powerpc/papr_scm: Implement initial support for injecting smart errors

Presently PAPR doesn't support injecting smart errors on an
NVDIMM. This makes testing the NVDIMM health reporting functionality
difficult as simulating NVDIMM health related events need a hacked up
qemu version.

To solve this problem this patch proposes simulating certain set of
NVDIMM health related events in papr_scm. Specifically 'fatal' health
state and 'dirty' shutdown state. These error can be injected via the
user-space 'ndctl-inject-smart(1)' command. With the proposed patch and
corresponding ndctl patches following command flow is expected:

$ sudo ndctl list -DH -d nmem0
...
      "health_state":"ok",
      "shutdown_state":"clean",
...
 # inject unsafe shutdown and fatal health error
$ sudo ndctl inject-smart nmem0 -Uf
...
      "health_state":"fatal",
      "shutdown_state":"dirty",
...
 # uninject all errors
$ sudo ndctl inject-smart nmem0 -N
...
      "health_state":"ok",
      "shutdown_state":"clean",
...

The patch adds a new member 'health_bitmap_inject_mask' inside struct
papr_scm_priv which is then bitwise ANDed to the health bitmap fetched from the
hypervisor. The value for 'health_bitmap_inject_mask' is accessible from sysfs
at nmemX/papr/health_bitmap_inject.

A new PDSM named 'SMART_INJECT' is proposed that accepts newly
introduced 'struct nd_papr_pdsm_smart_inject' as payload thats
exchanged between libndctl and papr_scm to indicate the requested
smart-error states.

When the processing the PDSM 'SMART_INJECT', papr_pdsm_smart_inject()
constructs a pair or 'inject_mask' and 'clear_mask' bitmaps from the payload
and bit-blt it to the 'health_bitmap_inject_mask'. This ensures the after being
fetched from the hypervisor, the health_bitmap reflects requested smart-error
states.

Signed-off-by: Vaibhav Jain <vaibhav@linux.ibm.com>
Signed-off-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220124202204.1488346-1-vaibhav@linux.ibm.com

1 files changed, 18 insertions, 0 deletions

diff --git a/arch/powerpc/include/uapi/asm/papr_pdsm.h b/arch/powerpc/include/uapi/asm/papr_pdsm.h
index 82488b1e7276..17439925045c 100644
--- a/arch/powerpc/include/uapi/asm/papr_pdsm.h
+++ b/arch/powerpc/include/uapi/asm/papr_pdsm.h
@@ -116,6 +116,22 @@ struct nd_papr_pdsm_health {
 	};
 };
 
+/* 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];
+	};
+};
+
 /*
  * Methods to be embedded in ND_CMD_CALL request. These are sent to the kernel
  * via 'nd_cmd_pkg.nd_command' member of the ioctl struct
@@ -123,12 +139,14 @@ struct nd_papr_pdsm_health {
 enum papr_pdsm {
 	PAPR_PDSM_MIN = 0x0,
 	PAPR_PDSM_HEALTH,
+	PAPR_PDSM_SMART_INJECT,
 	PAPR_PDSM_MAX,
 };
 
 /* 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 smart_inject;
 	__u8 buf[ND_PDSM_PAYLOAD_MAX_SIZE];
 } __packed;