "%s\n", subsys->model_number ?
subsys->model_number : NVMET_DEFAULT_CTRL_MODEL);
mutex_unlock(&subsys->lock);
return ret;
}
/* See Section 1.5 of NVMe 1.4 */
static bool nvmet_is_ascii(const char c)
{
return c >= 0x20 && c <= 0x7e;
return snprintf(page, PAGE_SIZE, "%s\n", subsys->model_number);
}
static ssize_t nvmet_subsys_attr_model_store_locked(struct nvmet_subsys *subsys,
@ -1139,7 +1189,7 @@ static ssize_t nvmet_subsys_attr_model_store_locked(struct nvmet_subsys *subsys,
{
int pos = 0, len;
if (subsys->model_number) {
if (subsys->subsys_discovered) {
pr_err("Can't set model number. %s is already assigned\n",
subsys->model_number);
return -EINVAL;

98
drivers/nvme/target/core.c

@ -16,6 +16,7 @@
#include "nvmet.h"
struct workqueue_struct *buffered_io_wq;
struct workqueue_struct *zbd_wq;
static const struct nvmet_fabrics_ops *nvmet_transports[NVMF_TRTYPE_MAX];
static DEFINE_IDA(cntlid_ida);
@ -43,43 +44,34 @@ DECLARE_RWSEM(nvmet_ana_sem);
inline u16 errno_to_nvme_status(struct nvmet_req *req, int errno)
{
u16 status;
switch (errno) {
case 0:
status = NVME_SC_SUCCESS;
break;
return NVME_SC_SUCCESS;
case -ENOSPC:
req->error_loc = offsetof(struct nvme_rw_command, length);
status = NVME_SC_CAP_EXCEEDED | NVME_SC_DNR;
break;
return NVME_SC_CAP_EXCEEDED | NVME_SC_DNR;
case -EREMOTEIO:
req->error_loc = offsetof(struct nvme_rw_command, slba);
status = NVME_SC_LBA_RANGE | NVME_SC_DNR;
break;
return NVME_SC_LBA_RANGE | NVME_SC_DNR;
case -EOPNOTSUPP:
req->error_loc = offsetof(struct nvme_common_command, opcode);
switch (req->cmd->common.opcode) {
case nvme_cmd_dsm:
case nvme_cmd_write_zeroes:
status = NVME_SC_ONCS_NOT_SUPPORTED | NVME_SC_DNR;
break;
return NVME_SC_ONCS_NOT_SUPPORTED | NVME_SC_DNR;
default:
status = NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
}
break;
case -ENODATA:
req->error_loc = offsetof(struct nvme_rw_command, nsid);
status = NVME_SC_ACCESS_DENIED;
break;
return NVME_SC_ACCESS_DENIED;
case -EIO:
fallthrough;
default:
req->error_loc = offsetof(struct nvme_common_command, opcode);
status = NVME_SC_INTERNAL | NVME_SC_DNR;
return NVME_SC_INTERNAL | NVME_SC_DNR;
}
return status;
}
u16 nvmet_report_invalid_opcode(struct nvmet_req *req)
@ -122,11 +114,11 @@ u16 nvmet_zero_sgl(struct nvmet_req *req, off_t off, size_t len)
return 0;
}
static unsigned int nvmet_max_nsid(struct nvmet_subsys *subsys)
static u32 nvmet_max_nsid(struct nvmet_subsys *subsys)
{
unsigned long nsid = 0;
struct nvmet_ns *cur;
unsigned long idx;
u32 nsid = 0;
xa_for_each(&subsys->namespaces, idx, cur)
nsid = cur->nsid;
@ -141,14 +133,13 @@ static u32 nvmet_async_event_result(struct nvmet_async_event *aen)
static void nvmet_async_events_failall(struct nvmet_ctrl *ctrl)
{
u16 status = NVME_SC_INTERNAL | NVME_SC_DNR;
struct nvmet_req *req;
mutex_lock(&ctrl->lock);
while (ctrl->nr_async_event_cmds) {
req = ctrl->async_event_cmds[--ctrl->nr_async_event_cmds];
mutex_unlock(&ctrl->lock);
nvmet_req_complete(req, status);
nvmet_req_complete(req, NVME_SC_INTERNAL | NVME_SC_DNR);
mutex_lock(&ctrl->lock);
}
mutex_unlock(&ctrl->lock);
@ -692,6 +683,7 @@ struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid)
uuid_gen(&ns->uuid);
ns->buffered_io = false;
ns->csi = NVME_CSI_NVM;
return ns;
}
@ -887,10 +879,18 @@ static u16 nvmet_parse_io_cmd(struct nvmet_req *req)
return ret;
}
if (req->ns->file)
return nvmet_file_parse_io_cmd(req);
return nvmet_bdev_parse_io_cmd(req);
switch (req->ns->csi) {
case NVME_CSI_NVM:
if (req->ns->file)
return nvmet_file_parse_io_cmd(req);
return nvmet_bdev_parse_io_cmd(req);
case NVME_CSI_ZNS:
if (IS_ENABLED(CONFIG_BLK_DEV_ZONED))
return nvmet_bdev_zns_parse_io_cmd(req);
return NVME_SC_INVALID_IO_CMD_SET;
default:
return NVME_SC_INVALID_IO_CMD_SET;
}
}
bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
@ -1112,6 +1112,17 @@ static inline u8 nvmet_cc_iocqes(u32 cc)
return (cc >> NVME_CC_IOCQES_SHIFT) & 0xf;
}
static inline bool nvmet_css_supported(u8 cc_css)
{
switch (cc_css <<= NVME_CC_CSS_SHIFT) {
case NVME_CC_CSS_NVM:
case NVME_CC_CSS_CSI:
return true;
default:
return false;
}
}
static void nvmet_start_ctrl(struct nvmet_ctrl *ctrl)
{
lockdep_assert_held(&ctrl->lock);
@ -1131,7 +1142,7 @@ static void nvmet_start_ctrl(struct nvmet_ctrl *ctrl)
if (nvmet_cc_mps(ctrl->cc) != 0 ||
nvmet_cc_ams(ctrl->cc) != 0 ||
nvmet_cc_css(ctrl->cc) != 0) {
!nvmet_css_supported(nvmet_cc_css(ctrl->cc))) {
ctrl->csts = NVME_CSTS_CFS;
return;
}
@ -1182,6 +1193,8 @@ static void nvmet_init_cap(struct nvmet_ctrl *ctrl)
{
/* command sets supported: NVMe command set: */
ctrl->cap = (1ULL << 37);
/* Controller supports one or more I/O Command Sets */
ctrl->cap |= (1ULL << 43);
/* CC.EN timeout in 500msec units: */
ctrl->cap |= (15ULL << 24);
/* maximum queue entries supported: */
@ -1493,6 +1506,8 @@ struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn,
enum nvme_subsys_type type)
{
struct nvmet_subsys *subsys;
char serial[NVMET_SN_MAX_SIZE / 2];
int ret;
subsys = kzalloc(sizeof(*subsys), GFP_KERNEL);
if (!subsys)
@ -1500,7 +1515,14 @@ struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn,
subsys->ver = NVMET_DEFAULT_VS;
/* generate a random serial number as our controllers are ephemeral: */
get_random_bytes(&subsys->serial, sizeof(subsys->serial));
get_random_bytes(&serial, sizeof(serial));
bin2hex(subsys->serial, &serial, sizeof(serial));
subsys->model_number = kstrdup(NVMET_DEFAULT_CTRL_MODEL, GFP_KERNEL);
if (!subsys->model_number) {
ret = -ENOMEM;
goto free_subsys;
}
switch (type) {
case NVME_NQN_NVME:
@ -1511,15 +1533,15 @@ struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn,
break;
default:
pr_err("%s: Unknown Subsystem type - %d\n", __func__, type);
kfree(subsys);
return ERR_PTR(-EINVAL);
ret = -EINVAL;
goto free_mn;
}
subsys->type = type;
subsys->subsysnqn = kstrndup(subsysnqn, NVMF_NQN_SIZE,
GFP_KERNEL);
if (!subsys->subsysnqn) {
kfree(subsys);
return ERR_PTR(-ENOMEM);
ret = -ENOMEM;
goto free_mn;
}
subsys->cntlid_min = NVME_CNTLID_MIN;
subsys->cntlid_max = NVME_CNTLID_MAX;
@ -1531,6 +1553,12 @@ struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn,
INIT_LIST_HEAD(&subsys->hosts);
return subsys;
free_mn:
kfree(subsys->model_number);
free_subsys:
kfree(subsys);
return ERR_PTR(ret);
}
static void nvmet_subsys_free(struct kref *ref)
@ -1569,11 +1597,15 @@ static int __init nvmet_init(void)
nvmet_ana_group_enabled[NVMET_DEFAULT_ANA_GRPID] = 1;
zbd_wq = alloc_workqueue("nvmet-zbd-wq", WQ_MEM_RECLAIM, 0);
if (!zbd_wq)
return -ENOMEM;
buffered_io_wq = alloc_workqueue("nvmet-buffered-io-wq",
WQ_MEM_RECLAIM, 0);
if (!buffered_io_wq) {
error = -ENOMEM;
goto out;
goto out_free_zbd_work_queue;
}
error = nvmet_init_discovery();
@ -1589,7 +1621,8 @@ out_exit_discovery:
nvmet_exit_discovery();
out_free_work_queue:
destroy_workqueue(buffered_io_wq);
out:
out_free_zbd_work_queue:
destroy_workqueue(zbd_wq);
return error;
}
@ -1599,6 +1632,7 @@ static void __exit nvmet_exit(void)
nvmet_exit_discovery();
ida_destroy(&cntlid_ida);
destroy_workqueue(buffered_io_wq);
destroy_workqueue(zbd_wq);
BUILD_BUG_ON(sizeof(struct nvmf_disc_rsp_page_entry) != 1024);
BUILD_BUG_ON(sizeof(struct nvmf_disc_rsp_page_hdr) != 1024);

