mirror of
https://github.com/torvalds/linux
synced 2024-09-06 18:01:05 +00:00
![Maciej Fijalkowski](/assets/img/avatar_default.png)
Fix a crash that happens if an Rx only socket is created first, then a
second socket is created that is Tx only and bound to the same umem as
the first socket and also the same netdev and queue_id together with the
XDP_SHARED_UMEM flag. In this specific case, the tx_descs array page
pool was not created by the first socket as it was an Rx only socket.
When the second socket is bound it needs this tx_descs array of this
shared page pool as it has a Tx component, but unfortunately it was
never allocated, leading to a crash. Note that this array is only used
for zero-copy drivers using the batched Tx APIs, currently only ice and
i40e.
[ 5511.150360] BUG: kernel NULL pointer dereference, address: 0000000000000008
[ 5511.158419] #PF: supervisor write access in kernel mode
[ 5511.164472] #PF: error_code(0x0002) - not-present page
[ 5511.170416] PGD 0 P4D 0
[ 5511.173347] Oops: 0002 [#1] PREEMPT SMP PTI
[ 5511.178186] CPU: 0 PID: 0 Comm: swapper/0 Tainted: G E 5.18.0-rc1+ #97
[ 5511.187245] Hardware name: Intel Corp. GRANTLEY/GRANTLEY, BIOS GRRFCRB1.86B.0276.D07.1605190235 05/19/2016
[ 5511.198418] RIP: 0010:xsk_tx_peek_release_desc_batch+0x198/0x310
[ 5511.205375] Code: c0 83 c6 01 84 c2 74 6d 8d 46 ff 23 07 44 89 e1 48 83 c0 14 48 c1 e1 04 48 c1 e0 04 48 03 47 10 4c 01 c1 48 8b 50 08 48 8b 00 <48> 89 51 08 48 89 01 41 80 bd d7 00 00 00 00 75 82 48 8b 19 49 8b
[ 5511.227091] RSP: 0018:ffffc90000003dd0 EFLAGS: 00010246
[ 5511.233135] RAX: 0000000000000000 RBX: ffff88810c8da600 RCX: 0000000000000000
[ 5511.241384] RDX: 000000000000003c RSI: 0000000000000001 RDI: ffff888115f555c0
[ 5511.249634] RBP: ffffc90000003e08 R08: 0000000000000000 R09: ffff889092296b48
[ 5511.257886] R10: 0000ffffffffffff R11: ffff889092296800 R12: 0000000000000000
[ 5511.266138] R13: ffff88810c8db500 R14: 0000000000000040 R15: 0000000000000100
[ 5511.274387] FS: 0000000000000000(0000) GS:ffff88903f800000(0000) knlGS:0000000000000000
[ 5511.283746] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 5511.290389] CR2: 0000000000000008 CR3: 00000001046e2001 CR4: 00000000003706f0
[ 5511.298640] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 5511.306892] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 5511.315142] Call Trace:
[ 5511.317972] <IRQ>
[ 5511.320301] ice_xmit_zc+0x68/0x2f0 [ice]
[ 5511.324977] ? ktime_get+0x38/0xa0
[ 5511.328913] ice_napi_poll+0x7a/0x6a0 [ice]
[ 5511.333784] __napi_poll+0x2c/0x160
[ 5511.337821] net_rx_action+0xdd/0x200
[ 5511.342058] __do_softirq+0xe6/0x2dd
[ 5511.346198] irq_exit_rcu+0xb5/0x100
[ 5511.350339] common_interrupt+0xa4/0xc0
[ 5511.354777] </IRQ>
[ 5511.357201] <TASK>
[ 5511.359625] asm_common_interrupt+0x1e/0x40
[ 5511.364466] RIP: 0010:cpuidle_enter_state+0xd2/0x360
