linux/include/net/xdp_sock_drv.h
Maciej Fijalkowski 82ee4781b8 xsk: fix usage of multi-buffer BPF helpers for ZC XDP
[ Upstream commit c5114710c8 ]

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: 24ea50127e ("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>
Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-01-31 16:19:04 -08:00

367 lines
8.3 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
/* Interface for implementing AF_XDP zero-copy support in drivers.
* Copyright(c) 2020 Intel Corporation.
*/
#ifndef _LINUX_XDP_SOCK_DRV_H
#define _LINUX_XDP_SOCK_DRV_H
#include <net/xdp_sock.h>
#include <net/xsk_buff_pool.h>
#define XDP_UMEM_MIN_CHUNK_SHIFT 11
#define XDP_UMEM_MIN_CHUNK_SIZE (1 << XDP_UMEM_MIN_CHUNK_SHIFT)
#ifdef CONFIG_XDP_SOCKETS
void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries);
bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc);
u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 max);
void xsk_tx_release(struct xsk_buff_pool *pool);
struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev,
u16 queue_id);
void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool);
void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool);
void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool);
void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool);
bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool);
static inline u32 xsk_pool_get_headroom(struct xsk_buff_pool *pool)
{
return XDP_PACKET_HEADROOM + pool->headroom;
}
static inline u32 xsk_pool_get_chunk_size(struct xsk_buff_pool *pool)
{
return pool->chunk_size;
}
static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool)
{
return xsk_pool_get_chunk_size(pool) - xsk_pool_get_headroom(pool);
}
static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool,
struct xdp_rxq_info *rxq)
{
xp_set_rxq_info(pool, rxq);
}
static inline unsigned int xsk_pool_get_napi_id(struct xsk_buff_pool *pool)
{
#ifdef CONFIG_NET_RX_BUSY_POLL
return pool->heads[0].xdp.rxq->napi_id;
#else
return 0;
#endif
}
static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool,
unsigned long attrs)
{
xp_dma_unmap(pool, attrs);
}
static inline int xsk_pool_dma_map(struct xsk_buff_pool *pool,
struct device *dev, unsigned long attrs)
{
struct xdp_umem *umem = pool->umem;
return xp_dma_map(pool, dev, attrs, umem->pgs, umem->npgs);
}
static inline dma_addr_t xsk_buff_xdp_get_dma(struct xdp_buff *xdp)
{
struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
return xp_get_dma(xskb);
}
static inline dma_addr_t xsk_buff_xdp_get_frame_dma(struct xdp_buff *xdp)
{
struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
return xp_get_frame_dma(xskb);
}
static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool)
{
return xp_alloc(pool);
}
static inline bool xsk_is_eop_desc(struct xdp_desc *desc)
{
return !xp_mb_desc(desc);
}
/* Returns as many entries as possible up to max. 0 <= N <= max. */
static inline u32 xsk_buff_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max)
{
return xp_alloc_batch(pool, xdp, max);
}
static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count)
{
return xp_can_alloc(pool, count);
}
static inline void xsk_buff_free(struct xdp_buff *xdp)
{
struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
struct list_head *xskb_list = &xskb->pool->xskb_list;
struct xdp_buff_xsk *pos, *tmp;
if (likely(!xdp_buff_has_frags(xdp)))
goto out;
list_for_each_entry_safe(pos, tmp, xskb_list, xskb_list_node) {
list_del(&pos->xskb_list_node);
xp_free(pos);
}
xdp_get_shared_info_from_buff(xdp)->nr_frags = 0;
out:
xp_free(xskb);
}
static inline void xsk_buff_add_frag(struct xdp_buff *xdp)
{
struct xdp_buff_xsk *frag = container_of(xdp, struct xdp_buff_xsk, xdp);
list_add_tail(&frag->xskb_list_node, &frag->pool->xskb_list);
}
static inline struct xdp_buff *xsk_buff_get_frag(struct xdp_buff *first)
{
struct xdp_buff_xsk *xskb = container_of(first, struct xdp_buff_xsk, xdp);
struct xdp_buff *ret = NULL;
struct xdp_buff_xsk *frag;
frag = list_first_entry_or_null(&xskb->pool->xskb_list,
struct xdp_buff_xsk, xskb_list_node);
if (frag) {
list_del(&frag->xskb_list_node);
ret = &frag->xdp;
}
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;
xdp->data_meta = xdp->data;
xdp->data_end = xdp->data + size;
xdp->flags = 0;
}
static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool,
u64 addr)
{
return xp_raw_get_dma(pool, addr);
}
static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
{
return xp_raw_get_data(pool, addr);
}
static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool)
{
struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
if (!pool->dma_need_sync)
return;
xp_dma_sync_for_cpu(xskb);
}
static inline void xsk_buff_raw_dma_sync_for_device(struct xsk_buff_pool *pool,
dma_addr_t dma,
size_t size)
{
xp_dma_sync_for_device(pool, dma, size);
}
#else
static inline void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries)
{
}
static inline bool xsk_tx_peek_desc(struct xsk_buff_pool *pool,
struct xdp_desc *desc)
{
return false;
}
static inline u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 max)
{
return 0;
}
static inline void xsk_tx_release(struct xsk_buff_pool *pool)
{
}
static inline struct xsk_buff_pool *
xsk_get_pool_from_qid(struct net_device *dev, u16 queue_id)
{
return NULL;
}
static inline void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool)
{
}
static inline void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool)
{
}
static inline void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool)
{
}
static inline void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool)
{
}
static inline bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool)
{
return false;
}
static inline u32 xsk_pool_get_headroom(struct xsk_buff_pool *pool)
{
return 0;
}
static inline u32 xsk_pool_get_chunk_size(struct xsk_buff_pool *pool)
{
return 0;
}
static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool)
{
return 0;
}
static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool,
struct xdp_rxq_info *rxq)
{
}
static inline unsigned int xsk_pool_get_napi_id(struct xsk_buff_pool *pool)
{
return 0;
}
static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool,
unsigned long attrs)
{
}
static inline int xsk_pool_dma_map(struct xsk_buff_pool *pool,
struct device *dev, unsigned long attrs)
{
return 0;
}
static inline dma_addr_t xsk_buff_xdp_get_dma(struct xdp_buff *xdp)
{
return 0;
}
static inline dma_addr_t xsk_buff_xdp_get_frame_dma(struct xdp_buff *xdp)
{
return 0;
}
static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool)
{
return NULL;
}
static inline bool xsk_is_eop_desc(struct xdp_desc *desc)
{
return false;
}
static inline u32 xsk_buff_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max)
{
return 0;
}
static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count)
{
return false;
}
static inline void xsk_buff_free(struct xdp_buff *xdp)
{
}
static inline void xsk_buff_add_frag(struct xdp_buff *xdp)
{
}
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)
{
}
static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool,
u64 addr)
{
return 0;
}
static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
{
return NULL;
}
static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool)
{
}
static inline void xsk_buff_raw_dma_sync_for_device(struct xsk_buff_pool *pool,
dma_addr_t dma,
size_t size)
{
}
#endif /* CONFIG_XDP_SOCKETS */
#endif /* _LINUX_XDP_SOCK_DRV_H */