summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2018-05-07 23:35:08 -0400
committerDavid S. Miller <davem@davemloft.net>2018-05-07 23:35:08 -0400
commit01adc4851a8090b46c7a5ed9cfc4b97e65abfbf4 (patch)
tree2ae02593d7139962648dff203f3f9701e34ccbc3 /net
parent18b338f5f9539512e76fd9ebd4c6ca1a0e159e2b (diff)
parente94fa1d93117e7f1eb783dc9cae6c70650944449 (diff)
downloadlinux-01adc4851a8090b46c7a5ed9cfc4b97e65abfbf4.tar.bz2
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Minor conflict, a CHECK was placed into an if() statement in net-next, whilst a newline was added to that CHECK call in 'net'. Thanks to Daniel for the merge resolution. Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
-rw-r--r--net/Kconfig1
-rw-r--r--net/Makefile1
-rw-r--r--net/core/dev.c73
-rw-r--r--net/core/filter.c345
-rw-r--r--net/core/sock.c12
-rw-r--r--net/core/xdp.c15
-rw-r--r--net/packet/af_packet.c42
-rw-r--r--net/xdp/Kconfig7
-rw-r--r--net/xdp/Makefile2
-rw-r--r--net/xdp/xdp_umem.c260
-rw-r--r--net/xdp/xdp_umem.h67
-rw-r--r--net/xdp/xdp_umem_props.h23
-rw-r--r--net/xdp/xsk.c656
-rw-r--r--net/xdp/xsk_queue.c73
-rw-r--r--net/xdp/xsk_queue.h247
15 files changed, 1734 insertions, 90 deletions
diff --git a/net/Kconfig b/net/Kconfig
index b62089fb1332..df8d45ef47d8 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -59,6 +59,7 @@ source "net/tls/Kconfig"
source "net/xfrm/Kconfig"
source "net/iucv/Kconfig"
source "net/smc/Kconfig"
+source "net/xdp/Kconfig"
config INET
bool "TCP/IP networking"
diff --git a/net/Makefile b/net/Makefile
index a6147c61b174..77aaddedbd29 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -85,3 +85,4 @@ obj-y += l3mdev/
endif
obj-$(CONFIG_QRTR) += qrtr/
obj-$(CONFIG_NET_NCSI) += ncsi/
+obj-$(CONFIG_XDP_SOCKETS) += xdp/
diff --git a/net/core/dev.c b/net/core/dev.c
index bb81a6e1d354..29bf39174900 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3627,6 +3627,44 @@ int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv)
}
EXPORT_SYMBOL(dev_queue_xmit_accel);
+int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
+{
+ struct net_device *dev = skb->dev;
+ struct sk_buff *orig_skb = skb;
+ struct netdev_queue *txq;
+ int ret = NETDEV_TX_BUSY;
+ bool again = false;
+
+ if (unlikely(!netif_running(dev) ||
+ !netif_carrier_ok(dev)))
+ goto drop;
+
+ skb = validate_xmit_skb_list(skb, dev, &again);
+ if (skb != orig_skb)
+ goto drop;
+
+ skb_set_queue_mapping(skb, queue_id);
+ txq = skb_get_tx_queue(dev, skb);
+
+ local_bh_disable();
+
+ HARD_TX_LOCK(dev, txq, smp_processor_id());
+ if (!netif_xmit_frozen_or_drv_stopped(txq))
+ ret = netdev_start_xmit(skb, dev, txq, false);
+ HARD_TX_UNLOCK(dev, txq);
+
+ local_bh_enable();
+
+ if (!dev_xmit_complete(ret))
+ kfree_skb(skb);
+
+ return ret;
+drop:
+ atomic_long_inc(&dev->tx_dropped);
+ kfree_skb_list(skb);
+ return NET_XMIT_DROP;
+}
+EXPORT_SYMBOL(dev_direct_xmit);
/*************************************************************************
* Receiver routines
@@ -3996,12 +4034,12 @@ static struct netdev_rx_queue *netif_get_rxqueue(struct sk_buff *skb)
}
static u32 netif_receive_generic_xdp(struct sk_buff *skb,
+ struct xdp_buff *xdp,
struct bpf_prog *xdp_prog)
{
struct netdev_rx_queue *rxqueue;
void *orig_data, *orig_data_end;
u32 metalen, act = XDP_DROP;
- struct xdp_buff xdp;
int hlen, off;
u32 mac_len;
@@ -4036,19 +4074,19 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
*/
mac_len = skb->data - skb_mac_header(skb);
hlen = skb_headlen(skb) + mac_len;
- xdp.data = skb->data - mac_len;
- xdp.data_meta = xdp.data;
- xdp.data_end = xdp.data + hlen;
- xdp.data_hard_start = skb->data - skb_headroom(skb);
- orig_data_end = xdp.data_end;
- orig_data = xdp.data;
+ xdp->data = skb->data - mac_len;
+ xdp->data_meta = xdp->data;
+ xdp->data_end = xdp->data + hlen;
+ xdp->data_hard_start = skb->data - skb_headroom(skb);
+ orig_data_end = xdp->data_end;
+ orig_data = xdp->data;
rxqueue = netif_get_rxqueue(skb);
- xdp.rxq = &rxqueue->xdp_rxq;
+ xdp->rxq = &rxqueue->xdp_rxq;
- act = bpf_prog_run_xdp(xdp_prog, &xdp);
+ act = bpf_prog_run_xdp(xdp_prog, xdp);
- off = xdp.data - orig_data;
+ off = xdp->data - orig_data;
if (off > 0)
__skb_pull(skb, off);
else if (off < 0)
@@ -4058,10 +4096,11 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
/* check if bpf_xdp_adjust_tail was used. it can only "shrink"
* pckt.
*/
- off = orig_data_end - xdp.data_end;
+ off = orig_data_end - xdp->data_end;
if (off != 0) {
- skb_set_tail_pointer(skb, xdp.data_end - xdp.data);
+ skb_set_tail_pointer(skb, xdp->data_end - xdp->data);
skb->len -= off;
+
}
switch (act) {
@@ -4070,7 +4109,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
__skb_push(skb, mac_len);
break;
case XDP_PASS:
- metalen = xdp.data - xdp.data_meta;
+ metalen = xdp->data - xdp->data_meta;
if (metalen)
skb_metadata_set(skb, metalen);
break;
@@ -4120,17 +4159,19 @@ static struct static_key generic_xdp_needed __read_mostly;
int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb)
{
if (xdp_prog) {
- u32 act = netif_receive_generic_xdp(skb, xdp_prog);
+ struct xdp_buff xdp;
+ u32 act;
int err;
+ act = netif_receive_generic_xdp(skb, &xdp, xdp_prog);
if (act != XDP_PASS) {
switch (act) {
case XDP_REDIRECT:
err = xdp_do_generic_redirect(skb->dev, skb,
- xdp_prog);
+ &xdp, xdp_prog);
if (err)
goto out_redir;
- /* fallthru to submit skb */
+ break;
case XDP_TX:
generic_xdp_tx(skb, xdp_prog);
break;
diff --git a/net/core/filter.c b/net/core/filter.c
index d3781daa26ab..6877426c23a6 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -59,6 +59,7 @@
#include <net/tcp.h>
#include <net/xfrm.h>
#include <linux/bpf_trace.h>
+#include <net/xdp_sock.h>
/**
* sk_filter_trim_cap - run a packet through a socket filter
@@ -112,12 +113,12 @@ int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap)
}
EXPORT_SYMBOL(sk_filter_trim_cap);
-BPF_CALL_1(__skb_get_pay_offset, struct sk_buff *, skb)
+BPF_CALL_1(bpf_skb_get_pay_offset, struct sk_buff *, skb)
{
return skb_get_poff(skb);
}
-BPF_CALL_3(__skb_get_nlattr, struct sk_buff *, skb, u32, a, u32, x)
+BPF_CALL_3(bpf_skb_get_nlattr, struct sk_buff *, skb, u32, a, u32, x)
{
struct nlattr *nla;
@@ -137,7 +138,7 @@ BPF_CALL_3(__skb_get_nlattr, struct sk_buff *, skb, u32, a, u32, x)
return 0;
}
-BPF_CALL_3(__skb_get_nlattr_nest, struct sk_buff *, skb, u32, a, u32, x)
+BPF_CALL_3(bpf_skb_get_nlattr_nest, struct sk_buff *, skb, u32, a, u32, x)
{
struct nlattr *nla;
@@ -161,13 +162,94 @@ BPF_CALL_3(__skb_get_nlattr_nest, struct sk_buff *, skb, u32, a, u32, x)
return 0;
}
-BPF_CALL_0(__get_raw_cpu_id)
+BPF_CALL_4(bpf_skb_load_helper_8, const struct sk_buff *, skb, const void *,
+ data, int, headlen, int, offset)
+{
+ u8 tmp, *ptr;
+ const int len = sizeof(tmp);
+
+ if (offset >= 0) {
+ if (headlen - offset >= len)
+ return *(u8 *)(data + offset);
+ if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp)))
+ return tmp;
+ } else {
+ ptr = bpf_internal_load_pointer_neg_helper(skb, offset, len);
+ if (likely(ptr))
+ return *(u8 *)ptr;
+ }
+
+ return -EFAULT;
+}
+
+BPF_CALL_2(bpf_skb_load_helper_8_no_cache, const struct sk_buff *, skb,
+ int, offset)
+{
+ return ____bpf_skb_load_helper_8(skb, skb->data, skb->len - skb->data_len,
+ offset);
+}
+
+BPF_CALL_4(bpf_skb_load_helper_16, const struct sk_buff *, skb, const void *,
+ data, int, headlen, int, offset)
+{
+ u16 tmp, *ptr;
+ const int len = sizeof(tmp);
+
+ if (offset >= 0) {
+ if (headlen - offset >= len)
+ return get_unaligned_be16(data + offset);
+ if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp)))