[ 5511.370211] Code: 49 89 c5 0f 1f 44 00 00 31 ff e8 e9 00 7b ff 45 84 ff 74 12 9c 58 f6 c4 02 0f 85 72 02 00 00 31 ff e8 02 0c 80 ff fb 45 85 f6 <0f> 88 11 01 00 00 49 63 c6 4c 2b 2c 24 48 8d 14 40 48 8d 14 90 49
[ 5511.391921] RSP: 0018:ffffffff82a03e60 EFLAGS: 00000202
[ 5511.397962] RAX: ffff88903f800000 RBX: 0000000000000001 RCX: 000000000000001f
[ 5511.406214] RDX: 0000000000000000 RSI: ffffffff823400b9 RDI: ffffffff8234c046
[ 5511.424646] RBP: ffff88810a384800 R08: 000005032a28c046 R09: 0000000000000008
[ 5511.443233] R10: 000000000000000b R11: 0000000000000006 R12: ffffffff82bcf700
[ 5511.461922] R13: 000005032a28c046 R14: 0000000000000001 R15: 0000000000000000
[ 5511.480300] cpuidle_enter+0x29/0x40
[ 5511.494329] do_idle+0x1c7/0x250
[ 5511.507610] cpu_startup_entry+0x19/0x20
[ 5511.521394] start_kernel+0x649/0x66e
[ 5511.534626] secondary_startup_64_no_verify+0xc3/0xcb
[ 5511.549230] </TASK>
Detect such case during bind() and allocate this memory region via newly
introduced xp_alloc_tx_descs(). Also, use kvcalloc instead of kcalloc as
for other buffer pool allocations, so that it matches the kvfree() from
xp_destroy().
Fixes: d1bc532e99
("i40e: xsk: Move tmp desc array from driver to pool")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/bpf/20220425153745.481322-1-maciej.fijalkowski@intel.com
230 lines
6.5 KiB
C
230 lines
6.5 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/* Copyright(c) 2020 Intel Corporation. */
|
|
|
|
#ifndef XSK_BUFF_POOL_H_
|
|
#define XSK_BUFF_POOL_H_
|
|
|
|
#include <linux/if_xdp.h>
|
|
#include <linux/types.h>
|
|
#include <linux/dma-mapping.h>
|
|
#include <linux/bpf.h>
|
|
#include <net/xdp.h>
|
|
|
|
struct xsk_buff_pool;
|
|
struct xdp_rxq_info;
|
|
struct xsk_queue;
|
|
struct xdp_desc;
|
|
struct xdp_umem;
|
|
struct xdp_sock;
|
|
struct device;
|
|
struct page;
|
|
|
|
struct xdp_buff_xsk {
|
|
struct xdp_buff xdp;
|
|
dma_addr_t dma;
|
|
dma_addr_t frame_dma;
|
|
struct xsk_buff_pool *pool;
|
|
u64 orig_addr;
|
|
struct list_head free_list_node;
|
|
};
|
|
|
|
struct xsk_dma_map {
|
|
dma_addr_t *dma_pages;
|
|
struct device *dev;
|
|
struct net_device *netdev;
|
|
refcount_t users;
|
|
struct list_head list; /* Protected by the RTNL_LOCK */
|
|
u32 dma_pages_cnt;
|
|
bool dma_need_sync;
|
|
};
|
|
|
|
struct xsk_buff_pool {
|
|
/* Members only used in the control path first. */
|
|
struct device *dev;
|
|
struct net_device *netdev;
|
|
struct list_head xsk_tx_list;
|
|
/* Protects modifications to the xsk_tx_list */
|
|
spinlock_t xsk_tx_list_lock;
|
|
refcount_t users;
|
|
struct xdp_umem *umem;
|
|
struct work_struct work;
|
|
struct list_head free_list;
|
|
u32 heads_cnt;
|
|
u16 queue_id;
|
|
|
|
/* Data path members as close to free_heads at the end as possible. */
|
|
struct xsk_queue *fq ____cacheline_aligned_in_smp;
|
|
struct xsk_queue *cq;
|
|
/* For performance reasons, each buff pool has its own array of dma_pages
|
|
* even when they are identical.
