summaryrefslogtreecommitdiff
path: root/net/xdp/xdp_umem.c
diff options
context:
space:
mode:
authorBjörn Töpel <bjorn.topel@intel.com>2018-06-04 13:57:13 +0200
committerDaniel Borkmann <daniel@iogearbox.net>2018-06-04 17:21:02 +0200
commitbbff2f321a864ee07c9d3d1245af498023146951 (patch)
tree962414a03f749ce22e52ed553780a74216992d0a /net/xdp/xdp_umem.c
parenta509a95536a86ef84deb16c656d741437791b414 (diff)
xsk: new descriptor addressing scheme
Currently, AF_XDP only supports a fixed frame-size memory scheme where each frame is referenced via an index (idx). A user passes the frame index to the kernel, and the kernel acts upon the data. Some NICs, however, do not have a fixed frame-size model, instead they have a model where a memory window is passed to the hardware and multiple frames are filled into that window (referred to as the "type-writer" model). By changing the descriptor format from the current frame index addressing scheme, AF_XDP can in the future be extended to support these kinds of NICs. In the index-based model, an idx refers to a frame of size frame_size. Addressing a frame in the UMEM is done by offseting the UMEM starting address by a global offset, idx * frame_size + offset. Communicating via the fill- and completion-rings are done by means of idx. In this commit, the idx is removed in favor of an address (addr), which is a relative address ranging over the UMEM. To convert an idx-based address to the new addr is simply: addr = idx * frame_size + offset. We also stop referring to the UMEM "frame" as a frame. Instead it is simply called a chunk. To transfer ownership of a chunk to the kernel, the addr of the chunk is passed in the fill-ring. Note, that the kernel will mask addr to make it chunk aligned, so there is no need for userspace to do that. E.g., for a chunk size of 2k, passing an addr of 2048, 2050 or 3000 to the fill-ring will refer to the same chunk. On the completion-ring, the addr will match that of the Tx descriptor, passed to the kernel. Changing the descriptor format to use chunks/addr will allow for future changes to move to a type-writer based model, where multiple frames can reside in one chunk. In this model passing one single chunk into the fill-ring, would potentially result in multiple Rx descriptors. This commit changes the uapi of AF_XDP sockets, and updates the documentation. Signed-off-by: Björn Töpel <bjorn.topel@intel.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Diffstat (limited to 'net/xdp/xdp_umem.c')
-rw-r--r--net/xdp/xdp_umem.c33
1 files changed, 15 insertions, 18 deletions
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index 87998818116f..9ad791ff4739 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -14,7 +14,7 @@
#include "xdp_umem.h"
-#define XDP_UMEM_MIN_FRAME_SIZE 2048
+#define XDP_UMEM_MIN_CHUNK_SIZE 2048
static void xdp_umem_unpin_pages(struct xdp_umem *umem)
{
@@ -151,12 +151,12 @@ static int xdp_umem_account_pages(struct xdp_umem *umem)
static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
{
- u32 frame_size = mr->frame_size, frame_headroom = mr->frame_headroom;
+ u32 chunk_size = mr->chunk_size, headroom = mr->headroom;
+ unsigned int chunks, chunks_per_page;
u64 addr = mr->addr, size = mr->len;
- unsigned int nframes, nfpp;
int size_chk, err;
- if (frame_size < XDP_UMEM_MIN_FRAME_SIZE || frame_size > PAGE_SIZE) {
+ if (chunk_size < XDP_UMEM_MIN_CHUNK_SIZE || chunk_size > PAGE_SIZE) {
/* Strictly speaking we could support this, if:
* - huge pages, or*
* - using an IOMMU, or
@@ -166,7 +166,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
return -EINVAL;
}
- if (!is_power_of_2(frame_size))
+ if (!is_power_of_2(chunk_size))
return -EINVAL;
if (!PAGE_ALIGNED(addr)) {
@@ -179,33 +179,30 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
if ((addr + size) < addr)
return -EINVAL;
- nframes = (unsigned int)div_u64(size, frame_size);
- if (nframes == 0 || nframes > UINT_MAX)
+ chunks = (unsigned int)div_u64(size, chunk_size);
+ if (chunks == 0)
return -EINVAL;
- nfpp = PAGE_SIZE / frame_size;
- if (nframes < nfpp || nframes % nfpp)
+ chunks_per_page = PAGE_SIZE / chunk_size;
+ if (chunks < chunks_per_page || chunks % chunks_per_page)
return -EINVAL;
- frame_headroom = ALIGN(frame_headroom, 64);
+ headroom = ALIGN(headroom, 64);
- size_chk = frame_size - frame_headroom - XDP_PACKET_HEADROOM;
+ size_chk = chunk_size - headroom - XDP_PACKET_HEADROOM;
if (size_chk < 0)
return -EINVAL;
umem->pid = get_task_pid(current, PIDTYPE_PID);
- umem->size = (size_t)size;
umem->address = (unsigned long)addr;
- umem->props.frame_size = frame_size;
- umem->props.nframes = nframes;
- umem->frame_headroom = frame_headroom;
+ umem->props.chunk_mask = ~((u64)chunk_size - 1);
+ umem->props.size = size;
+ umem->headroom = headroom;
+ umem->chunk_size_nohr = chunk_size - headroom;
umem->npgs = size / PAGE_SIZE;
umem->pgs = NULL;
umem->user = NULL;
- umem->frame_size_log2 = ilog2(frame_size);
- umem->nfpp_mask = nfpp - 1;
- umem->nfpplog2 = ilog2(nfpp);
refcount_set(&umem->users, 1);
err = xdp_umem_account_pages(umem);