8
drivers/nvme/target/discovery.c

@ -244,7 +244,6 @@ static void nvmet_execute_disc_identify(struct nvmet_req *req)
{
struct nvmet_ctrl *ctrl = req->sq->ctrl;
struct nvme_id_ctrl *id;
const char model[] = "Linux";
u16 status = 0;
if (!nvmet_check_transfer_len(req, NVME_IDENTIFY_DATA_SIZE))
@ -262,11 +261,10 @@ static void nvmet_execute_disc_identify(struct nvmet_req *req)
goto out;
}
memset(id->sn, ' ', sizeof(id->sn));
bin2hex(id->sn, &ctrl->subsys->serial,
min(sizeof(ctrl->subsys->serial), sizeof(id->sn) / 2));
memcpy(id->sn, ctrl->subsys->serial, NVMET_SN_MAX_SIZE);
memset(id->fr, ' ', sizeof(id->fr));
memcpy_and_pad(id->mn, sizeof(id->mn), model, sizeof(model) - 1, ' ');
memcpy_and_pad(id->mn, sizeof(id->mn), ctrl->subsys->model_number,
strlen(ctrl->subsys->model_number), ' ');
memcpy_and_pad(id->fr, sizeof(id->fr),
UTS_RELEASE, strlen(UTS_RELEASE), ' ');

