megaraid_sas : Firmware crash dump feature support

Resending the patch. Addressed the review comments from Tomas Henzl.
Move buff_offset inside spinlock, corrected loop at crash dump buffer free,
reset_devices check is added to disable fw crash dump feature in kdump kernel.

This feature will provide similar interface as kernel crash dump feature.
When megaraid firmware encounter any crash, driver will collect the firmware raw image and
dump it into pre-configured location.

Driver will allocate two different segment of memory.
#1 Non-DMA able large buffer (will be allocated on demand) to capture actual FW crash dump.
#2 DMA buffer (persistence allocation) just to do a arbitrator job.

Firmware will keep writing Crash dump data in chucks of DMA buffer size into #2,
which will be copy back by driver to the host memory as described in #1.

Driver-Firmware interface:
==================
A.) Host driver can allocate maximum 512MB Host memory to store crash dump data.

This memory will be internal to the host and will not be exposed to the Firmware.
Driver may not be able to allocate 512 MB. In that case, driver will do possible memory
(available at run time) allocation to store crash dump data.

Let’s call this buffer as Host Crash Buffer.

Host Crash buffer will not be contigious as a whole, but it will have multiple chunk of contigious memory.
This will be internal to driver and firmware/application are unaware of it.
Partial allocation of Host Crash buffer may have valid information to debug depending upon
what was collected in that buffer and depending on nature of failure.

Complete Crash dump is the best case, but we do want to capture partial buffer just to grab something rather than nothing.
Host Crash buffer will be allocated only when FW Crash dump data is available,
and will be deallocated once application copy Host Crash buffer to the file.
Host Crash buffer size can be anything between 1MB to 512MB. (It will be multiple of 1MBs)

B.) Irrespective of underlying Firmware capability of crash dump support,
driver will allocate DMA buffer at start of the day for each MR controllers.
Let’s call this buffer as “DMA Crash Buffer”.

For this feature, size of DMA crash buffer will be 1MB.
(We will not gain much even if DMA buffer size is increased.)

C.) Driver will now read Controller Info sending existing dcmd “MR_DCMD_CTRL_GET_INFO”.
Driver should extract the information from ctrl info provided by firmware and
figure out if firmware support crash dump feature or not.

Driver will enable crash dump feature only if
“Firmware support Crash dump” +
“Driver was able to create DMA Crash Buffer”.

If either one from above is not set, Crash dump feature should be disable in driver.
Firmware will enable crash dump feature only if “Driver Send DCMD- MR_DCMD_SET_CRASH_BUF_PARA with MR_CRASH_BUF_TURN_ON”

Helper application/script should use sysfs parameter fw_crash_xxx to actually copy data from
host memory to the filesystem.

Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

1 files changed, 57 insertions, 1 deletions

diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h
index bc7adcf537f2..e0f03e2f6ddf 100644
--- a/drivers/scsi/megaraid/megaraid_sas.h
+++ b/drivers/scsi/megaraid/megaraid_sas.h
@@ -105,6 +105,9 @@
 #define MFI_STATE_READY				0xB0000000
 #define MFI_STATE_OPERATIONAL			0xC0000000
 #define MFI_STATE_FAULT				0xF0000000
+#define MFI_STATE_FORCE_OCR			0x00000080
+#define MFI_STATE_DMADONE			0x00000008
+#define MFI_STATE_CRASH_DUMP_DONE		0x00000004
 #define MFI_RESET_REQUIRED			0x00000001
 #define MFI_RESET_ADAPTER			0x00000002
 #define MEGAMFI_FRAME_SIZE			64
@@ -191,6 +194,9 @@
 #define MR_DCMD_CLUSTER_RESET_LD		0x08010200
 #define MR_DCMD_PD_LIST_QUERY                   0x02010100
 
+#define MR_DCMD_CTRL_SET_CRASH_DUMP_PARAMS	0x01190100
+#define MR_DRIVER_SET_APP_CRASHDUMP_MODE	(0xF0010000 | 0x0600)
+
 /*
  * Global functions
  */
@@ -264,6 +270,25 @@ enum MFI_STAT {
 };
 
 /*
+ * Crash dump related defines
+ */
+#define MAX_CRASH_DUMP_SIZE 512
+#define CRASH_DMA_BUF_SIZE  (1024 * 1024)
+
+enum MR_FW_CRASH_DUMP_STATE {
+	UNAVAILABLE = 0,
+	AVAILABLE = 1,
+	COPYING = 2,
+	COPIED = 3,
+	COPY_ERROR = 4,
+};
+
+enum _MR_CRASH_BUF_STATUS {
+	MR_CRASH_BUF_TURN_OFF = 0,
+	MR_CRASH_BUF_TURN_ON = 1,
+};
+
+/*
  * Number of mailbox bytes in DCMD message frame
  */
 #define MFI_MBOX_SIZE				12
@@ -933,7 +958,19 @@ struct megasas_ctrl_info {
 		u8  reserved;                   /*0x7E7*/
 	} iov;
 
-	u8          pad[0x800-0x7E8];           /*0x7E8 pad to 2k */
+	struct {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u32     reserved:25;
+		u32     supportCrashDump:1;
+		u32     reserved1:6;
+#else
+		u32     reserved1:6;
+		u32     supportCrashDump:1;
+		u32     reserved:25;
+#endif
+	} adapterOperations3;
+
+	u8          pad[0x800-0x7EC];
 } __packed;
 
 /*
@@ -1559,6 +1596,20 @@ struct megasas_instance {
 	u32 *reply_queue;
 	dma_addr_t reply_queue_h;
 
+	u32 *crash_dump_buf;
+	dma_addr_t crash_dump_h;
+	void *crash_buf[MAX_CRASH_DUMP_SIZE];
+	u32 crash_buf_pages;
+	unsigned int    fw_crash_buffer_size;
+	unsigned int    fw_crash_state;
+	unsigned int    fw_crash_buffer_offset;
+	u32 drv_buf_index;
+	u32 drv_buf_alloc;
+	u32 crash_dump_fw_support;
+	u32 crash_dump_drv_support;
+	u32 crash_dump_app_support;
+	spinlock_t crashdump_lock;
+
 	struct megasas_register_set __iomem *reg_set;
 	u32 *reply_post_host_index_addr[MR_MAX_MSIX_REG_ARRAY];
 	struct megasas_pd_list          pd_list[MEGASAS_MAX_PD];
@@ -1606,6 +1657,7 @@ struct megasas_instance {
 	struct megasas_instance_template *instancet;
 	struct tasklet_struct isr_tasklet;
 	struct work_struct work_init;
+	struct work_struct crash_init;
 
 	u8 flag;
 	u8 unload;
@@ -1830,4 +1882,8 @@ u16 MR_LdSpanArrayGet(u32 ld, u32 span, struct MR_FW_RAID_MAP_ALL *map);
 u16 MR_PdDevHandleGet(u32 pd, struct MR_FW_RAID_MAP_ALL *map);
 u16 MR_GetLDTgtId(u32 ld, struct MR_FW_RAID_MAP_ALL *map);
 
+int megasas_set_crash_dump_params(struct megasas_instance *instance,
+		u8 crash_buf_state);
+void megasas_free_host_crash_buffer(struct megasas_instance *instance);
+void megasas_fusion_crash_dump_wq(struct work_struct *work);
 #endif				/*LSI_MEGARAID_SAS_H */