From 07a70f38e9c33b3c614668b12a847f9fe65a4e25 Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Thu, 15 Sep 2022 18:43:45 -0700
Subject: drm/i915: Split GAM and MSLICE steering

Although the bspec lists several MMIO ranges as "MSLICE," it turns out
that a subset of these are of a "GAM" subclass that has unique rules and
doesn't followed regular mslice steering behavior.

 * Xe_HP SDV:  GAM ranges must always be steered to 0,0.  These
   registers share the regular steering control register (0xFDC) with
   other steering types

 * DG2:  GAM ranges must always be steered to 1,0.  GAM registers have a
   dedicated steering control register (0xFE0) so we can set the value
   once at startup and rely on implicit steering.  Technically the
   hardware default should already be set to 1,0 properly, but it never
   hurts to ensure that in the driver.

Bspec: 66534
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Prathap Kumar Valsan <prathap.kumar.valsan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220916014345.3317739-1-matthew.d.roper@intel.com
---
 drivers/gpu/drm/i915/gt/intel_gt_mcr.c | 24 ++++++++++++++++++++++--
 1 file changed, 22 insertions(+), 2 deletions(-)

(limited to 'drivers/gpu/drm/i915/gt/intel_gt_mcr.c')

diff --git a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
index e79405a45312..a2047a68ea7a 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
@@ -40,6 +40,7 @@ static const char * const intel_steering_types[] = {
 	"L3BANK",
 	"MSLICE",
 	"LNCF",
+	"GAM",
 	"INSTANCE 0",
 };
 
@@ -48,14 +49,23 @@ static const struct intel_mmio_range icl_l3bank_steering_table[] = {
 	{},
 };
 
+/*
+ * Although the bspec lists more "MSLICE" ranges than shown here, some of those
+ * are of a "GAM" subclass that has special rules.  Thus we use a separate
+ * GAM table farther down for those.
+ */
 static const struct intel_mmio_range xehpsdv_mslice_steering_table[] = {
-	{ 0x004000, 0x004AFF },
-	{ 0x00C800, 0x00CFFF },
 	{ 0x00DD00, 0x00DDFF },
 	{ 0x00E900, 0x00FFFF }, /* 0xEA00 - OxEFFF is unused */
 	{},
 };
 
+static const struct intel_mmio_range xehpsdv_gam_steering_table[] = {
+	{ 0x004000, 0x004AFF },
+	{ 0x00C800, 0x00CFFF },
+	{},
+};
+
 static const struct intel_mmio_range xehpsdv_lncf_steering_table[] = {
 	{ 0x00B000, 0x00B0FF },
 	{ 0x00D800, 0x00D8FF },
@@ -114,9 +124,15 @@ void intel_gt_mcr_init(struct intel_gt *gt)
 	} else if (IS_DG2(i915)) {
 		gt->steering_table[MSLICE] = xehpsdv_mslice_steering_table;
 		gt->steering_table[LNCF] = dg2_lncf_steering_table;
+		/*
+		 * No need to hook up the GAM table since it has a dedicated
+		 * steering control register on DG2 and can use implicit
+		 * steering.
+		 */
 	} else if (IS_XEHPSDV(i915)) {
 		gt->steering_table[MSLICE] = xehpsdv_mslice_steering_table;
 		gt->steering_table[LNCF] = xehpsdv_lncf_steering_table;
+		gt->steering_table[GAM] = xehpsdv_gam_steering_table;
 	} else if (GRAPHICS_VER(i915) >= 11 &&
 		   GRAPHICS_VER_FULL(i915) < IP_VER(12, 50)) {
 		gt->steering_table[L3BANK] = icl_l3bank_steering_table;
@@ -351,6 +367,10 @@ static void get_nonterminated_steering(struct intel_gt *gt,
 		*group = __ffs(gt->info.mslice_mask) << 1;
 		*instance = 0;	/* unused */
 		break;
+	case GAM:
+		*group = IS_DG2(gt->i915) ? 1 : 0;
+		*instance = 0;
+		break;
 	case INSTANCE0:
 		/*
 		 * There are a lot of MCR types for which instance (0, 0)
-- 
cgit v1.2.3


From 851435ec3686c513b469f8d3d9f8bd405a312412 Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Fri, 14 Oct 2022 16:02:30 -0700
Subject: drm/i915/gt: Add intel_gt_mcr_multicast_rmw() operation

There are cases where we wish to read from any non-terminated MCR
register instance (or the primary instance in the case of GAM ranges),
clear/set some bits, and then write the value back out to the register
in a multicast manner.  Adding a "multicast RMW" will avoid the need to
open-code this.

v2:
 - Return a u32 to align with the recent change to intel_uncore_rmw.

Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Balasubramani Vivekanandan <balasubramani.vivekanandan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221014230239.1023689-6-matthew.d.roper@intel.com
---
 drivers/gpu/drm/i915/gt/intel_gt_mcr.c | 28 ++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/gt/intel_gt_mcr.h |  3 +++
 2 files changed, 31 insertions(+)

(limited to 'drivers/gpu/drm/i915/gt/intel_gt_mcr.c')

diff --git a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
index a2047a68ea7a..4dc360f4e344 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
@@ -302,6 +302,34 @@ void intel_gt_mcr_multicast_write_fw(struct intel_gt *gt, i915_reg_t reg, u32 va
 	intel_uncore_write_fw(gt->uncore, reg, value);
 }
 
+/**
+ * intel_gt_mcr_multicast_rmw - Performs a multicast RMW operations
+ * @gt: GT structure
+ * @reg: the MCR register to read and write
+ * @clear: bits to clear during RMW
+ * @set: bits to set during RMW
+ *
+ * Performs a read-modify-write on an MCR register in a multicast manner.
+ * This operation only makes sense on MCR registers where all instances are
+ * expected to have the same value.  The read will target any non-terminated
+ * instance and the write will be applied to all instances.
+ *
+ * This function assumes the caller is already holding any necessary forcewake
+ * domains; use intel_gt_mcr_multicast_rmw() in cases where forcewake should
+ * be obtained automatically.
+ *
+ * Returns the old (unmodified) value read.
+ */
+u32 intel_gt_mcr_multicast_rmw(struct intel_gt *gt, i915_reg_t reg,
+			       u32 clear, u32 set)
+{
+	u32 val = intel_gt_mcr_read_any(gt, reg);
+
+	intel_gt_mcr_multicast_write(gt, reg, (val & ~clear) | set);
+
+	return val;
+}
+
 /*
  * reg_needs_read_steering - determine whether a register read requires
  *     explicit steering
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_mcr.h b/drivers/gpu/drm/i915/gt/intel_gt_mcr.h
index 77a8b11c287d..781b267478db 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_mcr.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_mcr.h
@@ -24,6 +24,9 @@ void intel_gt_mcr_multicast_write(struct intel_gt *gt,
 void intel_gt_mcr_multicast_write_fw(struct intel_gt *gt,
 				     i915_reg_t reg, u32 value);
 
+u32 intel_gt_mcr_multicast_rmw(struct intel_gt *gt, i915_reg_t reg,
+			       u32 clear, u32 set);
+
 void intel_gt_mcr_get_nonterminated_steering(struct intel_gt *gt,
 					     i915_reg_t reg,
 					     u8 *group, u8 *instance);
-- 
cgit v1.2.3


From 3068bec83eea324b299105ec69a3f42c7968c6c0 Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Fri, 14 Oct 2022 16:02:32 -0700
Subject: drm/i915/gt: Add intel_gt_mcr_wait_for_reg_fw()

Xe_HP has some MCR registers that need to be polled for completion of
operations like TLB invalidation.  Those registers are in the GAM range,
which rolls up the status from each unit into the 'primary' instance's
value.  This makes it useful to have a dedicated 'wait for register'
function that handles this on MCR registers, similar to the
__intel_wait_for_register_fw() function we already have for regular
registers.

Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Balasubramani Vivekanandan <balasubramani.vivekanandan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221014230239.1023689-8-matthew.d.roper@intel.com
---
 drivers/gpu/drm/i915/gt/intel_gt_mcr.c | 55 ++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/gt/intel_gt_mcr.h |  7 +++++
 2 files changed, 62 insertions(+)

(limited to 'drivers/gpu/drm/i915/gt/intel_gt_mcr.c')

diff --git a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
index 4dc360f4e344..1ed9bc4dccfd 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
@@ -568,3 +568,58 @@ void intel_gt_mcr_get_ss_steering(struct intel_gt *gt, unsigned int dss,
 		return;
 	}
 }
+
+/**
+ * intel_gt_mcr_wait_for_reg_fw - wait until MCR register matches expected state
+ * @gt: GT structure
+ * @reg: the register to read
+ * @mask: mask to apply to register value
+ * @value: value to wait for
+ * @fast_timeout_us: fast timeout in microsecond for atomic/tight wait
+ * @slow_timeout_ms: slow timeout in millisecond
+ *
+ * This routine waits until the target register @reg contains the expected
+ * @value after applying the @mask, i.e. it waits until ::
+ *
+ *     (intel_gt_mcr_read_any_fw(gt, reg) & mask) == value
+ *
+ * Otherwise, the wait will timeout after @slow_timeout_ms milliseconds.
+ * For atomic context @slow_timeout_ms must be zero and @fast_timeout_us
+ * must be not larger than 20,0000 microseconds.
+ *
+ * This function is basically an MCR-friendly version of
+ * __intel_wait_for_register_fw().  Generally this function will only be used
+ * on GAM registers which are a bit special --- although they're MCR registers,
+ * reads (e.g., waiting for status updates) are always directed to the primary
+ * instance.
+ *
+ * Note that this routine assumes the caller holds forcewake asserted, it is
+ * not suitable for very long waits.
+ *
+ * Return: 0 if the register matches the desired condition, or -ETIMEDOUT.
+ */
+int intel_gt_mcr_wait_for_reg_fw(struct intel_gt *gt,
+				 i915_reg_t reg,
+				 u32 mask,
+				 u32 value,
+				 unsigned int fast_timeout_us,
+				 unsigned int slow_timeout_ms)
+{
+	u32 reg_value = 0;
+#define done (((reg_value = intel_gt_mcr_read_any_fw(gt, reg)) & mask) == value)
+	int ret;
+
+	/* Catch any overuse of this function */
+	might_sleep_if(slow_timeout_ms);
+	GEM_BUG_ON(fast_timeout_us > 20000);
+	GEM_BUG_ON(!fast_timeout_us && !slow_timeout_ms);
+
+	ret = -ETIMEDOUT;
+	if (fast_timeout_us && fast_timeout_us <= 20000)
+		ret = _wait_for_atomic(done, fast_timeout_us, 0);
+	if (ret && slow_timeout_ms)
+		ret = wait_for(done, slow_timeout_ms);
+
+	return ret;
+#undef done
+}
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_mcr.h b/drivers/gpu/drm/i915/gt/intel_gt_mcr.h
index 781b267478db..548f922cd9fa 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_mcr.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_mcr.h
@@ -37,6 +37,13 @@ void intel_gt_mcr_report_steering(struct drm_printer *p, struct intel_gt *gt,
 void intel_gt_mcr_get_ss_steering(struct intel_gt *gt, unsigned int dss,
 				  unsigned int *group, unsigned int *instance);
 
+int intel_gt_mcr_wait_for_reg_fw(struct intel_gt *gt,
+				 i915_reg_t reg,
+				 u32 mask,
+				 u32 value,
+				 unsigned int fast_timeout_us,
+				 unsigned int slow_timeout_ms);
+
 /*
  * Helper for for_each_ss_steering loop.  On pre-Xe_HP platforms, subslice
  * presence is determined by using the group/instance as direct lookups in the
-- 
cgit v1.2.3


From 58bc2453ab8a4b5e1f2969e09c12ab69b8aaaf98 Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Fri, 14 Oct 2022 16:02:37 -0700
Subject: drm/i915: Define multicast registers as a new type

Rather than treating multicast registers as 'i915_reg_t' let's define
them as a completely new type.  This will allow the compiler to help us
make sure we're using multicast-aware functions to operate on multicast
registers.

This plan does break down a bit in places where we're just maintaining
heterogeneous lists of registers (e.g., various MMIO whitelists used by
perf, GVT, etc.) rather than performing reads/writes.  We only really
care about the offset in those cases, so for now we can "cast" the
registers as non-MCR, leaving us with a list of i915_reg_t's, but we may
want to look for better ways to store mixed collections of i915_reg_t
and i915_mcr_reg_t in the future.

v2:
 - Add TLB invalidation registers
v3:
 - Make type checking of i915_mmio_reg_offset() stricter.  It will
   accept either i915_reg_t or i915_mcr_reg_t, but will now raise a
   compile error if any other type is passed, even if that type contains
   a 'reg' field.  (Jani)
 - Drop a ton of GVT changes; allowing i915_mmio_reg_offset() to take
   either an i915_reg_t or an i915_mcr_reg_t means that the huge lists
   of MMIO_D*() macros used in GVT will continue to work without
   modification.  We need only make changes to structures that have an
   explicit i915_reg_t in them now.

Cc: Jani Nikula <jani.nikula@linux.intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Balasubramani Vivekanandan <balasubramani.vivekanandan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221014230239.1023689-13-matthew.d.roper@intel.com
---
 drivers/gpu/drm/i915/gt/intel_gt.c                | 16 +++++--
 drivers/gpu/drm/i915/gt/intel_gt_mcr.c            | 51 ++++++++++++++---------
 drivers/gpu/drm/i915/gt/intel_gt_mcr.h            | 18 ++++----
 drivers/gpu/drm/i915/gt/intel_gt_regs.h           | 27 ++++++++----
 drivers/gpu/drm/i915/gt/intel_workarounds.c       | 32 +++++++-------
 drivers/gpu/drm/i915/gt/intel_workarounds_types.h |  5 ++-
 drivers/gpu/drm/i915/gt/selftest_workarounds.c    |  2 +-
 drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c        |  2 +-
 drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c    |  4 +-
 drivers/gpu/drm/i915/gvt/handlers.c               |  2 +-
 drivers/gpu/drm/i915/gvt/mmio_context.c           | 14 +++----
 drivers/gpu/drm/i915/i915_reg_defs.h              | 27 ++++++------
 12 files changed, 117 insertions(+), 83 deletions(-)

(limited to 'drivers/gpu/drm/i915/gt/intel_gt_mcr.c')

diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index 3df0d0336dbc..27dbb9e4bd6c 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -991,7 +991,10 @@ void intel_gt_info_print(const struct intel_gt_info *info,
 }
 
 struct reg_and_bit {
-	i915_reg_t reg;
+	union {
+		i915_reg_t reg;
+		i915_mcr_reg_t mcr_reg;
+	};
 	u32 bit;
 };
 
@@ -1033,7 +1036,7 @@ get_reg_and_bit(const struct intel_engine_cs *engine, const bool gen8,
 static int wait_for_invalidate(struct intel_gt *gt, struct reg_and_bit rb)
 {
 	if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 50))
-		return intel_gt_mcr_wait_for_reg_fw(gt, rb.reg, rb.bit, 0,
+		return intel_gt_mcr_wait_for_reg_fw(gt, rb.mcr_reg, rb.bit, 0,
 						    TLB_INVAL_TIMEOUT_US,
 						    TLB_INVAL_TIMEOUT_MS);
 	else
@@ -1058,7 +1061,7 @@ static void mmio_invalidate_full(struct intel_gt *gt)
 		[COPY_ENGINE_CLASS]		= GEN12_BLT_TLB_INV_CR,
 		[COMPUTE_CLASS]			= GEN12_COMPCTX_TLB_INV_CR,
 	};
-	static const i915_reg_t xehp_regs[] = {
+	static const i915_mcr_reg_t xehp_regs[] = {
 		[RENDER_CLASS]			= XEHP_GFX_TLB_INV_CR,
 		[VIDEO_DECODE_CLASS]		= XEHP_VD_TLB_INV_CR,
 		[VIDEO_ENHANCEMENT_CLASS]	= XEHP_VE_TLB_INV_CR,
@@ -1131,7 +1134,12 @@ static void mmio_invalidate_full(struct intel_gt *gt)
 	for_each_engine_masked(engine, gt, awake, tmp) {
 		struct reg_and_bit rb;
 
-		rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
+		if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) {
+			rb.mcr_reg = xehp_regs[engine->class];
+			rb.bit = BIT(engine->instance);
+		} else {
+			rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
+		}
 
 		if (wait_for_invalidate(gt, rb))
 			drm_err_ratelimited(&gt->i915->drm,
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
index 1ed9bc4dccfd..349074bf365f 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
@@ -150,6 +150,19 @@ void intel_gt_mcr_init(struct intel_gt *gt)
 	}
 }
 