|
|
*/
|
|
dma_addr_t *dma_pages;
|
|
struct xdp_buff_xsk *heads;
|
|
struct xdp_desc *tx_descs;
|
|
u64 chunk_mask;
|
|
u64 addrs_cnt;
|
|
u32 free_list_cnt;
|
|
u32 dma_pages_cnt;
|
|
u32 free_heads_cnt;
|
|
u32 headroom;
|
|
u32 chunk_size;
|
|
u32 chunk_shift;
|
|
u32 frame_len;
|
|
u8 cached_need_wakeup;
|
|
bool uses_need_wakeup;
|
|
bool dma_need_sync;
|
|
bool unaligned;
|
|
void *addrs;
|
|
/* Mutual exclusion of the completion ring in the SKB mode. Two cases to protect:
|
|
* NAPI TX thread and sendmsg error paths in the SKB destructor callback and when
|
|
* sockets share a single cq when the same netdev and queue id is shared.
|
|
*/
|
|
spinlock_t cq_lock;
|
|
struct xdp_buff_xsk *free_heads[];
|
|
};
|
|
|
|
/* Masks for xdp_umem_page flags.
|
|
* The low 12-bits of the addr will be 0 since this is the page address, so we
|
|
* can use them for flags.
|
|
*/
|
|
#define XSK_NEXT_PG_CONTIG_SHIFT 0
|
|
#define XSK_NEXT_PG_CONTIG_MASK BIT_ULL(XSK_NEXT_PG_CONTIG_SHIFT)
|
|
|
|
/* AF_XDP core. */
|
|
struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
|
|
struct xdp_umem *umem);
|
|
int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev,
|
|
u16 queue_id, u16 flags);
|
|
int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem,
|
|
struct net_device *dev, u16 queue_id);
|
|
int xp_alloc_tx_descs(struct xsk_buff_pool *pool, struct xdp_sock *xs);
|
|
void xp_destroy(struct xsk_buff_pool *pool);
|
|
void xp_get_pool(struct xsk_buff_pool *pool);
|
|
bool xp_put_pool(struct xsk_buff_pool *pool);
|
|
void xp_clear_dev(struct xsk_buff_pool *pool);
|
|
void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs);
|
|
void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs);
|
|
|
|
/* AF_XDP, and XDP core. */
|
|
void xp_free(struct xdp_buff_xsk *xskb);
|
|
|
|
static inline void xp_init_xskb_addr(struct xdp_buff_xsk *xskb, struct xsk_buff_pool *pool,
|
|
u64 addr)
|
|
{
|
|
xskb->orig_addr = addr;
|
|
xskb->xdp.data_hard_start = pool->addrs + addr + pool->headroom;
|
|
}
|
|
|
|
static inline void xp_init_xskb_dma(struct xdp_buff_xsk *xskb, struct xsk_buff_pool *pool,
|
|
dma_addr_t *dma_pages, u64 addr)
|
|
{
|
|
xskb->frame_dma = (dma_pages[addr >> PAGE_SHIFT] & ~XSK_NEXT_PG_CONTIG_MASK) +
|
|
(addr & ~PAGE_MASK);
|
|
xskb->dma = xskb->frame_dma + pool->headroom + XDP_PACKET_HEADROOM;
|
|
}
|
|
|
|
/* AF_XDP ZC drivers, via xdp_sock_buff.h */
|
|
void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq);
|
|
int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev,
|
|
unsigned long attrs, struct page **pages, u32 nr_pages);
|
|
void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs);
|
|
struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool);
|
|
u32 xp_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max);
|
|
bool xp_can_alloc(struct xsk_buff_pool *pool, u32 count);
|
|
void *xp_raw_get_data(struct xsk_buff_pool *pool, u64 addr);
|
|
dma_addr_t xp_raw_get_dma(struct xsk_buff_pool *pool, u64 addr);
|
|
static inline dma_addr_t xp_get_dma(struct xdp_buff_xsk *xskb)
|
|
{
|
|
return xskb->dma;
|
|
}
|
|
|
|
static inline dma_addr_t xp_get_frame_dma(struct xdp_buff_xsk *xskb)
|
|
{
|
|
return xskb->frame_dma;
|
|
}
|
|
|
|
void xp_dma_sync_for_cpu_slow(struct xdp_buff_xsk *xskb);
|
|
static inline void xp_dma_sync_for_cpu(struct xdp_buff_xsk *xskb)
|
|
{
|
|
xp_dma_sync_for_cpu_slow(xskb);
|
|
}
|
|
|
|
void xp_dma_sync_for_device_slow(struct xsk_buff_pool *pool, dma_addr_t dma,
|
|
size_t size);
|
|
static inline void xp_dma_sync_for_device(struct xsk_buff_pool *pool,
|
|
dma_addr_t dma, size_t size)
|
|
{
|
|
if (!pool->dma_need_sync)
|
|
return;
|
|
|
|
xp_dma_sync_for_device_slow(pool, dma, size);
|
|
}
|
|
|
|
/* Masks for xdp_umem_page flags.
