| Message ID | 1393016794-4588-1-git-send-email-benjamin.widawsky@intel.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
On Fri, 2014-02-21 at 13:06 -0800, Ben Widawsky wrote: > With the original PPGTT implementation if the number of PDPs was not a > power of two, the number of pages for the page tables would end up being > rounded up. The code actually had a bug here afaict, but this is a > theoretical bug as I don't believe this can actually occur with the > current code/HW.. > > With the rework of the page table allocations, there is no longer a > distinction between number of page table pages, and number of page > directory entries. To avoid confusion, kill the redundant (and newer) > struct member. > > Cc: Imre Deak <imre.deak@intel.com> > Signed-off-by: Ben Widawsky <ben@bwidawsk.net> Nitpick: keeping num_pt_pages instead would make the code more understandable to me and symmetric with num_pd_pages, but that would've been much more churn. In any case nice simplification, Reviewed-by: Imre Deak <imre.deak@intel.com> > --- > drivers/gpu/drm/i915/i915_debugfs.c | 2 +- > drivers/gpu/drm/i915/i915_drv.h | 3 +-- > drivers/gpu/drm/i915/i915_gem_gtt.c | 14 ++++---------- > 3 files changed, 6 insertions(+), 13 deletions(-) > > diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c > index 509e2e1..e0c42a6 100644 > --- a/drivers/gpu/drm/i915/i915_debugfs.c > +++ b/drivers/gpu/drm/i915/i915_debugfs.c > @@ -1757,7 +1757,7 @@ static void gen8_ppgtt_info(struct seq_file *m, struct drm_device *dev) > return; > > seq_printf(m, "Page directories: %d\n", ppgtt->num_pd_pages); > - seq_printf(m, "Page tables: %d\n", ppgtt->num_pt_pages); > + seq_printf(m, "Page tables: %d\n", ppgtt->num_pd_entries); > for_each_ring(ring, dev_priv, unused) { > seq_printf(m, "%s\n", ring->name); > for (i = 0; i < 4; i++) { > diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h > index 2f29558..a9f1cae 100644 > --- a/drivers/gpu/drm/i915/i915_drv.h > +++ b/drivers/gpu/drm/i915/i915_drv.h > @@ -698,13 +698,12 @@ struct i915_hw_ppgtt { > struct kref ref; > struct drm_mm_node node; > unsigned num_pd_entries; > + unsigned num_pd_pages; /* gen8+ */ > union { > struct page **pt_pages; > struct page **gen8_pt_pages[GEN8_LEGACY_PDPS]; > }; > struct page *pd_pages; > - int num_pd_pages; > - int num_pt_pages; > union { > uint32_t pd_offset; > dma_addr_t pd_dma_addr[GEN8_LEGACY_PDPS]; > diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c > index 6c03929..bd815d7 100644 > --- a/drivers/gpu/drm/i915/i915_gem_gtt.c > +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c > @@ -433,7 +433,6 @@ static int gen8_ppgtt_allocate_page_tables(struct i915_hw_ppgtt *ppgtt, > const int max_pdp) > { > struct page **pt_pages[GEN8_LEGACY_PDPS]; > - const int num_pt_pages = GEN8_PDES_PER_PAGE * max_pdp; > int i, ret; > > for (i = 0; i < max_pdp; i++) { > @@ -450,8 +449,6 @@ static int gen8_ppgtt_allocate_page_tables(struct i915_hw_ppgtt *ppgtt, > for (i = 0; i < max_pdp; i++) > ppgtt->gen8_pt_pages[i] = pt_pages[i]; > > - ppgtt->num_pt_pages = 1 << get_order(num_pt_pages << PAGE_SHIFT); > - > return 0; > > unwind_out: > @@ -618,18 +615,15 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size) > ppgtt->base.insert_entries = gen8_ppgtt_insert_entries; > ppgtt->base.cleanup = gen8_ppgtt_cleanup; > ppgtt->base.start = 0; > - ppgtt->base.total = ppgtt->num_pt_pages * GEN8_PTES_PER_PAGE * PAGE_SIZE; > + ppgtt->base.total = ppgtt->num_pd_entries * GEN8_PTES_PER_PAGE * PAGE_SIZE; > > - ppgtt->base.clear_range(&ppgtt->base, 0, > - ppgtt->num_pd_entries * GEN8_PTES_PER_PAGE * PAGE_SIZE, > - true); > + ppgtt->base.clear_range(&ppgtt->base, 0, ppgtt->base.total, true); > > DRM_DEBUG_DRIVER("Allocated %d pages for page directories (%d wasted)\n", > ppgtt->num_pd_pages, ppgtt->num_pd_pages - max_pdp); > DRM_DEBUG_DRIVER("Allocated %d pages for page tables (%lld wasted)\n", > - ppgtt->num_pt_pages, > - (ppgtt->num_pt_pages - min_pt_pages) + > - size % (1<<30)); > + ppgtt->num_pd_entries, > + (ppgtt->num_pd_entries - min_pt_pages) + size % (1<<30)); > return 0; > > bail:
