Merge patch series "smartpqi updates"

Don Brace <[email protected]> says:

These patches are based on Martin Petersen's 6.12/scsi-queue tree
  https://git.kernel.org/pub/scm/linux/kernel/git/mkp/scsi.git
  6.12/scsi-queue

There are two functional changes:
    smartpqi-add-fw-log-to-kdump
    smartpqi-add-counter-for-parity-write-stream-requests

There are three minor bug fixes:
    smartpqi-fix-stream-detection
    smartpqi-fix-rare-system-hang-during-LUN-reset
    smartpqi-fix-volume-size-updates

The other two patches add PCI-IDs for new controllers and change the
driver version.

This set of changes consists of:
* smartpqi-add-fw-log-to-kdump

  During a kdump, the driver tells the controller to copy its logging
  information to some pre-allocated buffers that can be analyzed
  later.

  This is a "feature" driven capability and is backward compatible
  with existing controller FW.

  This patch renames some prefixes for OFA (Online-Firmware Activation
  ofa_*) buffers to host_memory_*. So, not a lot of actual functional
  changes to smartpqi_init.c, mainly determining the memory size
  allocation.

  We added a function to notify the controller to copy debug data into
  host memory before continuing kdump.

  Most of the functional changes are in smartpqi_sis.c where the
  actual handshaking is done.

* smartpqi-fix-stream-detection

  Correct some false write-stream detections. The data structure used
  to check for write-streams was not initialized to all 0's causing
  some false write stream detections. The driver sends down streamed
  requests to the raid engine instead of using AIO bypass for some
  extra performance.  (Potential full-stripe write verses Read Modify
  Write).

  False detections have not caused any data corruption.  Found by
  internal testing. No known externally reported bugs.

* smartpqi-add-counter-for-parity-write-stream-requests

  Adding some counters for raid_bypass and write streams. These two
  counters are related because write stream detection is only checked
  if an I/O request is eligible for bypass (AIO).

  The bypass counter (raid_bypass_cnt) was moved into a common
  structure (pqi_raid_io_stats) and changed to type __percpu. The
  write stream counter is (write_stream_cnt) has been added to this
  same structure.

  These counters are __percpu counters for performance. We added a
  sysfs entry to show the write stream count. The raid bypass counter
  sysfs entry already exists.

  Useful for checking streaming writes. The change in the sysfs entry
  write_stream_cnt can be checked during AIO eligible write
  operations.

* smartpqi-add-new-controller-PCI-IDs

  Adding support for new controller HW.  No functional changes.

* smartpqi-fix-rare-system-hang-during-LUN-reset

  We found a rare race condition that can occur during a LUN reset. We
  were not emptying our internal queue completely.

  There have been some rare conditions where our internal request
  queue has requests for multiple LUNs and a reset comes in for one of
  the LUNs. The driver waits for this internal queue to empty. We were
  only clearing out the requests for the LUN being reset so the
  request queue was never empty causing a hang.

  The Fix:

     For all requests in our internal request queue:

        Complete requests with DID_RESET for queued requests for the
        device undergoing a reset.

        Complete requests with DID_REQUEUE for all other queued requests.

  Found by internal testing. No known externally reported bugs.

* smartpqi-fix-volume-size-updates

  The current code only checks for a size change if there is also a
  queue depth change.  We are separating the check for queue depth and
  the size changes.

  Found by internal testing. No known bugs were filed.

* smartpqi-update-version-to-2.1.30-031
  No functional changes.

Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Martin K. Petersen <[email protected]>

Author: martinkpetersen

drivers/scsi/smartpqi/smartpqi.h

@@ -505,7 +505,7 @@ struct pqi_vendor_general_request {
 			__le64	buffer_address;
 			__le32	buffer_length;
 			u8	reserved[40];
-		} ofa_memory_allocation;
+		} host_memory_allocation;
 	} data;
 };
 
@@ -517,21 +517,30 @@ struct pqi_vendor_general_response {
 	u8	reserved[2];
 };
 
-#define PQI_VENDOR_GENERAL_CONFIG_TABLE_UPDATE	0
-#define PQI_VENDOR_GENERAL_HOST_MEMORY_UPDATE	1
+#define PQI_VENDOR_GENERAL_CONFIG_TABLE_UPDATE		0
+#define PQI_VENDOR_GENERAL_OFA_MEMORY_UPDATE		1
+#define PQI_VENDOR_GENERAL_CTRL_LOG_MEMORY_UPDATE	2
 