+ return be16_to_cpu(tmp);
+ } else {
+ ptr = bpf_internal_load_pointer_neg_helper(skb, offset, len);
+ if (likely(ptr))
+ return get_unaligned_be16(ptr);
+ }
+
+ return -EFAULT;
+}
+
+BPF_CALL_2(bpf_skb_load_helper_16_no_cache, const struct sk_buff *, skb,
+ int, offset)
+{
+ return ____bpf_skb_load_helper_16(skb, skb->data, skb->len - skb->data_len,
+ offset);
+}
+
+BPF_CALL_4(bpf_skb_load_helper_32, const struct sk_buff *, skb, const void *,
+ data, int, headlen, int, offset)
+{
+ u32 tmp, *ptr;
+ const int len = sizeof(tmp);
+
+ if (likely(offset >= 0)) {
+ if (headlen - offset >= len)
+ return get_unaligned_be32(data + offset);
+ if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp)))
+ return be32_to_cpu(tmp);
+ } else {
+ ptr = bpf_internal_load_pointer_neg_helper(skb, offset, len);
+ if (likely(ptr))
+ return get_unaligned_be32(ptr);
+ }
+
+ return -EFAULT;
+}
+
+BPF_CALL_2(bpf_skb_load_helper_32_no_cache, const struct sk_buff *, skb,
+ int, offset)
+{
+ return ____bpf_skb_load_helper_32(skb, skb->data, skb->len - skb->data_len,
+ offset);
+}
+
+BPF_CALL_0(bpf_get_raw_cpu_id)
{
return raw_smp_processor_id();
}
static const struct bpf_func_proto bpf_get_raw_smp_processor_id_proto = {
- .func = __get_raw_cpu_id,
+ .func = bpf_get_raw_cpu_id,
.gpl_only = false,
.ret_type = RET_INTEGER,
};
@@ -317,16 +399,16 @@ static bool convert_bpf_extensions(struct sock_filter *fp,
/* Emit call(arg1=CTX, arg2=A, arg3=X) */
switch (fp->k) {
case SKF_AD_OFF + SKF_AD_PAY_OFFSET:
- *insn = BPF_EMIT_CALL(__skb_get_pay_offset);
+ *insn = BPF_EMIT_CALL(bpf_skb_get_pay_offset);
break;
case SKF_AD_OFF + SKF_AD_NLATTR:
- *insn = BPF_EMIT_CALL(__skb_get_nlattr);
+ *insn = BPF_EMIT_CALL(bpf_skb_get_nlattr);
break;
case SKF_AD_OFF + SKF_AD_NLATTR_NEST:
- *insn = BPF_EMIT_CALL(__skb_get_nlattr_nest);
+ *insn = BPF_EMIT_CALL(bpf_skb_get_nlattr_nest);
break;
case SKF_AD_OFF + SKF_AD_CPU:
- *insn = BPF_EMIT_CALL(__get_raw_cpu_id);
+ *insn = BPF_EMIT_CALL(bpf_get_raw_cpu_id);
break;
case SKF_AD_OFF + SKF_AD_RANDOM:
*insn = BPF_EMIT_CALL(bpf_user_rnd_u32);
@@ -353,26 +435,87 @@ static bool convert_bpf_extensions(struct sock_filter *fp,
return true;
}
+static bool convert_bpf_ld_abs(struct sock_filter *fp, struct bpf_insn **insnp)
+{
+ const bool unaligned_ok = IS_BUILTIN(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS);
+ int size = bpf_size_to_bytes(BPF_SIZE(fp->code));
+ bool endian = BPF_SIZE(fp->code) == BPF_H ||
+ BPF_SIZE(fp->code) == BPF_W;
+ bool indirect = BPF_MODE(fp->code) == BPF_IND;
+ const int ip_align = NET_IP_ALIGN;
+ struct bpf_insn *insn = *insnp;
+ int offset = fp->k;
+
+ if (!indirect &&
+ ((unaligned_ok && offset >= 0) ||
+ (!unaligned_ok && offset >= 0 &&
+ offset + ip_align >= 0 &&
+ offset + ip_align % size == 0))) {
+ *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_H);
+ *insn++ = BPF_ALU64_IMM(BPF_SUB, BPF_REG_TMP, offset);
+ *insn++ = BPF_JMP_IMM(BPF_JSLT, BPF_REG_TMP, size, 2 + endian);
+ *insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A, BPF_REG_D,
+ offset);
+ if (endian)
+ *insn++ = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, size * 8);
+ *insn++ = BPF_JMP_A(8);
+ }
+
+ *insn++ = BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX);
+ *insn++ = BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_D);
+ *insn++ = BPF_MOV64_REG(BPF_REG_ARG3, BPF_REG_H);
+ if (!indirect) {
+ *insn++ = BPF_MOV64_IMM(BPF_REG_ARG4, offset);
+ } else {
+ *insn++ = BPF_MOV64_REG(BPF_REG_ARG4, BPF_REG_X);
+ if (fp->k)
+ *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_ARG4, offset);
+ }
+
+ switch (BPF_SIZE(fp->code)) {
+ case BPF_B:
+ *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_8);
+ break;
+ case BPF_H:
+ *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_16);
+ break;
+ case BPF_W:
+ *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_32);
+ break;
+ default:
+ return false;
+ }
+
+ *insn++ = BPF_JMP_IMM(BPF_JSGE, BPF_REG_A, 0, 2);
+ *insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_A);
+ *insn = BPF_EXIT_INSN();
+
+ *insnp = insn;
+ return true;
+}
+
/**
* bpf_convert_filter - convert filter program
* @prog: the user passed filter program
* @len: the length of the user passed filter program
* @new_prog: allocated 'struct bpf_prog' or NULL
* @new_len: pointer to store length of converted program
+ * @seen_ld_abs: bool whether we've seen ld_abs/ind
*
* Remap 'sock_filter' style classic BPF (cBPF) instruction set to 'bpf_insn'
* style extended BPF (eBPF).
* Conversion workflow:
*
* 1) First pass for calculating the new program length:
- * bpf_convert_filter(old_prog, old_len, NULL, &new_len)
+ * bpf_convert_filter(old_prog, old_len, NULL, &new_len, &seen_ld_abs)
*
* 2) 2nd pass to remap in two passes: 1st pass finds new
* jump offsets, 2nd pass remapping:
- * bpf_convert_filter(old_prog, old_len, new_prog, &new_len);
+ * bpf_convert_filter(old_prog, old_len, new_prog, &new_len, &seen_ld_abs)
*/
static int bpf_convert_filter(struct sock_filter *prog, int len,
- struct bpf_prog *new_prog, int *new_len)
+ struct bpf_prog *new_prog, int *new_len,
+ bool *seen_ld_abs)
{
int new_flen = 0, pass = 0, target, i, stack_off;
struct bpf_insn *new_insn, *first_insn = NULL;
@@ -411,12 +554,27 @@ do_pass:
* do this ourself. Initial CTX is present in BPF_REG_ARG1.
*/
*new_insn++ = BPF_MOV64_REG(BPF_REG_CTX, BPF_REG_ARG1);
+ if (*seen_ld_abs) {
+ /* For packet access in classic BPF, cache skb->data
+ * in callee-saved BPF R8 and skb->len - skb->data_len
+ * (headlen) in BPF R9. Since classic BPF is read-only
+ * on CTX, we only need to cache it once.
+ */
+ *new_insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data),
+ BPF_REG_D, BPF_REG_CTX,
+ offsetof(struct sk_buff, data));
+ *new_insn++ = BPF_LDX_MEM(BPF_W, BPF_REG_H, BPF_REG_CTX,
+ offsetof(struct sk_buff, len));
+ *new_insn++ = BPF_LDX_MEM(BPF_W, BPF_REG_TMP, BPF_REG_CTX,
+ offsetof(struct sk_buff, data_len));
+ *new_insn++ = BPF_ALU32_REG(BPF_SUB, BPF_REG_H, BPF_REG_TMP);
+ }
} else {
new_insn += 3;
}
for (i = 0; i < len; fp++, i++) {
- struct bpf_insn tmp_insns[6] = { };
+ struct bpf_insn tmp_insns[32] = { };
struct bpf_insn *insn = tmp_insns;
if (addrs)
@@ -459,6 +617,11 @@ do_pass:
BPF_MODE(fp->code) == BPF_ABS &&
convert_bpf_extensions(fp, &insn))
break;
+ if (BPF_CLASS(fp->code) == BPF_LD &&
+ convert_bpf_ld_abs(fp, &insn)) {
+ *seen_ld_abs = true;
+ break;
+ }
if (fp->code == (BPF_ALU | BPF_DIV | BPF_X) ||
fp->code == (BPF_ALU | BPF_MOD | BPF_X)) {
@@ -561,21 +724,31 @@ jmp_rest:
break;
/* ldxb 4 * ([14] & 0xf) is remaped into 6 insns. */
- case BPF_LDX | BPF_MSH | BPF_B:
- /* tmp = A */
- *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_A);
+ case BPF_LDX | BPF_MSH | BPF_B: {
+ struct sock_filter tmp = {
+ .code = BPF_LD | BPF_ABS | BPF_B,
+ .k = fp->k,
+ };
+
+ *seen_ld_abs = true;
+
+ /* X = A */
+ *insn++ = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A);
/* A = BPF_R0 = *(u8 *) (skb->data + K) */
- *insn++ = BPF_LD_ABS(BPF_B, fp->k);
+ convert_bpf_ld_abs(&tmp, &insn);
+ insn++;
/* A &= 0xf */
*insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 0xf);
/* A <<= 2 */
*insn++ = BPF_ALU32_IMM(BPF_LSH, BPF_REG_A, 2);
+ /* tmp = X */
+ *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_X);
/* X = A */
*insn++ = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A);
/* A = tmp */
*insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_TMP);
break;
-
+ }
/* RET_K is remaped into 2 insns. RET_A case doesn't need an
* extra mov as BPF_REG_0 is already mapped into BPF_REG_A.
