Merge tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi
Pull more SCSI updates from James Bottomley:
"The vfs has long had a write lifetime hint mechanism that gives the
expected longevity on storage of the data being written. f2fs was the
original consumer of this and used the hint for flash data placement
(mostly to avoid write amplification by placing objects with similar
lifetimes in the same erase block).
More recently the SCSI based UFS (Universal Flash Storage) drivers
have wanted to take advantage of this as well, for the same reasons as
f2fs, necessitating plumbing the write hints through the block layer
and then adding it to the SCSI core.
The vfs write_hints already taken plumbs this as far as block and this
completes the SCSI core enabling based on a recently agreed reuse of
the old write command group number. The additions to the scsi_debug
driver are for emulating this property so we can run tests on it in
the absence of an actual UFS device"
* tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi:
scsi: scsi_debug: Maintain write statistics per group number
scsi: scsi_debug: Implement GET STREAM STATUS
scsi: scsi_debug: Implement the IO Advice Hints Grouping mode page
scsi: scsi_debug: Allocate the MODE SENSE response from the heap
scsi: scsi_debug: Rework subpage code error handling
scsi: scsi_debug: Rework page code error handling
scsi: scsi_debug: Support the block limits extension VPD page
scsi: scsi_debug: Reduce code duplication
scsi: sd: Translate data lifetime information
scsi: scsi_proto: Add structures and constants related to I/O groups and streams
scsi: core: Query the Block Limits Extension VPD page
diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index 8b40f75..634f2f5 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -241,6 +241,11 @@
Note that this setting also affects whether resuming from
system suspend will be performed asynchronously.
+config SCSI_PROTO_TEST
+ tristate "scsi_proto.h unit tests" if !KUNIT_ALL_TESTS
+ depends on SCSI && KUNIT
+ default KUNIT_ALL_TESTS
+
menu "SCSI Transports"
depends on SCSI
diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile
index f055bfd..1313ddf 100644
--- a/drivers/scsi/Makefile
+++ b/drivers/scsi/Makefile
@@ -24,6 +24,8 @@
obj-$(CONFIG_RAID_ATTRS) += raid_class.o
+obj-$(CONFIG_SCSI_PROTO_TEST) += scsi_proto_test.o
+
# --- NOTE ORDERING HERE ---
# For kernel non-modular link, transport attributes need to
# be initialised before drivers
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index 8cad979..3e0c038 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -517,6 +517,8 @@
scsi_update_vpd_page(sdev, 0xb1, &sdev->vpd_pgb1);
if (vpd_buf->data[i] == 0xb2)
scsi_update_vpd_page(sdev, 0xb2, &sdev->vpd_pgb2);
+ if (vpd_buf->data[i] == 0xb7)
+ scsi_update_vpd_page(sdev, 0xb7, &sdev->vpd_pgb7);
}
kfree(vpd_buf);
}
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 914d9c1..acf0592 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -43,6 +43,7 @@
#include <linux/prefetch.h>
#include <linux/debugfs.h>
#include <linux/async.h>
+#include <linux/cleanup.h>
#include <net/checksum.h>
@@ -532,6 +533,8 @@
static int resp_start_stop(struct scsi_cmnd *, struct sdebug_dev_info *);
static int resp_readcap16(struct scsi_cmnd *, struct sdebug_dev_info *);
static int resp_get_lba_status(struct scsi_cmnd *, struct sdebug_dev_info *);
+static int resp_get_stream_status(struct scsi_cmnd *scp,
+ struct sdebug_dev_info *devip);
static int resp_report_tgtpgs(struct scsi_cmnd *, struct sdebug_dev_info *);
static int resp_unmap(struct scsi_cmnd *, struct sdebug_dev_info *);
static int resp_rsup_opcodes(struct scsi_cmnd *, struct sdebug_dev_info *);
@@ -606,6 +609,9 @@
{0, 0x9e, 0x12, F_SA_LOW | F_D_IN, resp_get_lba_status, NULL,
{16, 0x12, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
0xff, 0xff, 0xff, 0, 0xc7} }, /* GET LBA STATUS(16) */
+ {0, 0x9e, 0x16, F_SA_LOW | F_D_IN, resp_get_stream_status, NULL,
+ {16, 0x16, 0, 0, 0xff, 0xff, 0, 0, 0, 0, 0xff, 0xff, 0xff, 0xff,
