- Kernel - mailweb.openeuler.org

[PATCH openEuler-22.03-LTS-SP1] bcache: fix variable length array abuse in btree_iter
by Yuan Can 26 Sep '24

26 Sep '24

From: Matthew Mirvish <matthew(a)mm12.xyz> stable inclusion from stable-v5.10.221 commit 2c3d7b03b658dc8bfa6112b194b67b92a87e081b category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAB04K CVE: CVE-2024-39482 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 3a861560ccb35f2a4f0a4b8207fa7c2a35fc7f31 upstream. btree_iter is used in two ways: either allocated on the stack with a fixed size MAX_BSETS, or from a mempool with a dynamic size based on the specific cache set. Previously, the struct had a fixed-length array of size MAX_BSETS which was indexed out-of-bounds for the dynamically-sized iterators, which causes UBSAN to complain. This patch uses the same approach as in bcachefs's sort_iter and splits the iterator into a btree_iter with a flexible array member and a btree_iter_stack which embeds a btree_iter as well as a fixed-length data array. Cc: stable(a)vger.kernel.org Closes: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/2039368 Signed-off-by: Matthew Mirvish <matthew(a)mm12.xyz> Signed-off-by: Coly Li <colyli(a)suse.de> Link: https://lore.kernel.org/r/20240509011117.2697-3-colyli@suse.de Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yuan Can <yuancan(a)huawei.com> --- drivers/md/bcache/bset.c | 44 +++++++++++++++++------------------ drivers/md/bcache/bset.h | 28 ++++++++++++++-------- drivers/md/bcache/btree.c | 40 ++++++++++++++++--------------- drivers/md/bcache/super.c | 5 ++-- drivers/md/bcache/sysfs.c | 2 +- drivers/md/bcache/writeback.c | 10 ++++---- 6 files changed, 70 insertions(+), 59 deletions(-) diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c index 94d38e8a59b3..cb544207427b 100644 --- a/drivers/md/bcache/bset.c +++ b/drivers/md/bcache/bset.c @@ -54,7 +54,7 @@ void bch_dump_bucket(struct btree_keys *b) int __bch_count_data(struct btree_keys *b) { unsigned int ret = 0; - struct btree_iter iter; + struct btree_iter_stack iter; struct bkey *k; if (b->ops->is_extents) @@ -67,7 +67,7 @@ void __bch_check_keys(struct btree_keys *b, const char *fmt, ...) { va_list args; struct bkey *k, *p = NULL; - struct btree_iter iter; + struct btree_iter_stack iter; const char *err; for_each_key(b, k, &iter) { @@ -879,7 +879,7 @@ unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k, unsigned int status = BTREE_INSERT_STATUS_NO_INSERT; struct bset *i = bset_tree_last(b)->data; struct bkey *m, *prev = NULL; - struct btree_iter iter; + struct btree_iter_stack iter; struct bkey preceding_key_on_stack = ZERO_KEY; struct bkey *preceding_key_p = &preceding_key_on_stack; @@ -895,9 +895,9 @@ unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k, else preceding_key(k, &preceding_key_p); - m = bch_btree_iter_init(b, &iter, preceding_key_p); + m = bch_btree_iter_stack_init(b, &iter, preceding_key_p); - if (b->ops->insert_fixup(b, k, &iter, replace_key)) + if (b->ops->insert_fixup(b, k, &iter.iter, replace_key)) return status; status = BTREE_INSERT_STATUS_INSERT; @@ -1100,33 +1100,33 @@ void bch_btree_iter_push(struct btree_iter *iter, struct bkey *k, btree_iter_cmp)); } -static struct bkey *__bch_btree_iter_init(struct btree_keys *b, - struct btree_iter *iter, - struct bkey *search, - struct bset_tree *start) +static struct bkey *__bch_btree_iter_stack_init(struct btree_keys *b, + struct btree_iter_stack *iter, + struct bkey *search, + struct bset_tree *start) { struct bkey *ret = NULL; - iter->size = ARRAY_SIZE(iter->data); - iter->used = 0; + iter->iter.size = ARRAY_SIZE(iter->stack_data); + iter->iter.used = 0; #ifdef CONFIG_BCACHE_DEBUG - iter->b = b; + iter->iter.b = b; #endif for (; start <= bset_tree_last(b); start++) { ret = bch_bset_search(b, start, search); - bch_btree_iter_push(iter, ret, bset_bkey_last(start->data)); + bch_btree_iter_push(&iter->iter, ret, bset_bkey_last(start->data)); } return ret; } -struct bkey *bch_btree_iter_init(struct btree_keys *b, - struct btree_iter *iter, +struct bkey *bch_btree_iter_stack_init(struct btree_keys *b, + struct btree_iter_stack *iter, struct bkey *search) { - return __bch_btree_iter_init(b, iter, search, b->set); + return __bch_btree_iter_stack_init(b, iter, search, b->set); } static inline struct bkey *__bch_btree_iter_next(struct btree_iter *iter, @@ -1293,10 +1293,10 @@ void bch_btree_sort_partial(struct btree_keys *b, unsigned int start, struct bset_sort_state *state) { size_t order = b->page_order, keys = 0; - struct btree_iter iter; + struct btree_iter_stack iter; int oldsize = bch_count_data(b); - __bch_btree_iter_init(b, &iter, NULL, &b->set[start]); + __bch_btree_iter_stack_init(b, &iter, NULL, &b->set[start]); if (start) { unsigned int i; @@ -1307,7 +1307,7 @@ void bch_btree_sort_partial(struct btree_keys *b, unsigned int start, order = get_order(__set_bytes(b->set->data, keys)); } - __btree_sort(b, &iter, start, order, false, state); + __btree_sort(b, &iter.iter, start, order, false, state); EBUG_ON(oldsize >= 0 && bch_count_data(b) != oldsize); } @@ -1323,11 +1323,11 @@ void bch_btree_sort_into(struct btree_keys *b, struct btree_keys *new, struct bset_sort_state *state) { uint64_t start_time = local_clock(); - struct btree_iter iter; + struct btree_iter_stack iter; - bch_btree_iter_init(b, &iter, NULL); + bch_btree_iter_stack_init(b, &iter, NULL); - btree_mergesort(b, new->set->data, &iter, false, true); + btree_mergesort(b, new->set->data, &iter.iter, false, true); bch_time_stats_update(&state->time, start_time); diff --git a/drivers/md/bcache/bset.h b/drivers/md/bcache/bset.h index d795c84246b0..011f6062c4c0 100644 --- a/drivers/md/bcache/bset.h +++ b/drivers/md/bcache/bset.h @@ -321,7 +321,14 @@ struct btree_iter { #endif struct btree_iter_set { struct bkey *k, *end; - } data[MAX_BSETS]; + } data[]; +}; + +/* Fixed-size btree_iter that can be allocated on the stack */ + +struct btree_iter_stack { + struct btree_iter iter; + struct btree_iter_set stack_data[MAX_BSETS]; }; typedef bool (*ptr_filter_fn)(struct btree_keys *b, const struct bkey *k); @@ -333,9 +340,9 @@ struct bkey *bch_btree_iter_next_filter(struct btree_iter *iter, void bch_btree_iter_push(struct btree_iter *iter, struct bkey *k, struct bkey *end); -struct bkey *bch_btree_iter_init(struct btree_keys *b, - struct btree_iter *iter, - struct bkey *search); +struct bkey *bch_btree_iter_stack_init(struct btree_keys *b, + struct btree_iter_stack *iter, + struct bkey *search); struct bkey *__bch_bset_search(struct btree_keys *b, struct bset_tree *t, const struct bkey *search); @@ -350,13 +357,14 @@ static inline struct bkey *bch_bset_search(struct btree_keys *b, return search ? __bch_bset_search(b, t, search) : t->data->start; } -#define for_each_key_filter(b, k, iter, filter) \ - for (bch_btree_iter_init((b), (iter), NULL); \ - ((k) = bch_btree_iter_next_filter((iter), (b), filter));) +#define