From 9999e48639b3cecb08ffb37358bcba3b48161b29 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Fri, 10 May 2024 08:50:17 +0000
Subject: [PATCH] add ax88772_rst
---
kernel/kernel/bpf/core.c | 1124 ++++++++++++++++++++++++++++++++++++++++-------------------
1 files changed, 761 insertions(+), 363 deletions(-)
diff --git a/kernel/kernel/bpf/core.c b/kernel/kernel/bpf/core.c
index 02f8193..b22447c 100644
--- a/kernel/kernel/bpf/core.c
+++ b/kernel/kernel/bpf/core.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Linux Socket Filter - Kernel level socket filtering
*
@@ -12,29 +13,31 @@
* Alexei Starovoitov <ast@plumgrid.com>
* Daniel Borkmann <dborkman@redhat.com>
*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
* Andi Kleen - Fix a few bad bugs and races.
* Kris Katterjohn - Added many additional checks in bpf_check_classic()
*/
+#include <uapi/linux/btf.h>
#include <linux/filter.h>
#include <linux/skbuff.h>
#include <linux/vmalloc.h>
#include <linux/random.h>
#include <linux/moduleloader.h>
#include <linux/bpf.h>
-#include <linux/frame.h>
+#include <linux/btf.h>
+#include <linux/objtool.h>
#include <linux/rbtree_latch.h>
#include <linux/kallsyms.h>
#include <linux/rcupdate.h>
#include <linux/perf_event.h>
+#include <linux/extable.h>
+#include <linux/log2.h>
+#include <linux/nospec.h>
#include <asm/barrier.h>
#include <asm/unaligned.h>
+
+#include <trace/hooks/memory.h>
/* Registers */
#define BPF_R0 regs[BPF_REG_0]
@@ -66,25 +69,27 @@
{
u8 *ptr = NULL;
- if (k >= SKF_NET_OFF)
+ if (k >= SKF_NET_OFF) {
ptr = skb_network_header(skb) + k - SKF_NET_OFF;
- else if (k >= SKF_LL_OFF)
+ } else if (k >= SKF_LL_OFF) {
+ if (unlikely(!skb_mac_header_was_set(skb)))
+ return NULL;
ptr = skb_mac_header(skb) + k - SKF_LL_OFF;
-
+ }
if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb))
return ptr;
return NULL;
}
-struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags)
+struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flags)
{
gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
struct bpf_prog_aux *aux;
struct bpf_prog *fp;
size = round_up(size, PAGE_SIZE);
- fp = __vmalloc(size, gfp_flags, PAGE_KERNEL);
+ fp = __vmalloc(size, gfp_flags);
if (fp == NULL)
return NULL;
@@ -99,11 +104,124 @@
fp->aux->prog = fp;
fp->jit_requested = ebpf_jit_enabled();
- INIT_LIST_HEAD_RCU(&fp->aux->ksym_lnode);
+ INIT_LIST_HEAD_RCU(&fp->aux->ksym.lnode);
+ mutex_init(&fp->aux->used_maps_mutex);
+ mutex_init(&fp->aux->dst_mutex);
return fp;
}
+
+struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags)
+{
+ gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
+ struct bpf_prog *prog;
+ int cpu;
+
+ prog = bpf_prog_alloc_no_stats(size, gfp_extra_flags);
+ if (!prog)
+ return NULL;
+
+ prog->aux->stats = alloc_percpu_gfp(struct bpf_prog_stats, gfp_flags);
+ if (!prog->aux->stats) {
+ kfree(prog->aux);
+ vfree(prog);
+ return NULL;
+ }
+
+ for_each_possible_cpu(cpu) {
+ struct bpf_prog_stats *pstats;
+
+ pstats = per_cpu_ptr(prog->aux->stats, cpu);
+ u64_stats_init(&pstats->syncp);
+ }
+ return prog;
+}
EXPORT_SYMBOL_GPL(bpf_prog_alloc);
+
+int bpf_prog_alloc_jited_linfo(struct bpf_prog *prog)
+{
+ if (!prog->aux->nr_linfo || !prog->jit_requested)
+ return 0;
+
+ prog->aux->jited_linfo = kcalloc(prog->aux->nr_linfo,
+ sizeof(*prog->aux->jited_linfo),
+ GFP_KERNEL | __GFP_NOWARN);
+ if (!prog->aux->jited_linfo)
+ return -ENOMEM;
+
+ return 0;
+}
+
+void bpf_prog_free_jited_linfo(struct bpf_prog *prog)
+{
+ kfree(prog->aux->jited_linfo);
+ prog->aux->jited_linfo = NULL;
+}
+
+void bpf_prog_free_unused_jited_linfo(struct bpf_prog *prog)
+{
+ if (prog->aux->jited_linfo && !prog->aux->jited_linfo[0])
+ bpf_prog_free_jited_linfo(prog);
+}
+
+/* The jit engine is responsible to provide an array
+ * for insn_off to the jited_off mapping (insn_to_jit_off).
+ *
+ * The idx to this array is the insn_off. Hence, the insn_off
+ * here is relative to the prog itself instead of the main prog.
+ * This array has one entry for each xlated bpf insn.
+ *
+ * jited_off is the byte off to the last byte of the jited insn.
+ *
+ * Hence, with
+ * insn_start:
+ * The first bpf insn off of the prog. The insn off
+ * here is relative to the main prog.
+ * e.g. if prog is a subprog, insn_start > 0
+ * linfo_idx:
+ * The prog's idx to prog->aux->linfo and jited_linfo
+ *
+ * jited_linfo[linfo_idx] = prog->bpf_func
+ *
+ * For i > linfo_idx,
+ *
+ * jited_linfo[i] = prog->bpf_func +
+ * insn_to_jit_off[linfo[i].insn_off - insn_start - 1]
+ */
+void bpf_prog_fill_jited_linfo(struct bpf_prog *prog,
+ const u32 *insn_to_jit_off)
+{
+ u32 linfo_idx, insn_start, insn_end, nr_linfo, i;
+ const struct bpf_line_info *linfo;
+ void **jited_linfo;
+
+ if (!prog->aux->jited_linfo)
+ /* Userspace did not provide linfo */
+ return;
+
+ linfo_idx = prog->aux->linfo_idx;
+ linfo = &prog->aux->linfo[linfo_idx];
+ insn_start = linfo[0].insn_off;
+ insn_end = insn_start + prog->len;
+
+ jited_linfo = &prog->aux->jited_linfo[linfo_idx];
+ jited_linfo[0] = prog->bpf_func;
+
+ nr_linfo = prog->aux->nr_linfo - linfo_idx;
+
+ for (i = 1; i < nr_linfo && linfo[i].insn_off < insn_end; i++)
+ /* The verifier ensures that linfo[i].insn_off is
+ * strictly increasing
+ */
+ jited_linfo[i] = prog->bpf_func +
+ insn_to_jit_off[linfo[i].insn_off - insn_start - 1];
+}
+
+void bpf_prog_free_linfo(struct bpf_prog *prog)
+{
+ bpf_prog_free_jited_linfo(prog);
+ kvfree(prog->aux->linfo);
+}
struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
gfp_t gfp_extra_flags)
@@ -112,8 +230,6 @@
struct bpf_prog *fp;
u32 pages, delta;
int ret;
-
- BUG_ON(fp_old == NULL);
size = round_up(size, PAGE_SIZE);
pages = size / PAGE_SIZE;
@@ -125,7 +241,7 @@
if (ret)
return NULL;
- fp = __vmalloc(size, gfp_flags, PAGE_KERNEL);
+ fp = __vmalloc(size, gfp_flags);
if (fp == NULL) {
__bpf_prog_uncharge(fp_old->aux->user, delta);
} else {
