Merge patch series "Optimize the hot path in the UFS driver"

Bart Van Assche <bvanassche@acm.org> says:

Hi Martin,

This patch series optimizes the hot path of the UFS driver by making
struct scsi_cmnd and struct ufshcd_lrb adjacent. Making these two data
structures adjacent is realized as follows:

@@ -9040,6 +9046,7 @@ static const struct scsi_host_template ufshcd_driver_template = {
     .name           = UFSHCD,
     .proc_name      = UFSHCD,
     .map_queues     = ufshcd_map_queues,
+    .cmd_size       = sizeof(struct ufshcd_lrb),
     .init_cmd_priv  = ufshcd_init_cmd_priv,
     .queuecommand   = ufshcd_queuecommand,
     .mq_poll        = ufshcd_poll,

The following changes had to be made prior to making these two data
structures adjacent:
* Add support for driver-internal and reserved commands in the SCSI core.
* Instead of making the reserved command slot (hba->reserved_slot)
  invisible to the SCSI core, let the SCSI core allocate a reserved command.
* Remove all UFS data structure members that are no longer needed
  because struct scsi_cmnd and struct ufshcd_lrb are now adjacent
* Call ufshcd_init_lrb() from inside the code for queueing a command instead of
  calling this function before I/O starts. This is necessary because
  ufshcd_memory_alloc() allocates fewer instances than the block layer
  allocates requests. See also the following code in the block layer
  core:

    if (blk_mq_init_request(set, hctx->fq->flush_rq, hctx_idx,
                hctx->numa_node))

  Although the UFS driver could be modified such that ufshcd_init_lrb()
  is called from ufshcd_init_cmd_priv(), realizing this would require
  moving the memory allocations that happen from inside
  ufshcd_memory_alloc() into ufshcd_init_cmd_priv(). That would make
  this patch series even larger. Although ufshcd_init_lrb() is called for each
  command, the benefits of reduced indirection and better cache efficiency
  outweigh the small overhead of per-command lrb initialization.
* ufshcd_add_scsi_host() happens now before any device management
  commands are submitted. This change is necessary because this patch
  makes device management command allocation happen when the SCSI host
  is allocated.
* Allocate as many command slots as the host controller supports. Decrease
  host->cmds_per_lun if necessary once it is clear whether or not the UFS
  device supports less command slots than the host controller.

Please consider this patch series for the next merge window.

Thanks,

Bart.

Link: https://patch.msgid.link/20251031204029.2883185-1-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

1 files changed, 0 insertions, 12 deletions

diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h
index 00152e135fc9..c07ba003a5cb 100644
--- a/include/ufs/ufshcd.h
+++ b/include/ufs/ufshcd.h
@@ -161,7 +161,6 @@ struct ufs_pm_lvl_states {
  * @ucd_prdt_dma_addr: PRDT dma address for debug
  * @ucd_rsp_dma_addr: UPIU response dma address for debug
  * @ucd_req_dma_addr: UPIU request dma address for debug
- * @cmd: pointer to SCSI command
  * @scsi_status: SCSI status of the command
  * @command_type: SCSI, UFS, Query.
  * @task_tag: Task tag of the command
@@ -186,11 +185,9 @@ struct ufshcd_lrb {
 	dma_addr_t ucd_rsp_dma_addr;
 	dma_addr_t ucd_prdt_dma_addr;
 
-	struct scsi_cmnd *cmd;
 	int scsi_status;
 
 	int command_type;
-	int task_tag;
 	u8 lun; /* UPIU LUN id field is only 8-bit wide */
 	bool intr_cmd;
 	bool req_abort_skip;
@@ -239,13 +236,11 @@ struct ufs_query {
  * struct ufs_dev_cmd - all assosiated fields with device management commands
  * @type: device management command type - Query, NOP OUT
  * @lock: lock to allow one command at a time
- * @complete: internal commands completion
  * @query: Device management query information
  */
 struct ufs_dev_cmd {
 	enum dev_cmd_type type;
 	struct mutex lock;
-	struct completion complete;
 	struct ufs_query query;
 };
 
@@ -833,7 +828,6 @@ enum ufshcd_mcq_opr {
  * @spm_lvl: desired UFS power management level during system PM.
  * @pm_op_in_progress: whether or not a PM operation is in progress.
  * @ahit: value of Auto-Hibernate Idle Timer register.
- * @lrb: local reference block
  * @outstanding_tasks: Bits representing outstanding task requests
  * @outstanding_lock: Protects @outstanding_reqs.
  * @outstanding_reqs: Bits representing outstanding transfer requests
@@ -842,7 +836,6 @@ enum ufshcd_mcq_opr {
  * @nutrs: Transfer Request Queue depth supported by controller
  * @nortt - Max outstanding RTTs supported by controller
  * @nutmrs: Task Management Queue depth supported by controller
- * @reserved_slot: Used to submit device commands. Protected by @dev_cmd.lock.
  * @ufs_version: UFS Version to which controller complies
  * @vops: pointer to variant specific operations
  * @vps: pointer to variant specific parameters
@@ -933,7 +926,6 @@ enum ufshcd_mcq_opr {
  * @res: array of resource info of MCQ registers
  * @mcq_base: Multi circular queue registers base address
  * @uhq: array of supported hardware queues
- * @dev_cmd_queue: Queue for issuing device management commands
  * @mcq_opr: MCQ operation and runtime registers
  * @ufs_rtc_update_work: A work for UFS RTC periodic update
  * @pm_qos_req: PM QoS request handle
@@ -976,8 +968,6 @@ struct ufs_hba {
 	/* Auto-Hibernate Idle Timer register value */
 	u32 ahit;
 
-	struct ufshcd_lrb *lrb;
-
 	unsigned long outstanding_tasks;
 	spinlock_t outstanding_lock;
 	unsigned long outstanding_reqs;
@@ -987,7 +977,6 @@ struct ufs_hba {
 	int nortt;
 	u32 mcq_capabilities;
 	int nutmrs;
-	u32 reserved_slot;
 	u32 ufs_version;
 	const struct ufs_hba_variant_ops *vops;
 	struct ufs_hba_variant_params *vps;
@@ -1105,7 +1094,6 @@ struct ufs_hba {
 	bool mcq_esi_enabled;
 	void __iomem *mcq_base;
 	struct ufs_hw_queue *uhq;
-	struct ufs_hw_queue *dev_cmd_queue;
 	struct ufshcd_mcq_opr_info_t mcq_opr[OPR_MAX];
 
 	struct delayed_work ufs_rtc_update_work;