for_each_key_filter(b, k, stack_iter, filter) \ + for (bch_btree_iter_stack_init((b), (stack_iter), NULL); \ + ((k) = bch_btree_iter_next_filter(&((stack_iter)->iter), (b), \ + filter));) -#define for_each_key(b, k, iter) \ - for (bch_btree_iter_init((b), (iter), NULL); \ - ((k) = bch_btree_iter_next(iter));) +#define for_each_key(b, k, stack_iter) \ + for (bch_btree_iter_stack_init((b), (stack_iter), NULL); \ + ((k) = bch_btree_iter_next(&((stack_iter)->iter)));) /* Sorting */ diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index 98daa9d200f7..da24a3ca69e5 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -1274,7 +1274,7 @@ static bool btree_gc_mark_node(struct btree *b, struct gc_stat *gc) uint8_t stale = 0; unsigned int keys = 0, good_keys = 0; struct bkey *k; - struct btree_iter iter; + struct btree_iter_stack iter; struct bset_tree *t; gc->nodes++; @@ -1533,7 +1533,7 @@ static int btree_gc_rewrite_node(struct btree *b, struct btree_op *op, static unsigned int btree_gc_count_keys(struct btree *b) { struct bkey *k; - struct btree_iter iter; + struct btree_iter_stack iter; unsigned int ret = 0; for_each_key_filter(&b->keys, k, &iter, bch_ptr_bad) @@ -1574,17 +1574,18 @@ static int btree_gc_recurse(struct btree *b, struct btree_op *op, int ret = 0; bool should_rewrite; struct bkey *k; - struct btree_iter iter; + struct btree_iter_stack iter; struct gc_merge_info r[GC_MERGE_NODES]; struct gc_merge_info *i, *last = r + ARRAY_SIZE(r) - 1; - bch_btree_iter_init(&b->keys, &iter, &b->c->gc_done); + bch_btree_iter_stack_init(&b->keys, &iter, &b->c->gc_done); for (i = r; i < r + ARRAY_SIZE(r); i++) i->b = ERR_PTR(-EINTR); while (1) { - k = bch_btree_iter_next_filter(&iter, &b->keys, bch_ptr_bad); + k = bch_btree_iter_next_filter(&iter.iter, &b->keys, + bch_ptr_bad); if (k) { r->b = bch_btree_node_get(b->c, op, k, b->level - 1, true, b); @@ -1874,7 +1875,7 @@ static int bch_btree_check_recurse(struct btree *b, struct btree_op *op) { int ret = 0; struct bkey *k, *p = NULL; - struct btree_iter iter; + struct btree_iter_stack iter; for_each_key_filter(&b->keys, k, &iter, bch_ptr_invalid) bch_initial_mark_key(b->c, b->level, k); @@ -1882,10 +1883,10 @@ static int bch_btree_check_recurse(struct btree *b, struct btree_op *op) bch_initial_mark_key(b->c, b->level + 1, &b->key); if (b->level) { - bch_btree_iter_init(&b->keys, &iter, NULL); + bch_btree_iter_stack_init(&b->keys, &iter, NULL); do { - k = bch_btree_iter_next_filter(&iter, &b->keys, + k = bch_btree_iter_next_filter(&iter.iter, &b->keys, bch_ptr_bad); if (k) { btree_node_prefetch(b, k); @@ -1913,7 +1914,7 @@ static int bch_btree_check_thread(void *arg) struct btree_check_info *info = arg; struct btree_check_state *check_state = info->state; struct cache_set *c = check_state->c; - struct btree_iter iter; + struct btree_iter_stack iter; struct bkey *k, *p; int cur_idx, prev_idx, skip_nr; @@ -1922,8 +1923,8 @@ static int bch_btree_check_thread(void *arg) ret = 0; /* root node keys are checked before thread created */ - bch_btree_iter_init(&c->root->keys, &iter, NULL); - k = bch_btree_iter_next_filter(&iter, &c->root->keys, bch_ptr_bad); + bch_btree_iter_stack_init(&c->root->keys, &iter, NULL); + k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad); BUG_ON(!k); p = k; @@ -1941,7 +1942,7 @@ static int bch_btree_check_thread(void *arg) skip_nr = cur_idx - prev_idx; while (skip_nr) { - k = bch_btree_iter_next_filter(&iter, + k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad); if (k) @@ -2005,7 +2006,7 @@ int bch_btree_check(struct cache_set *c) int ret = 0; int i; struct bkey *k = NULL; - struct btree_iter iter; + struct btree_iter_stack iter; struct btree_check_state check_state; /* check and mark root node keys */ @@ -2501,11 +2502,11 @@ static int bch_btree_map_nodes_recurse(struct btree *b, struct btree_op *op, if (b->level) { struct bkey *k; - struct btree_iter iter; + struct btree_iter_stack iter; - bch_btree_iter_init(&b->keys, &iter, from); + bch_btree_iter_stack_init(&b->keys, &iter, from); - while ((k = bch_btree_iter_next_filter(&iter, &b->keys, + while ((k = bch_btree_iter_next_filter(&iter.iter, &b->keys, bch_ptr_bad))) { ret = bcache_btree(map_nodes_recurse, k, b, op, from, fn, flags); @@ -2534,11 +2535,12 @@ int bch_btree_map_keys_recurse(struct btree *b, struct btree_op *op, { int ret = MAP_CONTINUE; struct bkey *k; - struct btree_iter iter; + struct btree_iter_stack iter; - bch_btree_iter_init(&b->keys, &iter, from); + bch_btree_iter_stack_init(&b->keys, &iter, from); - while ((k = bch_btree_iter_next_filter(&iter, &b->keys, bch_ptr_bad))) { + while ((k = bch_btree_iter_next_filter(&iter.iter, &b->keys, + bch_ptr_bad))) { ret = !b->level ? fn(op, b, k) : bcache_btree(map_keys_recurse, k, diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index b5601f200c09..c778862f4f33 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1928,8 +1928,9 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb) INIT_LIST_HEAD(&c->btree_cache_freed); INIT_LIST_HEAD(&c->data_buckets); - iter_size = ((meta_bucket_pages(sb) * PAGE_SECTORS) / sb->block_size + 1) * - sizeof(struct btree_iter_set); + iter_size = sizeof(struct btree_iter) + + ((meta_bucket_pages(sb) * PAGE_SECTORS) / sb->block_size) * + sizeof(struct btree_iter_set); c->devices = kcalloc(c->nr_uuids, sizeof(void *), GFP_KERNEL); if (!c->devices) diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index 8467e37411a7..84b8e9e90ee6 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -660,7 +660,7 @@ static unsigned int bch_root_usage(struct cache_set *c) unsigned int bytes = 0; struct bkey *k; struct btree *b; - struct btree_iter iter; + struct btree_iter_stack iter; goto lock_root; diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index 83dcdd85abc0..9502cc9b0c80 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -899,15 +899,15 @@ static int bch_dirty_init_thread(void *arg) struct dirty_init_thrd_info *info = arg; struct bch_dirty_init_state *state = info->state; struct cache_set *c = state->c; - struct btree_iter iter; + struct btree_iter_stack iter; struct bkey *k, *p; int cur_idx, prev_idx, skip_nr; k = p = NULL; cur_idx = prev_idx = 0; - bch_btree_iter_init(&c->root->keys, &iter, NULL); - k = bch_btree_iter_next_filter(&iter, &c->root->keys, bch_ptr_bad); + bch_btree_iter_stack_init(&c->root->keys, &iter, NULL); + k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad); BUG_ON(!k); p = k; @@ -921,7 +921,7 @@ static int bch_dirty_init_thread(void *arg) skip_nr = cur_idx - prev_idx; while (skip_nr) { - k = bch_btree_iter_next_filter(&iter, + k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad); if (k) @@ -969,7 +969,7 @@ void bch_sectors_dirty_init(struct bcache_device *d) { int i; struct bkey *k = NULL; - struct btree_iter iter; + struct btree_iter_stack iter; struct sectors_dirty_init op; struct cache_set *c = d->c; struct bch_dirty_init_state state; -- 2.17.1