*/
@@ -657,6 +830,8 @@ jmp_rest:
if (!new_prog) {
/* Only calculating new length. */
*new_len = new_insn - first_insn;
+ if (*seen_ld_abs)
+ *new_len += 4; /* Prologue bits. */
return 0;
}
@@ -1018,6 +1193,7 @@ static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp)
struct sock_filter *old_prog;
struct bpf_prog *old_fp;
int err, new_len, old_len = fp->len;
+ bool seen_ld_abs = false;
/* We are free to overwrite insns et al right here as it
* won't be used at this point in time anymore internally
@@ -1039,7 +1215,8 @@ static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp)
}
/* 1st pass: calculate the new program length. */
- err = bpf_convert_filter(old_prog, old_len, NULL, &new_len);
+ err = bpf_convert_filter(old_prog, old_len, NULL, &new_len,
+ &seen_ld_abs);
if (err)
goto out_err_free;
@@ -1058,7 +1235,8 @@ static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp)
fp->len = new_len;
/* 2nd pass: remap sock_filter insns into bpf_insn insns. */
- err = bpf_convert_filter(old_prog, old_len, fp, &new_len);
+ err = bpf_convert_filter(old_prog, old_len, fp, &new_len,
+ &seen_ld_abs);
if (err)
/* 2nd bpf_convert_filter() can fail only if it fails
* to allocate memory, remapping must succeed. Note,
@@ -1506,6 +1684,47 @@ static const struct bpf_func_proto bpf_skb_load_bytes_proto = {
.arg4_type = ARG_CONST_SIZE,
};
+BPF_CALL_5(bpf_skb_load_bytes_relative, const struct sk_buff *, skb,
+ u32, offset, void *, to, u32, len, u32, start_header)
+{
+ u8 *ptr;
+
+ if (unlikely(offset > 0xffff || len > skb_headlen(skb)))
+ goto err_clear;
+
+ switch (start_header) {
+ case BPF_HDR_START_MAC:
+ ptr = skb_mac_header(skb) + offset;
+ break;
+ case BPF_HDR_START_NET:
+ ptr = skb_network_header(skb) + offset;
+ break;
+ default:
+ goto err_clear;
+ }
+
+ if (likely(ptr >= skb_mac_header(skb) &&
+ ptr + len <= skb_tail_pointer(skb))) {
+ memcpy(to, ptr, len);
+ return 0;
+ }
+
+err_clear:
+ memset(to, 0, len);
+ return -EFAULT;
+}
+
+static const struct bpf_func_proto bpf_skb_load_bytes_relative_proto = {
+ .func = bpf_skb_load_bytes_relative,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+ .arg3_type = ARG_PTR_TO_UNINIT_MEM,
+ .arg4_type = ARG_CONST_SIZE,
+ .arg5_type = ARG_ANYTHING,
+};
+
BPF_CALL_2(bpf_skb_pull_data, struct sk_buff *, skb, u32, len)
{
/* Idea is the following: should the needed direct read/write
@@ -2180,7 +2399,7 @@ BPF_CALL_3(bpf_skb_vlan_push, struct sk_buff *, skb, __be16, vlan_proto,
return ret;
}
-const struct bpf_func_proto bpf_skb_vlan_push_proto = {
+static const struct bpf_func_proto bpf_skb_vlan_push_proto = {
.func = bpf_skb_vlan_push,
.gpl_only = false,
.ret_type = RET_INTEGER,
@@ -2188,7 +2407,6 @@ const struct bpf_func_proto bpf_skb_vlan_push_proto = {
.arg2_type = ARG_ANYTHING,
.arg3_type = ARG_ANYTHING,
};
-EXPORT_SYMBOL_GPL(bpf_skb_vlan_push_proto);
BPF_CALL_1(bpf_skb_vlan_pop, struct sk_buff *, skb)
{
@@ -2202,13 +2420,12 @@ BPF_CALL_1(bpf_skb_vlan_pop, struct sk_buff *, skb)
return ret;
}
-const struct bpf_func_proto bpf_skb_vlan_pop_proto = {
+static const struct bpf_func_proto bpf_skb_vlan_pop_proto = {
.func = bpf_skb_vlan_pop,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
};
-EXPORT_SYMBOL_GPL(bpf_skb_vlan_pop_proto);
static int bpf_skb_generic_push(struct sk_buff *skb, u32 off, u32 len)
{
@@ -2801,7 +3018,8 @@ static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd,
{
int err;
- if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
+ switch (map->map_type) {
+ case BPF_MAP_TYPE_DEVMAP: {
struct net_device *dev = fwd;
struct xdp_frame *xdpf;
@@ -2819,14 +3037,25 @@ static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd,
if (err)
return err;
__dev_map_insert_ctx(map, index);
-
- } else if (map->map_type == BPF_MAP_TYPE_CPUMAP) {
+ break;
+ }
+ case BPF_MAP_TYPE_CPUMAP: {
struct bpf_cpu_map_entry *rcpu = fwd;
err = cpu_map_enqueue(rcpu, xdp, dev_rx);
if (err)
return err;
__cpu_map_insert_ctx(map, index);
+ break;
+ }
+ case BPF_MAP_TYPE_XSKMAP: {
+ struct xdp_sock *xs = fwd;
+
+ err = __xsk_map_redirect(map, xdp, xs);
+ return err;
+ }
+ default:
+ break;
}
return 0;
}
@@ -2845,6 +3074,9 @@ void xdp_do_flush_map(void)
case BPF_MAP_TYPE_CPUMAP:
__cpu_map_flush(map);
break;
+ case BPF_MAP_TYPE_XSKMAP:
+ __xsk_map_flush(map);
+ break;
default:
break;
}
@@ -2859,6 +3091,8 @@ static void *__xdp_map_lookup_elem(struct bpf_map *map, u32 index)
return __dev_map_lookup_elem(map, index);
case BPF_MAP_TYPE_CPUMAP:
return __cpu_map_lookup_elem(map, index);
+ case BPF_MAP_TYPE_XSKMAP:
+ return __xsk_map_lookup_elem(map, index);
default:
return NULL;
}
@@ -2956,13 +3190,14 @@ static int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, struct net_device *fwd)
static int xdp_do_generic_redirect_map(struct net_device *dev,
struct sk_buff *skb,
+ struct xdp_buff *xdp,
struct bpf_prog *xdp_prog)
{
struct redirect_info *ri = this_cpu_ptr(&redirect_info);
unsigned long map_owner = ri->map_owner;
struct bpf_map *map = ri->map;
- struct net_device *fwd = NULL;
u32 index = ri->ifindex;
+ void *fwd = NULL;
int err = 0;
ri->ifindex = 0;
@@ -2984,6 +3219,14 @@ static int xdp_do_generic_redirect_map(struct net_device *dev,
if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd))))
goto err;
skb->dev = fwd;
+ generic_xdp_tx(skb, xdp_prog);
+ } else if (map->map_type == BPF_MAP_TYPE_XSKMAP) {
+ struct xdp_sock *xs = fwd;
+
+ err = xsk_generic_rcv(xs, xdp);
+ if (err)
+ goto err;
+ consume_skb(skb);
} else {
/* TODO: Handle BPF_MAP_TYPE_CPUMAP */
err = -EBADRQC;
@@ -2998,7 +3241,7 @@ err:
}
int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
- struct bpf_prog *xdp_prog)
+ struct xdp_buff *xdp, struct bpf_prog *xdp_prog)
{
struct redirect_info *ri = this_cpu_ptr(&redirect_info);
u32 index = ri->ifindex;
@@ -3006,7 +3249,7 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
int err = 0;
if (ri->map)
- return xdp_do_generic_redirect_map(dev, skb, xdp_prog);
+ return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog);
ri->ifindex = 0;
fwd = dev_get_by_index_rcu(dev_net(dev), index);
@@ -3020,6 +3263,7 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
skb->dev = fwd;
_trace_xdp_redirect(dev, xdp_prog, index);
+ generic_xdp_tx(skb, xdp_prog);
return 0;
err:
_trace_xdp_redirect_err(dev, xdp_prog, index, err);
@@ -3858,6 +4102,8 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
switch (func_id) {
case BPF_FUNC_skb_load_bytes:
return &bpf_skb_load_bytes_proto;
+ case BPF_FUNC_skb_load_bytes_relative:
+ return &bpf_skb_load_bytes_relative_proto;
case BPF_FUNC_get_socket_cookie:
return &bpf_get_socket_cookie_proto;
case BPF_FUNC_get_socket_uid:
@@ -3875,6 +4121,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_skb_store_bytes_proto;
case BPF_FUNC_skb_load_bytes:
return &bpf_skb_load_bytes_proto;
+ case BPF_FUNC_skb_load_bytes_relative:
+ return &bpf_skb_load_bytes_relative_proto;
case BPF_FUNC_skb_pull_data:
return &bpf_skb_pull_data_proto;
case BPF_FUNC_csum_diff:
@@ -4304,6 +4552,41 @@ static int bpf_unclone_prologue(struct bpf_insn *insn_buf, bool direct_write,
