scsi: ufs: core: Allow RTT negotiation

The rtt-upiu packets precede any data-out upiu packets, thus synchronizing
the data input to the device: this mostly applies to write operations, but
there are other operations that requires rtt as well.

There are several rules binding this rtt - data-out dialog, specifically
There can be at most outstanding bMaxNumOfRTT such packets. This might
have an effect on write performance (sequential write in particular), as
each data-out upiu must wait for its rtt sibling.

UFSHCI expects bMaxNumOfRTT to be min(bDeviceRTTCap, NORTT). However, as of
today, there does not appears to be no-one who sets it: not the host
controller nor the driver. It wasn't an issue up to now: bMaxNumOfRTT is
set to 2 after manufacturing, and wasn't limiting the write performance.

UFS4.0, and specifically gear 5 changes this, and requires the device to be
more attentive. This doesn't come free - the device has to allocate more
resources to that end, but the sequential write performance improvement is
significant. Early measurements shows 25% gain when moving from rtt 2 to
9. Therefore, set bMaxNumOfRTT to be min(bDeviceRTTCap, NORTT) as UFSHCI
expects.

Signed-off-by: Avri Altman <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Reviewed-by: Bean Huo <[e-mail]>
Reviewed-by: Bart Van Assche <[e-mail]>
Signed-off-by: Martin K. Petersen <[e-mail]>

drivers/ufs/core/ufshcd.c

···
 /* Default RTC update every 10 seconds */
 #define UFS_RTC_UPDATE_INTERVAL_MS (10 * MSEC_PER_SEC)
 
+/* bMaxNumOfRTT is equal to two after device manufacturing */
+#define DEFAULT_MAX_NUM_RTT 2
+
 /* UFSHC 4.0 compliant HC support this mode. */
 static bool use_mcq_mode = true;
 
···
 	hba->nutmrs =
 	((hba->capabilities & MASK_TASK_MANAGEMENT_REQUEST_SLOTS) >> 16) + 1;
 	hba->reserved_slot = hba->nutrs - 1;
+
+	hba->nortt = FIELD_GET(MASK_NUMBER_OUTSTANDING_RTT, hba->capabilities) + 1;
 
 	/* Read crypto capabilities */
 	err = ufshcd_hba_init_crypto_capabilities(hba);
···
 	dev_info->b_ext_iid_en = ext_iid_en;
 }
 
+static void ufshcd_set_rtt(struct ufs_hba *hba)
+{
+	struct ufs_dev_info *dev_info = &hba->dev_info;
+	u32 rtt = 0;
+	u32 dev_rtt = 0;
+
+	/* RTT override makes sense only for UFS-4.0 and above */
+	if (dev_info->wspecversion < 0x400)
+		return;
+
+	if (ufshcd_query_attr_retry(hba, UPIU_QUERY_OPCODE_READ_ATTR,
+				    QUERY_ATTR_IDN_MAX_NUM_OF_RTT, 0, 0, &dev_rtt)) {
+		dev_err(hba->dev, "failed reading bMaxNumOfRTT\n");
+		return;
+	}
+
+	/* do not override if it was already written */
+	if (dev_rtt != DEFAULT_MAX_NUM_RTT)
+		return;
+
+	rtt = min_t(int, dev_info->rtt_cap, hba->nortt);
+	if (rtt == dev_rtt)
+		return;
+
+	if (ufshcd_query_attr_retry(hba, UPIU_QUERY_OPCODE_WRITE_ATTR,
+				    QUERY_ATTR_IDN_MAX_NUM_OF_RTT, 0, 0, &rtt))
+		dev_err(hba->dev, "failed writing bMaxNumOfRTT\n");
+}
+
 void ufshcd_fixup_dev_quirks(struct ufs_hba *hba,
 			     const struct ufs_dev_quirk *fixups)
 {
···
 	dev_info->wspecversion = desc_buf[DEVICE_DESC_PARAM_SPEC_VER] << 8 |
 				      desc_buf[DEVICE_DESC_PARAM_SPEC_VER + 1];
 	dev_info->bqueuedepth = desc_buf[DEVICE_DESC_PARAM_Q_DPTH];
+
+	dev_info->rtt_cap = desc_buf[DEVICE_DESC_PARAM_RTT_CAP];
 
 	model_index = desc_buf[DEVICE_DESC_PARAM_PRDCT_NAME];
 
···
 			__func__, ret);
 		goto out;
 	}
+
+	ufshcd_set_rtt(hba);
 
 	ufshcd_get_ref_clk_gating_wait(hba);
 

include/ufs/ufs.h

···
 	enum ufs_rtc_time rtc_type;
 	time64_t rtc_time_baseline;
 	u32 rtc_update_period;
+
+	u8 rtt_cap; /* bDeviceRTTCap */
 };
 
 /*

include/ufs/ufshcd.h

···
  * @capabilities: UFS Controller Capabilities
  * @mcq_capabilities: UFS Multi Circular Queue capabilities
  * @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
···
 
 	u32 capabilities;
 	int nutrs;
+	int nortt;
 	u32 mcq_capabilities;
 	int nutmrs;
 	u32 reserved_slot;

include/ufs/ufshci.h

···
 /* Controller capability masks */
 enum {
 	MASK_TRANSFER_REQUESTS_SLOTS		= 0x0000001F,
+	MASK_NUMBER_OUTSTANDING_RTT		= 0x0000FF00,
 	MASK_TASK_MANAGEMENT_REQUEST_SLOTS	= 0x00070000,
 	MASK_EHSLUTRD_SUPPORTED			= 0x00400000,
 	MASK_AUTO_HIBERN8_SUPPORT		= 0x00800000,