15 bpf 5.4

Documentation/networking/00-INDEX

@@ -228,6 +228,8 @@ x25.txt
 	- general info on X.25 development.
 x25-iface.txt
 	- description of the X.25 Packet Layer to LAPB device interface.
+xfrm_device.txt
+	- description of XFRM offload API
 xfrm_proc.txt
 	- description of the statistics package for XFRM.
 xfrm_sync.txt

Documentation/networking/xfrm_device.txt

@@ -0,0 +1,132 @@
+
+===============================================
+XFRM device - offloading the IPsec computations
+===============================================
+Shannon Nelson <[email protected]>
+
+
+Overview
+========
+
+IPsec is a useful feature for securing network traffic, but the
+computational cost is high: a 10Gbps link can easily be brought down
+to under 1Gbps, depending on the traffic and link configuration.
+Luckily, there are NICs that offer a hardware based IPsec offload which
+can radically increase throughput and decrease CPU utilization.  The XFRM
+Device interface allows NIC drivers to offer to the stack access to the
+hardware offload.
+
+Userland access to the offload is typically through a system such as
+libreswan or KAME/raccoon, but the iproute2 'ip xfrm' command set can
+be handy when experimenting.  An example command might look something
+like this:
+
+  ip x s add proto esp dst 14.0.0.70 src 14.0.0.52 spi 0x07 mode transport \
+     reqid 0x07 replay-window 32 \
+     aead 'rfc4106(gcm(aes))' 0x44434241343332312423222114131211f4f3f2f1 128 \
+     sel src 14.0.0.52/24 dst 14.0.0.70/24 proto tcp \
+     offload dev eth4 dir in
+
+Yes, that's ugly, but that's what shell scripts and/or libreswan are for.
+
+
+
+Callbacks to implement
+======================
+
+/* from include/linux/netdevice.h */
+struct xfrmdev_ops {
+	int	(*xdo_dev_state_add) (struct xfrm_state *x);
+	void	(*xdo_dev_state_delete) (struct xfrm_state *x);
+	void	(*xdo_dev_state_free) (struct xfrm_state *x);
+	bool	(*xdo_dev_offload_ok) (struct sk_buff *skb,
+				       struct xfrm_state *x);
+};
+
+The NIC driver offering ipsec offload will need to implement these
+callbacks to make the offload available to the network stack's
+XFRM subsytem.  Additionally, the feature bits NETIF_F_HW_ESP and
+NETIF_F_HW_ESP_TX_CSUM will signal the availability of the offload.
+
+
+
+Flow
+====
+
+At probe time and before the call to register_netdev(), the driver should
+set up local data structures and XFRM callbacks, and set the feature bits.
+The XFRM code's listener will finish the setup on NETDEV_REGISTER.
+
+		adapter->netdev->xfrmdev_ops = &ixgbe_xfrmdev_ops;
+		adapter->netdev->features |= NETIF_F_HW_ESP;
+		adapter->netdev->hw_enc_features |= NETIF_F_HW_ESP;
+
+When new SAs are set up with a request for "offload" feature, the
+driver's xdo_dev_state_add() will be given the new SA to be offloaded
+and an indication of whether it is for Rx or Tx.  The driver should
+	- verify the algorithm is supported for offloads
+	- store the SA information (key, salt, target-ip, protocol, etc)
+	- enable the HW offload of the SA
+
+The driver can also set an offload_handle in the SA, an opaque void pointer
+that can be used to convey context into the fast-path offload requests.
+
+		xs->xso.offload_handle = context;
+
+
+When the network stack is preparing an IPsec packet for an SA that has
+been setup for offload, it first calls into xdo_dev_offload_ok() with
+the skb and the intended offload state to ask the driver if the offload
+will serviceable.  This can check the packet information to be sure the
+offload can be supported (e.g. IPv4 or IPv6, no IPv4 options, etc) and
+return true of false to signify its support.
+
+When ready to send, the driver needs to inspect the Tx packet for the
+offload information, including the opaque context, and set up the packet
+send accordingly.
+
+		xs = xfrm_input_state(skb);
+		context = xs->xso.offload_handle;
+		set up HW for send
+
+The stack has already inserted the appropriate IPsec headers in the
+packet data, the offload just needs to do the encryption and fix up the
+header values.
+
+
+When a packet is received and the HW has indicated that it offloaded a
+decryption, the driver needs to add a reference to the decoded SA into
+the packet's skb.  At this point the data should be decrypted but the
+IPsec headers are still in the packet data; they are removed later up
+the stack in xfrm_input().
+
+	find and hold the SA that was used to the Rx skb
+		get spi, protocol, and destination IP from packet headers
+		xs = find xs from (spi, protocol, dest_IP)
+		xfrm_state_hold(xs);
+
+	store the state information into the skb
+		skb->sp = secpath_dup(skb->sp);
+		skb->sp->xvec[skb->sp->len++] = xs;
+		skb->sp->olen++;
+
+	indicate the success and/or error status of the offload
+		xo = xfrm_offload(skb);
+		xo->flags = CRYPTO_DONE;
+		xo->status = crypto_status;
+
+	hand the packet to napi_gro_receive() as usual
+
+
+When the SA is removed by the user, the driver's xdo_dev_state_delete()
+is asked to disable the offload.  Later, xdo_dev_state_free() is called
+from a garbage collection routine after all reference counts to the state
+have been removed and any remaining resources can be cleared for the
+offload state.  How these are used by the driver will depend on specific
+hardware needs.
+
+As a netdev is set to DOWN the XFRM stack's netdev listener will call
+xdo_dev_state_delete() and xdo_dev_state_free() on any remaining offloaded
+states.
+
+

arch/arm/net/bpf_jit_32.c

@@ -1827,7 +1827,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	/* If BPF JIT was not enabled then we must fall back to
 	 * the interpreter.
 	 */
-	if (!bpf_jit_enable)
+	if (!prog->jit_requested)
 		return orig_prog;
 
 	/* If constant blinding was enabled and we failed during blinding

arch/arm64/net/bpf_jit_comp.c

@@ -852,7 +852,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	int image_size;
 	u8 *image_ptr;
 
-	if (!bpf_jit_enable)
+	if (!prog->jit_requested)
 		return orig_prog;
 
 	tmp = bpf_jit_blind_constants(prog);

arch/s390/net/bpf_jit_comp.c

@@ -1363,7 +1363,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	struct bpf_jit jit;
 	int pass;
 
-	if (!bpf_jit_enable)
+	if (!fp->jit_requested)
 		return orig_fp;
 
 	tmp = bpf_jit_blind_constants(fp);

arch/sparc/net/bpf_jit_comp_64.c

@@ -1529,7 +1529,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	u8 *image_ptr;
 	int pass;
 
-	if (!bpf_jit_enable)
+	if (!prog->jit_requested)
 		return orig_prog;
 
 	tmp = bpf_jit_blind_constants(prog);

arch/x86/net/bpf_jit_comp.c

@@ -1129,19 +1129,29 @@ xadd:			if (is_imm8(insn->off))
 	return proglen;
 }
 
+struct x64_jit_data {
+	struct bpf_binary_header *header;
+	int *addrs;
+	u8 *image;
+	int proglen;
+	struct jit_context ctx;
+};
+
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 {
 	struct bpf_binary_header *header = NULL;
 	struct bpf_prog *tmp, *orig_prog = prog;
+	struct x64_jit_data *jit_data;
 	int proglen, oldproglen = 0;
 	struct jit_context ctx = {};
 	bool tmp_blinded = false;
+	bool extra_pass = false;
 	u8 *image = NULL;
 	int *addrs;
 	int pass;
 	int i;
 
-	if (!bpf_jit_enable)
+	if (!prog->jit_requested)
 		return orig_prog;
 
 	tmp = bpf_jit_blind_constants(prog);
@@ -1155,10 +1165,28 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		prog = tmp;
 	}
 