+ 0, 0} }, /* GET STREAM STATUS */
};
static const struct opcode_info_t vl_iarr[] = { /* VARIABLE LENGTH */
@@ -896,6 +902,8 @@
static int submit_queues = DEF_SUBMIT_QUEUES; /* > 1 for multi-queue (mq) */
static int poll_queues; /* iouring iopoll interface.*/
+static atomic_long_t writes_by_group_number[64];
+
static char sdebug_proc_name[] = MY_NAME;
static const char *my_name = MY_NAME;
@@ -1867,6 +1875,19 @@
return 0x3c;
}
+#define SDEBUG_BLE_LEN_AFTER_B4 28 /* thus vpage 32 bytes long */
+
+enum { MAXIMUM_NUMBER_OF_STREAMS = 6, PERMANENT_STREAM_COUNT = 5 };
+
+/* Block limits extension VPD page (SBC-4) */
+static int inquiry_vpd_b7(unsigned char *arrb4)
+{
+ memset(arrb4, 0, SDEBUG_BLE_LEN_AFTER_B4);
+ arrb4[1] = 1; /* Reduced stream control support (RSCS) */
+ put_unaligned_be16(MAXIMUM_NUMBER_OF_STREAMS, &arrb4[2]);
+ return SDEBUG_BLE_LEN_AFTER_B4;
+}
+
#define SDEBUG_LONG_INQ_SZ 96
#define SDEBUG_MAX_INQ_ARR_SZ 584
@@ -1903,7 +1924,8 @@
u32 len;
char lu_id_str[6];
int host_no = devip->sdbg_host->shost->host_no;
-
+
+ arr[1] = cmd[2];
port_group_id = (((host_no + 1) & 0x7f) << 8) +
(devip->channel & 0x7f);
if (sdebug_vpd_use_hostno == 0)
@@ -1914,7 +1936,6 @@
(devip->target * 1000) - 3;
len = scnprintf(lu_id_str, 6, "%d", lu_id_num);
if (0 == cmd[2]) { /* supported vital product data pages */
- arr[1] = cmd[2]; /*sanity */
n = 4;
arr[n++] = 0x0; /* this page */
arr[n++] = 0x80; /* unit serial number */
@@ -1932,26 +1953,22 @@
arr[n++] = 0xb2; /* LB Provisioning */
if (is_zbc)
arr[n++] = 0xb6; /* ZB dev. char. */
+ arr[n++] = 0xb7; /* Block limits extension */
}
arr[3] = n - 4; /* number of supported VPD pages */
} else if (0x80 == cmd[2]) { /* unit serial number */
- arr[1] = cmd[2]; /*sanity */
arr[3] = len;
memcpy(&arr[4], lu_id_str, len);
} else if (0x83 == cmd[2]) { /* device identification */
- arr[1] = cmd[2]; /*sanity */
arr[3] = inquiry_vpd_83(&arr[4], port_group_id,
target_dev_id, lu_id_num,
lu_id_str, len,
&devip->lu_name);
} else if (0x84 == cmd[2]) { /* Software interface ident. */
- arr[1] = cmd[2]; /*sanity */
arr[3] = inquiry_vpd_84(&arr[4]);
} else if (0x85 == cmd[2]) { /* Management network addresses */
- arr[1] = cmd[2]; /*sanity */
arr[3] = inquiry_vpd_85(&arr[4]);
} else if (0x86 == cmd[2]) { /* extended inquiry */
- arr[1] = cmd[2]; /*sanity */
arr[3] = 0x3c; /* number of following entries */
if (sdebug_dif == T10_PI_TYPE3_PROTECTION)
arr[4] = 0x4; /* SPT: GRD_CHK:1 */
@@ -1959,33 +1976,32 @@
arr[4] = 0x5; /* SPT: GRD_CHK:1, REF_CHK:1 */
else
arr[4] = 0x0; /* no protection stuff */
- arr[5] = 0x7; /* head of q, ordered + simple q's */
+ /*
+ * GROUP_SUP=1; HEADSUP=1 (HEAD OF QUEUE); ORDSUP=1
+ * (ORDERED queuing); SIMPSUP=1 (SIMPLE queuing).
+ */
+ arr[5] = 0x17;
} else if (0x87 == cmd[2]) { /* mode page policy */
- arr[1] = cmd[2]; /*sanity */
arr[3] = 0x8; /* number of following entries */
arr[4] = 0x2; /* disconnect-reconnect mp */
arr[6] = 0x80; /* mlus, shared */
arr[8] = 0x18; /* protocol specific lu */
arr[10] = 0x82; /* mlus, per initiator port */
} else if (0x88 == cmd[2]) { /* SCSI Ports */
- arr[1] = cmd[2]; /*sanity */
arr[3] = inquiry_vpd_88(&arr[4], target_dev_id);
} else if (is_disk_zbc && 0x89 == cmd[2]) { /* ATA info */
- arr[1] = cmd[2]; /*sanity */
n = inquiry_vpd_89(&arr[4]);
put_unaligned_be16(n, arr + 2);
} else if (is_disk_zbc && 0xb0 == cmd[2]) { /* Block limits */
- arr[1] = cmd[2]; /*sanity */
arr[3] = inquiry_vpd_b0(&arr[4]);
} else if (is_disk_zbc && 0xb1 == cmd[2]) { /* Block char. */
- arr[1] = cmd[2]; /*sanity */
arr[3] = inquiry_vpd_b1(devip, &arr[4]);
} else if (is_disk && 0xb2 == cmd[2]) { /* LB Prov. */
- arr[1] = cmd[2]; /*sanity */
arr[3] = inquiry_vpd_b2(&arr[4]);
} else if (is_zbc && cmd[2] == 0xb6) { /* ZB dev. charact. */
- arr[1] = cmd[2]; /*sanity */
arr[3] = inquiry_vpd_b6(devip, &arr[4]);
+ } else if (cmd[2] == 0xb7) { /* block limits extension page */
+ arr[3] = inquiry_vpd_b7(&arr[4]);
} else {
mk_sense_invalid_fld(scp, SDEB_IN_CDB, 2, -1);
kfree(arr);
@@ -2554,6 +2570,40 @@
