Serialize mapping changes with the write semaphore before the PT
spinlock, reject occupied PTEs and roll back only this insertion's
completed prefix on collision or allocation failure. Flush the
invalidations before returning failure; preserve existing mappings.
Only with exclusive rollback may GEM propagate insertion errors and
release temporary backing pages. Keep the writer-lock change, rollback
and all newly introduced error cleanup in one patch. Stable must not
select an error path that frees pages still referenced by partial PTEs,
or a rollback path whose inserted prefix another writer can change.
Probe also stops on stolen-map failure before installing contexts.
Backport this whole transaction and its range-validation prerequisite;
do not split out err_put_pages or weaken its lock contract. Existing
WC/WB cache-attribute error handling is unchanged.
Fixes: 8c8f1c958ab5 ("gma500: introduce the GTT and MMU handling logic")
Fixes: ae012bdc5799 ("drm/gma500: Hook up the MMU")
Signed-off-by: Gabriel Gama <[email protected]>
---
diff --git a/drivers/gpu/drm/gma500/gem.c b/drivers/gpu/drm/gma500/gem.c
index
920847cbc4cd7c8c1fbc4f307f29640e2ac10064..05592a01bae1774dc2e8612b7088e82123bd76ae
100644
--- a/drivers/gpu/drm/gma500/gem.c
+++ b/drivers/gpu/drm/gma500/gem.c
@@ -32,7 +32,7 @@
struct drm_gem_object *obj = &pobj->base;
struct drm_device *dev = obj->dev;
struct drm_psb_private *dev_priv = to_drm_psb_private(dev);
- u32 gpu_base = dev_priv->gtt.gatt_start;
+ u64 gpu_address = (u64)dev_priv->gtt.gatt_start + pobj->offset;
struct page **pages;
unsigned int npages;
int ret;
@@ -43,6 +43,11 @@
if (pobj->in_gart || pobj->stolen)
goto out; /* already mapped */
+
+ if (gpu_address >= BIT_ULL(32)) {
+ ret = -ERANGE;
+ goto err_dma_resv_unlock;
+ }
pages = drm_gem_get_pages(obj);
if (IS_ERR(pages)) {
@@ -52,12 +57,14 @@
npages = obj->size / PAGE_SIZE;
+ ret = psb_mmu_insert_pages(psb_mmu_get_default_pd(dev_priv->mmu),
+ pages, gpu_address, npages, 0, 0,
+ PSB_MMU_CACHED_MEMORY);
+ if (ret)
+ goto err_put_pages;
+
set_pages_array_wc(pages, npages);
-
psb_gtt_insert_pages(dev_priv, &pobj->resource, pages);
- psb_mmu_insert_pages(psb_mmu_get_default_pd(dev_priv->mmu), pages,
- (gpu_base + pobj->offset), npages, 0, 0,
- PSB_MMU_CACHED_MEMORY);
pobj->pages = pages;
@@ -67,6 +74,8 @@
return 0;
+err_put_pages:
+ drm_gem_put_pages(obj, pages, false, false);
err_dma_resv_unlock:
dma_resv_unlock(obj->resv);
return ret;
diff --git a/drivers/gpu/drm/gma500/mmu.c b/drivers/gpu/drm/gma500/mmu.c
index
b5854ed29c28cc33205e02018dc2e1ec505b0137..0d98c78706d238a8da754e2edfe502aeae5e9b0d
100644
--- a/drivers/gpu/drm/gma500/mmu.c
+++ b/drivers/gpu/drm/gma500/mmu.c
@@ -555,6 +555,30 @@
return 0;
}
+/* The caller holds driver->sem for write; only its inserted prefix is undone.
*/
+static void psb_mmu_rollback_pages(struct psb_mmu_pd *pd,
+ unsigned long address, u32 inserted,
+ u32 desired_tile_stride, u32 hw_tile_stride)
+{
+ struct psb_mmu_pt *pt;
+ u64 offset;
+ u32 i;
+
+ for (i = 0; i < inserted; i++) {
+ if (hw_tile_stride)
+ offset = (u64)(i / desired_tile_stride) *
hw_tile_stride +
+ i % desired_tile_stride;
+ else
+ offset = i;
+ pt = psb_mmu_pt_map_lock(pd, address + (offset << PAGE_SHIFT));
+ if (WARN_ON_ONCE(!pt))
+ continue;
+ psb_mmu_invalidate_pte(pt, address + (offset << PAGE_SHIFT));
+ pt->count--;
+ psb_mmu_pt_unmap_unlock(pt);
+ }
+}
+
void psb_mmu_remove_pfn_sequence(struct psb_mmu_pd *pd,
unsigned long address, uint32_t num_pages)
{
@@ -567,7 +591,7 @@
if (!num_pages || psb_mmu_check_range(address, num_pages, 0, 0))
return;
- down_read(&pd->driver->sem);
+ down_write(&pd->driver->sem);
addr = address;
end = addr + ((u64)num_pages << PAGE_SHIFT);
@@ -590,7 +614,7 @@
