arm_mpam: Add workaround for T241-MPAM-6

The registers MSMON_MBWU_L and MSMON_MBWU return the number of requests
rather than the number of bytes transferred.

Bandwidth resource monitoring is performed at the last level cache, where
each request arrive in 64Byte granularity. The current implementation
returns the number of transactions received at the last level cache but
does not provide the value in bytes. Scaling by 64 gives an accurate byte
count to match the MPAM specification for the MSMON_MBWU and MSMON_MBWU_L
registers. This patch fixes the issue by reporting the actual number of
bytes instead of the number of transactions from __ris_msmon_read().

Tested-by: Gavin Shan <gshan@redhat.com>
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Punit Agrawal <punit.agrawal@oss.qualcomm.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Jesse Chick <jessechick@os.amperecomputing.com>
Reviewed-by: Zeng Heng <zengheng4@huawei.com>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Signed-off-by: Shanker Donthineni <sdonthineni@nvidia.com>
Signed-off-by: Ben Horgan <ben.horgan@arm.com>
Signed-off-by: James Morse <james.morse@arm.com>

Author: shankerd04

Documentation/arch/arm64/silicon-errata.rst

@@ -251,6 +251,8 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | NVIDIA         | T241 MPAM       | T241-MPAM-4     | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
+| NVIDIA         | T241 MPAM       | T241-MPAM-6     | N/A                         |
++----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+
 | Freescale/NXP  | LS2080A/LS1043A | A-008585        | FSL_ERRATUM_A008585         |
 +----------------+-----------------+-----------------+-----------------------------+

drivers/resctrl/mpam_devices.c

@@ -685,6 +685,12 @@ static const struct mpam_quirk mpam_quirks[] = {
 		.iidr_mask  = MPAM_IIDR_MATCH_ONE,
 		.workaround = T241_FORCE_MBW_MIN_TO_ONE,
 	},
+	{
+		/* NVIDIA t241 erratum T241-MPAM-6 */
+		.iidr       = MPAM_IIDR_NVIDIA_T241,
+		.iidr_mask  = MPAM_IIDR_MATCH_ONE,
+		.workaround = T241_MBW_COUNTER_SCALE_64,
+	},
 	{ NULL } /* Sentinel */
 };
 
@@ -1146,7 +1152,7 @@ static void write_msmon_ctl_flt_vals(struct mon_read *m, u32 ctl_val,
 	}
 }
 
-static u64 mpam_msmon_overflow_val(enum mpam_device_features type)
+static u64 __mpam_msmon_overflow_val(enum mpam_device_features type)
 {
 	/* TODO: implement scaling counters */
 	switch (type) {
@@ -1161,6 +1167,18 @@ static u64 mpam_msmon_overflow_val(enum mpam_device_features type)
 	}
 }
 
+static u64 mpam_msmon_overflow_val(enum mpam_device_features type,
+				   struct mpam_msc *msc)
+{
+	u64 overflow_val = __mpam_msmon_overflow_val(type);
+
+	if (mpam_has_quirk(T241_MBW_COUNTER_SCALE_64, msc) &&
+	    type != mpam_feat_msmon_mbwu_63counter)
+		overflow_val *= 64;
+
+	return overflow_val;
+}
+
 static void __ris_msmon_read(void *arg)
 {
 	u64 now;
@@ -1251,13 +1269,17 @@ static void __ris_msmon_read(void *arg)
 			now = FIELD_GET(MSMON___VALUE, now);
 		}
 
+		if (mpam_has_quirk(T241_MBW_COUNTER_SCALE_64, msc) &&
+		    m->type != mpam_feat_msmon_mbwu_63counter)
+			now *= 64;
+
 		if (nrdy)
 			break;
 
 		mbwu_state = &ris->mbwu_state[ctx->mon];
 
 		if (overflow)
-			mbwu_state->correction += mpam_msmon_overflow_val(m->type);
+			mbwu_state->correction += mpam_msmon_overflow_val(m->type, msc);
 
 		/*
 		 * Include bandwidth consumed before the last hardware reset and

drivers/resctrl/mpam_internal.h

@@ -225,6 +225,7 @@ struct mpam_props {
 enum mpam_device_quirks {
 	T241_SCRUB_SHADOW_REGS,
 	T241_FORCE_MBW_MIN_TO_ONE,
+	T241_MBW_COUNTER_SCALE_64,
 	MPAM_QUIRK_LAST
 };