* We can't use an array for xlt_emergency_page because dma_map_single doesn't
* work on kernel modules memory
*/
-unsigned long xlt_emergency_page;
+void *xlt_emergency_page;
static DEFINE_MUTEX(xlt_emergency_page_mutex);
enum {
MLX5_UMR_MTT_ALIGNMENT)
#define MLX5_SPARE_UMR_CHUNK 0x10000
-static unsigned long mlx5_ib_get_xlt_emergency_page(void)
+/*
+ * Allocate a temporary buffer to hold the per-page information to transfer to
+ * HW. For efficiency this should be as large as it can be, but buffer
+ * allocation failure is not allowed, so try smaller sizes.
+ */
+static void *mlx5_ib_alloc_xlt(size_t *nents, size_t ent_size, gfp_t gfp_mask)
{
+ const size_t xlt_chunk_align =
+ MLX5_UMR_MTT_ALIGNMENT / sizeof(ent_size);
+ size_t size;
+ void *res = NULL;
+
+ static_assert(PAGE_SIZE % MLX5_UMR_MTT_ALIGNMENT == 0);
+
+ /*
+ * MLX5_IB_UPD_XLT_ATOMIC doesn't signal an atomic context just that the
+ * allocation can't trigger any kind of reclaim.
+ */
+ might_sleep();
+
+ gfp_mask |= __GFP_ZERO;
+
+ /*
+ * If the system already has a suitable high order page then just use
+ * that, but don't try hard to create one. This max is about 1M, so a
+ * free x86 huge page will satisfy it.
+ */
+ size = min_t(size_t, ent_size * ALIGN(*nents, xlt_chunk_align),
+ MLX5_MAX_UMR_CHUNK);
+ *nents = size / ent_size;
+ res = (void *)__get_free_pages(gfp_mask | __GFP_NOWARN,
+ get_order(size));
+ if (res)
+ return res;
+
+ if (size > MLX5_SPARE_UMR_CHUNK) {
+ size = MLX5_SPARE_UMR_CHUNK;
+ *nents = get_order(size) / ent_size;
+ res = (void *)__get_free_pages(gfp_mask | __GFP_NOWARN,
+ get_order(size));
+ if (res)
+ return res;
+ }
+
+ *nents = PAGE_SIZE / ent_size;
+ res = (void *)__get_free_page(gfp_mask);
+ if (res)
+ return res;
+
mutex_lock(&xlt_emergency_page_mutex);
+ memset(xlt_emergency_page, 0, PAGE_SIZE);
return xlt_emergency_page;
}
-static void mlx5_ib_put_xlt_emergency_page(void)
+static void mlx5_ib_free_xlt(void *xlt, size_t length)
+{
+ if (xlt == xlt_emergency_page) {
+ mutex_unlock(&xlt_emergency_page_mutex);
+ return;
+ }
+
+ free_pages((unsigned long)xlt, get_order(length));
+}
+
+/*
+ * Create a MLX5_IB_SEND_UMR_UPDATE_XLT work request and XLT buffer ready for
+ * submission.
+ */
+static void *mlx5_ib_create_xlt_wr(struct mlx5_ib_mr *mr,
+ struct mlx5_umr_wr *wr, struct ib_sge *sg,
+ size_t nents, size_t ent_size,
+ unsigned int flags)
+{
+ struct mlx5_ib_dev *dev = mr->dev;
+ struct device *ddev = dev->ib_dev.dev.parent;
+ dma_addr_t dma;
+ void *xlt;
+
+ xlt = mlx5_ib_alloc_xlt(&nents, ent_size,
+ flags & MLX5_IB_UPD_XLT_ATOMIC ? GFP_ATOMIC :
+ GFP_KERNEL);
+ sg->length = nents * ent_size;
+ dma = dma_map_single(ddev, xlt, sg->length, DMA_TO_DEVICE);
+ if (dma_mapping_error(ddev, dma)) {
+ mlx5_ib_err(dev, "unable to map DMA during XLT update.\n");
+ mlx5_ib_free_xlt(xlt, sg->length);
+ return NULL;
+ }
+ sg->addr = dma;
+ sg->lkey = dev->umrc.pd->local_dma_lkey;
+
+ memset(wr, 0, sizeof(*wr));
+ wr->wr.send_flags = MLX5_IB_SEND_UMR_UPDATE_XLT;
+ if (!(flags & MLX5_IB_UPD_XLT_ENABLE))
+ wr->wr.send_flags |= MLX5_IB_SEND_UMR_FAIL_IF_FREE;
+ wr->wr.sg_list = sg;
+ wr->wr.num_sge = 1;
+ wr->wr.opcode = MLX5_IB_WR_UMR;
+ wr->pd = mr->ibmr.pd;
+ wr->mkey = mr->mmkey.key;
+ wr->length = mr->mmkey.size;
+ wr->virt_addr = mr->mmkey.iova;
+ wr->access_flags = mr->access_flags;
+ wr->page_shift = mr->page_shift;
+ wr->xlt_size = sg->length;
+ return xlt;
+}
+
+static void mlx5_ib_unmap_free_xlt(struct mlx5_ib_dev *dev, void *xlt,
+ struct ib_sge *sg)
{
- mutex_unlock(&xlt_emergency_page_mutex);