+/*
+ * Although the rest of the driver should use MCR-specific functions to
+ * read/write MCR registers, we still use the regular intel_uncore_* functions
+ * internally to implement those, so we need a way for the functions in this
+ * file to "cast" an i915_mcr_reg_t into an i915_reg_t.
+ */
+static i915_reg_t mcr_reg_cast(const i915_mcr_reg_t mcr)
+{
+	i915_reg_t r = { .reg = mcr.reg };
+
+	return r;
+}
+
 /*
  * rw_with_mcr_steering_fw - Access a register with specific MCR steering
  * @uncore: pointer to struct intel_uncore
@@ -164,7 +177,7 @@ void intel_gt_mcr_init(struct intel_gt *gt)
  * Caller needs to make sure the relevant forcewake wells are up.
  */
 static u32 rw_with_mcr_steering_fw(struct intel_uncore *uncore,
-				   i915_reg_t reg, u8 rw_flag,
+				   i915_mcr_reg_t reg, u8 rw_flag,
 				   int group, int instance, u32 value)
 {
 	u32 mcr_mask, mcr_ss, mcr, old_mcr, val = 0;
@@ -201,9 +214,9 @@ static u32 rw_with_mcr_steering_fw(struct intel_uncore *uncore,
 	intel_uncore_write_fw(uncore, GEN8_MCR_SELECTOR, mcr);
 
 	if (rw_flag == FW_REG_READ)
-		val = intel_uncore_read_fw(uncore, reg);
+		val = intel_uncore_read_fw(uncore, mcr_reg_cast(reg));
 	else
-		intel_uncore_write_fw(uncore, reg, value);
+		intel_uncore_write_fw(uncore, mcr_reg_cast(reg), value);
 
 	mcr &= ~mcr_mask;
 	mcr |= old_mcr & mcr_mask;
@@ -214,14 +227,14 @@ static u32 rw_with_mcr_steering_fw(struct intel_uncore *uncore,
 }
 
 static u32 rw_with_mcr_steering(struct intel_uncore *uncore,
-				i915_reg_t reg, u8 rw_flag,
+				i915_mcr_reg_t reg, u8 rw_flag,
 				int group, int instance,
 				u32 value)
 {
 	enum forcewake_domains fw_domains;
 	u32 val;
 
-	fw_domains = intel_uncore_forcewake_for_reg(uncore, reg,
+	fw_domains = intel_uncore_forcewake_for_reg(uncore, mcr_reg_cast(reg),
 						    rw_flag);
 	fw_domains |= intel_uncore_forcewake_for_reg(uncore,
 						     GEN8_MCR_SELECTOR,
@@ -249,7 +262,7 @@ static u32 rw_with_mcr_steering(struct intel_uncore *uncore,
  * group/instance.
  */
 u32 intel_gt_mcr_read(struct intel_gt *gt,
-		      i915_reg_t reg,
+		      i915_mcr_reg_t reg,
 		      int group, int instance)
 {
 	return rw_with_mcr_steering(gt->uncore, reg, FW_REG_READ, group, instance, 0);
@@ -266,7 +279,7 @@ u32 intel_gt_mcr_read(struct intel_gt *gt,
  * Write an MCR register in unicast mode after steering toward a specific
  * group/instance.
  */
-void intel_gt_mcr_unicast_write(struct intel_gt *gt, i915_reg_t reg, u32 value,
+void intel_gt_mcr_unicast_write(struct intel_gt *gt, i915_mcr_reg_t reg, u32 value,
 				int group, int instance)
 {
 	rw_with_mcr_steering(gt->uncore, reg, FW_REG_WRITE, group, instance, value);
@@ -281,9 +294,9 @@ void intel_gt_mcr_unicast_write(struct intel_gt *gt, i915_reg_t reg, u32 value,
  * Write an MCR register in multicast mode to update all instances.
  */
 void intel_gt_mcr_multicast_write(struct intel_gt *gt,
-				i915_reg_t reg, u32 value)
+				  i915_mcr_reg_t reg, u32 value)
 {
-	intel_uncore_write(gt->uncore, reg, value);
+	intel_uncore_write(gt->uncore, mcr_reg_cast(reg), value);
 }
 
 /**
@@ -297,9 +310,9 @@ void intel_gt_mcr_multicast_write(struct intel_gt *gt,
  * domains; use intel_gt_mcr_multicast_write() in cases where forcewake should
  * be obtained automatically.
  */
-void intel_gt_mcr_multicast_write_fw(struct intel_gt *gt, i915_reg_t reg, u32 value)
+void intel_gt_mcr_multicast_write_fw(struct intel_gt *gt, i915_mcr_reg_t reg, u32 value)
 {
-	intel_uncore_write_fw(gt->uncore, reg, value);
+	intel_uncore_write_fw(gt->uncore, mcr_reg_cast(reg), value);
 }
 
 /**
@@ -320,7 +333,7 @@ void intel_gt_mcr_multicast_write_fw(struct intel_gt *gt, i915_reg_t reg, u32 va
  *
  * Returns the old (unmodified) value read.
  */
-u32 intel_gt_mcr_multicast_rmw(struct intel_gt *gt, i915_reg_t reg,
+u32 intel_gt_mcr_multicast_rmw(struct intel_gt *gt, i915_mcr_reg_t reg,
 			       u32 clear, u32 set)
 {
 	u32 val = intel_gt_mcr_read_any(gt, reg);
@@ -345,7 +358,7 @@ u32 intel_gt_mcr_multicast_rmw(struct intel_gt *gt, i915_reg_t reg,
  * for @type steering too.
  */
 static bool reg_needs_read_steering(struct intel_gt *gt,
-				    i915_reg_t reg,
+				    i915_mcr_reg_t reg,
 				    enum intel_steering_type type)
 {
 	const u32 offset = i915_mmio_reg_offset(reg);
@@ -428,7 +441,7 @@ static void get_nonterminated_steering(struct intel_gt *gt,
  * steering.
  */
 void intel_gt_mcr_get_nonterminated_steering(struct intel_gt *gt,
-					     i915_reg_t reg,
+					     i915_mcr_reg_t reg,
 					     u8 *group, u8 *instance)
 {
 	int type;
@@ -457,7 +470,7 @@ void intel_gt_mcr_get_nonterminated_steering(struct intel_gt *gt,
  *
  * Returns the value from a non-terminated instance of @reg.
  */
-u32 intel_gt_mcr_read_any_fw(struct intel_gt *gt, i915_reg_t reg)
+u32 intel_gt_mcr_read_any_fw(struct intel_gt *gt, i915_mcr_reg_t reg)
 {
 	int type;
 	u8 group, instance;
@@ -471,7 +484,7 @@ u32 intel_gt_mcr_read_any_fw(struct intel_gt *gt, i915_reg_t reg)
 		}
 	}
 
-	return intel_uncore_read_fw(gt->uncore, reg);
+	return intel_uncore_read_fw(gt->uncore, mcr_reg_cast(reg));
 }
 
 /**
@@ -484,7 +497,7 @@ u32 intel_gt_mcr_read_any_fw(struct intel_gt *gt, i915_reg_t reg)
  *
  * Returns the value from a non-terminated instance of @reg.
  */
-u32 intel_gt_mcr_read_any(struct intel_gt *gt, i915_reg_t reg)
+u32 intel_gt_mcr_read_any(struct intel_gt *gt, i915_mcr_reg_t reg)
 {
 	int type;
 	u8 group, instance;
@@ -498,7 +511,7 @@ u32 intel_gt_mcr_read_any(struct intel_gt *gt, i915_reg_t reg)
 		}
 	}
 
-	return intel_uncore_read(gt->uncore, reg);
+	return intel_uncore_read(gt->uncore, mcr_reg_cast(reg));
 }
 
 static void report_steering_type(struct drm_printer *p,
@@ -599,7 +612,7 @@ void intel_gt_mcr_get_ss_steering(struct intel_gt *gt, unsigned int dss,
  * Return: 0 if the register matches the desired condition, or -ETIMEDOUT.
  */
 int intel_gt_mcr_wait_for_reg_fw(struct intel_gt *gt,
-				 i915_reg_t reg,
+				 i915_mcr_reg_t reg,
 				 u32 mask,
 				 u32 value,
 				 unsigned int fast_timeout_us,
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_mcr.h b/drivers/gpu/drm/i915/gt/intel_gt_mcr.h
index 548f922cd9fa..3fb0502bff22 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_mcr.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_mcr.h
@@ -11,24 +11,24 @@
 void intel_gt_mcr_init(struct intel_gt *gt);
 
 u32 intel_gt_mcr_read(struct intel_gt *gt,
-		      i915_reg_t reg,
+		      i915_mcr_reg_t reg,
 		      int group, int instance);
-u32 intel_gt_mcr_read_any_fw(struct intel_gt *gt, i915_reg_t reg);
-u32 intel_gt_mcr_read_any(struct intel_gt *gt, i915_reg_t reg);
+u32 intel_gt_mcr_read_any_fw(struct intel_gt *gt, i915_mcr_reg_t reg);
+u32 intel_gt_mcr_read_any(struct intel_gt *gt, i915_mcr_reg_t reg);
 
 void intel_gt_mcr_unicast_write(struct intel_gt *gt,
-				i915_reg_t reg, u32 value,
+				i915_mcr_reg_t reg, u32 value,
 				int group, int instance);
 void intel_gt_mcr_multicast_write(struct intel_gt *gt,
-				  i915_reg_t reg, u32 value);
+				  i915_mcr_reg_t reg, u32 value);
 void intel_gt_mcr_multicast_write_fw(struct intel_gt *gt,
-				     i915_reg_t reg, u32 value);
+				     i915_mcr_reg_t reg, u32 value);
 
