BPF Archive on lore.kernel.org
 help / color / Atom feed
From: Sasha Levin <sashal@kernel.org>
To: linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc: Magnus Karlsson <magnus.karlsson@intel.com>,
	Eloy Degen <degeneloy@gmail.com>,
	Alexei Starovoitov <ast@kernel.org>,
	Jonathan Lemon <jonathan.lemon@gmail.com>,
	Sasha Levin <sashal@kernel.org>,
	netdev@vger.kernel.org, bpf@vger.kernel.org
Subject: [PATCH AUTOSEL 5.4 077/205] libbpf: Fix compatibility for kernels without need_wakeup
Date: Thu, 16 Jan 2020 11:40:52 -0500
Message-ID: <20200116164300.6705-77-sashal@kernel.org> (raw)
In-Reply-To: <20200116164300.6705-1-sashal@kernel.org>

From: Magnus Karlsson <magnus.karlsson@intel.com>

[ Upstream commit 94ff9ebb49a546b7f009ed840bafa235c96d4c4b ]

When the need_wakeup flag was added to AF_XDP, the format of the
XDP_MMAP_OFFSETS getsockopt was extended. Code was added to the
kernel to take care of compatibility issues arrising from running
applications using any of the two formats. However, libbpf was
not extended to take care of the case when the application/libbpf
uses the new format but the kernel only supports the old
format. This patch adds support in libbpf for parsing the old
format, before the need_wakeup flag was added, and emulating a
set of static need_wakeup flags that will always work for the
application.

v2 -> v3:
* Incorporated code improvements suggested by Jonathan Lemon

v1 -> v2:
* Rebased to bpf-next
* Rewrote the code as the previous version made you blind

Fixes: a4500432c2587cb2a ("libbpf: add support for need_wakeup flag in AF_XDP part")
Reported-by: Eloy Degen <degeneloy@gmail.com>
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Link: https://lore.kernel.org/bpf/1571995035-21889-1-git-send-email-magnus.karlsson@intel.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/lib/bpf/xsk.c | 83 ++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 71 insertions(+), 12 deletions(-)

diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index 70f9e10de286..b29d37fba2b0 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -73,6 +73,21 @@ struct xsk_nl_info {
 	int fd;
 };
 
+/* Up until and including Linux 5.3 */
+struct xdp_ring_offset_v1 {
+	__u64 producer;
+	__u64 consumer;
+	__u64 desc;
+};
+
+/* Up until and including Linux 5.3 */
+struct xdp_mmap_offsets_v1 {
+	struct xdp_ring_offset_v1 rx;
+	struct xdp_ring_offset_v1 tx;
+	struct xdp_ring_offset_v1 fr;
+	struct xdp_ring_offset_v1 cr;
+};
+
 int xsk_umem__fd(const struct xsk_umem *umem)
 {
 	return umem ? umem->fd : -EINVAL;
@@ -133,6 +148,58 @@ static int xsk_set_xdp_socket_config(struct xsk_socket_config *cfg,
 	return 0;
 }
 
+static void xsk_mmap_offsets_v1(struct xdp_mmap_offsets *off)
+{
+	struct xdp_mmap_offsets_v1 off_v1;
+
+	/* getsockopt on a kernel <= 5.3 has no flags fields.
+	 * Copy over the offsets to the correct places in the >=5.4 format
+	 * and put the flags where they would have been on that kernel.
+	 */
+	memcpy(&off_v1, off, sizeof(off_v1));
+
+	off->rx.producer = off_v1.rx.producer;
+	off->rx.consumer = off_v1.rx.consumer;
+	off->rx.desc = off_v1.rx.desc;
+	off->rx.flags = off_v1.rx.consumer + sizeof(u32);
+
+	off->tx.producer = off_v1.tx.producer;
+	off->tx.consumer = off_v1.tx.consumer;
+	off->tx.desc = off_v1.tx.desc;
+	off->tx.flags = off_v1.tx.consumer + sizeof(u32);
+
+	off->fr.producer = off_v1.fr.producer;
+	off->fr.consumer = off_v1.fr.consumer;
+	off->fr.desc = off_v1.fr.desc;
+	off->fr.flags = off_v1.fr.consumer + sizeof(u32);
+
+	off->cr.producer = off_v1.cr.producer;
+	off->cr.consumer = off_v1.cr.consumer;
+	off->cr.desc = off_v1.cr.desc;
+	off->cr.flags = off_v1.cr.consumer + sizeof(u32);
+}
+
+static int xsk_get_mmap_offsets(int fd, struct xdp_mmap_offsets *off)
+{
+	socklen_t optlen;
+	int err;
+
+	optlen = sizeof(*off);
+	err = getsockopt(fd, SOL_XDP, XDP_MMAP_OFFSETS, off, &optlen);
+	if (err)
+		return err;
+
+	if (optlen == sizeof(*off))
+		return 0;
+
+	if (optlen == sizeof(struct xdp_mmap_offsets_v1)) {
+		xsk_mmap_offsets_v1(off);
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
 int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area,
 			    __u64 size, struct xsk_ring_prod *fill,
 			    struct xsk_ring_cons *comp,
@@ -141,7 +208,6 @@ int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area,
 	struct xdp_mmap_offsets off;
 	struct xdp_umem_reg mr;
 	struct xsk_umem *umem;
-	socklen_t optlen;
 	void *map;
 	int err;
 