2 1

[PATCH OLK-6.6] fix: fix version showed in ethtool
by s00851154 26 Sep '24

26 Sep '24

Fix the version in the output of ethtool commands from empty to the kernel version. Use the macro HINIC3_NIC_DRV_VERSION to record driver changes for developers. The last number 1.0.X grow as minor changes, like this revision which does not affect the main functions. The middle number 1.X.1 iterates with changes to drivers functionality and fixing of serious bugs, and the first one X.0.1 means the number of releases of the driver. Signed-off-by: Shi Jing <shijing34(a)huawei.com> --- drivers/net/ethernet/huawei/hinic3/hinic3_ethtool.c | 1 - drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_ethtool.c b/drivers/net/ethernet/huawei/hinic3/hinic3_ethtool.c index 5a1995956a555..4ea526329d155 100644 --- a/drivers/net/ethernet/huawei/hinic3/hinic3_ethtool.c +++ b/drivers/net/ethernet/huawei/hinic3/hinic3_ethtool.c @@ -45,7 +45,6 @@ static void hinic3_get_drvinfo(struct net_device *netdev, int err; strscpy(info->driver, HINIC3_NIC_DRV_NAME, sizeof(info->driver)); - strscpy(info->version, HINIC3_NIC_DRV_VERSION, sizeof(info->version)); strscpy(info->bus_info, pci_name(pdev), sizeof(info->bus_info)); err = hinic3_get_mgmt_version(nic_dev->hwdev, mgmt_ver, diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h index 2967311aab76c..5868187eafa99 100644 --- a/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h +++ b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h @@ -17,7 +17,7 @@ #include "hinic3_dcb.h" #define HINIC3_NIC_DRV_NAME "hinic3" -#define HINIC3_NIC_DRV_VERSION "" +#define HINIC3_NIC_DRV_VERSION "1.0.1" #define HINIC3_FUNC_IS_VF(hwdev) (hinic3_func_type(hwdev) == TYPE_VF) -- 2.28.0.windows.1

2 1

[PATCH OLK-5.10] bpf: verifier: prevent userspace memory access
by Pu Lehui 26 Sep '24

