scsi: target: Make state_list per CPU

[ Upstream commit 1526d9f10c6184031e42afad0adbdde1213e8ad1 ]

Do a state_list/execute_task_lock per CPU, so we can do submissions from
different CPUs without contention with each other.

Note: tcm_fc was passing TARGET_SCF_USE_CPUID, but never set cpuid.  The
assumption is that it wanted to set the cpuid to the CPU it was submitting
from so it will get this behavior with this patch.

[mkp: s/printk/pr_err/ + resolve COMPARE AND WRITE patch conflict]

Link: https://lore.kernel.org/r/1604257174-4524-8-git-send-email-michael.christie@oracle.com
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Mike Christie <michael.christie@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Stable-dep-of: 673db054d7a2 ("scsi: target: Fix multiple LUN_RESET handling")
Signed-off-by: Sasha Levin <sashal@kernel.org>

include/target/target_core_base.h

@@ -541,6 +541,10 @@ struct se_cmd {
 	unsigned int		t_prot_nents;
 	sense_reason_t		pi_err;
 	u64			sense_info;
+	/*
+	 * CPU LIO will execute the cmd on. Defaults to the CPU the cmd is
+	 * initialized on. Drivers can override.
+	 */
 	int			cpuid;
 };
 
@@ -761,6 +765,11 @@ struct se_dev_stat_grps {
 	struct config_group scsi_lu_group;
 };
 
+struct se_device_queue {
+	struct list_head	state_list;
+	spinlock_t		lock;
+};
+
 struct se_device {
 	/* RELATIVE TARGET PORT IDENTIFER Counter */
 	u16			dev_rpti_counter;
@@ -794,7 +803,6 @@ struct se_device {
 	atomic_t		dev_qf_count;
 	u32			export_count;
 	spinlock_t		delayed_cmd_lock;
-	spinlock_t		execute_task_lock;
 	spinlock_t		dev_reservation_lock;
 	unsigned int		dev_reservation_flags;
 #define DRF_SPC2_RESERVATIONS			0x00000001
@@ -814,7 +822,6 @@ struct se_device {
 	struct work_struct	qf_work_queue;
 	struct work_struct	delayed_cmd_work;
 	struct list_head	delayed_cmd_list;
-	struct list_head	state_list;
 	struct list_head	qf_cmd_list;
 	/* Pointer to associated SE HBA */
 	struct se_hba		*se_hba;
@@ -841,6 +848,8 @@ struct se_device {
 	/* For se_lun->lun_se_dev RCU read-side critical access */
 	u32			hba_index;
 	struct rcu_head		rcu_head;
+	int			queue_cnt;
+	struct se_device_queue	*queues;
 };
 
 struct se_hba {