return insn - insn_buf;
}
+static int bpf_gen_ld_abs(const struct bpf_insn *orig,
+ struct bpf_insn *insn_buf)
+{
+ bool indirect = BPF_MODE(orig->code) == BPF_IND;
+ struct bpf_insn *insn = insn_buf;
+
+ /* We're guaranteed here that CTX is in R6. */
+ *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_CTX);
+ if (!indirect) {
+ *insn++ = BPF_MOV64_IMM(BPF_REG_2, orig->imm);
+ } else {
+ *insn++ = BPF_MOV64_REG(BPF_REG_2, orig->src_reg);
+ if (orig->imm)
+ *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, orig->imm);
+ }
+
+ switch (BPF_SIZE(orig->code)) {
+ case BPF_B:
+ *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_8_no_cache);
+ break;
+ case BPF_H:
+ *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_16_no_cache);
+ break;
+ case BPF_W:
+ *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_32_no_cache);
+ break;
+ }
+
+ *insn++ = BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 0, 2);
+ *insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_0, BPF_REG_0);
+ *insn++ = BPF_EXIT_INSN();
+
+ return insn - insn_buf;
+}
+
static int tc_cls_act_prologue(struct bpf_insn *insn_buf, bool direct_write,
const struct bpf_prog *prog)
{
@@ -5573,6 +5856,7 @@ const struct bpf_verifier_ops sk_filter_verifier_ops = {
.get_func_proto = sk_filter_func_proto,
.is_valid_access = sk_filter_is_valid_access,
.convert_ctx_access = bpf_convert_ctx_access,
+ .gen_ld_abs = bpf_gen_ld_abs,
};
const struct bpf_prog_ops sk_filter_prog_ops = {
@@ -5584,6 +5868,7 @@ const struct bpf_verifier_ops tc_cls_act_verifier_ops = {
.is_valid_access = tc_cls_act_is_valid_access,
.convert_ctx_access = tc_cls_act_convert_ctx_access,
.gen_prologue = tc_cls_act_prologue,
+ .gen_ld_abs = bpf_gen_ld_abs,
};
const struct bpf_prog_ops tc_cls_act_prog_ops = {
diff --git a/net/core/sock.c b/net/core/sock.c
index b2c3db169ca1..e7d8b6c955c6 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -226,7 +226,8 @@ static struct lock_class_key af_family_kern_slock_keys[AF_MAX];
x "AF_RXRPC" , x "AF_ISDN" , x "AF_PHONET" , \
x "AF_IEEE802154", x "AF_CAIF" , x "AF_ALG" , \
x "AF_NFC" , x "AF_VSOCK" , x "AF_KCM" , \
- x "AF_QIPCRTR", x "AF_SMC" , x "AF_MAX"
+ x "AF_QIPCRTR", x "AF_SMC" , x "AF_XDP" , \
+ x "AF_MAX"
static const char *const af_family_key_strings[AF_MAX+1] = {
_sock_locks("sk_lock-")
@@ -262,7 +263,8 @@ static const char *const af_family_rlock_key_strings[AF_MAX+1] = {
"rlock-AF_RXRPC" , "rlock-AF_ISDN" , "rlock-AF_PHONET" ,
"rlock-AF_IEEE802154", "rlock-AF_CAIF" , "rlock-AF_ALG" ,
"rlock-AF_NFC" , "rlock-AF_VSOCK" , "rlock-AF_KCM" ,
- "rlock-AF_QIPCRTR", "rlock-AF_SMC" , "rlock-AF_MAX"
+ "rlock-AF_QIPCRTR", "rlock-AF_SMC" , "rlock-AF_XDP" ,
+ "rlock-AF_MAX"
};
static const char *const af_family_wlock_key_strings[AF_MAX+1] = {
"wlock-AF_UNSPEC", "wlock-AF_UNIX" , "wlock-AF_INET" ,
@@ -279,7 +281,8 @@ static const char *const af_family_wlock_key_strings[AF_MAX+1] = {
"wlock-AF_RXRPC" , "wlock-AF_ISDN" , "wlock-AF_PHONET" ,
"wlock-AF_IEEE802154", "wlock-AF_CAIF" , "wlock-AF_ALG" ,
"wlock-AF_NFC" , "wlock-AF_VSOCK" , "wlock-AF_KCM" ,
- "wlock-AF_QIPCRTR", "wlock-AF_SMC" , "wlock-AF_MAX"
+ "wlock-AF_QIPCRTR", "wlock-AF_SMC" , "wlock-AF_XDP" ,
+ "wlock-AF_MAX"
};
static const char *const af_family_elock_key_strings[AF_MAX+1] = {
"elock-AF_UNSPEC", "elock-AF_UNIX" , "elock-AF_INET" ,
@@ -296,7 +299,8 @@ static const char *const af_family_elock_key_strings[AF_MAX+1] = {
"elock-AF_RXRPC" , "elock-AF_ISDN" , "elock-AF_PHONET" ,
"elock-AF_IEEE802154", "elock-AF_CAIF" , "elock-AF_ALG" ,
"elock-AF_NFC" , "elock-AF_VSOCK" , "elock-AF_KCM" ,
- "elock-AF_QIPCRTR", "elock-AF_SMC" , "elock-AF_MAX"
+ "elock-AF_QIPCRTR", "elock-AF_SMC" , "elock-AF_XDP" ,
+ "elock-AF_MAX"
};
/*
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 0c86b53a3a63..bf6758f74339 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -308,11 +308,9 @@ err:
}
EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model);
-void xdp_return_frame(struct xdp_frame *xdpf)
+static void xdp_return(void *data, struct xdp_mem_info *mem)
{
- struct xdp_mem_info *mem = &xdpf->mem;
struct xdp_mem_allocator *xa;
- void *data = xdpf->data;
struct page *page;
switch (mem->type) {
@@ -339,4 +337,15 @@ void xdp_return_frame(struct xdp_frame *xdpf)
break;
}
}
+
+void xdp_return_frame(struct xdp_frame *xdpf)
+{
+ xdp_return(xdpf->data, &xdpf->mem);
+}
EXPORT_SYMBOL_GPL(xdp_return_frame);
+
+void xdp_return_buff(struct xdp_buff *xdp)
+{
+ xdp_return(xdp->data, &xdp->rxq->mem);
+}
+EXPORT_SYMBOL_GPL(xdp_return_buff);
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 01f3515cada0..611a26d5235c 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -209,7 +209,7 @@ static void prb_clear_rxhash(struct tpacket_kbdq_core *,
static void prb_fill_vlan_info(struct tpacket_kbdq_core *,
struct tpacket3_hdr *);
static void packet_flush_mclist(struct sock *sk);
-static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb);
+static u16 packet_pick_tx_queue(struct sk_buff *skb);
struct packet_skb_cb {
union {
@@ -243,40 +243,7 @@ static void __fanout_link(struct sock *sk, struct packet_sock *po);
static int packet_direct_xmit(struct sk_buff *skb)
{
- struct net_device *dev = skb->dev;
- struct sk_buff *orig_skb = skb;
- struct netdev_queue *txq;
- int ret = NETDEV_TX_BUSY;
- bool again = false;
-
- if (unlikely(!netif_running(dev) ||
- !netif_carrier_ok(dev)))
- goto drop;
-
- skb = validate_xmit_skb_list(skb, dev, &again);
- if (skb != orig_skb)
- goto drop;
-
- packet_pick_tx_queue(dev, skb);
- txq = skb_get_tx_queue(dev, skb);
-
- local_bh_disable();
-
- HARD_TX_LOCK(dev, txq, smp_processor_id());
- if (!netif_xmit_frozen_or_drv_stopped(txq))
- ret = netdev_start_xmit(skb, dev, txq, false);
- HARD_TX_UNLOCK(dev, txq);
-
- local_bh_enable();
-
- if (!dev_xmit_complete(ret))
- kfree_skb(skb);
-
- return ret;
-drop:
- atomic_long_inc(&dev->tx_dropped);
- kfree_skb_list(skb);
- return NET_XMIT_DROP;
+ return dev_direct_xmit(skb, packet_pick_tx_queue(skb));
}
static struct net_device *packet_cached_dev_get(struct packet_sock *po)
@@ -313,8 +280,9 @@ static u16 __packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb)
return (u16) raw_smp_processor_id() % dev->real_num_tx_queues;
}
-static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 packet_pick_tx_queue(struct sk_buff *skb)
{
+ struct net_device *dev = skb->dev;
const struct net_device_ops *ops = dev->netdev_ops;
u16 queue_index;
@@ -326,7 +294,7 @@ static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb)
queue_index = __packet_pick_tx_queue(dev, skb);
}
- skb_set_queue_mapping(skb, queue_index);
+ return queue_index;
}
/* __register_prot_hook must be invoked through register_prot_hook
diff --git a/net/xdp/Kconfig b/net/xdp/Kconfig
new file mode 100644
index 000000000000..90e4a7152854
--- /dev/null
+++ b/net/xdp/Kconfig
@@ -0,0 +1,7 @@
+config XDP_SOCKETS
+ bool "XDP sockets"
+ depends on BPF_SYSCALL
+ default n
+ help
+ XDP sockets allows a channel between XDP programs and
+ userspace applications.
