From: Jérôme Glisse jglisse@redhat.com

People interested in providing uncached or write combined mapping on there architecture need to do the ground work inside there arch specific code to allow to break the linear kernel mapping so that page mapping attributes can be updated, in the meantime force cached mapping for non x86 architecture.

Signed-off-by: Jérôme Glisse jglisse@redhat.com Signed-off-by: Benjamin Herrenschmidt benh@palm4.ozlabs.ibm.com ---

[Minor compile fixes on top of Jerome original v3]

drivers/gpu/drm/radeon/radeon_ttm.c | 2 +- drivers/gpu/drm/ttm/ttm_bo.c | 2 +- drivers/gpu/drm/ttm/ttm_bo_util.c | 2 +- drivers/gpu/drm/ttm/ttm_tt.c | 32 +++++++++++++++++++++----------- include/drm/ttm/ttm_bo_driver.h | 2 +- 5 files changed, 25 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index 72afe82..4dd5060 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -304,7 +304,7 @@ static int radeon_move_vram_ram(struct ttm_buffer_object *bo, return r; }

- r = ttm_tt_set_placement_caching(bo->ttm, tmp_mem.placement); + r = ttm_tt_set_placement_caching(bo->ttm, &tmp_mem.placement); if (unlikely(r)) { goto out_cleanup; } diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 3da89d5..4dc21c3 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -305,7 +305,7 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo, goto out_err; }

- ret = ttm_tt_set_placement_caching(bo->ttm, mem->placement); + ret = ttm_tt_set_placement_caching(bo->ttm, &mem->placement); if (ret) goto out_err;

diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index 30e5d90..e31d48c 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -59,7 +59,7 @@ int ttm_bo_move_ttm(struct ttm_buffer_object *bo, old_mem->mem_type = TTM_PL_SYSTEM; }

- ret = ttm_tt_set_placement_caching(ttm, new_mem->placement); + ret = ttm_tt_set_placement_caching(ttm, &new_mem->placement); if (unlikely(ret != 0)) return ret;

diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c index bf080ab..19ae8ee 100644 --- a/drivers/gpu/drm/ttm/ttm_tt.c +++ b/drivers/gpu/drm/ttm/ttm_tt.c @@ -89,14 +89,6 @@ static inline int ttm_tt_set_page_caching(struct page *p,

return ret; } -#else /* CONFIG_X86 */ -static inline int ttm_tt_set_page_caching(struct page *p, - enum ttm_caching_state c_old, - enum ttm_caching_state c_new) -{ - return 0; -} -#endif /* CONFIG_X86 */

/* * Change caching policy for the linear kernel map @@ -149,19 +141,37 @@ out_err: return ret; }

-int ttm_tt_set_placement_caching(struct ttm_tt *ttm, uint32_t placement) +int ttm_tt_set_placement_caching(struct ttm_tt *ttm, uint32_t *placement) { enum ttm_caching_state state;

- if (placement & TTM_PL_FLAG_WC) + if (*placement & TTM_PL_FLAG_WC) state = tt_wc; - else if (placement & TTM_PL_FLAG_UNCACHED) + else if (*placement & TTM_PL_FLAG_UNCACHED) state = tt_uncached; else state = tt_cached;

return ttm_tt_set_caching(ttm, state); } +#else /* CONFIG_X86 */ +int ttm_tt_set_placement_caching(struct ttm_tt *ttm, uint32_t *placement) +{ + if (*placement & (TTM_PL_TT | TTM_PL_FLAG_SYSTEM)) { + ttm->caching_state = tt_cached; + *placement &= ~TTM_PL_MASK_CACHING; + *placement |= TTM_PL_FLAG_CACHED; + } else { + if (*placement & TTM_PL_FLAG_WC) + ttm->caching_state = tt_wc; + else if (*placement & TTM_PL_FLAG_UNCACHED) + ttm->caching_state = tt_uncached; + else + ttm->caching_state = tt_cached; + } + return 0; +} +#endif /* CONFIG_X86 */ EXPORT_SYMBOL(ttm_tt_set_placement_caching);

void ttm_tt_destroy(struct ttm_tt *ttm) diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 1d9f0f1..cbc5ad2 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -669,7 +669,7 @@ extern int ttm_tt_swapin(struct ttm_tt *ttm); * hit RAM. This function may be very costly as it involves global TLB * and cache flushes and potential page splitting / combining. */ -extern int ttm_tt_set_placement_caching(struct ttm_tt *ttm, uint32_t placement); +extern int ttm_tt_set_placement_caching(struct ttm_tt *ttm, uint32_t *placement); extern int ttm_tt_swapout(struct ttm_tt *ttm, struct file *persistent_swap_storage);