10
drivers/nvme/target/fc.c

@ -2510,13 +2510,6 @@ nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport,
u32 xfrlen = be32_to_cpu(cmdiu->data_len);
int ret;
/*
* if there is no nvmet mapping to the targetport there
* shouldn't be requests. just terminate them.
*/
if (!tgtport->pe)
goto transport_error;
/*
* Fused commands are currently not supported in the linux
* implementation.
@ -2544,7 +2537,8 @@ nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport,
fod->req.cmd = &fod->cmdiubuf.sqe;
fod->req.cqe = &fod->rspiubuf.cqe;
fod->req.port = tgtport->pe->port;
if (tgtport->pe)
fod->req.port = tgtport->pe->port;
/* clear any response payload */
memset(&fod->rspiubuf, 0, sizeof(fod->rspiubuf));

33
drivers/nvme/target/io-cmd-bdev.c

@ -47,6 +47,14 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id)
id->nows = to0based(ql->io_opt / ql->logical_block_size);
}
void nvmet_bdev_ns_disable(struct nvmet_ns *ns)
{
if (ns->bdev) {
blkdev_put(ns->bdev, FMODE_WRITE | FMODE_READ);
ns->bdev = NULL;
}
}
static void nvmet_bdev_ns_enable_integrity(struct nvmet_ns *ns)
{
struct blk_integrity *bi = bdev_get_integrity(ns->bdev);
@ -86,15 +94,15 @@ int nvmet_bdev_ns_enable(struct nvmet_ns *ns)
if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY_T10))
nvmet_bdev_ns_enable_integrity(ns);
return 0;
}
void nvmet_bdev_ns_disable(struct nvmet_ns *ns)
{
if (ns->bdev) {
blkdev_put(ns->bdev, FMODE_WRITE | FMODE_READ);
ns->bdev = NULL;
if (bdev_is_zoned(ns->bdev)) {
if (!nvmet_bdev_zns_enable(ns)) {
nvmet_bdev_ns_disable(ns);
return -EINVAL;
}
ns->csi = NVME_CSI_ZNS;
}
return 0;
}
void nvmet_bdev_ns_revalidate(struct nvmet_ns *ns)
@ -102,7 +110,7 @@ void nvmet_bdev_ns_revalidate(struct nvmet_ns *ns)
ns->size = i_size_read(ns->bdev->bd_inode);
}
static u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts)
u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts)
{
u16 status = NVME_SC_SUCCESS;
@ -164,8 +172,7 @@ static void nvmet_bio_done(struct bio *bio)
struct nvmet_req *req = bio->bi_private;
nvmet_req_complete(req, blk_to_nvme_status(req, bio->bi_status));
if (bio != &req->b.inline_bio)
bio_put(bio);
nvmet_req_bio_put(req, bio);
}
#ifdef CONFIG_BLK_DEV_INTEGRITY
@ -429,9 +436,7 @@ static void nvmet_bdev_execute_write_zeroes(struct nvmet_req *req)
u16 nvmet_bdev_parse_io_cmd(struct nvmet_req *req)
{
struct nvme_command *cmd = req->cmd;
switch (cmd->common.opcode) {
switch (req->cmd->common.opcode) {
case nvme_cmd_read:
case nvme_cmd_write:
req->execute = nvmet_bdev_execute_rw;

4
drivers/nvme/target/io-cmd-file.c

@ -385,9 +385,7 @@ static void nvmet_file_execute_write_zeroes(struct nvmet_req *req)
u16 nvmet_file_parse_io_cmd(struct nvmet_req *req)
{
struct nvme_command *cmd = req->cmd;
switch (cmd->common.opcode) {
switch (req->cmd->common.opcode) {
case nvme_cmd_read:
case nvme_cmd_write:
req->execute = nvmet_file_execute_rw;