return sizeof(ctrl_m_pg);
}
+/* IO Advice Hints Grouping mode page */
+static int resp_grouping_m_pg(unsigned char *p, int pcontrol, int target)
+{
+ /* IO Advice Hints Grouping mode page */
+ struct grouping_m_pg {
+ u8 page_code; /* OR 0x40 when subpage_code > 0 */
+ u8 subpage_code;
+ __be16 page_length;
+ u8 reserved[12];
+ struct scsi_io_group_descriptor descr[MAXIMUM_NUMBER_OF_STREAMS];
+ };
+ static const struct grouping_m_pg gr_m_pg = {
+ .page_code = 0xa | 0x40,
+ .subpage_code = 5,
+ .page_length = cpu_to_be16(sizeof(gr_m_pg) - 4),
+ .descr = {
+ { .st_enble = 1 },
+ { .st_enble = 1 },
+ { .st_enble = 1 },
+ { .st_enble = 1 },
+ { .st_enble = 1 },
+ { .st_enble = 0 },
+ }
+ };
+
+ BUILD_BUG_ON(sizeof(struct grouping_m_pg) !=
+ 16 + MAXIMUM_NUMBER_OF_STREAMS * 16);
+ memcpy(p, &gr_m_pg, sizeof(gr_m_pg));
+ if (1 == pcontrol) {
+ /* There are no changeable values so clear from byte 4 on. */
+ memset(p + 4, 0, sizeof(gr_m_pg) - 4);
+ }
+ return sizeof(gr_m_pg);
+}
static int resp_iec_m_pg(unsigned char *p, int pcontrol, int target)
{ /* Informational Exceptions control mode page for mode_sense */
@@ -2627,7 +2677,8 @@
return sizeof(sas_sha_m_pg);
}
-#define SDEBUG_MAX_MSENSE_SZ 256
+/* PAGE_SIZE is more than necessary but provides room for future expansion. */
+#define SDEBUG_MAX_MSENSE_SZ PAGE_SIZE
static int resp_mode_sense(struct scsi_cmnd *scp,
struct sdebug_dev_info *devip)
@@ -2638,10 +2689,13 @@
int target_dev_id;
int target = scp->device->id;
unsigned char *ap;
- unsigned char arr[SDEBUG_MAX_MSENSE_SZ];
+ unsigned char *arr __free(kfree);
unsigned char *cmd = scp->cmnd;
- bool dbd, llbaa, msense_6, is_disk, is_zbc, bad_pcode;
+ bool dbd, llbaa, msense_6, is_disk, is_zbc;
+ arr = kzalloc(SDEBUG_MAX_MSENSE_SZ, GFP_ATOMIC);
+ if (!arr)
+ return -ENOMEM;
dbd = !!(cmd[1] & 0x8); /* disable block descriptors */
pcontrol = (cmd[2] & 0xc0) >> 6;
pcode = cmd[2] & 0x3f;
@@ -2699,45 +2753,63 @@
ap = arr + offset;
}
- if ((subpcode > 0x0) && (subpcode < 0xff) && (0x19 != pcode)) {
- /* TODO: Control Extension page */
- mk_sense_invalid_fld(scp, SDEB_IN_CDB, 3, -1);
- return check_condition_result;
- }
- bad_pcode = false;
-
+ /*
+ * N.B. If len>0 before resp_*_pg() call, then form of that call should be:
+ * len += resp_*_pg(ap + len, pcontrol, target);
+ */
switch (pcode) {
case 0x1: /* Read-Write error recovery page, direct access */
+ if (subpcode > 0x0 && subpcode < 0xff)
+ goto bad_subpcode;
len = resp_err_recov_pg(ap, pcontrol, target);
offset += len;
break;
case 0x2: /* Disconnect-Reconnect page, all devices */
+ if (subpcode > 0x0 && subpcode < 0xff)
+ goto bad_subpcode;
len = resp_disconnect_pg(ap, pcontrol, target);
offset += len;
break;
case 0x3: /* Format device page, direct access */
+ if (subpcode > 0x0 && subpcode < 0xff)
+ goto bad_subpcode;
if (is_disk) {
len = resp_format_pg(ap, pcontrol, target);
offset += len;
- } else
- bad_pcode = true;
+ } else {
+ goto bad_pcode;
+ }
break;
case 0x8: /* Caching page, direct access */
+ if (subpcode > 0x0 && subpcode < 0xff)
+ goto bad_subpcode;
if (is_disk || is_zbc) {
len = resp_caching_pg(ap, pcontrol, target);
offset += len;
- } else
- bad_pcode = true;
+ } else {
+ goto bad_pcode;
+ }
break;
case 0xa: /* Control Mode page, all devices */
- len = resp_ctrl_m_pg(ap, pcontrol, target);
+ switch (subpcode) {
+ case 0:
+ len = resp_ctrl_m_pg(ap, pcontrol, target);
+ break;
+ case 0x05:
+ len = resp_grouping_m_pg(ap, pcontrol, target);
+ break;
+ case 0xff:
+ len = resp_ctrl_m_pg(ap, pcontrol, target);
+ len += resp_grouping_m_pg(ap + len, pcontrol, target);
+ break;
+ default:
+ goto bad_subpcode;
+ }
offset += len;
break;
case 0x19: /* if spc==1 then sas phy, control+discover */
- if ((subpcode > 0x2) && (subpcode < 0xff)) {
- mk_sense_invalid_fld(scp, SDEB_IN_CDB, 3, -1);
- return check_condition_result;
- }
+ if (subpcode > 0x2 && subpcode < 0xff)
+ goto bad_subpcode;
len = 0;
if ((0x0 == subpcode) || (0xff == subpcode))
len += resp_sas_sf_m_pg(ap + len, pcontrol, target);
@@ -2749,49 +2821,50 @@