@@ -145,16 +261,22 @@
void __bpf_prog_free(struct bpf_prog *fp)
{
- kfree(fp->aux);
+ if (fp->aux) {
+ mutex_destroy(&fp->aux->used_maps_mutex);
+ mutex_destroy(&fp->aux->dst_mutex);
+ free_percpu(fp->aux->stats);
+ kfree(fp->aux->poke_tab);
+ kfree(fp->aux);
+ }
vfree(fp);
}
int bpf_prog_calc_tag(struct bpf_prog *fp)
{
- const u32 bits_offset = SHA_MESSAGE_BYTES - sizeof(__be64);
+ const u32 bits_offset = SHA1_BLOCK_SIZE - sizeof(__be64);
u32 raw_size = bpf_prog_tag_scratch_size(fp);
- u32 digest[SHA_DIGEST_WORDS];
- u32 ws[SHA_WORKSPACE_WORDS];
+ u32 digest[SHA1_DIGEST_WORDS];
+ u32 ws[SHA1_WORKSPACE_WORDS];
u32 i, bsize, psize, blocks;
struct bpf_insn *dst;
bool was_ld_map;
@@ -166,7 +288,7 @@
if (!raw)
return -ENOMEM;
- sha_init(digest);
+ sha1_init(digest);
memset(ws, 0, sizeof(ws));
/* We need to take out the map fd for the digest calculation
@@ -177,7 +299,8 @@
dst[i] = fp->insnsi[i];
if (!was_ld_map &&
dst[i].code == (BPF_LD | BPF_IMM | BPF_DW) &&
- dst[i].src_reg == BPF_PSEUDO_MAP_FD) {
+ (dst[i].src_reg == BPF_PSEUDO_MAP_FD ||
+ dst[i].src_reg == BPF_PSEUDO_MAP_VALUE)) {
was_ld_map = true;
dst[i].imm = 0;
} else if (was_ld_map &&
@@ -196,8 +319,8 @@
memset(&raw[psize], 0, raw_size - psize);
raw[psize++] = 0x80;
- bsize = round_up(psize, SHA_MESSAGE_BYTES);
- blocks = bsize / SHA_MESSAGE_BYTES;
+ bsize = round_up(psize, SHA1_BLOCK_SIZE);
+ blocks = bsize / SHA1_BLOCK_SIZE;
todo = raw;
if (bsize - psize >= sizeof(__be64)) {
bits = (__be64 *)(todo + bsize - sizeof(__be64));
@@ -208,12 +331,12 @@
*bits = cpu_to_be64((psize - 1) << 3);
while (blocks--) {
- sha_transform(digest, todo, ws);
- todo += SHA_MESSAGE_BYTES;
+ sha1_transform(digest, todo, ws);
+ todo += SHA1_BLOCK_SIZE;
}
result = (__force __be32 *)digest;
- for (i = 0; i < SHA_DIGEST_WORDS; i++)
+ for (i = 0; i < SHA1_DIGEST_WORDS; i++)
result[i] = cpu_to_be32(digest[i]);
memcpy(fp->tag, result, sizeof(fp->tag));
@@ -221,15 +344,16 @@
return 0;
}
-static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, u32 delta,
- u32 curr, const bool probe_pass)
+static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, s32 end_old,
+ s32 end_new, s32 curr, const bool probe_pass)
{
const s64 imm_min = S32_MIN, imm_max = S32_MAX;
+ s32 delta = end_new - end_old;
s64 imm = insn->imm;
- if (curr < pos && curr + imm + 1 > pos)
+ if (curr < pos && curr + imm + 1 >= end_old)
imm += delta;
- else if (curr > pos + delta && curr + imm + 1 <= pos + delta)
+ else if (curr >= end_new && curr + imm + 1 < end_new)
imm -= delta;
if (imm < imm_min || imm > imm_max)
return -ERANGE;
@@ -238,15 +362,16 @@
return 0;
}
-static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, u32 delta,
- u32 curr, const bool probe_pass)
+static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old,
+ s32 end_new, s32 curr, const bool probe_pass)
{
const s32 off_min = S16_MIN, off_max = S16_MAX;
+ s32 delta = end_new - end_old;
s32 off = insn->off;
- if (curr < pos && curr + off + 1 > pos)
+ if (curr < pos && curr + off + 1 >= end_old)
off += delta;
- else if (curr > pos + delta && curr + off + 1 <= pos + delta)
+ else if (curr >= end_new && curr + off + 1 < end_new)
off -= delta;
if (off < off_min || off > off_max)
return -ERANGE;
@@ -255,10 +380,10 @@
return 0;
}
-static int bpf_adj_branches(struct bpf_prog *prog, u32 pos, u32 delta,
- const bool probe_pass)
+static int bpf_adj_branches(struct bpf_prog *prog, u32 pos, s32 end_old,
+ s32 end_new, const bool probe_pass)
{
- u32 i, insn_cnt = prog->len + (probe_pass ? delta : 0);
+ u32 i, insn_cnt = prog->len + (probe_pass ? end_new - end_old : 0);
struct bpf_insn *insn = prog->insnsi;
int ret = 0;
@@ -270,22 +395,23 @@
* do any other adjustments. Therefore skip the patchlet.
*/
if (probe_pass && i == pos) {
- i += delta + 1;
- insn++;
+ i = end_new;
+ insn = prog->insnsi + end_old;
}
code = insn->code;
- if (BPF_CLASS(code) != BPF_JMP ||
+ if ((BPF_CLASS(code) != BPF_JMP &&
+ BPF_CLASS(code) != BPF_JMP32) ||
BPF_OP(code) == BPF_EXIT)
continue;
/* Adjust offset of jmps if we cross patch boundaries. */
if (BPF_OP(code) == BPF_CALL) {
if (insn->src_reg != BPF_PSEUDO_CALL)
continue;
- ret = bpf_adj_delta_to_imm(insn, pos, delta, i,
- probe_pass);
+ ret = bpf_adj_delta_to_imm(insn, pos, end_old,
+ end_new, i, probe_pass);
} else {
- ret = bpf_adj_delta_to_off(insn, pos, delta, i,
- probe_pass);
+ ret = bpf_adj_delta_to_off(insn, pos, end_old,
+ end_new, i, probe_pass);
}
if (ret)
break;
@@ -294,12 +420,33 @@
return ret;
}
+static void bpf_adj_linfo(struct bpf_prog *prog, u32 off, u32 delta)
+{
+ struct bpf_line_info *linfo;
+ u32 i, nr_linfo;
+
+ nr_linfo = prog->aux->nr_linfo;
+ if (!nr_linfo || !delta)
+ return;
+
+ linfo = prog->aux->linfo;
+
+ for (i = 0; i < nr_linfo; i++)
+ if (off < linfo[i].insn_off)
+ break;
+
+ /* Push all off < linfo[i].insn_off by delta */
+ for (; i < nr_linfo; i++)
+ linfo[i].insn_off += delta;
+}
+
struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
const struct bpf_insn *patch, u32 len)
{
u32 insn_adj_cnt, insn_rest, insn_delta = len - 1;
const u32 cnt_max = S16_MAX;
struct bpf_prog *prog_adj;
+ int err;
/* Since our patchlet doesn't expand the image, we're done. */
if (insn_delta == 0) {
@@ -315,8 +462,8 @@
* we afterwards may not fail anymore.
*/
if (insn_adj_cnt > cnt_max &&
- bpf_adj_branches(prog, off, insn_delta, true))
- return NULL;
+ (err = bpf_adj_branches(prog, off, off + 1, off + len, true)))
+ return ERR_PTR(err);
/* Several new instructions need to be inserted. Make room
* for them. Likely, there's no need for a new allocation as
@@ -325,7 +472,7 @@
prog_adj = bpf_prog_realloc(prog, bpf_prog_size(insn_adj_cnt),
GFP_USER);
if (!prog_adj)
- return NULL;
+ return ERR_PTR(-ENOMEM);
prog_adj->len = insn_adj_cnt;
@@ -347,12 +494,26 @@
* the ship has sailed to reverse to the original state. An
* overflow cannot happen at this point.