41
drivers/nvme/target/nvmet.h

@ -28,6 +28,7 @@
#define NVMET_NO_ERROR_LOC ((u16)-1)
#define NVMET_DEFAULT_CTRL_MODEL "Linux"
#define NVMET_MN_MAX_SIZE 40
#define NVMET_SN_MAX_SIZE 20
/*
* Supported optional AENs:
@ -82,6 +83,7 @@ struct nvmet_ns {
struct pci_dev *p2p_dev;
int pi_type;
int metadata_size;
u8 csi;
};
static inline struct nvmet_ns *to_nvmet_ns(struct config_item *item)
@ -217,7 +219,7 @@ struct nvmet_subsys {
struct xarray namespaces;
unsigned int nr_namespaces;
unsigned int max_nsid;
u32 max_nsid;
u16 cntlid_min;
u16 cntlid_max;
@ -229,7 +231,8 @@ struct nvmet_subsys {
u16 max_qid;
u64 ver;
u64 serial;
char serial[NVMET_SN_MAX_SIZE];
bool subsys_discovered;
char *subsysnqn;
bool pi_support;
@ -247,6 +250,10 @@ struct nvmet_subsys {
unsigned int admin_timeout;
unsigned int io_timeout;
#endif /* CONFIG_NVME_TARGET_PASSTHRU */
#ifdef CONFIG_BLK_DEV_ZONED
u8 zasl;
#endif /* CONFIG_BLK_DEV_ZONED */
};
static inline struct nvmet_subsys *to_subsys(struct config_item *item)
@ -332,6 +339,12 @@ struct nvmet_req {
struct work_struct work;
bool use_workqueue;
} p;
#ifdef CONFIG_BLK_DEV_ZONED
struct {
struct bio inline_bio;
struct work_struct zmgmt_work;
} z;
#endif /* CONFIG_BLK_DEV_ZONED */
};
int sg_cnt;
int metadata_sg_cnt;
@ -351,6 +364,7 @@ struct nvmet_req {
};
extern struct workqueue_struct *buffered_io_wq;
extern struct workqueue_struct *zbd_wq;
static inline void nvmet_set_result(struct nvmet_req *req, u32 result)
{
@ -400,6 +414,7 @@ u16 nvmet_parse_connect_cmd(struct nvmet_req *req);
void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id);
u16 nvmet_bdev_parse_io_cmd(struct nvmet_req *req);
u16 nvmet_file_parse_io_cmd(struct nvmet_req *req);
u16 nvmet_bdev_zns_parse_io_cmd(struct nvmet_req *req);
u16 nvmet_parse_admin_cmd(struct nvmet_req *req);
u16 nvmet_parse_discovery_cmd(struct nvmet_req *req);
u16 nvmet_parse_fabrics_cmd(struct nvmet_req *req);
@ -527,6 +542,14 @@ void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid);
void nvmet_bdev_ns_revalidate(struct nvmet_ns *ns);
int nvmet_file_ns_revalidate(struct nvmet_ns *ns);
void nvmet_ns_revalidate(struct nvmet_ns *ns);
u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts);
bool nvmet_bdev_zns_enable(struct nvmet_ns *ns);
void nvmet_execute_identify_cns_cs_ctrl(struct nvmet_req *req);
void nvmet_execute_identify_cns_cs_ns(struct nvmet_req *req);
void nvmet_bdev_execute_zone_mgmt_recv(struct nvmet_req *req);
void nvmet_bdev_execute_zone_mgmt_send(struct nvmet_req *req);
void nvmet_bdev_execute_zone_append(struct nvmet_req *req);
static inline u32 nvmet_rw_data_len(struct nvmet_req *req)
{
@ -622,4 +645,18 @@ static inline bool nvmet_use_inline_bvec(struct nvmet_req *req)
req->sg_cnt <= NVMET_MAX_INLINE_BIOVEC;
}
static inline void nvmet_req_cns_error_complete(struct nvmet_req *req)
{
pr_debug("unhandled identify cns %d on qid %d\n",
req->cmd->identify.cns, req->sq->qid);
req->error_loc = offsetof(struct nvme_identify, cns);
nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR);
}
static inline void nvmet_req_bio_put(struct nvmet_req *req, struct bio *bio)
{
if (bio != &req->b.inline_bio)
bio_put(bio);
}
#endif /* _NVMET_H */

3
drivers/nvme/target/passthru.c

@ -206,8 +206,7 @@ static int nvmet_passthru_map_sg(struct nvmet_req *req, struct request *rq)
for_each_sg(req->sg, sg, req->sg_cnt, i) {
if (bio_add_pc_page(rq->q, bio, sg_page(sg), sg->length,
sg->offset) < sg->length) {
if (bio != &req->p.inline_bio)
bio_put(bio);
nvmet_req_bio_put(req, bio);
return -EINVAL;
}
}

3
drivers/nvme/target/rdma.c

@ -1257,7 +1257,7 @@ out_err:
static int nvmet_rdma_create_queue_ib(struct nvmet_rdma_queue *queue)
{
struct ib_qp_init_attr qp_attr;
struct ib_qp_init_attr qp_attr = { };
struct nvmet_rdma_device *ndev = queue->dev;
int nr_cqe, ret, i, factor;
@ -1275,7 +1275,6 @@ static int nvmet_rdma_create_queue_ib(struct nvmet_rdma_queue *queue)
goto out;
}
memset(&qp_attr, 0, sizeof(qp_attr));
qp_attr.qp_context = queue;
qp_attr.event_handler = nvmet_rdma_qp_event;
qp_attr.send_cq = queue->cq;