offset += len;
break;
case 0x1c: /* Informational Exceptions Mode page, all devices */
+ if (subpcode > 0x0 && subpcode < 0xff)
+ goto bad_subpcode;
len = resp_iec_m_pg(ap, pcontrol, target);
offset += len;
break;
case 0x3f: /* Read all Mode pages */
- if ((0 == subpcode) || (0xff == subpcode)) {
- len = resp_err_recov_pg(ap, pcontrol, target);
- len += resp_disconnect_pg(ap + len, pcontrol, target);
- if (is_disk) {
- len += resp_format_pg(ap + len, pcontrol,
- target);
- len += resp_caching_pg(ap + len, pcontrol,
- target);
- } else if (is_zbc) {
- len += resp_caching_pg(ap + len, pcontrol,
- target);
- }
- len += resp_ctrl_m_pg(ap + len, pcontrol, target);
- len += resp_sas_sf_m_pg(ap + len, pcontrol, target);
- if (0xff == subpcode) {
- len += resp_sas_pcd_m_spg(ap + len, pcontrol,
- target, target_dev_id);
- len += resp_sas_sha_m_spg(ap + len, pcontrol);
- }
- len += resp_iec_m_pg(ap + len, pcontrol, target);
- offset += len;
- } else {
- mk_sense_invalid_fld(scp, SDEB_IN_CDB, 3, -1);
- return check_condition_result;
+ if (subpcode > 0x0 && subpcode < 0xff)
+ goto bad_subpcode;
+ len = resp_err_recov_pg(ap, pcontrol, target);
+ len += resp_disconnect_pg(ap + len, pcontrol, target);
+ if (is_disk) {
+ len += resp_format_pg(ap + len, pcontrol, target);
+ len += resp_caching_pg(ap + len, pcontrol, target);
+ } else if (is_zbc) {
+ len += resp_caching_pg(ap + len, pcontrol, target);
}
+ len += resp_ctrl_m_pg(ap + len, pcontrol, target);
+ if (0xff == subpcode)
+ len += resp_grouping_m_pg(ap + len, pcontrol, target);
+ len += resp_sas_sf_m_pg(ap + len, pcontrol, target);
+ if (0xff == subpcode) {
+ len += resp_sas_pcd_m_spg(ap + len, pcontrol, target,
+ target_dev_id);
+ len += resp_sas_sha_m_spg(ap + len, pcontrol);
+ }
+ len += resp_iec_m_pg(ap + len, pcontrol, target);
+ offset += len;
break;
default:
- bad_pcode = true;
- break;
- }
- if (bad_pcode) {
- mk_sense_invalid_fld(scp, SDEB_IN_CDB, 2, 5);
- return check_condition_result;
+ goto bad_pcode;
}
if (msense_6)
arr[0] = offset - 1;
else
put_unaligned_be16((offset - 2), arr + 0);
return fill_from_dev_buffer(scp, arr, min_t(u32, alloc_len, offset));
+
+bad_pcode:
+ mk_sense_invalid_fld(scp, SDEB_IN_CDB, 2, 5);
+ return check_condition_result;
+
+bad_subpcode:
+ mk_sense_invalid_fld(scp, SDEB_IN_CDB, 3, -1);
+ return check_condition_result;
}
#define SDEBUG_MAX_MSELECT_SZ 512
@@ -3306,7 +3379,8 @@
/* Returns number of bytes copied or -1 if error. */
static int do_device_access(struct sdeb_store_info *sip, struct scsi_cmnd *scp,
- u32 sg_skip, u64 lba, u32 num, bool do_write)
+ u32 sg_skip, u64 lba, u32 num, bool do_write,
+ u8 group_number)
{
int ret;
u64 block, rest = 0;
@@ -3325,6 +3399,10 @@
return 0;
if (scp->sc_data_direction != dir)
return -1;
+
+ if (do_write && group_number < ARRAY_SIZE(writes_by_group_number))
+ atomic_long_inc(&writes_by_group_number[group_number]);
+
fsp = sip->storep;
block = do_div(lba, sdebug_store_sectors);
@@ -3698,7 +3776,7 @@
}
}
- ret = do_device_access(sip, scp, 0, lba, num, false);
+ ret = do_device_access(sip, scp, 0, lba, num, false, 0);
sdeb_read_unlock(sip);
if (unlikely(ret == -1))
return DID_ERROR << 16;
@@ -3883,6 +3961,7 @@
{
bool check_prot;
u32 num;
+ u8 group = 0;
u32 ei_lba;
int ret;
u64 lba;
@@ -3894,11 +3973,13 @@
ei_lba = 0;
lba = get_unaligned_be64(cmd + 2);
num = get_unaligned_be32(cmd + 10);
+ group = cmd[14] & 0x3f;
check_prot = true;
break;
case WRITE_10:
ei_lba = 0;
lba = get_unaligned_be32(cmd + 2);
+ group = cmd[6] & 0x3f;
num = get_unaligned_be16(cmd + 7);
check_prot = true;
break;
@@ -3913,15 +3994,18 @@
ei_lba = 0;
lba = get_unaligned_be32(cmd + 2);
num = get_unaligned_be32(cmd + 6);
+ group = cmd[6] & 0x3f;
check_prot = true;
break;
case 0x53: /* XDWRITEREAD(10) */
ei_lba = 0;
lba = get_unaligned_be32(cmd + 2);
+ group = cmd[6] & 0x1f;
num = get_unaligned_be16(cmd + 7);
check_prot = false;
break;
default: /* assume WRITE(32) */
+ group = cmd[6] & 0x3f;
lba = get_unaligned_be64(cmd + 12);
ei_lba = get_unaligned_be32(cmd + 20);
