diff mbox

[1/2] drm/i915: Make PTE valid encoding optional

Message ID 1381940302-1920-1-git-send-email-benjamin.widawsky@intel.com (mailing list archive)
State New, archived
Headers show

Commit Message

Ben Widawsky Oct. 16, 2013, 4:18 p.m. UTC 
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
---
 drivers/gpu/drm/i915/i915_drv.h     |  3 ++-
 drivers/gpu/drm/i915/i915_gem_gtt.c | 35 ++++++++++++++++++++---------------
 2 files changed, 22 insertions(+), 16 deletions(-)

Comments

Daniel Vetter Oct. 18, 2013, 1:40 p.m. UTC | #1 
On Wed, Oct 16, 2013 at 09:18:21AM -0700, Ben Widawsky wrote:

Empty commit messages aren't cool, especially for a fix this late in the
-rc cycle. Patches simply need to be justified. I've filled something in
when merging.

> Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
> ---
>  drivers/gpu/drm/i915/i915_drv.h     |  3 ++-
>  drivers/gpu/drm/i915/i915_gem_gtt.c | 35 ++++++++++++++++++++---------------
>  2 files changed, 22 insertions(+), 16 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index 6106d3d..0cbeb0e 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -517,7 +517,8 @@ struct i915_address_space {
>  
>  	/* FIXME: Need a more generic return type */
>  	gen6_gtt_pte_t (*pte_encode)(dma_addr_t addr,
> -				     enum i915_cache_level level);
> +				     enum i915_cache_level level,
> +				     bool valid); /* Create a valid PTE */
>  	void (*clear_range)(struct i915_address_space *vm,
>  			    unsigned int first_entry,
>  			    unsigned int num_entries);
> diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
> index e999496..81dce29 100644
> --- a/drivers/gpu/drm/i915/i915_gem_gtt.c
> +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
> @@ -58,9 +58,10 @@
>  #define HSW_WT_ELLC_LLC_AGE0		HSW_CACHEABILITY_CONTROL(0x6)
>  
>  static gen6_gtt_pte_t snb_pte_encode(dma_addr_t addr,
> -				     enum i915_cache_level level)
> +				     enum i915_cache_level level,
> +				     bool valid)
>  {
> -	gen6_gtt_pte_t pte = GEN6_PTE_VALID;
> +	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
>  	pte |= GEN6_PTE_ADDR_ENCODE(addr);
>  
>  	switch (level) {
> @@ -79,9 +80,10 @@ static gen6_gtt_pte_t snb_pte_encode(dma_addr_t addr,
>  }
>  
>  static gen6_gtt_pte_t ivb_pte_encode(dma_addr_t addr,
> -				     enum i915_cache_level level)
> +				     enum i915_cache_level level,
> +				     bool valid)
>  {
> -	gen6_gtt_pte_t pte = GEN6_PTE_VALID;
> +	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
>  	pte |= GEN6_PTE_ADDR_ENCODE(addr);
>  
>  	switch (level) {
> @@ -105,9 +107,10 @@ static gen6_gtt_pte_t ivb_pte_encode(dma_addr_t addr,
>  #define BYT_PTE_SNOOPED_BY_CPU_CACHES	(1 << 2)
>  
>  static gen6_gtt_pte_t byt_pte_encode(dma_addr_t addr,
> -				     enum i915_cache_level level)
> +				     enum i915_cache_level level,
> +				     bool valid)
>  {
> -	gen6_gtt_pte_t pte = GEN6_PTE_VALID;
> +	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
