#define VM_SEALED_SYSMAP VM_NONE
#endif
+/*
+ * DMA mapping IDs for page_pool
+ *
+ * When DMA-mapping a page, page_pool allocates an ID (from an xarray) and
+ * stashes it in the upper bits of page->pp_magic. We always want to be able to
+ * unambiguously identify page pool pages (using page_pool_page_is_pp()). Non-PP
+ * pages can have arbitrary kernel pointers stored in the same field as pp_magic
+ * (since it overlaps with page->lru.next), so we must ensure that we cannot
+ * mistake a valid kernel pointer with any of the values we write into this
+ * field.
+ *
+ * On architectures that set POISON_POINTER_DELTA, this is already ensured,
+ * since this value becomes part of PP_SIGNATURE; meaning we can just use the
+ * space between the PP_SIGNATURE value (without POISON_POINTER_DELTA), and the
+ * lowest bits of POISON_POINTER_DELTA. On arches where POISON_POINTER_DELTA is
+ * 0, we make sure that we leave the two topmost bits empty, as that guarantees
+ * we won't mistake a valid kernel pointer for a value we set, regardless of the
+ * VMSPLIT setting.
+ *
+ * Altogether, this means that the number of bits available is constrained by
+ * the size of an unsigned long (at the upper end, subtracting two bits per the
+ * above), and the definition of PP_SIGNATURE (with or without
+ * POISON_POINTER_DELTA).
+ */
+#define PP_DMA_INDEX_SHIFT (1 + __fls(PP_SIGNATURE - POISON_POINTER_DELTA))
+#if POISON_POINTER_DELTA > 0
+/* PP_SIGNATURE includes POISON_POINTER_DELTA, so limit the size of the DMA
+ * index to not overlap with that if set
+ */
+#define PP_DMA_INDEX_BITS MIN(32, __ffs(POISON_POINTER_DELTA) - PP_DMA_INDEX_SHIFT)
+#else
+/* Always leave out the topmost two; see above. */
+#define PP_DMA_INDEX_BITS MIN(32, BITS_PER_LONG - PP_DMA_INDEX_SHIFT - 2)
+#endif
+
+#define PP_DMA_INDEX_MASK GENMASK(PP_DMA_INDEX_BITS + PP_DMA_INDEX_SHIFT - 1, \
+ PP_DMA_INDEX_SHIFT)
+
/* Mask used for checking in page_pool_page_is_pp() below. page->pp_magic is
* OR'ed with PP_SIGNATURE after the allocation in order to preserve bit 0 for
- * the head page of compound page and bit 1 for pfmemalloc page.
- * page_is_pfmemalloc() is checked in __page_pool_put_page() to avoid recycling
- * the pfmemalloc page.
+ * the head page of compound page and bit 1 for pfmemalloc page, as well as the
+ * bits used for the DMA index. page_is_pfmemalloc() is checked in
+ * __page_pool_put_page() to avoid recycling the pfmemalloc page.
*/
-#define PP_MAGIC_MASK ~0x3UL
+#define PP_MAGIC_MASK ~(PP_DMA_INDEX_MASK | 0x3UL)
#ifdef CONFIG_PAGE_POOL
static inline bool page_pool_page_is_pp(struct page *page)
/* Driver calling page_pool_create() also call page_pool_destroy() */
refcount_set(&pool->user_cnt, 1);
- if (pool->dma_map)
- get_device(pool->p.dev);
+ xa_init_flags(&pool->dma_mapped, XA_FLAGS_ALLOC1);
if (pool->slow.flags & PP_FLAG_ALLOW_UNREADABLE_NETMEM) {
netdev_assert_locked(pool->slow.netdev);
static void page_pool_uninit(struct page_pool *pool)
{
ptr_ring_cleanup(&pool->ring, NULL);
-
- if (pool->dma_map)
- put_device(pool->p.dev);
+ xa_destroy(&pool->dma_mapped);
#ifdef CONFIG_PAGE_POOL_STATS
if (!pool->system)
netmem_ref netmem,
u32 dma_sync_size)
{
- if (pool->dma_sync && dma_dev_need_sync(pool->p.dev))
- __page_pool_dma_sync_for_device(pool, netmem, dma_sync_size);
+ if (pool->dma_sync && dma_dev_need_sync(pool->p.dev)) {
+ rcu_read_lock();
+ /* re-check under rcu_read_lock() to sync with page_pool_scrub() */
+ if (pool->dma_sync)
+ __page_pool_dma_sync_for_device(pool, netmem,
+ dma_sync_size);
