From c787f1baa5031c22cbe20af17b2ee36ad32957ea Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 7 Apr 2023 15:05:34 -0500 Subject: block: Add PR callouts for read keys and reservation Add callouts for reading keys and reservations. This allows LIO to support the READ_KEYS and READ_RESERVATION commands so it can export devices to VMs for software like windows clustering. Signed-off-by: Mike Christie Link: https://lore.kernel.org/r/20230407200551.12660-2-michael.christie@oracle.com Reviewed-by: Chaitanya Kulkarni Reviewed-by: Christoph Hellwig Reviewed-by: Bart Van Assche Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- include/linux/pr.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include') diff --git a/include/linux/pr.h b/include/linux/pr.h index 94ceec713afe..3003daec28a5 100644 --- a/include/linux/pr.h +++ b/include/linux/pr.h @@ -4,6 +4,18 @@ #include +struct pr_keys { + u32 generation; + u32 num_keys; + u64 keys[]; +}; + +struct pr_held_reservation { + u64 key; + u32 generation; + enum pr_type type; +}; + struct pr_ops { int (*pr_register)(struct block_device *bdev, u64 old_key, u64 new_key, u32 flags); @@ -14,6 +26,19 @@ struct pr_ops { int (*pr_preempt)(struct block_device *bdev, u64 old_key, u64 new_key, enum pr_type type, bool abort); int (*pr_clear)(struct block_device *bdev, u64 key); + /* + * pr_read_keys - Read the registered keys and return them in the + * pr_keys->keys array. The keys array will have been allocated at the + * end of the pr_keys struct, and pr_keys->num_keys must be set to the + * number of keys the array can hold. If there are more than can fit + * in the array, success will still be returned and pr_keys->num_keys + * will reflect the total number of keys the device contains, so the + * caller can retry with a larger array. + */ + int (*pr_read_keys)(struct block_device *bdev, + struct pr_keys *keys_info); + int (*pr_read_reservation)(struct block_device *bdev, + struct pr_held_reservation *rsv); }; #endif /* LINUX_PR_H */ -- cgit v1.2.3 From 7ba150834b840f6f5cdd07ca69a4ccf39df59a66 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 7 Apr 2023 15:05:35 -0500 Subject: block: Rename BLK_STS_NEXUS to BLK_STS_RESV_CONFLICT BLK_STS_NEXUS is used for NVMe/SCSI reservation conflicts and DASD's locking feature which works similar to NVMe/SCSI reservations where a host can get a lock on a device and when the lock is taken it will get failures. This patch renames BLK_STS_NEXUS so it better reflects this type of use. Signed-off-by: Mike Christie Link: https://lore.kernel.org/r/20230407200551.12660-3-michael.christie@oracle.com Acked-by: Stefan Haberland Reviewed-by: Bart Van Assche Reviewed-by: Chaitanya Kulkarni Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- block/blk-core.c | 2 +- drivers/nvme/host/core.c | 2 +- drivers/s390/block/dasd.c | 7 ++++++- drivers/scsi/scsi_lib.c | 2 +- include/linux/blk_types.h | 4 ++-- 5 files changed, 11 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/block/blk-core.c b/block/blk-core.c index 9e5e0277a4d9..ff8fb7a49389 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -155,7 +155,7 @@ static const struct { [BLK_STS_NOSPC] = { -ENOSPC, "critical space allocation" }, [BLK_STS_TRANSPORT] = { -ENOLINK, "recoverable transport" }, [BLK_STS_TARGET] = { -EREMOTEIO, "critical target" }, - [BLK_STS_NEXUS] = { -EBADE, "critical nexus" }, + [BLK_STS_RESV_CONFLICT] = { -EBADE, "reservation conflict" }, [BLK_STS_MEDIUM] = { -ENODATA, "critical medium" }, [BLK_STS_PROTECTION] = { -EILSEQ, "protection" }, [BLK_STS_RESOURCE] = { -ENOMEM, "kernel resource" }, diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index c2730b116dc6..535a26ceb205 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -279,7 +279,7 @@ static blk_status_t nvme_error_status(u16 status) case NVME_SC_INVALID_PI: return BLK_STS_PROTECTION; case NVME_SC_RESERVATION_CONFLICT: - return BLK_STS_NEXUS; + return BLK_STS_RESV_CONFLICT; case NVME_SC_HOST_PATH_ERROR: return BLK_STS_TRANSPORT; case NVME_SC_ZONE_TOO_MANY_ACTIVE: diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index a9c2a8d76c45..ca0df87fa8f4 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -2723,7 +2723,12 @@ static void __dasd_cleanup_cqr(struct dasd_ccw_req *cqr) else if (status == 0) { switch (cqr->intrc) { case -EPERM: - error = BLK_STS_NEXUS; + /* + * DASD doesn't implement SCSI/NVMe reservations, but it + * implements a locking scheme similar to them. We + * return this error when we no longer have the lock. + */ + error = BLK_STS_RESV_CONFLICT; break; case -ENOLINK: error = BLK_STS_TRANSPORT; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index b7c569a42aa4..e1468483ac7e 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -599,7 +599,7 @@ static blk_status_t scsi_result_to_blk_status(int result) case SCSIML_STAT_OK: break; case SCSIML_STAT_RESV_CONFLICT: - return BLK_STS_NEXUS; + return BLK_STS_RESV_CONFLICT; case SCSIML_STAT_NOSPC: return BLK_STS_NOSPC; case SCSIML_STAT_MED_ERROR: diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 99be590f952f..2b2452086a2f 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -96,7 +96,7 @@ typedef u16 blk_short_t; #define BLK_STS_NOSPC ((__force blk_status_t)3) #define BLK_STS_TRANSPORT ((__force blk_status_t)4) #define BLK_STS_TARGET ((__force blk_status_t)5) -#define BLK_STS_NEXUS ((__force blk_status_t)6) +#define BLK_STS_RESV_CONFLICT ((__force blk_status_t)6) #define BLK_STS_MEDIUM ((__force blk_status_t)7) #define BLK_STS_PROTECTION ((__force blk_status_t)8) #define BLK_STS_RESOURCE ((__force blk_status_t)9) @@ -184,7 +184,7 @@ static inline bool blk_path_error(blk_status_t error) case BLK_STS_NOTSUPP: case BLK_STS_NOSPC: case BLK_STS_TARGET: - case BLK_STS_NEXUS: + case BLK_STS_RESV_CONFLICT: case BLK_STS_MEDIUM: case BLK_STS_PROTECTION: return false; -- cgit v1.2.3 From 0730b1632b7e803aad81ff19a4fda964a9d97053 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 7 Apr 2023 15:05:37 -0500 Subject: scsi: Move sd_pr_type to scsi_common LIO is going to want to do the same block to/from SCSI pr types as sd.c so this moves the sd_pr_type helper to scsi_common and renames it. The next patch will then also add a helper to go from the SCSI value to the block one for use with PERSISTENT_RESERVE_IN commands. Signed-off-by: Mike Christie Link: https://lore.kernel.org/r/20230407200551.12660-5-michael.christie@oracle.com Reviewed-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Reviewed-by: Bart Van Assche Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_common.c | 22 ++++++++++++++++++++++ drivers/scsi/sd.c | 33 ++++++++------------------------- include/scsi/scsi_common.h | 12 ++++++++++++ 3 files changed, 42 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/drivers/scsi/scsi_common.c b/drivers/scsi/scsi_common.c index 6e50e81a8216..11bf6c275d4e 100644 --- a/drivers/scsi/scsi_common.c +++ b/drivers/scsi/scsi_common.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include @@ -63,6 +64,27 @@ const char *scsi_device_type(unsigned type) } EXPORT_SYMBOL(scsi_device_type); +enum scsi_pr_type block_pr_type_to_scsi(enum pr_type type) +{ + switch (type) { + case PR_WRITE_EXCLUSIVE: + return SCSI_PR_WRITE_EXCLUSIVE; + case PR_EXCLUSIVE_ACCESS: + return SCSI_PR_EXCLUSIVE_ACCESS; + case PR_WRITE_EXCLUSIVE_REG_ONLY: + return SCSI_PR_WRITE_EXCLUSIVE_REG_ONLY; + case PR_EXCLUSIVE_ACCESS_REG_ONLY: + return SCSI_PR_EXCLUSIVE_ACCESS_REG_ONLY; + case PR_WRITE_EXCLUSIVE_ALL_REGS: + return SCSI_PR_WRITE_EXCLUSIVE_ALL_REGS; + case PR_EXCLUSIVE_ACCESS_ALL_REGS: + return SCSI_PR_EXCLUSIVE_ACCESS_ALL_REGS; + } + + return 0; +} +EXPORT_SYMBOL_GPL(block_pr_type_to_scsi); + /** * scsilun_to_int - convert a scsi_lun to an int * @scsilun: struct scsi_lun to be converted. diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 5c0f235a0502..fa3123a63f65 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -67,6 +67,7 @@ #include #include #include +#include #include "sd.h" #include "scsi_priv.h" @@ -1692,26 +1693,6 @@ out_unlock: return ret; } -static char sd_pr_type(enum pr_type type) -{ - switch (type) { - case PR_WRITE_EXCLUSIVE: - return 0x01; - case PR_EXCLUSIVE_ACCESS: - return 0x03; - case PR_WRITE_EXCLUSIVE_REG_ONLY: - return 0x05; - case PR_EXCLUSIVE_ACCESS_REG_ONLY: - return 0x06; - case PR_WRITE_EXCLUSIVE_ALL_REGS: - return 0x07; - case PR_EXCLUSIVE_ACCESS_ALL_REGS: - return 0x08; - default: - return 0; - } -}; - static int sd_scsi_to_pr_err(struct scsi_sense_hdr *sshdr, int result) { switch (host_byte(result)) { @@ -1742,8 +1723,8 @@ static int sd_scsi_to_pr_err(struct scsi_sense_hdr *sshdr, int result) } } -static int sd_pr_out_command(struct block_device *bdev, u8 sa, - u64 key, u64 sa_key, u8 type, u8 flags) +static int sd_pr_out_command(struct block_device *bdev, u8 sa, u64 key, + u64 sa_key, enum scsi_pr_type type, u8 flags) { struct scsi_disk *sdkp = scsi_disk(bdev->bd_disk); struct scsi_device *sdev = sdkp->device; @@ -1795,19 +1776,21 @@ static int sd_pr_reserve(struct block_device *bdev, u64 key, enum pr_type type, { if (flags) return -EOPNOTSUPP; - return sd_pr_out_command(bdev, 0x01, key, 0, sd_pr_type(type), 0); + return sd_pr_out_command(bdev, 0x01, key, 0, + block_pr_type_to_scsi(type), 0); } static int sd_pr_release(struct block_device *bdev, u64 key, enum pr_type type) { - return sd_pr_out_command(bdev, 0x02, key, 0, sd_pr_type(type), 0); + return sd_pr_out_command(bdev, 0x02, key, 0, + block_pr_type_to_scsi(type), 0); } static int sd_pr_preempt(struct block_device *bdev, u64 old_key, u64 new_key, enum pr_type type, bool abort) { return sd_pr_out_command(bdev, abort ? 0x05 : 0x04, old_key, new_key, - sd_pr_type(type), 0); + block_pr_type_to_scsi(type), 0); } static int sd_pr_clear(struct block_device *bdev, u64 key) diff --git a/include/scsi/scsi_common.h b/include/scsi/scsi_common.h index 5b567b43e1b1..e25291bbbe9b 100644 --- a/include/scsi/scsi_common.h +++ b/include/scsi/scsi_common.h @@ -7,8 +7,20 @@ #define _SCSI_COMMON_H_ #include +#include #include +enum scsi_pr_type { + SCSI_PR_WRITE_EXCLUSIVE = 0x01, + SCSI_PR_EXCLUSIVE_ACCESS = 0x03, + SCSI_PR_WRITE_EXCLUSIVE_REG_ONLY = 0x05, + SCSI_PR_EXCLUSIVE_ACCESS_REG_ONLY = 0x06, + SCSI_PR_WRITE_EXCLUSIVE_ALL_REGS = 0x07, + SCSI_PR_EXCLUSIVE_ACCESS_ALL_REGS = 0x08, +}; + +enum scsi_pr_type block_pr_type_to_scsi(enum pr_type type); + static inline unsigned scsi_varlen_cdb_length(const void *hdr) { -- cgit v1.2.3 From 0af7b5e2362d3b67334f20e49138d89141dc24d3 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 7 Apr 2023 15:05:38 -0500 Subject: scsi: Add support for block PR read keys/reservation This adds support in sd.c for the block PR read keys and read reservation callouts, so upper layers like LIO can get the PR info that's been setup using the existing pr callouts and return it to initiators. Signed-off-by: Mike Christie Link: https://lore.kernel.org/r/20230407200551.12660-6-michael.christie@oracle.com Reviewed-by: Chaitanya Kulkarni Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_common.c | 21 +++++++++++ drivers/scsi/sd.c | 91 ++++++++++++++++++++++++++++++++++++++++++++++ include/scsi/scsi_common.h | 1 + include/scsi/scsi_proto.h | 5 +++ 4 files changed, 118 insertions(+) (limited to 'include') diff --git a/drivers/scsi/scsi_common.c b/drivers/scsi/scsi_common.c index 11bf6c275d4e..b7a7a2eea887 100644 --- a/drivers/scsi/scsi_common.c +++ b/drivers/scsi/scsi_common.c @@ -64,6 +64,27 @@ const char *scsi_device_type(unsigned type) } EXPORT_SYMBOL(scsi_device_type); +enum pr_type scsi_pr_type_to_block(enum scsi_pr_type type) +{ + switch (type) { + case SCSI_PR_WRITE_EXCLUSIVE: + return PR_WRITE_EXCLUSIVE; + case SCSI_PR_EXCLUSIVE_ACCESS: + return PR_EXCLUSIVE_ACCESS; + case SCSI_PR_WRITE_EXCLUSIVE_REG_ONLY: + return PR_WRITE_EXCLUSIVE_REG_ONLY; + case SCSI_PR_EXCLUSIVE_ACCESS_REG_ONLY: + return PR_EXCLUSIVE_ACCESS_REG_ONLY; + case SCSI_PR_WRITE_EXCLUSIVE_ALL_REGS: + return PR_WRITE_EXCLUSIVE_ALL_REGS; + case SCSI_PR_EXCLUSIVE_ACCESS_ALL_REGS: + return PR_EXCLUSIVE_ACCESS_ALL_REGS; + } + + return 0; +} +EXPORT_SYMBOL_GPL(scsi_pr_type_to_block); + enum scsi_pr_type block_pr_type_to_scsi(enum pr_type type) { switch (type) { diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index fa3123a63f65..3e7a69eeb8f0 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1723,6 +1723,95 @@ static int sd_scsi_to_pr_err(struct scsi_sense_hdr *sshdr, int result) } } +static int sd_pr_in_command(struct block_device *bdev, u8 sa, + unsigned char *data, int data_len) +{ + struct scsi_disk *sdkp = scsi_disk(bdev->bd_disk); + struct scsi_device *sdev = sdkp->device; + struct scsi_sense_hdr sshdr; + u8 cmd[10] = { PERSISTENT_RESERVE_IN, sa }; + const struct scsi_exec_args exec_args = { + .sshdr = &sshdr, + }; + int result; + + put_unaligned_be16(data_len, &cmd[7]); + + result = scsi_execute_cmd(sdev, cmd, REQ_OP_DRV_IN, data, data_len, + SD_TIMEOUT, sdkp->max_retries, &exec_args); + if (scsi_status_is_check_condition(result) && + scsi_sense_valid(&sshdr)) { + sdev_printk(KERN_INFO, sdev, "PR command failed: %d\n", result); + scsi_print_sense_hdr(sdev, NULL, &sshdr); + } + + if (result <= 0) + return result; + + return sd_scsi_to_pr_err(&sshdr, result); +} + +static int sd_pr_read_keys(struct block_device *bdev, struct pr_keys *keys_info) +{ + int result, i, data_offset, num_copy_keys; + u32 num_keys = keys_info->num_keys; + int data_len = num_keys * 8 + 8; + u8 *data; + + data = kzalloc(data_len, GFP_KERNEL); + if (!data) + return -ENOMEM; + + result = sd_pr_in_command(bdev, READ_KEYS, data, data_len); + if (result) + goto free_data; + + keys_info->generation = get_unaligned_be32(&data[0]); + keys_info->num_keys = get_unaligned_be32(&data[4]) / 8; + + data_offset = 8; + num_copy_keys = min(num_keys, keys_info->num_keys); + + for (i = 0; i < num_copy_keys; i++) { + keys_info->keys[i] = get_unaligned_be64(&data[data_offset]); + data_offset += 8; + } + +free_data: + kfree(data); + return result; +} + +static int sd_pr_read_reservation(struct block_device *bdev, + struct pr_held_reservation *rsv) +{ + struct scsi_disk *sdkp = scsi_disk(bdev->bd_disk); + struct scsi_device *sdev = sdkp->device; + u8 data[24] = { }; + int result, len; + + result = sd_pr_in_command(bdev, READ_RESERVATION, data, sizeof(data)); + if (result) + return result; + + len = get_unaligned_be32(&data[4]); + if (!len) + return 0; + + /* Make sure we have at least the key and type */ + if (len < 14) { + sdev_printk(KERN_INFO, sdev, + "READ RESERVATION failed due to short return buffer of %d bytes\n", + len); + return -EINVAL; + } + + rsv->generation = get_unaligned_be32(&data[0]); + rsv->key = get_unaligned_be64(&data[8]); + rsv->type = scsi_pr_type_to_block(data[21] & 0x0f); + return 0; +} + static int sd_pr_out_command(struct block_device *bdev, u8 sa, u64 key, u64 sa_key, enum scsi_pr_type type, u8 flags) { @@ -1804,6 +1893,8 @@ static const struct pr_ops sd_pr_ops = { .pr_release = sd_pr_release, .pr_preempt = sd_pr_preempt, .pr_clear = sd_pr_clear, + .pr_read_keys = sd_pr_read_keys, + .pr_read_reservation = sd_pr_read_reservation, }; static void scsi_disk_free_disk(struct gendisk *disk) diff --git a/include/scsi/scsi_common.h b/include/scsi/scsi_common.h index e25291bbbe9b..fb58715fac86 100644 --- a/include/scsi/scsi_common.h +++ b/include/scsi/scsi_common.h @@ -20,6 +20,7 @@ enum scsi_pr_type { }; enum scsi_pr_type block_pr_type_to_scsi(enum pr_type type); +enum pr_type scsi_pr_type_to_block(enum scsi_pr_type type); static inline unsigned scsi_varlen_cdb_length(const void *hdr) diff --git a/include/scsi/scsi_proto.h b/include/scsi/scsi_proto.h index fbe5bdfe4d6e..07d65c1f59db 100644 --- a/include/scsi/scsi_proto.h +++ b/include/scsi/scsi_proto.h @@ -151,6 +151,11 @@ #define ZO_FINISH_ZONE 0x02 #define ZO_OPEN_ZONE 0x03 #define ZO_RESET_WRITE_POINTER 0x04 +/* values for PR in service action */ +#define READ_KEYS 0x00 +#define READ_RESERVATION 0x01 +#define REPORT_CAPABILITES 0x02 +#define READ_FULL_STATUS 0x03 /* values for variable length command */ #define XDREAD_32 0x03 #define XDWRITE_32 0x04 -- cgit v1.2.3 From f2bf2e7e2d526116aab942aaf1b71a949a570ba6 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 7 Apr 2023 15:05:40 -0500 Subject: nvme: Fix reservation status related structs This fixes the following issues with the reservation status structs: 1. resv10 is bytes 23:10 so it should be 14 bytes. 2. regctl_ds only supports 64 bit host IDs. These are not currently used, but will be in this patchset which adds support for the reservation report command. Signed-off-by: Mike Christie Link: https://lore.kernel.org/r/20230407200551.12660-8-michael.christie@oracle.com Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- include/linux/nvme.h | 38 ++++++++++++++++++++++++++++++-------- 1 file changed, 30 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 4fad4aa245fb..57b5b2b8d95b 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -759,20 +759,42 @@ enum { NVME_LBART_ATTRIB_HIDE = 1 << 1, }; +struct nvme_registered_ctrl { + __le16 cntlid; + __u8 rcsts; + __u8 rsvd3[5]; + __le64 hostid; + __le64 rkey; +}; + struct nvme_reservation_status { __le32 gen; __u8 rtype; __u8 regctl[2]; __u8 resv5[2]; __u8 ptpls; - __u8 resv10[13]; - struct { - __le16 cntlid; - __u8 rcsts; - __u8 resv3[5]; - __le64 hostid; - __le64 rkey; - } regctl_ds[]; + __u8 resv10[14]; + struct nvme_registered_ctrl regctl_ds[]; +}; + +struct nvme_registered_ctrl_ext { + __le16 cntlid; + __u8 rcsts; + __u8 rsvd3[5]; + __le64 rkey; + __u8 hostid[16]; + __u8 rsvd32[32]; +}; + +struct nvme_reservation_status_ext { + __le32 gen; + __u8 rtype; + __u8 regctl[2]; + __u8 resv5[2]; + __u8 ptpls; + __u8 resv10[14]; + __u8 rsvd24[40]; + struct nvme_registered_ctrl_ext regctl_eds[]; }; enum nvme_async_event_type { -- cgit v1.2.3 From 5fd96a4e15de8442915a912233d800c56f49001d Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 7 Apr 2023 15:05:44 -0500 Subject: nvme: Add pr_ops read_keys support This patch adds support for the pr_ops read_keys callout by calling the NVMe Reservation Report helper, then parsing that info to get the controller's registered keys. Because the callout is only used in the kernel where the callers, like LIO, do not know about controller/host IDs, the callout just returns the registered keys which is required by the SCSI PR in READ KEYS command. Signed-off-by: Mike Christie Link: https://lore.kernel.org/r/20230407200551.12660-12-michael.christie@oracle.com Reviewed-by: Chaitanya Kulkarni Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- drivers/nvme/host/pr.c | 69 ++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/nvme.h | 4 +++ 2 files changed, 73 insertions(+) (limited to 'include') diff --git a/drivers/nvme/host/pr.c b/drivers/nvme/host/pr.c index cd93d2e5b340..0ee656404437 100644 --- a/drivers/nvme/host/pr.c +++ b/drivers/nvme/host/pr.c @@ -154,10 +154,79 @@ static int nvme_pr_release(struct block_device *bdev, u64 key, enum pr_type type return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_release); } +static int nvme_pr_resv_report(struct block_device *bdev, void *data, + u32 data_len, bool *eds) +{ + struct nvme_command c = { }; + int ret; + + c.common.opcode = nvme_cmd_resv_report; + c.common.cdw10 = cpu_to_le32(nvme_bytes_to_numd(data_len)); + c.common.cdw11 = cpu_to_le32(NVME_EXTENDED_DATA_STRUCT); + *eds = true; + +retry: + ret = nvme_send_pr_command(bdev, &c, data, data_len); + if (ret == NVME_SC_HOST_ID_INCONSIST && + c.common.cdw11 == cpu_to_le32(NVME_EXTENDED_DATA_STRUCT)) { + c.common.cdw11 = 0; + *eds = false; + goto retry; + } + + if (ret < 0) + return ret; + + return nvme_sc_to_pr_err(ret); +} + +static int nvme_pr_read_keys(struct block_device *bdev, + struct pr_keys *keys_info) +{ + u32 rse_len, num_keys = keys_info->num_keys; + struct nvme_reservation_status_ext *rse; + int ret, i; + bool eds; + + /* + * Assume we are using 128-bit host IDs and allocate a buffer large + * enough to get enough keys to fill the return keys buffer. + */ + rse_len = struct_size(rse, regctl_eds, num_keys); + rse = kzalloc(rse_len, GFP_KERNEL); + if (!rse) + return -ENOMEM; + + ret = nvme_pr_resv_report(bdev, rse, rse_len, &eds); + if (ret) + goto free_rse; + + keys_info->generation = le32_to_cpu(rse->gen); + keys_info->num_keys = get_unaligned_le16(&rse->regctl); + + num_keys = min(num_keys, keys_info->num_keys); + for (i = 0; i < num_keys; i++) { + if (eds) { + keys_info->keys[i] = + le64_to_cpu(rse->regctl_eds[i].rkey); + } else { + struct nvme_reservation_status *rs; + + rs = (struct nvme_reservation_status *)rse; + keys_info->keys[i] = le64_to_cpu(rs->regctl_ds[i].rkey); + } + } + +free_rse: + kfree(rse); + return ret; +} + const struct pr_ops nvme_pr_ops = { .pr_register = nvme_pr_register, .pr_reserve = nvme_pr_reserve, .pr_release = nvme_pr_release, .pr_preempt = nvme_pr_preempt, .pr_clear = nvme_pr_clear, + .pr_read_keys = nvme_pr_read_keys, }; diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 57b5b2b8d95b..a617e250d629 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -759,6 +759,10 @@ enum { NVME_LBART_ATTRIB_HIDE = 1 << 1, }; +enum nvme_eds { + NVME_EXTENDED_DATA_STRUCT = 0x1, +}; + struct nvme_registered_ctrl { __le16 cntlid; __u8 rcsts; -- cgit v1.2.3 From be1a7cd2d0ed028ffdd60c65e3734e2a1d8b17df Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 7 Apr 2023 15:05:45 -0500 Subject: nvme: Add a nvme_pr_type enum The next patch adds support to report the reservation type, so we need to be able to convert from the NVMe PR value we get from the device to the linux block layer PR value that will be returned to callers. To prepare for that, this patch adds a nvme_pr_type enum and renames the nvme_pr_type function. Signed-off-by: Mike Christie Link: https://lore.kernel.org/r/20230407200551.12660-13-michael.christie@oracle.com Reviewed-by: Chaitanya Kulkarni Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- drivers/nvme/host/pr.c | 24 ++++++++++++------------ include/linux/nvme.h | 9 +++++++++ 2 files changed, 21 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/drivers/nvme/host/pr.c b/drivers/nvme/host/pr.c index 0ee656404437..732c56b417c2 100644 --- a/drivers/nvme/host/pr.c +++ b/drivers/nvme/host/pr.c @@ -9,24 +9,24 @@ #include "nvme.h" -static char nvme_pr_type(enum pr_type type) +static enum nvme_pr_type nvme_pr_type_from_blk(enum pr_type type) { switch (type) { case PR_WRITE_EXCLUSIVE: - return 1; + return NVME_PR_WRITE_EXCLUSIVE; case PR_EXCLUSIVE_ACCESS: - return 2; + return NVME_PR_EXCLUSIVE_ACCESS; case PR_WRITE_EXCLUSIVE_REG_ONLY: - return 3; + return NVME_PR_WRITE_EXCLUSIVE_REG_ONLY; case PR_EXCLUSIVE_ACCESS_REG_ONLY: - return 4; + return NVME_PR_EXCLUSIVE_ACCESS_REG_ONLY; case PR_WRITE_EXCLUSIVE_ALL_REGS: - return 5; + return NVME_PR_WRITE_EXCLUSIVE_ALL_REGS; case PR_EXCLUSIVE_ACCESS_ALL_REGS: - return 6; - default: - return 0; + return NVME_PR_EXCLUSIVE_ACCESS_ALL_REGS; } + + return 0; } static int nvme_send_ns_head_pr_command(struct block_device *bdev, @@ -127,7 +127,7 @@ static int nvme_pr_reserve(struct block_device *bdev, u64 key, if (flags & ~PR_FL_IGNORE_KEY) return -EOPNOTSUPP; - cdw10 = nvme_pr_type(type) << 8; + cdw10 = nvme_pr_type_from_blk(type) << 8; cdw10 |= ((flags & PR_FL_IGNORE_KEY) ? 1 << 3 : 0); return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_acquire); } @@ -135,7 +135,7 @@ static int nvme_pr_reserve(struct block_device *bdev, u64 key, static int nvme_pr_preempt(struct block_device *bdev, u64 old, u64 new, enum pr_type type, bool abort) { - u32 cdw10 = nvme_pr_type(type) << 8 | (abort ? 2 : 1); + u32 cdw10 = nvme_pr_type_from_blk(type) << 8 | (abort ? 