>  	pte |= GEN6_PTE_ADDR_ENCODE(addr);
>  
>  	/* Mark the page as writeable.  Other platforms don't have a
> @@ -122,9 +125,10 @@ static gen6_gtt_pte_t byt_pte_encode(dma_addr_t addr,
>  }
>  
>  static gen6_gtt_pte_t hsw_pte_encode(dma_addr_t addr,
> -				     enum i915_cache_level level)
> +				     enum i915_cache_level level,
> +				     bool valid)
>  {
> -	gen6_gtt_pte_t pte = GEN6_PTE_VALID;
> +	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
>  	pte |= HSW_PTE_ADDR_ENCODE(addr);
>  
>  	if (level != I915_CACHE_NONE)
> @@ -134,9 +138,10 @@ static gen6_gtt_pte_t hsw_pte_encode(dma_addr_t addr,
>  }
>  
>  static gen6_gtt_pte_t iris_pte_encode(dma_addr_t addr,
> -				      enum i915_cache_level level)
> +				      enum i915_cache_level level,
> +				      bool valid)
>  {
> -	gen6_gtt_pte_t pte = GEN6_PTE_VALID;
> +	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
>  	pte |= HSW_PTE_ADDR_ENCODE(addr);
>  
>  	switch (level) {
> @@ -245,7 +250,7 @@ static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
>  	unsigned first_pte = first_entry % I915_PPGTT_PT_ENTRIES;
>  	unsigned last_pte, i;
>  
> -	scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC);
> +	scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC, true);
>  
>  	while (num_entries) {
>  		last_pte = first_pte + num_entries;
> @@ -282,7 +287,7 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
>  		dma_addr_t page_addr;
>  
>  		page_addr = sg_page_iter_dma_address(&sg_iter);
> -		pt_vaddr[act_pte] = vm->pte_encode(page_addr, cache_level);
> +		pt_vaddr[act_pte] = vm->pte_encode(page_addr, cache_level, true);
>  		if (++act_pte == I915_PPGTT_PT_ENTRIES) {
>  			kunmap_atomic(pt_vaddr);
>  			act_pt++;
> @@ -536,7 +541,7 @@ static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
>  
>  	for_each_sg_page(st->sgl, &sg_iter, st->nents, 0) {
>  		addr = sg_page_iter_dma_address(&sg_iter);
> -		iowrite32(vm->pte_encode(addr, level), &gtt_entries[i]);
> +		iowrite32(vm->pte_encode(addr, level, true), &gtt_entries[i]);
>  		i++;
>  	}
>  
> @@ -548,7 +553,7 @@ static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
>  	 */
>  	if (i != 0)
>  		WARN_ON(readl(&gtt_entries[i-1]) !=
> -			vm->pte_encode(addr, level));
> +			vm->pte_encode(addr, level, true));
>  
>  	/* This next bit makes the above posting read even more important. We
>  	 * want to flush the TLBs only after we're certain all the PTE updates
> @@ -573,7 +578,7 @@ static void gen6_ggtt_clear_range(struct i915_address_space *vm,
>  		 first_entry, num_entries, max_entries))
>  		num_entries = max_entries;
>  
> -	scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC);
> +	scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC, true);
>  	for (i = 0; i < num_entries; i++)
>  		iowrite32(scratch_pte, &gtt_base[i]);
>  	readl(gtt_base);
> -- 
> 1.8.4
> 
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/intel-gfx
diff mbox