+	jit_data = prog->aux->jit_data;
+	if (!jit_data) {
+		jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL);
+		if (!jit_data) {
+			prog = orig_prog;
+			goto out;
+		}
+		prog->aux->jit_data = jit_data;
+	}
+	addrs = jit_data->addrs;
+	if (addrs) {
+		ctx = jit_data->ctx;
+		oldproglen = jit_data->proglen;
+		image = jit_data->image;
+		header = jit_data->header;
+		extra_pass = true;
+		goto skip_init_addrs;
+	}
 	addrs = kmalloc(prog->len * sizeof(*addrs), GFP_KERNEL);
 	if (!addrs) {
 		prog = orig_prog;
-		goto out;
+		goto out_addrs;
 	}
 
 	/* Before first pass, make a rough estimation of addrs[]
@@ -1170,6 +1198,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	}
 	ctx.cleanup_addr = proglen;
 
+skip_init_addrs:
 	/* JITed image shrinks with every pass and the loop iterates
 	 * until the image stops shrinking. Very large bpf programs
 	 * may converge on the last pass. In such case do one more
@@ -1210,16 +1239,30 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 
 	if (image) {
 		bpf_flush_icache(header, image + proglen);
-		bpf_jit_binary_lock_ro(header);
+		if (!prog->is_func || extra_pass) {
+			bpf_jit_binary_lock_ro(header);
+		} else {
+			jit_data->addrs = addrs;
+			jit_data->ctx = ctx;
+			jit_data->proglen = proglen;
+			jit_data->image = image;
+			jit_data->header = header;
+		}
 		prog->bpf_func = (void *)image;
 		prog->jited = 1;
 		prog->jited_len = proglen;
 	} else {
 		prog = orig_prog;
 	}
 
+	if (!image || !prog->is_func || extra_pass) {
+		if (image)
+			bpf_prog_fill_jited_linfo(prog, addrs);
 out_addrs:
-	kfree(addrs);
+		kfree(addrs);
+		kfree(jit_data);
+		prog->aux->jit_data = NULL;
+	}
 out:
 	if (tmp_blinded)
 		bpf_jit_prog_release_other(prog, prog == orig_prog ?

drivers/net/tun.c

@@ -1335,6 +1335,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 
 		xdp.data_hard_start = buf;
 		xdp.data = buf + pad;
+		xdp_set_data_meta_invalid(&xdp);
 		xdp.data_end = xdp.data + len;
 		orig_data = xdp.data;
 		act = bpf_prog_run_xdp(xdp_prog, &xdp);

drivers/net/virtio_net.c

@@ -551,6 +551,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 
 		xdp.data_hard_start = buf + VIRTNET_RX_PAD + vi->hdr_len;
 		xdp.data = xdp.data_hard_start + xdp_headroom;
+		xdp_set_data_meta_invalid(&xdp);
 		xdp.data_end = xdp.data + len;
 		orig_data = xdp.data;
 		act = bpf_prog_run_xdp(xdp_prog, &xdp);
@@ -673,6 +674,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 		data = page_address(xdp_page) + offset;
 		xdp.data_hard_start = data - VIRTIO_XDP_HEADROOM + vi->hdr_len;
 		xdp.data = data + vi->hdr_len;
+		xdp_set_data_meta_invalid(&xdp);
 		xdp.data_end = xdp.data + (len - vi->hdr_len);
 		act = bpf_prog_run_xdp(xdp_prog, &xdp);
 

fs/namei.c

@@ -3052,6 +3052,26 @@ int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 }
 EXPORT_SYMBOL(vfs_create);
 
+int vfs_mkobj(struct dentry *dentry, umode_t mode,
+		int (*f)(struct dentry *, umode_t, void *),
+		void *arg)
+{
+	struct inode *dir = dentry->d_parent->d_inode;
+	int error = may_create(NULL, dir, dentry);
+	if (error)
+		return error;
+	mode &= S_IALLUGO;
+	mode |= S_IFREG;
+	error = security_inode_create(dir, dentry, mode);
+	if (error)
+		return error;
+	error = f(dentry, mode, arg);
+	if (!error)
+		fsnotify_create(dir, dentry);
+	return error;
+}
+EXPORT_SYMBOL(vfs_mkobj);
+
 bool may_open_dev(const struct path *path)
 {
 	return !(path->mnt->mnt_flags & MNT_NODEV) &&