*/
- BUG_ON(bpf_adj_branches(prog_adj, off, insn_delta, false));
+ BUG_ON(bpf_adj_branches(prog_adj, off, off + 1, off + len, false));
+
+ bpf_adj_linfo(prog_adj, off, insn_delta);
return prog_adj;
}
-void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp)
+int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt)
+{
+ /* Branch offsets can't overflow when program is shrinking, no need
+ * to call bpf_adj_branches(..., true) here
+ */
+ memmove(prog->insnsi + off, prog->insnsi + off + cnt,
+ sizeof(struct bpf_insn) * (prog->len - off - cnt));
+ prog->len -= cnt;
+
+ return WARN_ON_ONCE(bpf_adj_branches(prog, off, off + cnt, off, false));
+}
+
+static void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp)
{
int i;
@@ -368,29 +529,31 @@
#ifdef CONFIG_BPF_JIT
/* All BPF JIT sysctl knobs here. */
-int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_ALWAYS_ON);
+int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON);
+int bpf_jit_kallsyms __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON);
int bpf_jit_harden __read_mostly;
-int bpf_jit_kallsyms __read_mostly;
long bpf_jit_limit __read_mostly;
long bpf_jit_limit_max __read_mostly;
-static __always_inline void
-bpf_get_prog_addr_region(const struct bpf_prog *prog,
- unsigned long *symbol_start,
- unsigned long *symbol_end)
+static void
+bpf_prog_ksym_set_addr(struct bpf_prog *prog)
{
const struct bpf_binary_header *hdr = bpf_jit_binary_hdr(prog);
unsigned long addr = (unsigned long)hdr;
WARN_ON_ONCE(!bpf_prog_ebpf_jited(prog));
- *symbol_start = addr;
- *symbol_end = addr + hdr->pages * PAGE_SIZE;
+ prog->aux->ksym.start = (unsigned long) prog->bpf_func;
+ prog->aux->ksym.end = addr + hdr->pages * PAGE_SIZE;
}
-static void bpf_get_prog_name(const struct bpf_prog *prog, char *sym)
+static void
+bpf_prog_ksym_set_name(struct bpf_prog *prog)
{
+ char *sym = prog->aux->ksym.name;
const char *end = sym + KSYM_NAME_LEN;
+ const struct btf_type *type;
+ const char *func_name;
BUILD_BUG_ON(sizeof("bpf_prog_") +
sizeof(prog->tag) * 2 +
@@ -405,42 +568,43 @@
sym += snprintf(sym, KSYM_NAME_LEN, "bpf_prog_");
sym = bin2hex(sym, prog->tag, sizeof(prog->tag));
+
+ /* prog->aux->name will be ignored if full btf name is available */
+ if (prog->aux->func_info_cnt) {
+ type = btf_type_by_id(prog->aux->btf,
+ prog->aux->func_info[prog->aux->func_idx].type_id);
+ func_name = btf_name_by_offset(prog->aux->btf, type->name_off);
+ snprintf(sym, (size_t)(end - sym), "_%s", func_name);
+ return;
+ }
+
if (prog->aux->name[0])
snprintf(sym, (size_t)(end - sym), "_%s", prog->aux->name);
else
*sym = 0;
}
-static __always_inline unsigned long
-bpf_get_prog_addr_start(struct latch_tree_node *n)
+static unsigned long bpf_get_ksym_start(struct latch_tree_node *n)
{
- unsigned long symbol_start, symbol_end;
- const struct bpf_prog_aux *aux;
-
- aux = container_of(n, struct bpf_prog_aux, ksym_tnode);
- bpf_get_prog_addr_region(aux->prog, &symbol_start, &symbol_end);
-
- return symbol_start;
+ return container_of(n, struct bpf_ksym, tnode)->start;
}
static __always_inline bool bpf_tree_less(struct latch_tree_node *a,
struct latch_tree_node *b)
{
- return bpf_get_prog_addr_start(a) < bpf_get_prog_addr_start(b);
+ return bpf_get_ksym_start(a) < bpf_get_ksym_start(b);
}
static __always_inline int bpf_tree_comp(void *key, struct latch_tree_node *n)
{
unsigned long val = (unsigned long)key;
- unsigned long symbol_start, symbol_end;
- const struct bpf_prog_aux *aux;
+ const struct bpf_ksym *ksym;
- aux = container_of(n, struct bpf_prog_aux, ksym_tnode);
- bpf_get_prog_addr_region(aux->prog, &symbol_start, &symbol_end);
+ ksym = container_of(n, struct bpf_ksym, tnode);
- if (val < symbol_start)
+ if (val < ksym->start)
return -1;
- if (val >= symbol_end)
+ if (val >= ksym->end)
return 1;
return 0;
@@ -455,20 +619,29 @@
static LIST_HEAD(bpf_kallsyms);
static struct latch_tree_root bpf_tree __cacheline_aligned;
-static void bpf_prog_ksym_node_add(struct bpf_prog_aux *aux)
+void bpf_ksym_add(struct bpf_ksym *ksym)
{
- WARN_ON_ONCE(!list_empty(&aux->ksym_lnode));
- list_add_tail_rcu(&aux->ksym_lnode, &bpf_kallsyms);
- latch_tree_insert(&aux->ksym_tnode, &bpf_tree, &bpf_tree_ops);
+ spin_lock_bh(&bpf_lock);
+ WARN_ON_ONCE(!list_empty(&ksym->lnode));
+ list_add_tail_rcu(&ksym->lnode, &bpf_kallsyms);
+ latch_tree_insert(&ksym->tnode, &bpf_tree, &bpf_tree_ops);
+ spin_unlock_bh(&bpf_lock);
}
-static void bpf_prog_ksym_node_del(struct bpf_prog_aux *aux)
+static void __bpf_ksym_del(struct bpf_ksym *ksym)
{
- if (list_empty(&aux->ksym_lnode))
+ if (list_empty(&ksym->lnode))
return;
- latch_tree_erase(&aux->ksym_tnode, &bpf_tree, &bpf_tree_ops);
- list_del_rcu(&aux->ksym_lnode);
+ latch_tree_erase(&ksym->tnode, &bpf_tree, &bpf_tree_ops);
+ list_del_rcu(&ksym->lnode);
+}
+
+void bpf_ksym_del(struct bpf_ksym *ksym)
+{
+ spin_lock_bh(&bpf_lock);
+ __bpf_ksym_del(ksym);
+ spin_unlock_bh(&bpf_lock);
}
static bool bpf_prog_kallsyms_candidate(const struct bpf_prog *fp)
@@ -478,19 +651,21 @@
static bool bpf_prog_kallsyms_verify_off(const struct bpf_prog *fp)
{
- return list_empty(&fp->aux->ksym_lnode) ||
- fp->aux->ksym_lnode.prev == LIST_POISON2;
+ return list_empty(&fp->aux->ksym.lnode) ||
+ fp->aux->ksym.lnode.prev == LIST_POISON2;
}
void bpf_prog_kallsyms_add(struct bpf_prog *fp)
{
if (!bpf_prog_kallsyms_candidate(fp) ||
- !capable(CAP_SYS_ADMIN))
+ !bpf_capable())
return;
- spin_lock_bh(&bpf_lock);
- bpf_prog_ksym_node_add(fp->aux);
- spin_unlock_bh(&bpf_lock);
+ bpf_prog_ksym_set_addr(fp);
+ bpf_prog_ksym_set_name(fp);
+ fp->aux->ksym.prog = true;
+
+ bpf_ksym_add(&fp->aux->ksym);
}
void bpf_prog_kallsyms_del(struct bpf_prog *fp)
@@ -498,36 +673,30 @@
if (!bpf_prog_kallsyms_candidate(fp))
return;
- spin_lock_bh(&bpf_lock);
- bpf_prog_ksym_node_del(fp->aux);
- spin_unlock_bh(&bpf_lock);
+ bpf_ksym_del(&fp->aux->ksym);
}
-static struct bpf_prog *bpf_prog_kallsyms_find(unsigned long addr)
+static struct bpf_ksym *bpf_ksym_find(unsigned long addr)
{
struct latch_tree_node *n;
- if (!bpf_jit_kallsyms_enabled())
- return NULL;
-
n = latch_tree_find((void *)addr, &bpf_tree, &bpf_tree_ops);
- return n ?