615
drivers/nvme/target/zns.c Normal file

@ -0,0 +1,615 @@
// SPDX-License-Identifier: GPL-2.0
/*
* NVMe ZNS-ZBD command implementation.
* Copyright (C) 2021 Western Digital Corporation or its affiliates.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/nvme.h>
#include <linux/blkdev.h>
#include "nvmet.h"
/*
* We set the Memory Page Size Minimum (MPSMIN) for target controller to 0
* which gets added by 12 in the nvme_enable_ctrl() which results in 2^12 = 4k
* as page_shift value. When calculating the ZASL use shift by 12.
*/
#define NVMET_MPSMIN_SHIFT 12
static inline u8 nvmet_zasl(unsigned int zone_append_sects)
{
/*
* Zone Append Size Limit (zasl) is expressed as a power of 2 value
* with the minimum memory page size (i.e. 12) as unit.
*/
return ilog2(zone_append_sects >> (NVMET_MPSMIN_SHIFT - 9));
}
static int validate_conv_zones_cb(struct blk_zone *z,
unsigned int i, void *data)
{
if (z->type == BLK_ZONE_TYPE_CONVENTIONAL)
return -EOPNOTSUPP;
return 0;
}
bool nvmet_bdev_zns_enable(struct nvmet_ns *ns)
{
struct request_queue *q = ns->bdev->bd_disk->queue;
u8 zasl = nvmet_zasl(queue_max_zone_append_sectors(q));
struct gendisk *bd_disk = ns->bdev->bd_disk;
int ret;
if (ns->subsys->zasl) {
if (ns->subsys->zasl > zasl)
return false;
}
ns->subsys->zasl = zasl;
/*
* Generic zoned block devices may have a smaller last zone which is
* not supported by ZNS. Exclude zoned drives that have such smaller
* last zone.
*/
if (get_capacity(bd_disk) & (bdev_zone_sectors(ns->bdev) - 1))
return false;
/*
* ZNS does not define a conventional zone type. If the underlying
* device has a bitmap set indicating the existence of conventional
* zones, reject the device. Otherwise, use report zones to detect if
* the device has conventional zones.
*/
if (ns->bdev->bd_disk->queue->conv_zones_bitmap)
return false;
ret = blkdev_report_zones(ns->bdev, 0, blkdev_nr_zones(bd_disk),
validate_conv_zones_cb, NULL);
if (ret < 0)
return false;
ns->blksize_shift = blksize_bits(bdev_logical_block_size(ns->bdev));
return true;
}
void nvmet_execute_identify_cns_cs_ctrl(struct nvmet_req *req)
{
u8 zasl = req->sq->ctrl->subsys->zasl;
struct nvmet_ctrl *ctrl = req->sq->ctrl;
struct nvme_id_ctrl_zns *id;
u16 status;
id = kzalloc(sizeof(*id), GFP_KERNEL);
if (!id) {
status = NVME_SC_INTERNAL;
goto out;
}
if (ctrl->ops->get_mdts)
id->zasl = min_t(u8, ctrl->ops->get_mdts(ctrl), zasl);
else
id->zasl = zasl;
status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id));
kfree(id);
out:
nvmet_req_complete(req, status);
}
void nvmet_execute_identify_cns_cs_ns(struct nvmet_req *req)
{
struct nvme_id_ns_zns *id_zns;
u64 zsze;
u16 status;
if (le32_to_cpu(req->cmd->identify.nsid) == NVME_NSID_ALL) {
req->error_loc = offsetof(struct nvme_identify, nsid);
status = NVME_SC_INVALID_NS | NVME_SC_DNR;
goto out;
}
id_zns = kzalloc(sizeof(*id_zns), GFP_KERNEL);
if (!id_zns) {
status = NVME_SC_INTERNAL;
goto out;
}
status = nvmet_req_find_ns(req);
if (status) {
status = NVME_SC_INTERNAL;
goto done;
}
if (!bdev_is_zoned(req->ns->bdev)) {
req->error_loc = offsetof(struct nvme_identify, nsid);
status = NVME_SC_INVALID_NS | NVME_SC_DNR;
goto done;
}
nvmet_ns_revalidate(req->ns);
zsze = (bdev_zone_sectors(req->ns->bdev) << 9) >>
req->ns->blksize_shift;
id_zns->lbafe[0].zsze = cpu_to_le64(zsze);
id_zns->mor = cpu_to_le32(bdev_max_open_zones(req->ns->bdev));
id_zns->mar = cpu_to_le32(bdev_max_active_zones(req->ns->bdev));
done:
status = nvmet_copy_to_sgl(req, 0, id_zns, sizeof(*id_zns));
kfree(id_zns);
out:
nvmet_req_complete(req, status);
}
static u16 nvmet_bdev_validate_zone_mgmt_recv(struct nvmet_req *req)
{
sector_t sect = nvmet_lba_to_sect(req->ns, req->cmd->zmr.slba);
u32 out_bufsize = (le32_to_cpu(req->cmd->zmr.numd) + 1) << 2;
if (sect >= get_capacity(req->ns->bdev->bd_disk)) {
req->error_loc = offsetof(struct nvme_zone_mgmt_recv_cmd, slba);
return NVME_SC_LBA_RANGE | NVME_SC_DNR;
}
if (out_bufsize < sizeof(struct nvme_zone_report)) {
req->error_loc = offsetof(struct nvme_zone_mgmt_recv_cmd, numd);
return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
}
if (req->cmd->zmr.zra != NVME_ZRA_ZONE_REPORT) {
req->error_loc = offsetof(struct nvme_zone_mgmt_recv_cmd, zra);
return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
}
switch (req->cmd->zmr.pr) {
case 0:
case 1:
break;
default:
req->error_loc = offsetof(struct nvme_zone_mgmt_recv_cmd, pr);
return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
}
switch (req->cmd->zmr.zrasf) {
case NVME_ZRASF_ZONE_REPORT_ALL:
case NVME_ZRASF_ZONE_STATE_EMPTY:
case NVME_ZRASF_ZONE_STATE_IMP_OPEN:
case NVME_ZRASF_ZONE_STATE_EXP_OPEN:
case NVME_ZRASF_ZONE_STATE_CLOSED:
case NVME_ZRASF_ZONE_STATE_FULL:
case NVME_ZRASF_ZONE_STATE_READONLY:
case NVME_ZRASF_ZONE_STATE_OFFLINE:
break;
default:
req->error_loc =
offsetof(struct nvme_zone_mgmt_recv_cmd, zrasf);
return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
}
return NVME_SC_SUCCESS;
}
struct nvmet_report_zone_data {
struct nvmet_req *req;
u64 out_buf_offset;
u64 out_nr_zones;
u64 nr_zones;
