ndctl/9ef460e-libndctl-papr-Add-limited-support-for-inject-smart.patch
2022-06-18 10:01:47 +00:00

180 lines
5.2 KiB
Diff

libndctl/papr: Add limited support for inject-smart
BZ:
Brew:
commit 9ef460eb7fd1b1f286955b18db8c18cd1a640e77
Author: Vaibhav Jain <vaibhav@linux.ibm.com>
Date: Tue Jan 25 02:08:04 2022 +0530
libndctl/papr: Add limited support for inject-smart
Implements support for ndctl inject-smart command by providing an
implementation of 'smart_inject*' dimm-ops callbacks. Presently only
support for injecting unsafe-shutdown and fatal-health states is
available.
The patch also introduce various PAPR PDSM structures that are used to
communicate the inject-smart errors to the papr_scm kernel
module. This is done via SMART_INJECT PDSM which sends a payload of
type 'struct nd_papr_pdsm_smart_inject'.
With the patch following output from ndctl inject-smart command is
expected for PAPR NVDIMMs:
$ sudo ndctl inject-smart -fU nmem0
[
{
"dev":"nmem0",
"flag_failed_flush":true,
"flag_smart_event":true,
"health":{
"health_state":"fatal",
"shutdown_state":"dirty",
"shutdown_count":0
}
}
]
$ sudo ndctl inject-smart -N nmem0
[
{
"dev":"nmem0",
"health":{
"health_state":"ok",
"shutdown_state":"clean",
"shutdown_count":0
}
}
]
The patch depends on the kernel PAPR PDSM implementation for
PDSM_SMART_INJECT posted at [1].
[1] : https://lore.kernel.org/nvdimm/20220124202204.1488346-1-vaibhav@linux.ibm.com/
Link: https://lore.kernel.org/r/20220124203804.1490254-1-vaibhav@linux.ibm.com
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Signed-off-by: Vaibhav Jain <vaibhav@linux.ibm.com>
Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
diff --git a/ndctl/lib/papr.c b/ndctl/lib/papr.c
index 46cf9c1..7a1d559 100644
--- a/ndctl/lib/papr.c
+++ b/ndctl/lib/papr.c
@@ -221,6 +221,41 @@ static unsigned int papr_smart_get_shutdown_state(struct ndctl_cmd *cmd)
return health.dimm_bad_shutdown;
}
+static int papr_smart_inject_supported(struct ndctl_dimm *dimm)
+{
+ if (!ndctl_dimm_is_cmd_supported(dimm, ND_CMD_CALL))
+ return -EOPNOTSUPP;
+
+ if (!test_dimm_dsm(dimm, PAPR_PDSM_SMART_INJECT))
+ return -EIO;
+
+ return ND_SMART_INJECT_HEALTH_STATE | ND_SMART_INJECT_UNCLEAN_SHUTDOWN;
+}
+
+static int papr_smart_inject_valid(struct ndctl_cmd *cmd)
+{
+ if (cmd->type != ND_CMD_CALL ||
+ to_pdsm(cmd)->cmd_status != 0 ||
+ to_pdsm_cmd(cmd) != PAPR_PDSM_SMART_INJECT)
+ return -EINVAL;
+
+ return 0;
+}
+
+static struct ndctl_cmd *papr_new_smart_inject(struct ndctl_dimm *dimm)
+{
+ struct ndctl_cmd *cmd;
+
+ cmd = allocate_cmd(dimm, PAPR_PDSM_SMART_INJECT,
+ sizeof(struct nd_papr_pdsm_smart_inject));
+ if (!cmd)
+ return NULL;
+ /* Set the input payload size */
+ to_ndcmd(cmd)->nd_size_in = ND_PDSM_HDR_SIZE +
+ sizeof(struct nd_papr_pdsm_smart_inject);
+ return cmd;
+}
+
static unsigned int papr_smart_get_life_used(struct ndctl_cmd *cmd)
{
struct nd_papr_pdsm_health health;
@@ -255,11 +290,37 @@ static unsigned int papr_smart_get_shutdown_count(struct ndctl_cmd *cmd)
return (health.extension_flags & PDSM_DIMM_DSC_VALID) ?
(health.dimm_dsc) : 0;
+}
+
+static int papr_cmd_smart_inject_fatal(struct ndctl_cmd *cmd, bool enable)
+{
+ if (papr_smart_inject_valid(cmd) < 0)
+ return -EINVAL;
+
+ to_payload(cmd)->inject.flags |= PDSM_SMART_INJECT_HEALTH_FATAL;
+ to_payload(cmd)->inject.fatal_enable = enable;
+ return 0;
+}
+
+static int papr_cmd_smart_inject_unsafe_shutdown(struct ndctl_cmd *cmd,
+ bool enable)
+{
+ if (papr_smart_inject_valid(cmd) < 0)
+ return -EINVAL;
+
+ to_payload(cmd)->inject.flags |= PDSM_SMART_INJECT_BAD_SHUTDOWN;
+ to_payload(cmd)->inject.unsafe_shutdown_enable = enable;
+
+ return 0;
}
struct ndctl_dimm_ops * const papr_dimm_ops = &(struct ndctl_dimm_ops) {
.cmd_is_supported = papr_cmd_is_supported,
+ .new_smart_inject = papr_new_smart_inject,
+ .smart_inject_supported = papr_smart_inject_supported,
+ .smart_inject_fatal = papr_cmd_smart_inject_fatal,
+ .smart_inject_unsafe_shutdown = papr_cmd_smart_inject_unsafe_shutdown,
.smart_get_flags = papr_smart_get_flags,
.get_firmware_status = papr_get_firmware_status,
.xlat_firmware_status = papr_xlat_firmware_status,
diff --git a/ndctl/lib/papr_pdsm.h b/ndctl/lib/papr_pdsm.h
index f45b1e4..20ac20f 100644
--- a/ndctl/lib/papr_pdsm.h
+++ b/ndctl/lib/papr_pdsm.h
@@ -121,12 +121,29 @@ struct nd_papr_pdsm_health {
enum papr_pdsm {
PAPR_PDSM_MIN = 0x0,
PAPR_PDSM_HEALTH,
+ PAPR_PDSM_SMART_INJECT,
PAPR_PDSM_MAX,
};
+/* Flags for injecting specific smart errors */
+#define PDSM_SMART_INJECT_HEALTH_FATAL (1 << 0)
+#define PDSM_SMART_INJECT_BAD_SHUTDOWN (1 << 1)
+
+struct nd_papr_pdsm_smart_inject {
+ union {
+ struct {
+ /* One or more of PDSM_SMART_INJECT_ */
+ __u32 flags;
+ __u8 fatal_enable;
+ __u8 unsafe_shutdown_enable;
+ };
+ __u8 buf[ND_PDSM_PAYLOAD_MAX_SIZE];
+ };
+};
/* Maximal union that can hold all possible payload types */
union nd_pdsm_payload {
struct nd_papr_pdsm_health health;
+ struct nd_papr_pdsm_smart_inject inject;
__u8 buf[ND_PDSM_PAYLOAD_MAX_SIZE];
} __attribute__((packed));