@@ -190,8 +256,7 @@ int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area,
 		goto out_socket;
 	}
 
-	optlen = sizeof(off);
-	err = getsockopt(umem->fd, SOL_XDP, XDP_MMAP_OFFSETS, &off, &optlen);
+	err = xsk_get_mmap_offsets(umem->fd, &off);
 	if (err) {
 		err = -errno;
 		goto out_socket;
@@ -499,7 +564,6 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 	struct sockaddr_xdp sxdp = {};
 	struct xdp_mmap_offsets off;
 	struct xsk_socket *xsk;
-	socklen_t optlen;
 	int err;
 
 	if (!umem || !xsk_ptr || !rx || !tx)
@@ -558,8 +622,7 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 		}
 	}
 
-	optlen = sizeof(off);
-	err = getsockopt(xsk->fd, SOL_XDP, XDP_MMAP_OFFSETS, &off, &optlen);
+	err = xsk_get_mmap_offsets(xsk->fd, &off);
 	if (err) {
 		err = -errno;
 		goto out_socket;
@@ -645,7 +708,6 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 int xsk_umem__delete(struct xsk_umem *umem)
 {
 	struct xdp_mmap_offsets off;
-	socklen_t optlen;
 	int err;
 
 	if (!umem)
@@ -654,8 +716,7 @@ int xsk_umem__delete(struct xsk_umem *umem)
 	if (umem->refcount)
 		return -EBUSY;
 
-	optlen = sizeof(off);
-	err = getsockopt(umem->fd, SOL_XDP, XDP_MMAP_OFFSETS, &off, &optlen);
+	err = xsk_get_mmap_offsets(umem->fd, &off);
 	if (!err) {
 		munmap(umem->fill->ring - off.fr.desc,
 		       off.fr.desc + umem->config.fill_size * sizeof(__u64));
@@ -673,7 +734,6 @@ void xsk_socket__delete(struct xsk_socket *xsk)
 {
 	size_t desc_sz = sizeof(struct xdp_desc);
 	struct xdp_mmap_offsets off;
-	socklen_t optlen;
 	int err;
 
 	if (!xsk)
@@ -684,8 +744,7 @@ void xsk_socket__delete(struct xsk_socket *xsk)
 		close(xsk->prog_fd);
 	}
 
-	optlen = sizeof(off);
-	err = getsockopt(xsk->fd, SOL_XDP, XDP_MMAP_OFFSETS, &off, &optlen);
+	err = xsk_get_mmap_offsets(xsk->fd, &off);
 	if (!err) {
 		if (xsk->rx) {
 			munmap(xsk->rx->ring - off.rx.desc,
-- 
2.20.1


  parent reply index

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <20200116164300.6705-1-sashal@kernel.org>
2020-01-16 16:40 ` [PATCH AUTOSEL 5.4 049/205] net: netsec: Correct dma sync for XDP_TX frames Sasha Levin
2020-01-16 16:40 ` Sasha Levin [this message]
2020-01-16 16:40 ` [PATCH AUTOSEL 5.4 080/205] libbpf: Don't use kernel-side u32 type in xsk.c Sasha Levin
2020-01-16 16:41 ` [PATCH AUTOSEL 5.4 111/205] libbpf: Fix memory leak/double free issue Sasha Levin
2020-01-16 16:41 ` [PATCH AUTOSEL 5.4 112/205] libbpf: Fix potential overflow issue Sasha Levin
2020-01-16 16:41 ` [PATCH AUTOSEL 5.4 113/205] libbpf: Fix another potential overflow issue in bpf_prog_linfo Sasha Levin
2020-01-16 16:41 ` [PATCH AUTOSEL 5.4 114/205] libbpf: Make btf__resolve_size logic always check size error condition Sasha Levin
2020-01-16 16:42 ` [PATCH AUTOSEL 5.4 155/205] libbpf: Fix call relocation offset calculation bug Sasha Levin
2020-01-16 16:42 ` [PATCH AUTOSEL 5.4 164/205] bpf: skmsg, fix potential psock NULL pointer dereference Sasha Levin
2020-01-16 16:42 ` [PATCH AUTOSEL 5.4 172/205] xdp: Fix cleanup on map free for devmap_hash map type Sasha Levin
2020-01-16 16:42 ` [PATCH AUTOSEL 5.4 179/205] bpf: Support pre-2.25-binutils objcopy for vmlinux BTF Sasha Levin
2020-01-16 16:42 ` [PATCH AUTOSEL 5.4 180/205] libbpf: Fix Makefile' libbpf symbol mismatch diagnostic Sasha Levin
2020-01-16 16:42 ` [PATCH AUTOSEL 5.4 186/205] bpf: Force .BTF section start to zero when dumping from vmlinux Sasha Levin
2020-01-16 16:42 ` [PATCH AUTOSEL 5.4 191/205] samples/bpf: Fix broken xdp_rxq_info due to map order assumptions Sasha Levin

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200116164300.6705-77-sashal@kernel.org \
    --to=sashal@kernel.org \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=degeneloy@gmail.com \
    --cc=jonathan.lemon@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=magnus.karlsson@intel.com \
    --cc=netdev@vger.kernel.org \
    --cc=stable@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

BPF Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/bpf/0 bpf/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 bpf bpf/ https://lore.kernel.org/bpf \
		bpf@vger.kernel.org
	public-inbox-index bpf

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.bpf


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git