diff --git a/net/xdp/Makefile b/net/xdp/Makefile
new file mode 100644
index 000000000000..074fb2b2d51c
--- /dev/null
+++ b/net/xdp/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_XDP_SOCKETS) += xsk.o xdp_umem.o xsk_queue.o
+
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
new file mode 100644
index 000000000000..881dfdefe235
--- /dev/null
+++ b/net/xdp/xdp_umem.c
@@ -0,0 +1,260 @@
+// SPDX-License-Identifier: GPL-2.0
+/* XDP user-space packet buffer
+ * Copyright(c) 2018 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/init.h>
+#include <linux/sched/mm.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/task.h>
+#include <linux/uaccess.h>
+#include <linux/slab.h>
+#include <linux/bpf.h>
+#include <linux/mm.h>
+
+#include "xdp_umem.h"
+
+#define XDP_UMEM_MIN_FRAME_SIZE 2048
+
+int xdp_umem_create(struct xdp_umem **umem)
+{
+ *umem = kzalloc(sizeof(**umem), GFP_KERNEL);
+
+ if (!(*umem))
+ return -ENOMEM;
+
+ return 0;
+}
+
+static void xdp_umem_unpin_pages(struct xdp_umem *umem)
+{
+ unsigned int i;
+
+ if (umem->pgs) {
+ for (i = 0; i < umem->npgs; i++) {
+ struct page *page = umem->pgs[i];
+
+ set_page_dirty_lock(page);
+ put_page(page);
+ }
+
+ kfree(umem->pgs);
+ umem->pgs = NULL;
+ }
+}
+
+static void xdp_umem_unaccount_pages(struct xdp_umem *umem)
+{
+ if (umem->user) {
+ atomic_long_sub(umem->npgs, &umem->user->locked_vm);
+ free_uid(umem->user);
+ }
+}
+
+static void xdp_umem_release(struct xdp_umem *umem)
+{
+ struct task_struct *task;
+ struct mm_struct *mm;
+
+ if (umem->fq) {
+ xskq_destroy(umem->fq);
+ umem->fq = NULL;
+ }
+
+ if (umem->cq) {
+ xskq_destroy(umem->cq);
+ umem->cq = NULL;
+ }
+
+ if (umem->pgs) {
+ xdp_umem_unpin_pages(umem);
+
+ task = get_pid_task(umem->pid, PIDTYPE_PID);
+ put_pid(umem->pid);
+ if (!task)
+ goto out;
+ mm = get_task_mm(task);
+ put_task_struct(task);
+ if (!mm)
+ goto out;
+
+ mmput(mm);
+ umem->pgs = NULL;
+ }
+
+ xdp_umem_unaccount_pages(umem);
+out:
+ kfree(umem);
+}
+
+static void xdp_umem_release_deferred(struct work_struct *work)
+{
+ struct xdp_umem *umem = container_of(work, struct xdp_umem, work);
+
+ xdp_umem_release(umem);
+}
+
+void xdp_get_umem(struct xdp_umem *umem)
+{
+ atomic_inc(&umem->users);
+}
+
+void xdp_put_umem(struct xdp_umem *umem)
+{
+ if (!umem)
+ return;
+
+ if (atomic_dec_and_test(&umem->users)) {
+ INIT_WORK(&umem->work, xdp_umem_release_deferred);
+ schedule_work(&umem->work);
+ }
+}
+
+static int xdp_umem_pin_pages(struct xdp_umem *umem)
+{
+ unsigned int gup_flags = FOLL_WRITE;
+ long npgs;
+ int err;
+
+ umem->pgs = kcalloc(umem->npgs, sizeof(*umem->pgs), GFP_KERNEL);
+ if (!umem->pgs)
+ return -ENOMEM;
+
+ down_write(&current->mm->mmap_sem);
+ npgs = get_user_pages(umem->address, umem->npgs,
+ gup_flags, &umem->pgs[0], NULL);
+ up_write(&current->mm->mmap_sem);
+
+ if (npgs != umem->npgs) {
+ if (npgs >= 0) {
+ umem->npgs = npgs;
+ err = -ENOMEM;
+ goto out_pin;
+ }
+ err = npgs;
+ goto out_pgs;
+ }
+ return 0;
+
+out_pin:
+ xdp_umem_unpin_pages(umem);
+out_pgs:
+ kfree(umem->pgs);
+ umem->pgs = NULL;
+ return err;
+}
+
+static int xdp_umem_account_pages(struct xdp_umem *umem)
+{
+ unsigned long lock_limit, new_npgs, old_npgs;
+
+ if (capable(CAP_IPC_LOCK))
+ return 0;
+
+ lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+ umem->user = get_uid(current_user());
+
+ do {
+ old_npgs = atomic_long_read(&umem->user->locked_vm);
+ new_npgs = old_npgs + umem->npgs;
+ if (new_npgs > lock_limit) {
+ free_uid(umem->user);
+ umem->user = NULL;
+ return -ENOBUFS;
+ }
+ } while (atomic_long_cmpxchg(&umem->user->locked_vm, old_npgs,
+ new_npgs) != old_npgs);
+ return 0;
+}
+
+int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
+{
+ u32 frame_size = mr->frame_size, frame_headroom = mr->frame_headroom;
+ u64 addr = mr->addr, size = mr->len;
+ unsigned int nframes, nfpp;
+ int size_chk, err;
+
+ if (!umem)
+ return -EINVAL;
+
+ if (frame_size < XDP_UMEM_MIN_FRAME_SIZE || frame_size > PAGE_SIZE) {
+ /* Strictly speaking we could support this, if:
+ * - huge pages, or*
+ * - using an IOMMU, or
+ * - making sure the memory area is consecutive
+ * but for now, we simply say "computer says no".
+ */
+ return -EINVAL;
+ }
+
+ if (!is_power_of_2(frame_size))
+ return -EINVAL;
+
+ if (!PAGE_ALIGNED(addr)) {
+ /* Memory area has to be page size aligned. For
+ * simplicity, this might change.
+ */
+ return -EINVAL;
+ }
+
+ if ((addr + size) < addr)
+ return -EINVAL;
+
+ nframes = size / frame_size;
+ if (nframes == 0 || nframes > UINT_MAX)
+ return -EINVAL;
+
+ nfpp = PAGE_SIZE / frame_size;
+ if (nframes < nfpp || nframes % nfpp)
+ return -EINVAL;
+
+ frame_headroom = ALIGN(frame_headroom, 64);
+
+ size_chk = frame_size - frame_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->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);
+ atomic_set(&umem->users, 1);
+
+ err = xdp_umem_account_pages(umem);
+ if (err)
+ goto out;
+
+ err = xdp_umem_pin_pages(umem);
+ if (err)
+ goto out_account;
+ return 0;
+
+out_account:
+ xdp_umem_unaccount_pages(umem);
+out:
+ put_pid(umem->pid);
+ return err;
+}
+
+bool xdp_umem_validate_queues(struct xdp_umem *umem)
+{
+ return (umem->fq && umem->cq);
+}
diff --git a/net/xdp/xdp_umem.h b/net/xdp/xdp_umem.h
new file mode 100644
index 000000000000..7e0b2fab8522
--- /dev/null
+++ b/net/xdp/xdp_umem.h
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0
+ * XDP user-space packet buffer
+ * Copyright(c) 2018 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef XDP_UMEM_H_
+#define XDP_UMEM_H_
+
+#include <linux/mm.h>
+#include <linux/if_xdp.h>
+#include <linux/workqueue.h>
+
+#include "xsk_queue.h"
+#include "xdp_umem_props.h"
+
+struct xdp_umem {
+ struct xsk_queue *fq;
+ struct xsk_queue *cq;
+ struct page **pgs;
+ struct xdp_umem_props props;
+ u32 npgs;
+ u32 frame_headroom;
+ u32 nfpp_mask;
+ u32 nfpplog2;
+ u32 frame_size_log2;
+ struct user_struct *user;
+ struct pid *pid;
+ unsigned long address;
+ size_t size;
+ atomic_t users;
+ struct work_struct work;
+};
+
+static inline char *xdp_umem_get_data(struct xdp_umem *umem, u32 idx)
+{
+ u64 pg, off;
+ char *data;
+
+ pg = idx >> umem->nfpplog2;
+ off = (idx & umem->nfpp_mask) << umem->frame_size_log2;
+
+ data = page_address(umem->pgs[pg]);
+ return data + off;
+}
+
+static inline char *xdp_umem_get_data_with_headroom(struct xdp_umem *umem,
+ u32 idx)
+{
+ return xdp_umem_get_data(umem, idx) + umem->frame_headroom;
+}
+
+bool xdp_umem_validate_queues(struct xdp_umem *umem);
+int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr);
+void xdp_get_umem(struct xdp_umem *umem);
+void xdp_put_umem(struct xdp_umem *umem);
+int xdp_umem_create(struct xdp_umem **umem);
+
+#endif /* XDP_UMEM_H_ */
diff --git a/net/xdp/xdp_umem_props.h b/net/xdp/xdp_umem_props.h
new file mode 100644
index 000000000000..77fb5daf29f3
--- /dev/null
+++ b/net/xdp/xdp_umem_props.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0
+ * XDP user-space packet buffer
+ * Copyright(c) 2018 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef XDP_UMEM_PROPS_H_
+#define XDP_UMEM_PROPS_H_
+
+struct xdp_umem_props {
+ u32 frame_size;
+ u32 nframes;
+};
+
+#endif /* XDP_UMEM_PROPS_H_ */
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
new file mode 100644
index 000000000000..009c5af5bba5
--- /dev/null
+++ b/net/xdp/xsk.c
@@ -0,0 +1,656 @@
+// SPDX-License-Identifier: GPL-2.0
+/* XDP sockets
+ *
+ * AF_XDP sockets allows a channel between XDP programs and userspace
+ * applications.
