xsk: fix usage of multi-buffer BPF helpers for ZC XDP

Currently when packet is shrunk via bpf_xdp_adjust_tail() and memory
type is set to MEM_TYPE_XSK_BUFF_POOL, null ptr dereference happens:

[1136314.192256] BUG: kernel NULL pointer dereference, address:
0000000000000034
[1136314.203943] #PF: supervisor read access in kernel mode
[1136314.213768] #PF: error_code(0x0000) - not-present page
[1136314.223550] PGD 0 P4D 0
[1136314.230684] Oops: 0000 [#1] PREEMPT SMP NOPTI
[1136314.239621] CPU: 8 PID: 54203 Comm: xdpsock Not tainted 6.6.0+ #257
[1136314.250469] Hardware name: Intel Corporation S2600WFT/S2600WFT,
BIOS SE5C620.86B.02.01.0008.031920191559 03/19/2019
[1136314.265615] RIP: 0010:__xdp_return+0x6c/0x210
[1136314.274653] Code: ad 00 48 8b 47 08 49 89 f8 a8 01 0f 85 9b 01 00 00 0f 1f 44 00 00 f0 41 ff 48 34 75 32 4c 89 c7 e9 79 cd 80 ff 83 fe 03 75 17 <f6> 41 34 01 0f 85 02 01 00 00 48 89 cf e9 22 cc 1e 00 e9 3d d2 86
[1136314.302907] RSP: 0018:ffffc900089f8db0 EFLAGS: 00010246
[1136314.312967] RAX: ffffc9003168aed0 RBX: ffff8881c3300000 RCX:
0000000000000000
[1136314.324953] RDX: 0000000000000000 RSI: 0000000000000003 RDI:
ffffc9003168c000
[1136314.336929] RBP: 0000000000000ae0 R08: 0000000000000002 R09:
0000000000010000
[1136314.348844] R10: ffffc9000e495000 R11: 0000000000000040 R12:
0000000000000001
[1136314.360706] R13: 0000000000000524 R14: ffffc9003168aec0 R15:
0000000000000001
[1136314.373298] FS:  00007f8df8bbcb80(0000) GS:ffff8897e0e00000(0000)
knlGS:0000000000000000
[1136314.386105] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[1136314.396532] CR2: 0000000000000034 CR3: 00000001aa912002 CR4:
00000000007706f0
[1136314.408377] DR0: 0000000000000000 DR1: 0000000000000000 DR2:
0000000000000000
[1136314.420173] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7:
0000000000000400
[1136314.431890] PKRU: 55555554
[1136314.439143] Call Trace:
[1136314.446058]  <IRQ>
[1136314.452465]  ? __die+0x20/0x70
[1136314.459881]  ? page_fault_oops+0x15b/0x440
[1136314.468305]  ? exc_page_fault+0x6a/0x150
[1136314.476491]  ? asm_exc_page_fault+0x22/0x30
[1136314.484927]  ? __xdp_return+0x6c/0x210
[1136314.492863]  bpf_xdp_adjust_tail+0x155/0x1d0
[1136314.501269]  bpf_prog_ccc47ae29d3b6570_xdp_sock_prog+0x15/0x60
[1136314.511263]  ice_clean_rx_irq_zc+0x206/0xc60 [ice]
[1136314.520222]  ? ice_xmit_zc+0x6e/0x150 [ice]
[1136314.528506]  ice_napi_poll+0x467/0x670 [ice]
[1136314.536858]  ? ttwu_do_activate.constprop.0+0x8f/0x1a0
[1136314.546010]  __napi_poll+0x29/0x1b0
[1136314.553462]  net_rx_action+0x133/0x270
[1136314.561619]  __do_softirq+0xbe/0x28e
[1136314.569303]  do_softirq+0x3f/0x60

This comes from __xdp_return() call with xdp_buff argument passed as
NULL which is supposed to be consumed by xsk_buff_free() call.

To address this properly, in ZC case, a node that represents the frag
being removed has to be pulled out of xskb_list. Introduce
appropriate xsk helpers to do such node operation and use them
accordingly within bpf_xdp_adjust_tail().

