Merge branch 'bpf: support input xdp_md context in BPF_PROG_TEST_RUN'

Zvi Effron says:

====================

This patchset adds support for passing an xdp_md via ctx_in/ctx_out in
bpf_attr for BPF_PROG_TEST_RUN of XDP programs.

Patch 1 adds a function to validate XDP meta data lengths.

Patch 2 adds initial support for passing XDP meta data in addition to
packet data.

Patch 3 adds support for also specifying the ingress interface and
rx queue.

Patch 4 adds selftests to ensure functionality is correct.

Changelog:
----------
v7->v8
v7: https://lore.kernel.org/bpf/20210624211304.90807-1-zeffron@riotgames.com/

 * Fix too long comment line in patch 3

v6->v7
v6: https://lore.kernel.org/bpf/20210617232904.1899-1-zeffron@riotgames.com/

 * Add Yonghong Song's Acked-by to commit message in patch 1
 * Add Yonghong Song's Acked-by to commit message in patch 2
 * Extracted the post-update of the xdp_md context into a function (again)
 * Validate that the rx queue was registered with XDP info
 * Decrement the reference count on a found netdevice on failure to find
  a valid rx queue
 * Decrement the reference count on a found netdevice after the XDP
  program is run
 * Drop Yonghong Song's Acked-By for patch 3 because of patch changes
 * Improve a comment in the selftests
 * Drop Yonghong Song's Acked-By for patch 4 because of patch changes

v5->v6
v5: https://lore.kernel.org/bpf/20210616224712.3243-1-zeffron@riotgames.com/

 * Correct commit messages in patches 1 and 3
 * Add Acked-by to commit message in patch 4
 * Use gotos instead of returns to correctly free resources in
  bpf_prog_test_run_xdp
 * Rename xdp_metalen_valid to xdp_metalen_invalid
 * Improve the function signature for xdp_metalen_invalid
 * Merged declaration of ingress_ifindex and rx_queue_index into one line

v4->v5
v4: https://lore.kernel.org/bpf/20210604220235.6758-1-zeffron@riotgames.com/

 * Add new patch to introduce xdp_metalen_valid inline function to avoid
  duplicated code from net/core/filter.c
 * Correct size of bad_ctx in selftests
 * Make all declarations reverse Christmas tree
 * Move data check from xdp_convert_md_to_buff to bpf_prog_test_run_xdp
 * Merge xdp_convert_buff_to_md into bpf_prog_test_run_xdp
 * Fix line too long
 * Extracted common checks in selftests to a helper function
 * Removed redundant assignment in selftests
 * Reordered test cases in selftests
 * Check data against 0 instead of data_meta in selftests
 * Made selftests use EINVAL instead of hardcoded 22
 * Dropped "_" from XDP function name
 * Changed casts in XDP program from unsigned long to long
 * Added a comment explaining the use of the loopback interface in selftests
 * Change parameter order in xdp_convert_md_to_buff to be input first
 * Assigned xdp->ingress_ifindex and xdp->rx_queue_index to local variables in
  xdp_convert_md_to_buff
 * Made use of "meta data" versus "metadata" consistent in comments and commit
  messages

v3->v4
v3: https://lore.kernel.org/bpf/20210602190815.8096-1-zeffron@riotgames.com/

 * Clean up nits
 * Validate xdp_md->data_end in bpf_prog_test_run_xdp
 * Remove intermediate metalen variables

v2 -> v3
v2: https://lore.kernel.org/bpf/20210527201341.7128-1-zeffron@riotgames.com/

 * Check errno first in selftests
 * Use DECLARE_LIBBPF_OPTS
 * Rename tattr to opts in selftests
 * Remove extra new line
 * Rename convert_xdpmd_to_xdpb to xdp_convert_md_to_buff
 * Rename convert_xdpb_to_xdpmd to xdp_convert_buff_to_md
 * Move declaration of device and rxqueue in xdp_convert_md_to_buff to
  patch 2
 * Reorder the kfree calls in bpf_prog_test_run_xdp

v1 -> v2
v1: https://lore.kernel.org/bpf/20210524220555.251473-1-zeffron@riotgames.com

 * Fix null pointer dereference with no context
 * Use the BPF skeleton and replace CHECK with ASSERT macros
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 101 insertions, 8 deletions

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index aa47af349ba8..cda8375bbbaf 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -15,6 +15,7 @@
 #include <linux/error-injection.h>
 #include <linux/smp.h>
 #include <linux/sock_diag.h>
+#include <net/xdp.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/bpf_test_run.h>
@@ -687,6 +688,64 @@ out:
 	return ret;
 }
 