-u32 intel_gt_mcr_multicast_rmw(struct intel_gt *gt, i915_reg_t reg,
+u32 intel_gt_mcr_multicast_rmw(struct intel_gt *gt, i915_mcr_reg_t reg,
 			       u32 clear, u32 set);
 
 void intel_gt_mcr_get_nonterminated_steering(struct intel_gt *gt,
-					     i915_reg_t reg,
+					     i915_mcr_reg_t reg,
 					     u8 *group, u8 *instance);
 
 void intel_gt_mcr_report_steering(struct drm_printer *p, struct intel_gt *gt,
@@ -38,7 +38,7 @@ void intel_gt_mcr_get_ss_steering(struct intel_gt *gt, unsigned int dss,
 				  unsigned int *group, unsigned int *instance);
 
 int intel_gt_mcr_wait_for_reg_fw(struct intel_gt *gt,
-				 i915_reg_t reg,
+				 i915_mcr_reg_t reg,
 				 u32 mask,
 				 u32 value,
 				 unsigned int fast_timeout_us,
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
index bd2bbacf2386..1116bc3dba51 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
@@ -8,7 +8,18 @@
 
 #include "i915_reg_defs.h"
 
-#define MCR_REG(offset)	_MMIO(offset)
+#define MCR_REG(offset)	((const i915_mcr_reg_t){ .reg = (offset) })
+
+/*
+ * The perf control registers are technically multicast registers, but the
+ * driver never needs to read/write them directly; we only use them to build
+ * lists of registers (where they're mixed in with other non-MCR registers)
+ * and then operate on the offset directly.  For now we'll just define them
+ * as non-multicast so we can place them on the same list, but we may want
+ * to try to come up with a better way to handle heterogeneous lists of
+ * registers in the future.
+ */
+#define PERF_REG(offset)			_MMIO(offset)
 
 /* RPM unit config (Gen8+) */
 #define RPM_CONFIG0				_MMIO(0xd00)
@@ -1113,8 +1124,8 @@
 #define   FLOAT_BLEND_OPTIMIZATION_ENABLE	REG_BIT(4)
 #define   ENABLE_PREFETCH_INTO_IC		REG_BIT(3)
 
-#define EU_PERF_CNTL0				MCR_REG(0xe458)
-#define EU_PERF_CNTL4				MCR_REG(0xe45c)
+#define EU_PERF_CNTL0				PERF_REG(0xe458)
+#define EU_PERF_CNTL4				PERF_REG(0xe45c)
 
 #define GEN9_ROW_CHICKEN4			MCR_REG(0xe48c)
 #define   GEN12_DISABLE_GRF_CLEAR		REG_BIT(13)
@@ -1151,16 +1162,16 @@
 #define   STACKID_CTRL				REG_GENMASK(6, 5)
 #define   STACKID_CTRL_512			REG_FIELD_PREP(STACKID_CTRL, 0x2)
 
-#define EU_PERF_CNTL1				MCR_REG(0xe558)
-#define EU_PERF_CNTL5				MCR_REG(0xe55c)
+#define EU_PERF_CNTL1				PERF_REG(0xe558)
+#define EU_PERF_CNTL5				PERF_REG(0xe55c)
 
 #define XEHP_HDC_CHICKEN0			MCR_REG(0xe5f0)
 #define   LSC_L1_FLUSH_CTL_3D_DATAPORT_FLUSH_EVENTS_MASK	REG_GENMASK(13, 11)
 #define ICL_HDC_MODE				MCR_REG(0xe5f4)
 
-#define EU_PERF_CNTL2				MCR_REG(0xe658)
-#define EU_PERF_CNTL6				MCR_REG(0xe65c)
-#define EU_PERF_CNTL3				MCR_REG(0xe758)
+#define EU_PERF_CNTL2				PERF_REG(0xe658)
+#define EU_PERF_CNTL6				PERF_REG(0xe65c)
+#define EU_PERF_CNTL3				PERF_REG(0xe758)
 
 #define LSC_CHICKEN_BIT_0			MCR_REG(0xe7c8)
 #define   DISABLE_D8_D16_COASLESCE		REG_BIT(30)
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 7671994d5b7a..dadb60e6a58f 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -166,11 +166,11 @@ static void wa_add(struct i915_wa_list *wal, i915_reg_t reg,
 	_wa_add(wal, &wa);
 }
 
-static void wa_mcr_add(struct i915_wa_list *wal, i915_reg_t reg,
+static void wa_mcr_add(struct i915_wa_list *wal, i915_mcr_reg_t reg,
 		       u32 clear, u32 set, u32 read_mask, bool masked_reg)
 {
 	struct i915_wa wa = {
-		.reg  = reg,
+		.mcr_reg = reg,
 		.clr  = clear,
 		.set  = set,
 		.read = read_mask,
@@ -188,7 +188,7 @@ wa_write_clr_set(struct i915_wa_list *wal, i915_reg_t reg, u32 clear, u32 set)
 }
 
 static void
-wa_mcr_write_clr_set(struct i915_wa_list *wal, i915_reg_t reg, u32 clear, u32 set)
+wa_mcr_write_clr_set(struct i915_wa_list *wal, i915_mcr_reg_t reg, u32 clear, u32 set)
 {
 	wa_mcr_add(wal, reg, clear, set, clear, false);
 }
@@ -206,7 +206,7 @@ wa_write_or(struct i915_wa_list *wal, i915_reg_t reg, u32 set)
 }
 
 static void
-wa_mcr_write_or(struct i915_wa_list *wal, i915_reg_t reg, u32 set)
+wa_mcr_write_or(struct i915_wa_list *wal, i915_mcr_reg_t reg, u32 set)
 {
 	wa_mcr_write_clr_set(wal, reg, set, set);
 }
@@ -218,7 +218,7 @@ wa_write_clr(struct i915_wa_list *wal, i915_reg_t reg, u32 clr)
 }
 
 static void
-wa_mcr_write_clr(struct i915_wa_list *wal, i915_reg_t reg, u32 clr)
+wa_mcr_write_clr(struct i915_wa_list *wal, i915_mcr_reg_t reg, u32 clr)
 {
 	wa_mcr_write_clr_set(wal, reg, clr, 0);
 }
@@ -241,7 +241,7 @@ wa_masked_en(struct i915_wa_list *wal, i915_reg_t reg, u32 val)
 }
 
 static void
-wa_mcr_masked_en(struct i915_wa_list *wal, i915_reg_t reg, u32 val)
+wa_mcr_masked_en(struct i915_wa_list *wal, i915_mcr_reg_t reg, u32 val)
 {
 	wa_mcr_add(wal, reg, 0, _MASKED_BIT_ENABLE(val), val, true);
 }
@@ -253,7 +253,7 @@ wa_masked_dis(struct i915_wa_list *wal, i915_reg_t reg, u32 val)
 }
 
 static void
-wa_mcr_masked_dis(struct i915_wa_list *wal, i915_reg_t reg, u32 val)
+wa_mcr_masked_dis(struct i915_wa_list *wal, i915_mcr_reg_t reg, u32 val)
 {
 	wa_mcr_add(wal, reg, 0, _MASKED_BIT_DISABLE(val), val, true);
 }
@@ -266,7 +266,7 @@ wa_masked_field_set(struct i915_wa_list *wal, i915_reg_t reg,
 }
 
 static void
-wa_mcr_masked_field_set(struct i915_wa_list *wal, i915_reg_t reg,
+wa_mcr_masked_field_set(struct i915_wa_list *wal, i915_mcr_reg_t reg,
 			u32 mask, u32 val)
 {
 	wa_mcr_add(wal, reg, 0, _MASKED_FIELD(mask, val), mask, true);
@@ -1692,19 +1692,19 @@ wa_list_apply(struct intel_gt *gt, const struct i915_wa_list *wal)
 		/* open-coded rmw due to steering */
 		if (wa->clr)
 			old = wa->is_mcr ?
-				intel_gt_mcr_read_any_fw(gt, wa->reg) :
+				intel_gt_mcr_read_any_fw(gt, wa->mcr_reg) :
 				intel_uncore_read_fw(uncore, wa->reg);
 		val = (old & ~wa->clr) | wa->set;
 		if (val != old || !wa->clr) {
 			if (wa->is_mcr)
-				intel_gt_mcr_multicast_write_fw(gt, wa->reg, val);
+				intel_gt_mcr_multicast_write_fw(gt, wa->mcr_reg, val);
 			else
 				intel_uncore_write_fw(uncore, wa->reg, val);
 		}
 
 		if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)) {
 			u32 val = wa->is_mcr ?
-				intel_gt_mcr_read_any_fw(gt, wa->reg) :
+				intel_gt_mcr_read_any_fw(gt, wa->mcr_reg) :
 				intel_uncore_read_fw(uncore, wa->reg);
 
 			wa_verify(wa, val, wal->name, "application");
@@ -1738,7 +1738,7 @@ static bool wa_list_verify(struct intel_gt *gt,
 
 	for (i = 0, wa = wal->list; i < wal->count; i++, wa++)
 		ok &= wa_verify(wa, wa->is_mcr ?
-				intel_gt_mcr_read_any_fw(gt, wa->reg) :
+				intel_gt_mcr_read_any_fw(gt, wa->mcr_reg) :
 				intel_uncore_read_fw(uncore, wa->reg),
 				wal->name, from);
 