+ struct device *ddev = dev->ib_dev.dev.parent;
+
+ dma_unmap_single(ddev, sg->addr, sg->length, DMA_TO_DEVICE);
+ mlx5_ib_free_xlt(xlt, sg->length);
}
int mlx5_ib_update_xlt(struct mlx5_ib_mr *mr, u64 idx, int npages,
{
struct mlx5_ib_dev *dev = mr->dev;
struct device *ddev = dev->ib_dev.dev.parent;
- int size;
void *xlt;
- dma_addr_t dma;
struct mlx5_umr_wr wr;
struct ib_sge sg;
int err = 0;
const int page_mask = page_align - 1;
size_t pages_mapped = 0;
size_t pages_to_map = 0;
- size_t pages_iter = 0;
+ size_t pages_iter;
size_t size_to_map = 0;
- gfp_t gfp;
- bool use_emergency_page = false;
+ size_t orig_sg_length;
if ((flags & MLX5_IB_UPD_XLT_INDIRECT) &&
!umr_can_use_indirect_mkey(dev))
npages += idx & page_mask;
idx &= ~page_mask;
}
-
- gfp = flags & MLX5_IB_UPD_XLT_ATOMIC ? GFP_ATOMIC : GFP_KERNEL;
- gfp |= __GFP_ZERO | __GFP_NOWARN;
-
pages_to_map = ALIGN(npages, page_align);
- size = desc_size * pages_to_map;
- size = min_t(int, size, MLX5_MAX_UMR_CHUNK);
-
- xlt = (void *)__get_free_pages(gfp, get_order(size));
- if (!xlt && size > MLX5_SPARE_UMR_CHUNK) {
- mlx5_ib_dbg(dev, "Failed to allocate %d bytes of order %d. fallback to spare UMR allocation od %d bytes\n",
- size, get_order(size), MLX5_SPARE_UMR_CHUNK);
- size = MLX5_SPARE_UMR_CHUNK;
- xlt = (void *)__get_free_pages(gfp, get_order(size));
- }
-
- if (!xlt) {
- mlx5_ib_warn(dev, "Using XLT emergency buffer\n");
- xlt = (void *)mlx5_ib_get_xlt_emergency_page();
- size = PAGE_SIZE;
- memset(xlt, 0, size);
- use_emergency_page = true;
- }
- pages_iter = size / desc_size;
- dma = dma_map_single(ddev, xlt, size, DMA_TO_DEVICE);
- if (dma_mapping_error(ddev, dma)) {
- mlx5_ib_err(dev, "unable to map DMA during XLT update.\n");
- err = -ENOMEM;
- goto free_xlt;
- }
+ xlt = mlx5_ib_create_xlt_wr(mr, &wr, &sg, npages, desc_size, flags);
+ if (!xlt)
+ return -ENOMEM;
+ pages_iter = sg.length / desc_size;
+ orig_sg_length = sg.length;
if (mr->umem->is_odp) {
if (!(flags & MLX5_IB_UPD_XLT_INDIRECT)) {
}
}
- sg.addr = dma;
- sg.lkey = dev->umrc.pd->local_dma_lkey;
-
- memset(&wr, 0, sizeof(wr));
- wr.wr.send_flags = MLX5_IB_SEND_UMR_UPDATE_XLT;
- if (!(flags & MLX5_IB_UPD_XLT_ENABLE))
- wr.wr.send_flags |= MLX5_IB_SEND_UMR_FAIL_IF_FREE;
- wr.wr.sg_list = &sg;
- wr.wr.num_sge = 1;
- wr.wr.opcode = MLX5_IB_WR_UMR;
-
- wr.pd = mr->ibmr.pd;
- wr.mkey = mr->mmkey.key;
- wr.length = mr->mmkey.size;
- wr.virt_addr = mr->mmkey.iova;
- wr.access_flags = mr->access_flags;
wr.page_shift = page_shift;
for (pages_mapped = 0;
pages_mapped += pages_iter, idx += pages_iter) {
npages = min_t(int, pages_iter, pages_to_map - pages_mapped);
size_to_map = npages * desc_size;
- dma_sync_single_for_cpu(ddev, dma, size, DMA_TO_DEVICE);
+ dma_sync_single_for_cpu(ddev, sg.addr, sg.length,
+ DMA_TO_DEVICE);
if (mr->umem->is_odp) {
mlx5_odp_populate_xlt(xlt, idx, npages, mr, flags);
} else {
/* Clear padding after the pages
* brought from the umem.
*/
- memset(xlt + size_to_map, 0, size - size_to_map);
+ memset(xlt + size_to_map, 0, sg.length - size_to_map);
}
- dma_sync_single_for_device(ddev, dma, size, DMA_TO_DEVICE);
+ dma_sync_single_for_device(ddev, sg.addr, sg.length,
+ DMA_TO_DEVICE);
sg.length = ALIGN(size_to_map, MLX5_UMR_MTT_ALIGNMENT);
err = mlx5_ib_post_send_wait(dev, &wr);
}
- dma_unmap_single(ddev, dma, size, DMA_TO_DEVICE);
-
-free_xlt:
- if (use_emergency_page)
- mlx5_ib_put_xlt_emergency_page();
- else
- free_pages((unsigned long)xlt, get_order(size));
-
+ sg.length = orig_sg_length;
+ mlx5_ib_unmap_free_xlt(dev, xlt, &sg);
return err;
}
projects / linux-2.6-microblaze.git / commitdiff