+static int xdp_convert_md_to_buff(struct xdp_md *xdp_md, struct xdp_buff *xdp)
+{
+	unsigned int ingress_ifindex, rx_queue_index;
+	struct netdev_rx_queue *rxqueue;
+	struct net_device *device;
+
+	if (!xdp_md)
+		return 0;
+
+	if (xdp_md->egress_ifindex != 0)
+		return -EINVAL;
+
+	ingress_ifindex = xdp_md->ingress_ifindex;
+	rx_queue_index = xdp_md->rx_queue_index;
+
+	if (!ingress_ifindex && rx_queue_index)
+		return -EINVAL;
+
+	if (ingress_ifindex) {
+		device = dev_get_by_index(current->nsproxy->net_ns,
+					  ingress_ifindex);
+		if (!device)
+			return -ENODEV;
+
+		if (rx_queue_index >= device->real_num_rx_queues)
+			goto free_dev;
+
+		rxqueue = __netif_get_rx_queue(device, rx_queue_index);
+
+		if (!xdp_rxq_info_is_reg(&rxqueue->xdp_rxq))
+			goto free_dev;
+
+		xdp->rxq = &rxqueue->xdp_rxq;
+		/* The device is now tracked in the xdp->rxq for later
+		 * dev_put()
+		 */
+	}
+
+	xdp->data = xdp->data_meta + xdp_md->data;
+	return 0;
+
+free_dev:
+	dev_put(device);
+	return -EINVAL;
+}
+
+static void xdp_convert_buff_to_md(struct xdp_buff *xdp, struct xdp_md *xdp_md)
+{
+	if (!xdp_md)
+		return;
+
+	xdp_md->data = xdp->data - xdp->data_meta;
+	xdp_md->data_end = xdp->data_end - xdp->data_meta;
+
+	if (xdp_md->ingress_ifindex)
+		dev_put(xdp->rxq->dev);
+}
+
 int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 			  union bpf_attr __user *uattr)
 {
@@ -697,35 +756,69 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 	struct netdev_rx_queue *rxqueue;
 	struct xdp_buff xdp = {};
 	u32 retval, duration;
+	struct xdp_md *ctx;
 	u32 max_data_sz;
 	void *data;
-	int ret;
+	int ret = -EINVAL;
 
-	if (kattr->test.ctx_in || kattr->test.ctx_out)
-		return -EINVAL;
+	ctx = bpf_ctx_init(kattr, sizeof(struct xdp_md));
+	if (IS_ERR(ctx))
+		return PTR_ERR(ctx);
+
+	if (ctx) {
+		/* There can't be user provided data before the meta data */
+		if (ctx->data_meta || ctx->data_end != size ||
+		    ctx->data > ctx->data_end ||
+		    unlikely(xdp_metalen_invalid(ctx->data)))
+			goto free_ctx;
+		/* Meta data is allocated from the headroom */
+		headroom -= ctx->data;
+	}
 
 	/* XDP have extra tailroom as (most) drivers use full page */
 	max_data_sz = 4096 - headroom - tailroom;
 
 	data = bpf_test_init(kattr, max_data_sz, headroom, tailroom);
-	if (IS_ERR(data))
-		return PTR_ERR(data);
+	if (IS_ERR(data)) {
+		ret = PTR_ERR(data);
+		goto free_ctx;
+	}
 
 	rxqueue = __netif_get_rx_queue(current->nsproxy->net_ns->loopback_dev, 0);
 	xdp_init_buff(&xdp, headroom + max_data_sz + tailroom,
 		      &rxqueue->xdp_rxq);
 	xdp_prepare_buff(&xdp, data, headroom, size, true);
 
+	ret = xdp_convert_md_to_buff(ctx, &xdp);
+	if (ret)
+		goto free_data;
+
 	bpf_prog_change_xdp(NULL, prog);
 	ret = bpf_test_run(prog, &xdp, repeat, &retval, &duration, true);
+	/* We convert the xdp_buff back to an xdp_md before checking the return
+	 * code so the reference count of any held netdevice will be decremented
+	 * even if the test run failed.
+	 */
+	xdp_convert_buff_to_md(&xdp, ctx);
 	if (ret)
 		goto out;
-	if (xdp.data != data + headroom || xdp.data_end != xdp.data + size)
-		size = xdp.data_end - xdp.data;
-	ret = bpf_test_finish(kattr, uattr, xdp.data, size, retval, duration);
+
+	if (xdp.data_meta != data + headroom ||
+	    xdp.data_end != xdp.data_meta + size)
+		size = xdp.data_end - xdp.data_meta;
+
+	ret = bpf_test_finish(kattr, uattr, xdp.data_meta, size, retval,
+			      duration);
+	if (!ret)
+		ret = bpf_ctx_finish(kattr, uattr, ctx,
+				     sizeof(struct xdp_md));
+
 out:
 	bpf_prog_change_xdp(prog, NULL);
+free_data:
 	kfree(data);
+free_ctx:
+	kfree(ctx);
 	return ret;
 }