- container_of(n, struct bpf_prog_aux, ksym_tnode)->prog :
- NULL;
+ return n ? container_of(n, struct bpf_ksym, tnode) : NULL;
}
const char *__bpf_address_lookup(unsigned long addr, unsigned long *size,
unsigned long *off, char *sym)
{
- unsigned long symbol_start, symbol_end;
- struct bpf_prog *prog;
+ struct bpf_ksym *ksym;
char *ret = NULL;
rcu_read_lock();
- prog = bpf_prog_kallsyms_find(addr);
- if (prog) {
- bpf_get_prog_addr_region(prog, &symbol_start, &symbol_end);
- bpf_get_prog_name(prog, sym);
+ ksym = bpf_ksym_find(addr);
+ if (ksym) {
+ unsigned long symbol_start = ksym->start;
+ unsigned long symbol_end = ksym->end;
+
+ strncpy(sym, ksym->name, KSYM_NAME_LEN);
ret = sym;
if (size)
@@ -545,17 +714,43 @@
bool ret;
rcu_read_lock();
- ret = bpf_prog_kallsyms_find(addr) != NULL;
+ ret = bpf_ksym_find(addr) != NULL;
rcu_read_unlock();
return ret;
}
+static struct bpf_prog *bpf_prog_ksym_find(unsigned long addr)
+{
+ struct bpf_ksym *ksym = bpf_ksym_find(addr);
+
+ return ksym && ksym->prog ?
+ container_of(ksym, struct bpf_prog_aux, ksym)->prog :
+ NULL;
+}
+
+const struct exception_table_entry *search_bpf_extables(unsigned long addr)
+{
+ const struct exception_table_entry *e = NULL;
+ struct bpf_prog *prog;
+
+ rcu_read_lock();
+ prog = bpf_prog_ksym_find(addr);
+ if (!prog)
+ goto out;
+ if (!prog->aux->num_exentries)
+ goto out;
+
+ e = search_extable(prog->aux->extable, prog->aux->num_exentries, addr);
+out:
+ rcu_read_unlock();
+ return e;
+}
+
int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
char *sym)
{
- unsigned long symbol_start, symbol_end;
- struct bpf_prog_aux *aux;
+ struct bpf_ksym *ksym;
unsigned int it = 0;
int ret = -ERANGE;
@@ -563,14 +758,13 @@
return ret;
rcu_read_lock();
- list_for_each_entry_rcu(aux, &bpf_kallsyms, ksym_lnode) {
+ list_for_each_entry_rcu(ksym, &bpf_kallsyms, lnode) {
if (it++ != symnum)
continue;
- bpf_get_prog_addr_region(aux->prog, &symbol_start, &symbol_end);
- bpf_get_prog_name(aux->prog, sym);
+ strncpy(sym, ksym->name, KSYM_NAME_LEN);
- *value = symbol_start;
+ *value = ksym->start;
*type = BPF_SYM_ELF_TYPE;
ret = 0;
@@ -579,6 +773,40 @@
rcu_read_unlock();
return ret;
+}
+
+int bpf_jit_add_poke_descriptor(struct bpf_prog *prog,
+ struct bpf_jit_poke_descriptor *poke)
+{
+ struct bpf_jit_poke_descriptor *tab = prog->aux->poke_tab;
+ static const u32 poke_tab_max = 1024;
+ u32 slot = prog->aux->size_poke_tab;
+ u32 size = slot + 1;
+
+ if (size > poke_tab_max)
+ return -ENOSPC;
+ if (poke->tailcall_target || poke->tailcall_target_stable ||
+ poke->tailcall_bypass || poke->adj_off || poke->bypass_addr)
+ return -EINVAL;
+
+ switch (poke->reason) {
+ case BPF_POKE_REASON_TAIL_CALL:
+ if (!poke->tail_call.map)
+ return -EINVAL;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ tab = krealloc(tab, size * sizeof(*poke), GFP_KERNEL);
+ if (!tab)
+ return -ENOMEM;
+
+ memcpy(&tab[slot], poke, sizeof(*poke));
+ prog->aux->size_poke_tab = size;
+ prog->aux->poke_tab = tab;
+
+ return slot;
}
static atomic_long_t bpf_jit_current;
@@ -600,17 +828,17 @@
{
/* Only used as heuristic here to derive limit. */
bpf_jit_limit_max = bpf_jit_alloc_exec_limit();
- bpf_jit_limit = min_t(u64, round_up(bpf_jit_limit_max >> 2,
+ bpf_jit_limit = min_t(u64, round_up(bpf_jit_limit_max >> 1,
PAGE_SIZE), LONG_MAX);
return 0;
}
pure_initcall(bpf_jit_charge_init);
-static int bpf_jit_charge_modmem(u32 pages)
+int bpf_jit_charge_modmem(u32 pages)
{
if (atomic_long_add_return(pages, &bpf_jit_current) >
(bpf_jit_limit >> PAGE_SHIFT)) {
- if (!capable(CAP_SYS_ADMIN)) {
+ if (!bpf_capable()) {
atomic_long_sub(pages, &bpf_jit_current);
return -EPERM;
}
@@ -619,18 +847,20 @@
return 0;
}
-static void bpf_jit_uncharge_modmem(u32 pages)
+void bpf_jit_uncharge_modmem(u32 pages)
{
atomic_long_sub(pages, &bpf_jit_current);
}
-#if IS_ENABLED(CONFIG_BPF_JIT) && IS_ENABLED(CONFIG_CFI_CLANG)
-bool __weak arch_bpf_jit_check_func(const struct bpf_prog *prog)
+void *__weak bpf_jit_alloc_exec(unsigned long size)
{
- return true;
+ return module_alloc(size);
}
-EXPORT_SYMBOL_GPL(arch_bpf_jit_check_func);
-#endif
+
+void __weak bpf_jit_free_exec(void *addr)
+{
+ module_memfree(addr);
+}
struct bpf_binary_header *
bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
@@ -639,6 +869,9 @@
{
struct bpf_binary_header *hdr;
u32 size, hole, start, pages;
+
+ WARN_ON_ONCE(!is_power_of_2(alignment) ||
+ alignment > BPF_IMAGE_ALIGNMENT);
/* Most of BPF filters are really small, but if some of them
* fill a page, allow at least 128 extra bytes to insert a
@@ -649,7 +882,7 @@
if (bpf_jit_charge_modmem(pages))
return NULL;
- hdr = module_alloc(size);
+ hdr = bpf_jit_alloc_exec(size);
if (!hdr) {
bpf_jit_uncharge_modmem(pages);
return NULL;
@@ -658,7 +891,6 @@
/* Fill space with illegal/arch-dep instructions. */
bpf_fill_ill_insns(hdr, size);
- bpf_jit_set_header_magic(hdr);
hdr->pages = pages;
hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)),
PAGE_SIZE - sizeof(*hdr));
@@ -674,7 +906,9 @@
{
u32 pages = hdr->pages;
- module_memfree(hdr);
+ trace_android_vh_set_memory_rw((unsigned long)hdr, pages);
+ trace_android_vh_set_memory_nx((unsigned long)hdr, pages);
+ bpf_jit_free_exec(hdr);
bpf_jit_uncharge_modmem(pages);
}
@@ -687,7 +921,6 @@
if (fp->jited) {
struct bpf_binary_header *hdr = bpf_jit_binary_hdr(fp);
- bpf_jit_binary_unlock_ro(hdr);
bpf_jit_binary_free(hdr);
WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(fp));
@@ -696,9 +929,44 @@
bpf_prog_unlock_free(fp);
}
+int bpf_jit_get_func_addr(const struct bpf_prog *prog,
+ const struct bpf_insn *insn, bool extra_pass,
+ u64 *func_addr, bool *func_addr_fixed)
+{
+ s16 off = insn->off;
+ s32 imm = insn->imm;
+ u8 *addr;
+
+ *func_addr_fixed = insn->src_reg != BPF_PSEUDO_CALL;
+ if (!*func_addr_fixed) {
+ /* Place-holder address till the last pass has collected
+ * all addresses for JITed subprograms in which case we
+ * can pick them up from prog->aux.
