bpf: Ensure 8-byte alignment for lpm_trie map values
PATCH 1/1 bpf: Ensure 8-byte alignment for lpm_trie map values
The BPF verifier validates the alignment of PTR_TO_MAP_VALUE accesses in check_ptr_alignment() only against the offset relative to the start of the map value, assuming that the map value base address itself is at least 8-byte aligned.
While hash maps enforce this invariant by rounding the key size up to 8 bytes (l->key + round_up(key_size, 8)), lpm_trie places the map value immediately after the key bytes at node->data + trie->data_size without padding. Because trie->data_size (key_size - 4) can be any value from 1 to 256, the value pointer returned by trie_lookup_elem() is only aligned to (trie->data_size % 8).
In particular, for an IPv4 LPM trie (key_size = 8, data_size = 4), the map value base address is always 4-byte aligned (4 mod 8, and either 4 or 12 mod 16). The verifier accepts 8-byte atomic operations (BPF_ATOMIC | BPF_DW) at 8-byte aligned offsets within the value (e.g. offset 0 and offset 8), but at runtime on arm64 the JITed 64-bit atomic (stadd) faults with an unhandled hardware alignment fault (ESR.FSC = 0x21, crossing a 16-byte granule boundary on FEAT_LSE2 CPUs, or on any 4-byte aligned address without FEAT_LSE2) and panics the kernel:
Unable to handle kernel paging request at virtual address
0xffff00000159db6c
Mem abort info:
ESR = 0x0000000096000021
EC = 0x25: DABT (current EL), IL = 32 bits
FSC = 0x21: alignment fault
Internal error: Oops: 0x96000021 [#1] SMP
pc : bpf_prog_cc9155b98965fc5e+0x64/0x90
Call trace:
bpf_prog_cc9155b98965fc5e+0x64/0x90 (P)
bpf_dispatcher_xdp_func+0x14/0x28
bpf_test_run+0x11c/0x360
bpf_prog_test_run_xdp+0x358/0x548
Kernel panic - not syncing: Oops: Fatal exception in interruptThis issue was found while formally specifying eBPF map-value alignment invariants on Linux 7.3.5.
Fix this by marking struct lpm_trie_node's data[] flexible array as __aligned(8) and rounding the value offset up to 8 bytes with round_up(trie->data_size, 8) in trie_alloc(), lpm_trie_node_alloc(), trie_lookup_elem(), and trie_mem_usage(), matching hashtab. Verified on Linux 7.3.5 (arm64 under QEMU) with an XDP program executing 64-bit atomic adds at offsets 0 and 8 of an IPv4 lpm_trie map value.
---
A standalone reproducer is available on request.
kernel/bpf/lpm_trie.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-)
kernel/bpf/lpm_trie.c +8 -6
@@ -27,7 +27,7 @@ struct lpm_trie_node {struct lpm_trie_node __rcu *child[2 ];u32 prefixlen;u32 flags; -u8 data[]; +u8 data[]__aligned(8) ; };struct lpm_trie {
@@ -286,7 +286,7 @@ static void *trie_lookup_elem(struct bpf_map *map, void *_key)if (!found)return NULL ; -return found->data + trie->data_size; +return found->data +round_up (trie->data_size,8 ); } static struct lpm_trie_node *lpm_trie_node_alloc(struct lpm_trie *trie,
@@ -302,7 +302,7 @@ static struct lpm_trie_node *lpm_trie_node_alloc(struct lpm_trie *trie, node->flags =0 ;if (value) -memcpy (node->data + trie->data_size, value, +memcpy (node->data +round_up (trie->data_size,8 ), value, trie->map.value_size);return node;
@@ -598,7 +598,8 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr)raw_res_spin_lock_init (&trie->lock);/* Allocate intermediate and leaf nodes from the same allocator */ - leaf_size =sizeof (struct lpm_trie_node ) + trie->data_size + + leaf_size =sizeof (struct lpm_trie_node ) + +round_up (trie->data_size,8 ) + trie->map.value_size; err =bpf_mem_alloc_init (&trie->ma, leaf_size, false);if (err)
@@ -766,8 +767,9 @@ static u64 trie_mem_usage(const struct bpf_map *map) struct lpm_trie *trie = container_of(map, struct lpm_trie, map);u64 elem_size; - elem_size =sizeof (struct lpm_trie_node ) + trie->data_size + - trie->map.value_size; + elem_size =sizeof (struct lpm_trie_node ) + +round_up (trie->data_size,8 ) + + trie->map.value_size;return elem_size *READ_ONCE (trie->n_entries); }
Signature · 1 line
2.46.0