Fixes: 24ea50127ecf ("xsk: support mbuf on ZC RX")
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com> # For the xsk header part
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20240124191602.566724-4-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index 9819e2af0378c365f33950275827c3207a5266d7..c9aec9ab6191205c7c6f8d3f0f5c136cae520750 100644 (file)
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -159,6 +159,23 @@ static inline struct xdp_buff *xsk_buff_get_frag(struct xdp_buff *first)
        return ret;
 }
 
+static inline void xsk_buff_del_tail(struct xdp_buff *tail)
+{
+       struct xdp_buff_xsk *xskb = container_of(tail, struct xdp_buff_xsk, xdp);
+
+       list_del(&xskb->xskb_list_node);
+}
+
+static inline struct xdp_buff *xsk_buff_get_tail(struct xdp_buff *first)
+{
+       struct xdp_buff_xsk *xskb = container_of(first, struct xdp_buff_xsk, xdp);
+       struct xdp_buff_xsk *frag;
+
+       frag = list_last_entry(&xskb->pool->xskb_list, struct xdp_buff_xsk,
+                              xskb_list_node);
+       return &frag->xdp;
+}
+
 static inline void xsk_buff_set_size(struct xdp_buff *xdp, u32 size)
 {
        xdp->data = xdp->data_hard_start + XDP_PACKET_HEADROOM;
@@ -351,6 +368,15 @@ static inline struct xdp_buff *xsk_buff_get_frag(struct xdp_buff *first)
        return NULL;
 }
 
+static inline void xsk_buff_del_tail(struct xdp_buff *tail)
+{
+}
+
+static inline struct xdp_buff *xsk_buff_get_tail(struct xdp_buff *first)
+{
+       return NULL;
+}
+
 static inline void xsk_buff_set_size(struct xdp_buff *xdp, u32 size)
 {
 }

diff --git a/net/core/filter.c b/net/core/filter.c
index 24061f29c9dd25bcf2e852471d0e8e394ff4121a..36fb5ae8af699be6f0f6b3e70a4d8c9eb8f0fab6 100644 (file)
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -83,6 +83,7 @@
 #include <net/netfilter/nf_conntrack_bpf.h>
 #include <net/netkit.h>
 #include <linux/un.h>
+#include <net/xdp_sock_drv.h>
 
 #include "dev.h"
 
@@ -4096,6 +4097,40 @@ static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset)
        return 0;
 }
 
+static void bpf_xdp_shrink_data_zc(struct xdp_buff *xdp, int shrink,
+                                  struct xdp_mem_info *mem_info, bool release)
+{
+       struct xdp_buff *zc_frag = xsk_buff_get_tail(xdp);
+
+       if (release) {
+               xsk_buff_del_tail(zc_frag);
+               __xdp_return(NULL, mem_info, false, zc_frag);
+       } else {
+               zc_frag->data_end -= shrink;
+       }
+}
+
+static bool bpf_xdp_shrink_data(struct xdp_buff *xdp, skb_frag_t *frag,
+                               int shrink)
+{
+       struct xdp_mem_info *mem_info = &xdp->rxq->mem;
+       bool release = skb_frag_size(frag) == shrink;
+
+       if (mem_info->type == MEM_TYPE_XSK_BUFF_POOL) {
+               bpf_xdp_shrink_data_zc(xdp, shrink, mem_info, release);
+               goto out;
+       }
+
+       if (release) {
+               struct page *page = skb_frag_page(frag);
+
+               __xdp_return(page_address(page), mem_info, false, NULL);
+       }
+
+out:
+       return release;
+}
+
 static int bpf_xdp_frags_shrink_tail(struct xdp_buff *xdp, int offset)
 {
        struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
@@ -4110,12 +4145,7 @@ static int bpf_xdp_frags_shrink_tail(struct xdp_buff *xdp, int offset)
 
                len_free += shrink;
                offset -= shrink;
-
-               if (skb_frag_size(frag) == shrink) {
-                       struct page *page = skb_frag_page(frag);
-
-                       __xdp_return(page_address(page), &xdp->rxq->mem,
-                                    false, NULL);
+               if (bpf_xdp_shrink_data(xdp, frag, shrink)) {
                        n_frags_free++;
                } else {
                        skb_frag_size_sub(frag, shrink);