On Mon, Feb 24, 2014 at 07:17:02PM +0200, Imre Deak wrote: > On Fri, 2014-02-21 at 13:06 -0800, Ben Widawsky wrote: > > With the original PPGTT implementation if the number of PDPs was not a > > power of two, the number of pages for the page tables would end up being > > rounded up. The code actually had a bug here afaict, but this is a > > theoretical bug as I don't believe this can actually occur with the > > current code/HW.. > > > > With the rework of the page table allocations, there is no longer a > > distinction between number of page table pages, and number of page > > directory entries. To avoid confusion, kill the redundant (and newer) > > struct member. > > > > Cc: Imre Deak <imre.deak@intel.com> > > Signed-off-by: Ben Widawsky <ben@bwidawsk.net> > > Nitpick: keeping num_pt_pages instead would make the code more > understandable to me and symmetric with num_pd_pages, but that would've > been much more churn. In any case nice simplification, > > Reviewed-by: Imre Deak <imre.deak@intel.com> All merged to dinq, thanks for patches&review. -Daniel
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 509e2e1..e0c42a6 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -1757,7 +1757,7 @@ static void gen8_ppgtt_info(struct seq_file *m, struct drm_device *dev) return; seq_printf(m, "Page directories: %d\n", ppgtt->num_pd_pages); - seq_printf(m, "Page tables: %d\n", ppgtt->num_pt_pages); + seq_printf(m, "Page tables: %d\n", ppgtt->num_pd_entries); for_each_ring(ring, dev_priv, unused) { seq_printf(m, "%s\n", ring->name); for (i = 0; i < 4; i++) { diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 2f29558..a9f1cae 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -698,13 +698,12 @@ struct i915_hw_ppgtt { struct kref ref; struct drm_mm_node node; unsigned num_pd_entries; + unsigned num_pd_pages; /* gen8+ */ union { struct page **pt_pages; struct page **gen8_pt_pages[GEN8_LEGACY_PDPS]; }; struct page *pd_pages; - int num_pd_pages; - int num_pt_pages; union { uint32_t pd_offset; dma_addr_t pd_dma_addr[GEN8_LEGACY_PDPS]; diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 6c03929..bd815d7 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -433,7 +433,6 @@ static int gen8_ppgtt_allocate_page_tables(struct i915_hw_ppgtt *ppgtt, const int max_pdp) { struct page **pt_pages[GEN8_LEGACY_PDPS]; - const int num_pt_pages = GEN8_PDES_PER_PAGE * max_pdp; int i, ret; for (i = 0; i < max_pdp; i++) { @@ -450,8 +449,6 @@ static int gen8_ppgtt_allocate_page_tables(struct i915_hw_ppgtt *ppgtt, for (i = 0; i < max_pdp; i++) ppgtt->gen8_pt_pages[i] = pt_pages[i]; - ppgtt->num_pt_pages = 1 << get_order(num_pt_pages << PAGE_SHIFT); - return 0; unwind_out: @@ -618,18 +615,15 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size) ppgtt->base.insert_entries = gen8_ppgtt_insert_entries; ppgtt->base.cleanup = gen8_ppgtt_cleanup; ppgtt->base.start = 0; - ppgtt->base.total = ppgtt->num_pt_pages * GEN8_PTES_PER_PAGE * PAGE_SIZE; + ppgtt->base.total = ppgtt->num_pd_entries * GEN8_PTES_PER_PAGE * PAGE_SIZE; - ppgtt->base.clear_range(&ppgtt->base, 0, - ppgtt->num_pd_entries * GEN8_PTES_PER_PAGE * PAGE_SIZE, - true); + ppgtt->base.clear_range(&ppgtt->base, 0, ppgtt->base.total, true); DRM_DEBUG_DRIVER("Allocated %d pages for page directories (%d wasted)\n", ppgtt->num_pd_pages, ppgtt->num_pd_pages - max_pdp); DRM_DEBUG_DRIVER("Allocated %d pages for page tables (%lld wasted)\n", - ppgtt->num_pt_pages, - (ppgtt->num_pt_pages - min_pt_pages) + - size % (1<<30)); + ppgtt->num_pd_entries, + (ppgtt->num_pd_entries - min_pt_pages) + size % (1<<30)); return 0; bail:
With the original PPGTT implementation if the number of PDPs was not a power of two, the number of pages for the page tables would end up being rounded up. The code actually had a bug here afaict, but this is a theoretical bug as I don't believe this can actually occur with the current code/HW.. With the rework of the page table allocations, there is no longer a distinction between number of page table pages, and number of page directory entries. To avoid confusion, kill the redundant (and newer) struct member. Cc: Imre Deak <imre.deak@intel.com> Signed-off-by: Ben Widawsky <ben@bwidawsk.net> --- drivers/gpu/drm/i915/i915_debugfs.c | 2 +- drivers/gpu/drm/i915/i915_drv.h | 3 +-- drivers/gpu/drm/i915/i915_gem_gtt.c | 14 ++++---------- 3 files changed, 6 insertions(+), 13 deletions(-)