u8 zrasf;
};
static int nvmet_bdev_report_zone_cb(struct blk_zone *z, unsigned i, void *d)
{
static const unsigned int nvme_zrasf_to_blk_zcond[] = {
[NVME_ZRASF_ZONE_STATE_EMPTY] = BLK_ZONE_COND_EMPTY,
[NVME_ZRASF_ZONE_STATE_IMP_OPEN] = BLK_ZONE_COND_IMP_OPEN,
[NVME_ZRASF_ZONE_STATE_EXP_OPEN] = BLK_ZONE_COND_EXP_OPEN,
[NVME_ZRASF_ZONE_STATE_CLOSED] = BLK_ZONE_COND_CLOSED,
[NVME_ZRASF_ZONE_STATE_READONLY] = BLK_ZONE_COND_READONLY,
[NVME_ZRASF_ZONE_STATE_FULL] = BLK_ZONE_COND_FULL,
[NVME_ZRASF_ZONE_STATE_OFFLINE] = BLK_ZONE_COND_OFFLINE,
};
struct nvmet_report_zone_data *rz = d;
if (rz->zrasf != NVME_ZRASF_ZONE_REPORT_ALL &&
z->cond != nvme_zrasf_to_blk_zcond[rz->zrasf])
return 0;
if (rz->nr_zones < rz->out_nr_zones) {
struct nvme_zone_descriptor zdesc = { };
u16 status;
zdesc.zcap = nvmet_sect_to_lba(rz->req->ns, z->capacity);
zdesc.zslba = nvmet_sect_to_lba(rz->req->ns, z->start);
zdesc.wp = nvmet_sect_to_lba(rz->req->ns, z->wp);
zdesc.za = z->reset ? 1 << 2 : 0;
zdesc.zs = z->cond << 4;
zdesc.zt = z->type;
status = nvmet_copy_to_sgl(rz->req, rz->out_buf_offset, &zdesc,
sizeof(zdesc));
if (status)
return -EINVAL;
rz->out_buf_offset += sizeof(zdesc);
}
rz->nr_zones++;
return 0;
}
static unsigned long nvmet_req_nr_zones_from_slba(struct nvmet_req *req)
{
unsigned int sect = nvmet_lba_to_sect(req->ns, req->cmd->zmr.slba);
return blkdev_nr_zones(req->ns->bdev->bd_disk) -
(sect >> ilog2(bdev_zone_sectors(req->ns->bdev)));
}
static unsigned long get_nr_zones_from_buf(struct nvmet_req *req, u32 bufsize)
{
if (bufsize <= sizeof(struct nvme_zone_report))
return 0;
return (bufsize - sizeof(struct nvme_zone_report)) /
sizeof(struct nvme_zone_descriptor);
}
static void nvmet_bdev_zone_zmgmt_recv_work(struct work_struct *w)
{
struct nvmet_req *req = container_of(w, struct nvmet_req, z.zmgmt_work);
sector_t start_sect = nvmet_lba_to_sect(req->ns, req->cmd->zmr.slba);
unsigned long req_slba_nr_zones = nvmet_req_nr_zones_from_slba(req);
u32 out_bufsize = (le32_to_cpu(req->cmd->zmr.numd) + 1) << 2;
__le64 nr_zones;
u16 status;
int ret;
struct nvmet_report_zone_data rz_data = {
.out_nr_zones = get_nr_zones_from_buf(req, out_bufsize),
/* leave the place for report zone header */
.out_buf_offset = sizeof(struct nvme_zone_report),
.zrasf = req->cmd->zmr.zrasf,
.nr_zones = 0,
.req = req,
};
status = nvmet_bdev_validate_zone_mgmt_recv(req);
if (status)
goto out;
if (!req_slba_nr_zones) {
status = NVME_SC_SUCCESS;
goto out;
}
ret = blkdev_report_zones(req->ns->bdev, start_sect, req_slba_nr_zones,
nvmet_bdev_report_zone_cb, &rz_data);
if (ret < 0) {
status = NVME_SC_INTERNAL;
goto out;
}
/*
* When partial bit is set nr_zones must indicate the number of zone
* descriptors actually transferred.
*/
if (req->cmd->zmr.pr)
rz_data.nr_zones = min(rz_data.nr_zones, rz_data.out_nr_zones);
nr_zones = cpu_to_le64(rz_data.nr_zones);
status = nvmet_copy_to_sgl(req, 0, &nr_zones, sizeof(nr_zones));
out:
nvmet_req_complete(req, status);
}
void nvmet_bdev_execute_zone_mgmt_recv(struct nvmet_req *req)
{
INIT_WORK(&req->z.zmgmt_work, nvmet_bdev_zone_zmgmt_recv_work);
queue_work(zbd_wq, &req->z.zmgmt_work);
}
static inline enum req_opf zsa_req_op(u8 zsa)
{
switch (zsa) {
case NVME_ZONE_OPEN:
return REQ_OP_ZONE_OPEN;
case NVME_ZONE_CLOSE:
return REQ_OP_ZONE_CLOSE;
case NVME_ZONE_FINISH:
return REQ_OP_ZONE_FINISH;
case NVME_ZONE_RESET:
return REQ_OP_ZONE_RESET;
default:
return REQ_OP_LAST;
}
}
static u16 blkdev_zone_mgmt_errno_to_nvme_status(int ret)
{
switch (ret) {
case 0:
return NVME_SC_SUCCESS;
case -EINVAL:
case -EIO:
return NVME_SC_ZONE_INVALID_TRANSITION | NVME_SC_DNR;
default:
return NVME_SC_INTERNAL;
}
}
struct nvmet_zone_mgmt_send_all_data {
unsigned long *zbitmap;
struct nvmet_req *req;
};
static int zmgmt_send_scan_cb(struct blk_zone *z, unsigned i, void *d)
{
struct nvmet_zone_mgmt_send_all_data *data = d;
switch (zsa_req_op(data->req->cmd->zms.zsa)) {
case REQ_OP_ZONE_OPEN:
switch (z->cond) {
case BLK_ZONE_COND_CLOSED:
break;
default:
return 0;
}
break;
case REQ_OP_ZONE_CLOSE:
switch (z->cond) {
case BLK_ZONE_COND_IMP_OPEN:
case BLK_ZONE_COND_EXP_OPEN:
break;
default:
return 0;
}
break;
case REQ_OP_ZONE_FINISH:
switch (z->cond) {
case BLK_ZONE_COND_IMP_OPEN:
case BLK_ZONE_COND_EXP_OPEN:
case BLK_ZONE_COND_CLOSED:
break;
default:
return 0;
}
break;
default:
return -EINVAL;
}
set_bit(i, data->zbitmap);
return 0;
}
static u16 nvmet_bdev_zone_mgmt_emulate_all(struct nvmet_req *req)
{
struct block_device *bdev = req->ns->bdev;
unsigned int nr_zones = blkdev_nr_zones(bdev->bd_disk);
struct request_queue *q = bdev_get_queue(bdev);
struct bio *bio = NULL;
sector_t sector = 0;
int ret;
struct nvmet_zone_mgmt_send_all_data d = {
.req = req,
};
d.zbitmap = kcalloc_node(BITS_TO_LONGS(nr_zones), sizeof(*(d.zbitmap)),
GFP_NOIO, q->node);
if (!d.zbitmap) {
ret = -ENOMEM;
goto out;
}
/* Scan and build bitmap of the eligible zones */
ret = blkdev_report_zones(bdev, 0, nr_zones, zmgmt_send_scan_cb, &d);
if (ret != nr_zones) {
if (ret > 0)
ret = -EIO;
goto out;
} else {