Patch

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 6106d3d..0cbeb0e 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -517,7 +517,8 @@  struct i915_address_space {
 
 	/* FIXME: Need a more generic return type */
 	gen6_gtt_pte_t (*pte_encode)(dma_addr_t addr,
-				     enum i915_cache_level level);
+				     enum i915_cache_level level,
+				     bool valid); /* Create a valid PTE */
 	void (*clear_range)(struct i915_address_space *vm,
 			    unsigned int first_entry,
 			    unsigned int num_entries);
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index e999496..81dce29 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -58,9 +58,10 @@ 
 #define HSW_WT_ELLC_LLC_AGE0		HSW_CACHEABILITY_CONTROL(0x6)
 
 static gen6_gtt_pte_t snb_pte_encode(dma_addr_t addr,
-				     enum i915_cache_level level)
+				     enum i915_cache_level level,
+				     bool valid)
 {
-	gen6_gtt_pte_t pte = GEN6_PTE_VALID;
+	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
 	pte |= GEN6_PTE_ADDR_ENCODE(addr);
 
 	switch (level) {
@@ -79,9 +80,10 @@  static gen6_gtt_pte_t snb_pte_encode(dma_addr_t addr,
 }
 
 static gen6_gtt_pte_t ivb_pte_encode(dma_addr_t addr,
-				     enum i915_cache_level level)
+				     enum i915_cache_level level,
+				     bool valid)
 {
-	gen6_gtt_pte_t pte = GEN6_PTE_VALID;
+	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
 	pte |= GEN6_PTE_ADDR_ENCODE(addr);
 
 	switch (level) {
@@ -105,9 +107,10 @@  static gen6_gtt_pte_t ivb_pte_encode(dma_addr_t addr,
 #define BYT_PTE_SNOOPED_BY_CPU_CACHES	(1 << 2)
 
 static gen6_gtt_pte_t byt_pte_encode(dma_addr_t addr,
-				     enum i915_cache_level level)
+				     enum i915_cache_level level,
+				     bool valid)
 {
-	gen6_gtt_pte_t pte = GEN6_PTE_VALID;
+	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
 	pte |= GEN6_PTE_ADDR_ENCODE(addr);
 
 	/* Mark the page as writeable.  Other platforms don't have a
@@ -122,9 +125,10 @@  static gen6_gtt_pte_t byt_pte_encode(dma_addr_t addr,
 }
 
 static gen6_gtt_pte_t hsw_pte_encode(dma_addr_t addr,
-				     enum i915_cache_level level)
+				     enum i915_cache_level level,
+				     bool valid)
 {
-	gen6_gtt_pte_t pte = GEN6_PTE_VALID;
+	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
 	pte |= HSW_PTE_ADDR_ENCODE(addr);
 
 	if (level != I915_CACHE_NONE)
@@ -134,9 +138,10 @@  static gen6_gtt_pte_t hsw_pte_encode(dma_addr_t addr,
 }
 
 static gen6_gtt_pte_t iris_pte_encode(dma_addr_t addr,
-				      enum i915_cache_level level)
+				      enum i915_cache_level level,
+				      bool valid)
 {
-	gen6_gtt_pte_t pte = GEN6_PTE_VALID;
+	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
 	pte |= HSW_PTE_ADDR_ENCODE(addr);
 
 	switch (level) {
@@ -245,7 +250,7 @@  static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
 	unsigned first_pte = first_entry % I915_PPGTT_PT_ENTRIES;
 	unsigned last_pte, i;
 
-	scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC);
+	scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC, true);
 
 	while (num_entries) {
 		last_pte = first_pte + num_entries;
@@ -282,7 +287,7 @@  static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
 		dma_addr_t page_addr;
 
 		page_addr = sg_page_iter_dma_address(&sg_iter);
-		pt_vaddr[act_pte] = vm->pte_encode(page_addr, cache_level);
+		pt_vaddr[act_pte] = vm->pte_encode(page_addr, cache_level, true);
 		if (++act_pte == I915_PPGTT_PT_ENTRIES) {
 			kunmap_atomic(pt_vaddr);
 			act_pt++;
@@ -536,7 +541,7 @@  static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
 
 	for_each_sg_page(st->sgl, &sg_iter, st->nents, 0) {
 		addr = sg_page_iter_dma_address(&sg_iter);
-		iowrite32(vm->pte_encode(addr, level), &gtt_entries[i]);
+		iowrite32(vm->pte_encode(addr, level, true), &gtt_entries[i]);
 		i++;
 	}
 
@@ -548,7 +553,7 @@  static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
 	 */
 	if (i != 0)
 		WARN_ON(readl(&gtt_entries[i-1]) !=
-			vm->pte_encode(addr, level));
+			vm->pte_encode(addr, level, true));
 
 	/* This next bit makes the above posting read even more important. We
 	 * want to flush the TLBs only after we're certain all the PTE updates
@@ -573,7 +578,7 @@  static void gen6_ggtt_clear_range(struct i915_address_space *vm,
 		 first_entry, num_entries, max_entries))
 		num_entries = max_entries;
 
-	scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC);
+	scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC, true);
 	for (i = 0; i < num_entries; i++)
 		iowrite32(scratch_pte, &gtt_base[i]);
 	readl(gtt_base);