+ */
+ if (!extra_pass)
+ addr = NULL;
+ else if (prog->aux->func &&
+ off >= 0 && off < prog->aux->func_cnt)
+ addr = (u8 *)prog->aux->func[off]->bpf_func;
+ else
+ return -EINVAL;
+ } else {
+ /* Address of a BPF helper call. Since part of the core
+ * kernel, it's always at a fixed location. __bpf_call_base
+ * and the helper with imm relative to it are both in core
+ * kernel.
+ */
+ addr = (u8 *)__bpf_call_base + imm;
+ }
+
+ *func_addr = (unsigned long)addr;
+ return 0;
+}
+
static int bpf_jit_blind_insn(const struct bpf_insn *from,
const struct bpf_insn *aux,
- struct bpf_insn *to_buff)
+ struct bpf_insn *to_buff,
+ bool emit_zext)
{
struct bpf_insn *to = to_buff;
u32 imm_rnd = get_random_int();
@@ -717,6 +985,9 @@
* below.
*
* Constant blinding is only used by JITs, not in the interpreter.
+ * The interpreter uses AX in some occasions as a local temporary
+ * register e.g. in DIV or MOD instructions.
+ *
* In restricted circumstances, the verifier can also use the AX
* register for rewrites as long as they do not interfere with
* the above cases!
@@ -780,6 +1051,27 @@
*to++ = BPF_JMP_REG(from->code, from->dst_reg, BPF_REG_AX, off);
break;
+ case BPF_JMP32 | BPF_JEQ | BPF_K:
+ case BPF_JMP32 | BPF_JNE | BPF_K:
+ case BPF_JMP32 | BPF_JGT | BPF_K:
+ case BPF_JMP32 | BPF_JLT | BPF_K:
+ case BPF_JMP32 | BPF_JGE | BPF_K:
+ case BPF_JMP32 | BPF_JLE | BPF_K:
+ case BPF_JMP32 | BPF_JSGT | BPF_K:
+ case BPF_JMP32 | BPF_JSLT | BPF_K:
+ case BPF_JMP32 | BPF_JSGE | BPF_K:
+ case BPF_JMP32 | BPF_JSLE | BPF_K:
+ case BPF_JMP32 | BPF_JSET | BPF_K:
+ /* Accommodate for extra offset in case of a backjump. */
+ off = from->off;
+ if (off < 0)
+ off -= 2;
+ *to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
+ *to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
+ *to++ = BPF_JMP32_REG(from->code, from->dst_reg, BPF_REG_AX,
+ off);
+ break;
+
case BPF_LD | BPF_IMM | BPF_DW:
*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[1].imm);
*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
@@ -789,6 +1081,8 @@
case 0: /* Part 2 of BPF_LD | BPF_IMM | BPF_DW. */
*to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[0].imm);
*to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
+ if (emit_zext)
+ *to++ = BPF_ZEXT_REG(BPF_REG_AX);
*to++ = BPF_ALU64_REG(BPF_OR, aux[0].dst_reg, BPF_REG_AX);
break;
@@ -811,7 +1105,7 @@
gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
struct bpf_prog *fp;
- fp = __vmalloc(fp_other->pages * PAGE_SIZE, gfp_flags, PAGE_KERNEL);
+ fp = __vmalloc(fp_other->pages * PAGE_SIZE, gfp_flags);
if (fp != NULL) {
/* aux->prog still points to the fp_other one, so
* when promoting the clone to the real program,
@@ -872,18 +1166,19 @@
insn[1].code == 0)
memcpy(aux, insn, sizeof(aux));
- rewritten = bpf_jit_blind_insn(insn, aux, insn_buff);
+ rewritten = bpf_jit_blind_insn(insn, aux, insn_buff,
+ clone->aux->verifier_zext);
if (!rewritten)
continue;
tmp = bpf_patch_insn_single(clone, i, insn_buff, rewritten);
- if (!tmp) {
+ if (IS_ERR(tmp)) {
/* Patching may have repointed aux->prog during
* realloc from the original one, so we need to
* fix it up here on error.
*/
bpf_jit_prog_release_other(prog, clone);
- return ERR_PTR(-ENOMEM);
+ return tmp;
}
clone = tmp;
@@ -916,32 +1211,34 @@
#define BPF_INSN_MAP(INSN_2, INSN_3) \
/* 32 bit ALU operations. */ \
/* Register based. */ \
- INSN_3(ALU, ADD, X), \
- INSN_3(ALU, SUB, X), \
- INSN_3(ALU, AND, X), \
- INSN_3(ALU, OR, X), \
- INSN_3(ALU, LSH, X), \
- INSN_3(ALU, RSH, X), \
- INSN_3(ALU, XOR, X), \
- INSN_3(ALU, MUL, X), \
- INSN_3(ALU, MOV, X), \
- INSN_3(ALU, DIV, X), \
- INSN_3(ALU, MOD, X), \
+ INSN_3(ALU, ADD, X), \
+ INSN_3(ALU, SUB, X), \
+ INSN_3(ALU, AND, X), \
+ INSN_3(ALU, OR, X), \
+ INSN_3(ALU, LSH, X), \
+ INSN_3(ALU, RSH, X), \
+ INSN_3(ALU, XOR, X), \
+ INSN_3(ALU, MUL, X), \
+ INSN_3(ALU, MOV, X), \
+ INSN_3(ALU, ARSH, X), \
+ INSN_3(ALU, DIV, X), \
+ INSN_3(ALU, MOD, X), \
INSN_2(ALU, NEG), \
INSN_3(ALU, END, TO_BE), \
INSN_3(ALU, END, TO_LE), \
/* Immediate based. */ \
- INSN_3(ALU, ADD, K), \
- INSN_3(ALU, SUB, K), \
- INSN_3(ALU, AND, K), \
- INSN_3(ALU, OR, K), \
- INSN_3(ALU, LSH, K), \
- INSN_3(ALU, RSH, K), \
- INSN_3(ALU, XOR, K), \
- INSN_3(ALU, MUL, K), \
- INSN_3(ALU, MOV, K), \
- INSN_3(ALU, DIV, K), \
- INSN_3(ALU, MOD, K), \
+ INSN_3(ALU, ADD, K), \
+ INSN_3(ALU, SUB, K), \
+ INSN_3(ALU, AND, K), \
+ INSN_3(ALU, OR, K), \
+ INSN_3(ALU, LSH, K), \
+ INSN_3(ALU, RSH, K), \
+ INSN_3(ALU, XOR, K), \
+ INSN_3(ALU, MUL, K), \
+ INSN_3(ALU, MOV, K), \
+ INSN_3(ALU, ARSH, K), \
+ INSN_3(ALU, DIV, K), \
+ INSN_3(ALU, MOD, K), \
/* 64 bit ALU operations. */ \
/* Register based. */ \
INSN_3(ALU64, ADD, X), \
@@ -974,6 +1271,31 @@
INSN_2(JMP, CALL), \
/* Exit instruction. */ \
INSN_2(JMP, EXIT), \
+ /* 32-bit Jump instructions. */ \
+ /* Register based. */ \
+ INSN_3(JMP32, JEQ, X), \
+ INSN_3(JMP32, JNE, X), \
+ INSN_3(JMP32, JGT, X), \
+ INSN_3(JMP32, JLT, X), \
+ INSN_3(JMP32, JGE, X), \
+ INSN_3(JMP32, JLE, X), \
+ INSN_3(JMP32, JSGT, X), \
+ INSN_3(JMP32, JSLT, X), \
+ INSN_3(JMP32, JSGE, X), \
+ INSN_3(JMP32, JSLE, X), \
+ INSN_3(JMP32, JSET, X), \
+ /* Immediate based. */ \
+ INSN_3(JMP32, JEQ, K), \
+ INSN_3(JMP32, JNE, K), \
+ INSN_3(JMP32, JGT, K), \
+ INSN_3(JMP32, JLT, K), \
+ INSN_3(JMP32, JGE, K), \
+ INSN_3(JMP32, JLE, K), \
+ INSN_3(JMP32, JSGT, K), \
+ INSN_3(JMP32, JSLT, K), \
+ INSN_3(JMP32, JSGE, K), \
+ INSN_3(JMP32, JSLE, K), \
+ INSN_3(JMP32, JSET, K), \
/* Jump instructions. */ \
/* Register based. */ \
INSN_3(JMP, JEQ, X), \
@@ -1044,10 +1366,17 @@
}
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
+u64 __weak bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr)
+{
+ memset(dst, 0, size);
+ return -EFAULT;
+}
+
/**
* __bpf_prog_run - run eBPF program on a given context
- * @ctx: is the data we are operating on
+ * @regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers
* @insn: is the array of eBPF instructions
+ * @stack: is the eBPF storage stack
*
* Decode and execute eBPF instructions.