/* We scanned all the zones */
ret = 0;
}
while (sector < get_capacity(bdev->bd_disk)) {
if (test_bit(blk_queue_zone_no(q, sector), d.zbitmap)) {
bio = blk_next_bio(bio, 0, GFP_KERNEL);
bio->bi_opf = zsa_req_op(req->cmd->zms.zsa) | REQ_SYNC;
bio->bi_iter.bi_sector = sector;
bio_set_dev(bio, bdev);
/* This may take a while, so be nice to others */
cond_resched();
}
sector += blk_queue_zone_sectors(q);
}
if (bio) {
ret = submit_bio_wait(bio);
bio_put(bio);
}
out:
kfree(d.zbitmap);
return blkdev_zone_mgmt_errno_to_nvme_status(ret);
}
static u16 nvmet_bdev_execute_zmgmt_send_all(struct nvmet_req *req)
{
int ret;
switch (zsa_req_op(req->cmd->zms.zsa)) {
case REQ_OP_ZONE_RESET:
ret = blkdev_zone_mgmt(req->ns->bdev, REQ_OP_ZONE_RESET, 0,
get_capacity(req->ns->bdev->bd_disk),
GFP_KERNEL);
if (ret < 0)
return blkdev_zone_mgmt_errno_to_nvme_status(ret);
break;
case REQ_OP_ZONE_OPEN:
case REQ_OP_ZONE_CLOSE:
case REQ_OP_ZONE_FINISH:
return nvmet_bdev_zone_mgmt_emulate_all(req);
default:
/* this is needed to quiet compiler warning */
req->error_loc = offsetof(struct nvme_zone_mgmt_send_cmd, zsa);
return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
}
return NVME_SC_SUCCESS;
}
static void nvmet_bdev_zmgmt_send_work(struct work_struct *w)
{
struct nvmet_req *req = container_of(w, struct nvmet_req, z.zmgmt_work);
sector_t sect = nvmet_lba_to_sect(req->ns, req->cmd->zms.slba);
enum req_opf op = zsa_req_op(req->cmd->zms.zsa);
struct block_device *bdev = req->ns->bdev;
sector_t zone_sectors = bdev_zone_sectors(bdev);
u16 status = NVME_SC_SUCCESS;
int ret;
if (op == REQ_OP_LAST) {
req->error_loc = offsetof(struct nvme_zone_mgmt_send_cmd, zsa);
status = NVME_SC_ZONE_INVALID_TRANSITION | NVME_SC_DNR;
goto out;
}
/* when select all bit is set slba field is ignored */
if (req->cmd->zms.select_all) {
status = nvmet_bdev_execute_zmgmt_send_all(req);
goto out;
}
if (sect >= get_capacity(bdev->bd_disk)) {
req->error_loc = offsetof(struct nvme_zone_mgmt_send_cmd, slba);
status = NVME_SC_LBA_RANGE | NVME_SC_DNR;
goto out;
}
if (sect & (zone_sectors - 1)) {
req->error_loc = offsetof(struct nvme_zone_mgmt_send_cmd, slba);
status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
goto out;
}
ret = blkdev_zone_mgmt(bdev, op, sect, zone_sectors, GFP_KERNEL);
if (ret < 0)
status = blkdev_zone_mgmt_errno_to_nvme_status(ret);
out:
nvmet_req_complete(req, status);
}
void nvmet_bdev_execute_zone_mgmt_send(struct nvmet_req *req)
{
INIT_WORK(&req->z.zmgmt_work, nvmet_bdev_zmgmt_send_work);
queue_work(zbd_wq, &req->z.zmgmt_work);
}
static void nvmet_bdev_zone_append_bio_done(struct bio *bio)
{
struct nvmet_req *req = bio->bi_private;
if (bio->bi_status == BLK_STS_OK) {
req->cqe->result.u64 =
nvmet_sect_to_lba(req->ns, bio->bi_iter.bi_sector);
}
nvmet_req_complete(req, blk_to_nvme_status(req, bio->bi_status));
nvmet_req_bio_put(req, bio);
}
void nvmet_bdev_execute_zone_append(struct nvmet_req *req)
{
sector_t sect = nvmet_lba_to_sect(req->ns, req->cmd->rw.slba);
u16 status = NVME_SC_SUCCESS;
unsigned int total_len = 0;
struct scatterlist *sg;
struct bio *bio;
int sg_cnt;
/* Request is completed on len mismatch in nvmet_check_transter_len() */
if (!nvmet_check_transfer_len(req, nvmet_rw_data_len(req)))
return;
if (!req->sg_cnt) {
nvmet_req_complete(req, 0);
return;
}
if (sect >= get_capacity(req->ns->bdev->bd_disk)) {
req->error_loc = offsetof(struct nvme_rw_command, slba);
status = NVME_SC_LBA_RANGE | NVME_SC_DNR;
goto out;
}
if (sect & (bdev_zone_sectors(req->ns->bdev) - 1)) {
req->error_loc = offsetof(struct nvme_rw_command, slba);
status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
goto out;
}
if (nvmet_use_inline_bvec(req)) {
bio = &req->z.inline_bio;
bio_init(bio, req->inline_bvec, ARRAY_SIZE(req->inline_bvec));
} else {
bio = bio_alloc(GFP_KERNEL, req->sg_cnt);
}
bio->bi_opf = REQ_OP_ZONE_APPEND | REQ_SYNC | REQ_IDLE;
bio->bi_end_io = nvmet_bdev_zone_append_bio_done;
bio_set_dev(bio, req->ns->bdev);
bio->bi_iter.bi_sector = sect;
bio->bi_private = req;
if (req->cmd->rw.control & cpu_to_le16(NVME_RW_FUA))
bio->bi_opf |= REQ_FUA;
for_each_sg(req->sg, sg, req->sg_cnt, sg_cnt) {
struct page *p = sg_page(sg);
unsigned int l = sg->length;
unsigned int o = sg->offset;
unsigned int ret;
ret = bio_add_zone_append_page(bio, p, l, o);
if (ret != sg->length) {
status = NVME_SC_INTERNAL;
goto out_put_bio;
}
total_len += sg->length;
}
if (total_len != nvmet_rw_data_len(req)) {
status = NVME_SC_INTERNAL | NVME_SC_DNR;
goto out_put_bio;
}
submit_bio(bio);
return;
out_put_bio:
nvmet_req_bio_put(req, bio);
out:
nvmet_req_complete(req, status);
}
u16 nvmet_bdev_zns_parse_io_cmd(struct nvmet_req *req)
{
struct nvme_command *cmd = req->cmd;
switch (cmd->common.opcode) {
case nvme_cmd_zone_append:
req->execute = nvmet_bdev_execute_zone_append;
return 0;
case nvme_cmd_zone_mgmt_recv:
req->execute = nvmet_bdev_execute_zone_mgmt_recv;
return 0;
case nvme_cmd_zone_mgmt_send:
req->execute = nvmet_bdev_execute_zone_mgmt_send;
return 0;
default:
return nvmet_bdev_parse_io_cmd(req);
}
}

5
include/linux/acpi.h

@ -1004,6 +1004,7 @@ int acpi_dev_resume(struct device *dev);
int acpi_subsys_runtime_suspend(struct device *dev);
int acpi_subsys_runtime_resume(struct device *dev);
int acpi_dev_pm_attach(struct device *dev, bool power_on);
bool acpi_storage_d3(struct device *dev);
#else
static inline int acpi_subsys_runtime_suspend(struct device *dev) { return 0; }
static inline int acpi_subsys_runtime_resume(struct device *dev) { return 0; }
@ -1011,6 +1012,10 @@ static inline int acpi_dev_pm_attach(struct device *dev, bool power_on)
{
return 0;
}
static inline bool acpi_storage_d3(struct device *dev)
{
return false;
}
#endif
#if defined(CONFIG_ACPI) && defined(CONFIG_PM_SLEEP)

2
include/linux/bio.h

@ -822,4 +822,6 @@ static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb)
bio->bi_opf |= REQ_NOWAIT;
}
struct bio *blk_next_bio(struct bio *bio, unsigned int nr_pages, gfp_t gfp);
#endif /* __LINUX_BIO_H */

12
include/linux/nvme.h

@ -636,8 +636,8 @@ struct nvme_lba_range_type {
__u8 type;
__u8 attributes;
__u8 rsvd2[14];
__u64 slba;
__u64 nlb;
__le64 slba;
__le64 nlb;
__u8 guid[16];
__u8 rsvd48[16];
};
@ -944,6 +944,13 @@ struct nvme_zone_mgmt_recv_cmd {
enum {
NVME_ZRA_ZONE_REPORT = 0,
NVME_ZRASF_ZONE_REPORT_ALL = 0,
NVME_ZRASF_ZONE_STATE_EMPTY = 0x01,
NVME_ZRASF_ZONE_STATE_IMP_OPEN = 0x02,
NVME_ZRASF_ZONE_STATE_EXP_OPEN = 0x03,
NVME_ZRASF_ZONE_STATE_CLOSED = 0x04,
NVME_ZRASF_ZONE_STATE_READONLY = 0x05,
NVME_ZRASF_ZONE_STATE_FULL = 0x06,
NVME_ZRASF_ZONE_STATE_OFFLINE = 0x07,
NVME_REPORT_ZONE_PARTIAL = 1,
};
@ -1504,6 +1511,7 @@ enum {
NVME_SC_NS_WRITE_PROTECTED = 0x20,
NVME_SC_CMD_INTERRUPTED = 0x21,
NVME_SC_TRANSIENT_TR_ERR = 0x22,
NVME_SC_INVALID_IO_CMD_SET = 0x2C,
NVME_SC_LBA_RANGE = 0x80,
NVME_SC_CAP_EXCEEDED = 0x81,