2 : 1); return nvme_pr_command(bdev, cdw10, old, new, nvme_cmd_resv_acquire); } @@ -149,7 +149,7 @@ static int nvme_pr_clear(struct block_device *bdev, u64 key) static int nvme_pr_release(struct block_device *bdev, u64 key, enum pr_type type) { - u32 cdw10 = nvme_pr_type(type) << 8 | (key ? 0 : 1 << 3); + u32 cdw10 = nvme_pr_type_from_blk(type) << 8 | (key ? 0 : 1 << 3); return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_release); } diff --git a/include/linux/nvme.h b/include/linux/nvme.h index a617e250d629..4013abb86642 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -759,6 +759,15 @@ enum { NVME_LBART_ATTRIB_HIDE = 1 << 1, }; +enum nvme_pr_type { + NVME_PR_WRITE_EXCLUSIVE = 1, + NVME_PR_EXCLUSIVE_ACCESS = 2, + NVME_PR_WRITE_EXCLUSIVE_REG_ONLY = 3, + NVME_PR_EXCLUSIVE_ACCESS_REG_ONLY = 4, + NVME_PR_WRITE_EXCLUSIVE_ALL_REGS = 5, + NVME_PR_EXCLUSIVE_ACCESS_ALL_REGS = 6, +}; + enum nvme_eds { NVME_EXTENDED_DATA_STRUCT = 0x1, }; -- cgit v1.2.3 From 0217da08c1b904be49ac141442bbc1671d3630e7 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 7 Apr 2023 15:05:47 -0500 Subject: scsi: target: Rename sbc_ops to exec_cmd_ops The next patches allow us to call the block layer's pr_ops from the backends. This will require allowing the backends to hook into the cmd processing for SPC commands, so this renames sbc_ops to a more generic exec_cmd_ops. Signed-off-by: Mike Christie Link: https://lore.kernel.org/r/20230407200551.12660-15-michael.christie@oracle.com Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- drivers/target/target_core_file.c | 4 ++-- drivers/target/target_core_iblock.c | 4 ++-- drivers/target/target_core_rd.c | 4 ++-- drivers/target/target_core_sbc.c | 13 +++++++------ drivers/target/target_core_spc.c | 4 ++-- include/target/target_core_backend.h | 4 ++-- 6 files changed, 17 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c index ce0e000b74fc..4d447520bab8 100644 --- a/drivers/target/target_core_file.c +++ b/drivers/target/target_core_file.c @@ -896,7 +896,7 @@ static void fd_free_prot(struct se_device *dev) fd_dev->fd_prot_file = NULL; } -static struct sbc_ops fd_sbc_ops = { +static struct exec_cmd_ops fd_exec_cmd_ops = { .execute_rw = fd_execute_rw, .execute_sync_cache = fd_execute_sync_cache, .execute_write_same = fd_execute_write_same, @@ -906,7 +906,7 @@ static struct sbc_ops fd_sbc_ops = { static sense_reason_t fd_parse_cdb(struct se_cmd *cmd) { - return sbc_parse_cdb(cmd, &fd_sbc_ops); + return sbc_parse_cdb(cmd, &fd_exec_cmd_ops); } static const struct target_backend_ops fileio_ops = { diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index cc838ffd1294..d93f24f9687d 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -869,7 +869,7 @@ static unsigned int iblock_get_io_opt(struct se_device *dev) return bdev_io_opt(bd); } -static struct sbc_ops iblock_sbc_ops = { +static struct exec_cmd_ops iblock_exec_cmd_ops = { .execute_rw = iblock_execute_rw, .execute_sync_cache = iblock_execute_sync_cache, .execute_write_same = iblock_execute_write_same, @@ -879,7 +879,7 @@ static struct sbc_ops iblock_sbc_ops = { static sense_reason_t iblock_parse_cdb(struct se_cmd *cmd) { - return sbc_parse_cdb(cmd, &iblock_sbc_ops); + return sbc_parse_cdb(cmd, &iblock_exec_cmd_ops); } static bool iblock_get_write_cache(struct se_device *dev) diff --git a/drivers/target/target_core_rd.c b/drivers/target/target_core_rd.c index 6648c1c90e19..6f67cc09c2b5 100644 --- a/drivers/target/target_core_rd.c +++ b/drivers/target/target_core_rd.c @@ -643,14 +643,14 @@ static void rd_free_prot(struct se_device *dev) rd_release_prot_space(rd_dev); } -static struct sbc_ops rd_sbc_ops = { +static struct exec_cmd_ops rd_exec_cmd_ops = { .execute_rw = rd_execute_rw, }; static sense_reason_t rd_parse_cdb(struct se_cmd *cmd) { - return sbc_parse_cdb(cmd, &rd_sbc_ops); + return sbc_parse_cdb(cmd, &rd_exec_cmd_ops); } static const struct target_backend_ops rd_mcp_ops = { diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c index 7536ca797606..6a02561cc20c 100644 --- a/drivers/target/target_core_sbc.c +++ b/drivers/target/target_core_sbc.c @@ -192,7 +192,7 @@ EXPORT_SYMBOL(sbc_get_write_same_sectors); static sense_reason_t sbc_execute_write_same_unmap(struct se_cmd *cmd) { - struct sbc_ops *ops = cmd->protocol_data; + struct exec_cmd_ops *ops = cmd->protocol_data; sector_t nolb = sbc_get_write_same_sectors(cmd); sense_reason_t ret; @@ -271,7 +271,8 @@ static inline unsigned long long transport_lba_64(unsigned char *cdb) } static sense_reason_t -sbc_setup_write_same(struct se_cmd *cmd, unsigned char flags, struct sbc_ops *ops) +sbc_setup_write_same(struct se_cmd *cmd, unsigned char flags, + struct exec_cmd_ops *ops) { struct se_device *dev = cmd->se_dev; sector_t end_lba = dev->transport->get_blocks(dev) + 1; @@ -340,7 +341,7 @@ sbc_setup_write_same(struct se_cmd *cmd, unsigned char flags, struct sbc_ops *op static sense_reason_t sbc_execute_rw(struct se_cmd *cmd) { - struct sbc_ops *ops = cmd->protocol_data; + struct exec_cmd_ops *ops = cmd->protocol_data; return ops->execute_rw(cmd, cmd->t_data_sg, cmd->t_data_nents, cmd->data_direction); @@ -566,7 +567,7 @@ out: static sense_reason_t sbc_compare_and_write(struct se_cmd *cmd) { - struct sbc_ops *ops = cmd->protocol_data; + struct exec_cmd_ops *ops = cmd->protocol_data; struct se_device *dev = cmd->se_dev; sense_reason_t ret; int rc; @@ -764,7 +765,7 @@ sbc_check_dpofua(struct se_device *dev, struct se_cmd *cmd, unsigned char *cdb) } sense_reason_t -sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops) +sbc_parse_cdb(struct se_cmd *cmd, struct exec_cmd_ops *ops) { struct se_device *dev = cmd->se_dev; unsigned char *cdb = cmd->t_task_cdb; @@ -1076,7 +1077,7 @@ EXPORT_SYMBOL(sbc_get_device_type); static sense_reason_t sbc_execute_unmap(struct se_cmd *cmd) { - struct sbc_ops *ops = cmd->protocol_data; + struct exec_cmd_ops *ops = cmd->protocol_data; struct se_device *dev = cmd->se_dev; unsigned char *buf, *ptr = NULL; sector_t lba; diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c index fcc7b10a7ae3..00d34616df5d 100644 --- a/drivers/target/target_core_spc.c +++ b/drivers/target/target_core_spc.c @@ -1431,7 +1431,7 @@ static struct target_opcode_descriptor tcm_opcode_write_verify16 = { static bool tcm_is_ws_enabled(struct se_cmd *cmd) { - struct sbc_ops *ops = cmd->protocol_data; + struct exec_cmd_ops *ops = cmd->protocol_data; struct se_device *dev = cmd->se_dev; return (dev->dev_attrib.emulate_tpws && !!ops->execute_unmap) || @@ -1544,7 +1544,7 @@ static struct target_opcode_descriptor tcm_opcode_sync_cache16 = { static bool tcm_is_unmap_enabled(struct se_cmd *cmd) { - struct sbc_ops *ops = cmd->protocol_data; + struct exec_cmd_ops *ops = cmd->protocol_data; struct se_device *dev = cmd->se_dev; return ops->execute_unmap && dev->dev_attrib.emulate_tpu; diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h index a3c193df25b3..c5df78959532 100644 --- a/include/target/target_core_backend.h +++ b/include/target/target_core_backend.h @@ -62,7 +62,7 @@ struct target_backend_ops { struct configfs_attribute **tb_dev_action_attrs; }; -struct sbc_ops { +struct exec_cmd_ops { sense_reason_t (*execute_rw)(struct se_cmd *cmd, struct scatterlist *, u32, enum dma_data_direction); sense_reason_t (*execute_sync_cache)(struct se_cmd *cmd); @@ -86,7 +86,7 @@ sense_reason_t spc_emulate_report_luns(struct se_cmd *cmd); sense_reason_t spc_emulate_inquiry_std(struct se_cmd *, unsigned char *); sense_reason_t spc_emulate_evpd_83(struct se_cmd *, unsigned char *); -sense_reason_t sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops); +sense_reason_t sbc_parse_cdb(struct se_cmd *cmd, struct exec_cmd_ops *ops); u32 sbc_get_device_rev(struct se_device *dev); u32 sbc_get_device_type(struct se_device *dev); sector_t sbc_get_write_same_sectors(struct se_cmd *cmd); -- cgit v1.2.3 From 53062ace0b6e47f17cae2db453858c8a369a2fe4 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 7 Apr 2023 15:05:48 -0500 Subject: scsi: target: Allow backends to hook into PR handling For the cases where you want to export a device to a VM via a single I_T nexus and want to passthrough the PR handling to the physical/real device you have to use pscsi or tcmu. Both are good for specific uses however for the case where you want good performance, and are not using SCSI devices directly (using DM/MD RAID or multipath devices) then we are out of luck. The following patches allow iblock to mimimally hook into the LIO PR code and then pass the PR handling to the physical device. Note that like with the tcmu an pscsi cases it's only supported when you export the device via one I_T nexus. This patch adds the initial LIO callouts. The next patch will modify iblock. Signed-off-by: Mike Christie Link: https://lore.kernel.org/r/20230407200551.12660-16-michael.christie@oracle.com Reviewed-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- drivers/target/target_core_pr.c | 62 +++++++++++++++++++++++++++++++++++- include/target/target_core_backend.h | 4 +++ 2 files changed, 65 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c index 1493b1d01194..e16ef7d676af 100644 --- a/drivers/target/target_core_pr.c +++ b/drivers/target/target_core_pr.c @@ -3538,6 +3538,25 @@ out_put_pr_reg: return ret; } +static sense_reason_t +target_try_pr_out_pt(struct se_cmd *cmd, u8 sa, u64 res_key, u64 sa_res_key, + u8 type, bool aptpl, bool all_tg_pt, bool spec_i_pt) +{ + struct exec_cmd_ops *ops = cmd->protocol_data; + + if (!cmd->se_sess || !cmd->se_lun) { + pr_err("SPC-3 PR: se_sess || struct se_lun is NULL!\n"); + return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; + } + + if (!ops->execute_pr_out) { + pr_err("SPC-3 PR: Device has been configured for PR passthrough but it's not supported by the backend.\n"); + return TCM_UNSUPPORTED_SCSI_OPCODE; + } + + return ops->execute_pr_out(cmd, sa, res_key, sa_res_key, type, aptpl); +} + /* * See spc4r17 section 6.14 Table 170 */ @@ -3641,6 +3660,12 @@ target_scsi3_emulate_pr_out(struct se_cmd *cmd) return TCM_PARAMETER_LIST_LENGTH_ERROR; } + if (dev->transport_flags & TRANSPORT_FLAG_PASSTHROUGH_PGR) { + ret = target_try_pr_out_pt(cmd, sa, res_key, sa_res_key, type, + aptpl, all_tg_pt, spec_i_pt); + goto done; + } + /* * (core_scsi3_emulate_pro_* function parameters * are defined by spc4r17 Table 174: @@ -3682,6 +3707,7 @@ target_scsi3_emulate_pr_out(struct se_cmd *cmd) return TCM_INVALID_CDB_FIELD; } +done: if (!ret) target_complete_cmd(cmd, SAM_STAT_GOOD); return ret; @@ -4039,9 +4065,37 @@ core_scsi3_pri_read_full_status(struct se_cmd *cmd) return 0; } +static sense_reason_t target_try_pr_in_pt(struct se_cmd *cmd, u8 sa) +{ + struct exec_cmd_ops *ops = cmd->protocol_data; + unsigned char *buf; + sense_reason_t ret; + + if (cmd->data_length < 8) { + pr_err("PRIN SA SCSI Data Length: %u too small\n", + cmd->data_length); + return TCM_INVALID_CDB_FIELD; + } + + if (!ops->execute_pr_in) { + pr_err("SPC-3 PR: Device has been configured for PR passthrough but it's not supported by the backend.\n"); + return TCM_UNSUPPORTED_SCSI_OPCODE; + } + + buf = transport_kmap_data_sg(cmd); + if (!buf) + return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; + + ret = ops->execute_pr_in(cmd, sa, buf); + + transport_kunmap_data_sg(cmd); + return ret; +} + sense_reason_t target_scsi3_emulate_pr_in(struct se_cmd *cmd) { + u8 sa = cmd->t_task_cdb[1] & 0x1f; sense_reason_t ret; /* @@ -4060,7 +4114,12 @@ target_scsi3_emulate_pr_in(struct se_cmd *cmd) return TCM_RESERVATION_CONFLICT; } - switch (cmd->t_task_cdb[1] & 0x1f) { + if (cmd->se_dev->transport_flags & TRANSPORT_FLAG_PASSTHROUGH_PGR) { + ret = target_try_pr_in_pt(cmd, sa); + goto done; + } + + switch (sa) { case PRI_READ_KEYS: ret = core_scsi3_pri_read_keys(cmd); break; @@ -4079,6 +4138,7 @@ target_scsi3_emulate_pr_in(struct se_cmd *cmd) return TCM_INVALID_CDB_FIELD; } +done: if (!ret) target_complete_cmd(cmd, SAM_STAT_GOOD); return ret; diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h index c5df78959532..739df993aa5e 100644 --- a/include/target/target_core_backend.h +++ b/include/target/target_core_backend.h @@ -69,6 +69,10 @@ struct exec_cmd_ops { sense_reason_t (*execute_write_same)(struct se_cmd *cmd); sense_reason_t (*execute_unmap)(struct se_cmd *cmd, sector_t lba, sector_t nolb); + sense_reason_t (*execute_pr_out)(struct se_cmd *cmd, u8 sa, u64 key, + u64 sa_key, u8 type, bool aptpl); + sense_reason_t (*execute_pr_in)(struct se_cmd *cmd, u8 sa, + unsigned char *param_data); }; int transport_backend_register(const struct target_backend_ops *); -- cgit v1.2.3 From d9b3275bddd58f1e61171483c3625b5bd0841b71 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 7 Apr 2023 15:05:49 -0500 Subject: scsi: target: Pass struct target_opcode_descriptor to enabled The iblock pr_ops support does not support commands that require port or I_T Nexus info. This adds a struct target_opcode_descriptor as an argument to the enabled callout so we can still have the common tcm_is_pr_enabled and tcm_is_scsi2_reservations_enabled functions and also determine if the command is supported based on the command and service action and device settings. Signed-off-by: Mike Christie Link: https://lore.kernel.org/r/20230407200551.12660-17-michael.christie@oracle.com Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- drivers/target/target_core_spc.c | 40 ++++++++++++++++++++++++--------------- include/target/target_core_base.h | 3 ++- 2 files changed, 27 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c index 00d34616df5d..caf8d1325007 100644 --- a/drivers/target/target_core_spc.c +++ b/drivers/target/target_core_spc.c @@ -1429,7 +1429,8 @@ static struct target_opcode_descriptor tcm_opcode_write_verify16 = { .update_usage_bits = set_dpofua_usage_bits, }; -static bool tcm_is_ws_enabled(struct se_cmd *cmd) +static bool tcm_is_ws_enabled(struct target_opcode_descriptor *descr, + struct se_cmd *cmd) { struct exec_cmd_ops *ops = cmd->protocol_data; struct se_device *dev = cmd->se_dev; @@ -1456,7 +1457,8 @@ static struct target_opcode_descriptor tcm_opcode_write_same32 = { .update_usage_bits = set_dpofua_usage_bits32, }; -static bool tcm_is_caw_enabled(struct se_cmd *cmd) +static bool tcm_is_caw_enabled(struct target_opcode_descriptor *descr, + struct se_cmd *cmd) { struct se_device *dev = cmd->se_dev; @@ -1496,7 +1498,8 @@ static struct target_opcode_descriptor tcm_opcode_read_capacity16 = { 0xff, 0xff, 0x00, SCSI_CONTROL_MASK}, }; -static bool tcm_is_rep_ref_enabled(struct se_cmd *cmd) +static bool tcm_is_rep_ref_enabled(struct target_opcode_descriptor *descr, + struct se_cmd *cmd) { struct se_device *dev = cmd->se_dev; @@ -1507,7 +1510,6 @@ static bool tcm_is_rep_ref_enabled(struct se_cmd *cmd) } spin_unlock(&dev->t10_alua.lba_map_lock); return true; - } static struct target_opcode_descriptor tcm_opcode_read_report_refferals = { @@ -1542,7 +1544,8 @@ static struct target_opcode_descriptor tcm_opcode_sync_cache16 = { 0xff, 0xff, SCSI_GROUP_NUMBER_MASK, SCSI_CONTROL_MASK}, }; -static bool tcm_is_unmap_enabled(struct se_cmd *cmd) +static bool tcm_is_unmap_enabled(struct target_opcode_descriptor *descr, + struct se_cmd *cmd) { struct exec_cmd_ops *ops = cmd->protocol_data; struct se_device *dev = cmd->se_dev; @@ -1664,7 +1667,8 @@ static struct target_opcode_descriptor tcm_opcode_pri_read_resrv = { 0xff, SCSI_CONTROL_MASK}, }; -static bool tcm_is_pr_enabled(struct se_cmd *cmd) +static bool tcm_is_pr_enabled(struct target_opcode_descriptor *descr, + struct se_cmd *cmd) { struct se_device *dev = cmd->se_dev; @@ -1793,7 +1797,9 @@ static struct target_opcode_descriptor tcm_opcode_pro_register_move = { .enabled = tcm_is_pr_enabled, }; -static bool tcm_is_scsi2_reservations_enabled(struct se_cmd *cmd) +static bool +tcm_is_scsi2_reservations_enabled(struct target_opcode_descriptor *descr, + struct se_cmd *cmd) { struct se_device *dev = cmd->se_dev; @@ -1854,7 +1860,8 @@ static struct target_opcode_descriptor tcm_opcode_inquiry = { 0xff, SCSI_CONTROL_MASK}, }; -static bool tcm_is_3pc_enabled(struct se_cmd *cmd) +static bool tcm_is_3pc_enabled(struct target_opcode_descriptor *descr, + struct se_cmd *cmd) { struct se_device *dev = cmd->se_dev; @@ -1915,8 +1922,8 @@ static struct target_opcode_descriptor tcm_opcode_report_target_pgs = { 0xff, 0xff, 0x00, SCSI_CONTROL_MASK}, }; - -static bool spc_rsoc_enabled(struct se_cmd *cmd) +static bool spc_rsoc_enabled(struct target_opcode_descriptor *descr, + struct se_cmd *cmd) { struct se_device *dev = cmd->se_dev; @@ -1936,7 +1943,8 @@ static struct target_opcode_descriptor tcm_opcode_report_supp_opcodes = { .enabled = spc_rsoc_enabled, }; -static bool tcm_is_set_tpg_enabled(struct se_cmd *cmd) +static bool tcm_is_set_tpg_enabled(struct target_opcode_descriptor *descr, + struct se_cmd *cmd) { struct t10_alua_tg_pt_gp *l_tg_pt_gp; struct se_lun *l_lun = cmd->se_lun; @@ -2123,7 +2131,7 @@ spc_rsoc_get_descr(struct se_cmd *cmd, struct target_opcode_descriptor **opcode) if (descr->serv_action_valid) return TCM_INVALID_CDB_FIELD; - if (!descr->enabled || descr->enabled(cmd)) + if (!descr->enabled || descr->enabled(descr, cmd)) *opcode = descr; break; case 0x2: @@ -2137,7 +2145,8 @@ spc_rsoc_get_descr(struct se_cmd *cmd, struct target_opcode_descriptor **opcode) */ if (descr->serv_action_valid && descr->service_action == requested_sa) { - if (!descr->enabled || descr->enabled(cmd)) + if (!descr->enabled || descr->enabled(descr, + cmd)) *opcode = descr; } else if (!descr->serv_action_valid) return TCM_INVALID_CDB_FIELD; @@ -2150,7 +2159,8 @@ spc_rsoc_get_descr(struct se_cmd *cmd, struct target_opcode_descriptor **opcode) * be returned in the one_command parameter data format. */ if (descr->service_action == requested_sa) - if (!descr->enabled || descr->enabled(cmd)) + if (!descr->enabled || descr->enabled(descr, + cmd)) *opcode = descr; break; } @@ -2207,7 +2217,7 @@ spc_emulate_report_supp_op_codes(struct se_cmd *cmd) for (i = 0; i < ARRAY_SIZE(tcm_supported_opcodes); i++) { descr = tcm_supported_opcodes[i]; - if (descr->enabled && !descr->enabled(cmd)) + if (descr->enabled && !descr->enabled(descr, cmd)) continue; response_length += spc_rsoc_encode_command_descriptor( diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 12c9ba16217e..04646b3dbf75 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -878,7 +878,8 @@ struct target_opcode_descriptor { u8 specific_timeout; u16 nominal_timeout; u16 recommended_timeout; - bool (*enabled)(struct se_cmd *cmd); + bool (*enabled)(struct target_opcode_descriptor *descr, + struct se_cmd *cmd); void (*update_usage_bits)(u8 *usage_bits, struct se_device *dev); u8 usage_bits[]; -- cgit v1.2.3 From eca2040972b411ec27483bf75dc8b84e730e88ff Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 11 May 2023 03:13:34 +0200 Subject: scsi: block: ioprio: Clean up interface definition The I/O priority user interface defines the 16-bits ioprio values as the combination of the upper 3-bits for an I/O priority class and the lower 13-bits as priority data. However, the kernel only uses the lower 3-bits of the priority data to define priority levels for the RT and BE priority classes. The data part of an ioprio value is completely ignored for the IDLE and NONE classes. This is enforced by checks done in ioprio_check_cap(), which is called for all paths that allow defining an I/O priority for I/Os: the per-context ioprio_set() system call, aio interface and io_uring interface. Clarify this fact in the uapi ioprio.h header file and introduce the IOPRIO_PRIO_LEVEL_MASK and IOPRIO_PRIO_LEVEL() macros for users to define and get priority levels in an ioprio value. The coarser macro IOPRIO_PRIO_DATA() is retained for backward compatibility with old applications already using it. There is no functional change introduced with this. In-kernel users of the IOPRIO_PRIO_DATA() macro which are explicitly handling I/O priority data as a priority level are modified to use the new IOPRIO_PRIO_LEVEL() macro without any functional change. Since f2fs is the only user of this macro not explicitly using that value as a priority level, it is left unchanged. Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Signed-off-by: Niklas Cassel Link: https://lore.kernel.org/r/20230511011356.227789-2-nks@flawful.org Signed-off-by: Martin K. Petersen --- block/bfq-iosched.c | 8 ++++---- block/ioprio.c | 6 +++--- include/uapi/linux/ioprio.h | 19 ++++++++++++++----- 3 files changed, 21 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 3164e3177965..3067b75f3fd0 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -5524,16 +5524,16 @@ bfq_set_next_ioprio_data(struct bfq_queue *bfqq, struct bfq_io_cq *bic) bfqq->new_ioprio_class = task_nice_ioclass(tsk); break; case IOPRIO_CLASS_RT: - bfqq->new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio); + bfqq->new_ioprio = IOPRIO_PRIO_LEVEL(bic->ioprio); bfqq->new_ioprio_class = IOPRIO_CLASS_RT; break; case IOPRIO_CLASS_BE: - bfqq->new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio); + bfqq->new_ioprio = IOPRIO_PRIO_LEVEL(bic->ioprio); bfqq->new_ioprio_class = IOPRIO_CLASS_BE; break; case IOPRIO_CLASS_IDLE: bfqq->new_ioprio_class = IOPRIO_CLASS_IDLE; - bfqq->new_ioprio = 7; + bfqq->new_ioprio = IOPRIO_NR_LEVELS - 1; break; } @@ -5830,7 +5830,7 @@ static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd, struct bfq_io_cq *bic, bool respawn) { - const int ioprio = IOPRIO_PRIO_DATA(bic->ioprio); + const int ioprio = IOPRIO_PRIO_LEVEL(bic->ioprio); const int ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio); struct bfq_queue **async_bfqq = NULL; struct bfq_queue *bfqq; diff --git a/block/ioprio.c b/block/ioprio.c index 32a456b45804..f0d9e818abc5 100644 --- a/block/ioprio.c +++ b/block/ioprio.c @@ -33,7 +33,7 @@ int ioprio_check_cap(int ioprio) { int class = IOPRIO_PRIO_CLASS(ioprio); - int data = IOPRIO_PRIO_DATA(ioprio); + int level = IOPRIO_PRIO_LEVEL(ioprio); switch (class) { case IOPRIO_CLASS_RT: @@ -49,13 +49,13 @@ int ioprio_check_cap(int ioprio) fallthrough; /* rt has prio field too */ case IOPRIO_CLASS_BE: - if (data >= IOPRIO_NR_LEVELS || data < 0) + if (level >= IOPRIO_NR_LEVELS) return -EINVAL; break; case IOPRIO_CLASS_IDLE: break; case IOPRIO_CLASS_NONE: - if (data) + if (level) return -EINVAL; break; default: diff --git a/include/uapi/linux/ioprio.h b/include/uapi/linux/ioprio.h index f70f2596a6bf..4444b4e4fdad 100644 --- a/include/uapi/linux/ioprio.h +++ b/include/uapi/linux/ioprio.h @@ -17,7 +17,7 @@ ((data) & IOPRIO_PRIO_MASK)) /* - * These are the io priority groups as implemented by the BFQ and mq-deadline + * These are the io priority classes as implemented by the BFQ and mq-deadline * schedulers. RT is the realtime class, it always gets premium service. For * ATA disks supporting NCQ IO priority, RT class IOs will be processed using * high priority NCQ commands. BE is the best-effort scheduling class, the @@ -32,11 +32,20 @@ enum { }; /* - * The RT and BE priority classes both support up to 8 priority levels. + * The RT and BE priority classes both support up to 8 priority levels that + * can be specified using the lower 3-bits of the priority data. */ -#define IOPRIO_NR_LEVELS 8 -#define IOPRIO_BE_NR IOPRIO_NR_LEVELS +#define IOPRIO_LEVEL_NR_BITS 3 +#define IOPRIO_NR_LEVELS (1 << IOPRIO_LEVEL_NR_BITS) +#define IOPRIO_LEVEL_MASK (IOPRIO_NR_LEVELS - 1) +#define IOPRIO_PRIO_LEVEL(ioprio) ((ioprio) & IOPRIO_LEVEL_MASK) +#define IOPRIO_BE_NR IOPRIO_NR_LEVELS + +/* + * Possible values for the "which" argument of the ioprio_get() and + * ioprio_set() system calls (see "man ioprio_set"). + */ enum { IOPRIO_WHO_PROCESS = 1, IOPRIO_WHO_PGRP, @@ -44,7 +53,7 @@ enum { }; /* - * Fallback BE priority level. + * Fallback BE class priority level. */ #define IOPRIO_NORM 4 #define IOPRIO_BE_NORM IOPRIO_NORM -- cgit v1.2.3 From 6c913257226a25879bfd6226e0ee265e98904ce6 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 11 May 2023 03:13:35 +0200 Subject: scsi: block: Introduce ioprio hints I/O priorities currently only use 6-bits of the 16-bits ioprio value: the 3-upper bits are used to define up to 8 priority classes (4 of which are valid) and the 3 lower bits of the value are used to define a priority level for the real-time and best-effort class. The remaining 10-bits between the I/O priority class and level are unused, and in fact, cannot be used by the user as doing so would either result in the value being completely ignored, or in an error returned by ioprio_check_cap(). Use these 10-bits of an ioprio value to allow a user to specify I/O hints. An I/O hint is defined as a 10-bitsvalue, allowing up to 1023 different hints to be specified, with the value 0 being reserved as the "no hint" case. An I/O hint can apply to any I/O that specifies a valid priority class other than NONE, regardless of the I/O priority level specified. To do so, the macros IOPRIO_PRIO_HINT() and IOPRIO_PRIO_VALUE_HINT() are introduced in include/uapi/linux/ioprio.h to respectively allow a user to get and set a hint in an ioprio value. To support the ATA and SCSI command duration limits feature, 7 hints are defined: IOPRIO_HINT_DEV_DURATION_LIMIT_1 to IOPRIO_HINT_DEV_DURATION_LIMIT_7, allowing a user to specify which command duration limit descriptor should be applied to the commands serving an I/O. Specifying these hints has for now no effect whatsoever if the target block devices do not support the command duration limits feature. However, in the future, block I/O schedulers can be modified to optimize I/O issuing order based on these hints, even for devices that do not support the command duration limits feature. Given that the 7 duration limits hints defined have no effect on any block layer component, the actual definition of the duration limits implied by these hints remains at the device level. Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Signed-off-by: Niklas Cassel Link: https://lore.kernel.org/r/20230511011356.227789-3-nks@flawful.org Signed-off-by: Martin K. Petersen --- include/uapi/linux/ioprio.h | 49 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/ioprio.h b/include/uapi/linux/ioprio.h index 4444b4e4fdad..4c4806e8230b 100644 --- a/include/uapi/linux/ioprio.h +++ b/include/uapi/linux/ioprio.h @@ -58,4 +58,53 @@ enum { #define IOPRIO_NORM 4 #define IOPRIO_BE_NORM IOPRIO_NORM +/* + * The 10 bits between the priority class and the priority level are used to + * optionally define I/O hints for any combination of I/O priority class and + * level. Depending on the kernel configuration, I/O scheduler being used and + * the target I/O device being used, hints can influence how I/Os are processed + * without affecting the I/O scheduling ordering defined by the I/O priority + * class and level. + */ +#define IOPRIO_HINT_SHIFT IOPRIO_LEVEL_NR_BITS +#define IOPRIO_HINT_NR_BITS 10 +#define IOPRIO_NR_HINTS (1 << IOPRIO_HINT_NR_BITS) +#define IOPRIO_HINT_MASK (IOPRIO_NR_HINTS - 1) +#define IOPRIO_PRIO_HINT(ioprio) \ + (((ioprio) >> IOPRIO_HINT_SHIFT) & IOPRIO_HINT_MASK) + +/* + * Alternate macro for IOPRIO_PRIO_VALUE() to define an I/O priority with + * a class, level and hint. + */ +#define IOPRIO_PRIO_VALUE_HINT(class, level, hint) \ + ((((class) & IOPRIO_CLASS_MASK) << IOPRIO_CLASS_SHIFT) | \ + (((hint) & IOPRIO_HINT_MASK) << IOPRIO_HINT_SHIFT) | \ + ((level) & IOPRIO_LEVEL_MASK)) + +/* + * I/O hints. + */ +enum { + /* No hint */ + IOPRIO_HINT_NONE = 0, + + /* + * Device command duration limits: indicate to the device a desired + * duration limit for the commands that will be used to process an I/O. + * These will currently only be effective for SCSI and ATA devices that + * support the command duration limits feature. If this feature is + * enabled, then the commands issued to the device to process an I/O with + * one of these hints set will have the duration limit index (dld field) + * set to the value of the hint. + */ + IOPRIO_HINT_DEV_DURATION_LIMIT_1 = 1, + IOPRIO_HINT_DEV_DURATION_LIMIT_2 = 2, + IOPRIO_HINT_DEV_DURATION_LIMIT_3 = 3, + IOPRIO_HINT_DEV_DURATION_LIMIT_4 = 4, + IOPRIO_HINT_DEV_DURATION_LIMIT_5 = 5, + IOPRIO_HINT_DEV_DURATION_LIMIT_6 = 6, + IOPRIO_HINT_DEV_DURATION_LIMIT_7 = 7, +}; + #endif /* _UAPI_LINUX_IOPRIO_H */ -- cgit v1.2.3 From dffc480d2df1772d6092f46f2b4c5e0de941bd47 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 11 May 2023 03:13:36 +0200 Subject: scsi: block: Introduce BLK_STS_DURATION_LIMIT Introduce the new block I/O status BLK_STS_DURATION_LIMIT for LLDDs to report command that failed due to a command duration limit being exceeded. This new status is mapped to the ETIME error code to allow users to differentiate "soft" duration limit failures from other more serious hardware related errors. If we compare BLK_STS_DURATION_LIMIT with BLK_STS_TIMEOUT: -BLK_STS_DURATION_LIMIT means that the drive gave a reply indicating that the command duration limit was exceeded before the command could be completed. This I/O status is mapped to ETIME for user space. -BLK_STS_TIMEOUT means that the drive never gave a reply at all. This I/O status is mapped to ETIMEDOUT for user space. Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Co-developed-by: Niklas Cassel Signed-off-by: Niklas Cassel Link: https://lore.kernel.org/r/20230511011356.227789-4-nks@flawful.org Signed-off-by: Martin K. Petersen --- block/blk-core.c | 3 +++ include/linux/blk_types.h | 6 ++++++ 2 files changed, 9 insertions(+) (limited to 'include') diff --git a/block/blk-core.c b/block/blk-core.c index 00c74330fa92..04ad13ec6ead 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -170,6 +170,9 @@ static const struct { [BLK_STS_ZONE_OPEN_RESOURCE] = { -ETOOMANYREFS, "open zones exceeded" }, [BLK_STS_ZONE_ACTIVE_RESOURCE] = { -EOVERFLOW, "active zones exceeded" }, + /* Command duration limit device-side timeout */ + [BLK_STS_DURATION_LIMIT] = { -ETIME, "duration limit exceeded" }, + /* everything else not covered above: */ [BLK_STS_IOERR] = { -EIO, "I/O" }, }; diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 740afe80f297..dfdcd218aaac 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -171,6 +171,12 @@ typedef u16 blk_short_t; */ #define BLK_STS_OFFLINE ((__force blk_status_t)17) +/* + * BLK_STS_DURATION_LIMIT is returned from the driver when the target device + * aborted the command because it exceeded one of its Command Duration Limits. + */ +#define BLK_STS_DURATION_LIMIT ((__force blk_status_t)18) + /** * blk_path_error - returns true if error may be path related * @error: status the request was completed with -- cgit v1.2.3 From 3d848ca1ebc8d8864f25bd461914c93eff82a2d2 Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Thu, 11 May 2023 03:13:37 +0200 Subject: scsi: core: Allow libata to complete successful commands via EH In SCSI, we get the sense data as part of the completion, for ATA however, we need to fetch the sense data as an extra step. For an aborted ATA command the sense data is fetched via libata's ->eh_strategy_handler(). For Command Duration Limits policy 0xD: The device shall complete the command without error with the additional sense code set to DATA CURRENTLY UNAVAILABLE. In order to handle this policy in libata, we intend to send a successful command via SCSI EH, and let libata's ->eh_strategy_handler() fetch the sense data for the good command. This is similar to how we handle an aborted ATA command, just that we need to read the Successful NCQ Commands log instead of the NCQ Command Error log. When we get a SATA completion with successful commands, ATA_SENSE will be set, indicating that some commands in the completion have sense data. The sense_valid bitmask in the Sense Data for Successful NCQ Commands log will inform exactly which commands that had sense data, which might be a subset of all the commands that was completed in the same completion. (Yet all will have ATA_SENSE set, since the status is per completion.) The successful commands that have e.g. a "DATA CURRENTLY UNAVAILABLE" sense data will have a SCSI ML byte set, so scsi_eh_flush_done_q() will not set the scmd->result to DID_TIME_OUT for these commands. However, the successful commands that did not have sense data, must not get their result marked as DID_TIME_OUT by SCSI EH. Add a new flag SCMD_FORCE_EH_SUCCESS, which tells SCSI EH to not mark a command as DID_TIME_OUT, even if it has scmd->result == SAM_STAT_GOOD. This will be used by libata in a subsequent commit. Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Niklas Cassel Link: https://lore.kernel.org/r/20230511011356.227789-5-nks@flawful.org Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_error.c | 3 ++- include/scsi/scsi_cmnd.h | 5 +++++ 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 3ec8bfd4090f..8b7d227bfe1c 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -2165,7 +2165,8 @@ void scsi_eh_flush_done_q(struct list_head *done_q) * scsi_eh_get_sense), scmd->result is already * set, do not set DID_TIME_OUT. */ - if (!scmd->result) + if (!scmd->result && + !(scmd->flags & SCMD_FORCE_EH_SUCCESS)) scmd->result |= (DID_TIME_OUT << 16); SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index c2cb5f69635c..526def14e7fb 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -52,6 +52,11 @@ struct scsi_pointer { #define SCMD_TAGGED (1 << 0) #define SCMD_INITIALIZED (1 << 1) #define SCMD_LAST (1 << 2) +/* + * libata uses SCSI EH to fetch sense data for successful commands. + * SCSI EH should not overwrite scmd->result when SCMD_FORCE_EH_SUCCESS is set. + */ +#define SCMD_FORCE_EH_SUCCESS (1 << 3) #define SCMD_FAIL_IF_RECOVERING (1 << 4) /* flags preserved across unprep / reprep */ #define SCMD_PRESERVED_FLAGS (SCMD_INITIALIZED | SCMD_FAIL_IF_RECOVERING) -- cgit v1.2.3 From a6cdc35fab0d813d54744abe2af07d6c49c07d6e Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 11 May 2023 03:13:39 +0200 Subject: scsi: core: Support retrieving sub-pages of mode pages Allow scsi_mode_sense() to retrieve sub-pages of mode pages by adding the subpage argument. Change all the current caller sites to specify the subpage 0. Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Reviewed-by: Bart Van Assche Signed-off-by: Niklas Cassel Link: https://lore.kernel.org/r/20230511011356.227789-7-nks@flawful.org Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_lib.c | 4 +++- drivers/scsi/scsi_transport_sas.c | 2 +- drivers/scsi/sd.c | 9 ++++----- drivers/scsi/sr.c | 2 +- include/scsi/scsi_device.h | 8 ++++---- 5 files changed, 13 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index fac9c31161d2..633c4e8af830 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -2144,6 +2144,7 @@ EXPORT_SYMBOL_GPL(scsi_mode_select); * @sdev: SCSI device to be queried * @dbd: set to prevent mode sense from returning block descriptors * @modepage: mode page being requested + * @subpage: sub-page of the mode page being requested * @buffer: request buffer (may not be smaller than eight bytes) * @len: length of request buffer. * @timeout: command timeout @@ -2155,7 +2156,7 @@ EXPORT_SYMBOL_GPL(scsi_mode_select); * Returns zero if successful, or a negative error number on failure */ int -scsi_mode_sense(struct scsi_device *sdev, int dbd, int modepage, +scsi_mode_sense(struct scsi_device *sdev, int dbd, int modepage, int subpage, unsigned char *buffer, int len, int timeout, int retries, struct scsi_mode_data *data, struct scsi_sense_hdr *sshdr) { @@ -2175,6 +2176,7 @@ scsi_mode_sense(struct scsi_device *sdev, int dbd, int modepage, dbd = sdev->set_dbd_for_ms ? 8 : dbd; cmd[1] = dbd & 0x18; /* allows DBD and LLBA bits */ cmd[2] = modepage; + cmd[3] = subpage; sshdr = exec_args.sshdr; diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c index 74b99f2b0b74..d704c484a251 100644 --- a/drivers/scsi/scsi_transport_sas.c +++ b/drivers/scsi/scsi_transport_sas.c @@ -1245,7 +1245,7 @@ int sas_read_port_mode_page(struct scsi_device *sdev) if (!buffer) return -ENOMEM; - error = scsi_mode_sense(sdev, 1, 0x19, buffer, BUF_SIZE, 30*HZ, 3, + error = scsi_mode_sense(sdev, 1, 0x19, 0, buffer, BUF_SIZE, 30*HZ, 3, &mode_data, NULL); if (error) diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 1624d528aa1f..cdcef1b651c1 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -183,7 +183,7 @@ cache_type_store(struct device *dev, struct device_attribute *attr, return count; } - if (scsi_mode_sense(sdp, 0x08, 8, buffer, sizeof(buffer), SD_TIMEOUT, + if (scsi_mode_sense(sdp, 0x08, 8, 0, buffer, sizeof(buffer), SD_TIMEOUT, sdkp->max_retries, &data, NULL)) return -EINVAL; len = min_t(size_t, sizeof(buffer), data.length - data.header_length - @@ -2609,9 +2609,8 @@ sd_do_mode_sense(struct scsi_disk *sdkp, int dbd, int modepage, if (sdkp->device->use_10_for_ms && len < 8) len = 8; - return scsi_mode_sense(sdkp->device, dbd, modepage, buffer, len, - SD_TIMEOUT, sdkp->max_retries, data, - sshdr); + return scsi_mode_sense(sdkp->device, dbd, modepage, 0, buffer, len, + SD_TIMEOUT, sdkp->max_retries, data, sshdr); } /* @@ -2868,7 +2867,7 @@ static void sd_read_app_tag_own(struct scsi_disk *sdkp, unsigned char *buffer) if (sdkp->protection_type == 0) return; - res = scsi_mode_sense(sdp, 1, 0x0a, buffer, 36, SD_TIMEOUT, + res = scsi_mode_sense(sdp, 1, 0x0a, 0, buffer, 36, SD_TIMEOUT, sdkp->max_retries, &data, &sshdr); if (res < 0 || !data.header_length || diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 12869e6d4ebd..cd5b08689c1a 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -825,7 +825,7 @@ static int get_capabilities(struct scsi_cd *cd) scsi_test_unit_ready(cd->device, SR_TIMEOUT, MAX_RETRIES, &sshdr); /* ask for mode page 0x2a */ - rc = scsi_mode_sense(cd->device, 0, 0x2a, buffer, ms_len, + rc = scsi_mode_sense(cd->device, 0, 0x2a, 0, buffer, ms_len, SR_TIMEOUT, 3, &data, NULL); if (rc < 0 || data.length > ms_len || diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index f10a008e5bfa..c146cc807d44 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -421,10 +421,10 @@ extern int scsi_track_queue_full(struct scsi_device *, int); extern int scsi_set_medium_removal(struct scsi_device *, char); -extern int scsi_mode_sense(struct scsi_device *sdev, int dbd, int modepage, - unsigned char *buffer, int len, int timeout, - int retries, struct scsi_mode_data *data, - struct scsi_sense_hdr *); +int scsi_mode_sense(struct scsi_device *sdev, int dbd, int modepage, + int subpage, unsigned char *buffer, int len, int timeout, + int retries, struct scsi_mode_data *data, + struct scsi_sense_hdr *); extern int scsi_mode_select(struct scsi_device *sdev, int pf, int sp, unsigned char *buffer, int len, int timeout, int retries, struct scsi_mode_data *data, -- cgit v1.2.3 From 152e52fb6ff180e97d64585e87fea44c49b8bda8 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 11 May 2023 03:13:40 +0200 Subject: scsi: core: Support Service Action in scsi_report_opcode() The REPORT_SUPPORTED_OPERATION_CODES command allows checking for support of commands that have the same opcode but different service actions, such as READ 32 and WRITE 32. However, the current implementation of scsi_report_opcode() only allows checking an operation code without a service action differentiation. Add the "sa" argument to scsi_report_opcode() to allow passing a service action. If a non-zero service action is specified, the reporting options field value is set to 3 to have the service action field taken into account by the device. If no service action field is specified (zero), the reporting options field is set to 1 as before. Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Reviewed-by: Bart Van Assche Signed-off-by: Niklas Cassel Link: https://lore.kernel.org/r/20230511011356.227789-8-nks@flawful.org Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi.c | 28 +++++++++++++++++++--------- drivers/scsi/sd.c | 10 +++++----- include/scsi/scsi_device.h | 5 +++-- 3 files changed, 27 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c index 09ef0b31dfc0..62d9472e08e9 100644 --- a/drivers/scsi/scsi.c +++ b/drivers/scsi/scsi.c @@ -504,18 +504,22 @@ void scsi_attach_vpd(struct scsi_device *sdev) } /** - * scsi_report_opcode - Find out if a given command opcode is supported + * scsi_report_opcode - Find out if a given command is supported * @sdev: scsi device to query * @buffer: scratch buffer (must be at least 20 bytes long) * @len: length of buffer - * @opcode: opcode for command to look up - * - * Uses the REPORT SUPPORTED OPERATION CODES to look up the given - * opcode. Returns -EINVAL if RSOC fails, 0 if the command opcode is - * unsupported and 1 if the device claims to support the command. + * @opcode: opcode for the command to look up + * @sa: service action for the command to look up + * + * Uses the REPORT SUPPORTED OPERATION CODES to check support for the + * command identified with @opcode and @sa. If the command does not + * have a service action, @sa must be 0. Returns -EINVAL if RSOC fails, + * 0 if the command is not supported and 1 if the device claims to + * support the command. */ int scsi_report_opcode(struct scsi_device *sdev, unsigned char *buffer, - unsigned int len, unsigned char opcode) + unsigned int len, unsigned char opcode, + unsigned short sa) { unsigned char cmd[16]; struct scsi_sense_hdr sshdr; @@ -539,8 +543,14 @@ int scsi_report_opcode(struct scsi_device *sdev, unsigned char *buffer, memset(cmd, 0, 16); cmd[0] = MAINTENANCE_IN; cmd[1] = MI_REPORT_SUPPORTED_OPERATION_CODES; - cmd[2] = 1; /* One command format */ - cmd[3] = opcode; + if (!sa) { + cmd[2] = 1; /* One command format */ + cmd[3] = opcode; + } else { + cmd[2] = 3; /* One command format with service action */ + cmd[3] = opcode; + put_unaligned_be16(sa, &cmd[4]); + } put_unaligned_be32(request_len, &cmd[6]); memset(buffer, 0, len); diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index cdcef1b651c1..a76092663246 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3056,7 +3056,7 @@ static void sd_read_write_same(struct scsi_disk *sdkp, unsigned char *buffer) return; } - if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, INQUIRY) < 0) { + if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, INQUIRY, 0) < 0) { struct scsi_vpd *vpd; sdev->no_report_opcodes = 1; @@ -3072,10 +3072,10 @@ static void sd_read_write_same(struct scsi_disk *sdkp, unsigned char *buffer) rcu_read_unlock(); } - if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, WRITE_SAME_16) == 1) + if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, WRITE_SAME_16, 0) == 1) sdkp->ws16 = 1; - if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, WRITE_SAME) == 1) + if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, WRITE_SAME, 0) == 1) sdkp->ws10 = 1; } @@ -3087,9 +3087,9 @@ static void sd_read_security(struct scsi_disk *sdkp, unsigned char *buffer) return; if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, - SECURITY_PROTOCOL_IN) == 1 && + SECURITY_PROTOCOL_IN, 0) == 1 && scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, - SECURITY_PROTOCOL_OUT) == 1) + SECURITY_PROTOCOL_OUT, 0) == 1) sdkp->security = 1; } diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index c146cc807d44..c93c5aaf637e 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -433,8 +433,9 @@ extern int scsi_test_unit_ready(struct scsi_device *sdev, int timeout, int retries, struct scsi_sense_hdr *sshdr); extern int scsi_get_vpd_page(struct scsi_device *, u8 page, unsigned char *buf, int buf_len); -extern int scsi_report_opcode(struct scsi_device *sdev, unsigned char *buffer, - unsigned int len, unsigned char opcode); +int scsi_report_opcode(struct scsi_device *sdev, unsigned char *buffer, + unsigned int len, unsigned char opcode, + unsigned short sa); extern int scsi_device_set_state(struct scsi_device *sdev, enum scsi_device_state state); extern struct scsi_event *sdev_evt_alloc(enum scsi_device_event evt_type, -- cgit v1.2.3 From 624885209f31eb9985bf51abe204ecbffe2fdeea Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 11 May 2023 03:13:41 +0200 Subject: scsi: core: Detect support for command duration limits Introduce the function scsi_cdl_check() to detect if a device supports command duration limits (CDL). Support for the READ 16, WRITE 16, READ 32 and WRITE 32 commands are checked using the function scsi_report_opcode() to probe the rwcdlp and cdlp bits as they indicate the mode page defining the command duration limits descriptors that apply to the command being tested. If any of these commands support CDL, the field cdl_supported of struct scsi_device is set to 1 to indicate that the device supports CDL. Support for CDL for a device is advertizes through sysfs using the new cdl_supported device attribute. This attribute value is 1 for a device supporting CDL and 0 otherwise. Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Co-developed-by: Niklas Cassel Signed-off-by: Niklas Cassel Link: https://lore.kernel.org/r/20230511011356.227789-9-nks@flawful.org Signed-off-by: Martin K. Petersen --- Documentation/ABI/testing/sysfs-block-device | 9 ++++ drivers/scsi/scsi.c | 81 ++++++++++++++++++++++++++++ drivers/scsi/scsi_scan.c | 3 ++ drivers/scsi/scsi_sysfs.c | 2 + include/scsi/scsi_device.h | 3 ++ 5 files changed, 98 insertions(+) (limited to 'include') diff --git a/Documentation/ABI/testing/sysfs-block-device b/Documentation/ABI/testing/sysfs-block-device index 7ac7b19b2f72..ffc3358cba57 100644 --- a/Documentation/ABI/testing/sysfs-block-device +++ b/Documentation/ABI/testing/sysfs-block-device @@ -95,3 +95,12 @@ Description: This file does not exist if the HBA driver does not implement support for the SATA NCQ priority feature, regardless of the device support for this feature. + + +What: /sys/block/*/device/cdl_supported +Date: May, 2023 +KernelVersion: v6.5 +Contact: linux-scsi@vger.kernel.org +Description: + (RO) Indicates if the device supports the command duration + limits feature found in some ATA and SCSI devices. diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c index 62d9472e08e9..c03814ce23ca 100644 --- a/drivers/scsi/scsi.c +++ b/drivers/scsi/scsi.c @@ -570,6 +570,87 @@ int scsi_report_opcode(struct scsi_device *sdev, unsigned char *buffer, } EXPORT_SYMBOL(scsi_report_opcode); +#define SCSI_CDL_CHECK_BUF_LEN 64 + +static bool scsi_cdl_check_cmd(struct scsi_device *sdev, u8 opcode, u16 sa, + unsigned char *buf) +{ + int ret; + u8 cdlp; + + /* Check operation code */ + ret = scsi_report_opcode(sdev, buf, SCSI_CDL_CHECK_BUF_LEN, opcode, sa); + if (ret <= 0) + return false; + + if ((buf[1] & 0x03) != 0x03) + return false; + + /* See SPC-6, one command format of REPORT SUPPORTED OPERATION CODES */ + cdlp = (buf[1] & 0x18) >> 3; + if (buf[0] & 0x01) { + /* rwcdlp == 1 */ + switch (cdlp) { + case 0x01: + /* T2A page */ + return true; + case 0x02: + /* T2B page */ + return true; + } + } else { + /* rwcdlp == 0 */ + switch (cdlp) { + case 0x01: + /* A page */ + return true; + case 0x02: + /* B page */ + return true; + } + } + + return false; +} + +/** + * scsi_cdl_check - Check if a SCSI device supports Command Duration Limits + * @sdev: The device to check + */ +void scsi_cdl_check(struct scsi_device *sdev) +{ + bool cdl_supported; + unsigned char *buf; + + buf = kmalloc(SCSI_CDL_CHECK_BUF_LEN, GFP_KERNEL); + if (!buf) { + sdev->cdl_supported = 0; + return; + } + + /* Check support for READ_16, WRITE_16, READ_32 and WRITE_32 commands */ + cdl_supported = + scsi_cdl_check_cmd(sdev, READ_16, 0, buf) || + scsi_cdl_check_cmd(sdev, WRITE_16, 0, buf) || + scsi_cdl_check_cmd(sdev, VARIABLE_LENGTH_CMD, READ_32, buf) || + scsi_cdl_check_cmd(sdev, VARIABLE_LENGTH_CMD, WRITE_32, buf); + if (cdl_supported) { + /* + * We have CDL support: force the use of READ16/WRITE16. + * READ32 and WRITE32 will be used for devices that support + * the T10_PI_TYPE2_PROTECTION protection type. + */ + sdev->use_16_for_rw = 1; + sdev->use_10_for_rw = 0; + + sdev->cdl_supported = 1; + } else { + sdev->cdl_supported = 0; + } + + kfree(buf); +} + /** * scsi_device_get - get an additional reference to a scsi_device * @sdev: device to get a reference to diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index d217be323cc6..aa13feb17c62 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -1087,6 +1087,8 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result, if (sdev->scsi_level >= SCSI_3) scsi_attach_vpd(sdev); + scsi_cdl_check(sdev); + sdev->max_queue_depth = sdev->queue_depth; WARN_ON_ONCE(sdev->max_queue_depth > sdev->budget_map.depth); sdev->sdev_bflags = *bflags; @@ -1624,6 +1626,7 @@ void scsi_rescan_device(struct device *dev) device_lock(dev); scsi_attach_vpd(sdev); + scsi_cdl_check(sdev); if (sdev->handler && sdev->handler->rescan) sdev->handler->rescan(sdev); diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 603e8fcfcb8a..98fcbbf1c1e3 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -670,6 +670,7 @@ sdev_rd_attr (scsi_level, "%d\n"); sdev_rd_attr (vendor, "%.8s\n"); sdev_rd_attr (model, "%.16s\n"); sdev_rd_attr (rev, "%.4s\n"); +sdev_rd_attr (cdl_supported, "%d\n"); static ssize_t sdev_show_device_busy(struct device *dev, struct device_attribute *attr, @@ -1300,6 +1301,7 @@ static struct attribute *scsi_sdev_attrs[] = { &dev_attr_preferred_path.attr, #endif &dev_attr_queue_ramp_up_period.attr, + &dev_attr_cdl_supported.attr, REF_EVT(media_change), REF_EVT(inquiry_change_reported), REF_EVT(capacity_change_reported), diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index c93c5aaf637e..6b8df9e253a0 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -218,6 +218,8 @@ struct scsi_device { unsigned silence_suspend:1; /* Do not print runtime PM related messages */ unsigned no_vpd_size:1; /* No VPD size reported in header */ + unsigned cdl_supported:1; /* Command duration limits supported */ + unsigned int queue_stopped; /* request queue is quiesced */ bool offline_already; /* Device offline message logged */ @@ -364,6 +366,7 @@ extern int scsi_register_device_handler(struct scsi_device_handler *scsi_dh); extern void scsi_remove_device(struct scsi_device *); extern int scsi_unregister_device_handler(struct scsi_device_handler *scsi_dh); void scsi_attach_vpd(struct scsi_device *sdev); +void scsi_cdl_check(struct scsi_device *sdev); extern struct scsi_device *scsi_device_from_queue(struct request_queue *q); extern int __must_check scsi_device_get(struct scsi_device *); -- cgit v1.2.3 From 1b22cfb14142aba7742d307c4f8d7006f919308c Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 11 May 2023 03:13:42 +0200 Subject: scsi: core: Allow enabling and disabling command duration limits Add the sysfs scsi_device attribute cdl_enable to allow a user to enable or disable a device command duration limits feature. CDL is disabled by default. This feature must be explicitly enabled by a user by setting the cdl_enable attribute to 1. The new function scsi_cdl_enable() does not do anything beside setting the cdl_enable field of struct scsi_device in the case of a (real) SCSI device (e.g. a SAS HDD). For ATA devices, the command duration limits feature needs to be enabled/disabled using the ATA feature sub-page of the control mode page. To do so, the scsi_cdl_enable() function checks if this mode page is supported using scsi_mode_sense(). If it is, scsi_mode_select() is used to enable and disable CDL. Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Co-developed-by: Niklas Cassel Signed-off-by: Niklas Cassel Link: https://lore.kernel.org/r/20230511011356.227789-10-nks@flawful.org Signed-off-by: Martin K. Petersen --- Documentation/ABI/testing/sysfs-block-device | 13 ++++++ drivers/scsi/scsi.c | 62 ++++++++++++++++++++++++++++ drivers/scsi/scsi_sysfs.c | 28 +++++++++++++ include/scsi/scsi_device.h | 2 + 4 files changed, 105 insertions(+) (limited to 'include') diff --git a/Documentation/ABI/testing/sysfs-block-device b/Documentation/ABI/testing/sysfs-block-device index ffc3358cba57..2d543cfa4079 100644 --- a/Documentation/ABI/testing/sysfs-block-device +++ b/Documentation/ABI/testing/sysfs-block-device @@ -104,3 +104,16 @@ Contact: linux-scsi@vger.kernel.org Description: (RO) Indicates if the device supports the command duration limits feature found in some ATA and SCSI devices. + + +What: /sys/block/*/device/cdl_enable +Date: May, 2023 +KernelVersion: v6.5 +Contact: linux-scsi@vger.kernel.org +Description: + (RW) For a device supporting the command duration limits + feature, write to the file to turn on or off the feature. + By default this feature is turned off. + Writing "1" to this file enables the use of command duration + limits for read and write commands in the kernel and turns on + the feature on the device. Writing "0" disables the feature. diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c index c03814ce23ca..c4bf99a842f3 100644 --- a/drivers/scsi/scsi.c +++ b/drivers/scsi/scsi.c @@ -651,6 +651,68 @@ void scsi_cdl_check(struct scsi_device *sdev) kfree(buf); } +/** + * scsi_cdl_enable - Enable or disable a SCSI device supports for Command + * Duration Limits + * @sdev: The target device + * @enable: the target state + */ +int scsi_cdl_enable(struct scsi_device *sdev, bool enable) +{ + struct scsi_mode_data data; + struct scsi_sense_hdr sshdr; + struct scsi_vpd *vpd; + bool is_ata = false; + char buf[64]; + int ret; + + if (!sdev->cdl_supported) + return -EOPNOTSUPP; + + rcu_read_lock(); + vpd = rcu_dereference(sdev->vpd_pg89); + if (vpd) + is_ata = true; + rcu_read_unlock(); + + /* + * For ATA devices, CDL needs to be enabled with a SET FEATURES command. + */ + if (is_ata) { + char *buf_data; + int len; + + ret = scsi_mode_sense(sdev, 0x08, 0x0a, 0xf2, buf, sizeof(buf), + 5 * HZ, 3, &data, NULL); + if (ret) + return -EINVAL; + + /* Enable CDL using the ATA feature page */ + len = min_t(size_t, sizeof(buf), + data.length - data.header_length - + data.block_descriptor_length); + buf_data = buf + data.header_length + + data.block_descriptor_length; + if (enable) + buf_data[4] = 0x02; + else + buf_data[4] = 0; + + ret = scsi_mode_select(sdev, 1, 0, buf_data, len, 5 * HZ, 3, + &data, &sshdr); + if (ret) { + if (scsi_sense_valid(&sshdr)) + scsi_print_sense_hdr(sdev, + dev_name(&sdev->sdev_gendev), &sshdr); + return ret; + } + } + + sdev->cdl_enable = enable; + + return 0; +} + /** * scsi_device_get - get an additional reference to a scsi_device * @sdev: device to get a reference to diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 98fcbbf1c1e3..60317676e45f 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -1222,6 +1222,33 @@ static DEVICE_ATTR(queue_ramp_up_period, S_IRUGO | S_IWUSR, sdev_show_queue_ramp_up_period, sdev_store_queue_ramp_up_period); +static ssize_t sdev_show_cdl_enable(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct scsi_device *sdev = to_scsi_device(dev); + + return sysfs_emit(buf, "%d\n", (int)sdev->cdl_enable); +} + +static ssize_t sdev_store_cdl_enable(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + int ret; + bool v; + + if (kstrtobool(buf, &v)) + return -EINVAL; + + ret = scsi_cdl_enable(to_scsi_device(dev), v); + if (ret) + return ret; + + return count; +} +static DEVICE_ATTR(cdl_enable, S_IRUGO | S_IWUSR, + sdev_show_cdl_enable, sdev_store_cdl_enable); + static umode_t scsi_sdev_attr_is_visible(struct kobject *kobj, struct attribute *attr, int i) { @@ -1302,6 +1329,7 @@ static struct attribute *scsi_sdev_attrs[] = { #endif &dev_attr_queue_ramp_up_period.attr, &dev_attr_cdl_supported.attr, + &dev_attr_cdl_enable.attr, REF_EVT(media_change), REF_EVT(inquiry_change_reported), REF_EVT(capacity_change_reported), diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 6b8df9e253a0..b2cdb078b7bd 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -219,6 +219,7 @@ struct scsi_device { unsigned no_vpd_size:1; /* No VPD size reported in header */ unsigned cdl_supported:1; /* Command duration limits supported */ + unsigned cdl_enable:1; /* Enable/disable Command duration limits */ unsigned int queue_stopped; /* request queue is quiesced */ bool offline_already; /* Device offline message logged */ @@ -367,6 +368,7 @@ extern void scsi_remove_device(struct scsi_device *); extern int scsi_unregister_device_handler(struct scsi_device_handler *scsi_dh); void scsi_attach_vpd(struct scsi_device *sdev); void scsi_cdl_check(struct scsi_device *sdev); +int scsi_cdl_enable(struct scsi_device *sdev, bool enable); extern struct scsi_device *scsi_device_from_queue(struct request_queue *q); extern int __must_check scsi_device_get(struct scsi_device *); -- cgit v1.2.3 From 62e4a60e0cdb540b314061469e025fd834ff300c Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 11 May 2023 03:13:47 +0200 Subject: scsi: ata: libata: Detect support for command duration limits Use the supported capabilities identify device data log page to detect if a device supports the command duration limits feature. For devices supporting this feature, set the device flag ATA_DFLAG_CDL. To support SCSI-ATA translation, retrieve the command duration limits log page 18h and cache this page content using the cdl array added to the ata_device data structure. Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Co-developed-by: Niklas Cassel Signed-off-by: Niklas Cassel Link: https://lore.kernel.org/r/20230511011356.227789-15-nks@flawful.org Signed-off-by: Martin K. Petersen --- drivers/ata/libata-core.c | 52 ++++++++++++++++++++++++++++++++++++++++++++++- drivers/ata/libata-scsi.c | 17 ++++++++-------- include/linux/ata.h | 5 ++++- include/linux/libata.h | 29 +++++++++++++++----------- 4 files changed, 80 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 8bf612bdd61a..83fe037f63b9 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2367,6 +2367,54 @@ static void ata_dev_config_trusted(struct ata_device *dev) dev->flags |= ATA_DFLAG_TRUSTED; } +static void ata_dev_config_cdl(struct ata_device *dev) +{ + struct ata_port *ap = dev->link->ap; + unsigned int err_mask; + u64 val; + + if (ata_id_major_version(dev->id) < 12) + goto not_supported; + + if (!ata_log_supported(dev, ATA_LOG_IDENTIFY_DEVICE) || + !ata_identify_page_supported(dev, ATA_LOG_SUPPORTED_CAPABILITIES)) + goto not_supported; + + err_mask = ata_read_log_page(dev, ATA_LOG_IDENTIFY_DEVICE, + ATA_LOG_SUPPORTED_CAPABILITIES, + ap->sector_buf, 1); + if (err_mask) + goto not_supported; + + /* Check Command Duration Limit Supported bits */ + val = get_unaligned_le64(&ap->sector_buf[168]); + if (!(val & BIT_ULL(63)) || !(val & BIT_ULL(0))) + goto not_supported; + + /* Warn the user if command duration guideline is not supported */ + if (!(val & BIT_ULL(1))) + ata_dev_warn(dev, + "Command duration guideline is not supported\n"); + + /* + * Command duration limits is supported: cache the CDL log page 18h + * (command duration descriptors). + */ + err_mask = ata_read_log_page(dev, ATA_LOG_CDL, 0, ap->sector_buf, 1); + if (err_mask) { + ata_dev_warn(dev, "Read Command Duration Limits log failed\n"); + goto not_supported; + } + + memcpy(dev->cdl, ap->sector_buf, ATA_LOG_CDL_SIZE); + dev->flags |= ATA_DFLAG_CDL; + + return; + +not_supported: + dev->flags &= ~ATA_DFLAG_CDL; +} + static int ata_dev_config_lba(struct ata_device *dev) { const u16 *id = dev->id; @@ -2534,13 +2582,14 @@ static void ata_dev_print_features(struct ata_device *dev) return; ata_dev_info(dev, - "Features:%s%s%s%s%s%s%s\n", + "Features:%s%s%s%s%s%s%s%s\n", dev->flags & ATA_DFLAG_FUA ? " FUA" : "", dev->flags & ATA_DFLAG_TRUSTED ? " Trust" : "", dev->flags & ATA_DFLAG_DA ? " Dev-Attention" : "", dev->flags & ATA_DFLAG_DEVSLP ? " Dev-Sleep" : "", dev->flags & ATA_DFLAG_NCQ_SEND_RECV ? " NCQ-sndrcv" : "", dev->flags & ATA_DFLAG_NCQ_PRIO ? " NCQ-prio" : "", + dev->flags & ATA_DFLAG_CDL ? " CDL" : "", dev->cpr_log ? " CPR" : ""); } @@ -2702,6 +2751,7 @@ int ata_dev_configure(struct ata_device *dev) ata_dev_config_zac(dev); ata_dev_config_trusted(dev); ata_dev_config_cpr(dev); + ata_dev_config_cdl(dev); dev->cdb_len = 32; if (print_info) diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 072785808751..3434fec8ca5c 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -47,15 +47,14 @@ typedef unsigned int (*ata_xlat_func_t)(struct ata_queued_cmd *qc); static struct ata_device *__ata_scsi_find_dev(struct ata_port *ap, const struct scsi_device *scsidev); -#define RW_RECOVERY_MPAGE 0x1 -#define RW_RECOVERY_MPAGE_LEN 12 -#define CACHE_MPAGE 0x8 -#define CACHE_MPAGE_LEN 20 -#define CONTROL_MPAGE 0xa -#define CONTROL_MPAGE_LEN 12 -#define ALL_MPAGES 0x3f -#define ALL_SUB_MPAGES 0xff - +#define RW_RECOVERY_MPAGE 0x1 +#define RW_RECOVERY_MPAGE_LEN 12 +#define CACHE_MPAGE 0x8 +#define CACHE_MPAGE_LEN 20 +#define CONTROL_MPAGE 0xa +#define CONTROL_MPAGE_LEN 12 +#define ALL_MPAGES 0x3f +#define ALL_SUB_MPAGES 0xff static const u8 def_rw_recovery_mpage[RW_RECOVERY_MPAGE_LEN] = { RW_RECOVERY_MPAGE, diff --git a/include/linux/ata.h b/include/linux/ata.h index c224dbddb9b2..1eda46b63dcc 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -322,15 +322,18 @@ enum { ATA_LOG_SATA_NCQ = 0x10, ATA_LOG_NCQ_NON_DATA = 0x12, ATA_LOG_NCQ_SEND_RECV = 0x13, + ATA_LOG_CDL = 0x18, + ATA_LOG_CDL_SIZE = ATA_SECT_SIZE, ATA_LOG_IDENTIFY_DEVICE = 0x30, ATA_LOG_CONCURRENT_POSITIONING_RANGES = 0x47, /* Identify device log pages: */ + ATA_LOG_SUPPORTED_CAPABILITIES = 0x03, ATA_LOG_SECURITY = 0x06, ATA_LOG_SATA_SETTINGS = 0x08, ATA_LOG_ZONED_INFORMATION = 0x09, - /* Identify device SATA settings log:*/ + /* Identify device SATA settings log: */ ATA_LOG_DEVSLP_OFFSET = 0x30, ATA_LOG_DEVSLP_SIZE = 0x08, ATA_LOG_DEVSLP_MDAT = 0x00, diff --git a/include/linux/libata.h b/include/linux/libata.h index 311cd93377c7..e8a45f7f3f5c 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -94,17 +94,18 @@ enum { ATA_DFLAG_DMADIR = (1 << 10), /* device requires DMADIR */ ATA_DFLAG_NCQ_SEND_RECV = (1 << 11), /* device supports NCQ SEND and RECV */ ATA_DFLAG_NCQ_PRIO = (1 << 12), /* device supports NCQ priority */ - ATA_DFLAG_CFG_MASK = (1 << 13) - 1, - - ATA_DFLAG_PIO = (1 << 13), /* device limited to PIO mode */ - ATA_DFLAG_NCQ_OFF = (1 << 14), /* device limited to non-NCQ mode */ - ATA_DFLAG_SLEEPING = (1 << 15), /* device is sleeping */ - ATA_DFLAG_DUBIOUS_XFER = (1 << 16), /* data transfer not verified */ - ATA_DFLAG_NO_UNLOAD = (1 << 17), /* device doesn't support unload */ - ATA_DFLAG_UNLOCK_HPA = (1 << 18), /* unlock HPA */ - ATA_DFLAG_INIT_MASK = (1 << 19) - 1, - - ATA_DFLAG_NCQ_PRIO_ENABLED = (1 << 19), /* Priority cmds sent to dev */ + ATA_DFLAG_CDL = (1 << 13), /* supports cmd duration limits */ + ATA_DFLAG_CFG_MASK = (1 << 14) - 1, + + ATA_DFLAG_PIO = (1 << 14), /* device limited to PIO mode */ + ATA_DFLAG_NCQ_OFF = (1 << 15), /* device limited to non-NCQ mode */ + ATA_DFLAG_SLEEPING = (1 << 16), /* device is sleeping */ + ATA_DFLAG_DUBIOUS_XFER = (1 << 17), /* data transfer not verified */ + ATA_DFLAG_NO_UNLOAD = (1 << 18), /* device doesn't support unload */ + ATA_DFLAG_UNLOCK_HPA = (1 << 19), /* unlock HPA */ + ATA_DFLAG_INIT_MASK = (1 << 20) - 1, + + ATA_DFLAG_NCQ_PRIO_ENABLED = (1 << 20), /* Priority cmds sent to dev */ ATA_DFLAG_DETACH = (1 << 24), ATA_DFLAG_DETACHED = (1 << 25), ATA_DFLAG_DA = (1 << 26), /* device supports Device Attention */ @@ -115,7 +116,8 @@ enum { ATA_DFLAG_FEATURES_MASK = (ATA_DFLAG_TRUSTED | ATA_DFLAG_DA | \ ATA_DFLAG_DEVSLP | ATA_DFLAG_NCQ_SEND_RECV | \ - ATA_DFLAG_NCQ_PRIO | ATA_DFLAG_FUA), + ATA_DFLAG_NCQ_PRIO | ATA_DFLAG_FUA | \ + ATA_DFLAG_CDL), ATA_DEV_UNKNOWN = 0, /* unknown device */ ATA_DEV_ATA = 1, /* ATA device */ @@ -709,6 +711,9 @@ struct ata_device { /* Concurrent positioning ranges */ struct ata_cpr_log *cpr_log; + /* Command Duration Limits log support */ + u8 cdl[ATA_LOG_CDL_SIZE]; + /* error history */ int spdn_cnt; /* ering is CLEAR_END, read comment above CLEAR_END */ -- cgit v1.2.3 From df60f9c64576d6d05b59ec5c34addcd61ef1efb0 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 11 May 2023 03:13:50 +0200 Subject: scsi: ata: libata: Add ATA feature control sub-page translation Add support for the ATA feature control sub-page of the control mode page to enable/disable the command duration limits feature using the cdl_ctrl field of the ATA feature control sub-page. Both mode sense and mode select translation are supported. For mode sense, the ata device flag ATA_DFLAG_CDL_ENABLED is used to cache the status of the command duration limits feature. Enabling this feature is done using a SET FEATURES command with a cdl action set to 1 when the page cdl_ctrl field value is 0x2 (T2A and T2B pages supported). If this field is 0, CDL is disabled using the SET FEATURES command with a cdl action set to 0. Since a device CDL and NCQ priority features should not be used simultaneously, ata_mselect_control_ata_feature() returns an error when attempting to enable CDL with the device priority feature enabled. Conversely, the function ata_ncq_prio_enable_store() used to enable the use of the device NCQ priority feature through sysfs is modified to return an error if the device CDL feature is enabled. Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Co-developed-by: Niklas Cassel Signed-off-by: Niklas Cassel Link: https://lore.kernel.org/r/20230511011356.227789-18-nks@flawful.org Signed-off-by: Martin K. Petersen --- drivers/ata/libata-core.c | 40 ++++++++++- drivers/ata/libata-sata.c | 11 ++- drivers/ata/libata-scsi.c | 167 +++++++++++++++++++++++++++++++++++++++------- include/linux/ata.h | 3 + include/linux/libata.h | 1 + 5 files changed, 193 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 83fe037f63b9..cd7aaf202397 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2371,13 +2371,15 @@ static void ata_dev_config_cdl(struct ata_device *dev) { struct ata_port *ap = dev->link->ap; unsigned int err_mask; + bool cdl_enabled; u64 val; if (ata_id_major_version(dev->id) < 12) goto not_supported; if (!ata_log_supported(dev, ATA_LOG_IDENTIFY_DEVICE) || - !ata_identify_page_supported(dev, ATA_LOG_SUPPORTED_CAPABILITIES)) + !ata_identify_page_supported(dev, ATA_LOG_SUPPORTED_CAPABILITIES) || + !ata_identify_page_supported(dev, ATA_LOG_CURRENT_SETTINGS)) goto not_supported; err_mask = ata_read_log_page(dev, ATA_LOG_IDENTIFY_DEVICE, @@ -2396,6 +2398,40 @@ static void ata_dev_config_cdl(struct ata_device *dev) ata_dev_warn(dev, "Command duration guideline is not supported\n"); + /* + * If CDL is marked as enabled, make sure the feature is enabled too. + * Conversely, if CDL is disabled, make sure the feature is turned off. + */ + err_mask = ata_read_log_page(dev, ATA_LOG_IDENTIFY_DEVICE, + ATA_LOG_CURRENT_SETTINGS, + ap->sector_buf, 1); + if (err_mask) + goto not_supported; + + val = get_unaligned_le64(&ap->sector_buf[8]); + cdl_enabled = val & BIT_ULL(63) && val & BIT_ULL(21); + if (dev->flags & ATA_DFLAG_CDL_ENABLED) { + if (!cdl_enabled) { + /* Enable CDL on the device */ + err_mask = ata_dev_set_feature(dev, SETFEATURES_CDL, 1); + if (err_mask) { + ata_dev_err(dev, + "Enable CDL feature failed\n"); + goto not_supported; + } + } + } else { + if (cdl_enabled) { + /* Disable CDL on the device */ + err_mask = ata_dev_set_feature(dev, SETFEATURES_CDL, 0); + if (err_mask) { + ata_dev_err(dev, + "Disable CDL feature failed\n"); + goto not_supported; + } + } + } + /* * Command duration limits is supported: cache the CDL log page 18h * (command duration descriptors). @@ -2412,7 +2448,7 @@ static void ata_dev_config_cdl(struct ata_device *dev) return; not_supported: - dev->flags &= ~ATA_DFLAG_CDL; + dev->flags &= ~(ATA_DFLAG_CDL | ATA_DFLAG_CDL_ENABLED); } static int ata_dev_config_lba(struct ata_device *dev) diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c index f3e7396e3191..57cb33060c9d 100644 --- a/drivers/ata/libata-sata.c +++ b/drivers/ata/libata-sata.c @@ -907,10 +907,17 @@ static ssize_t ata_ncq_prio_enable_store(struct device *device, goto unlock; } - if (input) + if (input) { + if (dev->flags & ATA_DFLAG_CDL_ENABLED) { + ata_dev_err(dev, + "CDL must be disabled to enable NCQ priority\n"); + rc = -EINVAL; + goto unlock; + } dev->flags |= ATA_DFLAG_NCQ_PRIO_ENABLED; - else + } else { dev->flags &= ~ATA_DFLAG_NCQ_PRIO_ENABLED; + } unlock: spin_unlock_irq(ap->lock); diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 4a4c6405d52e..91db4e7f4906 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -58,6 +58,8 @@ static struct ata_device *__ata_scsi_find_dev(struct ata_port *ap, #define CDL_T2A_SUB_MPAGE 0x07 #define CDL_T2B_SUB_MPAGE 0x08 #define CDL_T2_SUB_MPAGE_LEN 232 +#define ATA_FEATURE_SUB_MPAGE 0xf2 +#define ATA_FEATURE_SUB_MPAGE_LEN 16 static const u8 def_rw_recovery_mpage[RW_RECOVERY_MPAGE_LEN] = { RW_RECOVERY_MPAGE, @@ -2286,6 +2288,31 @@ static unsigned int ata_msense_control_spgt2(struct ata_device *dev, u8 *buf, return CDL_T2_SUB_MPAGE_LEN; } +/* + * Simulate MODE SENSE control mode page, sub-page f2h + * (ATA feature control mode page). + */ +static unsigned int ata_msense_control_ata_feature(struct ata_device *dev, + u8 *buf) +{ + /* PS=0, SPF=1 */ + buf[0] = CONTROL_MPAGE | (1 << 6); + buf[1] = ATA_FEATURE_SUB_MPAGE; + + /* + * The first four bytes of ATA Feature Control mode page are a header. + * The PAGE LENGTH field is the size of the page excluding the header. + */ + put_unaligned_be16(ATA_FEATURE_SUB_MPAGE_LEN - 4, &buf[2]); + + if (dev->flags & ATA_DFLAG_CDL) + buf[4] = 0x02; /* Support T2A and T2B pages */ + else + buf[4] = 0; + + return ATA_FEATURE_SUB_MPAGE_LEN; +} + /** * ata_msense_control - Simulate MODE SENSE control mode page * @dev: ATA device of interest @@ -2309,10 +2336,13 @@ static unsigned int ata_msense_control(struct ata_device *dev, u8 *buf, case CDL_T2A_SUB_MPAGE: case CDL_T2B_SUB_MPAGE: return ata_msense_control_spgt2(dev, buf, spg); + case ATA_FEATURE_SUB_MPAGE: + return ata_msense_control_ata_feature(dev, buf); case ALL_SUB_MPAGES: n = ata_msense_control_spg0(dev, buf, changeable); n += ata_msense_control_spgt2(dev, buf + n, CDL_T2A_SUB_MPAGE); n += ata_msense_control_spgt2(dev, buf + n, CDL_T2A_SUB_MPAGE); + n += ata_msense_control_ata_feature(dev, buf + n); return n; default: return 0; @@ -2391,7 +2421,7 @@ static unsigned int ata_scsiop_mode_sense(struct ata_scsi_args *args, u8 *rbuf) spg = scsicmd[3]; /* - * Supported subpages: all subpages and sub-pages 07h and 08h of + * Supported subpages: all subpages and sub-pages 07h, 08h and f2h of * the control page. */ if (spg) { @@ -2400,6 +2430,7 @@ static unsigned int ata_scsiop_mode_sense(struct ata_scsi_args *args, u8 *rbuf) break; case CDL_T2A_SUB_MPAGE: case CDL_T2B_SUB_MPAGE: + case ATA_FEATURE_SUB_MPAGE: if (dev->flags & ATA_DFLAG_CDL && pg == CONTROL_MPAGE) break; fallthrough; @@ -3708,20 +3739,11 @@ static int ata_mselect_caching(struct ata_queued_cmd *qc, return 0; } -/** - * ata_mselect_control - Simulate MODE SELECT for control page - * @qc: Storage for translated ATA taskfile - * @buf: input buffer - * @len: number of valid bytes in the input buffer - * @fp: out parameter for the failed field on error - * - * Prepare a taskfile to modify caching information for the device. - * - * LOCKING: - * None. +/* + * Simulate MODE SELECT control mode page, sub-page 0. */ -static int ata_mselect_control(struct ata_queued_cmd *qc, - const u8 *buf, int len, u16 *fp) +static int ata_mselect_control_spg0(struct ata_queued_cmd *qc, + const u8 *buf, int len, u16 *fp) { struct ata_device *dev = qc->dev; u8 mpage[CONTROL_MPAGE_LEN]; @@ -3759,6 +3781,83 @@ static int ata_mselect_control(struct ata_queued_cmd *qc, return 0; } +/* + * Translate MODE SELECT control mode page, sub-pages f2h (ATA feature mode + * page) into a SET FEATURES command. + */ +static unsigned int ata_mselect_control_ata_feature(struct ata_queued_cmd *qc, + const u8 *buf, int len, + u16 *fp) +{ + struct ata_device *dev = qc->dev; + struct ata_taskfile *tf = &qc->tf; + u8 cdl_action; + + /* + * The first four bytes of ATA Feature Control mode page are a header, + * so offsets in mpage are off by 4 compared to buf. Same for len. + */ + if (len != ATA_FEATURE_SUB_MPAGE_LEN - 4) { + *fp = min(len, ATA_FEATURE_SUB_MPAGE_LEN - 4); + return -EINVAL; + } + + /* Check cdl_ctrl */ + switch (buf[0] & 0x03) { + case 0: + /* Disable CDL */ + cdl_action = 0; + dev->flags &= ~ATA_DFLAG_CDL_ENABLED; + break; + case 0x02: + /* Enable CDL T2A/T2B: NCQ priority must be disabled */ + if (dev->flags & ATA_DFLAG_NCQ_PRIO_ENABLED) { + ata_dev_err(dev, + "NCQ priority must be disabled to enable CDL\n"); + return -EINVAL; + } + cdl_action = 1; + dev->flags |= ATA_DFLAG_CDL_ENABLED; + break; + default: + *fp = 0; + return -EINVAL; + } + + tf->flags |= ATA_TFLAG_DEVICE | ATA_TFLAG_ISADDR; + tf->protocol = ATA_PROT_NODATA; + tf->command = ATA_CMD_SET_FEATURES; + tf->feature = SETFEATURES_CDL; + tf->nsect = cdl_action; + + return 1; +} + +/** + * ata_mselect_control - Simulate MODE SELECT for control page + * @qc: Storage for translated ATA taskfile + * @buf: input buffer + * @len: number of valid bytes in the input buffer + * @fp: out parameter for the failed field on error + * + * Prepare a taskfile to modify caching information for the device. + * + * LOCKING: + * None. + */ +static int ata_mselect_control(struct ata_queued_cmd *qc, u8 spg, + const u8 *buf, int len, u16 *fp) +{ + switch (spg) { + case 0: + return ata_mselect_control_spg0(qc, buf, len, fp); + case ATA_FEATURE_SUB_MPAGE: + return ata_mselect_control_ata_feature(qc, buf, len, fp); + default: + return -EINVAL; + } +} + /** * ata_scsi_mode_select_xlat - Simulate MODE SELECT 6, 10 commands * @qc: Storage for translated ATA taskfile @@ -3776,7 +3875,7 @@ static unsigned int ata_scsi_mode_select_xlat(struct ata_queued_cmd *qc) const u8 *cdb = scmd->cmnd; u8 pg, spg; unsigned six_byte, pg_len, hdr_len, bd_len; - int len; + int len, ret; u16 fp = (u16)-1; u8 bp = 0xff; u8 buffer[64]; @@ -3861,13 +3960,29 @@ static unsigned int ata_scsi_mode_select_xlat(struct ata_queued_cmd *qc) } /* - * No mode subpages supported (yet) but asking for _all_ - * subpages may be valid + * Supported subpages: all subpages and ATA feature sub-page f2h of + * the control page. */ - if (spg && (spg != ALL_SUB_MPAGES)) { - fp = (p[0] & 0x40) ? 1 : 0; - fp += hdr_len + bd_len; - goto invalid_param; + if (spg) { + switch (spg) { + case ALL_SUB_MPAGES: + /* All subpages is not supported for the control page */ + if (pg == CONTROL_MPAGE) { + fp = (p[0] & 0x40) ? 1 : 0; + fp += hdr_len + bd_len; + goto invalid_param; + } + break; + case ATA_FEATURE_SUB_MPAGE: + if (qc->dev->flags & ATA_DFLAG_CDL && + pg == CONTROL_MPAGE) + break; + fallthrough; + default: + fp = (p[0] & 0x40) ? 1 : 0; + fp += hdr_len + bd_len; + goto invalid_param; + } } if (pg_len > len) goto invalid_param_len; @@ -3880,14 +3995,16 @@ static unsigned int ata_scsi_mode_select_xlat(struct ata_queued_cmd *qc) } break; case CONTROL_MPAGE: - if (ata_mselect_control(qc, p, pg_len, &fp) < 0) { + ret = ata_mselect_control(qc, spg, p, pg_len, &fp); + if (ret < 0) { fp += hdr_len + bd_len; goto invalid_param; - } else { - goto skip; /* No ATA command to send */ } + if (!ret) + goto skip; /* No ATA command to send */ break; - default: /* invalid page code */ + default: + /* Invalid page code */ fp = bd_len + hdr_len; goto invalid_param; } diff --git a/include/linux/ata.h b/include/linux/ata.h index 1eda46b63dcc..21108471c6af 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -329,6 +329,7 @@ enum { /* Identify device log pages: */ ATA_LOG_SUPPORTED_CAPABILITIES = 0x03, + ATA_LOG_CURRENT_SETTINGS = 0x04, ATA_LOG_SECURITY = 0x06, ATA_LOG_SATA_SETTINGS = 0x08, ATA_LOG_ZONED_INFORMATION = 0x09, @@ -418,6 +419,8 @@ enum { SETFEATURES_SATA_ENABLE = 0x10, /* Enable use of SATA feature */ SETFEATURES_SATA_DISABLE = 0x90, /* Disable use of SATA feature */ + SETFEATURES_CDL = 0x0d, /* Enable/disable cmd duration limits */ + /* SETFEATURE Sector counts for SATA features */ SATA_FPDMA_OFFSET = 0x01, /* FPDMA non-zero buffer offsets */ SATA_FPDMA_AA = 0x02, /* FPDMA Setup FIS Auto-Activate */ diff --git a/include/linux/libata.h b/include/linux/libata.h index e8a45f7f3f5c..385ca23d5ad0 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -106,6 +106,7 @@ enum { ATA_DFLAG_INIT_MASK = (1 << 20) - 1, ATA_DFLAG_NCQ_PRIO_ENABLED = (1 << 20), /* Priority cmds sent to dev */ + ATA_DFLAG_CDL_ENABLED = (1 << 21), /* cmd duration limits is enabled */ ATA_DFLAG_DETACH = (1 << 24), ATA_DFLAG_DETACHED = (1 << 25), ATA_DFLAG_DA = (1 << 26), /* device supports Device Attention */ -- cgit v1.2.3 From eafe804bda7ba01da562c43351068b8a76a579af Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 11 May 2023 03:13:51 +0200 Subject: scsi: ata: libata: Set read/write commands CDL index For devices supporting the command duration limits feature, translate the dld field of read and write operation to set the command duration limit index field of the command task file when the duration limit feature is enabled. The function ata_set_tf_cdl() is introduced to do this. For unqueued (non NCQ) read and write operations, this function sets the command duration limit index set as the lower 3 bits of the feature field. For queued NCQ read/write commands, the index is set as the lower 3 bits of the auxiliary field. The flag ATA_QCFLAG_HAS_CDL is introduced to indicate that a command taskfile has a non zero cdl field. Signed-off-by: Damien Le Moal Reviewed-by: Igor Pylypiv Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Co-developed-by: Niklas Cassel Signed-off-by: Niklas Cassel Link: https://lore.kernel.org/r/20230511011356.227789-19-nks@flawful.org Signed-off-by: Martin K. Petersen --- drivers/ata/libata-core.c | 32 +++++++++++++++++++++++++++++--- drivers/ata/libata-scsi.c | 16 +++++++++++++++- drivers/ata/libata.h | 2 +- include/linux/libata.h | 1 + 4 files changed, 46 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index cd7aaf202397..e63773740fc2 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -665,12 +665,29 @@ u64 ata_tf_read_block(const struct ata_taskfile *tf, struct ata_device *dev) return block; } +/* + * Set a taskfile command duration limit index. + */ +static inline void ata_set_tf_cdl(struct ata_queued_cmd *qc, int cdl) +{ + struct ata_taskfile *tf = &qc->tf; + + if (tf->protocol == ATA_PROT_NCQ) + tf->auxiliary |= cdl; + else + tf->feature |= cdl; + + /* Mark this command as having a CDL */ + qc->flags |= ATA_QCFLAG_HAS_CDL; +} + /** * ata_build_rw_tf - Build ATA taskfile for given read/write request * @qc: Metadata associated with the taskfile to build * @block: Block address * @n_block: Number of blocks * @tf_flags: RW/FUA etc... + * @cdl: Command duration limit index * @class: IO priority class * * LOCKING: @@ -685,7 +702,7 @@ u64 ata_tf_read_block(const struct ata_taskfile *tf, struct ata_device *dev) * -EINVAL if the request is invalid. */ int ata_build_rw_tf(struct ata_queued_cmd *qc, u64 block, u32 n_block, - unsigned int tf_flags, int class) + unsigned int tf_flags, int cdl, int class) { struct ata_taskfile *tf = &qc->tf; struct ata_device *dev = qc->dev; @@ -724,11 +741,20 @@ int ata_build_rw_tf(struct ata_queued_cmd *qc, u64 block, u32 n_block, if (dev->flags & ATA_DFLAG_NCQ_PRIO_ENABLED && class == IOPRIO_CLASS_RT) tf->hob_nsect |= ATA_PRIO_HIGH << ATA_SHIFT_PRIO; + + if ((dev->flags & ATA_DFLAG_CDL_ENABLED) && cdl) + ata_set_tf_cdl(qc, cdl); + } else if (dev->flags & ATA_DFLAG_LBA) { tf->flags |= ATA_TFLAG_LBA; - /* We need LBA48 for FUA writes */ - if (!(tf->flags & ATA_TFLAG_FUA) && lba_28_ok(block, n_block)) { + if ((dev->flags & ATA_DFLAG_CDL_ENABLED) && cdl) + ata_set_tf_cdl(qc, cdl); + + /* Both FUA writes and a CDL index require 48-bit commands */ + if (!(tf->flags & ATA_TFLAG_FUA) && + !(qc->flags & ATA_QCFLAG_HAS_CDL) && + lba_28_ok(block, n_block)) { /* use LBA28 */ tf->device |= (block >> 24) & 0xf; } else if (lba_48_ok(block, n_block)) { diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 91db4e7f4906..69fc0d2c2123 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1380,6 +1380,18 @@ static inline void scsi_16_lba_len(const u8 *cdb, u64 *plba, u32 *plen) *plen = get_unaligned_be32(&cdb[10]); } +/** + * scsi_dld - Get duration limit descriptor index + * @cdb: SCSI command to translate + * + * Returns the dld bits indicating the index of a command duration limit + * descriptor. + */ +static inline int scsi_dld(const u8 *cdb) +{ + return ((cdb[1] & 0x01) << 2) | ((cdb[14] >> 6) & 0x03); +} + /** * ata_scsi_verify_xlat - Translate SCSI VERIFY command into an ATA one * @qc: Storage for translated ATA taskfile @@ -1548,6 +1560,7 @@ static unsigned int ata_scsi_rw_xlat(struct ata_queued_cmd *qc) struct request *rq = scsi_cmd_to_rq(scmd); int class = IOPRIO_PRIO_CLASS(req_get_ioprio(rq)); unsigned int tf_flags = 0; + int dld = 0; u64 block; u32 n_block; int rc; @@ -1598,6 +1611,7 @@ static unsigned int ata_scsi_rw_xlat(struct ata_queued_cmd *qc) goto invalid_fld; } scsi_16_lba_len(cdb, &block, &n_block); + dld = scsi_dld(cdb); if (cdb[1] & (1 << 3)) tf_flags |= ATA_TFLAG_FUA; if (!ata_check_nblocks(scmd, n_block)) @@ -1622,7 +1636,7 @@ static unsigned int ata_scsi_rw_xlat(struct ata_queued_cmd *qc) qc->flags |= ATA_QCFLAG_IO; qc->nbytes = n_block * scmd->device->sector_size; - rc = ata_build_rw_tf(qc, block, n_block, tf_flags, class); + rc = ata_build_rw_tf(qc, block, n_block, tf_flags, dld, class); if (likely(rc == 0)) return 0; diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h index 926d0d33cd29..cf993885d2b2 100644 --- a/drivers/ata/libata.h +++ b/drivers/ata/libata.h @@ -45,7 +45,7 @@ static inline void ata_force_cbl(struct ata_port *ap) { } extern u64 ata_tf_to_lba(const struct ata_taskfile *tf); extern u64 ata_tf_to_lba48(const struct ata_taskfile *tf); extern int ata_build_rw_tf(struct ata_queued_cmd *qc, u64 block, u32 n_block, - unsigned int tf_flags, int class); + unsigned int tf_flags, int dld, int class); extern u64 ata_tf_read_block(const struct ata_taskfile *tf, struct ata_device *dev); extern unsigned ata_exec_internal(struct ata_device *dev, diff --git a/include/linux/libata.h b/include/linux/libata.h index 385ca23d5ad0..f679abd2e61f 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -209,6 +209,7 @@ enum { ATA_QCFLAG_CLEAR_EXCL = (1 << 5), /* clear excl_link on completion */ ATA_QCFLAG_QUIET = (1 << 6), /* don't report device error */ ATA_QCFLAG_RETRY = (1 << 7), /* retry after failure */ + ATA_QCFLAG_HAS_CDL = (1 << 8), /* qc has CDL a descriptor set */ ATA_QCFLAG_EH = (1 << 16), /* cmd aborted and owned by EH */ ATA_QCFLAG_SENSE_VALID = (1 << 17), /* sense data valid */ -- cgit v1.2.3 From 18bd7718b5c489b3161b6c2ab4685d57c1e2da3b Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Thu, 11 May 2023 03:13:52 +0200 Subject: scsi: ata: libata: Handle completion of CDL commands using policy 0xD A CDL timeout for policy 0xF is defined as a NCQ error, just with a CDL specific sk/asc/ascq in the sense data. Therefore, the existing code in libata does not need to be modified to handle a policy 0xF CDL timeout. For Command Duration Limits policy 0xD: The device shall complete the command without error with the additional sense code set to DATA CURRENTLY UNAVAILABLE. Since a CDL timeout for policy 0xD is not an error, we cannot use the NCQ Command Error log (10h). Instead, we need to read the Sense Data for Successful NCQ Commands log (0Fh). In the success case, just like in the error case, we cannot simply read a log page from the interrupt handler itself, since reading a log page involves sending a READ LOG DMA EXT or READ LOG EXT command. Therefore, we add a new EH action ATA_EH_GET_SUCCESS_SENSE. When a command completes without error, and when the ATA_SENSE bit is set, this new action is set as pending, and EH is scheduled. This way, similar to the NCQ error case, the log page will be read from EH context. An alternative would have been to add a new kthread or workqueue to handle this. However, extending EH can be done with minimal changes and avoids the need to synchronize a new kthread/workqueue with EH. Co-developed-by: Damien Le Moal Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Signed-off-by: Niklas Cassel Link: https://lore.kernel.org/r/20230511011356.227789-20-nks@flawful.org Signed-off-by: Martin K. Petersen --- drivers/ata/libata-core.c | 88 +++++++++++++++++++++++++++++++++++++- drivers/ata/libata-eh.c | 105 +++++++++++++++++++++++++++++++++++++++++++++- drivers/ata/libata-sata.c | 92 ++++++++++++++++++++++++++++++++++++++++ include/linux/ata.h | 3 ++ include/linux/libata.h | 11 ++++- 5 files changed, 295 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index e63773740fc2..ddc3d9f8fa02 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -677,8 +677,12 @@ static inline void ata_set_tf_cdl(struct ata_queued_cmd *qc, int cdl) else tf->feature |= cdl; - /* Mark this command as having a CDL */ - qc->flags |= ATA_QCFLAG_HAS_CDL; + /* + * Mark this command as having a CDL and request the result + * task file so that we can inspect the sense data available + * bit on completion. + */ + qc->flags |= ATA_QCFLAG_HAS_CDL | ATA_QCFLAG_RESULT_TF; } /** @@ -2424,6 +2428,24 @@ static void ata_dev_config_cdl(struct ata_device *dev) ata_dev_warn(dev, "Command duration guideline is not supported\n"); + /* + * We must have support for the sense data for successful NCQ commands + * log indicated by the successful NCQ command sense data supported bit. + */ + val = get_unaligned_le64(&ap->sector_buf[8]); + if (!(val & BIT_ULL(63)) || !(val & BIT_ULL(47))) { + ata_dev_warn(dev, + "CDL supported but Successful NCQ Command Sense Data is not supported\n"); + goto not_supported; + } + + /* Without NCQ autosense, the successful NCQ commands log is useless. */ + if (!ata_id_has_ncq_autosense(dev->id)) { + ata_dev_warn(dev, + "CDL supported but NCQ autosense is not supported\n"); + goto not_supported; + } + /* * If CDL is marked as enabled, make sure the feature is enabled too. * Conversely, if CDL is disabled, make sure the feature is turned off. @@ -2458,6 +2480,35 @@ static void ata_dev_config_cdl(struct ata_device *dev) } } + /* + * While CDL itself has to be enabled using sysfs, CDL requires that + * sense data for successful NCQ commands is enabled to work properly. + * Just like ata_dev_config_sense_reporting(), enable it unconditionally + * if supported. + */ + if (!(val & BIT_ULL(63)) || !(val & BIT_ULL(18))) { + err_mask = ata_dev_set_feature(dev, + SETFEATURE_SENSE_DATA_SUCC_NCQ, 0x1); + if (err_mask) { + ata_dev_warn(dev, + "failed to enable Sense Data for successful NCQ commands, Emask 0x%x\n", + err_mask); + goto not_supported; + } + } + + /* + * Allocate a buffer to handle reading the sense data for successful + * NCQ Commands log page for commands using a CDL with one of the limit + * policy set to 0xD (successful completion with sense data available + * bit set). + */ + if (!ap->ncq_sense_buf) { + ap->ncq_sense_buf = kmalloc(ATA_LOG_SENSE_NCQ_SIZE, GFP_KERNEL); + if (!ap->ncq_sense_buf) + goto not_supported; + } + /* * Command duration limits is supported: cache the CDL log page 18h * (command duration descriptors). @@ -2475,6 +2526,8 @@ static void ata_dev_config_cdl(struct ata_device *dev) not_supported: dev->flags &= ~(ATA_DFLAG_CDL | ATA_DFLAG_CDL_ENABLED); + kfree(ap->ncq_sense_buf); + ap->ncq_sense_buf = NULL; } static int ata_dev_config_lba(struct ata_device *dev) @@ -4878,6 +4931,36 @@ void ata_qc_complete(struct ata_queued_cmd *qc) fill_result_tf(qc); trace_ata_qc_complete_done(qc); + + /* + * For CDL commands that completed without an error, check if + * we have sense data (ATA_SENSE is set). If we do, then the + * command may have been aborted by the device due to a limit + * timeout using the policy 0xD. For these commands, invoke EH + * to get the command sense data. + */ + if (qc->result_tf.status & ATA_SENSE && + ((ata_is_ncq(qc->tf.protocol) && + dev->flags & ATA_DFLAG_CDL_ENABLED) || + (!(ata_is_ncq(qc->tf.protocol) && + ata_id_sense_reporting_enabled(dev->id))))) { + /* + * Tell SCSI EH to not overwrite scmd->result even if + * this command is finished with result SAM_STAT_GOOD. + */ + qc->scsicmd->flags |= SCMD_FORCE_EH_SUCCESS; + qc->flags |= ATA_QCFLAG_EH_SUCCESS_CMD; + ehi->dev_action[dev->devno] |= ATA_EH_GET_SUCCESS_SENSE; + + /* + * set pending so that ata_qc_schedule_eh() does not + * trigger fast drain, and freeze the port. + */ + ap->pflags |= ATA_PFLAG_EH_PENDING; + ata_qc_schedule_eh(qc); + return; + } + /* Some commands need post-processing after successful * completion. */ @@ -5510,6 +5593,7 @@ static void ata_host_release(struct kref *kref) kfree(ap->pmp_link); kfree(ap->slave_link); + kfree(ap->ncq_sense_buf); kfree(ap); host->ports[i] = NULL; } diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index 598ae07195b6..05af292eb8ce 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -1917,6 +1917,99 @@ static inline bool ata_eh_quiet(struct ata_queued_cmd *qc) return qc->flags & ATA_QCFLAG_QUIET; } +static int ata_eh_read_sense_success_non_ncq(struct ata_link *link) +{ + struct ata_port *ap = link->ap; + struct ata_queued_cmd *qc; + + qc = __ata_qc_from_tag(ap, link->active_tag); + if (!qc) + return -EIO; + + if (!(qc->flags & ATA_QCFLAG_EH) || + !(qc->flags & ATA_QCFLAG_EH_SUCCESS_CMD) || + qc->err_mask) + return -EIO; + + if (!ata_eh_request_sense(qc)) + return -EIO; + + /* + * If we have sense data, call scsi_check_sense() in order to set the + * correct SCSI ML byte (if any). No point in checking the return value, + * since the command has already completed successfully. + */ + scsi_check_sense(qc->scsicmd); + + return 0; +} + +static void ata_eh_get_success_sense(struct ata_link *link) +{ + struct ata_eh_context *ehc = &link->eh_context; + struct ata_device *dev = link->device; + struct ata_port *ap = link->ap; + struct ata_queued_cmd *qc; + int tag, ret = 0; + + if (!(ehc->i.dev_action[dev->devno] & ATA_EH_GET_SUCCESS_SENSE)) + return; + + /* if frozen, we can't do much */ + if (ata_port_is_frozen(ap)) { + ata_dev_warn(dev, + "successful sense data available but port frozen\n"); + goto out; + } + + /* + * If the link has sactive set, then we have outstanding NCQ commands + * and have to read the Successful NCQ Commands log to get the sense + * data. Otherwise, we are dealing with a non-NCQ command and use + * request sense ext command to retrieve the sense data. + */ + if (link->sactive) + ret = ata_eh_read_sense_success_ncq_log(link); + else + ret = ata_eh_read_sense_success_non_ncq(link); + if (ret) + goto out; + + ata_eh_done(link, dev, ATA_EH_GET_SUCCESS_SENSE); + return; + +out: + /* + * If we failed to get sense data for a successful command that ought to + * have sense data, we cannot simply return BLK_STS_OK to user space. + * This is because we can't know if the sense data that we couldn't get + * was actually "DATA CURRENTLY UNAVAILABLE". Reporting such a command + * as success to user space would result in a silent data corruption. + * Thus, add a bogus ABORTED_COMMAND sense data to such commands, such + * that SCSI will report these commands as BLK_STS_IOERR to user space. + */ + ata_qc_for_each_raw(ap, qc, tag) { + if (!(qc->flags & ATA_QCFLAG_EH) || + !(qc->flags & ATA_QCFLAG_EH_SUCCESS_CMD) || + qc->err_mask || + ata_dev_phys_link(qc->dev) != link) + continue; + + /* We managed to get sense for this success command, skip. */ + if (qc->flags & ATA_QCFLAG_SENSE_VALID) + continue; + + /* This success command did not have any sense data, skip. */ + if (!(qc->result_tf.status & ATA_SENSE)) + continue; + + /* This success command had sense data, but we failed to get. */ + ata_scsi_set_sense(dev, qc->scsicmd, ABORTED_COMMAND, 0, 0); + qc->flags |= ATA_QCFLAG_SENSE_VALID; + } + ata_eh_done(link, dev, ATA_EH_GET_SUCCESS_SENSE); +} + /** * ata_eh_link_autopsy - analyze error and determine recovery action * @link: host link to perform autopsy on @@ -1957,6 +2050,14 @@ static void ata_eh_link_autopsy(struct ata_link *link) /* analyze NCQ failure */ ata_eh_analyze_ncq_error(link); + /* + * Check if this was a successful command that simply needs sense data. + * Since the sense data is not part of the completion, we need to fetch + * it using an additional command. Since this can't be done from irq + * context, the sense data for successful commands are fetched by EH. + */ + ata_eh_get_success_sense(link); + /* any real error trumps AC_ERR_OTHER */ if (ehc->i.err_mask & ~AC_ERR_OTHER) ehc->i.err_mask &= ~AC_ERR_OTHER; @@ -1966,6 +2067,7 @@ static void ata_eh_link_autopsy(struct ata_link *link) ata_qc_for_each_raw(ap, qc, tag) { if (!(qc->flags & ATA_QCFLAG_EH) || qc->flags & ATA_QCFLAG_RETRY || + qc->flags & ATA_QCFLAG_EH_SUCCESS_CMD || ata_dev_phys_link(qc->dev) != link) continue; @@ -3825,7 +3927,8 @@ void ata_eh_finish(struct ata_port *ap) else ata_eh_qc_complete(qc); } else { - if (qc->flags & ATA_QCFLAG_SENSE_VALID) { + if (qc->flags & ATA_QCFLAG_SENSE_VALID || + qc->flags & ATA_QCFLAG_EH_SUCCESS_CMD) { ata_eh_qc_complete(qc); } else { /* feed zero TF to sense generation */ diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c index 57cb33060c9d..7de4d8901fac 100644 --- a/drivers/ata/libata-sata.c +++ b/drivers/ata/libata-sata.c @@ -11,7 +11,9 @@ #include #include #include +#include #include +#include #include "libata.h" #include "libata-transport.h" @@ -1408,6 +1410,95 @@ static int ata_eh_read_log_10h(struct ata_device *dev, return 0; } +/** + * ata_eh_read_sense_success_ncq_log - Read the sense data for successful + * NCQ commands log + * @link: ATA link to get sense data for + * + * Read the sense data for successful NCQ commands log page to obtain + * sense data for all NCQ commands that completed successfully with + * the sense data available bit set. + * + * LOCKING: + * Kernel thread context (may sleep). + * + * RETURNS: + * 0 on success, -errno otherwise. + */ +int ata_eh_read_sense_success_ncq_log(struct ata_link *link) +{ + struct ata_device *dev = link->device; + struct ata_port *ap = dev->link->ap; + u8 *buf = ap->ncq_sense_buf; + struct ata_queued_cmd *qc; + unsigned int err_mask, tag; + u8 *sense, sk = 0, asc = 0, ascq = 0; + u64 sense_valid, val; + int ret = 0; + + err_mask = ata_read_log_page(dev, ATA_LOG_SENSE_NCQ, 0, buf, 2); + if (err_mask) { + ata_dev_err(dev, + "Failed to read Sense Data for Successful NCQ Commands log\n"); + return -EIO; + } + + /* Check the log header */ + val = get_unaligned_le64(&buf[0]); + if ((val & 0xffff) != 1 || ((val >> 16) & 0xff) != 0x0f) { + ata_dev_err(dev, + "Invalid Sense Data for Successful NCQ Commands log\n"); + return -EIO; + } + + sense_valid = (u64)buf[8] | ((u64)buf[9] << 8) | + ((u64)buf[10] << 16) | ((u64)buf[11] << 24); + + ata_qc_for_each_raw(ap, qc, tag) { + if (!(qc->flags & ATA_QCFLAG_EH) || + !(qc->flags & ATA_QCFLAG_EH_SUCCESS_CMD) || + qc->err_mask || + ata_dev_phys_link(qc->dev) != link) + continue; + + /* + * If the command does not have any sense data, clear ATA_SENSE. + * Keep ATA_QCFLAG_EH_SUCCESS_CMD so that command is finished. + */ + if (!