@@ -1786,10 +1786,10 @@ whitelist_reg_ext(struct i915_wa_list *wal, i915_reg_t reg, u32 flags)
 }
 
 static void
-whitelist_mcr_reg_ext(struct i915_wa_list *wal, i915_reg_t reg, u32 flags)
+whitelist_mcr_reg_ext(struct i915_wa_list *wal, i915_mcr_reg_t reg, u32 flags)
 {
 	struct i915_wa wa = {
-		.reg = reg,
+		.mcr_reg = reg,
 		.is_mcr = 1,
 	};
 
@@ -1799,7 +1799,7 @@ whitelist_mcr_reg_ext(struct i915_wa_list *wal, i915_reg_t reg, u32 flags)
 	if (GEM_DEBUG_WARN_ON(!is_nonpriv_flags_valid(flags)))
 		return;
 
-	wa.reg.reg |= flags;
+	wa.mcr_reg.reg |= flags;
 	_wa_add(wal, &wa);
 }
 
@@ -1810,7 +1810,7 @@ whitelist_reg(struct i915_wa_list *wal, i915_reg_t reg)
 }
 
 static void
-whitelist_mcr_reg(struct i915_wa_list *wal, i915_reg_t reg)
+whitelist_mcr_reg(struct i915_wa_list *wal, i915_mcr_reg_t reg)
 {
 	whitelist_mcr_reg_ext(wal, reg, RING_FORCE_TO_NONPRIV_ACCESS_RW);
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds_types.h b/drivers/gpu/drm/i915/gt/intel_workarounds_types.h
index f05b37e56fa9..7c8b01d00043 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds_types.h
@@ -11,7 +11,10 @@
 #include "i915_reg_defs.h"
 
 struct i915_wa {
-	i915_reg_t	reg;
+	union {
+		i915_reg_t	reg;
+		i915_mcr_reg_t	mcr_reg;
+	};
 	u32		clr;
 	u32		set;
 	u32		read;
diff --git a/drivers/gpu/drm/i915/gt/selftest_workarounds.c b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
index 67a9aab801dd..21b1edc052f8 100644
--- a/drivers/gpu/drm/i915/gt/selftest_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
@@ -991,7 +991,7 @@ static bool pardon_reg(struct drm_i915_private *i915, i915_reg_t reg)
 	/* Alas, we must pardon some whitelists. Mistakes already made */
 	static const struct regmask pardon[] = {
 		{ GEN9_CTX_PREEMPT_REG, 9 },
-		{ GEN8_L3SQCREG4, 9 },
+		{ _MMIO(0xb118), 9 }, /* GEN8_L3SQCREG4 */
 	};
 
 	return find_reg(i915, reg, pardon, ARRAY_SIZE(pardon));
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c
index de923fb82301..34ef4f36e660 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c
@@ -328,7 +328,7 @@ static long __must_check guc_mmio_reg_add(struct intel_gt *gt,
 
 static long __must_check guc_mcr_reg_add(struct intel_gt *gt,
 					 struct temp_regset *regset,
-					 i915_reg_t reg, u32 flags)
+					 i915_mcr_reg_t reg, u32 flags)
 {
 	u8 group, inst;
 
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c
index 9495a7928bc8..d5c03e7a7843 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c
@@ -240,7 +240,7 @@ static void guc_capture_free_extlists(struct __guc_mmio_reg_descr_group *reglist
 
 struct __ext_steer_reg {
 	const char *name;
-	i915_reg_t reg;
+	i915_mcr_reg_t reg;
 };
 
 static const struct __ext_steer_reg xe_extregs[] = {
@@ -252,7 +252,7 @@ static void __fill_ext_reg(struct __guc_mmio_reg_descr *ext,
 			   const struct __ext_steer_reg *extlist,
 			   int slice_id, int subslice_id)
 {
-	ext->reg = extlist->reg;
+	ext->reg = _MMIO(i915_mmio_reg_offset(extlist->reg));
 	ext->flags = FIELD_PREP(GUC_REGSET_STEERING_GROUP, slice_id);
 	ext->flags |= FIELD_PREP(GUC_REGSET_STEERING_INSTANCE, subslice_id);
 	ext->regname = extlist->name;
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 683f88f5d669..41ab6c99e3a0 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -734,7 +734,7 @@ static i915_reg_t force_nonpriv_white_list[] = {
 	_MMIO(0x770c),
 	_MMIO(0x83a8),
 	_MMIO(0xb110),
-	GEN8_L3SQCREG4,//_MMIO(0xb118)
+	_MMIO(0xb118),
 	_MMIO(0xe100),
 	_MMIO(0xe18c),
 	_MMIO(0xe48c),
diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c
index 485ff6c8e558..5197e15cb78e 100644
--- a/drivers/gpu/drm/i915/gvt/mmio_context.c
+++ b/drivers/gpu/drm/i915/gvt/mmio_context.c
@@ -106,15 +106,15 @@ static struct engine_mmio gen9_engine_mmio_list[] __cacheline_aligned = {
 	{RCS0, GEN8_CS_CHICKEN1, 0xffff, true}, /* 0x2580 */
 	{RCS0, COMMON_SLICE_CHICKEN2, 0xffff, true}, /* 0x7014 */
 	{RCS0, GEN9_CS_DEBUG_MODE1, 0xffff, false}, /* 0x20ec */
-	{RCS0, GEN8_L3SQCREG4, 0, false}, /* 0xb118 */
-	{RCS0, GEN9_SCRATCH1, 0, false}, /* 0xb11c */
+	{RCS0, _MMIO(0xb118), 0, false}, /* GEN8_L3SQCREG4 */
+	{RCS0, _MMIO(0xb11c), 0, false}, /* GEN9_SCRATCH1 */
 	{RCS0, GEN9_SCRATCH_LNCF1, 0, false}, /* 0xb008 */
 	{RCS0, GEN7_HALF_SLICE_CHICKEN1, 0xffff, true}, /* 0xe100 */
-	{RCS0, HALF_SLICE_CHICKEN2, 0xffff, true}, /* 0xe180 */
-	{RCS0, GEN8_HALF_SLICE_CHICKEN3, 0xffff, true}, /* 0xe184 */
-	{RCS0, GEN9_HALF_SLICE_CHICKEN5, 0xffff, true}, /* 0xe188 */
-	{RCS0, GEN9_HALF_SLICE_CHICKEN7, 0xffff, true}, /* 0xe194 */
-	{RCS0, GEN8_ROW_CHICKEN, 0xffff, true}, /* 0xe4f0 */
+	{RCS0, _MMIO(0xe180), 0xffff, true}, /* HALF_SLICE_CHICKEN2 */
+	{RCS0, _MMIO(0xe184), 0xffff, true}, /* GEN8_HALF_SLICE_CHICKEN3 */
+	{RCS0, _MMIO(0xe188), 0xffff, true}, /* GEN9_HALF_SLICE_CHICKEN5 */
+	{RCS0, _MMIO(0xe194), 0xffff, true}, /* GEN9_HALF_SLICE_CHICKEN7 */
+	{RCS0, _MMIO(0xe4f0), 0xffff, true}, /* GEN8_ROW_CHICKEN */
 	{RCS0, TRVATTL3PTRDW(0), 0, true}, /* 0x4de0 */
 	{RCS0, TRVATTL3PTRDW(1), 0, true}, /* 0x4de4 */
 	{RCS0, TRNULLDETCT, 0, true}, /* 0x4de8 */
diff --git a/drivers/gpu/drm/i915/i915_reg_defs.h b/drivers/gpu/drm/i915/i915_reg_defs.h
index 8f486f77609f..f1859046a9c4 100644
--- a/drivers/gpu/drm/i915/i915_reg_defs.h
+++ b/drivers/gpu/drm/i915/i915_reg_defs.h
@@ -104,22 +104,21 @@ typedef struct {
 
 #define _MMIO(r) ((const i915_reg_t){ .reg = (r) })
 
-#define INVALID_MMIO_REG _MMIO(0)
-
-static __always_inline u32 i915_mmio_reg_offset(i915_reg_t reg)
-{
-	return reg.reg;
-}
+typedef struct {
+	u32 reg;
+} i915_mcr_reg_t;
 
-static inline bool i915_mmio_reg_equal(i915_reg_t a, i915_reg_t b)
-{
-	return i915_mmio_reg_offset(a) == i915_mmio_reg_offset(b);
-}
+#define INVALID_MMIO_REG _MMIO(0)
 
-static inline bool i915_mmio_reg_valid(i915_reg_t reg)
-{
-	return !i915_mmio_reg_equal(reg, INVALID_MMIO_REG);
-}
+/*
+ * These macros can be used on either i915_reg_t or i915_mcr_reg_t since they're
+ * simply operations on the register's offset and don't care about the MCR vs
+ * non-MCR nature of the register.
+ */
+#define i915_mmio_reg_offset(r) \
+	_Generic((r), i915_reg_t: (r).reg, i915_mcr_reg_t: (r).reg)
+#define i915_mmio_reg_equal(a, b) (i915_mmio_reg_offset(a) == i915_mmio_reg_offset(b))
+#define i915_mmio_reg_valid(r) (!i915_mmio_reg_equal(r, INVALID_MMIO_REG))
 
 #define VLV_DISPLAY_BASE		0x180000
 
-- 
cgit v1.2.3


From f32898c94a105c221e6fe957aee833e7fc98f95f Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Fri, 14 Oct 2022 16:02:38 -0700
Subject: drm/i915/xelpg: Add multicast steering

MTL's graphics IP (Xe_LPG) once again changes the multicast register
types and steering details.  Key changes from past platforms:
 * The number of instances of some MCR types (NODE, OAAL2, and GAM) vary
   according to the MTL subplatform and cannot be read from fuse
   registers.  However steering to instance #0 will always provided a
   non-terminated value, so we can lump these all into a single
   "instance0" table.
 * The MCR steering register (and its bitfields) has changed.

