megaraid_sas : MFI MPT linked list corruption fix

Resending the patch. Addressed the review comments from Tomas Henzl.
Added comment for to-do work.

Problem statement:
MFI link list in megaraid_sas driver is used from mfi-mpt pass-through commands.
This list can be corrupted due to many possible race conditions in driver and
eventually we may see kernel panic.

One example -
MFI frame is freed from calling process as driver send command via polling method and interrupt
for that command comes after driver free mfi frame (actually even after some other context reuse
the mfi frame). When driver receive MPT frame in ISR, driver will be using the index of MFI and
access that MFI frame and finally in-used MFI frame’s list will be corrupted.

High level description of new solution -
Free MFI and MPT command from same context.
Free both the command either from process (from where mfi-mpt pass-through was called) or from
ISR context. Do not split freeing of MFI and MPT, because it creates the race condition which
will do MFI/MPT list corruption.

Renamed the cmd_pool_lock which is used in instance as well as fusion with below name.
mfi_pool_lock and mpt_pool_lock to add more code readability.

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, 23 insertions, 2 deletions

diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h
index 156d4b97d2bd..f99db18c809c 100644
--- a/drivers/scsi/megaraid/megaraid_sas.h
+++ b/drivers/scsi/megaraid/megaraid_sas.h
@@ -1016,6 +1016,12 @@ struct megasas_ctrl_info {
 
 #define VD_EXT_DEBUG 0
 
+enum MR_MFI_MPT_PTHR_FLAGS {
+	MFI_MPT_DETACHED = 0,
+	MFI_LIST_ADDED = 1,
+	MFI_MPT_ATTACHED = 2,
+};
+
 /* Frame Type */
 #define IO_FRAME				0
 #define PTHRU_FRAME				1
@@ -1033,7 +1039,7 @@ struct megasas_ctrl_info {
 #define MEGASAS_IOCTL_CMD			0
 #define MEGASAS_DEFAULT_CMD_TIMEOUT		90
 #define MEGASAS_THROTTLE_QUEUE_DEPTH		16
-
+#define MEGASAS_BLOCKED_CMD_TIMEOUT		60
 /*
  * FW reports the maximum of number of commands that it can accept (maximum
  * commands that can be outstanding) at any time. The driver must report a
@@ -1652,7 +1658,7 @@ struct megasas_instance {
 	struct megasas_cmd **cmd_list;
 	struct list_head cmd_pool;
 	/* used to sync fire the cmd to fw */
-	spinlock_t cmd_pool_lock;
+	spinlock_t mfi_pool_lock;
 	/* used to sync fire the cmd to fw */
 	spinlock_t hba_lock;
 	/* used to synch producer, consumer ptrs in dpc */
@@ -1839,6 +1845,11 @@ struct megasas_cmd {
 
 	struct list_head list;
 	struct scsi_cmnd *scmd;
+
+	void *mpt_pthr_cmd_blocked;
+	atomic_t mfi_mpt_pthr;
+	u8 is_wait_event;
+
 	struct megasas_instance *instance;
 	union {
 		struct {
@@ -1927,4 +1938,14 @@ int megasas_set_crash_dump_params(struct megasas_instance *instance,
 void megasas_free_host_crash_buffer(struct megasas_instance *instance);
 void megasas_fusion_crash_dump_wq(struct work_struct *work);
 
+void megasas_return_cmd_fusion(struct megasas_instance *instance,
+	struct megasas_cmd_fusion *cmd);
+int megasas_issue_blocked_cmd(struct megasas_instance *instance,
+	struct megasas_cmd *cmd, int timeout);
+void __megasas_return_cmd(struct megasas_instance *instance,
+	struct megasas_cmd *cmd);
+
+void megasas_return_mfi_mpt_pthr(struct megasas_instance *instance,
+	struct megasas_cmd *cmd_mfi, struct megasas_cmd_fusion *cmd_fusion);
+
 #endif				/*LSI_MEGARAID_SAS_H */