num = get_unaligned_be32(cmd + 28);
@@ -3976,7 +4060,7 @@
}
}
- ret = do_device_access(sip, scp, 0, lba, num, true);
+ ret = do_device_access(sip, scp, 0, lba, num, true, group);
if (unlikely(scsi_debug_lbp()))
map_region(sip, lba, num);
/* If ZBC zone then bump its write pointer */
@@ -4028,12 +4112,14 @@
u32 lb_size = sdebug_sector_size;
u32 ei_lba;
u64 lba;
+ u8 group;
int ret, res;
bool is_16;
static const u32 lrd_size = 32; /* + parameter list header size */
if (cmd[0] == VARIABLE_LENGTH_CMD) {
is_16 = false;
+ group = cmd[6] & 0x3f;
wrprotect = (cmd[10] >> 5) & 0x7;
lbdof = get_unaligned_be16(cmd + 12);
num_lrd = get_unaligned_be16(cmd + 16);
@@ -4044,6 +4130,7 @@
lbdof = get_unaligned_be16(cmd + 4);
num_lrd = get_unaligned_be16(cmd + 8);
bt_len = get_unaligned_be32(cmd + 10);
+ group = cmd[14] & 0x3f;
if (unlikely(have_dif_prot)) {
if (sdebug_dif == T10_PI_TYPE2_PROTECTION &&
wrprotect) {
@@ -4132,7 +4219,7 @@
}
}
- ret = do_device_access(sip, scp, sg_off, lba, num, true);
+ ret = do_device_access(sip, scp, sg_off, lba, num, true, group);
/* If ZBC zone then bump its write pointer */
if (sdebug_dev_is_zoned(devip))
zbc_inc_wp(devip, lba, num);
@@ -4507,6 +4594,51 @@
return fill_from_dev_buffer(scp, arr, SDEBUG_GET_LBA_STATUS_LEN);
}
+static int resp_get_stream_status(struct scsi_cmnd *scp,
+ struct sdebug_dev_info *devip)
+{
+ u16 starting_stream_id, stream_id;
+ const u8 *cmd = scp->cmnd;
+ u32 alloc_len, offset;
+ u8 arr[256] = {};
+ struct scsi_stream_status_header *h = (void *)arr;
+
+ starting_stream_id = get_unaligned_be16(cmd + 4);
+ alloc_len = get_unaligned_be32(cmd + 10);
+
+ if (alloc_len < 8) {
+ mk_sense_invalid_fld(scp, SDEB_IN_CDB, 10, -1);
+ return check_condition_result;
+ }
+
+ if (starting_stream_id >= MAXIMUM_NUMBER_OF_STREAMS) {
+ mk_sense_invalid_fld(scp, SDEB_IN_CDB, 4, -1);
+ return check_condition_result;
+ }
+
+ /*
+ * The GET STREAM STATUS command only reports status information
+ * about open streams. Treat the non-permanent stream as open.
+ */
+ put_unaligned_be16(MAXIMUM_NUMBER_OF_STREAMS,
+ &h->number_of_open_streams);
+
+ for (offset = 8, stream_id = starting_stream_id;
+ offset + 8 <= min_t(u32, alloc_len, sizeof(arr)) &&
+ stream_id < MAXIMUM_NUMBER_OF_STREAMS;
+ offset += 8, stream_id++) {
+ struct scsi_stream_status *stream_status = (void *)arr + offset;
+
+ stream_status->perm = stream_id < PERMANENT_STREAM_COUNT;
+ put_unaligned_be16(stream_id,
+ &stream_status->stream_identifier);
+ stream_status->rel_lifetime = stream_id + 1;
+ }
+ put_unaligned_be32(offset - 8, &h->len); /* PARAMETER DATA LENGTH */
+
+ return fill_from_dev_buffer(scp, arr, min(offset, alloc_len));
+}
+
static int resp_sync_cache(struct scsi_cmnd *scp,
struct sdebug_dev_info *devip)
{
@@ -7182,6 +7314,30 @@
}
static DRIVER_ATTR_RO(tur_ms_to_ready);
+static ssize_t group_number_stats_show(struct device_driver *ddp, char *buf)
+{
+ char *p = buf, *end = buf + PAGE_SIZE;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(writes_by_group_number); i++)
+ p += scnprintf(p, end - p, "%d %ld\n", i,
+ atomic_long_read(&writes_by_group_number[i]));
+
+ return p - buf;
+}
+
+static ssize_t group_number_stats_store(struct device_driver *ddp,
+ const char *buf, size_t count)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(writes_by_group_number); i++)
+ atomic_long_set(&writes_by_group_number[i], 0);
+
+ return count;
+}
+static DRIVER_ATTR_RW(group_number_stats);
+
/* Note: The following array creates attribute files in the
/sys/bus/pseudo/drivers/scsi_debug directory. The advantage of these
files (over those found in the /sys/module/scsi_debug/parameters
@@ -7228,6 +7384,7 @@
&driver_attr_cdb_len.attr,
&driver_attr_tur_ms_to_ready.attr,
&driver_attr_zbc.attr,
+ &driver_attr_group_number_stats.attr,
NULL,
};
ATTRIBUTE_GROUPS(sdebug_drv);
diff --git a/drivers/scsi/scsi_proto_test.c b/drivers/scsi/scsi_proto_test.c
new file mode 100644
index 0000000..7fa0a78
--- /dev/null
+++ b/drivers/scsi/scsi_proto_test.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2023 Google LLC