26 Sep '24

From: Puranjay Mohan <puranjay12(a)gmail.com> mainline inclusion from mainline-v6.9-rc7 commit 66e13b615a0ce76b785d780ecc9776ba71983629 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IATK7C Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- With BPF_PROBE_MEM, BPF allows de-referencing an untrusted pointer. To thwart invalid memory accesses, the JITs add an exception table entry for all such accesses. But in case the src_reg + offset is a userspace address, the BPF program might read that memory if the user has mapped it. Make the verifier add guard instructions around such memory accesses and skip the load if the address falls into the userspace region. The JITs need to implement bpf_arch_uaddress_limit() to define where the userspace addresses end for that architecture or TASK_SIZE is taken as default. The implementation is as follows: REG_AX = SRC_REG if(offset) REG_AX += offset; REG_AX >>= 32; if (REG_AX <= (uaddress_limit >> 32)) DST_REG = 0; else DST_REG = *(size *)(SRC_REG + offset); Comparing just the upper 32 bits of the load address with the upper 32 bits of uaddress_limit implies that the values are being aligned down to a 4GB boundary before comparison. The above means that all loads with address <= uaddress_limit + 4GB are skipped. This is acceptable because there is a large hole (much larger than 4GB) between userspace and kernel space memory, therefore a correctly functioning BPF program should not access this 4GB memory above the userspace. Let's analyze what this patch does to the following fentry program dereferencing an untrusted pointer: SEC("fentry/tcp_v4_connect") int BPF_PROG(fentry_tcp_v4_connect, struct sock *sk) { *(volatile long *)sk; return 0; } BPF Program before | BPF Program after ------------------ | ----------------- 0: (79) r1 = *(u64 *)(r1 +0) 0: (79) r1 = *(u64 *)(r1 +0) ----------------------------------------------------------------------- 1: (79) r1 = *(u64 *)(r1 +0) --\ 1: (bf) r11 = r1 ----------------------------\ \ 2: (77) r11 >>= 32 2: (b7) r0 = 0 \ \ 3: (b5) if r11 <= 0x8000 goto pc+2 3: (95) exit \ \-> 4: (79) r1 = *(u64 *)(r1 +0) \ 5: (05) goto pc+1 \ 6: (b7) r1 = 0 \-------------------------------------- 7: (b7) r0 = 0 8: (95) exit As you can see from above, in the best case (off=0), 5 extra instructions are emitted. Now, we analyze the same program after it has gone through the JITs of ARM64 and RISC-V architectures. We follow the single load instruction that has the untrusted pointer and see what instrumentation has been added around it. x86-64 JIT ========== JIT's Instrumentation (upstream) --------------------- 0: nopl 0x0(%rax,%rax,1) 5: xchg %ax,%ax 7: push %rbp 8: mov %rsp,%rbp b: mov 0x0(%rdi),%rdi --------------------------------- f: movabs $0x800000000000,%r11 19: cmp %r11,%rdi 1c: jb 0x000000000000002a 1e: mov %rdi,%r11 21: add $0x0,%r11 28: jae 0x000000000000002e 2a: xor %edi,%edi 2c: jmp 0x0000000000000032 2e: mov 0x0(%rdi),%rdi --------------------------------- 32: xor %eax,%eax 34: leave 35: ret The x86-64 JIT already emits some instructions to protect against user memory access. This patch doesn't make any changes for the x86-64 JIT. ARM64 JIT ========= No Intrumentation Verifier's Instrumentation (upstream) (This patch) ----------------- -------------------------- 0: add x9, x30, #0x0 0: add x9, x30, #0x0 4: nop 4: nop 8: paciasp 8: paciasp c: stp x29, x30, [sp, #-16]! c: stp x29, x30, [sp, #-16]! 10: mov x29, sp 10: mov x29, sp 14: stp x19, x20, [sp, #-16]! 14: stp x19, x20, [sp, #-16]! 18: stp x21, x22, [sp, #-16]! 18: stp x21, x22, [sp, #-16]! 1c: stp x25, x26, [sp, #-16]! 1c: stp x25, x26, [sp, #-16]! 20: stp x27, x28, [sp, #-16]! 20: stp x27, x28, [sp, #-16]! 24: mov x25, sp 24: mov x25, sp 28: mov x26, #0x0 28: mov x26, #0x0 2c: sub x27, x25, #0x0 2c: sub x27, x25, #0x0 30: sub sp, sp, #0x0 30: sub sp, sp, #0x0 34: ldr x0, [x0] 34: ldr x0, [x0] -------------------------------------------------------------------------------- 38: ldr x0, [x0] ----------\ 38: add x9, x0, #0x0 -----------------------------------\\ 3c: lsr x9, x9, #32 3c: mov x7, #0x0 \\ 40: cmp x9, #0x10, lsl #12 40: mov sp, sp \\ 44: b.ls 0x0000000000000050 44: ldp x27, x28, [sp], #16 \\--> 48: ldr x0, [x0] 48: ldp x25, x26, [sp], #16 \ 4c: b 0x0000000000000054 4c: ldp x21, x22, [sp], #16 \ 50: mov x0, #0x0 50: ldp x19, x20, [sp], #16 \--------------------------------------- 54: ldp x29, x30, [sp], #16 54: mov x7, #0x0 58: add x0, x7, #0x0 58: mov sp, sp 5c: autiasp 5c: ldp x27, x28, [sp], #16 60: ret 60: ldp x25, x26, [sp], #16 64: nop 64: ldp x21, x22, [sp], #16 68: ldr x10, 0x0000000000000070 68: ldp x19, x20, [sp], #16 6c: br x10 6c: ldp x29, x30, [sp], #16 70: add x0, x7, #0x0 74: autiasp 78: ret 7c: nop 80: ldr x10, 0x0000000000000088 84: br x10 There are 6 extra instructions added in ARM64 in the best case. This will become 7 in the worst case (off != 0). RISC-V JIT (RISCV_ISA_C Disabled) ========== No Intrumentation Verifier's Instrumentation (upstream) (This patch) ----------------- -------------------------- 0: nop 0: nop 4: nop 4: nop 8: li a6, 33 8: li a6, 33 c: addi sp, sp, -16 c: addi sp, sp, -16 10: sd s0, 8(sp) 10: sd s0, 8(sp) 14: addi s0, sp, 16 14: addi s0, sp, 16 18: ld a0, 0(a0) 18: ld a0, 0(a0) --------------------------------------------------------------- 1c: ld a0, 0(a0) --\ 1c: mv t0, a0 --------------------------\ \ 20: srli t0, t0, 32 20: li a5, 0 \ \ 24: lui t1, 4096 24: ld s0, 8(sp) \ \ 28: sext.w t1, t1 28: addi sp, sp, 16 \ \ 2c: bgeu t1, t0, 12 2c: sext.w a0, a5 \ \--> 30: ld a0, 0(a0) 30: ret \ 34: j 8 \ 38: li a0, 0 \------------------------------ 3c: li a5, 0 40: ld s0, 8(sp) 44: addi sp, sp, 16 48: sext.w a0, a5 4c: ret There are 7 extra instructions added in RISC-V. Fixes: 800834285361 ("bpf, arm64: Add BPF exception tables") Reported-by: Breno Leitao <leitao(a)debian.org> Suggested-by: Alexei Starovoitov <ast(a)kernel.org> Acked-by: Ilya Leoshkevich <iii(a)linux.ibm.com> Signed-off-by: Puranjay Mohan <puranjay12(a)gmail.com> Link: https://lore.kernel.org/r/20240424100210.11982-2-puranjay@kernel.org Signed-off-by: Alexei Starovoitov <ast(a)kernel.org> Conflicts: arch/x86/net/bpf_jit_comp.c kernel/bpf/core.c kernel/bpf/verifier.c include/linux/filter.h [The conflicts were due to not support BPF_PROBE_MEMSX and refactoring about do_misc_fixups] Signed-off-by: Pu Lehui <pulehui(a)huawei.com> --- arch/x86/net/bpf_jit_comp.c | 6 ++++++ include/linux/filter.h | 1 + kernel/bpf/core.c | 9 +++++++++ kernel/bpf/verifier.c | 29 +++++++++++++++++++++++++++++ 4 files changed, 45 insertions(+) diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 8e3c3d8916dd..6c8b9151eda8 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -2156,3 +2156,9 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) tmp : orig_prog); return prog; } + +/* x86-64 JIT emits its own code to filter user addresses so return 0 here */ +u64 bpf_arch_uaddress_limit(void) +{ + return 0; +} diff --git a/include/linux/filter.h b/include/linux/filter.h index ee12183ffad9..8ee00f20614f 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -908,6 +908,7 @@ u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog); void bpf_jit_compile(struct bpf_prog *prog); bool bpf_jit_needs_zext(void); +u64 bpf_arch_uaddress_limit(void); bool bpf_helper_changes_pkt_data(void *func); static inline bool bpf_dump_raw_ok(const struct cred *cred) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 681070bf910b..7db8a815e835 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2321,6 +2321,15 @@ bool __weak bpf_helper_changes_pkt_data(void *func) return false; } +u64 __weak bpf_arch_uaddress_limit(void) +{ +#if defined(CONFIG_64BIT) && defined(CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE) + return TASK_SIZE; +#else + return 0; +#endif +} + /* Return TRUE if the JIT backend wants verifier to enable sub-register usage * analysis code and wants explicit zero extension inserted by verifier. * Otherwise, return FALSE. diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 18ab413ef2ba..a2a77348fa60 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -11464,6 +11464,35 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) continue; } + /* Make it impossible to de-reference a userspace address */ + if (BPF_CLASS(insn->code) == BPF_LDX && + BPF_MODE(insn->code) == BPF_PROBE_MEM) { + struct bpf_insn *patch = &insn_buf[0]; + u64 uaddress_limit = bpf_arch_uaddress_limit(); + + if (!uaddress_limit) + continue; + + *patch++ = BPF_MOV64_REG(BPF_REG_AX, insn->src_reg); + if (insn->off) + *patch++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_AX, insn->off); + *patch++ = BPF_ALU64_IMM(BPF_RSH, BPF_REG_AX, 32); + *patch++ = BPF_JMP_IMM(BPF_JLE, BPF_REG_AX, uaddress_limit >> 32, 2); + *patch++ = *insn; + *patch++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); + *patch++ = BPF_MOV64_IMM(insn->dst_reg, 0); + + cnt = patch - insn_buf; + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } + if (BPF_CLASS(insn->code) == BPF_LD && (BPF_MODE(insn->code) == BPF_ABS || BPF_MODE(insn->code) == BPF_IND)) { -- 2.34.1

2 1

[PATCH openEuler-22.03-LTS-SP1] bpf: verifier: prevent userspace memory access
by Pu Lehui 26 Sep '24