*/
@@ -1055,7 +1384,7 @@
{
#define BPF_INSN_2_LBL(x, y) [BPF_##x | BPF_##y] = &&x##_##y
#define BPF_INSN_3_LBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = &&x##_##y##_##z
- static const void *jumptable[256] = {
+ static const void * const jumptable[256] __annotate_jump_table = {
[0 ... 255] = &&default_label,
/* Now overwrite non-defaults ... */
BPF_INSN_MAP(BPF_INSN_2_LBL, BPF_INSN_3_LBL),
@@ -1063,11 +1392,14 @@
[BPF_JMP | BPF_CALL_ARGS] = &&JMP_CALL_ARGS,
[BPF_JMP | BPF_TAIL_CALL] = &&JMP_TAIL_CALL,
[BPF_ST | BPF_NOSPEC] = &&ST_NOSPEC,
+ [BPF_LDX | BPF_PROBE_MEM | BPF_B] = &&LDX_PROBE_MEM_B,
+ [BPF_LDX | BPF_PROBE_MEM | BPF_H] = &&LDX_PROBE_MEM_H,
+ [BPF_LDX | BPF_PROBE_MEM | BPF_W] = &&LDX_PROBE_MEM_W,
+ [BPF_LDX | BPF_PROBE_MEM | BPF_DW] = &&LDX_PROBE_MEM_DW,
};
#undef BPF_INSN_3_LBL
#undef BPF_INSN_2_LBL
u32 tail_call_cnt = 0;
- u64 tmp;
#define CONT ({ insn++; goto select_insn; })
#define CONT_JMP ({ insn++; goto select_insn; })
@@ -1075,29 +1407,54 @@
select_insn:
goto *jumptable[insn->code];
- /* ALU */
-#define ALU(OPCODE, OP) \
- ALU64_##OPCODE##_X: \
- DST = DST OP SRC; \
- CONT; \
- ALU_##OPCODE##_X: \
- DST = (u32) DST OP (u32) SRC; \
- CONT; \
- ALU64_##OPCODE##_K: \
- DST = DST OP IMM; \
- CONT; \
- ALU_##OPCODE##_K: \
- DST = (u32) DST OP (u32) IMM; \
+ /* Explicitly mask the register-based shift amounts with 63 or 31
+ * to avoid undefined behavior. Normally this won't affect the
+ * generated code, for example, in case of native 64 bit archs such
+ * as x86-64 or arm64, the compiler is optimizing the AND away for
+ * the interpreter. In case of JITs, each of the JIT backends compiles
+ * the BPF shift operations to machine instructions which produce
+ * implementation-defined results in such a case; the resulting
+ * contents of the register may be arbitrary, but program behaviour
+ * as a whole remains defined. In other words, in case of JIT backends,
+ * the AND must /not/ be added to the emitted LSH/RSH/ARSH translation.
+ */
+ /* ALU (shifts) */
+#define SHT(OPCODE, OP) \
+ ALU64_##OPCODE##_X: \
+ DST = DST OP (SRC & 63); \
+ CONT; \
+ ALU_##OPCODE##_X: \
+ DST = (u32) DST OP ((u32) SRC & 31); \
+ CONT; \
+ ALU64_##OPCODE##_K: \
+ DST = DST OP IMM; \
+ CONT; \
+ ALU_##OPCODE##_K: \
+ DST = (u32) DST OP (u32) IMM; \
CONT;
-
+ /* ALU (rest) */
+#define ALU(OPCODE, OP) \
+ ALU64_##OPCODE##_X: \
+ DST = DST OP SRC; \
+ CONT; \
+ ALU_##OPCODE##_X: \
+ DST = (u32) DST OP (u32) SRC; \
+ CONT; \
+ ALU64_##OPCODE##_K: \
+ DST = DST OP IMM; \
+ CONT; \
+ ALU_##OPCODE##_K: \
+ DST = (u32) DST OP (u32) IMM; \
+ CONT;
ALU(ADD, +)
ALU(SUB, -)
ALU(AND, &)
ALU(OR, |)
- ALU(LSH, <<)
- ALU(RSH, >>)
ALU(XOR, ^)
ALU(MUL, *)
+ SHT(LSH, <<)
+ SHT(RSH, >>)
+#undef SHT
#undef ALU
ALU_NEG:
DST = (u32) -DST;
@@ -1121,43 +1478,49 @@
DST = (u64) (u32) insn[0].imm | ((u64) (u32) insn[1].imm) << 32;
insn++;
CONT;
+ ALU_ARSH_X:
+ DST = (u64) (u32) (((s32) DST) >> (SRC & 31));
+ CONT;
+ ALU_ARSH_K:
+ DST = (u64) (u32) (((s32) DST) >> IMM);
+ CONT;
ALU64_ARSH_X:
- (*(s64 *) &DST) >>= SRC;
+ (*(s64 *) &DST) >>= (SRC & 63);
CONT;
ALU64_ARSH_K:
(*(s64 *) &DST) >>= IMM;
CONT;
ALU64_MOD_X:
- div64_u64_rem(DST, SRC, &tmp);
- DST = tmp;
+ div64_u64_rem(DST, SRC, &AX);
+ DST = AX;
CONT;
ALU_MOD_X:
- tmp = (u32) DST;
- DST = do_div(tmp, (u32) SRC);
+ AX = (u32) DST;
+ DST = do_div(AX, (u32) SRC);
CONT;
ALU64_MOD_K:
- div64_u64_rem(DST, IMM, &tmp);
- DST = tmp;
+ div64_u64_rem(DST, IMM, &AX);
+ DST = AX;
CONT;
ALU_MOD_K:
- tmp = (u32) DST;
- DST = do_div(tmp, (u32) IMM);
+ AX = (u32) DST;
+ DST = do_div(AX, (u32) IMM);
CONT;
ALU64_DIV_X:
DST = div64_u64(DST, SRC);
CONT;
ALU_DIV_X:
- tmp = (u32) DST;
- do_div(tmp, (u32) SRC);
- DST = (u32) tmp;
+ AX = (u32) DST;
+ do_div(AX, (u32) SRC);
+ DST = (u32) AX;
CONT;
ALU64_DIV_K:
DST = div64_u64(DST, IMM);
CONT;
ALU_DIV_K:
- tmp = (u32) DST;
- do_div(tmp, (u32) IMM);
- DST = (u32) tmp;
+ AX = (u32) DST;
+ do_div(AX, (u32) IMM);
+ DST = (u32) AX;
CONT;
ALU_END_TO_BE:
switch (IMM) {
@@ -1222,7 +1585,7 @@
/* ARG1 at this point is guaranteed to point to CTX from
* the verifier side due to the fact that the tail call is
- * handeled like a helper, that is, bpf_tail_call_proto,
+ * handled like a helper, that is, bpf_tail_call_proto,
* where arg1_type is ARG_PTR_TO_CTX.