+ */
+#include <kunit/test.h>
+#include <asm-generic/unaligned.h>
+#include <scsi/scsi_proto.h>
+
+static void test_scsi_proto(struct kunit *test)
+{
+ static const union {
+ struct scsi_io_group_descriptor desc;
+ u8 arr[sizeof(struct scsi_io_group_descriptor)];
+ } d = { .arr = { 0x45, 0, 0, 0, 0xb0, 0xe4, 0xe3 } };
+ KUNIT_EXPECT_EQ(test, d.desc.io_advice_hints_mode + 0, 1);
+ KUNIT_EXPECT_EQ(test, d.desc.st_enble + 0, 1);
+ KUNIT_EXPECT_EQ(test, d.desc.cs_enble + 0, 0);
+ KUNIT_EXPECT_EQ(test, d.desc.ic_enable + 0, 1);
+ KUNIT_EXPECT_EQ(test, d.desc.acdlu + 0, 1);
+ KUNIT_EXPECT_EQ(test, d.desc.rlbsr + 0, 3);
+ KUNIT_EXPECT_EQ(test, d.desc.lbm_descriptor_type + 0, 0);
+ KUNIT_EXPECT_EQ(test, d.desc.params[0] + 0, 0xe4);
+ KUNIT_EXPECT_EQ(test, d.desc.params[1] + 0, 0xe3);
+
+ static const union {
+ struct scsi_stream_status s;
+ u8 arr[sizeof(struct scsi_stream_status)];
+ } ss = { .arr = { 0x80, 0, 0x12, 0x34, 0x3f } };
+ KUNIT_EXPECT_EQ(test, ss.s.perm + 0, 1);
+ KUNIT_EXPECT_EQ(test, get_unaligned_be16(&ss.s.stream_identifier),
+ 0x1234);
+ KUNIT_EXPECT_EQ(test, ss.s.rel_lifetime + 0, 0x3f);
+
+ static const union {
+ struct scsi_stream_status_header h;
+ u8 arr[sizeof(struct scsi_stream_status_header)];
+ } sh = { .arr = { 1, 2, 3, 4, 0, 0, 5, 6 } };
+ KUNIT_EXPECT_EQ(test, get_unaligned_be32(&sh.h.len), 0x1020304);
+ KUNIT_EXPECT_EQ(test, get_unaligned_be16(&sh.h.number_of_open_streams),
+ 0x506);
+}
+
+static struct kunit_case scsi_proto_test_cases[] = {
+ KUNIT_CASE(test_scsi_proto),
+ {}
+};
+
+static struct kunit_suite scsi_proto_test_suite = {
+ .name = "scsi_proto",
+ .test_cases = scsi_proto_test_cases,
+};
+kunit_test_suite(scsi_proto_test_suite);
+
+MODULE_DESCRIPTION("<scsi/scsi_proto.h> unit tests");
+MODULE_AUTHOR("Bart Van Assche");
+MODULE_LICENSE("GPL");
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index 49dd344..775df00 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -449,6 +449,7 @@
struct scsi_vpd *vpd_pg80 = NULL, *vpd_pg83 = NULL;
struct scsi_vpd *vpd_pg0 = NULL, *vpd_pg89 = NULL;
struct scsi_vpd *vpd_pgb0 = NULL, *vpd_pgb1 = NULL, *vpd_pgb2 = NULL;
+ struct scsi_vpd *vpd_pgb7 = NULL;
unsigned long flags;
might_sleep();
@@ -494,6 +495,8 @@
lockdep_is_held(&sdev->inquiry_mutex));
vpd_pgb2 = rcu_replace_pointer(sdev->vpd_pgb2, vpd_pgb2,
lockdep_is_held(&sdev->inquiry_mutex));
+ vpd_pgb7 = rcu_replace_pointer(sdev->vpd_pgb7, vpd_pgb7,
+ lockdep_is_held(&sdev->inquiry_mutex));
mutex_unlock(&sdev->inquiry_mutex);
if (vpd_pg0)
@@ -510,6 +513,8 @@
kfree_rcu(vpd_pgb1, rcu);
if (vpd_pgb2)
kfree_rcu(vpd_pgb2, rcu);
+ if (vpd_pgb7)
+ kfree_rcu(vpd_pgb7, rcu);
kfree(sdev->inquiry);
kfree(sdev);
@@ -921,6 +926,7 @@
sdev_vpd_pg_attr(pgb0);
sdev_vpd_pg_attr(pgb1);
sdev_vpd_pg_attr(pgb2);
+sdev_vpd_pg_attr(pgb7);
sdev_vpd_pg_attr(pg0);
static ssize_t show_inquiry(struct file *filep, struct kobject *kobj,
@@ -1295,6 +1301,9 @@
if (attr == &dev_attr_vpd_pgb2 && !sdev->vpd_pgb2)
return 0;
+ if (attr == &dev_attr_vpd_pgb7 && !sdev->vpd_pgb7)
+ return 0;
+
return S_IRUGO;
}
@@ -1347,6 +1356,7 @@
&dev_attr_vpd_pgb0,
&dev_attr_vpd_pgb1,
&dev_attr_vpd_pgb2,
+ &dev_attr_vpd_pgb7,
&dev_attr_inquiry,
NULL
};
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 2cc73c6..ccff8f2 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -47,6 +47,7 @@
#include <linux/blkpg.h>
#include <linux/blk-pm.h>
#include <linux/delay.h>
+#include <linux/rw_hint.h>
#include <linux/major.h>
#include <linux/mutex.h>
#include <linux/string_helpers.h>
@@ -1080,12 +1081,38 @@
return BLK_STS_OK;
}
+/**
+ * sd_group_number() - Compute the GROUP NUMBER field
+ * @cmd: SCSI command for which to compute the value of the six-bit GROUP NUMBER
+ * field.
+ *
+ * From SBC-5 r05 (https://www.t10.org/cgi-bin/ac.pl?t=f&f=sbc5r05.pdf):
+ * 0: no relative lifetime.
+ * 1: shortest relative lifetime.
+ * 2: second shortest relative lifetime.
+ * 3 - 0x3d: intermediate relative lifetimes.
+ * 0x3e: second longest relative lifetime.
+ * 0x3f: longest relative lifetime.