26 Sep '24

From: Puranjay Mohan <puranjay12(a)gmail.com> mainline inclusion from mainline-v6.9-rc7 commit 66e13b615a0ce76b785d780ecc9776ba71983629 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IATK7C Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- With BPF_PROBE_MEM, BPF allows de-referencing an untrusted pointer. To thwart invalid memory accesses, the JITs add an exception table entry for all such accesses. But in case the src_reg + offset is a userspace address, the BPF program might read that memory if the user has mapped it. Make the verifier add guard instructions around such memory accesses and skip the load if the address falls into the userspace region. The JITs need to implement bpf_arch_uaddress_limit() to define where the userspace addresses end for that architecture or TASK_SIZE is taken as default. The implementation is as follows: REG_AX = SRC_REG if(offset) REG_AX += offset; REG_AX >>= 32; if (REG_AX <= (uaddress_limit >> 32)) DST_REG = 0; else DST_REG = *(size *)(SRC_REG + offset); Comparing just the upper 32 bits of the load address with the upper 32 bits of uaddress_limit implies that the values are being aligned down to a 4GB boundary before comparison. The above means that all loads with address <= uaddress_limit + 4GB are skipped. This is acceptable because there is a large hole (much larger than 4GB) between userspace and kernel space memory, therefore a correctly functioning BPF program should not access this 4GB memory above the userspace. Let's analyze what this patch does to the following fentry program dereferencing an untrusted pointer: SEC("fentry/tcp_v4_connect") int BPF_PROG(fentry_tcp_v4_connect, struct sock *sk) { *(volatile long *)sk; return 0; } BPF Program before | BPF Program after ------------------ | ----------------- 0: (79) r1 = *(u64 *)(r1 +0) 0: (79) r1 = *(u64 *)(r1 +0) ----------------------------------------------------------------------- 1: (79) r1 = *(u64 *)(r1 +0) --\ 1: (bf) r11 = r1 ----------------------------\ \ 2: (77) r11 >>= 32 2: (b7) r0 = 0 \ \ 3: (b5) if r11 <= 0x8000 goto pc+2 3: (95) exit \ \-> 4: (79) r1 = *(u64 *)(r1 +0) \ 5: (05) goto pc+1 \ 6: (b7) r1 = 0 \-------------------------------------- 7: (b7) r0 = 0 8: (95) exit As you can see from above, in the best case (off=0), 5 extra instructions are emitted. Now, we analyze the same program after it has gone through the JITs of ARM64 and RISC-V architectures. We follow the single load instruction that has the untrusted pointer and see what instrumentation has been added around it. x86-64 JIT ========== JIT's Instrumentation (upstream) --------------------- 0: nopl 0x0(%rax,%rax,1) 5: xchg %ax,%ax 7: push %rbp 8: mov %rsp,%rbp b: mov 0x0(%rdi),%rdi --------------------------------- f: movabs $0x800000000000,%r11 19: cmp %r11,%rdi 1c: jb 0x000000000000002a 1e: mov %rdi,%r11 21: add $0x0,%r11 28: jae 0x000000000000002e 2a: xor %edi,%edi 2c: jmp 0x0000000000000032 2e: mov 0x0(%rdi),%rdi --------------------------------- 32: xor %eax,%eax 34: leave 35: ret The x86-64 JIT already emits some instructions to protect against user memory access. This patch doesn't make any changes for the x86-64 JIT. ARM64 JIT ========= No Intrumentation Verifier's Instrumentation (upstream) (This patch) ----------------- -------------------------- 0: add x9, x30, #0x0 0: add x9, x30, #0x0 4: nop 4: nop 8: paciasp 8: paciasp c: stp x29, x30, [sp, #-16]! c: stp x29, x30, [sp, #-16]! 10: mov x29, sp 10: mov x29, sp 14: stp x19, x20, [sp, #-16]! 14: stp x19, x20, [sp, #-16]! 18: stp x21, x22, [sp, #-16]! 18: stp x21, x22, [sp, #-16]! 1c: stp x25, x26, [sp, #-16]! 1c: stp x25, x26, [sp, #-16]! 20: stp x27, x28, [sp, #-16]! 20: stp x27, x28, [sp, #-16]! 24: mov x25, sp 24: mov x25, sp 28: mov x26, #0x0 28: mov x26, #0x0 2c: sub x27, x25, #0x0 2c: sub x27, x25, #0x0 30: sub sp, sp, #0x0 30: sub sp, sp, #0x0 34: ldr x0, [x0] 34: ldr x0, [x0] -------------------------------------------------------------------------------- 38: ldr x0, [x0] ----------\ 38: add x9, x0, #0x0 -----------------------------------\\ 3c: lsr x9, x9, #32 3c: mov x7, #0x0 \\ 40: cmp x9, #0x10, lsl #12 40: mov sp, sp \\ 44: b.ls 0x0000000000000050 44: ldp x27, x28, [sp], #16 \\--> 48: ldr x0, [x0] 48: ldp x25, x26, [sp], #16 \ 4c: b 0x0000000000000054 4c: ldp x21, x22, [sp], #16 \ 50: mov x0, #0x0 50: ldp x19, x20, [sp], #16 \--------------------------------------- 54: ldp x29, x30, [sp], #16 54: mov x7, #0x0 58: add x0, x7, #0x0 58: mov sp, sp 5c: autiasp 5c: ldp x27, x28, [sp], #16 60: ret 60: ldp x25, x26, [sp], #16 64: nop 64: ldp x21, x22, [sp], #16 68: ldr x10, 0x0000000000000070 68: ldp x19, x20, [sp], #16 6c: br x10 6c: ldp x29, x30, [sp], #16 70: add x0, x7, #0x0 74: autiasp 78: ret 7c: nop 80: ldr x10, 0x0000000000000088 84: br x10 There are 6 extra instructions added in ARM64 in the best case. This will become 7 in the worst case (off != 0). RISC-V JIT (RISCV_ISA_C Disabled) ========== No Intrumentation Verifier's Instrumentation (upstream) (This patch) ----------------- -------------------------- 0: nop 0: nop 4: nop 4: nop 8: li a6, 33 8: li a6, 33 c: addi sp, sp, -16 c: addi sp, sp, -16 10: sd s0, 8(sp) 10: sd s0, 8(sp) 14: addi s0, sp, 16 14: addi s0, sp, 16 18: ld a0, 0(a0) 18: ld a0, 0(a0) --------------------------------------------------------------- 1c: ld a0, 0(a0) --\ 1c: mv t0, a0 --------------------------\ \ 20: srli t0, t0, 32 20: li a5, 0 \ \ 24: lui t1, 4096 24: ld s0, 8(sp) \ \ 28: sext.w t1, t1 28: addi sp, sp, 16 \ \ 2c: bgeu t1, t0, 12 2c: sext.w a0, a5 \ \--> 30: ld a0, 0(a0) 30: ret \ 34: j 8 \ 38: li a0, 0 \------------------------------ 3c: li a5, 0 40: ld s0, 8(sp) 44: addi sp, sp, 16 48: sext.w a0, a5 4c: ret There are 7 extra instructions added in RISC-V. Fixes: 800834285361 ("bpf, arm64: Add BPF exception tables") Reported-by: Breno Leitao <leitao(a)debian.org> Suggested-by: Alexei Starovoitov <ast(a)kernel.org> Acked-by: Ilya Leoshkevich <iii(a)linux.ibm.com> Signed-off-by: Puranjay Mohan <puranjay12(a)gmail.com> Link: https://lore.kernel.org/r/20240424100210.11982-2-puranjay@kernel.org Signed-off-by: Alexei Starovoitov <ast(a)kernel.org> Conflicts: arch/x86/net/bpf_jit_comp.c kernel/bpf/core.c kernel/bpf/verifier.c include/linux/filter.h [The conflicts were due to not support BPF_PROBE_MEMSX and refactoring about do_misc_fixups] Signed-off-by: Pu Lehui <pulehui(a)huawei.com> --- arch/x86/net/bpf_jit_comp.c | 6 ++++++ include/linux/filter.h | 1 + kernel/bpf/core.c | 9 +++++++++ kernel/bpf/verifier.c | 29 +++++++++++++++++++++++++++++ 4 files changed, 45 insertions(+) diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 8e3c3d8916dd..6c8b9151eda8 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -2156,3 +2156,9 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) tmp : orig_prog); return prog; } + +/* x86-64 JIT emits its own code to filter user addresses so return 0 here */ +u64 bpf_arch_uaddress_limit(void) +{ + return 0; +} diff --git a/include/linux/filter.h b/include/linux/filter.h index ee12183ffad9..8ee00f20614f 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -908,6 +908,7 @@ u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog); void bpf_jit_compile(struct bpf_prog *prog); bool bpf_jit_needs_zext(void); +u64 bpf_arch_uaddress_limit(void); bool bpf_helper_changes_pkt_data(void *func); static inline bool bpf_dump_raw_ok(const struct cred *cred) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 681070bf910b..7db8a815e835 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2321,6 +2321,15 @@ bool __weak bpf_helper_changes_pkt_data(void *func) return false; } +u64 __weak bpf_arch_uaddress_limit(void) +{ +#if defined(CONFIG_64BIT) && defined(CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE) + return TASK_SIZE; +#else + return 0; +#endif +} + /* Return TRUE if the JIT backend wants verifier to enable sub-register usage * analysis code and wants explicit zero extension inserted by verifier. * Otherwise, return FALSE. diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 18ab413ef2ba..a2a77348fa60 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -11464,6 +11464,35 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) continue; } + /* Make it impossible to de-reference a userspace address */ + if (BPF_CLASS(insn->code) == BPF_LDX && + BPF_MODE(insn->code) == BPF_PROBE_MEM) { + struct bpf_insn *patch = &insn_buf[0]; + u64 uaddress_limit = bpf_arch_uaddress_limit(); + + if (!uaddress_limit) + continue; + + *patch++ = BPF_MOV64_REG(BPF_REG_AX, insn->src_reg); + if (insn->off) + *patch++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_AX, insn->off); + *patch++ = BPF_ALU64_IMM(BPF_RSH, BPF_REG_AX, 32); + *patch++ = BPF_JMP_IMM(BPF_JLE, BPF_REG_AX, uaddress_limit >> 32, 2); + *patch++ = *insn; + *patch++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); + *patch++ = BPF_MOV64_IMM(insn->dst_reg, 0); + + cnt = patch - insn_buf; + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } + if (BPF_CLASS(insn->code) == BPF_LD && (BPF_MODE(insn->code) == BPF_ABS || BPF_MODE(insn->code) == BPF_IND)) { -- 2.34.1