+ * Copyright(c) 2018 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * Author(s): Björn Töpel <bjorn.topel@intel.com>
+ * Magnus Karlsson <magnus.karlsson@intel.com>
+ */
+
+#define pr_fmt(fmt) "AF_XDP: %s: " fmt, __func__
+
+#include <linux/if_xdp.h>
+#include <linux/init.h>
+#include <linux/sched/mm.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/task.h>
+#include <linux/socket.h>
+#include <linux/file.h>
+#include <linux/uaccess.h>
+#include <linux/net.h>
+#include <linux/netdevice.h>
+#include <net/xdp_sock.h>
+#include <net/xdp.h>
+
+#include "xsk_queue.h"
+#include "xdp_umem.h"
+
+#define TX_BATCH_SIZE 16
+
+static struct xdp_sock *xdp_sk(struct sock *sk)
+{
+ return (struct xdp_sock *)sk;
+}
+
+bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs)
+{
+ return !!xs->rx;
+}
+
+static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
+{
+ u32 *id, len = xdp->data_end - xdp->data;
+ void *buffer;
+ int err = 0;
+
+ if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index)
+ return -EINVAL;
+
+ id = xskq_peek_id(xs->umem->fq);
+ if (!id)
+ return -ENOSPC;
+
+ buffer = xdp_umem_get_data_with_headroom(xs->umem, *id);
+ memcpy(buffer, xdp->data, len);
+ err = xskq_produce_batch_desc(xs->rx, *id, len,
+ xs->umem->frame_headroom);
+ if (!err)
+ xskq_discard_id(xs->umem->fq);
+
+ return err;
+}
+
+int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
+{
+ int err;
+
+ err = __xsk_rcv(xs, xdp);
+ if (likely(!err))
+ xdp_return_buff(xdp);
+ else
+ xs->rx_dropped++;
+
+ return err;
+}
+
+void xsk_flush(struct xdp_sock *xs)
+{
+ xskq_produce_flush_desc(xs->rx);
+ xs->sk.sk_data_ready(&xs->sk);
+}
+
+int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
+{
+ int err;
+
+ err = __xsk_rcv(xs, xdp);
+ if (!err)
+ xsk_flush(xs);
+ else
+ xs->rx_dropped++;
+
+ return err;
+}
+
+static void xsk_destruct_skb(struct sk_buff *skb)
+{
+ u32 id = (u32)(long)skb_shinfo(skb)->destructor_arg;
+ struct xdp_sock *xs = xdp_sk(skb->sk);
+
+ WARN_ON_ONCE(xskq_produce_id(xs->umem->cq, id));
+
+ sock_wfree(skb);
+}
+
+static int xsk_generic_xmit(struct sock *sk, struct msghdr *m,
+ size_t total_len)
+{
+ bool need_wait = !(m->msg_flags & MSG_DONTWAIT);
+ u32 max_batch = TX_BATCH_SIZE;
+ struct xdp_sock *xs = xdp_sk(sk);
+ bool sent_frame = false;
+ struct xdp_desc desc;
+ struct sk_buff *skb;
+ int err = 0;
+
+ if (unlikely(!xs->tx))
+ return -ENOBUFS;
+ if (need_wait)
+ return -EOPNOTSUPP;
+
+ mutex_lock(&xs->mutex);
+
+ while (xskq_peek_desc(xs->tx, &desc)) {
+ char *buffer;
+ u32 id, len;
+
+ if (max_batch-- == 0) {
+ err = -EAGAIN;
+ goto out;
+ }
+
+ if (xskq_reserve_id(xs->umem->cq)) {
+ err = -EAGAIN;
+ goto out;
+ }
+
+ len = desc.len;
+ if (unlikely(len > xs->dev->mtu)) {
+ err = -EMSGSIZE;
+ goto out;
+ }
+
+ skb = sock_alloc_send_skb(sk, len, !need_wait, &err);
+ if (unlikely(!skb)) {
+ err = -EAGAIN;
+ goto out;
+ }
+
+ skb_put(skb, len);
+ id = desc.idx;
+ buffer = xdp_umem_get_data(xs->umem, id) + desc.offset;
+ err = skb_store_bits(skb, 0, buffer, len);
+ if (unlikely(err)) {
+ kfree_skb(skb);
+ goto out;
+ }
+
+ skb->dev = xs->dev;
+ skb->priority = sk->sk_priority;
+ skb->mark = sk->sk_mark;
+ skb_shinfo(skb)->destructor_arg = (void *)(long)id;
+ skb->destructor = xsk_destruct_skb;
+
+ err = dev_direct_xmit(skb, xs->queue_id);
+ /* Ignore NET_XMIT_CN as packet might have been sent */
+ if (err == NET_XMIT_DROP || err == NETDEV_TX_BUSY) {
+ err = -EAGAIN;
+ /* SKB consumed by dev_direct_xmit() */
+ goto out;
+ }
+
+ sent_frame = true;
+ xskq_discard_desc(xs->tx);
+ }
+
+out:
+ if (sent_frame)
+ sk->sk_write_space(sk);
+
+ mutex_unlock(&xs->mutex);
+ return err;
+}
+
+static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
+{
+ struct sock *sk = sock->sk;
+ struct xdp_sock *xs = xdp_sk(sk);
+
+ if (unlikely(!xs->dev))
+ return -ENXIO;
+ if (unlikely(!(xs->dev->flags & IFF_UP)))
+ return -ENETDOWN;
+
+ return xsk_generic_xmit(sk, m, total_len);
+}
+
+static unsigned int xsk_poll(struct file *file, struct socket *sock,
+ struct poll_table_struct *wait)
+{
+ unsigned int mask = datagram_poll(file, sock, wait);
+ struct sock *sk = sock->sk;
+ struct xdp_sock *xs = xdp_sk(sk);
+
+ if (xs->rx && !xskq_empty_desc(xs->rx))
+ mask |= POLLIN | POLLRDNORM;
+ if (xs->tx && !xskq_full_desc(xs->tx))
+ mask |= POLLOUT | POLLWRNORM;
+
+ return mask;
+}
+
+static int xsk_init_queue(u32 entries, struct xsk_queue **queue,
+ bool umem_queue)
+{
+ struct xsk_queue *q;
+
+ if (entries == 0 || *queue || !is_power_of_2(entries))
+ return -EINVAL;
+
+ q = xskq_create(entries, umem_queue);
+ if (!q)
+ return -ENOMEM;
+
+ *queue = q;
+ return 0;
+}
+
+static void __xsk_release(struct xdp_sock *xs)
+{
+ /* Wait for driver to stop using the xdp socket. */
+ synchronize_net();
+
+ dev_put(xs->dev);
+}
+
+static int xsk_release(struct socket *sock)
+{
+ struct sock *sk = sock->sk;
+ struct xdp_sock *xs = xdp_sk(sk);
+ struct net *net;
+
+ if (!sk)
+ return 0;
+
+ net = sock_net(sk);
+
+ local_bh_disable();
+ sock_prot_inuse_add(net, sk->sk_prot, -1);
+ local_bh_enable();
+
+ if (xs->dev) {
+ __xsk_release(xs);
+ xs->dev = NULL;
+ }
+
+ sock_orphan(sk);
+ sock->sk = NULL;
+
+ sk_refcnt_debug_release(sk);
+ sock_put(sk);
+
+ return 0;
+}
+
+static struct socket *xsk_lookup_xsk_from_fd(int fd)
+{
+ struct socket *sock;
+ int err;
+
+ sock = sockfd_lookup(fd, &err);
+ if (!sock)
+ return ERR_PTR(-ENOTSOCK);
+
+ if (sock->sk->sk_family != PF_XDP) {
+ sockfd_put(sock);
+ return ERR_PTR(-ENOPROTOOPT);
+ }
+
+ return sock;
+}
+
+static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
+{
+ struct sockaddr_xdp *sxdp = (struct sockaddr_xdp *)addr;
+ struct sock *sk = sock->sk;
+ struct net_device *dev, *dev_curr;
+ struct xdp_sock *xs = xdp_sk(sk);
+ struct xdp_umem *old_umem = NULL;
+ int err = 0;
+
+ if (addr_len < sizeof(struct sockaddr_xdp))
+ return -EINVAL;
+ if (sxdp->sxdp_family != AF_XDP)
+ return -EINVAL;
+
+ mutex_lock(&xs->mutex);
+ dev_curr = xs->dev;
+ dev = dev_get_by_index(sock_net(sk), sxdp->sxdp_ifindex);
+ if (!dev) {
+ err = -ENODEV;
+ goto out_release;
+ }
+
+ if (!xs->rx && !xs->tx) {
+ err = -EINVAL;
+ goto out_unlock;
+ }
+
+ if (sxdp->sxdp_queue_id >= dev->num_rx_queues) {
+ err = -EINVAL;
+ goto out_unlock;
+ }
+
+ if (sxdp->sxdp_flags & XDP_SHARED_UMEM) {
+ struct xdp_sock *umem_xs;
+ struct socket *sock;
+
+ if (xs->umem) {
+ /* We have already our own. */
+ err = -EINVAL;
+ goto out_unlock;
+ }
+
+ sock = xsk_lookup_xsk_from_fd(sxdp->sxdp_shared_umem_fd);
+ if (IS_ERR(sock)) {
+ err = PTR_ERR(sock);
+ goto out_unlock;
+ }
+
+ umem_xs = xdp_sk(sock->sk);
+ if (!umem_xs->umem) {
+ /* No umem to inherit. */
+ err = -EBADF;
+ sockfd_put(sock);