|
|
* The low 12-bits of the addr will be 0 since this is the page address, so we
|
|
* can use them for flags.
|
|
*/
|
|
#define XSK_NEXT_PG_CONTIG_SHIFT 0
|
|
#define XSK_NEXT_PG_CONTIG_MASK BIT_ULL(XSK_NEXT_PG_CONTIG_SHIFT)
|
|
|
|
static inline bool xp_desc_crosses_non_contig_pg(struct xsk_buff_pool *pool,
|
|
u64 addr, u32 len)
|
|
{
|
|
bool cross_pg = (addr & (PAGE_SIZE - 1)) + len > PAGE_SIZE;
|
|
|
|
if (likely(!cross_pg))
|
|
return false;
|
|
|
|
if (pool->dma_pages_cnt) {
|
|
return !(pool->dma_pages[addr >> PAGE_SHIFT] &
|
|
XSK_NEXT_PG_CONTIG_MASK);
|
|
}
|
|
|
|
/* skb path */
|
|
return addr + len > pool->addrs_cnt;
|
|
}
|
|
|
|
static inline u64 xp_aligned_extract_addr(struct xsk_buff_pool *pool, u64 addr)
|
|
{
|
|
return addr & pool->chunk_mask;
|
|
}
|
|
|
|
static inline u64 xp_unaligned_extract_addr(u64 addr)
|
|
{
|
|
return addr & XSK_UNALIGNED_BUF_ADDR_MASK;
|
|
}
|
|
|
|
static inline u64 xp_unaligned_extract_offset(u64 addr)
|
|
{
|
|
return addr >> XSK_UNALIGNED_BUF_OFFSET_SHIFT;
|
|
}
|
|
|
|
static inline u64 xp_unaligned_add_offset_to_addr(u64 addr)
|
|
{
|
|
return xp_unaligned_extract_addr(addr) +
|
|
xp_unaligned_extract_offset(addr);
|
|
}
|
|
|
|
static inline u32 xp_aligned_extract_idx(struct xsk_buff_pool *pool, u64 addr)
|
|
{
|
|
return xp_aligned_extract_addr(pool, addr) >> pool->chunk_shift;
|
|
}
|
|
|
|
static inline void xp_release(struct xdp_buff_xsk *xskb)
|
|
{
|
|
if (xskb->pool->unaligned)
|
|
xskb->pool->free_heads[xskb->pool->free_heads_cnt++] = xskb;
|
|
}
|
|
|
|
static inline u64 xp_get_handle(struct xdp_buff_xsk *xskb)
|
|
{
|
|
u64 offset = xskb->xdp.data - xskb->xdp.data_hard_start;
|
|
|
|
offset += xskb->pool->headroom;
|
|
if (!xskb->pool->unaligned)
|
|
return xskb->orig_addr + offset;
|
|
return xskb->orig_addr + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT);
|
|
}
|
|
|
|
#endif /* XSK_BUFF_POOL_H_ */
|