+ */
+static u8 sd_group_number(struct scsi_cmnd *cmd)
+{
+ const struct request *rq = scsi_cmd_to_rq(cmd);
+ struct scsi_disk *sdkp = scsi_disk(rq->q->disk);
+
+ if (!sdkp->rscs)
+ return 0;
+
+ return min3((u32)rq->write_hint, (u32)sdkp->permanent_stream_count,
+ 0x3fu);
+}
+
static blk_status_t sd_setup_rw32_cmnd(struct scsi_cmnd *cmd, bool write,
sector_t lba, unsigned int nr_blocks,
unsigned char flags, unsigned int dld)
{
cmd->cmd_len = SD_EXT_CDB_SIZE;
cmd->cmnd[0] = VARIABLE_LENGTH_CMD;
+ cmd->cmnd[6] = sd_group_number(cmd);
cmd->cmnd[7] = 0x18; /* Additional CDB len */
cmd->cmnd[9] = write ? WRITE_32 : READ_32;
cmd->cmnd[10] = flags;
@@ -1104,7 +1131,7 @@
cmd->cmd_len = 16;
cmd->cmnd[0] = write ? WRITE_16 : READ_16;
cmd->cmnd[1] = flags | ((dld >> 2) & 0x01);
- cmd->cmnd[14] = (dld & 0x03) << 6;
+ cmd->cmnd[14] = ((dld & 0x03) << 6) | sd_group_number(cmd);
cmd->cmnd[15] = 0;
put_unaligned_be64(lba, &cmd->cmnd[2]);
put_unaligned_be32(nr_blocks, &cmd->cmnd[10]);
@@ -1119,7 +1146,7 @@
cmd->cmd_len = 10;
cmd->cmnd[0] = write ? WRITE_10 : READ_10;
cmd->cmnd[1] = flags;
- cmd->cmnd[6] = 0;
+ cmd->cmnd[6] = sd_group_number(cmd);
cmd->cmnd[9] = 0;
put_unaligned_be32(lba, &cmd->cmnd[2]);
put_unaligned_be16(nr_blocks, &cmd->cmnd[7]);
@@ -1256,7 +1283,7 @@
ret = sd_setup_rw16_cmnd(cmd, write, lba, nr_blocks,
protect | fua, dld);
} else if ((nr_blocks > 0xff) || (lba > 0x1fffff) ||
- sdp->use_10_for_rw || protect) {
+ sdp->use_10_for_rw || protect || rq->write_hint) {
ret = sd_setup_rw10_cmnd(cmd, write, lba, nr_blocks,
protect | fua);
} else {
@@ -3059,6 +3086,70 @@
sdkp->DPOFUA = 0;
}
+static bool sd_is_perm_stream(struct scsi_disk *sdkp, unsigned int stream_id)
+{
+ u8 cdb[16] = { SERVICE_ACTION_IN_16, SAI_GET_STREAM_STATUS };
+ struct {
+ struct scsi_stream_status_header h;
+ struct scsi_stream_status s;
+ } buf;
+ struct scsi_device *sdev = sdkp->device;
+ struct scsi_sense_hdr sshdr;
+ const struct scsi_exec_args exec_args = {
+ .sshdr = &sshdr,
+ };
+ int res;
+
+ put_unaligned_be16(stream_id, &cdb[4]);
+ put_unaligned_be32(sizeof(buf), &cdb[10]);
+
+ res = scsi_execute_cmd(sdev, cdb, REQ_OP_DRV_IN, &buf, sizeof(buf),
+ SD_TIMEOUT, sdkp->max_retries, &exec_args);
+ if (res < 0)
+ return false;
+ if (scsi_status_is_check_condition(res) && scsi_sense_valid(&sshdr))
+ sd_print_sense_hdr(sdkp, &sshdr);
+ if (res)
+ return false;
+ if (get_unaligned_be32(&buf.h.len) < sizeof(struct scsi_stream_status))
+ return false;
+ return buf.h.stream_status[0].perm;
+}
+
+static void sd_read_io_hints(struct scsi_disk *sdkp, unsigned char *buffer)
+{
+ struct scsi_device *sdp = sdkp->device;
+ const struct scsi_io_group_descriptor *desc, *start, *end;
+ struct scsi_sense_hdr sshdr;
+ struct scsi_mode_data data;
+ int res;
+
+ res = scsi_mode_sense(sdp, /*dbd=*/0x8, /*modepage=*/0x0a,
+ /*subpage=*/0x05, buffer, SD_BUF_SIZE, SD_TIMEOUT,
+ sdkp->max_retries, &data, &sshdr);
+ if (res < 0)
+ return;
+ start = (void *)buffer + data.header_length + 16;
+ end = (void *)buffer + ALIGN_DOWN(data.header_length + data.length,
+ sizeof(*end));
+ /*
+ * From "SBC-5 Constrained Streams with Data Lifetimes": Device severs
+ * should assign the lowest numbered stream identifiers to permanent
+ * streams.
+ */
+ for (desc = start; desc < end; desc++)
+ if (!desc->st_enble || !sd_is_perm_stream(sdkp, desc - start))
+ break;
+ sdkp->permanent_stream_count = desc - start;
+ if (sdkp->rscs && sdkp->permanent_stream_count < 2)
+ sd_printk(KERN_INFO, sdkp,
+ "Unexpected: RSCS has been set and the permanent stream count is %u\n",
+ sdkp->permanent_stream_count);
+ else if (sdkp->permanent_stream_count)
+ sd_printk(KERN_INFO, sdkp, "permanent stream count = %d\n",
+ sdkp->permanent_stream_count);
+}
+
/*
* The ATO bit indicates whether the DIF application tag is available
* for use by the operating system.