+ goto out_unlock;
+ } else if (umem_xs->dev != dev ||
+ umem_xs->queue_id != sxdp->sxdp_queue_id) {
+ err = -EINVAL;
+ sockfd_put(sock);
+ goto out_unlock;
+ }
+
+ xdp_get_umem(umem_xs->umem);
+ old_umem = xs->umem;
+ xs->umem = umem_xs->umem;
+ sockfd_put(sock);
+ } else if (!xs->umem || !xdp_umem_validate_queues(xs->umem)) {
+ err = -EINVAL;
+ goto out_unlock;
+ } else {
+ /* This xsk has its own umem. */
+ xskq_set_umem(xs->umem->fq, &xs->umem->props);
+ xskq_set_umem(xs->umem->cq, &xs->umem->props);
+ }
+
+ /* Rebind? */
+ if (dev_curr && (dev_curr != dev ||
+ xs->queue_id != sxdp->sxdp_queue_id)) {
+ __xsk_release(xs);
+ if (old_umem)
+ xdp_put_umem(old_umem);
+ }
+
+ xs->dev = dev;
+ xs->queue_id = sxdp->sxdp_queue_id;
+
+ xskq_set_umem(xs->rx, &xs->umem->props);
+ xskq_set_umem(xs->tx, &xs->umem->props);
+
+out_unlock:
+ if (err)
+ dev_put(dev);
+out_release:
+ mutex_unlock(&xs->mutex);
+ return err;
+}
+
+static int xsk_setsockopt(struct socket *sock, int level, int optname,
+ char __user *optval, unsigned int optlen)
+{
+ struct sock *sk = sock->sk;
+ struct xdp_sock *xs = xdp_sk(sk);
+ int err;
+
+ if (level != SOL_XDP)
+ return -ENOPROTOOPT;
+
+ switch (optname) {
+ case XDP_RX_RING:
+ case XDP_TX_RING:
+ {
+ struct xsk_queue **q;
+ int entries;
+
+ if (optlen < sizeof(entries))
+ return -EINVAL;
+ if (copy_from_user(&entries, optval, sizeof(entries)))
+ return -EFAULT;
+
+ mutex_lock(&xs->mutex);
+ q = (optname == XDP_TX_RING) ? &xs->tx : &xs->rx;
+ err = xsk_init_queue(entries, q, false);
+ mutex_unlock(&xs->mutex);
+ return err;
+ }
+ case XDP_UMEM_REG:
+ {
+ struct xdp_umem_reg mr;
+ struct xdp_umem *umem;
+
+ if (xs->umem)
+ return -EBUSY;
+
+ if (copy_from_user(&mr, optval, sizeof(mr)))
+ return -EFAULT;
+
+ mutex_lock(&xs->mutex);
+ err = xdp_umem_create(&umem);
+
+ err = xdp_umem_reg(umem, &mr);
+ if (err) {
+ kfree(umem);
+ mutex_unlock(&xs->mutex);
+ return err;
+ }
+
+ /* Make sure umem is ready before it can be seen by others */
+ smp_wmb();
+
+ xs->umem = umem;
+ mutex_unlock(&xs->mutex);
+ return 0;
+ }
+ case XDP_UMEM_FILL_RING:
+ case XDP_UMEM_COMPLETION_RING:
+ {
+ struct xsk_queue **q;
+ int entries;
+
+ if (!xs->umem)
+ return -EINVAL;
+
+ if (copy_from_user(&entries, optval, sizeof(entries)))
+ return -EFAULT;
+
+ mutex_lock(&xs->mutex);
+ q = (optname == XDP_UMEM_FILL_RING) ? &xs->umem->fq :
+ &xs->umem->cq;
+ err = xsk_init_queue(entries, q, true);
+ mutex_unlock(&xs->mutex);
+ return err;
+ }
+ default:
+ break;
+ }
+
+ return -ENOPROTOOPT;
+}
+
+static int xsk_getsockopt(struct socket *sock, int level, int optname,
+ char __user *optval, int __user *optlen)
+{
+ struct sock *sk = sock->sk;
+ struct xdp_sock *xs = xdp_sk(sk);
+ int len;
+
+ if (level != SOL_XDP)
+ return -ENOPROTOOPT;
+
+ if (get_user(len, optlen))
+ return -EFAULT;
+ if (len < 0)
+ return -EINVAL;
+
+ switch (optname) {
+ case XDP_STATISTICS:
+ {
+ struct xdp_statistics stats;
+
+ if (len < sizeof(stats))
+ return -EINVAL;
+
+ mutex_lock(&xs->mutex);
+ stats.rx_dropped = xs->rx_dropped;
+ stats.rx_invalid_descs = xskq_nb_invalid_descs(xs->rx);
+ stats.tx_invalid_descs = xskq_nb_invalid_descs(xs->tx);
+ mutex_unlock(&xs->mutex);
+
+ if (copy_to_user(optval, &stats, sizeof(stats)))
+ return -EFAULT;
+ if (put_user(sizeof(stats), optlen))
+ return -EFAULT;
+
+ return 0;
+ }
+ default:
+ break;
+ }
+
+ return -EOPNOTSUPP;
+}
+
+static int xsk_mmap(struct file *file, struct socket *sock,
+ struct vm_area_struct *vma)
+{
+ unsigned long offset = vma->vm_pgoff << PAGE_SHIFT;
+ unsigned long size = vma->vm_end - vma->vm_start;
+ struct xdp_sock *xs = xdp_sk(sock->sk);
+ struct xsk_queue *q = NULL;
+ unsigned long pfn;
+ struct page *qpg;
+
+ if (offset == XDP_PGOFF_RX_RING) {
+ q = xs->rx;
+ } else if (offset == XDP_PGOFF_TX_RING) {
+ q = xs->tx;
+ } else {
+ if (!xs->umem)
+ return -EINVAL;
+
+ if (offset == XDP_UMEM_PGOFF_FILL_RING)
+ q = xs->umem->fq;
+ else if (offset == XDP_UMEM_PGOFF_COMPLETION_RING)
+ q = xs->umem->cq;
+ }
+
+ if (!q)
+ return -EINVAL;
+
+ qpg = virt_to_head_page(q->ring);
+ if (size > (PAGE_SIZE << compound_order(qpg)))
+ return -EINVAL;
+
+ pfn = virt_to_phys(q->ring) >> PAGE_SHIFT;
+ return remap_pfn_range(vma, vma->vm_start, pfn,
+ size, vma->vm_page_prot);
+}
+
+static struct proto xsk_proto = {
+ .name = "XDP",
+ .owner = THIS_MODULE,
+ .obj_size = sizeof(struct xdp_sock),
+};
+
+static const struct proto_ops xsk_proto_ops = {
+ .family = PF_XDP,
+ .owner = THIS_MODULE,
+ .release = xsk_release,
+ .bind = xsk_bind,
+ .connect = sock_no_connect,
+ .socketpair = sock_no_socketpair,
+ .accept = sock_no_accept,
+ .getname = sock_no_getname,
+ .poll = xsk_poll,
+ .ioctl = sock_no_ioctl,
+ .listen = sock_no_listen,
+ .shutdown = sock_no_shutdown,
+ .setsockopt = xsk_setsockopt,
+ .getsockopt = xsk_getsockopt,
+ .sendmsg = xsk_sendmsg,
+ .recvmsg = sock_no_recvmsg,
+ .mmap = xsk_mmap,
+ .sendpage = sock_no_sendpage,
+};
+
+static void xsk_destruct(struct sock *sk)
+{
+ struct xdp_sock *xs = xdp_sk(sk);
+
+ if (!sock_flag(sk, SOCK_DEAD))
+ return;
+
+ xskq_destroy(xs->rx);
+ xskq_destroy(xs->tx);
+ xdp_put_umem(xs->umem);
+
+ sk_refcnt_debug_dec(sk);
+}
+
+static int xsk_create(struct net *net, struct socket *sock, int protocol,
+ int kern)
+{
+ struct sock *sk;
+ struct xdp_sock *xs;
+
+ if (!ns_capable(net->user_ns, CAP_NET_RAW))
+ return -EPERM;
+ if (sock->type != SOCK_RAW)
+ return -ESOCKTNOSUPPORT;
+
+ if (protocol)
+ return -EPROTONOSUPPORT;
+
+ sock->state = SS_UNCONNECTED;
+
+ sk = sk_alloc(net, PF_XDP, GFP_KERNEL, &xsk_proto, kern);
+ if (!sk)
+ return -ENOBUFS;
+
+ sock->ops = &xsk_proto_ops;
+
+ sock_init_data(sock, sk);
+
+ sk->sk_family = PF_XDP;
+
+ sk->sk_destruct = xsk_destruct;
+ sk_refcnt_debug_inc(sk);
+
+ xs = xdp_sk(sk);
+ mutex_init(&xs->mutex);
+
+ local_bh_disable();
+ sock_prot_inuse_add(net, &xsk_proto, 1);
+ local_bh_enable();
+
+ return 0;
+}
+
+static const struct net_proto_family xsk_family_ops = {
+ .family = PF_XDP,
+ .create = xsk_create,
+ .owner = THIS_MODULE,
+};
+
+static int __init xsk_init(void)
+{
+ int err;
+
+ err = proto_register(&xsk_proto, 0 /* no slab */);
+ if (err)
+ goto out;
+
+ err = sock_register(&xsk_family_ops);
+ if (err)
+ goto out_proto;
+
+ return 0;
+
+out_proto:
+ proto_unregister(&xsk_proto);
+out:
+ return err;
+}
+
+fs_initcall(xsk_init);
diff --git a/net/xdp/xsk_queue.c b/net/xdp/xsk_queue.c
new file mode 100644
index 000000000000..d012e5e23591
--- /dev/null
+++ b/net/xdp/xsk_queue.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0
+/* XDP user-space ring structure
+ * Copyright(c) 2018 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/slab.h>
+
+#include "xsk_queue.h"
+
+void xskq_set_umem(struct xsk_queue *q, struct xdp_umem_props *umem_props)
+{
+ if (!q)
+ return;
+
+ q->umem_props = *umem_props;
+}
+
+static u32 xskq_umem_get_ring_size(struct xsk_queue *q)
+{
+ return sizeof(struct xdp_umem_ring) + q->nentries * sizeof(u32);
+}
+
+static u32 xskq_rxtx_get_ring_size(struct xsk_queue *q)
+{
+ return (sizeof(struct xdp_ring) +
+ q->nentries * sizeof(struct xdp_desc));
+}
+
+struct xsk_queue *xskq_create(u32 nentries, bool umem_queue)
+{
+ struct xsk_queue *q;
+ gfp_t gfp_flags;
+ size_t size;
+
+ q = kzalloc(sizeof(*q), GFP_KERNEL);
+ if (!q)
+ return NULL;
+
+ q->nentries = nentries;
+ q->ring_mask = nentries - 1;
+
+ gfp_flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN |
+ __GFP_COMP | __GFP_NORETRY;
+ size = umem_queue ? xskq_umem_get_ring_size(q) :
+ xskq_rxtx_get_ring_size(q);
+
+ q->ring = (struct xdp_ring *)__get_free_pages(gfp_flags,
+ get_order(size));
+ if (!q->ring) {
+ kfree(q);
+ return NULL;
+ }
+
+ return q;
+}
+
+void xskq_destroy(struct xsk_queue *q)
+{
+ if (!q)
+ return;
+
+ page_frag_free(q->ring);
+ kfree(q);
+}
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
new file mode 100644
index 000000000000..7aa9a535db0e
--- /dev/null
+++ b/net/xdp/xsk_queue.h
@@ -0,0 +1,247 @@
+/* SPDX-License-Identifier: GPL-2.0
+ * XDP user-space ring structure
+ * Copyright(c) 2018 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef _LINUX_XSK_QUEUE_H
+#define _LINUX_XSK_QUEUE_H
+
+#include <linux/types.h>
+#include <linux/if_xdp.h>
+
+#include "xdp_umem_props.h"
+
+#define RX_BATCH_SIZE 16
+
+struct xsk_queue {
+ struct xdp_umem_props umem_props;
+ u32 ring_mask;
+ u32 nentries;
+ u32 prod_head;
+ u32 prod_tail;
+ u32 cons_head;
+ u32 cons_tail;
+ struct xdp_ring *ring;
+ u64 invalid_descs;
+};
+
+/* Common functions operating for both RXTX and umem queues */
+
+static inline u64 xskq_nb_invalid_descs(struct xsk_queue *q)
+{
+ return q ? q->invalid_descs : 0;
+}
+
+static inline u32 xskq_nb_avail(struct xsk_queue *q, u32 dcnt)
+{
+ u32 entries = q->prod_tail - q->cons_tail;
+
+ if (entries == 0) {
+ /* Refresh the local pointer */
+ q->prod_tail = READ_ONCE(q->ring->producer);
+ entries = q->prod_tail - q->cons_tail;
+ }
+
+ return (entries > dcnt) ? dcnt : entries;
+}
+
+static inline u32 xskq_nb_free(struct xsk_queue *q, u32 producer, u32 dcnt)
+{
+ u32 free_entries = q->nentries - (producer - q->cons_tail);
+
+ if (free_entries >= dcnt)
+ return free_entries;
+
+ /* Refresh the local tail pointer */
+ q->cons_tail = READ_ONCE(q->ring->consumer);
+ return q->nentries - (producer - q->cons_tail);
+}
+
+/* UMEM queue */
+
+static inline bool xskq_is_valid_id(struct xsk_queue *q, u32 idx)
+{
+ if (unlikely(idx >= q->umem_props.nframes)) {
+ q->invalid_descs++;
+ return false;
+ }
+ return true;
+}
+
+static inline u32 *xskq_validate_id(struct xsk_queue *q)
+{
+ while (q->cons_tail != q->cons_head) {
+ struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring;
+ unsigned int idx = q->cons_tail & q->ring_mask;
+
+ if (xskq_is_valid_id(q, ring->desc[idx]))
+ return &ring->desc[idx];
+
+ q->cons_tail++;
+ }
+
+ return NULL;
+}
+
+static inline u32 *xskq_peek_id(struct xsk_queue *q)
+{
+ struct xdp_umem_ring *ring;
+
+ if (q->cons_tail == q->cons_head) {
+ WRITE_ONCE(q->ring->consumer, q->cons_tail);
+ q->cons_head = q->cons_tail + xskq_nb_avail(q, RX_BATCH_SIZE);
+
+ /* Order consumer and data */
+ smp_rmb();
+
+ return xskq_validate_id(q);
+ }
+
+ ring = (struct xdp_umem_ring *)q->ring;
+ return &ring->desc[q->cons_tail & q->ring_mask];
+}
+
+static inline void xskq_discard_id(struct xsk_queue *q)
+{
+ q->cons_tail++;
+ (void)xskq_validate_id(q);
+}
+
+static inline int xskq_produce_id(struct xsk_queue *q, u32 id)
+{
+ struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring;
+
+ ring->desc[q->prod_tail++ & q->ring_mask] = id;
+
+ /* Order producer and data */
+ smp_wmb();
+
+ WRITE_ONCE(q->ring->producer, q->prod_tail);
+ return 0;
+}
+
+static inline int xskq_reserve_id(struct xsk_queue *q)
+{
+ if (xskq_nb_free(q, q->prod_head, 1) == 0)
+ return -ENOSPC;
+
+ q->prod_head++;
+ return 0;
+}
+
+/* Rx/Tx queue */
+
+static inline bool xskq_is_valid_desc(struct xsk_queue *q, struct xdp_desc *d)
+{
+ u32 buff_len;
+
+ if (unlikely(d->idx >= q->umem_props.nframes)) {
+ q->invalid_descs++;
+ return false;
+ }
+
+ buff_len = q->umem_props.frame_size;
+ if (unlikely(d->len > buff_len || d->len == 0 ||
+ d->offset > buff_len || d->offset + d->len > buff_len)) {
+ q->invalid_descs++;
+ return false;
+ }
+
+ return true;
+}
+
+static inline struct xdp_desc *xskq_validate_desc(struct xsk_queue *q,
+ struct xdp_desc *desc)
+{
+ while (q->cons_tail != q->cons_head) {
+ struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring;
+ unsigned int idx = q->cons_tail & q->ring_mask;
+
+ if (xskq_is_valid_desc(q, &ring->desc[idx])) {
+ if (desc)
+ *desc = ring->desc[idx];
+ return desc;
+ }
+
+ q->cons_tail++;
+ }
+
+ return NULL;
+}
+
+static inline struct xdp_desc *xskq_peek_desc(struct xsk_queue *q,
+ struct xdp_desc *desc)
+{
+ struct xdp_rxtx_ring *ring;
+
+ if (q->cons_tail == q->cons_head) {
+ WRITE_ONCE(q->ring->consumer, q->cons_tail);
+ q->cons_head = q->cons_tail + xskq_nb_avail(q, RX_BATCH_SIZE);
+
+ /* Order consumer and data */
+ smp_rmb();
+
+ return xskq_validate_desc(q, desc);
+ }
+
+ ring = (struct xdp_rxtx_ring *)q->ring;
+ *desc = ring->desc[q->cons_tail & q->ring_mask];
+ return desc;
+}
+
+static inline void xskq_discard_desc(struct xsk_queue *q)
+{
+ q->cons_tail++;
+ (void)xskq_validate_desc(q, NULL);
+}
+
+static inline int xskq_produce_batch_desc(struct xsk_queue *q,
+ u32 id, u32 len, u16 offset)
+{
+ struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring;
+ unsigned int idx;
+
+ if (xskq_nb_free(q, q->prod_head, 1) == 0)
+ return -ENOSPC;
+
+ idx = (q->prod_head++) & q->ring_mask;
+ ring->desc[idx].idx = id;
+ ring->desc[idx].len = len;
+ ring->desc[idx].offset = offset;
+
+ return 0;
+}
+
+static inline void xskq_produce_flush_desc(struct xsk_queue *q)
+{
+ /* Order producer and data */
+ smp_wmb();
+
+ q->prod_tail = q->prod_head,
+ WRITE_ONCE(q->ring->producer, q->prod_tail);
+}
+
+static inline bool xskq_full_desc(struct xsk_queue *q)
+{
+ return (xskq_nb_avail(q, q->nentries) == q->nentries);
+}
+
+static inline bool xskq_empty_desc(struct xsk_queue *q)
+{
+ return (xskq_nb_free(q, q->prod_tail, 1) == q->nentries);
+}
+
+void xskq_set_umem(struct xsk_queue *q, struct xdp_umem_props *umem_props);
+struct xsk_queue *xskq_create(u32 nentries, bool umem_queue);
+void xskq_destroy(struct xsk_queue *q_ops);
+
+#endif /* _LINUX_XSK_QUEUE_H */