Re: [Intel-gfx] [PATCH 2/8] drm/i915/gt: Refactor _wa_add to reuse wa_index and wa_list_grow

[Lucas De Marchi <lucas.demarchi@intel.com>]

On Tue, Nov 17, 2020 at 10:14:00AM -0800, Umesh Nerlige Ramappa wrote:
>This is quite different and much cleane from my original patch :), so 
>you should be the author. With that, this is
>
>Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>

any chance to get at least patches 1 and 2 applied?

Lucas De Marchi

>
>Thanks,
>Umesh
>
>On Tue, Nov 17, 2020 at 11:01:26AM +0000, Chris Wilson wrote:
>>From: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
>>
>>Switch the search and grow code of the _wa_add to use _wa_index and
>>_wa_list_grow.
>>
>>Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
>>---
>>drivers/gpu/drm/i915/gt/intel_workarounds.c | 124 +++++++++++---------
>>1 file changed, 71 insertions(+), 53 deletions(-)
>>
>>diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
>>index c49083957074..e50c72d2b3f1 100644
>>--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
>>+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
>>@@ -91,20 +91,19 @@ static void wa_init_start(struct i915_wa_list *wal, const char *name, const char
>>
>>#define WA_LIST_CHUNK (1 << 4)
>>
>>-static void wa_init_finish(struct i915_wa_list *wal)
>>+static void wa_trim(struct i915_wa_list *wal, gfp_t gfp)
>>{
>>+	struct i915_wa *list;
>>+
>>	/* Trim unused entries. */
>>-	if (!IS_ALIGNED(wal->count, WA_LIST_CHUNK)) {
>>-		struct i915_wa *list = kmemdup(wal->list,
>>-					       wal->count * sizeof(*list),
>>-					       GFP_KERNEL);
>>-
>>-		if (list) {
>>-			kfree(wal->list);
>>-			wal->list = list;
>>-		}
>>-	}
>>+	list = krealloc(wal->list, wal->count * sizeof(*list), gfp);
>>+	if (list)
>>+		wal->list = list;
>>+}
>>
>>+static void wa_init_finish(struct i915_wa_list *wal)
>>+{
>>+	wa_trim(wal, GFP_KERNEL);
>>	if (!wal->count)
>>		return;
>>
>>@@ -112,57 +111,60 @@ static void wa_init_finish(struct i915_wa_list *wal)
>>			 wal->wa_count, wal->name, wal->engine_name);
>>}
>>
>>-static void _wa_add(struct i915_wa_list *wal, const struct i915_wa *wa)
>>+static int wa_index(struct i915_wa_list *wal, i915_reg_t reg)
>>{
>>-	unsigned int addr = i915_mmio_reg_offset(wa->reg);
>>-	unsigned int start = 0, end = wal->count;
>>-	const unsigned int grow = WA_LIST_CHUNK;
>>-	struct i915_wa *wa_;
>>+	unsigned int addr = i915_mmio_reg_offset(reg);
>>+	int start = 0, end = wal->count;
>>
>>-	GEM_BUG_ON(!is_power_of_2(grow));
>>+	/* addr and wal->list[].reg, both include the R/W flags */
>>+	while (start < end) {
>>+		unsigned int mid = start + (end - start) / 2;
>>
>>-	if (IS_ALIGNED(wal->count, grow)) { /* Either uninitialized or full. */
>>-		struct i915_wa *list;
>>+		if (i915_mmio_reg_offset(wal->list[mid].reg) < addr)
>>+			start = mid + 1;
>>+		else if (i915_mmio_reg_offset(wal->list[mid].reg) > addr)