@@ -3166,6 +3257,18 @@
rcu_read_unlock();
}
+/* Parse the Block Limits Extension VPD page (0xb7) */
+static void sd_read_block_limits_ext(struct scsi_disk *sdkp)
+{
+ struct scsi_vpd *vpd;
+
+ rcu_read_lock();
+ vpd = rcu_dereference(sdkp->device->vpd_pgb7);
+ if (vpd && vpd->len >= 2)
+ sdkp->rscs = vpd->data[5] & 1;
+ rcu_read_unlock();
+}
+
/**
* sd_read_block_characteristics - Query block dev. characteristics
* @sdkp: disk to query
@@ -3541,6 +3644,7 @@
if (scsi_device_supports_vpd(sdp)) {
sd_read_block_provisioning(sdkp);
sd_read_block_limits(sdkp);
+ sd_read_block_limits_ext(sdkp);
sd_read_block_characteristics(sdkp);
sd_zbc_read_zones(sdkp, buffer);
sd_read_cpr(sdkp);
@@ -3550,6 +3654,7 @@
sd_read_write_protect_flag(sdkp, buffer);
sd_read_cache_type(sdkp, buffer);
+ sd_read_io_hints(sdkp, buffer);
sd_read_app_tag_own(sdkp, buffer);
sd_read_write_same(sdkp, buffer);
sd_read_security(sdkp, buffer);
diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index 409dda5..5c4285a 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -125,6 +125,8 @@
unsigned int physical_block_size;
unsigned int max_medium_access_timeouts;
unsigned int medium_access_timed_out;
+ /* number of permanent streams */
+ u16 permanent_stream_count;
u8 media_present;
u8 write_prot;
u8 protection_type;/* Data Integrity Field */
@@ -151,6 +153,7 @@
unsigned urswrz : 1;
unsigned security : 1;
unsigned ignore_medium_access_errors : 1;
+ unsigned rscs : 1; /* reduced stream control support */
};
#define to_scsi_disk(obj) container_of(obj, struct scsi_disk, disk_dev)
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index fddc767..9c540f5 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -149,6 +149,7 @@
struct scsi_vpd __rcu *vpd_pgb0;
struct scsi_vpd __rcu *vpd_pgb1;
struct scsi_vpd __rcu *vpd_pgb2;
+ struct scsi_vpd __rcu *vpd_pgb7;
struct scsi_target *sdev_target;
diff --git a/include/scsi/scsi_proto.h b/include/scsi/scsi_proto.h
index 07d65c1..843106e 100644
--- a/include/scsi/scsi_proto.h
+++ b/include/scsi/scsi_proto.h
@@ -10,6 +10,7 @@
#ifndef _SCSI_PROTO_H_
#define _SCSI_PROTO_H_
+#include <linux/build_bug.h>
#include <linux/types.h>
/*
@@ -126,6 +127,7 @@
#define SAI_READ_CAPACITY_16 0x10
#define SAI_GET_LBA_STATUS 0x12
#define SAI_REPORT_REFERRALS 0x13
+#define SAI_GET_STREAM_STATUS 0x16
/* values for maintenance in */
#define MI_REPORT_IDENTIFYING_INFORMATION 0x05
#define MI_REPORT_TARGET_PGS 0x0a
@@ -275,6 +277,82 @@
__u8 scsi_lun[8];
};
+/* SBC-5 IO advice hints group descriptor */
+struct scsi_io_group_descriptor {
+#if defined(__BIG_ENDIAN)
+ u8 io_advice_hints_mode: 2;
+ u8 reserved1: 3;
+ u8 st_enble: 1;
+ u8 cs_enble: 1;
+ u8 ic_enable: 1;
+#elif defined(__LITTLE_ENDIAN)
+ u8 ic_enable: 1;
+ u8 cs_enble: 1;
+ u8 st_enble: 1;
+ u8 reserved1: 3;
+ u8 io_advice_hints_mode: 2;
+#else
+#error
+#endif
+ u8 reserved2[3];
+ /* Logical block markup descriptor */
+#if defined(__BIG_ENDIAN)
+ u8 acdlu: 1;
+ u8 reserved3: 1;
+ u8 rlbsr: 2;
+ u8 lbm_descriptor_type: 4;
+#elif defined(__LITTLE_ENDIAN)
+ u8 lbm_descriptor_type: 4;
+ u8 rlbsr: 2;
+ u8 reserved3: 1;
+ u8 acdlu: 1;
+#else
+#error
+#endif
+ u8 params[2];
+ u8 reserved4;
+ u8 reserved5[8];
+};
+
+static_assert(sizeof(struct scsi_io_group_descriptor) == 16);
+
+/* SCSI stream status descriptor */
+struct scsi_stream_status {
+#if defined(__BIG_ENDIAN)
+ u8 perm: 1;
+ u8 reserved1: 7;
+#elif defined(__LITTLE_ENDIAN)
+ u8 reserved1: 7;
+ u8 perm: 1;
+#else
+#error
+#endif
+ u8 reserved2;
+ __be16 stream_identifier;
+#if defined(__BIG_ENDIAN)
+ u8 reserved3: 2;
+ u8 rel_lifetime: 6;
+#elif defined(__LITTLE_ENDIAN)
+ u8 rel_lifetime: 6;
+ u8 reserved3: 2;
+#else
+#error
+#endif
+ u8 reserved4[3];
+};
+
+static_assert(sizeof(struct scsi_stream_status) == 8);
+
+/* GET STREAM STATUS parameter data */
+struct scsi_stream_status_header {
+ __be32 len; /* length in bytes of stream_status[] array. */
+ u16 reserved;
+ __be16 number_of_open_streams;
+ DECLARE_FLEX_ARRAY(struct scsi_stream_status, stream_status);
+};
+
+static_assert(sizeof(struct scsi_stream_status_header) == 8);
+
/* SPC asymmetric access states */
#define SCSI_ACCESS_STATE_OPTIMAL 0x00
#define SCSI_ACCESS_STATE_ACTIVE 0x01