if (pd->hw_context != -1)
psb_mmu_flush_ptes(pd, f_address, num_pages, 1, 1);
- up_read(&pd->driver->sem);
+ up_write(&pd->driver->sem);
if (pd->hw_context != -1)
psb_mmu_flush(pd->driver);
@@ -624,7 +648,7 @@
add = (u64)desired_tile_stride << PAGE_SHIFT;
row_add = (u64)hw_tile_stride << PAGE_SHIFT;
- down_read(&pd->driver->sem);
+ down_write(&pd->driver->sem);
/* Make sure we only need to flush this processor's cache */
@@ -654,7 +678,7 @@
psb_mmu_flush_ptes(pd, f_address, num_pages,
desired_tile_stride, hw_tile_stride);
- up_read(&pd->driver->sem);
+ up_write(&pd->driver->sem);
if (pd->hw_context != -1)
psb_mmu_flush(pd->driver);
@@ -670,6 +694,7 @@
u64 end;
u64 next;
unsigned long f_address = address;
+ u32 inserted = 0;
int ret;
ret = psb_mmu_check_range(address, num_pages, 0, 0);
@@ -678,7 +703,7 @@
if ((u64)start_pfn + num_pages > BIT_ULL(20))
return -ERANGE;
- down_read(&pd->driver->sem);
+ down_write(&pd->driver->sem);
addr = address;
end = addr + ((u64)num_pages << PAGE_SHIFT);
@@ -691,9 +716,15 @@
goto out;
}
do {
+ if (pt->v[psb_mmu_pt_index(addr)] != pd->invalid_pte) {
+ psb_mmu_pt_unmap_unlock(pt);
+ ret = -EBUSY;
+ goto out;
+ }
pte = psb_mmu_mask_pte(start_pfn++, type);
psb_mmu_set_pte(pt, addr, pte);
pt->count++;
+ inserted++;
} while (addr += PAGE_SIZE, addr < next);
psb_mmu_pt_unmap_unlock(pt);
@@ -701,10 +732,12 @@
ret = 0;
out:
+ if (ret)
+ psb_mmu_rollback_pages(pd, f_address, inserted, 0, 0);
if (pd->hw_context != -1)
psb_mmu_flush_ptes(pd, f_address, num_pages, 1, 1);
- up_read(&pd->driver->sem);
+ up_write(&pd->driver->sem);
if (pd->hw_context != -1)
psb_mmu_flush(pd->driver);
@@ -727,6 +760,7 @@
u64 add;
u64 row_add;
unsigned long f_address = address;
+ u32 inserted = 0;
int ret;
ret = psb_mmu_check_range(address, num_pages,
@@ -748,7 +782,7 @@
add = (u64)desired_tile_stride << PAGE_SHIFT;
row_add = (u64)hw_tile_stride << PAGE_SHIFT;
- down_read(&pd->driver->sem);
+ down_write(&pd->driver->sem);
for (i = 0; i < rows; ++i) {
@@ -763,10 +797,16 @@
goto out;
}
do {
+ if (pt->v[psb_mmu_pt_index(addr)] !=
pd->invalid_pte) {
+ psb_mmu_pt_unmap_unlock(pt);
+ ret = -EBUSY;
+ goto out;
+ }
pte = psb_mmu_mask_pte(page_to_pfn(*pages++),
type);
psb_mmu_set_pte(pt, addr, pte);
pt->count++;
+ inserted++;
} while (addr += PAGE_SIZE, addr < next);
psb_mmu_pt_unmap_unlock(pt);
@@ -777,11 +817,14 @@
ret = 0;
out:
+ if (ret)
+ psb_mmu_rollback_pages(pd, f_address, inserted,
desired_tile_stride,
+ hw_tile_stride);
if (pd->hw_context != -1)
psb_mmu_flush_ptes(pd, f_address, num_pages,
desired_tile_stride, hw_tile_stride);
- up_read(&pd->driver->sem);
+ up_write(&pd->driver->sem);
if (pd->hw_context != -1)
psb_mmu_flush(pd->driver);
diff --git a/drivers/gpu/drm/gma500/mmu.h b/drivers/gpu/drm/gma500/mmu.h
index
e6d39703718c49a7c6345f8787593acd049e0130..4474718aac777632021507ade9435d37144e2f9d
100644
--- a/drivers/gpu/drm/gma500/mmu.h
+++ b/drivers/gpu/drm/gma500/mmu.h
@@ -9,8 +9,9 @@
#define __MMU_H
struct psb_mmu_driver {
- /* protects driver- and pd structures. Always take in read mode
- * before taking the page table spinlock.
+ /*
+ * Protects driver and page-directory structures. Mapping changes take
+ * this semaphore for write, before the page-table spinlock.
*/
struct rw_semaphore sem;
diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c
index
4102b6de69a2c5b15e74a67676190a8f13c6031d..bf94d0a38d0f61daddab1da182f5ebf1e9887c1d
100644
--- a/drivers/gpu/drm/gma500/psb_drv.c
+++ b/drivers/gpu/drm/gma500/psb_drv.c
@@ -354,6 +354,8 @@
dev_priv->stolen_base >> PAGE_SHIFT,
pg->gatt_start,
pg->stolen_size >> PAGE_SHIFT, 0);
+ if (ret)
+ goto out_err;
psb_mmu_set_pd_context(psb_mmu_get_default_pd(dev_priv->mmu), 0);
psb_mmu_set_pd_context(dev_priv->pf_pd, 1);