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 <avri.altman@wdc.com>
Link: https://lore.kernel.org/r/20240530142510.734-2-avri.altman@wdc.com
Reviewed-by: Bean Huo <beanhuo@micron.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

1 files changed, 38 insertions, 0 deletions

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 0cf07194bbe8..dda6d7e44436 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -102,6 +102,9 @@
 /* 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;
 
@@ -2405,6 +2408,8 @@ static inline int ufshcd_hba_capabilities(struct ufs_hba *hba)
 	((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);
 	if (err) {
@@ -8121,6 +8126,35 @@ out:
 	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)
 {
@@ -8256,6 +8290,8 @@ static int ufs_get_device_desc(struct ufs_hba *hba)
 				      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];
 
 	err = ufshcd_read_string_desc(hba, model_index,
@@ -8508,6 +8544,8 @@ static int ufshcd_device_params_init(struct ufs_hba *hba)
 		goto out;
 	}
 
+	ufshcd_set_rtt(hba);
+
 	ufshcd_get_ref_clk_gating_wait(hba);
 
 	if (!ufshcd_query_flag_retry(hba, UPIU_QUERY_OPCODE_READ_FLAG,