>>+			end = mid;
>>+		else
>>+			return mid;
>>+	}
>>
>>-		list = kmalloc_array(ALIGN(wal->count + 1, grow), sizeof(*wa),
>>-				     GFP_KERNEL);
>>-		if (!list) {
>>-			DRM_ERROR("No space for workaround init!\n");
>>-			return;
>>-		}
>>+	return -ENOENT;
>>+}
>>
>>-		if (wal->list) {
>>-			memcpy(list, wal->list, sizeof(*wa) * wal->count);
>>-			kfree(wal->list);
>>-		}
>>+static int wa_list_grow(struct i915_wa_list *wal, size_t count, gfp_t gfp)
>>+{
>>+	struct i915_wa *list;
>>
>>-		wal->list = list;
>>-	}
>>+	list = krealloc(wal->list, count * sizeof(*list), gfp);
>>+	if (!list)
>>+		return -ENOMEM;
>>
>>-	while (start < end) {
>>-		unsigned int mid = start + (end - start) / 2;
>>+	wal->list = list;
>>+	return 0;
>>+}
>>
>>-		if (i915_mmio_reg_offset(wal->list[mid].reg) < addr) {
>>-			start = mid + 1;
>>-		} else if (i915_mmio_reg_offset(wal->list[mid].reg) > addr) {
>>-			end = mid;
>>-		} else {
>>-			wa_ = &wal->list[mid];
>>-
>>-			if ((wa->clr | wa_->clr) && !(wa->clr & ~wa_->clr)) {
>>-				DRM_ERROR("Discarding overwritten w/a for reg %04x (clear: %08x, set: %08x)\n",
>>-					  i915_mmio_reg_offset(wa_->reg),
>>-					  wa_->clr, wa_->set);
>>-
>>-				wa_->set &= ~wa->clr;
>>-			}
>>-
>>-			wal->wa_count++;
>>-			wa_->set |= wa->set;
>>-			wa_->clr |= wa->clr;
>>-			wa_->read |= wa->read;
>>-			return;
>>+static void __wa_add(struct i915_wa_list *wal, const struct i915_wa *wa)
>>+{
>>+	struct i915_wa *wa_;
>>+	int index;
>>+
>>+	index = wa_index(wal, wa->reg);
>>+	if (index >= 0) {
>>+		wa_ = &wal->list[index];
>>+
>>+		if ((wa->clr | wa_->clr) && !(wa->clr & ~wa_->clr)) {
>>+			DRM_ERROR("Discarding overwritten w/a for reg %04x (clear: %08x, set: %08x)\n",
>>+				  i915_mmio_reg_offset(wa_->reg),
>>+				  wa_->clr, wa_->set);
>>+
>>+			wa_->set &= ~wa->clr;
>>		}
>>+
>>+		wal->wa_count++;
>>+		wa_->set |= wa->set;
>>+		wa_->clr |= wa->clr;
>>+		wa_->read |= wa->read;
>>+		return;
>>	}
>>
>>	wal->wa_count++;
>>@@ -180,6 +182,22 @@ static void _wa_add(struct i915_wa_list *wal, const struct i915_wa *wa)
>>	}
>>}
>>
>>+static void _wa_add(struct i915_wa_list *wal, const struct i915_wa *wa)
>>+{
>>+	const unsigned int grow = WA_LIST_CHUNK;
>>+
>>+	GEM_BUG_ON(!is_power_of_2(grow));
>>+
>>+	if (IS_ALIGNED(wal->count, grow) && /* Either uninitialized or full. */
>>+	    wa_list_grow(wal, ALIGN(wal->count + 1, grow), GFP_KERNEL)) {
>>+		DRM_ERROR("Unable to store w/a for reg %04x\n",
>>+			  i915_mmio_reg_offset(wa->reg));
>>+		return;
>>+	}
>>+
>>+	__wa_add(wal, wa);
>>+}
>>+
>>static void wa_add(struct i915_wa_list *wal, i915_reg_t reg,
>>		   u32 clear, u32 set, u32 read_mask)
>>{
>>-- 
>>2.20.1
>>
>_______________________________________________
>Intel-gfx mailing list
>Intel-gfx@lists.freedesktop.org
>https://lists.freedesktop.org/mailman/listinfo/intel-gfx
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx