Merge tag 'mlx5-fixes-2020-05-28' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux
Saeed Mahameed says:
====================
mlx5 fixes 2020-05-28
This series introduces some fixes to mlx5 driver.
v1->v2:
- Fix bad sha1, Jakub.
- Added one more patch by Pablo.
net/mlx5e: replace EINVAL in mlx5e_flower_parse_meta()
Nothing major, the only patch worth mentioning is the suspend/resume crash
fix by adding the missing pci device handlers, the fix is very straight
forward and as Dexuan already expressed, the patch is important for Azure
users to avoid crash on VM hibernation, patch is marked for -stable v4.6
below.
Conflict note:
('net/mlx5e: Fix MLX5_TC_CT dependencies') has a trivial one line conflict
with current net-next, which can be resolved by simply using the line from
net-next.
Please pull and let me know if there is any problem.
For -stable v4.6
('net/mlx5: Fix crash upon suspend/resume')
For -stable v5.6
('net/mlx5e: replace EINVAL in mlx5e_flower_parse_meta()')
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index d13b532..b29d7cb 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -126,6 +126,7 @@
select ARCH_HAS_MMIOWB if PPC64
select ARCH_HAS_PHYS_TO_DMA
select ARCH_HAS_PMEM_API
+ select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
select ARCH_HAS_PTE_DEVMAP if PPC_BOOK3S_64
select ARCH_HAS_PTE_SPECIAL
select ARCH_HAS_MEMBARRIER_CALLBACKS
diff --git a/include/net/espintcp.h b/include/net/espintcp.h
index dd7026a..0335bbd 100644
--- a/include/net/espintcp.h
+++ b/include/net/espintcp.h
@@ -25,6 +25,7 @@
struct espintcp_msg partial;
void (*saved_data_ready)(struct sock *sk);
void (*saved_write_space)(struct sock *sk);
+ void (*saved_destruct)(struct sock *sk);
struct work_struct work;
bool tx_running;
};
diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h
index 5f3b9fe..ff7cfdc 100644
--- a/include/uapi/linux/xfrm.h
+++ b/include/uapi/linux/xfrm.h
@@ -304,7 +304,7 @@
XFRMA_PROTO, /* __u8 */
XFRMA_ADDRESS_FILTER, /* struct xfrm_address_filter */
XFRMA_PAD,
- XFRMA_OFFLOAD_DEV, /* struct xfrm_state_offload */
+ XFRMA_OFFLOAD_DEV, /* struct xfrm_user_offload */
XFRMA_SET_MARK, /* __u32 */
XFRMA_SET_MARK_MASK, /* __u32 */
XFRMA_IF_ID, /* __u32 */
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 8d7ee40..efe14cf 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1168,14 +1168,14 @@
* but must be positive otherwise set to worse case bounds
* and refine later from tnum.
*/
- if (reg->s32_min_value > 0)
- reg->smin_value = reg->s32_min_value;
- else
- reg->smin_value = 0;
- if (reg->s32_max_value > 0)
+ if (reg->s32_min_value >= 0 && reg->s32_max_value >= 0)
reg->smax_value = reg->s32_max_value;
else
reg->smax_value = U32_MAX;
+ if (reg->s32_min_value >= 0)
+ reg->smin_value = reg->s32_min_value;
+ else
+ reg->smin_value = 0;
}
static void __reg_combine_32_into_64(struct bpf_reg_state *reg)
@@ -10428,22 +10428,13 @@
}
#define SECURITY_PREFIX "security_"
-static int check_attach_modify_return(struct bpf_verifier_env *env)
+static int check_attach_modify_return(struct bpf_prog *prog, unsigned long addr)
{
- struct bpf_prog *prog = env->prog;
- unsigned long addr = (unsigned long) prog->aux->trampoline->func.addr;
-
- /* This is expected to be cleaned up in the future with the KRSI effort
- * introducing the LSM_HOOK macro for cleaning up lsm_hooks.h.
- */
if (within_error_injection_list(addr) ||
!strncmp(SECURITY_PREFIX, prog->aux->attach_func_name,
sizeof(SECURITY_PREFIX) - 1))
return 0;
- verbose(env, "fmod_ret attach_btf_id %u (%s) is not modifiable\n",
- prog->aux->attach_btf_id, prog->aux->attach_func_name);
-
return -EINVAL;
}
@@ -10654,11 +10645,18 @@
goto out;
}
}
+
+ if (prog->expected_attach_type == BPF_MODIFY_RETURN) {
+ ret = check_attach_modify_return(prog, addr);
+ if (ret)
+ verbose(env, "%s() is not modifiable\n",
+ prog->aux->attach_func_name);
+ }
+
+ if (ret)
+ goto out;
tr->func.addr = (void *)addr;
prog->aux->trampoline = tr;
-
- if (prog->expected_attach_type == BPF_MODIFY_RETURN)
- ret = check_attach_modify_return(env);
out:
mutex_unlock(&tr->mutex);
if (ret)
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index 731022c..d14133e 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -63,10 +63,8 @@
sp->olen++;
xo = xfrm_offload(skb);
- if (!xo) {
- xfrm_state_put(x);
+ if (!xo)
goto out_reset;
- }
}
xo->flags |= XFRM_GRO;
@@ -139,19 +137,27 @@
struct xfrm_offload *xo = xfrm_offload(skb);
struct sk_buff *segs = ERR_PTR(-EINVAL);
const struct net_offload *ops;
- int proto = xo->proto;
+ u8 proto = xo->proto;
skb->transport_header += x->props.header_len;
- if (proto == IPPROTO_BEETPH) {
- struct ip_beet_phdr *ph = (struct ip_beet_phdr *)skb->data;
+ if (x->sel.family != AF_INET6) {
+ if (proto == IPPROTO_BEETPH) {
+ struct ip_beet_phdr *ph =
+ (struct ip_beet_phdr *)skb->data;
- skb->transport_header += ph->hdrlen * 8;
- proto = ph->nexthdr;
- } else if (x->sel.family != AF_INET6) {
- skb->transport_header -= IPV4_BEET_PHMAXLEN;
- } else if (proto == IPPROTO_TCP) {
- skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4;
+ skb->transport_header += ph->hdrlen * 8;
+ proto = ph->nexthdr;
+ } else {
+ skb->transport_header -= IPV4_BEET_PHMAXLEN;
+ }
+ } else {
+ __be16 frag;
+
+ skb->transport_header +=
+ ipv6_skip_exthdr(skb, 0, &proto, &frag);
+ if (proto == IPPROTO_TCP)
+ skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4;
}
__skb_pull(skb, skb_transport_offset(skb));
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 1b4e6f2..1dda7c1 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -93,7 +93,28 @@
static int vti_rcv_tunnel(struct sk_buff *skb)
{
- return vti_rcv(skb, ip_hdr(skb)->saddr, true);
+ struct ip_tunnel_net *itn = net_generic(dev_net(skb->dev), vti_net_id);
+ const struct iphdr *iph = ip_hdr(skb);
+ struct ip_tunnel *tunnel;
+
+ tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
+ iph->saddr, iph->daddr, 0);
+ if (tunnel) {
+ struct tnl_ptk_info tpi = {
+ .proto = htons(ETH_P_IP),
+ };
+
+ if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
+ goto drop;
+ if (iptunnel_pull_header(skb, 0, tpi.proto, false))
+ goto drop;
+ return ip_tunnel_rcv(tunnel, skb, &tpi, NULL, false);
+ }
+
+ return -EINVAL;
+drop:
+ kfree_skb(skb);
+ return 0;
}
static int vti_rcv_cb(struct sk_buff *skb, int err)
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index 8eab2c8..ab0eea3 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -85,10 +85,8 @@
sp->olen++;
xo = xfrm_offload(skb);
- if (!xo) {
- xfrm_state_put(x);
+ if (!xo)
goto out_reset;
- }
}
xo->flags |= XFRM_GRO;
@@ -123,9 +121,16 @@
struct ip_esp_hdr *esph;
struct ipv6hdr *iph = ipv6_hdr(skb);
struct xfrm_offload *xo = xfrm_offload(skb);
- int proto = iph->nexthdr;
+ u8 proto = iph->nexthdr;
skb_push(skb, -skb_network_offset(skb));
+
+ if (x->outer_mode.encap == XFRM_MODE_TRANSPORT) {
+ __be16 frag;
+
+ ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &proto, &frag);
+ }
+
esph = ip_esp_hdr(skb);
*skb_mac_header(skb) = IPPROTO_ESP;
@@ -166,23 +171,31 @@
struct xfrm_offload *xo = xfrm_offload(skb);
struct sk_buff *segs = ERR_PTR(-EINVAL);
const struct net_offload *ops;
- int proto = xo->proto;
+ u8 proto = xo->proto;
skb->transport_header += x->props.header_len;
- if (proto == IPPROTO_BEETPH) {
- struct ip_beet_phdr *ph = (struct ip_beet_phdr *)skb->data;
-
- skb->transport_header += ph->hdrlen * 8;
- proto = ph->nexthdr;
- }
-
if (x->sel.family != AF_INET6) {
skb->transport_header -=
(sizeof(struct ipv6hdr) - sizeof(struct iphdr));
+ if (proto == IPPROTO_BEETPH) {
+ struct ip_beet_phdr *ph =
+ (struct ip_beet_phdr *)skb->data;
+
+ skb->transport_header += ph->hdrlen * 8;
+ proto = ph->nexthdr;
+ } else {
+ skb->transport_header -= IPV4_BEET_PHMAXLEN;
+ }
+
if (proto == IPPROTO_TCP)
skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV6;
+ } else {
+ __be16 frag;
+
+ skb->transport_header +=
+ ipv6_skip_exthdr(skb, 0, &proto, &frag);
}
__skb_pull(skb, skb_transport_offset(skb));
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index ed7a606..3889bd9 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -341,8 +341,8 @@
{
bool unaligned_chunks = mr->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG;
u32 chunk_size = mr->chunk_size, headroom = mr->headroom;
+ u64 npgs, addr = mr->addr, size = mr->len;
unsigned int chunks, chunks_per_page;
- u64 addr = mr->addr, size = mr->len;
int err;
if (chunk_size < XDP_UMEM_MIN_CHUNK_SIZE || chunk_size > PAGE_SIZE) {
@@ -372,6 +372,10 @@
if ((addr + size) < addr)
return -EINVAL;
+ npgs = div_u64(size, PAGE_SIZE);
+ if (npgs > U32_MAX)
+ return -EINVAL;
+
chunks = (unsigned int)div_u64(size, chunk_size);
if (chunks == 0)
return -EINVAL;
@@ -391,7 +395,7 @@
umem->size = size;
umem->headroom = headroom;
umem->chunk_size_nohr = chunk_size - headroom;
- umem->npgs = size / PAGE_SIZE;
+ umem->npgs = (u32)npgs;
umem->pgs = NULL;
umem->user = NULL;
umem->flags = mr->flags;
diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c
index 037ea15..5a0ff66 100644
--- a/net/xfrm/espintcp.c
+++ b/net/xfrm/espintcp.c
@@ -379,6 +379,7 @@
{
struct espintcp_ctx *ctx = espintcp_getctx(sk);
+ ctx->saved_destruct(sk);
kfree(ctx);
}
@@ -419,6 +420,7 @@
sk->sk_socket->ops = &espintcp_ops;
ctx->saved_data_ready = sk->sk_data_ready;
ctx->saved_write_space = sk->sk_write_space;
+ ctx->saved_destruct = sk->sk_destruct;
sk->sk_data_ready = espintcp_data_ready;
sk->sk_write_space = espintcp_write_space;
sk->sk_destruct = espintcp_destruct;
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index 6cc7f7f..f50d1f9 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -25,12 +25,10 @@
struct xfrm_offload *xo = xfrm_offload(skb);
skb_reset_mac_len(skb);
- pskb_pull(skb, skb->mac_len + hsize + x->props.header_len);
-
- if (xo->flags & XFRM_GSO_SEGMENT) {
- skb_reset_transport_header(skb);
+ if (xo->flags & XFRM_GSO_SEGMENT)
skb->transport_header -= x->props.header_len;
- }
+
+ pskb_pull(skb, skb_transport_offset(skb) + x->props.header_len);
}
static void __xfrm_mode_tunnel_prep(struct xfrm_state *x, struct sk_buff *skb,
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index aa35f23..8a202c44 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -644,7 +644,7 @@
dev_put(skb->dev);
spin_lock(&x->lock);
- if (nexthdr <= 0) {
+ if (nexthdr < 0) {
if (nexthdr == -EBADMSG) {
xfrm_audit_state_icvfail(x, skb,
x->type->proto);
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index 3361e3a..1e115cb 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -750,7 +750,28 @@
.get_link_net = xfrmi_get_link_net,
};
+static void __net_exit xfrmi_exit_batch_net(struct list_head *net_exit_list)
+{
+ struct net *net;
+ LIST_HEAD(list);
+
+ rtnl_lock();
+ list_for_each_entry(net, net_exit_list, exit_list) {
+ struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id);
+ struct xfrm_if __rcu **xip;
+ struct xfrm_if *xi;
+
+ for (xip = &xfrmn->xfrmi[0];
+ (xi = rtnl_dereference(*xip)) != NULL;
+ xip = &xi->next)
+ unregister_netdevice_queue(xi->dev, &list);
+ }
+ unregister_netdevice_many(&list);
+ rtnl_unlock();
+}
+
static struct pernet_operations xfrmi_net_ops = {
+ .exit_batch = xfrmi_exit_batch_net,
.id = &xfrmi_net_id,
.size = sizeof(struct xfrmi_net),
};
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 2fd3d99..69c4900 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -583,18 +583,20 @@
xfrm_state_hold(x);
if (skb_is_gso(skb)) {
- skb_shinfo(skb)->gso_type |= SKB_GSO_ESP;
+ if (skb->inner_protocol)
+ return xfrm_output_gso(net, sk, skb);
- return xfrm_output2(net, sk, skb);
+ skb_shinfo(skb)->gso_type |= SKB_GSO_ESP;
+ goto out;
}
if (x->xso.dev && x->xso.dev->features & NETIF_F_HW_ESP_TX_CSUM)
goto out;
+ } else {
+ if (skb_is_gso(skb))
+ return xfrm_output_gso(net, sk, skb);
}
- if (skb_is_gso(skb))
- return xfrm_output_gso(net, sk, skb);
-
if (skb->ip_summed == CHECKSUM_PARTIAL) {
err = skb_checksum_help(skb);
if (err) {
@@ -640,7 +642,8 @@
if (skb->protocol == htons(ETH_P_IP))
proto = AF_INET;
- else if (skb->protocol == htons(ETH_P_IPV6))
+ else if (skb->protocol == htons(ETH_P_IPV6) &&
+ skb->sk->sk_family == AF_INET6)
proto = AF_INET6;
else
return;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 297b2fd..564aa649 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1436,12 +1436,7 @@
static bool xfrm_policy_mark_match(struct xfrm_policy *policy,
struct xfrm_policy *pol)
{
- u32 mark = policy->mark.v & policy->mark.m;
-
- if (policy->mark.v == pol->mark.v && policy->mark.m == pol->mark.m)
- return true;
-
- if ((mark & pol->mark.m) == pol->mark.v &&
+ if (policy->mark.v == pol->mark.v &&
policy->priority == pol->priority)
return true;
diff --git a/tools/testing/selftests/bpf/verifier/bounds.c b/tools/testing/selftests/bpf/verifier/bounds.c
index a253a06..58f4aa59 100644
--- a/tools/testing/selftests/bpf/verifier/bounds.c
+++ b/tools/testing/selftests/bpf/verifier/bounds.c
@@ -238,7 +238,7 @@
BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
BPF_LD_MAP_FD(BPF_REG_1, 0),
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
- BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8),
/* r1 = [0x00, 0xff] */
BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0xffffff80 >> 1),
@@ -253,10 +253,6 @@
* [0xffff'ffff'0000'0080, 0xffff'ffff'ffff'ffff]
*/
BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 0xffffff80 >> 1),
- /* r1 = 0 or
- * [0x00ff'ffff'ff00'0000, 0x00ff'ffff'ffff'ffff]
- */
- BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 8),
/* error on OOB pointer computation */
BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
/* exit */
@@ -265,8 +261,10 @@
},
.fixup_map_hash_8b = { 3 },
/* not actually fully unbounded, but the bound is very high */
- .errstr = "value 72057594021150720 makes map_value pointer be out of bounds",
- .result = REJECT
+ .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds, pointer arithmetic with it prohibited for !root",
+ .result_unpriv = REJECT,
+ .errstr = "value -4294967168 makes map_value pointer be out of bounds",
+ .result = REJECT,
},
{
"bounds check after truncation of boundary-crossing range (2)",
@@ -276,7 +274,7 @@
BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
BPF_LD_MAP_FD(BPF_REG_1, 0),
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
- BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8),
/* r1 = [0x00, 0xff] */
BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0xffffff80 >> 1),
@@ -293,10 +291,6 @@
* [0xffff'ffff'0000'0080, 0xffff'ffff'ffff'ffff]
*/
BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 0xffffff80 >> 1),
- /* r1 = 0 or
- * [0x00ff'ffff'ff00'0000, 0x00ff'ffff'ffff'ffff]
- */
- BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 8),
/* error on OOB pointer computation */
BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
/* exit */
@@ -305,8 +299,10 @@
},
.fixup_map_hash_8b = { 3 },
/* not actually fully unbounded, but the bound is very high */
- .errstr = "value 72057594021150720 makes map_value pointer be out of bounds",
- .result = REJECT
+ .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds, pointer arithmetic with it prohibited for !root",
+ .result_unpriv = REJECT,
+ .errstr = "value -4294967168 makes map_value pointer be out of bounds",
+ .result = REJECT,
},
{
"bounds check after wrapping 32-bit addition",
@@ -539,3 +535,25 @@
},
.result = ACCEPT
},
+{
+ "assigning 32bit bounds to 64bit for wA = 0, wB = wA",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1,
+ offsetof(struct __sk_buff, data_end)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
+ offsetof(struct __sk_buff, data)),
+ BPF_MOV32_IMM(BPF_REG_9, 0),
+ BPF_MOV32_REG(BPF_REG_2, BPF_REG_9),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_7),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_6, BPF_REG_2),
+ BPF_MOV64_REG(BPF_REG_3, BPF_REG_6),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 8),
+ BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_8, 1),
+ BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_6, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