Unlike past platforms, we will be explicitly steering all types of MCR
accesses, including those for "SLICE" and "DSS" ranges; we no longer
rely on implicit steering.  On previous platforms, various
hardware/firmware agents that needed to access registers typically had
their own steering control registers, allowing them to perform multicast
steering without clobbering the CPU/kernel steering.  Starting with MTL,
more of these agents now share a single steering register (0xFD4) and it
is no longer safe for us to assume that the value will remain unchanged
from how we initialized it during startup.  There is also a slight
chance of race conditions between the driver and a hardware/firmware
agent, so the hardware provides a semaphore register that can be used to
coordinate access to the steering register.  Support for the semaphore
register will be introduced in a future patch.

v2:
 - Use Xe_LPG terminology instead of "MTL 3D" since it's the IP version
   we're matching on now rather than the platform.
 - Don't combine l3bank and mslice masks into a union.  It's not related
   to the other changes here and we might still need both of them on
   some future platform.
 - Separate debug dumping of steering settings to a separate helper
   function.  (Tvrtko)
 - Update debug dumping to include DSS ranges (and future-proof it so
   that any new ranges added on future platforms will also be dumped).
 - Restore MULTICAST bit at the end of rw_with_mcr_steering_fw() if we
   cleared it.  Also force the MULTICAST bit to true at the beginning of
   multicast writes just to be safe.  (Bala)

Bspec: 67788, 67112
Cc: Radhakrishna Sripada <radhakrishna.sripada@intel.com>
Cc: Balasubramani Vivekanandan <balasubramani.vivekanandan@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Balasubramani Vivekanandan <balasubramani.vivekanandan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221014230239.1023689-14-matthew.d.roper@intel.com
---
 drivers/gpu/drm/i915/gt/intel_gt_mcr.c      | 135 ++++++++++++++++++++++++----
 drivers/gpu/drm/i915/gt/intel_gt_regs.h     |   5 ++
 drivers/gpu/drm/i915/gt/intel_gt_types.h    |   1 +
 drivers/gpu/drm/i915/gt/intel_workarounds.c |  33 +++++--
 drivers/gpu/drm/i915/i915_pci.c             |   1 +
 5 files changed, 154 insertions(+), 21 deletions(-)

(limited to 'drivers/gpu/drm/i915/gt/intel_gt_mcr.c')

diff --git a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
index 349074bf365f..23a1ef9659bf 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
@@ -41,6 +41,7 @@ static const char * const intel_steering_types[] = {
 	"MSLICE",
 	"LNCF",
 	"GAM",
+	"DSS",
 	"INSTANCE 0",
 };
 
@@ -99,9 +100,40 @@ static const struct intel_mmio_range pvc_instance0_steering_table[] = {
 	{},
 };
 
+static const struct intel_mmio_range xelpg_instance0_steering_table[] = {
+	{ 0x000B00, 0x000BFF },         /* SQIDI */
+	{ 0x001000, 0x001FFF },         /* SQIDI */
+	{ 0x004000, 0x0048FF },         /* GAM */
+	{ 0x008700, 0x0087FF },         /* SQIDI */
+	{ 0x00B000, 0x00B0FF },         /* NODE */
+	{ 0x00C800, 0x00CFFF },         /* GAM */
+	{ 0x00D880, 0x00D8FF },         /* NODE */
+	{ 0x00DD00, 0x00DDFF },         /* OAAL2 */
+	{},
+};
+
+static const struct intel_mmio_range xelpg_l3bank_steering_table[] = {
+	{ 0x00B100, 0x00B3FF },
+	{},
+};
+
+/* DSS steering is used for SLICE ranges as well */
+static const struct intel_mmio_range xelpg_dss_steering_table[] = {
+	{ 0x005200, 0x0052FF },		/* SLICE */
+	{ 0x005500, 0x007FFF },		/* SLICE */
+	{ 0x008140, 0x00815F },		/* SLICE (0x8140-0x814F), DSS (0x8150-0x815F) */
+	{ 0x0094D0, 0x00955F },		/* SLICE (0x94D0-0x951F), DSS (0x9520-0x955F) */
+	{ 0x009680, 0x0096FF },		/* DSS */
+	{ 0x00D800, 0x00D87F },		/* SLICE */
+	{ 0x00DC00, 0x00DCFF },		/* SLICE */
+	{ 0x00DE80, 0x00E8FF },		/* DSS (0xE000-0xE0FF reserved) */
+};
+
 void intel_gt_mcr_init(struct intel_gt *gt)
 {
 	struct drm_i915_private *i915 = gt->i915;
+	unsigned long fuse;
+	int i;
 
 	/*
 	 * An mslice is unavailable only if both the meml3 for the slice is
@@ -119,7 +151,22 @@ void intel_gt_mcr_init(struct intel_gt *gt)
 			drm_warn(&i915->drm, "mslice mask all zero!\n");
 	}
 
-	if (IS_PONTEVECCHIO(i915)) {
+	if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70) &&
+	    gt->type == GT_PRIMARY) {
+		fuse = REG_FIELD_GET(GT_L3_EXC_MASK,
+				     intel_uncore_read(gt->uncore, XEHP_FUSE4));
+
+		/*
+		 * Despite the register field being named "exclude mask" the
+		 * bits actually represent enabled banks (two banks per bit).
+		 */
+		for_each_set_bit(i, &fuse, 3)
+			gt->info.l3bank_mask |= 0x3 << 2 * i;
+
+		gt->steering_table[INSTANCE0] = xelpg_instance0_steering_table;
+		gt->steering_table[L3BANK] = xelpg_l3bank_steering_table;
+		gt->steering_table[DSS] = xelpg_dss_steering_table;
+	} else if (IS_PONTEVECCHIO(i915)) {
 		gt->steering_table[INSTANCE0] = pvc_instance0_steering_table;
 	} else if (IS_DG2(i915)) {
 		gt->steering_table[MSLICE] = xehpsdv_mslice_steering_table;
@@ -184,7 +231,19 @@ static u32 rw_with_mcr_steering_fw(struct intel_uncore *uncore,
 
 	lockdep_assert_held(&uncore->lock);
 
-	if (GRAPHICS_VER(uncore->i915) >= 11) {
+	if (GRAPHICS_VER_FULL(uncore->i915) >= IP_VER(12, 70)) {
+		/*
+		 * Always leave the hardware in multicast mode when doing reads
+		 * (see comment about Wa_22013088509 below) and only change it
+		 * to unicast mode when doing writes of a specific instance.
+		 *
+		 * No need to save old steering reg value.
+		 */
+		intel_uncore_write_fw(uncore, MTL_MCR_SELECTOR,
+				      REG_FIELD_PREP(MTL_MCR_GROUPID, group) |
+				      REG_FIELD_PREP(MTL_MCR_INSTANCEID, instance) |
+				      (rw_flag == FW_REG_READ) ? GEN11_MCR_MULTICAST : 0);
+	} else if (GRAPHICS_VER(uncore->i915) >= 11) {
 		mcr_mask = GEN11_MCR_SLICE_MASK | GEN11_MCR_SUBSLICE_MASK;
 		mcr_ss = GEN11_MCR_SLICE(group) | GEN11_MCR_SUBSLICE(instance);
 
@@ -202,26 +261,40 @@ static u32 rw_with_mcr_steering_fw(struct intel_uncore *uncore,
 		 */
 		if (rw_flag == FW_REG_WRITE)
 			mcr_mask |= GEN11_MCR_MULTICAST;
+
+		mcr = intel_uncore_read_fw(uncore, GEN8_MCR_SELECTOR);
+		old_mcr = mcr;
+
+		mcr &= ~mcr_mask;
+		mcr |= mcr_ss;
+		intel_uncore_write_fw(uncore, GEN8_MCR_SELECTOR, mcr);
 	} else {
 		mcr_mask = GEN8_MCR_SLICE_MASK | GEN8_MCR_SUBSLICE_MASK;
 		mcr_ss = GEN8_MCR_SLICE(group) | GEN8_MCR_SUBSLICE(instance);
-	}
 