*/
insn = prog->insnsi;
@@ -1230,145 +1593,49 @@
out:
CONT;
}
- /* JMP */
JMP_JA:
insn += insn->off;
CONT;
- JMP_JEQ_X:
- if (DST == SRC) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JEQ_K:
- if (DST == IMM) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JNE_X:
- if (DST != SRC) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JNE_K:
- if (DST != IMM) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JGT_X:
- if (DST > SRC) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JGT_K:
- if (DST > IMM) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JLT_X:
- if (DST < SRC) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JLT_K:
- if (DST < IMM) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JGE_X:
- if (DST >= SRC) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JGE_K:
- if (DST >= IMM) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JLE_X:
- if (DST <= SRC) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JLE_K:
- if (DST <= IMM) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JSGT_X:
- if (((s64) DST) > ((s64) SRC)) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JSGT_K:
- if (((s64) DST) > ((s64) IMM)) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JSLT_X:
- if (((s64) DST) < ((s64) SRC)) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JSLT_K:
- if (((s64) DST) < ((s64) IMM)) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JSGE_X:
- if (((s64) DST) >= ((s64) SRC)) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JSGE_K:
- if (((s64) DST) >= ((s64) IMM)) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JSLE_X:
- if (((s64) DST) <= ((s64) SRC)) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JSLE_K:
- if (((s64) DST) <= ((s64) IMM)) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JSET_X:
- if (DST & SRC) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
- JMP_JSET_K:
- if (DST & IMM) {
- insn += insn->off;
- CONT_JMP;
- }
- CONT;
JMP_EXIT:
return BPF_R0;
-
+ /* JMP */
+#define COND_JMP(SIGN, OPCODE, CMP_OP) \
+ JMP_##OPCODE##_X: \
+ if ((SIGN##64) DST CMP_OP (SIGN##64) SRC) { \
+ insn += insn->off; \
+ CONT_JMP; \
+ } \
+ CONT; \
+ JMP32_##OPCODE##_X: \
+ if ((SIGN##32) DST CMP_OP (SIGN##32) SRC) { \
+ insn += insn->off; \
+ CONT_JMP; \
+ } \
+ CONT; \
+ JMP_##OPCODE##_K: \
+ if ((SIGN##64) DST CMP_OP (SIGN##64) IMM) { \
+ insn += insn->off; \
+ CONT_JMP; \
+ } \
+ CONT; \
+ JMP32_##OPCODE##_K: \
+ if ((SIGN##32) DST CMP_OP (SIGN##32) IMM) { \
+ insn += insn->off; \
+ CONT_JMP; \
+ } \
+ CONT;
+ COND_JMP(u, JEQ, ==)
+ COND_JMP(u, JNE, !=)
+ COND_JMP(u, JGT, >)
+ COND_JMP(u, JLT, <)
+ COND_JMP(u, JGE, >=)
+ COND_JMP(u, JLE, <=)
+ COND_JMP(u, JSET, &)
+ COND_JMP(s, JSGT, >)
+ COND_JMP(s, JSLT, <)
+ COND_JMP(s, JSGE, >=)
+ COND_JMP(s, JSLE, <=)
+#undef COND_JMP
/* ST, STX and LDX*/
ST_NOSPEC:
/* Speculation barrier for mitigating Speculative Store Bypass.
@@ -1380,9 +1647,7 @@
* reuse preexisting logic from Spectre v1 mitigation that
* happens to produce the required code on x86 for v4 as well.
*/
-#ifdef CONFIG_X86
barrier_nospec();
-#endif
CONT;
#define LDST(SIZEOP, SIZE) \
STX_MEM_##SIZEOP: \
@@ -1393,6 +1658,11 @@
CONT; \
LDX_MEM_##SIZEOP: \
DST = *(SIZE *)(unsigned long) (SRC + insn->off); \
+ CONT; \
+ LDX_PROBE_MEM_##SIZEOP: \
+ bpf_probe_read_kernel(&DST, sizeof(SIZE), \
+ (const void *)(long) (SRC + insn->off)); \
+ DST = *((SIZE *)&DST); \
CONT;
LDST(B, u8)
@@ -1400,6 +1670,7 @@
LDST(W, u32)
LDST(DW, u64)
#undef LDST
+
STX_XADD_W: /* lock xadd *(u32 *)(dst_reg + off16) += src_reg */
atomic_add((u32) SRC, (atomic_t *)(unsigned long)
(DST + insn->off));
@@ -1420,7 +1691,6 @@
BUG_ON(1);
return 0;
}
-STACK_FRAME_NON_STANDARD(___bpf_prog_run); /* jump table */
#define PROG_NAME(stack_size) __bpf_prog_run##stack_size
#define DEFINE_BPF_PROG_RUN(stack_size) \
@@ -1508,28 +1778,34 @@
bool bpf_prog_array_compatible(struct bpf_array *array,
const struct bpf_prog *fp)
{
+ bool ret;
+
if (fp->kprobe_override)
return false;
- if (!array->owner_prog_type) {
+ spin_lock(&array->aux->owner.lock);
+
+ if (!array->aux->owner.type) {
/* There's no owner yet where we could check for
* compatibility.
*/
- array->owner_prog_type = fp->type;
- array->owner_jited = fp->jited;
-
- return true;
+ array->aux->owner.type = fp->type;
+ array->aux->owner.jited = fp->jited;
+ ret = true;
+ } else {
+ ret = array->aux->owner.type == fp->type &&
+ array->aux->owner.jited == fp->jited;
}
-
- return array->owner_prog_type == fp->type &&
- array->owner_jited == fp->jited;
+ spin_unlock(&array->aux->owner.lock);
+ return ret;
}
static int bpf_check_tail_call(const struct bpf_prog *fp)
{
struct bpf_prog_aux *aux = fp->aux;
- int i;
+ int i, ret = 0;
+ mutex_lock(&aux->used_maps_mutex);
for (i = 0; i < aux->used_map_cnt; i++) {
struct bpf_map *map = aux->used_maps[i];
struct bpf_array *array;
@@ -1538,11 +1814,15 @@
continue;
array = container_of(map, struct bpf_array, map);
- if (!bpf_prog_array_compatible(array, fp))
- return -EINVAL;
+ if (!bpf_prog_array_compatible(array, fp)) {
+ ret = -EINVAL;
+ goto out;
+ }
}
- return 0;
+out:
+ mutex_unlock(&aux->used_maps_mutex);
+ return ret;
}
static void bpf_prog_select_func(struct bpf_prog *fp)
@@ -1581,13 +1861,20 @@
* be JITed, but falls back to the interpreter.
*/
if (!bpf_prog_is_dev_bound(fp->aux)) {
+ *err = bpf_prog_alloc_jited_linfo(fp);
+ if (*err)
+ return fp;
+
fp = bpf_int_jit_compile(fp);
-#ifdef CONFIG_BPF_JIT_ALWAYS_ON
if (!fp->jited) {
+ bpf_prog_free_jited_linfo(fp);
+#ifdef CONFIG_BPF_JIT_ALWAYS_ON
*err = -ENOTSUPP;
return fp;
- }
#endif
+ } else {
+ bpf_prog_free_unused_jited_linfo(fp);
+ }
} else {
*err = bpf_prog_offload_compile(fp);
if (*err)
@@ -1646,38 +1933,42 @@
return &empty_prog_array.hdr;
}
-void bpf_prog_array_free(struct bpf_prog_array __rcu *progs)
+void bpf_prog_array_free(struct bpf_prog_array *progs)
{
- if (!progs ||
- progs == (struct bpf_prog_array __rcu *)&empty_prog_array.hdr)
+ if (!progs || progs == &empty_prog_array.hdr)
return;
kfree_rcu(progs, rcu);
}
-int bpf_prog_array_length(struct bpf_prog_array __rcu *array)
+int bpf_prog_array_length(struct bpf_prog_array *array)
{
struct bpf_prog_array_item *item;
u32 cnt = 0;
- rcu_read_lock();
- item = rcu_dereference(array)->items;
- for (; item->prog; item++)
+ for (item = array->items; item->prog; item++)
if (item->prog != &dummy_bpf_prog.prog)
cnt++;
- rcu_read_unlock();
return cnt;
}
+bool bpf_prog_array_is_empty(struct bpf_prog_array *array)
+{
+ struct bpf_prog_array_item *item;
-static bool bpf_prog_array_copy_core(struct bpf_prog_array __rcu *array,
+ for (item = array->items; item->prog; item++)
+ if (item->prog != &dummy_bpf_prog.prog)
+ return false;
+ return true;
+}
+
+static bool bpf_prog_array_copy_core(struct bpf_prog_array *array,
u32 *prog_ids,
u32 request_cnt)
{
struct bpf_prog_array_item *item;
int i = 0;
- item = rcu_dereference_check(array, 1)->items;
- for (; item->prog; item++) {
+ for (item = array->items; item->prog; item++) {
if (item->prog == &dummy_bpf_prog.prog)
continue;
prog_ids[i] = item->prog->aux->id;
@@ -1690,7 +1981,7 @@
return !!(item->prog);
}
-int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *array,
+int bpf_prog_array_copy_to_user(struct bpf_prog_array *array,
__u32 __user *prog_ids, u32 cnt)
{
unsigned long err = 0;
@@ -1701,18 +1992,12 @@
* cnt = bpf_prog_array_length();
* if (cnt > 0)
* bpf_prog_array_copy_to_user(..., cnt);
- * so below kcalloc doesn't need extra cnt > 0 check, but
- * bpf_prog_array_length() releases rcu lock and
- * prog array could have been swapped with empty or larger array,
- * so always copy 'cnt' prog_ids to the user.