2 1

[PATCH OLK-6.6] bpf: verifier: prevent userspace memory access
by Pu Lehui 26 Sep '24

26 Sep '24

From: Puranjay Mohan <puranjay12(a)gmail.com> mainline inclusion from mainline-v6.9-rc7 commit 66e13b615a0ce76b785d780ecc9776ba71983629 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IATK7C Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- With BPF_PROBE_MEM, BPF allows de-referencing an untrusted pointer. To thwart invalid memory accesses, the JITs add an exception table entry for all such accesses. But in case the src_reg + offset is a userspace address, the BPF program might read that memory if the user has mapped it. Make the verifier add guard instructions around such memory accesses and skip the load if the address falls into the userspace region. The JITs need to implement bpf_arch_uaddress_limit() to define where the userspace addresses end for that architecture or TASK_SIZE is taken as default. The implementation is as follows: REG_AX = SRC_REG if(offset) REG_AX += offset; REG_AX >>= 32; if (REG_AX <= (uaddress_limit >> 32)) DST_REG = 0; else DST_REG = *(size *)(SRC_REG + offset); Comparing just the upper 32 bits of the load address with the upper 32 bits of uaddress_limit implies that the values are being aligned down to a 4GB boundary before comparison. The above means that all loads with address <= uaddress_limit + 4GB are skipped. This is acceptable because there is a large hole (much larger than 4GB) between userspace and kernel space memory, therefore a correctly functioning BPF program should not access this 4GB memory above the userspace. Let's analyze what this patch does to the following fentry program dereferencing an untrusted pointer: SEC("fentry/tcp_v4_connect") int BPF_PROG(fentry_tcp_v4_connect, struct sock *sk) { *(volatile long *)sk; return 0; } BPF Program before | BPF Program after ------------------ | ----------------- 0: (79) r1 = *(u64 *)(r1 +0) 0: (79) r1 = *(u64 *)(r1 +0) ----------------------------------------------------------------------- 1: (79) r1 = *(u64 *)(r1 +0) --\ 1: (bf) r11 = r1 ----------------------------\ \ 2: (77) r11 >>= 32 2: (b7) r0 = 0 \ \ 3: (b5) if r11 <= 0x8000 goto pc+2 3: (95) exit \ \-> 4: (79) r1 = *(u64 *)(r1 +0) \ 5: (05) goto pc+1 \ 6: (b7) r1 = 0 \-------------------------------------- 7: (b7) r0 = 0 8: (95) exit As you can see from above, in the best case (off=0), 5 extra instructions are emitted. Now, we analyze the same program after it has gone through the JITs of ARM64 and RISC-V architectures. We follow the single load instruction that has the untrusted pointer and see what instrumentation has been added around it. x86-64 JIT ========== JIT's Instrumentation (upstream) --------------------- 0: nopl 0x0(%rax,%rax,1) 5: xchg %ax,%ax 7: push %rbp 8: mov %rsp,%rbp b: mov 0x0(%rdi),%rdi --------------------------------- f: movabs $0x800000000000,%r11 19: cmp %r11,%rdi 1c: jb 0x000000000000002a 1e: mov %rdi,%r11 21: add $0x0,%r11 28: jae 0x000000000000002e 2a: xor %edi,%edi 2c: jmp 0x0000000000000032 2e: mov 0x0(%rdi),%rdi --------------------------------- 32: xor %eax,%eax 34: leave 35: ret The x86-64 JIT already emits some instructions to protect against user memory access. This patch doesn't make any changes for the x86-64 JIT. ARM64 JIT ========= No Intrumentation Verifier's Instrumentation (upstream) (This patch) ----------------- -------------------------- 0: add x9, x30, #0x0 0: add x9, x30, #0x0 4: nop 4: nop 8: paciasp 8: paciasp c: stp x29, x30, [sp, #-16]! c: stp x29, x30, [sp, #-16]! 10: mov x29, sp 10: mov x29, sp 14: stp x19, x20, [sp, #-16]! 14: stp x19, x20, [sp, #-16]! 18: stp x21, x22, [sp, #-16]! 18: stp x21, x22, [sp, #-16]! 1c: stp x25, x26, [sp, #-16]! 1c: stp x25, x26, [sp, #-16]! 20: stp x27, x28, [sp, #-16]! 20: stp x27, x28, [sp, #-16]! 24: mov x25, sp 24: mov x25, sp 28: mov x26, #0x0 28: mov x26, #0x0 2c: sub x27, x25, #0x0 2c: sub x27, x25, #0x0 30: sub sp, sp, #0x0 30: sub sp, sp, #0x0 34: ldr x0, [x0] 34: ldr x0, [x0] -------------------------------------------------------------------------------- 38: ldr x0, [x0] ----------\ 38: add x9, x0, #0x0 -----------------------------------\\ 3c: lsr x9, x9, #32 3c: mov x7, #0x0 \\ 40: cmp x9, #0x10, lsl #12 40: mov sp, sp \\ 44: b.ls 0x0000000000000050 44: ldp x27, x28, [sp], #16 \\--> 48: ldr x0, [x0] 48: ldp x25, x26, [sp], #16 \ 4c: b 0x0000000000000054 4c: ldp x21, x22, [sp], #16 \ 50: mov x0, #0x0 50: ldp x19, x20, [sp], #16 \--------------------------------------- 54: ldp x29, x30, [sp], #16 54: mov x7, #0x0 58: add x0, x7, #0x0 58: mov sp, sp 5c: autiasp 5c: ldp x27, x28, [sp], #16 60: ret 60: ldp x25, x26, [sp], #16 64: nop 64: ldp x21, x22, [sp], #16 68: ldr x10, 0x0000000000000070 68: ldp x19, x20, [sp], #16 6c: br x10 6c: ldp