-	old_mcr = mcr = intel_uncore_read_fw(uncore, GEN8_MCR_SELECTOR);
+		mcr = intel_uncore_read_fw(uncore, GEN8_MCR_SELECTOR);
+		old_mcr = mcr;
 
-	mcr &= ~mcr_mask;
-	mcr |= mcr_ss;
-	intel_uncore_write_fw(uncore, GEN8_MCR_SELECTOR, mcr);
+		mcr &= ~mcr_mask;
+		mcr |= mcr_ss;
+		intel_uncore_write_fw(uncore, GEN8_MCR_SELECTOR, mcr);
+	}
 
 	if (rw_flag == FW_REG_READ)
 		val = intel_uncore_read_fw(uncore, mcr_reg_cast(reg));
 	else
 		intel_uncore_write_fw(uncore, mcr_reg_cast(reg), value);
 
-	mcr &= ~mcr_mask;
-	mcr |= old_mcr & mcr_mask;
-
-	intel_uncore_write_fw(uncore, GEN8_MCR_SELECTOR, mcr);
+	/*
+	 * For pre-MTL platforms, we need to restore the old value of the
+	 * steering control register to ensure that implicit steering continues
+	 * to behave as expected.  For MTL and beyond, we need only reinstate
+	 * the 'multicast' bit (and only if we did a write that cleared it).
+	 */
+	if (GRAPHICS_VER_FULL(uncore->i915) >= IP_VER(12, 70) && rw_flag == FW_REG_WRITE)
+		intel_uncore_write_fw(uncore, MTL_MCR_SELECTOR, GEN11_MCR_MULTICAST);
+	else if (GRAPHICS_VER_FULL(uncore->i915) < IP_VER(12, 70))
+		intel_uncore_write_fw(uncore, GEN8_MCR_SELECTOR, old_mcr);
 
 	return val;
 }
@@ -296,6 +369,13 @@ void intel_gt_mcr_unicast_write(struct intel_gt *gt, i915_mcr_reg_t reg, u32 val
 void intel_gt_mcr_multicast_write(struct intel_gt *gt,
 				  i915_mcr_reg_t reg, u32 value)
 {
+	/*
+	 * Ensure we have multicast behavior, just in case some non-i915 agent
+	 * left the hardware in unicast mode.
+	 */
+	if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 70))
+		intel_uncore_write_fw(gt->uncore, MTL_MCR_SELECTOR, GEN11_MCR_MULTICAST);
+
 	intel_uncore_write(gt->uncore, mcr_reg_cast(reg), value);
 }
 
@@ -312,6 +392,13 @@ void intel_gt_mcr_multicast_write(struct intel_gt *gt,
  */
 void intel_gt_mcr_multicast_write_fw(struct intel_gt *gt, i915_mcr_reg_t reg, u32 value)
 {
+	/*
+	 * Ensure we have multicast behavior, just in case some non-i915 agent
+	 * left the hardware in unicast mode.
+	 */
+	if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 70))
+		intel_uncore_write_fw(gt->uncore, MTL_MCR_SELECTOR, GEN11_MCR_MULTICAST);
+
 	intel_uncore_write_fw(gt->uncore, mcr_reg_cast(reg), value);
 }
 
@@ -389,6 +476,8 @@ static void get_nonterminated_steering(struct intel_gt *gt,
 				       enum intel_steering_type type,
 				       u8 *group, u8 *instance)
 {
+	u32 dss;
+
 	switch (type) {
 	case L3BANK:
 		*group = 0;		/* unused */
@@ -412,6 +501,11 @@ static void get_nonterminated_steering(struct intel_gt *gt,
 		*group = IS_DG2(gt->i915) ? 1 : 0;
 		*instance = 0;
 		break;
+	case DSS:
+		dss = intel_sseu_find_first_xehp_dss(&gt->info.sseu, 0, 0);
+		*group = dss / GEN_DSS_PER_GSLICE;
+		*instance = dss % GEN_DSS_PER_GSLICE;
+		break;
 	case INSTANCE0:
 		/*
 		 * There are a lot of MCR types for which instance (0, 0)
@@ -544,11 +638,20 @@ static void report_steering_type(struct drm_printer *p,
 void intel_gt_mcr_report_steering(struct drm_printer *p, struct intel_gt *gt,
 				  bool dump_table)
 {
-	drm_printf(p, "Default steering: group=0x%x, instance=0x%x\n",
-		   gt->default_steering.groupid,
-		   gt->default_steering.instanceid);
-
-	if (IS_PONTEVECCHIO(gt->i915)) {
+	/*
+	 * Starting with MTL we no longer have default steering;
+	 * all ranges are explicitly steered.
+	 */
+	if (GRAPHICS_VER_FULL(gt->i915) < IP_VER(12, 70))
+		drm_printf(p, "Default steering: group=0x%x, instance=0x%x\n",
+			   gt->default_steering.groupid,
+			   gt->default_steering.instanceid);
+
+	if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 70)) {
+		for (int i = 0; i < NUM_STEERING_TYPES; i++)
+			if (gt->steering_table[i])
+				report_steering_type(p, gt, i, dump_table);
+	} else if (IS_PONTEVECCHIO(gt->i915)) {
 		report_steering_type(p, gt, INSTANCE0, dump_table);
 	} else if (HAS_MSLICE_STEERING(gt->i915)) {
 		report_steering_type(p, gt, MSLICE, dump_table);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
index 1116bc3dba51..1c3a46ee876d 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
@@ -56,6 +56,7 @@
 #define FORCEWAKE_ACK_GT_MTL			_MMIO(0xdfc)
 
 #define MCFG_MCR_SELECTOR			_MMIO(0xfd0)
+#define MTL_MCR_SELECTOR			_MMIO(0xfd4)
 #define SF_MCR_SELECTOR				_MMIO(0xfd8)
 #define GEN8_MCR_SELECTOR			_MMIO(0xfdc)
 #define GAM_MCR_SELECTOR			_MMIO(0xfe0)
@@ -68,6 +69,8 @@
 #define   GEN11_MCR_SLICE_MASK			GEN11_MCR_SLICE(0xf)
 #define   GEN11_MCR_SUBSLICE(subslice)		(((subslice) & 0x7) << 24)
 #define   GEN11_MCR_SUBSLICE_MASK		GEN11_MCR_SUBSLICE(0x7)
+#define   MTL_MCR_GROUPID			REG_GENMASK(11, 8)
+#define   MTL_MCR_INSTANCEID			REG_GENMASK(3, 0)
 
 #define IPEIR_I965				_MMIO(0x2064)
 #define IPEHR_I965				_MMIO(0x2068)
@@ -528,6 +531,8 @@
 #define   GEN6_MBCTL_BOOT_FETCH_MECH		(1 << 0)
 
 /* Fuse readout registers for GT */
+#define XEHP_FUSE4				_MMIO(0x9114)
+#define   GT_L3_EXC_MASK			REG_GENMASK(6, 4)
 #define	GEN10_MIRROR_FUSE3			_MMIO(0x9118)
 #define   GEN10_L3BANK_PAIR_COUNT		4
 #define   GEN10_L3BANK_MASK			0x0F
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h
index 30003d68fd51..0bb73d110a84 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h
@@ -60,6 +60,7 @@ enum intel_steering_type {
 	MSLICE,
 	LNCF,
 	GAM,
+	DSS,
 
 	/*
 	 * On some platforms there are multiple types of MCR registers that
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index dadb60e6a58f..711a31935857 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -1128,18 +1128,23 @@ static void __set_mcr_steering(struct i915_wa_list *wal,
 	wa_write_clr_set(wal, steering_reg, mcr_mask, mcr);
 }
 
-static void __add_mcr_wa(struct intel_gt *gt, struct i915_wa_list *wal,
-			 unsigned int slice, unsigned int subslice)
+static void debug_dump_steering(struct intel_gt *gt)
 {
 	struct drm_printer p = drm_debug_printer("MCR Steering:");
 
+	if (drm_debug_enabled(DRM_UT_DRIVER))
+		intel_gt_mcr_report_steering(&p, gt, false);
+}
+
+static void __add_mcr_wa(struct intel_gt *gt, struct i915_wa_list *wal,
+			 unsigned int slice, unsigned int subslice)
+{
 	__set_mcr_steering(wal, GEN8_MCR_SELECTOR, slice, subslice);
 
 	gt->default_steering.groupid = slice;
 	gt->default_steering.instanceid = subslice;
 
-	if (drm_debug_enabled(DRM_UT_DRIVER))
-		intel_gt_mcr_report_steering(&p, gt, false);
+	debug_dump_steering(gt);
 }
 
 static void
@@ -1581,12 +1586,30 @@ pvc_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
 	wa_mcr_write_clr(wal, GEN8_MISCCPCTL, GEN12_DOP_CLOCK_GATE_RENDER_ENABLE);
 }
 