(sense_valid & (1ULL << tag))) { + qc->result_tf.status &= ~ATA_SENSE; + continue; + } + + sense = &buf[32 + 24 * tag]; + sk = sense[0]; + asc = sense[1]; + ascq = sense[2]; + + if (!ata_scsi_sense_is_valid(sk, asc, ascq)) { + ret = -EIO; + continue; + } + + /* Set sense without also setting scsicmd->result */ + scsi_build_sense_buffer(dev->flags & ATA_DFLAG_D_SENSE, + qc->scsicmd->sense_buffer, sk, + asc, ascq); + qc->flags |= ATA_QCFLAG_SENSE_VALID; + + /* + * If we have sense data, call scsi_check_sense() in order to + * set the correct SCSI ML byte (if any). No point in checking + * the return value, since the command has already completed + * successfully. + */ + scsi_check_sense(qc->scsicmd); + } + + return ret; +} +EXPORT_SYMBOL_GPL(ata_eh_read_sense_success_ncq_log); + /** * ata_eh_analyze_ncq_error - analyze NCQ error * @link: ATA link to analyze NCQ error for @@ -1488,6 +1579,7 @@ void ata_eh_analyze_ncq_error(struct ata_link *link) ata_qc_for_each_raw(ap, qc, tag) { if (!(qc->flags & ATA_QCFLAG_EH) || + qc->flags & ATA_QCFLAG_EH_SUCCESS_CMD || ata_dev_phys_link(qc->dev) != link) continue; diff --git a/include/linux/ata.h b/include/linux/ata.h index 21108471c6af..792e10a09787 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -325,6 +325,8 @@ enum { ATA_LOG_CDL = 0x18, ATA_LOG_CDL_SIZE = ATA_SECT_SIZE, ATA_LOG_IDENTIFY_DEVICE = 0x30, + ATA_LOG_SENSE_NCQ = 0x0F, + ATA_LOG_SENSE_NCQ_SIZE = ATA_SECT_SIZE * 2, ATA_LOG_CONCURRENT_POSITIONING_RANGES = 0x47, /* Identify device log pages: */ @@ -431,6 +433,7 @@ enum { SATA_DEVSLP = 0x09, /* Device Sleep */ SETFEATURE_SENSE_DATA = 0xC3, /* Sense Data Reporting feature */ + SETFEATURE_SENSE_DATA_SUCC_NCQ = 0xC4, /* Sense Data for successful NCQ commands */ /* feature values for SET_MAX */ ATA_SET_MAX_ADDR = 0x00, diff --git a/include/linux/libata.h b/include/linux/libata.h index f679abd2e61f..5c8ef33b0af2 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -214,6 +214,7 @@ enum { ATA_QCFLAG_EH = (1 << 16), /* cmd aborted and owned by EH */ ATA_QCFLAG_SENSE_VALID = (1 << 17), /* sense data valid */ ATA_QCFLAG_EH_SCHEDULED = (1 << 18), /* EH scheduled (obsolete) */ + ATA_QCFLAG_EH_SUCCESS_CMD = (1 << 19), /* EH should fetch sense for this successful cmd */ /* host set flags */ ATA_HOST_SIMPLEX = (1 << 0), /* Host is simplex, one DMA channel per host only */ @@ -312,8 +313,10 @@ enum { ATA_EH_RESET = ATA_EH_SOFTRESET | ATA_EH_HARDRESET, ATA_EH_ENABLE_LINK = (1 << 3), ATA_EH_PARK = (1 << 5), /* unload heads and stop I/O */ + ATA_EH_GET_SUCCESS_SENSE = (1 << 6), /* Get sense data for successful cmd */ - ATA_EH_PERDEV_MASK = ATA_EH_REVALIDATE | ATA_EH_PARK, + ATA_EH_PERDEV_MASK = ATA_EH_REVALIDATE | ATA_EH_PARK | + ATA_EH_GET_SUCCESS_SENSE, ATA_EH_ALL_ACTIONS = ATA_EH_REVALIDATE | ATA_EH_RESET | ATA_EH_ENABLE_LINK, @@ -867,6 +870,7 @@ struct ata_port { struct ata_acpi_gtm __acpi_init_gtm; /* use ata_acpi_init_gtm() */ #endif /* owned by EH */ + u8 *ncq_sense_buf; u8 sector_buf[ATA_SECT_SIZE] ____cacheline_aligned; }; @@ -1185,6 +1189,7 @@ extern int sata_link_hardreset(struct ata_link *link, bool *online, int (*check_ready)(struct ata_link *)); extern int sata_link_resume(struct ata_link *link, const unsigned long *params, unsigned long deadline); +extern int ata_eh_read_sense_success_ncq_log(struct ata_link *link); extern void ata_eh_analyze_ncq_error(struct ata_link *link); #else static inline const unsigned long * @@ -1222,6 +1227,10 @@ static inline int sata_link_resume(struct ata_link *link, { return -EOPNOTSUPP; } +static inline int ata_eh_read_sense_success_ncq_log(struct ata_link *link) +{ + return -EOPNOTSUPP; +} static inline void ata_eh_analyze_ncq_error(struct ata_link *link) { } #endif extern int sata_link_debounce(struct ata_link *link, -- cgit v1.2.3 From 8bb1c6243c4ba397958fe67837e075bd1bb8d3b4 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Thu, 18 May 2023 12:31:58 -0700 Subject: scsi: core: Trace SCSI sense data If a command fails, SCSI sense data is essential to determine why it failed. Hence make the sense key, ASC and ASCQ codes available in the ftrace output. Cc: Niklas Cassel Cc: Christoph Hellwig Cc: Ming Lei Cc: Hannes Reinecke Cc: John Garry Cc: Mike Christie Signed-off-by: Bart Van Assche Link: https://lore.kernel.org/r/20230518193159.1166304-3-bvanassche@acm.org Reviewed-by: Ming Lei Reviewed-by: Niklas Cassel Signed-off-by: Martin K. Petersen --- include/trace/events/scsi.h | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/trace/events/scsi.h b/include/trace/events/scsi.h index a2c7befd451a..8e2d9b1b0e77 100644 --- a/include/trace/events/scsi.h +++ b/include/trace/events/scsi.h @@ -269,9 +269,14 @@ DECLARE_EVENT_CLASS(scsi_cmd_done_timeout_template, __field( unsigned int, prot_sglen ) __field( unsigned char, prot_op ) __dynamic_array(unsigned char, cmnd, cmd->cmd_len) + __field( u8, sense_key ) + __field( u8, asc ) + __field( u8, ascq ) ), TP_fast_assign( + struct scsi_sense_hdr sshdr; + __entry->host_no = cmd->device->host->host_no; __entry->channel = cmd->device->channel; __entry->id = cmd->device->id; @@ -285,11 +290,22 @@ DECLARE_EVENT_CLASS(scsi_cmd_done_timeout_template, __entry->prot_sglen = scsi_prot_sg_count(cmd); __entry->prot_op = scsi_get_prot_op(cmd); memcpy(__get_dynamic_array(cmnd), cmd->cmnd, cmd->cmd_len); + if (cmd->sense_buffer && SCSI_SENSE_VALID(cmd) && + scsi_command_normalize_sense(cmd, &sshdr)) { + __entry->sense_key = sshdr.sense_key; + __entry->asc = sshdr.asc; + __entry->ascq = sshdr.ascq; + } else { + __entry->sense_key = 0; + __entry->asc = 0; + __entry->ascq = 0; + } ), TP_printk("host_no=%u channel=%u id=%u lun=%u data_sgl=%u prot_sgl=%u " \ "prot_op=%s driver_tag=%d scheduler_tag=%d cmnd=(%s %s raw=%s) " \ - "result=(driver=%s host=%s message=%s status=%s)", + "result=(driver=%s host=%s message=%s status=%s) " + "sense=(key=%#x asc=%#x ascq=%#x)", __entry->host_no, __entry->channel, __entry->id, __entry->lun, __entry->data_sglen, __entry->prot_sglen, show_prot_op_name(__entry->prot_op), __entry->driver_tag, @@ -299,7 +315,8 @@ DECLARE_EVENT_CLASS(scsi_cmd_done_timeout_template, "DRIVER_OK", show_hostbyte_name(((__entry->result) >> 16) & 0xff), "COMMAND_COMPLETE", - show_statusbyte_name(__entry->result & 0xff)) + show_statusbyte_name(__entry->result & 0xff), + __entry->sense_key, __entry->asc, __entry->ascq) ); DEFINE_EVENT(scsi_cmd_done_timeout_template, scsi_dispatch_cmd_done, -- cgit v1.2.3 From b125bb99559e3639764b8d169e3e9b80858fa2af Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Mon, 29 May 2023 13:26:37 -0700 Subject: scsi: core: Support setting BLK_MQ_F_BLOCKING Prepare for adding code in ufshcd_queuecommand() that may sleep. This patch is similar to a patch posted last year by Mike Christie. See also https://lore.kernel.org/all/20220308003957.123312-2-michael.christie@oracle.com/ Cc: Mike Christie Signed-off-by: Bart Van Assche Link: https://lore.kernel.org/r/20230529202640.11883-3-bvanassche@acm.org Signed-off-by: Martin K. Petersen --- drivers/scsi/hosts.c | 1 + drivers/scsi/scsi_lib.c | 11 ++++------- include/scsi/scsi_host.h | 6 ++++++ 3 files changed, 11 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index f0bc8bbb3938..198edf03f929 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -441,6 +441,7 @@ struct Scsi_Host *scsi_host_alloc(const struct scsi_host_template *sht, int priv shost->cmd_per_lun = sht->cmd_per_lun; shost->no_write_same = sht->no_write_same; shost->host_tagset = sht->host_tagset; + shost->queuecommand_may_block = sht->queuecommand_may_block; if (shost_eh_deadline == -1 || !sht->eh_host_reset_handler) shost->eh_deadline = -1; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 758a57616dd3..c7588c451e30 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1982,6 +1982,8 @@ int scsi_mq_setup_tags(struct Scsi_Host *shost) tag_set->flags = BLK_MQ_F_SHOULD_MERGE; tag_set->flags |= BLK_ALLOC_POLICY_TO_MQ_FLAG(shost->hostt->tag_alloc_policy); + if (shost->queuecommand_may_block) + tag_set->flags |= BLK_MQ_F_BLOCKING; tag_set->driver_data = shost; if (shost->host_tagset) tag_set->flags |= BLK_MQ_F_TAG_HCTX_SHARED; @@ -2968,13 +2970,8 @@ scsi_host_block(struct Scsi_Host *shost) } } - /* - * SCSI never enables blk-mq's BLK_MQ_F_BLOCKING flag so - * calling synchronize_rcu() once is enough. - */ - WARN_ON_ONCE(shost->tag_set.flags & BLK_MQ_F_BLOCKING); - - synchronize_rcu(); + /* Wait for ongoing scsi_queue_rq() calls to finish. */ + blk_mq_wait_quiesce_done(&shost->tag_set); return 0; } diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index 0f29799efa02..70b7475dcf56 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -458,6 +458,9 @@ struct scsi_host_template { /* True if the host uses host-wide tagspace */ unsigned host_tagset:1; + /* The queuecommand callback may block. See also BLK_MQ_F_BLOCKING. */ + unsigned queuecommand_may_block:1; + /* * Countdown for host blocking with no commands outstanding. */ @@ -653,6 +656,9 @@ struct Scsi_Host { /* True if the host uses host-wide tagspace */ unsigned host_tagset:1; + /* The queuecommand callback may block. See also BLK_MQ_F_BLOCKING. */ + unsigned queuecommand_may_block:1; + /* Host responded with short (<36 bytes) INQUIRY result */ unsigned short_inquiry:1; -- cgit v1.2.3 From 078f4f4b34d6c2dadabb363d3fc6c84b32927dea Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Mon, 29 May 2023 13:26:40 -0700 Subject: scsi: ufs: Ungate the clock synchronously Ungating the clock asynchronously causes ufshcd_queuecommand() to return SCSI_MLQUEUE_HOST_BUSY and hence causes commands to be requeued. This is suboptimal. Allow ufshcd_queuecommand() to sleep such that clock ungating does not trigger command requeuing. Remove the ufshcd_scsi_block_requests() and ufshcd_scsi_unblock_requests() calls because these are no longer needed. The flush_work(&hba->clk_gating.ungate_work) call is sufficient to make the SCSI core wait for clock ungating to complete. Acked-by: Adrian Hunter Signed-off-by: Bart Van Assche Link: https://lore.kernel.org/r/20230529202640.11883-6-bvanassche@acm.org Reviewed-by: Bean Huo Reviewed-by: Bao D. Nguyen Signed-off-by: Martin K. Petersen --- drivers/ufs/core/ufs-sysfs.c | 2 +- drivers/ufs/core/ufshcd-crypto.c | 2 +- drivers/ufs/core/ufshcd.c | 86 +++++++++++++--------------------------- include/ufs/ufshcd.h | 2 +- 4 files changed, 30 insertions(+), 62 deletions(-) (limited to 'include') diff --git a/drivers/ufs/core/ufs-sysfs.c b/drivers/ufs/core/ufs-sysfs.c index 883f0e44b54e..cdf3d5f2b77b 100644 --- a/drivers/ufs/core/ufs-sysfs.c +++ b/drivers/ufs/core/ufs-sysfs.c @@ -168,7 +168,7 @@ static ssize_t auto_hibern8_show(struct device *dev, } pm_runtime_get_sync(hba->dev); - ufshcd_hold(hba, false); + ufshcd_hold(hba); ahit = ufshcd_readl(hba, REG_AUTO_HIBERNATE_IDLE_TIMER); ufshcd_release(hba); pm_runtime_put_sync(hba->dev); diff --git a/drivers/ufs/core/ufshcd-crypto.c b/drivers/ufs/core/ufshcd-crypto.c index 198360fe5e8e..f2c4422cab86 100644 --- a/drivers/ufs/core/ufshcd-crypto.c +++ b/drivers/ufs/core/ufshcd-crypto.c @@ -24,7 +24,7 @@ static int ufshcd_program_key(struct ufs_hba *hba, u32 slot_offset = hba->crypto_cfg_register + slot * sizeof(*cfg); int err = 0; - ufshcd_hold(hba, false); + ufshcd_hold(hba); if (hba->vops && hba->vops->program_key) { err = hba->vops->program_key(hba, cfg, slot); diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index e093ce33887c..92436bd827be 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -1205,7 +1205,7 @@ static int ufshcd_wait_for_doorbell_clr(struct ufs_hba *hba, bool timeout = false, do_last_check = false; ktime_t start; - ufshcd_hold(hba, false); + ufshcd_hold(hba); spin_lock_irqsave(hba->host->host_lock, flags); /* * Wait for all the outstanding tasks/transfer requests. @@ -1326,7 +1326,7 @@ static int ufshcd_clock_scaling_prepare(struct ufs_hba *hba, u64 timeout_us) } /* let's not get into low power until clock scaling is completed */ - ufshcd_hold(hba, false); + ufshcd_hold(hba); out: return ret; @@ -1656,7 +1656,7 @@ static ssize_t ufshcd_clkscale_enable_store(struct device *dev, goto out; ufshcd_rpm_get_sync(hba); - ufshcd_hold(hba, false); + ufshcd_hold(hba); hba->clk_scaling.is_enabled = value; @@ -1739,7 +1739,7 @@ static void ufshcd_ungate_work(struct work_struct *work) spin_lock_irqsave(hba->host->host_lock, flags); if (hba->clk_gating.state == CLKS_ON) { spin_unlock_irqrestore(hba->host->host_lock, flags); - goto unblock_reqs; + return; } spin_unlock_irqrestore(hba->host->host_lock, flags); @@ -1762,25 +1762,21 @@ static void ufshcd_ungate_work(struct work_struct *work) } hba->clk_gating.is_suspended = false; } -unblock_reqs: - ufshcd_scsi_unblock_requests(hba); } /** * ufshcd_hold - Enable clocks that were gated earlier due to ufshcd_release. * Also, exit from hibern8 mode and set the link as active. * @hba: per adapter instance - * @async: This indicates whether caller should ungate clocks asynchronously. */ -int ufshcd_hold(struct ufs_hba *hba, bool async) +void ufshcd_hold(struct ufs_hba *hba) { - int rc = 0; bool flush_result; unsigned long flags; if (!ufshcd_is_clkgating_allowed(hba) || !hba->clk_gating.is_initialized) - goto out; + return; spin_lock_irqsave(hba->host->host_lock, flags); hba->clk_gating.active_reqs++; @@ -1797,15 +1793,10 @@ start: */ if (ufshcd_can_hibern8_during_gating(hba) && ufshcd_is_link_hibern8(hba)) { - if (async) { - rc = -EAGAIN; - hba->clk_gating.active_reqs--; - break; - } spin_unlock_irqrestore(hba->host->host_lock, flags); flush_result = flush_work(&hba->clk_gating.ungate_work); if (hba->clk_gating.is_suspended && !flush_result) - goto out; + return; spin_lock_irqsave(hba->host->host_lock, flags); goto start; } @@ -1827,21 +1818,14 @@ start: hba->clk_gating.state = REQ_CLKS_ON; trace_ufshcd_clk_gating(dev_name(hba->dev), hba->clk_gating.state); - if (queue_work(hba->clk_gating.clk_gating_workq, - &hba->clk_gating.ungate_work)) - ufshcd_scsi_block_requests(hba); + queue_work(hba->clk_gating.clk_gating_workq, + &hba->clk_gating.ungate_work); /* * fall through to check if we should wait for this * work to be done or not. */ fallthrough; case REQ_CLKS_ON: - if (async) { - rc = -EAGAIN; - hba->clk_gating.active_reqs--; - break; - } - spin_unlock_irqrestore(hba->host->host_lock, flags); flush_work(&hba->clk_gating.ungate_work); /* Make sure state is CLKS_ON before returning */ @@ -1853,8 +1837,6 @@ start: break; } spin_unlock_irqrestore(hba->host->host_lock, flags); -out: - return rc; } EXPORT_SYMBOL_GPL(ufshcd_hold); @@ -2086,7 +2068,7 @@ static void ufshcd_exit_clk_gating(struct ufs_hba *hba) ufshcd_remove_clk_gating_sysfs(hba); /* Ungate the clock if necessary. */ - ufshcd_hold(hba, false); + ufshcd_hold(hba); hba->clk_gating.is_initialized = false; ufshcd_release(hba); @@ -2482,7 +2464,7 @@ int ufshcd_send_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd) if (hba->quirks & UFSHCD_QUIRK_BROKEN_UIC_CMD) return 0; - ufshcd_hold(hba, false); + ufshcd_hold(hba); mutex_lock(&hba->uic_cmd_mutex); ufshcd_add_delay_before_dme_cmd(hba); @@ -2885,12 +2867,6 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd) WARN_ONCE(tag < 0 || tag >= hba->nutrs, "Invalid tag %d\n", tag); - /* - * Allows the UFS error handler to wait for prior ufshcd_queuecommand() - * calls. - */ - rcu_read_lock(); - switch (hba->ufshcd_state) { case UFSHCD_STATE_OPERATIONAL: break; @@ -2936,13 +2912,7 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd) hba->req_abort_count = 0; - err = ufshcd_hold(hba, true); - if (err) { - err = SCSI_MLQUEUE_HOST_BUSY; - goto out; - } - WARN_ON(ufshcd_is_clkgating_allowed(hba) && - (hba->clk_gating.state != CLKS_ON)); + ufshcd_hold(hba); lrbp = &hba->lrb[tag]; WARN_ON(lrbp->cmd); @@ -2972,8 +2942,6 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd) ufshcd_send_command(hba, tag, hwq); out: - rcu_read_unlock(); - if (ufs_trigger_eh()) { unsigned long flags; @@ -3267,7 +3235,7 @@ int ufshcd_query_flag(struct ufs_hba *hba, enum query_opcode opcode, BUG_ON(!hba); - ufshcd_hold(hba, false); + ufshcd_hold(hba); mutex_lock(&hba->dev_cmd.lock); ufshcd_init_query(hba, &request, &response, opcode, idn, index, selector); @@ -3341,7 +3309,7 @@ int ufshcd_query_attr(struct ufs_hba *hba, enum query_opcode opcode, return -EINVAL; } - ufshcd_hold(hba, false); + ufshcd_hold(hba); mutex_lock(&hba->dev_cmd.lock); ufshcd_init_query(hba, &request, &response, opcode, idn, index, @@ -3437,7 +3405,7 @@ static int __ufshcd_query_descriptor(struct ufs_hba *hba, return -EINVAL; } - ufshcd_hold(hba, false); + ufshcd_hold(hba); mutex_lock(&hba->dev_cmd.lock); ufshcd_init_query(hba, &request, &response, opcode, idn, index, @@ -4255,7 +4223,7 @@ int ufshcd_uic_change_pwr_mode(struct ufs_hba *hba, u8 mode) uic_cmd.command = UIC_CMD_DME_SET; uic_cmd.argument1 = UIC_ARG_MIB(PA_PWRMODE); uic_cmd.argument3 = mode; - ufshcd_hold(hba, false); + ufshcd_hold(hba); ret = ufshcd_uic_pwr_ctrl(hba, &uic_cmd); ufshcd_release(hba); @@ -4362,7 +4330,7 @@ void ufshcd_auto_hibern8_update(struct ufs_hba *hba, u32 ahit) if (update && !pm_runtime_suspended(&hba->ufs_device_wlun->sdev_gendev)) { ufshcd_rpm_get_sync(hba); - ufshcd_hold(hba, false); + ufshcd_hold(hba); ufshcd_auto_hibern8_enable(hba); ufshcd_release(hba); ufshcd_rpm_put_sync(hba); @@ -4955,7 +4923,7 @@ static int ufshcd_verify_dev_init(struct ufs_hba *hba) int err = 0; int retries; - ufshcd_hold(hba, false); + ufshcd_hold(hba); mutex_lock(&hba->dev_cmd.lock); for (retries = NOP_OUT_RETRIES; retries > 0; retries--) { err = ufshcd_exec_dev_cmd(hba, DEV_CMD_TYPE_NOP, @@ -6241,22 +6209,22 @@ static void ufshcd_err_handling_prepare(struct ufs_hba *hba) ufshcd_setup_vreg(hba, true); ufshcd_config_vreg_hpm(hba, hba->vreg_info.vccq); ufshcd_config_vreg_hpm(hba, hba->vreg_info.vccq2); - ufshcd_hold(hba, false); + ufshcd_hold(hba); if (!ufshcd_is_clkgating_allowed(hba)) ufshcd_setup_clocks(hba, true); ufshcd_release(hba); pm_op = hba->is_sys_suspended ? UFS_SYSTEM_PM : UFS_RUNTIME_PM; ufshcd_vops_resume(hba, pm_op); } else { - ufshcd_hold(hba, false); + ufshcd_hold(hba); if (ufshcd_is_clkscaling_supported(hba) && hba->clk_scaling.is_enabled) ufshcd_suspend_clkscaling(hba); ufshcd_clk_scaling_allow(hba, false); } ufshcd_scsi_block_requests(hba); - /* Drain ufshcd_queuecommand() */ - synchronize_rcu(); + /* Wait for ongoing ufshcd_queuecommand() calls to finish. */ + blk_mq_wait_quiesce_done(&hba->host->tag_set); cancel_work_sync(&hba->eeh_work); } @@ -6901,7 +6869,7 @@ static int __ufshcd_issue_tm_cmd(struct ufs_hba *hba, return PTR_ERR(req); req->end_io_data = &wait; - ufshcd_hold(hba, false); + ufshcd_hold(hba); spin_lock_irqsave(host->host_lock, flags); @@ -7138,7 +7106,7 @@ int ufshcd_exec_raw_upiu_cmd(struct ufs_hba *hba, cmd_type = DEV_CMD_TYPE_NOP; fallthrough; case UPIU_TRANSACTION_QUERY_REQ: - ufshcd_hold(hba, false); + ufshcd_hold(hba); mutex_lock(&hba->dev_cmd.lock); err = ufshcd_issue_devman_upiu_cmd(hba, req_upiu, rsp_upiu, desc_buff, buff_len, @@ -7204,7 +7172,7 @@ int ufshcd_advanced_rpmb_req_handler(struct ufs_hba *hba, struct utp_upiu_req *r u16 ehs_len; /* Protects use of hba->reserved_slot. */ - ufshcd_hold(hba, false); + ufshcd_hold(hba); mutex_lock(&hba->dev_cmd.lock); down_read(&hba->clk_scaling_lock); @@ -7439,7 +7407,7 @@ static int ufshcd_abort(struct scsi_cmnd *cmd) WARN_ONCE(tag < 0, "Invalid tag %d\n", tag); - ufshcd_hold(hba, false); + ufshcd_hold(hba); reg = ufshcd_readl(hba, REG_UTP_TRANSFER_REQ_DOOR_BELL); /* If command is already aborted/completed, return FAILED. */ if (!(test_bit(tag, &hba->outstanding_reqs))) { @@ -9430,7 +9398,7 @@ static int __ufshcd_wl_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op) * If we can't transition into any of the low power modes * just gate the clocks. */ - ufshcd_hold(hba, false); + ufshcd_hold(hba); hba->clk_gating.is_suspended = true; if (ufshcd_is_clkscaling_supported(hba)) diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h index f7553293ba98..8039c2b72502 100644 --- a/include/ufs/ufshcd.h +++ b/include/ufs/ufshcd.h @@ -1358,7 +1358,7 @@ void ufshcd_fixup_dev_quirks(struct ufs_hba *hba, int ufshcd_read_string_desc(struct ufs_hba *hba, u8 desc_index, u8 **buf, bool ascii); -int ufshcd_hold(struct ufs_hba *hba, bool async); +void ufshcd_hold(struct ufs_hba *hba); void ufshcd_release(struct ufs_hba *hba); void ufshcd_clkgate_delay_set(struct device *dev, unsigned long value); -- cgit v1.2.3 From 23caa33d36e7e6f75597b333634d9e54fb40001b Mon Sep 17 00:00:00 2001 From: Avri Altman Date: Wed, 31 May 2023 10:00:09 +0300 Subject: scsi: ufs: core: Do not open code SZ_x Do not open code SZ_x. Signed-off-by: Avri Altman Link: https://lore.kernel.org/r/20230531070009.4593-1-avri.altman@wdc.com Reviewed-by: Bean Huo Reviewed-by: Stanley Chu Reviewed-by: Keoseong Park Signed-off-by: Martin K. Petersen --- drivers/ufs/core/ufshcd.c | 14 +++++++------- drivers/ufs/core/ufshpb.c | 6 +++--- drivers/ufs/core/ufshpb.h | 2 +- drivers/ufs/host/ufs-exynos.c | 2 +- drivers/ufs/host/ufs-hisi.c | 24 ++++++++++++------------ include/ufs/ufshci.h | 2 +- 6 files changed, 25 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 941e613548da..0b2dc692d1b8 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -2501,7 +2501,7 @@ static void ufshcd_sgl_to_prdt(struct ufs_hba *hba, struct ufshcd_lrb *lrbp, int * 11b to indicate Dword granularity. A value of '3' * indicates 4 bytes, '7' indicates 8 bytes, etc." */ - WARN_ONCE(len > 256 * 1024, "len = %#x\n", len); + WARN_ONCE(len > SZ_256K, "len = %#x\n", len); prd->size = cpu_to_le32(len - 1); prd->addr = cpu_to_le64(sg->dma_address); prd->reserved = 0; @@ -3733,7 +3733,7 @@ static int ufshcd_memory_alloc(struct ufs_hba *hba) /* * Allocate memory for UTP Transfer descriptors - * UFSHCI requires 1024 byte alignment of UTRD + * UFSHCI requires 1KB alignment of UTRD */ utrdl_size = (sizeof(struct utp_transfer_req_desc) * hba->nutrs); hba->utrdl_base_addr = dmam_alloc_coherent(hba->dev, @@ -3741,7 +3741,7 @@ static int ufshcd_memory_alloc(struct ufs_hba *hba) &hba->utrdl_dma_addr, GFP_KERNEL); if (!hba->utrdl_base_addr || - WARN_ON(hba->utrdl_dma_addr & (1024 - 1))) { + WARN_ON(hba->utrdl_dma_addr & (SZ_1K - 1))) { dev_err(hba->dev, "Transfer Descriptor Memory allocation failed\n"); goto out; @@ -3757,7 +3757,7 @@ static int ufshcd_memory_alloc(struct ufs_hba *hba) goto skip_utmrdl; /* * Allocate memory for UTP Task Management descriptors - * UFSHCI requires 1024 byte alignment of UTMRD + * UFSHCI requires 1KB alignment of UTMRD */ utmrdl_size = sizeof(struct utp_task_req_desc) * hba->nutmrs; hba->utmrdl_base_addr = dmam_alloc_coherent(hba->dev, @@ -3765,7 +3765,7 @@ static int ufshcd_memory_alloc(struct ufs_hba *hba) &hba->utmrdl_dma_addr, GFP_KERNEL); if (!hba->utmrdl_base_addr || - WARN_ON(hba->utmrdl_dma_addr & (1024 - 1))) { + WARN_ON(hba->utmrdl_dma_addr & (SZ_1K - 1))) { dev_err(hba->dev, "Task Management Descriptor Memory allocation failed\n"); goto out; @@ -5102,7 +5102,7 @@ static int ufshcd_slave_configure(struct scsi_device *sdev) blk_queue_update_dma_pad(q, PRDT_DATA_BYTE_COUNT_PAD - 1); if (hba->quirks & UFSHCD_QUIRK_4KB_DMA_ALIGNMENT) - blk_queue_update_dma_alignment(q, 4096 - 1); + blk_queue_update_dma_alignment(q, SZ_4K - 1); /* * Block runtime-pm until all consumers are added. * Refer ufshcd_setup_links(). @@ -8728,7 +8728,7 @@ static const struct scsi_host_template ufshcd_driver_template = { .cmd_per_lun = UFSHCD_CMD_PER_LUN, .can_queue = UFSHCD_CAN_QUEUE, .max_segment_size = PRDT_DATA_BYTE_COUNT_MAX, - .max_sectors = (1 << 20) / SECTOR_SIZE, /* 1 MiB */ + .max_sectors = SZ_1M / SECTOR_SIZE, .max_host_blocked = 1, .track_queue_depth = 1, .skip_settle_delay = 1, diff --git a/drivers/ufs/core/ufshpb.c b/drivers/ufs/core/ufshpb.c index a46a7666c891..255f8b38d0c2 100644 --- a/drivers/ufs/core/ufshpb.c +++ b/drivers/ufs/core/ufshpb.c @@ -30,7 +30,7 @@ static struct kmem_cache *ufshpb_mctx_cache; static mempool_t *ufshpb_mctx_pool; static mempool_t *ufshpb_page_pool; /* A cache size of 2MB can cache ppn in the 1GB range. */ -static unsigned int ufshpb_host_map_kbytes = 2048; +static unsigned int ufshpb_host_map_kbytes = SZ_2K; static int tot_active_srgn_pages; static struct workqueue_struct *ufshpb_wq; @@ -2461,7 +2461,7 @@ static void ufshpb_hpb_lu_prepared(struct ufs_hba *hba) init_success = !ufshpb_check_hpb_reset_query(hba); - pool_size = PAGE_ALIGN(ufshpb_host_map_kbytes * 1024) / PAGE_SIZE; + pool_size = PAGE_ALIGN(ufshpb_host_map_kbytes * SZ_1K) / PAGE_SIZE; if (pool_size > tot_active_srgn_pages) { mempool_resize(ufshpb_mctx_pool, tot_active_srgn_pages); mempool_resize(ufshpb_page_pool, tot_active_srgn_pages); @@ -2527,7 +2527,7 @@ static int ufshpb_init_mem_wq(struct ufs_hba *hba) return -ENOMEM; } - pool_size = PAGE_ALIGN(ufshpb_host_map_kbytes * 1024) / PAGE_SIZE; + pool_size = PAGE_ALIGN(ufshpb_host_map_kbytes * SZ_1K) / PAGE_SIZE; dev_info(hba->dev, "%s:%d ufshpb_host_map_kbytes %u pool_size %u\n", __func__, __LINE__, ufshpb_host_map_kbytes, pool_size); diff --git a/drivers/ufs/core/ufshpb.h b/drivers/ufs/core/ufshpb.h index 0d6e6004d783..b428bbdd2799 100644 --- a/drivers/ufs/core/ufshpb.h +++ b/drivers/ufs/core/ufshpb.h @@ -25,7 +25,7 @@ /* hpb map & entries macro */ #define HPB_RGN_SIZE_UNIT 512 -#define HPB_ENTRY_BLOCK_SIZE 4096 +#define HPB_ENTRY_BLOCK_SIZE SZ_4K #define HPB_ENTRY_SIZE 0x8 #define PINNED_NOT_SET U32_MAX diff --git a/drivers/ufs/host/ufs-exynos.c b/drivers/ufs/host/ufs-exynos.c index 0bf5390739e1..d56840447bd0 100644 --- a/drivers/ufs/host/ufs-exynos.c +++ b/drivers/ufs/host/ufs-exynos.c @@ -1306,7 +1306,7 @@ static int exynos_ufs_hce_enable_notify(struct ufs_hba *hba, * (ufshcd_async_scan()). Note: this callback may also be called * from other functions than ufshcd_init(). */ - hba->host->max_segment_size = 4096; + hba->host->max_segment_size = SZ_4K; if (ufs->drv_data->pre_hce_enable) { ret = ufs->drv_data->pre_hce_enable(ufs); diff --git a/drivers/ufs/host/ufs-hisi.c b/drivers/ufs/host/ufs-hisi.c index 4c423eba8aa9..1e1d388f359a 100644 --- a/drivers/ufs/host/ufs-hisi.c +++ b/drivers/ufs/host/ufs-hisi.c @@ -335,29 +335,29 @@ static void ufs_hisi_pwr_change_pre_change(struct ufs_hba *hba) /* PA_TxSkip */ ufshcd_dme_set(hba, UIC_ARG_MIB(0x155c), 0x0); /*PA_PWRModeUserData0 = 8191, default is 0*/ - ufshcd_dme_set(hba, UIC_ARG_MIB(0x15b0), 8191); + ufshcd_dme_set(hba, UIC_ARG_MIB(0x15b0), SZ_8K - 1); /*PA_PWRModeUserData1 = 65535, default is 0*/ - ufshcd_dme_set(hba, UIC_ARG_MIB(0x15b1), 65535); + ufshcd_dme_set(hba, UIC_ARG_MIB(0x15b1), SZ_64K - 1); /*PA_PWRModeUserData2 = 32767, default is 0*/ - ufshcd_dme_set(hba, UIC_ARG_MIB(0x15b2), 32767); + ufshcd_dme_set(hba, UIC_ARG_MIB(0x15b2), SZ_32K - 1); /*DME_FC0ProtectionTimeOutVal = 8191, default is 0*/ - ufshcd_dme_set(hba, UIC_ARG_MIB(0xd041), 8191); + ufshcd_dme_set(hba, UIC_ARG_MIB(0xd041), SZ_8K - 1); /*DME_TC0ReplayTimeOutVal = 65535, default is 0*/ - ufshcd_dme_set(hba, UIC_ARG_MIB(0xd042), 65535); + ufshcd_dme_set(hba, UIC_ARG_MIB(0xd042), SZ_64K - 1); /*DME_AFC0ReqTimeOutVal = 32767, default is 0*/ - ufshcd_dme_set(hba, UIC_ARG_MIB(0xd043), 32767); + ufshcd_dme_set(hba, UIC_ARG_MIB(0xd043), SZ_32K - 1); /*PA_PWRModeUserData3 = 8191, default is 0*/ - ufshcd_dme_set(hba, UIC_ARG_MIB(0x15b3), 8191); + ufshcd_dme_set(hba, UIC_ARG_MIB(0x15b3), SZ_8K - 1); /*PA_PWRModeUserData4 = 65535, default is 0*/ - ufshcd_dme_set(hba, UIC_ARG_MIB(0x15b4), 65535); + ufshcd_dme_set(hba, UIC_ARG_MIB(0x15b4), SZ_64K - 1); /*PA_PWRModeUserData5 = 32767, default is 0*/ - ufshcd_dme_set(hba, UIC_ARG_MIB(0x15b5), 32767); + ufshcd_dme_set(hba, UIC_ARG_MIB(0x15b5), SZ_32K - 1); /*DME_FC1ProtectionTimeOutVal = 8191, default is 0*/ - ufshcd_dme_set(hba, UIC_ARG_MIB(0xd044), 8191); + ufshcd_dme_set(hba, UIC_ARG_MIB(0xd044), SZ_8K - 1); /*DME_TC1ReplayTimeOutVal = 65535, default is 0*/ - ufshcd_dme_set(hba, UIC_ARG_MIB(0xd045), 65535); + ufshcd_dme_set(hba, UIC_ARG_MIB(0xd045), SZ_64K - 1); /*DME_AFC1ReqTimeOutVal = 32767, default is 0*/ - ufshcd_dme_set(hba, UIC_ARG_MIB(0xd046), 32767); + ufshcd_dme_set(hba, UIC_ARG_MIB(0xd046), SZ_32K - 1); } static int ufs_hisi_pwr_change_notify(struct ufs_hba *hba, diff --git a/include/ufs/ufshci.h b/include/ufs/ufshci.h index 11424bb03814..db2d5db5c88e 100644 --- a/include/ufs/ufshci.h +++ b/include/ufs/ufshci.h @@ -453,7 +453,7 @@ enum { }; /* The maximum length of the data byte count field in the PRDT is 256KB */ -#define PRDT_DATA_BYTE_COUNT_MAX (256 * 1024) +#define PRDT_DATA_BYTE_COUNT_MAX SZ_256K /* The granularity of the data byte count field in the PRDT is 32-bit */ #define PRDT_DATA_BYTE_COUNT_PAD 4 -- cgit v1.2.3 From a8f9a36e46344ea5bdc301c2fde0389a463bf0a3 Mon Sep 17 00:00:00 2001 From: "Bao D. Nguyen" Date: Mon, 29 May 2023 15:12:20 -0700 Subject: scsi: ufs: core: Combine 32-bit command_desc_base_addr_lo/hi The UTP command descriptor base address is a 57-bit field in the UTP transfer request descriptor. Combine the two 32-bit command_desc_base_addr_lo/hi fields into a 64-bit for better handling of this field. Signed-off-by: Bao D. Nguyen Link: https://lore.kernel.org/r/4e6f7f5a15000cdae77c3014b477264f57bf572c.1685396241.git.quic_nguyenb@quicinc.com Reviewed-by: Bart Van Assche Reviewed-by: Stanley Chu Tested-by: Stanley Chu Reviewed-by: Can Guo Signed-off-by: Martin K. Petersen --- drivers/ufs/core/ufshcd.c | 6 ++---- include/ufs/ufshci.h | 6 ++---- 2 files changed, 4 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 17d7bb875fee..682da831f133 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -3868,10 +3868,8 @@ static void ufshcd_host_memory_configure(struct ufs_hba *hba) /* Configure UTRD with command descriptor base address */ cmd_desc_element_addr = (cmd_desc_dma_addr + (cmd_desc_size * i)); - utrdlp[i].command_desc_base_addr_lo = - cpu_to_le32(lower_32_bits(cmd_desc_element_addr)); - utrdlp[i].command_desc_base_addr_hi = - cpu_to_le32(upper_32_bits(cmd_desc_element_addr)); + utrdlp[i].command_desc_base_addr = + cpu_to_le64(cmd_desc_element_addr); /* Response upiu and prdt offset should be in double words */ if (hba->quirks & UFSHCD_QUIRK_PRDT_BYTE_GRAN) { diff --git a/include/ufs/ufshci.h b/include/ufs/ufshci.h index 11424bb03814..7c5a76b2c70a 100644 --- a/include/ufs/ufshci.h +++ b/include/ufs/ufshci.h @@ -503,8 +503,7 @@ struct request_desc_header { /** * struct utp_transfer_req_desc - UTP Transfer Request Descriptor (UTRD) * @header: UTRD header DW-0 to DW-3 - * @command_desc_base_addr_lo: UCD base address low DW-4 - * @command_desc_base_addr_hi: UCD base address high DW-5 + * @command_desc_base_addr: UCD base address DW 4-5 * @response_upiu_length: response UPIU length DW-6 * @response_upiu_offset: response UPIU offset DW-6 * @prd_table_length: Physical region descriptor length DW-7 @@ -516,8 +515,7 @@ struct utp_transfer_req_desc { struct request_desc_header header; /* DW 4-5*/ - __le32 command_desc_base_addr_lo; - __le32 command_desc_base_addr_hi; + __le64 command_desc_base_addr; /* DW 6 */ __le16 response_upiu_length; -- cgit v1.2.3 From 8d7290348992f27242dd6a696fa2eede709f0b14 Mon Sep 17 00:00:00 2001 From: "Bao D. Nguyen" Date: Mon, 29 May 2023 15:12:22 -0700 Subject: scsi: ufs: mcq: Add supporting functions for MCQ abort Add supporting functions to handle UFS abort in MCQ mode. Signed-off-by: Bao D. Nguyen Link: https://lore.kernel.org/r/d452c5ad62dc863cc067ec82daa0885ec98bd508.1685396241.git.quic_nguyenb@quicinc.com Reviewed-by: Bart Van Assche Reviewed-by: Stanley Chu Tested-by: Stanley Chu Reviewed-by: Can Guo Signed-off-by: Martin K. Petersen --- drivers/ufs/core/ufs-mcq.c | 167 +++++++++++++++++++++++++++++++++++++++++ drivers/ufs/core/ufshcd-priv.h | 10 +++ drivers/ufs/core/ufshcd.c | 1 - include/ufs/ufshcd.h | 3 + include/ufs/ufshci.h | 17 +++++ 5 files changed, 197 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c index 202ff71e1b58..655f22087ea1 100644 --- a/drivers/ufs/core/ufs-mcq.c +++ b/drivers/ufs/core/ufs-mcq.c @@ -12,6 +12,10 @@ #include #include #include "ufshcd-priv.h" +#include +#include +#include +#include #define MAX_QUEUE_SUP GENMASK(7, 0) #define UFS_MCQ_MIN_RW_QUEUES 2 @@ -27,6 +31,9 @@ #define MCQ_ENTRY_SIZE_IN_DWORD 8 #define CQE_UCD_BA GENMASK_ULL(63, 7) +/* Max mcq register polling time in microseconds */ +#define MCQ_POLL_US 500000 + static int rw_queue_count_set(const char *val, const struct kernel_param *kp) { return param_set_uint_minmax(val, kp, UFS_MCQ_MIN_RW_QUEUES, @@ -419,6 +426,7 @@ int ufshcd_mcq_init(struct ufs_hba *hba) hwq->max_entries = hba->nutrs; spin_lock_init(&hwq->sq_lock); spin_lock_init(&hwq->cq_lock); + mutex_init(&hwq->sq_mutex); } /* The very first HW queue serves device commands */ @@ -429,3 +437,162 @@ int ufshcd_mcq_init(struct ufs_hba *hba) host->host_tagset = 1; return 0; } + +static int ufshcd_mcq_sq_stop(struct ufs_hba *hba, struct ufs_hw_queue *hwq) +{ + void __iomem *reg; + u32 id = hwq->id, val; + int err; + + writel(SQ_STOP, mcq_opr_base(hba, OPR_SQD, id) + REG_SQRTC); + reg = mcq_opr_base(hba, OPR_SQD, id) + REG_SQRTS; + err = read_poll_timeout(readl, val, val & SQ_STS, 20, + MCQ_POLL_US, false, reg); + if (err) + dev_err(hba->dev, "%s: failed. hwq-id=%d, err=%d\n", + __func__, id, err); + return err; +} + +static int ufshcd_mcq_sq_start(struct ufs_hba *hba, struct ufs_hw_queue *hwq) +{ + void __iomem *reg; + u32 id = hwq->id, val; + int err; + + writel(SQ_START, mcq_opr_base(hba, OPR_SQD, id) + REG_SQRTC); + reg = mcq_opr_base(hba, OPR_SQD, id) + REG_SQRTS; + err = read_poll_timeout(readl, val, !(val & SQ_STS), 20, + MCQ_POLL_US, false, reg); + if (err) + dev_err(hba->dev, "%s: failed. hwq-id=%d, err=%d\n", + __func__, id, err); + return err; +} + +/** + * ufshcd_mcq_sq_cleanup - Clean up submission queue resources + * associated with the pending command. + * @hba - per adapter instance. + * @task_tag - The command's task tag. + * + * Returns 0 for success; error code otherwise. + */ +int ufshcd_mcq_sq_cleanup(struct ufs_hba *hba, int task_tag) +{ + struct ufshcd_lrb *lrbp = &hba->lrb[task_tag]; + struct scsi_cmnd *cmd = lrbp->cmd; + struct ufs_hw_queue *hwq; + void __iomem *reg, *opr_sqd_base; + u32 nexus, id, val; + int err; + + if (task_tag != hba->nutrs - UFSHCD_NUM_RESERVED) { + if (!cmd) + return -EINVAL; + hwq = ufshcd_mcq_req_to_hwq(hba, scsi_cmd_to_rq(cmd)); + } else { + hwq = hba->dev_cmd_queue; + } + + id = hwq->id; + + mutex_lock(&hwq->sq_mutex); + + /* stop the SQ fetching before working on it */ + err = ufshcd_mcq_sq_stop(hba, hwq); + if (err) + goto unlock; + + /* SQCTI = EXT_IID, IID, LUN, Task Tag */ + nexus = lrbp->lun << 8 | task_tag; + opr_sqd_base = mcq_opr_base(hba, OPR_SQD, id); + writel(nexus, opr_sqd_base + REG_SQCTI); + + /* SQRTCy.ICU = 1 */ + writel(SQ_ICU, opr_sqd_base + REG_SQRTC); + + /* Poll SQRTSy.CUS = 1. Return result from SQRTSy.RTC */ + reg = opr_sqd_base + REG_SQRTS; + err = read_poll_timeout(readl, val, val & SQ_CUS, 20, + MCQ_POLL_US, false, reg); + if (err) + dev_err(hba->dev, "%s: failed. hwq=%d, tag=%d err=%ld\n", + __func__, id, task_tag, + FIELD_GET(SQ_ICU_ERR_CODE_MASK, readl(reg))); + + if (ufshcd_mcq_sq_start(hba, hwq)) + err = -ETIMEDOUT; + +unlock: + mutex_unlock(&hwq->sq_mutex); + return err; +} + +/** + * ufshcd_mcq_nullify_sqe - Nullify the submission queue entry. + * Write the sqe's Command Type to 0xF. The host controller will not + * fetch any sqe with Command Type = 0xF. + * + * @utrd - UTP Transfer Request Descriptor to be nullified. + */ +static void ufshcd_mcq_nullify_sqe(struct utp_transfer_req_desc *utrd) +{ + u32 dword_0; + + dword_0 = le32_to_cpu(utrd->header.dword_0); + dword_0 &= ~UPIU_COMMAND_TYPE_MASK; + dword_0 |= FIELD_PREP(UPIU_COMMAND_TYPE_MASK, 0xF); + utrd->header.dword_0 = cpu_to_le32(dword_0); +} + +/** + * ufshcd_mcq_sqe_search - Search for the command in the submission queue + * If the command is in the submission queue and not issued to the device yet, + * nullify the sqe so the host controller will skip fetching the sqe. + * + * @hba - per adapter instance. + * @hwq - Hardware Queue to be searched. + * @task_tag - The command's task tag. + * + * Returns true if the SQE containing the command is present in the SQ + * (not fetched by the controller); returns false if the SQE is not in the SQ. + */ +static bool ufshcd_mcq_sqe_search(struct ufs_hba *hba, + struct ufs_hw_queue *hwq, int task_tag) +{ + struct ufshcd_lrb *lrbp = &hba->lrb[task_tag]; + struct utp_transfer_req_desc *utrd; + u32 mask = hwq->max_entries - 1; + __le64 cmd_desc_base_addr; + bool ret = false; + u64 addr, match; + u32 sq_head_slot; + + mutex_lock(&hwq->sq_mutex); + + ufshcd_mcq_sq_stop(hba, hwq); + sq_head_slot = ufshcd_mcq_get_sq_head_slot(hwq); + if (sq_head_slot == hwq->sq_tail_slot) + goto out; + + cmd_desc_base_addr = lrbp->utr_descriptor_ptr->command_desc_base_addr; + addr = le64_to_cpu(cmd_desc_base_addr) & CQE_UCD_BA; + + while (sq_head_slot != hwq->sq_tail_slot) { + utrd = hwq->sqe_base_addr + + sq_head_slot * sizeof(struct utp_transfer_req_desc); + match = le64_to_cpu(utrd->command_desc_base_addr) & CQE_UCD_BA; + if (addr == match) { + ufshcd_mcq_nullify_sqe(utrd); + ret = true; + goto out; + } + sq_head_slot = (sq_head_slot + 1) & mask; + } + +out: + ufshcd_mcq_sq_start(hba, hwq); + mutex_unlock(&hwq->sq_mutex); + return ret; +} diff --git a/drivers/ufs/core/ufshcd-priv.h b/drivers/ufs/core/ufshcd-priv.h index d53b93c21a0c..40727e89200d 100644 --- a/drivers/ufs/core/ufshcd-priv.h +++ b/drivers/ufs/core/ufshcd-priv.h @@ -78,6 +78,8 @@ struct ufs_hw_queue *ufshcd_mcq_req_to_hwq(struct ufs_hba *hba, unsigned long ufshcd_mcq_poll_cqe_lock(struct ufs_hba *hba, struct ufs_hw_queue *hwq); +int ufshcd_mcq_sq_cleanup(struct ufs_hba *hba, int task_tag); + #define UFSHCD_MCQ_IO_QUEUE_OFFSET 1 #define SD_ASCII_STD true #define SD_RAW false @@ -404,4 +406,12 @@ static inline struct cq_entry *ufshcd_mcq_cur_cqe(struct ufs_hw_queue *q) return cqe + q->cq_head_slot; } + +static inline u32 ufshcd_mcq_get_sq_head_slot(struct ufs_hw_queue *q) +{ + u32 val = readl(q->mcq_sq_head); + + return val / sizeof(struct utp_transfer_req_desc); +} + #endif /* _UFSHCD_PRIV_H_ */ diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index a96c464bd1b7..d0e1570f2411 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -173,7 +173,6 @@ EXPORT_SYMBOL_GPL(ufshcd_dump_regs); enum { UFSHCD_MAX_CHANNEL = 0, UFSHCD_MAX_ID = 1, - UFSHCD_NUM_RESERVED = 1, UFSHCD_CMD_PER_LUN = 32 - UFSHCD_NUM_RESERVED, UFSHCD_CAN_QUEUE = 32 - UFSHCD_NUM_RESERVED, }; diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h index f7553293ba98..145710e9c2a5 100644 --- a/include/ufs/ufshcd.h +++ b/include/ufs/ufshcd.h @@ -1087,6 +1087,7 @@ struct ufs_hba { * @cq_tail_slot: current slot to which CQ tail pointer is pointing * @cq_head_slot: current slot to which CQ head pointer is pointing * @cq_lock: Synchronize between multiple polling instances + * @sq_mutex: prevent submission queue concurrent access */ struct ufs_hw_queue { void __iomem *mcq_sq_head; @@ -1105,6 +1106,8 @@ struct ufs_hw_queue { u32 cq_tail_slot; u32 cq_head_slot; spinlock_t cq_lock; + /* prevent concurrent access to submission queue */ + struct mutex sq_mutex; }; static inline bool is_mcq_enabled(struct ufs_hba *hba) diff --git a/include/ufs/ufshci.h b/include/ufs/ufshci.h index 7c5a76b2c70a..9d291ca7f31d 100644 --- a/include/ufs/ufshci.h +++ b/include/ufs/ufshci.h @@ -99,6 +99,9 @@ enum { enum { REG_SQHP = 0x0, REG_SQTP = 0x4, + REG_SQRTC = 0x8, + REG_SQCTI = 0xC, + REG_SQRTS = 0x10, }; enum { @@ -111,12 +114,26 @@ enum { REG_CQIE = 0x4, }; +enum { + SQ_START = 0x0, + SQ_STOP = 0x1, + SQ_ICU = 0x2, +}; + +enum { + SQ_STS = 0x1, + SQ_CUS = 0x2, +}; + +#define SQ_ICU_ERR_CODE_MASK GENMASK(7, 4) +#define UPIU_COMMAND_TYPE_MASK GENMASK(31, 28) #define UFS_MASK(mask, offset) ((mask) << (offset)) /* UFS Version 08h */ #define MINOR_VERSION_NUM_MASK UFS_MASK(0xFFFF, 0) #define MAJOR_VERSION_NUM_MASK UFS_MASK(0xFFFF, 16) +#define UFSHCD_NUM_RESERVED 1 /* * Controller UFSHCI version * - 2.x and newer use the following scheme: -- cgit v1.2.3 From 57d6ef4601c0b7975aab5144c7c3760846362e1c Mon Sep 17 00:00:00 2001 From: "Bao D. Nguyen" Date: Mon, 29 May 2023 15:12:25 -0700 Subject: scsi: ufs: mcq: Use ufshcd_mcq_poll_cqe_lock() in MCQ mode In preparation for adding MCQ error handler support, update the MCQ code to use the ufshcd_mcq_poll_cqe_lock() in interrupt context instead of using ufshcd_mcq_poll_cqe_nolock(). This is to keep synchronization between MCQ interrupt and error handler contexts because both need to access the MCQ hardware in separate contexts. Signed-off-by: Bao D. Nguyen Link: https://lore.kernel.org/r/6ae727ad2a4040469b8f0632b55e0577d80da11b.1685396241.git.quic_nguyenb@quicinc.com Reviewed-by: Bart Van Assche Reviewed-by: Stanley Chu Tested-by: Stanley Chu Reviewed-by: Can Guo Signed-off-by: Martin K. Petersen --- drivers/ufs/core/ufs-mcq.c | 6 +++--- drivers/ufs/core/ufshcd-priv.h | 2 -- drivers/ufs/core/ufshcd.c | 2 +- drivers/ufs/host/ufs-qcom.c | 2 +- include/ufs/ufshcd.h | 2 +- 5 files changed, 6 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c index 63db20b9edb1..2efa0129b2c4 100644 --- a/drivers/ufs/core/ufs-mcq.c +++ b/drivers/ufs/core/ufs-mcq.c @@ -284,8 +284,8 @@ static void ufshcd_mcq_process_cqe(struct ufs_hba *hba, ufshcd_compl_one_cqe(hba, tag, cqe); } -unsigned long ufshcd_mcq_poll_cqe_nolock(struct ufs_hba *hba, - struct ufs_hw_queue *hwq) +static unsigned long ufshcd_mcq_poll_cqe_nolock(struct ufs_hba *hba, + struct ufs_hw_queue *hwq) { unsigned long completed_reqs = 0; @@ -301,7 +301,6 @@ unsigned long ufshcd_mcq_poll_cqe_nolock(struct ufs_hba *hba, return completed_reqs; } -EXPORT_SYMBOL_GPL(ufshcd_mcq_poll_cqe_nolock); unsigned long ufshcd_mcq_poll_cqe_lock(struct ufs_hba *hba, struct ufs_hw_queue *hwq) @@ -314,6 +313,7 @@ unsigned long ufshcd_mcq_poll_cqe_lock(struct ufs_hba *hba, return completed_reqs; } +EXPORT_SYMBOL_GPL(ufshcd_mcq_poll_cqe_lock); void ufshcd_mcq_make_queues_operational(struct ufs_hba *hba) { diff --git a/drivers/ufs/core/ufshcd-priv.h b/drivers/ufs/core/ufshcd-priv.h index 80293fd88ef0..339ab51ce974 100644 --- a/drivers/ufs/core/ufshcd-priv.h +++ b/drivers/ufs/core/ufshcd-priv.h @@ -71,8 +71,6 @@ void ufshcd_mcq_config_mac(struct ufs_hba *hba, u32 max_active_cmds); void ufshcd_mcq_select_mcq_mode(struct ufs_hba *hba); u32 ufshcd_mcq_read_cqis(struct ufs_hba *hba, int i); void ufshcd_mcq_write_cqis(struct ufs_hba *hba, u32 val, int i); -unsigned long ufshcd_mcq_poll_cqe_nolock(struct ufs_hba *hba, - struct ufs_hw_queue *hwq); struct ufs_hw_queue *ufshcd_mcq_req_to_hwq(struct ufs_hba *hba, struct request *req); unsigned long ufshcd_mcq_poll_cqe_lock(struct ufs_hba *hba, diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 2436539b0dc2..1db2eb207cc8 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -6804,7 +6804,7 @@ static irqreturn_t ufshcd_handle_mcq_cq_events(struct ufs_hba *hba) ufshcd_mcq_write_cqis(hba, events, i); if (events & UFSHCD_MCQ_CQIS_TAIL_ENT_PUSH_STS) - ufshcd_mcq_poll_cqe_nolock(hba, hwq); + ufshcd_mcq_poll_cqe_lock(hba, hwq); } return IRQ_HANDLED; diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c index 82d02e7f3b4f..57f567492e09 100644 --- a/drivers/ufs/host/ufs-qcom.c +++ b/drivers/ufs/host/ufs-qcom.c @@ -1556,7 +1556,7 @@ static irqreturn_t ufs_qcom_mcq_esi_handler(int irq, void *__hba) struct ufs_hw_queue *hwq = &hba->uhq[id]; ufshcd_mcq_write_cqis(hba, 0x1, id); - ufshcd_mcq_poll_cqe_nolock(hba, hwq); + ufshcd_mcq_poll_cqe_lock(hba, hwq); return IRQ_HANDLED; } diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h index 145710e9c2a5..12e3149617db 100644 --- a/include/ufs/ufshcd.h +++ b/include/ufs/ufshcd.h @@ -1243,7 +1243,7 @@ void ufshcd_update_evt_hist(struct ufs_hba *hba, u32 id, u32 val); void ufshcd_hba_stop(struct ufs_hba *hba); void ufshcd_schedule_eh_work(struct ufs_hba *hba); void ufshcd_mcq_write_cqis(struct ufs_hba *hba, u32 val, int i); -unsigned long ufshcd_mcq_poll_cqe_nolock(struct ufs_hba *hba, +unsigned long ufshcd_mcq_poll_cqe_lock(struct ufs_hba *hba, struct ufs_hw_queue *hwq); void ufshcd_mcq_enable_esi(struct ufs_hba *hba); void ufshcd_mcq_config_esi(struct ufs_hba *hba, struct msi_msg *msg); -- cgit v1.2.3 From 0818a6903c8081a17da4b1f50ff156537f99b02f Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 24 May 2023 13:36:22 -0700 Subject: scsi: ufs: core: Simplify driver shutdown All UFS host drivers call ufshcd_shutdown(). Hence, instead of calling ufshcd_shutdown() from the host driver .shutdown() callback, inline that function into ufshcd_wl_shutdown(). Reviewed-by: Adrian Hunter Signed-off-by: Bart Van Assche Link: https://lore.kernel.org/r/20230524203659.1394307-5-bvanassche@acm.org Signed-off-by: Martin K. Petersen --- drivers/ufs/core/ufshcd.c | 23 +++++------------------ drivers/ufs/host/cdns-pltfrm.c | 1 - drivers/ufs/host/tc-dwc-g210-pci.c | 10 ---------- drivers/ufs/host/tc-dwc-g210-pltfrm.c | 1 - drivers/ufs/host/ufs-exynos.c | 1 - drivers/ufs/host/ufs-hisi.c | 1 - drivers/ufs/host/ufs-mediatek.c | 1 - drivers/ufs/host/ufs-qcom.c | 1 - drivers/ufs/host/ufs-sprd.c | 1 - drivers/ufs/host/ufshcd-pci.c | 10 ---------- drivers/ufs/host/ufshcd-pltfrm.c | 6 ------ drivers/ufs/host/ufshcd-pltfrm.h | 1 - include/ufs/ufshcd.h | 1 - 13 files changed, 5 insertions(+), 53 deletions(-) (limited to 'include') diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index f84af598af33..00f730671f4b 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -9950,9 +9950,7 @@ EXPORT_SYMBOL(ufshcd_runtime_resume); static void ufshcd_wl_shutdown(struct device *dev) { struct scsi_device *sdev = to_scsi_device(dev); - struct ufs_hba *hba; - - hba = shost_priv(sdev->host); + struct ufs_hba *hba = shost_priv(sdev->host); down(&hba->host_sem); hba->shutting_down = true; @@ -9967,27 +9965,16 @@ static void ufshcd_wl_shutdown(struct device *dev) scsi_device_quiesce(sdev); } __ufshcd_wl_suspend(hba, UFS_SHUTDOWN_PM); -} -/** - * ufshcd_shutdown - shutdown routine - * @hba: per adapter instance - * - * This function would turn off both UFS device and UFS hba - * regulators. It would also disable clocks. - * - * Returns 0 always to allow force shutdown even in case of errors. - */ -int ufshcd_shutdown(struct ufs_hba *hba) -{ + /* + * Next, turn off the UFS controller and the UFS regulators. Disable + * clocks. + */ if (ufshcd_is_ufs_dev_poweroff(hba) && ufshcd_is_link_off(hba)) ufshcd_suspend(hba); hba->is_powered = false; - /* allow force shutdown even in case of errors */ - return 0; } -EXPORT_SYMBOL(ufshcd_shutdown); /** * ufshcd_remove - de-allocate SCSI host and host memory space diff --git a/drivers/ufs/host/cdns-pltfrm.c b/drivers/ufs/host/cdns-pltfrm.c index e05c0ae64eea..26761425a76c 100644 --- a/drivers/ufs/host/cdns-pltfrm.c +++ b/drivers/ufs/host/cdns-pltfrm.c @@ -328,7 +328,6 @@ static const struct dev_pm_ops cdns_ufs_dev_pm_ops = { static struct platform_driver cdns_ufs_pltfrm_driver = { .probe = cdns_ufs_pltfrm_probe, .remove = cdns_ufs_pltfrm_remove, - .shutdown = ufshcd_pltfrm_shutdown, .driver = { .name = "cdns-ufshcd", .pm = &cdns_ufs_dev_pm_ops, diff --git a/drivers/ufs/host/tc-dwc-g210-pci.c b/drivers/ufs/host/tc-dwc-g210-pci.c index 92b8ad4b58fe..f96fe5855841 100644 --- a/drivers/ufs/host/tc-dwc-g210-pci.c +++ b/drivers/ufs/host/tc-dwc-g210-pci.c @@ -32,15 +32,6 @@ static struct ufs_hba_variant_ops tc_dwc_g210_pci_hba_vops = { .link_startup_notify = ufshcd_dwc_link_startup_notify, }; -/** - * tc_dwc_g210_pci_shutdown - main function to put the controller in reset state - * @pdev: pointer to PCI device handle - */ -static void tc_dwc_g210_pci_shutdown(struct pci_dev *pdev) -{ - ufshcd_shutdown((struct ufs_hba *)pci_get_drvdata(pdev)); -} - /** * tc_dwc_g210_pci_remove - de-allocate PCI/SCSI host and host memory space * data structure memory @@ -137,7 +128,6 @@ static struct pci_driver tc_dwc_g210_pci_driver = { .id_table = tc_dwc_g210_pci_tbl, .probe = tc_dwc_g210_pci_probe, .remove = tc_dwc_g210_pci_remove, - .shutdown = tc_dwc_g210_pci_shutdown, .driver = { .pm = &tc_dwc_g210_pci_pm_ops }, diff --git a/drivers/ufs/host/tc-dwc-g210-pltfrm.c b/drivers/ufs/host/tc-dwc-g210-pltfrm.c index f15a84d0c176..4d5389dd9585 100644 --- a/drivers/ufs/host/tc-dwc-g210-pltfrm.c +++ b/drivers/ufs/host/tc-dwc-g210-pltfrm.c @@ -92,7 +92,6 @@ static const struct dev_pm_ops tc_dwc_g210_pltfm_pm_ops = { static struct platform_driver tc_dwc_g210_pltfm_driver = { .probe = tc_dwc_g210_pltfm_probe, .remove = tc_dwc_g210_pltfm_remove, - .shutdown = ufshcd_pltfrm_shutdown, .driver = { .name = "tc-dwc-g210-pltfm", .pm = &tc_dwc_g210_pltfm_pm_ops, diff --git a/drivers/ufs/host/ufs-exynos.c b/drivers/ufs/host/ufs-exynos.c index 0bf5390739e1..f41056f57fd7 100644 --- a/drivers/ufs/host/ufs-exynos.c +++ b/drivers/ufs/host/ufs-exynos.c @@ -1757,7 +1757,6 @@ static const struct dev_pm_ops exynos_ufs_pm_ops = { static struct platform_driver exynos_ufs_pltform = { .probe = exynos_ufs_probe, .remove = exynos_ufs_remove, - .shutdown = ufshcd_pltfrm_shutdown, .driver = { .name = "exynos-ufshc", .pm = &exynos_ufs_pm_ops, diff --git a/drivers/ufs/host/ufs-hisi.c b/drivers/ufs/host/ufs-hisi.c index 4c423eba8aa9..18b72e2e68c1 100644 --- a/drivers/ufs/host/ufs-hisi.c +++ b/drivers/ufs/host/ufs-hisi.c @@ -593,7 +593,6 @@ static const struct dev_pm_ops ufs_hisi_pm_ops = { static struct platform_driver ufs_hisi_pltform = { .probe = ufs_hisi_probe, .remove = ufs_hisi_remove, - .shutdown = ufshcd_pltfrm_shutdown, .driver = { .name = "ufshcd-hisi", .pm = &ufs_hisi_pm_ops, diff --git a/drivers/ufs/host/ufs-mediatek.c b/drivers/ufs/host/ufs-mediatek.c index 73e217260390..e89b625d3c5a 100644 --- a/drivers/ufs/host/ufs-mediatek.c +++ b/drivers/ufs/host/ufs-mediatek.c @@ -1650,7 +1650,6 @@ static const struct dev_pm_ops ufs_mtk_pm_ops = { static struct platform_driver ufs_mtk_pltform = { .probe = ufs_mtk_probe, .remove = ufs_mtk_remove, - .shutdown = ufshcd_pltfrm_shutdown, .driver = { .name = "ufshcd-mtk", .pm = &ufs_mtk_pm_ops, diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c index 82d02e7f3b4f..059de74dfea3 100644 --- a/drivers/ufs/host/ufs-qcom.c +++ b/drivers/ufs/host/ufs-qcom.c @@ -1723,7 +1723,6 @@ static const struct dev_pm_ops ufs_qcom_pm_ops = { static struct platform_driver ufs_qcom_pltform = { .probe = ufs_qcom_probe, .remove = ufs_qcom_remove, - .shutdown = ufshcd_pltfrm_shutdown, .driver = { .name = "ufshcd-qcom", .pm = &ufs_qcom_pm_ops, diff --git a/drivers/ufs/host/ufs-sprd.c b/drivers/ufs/host/ufs-sprd.c index 051f3f40d92c..2bad75dd6d58 100644 --- a/drivers/ufs/host/ufs-sprd.c +++ b/drivers/ufs/host/ufs-sprd.c @@ -444,7 +444,6 @@ static const struct dev_pm_ops ufs_sprd_pm_ops = { static struct platform_driver ufs_sprd_pltform = { .probe = ufs_sprd_probe, .remove = ufs_sprd_remove, - .shutdown = ufshcd_pltfrm_shutdown, .driver = { .name = "ufshcd-sprd", .pm = &ufs_sprd_pm_ops, diff --git a/drivers/ufs/host/ufshcd-pci.c b/drivers/ufs/host/ufshcd-pci.c index 9c911787f84c..38276dac8e52 100644 --- a/drivers/ufs/host/ufshcd-pci.c +++ b/drivers/ufs/host/ufshcd-pci.c @@ -504,15 +504,6 @@ static int ufshcd_pci_restore(struct device *dev) } #endif -/** - * ufshcd_pci_shutdown - main function to put the controller in reset state - * @pdev: pointer to PCI device handle - */ -static void ufshcd_pci_shutdown(struct pci_dev *pdev) -{ - ufshcd_shutdown((struct ufs_hba *)pci_get_drvdata(pdev)); -} - /** * ufshcd_pci_remove - de-allocate PCI/SCSI host and host memory space * data structure memory @@ -618,7 +609,6 @@ static struct pci_driver ufshcd_pci_driver = { .id_table = ufshcd_pci_tbl, .probe = ufshcd_pci_probe, .remove = ufshcd_pci_remove, - .shutdown = ufshcd_pci_shutdown, .driver = { .pm = &ufshcd_pci_pm_ops }, diff --git a/drivers/ufs/host/ufshcd-pltfrm.c b/drivers/ufs/host/ufshcd-pltfrm.c index 5739ff007828..0b7430033047 100644 --- a/drivers/ufs/host/ufshcd-pltfrm.c +++ b/drivers/ufs/host/ufshcd-pltfrm.c @@ -190,12 +190,6 @@ out: return err; } -void ufshcd_pltfrm_shutdown(struct platform_device *pdev) -{ - ufshcd_shutdown((struct ufs_hba *)platform_get_drvdata(pdev)); -} -EXPORT_SYMBOL_GPL(ufshcd_pltfrm_shutdown); - static void ufshcd_init_lanes_per_dir(struct ufs_hba *hba) { struct device *dev = hba->dev; diff --git a/drivers/ufs/host/ufshcd-pltfrm.h b/drivers/ufs/host/ufshcd-pltfrm.h index 2e4ba2bfbcad..2df108f4ac13 100644 --- a/drivers/ufs/host/ufshcd-pltfrm.h +++ b/drivers/ufs/host/ufshcd-pltfrm.h @@ -31,7 +31,6 @@ int ufshcd_get_pwr_dev_param(const struct ufs_dev_params *dev_param, void ufshcd_init_pwr_dev_param(struct ufs_dev_params *dev_param); int ufshcd_pltfrm_init(struct platform_device *pdev, const struct ufs_hba_variant_ops *vops); -void ufshcd_pltfrm_shutdown(struct platform_device *pdev); int ufshcd_populate_vreg(struct device *dev, const char *name, struct ufs_vreg **out_vreg); diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h index f7553293ba98..db2e669985d5 100644 --- a/include/ufs/ufshcd.h +++ b/include/ufs/ufshcd.h @@ -1277,7 +1277,6 @@ extern int ufshcd_system_freeze(struct device *dev); extern int ufshcd_system_thaw(struct device *dev); extern int ufshcd_system_restore(struct device *dev); #endif -extern int ufshcd_shutdown(struct ufs_hba *hba); extern int ufshcd_dme_configure_adapt(struct ufs_hba *hba, int agreed_gear, -- cgit v1.2.3 From 01584c1e233740519d0e11aa20daa323d26bf598 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 8 Jun 2023 18:55:56 +0900 Subject: scsi: block: Improve ioprio value validity checks The introduction of the macro IOPRIO_PRIO_LEVEL() in commit eca2040972b4 ("scsi: block: ioprio: Clean up interface definition") results in an iopriority level to always be masked using the macro IOPRIO_LEVEL_MASK, and thus to the kernel always seeing an acceptable value for an I/O priority level when checked in ioprio_check_cap(). Before this patch, this function would return an error for some (but not all) invalid values for a level valid range of [0..7]. Restore and improve the detection of invalid priority levels by introducing the inline function ioprio_value() to check an ioprio class, level and hint value before combining these fields into a single value to be used with ioprio_set() or AIOs. If an invalid value for the class, level or hint of an ioprio is detected, ioprio_value() returns an ioprio using the class IOPRIO_CLASS_INVALID, indicating an invalid value and causing ioprio_check_cap() to return -EINVAL. Fixes: 6c913257226a ("scsi: block: Introduce ioprio hints") Fixes: eca2040972b4 ("scsi: block: ioprio: Clean up interface definition") Signed-off-by: Damien Le Moal Link: https://lore.kernel.org/r/20230608095556.124001-1-dlemoal@kernel.org Reviewed-by: Niklas Cassel Reviewed-by: Linus Walleij Signed-off-by: Martin K. Petersen --- block/ioprio.c | 1 + include/uapi/linux/ioprio.h | 50 ++++++++++++++++++++++++++++++--------------- 2 files changed, 34 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/block/ioprio.c b/block/ioprio.c index f0d9e818abc5..b5a942519a79 100644 --- a/block/ioprio.c +++ b/block/ioprio.c @@ -58,6 +58,7 @@ int ioprio_check_cap(int ioprio) if (level) return -EINVAL; break; + case IOPRIO_CLASS_INVALID: default: return -EINVAL; } diff --git a/include/uapi/linux/ioprio.h b/include/uapi/linux/ioprio.h index 4c4806e8230b..99440b2e8c35 100644 --- a/include/uapi/linux/ioprio.h +++ b/include/uapi/linux/ioprio.h @@ -2,19 +2,20 @@ #ifndef _UAPI_LINUX_IOPRIO_H #define _UAPI_LINUX_IOPRIO_H +#include +#include + /* * Gives us 8 prio classes with 13-bits of data for each class */ #define IOPRIO_CLASS_SHIFT 13 -#define IOPRIO_CLASS_MASK 0x07 +#define IOPRIO_NR_CLASSES 8 +#define IOPRIO_CLASS_MASK (IOPRIO_NR_CLASSES - 1) #define IOPRIO_PRIO_MASK ((1UL << IOPRIO_CLASS_SHIFT) - 1) #define IOPRIO_PRIO_CLASS(ioprio) \ (((ioprio) >> IOPRIO_CLASS_SHIFT) & IOPRIO_CLASS_MASK) #define IOPRIO_PRIO_DATA(ioprio) ((ioprio) & IOPRIO_PRIO_MASK) -#define IOPRIO_PRIO_VALUE(class, data) \ - ((((class) & IOPRIO_CLASS_MASK) << IOPRIO_CLASS_SHIFT) | \ - ((data) & IOPRIO_PRIO_MASK)) /* * These are the io priority classes as implemented by the BFQ and mq-deadline @@ -25,10 +26,13 @@ * served when no one else is using the disk. */ enum { - IOPRIO_CLASS_NONE, - IOPRIO_CLASS_RT, - IOPRIO_CLASS_BE, - IOPRIO_CLASS_IDLE, + IOPRIO_CLASS_NONE = 0, + IOPRIO_CLASS_RT = 1, + IOPRIO_CLASS_BE = 2, + IOPRIO_CLASS_IDLE = 3, + + /* Special class to indicate an invalid ioprio value */ + IOPRIO_CLASS_INVALID = 7, }; /* @@ -73,15 +77,6 @@ enum { #define IOPRIO_PRIO_HINT(ioprio) \ (((ioprio) >> IOPRIO_HINT_SHIFT) & IOPRIO_HINT_MASK) -/* - * Alternate macro for IOPRIO_PRIO_VALUE() to define an I/O priority with - * a class, level and hint. - */ -#define IOPRIO_PRIO_VALUE_HINT(class, level, hint) \ - ((((class) & IOPRIO_CLASS_MASK) << IOPRIO_CLASS_SHIFT) | \ - (((hint) & IOPRIO_HINT_MASK) << IOPRIO_HINT_SHIFT) | \ - ((level) & IOPRIO_LEVEL_MASK)) - /* * I/O hints. */ @@ -107,4 +102,25 @@ enum { IOPRIO_HINT_DEV_DURATION_LIMIT_7 = 7, }; +#define IOPRIO_BAD_VALUE(val, max) ((val) < 0 || (val) >= (max)) + +/* + * Return an I/O priority value based on a class, a level and a hint. + */ +static __always_inline __u16 ioprio_value(int class, int level, int hint) +{ + if (IOPRIO_BAD_VALUE(class, IOPRIO_NR_CLASSES) || + IOPRIO_BAD_VALUE(level, IOPRIO_NR_LEVELS) || + IOPRIO_BAD_VALUE(hint, IOPRIO_NR_HINTS)) + return IOPRIO_CLASS_INVALID << IOPRIO_CLASS_SHIFT; + + return (class << IOPRIO_CLASS_SHIFT) | + (hint << IOPRIO_HINT_SHIFT) | level; +} + +#define IOPRIO_PRIO_VALUE(class, level) \ + ioprio_value(class, level, IOPRIO_HINT_NONE) +#define IOPRIO_PRIO_VALUE_HINT(class, level, hint) \ + ioprio_value(class, level, hint) + #endif /* _UAPI_LINUX_IOPRIO_H */ -- cgit v1.2.3 From 0fef6bb730c490fcdc4347dbd21646d3ffe62cf5 Mon Sep 17 00:00:00 2001 From: Stanley Chu Date: Sat, 10 Jun 2023 10:15:51 +0800 Subject: scsi: ufs: core: mcq: Fix the incorrect OCS value for the device command In MCQ mode, when a device command uses a hardware queue shared with other commands, a race condition may occur in the following scenario: 1. A device command is completed in CQx with CQE entry "e". 2. The interrupt handler copies the "cqe" pointer to "hba->dev_cmd.cqe" and completes "hba->dev_cmd.complete". 3. The "ufshcd_wait_for_dev_cmd()" function is awakened and retrieves the OCS value from "hba->dev_cmd.cqe". However, there is a possibility that the CQE entry "e" will be overwritten by newly completed commands in CQx, resulting in an incorrect OCS value being received by "ufshcd_wait_for_dev_cmd()". To avoid this race condition, the OCS value should be immediately copied to the struct "lrb" of the device command. Then "ufshcd_wait_for_dev_cmd()" can retrieve the OCS value from the struct "lrb". Fixes: 57b1c0ef89ac ("scsi: ufs: core: mcq: Add support to allocate multiple queues") Suggested-by: Can Guo Signed-off-by: Stanley Chu Link: https://lore.kernel.org/r/20230610021553.1213-2-powen.kao@mediatek.com Tested-by: Po-Wen Kao Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/ufs/core/ufshcd.c | 10 +++++++--- include/ufs/ufshcd.h | 1 - 2 files changed, 7 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index add9ec12aa4d..ee4229c0e364 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -3086,7 +3086,7 @@ retry: * not trigger any race conditions. */ hba->dev_cmd.complete = NULL; - err = ufshcd_get_tr_ocs(lrbp, hba->dev_cmd.cqe); + err = ufshcd_get_tr_ocs(lrbp, NULL); if (!err) err = ufshcd_dev_cmd_completion(hba, lrbp); } else { @@ -3182,7 +3182,6 @@ static int ufshcd_exec_dev_cmd(struct ufs_hba *hba, goto out; hba->dev_cmd.complete = &wait; - hba->dev_cmd.cqe = NULL; ufshcd_add_query_upiu_trace(hba, UFS_QUERY_SEND, lrbp->ucd_req_ptr); @@ -5431,6 +5430,7 @@ void ufshcd_compl_one_cqe(struct ufs_hba *hba, int task_tag, { struct ufshcd_lrb *lrbp; struct scsi_cmnd *cmd; + enum utp_ocs ocs; lrbp = &hba->lrb[task_tag]; lrbp->compl_time_stamp = ktime_get(); @@ -5446,7 +5446,11 @@ void ufshcd_compl_one_cqe(struct ufs_hba *hba, int task_tag, } else if (lrbp->command_type == UTP_CMD_TYPE_DEV_MANAGE || lrbp->command_type == UTP_CMD_TYPE_UFS_STORAGE) { if (hba->dev_cmd.complete) { - hba->dev_cmd.cqe = cqe; + if (cqe) { + ocs = le32_to_cpu(cqe->status) & MASK_OCS; + lrbp->utr_descriptor_ptr->header.dword_2 = + cpu_to_le32(ocs); + } complete(hba->dev_cmd.complete); ufshcd_clk_scaling_update_busy(hba); } diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h index d65c9d07694d..92f073bda405 100644 --- a/include/ufs/ufshcd.h +++ b/include/ufs/ufshcd.h @@ -225,7 +225,6 @@ struct ufs_dev_cmd { struct mutex lock; struct completion *complete; struct ufs_query query; - struct cq_entry *cqe; }; /** -- cgit v1.2.3 From c4ad4f2e6646dcd29a1ff7ff682bf650a67b0335 Mon Sep 17 00:00:00 2001 From: Po-Wen Kao Date: Mon, 12 Jun 2023 16:58:09 +0800 Subject: scsi: ufs: core: Add host quirk UFSHCD_QUIRK_MCQ_BROKEN_INTR Quirk UFSHCD_QUIRK_MCQ_BROKEN_INTR is introduced for hosts that implement a different interrupt topology from the UFSHCI 4.0 spec. Some hosts raise per hw queue interrupt in addition to CQES (traditional) when ESI is disabled. Enabling this quirk will disable CQES and use only per hw queue interrupt. Signed-off-by: Po-Wen Kao Link: https://lore.kernel.org/r/20230612085817.12275-2-powen.kao@mediatek.com Reviewed-by: Stanley Chu Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/ufs/core/ufshcd.c | 6 +++++- include/ufs/ufshcd.h | 7 +++++++ 2 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index a1d009ad5f26..358b3240b6c5 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -8612,11 +8612,15 @@ err: static void ufshcd_config_mcq(struct ufs_hba *hba) { int ret; + u32 intrs; ret = ufshcd_mcq_vops_config_esi(hba); dev_info(hba->dev, "ESI %sconfigured\n", ret ? "is not " : ""); - ufshcd_enable_intr(hba, UFSHCD_ENABLE_MCQ_INTRS); + intrs = UFSHCD_ENABLE_MCQ_INTRS; + if (hba->quirks & UFSHCD_QUIRK_MCQ_BROKEN_INTR) + intrs &= ~MCQ_CQ_EVENT_STATUS; + ufshcd_enable_intr(hba, intrs); ufshcd_mcq_make_queues_operational(hba); ufshcd_mcq_config_mac(hba, hba->nutrs); diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h index 92f073bda405..5dc37e47f399 100644 --- a/include/ufs/ufshcd.h +++ b/include/ufs/ufshcd.h @@ -610,6 +610,13 @@ enum ufshcd_quirks { * to reinit the device after switching to maximum gear. */ UFSHCD_QUIRK_REINIT_AFTER_MAX_GEAR_SWITCH = 1 << 19, + + /* + * Some host raises interrupt (per queue) in addition to + * CQES (traditional) when ESI is disabled. + * Enable this quirk will disable CQES and use per queue interrupt. + */ + UFSHCD_QUIRK_MCQ_BROKEN_INTR = 1 << 20, }; enum ufshcd_caps { -- cgit v1.2.3 From aa9d5d0015a8b73aa557ab45933efe9cb68a3784 Mon Sep 17 00:00:00 2001 From: Po-Wen Kao Date: Mon, 12 Jun 2023 16:58:10 +0800 Subject: scsi: ufs: core: Add host quirk UFSHCD_QUIRK_MCQ_BROKEN_RTC Some hosts do not implement SQ Run Time Command (SQRTC) register, thus we need this quirk to skip the related flow. Signed-off-by: Po-Wen Kao Link: https://lore.kernel.org/r/20230612085817.12275-3-powen.kao@mediatek.com Reviewed-by: Bart Van Assche Reviewed-by: Stanley Chu Signed-off-by: Martin K. Petersen --- drivers/ufs/core/ufs-mcq.c | 12 ++++++++++++ include/ufs/ufshcd.h | 6 ++++++ 2 files changed, 18 insertions(+) (limited to 'include') diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c index 7b78cf2e0f53..420ae05b1078 100644 --- a/drivers/ufs/core/ufs-mcq.c +++ b/drivers/ufs/core/ufs-mcq.c @@ -451,6 +451,9 @@ static int ufshcd_mcq_sq_stop(struct ufs_hba *hba, struct ufs_hw_queue *hwq) u32 id = hwq->id, val; int err; + if (hba->quirks & UFSHCD_QUIRK_MCQ_BROKEN_RTC) + return -ETIMEDOUT; + writel(SQ_STOP, mcq_opr_base(hba, OPR_SQD, id) + REG_SQRTC); reg = mcq_opr_base(hba, OPR_SQD, id) + REG_SQRTS; err = read_poll_timeout(readl, val, val & SQ_STS, 20, @@ -467,6 +470,9 @@ static int ufshcd_mcq_sq_start(struct ufs_hba *hba, struct ufs_hw_queue *hwq) u32 id = hwq->id, val; int err; + if (hba->quirks & UFSHCD_QUIRK_MCQ_BROKEN_RTC) + return -ETIMEDOUT; + writel(SQ_START, mcq_opr_base(hba, OPR_SQD, id) + REG_SQRTC); reg = mcq_opr_base(hba, OPR_SQD, id) + REG_SQRTS; err = read_poll_timeout(readl, val, !(val & SQ_STS), 20, @@ -494,6 +500,9 @@ int ufshcd_mcq_sq_cleanup(struct ufs_hba *hba, int task_tag) u32 nexus, id, val; int err; + if (hba->quirks & UFSHCD_QUIRK_MCQ_BROKEN_RTC) + return -ETIMEDOUT; + if (task_tag != hba->nutrs - UFSHCD_NUM_RESERVED) { if (!cmd) return -EINVAL; @@ -576,6 +585,9 @@ static bool ufshcd_mcq_sqe_search(struct ufs_hba *hba, u64 addr, match; u32 sq_head_slot; + if (hba->quirks & UFSHCD_QUIRK_MCQ_BROKEN_RTC) + return true; + mutex_lock(&hwq->sq_mutex); ufshcd_mcq_sq_stop(hba, hwq); diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h index 5dc37e47f399..9674094d623d 100644 --- a/include/ufs/ufshcd.h +++ b/include/ufs/ufshcd.h @@ -617,6 +617,12 @@ enum ufshcd_quirks { * Enable this quirk will disable CQES and use per queue interrupt. */ UFSHCD_QUIRK_MCQ_BROKEN_INTR = 1 << 20, + + /* + * Some host does not implement SQ Run Time Command (SQRTC) register + * thus need this quirk to skip related flow. + */ + UFSHCD_QUIRK_MCQ_BROKEN_RTC = 1 << 21, }; enum ufshcd_caps { -- cgit v1.2.3 From 31950192d939a969415d0e1da4c62598023b0850 Mon Sep 17 00:00:00 2001 From: Martin Wilck Date: Wed, 14 Jun 2023 12:36:15 +0200 Subject: scsi: core: Replace scsi_target_block() with scsi_block_targets() All callers (fc_remote_port_delete(), __iscsi_block_session(), __srp_start_tl_fail_timers(), srp_reconnect_rport(), snic_tgt_del()) pass parent devices of scsi_target devices to scsi_target_block(). Rename the function to scsi_block_targets(), and simplify it by assuming that it is always passed a parent device. Also, have callers pass the Scsi_Host pointer to scsi_block_targets(), as every caller has this pointer readily available. Suggested-by: Christoph Hellwig Suggested-by: Bart Van Assche Signed-off-by: Martin Wilck Link: https://lore.kernel.org/r/20230614103616.31857-7-mwilck@suse.com Cc: Karan Tilak Kumar Cc: Sesidhar Baddela Reviewed-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_lib.c | 26 ++++++++++++++++---------- drivers/scsi/scsi_transport_fc.c | 2 +- drivers/scsi/scsi_transport_iscsi.c | 3 ++- drivers/scsi/scsi_transport_srp.c | 6 +++--- drivers/scsi/snic/snic_disc.c | 2 +- include/scsi/scsi_device.h | 2 +- 6 files changed, 24 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index b98750028044..55a327b2dd8b 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -2890,20 +2890,26 @@ target_block(struct device *dev, void *data) return 0; } +/** + * scsi_block_targets - transition all SCSI child devices to SDEV_BLOCK state + * @dev: a parent device of one or more scsi_target devices + * @shost: the Scsi_Host to which this device belongs + * + * Iterate over all children of @dev, which should be scsi_target devices, + * and switch all subordinate scsi devices to SDEV_BLOCK state. Wait for + * ongoing scsi_queue_rq() calls to finish. May sleep. + * + * Note: + * @dev must not itself be a scsi_target device. + */ void -scsi_target_block(struct device *dev) +scsi_block_targets(struct Scsi_Host *shost, struct device *dev) { - struct Scsi_Host *shost = dev_to_shost(dev); - - if (scsi_is_target_device(dev)) - starget_for_each_device(to_scsi_target(dev), NULL, - scsi_device_block); - else - device_for_each_child(dev, NULL, target_block); - + WARN_ON_ONCE(scsi_is_target_device(dev)); + device_for_each_child(dev, NULL, target_block); blk_mq_wait_quiesce_done(&shost->tag_set); } -EXPORT_SYMBOL_GPL(scsi_target_block); +EXPORT_SYMBOL_GPL(scsi_block_targets); static void device_unblock(struct scsi_device *sdev, void *data) diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c index 64ff2629eaf9..b04075f19445 100644 --- a/drivers/scsi/scsi_transport_fc.c +++ b/drivers/scsi/scsi_transport_fc.c @@ -3451,7 +3451,7 @@ fc_remote_port_delete(struct fc_rport *rport) spin_unlock_irqrestore(shost->host_lock, flags); - scsi_target_block(&rport->dev); + scsi_block_targets(shost, &rport->dev); /* see if we need to kill io faster than waiting for device loss */ if ((rport->fast_io_fail_tmo != -1) && diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index b9b97300e3b3..e527ece12453 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -1943,13 +1943,14 @@ static void __iscsi_block_session(struct work_struct *work) struct iscsi_cls_session *session = container_of(work, struct iscsi_cls_session, block_work); + struct Scsi_Host *shost = iscsi_session_to_shost(session); unsigned long flags; ISCSI_DBG_TRANS_SESSION(session, "Blocking session\n"); spin_lock_irqsave(&session->lock, flags); session->state = ISCSI_SESSION_FAILED; spin_unlock_irqrestore(&session->lock, flags); - scsi_target_block(&session->dev); + scsi_block_targets(shost, &session->dev); ISCSI_DBG_TRANS_SESSION(session, "Completed SCSI target blocking\n"); if (session->recovery_tmo >= 0) queue_delayed_work(session->workq, diff --git a/drivers/scsi/scsi_transport_srp.c b/drivers/scsi/scsi_transport_srp.c index 87d0fb8dc503..64f6b22e8cc0 100644 --- a/drivers/scsi/scsi_transport_srp.c +++ b/drivers/scsi/scsi_transport_srp.c @@ -396,7 +396,7 @@ static void srp_reconnect_work(struct work_struct *work) } /* - * scsi_target_block() must have been called before this function is + * scsi_block_targets() must have been called before this function is * called to guarantee that no .queuecommand() calls are in progress. */ static void __rport_fail_io_fast(struct srp_rport *rport) @@ -480,7 +480,7 @@ static void __srp_start_tl_fail_timers(struct srp_rport *rport) srp_rport_set_state(rport, SRP_RPORT_BLOCKED) == 0) { pr_debug("%s new state: %d\n", dev_name(&shost->shost_gendev), rport->state); - scsi_target_block(&shost->shost_gendev); + scsi_block_targets(shost, &shost->shost_gendev); if (fast_io_fail_tmo >= 0) queue_delayed_work(system_long_wq, &rport->fast_io_fail_work, @@ -548,7 +548,7 @@ int srp_reconnect_rport(struct srp_rport *rport) * later is ok though, scsi_internal_device_unblock_nowait() * treats SDEV_TRANSPORT_OFFLINE like SDEV_BLOCK. */ - scsi_target_block(&shost->shost_gendev); + scsi_block_targets(shost, &shost->shost_gendev); res = rport->state != SRP_RPORT_LOST ? i->f->reconnect(rport) : -ENODEV; pr_debug("%s (state %d): transport.reconnect() returned %d\n", dev_name(&shost->shost_gendev), rport->state, res); diff --git a/drivers/scsi/snic/snic_disc.c b/drivers/scsi/snic/snic_disc.c index 8fbf3c1b1311..3e2e5783924d 100644 --- a/drivers/scsi/snic/snic_disc.c +++ b/drivers/scsi/snic/snic_disc.c @@ -214,7 +214,7 @@ snic_tgt_del(struct work_struct *work) scsi_flush_work(shost); /* Block IOs on child devices, stops new IOs */ - scsi_target_block(&tgt->dev); + scsi_block_targets(shost, &tgt->dev); /* Cleanup IOs */ snic_tgt_scsi_abort_io(tgt); diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index f10a008e5bfa..8bd5b00b33cc 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -450,7 +450,7 @@ extern void scsi_scan_target(struct device *parent, unsigned int channel, unsigned int id, u64 lun, enum scsi_scan_mode rescan); extern void scsi_target_reap(struct scsi_target *); -extern void scsi_target_block(struct device *); +void scsi_block_targets(struct Scsi_Host *shost, struct device *dev); extern void scsi_target_unblock(struct device *, enum scsi_device_state); extern void scsi_remove_target(struct device *); extern const char *scsi_device_state_name(enum scsi_device_state); -- cgit v1.2.3