x29, x30, [sp], #16 70: add x0, x7, #0x0 74: autiasp 78: ret 7c: nop 80: ldr x10, 0x0000000000000088 84: br x10 There are 6 extra instructions added in ARM64 in the best case. This will become 7 in the worst case (off != 0). RISC-V JIT (RISCV_ISA_C Disabled) ========== No Intrumentation Verifier's Instrumentation (upstream) (This patch) ----------------- -------------------------- 0: nop 0: nop 4: nop 4: nop 8: li a6, 33 8: li a6, 33 c: addi sp, sp, -16 c: addi sp, sp, -16 10: sd s0, 8(sp) 10: sd s0, 8(sp) 14: addi s0, sp, 16 14: addi s0, sp, 16 18: ld a0, 0(a0) 18: ld a0, 0(a0) --------------------------------------------------------------- 1c: ld a0, 0(a0) --\ 1c: mv t0, a0 --------------------------\ \ 20: srli t0, t0, 32 20: li a5, 0 \ \ 24: lui t1, 4096 24: ld s0, 8(sp) \ \ 28: sext.w t1, t1 28: addi sp, sp, 16 \ \ 2c: bgeu t1, t0, 12 2c: sext.w a0, a5 \ \--> 30: ld a0, 0(a0) 30: ret \ 34: j 8 \ 38: li a0, 0 \------------------------------ 3c: li a5, 0 40: ld s0, 8(sp) 44: addi sp, sp, 16 48: sext.w a0, a5 4c: ret There are 7 extra instructions added in RISC-V. Fixes: 800834285361 ("bpf, arm64: Add BPF exception tables") Reported-by: Breno Leitao <leitao(a)debian.org> Suggested-by: Alexei Starovoitov <ast(a)kernel.org> Acked-by: Ilya Leoshkevich <iii(a)linux.ibm.com> Signed-off-by: Puranjay Mohan <puranjay12(a)gmail.com> Link: https://lore.kernel.org/r/20240424100210.11982-2-puranjay@kernel.org Signed-off-by: Alexei Starovoitov <ast(a)kernel.org> Conflicts: arch/x86/net/bpf_jit_comp.c kernel/bpf/core.c kernel/bpf/verifier.c include/linux/filter.h [The conflicts were due to refactoring about do_misc_fixups] Signed-off-by: Pu Lehui <pulehui(a)huawei.com> --- arch/x86/net/bpf_jit_comp.c | 6 ++++++ include/linux/filter.h | 1 + kernel/bpf/core.c | 9 +++++++++ kernel/bpf/verifier.c | 30 ++++++++++++++++++++++++++++++ 4 files changed, 46 insertions(+) diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 878a4c6dd756..989b409f0cee 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -2968,3 +2968,9 @@ void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke, BUG_ON(ret < 0); } } + +/* x86-64 JIT emits its own code to filter user addresses so return 0 here */ +u64 bpf_arch_uaddress_limit(void) +{ + return 0; +} diff --git a/include/linux/filter.h b/include/linux/filter.h index 20b777ef5531..29f6a10b3acf 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -916,6 +916,7 @@ bool bpf_jit_needs_zext(void); bool bpf_jit_supports_subprog_tailcalls(void); bool bpf_jit_supports_kfunc_call(void); bool bpf_jit_supports_far_kfunc_call(void); +u64 bpf_arch_uaddress_limit(void); bool bpf_helper_changes_pkt_data(void *func); static inline bool bpf_dump_raw_ok(const struct cred *cred) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index d568244f5ae8..caea5f14ac99 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2906,6 +2906,15 @@ bool __weak bpf_jit_supports_far_kfunc_call(void) return false; } +u64 __weak bpf_arch_uaddress_limit(void) +{ +#if defined(CONFIG_64BIT) && defined(CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE) + return TASK_SIZE; +#else + return 0; +#endif +} + /* To execute LD_ABS/LD_IND instructions __bpf_prog_run() may call * skb_copy_bits(), so provide a weak definition of it for NET-less config. */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6a94f341587a..cbaa7dbf5f20 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -18942,6 +18942,36 @@ static int do_misc_fixups(struct bpf_verifier_env *env) continue; } + /* Make it impossible to de-reference a userspace address */ + if (BPF_CLASS(insn->code) == BPF_LDX && + (BPF_MODE(insn->code) == BPF_PROBE_MEM || + BPF_MODE(insn->code) == BPF_PROBE_MEMSX)) { + struct bpf_insn *patch = &insn_buf[0]; + u64 uaddress_limit = bpf_arch_uaddress_limit(); + + if (!uaddress_limit) + continue; + + *patch++ = BPF_MOV64_REG(BPF_REG_AX, insn->src_reg); + if (insn->off) + *patch++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_AX, insn->off); + *patch++ = BPF_ALU64_IMM(BPF_RSH, BPF_REG_AX, 32); + *patch++ = BPF_JMP_IMM(BPF_JLE, BPF_REG_AX, uaddress_limit >> 32, 2); + *patch++ = *insn; + *patch++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); + *patch++ = BPF_MOV64_IMM(insn->dst_reg, 0); + + cnt = patch - insn_buf; + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } + /* Implement LD_ABS and LD_IND with a rewrite, if supported by the program type. */ if (BPF_CLASS(insn->code) == BPF_LD && (BPF_MODE(insn->code) == BPF_ABS || -- 2.34.1

2 1

[PATCH OLK-6.6 0/2] fix CVE-2024-46771
by Zhang Changzhong 26 Sep '24

26 Sep '24

Kuniyuki Iwashima (2): can: bcm: Remove proc entry when dev is unregistered. can: bcm: Clear bo->bcm_proc_read after remove_proc_entry(). net/can/bcm.c | 6 ++++++ 1 file changed, 6 insertions(+) -- 2.9.5