- * In a rare race the user will see zero prog_ids
+ * so below kcalloc doesn't need extra cnt > 0 check.
*/
ids = kcalloc(cnt, sizeof(u32), GFP_USER | __GFP_NOWARN);
if (!ids)
return -ENOMEM;
- rcu_read_lock();
nospc = bpf_prog_array_copy_core(array, ids, cnt);
- rcu_read_unlock();
err = copy_to_user(prog_ids, ids, cnt * sizeof(u32));
kfree(ids);
if (err)
@@ -1722,19 +2007,74 @@
return 0;
}
-void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *array,
+void bpf_prog_array_delete_safe(struct bpf_prog_array *array,
struct bpf_prog *old_prog)
{
- struct bpf_prog_array_item *item = array->items;
+ struct bpf_prog_array_item *item;
- for (; item->prog; item++)
+ for (item = array->items; item->prog; item++)
if (item->prog == old_prog) {
WRITE_ONCE(item->prog, &dummy_bpf_prog.prog);
break;
}
}
-int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
+/**
+ * bpf_prog_array_delete_safe_at() - Replaces the program at the given
+ * index into the program array with
+ * a dummy no-op program.
+ * @array: a bpf_prog_array
+ * @index: the index of the program to replace
+ *
+ * Skips over dummy programs, by not counting them, when calculating
+ * the position of the program to replace.
+ *
+ * Return:
+ * * 0 - Success
+ * * -EINVAL - Invalid index value. Must be a non-negative integer.
+ * * -ENOENT - Index out of range
+ */
+int bpf_prog_array_delete_safe_at(struct bpf_prog_array *array, int index)
+{
+ return bpf_prog_array_update_at(array, index, &dummy_bpf_prog.prog);
+}
+
+/**
+ * bpf_prog_array_update_at() - Updates the program at the given index
+ * into the program array.
+ * @array: a bpf_prog_array
+ * @index: the index of the program to update
+ * @prog: the program to insert into the array
+ *
+ * Skips over dummy programs, by not counting them, when calculating
+ * the position of the program to update.
+ *
+ * Return:
+ * * 0 - Success
+ * * -EINVAL - Invalid index value. Must be a non-negative integer.
+ * * -ENOENT - Index out of range
+ */
+int bpf_prog_array_update_at(struct bpf_prog_array *array, int index,
+ struct bpf_prog *prog)
+{
+ struct bpf_prog_array_item *item;
+
+ if (unlikely(index < 0))
+ return -EINVAL;
+
+ for (item = array->items; item->prog; item++) {
+ if (item->prog == &dummy_bpf_prog.prog)
+ continue;
+ if (!index) {
+ WRITE_ONCE(item->prog, prog);
+ return 0;
+ }
+ index--;
+ }
+ return -ENOENT;
+}
+
+int bpf_prog_array_copy(struct bpf_prog_array *old_array,
struct bpf_prog *exclude_prog,
struct bpf_prog *include_prog,
struct bpf_prog_array **new_array)
@@ -1798,7 +2138,7 @@
return 0;
}
-int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array,
+int bpf_prog_array_copy_info(struct bpf_prog_array *array,
u32 *prog_ids, u32 request_cnt,
u32 *prog_cnt)
{
@@ -1818,18 +2158,41 @@
: 0;
}
+void __bpf_free_used_maps(struct bpf_prog_aux *aux,
+ struct bpf_map **used_maps, u32 len)
+{
+ struct bpf_map *map;
+ u32 i;
+
+ for (i = 0; i < len; i++) {
+ map = used_maps[i];
+ if (map->ops->map_poke_untrack)
+ map->ops->map_poke_untrack(map, aux);
+ bpf_map_put(map);
+ }
+}
+
+static void bpf_free_used_maps(struct bpf_prog_aux *aux)
+{
+ __bpf_free_used_maps(aux, aux->used_maps, aux->used_map_cnt);
+ kfree(aux->used_maps);
+}
+
static void bpf_prog_free_deferred(struct work_struct *work)
{
struct bpf_prog_aux *aux;
int i;
aux = container_of(work, struct bpf_prog_aux, work);
+ bpf_free_used_maps(aux);
if (bpf_prog_is_dev_bound(aux))
bpf_prog_offload_destroy(aux->prog);
#ifdef CONFIG_PERF_EVENTS
if (aux->prog->has_callchain_buf)
put_callchain_buffers();
#endif
+ if (aux->dst_trampoline)
+ bpf_trampoline_put(aux->dst_trampoline);
for (i = 0; i < aux->func_cnt; i++)
bpf_jit_free(aux->func[i]);
if (aux->func_cnt) {
@@ -1845,6 +2208,8 @@
{
struct bpf_prog_aux *aux = fp->aux;
+ if (aux->dst_prog)
+ bpf_prog_put(aux->dst_prog);
INIT_WORK(&aux->work, bpf_prog_free_deferred);
schedule_work(&aux->work);
}
@@ -1876,10 +2241,21 @@
return res;
}
+BPF_CALL_0(bpf_get_raw_cpu_id)
+{
+ return raw_smp_processor_id();
+}
+
/* Weak definitions of helper functions in case we don't have bpf syscall. */
const struct bpf_func_proto bpf_map_lookup_elem_proto __weak;
const struct bpf_func_proto bpf_map_update_elem_proto __weak;
const struct bpf_func_proto bpf_map_delete_elem_proto __weak;
+const struct bpf_func_proto bpf_map_push_elem_proto __weak;
+const struct bpf_func_proto bpf_map_pop_elem_proto __weak;
+const struct bpf_func_proto bpf_map_peek_elem_proto __weak;
+const struct bpf_func_proto bpf_spin_lock_proto __weak;
+const struct bpf_func_proto bpf_spin_unlock_proto __weak;
+const struct bpf_func_proto bpf_jiffies64_proto __weak;
const struct bpf_func_proto bpf_get_prandom_u32_proto __weak;
const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak;
@@ -1890,10 +2266,12 @@
const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak;
const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak;
const struct bpf_func_proto bpf_get_current_comm_proto __weak;
-const struct bpf_func_proto bpf_sock_map_update_proto __weak;
-const struct bpf_func_proto bpf_sock_hash_update_proto __weak;
const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak;
+const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto __weak;
const struct bpf_func_proto bpf_get_local_storage_proto __weak;
+const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto __weak;
+const struct bpf_func_proto bpf_snprintf_btf_proto __weak;
+const struct bpf_func_proto bpf_seq_printf_btf_proto __weak;
const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
{
@@ -1939,6 +2317,15 @@
return false;
}
+/* 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.
+ */
+bool __weak bpf_jit_needs_zext(void)
+{
+ return false;
+}
+
/* 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.
*/
@@ -1948,8 +2335,19 @@
return -EFAULT;
}
+int __weak bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
+ void *addr1, void *addr2)
+{
+ return -ENOTSUPP;
+}
+
+DEFINE_STATIC_KEY_FALSE(bpf_stats_enabled_key);
+EXPORT_SYMBOL(bpf_stats_enabled_key);
+
/* All definitions of tracepoints related to BPF. */
+#undef TRACE_INCLUDE_PATH
#define CREATE_TRACE_POINTS
#include <linux/bpf_trace.h>
EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_exception);
+EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_bulk_tx);
--
Gitblit v1.6.2