+static void
+xelpg_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
+{
+	/* FIXME: Actual workarounds will be added in future patch(es) */
+
+	/*
+	 * Unlike older platforms, we no longer setup implicit steering here;
+	 * all MCR accesses are explicitly steered.
+	 */
+	debug_dump_steering(gt);
+}
+
 static void
 gt_init_workarounds(struct intel_gt *gt, struct i915_wa_list *wal)
 {
 	struct drm_i915_private *i915 = gt->i915;
 
-	if (IS_PONTEVECCHIO(i915))
+	/* FIXME: Media GT handling will be added in an upcoming patch */
+	if (gt->type == GT_MEDIA)
+		return;
+
+	if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70))
+		xelpg_gt_workarounds_init(gt, wal);
+	else if (IS_PONTEVECCHIO(i915))
 		pvc_gt_workarounds_init(gt, wal);
 	else if (IS_DG2(i915))
 		dg2_gt_workarounds_init(gt, wal);
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index f1344db626f5..4757ad0173da 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -1142,6 +1142,7 @@ static const struct intel_device_info mtl_info = {
 	.display.has_modular_fia = 1,
 	.extra_gt_list = xelpmp_extra_gt,
 	.has_flat_ccs = 0,
+	.has_mslice_steering = 0,
 	.has_snoop = 1,
 	.__runtime.memory_regions = REGION_SMEM | REGION_STOLEN_LMEM,
 	.__runtime.platform_engine_mask = BIT(RCS0) | BIT(BCS0) | BIT(CCS0),
-- 
cgit v1.2.3


From a7ec65fc7e83f342d1392cac69e4f60c7a7cc4ba Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Fri, 14 Oct 2022 16:02:39 -0700
Subject: drm/i915/xelpmp: Add multicast steering for media GT

MTL's media IP (Xe_LPM+) only has a single type of steering ("OAADDRM")
which selects between media slice 0 and media slice 1.  We'll always
steer to media slice 0 unless it is fused off (which is the case when
VD0, VE0, and SFC0 are all reported as unavailable).

Bspec: 67789
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Balasubramani Vivekanandan <balasubramani.vivekanandan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221014230239.1023689-15-matthew.d.roper@intel.com
---
 drivers/gpu/drm/i915/gt/intel_gt_mcr.c      | 18 ++++++++++++++++--
 drivers/gpu/drm/i915/gt/intel_gt_types.h    |  1 +
 drivers/gpu/drm/i915/gt/intel_workarounds.c | 17 +++++++++++++++--
 3 files changed, 32 insertions(+), 4 deletions(-)

(limited to 'drivers/gpu/drm/i915/gt/intel_gt_mcr.c')

diff --git a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
index 23a1ef9659bf..0d2811724b00 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
@@ -42,6 +42,7 @@ static const char * const intel_steering_types[] = {
 	"LNCF",
 	"GAM",
 	"DSS",
+	"OADDRM",
 	"INSTANCE 0",
 };
 
@@ -129,6 +130,11 @@ static const struct intel_mmio_range xelpg_dss_steering_table[] = {
 	{ 0x00DE80, 0x00E8FF },		/* DSS (0xE000-0xE0FF reserved) */
 };
 
+static const struct intel_mmio_range xelpmp_oaddrm_steering_table[] = {
+	{ 0x393200, 0x39323F },
+	{ 0x393400, 0x3934FF },
+};
+
 void intel_gt_mcr_init(struct intel_gt *gt)
 {
 	struct drm_i915_private *i915 = gt->i915;
@@ -151,8 +157,9 @@ void intel_gt_mcr_init(struct intel_gt *gt)
 			drm_warn(&i915->drm, "mslice mask all zero!\n");
 	}
 
-	if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70) &&
-	    gt->type == GT_PRIMARY) {
+	if (MEDIA_VER(i915) >= 13 && gt->type == GT_MEDIA) {
+		gt->steering_table[OADDRM] = xelpmp_oaddrm_steering_table;
+	} else if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70)) {
 		fuse = REG_FIELD_GET(GT_L3_EXC_MASK,
 				     intel_uncore_read(gt->uncore, XEHP_FUSE4));
 
@@ -514,6 +521,13 @@ static void get_nonterminated_steering(struct intel_gt *gt,
 		*group = 0;
 		*instance = 0;
 		break;
+	case OADDRM:
+		if ((VDBOX_MASK(gt) | VEBOX_MASK(gt) | gt->info.sfc_mask) & BIT(0))
+			*group = 0;
+		else
+			*group = 1;
+		*instance = 0;
+		break;
 	default:
 		MISSING_CASE(type);
 		*group = 0;
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h
index 0bb73d110a84..64aa2ba624fc 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h
@@ -61,6 +61,7 @@ enum intel_steering_type {
 	LNCF,
 	GAM,
 	DSS,
+	OADDRM,
 
 	/*
 	 * On some platforms there are multiple types of MCR registers that
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 711a31935857..bae960486872 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -1598,14 +1598,27 @@ xelpg_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
 	debug_dump_steering(gt);
 }
 
+static void
+xelpmp_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
+{
+	/* FIXME: Actual workarounds will be added in future patch(es) */
+
+	debug_dump_steering(gt);
+}
+
 static void
 gt_init_workarounds(struct intel_gt *gt, struct i915_wa_list *wal)
 {
 	struct drm_i915_private *i915 = gt->i915;
 
-	/* FIXME: Media GT handling will be added in an upcoming patch */
-	if (gt->type == GT_MEDIA)
+	if (gt->type == GT_MEDIA) {
+		if (MEDIA_VER(i915) >= 13)
+			xelpmp_gt_workarounds_init(gt, wal);
+		else
+			MISSING_CASE(MEDIA_VER(i915));
+
 		return;
+	}
 
 	if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70))
 		xelpg_gt_workarounds_init(gt, wal);
-- 
cgit v1.2.3


From a47e8a46a7f02ab6e5b225bcaec4fd2c0bec5e6f Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Wed, 19 Oct 2022 15:24:37 -0700
Subject: drm/i915/xelpg: Fix write to MTL_MCR_SELECTOR

A misplaced closing parenthesis caused the groupid/instanceid values to
be considered part of the ternary operator's condition instead of being
OR'd into the resulting value.

Fixes: f32898c94a10 ("drm/i915/xelpg: Add multicast steering")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Arun R Murthy <arun.r.murthy@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221019222437.3035182-1-matthew.d.roper@intel.com
---
 drivers/gpu/drm/i915/gt/intel_gt_mcr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/gpu/drm/i915/gt/intel_gt_mcr.c')

diff --git a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
index 0d2811724b00..46cf2f3d1e8e 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
@@ -249,7 +249,7 @@ static u32 rw_with_mcr_steering_fw(struct intel_uncore *uncore,
 		intel_uncore_write_fw(uncore, MTL_MCR_SELECTOR,
 				      REG_FIELD_PREP(MTL_MCR_GROUPID, group) |
 				      REG_FIELD_PREP(MTL_MCR_INSTANCEID, instance) |
-				      (rw_flag == FW_REG_READ) ? GEN11_MCR_MULTICAST : 0);
+				      (rw_flag == FW_REG_READ ? GEN11_MCR_MULTICAST : 0));
 	} else if (GRAPHICS_VER(uncore->i915) >= 11) {
 		mcr_mask = GEN11_MCR_SLICE_MASK | GEN11_MCR_SUBSLICE_MASK;
 		mcr_ss = GEN11_MCR_SLICE(group) | GEN11_MCR_SUBSLICE(instance);
-- 
cgit v1.2.3


From 876e9047a91839ee5be0ba099036d19883e52ca2 Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Fri, 28 Oct 2022 15:40:22 -0700
Subject: drm/i915/mtl: Add missing steering table terminators

The termination entries were missing for a couple of the recently-added
MTL steering tables.

Fixes: f32898c94a10 ("drm/i915/xelpg: Add multicast steering")
Fixes: a7ec65fc7e83 ("drm/i915/xelpmp: Add multicast steering for media GT")
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221028224022.964997-1-matthew.d.roper@intel.com
---
 drivers/gpu/drm/i915/gt/intel_gt_mcr.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'drivers/gpu/drm/i915/gt/intel_gt_mcr.c')

diff --git a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
index 46cf2f3d1e8e..830edffe88cc 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
@@ -128,11 +128,13 @@ static const struct intel_mmio_range xelpg_dss_steering_table[] = {
 	{ 0x00D800, 0x00D87F },		/* SLICE */
 	{ 0x00DC00, 0x00DCFF },		/* SLICE */
 	{ 0x00DE80, 0x00E8FF },		/* DSS (0xE000-0xE0FF reserved) */
+	{},
 };
 
 static const struct intel_mmio_range xelpmp_oaddrm_steering_table[] = {
 	{ 0x393200, 0x39323F },
 	{ 0x393400, 0x3934FF },
+	{},
 };
 
 void intel_gt_mcr_init(struct intel_gt *gt)
-- 
cgit v1.2.3