2 3

[PATCH OLK-5.10 0/2] CVE-2024-46771
by Zhang Changzhong 26 Sep '24

26 Sep '24

Kuniyuki Iwashima (2): can: bcm: Remove proc entry when dev is unregistered. can: bcm: Clear bo->bcm_proc_read after remove_proc_entry(). net/can/bcm.c | 6 ++++++ 1 file changed, 6 insertions(+) -- 2.9.5

2 3

[PATCH openEuler-1.0-LTS 0/2] CVE-2024-46771
by Zhang Changzhong 26 Sep '24

26 Sep '24

Kuniyuki Iwashima (2): can: bcm: Remove proc entry when dev is unregistered. can: bcm: Clear bo->bcm_proc_read after remove_proc_entry(). net/can/bcm.c | 6 ++++++ 1 file changed, 6 insertions(+) -- 2.9.5

2 3

[PATCH openEuler-22.03-LTS-SP1 0/2] fix CVE-2024-46771
by Zhang Changzhong 26 Sep '24

26 Sep '24

Kuniyuki Iwashima (2): can: bcm: Remove proc entry when dev is unregistered. can: bcm: Clear bo->bcm_proc_read after remove_proc_entry(). net/can/bcm.c | 6 ++++++ 1 file changed, 6 insertions(+) -- 2.9.5

2 3

[PATCH OLK-6.6] userfaultfd: fix checks for huge PMDs
by Liu Shixin 26 Sep '24

26 Sep '24

From: Jann Horn <jannh(a)google.com> stable inclusion from stable-v6.6.51 commit 3c6b4bcf37845c9359aed926324bed66bdd2448d category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IARWOX CVE: CVE-2024-46787 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 71c186efc1b2cf1aeabfeff3b9bd5ac4c5ac14d8 upstream. Patch series "userfaultfd: fix races around pmd_trans_huge() check", v2. The pmd_trans_huge() code in mfill_atomic() is wrong in three different ways depending on kernel version: 1. The pmd_trans_huge() check is racy and can lead to a BUG_ON() (if you hit the right two race windows) - I've tested this in a kernel build with some extra mdelay() calls. See the commit message for a description of the race scenario. On older kernels (before 6.5), I think the same bug can even theoretically lead to accessing transhuge page contents as a page table if you hit the right 5 narrow race windows (I haven't tested this case). 2. As pointed out by Qi Zheng, pmd_trans_huge() is not sufficient for detecting PMDs that don't point to page tables. On older kernels (before 6.5), you'd just have to win a single fairly wide race to hit this. I've tested this on 6.1 stable by racing migration (with a mdelay() patched into try_to_migrate()) against UFFDIO_ZEROPAGE - on my x86 VM, that causes a kernel oops in ptlock_ptr(). 3. On newer kernels (>=6.5), for shmem mappings, khugepaged is allowed to yank page tables out from under us (though I haven't tested that), so I think the BUG_ON() checks in mfill_atomic() are just wrong. I decided to write two separate fixes for these (one fix for bugs 1+2, one fix for bug 3), so that the first fix can be backported to kernels affected by bugs 1+2. This patch (of 2): This fixes two issues. I discovered that the following race can occur: mfill_atomic other thread ============ ============ <zap PMD> pmdp_get_lockless() [reads none pmd] <bail if trans_huge> <if none:> <pagefault creates transhuge zeropage> __pte_alloc [no-op] <zap PMD> <bail if pmd_trans_huge(*dst_pmd)> BUG_ON(pmd_none(*dst_pmd)) I have experimentally verified this in a kernel with extra mdelay() calls; the BUG_ON(pmd_none(*dst_pmd)) triggers. On kernels newer than commit 0d940a9b270b ("mm/pgtable: allow pte_offset_map[_lock]() to fail"), this can't lead to anything worse than a BUG_ON(), since the page table access helpers are actually designed to deal with page tables concurrently disappearing; but on older kernels (<=6.4), I think we could probably theoretically race past the two BUG_ON() checks and end up treating a hugepage as a page table. The second issue is that, as Qi Zheng pointed out, there are other types of huge PMDs that pmd_trans_huge() can't catch: devmap PMDs and swap PMDs (in particular, migration PMDs). On <=6.4, this is worse than the first issue: If mfill_atomic() runs on a PMD that contains a migration entry (which just requires winning a single, fairly wide race), it will pass the PMD to pte_offset_map_lock(), which assumes that the PMD points to a page table. Breakage follows: First, the kernel tries to take the PTE lock (which will crash or maybe worse if there is no "struct page" for the address bits in the migration entry PMD - I think at least on X86 there usually is no corresponding "struct page" thanks to the PTE inversion mitigation, amd64 looks different). If that didn't crash, the kernel would next try to write a PTE into what it wrongly thinks is a page table. As part of fixing these issues, get rid of the check for pmd_trans_huge() before __pte_alloc() - that's redundant, we're going to have to check for that after the __pte_alloc() anyway. Backport note: pmdp_get_lockless() is pmd_read_atomic() in older kernels. Link: https://lkml.kernel.org/r/20240813-uffd-thp-flip-fix-v2-0-5efa61078a41@goog… Link: https://lkml.kernel.org/r/20240813-uffd-thp-flip-fix-v2-1-5efa61078a41@goog… Fixes: c1a4de99fada ("userfaultfd: mcopy_atomic|mfill_zeropage: UFFDIO_COPY|UFFDIO_ZEROPAGE preparation") Signed-off-by: Jann Horn <jannh(a)google.com> Acked-by: David Hildenbrand <david(a)redhat.com> Cc: Andrea Arcangeli <aarcange(a)redhat.com> Cc: Hugh Dickins <hughd(a)google.com> Cc: Jann Horn <jannh(a)google.com> Cc: Pavel Emelyanov <xemul(a)virtuozzo.com> Cc: Qi Zheng <zhengqi.arch(a)bytedance.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Liu Shixin <liushixin2(a)huawei.com> --- mm/userfaultfd.c | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 8c22dd4e5e15..b7562e6847b2 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -704,21 +704,23 @@ static __always_inline ssize_t mfill_atomic(struct mm_struct *dst_mm, } dst_pmdval = pmdp_get_lockless(dst_pmd); - /* - * If the dst_pmd is mapped as THP don't - * override it and just be strict. - */ - if (unlikely(pmd_trans_huge(dst_pmdval))) { - err = -EEXIST; - break; - } if (unlikely(pmd_none(dst_pmdval)) && unlikely(__pte_alloc(dst_mm, dst_pmd))) { err = -ENOMEM; break; } - /* If an huge pmd materialized from under us fail */ - if (unlikely(pmd_trans_huge(*dst_pmd))) { + dst_pmdval = pmdp_get_lockless(dst_pmd); + /* + * If the dst_pmd is THP don't override it and just be strict. + * (This includes the case where the PMD used to be THP and + * changed back to none after __pte_alloc().) + */ + if (unlikely(!pmd_present(dst_pmdval) || pmd_trans_huge(dst_pmdval) || + pmd_devmap(dst_pmdval))) { + err = -EEXIST; + break; + } + if (unlikely(pmd_bad(dst_pmdval))) { err = -EFAULT; break; } -- 2.34.1

2 1

2024

2023

2022

2021

2020

2019

Kernel