+ rcu_read_unlock();
+ }
}
-static bool page_pool_dma_map(struct page_pool *pool, netmem_ref netmem)
+static bool page_pool_dma_map(struct page_pool *pool, netmem_ref netmem, gfp_t gfp)
{
dma_addr_t dma;
+ int err;
+ u32 id;
/* Setup DMA mapping: use 'struct page' area for storing DMA-addr
* since dma_addr_t can be either 32 or 64 bits and does not always fit
if (dma_mapping_error(pool->p.dev, dma))
return false;
- if (page_pool_set_dma_addr_netmem(netmem, dma))
+ if (page_pool_set_dma_addr_netmem(netmem, dma)) {
+ WARN_ONCE(1, "unexpected DMA address, please report to netdev@");
goto unmap_failed;
+ }
+
+ if (in_softirq())
+ err = xa_alloc(&pool->dma_mapped, &id, netmem_to_page(netmem),
+ PP_DMA_INDEX_LIMIT, gfp);
+ else
+ err = xa_alloc_bh(&pool->dma_mapped, &id, netmem_to_page(netmem),
+ PP_DMA_INDEX_LIMIT, gfp);
+ if (err) {
+ WARN_ONCE(err != -ENOMEM, "couldn't track DMA mapping, please report to netdev@");
+ goto unset_failed;
+ }
+ netmem_set_dma_index(netmem, id);
page_pool_dma_sync_for_device(pool, netmem, pool->p.max_len);
return true;
+unset_failed:
+ page_pool_set_dma_addr_netmem(netmem, 0);
unmap_failed:
- WARN_ONCE(1, "unexpected DMA address, please report to netdev@");
dma_unmap_page_attrs(pool->p.dev, dma,
PAGE_SIZE << pool->p.order, pool->p.dma_dir,
DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING);
if (unlikely(!page))
return NULL;
- if (pool->dma_map && unlikely(!page_pool_dma_map(pool, page_to_netmem(page)))) {
+ if (pool->dma_map && unlikely(!page_pool_dma_map(pool, page_to_netmem(page), gfp))) {
put_page(page);
return NULL;
}
*/
for (i = 0; i < nr_pages; i++) {
netmem = pool->alloc.cache[i];
- if (dma_map && unlikely(!page_pool_dma_map(pool, netmem))) {
+ if (dma_map && unlikely(!page_pool_dma_map(pool, netmem, gfp))) {
put_page(netmem_to_page(netmem));
continue;
}
static __always_inline void __page_pool_release_page_dma(struct page_pool *pool,
netmem_ref netmem)
{
+ struct page *old, *page = netmem_to_page(netmem);
+ unsigned long id;
dma_addr_t dma;
if (!pool->dma_map)
*/
return;
+ id = netmem_get_dma_index(netmem);
+ if (!id)
+ return;
+
+ if (in_softirq())
+ old = xa_cmpxchg(&pool->dma_mapped, id, page, NULL, 0);
+ else
+ old = xa_cmpxchg_bh(&pool->dma_mapped, id, page, NULL, 0);
+ if (old != page)
+ return;
+
dma = page_pool_get_dma_addr_netmem(netmem);
/* When page is unmapped, it cannot be returned to our pool */
PAGE_SIZE << pool->p.order, pool->p.dma_dir,
DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING);
page_pool_set_dma_addr_netmem(netmem, 0);
+ netmem_set_dma_index(netmem, 0);
}
/* Disconnects a page (from a page_pool). API users can have a need
static void page_pool_scrub(struct page_pool *pool)
{
+ unsigned long id;
+ void *ptr;
+
page_pool_empty_alloc_cache_once(pool);
- pool->destroy_cnt++;
+ if (!pool->destroy_cnt++ && pool->dma_map) {
+ if (pool->dma_sync) {
+ /* Disable page_pool_dma_sync_for_device() */
+ pool->dma_sync = false;
+
+ /* Make sure all concurrent returns that may see the old
+ * value of dma_sync (and thus perform a sync) have
+ * finished before doing the unmapping below. Skip the
+ * wait if the device doesn't actually need syncing, or
+ * if there are no outstanding mapped pages.
+ */
+ if (dma_dev_need_sync(pool->p.dev) &&
+ !xa_empty(&pool->dma_mapped))
+ synchronize_net();
+ }
+
+ xa_for_each(&pool->dma_mapped, id, ptr)
+ __page_pool_release_page_dma(pool, page_to_netmem(ptr));
+ }
/* No more consumers should exist, but producers could still
* be in-flight.
projects / thirdparty / linux.git / commitdiff