 #define PQI_OFA_VERSION			1
 #define PQI_OFA_SIGNATURE		"OFA_QRM"
-#define PQI_OFA_MAX_SG_DESCRIPTORS	64
+#define PQI_CTRL_LOG_VERSION		1
+#define PQI_CTRL_LOG_SIGNATURE		"FW_DATA"
+#define PQI_HOST_MAX_SG_DESCRIPTORS	64
 
-struct pqi_ofa_memory {
-	__le64	signature;	/* "OFA_QRM" */
+struct pqi_host_memory {
+	__le64	signature;	/* "OFA_QRM", "FW_DATA", etc. */
 	__le16	version;	/* version of this struct (1 = 1st version) */
 	u8	reserved[62];
 	__le32	bytes_allocated;	/* total allocated memory in bytes */
 	__le16	num_memory_descriptors;
 	u8	reserved1[2];
-	struct pqi_sg_descriptor sg_descriptor[PQI_OFA_MAX_SG_DESCRIPTORS];
+	struct pqi_sg_descriptor sg_descriptor[PQI_HOST_MAX_SG_DESCRIPTORS];
+};
+
+struct pqi_host_memory_descriptor {
+	struct pqi_host_memory *host_memory;
+	dma_addr_t		host_memory_dma_handle;
+	void			**host_chunk_virt_address;
 };
 
 struct pqi_aio_error_info {
@@ -867,7 +876,8 @@ struct pqi_config_table_firmware_features {
 #define PQI_FIRMWARE_FEATURE_FW_TRIAGE				17
 #define PQI_FIRMWARE_FEATURE_RPL_EXTENDED_FORMAT_4_5		18
 #define PQI_FIRMWARE_FEATURE_MULTI_LUN_DEVICE_SUPPORT           21
-#define PQI_FIRMWARE_FEATURE_MAXIMUM                            21
+#define PQI_FIRMWARE_FEATURE_CTRL_LOGGING			22
+#define PQI_FIRMWARE_FEATURE_MAXIMUM				22
 
 struct pqi_config_table_debug {
 	struct pqi_config_table_section_header header;
@@ -1096,6 +1106,11 @@ struct pqi_tmf_work {
 	u8	scsi_opcode;
 };
 
+struct pqi_raid_io_stats {
+	u64	raid_bypass_cnt;
+	u64	write_stream_cnt;
+};
+
 struct pqi_scsi_dev {
 	int	devtype;		/* as reported by INQUIRY command */
 	u8	device_type;		/* as reported by */
@@ -1158,7 +1173,7 @@ struct pqi_scsi_dev {
 
 	struct pqi_stream_data stream_data[NUM_STREAMS_PER_LUN];
 	atomic_t scsi_cmds_outstanding[PQI_MAX_LUNS_PER_DEVICE];
-	u64 __percpu *raid_bypass_cnt;
+	struct pqi_raid_io_stats __percpu *raid_io_stats;
 
 	struct pqi_tmf_work tmf_work[PQI_MAX_LUNS_PER_DEVICE];
 };
@@ -1357,6 +1372,7 @@ struct pqi_ctrl_info {
 	u8		firmware_triage_supported : 1;
 	u8		rpl_extended_format_4_5_supported : 1;
 	u8		multi_lun_device_supported : 1;
+	u8		ctrl_logging_supported : 1;
 	u8		enable_r1_writes : 1;
 	u8		enable_r5_writes : 1;
 	u8		enable_r6_writes : 1;
@@ -1398,13 +1414,12 @@ struct pqi_ctrl_info {
 	wait_queue_head_t block_requests_wait;
 
 	struct mutex	ofa_mutex;
-	struct pqi_ofa_memory *pqi_ofa_mem_virt_addr;
-	dma_addr_t	pqi_ofa_mem_dma_handle;
-	void		**pqi_ofa_chunk_virt_addr;
 	struct work_struct ofa_memory_alloc_work;
 	struct work_struct ofa_quiesce_work;
 	u32		ofa_bytes_requested;
 	u16		ofa_cancel_reason;
+	struct pqi_host_memory_descriptor ofa_memory;
+	struct pqi_host_memory_descriptor ctrl_log_memory;
 	enum pqi_ctrl_removal_state ctrl_removal_state;
 };